diff options
533 files changed, 18144 insertions, 4035 deletions
diff --git a/.gitignore b/.gitignore index 7902adf4f7f1..38b7ab9e7dc4 100644 --- a/.gitignore +++ b/.gitignore @@ -24,6 +24,7 @@ *.dwo *.elf *.gcno +*.gcda *.gz *.i *.ko diff --git a/Documentation/dev-tools/gcov.rst b/Documentation/dev-tools/gcov.rst index 5fce2b06f229..dbd26b02ff3c 100644 --- a/Documentation/dev-tools/gcov.rst +++ b/Documentation/dev-tools/gcov.rst @@ -75,6 +75,17 @@ Only files which are linked to the main kernel image or are compiled as kernel modules are supported by this mechanism. +Module specific configs +----------------------- + +Gcov kernel configs for specific modules are described below: + +CONFIG_GCOV_PROFILE_RDS: + Enables GCOV profiling on RDS for checking which functions or + lines are executed. This config is used by the rds selftest to + generate coverage reports. If left unset the report is omitted. + + Files ----- diff --git a/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml b/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml index f197d9b516bb..97dd1a7c5ed2 100644 --- a/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml +++ b/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml @@ -17,6 +17,7 @@ properties: compatible: oneOf: - enum: + - fsl,imx95-flexcan - fsl,imx93-flexcan - fsl,imx8qm-flexcan - fsl,imx8mp-flexcan @@ -39,9 +40,6 @@ properties: - fsl,imx6sx-flexcan - const: fsl,imx6q-flexcan - items: - - const: fsl,imx95-flexcan - - const: fsl,imx93-flexcan - - items: - enum: - fsl,ls1028ar1-flexcan - const: fsl,lx2160ar1-flexcan @@ -80,6 +78,10 @@ properties: node then controller is assumed to be little endian. If this property is present then controller is assumed to be big endian. + can-transceiver: + $ref: can-transceiver.yaml# + unevaluatedProperties: false + fsl,stop-mode: description: | Register bits of stop mode control. diff --git a/Documentation/devicetree/bindings/net/dsa/mediatek,mt7530.yaml b/Documentation/devicetree/bindings/net/dsa/mediatek,mt7530.yaml index 7e405ad96eb2..ea979bcae1d6 100644 --- a/Documentation/devicetree/bindings/net/dsa/mediatek,mt7530.yaml +++ b/Documentation/devicetree/bindings/net/dsa/mediatek,mt7530.yaml @@ -92,6 +92,10 @@ properties: Built-in switch of the MT7988 SoC const: mediatek,mt7988-switch + - description: + Built-in switch of the Airoha EN7581 SoC + const: airoha,en7581-switch + reg: maxItems: 1 @@ -284,7 +288,9 @@ allOf: - if: properties: compatible: - const: mediatek,mt7988-switch + enum: + - mediatek,mt7988-switch + - airoha,en7581-switch then: $ref: "#/$defs/mt7530-dsa-port" properties: diff --git a/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml b/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml index 52acc15ebcbf..30c0c3e6f37a 100644 --- a/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml +++ b/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml @@ -22,7 +22,9 @@ properties: - microchip,ksz8794 - microchip,ksz8795 - microchip,ksz8863 + - microchip,ksz8864 # 4-port version of KSZ8895 family switch - microchip,ksz8873 + - microchip,ksz8895 # 5-port version of KSZ8895 family switch - microchip,ksz9477 - microchip,ksz9897 - microchip,ksz9896 @@ -51,6 +53,11 @@ properties: Set if the output SYNCLKO clock should be disabled. Do not mix with microchip,synclko-125. + microchip,pme-active-high: + $ref: /schemas/types.yaml#/definitions/flag + description: + Indicates if the PME pin polarity is active-high. + microchip,io-drive-strength-microamp: description: IO Pad Drive Strength diff --git a/Documentation/devicetree/bindings/net/dsa/vitesse,vsc73xx.yaml b/Documentation/devicetree/bindings/net/dsa/vitesse,vsc73xx.yaml index b99d7a694b70..51cf574249be 100644 --- a/Documentation/devicetree/bindings/net/dsa/vitesse,vsc73xx.yaml +++ b/Documentation/devicetree/bindings/net/dsa/vitesse,vsc73xx.yaml @@ -52,6 +52,25 @@ properties: allOf: - $ref: dsa.yaml#/$defs/ethernet-ports +patternProperties: + "^(ethernet-)?ports$": + additionalProperties: true + patternProperties: + "^(ethernet-)?port@6$": + allOf: + - if: + properties: + phy-mode: + contains: + enum: + - rgmii + then: + properties: + rx-internal-delay-ps: + $ref: "#/$defs/internal-delay-ps" + tx-internal-delay-ps: + $ref: "#/$defs/internal-delay-ps" + # This checks if reg is a chipselect so the device is on an SPI # bus, the if-clause will fail if reg is a tuple such as for a # platform device. @@ -67,6 +86,15 @@ required: - compatible - reg +$defs: + internal-delay-ps: + description: + Disable tunable delay lines using 0 ps, or enable them and select + the phase between 1400 ps and 2000 ps in increments of 300 ps. + default: 2000 + enum: + [0, 1400, 1700, 2000] + unevaluatedProperties: false examples: @@ -108,6 +136,8 @@ examples: reg = <6>; ethernet = <&gmac1>; phy-mode = "rgmii"; + rx-internal-delay-ps = <0>; + tx-internal-delay-ps = <0>; fixed-link { speed = <1000>; full-duplex; @@ -150,6 +180,8 @@ examples: ethernet-port@6 { reg = <6>; ethernet = <&enet0>; + rx-internal-delay-ps = <0>; + tx-internal-delay-ps = <0>; phy-mode = "rgmii"; fixed-link { speed = <1000>; diff --git a/Documentation/devicetree/bindings/net/fsl,qoriq-mc-dpmac.yaml b/Documentation/devicetree/bindings/net/fsl,qoriq-mc-dpmac.yaml index 42f9843d1868..be8a2163b73e 100644 --- a/Documentation/devicetree/bindings/net/fsl,qoriq-mc-dpmac.yaml +++ b/Documentation/devicetree/bindings/net/fsl,qoriq-mc-dpmac.yaml @@ -24,20 +24,12 @@ properties: maxItems: 1 description: The DPMAC number - phy-handle: true - - phy-connection-type: true - - phy-mode: true - pcs-handle: maxItems: 1 description: A reference to a node representing a PCS PHY device found on the internal MDIO bus. - managed: true - phys: description: A reference to the SerDes lane(s) maxItems: 1 @@ -45,7 +37,7 @@ properties: required: - reg -additionalProperties: false +unevaluatedProperties: false examples: - | diff --git a/Documentation/devicetree/bindings/net/mdio.yaml b/Documentation/devicetree/bindings/net/mdio.yaml index a266ade918ca..bed3987a8fbf 100644 --- a/Documentation/devicetree/bindings/net/mdio.yaml +++ b/Documentation/devicetree/bindings/net/mdio.yaml @@ -19,7 +19,7 @@ description: properties: $nodename: - pattern: "^mdio(@.*)?" + pattern: '^mdio(-(bus|external))?(@.+|-([0-9]+))?$' "#address-cells": const: 1 diff --git a/Documentation/devicetree/bindings/net/mediatek,net.yaml b/Documentation/devicetree/bindings/net/mediatek,net.yaml index 686b5c2fae40..9e02fd80af83 100644 --- a/Documentation/devicetree/bindings/net/mediatek,net.yaml +++ b/Documentation/devicetree/bindings/net/mediatek,net.yaml @@ -30,8 +30,13 @@ properties: reg: maxItems: 1 - clocks: true - clock-names: true + clocks: + minItems: 2 + maxItems: 24 + + clock-names: + minItems: 2 + maxItems: 24 interrupts: minItems: 1 @@ -127,6 +132,7 @@ allOf: then: properties: interrupts: + minItems: 3 maxItems: 3 clocks: @@ -183,6 +189,7 @@ allOf: then: properties: interrupts: + minItems: 3 maxItems: 3 clocks: @@ -222,6 +229,7 @@ allOf: then: properties: interrupts: + minItems: 3 maxItems: 3 clocks: diff --git a/Documentation/devicetree/bindings/net/pse-pd/ti,tps23881.yaml b/Documentation/devicetree/bindings/net/pse-pd/ti,tps23881.yaml index 6992d56832bf..d08abcb01211 100644 --- a/Documentation/devicetree/bindings/net/pse-pd/ti,tps23881.yaml +++ b/Documentation/devicetree/bindings/net/pse-pd/ti,tps23881.yaml @@ -23,6 +23,9 @@ properties: '#pse-cells': const: 1 + reset-gpios: + maxItems: 1 + channels: description: each set of 8 ports can be assigned to one physical channels or two for PoE4. This parameter describes the configuration diff --git a/Documentation/devicetree/bindings/net/renesas,etheravb.yaml b/Documentation/devicetree/bindings/net/renesas,etheravb.yaml index 21a92f179093..1e00ef5b3acd 100644 --- a/Documentation/devicetree/bindings/net/renesas,etheravb.yaml +++ b/Documentation/devicetree/bindings/net/renesas,etheravb.yaml @@ -62,15 +62,27 @@ properties: - renesas,r9a08g045-gbeth # RZ/G3S - const: renesas,rzg2l-gbeth # RZ/{G2L,G2UL,V2L} family - reg: true + reg: + minItems: 1 + items: + - description: MAC register block + - description: Stream buffer - interrupts: true + interrupts: + minItems: 1 + maxItems: 29 - interrupt-names: true + interrupt-names: + minItems: 1 + maxItems: 29 - clocks: true + clocks: + minItems: 1 + maxItems: 3 - clock-names: true + clock-names: + minItems: 1 + maxItems: 3 iommus: maxItems: 1 @@ -150,14 +162,11 @@ allOf: then: properties: reg: - items: - - description: MAC register block - - description: Stream buffer + minItems: 2 else: properties: reg: - items: - - description: MAC register block + maxItems: 1 - if: properties: diff --git a/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml b/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml index 6bbe96e35250..f8a576611d6c 100644 --- a/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml +++ b/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml @@ -25,6 +25,7 @@ select: - rockchip,rk3368-gmac - rockchip,rk3399-gmac - rockchip,rk3568-gmac + - rockchip,rk3576-gmac - rockchip,rk3588-gmac - rockchip,rv1108-gmac - rockchip,rv1126-gmac @@ -52,6 +53,7 @@ properties: - items: - enum: - rockchip,rk3568-gmac + - rockchip,rk3576-gmac - rockchip,rk3588-gmac - rockchip,rv1126-gmac - const: snps,dwmac-4.20a diff --git a/Documentation/devicetree/bindings/net/snps,dwmac.yaml b/Documentation/devicetree/bindings/net/snps,dwmac.yaml index 3eb65e63fdae..4e2ba1bf788c 100644 --- a/Documentation/devicetree/bindings/net/snps,dwmac.yaml +++ b/Documentation/devicetree/bindings/net/snps,dwmac.yaml @@ -80,6 +80,7 @@ properties: - rockchip,rk3328-gmac - rockchip,rk3366-gmac - rockchip,rk3368-gmac + - rockchip,rk3576-gmac - rockchip,rk3588-gmac - rockchip,rk3399-gmac - rockchip,rv1108-gmac diff --git a/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.yaml b/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.yaml index b0ebcef6801c..4eb63b303cff 100644 --- a/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.yaml +++ b/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.yaml @@ -41,13 +41,17 @@ properties: minItems: 1 maxItems: 4 - clock-names: true + clock-names: + minItems: 1 + maxItems: 4 resets: minItems: 1 maxItems: 2 - reset-names: true + reset-names: + minItems: 1 + maxItems: 2 socionext,syscon-phy-mode: $ref: /schemas/types.yaml#/definitions/phandle-array diff --git a/Documentation/devicetree/bindings/ptp/fsl,ptp.yaml b/Documentation/devicetree/bindings/ptp/fsl,ptp.yaml index 3bb8615e3e91..42ca895f3c4e 100644 --- a/Documentation/devicetree/bindings/ptp/fsl,ptp.yaml +++ b/Documentation/devicetree/bindings/ptp/fsl,ptp.yaml @@ -11,11 +11,14 @@ maintainers: properties: compatible: - enum: - - fsl,etsec-ptp - - fsl,fman-ptp-timer - - fsl,dpaa2-ptp - - fsl,enetc-ptp + oneOf: + - enum: + - fsl,etsec-ptp + - fsl,fman-ptp-timer + - fsl,dpaa2-ptp + - items: + - const: pci1957,ee02 + - const: fsl,enetc-ptp reg: maxItems: 1 @@ -123,6 +126,15 @@ required: - compatible - reg +allOf: + - if: + properties: + compatible: + contains: + const: fsl,enetc-ptp + then: + $ref: /schemas/pci/pci-device.yaml + additionalProperties: false examples: diff --git a/Documentation/devicetree/bindings/soc/ti/ti,pruss.yaml b/Documentation/devicetree/bindings/soc/ti/ti,pruss.yaml index c402cb2928e8..3cb1471cc6b6 100644 --- a/Documentation/devicetree/bindings/soc/ti/ti,pruss.yaml +++ b/Documentation/devicetree/bindings/soc/ti/ti,pruss.yaml @@ -278,6 +278,26 @@ patternProperties: additionalProperties: false + ^pa-stats@[a-f0-9]+$: + description: | + PA-STATS sub-module represented as a SysCon. PA_STATS is a set of + registers where different statistics related to ICSSG, are dumped by + ICSSG firmware. This syscon sub-module will help the device to + access/read/write those statistics. + + type: object + + additionalProperties: false + + properties: + compatible: + items: + - const: ti,pruss-pa-st + - const: syscon + + reg: + maxItems: 1 + interrupt-controller@[a-f0-9]+$: description: | PRUSS INTC Node. Each PRUSS has a single interrupt controller instance diff --git a/Documentation/driver-api/dpll.rst b/Documentation/driver-api/dpll.rst index ea8d16600e16..e6855cd37e85 100644 --- a/Documentation/driver-api/dpll.rst +++ b/Documentation/driver-api/dpll.rst @@ -214,6 +214,27 @@ offset values are fractional with 3-digit decimal places and shell be divided with ``DPLL_PIN_PHASE_OFFSET_DIVIDER`` to get integer part and modulo divided to get fractional part. +Embedded SYNC +============= + +Device may provide ability to use Embedded SYNC feature. It allows +to embed additional SYNC signal into the base frequency of a pin - a one +special pulse of base frequency signal every time SYNC signal pulse +happens. The user can configure the frequency of Embedded SYNC. +The Embedded SYNC capability is always related to a given base frequency +and HW capabilities. The user is provided a range of Embedded SYNC +frequencies supported, depending on current base frequency configured for +the pin. + + ========================================= ================================= + ``DPLL_A_PIN_ESYNC_FREQUENCY`` current Embedded SYNC frequency + ``DPLL_A_PIN_ESYNC_FREQUENCY_SUPPORTED`` nest available Embedded SYNC + frequency ranges + ``DPLL_A_PIN_FREQUENCY_MIN`` attr minimum value of frequency + ``DPLL_A_PIN_FREQUENCY_MAX`` attr maximum value of frequency + ``DPLL_A_PIN_ESYNC_PULSE`` pulse type of Embedded SYNC + ========================================= ================================= + Configuration commands group ============================ diff --git a/Documentation/netlink/specs/dpll.yaml b/Documentation/netlink/specs/dpll.yaml index 94132d30e0e0..f2894ca35de8 100644 --- a/Documentation/netlink/specs/dpll.yaml +++ b/Documentation/netlink/specs/dpll.yaml @@ -345,6 +345,26 @@ attribute-sets: Value is in PPM (parts per million). This may be implemented for example for pin of type PIN_TYPE_SYNCE_ETH_PORT. + - + name: esync-frequency + type: u64 + doc: | + Frequency of Embedded SYNC signal. If provided, the pin is configured + with a SYNC signal embedded into its base clock frequency. + - + name: esync-frequency-supported + type: nest + multi-attr: true + nested-attributes: frequency-range + doc: | + If provided a pin is capable of embedding a SYNC signal (within given + range) into its base frequency signal. + - + name: esync-pulse + type: u32 + doc: | + A ratio of high to low state of a SYNC signal pulse embedded + into base clock frequency. Value is in percents. - name: pin-parent-device subset-of: pin @@ -510,6 +530,9 @@ operations: - phase-adjust-max - phase-adjust - fractional-frequency-offset + - esync-frequency + - esync-frequency-supported + - esync-pulse dump: request: @@ -536,6 +559,7 @@ operations: - parent-device - parent-pin - phase-adjust + - esync-frequency - name: pin-create-ntf doc: Notification about pin appearing diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml index ea21fe135b97..6a050d755b9c 100644 --- a/Documentation/netlink/specs/ethtool.yaml +++ b/Documentation/netlink/specs/ethtool.yaml @@ -39,6 +39,11 @@ definitions: - ovld-detected - power-not-available - short-detected + - + name: phy-upstream-type + enum-name: + type: enum + entries: [ mac, phy ] attribute-sets: - @@ -54,6 +59,9 @@ attribute-sets: name: flags type: u32 enum: header-flags + - + name: phy-index + type: u32 - name: bitset-bit @@ -659,6 +667,9 @@ attribute-sets: - name: code type: u8 + - + name: src + type: u32 - name: cable-fault-length attributes: @@ -668,6 +679,9 @@ attribute-sets: - name: cm type: u32 + - + name: src + type: u32 - name: cable-nest attributes: @@ -1022,12 +1036,16 @@ attribute-sets: - name: indir type: binary + sub-type: u32 - name: hkey type: binary - name: input_xfrm type: u32 + - + name: start-context + type: u32 - name: plca attributes: @@ -1085,6 +1103,35 @@ attribute-sets: - name: total type: uint + - + name: phy + attributes: + - + name: header + type: nest + nested-attributes: header + - + name: index + type: u32 + - + name: drvname + type: string + - + name: name + type: string + - + name: upstream-type + type: u32 + enum: phy-upstream-type + - + name: upstream-index + type: u32 + - + name: upstream-sfp-name + type: string + - + name: downstream-sfp-name + type: string operations: enum-model: directional @@ -1749,12 +1796,12 @@ operations: attribute-set: rss - do: &rss-get-op + do: request: attributes: - header - context - reply: + reply: &rss-reply attributes: - header - context @@ -1762,6 +1809,12 @@ operations: - indir - hkey - input_xfrm + dump: + request: + attributes: + - header + - start-context + reply: *rss-reply - name: plca-get-cfg doc: Get PLCA params. @@ -1877,3 +1930,24 @@ operations: - status-msg - done - total + - + name: phy-get + doc: Get PHY devices attached to an interface + + attribute-set: phy + + do: &phy-get-op + request: + attributes: + - header + reply: + attributes: + - header + - index + - drvname + - name + - upstream-type + - upstream-index + - upstream-sfp-name + - downstream-sfp-name + dump: *phy-get-op diff --git a/Documentation/netlink/specs/rt_link.yaml b/Documentation/netlink/specs/rt_link.yaml index de08c12fd56f..0c4d5d40cae9 100644 --- a/Documentation/netlink/specs/rt_link.yaml +++ b/Documentation/netlink/specs/rt_link.yaml @@ -903,6 +903,22 @@ definitions: - cfm-config - cfm-status - mst + - + name: netkit-policy + type: enum + entries: + - + name: forward + value: 0 + - + name: blackhole + value: 2 + - + name: netkit-mode + type: enum + entries: + - name: l2 + - name: l3 attribute-sets: - @@ -2109,6 +2125,28 @@ attribute-sets: - name: id type: u32 + - + name: linkinfo-netkit-attrs + name-prefix: ifla-netkit- + attributes: + - + name: peer-info + type: binary + - + name: primary + type: u8 + - + name: policy + type: u32 + enum: netkit-policy + - + name: peer-policy + type: u32 + enum: netkit-policy + - + name: mode + type: u32 + enum: netkit-mode sub-messages: - @@ -2147,6 +2185,9 @@ sub-messages: - value: vrf attribute-set: linkinfo-vrf-attrs + - + value: netkit + attribute-set: linkinfo-netkit-attrs - name: linkinfo-member-data-msg formats: diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index d5f246aceb9f..ba90457b8b2d 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -57,6 +57,7 @@ Structure of this header is ``ETHTOOL_A_HEADER_DEV_INDEX`` u32 device ifindex ``ETHTOOL_A_HEADER_DEV_NAME`` string device name ``ETHTOOL_A_HEADER_FLAGS`` u32 flags common for all requests + ``ETHTOOL_A_HEADER_PHY_INDEX`` u32 phy device index ============================== ====== ============================= ``ETHTOOL_A_HEADER_DEV_INDEX`` and ``ETHTOOL_A_HEADER_DEV_NAME`` identify the @@ -81,6 +82,12 @@ the behaviour is backward compatible, i.e. requests from old clients not aware of the flag should be interpreted the way the client expects. A client must not set flags it does not understand. +``ETHTOOL_A_HEADER_PHY_INDEX`` identifies the Ethernet PHY the message relates to. +As there are numerous commands that are related to PHY configuration, and because +there may be more than one PHY on the link, the PHY index can be passed in the +request for the commands that needs it. It is, however, not mandatory, and if it +is not passed for commands that target a PHY, the net_device.phydev pointer +is used. Bit sets ======== @@ -934,18 +941,18 @@ Request contents: ==================================== ====== =========================== Kernel checks that requested ring sizes do not exceed limits reported by -driver. Driver may impose additional constraints and may not suspport all +driver. Driver may impose additional constraints and may not support all attributes. ``ETHTOOL_A_RINGS_CQE_SIZE`` specifies the completion queue event size. -Completion queue events(CQE) are the events posted by NIC to indicate the -completion status of a packet when the packet is sent(like send success or -error) or received(like pointers to packet fragments). The CQE size parameter +Completion queue events (CQE) are the events posted by NIC to indicate the +completion status of a packet when the packet is sent (like send success or +error) or received (like pointers to packet fragments). The CQE size parameter enables to modify the CQE size other than default size if NIC supports it. -A bigger CQE can have more receive buffer pointers inturn NIC can transfer -a bigger frame from wire. Based on the NIC hardware, the overall completion -queue size can be adjusted in the driver if CQE size is modified. +A bigger CQE can have more receive buffer pointers, and in turn the NIC can +transfer a bigger frame from wire. Based on the NIC hardware, the overall +completion queue size can be adjusted in the driver if CQE size is modified. CHANNELS_GET ============ @@ -989,7 +996,7 @@ Request contents: ===================================== ====== ========================== Kernel checks that requested channel counts do not exceed limits reported by -driver. Driver may impose additional constraints and may not suspport all +driver. Driver may impose additional constraints and may not support all attributes. @@ -1307,12 +1314,17 @@ information. +-+-+-----------------------------------------+--------+---------------------+ | | | ``ETHTOOL_A_CABLE_RESULTS_CODE`` | u8 | result code | +-+-+-----------------------------------------+--------+---------------------+ + | | | ``ETHTOOL_A_CABLE_RESULT_SRC`` | u32 | information source | + +-+-+-----------------------------------------+--------+---------------------+ | | ``ETHTOOL_A_CABLE_NEST_FAULT_LENGTH`` | nested | cable length | +-+-+-----------------------------------------+--------+---------------------+ | | | ``ETHTOOL_A_CABLE_FAULT_LENGTH_PAIR`` | u8 | pair number | +-+-+-----------------------------------------+--------+---------------------+ | | | ``ETHTOOL_A_CABLE_FAULT_LENGTH_CM`` | u32 | length in cm | +-+-+-----------------------------------------+--------+---------------------+ + | | | ``ETHTOOL_A_CABLE_FAULT_LENGTH_SRC`` | u32 | information source | + +-+-+-----------------------------------------+--------+---------------------+ + CABLE_TEST TDR ============== @@ -1866,10 +1878,18 @@ RSS context of an interface similar to ``ETHTOOL_GRSSH`` ioctl request. Request contents: -===================================== ====== ========================== +===================================== ====== ============================ ``ETHTOOL_A_RSS_HEADER`` nested request header ``ETHTOOL_A_RSS_CONTEXT`` u32 context number -===================================== ====== ========================== + ``ETHTOOL_A_RSS_START_CONTEXT`` u32 start context number (dumps) +===================================== ====== ============================ + +``ETHTOOL_A_RSS_CONTEXT`` specifies which RSS context number to query, +if not set context 0 (the main context) is queried. Dumps can be filtered +by device (only listing contexts of a given netdev). Filtering single +context number is not supported but ``ETHTOOL_A_RSS_START_CONTEXT`` +can be used to start dumping context from the given number (primarily +used to ignore context 0s and only dump additional contexts). Kernel response contents: @@ -1927,7 +1947,7 @@ When set, the optional ``ETHTOOL_A_PLCA_VERSION`` attribute indicates which standard and version the PLCA management interface complies to. When not set, the interface is vendor-specific and (possibly) supplied by the driver. The OPEN Alliance SIG specifies a standard register map for 10BASE-T1S PHYs -embedding the PLCA Reconcialiation Sublayer. See "10BASE-T1S PLCA Management +embedding the PLCA Reconciliation Sublayer. See "10BASE-T1S PLCA Management Registers" at https://www.opensig.org/about/specifications/. When set, the optional ``ETHTOOL_A_PLCA_ENABLED`` attribute indicates the @@ -1989,7 +2009,7 @@ Request contents: ``ETHTOOL_A_PLCA_ENABLED`` u8 PLCA Admin State ``ETHTOOL_A_PLCA_NODE_ID`` u8 PLCA unique local node ID ``ETHTOOL_A_PLCA_NODE_CNT`` u8 Number of PLCA nodes on the - netkork, including the + network, including the coordinator ``ETHTOOL_A_PLCA_TO_TMR`` u8 Transmit Opportunity Timer value in bit-times (BT) @@ -2176,6 +2196,49 @@ string. The ``ETHTOOL_A_MODULE_FW_FLASH_DONE`` and ``ETHTOOL_A_MODULE_FW_FLASH_TOTAL`` attributes encode the completed and total amount of work, respectively. +PHY_GET +======= + +Retrieve information about a given Ethernet PHY sitting on the link. The DO +operation returns all available information about dev->phydev. User can also +specify a PHY_INDEX, in which case the DO request returns information about that +specific PHY. + +As there can be more than one PHY, the DUMP operation can be used to list the PHYs +present on a given interface, by passing an interface index or name in +the dump request. + +For more information, refer to :ref:`phy_link_topology` + +Request contents: + + ==================================== ====== ========================== + ``ETHTOOL_A_PHY_HEADER`` nested request header + ==================================== ====== ========================== + +Kernel response contents: + + ===================================== ====== =============================== + ``ETHTOOL_A_PHY_HEADER`` nested request header + ``ETHTOOL_A_PHY_INDEX`` u32 the phy's unique index, that can + be used for phy-specific + requests + ``ETHTOOL_A_PHY_DRVNAME`` string the phy driver name + ``ETHTOOL_A_PHY_NAME`` string the phy device name + ``ETHTOOL_A_PHY_UPSTREAM_TYPE`` u32 the type of device this phy is + connected to + ``ETHTOOL_A_PHY_UPSTREAM_INDEX`` u32 the PHY index of the upstream + PHY + ``ETHTOOL_A_PHY_UPSTREAM_SFP_NAME`` string if this PHY is connected to + its parent PHY through an SFP + bus, the name of this sfp bus + ``ETHTOOL_A_PHY_DOWNSTREAM_SFP_NAME`` string if the phy controls an sfp bus, + the name of the sfp bus + ===================================== ====== =============================== + +When ``ETHTOOL_A_PHY_UPSTREAM_TYPE`` is PHY_UPSTREAM_PHY, the PHY's parent is +another PHY. + Request translation =================== @@ -2283,4 +2346,5 @@ are netlink only. n/a ``ETHTOOL_MSG_MM_GET`` n/a ``ETHTOOL_MSG_MM_SET`` n/a ``ETHTOOL_MSG_MODULE_FW_FLASH_ACT`` + n/a ``ETHTOOL_MSG_PHY_GET`` =================================== ===================================== diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst index d1af04b952f8..c71b87346178 100644 --- a/Documentation/networking/index.rst +++ b/Documentation/networking/index.rst @@ -91,6 +91,7 @@ Contents: operstates packet_mmap phonet + phy-link-topology pktgen plip ppp_generic diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index 3616389c8c2d..eacf8983e230 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -2362,6 +2362,20 @@ ra_honor_pio_life - BOOLEAN Default: 0 (disabled) +ra_honor_pio_pflag - BOOLEAN + The Prefix Information Option P-flag indicates the network can + allocate a unique IPv6 prefix per client using DHCPv6-PD. + This sysctl can be enabled when a userspace DHCPv6-PD client + is running to cause the P-flag to take effect: i.e. the + P-flag suppresses any effects of the A-flag within the same + PIO. For a given PIO, P=1 and A=1 is treated as A=0. + + - If disabled, the P-flag is ignored. + - If enabled, the P-flag will disable SLAAC autoconfiguration + for the given Prefix Information Option. + + Default: 0 (disabled) + accept_ra_rt_info_min_plen - INTEGER Minimum prefix length of Route Information in RA. diff --git a/Documentation/networking/l2tp.rst b/Documentation/networking/l2tp.rst index 8496b467dea4..e8cf8b3e60ac 100644 --- a/Documentation/networking/l2tp.rst +++ b/Documentation/networking/l2tp.rst @@ -638,9 +638,8 @@ Tunnels are identified by a unique tunnel id. The id is 16-bit for L2TPv2 and 32-bit for L2TPv3. Internally, the id is stored as a 32-bit value. -Tunnels are kept in a per-net list, indexed by tunnel id. The tunnel -id namespace is shared by L2TPv2 and L2TPv3. The tunnel context can be -derived from the socket's sk_user_data. +Tunnels are kept in a per-net list, indexed by tunnel id. The +tunnel id namespace is shared by L2TPv2 and L2TPv3. Handling tunnel socket close is perhaps the most tricky part of the L2TP implementation. If userspace closes a tunnel socket, the L2TP @@ -652,9 +651,7 @@ socket's encap_destroy handler is invoked, which L2TP uses to initiate its tunnel close actions. For L2TPIP sockets, the socket's close handler initiates the same tunnel close actions. All sessions are first closed. Each session drops its tunnel ref. When the tunnel ref -reaches zero, the tunnel puts its socket ref. When the socket is -eventually destroyed, its sk_destruct finally frees the L2TP tunnel -context. +reaches zero, the tunnel drops its socket ref. Sessions -------- @@ -667,10 +664,7 @@ pseudowire) or other data types such as PPP, ATM, HDLC or Frame Relay. Linux currently implements only Ethernet and PPP session types. Some L2TP session types also have a socket (PPP pseudowires) while -others do not (Ethernet pseudowires). We can't therefore use the -socket reference count as the reference count for session -contexts. The L2TP implementation therefore has its own internal -reference counts on the session contexts. +others do not (Ethernet pseudowires). Like tunnels, L2TP sessions are identified by a unique session id. Just as with tunnel ids, the session id is 16-bit for @@ -680,21 +674,19 @@ value. Sessions hold a ref on their parent tunnel to ensure that the tunnel stays extant while one or more sessions references it. -Sessions are kept in a per-tunnel list, indexed by session id. L2TPv3 -sessions are also kept in a per-net list indexed by session id, -because L2TPv3 session ids are unique across all tunnels and L2TPv3 -data packets do not contain a tunnel id in the header. This list is -therefore needed to find the session context associated with a -received data packet when the tunnel context cannot be derived from -the tunnel socket. +Sessions are kept in a per-net list. L2TPv2 sessions and L2TPv3 +sessions are stored in separate lists. L2TPv2 sessions are keyed +by a 32-bit key made up of the 16-bit tunnel ID and 16-bit +session ID. L2TPv3 sessions are keyed by the 32-bit session ID, since +L2TPv3 session ids are unique across all tunnels. Although the L2TPv3 RFC specifies that L2TPv3 session ids are not -scoped by the tunnel, the kernel does not police this for L2TPv3 UDP -tunnels and does not add sessions of L2TPv3 UDP tunnels into the -per-net session list. In the UDP receive code, we must trust that the -tunnel can be identified using the tunnel socket's sk_user_data and -lookup the session in the tunnel's session list instead of the per-net -session list. +scoped by the tunnel, the Linux implementation has historically +allowed this. Such session id collisions are supported using a per-net +hash table keyed by sk and session ID. When looking up L2TPv3 +sessions, the list entry may link to multiple sessions with that +session ID, in which case the session matching the given sk (tunnel) +is used. PPP --- @@ -714,10 +706,9 @@ The L2TP PPP implementation handles the closing of a PPPoL2TP socket by closing its corresponding L2TP session. This is complicated because it must consider racing with netlink session create/destroy requests and pppol2tp_connect trying to reconnect with a session that is in the -process of being closed. Unlike tunnels, PPP sessions do not hold a -ref on their associated socket, so code must be careful to sock_hold -the socket where necessary. For all the details, see commit -3d609342cc04129ff7568e19316ce3d7451a27e8. +process of being closed. PPP sessions hold a ref on their associated +socket in order that the socket remains extants while the session +references it. Ethernet -------- @@ -761,15 +752,10 @@ Limitations The current implementation has a number of limitations: - 1) Multiple UDP sockets with the same 5-tuple address cannot be - used. The kernel's tunnel context is identified using private - data associated with the socket so it is important that each - socket is uniquely identified by its address. - - 2) Interfacing with openvswitch is not yet implemented. It may be + 1) Interfacing with openvswitch is not yet implemented. It may be useful to map OVS Ethernet and VLAN ports into L2TPv3 tunnels. - 3) VLAN pseudowires are implemented using an ``l2tpethN`` interface + 2) VLAN pseudowires are implemented using an ``l2tpethN`` interface configured with a VLAN sub-interface. Since L2TPv3 VLAN pseudowires carry one and only one VLAN, it may be better to use a single netdevice rather than an ``l2tpethN`` and ``l2tpethN``:M diff --git a/Documentation/networking/multi-pf-netdev.rst b/Documentation/networking/multi-pf-netdev.rst index 268819225866..2cd25d81aaa7 100644 --- a/Documentation/networking/multi-pf-netdev.rst +++ b/Documentation/networking/multi-pf-netdev.rst @@ -111,11 +111,11 @@ The relation between PF, irq, napi, and queue can be observed via netlink spec:: Here you can clearly observe our channels distribution policy:: $ ls /proc/irq/{36,39,40,41,42}/mlx5* -d -1 - /proc/irq/36/mlx5_comp1@pci:0000:08:00.0 - /proc/irq/39/mlx5_comp1@pci:0000:09:00.0 - /proc/irq/40/mlx5_comp2@pci:0000:08:00.0 - /proc/irq/41/mlx5_comp2@pci:0000:09:00.0 - /proc/irq/42/mlx5_comp3@pci:0000:08:00.0 + /proc/irq/36/mlx5_comp0@pci:0000:08:00.0 + /proc/irq/39/mlx5_comp0@pci:0000:09:00.0 + /proc/irq/40/mlx5_comp1@pci:0000:08:00.0 + /proc/irq/41/mlx5_comp1@pci:0000:09:00.0 + /proc/irq/42/mlx5_comp2@pci:0000:08:00.0 Steering ======== diff --git a/Documentation/networking/phy-link-topology.rst b/Documentation/networking/phy-link-topology.rst new file mode 100644 index 000000000000..4dec5d7d6513 --- /dev/null +++ b/Documentation/networking/phy-link-topology.rst @@ -0,0 +1,121 @@ +.. SPDX-License-Identifier: GPL-2.0 +.. _phy_link_topology: + +================= +PHY link topology +================= + +Overview +======== + +The PHY link topology representation in the networking stack aims at representing +the hardware layout for any given Ethernet link. + +An Ethernet interface from userspace's point of view is nothing but a +:c:type:`struct net_device <net_device>`, which exposes configuration options +through the legacy ioctls and the ethtool netlink commands. The base assumption +when designing these configuration APIs were that the link looks something like :: + + +-----------------------+ +----------+ +--------------+ + | Ethernet Controller / | | Ethernet | | Connector / | + | MAC | ------ | PHY | ---- | Port | ---... to LP + +-----------------------+ +----------+ +--------------+ + struct net_device struct phy_device + +Commands that needs to configure the PHY will go through the net_device.phydev +field to reach the PHY and perform the relevant configuration. + +This assumption falls apart in more complex topologies that can arise when, +for example, using SFP transceivers (although that's not the only specific case). + +Here, we have 2 basic scenarios. Either the MAC is able to output a serialized +interface, that can directly be fed to an SFP cage, such as SGMII, 1000BaseX, +10GBaseR, etc. + +The link topology then looks like this (when an SFP module is inserted) :: + + +-----+ SGMII +------------+ + | MAC | ------- | SFP Module | + +-----+ +------------+ + +Knowing that some modules embed a PHY, the actual link is more like :: + + +-----+ SGMII +--------------+ + | MAC | -------- | PHY (on SFP) | + +-----+ +--------------+ + +In this case, the SFP PHY is handled by phylib, and registered by phylink through +its SFP upstream ops. + +Now some Ethernet controllers aren't able to output a serialized interface, so +we can't directly connect them to an SFP cage. However, some PHYs can be used +as media-converters, to translate the non-serialized MAC MII interface to a +serialized MII interface fed to the SFP :: + + +-----+ RGMII +-----------------------+ SGMII +--------------+ + | MAC | ------- | PHY (media converter) | ------- | PHY (on SFP) | + +-----+ +-----------------------+ +--------------+ + +This is where the model of having a single net_device.phydev pointer shows its +limitations, as we now have 2 PHYs on the link. + +The phy_link topology framework aims at providing a way to keep track of every +PHY on the link, for use by both kernel drivers and subsystems, but also to +report the topology to userspace, allowing to target individual PHYs in configuration +commands. + +API +=== + +The :c:type:`struct phy_link_topology <phy_link_topology>` is a per-netdevice +resource, that gets initialized at netdevice creation. Once it's initialized, +it is then possible to register PHYs to the topology through : + +:c:func:`phy_link_topo_add_phy` + +Besides registering the PHY to the topology, this call will also assign a unique +index to the PHY, which can then be reported to userspace to refer to this PHY +(akin to the ifindex). This index is a u32, ranging from 1 to U32_MAX. The value +0 is reserved to indicate the PHY doesn't belong to any topology yet. + +The PHY can then be removed from the topology through + +:c:func:`phy_link_topo_del_phy` + +These function are already hooked into the phylib subsystem, so all PHYs that +are linked to a net_device through :c:func:`phy_attach_direct` will automatically +join the netdev's topology. + +PHYs that are on a SFP module will also be automatically registered IF the SFP +upstream is phylink (so, no media-converter). + +PHY drivers that can be used as SFP upstream need to call :c:func:`phy_sfp_attach_phy` +and :c:func:`phy_sfp_detach_phy`, which can be used as a +.attach_phy / .detach_phy implementation for the +:c:type:`struct sfp_upstream_ops <sfp_upstream_ops>`. + +UAPI +==== + +There exist a set of netlink commands to query the link topology from userspace, +see ``Documentation/networking/ethtool-netlink.rst``. + +The whole point of having a topology representation is to assign the phyindex +field in :c:type:`struct phy_device <phy_device>`. This index is reported to +userspace using the ``ETHTOOL_MSG_PHY_GET`` ethtnl command. Performing a DUMP operation +will result in all PHYs from all net_device being listed. The DUMP command +accepts either a ``ETHTOOL_A_HEADER_DEV_INDEX`` or ``ETHTOOL_A_HEADER_DEV_NAME`` +to be passed in the request to filter the DUMP to a single net_device. + +The retrieved index can then be passed as a request parameter using the +``ETHTOOL_A_HEADER_PHY_INDEX`` field in the following ethnl commands : + +* ``ETHTOOL_MSG_STRSET_GET`` to get the stats string set from a given PHY +* ``ETHTOOL_MSG_CABLE_TEST_ACT`` and ``ETHTOOL_MSG_CABLE_TEST_ACT``, to perform + cable testing on a given PHY on the link (most likely the outermost PHY) +* ``ETHTOOL_MSG_PSE_SET`` and ``ETHTOOL_MSG_PSE_GET`` for PHY-controlled PoE and PSE settings +* ``ETHTOOL_MSG_PLCA_GET_CFG``, ``ETHTOOL_MSG_PLCA_SET_CFG`` and ``ETHTOOL_MSG_PLCA_GET_STATUS`` + to set the PLCA (Physical Layer Collision Avoidance) parameters + +Note that the PHY index can be passed to other requests, which will silently +ignore it if present and irrelevant. diff --git a/MAINTAINERS b/MAINTAINERS index a70b7c9c3533..289a6b5615ce 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8341,6 +8341,7 @@ F: include/linux/mii.h 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/phylib_stubs.h F: include/linux/platform_data/mdio-bcm-unimac.h F: include/linux/platform_data/mdio-gpio.h @@ -14493,7 +14494,7 @@ MELLANOX ETHERNET DRIVER (mlx4_en) M: Tariq Toukan <tariqt@nvidia.com> L: netdev@vger.kernel.org S: Supported -W: http://www.mellanox.com +W: https://www.nvidia.com/networking/ Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: drivers/net/ethernet/mellanox/mlx4/en_* @@ -14502,7 +14503,7 @@ M: Saeed Mahameed <saeedm@nvidia.com> M: Tariq Toukan <tariqt@nvidia.com> L: netdev@vger.kernel.org S: Supported -W: http://www.mellanox.com +W: https://www.nvidia.com/networking/ Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: drivers/net/ethernet/mellanox/mlx5/core/en_* @@ -14510,7 +14511,7 @@ MELLANOX ETHERNET INNOVA DRIVERS R: Boris Pismenny <borisp@nvidia.com> L: netdev@vger.kernel.org S: Supported -W: http://www.mellanox.com +W: https://www.nvidia.com/networking/ Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: drivers/net/ethernet/mellanox/mlx5/core/en_accel/* F: drivers/net/ethernet/mellanox/mlx5/core/fpga/* @@ -14521,7 +14522,7 @@ M: Ido Schimmel <idosch@nvidia.com> M: Petr Machata <petrm@nvidia.com> L: netdev@vger.kernel.org S: Supported -W: http://www.mellanox.com +W: https://www.nvidia.com/networking/ Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: drivers/net/ethernet/mellanox/mlxsw/ F: tools/testing/selftests/drivers/net/mlxsw/ @@ -14530,7 +14531,7 @@ MELLANOX FIRMWARE FLASH LIBRARY (mlxfw) M: mlxsw@nvidia.com L: netdev@vger.kernel.org S: Supported -W: http://www.mellanox.com +W: https://www.nvidia.com/networking/ Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: drivers/net/ethernet/mellanox/mlxfw/ @@ -14549,7 +14550,7 @@ M: Tariq Toukan <tariqt@nvidia.com> L: netdev@vger.kernel.org L: linux-rdma@vger.kernel.org S: Supported -W: http://www.mellanox.com +W: https://www.nvidia.com/networking/ Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: drivers/net/ethernet/mellanox/mlx4/ F: include/linux/mlx4/ @@ -14558,7 +14559,7 @@ MELLANOX MLX4 IB driver M: Yishai Hadas <yishaih@nvidia.com> L: linux-rdma@vger.kernel.org S: Supported -W: http://www.mellanox.com +W: https://www.nvidia.com/networking/ Q: http://patchwork.kernel.org/project/linux-rdma/list/ F: drivers/infiniband/hw/mlx4/ F: include/linux/mlx4/ @@ -14571,7 +14572,7 @@ M: Tariq Toukan <tariqt@nvidia.com> L: netdev@vger.kernel.org L: linux-rdma@vger.kernel.org S: Supported -W: http://www.mellanox.com +W: https://www.nvidia.com/networking/ Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: Documentation/networking/device_drivers/ethernet/mellanox/ F: drivers/net/ethernet/mellanox/mlx5/core/ @@ -14581,7 +14582,7 @@ MELLANOX MLX5 IB driver M: Leon Romanovsky <leonro@nvidia.com> L: linux-rdma@vger.kernel.org S: Supported -W: http://www.mellanox.com +W: https://www.nvidia.com/networking/ Q: http://patchwork.kernel.org/project/linux-rdma/list/ F: drivers/infiniband/hw/mlx5/ F: include/linux/mlx5/ @@ -15774,6 +15775,7 @@ M: Breno Leitao <leitao@debian.org> S: Maintained F: Documentation/networking/netconsole.rst F: drivers/net/netconsole.c +F: tools/testing/selftests/drivers/net/netcons_basic.sh NETDEVSIM M: Jakub Kicinski <kuba@kernel.org> @@ -19216,6 +19218,7 @@ S: Supported W: https://oss.oracle.com/projects/rds/ F: Documentation/networking/rds.rst F: net/rds/ +F: tools/testing/selftests/net/rds/ RDT - RESOURCE ALLOCATION M: Fenghua Yu <fenghua.yu@intel.com> diff --git a/drivers/dpll/dpll_netlink.c b/drivers/dpll/dpll_netlink.c index 98e6ad8528d3..fc0280dcddd1 100644 --- a/drivers/dpll/dpll_netlink.c +++ b/drivers/dpll/dpll_netlink.c @@ -342,6 +342,51 @@ dpll_msg_add_pin_freq(struct sk_buff *msg, struct dpll_pin *pin, return 0; } +static int +dpll_msg_add_pin_esync(struct sk_buff *msg, struct dpll_pin *pin, + struct dpll_pin_ref *ref, struct netlink_ext_ack *extack) +{ + const struct dpll_pin_ops *ops = dpll_pin_ops(ref); + struct dpll_device *dpll = ref->dpll; + struct dpll_pin_esync esync; + struct nlattr *nest; + int ret, i; + + if (!ops->esync_get) + return 0; + ret = ops->esync_get(pin, dpll_pin_on_dpll_priv(dpll, pin), dpll, + dpll_priv(dpll), &esync, extack); + if (ret == -EOPNOTSUPP) + return 0; + else if (ret) + return ret; + if (nla_put_64bit(msg, DPLL_A_PIN_ESYNC_FREQUENCY, sizeof(esync.freq), + &esync.freq, DPLL_A_PIN_PAD)) + return -EMSGSIZE; + if (nla_put_u32(msg, DPLL_A_PIN_ESYNC_PULSE, esync.pulse)) + return -EMSGSIZE; + for (i = 0; i < esync.range_num; i++) { + nest = nla_nest_start(msg, + DPLL_A_PIN_ESYNC_FREQUENCY_SUPPORTED); + if (!nest) + return -EMSGSIZE; + if (nla_put_64bit(msg, DPLL_A_PIN_FREQUENCY_MIN, + sizeof(esync.range[i].min), + &esync.range[i].min, DPLL_A_PIN_PAD)) + goto nest_cancel; + if (nla_put_64bit(msg, DPLL_A_PIN_FREQUENCY_MAX, + sizeof(esync.range[i].max), + &esync.range[i].max, DPLL_A_PIN_PAD)) + goto nest_cancel; + nla_nest_end(msg, nest); + } + return 0; + +nest_cancel: + nla_nest_cancel(msg, nest); + return -EMSGSIZE; +} + static bool dpll_pin_is_freq_supported(struct dpll_pin *pin, u32 freq) { int fs; @@ -483,6 +528,9 @@ dpll_cmd_pin_get_one(struct sk_buff *msg, struct dpll_pin *pin, ret = dpll_msg_add_ffo(msg, pin, ref, extack); if (ret) return ret; + ret = dpll_msg_add_pin_esync(msg, pin, ref, extack); + if (ret) + return ret; if (xa_empty(&pin->parent_refs)) ret = dpll_msg_add_pin_dplls(msg, pin, extack); else @@ -739,6 +787,83 @@ rollback: } static int +dpll_pin_esync_set(struct dpll_pin *pin, struct nlattr *a, + struct netlink_ext_ack *extack) +{ + struct dpll_pin_ref *ref, *failed; + const struct dpll_pin_ops *ops; + struct dpll_pin_esync esync; + u64 freq = nla_get_u64(a); + struct dpll_device *dpll; + bool supported = false; + unsigned long i; + int ret; + + xa_for_each(&pin->dpll_refs, i, ref) { + ops = dpll_pin_ops(ref); + if (!ops->esync_set || !ops->esync_get) { + NL_SET_ERR_MSG(extack, + "embedded sync feature is not supported by this device"); + return -EOPNOTSUPP; + } + } + ref = dpll_xa_ref_dpll_first(&pin->dpll_refs); + ops = dpll_pin_ops(ref); + dpll = ref->dpll; + ret = ops->esync_get(pin, dpll_pin_on_dpll_priv(dpll, pin), dpll, + dpll_priv(dpll), &esync, extack); + if (ret) { + NL_SET_ERR_MSG(extack, "unable to get current embedded sync frequency value"); + return ret; + } + if (freq == esync.freq) + return 0; + for (i = 0; i < esync.range_num; i++) + if (freq <= esync.range[i].max && freq >= esync.range[i].min) + supported = true; + if (!supported) { + NL_SET_ERR_MSG_ATTR(extack, a, + "requested embedded sync frequency value is not supported by this device"); + return -EINVAL; + } + + xa_for_each(&pin->dpll_refs, i, ref) { + void *pin_dpll_priv; + + ops = dpll_pin_ops(ref); + dpll = ref->dpll; + pin_dpll_priv = dpll_pin_on_dpll_priv(dpll, pin); + ret = ops->esync_set(pin, pin_dpll_priv, dpll, dpll_priv(dpll), + freq, extack); + if (ret) { + failed = ref; + NL_SET_ERR_MSG_FMT(extack, + "embedded sync frequency set failed for dpll_id: %u", + dpll->id); + goto rollback; + } + } + __dpll_pin_change_ntf(pin); + + return 0; + +rollback: + xa_for_each(&pin->dpll_refs, i, ref) { + void *pin_dpll_priv; + + if (ref == failed) + break; + ops = dpll_pin_ops(ref); + dpll = ref->dpll; + pin_dpll_priv = dpll_pin_on_dpll_priv(dpll, pin); + if (ops->esync_set(pin, pin_dpll_priv, dpll, dpll_priv(dpll), + esync.freq, extack)) + NL_SET_ERR_MSG(extack, "set embedded sync frequency rollback failed"); + } + return ret; +} + +static int dpll_pin_on_pin_state_set(struct dpll_pin *pin, u32 parent_idx, enum dpll_pin_state state, struct netlink_ext_ack *extack) @@ -1039,6 +1164,11 @@ dpll_pin_set_from_nlattr(struct dpll_pin *pin, struct genl_info *info) if (ret) return ret; break; + case DPLL_A_PIN_ESYNC_FREQUENCY: + ret = dpll_pin_esync_set(pin, a, info->extack); + if (ret) + return ret; + break; } } diff --git a/drivers/dpll/dpll_nl.c b/drivers/dpll/dpll_nl.c index 1e95f5397cfc..fe9b6893d261 100644 --- a/drivers/dpll/dpll_nl.c +++ b/drivers/dpll/dpll_nl.c @@ -62,7 +62,7 @@ static const struct nla_policy dpll_pin_get_dump_nl_policy[DPLL_A_PIN_ID + 1] = }; /* DPLL_CMD_PIN_SET - do */ -static const struct nla_policy dpll_pin_set_nl_policy[DPLL_A_PIN_PHASE_ADJUST + 1] = { +static const struct nla_policy dpll_pin_set_nl_policy[DPLL_A_PIN_ESYNC_FREQUENCY + 1] = { [DPLL_A_PIN_ID] = { .type = NLA_U32, }, [DPLL_A_PIN_FREQUENCY] = { .type = NLA_U64, }, [DPLL_A_PIN_DIRECTION] = NLA_POLICY_RANGE(NLA_U32, 1, 2), @@ -71,6 +71,7 @@ static const struct nla_policy dpll_pin_set_nl_policy[DPLL_A_PIN_PHASE_ADJUST + [DPLL_A_PIN_PARENT_DEVICE] = NLA_POLICY_NESTED(dpll_pin_parent_device_nl_policy), [DPLL_A_PIN_PARENT_PIN] = NLA_POLICY_NESTED(dpll_pin_parent_pin_nl_policy), [DPLL_A_PIN_PHASE_ADJUST] = { .type = NLA_S32, }, + [DPLL_A_PIN_ESYNC_FREQUENCY] = { .type = NLA_U64, }, }; /* Ops table for dpll */ @@ -138,7 +139,7 @@ static const struct genl_split_ops dpll_nl_ops[] = { .doit = dpll_nl_pin_set_doit, .post_doit = dpll_pin_post_doit, .policy = dpll_pin_set_nl_policy, - .maxattr = DPLL_A_PIN_PHASE_ADJUST, + .maxattr = DPLL_A_PIN_ESYNC_FREQUENCY, .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, }, }; diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index bb9c3d6ef435..cb6a694313d5 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -2300,7 +2300,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, goto err_sysfs_del; } - res = slave_dev->netdev_ops->ndo_bpf(slave_dev, &xdp); + res = dev_xdp_propagate(slave_dev, &xdp); if (res < 0) { /* ndo_bpf() sets extack error message */ slave_dbg(bond_dev, slave_dev, "Error %d calling ndo_bpf\n", res); @@ -2436,7 +2436,7 @@ static int __bond_release_one(struct net_device *bond_dev, .prog = NULL, .extack = NULL, }; - if (slave_dev->netdev_ops->ndo_bpf(slave_dev, &xdp)) + if (dev_xdp_propagate(slave_dev, &xdp)) slave_warn(bond_dev, slave_dev, "failed to unload XDP program\n"); } @@ -5626,7 +5626,7 @@ static int bond_xdp_set(struct net_device *dev, struct bpf_prog *prog, goto err; } - err = slave_dev->netdev_ops->ndo_bpf(slave_dev, &xdp); + err = dev_xdp_propagate(slave_dev, &xdp); if (err < 0) { /* ndo_bpf() sets extack error message */ slave_err(dev, slave_dev, "Error %d calling ndo_bpf\n", err); @@ -5658,7 +5658,7 @@ err: if (slave == rollback_slave) break; - err_unwind = slave_dev->netdev_ops->ndo_bpf(slave_dev, &xdp); + err_unwind = dev_xdp_propagate(slave_dev, &xdp); if (err_unwind < 0) slave_err(dev, slave_dev, "Error %d when unwinding XDP program change\n", err_unwind); @@ -6384,7 +6384,8 @@ static int bond_init(struct net_device *bond_dev) netdev_dbg(bond_dev, "Begin bond_init\n"); - bond->wq = alloc_ordered_workqueue(bond_dev->name, WQ_MEM_RECLAIM); + bond->wq = alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM, + bond_dev->name); if (!bond->wq) return -ENOMEM; diff --git a/drivers/net/can/esd/esd_402_pci-core.c b/drivers/net/can/esd/esd_402_pci-core.c index b7cdcffd0e45..5d6d2828cd04 100644 --- a/drivers/net/can/esd/esd_402_pci-core.c +++ b/drivers/net/can/esd/esd_402_pci-core.c @@ -369,12 +369,13 @@ static int pci402_init_cores(struct pci_dev *pdev) SET_NETDEV_DEV(netdev, &pdev->dev); priv = netdev_priv(netdev); + priv->can.clock.freq = card->ov.core_frequency; priv->can.ctrlmode_supported = CAN_CTRLMODE_LOOPBACK | CAN_CTRLMODE_LISTENONLY | CAN_CTRLMODE_BERR_REPORTING | CAN_CTRLMODE_CC_LEN8_DLC; - - priv->can.clock.freq = card->ov.core_frequency; + if (card->ov.features & ACC_OV_REG_FEAT_MASK_DAR) + priv->can.ctrlmode_supported |= CAN_CTRLMODE_ONE_SHOT; if (card->ov.features & ACC_OV_REG_FEAT_MASK_CANFD) priv->can.bittiming_const = &pci402_bittiming_const_canfd; else diff --git a/drivers/net/can/esd/esdacc.c b/drivers/net/can/esd/esdacc.c index 121cbbf81458..c80032bc1a52 100644 --- a/drivers/net/can/esd/esdacc.c +++ b/drivers/net/can/esd/esdacc.c @@ -17,6 +17,9 @@ /* esdACC DLC register layout */ #define ACC_DLC_DLC_MASK GENMASK(3, 0) #define ACC_DLC_RTR_FLAG BIT(4) +#define ACC_DLC_SSTX_FLAG BIT(24) /* Single Shot TX */ + +/* esdACC DLC in struct acc_bmmsg_rxtxdone::acc_dlc.len only! */ #define ACC_DLC_TXD_FLAG BIT(5) /* ecc value of esdACC equals SJA1000's ECC register */ @@ -43,8 +46,8 @@ static void acc_resetmode_enter(struct acc_core *core) { - acc_set_bits(core, ACC_CORE_OF_CTRL_MODE, - ACC_REG_CONTROL_MASK_MODE_RESETMODE); + acc_set_bits(core, ACC_CORE_OF_CTRL, + ACC_REG_CTRL_MASK_RESETMODE); /* Read back reset mode bit to flush PCI write posting */ acc_resetmode_entered(core); @@ -52,14 +55,14 @@ static void acc_resetmode_enter(struct acc_core *core) static void acc_resetmode_leave(struct acc_core *core) { - acc_clear_bits(core, ACC_CORE_OF_CTRL_MODE, - ACC_REG_CONTROL_MASK_MODE_RESETMODE); + acc_clear_bits(core, ACC_CORE_OF_CTRL, + ACC_REG_CTRL_MASK_RESETMODE); /* Read back reset mode bit to flush PCI write posting */ acc_resetmode_entered(core); } -static void acc_txq_put(struct acc_core *core, u32 acc_id, u8 acc_dlc, +static void acc_txq_put(struct acc_core *core, u32 acc_id, u32 acc_dlc, const void *data) { acc_write32_noswap(core, ACC_CORE_OF_TXFIFO_DATA_1, @@ -172,7 +175,7 @@ int acc_open(struct net_device *netdev) struct acc_net_priv *priv = netdev_priv(netdev); struct acc_core *core = priv->core; u32 tx_fifo_status; - u32 ctrl_mode; + u32 ctrl; int err; /* Retry to enter RESET mode if out of sync. */ @@ -187,19 +190,19 @@ int acc_open(struct net_device *netdev) if (err) return err; - ctrl_mode = ACC_REG_CONTROL_MASK_IE_RXTX | - ACC_REG_CONTROL_MASK_IE_TXERROR | - ACC_REG_CONTROL_MASK_IE_ERRWARN | - ACC_REG_CONTROL_MASK_IE_OVERRUN | - ACC_REG_CONTROL_MASK_IE_ERRPASS; + ctrl = ACC_REG_CTRL_MASK_IE_RXTX | + ACC_REG_CTRL_MASK_IE_TXERROR | + ACC_REG_CTRL_MASK_IE_ERRWARN | + ACC_REG_CTRL_MASK_IE_OVERRUN | + ACC_REG_CTRL_MASK_IE_ERRPASS; if (priv->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING) - ctrl_mode |= ACC_REG_CONTROL_MASK_IE_BUSERR; + ctrl |= ACC_REG_CTRL_MASK_IE_BUSERR; if (priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY) - ctrl_mode |= ACC_REG_CONTROL_MASK_MODE_LOM; + ctrl |= ACC_REG_CTRL_MASK_LOM; - acc_set_bits(core, ACC_CORE_OF_CTRL_MODE, ctrl_mode); + acc_set_bits(core, ACC_CORE_OF_CTRL, ctrl); acc_resetmode_leave(core); priv->can.state = CAN_STATE_ERROR_ACTIVE; @@ -218,13 +221,13 @@ int acc_close(struct net_device *netdev) struct acc_net_priv *priv = netdev_priv(netdev); struct acc_core *core = priv->core; - acc_clear_bits(core, ACC_CORE_OF_CTRL_MODE, - ACC_REG_CONTROL_MASK_IE_RXTX | - ACC_REG_CONTROL_MASK_IE_TXERROR | - ACC_REG_CONTROL_MASK_IE_ERRWARN | - ACC_REG_CONTROL_MASK_IE_OVERRUN | - ACC_REG_CONTROL_MASK_IE_ERRPASS | - ACC_REG_CONTROL_MASK_IE_BUSERR); + acc_clear_bits(core, ACC_CORE_OF_CTRL, + ACC_REG_CTRL_MASK_IE_RXTX | + ACC_REG_CTRL_MASK_IE_TXERROR | + ACC_REG_CTRL_MASK_IE_ERRWARN | + ACC_REG_CTRL_MASK_IE_OVERRUN | + ACC_REG_CTRL_MASK_IE_ERRPASS | + ACC_REG_CTRL_MASK_IE_BUSERR); netif_stop_queue(netdev); acc_resetmode_enter(core); @@ -233,9 +236,9 @@ int acc_close(struct net_device *netdev) /* Mark pending TX requests to be aborted after controller restart. */ acc_write32(core, ACC_CORE_OF_TX_ABORT_MASK, 0xffff); - /* ACC_REG_CONTROL_MASK_MODE_LOM is only accessible in RESET mode */ - acc_clear_bits(core, ACC_CORE_OF_CTRL_MODE, - ACC_REG_CONTROL_MASK_MODE_LOM); + /* ACC_REG_CTRL_MASK_LOM is only accessible in RESET mode */ + acc_clear_bits(core, ACC_CORE_OF_CTRL, + ACC_REG_CTRL_MASK_LOM); close_candev(netdev); return 0; @@ -249,7 +252,7 @@ netdev_tx_t acc_start_xmit(struct sk_buff *skb, struct net_device *netdev) u8 tx_fifo_head = core->tx_fifo_head; int fifo_usage; u32 acc_id; - u8 acc_dlc; + u32 acc_dlc; if (can_dropped_invalid_skb(netdev, skb)) return NETDEV_TX_OK; @@ -274,6 +277,8 @@ netdev_tx_t acc_start_xmit(struct sk_buff *skb, struct net_device *netdev) acc_dlc = can_get_cc_dlc(cf, priv->can.ctrlmode); if (cf->can_id & CAN_RTR_FLAG) acc_dlc |= ACC_DLC_RTR_FLAG; + if (priv->can.ctrlmode & CAN_CTRLMODE_ONE_SHOT) + acc_dlc |= ACC_DLC_SSTX_FLAG; if (cf->can_id & CAN_EFF_FLAG) { acc_id = cf->can_id & CAN_EFF_MASK; diff --git a/drivers/net/can/esd/esdacc.h b/drivers/net/can/esd/esdacc.h index a70488b25d39..6b7ebd8c91b2 100644 --- a/drivers/net/can/esd/esdacc.h +++ b/drivers/net/can/esd/esdacc.h @@ -35,6 +35,7 @@ */ #define ACC_OV_REG_FEAT_MASK_CANFD BIT(27 - 16) #define ACC_OV_REG_FEAT_MASK_NEW_PSC BIT(28 - 16) +#define ACC_OV_REG_FEAT_MASK_DAR BIT(30 - 16) #define ACC_OV_REG_MODE_MASK_ENDIAN_LITTLE BIT(0) #define ACC_OV_REG_MODE_MASK_BM_ENABLE BIT(1) @@ -50,7 +51,7 @@ #define ACC_OV_REG_MODE_MASK_FPGA_RESET BIT(31) /* esdACC CAN Core Module */ -#define ACC_CORE_OF_CTRL_MODE 0x0000 +#define ACC_CORE_OF_CTRL 0x0000 #define ACC_CORE_OF_STATUS_IRQ 0x0008 #define ACC_CORE_OF_BRP 0x000c #define ACC_CORE_OF_BTR 0x0010 @@ -66,21 +67,22 @@ #define ACC_CORE_OF_TXFIFO_DATA_0 0x00c8 #define ACC_CORE_OF_TXFIFO_DATA_1 0x00cc -#define ACC_REG_CONTROL_MASK_MODE_RESETMODE BIT(0) -#define ACC_REG_CONTROL_MASK_MODE_LOM BIT(1) -#define ACC_REG_CONTROL_MASK_MODE_STM BIT(2) -#define ACC_REG_CONTROL_MASK_MODE_TRANSEN BIT(5) -#define ACC_REG_CONTROL_MASK_MODE_TS BIT(6) -#define ACC_REG_CONTROL_MASK_MODE_SCHEDULE BIT(7) - -#define ACC_REG_CONTROL_MASK_IE_RXTX BIT(8) -#define ACC_REG_CONTROL_MASK_IE_TXERROR BIT(9) -#define ACC_REG_CONTROL_MASK_IE_ERRWARN BIT(10) -#define ACC_REG_CONTROL_MASK_IE_OVERRUN BIT(11) -#define ACC_REG_CONTROL_MASK_IE_TSI BIT(12) -#define ACC_REG_CONTROL_MASK_IE_ERRPASS BIT(13) -#define ACC_REG_CONTROL_MASK_IE_ALI BIT(14) -#define ACC_REG_CONTROL_MASK_IE_BUSERR BIT(15) +/* CTRL register layout */ +#define ACC_REG_CTRL_MASK_RESETMODE BIT(0) +#define ACC_REG_CTRL_MASK_LOM BIT(1) +#define ACC_REG_CTRL_MASK_STM BIT(2) +#define ACC_REG_CTRL_MASK_TRANSEN BIT(5) +#define ACC_REG_CTRL_MASK_TS BIT(6) +#define ACC_REG_CTRL_MASK_SCHEDULE BIT(7) + +#define ACC_REG_CTRL_MASK_IE_RXTX BIT(8) +#define ACC_REG_CTRL_MASK_IE_TXERROR BIT(9) +#define ACC_REG_CTRL_MASK_IE_ERRWARN BIT(10) +#define ACC_REG_CTRL_MASK_IE_OVERRUN BIT(11) +#define ACC_REG_CTRL_MASK_IE_TSI BIT(12) +#define ACC_REG_CTRL_MASK_IE_ERRPASS BIT(13) +#define ACC_REG_CTRL_MASK_IE_ALI BIT(14) +#define ACC_REG_CTRL_MASK_IE_BUSERR BIT(15) /* BRP and BTR register layout for CAN-Classic version */ #define ACC_REG_BRP_CL_MASK_BRP GENMASK(8, 0) @@ -300,9 +302,9 @@ static inline void acc_clear_bits(struct acc_core *core, static inline int acc_resetmode_entered(struct acc_core *core) { - u32 ctrl = acc_read32(core, ACC_CORE_OF_CTRL_MODE); + u32 ctrl = acc_read32(core, ACC_CORE_OF_CTRL); - return (ctrl & ACC_REG_CONTROL_MASK_MODE_RESETMODE) != 0; + return (ctrl & ACC_REG_CTRL_MASK_RESETMODE) != 0; } static inline u32 acc_ov_read32(struct acc_ov *ov, unsigned short offs) diff --git a/drivers/net/can/flexcan/flexcan-core.c b/drivers/net/can/flexcan/flexcan-core.c index 8ea7f2795551..d11411029330 100644 --- a/drivers/net/can/flexcan/flexcan-core.c +++ b/drivers/net/can/flexcan/flexcan-core.c @@ -354,6 +354,14 @@ static struct flexcan_devtype_data fsl_imx93_devtype_data = { FLEXCAN_QUIRK_SUPPORT_RX_MAILBOX_RTR, }; +static const struct flexcan_devtype_data fsl_imx95_devtype_data = { + .quirks = FLEXCAN_QUIRK_DISABLE_RXFG | FLEXCAN_QUIRK_ENABLE_EACEN_RRS | + FLEXCAN_QUIRK_DISABLE_MECR | FLEXCAN_QUIRK_USE_RX_MAILBOX | + FLEXCAN_QUIRK_BROKEN_PERR_STATE | FLEXCAN_QUIRK_SUPPORT_FD | + FLEXCAN_QUIRK_SUPPORT_ECC | FLEXCAN_QUIRK_SUPPORT_RX_MAILBOX | + FLEXCAN_QUIRK_SUPPORT_RX_MAILBOX_RTR | FLEXCAN_QUIRK_SETUP_STOP_MODE_SCMI, +}; + static const struct flexcan_devtype_data fsl_vf610_devtype_data = { .quirks = FLEXCAN_QUIRK_DISABLE_RXFG | FLEXCAN_QUIRK_ENABLE_EACEN_RRS | FLEXCAN_QUIRK_DISABLE_MECR | FLEXCAN_QUIRK_USE_RX_MAILBOX | @@ -544,6 +552,13 @@ static inline int flexcan_enter_stop_mode(struct flexcan_priv *priv) } else if (priv->devtype_data.quirks & FLEXCAN_QUIRK_SETUP_STOP_MODE_GPR) { regmap_update_bits(priv->stm.gpr, priv->stm.req_gpr, 1 << priv->stm.req_bit, 1 << priv->stm.req_bit); + } else if (priv->devtype_data.quirks & FLEXCAN_QUIRK_SETUP_STOP_MODE_SCMI) { + /* For the SCMI mode, driver do nothing, ATF will send request to + * SM(system manager, M33 core) through SCMI protocol after linux + * suspend. Once SM get this request, it will send IPG_STOP signal + * to Flex_CAN, let CAN in STOP mode. + */ + return 0; } return flexcan_low_power_enter_ack(priv); @@ -555,7 +570,11 @@ static inline int flexcan_exit_stop_mode(struct flexcan_priv *priv) u32 reg_mcr; int ret; - /* remove stop request */ + /* Remove stop request, for FLEXCAN_QUIRK_SETUP_STOP_MODE_SCMI, + * do nothing here, because ATF already send request to SM before + * linux resume. Once SM get this request, it will deassert the + * IPG_STOP signal to Flex_CAN. + */ if (priv->devtype_data.quirks & FLEXCAN_QUIRK_SETUP_STOP_MODE_SCFW) { ret = flexcan_stop_mode_enable_scfw(priv, false); if (ret < 0) @@ -1983,6 +2002,9 @@ static int flexcan_setup_stop_mode(struct platform_device *pdev) ret = flexcan_setup_stop_mode_scfw(pdev); else if (priv->devtype_data.quirks & FLEXCAN_QUIRK_SETUP_STOP_MODE_GPR) ret = flexcan_setup_stop_mode_gpr(pdev); + else if (priv->devtype_data.quirks & FLEXCAN_QUIRK_SETUP_STOP_MODE_SCMI) + /* ATF will handle all STOP_IPG related work */ + ret = 0; else /* return 0 directly if doesn't support stop mode feature */ return 0; @@ -2009,6 +2031,7 @@ static const struct of_device_id flexcan_of_match[] = { { .compatible = "fsl,imx8qm-flexcan", .data = &fsl_imx8qm_devtype_data, }, { .compatible = "fsl,imx8mp-flexcan", .data = &fsl_imx8mp_devtype_data, }, { .compatible = "fsl,imx93-flexcan", .data = &fsl_imx93_devtype_data, }, + { .compatible = "fsl,imx95-flexcan", .data = &fsl_imx95_devtype_data, }, { .compatible = "fsl,imx6q-flexcan", .data = &fsl_imx6q_devtype_data, }, { .compatible = "fsl,imx28-flexcan", .data = &fsl_imx28_devtype_data, }, { .compatible = "fsl,imx53-flexcan", .data = &fsl_imx25_devtype_data, }, @@ -2309,9 +2332,19 @@ static int __maybe_unused flexcan_noirq_suspend(struct device *device) if (device_may_wakeup(device)) flexcan_enable_wakeup_irq(priv, true); - err = pm_runtime_force_suspend(device); - if (err) - return err; + /* For FLEXCAN_QUIRK_SETUP_STOP_MODE_SCMI, it need ATF to send + * to SM through SCMI protocol, SM will assert the IPG_STOP + * signal. But all this works need the CAN clocks keep on. + * After the CAN module get the IPG_STOP mode, and switch to + * STOP mode, whether still keep the CAN clocks on or gate them + * off depend on the Hardware design. + */ + if (!(device_may_wakeup(device) && + priv->devtype_data.quirks & FLEXCAN_QUIRK_SETUP_STOP_MODE_SCMI)) { + err = pm_runtime_force_suspend(device); + if (err) + return err; + } } return 0; @@ -2325,9 +2358,12 @@ static int __maybe_unused flexcan_noirq_resume(struct device *device) if (netif_running(dev)) { int err; - err = pm_runtime_force_resume(device); - if (err) - return err; + if (!(device_may_wakeup(device) && + priv->devtype_data.quirks & FLEXCAN_QUIRK_SETUP_STOP_MODE_SCMI)) { + err = pm_runtime_force_resume(device); + if (err) + return err; + } if (device_may_wakeup(device)) flexcan_enable_wakeup_irq(priv, false); diff --git a/drivers/net/can/flexcan/flexcan.h b/drivers/net/can/flexcan/flexcan.h index 025c3417031f..4933d8c7439e 100644 --- a/drivers/net/can/flexcan/flexcan.h +++ b/drivers/net/can/flexcan/flexcan.h @@ -68,6 +68,8 @@ #define FLEXCAN_QUIRK_SUPPORT_RX_MAILBOX_RTR BIT(15) /* Device supports RX via FIFO */ #define FLEXCAN_QUIRK_SUPPORT_RX_FIFO BIT(16) +/* Setup stop mode with ATF SCMI protocol to support wakeup */ +#define FLEXCAN_QUIRK_SETUP_STOP_MODE_SCMI BIT(17) struct flexcan_devtype_data { u32 quirks; /* quirks needed for different IP cores */ diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb.h b/drivers/net/can/usb/kvaser_usb/kvaser_usb.h index ff10b3790d84..078496d9b7ba 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb.h +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb.h @@ -22,6 +22,8 @@ */ #include <linux/completion.h> +#include <linux/ktime.h> +#include <linux/math64.h> #include <linux/spinlock.h> #include <linux/types.h> #include <linux/usb.h> @@ -39,7 +41,6 @@ #define KVASER_USB_QUIRK_HAS_SILENT_MODE BIT(0) #define KVASER_USB_QUIRK_HAS_TXRX_ERRORS BIT(1) #define KVASER_USB_QUIRK_IGNORE_CLK_FREQ BIT(2) -#define KVASER_USB_QUIRK_HAS_HARDWARE_TIMESTAMP BIT(3) /* Device capabilities */ #define KVASER_USB_CAP_BERR_CAP 0x01 @@ -68,6 +69,7 @@ struct kvaser_usb_dev_card_data { u32 ctrlmode_supported; u32 capabilities; struct kvaser_usb_dev_card_data_hydra hydra; + u32 usbcan_timestamp_msb; }; /* Context for an outstanding, not yet ACKed, transmission */ @@ -216,4 +218,26 @@ int kvaser_usb_can_rx_over_error(struct net_device *netdev); extern const struct can_bittiming_const kvaser_usb_flexc_bittiming_const; +static inline ktime_t kvaser_usb_ticks_to_ktime(const struct kvaser_usb_dev_cfg *cfg, + u64 ticks) +{ + return ns_to_ktime(div_u64(ticks * 1000, cfg->timestamp_freq)); +} + +static inline ktime_t kvaser_usb_timestamp48_to_ktime(const struct kvaser_usb_dev_cfg *cfg, + const __le16 *timestamp) +{ + u64 ticks = le16_to_cpu(timestamp[0]) | + (u64)(le16_to_cpu(timestamp[1])) << 16 | + (u64)(le16_to_cpu(timestamp[2])) << 32; + + return kvaser_usb_ticks_to_ktime(cfg, ticks); +} + +static inline ktime_t kvaser_usb_timestamp64_to_ktime(const struct kvaser_usb_dev_cfg *cfg, + __le64 timestamp) +{ + return kvaser_usb_ticks_to_ktime(cfg, le64_to_cpu(timestamp)); +} + #endif /* KVASER_USB_H */ 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 daa34b532aa8..35b4132b0639 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c @@ -94,7 +94,7 @@ #define USB_MINI_PCIE_1XCAN_PRODUCT_ID 0x011B static const struct kvaser_usb_driver_info kvaser_usb_driver_info_hydra = { - .quirks = KVASER_USB_QUIRK_HAS_HARDWARE_TIMESTAMP, + .quirks = 0, .ops = &kvaser_usb_hydra_dev_ops, }; @@ -756,23 +756,12 @@ freeurb: static const struct net_device_ops kvaser_usb_netdev_ops = { .ndo_open = kvaser_usb_open, .ndo_stop = kvaser_usb_close, - .ndo_start_xmit = kvaser_usb_start_xmit, - .ndo_change_mtu = can_change_mtu, -}; - -static const struct net_device_ops kvaser_usb_netdev_ops_hwts = { - .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, }; static const struct ethtool_ops kvaser_usb_ethtool_ops = { - .get_ts_info = ethtool_op_get_ts_info, -}; - -static const struct ethtool_ops kvaser_usb_ethtool_ops_hwts = { .get_ts_info = can_ethtool_op_get_ts_info_hwts, }; @@ -859,13 +848,7 @@ static int kvaser_usb_init_one(struct kvaser_usb *dev, int channel) netdev->flags |= IFF_ECHO; netdev->netdev_ops = &kvaser_usb_netdev_ops; - if (driver_info->quirks & KVASER_USB_QUIRK_HAS_HARDWARE_TIMESTAMP) { - netdev->netdev_ops = &kvaser_usb_netdev_ops_hwts; - netdev->ethtool_ops = &kvaser_usb_ethtool_ops_hwts; - } else { - netdev->netdev_ops = &kvaser_usb_netdev_ops; - netdev->ethtool_ops = &kvaser_usb_ethtool_ops; - } + netdev->ethtool_ops = &kvaser_usb_ethtool_ops; SET_NETDEV_DEV(netdev, &dev->intf->dev); netdev->dev_id = channel; diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c index c7ba768dfe17..3764b263add3 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c @@ -10,7 +10,6 @@ * - Transition from CAN_STATE_ERROR_WARNING to CAN_STATE_ERROR_ACTIVE is only * reported after a call to do_get_berr_counter(), since firmware does not * distinguish between ERROR_WARNING and ERROR_ACTIVE. - * - Hardware timestamps are not set for CAN Tx frames. */ #include <linux/completion.h> @@ -261,6 +260,15 @@ struct kvaser_cmd_tx_can { u8 reserved[11]; } __packed; +struct kvaser_cmd_tx_ack { + __le32 id; + u8 data[8]; + u8 dlc; + u8 flags; + __le16 timestamp[3]; + u8 reserved0[8]; +} __packed; + struct kvaser_cmd_header { u8 cmd_no; /* The destination HE address is stored in 0..5 of he_addr. @@ -297,6 +305,7 @@ struct kvaser_cmd { struct kvaser_cmd_rx_can rx_can; struct kvaser_cmd_tx_can tx_can; + struct kvaser_cmd_tx_ack tx_ack; } __packed; } __packed; @@ -522,23 +531,25 @@ kvaser_usb_hydra_net_priv_from_cmd(const struct kvaser_usb *dev, return priv; } -static ktime_t -kvaser_usb_hydra_ktime_from_rx_cmd(const struct kvaser_usb_dev_cfg *cfg, - const struct kvaser_cmd *cmd) +static ktime_t kvaser_usb_hydra_ktime_from_cmd(const struct kvaser_usb_dev_cfg *cfg, + const struct kvaser_cmd *cmd) { - u64 ticks; + ktime_t hwtstamp = 0; if (cmd->header.cmd_no == CMD_EXTENDED) { struct kvaser_cmd_ext *cmd_ext = (struct kvaser_cmd_ext *)cmd; - ticks = le64_to_cpu(cmd_ext->rx_can.timestamp); - } else { - ticks = le16_to_cpu(cmd->rx_can.timestamp[0]); - ticks += (u64)(le16_to_cpu(cmd->rx_can.timestamp[1])) << 16; - ticks += (u64)(le16_to_cpu(cmd->rx_can.timestamp[2])) << 32; + if (cmd_ext->cmd_no_ext == CMD_RX_MESSAGE_FD) + hwtstamp = kvaser_usb_timestamp64_to_ktime(cfg, cmd_ext->rx_can.timestamp); + else if (cmd_ext->cmd_no_ext == CMD_TX_ACKNOWLEDGE_FD) + hwtstamp = kvaser_usb_timestamp64_to_ktime(cfg, cmd_ext->tx_ack.timestamp); + } else if (cmd->header.cmd_no == CMD_RX_MESSAGE) { + hwtstamp = kvaser_usb_timestamp48_to_ktime(cfg, cmd->rx_can.timestamp); + } else if (cmd->header.cmd_no == CMD_TX_ACKNOWLEDGE) { + hwtstamp = kvaser_usb_timestamp48_to_ktime(cfg, cmd->tx_ack.timestamp); } - return ns_to_ktime(div_u64(ticks * 1000, cfg->timestamp_freq)); + return hwtstamp; } static int kvaser_usb_hydra_send_simple_cmd(struct kvaser_usb *dev, @@ -1175,6 +1186,7 @@ static void kvaser_usb_hydra_tx_acknowledge(const struct kvaser_usb *dev, bool one_shot_fail = false; bool is_err_frame = false; u16 transid = kvaser_usb_hydra_get_cmd_transid(cmd); + struct sk_buff *skb; priv = kvaser_usb_hydra_net_priv_from_cmd(dev, cmd); if (!priv) @@ -1201,6 +1213,9 @@ static void kvaser_usb_hydra_tx_acknowledge(const struct kvaser_usb *dev, spin_lock_irqsave(&priv->tx_contexts_lock, irq_flags); + skb = priv->can.echo_skb[context->echo_index]; + if (skb) + skb_hwtstamps(skb)->hwtstamp = kvaser_usb_hydra_ktime_from_cmd(dev->cfg, cmd); len = can_get_echo_skb(priv->netdev, context->echo_index, NULL); context->echo_index = dev->max_tx_urbs; --priv->active_tx_contexts; @@ -1234,7 +1249,7 @@ static void kvaser_usb_hydra_rx_msg_std(const struct kvaser_usb *dev, stats = &priv->netdev->stats; flags = cmd->rx_can.flags; - hwtstamp = kvaser_usb_hydra_ktime_from_rx_cmd(dev->cfg, cmd); + hwtstamp = kvaser_usb_hydra_ktime_from_cmd(dev->cfg, cmd); if (flags & KVASER_USB_HYDRA_CF_FLAG_ERROR_FRAME) { kvaser_usb_hydra_error_frame(priv, &cmd->rx_can.err_frame_data, @@ -1302,7 +1317,7 @@ static void kvaser_usb_hydra_rx_msg_ext(const struct kvaser_usb *dev, KVASER_USB_KCAN_DATA_DLC_SHIFT; flags = le32_to_cpu(cmd->rx_can.flags); - hwtstamp = kvaser_usb_hydra_ktime_from_rx_cmd(dev->cfg, std_cmd); + hwtstamp = kvaser_usb_hydra_ktime_from_cmd(dev->cfg, std_cmd); if (flags & KVASER_USB_HYDRA_CF_FLAG_ERROR_FRAME) { kvaser_usb_hydra_error_frame(priv, &cmd->rx_can.err_frame_data, diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c index 23bd7574b1c7..6b9122ab1464 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c @@ -119,6 +119,10 @@ /* Extended CAN identifier flag */ #define KVASER_EXTENDED_FRAME BIT(31) +/* USBCanII timestamp */ +#define KVASER_USB_USBCAN_CLK_OVERFLOW_MASK GENMASK(31, 16) +#define KVASER_USB_USBCAN_TIMESTAMP_FACTOR 10 + struct kvaser_cmd_simple { u8 tid; u8 channel; @@ -235,6 +239,20 @@ struct kvaser_cmd_tx_acknowledge_header { u8 tid; } __packed; +struct leaf_cmd_tx_acknowledge { + u8 channel; + u8 tid; + __le16 time[3]; + u8 padding[2]; +} __packed; + +struct usbcan_cmd_tx_acknowledge { + u8 channel; + u8 tid; + __le16 time; + u8 padding[2]; +} __packed; + struct leaf_cmd_can_error_event { u8 tid; u8 flags; @@ -281,6 +299,12 @@ struct usbcan_cmd_error_event { __le16 padding; } __packed; +struct usbcan_cmd_clk_overflow_event { + u8 tid; + u8 padding; + __le32 time; +} __packed; + struct kvaser_cmd_ctrl_mode { u8 tid; u8 channel; @@ -347,6 +371,7 @@ struct kvaser_cmd { struct leaf_cmd_error_event error_event; struct kvaser_cmd_cap_req cap_req; struct kvaser_cmd_cap_res cap_res; + struct leaf_cmd_tx_acknowledge tx_ack; } __packed leaf; union { @@ -355,6 +380,8 @@ struct kvaser_cmd { struct usbcan_cmd_chip_state_event chip_state_event; struct usbcan_cmd_can_error_event can_error_event; struct usbcan_cmd_error_event error_event; + struct usbcan_cmd_tx_acknowledge tx_ack; + struct usbcan_cmd_clk_overflow_event clk_overflow_event; } __packed usbcan; struct kvaser_cmd_tx_can tx_can; @@ -370,7 +397,7 @@ static const u8 kvaser_usb_leaf_cmd_sizes_leaf[] = { [CMD_START_CHIP_REPLY] = kvaser_fsize(u.simple), [CMD_STOP_CHIP_REPLY] = kvaser_fsize(u.simple), [CMD_GET_CARD_INFO_REPLY] = kvaser_fsize(u.cardinfo), - [CMD_TX_ACKNOWLEDGE] = kvaser_fsize(u.tx_acknowledge_header), + [CMD_TX_ACKNOWLEDGE] = kvaser_fsize(u.leaf.tx_ack), [CMD_GET_SOFTWARE_INFO_REPLY] = kvaser_fsize(u.leaf.softinfo), [CMD_RX_STD_MESSAGE] = kvaser_fsize(u.leaf.rx_can), [CMD_RX_EXT_MESSAGE] = kvaser_fsize(u.leaf.rx_can), @@ -388,15 +415,14 @@ static const u8 kvaser_usb_leaf_cmd_sizes_usbcan[] = { [CMD_START_CHIP_REPLY] = kvaser_fsize(u.simple), [CMD_STOP_CHIP_REPLY] = kvaser_fsize(u.simple), [CMD_GET_CARD_INFO_REPLY] = kvaser_fsize(u.cardinfo), - [CMD_TX_ACKNOWLEDGE] = kvaser_fsize(u.tx_acknowledge_header), + [CMD_TX_ACKNOWLEDGE] = kvaser_fsize(u.usbcan.tx_ack), [CMD_GET_SOFTWARE_INFO_REPLY] = kvaser_fsize(u.usbcan.softinfo), [CMD_RX_STD_MESSAGE] = kvaser_fsize(u.usbcan.rx_can), [CMD_RX_EXT_MESSAGE] = kvaser_fsize(u.usbcan.rx_can), [CMD_CHIP_STATE_EVENT] = kvaser_fsize(u.usbcan.chip_state_event), [CMD_CAN_ERROR_EVENT] = kvaser_fsize(u.usbcan.can_error_event), [CMD_ERROR_EVENT] = kvaser_fsize(u.usbcan.error_event), - /* ignored events: */ - [CMD_USBCAN_CLOCK_OVERFLOW_EVENT] = CMD_SIZE_ANY, + [CMD_USBCAN_CLOCK_OVERFLOW_EVENT] = kvaser_fsize(u.usbcan.clk_overflow_event), }; /* Summary of a kvaser error event, for a unified Leaf/Usbcan error @@ -463,11 +489,27 @@ static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_usbcan_dev_cfg = { .bittiming_const = &kvaser_usb_leaf_m16c_bittiming_const, }; -static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_m32c_dev_cfg = { +static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_m32c_dev_cfg_16mhz = { .clock = { .freq = 16 * MEGA /* Hz */, }, - .timestamp_freq = 1, + .timestamp_freq = 16, + .bittiming_const = &kvaser_usb_leaf_m32c_bittiming_const, +}; + +static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_m32c_dev_cfg_24mhz = { + .clock = { + .freq = 16 * MEGA /* Hz */, + }, + .timestamp_freq = 24, + .bittiming_const = &kvaser_usb_leaf_m32c_bittiming_const, +}; + +static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_m32c_dev_cfg_32mhz = { + .clock = { + .freq = 16 * MEGA /* Hz */, + }, + .timestamp_freq = 32, .bittiming_const = &kvaser_usb_leaf_m32c_bittiming_const, }; @@ -475,7 +517,7 @@ static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_imx_dev_cfg_16mhz = { .clock = { .freq = 16 * MEGA /* Hz */, }, - .timestamp_freq = 1, + .timestamp_freq = 16, .bittiming_const = &kvaser_usb_flexc_bittiming_const, }; @@ -483,7 +525,7 @@ static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_imx_dev_cfg_24mhz = { .clock = { .freq = 24 * MEGA /* Hz */, }, - .timestamp_freq = 1, + .timestamp_freq = 24, .bittiming_const = &kvaser_usb_flexc_bittiming_const, }; @@ -491,10 +533,19 @@ static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_imx_dev_cfg_32mhz = { .clock = { .freq = 32 * MEGA /* Hz */, }, - .timestamp_freq = 1, + .timestamp_freq = 32, .bittiming_const = &kvaser_usb_flexc_bittiming_const, }; +static inline ktime_t kvaser_usb_usbcan_timestamp_to_ktime(const struct kvaser_usb *dev, + __le16 timestamp) +{ + u64 ticks = le16_to_cpu(timestamp) | + dev->card_data.usbcan_timestamp_msb; + + return kvaser_usb_ticks_to_ktime(dev->cfg, ticks * KVASER_USB_USBCAN_TIMESTAMP_FACTOR); +} + static int kvaser_usb_leaf_verify_size(const struct kvaser_usb *dev, const struct kvaser_cmd *cmd) { @@ -678,8 +729,19 @@ static void kvaser_usb_leaf_get_software_info_leaf(struct kvaser_usb *dev, if (dev->driver_info->quirks & KVASER_USB_QUIRK_IGNORE_CLK_FREQ) { /* Firmware expects bittiming parameters calculated for 16MHz * clock, regardless of the actual clock + * Though, the reported freq is used for timestamps */ - dev->cfg = &kvaser_usb_leaf_m32c_dev_cfg; + switch (sw_options & KVASER_USB_LEAF_SWOPTION_FREQ_MASK) { + case KVASER_USB_LEAF_SWOPTION_FREQ_16_MHZ_CLK: + dev->cfg = &kvaser_usb_leaf_m32c_dev_cfg_16mhz; + break; + case KVASER_USB_LEAF_SWOPTION_FREQ_24_MHZ_CLK: + dev->cfg = &kvaser_usb_leaf_m32c_dev_cfg_24mhz; + break; + case KVASER_USB_LEAF_SWOPTION_FREQ_32_MHZ_CLK: + dev->cfg = &kvaser_usb_leaf_m32c_dev_cfg_32mhz; + break; + } } else { switch (sw_options & KVASER_USB_LEAF_SWOPTION_FREQ_MASK) { case KVASER_USB_LEAF_SWOPTION_FREQ_16_MHZ_CLK: @@ -880,6 +942,8 @@ static void kvaser_usb_leaf_tx_acknowledge(const struct kvaser_usb *dev, struct kvaser_usb_net_priv *priv; unsigned long flags; u8 channel, tid; + struct sk_buff *skb; + ktime_t hwtstamp = 0; channel = cmd->u.tx_acknowledge_header.channel; tid = cmd->u.tx_acknowledge_header.tid; @@ -901,14 +965,14 @@ static void kvaser_usb_leaf_tx_acknowledge(const struct kvaser_usb *dev, /* Sometimes the state change doesn't come after a bus-off event */ if (priv->can.restart_ms && priv->can.state == CAN_STATE_BUS_OFF) { - struct sk_buff *skb; + struct sk_buff *err_skb; struct can_frame *cf; - skb = alloc_can_err_skb(priv->netdev, &cf); - if (skb) { + err_skb = alloc_can_err_skb(priv->netdev, &cf); + if (err_skb) { cf->can_id |= CAN_ERR_RESTARTED; - netif_rx(skb); + netif_rx(err_skb); } else { netdev_err(priv->netdev, "No memory left for err_skb\n"); @@ -919,9 +983,20 @@ static void kvaser_usb_leaf_tx_acknowledge(const struct kvaser_usb *dev, priv->can.state = CAN_STATE_ERROR_ACTIVE; } + switch (dev->driver_info->family) { + case KVASER_LEAF: + hwtstamp = kvaser_usb_timestamp48_to_ktime(dev->cfg, cmd->u.leaf.tx_ack.time); + break; + case KVASER_USBCAN: + hwtstamp = kvaser_usb_usbcan_timestamp_to_ktime(dev, cmd->u.usbcan.tx_ack.time); + break; + } spin_lock_irqsave(&priv->tx_contexts_lock, flags); + skb = priv->can.echo_skb[context->echo_index]; + if (skb) + skb_hwtstamps(skb)->hwtstamp = hwtstamp; stats->tx_packets++; stats->tx_bytes += can_get_echo_skb(priv->netdev, context->echo_index, NULL); @@ -1299,6 +1374,7 @@ static void kvaser_usb_leaf_rx_can_msg(const struct kvaser_usb *dev, struct net_device_stats *stats; u8 channel = cmd->u.rx_can_header.channel; const u8 *rx_data = NULL; /* GCC */ + ktime_t hwtstamp = 0; if (channel >= dev->nchannels) { dev_err(&dev->intf->dev, @@ -1329,9 +1405,11 @@ static void kvaser_usb_leaf_rx_can_msg(const struct kvaser_usb *dev, switch (dev->driver_info->family) { case KVASER_LEAF: rx_data = cmd->u.leaf.rx_can.data; + hwtstamp = kvaser_usb_timestamp48_to_ktime(dev->cfg, cmd->u.leaf.rx_can.time); break; case KVASER_USBCAN: rx_data = cmd->u.usbcan.rx_can.data; + hwtstamp = kvaser_usb_usbcan_timestamp_to_ktime(dev, cmd->u.usbcan.rx_can.time); break; } @@ -1375,6 +1453,7 @@ static void kvaser_usb_leaf_rx_can_msg(const struct kvaser_usb *dev, memcpy(cf->data, &rx_data[6], cf->len); } + skb_hwtstamps(skb)->hwtstamp = hwtstamp; stats->rx_packets++; if (!(cf->can_id & CAN_RTR_FLAG)) stats->rx_bytes += cf->len; @@ -1508,7 +1587,7 @@ static void kvaser_usb_leaf_get_busparams_reply(const struct kvaser_usb *dev, complete(&priv->get_busparams_comp); } -static void kvaser_usb_leaf_handle_command(const struct kvaser_usb *dev, +static void kvaser_usb_leaf_handle_command(struct kvaser_usb *dev, const struct kvaser_cmd *cmd) { if (kvaser_usb_leaf_verify_size(dev, cmd) < 0) @@ -1554,12 +1633,15 @@ static void kvaser_usb_leaf_handle_command(const struct kvaser_usb *dev, kvaser_usb_leaf_get_busparams_reply(dev, cmd); break; - /* Ignored commands */ case CMD_USBCAN_CLOCK_OVERFLOW_EVENT: if (dev->driver_info->family != KVASER_USBCAN) goto warn; + dev->card_data.usbcan_timestamp_msb = + le32_to_cpu(cmd->u.usbcan.clk_overflow_event.time) & + KVASER_USB_USBCAN_CLK_OVERFLOW_MASK; break; + /* Ignored commands */ case CMD_FLUSH_QUEUE_REPLY: if (dev->driver_info->family != KVASER_LEAF) goto warn; diff --git a/drivers/net/dsa/b53/b53_mdio.c b/drivers/net/dsa/b53/b53_mdio.c index 897e5e8b3d69..31d070bf161a 100644 --- a/drivers/net/dsa/b53/b53_mdio.c +++ b/drivers/net/dsa/b53/b53_mdio.c @@ -343,10 +343,9 @@ static int b53_mdio_probe(struct mdio_device *mdiodev) dev_set_drvdata(&mdiodev->dev, dev); ret = b53_switch_register(dev); - if (ret) { - dev_err(&mdiodev->dev, "failed to register switch: %i\n", ret); - return ret; - } + if (ret) + return dev_err_probe(&mdiodev->dev, ret, + "failed to register switch\n"); return ret; } diff --git a/drivers/net/dsa/microchip/ksz8.h b/drivers/net/dsa/microchip/ksz8.h index ae43077e76c3..e1c79ff97123 100644 --- a/drivers/net/dsa/microchip/ksz8.h +++ b/drivers/net/dsa/microchip/ksz8.h @@ -54,6 +54,9 @@ int ksz8_reset_switch(struct ksz_device *dev); int ksz8_switch_init(struct ksz_device *dev); void ksz8_switch_exit(struct ksz_device *dev); int ksz8_change_mtu(struct ksz_device *dev, int port, int mtu); +int ksz8_pme_write8(struct ksz_device *dev, u32 reg, u8 value); +int ksz8_pme_pread8(struct ksz_device *dev, int port, int offset, u8 *data); +int ksz8_pme_pwrite8(struct ksz_device *dev, int port, int offset, u8 data); void ksz8_phylink_mac_link_up(struct phylink_config *config, struct phy_device *phydev, unsigned int mode, phy_interface_t interface, int speed, int duplex, diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c index d27b9c36d73f..aa09d89debf0 100644 --- a/drivers/net/dsa/microchip/ksz8795.c +++ b/drivers/net/dsa/microchip/ksz8795.c @@ -38,6 +38,20 @@ static void ksz_port_cfg(struct ksz_device *dev, int port, int offset, u8 bits, bits, set ? bits : 0); } +/** + * ksz8_ind_write8 - EEE/ACL/PME indirect register write + * @dev: The device structure. + * @table: Function & table select, register 110. + * @addr: Indirect access control, register 111. + * @data: The data to be written. + * + * This function performs an indirect register write for EEE, ACL or + * PME switch functionalities. Both 8-bit registers 110 and 111 are + * written at once with ksz_write16, using the serial multiple write + * functionality. + * + * Return: 0 on success, or an error code on failure. + */ static int ksz8_ind_write8(struct ksz_device *dev, u8 table, u16 addr, u8 data) { const u16 *regs; @@ -58,6 +72,59 @@ static int ksz8_ind_write8(struct ksz_device *dev, u8 table, u16 addr, u8 data) return ret; } +/** + * ksz8_ind_read8 - EEE/ACL/PME indirect register read + * @dev: The device structure. + * @table: Function & table select, register 110. + * @addr: Indirect access control, register 111. + * @val: The value read. + * + * This function performs an indirect register read for EEE, ACL or + * PME switch functionalities. Both 8-bit registers 110 and 111 are + * written at once with ksz_write16, using the serial multiple write + * functionality. + * + * Return: 0 on success, or an error code on failure. + */ +static int ksz8_ind_read8(struct ksz_device *dev, u8 table, u16 addr, u8 *val) +{ + const u16 *regs; + u16 ctrl_addr; + int ret = 0; + + regs = dev->info->regs; + + mutex_lock(&dev->alu_mutex); + + ctrl_addr = IND_ACC_TABLE(table | TABLE_READ) | addr; + ret = ksz_write16(dev, regs[REG_IND_CTRL_0], ctrl_addr); + if (!ret) + ret = ksz_read8(dev, regs[REG_IND_BYTE], val); + + mutex_unlock(&dev->alu_mutex); + + return ret; +} + +int ksz8_pme_write8(struct ksz_device *dev, u32 reg, u8 value) +{ + return ksz8_ind_write8(dev, (u8)(reg >> 8), (u8)(reg), value); +} + +int ksz8_pme_pread8(struct ksz_device *dev, int port, int offset, u8 *data) +{ + u8 table = (u8)(offset >> 8 | (port + 1)); + + return ksz8_ind_read8(dev, table, (u8)(offset), data); +} + +int ksz8_pme_pwrite8(struct ksz_device *dev, int port, int offset, u8 data) +{ + u8 table = (u8)(offset >> 8 | (port + 1)); + + return ksz8_ind_write8(dev, table, (u8)(offset), data); +} + int ksz8_reset_switch(struct ksz_device *dev) { if (ksz_is_ksz88x3(dev)) { @@ -121,6 +188,8 @@ int ksz8_change_mtu(struct ksz_device *dev, int port, int mtu) case KSZ8765_CHIP_ID: return ksz8795_change_mtu(dev, frame_size); case KSZ8830_CHIP_ID: + case KSZ8864_CHIP_ID: + case KSZ8895_CHIP_ID: return ksz8863_change_mtu(dev, frame_size); } @@ -317,7 +386,7 @@ static void ksz8863_r_mib_pkt(struct ksz_device *dev, int port, u16 addr, void ksz8_r_mib_pkt(struct ksz_device *dev, int port, u16 addr, u64 *dropped, u64 *cnt) { - if (ksz_is_ksz88x3(dev)) + if (is_ksz88xx(dev)) ksz8863_r_mib_pkt(dev, port, addr, dropped, cnt); else ksz8795_r_mib_pkt(dev, port, addr, dropped, cnt); @@ -325,7 +394,7 @@ void ksz8_r_mib_pkt(struct ksz_device *dev, int port, u16 addr, void ksz8_freeze_mib(struct ksz_device *dev, int port, bool freeze) { - if (ksz_is_ksz88x3(dev)) + if (is_ksz88xx(dev)) return; /* enable the port for flush/freeze function */ @@ -343,7 +412,8 @@ void ksz8_port_init_cnt(struct ksz_device *dev, int port) struct ksz_port_mib *mib = &dev->ports[port].mib; u64 *dropped; - if (!ksz_is_ksz88x3(dev)) { + /* For KSZ8795 family. */ + if (ksz_is_ksz87xx(dev)) { /* flush all enabled port MIB counters */ ksz_cfg(dev, REG_SW_CTRL_6, BIT(port), true); ksz_cfg(dev, REG_SW_CTRL_6, SW_MIB_COUNTER_FLUSH, true); @@ -542,11 +612,11 @@ static int ksz8_r_sta_mac_table(struct ksz_device *dev, u16 addr, shifts[STATIC_MAC_FWD_PORTS]; alu->is_override = (data_hi & masks[STATIC_MAC_TABLE_OVERRIDE]) ? 1 : 0; - /* KSZ8795 family switches have STATIC_MAC_TABLE_USE_FID and + /* KSZ8795/KSZ8895 family switches have STATIC_MAC_TABLE_USE_FID and * STATIC_MAC_TABLE_FID definitions off by 1 when doing read on the * static MAC table compared to doing write. */ - if (ksz_is_ksz87xx(dev)) + if (ksz_is_ksz87xx(dev) || ksz_is_8895_family(dev)) data_hi >>= 1; alu->is_static = true; alu->is_use_fid = (data_hi & masks[STATIC_MAC_TABLE_USE_FID]) ? 1 : 0; @@ -1545,6 +1615,7 @@ static void ksz8795_cpu_interface_select(struct ksz_device *dev, int port) void ksz8_port_setup(struct ksz_device *dev, int port, bool cpu_port) { + const u16 *regs = dev->info->regs; struct dsa_switch *ds = dev->ds; const u32 *masks; int queues; @@ -1575,6 +1646,13 @@ void ksz8_port_setup(struct ksz_device *dev, int port, bool cpu_port) member = BIT(dsa_upstream_port(ds, port)); ksz8_cfg_port_member(dev, port, member); + + /* Disable all WoL options by default. Otherwise + * ksz_switch_macaddr_get/put logic will not work properly. + * CPU port 4 has no WoL functionality. + */ + if (ksz_is_ksz87xx(dev) && !cpu_port) + ksz8_pme_pwrite8(dev, port, regs[REG_PORT_PME_CTRL], 0); } static void ksz88x3_config_rmii_clk(struct ksz_device *dev) @@ -1617,7 +1695,8 @@ void ksz8_config_cpu_port(struct dsa_switch *ds) for (i = 0; i < dev->phy_port_cnt; i++) { p = &dev->ports[i]; - if (!ksz_is_ksz88x3(dev)) { + /* For KSZ8795 family. */ + if (ksz_is_ksz87xx(dev)) { ksz_pread8(dev, i, regs[P_REMOTE_STATUS], &remote); if (remote & KSZ8_PORT_FIBER_MODE) p->fiber = 1; @@ -1790,7 +1869,8 @@ int ksz8_enable_stp_addr(struct ksz_device *dev) int ksz8_setup(struct dsa_switch *ds) { struct ksz_device *dev = ds->priv; - int i; + const u16 *regs = dev->info->regs; + int i, ret = 0; ds->mtu_enforcement_ingress = true; @@ -1829,7 +1909,21 @@ int ksz8_setup(struct dsa_switch *ds) for (i = 0; i < (dev->info->num_vlans / 4); i++) ksz8_r_vlan_entries(dev, i); - return ksz8_handle_global_errata(ds); + /* Make sure PME (WoL) is not enabled. If requested, it will + * be enabled by ksz_wol_pre_shutdown(). Otherwise, some PMICs + * do not like PME events changes before shutdown. PME only + * available on KSZ87xx family. + */ + if (ksz_is_ksz87xx(dev)) { + ret = ksz8_pme_write8(dev, regs[REG_SW_PME_CTRL], 0); + if (!ret) + ret = ksz_rmw8(dev, REG_INT_ENABLE, INT_PME, 0); + } + + if (!ret) + return ksz8_handle_global_errata(ds); + else + return ret; } void ksz8_get_caps(struct ksz_device *dev, int port, diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c index 425e20daf1e9..0ba658a72d8f 100644 --- a/drivers/net/dsa/microchip/ksz9477.c +++ b/drivers/net/dsa/microchip/ksz9477.c @@ -56,187 +56,6 @@ int ksz9477_change_mtu(struct ksz_device *dev, int port, int mtu) REG_SW_MTU_MASK, frame_size); } -/** - * ksz9477_handle_wake_reason - Handle wake reason on a specified port. - * @dev: The device structure. - * @port: The port number. - * - * This function reads the PME (Power Management Event) status register of a - * specified port to determine the wake reason. If there is no wake event, it - * returns early. Otherwise, it logs the wake reason which could be due to a - * "Magic Packet", "Link Up", or "Energy Detect" event. The PME status register - * is then cleared to acknowledge the handling of the wake event. - * - * Return: 0 on success, or an error code on failure. - */ -static int ksz9477_handle_wake_reason(struct ksz_device *dev, int port) -{ - u8 pme_status; - int ret; - - ret = ksz_pread8(dev, port, REG_PORT_PME_STATUS, &pme_status); - if (ret) - return ret; - - if (!pme_status) - return 0; - - dev_dbg(dev->dev, "Wake event on port %d due to:%s%s%s\n", port, - pme_status & PME_WOL_MAGICPKT ? " \"Magic Packet\"" : "", - pme_status & PME_WOL_LINKUP ? " \"Link Up\"" : "", - pme_status & PME_WOL_ENERGY ? " \"Energy detect\"" : ""); - - return ksz_pwrite8(dev, port, REG_PORT_PME_STATUS, pme_status); -} - -/** - * ksz9477_get_wol - Get Wake-on-LAN settings for a specified port. - * @dev: The device structure. - * @port: The port number. - * @wol: Pointer to ethtool Wake-on-LAN settings structure. - * - * This function checks the PME Pin Control Register to see if PME Pin Output - * Enable is set, indicating PME is enabled. If enabled, it sets the supported - * and active WoL flags. - */ -void ksz9477_get_wol(struct ksz_device *dev, int port, - struct ethtool_wolinfo *wol) -{ - u8 pme_ctrl; - int ret; - - if (!dev->wakeup_source) - return; - - wol->supported = WAKE_PHY; - - /* Check if the current MAC address on this port can be set - * as global for WAKE_MAGIC support. The result may vary - * dynamically based on other ports configurations. - */ - if (ksz_is_port_mac_global_usable(dev->ds, port)) - wol->supported |= WAKE_MAGIC; - - ret = ksz_pread8(dev, port, REG_PORT_PME_CTRL, &pme_ctrl); - if (ret) - return; - - if (pme_ctrl & PME_WOL_MAGICPKT) - wol->wolopts |= WAKE_MAGIC; - if (pme_ctrl & (PME_WOL_LINKUP | PME_WOL_ENERGY)) - wol->wolopts |= WAKE_PHY; -} - -/** - * ksz9477_set_wol - Set Wake-on-LAN settings for a specified port. - * @dev: The device structure. - * @port: The port number. - * @wol: Pointer to ethtool Wake-on-LAN settings structure. - * - * This function configures Wake-on-LAN (WoL) settings for a specified port. - * It validates the provided WoL options, checks if PME is enabled via the - * switch's PME Pin Control Register, clears any previous wake reasons, - * and sets the Magic Packet flag in the port's PME control register if - * specified. - * - * Return: 0 on success, or other error codes on failure. - */ -int ksz9477_set_wol(struct ksz_device *dev, int port, - struct ethtool_wolinfo *wol) -{ - u8 pme_ctrl = 0, pme_ctrl_old = 0; - bool magic_switched_off; - bool magic_switched_on; - int ret; - - if (wol->wolopts & ~(WAKE_PHY | WAKE_MAGIC)) - return -EINVAL; - - if (!dev->wakeup_source) - return -EOPNOTSUPP; - - ret = ksz9477_handle_wake_reason(dev, port); - if (ret) - return ret; - - if (wol->wolopts & WAKE_MAGIC) - pme_ctrl |= PME_WOL_MAGICPKT; - if (wol->wolopts & WAKE_PHY) - pme_ctrl |= PME_WOL_LINKUP | PME_WOL_ENERGY; - - ret = ksz_pread8(dev, port, REG_PORT_PME_CTRL, &pme_ctrl_old); - if (ret) - return ret; - - if (pme_ctrl_old == pme_ctrl) - return 0; - - magic_switched_off = (pme_ctrl_old & PME_WOL_MAGICPKT) && - !(pme_ctrl & PME_WOL_MAGICPKT); - magic_switched_on = !(pme_ctrl_old & PME_WOL_MAGICPKT) && - (pme_ctrl & PME_WOL_MAGICPKT); - - /* To keep reference count of MAC address, we should do this - * operation only on change of WOL settings. - */ - if (magic_switched_on) { - ret = ksz_switch_macaddr_get(dev->ds, port, NULL); - if (ret) - return ret; - } else if (magic_switched_off) { - ksz_switch_macaddr_put(dev->ds); - } - - ret = ksz_pwrite8(dev, port, REG_PORT_PME_CTRL, pme_ctrl); - if (ret) { - if (magic_switched_on) - ksz_switch_macaddr_put(dev->ds); - return ret; - } - - return 0; -} - -/** - * ksz9477_wol_pre_shutdown - Prepares the switch device for shutdown while - * considering Wake-on-LAN (WoL) settings. - * @dev: The switch device structure. - * @wol_enabled: Pointer to a boolean which will be set to true if WoL is - * enabled on any port. - * - * This function prepares the switch device for a safe shutdown while taking - * into account the Wake-on-LAN (WoL) settings on the user ports. It updates - * the wol_enabled flag accordingly to reflect whether WoL is active on any - * port. - */ -void ksz9477_wol_pre_shutdown(struct ksz_device *dev, bool *wol_enabled) -{ - struct dsa_port *dp; - int ret; - - *wol_enabled = false; - - if (!dev->wakeup_source) - return; - - dsa_switch_for_each_user_port(dp, dev->ds) { - u8 pme_ctrl = 0; - - ret = ksz_pread8(dev, dp->index, REG_PORT_PME_CTRL, &pme_ctrl); - if (!ret && pme_ctrl) - *wol_enabled = true; - - /* make sure there are no pending wake events which would - * prevent the device from going to sleep/shutdown. - */ - ksz9477_handle_wake_reason(dev, dp->index); - } - - /* Now we are save to enable PME pin. */ - if (*wol_enabled) - ksz_write8(dev, REG_SW_PME_CTRL, PME_ENABLE); -} - static int ksz9477_wait_vlan_ctrl_ready(struct ksz_device *dev) { unsigned int val; @@ -427,54 +246,70 @@ void ksz9477_freeze_mib(struct ksz_device *dev, int port, bool freeze) mutex_unlock(&p->mib.cnt_mutex); } -int ksz9477_errata_monitor(struct ksz_device *dev, int port, - u64 tx_late_col) +static int ksz9477_half_duplex_monitor(struct ksz_device *dev, int port, + u64 tx_late_col) { + u8 lue_ctrl; u32 pmavbc; - u8 status; u16 pqm; int ret; - ret = ksz_pread8(dev, port, REG_PORT_STATUS_0, &status); + /* Errata DS80000754 recommends monitoring potential faults in + * half-duplex mode. The switch might not be able to communicate anymore + * in these states. If you see this message, please read the + * errata-sheet for more information: + * https://ww1.microchip.com/downloads/aemDocuments/documents/UNG/ProductDocuments/Errata/KSZ9477S-Errata-DS80000754.pdf + * To workaround this issue, half-duplex mode should be avoided. + * A software reset could be implemented to recover from this state. + */ + dev_warn_once(dev->dev, + "Half-duplex detected on port %d, transmission halt may occur\n", + port); + if (tx_late_col != 0) { + /* Transmission halt with late collisions */ + dev_crit_once(dev->dev, + "TX late collisions detected, transmission may be halted on port %d\n", + port); + } + ret = ksz_read8(dev, REG_SW_LUE_CTRL_0, &lue_ctrl); if (ret) return ret; - if (!(FIELD_GET(PORT_INTF_SPEED_MASK, status) == PORT_INTF_SPEED_NONE) && - !(status & PORT_INTF_FULL_DUPLEX)) { - /* Errata DS80000754 recommends monitoring potential faults in - * half-duplex mode. The switch might not be able to communicate anymore - * in these states. - * If you see this message, please read the errata-sheet for more information: - * https://ww1.microchip.com/downloads/aemDocuments/documents/UNG/ProductDocuments/Errata/KSZ9477S-Errata-DS80000754.pdf - * To workaround this issue, half-duplex mode should be avoided. - * A software reset could be implemented to recover from this state. - */ - dev_warn_once(dev->dev, - "Half-duplex detected on port %d, transmission halt may occur\n", - port); - if (tx_late_col != 0) { - /* Transmission halt with late collisions */ - dev_crit_once(dev->dev, - "TX late collisions detected, transmission may be halted on port %d\n", - port); - } - ret = ksz_read8(dev, REG_SW_LUE_CTRL_0, &status); + if (lue_ctrl & SW_VLAN_ENABLE) { + ret = ksz_pread16(dev, port, REG_PORT_QM_TX_CNT_0__4, &pqm); if (ret) return ret; - if (status & SW_VLAN_ENABLE) { - ret = ksz_pread16(dev, port, REG_PORT_QM_TX_CNT_0__4, &pqm); - if (ret) - return ret; - ret = ksz_read32(dev, REG_PMAVBC, &pmavbc); - if (ret) - return ret; - if ((FIELD_GET(PMAVBC_MASK, pmavbc) <= PMAVBC_MIN) || - (FIELD_GET(PORT_QM_TX_CNT_M, pqm) >= PORT_QM_TX_CNT_MAX)) { - /* Transmission halt with Half-Duplex and VLAN */ - dev_crit_once(dev->dev, - "resources out of limits, transmission may be halted\n"); - } + + ret = ksz_read32(dev, REG_PMAVBC, &pmavbc); + if (ret) + return ret; + + if ((FIELD_GET(PMAVBC_MASK, pmavbc) <= PMAVBC_MIN) || + (FIELD_GET(PORT_QM_TX_CNT_M, pqm) >= PORT_QM_TX_CNT_MAX)) { + /* Transmission halt with Half-Duplex and VLAN */ + dev_crit_once(dev->dev, + "resources out of limits, transmission may be halted\n"); } } + + return ret; +} + +int ksz9477_errata_monitor(struct ksz_device *dev, int port, + u64 tx_late_col) +{ + u8 status; + int ret; + + ret = ksz_pread8(dev, port, REG_PORT_STATUS_0, &status); + if (ret) + return ret; + + if (!(FIELD_GET(PORT_INTF_SPEED_MASK, status) + == PORT_INTF_SPEED_NONE) && + !(status & PORT_INTF_FULL_DUPLEX)) { + ret = ksz9477_half_duplex_monitor(dev, port, tx_late_col); + } + return ret; } @@ -1188,6 +1023,7 @@ void ksz9477_port_queue_split(struct ksz_device *dev, int port) void ksz9477_port_setup(struct ksz_device *dev, int port, bool cpu_port) { + const u16 *regs = dev->info->regs; struct dsa_switch *ds = dev->ds; u16 data16; u8 member; @@ -1232,12 +1068,12 @@ void ksz9477_port_setup(struct ksz_device *dev, int port, bool cpu_port) ksz9477_port_acl_init(dev, port); /* clear pending wake flags */ - ksz9477_handle_wake_reason(dev, port); + ksz_handle_wake_reason(dev, port); /* Disable all WoL options by default. Otherwise * ksz_switch_macaddr_get/put logic will not work properly. */ - ksz_pwrite8(dev, port, REG_PORT_PME_CTRL, 0); + ksz_pwrite8(dev, port, regs[REG_PORT_PME_CTRL], 0); } void ksz9477_config_cpu_port(struct dsa_switch *ds) @@ -1334,6 +1170,7 @@ int ksz9477_enable_stp_addr(struct ksz_device *dev) int ksz9477_setup(struct dsa_switch *ds) { struct ksz_device *dev = ds->priv; + const u16 *regs = dev->info->regs; int ret = 0; ds->mtu_enforcement_ingress = true; @@ -1364,13 +1201,11 @@ int ksz9477_setup(struct dsa_switch *ds) /* enable global MIB counter freeze function */ ksz_cfg(dev, REG_SW_MAC_CTRL_6, SW_MIB_COUNTER_FREEZE, true); - /* Make sure PME (WoL) is not enabled. If requested, it will be - * enabled by ksz9477_wol_pre_shutdown(). Otherwise, some PMICs do not - * like PME events changes before shutdown. + /* Make sure PME (WoL) is not enabled. If requested, it will + * be enabled by ksz_wol_pre_shutdown(). Otherwise, some PMICs + * do not like PME events changes before shutdown. */ - ksz_write8(dev, REG_SW_PME_CTRL, 0); - - return 0; + return ksz_write8(dev, regs[REG_SW_PME_CTRL], 0); } u32 ksz9477_get_port_addr(int port, int offset) diff --git a/drivers/net/dsa/microchip/ksz9477.h b/drivers/net/dsa/microchip/ksz9477.h index 239a281da10b..d2166b0d881e 100644 --- a/drivers/net/dsa/microchip/ksz9477.h +++ b/drivers/net/dsa/microchip/ksz9477.h @@ -60,11 +60,6 @@ void ksz9477_switch_exit(struct ksz_device *dev); void ksz9477_port_queue_split(struct ksz_device *dev, int port); void ksz9477_hsr_join(struct dsa_switch *ds, int port, struct net_device *hsr); void ksz9477_hsr_leave(struct dsa_switch *ds, int port, struct net_device *hsr); -void ksz9477_get_wol(struct ksz_device *dev, int port, - struct ethtool_wolinfo *wol); -int ksz9477_set_wol(struct ksz_device *dev, int port, - struct ethtool_wolinfo *wol); -void ksz9477_wol_pre_shutdown(struct ksz_device *dev, bool *wol_enabled); int ksz9477_port_acl_init(struct ksz_device *dev, int port); void ksz9477_port_acl_free(struct ksz_device *dev, int port); diff --git a/drivers/net/dsa/microchip/ksz9477_reg.h b/drivers/net/dsa/microchip/ksz9477_reg.h index d5354c600ea1..04235c22bf40 100644 --- a/drivers/net/dsa/microchip/ksz9477_reg.h +++ b/drivers/net/dsa/microchip/ksz9477_reg.h @@ -38,11 +38,6 @@ #define SWITCH_REVISION_S 4 #define SWITCH_RESET 0x01 -#define REG_SW_PME_CTRL 0x0006 - -#define PME_ENABLE BIT(1) -#define PME_POLARITY BIT(0) - #define REG_GLOBAL_OPTIONS 0x000F #define SW_GIGABIT_ABLE BIT(6) @@ -807,13 +802,6 @@ #define REG_PORT_AVB_SR_1_TYPE 0x0008 #define REG_PORT_AVB_SR_2_TYPE 0x000A -#define REG_PORT_PME_STATUS 0x0013 -#define REG_PORT_PME_CTRL 0x0017 - -#define PME_WOL_MAGICPKT BIT(2) -#define PME_WOL_LINKUP BIT(1) -#define PME_WOL_ENERGY BIT(0) - #define REG_PORT_INT_STATUS 0x001B #define REG_PORT_INT_MASK 0x001F diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 1491099528be..6609bf271ad0 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -2,7 +2,7 @@ /* * Microchip switch driver main logic * - * Copyright (C) 2017-2019 Microchip Technology Inc. + * Copyright (C) 2017-2024 Microchip Technology Inc. */ #include <linux/delay.h> @@ -277,7 +277,7 @@ static const struct phylink_mac_ops ksz8_phylink_mac_ops = { .mac_link_up = ksz8_phylink_mac_link_up, }; -static const struct ksz_dev_ops ksz8_dev_ops = { +static const struct ksz_dev_ops ksz88xx_dev_ops = { .setup = ksz8_setup, .get_port_addr = ksz8_get_port_addr, .cfg_port_member = ksz8_cfg_port_member, @@ -307,6 +307,44 @@ static const struct ksz_dev_ops ksz8_dev_ops = { .init = ksz8_switch_init, .exit = ksz8_switch_exit, .change_mtu = ksz8_change_mtu, + .pme_write8 = ksz8_pme_write8, + .pme_pread8 = ksz8_pme_pread8, + .pme_pwrite8 = ksz8_pme_pwrite8, +}; + +static const struct ksz_dev_ops ksz87xx_dev_ops = { + .setup = ksz8_setup, + .get_port_addr = ksz8_get_port_addr, + .cfg_port_member = ksz8_cfg_port_member, + .flush_dyn_mac_table = ksz8_flush_dyn_mac_table, + .port_setup = ksz8_port_setup, + .r_phy = ksz8_r_phy, + .w_phy = ksz8_w_phy, + .r_mib_cnt = ksz8_r_mib_cnt, + .r_mib_pkt = ksz8_r_mib_pkt, + .r_mib_stat64 = ksz_r_mib_stats64, + .freeze_mib = ksz8_freeze_mib, + .port_init_cnt = ksz8_port_init_cnt, + .fdb_dump = ksz8_fdb_dump, + .fdb_add = ksz8_fdb_add, + .fdb_del = ksz8_fdb_del, + .mdb_add = ksz8_mdb_add, + .mdb_del = ksz8_mdb_del, + .vlan_filtering = ksz8_port_vlan_filtering, + .vlan_add = ksz8_port_vlan_add, + .vlan_del = ksz8_port_vlan_del, + .mirror_add = ksz8_port_mirror_add, + .mirror_del = ksz8_port_mirror_del, + .get_caps = ksz8_get_caps, + .config_cpu_port = ksz8_config_cpu_port, + .enable_stp_addr = ksz8_enable_stp_addr, + .reset = ksz8_reset_switch, + .init = ksz8_switch_init, + .exit = ksz8_switch_exit, + .change_mtu = ksz8_change_mtu, + .pme_write8 = ksz8_pme_write8, + .pme_pread8 = ksz8_pme_pread8, + .pme_pwrite8 = ksz8_pme_pwrite8, }; static void ksz9477_phylink_mac_link_up(struct phylink_config *config, @@ -348,9 +386,9 @@ static const struct ksz_dev_ops ksz9477_dev_ops = { .mdb_add = ksz9477_mdb_add, .mdb_del = ksz9477_mdb_del, .change_mtu = ksz9477_change_mtu, - .get_wol = ksz9477_get_wol, - .set_wol = ksz9477_set_wol, - .wol_pre_shutdown = ksz9477_wol_pre_shutdown, + .pme_write8 = ksz_write8, + .pme_pread8 = ksz_pread8, + .pme_pwrite8 = ksz_pwrite8, .config_cpu_port = ksz9477_config_cpu_port, .tc_cbs_set_cinc = ksz9477_tc_cbs_set_cinc, .enable_stp_addr = ksz9477_enable_stp_addr, @@ -423,6 +461,9 @@ static const u16 ksz8795_regs[] = { [S_MULTICAST_CTRL] = 0x04, [P_XMII_CTRL_0] = 0x06, [P_XMII_CTRL_1] = 0x06, + [REG_SW_PME_CTRL] = 0x8003, + [REG_PORT_PME_STATUS] = 0x8003, + [REG_PORT_PME_CTRL] = 0x8007, }; static const u32 ksz8795_masks[] = { @@ -531,6 +572,61 @@ static u8 ksz8863_shifts[] = { [DYNAMIC_MAC_SRC_PORT] = 20, }; +static const u16 ksz8895_regs[] = { + [REG_SW_MAC_ADDR] = 0x68, + [REG_IND_CTRL_0] = 0x6E, + [REG_IND_DATA_8] = 0x70, + [REG_IND_DATA_CHECK] = 0x72, + [REG_IND_DATA_HI] = 0x71, + [REG_IND_DATA_LO] = 0x75, + [REG_IND_MIB_CHECK] = 0x75, + [P_FORCE_CTRL] = 0x0C, + [P_LINK_STATUS] = 0x0E, + [P_LOCAL_CTRL] = 0x0C, + [P_NEG_RESTART_CTRL] = 0x0D, + [P_REMOTE_STATUS] = 0x0E, + [P_SPEED_STATUS] = 0x09, + [S_TAIL_TAG_CTRL] = 0x0C, + [P_STP_CTRL] = 0x02, + [S_START_CTRL] = 0x01, + [S_BROADCAST_CTRL] = 0x06, + [S_MULTICAST_CTRL] = 0x04, +}; + +static const u32 ksz8895_masks[] = { + [PORT_802_1P_REMAPPING] = BIT(7), + [SW_TAIL_TAG_ENABLE] = BIT(1), + [MIB_COUNTER_OVERFLOW] = BIT(7), + [MIB_COUNTER_VALID] = BIT(6), + [VLAN_TABLE_FID] = GENMASK(6, 0), + [VLAN_TABLE_MEMBERSHIP] = GENMASK(11, 7), + [VLAN_TABLE_VALID] = BIT(12), + [STATIC_MAC_TABLE_VALID] = BIT(21), + [STATIC_MAC_TABLE_USE_FID] = BIT(23), + [STATIC_MAC_TABLE_FID] = GENMASK(30, 24), + [STATIC_MAC_TABLE_OVERRIDE] = BIT(22), + [STATIC_MAC_TABLE_FWD_PORTS] = GENMASK(20, 16), + [DYNAMIC_MAC_TABLE_ENTRIES_H] = GENMASK(6, 0), + [DYNAMIC_MAC_TABLE_MAC_EMPTY] = BIT(7), + [DYNAMIC_MAC_TABLE_NOT_READY] = BIT(7), + [DYNAMIC_MAC_TABLE_ENTRIES] = GENMASK(31, 29), + [DYNAMIC_MAC_TABLE_FID] = GENMASK(22, 16), + [DYNAMIC_MAC_TABLE_SRC_PORT] = GENMASK(26, 24), + [DYNAMIC_MAC_TABLE_TIMESTAMP] = GENMASK(28, 27), +}; + +static const u8 ksz8895_shifts[] = { + [VLAN_TABLE_MEMBERSHIP_S] = 7, + [VLAN_TABLE] = 13, + [STATIC_MAC_FWD_PORTS] = 16, + [STATIC_MAC_FID] = 24, + [DYNAMIC_MAC_ENTRIES_H] = 3, + [DYNAMIC_MAC_ENTRIES] = 29, + [DYNAMIC_MAC_FID] = 16, + [DYNAMIC_MAC_TIMESTAMP] = 27, + [DYNAMIC_MAC_SRC_PORT] = 24, +}; + static const u16 ksz9477_regs[] = { [REG_SW_MAC_ADDR] = 0x0302, [P_STP_CTRL] = 0x0B04, @@ -539,6 +635,9 @@ static const u16 ksz9477_regs[] = { [S_MULTICAST_CTRL] = 0x0331, [P_XMII_CTRL_0] = 0x0300, [P_XMII_CTRL_1] = 0x0301, + [REG_SW_PME_CTRL] = 0x0006, + [REG_PORT_PME_STATUS] = 0x0013, + [REG_PORT_PME_CTRL] = 0x0017, }; static const u32 ksz9477_masks[] = { @@ -1253,12 +1352,12 @@ const struct ksz_chip_data ksz_switch_chips[] = { .dev_name = "KSZ8795", .num_vlans = 4096, .num_alus = 0, - .num_statics = 8, + .num_statics = 32, .cpu_ports = 0x10, /* can be configured as cpu port */ .port_cnt = 5, /* total cpu and user ports */ .num_tx_queues = 4, .num_ipms = 4, - .ops = &ksz8_dev_ops, + .ops = &ksz87xx_dev_ops, .phylink_mac_ops = &ksz8_phylink_mac_ops, .ksz87xx_eee_link_erratum = true, .mib_names = ksz9477_mib_names, @@ -1294,12 +1393,12 @@ const struct ksz_chip_data ksz_switch_chips[] = { .dev_name = "KSZ8794", .num_vlans = 4096, .num_alus = 0, - .num_statics = 8, + .num_statics = 32, .cpu_ports = 0x10, /* can be configured as cpu port */ .port_cnt = 5, /* total cpu and user ports */ .num_tx_queues = 4, .num_ipms = 4, - .ops = &ksz8_dev_ops, + .ops = &ksz87xx_dev_ops, .phylink_mac_ops = &ksz8_phylink_mac_ops, .ksz87xx_eee_link_erratum = true, .mib_names = ksz9477_mib_names, @@ -1321,12 +1420,12 @@ const struct ksz_chip_data ksz_switch_chips[] = { .dev_name = "KSZ8765", .num_vlans = 4096, .num_alus = 0, - .num_statics = 8, + .num_statics = 32, .cpu_ports = 0x10, /* can be configured as cpu port */ .port_cnt = 5, /* total cpu and user ports */ .num_tx_queues = 4, .num_ipms = 4, - .ops = &ksz8_dev_ops, + .ops = &ksz87xx_dev_ops, .phylink_mac_ops = &ksz8_phylink_mac_ops, .ksz87xx_eee_link_erratum = true, .mib_names = ksz9477_mib_names, @@ -1353,7 +1452,7 @@ const struct ksz_chip_data ksz_switch_chips[] = { .port_cnt = 3, .num_tx_queues = 4, .num_ipms = 4, - .ops = &ksz8_dev_ops, + .ops = &ksz88xx_dev_ops, .phylink_mac_ops = &ksz8830_phylink_mac_ops, .mib_names = ksz88xx_mib_names, .mib_cnt = ARRAY_SIZE(ksz88xx_mib_names), @@ -1368,6 +1467,61 @@ const struct ksz_chip_data ksz_switch_chips[] = { .rd_table = &ksz8873_register_set, }, + [KSZ8864] = { + /* WARNING + * ======= + * KSZ8864 is similar to KSZ8895, except the first port + * does not exist. + * external cpu + * KSZ8864 1,2,3 4 + * KSZ8895 0,1,2,3 4 + * port_cnt is configured as 5, even though it is 4 + */ + .chip_id = KSZ8864_CHIP_ID, + .dev_name = "KSZ8864", + .num_vlans = 4096, + .num_alus = 0, + .num_statics = 32, + .cpu_ports = 0x10, /* can be configured as cpu port */ + .port_cnt = 5, /* total cpu and user ports */ + .num_tx_queues = 4, + .num_ipms = 4, + .ops = &ksz88xx_dev_ops, + .phylink_mac_ops = &ksz8830_phylink_mac_ops, + .mib_names = ksz88xx_mib_names, + .mib_cnt = ARRAY_SIZE(ksz88xx_mib_names), + .reg_mib_cnt = MIB_COUNTER_NUM, + .regs = ksz8895_regs, + .masks = ksz8895_masks, + .shifts = ksz8895_shifts, + .supports_mii = {false, false, false, false, true}, + .supports_rmii = {false, false, false, false, true}, + .internal_phy = {false, true, true, true, false}, + }, + + [KSZ8895] = { + .chip_id = KSZ8895_CHIP_ID, + .dev_name = "KSZ8895", + .num_vlans = 4096, + .num_alus = 0, + .num_statics = 32, + .cpu_ports = 0x10, /* can be configured as cpu port */ + .port_cnt = 5, /* total cpu and user ports */ + .num_tx_queues = 4, + .num_ipms = 4, + .ops = &ksz88xx_dev_ops, + .phylink_mac_ops = &ksz8830_phylink_mac_ops, + .mib_names = ksz88xx_mib_names, + .mib_cnt = ARRAY_SIZE(ksz88xx_mib_names), + .reg_mib_cnt = MIB_COUNTER_NUM, + .regs = ksz8895_regs, + .masks = ksz8895_masks, + .shifts = ksz8895_shifts, + .supports_mii = {false, false, false, false, true}, + .supports_rmii = {false, false, false, false, true}, + .internal_phy = {true, true, true, true, false}, + }, + [KSZ9477] = { .chip_id = KSZ9477_CHIP_ID, .dev_name = "KSZ9477", @@ -2893,9 +3047,7 @@ static enum dsa_tag_protocol ksz_get_tag_protocol(struct dsa_switch *ds, struct ksz_device *dev = ds->priv; enum dsa_tag_protocol proto = DSA_TAG_PROTO_NONE; - if (dev->chip_id == KSZ8795_CHIP_ID || - dev->chip_id == KSZ8794_CHIP_ID || - dev->chip_id == KSZ8765_CHIP_ID) + if (ksz_is_ksz87xx(dev) || ksz_is_8895_family(dev)) proto = DSA_TAG_PROTO_KSZ8795; if (dev->chip_id == KSZ8830_CHIP_ID || @@ -3011,6 +3163,8 @@ static int ksz_max_mtu(struct dsa_switch *ds, int port) case KSZ8765_CHIP_ID: return KSZ8795_HUGE_PACKET_SIZE - VLAN_ETH_HLEN - ETH_FCS_LEN; case KSZ8830_CHIP_ID: + case KSZ8864_CHIP_ID: + case KSZ8895_CHIP_ID: return KSZ8863_HUGE_PACKET_SIZE - VLAN_ETH_HLEN - ETH_FCS_LEN; case KSZ8563_CHIP_ID: case KSZ8567_CHIP_ID: @@ -3368,6 +3522,18 @@ static int ksz_switch_detect(struct ksz_device *dev) else return -ENODEV; break; + case KSZ8895_FAMILY_ID: + if (id2 == KSZ8895_CHIP_ID_95 || + id2 == KSZ8895_CHIP_ID_95R) + dev->chip_id = KSZ8895_CHIP_ID; + else + return -ENODEV; + ret = ksz_read8(dev, REG_KSZ8864_CHIP_ID, &id4); + if (ret) + return ret; + if (id4 & SW_KSZ8864) + dev->chip_id = KSZ8864_CHIP_ID; + break; default: ret = ksz_read32(dev, REG_CHIP_ID0, &id32); if (ret) @@ -3742,24 +3908,214 @@ static int ksz_setup_tc(struct dsa_switch *ds, int port, } } +/** + * ksz_handle_wake_reason - Handle wake reason on a specified port. + * @dev: The device structure. + * @port: The port number. + * + * This function reads the PME (Power Management Event) status register of a + * specified port to determine the wake reason. If there is no wake event, it + * returns early. Otherwise, it logs the wake reason which could be due to a + * "Magic Packet", "Link Up", or "Energy Detect" event. The PME status register + * is then cleared to acknowledge the handling of the wake event. + * + * Return: 0 on success, or an error code on failure. + */ +int ksz_handle_wake_reason(struct ksz_device *dev, int port) +{ + const struct ksz_dev_ops *ops = dev->dev_ops; + const u16 *regs = dev->info->regs; + u8 pme_status; + int ret; + + ret = ops->pme_pread8(dev, port, regs[REG_PORT_PME_STATUS], + &pme_status); + if (ret) + return ret; + + if (!pme_status) + return 0; + + dev_dbg(dev->dev, "Wake event on port %d due to:%s%s%s\n", port, + pme_status & PME_WOL_MAGICPKT ? " \"Magic Packet\"" : "", + pme_status & PME_WOL_LINKUP ? " \"Link Up\"" : "", + pme_status & PME_WOL_ENERGY ? " \"Energy detect\"" : ""); + + return ops->pme_pwrite8(dev, port, regs[REG_PORT_PME_STATUS], + pme_status); +} + +/** + * ksz_get_wol - Get Wake-on-LAN settings for a specified port. + * @ds: The dsa_switch structure. + * @port: The port number. + * @wol: Pointer to ethtool Wake-on-LAN settings structure. + * + * This function checks the device PME wakeup_source flag and chip_id. + * If enabled and supported, it sets the supported and active WoL + * flags. + */ static void ksz_get_wol(struct dsa_switch *ds, int port, struct ethtool_wolinfo *wol) { struct ksz_device *dev = ds->priv; + const u16 *regs = dev->info->regs; + u8 pme_ctrl; + int ret; + + if (!is_ksz9477(dev) && !ksz_is_ksz87xx(dev)) + return; - if (dev->dev_ops->get_wol) - dev->dev_ops->get_wol(dev, port, wol); + if (!dev->wakeup_source) + return; + + wol->supported = WAKE_PHY; + + /* Check if the current MAC address on this port can be set + * as global for WAKE_MAGIC support. The result may vary + * dynamically based on other ports configurations. + */ + if (ksz_is_port_mac_global_usable(dev->ds, port)) + wol->supported |= WAKE_MAGIC; + + ret = dev->dev_ops->pme_pread8(dev, port, regs[REG_PORT_PME_CTRL], + &pme_ctrl); + if (ret) + return; + + if (pme_ctrl & PME_WOL_MAGICPKT) + wol->wolopts |= WAKE_MAGIC; + if (pme_ctrl & (PME_WOL_LINKUP | PME_WOL_ENERGY)) + wol->wolopts |= WAKE_PHY; } +/** + * ksz_set_wol - Set Wake-on-LAN settings for a specified port. + * @ds: The dsa_switch structure. + * @port: The port number. + * @wol: Pointer to ethtool Wake-on-LAN settings structure. + * + * This function configures Wake-on-LAN (WoL) settings for a specified + * port. It validates the provided WoL options, checks if PME is + * enabled and supported, clears any previous wake reasons, and sets + * the Magic Packet flag in the port's PME control register if + * specified. + * + * Return: 0 on success, or other error codes on failure. + */ static int ksz_set_wol(struct dsa_switch *ds, int port, struct ethtool_wolinfo *wol) { + u8 pme_ctrl = 0, pme_ctrl_old = 0; struct ksz_device *dev = ds->priv; + const u16 *regs = dev->info->regs; + bool magic_switched_off; + bool magic_switched_on; + int ret; - if (dev->dev_ops->set_wol) - return dev->dev_ops->set_wol(dev, port, wol); + if (wol->wolopts & ~(WAKE_PHY | WAKE_MAGIC)) + return -EINVAL; - return -EOPNOTSUPP; + if (!is_ksz9477(dev) && !ksz_is_ksz87xx(dev)) + return -EOPNOTSUPP; + + if (!dev->wakeup_source) + return -EOPNOTSUPP; + + ret = ksz_handle_wake_reason(dev, port); + if (ret) + return ret; + + if (wol->wolopts & WAKE_MAGIC) + pme_ctrl |= PME_WOL_MAGICPKT; + if (wol->wolopts & WAKE_PHY) + pme_ctrl |= PME_WOL_LINKUP | PME_WOL_ENERGY; + + ret = dev->dev_ops->pme_pread8(dev, port, regs[REG_PORT_PME_CTRL], + &pme_ctrl_old); + if (ret) + return ret; + + if (pme_ctrl_old == pme_ctrl) + return 0; + + magic_switched_off = (pme_ctrl_old & PME_WOL_MAGICPKT) && + !(pme_ctrl & PME_WOL_MAGICPKT); + magic_switched_on = !(pme_ctrl_old & PME_WOL_MAGICPKT) && + (pme_ctrl & PME_WOL_MAGICPKT); + + /* To keep reference count of MAC address, we should do this + * operation only on change of WOL settings. + */ + if (magic_switched_on) { + ret = ksz_switch_macaddr_get(dev->ds, port, NULL); + if (ret) + return ret; + } else if (magic_switched_off) { + ksz_switch_macaddr_put(dev->ds); + } + + ret = dev->dev_ops->pme_pwrite8(dev, port, regs[REG_PORT_PME_CTRL], + pme_ctrl); + if (ret) { + if (magic_switched_on) + ksz_switch_macaddr_put(dev->ds); + return ret; + } + + return 0; +} + +/** + * ksz_wol_pre_shutdown - Prepares the switch device for shutdown while + * considering Wake-on-LAN (WoL) settings. + * @dev: The switch device structure. + * @wol_enabled: Pointer to a boolean which will be set to true if WoL is + * enabled on any port. + * + * This function prepares the switch device for a safe shutdown while taking + * into account the Wake-on-LAN (WoL) settings on the user ports. It updates + * the wol_enabled flag accordingly to reflect whether WoL is active on any + * port. + */ +static void ksz_wol_pre_shutdown(struct ksz_device *dev, bool *wol_enabled) +{ + const struct ksz_dev_ops *ops = dev->dev_ops; + const u16 *regs = dev->info->regs; + u8 pme_pin_en = PME_ENABLE; + struct dsa_port *dp; + int ret; + + *wol_enabled = false; + + if (!is_ksz9477(dev) && !ksz_is_ksz87xx(dev)) + return; + + if (!dev->wakeup_source) + return; + + dsa_switch_for_each_user_port(dp, dev->ds) { + u8 pme_ctrl = 0; + + ret = ops->pme_pread8(dev, dp->index, + regs[REG_PORT_PME_CTRL], &pme_ctrl); + if (!ret && pme_ctrl) + *wol_enabled = true; + + /* make sure there are no pending wake events which would + * prevent the device from going to sleep/shutdown. + */ + ksz_handle_wake_reason(dev, dp->index); + } + + /* Now we are save to enable PME pin. */ + if (*wol_enabled) { + if (dev->pme_active_high) + pme_pin_en |= PME_POLARITY; + ops->pme_write8(dev, regs[REG_SW_PME_CTRL], pme_pin_en); + if (ksz_is_ksz87xx(dev)) + ksz_write8(dev, KSZ87XX_REG_INT_EN, KSZ87XX_INT_PME_MASK); + } } static int ksz_port_set_mac_address(struct dsa_switch *ds, int port, @@ -4072,8 +4428,7 @@ void ksz_switch_shutdown(struct ksz_device *dev) { bool wol_enabled = false; - if (dev->dev_ops->wol_pre_shutdown) - dev->dev_ops->wol_pre_shutdown(dev, &wol_enabled); + ksz_wol_pre_shutdown(dev, &wol_enabled); if (dev->dev_ops->reset && !wol_enabled) dev->dev_ops->reset(dev); @@ -4475,6 +4830,8 @@ int ksz_switch_register(struct ksz_device *dev) dev->wakeup_source = of_property_read_bool(dev->dev->of_node, "wakeup-source"); + dev->pme_active_high = of_property_read_bool(dev->dev->of_node, + "microchip,pme-active-high"); } ret = dsa_register_switch(dev->ds); diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h index 5f0a628b9849..e08d5a1339f4 100644 --- a/drivers/net/dsa/microchip/ksz_common.h +++ b/drivers/net/dsa/microchip/ksz_common.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Microchip switch driver common header * - * Copyright (C) 2017-2019 Microchip Technology Inc. + * Copyright (C) 2017-2024 Microchip Technology Inc. */ #ifndef __KSZ_COMMON_H @@ -174,6 +174,7 @@ struct ksz_device { bool synclko_125; bool synclko_disable; bool wakeup_source; + bool pme_active_high; struct vlan_table *vlan_cache; @@ -200,6 +201,8 @@ enum ksz_model { KSZ8794, KSZ8765, KSZ8830, + KSZ8864, + KSZ8895, KSZ9477, KSZ9896, KSZ9897, @@ -235,6 +238,9 @@ enum ksz_regs { S_MULTICAST_CTRL, P_XMII_CTRL_0, P_XMII_CTRL_1, + REG_SW_PME_CTRL, + REG_PORT_PME_STATUS, + REG_PORT_PME_CTRL, }; enum ksz_masks { @@ -354,6 +360,11 @@ struct ksz_dev_ops { void (*get_caps)(struct ksz_device *dev, int port, struct phylink_config *config); int (*change_mtu)(struct ksz_device *dev, int port, int mtu); + int (*pme_write8)(struct ksz_device *dev, u32 reg, u8 value); + int (*pme_pread8)(struct ksz_device *dev, int port, int offset, + u8 *data); + int (*pme_pwrite8)(struct ksz_device *dev, int port, int offset, + u8 data); void (*freeze_mib)(struct ksz_device *dev, int port, bool freeze); void (*port_init_cnt)(struct ksz_device *dev, int port); void (*phylink_mac_link_up)(struct ksz_device *dev, int port, @@ -363,11 +374,6 @@ struct ksz_dev_ops { int duplex, bool tx_pause, bool rx_pause); void (*setup_rgmii_delay)(struct ksz_device *dev, int port); int (*tc_cbs_set_cinc)(struct ksz_device *dev, int port, u32 val); - void (*get_wol)(struct ksz_device *dev, int port, - struct ethtool_wolinfo *wol); - int (*set_wol)(struct ksz_device *dev, int port, - struct ethtool_wolinfo *wol); - void (*wol_pre_shutdown)(struct ksz_device *dev, bool *wol_enabled); void (*config_cpu_port)(struct dsa_switch *ds); int (*enable_stp_addr)(struct ksz_device *dev); int (*reset)(struct ksz_device *dev); @@ -391,6 +397,7 @@ int ksz_switch_macaddr_get(struct dsa_switch *ds, int port, struct netlink_ext_ack *extack); void ksz_switch_macaddr_put(struct dsa_switch *ds); void ksz_switch_shutdown(struct ksz_device *dev); +int ksz_handle_wake_reason(struct ksz_device *dev, int port); /* Common register access functions */ static inline struct regmap *ksz_regmap_8(struct ksz_device *dev) @@ -624,9 +631,26 @@ static inline bool ksz_is_ksz88x3(struct ksz_device *dev) return dev->chip_id == KSZ8830_CHIP_ID; } +static inline bool ksz_is_8895_family(struct ksz_device *dev) +{ + return dev->chip_id == KSZ8895_CHIP_ID || + dev->chip_id == KSZ8864_CHIP_ID; +} + static inline bool is_ksz8(struct ksz_device *dev) { - return ksz_is_ksz87xx(dev) || ksz_is_ksz88x3(dev); + return ksz_is_ksz87xx(dev) || ksz_is_ksz88x3(dev) || + ksz_is_8895_family(dev); +} + +static inline bool is_ksz88xx(struct ksz_device *dev) +{ + return ksz_is_ksz88x3(dev) || ksz_is_8895_family(dev); +} + +static inline bool is_ksz9477(struct ksz_device *dev) +{ + return dev->chip_id == KSZ9477_CHIP_ID; } static inline int is_lan937x(struct ksz_device *dev) @@ -655,6 +679,7 @@ static inline bool is_lan937x_tx_phy(struct ksz_device *dev, int port) #define SW_FAMILY_ID_M GENMASK(15, 8) #define KSZ87_FAMILY_ID 0x87 #define KSZ88_FAMILY_ID 0x88 +#define KSZ8895_FAMILY_ID 0x95 #define KSZ8_PORT_STATUS_0 0x08 #define KSZ8_PORT_FIBER_MODE BIT(7) @@ -663,6 +688,12 @@ static inline bool is_lan937x_tx_phy(struct ksz_device *dev, int port) #define KSZ87_CHIP_ID_94 0x6 #define KSZ87_CHIP_ID_95 0x9 #define KSZ88_CHIP_ID_63 0x3 +#define KSZ8895_CHIP_ID_95 0x4 +#define KSZ8895_CHIP_ID_95R 0x6 + +/* KSZ8895 specific register */ +#define REG_KSZ8864_CHIP_ID 0xFE +#define SW_KSZ8864 BIT(7) #define SW_REV_ID_M GENMASK(7, 4) @@ -695,6 +726,17 @@ static inline bool is_lan937x_tx_phy(struct ksz_device *dev, int port) #define P_MII_MAC_MODE BIT(2) #define P_MII_SEL_M 0x3 +/* KSZ9477, KSZ87xx Wake-on-LAN (WoL) masks */ +#define PME_WOL_MAGICPKT BIT(2) +#define PME_WOL_LINKUP BIT(1) +#define PME_WOL_ENERGY BIT(0) + +#define PME_ENABLE BIT(1) +#define PME_POLARITY BIT(0) + +#define KSZ87XX_REG_INT_EN 0x7D +#define KSZ87XX_INT_PME_MASK BIT(4) + /* Interrupt */ #define REG_SW_PORT_INT_STATUS__1 0x001B #define REG_SW_PORT_INT_MASK__1 0x001F diff --git a/drivers/net/dsa/microchip/ksz_dcb.c b/drivers/net/dsa/microchip/ksz_dcb.c index 086bc9b3cf53..30b4a6186e38 100644 --- a/drivers/net/dsa/microchip/ksz_dcb.c +++ b/drivers/net/dsa/microchip/ksz_dcb.c @@ -113,7 +113,7 @@ static void ksz_get_default_port_prio_reg(struct ksz_device *dev, int *reg, static void ksz_get_dscp_prio_reg(struct ksz_device *dev, int *reg, int *per_reg, u8 *mask) { - if (ksz_is_ksz87xx(dev)) { + if (ksz_is_ksz87xx(dev) || ksz_is_8895_family(dev)) { *reg = KSZ8765_REG_TOS_DSCP_CTRL; *per_reg = 4; *mask = GENMASK(1, 0); diff --git a/drivers/net/dsa/microchip/ksz_spi.c b/drivers/net/dsa/microchip/ksz_spi.c index 8e8d83213b04..f4287310e89f 100644 --- a/drivers/net/dsa/microchip/ksz_spi.c +++ b/drivers/net/dsa/microchip/ksz_spi.c @@ -2,7 +2,7 @@ /* * Microchip ksz series register access through SPI * - * Copyright (C) 2017 Microchip Technology Inc. + * Copyright (C) 2017-2024 Microchip Technology Inc. * Tristram Ha <Tristram.Ha@microchip.com> */ @@ -60,6 +60,9 @@ static int ksz_spi_probe(struct spi_device *spi) chip->chip_id == KSZ8794_CHIP_ID || chip->chip_id == KSZ8765_CHIP_ID) regmap_config = ksz8795_regmap_config; + else if (chip->chip_id == KSZ8895_CHIP_ID || + chip->chip_id == KSZ8864_CHIP_ID) + regmap_config = ksz8863_regmap_config; else regmap_config = ksz9477_regmap_config; @@ -137,10 +140,18 @@ static const struct of_device_id ksz_dt_ids[] = { .data = &ksz_switch_chips[KSZ8830] }, { + .compatible = "microchip,ksz8864", + .data = &ksz_switch_chips[KSZ8864] + }, + { .compatible = "microchip,ksz8873", .data = &ksz_switch_chips[KSZ8830] }, { + .compatible = "microchip,ksz8895", + .data = &ksz_switch_chips[KSZ8895] + }, + { .compatible = "microchip,ksz9477", .data = &ksz_switch_chips[KSZ9477] }, @@ -201,7 +212,9 @@ static const struct spi_device_id ksz_spi_ids[] = { { "ksz8794" }, { "ksz8795" }, { "ksz8863" }, + { "ksz8864" }, { "ksz8873" }, + { "ksz8895" }, { "ksz9477" }, { "ksz9896" }, { "ksz9897" }, diff --git a/drivers/net/dsa/mt7530-mmio.c b/drivers/net/dsa/mt7530-mmio.c index b74a230a3f13..10dc49961f15 100644 --- a/drivers/net/dsa/mt7530-mmio.c +++ b/drivers/net/dsa/mt7530-mmio.c @@ -11,6 +11,7 @@ #include "mt7530.h" static const struct of_device_id mt7988_of_match[] = { + { .compatible = "airoha,en7581-switch", .data = &mt753x_table[ID_EN7581], }, { .compatible = "mediatek,mt7988-switch", .data = &mt753x_table[ID_MT7988], }, { /* sentinel */ }, }; diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index ec18e68bf3a8..d84ee1b419a6 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -1152,7 +1152,8 @@ mt753x_cpu_port_enable(struct dsa_switch *ds, int port) * the MT7988 SoC. Trapped frames will be forwarded to the CPU port that * is affine to the inbound user port. */ - if (priv->id == ID_MT7531 || priv->id == ID_MT7988) + if (priv->id == ID_MT7531 || priv->id == ID_MT7988 || + priv->id == ID_EN7581) mt7530_set(priv, MT7531_CFC, MT7531_CPU_PMAP(BIT(port))); /* CPU port gets connected to all user ports of @@ -2207,7 +2208,7 @@ mt7530_setup_irq(struct mt7530_priv *priv) return priv->irq ? : -EINVAL; } - if (priv->id == ID_MT7988) + if (priv->id == ID_MT7988 || priv->id == ID_EN7581) priv->irq_domain = irq_domain_add_linear(np, MT7530_NUM_PHYS, &mt7988_irq_domain_ops, priv); @@ -2438,8 +2439,10 @@ mt7530_setup(struct dsa_switch *ds) /* Clear link settings and enable force mode to force link down * on all ports until they're enabled later. */ - mt7530_rmw(priv, MT753X_PMCR_P(i), PMCR_LINK_SETTINGS_MASK | - MT7530_FORCE_MODE, MT7530_FORCE_MODE); + mt7530_rmw(priv, MT753X_PMCR_P(i), + PMCR_LINK_SETTINGS_MASK | + MT753X_FORCE_MODE(priv->id), + MT753X_FORCE_MODE(priv->id)); /* Disable forwarding by default on all ports */ mt7530_rmw(priv, MT7530_PCR_P(i), PCR_MATRIX_MASK, @@ -2550,8 +2553,10 @@ mt7531_setup_common(struct dsa_switch *ds) /* Clear link settings and enable force mode to force link down * on all ports until they're enabled later. */ - mt7530_rmw(priv, MT753X_PMCR_P(i), PMCR_LINK_SETTINGS_MASK | - MT7531_FORCE_MODE_MASK, MT7531_FORCE_MODE_MASK); + mt7530_rmw(priv, MT753X_PMCR_P(i), + PMCR_LINK_SETTINGS_MASK | + MT753X_FORCE_MODE(priv->id), + MT753X_FORCE_MODE(priv->id)); /* Disable forwarding by default on all ports */ mt7530_rmw(priv, MT7530_PCR_P(i), PCR_MATRIX_MASK, @@ -2783,6 +2788,28 @@ static void mt7988_mac_port_get_caps(struct dsa_switch *ds, int port, } } +static void en7581_mac_port_get_caps(struct dsa_switch *ds, int port, + struct phylink_config *config) +{ + switch (port) { + /* Ports which are connected to switch PHYs. There is no MII pinout. */ + case 0 ... 4: + __set_bit(PHY_INTERFACE_MODE_INTERNAL, + config->supported_interfaces); + + config->mac_capabilities |= MAC_10 | MAC_100 | MAC_1000FD; + break; + + /* Port 6 is connected to SoC's XGMII MAC. There is no MII pinout. */ + case 6: + __set_bit(PHY_INTERFACE_MODE_INTERNAL, + config->supported_interfaces); + + config->mac_capabilities |= MAC_10000FD; + break; + } +} + static void mt7530_mac_config(struct dsa_switch *ds, int port, unsigned int mode, phy_interface_t interface) @@ -3220,6 +3247,16 @@ const struct mt753x_info mt753x_table[] = { .phy_write_c45 = mt7531_ind_c45_phy_write, .mac_port_get_caps = mt7988_mac_port_get_caps, }, + [ID_EN7581] = { + .id = ID_EN7581, + .pcs_ops = &mt7530_pcs_ops, + .sw_setup = mt7988_setup, + .phy_read_c22 = mt7531_ind_c22_phy_read, + .phy_write_c22 = mt7531_ind_c22_phy_write, + .phy_read_c45 = mt7531_ind_c45_phy_read, + .phy_write_c45 = mt7531_ind_c45_phy_write, + .mac_port_get_caps = en7581_mac_port_get_caps, + }, }; EXPORT_SYMBOL_GPL(mt753x_table); diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h index 28592123070b..6ad33a9f6b1d 100644 --- a/drivers/net/dsa/mt7530.h +++ b/drivers/net/dsa/mt7530.h @@ -19,6 +19,7 @@ enum mt753x_id { ID_MT7621 = 1, ID_MT7531 = 2, ID_MT7988 = 3, + ID_EN7581 = 4, }; #define NUM_TRGMII_CTRL 5 @@ -64,25 +65,30 @@ enum mt753x_id { #define MT7531_CPU_PMAP(x) FIELD_PREP(MT7531_CPU_PMAP_MASK, x) #define MT753X_MIRROR_REG(id) ((id == ID_MT7531 || \ - id == ID_MT7988) ? \ + id == ID_MT7988 || \ + id == ID_EN7581) ? \ MT7531_CFC : MT753X_MFC) #define MT753X_MIRROR_EN(id) ((id == ID_MT7531 || \ - id == ID_MT7988) ? \ + id == ID_MT7988 || \ + id == ID_EN7581) ? \ MT7531_MIRROR_EN : MT7530_MIRROR_EN) #define MT753X_MIRROR_PORT_MASK(id) ((id == ID_MT7531 || \ - id == ID_MT7988) ? \ + id == ID_MT7988 || \ + id == ID_EN7581) ? \ MT7531_MIRROR_PORT_MASK : \ MT7530_MIRROR_PORT_MASK) #define MT753X_MIRROR_PORT_GET(id, val) ((id == ID_MT7531 || \ - id == ID_MT7988) ? \ + id == ID_MT7988 || \ + id == ID_EN7581) ? \ MT7531_MIRROR_PORT_GET(val) : \ MT7530_MIRROR_PORT_GET(val)) #define MT753X_MIRROR_PORT_SET(id, val) ((id == ID_MT7531 || \ - id == ID_MT7988) ? \ + id == ID_MT7988 || \ + id == ID_EN7581) ? \ MT7531_MIRROR_PORT_SET(val) : \ MT7530_MIRROR_PORT_SET(val)) @@ -355,6 +361,10 @@ enum mt7530_vlan_port_acc_frm { MT7531_FORCE_MODE_TX_FC | \ MT7531_FORCE_MODE_EEE100 | \ MT7531_FORCE_MODE_EEE1G) +#define MT753X_FORCE_MODE(id) ((id == ID_MT7531 || \ + id == ID_MT7988) ? \ + MT7531_FORCE_MODE_MASK : \ + MT7530_FORCE_MODE) #define PMCR_LINK_SETTINGS_MASK (PMCR_MAC_TX_EN | PMCR_MAC_RX_EN | \ PMCR_FORCE_EEE1G | \ PMCR_FORCE_EEE100 | \ diff --git a/drivers/net/dsa/mv88e6xxx/global2_scratch.c b/drivers/net/dsa/mv88e6xxx/global2_scratch.c index 61ab6cc4fbfc..53a6d3ed63b3 100644 --- a/drivers/net/dsa/mv88e6xxx/global2_scratch.c +++ b/drivers/net/dsa/mv88e6xxx/global2_scratch.c @@ -146,7 +146,7 @@ static int mv88e6352_g2_scratch_gpio_set_data(struct mv88e6xxx_chip *chip, * @chip: chip private data * @pin: gpio index * - * Return: 0 for output, 1 for input (same as GPIOF_DIR_XXX). + * Return: 0 for output, 1 for input. */ static int mv88e6352_g2_scratch_gpio_get_dir(struct mv88e6xxx_chip *chip, unsigned int pin) diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index 4a705f7333f4..3aa9c997018a 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -1370,9 +1370,8 @@ static int felix_parse_ports_node(struct felix *felix, phy_interface_t *port_phy_modes) { struct device *dev = felix->ocelot.dev; - struct device_node *child; - for_each_available_child_of_node(ports_node, child) { + for_each_available_child_of_node_scoped(ports_node, child) { phy_interface_t phy_mode; u32 port; int err; @@ -1381,7 +1380,6 @@ static int felix_parse_ports_node(struct felix *felix, if (of_property_read_u32(child, "reg", &port) < 0) { dev_err(dev, "Port number not defined in device tree " "(property \"reg\")\n"); - of_node_put(child); return -ENODEV; } @@ -1391,7 +1389,6 @@ static int felix_parse_ports_node(struct felix *felix, dev_err(dev, "Failed to read phy-mode or " "phy-interface-type property for port %d\n", port); - of_node_put(child); return -ENODEV; } diff --git a/drivers/net/dsa/realtek/rtl83xx.c b/drivers/net/dsa/realtek/rtl83xx.c index 35709a1756ae..3c5018d5e1f9 100644 --- a/drivers/net/dsa/realtek/rtl83xx.c +++ b/drivers/net/dsa/realtek/rtl83xx.c @@ -185,11 +185,9 @@ rtl83xx_probe(struct device *dev, /* TODO: if power is software controlled, set up any regulators here */ priv->reset_ctl = devm_reset_control_get_optional(dev, NULL); - if (IS_ERR(priv->reset_ctl)) { - ret = PTR_ERR(priv->reset_ctl); - dev_err_probe(dev, ret, "failed to get reset control\n"); - return ERR_CAST(priv->reset_ctl); - } + if (IS_ERR(priv->reset_ctl)) + return dev_err_cast_probe(dev, priv->reset_ctl, + "failed to get reset control\n"); priv->reset = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_LOW); if (IS_ERR(priv->reset)) { diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index c7282ce3d11c..bc7e50dcb57c 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -1188,9 +1188,8 @@ static int sja1105_parse_ports_node(struct sja1105_private *priv, struct device_node *ports_node) { struct device *dev = &priv->spidev->dev; - struct device_node *child; - for_each_available_child_of_node(ports_node, child) { + for_each_available_child_of_node_scoped(ports_node, child) { struct device_node *phy_node; phy_interface_t phy_mode; u32 index; @@ -1200,7 +1199,6 @@ static int sja1105_parse_ports_node(struct sja1105_private *priv, if (of_property_read_u32(child, "reg", &index) < 0) { dev_err(dev, "Port number not defined in device tree " "(property \"reg\")\n"); - of_node_put(child); return -ENODEV; } @@ -1210,7 +1208,6 @@ static int sja1105_parse_ports_node(struct sja1105_private *priv, dev_err(dev, "Failed to read phy-mode or " "phy-interface-type property for port %d\n", index); - of_node_put(child); return -ENODEV; } @@ -1219,7 +1216,6 @@ static int sja1105_parse_ports_node(struct sja1105_private *priv, if (!of_phy_is_fixed_link(child)) { dev_err(dev, "phy-handle or fixed-link " "properties missing!\n"); - of_node_put(child); return -ENODEV; } /* phy-handle is missing, but fixed-link isn't. @@ -1233,10 +1229,8 @@ static int sja1105_parse_ports_node(struct sja1105_private *priv, priv->phy_mode[index] = phy_mode; err = sja1105_parse_rgmii_delays(priv, index, child); - if (err) { - of_node_put(child); + if (err) return err; - } } return 0; diff --git a/drivers/net/dsa/vitesse-vsc73xx-core.c b/drivers/net/dsa/vitesse-vsc73xx-core.c index e3f95d2cc2c1..4d693c029c1f 100644 --- a/drivers/net/dsa/vitesse-vsc73xx-core.c +++ b/drivers/net/dsa/vitesse-vsc73xx-core.c @@ -21,6 +21,7 @@ #include <linux/of.h> #include <linux/of_mdio.h> #include <linux/bitops.h> +#include <linux/bitfield.h> #include <linux/if_bridge.h> #include <linux/if_vlan.h> #include <linux/etherdevice.h> @@ -225,9 +226,27 @@ #define VSC73XX_VLANACCESS_VLAN_TBL_CMD_CLEAR_TABLE 3 /* MII block 3 registers */ -#define VSC73XX_MII_STAT 0x0 -#define VSC73XX_MII_CMD 0x1 -#define VSC73XX_MII_DATA 0x2 +#define VSC73XX_MII_STAT 0x0 +#define VSC73XX_MII_CMD 0x1 +#define VSC73XX_MII_DATA 0x2 +#define VSC73XX_MII_MPRES 0x3 + +#define VSC73XX_MII_STAT_BUSY BIT(3) +#define VSC73XX_MII_STAT_READ BIT(2) +#define VSC73XX_MII_STAT_WRITE BIT(1) + +#define VSC73XX_MII_CMD_SCAN BIT(27) +#define VSC73XX_MII_CMD_OPERATION BIT(26) +#define VSC73XX_MII_CMD_PHY_ADDR GENMASK(25, 21) +#define VSC73XX_MII_CMD_PHY_REG GENMASK(20, 16) +#define VSC73XX_MII_CMD_WRITE_DATA GENMASK(15, 0) + +#define VSC73XX_MII_DATA_FAILURE BIT(16) +#define VSC73XX_MII_DATA_READ_DATA GENMASK(15, 0) + +#define VSC73XX_MII_MPRES_NOPREAMBLE BIT(6) +#define VSC73XX_MII_MPRES_PRESCALEVAL GENMASK(5, 0) +#define VSC73XX_MII_PRESCALEVAL_MIN 3 /* min allowed mdio clock prescaler */ #define VSC73XX_MII_STAT_BUSY BIT(3) @@ -562,8 +581,11 @@ static int vsc73xx_phy_read(struct dsa_switch *ds, int phy, int regnum) return ret; /* Setting bit 26 means "read" */ - cmd = BIT(26) | (phy << 21) | (regnum << 16); - ret = vsc73xx_write(vsc, VSC73XX_BLOCK_MII, 0, 1, cmd); + cmd = VSC73XX_MII_CMD_OPERATION | + FIELD_PREP(VSC73XX_MII_CMD_PHY_ADDR, phy) | + FIELD_PREP(VSC73XX_MII_CMD_PHY_REG, regnum); + ret = vsc73xx_write(vsc, VSC73XX_BLOCK_MII, VSC73XX_BLOCK_MII_INTERNAL, + VSC73XX_MII_CMD, cmd); if (ret) return ret; @@ -571,15 +593,16 @@ static int vsc73xx_phy_read(struct dsa_switch *ds, int phy, int regnum) if (ret) return ret; - ret = vsc73xx_read(vsc, VSC73XX_BLOCK_MII, 0, 2, &val); + ret = vsc73xx_read(vsc, VSC73XX_BLOCK_MII, VSC73XX_BLOCK_MII_INTERNAL, + VSC73XX_MII_DATA, &val); if (ret) return ret; - if (val & BIT(16)) { + if (val & VSC73XX_MII_DATA_FAILURE) { dev_err(vsc->dev, "reading reg %02x from phy%d failed\n", regnum, phy); return -EIO; } - val &= 0xFFFFU; + val &= VSC73XX_MII_DATA_READ_DATA; dev_dbg(vsc->dev, "read reg %02x from phy%d = %04x\n", regnum, phy, val); @@ -598,8 +621,11 @@ static int vsc73xx_phy_write(struct dsa_switch *ds, int phy, int regnum, if (ret) return ret; - cmd = (phy << 21) | (regnum << 16) | val; - ret = vsc73xx_write(vsc, VSC73XX_BLOCK_MII, 0, 1, cmd); + cmd = FIELD_PREP(VSC73XX_MII_CMD_PHY_ADDR, phy) | + FIELD_PREP(VSC73XX_MII_CMD_PHY_REG, regnum) | + FIELD_PREP(VSC73XX_MII_CMD_WRITE_DATA, val); + ret = vsc73xx_write(vsc, VSC73XX_BLOCK_MII, VSC73XX_BLOCK_MII_INTERNAL, + VSC73XX_MII_CMD, cmd); if (ret) return ret; @@ -708,10 +734,71 @@ vsc73xx_update_vlan_table(struct vsc73xx *vsc, int port, u16 vid, bool set) return vsc73xx_write_vlan_table_entry(vsc, vid, portmap); } +static int vsc73xx_configure_rgmii_port_delay(struct dsa_switch *ds) +{ + /* Keep 2.0 ns delay for backward complatibility */ + u32 tx_delay = VSC73XX_GMIIDELAY_GMII0_GTXDELAY_2_0_NS; + u32 rx_delay = VSC73XX_GMIIDELAY_GMII0_RXDELAY_2_0_NS; + struct dsa_port *dp = dsa_to_port(ds, CPU_PORT); + struct device_node *port_dn = dp->dn; + struct vsc73xx *vsc = ds->priv; + u32 delay; + + if (!of_property_read_u32(port_dn, "tx-internal-delay-ps", &delay)) { + switch (delay) { + case 0: + tx_delay = VSC73XX_GMIIDELAY_GMII0_GTXDELAY_NONE; + break; + case 1400: + tx_delay = VSC73XX_GMIIDELAY_GMII0_GTXDELAY_1_4_NS; + break; + case 1700: + tx_delay = VSC73XX_GMIIDELAY_GMII0_GTXDELAY_1_7_NS; + break; + case 2000: + break; + default: + dev_err(vsc->dev, + "Unsupported RGMII Transmit Clock Delay\n"); + return -EINVAL; + } + } else { + dev_dbg(vsc->dev, + "RGMII Transmit Clock Delay isn't configured, set to 2.0 ns\n"); + } + + if (!of_property_read_u32(port_dn, "rx-internal-delay-ps", &delay)) { + switch (delay) { + case 0: + rx_delay = VSC73XX_GMIIDELAY_GMII0_RXDELAY_NONE; + break; + case 1400: + rx_delay = VSC73XX_GMIIDELAY_GMII0_RXDELAY_1_4_NS; + break; + case 1700: + rx_delay = VSC73XX_GMIIDELAY_GMII0_RXDELAY_1_7_NS; + break; + case 2000: + break; + default: + dev_err(vsc->dev, + "Unsupported RGMII Receive Clock Delay value\n"); + return -EINVAL; + } + } else { + dev_dbg(vsc->dev, + "RGMII Receive Clock Delay isn't configured, set to 2.0 ns\n"); + } + + /* MII delay, set both GTX and RX delay */ + return vsc73xx_write(vsc, VSC73XX_BLOCK_SYSTEM, 0, VSC73XX_GMIIDELAY, + tx_delay | rx_delay); +} + static int vsc73xx_setup(struct dsa_switch *ds) { struct vsc73xx *vsc = ds->priv; - int i, ret; + int i, ret, val; dev_info(vsc->dev, "set up the switch\n"); @@ -770,10 +857,11 @@ static int vsc73xx_setup(struct dsa_switch *ds) VSC73XX_MAC_CFG, VSC73XX_MAC_CFG_RESET); } - /* MII delay, set both GTX and RX delay to 2 ns */ - vsc73xx_write(vsc, VSC73XX_BLOCK_SYSTEM, 0, VSC73XX_GMIIDELAY, - VSC73XX_GMIIDELAY_GMII0_GTXDELAY_2_0_NS | - VSC73XX_GMIIDELAY_GMII0_RXDELAY_2_0_NS); + /* Configure RGMII delay */ + ret = vsc73xx_configure_rgmii_port_delay(ds); + if (ret) + return ret; + /* Ingess VLAN reception mask (table 145) */ vsc73xx_write(vsc, VSC73XX_BLOCK_ANALYZER, 0, VSC73XX_VLANMASK, 0xff); @@ -783,6 +871,15 @@ static int vsc73xx_setup(struct dsa_switch *ds) mdelay(50); + /* Disable preamble and use maximum allowed clock for the internal + * mdio bus, used for communication with internal PHYs only. + */ + val = VSC73XX_MII_MPRES_NOPREAMBLE | + FIELD_PREP(VSC73XX_MII_MPRES_PRESCALEVAL, + VSC73XX_MII_PRESCALEVAL_MIN); + vsc73xx_write(vsc, VSC73XX_BLOCK_MII, VSC73XX_BLOCK_MII_INTERNAL, + VSC73XX_MII_MPRES, val); + /* Release reset from the internal PHYs */ vsc73xx_write(vsc, VSC73XX_BLOCK_SYSTEM, 0, VSC73XX_GLORESET, VSC73XX_GLORESET_PHY_RESET); diff --git a/drivers/net/ethernet/alacritech/slicoss.c b/drivers/net/ethernet/alacritech/slicoss.c index 78231c85234d..7f0c07c20be3 100644 --- a/drivers/net/ethernet/alacritech/slicoss.c +++ b/drivers/net/ethernet/alacritech/slicoss.c @@ -1051,11 +1051,9 @@ static int slic_load_rcvseq_firmware(struct slic_device *sdev) file = (sdev->model == SLIC_MODEL_OASIS) ? SLIC_RCV_FIRMWARE_OASIS : SLIC_RCV_FIRMWARE_MOJAVE; err = request_firmware(&fw, file, &sdev->pdev->dev); - if (err) { - dev_err(&sdev->pdev->dev, + if (err) + return dev_err_probe(&sdev->pdev->dev, err, "failed to load receive sequencer firmware %s\n", file); - return err; - } /* Do an initial sanity check concerning firmware size now. A further * check follows below. */ @@ -1126,10 +1124,9 @@ static int slic_load_firmware(struct slic_device *sdev) file = (sdev->model == SLIC_MODEL_OASIS) ? SLIC_FIRMWARE_OASIS : SLIC_FIRMWARE_MOJAVE; err = request_firmware(&fw, file, &sdev->pdev->dev); - if (err) { - dev_err(&sdev->pdev->dev, "failed to load firmware %s\n", file); - return err; - } + if (err) + return dev_err_probe(&sdev->pdev->dev, err, + "failed to load firmware %s\n", file); /* Do an initial sanity check concerning firmware size now. A further * check follows below. */ @@ -1678,17 +1675,15 @@ static int slic_init(struct slic_device *sdev) slic_card_reset(sdev); err = slic_load_firmware(sdev); - if (err) { - dev_err(&sdev->pdev->dev, "failed to load firmware\n"); - return err; - } + if (err) + return dev_err_probe(&sdev->pdev->dev, err, + "failed to load firmware\n"); /* we need the shared memory to read EEPROM so set it up temporarily */ err = slic_init_shmem(sdev); - if (err) { - dev_err(&sdev->pdev->dev, "failed to init shared memory\n"); - return err; - } + if (err) + return dev_err_probe(&sdev->pdev->dev, err, + "failed to init shared memory\n"); err = slic_read_eeprom(sdev); if (err) { @@ -1741,10 +1736,9 @@ static int slic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) int err; err = pci_enable_device(pdev); - if (err) { - dev_err(&pdev->dev, "failed to enable PCI device\n"); - return err; - } + if (err) + return dev_err_probe(&pdev->dev, err, + "failed to enable PCI device\n"); pci_set_master(pdev); pci_try_set_mwi(pdev); diff --git a/drivers/net/ethernet/alteon/acenic.c b/drivers/net/ethernet/alteon/acenic.c index 3d8ac63132fb..9e6f91df2ba0 100644 --- a/drivers/net/ethernet/alteon/acenic.c +++ b/drivers/net/ethernet/alteon/acenic.c @@ -1560,9 +1560,9 @@ static void ace_watchdog(struct net_device *data, unsigned int txqueue) } -static void ace_tasklet(struct tasklet_struct *t) +static void ace_bh_work(struct work_struct *work) { - struct ace_private *ap = from_tasklet(ap, t, ace_tasklet); + struct ace_private *ap = from_work(ap, work, ace_bh_work); struct net_device *dev = ap->ndev; int cur_size; @@ -1595,7 +1595,7 @@ static void ace_tasklet(struct tasklet_struct *t) #endif ace_load_jumbo_rx_ring(dev, RX_JUMBO_SIZE - cur_size); } - ap->tasklet_pending = 0; + ap->bh_work_pending = 0; } @@ -1617,7 +1617,7 @@ static void ace_dump_trace(struct ace_private *ap) * * Loading rings is safe without holding the spin lock since this is * done only before the device is enabled, thus no interrupts are - * generated and by the interrupt handler/tasklet handler. + * generated and by the interrupt handler/bh handler. */ static void ace_load_std_rx_ring(struct net_device *dev, int nr_bufs) { @@ -2160,7 +2160,7 @@ static irqreturn_t ace_interrupt(int irq, void *dev_id) */ if (netif_running(dev)) { int cur_size; - int run_tasklet = 0; + int run_bh_work = 0; cur_size = atomic_read(&ap->cur_rx_bufs); if (cur_size < RX_LOW_STD_THRES) { @@ -2172,7 +2172,7 @@ static irqreturn_t ace_interrupt(int irq, void *dev_id) ace_load_std_rx_ring(dev, RX_RING_SIZE - cur_size); } else - run_tasklet = 1; + run_bh_work = 1; } if (!ACE_IS_TIGON_I(ap)) { @@ -2188,7 +2188,7 @@ static irqreturn_t ace_interrupt(int irq, void *dev_id) ace_load_mini_rx_ring(dev, RX_MINI_SIZE - cur_size); } else - run_tasklet = 1; + run_bh_work = 1; } } @@ -2205,12 +2205,12 @@ static irqreturn_t ace_interrupt(int irq, void *dev_id) ace_load_jumbo_rx_ring(dev, RX_JUMBO_SIZE - cur_size); } else - run_tasklet = 1; + run_bh_work = 1; } } - if (run_tasklet && !ap->tasklet_pending) { - ap->tasklet_pending = 1; - tasklet_schedule(&ap->ace_tasklet); + if (run_bh_work && !ap->bh_work_pending) { + ap->bh_work_pending = 1; + queue_work(system_bh_wq, &ap->ace_bh_work); } } @@ -2267,7 +2267,7 @@ static int ace_open(struct net_device *dev) /* * Setup the bottom half rx ring refill handler */ - tasklet_setup(&ap->ace_tasklet, ace_tasklet); + INIT_WORK(&ap->ace_bh_work, ace_bh_work); return 0; } @@ -2301,7 +2301,7 @@ static int ace_close(struct net_device *dev) cmd.idx = 0; ace_issue_cmd(regs, &cmd); - tasklet_kill(&ap->ace_tasklet); + cancel_work_sync(&ap->ace_bh_work); /* * Make sure one CPU is not processing packets while diff --git a/drivers/net/ethernet/alteon/acenic.h b/drivers/net/ethernet/alteon/acenic.h index ca5ce0cbbad1..0e45a97b9c9b 100644 --- a/drivers/net/ethernet/alteon/acenic.h +++ b/drivers/net/ethernet/alteon/acenic.h @@ -2,7 +2,7 @@ #ifndef _ACENIC_H_ #define _ACENIC_H_ #include <linux/interrupt.h> - +#include <linux/workqueue.h> /* * Generate TX index update each time, when TX ring is closed. @@ -667,8 +667,8 @@ struct ace_private struct rx_desc *rx_mini_ring; struct rx_desc *rx_return_ring; - int tasklet_pending, jumbo; - struct tasklet_struct ace_tasklet; + int bh_work_pending, jumbo; + struct work_struct ace_bh_work; struct event *evt_ring; @@ -776,7 +776,7 @@ static int ace_open(struct net_device *dev); static netdev_tx_t ace_start_xmit(struct sk_buff *skb, struct net_device *dev); static int ace_close(struct net_device *dev); -static void ace_tasklet(struct tasklet_struct *t); +static void ace_bh_work(struct work_struct *work); static void ace_dump_trace(struct ace_private *ap); static void ace_set_multicast_list(struct net_device *dev); static int ace_change_mtu(struct net_device *dev, int new_mtu); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index c4a4e316683f..5475867708f4 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -403,9 +403,9 @@ static bool xgbe_ecc_ded(struct xgbe_prv_data *pdata, unsigned long *period, return false; } -static void xgbe_ecc_isr_task(struct tasklet_struct *t) +static void xgbe_ecc_isr_bh_work(struct work_struct *work) { - struct xgbe_prv_data *pdata = from_tasklet(pdata, t, tasklet_ecc); + struct xgbe_prv_data *pdata = from_work(pdata, work, ecc_bh_work); unsigned int ecc_isr; bool stop = false; @@ -465,17 +465,17 @@ static irqreturn_t xgbe_ecc_isr(int irq, void *data) { struct xgbe_prv_data *pdata = data; - if (pdata->isr_as_tasklet) - tasklet_schedule(&pdata->tasklet_ecc); + if (pdata->isr_as_bh_work) + queue_work(system_bh_wq, &pdata->ecc_bh_work); else - xgbe_ecc_isr_task(&pdata->tasklet_ecc); + xgbe_ecc_isr_bh_work(&pdata->ecc_bh_work); return IRQ_HANDLED; } -static void xgbe_isr_task(struct tasklet_struct *t) +static void xgbe_isr_bh_work(struct work_struct *work) { - struct xgbe_prv_data *pdata = from_tasklet(pdata, t, tasklet_dev); + struct xgbe_prv_data *pdata = from_work(pdata, work, dev_bh_work); struct xgbe_hw_if *hw_if = &pdata->hw_if; struct xgbe_channel *channel; unsigned int dma_isr, dma_ch_isr; @@ -582,7 +582,7 @@ isr_done: /* If there is not a separate ECC irq, handle it here */ if (pdata->vdata->ecc_support && (pdata->dev_irq == pdata->ecc_irq)) - xgbe_ecc_isr_task(&pdata->tasklet_ecc); + xgbe_ecc_isr_bh_work(&pdata->ecc_bh_work); /* If there is not a separate I2C irq, handle it here */ if (pdata->vdata->i2c_support && (pdata->dev_irq == pdata->i2c_irq)) @@ -604,10 +604,10 @@ static irqreturn_t xgbe_isr(int irq, void *data) { struct xgbe_prv_data *pdata = data; - if (pdata->isr_as_tasklet) - tasklet_schedule(&pdata->tasklet_dev); + if (pdata->isr_as_bh_work) + queue_work(system_bh_wq, &pdata->dev_bh_work); else - xgbe_isr_task(&pdata->tasklet_dev); + xgbe_isr_bh_work(&pdata->dev_bh_work); return IRQ_HANDLED; } @@ -1007,8 +1007,8 @@ static int xgbe_request_irqs(struct xgbe_prv_data *pdata) unsigned int i; int ret; - tasklet_setup(&pdata->tasklet_dev, xgbe_isr_task); - tasklet_setup(&pdata->tasklet_ecc, xgbe_ecc_isr_task); + INIT_WORK(&pdata->dev_bh_work, xgbe_isr_bh_work); + INIT_WORK(&pdata->ecc_bh_work, xgbe_ecc_isr_bh_work); ret = devm_request_irq(pdata->dev, pdata->dev_irq, xgbe_isr, 0, netdev_name(netdev), pdata); @@ -1078,8 +1078,8 @@ static void xgbe_free_irqs(struct xgbe_prv_data *pdata) devm_free_irq(pdata->dev, pdata->dev_irq, pdata); - tasklet_kill(&pdata->tasklet_dev); - tasklet_kill(&pdata->tasklet_ecc); + cancel_work_sync(&pdata->dev_bh_work); + cancel_work_sync(&pdata->ecc_bh_work); if (pdata->vdata->ecc_support && (pdata->dev_irq != pdata->ecc_irq)) devm_free_irq(pdata->dev, pdata->ecc_irq, pdata); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-i2c.c b/drivers/net/ethernet/amd/xgbe/xgbe-i2c.c index a9ccc4258ee5..7a833894f52a 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-i2c.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-i2c.c @@ -274,9 +274,9 @@ static void xgbe_i2c_clear_isr_interrupts(struct xgbe_prv_data *pdata, XI2C_IOREAD(pdata, IC_CLR_STOP_DET); } -static void xgbe_i2c_isr_task(struct tasklet_struct *t) +static void xgbe_i2c_isr_bh_work(struct work_struct *work) { - struct xgbe_prv_data *pdata = from_tasklet(pdata, t, tasklet_i2c); + struct xgbe_prv_data *pdata = from_work(pdata, work, i2c_bh_work); struct xgbe_i2c_op_state *state = &pdata->i2c.op_state; unsigned int isr; @@ -321,10 +321,10 @@ static irqreturn_t xgbe_i2c_isr(int irq, void *data) { struct xgbe_prv_data *pdata = (struct xgbe_prv_data *)data; - if (pdata->isr_as_tasklet) - tasklet_schedule(&pdata->tasklet_i2c); + if (pdata->isr_as_bh_work) + queue_work(system_bh_wq, &pdata->i2c_bh_work); else - xgbe_i2c_isr_task(&pdata->tasklet_i2c); + xgbe_i2c_isr_bh_work(&pdata->i2c_bh_work); return IRQ_HANDLED; } @@ -369,7 +369,7 @@ static void xgbe_i2c_set_target(struct xgbe_prv_data *pdata, unsigned int addr) static irqreturn_t xgbe_i2c_combined_isr(struct xgbe_prv_data *pdata) { - xgbe_i2c_isr_task(&pdata->tasklet_i2c); + xgbe_i2c_isr_bh_work(&pdata->i2c_bh_work); return IRQ_HANDLED; } @@ -449,7 +449,7 @@ static void xgbe_i2c_stop(struct xgbe_prv_data *pdata) if (pdata->dev_irq != pdata->i2c_irq) { devm_free_irq(pdata->dev, pdata->i2c_irq, pdata); - tasklet_kill(&pdata->tasklet_i2c); + cancel_work_sync(&pdata->i2c_bh_work); } } @@ -464,7 +464,7 @@ static int xgbe_i2c_start(struct xgbe_prv_data *pdata) /* If we have a separate I2C irq, enable it */ if (pdata->dev_irq != pdata->i2c_irq) { - tasklet_setup(&pdata->tasklet_i2c, xgbe_i2c_isr_task); + INIT_WORK(&pdata->i2c_bh_work, xgbe_i2c_isr_bh_work); ret = devm_request_irq(pdata->dev, pdata->i2c_irq, xgbe_i2c_isr, 0, pdata->i2c_name, diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c index 4a2dc705b528..07f4f3418d01 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c @@ -703,9 +703,9 @@ static void xgbe_an73_isr(struct xgbe_prv_data *pdata) } } -static void xgbe_an_isr_task(struct tasklet_struct *t) +static void xgbe_an_isr_bh_work(struct work_struct *work) { - struct xgbe_prv_data *pdata = from_tasklet(pdata, t, tasklet_an); + struct xgbe_prv_data *pdata = from_work(pdata, work, an_bh_work); netif_dbg(pdata, intr, pdata->netdev, "AN interrupt received\n"); @@ -727,17 +727,17 @@ static irqreturn_t xgbe_an_isr(int irq, void *data) { struct xgbe_prv_data *pdata = (struct xgbe_prv_data *)data; - if (pdata->isr_as_tasklet) - tasklet_schedule(&pdata->tasklet_an); + if (pdata->isr_as_bh_work) + queue_work(system_bh_wq, &pdata->an_bh_work); else - xgbe_an_isr_task(&pdata->tasklet_an); + xgbe_an_isr_bh_work(&pdata->an_bh_work); return IRQ_HANDLED; } static irqreturn_t xgbe_an_combined_isr(struct xgbe_prv_data *pdata) { - xgbe_an_isr_task(&pdata->tasklet_an); + xgbe_an_isr_bh_work(&pdata->an_bh_work); return IRQ_HANDLED; } @@ -1454,7 +1454,7 @@ static void xgbe_phy_stop(struct xgbe_prv_data *pdata) if (pdata->dev_irq != pdata->an_irq) { devm_free_irq(pdata->dev, pdata->an_irq, pdata); - tasklet_kill(&pdata->tasklet_an); + cancel_work_sync(&pdata->an_bh_work); } pdata->phy_if.phy_impl.stop(pdata); @@ -1477,7 +1477,7 @@ static int xgbe_phy_start(struct xgbe_prv_data *pdata) /* If we have a separate AN irq, enable it */ if (pdata->dev_irq != pdata->an_irq) { - tasklet_setup(&pdata->tasklet_an, xgbe_an_isr_task); + INIT_WORK(&pdata->an_bh_work, xgbe_an_isr_bh_work); ret = devm_request_irq(pdata->dev, pdata->an_irq, xgbe_an_isr, 0, pdata->an_name, diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c index c5e5fac49779..c636999a6a84 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c @@ -139,7 +139,7 @@ static int xgbe_config_multi_msi(struct xgbe_prv_data *pdata) return ret; } - pdata->isr_as_tasklet = 1; + pdata->isr_as_bh_work = 1; pdata->irq_count = ret; pdata->dev_irq = pci_irq_vector(pdata->pcidev, 0); @@ -176,7 +176,7 @@ static int xgbe_config_irqs(struct xgbe_prv_data *pdata) return ret; } - pdata->isr_as_tasklet = pdata->pcidev->msi_enabled ? 1 : 0; + pdata->isr_as_bh_work = pdata->pcidev->msi_enabled ? 1 : 0; pdata->irq_count = 1; pdata->channel_irq_count = 1; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h index f01a1e566da6..d85386cac8d1 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe.h @@ -1298,11 +1298,11 @@ struct xgbe_prv_data { unsigned int lpm_ctrl; /* CTRL1 for resume */ - unsigned int isr_as_tasklet; - struct tasklet_struct tasklet_dev; - struct tasklet_struct tasklet_ecc; - struct tasklet_struct tasklet_i2c; - struct tasklet_struct tasklet_an; + unsigned int isr_as_bh_work; + struct work_struct dev_bh_work; + struct work_struct ecc_bh_work; + struct work_struct i2c_bh_work; + struct work_struct an_bh_work; struct dentry *xgbe_debugfs; diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c index d0aecd1d7357..440ff4616fec 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c @@ -266,7 +266,7 @@ static void aq_ethtool_get_strings(struct net_device *ndev, const int rx_stat_cnt = ARRAY_SIZE(aq_ethtool_queue_rx_stat_names); const int tx_stat_cnt = ARRAY_SIZE(aq_ethtool_queue_tx_stat_names); char tc_string[8]; - int tc; + unsigned int tc; memset(tc_string, 0, sizeof(tc_string)); memcpy(p, aq_ethtool_stat_names, @@ -275,22 +275,20 @@ static void aq_ethtool_get_strings(struct net_device *ndev, for (tc = 0; tc < cfg->tcs; tc++) { if (cfg->is_qos) - snprintf(tc_string, 8, "TC%d ", tc); + snprintf(tc_string, 8, "TC%u ", tc); for (i = 0; i < cfg->vecs; i++) { for (si = 0; si < rx_stat_cnt; si++) { - snprintf(p, ETH_GSTRING_LEN, + ethtool_sprintf(&p, aq_ethtool_queue_rx_stat_names[si], tc_string, AQ_NIC_CFG_TCVEC2RING(cfg, tc, i)); - p += ETH_GSTRING_LEN; } for (si = 0; si < tx_stat_cnt; si++) { - snprintf(p, ETH_GSTRING_LEN, + ethtool_sprintf(&p, aq_ethtool_queue_tx_stat_names[si], tc_string, AQ_NIC_CFG_TCVEC2RING(cfg, tc, i)); - p += ETH_GSTRING_LEN; } } } @@ -305,20 +303,18 @@ static void aq_ethtool_get_strings(struct net_device *ndev, for (i = 0; i < max(rx_ring_cnt, tx_ring_cnt); i++) { for (si = 0; si < rx_stat_cnt; si++) { - snprintf(p, ETH_GSTRING_LEN, + ethtool_sprintf(&p, aq_ethtool_queue_rx_stat_names[si], tc_string, i ? PTP_HWST_RING_IDX : ptp_ring_idx); - p += ETH_GSTRING_LEN; } if (i >= tx_ring_cnt) continue; for (si = 0; si < tx_stat_cnt; si++) { - snprintf(p, ETH_GSTRING_LEN, + ethtool_sprintf(&p, aq_ethtool_queue_tx_stat_names[si], tc_string, i ? PTP_HWST_RING_IDX : ptp_ring_idx); - p += ETH_GSTRING_LEN; } } } @@ -338,9 +334,8 @@ static void aq_ethtool_get_strings(struct net_device *ndev, for (si = 0; si < ARRAY_SIZE(aq_macsec_txsc_stat_names); si++) { - snprintf(p, ETH_GSTRING_LEN, + ethtool_sprintf(&p, aq_macsec_txsc_stat_names[si], i); - p += ETH_GSTRING_LEN; } aq_txsc = &nic->macsec_cfg->aq_txsc[i]; for (sa = 0; sa < MACSEC_NUM_AN; sa++) { @@ -349,10 +344,9 @@ static void aq_ethtool_get_strings(struct net_device *ndev, for (si = 0; si < ARRAY_SIZE(aq_macsec_txsa_stat_names); si++) { - snprintf(p, ETH_GSTRING_LEN, + ethtool_sprintf(&p, aq_macsec_txsa_stat_names[si], i, sa); - p += ETH_GSTRING_LEN; } } } @@ -369,10 +363,9 @@ static void aq_ethtool_get_strings(struct net_device *ndev, for (si = 0; si < ARRAY_SIZE(aq_macsec_rxsa_stat_names); si++) { - snprintf(p, ETH_GSTRING_LEN, + ethtool_sprintf(&p, aq_macsec_rxsa_stat_names[si], i, sa); - p += ETH_GSTRING_LEN; } } } diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c index a38be924cdaa..db2a8ade6205 100644 --- a/drivers/net/ethernet/atheros/ag71xx.c +++ b/drivers/net/ethernet/atheros/ag71xx.c @@ -380,9 +380,7 @@ struct ag71xx { int mac_idx; struct reset_control *mdio_reset; - struct mii_bus *mii_bus; struct clk *clk_mdio; - struct clk *clk_eth; }; static int ag71xx_desc_empty(struct ag71xx_desc *desc) @@ -447,6 +445,13 @@ static void ag71xx_int_disable(struct ag71xx *ag, u32 ints) ag71xx_cb(ag, AG71XX_REG_INT_ENABLE, ints); } +static int ag71xx_do_ioctl(struct net_device *ndev, struct ifreq *ifr, int cmd) +{ + struct ag71xx *ag = netdev_priv(ndev); + + return phylink_mii_ioctl(ag->phylink, ifr, cmd); +} + static void ag71xx_get_drvinfo(struct net_device *ndev, struct ethtool_drvinfo *info) { @@ -690,31 +695,21 @@ static int ag71xx_mdio_probe(struct ag71xx *ag) int err; np = dev->of_node; - ag->mii_bus = NULL; - ag->clk_mdio = devm_clk_get(dev, "mdio"); + ag->clk_mdio = devm_clk_get_enabled(dev, "mdio"); if (IS_ERR(ag->clk_mdio)) { netif_err(ag, probe, ndev, "Failed to get mdio clk.\n"); return PTR_ERR(ag->clk_mdio); } - err = clk_prepare_enable(ag->clk_mdio); - if (err) { - netif_err(ag, probe, ndev, "Failed to enable mdio clk.\n"); - return err; - } - mii_bus = devm_mdiobus_alloc(dev); - if (!mii_bus) { - err = -ENOMEM; - goto mdio_err_put_clk; - } + if (!mii_bus) + return -ENOMEM; ag->mdio_reset = of_reset_control_get_exclusive(np, "mdio"); if (IS_ERR(ag->mdio_reset)) { netif_err(ag, probe, ndev, "Failed to get reset mdio.\n"); - err = PTR_ERR(ag->mdio_reset); - goto mdio_err_put_clk; + return PTR_ERR(ag->mdio_reset); } mii_bus->name = "ag71xx_mdio"; @@ -733,25 +728,12 @@ static int ag71xx_mdio_probe(struct ag71xx *ag) } mnp = of_get_child_by_name(np, "mdio"); - err = of_mdiobus_register(mii_bus, mnp); + err = devm_of_mdiobus_register(dev, mii_bus, mnp); of_node_put(mnp); if (err) - goto mdio_err_put_clk; - - ag->mii_bus = mii_bus; + return err; return 0; - -mdio_err_put_clk: - clk_disable_unprepare(ag->clk_mdio); - return err; -} - -static void ag71xx_mdio_remove(struct ag71xx *ag) -{ - if (ag->mii_bus) - mdiobus_unregister(ag->mii_bus); - clk_disable_unprepare(ag->clk_mdio); } static void ag71xx_hw_stop(struct ag71xx *ag) @@ -1799,7 +1781,7 @@ static const struct net_device_ops ag71xx_netdev_ops = { .ndo_open = ag71xx_open, .ndo_stop = ag71xx_stop, .ndo_start_xmit = ag71xx_hard_start_xmit, - .ndo_eth_ioctl = phy_do_ioctl, + .ndo_eth_ioctl = ag71xx_do_ioctl, .ndo_tx_timeout = ag71xx_tx_timeout, .ndo_change_mtu = ag71xx_change_mtu, .ndo_set_mac_address = eth_mac_addr, @@ -1816,6 +1798,7 @@ static int ag71xx_probe(struct platform_device *pdev) const struct ag71xx_dcfg *dcfg; struct net_device *ndev; struct resource *res; + struct clk *clk_eth; int tx_size, err, i; struct ag71xx *ag; @@ -1846,10 +1829,10 @@ static int ag71xx_probe(struct platform_device *pdev) return -EINVAL; } - ag->clk_eth = devm_clk_get(&pdev->dev, "eth"); - if (IS_ERR(ag->clk_eth)) { + clk_eth = devm_clk_get_enabled(&pdev->dev, "eth"); + if (IS_ERR(clk_eth)) { netif_err(ag, probe, ndev, "Failed to get eth clk.\n"); - return PTR_ERR(ag->clk_eth); + return PTR_ERR(clk_eth); } SET_NETDEV_DEV(ndev, &pdev->dev); @@ -1912,6 +1895,8 @@ static int ag71xx_probe(struct platform_device *pdev) ag->stop_desc->next = (u32)ag->stop_desc_dma; err = of_get_ethdev_address(np, ndev); + if (err == -EPROBE_DEFER) + return err; if (err) { netif_err(ag, probe, ndev, "invalid MAC address, using random address\n"); eth_hw_addr_random(ndev); @@ -1926,33 +1911,27 @@ static int ag71xx_probe(struct platform_device *pdev) netif_napi_add_weight(ndev, &ag->napi, ag71xx_poll, AG71XX_NAPI_WEIGHT); - err = clk_prepare_enable(ag->clk_eth); - if (err) { - netif_err(ag, probe, ndev, "Failed to enable eth clk.\n"); - return err; - } - ag71xx_wr(ag, AG71XX_REG_MAC_CFG1, 0); ag71xx_hw_init(ag); err = ag71xx_mdio_probe(ag); if (err) - goto err_put_clk; + return err; platform_set_drvdata(pdev, ndev); err = ag71xx_phylink_setup(ag); if (err) { netif_err(ag, probe, ndev, "failed to setup phylink (%d)\n", err); - goto err_mdio_remove; + return err; } - err = register_netdev(ndev); + err = devm_register_netdev(&pdev->dev, ndev); if (err) { netif_err(ag, probe, ndev, "unable to register net device\n"); platform_set_drvdata(pdev, NULL); - goto err_mdio_remove; + return err; } netif_info(ag, probe, ndev, "Atheros AG71xx at 0x%08lx, irq %d, mode:%s\n", @@ -1960,27 +1939,6 @@ static int ag71xx_probe(struct platform_device *pdev) phy_modes(ag->phy_if_mode)); return 0; - -err_mdio_remove: - ag71xx_mdio_remove(ag); -err_put_clk: - clk_disable_unprepare(ag->clk_eth); - return err; -} - -static void ag71xx_remove(struct platform_device *pdev) -{ - struct net_device *ndev = platform_get_drvdata(pdev); - struct ag71xx *ag; - - if (!ndev) - return; - - ag = netdev_priv(ndev); - unregister_netdev(ndev); - ag71xx_mdio_remove(ag); - clk_disable_unprepare(ag->clk_eth); - platform_set_drvdata(pdev, NULL); } static const u32 ar71xx_fifo_ar7100[] = { @@ -2064,10 +2022,10 @@ static const struct of_device_id ag71xx_match[] = { { .compatible = "qca,qca9560-eth", .data = &ag71xx_dcfg_qca9550 }, {} }; +MODULE_DEVICE_TABLE(of, ag71xx_match); static struct platform_driver ag71xx_driver = { .probe = ag71xx_probe, - .remove_new = ag71xx_remove, .driver = { .name = "ag71xx", .of_match_table = ag71xx_match, diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h index 4e9215bce4ad..a018f251d198 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h @@ -868,6 +868,8 @@ #define DORQ_REG_VF_TYPE_VALUE_0 0x170258 #define DORQ_REG_VF_USAGE_CT_LIMIT 0x170340 +extern const u32 dmae_reg_go_c[]; + /* [RW 4] Initial activity counter value on the load request; when the shortcut is done. */ #define DORQ_REG_SHRT_ACT_CNT 0x170070 diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c index 77d4cb4ad782..12198fc3ab22 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c @@ -2652,10 +2652,10 @@ int bnx2x_get_vf_config(struct net_device *dev, int vfidx, /* vlan */ if (bulletin->valid_bitmap & (1 << VLAN_VALID)) /* vlan configured by ndo so its in bulletin board */ - memcpy(&ivi->vlan, &bulletin->vlan, VLAN_HLEN); + ivi->vlan = bulletin->vlan; else /* function has not been loaded yet. Show vlans as 0s */ - memset(&ivi->vlan, 0, VLAN_HLEN); + ivi->vlan = 0; mutex_unlock(&bp->vfdb->bulletin_mutex); } diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c index 2bb133ae61c3..ba6729f2f9c0 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c @@ -23,8 +23,6 @@ #include "bnx2x_cmn.h" #include "bnx2x_sriov.h" -extern const u32 dmae_reg_go_c[]; - /* Statistics */ /* diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 04a623b3eee2..b26a7e2aa132 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -6579,7 +6579,8 @@ int bnxt_hwrm_vnic_cfg(struct bnxt *bp, struct bnxt_vnic_info *vnic) req->dflt_ring_grp = cpu_to_le16(bp->grp_info[grp_idx].fw_grp_id); req->lb_rule = cpu_to_le16(0xffff); vnic_mru: - req->mru = cpu_to_le16(bp->dev->mtu + ETH_HLEN + VLAN_HLEN); + vnic->mru = bp->dev->mtu + ETH_HLEN + VLAN_HLEN; + req->mru = cpu_to_le16(vnic->mru); req->vnic_id = cpu_to_le16(vnic->fw_vnic_id); #ifdef CONFIG_BNXT_SRIOV @@ -6715,6 +6716,8 @@ static int bnxt_hwrm_vnic_qcaps(struct bnxt *bp) bp->rss_cap |= BNXT_RSS_CAP_ESP_V4_RSS_CAP; if (flags & VNIC_QCAPS_RESP_FLAGS_RSS_IPSEC_ESP_SPI_IPV6_CAP) bp->rss_cap |= BNXT_RSS_CAP_ESP_V6_RSS_CAP; + if (flags & VNIC_QCAPS_RESP_FLAGS_RE_FLUSH_CAP) + bp->fw_cap |= BNXT_FW_CAP_VNIC_RE_FLUSH; } hwrm_req_drop(bp, req); return rc; @@ -10089,6 +10092,26 @@ vnic_setup_err: return rc; } +int bnxt_hwrm_vnic_update(struct bnxt *bp, struct bnxt_vnic_info *vnic, + u8 valid) +{ + struct hwrm_vnic_update_input *req; + int rc; + + rc = hwrm_req_init(bp, req, HWRM_VNIC_UPDATE); + if (rc) + return rc; + + req->vnic_id = cpu_to_le32(vnic->fw_vnic_id); + + if (valid & VNIC_UPDATE_REQ_ENABLES_MRU_VALID) + req->mru = cpu_to_le16(vnic->mru); + + req->enables = cpu_to_le32(valid); + + return hwrm_req_send(bp, req); +} + int bnxt_hwrm_vnic_rss_cfg_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic) { int rc; @@ -15154,7 +15177,8 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx) struct bnxt *bp = netdev_priv(dev); struct bnxt_rx_ring_info *rxr, *clone; struct bnxt_cp_ring_info *cpr; - int rc; + struct bnxt_vnic_info *vnic; + int i, rc; rxr = &bp->rx_ring[idx]; clone = qmem; @@ -15179,11 +15203,16 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx) if (bp->flags & BNXT_FLAG_AGG_RINGS) bnxt_db_write(bp, &rxr->rx_agg_db, rxr->rx_agg_prod); - napi_enable(&rxr->bnapi->napi); - cpr = &rxr->bnapi->cp_ring; cpr->sw_stats->rx.rx_resets++; + for (i = 0; i <= BNXT_VNIC_NTUPLE; i++) { + vnic = &bp->vnic_info[i]; + vnic->mru = bp->dev->mtu + ETH_HLEN + VLAN_HLEN; + bnxt_hwrm_vnic_update(bp, vnic, + VNIC_UPDATE_REQ_ENABLES_MRU_VALID); + } + return 0; err_free_hwrm_rx_ring: @@ -15195,9 +15224,17 @@ static int bnxt_queue_stop(struct net_device *dev, void *qmem, int idx) { struct bnxt *bp = netdev_priv(dev); struct bnxt_rx_ring_info *rxr; + struct bnxt_vnic_info *vnic; + int i; + + for (i = 0; i <= BNXT_VNIC_NTUPLE; i++) { + vnic = &bp->vnic_info[i]; + vnic->mru = 0; + bnxt_hwrm_vnic_update(bp, vnic, + VNIC_UPDATE_REQ_ENABLES_MRU_VALID); + } rxr = &bp->rx_ring[idx]; - napi_disable(&rxr->bnapi->napi); bnxt_hwrm_rx_ring_free(bp, rxr, false); bnxt_hwrm_rx_agg_ring_free(bp, rxr, false); rxr->rx_next_cons = 0; @@ -15681,7 +15718,6 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) dev->stat_ops = &bnxt_stat_ops; dev->watchdog_timeo = BNXT_TX_TIMEOUT; dev->ethtool_ops = &bnxt_ethtool_ops; - dev->queue_mgmt_ops = &bnxt_queue_mgmt_ops; pci_set_drvdata(pdev, dev); rc = bnxt_alloc_hwrm_resources(bp); @@ -15862,6 +15898,8 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (BNXT_SUPPORTS_NTUPLE_VNIC(bp)) bp->rss_cap |= BNXT_RSS_CAP_MULTI_RSS_CTX; + if (BNXT_SUPPORTS_QUEUE_API(bp)) + dev->queue_mgmt_ops = &bnxt_queue_mgmt_ops; rc = register_netdev(dev); if (rc) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 059a6f81c1a8..610c0fe468ad 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -1250,6 +1250,7 @@ struct bnxt_vnic_info { #define BNXT_MAX_CTX_PER_VNIC 8 u16 fw_rss_cos_lb_ctx[BNXT_MAX_CTX_PER_VNIC]; u16 fw_l2_ctx_id; + u16 mru; #define BNXT_MAX_UC_ADDRS 4 struct bnxt_l2_filter *l2_filters[BNXT_MAX_UC_ADDRS]; /* index 0 always dev_addr */ @@ -2437,6 +2438,7 @@ struct bnxt { #define BNXT_FW_CAP_VNIC_TUNNEL_TPA BIT_ULL(37) #define BNXT_FW_CAP_CFA_NTUPLE_RX_EXT_IP_PROTO BIT_ULL(38) #define BNXT_FW_CAP_CFA_RFS_RING_TBL_IDX_V3 BIT_ULL(39) + #define BNXT_FW_CAP_VNIC_RE_FLUSH BIT_ULL(40) u32 fw_dbg_cap; @@ -2449,6 +2451,9 @@ struct bnxt { #define BNXT_SUPPORTS_MULTI_RSS_CTX(bp) \ (BNXT_PF(bp) && BNXT_SUPPORTS_NTUPLE_VNIC(bp) && \ ((bp)->rss_cap & BNXT_RSS_CAP_MULTI_RSS_CTX)) +#define BNXT_SUPPORTS_QUEUE_API(bp) \ + (BNXT_PF(bp) && BNXT_SUPPORTS_NTUPLE_VNIC(bp) && \ + ((bp)->fw_cap & BNXT_FW_CAP_VNIC_RE_FLUSH)) u32 hwrm_spec_code; u16 hwrm_cmd_seq; @@ -2837,6 +2842,8 @@ int bnxt_hwrm_free_wol_fltr(struct bnxt *bp); int bnxt_hwrm_func_resc_qcaps(struct bnxt *bp, bool all); int bnxt_hwrm_func_qcaps(struct bnxt *bp); int bnxt_hwrm_fw_set_time(struct bnxt *); +int bnxt_hwrm_vnic_update(struct bnxt *bp, struct bnxt_vnic_info *vnic, + u8 valid); int bnxt_hwrm_vnic_rss_cfg_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic); int __bnxt_setup_vnic_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic); void bnxt_del_one_rss_ctx(struct bnxt *bp, struct bnxt_rss_ctx *rss_ctx, diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c index 156c2404854f..127b7015f676 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c @@ -64,9 +64,9 @@ static const struct file_operations debugfs_dim_fops = { static void debugfs_dim_ring_init(struct dim *dim, int ring_idx, struct dentry *dd) { - static char qname[16]; + static char qname[12]; - snprintf(qname, 10, "%d", ring_idx); + snprintf(qname, sizeof(qname), "%d", ring_idx); debugfs_create_file(qname, 0600, dd, dim, &debugfs_dim_fops); } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 4cf9bf8b01b0..194f47316c77 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -4157,7 +4157,7 @@ static void bnxt_get_pkgver(struct net_device *dev) if (!bnxt_get_pkginfo(dev, buf, sizeof(buf))) { len = strlen(bp->fw_ver_str); - snprintf(bp->fw_ver_str + len, FW_VER_STR_LEN - len - 1, + snprintf(bp->fw_ver_str + len, FW_VER_STR_LEN - len, "/pkg %s", buf); } } @@ -5285,7 +5285,7 @@ void bnxt_ethtool_free(struct bnxt *bp) const struct ethtool_ops bnxt_ethtool_ops = { .cap_link_lanes_supported = 1, - .cap_rss_ctx_supported = 1, + .rxfh_per_ctx_key = 1, .rxfh_max_num_contexts = BNXT_MAX_ETH_RSS_CTX + 1, .rxfh_indir_space = BNXT_MAX_RSS_TABLE_ENTRIES_P5, .rxfh_priv_size = sizeof(struct bnxt_rss_ctx), diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h index f219709f9563..f8ef6f1a1964 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h @@ -403,6 +403,9 @@ struct cmd_nums { #define HWRM_FUNC_LAG_UPDATE 0x1b1UL #define HWRM_FUNC_LAG_FREE 0x1b2UL #define HWRM_FUNC_LAG_QCFG 0x1b3UL + #define HWRM_FUNC_TIMEDTX_PACING_RATE_ADD 0x1c2UL + #define HWRM_FUNC_TIMEDTX_PACING_RATE_DELETE 0x1c3UL + #define HWRM_FUNC_TIMEDTX_PACING_RATE_QUERY 0x1c4UL #define HWRM_SELFTEST_QLIST 0x200UL #define HWRM_SELFTEST_EXEC 0x201UL #define HWRM_SELFTEST_IRQ 0x202UL @@ -430,6 +433,9 @@ struct cmd_nums { #define HWRM_STAT_GENERIC_QSTATS 0x218UL #define HWRM_MFG_PRVSN_EXPORT_CERT 0x219UL #define HWRM_STAT_DB_ERROR_QSTATS 0x21aUL + #define HWRM_MFG_TESTS 0x21bUL + #define HWRM_PORT_POE_CFG 0x230UL + #define HWRM_PORT_POE_QCFG 0x231UL #define HWRM_UDCC_QCAPS 0x258UL #define HWRM_UDCC_CFG 0x259UL #define HWRM_UDCC_QCFG 0x25aUL @@ -439,6 +445,9 @@ struct cmd_nums { #define HWRM_UDCC_COMP_CFG 0x25eUL #define HWRM_UDCC_COMP_QCFG 0x25fUL #define HWRM_UDCC_COMP_QUERY 0x260UL + #define HWRM_QUEUE_PFCWD_TIMEOUT_QCAPS 0x261UL + #define HWRM_QUEUE_PFCWD_TIMEOUT_CFG 0x262UL + #define HWRM_QUEUE_PFCWD_TIMEOUT_QCFG 0x263UL #define HWRM_TF 0x2bcUL #define HWRM_TF_VERSION_GET 0x2bdUL #define HWRM_TF_SESSION_OPEN 0x2c6UL @@ -500,10 +509,8 @@ struct cmd_nums { #define HWRM_TFC_IF_TBL_GET 0x399UL #define HWRM_TFC_TBL_SCOPE_CONFIG_GET 0x39aUL #define HWRM_TFC_RESC_USAGE_QUERY 0x39bUL - #define HWRM_QUEUE_PFCWD_TIMEOUT_QCAPS 0x39cUL - #define HWRM_QUEUE_PFCWD_TIMEOUT_CFG 0x39dUL - #define HWRM_QUEUE_PFCWD_TIMEOUT_QCFG 0x39eUL #define HWRM_SV 0x400UL + #define HWRM_DBG_SERDES_TEST 0xff0eUL #define HWRM_DBG_LOG_BUFFER_FLUSH 0xff0fUL #define HWRM_DBG_READ_DIRECT 0xff10UL #define HWRM_DBG_READ_INDIRECT 0xff11UL @@ -533,6 +540,9 @@ struct cmd_nums { #define HWRM_DBG_USEQ_RUN 0xff29UL #define HWRM_DBG_USEQ_DELIVERY_REQ 0xff2aUL #define HWRM_DBG_USEQ_RESP_HDR 0xff2bUL + #define HWRM_DBG_COREDUMP_CAPTURE 0xff2cUL + #define HWRM_DBG_PTRACE 0xff2dUL + #define HWRM_DBG_SIM_CABLE_STATE 0xff2eUL #define HWRM_NVM_GET_VPD_FIELD_INFO 0xffeaUL #define HWRM_NVM_SET_VPD_FIELD_INFO 0xffebUL #define HWRM_NVM_DEFRAG 0xffecUL @@ -582,6 +592,7 @@ struct ret_codes { #define HWRM_ERR_CODE_RESOURCE_LOCKED 0x11UL #define HWRM_ERR_CODE_PF_UNAVAILABLE 0x12UL #define HWRM_ERR_CODE_ENTITY_NOT_PRESENT 0x13UL + #define HWRM_ERR_CODE_SECURE_SOC_ERROR 0x14UL #define HWRM_ERR_CODE_TLV_ENCAPSULATED_RESPONSE 0x8000UL #define HWRM_ERR_CODE_UNKNOWN_ERR 0xfffeUL #define HWRM_ERR_CODE_CMD_NOT_SUPPORTED 0xffffUL @@ -613,8 +624,8 @@ struct hwrm_err_output { #define HWRM_VERSION_MAJOR 1 #define HWRM_VERSION_MINOR 10 #define HWRM_VERSION_UPDATE 3 -#define HWRM_VERSION_RSVD 44 -#define HWRM_VERSION_STR "1.10.3.44" +#define HWRM_VERSION_RSVD 68 +#define HWRM_VERSION_STR "1.10.3.68" /* hwrm_ver_get_input (size:192b/24B) */ struct hwrm_ver_get_input { @@ -850,7 +861,10 @@ struct hwrm_async_event_cmpl { #define ASYNC_EVENT_CMPL_EVENT_ID_UDCC_SESSION_CHANGE 0x4bUL #define ASYNC_EVENT_CMPL_EVENT_ID_DBG_BUF_PRODUCER 0x4cUL #define ASYNC_EVENT_CMPL_EVENT_ID_PEER_MMAP_CHANGE 0x4dUL - #define ASYNC_EVENT_CMPL_EVENT_ID_MAX_RGTR_EVENT_ID 0x4eUL + #define ASYNC_EVENT_CMPL_EVENT_ID_REPRESENTOR_PAIR_CHANGE 0x4eUL + #define ASYNC_EVENT_CMPL_EVENT_ID_VF_STAT_CHANGE 0x4fUL + #define ASYNC_EVENT_CMPL_EVENT_ID_HOST_COREDUMP 0x50UL + #define ASYNC_EVENT_CMPL_EVENT_ID_MAX_RGTR_EVENT_ID 0x51UL #define ASYNC_EVENT_CMPL_EVENT_ID_FW_TRACE_MSG 0xfeUL #define ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR 0xffUL #define ASYNC_EVENT_CMPL_EVENT_ID_LAST ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR @@ -1691,7 +1705,7 @@ struct hwrm_func_qcaps_input { u8 unused_0[6]; }; -/* hwrm_func_qcaps_output (size:1088b/136B) */ +/* hwrm_func_qcaps_output (size:1152b/144B) */ struct hwrm_func_qcaps_output { __le16 error_code; __le16 req_type; @@ -1824,6 +1838,9 @@ struct hwrm_func_qcaps_output { #define FUNC_QCAPS_RESP_FLAGS_EXT2_TF_EGRESS_NIC_FLOW_SUPPORTED 0x4000000UL #define FUNC_QCAPS_RESP_FLAGS_EXT2_MULTI_LOSSLESS_QUEUES_SUPPORTED 0x8000000UL #define FUNC_QCAPS_RESP_FLAGS_EXT2_PEER_MMAP_SUPPORTED 0x10000000UL + #define FUNC_QCAPS_RESP_FLAGS_EXT2_TIMED_TX_PACING_SUPPORTED 0x20000000UL + #define FUNC_QCAPS_RESP_FLAGS_EXT2_VF_STAT_EJECTION_SUPPORTED 0x40000000UL + #define FUNC_QCAPS_RESP_FLAGS_EXT2_HOST_COREDUMP_SUPPORTED 0x80000000UL __le16 tunnel_disable_flag; #define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_VXLAN 0x1UL #define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_NGE 0x2UL @@ -1845,7 +1862,9 @@ struct hwrm_func_qcaps_output { __le32 roce_vf_max_qp; __le32 roce_vf_max_srq; __le32 roce_vf_max_gid; - u8 unused_3[3]; + __le32 flags_ext3; + #define FUNC_QCAPS_RESP_FLAGS_EXT3_RM_RSV_WHILE_ALLOC_CAP 0x1UL + u8 unused_3[7]; u8 valid; }; @@ -2021,7 +2040,8 @@ struct hwrm_func_qcfg_output { #define FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_UNIT_PERCENT1_100 (0x1UL << 29) #define FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_UNIT_LAST FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_UNIT_PERCENT1_100 __le16 host_mtu; - u8 unused_3[2]; + __le16 flags2; + #define FUNC_QCFG_RESP_FLAGS2_SRIOV_DSCP_INSERT_ENABLED 0x1UL u8 unused_4[2]; u8 port_kdnet_mode; #define FUNC_QCFG_RESP_PORT_KDNET_MODE_DISABLED 0x0UL @@ -3671,33 +3691,38 @@ struct hwrm_func_backing_store_cfg_v2_input { __le16 target_id; __le64 resp_addr; __le16 type; - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_QP 0x0UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRQ 0x1UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CQ 0x2UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_VNIC 0x3UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_STAT 0x4UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SP_TQM_RING 0x5UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_FP_TQM_RING 0x6UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_MRAV 0xeUL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TIM 0xfUL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TX_CK 0x13UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RX_CK 0x14UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_MP_TQM_RING 0x15UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SQ_DB_SHADOW 0x16UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RQ_DB_SHADOW 0x17UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRQ_DB_SHADOW 0x18UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CQ_DB_SHADOW 0x19UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TBL_SCOPE 0x1cUL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_XID_PARTITION 0x1dUL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRT_TRACE 0x1eUL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRT2_TRACE 0x1fUL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CRT_TRACE 0x20UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CRT2_TRACE 0x21UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RIGP0_TRACE 0x22UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_L2_HWRM_TRACE 0x23UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_ROCE_HWRM_TRACE 0x24UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_INVALID 0xffffUL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_LAST FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_INVALID + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_QP 0x0UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRQ 0x1UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CQ 0x2UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_VNIC 0x3UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_STAT 0x4UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SP_TQM_RING 0x5UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_FP_TQM_RING 0x6UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_MRAV 0xeUL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TIM 0xfUL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TX_CK 0x13UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RX_CK 0x14UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_MP_TQM_RING 0x15UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SQ_DB_SHADOW 0x16UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RQ_DB_SHADOW 0x17UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRQ_DB_SHADOW 0x18UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CQ_DB_SHADOW 0x19UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TBL_SCOPE 0x1cUL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_XID_PARTITION 0x1dUL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRT_TRACE 0x1eUL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRT2_TRACE 0x1fUL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CRT_TRACE 0x20UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CRT2_TRACE 0x21UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RIGP0_TRACE 0x22UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_L2_HWRM_TRACE 0x23UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_ROCE_HWRM_TRACE 0x24UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TTX_PACING_TQM_RING 0x25UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CA0_TRACE 0x26UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CA1_TRACE 0x27UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CA2_TRACE 0x28UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RIGP1_TRACE 0x29UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_INVALID 0xffffUL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_LAST FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_INVALID __le16 instance; __le32 flags; #define FUNC_BACKING_STORE_CFG_V2_REQ_FLAGS_PREBOOT_MODE 0x1UL @@ -3772,6 +3797,11 @@ struct hwrm_func_backing_store_qcfg_v2_input { #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_RIGP0_TRACE 0x22UL #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_L2_HWRM_TRACE 0x23UL #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_ROCE_HWRM_TRACE 0x24UL + #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_TTX_PACING_TQM_RING 0x25UL + #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CA0_TRACE 0x26UL + #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CA1_TRACE 0x27UL + #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CA2_TRACE 0x28UL + #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_RIGP1_TRACE 0x29UL #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_INVALID 0xffffUL #define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_LAST FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_INVALID __le16 instance; @@ -3785,29 +3815,34 @@ struct hwrm_func_backing_store_qcfg_v2_output { __le16 seq_id; __le16 resp_len; __le16 type; - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_QP 0x0UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SRQ 0x1UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CQ 0x2UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_VNIC 0x3UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_STAT 0x4UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SP_TQM_RING 0x5UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_FP_TQM_RING 0x6UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_MRAV 0xeUL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TIM 0xfUL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TX_CK 0x13UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_RX_CK 0x14UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_MP_TQM_RING 0x15UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TBL_SCOPE 0x1cUL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_XID_PARTITION 0x1dUL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SRT_TRACE 0x1eUL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SRT2_TRACE 0x1fUL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CRT_TRACE 0x20UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CRT2_TRACE 0x21UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_RIGP0_TRACE 0x22UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_L2_HWRM_TRACE 0x23UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_ROCE_HWRM_TRACE 0x24UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_INVALID 0xffffUL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_LAST FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_INVALID + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_QP 0x0UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SRQ 0x1UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CQ 0x2UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_VNIC 0x3UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_STAT 0x4UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SP_TQM_RING 0x5UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_FP_TQM_RING 0x6UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_MRAV 0xeUL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TIM 0xfUL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TX_CK 0x13UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_RX_CK 0x14UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_MP_TQM_RING 0x15UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TBL_SCOPE 0x1cUL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_XID_PARTITION 0x1dUL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SRT_TRACE 0x1eUL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SRT2_TRACE 0x1fUL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CRT_TRACE 0x20UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CRT2_TRACE 0x21UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_RIGP0_TRACE 0x22UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_L2_HWRM_TRACE 0x23UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_ROCE_HWRM_TRACE 0x24UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TTX_PACING_TQM_RING 0x25UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CA0_TRACE 0x26UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CA1_TRACE 0x27UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CA2_TRACE 0x28UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_RIGP1_TRACE 0x29UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_INVALID 0xffffUL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_LAST FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_INVALID __le16 instance; __le32 flags; __le64 page_dir; @@ -3883,6 +3918,13 @@ struct ts_split_entries { __le32 rsvd2[2]; }; +/* ck_split_entries (size:128b/16B) */ +struct ck_split_entries { + __le32 num_quic_entries; + __le32 rsvd; + __le32 rsvd2[2]; +}; + /* hwrm_func_backing_store_qcaps_v2_input (size:192b/24B) */ struct hwrm_func_backing_store_qcaps_v2_input { __le16 req_type; @@ -3891,33 +3933,38 @@ struct hwrm_func_backing_store_qcaps_v2_input { __le16 target_id; __le64 resp_addr; __le16 type; - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_QP 0x0UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRQ 0x1UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CQ 0x2UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_VNIC 0x3UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_STAT 0x4UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SP_TQM_RING 0x5UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_FP_TQM_RING 0x6UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MRAV 0xeUL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TIM 0xfUL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TX_CK 0x13UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RX_CK 0x14UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MP_TQM_RING 0x15UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SQ_DB_SHADOW 0x16UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RQ_DB_SHADOW 0x17UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRQ_DB_SHADOW 0x18UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CQ_DB_SHADOW 0x19UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TBL_SCOPE 0x1cUL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_XID_PARTITION 0x1dUL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRT_TRACE 0x1eUL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRT2_TRACE 0x1fUL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CRT_TRACE 0x20UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CRT2_TRACE 0x21UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RIGP0_TRACE 0x22UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_L2_HWRM_TRACE 0x23UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_ROCE_HWRM_TRACE 0x24UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_INVALID 0xffffUL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_LAST FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_INVALID + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_QP 0x0UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRQ 0x1UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CQ 0x2UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_VNIC 0x3UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_STAT 0x4UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SP_TQM_RING 0x5UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_FP_TQM_RING 0x6UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MRAV 0xeUL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TIM 0xfUL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TX_CK 0x13UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RX_CK 0x14UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MP_TQM_RING 0x15UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SQ_DB_SHADOW 0x16UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RQ_DB_SHADOW 0x17UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRQ_DB_SHADOW 0x18UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CQ_DB_SHADOW 0x19UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TBL_SCOPE 0x1cUL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_XID_PARTITION 0x1dUL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRT_TRACE 0x1eUL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRT2_TRACE 0x1fUL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CRT_TRACE 0x20UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CRT2_TRACE 0x21UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RIGP0_TRACE 0x22UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_L2_HWRM_TRACE 0x23UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_ROCE_HWRM_TRACE 0x24UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TTX_PACING_TQM_RING 0x25UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CA0_TRACE 0x26UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CA1_TRACE 0x27UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CA2_TRACE 0x28UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RIGP1_TRACE 0x29UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_INVALID 0xffffUL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_LAST FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_INVALID u8 rsvd[6]; }; @@ -3928,39 +3975,45 @@ struct hwrm_func_backing_store_qcaps_v2_output { __le16 seq_id; __le16 resp_len; __le16 type; - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_QP 0x0UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRQ 0x1UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CQ 0x2UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_VNIC 0x3UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_STAT 0x4UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SP_TQM_RING 0x5UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_FP_TQM_RING 0x6UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_MRAV 0xeUL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TIM 0xfUL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TX_CK 0x13UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RX_CK 0x14UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_MP_TQM_RING 0x15UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SQ_DB_SHADOW 0x16UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RQ_DB_SHADOW 0x17UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRQ_DB_SHADOW 0x18UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CQ_DB_SHADOW 0x19UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TBL_SCOPE 0x1cUL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_XID_PARTITION 0x1dUL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRT_TRACE 0x1eUL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRT2_TRACE 0x1fUL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CRT_TRACE 0x20UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CRT2_TRACE 0x21UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RIGP0_TRACE 0x22UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_L2_HWRM_TRACE 0x23UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_ROCE_HWRM_TRACE 0x24UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_INVALID 0xffffUL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_LAST FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_INVALID + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_QP 0x0UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRQ 0x1UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CQ 0x2UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_VNIC 0x3UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_STAT 0x4UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SP_TQM_RING 0x5UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_FP_TQM_RING 0x6UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_MRAV 0xeUL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TIM 0xfUL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TX_CK 0x13UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RX_CK 0x14UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_MP_TQM_RING 0x15UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SQ_DB_SHADOW 0x16UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RQ_DB_SHADOW 0x17UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRQ_DB_SHADOW 0x18UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CQ_DB_SHADOW 0x19UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TBL_SCOPE 0x1cUL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_XID_PARTITION 0x1dUL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRT_TRACE 0x1eUL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRT2_TRACE 0x1fUL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CRT_TRACE 0x20UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CRT2_TRACE 0x21UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RIGP0_TRACE 0x22UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_L2_HWRM_TRACE 0x23UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_ROCE_HWRM_TRACE 0x24UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TTX_PACING_TQM_RING 0x25UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CA0_TRACE 0x26UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CA1_TRACE 0x27UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CA2_TRACE 0x28UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RIGP1_TRACE 0x29UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_INVALID 0xffffUL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_LAST FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_INVALID __le16 entry_size; __le32 flags; #define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_ENABLE_CTX_KIND_INIT 0x1UL #define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_TYPE_VALID 0x2UL #define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_DRIVER_MANAGED_MEMORY 0x4UL #define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_ROCE_QP_PSEUDO_STATIC_ALLOC 0x8UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_FW_DBG_TRACE 0x10UL __le32 instance_bit_map; u8 ctx_init_value; u8 ctx_init_offset; @@ -4410,6 +4463,7 @@ struct hwrm_port_phy_qcfg_output { #define PORT_PHY_QCFG_RESP_MODULE_STATUS_PWRDOWN 0x3UL #define PORT_PHY_QCFG_RESP_MODULE_STATUS_NOTINSERTED 0x4UL #define PORT_PHY_QCFG_RESP_MODULE_STATUS_CURRENTFAULT 0x5UL + #define PORT_PHY_QCFG_RESP_MODULE_STATUS_OVERHEATED 0x6UL #define PORT_PHY_QCFG_RESP_MODULE_STATUS_NOTAPPLICABLE 0xffUL #define PORT_PHY_QCFG_RESP_MODULE_STATUS_LAST PORT_PHY_QCFG_RESP_MODULE_STATUS_NOTAPPLICABLE __le32 preemphasis; @@ -4941,7 +4995,9 @@ struct hwrm_port_qstats_output { __le16 resp_len; __le16 tx_stat_size; __le16 rx_stat_size; - u8 unused_0[3]; + u8 flags; + #define PORT_QSTATS_RESP_FLAGS_CLEARED 0x1UL + u8 unused_0[2]; u8 valid; }; @@ -5074,6 +5130,7 @@ struct hwrm_port_qstats_ext_output { __le16 total_active_cos_queues; u8 flags; #define PORT_QSTATS_EXT_RESP_FLAGS_CLEAR_ROCE_COUNTERS_SUPPORTED 0x1UL + #define PORT_QSTATS_EXT_RESP_FLAGS_CLEARED 0x2UL u8 valid; }; @@ -6510,6 +6567,43 @@ struct hwrm_vnic_alloc_output { u8 valid; }; +/* hwrm_vnic_update_input (size:256b/32B) */ +struct hwrm_vnic_update_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + __le32 vnic_id; + __le32 enables; + #define VNIC_UPDATE_REQ_ENABLES_VNIC_STATE_VALID 0x1UL + #define VNIC_UPDATE_REQ_ENABLES_MRU_VALID 0x2UL + #define VNIC_UPDATE_REQ_ENABLES_METADATA_FORMAT_TYPE_VALID 0x4UL + u8 vnic_state; + #define VNIC_UPDATE_REQ_VNIC_STATE_NORMAL 0x0UL + #define VNIC_UPDATE_REQ_VNIC_STATE_DROP 0x1UL + #define VNIC_UPDATE_REQ_VNIC_STATE_LAST VNIC_UPDATE_REQ_VNIC_STATE_DROP + u8 metadata_format_type; + #define VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_0 0x0UL + #define VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_1 0x1UL + #define VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_2 0x2UL + #define VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_3 0x3UL + #define VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_4 0x4UL + #define VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_LAST VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_4 + __le16 mru; + u8 unused_1[4]; +}; + +/* hwrm_vnic_update_output (size:128b/16B) */ +struct hwrm_vnic_update_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + u8 unused_0[7]; + u8 valid; +}; + /* hwrm_vnic_free_input (size:192b/24B) */ struct hwrm_vnic_free_input { __le16 req_type; @@ -6640,6 +6734,7 @@ struct hwrm_vnic_qcaps_output { #define VNIC_QCAPS_RESP_FLAGS_RSS_PROF_TCAM_MODE_ENABLED 0x8000000UL #define VNIC_QCAPS_RESP_FLAGS_VNIC_RSS_HASH_MODE_CAP 0x10000000UL #define VNIC_QCAPS_RESP_FLAGS_HW_TUNNEL_TPA_CAP 0x20000000UL + #define VNIC_QCAPS_RESP_FLAGS_RE_FLUSH_CAP 0x40000000UL __le16 max_aggs_supported; u8 unused_1[5]; u8 valid; @@ -7484,23 +7579,24 @@ struct hwrm_cfa_l2_filter_cfg_input { __le16 target_id; __le64 resp_addr; __le32 flags; - #define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH 0x1UL - #define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_TX 0x0UL - #define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_RX 0x1UL - #define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_LAST CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_RX - #define CFA_L2_FILTER_CFG_REQ_FLAGS_DROP 0x2UL - #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_MASK 0xcUL - #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_SFT 2 - #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_NO_ROCE_L2 (0x0UL << 2) - #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_L2 (0x1UL << 2) - #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_ROCE (0x2UL << 2) - #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_LAST CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_ROCE - #define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_MASK 0x30UL - #define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_SFT 4 - #define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_NO_UPDATE (0x0UL << 4) - #define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_BYPASS_LKUP (0x1UL << 4) - #define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_ENABLE_LKUP (0x2UL << 4) - #define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_LAST CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_ENABLE_LKUP + #define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH 0x1UL + #define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_TX 0x0UL + #define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_RX 0x1UL + #define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_LAST CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_RX + #define CFA_L2_FILTER_CFG_REQ_FLAGS_DROP 0x2UL + #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_MASK 0xcUL + #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_SFT 2 + #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_NO_ROCE_L2 (0x0UL << 2) + #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_L2 (0x1UL << 2) + #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_ROCE (0x2UL << 2) + #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_LAST CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_ROCE + #define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_MASK 0x30UL + #define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_SFT 4 + #define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_NO_UPDATE (0x0UL << 4) + #define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_BYPASS_LKUP (0x1UL << 4) + #define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_ENABLE_LKUP (0x2UL << 4) + #define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_RESTORE_FW_OP (0x3UL << 4) + #define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_LAST CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_RESTORE_FW_OP __le32 enables; #define CFA_L2_FILTER_CFG_REQ_ENABLES_DST_ID 0x1UL #define CFA_L2_FILTER_CFG_REQ_ENABLES_NEW_MIRROR_VNIC_ID 0x2UL @@ -8766,7 +8862,7 @@ struct ctx_hw_stats_ext { __le64 rx_tpa_events; }; -/* hwrm_stat_ctx_alloc_input (size:320b/40B) */ +/* hwrm_stat_ctx_alloc_input (size:384b/48B) */ struct hwrm_stat_ctx_alloc_input { __le16 req_type; __le16 cmpl_ring; @@ -8776,13 +8872,16 @@ struct hwrm_stat_ctx_alloc_input { __le64 stats_dma_addr; __le32 update_period_ms; u8 stat_ctx_flags; - #define STAT_CTX_ALLOC_REQ_STAT_CTX_FLAGS_ROCE 0x1UL + #define STAT_CTX_ALLOC_REQ_STAT_CTX_FLAGS_ROCE 0x1UL + #define STAT_CTX_ALLOC_REQ_STAT_CTX_FLAGS_DUP_HOST_BUF 0x2UL u8 unused_0; __le16 stats_dma_length; __le16 flags; #define STAT_CTX_ALLOC_REQ_FLAGS_STEERING_TAG_VALID 0x1UL __le16 steering_tag; - __le32 unused_1; + __le32 stat_ctx_id; + __le16 alloc_seq_id; + u8 unused_1[6]; }; /* hwrm_stat_ctx_alloc_output (size:128b/16B) */ @@ -9650,10 +9749,13 @@ struct hwrm_dbg_qcaps_output { __le32 coredump_component_disable_caps; #define DBG_QCAPS_RESP_COREDUMP_COMPONENT_DISABLE_CAPS_NVRAM 0x1UL __le32 flags; - #define DBG_QCAPS_RESP_FLAGS_CRASHDUMP_NVM 0x1UL - #define DBG_QCAPS_RESP_FLAGS_CRASHDUMP_HOST_DDR 0x2UL - #define DBG_QCAPS_RESP_FLAGS_CRASHDUMP_SOC_DDR 0x4UL - #define DBG_QCAPS_RESP_FLAGS_USEQ 0x8UL + #define DBG_QCAPS_RESP_FLAGS_CRASHDUMP_NVM 0x1UL + #define DBG_QCAPS_RESP_FLAGS_CRASHDUMP_HOST_DDR 0x2UL + #define DBG_QCAPS_RESP_FLAGS_CRASHDUMP_SOC_DDR 0x4UL + #define DBG_QCAPS_RESP_FLAGS_USEQ 0x8UL + #define DBG_QCAPS_RESP_FLAGS_COREDUMP_HOST_DDR 0x10UL + #define DBG_QCAPS_RESP_FLAGS_COREDUMP_HOST_CAPTURE 0x20UL + #define DBG_QCAPS_RESP_FLAGS_PTRACE 0x40UL u8 unused_1[3]; u8 valid; }; @@ -10092,16 +10194,19 @@ struct hwrm_nvm_erase_dir_entry_output { u8 valid; }; -/* hwrm_nvm_get_dev_info_input (size:128b/16B) */ +/* hwrm_nvm_get_dev_info_input (size:192b/24B) */ struct hwrm_nvm_get_dev_info_input { __le16 req_type; __le16 cmpl_ring; __le16 seq_id; __le16 target_id; __le64 resp_addr; + u8 flags; + #define NVM_GET_DEV_INFO_REQ_FLAGS_SECURITY_SOC_NVM 0x1UL + u8 unused_0[7]; }; -/* hwrm_nvm_get_dev_info_output (size:704b/88B) */ +/* hwrm_nvm_get_dev_info_output (size:768b/96B) */ struct hwrm_nvm_get_dev_info_output { __le16 error_code; __le16 req_type; @@ -10135,6 +10240,10 @@ struct hwrm_nvm_get_dev_info_output { __le16 netctrl_fw_minor; __le16 netctrl_fw_build; __le16 netctrl_fw_patch; + __le16 srt2_fw_major; + __le16 srt2_fw_minor; + __le16 srt2_fw_build; + __le16 srt2_fw_patch; u8 unused_0[7]; u8 valid; }; diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c index c2b4188a1ef1..a9040c42d2ff 100644 --- a/drivers/net/ethernet/broadcom/cnic.c +++ b/drivers/net/ethernet/broadcom/cnic.c @@ -31,6 +31,7 @@ #include <linux/if_vlan.h> #include <linux/prefetch.h> #include <linux/random.h> +#include <linux/workqueue.h> #if IS_ENABLED(CONFIG_VLAN_8021Q) #define BCM_VLAN 1 #endif @@ -3015,9 +3016,9 @@ static int cnic_service_bnx2(void *data, void *status_blk) return cnic_service_bnx2_queues(dev); } -static void cnic_service_bnx2_msix(struct tasklet_struct *t) +static void cnic_service_bnx2_msix(struct work_struct *work) { - struct cnic_local *cp = from_tasklet(cp, t, cnic_irq_task); + struct cnic_local *cp = from_work(cp, work, cnic_irq_bh_work); struct cnic_dev *dev = cp->dev; cp->last_status_idx = cnic_service_bnx2_queues(dev); @@ -3036,7 +3037,7 @@ static void cnic_doirq(struct cnic_dev *dev) prefetch(cp->status_blk.gen); prefetch(&cp->kcq1.kcq[KCQ_PG(prod)][KCQ_IDX(prod)]); - tasklet_schedule(&cp->cnic_irq_task); + queue_work(system_bh_wq, &cp->cnic_irq_bh_work); } } @@ -3140,9 +3141,9 @@ static u32 cnic_service_bnx2x_kcq(struct cnic_dev *dev, struct kcq_info *info) return last_status; } -static void cnic_service_bnx2x_bh(struct tasklet_struct *t) +static void cnic_service_bnx2x_bh_work(struct work_struct *work) { - struct cnic_local *cp = from_tasklet(cp, t, cnic_irq_task); + struct cnic_local *cp = from_work(cp, work, cnic_irq_bh_work); struct cnic_dev *dev = cp->dev; struct bnx2x *bp = netdev_priv(dev->netdev); u32 status_idx, new_status_idx; @@ -4428,7 +4429,7 @@ static void cnic_free_irq(struct cnic_dev *dev) if (ethdev->drv_state & CNIC_DRV_STATE_USING_MSIX) { cp->disable_int_sync(dev); - tasklet_kill(&cp->cnic_irq_task); + cancel_work_sync(&cp->cnic_irq_bh_work); free_irq(ethdev->irq_arr[0].vector, dev); } } @@ -4441,7 +4442,7 @@ static int cnic_request_irq(struct cnic_dev *dev) err = request_irq(ethdev->irq_arr[0].vector, cnic_irq, 0, "cnic", dev); if (err) - tasklet_disable(&cp->cnic_irq_task); + disable_work_sync(&cp->cnic_irq_bh_work); return err; } @@ -4464,7 +4465,7 @@ static int cnic_init_bnx2_irq(struct cnic_dev *dev) CNIC_WR(dev, base + BNX2_HC_CMD_TICKS_OFF, (64 << 16) | 220); cp->last_status_idx = cp->status_blk.bnx2->status_idx; - tasklet_setup(&cp->cnic_irq_task, cnic_service_bnx2_msix); + INIT_WORK(&cp->cnic_irq_bh_work, cnic_service_bnx2_msix); err = cnic_request_irq(dev); if (err) return err; @@ -4873,7 +4874,7 @@ static int cnic_init_bnx2x_irq(struct cnic_dev *dev) struct cnic_eth_dev *ethdev = cp->ethdev; int err = 0; - tasklet_setup(&cp->cnic_irq_task, cnic_service_bnx2x_bh); + INIT_WORK(&cp->cnic_irq_bh_work, cnic_service_bnx2x_bh_work); if (ethdev->drv_state & CNIC_DRV_STATE_USING_MSIX) err = cnic_request_irq(dev); diff --git a/drivers/net/ethernet/broadcom/cnic.h b/drivers/net/ethernet/broadcom/cnic.h index fedc84ada937..1a314a75d2d2 100644 --- a/drivers/net/ethernet/broadcom/cnic.h +++ b/drivers/net/ethernet/broadcom/cnic.h @@ -268,7 +268,7 @@ struct cnic_local { u32 bnx2x_igu_sb_id; u32 int_num; u32 last_status_idx; - struct tasklet_struct cnic_irq_task; + struct work_struct cnic_irq_bh_work; struct kcqe *completed_kcq[MAX_COMPLETED_KCQE]; diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h index ea71612f6b36..5740c98d8c9f 100644 --- a/drivers/net/ethernet/cadence/macb.h +++ b/drivers/net/ethernet/cadence/macb.h @@ -13,6 +13,7 @@ #include <linux/net_tstamp.h> #include <linux/interrupt.h> #include <linux/phy/phy.h> +#include <linux/workqueue.h> #if defined(CONFIG_ARCH_DMA_ADDR_T_64BIT) || defined(CONFIG_MACB_USE_HWSTAMP) #define MACB_EXT_DESC @@ -1330,7 +1331,7 @@ struct macb { spinlock_t rx_fs_lock; unsigned int max_tuples; - struct tasklet_struct hresp_err_tasklet; + struct work_struct hresp_err_bh_work; int rx_bd_rd_prefetch; int tx_bd_rd_prefetch; diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index dcd3f54ed0cf..127bb3208034 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -1792,9 +1792,9 @@ static int macb_tx_poll(struct napi_struct *napi, int budget) return work_done; } -static void macb_hresp_error_task(struct tasklet_struct *t) +static void macb_hresp_error_task(struct work_struct *work) { - struct macb *bp = from_tasklet(bp, t, hresp_err_tasklet); + struct macb *bp = from_work(bp, work, hresp_err_bh_work); struct net_device *dev = bp->dev; struct macb_queue *queue; unsigned int q; @@ -1994,7 +1994,7 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id) } if (status & MACB_BIT(HRESP)) { - tasklet_schedule(&bp->hresp_err_tasklet); + queue_work(system_bh_wq, &bp->hresp_err_bh_work); netdev_err(dev, "DMA bus error: HRESP not OK\n"); if (bp->caps & MACB_CAPS_ISR_CLEAR_ON_WRITE) @@ -5119,12 +5119,12 @@ static int macb_probe(struct platform_device *pdev) goto err_out_free_netdev; } - /* MTU range: 68 - 1500 or 10240 */ + /* MTU range: 68 - 1518 or 10240 */ dev->min_mtu = GEM_MTU_MIN_SIZE; if ((bp->caps & MACB_CAPS_JUMBO) && bp->jumbo_max_len) dev->max_mtu = bp->jumbo_max_len - ETH_HLEN - ETH_FCS_LEN; else - dev->max_mtu = ETH_DATA_LEN; + dev->max_mtu = 1536 - ETH_HLEN - ETH_FCS_LEN; if (bp->caps & MACB_CAPS_BD_RD_PREFETCH) { val = GEM_BFEXT(RXBD_RDBUFF, gem_readl(bp, DCFG10)); @@ -5172,7 +5172,7 @@ static int macb_probe(struct platform_device *pdev) goto err_out_unregister_mdio; } - tasklet_setup(&bp->hresp_err_tasklet, macb_hresp_error_task); + INIT_WORK(&bp->hresp_err_bh_work, macb_hresp_error_task); netdev_info(dev, "Cadence %s rev 0x%08x at 0x%08lx irq %d (%pM)\n", macb_is_gem(bp) ? "GEM" : "MACB", macb_readl(bp, MID), @@ -5216,7 +5216,7 @@ static void macb_remove(struct platform_device *pdev) mdiobus_free(bp->mii_bus); unregister_netdev(dev); - tasklet_kill(&bp->hresp_err_tasklet); + cancel_work_sync(&bp->hresp_err_bh_work); pm_runtime_disable(&pdev->dev); pm_runtime_dont_use_autosuspend(&pdev->dev); if (!pm_runtime_suspended(&pdev->dev)) { diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.h b/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.h index 2d06097d3f61..40f529d0bc4c 100644 --- a/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.h +++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.h @@ -43,6 +43,4 @@ int cn23xx_octeon_pfvf_handshake(struct octeon_device *oct); int cn23xx_setup_octeon_vf_device(struct octeon_device *oct); u32 cn23xx_vf_get_oq_ticks(struct octeon_device *oct, u32 time_intr_in_us); - -void cn23xx_dump_vf_initialized_regs(struct octeon_device *oct); #endif diff --git a/drivers/net/ethernet/cavium/liquidio/cn66xx_device.h b/drivers/net/ethernet/cavium/liquidio/cn66xx_device.h index 8ed57134ee0c..129c8b84f549 100644 --- a/drivers/net/ethernet/cavium/liquidio/cn66xx_device.h +++ b/drivers/net/ethernet/cavium/liquidio/cn66xx_device.h @@ -86,7 +86,6 @@ u32 lio_cn6xxx_update_read_index(struct octeon_instr_queue *iq); void lio_cn6xxx_enable_interrupt(struct octeon_device *oct, u8 unused); void lio_cn6xxx_disable_interrupt(struct octeon_device *oct, u8 unused); -void cn6xxx_get_pcie_qlmport(struct octeon_device *oct); void lio_cn6xxx_setup_reg_address(struct octeon_device *oct, void *chip, struct octeon_reg_list *reg_list); u32 lio_cn6xxx_coprocessor_clock(struct octeon_device *oct); diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.h b/drivers/net/ethernet/cavium/liquidio/octeon_device.h index fb380b4f3e02..d26364c2ac81 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_device.h +++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.h @@ -804,13 +804,6 @@ int octeon_init_consoles(struct octeon_device *oct); int octeon_add_console(struct octeon_device *oct, u32 console_num, char *dbg_enb); -/** write or read from a console */ -int octeon_console_write(struct octeon_device *oct, u32 console_num, - char *buffer, u32 write_request_size, u32 flags); -int octeon_console_write_avail(struct octeon_device *oct, u32 console_num); - -int octeon_console_read_avail(struct octeon_device *oct, u32 console_num); - /** Removes all attached consoles. */ void octeon_remove_consoles(struct octeon_device *oct); diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_droq.h b/drivers/net/ethernet/cavium/liquidio/octeon_droq.h index c9b19e624dce..232ae72c0e37 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_droq.h +++ b/drivers/net/ethernet/cavium/liquidio/octeon_droq.h @@ -395,8 +395,6 @@ int octeon_register_dispatch_fn(struct octeon_device *oct, void *octeon_get_dispatch_arg(struct octeon_device *oct, u16 opcode, u16 subcode); -void octeon_droq_print_stats(void); - u32 octeon_droq_check_hw_for_pkts(struct octeon_droq *droq); int octeon_create_droq(struct octeon_device *oct, u32 q_no, diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_iq.h b/drivers/net/ethernet/cavium/liquidio/octeon_iq.h index bebf3bd349c6..a04f36a0e1a0 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_iq.h +++ b/drivers/net/ethernet/cavium/liquidio/octeon_iq.h @@ -378,9 +378,6 @@ int octeon_send_command(struct octeon_device *oct, u32 iq_no, u32 force_db, void *cmd, void *buf, u32 datasize, u32 reqtype); -void octeon_dump_soft_command(struct octeon_device *oct, - struct octeon_soft_command *sc); - void octeon_prepare_soft_command(struct octeon_device *oct, struct octeon_soft_command *sc, u8 opcode, u8 subcode, diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h index 8453defc296c..b7531041c56d 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h +++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h @@ -359,8 +359,6 @@ int nicvf_is_intr_enabled(struct nicvf *nic, int int_type, int q_idx); /* Register access APIs */ void nicvf_reg_write(struct nicvf *nic, u64 offset, u64 val); u64 nicvf_reg_read(struct nicvf *nic, u64 offset); -void nicvf_qset_reg_write(struct nicvf *nic, u64 offset, u64 val); -u64 nicvf_qset_reg_read(struct nicvf *nic, u64 offset); void nicvf_queue_reg_write(struct nicvf *nic, u64 offset, u64 qidx, u64 val); u64 nicvf_queue_reg_read(struct nicvf *nic, diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h index cdea49392185..84f16ababaee 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h @@ -219,9 +219,7 @@ void bgx_set_dmac_cam_filter(int node, int bgx_idx, int lmacid, u64 mac, u8 vf); void bgx_reset_xcast_mode(int node, int bgx_idx, int lmacid, u8 vf); void bgx_set_xcast_mode(int node, int bgx_idx, int lmacid, u8 mode); -void octeon_mdiobus_force_mod_depencency(void); void bgx_lmac_rx_tx_enable(int node, int bgx_idx, int lmacid, bool enable); -void bgx_add_dmac_addr(u64 dmac, int node, int bgx_idx, int lmac); unsigned bgx_get_map(int node); int bgx_get_lmac_count(int node, int bgx); const u8 *bgx_get_lmac_mac(int node, int bgx_idx, int lmacid); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32_parse.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32_parse.h index 9050568a034c..64663112cad8 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32_parse.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32_parse.h @@ -242,7 +242,7 @@ struct cxgb4_next_header { * field's value to jump to next header such as IHL field * in IPv4 header. */ - struct tc_u32_sel sel; + struct tc_u32_sel_hdr sel; struct tc_u32_key key; /* location of jump to make */ const struct cxgb4_match_field *jump; diff --git a/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.c b/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.c index 854d87e1125c..2e3973a32d9d 100644 --- a/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.c +++ b/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.c @@ -342,10 +342,10 @@ int cxgbi_ppm_release(struct cxgbi_ppm *ppm) } EXPORT_SYMBOL(cxgbi_ppm_release); -static struct cxgbi_ppm_pool *ppm_alloc_cpu_pool(unsigned int *total, - unsigned int *pcpu_ppmax) +static struct cxgbi_ppm_pool __percpu * +ppm_alloc_cpu_pool(unsigned int *total, unsigned int *pcpu_ppmax) { - struct cxgbi_ppm_pool *pools; + struct cxgbi_ppm_pool __percpu *pools; unsigned int ppmax = (*total) / num_possible_cpus(); unsigned int max = (PCPU_MIN_UNIT_SIZE - sizeof(*pools)) << 3; unsigned int bmap; @@ -392,7 +392,7 @@ int cxgbi_ppm_init(void **ppm_pp, struct net_device *ndev, unsigned int iscsi_edram_size) { struct cxgbi_ppm *ppm = (struct cxgbi_ppm *)(*ppm_pp); - struct cxgbi_ppm_pool *pool = NULL; + struct cxgbi_ppm_pool __percpu *pool = NULL; unsigned int pool_index_max = 0; unsigned int ppmax_pool = 0; unsigned int ppod_bmap_size; diff --git a/drivers/net/ethernet/davicom/dm9051.c b/drivers/net/ethernet/davicom/dm9051.c index bcfe52c11804..59ea48d4c9de 100644 --- a/drivers/net/ethernet/davicom/dm9051.c +++ b/drivers/net/ethernet/davicom/dm9051.c @@ -1235,6 +1235,7 @@ static const struct of_device_id dm9051_match_table[] = { { .compatible = "davicom,dm9051" }, {} }; +MODULE_DEVICE_TABLE(of, dm9051_match_table); static const struct spi_device_id dm9051_id_table[] = { { "dm9051", 0 }, diff --git a/drivers/net/ethernet/dlink/dl2k.c b/drivers/net/ethernet/dlink/dl2k.c index 7bfeae04b52b..d0ea92607870 100644 --- a/drivers/net/ethernet/dlink/dl2k.c +++ b/drivers/net/ethernet/dlink/dl2k.c @@ -1842,7 +1842,7 @@ static int rio_resume(struct device *device) return 0; } -static SIMPLE_DEV_PM_OPS(rio_pm_ops, rio_suspend, rio_resume); +static DEFINE_SIMPLE_DEV_PM_OPS(rio_pm_ops, rio_suspend, rio_resume); #define RIO_PM_OPS (&rio_pm_ops) #else diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c index 4c546c3aef0f..f3cc14cc757d 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.c +++ b/drivers/net/ethernet/faraday/ftgmac100.c @@ -24,6 +24,7 @@ #include <linux/crc32.h> #include <linux/if_vlan.h> #include <linux/of_net.h> +#include <linux/phy_fixed.h> #include <net/ip.h> #include <net/ncsi.h> @@ -50,6 +51,15 @@ #define FTGMAC_100MHZ 100000000 #define FTGMAC_25MHZ 25000000 +/* For NC-SI to register a fixed-link phy device */ +static struct fixed_phy_status ncsi_phy_status = { + .link = 1, + .speed = SPEED_100, + .duplex = DUPLEX_FULL, + .pause = 0, + .asym_pause = 0 +}; + struct ftgmac100 { /* Registers */ struct resource *res; @@ -1541,7 +1551,8 @@ static int ftgmac100_open(struct net_device *netdev) if (netdev->phydev) { /* If we have a PHY, start polling */ phy_start(netdev->phydev); - } else if (priv->use_ncsi) { + } + if (priv->use_ncsi) { /* If using NC-SI, set our carrier on and start the stack */ netif_carrier_on(netdev); @@ -1554,6 +1565,7 @@ static int ftgmac100_open(struct net_device *netdev) return 0; err_ncsi: + phy_stop(netdev->phydev); napi_disable(&priv->napi); netif_stop_queue(netdev); err_alloc: @@ -1587,7 +1599,7 @@ static int ftgmac100_stop(struct net_device *netdev) netif_napi_del(&priv->napi); if (netdev->phydev) phy_stop(netdev->phydev); - else if (priv->use_ncsi) + if (priv->use_ncsi) ncsi_stop_dev(priv->ndev); ftgmac100_stop_hw(priv); @@ -1725,6 +1737,9 @@ static void ftgmac100_phy_disconnect(struct net_device *netdev) phy_disconnect(netdev->phydev); if (of_phy_is_fixed_link(priv->dev->of_node)) of_phy_deregister_fixed_link(priv->dev->of_node); + + if (priv->use_ncsi) + fixed_phy_unregister(netdev->phydev); } static void ftgmac100_destroy_mdio(struct net_device *netdev) @@ -1802,6 +1817,7 @@ static int ftgmac100_probe(struct platform_device *pdev) struct resource *res; int irq; struct net_device *netdev; + struct phy_device *phydev; struct ftgmac100 *priv; struct device_node *np; int err = 0; @@ -1889,6 +1905,14 @@ static int ftgmac100_probe(struct platform_device *pdev) err = -EINVAL; goto err_phy_connect; } + + phydev = fixed_phy_register(PHY_POLL, &ncsi_phy_status, NULL); + err = phy_connect_direct(netdev, phydev, ftgmac100_adjust_link, + PHY_INTERFACE_MODE_MII); + if (err) { + dev_err(&pdev->dev, "Connecting PHY failed\n"); + goto err_phy_connect; + } } else if (np && of_phy_is_fixed_link(np)) { struct phy_device *phy; diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index cfe6b57b1da0..5d99cfb4e994 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -3156,8 +3156,9 @@ static void dpaa_napi_del(struct net_device *net_dev) for_each_possible_cpu(cpu) { percpu_priv = per_cpu_ptr(priv->percpu_priv, cpu); - netif_napi_del(&percpu_priv->np.napi); + __netif_napi_del(&percpu_priv->np.napi); } + synchronize_net(); } static inline void dpaa_bp_free_pf(const struct dpaa_bp *bp, diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index a923cb95cdc6..8c3bf0faba63 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -4606,7 +4606,7 @@ fec_drv_remove(struct platform_device *pdev) free_netdev(ndev); } -static int __maybe_unused fec_suspend(struct device *dev) +static int fec_suspend(struct device *dev) { struct net_device *ndev = dev_get_drvdata(dev); struct fec_enet_private *fep = netdev_priv(ndev); @@ -4659,7 +4659,7 @@ static int __maybe_unused fec_suspend(struct device *dev) return 0; } -static int __maybe_unused fec_resume(struct device *dev) +static int fec_resume(struct device *dev) { struct net_device *ndev = dev_get_drvdata(dev); struct fec_enet_private *fep = netdev_priv(ndev); @@ -4714,7 +4714,7 @@ failed_clk: return ret; } -static int __maybe_unused fec_runtime_suspend(struct device *dev) +static int fec_runtime_suspend(struct device *dev) { struct net_device *ndev = dev_get_drvdata(dev); struct fec_enet_private *fep = netdev_priv(ndev); @@ -4725,7 +4725,7 @@ static int __maybe_unused fec_runtime_suspend(struct device *dev) return 0; } -static int __maybe_unused fec_runtime_resume(struct device *dev) +static int fec_runtime_resume(struct device *dev) { struct net_device *ndev = dev_get_drvdata(dev); struct fec_enet_private *fep = netdev_priv(ndev); @@ -4746,14 +4746,14 @@ failed_clk_ipg: } static const struct dev_pm_ops fec_pm_ops = { - SET_SYSTEM_SLEEP_PM_OPS(fec_suspend, fec_resume) - SET_RUNTIME_PM_OPS(fec_runtime_suspend, fec_runtime_resume, NULL) + SYSTEM_SLEEP_PM_OPS(fec_suspend, fec_resume) + RUNTIME_PM_OPS(fec_runtime_suspend, fec_runtime_resume, NULL) }; static struct platform_driver fec_driver = { .driver = { .name = DRIVER_NAME, - .pm = &fec_pm_ops, + .pm = pm_ptr(&fec_pm_ops), .of_match_table = fec_dt_ids, .suppress_bind_attrs = true, }, diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c index 2e4f3e1782a2..4cffda363a14 100644 --- a/drivers/net/ethernet/freescale/fec_ptp.c +++ b/drivers/net/ethernet/freescale/fec_ptp.c @@ -91,6 +91,30 @@ #define FEC_PTP_MAX_NSEC_COUNTER 0x80000000ULL /** + * fec_ptp_read - read raw cycle counter (to be used by time counter) + * @cc: the cyclecounter structure + * + * this function reads the cyclecounter registers and is called by the + * cyclecounter structure used to construct a ns counter from the + * arbitrary fixed point registers + */ +static u64 fec_ptp_read(const struct cyclecounter *cc) +{ + struct fec_enet_private *fep = + container_of(cc, struct fec_enet_private, cc); + u32 tempval; + + tempval = readl(fep->hwp + FEC_ATIME_CTRL); + tempval |= FEC_T_CTRL_CAPTURE; + writel(tempval, fep->hwp + FEC_ATIME_CTRL); + + if (fep->quirks & FEC_QUIRK_BUG_CAPTURE) + udelay(1); + + return readl(fep->hwp + FEC_ATIME); +} + +/** * fec_ptp_enable_pps * @fep: the fec_enet_private structure handle * @enable: enable the channel pps output @@ -136,7 +160,7 @@ static int fec_ptp_enable_pps(struct fec_enet_private *fep, uint enable) * NSEC_PER_SEC - ts.tv_nsec. Add the remaining nanoseconds * to current timer would be next second. */ - tempval = fep->cc.read(&fep->cc); + tempval = fec_ptp_read(&fep->cc); /* Convert the ptp local counter to 1588 timestamp */ ns = timecounter_cyc2time(&fep->tc, tempval); ts = ns_to_timespec64(ns); @@ -211,13 +235,7 @@ static int fec_ptp_pps_perout(struct fec_enet_private *fep) timecounter_read(&fep->tc); /* Get the current ptp hardware time counter */ - temp_val = readl(fep->hwp + FEC_ATIME_CTRL); - temp_val |= FEC_T_CTRL_CAPTURE; - writel(temp_val, fep->hwp + FEC_ATIME_CTRL); - if (fep->quirks & FEC_QUIRK_BUG_CAPTURE) - udelay(1); - - ptp_hc = readl(fep->hwp + FEC_ATIME); + ptp_hc = fec_ptp_read(&fep->cc); /* Convert the ptp local counter to 1588 timestamp */ curr_time = timecounter_cyc2time(&fep->tc, ptp_hc); @@ -272,30 +290,6 @@ static enum hrtimer_restart fec_ptp_pps_perout_handler(struct hrtimer *timer) } /** - * fec_ptp_read - read raw cycle counter (to be used by time counter) - * @cc: the cyclecounter structure - * - * this function reads the cyclecounter registers and is called by the - * cyclecounter structure used to construct a ns counter from the - * arbitrary fixed point registers - */ -static u64 fec_ptp_read(const struct cyclecounter *cc) -{ - struct fec_enet_private *fep = - container_of(cc, struct fec_enet_private, cc); - u32 tempval; - - tempval = readl(fep->hwp + FEC_ATIME_CTRL); - tempval |= FEC_T_CTRL_CAPTURE; - writel(tempval, fep->hwp + FEC_ATIME_CTRL); - - if (fep->quirks & FEC_QUIRK_BUG_CAPTURE) - udelay(1); - - return readl(fep->hwp + FEC_ATIME); -} - -/** * fec_ptp_start_cyclecounter - create the cycle counter from hw * @ndev: network device * diff --git a/drivers/net/ethernet/freescale/fman/fman_port.c b/drivers/net/ethernet/freescale/fman/fman_port.c index 406e75e9e5ea..f17a4e511510 100644 --- a/drivers/net/ethernet/freescale/fman/fman_port.c +++ b/drivers/net/ethernet/freescale/fman/fman_port.c @@ -1748,7 +1748,7 @@ static int fman_port_probe(struct platform_device *of_dev) struct resource res; struct resource *dev_res; u32 val; - int err = 0, lenp; + int err = 0; enum fman_port_type port_type; u16 port_speed; u8 port_id; @@ -1795,7 +1795,7 @@ static int fman_port_probe(struct platform_device *of_dev) if (of_device_is_compatible(port_node, "fsl,fman-v3-port-tx")) { port_type = FMAN_PORT_TYPE_TX; port_speed = 1000; - if (of_find_property(port_node, "fsl,fman-10g-port", &lenp)) + if (of_property_read_bool(port_node, "fsl,fman-10g-port")) port_speed = 10000; } else if (of_device_is_compatible(port_node, "fsl,fman-v2-port-tx")) { @@ -1808,7 +1808,7 @@ static int fman_port_probe(struct platform_device *of_dev) } else if (of_device_is_compatible(port_node, "fsl,fman-v3-port-rx")) { port_type = FMAN_PORT_TYPE_RX; port_speed = 1000; - if (of_find_property(port_node, "fsl,fman-10g-port", &lenp)) + if (of_property_read_bool(port_node, "fsl,fman-10g-port")) port_speed = 10000; } else if (of_device_is_compatible(port_node, "fsl,fman-v2-port-rx")) { diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-scc.c b/drivers/net/ethernet/freescale/fs_enet/mac-scc.c index a64cb6270515..9e89ac2b6ce3 100644 --- a/drivers/net/ethernet/freescale/fs_enet/mac-scc.c +++ b/drivers/net/ethernet/freescale/fs_enet/mac-scc.c @@ -131,15 +131,14 @@ static int setup_data(struct net_device *dev) static int allocate_bd(struct net_device *dev) { struct fs_enet_private *fep = netdev_priv(dev); - const struct fs_platform_info *fpi = fep->fpi; + struct fs_platform_info *fpi = fep->fpi; - fep->ring_mem_addr = cpm_muram_alloc((fpi->tx_ring + fpi->rx_ring) * - sizeof(cbd_t), 8); - if (IS_ERR_VALUE(fep->ring_mem_addr)) + fpi->dpram_offset = cpm_muram_alloc((fpi->tx_ring + fpi->rx_ring) * + sizeof(cbd_t), 8); + if (IS_ERR_VALUE(fpi->dpram_offset)) return -ENOMEM; - fep->ring_base = (void __iomem __force*) - cpm_muram_addr(fep->ring_mem_addr); + fep->ring_base = cpm_muram_addr(fpi->dpram_offset); return 0; } @@ -147,9 +146,10 @@ static int allocate_bd(struct net_device *dev) static void free_bd(struct net_device *dev) { struct fs_enet_private *fep = netdev_priv(dev); + const struct fs_platform_info *fpi = fep->fpi; if (fep->ring_base) - cpm_muram_free(fep->ring_mem_addr); + cpm_muram_free(fpi->dpram_offset); } static void cleanup_data(struct net_device *dev) @@ -247,9 +247,9 @@ static void restart(struct net_device *dev) __fs_out8((u8 __iomem *)ep + i, 0); /* point to bds */ - W16(ep, sen_genscc.scc_rbase, fep->ring_mem_addr); + W16(ep, sen_genscc.scc_rbase, fpi->dpram_offset); W16(ep, sen_genscc.scc_tbase, - fep->ring_mem_addr + sizeof(cbd_t) * fpi->rx_ring); + fpi->dpram_offset + sizeof(cbd_t) * fpi->rx_ring); /* Initialize function code registers for big-endian. */ diff --git a/drivers/net/ethernet/fungible/funcore/fun_dev.c b/drivers/net/ethernet/fungible/funcore/fun_dev.c index a7fbd4cd560a..ce97b76f9ae0 100644 --- a/drivers/net/ethernet/fungible/funcore/fun_dev.c +++ b/drivers/net/ethernet/fungible/funcore/fun_dev.c @@ -546,17 +546,14 @@ int fun_bind(struct fun_dev *fdev, enum fun_admin_bind_type type0, unsigned int id0, enum fun_admin_bind_type type1, unsigned int id1) { - struct { - struct fun_admin_bind_req req; - struct fun_admin_bind_entry entry[2]; - } cmd = { - .req.common = FUN_ADMIN_REQ_COMMON_INIT2(FUN_ADMIN_OP_BIND, - sizeof(cmd)), - .entry[0] = FUN_ADMIN_BIND_ENTRY_INIT(type0, id0), - .entry[1] = FUN_ADMIN_BIND_ENTRY_INIT(type1, id1), - }; + DEFINE_RAW_FLEX(struct fun_admin_bind_req, cmd, entry, 2); + + cmd->common = FUN_ADMIN_REQ_COMMON_INIT2(FUN_ADMIN_OP_BIND, + __struct_size(cmd)); + cmd->entry[0] = FUN_ADMIN_BIND_ENTRY_INIT(type0, id0); + cmd->entry[1] = FUN_ADMIN_BIND_ENTRY_INIT(type1, id1); - return fun_submit_admin_sync_cmd(fdev, &cmd.req.common, NULL, 0, 0); + return fun_submit_admin_sync_cmd(fdev, &cmd->common, NULL, 0, 0); } EXPORT_SYMBOL_GPL(fun_bind); diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h index 84ac004d3953..301fa1ea4f51 100644 --- a/drivers/net/ethernet/google/gve/gve.h +++ b/drivers/net/ethernet/google/gve/gve.h @@ -784,6 +784,8 @@ struct gve_priv { u32 adminq_verify_driver_compatibility_cnt; u32 adminq_query_flow_rules_cnt; u32 adminq_cfg_flow_rule_cnt; + u32 adminq_cfg_rss_cnt; + u32 adminq_query_rss_cnt; /* Global stats */ u32 interface_up_cnt; /* count of times interface turned up since last reset */ @@ -831,6 +833,9 @@ struct gve_priv { u32 num_flow_rules; struct gve_flow_rules_cache flow_rules_cache; + + u16 rss_key_size; + u16 rss_lut_size; }; enum gve_service_task_flags_bit { @@ -1148,7 +1153,6 @@ int gve_rx_alloc_ring_gqi(struct gve_priv *priv, int idx); void gve_rx_free_ring_gqi(struct gve_priv *priv, struct gve_rx_ring *rx, struct gve_rx_alloc_rings_cfg *cfg); -int gve_rx_alloc_rings(struct gve_priv *priv); int gve_rx_alloc_rings_gqi(struct gve_priv *priv, struct gve_rx_alloc_rings_cfg *cfg); void gve_rx_free_rings_gqi(struct gve_priv *priv, diff --git a/drivers/net/ethernet/google/gve/gve_adminq.c b/drivers/net/ethernet/google/gve/gve_adminq.c index c5bbc1b7524e..e44e8b139633 100644 --- a/drivers/net/ethernet/google/gve/gve_adminq.c +++ b/drivers/net/ethernet/google/gve/gve_adminq.c @@ -45,6 +45,7 @@ void gve_parse_device_option(struct gve_priv *priv, struct gve_device_option_dqo_qpl **dev_op_dqo_qpl, struct gve_device_option_buffer_sizes **dev_op_buffer_sizes, struct gve_device_option_flow_steering **dev_op_flow_steering, + struct gve_device_option_rss_config **dev_op_rss_config, struct gve_device_option_modify_ring **dev_op_modify_ring) { u32 req_feat_mask = be32_to_cpu(option->required_features_mask); @@ -207,6 +208,23 @@ void gve_parse_device_option(struct gve_priv *priv, "Flow Steering"); *dev_op_flow_steering = (void *)(option + 1); break; + case GVE_DEV_OPT_ID_RSS_CONFIG: + if (option_length < sizeof(**dev_op_rss_config) || + req_feat_mask != GVE_DEV_OPT_REQ_FEAT_MASK_RSS_CONFIG) { + dev_warn(&priv->pdev->dev, GVE_DEVICE_OPTION_ERROR_FMT, + "RSS config", + (int)sizeof(**dev_op_rss_config), + GVE_DEV_OPT_REQ_FEAT_MASK_RSS_CONFIG, + option_length, req_feat_mask); + break; + } + + if (option_length > sizeof(**dev_op_rss_config)) + dev_warn(&priv->pdev->dev, + GVE_DEVICE_OPTION_TOO_BIG_FMT, + "RSS config"); + *dev_op_rss_config = (void *)(option + 1); + break; default: /* If we don't recognize the option just continue * without doing anything. @@ -227,6 +245,7 @@ gve_process_device_options(struct gve_priv *priv, struct gve_device_option_dqo_qpl **dev_op_dqo_qpl, struct gve_device_option_buffer_sizes **dev_op_buffer_sizes, struct gve_device_option_flow_steering **dev_op_flow_steering, + struct gve_device_option_rss_config **dev_op_rss_config, struct gve_device_option_modify_ring **dev_op_modify_ring) { const int num_options = be16_to_cpu(descriptor->num_device_options); @@ -249,7 +268,8 @@ gve_process_device_options(struct gve_priv *priv, dev_op_gqi_rda, dev_op_gqi_qpl, dev_op_dqo_rda, dev_op_jumbo_frames, dev_op_dqo_qpl, dev_op_buffer_sizes, - dev_op_flow_steering, dev_op_modify_ring); + dev_op_flow_steering, dev_op_rss_config, + dev_op_modify_ring); dev_opt = next_opt; } @@ -289,6 +309,8 @@ int gve_adminq_alloc(struct device *dev, struct gve_priv *priv) priv->adminq_get_ptype_map_cnt = 0; priv->adminq_query_flow_rules_cnt = 0; priv->adminq_cfg_flow_rule_cnt = 0; + priv->adminq_cfg_rss_cnt = 0; + priv->adminq_query_rss_cnt = 0; /* Setup Admin queue with the device */ if (priv->pdev->revision < 0x1) { @@ -534,6 +556,12 @@ static int gve_adminq_issue_cmd(struct gve_priv *priv, case GVE_ADMINQ_CONFIGURE_FLOW_RULE: priv->adminq_cfg_flow_rule_cnt++; break; + case GVE_ADMINQ_CONFIGURE_RSS: + priv->adminq_cfg_rss_cnt++; + break; + case GVE_ADMINQ_QUERY_RSS: + priv->adminq_query_rss_cnt++; + break; default: dev_err(&priv->pdev->dev, "unknown AQ command opcode %d\n", opcode); } @@ -867,6 +895,8 @@ static void gve_enable_supported_features(struct gve_priv *priv, *dev_op_buffer_sizes, const struct gve_device_option_flow_steering *dev_op_flow_steering, + const struct gve_device_option_rss_config + *dev_op_rss_config, const struct gve_device_option_modify_ring *dev_op_modify_ring) { @@ -931,6 +961,14 @@ static void gve_enable_supported_features(struct gve_priv *priv, priv->max_flow_rules); } } + + if (dev_op_rss_config && + (supported_features_mask & GVE_SUP_RSS_CONFIG_MASK)) { + priv->rss_key_size = + be16_to_cpu(dev_op_rss_config->hash_key_size); + priv->rss_lut_size = + be16_to_cpu(dev_op_rss_config->hash_lut_size); + } } int gve_adminq_describe_device(struct gve_priv *priv) @@ -939,6 +977,7 @@ int gve_adminq_describe_device(struct gve_priv *priv) struct gve_device_option_buffer_sizes *dev_op_buffer_sizes = NULL; struct gve_device_option_jumbo_frames *dev_op_jumbo_frames = NULL; struct gve_device_option_modify_ring *dev_op_modify_ring = NULL; + struct gve_device_option_rss_config *dev_op_rss_config = NULL; struct gve_device_option_gqi_rda *dev_op_gqi_rda = NULL; struct gve_device_option_gqi_qpl *dev_op_gqi_qpl = NULL; struct gve_device_option_dqo_rda *dev_op_dqo_rda = NULL; @@ -973,6 +1012,7 @@ int gve_adminq_describe_device(struct gve_priv *priv) &dev_op_jumbo_frames, &dev_op_dqo_qpl, &dev_op_buffer_sizes, &dev_op_flow_steering, + &dev_op_rss_config, &dev_op_modify_ring); if (err) goto free_device_descriptor; @@ -1035,7 +1075,7 @@ int gve_adminq_describe_device(struct gve_priv *priv) gve_enable_supported_features(priv, supported_features_mask, dev_op_jumbo_frames, dev_op_dqo_qpl, dev_op_buffer_sizes, dev_op_flow_steering, - dev_op_modify_ring); + dev_op_rss_config, dev_op_modify_ring); free_device_descriptor: dma_pool_free(priv->adminq_pool, descriptor, descriptor_bus); @@ -1248,6 +1288,81 @@ int gve_adminq_reset_flow_rules(struct gve_priv *priv) return gve_adminq_configure_flow_rule(priv, &flow_rule_cmd); } +int gve_adminq_configure_rss(struct gve_priv *priv, struct ethtool_rxfh_param *rxfh) +{ + dma_addr_t lut_bus = 0, key_bus = 0; + u16 key_size = 0, lut_size = 0; + union gve_adminq_command cmd; + __be32 *lut = NULL; + u8 hash_alg = 0; + u8 *key = NULL; + int err = 0; + u16 i; + + switch (rxfh->hfunc) { + case ETH_RSS_HASH_NO_CHANGE: + break; + case ETH_RSS_HASH_TOP: + hash_alg = ETH_RSS_HASH_TOP; + break; + default: + return -EOPNOTSUPP; + } + + if (rxfh->indir) { + lut_size = priv->rss_lut_size; + lut = dma_alloc_coherent(&priv->pdev->dev, + lut_size * sizeof(*lut), + &lut_bus, GFP_KERNEL); + if (!lut) + return -ENOMEM; + + for (i = 0; i < priv->rss_lut_size; i++) + lut[i] = cpu_to_be32(rxfh->indir[i]); + } + + if (rxfh->key) { + key_size = priv->rss_key_size; + key = dma_alloc_coherent(&priv->pdev->dev, + key_size, &key_bus, GFP_KERNEL); + if (!key) { + err = -ENOMEM; + goto out; + } + + memcpy(key, rxfh->key, key_size); + } + + /* Zero-valued fields in the cmd.configure_rss instruct the device to + * not update those fields. + */ + memset(&cmd, 0, sizeof(cmd)); + cmd.opcode = cpu_to_be32(GVE_ADMINQ_CONFIGURE_RSS); + cmd.configure_rss = (struct gve_adminq_configure_rss) { + .hash_types = cpu_to_be16(BIT(GVE_RSS_HASH_TCPV4) | + BIT(GVE_RSS_HASH_UDPV4) | + BIT(GVE_RSS_HASH_TCPV6) | + BIT(GVE_RSS_HASH_UDPV6)), + .hash_alg = hash_alg, + .hash_key_size = cpu_to_be16(key_size), + .hash_lut_size = cpu_to_be16(lut_size), + .hash_key_addr = cpu_to_be64(key_bus), + .hash_lut_addr = cpu_to_be64(lut_bus), + }; + + err = gve_adminq_execute_cmd(priv, &cmd); + +out: + if (lut) + dma_free_coherent(&priv->pdev->dev, + lut_size * sizeof(*lut), + lut, lut_bus); + if (key) + dma_free_coherent(&priv->pdev->dev, + key_size, key, key_bus); + return err; +} + /* In the dma memory that the driver allocated for the device to query the flow rules, the device * will first write it with a struct of gve_query_flow_rules_descriptor. Next to it, the device * will write an array of rules or rule ids with the count that specified in the descriptor. @@ -1325,3 +1440,66 @@ out: dma_pool_free(priv->adminq_pool, descriptor, descriptor_bus); return err; } + +static int gve_adminq_process_rss_query(struct gve_priv *priv, + struct gve_query_rss_descriptor *descriptor, + struct ethtool_rxfh_param *rxfh) +{ + u32 total_memory_length; + u16 hash_lut_length; + void *rss_info_addr; + __be32 *lut; + u16 i; + + total_memory_length = be32_to_cpu(descriptor->total_length); + hash_lut_length = priv->rss_lut_size * sizeof(*rxfh->indir); + + if (sizeof(*descriptor) + priv->rss_key_size + hash_lut_length != total_memory_length) { + dev_err(&priv->dev->dev, + "rss query desc from device has invalid length parameter.\n"); + return -EINVAL; + } + + rxfh->hfunc = descriptor->hash_alg; + + rss_info_addr = (void *)(descriptor + 1); + if (rxfh->key) + memcpy(rxfh->key, rss_info_addr, priv->rss_key_size); + + rss_info_addr += priv->rss_key_size; + lut = (__be32 *)rss_info_addr; + if (rxfh->indir) { + for (i = 0; i < priv->rss_lut_size; i++) + rxfh->indir[i] = be32_to_cpu(lut[i]); + } + + return 0; +} + +int gve_adminq_query_rss_config(struct gve_priv *priv, struct ethtool_rxfh_param *rxfh) +{ + struct gve_query_rss_descriptor *descriptor; + union gve_adminq_command cmd; + dma_addr_t descriptor_bus; + int err = 0; + + descriptor = dma_pool_alloc(priv->adminq_pool, GFP_KERNEL, &descriptor_bus); + if (!descriptor) + return -ENOMEM; + + memset(&cmd, 0, sizeof(cmd)); + cmd.opcode = cpu_to_be32(GVE_ADMINQ_QUERY_RSS); + cmd.query_rss = (struct gve_adminq_query_rss) { + .available_length = cpu_to_be64(GVE_ADMINQ_BUFFER_SIZE), + .rss_descriptor_addr = cpu_to_be64(descriptor_bus), + }; + err = gve_adminq_execute_cmd(priv, &cmd); + if (err) + goto out; + + err = gve_adminq_process_rss_query(priv, descriptor, rxfh); + +out: + dma_pool_free(priv->adminq_pool, descriptor, descriptor_bus); + return err; +} diff --git a/drivers/net/ethernet/google/gve/gve_adminq.h b/drivers/net/ethernet/google/gve/gve_adminq.h index ed1370c9b197..863683de9694 100644 --- a/drivers/net/ethernet/google/gve/gve_adminq.h +++ b/drivers/net/ethernet/google/gve/gve_adminq.h @@ -20,12 +20,14 @@ enum gve_adminq_opcodes { GVE_ADMINQ_DESTROY_TX_QUEUE = 0x7, GVE_ADMINQ_DESTROY_RX_QUEUE = 0x8, GVE_ADMINQ_DECONFIGURE_DEVICE_RESOURCES = 0x9, + GVE_ADMINQ_CONFIGURE_RSS = 0xA, GVE_ADMINQ_SET_DRIVER_PARAMETER = 0xB, GVE_ADMINQ_REPORT_STATS = 0xC, GVE_ADMINQ_REPORT_LINK_SPEED = 0xD, GVE_ADMINQ_GET_PTYPE_MAP = 0xE, GVE_ADMINQ_VERIFY_DRIVER_COMPATIBILITY = 0xF, GVE_ADMINQ_QUERY_FLOW_RULES = 0x10, + GVE_ADMINQ_QUERY_RSS = 0x12, /* For commands that are larger than 56 bytes */ GVE_ADMINQ_EXTENDED_COMMAND = 0xFF, @@ -164,6 +166,14 @@ struct gve_device_option_flow_steering { static_assert(sizeof(struct gve_device_option_flow_steering) == 12); +struct gve_device_option_rss_config { + __be32 supported_features_mask; + __be16 hash_key_size; + __be16 hash_lut_size; +}; + +static_assert(sizeof(struct gve_device_option_rss_config) == 8); + /* Terminology: * * RDA - Raw DMA Addressing - Buffers associated with SKBs are directly DMA @@ -182,6 +192,7 @@ enum gve_dev_opt_id { GVE_DEV_OPT_ID_JUMBO_FRAMES = 0x8, GVE_DEV_OPT_ID_BUFFER_SIZES = 0xa, GVE_DEV_OPT_ID_FLOW_STEERING = 0xb, + GVE_DEV_OPT_ID_RSS_CONFIG = 0xe, }; enum gve_dev_opt_req_feat_mask { @@ -194,6 +205,7 @@ enum gve_dev_opt_req_feat_mask { GVE_DEV_OPT_REQ_FEAT_MASK_BUFFER_SIZES = 0x0, GVE_DEV_OPT_REQ_FEAT_MASK_MODIFY_RING = 0x0, GVE_DEV_OPT_REQ_FEAT_MASK_FLOW_STEERING = 0x0, + GVE_DEV_OPT_REQ_FEAT_MASK_RSS_CONFIG = 0x0, }; enum gve_sup_feature_mask { @@ -201,6 +213,7 @@ enum gve_sup_feature_mask { GVE_SUP_JUMBO_FRAMES_MASK = 1 << 2, GVE_SUP_BUFFER_SIZES_MASK = 1 << 4, GVE_SUP_FLOW_STEERING_MASK = 1 << 5, + GVE_SUP_RSS_CONFIG_MASK = 1 << 7, }; #define GVE_DEV_OPT_LEN_GQI_RAW_ADDRESSING 0x0 @@ -214,6 +227,7 @@ enum gve_driver_capbility { gve_driver_capability_dqo_rda = 3, gve_driver_capability_alt_miss_compl = 4, gve_driver_capability_flexible_buffer_size = 5, + gve_driver_capability_flexible_rss_size = 6, }; #define GVE_CAP1(a) BIT((int)a) @@ -226,7 +240,8 @@ enum gve_driver_capbility { GVE_CAP1(gve_driver_capability_gqi_rda) | \ GVE_CAP1(gve_driver_capability_dqo_rda) | \ GVE_CAP1(gve_driver_capability_alt_miss_compl) | \ - GVE_CAP1(gve_driver_capability_flexible_buffer_size)) + GVE_CAP1(gve_driver_capability_flexible_buffer_size) | \ + GVE_CAP1(gve_driver_capability_flexible_rss_size)) #define GVE_DRIVER_CAPABILITY_FLAGS2 0x0 #define GVE_DRIVER_CAPABILITY_FLAGS3 0x0 @@ -509,6 +524,44 @@ struct gve_adminq_query_flow_rules { static_assert(sizeof(struct gve_adminq_query_flow_rules) == 24); +enum gve_rss_hash_type { + GVE_RSS_HASH_IPV4, + GVE_RSS_HASH_TCPV4, + GVE_RSS_HASH_IPV6, + GVE_RSS_HASH_IPV6_EX, + GVE_RSS_HASH_TCPV6, + GVE_RSS_HASH_TCPV6_EX, + GVE_RSS_HASH_UDPV4, + GVE_RSS_HASH_UDPV6, + GVE_RSS_HASH_UDPV6_EX, +}; + +struct gve_adminq_configure_rss { + __be16 hash_types; + u8 hash_alg; + u8 reserved; + __be16 hash_key_size; + __be16 hash_lut_size; + __be64 hash_key_addr; + __be64 hash_lut_addr; +}; + +static_assert(sizeof(struct gve_adminq_configure_rss) == 24); + +struct gve_query_rss_descriptor { + __be32 total_length; + __be16 hash_types; + u8 hash_alg; + u8 reserved; +}; + +struct gve_adminq_query_rss { + __be64 available_length; + __be64 rss_descriptor_addr; +}; + +static_assert(sizeof(struct gve_adminq_query_rss) == 16); + union gve_adminq_command { struct { __be32 opcode; @@ -530,6 +583,8 @@ union gve_adminq_command { struct gve_adminq_verify_driver_compatibility verify_driver_compatibility; struct gve_adminq_query_flow_rules query_flow_rules; + struct gve_adminq_configure_rss configure_rss; + struct gve_adminq_query_rss query_rss; struct gve_adminq_extended_command extended_command; }; }; @@ -568,6 +623,8 @@ int gve_adminq_add_flow_rule(struct gve_priv *priv, struct gve_adminq_flow_rule int gve_adminq_del_flow_rule(struct gve_priv *priv, u32 loc); int gve_adminq_reset_flow_rules(struct gve_priv *priv); int gve_adminq_query_flow_rules(struct gve_priv *priv, u16 query_opcode, u32 starting_loc); +int gve_adminq_configure_rss(struct gve_priv *priv, struct ethtool_rxfh_param *rxfh); +int gve_adminq_query_rss_config(struct gve_priv *priv, struct ethtool_rxfh_param *rxfh); struct gve_ptype_lut; int gve_adminq_get_ptype_map_dqo(struct gve_priv *priv, diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c index 5a8b490ab3ad..bdfc6e77b2af 100644 --- a/drivers/net/ethernet/google/gve/gve_ethtool.c +++ b/drivers/net/ethernet/google/gve/gve_ethtool.c @@ -75,7 +75,8 @@ static const char gve_gstrings_adminq_stats[][ETH_GSTRING_LEN] = { "adminq_destroy_tx_queue_cnt", "adminq_destroy_rx_queue_cnt", "adminq_dcfg_device_resources_cnt", "adminq_set_driver_parameter_cnt", "adminq_report_stats_cnt", "adminq_report_link_speed_cnt", "adminq_get_ptype_map_cnt", - "adminq_query_flow_rules", "adminq_cfg_flow_rule", + "adminq_query_flow_rules", "adminq_cfg_flow_rule", "adminq_cfg_rss_cnt", + "adminq_query_rss_cnt", }; static const char gve_gstrings_priv_flags[][ETH_GSTRING_LEN] = { @@ -453,6 +454,8 @@ gve_get_ethtool_stats(struct net_device *netdev, data[i++] = priv->adminq_get_ptype_map_cnt; data[i++] = priv->adminq_query_flow_rules_cnt; data[i++] = priv->adminq_cfg_flow_rule_cnt; + data[i++] = priv->adminq_cfg_rss_cnt; + data[i++] = priv->adminq_query_rss_cnt; } static void gve_get_channels(struct net_device *netdev, @@ -838,6 +841,41 @@ static int gve_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, u return err; } +static u32 gve_get_rxfh_key_size(struct net_device *netdev) +{ + struct gve_priv *priv = netdev_priv(netdev); + + return priv->rss_key_size; +} + +static u32 gve_get_rxfh_indir_size(struct net_device *netdev) +{ + struct gve_priv *priv = netdev_priv(netdev); + + return priv->rss_lut_size; +} + +static int gve_get_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh) +{ + struct gve_priv *priv = netdev_priv(netdev); + + if (!priv->rss_key_size || !priv->rss_lut_size) + return -EOPNOTSUPP; + + return gve_adminq_query_rss_config(priv, rxfh); +} + +static int gve_set_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh, + struct netlink_ext_ack *extack) +{ + struct gve_priv *priv = netdev_priv(netdev); + + if (!priv->rss_key_size || !priv->rss_lut_size) + return -EOPNOTSUPP; + + return gve_adminq_configure_rss(priv, rxfh); +} + const struct ethtool_ops gve_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_USECS, .supported_ring_params = ETHTOOL_RING_USE_TCP_DATA_SPLIT, @@ -851,6 +889,10 @@ const struct ethtool_ops gve_ethtool_ops = { .get_channels = gve_get_channels, .set_rxnfc = gve_set_rxnfc, .get_rxnfc = gve_get_rxnfc, + .get_rxfh_indir_size = gve_get_rxfh_indir_size, + .get_rxfh_key_size = gve_get_rxfh_key_size, + .get_rxfh = gve_get_rxfh, + .set_rxfh = gve_set_rxfh, .get_link = ethtool_op_get_link, .get_coalesce = gve_get_coalesce, .set_coalesce = gve_set_coalesce, diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c index b91e7a06b97f..beb815e5289b 100644 --- a/drivers/net/ethernet/hisilicon/hip04_eth.c +++ b/drivers/net/ethernet/hisilicon/hip04_eth.c @@ -947,6 +947,7 @@ static int hip04_mac_probe(struct platform_device *pdev) priv->tx_coalesce_timer.function = tx_done; priv->map = syscon_node_to_regmap(arg.np); + of_node_put(arg.np); if (IS_ERR(priv->map)) { dev_warn(d, "no syscon hisilicon,hip04-ppe\n"); ret = PTR_ERR(priv->map); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c index f75668c47935..58baac7103b3 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c @@ -734,7 +734,7 @@ hns_mac_register_phydev(struct mii_bus *mdio, struct hns_mac_cb *mac_cb, return -ENODATA; phy = get_phy_device(mdio, addr, is_c45); - if (!phy || IS_ERR(phy)) + if (IS_ERR_OR_NULL(phy)) return -EIO; phy->irq = mdio->irq[addr]; @@ -933,6 +933,7 @@ static int hns_mac_get_info(struct hns_mac_cb *mac_cb) mac_cb->cpld_ctrl = NULL; } else { syscon = syscon_node_to_regmap(cpld_args.np); + of_node_put(cpld_args.np); if (IS_ERR_OR_NULL(syscon)) { dev_dbg(mac_cb->dev, "no cpld-syscon found!\n"); mac_cb->cpld_ctrl = NULL; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 6c33195a1168..bd86efd92a5a 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -13,8 +13,9 @@ #include <linux/platform_device.h> #include <linux/if_vlan.h> #include <linux/crash_dump.h> -#include <net/ipv6.h> + #include <net/rtnetlink.h> + #include "hclge_cmd.h" #include "hclge_dcb.h" #include "hclge_main.h" @@ -6290,15 +6291,15 @@ static void hclge_fd_get_ip4_tuple(struct ethtool_rx_flow_spec *fs, static void hclge_fd_get_tcpip6_tuple(struct ethtool_rx_flow_spec *fs, struct hclge_fd_rule *rule, u8 ip_proto) { - be32_to_cpu_array(rule->tuples.src_ip, fs->h_u.tcp_ip6_spec.ip6src, - IPV6_SIZE); - be32_to_cpu_array(rule->tuples_mask.src_ip, fs->m_u.tcp_ip6_spec.ip6src, - IPV6_SIZE); + ipv6_addr_be32_to_cpu(rule->tuples.src_ip, + fs->h_u.tcp_ip6_spec.ip6src); + ipv6_addr_be32_to_cpu(rule->tuples_mask.src_ip, + fs->m_u.tcp_ip6_spec.ip6src); - be32_to_cpu_array(rule->tuples.dst_ip, fs->h_u.tcp_ip6_spec.ip6dst, - IPV6_SIZE); - be32_to_cpu_array(rule->tuples_mask.dst_ip, fs->m_u.tcp_ip6_spec.ip6dst, - IPV6_SIZE); + ipv6_addr_be32_to_cpu(rule->tuples.dst_ip, + fs->h_u.tcp_ip6_spec.ip6dst); + ipv6_addr_be32_to_cpu(rule->tuples_mask.dst_ip, + fs->m_u.tcp_ip6_spec.ip6dst); rule->tuples.src_port = be16_to_cpu(fs->h_u.tcp_ip6_spec.psrc); rule->tuples_mask.src_port = be16_to_cpu(fs->m_u.tcp_ip6_spec.psrc); @@ -6319,15 +6320,15 @@ static void hclge_fd_get_tcpip6_tuple(struct ethtool_rx_flow_spec *fs, static void hclge_fd_get_ip6_tuple(struct ethtool_rx_flow_spec *fs, struct hclge_fd_rule *rule) { - be32_to_cpu_array(rule->tuples.src_ip, fs->h_u.usr_ip6_spec.ip6src, - IPV6_SIZE); - be32_to_cpu_array(rule->tuples_mask.src_ip, fs->m_u.usr_ip6_spec.ip6src, - IPV6_SIZE); + ipv6_addr_be32_to_cpu(rule->tuples.src_ip, + fs->h_u.usr_ip6_spec.ip6src); + ipv6_addr_be32_to_cpu(rule->tuples_mask.src_ip, + fs->m_u.usr_ip6_spec.ip6src); - be32_to_cpu_array(rule->tuples.dst_ip, fs->h_u.usr_ip6_spec.ip6dst, - IPV6_SIZE); - be32_to_cpu_array(rule->tuples_mask.dst_ip, fs->m_u.usr_ip6_spec.ip6dst, - IPV6_SIZE); + ipv6_addr_be32_to_cpu(rule->tuples.dst_ip, + fs->h_u.usr_ip6_spec.ip6dst); + ipv6_addr_be32_to_cpu(rule->tuples_mask.dst_ip, + fs->m_u.usr_ip6_spec.ip6dst); rule->tuples.ip_proto = fs->h_u.usr_ip6_spec.l4_proto; rule->tuples_mask.ip_proto = fs->m_u.usr_ip6_spec.l4_proto; @@ -6756,21 +6757,19 @@ static void hclge_fd_get_tcpip6_info(struct hclge_fd_rule *rule, struct ethtool_tcpip6_spec *spec, struct ethtool_tcpip6_spec *spec_mask) { - cpu_to_be32_array(spec->ip6src, - rule->tuples.src_ip, IPV6_SIZE); - cpu_to_be32_array(spec->ip6dst, - rule->tuples.dst_ip, IPV6_SIZE); + ipv6_addr_cpu_to_be32(spec->ip6src, rule->tuples.src_ip); + ipv6_addr_cpu_to_be32(spec->ip6dst, rule->tuples.dst_ip); if (rule->unused_tuple & BIT(INNER_SRC_IP)) memset(spec_mask->ip6src, 0, sizeof(spec_mask->ip6src)); else - cpu_to_be32_array(spec_mask->ip6src, rule->tuples_mask.src_ip, - IPV6_SIZE); + ipv6_addr_cpu_to_be32(spec_mask->ip6src, + rule->tuples_mask.src_ip); if (rule->unused_tuple & BIT(INNER_DST_IP)) memset(spec_mask->ip6dst, 0, sizeof(spec_mask->ip6dst)); else - cpu_to_be32_array(spec_mask->ip6dst, rule->tuples_mask.dst_ip, - IPV6_SIZE); + ipv6_addr_cpu_to_be32(spec_mask->ip6dst, + rule->tuples_mask.dst_ip); spec->tclass = rule->tuples.ip_tos; spec_mask->tclass = rule->unused_tuple & BIT(INNER_IP_TOS) ? @@ -6789,19 +6788,19 @@ static void hclge_fd_get_ip6_info(struct hclge_fd_rule *rule, struct ethtool_usrip6_spec *spec, struct ethtool_usrip6_spec *spec_mask) { - cpu_to_be32_array(spec->ip6src, rule->tuples.src_ip, IPV6_SIZE); - cpu_to_be32_array(spec->ip6dst, rule->tuples.dst_ip, IPV6_SIZE); + ipv6_addr_cpu_to_be32(spec->ip6src, rule->tuples.src_ip); + ipv6_addr_cpu_to_be32(spec->ip6dst, rule->tuples.dst_ip); if (rule->unused_tuple & BIT(INNER_SRC_IP)) memset(spec_mask->ip6src, 0, sizeof(spec_mask->ip6src)); else - cpu_to_be32_array(spec_mask->ip6src, - rule->tuples_mask.src_ip, IPV6_SIZE); + ipv6_addr_cpu_to_be32(spec_mask->ip6src, + rule->tuples_mask.src_ip); if (rule->unused_tuple & BIT(INNER_DST_IP)) memset(spec_mask->ip6dst, 0, sizeof(spec_mask->ip6dst)); else - cpu_to_be32_array(spec_mask->ip6dst, - rule->tuples_mask.dst_ip, IPV6_SIZE); + ipv6_addr_cpu_to_be32(spec_mask->ip6dst, + rule->tuples_mask.dst_ip); spec->tclass = rule->tuples.ip_tos; spec_mask->tclass = rule->unused_tuple & BIT(INNER_IP_TOS) ? @@ -7019,7 +7018,7 @@ static void hclge_fd_get_flow_tuples(const struct flow_keys *fkeys, } else { int i; - for (i = 0; i < IPV6_SIZE; i++) { + for (i = 0; i < IPV6_ADDR_WORDS; i++) { tuples->src_ip[i] = be32_to_cpu(flow_ip6_src[i]); tuples->dst_ip[i] = be32_to_cpu(flow_ip6_dst[i]); } @@ -7274,14 +7273,14 @@ static int hclge_get_cls_key_ip(const struct flow_rule *flow, struct flow_match_ipv6_addrs match; flow_rule_match_ipv6_addrs(flow, &match); - be32_to_cpu_array(rule->tuples.src_ip, match.key->src.s6_addr32, - IPV6_SIZE); - be32_to_cpu_array(rule->tuples_mask.src_ip, - match.mask->src.s6_addr32, IPV6_SIZE); - be32_to_cpu_array(rule->tuples.dst_ip, match.key->dst.s6_addr32, - IPV6_SIZE); - be32_to_cpu_array(rule->tuples_mask.dst_ip, - match.mask->dst.s6_addr32, IPV6_SIZE); + ipv6_addr_be32_to_cpu(rule->tuples.src_ip, + match.key->src.s6_addr32); + ipv6_addr_be32_to_cpu(rule->tuples_mask.src_ip, + match.mask->src.s6_addr32); + ipv6_addr_be32_to_cpu(rule->tuples.dst_ip, + match.key->dst.s6_addr32); + ipv6_addr_be32_to_cpu(rule->tuples_mask.dst_ip, + match.mask->dst.s6_addr32); } else { rule->unused_tuple |= BIT(INNER_SRC_IP); rule->unused_tuple |= BIT(INNER_DST_IP); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index b5178b0f88b3..b9fc719880bb 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -8,7 +8,9 @@ #include <linux/phy.h> #include <linux/if_vlan.h> #include <linux/kfifo.h> + #include <net/devlink.h> +#include <net/ipv6.h> #include "hclge_cmd.h" #include "hclge_ptp.h" @@ -718,15 +720,15 @@ struct hclge_fd_cfg { }; #define IPV4_INDEX 3 -#define IPV6_SIZE 4 + struct hclge_fd_rule_tuples { u8 src_mac[ETH_ALEN]; u8 dst_mac[ETH_ALEN]; /* Be compatible for ip address of both ipv4 and ipv6. * For ipv4 address, we store it in src/dst_ip[3]. */ - u32 src_ip[IPV6_SIZE]; - u32 dst_ip[IPV6_SIZE]; + u32 src_ip[IPV6_ADDR_WORDS]; + u32 dst_ip[IPV6_ADDR_WORDS]; u16 src_port; u16 dst_port; u16 vlan_tag1; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c index 65b9dcd38137..6db415d8b917 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c @@ -134,17 +134,17 @@ void hclgevf_get_regs(struct hnae3_handle *handle, u32 *version, reg += hclgevf_reg_get_header(reg); /* fetching per-VF registers values from VF PCIe register space */ - reg_um = sizeof(cmdq_reg_addr_list) / sizeof(u32); + reg_um = ARRAY_SIZE(cmdq_reg_addr_list); reg += hclgevf_reg_get_tlv(HCLGEVF_REG_TAG_CMDQ, reg_um, reg); for (i = 0; i < reg_um; i++) *reg++ = hclgevf_read_dev(&hdev->hw, cmdq_reg_addr_list[i]); - reg_um = sizeof(common_reg_addr_list) / sizeof(u32); + reg_um = ARRAY_SIZE(common_reg_addr_list); reg += hclgevf_reg_get_tlv(HCLGEVF_REG_TAG_COMMON, reg_um, reg); for (i = 0; i < reg_um; i++) *reg++ = hclgevf_read_dev(&hdev->hw, common_reg_addr_list[i]); - reg_um = sizeof(ring_reg_addr_list) / sizeof(u32); + reg_um = ARRAY_SIZE(ring_reg_addr_list); for (j = 0; j < hdev->num_tqps; j++) { reg += hclgevf_reg_get_tlv(HCLGEVF_REG_TAG_RING, reg_um, reg); for (i = 0; i < reg_um; i++) @@ -153,7 +153,7 @@ void hclgevf_get_regs(struct hnae3_handle *handle, u32 *version, HCLGEVF_RING_REG_OFFSET * j); } - reg_um = sizeof(tqp_intr_reg_addr_list) / sizeof(u32); + reg_um = ARRAY_SIZE(tqp_intr_reg_addr_list); for (j = 0; j < hdev->num_msi_used - 1; j++) { reg += hclgevf_reg_get_tlv(HCLGEVF_REG_TAG_TQP_INTR, reg_um, reg); for (i = 0; i < reg_um; i++) diff --git a/drivers/net/ethernet/hisilicon/hns_mdio.c b/drivers/net/ethernet/hisilicon/hns_mdio.c index ed73707176c1..8a047145f0c5 100644 --- a/drivers/net/ethernet/hisilicon/hns_mdio.c +++ b/drivers/net/ethernet/hisilicon/hns_mdio.c @@ -575,6 +575,7 @@ static int hns_mdio_probe(struct platform_device *pdev) MDIO_SC_RESET_ST; } } + of_node_put(reg_args.np); } else { dev_warn(&pdev->dev, "find syscon ret = %#x\n", ret); mdio_dev->subctrl_vbase = NULL; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c index 0304f03d4093..c559dd4291d3 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c @@ -1471,7 +1471,6 @@ static void hinic_get_strings(struct net_device *netdev, u32 stringset, u8 *data) { struct hinic_dev *nic_dev = netdev_priv(netdev); - char *p = (char *)data; u16 i, j; switch (stringset) { @@ -1479,31 +1478,19 @@ static void hinic_get_strings(struct net_device *netdev, memcpy(data, *hinic_test_strings, sizeof(hinic_test_strings)); return; case ETH_SS_STATS: - for (i = 0; i < ARRAY_SIZE(hinic_function_stats); i++) { - memcpy(p, hinic_function_stats[i].name, - ETH_GSTRING_LEN); - p += ETH_GSTRING_LEN; - } + for (i = 0; i < ARRAY_SIZE(hinic_function_stats); i++) + ethtool_puts(&data, hinic_function_stats[i].name); - for (i = 0; i < ARRAY_SIZE(hinic_port_stats); i++) { - memcpy(p, hinic_port_stats[i].name, - ETH_GSTRING_LEN); - p += ETH_GSTRING_LEN; - } + for (i = 0; i < ARRAY_SIZE(hinic_port_stats); i++) + ethtool_puts(&data, hinic_port_stats[i].name); - for (i = 0; i < nic_dev->num_qps; i++) { - for (j = 0; j < ARRAY_SIZE(hinic_tx_queue_stats); j++) { - sprintf(p, hinic_tx_queue_stats[j].name, i); - p += ETH_GSTRING_LEN; - } - } + for (i = 0; i < nic_dev->num_qps; i++) + for (j = 0; j < ARRAY_SIZE(hinic_tx_queue_stats); j++) + ethtool_sprintf(&data, hinic_tx_queue_stats[j].name, i); - for (i = 0; i < nic_dev->num_qps; i++) { - for (j = 0; j < ARRAY_SIZE(hinic_rx_queue_stats); j++) { - sprintf(p, hinic_rx_queue_stats[j].name, i); - p += ETH_GSTRING_LEN; - } - } + for (i = 0; i < nic_dev->num_qps; i++) + for (j = 0; j < ARRAY_SIZE(hinic_rx_queue_stats); j++) + ethtool_sprintf(&data, hinic_rx_queue_stats[j].name, i); return; default: diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c index 1e29e5c9a2df..c41c3f1cc506 100644 --- a/drivers/net/ethernet/ibm/ehea/ehea_main.c +++ b/drivers/net/ethernet/ibm/ehea/ehea_main.c @@ -3063,14 +3063,13 @@ static void ehea_shutdown_single_port(struct ehea_port *port) static int ehea_setup_ports(struct ehea_adapter *adapter) { struct device_node *lhea_dn; - struct device_node *eth_dn = NULL; + struct device_node *eth_dn; const u32 *dn_log_port_id; int i = 0; lhea_dn = adapter->ofdev->dev.of_node; - while ((eth_dn = of_get_next_child(lhea_dn, eth_dn))) { - + for_each_child_of_node(lhea_dn, eth_dn) { dn_log_port_id = of_get_property(eth_dn, "ibm,hea-port-no", NULL); if (!dn_log_port_id) { @@ -3102,12 +3101,11 @@ static struct device_node *ehea_get_eth_dn(struct ehea_adapter *adapter, u32 logical_port_id) { struct device_node *lhea_dn; - struct device_node *eth_dn = NULL; + struct device_node *eth_dn; const u32 *dn_log_port_id; lhea_dn = adapter->ofdev->dev.of_node; - while ((eth_dn = of_get_next_child(lhea_dn, eth_dn))) { - + for_each_child_of_node(lhea_dn, eth_dn) { dn_log_port_id = of_get_property(eth_dn, "ibm,hea-port-no", NULL); if (dn_log_port_id) diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index 4c9d9badd698..b619a3ec245b 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -39,7 +39,8 @@ #include "ibmveth.h" static irqreturn_t ibmveth_interrupt(int irq, void *dev_instance); -static void ibmveth_rxq_harvest_buffer(struct ibmveth_adapter *adapter); +static void ibmveth_rxq_harvest_buffer(struct ibmveth_adapter *adapter, + bool reuse); static unsigned long ibmveth_get_desired_dma(struct vio_dev *vdev); static struct kobj_type ktype_veth_pool; @@ -226,6 +227,16 @@ static void ibmveth_replenish_buffer_pool(struct ibmveth_adapter *adapter, for (i = 0; i < count; ++i) { union ibmveth_buf_desc desc; + free_index = pool->consumer_index; + index = pool->free_map[free_index]; + skb = NULL; + + BUG_ON(index == IBM_VETH_INVALID_MAP); + + /* are we allocating a new buffer or recycling an old one */ + if (pool->skbuff[index]) + goto reuse; + skb = netdev_alloc_skb(adapter->netdev, pool->buff_size); if (!skb) { @@ -235,46 +246,46 @@ static void ibmveth_replenish_buffer_pool(struct ibmveth_adapter *adapter, break; } - free_index = pool->consumer_index; - pool->consumer_index++; - if (pool->consumer_index >= pool->size) - pool->consumer_index = 0; - index = pool->free_map[free_index]; - - BUG_ON(index == IBM_VETH_INVALID_MAP); - BUG_ON(pool->skbuff[index] != NULL); - dma_addr = dma_map_single(&adapter->vdev->dev, skb->data, pool->buff_size, DMA_FROM_DEVICE); if (dma_mapping_error(&adapter->vdev->dev, dma_addr)) goto failure; - pool->free_map[free_index] = IBM_VETH_INVALID_MAP; pool->dma_addr[index] = dma_addr; pool->skbuff[index] = skb; - correlator = ((u64)pool->index << 32) | index; - *(u64 *)skb->data = correlator; - - desc.fields.flags_len = IBMVETH_BUF_VALID | pool->buff_size; - desc.fields.address = dma_addr; - if (rx_flush) { unsigned int len = min(pool->buff_size, - adapter->netdev->mtu + - IBMVETH_BUFF_OH); + adapter->netdev->mtu + + IBMVETH_BUFF_OH); ibmveth_flush_buffer(skb->data, len); } +reuse: + dma_addr = pool->dma_addr[index]; + desc.fields.flags_len = IBMVETH_BUF_VALID | pool->buff_size; + desc.fields.address = dma_addr; + + correlator = ((u64)pool->index << 32) | index; + *(u64 *)pool->skbuff[index]->data = correlator; + lpar_rc = h_add_logical_lan_buffer(adapter->vdev->unit_address, desc.desc); if (lpar_rc != H_SUCCESS) { + netdev_warn(adapter->netdev, + "%sadd_logical_lan failed %lu\n", + skb ? "" : "When recycling: ", lpar_rc); goto failure; - } else { - buffers_added++; - adapter->replenish_add_buff_success++; } + + pool->free_map[free_index] = IBM_VETH_INVALID_MAP; + pool->consumer_index++; + if (pool->consumer_index >= pool->size) + pool->consumer_index = 0; + + buffers_added++; + adapter->replenish_add_buff_success++; } mb(); @@ -282,17 +293,13 @@ static void ibmveth_replenish_buffer_pool(struct ibmveth_adapter *adapter, return; failure: - pool->free_map[free_index] = index; - pool->skbuff[index] = NULL; - if (pool->consumer_index == 0) - pool->consumer_index = pool->size - 1; - else - pool->consumer_index--; - if (!dma_mapping_error(&adapter->vdev->dev, dma_addr)) + + if (dma_addr && !dma_mapping_error(&adapter->vdev->dev, dma_addr)) dma_unmap_single(&adapter->vdev->dev, pool->dma_addr[index], pool->buff_size, DMA_FROM_DEVICE); - dev_kfree_skb_any(skb); + dev_kfree_skb_any(pool->skbuff[index]); + pool->skbuff[index] = NULL; adapter->replenish_add_buff_failure++; mb(); @@ -365,7 +372,7 @@ static void ibmveth_free_buffer_pool(struct ibmveth_adapter *adapter, /* remove a buffer from a pool */ static void ibmveth_remove_buffer_from_pool(struct ibmveth_adapter *adapter, - u64 correlator) + u64 correlator, bool reuse) { unsigned int pool = correlator >> 32; unsigned int index = correlator & 0xffffffffUL; @@ -376,15 +383,23 @@ static void ibmveth_remove_buffer_from_pool(struct ibmveth_adapter *adapter, BUG_ON(index >= adapter->rx_buff_pool[pool].size); skb = adapter->rx_buff_pool[pool].skbuff[index]; - BUG_ON(skb == NULL); - adapter->rx_buff_pool[pool].skbuff[index] = NULL; + /* if we are going to reuse the buffer then keep the pointers around + * but mark index as available. replenish will see the skb pointer and + * assume it is to be recycled. + */ + if (!reuse) { + /* remove the skb pointer to mark free. actual freeing is done + * by upper level networking after gro_recieve + */ + adapter->rx_buff_pool[pool].skbuff[index] = NULL; - dma_unmap_single(&adapter->vdev->dev, - adapter->rx_buff_pool[pool].dma_addr[index], - adapter->rx_buff_pool[pool].buff_size, - DMA_FROM_DEVICE); + dma_unmap_single(&adapter->vdev->dev, + adapter->rx_buff_pool[pool].dma_addr[index], + adapter->rx_buff_pool[pool].buff_size, + DMA_FROM_DEVICE); + } free_index = adapter->rx_buff_pool[pool].producer_index; adapter->rx_buff_pool[pool].producer_index++; @@ -411,51 +426,13 @@ static inline struct sk_buff *ibmveth_rxq_get_buffer(struct ibmveth_adapter *ada return adapter->rx_buff_pool[pool].skbuff[index]; } -/* recycle the current buffer on the rx queue */ -static int ibmveth_rxq_recycle_buffer(struct ibmveth_adapter *adapter) +static void ibmveth_rxq_harvest_buffer(struct ibmveth_adapter *adapter, + bool reuse) { - u32 q_index = adapter->rx_queue.index; - u64 correlator = adapter->rx_queue.queue_addr[q_index].correlator; - unsigned int pool = correlator >> 32; - unsigned int index = correlator & 0xffffffffUL; - union ibmveth_buf_desc desc; - unsigned long lpar_rc; - int ret = 1; - - BUG_ON(pool >= IBMVETH_NUM_BUFF_POOLS); - BUG_ON(index >= adapter->rx_buff_pool[pool].size); - - if (!adapter->rx_buff_pool[pool].active) { - ibmveth_rxq_harvest_buffer(adapter); - ibmveth_free_buffer_pool(adapter, &adapter->rx_buff_pool[pool]); - goto out; - } - - desc.fields.flags_len = IBMVETH_BUF_VALID | - adapter->rx_buff_pool[pool].buff_size; - desc.fields.address = adapter->rx_buff_pool[pool].dma_addr[index]; - - lpar_rc = h_add_logical_lan_buffer(adapter->vdev->unit_address, desc.desc); - - if (lpar_rc != H_SUCCESS) { - netdev_dbg(adapter->netdev, "h_add_logical_lan_buffer failed " - "during recycle rc=%ld", lpar_rc); - ibmveth_remove_buffer_from_pool(adapter, adapter->rx_queue.queue_addr[adapter->rx_queue.index].correlator); - ret = 0; - } - - if (++adapter->rx_queue.index == adapter->rx_queue.num_slots) { - adapter->rx_queue.index = 0; - adapter->rx_queue.toggle = !adapter->rx_queue.toggle; - } - -out: - return ret; -} + u64 cor; -static void ibmveth_rxq_harvest_buffer(struct ibmveth_adapter *adapter) -{ - ibmveth_remove_buffer_from_pool(adapter, adapter->rx_queue.queue_addr[adapter->rx_queue.index].correlator); + cor = adapter->rx_queue.queue_addr[adapter->rx_queue.index].correlator; + ibmveth_remove_buffer_from_pool(adapter, cor, reuse); if (++adapter->rx_queue.index == adapter->rx_queue.num_slots) { adapter->rx_queue.index = 0; @@ -1337,6 +1314,7 @@ static int ibmveth_poll(struct napi_struct *napi, int budget) unsigned long lpar_rc; u16 mss = 0; +restart_poll: while (frames_processed < budget) { if (!ibmveth_rxq_pending_buffer(adapter)) break; @@ -1346,7 +1324,7 @@ static int ibmveth_poll(struct napi_struct *napi, int budget) wmb(); /* suggested by larson1 */ adapter->rx_invalid_buffer++; netdev_dbg(netdev, "recycling invalid buffer\n"); - ibmveth_rxq_recycle_buffer(adapter); + ibmveth_rxq_harvest_buffer(adapter, true); } else { struct sk_buff *skb, *new_skb; int length = ibmveth_rxq_frame_length(adapter); @@ -1379,11 +1357,10 @@ static int ibmveth_poll(struct napi_struct *napi, int budget) if (rx_flush) ibmveth_flush_buffer(skb->data, length + offset); - if (!ibmveth_rxq_recycle_buffer(adapter)) - kfree_skb(skb); + ibmveth_rxq_harvest_buffer(adapter, true); skb = new_skb; } else { - ibmveth_rxq_harvest_buffer(adapter); + ibmveth_rxq_harvest_buffer(adapter, false); skb_reserve(skb, offset); } @@ -1420,24 +1397,25 @@ static int ibmveth_poll(struct napi_struct *napi, int budget) ibmveth_replenish_task(adapter); - if (frames_processed < budget) { - napi_complete_done(napi, frames_processed); + if (frames_processed == budget) + goto out; - /* We think we are done - reenable interrupts, - * then check once more to make sure we are done. - */ - lpar_rc = h_vio_signal(adapter->vdev->unit_address, - VIO_IRQ_ENABLE); + if (!napi_complete_done(napi, frames_processed)) + goto out; - BUG_ON(lpar_rc != H_SUCCESS); + /* We think we are done - reenable interrupts, + * then check once more to make sure we are done. + */ + lpar_rc = h_vio_signal(adapter->vdev->unit_address, VIO_IRQ_ENABLE); + BUG_ON(lpar_rc != H_SUCCESS); - if (ibmveth_rxq_pending_buffer(adapter) && - napi_schedule(napi)) { - lpar_rc = h_vio_signal(adapter->vdev->unit_address, - VIO_IRQ_DISABLE); - } + if (ibmveth_rxq_pending_buffer(adapter) && napi_schedule(napi)) { + lpar_rc = h_vio_signal(adapter->vdev->unit_address, + VIO_IRQ_DISABLE); + goto restart_poll; } +out: return frames_processed; } diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 23ebeb143987..87e693a81433 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -117,6 +117,7 @@ static void free_long_term_buff(struct ibmvnic_adapter *adapter, struct ibmvnic_long_term_buff *ltb); static void ibmvnic_disable_irqs(struct ibmvnic_adapter *adapter); static void flush_reset_queue(struct ibmvnic_adapter *adapter); +static void print_subcrq_error(struct device *dev, int rc, const char *func); struct ibmvnic_stat { char name[ETH_GSTRING_LEN]; @@ -2140,63 +2141,49 @@ static int ibmvnic_close(struct net_device *netdev) } /** - * build_hdr_data - creates L2/L3/L4 header data buffer + * get_hdr_lens - fills list of L2/L3/L4 hdr lens * @hdr_field: bitfield determining needed headers * @skb: socket buffer - * @hdr_len: array of header lengths - * @hdr_data: buffer to write the header to + * @hdr_len: array of header lengths to be filled * * Reads hdr_field to determine which headers are needed by firmware. * Builds a buffer containing these headers. Saves individual header * lengths and total buffer length to be used to build descriptors. + * + * Return: total len of all headers */ -static int build_hdr_data(u8 hdr_field, struct sk_buff *skb, - int *hdr_len, u8 *hdr_data) +static int get_hdr_lens(u8 hdr_field, struct sk_buff *skb, + int *hdr_len) { int len = 0; - u8 *hdr; - if (skb_vlan_tagged(skb) && !skb_vlan_tag_present(skb)) - hdr_len[0] = sizeof(struct vlan_ethhdr); - else - hdr_len[0] = sizeof(struct ethhdr); + + if ((hdr_field >> 6) & 1) { + hdr_len[0] = skb_mac_header_len(skb); + len += hdr_len[0]; + } + + if ((hdr_field >> 5) & 1) { + hdr_len[1] = skb_network_header_len(skb); + len += hdr_len[1]; + } + + if (!((hdr_field >> 4) & 1)) + return len; if (skb->protocol == htons(ETH_P_IP)) { - hdr_len[1] = ip_hdr(skb)->ihl * 4; if (ip_hdr(skb)->protocol == IPPROTO_TCP) hdr_len[2] = tcp_hdrlen(skb); else if (ip_hdr(skb)->protocol == IPPROTO_UDP) hdr_len[2] = sizeof(struct udphdr); } else if (skb->protocol == htons(ETH_P_IPV6)) { - hdr_len[1] = sizeof(struct ipv6hdr); if (ipv6_hdr(skb)->nexthdr == IPPROTO_TCP) hdr_len[2] = tcp_hdrlen(skb); else if (ipv6_hdr(skb)->nexthdr == IPPROTO_UDP) hdr_len[2] = sizeof(struct udphdr); - } else if (skb->protocol == htons(ETH_P_ARP)) { - hdr_len[1] = arp_hdr_len(skb->dev); - hdr_len[2] = 0; } - memset(hdr_data, 0, 120); - if ((hdr_field >> 6) & 1) { - hdr = skb_mac_header(skb); - memcpy(hdr_data, hdr, hdr_len[0]); - len += hdr_len[0]; - } - - if ((hdr_field >> 5) & 1) { - hdr = skb_network_header(skb); - memcpy(hdr_data + len, hdr, hdr_len[1]); - len += hdr_len[1]; - } - - if ((hdr_field >> 4) & 1) { - hdr = skb_transport_header(skb); - memcpy(hdr_data + len, hdr, hdr_len[2]); - len += hdr_len[2]; - } - return len; + return len + hdr_len[2]; } /** @@ -2209,12 +2196,14 @@ static int build_hdr_data(u8 hdr_field, struct sk_buff *skb, * * Creates header and, if needed, header extension descriptors and * places them in a descriptor array, scrq_arr + * + * Return: Number of header descs */ static int create_hdr_descs(u8 hdr_field, u8 *hdr_data, int len, int *hdr_len, union sub_crq *scrq_arr) { - union sub_crq hdr_desc; + union sub_crq *hdr_desc; int tmp_len = len; int num_descs = 0; u8 *data, *cur; @@ -2223,28 +2212,26 @@ static int create_hdr_descs(u8 hdr_field, u8 *hdr_data, int len, int *hdr_len, while (tmp_len > 0) { cur = hdr_data + len - tmp_len; - memset(&hdr_desc, 0, sizeof(hdr_desc)); - if (cur != hdr_data) { - data = hdr_desc.hdr_ext.data; + hdr_desc = &scrq_arr[num_descs]; + if (num_descs) { + data = hdr_desc->hdr_ext.data; tmp = tmp_len > 29 ? 29 : tmp_len; - hdr_desc.hdr_ext.first = IBMVNIC_CRQ_CMD; - hdr_desc.hdr_ext.type = IBMVNIC_HDR_EXT_DESC; - hdr_desc.hdr_ext.len = tmp; + hdr_desc->hdr_ext.first = IBMVNIC_CRQ_CMD; + hdr_desc->hdr_ext.type = IBMVNIC_HDR_EXT_DESC; + hdr_desc->hdr_ext.len = tmp; } else { - data = hdr_desc.hdr.data; + data = hdr_desc->hdr.data; tmp = tmp_len > 24 ? 24 : tmp_len; - hdr_desc.hdr.first = IBMVNIC_CRQ_CMD; - hdr_desc.hdr.type = IBMVNIC_HDR_DESC; - hdr_desc.hdr.len = tmp; - hdr_desc.hdr.l2_len = (u8)hdr_len[0]; - hdr_desc.hdr.l3_len = cpu_to_be16((u16)hdr_len[1]); - hdr_desc.hdr.l4_len = (u8)hdr_len[2]; - hdr_desc.hdr.flag = hdr_field << 1; + hdr_desc->hdr.first = IBMVNIC_CRQ_CMD; + hdr_desc->hdr.type = IBMVNIC_HDR_DESC; + hdr_desc->hdr.len = tmp; + hdr_desc->hdr.l2_len = (u8)hdr_len[0]; + hdr_desc->hdr.l3_len = cpu_to_be16((u16)hdr_len[1]); + hdr_desc->hdr.l4_len = (u8)hdr_len[2]; + hdr_desc->hdr.flag = hdr_field << 1; } memcpy(data, cur, tmp); tmp_len -= tmp; - *scrq_arr = hdr_desc; - scrq_arr++; num_descs++; } @@ -2267,13 +2254,11 @@ static void build_hdr_descs_arr(struct sk_buff *skb, int *num_entries, u8 hdr_field) { int hdr_len[3] = {0, 0, 0}; - u8 hdr_data[140] = {0}; int tot_len; - tot_len = build_hdr_data(hdr_field, skb, hdr_len, - hdr_data); - *num_entries += create_hdr_descs(hdr_field, hdr_data, tot_len, hdr_len, - indir_arr + 1); + tot_len = get_hdr_lens(hdr_field, skb, hdr_len); + *num_entries += create_hdr_descs(hdr_field, skb_mac_header(skb), + tot_len, hdr_len, indir_arr + 1); } static int ibmvnic_xmit_workarounds(struct sk_buff *skb, @@ -2350,8 +2335,29 @@ static void ibmvnic_tx_scrq_clean_buffer(struct ibmvnic_adapter *adapter, } } +static int send_subcrq_direct(struct ibmvnic_adapter *adapter, + u64 remote_handle, u64 *entry) +{ + unsigned int ua = adapter->vdev->unit_address; + struct device *dev = &adapter->vdev->dev; + int rc; + + /* Make sure the hypervisor sees the complete request */ + dma_wmb(); + rc = plpar_hcall_norets(H_SEND_SUB_CRQ, ua, + cpu_to_be64(remote_handle), + cpu_to_be64(entry[0]), cpu_to_be64(entry[1]), + cpu_to_be64(entry[2]), cpu_to_be64(entry[3])); + + if (rc) + print_subcrq_error(dev, rc, __func__); + + return rc; +} + static int ibmvnic_tx_scrq_flush(struct ibmvnic_adapter *adapter, - struct ibmvnic_sub_crq_queue *tx_scrq) + struct ibmvnic_sub_crq_queue *tx_scrq, + bool indirect) { struct ibmvnic_ind_xmit_queue *ind_bufp; u64 dma_addr; @@ -2366,7 +2372,13 @@ static int ibmvnic_tx_scrq_flush(struct ibmvnic_adapter *adapter, if (!entries) return 0; - rc = send_subcrq_indirect(adapter, handle, dma_addr, entries); + + if (indirect) + rc = send_subcrq_indirect(adapter, handle, dma_addr, entries); + else + rc = send_subcrq_direct(adapter, handle, + (u64 *)ind_bufp->indir_arr); + if (rc) ibmvnic_tx_scrq_clean_buffer(adapter, tx_scrq); else @@ -2397,6 +2409,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) unsigned long lpar_rc; union sub_crq tx_crq; unsigned int offset; + bool use_scrq_send_direct = false; int num_entries = 1; unsigned char *dst; int bufidx = 0; @@ -2424,7 +2437,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) tx_dropped++; tx_send_failed++; ret = NETDEV_TX_OK; - lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq); + lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq, true); if (lpar_rc != H_SUCCESS) goto tx_err; goto out; @@ -2442,7 +2455,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) tx_send_failed++; tx_dropped++; ret = NETDEV_TX_OK; - lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq); + lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq, true); if (lpar_rc != H_SUCCESS) goto tx_err; goto out; @@ -2456,6 +2469,18 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) memset(dst, 0, tx_pool->buf_size); data_dma_addr = ltb->addr + offset; + /* if we are going to send_subcrq_direct this then we need to + * update the checksum before copying the data into ltb. Essentially + * these packets force disable CSO so that we can guarantee that + * FW does not need header info and we can send direct. + */ + if (!skb_is_gso(skb) && !ind_bufp->index && !netdev_xmit_more()) { + use_scrq_send_direct = true; + if (skb->ip_summed == CHECKSUM_PARTIAL && + skb_checksum_help(skb)) + use_scrq_send_direct = false; + } + if (skb_shinfo(skb)->nr_frags) { int cur, i; @@ -2475,9 +2500,6 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) skb_copy_from_linear_data(skb, dst, skb->len); } - /* post changes to long_term_buff *dst before VIOS accessing it */ - dma_wmb(); - tx_pool->consumer_index = (tx_pool->consumer_index + 1) % tx_pool->num_buffers; @@ -2540,6 +2562,18 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) tx_crq.v1.flags1 |= IBMVNIC_TX_LSO; tx_crq.v1.mss = cpu_to_be16(skb_shinfo(skb)->gso_size); hdrs += 2; + } else if (use_scrq_send_direct) { + /* See above comment, CSO disabled with direct xmit */ + tx_crq.v1.flags1 &= ~(IBMVNIC_TX_CHKSUM_OFFLOAD); + ind_bufp->index = 1; + tx_buff->num_entries = 1; + netdev_tx_sent_queue(txq, skb->len); + ind_bufp->indir_arr[0] = tx_crq; + lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq, false); + if (lpar_rc != H_SUCCESS) + goto tx_err; + + goto early_exit; } if ((*hdrs >> 7) & 1) @@ -2549,7 +2583,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) tx_buff->num_entries = num_entries; /* flush buffer if current entry can not fit */ if (num_entries + ind_bufp->index > IBMVNIC_MAX_IND_DESCS) { - lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq); + lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq, true); if (lpar_rc != H_SUCCESS) goto tx_flush_err; } @@ -2557,15 +2591,17 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) indir_arr[0] = tx_crq; memcpy(&ind_bufp->indir_arr[ind_bufp->index], &indir_arr[0], num_entries * sizeof(struct ibmvnic_generic_scrq)); + ind_bufp->index += num_entries; if (__netdev_tx_sent_queue(txq, skb->len, netdev_xmit_more() && ind_bufp->index < IBMVNIC_MAX_IND_DESCS)) { - lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq); + lpar_rc = ibmvnic_tx_scrq_flush(adapter, tx_scrq, true); if (lpar_rc != H_SUCCESS) goto tx_err; } +early_exit: if (atomic_add_return(num_entries, &tx_scrq->used) >= adapter->req_tx_entries_per_subcrq) { netdev_dbg(netdev, "Stopping queue %d\n", queue_num); @@ -3527,9 +3563,8 @@ restart_poll: } if (adapter->state != VNIC_CLOSING && - ((atomic_read(&adapter->rx_pool[scrq_num].available) < - adapter->req_rx_add_entries_per_subcrq / 2) || - frames_processed < budget)) + (atomic_read(&adapter->rx_pool[scrq_num].available) < + adapter->req_rx_add_entries_per_subcrq / 2)) replenish_rx_pool(adapter, &adapter->rx_pool[scrq_num]); if (frames_processed < budget) { if (napi_complete_done(napi, frames_processed)) { @@ -4169,20 +4204,17 @@ static int ibmvnic_complete_tx(struct ibmvnic_adapter *adapter, struct ibmvnic_sub_crq_queue *scrq) { struct device *dev = &adapter->vdev->dev; + int num_packets = 0, total_bytes = 0; struct ibmvnic_tx_pool *tx_pool; struct ibmvnic_tx_buff *txbuff; struct netdev_queue *txq; union sub_crq *next; - int index; - int i; + int index, i; restart_loop: while (pending_scrq(adapter, scrq)) { unsigned int pool = scrq->pool_index; int num_entries = 0; - int total_bytes = 0; - int num_packets = 0; - next = ibmvnic_next_scrq(adapter, scrq); for (i = 0; i < next->tx_comp.num_comps; i++) { index = be32_to_cpu(next->tx_comp.correlators[i]); @@ -4218,8 +4250,6 @@ restart_loop: /* remove tx_comp scrq*/ next->tx_comp.first = 0; - txq = netdev_get_tx_queue(adapter->netdev, scrq->pool_index); - netdev_tx_completed_queue(txq, num_packets, total_bytes); if (atomic_sub_return(num_entries, &scrq->used) <= (adapter->req_tx_entries_per_subcrq / 2) && @@ -4244,6 +4274,9 @@ restart_loop: goto restart_loop; } + txq = netdev_get_tx_queue(adapter->netdev, scrq->pool_index); + netdev_tx_completed_queue(txq, num_packets, total_bytes); + return 0; } diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index 23a6557fc3db..48cd1d06761c 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -33,6 +33,7 @@ #include <net/udp.h> #include <net/tc_act/tc_gact.h> #include <net/tc_act/tc_mirred.h> +#include <net/tc_act/tc_skbedit.h> #include "iavf_type.h" #include <linux/avf/virtchnl.h> @@ -393,6 +394,8 @@ struct iavf_adapter { VIRTCHNL_VF_OFFLOAD_VLAN_V2) #define CRC_OFFLOAD_ALLOWED(_a) ((_a)->vf_res->vf_cap_flags & \ VIRTCHNL_VF_OFFLOAD_CRC) +#define TC_U32_SUPPORT(_a) ((_a)->vf_res->vf_cap_flags & \ + VIRTCHNL_VF_OFFLOAD_TC_U32) #define VLAN_V2_FILTERING_ALLOWED(_a) \ (VLAN_V2_ALLOWED((_a)) && \ ((_a)->vlan_v2_caps.filtering.filtering_support.outer || \ @@ -437,6 +440,7 @@ struct iavf_adapter { #define IAVF_MAX_FDIR_FILTERS 128 /* max allowed Flow Director filters */ u16 fdir_active_fltr; + u16 raw_fdir_active_fltr; struct list_head fdir_list_head; spinlock_t fdir_fltr_lock; /* protect the Flow Director filter list */ @@ -444,6 +448,32 @@ struct iavf_adapter { spinlock_t adv_rss_lock; /* protect the RSS management list */ }; +/* Must be called with fdir_fltr_lock lock held */ +static inline bool iavf_fdir_max_reached(struct iavf_adapter *adapter) +{ + return adapter->fdir_active_fltr + adapter->raw_fdir_active_fltr >= + IAVF_MAX_FDIR_FILTERS; +} + +static inline void +iavf_inc_fdir_active_fltr(struct iavf_adapter *adapter, + struct iavf_fdir_fltr *fltr) +{ + if (iavf_is_raw_fdir(fltr)) + adapter->raw_fdir_active_fltr++; + else + adapter->fdir_active_fltr++; +} + +static inline void +iavf_dec_fdir_active_fltr(struct iavf_adapter *adapter, + struct iavf_fdir_fltr *fltr) +{ + if (iavf_is_raw_fdir(fltr)) + adapter->raw_fdir_active_fltr--; + else + adapter->fdir_active_fltr--; +} /* Ethtool Private Flags */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index 52273f7eab2c..74a1e9fe1821 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -927,7 +927,7 @@ iavf_get_ethtool_fdir_entry(struct iavf_adapter *adapter, spin_lock_bh(&adapter->fdir_fltr_lock); - rule = iavf_find_fdir_fltr_by_loc(adapter, fsp->location); + rule = iavf_find_fdir_fltr(adapter, false, fsp->location); if (!rule) { ret = -EINVAL; goto release_lock; @@ -1072,6 +1072,9 @@ iavf_get_fdir_fltr_ids(struct iavf_adapter *adapter, struct ethtool_rxnfc *cmd, spin_lock_bh(&adapter->fdir_fltr_lock); list_for_each_entry(fltr, &adapter->fdir_list_head, list) { + if (iavf_is_raw_fdir(fltr)) + continue; + if (cnt == cmd->rule_cnt) { val = -EMSGSIZE; goto release_lock; @@ -1263,15 +1266,7 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx return -EINVAL; spin_lock_bh(&adapter->fdir_fltr_lock); - if (adapter->fdir_active_fltr >= IAVF_MAX_FDIR_FILTERS) { - spin_unlock_bh(&adapter->fdir_fltr_lock); - dev_err(&adapter->pdev->dev, - "Unable to add Flow Director filter because VF reached the limit of max allowed filters (%u)\n", - IAVF_MAX_FDIR_FILTERS); - return -ENOSPC; - } - - if (iavf_find_fdir_fltr_by_loc(adapter, fsp->location)) { + if (iavf_find_fdir_fltr(adapter, false, fsp->location)) { dev_err(&adapter->pdev->dev, "Failed to add Flow Director filter, it already exists\n"); spin_unlock_bh(&adapter->fdir_fltr_lock); return -EEXIST; @@ -1291,23 +1286,10 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx } err = iavf_add_fdir_fltr_info(adapter, fsp, fltr); - if (err) - goto ret; - - spin_lock_bh(&adapter->fdir_fltr_lock); - iavf_fdir_list_add_fltr(adapter, fltr); - adapter->fdir_active_fltr++; - - if (adapter->link_up) - fltr->state = IAVF_FDIR_FLTR_ADD_REQUEST; - else - fltr->state = IAVF_FDIR_FLTR_INACTIVE; - spin_unlock_bh(&adapter->fdir_fltr_lock); + if (!err) + err = iavf_fdir_add_fltr(adapter, fltr); - if (adapter->link_up) - iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_ADD_FDIR_FILTER); -ret: - if (err && fltr) + if (err) kfree(fltr); mutex_unlock(&adapter->crit_lock); @@ -1324,34 +1306,11 @@ ret: static int iavf_del_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rxnfc *cmd) { struct ethtool_rx_flow_spec *fsp = (struct ethtool_rx_flow_spec *)&cmd->fs; - struct iavf_fdir_fltr *fltr = NULL; - int err = 0; if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED)) return -EOPNOTSUPP; - spin_lock_bh(&adapter->fdir_fltr_lock); - fltr = iavf_find_fdir_fltr_by_loc(adapter, fsp->location); - if (fltr) { - if (fltr->state == IAVF_FDIR_FLTR_ACTIVE) { - fltr->state = IAVF_FDIR_FLTR_DEL_REQUEST; - } else if (fltr->state == IAVF_FDIR_FLTR_INACTIVE) { - list_del(&fltr->list); - kfree(fltr); - adapter->fdir_active_fltr--; - fltr = NULL; - } else { - err = -EBUSY; - } - } else if (adapter->fdir_active_fltr) { - err = -EINVAL; - } - spin_unlock_bh(&adapter->fdir_fltr_lock); - - if (fltr && fltr->state == IAVF_FDIR_FLTR_DEL_REQUEST) - iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_DEL_FDIR_FILTER); - - return err; + return iavf_fdir_del_fltr(adapter, false, fsp->location); } /** diff --git a/drivers/net/ethernet/intel/iavf/iavf_fdir.c b/drivers/net/ethernet/intel/iavf/iavf_fdir.c index 2d47b0b4640e..a1b3b44cc14a 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_fdir.c +++ b/drivers/net/ethernet/intel/iavf/iavf_fdir.c @@ -796,6 +796,9 @@ bool iavf_fdir_is_dup_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr * spin_lock_bh(&adapter->fdir_fltr_lock); list_for_each_entry(tmp, &adapter->fdir_list_head, list) { + if (iavf_is_raw_fdir(fltr)) + continue; + if (tmp->flow_type != fltr->flow_type) continue; @@ -815,33 +818,52 @@ bool iavf_fdir_is_dup_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr * } /** - * iavf_find_fdir_fltr_by_loc - find filter with location + * iavf_find_fdir_fltr - find FDIR filter * @adapter: pointer to the VF adapter structure - * @loc: location to find. + * @is_raw: filter type, is raw (tc u32) or not (ethtool) + * @data: data to ID the filter, type dependent * - * Returns pointer to Flow Director filter if found or null + * Returns: pointer to Flow Director filter if found or NULL. Lock must be held. */ -struct iavf_fdir_fltr *iavf_find_fdir_fltr_by_loc(struct iavf_adapter *adapter, u32 loc) +struct iavf_fdir_fltr *iavf_find_fdir_fltr(struct iavf_adapter *adapter, + bool is_raw, u32 data) { struct iavf_fdir_fltr *rule; - list_for_each_entry(rule, &adapter->fdir_list_head, list) - if (rule->loc == loc) + list_for_each_entry(rule, &adapter->fdir_list_head, list) { + if ((is_raw && rule->cls_u32_handle == data) || + (!is_raw && rule->loc == data)) return rule; + } return NULL; } /** - * iavf_fdir_list_add_fltr - add a new node to the flow director filter list + * iavf_fdir_add_fltr - add a new node to the flow director filter list * @adapter: pointer to the VF adapter structure * @fltr: filter node to add to structure + * + * Return: 0 on success or negative errno on failure. */ -void iavf_fdir_list_add_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr) +int iavf_fdir_add_fltr(struct iavf_adapter *adapter, + struct iavf_fdir_fltr *fltr) { struct iavf_fdir_fltr *rule, *parent = NULL; + spin_lock_bh(&adapter->fdir_fltr_lock); + if (iavf_fdir_max_reached(adapter)) { + spin_unlock_bh(&adapter->fdir_fltr_lock); + dev_err(&adapter->pdev->dev, + "Unable to add Flow Director filter (limit (%u) reached)\n", + IAVF_MAX_FDIR_FILTERS); + return -ENOSPC; + } + list_for_each_entry(rule, &adapter->fdir_list_head, list) { + if (iavf_is_raw_fdir(fltr)) + break; + if (rule->loc >= fltr->loc) break; parent = rule; @@ -851,4 +873,55 @@ void iavf_fdir_list_add_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr list_add(&fltr->list, &parent->list); else list_add(&fltr->list, &adapter->fdir_list_head); + + iavf_inc_fdir_active_fltr(adapter, fltr); + + if (adapter->link_up) + fltr->state = IAVF_FDIR_FLTR_ADD_REQUEST; + else + fltr->state = IAVF_FDIR_FLTR_INACTIVE; + spin_unlock_bh(&adapter->fdir_fltr_lock); + + if (adapter->link_up) + iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_ADD_FDIR_FILTER); + + return 0; +} + +/** + * iavf_fdir_del_fltr - delete a flow director filter from the list + * @adapter: pointer to the VF adapter structure + * @is_raw: filter type, is raw (tc u32) or not (ethtool) + * @data: data to ID the filter, type dependent + * + * Return: 0 on success or negative errno on failure. + */ +int iavf_fdir_del_fltr(struct iavf_adapter *adapter, bool is_raw, u32 data) +{ + struct iavf_fdir_fltr *fltr = NULL; + int err = 0; + + spin_lock_bh(&adapter->fdir_fltr_lock); + fltr = iavf_find_fdir_fltr(adapter, is_raw, data); + + if (fltr) { + if (fltr->state == IAVF_FDIR_FLTR_ACTIVE) { + fltr->state = IAVF_FDIR_FLTR_DEL_REQUEST; + } else if (fltr->state == IAVF_FDIR_FLTR_INACTIVE) { + list_del(&fltr->list); + iavf_dec_fdir_active_fltr(adapter, fltr); + kfree(fltr); + fltr = NULL; + } else { + err = -EBUSY; + } + } else if (adapter->fdir_active_fltr) { + err = -EINVAL; + } + + if (fltr && fltr->state == IAVF_FDIR_FLTR_DEL_REQUEST) + iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_DEL_FDIR_FILTER); + + spin_unlock_bh(&adapter->fdir_fltr_lock); + return err; } diff --git a/drivers/net/ethernet/intel/iavf/iavf_fdir.h b/drivers/net/ethernet/intel/iavf/iavf_fdir.h index d31bd923ba8c..e84a5351162f 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_fdir.h +++ b/drivers/net/ethernet/intel/iavf/iavf_fdir.h @@ -117,17 +117,26 @@ struct iavf_fdir_fltr { u32 flow_id; + u32 cls_u32_handle; /* for FDIR added via tc u32 */ u32 loc; /* Rule location inside the flow table */ u32 q_index; struct virtchnl_fdir_add vc_add_msg; }; +static inline bool iavf_is_raw_fdir(struct iavf_fdir_fltr *fltr) +{ + return !fltr->vc_add_msg.rule_cfg.proto_hdrs.count; +} + int iavf_validate_fdir_fltr_masks(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr); int iavf_fill_fdir_add_msg(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr); void iavf_print_fdir_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr); bool iavf_fdir_is_dup_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr); -void iavf_fdir_list_add_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr); -struct iavf_fdir_fltr *iavf_find_fdir_fltr_by_loc(struct iavf_adapter *adapter, u32 loc); +int iavf_fdir_add_fltr(struct iavf_adapter *adapter, + struct iavf_fdir_fltr *fltr); +int iavf_fdir_del_fltr(struct iavf_adapter *adapter, bool is_raw, u32 data); +struct iavf_fdir_fltr *iavf_find_fdir_fltr(struct iavf_adapter *adapter, + bool is_raw, u32 data); #endif /* _IAVF_FDIR_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index ff11bafb3b4f..f782402cd789 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -4013,7 +4013,7 @@ static int iavf_delete_clsflower(struct iavf_adapter *adapter, /** * iavf_setup_tc_cls_flower - flower classifier offloads - * @adapter: board private structure + * @adapter: pointer to iavf adapter structure * @cls_flower: pointer to flow_cls_offload struct with flow info */ static int iavf_setup_tc_cls_flower(struct iavf_adapter *adapter, @@ -4032,6 +4032,154 @@ static int iavf_setup_tc_cls_flower(struct iavf_adapter *adapter, } /** + * iavf_add_cls_u32 - Add U32 classifier offloads + * @adapter: pointer to iavf adapter structure + * @cls_u32: pointer to tc_cls_u32_offload struct with flow info + * + * Return: 0 on success or negative errno on failure. + */ +static int iavf_add_cls_u32(struct iavf_adapter *adapter, + struct tc_cls_u32_offload *cls_u32) +{ + struct netlink_ext_ack *extack = cls_u32->common.extack; + struct virtchnl_fdir_rule *rule_cfg; + struct virtchnl_filter_action *vact; + struct virtchnl_proto_hdrs *hdrs; + struct ethhdr *spec_h, *mask_h; + const struct tc_action *act; + struct iavf_fdir_fltr *fltr; + struct tcf_exts *exts; + unsigned int q_index; + int i, status = 0; + int off_base = 0; + + if (cls_u32->knode.link_handle) { + NL_SET_ERR_MSG_MOD(extack, "Linking not supported"); + return -EOPNOTSUPP; + } + + fltr = kzalloc(sizeof(*fltr), GFP_KERNEL); + if (!fltr) + return -ENOMEM; + + rule_cfg = &fltr->vc_add_msg.rule_cfg; + hdrs = &rule_cfg->proto_hdrs; + hdrs->count = 0; + + /* The parser lib at the PF expects the packet starting with MAC hdr */ + switch (ntohs(cls_u32->common.protocol)) { + case ETH_P_802_3: + break; + case ETH_P_IP: + spec_h = (struct ethhdr *)hdrs->raw.spec; + mask_h = (struct ethhdr *)hdrs->raw.mask; + spec_h->h_proto = htons(ETH_P_IP); + mask_h->h_proto = htons(0xFFFF); + off_base += ETH_HLEN; + break; + default: + NL_SET_ERR_MSG_MOD(extack, "Only 802_3 and ip filter protocols are supported"); + status = -EOPNOTSUPP; + goto free_alloc; + } + + for (i = 0; i < cls_u32->knode.sel->nkeys; i++) { + __be32 val, mask; + int off; + + off = off_base + cls_u32->knode.sel->keys[i].off; + val = cls_u32->knode.sel->keys[i].val; + mask = cls_u32->knode.sel->keys[i].mask; + + if (off >= sizeof(hdrs->raw.spec)) { + NL_SET_ERR_MSG_MOD(extack, "Input exceeds maximum allowed."); + status = -EINVAL; + goto free_alloc; + } + + memcpy(&hdrs->raw.spec[off], &val, sizeof(val)); + memcpy(&hdrs->raw.mask[off], &mask, sizeof(mask)); + hdrs->raw.pkt_len = off + sizeof(val); + } + + /* Only one action is allowed */ + rule_cfg->action_set.count = 1; + vact = &rule_cfg->action_set.actions[0]; + exts = cls_u32->knode.exts; + + tcf_exts_for_each_action(i, act, exts) { + /* FDIR queue */ + if (is_tcf_skbedit_rx_queue_mapping(act)) { + q_index = tcf_skbedit_rx_queue_mapping(act); + if (q_index >= adapter->num_active_queues) { + status = -EINVAL; + goto free_alloc; + } + + vact->type = VIRTCHNL_ACTION_QUEUE; + vact->act_conf.queue.index = q_index; + break; + } + + /* Drop */ + if (is_tcf_gact_shot(act)) { + vact->type = VIRTCHNL_ACTION_DROP; + break; + } + + /* Unsupported action */ + NL_SET_ERR_MSG_MOD(extack, "Unsupported action."); + status = -EOPNOTSUPP; + goto free_alloc; + } + + fltr->vc_add_msg.vsi_id = adapter->vsi.id; + fltr->cls_u32_handle = cls_u32->knode.handle; + return iavf_fdir_add_fltr(adapter, fltr); + +free_alloc: + kfree(fltr); + return status; +} + +/** + * iavf_del_cls_u32 - Delete U32 classifier offloads + * @adapter: pointer to iavf adapter structure + * @cls_u32: pointer to tc_cls_u32_offload struct with flow info + * + * Return: 0 on success or negative errno on failure. + */ +static int iavf_del_cls_u32(struct iavf_adapter *adapter, + struct tc_cls_u32_offload *cls_u32) +{ + return iavf_fdir_del_fltr(adapter, true, cls_u32->knode.handle); +} + +/** + * iavf_setup_tc_cls_u32 - U32 filter offloads + * @adapter: pointer to iavf adapter structure + * @cls_u32: pointer to tc_cls_u32_offload struct with flow info + * + * Return: 0 on success or negative errno on failure. + */ +static int iavf_setup_tc_cls_u32(struct iavf_adapter *adapter, + struct tc_cls_u32_offload *cls_u32) +{ + if (!TC_U32_SUPPORT(adapter) || !FDIR_FLTR_SUPPORT(adapter)) + return -EOPNOTSUPP; + + switch (cls_u32->command) { + case TC_CLSU32_NEW_KNODE: + case TC_CLSU32_REPLACE_KNODE: + return iavf_add_cls_u32(adapter, cls_u32); + case TC_CLSU32_DELETE_KNODE: + return iavf_del_cls_u32(adapter, cls_u32); + default: + return -EOPNOTSUPP; + } +} + +/** * iavf_setup_tc_block_cb - block callback for tc * @type: type of offload * @type_data: offload data @@ -4050,6 +4198,8 @@ static int iavf_setup_tc_block_cb(enum tc_setup_type type, void *type_data, switch (type) { case TC_SETUP_CLSFLOWER: return iavf_setup_tc_cls_flower(cb_priv, type_data); + case TC_SETUP_CLSU32: + return iavf_setup_tc_cls_u32(cb_priv, type_data); default: return -EOPNOTSUPP; } @@ -4332,8 +4482,8 @@ static void iavf_disable_fdir(struct iavf_adapter *adapter) fdir->state == IAVF_FDIR_FLTR_INACTIVE) { /* Delete filters not registered in PF */ list_del(&fdir->list); + iavf_dec_fdir_active_fltr(adapter, fdir); kfree(fdir); - adapter->fdir_active_fltr--; } else if (fdir->state == IAVF_FDIR_FLTR_ADD_PENDING || fdir->state == IAVF_FDIR_FLTR_DIS_REQUEST || fdir->state == IAVF_FDIR_FLTR_ACTIVE) { @@ -4843,9 +4993,11 @@ int iavf_process_config(struct iavf_adapter *adapter) /* get HW VLAN features that can be toggled */ hw_vlan_features = iavf_get_netdev_vlan_hw_features(adapter); - /* Enable cloud filter if ADQ is supported */ - if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) + /* Enable HW TC offload if ADQ or tc U32 is supported */ + if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ || + TC_U32_SUPPORT(adapter)) hw_features |= NETIF_F_HW_TC; + if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_USO) hw_features |= NETIF_F_GSO_UDP_L4; diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 1e543f6a7c30..7e810b65380c 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -142,6 +142,7 @@ int iavf_send_vf_config_msg(struct iavf_adapter *adapter) VIRTCHNL_VF_OFFLOAD_WB_ON_ITR | VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2 | VIRTCHNL_VF_OFFLOAD_ENCAP | + VIRTCHNL_VF_OFFLOAD_TC_U32 | VIRTCHNL_VF_OFFLOAD_VLAN_V2 | VIRTCHNL_VF_OFFLOAD_CRC | VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM | @@ -1961,8 +1962,8 @@ static void iavf_activate_fdir_filters(struct iavf_adapter *adapter) * list on PF is already cleared after a reset */ list_del(&f->list); + iavf_dec_fdir_active_fltr(adapter, f); kfree(f); - adapter->fdir_active_fltr--; } } spin_unlock_bh(&adapter->fdir_fltr_lock); @@ -2135,8 +2136,8 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, dev_err(&adapter->pdev->dev, "%s\n", msg); list_del(&fdir->list); + iavf_dec_fdir_active_fltr(adapter, fdir); kfree(fdir); - adapter->fdir_active_fltr--; } } spin_unlock_bh(&adapter->fdir_fltr_lock); @@ -2451,8 +2452,12 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, list) { if (fdir->state == IAVF_FDIR_FLTR_ADD_PENDING) { if (add_fltr->status == VIRTCHNL_FDIR_SUCCESS) { - dev_info(&adapter->pdev->dev, "Flow Director filter with location %u is added\n", - fdir->loc); + if (!iavf_is_raw_fdir(fdir)) + dev_info(&adapter->pdev->dev, "Flow Director filter with location %u is added\n", + fdir->loc); + else + dev_info(&adapter->pdev->dev, "Flow Director filter (raw) for TC handle %x is added\n", + TC_U32_USERHTID(fdir->cls_u32_handle)); fdir->state = IAVF_FDIR_FLTR_ACTIVE; fdir->flow_id = add_fltr->flow_id; } else { @@ -2460,8 +2465,8 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, add_fltr->status); iavf_print_fdir_fltr(adapter, fdir); list_del(&fdir->list); + iavf_dec_fdir_active_fltr(adapter, fdir); kfree(fdir); - adapter->fdir_active_fltr--; } } } @@ -2479,11 +2484,15 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, if (del_fltr->status == VIRTCHNL_FDIR_SUCCESS || del_fltr->status == VIRTCHNL_FDIR_FAILURE_RULE_NONEXIST) { - dev_info(&adapter->pdev->dev, "Flow Director filter with location %u is deleted\n", - fdir->loc); + if (!iavf_is_raw_fdir(fdir)) + dev_info(&adapter->pdev->dev, "Flow Director filter with location %u is deleted\n", + fdir->loc); + else + dev_info(&adapter->pdev->dev, "Flow Director filter (raw) for TC handle %x is deleted\n", + TC_U32_USERHTID(fdir->cls_u32_handle)); list_del(&fdir->list); + iavf_dec_fdir_active_fltr(adapter, fdir); kfree(fdir); - adapter->fdir_active_fltr--; } else { fdir->state = IAVF_FDIR_FLTR_ACTIVE; dev_info(&adapter->pdev->dev, "Failed to delete Flow Director filter with status: %d\n", diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile index 03500e28ac99..b4f6fa4ba13d 100644 --- a/drivers/net/ethernet/intel/ice/Makefile +++ b/drivers/net/ethernet/intel/ice/Makefile @@ -28,6 +28,8 @@ ice-y := ice_main.o \ ice_vlan_mode.o \ ice_flex_pipe.o \ ice_flow.o \ + ice_parser.o \ + ice_parser_rt.o \ ice_idc.o \ devlink/devlink.o \ devlink/devlink_port.o \ diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index 66f02988d549..0be1a98d7cc1 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -2632,12 +2632,16 @@ struct ice_aq_desc { /* FW defined boundary for a large buffer, 4k >= Large buffer > 512 bytes */ #define ICE_AQ_LG_BUF 512 +#define ICE_AQ_FLAG_DD_S 0 +#define ICE_AQ_FLAG_CMP_S 1 #define ICE_AQ_FLAG_ERR_S 2 #define ICE_AQ_FLAG_LB_S 9 #define ICE_AQ_FLAG_RD_S 10 #define ICE_AQ_FLAG_BUF_S 12 #define ICE_AQ_FLAG_SI_S 13 +#define ICE_AQ_FLAG_DD BIT(ICE_AQ_FLAG_DD_S) /* 0x1 */ +#define ICE_AQ_FLAG_CMP BIT(ICE_AQ_FLAG_CMP_S) /* 0x2 */ #define ICE_AQ_FLAG_ERR BIT(ICE_AQ_FLAG_ERR_S) /* 0x4 */ #define ICE_AQ_FLAG_LB BIT(ICE_AQ_FLAG_LB_S) /* 0x200 */ #define ICE_AQ_FLAG_RD BIT(ICE_AQ_FLAG_RD_S) /* 0x400 */ diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h index 66f29bac783a..27208a60cece 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.h +++ b/drivers/net/ethernet/intel/ice/ice_common.h @@ -10,6 +10,7 @@ #include "ice_type.h" #include "ice_nvm.h" #include "ice_flex_pipe.h" +#include "ice_parser.h" #include <linux/avf/virtchnl.h> #include "ice_switch.h" #include "ice_fdir.h" diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.c b/drivers/net/ethernet/intel/ice/ice_controlq.c index ffaa6511c455..e3959ad442a2 100644 --- a/drivers/net/ethernet/intel/ice/ice_controlq.c +++ b/drivers/net/ethernet/intel/ice/ice_controlq.c @@ -99,17 +99,6 @@ ice_alloc_ctrlq_sq_ring(struct ice_hw *hw, struct ice_ctl_q_info *cq) return -ENOMEM; cq->sq.desc_buf.size = size; - cq->sq.cmd_buf = devm_kcalloc(ice_hw_to_dev(hw), cq->num_sq_entries, - sizeof(struct ice_sq_cd), GFP_KERNEL); - if (!cq->sq.cmd_buf) { - dmam_free_coherent(ice_hw_to_dev(hw), cq->sq.desc_buf.size, - cq->sq.desc_buf.va, cq->sq.desc_buf.pa); - cq->sq.desc_buf.va = NULL; - cq->sq.desc_buf.pa = 0; - cq->sq.desc_buf.size = 0; - return -ENOMEM; - } - return 0; } @@ -188,7 +177,7 @@ ice_alloc_rq_bufs(struct ice_hw *hw, struct ice_ctl_q_info *cq) if (cq->rq_buf_size > ICE_AQ_LG_BUF) desc->flags |= cpu_to_le16(ICE_AQ_FLAG_LB); desc->opcode = 0; - /* This is in accordance with Admin queue design, there is no + /* This is in accordance with control queue design, there is no * register for buffer size configuration */ desc->datalen = cpu_to_le16(bi->size); @@ -338,8 +327,6 @@ do { \ (qi)->ring.r.ring##_bi[i].size = 0;\ } \ } \ - /* free the buffer info list */ \ - devm_kfree(ice_hw_to_dev(hw), (qi)->ring.cmd_buf); \ /* free DMA head */ \ devm_kfree(ice_hw_to_dev(hw), (qi)->ring.dma_head); \ } while (0) @@ -405,11 +392,11 @@ init_ctrlq_exit: } /** - * ice_init_rq - initialize ARQ + * ice_init_rq - initialize receive side of a control queue * @hw: pointer to the hardware structure * @cq: pointer to the specific Control queue * - * The main initialization routine for the Admin Receive (Event) Queue. + * The main initialization routine for Receive side of a control queue. * Prior to calling this function, the driver *MUST* set the following fields * in the cq->structure: * - cq->num_rq_entries @@ -465,7 +452,7 @@ init_ctrlq_exit: } /** - * ice_shutdown_sq - shutdown the Control ATQ + * ice_shutdown_sq - shutdown the transmit side of a control queue * @hw: pointer to the hardware structure * @cq: pointer to the specific Control queue * @@ -482,7 +469,7 @@ static int ice_shutdown_sq(struct ice_hw *hw, struct ice_ctl_q_info *cq) goto shutdown_sq_out; } - /* Stop firmware AdminQ processing */ + /* Stop processing of the control queue */ wr32(hw, cq->sq.head, 0); wr32(hw, cq->sq.tail, 0); wr32(hw, cq->sq.len, 0); @@ -501,7 +488,7 @@ shutdown_sq_out: } /** - * ice_aq_ver_check - Check the reported AQ API version. + * ice_aq_ver_check - Check the reported AQ API version * @hw: pointer to the hardware structure * * Checks if the driver should load on a given AQ API version. @@ -521,14 +508,20 @@ static bool ice_aq_ver_check(struct ice_hw *hw) } else if (hw->api_maj_ver == exp_fw_api_ver_major) { if (hw->api_min_ver > (exp_fw_api_ver_minor + 2)) dev_info(ice_hw_to_dev(hw), - "The driver for the device detected a newer version of the NVM image than expected. Please install the most recent version of the network driver.\n"); + "The driver for the device detected a newer version (%u.%u) of the NVM image than expected (%u.%u). Please install the most recent version of the network driver.\n", + hw->api_maj_ver, hw->api_min_ver, + exp_fw_api_ver_major, exp_fw_api_ver_minor); else if ((hw->api_min_ver + 2) < exp_fw_api_ver_minor) dev_info(ice_hw_to_dev(hw), - "The driver for the device detected an older version of the NVM image than expected. Please update the NVM image.\n"); + "The driver for the device detected an older version (%u.%u) of the NVM image than expected (%u.%u). Please update the NVM image.\n", + hw->api_maj_ver, hw->api_min_ver, + exp_fw_api_ver_major, exp_fw_api_ver_minor); } else { /* Major API version is older than expected, log a warning */ dev_info(ice_hw_to_dev(hw), - "The driver for the device detected an older version of the NVM image than expected. Please update the NVM image.\n"); + "The driver for the device detected an older version (%u.%u) of the NVM image than expected (%u.%u). Please update the NVM image.\n", + hw->api_maj_ver, hw->api_min_ver, + exp_fw_api_ver_major, exp_fw_api_ver_minor); } return true; } @@ -855,7 +848,7 @@ void ice_destroy_all_ctrlq(struct ice_hw *hw) } /** - * ice_clean_sq - cleans Admin send queue (ATQ) + * ice_clean_sq - cleans send side of a control queue * @hw: pointer to the hardware structure * @cq: pointer to the specific Control queue * @@ -865,21 +858,17 @@ static u16 ice_clean_sq(struct ice_hw *hw, struct ice_ctl_q_info *cq) { struct ice_ctl_q_ring *sq = &cq->sq; u16 ntc = sq->next_to_clean; - struct ice_sq_cd *details; struct ice_aq_desc *desc; desc = ICE_CTL_Q_DESC(*sq, ntc); - details = ICE_CTL_Q_DETAILS(*sq, ntc); while (rd32(hw, cq->sq.head) != ntc) { ice_debug(hw, ICE_DBG_AQ_MSG, "ntc %d head %d.\n", ntc, rd32(hw, cq->sq.head)); memset(desc, 0, sizeof(*desc)); - memset(details, 0, sizeof(*details)); ntc++; if (ntc == sq->count) ntc = 0; desc = ICE_CTL_Q_DESC(*sq, ntc); - details = ICE_CTL_Q_DETAILS(*sq, ntc); } sq->next_to_clean = ntc; @@ -888,18 +877,43 @@ static u16 ice_clean_sq(struct ice_hw *hw, struct ice_ctl_q_info *cq) } /** + * ice_ctl_q_str - Convert control queue type to string + * @qtype: the control queue type + * + * Return: A string name for the given control queue type. + */ +static const char *ice_ctl_q_str(enum ice_ctl_q qtype) +{ + switch (qtype) { + case ICE_CTL_Q_UNKNOWN: + return "Unknown CQ"; + case ICE_CTL_Q_ADMIN: + return "AQ"; + case ICE_CTL_Q_MAILBOX: + return "MBXQ"; + case ICE_CTL_Q_SB: + return "SBQ"; + default: + return "Unrecognized CQ"; + } +} + +/** * ice_debug_cq * @hw: pointer to the hardware structure + * @cq: pointer to the specific Control queue * @desc: pointer to control queue descriptor * @buf: pointer to command buffer * @buf_len: max length of buf + * @response: true if this is the writeback response * * Dumps debug log about control command with descriptor contents. */ -static void ice_debug_cq(struct ice_hw *hw, void *desc, void *buf, u16 buf_len) +static void ice_debug_cq(struct ice_hw *hw, struct ice_ctl_q_info *cq, + void *desc, void *buf, u16 buf_len, bool response) { struct ice_aq_desc *cq_desc = desc; - u16 len; + u16 datalen, flags; if (!IS_ENABLED(CONFIG_DYNAMIC_DEBUG) && !((ICE_DBG_AQ_DESC | ICE_DBG_AQ_DESC_BUF) & hw->debug_mask)) @@ -908,48 +922,63 @@ static void ice_debug_cq(struct ice_hw *hw, void *desc, void *buf, u16 buf_len) if (!desc) return; - len = le16_to_cpu(cq_desc->datalen); + datalen = le16_to_cpu(cq_desc->datalen); + flags = le16_to_cpu(cq_desc->flags); - ice_debug(hw, ICE_DBG_AQ_DESC, "CQ CMD: opcode 0x%04X, flags 0x%04X, datalen 0x%04X, retval 0x%04X\n", - le16_to_cpu(cq_desc->opcode), - le16_to_cpu(cq_desc->flags), - le16_to_cpu(cq_desc->datalen), le16_to_cpu(cq_desc->retval)); - ice_debug(hw, ICE_DBG_AQ_DESC, "\tcookie (h,l) 0x%08X 0x%08X\n", + ice_debug(hw, ICE_DBG_AQ_DESC, "%s %s: opcode 0x%04X, flags 0x%04X, datalen 0x%04X, retval 0x%04X\n\tcookie (h,l) 0x%08X 0x%08X\n\tparam (0,1) 0x%08X 0x%08X\n\taddr (h,l) 0x%08X 0x%08X\n", + ice_ctl_q_str(cq->qtype), response ? "Response" : "Command", + le16_to_cpu(cq_desc->opcode), flags, datalen, + le16_to_cpu(cq_desc->retval), le32_to_cpu(cq_desc->cookie_high), - le32_to_cpu(cq_desc->cookie_low)); - ice_debug(hw, ICE_DBG_AQ_DESC, "\tparam (0,1) 0x%08X 0x%08X\n", + le32_to_cpu(cq_desc->cookie_low), le32_to_cpu(cq_desc->params.generic.param0), - le32_to_cpu(cq_desc->params.generic.param1)); - ice_debug(hw, ICE_DBG_AQ_DESC, "\taddr (h,l) 0x%08X 0x%08X\n", + le32_to_cpu(cq_desc->params.generic.param1), le32_to_cpu(cq_desc->params.generic.addr_high), le32_to_cpu(cq_desc->params.generic.addr_low)); - if (buf && cq_desc->datalen != 0) { - ice_debug(hw, ICE_DBG_AQ_DESC_BUF, "Buffer:\n"); - if (buf_len < len) - len = buf_len; - - ice_debug_array(hw, ICE_DBG_AQ_DESC_BUF, 16, 1, buf, len); + /* Dump buffer iff 1) one exists and 2) is either a response indicated + * by the DD and/or CMP flag set or a command with the RD flag set. + */ + if (buf && cq_desc->datalen && + (flags & (ICE_AQ_FLAG_DD | ICE_AQ_FLAG_CMP | ICE_AQ_FLAG_RD))) { + char prefix[] = KBUILD_MODNAME " 0x12341234 0x12341234 "; + + sprintf(prefix, KBUILD_MODNAME " 0x%08X 0x%08X ", + le32_to_cpu(cq_desc->params.generic.addr_high), + le32_to_cpu(cq_desc->params.generic.addr_low)); + ice_debug_array_w_prefix(hw, ICE_DBG_AQ_DESC_BUF, prefix, + buf, + min_t(u16, buf_len, datalen)); } } /** - * ice_sq_done - check if FW has processed the Admin Send Queue (ATQ) + * ice_sq_done - poll until the last send on a control queue has completed * @hw: pointer to the HW struct * @cq: pointer to the specific Control queue * - * Returns true if the firmware has processed all descriptors on the - * admin send queue. Returns false if there are still requests pending. + * Use read_poll_timeout to poll the control queue head, checking until it + * matches next_to_use. According to the control queue designers, this has + * better timing reliability than the DD bit. + * + * Return: true if all the descriptors on the send side of a control queue + * are finished processing, false otherwise. */ static bool ice_sq_done(struct ice_hw *hw, struct ice_ctl_q_info *cq) { - /* AQ designers suggest use of head for better - * timing reliability than DD bit + u32 head; + + /* Wait a short time before the initial check, to allow hardware time + * for completion. */ - return rd32(hw, cq->sq.head) == cq->sq.next_to_use; + udelay(5); + + return !rd32_poll_timeout(hw, cq->sq.head, + head, head == cq->sq.next_to_use, + 20, ICE_CTL_Q_SQ_CMD_TIMEOUT); } /** - * ice_sq_send_cmd - send command to Control Queue (ATQ) + * ice_sq_send_cmd - send command to a control queue * @hw: pointer to the HW struct * @cq: pointer to the specific Control queue * @desc: prefilled descriptor describing the command @@ -957,8 +986,9 @@ static bool ice_sq_done(struct ice_hw *hw, struct ice_ctl_q_info *cq) * @buf_size: size of buffer for indirect commands (or 0 for direct commands) * @cd: pointer to command details structure * - * This is the main send command routine for the ATQ. It runs the queue, - * cleans the queue, etc. + * Main command for the transmit side of a control queue. It puts the command + * on the queue, bumps the tail, waits for processing of the command, captures + * command status and results, etc. */ int ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq, @@ -968,8 +998,6 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq, struct ice_dma_mem *dma_buf = NULL; struct ice_aq_desc *desc_on_ring; bool cmd_completed = false; - struct ice_sq_cd *details; - unsigned long timeout; int status = 0; u16 retval = 0; u32 val = 0; @@ -1013,12 +1041,6 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq, goto sq_send_command_error; } - details = ICE_CTL_Q_DETAILS(cq->sq, cq->sq.next_to_use); - if (cd) - *details = *cd; - else - memset(details, 0, sizeof(*details)); - /* Call clean and check queue available function to reclaim the * descriptors that were processed by FW/MBX; the function returns the * number of desc available. The clean function called here could be @@ -1055,7 +1077,7 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq, /* Debug desc and buffer */ ice_debug(hw, ICE_DBG_AQ_DESC, "ATQ: Control Send queue desc and buffer:\n"); - ice_debug_cq(hw, (void *)desc_on_ring, buf, buf_size); + ice_debug_cq(hw, cq, (void *)desc_on_ring, buf, buf_size, false); (cq->sq.next_to_use)++; if (cq->sq.next_to_use == cq->sq.count) @@ -1063,20 +1085,9 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq, wr32(hw, cq->sq.tail, cq->sq.next_to_use); ice_flush(hw); - /* Wait a short time before initial ice_sq_done() check, to allow - * hardware time for completion. + /* Wait for the command to complete. If it finishes within the + * timeout, copy the descriptor back to temp. */ - udelay(5); - - timeout = jiffies + ICE_CTL_Q_SQ_CMD_TIMEOUT; - do { - if (ice_sq_done(hw, cq)) - break; - - usleep_range(100, 150); - } while (time_before(jiffies, timeout)); - - /* if ready, copy the desc back to temp */ if (ice_sq_done(hw, cq)) { memcpy(desc, desc_on_ring, sizeof(*desc)); if (buf) { @@ -1108,12 +1119,11 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq, ice_debug(hw, ICE_DBG_AQ_MSG, "ATQ: desc and buffer writeback:\n"); - ice_debug_cq(hw, (void *)desc, buf, buf_size); + ice_debug_cq(hw, cq, (void *)desc, buf, buf_size, true); /* save writeback AQ if requested */ - if (details->wb_desc) - memcpy(details->wb_desc, desc_on_ring, - sizeof(*details->wb_desc)); + if (cd && cd->wb_desc) + memcpy(cd->wb_desc, desc_on_ring, sizeof(*cd->wb_desc)); /* update the error if time out occurred */ if (!cmd_completed) { @@ -1154,9 +1164,9 @@ void ice_fill_dflt_direct_cmd_desc(struct ice_aq_desc *desc, u16 opcode) * @e: event info from the receive descriptor, includes any buffers * @pending: number of events that could be left to process * - * This function cleans one Admin Receive Queue element and returns - * the contents through e. It can also return how many events are - * left to process through 'pending'. + * Clean one element from the receive side of a control queue. On return 'e' + * contains contents of the message, and 'pending' contains the number of + * events left to process. */ int ice_clean_rq_elem(struct ice_hw *hw, struct ice_ctl_q_info *cq, @@ -1212,7 +1222,7 @@ ice_clean_rq_elem(struct ice_hw *hw, struct ice_ctl_q_info *cq, ice_debug(hw, ICE_DBG_AQ_DESC, "ARQ: desc and buffer:\n"); - ice_debug_cq(hw, (void *)desc, e->msg_buf, cq->rq_buf_size); + ice_debug_cq(hw, cq, (void *)desc, e->msg_buf, cq->rq_buf_size, true); /* Restore the original datalen and buffer address in the desc, * FW updates datalen to indicate the event message size diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.h b/drivers/net/ethernet/intel/ice/ice_controlq.h index 1d54b1cdb1c5..ca97b7365a1b 100644 --- a/drivers/net/ethernet/intel/ice/ice_controlq.h +++ b/drivers/net/ethernet/intel/ice/ice_controlq.h @@ -43,14 +43,13 @@ enum ice_ctl_q { }; /* Control Queue timeout settings - max delay 1s */ -#define ICE_CTL_Q_SQ_CMD_TIMEOUT HZ /* Wait max 1s */ +#define ICE_CTL_Q_SQ_CMD_TIMEOUT USEC_PER_SEC #define ICE_CTL_Q_ADMIN_INIT_TIMEOUT 10 /* Count 10 times */ #define ICE_CTL_Q_ADMIN_INIT_MSEC 100 /* Check every 100msec */ struct ice_ctl_q_ring { void *dma_head; /* Virtual address to DMA head */ struct ice_dma_mem desc_buf; /* descriptor ring memory */ - void *cmd_buf; /* command buffer memory */ union { struct ice_dma_mem *sq_bi; @@ -80,8 +79,6 @@ struct ice_sq_cd { struct ice_aq_desc *wb_desc; }; -#define ICE_CTL_Q_DETAILS(R, i) (&(((struct ice_sq_cd *)((R).cmd_buf))[i])) - /* rq event information */ struct ice_rq_event_info { struct ice_aq_desc desc; diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.c b/drivers/net/ethernet/intel/ice/ice_ddp.c index f182179529b7..953262b88a58 100644 --- a/drivers/net/ethernet/intel/ice/ice_ddp.c +++ b/drivers/net/ethernet/intel/ice/ice_ddp.c @@ -289,11 +289,11 @@ void *ice_pkg_enum_section(struct ice_seg *ice_seg, struct ice_pkg_enum *state, * indicates a base offset of 10, and the index for the entry is 2, then * section handler function should set the offset to 10 + 2 = 12. */ -static void *ice_pkg_enum_entry(struct ice_seg *ice_seg, - struct ice_pkg_enum *state, u32 sect_type, - u32 *offset, - void *(*handler)(u32 sect_type, void *section, - u32 index, u32 *offset)) +void *ice_pkg_enum_entry(struct ice_seg *ice_seg, + struct ice_pkg_enum *state, u32 sect_type, + u32 *offset, + void *(*handler)(u32 sect_type, void *section, + u32 index, u32 *offset)) { void *entry; diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.h b/drivers/net/ethernet/intel/ice/ice_ddp.h index 622543f08b43..97f272317475 100644 --- a/drivers/net/ethernet/intel/ice/ice_ddp.h +++ b/drivers/net/ethernet/intel/ice/ice_ddp.h @@ -261,10 +261,17 @@ struct ice_meta_sect { #define ICE_SID_CDID_KEY_BUILDER_RSS 47 #define ICE_SID_CDID_REDIR_RSS 48 +#define ICE_SID_RXPARSER_CAM 50 +#define ICE_SID_RXPARSER_NOMATCH_CAM 51 +#define ICE_SID_RXPARSER_IMEM 52 #define ICE_SID_RXPARSER_MARKER_PTYPE 55 #define ICE_SID_RXPARSER_BOOST_TCAM 56 +#define ICE_SID_RXPARSER_PROTO_GRP 57 #define ICE_SID_RXPARSER_METADATA_INIT 58 #define ICE_SID_TXPARSER_BOOST_TCAM 66 +#define ICE_SID_RXPARSER_MARKER_GRP 72 +#define ICE_SID_RXPARSER_PG_SPILL 76 +#define ICE_SID_RXPARSER_NOMATCH_SPILL 78 #define ICE_SID_XLT0_PE 80 #define ICE_SID_XLT_KEY_BUILDER_PE 81 @@ -276,6 +283,7 @@ struct ice_meta_sect { #define ICE_SID_CDID_KEY_BUILDER_PE 87 #define ICE_SID_CDID_REDIR_PE 88 +#define ICE_SID_RXPARSER_FLAG_REDIR 97 /* Label Metadata section IDs */ #define ICE_SID_LBL_FIRST 0x80000010 #define ICE_SID_LBL_RXPARSER_TMEM 0x80000018 @@ -451,6 +459,11 @@ int ice_update_pkg(struct ice_hw *hw, struct ice_buf *bufs, u32 count); int ice_pkg_buf_reserve_section(struct ice_buf_build *bld, u16 count); u16 ice_pkg_buf_get_active_sections(struct ice_buf_build *bld); +void * +ice_pkg_enum_entry(struct ice_seg *ice_seg, struct ice_pkg_enum *state, + u32 sect_type, u32 *offset, + void *(*handler)(u32 sect_type, void *section, + u32 index, u32 *offset)); void *ice_pkg_enum_section(struct ice_seg *ice_seg, struct ice_pkg_enum *state, u32 sect_type); diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.c b/drivers/net/ethernet/intel/ice/ice_dpll.c index e92be6f130a3..cd95705d1e7f 100644 --- a/drivers/net/ethernet/intel/ice/ice_dpll.c +++ b/drivers/net/ethernet/intel/ice/ice_dpll.c @@ -9,6 +9,7 @@ #define ICE_CGU_STATE_ACQ_ERR_THRESHOLD 50 #define ICE_DPLL_PIN_IDX_INVALID 0xff #define ICE_DPLL_RCLK_NUM_PER_PF 1 +#define ICE_DPLL_PIN_ESYNC_PULSE_HIGH_PERCENT 25 /** * enum ice_dpll_pin_type - enumerate ice pin types: @@ -30,6 +31,10 @@ static const char * const pin_type_name[] = { [ICE_DPLL_PIN_TYPE_RCLK_INPUT] = "rclk-input", }; +static const struct dpll_pin_frequency ice_esync_range[] = { + DPLL_PIN_FREQUENCY_RANGE(0, DPLL_PIN_FREQUENCY_1_HZ), +}; + /** * ice_dpll_is_reset - check if reset is in progress * @pf: private board structure @@ -394,8 +399,8 @@ ice_dpll_pin_state_update(struct ice_pf *pf, struct ice_dpll_pin *pin, switch (pin_type) { case ICE_DPLL_PIN_TYPE_INPUT: - ret = ice_aq_get_input_pin_cfg(&pf->hw, pin->idx, NULL, NULL, - NULL, &pin->flags[0], + ret = ice_aq_get_input_pin_cfg(&pf->hw, pin->idx, &pin->status, + NULL, NULL, &pin->flags[0], &pin->freq, &pin->phase_adjust); if (ret) goto err; @@ -430,7 +435,7 @@ ice_dpll_pin_state_update(struct ice_pf *pf, struct ice_dpll_pin *pin, goto err; parent &= ICE_AQC_GET_CGU_OUT_CFG_DPLL_SRC_SEL; - if (ICE_AQC_SET_CGU_OUT_CFG_OUT_EN & pin->flags[0]) { + if (ICE_AQC_GET_CGU_OUT_CFG_OUT_EN & pin->flags[0]) { pin->state[pf->dplls.eec.dpll_idx] = parent == pf->dplls.eec.dpll_idx ? DPLL_PIN_STATE_CONNECTED : @@ -1099,6 +1104,214 @@ ice_dpll_phase_offset_get(const struct dpll_pin *pin, void *pin_priv, } /** + * ice_dpll_output_esync_set - callback for setting embedded sync + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: registered dpll pointer + * @dpll_priv: private data pointer passed on dpll registration + * @freq: requested embedded sync frequency + * @extack: error reporting + * + * Dpll subsystem callback. Handler for setting embedded sync frequency value + * on output pin. + * + * Context: Acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - error + */ +static int +ice_dpll_output_esync_set(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + u64 freq, struct netlink_ext_ack *extack) +{ + struct ice_dpll_pin *p = pin_priv; + struct ice_dpll *d = dpll_priv; + struct ice_pf *pf = d->pf; + u8 flags = 0; + int ret; + + if (ice_dpll_is_reset(pf, extack)) + return -EBUSY; + mutex_lock(&pf->dplls.lock); + if (p->flags[0] & ICE_AQC_GET_CGU_OUT_CFG_OUT_EN) + flags = ICE_AQC_SET_CGU_OUT_CFG_OUT_EN; + if (freq == DPLL_PIN_FREQUENCY_1_HZ) { + if (p->flags[0] & ICE_AQC_GET_CGU_OUT_CFG_ESYNC_EN) { + ret = 0; + } else { + flags |= ICE_AQC_SET_CGU_OUT_CFG_ESYNC_EN; + ret = ice_aq_set_output_pin_cfg(&pf->hw, p->idx, flags, + 0, 0, 0); + } + } else { + if (!(p->flags[0] & ICE_AQC_GET_CGU_OUT_CFG_ESYNC_EN)) { + ret = 0; + } else { + flags &= ~ICE_AQC_SET_CGU_OUT_CFG_ESYNC_EN; + ret = ice_aq_set_output_pin_cfg(&pf->hw, p->idx, flags, + 0, 0, 0); + } + } + mutex_unlock(&pf->dplls.lock); + + return ret; +} + +/** + * ice_dpll_output_esync_get - callback for getting embedded sync config + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: registered dpll pointer + * @dpll_priv: private data pointer passed on dpll registration + * @esync: on success holds embedded sync pin properties + * @extack: error reporting + * + * Dpll subsystem callback. Handler for getting embedded sync frequency value + * and capabilities on output pin. + * + * Context: Acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - error + */ +static int +ice_dpll_output_esync_get(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + struct dpll_pin_esync *esync, + struct netlink_ext_ack *extack) +{ + struct ice_dpll_pin *p = pin_priv; + struct ice_dpll *d = dpll_priv; + struct ice_pf *pf = d->pf; + + if (ice_dpll_is_reset(pf, extack)) + return -EBUSY; + mutex_lock(&pf->dplls.lock); + if (!(p->flags[0] & ICE_AQC_GET_CGU_OUT_CFG_ESYNC_ABILITY) || + p->freq != DPLL_PIN_FREQUENCY_10_MHZ) { + mutex_unlock(&pf->dplls.lock); + return -EOPNOTSUPP; + } + esync->range = ice_esync_range; + esync->range_num = ARRAY_SIZE(ice_esync_range); + if (p->flags[0] & ICE_AQC_GET_CGU_OUT_CFG_ESYNC_EN) { + esync->freq = DPLL_PIN_FREQUENCY_1_HZ; + esync->pulse = ICE_DPLL_PIN_ESYNC_PULSE_HIGH_PERCENT; + } else { + esync->freq = 0; + esync->pulse = 0; + } + mutex_unlock(&pf->dplls.lock); + + return 0; +} + +/** + * ice_dpll_input_esync_set - callback for setting embedded sync + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: registered dpll pointer + * @dpll_priv: private data pointer passed on dpll registration + * @freq: requested embedded sync frequency + * @extack: error reporting + * + * Dpll subsystem callback. Handler for setting embedded sync frequency value + * on input pin. + * + * Context: Acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - error + */ +static int +ice_dpll_input_esync_set(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + u64 freq, struct netlink_ext_ack *extack) +{ + struct ice_dpll_pin *p = pin_priv; + struct ice_dpll *d = dpll_priv; + struct ice_pf *pf = d->pf; + u8 flags_en = 0; + int ret; + + if (ice_dpll_is_reset(pf, extack)) + return -EBUSY; + mutex_lock(&pf->dplls.lock); + if (p->flags[0] & ICE_AQC_GET_CGU_IN_CFG_FLG2_INPUT_EN) + flags_en = ICE_AQC_SET_CGU_IN_CFG_FLG2_INPUT_EN; + if (freq == DPLL_PIN_FREQUENCY_1_HZ) { + if (p->flags[0] & ICE_AQC_GET_CGU_IN_CFG_FLG2_ESYNC_EN) { + ret = 0; + } else { + flags_en |= ICE_AQC_SET_CGU_IN_CFG_FLG2_ESYNC_EN; + ret = ice_aq_set_input_pin_cfg(&pf->hw, p->idx, 0, + flags_en, 0, 0); + } + } else { + if (!(p->flags[0] & ICE_AQC_GET_CGU_IN_CFG_FLG2_ESYNC_EN)) { + ret = 0; + } else { + flags_en &= ~ICE_AQC_SET_CGU_IN_CFG_FLG2_ESYNC_EN; + ret = ice_aq_set_input_pin_cfg(&pf->hw, p->idx, 0, + flags_en, 0, 0); + } + } + mutex_unlock(&pf->dplls.lock); + + return ret; +} + +/** + * ice_dpll_input_esync_get - callback for getting embedded sync config + * @pin: pointer to a pin + * @pin_priv: private data pointer passed on pin registration + * @dpll: registered dpll pointer + * @dpll_priv: private data pointer passed on dpll registration + * @esync: on success holds embedded sync pin properties + * @extack: error reporting + * + * Dpll subsystem callback. Handler for getting embedded sync frequency value + * and capabilities on input pin. + * + * Context: Acquires pf->dplls.lock + * Return: + * * 0 - success + * * negative - error + */ +static int +ice_dpll_input_esync_get(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + struct dpll_pin_esync *esync, + struct netlink_ext_ack *extack) +{ + struct ice_dpll_pin *p = pin_priv; + struct ice_dpll *d = dpll_priv; + struct ice_pf *pf = d->pf; + + if (ice_dpll_is_reset(pf, extack)) + return -EBUSY; + mutex_lock(&pf->dplls.lock); + if (!(p->status & ICE_AQC_GET_CGU_IN_CFG_STATUS_ESYNC_CAP) || + p->freq != DPLL_PIN_FREQUENCY_10_MHZ) { + mutex_unlock(&pf->dplls.lock); + return -EOPNOTSUPP; + } + esync->range = ice_esync_range; + esync->range_num = ARRAY_SIZE(ice_esync_range); + if (p->flags[0] & ICE_AQC_GET_CGU_IN_CFG_FLG2_ESYNC_EN) { + esync->freq = DPLL_PIN_FREQUENCY_1_HZ; + esync->pulse = ICE_DPLL_PIN_ESYNC_PULSE_HIGH_PERCENT; + } else { + esync->freq = 0; + esync->pulse = 0; + } + mutex_unlock(&pf->dplls.lock); + + return 0; +} + +/** * ice_dpll_rclk_state_on_pin_set - set a state on rclk pin * @pin: pointer to a pin * @pin_priv: private data pointer passed on pin registration @@ -1222,6 +1435,8 @@ static const struct dpll_pin_ops ice_dpll_input_ops = { .phase_adjust_get = ice_dpll_pin_phase_adjust_get, .phase_adjust_set = ice_dpll_input_phase_adjust_set, .phase_offset_get = ice_dpll_phase_offset_get, + .esync_set = ice_dpll_input_esync_set, + .esync_get = ice_dpll_input_esync_get, }; static const struct dpll_pin_ops ice_dpll_output_ops = { @@ -1232,6 +1447,8 @@ static const struct dpll_pin_ops ice_dpll_output_ops = { .direction_get = ice_dpll_output_direction, .phase_adjust_get = ice_dpll_pin_phase_adjust_get, .phase_adjust_set = ice_dpll_output_phase_adjust_set, + .esync_set = ice_dpll_output_esync_set, + .esync_get = ice_dpll_output_esync_get, }; static const struct dpll_device_ops ice_dpll_ops = { diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.h b/drivers/net/ethernet/intel/ice/ice_dpll.h index 93172e93995b..c320f1bf7d6d 100644 --- a/drivers/net/ethernet/intel/ice/ice_dpll.h +++ b/drivers/net/ethernet/intel/ice/ice_dpll.h @@ -31,6 +31,7 @@ struct ice_dpll_pin { struct dpll_pin_properties prop; u32 freq; s32 phase_adjust; + u8 status; }; /** ice_dpll - store info required for DPLL control diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index bc79ba974e49..c7641d326ba5 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -4725,6 +4725,7 @@ static const struct ethtool_ops ice_ethtool_ops = { ETHTOOL_COALESCE_USE_ADAPTIVE | ETHTOOL_COALESCE_RX_USECS_HIGH, .cap_rss_sym_xor_supported = true, + .rxfh_per_ctx_key = true, .get_link_ksettings = ice_get_link_ksettings, .set_link_ksettings = ice_set_link_ksettings, .get_fec_stats = ice_get_fec_stats, diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c index 20d5db88c99f..ed95072ca6e3 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c +++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c @@ -2981,6 +2981,50 @@ ice_add_prof_attrib(struct ice_prof_map *prof, u8 ptg, u16 ptype, } /** + * ice_disable_fd_swap - set register appropriately to disable FD SWAP + * @hw: pointer to the HW struct + * @prof_id: profile ID + */ +static void +ice_disable_fd_swap(struct ice_hw *hw, u8 prof_id) +{ + u16 swap_val, fvw_num; + unsigned int i; + + swap_val = ICE_SWAP_VALID; + fvw_num = hw->blk[ICE_BLK_FD].es.fvw / ICE_FDIR_REG_SET_SIZE; + + /* Since the SWAP Flag in the Programming Desc doesn't work, + * here add method to disable the SWAP Option via setting + * certain SWAP and INSET register sets. + */ + for (i = 0; i < fvw_num ; i++) { + u32 raw_swap, raw_in; + unsigned int j; + + raw_swap = 0; + raw_in = 0; + + for (j = 0; j < ICE_FDIR_REG_SET_SIZE; j++) { + raw_swap |= (swap_val++) << (j * BITS_PER_BYTE); + raw_in |= ICE_INSET_DFLT << (j * BITS_PER_BYTE); + } + + /* write the FDIR swap register set */ + wr32(hw, GLQF_FDSWAP(prof_id, i), raw_swap); + + ice_debug(hw, ICE_DBG_INIT, "swap wr(%d, %d): 0x%x = 0x%08x\n", + prof_id, i, GLQF_FDSWAP(prof_id, i), raw_swap); + + /* write the FDIR inset register set */ + wr32(hw, GLQF_FDINSET(prof_id, i), raw_in); + + ice_debug(hw, ICE_DBG_INIT, "inset wr(%d, %d): 0x%x = 0x%08x\n", + prof_id, i, GLQF_FDINSET(prof_id, i), raw_in); + } +} + +/* * ice_add_prof - add profile * @hw: pointer to the HW struct * @blk: hardware block @@ -2991,6 +3035,7 @@ ice_add_prof_attrib(struct ice_prof_map *prof, u8 ptg, u16 ptype, * @es: extraction sequence (length of array is determined by the block) * @masks: mask for extraction sequence * @symm: symmetric setting for RSS profiles + * @fd_swap: enable/disable FDIR paired src/dst fields swap option * * This function registers a profile, which matches a set of PTYPES with a * particular extraction sequence. While the hardware profile is allocated @@ -3000,7 +3045,7 @@ ice_add_prof_attrib(struct ice_prof_map *prof, u8 ptg, u16 ptype, int ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[], const struct ice_ptype_attributes *attr, u16 attr_cnt, - struct ice_fv_word *es, u16 *masks, bool symm) + struct ice_fv_word *es, u16 *masks, bool symm, bool fd_swap) { u32 bytes = DIV_ROUND_UP(ICE_FLOW_PTYPE_MAX, BITS_PER_BYTE); DECLARE_BITMAP(ptgs_used, ICE_XLT1_CNT); @@ -3020,7 +3065,7 @@ ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[], status = ice_alloc_prof_id(hw, blk, &prof_id); if (status) goto err_ice_add_prof; - if (blk == ICE_BLK_FD) { + if (blk == ICE_BLK_FD && fd_swap) { /* For Flow Director block, the extraction sequence may * need to be altered in the case where there are paired * fields that have no match. This is necessary because @@ -3031,6 +3076,8 @@ ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[], status = ice_update_fd_swap(hw, prof_id, es); if (status) goto err_ice_add_prof; + } else if (blk == ICE_BLK_FD) { + ice_disable_fd_swap(hw, prof_id); } status = ice_update_prof_masking(hw, blk, prof_id, masks); if (status) @@ -4099,6 +4146,54 @@ err_ice_add_prof_id_flow: } /** + * ice_flow_assoc_fdir_prof - add an FDIR profile for main/ctrl VSI + * @hw: pointer to the HW struct + * @blk: HW block + * @dest_vsi: dest VSI + * @fdir_vsi: fdir programming VSI + * @hdl: profile handle + * + * Update the hardware tables to enable the FDIR profile indicated by @hdl for + * the VSI specified by @dest_vsi. On success, the flow will be enabled. + * + * Return: 0 on success or negative errno on failure. + */ +int +ice_flow_assoc_fdir_prof(struct ice_hw *hw, enum ice_block blk, + u16 dest_vsi, u16 fdir_vsi, u64 hdl) +{ + 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) { + ice_debug(hw, ICE_DBG_FLOW, "Adding HW profile failed for main VSI flow entry: %d\n", + status); + return status; + } + + vsi_num = ice_get_hw_vsi_num(hw, fdir_vsi); + status = ice_add_prof_id_flow(hw, blk, vsi_num, hdl); + if (status) { + ice_debug(hw, ICE_DBG_FLOW, "Adding HW profile failed for ctrl VSI flow entry: %d\n", + status); + goto err; + } + + return 0; + +err: + vsi_num = ice_get_hw_vsi_num(hw, dest_vsi); + ice_rem_prof_id_flow(hw, blk, vsi_num, hdl); + + return status; +} + +/** * ice_rem_prof_from_list - remove a profile from list * @hw: pointer to the HW struct * @lst: list to remove the profile from diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h index b39d7cdc381f..90b9b0993122 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h +++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h @@ -6,6 +6,8 @@ #include "ice_type.h" +#define ICE_FDIR_REG_SET_SIZE 4 + int ice_acquire_change_lock(struct ice_hw *hw, enum ice_aq_res_access_type access); void ice_release_change_lock(struct ice_hw *hw); @@ -42,13 +44,16 @@ bool ice_hw_ptype_ena(struct ice_hw *hw, u16 ptype); int ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[], const struct ice_ptype_attributes *attr, u16 attr_cnt, - struct ice_fv_word *es, u16 *masks, bool symm); + struct ice_fv_word *es, u16 *masks, bool symm, bool fd_swap); struct ice_prof_map * ice_search_prof_id(struct ice_hw *hw, enum ice_block blk, u64 id); int ice_add_prof_id_flow(struct ice_hw *hw, enum ice_block blk, u16 vsi, u64 hdl); int ice_rem_prof_id_flow(struct ice_hw *hw, enum ice_block blk, u16 vsi, u64 hdl); +int +ice_flow_assoc_fdir_prof(struct ice_hw *hw, enum ice_block blk, + u16 dest_vsi, u16 fdir_vsi, u64 hdl); enum ice_ddp_state ice_init_pkg(struct ice_hw *hw, u8 *buff, u32 len); enum ice_ddp_state ice_copy_and_init_pkg(struct ice_hw *hw, const u8 *buf, u32 len); diff --git a/drivers/net/ethernet/intel/ice/ice_flow.c b/drivers/net/ethernet/intel/ice/ice_flow.c index fc2b58f56279..d97b751052f2 100644 --- a/drivers/net/ethernet/intel/ice/ice_flow.c +++ b/drivers/net/ethernet/intel/ice/ice_flow.c @@ -409,6 +409,29 @@ static const u32 ice_ptypes_gtpc_tid[] = { }; /* Packet types for GTPU */ +static const struct ice_ptype_attributes ice_attr_gtpu_session[] = { + { ICE_MAC_IPV4_GTPU_IPV4_FRAG, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV4_GTPU_IPV4_PAY, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV4_GTPU_IPV4_UDP_PAY, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV4_GTPU_IPV4_TCP, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV4_GTPU_IPV4_ICMP, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV6_GTPU_IPV4_FRAG, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV6_GTPU_IPV4_PAY, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV6_GTPU_IPV4_UDP_PAY, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV6_GTPU_IPV4_TCP, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV6_GTPU_IPV4_ICMP, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV4_GTPU_IPV6_FRAG, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV4_GTPU_IPV6_PAY, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV4_GTPU_IPV6_UDP_PAY, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV4_GTPU_IPV6_TCP, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV4_GTPU_IPV6_ICMPV6, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV6_GTPU_IPV6_FRAG, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV6_GTPU_IPV6_PAY, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV6_GTPU_IPV6_UDP_PAY, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV6_GTPU_IPV6_TCP, ICE_PTYPE_ATTR_GTP_SESSION }, + { ICE_MAC_IPV6_GTPU_IPV6_ICMPV6, ICE_PTYPE_ATTR_GTP_SESSION }, +}; + static const struct ice_ptype_attributes ice_attr_gtpu_eh[] = { { ICE_MAC_IPV4_GTPU_IPV4_FRAG, ICE_PTYPE_ATTR_GTP_PDU_EH }, { ICE_MAC_IPV4_GTPU_IPV4_PAY, ICE_PTYPE_ATTR_GTP_PDU_EH }, @@ -1400,7 +1423,7 @@ ice_flow_add_prof_sync(struct ice_hw *hw, enum ice_block blk, /* Add a HW profile for this flow profile */ status = ice_add_prof(hw, blk, prof_id, (u8 *)params->ptypes, params->attr, params->attr_cnt, params->es, - params->mask, symm); + params->mask, symm, true); if (status) { ice_debug(hw, ICE_DBG_FLOW, "Error adding a HW flow profile\n"); goto out; @@ -1523,6 +1546,90 @@ ice_flow_disassoc_prof(struct ice_hw *hw, enum ice_block blk, return status; } +#define FLAG_GTP_EH_PDU_LINK BIT_ULL(13) +#define FLAG_GTP_EH_PDU BIT_ULL(14) + +#define HI_BYTE_IN_WORD GENMASK(15, 8) +#define LO_BYTE_IN_WORD GENMASK(7, 0) + +#define FLAG_GTPU_MSK \ + (FLAG_GTP_EH_PDU | FLAG_GTP_EH_PDU_LINK) +#define FLAG_GTPU_UP \ + (FLAG_GTP_EH_PDU | FLAG_GTP_EH_PDU_LINK) +#define FLAG_GTPU_DW FLAG_GTP_EH_PDU + +/** + * ice_flow_set_parser_prof - Set flow profile based on the parsed profile info + * @hw: pointer to the HW struct + * @dest_vsi: dest VSI + * @fdir_vsi: fdir programming VSI + * @prof: stores parsed profile info from raw flow + * @blk: classification blk + * + * Return: 0 on success or negative errno on failure. + */ +int +ice_flow_set_parser_prof(struct ice_hw *hw, u16 dest_vsi, u16 fdir_vsi, + struct ice_parser_profile *prof, enum ice_block blk) +{ + u64 id = find_first_bit(prof->ptypes, ICE_FLOW_PTYPE_MAX); + struct ice_flow_prof_params *params __free(kfree); + u8 fv_words = hw->blk[blk].es.fvw; + int status; + int i, idx; + + params = kzalloc(sizeof(*params), GFP_KERNEL); + if (!params) + return -ENOMEM; + + for (i = 0; i < ICE_MAX_FV_WORDS; i++) { + params->es[i].prot_id = ICE_PROT_INVALID; + params->es[i].off = ICE_FV_OFFSET_INVAL; + } + + for (i = 0; i < prof->fv_num; i++) { + if (hw->blk[blk].es.reverse) + idx = fv_words - i - 1; + else + idx = i; + params->es[idx].prot_id = prof->fv[i].proto_id; + params->es[idx].off = prof->fv[i].offset; + params->mask[idx] = (((prof->fv[i].msk) << BITS_PER_BYTE) & + HI_BYTE_IN_WORD) | + (((prof->fv[i].msk) >> BITS_PER_BYTE) & + LO_BYTE_IN_WORD); + } + + switch (prof->flags) { + case FLAG_GTPU_DW: + params->attr = ice_attr_gtpu_down; + params->attr_cnt = ARRAY_SIZE(ice_attr_gtpu_down); + break; + case FLAG_GTPU_UP: + params->attr = ice_attr_gtpu_up; + params->attr_cnt = ARRAY_SIZE(ice_attr_gtpu_up); + break; + default: + if (prof->flags_msk & FLAG_GTPU_MSK) { + params->attr = ice_attr_gtpu_session; + params->attr_cnt = ARRAY_SIZE(ice_attr_gtpu_session); + } + break; + } + + status = ice_add_prof(hw, blk, id, (u8 *)prof->ptypes, + params->attr, params->attr_cnt, + params->es, params->mask, false, false); + if (status) + return status; + + status = ice_flow_assoc_fdir_prof(hw, blk, dest_vsi, fdir_vsi, id); + if (status) + ice_rem_prof(hw, blk, id); + + return status; +} + /** * ice_flow_add_prof - Add a flow profile for packet segments and matched fields * @hw: pointer to the HW struct diff --git a/drivers/net/ethernet/intel/ice/ice_flow.h b/drivers/net/ethernet/intel/ice/ice_flow.h index 2fd2e0cb483d..6cb7bb879c98 100644 --- a/drivers/net/ethernet/intel/ice/ice_flow.h +++ b/drivers/net/ethernet/intel/ice/ice_flow.h @@ -5,6 +5,7 @@ #define _ICE_FLOW_H_ #include "ice_flex_type.h" +#include "ice_parser.h" #define ICE_FLOW_ENTRY_HANDLE_INVAL 0 #define ICE_FLOW_FLD_OFF_INVAL 0xffff @@ -326,6 +327,7 @@ enum ice_rss_cfg_hdr_type { ICE_RSS_ANY_HEADERS }; +struct ice_vsi; struct ice_rss_hash_cfg { u32 addl_hdrs; /* protocol header fields */ u64 hash_flds; /* hash bit field (ICE_FLOW_HASH_*) to configure */ @@ -445,6 +447,9 @@ ice_flow_add_prof(struct ice_hw *hw, enum ice_block blk, enum ice_flow_dir dir, bool symm, struct ice_flow_prof **prof); int ice_flow_rem_prof(struct ice_hw *hw, enum ice_block blk, u64 prof_id); int +ice_flow_set_parser_prof(struct ice_hw *hw, u16 dest_vsi, u16 fdir_vsi, + struct ice_parser_profile *prof, enum ice_block blk); +int ice_flow_add_entry(struct ice_hw *hw, enum ice_block blk, u64 prof_id, u64 entry_id, u16 vsi, enum ice_flow_priority prio, void *data, u64 *entry_h); diff --git a/drivers/net/ethernet/intel/ice/ice_osdep.h b/drivers/net/ethernet/intel/ice/ice_osdep.h index a2562f04267f..b9f383494b3f 100644 --- a/drivers/net/ethernet/intel/ice/ice_osdep.h +++ b/drivers/net/ethernet/intel/ice/ice_osdep.h @@ -12,6 +12,7 @@ #include <linux/ethtool.h> #include <linux/etherdevice.h> #include <linux/if_ether.h> +#include <linux/iopoll.h> #include <linux/pci_ids.h> #ifndef CONFIG_64BIT #include <linux/io-64-nonatomic-lo-hi.h> @@ -23,6 +24,9 @@ #define wr64(a, reg, value) writeq((value), ((a)->hw_addr + (reg))) #define rd64(a, reg) readq((a)->hw_addr + (reg)) +#define rd32_poll_timeout(a, addr, val, cond, delay_us, timeout_us) \ + read_poll_timeout(rd32, val, cond, delay_us, timeout_us, false, a, addr) + #define ice_flush(a) rd32((a), GLGEN_STAT) #define ICE_M(m, s) ((m ## U) << (s)) @@ -39,11 +43,10 @@ struct device *ice_hw_to_dev(struct ice_hw *hw); #define ice_debug(hw, type, fmt, args...) \ dev_dbg(ice_hw_to_dev(hw), fmt, ##args) -#define ice_debug_array(hw, type, rowsize, groupsize, buf, len) \ - print_hex_dump_debug(KBUILD_MODNAME " ", \ - DUMP_PREFIX_OFFSET, rowsize, \ - groupsize, buf, len, false) -#else +#define _ice_debug_array(hw, type, prefix, rowsize, groupsize, buf, len) \ + print_hex_dump_debug(prefix, DUMP_PREFIX_OFFSET, \ + rowsize, groupsize, buf, len, false) +#else /* CONFIG_DYNAMIC_DEBUG */ #define ice_debug(hw, type, fmt, args...) \ do { \ if ((type) & (hw)->debug_mask) \ @@ -51,16 +54,15 @@ do { \ } while (0) #ifdef DEBUG -#define ice_debug_array(hw, type, rowsize, groupsize, buf, len) \ +#define _ice_debug_array(hw, type, prefix, rowsize, groupsize, buf, len) \ do { \ if ((type) & (hw)->debug_mask) \ - print_hex_dump_debug(KBUILD_MODNAME, \ - DUMP_PREFIX_OFFSET, \ + print_hex_dump_debug(prefix, DUMP_PREFIX_OFFSET,\ rowsize, groupsize, buf, \ len, false); \ } while (0) -#else -#define ice_debug_array(hw, type, rowsize, groupsize, buf, len) \ +#else /* DEBUG */ +#define _ice_debug_array(hw, type, prefix, rowsize, groupsize, buf, len) \ do { \ struct ice_hw *hw_l = hw; \ if ((type) & (hw_l)->debug_mask) { \ @@ -78,4 +80,10 @@ do { \ #endif /* DEBUG */ #endif /* CONFIG_DYNAMIC_DEBUG */ +#define ice_debug_array(hw, type, rowsize, groupsize, buf, len) \ + _ice_debug_array(hw, type, KBUILD_MODNAME, rowsize, groupsize, buf, len) + +#define ice_debug_array_w_prefix(hw, type, prefix, buf, len) \ + _ice_debug_array(hw, type, prefix, 16, 1, buf, len) + #endif /* _ICE_OSDEP_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_parser.c b/drivers/net/ethernet/intel/ice/ice_parser.c new file mode 100644 index 000000000000..664beb64f557 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_parser.c @@ -0,0 +1,2430 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2024 Intel Corporation */ + +#include "ice_common.h" + +struct ice_pkg_sect_hdr { + __le16 count; + __le16 offset; +}; + +/** + * ice_parser_sect_item_get - parse an item from a section + * @sect_type: section type + * @section: section object + * @index: index of the item to get + * @offset: dummy as prototype of ice_pkg_enum_entry's last parameter + * + * Return: a pointer to the item or NULL. + */ +static void *ice_parser_sect_item_get(u32 sect_type, void *section, + u32 index, u32 __maybe_unused *offset) +{ + size_t data_off = ICE_SEC_DATA_OFFSET; + struct ice_pkg_sect_hdr *hdr; + size_t size; + + if (!section) + return NULL; + + switch (sect_type) { + case ICE_SID_RXPARSER_IMEM: + size = ICE_SID_RXPARSER_IMEM_ENTRY_SIZE; + break; + case ICE_SID_RXPARSER_METADATA_INIT: + size = ICE_SID_RXPARSER_METADATA_INIT_ENTRY_SIZE; + break; + case ICE_SID_RXPARSER_CAM: + size = ICE_SID_RXPARSER_CAM_ENTRY_SIZE; + break; + case ICE_SID_RXPARSER_PG_SPILL: + size = ICE_SID_RXPARSER_PG_SPILL_ENTRY_SIZE; + break; + case ICE_SID_RXPARSER_NOMATCH_CAM: + size = ICE_SID_RXPARSER_NOMATCH_CAM_ENTRY_SIZE; + break; + case ICE_SID_RXPARSER_NOMATCH_SPILL: + size = ICE_SID_RXPARSER_NOMATCH_SPILL_ENTRY_SIZE; + break; + case ICE_SID_RXPARSER_BOOST_TCAM: + size = ICE_SID_RXPARSER_BOOST_TCAM_ENTRY_SIZE; + break; + case ICE_SID_LBL_RXPARSER_TMEM: + data_off = ICE_SEC_LBL_DATA_OFFSET; + size = ICE_SID_LBL_ENTRY_SIZE; + break; + case ICE_SID_RXPARSER_MARKER_PTYPE: + size = ICE_SID_RXPARSER_MARKER_TYPE_ENTRY_SIZE; + break; + case ICE_SID_RXPARSER_MARKER_GRP: + size = ICE_SID_RXPARSER_MARKER_GRP_ENTRY_SIZE; + break; + case ICE_SID_RXPARSER_PROTO_GRP: + size = ICE_SID_RXPARSER_PROTO_GRP_ENTRY_SIZE; + break; + case ICE_SID_RXPARSER_FLAG_REDIR: + size = ICE_SID_RXPARSER_FLAG_REDIR_ENTRY_SIZE; + break; + default: + return NULL; + } + + hdr = section; + if (index >= le16_to_cpu(hdr->count)) + return NULL; + + return section + data_off + index * size; +} + +/** + * ice_parser_create_table - create an item table from a section + * @hw: pointer to the hardware structure + * @sect_type: section type + * @item_size: item size in bytes + * @length: number of items in the table to create + * @parse_item: the function to parse the item + * @no_offset: ignore header offset, calculate index from 0 + * + * Return: a pointer to the allocated table or ERR_PTR. + */ +static void * +ice_parser_create_table(struct ice_hw *hw, u32 sect_type, + u32 item_size, u32 length, + void (*parse_item)(struct ice_hw *hw, u16 idx, + void *item, void *data, + int size), bool no_offset) +{ + struct ice_pkg_enum state = {}; + struct ice_seg *seg = hw->seg; + void *table, *data, *item; + u16 idx = 0; + + if (!seg) + return ERR_PTR(-EINVAL); + + table = kzalloc(item_size * length, GFP_KERNEL); + if (!table) + return ERR_PTR(-ENOMEM); + + do { + data = ice_pkg_enum_entry(seg, &state, sect_type, NULL, + ice_parser_sect_item_get); + seg = NULL; + if (data) { + struct ice_pkg_sect_hdr *hdr = state.sect; + + if (!no_offset) + idx = le16_to_cpu(hdr->offset) + + state.entry_idx; + + item = (void *)((uintptr_t)table + idx * item_size); + parse_item(hw, idx, item, data, item_size); + + if (no_offset) + idx++; + } + } while (data); + + return table; +} + +/*** ICE_SID_RXPARSER_IMEM section ***/ +static void ice_imem_bst_bm_dump(struct ice_hw *hw, struct ice_bst_main *bm) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "boost main:\n"); + dev_info(dev, "\talu0 = %d\n", bm->alu0); + dev_info(dev, "\talu1 = %d\n", bm->alu1); + dev_info(dev, "\talu2 = %d\n", bm->alu2); + dev_info(dev, "\tpg = %d\n", bm->pg); +} + +static void ice_imem_bst_kb_dump(struct ice_hw *hw, + struct ice_bst_keybuilder *kb) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "boost key builder:\n"); + dev_info(dev, "\tpriority = %d\n", kb->prio); + dev_info(dev, "\ttsr_ctrl = %d\n", kb->tsr_ctrl); +} + +static void ice_imem_np_kb_dump(struct ice_hw *hw, + struct ice_np_keybuilder *kb) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "next proto key builder:\n"); + dev_info(dev, "\topc = %d\n", kb->opc); + dev_info(dev, "\tstart_or_reg0 = %d\n", kb->start_reg0); + dev_info(dev, "\tlen_or_reg1 = %d\n", kb->len_reg1); +} + +static void ice_imem_pg_kb_dump(struct ice_hw *hw, + struct ice_pg_keybuilder *kb) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "parse graph key builder:\n"); + dev_info(dev, "\tflag0_ena = %d\n", kb->flag0_ena); + dev_info(dev, "\tflag1_ena = %d\n", kb->flag1_ena); + dev_info(dev, "\tflag2_ena = %d\n", kb->flag2_ena); + dev_info(dev, "\tflag3_ena = %d\n", kb->flag3_ena); + dev_info(dev, "\tflag0_idx = %d\n", kb->flag0_idx); + dev_info(dev, "\tflag1_idx = %d\n", kb->flag1_idx); + dev_info(dev, "\tflag2_idx = %d\n", kb->flag2_idx); + dev_info(dev, "\tflag3_idx = %d\n", kb->flag3_idx); + dev_info(dev, "\talu_reg_idx = %d\n", kb->alu_reg_idx); +} + +static void ice_imem_alu_dump(struct ice_hw *hw, + struct ice_alu *alu, int index) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "alu%d:\n", index); + dev_info(dev, "\topc = %d\n", alu->opc); + dev_info(dev, "\tsrc_start = %d\n", alu->src_start); + dev_info(dev, "\tsrc_len = %d\n", alu->src_len); + dev_info(dev, "\tshift_xlate_sel = %d\n", alu->shift_xlate_sel); + dev_info(dev, "\tshift_xlate_key = %d\n", alu->shift_xlate_key); + dev_info(dev, "\tsrc_reg_id = %d\n", alu->src_reg_id); + dev_info(dev, "\tdst_reg_id = %d\n", alu->dst_reg_id); + dev_info(dev, "\tinc0 = %d\n", alu->inc0); + dev_info(dev, "\tinc1 = %d\n", alu->inc1); + dev_info(dev, "\tproto_offset_opc = %d\n", alu->proto_offset_opc); + dev_info(dev, "\tproto_offset = %d\n", alu->proto_offset); + dev_info(dev, "\tbranch_addr = %d\n", alu->branch_addr); + dev_info(dev, "\timm = %d\n", alu->imm); + dev_info(dev, "\tdst_start = %d\n", alu->dst_start); + dev_info(dev, "\tdst_len = %d\n", alu->dst_len); + dev_info(dev, "\tflags_extr_imm = %d\n", alu->flags_extr_imm); + dev_info(dev, "\tflags_start_imm= %d\n", alu->flags_start_imm); +} + +/** + * ice_imem_dump - dump an imem item info + * @hw: pointer to the hardware structure + * @item: imem item to dump + */ +static void ice_imem_dump(struct ice_hw *hw, struct ice_imem_item *item) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "index = %d\n", item->idx); + ice_imem_bst_bm_dump(hw, &item->b_m); + ice_imem_bst_kb_dump(hw, &item->b_kb); + dev_info(dev, "pg priority = %d\n", item->pg_prio); + ice_imem_np_kb_dump(hw, &item->np_kb); + ice_imem_pg_kb_dump(hw, &item->pg_kb); + ice_imem_alu_dump(hw, &item->alu0, 0); + ice_imem_alu_dump(hw, &item->alu1, 1); + ice_imem_alu_dump(hw, &item->alu2, 2); +} + +#define ICE_IM_BM_ALU0 BIT(0) +#define ICE_IM_BM_ALU1 BIT(1) +#define ICE_IM_BM_ALU2 BIT(2) +#define ICE_IM_BM_PG BIT(3) + +/** + * ice_imem_bm_init - parse 4 bits of Boost Main + * @bm: pointer to the Boost Main structure + * @data: Boost Main data to be parsed + */ +static void ice_imem_bm_init(struct ice_bst_main *bm, u8 data) +{ + bm->alu0 = FIELD_GET(ICE_IM_BM_ALU0, data); + bm->alu1 = FIELD_GET(ICE_IM_BM_ALU1, data); + bm->alu2 = FIELD_GET(ICE_IM_BM_ALU2, data); + bm->pg = FIELD_GET(ICE_IM_BM_PG, data); +} + +#define ICE_IM_BKB_PRIO GENMASK(7, 0) +#define ICE_IM_BKB_TSR_CTRL BIT(8) + +/** + * ice_imem_bkb_init - parse 10 bits of Boost Main Build + * @bkb: pointer to the Boost Main Build structure + * @data: Boost Main Build data to be parsed + */ +static void ice_imem_bkb_init(struct ice_bst_keybuilder *bkb, u16 data) +{ + bkb->prio = FIELD_GET(ICE_IM_BKB_PRIO, data); + bkb->tsr_ctrl = FIELD_GET(ICE_IM_BKB_TSR_CTRL, data); +} + +#define ICE_IM_NPKB_OPC GENMASK(1, 0) +#define ICE_IM_NPKB_S_R0 GENMASK(9, 2) +#define ICE_IM_NPKB_L_R1 GENMASK(17, 10) + +/** + * ice_imem_npkb_init - parse 18 bits of Next Protocol Key Build + * @kb: pointer to the Next Protocol Key Build structure + * @data: Next Protocol Key Build data to be parsed + */ +static void ice_imem_npkb_init(struct ice_np_keybuilder *kb, u32 data) +{ + kb->opc = FIELD_GET(ICE_IM_NPKB_OPC, data); + kb->start_reg0 = FIELD_GET(ICE_IM_NPKB_S_R0, data); + kb->len_reg1 = FIELD_GET(ICE_IM_NPKB_L_R1, data); +} + +#define ICE_IM_PGKB_F0_ENA BIT_ULL(0) +#define ICE_IM_PGKB_F0_IDX GENMASK_ULL(6, 1) +#define ICE_IM_PGKB_F1_ENA BIT_ULL(7) +#define ICE_IM_PGKB_F1_IDX GENMASK_ULL(13, 8) +#define ICE_IM_PGKB_F2_ENA BIT_ULL(14) +#define ICE_IM_PGKB_F2_IDX GENMASK_ULL(20, 15) +#define ICE_IM_PGKB_F3_ENA BIT_ULL(21) +#define ICE_IM_PGKB_F3_IDX GENMASK_ULL(27, 22) +#define ICE_IM_PGKB_AR_IDX GENMASK_ULL(34, 28) + +/** + * ice_imem_pgkb_init - parse 35 bits of Parse Graph Key Build + * @kb: pointer to the Parse Graph Key Build structure + * @data: Parse Graph Key Build data to be parsed + */ +static void ice_imem_pgkb_init(struct ice_pg_keybuilder *kb, u64 data) +{ + kb->flag0_ena = FIELD_GET(ICE_IM_PGKB_F0_ENA, data); + kb->flag0_idx = FIELD_GET(ICE_IM_PGKB_F0_IDX, data); + kb->flag1_ena = FIELD_GET(ICE_IM_PGKB_F1_ENA, data); + kb->flag1_idx = FIELD_GET(ICE_IM_PGKB_F1_IDX, data); + kb->flag2_ena = FIELD_GET(ICE_IM_PGKB_F2_ENA, data); + kb->flag2_idx = FIELD_GET(ICE_IM_PGKB_F2_IDX, data); + kb->flag3_ena = FIELD_GET(ICE_IM_PGKB_F3_ENA, data); + kb->flag3_idx = FIELD_GET(ICE_IM_PGKB_F3_IDX, data); + kb->alu_reg_idx = FIELD_GET(ICE_IM_PGKB_AR_IDX, data); +} + +#define ICE_IM_ALU_OPC GENMASK_ULL(5, 0) +#define ICE_IM_ALU_SS GENMASK_ULL(13, 6) +#define ICE_IM_ALU_SL GENMASK_ULL(18, 14) +#define ICE_IM_ALU_SXS BIT_ULL(19) +#define ICE_IM_ALU_SXK GENMASK_ULL(23, 20) +#define ICE_IM_ALU_SRID GENMASK_ULL(30, 24) +#define ICE_IM_ALU_DRID GENMASK_ULL(37, 31) +#define ICE_IM_ALU_INC0 BIT_ULL(38) +#define ICE_IM_ALU_INC1 BIT_ULL(39) +#define ICE_IM_ALU_POO GENMASK_ULL(41, 40) +#define ICE_IM_ALU_PO GENMASK_ULL(49, 42) +#define ICE_IM_ALU_BA_S 50 /* offset for the 2nd 64-bits field */ +#define ICE_IM_ALU_BA GENMASK_ULL(57 - ICE_IM_ALU_BA_S, \ + 50 - ICE_IM_ALU_BA_S) +#define ICE_IM_ALU_IMM GENMASK_ULL(73 - ICE_IM_ALU_BA_S, \ + 58 - ICE_IM_ALU_BA_S) +#define ICE_IM_ALU_DFE BIT_ULL(74 - ICE_IM_ALU_BA_S) +#define ICE_IM_ALU_DS GENMASK_ULL(80 - ICE_IM_ALU_BA_S, \ + 75 - ICE_IM_ALU_BA_S) +#define ICE_IM_ALU_DL GENMASK_ULL(86 - ICE_IM_ALU_BA_S, \ + 81 - ICE_IM_ALU_BA_S) +#define ICE_IM_ALU_FEI BIT_ULL(87 - ICE_IM_ALU_BA_S) +#define ICE_IM_ALU_FSI GENMASK_ULL(95 - ICE_IM_ALU_BA_S, \ + 88 - ICE_IM_ALU_BA_S) + +/** + * ice_imem_alu_init - parse 96 bits of ALU entry + * @alu: pointer to the ALU entry structure + * @data: ALU entry data to be parsed + * @off: offset of the ALU entry data + */ +static void ice_imem_alu_init(struct ice_alu *alu, u8 *data, u8 off) +{ + u64 d64; + u8 idd; + + d64 = *((u64 *)data) >> off; + + alu->opc = FIELD_GET(ICE_IM_ALU_OPC, d64); + alu->src_start = FIELD_GET(ICE_IM_ALU_SS, d64); + alu->src_len = FIELD_GET(ICE_IM_ALU_SL, d64); + alu->shift_xlate_sel = FIELD_GET(ICE_IM_ALU_SXS, d64); + alu->shift_xlate_key = FIELD_GET(ICE_IM_ALU_SXK, d64); + alu->src_reg_id = FIELD_GET(ICE_IM_ALU_SRID, d64); + alu->dst_reg_id = FIELD_GET(ICE_IM_ALU_DRID, d64); + alu->inc0 = FIELD_GET(ICE_IM_ALU_INC0, d64); + alu->inc1 = FIELD_GET(ICE_IM_ALU_INC1, d64); + alu->proto_offset_opc = FIELD_GET(ICE_IM_ALU_POO, d64); + alu->proto_offset = FIELD_GET(ICE_IM_ALU_PO, d64); + + idd = (ICE_IM_ALU_BA_S + off) / BITS_PER_BYTE; + off = (ICE_IM_ALU_BA_S + off) % BITS_PER_BYTE; + d64 = *((u64 *)(&data[idd])) >> off; + + alu->branch_addr = FIELD_GET(ICE_IM_ALU_BA, d64); + alu->imm = FIELD_GET(ICE_IM_ALU_IMM, d64); + alu->dedicate_flags_ena = FIELD_GET(ICE_IM_ALU_DFE, d64); + alu->dst_start = FIELD_GET(ICE_IM_ALU_DS, d64); + alu->dst_len = FIELD_GET(ICE_IM_ALU_DL, d64); + alu->flags_extr_imm = FIELD_GET(ICE_IM_ALU_FEI, d64); + alu->flags_start_imm = FIELD_GET(ICE_IM_ALU_FSI, d64); +} + +#define ICE_IMEM_BM_S 0 +#define ICE_IMEM_BKB_S 4 +#define ICE_IMEM_BKB_IDD (ICE_IMEM_BKB_S / BITS_PER_BYTE) +#define ICE_IMEM_BKB_OFF (ICE_IMEM_BKB_S % BITS_PER_BYTE) +#define ICE_IMEM_PGP GENMASK(15, 14) +#define ICE_IMEM_NPKB_S 16 +#define ICE_IMEM_NPKB_IDD (ICE_IMEM_NPKB_S / BITS_PER_BYTE) +#define ICE_IMEM_NPKB_OFF (ICE_IMEM_NPKB_S % BITS_PER_BYTE) +#define ICE_IMEM_PGKB_S 34 +#define ICE_IMEM_PGKB_IDD (ICE_IMEM_PGKB_S / BITS_PER_BYTE) +#define ICE_IMEM_PGKB_OFF (ICE_IMEM_PGKB_S % BITS_PER_BYTE) +#define ICE_IMEM_ALU0_S 69 +#define ICE_IMEM_ALU0_IDD (ICE_IMEM_ALU0_S / BITS_PER_BYTE) +#define ICE_IMEM_ALU0_OFF (ICE_IMEM_ALU0_S % BITS_PER_BYTE) +#define ICE_IMEM_ALU1_S 165 +#define ICE_IMEM_ALU1_IDD (ICE_IMEM_ALU1_S / BITS_PER_BYTE) +#define ICE_IMEM_ALU1_OFF (ICE_IMEM_ALU1_S % BITS_PER_BYTE) +#define ICE_IMEM_ALU2_S 357 +#define ICE_IMEM_ALU2_IDD (ICE_IMEM_ALU2_S / BITS_PER_BYTE) +#define ICE_IMEM_ALU2_OFF (ICE_IMEM_ALU2_S % BITS_PER_BYTE) + +/** + * ice_imem_parse_item - parse 384 bits of IMEM entry + * @hw: pointer to the hardware structure + * @idx: index of IMEM entry + * @item: item of IMEM entry + * @data: IMEM entry data to be parsed + * @size: size of IMEM entry + */ +static void ice_imem_parse_item(struct ice_hw *hw, u16 idx, void *item, + void *data, int __maybe_unused size) +{ + struct ice_imem_item *ii = item; + u8 *buf = data; + + ii->idx = idx; + + ice_imem_bm_init(&ii->b_m, *(u8 *)buf); + ice_imem_bkb_init(&ii->b_kb, + *((u16 *)(&buf[ICE_IMEM_BKB_IDD])) >> + ICE_IMEM_BKB_OFF); + + ii->pg_prio = FIELD_GET(ICE_IMEM_PGP, *(u16 *)buf); + + ice_imem_npkb_init(&ii->np_kb, + *((u32 *)(&buf[ICE_IMEM_NPKB_IDD])) >> + ICE_IMEM_NPKB_OFF); + ice_imem_pgkb_init(&ii->pg_kb, + *((u64 *)(&buf[ICE_IMEM_PGKB_IDD])) >> + ICE_IMEM_PGKB_OFF); + + ice_imem_alu_init(&ii->alu0, + &buf[ICE_IMEM_ALU0_IDD], + ICE_IMEM_ALU0_OFF); + ice_imem_alu_init(&ii->alu1, + &buf[ICE_IMEM_ALU1_IDD], + ICE_IMEM_ALU1_OFF); + ice_imem_alu_init(&ii->alu2, + &buf[ICE_IMEM_ALU2_IDD], + ICE_IMEM_ALU2_OFF); + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_imem_dump(hw, ii); +} + +/** + * ice_imem_table_get - create an imem table + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated IMEM table. + */ +static struct ice_imem_item *ice_imem_table_get(struct ice_hw *hw) +{ + return ice_parser_create_table(hw, ICE_SID_RXPARSER_IMEM, + sizeof(struct ice_imem_item), + ICE_IMEM_TABLE_SIZE, + ice_imem_parse_item, false); +} + +/*** ICE_SID_RXPARSER_METADATA_INIT section ***/ +/** + * ice_metainit_dump - dump an metainit item info + * @hw: pointer to the hardware structure + * @item: metainit item to dump + */ +static void ice_metainit_dump(struct ice_hw *hw, struct ice_metainit_item *item) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "index = %d\n", item->idx); + + dev_info(dev, "tsr = %d\n", item->tsr); + dev_info(dev, "ho = %d\n", item->ho); + dev_info(dev, "pc = %d\n", item->pc); + dev_info(dev, "pg_rn = %d\n", item->pg_rn); + dev_info(dev, "cd = %d\n", item->cd); + + dev_info(dev, "gpr_a_ctrl = %d\n", item->gpr_a_ctrl); + dev_info(dev, "gpr_a_data_mdid = %d\n", item->gpr_a_data_mdid); + dev_info(dev, "gpr_a_data_start = %d\n", item->gpr_a_data_start); + dev_info(dev, "gpr_a_data_len = %d\n", item->gpr_a_data_len); + dev_info(dev, "gpr_a_id = %d\n", item->gpr_a_id); + + dev_info(dev, "gpr_b_ctrl = %d\n", item->gpr_b_ctrl); + dev_info(dev, "gpr_b_data_mdid = %d\n", item->gpr_b_data_mdid); + dev_info(dev, "gpr_b_data_start = %d\n", item->gpr_b_data_start); + dev_info(dev, "gpr_b_data_len = %d\n", item->gpr_b_data_len); + dev_info(dev, "gpr_b_id = %d\n", item->gpr_b_id); + + dev_info(dev, "gpr_c_ctrl = %d\n", item->gpr_c_ctrl); + dev_info(dev, "gpr_c_data_mdid = %d\n", item->gpr_c_data_mdid); + dev_info(dev, "gpr_c_data_start = %d\n", item->gpr_c_data_start); + dev_info(dev, "gpr_c_data_len = %d\n", item->gpr_c_data_len); + dev_info(dev, "gpr_c_id = %d\n", item->gpr_c_id); + + dev_info(dev, "gpr_d_ctrl = %d\n", item->gpr_d_ctrl); + dev_info(dev, "gpr_d_data_mdid = %d\n", item->gpr_d_data_mdid); + dev_info(dev, "gpr_d_data_start = %d\n", item->gpr_d_data_start); + dev_info(dev, "gpr_d_data_len = %d\n", item->gpr_d_data_len); + dev_info(dev, "gpr_d_id = %d\n", item->gpr_d_id); + + dev_info(dev, "flags = 0x%llx\n", (unsigned long long)(item->flags)); +} + +#define ICE_MI_TSR GENMASK_ULL(7, 0) +#define ICE_MI_HO GENMASK_ULL(16, 8) +#define ICE_MI_PC GENMASK_ULL(24, 17) +#define ICE_MI_PGRN GENMASK_ULL(35, 25) +#define ICE_MI_CD GENMASK_ULL(38, 36) +#define ICE_MI_GAC BIT_ULL(39) +#define ICE_MI_GADM GENMASK_ULL(44, 40) +#define ICE_MI_GADS GENMASK_ULL(48, 45) +#define ICE_MI_GADL GENMASK_ULL(53, 49) +#define ICE_MI_GAI GENMASK_ULL(59, 56) +#define ICE_MI_GBC BIT_ULL(60) +#define ICE_MI_GBDM_S 61 /* offset for the 2nd 64-bits field */ +#define ICE_MI_GBDM_IDD (ICE_MI_GBDM_S / BITS_PER_BYTE) +#define ICE_MI_GBDM_OFF (ICE_MI_GBDM_S % BITS_PER_BYTE) + +#define ICE_MI_GBDM_GENMASK_ULL(high, low) \ + GENMASK_ULL((high) - ICE_MI_GBDM_S, (low) - ICE_MI_GBDM_S) +#define ICE_MI_GBDM ICE_MI_GBDM_GENMASK_ULL(65, 61) +#define ICE_MI_GBDS ICE_MI_GBDM_GENMASK_ULL(69, 66) +#define ICE_MI_GBDL ICE_MI_GBDM_GENMASK_ULL(74, 70) +#define ICE_MI_GBI ICE_MI_GBDM_GENMASK_ULL(80, 77) +#define ICE_MI_GCC BIT_ULL(81 - ICE_MI_GBDM_S) +#define ICE_MI_GCDM ICE_MI_GBDM_GENMASK_ULL(86, 82) +#define ICE_MI_GCDS ICE_MI_GBDM_GENMASK_ULL(90, 87) +#define ICE_MI_GCDL ICE_MI_GBDM_GENMASK_ULL(95, 91) +#define ICE_MI_GCI ICE_MI_GBDM_GENMASK_ULL(101, 98) +#define ICE_MI_GDC BIT_ULL(102 - ICE_MI_GBDM_S) +#define ICE_MI_GDDM ICE_MI_GBDM_GENMASK_ULL(107, 103) +#define ICE_MI_GDDS ICE_MI_GBDM_GENMASK_ULL(111, 108) +#define ICE_MI_GDDL ICE_MI_GBDM_GENMASK_ULL(116, 112) +#define ICE_MI_GDI ICE_MI_GBDM_GENMASK_ULL(122, 119) +#define ICE_MI_FLAG_S 123 /* offset for the 3rd 64-bits field */ +#define ICE_MI_FLAG_IDD (ICE_MI_FLAG_S / BITS_PER_BYTE) +#define ICE_MI_FLAG_OFF (ICE_MI_FLAG_S % BITS_PER_BYTE) +#define ICE_MI_FLAG GENMASK_ULL(186 - ICE_MI_FLAG_S, \ + 123 - ICE_MI_FLAG_S) + +/** + * ice_metainit_parse_item - parse 192 bits of Metadata Init entry + * @hw: pointer to the hardware structure + * @idx: index of Metadata Init entry + * @item: item of Metadata Init entry + * @data: Metadata Init entry data to be parsed + * @size: size of Metadata Init entry + */ +static void ice_metainit_parse_item(struct ice_hw *hw, u16 idx, void *item, + void *data, int __maybe_unused size) +{ + struct ice_metainit_item *mi = item; + u8 *buf = data; + u64 d64; + + mi->idx = idx; + + d64 = *(u64 *)buf; + + mi->tsr = FIELD_GET(ICE_MI_TSR, d64); + mi->ho = FIELD_GET(ICE_MI_HO, d64); + mi->pc = FIELD_GET(ICE_MI_PC, d64); + mi->pg_rn = FIELD_GET(ICE_MI_PGRN, d64); + mi->cd = FIELD_GET(ICE_MI_CD, d64); + + mi->gpr_a_ctrl = FIELD_GET(ICE_MI_GAC, d64); + mi->gpr_a_data_mdid = FIELD_GET(ICE_MI_GADM, d64); + mi->gpr_a_data_start = FIELD_GET(ICE_MI_GADS, d64); + mi->gpr_a_data_len = FIELD_GET(ICE_MI_GADL, d64); + mi->gpr_a_id = FIELD_GET(ICE_MI_GAI, d64); + + mi->gpr_b_ctrl = FIELD_GET(ICE_MI_GBC, d64); + + d64 = *((u64 *)&buf[ICE_MI_GBDM_IDD]) >> ICE_MI_GBDM_OFF; + + mi->gpr_b_data_mdid = FIELD_GET(ICE_MI_GBDM, d64); + mi->gpr_b_data_start = FIELD_GET(ICE_MI_GBDS, d64); + mi->gpr_b_data_len = FIELD_GET(ICE_MI_GBDL, d64); + mi->gpr_b_id = FIELD_GET(ICE_MI_GBI, d64); + + mi->gpr_c_ctrl = FIELD_GET(ICE_MI_GCC, d64); + mi->gpr_c_data_mdid = FIELD_GET(ICE_MI_GCDM, d64); + mi->gpr_c_data_start = FIELD_GET(ICE_MI_GCDS, d64); + mi->gpr_c_data_len = FIELD_GET(ICE_MI_GCDL, d64); + mi->gpr_c_id = FIELD_GET(ICE_MI_GCI, d64); + + mi->gpr_d_ctrl = FIELD_GET(ICE_MI_GDC, d64); + mi->gpr_d_data_mdid = FIELD_GET(ICE_MI_GDDM, d64); + mi->gpr_d_data_start = FIELD_GET(ICE_MI_GDDS, d64); + mi->gpr_d_data_len = FIELD_GET(ICE_MI_GDDL, d64); + mi->gpr_d_id = FIELD_GET(ICE_MI_GDI, d64); + + d64 = *((u64 *)&buf[ICE_MI_FLAG_IDD]) >> ICE_MI_FLAG_OFF; + + mi->flags = FIELD_GET(ICE_MI_FLAG, d64); + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_metainit_dump(hw, mi); +} + +/** + * ice_metainit_table_get - create a metainit table + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Metadata initialization table. + */ +static struct ice_metainit_item *ice_metainit_table_get(struct ice_hw *hw) +{ + return ice_parser_create_table(hw, ICE_SID_RXPARSER_METADATA_INIT, + sizeof(struct ice_metainit_item), + ICE_METAINIT_TABLE_SIZE, + ice_metainit_parse_item, false); +} + +/** + * ice_bst_tcam_search - find a TCAM item with specific type + * @tcam_table: the TCAM table + * @lbl_table: the lbl table to search + * @type: the type we need to match against + * @start: start searching from this index + * + * Return: a pointer to the matching BOOST TCAM item or NULL. + */ +struct ice_bst_tcam_item * +ice_bst_tcam_search(struct ice_bst_tcam_item *tcam_table, + struct ice_lbl_item *lbl_table, + enum ice_lbl_type type, u16 *start) +{ + u16 i = *start; + + for (; i < ICE_BST_TCAM_TABLE_SIZE; i++) { + if (lbl_table[i].type == type) { + *start = i; + return &tcam_table[lbl_table[i].idx]; + } + } + + return NULL; +} + +/*** ICE_SID_RXPARSER_CAM, ICE_SID_RXPARSER_PG_SPILL, + * ICE_SID_RXPARSER_NOMATCH_CAM and ICE_SID_RXPARSER_NOMATCH_CAM + * sections ***/ +static void ice_pg_cam_key_dump(struct ice_hw *hw, struct ice_pg_cam_key *key) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "key:\n"); + dev_info(dev, "\tvalid = %d\n", key->valid); + dev_info(dev, "\tnode_id = %d\n", key->node_id); + dev_info(dev, "\tflag0 = %d\n", key->flag0); + dev_info(dev, "\tflag1 = %d\n", key->flag1); + dev_info(dev, "\tflag2 = %d\n", key->flag2); + dev_info(dev, "\tflag3 = %d\n", key->flag3); + dev_info(dev, "\tboost_idx = %d\n", key->boost_idx); + dev_info(dev, "\talu_reg = 0x%04x\n", key->alu_reg); + dev_info(dev, "\tnext_proto = 0x%08x\n", key->next_proto); +} + +static void ice_pg_nm_cam_key_dump(struct ice_hw *hw, + struct ice_pg_nm_cam_key *key) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "key:\n"); + dev_info(dev, "\tvalid = %d\n", key->valid); + dev_info(dev, "\tnode_id = %d\n", key->node_id); + dev_info(dev, "\tflag0 = %d\n", key->flag0); + dev_info(dev, "\tflag1 = %d\n", key->flag1); + dev_info(dev, "\tflag2 = %d\n", key->flag2); + dev_info(dev, "\tflag3 = %d\n", key->flag3); + dev_info(dev, "\tboost_idx = %d\n", key->boost_idx); + dev_info(dev, "\talu_reg = 0x%04x\n", key->alu_reg); +} + +static void ice_pg_cam_action_dump(struct ice_hw *hw, + struct ice_pg_cam_action *action) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "action:\n"); + dev_info(dev, "\tnext_node = %d\n", action->next_node); + dev_info(dev, "\tnext_pc = %d\n", action->next_pc); + dev_info(dev, "\tis_pg = %d\n", action->is_pg); + dev_info(dev, "\tproto_id = %d\n", action->proto_id); + dev_info(dev, "\tis_mg = %d\n", action->is_mg); + dev_info(dev, "\tmarker_id = %d\n", action->marker_id); + dev_info(dev, "\tis_last_round = %d\n", action->is_last_round); + dev_info(dev, "\tho_polarity = %d\n", action->ho_polarity); + dev_info(dev, "\tho_inc = %d\n", action->ho_inc); +} + +/** + * ice_pg_cam_dump - dump an parse graph cam info + * @hw: pointer to the hardware structure + * @item: parse graph cam to dump + */ +static void ice_pg_cam_dump(struct ice_hw *hw, struct ice_pg_cam_item *item) +{ + dev_info(ice_hw_to_dev(hw), "index = %d\n", item->idx); + ice_pg_cam_key_dump(hw, &item->key); + ice_pg_cam_action_dump(hw, &item->action); +} + +/** + * ice_pg_nm_cam_dump - dump an parse graph no match cam info + * @hw: pointer to the hardware structure + * @item: parse graph no match cam to dump + */ +static void ice_pg_nm_cam_dump(struct ice_hw *hw, + struct ice_pg_nm_cam_item *item) +{ + dev_info(ice_hw_to_dev(hw), "index = %d\n", item->idx); + ice_pg_nm_cam_key_dump(hw, &item->key); + ice_pg_cam_action_dump(hw, &item->action); +} + +#define ICE_PGCA_NN GENMASK_ULL(10, 0) +#define ICE_PGCA_NPC GENMASK_ULL(18, 11) +#define ICE_PGCA_IPG BIT_ULL(19) +#define ICE_PGCA_PID GENMASK_ULL(30, 23) +#define ICE_PGCA_IMG BIT_ULL(31) +#define ICE_PGCA_MID GENMASK_ULL(39, 32) +#define ICE_PGCA_ILR BIT_ULL(40) +#define ICE_PGCA_HOP BIT_ULL(41) +#define ICE_PGCA_HOI GENMASK_ULL(50, 42) + +/** + * ice_pg_cam_action_init - parse 55 bits of Parse Graph CAM Action + * @action: pointer to the Parse Graph CAM Action structure + * @data: Parse Graph CAM Action data to be parsed + */ +static void ice_pg_cam_action_init(struct ice_pg_cam_action *action, u64 data) +{ + action->next_node = FIELD_GET(ICE_PGCA_NN, data); + action->next_pc = FIELD_GET(ICE_PGCA_NPC, data); + action->is_pg = FIELD_GET(ICE_PGCA_IPG, data); + action->proto_id = FIELD_GET(ICE_PGCA_PID, data); + action->is_mg = FIELD_GET(ICE_PGCA_IMG, data); + action->marker_id = FIELD_GET(ICE_PGCA_MID, data); + action->is_last_round = FIELD_GET(ICE_PGCA_ILR, data); + action->ho_polarity = FIELD_GET(ICE_PGCA_HOP, data); + action->ho_inc = FIELD_GET(ICE_PGCA_HOI, data); +} + +#define ICE_PGNCK_VLD BIT_ULL(0) +#define ICE_PGNCK_NID GENMASK_ULL(11, 1) +#define ICE_PGNCK_F0 BIT_ULL(12) +#define ICE_PGNCK_F1 BIT_ULL(13) +#define ICE_PGNCK_F2 BIT_ULL(14) +#define ICE_PGNCK_F3 BIT_ULL(15) +#define ICE_PGNCK_BH BIT_ULL(16) +#define ICE_PGNCK_BI GENMASK_ULL(24, 17) +#define ICE_PGNCK_AR GENMASK_ULL(40, 25) + +/** + * ice_pg_nm_cam_key_init - parse 41 bits of Parse Graph NoMatch CAM Key + * @key: pointer to the Parse Graph NoMatch CAM Key structure + * @data: Parse Graph NoMatch CAM Key data to be parsed + */ +static void ice_pg_nm_cam_key_init(struct ice_pg_nm_cam_key *key, u64 data) +{ + key->valid = FIELD_GET(ICE_PGNCK_VLD, data); + key->node_id = FIELD_GET(ICE_PGNCK_NID, data); + key->flag0 = FIELD_GET(ICE_PGNCK_F0, data); + key->flag1 = FIELD_GET(ICE_PGNCK_F1, data); + key->flag2 = FIELD_GET(ICE_PGNCK_F2, data); + key->flag3 = FIELD_GET(ICE_PGNCK_F3, data); + + if (FIELD_GET(ICE_PGNCK_BH, data)) + key->boost_idx = FIELD_GET(ICE_PGNCK_BI, data); + else + key->boost_idx = 0; + + key->alu_reg = FIELD_GET(ICE_PGNCK_AR, data); +} + +#define ICE_PGCK_VLD BIT_ULL(0) +#define ICE_PGCK_NID GENMASK_ULL(11, 1) +#define ICE_PGCK_F0 BIT_ULL(12) +#define ICE_PGCK_F1 BIT_ULL(13) +#define ICE_PGCK_F2 BIT_ULL(14) +#define ICE_PGCK_F3 BIT_ULL(15) +#define ICE_PGCK_BH BIT_ULL(16) +#define ICE_PGCK_BI GENMASK_ULL(24, 17) +#define ICE_PGCK_AR GENMASK_ULL(40, 25) +#define ICE_PGCK_NPK_S 41 /* offset for the 2nd 64-bits field */ +#define ICE_PGCK_NPK_IDD (ICE_PGCK_NPK_S / BITS_PER_BYTE) +#define ICE_PGCK_NPK_OFF (ICE_PGCK_NPK_S % BITS_PER_BYTE) +#define ICE_PGCK_NPK GENMASK_ULL(72 - ICE_PGCK_NPK_S, \ + 41 - ICE_PGCK_NPK_S) + +/** + * ice_pg_cam_key_init - parse 73 bits of Parse Graph CAM Key + * @key: pointer to the Parse Graph CAM Key structure + * @data: Parse Graph CAM Key data to be parsed + */ +static void ice_pg_cam_key_init(struct ice_pg_cam_key *key, u8 *data) +{ + u64 d64 = *(u64 *)data; + + key->valid = FIELD_GET(ICE_PGCK_VLD, d64); + key->node_id = FIELD_GET(ICE_PGCK_NID, d64); + key->flag0 = FIELD_GET(ICE_PGCK_F0, d64); + key->flag1 = FIELD_GET(ICE_PGCK_F1, d64); + key->flag2 = FIELD_GET(ICE_PGCK_F2, d64); + key->flag3 = FIELD_GET(ICE_PGCK_F3, d64); + + if (FIELD_GET(ICE_PGCK_BH, d64)) + key->boost_idx = FIELD_GET(ICE_PGCK_BI, d64); + else + key->boost_idx = 0; + + key->alu_reg = FIELD_GET(ICE_PGCK_AR, d64); + + d64 = *((u64 *)&data[ICE_PGCK_NPK_IDD]) >> ICE_PGCK_NPK_OFF; + + key->next_proto = FIELD_GET(ICE_PGCK_NPK, d64); +} + +#define ICE_PG_CAM_ACT_S 73 +#define ICE_PG_CAM_ACT_IDD (ICE_PG_CAM_ACT_S / BITS_PER_BYTE) +#define ICE_PG_CAM_ACT_OFF (ICE_PG_CAM_ACT_S % BITS_PER_BYTE) + +/** + * ice_pg_cam_parse_item - parse 128 bits of Parse Graph CAM Entry + * @hw: pointer to the hardware structure + * @idx: index of Parse Graph CAM Entry + * @item: item of Parse Graph CAM Entry + * @data: Parse Graph CAM Entry data to be parsed + * @size: size of Parse Graph CAM Entry + */ +static void ice_pg_cam_parse_item(struct ice_hw *hw, u16 idx, void *item, + void *data, int __maybe_unused size) +{ + struct ice_pg_cam_item *ci = item; + u8 *buf = data; + u64 d64; + + ci->idx = idx; + + ice_pg_cam_key_init(&ci->key, buf); + + d64 = *((u64 *)&buf[ICE_PG_CAM_ACT_IDD]) >> ICE_PG_CAM_ACT_OFF; + ice_pg_cam_action_init(&ci->action, d64); + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_pg_cam_dump(hw, ci); +} + +#define ICE_PG_SP_CAM_KEY_S 56 +#define ICE_PG_SP_CAM_KEY_IDD (ICE_PG_SP_CAM_KEY_S / BITS_PER_BYTE) + +/** + * ice_pg_sp_cam_parse_item - parse 136 bits of Parse Graph Spill CAM Entry + * @hw: pointer to the hardware structure + * @idx: index of Parse Graph Spill CAM Entry + * @item: item of Parse Graph Spill CAM Entry + * @data: Parse Graph Spill CAM Entry data to be parsed + * @size: size of Parse Graph Spill CAM Entry + */ +static void ice_pg_sp_cam_parse_item(struct ice_hw *hw, u16 idx, void *item, + void *data, int __maybe_unused size) +{ + struct ice_pg_cam_item *ci = item; + u8 *buf = data; + u64 d64; + + ci->idx = idx; + + d64 = *(u64 *)buf; + ice_pg_cam_action_init(&ci->action, d64); + + ice_pg_cam_key_init(&ci->key, &buf[ICE_PG_SP_CAM_KEY_IDD]); + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_pg_cam_dump(hw, ci); +} + +#define ICE_PG_NM_CAM_ACT_S 41 +#define ICE_PG_NM_CAM_ACT_IDD (ICE_PG_NM_CAM_ACT_S / BITS_PER_BYTE) +#define ICE_PG_NM_CAM_ACT_OFF (ICE_PG_NM_CAM_ACT_S % BITS_PER_BYTE) + +/** + * ice_pg_nm_cam_parse_item - parse 96 bits of Parse Graph NoMatch CAM Entry + * @hw: pointer to the hardware structure + * @idx: index of Parse Graph NoMatch CAM Entry + * @item: item of Parse Graph NoMatch CAM Entry + * @data: Parse Graph NoMatch CAM Entry data to be parsed + * @size: size of Parse Graph NoMatch CAM Entry + */ +static void ice_pg_nm_cam_parse_item(struct ice_hw *hw, u16 idx, void *item, + void *data, int __maybe_unused size) +{ + struct ice_pg_nm_cam_item *ci = item; + u8 *buf = data; + u64 d64; + + ci->idx = idx; + + d64 = *(u64 *)buf; + ice_pg_nm_cam_key_init(&ci->key, d64); + + d64 = *((u64 *)&buf[ICE_PG_NM_CAM_ACT_IDD]) >> ICE_PG_NM_CAM_ACT_OFF; + ice_pg_cam_action_init(&ci->action, d64); + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_pg_nm_cam_dump(hw, ci); +} + +#define ICE_PG_NM_SP_CAM_ACT_S 56 +#define ICE_PG_NM_SP_CAM_ACT_IDD (ICE_PG_NM_SP_CAM_ACT_S / BITS_PER_BYTE) +#define ICE_PG_NM_SP_CAM_ACT_OFF (ICE_PG_NM_SP_CAM_ACT_S % BITS_PER_BYTE) + +/** + * ice_pg_nm_sp_cam_parse_item - parse 104 bits of Parse Graph NoMatch Spill + * CAM Entry + * @hw: pointer to the hardware structure + * @idx: index of Parse Graph NoMatch Spill CAM Entry + * @item: item of Parse Graph NoMatch Spill CAM Entry + * @data: Parse Graph NoMatch Spill CAM Entry data to be parsed + * @size: size of Parse Graph NoMatch Spill CAM Entry + */ +static void ice_pg_nm_sp_cam_parse_item(struct ice_hw *hw, u16 idx, + void *item, void *data, + int __maybe_unused size) +{ + struct ice_pg_nm_cam_item *ci = item; + u8 *buf = data; + u64 d64; + + ci->idx = idx; + + d64 = *(u64 *)buf; + ice_pg_cam_action_init(&ci->action, d64); + + d64 = *((u64 *)&buf[ICE_PG_NM_SP_CAM_ACT_IDD]) >> + ICE_PG_NM_SP_CAM_ACT_OFF; + ice_pg_nm_cam_key_init(&ci->key, d64); + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_pg_nm_cam_dump(hw, ci); +} + +/** + * ice_pg_cam_table_get - create a parse graph cam table + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Parse Graph CAM table. + */ +static struct ice_pg_cam_item *ice_pg_cam_table_get(struct ice_hw *hw) +{ + return ice_parser_create_table(hw, ICE_SID_RXPARSER_CAM, + sizeof(struct ice_pg_cam_item), + ICE_PG_CAM_TABLE_SIZE, + ice_pg_cam_parse_item, false); +} + +/** + * ice_pg_sp_cam_table_get - create a parse graph spill cam table + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Parse Graph Spill CAM table. + */ +static struct ice_pg_cam_item *ice_pg_sp_cam_table_get(struct ice_hw *hw) +{ + return ice_parser_create_table(hw, ICE_SID_RXPARSER_PG_SPILL, + sizeof(struct ice_pg_cam_item), + ICE_PG_SP_CAM_TABLE_SIZE, + ice_pg_sp_cam_parse_item, false); +} + +/** + * ice_pg_nm_cam_table_get - create a parse graph no match cam table + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Parse Graph No Match CAM table. + */ +static struct ice_pg_nm_cam_item *ice_pg_nm_cam_table_get(struct ice_hw *hw) +{ + return ice_parser_create_table(hw, ICE_SID_RXPARSER_NOMATCH_CAM, + sizeof(struct ice_pg_nm_cam_item), + ICE_PG_NM_CAM_TABLE_SIZE, + ice_pg_nm_cam_parse_item, false); +} + +/** + * ice_pg_nm_sp_cam_table_get - create a parse graph no match spill cam table + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Parse Graph No Match Spill CAM table. + */ +static struct ice_pg_nm_cam_item *ice_pg_nm_sp_cam_table_get(struct ice_hw *hw) +{ + return ice_parser_create_table(hw, ICE_SID_RXPARSER_NOMATCH_SPILL, + sizeof(struct ice_pg_nm_cam_item), + ICE_PG_NM_SP_CAM_TABLE_SIZE, + ice_pg_nm_sp_cam_parse_item, false); +} + +static bool __ice_pg_cam_match(struct ice_pg_cam_item *item, + struct ice_pg_cam_key *key) +{ + return (item->key.valid && + !memcmp(&item->key.val, &key->val, sizeof(key->val))); +} + +static bool __ice_pg_nm_cam_match(struct ice_pg_nm_cam_item *item, + struct ice_pg_cam_key *key) +{ + return (item->key.valid && + !memcmp(&item->key.val, &key->val, sizeof(item->key.val))); +} + +/** + * ice_pg_cam_match - search parse graph cam table by key + * @table: parse graph cam table to search + * @size: cam table size + * @key: search key + * + * Return: a pointer to the matching PG CAM item or NULL. + */ +struct ice_pg_cam_item *ice_pg_cam_match(struct ice_pg_cam_item *table, + int size, struct ice_pg_cam_key *key) +{ + int i; + + for (i = 0; i < size; i++) { + struct ice_pg_cam_item *item = &table[i]; + + if (__ice_pg_cam_match(item, key)) + return item; + } + + return NULL; +} + +/** + * ice_pg_nm_cam_match - search parse graph no match cam table by key + * @table: parse graph no match cam table to search + * @size: cam table size + * @key: search key + * + * Return: a pointer to the matching PG No Match CAM item or NULL. + */ +struct ice_pg_nm_cam_item * +ice_pg_nm_cam_match(struct ice_pg_nm_cam_item *table, int size, + struct ice_pg_cam_key *key) +{ + int i; + + for (i = 0; i < size; i++) { + struct ice_pg_nm_cam_item *item = &table[i]; + + if (__ice_pg_nm_cam_match(item, key)) + return item; + } + + return NULL; +} + +/*** Ternary match ***/ +/* Perform a ternary match on a 1-byte pattern (@pat) given @key and @key_inv + * Rules (per bit): + * Key == 0 and Key_inv == 0 : Never match (Don't care) + * Key == 0 and Key_inv == 1 : Match on bit == 1 + * Key == 1 and Key_inv == 0 : Match on bit == 0 + * Key == 1 and Key_inv == 1 : Always match (Don't care) + * + * Return: true if all bits match, false otherwise. + */ +static bool ice_ternary_match_byte(u8 key, u8 key_inv, u8 pat) +{ + u8 bit_key, bit_key_inv, bit_pat; + int i; + + for (i = 0; i < BITS_PER_BYTE; i++) { + bit_key = key & BIT(i); + bit_key_inv = key_inv & BIT(i); + bit_pat = pat & BIT(i); + + if (bit_key != 0 && bit_key_inv != 0) + continue; + + if ((bit_key == 0 && bit_key_inv == 0) || bit_key == bit_pat) + return false; + } + + return true; +} + +static bool ice_ternary_match(const u8 *key, const u8 *key_inv, + const u8 *pat, int len) +{ + int i; + + for (i = 0; i < len; i++) + if (!ice_ternary_match_byte(key[i], key_inv[i], pat[i])) + return false; + + return true; +} + +/*** ICE_SID_RXPARSER_BOOST_TCAM and ICE_SID_LBL_RXPARSER_TMEM sections ***/ +static void ice_bst_np_kb_dump(struct ice_hw *hw, struct ice_np_keybuilder *kb) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "next proto key builder:\n"); + dev_info(dev, "\topc = %d\n", kb->opc); + dev_info(dev, "\tstart_reg0 = %d\n", kb->start_reg0); + dev_info(dev, "\tlen_reg1 = %d\n", kb->len_reg1); +} + +static void ice_bst_pg_kb_dump(struct ice_hw *hw, struct ice_pg_keybuilder *kb) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "parse graph key builder:\n"); + dev_info(dev, "\tflag0_ena = %d\n", kb->flag0_ena); + dev_info(dev, "\tflag1_ena = %d\n", kb->flag1_ena); + dev_info(dev, "\tflag2_ena = %d\n", kb->flag2_ena); + dev_info(dev, "\tflag3_ena = %d\n", kb->flag3_ena); + dev_info(dev, "\tflag0_idx = %d\n", kb->flag0_idx); + dev_info(dev, "\tflag1_idx = %d\n", kb->flag1_idx); + dev_info(dev, "\tflag2_idx = %d\n", kb->flag2_idx); + dev_info(dev, "\tflag3_idx = %d\n", kb->flag3_idx); + dev_info(dev, "\talu_reg_idx = %d\n", kb->alu_reg_idx); +} + +static void ice_bst_alu_dump(struct ice_hw *hw, struct ice_alu *alu, int idx) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "alu%d:\n", idx); + dev_info(dev, "\topc = %d\n", alu->opc); + dev_info(dev, "\tsrc_start = %d\n", alu->src_start); + dev_info(dev, "\tsrc_len = %d\n", alu->src_len); + dev_info(dev, "\tshift_xlate_sel = %d\n", alu->shift_xlate_sel); + dev_info(dev, "\tshift_xlate_key = %d\n", alu->shift_xlate_key); + dev_info(dev, "\tsrc_reg_id = %d\n", alu->src_reg_id); + dev_info(dev, "\tdst_reg_id = %d\n", alu->dst_reg_id); + dev_info(dev, "\tinc0 = %d\n", alu->inc0); + dev_info(dev, "\tinc1 = %d\n", alu->inc1); + dev_info(dev, "\tproto_offset_opc = %d\n", alu->proto_offset_opc); + dev_info(dev, "\tproto_offset = %d\n", alu->proto_offset); + dev_info(dev, "\tbranch_addr = %d\n", alu->branch_addr); + dev_info(dev, "\timm = %d\n", alu->imm); + dev_info(dev, "\tdst_start = %d\n", alu->dst_start); + dev_info(dev, "\tdst_len = %d\n", alu->dst_len); + dev_info(dev, "\tflags_extr_imm = %d\n", alu->flags_extr_imm); + dev_info(dev, "\tflags_start_imm= %d\n", alu->flags_start_imm); +} + +/** + * ice_bst_tcam_dump - dump a boost tcam info + * @hw: pointer to the hardware structure + * @item: boost tcam to dump + */ +static void ice_bst_tcam_dump(struct ice_hw *hw, struct ice_bst_tcam_item *item) +{ + struct device *dev = ice_hw_to_dev(hw); + int i; + + dev_info(dev, "addr = %d\n", item->addr); + + dev_info(dev, "key : "); + for (i = 0; i < ICE_BST_TCAM_KEY_SIZE; i++) + dev_info(dev, "%02x ", item->key[i]); + + dev_info(dev, "\n"); + + dev_info(dev, "key_inv: "); + for (i = 0; i < ICE_BST_TCAM_KEY_SIZE; i++) + dev_info(dev, "%02x ", item->key_inv[i]); + + dev_info(dev, "\n"); + + dev_info(dev, "hit_idx_grp = %d\n", item->hit_idx_grp); + dev_info(dev, "pg_prio = %d\n", item->pg_prio); + + ice_bst_np_kb_dump(hw, &item->np_kb); + ice_bst_pg_kb_dump(hw, &item->pg_kb); + + ice_bst_alu_dump(hw, &item->alu0, ICE_ALU0_IDX); + ice_bst_alu_dump(hw, &item->alu1, ICE_ALU1_IDX); + ice_bst_alu_dump(hw, &item->alu2, ICE_ALU2_IDX); +} + +static void ice_lbl_dump(struct ice_hw *hw, struct ice_lbl_item *item) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "index = %u\n", item->idx); + dev_info(dev, "type = %u\n", item->type); + dev_info(dev, "label = %s\n", item->label); +} + +#define ICE_BST_ALU_OPC GENMASK_ULL(5, 0) +#define ICE_BST_ALU_SS GENMASK_ULL(13, 6) +#define ICE_BST_ALU_SL GENMASK_ULL(18, 14) +#define ICE_BST_ALU_SXS BIT_ULL(19) +#define ICE_BST_ALU_SXK GENMASK_ULL(23, 20) +#define ICE_BST_ALU_SRID GENMASK_ULL(30, 24) +#define ICE_BST_ALU_DRID GENMASK_ULL(37, 31) +#define ICE_BST_ALU_INC0 BIT_ULL(38) +#define ICE_BST_ALU_INC1 BIT_ULL(39) +#define ICE_BST_ALU_POO GENMASK_ULL(41, 40) +#define ICE_BST_ALU_PO GENMASK_ULL(49, 42) +#define ICE_BST_ALU_BA_S 50 /* offset for the 2nd 64-bits field */ +#define ICE_BST_ALU_BA GENMASK_ULL(57 - ICE_BST_ALU_BA_S, \ + 50 - ICE_BST_ALU_BA_S) +#define ICE_BST_ALU_IMM GENMASK_ULL(73 - ICE_BST_ALU_BA_S, \ + 58 - ICE_BST_ALU_BA_S) +#define ICE_BST_ALU_DFE BIT_ULL(74 - ICE_BST_ALU_BA_S) +#define ICE_BST_ALU_DS GENMASK_ULL(80 - ICE_BST_ALU_BA_S, \ + 75 - ICE_BST_ALU_BA_S) +#define ICE_BST_ALU_DL GENMASK_ULL(86 - ICE_BST_ALU_BA_S, \ + 81 - ICE_BST_ALU_BA_S) +#define ICE_BST_ALU_FEI BIT_ULL(87 - ICE_BST_ALU_BA_S) +#define ICE_BST_ALU_FSI GENMASK_ULL(95 - ICE_BST_ALU_BA_S, \ + 88 - ICE_BST_ALU_BA_S) + +/** + * ice_bst_alu_init - parse 96 bits of ALU entry + * @alu: pointer to the ALU entry structure + * @data: ALU entry data to be parsed + * @off: offset of the ALU entry data + */ +static void ice_bst_alu_init(struct ice_alu *alu, u8 *data, u8 off) +{ + u64 d64; + u8 idd; + + d64 = *((u64 *)data) >> off; + + alu->opc = FIELD_GET(ICE_BST_ALU_OPC, d64); + alu->src_start = FIELD_GET(ICE_BST_ALU_SS, d64); + alu->src_len = FIELD_GET(ICE_BST_ALU_SL, d64); + alu->shift_xlate_sel = FIELD_GET(ICE_BST_ALU_SXS, d64); + alu->shift_xlate_key = FIELD_GET(ICE_BST_ALU_SXK, d64); + alu->src_reg_id = FIELD_GET(ICE_BST_ALU_SRID, d64); + alu->dst_reg_id = FIELD_GET(ICE_BST_ALU_DRID, d64); + alu->inc0 = FIELD_GET(ICE_BST_ALU_INC0, d64); + alu->inc1 = FIELD_GET(ICE_BST_ALU_INC1, d64); + alu->proto_offset_opc = FIELD_GET(ICE_BST_ALU_POO, d64); + alu->proto_offset = FIELD_GET(ICE_BST_ALU_PO, d64); + + idd = (ICE_BST_ALU_BA_S + off) / BITS_PER_BYTE; + off = (ICE_BST_ALU_BA_S + off) % BITS_PER_BYTE; + d64 = *((u64 *)(&data[idd])) >> off; + + alu->branch_addr = FIELD_GET(ICE_BST_ALU_BA, d64); + alu->imm = FIELD_GET(ICE_BST_ALU_IMM, d64); + alu->dedicate_flags_ena = FIELD_GET(ICE_BST_ALU_DFE, d64); + alu->dst_start = FIELD_GET(ICE_BST_ALU_DS, d64); + alu->dst_len = FIELD_GET(ICE_BST_ALU_DL, d64); + alu->flags_extr_imm = FIELD_GET(ICE_BST_ALU_FEI, d64); + alu->flags_start_imm = FIELD_GET(ICE_BST_ALU_FSI, d64); +} + +#define ICE_BST_PGKB_F0_ENA BIT_ULL(0) +#define ICE_BST_PGKB_F0_IDX GENMASK_ULL(6, 1) +#define ICE_BST_PGKB_F1_ENA BIT_ULL(7) +#define ICE_BST_PGKB_F1_IDX GENMASK_ULL(13, 8) +#define ICE_BST_PGKB_F2_ENA BIT_ULL(14) +#define ICE_BST_PGKB_F2_IDX GENMASK_ULL(20, 15) +#define ICE_BST_PGKB_F3_ENA BIT_ULL(21) +#define ICE_BST_PGKB_F3_IDX GENMASK_ULL(27, 22) +#define ICE_BST_PGKB_AR_IDX GENMASK_ULL(34, 28) + +/** + * ice_bst_pgkb_init - parse 35 bits of Parse Graph Key Build + * @kb: pointer to the Parse Graph Key Build structure + * @data: Parse Graph Key Build data to be parsed + */ +static void ice_bst_pgkb_init(struct ice_pg_keybuilder *kb, u64 data) +{ + kb->flag0_ena = FIELD_GET(ICE_BST_PGKB_F0_ENA, data); + kb->flag0_idx = FIELD_GET(ICE_BST_PGKB_F0_IDX, data); + kb->flag1_ena = FIELD_GET(ICE_BST_PGKB_F1_ENA, data); + kb->flag1_idx = FIELD_GET(ICE_BST_PGKB_F1_IDX, data); + kb->flag2_ena = FIELD_GET(ICE_BST_PGKB_F2_ENA, data); + kb->flag2_idx = FIELD_GET(ICE_BST_PGKB_F2_IDX, data); + kb->flag3_ena = FIELD_GET(ICE_BST_PGKB_F3_ENA, data); + kb->flag3_idx = FIELD_GET(ICE_BST_PGKB_F3_IDX, data); + kb->alu_reg_idx = FIELD_GET(ICE_BST_PGKB_AR_IDX, data); +} + +#define ICE_BST_NPKB_OPC GENMASK(1, 0) +#define ICE_BST_NPKB_S_R0 GENMASK(9, 2) +#define ICE_BST_NPKB_L_R1 GENMASK(17, 10) + +/** + * ice_bst_npkb_init - parse 18 bits of Next Protocol Key Build + * @kb: pointer to the Next Protocol Key Build structure + * @data: Next Protocol Key Build data to be parsed + */ +static void ice_bst_npkb_init(struct ice_np_keybuilder *kb, u32 data) +{ + kb->opc = FIELD_GET(ICE_BST_NPKB_OPC, data); + kb->start_reg0 = FIELD_GET(ICE_BST_NPKB_S_R0, data); + kb->len_reg1 = FIELD_GET(ICE_BST_NPKB_L_R1, data); +} + +#define ICE_BT_KEY_S 32 +#define ICE_BT_KEY_IDD (ICE_BT_KEY_S / BITS_PER_BYTE) +#define ICE_BT_KIV_S 192 +#define ICE_BT_KIV_IDD (ICE_BT_KIV_S / BITS_PER_BYTE) +#define ICE_BT_HIG_S 352 +#define ICE_BT_HIG_IDD (ICE_BT_HIG_S / BITS_PER_BYTE) +#define ICE_BT_PGP_S 360 +#define ICE_BT_PGP_IDD (ICE_BT_PGP_S / BITS_PER_BYTE) +#define ICE_BT_PGP_M GENMASK(361 - ICE_BT_PGP_S, 360 - ICE_BT_PGP_S) +#define ICE_BT_NPKB_S 362 +#define ICE_BT_NPKB_IDD (ICE_BT_NPKB_S / BITS_PER_BYTE) +#define ICE_BT_NPKB_OFF (ICE_BT_NPKB_S % BITS_PER_BYTE) +#define ICE_BT_PGKB_S 380 +#define ICE_BT_PGKB_IDD (ICE_BT_PGKB_S / BITS_PER_BYTE) +#define ICE_BT_PGKB_OFF (ICE_BT_PGKB_S % BITS_PER_BYTE) +#define ICE_BT_ALU0_S 415 +#define ICE_BT_ALU0_IDD (ICE_BT_ALU0_S / BITS_PER_BYTE) +#define ICE_BT_ALU0_OFF (ICE_BT_ALU0_S % BITS_PER_BYTE) +#define ICE_BT_ALU1_S 511 +#define ICE_BT_ALU1_IDD (ICE_BT_ALU1_S / BITS_PER_BYTE) +#define ICE_BT_ALU1_OFF (ICE_BT_ALU1_S % BITS_PER_BYTE) +#define ICE_BT_ALU2_S 607 +#define ICE_BT_ALU2_IDD (ICE_BT_ALU2_S / BITS_PER_BYTE) +#define ICE_BT_ALU2_OFF (ICE_BT_ALU2_S % BITS_PER_BYTE) + +/** + * ice_bst_parse_item - parse 704 bits of Boost TCAM entry + * @hw: pointer to the hardware structure + * @idx: index of Boost TCAM entry + * @item: item of Boost TCAM entry + * @data: Boost TCAM entry data to be parsed + * @size: size of Boost TCAM entry + */ +static void ice_bst_parse_item(struct ice_hw *hw, u16 idx, void *item, + void *data, int __maybe_unused size) +{ + struct ice_bst_tcam_item *ti = item; + u8 *buf = (u8 *)data; + int i; + + ti->addr = *(u16 *)buf; + + for (i = 0; i < ICE_BST_TCAM_KEY_SIZE; i++) { + ti->key[i] = buf[ICE_BT_KEY_IDD + i]; + ti->key_inv[i] = buf[ICE_BT_KIV_IDD + i]; + } + ti->hit_idx_grp = buf[ICE_BT_HIG_IDD]; + ti->pg_prio = buf[ICE_BT_PGP_IDD] & ICE_BT_PGP_M; + + ice_bst_npkb_init(&ti->np_kb, + *((u32 *)(&buf[ICE_BT_NPKB_IDD])) >> + ICE_BT_NPKB_OFF); + ice_bst_pgkb_init(&ti->pg_kb, + *((u64 *)(&buf[ICE_BT_PGKB_IDD])) >> + ICE_BT_PGKB_OFF); + + ice_bst_alu_init(&ti->alu0, &buf[ICE_BT_ALU0_IDD], ICE_BT_ALU0_OFF); + ice_bst_alu_init(&ti->alu1, &buf[ICE_BT_ALU1_IDD], ICE_BT_ALU1_OFF); + ice_bst_alu_init(&ti->alu2, &buf[ICE_BT_ALU2_IDD], ICE_BT_ALU2_OFF); + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_bst_tcam_dump(hw, ti); +} + +/** + * ice_bst_tcam_table_get - create a boost tcam table + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Boost TCAM table. + */ +static struct ice_bst_tcam_item *ice_bst_tcam_table_get(struct ice_hw *hw) +{ + return ice_parser_create_table(hw, ICE_SID_RXPARSER_BOOST_TCAM, + sizeof(struct ice_bst_tcam_item), + ICE_BST_TCAM_TABLE_SIZE, + ice_bst_parse_item, true); +} + +static void ice_parse_lbl_item(struct ice_hw *hw, u16 idx, void *item, + void *data, int __maybe_unused size) +{ + struct ice_lbl_item *lbl_item = item; + struct ice_lbl_item *lbl_data = data; + + lbl_item->idx = lbl_data->idx; + memcpy(lbl_item->label, lbl_data->label, sizeof(lbl_item->label)); + + if (strstarts(lbl_item->label, ICE_LBL_BST_DVM)) + lbl_item->type = ICE_LBL_BST_TYPE_DVM; + else if (strstarts(lbl_item->label, ICE_LBL_BST_SVM)) + lbl_item->type = ICE_LBL_BST_TYPE_SVM; + else if (strstarts(lbl_item->label, ICE_LBL_TNL_VXLAN)) + lbl_item->type = ICE_LBL_BST_TYPE_VXLAN; + else if (strstarts(lbl_item->label, ICE_LBL_TNL_GENEVE)) + lbl_item->type = ICE_LBL_BST_TYPE_GENEVE; + else if (strstarts(lbl_item->label, ICE_LBL_TNL_UDP_ECPRI)) + lbl_item->type = ICE_LBL_BST_TYPE_UDP_ECPRI; + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_lbl_dump(hw, lbl_item); +} + +/** + * ice_bst_lbl_table_get - create a boost label table + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Boost label table. + */ +static struct ice_lbl_item *ice_bst_lbl_table_get(struct ice_hw *hw) +{ + return ice_parser_create_table(hw, ICE_SID_LBL_RXPARSER_TMEM, + sizeof(struct ice_lbl_item), + ICE_BST_TCAM_TABLE_SIZE, + ice_parse_lbl_item, true); +} + +/** + * ice_bst_tcam_match - match a pattern on the boost tcam table + * @tcam_table: boost tcam table to search + * @pat: pattern to match + * + * Return: a pointer to the matching Boost TCAM item or NULL. + */ +struct ice_bst_tcam_item * +ice_bst_tcam_match(struct ice_bst_tcam_item *tcam_table, u8 *pat) +{ + int i; + + for (i = 0; i < ICE_BST_TCAM_TABLE_SIZE; i++) { + struct ice_bst_tcam_item *item = &tcam_table[i]; + + if (item->hit_idx_grp == 0) + continue; + if (ice_ternary_match(item->key, item->key_inv, pat, + ICE_BST_TCAM_KEY_SIZE)) + return item; + } + + return NULL; +} + +/*** ICE_SID_RXPARSER_MARKER_PTYPE section ***/ +/** + * ice_ptype_mk_tcam_dump - dump an ptype marker tcam info + * @hw: pointer to the hardware structure + * @item: ptype marker tcam to dump + */ +static void ice_ptype_mk_tcam_dump(struct ice_hw *hw, + struct ice_ptype_mk_tcam_item *item) +{ + struct device *dev = ice_hw_to_dev(hw); + int i; + + dev_info(dev, "address = %d\n", item->address); + dev_info(dev, "ptype = %d\n", item->ptype); + + dev_info(dev, "key :"); + for (i = 0; i < ICE_PTYPE_MK_TCAM_KEY_SIZE; i++) + dev_info(dev, "%02x ", item->key[i]); + + dev_info(dev, "\n"); + + dev_info(dev, "key_inv:"); + for (i = 0; i < ICE_PTYPE_MK_TCAM_KEY_SIZE; i++) + dev_info(dev, "%02x ", item->key_inv[i]); + + dev_info(dev, "\n"); +} + +static void ice_parse_ptype_mk_tcam_item(struct ice_hw *hw, u16 idx, + void *item, void *data, int size) +{ + memcpy(item, data, size); + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_ptype_mk_tcam_dump(hw, + (struct ice_ptype_mk_tcam_item *)item); +} + +/** + * ice_ptype_mk_tcam_table_get - create a ptype marker tcam table + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Marker PType TCAM table. + */ +static +struct ice_ptype_mk_tcam_item *ice_ptype_mk_tcam_table_get(struct ice_hw *hw) +{ + return ice_parser_create_table(hw, ICE_SID_RXPARSER_MARKER_PTYPE, + sizeof(struct ice_ptype_mk_tcam_item), + ICE_PTYPE_MK_TCAM_TABLE_SIZE, + ice_parse_ptype_mk_tcam_item, true); +} + +/** + * ice_ptype_mk_tcam_match - match a pattern on a ptype marker tcam table + * @table: ptype marker tcam table to search + * @pat: pattern to match + * @len: length of the pattern + * + * Return: a pointer to the matching Marker PType item or NULL. + */ +struct ice_ptype_mk_tcam_item * +ice_ptype_mk_tcam_match(struct ice_ptype_mk_tcam_item *table, + u8 *pat, int len) +{ + int i; + + for (i = 0; i < ICE_PTYPE_MK_TCAM_TABLE_SIZE; i++) { + struct ice_ptype_mk_tcam_item *item = &table[i]; + + if (ice_ternary_match(item->key, item->key_inv, pat, len)) + return item; + } + + return NULL; +} + +/*** ICE_SID_RXPARSER_MARKER_GRP section ***/ +/** + * ice_mk_grp_dump - dump an marker group item info + * @hw: pointer to the hardware structure + * @item: marker group item to dump + */ +static void ice_mk_grp_dump(struct ice_hw *hw, struct ice_mk_grp_item *item) +{ + struct device *dev = ice_hw_to_dev(hw); + int i; + + dev_info(dev, "index = %d\n", item->idx); + + dev_info(dev, "markers: "); + for (i = 0; i < ICE_MK_COUNT_PER_GRP; i++) + dev_info(dev, "%d ", item->markers[i]); + + dev_info(dev, "\n"); +} + +static void ice_mk_grp_parse_item(struct ice_hw *hw, u16 idx, void *item, + void *data, int __maybe_unused size) +{ + struct ice_mk_grp_item *grp = item; + u8 *buf = data; + int i; + + grp->idx = idx; + + for (i = 0; i < ICE_MK_COUNT_PER_GRP; i++) + grp->markers[i] = buf[i]; + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_mk_grp_dump(hw, grp); +} + +/** + * ice_mk_grp_table_get - create a marker group table + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Marker Group ID table. + */ +static struct ice_mk_grp_item *ice_mk_grp_table_get(struct ice_hw *hw) +{ + return ice_parser_create_table(hw, ICE_SID_RXPARSER_MARKER_GRP, + sizeof(struct ice_mk_grp_item), + ICE_MK_GRP_TABLE_SIZE, + ice_mk_grp_parse_item, false); +} + +/*** ICE_SID_RXPARSER_PROTO_GRP section ***/ +static void ice_proto_off_dump(struct ice_hw *hw, + struct ice_proto_off *po, int idx) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "proto %d\n", idx); + dev_info(dev, "\tpolarity = %d\n", po->polarity); + dev_info(dev, "\tproto_id = %d\n", po->proto_id); + dev_info(dev, "\toffset = %d\n", po->offset); +} + +/** + * ice_proto_grp_dump - dump a proto group item info + * @hw: pointer to the hardware structure + * @item: proto group item to dump + */ +static void ice_proto_grp_dump(struct ice_hw *hw, + struct ice_proto_grp_item *item) +{ + int i; + + dev_info(ice_hw_to_dev(hw), "index = %d\n", item->idx); + + for (i = 0; i < ICE_PROTO_COUNT_PER_GRP; i++) + ice_proto_off_dump(hw, &item->po[i], i); +} + +#define ICE_PO_POL BIT(0) +#define ICE_PO_PID GENMASK(8, 1) +#define ICE_PO_OFF GENMASK(21, 12) + +/** + * ice_proto_off_parse - parse 22 bits of Protocol entry + * @po: pointer to the Protocol entry structure + * @data: Protocol entry data to be parsed + */ +static void ice_proto_off_parse(struct ice_proto_off *po, u32 data) +{ + po->polarity = FIELD_GET(ICE_PO_POL, data); + po->proto_id = FIELD_GET(ICE_PO_PID, data); + po->offset = FIELD_GET(ICE_PO_OFF, data); +} + +/** + * ice_proto_grp_parse_item - parse 192 bits of Protocol Group Table entry + * @hw: pointer to the hardware structure + * @idx: index of Protocol Group Table entry + * @item: item of Protocol Group Table entry + * @data: Protocol Group Table entry data to be parsed + * @size: size of Protocol Group Table entry + */ +static void ice_proto_grp_parse_item(struct ice_hw *hw, u16 idx, void *item, + void *data, int __maybe_unused size) +{ + struct ice_proto_grp_item *grp = item; + u8 *buf = (u8 *)data; + u8 idd, off; + u32 d32; + int i; + + grp->idx = idx; + + for (i = 0; i < ICE_PROTO_COUNT_PER_GRP; i++) { + idd = (ICE_PROTO_GRP_ITEM_SIZE * i) / BITS_PER_BYTE; + off = (ICE_PROTO_GRP_ITEM_SIZE * i) % BITS_PER_BYTE; + d32 = *((u32 *)&buf[idd]) >> off; + ice_proto_off_parse(&grp->po[i], d32); + } + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_proto_grp_dump(hw, grp); +} + +/** + * ice_proto_grp_table_get - create a proto group table + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Protocol Group table. + */ +static struct ice_proto_grp_item *ice_proto_grp_table_get(struct ice_hw *hw) +{ + return ice_parser_create_table(hw, ICE_SID_RXPARSER_PROTO_GRP, + sizeof(struct ice_proto_grp_item), + ICE_PROTO_GRP_TABLE_SIZE, + ice_proto_grp_parse_item, false); +} + +/*** ICE_SID_RXPARSER_FLAG_REDIR section ***/ +/** + * ice_flg_rd_dump - dump a flag redirect item info + * @hw: pointer to the hardware structure + * @item: flag redirect item to dump + */ +static void ice_flg_rd_dump(struct ice_hw *hw, struct ice_flg_rd_item *item) +{ + struct device *dev = ice_hw_to_dev(hw); + + dev_info(dev, "index = %d\n", item->idx); + dev_info(dev, "expose = %d\n", item->expose); + dev_info(dev, "intr_flg_id = %d\n", item->intr_flg_id); +} + +#define ICE_FRT_EXPO BIT(0) +#define ICE_FRT_IFID GENMASK(6, 1) + +/** + * ice_flg_rd_parse_item - parse 8 bits of Flag Redirect Table entry + * @hw: pointer to the hardware structure + * @idx: index of Flag Redirect Table entry + * @item: item of Flag Redirect Table entry + * @data: Flag Redirect Table entry data to be parsed + * @size: size of Flag Redirect Table entry + */ +static void ice_flg_rd_parse_item(struct ice_hw *hw, u16 idx, void *item, + void *data, int __maybe_unused size) +{ + struct ice_flg_rd_item *rdi = item; + u8 d8 = *(u8 *)data; + + rdi->idx = idx; + rdi->expose = FIELD_GET(ICE_FRT_EXPO, d8); + rdi->intr_flg_id = FIELD_GET(ICE_FRT_IFID, d8); + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_flg_rd_dump(hw, rdi); +} + +/** + * ice_flg_rd_table_get - create a flag redirect table + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Flags Redirection table. + */ +static struct ice_flg_rd_item *ice_flg_rd_table_get(struct ice_hw *hw) +{ + return ice_parser_create_table(hw, ICE_SID_RXPARSER_FLAG_REDIR, + sizeof(struct ice_flg_rd_item), + ICE_FLG_RD_TABLE_SIZE, + ice_flg_rd_parse_item, false); +} + +/** + * ice_flg_redirect - redirect a parser flag to packet flag + * @table: flag redirect table + * @psr_flg: parser flag to redirect + * + * Return: flag or 0 if @psr_flag = 0. + */ +u64 ice_flg_redirect(struct ice_flg_rd_item *table, u64 psr_flg) +{ + u64 flg = 0; + int i; + + for (i = 0; i < ICE_FLG_RDT_SIZE; i++) { + struct ice_flg_rd_item *item = &table[i]; + + if (!item->expose) + continue; + + if (psr_flg & BIT(item->intr_flg_id)) + flg |= BIT(i); + } + + return flg; +} + +/*** ICE_SID_XLT_KEY_BUILDER_SW, ICE_SID_XLT_KEY_BUILDER_ACL, + * ICE_SID_XLT_KEY_BUILDER_FD and ICE_SID_XLT_KEY_BUILDER_RSS + * sections ***/ +static void ice_xlt_kb_entry_dump(struct ice_hw *hw, + struct ice_xlt_kb_entry *entry, int idx) +{ + struct device *dev = ice_hw_to_dev(hw); + int i; + + dev_info(dev, "key builder entry %d\n", idx); + dev_info(dev, "\txlt1_ad_sel = %d\n", entry->xlt1_ad_sel); + dev_info(dev, "\txlt2_ad_sel = %d\n", entry->xlt2_ad_sel); + + for (i = 0; i < ICE_XLT_KB_FLAG0_14_CNT; i++) + dev_info(dev, "\tflg%d_sel = %d\n", i, entry->flg0_14_sel[i]); + + dev_info(dev, "\txlt1_md_sel = %d\n", entry->xlt1_md_sel); + dev_info(dev, "\txlt2_md_sel = %d\n", entry->xlt2_md_sel); +} + +/** + * ice_xlt_kb_dump - dump a xlt key build info + * @hw: pointer to the hardware structure + * @kb: key build to dump + */ +static void ice_xlt_kb_dump(struct ice_hw *hw, struct ice_xlt_kb *kb) +{ + struct device *dev = ice_hw_to_dev(hw); + int i; + + dev_info(dev, "xlt1_pm = %d\n", kb->xlt1_pm); + dev_info(dev, "xlt2_pm = %d\n", kb->xlt2_pm); + dev_info(dev, "prof_id_pm = %d\n", kb->prof_id_pm); + dev_info(dev, "flag15 lo = 0x%08x\n", (u32)kb->flag15); + dev_info(dev, "flag15 hi = 0x%08x\n", + (u32)(kb->flag15 >> (sizeof(u32) * BITS_PER_BYTE))); + + for (i = 0; i < ICE_XLT_KB_TBL_CNT; i++) + ice_xlt_kb_entry_dump(hw, &kb->entries[i], i); +} + +#define ICE_XLT_KB_X1AS_S 32 /* offset for the 1st 64-bits field */ +#define ICE_XLT_KB_X1AS_IDD (ICE_XLT_KB_X1AS_S / BITS_PER_BYTE) +#define ICE_XLT_KB_X1AS_OFF (ICE_XLT_KB_X1AS_S % BITS_PER_BYTE) +#define ICE_XLT_KB_X1AS GENMASK_ULL(34 - ICE_XLT_KB_X1AS_S, \ + 32 - ICE_XLT_KB_X1AS_S) +#define ICE_XLT_KB_X2AS GENMASK_ULL(37 - ICE_XLT_KB_X1AS_S, \ + 35 - ICE_XLT_KB_X1AS_S) +#define ICE_XLT_KB_FL00 GENMASK_ULL(46 - ICE_XLT_KB_X1AS_S, \ + 38 - ICE_XLT_KB_X1AS_S) +#define ICE_XLT_KB_FL01 GENMASK_ULL(55 - ICE_XLT_KB_X1AS_S, \ + 47 - ICE_XLT_KB_X1AS_S) +#define ICE_XLT_KB_FL02 GENMASK_ULL(64 - ICE_XLT_KB_X1AS_S, \ + 56 - ICE_XLT_KB_X1AS_S) +#define ICE_XLT_KB_FL03 GENMASK_ULL(73 - ICE_XLT_KB_X1AS_S, \ + 65 - ICE_XLT_KB_X1AS_S) +#define ICE_XLT_KB_FL04 GENMASK_ULL(82 - ICE_XLT_KB_X1AS_S, \ + 74 - ICE_XLT_KB_X1AS_S) +#define ICE_XLT_KB_FL05 GENMASK_ULL(91 - ICE_XLT_KB_X1AS_S, \ + 83 - ICE_XLT_KB_X1AS_S) +#define ICE_XLT_KB_FL06_S 92 /* offset for the 2nd 64-bits field */ +#define ICE_XLT_KB_FL06_IDD (ICE_XLT_KB_FL06_S / BITS_PER_BYTE) +#define ICE_XLT_KB_FL06_OFF (ICE_XLT_KB_FL06_S % BITS_PER_BYTE) +#define ICE_XLT_KB_FL06 GENMASK_ULL(100 - ICE_XLT_KB_FL06_S, \ + 92 - ICE_XLT_KB_FL06_S) +#define ICE_XLT_KB_FL07 GENMASK_ULL(109 - ICE_XLT_KB_FL06_S, \ + 101 - ICE_XLT_KB_FL06_S) +#define ICE_XLT_KB_FL08 GENMASK_ULL(118 - ICE_XLT_KB_FL06_S, \ + 110 - ICE_XLT_KB_FL06_S) +#define ICE_XLT_KB_FL09 GENMASK_ULL(127 - ICE_XLT_KB_FL06_S, \ + 119 - ICE_XLT_KB_FL06_S) +#define ICE_XLT_KB_FL10 GENMASK_ULL(136 - ICE_XLT_KB_FL06_S, \ + 128 - ICE_XLT_KB_FL06_S) +#define ICE_XLT_KB_FL11 GENMASK_ULL(145 - ICE_XLT_KB_FL06_S, \ + 137 - ICE_XLT_KB_FL06_S) +#define ICE_XLT_KB_FL12_S 146 /* offset for the 3rd 64-bits field */ +#define ICE_XLT_KB_FL12_IDD (ICE_XLT_KB_FL12_S / BITS_PER_BYTE) +#define ICE_XLT_KB_FL12_OFF (ICE_XLT_KB_FL12_S % BITS_PER_BYTE) +#define ICE_XLT_KB_FL12 GENMASK_ULL(154 - ICE_XLT_KB_FL12_S, \ + 146 - ICE_XLT_KB_FL12_S) +#define ICE_XLT_KB_FL13 GENMASK_ULL(163 - ICE_XLT_KB_FL12_S, \ + 155 - ICE_XLT_KB_FL12_S) +#define ICE_XLT_KB_FL14 GENMASK_ULL(181 - ICE_XLT_KB_FL12_S, \ + 164 - ICE_XLT_KB_FL12_S) +#define ICE_XLT_KB_X1MS GENMASK_ULL(186 - ICE_XLT_KB_FL12_S, \ + 182 - ICE_XLT_KB_FL12_S) +#define ICE_XLT_KB_X2MS GENMASK_ULL(191 - ICE_XLT_KB_FL12_S, \ + 187 - ICE_XLT_KB_FL12_S) + +/** + * ice_kb_entry_init - parse 192 bits of XLT Key Builder entry + * @entry: pointer to the XLT Key Builder entry structure + * @data: XLT Key Builder entry data to be parsed + */ +static void ice_kb_entry_init(struct ice_xlt_kb_entry *entry, u8 *data) +{ + u8 i = 0; + u64 d64; + + d64 = *((u64 *)&data[ICE_XLT_KB_X1AS_IDD]) >> ICE_XLT_KB_X1AS_OFF; + + entry->xlt1_ad_sel = FIELD_GET(ICE_XLT_KB_X1AS, d64); + entry->xlt2_ad_sel = FIELD_GET(ICE_XLT_KB_X2AS, d64); + + entry->flg0_14_sel[i++] = FIELD_GET(ICE_XLT_KB_FL00, d64); + entry->flg0_14_sel[i++] = FIELD_GET(ICE_XLT_KB_FL01, d64); + entry->flg0_14_sel[i++] = FIELD_GET(ICE_XLT_KB_FL02, d64); + entry->flg0_14_sel[i++] = FIELD_GET(ICE_XLT_KB_FL03, d64); + entry->flg0_14_sel[i++] = FIELD_GET(ICE_XLT_KB_FL04, d64); + entry->flg0_14_sel[i++] = FIELD_GET(ICE_XLT_KB_FL05, d64); + + d64 = *((u64 *)&data[ICE_XLT_KB_FL06_IDD]) >> ICE_XLT_KB_FL06_OFF; + + entry->flg0_14_sel[i++] = FIELD_GET(ICE_XLT_KB_FL06, d64); + entry->flg0_14_sel[i++] = FIELD_GET(ICE_XLT_KB_FL07, d64); + entry->flg0_14_sel[i++] = FIELD_GET(ICE_XLT_KB_FL08, d64); + entry->flg0_14_sel[i++] = FIELD_GET(ICE_XLT_KB_FL09, d64); + entry->flg0_14_sel[i++] = FIELD_GET(ICE_XLT_KB_FL10, d64); + entry->flg0_14_sel[i++] = FIELD_GET(ICE_XLT_KB_FL11, d64); + + d64 = *((u64 *)&data[ICE_XLT_KB_FL12_IDD]) >> ICE_XLT_KB_FL12_OFF; + + entry->flg0_14_sel[i++] = FIELD_GET(ICE_XLT_KB_FL12, d64); + entry->flg0_14_sel[i++] = FIELD_GET(ICE_XLT_KB_FL13, d64); + entry->flg0_14_sel[i] = FIELD_GET(ICE_XLT_KB_FL14, d64); + + entry->xlt1_md_sel = FIELD_GET(ICE_XLT_KB_X1MS, d64); + entry->xlt2_md_sel = FIELD_GET(ICE_XLT_KB_X2MS, d64); +} + +#define ICE_XLT_KB_X1PM_OFF 0 +#define ICE_XLT_KB_X2PM_OFF 1 +#define ICE_XLT_KB_PIPM_OFF 2 +#define ICE_XLT_KB_FL15_OFF 4 +#define ICE_XLT_KB_TBL_OFF 12 + +/** + * ice_parse_kb_data - parse 204 bits of XLT Key Build Table + * @hw: pointer to the hardware structure + * @kb: pointer to the XLT Key Build Table structure + * @data: XLT Key Build Table data to be parsed + */ +static void ice_parse_kb_data(struct ice_hw *hw, struct ice_xlt_kb *kb, + void *data) +{ + u8 *buf = data; + int i; + + kb->xlt1_pm = buf[ICE_XLT_KB_X1PM_OFF]; + kb->xlt2_pm = buf[ICE_XLT_KB_X2PM_OFF]; + kb->prof_id_pm = buf[ICE_XLT_KB_PIPM_OFF]; + + kb->flag15 = *(u64 *)&buf[ICE_XLT_KB_FL15_OFF]; + for (i = 0; i < ICE_XLT_KB_TBL_CNT; i++) + ice_kb_entry_init(&kb->entries[i], + &buf[ICE_XLT_KB_TBL_OFF + + i * ICE_XLT_KB_TBL_ENTRY_SIZE]); + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_xlt_kb_dump(hw, kb); +} + +static struct ice_xlt_kb *ice_xlt_kb_get(struct ice_hw *hw, u32 sect_type) +{ + struct ice_pkg_enum state = {}; + struct ice_seg *seg = hw->seg; + struct ice_xlt_kb *kb; + void *data; + + if (!seg) + return ERR_PTR(-EINVAL); + + kb = kzalloc(sizeof(*kb), GFP_KERNEL); + if (!kb) + return ERR_PTR(-ENOMEM); + + data = ice_pkg_enum_section(seg, &state, sect_type); + if (!data) { + ice_debug(hw, ICE_DBG_PARSER, "failed to find section type %d.\n", + sect_type); + kfree(kb); + return ERR_PTR(-EINVAL); + } + + ice_parse_kb_data(hw, kb, data); + + return kb; +} + +/** + * ice_xlt_kb_get_sw - create switch xlt key build + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Key Builder table for Switch. + */ +static struct ice_xlt_kb *ice_xlt_kb_get_sw(struct ice_hw *hw) +{ + return ice_xlt_kb_get(hw, ICE_SID_XLT_KEY_BUILDER_SW); +} + +/** + * ice_xlt_kb_get_acl - create acl xlt key build + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Key Builder table for ACL. + */ +static struct ice_xlt_kb *ice_xlt_kb_get_acl(struct ice_hw *hw) +{ + return ice_xlt_kb_get(hw, ICE_SID_XLT_KEY_BUILDER_ACL); +} + +/** + * ice_xlt_kb_get_fd - create fdir xlt key build + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Key Builder table for Flow Director. + */ +static struct ice_xlt_kb *ice_xlt_kb_get_fd(struct ice_hw *hw) +{ + return ice_xlt_kb_get(hw, ICE_SID_XLT_KEY_BUILDER_FD); +} + +/** + * ice_xlt_kb_get_rss - create rss xlt key build + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated Key Builder table for RSS. + */ +static struct ice_xlt_kb *ice_xlt_kb_get_rss(struct ice_hw *hw) +{ + return ice_xlt_kb_get(hw, ICE_SID_XLT_KEY_BUILDER_RSS); +} + +#define ICE_XLT_KB_MASK GENMASK_ULL(5, 0) + +/** + * ice_xlt_kb_flag_get - aggregate 64 bits packet flag into 16 bits xlt flag + * @kb: xlt key build + * @pkt_flag: 64 bits packet flag + * + * Return: XLT flag or 0 if @pkt_flag = 0. + */ +u16 ice_xlt_kb_flag_get(struct ice_xlt_kb *kb, u64 pkt_flag) +{ + struct ice_xlt_kb_entry *entry = &kb->entries[0]; + u16 flag = 0; + int i; + + /* check flag 15 */ + if (kb->flag15 & pkt_flag) + flag = BIT(ICE_XLT_KB_FLAG0_14_CNT); + + /* check flag 0 - 14 */ + for (i = 0; i < ICE_XLT_KB_FLAG0_14_CNT; i++) { + /* only check first entry */ + u16 idx = entry->flg0_14_sel[i] & ICE_XLT_KB_MASK; + + if (pkt_flag & BIT(idx)) + flag |= (u16)BIT(i); + } + + return flag; +} + +/*** Parser API ***/ +/** + * ice_parser_create - create a parser instance + * @hw: pointer to the hardware structure + * + * Return: a pointer to the allocated parser instance or ERR_PTR + * in case of error. + */ +struct ice_parser *ice_parser_create(struct ice_hw *hw) +{ + struct ice_parser *p; + void *err; + + p = kzalloc(sizeof(*p), GFP_KERNEL); + if (!p) + return ERR_PTR(-ENOMEM); + + p->hw = hw; + p->rt.psr = p; + + p->imem_table = ice_imem_table_get(hw); + if (IS_ERR(p->imem_table)) { + err = p->imem_table; + goto err; + } + + p->mi_table = ice_metainit_table_get(hw); + if (IS_ERR(p->mi_table)) { + err = p->mi_table; + goto err; + } + + p->pg_cam_table = ice_pg_cam_table_get(hw); + if (IS_ERR(p->pg_cam_table)) { + err = p->pg_cam_table; + goto err; + } + + p->pg_sp_cam_table = ice_pg_sp_cam_table_get(hw); + if (IS_ERR(p->pg_sp_cam_table)) { + err = p->pg_sp_cam_table; + goto err; + } + + p->pg_nm_cam_table = ice_pg_nm_cam_table_get(hw); + if (IS_ERR(p->pg_nm_cam_table)) { + err = p->pg_nm_cam_table; + goto err; + } + + p->pg_nm_sp_cam_table = ice_pg_nm_sp_cam_table_get(hw); + if (IS_ERR(p->pg_nm_sp_cam_table)) { + err = p->pg_nm_sp_cam_table; + goto err; + } + + p->bst_tcam_table = ice_bst_tcam_table_get(hw); + if (IS_ERR(p->bst_tcam_table)) { + err = p->bst_tcam_table; + goto err; + } + + p->bst_lbl_table = ice_bst_lbl_table_get(hw); + if (IS_ERR(p->bst_lbl_table)) { + err = p->bst_lbl_table; + goto err; + } + + p->ptype_mk_tcam_table = ice_ptype_mk_tcam_table_get(hw); + if (IS_ERR(p->ptype_mk_tcam_table)) { + err = p->ptype_mk_tcam_table; + goto err; + } + + p->mk_grp_table = ice_mk_grp_table_get(hw); + if (IS_ERR(p->mk_grp_table)) { + err = p->mk_grp_table; + goto err; + } + + p->proto_grp_table = ice_proto_grp_table_get(hw); + if (IS_ERR(p->proto_grp_table)) { + err = p->proto_grp_table; + goto err; + } + + p->flg_rd_table = ice_flg_rd_table_get(hw); + if (IS_ERR(p->flg_rd_table)) { + err = p->flg_rd_table; + goto err; + } + + p->xlt_kb_sw = ice_xlt_kb_get_sw(hw); + if (IS_ERR(p->xlt_kb_sw)) { + err = p->xlt_kb_sw; + goto err; + } + + p->xlt_kb_acl = ice_xlt_kb_get_acl(hw); + if (IS_ERR(p->xlt_kb_acl)) { + err = p->xlt_kb_acl; + goto err; + } + + p->xlt_kb_fd = ice_xlt_kb_get_fd(hw); + if (IS_ERR(p->xlt_kb_fd)) { + err = p->xlt_kb_fd; + goto err; + } + + p->xlt_kb_rss = ice_xlt_kb_get_rss(hw); + if (IS_ERR(p->xlt_kb_rss)) { + err = p->xlt_kb_rss; + goto err; + } + + return p; +err: + ice_parser_destroy(p); + return err; +} + +/** + * ice_parser_destroy - destroy a parser instance + * @psr: pointer to a parser instance + */ +void ice_parser_destroy(struct ice_parser *psr) +{ + kfree(psr->imem_table); + kfree(psr->mi_table); + kfree(psr->pg_cam_table); + kfree(psr->pg_sp_cam_table); + kfree(psr->pg_nm_cam_table); + kfree(psr->pg_nm_sp_cam_table); + kfree(psr->bst_tcam_table); + kfree(psr->bst_lbl_table); + kfree(psr->ptype_mk_tcam_table); + kfree(psr->mk_grp_table); + kfree(psr->proto_grp_table); + kfree(psr->flg_rd_table); + kfree(psr->xlt_kb_sw); + kfree(psr->xlt_kb_acl); + kfree(psr->xlt_kb_fd); + kfree(psr->xlt_kb_rss); + + kfree(psr); +} + +/** + * ice_parser_run - parse on a packet in binary and return the result + * @psr: pointer to a parser instance + * @pkt_buf: packet data + * @pkt_len: packet length + * @rslt: input/output parameter to save parser result. + * + * Return: 0 on success or errno. + */ +int ice_parser_run(struct ice_parser *psr, const u8 *pkt_buf, + int pkt_len, struct ice_parser_result *rslt) +{ + ice_parser_rt_reset(&psr->rt); + ice_parser_rt_pktbuf_set(&psr->rt, pkt_buf, pkt_len); + + return ice_parser_rt_execute(&psr->rt, rslt); +} + +/** + * ice_parser_result_dump - dump a parser result info + * @hw: pointer to the hardware structure + * @rslt: parser result info to dump + */ +void ice_parser_result_dump(struct ice_hw *hw, struct ice_parser_result *rslt) +{ + struct device *dev = ice_hw_to_dev(hw); + int i; + + dev_info(dev, "ptype = %d\n", rslt->ptype); + for (i = 0; i < rslt->po_num; i++) + dev_info(dev, "proto = %d, offset = %d\n", + rslt->po[i].proto_id, rslt->po[i].offset); + + dev_info(dev, "flags_psr = 0x%016llx\n", rslt->flags_psr); + dev_info(dev, "flags_pkt = 0x%016llx\n", rslt->flags_pkt); + dev_info(dev, "flags_sw = 0x%04x\n", rslt->flags_sw); + dev_info(dev, "flags_fd = 0x%04x\n", rslt->flags_fd); + dev_info(dev, "flags_rss = 0x%04x\n", rslt->flags_rss); +} + +#define ICE_BT_VLD_KEY 0xFF +#define ICE_BT_INV_KEY 0xFE + +static void ice_bst_dvm_set(struct ice_parser *psr, enum ice_lbl_type type, + bool on) +{ + u16 i = 0; + + while (true) { + struct ice_bst_tcam_item *item; + u8 key; + + item = ice_bst_tcam_search(psr->bst_tcam_table, + psr->bst_lbl_table, + type, &i); + if (!item) + break; + + key = on ? ICE_BT_VLD_KEY : ICE_BT_INV_KEY; + item->key[ICE_BT_VM_OFF] = key; + item->key_inv[ICE_BT_VM_OFF] = key; + i++; + } +} + +/** + * ice_parser_dvm_set - configure double vlan mode for parser + * @psr: pointer to a parser instance + * @on: true to turn on; false to turn off + */ +void ice_parser_dvm_set(struct ice_parser *psr, bool on) +{ + ice_bst_dvm_set(psr, ICE_LBL_BST_TYPE_DVM, on); + ice_bst_dvm_set(psr, ICE_LBL_BST_TYPE_SVM, !on); +} + +static int ice_tunnel_port_set(struct ice_parser *psr, enum ice_lbl_type type, + u16 udp_port, bool on) +{ + u8 *buf = (u8 *)&udp_port; + u16 i = 0; + + while (true) { + struct ice_bst_tcam_item *item; + + item = ice_bst_tcam_search(psr->bst_tcam_table, + psr->bst_lbl_table, + type, &i); + if (!item) + break; + + /* found empty slot to add */ + if (on && item->key[ICE_BT_TUN_PORT_OFF_H] == ICE_BT_INV_KEY && + item->key_inv[ICE_BT_TUN_PORT_OFF_H] == ICE_BT_INV_KEY) { + item->key_inv[ICE_BT_TUN_PORT_OFF_L] = + buf[ICE_UDP_PORT_OFF_L]; + item->key_inv[ICE_BT_TUN_PORT_OFF_H] = + buf[ICE_UDP_PORT_OFF_H]; + + item->key[ICE_BT_TUN_PORT_OFF_L] = + ICE_BT_VLD_KEY - buf[ICE_UDP_PORT_OFF_L]; + item->key[ICE_BT_TUN_PORT_OFF_H] = + ICE_BT_VLD_KEY - buf[ICE_UDP_PORT_OFF_H]; + + return 0; + /* found a matched slot to delete */ + } else if (!on && + (item->key_inv[ICE_BT_TUN_PORT_OFF_L] == + buf[ICE_UDP_PORT_OFF_L] || + item->key_inv[ICE_BT_TUN_PORT_OFF_H] == + buf[ICE_UDP_PORT_OFF_H])) { + item->key_inv[ICE_BT_TUN_PORT_OFF_L] = ICE_BT_VLD_KEY; + item->key_inv[ICE_BT_TUN_PORT_OFF_H] = ICE_BT_INV_KEY; + + item->key[ICE_BT_TUN_PORT_OFF_L] = ICE_BT_VLD_KEY; + item->key[ICE_BT_TUN_PORT_OFF_H] = ICE_BT_INV_KEY; + + return 0; + } + i++; + } + + return -EINVAL; +} + +/** + * ice_parser_vxlan_tunnel_set - configure vxlan tunnel for parser + * @psr: pointer to a parser instance + * @udp_port: vxlan tunnel port in UDP header + * @on: true to turn on; false to turn off + * + * Return: 0 on success or errno on failure. + */ +int ice_parser_vxlan_tunnel_set(struct ice_parser *psr, + u16 udp_port, bool on) +{ + return ice_tunnel_port_set(psr, ICE_LBL_BST_TYPE_VXLAN, udp_port, on); +} + +/** + * ice_parser_geneve_tunnel_set - configure geneve tunnel for parser + * @psr: pointer to a parser instance + * @udp_port: geneve tunnel port in UDP header + * @on: true to turn on; false to turn off + * + * Return: 0 on success or errno on failure. + */ +int ice_parser_geneve_tunnel_set(struct ice_parser *psr, + u16 udp_port, bool on) +{ + return ice_tunnel_port_set(psr, ICE_LBL_BST_TYPE_GENEVE, udp_port, on); +} + +/** + * ice_parser_ecpri_tunnel_set - configure ecpri tunnel for parser + * @psr: pointer to a parser instance + * @udp_port: ecpri tunnel port in UDP header + * @on: true to turn on; false to turn off + * + * Return: 0 on success or errno on failure. + */ +int ice_parser_ecpri_tunnel_set(struct ice_parser *psr, + u16 udp_port, bool on) +{ + return ice_tunnel_port_set(psr, ICE_LBL_BST_TYPE_UDP_ECPRI, + udp_port, on); +} + +/** + * ice_nearest_proto_id - find nearest protocol ID + * @rslt: pointer to a parser result instance + * @offset: a min value for the protocol offset + * @proto_id: the protocol ID (output) + * @proto_off: the protocol offset (output) + * + * From the protocols in @rslt, find the nearest protocol that has offset + * larger than @offset. + * + * Return: if true, the protocol's ID and offset + */ +static bool ice_nearest_proto_id(struct ice_parser_result *rslt, u16 offset, + u8 *proto_id, u16 *proto_off) +{ + u16 dist = U16_MAX; + u8 proto = 0; + int i; + + for (i = 0; i < rslt->po_num; i++) { + if (offset < rslt->po[i].offset) + continue; + if (offset - rslt->po[i].offset < dist) { + proto = rslt->po[i].proto_id; + dist = offset - rslt->po[i].offset; + } + } + + if (dist % 2) + return false; + + *proto_id = proto; + *proto_off = dist; + + return true; +} + +/* default flag mask to cover GTP_EH_PDU, GTP_EH_PDU_LINK and TUN2 + * In future, the flag masks should learn from DDP + */ +#define ICE_KEYBUILD_FLAG_MASK_DEFAULT_SW 0x4002 +#define ICE_KEYBUILD_FLAG_MASK_DEFAULT_ACL 0x0000 +#define ICE_KEYBUILD_FLAG_MASK_DEFAULT_FD 0x6080 +#define ICE_KEYBUILD_FLAG_MASK_DEFAULT_RSS 0x6010 + +/** + * ice_parser_profile_init - initialize a FXP profile based on parser result + * @rslt: a instance of a parser result + * @pkt_buf: packet data buffer + * @msk_buf: packet mask buffer + * @buf_len: packet length + * @blk: FXP pipeline stage + * @prof: input/output parameter to save the profile + * + * Return: 0 on success or errno on failure. + */ +int ice_parser_profile_init(struct ice_parser_result *rslt, + const u8 *pkt_buf, const u8 *msk_buf, + int buf_len, enum ice_block blk, + struct ice_parser_profile *prof) +{ + u8 proto_id = U8_MAX; + u16 proto_off = 0; + u16 off; + + memset(prof, 0, sizeof(*prof)); + set_bit(rslt->ptype, prof->ptypes); + if (blk == ICE_BLK_SW) { + prof->flags = rslt->flags_sw; + prof->flags_msk = ICE_KEYBUILD_FLAG_MASK_DEFAULT_SW; + } else if (blk == ICE_BLK_ACL) { + prof->flags = rslt->flags_acl; + prof->flags_msk = ICE_KEYBUILD_FLAG_MASK_DEFAULT_ACL; + } else if (blk == ICE_BLK_FD) { + prof->flags = rslt->flags_fd; + prof->flags_msk = ICE_KEYBUILD_FLAG_MASK_DEFAULT_FD; + } else if (blk == ICE_BLK_RSS) { + prof->flags = rslt->flags_rss; + prof->flags_msk = ICE_KEYBUILD_FLAG_MASK_DEFAULT_RSS; + } else { + return -EINVAL; + } + + for (off = 0; off < buf_len - 1; off++) { + if (msk_buf[off] == 0 && msk_buf[off + 1] == 0) + continue; + if (!ice_nearest_proto_id(rslt, off, &proto_id, &proto_off)) + continue; + if (prof->fv_num >= ICE_PARSER_FV_MAX) + return -EINVAL; + + prof->fv[prof->fv_num].proto_id = proto_id; + prof->fv[prof->fv_num].offset = proto_off; + prof->fv[prof->fv_num].spec = *(const u16 *)&pkt_buf[off]; + prof->fv[prof->fv_num].msk = *(const u16 *)&msk_buf[off]; + prof->fv_num++; + } + + return 0; +} + +/** + * ice_parser_profile_dump - dump an FXP profile info + * @hw: pointer to the hardware structure + * @prof: profile info to dump + */ +void ice_parser_profile_dump(struct ice_hw *hw, + struct ice_parser_profile *prof) +{ + struct device *dev = ice_hw_to_dev(hw); + u16 i; + + dev_info(dev, "ptypes:\n"); + for (i = 0; i < ICE_FLOW_PTYPE_MAX; i++) + if (test_bit(i, prof->ptypes)) + dev_info(dev, "\t%u\n", i); + + for (i = 0; i < prof->fv_num; i++) + dev_info(dev, "proto = %u, offset = %2u, spec = 0x%04x, mask = 0x%04x\n", + prof->fv[i].proto_id, prof->fv[i].offset, + prof->fv[i].spec, prof->fv[i].msk); + + dev_info(dev, "flags = 0x%04x\n", prof->flags); + dev_info(dev, "flags_msk = 0x%04x\n", prof->flags_msk); +} diff --git a/drivers/net/ethernet/intel/ice/ice_parser.h b/drivers/net/ethernet/intel/ice/ice_parser.h new file mode 100644 index 000000000000..6509d807627c --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_parser.h @@ -0,0 +1,540 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2024 Intel Corporation */ + +#ifndef _ICE_PARSER_H_ +#define _ICE_PARSER_H_ + +#define ICE_SEC_DATA_OFFSET 4 +#define ICE_SID_RXPARSER_IMEM_ENTRY_SIZE 48 +#define ICE_SID_RXPARSER_METADATA_INIT_ENTRY_SIZE 24 +#define ICE_SID_RXPARSER_CAM_ENTRY_SIZE 16 +#define ICE_SID_RXPARSER_PG_SPILL_ENTRY_SIZE 17 +#define ICE_SID_RXPARSER_NOMATCH_CAM_ENTRY_SIZE 12 +#define ICE_SID_RXPARSER_NOMATCH_SPILL_ENTRY_SIZE 13 +#define ICE_SID_RXPARSER_BOOST_TCAM_ENTRY_SIZE 88 +#define ICE_SID_RXPARSER_MARKER_TYPE_ENTRY_SIZE 24 +#define ICE_SID_RXPARSER_MARKER_GRP_ENTRY_SIZE 8 +#define ICE_SID_RXPARSER_PROTO_GRP_ENTRY_SIZE 24 +#define ICE_SID_RXPARSER_FLAG_REDIR_ENTRY_SIZE 1 + +#define ICE_SEC_LBL_DATA_OFFSET 2 +#define ICE_SID_LBL_ENTRY_SIZE 66 + +/*** ICE_SID_RXPARSER_IMEM section ***/ +#define ICE_IMEM_TABLE_SIZE 192 + +/* TCAM boost Master; if bit is set, and TCAM hit, TCAM output overrides iMEM + * output. + */ +struct ice_bst_main { + bool alu0; + bool alu1; + bool alu2; + bool pg; +}; + +struct ice_bst_keybuilder { + u8 prio; /* 0-3: PG precedence within ALUs (3 highest) */ + bool tsr_ctrl; /* TCAM Search Register control */ +}; + +/* Next protocol Key builder */ +struct ice_np_keybuilder { + u8 opc; + u8 start_reg0; + u8 len_reg1; +}; + +enum ice_np_keybuilder_opcode { + ICE_NPKB_OPC_EXTRACT = 0, + ICE_NPKB_OPC_BUILD = 1, + ICE_NPKB_OPC_BYPASS = 2, +}; + +/* Parse Graph Key builder */ +struct ice_pg_keybuilder { + bool flag0_ena; + bool flag1_ena; + bool flag2_ena; + bool flag3_ena; + u8 flag0_idx; + u8 flag1_idx; + u8 flag2_idx; + u8 flag3_idx; + u8 alu_reg_idx; +}; + +enum ice_alu_idx { + ICE_ALU0_IDX = 0, + ICE_ALU1_IDX = 1, + ICE_ALU2_IDX = 2, +}; + +enum ice_alu_opcode { + ICE_ALU_PARK = 0, + ICE_ALU_MOV_ADD = 1, + ICE_ALU_ADD = 2, + ICE_ALU_MOV_AND = 4, + ICE_ALU_AND = 5, + ICE_ALU_AND_IMM = 6, + ICE_ALU_MOV_OR = 7, + ICE_ALU_OR = 8, + ICE_ALU_MOV_XOR = 9, + ICE_ALU_XOR = 10, + ICE_ALU_NOP = 11, + ICE_ALU_BR = 12, + ICE_ALU_BREQ = 13, + ICE_ALU_BRNEQ = 14, + ICE_ALU_BRGT = 15, + ICE_ALU_BRLT = 16, + ICE_ALU_BRGEQ = 17, + ICE_ALU_BRLEG = 18, + ICE_ALU_SETEQ = 19, + ICE_ALU_ANDEQ = 20, + ICE_ALU_OREQ = 21, + ICE_ALU_SETNEQ = 22, + ICE_ALU_ANDNEQ = 23, + ICE_ALU_ORNEQ = 24, + ICE_ALU_SETGT = 25, + ICE_ALU_ANDGT = 26, + ICE_ALU_ORGT = 27, + ICE_ALU_SETLT = 28, + ICE_ALU_ANDLT = 29, + ICE_ALU_ORLT = 30, + ICE_ALU_MOV_SUB = 31, + ICE_ALU_SUB = 32, + ICE_ALU_INVALID = 64, +}; + +enum ice_proto_off_opcode { + ICE_PO_OFF_REMAIN = 0, + ICE_PO_OFF_HDR_ADD = 1, + ICE_PO_OFF_HDR_SUB = 2, +}; + +struct ice_alu { + enum ice_alu_opcode opc; + u8 src_start; + u8 src_len; + bool shift_xlate_sel; + u8 shift_xlate_key; + u8 src_reg_id; + u8 dst_reg_id; + bool inc0; + bool inc1; + u8 proto_offset_opc; + u8 proto_offset; + u8 branch_addr; + u16 imm; + bool dedicate_flags_ena; + u8 dst_start; + u8 dst_len; + bool flags_extr_imm; + u8 flags_start_imm; +}; + +/* Parser program code (iMEM) */ +struct ice_imem_item { + u16 idx; + struct ice_bst_main b_m; + struct ice_bst_keybuilder b_kb; + u8 pg_prio; + struct ice_np_keybuilder np_kb; + struct ice_pg_keybuilder pg_kb; + struct ice_alu alu0; + struct ice_alu alu1; + struct ice_alu alu2; +}; + +/*** ICE_SID_RXPARSER_METADATA_INIT section ***/ +#define ICE_METAINIT_TABLE_SIZE 16 + +/* Metadata Initialization item */ +struct ice_metainit_item { + u16 idx; + + u8 tsr; /* TCAM Search key Register */ + u16 ho; /* Header Offset register */ + u16 pc; /* Program Counter register */ + u16 pg_rn; /* Parse Graph Root Node */ + u8 cd; /* Control Domain ID */ + + /* General Purpose Registers */ + bool gpr_a_ctrl; + u8 gpr_a_data_mdid; + u8 gpr_a_data_start; + u8 gpr_a_data_len; + u8 gpr_a_id; + + bool gpr_b_ctrl; + u8 gpr_b_data_mdid; + u8 gpr_b_data_start; + u8 gpr_b_data_len; + u8 gpr_b_id; + + bool gpr_c_ctrl; + u8 gpr_c_data_mdid; + u8 gpr_c_data_start; + u8 gpr_c_data_len; + u8 gpr_c_id; + + bool gpr_d_ctrl; + u8 gpr_d_data_mdid; + u8 gpr_d_data_start; + u8 gpr_d_data_len; + u8 gpr_d_id; + + u64 flags; /* Initial value for all flags */ +}; + +/*** ICE_SID_RXPARSER_CAM, ICE_SID_RXPARSER_PG_SPILL, + * ICE_SID_RXPARSER_NOMATCH_CAM and ICE_SID_RXPARSER_NOMATCH_CAM + * sections ***/ +#define ICE_PG_CAM_TABLE_SIZE 2048 +#define ICE_PG_SP_CAM_TABLE_SIZE 128 +#define ICE_PG_NM_CAM_TABLE_SIZE 1024 +#define ICE_PG_NM_SP_CAM_TABLE_SIZE 64 + +struct ice_pg_cam_key { + bool valid; + struct_group_attr(val, __packed, + u16 node_id; /* Node ID of protocol in parse graph */ + bool flag0; + bool flag1; + bool flag2; + bool flag3; + u8 boost_idx; /* Boost TCAM match index */ + u16 alu_reg; + u32 next_proto; /* next Protocol value (must be last) */ + ); +}; + +struct ice_pg_nm_cam_key { + bool valid; + struct_group_attr(val, __packed, + u16 node_id; + bool flag0; + bool flag1; + bool flag2; + bool flag3; + u8 boost_idx; + u16 alu_reg; + ); +}; + +struct ice_pg_cam_action { + u16 next_node; /* Parser Node ID for the next round */ + u8 next_pc; /* next Program Counter */ + bool is_pg; /* is protocol group */ + u8 proto_id; /* protocol ID or proto group ID */ + bool is_mg; /* is marker group */ + u8 marker_id; /* marker ID or marker group ID */ + bool is_last_round; + bool ho_polarity; /* header offset polarity */ + u16 ho_inc; +}; + +/* Parse Graph item */ +struct ice_pg_cam_item { + u16 idx; + struct ice_pg_cam_key key; + struct ice_pg_cam_action action; +}; + +/* Parse Graph No Match item */ +struct ice_pg_nm_cam_item { + u16 idx; + struct ice_pg_nm_cam_key key; + struct ice_pg_cam_action action; +}; + +struct ice_pg_cam_item *ice_pg_cam_match(struct ice_pg_cam_item *table, + int size, struct ice_pg_cam_key *key); +struct ice_pg_nm_cam_item * +ice_pg_nm_cam_match(struct ice_pg_nm_cam_item *table, int size, + struct ice_pg_cam_key *key); + +/*** ICE_SID_RXPARSER_BOOST_TCAM and ICE_SID_LBL_RXPARSER_TMEM sections ***/ +#define ICE_BST_TCAM_TABLE_SIZE 256 +#define ICE_BST_TCAM_KEY_SIZE 20 +#define ICE_BST_KEY_TCAM_SIZE 19 + +/* Boost TCAM item */ +struct ice_bst_tcam_item { + u16 addr; + u8 key[ICE_BST_TCAM_KEY_SIZE]; + u8 key_inv[ICE_BST_TCAM_KEY_SIZE]; + u8 hit_idx_grp; + u8 pg_prio; + struct ice_np_keybuilder np_kb; + struct ice_pg_keybuilder pg_kb; + struct ice_alu alu0; + struct ice_alu alu1; + struct ice_alu alu2; +}; + +#define ICE_LBL_LEN 64 +#define ICE_LBL_BST_DVM "BOOST_MAC_VLAN_DVM" +#define ICE_LBL_BST_SVM "BOOST_MAC_VLAN_SVM" +#define ICE_LBL_TNL_VXLAN "TNL_VXLAN" +#define ICE_LBL_TNL_GENEVE "TNL_GENEVE" +#define ICE_LBL_TNL_UDP_ECPRI "TNL_UDP_ECPRI" + +enum ice_lbl_type { + ICE_LBL_BST_TYPE_UNKNOWN, + ICE_LBL_BST_TYPE_DVM, + ICE_LBL_BST_TYPE_SVM, + ICE_LBL_BST_TYPE_VXLAN, + ICE_LBL_BST_TYPE_GENEVE, + ICE_LBL_BST_TYPE_UDP_ECPRI, +}; + +struct ice_lbl_item { + u16 idx; + char label[ICE_LBL_LEN]; + + /* must be at the end, not part of the DDP section */ + enum ice_lbl_type type; +}; + +struct ice_bst_tcam_item * +ice_bst_tcam_match(struct ice_bst_tcam_item *tcam_table, u8 *pat); +struct ice_bst_tcam_item * +ice_bst_tcam_search(struct ice_bst_tcam_item *tcam_table, + struct ice_lbl_item *lbl_table, + enum ice_lbl_type type, u16 *start); + +/*** ICE_SID_RXPARSER_MARKER_PTYPE section ***/ +#define ICE_PTYPE_MK_TCAM_TABLE_SIZE 1024 +#define ICE_PTYPE_MK_TCAM_KEY_SIZE 10 + +struct ice_ptype_mk_tcam_item { + u16 address; + u16 ptype; + u8 key[ICE_PTYPE_MK_TCAM_KEY_SIZE]; + u8 key_inv[ICE_PTYPE_MK_TCAM_KEY_SIZE]; +} __packed; + +struct ice_ptype_mk_tcam_item * +ice_ptype_mk_tcam_match(struct ice_ptype_mk_tcam_item *table, + u8 *pat, int len); +/*** ICE_SID_RXPARSER_MARKER_GRP section ***/ +#define ICE_MK_GRP_TABLE_SIZE 128 +#define ICE_MK_COUNT_PER_GRP 8 + +/* Marker Group item */ +struct ice_mk_grp_item { + int idx; + u8 markers[ICE_MK_COUNT_PER_GRP]; +}; + +/*** ICE_SID_RXPARSER_PROTO_GRP section ***/ +#define ICE_PROTO_COUNT_PER_GRP 8 +#define ICE_PROTO_GRP_TABLE_SIZE 192 +#define ICE_PROTO_GRP_ITEM_SIZE 22 +struct ice_proto_off { + bool polarity; /* true: positive, false: negative */ + u8 proto_id; + u16 offset; /* 10 bit protocol offset */ +}; + +/* Protocol Group item */ +struct ice_proto_grp_item { + u16 idx; + struct ice_proto_off po[ICE_PROTO_COUNT_PER_GRP]; +}; + +/*** ICE_SID_RXPARSER_FLAG_REDIR section ***/ +#define ICE_FLG_RD_TABLE_SIZE 64 +#define ICE_FLG_RDT_SIZE 64 + +/* Flags Redirection item */ +struct ice_flg_rd_item { + u16 idx; + bool expose; + u8 intr_flg_id; /* Internal Flag ID */ +}; + +u64 ice_flg_redirect(struct ice_flg_rd_item *table, u64 psr_flg); + +/*** ICE_SID_XLT_KEY_BUILDER_SW, ICE_SID_XLT_KEY_BUILDER_ACL, + * ICE_SID_XLT_KEY_BUILDER_FD and ICE_SID_XLT_KEY_BUILDER_RSS + * sections ***/ +#define ICE_XLT_KB_FLAG0_14_CNT 15 +#define ICE_XLT_KB_TBL_CNT 8 +#define ICE_XLT_KB_TBL_ENTRY_SIZE 24 + +struct ice_xlt_kb_entry { + u8 xlt1_ad_sel; + u8 xlt2_ad_sel; + u16 flg0_14_sel[ICE_XLT_KB_FLAG0_14_CNT]; + u8 xlt1_md_sel; + u8 xlt2_md_sel; +}; + +/* XLT Key Builder */ +struct ice_xlt_kb { + u8 xlt1_pm; /* XLT1 Partition Mode */ + u8 xlt2_pm; /* XLT2 Partition Mode */ + u8 prof_id_pm; /* Profile ID Partition Mode */ + u64 flag15; + + struct ice_xlt_kb_entry entries[ICE_XLT_KB_TBL_CNT]; +}; + +u16 ice_xlt_kb_flag_get(struct ice_xlt_kb *kb, u64 pkt_flag); + +/*** Parser API ***/ +#define ICE_GPR_HV_IDX 64 +#define ICE_GPR_HV_SIZE 32 +#define ICE_GPR_ERR_IDX 84 +#define ICE_GPR_FLG_IDX 104 +#define ICE_GPR_FLG_SIZE 16 + +#define ICE_GPR_TSR_IDX 108 /* TSR: TCAM Search Register */ +#define ICE_GPR_NN_IDX 109 /* NN: Next Parsing Cycle Node ID */ +#define ICE_GPR_HO_IDX 110 /* HO: Next Parsing Cycle hdr Offset */ +#define ICE_GPR_NP_IDX 111 /* NP: Next Parsing Cycle */ + +#define ICE_PARSER_MAX_PKT_LEN 504 +#define ICE_PARSER_PKT_REV 32 +#define ICE_PARSER_GPR_NUM 128 +#define ICE_PARSER_FLG_NUM 64 +#define ICE_PARSER_ERR_NUM 16 +#define ICE_BST_KEY_SIZE 10 +#define ICE_MARKER_ID_SIZE 9 +#define ICE_MARKER_MAX_SIZE \ + (ICE_MARKER_ID_SIZE * BITS_PER_BYTE - 1) +#define ICE_MARKER_ID_NUM 8 +#define ICE_PO_PAIR_SIZE 256 + +struct ice_gpr_pu { + /* array of flags to indicate if GRP needs to be updated */ + bool gpr_val_upd[ICE_PARSER_GPR_NUM]; + u16 gpr_val[ICE_PARSER_GPR_NUM]; + u64 flg_msk; + u64 flg_val; + u16 err_msk; + u16 err_val; +}; + +enum ice_pg_prio { + ICE_PG_P0 = 0, + ICE_PG_P1 = 1, + ICE_PG_P2 = 2, + ICE_PG_P3 = 3, +}; + +struct ice_parser_rt { + struct ice_parser *psr; + u16 gpr[ICE_PARSER_GPR_NUM]; + u8 pkt_buf[ICE_PARSER_MAX_PKT_LEN + ICE_PARSER_PKT_REV]; + u16 pkt_len; + u16 po; + u8 bst_key[ICE_BST_KEY_SIZE]; + struct ice_pg_cam_key pg_key; + struct ice_alu *alu0; + struct ice_alu *alu1; + struct ice_alu *alu2; + struct ice_pg_cam_action *action; + u8 pg_prio; + struct ice_gpr_pu pu; + u8 markers[ICE_MARKER_ID_SIZE]; + bool protocols[ICE_PO_PAIR_SIZE]; + u16 offsets[ICE_PO_PAIR_SIZE]; +}; + +struct ice_parser_proto_off { + u8 proto_id; /* hardware protocol ID */ + u16 offset; /* offset from the start of the protocol header */ +}; + +#define ICE_PARSER_PROTO_OFF_PAIR_SIZE 16 +#define ICE_PARSER_FLAG_PSR_SIZE 8 +#define ICE_PARSER_FV_SIZE 48 +#define ICE_PARSER_FV_MAX 24 +#define ICE_BT_TUN_PORT_OFF_H 16 +#define ICE_BT_TUN_PORT_OFF_L 15 +#define ICE_BT_VM_OFF 0 +#define ICE_UDP_PORT_OFF_H 1 +#define ICE_UDP_PORT_OFF_L 0 + +struct ice_parser_result { + u16 ptype; /* 16 bits hardware PTYPE */ + /* array of protocol and header offset pairs */ + struct ice_parser_proto_off po[ICE_PARSER_PROTO_OFF_PAIR_SIZE]; + int po_num; /* # of protocol-offset pairs must <= 16 */ + u64 flags_psr; /* parser flags */ + u64 flags_pkt; /* packet flags */ + u16 flags_sw; /* key builder flags for SW */ + u16 flags_acl; /* key builder flags for ACL */ + u16 flags_fd; /* key builder flags for FD */ + u16 flags_rss; /* key builder flags for RSS */ +}; + +void ice_parser_rt_reset(struct ice_parser_rt *rt); +void ice_parser_rt_pktbuf_set(struct ice_parser_rt *rt, const u8 *pkt_buf, + int pkt_len); +int ice_parser_rt_execute(struct ice_parser_rt *rt, + struct ice_parser_result *rslt); + +struct ice_parser { + struct ice_hw *hw; /* pointer to the hardware structure */ + + struct ice_imem_item *imem_table; + struct ice_metainit_item *mi_table; + + struct ice_pg_cam_item *pg_cam_table; + struct ice_pg_cam_item *pg_sp_cam_table; + struct ice_pg_nm_cam_item *pg_nm_cam_table; + struct ice_pg_nm_cam_item *pg_nm_sp_cam_table; + + struct ice_bst_tcam_item *bst_tcam_table; + struct ice_lbl_item *bst_lbl_table; + struct ice_ptype_mk_tcam_item *ptype_mk_tcam_table; + struct ice_mk_grp_item *mk_grp_table; + struct ice_proto_grp_item *proto_grp_table; + struct ice_flg_rd_item *flg_rd_table; + + struct ice_xlt_kb *xlt_kb_sw; + struct ice_xlt_kb *xlt_kb_acl; + struct ice_xlt_kb *xlt_kb_fd; + struct ice_xlt_kb *xlt_kb_rss; + + struct ice_parser_rt rt; +}; + +struct ice_parser *ice_parser_create(struct ice_hw *hw); +void ice_parser_destroy(struct ice_parser *psr); +void ice_parser_dvm_set(struct ice_parser *psr, bool on); +int ice_parser_vxlan_tunnel_set(struct ice_parser *psr, u16 udp_port, bool on); +int ice_parser_geneve_tunnel_set(struct ice_parser *psr, u16 udp_port, bool on); +int ice_parser_ecpri_tunnel_set(struct ice_parser *psr, u16 udp_port, bool on); +int ice_parser_run(struct ice_parser *psr, const u8 *pkt_buf, + int pkt_len, struct ice_parser_result *rslt); +void ice_parser_result_dump(struct ice_hw *hw, struct ice_parser_result *rslt); + +struct ice_parser_fv { + u8 proto_id; /* hardware protocol ID */ + u16 offset; /* offset from the start of the protocol header */ + u16 spec; /* pattern to match */ + u16 msk; /* pattern mask */ +}; + +struct ice_parser_profile { + /* array of field vectors */ + struct ice_parser_fv fv[ICE_PARSER_FV_SIZE]; + int fv_num; /* # of field vectors must <= 48 */ + u16 flags; /* key builder flags */ + u16 flags_msk; /* key builder flag mask */ + + DECLARE_BITMAP(ptypes, ICE_FLOW_PTYPE_MAX); /* PTYPE bitmap */ +}; + +int ice_parser_profile_init(struct ice_parser_result *rslt, + const u8 *pkt_buf, const u8 *msk_buf, + int buf_len, enum ice_block blk, + struct ice_parser_profile *prof); +void ice_parser_profile_dump(struct ice_hw *hw, + struct ice_parser_profile *prof); +#endif /* _ICE_PARSER_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_parser_rt.c b/drivers/net/ethernet/intel/ice/ice_parser_rt.c new file mode 100644 index 000000000000..dedf5e854e4b --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_parser_rt.c @@ -0,0 +1,861 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2024 Intel Corporation */ + +#include "ice_common.h" + +static void ice_rt_tsr_set(struct ice_parser_rt *rt, u16 tsr) +{ + rt->gpr[ICE_GPR_TSR_IDX] = tsr; +} + +static void ice_rt_ho_set(struct ice_parser_rt *rt, u16 ho) +{ + rt->gpr[ICE_GPR_HO_IDX] = ho; + memcpy(&rt->gpr[ICE_GPR_HV_IDX], &rt->pkt_buf[ho], ICE_GPR_HV_SIZE); +} + +static void ice_rt_np_set(struct ice_parser_rt *rt, u16 pc) +{ + rt->gpr[ICE_GPR_NP_IDX] = pc; +} + +static void ice_rt_nn_set(struct ice_parser_rt *rt, u16 node) +{ + rt->gpr[ICE_GPR_NN_IDX] = node; +} + +static void +ice_rt_flag_set(struct ice_parser_rt *rt, unsigned int idx, bool set) +{ + struct ice_hw *hw = rt->psr->hw; + unsigned int word, id; + + word = idx / ICE_GPR_FLG_SIZE; + id = idx % ICE_GPR_FLG_SIZE; + + if (set) { + rt->gpr[ICE_GPR_FLG_IDX + word] |= (u16)BIT(id); + ice_debug(hw, ICE_DBG_PARSER, "Set parser flag %u\n", idx); + } else { + rt->gpr[ICE_GPR_FLG_IDX + word] &= ~(u16)BIT(id); + ice_debug(hw, ICE_DBG_PARSER, "Clear parser flag %u\n", idx); + } +} + +static void ice_rt_gpr_set(struct ice_parser_rt *rt, int idx, u16 val) +{ + struct ice_hw *hw = rt->psr->hw; + + if (idx == ICE_GPR_HO_IDX) + ice_rt_ho_set(rt, val); + else + rt->gpr[idx] = val; + + ice_debug(hw, ICE_DBG_PARSER, "Set GPR %d value %d\n", idx, val); +} + +static void ice_rt_err_set(struct ice_parser_rt *rt, unsigned int idx, bool set) +{ + struct ice_hw *hw = rt->psr->hw; + + if (set) { + rt->gpr[ICE_GPR_ERR_IDX] |= (u16)BIT(idx); + ice_debug(hw, ICE_DBG_PARSER, "Set parser error %u\n", idx); + } else { + rt->gpr[ICE_GPR_ERR_IDX] &= ~(u16)BIT(idx); + ice_debug(hw, ICE_DBG_PARSER, "Reset parser error %u\n", idx); + } +} + +/** + * ice_parser_rt_reset - reset the parser runtime + * @rt: pointer to the parser runtime + */ +void ice_parser_rt_reset(struct ice_parser_rt *rt) +{ + struct ice_parser *psr = rt->psr; + struct ice_metainit_item *mi; + unsigned int i; + + mi = &psr->mi_table[0]; + + memset(rt, 0, sizeof(*rt)); + rt->psr = psr; + + ice_rt_tsr_set(rt, mi->tsr); + ice_rt_ho_set(rt, mi->ho); + ice_rt_np_set(rt, mi->pc); + ice_rt_nn_set(rt, mi->pg_rn); + + for (i = 0; i < ICE_PARSER_FLG_NUM; i++) { + if (mi->flags & BIT(i)) + ice_rt_flag_set(rt, i, true); + } +} + +/** + * ice_parser_rt_pktbuf_set - set a packet into parser runtime + * @rt: pointer to the parser runtime + * @pkt_buf: buffer with packet data + * @pkt_len: packet buffer length + */ +void ice_parser_rt_pktbuf_set(struct ice_parser_rt *rt, const u8 *pkt_buf, + int pkt_len) +{ + int len = min(ICE_PARSER_MAX_PKT_LEN, pkt_len); + u16 ho = rt->gpr[ICE_GPR_HO_IDX]; + + memcpy(rt->pkt_buf, pkt_buf, len); + rt->pkt_len = pkt_len; + + memcpy(&rt->gpr[ICE_GPR_HV_IDX], &rt->pkt_buf[ho], ICE_GPR_HV_SIZE); +} + +static void ice_bst_key_init(struct ice_parser_rt *rt, + struct ice_imem_item *imem) +{ + u8 tsr = (u8)rt->gpr[ICE_GPR_TSR_IDX]; + u16 ho = rt->gpr[ICE_GPR_HO_IDX]; + u8 *key = rt->bst_key; + int idd, i; + + idd = ICE_BST_TCAM_KEY_SIZE - 1; + if (imem->b_kb.tsr_ctrl) + key[idd] = tsr; + else + key[idd] = imem->b_kb.prio; + + idd = ICE_BST_KEY_TCAM_SIZE - 1; + for (i = idd; i >= 0; i--) { + int j; + + j = ho + idd - i; + if (j < ICE_PARSER_MAX_PKT_LEN) + key[i] = rt->pkt_buf[ho + idd - i]; + else + key[i] = 0; + } + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Generated Boost TCAM Key:\n"); + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "%02X %02X %02X %02X %02X %02X %02X %02X %02X %02X\n", + key[0], key[1], key[2], key[3], key[4], + key[5], key[6], key[7], key[8], key[9]); + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "\n"); +} + +static u16 ice_bit_rev_u16(u16 v, int len) +{ + return bitrev16(v) >> (BITS_PER_TYPE(v) - len); +} + +static u32 ice_bit_rev_u32(u32 v, int len) +{ + return bitrev32(v) >> (BITS_PER_TYPE(v) - len); +} + +static u32 ice_hv_bit_sel(struct ice_parser_rt *rt, int start, int len) +{ + int offset; + u32 buf[2]; + u64 val; + + offset = ICE_GPR_HV_IDX + (start / BITS_PER_TYPE(u16)); + + memcpy(buf, &rt->gpr[offset], sizeof(buf)); + + buf[0] = bitrev8x4(buf[0]); + buf[1] = bitrev8x4(buf[1]); + + val = *(u64 *)buf; + val >>= start % BITS_PER_TYPE(u16); + + return ice_bit_rev_u32(val, len); +} + +static u32 ice_pk_build(struct ice_parser_rt *rt, + struct ice_np_keybuilder *kb) +{ + if (kb->opc == ICE_NPKB_OPC_EXTRACT) + return ice_hv_bit_sel(rt, kb->start_reg0, kb->len_reg1); + else if (kb->opc == ICE_NPKB_OPC_BUILD) + return rt->gpr[kb->start_reg0] | + ((u32)rt->gpr[kb->len_reg1] << BITS_PER_TYPE(u16)); + else if (kb->opc == ICE_NPKB_OPC_BYPASS) + return 0; + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Unsupported OP Code %u\n", + kb->opc); + return U32_MAX; +} + +static bool ice_flag_get(struct ice_parser_rt *rt, unsigned int index) +{ + int word = index / ICE_GPR_FLG_SIZE; + int id = index % ICE_GPR_FLG_SIZE; + + return !!(rt->gpr[ICE_GPR_FLG_IDX + word] & (u16)BIT(id)); +} + +static int ice_imem_pgk_init(struct ice_parser_rt *rt, + struct ice_imem_item *imem) +{ + memset(&rt->pg_key, 0, sizeof(rt->pg_key)); + rt->pg_key.next_proto = ice_pk_build(rt, &imem->np_kb); + if (rt->pg_key.next_proto == U32_MAX) + return -EINVAL; + + if (imem->pg_kb.flag0_ena) + rt->pg_key.flag0 = ice_flag_get(rt, imem->pg_kb.flag0_idx); + if (imem->pg_kb.flag1_ena) + rt->pg_key.flag1 = ice_flag_get(rt, imem->pg_kb.flag1_idx); + if (imem->pg_kb.flag2_ena) + rt->pg_key.flag2 = ice_flag_get(rt, imem->pg_kb.flag2_idx); + if (imem->pg_kb.flag3_ena) + rt->pg_key.flag3 = ice_flag_get(rt, imem->pg_kb.flag3_idx); + + rt->pg_key.alu_reg = rt->gpr[imem->pg_kb.alu_reg_idx]; + rt->pg_key.node_id = rt->gpr[ICE_GPR_NN_IDX]; + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Generate Parse Graph Key: node_id(%d), flag0-3(%d,%d,%d,%d), boost_idx(%d), alu_reg(0x%04x), next_proto(0x%08x)\n", + rt->pg_key.node_id, + rt->pg_key.flag0, + rt->pg_key.flag1, + rt->pg_key.flag2, + rt->pg_key.flag3, + rt->pg_key.boost_idx, + rt->pg_key.alu_reg, + rt->pg_key.next_proto); + + return 0; +} + +static void ice_imem_alu0_set(struct ice_parser_rt *rt, + struct ice_imem_item *imem) +{ + rt->alu0 = &imem->alu0; + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Load ALU0 from imem pc %d\n", + imem->idx); +} + +static void ice_imem_alu1_set(struct ice_parser_rt *rt, + struct ice_imem_item *imem) +{ + rt->alu1 = &imem->alu1; + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Load ALU1 from imem pc %d\n", + imem->idx); +} + +static void ice_imem_alu2_set(struct ice_parser_rt *rt, + struct ice_imem_item *imem) +{ + rt->alu2 = &imem->alu2; + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Load ALU2 from imem pc %d\n", + imem->idx); +} + +static void ice_imem_pgp_set(struct ice_parser_rt *rt, + struct ice_imem_item *imem) +{ + rt->pg_prio = imem->pg_prio; + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Load PG priority %d from imem pc %d\n", + rt->pg_prio, imem->idx); +} + +static int ice_bst_pgk_init(struct ice_parser_rt *rt, + struct ice_bst_tcam_item *bst) +{ + memset(&rt->pg_key, 0, sizeof(rt->pg_key)); + rt->pg_key.boost_idx = bst->hit_idx_grp; + rt->pg_key.next_proto = ice_pk_build(rt, &bst->np_kb); + if (rt->pg_key.next_proto == U32_MAX) + return -EINVAL; + + if (bst->pg_kb.flag0_ena) + rt->pg_key.flag0 = ice_flag_get(rt, bst->pg_kb.flag0_idx); + if (bst->pg_kb.flag1_ena) + rt->pg_key.flag1 = ice_flag_get(rt, bst->pg_kb.flag1_idx); + if (bst->pg_kb.flag2_ena) + rt->pg_key.flag2 = ice_flag_get(rt, bst->pg_kb.flag2_idx); + if (bst->pg_kb.flag3_ena) + rt->pg_key.flag3 = ice_flag_get(rt, bst->pg_kb.flag3_idx); + + rt->pg_key.alu_reg = rt->gpr[bst->pg_kb.alu_reg_idx]; + rt->pg_key.node_id = rt->gpr[ICE_GPR_NN_IDX]; + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Generate Parse Graph Key: node_id(%d), flag0-3(%d,%d,%d,%d), boost_idx(%d), alu_reg(0x%04x), next_proto(0x%08x)\n", + rt->pg_key.node_id, + rt->pg_key.flag0, + rt->pg_key.flag1, + rt->pg_key.flag2, + rt->pg_key.flag3, + rt->pg_key.boost_idx, + rt->pg_key.alu_reg, + rt->pg_key.next_proto); + + return 0; +} + +static void ice_bst_alu0_set(struct ice_parser_rt *rt, + struct ice_bst_tcam_item *bst) +{ + rt->alu0 = &bst->alu0; + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Load ALU0 from boost address %d\n", + bst->addr); +} + +static void ice_bst_alu1_set(struct ice_parser_rt *rt, + struct ice_bst_tcam_item *bst) +{ + rt->alu1 = &bst->alu1; + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Load ALU1 from boost address %d\n", + bst->addr); +} + +static void ice_bst_alu2_set(struct ice_parser_rt *rt, + struct ice_bst_tcam_item *bst) +{ + rt->alu2 = &bst->alu2; + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Load ALU2 from boost address %d\n", + bst->addr); +} + +static void ice_bst_pgp_set(struct ice_parser_rt *rt, + struct ice_bst_tcam_item *bst) +{ + rt->pg_prio = bst->pg_prio; + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Load PG priority %d from boost address %d\n", + rt->pg_prio, bst->addr); +} + +static struct ice_pg_cam_item *ice_rt_pg_cam_match(struct ice_parser_rt *rt) +{ + struct ice_parser *psr = rt->psr; + struct ice_pg_cam_item *item; + + item = ice_pg_cam_match(psr->pg_cam_table, ICE_PG_CAM_TABLE_SIZE, + &rt->pg_key); + if (!item) + item = ice_pg_cam_match(psr->pg_sp_cam_table, + ICE_PG_SP_CAM_TABLE_SIZE, &rt->pg_key); + return item; +} + +static +struct ice_pg_nm_cam_item *ice_rt_pg_nm_cam_match(struct ice_parser_rt *rt) +{ + struct ice_parser *psr = rt->psr; + struct ice_pg_nm_cam_item *item; + + item = ice_pg_nm_cam_match(psr->pg_nm_cam_table, + ICE_PG_NM_CAM_TABLE_SIZE, &rt->pg_key); + + if (!item) + item = ice_pg_nm_cam_match(psr->pg_nm_sp_cam_table, + ICE_PG_NM_SP_CAM_TABLE_SIZE, + &rt->pg_key); + return item; +} + +static void ice_gpr_add(struct ice_parser_rt *rt, int idx, u16 val) +{ + rt->pu.gpr_val_upd[idx] = true; + rt->pu.gpr_val[idx] = val; + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Pending update for register %d value %d\n", + idx, val); +} + +static void ice_pg_exe(struct ice_parser_rt *rt) +{ + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Executing ParseGraph action ...\n"); + + ice_gpr_add(rt, ICE_GPR_NP_IDX, rt->action->next_pc); + ice_gpr_add(rt, ICE_GPR_NN_IDX, rt->action->next_node); + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Executing ParseGraph action done.\n"); +} + +static void ice_flg_add(struct ice_parser_rt *rt, int idx, bool val) +{ + rt->pu.flg_msk |= BIT_ULL(idx); + if (val) + rt->pu.flg_val |= BIT_ULL(idx); + else + rt->pu.flg_val &= ~BIT_ULL(idx); + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Pending update for flag %d value %d\n", + idx, val); +} + +static void ice_flg_update(struct ice_parser_rt *rt, struct ice_alu *alu) +{ + u32 hv_bit_sel; + int i; + + if (!alu->dedicate_flags_ena) + return; + + if (alu->flags_extr_imm) { + for (i = 0; i < alu->dst_len; i++) + ice_flg_add(rt, alu->dst_start + i, + !!(alu->flags_start_imm & BIT(i))); + } else { + for (i = 0; i < alu->dst_len; i++) { + hv_bit_sel = ice_hv_bit_sel(rt, + alu->flags_start_imm + i, + 1); + ice_flg_add(rt, alu->dst_start + i, !!hv_bit_sel); + } + } +} + +static void ice_po_update(struct ice_parser_rt *rt, struct ice_alu *alu) +{ + if (alu->proto_offset_opc == ICE_PO_OFF_HDR_ADD) + rt->po = (u16)(rt->gpr[ICE_GPR_HO_IDX] + alu->proto_offset); + else if (alu->proto_offset_opc == ICE_PO_OFF_HDR_SUB) + rt->po = (u16)(rt->gpr[ICE_GPR_HO_IDX] - alu->proto_offset); + else if (alu->proto_offset_opc == ICE_PO_OFF_REMAIN) + rt->po = rt->gpr[ICE_GPR_HO_IDX]; + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Update Protocol Offset = %d\n", + rt->po); +} + +static u16 ice_reg_bit_sel(struct ice_parser_rt *rt, int reg_idx, + int start, int len) +{ + int offset; + u32 val; + + offset = ICE_GPR_HV_IDX + (start / BITS_PER_TYPE(u16)); + + memcpy(&val, &rt->gpr[offset], sizeof(val)); + + val = bitrev8x4(val); + val >>= start % BITS_PER_TYPE(u16); + + return ice_bit_rev_u16(val, len); +} + +static void ice_err_add(struct ice_parser_rt *rt, int idx, bool val) +{ + rt->pu.err_msk |= (u16)BIT(idx); + if (val) + rt->pu.flg_val |= (u64)BIT_ULL(idx); + else + rt->pu.flg_val &= ~(u64)BIT_ULL(idx); + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Pending update for error %d value %d\n", + idx, val); +} + +static void ice_dst_reg_bit_set(struct ice_parser_rt *rt, struct ice_alu *alu, + bool val) +{ + u16 flg_idx; + + if (alu->dedicate_flags_ena) { + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "DedicatedFlagsEnable should not be enabled in opcode %d\n", + alu->opc); + return; + } + + if (alu->dst_reg_id == ICE_GPR_ERR_IDX) { + if (alu->dst_start >= ICE_PARSER_ERR_NUM) { + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Invalid error %d\n", + alu->dst_start); + return; + } + ice_err_add(rt, alu->dst_start, val); + } else if (alu->dst_reg_id >= ICE_GPR_FLG_IDX) { + flg_idx = (u16)(((alu->dst_reg_id - ICE_GPR_FLG_IDX) << 4) + + alu->dst_start); + + if (flg_idx >= ICE_PARSER_FLG_NUM) { + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Invalid flag %d\n", + flg_idx); + return; + } + ice_flg_add(rt, flg_idx, val); + } else { + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Unexpected Dest Register Bit set, RegisterID %d Start %d\n", + alu->dst_reg_id, alu->dst_start); + } +} + +static void ice_alu_exe(struct ice_parser_rt *rt, struct ice_alu *alu) +{ + u16 dst, src, shift, imm; + + if (alu->shift_xlate_sel) { + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "shift_xlate_sel != 0 is not expected\n"); + return; + } + + ice_po_update(rt, alu); + ice_flg_update(rt, alu); + + dst = rt->gpr[alu->dst_reg_id]; + src = ice_reg_bit_sel(rt, alu->src_reg_id, + alu->src_start, alu->src_len); + shift = alu->shift_xlate_key; + imm = alu->imm; + + switch (alu->opc) { + case ICE_ALU_PARK: + break; + case ICE_ALU_MOV_ADD: + dst = (src << shift) + imm; + ice_gpr_add(rt, alu->dst_reg_id, dst); + break; + case ICE_ALU_ADD: + dst += (src << shift) + imm; + ice_gpr_add(rt, alu->dst_reg_id, dst); + break; + case ICE_ALU_ORLT: + if (src < imm) + ice_dst_reg_bit_set(rt, alu, true); + ice_gpr_add(rt, ICE_GPR_NP_IDX, alu->branch_addr); + break; + case ICE_ALU_OREQ: + if (src == imm) + ice_dst_reg_bit_set(rt, alu, true); + ice_gpr_add(rt, ICE_GPR_NP_IDX, alu->branch_addr); + break; + case ICE_ALU_SETEQ: + ice_dst_reg_bit_set(rt, alu, src == imm); + ice_gpr_add(rt, ICE_GPR_NP_IDX, alu->branch_addr); + break; + case ICE_ALU_MOV_XOR: + dst = (src << shift) ^ imm; + ice_gpr_add(rt, alu->dst_reg_id, dst); + break; + default: + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Unsupported ALU instruction %d\n", + alu->opc); + break; + } +} + +static void ice_alu0_exe(struct ice_parser_rt *rt) +{ + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Executing ALU0 ...\n"); + ice_alu_exe(rt, rt->alu0); + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Executing ALU0 done.\n"); +} + +static void ice_alu1_exe(struct ice_parser_rt *rt) +{ + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Executing ALU1 ...\n"); + ice_alu_exe(rt, rt->alu1); + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Executing ALU1 done.\n"); +} + +static void ice_alu2_exe(struct ice_parser_rt *rt) +{ + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Executing ALU2 ...\n"); + ice_alu_exe(rt, rt->alu2); + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Executing ALU2 done.\n"); +} + +static void ice_pu_exe(struct ice_parser_rt *rt) +{ + struct ice_gpr_pu *pu = &rt->pu; + unsigned int i; + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Updating Registers ...\n"); + + for (i = 0; i < ICE_PARSER_GPR_NUM; i++) { + if (pu->gpr_val_upd[i]) + ice_rt_gpr_set(rt, i, pu->gpr_val[i]); + } + + for (i = 0; i < ICE_PARSER_FLG_NUM; i++) { + if (pu->flg_msk & BIT(i)) + ice_rt_flag_set(rt, i, pu->flg_val & BIT(i)); + } + + for (i = 0; i < ICE_PARSER_ERR_NUM; i++) { + if (pu->err_msk & BIT(i)) + ice_rt_err_set(rt, i, pu->err_val & BIT(i)); + } + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Updating Registers done.\n"); +} + +static void ice_alu_pg_exe(struct ice_parser_rt *rt) +{ + memset(&rt->pu, 0, sizeof(rt->pu)); + + switch (rt->pg_prio) { + case (ICE_PG_P0): + ice_pg_exe(rt); + ice_alu0_exe(rt); + ice_alu1_exe(rt); + ice_alu2_exe(rt); + break; + case (ICE_PG_P1): + ice_alu0_exe(rt); + ice_pg_exe(rt); + ice_alu1_exe(rt); + ice_alu2_exe(rt); + break; + case (ICE_PG_P2): + ice_alu0_exe(rt); + ice_alu1_exe(rt); + ice_pg_exe(rt); + ice_alu2_exe(rt); + break; + case (ICE_PG_P3): + ice_alu0_exe(rt); + ice_alu1_exe(rt); + ice_alu2_exe(rt); + ice_pg_exe(rt); + break; + } + + ice_pu_exe(rt); + + if (rt->action->ho_inc == 0) + return; + + if (rt->action->ho_polarity) + ice_rt_ho_set(rt, rt->gpr[ICE_GPR_HO_IDX] + rt->action->ho_inc); + else + ice_rt_ho_set(rt, rt->gpr[ICE_GPR_HO_IDX] - rt->action->ho_inc); +} + +static void ice_proto_off_update(struct ice_parser_rt *rt) +{ + struct ice_parser *psr = rt->psr; + + if (rt->action->is_pg) { + struct ice_proto_grp_item *proto_grp = + &psr->proto_grp_table[rt->action->proto_id]; + u16 po; + int i; + + for (i = 0; i < ICE_PROTO_COUNT_PER_GRP; i++) { + struct ice_proto_off *entry = &proto_grp->po[i]; + + if (entry->proto_id == U8_MAX) + break; + + if (!entry->polarity) + po = rt->po + entry->offset; + else + po = rt->po - entry->offset; + + rt->protocols[entry->proto_id] = true; + rt->offsets[entry->proto_id] = po; + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Set Protocol %d at offset %d\n", + entry->proto_id, po); + } + } else { + rt->protocols[rt->action->proto_id] = true; + rt->offsets[rt->action->proto_id] = rt->po; + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Set Protocol %d at offset %d\n", + rt->action->proto_id, rt->po); + } +} + +static void ice_marker_set(struct ice_parser_rt *rt, int idx) +{ + unsigned int byte = idx / BITS_PER_BYTE; + unsigned int bit = idx % BITS_PER_BYTE; + + rt->markers[byte] |= (u8)BIT(bit); +} + +static void ice_marker_update(struct ice_parser_rt *rt) +{ + struct ice_parser *psr = rt->psr; + + if (rt->action->is_mg) { + struct ice_mk_grp_item *mk_grp = + &psr->mk_grp_table[rt->action->marker_id]; + int i; + + for (i = 0; i < ICE_MARKER_ID_NUM; i++) { + u8 marker = mk_grp->markers[i]; + + if (marker == ICE_MARKER_MAX_SIZE) + break; + + ice_marker_set(rt, marker); + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Set Marker %d\n", + marker); + } + } else { + if (rt->action->marker_id != ICE_MARKER_MAX_SIZE) + ice_marker_set(rt, rt->action->marker_id); + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Set Marker %d\n", + rt->action->marker_id); + } +} + +static u16 ice_ptype_resolve(struct ice_parser_rt *rt) +{ + struct ice_ptype_mk_tcam_item *item; + struct ice_parser *psr = rt->psr; + + item = ice_ptype_mk_tcam_match(psr->ptype_mk_tcam_table, + rt->markers, ICE_MARKER_ID_SIZE); + if (item) + return item->ptype; + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Could not resolve PTYPE\n"); + return U16_MAX; +} + +static void ice_proto_off_resolve(struct ice_parser_rt *rt, + struct ice_parser_result *rslt) +{ + int i; + + for (i = 0; i < ICE_PO_PAIR_SIZE - 1; i++) { + if (rt->protocols[i]) { + rslt->po[rslt->po_num].proto_id = (u8)i; + rslt->po[rslt->po_num].offset = rt->offsets[i]; + rslt->po_num++; + } + } +} + +static void ice_result_resolve(struct ice_parser_rt *rt, + struct ice_parser_result *rslt) +{ + struct ice_parser *psr = rt->psr; + + memset(rslt, 0, sizeof(*rslt)); + + memcpy(&rslt->flags_psr, &rt->gpr[ICE_GPR_FLG_IDX], + ICE_PARSER_FLAG_PSR_SIZE); + rslt->flags_pkt = ice_flg_redirect(psr->flg_rd_table, rslt->flags_psr); + rslt->flags_sw = ice_xlt_kb_flag_get(psr->xlt_kb_sw, rslt->flags_pkt); + rslt->flags_fd = ice_xlt_kb_flag_get(psr->xlt_kb_fd, rslt->flags_pkt); + rslt->flags_rss = ice_xlt_kb_flag_get(psr->xlt_kb_rss, rslt->flags_pkt); + + ice_proto_off_resolve(rt, rslt); + rslt->ptype = ice_ptype_resolve(rt); +} + +/** + * ice_parser_rt_execute - parser execution routine + * @rt: pointer to the parser runtime + * @rslt: input/output parameter to save parser result + * + * Return: 0 on success or errno. + */ +int ice_parser_rt_execute(struct ice_parser_rt *rt, + struct ice_parser_result *rslt) +{ + struct ice_pg_nm_cam_item *pg_nm_cam; + struct ice_parser *psr = rt->psr; + struct ice_pg_cam_item *pg_cam; + int status = 0; + u16 node; + u16 pc; + + node = rt->gpr[ICE_GPR_NN_IDX]; + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Start with Node: %u\n", node); + + while (true) { + struct ice_bst_tcam_item *bst; + struct ice_imem_item *imem; + + pc = rt->gpr[ICE_GPR_NP_IDX]; + imem = &psr->imem_table[pc]; + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Load imem at pc: %u\n", + pc); + + ice_bst_key_init(rt, imem); + bst = ice_bst_tcam_match(psr->bst_tcam_table, rt->bst_key); + if (!bst) { + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "No Boost TCAM Match\n"); + status = ice_imem_pgk_init(rt, imem); + if (status) + break; + ice_imem_alu0_set(rt, imem); + ice_imem_alu1_set(rt, imem); + ice_imem_alu2_set(rt, imem); + ice_imem_pgp_set(rt, imem); + } else { + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Boost TCAM Match address: %u\n", + bst->addr); + if (imem->b_m.pg) { + status = ice_bst_pgk_init(rt, bst); + if (status) + break; + ice_bst_pgp_set(rt, bst); + } else { + status = ice_imem_pgk_init(rt, imem); + if (status) + break; + ice_imem_pgp_set(rt, imem); + } + + if (imem->b_m.alu0) + ice_bst_alu0_set(rt, bst); + else + ice_imem_alu0_set(rt, imem); + + if (imem->b_m.alu1) + ice_bst_alu1_set(rt, bst); + else + ice_imem_alu1_set(rt, imem); + + if (imem->b_m.alu2) + ice_bst_alu2_set(rt, bst); + else + ice_imem_alu2_set(rt, imem); + } + + rt->action = NULL; + pg_cam = ice_rt_pg_cam_match(rt); + if (!pg_cam) { + pg_nm_cam = ice_rt_pg_nm_cam_match(rt); + if (pg_nm_cam) { + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Match ParseGraph Nomatch CAM Address %u\n", + pg_nm_cam->idx); + rt->action = &pg_nm_cam->action; + } + } else { + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Match ParseGraph CAM Address %u\n", + pg_cam->idx); + rt->action = &pg_cam->action; + } + + if (!rt->action) { + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Failed to match ParseGraph CAM, stop parsing.\n"); + status = -EINVAL; + break; + } + + ice_alu_pg_exe(rt); + ice_marker_update(rt); + ice_proto_off_update(rt); + + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Go to node %u\n", + rt->action->next_node); + + if (rt->action->is_last_round) { + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Last Round in ParseGraph Action, stop parsing.\n"); + break; + } + + if (rt->gpr[ICE_GPR_HO_IDX] >= rt->pkt_len) { + ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Header Offset (%u) is larger than packet len (%u), stop parsing\n", + rt->gpr[ICE_GPR_HO_IDX], rt->pkt_len); + break; + } + } + + ice_result_resolve(rt, rslt); + + return status; +} diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c index ecf8f5d60292..6ca13c5dcb14 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.c +++ b/drivers/net/ethernet/intel/ice/ice_sched.c @@ -28,9 +28,8 @@ ice_sched_add_root_node(struct ice_port_info *pi, if (!root) return -ENOMEM; - /* coverity[suspicious_sizeof] */ root->children = devm_kcalloc(ice_hw_to_dev(hw), hw->max_children[0], - sizeof(*root), GFP_KERNEL); + sizeof(*root->children), GFP_KERNEL); if (!root->children) { devm_kfree(ice_hw_to_dev(hw), root); return -ENOMEM; @@ -186,10 +185,9 @@ ice_sched_add_node(struct ice_port_info *pi, u8 layer, if (!node) return -ENOMEM; if (hw->max_children[layer]) { - /* coverity[suspicious_sizeof] */ node->children = devm_kcalloc(ice_hw_to_dev(hw), hw->max_children[layer], - sizeof(*node), GFP_KERNEL); + sizeof(*node->children), GFP_KERNEL); if (!node->children) { devm_kfree(ice_hw_to_dev(hw), node); return -ENOMEM; diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index 96037bef3e78..b9e443232335 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -61,6 +61,7 @@ static inline u32 ice_round_to_num(u32 N, u32 R) ICE_DBG_AQ_DESC | \ ICE_DBG_AQ_DESC_BUF | \ ICE_DBG_AQ_CMD) +#define ICE_DBG_PARSER BIT_ULL(28) #define ICE_DBG_USER BIT_ULL(31) diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.h b/drivers/net/ethernet/intel/ice/ice_vf_lib.h index fec16919ec19..be4266899690 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.h @@ -12,6 +12,7 @@ #include <net/devlink.h> #include <linux/avf/virtchnl.h> #include "ice_type.h" +#include "ice_flow.h" #include "ice_virtchnl_fdir.h" #include "ice_vsi_vlan_ops.h" @@ -52,6 +53,12 @@ struct ice_mdd_vf_events { u16 last_printed; }; +/* Structure to store fdir fv entry */ +struct ice_fdir_prof_info { + struct ice_parser_profile prof; + u64 fdir_active_cnt; +}; + /* VF operations */ struct ice_vf_ops { enum ice_disq_rst_src reset_type; @@ -91,6 +98,7 @@ struct ice_vf { u16 lan_vsi_idx; /* index into PF struct */ u16 ctrl_vsi_idx; struct ice_vf_fdir fdir; + struct ice_fdir_prof_info fdir_prof_info[ICE_MAX_PTGS]; /* first vector index of this VF in the PF space */ int first_vector_idx; struct ice_sw *vf_sw_id; /* switch ID the VF VSIs connect to */ diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index 1c6ce0c4ed4e..59f62306b9cb 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -461,6 +461,10 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_FDIR_PF) vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_FDIR_PF; + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_TC_U32 && + vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_FDIR_PF) + vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_TC_U32; + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2) vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2; diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c index b4feb0927687..14e3f0f89c78 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c @@ -26,6 +26,15 @@ enum ice_fdir_tunnel_type { ICE_FDIR_TUNNEL_TYPE_NONE = 0, ICE_FDIR_TUNNEL_TYPE_GTPU, ICE_FDIR_TUNNEL_TYPE_GTPU_EH, + ICE_FDIR_TUNNEL_TYPE_ECPRI, + ICE_FDIR_TUNNEL_TYPE_GTPU_INNER, + ICE_FDIR_TUNNEL_TYPE_GTPU_EH_INNER, + ICE_FDIR_TUNNEL_TYPE_GRE, + ICE_FDIR_TUNNEL_TYPE_GTPOGRE, + ICE_FDIR_TUNNEL_TYPE_GTPOGRE_INNER, + ICE_FDIR_TUNNEL_TYPE_GRE_INNER, + ICE_FDIR_TUNNEL_TYPE_L2TPV2, + ICE_FDIR_TUNNEL_TYPE_L2TPV2_INNER, }; struct virtchnl_fdir_fltr_conf { @@ -33,6 +42,11 @@ struct virtchnl_fdir_fltr_conf { enum ice_fdir_tunnel_type ttype; u64 inset_flag; u32 flow_id; + + struct ice_parser_profile *prof; + bool parser_ena; + u8 *pkt_buf; + u8 pkt_len; }; struct virtchnl_fdir_inset_map { @@ -787,6 +801,107 @@ err_exit: } /** + * ice_vc_fdir_is_raw_flow - check if FDIR flow is raw (binary) + * @proto: virtchnl protocol headers + * + * Check if the FDIR rule is raw flow (protocol agnostic flow) or not. Note + * that common FDIR rule must have non-zero proto->count. Thus, we choose the + * tunnel_level and count of proto as the indicators. If both tunnel_level and + * count of proto are zero, this FDIR rule will be regarded as raw flow. + * + * Returns: true if headers describe raw flow, false otherwise. + */ +static bool +ice_vc_fdir_is_raw_flow(struct virtchnl_proto_hdrs *proto) +{ + return (proto->tunnel_level == 0 && proto->count == 0); +} + +/** + * ice_vc_fdir_parse_raw - parse a virtchnl raw FDIR rule + * @vf: pointer to the VF info + * @proto: virtchnl protocol headers + * @conf: FDIR configuration for each filter + * + * Parse the virtual channel filter's raw flow and store it in @conf + * + * Return: 0 on success or negative errno on failure. + */ +static int +ice_vc_fdir_parse_raw(struct ice_vf *vf, + struct virtchnl_proto_hdrs *proto, + struct virtchnl_fdir_fltr_conf *conf) +{ + u8 *pkt_buf, *msk_buf __free(kfree); + struct ice_parser_result rslt; + struct ice_pf *pf = vf->pf; + struct ice_parser *psr; + int status = -ENOMEM; + struct ice_hw *hw; + u16 udp_port = 0; + + pkt_buf = kzalloc(proto->raw.pkt_len, GFP_KERNEL); + msk_buf = kzalloc(proto->raw.pkt_len, GFP_KERNEL); + if (!pkt_buf || !msk_buf) + goto err_mem_alloc; + + memcpy(pkt_buf, proto->raw.spec, proto->raw.pkt_len); + memcpy(msk_buf, proto->raw.mask, proto->raw.pkt_len); + + hw = &pf->hw; + + /* Get raw profile info via Parser Lib */ + psr = ice_parser_create(hw); + if (IS_ERR(psr)) { + status = PTR_ERR(psr); + goto err_mem_alloc; + } + + ice_parser_dvm_set(psr, ice_is_dvm_ena(hw)); + + if (ice_get_open_tunnel_port(hw, &udp_port, TNL_VXLAN)) + ice_parser_vxlan_tunnel_set(psr, udp_port, true); + + status = ice_parser_run(psr, pkt_buf, proto->raw.pkt_len, &rslt); + if (status) + goto err_parser_destroy; + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_parser_result_dump(hw, &rslt); + + conf->prof = kzalloc(sizeof(*conf->prof), GFP_KERNEL); + if (!conf->prof) { + status = -ENOMEM; + goto err_parser_destroy; + } + + status = ice_parser_profile_init(&rslt, pkt_buf, msk_buf, + proto->raw.pkt_len, ICE_BLK_FD, + conf->prof); + if (status) + goto err_parser_profile_init; + + if (hw->debug_mask & ICE_DBG_PARSER) + ice_parser_profile_dump(hw, conf->prof); + + /* Store raw flow info into @conf */ + conf->pkt_len = proto->raw.pkt_len; + conf->pkt_buf = pkt_buf; + conf->parser_ena = true; + + ice_parser_destroy(psr); + return 0; + +err_parser_profile_init: + kfree(conf->prof); +err_parser_destroy: + ice_parser_destroy(psr); +err_mem_alloc: + kfree(pkt_buf); + return status; +} + +/** * ice_vc_fdir_parse_pattern * @vf: pointer to the VF info * @fltr: virtual channel add cmd buffer @@ -813,6 +928,10 @@ ice_vc_fdir_parse_pattern(struct ice_vf *vf, struct virtchnl_fdir_add *fltr, return -EINVAL; } + /* For raw FDIR filters created by the parser */ + if (ice_vc_fdir_is_raw_flow(proto)) + return ice_vc_fdir_parse_raw(vf, proto, conf); + for (i = 0; i < proto->count; i++) { struct virtchnl_proto_hdr *hdr = &proto->proto_hdr[i]; struct ip_esp_hdr *esph; @@ -1101,8 +1220,10 @@ ice_vc_validate_fdir_fltr(struct ice_vf *vf, struct virtchnl_fdir_add *fltr, struct virtchnl_proto_hdrs *proto = &fltr->rule_cfg.proto_hdrs; int ret; - if (!ice_vc_validate_pattern(vf, proto)) - return -EINVAL; + /* For raw FDIR filters created by the parser */ + if (!ice_vc_fdir_is_raw_flow(proto)) + if (!ice_vc_validate_pattern(vf, proto)) + return -EINVAL; ret = ice_vc_fdir_parse_pattern(vf, fltr, conf); if (ret) @@ -1295,11 +1416,15 @@ static int ice_vc_fdir_write_fltr(struct ice_vf *vf, return -ENOMEM; ice_fdir_get_prgm_desc(hw, input, &desc, add); - ret = ice_fdir_get_gen_prgm_pkt(hw, input, pkt, false, is_tun); - if (ret) { - dev_dbg(dev, "Gen training pkt for VF %d ptype %d failed\n", - vf->vf_id, input->flow_type); - goto err_free_pkt; + if (conf->parser_ena) { + memcpy(pkt, conf->pkt_buf, conf->pkt_len); + } else { + ret = ice_fdir_get_gen_prgm_pkt(hw, input, pkt, false, is_tun); + if (ret) { + dev_dbg(dev, "Gen training pkt for VF %d ptype %d failed\n", + vf->vf_id, input->flow_type); + goto err_free_pkt; + } } ret = ice_prgm_fdir_fltr(ctrl_vsi, &desc, pkt); @@ -1521,6 +1646,16 @@ err_exit: return ret; } +static int ice_fdir_is_tunnel(enum ice_fdir_tunnel_type ttype) +{ + return (ttype == ICE_FDIR_TUNNEL_TYPE_GRE_INNER || + ttype == ICE_FDIR_TUNNEL_TYPE_GTPU_INNER || + ttype == ICE_FDIR_TUNNEL_TYPE_GTPU_EH_INNER || + ttype == ICE_FDIR_TUNNEL_TYPE_GTPOGRE_INNER || + ttype == ICE_FDIR_TUNNEL_TYPE_ECPRI || + ttype == ICE_FDIR_TUNNEL_TYPE_L2TPV2_INNER); +} + /** * ice_vc_add_fdir_fltr_post * @vf: pointer to the VF structure @@ -1782,6 +1917,158 @@ static void ice_vc_fdir_clear_irq_ctx(struct ice_vf *vf) } /** + * ice_vc_parser_fv_check_diff - check two parsed FDIR profile fv context + * @fv_a: struct of parsed FDIR profile field vector + * @fv_b: struct of parsed FDIR profile field vector + * + * Check if the two parsed FDIR profile field vector context are different, + * including proto_id, offset and mask. + * + * Return: true on different, false on otherwise. + */ +static bool ice_vc_parser_fv_check_diff(struct ice_parser_fv *fv_a, + struct ice_parser_fv *fv_b) +{ + return (fv_a->proto_id != fv_b->proto_id || + fv_a->offset != fv_b->offset || + fv_a->msk != fv_b->msk); +} + +/** + * ice_vc_parser_fv_save - save parsed FDIR profile fv context + * @fv: struct of parsed FDIR profile field vector + * @fv_src: parsed FDIR profile field vector context to save + * + * Save the parsed FDIR profile field vector context, including proto_id, + * offset and mask. + * + * Return: Void. + */ +static void ice_vc_parser_fv_save(struct ice_parser_fv *fv, + struct ice_parser_fv *fv_src) +{ + fv->proto_id = fv_src->proto_id; + fv->offset = fv_src->offset; + fv->msk = fv_src->msk; + fv->spec = 0; +} + +/** + * ice_vc_add_fdir_raw - add a raw FDIR filter for VF + * @vf: pointer to the VF info + * @conf: FDIR configuration for each filter + * @v_ret: the final VIRTCHNL code + * @stat: pointer to the VIRTCHNL_OP_ADD_FDIR_FILTER + * @len: length of the stat + * + * Return: 0 on success or negative errno on failure. + */ +static int +ice_vc_add_fdir_raw(struct ice_vf *vf, + struct virtchnl_fdir_fltr_conf *conf, + enum virtchnl_status_code *v_ret, + struct virtchnl_fdir_add *stat, int len) +{ + struct ice_vsi *vf_vsi, *ctrl_vsi; + struct ice_fdir_prof_info *pi; + struct ice_pf *pf = vf->pf; + int ret, ptg, id, i; + struct device *dev; + struct ice_hw *hw; + bool fv_found; + + dev = ice_pf_to_dev(pf); + hw = &pf->hw; + *v_ret = VIRTCHNL_STATUS_ERR_PARAM; + stat->status = VIRTCHNL_FDIR_FAILURE_RULE_NORESOURCE; + + id = find_first_bit(conf->prof->ptypes, ICE_FLOW_PTYPE_MAX); + ptg = hw->blk[ICE_BLK_FD].xlt1.t[id]; + + vf_vsi = ice_get_vf_vsi(vf); + if (!vf_vsi) { + dev_err(dev, "Can not get FDIR vf_vsi for VF %d\n", vf->vf_id); + return -ENODEV; + } + + ctrl_vsi = pf->vsi[vf->ctrl_vsi_idx]; + if (!ctrl_vsi) { + dev_err(dev, "Can not get FDIR ctrl_vsi for VF %d\n", + vf->vf_id); + return -ENODEV; + } + + fv_found = false; + + /* Check if profile info already exists, then update the counter */ + pi = &vf->fdir_prof_info[ptg]; + if (pi->fdir_active_cnt != 0) { + for (i = 0; i < ICE_MAX_FV_WORDS; i++) + if (ice_vc_parser_fv_check_diff(&pi->prof.fv[i], + &conf->prof->fv[i])) + break; + if (i == ICE_MAX_FV_WORDS) { + fv_found = true; + pi->fdir_active_cnt++; + } + } + + /* HW profile setting is only required for the first time */ + if (!fv_found) { + ret = ice_flow_set_parser_prof(hw, vf_vsi->idx, + ctrl_vsi->idx, conf->prof, + ICE_BLK_FD); + + if (ret) { + *v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY; + dev_dbg(dev, "VF %d: insert hw prof failed\n", + vf->vf_id); + return ret; + } + } + + ret = ice_vc_fdir_insert_entry(vf, conf, &conf->flow_id); + if (ret) { + *v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY; + dev_dbg(dev, "VF %d: insert FDIR list failed\n", + vf->vf_id); + return ret; + } + + ret = ice_vc_fdir_set_irq_ctx(vf, conf, + VIRTCHNL_OP_ADD_FDIR_FILTER); + if (ret) { + dev_dbg(dev, "VF %d: set FDIR context failed\n", + vf->vf_id); + goto err_rem_entry; + } + + ret = ice_vc_fdir_write_fltr(vf, conf, true, false); + if (ret) { + dev_err(dev, "VF %d: adding FDIR raw flow rule failed, ret:%d\n", + vf->vf_id, ret); + goto err_clr_irq; + } + + /* Save parsed profile fv info of the FDIR rule for the first time */ + if (!fv_found) { + for (i = 0; i < conf->prof->fv_num; i++) + ice_vc_parser_fv_save(&pi->prof.fv[i], + &conf->prof->fv[i]); + pi->prof.fv_num = conf->prof->fv_num; + pi->fdir_active_cnt = 1; + } + + return 0; + +err_clr_irq: + ice_vc_fdir_clear_irq_ctx(vf); +err_rem_entry: + ice_vc_fdir_remove_entry(vf, conf, conf->flow_id); + return ret; +} + +/** * ice_vc_add_fdir_fltr - add a FDIR filter for VF by the msg buffer * @vf: pointer to the VF info * @msg: pointer to the msg buffer @@ -1846,7 +2133,7 @@ int ice_vc_add_fdir_fltr(struct ice_vf *vf, u8 *msg) len = sizeof(*stat); ret = ice_vc_validate_fdir_fltr(vf, fltr, conf); if (ret) { - v_ret = VIRTCHNL_STATUS_SUCCESS; + v_ret = VIRTCHNL_STATUS_ERR_PARAM; stat->status = VIRTCHNL_FDIR_FAILURE_RULE_INVALID; dev_dbg(dev, "Invalid FDIR filter from VF %d\n", vf->vf_id); goto err_free_conf; @@ -1861,6 +2148,15 @@ int ice_vc_add_fdir_fltr(struct ice_vf *vf, u8 *msg) goto exit; } + /* For raw FDIR filters created by the parser */ + if (conf->parser_ena) { + ret = ice_vc_add_fdir_raw(vf, conf, &v_ret, stat, len); + if (ret) + goto err_free_conf; + goto exit; + } + + is_tun = ice_fdir_is_tunnel(conf->ttype); ret = ice_vc_fdir_config_input_set(vf, fltr, conf, is_tun); if (ret) { v_ret = VIRTCHNL_STATUS_SUCCESS; @@ -1922,6 +2218,78 @@ err_exit: } /** + * ice_vc_del_fdir_raw - delete a raw FDIR filter for VF + * @vf: pointer to the VF info + * @conf: FDIR configuration for each filter + * @v_ret: the final VIRTCHNL code + * @stat: pointer to the VIRTCHNL_OP_DEL_FDIR_FILTER + * @len: length of the stat + * + * Return: 0 on success or negative errno on failure. + */ +static int +ice_vc_del_fdir_raw(struct ice_vf *vf, + struct virtchnl_fdir_fltr_conf *conf, + enum virtchnl_status_code *v_ret, + struct virtchnl_fdir_del *stat, int len) +{ + struct ice_vsi *vf_vsi, *ctrl_vsi; + enum ice_block blk = ICE_BLK_FD; + struct ice_fdir_prof_info *pi; + struct ice_pf *pf = vf->pf; + struct device *dev; + struct ice_hw *hw; + unsigned long id; + u16 vsi_num; + int ptg; + int ret; + + dev = ice_pf_to_dev(pf); + hw = &pf->hw; + *v_ret = VIRTCHNL_STATUS_ERR_PARAM; + stat->status = VIRTCHNL_FDIR_FAILURE_RULE_NORESOURCE; + + id = find_first_bit(conf->prof->ptypes, ICE_FLOW_PTYPE_MAX); + ptg = hw->blk[ICE_BLK_FD].xlt1.t[id]; + + ret = ice_vc_fdir_write_fltr(vf, conf, false, false); + if (ret) { + dev_err(dev, "VF %u: deleting FDIR raw flow rule failed: %d\n", + vf->vf_id, ret); + return ret; + } + + vf_vsi = ice_get_vf_vsi(vf); + if (!vf_vsi) { + dev_err(dev, "Can not get FDIR vf_vsi for VF %u\n", vf->vf_id); + return -ENODEV; + } + + ctrl_vsi = pf->vsi[vf->ctrl_vsi_idx]; + if (!ctrl_vsi) { + dev_err(dev, "Can not get FDIR ctrl_vsi for VF %u\n", + vf->vf_id); + return -ENODEV; + } + + pi = &vf->fdir_prof_info[ptg]; + if (pi->fdir_active_cnt != 0) { + pi->fdir_active_cnt--; + /* Remove the profile id flow if no active FDIR rule left */ + if (!pi->fdir_active_cnt) { + vsi_num = ice_get_hw_vsi_num(hw, ctrl_vsi->idx); + ice_rem_prof_id_flow(hw, blk, vsi_num, id); + + vsi_num = ice_get_hw_vsi_num(hw, vf_vsi->idx); + ice_rem_prof_id_flow(hw, blk, vsi_num, id); + } + } + + conf->parser_ena = false; + return 0; +} + +/** * ice_vc_del_fdir_fltr - delete a FDIR filter for VF by the msg buffer * @vf: pointer to the VF info * @msg: pointer to the msg buffer @@ -1933,7 +2301,10 @@ int ice_vc_del_fdir_fltr(struct ice_vf *vf, u8 *msg) struct virtchnl_fdir_del *fltr = (struct virtchnl_fdir_del *)msg; struct virtchnl_fdir_del *stat = NULL; struct virtchnl_fdir_fltr_conf *conf; + struct ice_vf_fdir *fdir = &vf->fdir; enum virtchnl_status_code v_ret; + struct ice_fdir_fltr *input; + enum ice_fltr_ptype flow; struct device *dev; struct ice_pf *pf; int is_tun = 0; @@ -1983,6 +2354,15 @@ int ice_vc_del_fdir_fltr(struct ice_vf *vf, u8 *msg) goto err_exit; } + /* For raw FDIR filters created by the parser */ + if (conf->parser_ena) { + ret = ice_vc_del_fdir_raw(vf, conf, &v_ret, stat, len); + if (ret) + goto err_del_tmr; + goto exit; + } + + is_tun = ice_fdir_is_tunnel(conf->ttype); ret = ice_vc_fdir_write_fltr(vf, conf, false, is_tun); if (ret) { v_ret = VIRTCHNL_STATUS_SUCCESS; @@ -1992,6 +2372,13 @@ int ice_vc_del_fdir_fltr(struct ice_vf *vf, u8 *msg) goto err_del_tmr; } + /* Remove unused profiles to avoid unexpected behaviors */ + input = &conf->input; + flow = input->flow_type; + if (fdir->fdir_fltr_cnt[flow][is_tun] == 1) + ice_vc_fdir_rem_prof(vf, flow, is_tun); + +exit: kfree(stat); return ret; diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c index 0b6c8fd5bc90..4f20343e49a9 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_lib.c +++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c @@ -357,24 +357,11 @@ int idpf_intr_req(struct idpf_adapter *adapter) goto free_msix; } - if (adapter->req_vec_chunks) { - struct virtchnl2_vector_chunks *vchunks; - struct virtchnl2_alloc_vectors *ac; - - ac = adapter->req_vec_chunks; - vchunks = &ac->vchunks; - - num_vec_ids = idpf_get_vec_ids(adapter, vecids, total_vecs, - vchunks); - if (num_vec_ids < v_actual) { - err = -EINVAL; - goto free_vecids; - } - } else { - int i; - - for (i = 0; i < v_actual; i++) - vecids[i] = i; + num_vec_ids = idpf_get_vec_ids(adapter, vecids, total_vecs, + &adapter->req_vec_chunks->vchunks); + if (num_vec_ids < v_actual) { + err = -EINVAL; + goto free_vecids; } for (vector = 0; vector < v_actual; vector++) { diff --git a/drivers/net/ethernet/intel/igbvf/igbvf.h b/drivers/net/ethernet/intel/igbvf/igbvf.h index 7b83678ba83a..6ad35a00a287 100644 --- a/drivers/net/ethernet/intel/igbvf/igbvf.h +++ b/drivers/net/ethernet/intel/igbvf/igbvf.h @@ -282,7 +282,6 @@ enum igbvf_state_t { extern char igbvf_driver_name[]; -void igbvf_check_options(struct igbvf_adapter *); void igbvf_set_ethtool_ops(struct net_device *); int igbvf_up(struct igbvf_adapter *); diff --git a/drivers/net/ethernet/intel/igbvf/mbx.h b/drivers/net/ethernet/intel/igbvf/mbx.h index e5b31818d565..7637d21445bf 100644 --- a/drivers/net/ethernet/intel/igbvf/mbx.h +++ b/drivers/net/ethernet/intel/igbvf/mbx.h @@ -49,7 +49,6 @@ #define E1000_PF_CONTROL_MSG 0x0100 /* PF control message */ -void e1000_init_mbx_ops_generic(struct e1000_hw *hw); s32 e1000_init_mbx_params_vf(struct e1000_hw *); #endif /* _E1000_MBX_H_ */ diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c index 9e6984815386..3c289bfe0a09 100644 --- a/drivers/net/ethernet/lantiq_etop.c +++ b/drivers/net/ethernet/lantiq_etop.c @@ -95,7 +95,6 @@ struct ltq_etop_priv { struct mii_bus *mii_bus; struct ltq_etop_chan ch[MAX_DMA_CHAN]; - int tx_free[MAX_DMA_CHAN >> 1]; int tx_burst_len; int rx_burst_len; diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 41894834fb53..d72b2d5f96db 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -1781,7 +1781,7 @@ static int mvneta_txq_sent_desc_proc(struct mvneta_port *pp, } /* Set TXQ descriptors fields relevant for CSUM calculation */ -static u32 mvneta_txq_desc_csum(int l3_offs, int l3_proto, +static u32 mvneta_txq_desc_csum(int l3_offs, __be16 l3_proto, int ip_hdr_len, int l4_proto) { u32 command; diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h index e809f91c08fb..9e02e4367bec 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h @@ -1088,7 +1088,7 @@ struct mvpp2 { unsigned int max_port_rxqs; /* Workqueue to gather hardware statistics */ - char queue_name[30]; + char queue_name[31]; struct workqueue_struct *stats_queue; /* Debugfs root entry */ diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c index 40aeaa7bd739..1641791a2d5b 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c @@ -1522,29 +1522,19 @@ static int mvpp22_rss_context_create(struct mvpp2_port *port, u32 *rss_ctx) return 0; } -int mvpp22_port_rss_ctx_create(struct mvpp2_port *port, u32 *port_ctx) +int mvpp22_port_rss_ctx_create(struct mvpp2_port *port, u32 port_ctx) { u32 rss_ctx; - int ret, i; + int ret; ret = mvpp22_rss_context_create(port, &rss_ctx); if (ret) return ret; - /* Find the first available context number in the port, starting from 1. - * Context 0 on each port is reserved for the default context. - */ - for (i = 1; i < MVPP22_N_RSS_TABLES; i++) { - if (port->rss_ctx[i] < 0) - break; - } - - if (i == MVPP22_N_RSS_TABLES) + if (WARN_ON_ONCE(port->rss_ctx[port_ctx] >= 0)) return -EINVAL; - port->rss_ctx[i] = rss_ctx; - *port_ctx = i; - + port->rss_ctx[port_ctx] = rss_ctx; return 0; } diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h index 663157dc8062..85c9c6e80678 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h @@ -264,7 +264,7 @@ int mvpp22_port_rss_init(struct mvpp2_port *port); int mvpp22_port_rss_enable(struct mvpp2_port *port); int mvpp22_port_rss_disable(struct mvpp2_port *port); -int mvpp22_port_rss_ctx_create(struct mvpp2_port *port, u32 *rss_ctx); +int mvpp22_port_rss_ctx_create(struct mvpp2_port *port, u32 rss_ctx); int mvpp22_port_rss_ctx_delete(struct mvpp2_port *port, u32 rss_ctx); int mvpp22_port_rss_ctx_indir_set(struct mvpp2_port *port, u32 rss_ctx, diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 0d62a33afa80..2fe8bae4eb3c 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -5696,40 +5696,82 @@ static int mvpp2_ethtool_get_rxfh(struct net_device *dev, return ret; } -static int mvpp2_ethtool_set_rxfh(struct net_device *dev, - struct ethtool_rxfh_param *rxfh, - struct netlink_ext_ack *extack) +static bool mvpp2_ethtool_rxfh_okay(struct mvpp2_port *port, + const struct ethtool_rxfh_param *rxfh) { - struct mvpp2_port *port = netdev_priv(dev); - u32 *rss_context = &rxfh->rss_context; - int ret = 0; - if (!mvpp22_rss_is_supported(port)) - return -EOPNOTSUPP; + return false; if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE && rxfh->hfunc != ETH_RSS_HASH_CRC32) - return -EOPNOTSUPP; + return false; if (rxfh->key) + return false; + + return true; +} + +static int mvpp2_create_rxfh_context(struct net_device *dev, + struct ethtool_rxfh_context *ctx, + const struct ethtool_rxfh_param *rxfh, + struct netlink_ext_ack *extack) +{ + struct mvpp2_port *port = netdev_priv(dev); + int ret = 0; + + if (!mvpp2_ethtool_rxfh_okay(port, rxfh)) return -EOPNOTSUPP; - if (*rss_context && rxfh->rss_delete) - return mvpp22_port_rss_ctx_delete(port, *rss_context); + ctx->hfunc = ETH_RSS_HASH_CRC32; - if (*rss_context == ETH_RXFH_CONTEXT_ALLOC) { - ret = mvpp22_port_rss_ctx_create(port, rss_context); - if (ret) - return ret; - } + ret = mvpp22_port_rss_ctx_create(port, rxfh->rss_context); + if (ret) + return ret; - if (rxfh->indir) - ret = mvpp22_port_rss_ctx_indir_set(port, *rss_context, + if (!rxfh->indir) + ret = mvpp22_port_rss_ctx_indir_get(port, rxfh->rss_context, + ethtool_rxfh_context_indir(ctx)); + else + ret = mvpp22_port_rss_ctx_indir_set(port, rxfh->rss_context, rxfh->indir); + return ret; +} +static int mvpp2_modify_rxfh_context(struct net_device *dev, + struct ethtool_rxfh_context *ctx, + const struct ethtool_rxfh_param *rxfh, + struct netlink_ext_ack *extack) +{ + struct mvpp2_port *port = netdev_priv(dev); + int ret = 0; + + if (!mvpp2_ethtool_rxfh_okay(port, rxfh)) + return -EOPNOTSUPP; + + if (rxfh->indir) + ret = mvpp22_port_rss_ctx_indir_set(port, rxfh->rss_context, + rxfh->indir); return ret; } +static int mvpp2_remove_rxfh_context(struct net_device *dev, + struct ethtool_rxfh_context *ctx, + u32 rss_context, + struct netlink_ext_ack *extack) +{ + struct mvpp2_port *port = netdev_priv(dev); + + return mvpp22_port_rss_ctx_delete(port, rss_context); +} + +static int mvpp2_ethtool_set_rxfh(struct net_device *dev, + struct ethtool_rxfh_param *rxfh, + struct netlink_ext_ack *extack) +{ + return mvpp2_modify_rxfh_context(dev, NULL, rxfh, extack); +} + /* Device ops */ static const struct net_device_ops mvpp2_netdev_ops = { @@ -5749,7 +5791,7 @@ static const struct net_device_ops mvpp2_netdev_ops = { }; static const struct ethtool_ops mvpp2_eth_tool_ops = { - .cap_rss_ctx_supported = true, + .rxfh_max_num_contexts = MVPP22_N_RSS_TABLES, .supported_coalesce_params = ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_MAX_FRAMES, .nway_reset = mvpp2_ethtool_nway_reset, @@ -5772,6 +5814,9 @@ static const struct ethtool_ops mvpp2_eth_tool_ops = { .get_rxfh_indir_size = mvpp2_ethtool_get_rxfh_indir_size, .get_rxfh = mvpp2_ethtool_get_rxfh, .set_rxfh = mvpp2_ethtool_set_rxfh, + .create_rxfh_context = mvpp2_create_rxfh_context, + .modify_rxfh_context = mvpp2_modify_rxfh_context, + .remove_rxfh_context = mvpp2_remove_rxfh_context, }; /* Used for PPv2.1, or PPv2.2 with the old Device Tree binding that @@ -7417,8 +7462,6 @@ static int mvpp2_get_sram(struct platform_device *pdev, static int mvpp2_probe(struct platform_device *pdev) { - struct fwnode_handle *fwnode = pdev->dev.fwnode; - struct fwnode_handle *port_fwnode; struct mvpp2 *priv; struct resource *res; void __iomem *base; @@ -7591,7 +7634,7 @@ static int mvpp2_probe(struct platform_device *pdev) } /* Map DTS-active ports. Should be done before FIFO mvpp2_init */ - fwnode_for_each_available_child_node(fwnode, port_fwnode) { + device_for_each_child_node_scoped(&pdev->dev, port_fwnode) { if (!fwnode_property_read_u32(port_fwnode, "port-id", &i)) priv->port_map |= BIT(i); } @@ -7614,7 +7657,7 @@ static int mvpp2_probe(struct platform_device *pdev) goto err_axi_clk; /* Initialize ports */ - fwnode_for_each_available_child_node(fwnode, port_fwnode) { + device_for_each_child_node_scoped(&pdev->dev, port_fwnode) { err = mvpp2_port_probe(pdev, port_fwnode, priv); if (err < 0) goto err_port_probe; @@ -7653,14 +7696,8 @@ static int mvpp2_probe(struct platform_device *pdev) return 0; err_port_probe: - fwnode_handle_put(port_fwnode); - - i = 0; - fwnode_for_each_available_child_node(fwnode, port_fwnode) { - if (priv->port_list[i]) - mvpp2_port_remove(priv->port_list[i]); - i++; - } + for (i = 0; i < priv->port_count; i++) + mvpp2_port_remove(priv->port_list[i]); err_axi_clk: clk_disable_unprepare(priv->axi_clk); err_mg_core_clk: @@ -7677,18 +7714,13 @@ err_pp_clk: static void mvpp2_remove(struct platform_device *pdev) { struct mvpp2 *priv = platform_get_drvdata(pdev); - struct fwnode_handle *fwnode = pdev->dev.fwnode; - int i = 0, poolnum = MVPP2_BM_POOLS_NUM; - struct fwnode_handle *port_fwnode; + int i, poolnum = MVPP2_BM_POOLS_NUM; mvpp2_dbgfs_cleanup(priv); - fwnode_for_each_available_child_node(fwnode, port_fwnode) { - if (priv->port_list[i]) { - mutex_destroy(&priv->port_list[i]->gather_stats_lock); - mvpp2_port_remove(priv->port_list[i]); - } - i++; + for (i = 0; i < priv->port_count; i++) { + mutex_destroy(&priv->port_list[i]->gather_stats_lock); + mvpp2_port_remove(priv->port_list[i]); } destroy_workqueue(priv->stats_queue); @@ -7711,7 +7743,7 @@ static void mvpp2_remove(struct platform_device *pdev) aggr_txq->descs_dma); } - if (is_acpi_node(port_fwnode)) + if (!dev_of_node(&pdev->dev)) return; clk_disable_unprepare(priv->axi_clk); diff --git a/drivers/net/ethernet/mediatek/airoha_eth.c b/drivers/net/ethernet/mediatek/airoha_eth.c index 1c5b85a86df1..930f180688e5 100644 --- a/drivers/net/ethernet/mediatek/airoha_eth.c +++ b/drivers/net/ethernet/mediatek/airoha_eth.c @@ -18,6 +18,7 @@ #include <uapi/linux/ppp_defs.h> #define AIROHA_MAX_NUM_GDM_PORTS 1 +#define AIROHA_MAX_NUM_QDMA 2 #define AIROHA_MAX_NUM_RSTS 3 #define AIROHA_MAX_NUM_XSI_RSTS 5 #define AIROHA_MAX_MTU 2000 @@ -66,9 +67,11 @@ #define FE_RST_GDM3_MBI_ARB_MASK BIT(2) #define FE_RST_CORE_MASK BIT(0) +#define REG_FE_WAN_MAC_H 0x0030 #define REG_FE_LAN_MAC_H 0x0040 -#define REG_FE_LAN_MAC_LMIN 0x0044 -#define REG_FE_LAN_MAC_LMAX 0x0048 + +#define REG_FE_MAC_LMIN(_n) ((_n) + 0x04) +#define REG_FE_MAC_LMAX(_n) ((_n) + 0x08) #define REG_FE_CDM1_OQ_MAP0 0x0050 #define REG_FE_CDM1_OQ_MAP1 0x0054 @@ -727,7 +730,7 @@ struct airoha_queue_entry { }; struct airoha_queue { - struct airoha_eth *eth; + struct airoha_qdma *qdma; /* protect concurrent queue accesses */ spinlock_t lock; @@ -746,7 +749,7 @@ struct airoha_queue { }; struct airoha_tx_irq_queue { - struct airoha_eth *eth; + struct airoha_qdma *qdma; struct napi_struct napi; u32 *q; @@ -782,9 +785,30 @@ struct airoha_hw_stats { u64 rx_len[7]; }; +struct airoha_qdma { + struct airoha_eth *eth; + void __iomem *regs; + + /* protect concurrent irqmask accesses */ + spinlock_t irq_lock; + u32 irqmask[QDMA_INT_REG_MAX]; + int irq; + + struct airoha_tx_irq_queue q_tx_irq[AIROHA_NUM_TX_IRQ]; + + struct airoha_queue q_tx[AIROHA_NUM_TX_RING]; + struct airoha_queue q_rx[AIROHA_NUM_RX_RING]; + + /* descriptor and packet buffers for qdma hw forward */ + struct { + void *desc; + void *q; + } hfwd; +}; + struct airoha_gdm_port { + struct airoha_qdma *qdma; struct net_device *dev; - struct airoha_eth *eth; int id; struct airoha_hw_stats stats; @@ -794,31 +818,15 @@ struct airoha_eth { struct device *dev; unsigned long state; - - void __iomem *qdma_regs; void __iomem *fe_regs; - /* protect concurrent irqmask accesses */ - spinlock_t irq_lock; - u32 irqmask[QDMA_INT_REG_MAX]; - int irq; - struct reset_control_bulk_data rsts[AIROHA_MAX_NUM_RSTS]; struct reset_control_bulk_data xsi_rsts[AIROHA_MAX_NUM_XSI_RSTS]; - struct airoha_gdm_port *ports[AIROHA_MAX_NUM_GDM_PORTS]; - struct net_device *napi_dev; - struct airoha_queue q_tx[AIROHA_NUM_TX_RING]; - struct airoha_queue q_rx[AIROHA_NUM_RX_RING]; - - struct airoha_tx_irq_queue q_tx_irq[AIROHA_NUM_TX_IRQ]; - /* descriptor and packet buffers for qdma hw forward */ - struct { - void *desc; - void *q; - } hfwd; + struct airoha_qdma qdma[AIROHA_MAX_NUM_QDMA]; + struct airoha_gdm_port *ports[AIROHA_MAX_NUM_GDM_PORTS]; }; static u32 airoha_rr(void __iomem *base, u32 offset) @@ -850,60 +858,72 @@ static u32 airoha_rmw(void __iomem *base, u32 offset, u32 mask, u32 val) #define airoha_fe_clear(eth, offset, val) \ airoha_rmw((eth)->fe_regs, (offset), (val), 0) -#define airoha_qdma_rr(eth, offset) \ - airoha_rr((eth)->qdma_regs, (offset)) -#define airoha_qdma_wr(eth, offset, val) \ - airoha_wr((eth)->qdma_regs, (offset), (val)) -#define airoha_qdma_rmw(eth, offset, mask, val) \ - airoha_rmw((eth)->qdma_regs, (offset), (mask), (val)) -#define airoha_qdma_set(eth, offset, val) \ - airoha_rmw((eth)->qdma_regs, (offset), 0, (val)) -#define airoha_qdma_clear(eth, offset, val) \ - airoha_rmw((eth)->qdma_regs, (offset), (val), 0) - -static void airoha_qdma_set_irqmask(struct airoha_eth *eth, int index, +#define airoha_qdma_rr(qdma, offset) \ + airoha_rr((qdma)->regs, (offset)) +#define airoha_qdma_wr(qdma, offset, val) \ + airoha_wr((qdma)->regs, (offset), (val)) +#define airoha_qdma_rmw(qdma, offset, mask, val) \ + airoha_rmw((qdma)->regs, (offset), (mask), (val)) +#define airoha_qdma_set(qdma, offset, val) \ + airoha_rmw((qdma)->regs, (offset), 0, (val)) +#define airoha_qdma_clear(qdma, offset, val) \ + airoha_rmw((qdma)->regs, (offset), (val), 0) + +static void airoha_qdma_set_irqmask(struct airoha_qdma *qdma, int index, u32 clear, u32 set) { unsigned long flags; - if (WARN_ON_ONCE(index >= ARRAY_SIZE(eth->irqmask))) + if (WARN_ON_ONCE(index >= ARRAY_SIZE(qdma->irqmask))) return; - spin_lock_irqsave(ð->irq_lock, flags); + spin_lock_irqsave(&qdma->irq_lock, flags); - eth->irqmask[index] &= ~clear; - eth->irqmask[index] |= set; - airoha_qdma_wr(eth, REG_INT_ENABLE(index), eth->irqmask[index]); + qdma->irqmask[index] &= ~clear; + qdma->irqmask[index] |= set; + airoha_qdma_wr(qdma, REG_INT_ENABLE(index), qdma->irqmask[index]); /* Read irq_enable register in order to guarantee the update above * completes in the spinlock critical section. */ - airoha_qdma_rr(eth, REG_INT_ENABLE(index)); + airoha_qdma_rr(qdma, REG_INT_ENABLE(index)); - spin_unlock_irqrestore(ð->irq_lock, flags); + spin_unlock_irqrestore(&qdma->irq_lock, flags); } -static void airoha_qdma_irq_enable(struct airoha_eth *eth, int index, +static void airoha_qdma_irq_enable(struct airoha_qdma *qdma, int index, u32 mask) { - airoha_qdma_set_irqmask(eth, index, 0, mask); + airoha_qdma_set_irqmask(qdma, index, 0, mask); } -static void airoha_qdma_irq_disable(struct airoha_eth *eth, int index, +static void airoha_qdma_irq_disable(struct airoha_qdma *qdma, int index, u32 mask) { - airoha_qdma_set_irqmask(eth, index, mask, 0); + airoha_qdma_set_irqmask(qdma, index, mask, 0); } -static void airoha_set_macaddr(struct airoha_eth *eth, const u8 *addr) +static bool airhoa_is_lan_gdm_port(struct airoha_gdm_port *port) { - u32 val; + /* GDM1 port on EN7581 SoC is connected to the lan dsa switch. + * GDM{2,3,4} can be used as wan port connected to an external + * phy module. + */ + return port->id == 1; +} +static void airoha_set_macaddr(struct airoha_gdm_port *port, const u8 *addr) +{ + struct airoha_eth *eth = port->qdma->eth; + u32 val, reg; + + reg = airhoa_is_lan_gdm_port(port) ? REG_FE_LAN_MAC_H + : REG_FE_WAN_MAC_H; val = (addr[0] << 16) | (addr[1] << 8) | addr[2]; - airoha_fe_wr(eth, REG_FE_LAN_MAC_H, val); + airoha_fe_wr(eth, reg, val); val = (addr[3] << 16) | (addr[4] << 8) | addr[5]; - airoha_fe_wr(eth, REG_FE_LAN_MAC_LMIN, val); - airoha_fe_wr(eth, REG_FE_LAN_MAC_LMAX, val); + airoha_fe_wr(eth, REG_FE_MAC_LMIN(reg), val); + airoha_fe_wr(eth, REG_FE_MAC_LMAX(reg), val); } static void airoha_set_gdm_port_fwd_cfg(struct airoha_eth *eth, u32 addr, @@ -1383,8 +1403,9 @@ static int airoha_fe_init(struct airoha_eth *eth) static int airoha_qdma_fill_rx_queue(struct airoha_queue *q) { enum dma_data_direction dir = page_pool_get_dma_dir(q->page_pool); - struct airoha_eth *eth = q->eth; - int qid = q - ð->q_rx[0]; + struct airoha_qdma *qdma = q->qdma; + struct airoha_eth *eth = qdma->eth; + int qid = q - &qdma->q_rx[0]; int nframes = 0; while (q->queued < q->ndesc - 1) { @@ -1420,7 +1441,8 @@ static int airoha_qdma_fill_rx_queue(struct airoha_queue *q) WRITE_ONCE(desc->msg2, 0); WRITE_ONCE(desc->msg3, 0); - airoha_qdma_rmw(eth, REG_RX_CPU_IDX(qid), RX_RING_CPU_IDX_MASK, + airoha_qdma_rmw(qdma, REG_RX_CPU_IDX(qid), + RX_RING_CPU_IDX_MASK, FIELD_PREP(RX_RING_CPU_IDX_MASK, q->head)); } @@ -1450,8 +1472,9 @@ static int airoha_qdma_get_gdm_port(struct airoha_eth *eth, static int airoha_qdma_rx_process(struct airoha_queue *q, int budget) { enum dma_data_direction dir = page_pool_get_dma_dir(q->page_pool); - struct airoha_eth *eth = q->eth; - int qid = q - ð->q_rx[0]; + struct airoha_qdma *qdma = q->qdma; + struct airoha_eth *eth = qdma->eth; + int qid = q - &qdma->q_rx[0]; int done = 0; while (done < budget) { @@ -1513,7 +1536,6 @@ static int airoha_qdma_rx_process(struct airoha_queue *q, int budget) static int airoha_qdma_rx_napi_poll(struct napi_struct *napi, int budget) { struct airoha_queue *q = container_of(napi, struct airoha_queue, napi); - struct airoha_eth *eth = q->eth; int cur, done = 0; do { @@ -1522,14 +1544,14 @@ static int airoha_qdma_rx_napi_poll(struct napi_struct *napi, int budget) } while (cur && done < budget); if (done < budget && napi_complete(napi)) - airoha_qdma_irq_enable(eth, QDMA_INT_REG_IDX1, + airoha_qdma_irq_enable(q->qdma, QDMA_INT_REG_IDX1, RX_DONE_INT_MASK); return done; } -static int airoha_qdma_init_rx_queue(struct airoha_eth *eth, - struct airoha_queue *q, int ndesc) +static int airoha_qdma_init_rx_queue(struct airoha_queue *q, + struct airoha_qdma *qdma, int ndesc) { const struct page_pool_params pp_params = { .order = 0, @@ -1538,15 +1560,16 @@ static int airoha_qdma_init_rx_queue(struct airoha_eth *eth, .dma_dir = DMA_FROM_DEVICE, .max_len = PAGE_SIZE, .nid = NUMA_NO_NODE, - .dev = eth->dev, + .dev = qdma->eth->dev, .napi = &q->napi, }; - int qid = q - ð->q_rx[0], thr; + struct airoha_eth *eth = qdma->eth; + int qid = q - &qdma->q_rx[0], thr; dma_addr_t dma_addr; q->buf_size = PAGE_SIZE / 2; q->ndesc = ndesc; - q->eth = eth; + q->qdma = qdma; q->entry = devm_kzalloc(eth->dev, q->ndesc * sizeof(*q->entry), GFP_KERNEL); @@ -1568,14 +1591,15 @@ static int airoha_qdma_init_rx_queue(struct airoha_eth *eth, netif_napi_add(eth->napi_dev, &q->napi, airoha_qdma_rx_napi_poll); - airoha_qdma_wr(eth, REG_RX_RING_BASE(qid), dma_addr); - airoha_qdma_rmw(eth, REG_RX_RING_SIZE(qid), RX_RING_SIZE_MASK, + airoha_qdma_wr(qdma, REG_RX_RING_BASE(qid), dma_addr); + airoha_qdma_rmw(qdma, REG_RX_RING_SIZE(qid), + RX_RING_SIZE_MASK, FIELD_PREP(RX_RING_SIZE_MASK, ndesc)); thr = clamp(ndesc >> 3, 1, 32); - airoha_qdma_rmw(eth, REG_RX_RING_SIZE(qid), RX_RING_THR_MASK, + airoha_qdma_rmw(qdma, REG_RX_RING_SIZE(qid), RX_RING_THR_MASK, FIELD_PREP(RX_RING_THR_MASK, thr)); - airoha_qdma_rmw(eth, REG_RX_DMA_IDX(qid), RX_RING_DMA_IDX_MASK, + airoha_qdma_rmw(qdma, REG_RX_DMA_IDX(qid), RX_RING_DMA_IDX_MASK, FIELD_PREP(RX_RING_DMA_IDX_MASK, q->head)); airoha_qdma_fill_rx_queue(q); @@ -1585,7 +1609,7 @@ static int airoha_qdma_init_rx_queue(struct airoha_eth *eth, static void airoha_qdma_cleanup_rx_queue(struct airoha_queue *q) { - struct airoha_eth *eth = q->eth; + struct airoha_eth *eth = q->qdma->eth; while (q->queued) { struct airoha_queue_entry *e = &q->entry[q->tail]; @@ -1599,11 +1623,11 @@ static void airoha_qdma_cleanup_rx_queue(struct airoha_queue *q) } } -static int airoha_qdma_init_rx(struct airoha_eth *eth) +static int airoha_qdma_init_rx(struct airoha_qdma *qdma) { int i; - for (i = 0; i < ARRAY_SIZE(eth->q_rx); i++) { + for (i = 0; i < ARRAY_SIZE(qdma->q_rx); i++) { int err; if (!(RX_DONE_INT_MASK & BIT(i))) { @@ -1611,7 +1635,7 @@ static int airoha_qdma_init_rx(struct airoha_eth *eth) continue; } - err = airoha_qdma_init_rx_queue(eth, ð->q_rx[i], + err = airoha_qdma_init_rx_queue(&qdma->q_rx[i], qdma, RX_DSCP_NUM(i)); if (err) return err; @@ -1623,12 +1647,14 @@ static int airoha_qdma_init_rx(struct airoha_eth *eth) static int airoha_qdma_tx_napi_poll(struct napi_struct *napi, int budget) { struct airoha_tx_irq_queue *irq_q; + struct airoha_qdma *qdma; struct airoha_eth *eth; int id, done = 0; irq_q = container_of(napi, struct airoha_tx_irq_queue, napi); - eth = irq_q->eth; - id = irq_q - ð->q_tx_irq[0]; + qdma = irq_q->qdma; + id = irq_q - &qdma->q_tx_irq[0]; + eth = qdma->eth; while (irq_q->queued > 0 && done < budget) { u32 qid, last, val = irq_q->q[irq_q->head]; @@ -1645,10 +1671,10 @@ static int airoha_qdma_tx_napi_poll(struct napi_struct *napi, int budget) last = FIELD_GET(IRQ_DESC_IDX_MASK, val); qid = FIELD_GET(IRQ_RING_IDX_MASK, val); - if (qid >= ARRAY_SIZE(eth->q_tx)) + if (qid >= ARRAY_SIZE(qdma->q_tx)) continue; - q = ð->q_tx[qid]; + q = &qdma->q_tx[qid]; if (!q->ndesc) continue; @@ -1697,28 +1723,29 @@ static int airoha_qdma_tx_napi_poll(struct napi_struct *napi, int budget) int i, len = done >> 7; for (i = 0; i < len; i++) - airoha_qdma_rmw(eth, REG_IRQ_CLEAR_LEN(id), + airoha_qdma_rmw(qdma, REG_IRQ_CLEAR_LEN(id), IRQ_CLEAR_LEN_MASK, 0x80); - airoha_qdma_rmw(eth, REG_IRQ_CLEAR_LEN(id), + airoha_qdma_rmw(qdma, REG_IRQ_CLEAR_LEN(id), IRQ_CLEAR_LEN_MASK, (done & 0x7f)); } if (done < budget && napi_complete(napi)) - airoha_qdma_irq_enable(eth, QDMA_INT_REG_IDX0, + airoha_qdma_irq_enable(qdma, QDMA_INT_REG_IDX0, TX_DONE_INT_MASK(id)); return done; } -static int airoha_qdma_init_tx_queue(struct airoha_eth *eth, - struct airoha_queue *q, int size) +static int airoha_qdma_init_tx_queue(struct airoha_queue *q, + struct airoha_qdma *qdma, int size) { - int i, qid = q - ð->q_tx[0]; + struct airoha_eth *eth = qdma->eth; + int i, qid = q - &qdma->q_tx[0]; dma_addr_t dma_addr; spin_lock_init(&q->lock); q->ndesc = size; - q->eth = eth; + q->qdma = qdma; q->free_thr = 1 + MAX_SKB_FRAGS; q->entry = devm_kzalloc(eth->dev, q->ndesc * sizeof(*q->entry), @@ -1738,20 +1765,20 @@ static int airoha_qdma_init_tx_queue(struct airoha_eth *eth, WRITE_ONCE(q->desc[i].ctrl, cpu_to_le32(val)); } - airoha_qdma_wr(eth, REG_TX_RING_BASE(qid), dma_addr); - airoha_qdma_rmw(eth, REG_TX_CPU_IDX(qid), TX_RING_CPU_IDX_MASK, + 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)); - airoha_qdma_rmw(eth, REG_TX_DMA_IDX(qid), TX_RING_DMA_IDX_MASK, + airoha_qdma_rmw(qdma, REG_TX_DMA_IDX(qid), TX_RING_DMA_IDX_MASK, FIELD_PREP(TX_RING_DMA_IDX_MASK, q->head)); return 0; } -static int airoha_qdma_tx_irq_init(struct airoha_eth *eth, - struct airoha_tx_irq_queue *irq_q, - int size) +static int airoha_qdma_tx_irq_init(struct airoha_tx_irq_queue *irq_q, + struct airoha_qdma *qdma, int size) { - int id = irq_q - ð->q_tx_irq[0]; + int id = irq_q - &qdma->q_tx_irq[0]; + struct airoha_eth *eth = qdma->eth; dma_addr_t dma_addr; netif_napi_add_tx(eth->napi_dev, &irq_q->napi, @@ -1763,30 +1790,30 @@ static int airoha_qdma_tx_irq_init(struct airoha_eth *eth, memset(irq_q->q, 0xff, size * sizeof(u32)); irq_q->size = size; - irq_q->eth = eth; + irq_q->qdma = qdma; - airoha_qdma_wr(eth, REG_TX_IRQ_BASE(id), dma_addr); - airoha_qdma_rmw(eth, REG_TX_IRQ_CFG(id), TX_IRQ_DEPTH_MASK, + airoha_qdma_wr(qdma, REG_TX_IRQ_BASE(id), dma_addr); + airoha_qdma_rmw(qdma, REG_TX_IRQ_CFG(id), TX_IRQ_DEPTH_MASK, FIELD_PREP(TX_IRQ_DEPTH_MASK, size)); - airoha_qdma_rmw(eth, REG_TX_IRQ_CFG(id), TX_IRQ_THR_MASK, + airoha_qdma_rmw(qdma, REG_TX_IRQ_CFG(id), TX_IRQ_THR_MASK, FIELD_PREP(TX_IRQ_THR_MASK, 1)); return 0; } -static int airoha_qdma_init_tx(struct airoha_eth *eth) +static int airoha_qdma_init_tx(struct airoha_qdma *qdma) { int i, err; - for (i = 0; i < ARRAY_SIZE(eth->q_tx_irq); i++) { - err = airoha_qdma_tx_irq_init(eth, ð->q_tx_irq[i], + for (i = 0; i < ARRAY_SIZE(qdma->q_tx_irq); i++) { + err = airoha_qdma_tx_irq_init(&qdma->q_tx_irq[i], qdma, IRQ_QUEUE_LEN(i)); if (err) return err; } - for (i = 0; i < ARRAY_SIZE(eth->q_tx); i++) { - err = airoha_qdma_init_tx_queue(eth, ð->q_tx[i], + for (i = 0; i < ARRAY_SIZE(qdma->q_tx); i++) { + err = airoha_qdma_init_tx_queue(&qdma->q_tx[i], qdma, TX_DSCP_NUM); if (err) return err; @@ -1797,7 +1824,7 @@ static int airoha_qdma_init_tx(struct airoha_eth *eth) static void airoha_qdma_cleanup_tx_queue(struct airoha_queue *q) { - struct airoha_eth *eth = q->eth; + struct airoha_eth *eth = q->qdma->eth; spin_lock_bh(&q->lock); while (q->queued) { @@ -1814,34 +1841,35 @@ static void airoha_qdma_cleanup_tx_queue(struct airoha_queue *q) spin_unlock_bh(&q->lock); } -static int airoha_qdma_init_hfwd_queues(struct airoha_eth *eth) +static int airoha_qdma_init_hfwd_queues(struct airoha_qdma *qdma) { + struct airoha_eth *eth = qdma->eth; dma_addr_t dma_addr; u32 status; int size; size = HW_DSCP_NUM * sizeof(struct airoha_qdma_fwd_desc); - eth->hfwd.desc = dmam_alloc_coherent(eth->dev, size, &dma_addr, - GFP_KERNEL); - if (!eth->hfwd.desc) + qdma->hfwd.desc = dmam_alloc_coherent(eth->dev, size, &dma_addr, + GFP_KERNEL); + if (!qdma->hfwd.desc) return -ENOMEM; - airoha_qdma_wr(eth, REG_FWD_DSCP_BASE, dma_addr); + airoha_qdma_wr(qdma, REG_FWD_DSCP_BASE, dma_addr); size = AIROHA_MAX_PACKET_SIZE * HW_DSCP_NUM; - eth->hfwd.q = dmam_alloc_coherent(eth->dev, size, &dma_addr, - GFP_KERNEL); - if (!eth->hfwd.q) + qdma->hfwd.q = dmam_alloc_coherent(eth->dev, size, &dma_addr, + GFP_KERNEL); + if (!qdma->hfwd.q) return -ENOMEM; - airoha_qdma_wr(eth, REG_FWD_BUF_BASE, dma_addr); + airoha_qdma_wr(qdma, REG_FWD_BUF_BASE, dma_addr); - airoha_qdma_rmw(eth, REG_HW_FWD_DSCP_CFG, + airoha_qdma_rmw(qdma, REG_HW_FWD_DSCP_CFG, HW_FWD_DSCP_PAYLOAD_SIZE_MASK, FIELD_PREP(HW_FWD_DSCP_PAYLOAD_SIZE_MASK, 0)); - airoha_qdma_rmw(eth, REG_FWD_DSCP_LOW_THR, FWD_DSCP_LOW_THR_MASK, + airoha_qdma_rmw(qdma, REG_FWD_DSCP_LOW_THR, FWD_DSCP_LOW_THR_MASK, FIELD_PREP(FWD_DSCP_LOW_THR_MASK, 128)); - airoha_qdma_rmw(eth, REG_LMGR_INIT_CFG, + airoha_qdma_rmw(qdma, REG_LMGR_INIT_CFG, LMGR_INIT_START | LMGR_SRAM_MODE_MASK | HW_FWD_DESC_NUM_MASK, FIELD_PREP(HW_FWD_DESC_NUM_MASK, HW_DSCP_NUM) | @@ -1849,87 +1877,87 @@ static int airoha_qdma_init_hfwd_queues(struct airoha_eth *eth) return read_poll_timeout(airoha_qdma_rr, status, !(status & LMGR_INIT_START), USEC_PER_MSEC, - 30 * USEC_PER_MSEC, true, eth, + 30 * USEC_PER_MSEC, true, qdma, REG_LMGR_INIT_CFG); } -static void airoha_qdma_init_qos(struct airoha_eth *eth) +static void airoha_qdma_init_qos(struct airoha_qdma *qdma) { - airoha_qdma_clear(eth, REG_TXWRR_MODE_CFG, TWRR_WEIGHT_SCALE_MASK); - airoha_qdma_set(eth, REG_TXWRR_MODE_CFG, TWRR_WEIGHT_BASE_MASK); + airoha_qdma_clear(qdma, REG_TXWRR_MODE_CFG, TWRR_WEIGHT_SCALE_MASK); + airoha_qdma_set(qdma, REG_TXWRR_MODE_CFG, TWRR_WEIGHT_BASE_MASK); - airoha_qdma_clear(eth, REG_PSE_BUF_USAGE_CFG, + airoha_qdma_clear(qdma, REG_PSE_BUF_USAGE_CFG, PSE_BUF_ESTIMATE_EN_MASK); - airoha_qdma_set(eth, REG_EGRESS_RATE_METER_CFG, + airoha_qdma_set(qdma, REG_EGRESS_RATE_METER_CFG, EGRESS_RATE_METER_EN_MASK | EGRESS_RATE_METER_EQ_RATE_EN_MASK); /* 2047us x 31 = 63.457ms */ - airoha_qdma_rmw(eth, REG_EGRESS_RATE_METER_CFG, + airoha_qdma_rmw(qdma, REG_EGRESS_RATE_METER_CFG, EGRESS_RATE_METER_WINDOW_SZ_MASK, FIELD_PREP(EGRESS_RATE_METER_WINDOW_SZ_MASK, 0x1f)); - airoha_qdma_rmw(eth, REG_EGRESS_RATE_METER_CFG, + airoha_qdma_rmw(qdma, REG_EGRESS_RATE_METER_CFG, EGRESS_RATE_METER_TIMESLICE_MASK, FIELD_PREP(EGRESS_RATE_METER_TIMESLICE_MASK, 0x7ff)); /* ratelimit init */ - airoha_qdma_set(eth, REG_GLB_TRTCM_CFG, GLB_TRTCM_EN_MASK); + airoha_qdma_set(qdma, REG_GLB_TRTCM_CFG, GLB_TRTCM_EN_MASK); /* fast-tick 25us */ - airoha_qdma_rmw(eth, REG_GLB_TRTCM_CFG, GLB_FAST_TICK_MASK, + airoha_qdma_rmw(qdma, REG_GLB_TRTCM_CFG, GLB_FAST_TICK_MASK, FIELD_PREP(GLB_FAST_TICK_MASK, 25)); - airoha_qdma_rmw(eth, REG_GLB_TRTCM_CFG, GLB_SLOW_TICK_RATIO_MASK, + airoha_qdma_rmw(qdma, REG_GLB_TRTCM_CFG, GLB_SLOW_TICK_RATIO_MASK, FIELD_PREP(GLB_SLOW_TICK_RATIO_MASK, 40)); - airoha_qdma_set(eth, REG_EGRESS_TRTCM_CFG, EGRESS_TRTCM_EN_MASK); - airoha_qdma_rmw(eth, REG_EGRESS_TRTCM_CFG, EGRESS_FAST_TICK_MASK, + airoha_qdma_set(qdma, REG_EGRESS_TRTCM_CFG, EGRESS_TRTCM_EN_MASK); + airoha_qdma_rmw(qdma, REG_EGRESS_TRTCM_CFG, EGRESS_FAST_TICK_MASK, FIELD_PREP(EGRESS_FAST_TICK_MASK, 25)); - airoha_qdma_rmw(eth, REG_EGRESS_TRTCM_CFG, + airoha_qdma_rmw(qdma, REG_EGRESS_TRTCM_CFG, EGRESS_SLOW_TICK_RATIO_MASK, FIELD_PREP(EGRESS_SLOW_TICK_RATIO_MASK, 40)); - airoha_qdma_set(eth, REG_INGRESS_TRTCM_CFG, INGRESS_TRTCM_EN_MASK); - airoha_qdma_clear(eth, REG_INGRESS_TRTCM_CFG, + airoha_qdma_set(qdma, REG_INGRESS_TRTCM_CFG, INGRESS_TRTCM_EN_MASK); + airoha_qdma_clear(qdma, REG_INGRESS_TRTCM_CFG, INGRESS_TRTCM_MODE_MASK); - airoha_qdma_rmw(eth, REG_INGRESS_TRTCM_CFG, INGRESS_FAST_TICK_MASK, + airoha_qdma_rmw(qdma, REG_INGRESS_TRTCM_CFG, INGRESS_FAST_TICK_MASK, FIELD_PREP(INGRESS_FAST_TICK_MASK, 125)); - airoha_qdma_rmw(eth, REG_INGRESS_TRTCM_CFG, + airoha_qdma_rmw(qdma, REG_INGRESS_TRTCM_CFG, INGRESS_SLOW_TICK_RATIO_MASK, FIELD_PREP(INGRESS_SLOW_TICK_RATIO_MASK, 8)); - airoha_qdma_set(eth, REG_SLA_TRTCM_CFG, SLA_TRTCM_EN_MASK); - airoha_qdma_rmw(eth, REG_SLA_TRTCM_CFG, SLA_FAST_TICK_MASK, + airoha_qdma_set(qdma, REG_SLA_TRTCM_CFG, SLA_TRTCM_EN_MASK); + airoha_qdma_rmw(qdma, REG_SLA_TRTCM_CFG, SLA_FAST_TICK_MASK, FIELD_PREP(SLA_FAST_TICK_MASK, 25)); - airoha_qdma_rmw(eth, REG_SLA_TRTCM_CFG, SLA_SLOW_TICK_RATIO_MASK, + airoha_qdma_rmw(qdma, REG_SLA_TRTCM_CFG, SLA_SLOW_TICK_RATIO_MASK, FIELD_PREP(SLA_SLOW_TICK_RATIO_MASK, 40)); } -static int airoha_qdma_hw_init(struct airoha_eth *eth) +static int airoha_qdma_hw_init(struct airoha_qdma *qdma) { int i; /* clear pending irqs */ - for (i = 0; i < ARRAY_SIZE(eth->irqmask); i++) - airoha_qdma_wr(eth, REG_INT_STATUS(i), 0xffffffff); + for (i = 0; i < ARRAY_SIZE(qdma->irqmask); i++) + airoha_qdma_wr(qdma, REG_INT_STATUS(i), 0xffffffff); /* setup irqs */ - airoha_qdma_irq_enable(eth, QDMA_INT_REG_IDX0, INT_IDX0_MASK); - airoha_qdma_irq_enable(eth, QDMA_INT_REG_IDX1, INT_IDX1_MASK); - airoha_qdma_irq_enable(eth, QDMA_INT_REG_IDX4, INT_IDX4_MASK); + airoha_qdma_irq_enable(qdma, QDMA_INT_REG_IDX0, INT_IDX0_MASK); + airoha_qdma_irq_enable(qdma, QDMA_INT_REG_IDX1, INT_IDX1_MASK); + airoha_qdma_irq_enable(qdma, QDMA_INT_REG_IDX4, INT_IDX4_MASK); /* setup irq binding */ - for (i = 0; i < ARRAY_SIZE(eth->q_tx); i++) { - if (!eth->q_tx[i].ndesc) + for (i = 0; i < ARRAY_SIZE(qdma->q_tx); i++) { + if (!qdma->q_tx[i].ndesc) continue; if (TX_RING_IRQ_BLOCKING_MAP_MASK & BIT(i)) - airoha_qdma_set(eth, REG_TX_RING_BLOCKING(i), + airoha_qdma_set(qdma, REG_TX_RING_BLOCKING(i), TX_RING_IRQ_BLOCKING_CFG_MASK); else - airoha_qdma_clear(eth, REG_TX_RING_BLOCKING(i), + airoha_qdma_clear(qdma, REG_TX_RING_BLOCKING(i), TX_RING_IRQ_BLOCKING_CFG_MASK); } - airoha_qdma_wr(eth, REG_QDMA_GLOBAL_CFG, + airoha_qdma_wr(qdma, REG_QDMA_GLOBAL_CFG, GLOBAL_CFG_RX_2B_OFFSET_MASK | FIELD_PREP(GLOBAL_CFG_DMA_PREFERENCE_MASK, 3) | GLOBAL_CFG_CPU_TXR_RR_MASK | @@ -1940,18 +1968,18 @@ static int airoha_qdma_hw_init(struct airoha_eth *eth) GLOBAL_CFG_TX_WB_DONE_MASK | FIELD_PREP(GLOBAL_CFG_MAX_ISSUE_NUM_MASK, 2)); - airoha_qdma_init_qos(eth); + airoha_qdma_init_qos(qdma); /* disable qdma rx delay interrupt */ - for (i = 0; i < ARRAY_SIZE(eth->q_rx); i++) { - if (!eth->q_rx[i].ndesc) + for (i = 0; i < ARRAY_SIZE(qdma->q_rx); i++) { + if (!qdma->q_rx[i].ndesc) continue; - airoha_qdma_clear(eth, REG_RX_DELAY_INT_IDX(i), + airoha_qdma_clear(qdma, REG_RX_DELAY_INT_IDX(i), RX_DELAY_INT_MASK); } - airoha_qdma_set(eth, REG_TXQ_CNGST_CFG, + airoha_qdma_set(qdma, REG_TXQ_CNGST_CFG, TXQ_CNGST_DROP_EN | TXQ_CNGST_DEI_DROP_EN); return 0; @@ -1959,150 +1987,180 @@ static int airoha_qdma_hw_init(struct airoha_eth *eth) static irqreturn_t airoha_irq_handler(int irq, void *dev_instance) { - struct airoha_eth *eth = dev_instance; - u32 intr[ARRAY_SIZE(eth->irqmask)]; + struct airoha_qdma *qdma = dev_instance; + u32 intr[ARRAY_SIZE(qdma->irqmask)]; int i; - for (i = 0; i < ARRAY_SIZE(eth->irqmask); i++) { - intr[i] = airoha_qdma_rr(eth, REG_INT_STATUS(i)); - intr[i] &= eth->irqmask[i]; - airoha_qdma_wr(eth, REG_INT_STATUS(i), intr[i]); + for (i = 0; i < ARRAY_SIZE(qdma->irqmask); i++) { + intr[i] = airoha_qdma_rr(qdma, REG_INT_STATUS(i)); + intr[i] &= qdma->irqmask[i]; + airoha_qdma_wr(qdma, REG_INT_STATUS(i), intr[i]); } - if (!test_bit(DEV_STATE_INITIALIZED, ð->state)) + if (!test_bit(DEV_STATE_INITIALIZED, &qdma->eth->state)) return IRQ_NONE; if (intr[1] & RX_DONE_INT_MASK) { - airoha_qdma_irq_disable(eth, QDMA_INT_REG_IDX1, + airoha_qdma_irq_disable(qdma, QDMA_INT_REG_IDX1, RX_DONE_INT_MASK); - for (i = 0; i < ARRAY_SIZE(eth->q_rx); i++) { - if (!eth->q_rx[i].ndesc) + for (i = 0; i < ARRAY_SIZE(qdma->q_rx); i++) { + if (!qdma->q_rx[i].ndesc) continue; if (intr[1] & BIT(i)) - napi_schedule(ð->q_rx[i].napi); + napi_schedule(&qdma->q_rx[i].napi); } } if (intr[0] & INT_TX_MASK) { - for (i = 0; i < ARRAY_SIZE(eth->q_tx_irq); i++) { - struct airoha_tx_irq_queue *irq_q = ð->q_tx_irq[i]; + for (i = 0; i < ARRAY_SIZE(qdma->q_tx_irq); i++) { + struct airoha_tx_irq_queue *irq_q = &qdma->q_tx_irq[i]; u32 status, head; if (!(intr[0] & TX_DONE_INT_MASK(i))) continue; - airoha_qdma_irq_disable(eth, QDMA_INT_REG_IDX0, + airoha_qdma_irq_disable(qdma, QDMA_INT_REG_IDX0, TX_DONE_INT_MASK(i)); - status = airoha_qdma_rr(eth, REG_IRQ_STATUS(i)); + status = airoha_qdma_rr(qdma, REG_IRQ_STATUS(i)); head = FIELD_GET(IRQ_HEAD_IDX_MASK, status); irq_q->head = head % irq_q->size; irq_q->queued = FIELD_GET(IRQ_ENTRY_LEN_MASK, status); - napi_schedule(ð->q_tx_irq[i].napi); + napi_schedule(&qdma->q_tx_irq[i].napi); } } return IRQ_HANDLED; } -static int airoha_qdma_init(struct airoha_eth *eth) +static int airoha_qdma_init(struct platform_device *pdev, + struct airoha_eth *eth, + struct airoha_qdma *qdma) { - int err; + int err, id = qdma - ð->qdma[0]; + const char *res; - err = devm_request_irq(eth->dev, eth->irq, airoha_irq_handler, - IRQF_SHARED, KBUILD_MODNAME, eth); - if (err) - return err; + spin_lock_init(&qdma->irq_lock); + qdma->eth = eth; - err = airoha_qdma_init_rx(eth); + res = devm_kasprintf(eth->dev, GFP_KERNEL, "qdma%d", id); + if (!res) + return -ENOMEM; + + qdma->regs = devm_platform_ioremap_resource_byname(pdev, res); + if (IS_ERR(qdma->regs)) + return dev_err_probe(eth->dev, PTR_ERR(qdma->regs), + "failed to iomap qdma%d regs\n", id); + + qdma->irq = platform_get_irq(pdev, 4 * id); + if (qdma->irq < 0) + return qdma->irq; + + err = devm_request_irq(eth->dev, qdma->irq, airoha_irq_handler, + IRQF_SHARED, KBUILD_MODNAME, qdma); if (err) return err; - err = airoha_qdma_init_tx(eth); + err = airoha_qdma_init_rx(qdma); if (err) return err; - err = airoha_qdma_init_hfwd_queues(eth); + err = airoha_qdma_init_tx(qdma); if (err) return err; - err = airoha_qdma_hw_init(eth); + err = airoha_qdma_init_hfwd_queues(qdma); if (err) return err; - set_bit(DEV_STATE_INITIALIZED, ð->state); - - return 0; + return airoha_qdma_hw_init(qdma); } -static int airoha_hw_init(struct airoha_eth *eth) +static int airoha_hw_init(struct platform_device *pdev, + struct airoha_eth *eth) { - int err; + int err, i; /* disable xsi */ - reset_control_bulk_assert(ARRAY_SIZE(eth->xsi_rsts), eth->xsi_rsts); + err = reset_control_bulk_assert(ARRAY_SIZE(eth->xsi_rsts), + eth->xsi_rsts); + if (err) + return err; + + err = reset_control_bulk_assert(ARRAY_SIZE(eth->rsts), eth->rsts); + if (err) + return err; - reset_control_bulk_assert(ARRAY_SIZE(eth->rsts), eth->rsts); - msleep(20); - reset_control_bulk_deassert(ARRAY_SIZE(eth->rsts), eth->rsts); msleep(20); + err = reset_control_bulk_deassert(ARRAY_SIZE(eth->rsts), eth->rsts); + if (err) + return err; + msleep(20); err = airoha_fe_init(eth); if (err) return err; - return airoha_qdma_init(eth); + for (i = 0; i < ARRAY_SIZE(eth->qdma); i++) { + err = airoha_qdma_init(pdev, eth, ð->qdma[i]); + if (err) + return err; + } + + set_bit(DEV_STATE_INITIALIZED, ð->state); + + return 0; } -static void airoha_hw_cleanup(struct airoha_eth *eth) +static void airoha_hw_cleanup(struct airoha_qdma *qdma) { int i; - for (i = 0; i < ARRAY_SIZE(eth->q_rx); i++) { - if (!eth->q_rx[i].ndesc) + for (i = 0; i < ARRAY_SIZE(qdma->q_rx); i++) { + if (!qdma->q_rx[i].ndesc) continue; - napi_disable(ð->q_rx[i].napi); - netif_napi_del(ð->q_rx[i].napi); - airoha_qdma_cleanup_rx_queue(ð->q_rx[i]); - if (eth->q_rx[i].page_pool) - page_pool_destroy(eth->q_rx[i].page_pool); + napi_disable(&qdma->q_rx[i].napi); + netif_napi_del(&qdma->q_rx[i].napi); + airoha_qdma_cleanup_rx_queue(&qdma->q_rx[i]); + if (qdma->q_rx[i].page_pool) + page_pool_destroy(qdma->q_rx[i].page_pool); } - for (i = 0; i < ARRAY_SIZE(eth->q_tx_irq); i++) { - napi_disable(ð->q_tx_irq[i].napi); - netif_napi_del(ð->q_tx_irq[i].napi); + for (i = 0; i < ARRAY_SIZE(qdma->q_tx_irq); i++) { + napi_disable(&qdma->q_tx_irq[i].napi); + netif_napi_del(&qdma->q_tx_irq[i].napi); } - for (i = 0; i < ARRAY_SIZE(eth->q_tx); i++) { - if (!eth->q_tx[i].ndesc) + for (i = 0; i < ARRAY_SIZE(qdma->q_tx); i++) { + if (!qdma->q_tx[i].ndesc) continue; - airoha_qdma_cleanup_tx_queue(ð->q_tx[i]); + airoha_qdma_cleanup_tx_queue(&qdma->q_tx[i]); } } -static void airoha_qdma_start_napi(struct airoha_eth *eth) +static void airoha_qdma_start_napi(struct airoha_qdma *qdma) { int i; - for (i = 0; i < ARRAY_SIZE(eth->q_tx_irq); i++) - napi_enable(ð->q_tx_irq[i].napi); + for (i = 0; i < ARRAY_SIZE(qdma->q_tx_irq); i++) + napi_enable(&qdma->q_tx_irq[i].napi); - for (i = 0; i < ARRAY_SIZE(eth->q_rx); i++) { - if (!eth->q_rx[i].ndesc) + for (i = 0; i < ARRAY_SIZE(qdma->q_rx); i++) { + if (!qdma->q_rx[i].ndesc) continue; - napi_enable(ð->q_rx[i].napi); + napi_enable(&qdma->q_rx[i].napi); } } static void airoha_update_hw_stats(struct airoha_gdm_port *port) { - struct airoha_eth *eth = port->eth; + struct airoha_eth *eth = port->qdma->eth; u32 val, i = 0; spin_lock(&port->stats.lock); @@ -2247,23 +2305,24 @@ static void airoha_update_hw_stats(struct airoha_gdm_port *port) static int airoha_dev_open(struct net_device *dev) { struct airoha_gdm_port *port = netdev_priv(dev); - struct airoha_eth *eth = port->eth; + struct airoha_qdma *qdma = port->qdma; int err; netif_tx_start_all_queues(dev); - err = airoha_set_gdm_ports(eth, true); + err = airoha_set_gdm_ports(qdma->eth, true); if (err) return err; if (netdev_uses_dsa(dev)) - airoha_fe_set(eth, REG_GDM_INGRESS_CFG(port->id), + airoha_fe_set(qdma->eth, REG_GDM_INGRESS_CFG(port->id), GDM_STAG_EN_MASK); else - airoha_fe_clear(eth, REG_GDM_INGRESS_CFG(port->id), + airoha_fe_clear(qdma->eth, REG_GDM_INGRESS_CFG(port->id), GDM_STAG_EN_MASK); - airoha_qdma_set(eth, REG_QDMA_GLOBAL_CFG, GLOBAL_CFG_TX_DMA_EN_MASK); - airoha_qdma_set(eth, REG_QDMA_GLOBAL_CFG, GLOBAL_CFG_RX_DMA_EN_MASK); + airoha_qdma_set(qdma, REG_QDMA_GLOBAL_CFG, + GLOBAL_CFG_TX_DMA_EN_MASK | + GLOBAL_CFG_RX_DMA_EN_MASK); return 0; } @@ -2271,16 +2330,17 @@ static int airoha_dev_open(struct net_device *dev) static int airoha_dev_stop(struct net_device *dev) { struct airoha_gdm_port *port = netdev_priv(dev); - struct airoha_eth *eth = port->eth; + struct airoha_qdma *qdma = port->qdma; int err; netif_tx_disable(dev); - err = airoha_set_gdm_ports(eth, false); + err = airoha_set_gdm_ports(qdma->eth, false); if (err) return err; - airoha_qdma_clear(eth, REG_QDMA_GLOBAL_CFG, GLOBAL_CFG_TX_DMA_EN_MASK); - airoha_qdma_clear(eth, REG_QDMA_GLOBAL_CFG, GLOBAL_CFG_RX_DMA_EN_MASK); + airoha_qdma_clear(qdma, REG_QDMA_GLOBAL_CFG, + GLOBAL_CFG_TX_DMA_EN_MASK | + GLOBAL_CFG_RX_DMA_EN_MASK); return 0; } @@ -2294,7 +2354,7 @@ static int airoha_dev_set_macaddr(struct net_device *dev, void *p) if (err) return err; - airoha_set_macaddr(port->eth, dev->dev_addr); + airoha_set_macaddr(port, dev->dev_addr); return 0; } @@ -2303,7 +2363,7 @@ static int airoha_dev_init(struct net_device *dev) { struct airoha_gdm_port *port = netdev_priv(dev); - airoha_set_macaddr(port->eth, dev->dev_addr); + airoha_set_macaddr(port, dev->dev_addr); return 0; } @@ -2337,7 +2397,7 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, struct airoha_gdm_port *port = netdev_priv(dev); u32 msg0 = 0, msg1, len = skb_headlen(skb); int i, qid = skb_get_queue_mapping(skb); - struct airoha_eth *eth = port->eth; + struct airoha_qdma *qdma = port->qdma; u32 nr_frags = 1 + sinfo->nr_frags; struct netdev_queue *txq; struct airoha_queue *q; @@ -2367,7 +2427,7 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, msg1 = FIELD_PREP(QDMA_ETH_TXMSG_FPORT_MASK, fport) | FIELD_PREP(QDMA_ETH_TXMSG_METER_MASK, 0x7f); - q = ð->q_tx[qid]; + q = &qdma->q_tx[qid]; if (WARN_ON_ONCE(!q->ndesc)) goto error; @@ -2411,7 +2471,8 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, e->dma_addr = addr; e->dma_len = len; - airoha_qdma_rmw(eth, REG_TX_CPU_IDX(qid), TX_RING_CPU_IDX_MASK, + airoha_qdma_rmw(qdma, REG_TX_CPU_IDX(qid), + TX_RING_CPU_IDX_MASK, FIELD_PREP(TX_RING_CPU_IDX_MASK, index)); data = skb_frag_address(frag); @@ -2448,7 +2509,7 @@ static void airoha_ethtool_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { struct airoha_gdm_port *port = netdev_priv(dev); - struct airoha_eth *eth = port->eth; + struct airoha_eth *eth = port->qdma->eth; strscpy(info->driver, eth->dev->driver->name, sizeof(info->driver)); strscpy(info->bus_info, dev_name(eth->dev), sizeof(info->bus_info)); @@ -2529,6 +2590,7 @@ static int airoha_alloc_gdm_port(struct airoha_eth *eth, struct device_node *np) { const __be32 *id_ptr = of_get_property(np, "reg", NULL); struct airoha_gdm_port *port; + struct airoha_qdma *qdma; struct net_device *dev; int err, index; u32 id; @@ -2558,6 +2620,7 @@ static int airoha_alloc_gdm_port(struct airoha_eth *eth, struct device_node *np) return -ENOMEM; } + qdma = ð->qdma[index % AIROHA_MAX_NUM_QDMA]; dev->netdev_ops = &airoha_netdev_ops; dev->ethtool_ops = &airoha_ethtool_ops; dev->max_mtu = AIROHA_MAX_MTU; @@ -2567,6 +2630,7 @@ static int airoha_alloc_gdm_port(struct airoha_eth *eth, struct device_node *np) NETIF_F_SG | NETIF_F_TSO; dev->features |= dev->hw_features; dev->dev.of_node = np; + dev->irq = qdma->irq; SET_NETDEV_DEV(dev, eth->dev); err = of_get_ethdev_address(np, dev); @@ -2582,8 +2646,8 @@ static int airoha_alloc_gdm_port(struct airoha_eth *eth, struct device_node *np) port = netdev_priv(dev); u64_stats_init(&port->stats.syncp); spin_lock_init(&port->stats.lock); + port->qdma = qdma; port->dev = dev; - port->eth = eth; port->id = id; eth->ports[index] = port; @@ -2613,11 +2677,6 @@ static int airoha_probe(struct platform_device *pdev) return dev_err_probe(eth->dev, PTR_ERR(eth->fe_regs), "failed to iomap fe regs\n"); - eth->qdma_regs = devm_platform_ioremap_resource_byname(pdev, "qdma0"); - if (IS_ERR(eth->qdma_regs)) - return dev_err_probe(eth->dev, PTR_ERR(eth->qdma_regs), - "failed to iomap qdma regs\n"); - eth->rsts[0].id = "fe"; eth->rsts[1].id = "pdma"; eth->rsts[2].id = "qdma"; @@ -2642,11 +2701,6 @@ static int airoha_probe(struct platform_device *pdev) return err; } - spin_lock_init(ð->irq_lock); - eth->irq = platform_get_irq(pdev, 0); - if (eth->irq < 0) - return eth->irq; - eth->napi_dev = alloc_netdev_dummy(0); if (!eth->napi_dev) return -ENOMEM; @@ -2656,11 +2710,13 @@ static int airoha_probe(struct platform_device *pdev) strscpy(eth->napi_dev->name, "qdma_eth", sizeof(eth->napi_dev->name)); platform_set_drvdata(pdev, eth); - err = airoha_hw_init(eth); + err = airoha_hw_init(pdev, eth); if (err) goto error; - airoha_qdma_start_napi(eth); + for (i = 0; i < ARRAY_SIZE(eth->qdma); i++) + airoha_qdma_start_napi(ð->qdma[i]); + for_each_child_of_node(pdev->dev.of_node, np) { if (!of_device_is_compatible(np, "airoha,eth-mac")) continue; @@ -2678,7 +2734,9 @@ static int airoha_probe(struct platform_device *pdev) return 0; error: - airoha_hw_cleanup(eth); + for (i = 0; i < ARRAY_SIZE(eth->qdma); i++) + airoha_hw_cleanup(ð->qdma[i]); + for (i = 0; i < ARRAY_SIZE(eth->ports); i++) { struct airoha_gdm_port *port = eth->ports[i]; @@ -2696,7 +2754,9 @@ static void airoha_remove(struct platform_device *pdev) struct airoha_eth *eth = platform_get_drvdata(pdev); int i; - airoha_hw_cleanup(eth); + for (i = 0; i < ARRAY_SIZE(eth->qdma); i++) + airoha_hw_cleanup(ð->qdma[i]); + for (i = 0; i < ARRAY_SIZE(eth->ports); i++) { struct airoha_gdm_port *port = eth->ports[i]; @@ -2715,6 +2775,7 @@ static const struct of_device_id of_airoha_match[] = { { .compatible = "airoha,en7581-eth" }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, of_airoha_match); static struct platform_driver airoha_driver = { .probe = airoha_probe, diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h index eb1708b43aa3..0d5225f1d3ee 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h @@ -724,12 +724,8 @@ enum mtk_clks_map { MTK_CLK_ETHWARP_WOCPU2, MTK_CLK_ETHWARP_WOCPU1, MTK_CLK_ETHWARP_WOCPU0, - MTK_CLK_TOP_USXGMII_SBUS_0_SEL, - MTK_CLK_TOP_USXGMII_SBUS_1_SEL, MTK_CLK_TOP_SGM_0_SEL, MTK_CLK_TOP_SGM_1_SEL, - MTK_CLK_TOP_XFI_PHY_0_XTAL_SEL, - MTK_CLK_TOP_XFI_PHY_1_XTAL_SEL, MTK_CLK_TOP_ETH_GMII_SEL, MTK_CLK_TOP_ETH_REFCK_50M_SEL, MTK_CLK_TOP_ETH_SYS_200M_SEL, @@ -800,19 +796,9 @@ enum mtk_clks_map { BIT_ULL(MTK_CLK_GP3) | BIT_ULL(MTK_CLK_XGP1) | \ BIT_ULL(MTK_CLK_XGP2) | BIT_ULL(MTK_CLK_XGP3) | \ BIT_ULL(MTK_CLK_CRYPTO) | \ - BIT_ULL(MTK_CLK_SGMII_TX_250M) | \ - BIT_ULL(MTK_CLK_SGMII_RX_250M) | \ - BIT_ULL(MTK_CLK_SGMII2_TX_250M) | \ - BIT_ULL(MTK_CLK_SGMII2_RX_250M) | \ BIT_ULL(MTK_CLK_ETHWARP_WOCPU2) | \ BIT_ULL(MTK_CLK_ETHWARP_WOCPU1) | \ BIT_ULL(MTK_CLK_ETHWARP_WOCPU0) | \ - BIT_ULL(MTK_CLK_TOP_USXGMII_SBUS_0_SEL) | \ - BIT_ULL(MTK_CLK_TOP_USXGMII_SBUS_1_SEL) | \ - BIT_ULL(MTK_CLK_TOP_SGM_0_SEL) | \ - BIT_ULL(MTK_CLK_TOP_SGM_1_SEL) | \ - BIT_ULL(MTK_CLK_TOP_XFI_PHY_0_XTAL_SEL) | \ - BIT_ULL(MTK_CLK_TOP_XFI_PHY_1_XTAL_SEL) | \ BIT_ULL(MTK_CLK_TOP_ETH_GMII_SEL) | \ BIT_ULL(MTK_CLK_TOP_ETH_REFCK_50M_SEL) | \ BIT_ULL(MTK_CLK_TOP_ETH_SYS_200M_SEL) | \ diff --git a/drivers/net/ethernet/mediatek/mtk_ppe.c b/drivers/net/ethernet/mediatek/mtk_ppe.c index 0acee405a749..ada852adc5f7 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe.c +++ b/drivers/net/ethernet/mediatek/mtk_ppe.c @@ -8,8 +8,11 @@ #include <linux/platform_device.h> #include <linux/if_ether.h> #include <linux/if_vlan.h> + #include <net/dst_metadata.h> #include <net/dsa.h> +#include <net/ipv6.h> + #include "mtk_eth_soc.h" #include "mtk_ppe.h" #include "mtk_ppe_regs.h" @@ -338,7 +341,6 @@ int mtk_foe_entry_set_ipv6_tuple(struct mtk_eth *eth, { int type = mtk_get_ib1_pkt_type(eth, entry->ib1); u32 *src, *dest; - int i; switch (type) { case MTK_PPE_PKT_TYPE_IPV4_DSLITE: @@ -359,10 +361,8 @@ int mtk_foe_entry_set_ipv6_tuple(struct mtk_eth *eth, return -EINVAL; } - for (i = 0; i < 4; i++) - src[i] = be32_to_cpu(src_addr[i]); - for (i = 0; i < 4; i++) - dest[i] = be32_to_cpu(dest_addr[i]); + ipv6_addr_be32_to_cpu(src, src_addr); + ipv6_addr_be32_to_cpu(dest, dest_addr); return 0; } diff --git a/drivers/net/ethernet/mediatek/mtk_ppe_debugfs.c b/drivers/net/ethernet/mediatek/mtk_ppe_debugfs.c index 1a97feca77f2..570ebf91f693 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe_debugfs.c +++ b/drivers/net/ethernet/mediatek/mtk_ppe_debugfs.c @@ -3,6 +3,9 @@ #include <linux/kernel.h> #include <linux/debugfs.h> + +#include <net/ipv6.h> + #include "mtk_eth_soc.h" struct mtk_flow_addr_info @@ -47,16 +50,14 @@ static const char *mtk_foe_pkt_type_str(int type) static void mtk_print_addr(struct seq_file *m, u32 *addr, bool ipv6) { - __be32 n_addr[4]; - int i; + __be32 n_addr[IPV6_ADDR_WORDS]; if (!ipv6) { seq_printf(m, "%pI4h", addr); return; } - for (i = 0; i < ARRAY_SIZE(n_addr); i++) - n_addr[i] = htonl(addr[i]); + ipv6_addr_cpu_to_be32(n_addr, addr); seq_printf(m, "%pI6", n_addr); } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index 943d6918c2ec..cd17a3f4faf8 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -2036,20 +2036,20 @@ static int mlx4_en_get_module_info(struct net_device *dev, switch (data[0] /* identifier */) { case MLX4_MODULE_ID_QSFP: modinfo->type = ETH_MODULE_SFF_8436; - modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN; + modinfo->eeprom_len = ETH_MODULE_SFF_8436_MAX_LEN; break; case MLX4_MODULE_ID_QSFP_PLUS: if (data[1] >= 0x3) { /* revision id */ modinfo->type = ETH_MODULE_SFF_8636; - modinfo->eeprom_len = ETH_MODULE_SFF_8636_LEN; + modinfo->eeprom_len = ETH_MODULE_SFF_8636_MAX_LEN; } else { modinfo->type = ETH_MODULE_SFF_8436; - modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN; + modinfo->eeprom_len = ETH_MODULE_SFF_8436_MAX_LEN; } break; case MLX4_MODULE_ID_QSFP28: modinfo->type = ETH_MODULE_SFF_8636; - modinfo->eeprom_len = ETH_MODULE_SFF_8636_LEN; + modinfo->eeprom_len = ETH_MODULE_SFF_8636_MAX_LEN; break; case MLX4_MODULE_ID_SFP: modinfo->type = ETH_MODULE_SFF_8472; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index d9e241423bc5..da0a1c65ec4a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -1173,14 +1173,16 @@ void mlx5e_ethtool_get_ringparam(struct mlx5e_priv *priv, struct ethtool_ringparam *param, struct kernel_ethtool_ringparam *kernel_param); int mlx5e_ethtool_set_ringparam(struct mlx5e_priv *priv, - struct ethtool_ringparam *param); + struct ethtool_ringparam *param, + struct netlink_ext_ack *extack); void mlx5e_ethtool_get_channels(struct mlx5e_priv *priv, struct ethtool_channels *ch); int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv, struct ethtool_channels *ch); int mlx5e_ethtool_get_coalesce(struct mlx5e_priv *priv, struct ethtool_coalesce *coal, - struct kernel_ethtool_coalesce *kernel_coal); + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack); int mlx5e_ethtool_set_coalesce(struct mlx5e_priv *priv, struct ethtool_coalesce *coal, struct kernel_ethtool_coalesce *kernel_coal, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs.h index bb6b1a979ba1..62b3f7ff5562 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs.h @@ -25,6 +25,8 @@ struct mlx5_ct_fs_ops { struct mlx5_flow_attr *attr, struct flow_rule *flow_rule); void (*ct_rule_del)(struct mlx5_ct_fs *fs, struct mlx5_ct_fs_rule *fs_rule); + int (*ct_rule_update)(struct mlx5_ct_fs *fs, struct mlx5_ct_fs_rule *fs_rule, + struct mlx5_flow_spec *spec, struct mlx5_flow_attr *attr); size_t priv_size; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_dmfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_dmfs.c index ae4f55be48ce..64a82aafaaca 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_dmfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_dmfs.c @@ -65,9 +65,30 @@ mlx5_ct_fs_dmfs_ct_rule_del(struct mlx5_ct_fs *fs, struct mlx5_ct_fs_rule *fs_ru kfree(dmfs_rule); } +static int mlx5_ct_fs_dmfs_ct_rule_update(struct mlx5_ct_fs *fs, struct mlx5_ct_fs_rule *fs_rule, + struct mlx5_flow_spec *spec, struct mlx5_flow_attr *attr) +{ + struct mlx5_ct_fs_dmfs_rule *dmfs_rule = container_of(fs_rule, + struct mlx5_ct_fs_dmfs_rule, + fs_rule); + struct mlx5e_priv *priv = netdev_priv(fs->netdev); + struct mlx5_flow_handle *rule; + + rule = mlx5_tc_rule_insert(priv, spec, attr); + if (IS_ERR(rule)) + return PTR_ERR(rule); + mlx5_tc_rule_delete(priv, dmfs_rule->rule, dmfs_rule->attr); + + dmfs_rule->rule = rule; + dmfs_rule->attr = attr; + + return 0; +} + static struct mlx5_ct_fs_ops dmfs_ops = { .ct_rule_add = mlx5_ct_fs_dmfs_ct_rule_add, .ct_rule_del = mlx5_ct_fs_dmfs_ct_rule_del, + .ct_rule_update = mlx5_ct_fs_dmfs_ct_rule_update, .init = mlx5_ct_fs_dmfs_init, .destroy = mlx5_ct_fs_dmfs_destroy, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c index 8c531f4ec912..1c062a2e8996 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c @@ -368,9 +368,35 @@ mlx5_ct_fs_smfs_ct_rule_del(struct mlx5_ct_fs *fs, struct mlx5_ct_fs_rule *fs_ru kfree(smfs_rule); } +static int mlx5_ct_fs_smfs_ct_rule_update(struct mlx5_ct_fs *fs, struct mlx5_ct_fs_rule *fs_rule, + struct mlx5_flow_spec *spec, struct mlx5_flow_attr *attr) +{ + struct mlx5_ct_fs_smfs_rule *smfs_rule = container_of(fs_rule, + struct mlx5_ct_fs_smfs_rule, + fs_rule); + struct mlx5_ct_fs_smfs *fs_smfs = mlx5_ct_fs_priv(fs); + struct mlx5dr_action *actions[3]; /* We only need to create 3 actions, see below. */ + struct mlx5dr_rule *rule; + + actions[0] = smfs_rule->count_action; + actions[1] = attr->modify_hdr->action.dr_action; + actions[2] = fs_smfs->fwd_action; + + rule = mlx5_smfs_rule_create(smfs_rule->smfs_matcher->dr_matcher, spec, + ARRAY_SIZE(actions), actions, spec->flow_context.flow_source); + if (!rule) + return -EINVAL; + + mlx5_smfs_rule_destroy(smfs_rule->rule); + smfs_rule->rule = rule; + + return 0; +} + static struct mlx5_ct_fs_ops fs_smfs_ops = { .ct_rule_add = mlx5_ct_fs_smfs_ct_rule_add, .ct_rule_del = mlx5_ct_fs_smfs_ct_rule_del, + .ct_rule_update = mlx5_ct_fs_smfs_ct_rule_update, .init = mlx5_ct_fs_smfs_init, .destroy = mlx5_ct_fs_smfs_destroy, 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 71a168746ebe..dcfccaaa8d91 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c @@ -876,15 +876,14 @@ err_attr: } static int -mlx5_tc_ct_entry_replace_rule(struct mlx5_tc_ct_priv *ct_priv, - struct flow_rule *flow_rule, - struct mlx5_ct_entry *entry, - bool nat, u8 zone_restore_id) +mlx5_tc_ct_entry_update_rule(struct mlx5_tc_ct_priv *ct_priv, + struct flow_rule *flow_rule, + struct mlx5_ct_entry *entry, + bool nat, u8 zone_restore_id) { struct mlx5_ct_zone_rule *zone_rule = &entry->zone_rules[nat]; struct mlx5_flow_attr *attr = zone_rule->attr, *old_attr; struct mlx5e_mod_hdr_handle *mh; - struct mlx5_ct_fs_rule *rule; struct mlx5_flow_spec *spec; int err; @@ -902,29 +901,26 @@ mlx5_tc_ct_entry_replace_rule(struct mlx5_tc_ct_priv *ct_priv, err = mlx5_tc_ct_entry_create_mod_hdr(ct_priv, attr, flow_rule, &mh, zone_restore_id, nat, mlx5_tc_ct_entry_in_ct_nat_table(entry)); if (err) { - ct_dbg("Failed to create ct entry mod hdr"); + ct_dbg("Failed to create ct entry mod hdr, err: %d", err); goto err_mod_hdr; } mlx5_tc_ct_set_tuple_match(ct_priv, spec, flow_rule); mlx5e_tc_match_to_reg_match(spec, ZONE_TO_REG, entry->tuple.zone, MLX5_CT_ZONE_MASK); - rule = ct_priv->fs_ops->ct_rule_add(ct_priv->fs, spec, attr, flow_rule); - if (IS_ERR(rule)) { - err = PTR_ERR(rule); - ct_dbg("Failed to add replacement ct entry rule, nat: %d", nat); + err = ct_priv->fs_ops->ct_rule_update(ct_priv->fs, zone_rule->rule, spec, attr); + if (err) { + ct_dbg("Failed to update ct entry rule, nat: %d, err: %d", nat, err); goto err_rule; } - ct_priv->fs_ops->ct_rule_del(ct_priv->fs, zone_rule->rule); - zone_rule->rule = rule; mlx5_tc_ct_entry_destroy_mod_hdr(ct_priv, old_attr, zone_rule->mh); zone_rule->mh = mh; mlx5_put_label_mapping(ct_priv, old_attr->ct_attr.ct_labels_id); kfree(old_attr); kvfree(spec); - ct_dbg("Replaced ct entry rule in zone %d", entry->tuple.zone); + ct_dbg("Updated ct entry rule in zone %d", entry->tuple.zone); return 0; @@ -1141,23 +1137,23 @@ err_orig: } static int -mlx5_tc_ct_entry_replace_rules(struct mlx5_tc_ct_priv *ct_priv, - struct flow_rule *flow_rule, - struct mlx5_ct_entry *entry, - u8 zone_restore_id) +mlx5_tc_ct_entry_update_rules(struct mlx5_tc_ct_priv *ct_priv, + struct flow_rule *flow_rule, + struct mlx5_ct_entry *entry, + u8 zone_restore_id) { int err = 0; if (mlx5_tc_ct_entry_in_ct_table(entry)) { - err = mlx5_tc_ct_entry_replace_rule(ct_priv, flow_rule, entry, false, - zone_restore_id); + err = mlx5_tc_ct_entry_update_rule(ct_priv, flow_rule, entry, false, + zone_restore_id); if (err) return err; } if (mlx5_tc_ct_entry_in_ct_nat_table(entry)) { - err = mlx5_tc_ct_entry_replace_rule(ct_priv, flow_rule, entry, true, - zone_restore_id); + err = mlx5_tc_ct_entry_update_rule(ct_priv, flow_rule, entry, true, + zone_restore_id); if (err && mlx5_tc_ct_entry_in_ct_table(entry)) mlx5_tc_ct_entry_del_rule(ct_priv, entry, false); } @@ -1165,13 +1161,13 @@ mlx5_tc_ct_entry_replace_rules(struct mlx5_tc_ct_priv *ct_priv, } static int -mlx5_tc_ct_block_flow_offload_replace(struct mlx5_ct_ft *ft, struct flow_rule *flow_rule, - struct mlx5_ct_entry *entry, unsigned long cookie) +mlx5_tc_ct_block_flow_offload_update(struct mlx5_ct_ft *ft, struct flow_rule *flow_rule, + struct mlx5_ct_entry *entry, unsigned long cookie) { struct mlx5_tc_ct_priv *ct_priv = ft->ct_priv; int err; - err = mlx5_tc_ct_entry_replace_rules(ct_priv, flow_rule, entry, ft->zone_restore_id); + err = mlx5_tc_ct_entry_update_rules(ct_priv, flow_rule, entry, ft->zone_restore_id); if (!err) return 0; @@ -1216,7 +1212,7 @@ mlx5_tc_ct_block_flow_offload_add(struct mlx5_ct_ft *ft, entry->restore_cookie = meta_action->ct_metadata.cookie; spin_unlock_bh(&ct_priv->ht_lock); - err = mlx5_tc_ct_block_flow_offload_replace(ft, flow_rule, entry, cookie); + err = mlx5_tc_ct_block_flow_offload_update(ft, flow_rule, entry, cookie); mlx5_tc_ct_entry_put(entry); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h index 6cc23af66b5b..efb34de4cb7a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h @@ -109,6 +109,7 @@ struct mlx5e_tc_flow { struct completion init_done; struct completion del_hw_done; struct mlx5_flow_attr *attr; + struct mlx5_flow_attr *extra_split_attr; struct list_head attrs; u32 chain_mapping; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c index 797db853de36..53cfa39188cb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c @@ -127,6 +127,7 @@ static void mlx5e_ipsec_packet_setup(void *obj, u32 pdn, MLX5_SET(ipsec_aso, aso_ctx, remove_flow_pkt_cnt, attrs->lft.hard_packet_limit); MLX5_SET(ipsec_aso, aso_ctx, hard_lft_arm, 1); + MLX5_SET(ipsec_aso, aso_ctx, remove_flow_enable, 1); } if (attrs->lft.soft_packet_limit != XFRM_INF) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 36845872ae94..4d123dae912c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -83,17 +83,15 @@ struct ptys2ethtool_config ptys2ext_ethtool_table[MLX5E_EXT_LINK_MODES_NUMBER]; ({ \ struct ptys2ethtool_config *cfg; \ const unsigned int modes[] = { __VA_ARGS__ }; \ - unsigned int i, bit, idx; \ + unsigned int i; \ cfg = &ptys2##table##_ethtool_table[reg_]; \ bitmap_zero(cfg->supported, \ __ETHTOOL_LINK_MODE_MASK_NBITS); \ bitmap_zero(cfg->advertised, \ __ETHTOOL_LINK_MODE_MASK_NBITS); \ for (i = 0 ; i < ARRAY_SIZE(modes) ; ++i) { \ - bit = modes[i] % 64; \ - idx = modes[i] / 64; \ - __set_bit(bit, &cfg->supported[idx]); \ - __set_bit(bit, &cfg->advertised[idx]); \ + bitmap_set(cfg->supported, modes[i], 1); \ + bitmap_set(cfg->advertised, modes[i], 1); \ } \ }) @@ -354,35 +352,25 @@ static void mlx5e_get_ringparam(struct net_device *dev, } int mlx5e_ethtool_set_ringparam(struct mlx5e_priv *priv, - struct ethtool_ringparam *param) + struct ethtool_ringparam *param, + struct netlink_ext_ack *extack) { struct mlx5e_params new_params; u8 log_rq_size; u8 log_sq_size; int err = 0; - if (param->rx_jumbo_pending) { - netdev_info(priv->netdev, "%s: rx_jumbo_pending not supported\n", - __func__); - return -EINVAL; - } - if (param->rx_mini_pending) { - netdev_info(priv->netdev, "%s: rx_mini_pending not supported\n", - __func__); - return -EINVAL; - } - if (param->rx_pending < (1 << MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE)) { - netdev_info(priv->netdev, "%s: rx_pending (%d) < min (%d)\n", - __func__, param->rx_pending, - 1 << MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE); + NL_SET_ERR_MSG_FMT_MOD(extack, "rx (%d) < min (%d)", + param->rx_pending, + 1 << MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE); return -EINVAL; } if (param->tx_pending < (1 << MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE)) { - netdev_info(priv->netdev, "%s: tx_pending (%d) < min (%d)\n", - __func__, param->tx_pending, - 1 << MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE); + NL_SET_ERR_MSG_FMT_MOD(extack, "tx (%d) < min (%d)", + param->tx_pending, + 1 << MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE); return -EINVAL; } @@ -418,7 +406,7 @@ static int mlx5e_set_ringparam(struct net_device *dev, { struct mlx5e_priv *priv = netdev_priv(dev); - return mlx5e_ethtool_set_ringparam(priv, param); + return mlx5e_ethtool_set_ringparam(priv, param, extack); } void mlx5e_ethtool_get_channels(struct mlx5e_priv *priv, @@ -445,7 +433,6 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv, unsigned int count = ch->combined_count; struct mlx5e_params new_params; bool arfs_enabled; - int rss_cnt; bool opened; int err = 0; @@ -499,17 +486,6 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv, goto out; } - /* Don't allow changing the number of channels if non-default RSS contexts exist, - * the kernel doesn't protect against set_channels operations that break them. - */ - rss_cnt = mlx5e_rx_res_rss_cnt(priv->rx_res) - 1; - if (rss_cnt) { - err = -EINVAL; - netdev_err(priv->netdev, "%s: Non-default RSS contexts exist (%d), cannot change the number of channels\n", - __func__, rss_cnt); - goto out; - } - /* Don't allow changing the number of channels if MQPRIO mode channel offload is active, * because it defines a partition over the channels queues. */ @@ -557,12 +533,15 @@ static int mlx5e_set_channels(struct net_device *dev, int mlx5e_ethtool_get_coalesce(struct mlx5e_priv *priv, struct ethtool_coalesce *coal, - struct kernel_ethtool_coalesce *kernel_coal) + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) { struct dim_cq_moder *rx_moder, *tx_moder; - if (!MLX5_CAP_GEN(priv->mdev, cq_moderation)) + if (!MLX5_CAP_GEN(priv->mdev, cq_moderation)) { + NL_SET_ERR_MSG_MOD(extack, "CQ moderation not supported"); return -EOPNOTSUPP; + } rx_moder = &priv->channels.params.rx_cq_moderation; coal->rx_coalesce_usecs = rx_moder->usec; @@ -586,7 +565,7 @@ static int mlx5e_get_coalesce(struct net_device *netdev, { struct mlx5e_priv *priv = netdev_priv(netdev); - return mlx5e_ethtool_get_coalesce(priv, coal, kernel_coal); + return mlx5e_ethtool_get_coalesce(priv, coal, kernel_coal, extack); } static int mlx5e_ethtool_get_per_queue_coalesce(struct mlx5e_priv *priv, u32 queue, @@ -708,26 +687,34 @@ int mlx5e_ethtool_set_coalesce(struct mlx5e_priv *priv, int err = 0; if (!MLX5_CAP_GEN(mdev, cq_moderation) || - !MLX5_CAP_GEN(mdev, cq_period_mode_modify)) + !MLX5_CAP_GEN(mdev, cq_period_mode_modify)) { + NL_SET_ERR_MSG_MOD(extack, "CQ moderation not supported"); return -EOPNOTSUPP; + } if (coal->tx_coalesce_usecs > MLX5E_MAX_COAL_TIME || coal->rx_coalesce_usecs > MLX5E_MAX_COAL_TIME) { - netdev_info(priv->netdev, "%s: maximum coalesce time supported is %lu usecs\n", - __func__, MLX5E_MAX_COAL_TIME); + NL_SET_ERR_MSG_FMT_MOD( + extack, + "Max coalesce time %lu usecs, tx-usecs (%u) rx-usecs (%u)", + MLX5E_MAX_COAL_TIME, coal->tx_coalesce_usecs, + coal->rx_coalesce_usecs); return -ERANGE; } if (coal->tx_max_coalesced_frames > MLX5E_MAX_COAL_FRAMES || coal->rx_max_coalesced_frames > MLX5E_MAX_COAL_FRAMES) { - netdev_info(priv->netdev, "%s: maximum coalesced frames supported is %lu\n", - __func__, MLX5E_MAX_COAL_FRAMES); + NL_SET_ERR_MSG_FMT_MOD( + extack, + "Max coalesce frames %lu, tx-frames (%u) rx-frames (%u)", + MLX5E_MAX_COAL_FRAMES, coal->tx_max_coalesced_frames, + coal->rx_max_coalesced_frames); return -ERANGE; } if ((kernel_coal->use_cqe_mode_rx || kernel_coal->use_cqe_mode_tx) && !MLX5_CAP_GEN(priv->mdev, cq_period_start_from_cqe)) { - NL_SET_ERR_MSG_MOD(extack, "cqe_mode_rx/tx is not supported on this device"); + NL_SET_ERR_MSG_MOD(extack, "cqe-mode-rx/tx is not supported on this device"); return -EOPNOTSUPP; } @@ -1299,7 +1286,8 @@ static u32 mlx5e_ethtool2ptys_adver_link(const unsigned long *link_modes) u32 i, ptys_modes = 0; for (i = 0; i < MLX5E_LINK_MODES_NUMBER; ++i) { - if (*ptys2legacy_ethtool_table[i].advertised == 0) + if (bitmap_empty(ptys2legacy_ethtool_table[i].advertised, + __ETHTOOL_LINK_MODE_MASK_NBITS)) continue; if (bitmap_intersects(ptys2legacy_ethtool_table[i].advertised, link_modes, @@ -1313,18 +1301,18 @@ static u32 mlx5e_ethtool2ptys_adver_link(const unsigned long *link_modes) static u32 mlx5e_ethtool2ptys_ext_adver_link(const unsigned long *link_modes) { u32 i, ptys_modes = 0; - unsigned long modes[2]; + __ETHTOOL_DECLARE_LINK_MODE_MASK(modes); for (i = 0; i < MLX5E_EXT_LINK_MODES_NUMBER; ++i) { - if (ptys2ext_ethtool_table[i].advertised[0] == 0 && - ptys2ext_ethtool_table[i].advertised[1] == 0) + if (bitmap_empty(ptys2ext_ethtool_table[i].advertised, + __ETHTOOL_LINK_MODE_MASK_NBITS)) continue; - memset(modes, 0, sizeof(modes)); + bitmap_zero(modes, __ETHTOOL_LINK_MODE_MASK_NBITS); bitmap_and(modes, ptys2ext_ethtool_table[i].advertised, link_modes, __ETHTOOL_LINK_MODE_MASK_NBITS); - if (modes[0] == ptys2ext_ethtool_table[i].advertised[0] && - modes[1] == ptys2ext_ethtool_table[i].advertised[1]) + if (bitmap_equal(modes, ptys2ext_ethtool_table[i].advertised, + __ETHTOOL_LINK_MODE_MASK_NBITS)) ptys_modes |= MLX5E_PROT_MASK(i); } return ptys_modes; @@ -2015,8 +2003,10 @@ static int mlx5e_get_module_eeprom_by_page(struct net_device *netdev, if (size_read == -EINVAL) return -EINVAL; if (size_read < 0) { - netdev_err(priv->netdev, "%s: mlx5_query_module_eeprom_by_page failed:0x%x\n", - __func__, size_read); + NL_SET_ERR_MSG_FMT_MOD( + extack, + "Query module eeprom by page failed, read %u bytes, err %d\n", + i, size_read); return i; } @@ -2605,6 +2595,7 @@ static void mlx5e_get_ts_stats(struct net_device *netdev, const struct ethtool_ops mlx5e_ethtool_ops = { .cap_rss_ctx_supported = true, + .rxfh_per_ctx_key = true, .supported_coalesce_params = ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_MAX_FRAMES | ETHTOOL_COALESCE_USE_ADAPTIVE | diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 8790d57dc6db..b885042eef14 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -360,7 +360,7 @@ mlx5e_rep_set_ringparam(struct net_device *dev, { struct mlx5e_priv *priv = netdev_priv(dev); - return mlx5e_ethtool_set_ringparam(priv, param); + return mlx5e_ethtool_set_ringparam(priv, param, extack); } static void mlx5e_rep_get_channels(struct net_device *dev, @@ -386,7 +386,7 @@ static int mlx5e_rep_get_coalesce(struct net_device *netdev, { struct mlx5e_priv *priv = netdev_priv(netdev); - return mlx5e_ethtool_get_coalesce(priv, coal, kernel_coal); + return mlx5e_ethtool_get_coalesce(priv, coal, kernel_coal, extack); } static int mlx5e_rep_set_coalesce(struct net_device *netdev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 30673292e15f..6b3b1afe8312 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1740,10 +1740,118 @@ has_encap_dests(struct mlx5_flow_attr *attr) } static int +extra_split_attr_dests_needed(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *attr) +{ + bool int_dest = false, ext_dest = false; + struct mlx5_esw_flow_attr *esw_attr; + int i; + + if (flow->attr != attr || + !list_is_first(&attr->list, &flow->attrs)) + return 0; + + if (flow_flag_test(flow, SLOW)) + return 0; + + esw_attr = attr->esw_attr; + if (!esw_attr->split_count || + esw_attr->split_count == esw_attr->out_count - 1) + return 0; + + if (esw_attr->dest_int_port && + (esw_attr->dests[esw_attr->split_count].flags & + MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE)) + return esw_attr->split_count + 1; + + for (i = esw_attr->split_count; i < esw_attr->out_count; i++) { + /* external dest with encap is considered as internal by firmware */ + if (esw_attr->dests[i].vport == MLX5_VPORT_UPLINK && + !(esw_attr->dests[i].flags & MLX5_ESW_DEST_ENCAP_VALID)) + ext_dest = true; + else + int_dest = true; + + if (ext_dest && int_dest) + return esw_attr->split_count; + } + + return 0; +} + +static int +extra_split_attr_dests(struct mlx5e_tc_flow *flow, + struct mlx5_flow_attr *attr, int split_count) +{ + struct mlx5e_post_act *post_act = get_post_action(flow->priv); + struct mlx5e_tc_flow_parse_attr *parse_attr, *parse_attr2; + struct mlx5_esw_flow_attr *esw_attr, *esw_attr2; + struct mlx5e_post_act_handle *handle; + struct mlx5_flow_attr *attr2; + int i, j, err; + + if (IS_ERR(post_act)) + return PTR_ERR(post_act); + + attr2 = mlx5_alloc_flow_attr(mlx5e_get_flow_namespace(flow)); + parse_attr2 = kvzalloc(sizeof(*parse_attr), GFP_KERNEL); + if (!attr2 || !parse_attr2) { + err = -ENOMEM; + goto err_free; + } + attr2->parse_attr = parse_attr2; + + handle = mlx5e_tc_post_act_add(post_act, attr2); + if (IS_ERR(handle)) { + err = PTR_ERR(handle); + goto err_free; + } + + esw_attr = attr->esw_attr; + esw_attr2 = attr2->esw_attr; + esw_attr2->in_rep = esw_attr->in_rep; + + parse_attr = attr->parse_attr; + parse_attr2->filter_dev = parse_attr->filter_dev; + + for (i = split_count, j = 0; i < esw_attr->out_count; i++, j++) + esw_attr2->dests[j] = esw_attr->dests[i]; + + esw_attr2->out_count = j; + attr2->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + + err = mlx5e_tc_post_act_offload(post_act, handle); + if (err) + goto err_post_act_offload; + + err = mlx5e_tc_post_act_set_handle(flow->priv->mdev, handle, + &parse_attr->mod_hdr_acts); + if (err) + goto err_post_act_set_handle; + + esw_attr->out_count = split_count; + attr->extra_split_ft = mlx5e_tc_post_act_get_ft(post_act); + flow->extra_split_attr = attr2; + + attr2->post_act_handle = handle; + + return 0; + +err_post_act_set_handle: + mlx5e_tc_post_act_unoffload(post_act, handle); +err_post_act_offload: + mlx5e_tc_post_act_del(post_act, handle); +err_free: + kvfree(parse_attr2); + kfree(attr2); + return err; +} + +static int post_process_attr(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *attr, struct netlink_ext_ack *extack) { + int extra_split; bool vf_tun; int err = 0; @@ -1757,6 +1865,13 @@ post_process_attr(struct mlx5e_tc_flow *flow, goto err_out; } + extra_split = extra_split_attr_dests_needed(flow, attr); + if (extra_split > 0) { + err = extra_split_attr_dests(flow, attr, extra_split); + if (err) + goto err_out; + } + if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) { err = mlx5e_tc_attach_mod_hdr(flow->priv, flow, attr); if (err) @@ -1971,6 +2086,11 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, mlx5e_tc_act_stats_del_flow(get_act_stats_handle(priv), flow); free_flow_post_acts(flow); + if (flow->extra_split_attr) { + mlx5_free_flow_attr_actions(flow, flow->extra_split_attr); + kvfree(flow->extra_split_attr->parse_attr); + kfree(flow->extra_split_attr); + } mlx5_free_flow_attr_actions(flow, attr); kvfree(attr->esw_attr->rx_tun_attr); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h index c24bda56b2b5..e1b8cb78369f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h @@ -86,6 +86,7 @@ struct mlx5_flow_attr { u32 dest_chain; struct mlx5_flow_table *ft; struct mlx5_flow_table *dest_ft; + struct mlx5_flow_table *extra_split_ft; u8 inner_match_level; u8 outer_match_level; u8 tun_ip_version; @@ -139,7 +140,7 @@ struct mlx5_rx_tun_attr { #define MLX5E_TC_TABLE_CHAIN_TAG_BITS 16 #define MLX5E_TC_TABLE_CHAIN_TAG_MASK GENMASK(MLX5E_TC_TABLE_CHAIN_TAG_BITS - 1, 0) -#define MLX5E_TC_MAX_INT_PORT_NUM (8) +#define MLX5E_TC_MAX_INT_PORT_NUM (32) #if IS_ENABLED(CONFIG_MLX5_CLS_ACT) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index cb7e7e4104af..f15ecaef1331 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -835,28 +835,9 @@ static void comp_irq_release_pci(struct mlx5_core_dev *dev, u16 vecidx) mlx5_irq_release_vector(irq); } -static int mlx5_cpumask_default_spread(int numa_node, int index) +static int mlx5_cpumask_default_spread(struct mlx5_core_dev *dev, int index) { - const struct cpumask *prev = cpu_none_mask; - const struct cpumask *mask; - int found_cpu = 0; - int i = 0; - int cpu; - - rcu_read_lock(); - for_each_numa_hop_mask(mask, numa_node) { - for_each_cpu_andnot(cpu, mask, prev) { - if (i++ == index) { - found_cpu = cpu; - goto spread_done; - } - } - prev = mask; - } - -spread_done: - rcu_read_unlock(); - return found_cpu; + return cpumask_local_spread(index, dev->priv.numa_node); } static struct cpu_rmap *mlx5_eq_table_get_pci_rmap(struct mlx5_core_dev *dev) @@ -880,7 +861,7 @@ static int comp_irq_request_pci(struct mlx5_core_dev *dev, u16 vecidx) int cpu; rmap = mlx5_eq_table_get_pci_rmap(dev); - cpu = mlx5_cpumask_default_spread(dev->priv.numa_node, vecidx); + cpu = mlx5_cpumask_default_spread(dev, vecidx); irq = mlx5_irq_request_vector(dev, cpu, vecidx, &rmap); if (IS_ERR(irq)) return PTR_ERR(irq); @@ -1145,7 +1126,7 @@ int mlx5_comp_vector_get_cpu(struct mlx5_core_dev *dev, int vector) if (mask) cpu = cpumask_first(mask); else - cpu = mlx5_cpumask_default_spread(dev->priv.numa_node, vector); + cpu = mlx5_cpumask_default_spread(dev, vector); return cpu; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 578466d69f21..f44b4c7ebcfd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -887,9 +887,6 @@ int mlx5_esw_ipsec_vf_packet_offload_set(struct mlx5_eswitch *esw, struct mlx5_v bool enable); int mlx5_esw_ipsec_vf_packet_offload_supported(struct mlx5_core_dev *dev, u16 vport_num); -void mlx5_esw_vport_ipsec_offload_enable(struct mlx5_eswitch *esw); -void mlx5_esw_vport_ipsec_offload_disable(struct mlx5_eswitch *esw); - #else /* CONFIG_MLX5_ESWITCH */ /* eswitch API stubs */ static inline int mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 768199d2255a..f24f91d213f2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -613,6 +613,13 @@ esw_setup_dests(struct mlx5_flow_destination *dest, } } + if (attr->extra_split_ft) { + flow_act->flags |= FLOW_ACT_IGNORE_FLOW_LEVEL; + dest[*i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; + dest[*i].ft = attr->extra_split_ft; + (*i)++; + } + out: return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c index b61b7d966114..76ad46bf477d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c @@ -224,6 +224,7 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev) if (MLX5_CAP_GEN(dev, mcam_reg)) { mlx5_get_mcam_access_reg_group(dev, MLX5_MCAM_REGS_FIRST_128); mlx5_get_mcam_access_reg_group(dev, MLX5_MCAM_REGS_0x9100_0x917F); + mlx5_get_mcam_access_reg_group(dev, MLX5_MCAM_REGS_0x9180_0x91FF); } if (MLX5_CAP_GEN(dev, qcam_reg)) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c index 26f8a11b8906..9772327d5124 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c @@ -74,7 +74,7 @@ static int mlx5i_set_ringparam(struct net_device *dev, { struct mlx5e_priv *priv = mlx5i_epriv(dev); - return mlx5e_ethtool_set_ringparam(priv, param); + return mlx5e_ethtool_set_ringparam(priv, param, extack); } static void mlx5i_get_ringparam(struct net_device *dev, @@ -132,7 +132,7 @@ static int mlx5i_get_coalesce(struct net_device *netdev, { struct mlx5e_priv *priv = mlx5i_epriv(netdev); - return mlx5e_ethtool_get_coalesce(priv, coal, kernel_coal); + return mlx5e_ethtool_get_coalesce(priv, coal, kernel_coal, extack); } static int mlx5i_get_ts_info(struct net_device *netdev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index 0361741632a6..b306ae79bf97 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -38,6 +38,10 @@ #include "lib/eq.h" #include "en.h" #include "clock.h" +#ifdef CONFIG_X86 +#include <linux/timekeeping.h> +#include <linux/cpufeature.h> +#endif /* CONFIG_X86 */ enum { MLX5_PIN_MODE_IN = 0x0, @@ -148,6 +152,87 @@ static int mlx5_set_mtutc(struct mlx5_core_dev *dev, u32 *mtutc, u32 size) MLX5_REG_MTUTC, 0, 1); } +#ifdef CONFIG_X86 +static bool mlx5_is_ptm_source_time_available(struct mlx5_core_dev *dev) +{ + u32 out[MLX5_ST_SZ_DW(mtptm_reg)] = {0}; + u32 in[MLX5_ST_SZ_DW(mtptm_reg)] = {0}; + int err; + + if (!MLX5_CAP_MCAM_REG3(dev, mtptm)) + return false; + + err = mlx5_core_access_reg(dev, in, sizeof(in), out, sizeof(out), MLX5_REG_MTPTM, + 0, 0); + if (err) + return false; + + return !!MLX5_GET(mtptm_reg, out, psta); +} + +static int mlx5_mtctr_syncdevicetime(ktime_t *device_time, + struct system_counterval_t *sys_counterval, + void *ctx) +{ + u32 out[MLX5_ST_SZ_DW(mtctr_reg)] = {0}; + u32 in[MLX5_ST_SZ_DW(mtctr_reg)] = {0}; + struct mlx5_core_dev *mdev = ctx; + bool real_time_mode; + u64 host, device; + int err; + + real_time_mode = mlx5_real_time_mode(mdev); + + MLX5_SET(mtctr_reg, in, first_clock_timestamp_request, + MLX5_MTCTR_REQUEST_PTM_ROOT_CLOCK); + MLX5_SET(mtctr_reg, in, second_clock_timestamp_request, + real_time_mode ? MLX5_MTCTR_REQUEST_REAL_TIME_CLOCK : + MLX5_MTCTR_REQUEST_FREE_RUNNING_COUNTER); + + err = mlx5_core_access_reg(mdev, in, sizeof(in), out, sizeof(out), MLX5_REG_MTCTR, + 0, 0); + if (err) + return err; + + if (!MLX5_GET(mtctr_reg, out, first_clock_valid) || + !MLX5_GET(mtctr_reg, out, second_clock_valid)) + return -EINVAL; + + host = MLX5_GET64(mtctr_reg, out, first_clock_timestamp); + *sys_counterval = (struct system_counterval_t) { + .cycles = host, + .cs_id = CSID_X86_ART, + .use_nsecs = true, + }; + + device = MLX5_GET64(mtctr_reg, out, second_clock_timestamp); + if (real_time_mode) + *device_time = ns_to_ktime(REAL_TIME_TO_NS(device >> 32, device & U32_MAX)); + else + *device_time = mlx5_timecounter_cyc2time(&mdev->clock, device); + + return 0; +} + +static int mlx5_ptp_getcrosststamp(struct ptp_clock_info *ptp, + struct system_device_crosststamp *cts) +{ + struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info); + struct system_time_snapshot history_begin = {0}; + struct mlx5_core_dev *mdev; + + mdev = container_of(clock, struct mlx5_core_dev, clock); + + if (!mlx5_is_ptm_source_time_available(mdev)) + return -EBUSY; + + ktime_get_snapshot(&history_begin); + + return get_device_system_crosststamp(mlx5_mtctr_syncdevicetime, mdev, + &history_begin, cts); +} +#endif /* CONFIG_X86 */ + static u64 mlx5_read_time(struct mlx5_core_dev *dev, struct ptp_system_timestamp *sts, bool real_time) @@ -1034,6 +1119,12 @@ static void mlx5_init_timer_clock(struct mlx5_core_dev *mdev) if (MLX5_CAP_MCAM_REG(mdev, mtutc)) mlx5_init_timer_max_freq_adjustment(mdev); +#ifdef CONFIG_X86 + if (MLX5_CAP_MCAM_REG3(mdev, mtptm) && + MLX5_CAP_MCAM_REG3(mdev, mtctr) && boot_cpu_has(X86_FEATURE_ART)) + clock->ptp_info.getcrosststamp = mlx5_ptp_getcrosststamp; +#endif /* CONFIG_X86 */ + mlx5_timecounter_init(mdev); mlx5_init_clock_info(mdev); mlx5_init_overflow_period(clock); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 5b7e6f4b5c7e..4b88d969a66c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -923,6 +923,11 @@ static int mlx5_pci_init(struct mlx5_core_dev *dev, struct pci_dev *pdev, } mlx5_pci_vsc_init(dev); + + err = pci_enable_ptm(pdev, NULL); + if (err) + mlx5_core_info(dev, "PTM is not supported by PCIe\n"); + return 0; err_clr_master: @@ -939,6 +944,7 @@ static void mlx5_pci_close(struct mlx5_core_dev *dev) * before removing the pci bars */ mlx5_drain_health_wq(dev); + pci_disable_ptm(dev->pdev); iounmap(dev->iseg); release_bar(dev->pdev); mlx5_pci_disable_device(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c index d894a88fa9f2..972e8e9df585 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c @@ -608,6 +608,11 @@ enum { RELEASE_ALL_PAGES_MASK = 0x4000, }; +/* This limit is based on the capability of the firmware as it cannot release + * more than 50000 back to the host in one go. + */ +#define MAX_RECLAIM_NPAGES (-50000) + static int req_pages_handler(struct notifier_block *nb, unsigned long type, void *data) { @@ -639,7 +644,16 @@ static int req_pages_handler(struct notifier_block *nb, req->dev = dev; req->func_id = func_id; - req->npages = npages; + + /* npages > 0 means HCA asking host to allocate/give pages, + * npages < 0 means HCA asking host to reclaim back the pages allocated. + * Here we are restricting the maximum number of pages that can be + * reclaimed to be MAX_RECLAIM_NPAGES. Note that MAX_RECLAIM_NPAGES is + * a negative value. + * Since MAX_RECLAIM is negative, we are using max() to restrict + * req->npages (and not min ()). + */ + req->npages = max_t(s32, npages, MAX_RECLAIM_NPAGES); req->ec_function = ec_function; req->release_all = release_all; INIT_WORK(&req->work, pages_work_handler); diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c index d61478c0c632..303d2ce4dc1e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c @@ -411,7 +411,7 @@ static const struct thermal_cooling_device_ops mlxsw_cooling_ops = { static int mlxsw_thermal_module_tz_init(struct mlxsw_thermal_module *module_tz) { - char tz_name[THERMAL_NAME_LENGTH]; + char tz_name[40]; int err; if (module_tz->slot_index) @@ -445,17 +445,13 @@ static void mlxsw_thermal_module_tz_fini(struct thermal_zone_device *tzdev) thermal_zone_device_unregister(tzdev); } -static void -mlxsw_thermal_module_init(struct device *dev, struct mlxsw_core *core, - struct mlxsw_thermal *thermal, +static int +mlxsw_thermal_module_init(struct mlxsw_thermal *thermal, struct mlxsw_thermal_area *area, u8 module) { struct mlxsw_thermal_module *module_tz; module_tz = &area->tz_module_arr[module]; - /* Skip if parent is already set (case of port split). */ - if (module_tz->parent) - return; module_tz->module = module; module_tz->slot_index = area->slot_index; module_tz->parent = thermal; @@ -465,15 +461,13 @@ mlxsw_thermal_module_init(struct device *dev, struct mlxsw_core *core, sizeof(thermal->trips)); memcpy(module_tz->cooling_states, default_cooling_states, sizeof(thermal->cooling_states)); + + return mlxsw_thermal_module_tz_init(module_tz); } static void mlxsw_thermal_module_fini(struct mlxsw_thermal_module *module_tz) { - if (module_tz && module_tz->tzdev) { - mlxsw_thermal_module_tz_fini(module_tz->tzdev); - module_tz->tzdev = NULL; - module_tz->parent = NULL; - } + mlxsw_thermal_module_tz_fini(module_tz->tzdev); } static int @@ -481,7 +475,6 @@ mlxsw_thermal_modules_init(struct device *dev, struct mlxsw_core *core, struct mlxsw_thermal *thermal, struct mlxsw_thermal_area *area) { - struct mlxsw_thermal_module *module_tz; char mgpir_pl[MLXSW_REG_MGPIR_LEN]; int i, err; @@ -503,22 +496,16 @@ mlxsw_thermal_modules_init(struct device *dev, struct mlxsw_core *core, if (!area->tz_module_arr) return -ENOMEM; - for (i = 0; i < area->tz_module_num; i++) - mlxsw_thermal_module_init(dev, core, thermal, area, i); - for (i = 0; i < area->tz_module_num; i++) { - module_tz = &area->tz_module_arr[i]; - if (!module_tz->parent) - continue; - err = mlxsw_thermal_module_tz_init(module_tz); + err = mlxsw_thermal_module_init(thermal, area, i); if (err) - goto err_thermal_module_tz_init; + goto err_thermal_module_init; } return 0; -err_thermal_module_tz_init: - for (i = area->tz_module_num - 1; i >= 0; i--) +err_thermal_module_init: + for (i--; i >= 0; i--) mlxsw_thermal_module_fini(&area->tz_module_arr[i]); kfree(area->tz_module_arr); return err; @@ -821,10 +808,7 @@ err_linecards_event_ops_register: err_thermal_gearboxes_init: mlxsw_thermal_modules_fini(thermal, &thermal->line_cards[0]); err_thermal_modules_init: - if (thermal->tzdev) { - thermal_zone_device_unregister(thermal->tzdev); - thermal->tzdev = NULL; - } + thermal_zone_device_unregister(thermal->tzdev); err_thermal_zone_device_register: err_thermal_cooling_device_register: for (i = 0; i < MLXSW_MFCR_PWMS_MAX; i++) @@ -845,10 +829,7 @@ void mlxsw_thermal_fini(struct mlxsw_thermal *thermal) thermal); mlxsw_thermal_gearboxes_fini(thermal, &thermal->line_cards[0]); mlxsw_thermal_modules_fini(thermal, &thermal->line_cards[0]); - if (thermal->tzdev) { - thermal_zone_device_unregister(thermal->tzdev); - thermal->tzdev = NULL; - } + thermal_zone_device_unregister(thermal->tzdev); for (i = 0; i < MLXSW_MFCR_PWMS_MAX; i++) thermal_cooling_device_unregister(thermal->cdevs[i].cdev); diff --git a/drivers/net/ethernet/meta/Kconfig b/drivers/net/ethernet/meta/Kconfig index c002ede36402..85519690b837 100644 --- a/drivers/net/ethernet/meta/Kconfig +++ b/drivers/net/ethernet/meta/Kconfig @@ -23,6 +23,8 @@ config FBNIC depends on !S390 depends on MAX_SKB_FRAGS < 22 depends on PCI_MSI + select NET_DEVLINK + select PAGE_POOL select PHYLINK help This driver supports Meta Platforms Host Network Interface. diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c index b7ce6da68543..571374361259 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c @@ -4,6 +4,7 @@ #include <linux/etherdevice.h> #include <linux/ipv6.h> #include <linux/types.h> +#include <net/netdev_queues.h> #include "fbnic.h" #include "fbnic_netdev.h" @@ -316,6 +317,74 @@ void fbnic_clear_rx_mode(struct net_device *netdev) __dev_mc_unsync(netdev, NULL); } +static void fbnic_get_stats64(struct net_device *dev, + struct rtnl_link_stats64 *stats64) +{ + u64 tx_bytes, tx_packets, tx_dropped = 0; + u64 rx_bytes, rx_packets, rx_dropped = 0; + struct fbnic_net *fbn = netdev_priv(dev); + struct fbnic_queue_stats *stats; + unsigned int start, i; + + stats = &fbn->tx_stats; + + tx_bytes = stats->bytes; + tx_packets = stats->packets; + tx_dropped = stats->dropped; + + stats64->tx_bytes = tx_bytes; + stats64->tx_packets = tx_packets; + stats64->tx_dropped = tx_dropped; + + for (i = 0; i < fbn->num_tx_queues; i++) { + struct fbnic_ring *txr = fbn->tx[i]; + + if (!txr) + continue; + + stats = &txr->stats; + do { + start = u64_stats_fetch_begin(&stats->syncp); + tx_bytes = stats->bytes; + tx_packets = stats->packets; + tx_dropped = stats->dropped; + } while (u64_stats_fetch_retry(&stats->syncp, start)); + + stats64->tx_bytes += tx_bytes; + stats64->tx_packets += tx_packets; + stats64->tx_dropped += tx_dropped; + } + + stats = &fbn->rx_stats; + + rx_bytes = stats->bytes; + rx_packets = stats->packets; + rx_dropped = stats->dropped; + + stats64->rx_bytes = rx_bytes; + stats64->rx_packets = rx_packets; + stats64->rx_dropped = rx_dropped; + + for (i = 0; i < fbn->num_rx_queues; i++) { + struct fbnic_ring *rxr = fbn->rx[i]; + + if (!rxr) + continue; + + stats = &rxr->stats; + do { + start = u64_stats_fetch_begin(&stats->syncp); + rx_bytes = stats->bytes; + rx_packets = stats->packets; + rx_dropped = stats->dropped; + } while (u64_stats_fetch_retry(&stats->syncp, start)); + + stats64->rx_bytes += rx_bytes; + stats64->rx_packets += rx_packets; + stats64->rx_dropped += rx_dropped; + } +} + static const struct net_device_ops fbnic_netdev_ops = { .ndo_open = fbnic_open, .ndo_stop = fbnic_stop, @@ -324,6 +393,72 @@ static const struct net_device_ops fbnic_netdev_ops = { .ndo_features_check = fbnic_features_check, .ndo_set_mac_address = fbnic_set_mac, .ndo_set_rx_mode = fbnic_set_rx_mode, + .ndo_get_stats64 = fbnic_get_stats64, +}; + +static void fbnic_get_queue_stats_rx(struct net_device *dev, int idx, + struct netdev_queue_stats_rx *rx) +{ + struct fbnic_net *fbn = netdev_priv(dev); + struct fbnic_ring *rxr = fbn->rx[idx]; + struct fbnic_queue_stats *stats; + unsigned int start; + u64 bytes, packets; + + if (!rxr) + return; + + stats = &rxr->stats; + do { + start = u64_stats_fetch_begin(&stats->syncp); + bytes = stats->bytes; + packets = stats->packets; + } while (u64_stats_fetch_retry(&stats->syncp, start)); + + rx->bytes = bytes; + rx->packets = packets; +} + +static void fbnic_get_queue_stats_tx(struct net_device *dev, int idx, + struct netdev_queue_stats_tx *tx) +{ + struct fbnic_net *fbn = netdev_priv(dev); + struct fbnic_ring *txr = fbn->tx[idx]; + struct fbnic_queue_stats *stats; + unsigned int start; + u64 bytes, packets; + + if (!txr) + return; + + stats = &txr->stats; + do { + start = u64_stats_fetch_begin(&stats->syncp); + bytes = stats->bytes; + packets = stats->packets; + } while (u64_stats_fetch_retry(&stats->syncp, start)); + + tx->bytes = bytes; + tx->packets = packets; +} + +static void fbnic_get_base_stats(struct net_device *dev, + struct netdev_queue_stats_rx *rx, + struct netdev_queue_stats_tx *tx) +{ + struct fbnic_net *fbn = netdev_priv(dev); + + tx->bytes = fbn->tx_stats.bytes; + tx->packets = fbn->tx_stats.packets; + + rx->bytes = fbn->rx_stats.bytes; + rx->packets = fbn->rx_stats.packets; +} + +static const struct netdev_stat_ops fbnic_stat_ops = { + .get_queue_stats_rx = fbnic_get_queue_stats_rx, + .get_queue_stats_tx = fbnic_get_queue_stats_tx, + .get_base_stats = fbnic_get_base_stats, }; void fbnic_reset_queues(struct fbnic_net *fbn, @@ -384,6 +519,7 @@ struct net_device *fbnic_netdev_alloc(struct fbnic_dev *fbd) fbd->netdev = netdev; netdev->netdev_ops = &fbnic_netdev_ops; + netdev->stat_ops = &fbnic_stat_ops; fbn = netdev_priv(netdev); diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h index 6bc0ebeb8182..60199e634468 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h @@ -40,6 +40,9 @@ struct fbnic_net { u32 rss_key[FBNIC_RPC_RSS_KEY_DWORD_LEN]; u32 rss_flow_hash[FBNIC_NUM_HASH_OPT]; + /* Storage for stats after ring destruction */ + struct fbnic_queue_stats tx_stats; + struct fbnic_queue_stats rx_stats; u64 link_down_events; struct list_head napis; diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c index 0ed4c9fff5d8..4d0406af297f 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c @@ -273,6 +273,9 @@ fbnic_xmit_frame_ring(struct sk_buff *skb, struct fbnic_ring *ring) err_free: dev_kfree_skb_any(skb); err_count: + u64_stats_update_begin(&ring->stats.syncp); + ring->stats.dropped++; + u64_stats_update_end(&ring->stats.syncp); return NETDEV_TX_OK; } @@ -363,10 +366,19 @@ static void fbnic_clean_twq0(struct fbnic_napi_vector *nv, int napi_budget, txq = txring_txq(nv->napi.dev, ring); if (unlikely(discard)) { + u64_stats_update_begin(&ring->stats.syncp); + ring->stats.dropped += total_packets; + u64_stats_update_end(&ring->stats.syncp); + netdev_tx_completed_queue(txq, total_packets, total_bytes); return; } + u64_stats_update_begin(&ring->stats.syncp); + ring->stats.bytes += total_bytes; + ring->stats.packets += total_packets; + u64_stats_update_end(&ring->stats.syncp); + netif_txq_completed_wake(txq, total_packets, total_bytes, fbnic_desc_unused(ring), FBNIC_TX_DESC_WAKEUP); @@ -730,12 +742,12 @@ static bool fbnic_rcd_metadata_err(u64 rcd) static int fbnic_clean_rcq(struct fbnic_napi_vector *nv, struct fbnic_q_triad *qt, int budget) { + unsigned int packets = 0, bytes = 0, dropped = 0; struct fbnic_ring *rcq = &qt->cmpl; struct fbnic_pkt_buff *pkt; s32 head0 = -1, head1 = -1; __le64 *raw_rcd, done; u32 head = rcq->head; - u64 packets = 0; done = (head & (rcq->size_mask + 1)) ? cpu_to_le64(FBNIC_RCD_DONE) : 0; raw_rcd = &rcq->desc[head & rcq->size_mask]; @@ -780,9 +792,11 @@ static int fbnic_clean_rcq(struct fbnic_napi_vector *nv, fbnic_populate_skb_fields(nv, rcd, skb, qt); packets++; + bytes += skb->len; napi_gro_receive(&nv->napi, skb); } else { + dropped++; fbnic_put_pkt_buff(nv, pkt, 1); } @@ -799,6 +813,14 @@ static int fbnic_clean_rcq(struct fbnic_napi_vector *nv, } } + u64_stats_update_begin(&rcq->stats.syncp); + rcq->stats.packets += packets; + rcq->stats.bytes += bytes; + /* Re-add ethernet header length (removed in fbnic_build_skb) */ + rcq->stats.bytes += ETH_HLEN * packets; + rcq->stats.dropped += dropped; + u64_stats_update_end(&rcq->stats.syncp); + /* Unmap and free processed buffers */ if (head0 >= 0) fbnic_clean_bdq(nv, budget, &qt->sub0, head0); @@ -865,12 +887,36 @@ static irqreturn_t fbnic_msix_clean_rings(int __always_unused irq, void *data) return IRQ_HANDLED; } +static void fbnic_aggregate_ring_rx_counters(struct fbnic_net *fbn, + struct fbnic_ring *rxr) +{ + struct fbnic_queue_stats *stats = &rxr->stats; + + /* Capture stats from queues before dissasociating them */ + fbn->rx_stats.bytes += stats->bytes; + fbn->rx_stats.packets += stats->packets; + fbn->rx_stats.dropped += stats->dropped; +} + +static void fbnic_aggregate_ring_tx_counters(struct fbnic_net *fbn, + struct fbnic_ring *txr) +{ + struct fbnic_queue_stats *stats = &txr->stats; + + /* Capture stats from queues before dissasociating them */ + fbn->tx_stats.bytes += stats->bytes; + fbn->tx_stats.packets += stats->packets; + fbn->tx_stats.dropped += stats->dropped; +} + static void fbnic_remove_tx_ring(struct fbnic_net *fbn, struct fbnic_ring *txr) { if (!(txr->flags & FBNIC_RING_F_STATS)) return; + fbnic_aggregate_ring_tx_counters(fbn, txr); + /* Remove pointer to the Tx ring */ WARN_ON(fbn->tx[txr->q_idx] && fbn->tx[txr->q_idx] != txr); fbn->tx[txr->q_idx] = NULL; @@ -882,6 +928,8 @@ static void fbnic_remove_rx_ring(struct fbnic_net *fbn, if (!(rxr->flags & FBNIC_RING_F_STATS)) return; + fbnic_aggregate_ring_rx_counters(fbn, rxr); + /* Remove pointer to the Rx ring */ WARN_ON(fbn->rx[rxr->q_idx] && fbn->rx[rxr->q_idx] != rxr); fbn->rx[rxr->q_idx] = NULL; @@ -974,6 +1022,7 @@ static int fbnic_alloc_nv_page_pool(struct fbnic_net *fbn, static void fbnic_ring_init(struct fbnic_ring *ring, u32 __iomem *doorbell, int q_idx, u8 flags) { + u64_stats_init(&ring->stats.syncp); ring->doorbell = doorbell; ring->q_idx = q_idx; ring->flags = flags; diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h index 4a206c0e7192..2f91f68d11d5 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h @@ -7,6 +7,7 @@ #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/types.h> +#include <linux/u64_stats_sync.h> #include <net/xdp.h> struct fbnic_net; @@ -51,6 +52,13 @@ struct fbnic_pkt_buff { u16 nr_frags; }; +struct fbnic_queue_stats { + u64 packets; + u64 bytes; + u64 dropped; + struct u64_stats_sync syncp; +}; + /* Pagecnt bias is long max to reserve the last bit to catch overflow * cases where if we overcharge the bias it will flip over to be negative. */ @@ -77,6 +85,8 @@ struct fbnic_ring { u32 head, tail; /* Head/Tail of ring */ + struct fbnic_queue_stats stats; + /* Slow path fields follow */ dma_addr_t dma; /* Phys addr of descriptor memory */ size_t size; /* Size of descriptor ring in memory */ diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 39f56973746d..3e865985340e 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -511,7 +511,7 @@ static u16 mana_select_queue(struct net_device *ndev, struct sk_buff *skb, } /* Release pre-allocated RX buffers */ -static void mana_pre_dealloc_rxbufs(struct mana_port_context *mpc) +void mana_pre_dealloc_rxbufs(struct mana_port_context *mpc) { struct device *dev; int i; @@ -608,7 +608,7 @@ static void mana_get_rxbuf_cfg(int mtu, u32 *datasize, u32 *alloc_size, *datasize = mtu + ETH_HLEN; } -static int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu) +int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu) { struct device *dev; struct page *page; @@ -622,7 +622,7 @@ static int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu) dev = mpc->ac->gdma_dev->gdma_context->dev; - num_rxb = mpc->num_queues * RX_BUFFERS_PER_QUEUE; + num_rxb = mpc->num_queues * mpc->rx_queue_size; WARN(mpc->rxbufs_pre, "mana rxbufs_pre exists\n"); mpc->rxbufs_pre = kmalloc_array(num_rxb, sizeof(void *), GFP_KERNEL); @@ -1909,15 +1909,17 @@ static int mana_create_txq(struct mana_port_context *apc, return -ENOMEM; /* The minimum size of the WQE is 32 bytes, hence - * MAX_SEND_BUFFERS_PER_QUEUE represents the maximum number of WQEs + * apc->tx_queue_size represents the maximum number of WQEs * the SQ can store. This value is then used to size other queues * to prevent overflow. + * Also note that the txq_size is always going to be MANA_PAGE_ALIGNED, + * as min val of apc->tx_queue_size is 128 and that would make + * txq_size 128*32 = 4096 and the other higher values of apc->tx_queue_size + * are always power of two */ - txq_size = MAX_SEND_BUFFERS_PER_QUEUE * 32; - BUILD_BUG_ON(!MANA_PAGE_ALIGNED(txq_size)); + txq_size = apc->tx_queue_size * 32; - cq_size = MAX_SEND_BUFFERS_PER_QUEUE * COMP_ENTRY_SIZE; - cq_size = MANA_PAGE_ALIGN(cq_size); + cq_size = apc->tx_queue_size * COMP_ENTRY_SIZE; gc = gd->gdma_context; @@ -2155,10 +2157,11 @@ static int mana_push_wqe(struct mana_rxq *rxq) static int mana_create_page_pool(struct mana_rxq *rxq, struct gdma_context *gc) { + struct mana_port_context *mpc = netdev_priv(rxq->ndev); struct page_pool_params pprm = {}; int ret; - pprm.pool_size = RX_BUFFERS_PER_QUEUE; + pprm.pool_size = mpc->rx_queue_size; pprm.nid = gc->numa_node; pprm.napi = &rxq->rx_cq.napi; pprm.netdev = rxq->ndev; @@ -2190,13 +2193,13 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc, gc = gd->gdma_context; - rxq = kzalloc(struct_size(rxq, rx_oobs, RX_BUFFERS_PER_QUEUE), + rxq = kzalloc(struct_size(rxq, rx_oobs, apc->rx_queue_size), GFP_KERNEL); if (!rxq) return NULL; rxq->ndev = ndev; - rxq->num_rx_buf = RX_BUFFERS_PER_QUEUE; + rxq->num_rx_buf = apc->rx_queue_size; rxq->rxq_idx = rxq_idx; rxq->rxobj = INVALID_MANA_HANDLE; @@ -2744,6 +2747,8 @@ static int mana_probe_port(struct mana_context *ac, int port_idx, apc->ndev = ndev; apc->max_queues = gc->max_num_queues; apc->num_queues = gc->max_num_queues; + apc->tx_queue_size = DEF_TX_BUFFERS_PER_QUEUE; + apc->rx_queue_size = DEF_RX_BUFFERS_PER_QUEUE; apc->port_handle = INVALID_MANA_HANDLE; apc->pf_filter_handle = INVALID_MANA_HANDLE; apc->port_idx = port_idx; diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c index 146d5db1792f..d6a35fbda447 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c +++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c @@ -369,6 +369,78 @@ static int mana_set_channels(struct net_device *ndev, return err; } +static void mana_get_ringparam(struct net_device *ndev, + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) +{ + struct mana_port_context *apc = netdev_priv(ndev); + + ring->rx_pending = apc->rx_queue_size; + ring->tx_pending = apc->tx_queue_size; + ring->rx_max_pending = MAX_RX_BUFFERS_PER_QUEUE; + ring->tx_max_pending = MAX_TX_BUFFERS_PER_QUEUE; +} + +static int mana_set_ringparam(struct net_device *ndev, + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) +{ + struct mana_port_context *apc = netdev_priv(ndev); + u32 new_tx, new_rx; + u32 old_tx, old_rx; + int err; + + old_tx = apc->tx_queue_size; + old_rx = apc->rx_queue_size; + + if (ring->tx_pending < MIN_TX_BUFFERS_PER_QUEUE) { + NL_SET_ERR_MSG_FMT(extack, "tx:%d less than the min:%d", ring->tx_pending, + MIN_TX_BUFFERS_PER_QUEUE); + return -EINVAL; + } + + if (ring->rx_pending < MIN_RX_BUFFERS_PER_QUEUE) { + NL_SET_ERR_MSG_FMT(extack, "rx:%d less than the min:%d", ring->rx_pending, + MIN_RX_BUFFERS_PER_QUEUE); + return -EINVAL; + } + + new_rx = roundup_pow_of_two(ring->rx_pending); + new_tx = roundup_pow_of_two(ring->tx_pending); + netdev_info(ndev, "Using nearest power of 2 values for Txq:%d Rxq:%d\n", + new_tx, new_rx); + + /* pre-allocating new buffers to prevent failures in mana_attach() later */ + apc->rx_queue_size = new_rx; + err = mana_pre_alloc_rxbufs(apc, ndev->mtu); + apc->rx_queue_size = old_rx; + if (err) { + netdev_err(ndev, "Insufficient memory for new allocations\n"); + return err; + } + + err = mana_detach(ndev, false); + if (err) { + netdev_err(ndev, "mana_detach failed: %d\n", err); + goto out; + } + + apc->tx_queue_size = new_tx; + apc->rx_queue_size = new_rx; + + err = mana_attach(ndev); + if (err) { + netdev_err(ndev, "mana_attach failed: %d\n", err); + apc->tx_queue_size = old_tx; + apc->rx_queue_size = old_rx; + } +out: + mana_pre_dealloc_rxbufs(apc); + return err; +} + const struct ethtool_ops mana_ethtool_ops = { .get_ethtool_stats = mana_get_ethtool_stats, .get_sset_count = mana_get_sset_count, @@ -380,4 +452,6 @@ const struct ethtool_ops mana_ethtool_ops = { .set_rxfh = mana_set_rxfh, .get_channels = mana_get_channels, .set_channels = mana_set_channels, + .get_ringparam = mana_get_ringparam, + .set_ringparam = mana_set_ringparam, }; diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c index df2ab5cbd49b..3a02eef58cc6 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c @@ -4537,8 +4537,8 @@ void *nfp_bpf_relo_for_vnic(struct nfp_prog *nfp_prog, struct nfp_bpf_vnic *bv) u64 *prog; int err; - prog = kmemdup(nfp_prog->prog, nfp_prog->prog_len * sizeof(u64), - GFP_KERNEL); + prog = kmemdup_array(nfp_prog->prog, nfp_prog->prog_len, sizeof(u64), + GFP_KERNEL); if (!prog) return ERR_PTR(-ENOMEM); diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_debugdump.c b/drivers/net/ethernet/netronome/nfp/nfp_net_debugdump.c index 2dd37557185e..7276e44a21d0 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_debugdump.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_debugdump.c @@ -41,6 +41,8 @@ struct nfp_dump_tl { ); char data[]; }; +static_assert(offsetof(struct nfp_dump_tl, data) == sizeof(struct nfp_dump_tl_hdr), + "struct member likely outside of struct_group_tagged()"); /* NFP CPP parameters */ struct nfp_dumpspec_cpp_isl_id { diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c index ed24d6af7487..9cff0a8ffb2c 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c @@ -3185,8 +3185,7 @@ netxen_list_config_ip(struct netxen_adapter *adapter, struct list_head *head; bool ret = false; - dev = ifa->ifa_dev ? ifa->ifa_dev->dev : NULL; - + dev = ifa->ifa_dev->dev; if (dev == NULL) goto out; @@ -3379,7 +3378,7 @@ netxen_inetaddr_event(struct notifier_block *this, struct in_ifaddr *ifa = (struct in_ifaddr *)ptr; unsigned long ip_event; - dev = ifa->ifa_dev ? ifa->ifa_dev->dev : NULL; + dev = ifa->ifa_dev->dev; ip_event = (event == NETDEV_UP) ? NX_IP_UP : NX_IP_DOWN; recheck: if (dev == NULL) diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c index 90df4a0909fa..b3588a1ebc25 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c @@ -4146,7 +4146,7 @@ qlcnic_inetaddr_event(struct notifier_block *this, struct in_ifaddr *ifa = (struct in_ifaddr *)ptr; - dev = ifa->ifa_dev ? ifa->ifa_dev->dev : NULL; + dev = ifa->ifa_dev->dev; recheck: if (dev == NULL) diff --git a/drivers/net/ethernet/sfc/ef100_ethtool.c b/drivers/net/ethernet/sfc/ef100_ethtool.c index 896ffca4aee2..5c2551369812 100644 --- a/drivers/net/ethernet/sfc/ef100_ethtool.c +++ b/drivers/net/ethernet/sfc/ef100_ethtool.c @@ -37,7 +37,6 @@ ef100_ethtool_get_ringparam(struct net_device *net_dev, /* Ethtool options available */ const struct ethtool_ops ef100_ethtool_ops = { - .cap_rss_ctx_supported = true, .get_drvinfo = efx_ethtool_get_drvinfo, .get_msglevel = efx_ethtool_get_msglevel, .set_msglevel = efx_ethtool_set_msglevel, @@ -59,6 +58,7 @@ const struct ethtool_ops ef100_ethtool_ops = { .get_rxfh_indir_size = efx_ethtool_get_rxfh_indir_size, .get_rxfh_key_size = efx_ethtool_get_rxfh_key_size, + .rxfh_per_ctx_key = true, .rxfh_priv_size = sizeof(struct efx_rss_context_priv), .get_rxfh = efx_ethtool_get_rxfh, .set_rxfh = efx_ethtool_set_rxfh, diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c index 7c887160e2ef..848b1923133a 100644 --- a/drivers/net/ethernet/sfc/ethtool.c +++ b/drivers/net/ethernet/sfc/ethtool.c @@ -240,7 +240,6 @@ static int efx_ethtool_get_ts_info(struct net_device *net_dev, } const struct ethtool_ops efx_ethtool_ops = { - .cap_rss_ctx_supported = true, .supported_coalesce_params = ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_USECS_IRQ | ETHTOOL_COALESCE_USE_ADAPTIVE_RX, @@ -268,6 +267,7 @@ const struct ethtool_ops efx_ethtool_ops = { .set_rxnfc = efx_ethtool_set_rxnfc, .get_rxfh_indir_size = efx_ethtool_get_rxfh_indir_size, .get_rxfh_key_size = efx_ethtool_get_rxfh_key_size, + .rxfh_per_ctx_key = true, .rxfh_priv_size = sizeof(struct efx_rss_context_priv), .get_rxfh = efx_ethtool_get_rxfh, .set_rxfh = efx_ethtool_set_rxfh, diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index cd36ff4da68c..684489156dce 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -29,6 +29,7 @@ /* Synopsys Core versions */ #define DWMAC_CORE_3_40 0x34 #define DWMAC_CORE_3_50 0x35 +#define DWMAC_CORE_3_70 0x37 #define DWMAC_CORE_4_00 0x40 #define DWMAC_CORE_4_10 0x41 #define DWMAC_CORE_5_00 0x50 diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c index 9e40c28d453a..bfe6e2d631bd 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c @@ -8,15 +8,90 @@ #include <linux/device.h> #include <linux/of_irq.h> #include "stmmac.h" +#include "dwmac_dma.h" +#include "dwmac1000.h" + +/* Normal Loongson Tx Summary */ +#define DMA_INTR_ENA_NIE_TX_LOONGSON 0x00040000 +/* Normal Loongson Rx Summary */ +#define DMA_INTR_ENA_NIE_RX_LOONGSON 0x00020000 + +#define DMA_INTR_NORMAL_LOONGSON (DMA_INTR_ENA_NIE_TX_LOONGSON | \ + DMA_INTR_ENA_NIE_RX_LOONGSON | \ + DMA_INTR_ENA_RIE | DMA_INTR_ENA_TIE) + +/* Abnormal Loongson Tx Summary */ +#define DMA_INTR_ENA_AIE_TX_LOONGSON 0x00010000 +/* Abnormal Loongson Rx Summary */ +#define DMA_INTR_ENA_AIE_RX_LOONGSON 0x00008000 + +#define DMA_INTR_ABNORMAL_LOONGSON (DMA_INTR_ENA_AIE_TX_LOONGSON | \ + DMA_INTR_ENA_AIE_RX_LOONGSON | \ + DMA_INTR_ENA_FBE | DMA_INTR_ENA_UNE) + +#define DMA_INTR_DEFAULT_MASK_LOONGSON (DMA_INTR_NORMAL_LOONGSON | \ + DMA_INTR_ABNORMAL_LOONGSON) + +/* Normal Loongson Tx Interrupt Summary */ +#define DMA_STATUS_NIS_TX_LOONGSON 0x00040000 +/* Normal Loongson Rx Interrupt Summary */ +#define DMA_STATUS_NIS_RX_LOONGSON 0x00020000 + +/* Abnormal Loongson Tx Interrupt Summary */ +#define DMA_STATUS_AIS_TX_LOONGSON 0x00010000 +/* Abnormal Loongson Rx Interrupt Summary */ +#define DMA_STATUS_AIS_RX_LOONGSON 0x00008000 + +/* Fatal Loongson Tx Bus Error Interrupt */ +#define DMA_STATUS_FBI_TX_LOONGSON 0x00002000 +/* Fatal Loongson Rx Bus Error Interrupt */ +#define DMA_STATUS_FBI_RX_LOONGSON 0x00001000 + +#define DMA_STATUS_MSK_COMMON_LOONGSON (DMA_STATUS_NIS_TX_LOONGSON | \ + DMA_STATUS_NIS_RX_LOONGSON | \ + DMA_STATUS_AIS_TX_LOONGSON | \ + DMA_STATUS_AIS_RX_LOONGSON | \ + DMA_STATUS_FBI_TX_LOONGSON | \ + DMA_STATUS_FBI_RX_LOONGSON) + +#define DMA_STATUS_MSK_RX_LOONGSON (DMA_STATUS_ERI | DMA_STATUS_RWT | \ + DMA_STATUS_RPS | DMA_STATUS_RU | \ + DMA_STATUS_RI | DMA_STATUS_OVF | \ + DMA_STATUS_MSK_COMMON_LOONGSON) + +#define DMA_STATUS_MSK_TX_LOONGSON (DMA_STATUS_ETI | DMA_STATUS_UNF | \ + DMA_STATUS_TJT | DMA_STATUS_TU | \ + DMA_STATUS_TPS | DMA_STATUS_TI | \ + DMA_STATUS_MSK_COMMON_LOONGSON) + +#define PCI_DEVICE_ID_LOONGSON_GMAC 0x7a03 +#define PCI_DEVICE_ID_LOONGSON_GNET 0x7a13 +#define DWMAC_CORE_LS_MULTICHAN 0x10 /* Loongson custom ID */ +#define CHANNEL_NUM 8 + +struct loongson_data { + u32 loongson_id; + struct device *dev; +}; + +struct stmmac_pci_info { + int (*setup)(struct pci_dev *pdev, struct plat_stmmacenet_data *plat); +}; -static int loongson_default_data(struct plat_stmmacenet_data *plat) +static void loongson_default_data(struct pci_dev *pdev, + struct plat_stmmacenet_data *plat) { + /* Get bus_id, this can be overwritten later */ + plat->bus_id = pci_dev_id(pdev); + plat->clk_csr = 2; /* clk_csr_i = 20-35MHz & MDC = clk_csr_i/16 */ plat->has_gmac = 1; plat->force_sf_dma_mode = 1; /* Set default value for multicast hash bins */ - plat->multicast_filter_bins = HASH_TABLE_SIZE; + plat->multicast_filter_bins = 256; + + plat->mac_interface = PHY_INTERFACE_MODE_NA; /* Set default value for unicast filter entries */ plat->unicast_filter_entries = 1; @@ -24,10 +99,6 @@ static int loongson_default_data(struct plat_stmmacenet_data *plat) /* 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; @@ -35,30 +106,424 @@ static int loongson_default_data(struct plat_stmmacenet_data *plat) /* 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; +} + +static int loongson_gmac_data(struct pci_dev *pdev, + struct plat_stmmacenet_data *plat) +{ + struct loongson_data *ld; + int i; + + ld = plat->bsp_priv; + + loongson_default_data(pdev, plat); + + if (ld->loongson_id == DWMAC_CORE_LS_MULTICHAN) { + plat->rx_queues_to_use = CHANNEL_NUM; + plat->tx_queues_to_use = CHANNEL_NUM; + + /* Only channel 0 supports checksum, + * so turn off checksum to enable multiple channels. + */ + for (i = 1; i < CHANNEL_NUM; i++) + plat->tx_queues_cfg[i].coe_unsupported = 1; + } else { + plat->tx_queues_to_use = 1; + plat->rx_queues_to_use = 1; + } + + plat->phy_interface = PHY_INTERFACE_MODE_RGMII_ID; - plat->multicast_filter_bins = 256; return 0; } -static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id *id) +static struct stmmac_pci_info loongson_gmac_pci_info = { + .setup = loongson_gmac_data, +}; + +static void loongson_gnet_fix_speed(void *priv, unsigned int speed, + unsigned int mode) { - struct plat_stmmacenet_data *plat; - struct stmmac_resources res; - struct device_node *np; - int ret, i, phy_mode; + struct loongson_data *ld = (struct loongson_data *)priv; + struct net_device *ndev = dev_get_drvdata(ld->dev); + struct stmmac_priv *ptr = netdev_priv(ndev); + + /* The integrated PHY has a weird problem with switching from the low + * speeds to 1000Mbps mode. The speedup procedure requires the PHY-link + * re-negotiation. + */ + if (speed == SPEED_1000) { + if (readl(ptr->ioaddr + MAC_CTRL_REG) & + GMAC_CONTROL_PS) + /* Word around hardware bug, restart autoneg */ + phy_restart_aneg(ndev->phydev); + } +} - np = dev_of_node(&pdev->dev); +static int loongson_gnet_data(struct pci_dev *pdev, + struct plat_stmmacenet_data *plat) +{ + struct loongson_data *ld; + int i; - if (!np) { - pr_info("dwmac_loongson_pci: No OF node\n"); - return -ENODEV; + ld = plat->bsp_priv; + + loongson_default_data(pdev, plat); + + if (ld->loongson_id == DWMAC_CORE_LS_MULTICHAN) { + plat->rx_queues_to_use = CHANNEL_NUM; + plat->tx_queues_to_use = CHANNEL_NUM; + + /* Only channel 0 supports checksum, + * so turn off checksum to enable multiple channels. + */ + for (i = 1; i < CHANNEL_NUM; i++) + plat->tx_queues_cfg[i].coe_unsupported = 1; + } else { + plat->tx_queues_to_use = 1; + plat->rx_queues_to_use = 1; } + plat->phy_interface = PHY_INTERFACE_MODE_GMII; + plat->mdio_bus_data->phy_mask = ~(u32)BIT(2); + plat->fix_mac_speed = loongson_gnet_fix_speed; + + return 0; +} + +static struct stmmac_pci_info loongson_gnet_pci_info = { + .setup = loongson_gnet_data, +}; + +static void loongson_dwmac_dma_init_channel(struct stmmac_priv *priv, + void __iomem *ioaddr, + struct stmmac_dma_cfg *dma_cfg, + u32 chan) +{ + int txpbl = dma_cfg->txpbl ?: dma_cfg->pbl; + int rxpbl = dma_cfg->rxpbl ?: dma_cfg->pbl; + u32 value; + + value = readl(ioaddr + DMA_CHAN_BUS_MODE(chan)); + + if (dma_cfg->pblx8) + value |= DMA_BUS_MODE_MAXPBL; + + value |= DMA_BUS_MODE_USP; + value &= ~(DMA_BUS_MODE_PBL_MASK | DMA_BUS_MODE_RPBL_MASK); + value |= (txpbl << DMA_BUS_MODE_PBL_SHIFT); + value |= (rxpbl << DMA_BUS_MODE_RPBL_SHIFT); + + /* Set the Fixed burst mode */ + if (dma_cfg->fixed_burst) + value |= DMA_BUS_MODE_FB; + + /* Mixed Burst has no effect when fb is set */ + if (dma_cfg->mixed_burst) + value |= DMA_BUS_MODE_MB; + + if (dma_cfg->atds) + value |= DMA_BUS_MODE_ATDS; + + if (dma_cfg->aal) + value |= DMA_BUS_MODE_AAL; + + writel(value, ioaddr + DMA_CHAN_BUS_MODE(chan)); + + /* Mask interrupts by writing to CSR7 */ + writel(DMA_INTR_DEFAULT_MASK_LOONGSON, ioaddr + + DMA_CHAN_INTR_ENA(chan)); +} + +static int loongson_dwmac_dma_interrupt(struct stmmac_priv *priv, + void __iomem *ioaddr, + struct stmmac_extra_stats *x, + u32 chan, u32 dir) +{ + struct stmmac_pcpu_stats *stats = this_cpu_ptr(priv->xstats.pcpu_stats); + u32 abnor_intr_status; + u32 nor_intr_status; + u32 fb_intr_status; + u32 intr_status; + int ret = 0; + + /* read the status register (CSR5) */ + intr_status = readl(ioaddr + DMA_CHAN_STATUS(chan)); + + if (dir == DMA_DIR_RX) + intr_status &= DMA_STATUS_MSK_RX_LOONGSON; + else if (dir == DMA_DIR_TX) + intr_status &= DMA_STATUS_MSK_TX_LOONGSON; + + nor_intr_status = intr_status & (DMA_STATUS_NIS_TX_LOONGSON | + DMA_STATUS_NIS_RX_LOONGSON); + abnor_intr_status = intr_status & (DMA_STATUS_AIS_TX_LOONGSON | + DMA_STATUS_AIS_RX_LOONGSON); + fb_intr_status = intr_status & (DMA_STATUS_FBI_TX_LOONGSON | + DMA_STATUS_FBI_RX_LOONGSON); + + /* ABNORMAL interrupts */ + if (unlikely(abnor_intr_status)) { + if (unlikely(intr_status & DMA_STATUS_UNF)) { + ret = tx_hard_error_bump_tc; + x->tx_undeflow_irq++; + } + if (unlikely(intr_status & DMA_STATUS_TJT)) + x->tx_jabber_irq++; + if (unlikely(intr_status & DMA_STATUS_OVF)) + x->rx_overflow_irq++; + if (unlikely(intr_status & DMA_STATUS_RU)) + x->rx_buf_unav_irq++; + if (unlikely(intr_status & DMA_STATUS_RPS)) + x->rx_process_stopped_irq++; + if (unlikely(intr_status & DMA_STATUS_RWT)) + x->rx_watchdog_irq++; + if (unlikely(intr_status & DMA_STATUS_ETI)) + x->tx_early_irq++; + if (unlikely(intr_status & DMA_STATUS_TPS)) { + x->tx_process_stopped_irq++; + ret = tx_hard_error; + } + if (unlikely(fb_intr_status)) { + x->fatal_bus_error_irq++; + ret = tx_hard_error; + } + } + /* TX/RX NORMAL interrupts */ + if (likely(nor_intr_status)) { + if (likely(intr_status & DMA_STATUS_RI)) { + u32 value = readl(ioaddr + DMA_INTR_ENA); + /* to schedule NAPI on real RIE event. */ + if (likely(value & DMA_INTR_ENA_RIE)) { + u64_stats_update_begin(&stats->syncp); + u64_stats_inc(&stats->rx_normal_irq_n[chan]); + u64_stats_update_end(&stats->syncp); + ret |= handle_rx; + } + } + if (likely(intr_status & DMA_STATUS_TI)) { + u64_stats_update_begin(&stats->syncp); + u64_stats_inc(&stats->tx_normal_irq_n[chan]); + u64_stats_update_end(&stats->syncp); + ret |= handle_tx; + } + if (unlikely(intr_status & DMA_STATUS_ERI)) + x->rx_early_irq++; + } + /* Optional hardware blocks, interrupts should be disabled */ + if (unlikely(intr_status & + (DMA_STATUS_GPI | DMA_STATUS_GMI | DMA_STATUS_GLI))) + pr_warn("%s: unexpected status %08x\n", __func__, intr_status); + + /* Clear the interrupt by writing a logic 1 to the CSR5[19-0] */ + writel((intr_status & 0x7ffff), ioaddr + DMA_CHAN_STATUS(chan)); + + return ret; +} + +static struct mac_device_info *loongson_dwmac_setup(void *apriv) +{ + struct stmmac_priv *priv = apriv; + struct mac_device_info *mac; + struct stmmac_dma_ops *dma; + struct loongson_data *ld; + struct pci_dev *pdev; + + 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; + + /* 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 the + * GMAC_VERSION.SNPSVER field to the custom 0x10 value on the + * network controllers with the multi-channels feature + * available to emphasize the differences: multiple DMA-channels, + * AV feature and GMAC_INT_STATUS CSR flags layout. Get back the + * original value so the correct HW-interface would be selected. + */ + if (ld->loongson_id == DWMAC_CORE_LS_MULTICHAN) { + priv->synopsys_id = DWMAC_CORE_3_70; + *dma = dwmac1000_dma_ops; + dma->init_chan = loongson_dwmac_dma_init_channel; + dma->dma_interrupt = loongson_dwmac_dma_interrupt; + mac->dma = dma; + } + + priv->dev->priv_flags |= IFF_UNICAST_FLT; + + /* Pre-initialize the respective "mac" fields as it's done in + * dwmac1000_setup() + */ + mac->pcsr = priv->ioaddr; + mac->multicast_filter_bins = priv->plat->multicast_filter_bins; + mac->unicast_filter_entries = priv->plat->unicast_filter_entries; + mac->mcast_bits_log2 = 0; + + if (mac->multicast_filter_bins) + mac->mcast_bits_log2 = ilog2(mac->multicast_filter_bins); + + /* Loongson GMAC doesn't support the flow control. LS2K2000 + * GNET doesn't support the half-duplex link mode. + */ + if (pdev->device == PCI_DEVICE_ID_LOONGSON_GMAC) { + mac->link.caps = MAC_10 | MAC_100 | MAC_1000; + } else { + if (ld->loongson_id == DWMAC_CORE_LS_MULTICHAN) + mac->link.caps = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | + MAC_10 | MAC_100 | MAC_1000; + else + mac->link.caps = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | + MAC_10FD | MAC_100FD | MAC_1000FD; + } + + mac->link.duplex = GMAC_CONTROL_DM; + mac->link.speed10 = GMAC_CONTROL_PS; + mac->link.speed100 = GMAC_CONTROL_PS | GMAC_CONTROL_FES; + mac->link.speed1000 = 0; + mac->link.speed_mask = GMAC_CONTROL_PS | GMAC_CONTROL_FES; + mac->mii.addr = GMAC_MII_ADDR; + mac->mii.data = GMAC_MII_DATA; + mac->mii.addr_shift = 11; + mac->mii.addr_mask = 0x0000F800; + mac->mii.reg_shift = 6; + mac->mii.reg_mask = 0x000007C0; + mac->mii.clk_csr_shift = 2; + mac->mii.clk_csr_mask = GENMASK(5, 2); + + return mac; +} + +static int loongson_dwmac_msi_config(struct pci_dev *pdev, + struct plat_stmmacenet_data *plat, + struct stmmac_resources *res) +{ + int i, ret, vecs; + + vecs = roundup_pow_of_two(CHANNEL_NUM * 2 + 1); + ret = pci_alloc_irq_vectors(pdev, vecs, vecs, PCI_IRQ_MSI); + if (ret < 0) { + dev_warn(&pdev->dev, "Failed to allocate MSI IRQs\n"); + return ret; + } + + res->irq = pci_irq_vector(pdev, 0); + + for (i = 0; i < plat->rx_queues_to_use; i++) { + res->rx_irq[CHANNEL_NUM - 1 - i] = + pci_irq_vector(pdev, 1 + i * 2); + } + + for (i = 0; i < plat->tx_queues_to_use; i++) { + res->tx_irq[CHANNEL_NUM - 1 - i] = + pci_irq_vector(pdev, 2 + i * 2); + } + + plat->flags |= STMMAC_FLAG_MULTI_MSI_EN; + + return 0; +} + +static void loongson_dwmac_msi_clear(struct pci_dev *pdev) +{ + pci_free_irq_vectors(pdev); +} + +static int loongson_dwmac_dt_config(struct pci_dev *pdev, + struct plat_stmmacenet_data *plat, + struct stmmac_resources *res) +{ + struct device_node *np = dev_of_node(&pdev->dev); + int ret; + + plat->mdio_node = of_get_child_by_name(np, "mdio"); + if (plat->mdio_node) { + dev_info(&pdev->dev, "Found MDIO subnode\n"); + plat->mdio_bus_data->needs_reset = true; + } + + ret = of_alias_get_id(np, "ethernet"); + if (ret >= 0) + plat->bus_id = ret; + + res->irq = of_irq_get_byname(np, "macirq"); + if (res->irq < 0) { + dev_err(&pdev->dev, "IRQ macirq not found\n"); + ret = -ENODEV; + goto err_put_node; + } + + res->wol_irq = of_irq_get_byname(np, "eth_wake_irq"); + if (res->wol_irq < 0) { + dev_info(&pdev->dev, + "IRQ eth_wake_irq not found, using macirq\n"); + res->wol_irq = res->irq; + } + + res->lpi_irq = of_irq_get_byname(np, "eth_lpi"); + if (res->lpi_irq < 0) { + dev_err(&pdev->dev, "IRQ eth_lpi not found\n"); + ret = -ENODEV; + goto err_put_node; + } + + ret = device_get_phy_mode(&pdev->dev); + if (ret < 0) { + dev_err(&pdev->dev, "phy_mode not found\n"); + ret = -ENODEV; + goto err_put_node; + } + + plat->phy_interface = ret; + + return 0; + +err_put_node: + of_node_put(plat->mdio_node); + + return ret; +} + +static void loongson_dwmac_dt_clear(struct pci_dev *pdev, + struct plat_stmmacenet_data *plat) +{ + of_node_put(plat->mdio_node); +} + +static int loongson_dwmac_acpi_config(struct pci_dev *pdev, + struct plat_stmmacenet_data *plat, + struct stmmac_resources *res) +{ + if (!pdev->irq) + return -EINVAL; + + res->irq = pdev->irq; + + return 0; +} + +static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id *id) +{ + struct plat_stmmacenet_data *plat; + struct stmmac_pci_info *info; + struct stmmac_resources res; + struct loongson_data *ld; + int ret, i; + plat = devm_kzalloc(&pdev->dev, sizeof(*plat), GFP_KERNEL); if (!plat) return -ENOMEM; @@ -69,25 +534,23 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id if (!plat->mdio_bus_data) return -ENOMEM; - plat->mdio_node = of_get_child_by_name(np, "mdio"); - if (plat->mdio_node) { - dev_info(&pdev->dev, "Found MDIO subnode\n"); - plat->mdio_bus_data->needs_reset = true; - } - plat->dma_cfg = devm_kzalloc(&pdev->dev, sizeof(*plat->dma_cfg), GFP_KERNEL); - if (!plat->dma_cfg) { - ret = -ENOMEM; - goto err_put_node; - } + if (!plat->dma_cfg) + return -ENOMEM; + + ld = devm_kzalloc(&pdev->dev, sizeof(*ld), GFP_KERNEL); + if (!ld) + return -ENOMEM; /* Enable pci device */ ret = pci_enable_device(pdev); if (ret) { dev_err(&pdev->dev, "%s: ERROR: failed to enable device\n", __func__); - goto err_put_node; + return ret; } + pci_set_master(pdev); + /* Get the base address of device */ for (i = 0; i < PCI_STD_NUM_BARS; i++) { if (pci_resource_len(pdev, i) == 0) @@ -98,59 +561,43 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id break; } - plat->bus_id = of_alias_get_id(np, "ethernet"); - if (plat->bus_id < 0) - plat->bus_id = pci_dev_id(pdev); - - phy_mode = device_get_phy_mode(&pdev->dev); - if (phy_mode < 0) { - dev_err(&pdev->dev, "phy_mode not found\n"); - ret = phy_mode; - goto err_disable_device; - } - - plat->phy_interface = phy_mode; - plat->mac_interface = PHY_INTERFACE_MODE_GMII; - - pci_set_master(pdev); - - loongson_default_data(plat); - pci_enable_msi(pdev); memset(&res, 0, sizeof(res)); res.addr = pcim_iomap_table(pdev)[0]; - res.irq = of_irq_get_byname(np, "macirq"); - if (res.irq < 0) { - dev_err(&pdev->dev, "IRQ macirq not found\n"); - ret = -ENODEV; - goto err_disable_msi; - } + plat->bsp_priv = ld; + plat->setup = loongson_dwmac_setup; + ld->dev = &pdev->dev; + ld->loongson_id = readl(res.addr + GMAC_VERSION) & 0xff; - res.wol_irq = of_irq_get_byname(np, "eth_wake_irq"); - if (res.wol_irq < 0) { - dev_info(&pdev->dev, "IRQ eth_wake_irq not found, using macirq\n"); - res.wol_irq = res.irq; - } + info = (struct stmmac_pci_info *)id->driver_data; + ret = info->setup(pdev, plat); + if (ret) + goto err_disable_device; - res.lpi_irq = of_irq_get_byname(np, "eth_lpi"); - if (res.lpi_irq < 0) { - dev_err(&pdev->dev, "IRQ eth_lpi not found\n"); - ret = -ENODEV; - goto err_disable_msi; - } + if (dev_of_node(&pdev->dev)) + ret = loongson_dwmac_dt_config(pdev, plat, &res); + else + ret = loongson_dwmac_acpi_config(pdev, plat, &res); + if (ret) + goto err_disable_device; + + /* Use the common MAC IRQ if per-channel MSIs allocation failed */ + if (ld->loongson_id == DWMAC_CORE_LS_MULTICHAN) + loongson_dwmac_msi_config(pdev, plat, &res); ret = stmmac_dvr_probe(&pdev->dev, plat, &res); if (ret) - goto err_disable_msi; + goto err_plat_clear; - return ret; + return 0; -err_disable_msi: - pci_disable_msi(pdev); +err_plat_clear: + if (dev_of_node(&pdev->dev)) + loongson_dwmac_dt_clear(pdev, plat); + if (ld->loongson_id == DWMAC_CORE_LS_MULTICHAN) + loongson_dwmac_msi_clear(pdev); err_disable_device: pci_disable_device(pdev); -err_put_node: - of_node_put(plat->mdio_node); return ret; } @@ -158,11 +605,18 @@ static void loongson_dwmac_remove(struct pci_dev *pdev) { struct net_device *ndev = dev_get_drvdata(&pdev->dev); struct stmmac_priv *priv = netdev_priv(ndev); + struct loongson_data *ld; int i; - of_node_put(priv->plat->mdio_node); + ld = priv->plat->bsp_priv; stmmac_dvr_remove(&pdev->dev); + if (dev_of_node(&pdev->dev)) + loongson_dwmac_dt_clear(pdev, priv->plat); + + if (ld->loongson_id == DWMAC_CORE_LS_MULTICHAN) + loongson_dwmac_msi_clear(pdev); + for (i = 0; i < PCI_STD_NUM_BARS; i++) { if (pci_resource_len(pdev, i) == 0) continue; @@ -170,7 +624,6 @@ static void loongson_dwmac_remove(struct pci_dev *pdev) break; } - pci_disable_msi(pdev); pci_disable_device(pdev); } @@ -213,7 +666,8 @@ static SIMPLE_DEV_PM_OPS(loongson_dwmac_pm_ops, loongson_dwmac_suspend, loongson_dwmac_resume); static const struct pci_device_id loongson_dwmac_id_table[] = { - { PCI_VDEVICE(LOONGSON, 0x7a03) }, + { PCI_DEVICE_DATA(LOONGSON, GMAC, &loongson_gmac_pci_info) }, + { PCI_DEVICE_DATA(LOONGSON, GNET, &loongson_gnet_pci_info) }, {} }; MODULE_DEVICE_TABLE(pci, loongson_dwmac_id_table); @@ -232,4 +686,5 @@ module_pci_driver(loongson_dwmac_driver); MODULE_DESCRIPTION("Loongson DWMAC PCI driver"); MODULE_AUTHOR("Qing Zhang <zhangqing@loongson.cn>"); +MODULE_AUTHOR("Yanteng Si <siyanteng@loongson.cn>"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c index 7ae04d8d291c..50073bdade46 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c @@ -1116,6 +1116,161 @@ static const struct rk_gmac_ops rk3568_ops = { }, }; +/* VCCIO0_1_3_IOC */ +#define RK3576_VCCIO0_1_3_IOC_CON2 0X6408 +#define RK3576_VCCIO0_1_3_IOC_CON3 0X640c +#define RK3576_VCCIO0_1_3_IOC_CON4 0X6410 +#define RK3576_VCCIO0_1_3_IOC_CON5 0X6414 + +#define RK3576_GMAC_RXCLK_DLY_ENABLE GRF_BIT(15) +#define RK3576_GMAC_RXCLK_DLY_DISABLE GRF_CLR_BIT(15) +#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) + +/* SDGMAC_GRF */ +#define RK3576_GRF_GMAC_CON0 0X0020 +#define RK3576_GRF_GMAC_CON1 0X0024 + +#define RK3576_GMAC_RMII_MODE GRF_BIT(3) +#define RK3576_GMAC_RGMII_MODE GRF_CLR_BIT(3) + +#define RK3576_GMAC_CLK_SELECT_IO GRF_BIT(7) +#define RK3576_GMAC_CLK_SELECT_CRU GRF_CLR_BIT(7) + +#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_RMII_GATE GRF_BIT(4) +#define RK3576_GMAC_CLK_RMII_NOGATE GRF_CLR_BIT(4) + +static void rk3576_set_to_rgmii(struct rk_priv_data *bsp_priv, + int tx_delay, int rx_delay) +{ + struct device *dev = &bsp_priv->pdev->dev; + unsigned int offset_con; + + if (IS_ERR(bsp_priv->grf) || IS_ERR(bsp_priv->php_grf)) { + dev_err(dev, "Missing rockchip,grf or rockchip,php-grf property\n"); + return; + } + + offset_con = bsp_priv->id == 1 ? RK3576_GRF_GMAC_CON1 : + RK3576_GRF_GMAC_CON0; + + regmap_write(bsp_priv->grf, offset_con, RK3576_GMAC_RGMII_MODE); + + offset_con = bsp_priv->id == 1 ? RK3576_VCCIO0_1_3_IOC_CON4 : + RK3576_VCCIO0_1_3_IOC_CON2; + + /* m0 && m1 delay enabled */ + regmap_write(bsp_priv->php_grf, offset_con, + DELAY_ENABLE(RK3576, tx_delay, rx_delay)); + regmap_write(bsp_priv->php_grf, offset_con + 0x4, + DELAY_ENABLE(RK3576, tx_delay, rx_delay)); + + /* m0 && m1 delay value */ + regmap_write(bsp_priv->php_grf, offset_con, + RK3576_GMAC_CLK_TX_DL_CFG(tx_delay) | + RK3576_GMAC_CLK_RX_DL_CFG(rx_delay)); + regmap_write(bsp_priv->php_grf, offset_con + 0x4, + RK3576_GMAC_CLK_TX_DL_CFG(tx_delay) | + RK3576_GMAC_CLK_RX_DL_CFG(rx_delay)); +} + +static void rk3576_set_to_rmii(struct rk_priv_data *bsp_priv) +{ + struct device *dev = &bsp_priv->pdev->dev; + unsigned int offset_con; + + if (IS_ERR(bsp_priv->grf)) { + dev_err(dev, "%s: Missing rockchip,grf property\n", __func__); + return; + } + + offset_con = bsp_priv->id == 1 ? RK3576_GRF_GMAC_CON1 : + RK3576_GRF_GMAC_CON0; + + regmap_write(bsp_priv->grf, offset_con, RK3576_GMAC_RMII_MODE); +} + +static void rk3576_set_gmac_speed(struct rk_priv_data *bsp_priv, int speed) +{ + struct device *dev = &bsp_priv->pdev->dev; + unsigned int val = 0, offset_con; + + switch (speed) { + case 10: + if (bsp_priv->phy_iface == PHY_INTERFACE_MODE_RMII) + val = RK3576_GMAC_CLK_RMII_DIV20; + else + val = RK3576_GMAC_CLK_RGMII_DIV50; + break; + case 100: + if (bsp_priv->phy_iface == PHY_INTERFACE_MODE_RMII) + val = RK3576_GMAC_CLK_RMII_DIV2; + else + val = RK3576_GMAC_CLK_RGMII_DIV5; + break; + case 1000: + if (bsp_priv->phy_iface != PHY_INTERFACE_MODE_RMII) + val = RK3576_GMAC_CLK_RGMII_DIV1; + else + goto err; + break; + default: + goto err; + } + + offset_con = bsp_priv->id == 1 ? RK3576_GRF_GMAC_CON1 : + RK3576_GRF_GMAC_CON0; + + regmap_write(bsp_priv->grf, offset_con, val); + + return; +err: + dev_err(dev, "unknown speed value for GMAC speed=%d", speed); +} + +static void rk3576_set_clock_selection(struct rk_priv_data *bsp_priv, bool input, + bool enable) +{ + unsigned int val = input ? RK3576_GMAC_CLK_SELECT_IO : + RK3576_GMAC_CLK_SELECT_CRU; + unsigned int offset_con; + + val |= enable ? RK3576_GMAC_CLK_RMII_NOGATE : + RK3576_GMAC_CLK_RMII_GATE; + + offset_con = bsp_priv->id == 1 ? RK3576_GRF_GMAC_CON1 : + RK3576_GRF_GMAC_CON0; + + regmap_write(bsp_priv->grf, offset_con, val); +} + +static const struct rk_gmac_ops rk3576_ops = { + .set_to_rgmii = rk3576_set_to_rgmii, + .set_to_rmii = rk3576_set_to_rmii, + .set_rgmii_speed = rk3576_set_gmac_speed, + .set_rmii_speed = rk3576_set_gmac_speed, + .set_clock_selection = rk3576_set_clock_selection, + .regs_valid = true, + .regs = { + 0x2a220000, /* gmac0 */ + 0x2a230000, /* gmac1 */ + 0x0, /* sentinel */ + }, +}; + /* sys_grf */ #define RK3588_GRF_GMAC_CON7 0X031c #define RK3588_GRF_GMAC_CON8 0X0320 @@ -1141,8 +1296,8 @@ static const struct rk_gmac_ops rk3568_ops = { #define RK3588_GMAC_CLK_RMII_MODE(id) GRF_BIT(5 * (id)) #define RK3588_GMAC_CLK_RGMII_MODE(id) GRF_CLR_BIT(5 * (id)) -#define RK3588_GMAC_CLK_SELET_CRU(id) GRF_BIT(5 * (id) + 4) -#define RK3588_GMAC_CLK_SELET_IO(id) GRF_CLR_BIT(5 * (id) + 4) +#define RK3588_GMAC_CLK_SELECT_CRU(id) GRF_BIT(5 * (id) + 4) +#define RK3588_GMAC_CLK_SELECT_IO(id) GRF_CLR_BIT(5 * (id) + 4) #define RK3588_GMA_CLK_RMII_DIV2(id) GRF_BIT(5 * (id) + 2) #define RK3588_GMA_CLK_RMII_DIV20(id) GRF_CLR_BIT(5 * (id) + 2) @@ -1240,8 +1395,8 @@ err: static void rk3588_set_clock_selection(struct rk_priv_data *bsp_priv, bool input, bool enable) { - unsigned int val = input ? RK3588_GMAC_CLK_SELET_IO(bsp_priv->id) : - RK3588_GMAC_CLK_SELET_CRU(bsp_priv->id); + unsigned int val = input ? RK3588_GMAC_CLK_SELECT_IO(bsp_priv->id) : + RK3588_GMAC_CLK_SELECT_CRU(bsp_priv->id); val |= enable ? RK3588_GMAC_CLK_RMII_NOGATE(bsp_priv->id) : RK3588_GMAC_CLK_RMII_GATE(bsp_priv->id); @@ -1908,6 +2063,7 @@ static const struct of_device_id rk_gmac_dwmac_match[] = { { .compatible = "rockchip,rk3368-gmac", .data = &rk3368_ops }, { .compatible = "rockchip,rk3399-gmac", .data = &rk3399_ops }, { .compatible = "rockchip,rk3568-gmac", .data = &rk3568_ops }, + { .compatible = "rockchip,rk3576-gmac", .data = &rk3576_ops }, { .compatible = "rockchip,rk3588-gmac", .data = &rk3588_ops }, { .compatible = "rockchip,rv1108-gmac", .data = &rv1108_ops }, { .compatible = "rockchip,rv1126-gmac", .data = &rv1126_ops }, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c index e1b761dcfa1d..cc93f73a380e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c @@ -299,7 +299,7 @@ static int sun8i_dwmac_dma_reset(void __iomem *ioaddr) * Called from stmmac via stmmac_dma_ops->init */ static void sun8i_dwmac_dma_init(void __iomem *ioaddr, - struct stmmac_dma_cfg *dma_cfg, int atds) + struct stmmac_dma_cfg *dma_cfg) { writel(EMAC_RX_INT | EMAC_TX_INT, ioaddr + EMAC_INT_EN); writel(0x1FFFFFF, ioaddr + EMAC_INT_STA); @@ -395,7 +395,7 @@ static void sun8i_dwmac_dma_start_tx(struct stmmac_priv *priv, writel(v, ioaddr + EMAC_TX_CTL1); } -static void sun8i_dwmac_enable_dma_transmission(void __iomem *ioaddr) +static void sun8i_dwmac_enable_dma_transmission(void __iomem *ioaddr, u32 chan) { u32 v; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c index adccdd816ea9..118a22406a2e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c @@ -70,15 +70,17 @@ static void dwmac1000_dma_axi(void __iomem *ioaddr, struct stmmac_axi *axi) writel(value, ioaddr + DMA_AXI_BUS_MODE); } -static void dwmac1000_dma_init(void __iomem *ioaddr, - struct stmmac_dma_cfg *dma_cfg, int atds) +static void dwmac1000_dma_init_channel(struct stmmac_priv *priv, + void __iomem *ioaddr, + struct stmmac_dma_cfg *dma_cfg, u32 chan) { - u32 value = readl(ioaddr + DMA_BUS_MODE); int txpbl = dma_cfg->txpbl ?: dma_cfg->pbl; int rxpbl = dma_cfg->rxpbl ?: dma_cfg->pbl; + u32 value; - /* - * Set the DMA PBL (Programmable Burst Length) mode. + value = readl(ioaddr + DMA_CHAN_BUS_MODE(chan)); + + /* Set the DMA PBL (Programmable Burst Length) mode. * * Note: before stmmac core 3.50 this mode bit was 4xPBL, and * post 3.5 mode bit acts as 8*PBL. @@ -98,16 +100,16 @@ static void dwmac1000_dma_init(void __iomem *ioaddr, if (dma_cfg->mixed_burst) value |= DMA_BUS_MODE_MB; - if (atds) + if (dma_cfg->atds) value |= DMA_BUS_MODE_ATDS; if (dma_cfg->aal) value |= DMA_BUS_MODE_AAL; - writel(value, ioaddr + DMA_BUS_MODE); + writel(value, ioaddr + DMA_CHAN_BUS_MODE(chan)); /* Mask interrupts by writing to CSR7 */ - writel(DMA_INTR_DEFAULT_MASK, ioaddr + DMA_INTR_ENA); + writel(DMA_INTR_DEFAULT_MASK, ioaddr + DMA_CHAN_INTR_ENA(chan)); } static void dwmac1000_dma_init_rx(struct stmmac_priv *priv, @@ -116,7 +118,7 @@ static void dwmac1000_dma_init_rx(struct stmmac_priv *priv, dma_addr_t dma_rx_phy, u32 chan) { /* RX descriptor base address list must be written into DMA CSR3 */ - writel(lower_32_bits(dma_rx_phy), ioaddr + DMA_RCV_BASE_ADDR); + writel(lower_32_bits(dma_rx_phy), ioaddr + DMA_CHAN_RCV_BASE_ADDR(chan)); } static void dwmac1000_dma_init_tx(struct stmmac_priv *priv, @@ -125,7 +127,7 @@ static void dwmac1000_dma_init_tx(struct stmmac_priv *priv, dma_addr_t dma_tx_phy, u32 chan) { /* TX descriptor base address list must be written into DMA CSR4 */ - writel(lower_32_bits(dma_tx_phy), ioaddr + DMA_TX_BASE_ADDR); + writel(lower_32_bits(dma_tx_phy), ioaddr + DMA_CHAN_TX_BASE_ADDR(chan)); } static u32 dwmac1000_configure_fc(u32 csr6, int rxfifosz) @@ -153,7 +155,7 @@ static void dwmac1000_dma_operation_mode_rx(struct stmmac_priv *priv, void __iomem *ioaddr, int mode, u32 channel, int fifosz, u8 qmode) { - u32 csr6 = readl(ioaddr + DMA_CONTROL); + u32 csr6 = readl(ioaddr + DMA_CHAN_CONTROL(channel)); if (mode == SF_DMA_MODE) { pr_debug("GMAC: enable RX store and forward mode\n"); @@ -175,14 +177,14 @@ static void dwmac1000_dma_operation_mode_rx(struct stmmac_priv *priv, /* Configure flow control based on rx fifo size */ csr6 = dwmac1000_configure_fc(csr6, fifosz); - writel(csr6, ioaddr + DMA_CONTROL); + writel(csr6, ioaddr + DMA_CHAN_CONTROL(channel)); } static void dwmac1000_dma_operation_mode_tx(struct stmmac_priv *priv, void __iomem *ioaddr, int mode, u32 channel, int fifosz, u8 qmode) { - u32 csr6 = readl(ioaddr + DMA_CONTROL); + u32 csr6 = readl(ioaddr + DMA_CHAN_CONTROL(channel)); if (mode == SF_DMA_MODE) { pr_debug("GMAC: enable TX store and forward mode\n"); @@ -209,7 +211,7 @@ static void dwmac1000_dma_operation_mode_tx(struct stmmac_priv *priv, csr6 |= DMA_CONTROL_TTC_256; } - writel(csr6, ioaddr + DMA_CONTROL); + writel(csr6, ioaddr + DMA_CHAN_CONTROL(channel)); } static void dwmac1000_dump_dma_regs(struct stmmac_priv *priv, @@ -271,12 +273,12 @@ static int dwmac1000_get_hw_feature(void __iomem *ioaddr, static void dwmac1000_rx_watchdog(struct stmmac_priv *priv, void __iomem *ioaddr, u32 riwt, u32 queue) { - writel(riwt, ioaddr + DMA_RX_WATCHDOG); + writel(riwt, ioaddr + DMA_CHAN_RX_WATCHDOG(queue)); } const struct stmmac_dma_ops dwmac1000_dma_ops = { .reset = dwmac_dma_reset, - .init = dwmac1000_dma_init, + .init_chan = dwmac1000_dma_init_channel, .init_rx_chan = dwmac1000_dma_init_rx, .init_tx_chan = dwmac1000_dma_init_tx, .axi = dwmac1000_dma_axi, @@ -294,3 +296,4 @@ const struct stmmac_dma_ops dwmac1000_dma_ops = { .get_hw_feature = dwmac1000_get_hw_feature, .rx_watchdog = dwmac1000_rx_watchdog, }; +EXPORT_SYMBOL_GPL(dwmac1000_dma_ops); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c index b402fb54f613..82957db47c99 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c @@ -19,7 +19,7 @@ #include "dwmac_dma.h" static void dwmac100_dma_init(void __iomem *ioaddr, - struct stmmac_dma_cfg *dma_cfg, int atds) + struct stmmac_dma_cfg *dma_cfg) { /* Enable Application Access by writing to DMA CSR0 */ writel(DMA_BUS_MODE_DEFAULT | (dma_cfg->pbl << DMA_BUS_MODE_PBL_SHIFT), diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c index 84d3a8551b03..e0165358c4ac 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c @@ -153,7 +153,7 @@ static void dwmac410_dma_init_channel(struct stmmac_priv *priv, } static void dwmac4_dma_init(void __iomem *ioaddr, - struct stmmac_dma_cfg *dma_cfg, int atds) + struct stmmac_dma_cfg *dma_cfg) { u32 value = readl(ioaddr + DMA_SYS_BUS_MODE); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h index 72672391675f..5d9c18f5bbf5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h @@ -22,6 +22,31 @@ #define DMA_INTR_ENA 0x0000101c /* Interrupt Enable */ #define DMA_MISSED_FRAME_CTR 0x00001020 /* Missed Frame Counter */ +/* Following DMA defines are channels oriented */ +#define DMA_CHAN_BASE_OFFSET 0x100 + +static inline u32 dma_chan_base_addr(u32 base, u32 chan) +{ + return base + chan * DMA_CHAN_BASE_OFFSET; +} + +#define DMA_CHAN_BUS_MODE(chan) dma_chan_base_addr(DMA_BUS_MODE, chan) +#define DMA_CHAN_XMT_POLL_DEMAND(chan) \ + dma_chan_base_addr(DMA_XMT_POLL_DEMAND, chan) +#define DMA_CHAN_RCV_POLL_DEMAND(chan) \ + dma_chan_base_addr(DMA_RCV_POLL_DEMAND, chan) +#define DMA_CHAN_RCV_BASE_ADDR(chan) \ + dma_chan_base_addr(DMA_RCV_BASE_ADDR, chan) +#define DMA_CHAN_TX_BASE_ADDR(chan) \ + dma_chan_base_addr(DMA_TX_BASE_ADDR, chan) +#define DMA_CHAN_STATUS(chan) dma_chan_base_addr(DMA_STATUS, chan) +#define DMA_CHAN_CONTROL(chan) dma_chan_base_addr(DMA_CONTROL, chan) +#define DMA_CHAN_INTR_ENA(chan) dma_chan_base_addr(DMA_INTR_ENA, chan) +#define DMA_CHAN_MISSED_FRAME_CTR(chan) \ + dma_chan_base_addr(DMA_MISSED_FRAME_CTR, chan) +#define DMA_CHAN_RX_WATCHDOG(chan) \ + dma_chan_base_addr(DMA_RX_WATCHDOG, chan) + /* SW Reset */ #define DMA_BUS_MODE_SFT_RESET 0x00000001 /* Software Reset */ @@ -152,7 +177,7 @@ #define NUM_DWMAC1000_DMA_REGS 23 #define NUM_DWMAC4_DMA_REGS 27 -void dwmac_enable_dma_transmission(void __iomem *ioaddr); +void dwmac_enable_dma_transmission(void __iomem *ioaddr, u32 chan); void dwmac_enable_dma_irq(struct stmmac_priv *priv, void __iomem *ioaddr, u32 chan, bool rx, bool tx); void dwmac_disable_dma_irq(struct stmmac_priv *priv, void __iomem *ioaddr, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c index 85e18f9a22f9..4846bf49c576 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c @@ -28,65 +28,65 @@ int dwmac_dma_reset(void __iomem *ioaddr) } /* CSR1 enables the transmit DMA to check for new descriptor */ -void dwmac_enable_dma_transmission(void __iomem *ioaddr) +void dwmac_enable_dma_transmission(void __iomem *ioaddr, u32 chan) { - writel(1, ioaddr + DMA_XMT_POLL_DEMAND); + writel(1, ioaddr + DMA_CHAN_XMT_POLL_DEMAND(chan)); } void dwmac_enable_dma_irq(struct stmmac_priv *priv, void __iomem *ioaddr, u32 chan, bool rx, bool tx) { - u32 value = readl(ioaddr + DMA_INTR_ENA); + u32 value = readl(ioaddr + DMA_CHAN_INTR_ENA(chan)); if (rx) value |= DMA_INTR_DEFAULT_RX; if (tx) value |= DMA_INTR_DEFAULT_TX; - writel(value, ioaddr + DMA_INTR_ENA); + writel(value, ioaddr + DMA_CHAN_INTR_ENA(chan)); } void dwmac_disable_dma_irq(struct stmmac_priv *priv, void __iomem *ioaddr, u32 chan, bool rx, bool tx) { - u32 value = readl(ioaddr + DMA_INTR_ENA); + u32 value = readl(ioaddr + DMA_CHAN_INTR_ENA(chan)); if (rx) value &= ~DMA_INTR_DEFAULT_RX; if (tx) value &= ~DMA_INTR_DEFAULT_TX; - writel(value, ioaddr + DMA_INTR_ENA); + writel(value, ioaddr + DMA_CHAN_INTR_ENA(chan)); } void dwmac_dma_start_tx(struct stmmac_priv *priv, void __iomem *ioaddr, u32 chan) { - u32 value = readl(ioaddr + DMA_CONTROL); + u32 value = readl(ioaddr + DMA_CHAN_CONTROL(chan)); value |= DMA_CONTROL_ST; - writel(value, ioaddr + DMA_CONTROL); + writel(value, ioaddr + DMA_CHAN_CONTROL(chan)); } void dwmac_dma_stop_tx(struct stmmac_priv *priv, void __iomem *ioaddr, u32 chan) { - u32 value = readl(ioaddr + DMA_CONTROL); + u32 value = readl(ioaddr + DMA_CHAN_CONTROL(chan)); value &= ~DMA_CONTROL_ST; - writel(value, ioaddr + DMA_CONTROL); + writel(value, ioaddr + DMA_CHAN_CONTROL(chan)); } void dwmac_dma_start_rx(struct stmmac_priv *priv, void __iomem *ioaddr, u32 chan) { - u32 value = readl(ioaddr + DMA_CONTROL); + u32 value = readl(ioaddr + DMA_CHAN_CONTROL(chan)); value |= DMA_CONTROL_SR; - writel(value, ioaddr + DMA_CONTROL); + writel(value, ioaddr + DMA_CHAN_CONTROL(chan)); } void dwmac_dma_stop_rx(struct stmmac_priv *priv, void __iomem *ioaddr, u32 chan) { - u32 value = readl(ioaddr + DMA_CONTROL); + u32 value = readl(ioaddr + DMA_CHAN_CONTROL(chan)); value &= ~DMA_CONTROL_SR; - writel(value, ioaddr + DMA_CONTROL); + writel(value, ioaddr + DMA_CHAN_CONTROL(chan)); } #ifdef DWMAC_DMA_DEBUG @@ -165,7 +165,7 @@ int dwmac_dma_interrupt(struct stmmac_priv *priv, void __iomem *ioaddr, struct stmmac_pcpu_stats *stats = this_cpu_ptr(priv->xstats.pcpu_stats); int ret = 0; /* read the status register (CSR5) */ - u32 intr_status = readl(ioaddr + DMA_STATUS); + u32 intr_status = readl(ioaddr + DMA_CHAN_STATUS(chan)); #ifdef DWMAC_DMA_DEBUG /* Enable it to monitor DMA rx/tx status in case of critical problems */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c index f196cd99d510..cbf2dd976ab1 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c @@ -846,42 +846,41 @@ static const struct dwxgmac3_error_desc dwxgmac3_dma_errors[32]= { { false, "UNKNOWN", "Unknown Error" }, /* 31 */ }; -#define DPP_RX_ERR "Read Rx Descriptor Parity checker Error" -#define DPP_TX_ERR "Read Tx Descriptor Parity checker Error" - +static const char dpp_rx_err[] = "Read Rx Descriptor Parity checker Error"; +static const char dpp_tx_err[] = "Read Tx Descriptor Parity checker Error"; static const struct dwxgmac3_error_desc dwxgmac3_dma_dpp_errors[32] = { - { true, "TDPES0", DPP_TX_ERR }, - { true, "TDPES1", DPP_TX_ERR }, - { true, "TDPES2", DPP_TX_ERR }, - { true, "TDPES3", DPP_TX_ERR }, - { true, "TDPES4", DPP_TX_ERR }, - { true, "TDPES5", DPP_TX_ERR }, - { true, "TDPES6", DPP_TX_ERR }, - { true, "TDPES7", DPP_TX_ERR }, - { true, "TDPES8", DPP_TX_ERR }, - { true, "TDPES9", DPP_TX_ERR }, - { true, "TDPES10", DPP_TX_ERR }, - { true, "TDPES11", DPP_TX_ERR }, - { true, "TDPES12", DPP_TX_ERR }, - { true, "TDPES13", DPP_TX_ERR }, - { true, "TDPES14", DPP_TX_ERR }, - { true, "TDPES15", DPP_TX_ERR }, - { true, "RDPES0", DPP_RX_ERR }, - { true, "RDPES1", DPP_RX_ERR }, - { true, "RDPES2", DPP_RX_ERR }, - { true, "RDPES3", DPP_RX_ERR }, - { true, "RDPES4", DPP_RX_ERR }, - { true, "RDPES5", DPP_RX_ERR }, - { true, "RDPES6", DPP_RX_ERR }, - { true, "RDPES7", DPP_RX_ERR }, - { true, "RDPES8", DPP_RX_ERR }, - { true, "RDPES9", DPP_RX_ERR }, - { true, "RDPES10", DPP_RX_ERR }, - { true, "RDPES11", DPP_RX_ERR }, - { true, "RDPES12", DPP_RX_ERR }, - { true, "RDPES13", DPP_RX_ERR }, - { true, "RDPES14", DPP_RX_ERR }, - { true, "RDPES15", DPP_RX_ERR }, + { true, "TDPES0", dpp_tx_err }, + { true, "TDPES1", dpp_tx_err }, + { true, "TDPES2", dpp_tx_err }, + { true, "TDPES3", dpp_tx_err }, + { true, "TDPES4", dpp_tx_err }, + { true, "TDPES5", dpp_tx_err }, + { true, "TDPES6", dpp_tx_err }, + { true, "TDPES7", dpp_tx_err }, + { true, "TDPES8", dpp_tx_err }, + { true, "TDPES9", dpp_tx_err }, + { true, "TDPES10", dpp_tx_err }, + { true, "TDPES11", dpp_tx_err }, + { true, "TDPES12", dpp_tx_err }, + { true, "TDPES13", dpp_tx_err }, + { true, "TDPES14", dpp_tx_err }, + { true, "TDPES15", dpp_tx_err }, + { true, "RDPES0", dpp_rx_err }, + { true, "RDPES1", dpp_rx_err }, + { true, "RDPES2", dpp_rx_err }, + { true, "RDPES3", dpp_rx_err }, + { true, "RDPES4", dpp_rx_err }, + { true, "RDPES5", dpp_rx_err }, + { true, "RDPES6", dpp_rx_err }, + { true, "RDPES7", dpp_rx_err }, + { true, "RDPES8", dpp_rx_err }, + { true, "RDPES9", dpp_rx_err }, + { true, "RDPES10", dpp_rx_err }, + { true, "RDPES11", dpp_rx_err }, + { true, "RDPES12", dpp_rx_err }, + { true, "RDPES13", dpp_rx_err }, + { true, "RDPES14", dpp_rx_err }, + { true, "RDPES15", dpp_rx_err }, }; static void dwxgmac3_handle_dma_err(struct net_device *ndev, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c index dd2ab6185c40..7840bc403788 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c @@ -20,7 +20,7 @@ static int dwxgmac2_dma_reset(void __iomem *ioaddr) } static void dwxgmac2_dma_init(void __iomem *ioaddr, - struct stmmac_dma_cfg *dma_cfg, int atds) + struct stmmac_dma_cfg *dma_cfg) { u32 value = readl(ioaddr + XGMAC_DMA_SYSBUS_MODE); diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h index e53c32362774..7e90f34b8c88 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.h +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h @@ -175,8 +175,7 @@ struct dma_features; struct stmmac_dma_ops { /* DMA core initialization */ int (*reset)(void __iomem *ioaddr); - void (*init)(void __iomem *ioaddr, struct stmmac_dma_cfg *dma_cfg, - int atds); + void (*init)(void __iomem *ioaddr, struct stmmac_dma_cfg *dma_cfg); void (*init_chan)(struct stmmac_priv *priv, void __iomem *ioaddr, struct stmmac_dma_cfg *dma_cfg, u32 chan); void (*init_rx_chan)(struct stmmac_priv *priv, void __iomem *ioaddr, @@ -198,7 +197,7 @@ struct stmmac_dma_ops { /* To track extra statistic (if supported) */ void (*dma_diagnostic_fr)(struct stmmac_extra_stats *x, void __iomem *ioaddr); - void (*enable_dma_transmission) (void __iomem *ioaddr); + void (*enable_dma_transmission)(void __iomem *ioaddr, u32 chan); void (*enable_dma_irq)(struct stmmac_priv *priv, void __iomem *ioaddr, u32 chan, bool rx, bool tx); void (*disable_dma_irq)(struct stmmac_priv *priv, void __iomem *ioaddr, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index f3a1b179aaea..d9fca8d1227c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -2367,9 +2367,11 @@ static void stmmac_dma_operation_mode(struct stmmac_priv *priv) if (txfifosz == 0) txfifosz = priv->dma_cap.tx_fifo_size; - /* Adjust for real per queue fifo size */ - rxfifosz /= rx_channels_count; - txfifosz /= tx_channels_count; + /* Split up the shared Tx/Rx FIFO memory on DW QoS Eth and DW XGMAC */ + if (priv->plat->has_gmac4 || priv->plat->has_xgmac) { + rxfifosz /= rx_channels_count; + txfifosz /= tx_channels_count; + } if (priv->plat->force_thresh_dma_mode) { txmode = tc; @@ -2553,7 +2555,7 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget) true, priv->mode, true, true, xdp_desc.len); - stmmac_enable_dma_transmission(priv, priv->ioaddr); + stmmac_enable_dma_transmission(priv, priv->ioaddr, queue); xsk_tx_metadata_to_compl(meta, &tx_q->tx_skbuff_dma[entry].xsk_meta); @@ -3003,7 +3005,6 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv) struct stmmac_rx_queue *rx_q; struct stmmac_tx_queue *tx_q; u32 chan = 0; - int atds = 0; int ret = 0; if (!priv->plat->dma_cfg || !priv->plat->dma_cfg->pbl) { @@ -3012,7 +3013,7 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv) } if (priv->extend_desc && (priv->mode == STMMAC_RING_MODE)) - atds = 1; + priv->plat->dma_cfg->atds = 1; ret = stmmac_reset(priv, priv->ioaddr); if (ret) { @@ -3021,7 +3022,7 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv) } /* DMA Configuration */ - stmmac_dma_init(priv, priv->ioaddr, priv->plat->dma_cfg, atds); + stmmac_dma_init(priv, priv->ioaddr, priv->plat->dma_cfg); if (priv->plat->axi) stmmac_axi(priv, priv->ioaddr, priv->plat->axi); @@ -4754,7 +4755,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) netdev_tx_sent_queue(netdev_get_tx_queue(dev, queue), skb->len); - stmmac_enable_dma_transmission(priv, priv->ioaddr); + stmmac_enable_dma_transmission(priv, priv->ioaddr, queue); stmmac_flush_tx_descriptors(priv, queue); stmmac_tx_timer_arm(priv, queue); @@ -4981,7 +4982,7 @@ static int stmmac_xdp_xmit_xdpf(struct stmmac_priv *priv, int queue, u64_stats_update_end(&txq_stats->q_syncp); } - stmmac_enable_dma_transmission(priv, priv->ioaddr); + stmmac_enable_dma_transmission(priv, priv->ioaddr, queue); entry = STMMAC_GET_ENTRY(entry, priv->dma_conf.dma_tx_size); tx_q->cur_tx = entry; diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c index 2f30715e9b67..1e887d951a04 100644 --- a/drivers/net/ethernet/sun/sunvnet.c +++ b/drivers/net/ethernet/sun/sunvnet.c @@ -114,37 +114,23 @@ static void vnet_get_strings(struct net_device *dev, u32 stringset, u8 *buf) { struct vnet *vp = (struct vnet *)netdev_priv(dev); struct vnet_port *port; - char *p = (char *)buf; switch (stringset) { case ETH_SS_STATS: memcpy(buf, ðtool_stats_keys, sizeof(ethtool_stats_keys)); - p += sizeof(ethtool_stats_keys); + buf += sizeof(ethtool_stats_keys); rcu_read_lock(); list_for_each_entry_rcu(port, &vp->port_list, list) { - snprintf(p, ETH_GSTRING_LEN, "p%u.%s-%pM", - port->q_index, port->switch_port ? "s" : "q", - port->raddr); - p += ETH_GSTRING_LEN; - snprintf(p, ETH_GSTRING_LEN, "p%u.rx_packets", - port->q_index); - p += ETH_GSTRING_LEN; - snprintf(p, ETH_GSTRING_LEN, "p%u.tx_packets", - port->q_index); - p += ETH_GSTRING_LEN; - snprintf(p, ETH_GSTRING_LEN, "p%u.rx_bytes", - port->q_index); - p += ETH_GSTRING_LEN; - snprintf(p, ETH_GSTRING_LEN, "p%u.tx_bytes", - port->q_index); - p += ETH_GSTRING_LEN; - snprintf(p, ETH_GSTRING_LEN, "p%u.event_up", - port->q_index); - p += ETH_GSTRING_LEN; - snprintf(p, ETH_GSTRING_LEN, "p%u.event_reset", - port->q_index); - p += ETH_GSTRING_LEN; + ethtool_sprintf(&buf, "p%u.%s-%pM", port->q_index, + port->switch_port ? "s" : "q", + port->raddr); + ethtool_sprintf(&buf, "p%u.rx_packets", port->q_index); + ethtool_sprintf(&buf, "p%u.tx_packets", port->q_index); + ethtool_sprintf(&buf, "p%u.rx_bytes", port->q_index); + ethtool_sprintf(&buf, "p%u.tx_bytes", port->q_index); + ethtool_sprintf(&buf, "p%u.event_up", port->q_index); + ethtool_sprintf(&buf, "p%u.event_reset", port->q_index); } rcu_read_unlock(); break; diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 81d9f21086ec..555aca4ffa24 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -2761,7 +2761,7 @@ am65_cpsw_nuss_init_port_ndev(struct am65_cpsw_common *common, u32 port_idx) } phylink = phylink_create(&port->slave.phylink_config, - of_node_to_fwnode(port->slave.port_np), + of_fwnode_handle(port->slave.port_np), port->slave.phy_if, &am65_cpsw_phylink_mac_ops); if (IS_ERR(phylink)) diff --git a/drivers/net/ethernet/ti/icssg/icssg_ethtool.c b/drivers/net/ethernet/ti/icssg/icssg_ethtool.c index 5688f054cec5..5073ec195854 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_ethtool.c +++ b/drivers/net/ethernet/ti/icssg/icssg_ethtool.c @@ -83,13 +83,11 @@ static void emac_get_strings(struct net_device *ndev, u32 stringset, u8 *data) switch (stringset) { case ETH_SS_STATS: - for (i = 0; i < ARRAY_SIZE(icssg_all_stats); i++) { - if (!icssg_all_stats[i].standard_stats) { - memcpy(p, icssg_all_stats[i].name, - ETH_GSTRING_LEN); - p += ETH_GSTRING_LEN; - } - } + for (i = 0; i < ARRAY_SIZE(icssg_all_miig_stats); i++) + if (!icssg_all_miig_stats[i].standard_stats) + ethtool_puts(&p, icssg_all_miig_stats[i].name); + for (i = 0; i < ARRAY_SIZE(icssg_all_pa_stats); i++) + ethtool_puts(&p, icssg_all_pa_stats[i].name); break; default: break; @@ -104,9 +102,12 @@ static void emac_get_ethtool_stats(struct net_device *ndev, emac_update_hardware_stats(emac); - for (i = 0; i < ARRAY_SIZE(icssg_all_stats); i++) - if (!icssg_all_stats[i].standard_stats) + for (i = 0; i < ARRAY_SIZE(icssg_all_miig_stats); i++) + if (!icssg_all_miig_stats[i].standard_stats) *(data++) = emac->stats[i]; + + for (i = 0; i < ARRAY_SIZE(icssg_all_pa_stats); i++) + *(data++) = emac->pa_stats[i]; } static int emac_get_ts_info(struct net_device *ndev, diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c index e3451beed323..becdda143c19 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c @@ -857,6 +857,7 @@ static int prueth_netdev_init(struct prueth *prueth, } ether_addr_copy(emac->mac_addr, ndev->dev_addr); + ndev->dev.of_node = eth_node; ndev->min_mtu = PRUETH_MIN_PKT_SIZE; ndev->max_mtu = PRUETH_MAX_MTU; ndev->netdev_ops = &emac_netdev_ops; @@ -1181,6 +1182,12 @@ static int prueth_probe(struct platform_device *pdev) return -ENODEV; } + prueth->pa_stats = syscon_regmap_lookup_by_phandle(np, "ti,pa-stats"); + if (IS_ERR(prueth->pa_stats)) { + dev_err(dev, "couldn't get ti,pa-stats syscon regmap\n"); + return -ENODEV; + } + if (eth0_node) { ret = prueth_get_cores(prueth, ICSS_SLICE0, false); if (ret) @@ -1271,8 +1278,8 @@ static int prueth_probe(struct platform_device *pdev) goto exit_iep; } - if (of_find_property(eth0_node, "ti,half-duplex-capable", NULL)) - prueth->emac[PRUETH_MAC0]->half_duplex = 1; + prueth->emac[PRUETH_MAC0]->half_duplex = + of_property_read_bool(eth0_node, "ti,half-duplex-capable"); prueth->emac[PRUETH_MAC0]->iep = prueth->iep0; } @@ -1285,8 +1292,8 @@ static int prueth_probe(struct platform_device *pdev) goto netdev_exit; } - if (of_find_property(eth1_node, "ti,half-duplex-capable", NULL)) - prueth->emac[PRUETH_MAC1]->half_duplex = 1; + prueth->emac[PRUETH_MAC1]->half_duplex = + of_property_read_bool(eth1_node, "ti,half-duplex-capable"); prueth->emac[PRUETH_MAC1]->iep = prueth->iep0; } diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.h b/drivers/net/ethernet/ti/icssg/icssg_prueth.h index f678d656a3ed..786bd1ba34ab 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.h +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.h @@ -50,8 +50,10 @@ #define ICSSG_MAX_RFLOWS 8 /* per slice */ +#define ICSSG_NUM_PA_STATS 4 +#define ICSSG_NUM_MIIG_STATS 60 /* Number of ICSSG related stats */ -#define ICSSG_NUM_STATS 60 +#define ICSSG_NUM_STATS (ICSSG_NUM_MIIG_STATS + ICSSG_NUM_PA_STATS) #define ICSSG_NUM_STANDARD_STATS 31 #define ICSSG_NUM_ETHTOOL_STATS (ICSSG_NUM_STATS - ICSSG_NUM_STANDARD_STATS) @@ -190,7 +192,8 @@ struct prueth_emac { int port_vlan; struct delayed_work stats_work; - u64 stats[ICSSG_NUM_STATS]; + u64 stats[ICSSG_NUM_MIIG_STATS]; + u64 pa_stats[ICSSG_NUM_PA_STATS]; /* RX IRQ Coalescing Related */ struct hrtimer rx_hrtimer; @@ -230,6 +233,7 @@ struct icssg_firmwares { * @registered_netdevs: list of registered netdevs * @miig_rt: regmap to mii_g_rt block * @mii_rt: regmap to mii_rt block + * @pa_stats: regmap to pa_stats block * @pru_id: ID for each of the PRUs * @pdev: pointer to ICSSG platform device * @pdata: pointer to platform data for ICSSG driver @@ -263,6 +267,7 @@ struct prueth { struct net_device *registered_netdevs[PRUETH_NUM_MACS]; struct regmap *miig_rt; struct regmap *mii_rt; + struct regmap *pa_stats; enum pruss_pru_id pru_id[PRUSS_NUM_PRUS]; struct platform_device *pdev; diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c b/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c index e180c1166170..292f04d29f4f 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c @@ -847,6 +847,7 @@ static int prueth_netdev_init(struct prueth *prueth, } ether_addr_copy(emac->mac_addr, ndev->dev_addr); + ndev->dev.of_node = eth_node; ndev->min_mtu = PRUETH_MIN_PKT_SIZE; ndev->max_mtu = PRUETH_MAX_MTU; ndev->netdev_ops = &emac_netdev_ops; @@ -1045,8 +1046,8 @@ static int prueth_probe(struct platform_device *pdev) goto exit_iep; } - if (of_find_property(eth0_node, "ti,half-duplex-capable", NULL)) - prueth->emac[PRUETH_MAC0]->half_duplex = 1; + prueth->emac[PRUETH_MAC0]->half_duplex = + of_property_read_bool(eth0_node, "ti,half-duplex-capable"); prueth->emac[PRUETH_MAC0]->iep = prueth->iep0; } @@ -1059,8 +1060,8 @@ static int prueth_probe(struct platform_device *pdev) goto netdev_exit; } - if (of_find_property(eth1_node, "ti,half-duplex-capable", NULL)) - prueth->emac[PRUETH_MAC1]->half_duplex = 1; + prueth->emac[PRUETH_MAC1]->half_duplex = + of_property_read_bool(eth1_node, "ti,half-duplex-capable"); prueth->emac[PRUETH_MAC1]->iep = prueth->iep1; } diff --git a/drivers/net/ethernet/ti/icssg/icssg_stats.c b/drivers/net/ethernet/ti/icssg/icssg_stats.c index 2fb150c13078..06a15c0b2acc 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_stats.c +++ b/drivers/net/ethernet/ti/icssg/icssg_stats.c @@ -11,6 +11,7 @@ #define ICSSG_TX_PACKET_OFFSET 0xA0 #define ICSSG_TX_BYTE_OFFSET 0xEC +#define ICSSG_FW_STATS_BASE 0x0248 static u32 stats_base[] = { 0x54c, /* Slice 0 stats start */ 0xb18, /* Slice 1 stats start */ @@ -22,24 +23,31 @@ void emac_update_hardware_stats(struct prueth_emac *emac) int slice = prueth_emac_slice(emac); u32 base = stats_base[slice]; u32 tx_pkt_cnt = 0; - u32 val; + u32 val, reg; int i; - for (i = 0; i < ARRAY_SIZE(icssg_all_stats); i++) { + for (i = 0; i < ARRAY_SIZE(icssg_all_miig_stats); i++) { regmap_read(prueth->miig_rt, - base + icssg_all_stats[i].offset, + base + icssg_all_miig_stats[i].offset, &val); regmap_write(prueth->miig_rt, - base + icssg_all_stats[i].offset, + base + icssg_all_miig_stats[i].offset, val); - if (icssg_all_stats[i].offset == ICSSG_TX_PACKET_OFFSET) + if (icssg_all_miig_stats[i].offset == ICSSG_TX_PACKET_OFFSET) tx_pkt_cnt = val; emac->stats[i] += val; - if (icssg_all_stats[i].offset == ICSSG_TX_BYTE_OFFSET) + if (icssg_all_miig_stats[i].offset == ICSSG_TX_BYTE_OFFSET) emac->stats[i] -= tx_pkt_cnt * 8; } + + for (i = 0; i < ARRAY_SIZE(icssg_all_pa_stats); i++) { + reg = ICSSG_FW_STATS_BASE + icssg_all_pa_stats[i].offset * + PRUETH_NUM_MACS + slice * sizeof(u32); + regmap_read(prueth->pa_stats, reg, &val); + emac->pa_stats[i] += val; + } } void icssg_stats_work_handler(struct work_struct *work) @@ -57,9 +65,14 @@ int emac_get_stat_by_name(struct prueth_emac *emac, char *stat_name) { int i; - for (i = 0; i < ARRAY_SIZE(icssg_all_stats); i++) { - if (!strcmp(icssg_all_stats[i].name, stat_name)) - return emac->stats[icssg_all_stats[i].offset / sizeof(u32)]; + for (i = 0; i < ARRAY_SIZE(icssg_all_miig_stats); i++) { + if (!strcmp(icssg_all_miig_stats[i].name, stat_name)) + return emac->stats[icssg_all_miig_stats[i].offset / sizeof(u32)]; + } + + for (i = 0; i < ARRAY_SIZE(icssg_all_pa_stats); i++) { + if (!strcmp(icssg_all_pa_stats[i].name, stat_name)) + return emac->pa_stats[icssg_all_pa_stats[i].offset / sizeof(u32)]; } netdev_err(emac->ndev, "Invalid stats %s\n", stat_name); diff --git a/drivers/net/ethernet/ti/icssg/icssg_stats.h b/drivers/net/ethernet/ti/icssg/icssg_stats.h index 999a4a91276c..e88b919f532c 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_stats.h +++ b/drivers/net/ethernet/ti/icssg/icssg_stats.h @@ -77,82 +77,114 @@ struct miig_stats_regs { u32 tx_bytes; }; -#define ICSSG_STATS(field, stats_type) \ +#define ICSSG_MIIG_STATS(field, stats_type) \ { \ #field, \ offsetof(struct miig_stats_regs, field), \ stats_type \ } -struct icssg_stats { +struct icssg_miig_stats { char name[ETH_GSTRING_LEN]; u32 offset; bool standard_stats; }; -static const struct icssg_stats icssg_all_stats[] = { +static const struct icssg_miig_stats icssg_all_miig_stats[] = { /* Rx */ - ICSSG_STATS(rx_packets, true), - ICSSG_STATS(rx_broadcast_frames, false), - ICSSG_STATS(rx_multicast_frames, true), - ICSSG_STATS(rx_crc_errors, true), - ICSSG_STATS(rx_mii_error_frames, false), - ICSSG_STATS(rx_odd_nibble_frames, false), - ICSSG_STATS(rx_frame_max_size, true), - ICSSG_STATS(rx_max_size_error_frames, false), - ICSSG_STATS(rx_frame_min_size, true), - ICSSG_STATS(rx_min_size_error_frames, false), - ICSSG_STATS(rx_over_errors, true), - ICSSG_STATS(rx_class0_hits, false), - ICSSG_STATS(rx_class1_hits, false), - ICSSG_STATS(rx_class2_hits, false), - ICSSG_STATS(rx_class3_hits, false), - ICSSG_STATS(rx_class4_hits, false), - ICSSG_STATS(rx_class5_hits, false), - ICSSG_STATS(rx_class6_hits, false), - ICSSG_STATS(rx_class7_hits, false), - ICSSG_STATS(rx_class8_hits, false), - ICSSG_STATS(rx_class9_hits, false), - ICSSG_STATS(rx_class10_hits, false), - ICSSG_STATS(rx_class11_hits, false), - ICSSG_STATS(rx_class12_hits, false), - ICSSG_STATS(rx_class13_hits, false), - ICSSG_STATS(rx_class14_hits, false), - ICSSG_STATS(rx_class15_hits, false), - ICSSG_STATS(rx_smd_frags, false), - ICSSG_STATS(rx_bucket1_size, true), - ICSSG_STATS(rx_bucket2_size, true), - ICSSG_STATS(rx_bucket3_size, true), - ICSSG_STATS(rx_bucket4_size, true), - ICSSG_STATS(rx_64B_frames, true), - ICSSG_STATS(rx_bucket1_frames, true), - ICSSG_STATS(rx_bucket2_frames, true), - ICSSG_STATS(rx_bucket3_frames, true), - ICSSG_STATS(rx_bucket4_frames, true), - ICSSG_STATS(rx_bucket5_frames, true), - ICSSG_STATS(rx_bytes, true), - ICSSG_STATS(rx_tx_total_bytes, false), + ICSSG_MIIG_STATS(rx_packets, true), + ICSSG_MIIG_STATS(rx_broadcast_frames, false), + ICSSG_MIIG_STATS(rx_multicast_frames, true), + ICSSG_MIIG_STATS(rx_crc_errors, true), + ICSSG_MIIG_STATS(rx_mii_error_frames, false), + ICSSG_MIIG_STATS(rx_odd_nibble_frames, false), + ICSSG_MIIG_STATS(rx_frame_max_size, true), + ICSSG_MIIG_STATS(rx_max_size_error_frames, false), + ICSSG_MIIG_STATS(rx_frame_min_size, true), + ICSSG_MIIG_STATS(rx_min_size_error_frames, false), + ICSSG_MIIG_STATS(rx_over_errors, true), + ICSSG_MIIG_STATS(rx_class0_hits, false), + ICSSG_MIIG_STATS(rx_class1_hits, false), + ICSSG_MIIG_STATS(rx_class2_hits, false), + ICSSG_MIIG_STATS(rx_class3_hits, false), + ICSSG_MIIG_STATS(rx_class4_hits, false), + ICSSG_MIIG_STATS(rx_class5_hits, false), + ICSSG_MIIG_STATS(rx_class6_hits, false), + ICSSG_MIIG_STATS(rx_class7_hits, false), + ICSSG_MIIG_STATS(rx_class8_hits, false), + ICSSG_MIIG_STATS(rx_class9_hits, false), + ICSSG_MIIG_STATS(rx_class10_hits, false), + ICSSG_MIIG_STATS(rx_class11_hits, false), + ICSSG_MIIG_STATS(rx_class12_hits, false), + ICSSG_MIIG_STATS(rx_class13_hits, false), + ICSSG_MIIG_STATS(rx_class14_hits, false), + ICSSG_MIIG_STATS(rx_class15_hits, false), + ICSSG_MIIG_STATS(rx_smd_frags, false), + ICSSG_MIIG_STATS(rx_bucket1_size, true), + ICSSG_MIIG_STATS(rx_bucket2_size, true), + ICSSG_MIIG_STATS(rx_bucket3_size, true), + ICSSG_MIIG_STATS(rx_bucket4_size, true), + ICSSG_MIIG_STATS(rx_64B_frames, true), + ICSSG_MIIG_STATS(rx_bucket1_frames, true), + ICSSG_MIIG_STATS(rx_bucket2_frames, true), + ICSSG_MIIG_STATS(rx_bucket3_frames, true), + ICSSG_MIIG_STATS(rx_bucket4_frames, true), + ICSSG_MIIG_STATS(rx_bucket5_frames, true), + ICSSG_MIIG_STATS(rx_bytes, true), + ICSSG_MIIG_STATS(rx_tx_total_bytes, false), /* Tx */ - ICSSG_STATS(tx_packets, true), - ICSSG_STATS(tx_broadcast_frames, false), - ICSSG_STATS(tx_multicast_frames, false), - ICSSG_STATS(tx_odd_nibble_frames, false), - ICSSG_STATS(tx_underflow_errors, false), - ICSSG_STATS(tx_frame_max_size, true), - ICSSG_STATS(tx_max_size_error_frames, false), - ICSSG_STATS(tx_frame_min_size, true), - ICSSG_STATS(tx_min_size_error_frames, false), - ICSSG_STATS(tx_bucket1_size, true), - ICSSG_STATS(tx_bucket2_size, true), - ICSSG_STATS(tx_bucket3_size, true), - ICSSG_STATS(tx_bucket4_size, true), - ICSSG_STATS(tx_64B_frames, true), - ICSSG_STATS(tx_bucket1_frames, true), - ICSSG_STATS(tx_bucket2_frames, true), - ICSSG_STATS(tx_bucket3_frames, true), - ICSSG_STATS(tx_bucket4_frames, true), - ICSSG_STATS(tx_bucket5_frames, true), - ICSSG_STATS(tx_bytes, true), + ICSSG_MIIG_STATS(tx_packets, true), + ICSSG_MIIG_STATS(tx_broadcast_frames, false), + ICSSG_MIIG_STATS(tx_multicast_frames, false), + ICSSG_MIIG_STATS(tx_odd_nibble_frames, false), + ICSSG_MIIG_STATS(tx_underflow_errors, false), + ICSSG_MIIG_STATS(tx_frame_max_size, true), + ICSSG_MIIG_STATS(tx_max_size_error_frames, false), + ICSSG_MIIG_STATS(tx_frame_min_size, true), + ICSSG_MIIG_STATS(tx_min_size_error_frames, false), + ICSSG_MIIG_STATS(tx_bucket1_size, true), + ICSSG_MIIG_STATS(tx_bucket2_size, true), + ICSSG_MIIG_STATS(tx_bucket3_size, true), + ICSSG_MIIG_STATS(tx_bucket4_size, true), + ICSSG_MIIG_STATS(tx_64B_frames, true), + ICSSG_MIIG_STATS(tx_bucket1_frames, true), + ICSSG_MIIG_STATS(tx_bucket2_frames, true), + ICSSG_MIIG_STATS(tx_bucket3_frames, true), + ICSSG_MIIG_STATS(tx_bucket4_frames, true), + ICSSG_MIIG_STATS(tx_bucket5_frames, true), + ICSSG_MIIG_STATS(tx_bytes, true), +}; + +/** + * struct pa_stats_regs - ICSSG Firmware maintained PA Stats register + * @fw_rx_cnt: Number of valid packets sent by Rx PRU to Host on PSI + * @fw_tx_cnt: Number of valid packets copied by RTU0 to Tx queues + * @fw_tx_pre_overflow: Host Egress Q (Pre-emptible) Overflow Counter + * @fw_tx_exp_overflow: Host Egress Q (Express) Overflow Counter + */ +struct pa_stats_regs { + u32 fw_rx_cnt; + u32 fw_tx_cnt; + u32 fw_tx_pre_overflow; + u32 fw_tx_exp_overflow; +}; + +#define ICSSG_PA_STATS(field) \ +{ \ + #field, \ + offsetof(struct pa_stats_regs, field), \ +} + +struct icssg_pa_stats { + char name[ETH_GSTRING_LEN]; + u32 offset; +}; + +static const struct icssg_pa_stats icssg_all_pa_stats[] = { + ICSSG_PA_STATS(fw_rx_cnt), + ICSSG_PA_STATS(fw_tx_cnt), + ICSSG_PA_STATS(fw_tx_pre_overflow), + ICSSG_PA_STATS(fw_tx_exp_overflow), }; #endif /* __NET_TI_ICSSG_STATS_H */ diff --git a/drivers/net/ethernet/vertexcom/mse102x.c b/drivers/net/ethernet/vertexcom/mse102x.c index edd8b59680e5..a04d4073def9 100644 --- a/drivers/net/ethernet/vertexcom/mse102x.c +++ b/drivers/net/ethernet/vertexcom/mse102x.c @@ -377,8 +377,8 @@ static int mse102x_tx_pkt_spi(struct mse102x_net *mse, struct sk_buff *txb, int ret; bool first = true; - if (txb->len < 60) - pad = 60 - txb->len; + if (txb->len < ETH_ZLEN) + pad = ETH_ZLEN - txb->len; while (1) { mse102x_tx_cmd_spi(mse, CMD_RTS | (txb->len + pad)); @@ -451,7 +451,7 @@ static void mse102x_tx_work(struct work_struct *work) if (ret == -ETIMEDOUT) { if (netif_msg_timer(mse)) - netdev_err(mse->ndev, "tx work timeout\n"); + netdev_err_once(mse->ndev, "tx work timeout\n"); mse->stats.tx_timeout++; } @@ -485,8 +485,8 @@ static void mse102x_init_mac(struct mse102x_net *mse, struct device_node *np) if (ret) { eth_hw_addr_random(ndev); - netdev_err(ndev, "Using random MAC address: %pM\n", - ndev->dev_addr); + dev_warn(ndev->dev.parent, "Using random MAC address: %pM\n", + ndev->dev_addr); } } @@ -622,8 +622,6 @@ static const struct ethtool_ops mse102x_ethtool_ops = { /* driver bus management functions */ -#ifdef CONFIG_PM_SLEEP - static int mse102x_suspend(struct device *dev) { struct mse102x_net *mse = dev_get_drvdata(dev); @@ -649,9 +647,8 @@ static int mse102x_resume(struct device *dev) return 0; } -#endif -static SIMPLE_DEV_PM_OPS(mse102x_pm_ops, mse102x_suspend, mse102x_resume); +static DEFINE_SIMPLE_DEV_PM_OPS(mse102x_pm_ops, mse102x_suspend, mse102x_resume); static int mse102x_probe_spi(struct spi_device *spi) { @@ -736,9 +733,6 @@ static void mse102x_remove_spi(struct spi_device *spi) struct mse102x_net *mse = dev_get_drvdata(&spi->dev); struct mse102x_net_spi *mses = to_mse102x_spi(mse); - if (netif_msg_drv(mse)) - dev_info(&spi->dev, "remove\n"); - mse102x_remove_device_debugfs(mses); unregister_netdev(mse->ndev); } @@ -761,7 +755,7 @@ static struct spi_driver mse102x_driver = { .driver = { .name = DRV_NAME, .of_match_table = mse102x_match_table, - .pm = &mse102x_pm_ops, + .pm = pm_sleep_ptr(&mse102x_pm_ops), }, .probe = mse102x_probe_spi, .remove = mse102x_remove_spi, diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_lib.c index 1eecba984f3b..2b3d6586f44a 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_lib.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.c @@ -251,10 +251,7 @@ static struct sk_buff *wx_build_skb(struct wx_ring *rx_ring, rx_buffer->page_offset; /* prefetch first cache line of first page */ - prefetch(page_addr); -#if L1_CACHE_BYTES < 128 - prefetch(page_addr + L1_CACHE_BYTES); -#endif + net_prefetch(page_addr); /* allocate a skb to store the frags */ skb = napi_alloc_skb(&rx_ring->q_vector->napi, WX_RXBUFFER_256); diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c index d6b2b3c781b6..cd1372da92a9 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c @@ -103,8 +103,7 @@ static int txgbe_calc_eeprom_checksum(struct wx *wx, u16 *checksum) if (i != wx->eeprom.sw_region_offset + TXGBE_EEPROM_CHECKSUM) *checksum += local_buffer[i]; - if (eeprom_ptrs) - kvfree(eeprom_ptrs); + kvfree(eeprom_ptrs); *checksum = TXGBE_EEPROM_SUM - *checksum; diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c index 5f502265f0a6..67b61afdde96 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c @@ -688,8 +688,7 @@ static int txgbe_ext_phy_init(struct txgbe *txgbe) mii_bus->parent = &pdev->dev; mii_bus->phy_mask = GENMASK(31, 1); mii_bus->priv = wx; - snprintf(mii_bus->id, MII_BUS_ID_SIZE, "txgbe-%x", - (pdev->bus->number << 8) | pdev->devfn); + snprintf(mii_bus->id, MII_BUS_ID_SIZE, "txgbe-%x", pci_dev_id(pdev)); ret = devm_mdiobus_register(&pdev->dev, mii_bus); if (ret) { diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h index 09c9f9787180..c301dd2ee083 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet.h +++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h @@ -29,26 +29,26 @@ /* Configuration options */ /* Accept all incoming packets. Default: disabled (cleared) */ -#define XAE_OPTION_PROMISC (1 << 0) +#define XAE_OPTION_PROMISC BIT(0) /* Jumbo frame support for Tx & Rx. Default: disabled (cleared) */ -#define XAE_OPTION_JUMBO (1 << 1) +#define XAE_OPTION_JUMBO BIT(1) /* VLAN Rx & Tx frame support. Default: disabled (cleared) */ -#define XAE_OPTION_VLAN (1 << 2) +#define XAE_OPTION_VLAN BIT(2) /* Enable recognition of flow control frames on Rx. Default: enabled (set) */ -#define XAE_OPTION_FLOW_CONTROL (1 << 4) +#define XAE_OPTION_FLOW_CONTROL BIT(4) /* Strip FCS and PAD from incoming frames. Note: PAD from VLAN frames is not * stripped. Default: disabled (set) */ -#define XAE_OPTION_FCS_STRIP (1 << 5) +#define XAE_OPTION_FCS_STRIP BIT(5) /* Generate FCS field and add PAD automatically for outgoing frames. * Default: enabled (set) */ -#define XAE_OPTION_FCS_INSERT (1 << 6) +#define XAE_OPTION_FCS_INSERT BIT(6) /* Enable Length/Type error checking for incoming frames. When this option is * set, the MAC will filter frames that have a mismatched type/length field @@ -56,13 +56,13 @@ * types of frames are encountered. When this option is cleared, the MAC will * allow these types of frames to be received. Default: enabled (set) */ -#define XAE_OPTION_LENTYPE_ERR (1 << 7) +#define XAE_OPTION_LENTYPE_ERR BIT(7) /* Enable the transmitter. Default: enabled (set) */ -#define XAE_OPTION_TXEN (1 << 11) +#define XAE_OPTION_TXEN BIT(11) /* Enable the receiver. Default: enabled (set) */ -#define XAE_OPTION_RXEN (1 << 12) +#define XAE_OPTION_RXEN BIT(12) /* Default options set when device is initialized or reset */ #define XAE_OPTION_DEFAULTS \ @@ -156,6 +156,7 @@ #define XAE_TPID0_OFFSET 0x00000028 /* VLAN TPID0 register */ #define XAE_TPID1_OFFSET 0x0000002C /* VLAN TPID1 register */ #define XAE_PPST_OFFSET 0x00000030 /* PCS PMA Soft Temac Status Reg */ +#define XAE_STATS_OFFSET 0x00000200 /* Statistics counters */ #define XAE_RCW0_OFFSET 0x00000400 /* Rx Configuration Word 0 */ #define XAE_RCW1_OFFSET 0x00000404 /* Rx Configuration Word 1 */ #define XAE_TC_OFFSET 0x00000408 /* Tx Configuration */ @@ -163,6 +164,7 @@ #define XAE_EMMC_OFFSET 0x00000410 /* MAC speed configuration */ #define XAE_PHYC_OFFSET 0x00000414 /* RX Max Frame Configuration */ #define XAE_ID_OFFSET 0x000004F8 /* Identification register */ +#define XAE_ABILITY_OFFSET 0x000004FC /* Ability Register offset */ #define XAE_MDIO_MC_OFFSET 0x00000500 /* MDIO Setup */ #define XAE_MDIO_MCR_OFFSET 0x00000504 /* MDIO Control */ #define XAE_MDIO_MWD_OFFSET 0x00000508 /* MDIO Write Data */ @@ -173,6 +175,8 @@ #define XAE_FFE_OFFSET 0x0000070C /* Frame Filter Enable */ #define XAE_AF0_OFFSET 0x00000710 /* Address Filter 0 */ #define XAE_AF1_OFFSET 0x00000714 /* Address Filter 1 */ +#define XAE_AM0_OFFSET 0x00000750 /* Frame Filter Mask Value Bytes 3-0 */ +#define XAE_AM1_OFFSET 0x00000754 /* Frame Filter Mask Value Bytes 7-4 */ #define XAE_TX_VLAN_DATA_OFFSET 0x00004000 /* TX VLAN data table address */ #define XAE_RX_VLAN_DATA_OFFSET 0x00008000 /* RX VLAN data table address */ @@ -284,6 +288,16 @@ #define XAE_PHYC_SGLINKSPD_100 0x40000000 /* SGMII link 100 Mbit */ #define XAE_PHYC_SGLINKSPD_1000 0x80000000 /* SGMII link 1000 Mbit */ +/* Bit masks for Axi Ethernet ability register */ +#define XAE_ABILITY_PFC BIT(16) +#define XAE_ABILITY_FRAME_FILTER BIT(10) +#define XAE_ABILITY_HALF_DUPLEX BIT(9) +#define XAE_ABILITY_STATS BIT(8) +#define XAE_ABILITY_2_5G BIT(3) +#define XAE_ABILITY_1G BIT(2) +#define XAE_ABILITY_100M BIT(1) +#define XAE_ABILITY_10M BIT(0) + /* Bit masks for Axi Ethernet MDIO interface MC register */ #define XAE_MDIO_MC_MDIOEN_MASK 0x00000040 /* MII management enable */ #define XAE_MDIO_MC_CLOCK_DIVIDE_MAX 0x3F /* Maximum MDIO divisor */ @@ -327,11 +341,12 @@ #define XAE_MULTICAST_CAM_TABLE_NUM 4 /* Axi Ethernet Synthesis features */ -#define XAE_FEATURE_PARTIAL_RX_CSUM (1 << 0) -#define XAE_FEATURE_PARTIAL_TX_CSUM (1 << 1) -#define XAE_FEATURE_FULL_RX_CSUM (1 << 2) -#define XAE_FEATURE_FULL_TX_CSUM (1 << 3) -#define XAE_FEATURE_DMA_64BIT (1 << 4) +#define XAE_FEATURE_PARTIAL_RX_CSUM BIT(0) +#define XAE_FEATURE_PARTIAL_TX_CSUM BIT(1) +#define XAE_FEATURE_FULL_RX_CSUM BIT(2) +#define XAE_FEATURE_FULL_TX_CSUM BIT(3) +#define XAE_FEATURE_DMA_64BIT BIT(4) +#define XAE_FEATURE_STATS BIT(5) #define XAE_NO_CSUM_OFFLOAD 0 @@ -345,6 +360,61 @@ #define XLNX_MII_STD_SELECT_REG 0x11 #define XLNX_MII_STD_SELECT_SGMII BIT(0) +/* enum temac_stat - TEMAC statistics counters + * + * Index of statistics counters within the TEMAC. This must match the + * order/offset of hardware registers exactly. + */ +enum temac_stat { + STAT_RX_BYTES = 0, + STAT_TX_BYTES, + STAT_UNDERSIZE_FRAMES, + STAT_FRAGMENT_FRAMES, + STAT_RX_64_BYTE_FRAMES, + STAT_RX_65_127_BYTE_FRAMES, + STAT_RX_128_255_BYTE_FRAMES, + STAT_RX_256_511_BYTE_FRAMES, + STAT_RX_512_1023_BYTE_FRAMES, + STAT_RX_1024_MAX_BYTE_FRAMES, + STAT_RX_OVERSIZE_FRAMES, + STAT_TX_64_BYTE_FRAMES, + STAT_TX_65_127_BYTE_FRAMES, + STAT_TX_128_255_BYTE_FRAMES, + STAT_TX_256_511_BYTE_FRAMES, + STAT_TX_512_1023_BYTE_FRAMES, + STAT_TX_1024_MAX_BYTE_FRAMES, + STAT_TX_OVERSIZE_FRAMES, + STAT_RX_GOOD_FRAMES, + STAT_RX_FCS_ERRORS, + STAT_RX_BROADCAST_FRAMES, + STAT_RX_MULTICAST_FRAMES, + STAT_RX_CONTROL_FRAMES, + STAT_RX_LENGTH_ERRORS, + STAT_RX_VLAN_FRAMES, + STAT_RX_PAUSE_FRAMES, + STAT_RX_CONTROL_OPCODE_ERRORS, + STAT_TX_GOOD_FRAMES, + STAT_TX_BROADCAST_FRAMES, + STAT_TX_MULTICAST_FRAMES, + STAT_TX_UNDERRUN_ERRORS, + STAT_TX_CONTROL_FRAMES, + STAT_TX_VLAN_FRAMES, + STAT_TX_PAUSE_FRAMES, + STAT_TX_SINGLE_COLLISION_FRAMES, + STAT_TX_MULTIPLE_COLLISION_FRAMES, + STAT_TX_DEFERRED_FRAMES, + STAT_TX_LATE_COLLISIONS, + STAT_TX_EXCESS_COLLISIONS, + STAT_TX_EXCESS_DEFERRAL, + STAT_RX_ALIGNMENT_ERRORS, + STAT_TX_PFC_FRAMES, + STAT_RX_PFC_FRAMES, + STAT_USER_DEFINED0, + STAT_USER_DEFINED1, + STAT_USER_DEFINED2, + STAT_COUNT, +}; + /** * struct axidma_bd - Axi Dma buffer descriptor layout * @next: MM2S/S2MM Next Descriptor Pointer @@ -435,6 +505,16 @@ struct skbuf_dma_descriptor { * @tx_packets: TX packet count for statistics * @tx_bytes: TX byte count for statistics * @tx_stat_sync: Synchronization object for TX stats + * @hw_stat_base: Base offset for statistics counters. This may be nonzero if + * the statistics counteres were reset or wrapped around. + * @hw_last_counter: Last-seen value of each statistic counter + * @reset_in_progress: Set while we are performing a reset and statistics + * counters may be invalid + * @hw_stats_seqcount: Sequence counter for @hw_stat_base, @hw_last_counter, + * and @reset_in_progress. + * @stats_lock: Lock for @hw_stats_seqcount + * @stats_work: Work for reading the hardware statistics counters often enough + * to catch overflows. * @dma_err_task: Work structure to process Axi DMA errors * @tx_irq: Axidma TX IRQ number * @rx_irq: Axidma RX IRQ number @@ -506,6 +586,13 @@ struct axienet_local { u64_stats_t tx_bytes; struct u64_stats_sync tx_stat_sync; + u64 hw_stat_base[STAT_COUNT]; + u32 hw_last_counter[STAT_COUNT]; + seqcount_mutex_t hw_stats_seqcount; + struct mutex stats_lock; + struct delayed_work stats_work; + bool reset_in_progress; + struct work_struct dma_err_task; int tx_irq; diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 9aeb7b9f3ae4..fe6a0e2e463f 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -415,6 +415,7 @@ static void axienet_set_mac_address(struct net_device *ndev, static int netdev_set_mac_address(struct net_device *ndev, void *p) { struct sockaddr *addr = p; + axienet_set_mac_address(ndev, addr->sa_data); return 0; } @@ -436,24 +437,27 @@ static void axienet_set_multicast_list(struct net_device *ndev) u32 reg, af0reg, af1reg; struct axienet_local *lp = netdev_priv(ndev); - if (ndev->flags & (IFF_ALLMULTI | IFF_PROMISC) || - netdev_mc_count(ndev) > XAE_MULTICAST_CAM_TABLE_NUM) { - /* We must make the kernel realize we had to move into - * promiscuous mode. If it was a promiscuous mode request - * the flag is already set. If not we set it. - */ - ndev->flags |= IFF_PROMISC; - reg = axienet_ior(lp, XAE_FMI_OFFSET); + reg = axienet_ior(lp, XAE_FMI_OFFSET); + reg &= ~XAE_FMI_PM_MASK; + if (ndev->flags & IFF_PROMISC) reg |= XAE_FMI_PM_MASK; + else + reg &= ~XAE_FMI_PM_MASK; + axienet_iow(lp, XAE_FMI_OFFSET, reg); + + if (ndev->flags & IFF_ALLMULTI || + netdev_mc_count(ndev) > XAE_MULTICAST_CAM_TABLE_NUM) { + reg &= 0xFFFFFF00; axienet_iow(lp, XAE_FMI_OFFSET, reg); - dev_info(&ndev->dev, "Promiscuous mode enabled.\n"); + axienet_iow(lp, XAE_AF0_OFFSET, 1); /* Multicast bit */ + axienet_iow(lp, XAE_AF1_OFFSET, 0); + axienet_iow(lp, XAE_AM0_OFFSET, 1); /* ditto */ + axienet_iow(lp, XAE_AM1_OFFSET, 0); + axienet_iow(lp, XAE_FFE_OFFSET, 1); + i = 1; } else if (!netdev_mc_empty(ndev)) { struct netdev_hw_addr *ha; - reg = axienet_ior(lp, XAE_FMI_OFFSET); - reg &= ~XAE_FMI_PM_MASK; - axienet_iow(lp, XAE_FMI_OFFSET, reg); - netdev_for_each_mc_addr(ha, ndev) { if (i >= XAE_MULTICAST_CAM_TABLE_NUM) break; @@ -466,25 +470,21 @@ static void axienet_set_multicast_list(struct net_device *ndev) af1reg = (ha->addr[4]); af1reg |= (ha->addr[5] << 8); - reg = axienet_ior(lp, XAE_FMI_OFFSET) & 0xFFFFFF00; + reg &= 0xFFFFFF00; reg |= i; axienet_iow(lp, XAE_FMI_OFFSET, reg); axienet_iow(lp, XAE_AF0_OFFSET, af0reg); axienet_iow(lp, XAE_AF1_OFFSET, af1reg); + axienet_iow(lp, XAE_AM0_OFFSET, 0xffffffff); + axienet_iow(lp, XAE_AM1_OFFSET, 0x0000ffff); axienet_iow(lp, XAE_FFE_OFFSET, 1); i++; } - } else { - reg = axienet_ior(lp, XAE_FMI_OFFSET); - reg &= ~XAE_FMI_PM_MASK; - - axienet_iow(lp, XAE_FMI_OFFSET, reg); - dev_info(&ndev->dev, "Promiscuous mode disabled.\n"); } for (; i < XAE_MULTICAST_CAM_TABLE_NUM; i++) { - reg = axienet_ior(lp, XAE_FMI_OFFSET) & 0xFFFFFF00; + reg &= 0xFFFFFF00; reg |= i; axienet_iow(lp, XAE_FMI_OFFSET, reg); axienet_iow(lp, XAE_FFE_OFFSET, 0); @@ -519,11 +519,55 @@ static void axienet_setoptions(struct net_device *ndev, u32 options) lp->options |= options; } +static u64 axienet_stat(struct axienet_local *lp, enum temac_stat stat) +{ + u32 counter; + + if (lp->reset_in_progress) + return lp->hw_stat_base[stat]; + + counter = axienet_ior(lp, XAE_STATS_OFFSET + stat * 8); + return lp->hw_stat_base[stat] + (counter - lp->hw_last_counter[stat]); +} + +static void axienet_stats_update(struct axienet_local *lp, bool reset) +{ + enum temac_stat stat; + + write_seqcount_begin(&lp->hw_stats_seqcount); + lp->reset_in_progress = reset; + for (stat = 0; stat < STAT_COUNT; stat++) { + u32 counter = axienet_ior(lp, XAE_STATS_OFFSET + stat * 8); + + lp->hw_stat_base[stat] += counter - lp->hw_last_counter[stat]; + lp->hw_last_counter[stat] = counter; + } + write_seqcount_end(&lp->hw_stats_seqcount); +} + +static void axienet_refresh_stats(struct work_struct *work) +{ + struct axienet_local *lp = container_of(work, struct axienet_local, + stats_work.work); + + mutex_lock(&lp->stats_lock); + axienet_stats_update(lp, false); + mutex_unlock(&lp->stats_lock); + + /* Just less than 2^32 bytes at 2.5 GBit/s */ + schedule_delayed_work(&lp->stats_work, 13 * HZ); +} + static int __axienet_device_reset(struct axienet_local *lp) { u32 value; int ret; + /* Save statistics counters in case they will be reset */ + mutex_lock(&lp->stats_lock); + if (lp->features & XAE_FEATURE_STATS) + axienet_stats_update(lp, true); + /* Reset Axi DMA. This would reset Axi Ethernet core as well. The reset * process of Axi DMA takes a while to complete as all pending * commands/transfers will be flushed or completed during this @@ -538,7 +582,7 @@ static int __axienet_device_reset(struct axienet_local *lp) XAXIDMA_TX_CR_OFFSET); if (ret) { dev_err(lp->dev, "%s: DMA reset timeout!\n", __func__); - return ret; + goto out; } /* Wait for PhyRstCmplt bit to be set, indicating the PHY reset has finished */ @@ -548,10 +592,29 @@ static int __axienet_device_reset(struct axienet_local *lp) XAE_IS_OFFSET); if (ret) { dev_err(lp->dev, "%s: timeout waiting for PhyRstCmplt\n", __func__); - return ret; + goto out; } - return 0; + /* Update statistics counters with new values */ + if (lp->features & XAE_FEATURE_STATS) { + enum temac_stat stat; + + write_seqcount_begin(&lp->hw_stats_seqcount); + lp->reset_in_progress = false; + for (stat = 0; stat < STAT_COUNT; stat++) { + u32 counter = + axienet_ior(lp, XAE_STATS_OFFSET + stat * 8); + + lp->hw_stat_base[stat] += + lp->hw_last_counter[stat] - counter; + lp->hw_last_counter[stat] = counter; + } + write_seqcount_end(&lp->hw_stats_seqcount); + } + +out: + mutex_unlock(&lp->stats_lock); + return ret; } /** @@ -614,8 +677,7 @@ static int axienet_device_reset(struct net_device *ndev) lp->options |= XAE_OPTION_VLAN; lp->options &= (~XAE_OPTION_JUMBO); - if ((ndev->mtu > XAE_MTU) && - (ndev->mtu <= XAE_JUMBO_MTU)) { + if (ndev->mtu > XAE_MTU && ndev->mtu <= XAE_JUMBO_MTU) { lp->max_frm_size = ndev->mtu + VLAN_ETH_HLEN + XAE_TRL_SIZE; @@ -1297,7 +1359,7 @@ static irqreturn_t axienet_eth_irq(int irq, void *_ndev) ndev->stats.rx_missed_errors++; if (pending & XAE_INT_RXRJECT_MASK) - ndev->stats.rx_frame_errors++; + ndev->stats.rx_dropped++; axienet_iow(lp, XAE_IS_OFFSET, pending); return IRQ_HANDLED; @@ -1515,8 +1577,6 @@ static int axienet_open(struct net_device *ndev) int ret; struct axienet_local *lp = netdev_priv(ndev); - dev_dbg(&ndev->dev, "%s\n", __func__); - /* When we do an Axi Ethernet reset, it resets the complete core * including the MDIO. MDIO must be disabled before resetting. * Hold MDIO bus lock to avoid MDIO accesses during the reset. @@ -1533,6 +1593,9 @@ static int axienet_open(struct net_device *ndev) phylink_start(lp->phylink); + /* Start the statistics refresh work */ + schedule_delayed_work(&lp->stats_work, 0); + if (lp->use_dmaengine) { /* Enable interrupts for Axi Ethernet core (if defined) */ if (lp->eth_irq > 0) { @@ -1557,6 +1620,7 @@ err_free_eth_irq: if (lp->eth_irq > 0) free_irq(lp->eth_irq, ndev); err_phy: + cancel_delayed_work_sync(&lp->stats_work); phylink_stop(lp->phylink); phylink_disconnect_phy(lp->phylink); return ret; @@ -1577,13 +1641,13 @@ static int axienet_stop(struct net_device *ndev) struct axienet_local *lp = netdev_priv(ndev); int i; - dev_dbg(&ndev->dev, "axienet_close()\n"); - if (!lp->use_dmaengine) { napi_disable(&lp->napi_tx); napi_disable(&lp->napi_rx); } + cancel_delayed_work_sync(&lp->stats_work); + phylink_stop(lp->phylink); phylink_disconnect_phy(lp->phylink); @@ -1658,6 +1722,7 @@ static int axienet_change_mtu(struct net_device *ndev, int new_mtu) static void axienet_poll_controller(struct net_device *ndev) { struct axienet_local *lp = netdev_priv(ndev); + disable_irq(lp->tx_irq); disable_irq(lp->rx_irq); axienet_rx_irq(lp->tx_irq, ndev); @@ -1696,6 +1761,35 @@ axienet_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) stats->tx_packets = u64_stats_read(&lp->tx_packets); stats->tx_bytes = u64_stats_read(&lp->tx_bytes); } while (u64_stats_fetch_retry(&lp->tx_stat_sync, start)); + + if (!(lp->features & XAE_FEATURE_STATS)) + return; + + do { + start = read_seqcount_begin(&lp->hw_stats_seqcount); + stats->rx_length_errors = + axienet_stat(lp, STAT_RX_LENGTH_ERRORS); + stats->rx_crc_errors = axienet_stat(lp, STAT_RX_FCS_ERRORS); + stats->rx_frame_errors = + axienet_stat(lp, STAT_RX_ALIGNMENT_ERRORS); + stats->rx_errors = axienet_stat(lp, STAT_UNDERSIZE_FRAMES) + + axienet_stat(lp, STAT_FRAGMENT_FRAMES) + + stats->rx_length_errors + + stats->rx_crc_errors + + stats->rx_frame_errors; + stats->multicast = axienet_stat(lp, STAT_RX_MULTICAST_FRAMES); + + stats->tx_aborted_errors = + axienet_stat(lp, STAT_TX_EXCESS_COLLISIONS); + stats->tx_fifo_errors = + axienet_stat(lp, STAT_TX_UNDERRUN_ERRORS); + stats->tx_window_errors = + axienet_stat(lp, STAT_TX_LATE_COLLISIONS); + stats->tx_errors = axienet_stat(lp, STAT_TX_EXCESS_DEFERRAL) + + stats->tx_aborted_errors + + stats->tx_fifo_errors + + stats->tx_window_errors; + } while (read_seqcount_retry(&lp->hw_stats_seqcount, start)); } static const struct net_device_ops axienet_netdev_ops = { @@ -1988,6 +2082,213 @@ static int axienet_ethtools_nway_reset(struct net_device *dev) return phylink_ethtool_nway_reset(lp->phylink); } +static void axienet_ethtools_get_ethtool_stats(struct net_device *dev, + struct ethtool_stats *stats, + u64 *data) +{ + struct axienet_local *lp = netdev_priv(dev); + unsigned int start; + + do { + start = read_seqcount_begin(&lp->hw_stats_seqcount); + data[0] = axienet_stat(lp, STAT_RX_BYTES); + data[1] = axienet_stat(lp, STAT_TX_BYTES); + data[2] = axienet_stat(lp, STAT_RX_VLAN_FRAMES); + data[3] = axienet_stat(lp, STAT_TX_VLAN_FRAMES); + data[6] = axienet_stat(lp, STAT_TX_PFC_FRAMES); + data[7] = axienet_stat(lp, STAT_RX_PFC_FRAMES); + data[8] = axienet_stat(lp, STAT_USER_DEFINED0); + data[9] = axienet_stat(lp, STAT_USER_DEFINED1); + data[10] = axienet_stat(lp, STAT_USER_DEFINED2); + } while (read_seqcount_retry(&lp->hw_stats_seqcount, start)); +} + +static const char axienet_ethtool_stats_strings[][ETH_GSTRING_LEN] = { + "Received bytes", + "Transmitted bytes", + "RX Good VLAN Tagged Frames", + "TX Good VLAN Tagged Frames", + "TX Good PFC Frames", + "RX Good PFC Frames", + "User Defined Counter 0", + "User Defined Counter 1", + "User Defined Counter 2", +}; + +static void axienet_ethtools_get_strings(struct net_device *dev, u32 stringset, u8 *data) +{ + switch (stringset) { + case ETH_SS_STATS: + memcpy(data, axienet_ethtool_stats_strings, + sizeof(axienet_ethtool_stats_strings)); + break; + } +} + +static int axienet_ethtools_get_sset_count(struct net_device *dev, int sset) +{ + struct axienet_local *lp = netdev_priv(dev); + + switch (sset) { + case ETH_SS_STATS: + if (lp->features & XAE_FEATURE_STATS) + return ARRAY_SIZE(axienet_ethtool_stats_strings); + fallthrough; + default: + return -EOPNOTSUPP; + } +} + +static void +axienet_ethtools_get_pause_stats(struct net_device *dev, + struct ethtool_pause_stats *pause_stats) +{ + struct axienet_local *lp = netdev_priv(dev); + unsigned int start; + + if (!(lp->features & XAE_FEATURE_STATS)) + return; + + do { + start = read_seqcount_begin(&lp->hw_stats_seqcount); + pause_stats->tx_pause_frames = + axienet_stat(lp, STAT_TX_PAUSE_FRAMES); + pause_stats->rx_pause_frames = + axienet_stat(lp, STAT_RX_PAUSE_FRAMES); + } while (read_seqcount_retry(&lp->hw_stats_seqcount, start)); +} + +static void +axienet_ethtool_get_eth_mac_stats(struct net_device *dev, + struct ethtool_eth_mac_stats *mac_stats) +{ + struct axienet_local *lp = netdev_priv(dev); + unsigned int start; + + if (!(lp->features & XAE_FEATURE_STATS)) + return; + + do { + start = read_seqcount_begin(&lp->hw_stats_seqcount); + mac_stats->FramesTransmittedOK = + axienet_stat(lp, STAT_TX_GOOD_FRAMES); + mac_stats->SingleCollisionFrames = + axienet_stat(lp, STAT_TX_SINGLE_COLLISION_FRAMES); + mac_stats->MultipleCollisionFrames = + axienet_stat(lp, STAT_TX_MULTIPLE_COLLISION_FRAMES); + mac_stats->FramesReceivedOK = + axienet_stat(lp, STAT_RX_GOOD_FRAMES); + mac_stats->FrameCheckSequenceErrors = + axienet_stat(lp, STAT_RX_FCS_ERRORS); + mac_stats->AlignmentErrors = + axienet_stat(lp, STAT_RX_ALIGNMENT_ERRORS); + mac_stats->FramesWithDeferredXmissions = + axienet_stat(lp, STAT_TX_DEFERRED_FRAMES); + mac_stats->LateCollisions = + axienet_stat(lp, STAT_TX_LATE_COLLISIONS); + mac_stats->FramesAbortedDueToXSColls = + axienet_stat(lp, STAT_TX_EXCESS_COLLISIONS); + mac_stats->MulticastFramesXmittedOK = + axienet_stat(lp, STAT_TX_MULTICAST_FRAMES); + mac_stats->BroadcastFramesXmittedOK = + axienet_stat(lp, STAT_TX_BROADCAST_FRAMES); + mac_stats->FramesWithExcessiveDeferral = + axienet_stat(lp, STAT_TX_EXCESS_DEFERRAL); + mac_stats->MulticastFramesReceivedOK = + axienet_stat(lp, STAT_RX_MULTICAST_FRAMES); + mac_stats->BroadcastFramesReceivedOK = + axienet_stat(lp, STAT_RX_BROADCAST_FRAMES); + mac_stats->InRangeLengthErrors = + axienet_stat(lp, STAT_RX_LENGTH_ERRORS); + } while (read_seqcount_retry(&lp->hw_stats_seqcount, start)); +} + +static void +axienet_ethtool_get_eth_ctrl_stats(struct net_device *dev, + struct ethtool_eth_ctrl_stats *ctrl_stats) +{ + struct axienet_local *lp = netdev_priv(dev); + unsigned int start; + + if (!(lp->features & XAE_FEATURE_STATS)) + return; + + do { + start = read_seqcount_begin(&lp->hw_stats_seqcount); + ctrl_stats->MACControlFramesTransmitted = + axienet_stat(lp, STAT_TX_CONTROL_FRAMES); + ctrl_stats->MACControlFramesReceived = + axienet_stat(lp, STAT_RX_CONTROL_FRAMES); + ctrl_stats->UnsupportedOpcodesReceived = + axienet_stat(lp, STAT_RX_CONTROL_OPCODE_ERRORS); + } while (read_seqcount_retry(&lp->hw_stats_seqcount, start)); +} + +static const struct ethtool_rmon_hist_range axienet_rmon_ranges[] = { + { 64, 64 }, + { 65, 127 }, + { 128, 255 }, + { 256, 511 }, + { 512, 1023 }, + { 1024, 1518 }, + { 1519, 16384 }, + { }, +}; + +static void +axienet_ethtool_get_rmon_stats(struct net_device *dev, + struct ethtool_rmon_stats *rmon_stats, + const struct ethtool_rmon_hist_range **ranges) +{ + struct axienet_local *lp = netdev_priv(dev); + unsigned int start; + + if (!(lp->features & XAE_FEATURE_STATS)) + return; + + do { + start = read_seqcount_begin(&lp->hw_stats_seqcount); + rmon_stats->undersize_pkts = + axienet_stat(lp, STAT_UNDERSIZE_FRAMES); + rmon_stats->oversize_pkts = + axienet_stat(lp, STAT_RX_OVERSIZE_FRAMES); + rmon_stats->fragments = + axienet_stat(lp, STAT_FRAGMENT_FRAMES); + + rmon_stats->hist[0] = + axienet_stat(lp, STAT_RX_64_BYTE_FRAMES); + rmon_stats->hist[1] = + axienet_stat(lp, STAT_RX_65_127_BYTE_FRAMES); + rmon_stats->hist[2] = + axienet_stat(lp, STAT_RX_128_255_BYTE_FRAMES); + rmon_stats->hist[3] = + axienet_stat(lp, STAT_RX_256_511_BYTE_FRAMES); + rmon_stats->hist[4] = + axienet_stat(lp, STAT_RX_512_1023_BYTE_FRAMES); + rmon_stats->hist[5] = + axienet_stat(lp, STAT_RX_1024_MAX_BYTE_FRAMES); + rmon_stats->hist[6] = + rmon_stats->oversize_pkts; + + rmon_stats->hist_tx[0] = + axienet_stat(lp, STAT_TX_64_BYTE_FRAMES); + rmon_stats->hist_tx[1] = + axienet_stat(lp, STAT_TX_65_127_BYTE_FRAMES); + rmon_stats->hist_tx[2] = + axienet_stat(lp, STAT_TX_128_255_BYTE_FRAMES); + rmon_stats->hist_tx[3] = + axienet_stat(lp, STAT_TX_256_511_BYTE_FRAMES); + rmon_stats->hist_tx[4] = + axienet_stat(lp, STAT_TX_512_1023_BYTE_FRAMES); + rmon_stats->hist_tx[5] = + axienet_stat(lp, STAT_TX_1024_MAX_BYTE_FRAMES); + rmon_stats->hist_tx[6] = + axienet_stat(lp, STAT_TX_OVERSIZE_FRAMES); + } while (read_seqcount_retry(&lp->hw_stats_seqcount, start)); + + *ranges = axienet_rmon_ranges; +} + static const struct ethtool_ops axienet_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_MAX_FRAMES | ETHTOOL_COALESCE_USECS, @@ -2004,6 +2305,13 @@ static const struct ethtool_ops axienet_ethtool_ops = { .get_link_ksettings = axienet_ethtools_get_link_ksettings, .set_link_ksettings = axienet_ethtools_set_link_ksettings, .nway_reset = axienet_ethtools_nway_reset, + .get_ethtool_stats = axienet_ethtools_get_ethtool_stats, + .get_strings = axienet_ethtools_get_strings, + .get_sset_count = axienet_ethtools_get_sset_count, + .get_pause_stats = axienet_ethtools_get_pause_stats, + .get_eth_mac_stats = axienet_ethtool_get_eth_mac_stats, + .get_eth_ctrl_stats = axienet_ethtool_get_eth_ctrl_stats, + .get_rmon_stats = axienet_ethtool_get_rmon_stats, }; static struct axienet_local *pcs_to_axienet_local(struct phylink_pcs *pcs) @@ -2272,6 +2580,10 @@ static int axienet_probe(struct platform_device *pdev) u64_stats_init(&lp->rx_stat_sync); u64_stats_init(&lp->tx_stat_sync); + mutex_init(&lp->stats_lock); + seqcount_mutex_init(&lp->hw_stats_seqcount, &lp->stats_lock); + INIT_DEFERRABLE_WORK(&lp->stats_work, axienet_refresh_stats); + lp->axi_clk = devm_clk_get_optional(&pdev->dev, "s_axi_lite_clk"); if (!lp->axi_clk) { /* For backward compatibility, if named AXI clock is not present, @@ -2312,6 +2624,9 @@ static int axienet_probe(struct platform_device *pdev) /* Setup checksum offload, but default to off if not specified */ lp->features = 0; + if (axienet_ior(lp, XAE_ABILITY_OFFSET) & XAE_ABILITY_STATS) + lp->features |= XAE_FEATURE_STATS; + ret = of_property_read_u32(pdev->dev.of_node, "xlnx,txcsum", &value); if (!ret) { switch (value) { @@ -2397,7 +2712,7 @@ static int axienet_probe(struct platform_device *pdev) goto cleanup_clk; } - if (!of_find_property(pdev->dev.of_node, "dmas", NULL)) { + if (!of_property_present(pdev->dev.of_node, "dmas")) { /* Find the DMA node, map the DMA registers, and decode the DMA IRQs */ np = of_parse_phandle(pdev->dev.of_node, "axistream-connected", 0); diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index 810977952f95..e690b95b1bbb 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -882,7 +882,7 @@ struct nvsp_message { #define VRSS_SEND_TAB_SIZE 16 /* must be power of 2 */ #define VRSS_CHANNEL_MAX 64 -#define VRSS_CHANNEL_DEFAULT 8 +#define VRSS_CHANNEL_DEFAULT 16 #define RNDIS_MAX_PKT_DEFAULT 8 #define RNDIS_PKT_ALIGN_DEFAULT 8 diff --git a/drivers/net/hyperv/netvsc_bpf.c b/drivers/net/hyperv/netvsc_bpf.c index 4a9522689fa4..e01c5997a551 100644 --- a/drivers/net/hyperv/netvsc_bpf.c +++ b/drivers/net/hyperv/netvsc_bpf.c @@ -183,7 +183,7 @@ int netvsc_vf_setxdp(struct net_device *vf_netdev, struct bpf_prog *prog) xdp.command = XDP_SETUP_PROG; xdp.prog = prog; - ret = vf_netdev->netdev_ops->ndo_bpf(vf_netdev, &xdp); + ret = dev_xdp_propagate(vf_netdev, &xdp); if (ret && prog) bpf_prog_put(prog); diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 44142245343d..153b97f8ec0d 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -987,7 +987,8 @@ struct netvsc_device_info *netvsc_devinfo_get(struct netvsc_device *nvdev) dev_info->bprog = prog; } } else { - dev_info->num_chn = VRSS_CHANNEL_DEFAULT; + dev_info->num_chn = max(VRSS_CHANNEL_DEFAULT, + netif_get_num_default_rss_queues()); dev_info->send_sections = NETVSC_DEFAULT_TX; dev_info->send_section_size = NETVSC_SEND_SECTION_SIZE; dev_info->recv_sections = NETVSC_DEFAULT_RX; diff --git a/drivers/net/ipa/ipa_power.c b/drivers/net/ipa/ipa_power.c index 65fd14da0f86..c572da9e9bc4 100644 --- a/drivers/net/ipa/ipa_power.c +++ b/drivers/net/ipa/ipa_power.c @@ -242,11 +242,8 @@ ipa_power_init(struct device *dev, const struct ipa_power_data *data) int ret; clk = clk_get(dev, "core"); - if (IS_ERR(clk)) { - dev_err_probe(dev, PTR_ERR(clk), "error getting core clock\n"); - - return ERR_CAST(clk); - } + if (IS_ERR(clk)) + return dev_err_cast_probe(dev, clk, "error getting core clock\n"); ret = clk_set_rate(clk, data->core_clock_rate); if (ret) { diff --git a/drivers/net/mdio/of_mdio.c b/drivers/net/mdio/of_mdio.c index 08e607f62e10..2f4fc664d2e1 100644 --- a/drivers/net/mdio/of_mdio.c +++ b/drivers/net/mdio/of_mdio.c @@ -390,7 +390,7 @@ EXPORT_SYMBOL(of_phy_get_and_connect); bool of_phy_is_fixed_link(struct device_node *np) { struct device_node *dn; - int len, err; + int err; const char *managed; /* New binding */ @@ -405,8 +405,7 @@ bool of_phy_is_fixed_link(struct device_node *np) return true; /* Old binding */ - if (of_get_property(np, "fixed-link", &len) && - len == (5 * sizeof(__be32))) + if (of_property_count_u32_elems(np, "fixed-link") == 5) return true; return false; diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c index 9c09293b5258..01cf33fa7503 100644 --- a/drivers/net/netconsole.c +++ b/drivers/net/netconsole.c @@ -37,8 +37,9 @@ #include <linux/configfs.h> #include <linux/etherdevice.h> #include <linux/utsname.h> +#include <linux/rtnetlink.h> -MODULE_AUTHOR("Maintainer: Matt Mackall <mpm@selenic.com>"); +MODULE_AUTHOR("Matt Mackall <mpm@selenic.com>"); MODULE_DESCRIPTION("Console driver for network interfaces"); MODULE_LICENSE("GPL"); @@ -72,9 +73,16 @@ __setup("netconsole=", option_setup); /* Linked list of all configured targets */ static LIST_HEAD(target_list); +/* target_cleanup_list is used to track targets that need to be cleaned outside + * of target_list_lock. It should be cleaned in the same function it is + * populated. + */ +static LIST_HEAD(target_cleanup_list); /* This needs to be a spinlock because write_msg() cannot sleep */ static DEFINE_SPINLOCK(target_list_lock); +/* This needs to be a mutex because netpoll_cleanup might sleep */ +static DEFINE_MUTEX(target_cleanup_list_lock); /* * Console driver for extended netconsoles. Registered on the first use to @@ -210,6 +218,33 @@ static struct netconsole_target *alloc_and_init(void) return nt; } +/* Clean up every target in the cleanup_list and move the clean targets back to + * the main target_list. + */ +static void netconsole_process_cleanups_core(void) +{ + struct netconsole_target *nt, *tmp; + unsigned long flags; + + /* The cleanup needs RTNL locked */ + ASSERT_RTNL(); + + mutex_lock(&target_cleanup_list_lock); + list_for_each_entry_safe(nt, tmp, &target_cleanup_list, list) { + /* all entries in the cleanup_list needs to be disabled */ + WARN_ON_ONCE(nt->enabled); + do_netpoll_cleanup(&nt->np); + /* moved the cleaned target to target_list. Need to hold both + * locks + */ + spin_lock_irqsave(&target_list_lock, flags); + list_move(&nt->list, &target_list); + spin_unlock_irqrestore(&target_list_lock, flags); + } + WARN_ON_ONCE(!list_empty(&target_cleanup_list)); + mutex_unlock(&target_cleanup_list_lock); +} + #ifdef CONFIG_NETCONSOLE_DYNAMIC /* @@ -246,6 +281,19 @@ static struct netconsole_target *to_target(struct config_item *item) struct netconsole_target, group); } +/* Do the list cleanup with the rtnl lock hold. rtnl lock is necessary because + * netdev might be cleaned-up by calling __netpoll_cleanup(), + */ +static void netconsole_process_cleanups(void) +{ + /* rtnl lock is called here, because it has precedence over + * target_cleanup_list_lock mutex and target_cleanup_list + */ + rtnl_lock(); + netconsole_process_cleanups_core(); + rtnl_unlock(); +} + /* Get rid of possible trailing newline, returning the new length */ static void trim_newline(char *s, size_t maxlen) { @@ -336,14 +384,14 @@ static ssize_t enabled_store(struct config_item *item, struct netconsole_target *nt = to_target(item); unsigned long flags; bool enabled; - int err; + ssize_t ret; mutex_lock(&dynamic_netconsole_mutex); - err = kstrtobool(buf, &enabled); - if (err) + ret = kstrtobool(buf, &enabled); + if (ret) goto out_unlock; - err = -EINVAL; + ret = -EINVAL; if (enabled == nt->enabled) { pr_info("network logging has already %s\n", nt->enabled ? "started" : "stopped"); @@ -365,8 +413,8 @@ static ssize_t enabled_store(struct config_item *item, */ netpoll_print_options(&nt->np); - err = netpoll_setup(&nt->np); - if (err) + ret = netpoll_setup(&nt->np); + if (ret) goto out_unlock; nt->enabled = true; @@ -376,17 +424,23 @@ static ssize_t enabled_store(struct config_item *item, * otherwise we might end up in write_msg() with * nt->np.dev == NULL and nt->enabled == true */ + mutex_lock(&target_cleanup_list_lock); spin_lock_irqsave(&target_list_lock, flags); nt->enabled = false; + /* Remove the target from the list, while holding + * target_list_lock + */ + list_move(&nt->list, &target_cleanup_list); spin_unlock_irqrestore(&target_list_lock, flags); - netpoll_cleanup(&nt->np); + mutex_unlock(&target_cleanup_list_lock); } - mutex_unlock(&dynamic_netconsole_mutex); - return strnlen(buf, count); + ret = strnlen(buf, count); + /* Deferred cleanup */ + netconsole_process_cleanups(); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); - return err; + return ret; } static ssize_t release_store(struct config_item *item, const char *buf, @@ -394,27 +448,26 @@ static ssize_t release_store(struct config_item *item, const char *buf, { struct netconsole_target *nt = to_target(item); bool release; - int err; + ssize_t ret; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { pr_err("target (%s) is enabled, disable to update parameters\n", config_item_name(&nt->group.cg_item)); - err = -EINVAL; + ret = -EINVAL; goto out_unlock; } - err = kstrtobool(buf, &release); - if (err) + ret = kstrtobool(buf, &release); + if (ret) goto out_unlock; nt->release = release; - mutex_unlock(&dynamic_netconsole_mutex); - return strnlen(buf, count); + ret = strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); - return err; + return ret; } static ssize_t extended_store(struct config_item *item, const char *buf, @@ -422,27 +475,25 @@ static ssize_t extended_store(struct config_item *item, const char *buf, { struct netconsole_target *nt = to_target(item); bool extended; - int err; + ssize_t ret; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { pr_err("target (%s) is enabled, disable to update parameters\n", config_item_name(&nt->group.cg_item)); - err = -EINVAL; + ret = -EINVAL; goto out_unlock; } - err = kstrtobool(buf, &extended); - if (err) + ret = kstrtobool(buf, &extended); + if (ret) goto out_unlock; nt->extended = extended; - - mutex_unlock(&dynamic_netconsole_mutex); - return strnlen(buf, count); + ret = strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); - return err; + return ret; } static ssize_t dev_name_store(struct config_item *item, const char *buf, @@ -469,7 +520,7 @@ static ssize_t local_port_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); - int rv = -EINVAL; + ssize_t ret = -EINVAL; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { @@ -478,21 +529,20 @@ static ssize_t local_port_store(struct config_item *item, const char *buf, goto out_unlock; } - rv = kstrtou16(buf, 10, &nt->np.local_port); - if (rv < 0) + ret = kstrtou16(buf, 10, &nt->np.local_port); + if (ret < 0) goto out_unlock; - mutex_unlock(&dynamic_netconsole_mutex); - return strnlen(buf, count); + ret = strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); - return rv; + return ret; } static ssize_t remote_port_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); - int rv = -EINVAL; + ssize_t ret = -EINVAL; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { @@ -501,20 +551,20 @@ static ssize_t remote_port_store(struct config_item *item, goto out_unlock; } - rv = kstrtou16(buf, 10, &nt->np.remote_port); - if (rv < 0) + ret = kstrtou16(buf, 10, &nt->np.remote_port); + if (ret < 0) goto out_unlock; - mutex_unlock(&dynamic_netconsole_mutex); - return strnlen(buf, count); + ret = strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); - return rv; + return ret; } static ssize_t local_ip_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); + ssize_t ret = -EINVAL; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { @@ -541,17 +591,17 @@ static ssize_t local_ip_store(struct config_item *item, const char *buf, goto out_unlock; } - mutex_unlock(&dynamic_netconsole_mutex); - return strnlen(buf, count); + ret = strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); - return -EINVAL; + return ret; } static ssize_t remote_ip_store(struct config_item *item, const char *buf, size_t count) { struct netconsole_target *nt = to_target(item); + ssize_t ret = -EINVAL; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { @@ -578,11 +628,10 @@ static ssize_t remote_ip_store(struct config_item *item, const char *buf, goto out_unlock; } - mutex_unlock(&dynamic_netconsole_mutex); - return strnlen(buf, count); + ret = strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); - return -EINVAL; + return ret; } static ssize_t remote_mac_store(struct config_item *item, const char *buf, @@ -590,6 +639,7 @@ static ssize_t remote_mac_store(struct config_item *item, const char *buf, { struct netconsole_target *nt = to_target(item); u8 remote_mac[ETH_ALEN]; + ssize_t ret = -EINVAL; mutex_lock(&dynamic_netconsole_mutex); if (nt->enabled) { @@ -604,11 +654,10 @@ static ssize_t remote_mac_store(struct config_item *item, const char *buf, goto out_unlock; memcpy(nt->np.remote_mac, remote_mac, ETH_ALEN); - mutex_unlock(&dynamic_netconsole_mutex); - return strnlen(buf, count); + ret = strnlen(buf, count); out_unlock: mutex_unlock(&dynamic_netconsole_mutex); - return -EINVAL; + return ret; } struct userdatum { @@ -685,7 +734,7 @@ static ssize_t userdatum_value_store(struct config_item *item, const char *buf, struct userdatum *udm = to_userdatum(item); struct netconsole_target *nt; struct userdata *ud; - int ret; + ssize_t ret; if (count > MAX_USERDATA_VALUE_LENGTH) return -EMSGSIZE; @@ -700,9 +749,7 @@ static ssize_t userdatum_value_store(struct config_item *item, const char *buf, ud = to_userdata(item->ci_parent); nt = userdata_to_target(ud); update_userdata(nt); - - mutex_unlock(&dynamic_netconsole_mutex); - return count; + ret = count; out_unlock: mutex_unlock(&dynamic_netconsole_mutex); return ret; @@ -778,7 +825,7 @@ static struct configfs_group_operations userdata_ops = { .drop_item = userdatum_drop, }; -static struct config_item_type userdata_type = { +static const struct config_item_type userdata_type = { .ct_item_ops = &userdatum_ops, .ct_group_ops = &userdata_ops, .ct_attrs = userdata_attrs, @@ -950,7 +997,7 @@ static int netconsole_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { unsigned long flags; - struct netconsole_target *nt; + struct netconsole_target *nt, *tmp; struct net_device *dev = netdev_notifier_info_to_dev(ptr); bool stopped = false; @@ -958,9 +1005,9 @@ static int netconsole_netdev_event(struct notifier_block *this, event == NETDEV_RELEASE || event == NETDEV_JOIN)) goto done; + mutex_lock(&target_cleanup_list_lock); spin_lock_irqsave(&target_list_lock, flags); -restart: - list_for_each_entry(nt, &target_list, list) { + list_for_each_entry_safe(nt, tmp, &target_list, list) { netconsole_target_get(nt); if (nt->np.dev == dev) { switch (event) { @@ -970,25 +1017,16 @@ restart: case NETDEV_RELEASE: case NETDEV_JOIN: case NETDEV_UNREGISTER: - /* rtnl_lock already held - * we might sleep in __netpoll_cleanup() - */ nt->enabled = false; - spin_unlock_irqrestore(&target_list_lock, flags); - - __netpoll_cleanup(&nt->np); - - spin_lock_irqsave(&target_list_lock, flags); - netdev_put(nt->np.dev, &nt->np.dev_tracker); - nt->np.dev = NULL; + list_move(&nt->list, &target_cleanup_list); stopped = true; - netconsole_target_put(nt); - goto restart; } } netconsole_target_put(nt); } spin_unlock_irqrestore(&target_list_lock, flags); + mutex_unlock(&target_cleanup_list_lock); + if (stopped) { const char *msg = "had an event"; @@ -1007,6 +1045,11 @@ restart: dev->name, msg); } + /* Process target_cleanup_list entries. By the end, target_cleanup_list + * should be empty + */ + netconsole_process_cleanups_core(); + done: return NOTIFY_DONE; } @@ -1215,11 +1258,18 @@ static struct netconsole_target *alloc_param_target(char *target_config, goto fail; err = netpoll_setup(&nt->np); - if (err) - goto fail; - + if (err) { + pr_err("Not enabling netconsole for %s%d. Netpoll setup failed\n", + NETCONSOLE_PARAM_TARGET_PREFIX, cmdline_count); + if (!IS_ENABLED(CONFIG_NETCONSOLE_DYNAMIC)) + /* only fail if dynamic reconfiguration is set, + * otherwise, keep the target in the list, but disabled. + */ + goto fail; + } else { + nt->enabled = true; + } populate_configfs_item(nt, cmdline_count); - nt->enabled = true; return nt; diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index 7fddc8306d82..f530fcd092fe 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -44,6 +44,9 @@ config LED_TRIGGER_PHY <Speed in megabits>Mbps OR <Speed in gigabits>Gbps OR link for any speed known to the PHY. +config OPEN_ALLIANCE_HELPERS + bool + config PHYLIB_LEDS def_bool OF depends on LEDS_CLASS=y || LEDS_CLASS=PHYLIB @@ -414,6 +417,7 @@ config DP83TD510_PHY config DP83TG720_PHY tristate "Texas Instruments DP83TG720 Ethernet 1000Base-T1 PHY" + select OPEN_ALLIANCE_HELPERS help The DP83TG720S-Q1 is an automotive Ethernet physical layer transceiver compliant with IEEE 802.3bp and Open Alliance diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile index 202ed7f450da..33adb3df5f64 100644 --- a/drivers/net/phy/Makefile +++ b/drivers/net/phy/Makefile @@ -2,7 +2,7 @@ # Makefile for Linux PHY drivers libphy-y := phy.o phy-c45.o phy-core.o phy_device.o \ - linkmode.o + linkmode.o phy_link_topology.o mdio-bus-y += mdio_bus.o mdio_device.o ifdef CONFIG_MDIO_DEVICE @@ -22,6 +22,7 @@ endif obj-$(CONFIG_MDIO_DEVRES) += mdio_devres.o libphy-$(CONFIG_SWPHY) += swphy.o libphy-$(CONFIG_LED_TRIGGER_PHY) += phy_led_triggers.o +libphy-$(CONFIG_OPEN_ALLIANCE_HELPERS) += open_alliance_helpers.o obj-$(CONFIG_PHYLINK) += phylink.o obj-$(CONFIG_PHYLIB) += libphy.o diff --git a/drivers/net/phy/dp83td510.c b/drivers/net/phy/dp83td510.c index 551e37786c2d..92aa3a2b9744 100644 --- a/drivers/net/phy/dp83td510.c +++ b/drivers/net/phy/dp83td510.c @@ -58,6 +58,10 @@ static const u16 dp83td510_mse_sqi_map[] = { 0x0000 /* 24dB =< SNR */ }; +struct dp83td510_priv { + bool alcd_test_active; +}; + /* Time Domain Reflectometry (TDR) Functionality of DP83TD510 PHY * * I assume that this PHY is using a variation of Spread Spectrum Time Domain @@ -169,6 +173,10 @@ static const u16 dp83td510_mse_sqi_map[] = { #define DP83TD510E_UNKN_030E 0x30e #define DP83TD510E_030E_VAL 0x2520 +#define DP83TD510E_ALCD_STAT 0xa9f +#define DP83TD510E_ALCD_COMPLETE BIT(15) +#define DP83TD510E_ALCD_CABLE_LENGTH GENMASK(10, 0) + static int dp83td510_config_intr(struct phy_device *phydev) { int ret; @@ -325,8 +333,23 @@ static int dp83td510_get_sqi_max(struct phy_device *phydev) */ static int dp83td510_cable_test_start(struct phy_device *phydev) { + struct dp83td510_priv *priv = phydev->priv; int ret; + /* If link partner is active, we won't be able to use TDR, since + * we can't force link partner to be silent. The autonegotiation + * pulses will be too frequent and the TDR sequence will be + * too long. So, TDR will always fail. Since the link is established + * we already know that the cable is working, so we can get some + * extra information line the cable length using ALCD. + */ + if (phydev->link) { + priv->alcd_test_active = true; + return 0; + } + + priv->alcd_test_active = false; + ret = phy_set_bits_mmd(phydev, MDIO_MMD_VEND2, DP83TD510E_CTRL, DP83TD510E_CTRL_HW_RESET); if (ret) @@ -402,8 +425,8 @@ static int dp83td510_cable_test_start(struct phy_device *phydev) } /** - * dp83td510_cable_test_get_status - Get the status of the cable test for the - * DP83TD510 PHY. + * dp83td510_cable_test_get_tdr_status - Get the status of the TDR test for the + * DP83TD510 PHY. * @phydev: Pointer to the phy_device structure. * @finished: Pointer to a boolean that indicates whether the test is finished. * @@ -411,13 +434,11 @@ static int dp83td510_cable_test_start(struct phy_device *phydev) * * Returns: 0 on success or a negative error code on failure. */ -static int dp83td510_cable_test_get_status(struct phy_device *phydev, - bool *finished) +static int dp83td510_cable_test_get_tdr_status(struct phy_device *phydev, + bool *finished) { int ret, stat; - *finished = false; - ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, DP83TD510E_TDR_CFG); if (ret < 0) return ret; @@ -459,6 +480,77 @@ static int dp83td510_cable_test_get_status(struct phy_device *phydev, return phy_init_hw(phydev); } +/** + * dp83td510_cable_test_get_alcd_status - Get the status of the ALCD test for the + * DP83TD510 PHY. + * @phydev: Pointer to the phy_device structure. + * @finished: Pointer to a boolean that indicates whether the test is finished. + * + * The function sets the @finished flag to true if the test is complete. + * The function reads the cable length and reports it to the user. + * + * Returns: 0 on success or a negative error code on failure. + */ +static int dp83td510_cable_test_get_alcd_status(struct phy_device *phydev, + bool *finished) +{ + unsigned int location; + int ret, phy_sts; + + phy_sts = phy_read(phydev, DP83TD510E_PHY_STS); + + if (!(phy_sts & DP83TD510E_LINK_STATUS)) { + /* If the link is down, we can't do any thing usable now */ + ethnl_cable_test_result_with_src(phydev, ETHTOOL_A_CABLE_PAIR_A, + ETHTOOL_A_CABLE_RESULT_CODE_UNSPEC, + ETHTOOL_A_CABLE_INF_SRC_ALCD); + *finished = true; + return 0; + } + + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, DP83TD510E_ALCD_STAT); + if (ret < 0) + return ret; + + if (!(ret & DP83TD510E_ALCD_COMPLETE)) + return 0; + + location = FIELD_GET(DP83TD510E_ALCD_CABLE_LENGTH, ret) * 100; + + ethnl_cable_test_fault_length_with_src(phydev, ETHTOOL_A_CABLE_PAIR_A, + location, + ETHTOOL_A_CABLE_INF_SRC_ALCD); + + ethnl_cable_test_result_with_src(phydev, ETHTOOL_A_CABLE_PAIR_A, + ETHTOOL_A_CABLE_RESULT_CODE_OK, + ETHTOOL_A_CABLE_INF_SRC_ALCD); + *finished = true; + + return 0; +} + +/** + * dp83td510_cable_test_get_status - Get the status of the cable test for the + * DP83TD510 PHY. + * @phydev: Pointer to the phy_device structure. + * @finished: Pointer to a boolean that indicates whether the test is finished. + * + * The function sets the @finished flag to true if the test is complete. + * + * Returns: 0 on success or a negative error code on failure. + */ +static int dp83td510_cable_test_get_status(struct phy_device *phydev, + bool *finished) +{ + struct dp83td510_priv *priv = phydev->priv; + *finished = false; + + if (priv->alcd_test_active) + return dp83td510_cable_test_get_alcd_status(phydev, finished); + + return dp83td510_cable_test_get_tdr_status(phydev, finished); +} + static int dp83td510_get_features(struct phy_device *phydev) { /* This PHY can't respond on MDIO bus if no RMII clock is enabled. @@ -477,12 +569,27 @@ static int dp83td510_get_features(struct phy_device *phydev) return 0; } +static int dp83td510_probe(struct phy_device *phydev) +{ + struct device *dev = &phydev->mdio.dev; + struct dp83td510_priv *priv; + + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + phydev->priv = priv; + + return 0; +} + static struct phy_driver dp83td510_driver[] = { { PHY_ID_MATCH_MODEL(DP83TD510E_PHY_ID), .name = "TI DP83TD510E", .flags = PHY_POLL_CABLE_TEST, + .probe = dp83td510_probe, .config_aneg = dp83td510_config_aneg, .read_status = dp83td510_read_status, .get_features = dp83td510_get_features, diff --git a/drivers/net/phy/dp83tg720.c b/drivers/net/phy/dp83tg720.c index c706429b225a..0ef4d7dba065 100644 --- a/drivers/net/phy/dp83tg720.c +++ b/drivers/net/phy/dp83tg720.c @@ -3,10 +3,13 @@ * Copyright (c) 2023 Pengutronix, Oleksij Rempel <kernel@pengutronix.de> */ #include <linux/bitfield.h> +#include <linux/ethtool_netlink.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/phy.h> +#include "open_alliance_helpers.h" + #define DP83TG720S_PHY_ID 0x2000a284 /* MDIO_MMD_VEND2 registers */ @@ -14,6 +17,17 @@ #define DP83TG720S_STS_MII_INT BIT(7) #define DP83TG720S_LINK_STATUS BIT(0) +/* TDR Configuration Register (0x1E) */ +#define DP83TG720S_TDR_CFG 0x1e +/* 1b = TDR start, 0b = No TDR */ +#define DP83TG720S_TDR_START BIT(15) +/* 1b = TDR auto on link down, 0b = Manual TDR start */ +#define DP83TG720S_CFG_TDR_AUTO_RUN BIT(14) +/* 1b = TDR done, 0b = TDR in progress */ +#define DP83TG720S_TDR_DONE BIT(1) +/* 1b = TDR fail, 0b = TDR success */ +#define DP83TG720S_TDR_FAIL BIT(0) + #define DP83TG720S_PHY_RESET 0x1f #define DP83TG720S_HW_RESET BIT(15) @@ -22,18 +36,155 @@ /* Power Mode 0 is Normal mode */ #define DP83TG720S_LPS_CFG3_PWR_MODE_0 BIT(0) +/* Open Aliance 1000BaseT1 compatible HDD.TDR Fault Status Register */ +#define DP83TG720S_TDR_FAULT_STATUS 0x30f + +/* Register 0x0301: TDR Configuration 2 */ +#define DP83TG720S_TDR_CFG2 0x301 + +/* Register 0x0303: TDR Configuration 3 */ +#define DP83TG720S_TDR_CFG3 0x303 + +/* Register 0x0304: TDR Configuration 4 */ +#define DP83TG720S_TDR_CFG4 0x304 + +/* Register 0x0405: Unknown Register */ +#define DP83TG720S_UNKNOWN_0405 0x405 + +/* Register 0x0576: TDR Master Link Down Control */ +#define DP83TG720S_TDR_MASTER_LINK_DOWN 0x576 + #define DP83TG720S_RGMII_DELAY_CTRL 0x602 /* In RGMII mode, Enable or disable the internal delay for RXD */ #define DP83TG720S_RGMII_RX_CLK_SEL BIT(1) /* In RGMII mode, Enable or disable the internal delay for TXD */ #define DP83TG720S_RGMII_TX_CLK_SEL BIT(0) +/* Register 0x083F: Unknown Register */ +#define DP83TG720S_UNKNOWN_083F 0x83f + #define DP83TG720S_SQI_REG_1 0x871 #define DP83TG720S_SQI_OUT_WORST GENMASK(7, 5) #define DP83TG720S_SQI_OUT GENMASK(3, 1) #define DP83TG720_SQI_MAX 7 +/** + * dp83tg720_cable_test_start - Start the cable test for the DP83TG720 PHY. + * @phydev: Pointer to the phy_device structure. + * + * This sequence is based on the documented procedure for the DP83TG720 PHY. + * + * Returns: 0 on success, a negative error code on failure. + */ +static int dp83tg720_cable_test_start(struct phy_device *phydev) +{ + int ret; + + /* Initialize the PHY to run the TDR test as described in the + * "DP83TG720S-Q1: Configuring for Open Alliance Specification + * Compliance (Rev. B)" application note. + * Most of the registers are not documented. Some of register names + * are guessed by comparing the register offsets with the DP83TD510E. + */ + + /* Force master link down */ + ret = phy_set_bits_mmd(phydev, MDIO_MMD_VEND2, + DP83TG720S_TDR_MASTER_LINK_DOWN, 0x0400); + if (ret) + return ret; + + ret = phy_write_mmd(phydev, MDIO_MMD_VEND2, DP83TG720S_TDR_CFG2, + 0xa008); + if (ret) + return ret; + + ret = phy_write_mmd(phydev, MDIO_MMD_VEND2, DP83TG720S_TDR_CFG3, + 0x0928); + if (ret) + return ret; + + ret = phy_write_mmd(phydev, MDIO_MMD_VEND2, DP83TG720S_TDR_CFG4, + 0x0004); + if (ret) + return ret; + + ret = phy_write_mmd(phydev, MDIO_MMD_VEND2, DP83TG720S_UNKNOWN_0405, + 0x6400); + if (ret) + return ret; + + ret = phy_write_mmd(phydev, MDIO_MMD_VEND2, DP83TG720S_UNKNOWN_083F, + 0x3003); + if (ret) + return ret; + + /* Start the TDR */ + ret = phy_set_bits_mmd(phydev, MDIO_MMD_VEND2, DP83TG720S_TDR_CFG, + DP83TG720S_TDR_START); + if (ret) + return ret; + + return 0; +} + +/** + * dp83tg720_cable_test_get_status - Get the status of the cable test for the + * DP83TG720 PHY. + * @phydev: Pointer to the phy_device structure. + * @finished: Pointer to a boolean that indicates whether the test is finished. + * + * The function sets the @finished flag to true if the test is complete. + * + * Returns: 0 on success or a negative error code on failure. + */ +static int dp83tg720_cable_test_get_status(struct phy_device *phydev, + bool *finished) +{ + int ret, stat; + + *finished = false; + + /* Read the TDR status */ + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, DP83TG720S_TDR_CFG); + if (ret < 0) + return ret; + + /* Check if the TDR test is done */ + if (!(ret & DP83TG720S_TDR_DONE)) + return 0; + + /* Check for TDR test failure */ + if (!(ret & DP83TG720S_TDR_FAIL)) { + int location; + + /* Read fault status */ + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, + DP83TG720S_TDR_FAULT_STATUS); + if (ret < 0) + return ret; + + /* Get fault type */ + stat = oa_1000bt1_get_ethtool_cable_result_code(ret); + + /* Determine fault location */ + location = oa_1000bt1_get_tdr_distance(ret); + if (location > 0) + ethnl_cable_test_fault_length(phydev, + ETHTOOL_A_CABLE_PAIR_A, + location); + } else { + /* Active link partner or other issues */ + stat = ETHTOOL_A_CABLE_RESULT_CODE_UNSPEC; + } + + *finished = true; + + ethnl_cable_test_result(phydev, ETHTOOL_A_CABLE_PAIR_A, stat); + + return phy_init_hw(phydev); +} + static int dp83tg720_config_aneg(struct phy_device *phydev) { int ret; @@ -195,12 +346,15 @@ static struct phy_driver dp83tg720_driver[] = { PHY_ID_MATCH_MODEL(DP83TG720S_PHY_ID), .name = "TI DP83TG720S", + .flags = PHY_POLL_CABLE_TEST, .config_aneg = dp83tg720_config_aneg, .read_status = dp83tg720_read_status, .get_features = genphy_c45_pma_read_ext_abilities, .config_init = dp83tg720_config_init, .get_sqi = dp83tg720_get_sqi, .get_sqi_max = dp83tg720_get_sqi_max, + .cable_test_start = dp83tg720_cable_test_start, + .cable_test_get_status = dp83tg720_cable_test_get_status, .suspend = genphy_suspend, .resume = genphy_resume, diff --git a/drivers/net/phy/marvell-88x2222.c b/drivers/net/phy/marvell-88x2222.c index b88398e6872b..0b777cdd7078 100644 --- a/drivers/net/phy/marvell-88x2222.c +++ b/drivers/net/phy/marvell-88x2222.c @@ -553,6 +553,8 @@ static const struct sfp_upstream_ops sfp_phy_ops = { .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 int mv2222_probe(struct phy_device *phydev) diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index b89fbffa6a93..9964bf3dea2f 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -3613,6 +3613,8 @@ static const struct sfp_upstream_ops m88e1510_sfp_ops = { .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 int m88e1510_probe(struct phy_device *phydev) diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c index ad43e280930c..6642eb642d4b 100644 --- a/drivers/net/phy/marvell10g.c +++ b/drivers/net/phy/marvell10g.c @@ -503,6 +503,8 @@ static int mv3310_sfp_insert(void *upstream, const struct sfp_eeprom_id *id) 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, }; diff --git a/drivers/net/phy/microchip_t1.c b/drivers/net/phy/microchip_t1.c index a35528497a57..5732ad65e7f9 100644 --- a/drivers/net/phy/microchip_t1.c +++ b/drivers/net/phy/microchip_t1.c @@ -12,6 +12,7 @@ #define PHY_ID_LAN87XX 0x0007c150 #define PHY_ID_LAN937X 0x0007c180 +#define PHY_ID_LAN887X 0x0007c1f0 /* External Register Control Register */ #define LAN87XX_EXT_REG_CTL (0x14) @@ -94,8 +95,101 @@ /* SQI defines */ #define LAN87XX_MAX_SQI 0x07 +/* Chiptop registers */ +#define LAN887X_PMA_EXT_ABILITY_2 0x12 +#define LAN887X_PMA_EXT_ABILITY_2_1000T1 BIT(1) +#define LAN887X_PMA_EXT_ABILITY_2_100T1 BIT(0) + +/* DSP 100M registers */ +#define LAN887x_CDR_CONFIG1_100 0x0405 +#define LAN887x_LOCK1_EQLSR_CONFIG_100 0x0411 +#define LAN887x_SLV_HD_MUFAC_CONFIG_100 0x0417 +#define LAN887x_PLOCK_MUFAC_CONFIG_100 0x041c +#define LAN887x_PROT_DISABLE_100 0x0425 +#define LAN887x_KF_LOOP_SAT_CONFIG_100 0x0454 + +/* DSP 1000M registers */ +#define LAN887X_LOCK1_EQLSR_CONFIG 0x0811 +#define LAN887X_LOCK3_EQLSR_CONFIG 0x0813 +#define LAN887X_PROT_DISABLE 0x0825 +#define LAN887X_FFE_GAIN6 0x0843 +#define LAN887X_FFE_GAIN7 0x0844 +#define LAN887X_FFE_GAIN8 0x0845 +#define LAN887X_FFE_GAIN9 0x0846 +#define LAN887X_ECHO_DELAY_CONFIG 0x08ec +#define LAN887X_FFE_MAX_CONFIG 0x08ee + +/* PCS 1000M registers */ +#define LAN887X_SCR_CONFIG_3 0x8043 +#define LAN887X_INFO_FLD_CONFIG_5 0x8048 + +/* T1 afe registers */ +#define LAN887X_ZQCAL_CONTROL_1 0x8080 +#define LAN887X_AFE_PORT_TESTBUS_CTRL2 0x8089 +#define LAN887X_AFE_PORT_TESTBUS_CTRL4 0x808b +#define LAN887X_AFE_PORT_TESTBUS_CTRL6 0x808d +#define LAN887X_TX_AMPLT_1000T1_REG 0x80b0 +#define LAN887X_INIT_COEFF_DFE1_100 0x0422 + +/* PMA registers */ +#define LAN887X_DSP_PMA_CONTROL 0x810e +#define LAN887X_DSP_PMA_CONTROL_LNK_SYNC BIT(4) + +/* PCS 100M registers */ +#define LAN887X_IDLE_ERR_TIMER_WIN 0x8204 +#define LAN887X_IDLE_ERR_CNT_THRESH 0x8213 + +/* Misc registers */ +#define LAN887X_REG_REG26 0x001a +#define LAN887X_REG_REG26_HW_INIT_SEQ_EN BIT(8) + +/* Mis registers */ +#define LAN887X_MIS_CFG_REG0 0xa00 +#define LAN887X_MIS_CFG_REG0_RCLKOUT_DIS BIT(5) +#define LAN887X_MIS_CFG_REG0_MAC_MODE_SEL GENMASK(1, 0) + +#define LAN887X_MAC_MODE_RGMII 0x01 +#define LAN887X_MAC_MODE_SGMII 0x03 + +#define LAN887X_MIS_DLL_CFG_REG0 0xa01 +#define LAN887X_MIS_DLL_CFG_REG1 0xa02 + +#define LAN887X_MIS_DLL_DELAY_EN BIT(15) +#define LAN887X_MIS_DLL_EN BIT(0) +#define LAN887X_MIS_DLL_CONF (LAN887X_MIS_DLL_DELAY_EN |\ + LAN887X_MIS_DLL_EN) + +#define LAN887X_MIS_CFG_REG2 0xa03 +#define LAN887X_MIS_CFG_REG2_FE_LPBK_EN BIT(2) + +#define LAN887X_MIS_PKT_STAT_REG0 0xa06 +#define LAN887X_MIS_PKT_STAT_REG1 0xa07 +#define LAN887X_MIS_PKT_STAT_REG3 0xa09 +#define LAN887X_MIS_PKT_STAT_REG4 0xa0a +#define LAN887X_MIS_PKT_STAT_REG5 0xa0b +#define LAN887X_MIS_PKT_STAT_REG6 0xa0c + +/* Chiptop common registers */ +#define LAN887X_COMMON_LED3_LED2 0xc05 +#define LAN887X_COMMON_LED2_MODE_SEL_MASK GENMASK(4, 0) +#define LAN887X_LED_LINK_ACT_ANY_SPEED 0x0 + +/* MX chip top registers */ +#define LAN887X_CHIP_SOFT_RST 0xf03f +#define LAN887X_CHIP_SOFT_RST_RESET BIT(0) + +#define LAN887X_SGMII_CTL 0xf01a +#define LAN887X_SGMII_CTL_SGMII_MUX_EN BIT(0) + +#define LAN887X_SGMII_PCS_CFG 0xf034 +#define LAN887X_SGMII_PCS_CFG_PCS_ENA BIT(9) + +#define LAN887X_EFUSE_READ_DAT9 0xf209 +#define LAN887X_EFUSE_READ_DAT9_SGMII_DIS BIT(9) +#define LAN887X_EFUSE_READ_DAT9_MAC_MODE GENMASK(1, 0) + #define DRIVER_AUTHOR "Nisar Sayed <nisar.sayed@microchip.com>" -#define DRIVER_DESC "Microchip LAN87XX/LAN937x T1 PHY driver" +#define DRIVER_DESC "Microchip LAN87XX/LAN937x/LAN887x T1 PHY driver" struct access_ereg_val { u8 mode; @@ -105,6 +199,32 @@ struct access_ereg_val { u16 mask; }; +struct lan887x_hw_stat { + const char *string; + u8 mmd; + u16 reg; + u8 bits; +}; + +static const struct lan887x_hw_stat lan887x_hw_stats[] = { + { "TX Good Count", MDIO_MMD_VEND1, LAN887X_MIS_PKT_STAT_REG0, 14}, + { "RX Good Count", MDIO_MMD_VEND1, LAN887X_MIS_PKT_STAT_REG1, 14}, + { "RX ERR Count detected by PCS", MDIO_MMD_VEND1, LAN887X_MIS_PKT_STAT_REG3, 16}, + { "TX CRC ERR Count", MDIO_MMD_VEND1, LAN887X_MIS_PKT_STAT_REG4, 8}, + { "RX CRC ERR Count", MDIO_MMD_VEND1, LAN887X_MIS_PKT_STAT_REG5, 8}, + { "RX ERR Count for SGMII MII2GMII", MDIO_MMD_VEND1, LAN887X_MIS_PKT_STAT_REG6, 8}, +}; + +struct lan887x_regwr_map { + u8 mmd; + u16 reg; + u16 val; +}; + +struct lan887x_priv { + u64 stats[ARRAY_SIZE(lan887x_hw_stats)]; +}; + static int lan937x_dsp_workaround(struct phy_device *phydev, u16 ereg, u8 bank) { u8 prev_bank; @@ -860,6 +980,446 @@ static int lan87xx_get_sqi_max(struct phy_device *phydev) return LAN87XX_MAX_SQI; } +static int lan887x_rgmii_init(struct phy_device *phydev) +{ + int ret; + + /* SGMII mux disable */ + ret = phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, + LAN887X_SGMII_CTL, + LAN887X_SGMII_CTL_SGMII_MUX_EN); + if (ret < 0) + return ret; + + /* Select MAC_MODE as RGMII */ + ret = phy_modify_mmd(phydev, MDIO_MMD_VEND1, LAN887X_MIS_CFG_REG0, + LAN887X_MIS_CFG_REG0_MAC_MODE_SEL, + LAN887X_MAC_MODE_RGMII); + if (ret < 0) + return ret; + + /* Disable PCS */ + ret = phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, + LAN887X_SGMII_PCS_CFG, + LAN887X_SGMII_PCS_CFG_PCS_ENA); + if (ret < 0) + return ret; + + /* LAN887x Errata: RGMII rx clock active in SGMII mode + * Disabled it for SGMII mode + * Re-enabling it for RGMII mode + */ + return phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, + LAN887X_MIS_CFG_REG0, + LAN887X_MIS_CFG_REG0_RCLKOUT_DIS); +} + +static int lan887x_sgmii_init(struct phy_device *phydev) +{ + int ret; + + /* SGMII mux enable */ + ret = phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, + LAN887X_SGMII_CTL, + LAN887X_SGMII_CTL_SGMII_MUX_EN); + if (ret < 0) + return ret; + + /* Select MAC_MODE as SGMII */ + ret = phy_modify_mmd(phydev, MDIO_MMD_VEND1, LAN887X_MIS_CFG_REG0, + LAN887X_MIS_CFG_REG0_MAC_MODE_SEL, + LAN887X_MAC_MODE_SGMII); + if (ret < 0) + return ret; + + /* LAN887x Errata: RGMII rx clock active in SGMII mode. + * So disabling it for SGMII mode + */ + ret = phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, LAN887X_MIS_CFG_REG0, + LAN887X_MIS_CFG_REG0_RCLKOUT_DIS); + if (ret < 0) + return ret; + + /* Enable PCS */ + return phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, LAN887X_SGMII_PCS_CFG, + LAN887X_SGMII_PCS_CFG_PCS_ENA); +} + +static int lan887x_config_rgmii_en(struct phy_device *phydev) +{ + int txc; + int rxc; + int ret; + + ret = lan887x_rgmii_init(phydev); + if (ret < 0) + return ret; + + /* Control bit to enable/disable TX DLL delay line in signal path */ + txc = phy_read_mmd(phydev, MDIO_MMD_VEND1, LAN887X_MIS_DLL_CFG_REG0); + if (txc < 0) + return txc; + + /* Control bit to enable/disable RX DLL delay line in signal path */ + rxc = phy_read_mmd(phydev, MDIO_MMD_VEND1, LAN887X_MIS_DLL_CFG_REG1); + if (rxc < 0) + return rxc; + + /* Configures the phy to enable RX/TX delay + * RGMII - TX & RX delays are either added by MAC or not needed, + * phy should not add + * RGMII_ID - Configures phy to enable TX & RX delays, MAC shouldn't add + * RGMII_RX_ID - Configures the PHY to enable the RX delay. + * The MAC shouldn't add the RX delay + * RGMII_TX_ID - Configures the PHY to enable the TX delay. + * The MAC shouldn't add the TX delay in this case + */ + switch (phydev->interface) { + case PHY_INTERFACE_MODE_RGMII: + txc &= ~LAN887X_MIS_DLL_CONF; + rxc &= ~LAN887X_MIS_DLL_CONF; + break; + case PHY_INTERFACE_MODE_RGMII_ID: + txc |= LAN887X_MIS_DLL_CONF; + rxc |= LAN887X_MIS_DLL_CONF; + break; + case PHY_INTERFACE_MODE_RGMII_RXID: + txc &= ~LAN887X_MIS_DLL_CONF; + rxc |= LAN887X_MIS_DLL_CONF; + break; + case PHY_INTERFACE_MODE_RGMII_TXID: + txc |= LAN887X_MIS_DLL_CONF; + rxc &= ~LAN887X_MIS_DLL_CONF; + break; + default: + WARN_ONCE(1, "Invalid phydev interface %d\n", phydev->interface); + return 0; + } + + /* Configures the PHY to enable/disable RX delay in signal path */ + ret = phy_modify_mmd(phydev, MDIO_MMD_VEND1, LAN887X_MIS_DLL_CFG_REG1, + LAN887X_MIS_DLL_CONF, rxc); + if (ret < 0) + return ret; + + /* Configures the PHY to enable/disable the TX delay in signal path */ + return phy_modify_mmd(phydev, MDIO_MMD_VEND1, LAN887X_MIS_DLL_CFG_REG0, + LAN887X_MIS_DLL_CONF, txc); +} + +static int lan887x_config_phy_interface(struct phy_device *phydev) +{ + int interface_mode; + int sgmii_dis; + int ret; + + /* Read sku efuse data for interfaces supported by sku */ + ret = phy_read_mmd(phydev, MDIO_MMD_VEND1, LAN887X_EFUSE_READ_DAT9); + if (ret < 0) + return ret; + + /* If interface_mode is 1 then efuse sets RGMII operations. + * If interface mode is 3 then efuse sets SGMII operations. + */ + interface_mode = ret & LAN887X_EFUSE_READ_DAT9_MAC_MODE; + /* SGMII disable is set for RGMII operations */ + sgmii_dis = ret & LAN887X_EFUSE_READ_DAT9_SGMII_DIS; + + switch (phydev->interface) { + case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_RXID: + case PHY_INTERFACE_MODE_RGMII_TXID: + /* Reject RGMII settings for SGMII only sku */ + ret = -EOPNOTSUPP; + + if (!((interface_mode & LAN887X_MAC_MODE_SGMII) == + LAN887X_MAC_MODE_SGMII)) + ret = lan887x_config_rgmii_en(phydev); + break; + case PHY_INTERFACE_MODE_SGMII: + /* Reject SGMII setting for RGMII only sku */ + ret = -EOPNOTSUPP; + + if (!sgmii_dis) + ret = lan887x_sgmii_init(phydev); + break; + default: + /* Reject setting for unsupported interfaces */ + ret = -EOPNOTSUPP; + } + + return ret; +} + +static int lan887x_get_features(struct phy_device *phydev) +{ + int ret; + + ret = genphy_c45_pma_read_abilities(phydev); + if (ret < 0) + return ret; + + /* Enable twisted pair */ + linkmode_set_bit(ETHTOOL_LINK_MODE_TP_BIT, phydev->supported); + + /* First patch only supports 100Mbps and 1000Mbps force-mode. + * T1 Auto-Negotiation (Clause 98 of IEEE 802.3) will be added later. + */ + linkmode_clear_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, phydev->supported); + + return 0; +} + +static int lan887x_phy_init(struct phy_device *phydev) +{ + int ret; + + /* Clear loopback */ + ret = phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, + LAN887X_MIS_CFG_REG2, + LAN887X_MIS_CFG_REG2_FE_LPBK_EN); + if (ret < 0) + return ret; + + /* Configure default behavior of led to link and activity for any + * speed + */ + ret = phy_modify_mmd(phydev, MDIO_MMD_VEND1, + LAN887X_COMMON_LED3_LED2, + LAN887X_COMMON_LED2_MODE_SEL_MASK, + LAN887X_LED_LINK_ACT_ANY_SPEED); + if (ret < 0) + return ret; + + /* PHY interface setup */ + return lan887x_config_phy_interface(phydev); +} + +static int lan887x_phy_config(struct phy_device *phydev, + const struct lan887x_regwr_map *reg_map, int cnt) +{ + int ret; + + for (int i = 0; i < cnt; i++) { + ret = phy_write_mmd(phydev, reg_map[i].mmd, + reg_map[i].reg, reg_map[i].val); + if (ret < 0) + return ret; + } + + return 0; +} + +static int lan887x_phy_setup(struct phy_device *phydev) +{ + static const struct lan887x_regwr_map phy_cfg[] = { + /* PORT_AFE writes */ + {MDIO_MMD_PMAPMD, LAN887X_ZQCAL_CONTROL_1, 0x4008}, + {MDIO_MMD_PMAPMD, LAN887X_AFE_PORT_TESTBUS_CTRL2, 0x0000}, + {MDIO_MMD_PMAPMD, LAN887X_AFE_PORT_TESTBUS_CTRL6, 0x0040}, + /* 100T1_PCS_VENDOR writes */ + {MDIO_MMD_PCS, LAN887X_IDLE_ERR_CNT_THRESH, 0x0008}, + {MDIO_MMD_PCS, LAN887X_IDLE_ERR_TIMER_WIN, 0x800d}, + /* 100T1 DSP writes */ + {MDIO_MMD_VEND1, LAN887x_CDR_CONFIG1_100, 0x0ab1}, + {MDIO_MMD_VEND1, LAN887x_LOCK1_EQLSR_CONFIG_100, 0x5274}, + {MDIO_MMD_VEND1, LAN887x_SLV_HD_MUFAC_CONFIG_100, 0x0d74}, + {MDIO_MMD_VEND1, LAN887x_PLOCK_MUFAC_CONFIG_100, 0x0aea}, + {MDIO_MMD_VEND1, LAN887x_PROT_DISABLE_100, 0x0360}, + {MDIO_MMD_VEND1, LAN887x_KF_LOOP_SAT_CONFIG_100, 0x0c30}, + /* 1000T1 DSP writes */ + {MDIO_MMD_VEND1, LAN887X_LOCK1_EQLSR_CONFIG, 0x2a78}, + {MDIO_MMD_VEND1, LAN887X_LOCK3_EQLSR_CONFIG, 0x1368}, + {MDIO_MMD_VEND1, LAN887X_PROT_DISABLE, 0x1354}, + {MDIO_MMD_VEND1, LAN887X_FFE_GAIN6, 0x3C84}, + {MDIO_MMD_VEND1, LAN887X_FFE_GAIN7, 0x3ca5}, + {MDIO_MMD_VEND1, LAN887X_FFE_GAIN8, 0x3ca5}, + {MDIO_MMD_VEND1, LAN887X_FFE_GAIN9, 0x3ca5}, + {MDIO_MMD_VEND1, LAN887X_ECHO_DELAY_CONFIG, 0x0024}, + {MDIO_MMD_VEND1, LAN887X_FFE_MAX_CONFIG, 0x227f}, + /* 1000T1 PCS writes */ + {MDIO_MMD_PCS, LAN887X_SCR_CONFIG_3, 0x1e00}, + {MDIO_MMD_PCS, LAN887X_INFO_FLD_CONFIG_5, 0x0fa1}, + }; + + return lan887x_phy_config(phydev, phy_cfg, ARRAY_SIZE(phy_cfg)); +} + +static int lan887x_100M_setup(struct phy_device *phydev) +{ + int ret; + + /* (Re)configure the speed/mode dependent T1 settings */ + if (phydev->master_slave_set == MASTER_SLAVE_CFG_MASTER_FORCE || + phydev->master_slave_set == MASTER_SLAVE_CFG_MASTER_PREFERRED){ + static const struct lan887x_regwr_map phy_cfg[] = { + {MDIO_MMD_PMAPMD, LAN887X_AFE_PORT_TESTBUS_CTRL4, 0x00b8}, + {MDIO_MMD_PMAPMD, LAN887X_TX_AMPLT_1000T1_REG, 0x0038}, + {MDIO_MMD_VEND1, LAN887X_INIT_COEFF_DFE1_100, 0x000f}, + }; + + ret = lan887x_phy_config(phydev, phy_cfg, ARRAY_SIZE(phy_cfg)); + } else { + static const struct lan887x_regwr_map phy_cfg[] = { + {MDIO_MMD_PMAPMD, LAN887X_AFE_PORT_TESTBUS_CTRL4, 0x0038}, + {MDIO_MMD_VEND1, LAN887X_INIT_COEFF_DFE1_100, 0x0014}, + }; + + ret = lan887x_phy_config(phydev, phy_cfg, ARRAY_SIZE(phy_cfg)); + } + if (ret < 0) + return ret; + + return phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, LAN887X_REG_REG26, + LAN887X_REG_REG26_HW_INIT_SEQ_EN); +} + +static int lan887x_1000M_setup(struct phy_device *phydev) +{ + static const struct lan887x_regwr_map phy_cfg[] = { + {MDIO_MMD_PMAPMD, LAN887X_TX_AMPLT_1000T1_REG, 0x003f}, + {MDIO_MMD_PMAPMD, LAN887X_AFE_PORT_TESTBUS_CTRL4, 0x00b8}, + }; + int ret; + + /* (Re)configure the speed/mode dependent T1 settings */ + ret = lan887x_phy_config(phydev, phy_cfg, ARRAY_SIZE(phy_cfg)); + if (ret < 0) + return ret; + + return phy_set_bits_mmd(phydev, MDIO_MMD_PMAPMD, LAN887X_DSP_PMA_CONTROL, + LAN887X_DSP_PMA_CONTROL_LNK_SYNC); +} + +static int lan887x_link_setup(struct phy_device *phydev) +{ + int ret = -EINVAL; + + if (phydev->speed == SPEED_1000) + ret = lan887x_1000M_setup(phydev); + else if (phydev->speed == SPEED_100) + ret = lan887x_100M_setup(phydev); + + return ret; +} + +/* LAN887x Errata: speed configuration changes require soft reset + * and chip soft reset + */ +static int lan887x_phy_reset(struct phy_device *phydev) +{ + int ret, val; + + /* Clear 1000M link sync */ + ret = phy_clear_bits_mmd(phydev, MDIO_MMD_PMAPMD, LAN887X_DSP_PMA_CONTROL, + LAN887X_DSP_PMA_CONTROL_LNK_SYNC); + if (ret < 0) + return ret; + + /* Clear 100M link sync */ + ret = phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, LAN887X_REG_REG26, + LAN887X_REG_REG26_HW_INIT_SEQ_EN); + if (ret < 0) + return ret; + + /* Chiptop soft-reset to allow the speed/mode change */ + ret = phy_write_mmd(phydev, MDIO_MMD_VEND1, LAN887X_CHIP_SOFT_RST, + LAN887X_CHIP_SOFT_RST_RESET); + if (ret < 0) + return ret; + + /* CL22 soft-reset to let the link re-train */ + ret = phy_modify(phydev, MII_BMCR, BMCR_RESET, BMCR_RESET); + if (ret < 0) + return ret; + + /* Wait for reset complete or timeout if > 10ms */ + return phy_read_poll_timeout(phydev, MII_BMCR, val, !(val & BMCR_RESET), + 5000, 10000, true); +} + +static int lan887x_phy_reconfig(struct phy_device *phydev) +{ + int ret; + + linkmode_zero(phydev->advertising); + + ret = genphy_c45_pma_setup_forced(phydev); + if (ret < 0) + return ret; + + return lan887x_link_setup(phydev); +} + +static int lan887x_config_aneg(struct phy_device *phydev) +{ + int ret; + + /* LAN887x Errata: speed configuration changes require soft reset + * and chip soft reset + */ + ret = lan887x_phy_reset(phydev); + if (ret < 0) + return ret; + + return lan887x_phy_reconfig(phydev); +} + +static int lan887x_probe(struct phy_device *phydev) +{ + struct lan887x_priv *priv; + + priv = devm_kzalloc(&phydev->mdio.dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + phydev->priv = priv; + + return lan887x_phy_setup(phydev); +} + +static u64 lan887x_get_stat(struct phy_device *phydev, int i) +{ + struct lan887x_hw_stat stat = lan887x_hw_stats[i]; + struct lan887x_priv *priv = phydev->priv; + int val; + u64 ret; + + if (stat.mmd) + val = phy_read_mmd(phydev, stat.mmd, stat.reg); + else + val = phy_read(phydev, stat.reg); + + if (val < 0) { + ret = U64_MAX; + } else { + val = val & ((1 << stat.bits) - 1); + priv->stats[i] += val; + ret = priv->stats[i]; + } + + return ret; +} + +static void lan887x_get_stats(struct phy_device *phydev, + struct ethtool_stats *stats, u64 *data) +{ + for (int i = 0; i < ARRAY_SIZE(lan887x_hw_stats); i++) + data[i] = lan887x_get_stat(phydev, i); +} + +static int lan887x_get_sset_count(struct phy_device *phydev) +{ + return ARRAY_SIZE(lan887x_hw_stats); +} + +static void lan887x_get_strings(struct phy_device *phydev, u8 *data) +{ + for (int i = 0; i < ARRAY_SIZE(lan887x_hw_stats); i++) + ethtool_puts(&data, lan887x_hw_stats[i].string); +} + static struct phy_driver microchip_t1_phy_driver[] = { { PHY_ID_MATCH_MODEL(PHY_ID_LAN87XX), @@ -894,6 +1454,20 @@ static struct phy_driver microchip_t1_phy_driver[] = { .get_sqi_max = lan87xx_get_sqi_max, .cable_test_start = lan87xx_cable_test_start, .cable_test_get_status = lan87xx_cable_test_get_status, + }, + { + PHY_ID_MATCH_MODEL(PHY_ID_LAN887X), + .name = "Microchip LAN887x T1 PHY", + .probe = lan887x_probe, + .get_features = lan887x_get_features, + .config_init = lan887x_phy_init, + .config_aneg = lan887x_config_aneg, + .get_stats = lan887x_get_stats, + .get_sset_count = lan887x_get_sset_count, + .get_strings = lan887x_get_strings, + .suspend = genphy_suspend, + .resume = genphy_resume, + .read_status = genphy_c45_read_status, } }; @@ -902,6 +1476,7 @@ module_phy_driver(microchip_t1_phy_driver); static struct mdio_device_id __maybe_unused microchip_t1_tbl[] = { { PHY_ID_MATCH_MODEL(PHY_ID_LAN87XX) }, { PHY_ID_MATCH_MODEL(PHY_ID_LAN937X) }, + { PHY_ID_MATCH_MODEL(PHY_ID_LAN887X) }, { } }; diff --git a/drivers/net/phy/open_alliance_helpers.c b/drivers/net/phy/open_alliance_helpers.c new file mode 100644 index 000000000000..36a70451d7da --- /dev/null +++ b/drivers/net/phy/open_alliance_helpers.c @@ -0,0 +1,77 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * open_alliance_helpers.c - OPEN Alliance specific PHY diagnostic helpers + * + * This file contains helper functions for implementing advanced diagnostic + * features as specified by the OPEN Alliance for automotive Ethernet PHYs. + * These helpers include functionality for Time Delay Reflection (TDR), dynamic + * channel quality assessment, and other PHY diagnostics. + * + * For more information on the specifications, refer to the OPEN Alliance + * documentation: https://opensig.org/automotive-ethernet-specifications/ + * Currently following specifications are partially or fully implemented: + * - Advanced diagnostic features for 1000BASE-T1 automotive Ethernet PHYs. + * TC12 - advanced PHY features. + * https://opensig.org/wp-content/uploads/2024/03/Advanced_PHY_features_for_automotive_Ethernet_v2.0_fin.pdf + */ + +#include <linux/bitfield.h> +#include <linux/ethtool_netlink.h> + +#include "open_alliance_helpers.h" + +/** + * oa_1000bt1_get_ethtool_cable_result_code - Convert TDR status to ethtool + * result code + * @reg_value: Value read from the TDR register + * + * This function takes a register value from the HDD.TDR register and converts + * the TDR status to the corresponding ethtool cable test result code. + * + * Return: The appropriate ethtool result code based on the TDR status + */ +int oa_1000bt1_get_ethtool_cable_result_code(u16 reg_value) +{ + u8 tdr_status = FIELD_GET(OA_1000BT1_HDD_TDR_STATUS_MASK, reg_value); + u8 dist_val = FIELD_GET(OA_1000BT1_HDD_TDR_DISTANCE_MASK, reg_value); + + switch (tdr_status) { + case OA_1000BT1_HDD_TDR_STATUS_CABLE_OK: + return ETHTOOL_A_CABLE_RESULT_CODE_OK; + case OA_1000BT1_HDD_TDR_STATUS_OPEN: + return ETHTOOL_A_CABLE_RESULT_CODE_OPEN; + case OA_1000BT1_HDD_TDR_STATUS_SHORT: + return ETHTOOL_A_CABLE_RESULT_CODE_SAME_SHORT; + case OA_1000BT1_HDD_TDR_STATUS_NOISE: + return ETHTOOL_A_CABLE_RESULT_CODE_NOISE; + default: + if (dist_val == OA_1000BT1_HDD_TDR_DISTANCE_RESOLUTION_NOT_POSSIBLE) + return ETHTOOL_A_CABLE_RESULT_CODE_RESOLUTION_NOT_POSSIBLE; + return ETHTOOL_A_CABLE_RESULT_CODE_UNSPEC; + } +} +EXPORT_SYMBOL_GPL(oa_1000bt1_get_ethtool_cable_result_code); + +/** + * oa_1000bt1_get_tdr_distance - Get distance to the main fault from TDR + * register value + * @reg_value: Value read from the TDR register + * + * This function takes a register value from the HDD.TDR register and extracts + * the distance to the main fault detected by the TDR feature. The distance is + * measured in centimeters and ranges from 0 to 3100 centimeters. If the + * distance is not available (0x3f), the function returns -ERANGE. + * + * Return: The distance to the main fault in centimeters, or -ERANGE if the + * resolution is not possible. + */ +int oa_1000bt1_get_tdr_distance(u16 reg_value) +{ + u8 dist_val = FIELD_GET(OA_1000BT1_HDD_TDR_DISTANCE_MASK, reg_value); + + if (dist_val == OA_1000BT1_HDD_TDR_DISTANCE_RESOLUTION_NOT_POSSIBLE) + return -ERANGE; + + return dist_val * 100; +} +EXPORT_SYMBOL_GPL(oa_1000bt1_get_tdr_distance); diff --git a/drivers/net/phy/open_alliance_helpers.h b/drivers/net/phy/open_alliance_helpers.h new file mode 100644 index 000000000000..8b7d97bc6f18 --- /dev/null +++ b/drivers/net/phy/open_alliance_helpers.h @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef OPEN_ALLIANCE_HELPERS_H +#define OPEN_ALLIANCE_HELPERS_H + +/* + * These defines reflect the TDR (Time Delay Reflection) diagnostic feature + * for 1000BASE-T1 automotive Ethernet PHYs as specified by the OPEN Alliance. + * + * The register values are part of the HDD.TDR register, which provides + * information about the cable status and faults. The exact register offset + * is device-specific and should be provided by the driver. + */ +#define OA_1000BT1_HDD_TDR_ACTIVATION_MASK GENMASK(1, 0) +#define OA_1000BT1_HDD_TDR_ACTIVATION_OFF 1 +#define OA_1000BT1_HDD_TDR_ACTIVATION_ON 2 + +#define OA_1000BT1_HDD_TDR_STATUS_MASK GENMASK(7, 4) +#define OA_1000BT1_HDD_TDR_STATUS_SHORT 3 +#define OA_1000BT1_HDD_TDR_STATUS_OPEN 6 +#define OA_1000BT1_HDD_TDR_STATUS_NOISE 5 +#define OA_1000BT1_HDD_TDR_STATUS_CABLE_OK 7 +#define OA_1000BT1_HDD_TDR_STATUS_TEST_IN_PROGRESS 8 +#define OA_1000BT1_HDD_TDR_STATUS_TEST_NOT_POSSIBLE 13 + +/* + * OA_1000BT1_HDD_TDR_DISTANCE_MASK: + * This mask is used to extract the distance to the first/main fault + * detected by the TDR feature. Each bit represents an approximate distance + * of 1 meter, ranging from 0 to 31 meters. The exact interpretation of the + * bits may vary, but generally: + * 000000 = no error + * 000001 = error about 0-1m away + * 000010 = error between 1-2m away + * ... + * 011111 = error about 30-31m away + * 111111 = resolution not possible / out of distance + */ +#define OA_1000BT1_HDD_TDR_DISTANCE_MASK GENMASK(13, 8) +#define OA_1000BT1_HDD_TDR_DISTANCE_NO_ERROR 0 +#define OA_1000BT1_HDD_TDR_DISTANCE_RESOLUTION_NOT_POSSIBLE 0x3f + +int oa_1000bt1_get_ethtool_cable_result_code(u16 reg_value); +int oa_1000bt1_get_tdr_distance(u16 reg_value); + +#endif /* OPEN_ALLIANCE_HELPERS_H */ + diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 785182fa5fe0..cba3af926429 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -1089,7 +1089,10 @@ int phy_ethtool_ksettings_set(struct phy_device *phydev, if (autoneg != AUTONEG_ENABLE && autoneg != AUTONEG_DISABLE) return -EINVAL; - if (autoneg == AUTONEG_ENABLE && linkmode_empty(advertising)) + if (autoneg == AUTONEG_ENABLE && + (linkmode_empty(advertising) || + !linkmode_test_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, + phydev->supported))) return -EINVAL; if (autoneg == AUTONEG_DISABLE && diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 7752e9386b40..8f5314c1fecc 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -29,6 +29,7 @@ #include <linux/phy.h> #include <linux/phylib_stubs.h> #include <linux/phy_led_triggers.h> +#include <linux/phy_link_topology.h> #include <linux/pse-pd/pse.h> #include <linux/property.h> #include <linux/rtnetlink.h> @@ -279,6 +280,15 @@ static struct phy_driver genphy_driver; static LIST_HEAD(phy_fixup_list); static DEFINE_MUTEX(phy_fixup_lock); +static bool phy_drv_wol_enabled(struct phy_device *phydev) +{ + struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL }; + + phy_ethtool_get_wol(phydev, &wol); + + return wol.wolopts != 0; +} + static bool mdio_bus_phy_may_suspend(struct phy_device *phydev) { struct device_driver *drv = phydev->mdio.dev.driver; @@ -288,6 +298,12 @@ static bool mdio_bus_phy_may_suspend(struct phy_device *phydev) if (!drv || !phydrv->suspend) return false; + /* 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)) + return false; + /* PHY not attached? May suspend if the PHY has not already been * suspended as part of a prior call to phy_disconnect() -> * phy_detach() -> phy_suspend() because the parent netdev might be the @@ -1370,6 +1386,48 @@ phy_standalone_show(struct device *dev, struct device_attribute *attr, static DEVICE_ATTR_RO(phy_standalone); /** + * phy_sfp_connect_phy - Connect the SFP module's PHY to the upstream PHY + * @upstream: pointer to the upstream phy device + * @phy: pointer to the SFP module's phy device + * + * This helper allows keeping track of PHY devices on the link. It adds the + * SFP module's phy to the phy namespace of the upstream phy + * + * Return: 0 on success, otherwise a negative error code. + */ +int phy_sfp_connect_phy(void *upstream, struct phy_device *phy) +{ + struct phy_device *phydev = upstream; + struct net_device *dev = phydev->attached_dev; + + if (dev) + return phy_link_topo_add_phy(dev, phy, PHY_UPSTREAM_PHY, phydev); + + return 0; +} +EXPORT_SYMBOL(phy_sfp_connect_phy); + +/** + * phy_sfp_disconnect_phy - Disconnect the SFP module's PHY from the upstream PHY + * @upstream: pointer to the upstream phy device + * @phy: pointer to the SFP module's phy device + * + * This helper allows keeping track of PHY devices on the link. It removes the + * SFP module's phy to the phy namespace of the upstream phy. As the module 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) +{ + struct phy_device *phydev = upstream; + struct net_device *dev = phydev->attached_dev; + + 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 * @upstream: pointer to the phy device * @bus: sfp bus representing cage being attached @@ -1511,6 +1569,10 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, if (phydev->sfp_bus_attached) dev->sfp_bus = phydev->sfp_bus; + + err = phy_link_topo_add_phy(dev, phydev, PHY_UPSTREAM_MAC, dev); + if (err) + goto error; } /* Some Ethernet drivers try to connect to a PHY device before @@ -1938,6 +2000,7 @@ void phy_detach(struct phy_device *phydev) if (dev) { phydev->attached_dev->phydev = NULL; phydev->attached_dev = NULL; + phy_link_topo_del_phy(dev, phydev); } phydev->phylink = NULL; @@ -1975,7 +2038,6 @@ EXPORT_SYMBOL(phy_detach); int phy_suspend(struct phy_device *phydev) { - struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL }; struct net_device *netdev = phydev->attached_dev; const struct phy_driver *phydrv = phydev->drv; int ret; @@ -1983,8 +2045,7 @@ int phy_suspend(struct phy_device *phydev) if (phydev->suspended || !phydrv) return 0; - phy_ethtool_get_wol(phydev, &wol); - phydev->wol_enabled = wol.wolopts || + phydev->wol_enabled = phy_drv_wol_enabled(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)) @@ -2095,22 +2156,20 @@ EXPORT_SYMBOL(phy_reset_after_clk_enable); /** * genphy_config_advert - sanitize and advertise auto-negotiation parameters * @phydev: target phy_device struct + * @advert: auto-negotiation parameters to advertise * * Description: Writes MII_ADVERTISE with the appropriate values, * after sanitizing the values to make sure we only advertise * what is supported. Returns < 0 on error, 0 if the PHY's advertisement * hasn't changed, and > 0 if it has changed. */ -static int genphy_config_advert(struct phy_device *phydev) +static int genphy_config_advert(struct phy_device *phydev, + const unsigned long *advert) { int err, bmsr, changed = 0; u32 adv; - /* Only allow advertising what this PHY supports */ - linkmode_and(phydev->advertising, phydev->advertising, - phydev->supported); - - adv = linkmode_adv_to_mii_adv_t(phydev->advertising); + adv = linkmode_adv_to_mii_adv_t(advert); /* Setup standard advertisement */ err = phy_modify_changed(phydev, MII_ADVERTISE, @@ -2133,7 +2192,7 @@ static int genphy_config_advert(struct phy_device *phydev) if (!(bmsr & BMSR_ESTATEN)) return changed; - adv = linkmode_adv_to_mii_ctrl1000_t(phydev->advertising); + adv = linkmode_adv_to_mii_ctrl1000_t(advert); err = phy_modify_changed(phydev, MII_CTRL1000, ADVERTISE_1000FULL | ADVERTISE_1000HALF, @@ -2357,6 +2416,9 @@ EXPORT_SYMBOL(genphy_check_and_restart_aneg); */ int __genphy_config_aneg(struct phy_device *phydev, bool changed) { + __ETHTOOL_DECLARE_LINK_MODE_MASK(fixed_advert); + const struct phy_setting *set; + unsigned long *advert; int err; err = genphy_c45_an_config_eee_aneg(phydev); @@ -2371,10 +2433,25 @@ int __genphy_config_aneg(struct phy_device *phydev, bool changed) else if (err) changed = true; - if (AUTONEG_ENABLE != phydev->autoneg) + if (phydev->autoneg == AUTONEG_ENABLE) { + /* Only allow advertising what this PHY supports */ + linkmode_and(phydev->advertising, phydev->advertising, + phydev->supported); + advert = phydev->advertising; + } else if (phydev->speed < SPEED_1000) { return genphy_setup_forced(phydev); + } else { + linkmode_zero(fixed_advert); + + set = phy_lookup_setting(phydev->speed, phydev->duplex, + phydev->supported, true); + if (set) + linkmode_set_bit(set->bit, fixed_advert); + + advert = fixed_advert; + } - err = genphy_config_advert(phydev); + err = genphy_config_advert(phydev, advert); if (err < 0) /* error */ return err; else if (err) diff --git a/drivers/net/phy/phy_link_topology.c b/drivers/net/phy/phy_link_topology.c new file mode 100644 index 000000000000..4a5d73002a1a --- /dev/null +++ b/drivers/net/phy/phy_link_topology.c @@ -0,0 +1,105 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Infrastructure to handle all PHY devices connected to a given netdev, + * either directly or indirectly attached. + * + * Copyright (c) 2023 Maxime Chevallier<maxime.chevallier@bootlin.com> + */ + +#include <linux/phy_link_topology.h> +#include <linux/phy.h> +#include <linux/rtnetlink.h> +#include <linux/xarray.h> + +static int netdev_alloc_phy_link_topology(struct net_device *dev) +{ + struct phy_link_topology *topo; + + topo = kzalloc(sizeof(*topo), GFP_KERNEL); + if (!topo) + return -ENOMEM; + + xa_init_flags(&topo->phys, XA_FLAGS_ALLOC1); + topo->next_phy_index = 1; + + dev->link_topo = topo; + + return 0; +} + +int phy_link_topo_add_phy(struct net_device *dev, + struct phy_device *phy, + enum phy_upstream upt, void *upstream) +{ + struct phy_link_topology *topo = dev->link_topo; + struct phy_device_node *pdn; + int ret; + + if (!topo) { + ret = netdev_alloc_phy_link_topology(dev); + if (ret) + return ret; + + topo = dev->link_topo; + } + + pdn = kzalloc(sizeof(*pdn), GFP_KERNEL); + if (!pdn) + return -ENOMEM; + + pdn->phy = phy; + switch (upt) { + case PHY_UPSTREAM_MAC: + pdn->upstream.netdev = (struct net_device *)upstream; + if (phy_on_sfp(phy)) + pdn->parent_sfp_bus = pdn->upstream.netdev->sfp_bus; + break; + case PHY_UPSTREAM_PHY: + pdn->upstream.phydev = (struct phy_device *)upstream; + if (phy_on_sfp(phy)) + pdn->parent_sfp_bus = pdn->upstream.phydev->sfp_bus; + break; + default: + ret = -EINVAL; + goto err; + } + pdn->upstream_type = upt; + + /* Attempt to re-use a previously allocated phy_index */ + if (phy->phyindex) + ret = xa_insert(&topo->phys, phy->phyindex, pdn, GFP_KERNEL); + else + ret = xa_alloc_cyclic(&topo->phys, &phy->phyindex, pdn, + xa_limit_32b, &topo->next_phy_index, + GFP_KERNEL); + + if (ret) + goto err; + + return 0; + +err: + kfree(pdn); + return ret; +} +EXPORT_SYMBOL_GPL(phy_link_topo_add_phy); + +void phy_link_topo_del_phy(struct net_device *dev, + struct phy_device *phy) +{ + struct phy_link_topology *topo = dev->link_topo; + struct phy_device_node *pdn; + + if (!topo) + return; + + pdn = xa_erase(&topo->phys, phy->phyindex); + + /* We delete the PHY from the topology, however we don't re-set the + * phy->phyindex field. If the PHY isn't gone, we can re-assign it the + * same index next time it's added back to the topology + */ + + kfree(pdn); +} +EXPORT_SYMBOL_GPL(phy_link_topo_del_phy); diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 51c526d227fa..ab4e9fc03017 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -3423,7 +3423,8 @@ static int phylink_sfp_connect_phy(void *upstream, struct phy_device *phy) return ret; } -static void phylink_sfp_disconnect_phy(void *upstream) +static void phylink_sfp_disconnect_phy(void *upstream, + struct phy_device *phydev) { phylink_disconnect_phy(upstream); } diff --git a/drivers/net/phy/qcom/at803x.c b/drivers/net/phy/qcom/at803x.c index c8f83e5f78ab..105602581a03 100644 --- a/drivers/net/phy/qcom/at803x.c +++ b/drivers/net/phy/qcom/at803x.c @@ -770,6 +770,8 @@ 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) diff --git a/drivers/net/phy/qcom/qca807x.c b/drivers/net/phy/qcom/qca807x.c index 672c6929119a..bd8a51ec0ecd 100644 --- a/drivers/net/phy/qcom/qca807x.c +++ b/drivers/net/phy/qcom/qca807x.c @@ -699,6 +699,8 @@ static const struct sfp_upstream_ops qca807x_sfp_ops = { .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) @@ -733,16 +735,6 @@ static int qca807x_probe(struct phy_device *phydev) "qcom,dac-disable-bias-current-tweak"); #if IS_ENABLED(CONFIG_GPIOLIB) - /* Make sure we don't have mixed leds node and gpio-controller - * to prevent registering leds and having gpio-controller usage - * conflicting with them. - */ - if (of_find_property(node, "leds", NULL) && - of_find_property(node, "gpio-controller", NULL)) { - phydev_err(phydev, "Invalid property detected. LEDs and gpio-controller are mutually exclusive."); - return -EINVAL; - } - /* Do not register a GPIO controller unless flagged for it */ if (of_property_read_bool(node, "gpio-controller")) { ret = qca807x_gpio(phydev); diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c index 2f44fc51848f..f13c00b5b449 100644 --- a/drivers/net/phy/sfp-bus.c +++ b/drivers/net/phy/sfp-bus.c @@ -487,7 +487,7 @@ static void sfp_unregister_bus(struct sfp_bus *bus) bus->socket_ops->stop(bus->sfp); bus->socket_ops->detach(bus->sfp); if (bus->phydev && ops && ops->disconnect_phy) - ops->disconnect_phy(bus->upstream); + ops->disconnect_phy(bus->upstream, bus->phydev); } bus->registered = false; } @@ -722,6 +722,28 @@ void sfp_bus_del_upstream(struct sfp_bus *bus) } EXPORT_SYMBOL_GPL(sfp_bus_del_upstream); +/** + * sfp_get_name() - Get the SFP device name + * @bus: a pointer to the &struct sfp_bus structure for the sfp module + * + * Gets the SFP device's name, if @bus has a registered socket. Callers must + * hold RTNL, and the returned name is only valid until RTNL is released. + * + * Returns: + * - The name of the SFP device registered with sfp_register_socket() + * - %NULL if no device was registered on @bus + */ +const char *sfp_get_name(struct sfp_bus *bus) +{ + ASSERT_RTNL(); + + if (bus->sfp_dev) + return dev_name(bus->sfp_dev); + + return NULL; +} +EXPORT_SYMBOL_GPL(sfp_get_name); + /* Socket driver entry points */ int sfp_add_phy(struct sfp_bus *bus, struct phy_device *phydev) { @@ -743,7 +765,7 @@ void sfp_remove_phy(struct sfp_bus *bus) const struct sfp_upstream_ops *ops = sfp_get_upstream_ops(bus); if (ops && ops->disconnect_phy) - ops->disconnect_phy(bus->upstream); + ops->disconnect_phy(bus->upstream, bus->phydev); bus->phydev = NULL; } EXPORT_SYMBOL_GPL(sfp_remove_phy); diff --git a/drivers/net/phy/vitesse.c b/drivers/net/phy/vitesse.c index 3b5fcaf0dd36..2377179de017 100644 --- a/drivers/net/phy/vitesse.c +++ b/drivers/net/phy/vitesse.c @@ -10,8 +10,10 @@ #include <linux/mii.h> #include <linux/ethtool.h> #include <linux/phy.h> +#include <linux/bitfield.h> /* Vitesse Extended Page Magic Register(s) */ +#define MII_VSC73XX_EXT_PAGE_1E 0x01 #define MII_VSC82X4_EXT_PAGE_16E 0x10 #define MII_VSC82X4_EXT_PAGE_17E 0x11 #define MII_VSC82X4_EXT_PAGE_18E 0x12 @@ -60,6 +62,28 @@ /* Vitesse Extended Page Access Register */ #define MII_VSC82X4_EXT_PAGE_ACCESS 0x1f +/* Vitesse VSC73XX Extended Control Register */ +#define MII_VSC73XX_PHY_CTRL_EXT3 0x14 + +#define MII_VSC73XX_PHY_CTRL_EXT3_DOWNSHIFT_EN BIT(4) +#define MII_VSC73XX_PHY_CTRL_EXT3_DOWNSHIFT_CNT GENMASK(3, 2) +#define MII_VSC73XX_PHY_CTRL_EXT3_DOWNSHIFT_STA BIT(1) +#define MII_VSC73XX_DOWNSHIFT_MAX 5 +#define MII_VSC73XX_DOWNSHIFT_INVAL 1 + +/* VSC73XX PHY_BYPASS_CTRL register*/ +#define MII_VSC73XX_PHY_BYPASS_CTRL MII_DCOUNTER +#define MII_VSC73XX_PBC_TX_DIS BIT(15) +#define MII_VSC73XX_PBC_FOR_SPD_AUTO_MDIX_DIS BIT(7) +#define MII_VSC73XX_PBC_PAIR_SWAP_DIS BIT(5) +#define MII_VSC73XX_PBC_POL_INV_DIS BIT(4) +#define MII_VSC73XX_PBC_PARALLEL_DET_DIS BIT(3) +#define MII_VSC73XX_PBC_AUTO_NP_EXCHANGE_DIS BIT(1) + +/* VSC73XX PHY_AUX_CTRL_STAT register */ +#define MII_VSC73XX_PHY_AUX_CTRL_STAT MII_NCONFIG +#define MII_VSC73XX_PACS_NO_MDI_X_IND BIT(13) + /* Vitesse VSC8601 Extended PHY Control Register 1 */ #define MII_VSC8601_EPHY_CTL 0x17 #define MII_VSC8601_EPHY_CTL_RGMII_SKEW (1 << 8) @@ -128,6 +152,74 @@ static int vsc73xx_write_page(struct phy_device *phydev, int page) return __phy_write(phydev, VSC73XX_EXT_PAGE_ACCESS, page); } +static int vsc73xx_get_downshift(struct phy_device *phydev, u8 *data) +{ + int val, enable, cnt; + + val = phy_read_paged(phydev, MII_VSC73XX_EXT_PAGE_1E, + MII_VSC73XX_PHY_CTRL_EXT3); + if (val < 0) + return val; + + enable = FIELD_GET(MII_VSC73XX_PHY_CTRL_EXT3_DOWNSHIFT_EN, val); + cnt = FIELD_GET(MII_VSC73XX_PHY_CTRL_EXT3_DOWNSHIFT_CNT, val) + 2; + + *data = enable ? cnt : DOWNSHIFT_DEV_DISABLE; + + return 0; +} + +static int vsc73xx_set_downshift(struct phy_device *phydev, u8 cnt) +{ + u16 mask, val; + int ret; + + if (cnt > MII_VSC73XX_DOWNSHIFT_MAX) + return -E2BIG; + else if (cnt == MII_VSC73XX_DOWNSHIFT_INVAL) + return -EINVAL; + + mask = MII_VSC73XX_PHY_CTRL_EXT3_DOWNSHIFT_EN; + + if (!cnt) { + val = 0; + } else { + mask |= MII_VSC73XX_PHY_CTRL_EXT3_DOWNSHIFT_CNT; + val = MII_VSC73XX_PHY_CTRL_EXT3_DOWNSHIFT_EN | + FIELD_PREP(MII_VSC73XX_PHY_CTRL_EXT3_DOWNSHIFT_CNT, + cnt - 2); + } + + ret = phy_modify_paged(phydev, MII_VSC73XX_EXT_PAGE_1E, + MII_VSC73XX_PHY_CTRL_EXT3, mask, val); + if (ret < 0) + return ret; + + return genphy_soft_reset(phydev); +} + +static int vsc73xx_get_tunable(struct phy_device *phydev, + struct ethtool_tunable *tuna, void *data) +{ + switch (tuna->id) { + case ETHTOOL_PHY_DOWNSHIFT: + return vsc73xx_get_downshift(phydev, data); + default: + return -EOPNOTSUPP; + } +} + +static int vsc73xx_set_tunable(struct phy_device *phydev, + struct ethtool_tunable *tuna, const void *data) +{ + switch (tuna->id) { + case ETHTOOL_PHY_DOWNSHIFT: + return vsc73xx_set_downshift(phydev, *(const u8 *)data); + default: + return -EOPNOTSUPP; + } +} + static void vsc73xx_config_init(struct phy_device *phydev) { /* Receiver init */ @@ -137,6 +229,12 @@ static void vsc73xx_config_init(struct phy_device *phydev) /* Config LEDs 0x61 */ phy_modify(phydev, MII_TPISTATUS, 0xff00, 0x0061); + + /* Enable downshift by default */ + vsc73xx_set_downshift(phydev, MII_VSC73XX_DOWNSHIFT_MAX); + + /* Set Auto MDI-X by default */ + phydev->mdix_ctrl = ETH_TP_MDI_AUTO; } static int vsc738x_config_init(struct phy_device *phydev) @@ -237,6 +335,75 @@ static int vsc739x_config_init(struct phy_device *phydev) return 0; } +static int vsc73xx_mdix_set(struct phy_device *phydev, u8 mdix) +{ + int ret; + u16 val; + + val = phy_read(phydev, MII_VSC73XX_PHY_BYPASS_CTRL); + + switch (mdix) { + case ETH_TP_MDI: + val |= MII_VSC73XX_PBC_FOR_SPD_AUTO_MDIX_DIS | + MII_VSC73XX_PBC_PAIR_SWAP_DIS | + MII_VSC73XX_PBC_POL_INV_DIS; + break; + case ETH_TP_MDI_X: + /* When MDI-X auto configuration is disabled, is possible + * to force only MDI mode. Let's use autoconfig for forced + * MDIX mode. + */ + case ETH_TP_MDI_AUTO: + val &= ~(MII_VSC73XX_PBC_FOR_SPD_AUTO_MDIX_DIS | + MII_VSC73XX_PBC_PAIR_SWAP_DIS | + MII_VSC73XX_PBC_POL_INV_DIS); + break; + default: + return -EINVAL; + } + + ret = phy_write(phydev, MII_VSC73XX_PHY_BYPASS_CTRL, val); + if (ret) + return ret; + + return genphy_restart_aneg(phydev); +} + +static int vsc73xx_config_aneg(struct phy_device *phydev) +{ + int ret; + + ret = vsc73xx_mdix_set(phydev, phydev->mdix_ctrl); + if (ret) + return ret; + + return genphy_config_aneg(phydev); +} + +static int vsc73xx_mdix_get(struct phy_device *phydev, u8 *mdix) +{ + u16 reg_val; + + reg_val = phy_read(phydev, MII_VSC73XX_PHY_AUX_CTRL_STAT); + if (reg_val & MII_VSC73XX_PACS_NO_MDI_X_IND) + *mdix = ETH_TP_MDI; + else + *mdix = ETH_TP_MDI_X; + + return 0; +} + +static int vsc73xx_read_status(struct phy_device *phydev) +{ + int ret; + + ret = vsc73xx_mdix_get(phydev, &phydev->mdix); + if (ret < 0) + return ret; + + return genphy_read_status(phydev); +} + /* This adds a skew for both TX and RX clocks, so the skew should only be * applied to "rgmii-id" interfaces. It may not work as expected * on "rgmii-txid", "rgmii-rxid" or "rgmii" interfaces. @@ -434,32 +601,48 @@ static struct phy_driver vsc82xx_driver[] = { .phy_id_mask = 0x000ffff0, /* PHY_GBIT_FEATURES */ .config_init = vsc738x_config_init, + .config_aneg = vsc73xx_config_aneg, + .read_status = vsc73xx_read_status, .read_page = vsc73xx_read_page, .write_page = vsc73xx_write_page, + .get_tunable = vsc73xx_get_tunable, + .set_tunable = vsc73xx_set_tunable, }, { .phy_id = PHY_ID_VSC7388, .name = "Vitesse VSC7388", .phy_id_mask = 0x000ffff0, /* PHY_GBIT_FEATURES */ .config_init = vsc738x_config_init, + .config_aneg = vsc73xx_config_aneg, + .read_status = vsc73xx_read_status, .read_page = vsc73xx_read_page, .write_page = vsc73xx_write_page, + .get_tunable = vsc73xx_get_tunable, + .set_tunable = vsc73xx_set_tunable, }, { .phy_id = PHY_ID_VSC7395, .name = "Vitesse VSC7395", .phy_id_mask = 0x000ffff0, /* PHY_GBIT_FEATURES */ .config_init = vsc739x_config_init, + .config_aneg = vsc73xx_config_aneg, + .read_status = vsc73xx_read_status, .read_page = vsc73xx_read_page, .write_page = vsc73xx_write_page, + .get_tunable = vsc73xx_get_tunable, + .set_tunable = vsc73xx_set_tunable, }, { .phy_id = PHY_ID_VSC7398, .name = "Vitesse VSC7398", .phy_id_mask = 0x000ffff0, /* PHY_GBIT_FEATURES */ .config_init = vsc739x_config_init, + .config_aneg = vsc73xx_config_aneg, + .read_status = vsc73xx_read_status, .read_page = vsc73xx_read_page, .write_page = vsc73xx_write_page, + .get_tunable = vsc73xx_get_tunable, + .set_tunable = vsc73xx_set_tunable, }, { .phy_id = PHY_ID_VSC8662, .name = "Vitesse VSC8662", diff --git a/drivers/net/pse-pd/tps23881.c b/drivers/net/pse-pd/tps23881.c index 2ea75686a319..5c4e88be46ee 100644 --- a/drivers/net/pse-pd/tps23881.c +++ b/drivers/net/pse-pd/tps23881.c @@ -8,6 +8,7 @@ #include <linux/bitfield.h> #include <linux/delay.h> #include <linux/firmware.h> +#include <linux/gpio/consumer.h> #include <linux/i2c.h> #include <linux/module.h> #include <linux/of.h> @@ -737,6 +738,7 @@ static int tps23881_i2c_probe(struct i2c_client *client) { struct device *dev = &client->dev; struct tps23881_priv *priv; + struct gpio_desc *reset; int ret; u8 val; @@ -749,6 +751,25 @@ static int tps23881_i2c_probe(struct i2c_client *client) if (!priv) return -ENOMEM; + reset = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH); + if (IS_ERR(reset)) + return dev_err_probe(&client->dev, PTR_ERR(reset), "Failed to get reset GPIO\n"); + + if (reset) { + /* TPS23880 datasheet (Rev G) indicates minimum reset pulse is 5us */ + usleep_range(5, 10); + gpiod_set_value_cansleep(reset, 0); /* De-assert reset */ + + /* TPS23880 datasheet indicates the minimum time after power on reset + * should be 20ms, but the document describing how to load SRAM ("How + * 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. + */ + msleep(50); + } + ret = i2c_smbus_read_byte_data(client, TPS23881_REG_DEVID); if (ret < 0) return ret; diff --git a/drivers/net/sungem_phy.c b/drivers/net/sungem_phy.c index d591e33268e5..55aa8d0c8e1f 100644 --- a/drivers/net/sungem_phy.c +++ b/drivers/net/sungem_phy.c @@ -893,7 +893,7 @@ static const struct mii_phy_ops bcm5201_phy_ops = { .read_link = genmii_read_link, }; -static struct mii_phy_def bcm5201_phy_def = { +static const struct mii_phy_def bcm5201_phy_def = { .phy_id = 0x00406210, .phy_id_mask = 0xfffffff0, .name = "BCM5201", @@ -912,7 +912,7 @@ static const struct mii_phy_ops bcm5221_phy_ops = { .read_link = genmii_read_link, }; -static struct mii_phy_def bcm5221_phy_def = { +static const struct mii_phy_def bcm5221_phy_def = { .phy_id = 0x004061e0, .phy_id_mask = 0xfffffff0, .name = "BCM5221", @@ -930,7 +930,8 @@ static const struct mii_phy_ops bcm5241_phy_ops = { .poll_link = genmii_poll_link, .read_link = genmii_read_link, }; -static struct mii_phy_def bcm5241_phy_def = { + +static const struct mii_phy_def bcm5241_phy_def = { .phy_id = 0x0143bc30, .phy_id_mask = 0xfffffff0, .name = "BCM5241", @@ -949,7 +950,7 @@ static const struct mii_phy_ops bcm5400_phy_ops = { .read_link = bcm54xx_read_link, }; -static struct mii_phy_def bcm5400_phy_def = { +static const struct mii_phy_def bcm5400_phy_def = { .phy_id = 0x00206040, .phy_id_mask = 0xfffffff0, .name = "BCM5400", @@ -968,7 +969,7 @@ static const struct mii_phy_ops bcm5401_phy_ops = { .read_link = bcm54xx_read_link, }; -static struct mii_phy_def bcm5401_phy_def = { +static const struct mii_phy_def bcm5401_phy_def = { .phy_id = 0x00206050, .phy_id_mask = 0xfffffff0, .name = "BCM5401", @@ -987,7 +988,7 @@ static const struct mii_phy_ops bcm5411_phy_ops = { .read_link = bcm54xx_read_link, }; -static struct mii_phy_def bcm5411_phy_def = { +static const struct mii_phy_def bcm5411_phy_def = { .phy_id = 0x00206070, .phy_id_mask = 0xfffffff0, .name = "BCM5411", @@ -1007,7 +1008,7 @@ static const struct mii_phy_ops bcm5421_phy_ops = { .enable_fiber = bcm5421_enable_fiber, }; -static struct mii_phy_def bcm5421_phy_def = { +static const struct mii_phy_def bcm5421_phy_def = { .phy_id = 0x002060e0, .phy_id_mask = 0xfffffff0, .name = "BCM5421", @@ -1026,7 +1027,7 @@ static const struct mii_phy_ops bcm5421k2_phy_ops = { .read_link = bcm54xx_read_link, }; -static struct mii_phy_def bcm5421k2_phy_def = { +static const struct mii_phy_def bcm5421k2_phy_def = { .phy_id = 0x002062e0, .phy_id_mask = 0xfffffff0, .name = "BCM5421-K2", @@ -1045,7 +1046,7 @@ static const struct mii_phy_ops bcm5461_phy_ops = { .enable_fiber = bcm5461_enable_fiber, }; -static struct mii_phy_def bcm5461_phy_def = { +static const struct mii_phy_def bcm5461_phy_def = { .phy_id = 0x002060c0, .phy_id_mask = 0xfffffff0, .name = "BCM5461", @@ -1064,7 +1065,7 @@ static const struct mii_phy_ops bcm5462V_phy_ops = { .read_link = bcm54xx_read_link, }; -static struct mii_phy_def bcm5462V_phy_def = { +static const struct mii_phy_def bcm5462V_phy_def = { .phy_id = 0x002060d0, .phy_id_mask = 0xfffffff0, .name = "BCM5462-Vesta", @@ -1094,7 +1095,7 @@ static const struct mii_phy_ops marvell88e1111_phy_ops = { /* two revs in darwin for the 88e1101 ... I could use a datasheet * to get the proper names... */ -static struct mii_phy_def marvell88e1101v1_phy_def = { +static const struct mii_phy_def marvell88e1101v1_phy_def = { .phy_id = 0x01410c20, .phy_id_mask = 0xfffffff0, .name = "Marvell 88E1101v1", @@ -1102,7 +1103,8 @@ static struct mii_phy_def marvell88e1101v1_phy_def = { .magic_aneg = 1, .ops = &marvell88e1101_phy_ops }; -static struct mii_phy_def marvell88e1101v2_phy_def = { + +static const struct mii_phy_def marvell88e1101v2_phy_def = { .phy_id = 0x01410c60, .phy_id_mask = 0xfffffff0, .name = "Marvell 88E1101v2", @@ -1110,7 +1112,8 @@ static struct mii_phy_def marvell88e1101v2_phy_def = { .magic_aneg = 1, .ops = &marvell88e1101_phy_ops }; -static struct mii_phy_def marvell88e1111_phy_def = { + +static const struct mii_phy_def marvell88e1111_phy_def = { .phy_id = 0x01410cc0, .phy_id_mask = 0xfffffff0, .name = "Marvell 88E1111", @@ -1127,7 +1130,7 @@ static const struct mii_phy_ops generic_phy_ops = { .read_link = genmii_read_link }; -static struct mii_phy_def genmii_phy_def = { +static const struct mii_phy_def genmii_phy_def = { .phy_id = 0x00000000, .phy_id_mask = 0x00000000, .name = "Generic MII", @@ -1136,7 +1139,7 @@ static struct mii_phy_def genmii_phy_def = { .ops = &generic_phy_ops }; -static struct mii_phy_def* mii_phy_table[] = { +static const struct mii_phy_def *mii_phy_table[] = { &bcm5201_phy_def, &bcm5221_phy_def, &bcm5241_phy_def, @@ -1156,9 +1159,9 @@ static struct mii_phy_def* mii_phy_table[] = { int sungem_phy_probe(struct mii_phy *phy, int mii_id) { + const struct mii_phy_def *def; int rc; u32 id; - struct mii_phy_def* def; int i; /* We do not reset the mii_phy structure as the driver diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c index 6d61052353f0..a6469235d904 100644 --- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -418,7 +418,8 @@ void usbnet_cdc_status(struct usbnet *dev, struct urb *urb) case USB_CDC_NOTIFY_NETWORK_CONNECTION: netif_dbg(dev, timer, dev->net, "CDC: carrier %s\n", event->wValue ? "on" : "off"); - usbnet_link_change(dev, !!event->wValue, 0); + if (netif_carrier_ok(dev->net) != !!event->wValue) + usbnet_link_change(dev, !!event->wValue, 0); break; case USB_CDC_NOTIFY_SPEED_CHANGE: /* tx/rx rates */ netif_dbg(dev, timer, dev->net, "CDC: speed change (len %d)\n", diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 426e68a95067..34499b91a8bd 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -1696,6 +1696,7 @@ static void veth_setup(struct net_device *dev) dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; dev->priv_flags |= IFF_NO_QUEUE; dev->priv_flags |= IFF_PHONY_HEADROOM; + dev->priv_flags |= IFF_DISABLE_NETPOLL; dev->netdev_ops = &veth_netdev_ops; dev->xdp_metadata_ops = &veth_xdp_metadata_ops; diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index c6af18948092..61ffa8851d7b 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -2885,6 +2885,25 @@ static void virtnet_cancel_dim(struct virtnet_info *vi, struct dim *dim) net_dim_work_cancel(dim); } +static void virtnet_update_settings(struct virtnet_info *vi) +{ + u32 speed; + u8 duplex; + + if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_SPEED_DUPLEX)) + return; + + virtio_cread_le(vi->vdev, struct virtio_net_config, speed, &speed); + + if (ethtool_validate_speed(speed)) + vi->speed = speed; + + virtio_cread_le(vi->vdev, struct virtio_net_config, duplex, &duplex); + + if (ethtool_validate_duplex(duplex)) + vi->duplex = duplex; +} + static int virtnet_open(struct net_device *dev) { struct virtnet_info *vi = netdev_priv(dev); @@ -2903,6 +2922,15 @@ static int virtnet_open(struct net_device *dev) goto err_enable_qp; } + if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_STATUS)) { + if (vi->status & VIRTIO_NET_S_LINK_UP) + netif_carrier_on(vi->dev); + virtio_config_driver_enable(vi->vdev); + } else { + vi->status = VIRTIO_NET_S_LINK_UP; + netif_carrier_on(dev); + } + return 0; err_enable_qp: @@ -3381,12 +3409,22 @@ static int virtnet_close(struct net_device *dev) disable_delayed_refill(vi); /* Make sure refill_work doesn't re-enable napi! */ cancel_delayed_work_sync(&vi->refill); + /* Prevent the config change callback from changing carrier + * after close + */ + virtio_config_driver_disable(vi->vdev); + /* Stop getting status/speed updates: we don't care until next + * open + */ + cancel_work_sync(&vi->config_work); for (i = 0; i < vi->max_queue_pairs; i++) { virtnet_disable_queue_pair(vi, i); virtnet_cancel_dim(vi, &vi->rq[i].dim); } + netif_carrier_off(dev); + return 0; } @@ -5095,25 +5133,6 @@ static void virtnet_init_settings(struct net_device *dev) vi->duplex = DUPLEX_UNKNOWN; } -static void virtnet_update_settings(struct virtnet_info *vi) -{ - u32 speed; - u8 duplex; - - if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_SPEED_DUPLEX)) - return; - - virtio_cread_le(vi->vdev, struct virtio_net_config, speed, &speed); - - if (ethtool_validate_speed(speed)) - vi->speed = speed; - - virtio_cread_le(vi->vdev, struct virtio_net_config, duplex, &duplex); - - if (ethtool_validate_duplex(duplex)) - vi->duplex = duplex; -} - static u32 virtnet_get_rxfh_key_size(struct net_device *dev) { return ((struct virtnet_info *)netdev_priv(dev))->rss_key_size; @@ -6524,6 +6543,9 @@ static int virtnet_probe(struct virtio_device *vdev) goto free_failover; } + /* Disable config change notification until ndo_open. */ + virtio_config_driver_disable(vi->vdev); + virtio_device_ready(vdev); virtnet_set_queues(vi, vi->curr_queue_pairs); @@ -6573,19 +6595,11 @@ static int virtnet_probe(struct virtio_device *vdev) vi->device_stats_cap = le64_to_cpu(v); } - rtnl_unlock(); - - err = virtnet_cpu_notif_add(vi); - if (err) { - pr_debug("virtio_net: registering cpu notifier failed\n"); - goto free_unregister_netdev; - } - /* Assume link up if device can't report link status, otherwise get link status from config. */ netif_carrier_off(dev); if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_STATUS)) { - schedule_work(&vi->config_work); + virtnet_config_changed_work(&vi->config_work); } else { vi->status = VIRTIO_NET_S_LINK_UP; virtnet_update_settings(vi); @@ -6597,6 +6611,14 @@ static int virtnet_probe(struct virtio_device *vdev) set_bit(guest_offloads[i], &vi->guest_offloads); vi->guest_offloads_capable = vi->guest_offloads; + rtnl_unlock(); + + err = virtnet_cpu_notif_add(vi); + if (err) { + pr_debug("virtio_net: registering cpu notifier failed\n"); + goto free_unregister_netdev; + } + pr_debug("virtnet: registered device %s with %d RX and TX vq's\n", dev->name, max_queue_pairs); diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index ba59e92ab941..34391c18bba7 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -277,8 +277,7 @@ static void __vxlan_fdb_notify(struct vxlan_dev *vxlan, struct vxlan_fdb *fdb, rtnl_notify(skb, net, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC); return; errout: - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_NEIGH, err); + rtnl_set_sk_err(net, RTNLGRP_NEIGH, err); } static void vxlan_fdb_switchdev_notifier_info(const struct vxlan_dev *vxlan, @@ -2690,11 +2689,11 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_rdst *rdst, *fdst = NULL; const struct ip_tunnel_info *info; - bool did_rsc = false; struct vxlan_fdb *f; struct ethhdr *eth; __be32 vni = 0; u32 nhid = 0; + bool did_rsc; info = skb_tunnel_info(skb); diff --git a/drivers/net/wwan/t7xx/t7xx_modem_ops.c b/drivers/net/wwan/t7xx/t7xx_modem_ops.c index 8d864d4ed77f..79f17100f70b 100644 --- a/drivers/net/wwan/t7xx/t7xx_modem_ops.c +++ b/drivers/net/wwan/t7xx/t7xx_modem_ops.c @@ -53,6 +53,7 @@ #define RGU_RESET_DELAY_MS 10 #define PORT_RESET_DELAY_MS 2000 +#define FASTBOOT_RESET_DELAY_MS 2000 #define EX_HS_TIMEOUT_MS 5000 #define EX_HS_POLL_DELAY_MS 10 @@ -167,19 +168,52 @@ static int t7xx_acpi_reset(struct t7xx_pci_dev *t7xx_dev, char *fn_name) } kfree(buffer.pointer); +#else + struct device *dev = &t7xx_dev->pdev->dev; + int ret; + ret = pci_reset_function(t7xx_dev->pdev); + if (ret) { + dev_err(dev, "Failed to reset device, error:%d\n", ret); + return ret; + } #endif return 0; } -int t7xx_acpi_fldr_func(struct t7xx_pci_dev *t7xx_dev) +static void t7xx_host_event_notify(struct t7xx_pci_dev *t7xx_dev, unsigned int event_id) { - return t7xx_acpi_reset(t7xx_dev, "_RST"); + u32 value; + + value = ioread32(IREG_BASE(t7xx_dev) + T7XX_PCIE_MISC_DEV_STATUS); + value &= ~HOST_EVENT_MASK; + value |= FIELD_PREP(HOST_EVENT_MASK, event_id); + iowrite32(value, IREG_BASE(t7xx_dev) + T7XX_PCIE_MISC_DEV_STATUS); } -int t7xx_acpi_pldr_func(struct t7xx_pci_dev *t7xx_dev) +int t7xx_reset_device(struct t7xx_pci_dev *t7xx_dev, enum reset_type type) { - return t7xx_acpi_reset(t7xx_dev, "MRST._RST"); + int ret = 0; + + pci_save_state(t7xx_dev->pdev); + t7xx_pci_reprobe_early(t7xx_dev); + t7xx_mode_update(t7xx_dev, T7XX_RESET); + + if (type == FLDR) { + ret = t7xx_acpi_reset(t7xx_dev, "_RST"); + } else if (type == PLDR) { + ret = t7xx_acpi_reset(t7xx_dev, "MRST._RST"); + } else if (type == FASTBOOT) { + t7xx_host_event_notify(t7xx_dev, FASTBOOT_DL_NOTIFY); + t7xx_mhccif_h2d_swint_trigger(t7xx_dev, H2D_CH_DEVICE_RESET); + msleep(FASTBOOT_RESET_DELAY_MS); + } + + pci_restore_state(t7xx_dev->pdev); + if (ret) + return ret; + + return t7xx_pci_reprobe(t7xx_dev, true); } static void t7xx_reset_device_via_pmic(struct t7xx_pci_dev *t7xx_dev) @@ -188,16 +222,15 @@ static void t7xx_reset_device_via_pmic(struct t7xx_pci_dev *t7xx_dev) val = ioread32(IREG_BASE(t7xx_dev) + T7XX_PCIE_MISC_DEV_STATUS); if (val & MISC_RESET_TYPE_PLDR) - t7xx_acpi_reset(t7xx_dev, "MRST._RST"); + t7xx_reset_device(t7xx_dev, PLDR); else if (val & MISC_RESET_TYPE_FLDR) - t7xx_acpi_fldr_func(t7xx_dev); + t7xx_reset_device(t7xx_dev, FLDR); } static irqreturn_t t7xx_rgu_isr_thread(int irq, void *data) { struct t7xx_pci_dev *t7xx_dev = data; - t7xx_mode_update(t7xx_dev, T7XX_RESET); msleep(RGU_RESET_DELAY_MS); t7xx_reset_device_via_pmic(t7xx_dev); return IRQ_HANDLED; diff --git a/drivers/net/wwan/t7xx/t7xx_modem_ops.h b/drivers/net/wwan/t7xx/t7xx_modem_ops.h index b39e945a92e0..39ed0000fbba 100644 --- a/drivers/net/wwan/t7xx/t7xx_modem_ops.h +++ b/drivers/net/wwan/t7xx/t7xx_modem_ops.h @@ -78,14 +78,19 @@ struct t7xx_modem { spinlock_t exp_lock; /* Protects exception events */ }; +enum reset_type { + FLDR, + PLDR, + FASTBOOT, +}; + void t7xx_md_exception_handshake(struct t7xx_modem *md); void t7xx_md_event_notify(struct t7xx_modem *md, enum md_event_id evt_id); int t7xx_md_reset(struct t7xx_pci_dev *t7xx_dev); int t7xx_md_init(struct t7xx_pci_dev *t7xx_dev); void t7xx_md_exit(struct t7xx_pci_dev *t7xx_dev); void t7xx_clear_rgu_irq(struct t7xx_pci_dev *t7xx_dev); -int t7xx_acpi_fldr_func(struct t7xx_pci_dev *t7xx_dev); -int t7xx_acpi_pldr_func(struct t7xx_pci_dev *t7xx_dev); +int t7xx_reset_device(struct t7xx_pci_dev *t7xx_dev, enum reset_type type); int t7xx_pci_mhccif_isr(struct t7xx_pci_dev *t7xx_dev); #endif /* __T7XX_MODEM_OPS_H__ */ diff --git a/drivers/net/wwan/t7xx/t7xx_pci.c b/drivers/net/wwan/t7xx/t7xx_pci.c index 10a8c1080b10..e556e5bd49ab 100644 --- a/drivers/net/wwan/t7xx/t7xx_pci.c +++ b/drivers/net/wwan/t7xx/t7xx_pci.c @@ -69,6 +69,7 @@ static ssize_t t7xx_mode_store(struct device *dev, { struct t7xx_pci_dev *t7xx_dev; struct pci_dev *pdev; + enum t7xx_mode mode; int index = 0; pdev = to_pci_dev(dev); @@ -76,12 +77,22 @@ static ssize_t t7xx_mode_store(struct device *dev, if (!t7xx_dev) return -ENODEV; + mode = READ_ONCE(t7xx_dev->mode); + index = sysfs_match_string(t7xx_mode_names, buf); + if (index == mode) + return -EBUSY; + if (index == T7XX_FASTBOOT_SWITCHING) { + if (mode == T7XX_FASTBOOT_DOWNLOAD) + return count; + WRITE_ONCE(t7xx_dev->mode, T7XX_FASTBOOT_SWITCHING); + pm_runtime_resume(dev); + t7xx_reset_device(t7xx_dev, FASTBOOT); } else if (index == T7XX_RESET) { - WRITE_ONCE(t7xx_dev->mode, T7XX_RESET); - t7xx_acpi_pldr_func(t7xx_dev); + pm_runtime_resume(dev); + t7xx_reset_device(t7xx_dev, PLDR); } return count; @@ -446,7 +457,7 @@ static int t7xx_pcie_reinit(struct t7xx_pci_dev *t7xx_dev, bool is_d3) if (is_d3) { t7xx_mhccif_init(t7xx_dev); - return t7xx_pci_pm_reinit(t7xx_dev); + t7xx_pci_pm_reinit(t7xx_dev); } return 0; @@ -481,6 +492,33 @@ static int t7xx_send_fsm_command(struct t7xx_pci_dev *t7xx_dev, u32 event) return ret; } +int t7xx_pci_reprobe_early(struct t7xx_pci_dev *t7xx_dev) +{ + enum t7xx_mode mode = READ_ONCE(t7xx_dev->mode); + int ret; + + if (mode == T7XX_FASTBOOT_DOWNLOAD) + pm_runtime_put_noidle(&t7xx_dev->pdev->dev); + + ret = t7xx_send_fsm_command(t7xx_dev, FSM_CMD_STOP); + if (ret) + return ret; + + return 0; +} + +int t7xx_pci_reprobe(struct t7xx_pci_dev *t7xx_dev, bool boot) +{ + int ret; + + ret = t7xx_pcie_reinit(t7xx_dev, boot); + if (ret) + return ret; + + t7xx_clear_rgu_irq(t7xx_dev); + return t7xx_send_fsm_command(t7xx_dev, FSM_CMD_START); +} + static int __t7xx_pci_pm_resume(struct pci_dev *pdev, bool state_check) { struct t7xx_pci_dev *t7xx_dev; @@ -507,16 +545,11 @@ static int __t7xx_pci_pm_resume(struct pci_dev *pdev, bool state_check) if (prev_state == PM_RESUME_REG_STATE_L3 || (prev_state == PM_RESUME_REG_STATE_INIT && atr_reg_val == ATR_SRC_ADDR_INVALID)) { - ret = t7xx_send_fsm_command(t7xx_dev, FSM_CMD_STOP); - if (ret) - return ret; - - ret = t7xx_pcie_reinit(t7xx_dev, true); + ret = t7xx_pci_reprobe_early(t7xx_dev); if (ret) return ret; - t7xx_clear_rgu_irq(t7xx_dev); - return t7xx_send_fsm_command(t7xx_dev, FSM_CMD_START); + return t7xx_pci_reprobe(t7xx_dev, true); } if (prev_state == PM_RESUME_REG_STATE_EXP || diff --git a/drivers/net/wwan/t7xx/t7xx_pci.h b/drivers/net/wwan/t7xx/t7xx_pci.h index 49a11586d8d8..cd8ea17c2644 100644 --- a/drivers/net/wwan/t7xx/t7xx_pci.h +++ b/drivers/net/wwan/t7xx/t7xx_pci.h @@ -133,4 +133,7 @@ int t7xx_pci_pm_entity_unregister(struct t7xx_pci_dev *t7xx_dev, struct md_pm_en void t7xx_pci_pm_init_late(struct t7xx_pci_dev *t7xx_dev); void t7xx_pci_pm_exp_detected(struct t7xx_pci_dev *t7xx_dev); void t7xx_mode_update(struct t7xx_pci_dev *t7xx_dev, enum t7xx_mode mode); +int t7xx_pci_reprobe(struct t7xx_pci_dev *t7xx_dev, bool boot); +int t7xx_pci_reprobe_early(struct t7xx_pci_dev *t7xx_dev); + #endif /* __T7XX_PCI_H__ */ diff --git a/drivers/net/wwan/t7xx/t7xx_port_proxy.c b/drivers/net/wwan/t7xx/t7xx_port_proxy.c index 7d6388bf1d7c..35743e7de0c3 100644 --- a/drivers/net/wwan/t7xx/t7xx_port_proxy.c +++ b/drivers/net/wwan/t7xx/t7xx_port_proxy.c @@ -553,7 +553,6 @@ static int t7xx_proxy_alloc(struct t7xx_modem *md) md->port_prox = port_prox; port_prox->dev = dev; - t7xx_port_proxy_set_cfg(md, PORT_CFG_ID_EARLY); return 0; } diff --git a/drivers/net/wwan/t7xx/t7xx_port_trace.c b/drivers/net/wwan/t7xx/t7xx_port_trace.c index 6a3f36385865..4ed8b4e29bf1 100644 --- a/drivers/net/wwan/t7xx/t7xx_port_trace.c +++ b/drivers/net/wwan/t7xx/t7xx_port_trace.c @@ -59,6 +59,7 @@ static void t7xx_trace_port_uninit(struct t7xx_port *port) relay_close(relaych); debugfs_remove_recursive(debugfs_dir); + port->log.relaych = NULL; } static int t7xx_trace_port_recv_skb(struct t7xx_port *port, struct sk_buff *skb) diff --git a/drivers/net/wwan/t7xx/t7xx_state_monitor.c b/drivers/net/wwan/t7xx/t7xx_state_monitor.c index 9889ca4621cf..3931c7a13f5a 100644 --- a/drivers/net/wwan/t7xx/t7xx_state_monitor.c +++ b/drivers/net/wwan/t7xx/t7xx_state_monitor.c @@ -213,16 +213,6 @@ static void fsm_routine_exception(struct t7xx_fsm_ctl *ctl, struct t7xx_fsm_comm fsm_finish_command(ctl, cmd, 0); } -static void t7xx_host_event_notify(struct t7xx_modem *md, unsigned int event_id) -{ - u32 value; - - value = ioread32(IREG_BASE(md->t7xx_dev) + T7XX_PCIE_MISC_DEV_STATUS); - value &= ~HOST_EVENT_MASK; - value |= FIELD_PREP(HOST_EVENT_MASK, event_id); - iowrite32(value, IREG_BASE(md->t7xx_dev) + T7XX_PCIE_MISC_DEV_STATUS); -} - static void t7xx_lk_stage_event_handling(struct t7xx_fsm_ctl *ctl, unsigned int status) { struct t7xx_modem *md = ctl->md; @@ -264,8 +254,14 @@ static void t7xx_lk_stage_event_handling(struct t7xx_fsm_ctl *ctl, unsigned int static int fsm_stopped_handler(struct t7xx_fsm_ctl *ctl) { + enum t7xx_mode mode; + ctl->curr_state = FSM_STATE_STOPPED; + mode = READ_ONCE(ctl->md->t7xx_dev->mode); + if (mode == T7XX_FASTBOOT_DOWNLOAD || mode == T7XX_FASTBOOT_DUMP) + return 0; + t7xx_fsm_broadcast_state(ctl, MD_STATE_STOPPED); return t7xx_md_reset(ctl->md->t7xx_dev); } @@ -284,8 +280,6 @@ static void fsm_routine_stopping(struct t7xx_fsm_ctl *ctl, struct t7xx_fsm_comma { struct cldma_ctrl *md_ctrl = ctl->md->md_ctrl[CLDMA_ID_MD]; struct t7xx_pci_dev *t7xx_dev = ctl->md->t7xx_dev; - enum t7xx_mode mode = READ_ONCE(t7xx_dev->mode); - int err; if (ctl->curr_state == FSM_STATE_STOPPED || ctl->curr_state == FSM_STATE_STOPPING) { fsm_finish_command(ctl, cmd, -EINVAL); @@ -296,21 +290,10 @@ static void fsm_routine_stopping(struct t7xx_fsm_ctl *ctl, struct t7xx_fsm_comma t7xx_fsm_broadcast_state(ctl, MD_STATE_WAITING_TO_STOP); t7xx_cldma_stop(md_ctrl); - if (mode == T7XX_FASTBOOT_SWITCHING) - t7xx_host_event_notify(ctl->md, FASTBOOT_DL_NOTIFY); - t7xx_mhccif_h2d_swint_trigger(t7xx_dev, H2D_CH_DRM_DISABLE_AP); /* Wait for the DRM disable to take effect */ msleep(FSM_DRM_DISABLE_DELAY_MS); - if (mode == T7XX_FASTBOOT_SWITCHING) { - t7xx_mhccif_h2d_swint_trigger(t7xx_dev, H2D_CH_DEVICE_RESET); - } else { - err = t7xx_acpi_fldr_func(t7xx_dev); - if (err) - t7xx_mhccif_h2d_swint_trigger(t7xx_dev, H2D_CH_DEVICE_RESET); - } - fsm_finish_command(ctl, cmd, fsm_stopped_handler(ctl)); } @@ -414,7 +397,9 @@ static void fsm_routine_start(struct t7xx_fsm_ctl *ctl, struct t7xx_fsm_command case T7XX_DEV_STAGE_LK: dev_dbg(dev, "LK_STAGE Entered\n"); + t7xx_port_proxy_set_cfg(md, PORT_CFG_ID_EARLY); t7xx_lk_stage_event_handling(ctl, status); + break; case T7XX_DEV_STAGE_LINUX: @@ -436,6 +421,9 @@ static void fsm_routine_start(struct t7xx_fsm_ctl *ctl, struct t7xx_fsm_command } finish_command: + if (ret) + t7xx_mode_update(md->t7xx_dev, T7XX_UNKNOWN); + fsm_finish_command(ctl, cmd, ret); } diff --git a/drivers/net/xen-netback/hash.c b/drivers/net/xen-netback/hash.c index ff96f22648ef..45ddce35f6d2 100644 --- a/drivers/net/xen-netback/hash.c +++ b/drivers/net/xen-netback/hash.c @@ -95,7 +95,7 @@ static u32 xenvif_new_hash(struct xenvif *vif, const u8 *data, static void xenvif_flush_hash(struct xenvif *vif) { - struct xenvif_hash_cache_entry *entry; + struct xenvif_hash_cache_entry *entry, *n; unsigned long flags; if (xenvif_hash_cache_size == 0) @@ -103,8 +103,7 @@ static void xenvif_flush_hash(struct xenvif *vif) spin_lock_irqsave(&vif->hash.cache.lock, flags); - list_for_each_entry_rcu(entry, &vif->hash.cache.list, link, - lockdep_is_held(&vif->hash.cache.lock)) { + list_for_each_entry_safe(entry, n, &vif->hash.cache.list, link) { list_del_rcu(&entry->link); vif->hash.cache.count--; kfree_rcu(entry, rcu); diff --git a/drivers/nfc/pn533/usb.c b/drivers/nfc/pn533/usb.c index a187f0e0b0f7..ffd7367ce119 100644 --- a/drivers/nfc/pn533/usb.c +++ b/drivers/nfc/pn533/usb.c @@ -254,7 +254,6 @@ struct pn533_acr122_ccid_hdr { * byte for reposnse msg */ u8 params[3]; - u8 data[]; /* payload */ } __packed; struct pn533_acr122_apdu_hdr { diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index bf664ec9341b..802153e23073 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -244,7 +244,7 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock, restart_tx = true; } - consume_skb(skb); + virtio_transport_consume_skb_sent(skb, true); } } while(likely(!vhost_exceeds_weight(vq, ++pkts, total_len))); if (added) @@ -451,6 +451,8 @@ static struct virtio_transport vhost_transport = { .notify_buffer_size = virtio_transport_notify_buffer_size, .notify_set_rcvlowat = virtio_transport_notify_set_rcvlowat, + .unsent_bytes = virtio_transport_unsent_bytes, + .read_skb = virtio_transport_read_skb, }, diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index bc1f962e483b..b9095751e43b 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -127,10 +127,12 @@ static void __virtio_config_changed(struct virtio_device *dev) { struct virtio_driver *drv = drv_to_virtio(dev->dev.driver); - if (!dev->config_enabled) + if (!dev->config_core_enabled || dev->config_driver_disabled) dev->config_change_pending = true; - else if (drv && drv->config_changed) + else if (drv && drv->config_changed) { drv->config_changed(dev); + dev->config_change_pending = false; + } } void virtio_config_changed(struct virtio_device *dev) @@ -143,20 +145,51 @@ void virtio_config_changed(struct virtio_device *dev) } EXPORT_SYMBOL_GPL(virtio_config_changed); -static void virtio_config_disable(struct virtio_device *dev) +/** + * virtio_config_driver_disable - disable config change reporting by drivers + * @dev: the device to reset + * + * This is only allowed to be called by a driver and disabling can't + * be nested. + */ +void virtio_config_driver_disable(struct virtio_device *dev) { spin_lock_irq(&dev->config_lock); - dev->config_enabled = false; + dev->config_driver_disabled = true; spin_unlock_irq(&dev->config_lock); } +EXPORT_SYMBOL_GPL(virtio_config_driver_disable); -static void virtio_config_enable(struct virtio_device *dev) +/** + * virtio_config_driver_enable - enable config change reporting by drivers + * @dev: the device to reset + * + * This is only allowed to be called by a driver and enabling can't + * be nested. + */ +void virtio_config_driver_enable(struct virtio_device *dev) { spin_lock_irq(&dev->config_lock); - dev->config_enabled = true; + dev->config_driver_disabled = false; + if (dev->config_change_pending) + __virtio_config_changed(dev); + spin_unlock_irq(&dev->config_lock); +} +EXPORT_SYMBOL_GPL(virtio_config_driver_enable); + +static void virtio_config_core_disable(struct virtio_device *dev) +{ + spin_lock_irq(&dev->config_lock); + dev->config_core_enabled = false; + spin_unlock_irq(&dev->config_lock); +} + +static void virtio_config_core_enable(struct virtio_device *dev) +{ + spin_lock_irq(&dev->config_lock); + dev->config_core_enabled = true; if (dev->config_change_pending) __virtio_config_changed(dev); - dev->config_change_pending = false; spin_unlock_irq(&dev->config_lock); } @@ -316,7 +349,7 @@ static int virtio_dev_probe(struct device *_d) if (drv->scan) drv->scan(dev); - virtio_config_enable(dev); + virtio_config_core_enable(dev); return 0; @@ -331,7 +364,7 @@ static void virtio_dev_remove(struct device *_d) struct virtio_device *dev = dev_to_virtio(_d); struct virtio_driver *drv = drv_to_virtio(dev->dev.driver); - virtio_config_disable(dev); + virtio_config_core_disable(dev); drv->remove(dev); @@ -443,7 +476,7 @@ int register_virtio_device(struct virtio_device *dev) goto out_ida_remove; spin_lock_init(&dev->config_lock); - dev->config_enabled = false; + dev->config_core_enabled = false; dev->config_change_pending = false; INIT_LIST_HEAD(&dev->vqs); @@ -500,14 +533,14 @@ int virtio_device_freeze(struct virtio_device *dev) struct virtio_driver *drv = drv_to_virtio(dev->dev.driver); int ret; - virtio_config_disable(dev); + virtio_config_core_disable(dev); dev->failed = dev->config->get_status(dev) & VIRTIO_CONFIG_S_FAILED; if (drv && drv->freeze) { ret = drv->freeze(dev); if (ret) { - virtio_config_enable(dev); + virtio_config_core_enable(dev); return ret; } } @@ -557,7 +590,7 @@ int virtio_device_restore(struct virtio_device *dev) if (!(dev->config->get_status(dev) & VIRTIO_CONFIG_S_DRIVER_OK)) virtio_device_ready(dev); - virtio_config_enable(dev); + virtio_config_core_enable(dev); return 0; diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index 8e177b67e82f..f41395264dca 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -247,6 +247,7 @@ VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vsi_resource); /* used to negotiate communicating link speeds in Mbps */ #define VIRTCHNL_VF_CAP_ADV_LINK_SPEED BIT(7) #define VIRTCHNL_VF_OFFLOAD_CRC BIT(10) +#define VIRTCHNL_VF_OFFLOAD_TC_U32 BIT(11) #define VIRTCHNL_VF_OFFLOAD_VLAN_V2 BIT(15) #define VIRTCHNL_VF_OFFLOAD_VLAN BIT(16) #define VIRTCHNL_VF_OFFLOAD_RX_POLLING BIT(17) @@ -1121,6 +1122,7 @@ enum virtchnl_vfr_states { }; #define VIRTCHNL_MAX_NUM_PROTO_HDRS 32 +#define VIRTCHNL_MAX_SIZE_RAW_PACKET 1024 #define PROTO_HDR_SHIFT 5 #define PROTO_HDR_FIELD_START(proto_hdr_type) ((proto_hdr_type) << PROTO_HDR_SHIFT) #define PROTO_HDR_FIELD_MASK ((1UL << PROTO_HDR_SHIFT) - 1) @@ -1266,13 +1268,22 @@ struct virtchnl_proto_hdrs { u8 pad[3]; /** * specify where protocol header start from. + * must be 0 when sending a raw packet request. * 0 - from the outer layer * 1 - from the first inner layer * 2 - from the second inner layer * .... **/ int count; /* the proto layers must < VIRTCHNL_MAX_NUM_PROTO_HDRS */ - struct virtchnl_proto_hdr proto_hdr[VIRTCHNL_MAX_NUM_PROTO_HDRS]; + union { + struct virtchnl_proto_hdr + proto_hdr[VIRTCHNL_MAX_NUM_PROTO_HDRS]; + struct { + u16 pkt_len; + u8 spec[VIRTCHNL_MAX_SIZE_RAW_PACKET]; + u8 mask[VIRTCHNL_MAX_SIZE_RAW_PACKET]; + } raw; + }; }; VIRTCHNL_CHECK_STRUCT_LEN(2312, virtchnl_proto_hdrs); diff --git a/include/linux/dpll.h b/include/linux/dpll.h index d275736230b3..81f7b623d0ba 100644 --- a/include/linux/dpll.h +++ b/include/linux/dpll.h @@ -15,6 +15,7 @@ struct dpll_device; struct dpll_pin; +struct dpll_pin_esync; struct dpll_device_ops { int (*mode_get)(const struct dpll_device *dpll, void *dpll_priv, @@ -83,6 +84,13 @@ struct dpll_pin_ops { int (*ffo_get)(const struct dpll_pin *pin, void *pin_priv, const struct dpll_device *dpll, void *dpll_priv, s64 *ffo, struct netlink_ext_ack *extack); + int (*esync_set)(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + u64 freq, struct netlink_ext_ack *extack); + int (*esync_get)(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + struct dpll_pin_esync *esync, + struct netlink_ext_ack *extack); }; struct dpll_pin_frequency { @@ -111,6 +119,13 @@ struct dpll_pin_phase_adjust_range { s32 max; }; +struct dpll_pin_esync { + u64 freq; + const struct dpll_pin_frequency *range; + u8 range_num; + u8 pulse; +}; + struct dpll_pin_properties { const char *board_label; const char *panel_label; diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 0ed47d00549b..30114c25ad12 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -645,7 +645,7 @@ static inline struct ethhdr *eth_skb_pull_mac(struct sk_buff *skb) } /** - * eth_skb_pad - Pad buffer to mininum number of octets for Ethernet frame + * eth_skb_pad - Pad buffer to minimum number of octets for Ethernet frame * @skb: Buffer to pad * * An Ethernet frame should have a minimum size of 60 bytes. This function diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 989c94eddb2b..12f6dc567598 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -727,9 +727,13 @@ struct kernel_ethtool_ts_info { * @cap_link_lanes_supported: indicates if the driver supports lanes * parameter. * @cap_rss_ctx_supported: indicates if the driver supports RSS - * contexts. + * contexts via legacy API, drivers implementing @create_rxfh_context + * do not have to set this bit. * @cap_rss_sym_xor_supported: indicates if the driver supports symmetric-xor * RSS. + * @rxfh_per_ctx_key: device supports setting different RSS key for each + * additional context. Netlink API should report hfunc, key, and input_xfrm + * for every context, not just context 0. * @rxfh_indir_space: max size of RSS indirection tables, if indirection table * size as returned by @get_rxfh_indir_size may change during lifetime * of the device. Leave as 0 if the table size is constant. @@ -951,6 +955,7 @@ struct ethtool_ops { u32 cap_link_lanes_supported:1; u32 cap_rss_ctx_supported:1; u32 cap_rss_sym_xor_supported:1; + u32 rxfh_per_ctx_key:1; u32 rxfh_indir_space; u16 rxfh_key_space; u16 rxfh_priv_size; diff --git a/include/linux/ethtool_netlink.h b/include/linux/ethtool_netlink.h index fae0dfb9a9c8..aba91335273a 100644 --- a/include/linux/ethtool_netlink.h +++ b/include/linux/ethtool_netlink.h @@ -23,8 +23,10 @@ struct phy_device; int ethnl_cable_test_alloc(struct phy_device *phydev, u8 cmd); void ethnl_cable_test_free(struct phy_device *phydev); void ethnl_cable_test_finished(struct phy_device *phydev); -int ethnl_cable_test_result(struct phy_device *phydev, u8 pair, u8 result); -int ethnl_cable_test_fault_length(struct phy_device *phydev, u8 pair, u32 cm); +int ethnl_cable_test_result_with_src(struct phy_device *phydev, u8 pair, + u8 result, u32 src); +int ethnl_cable_test_fault_length_with_src(struct phy_device *phydev, u8 pair, + u32 cm, u32 src); int ethnl_cable_test_amplitude(struct phy_device *phydev, u8 pair, s16 mV); int ethnl_cable_test_pulse(struct phy_device *phydev, u16 mV); int ethnl_cable_test_step(struct phy_device *phydev, u32 first, u32 last, @@ -54,14 +56,14 @@ static inline void ethnl_cable_test_free(struct phy_device *phydev) static inline void ethnl_cable_test_finished(struct phy_device *phydev) { } -static inline int ethnl_cable_test_result(struct phy_device *phydev, u8 pair, - u8 result) +static inline int ethnl_cable_test_result_with_src(struct phy_device *phydev, + u8 pair, u8 result, u32 src) { return -EOPNOTSUPP; } -static inline int ethnl_cable_test_fault_length(struct phy_device *phydev, - u8 pair, u32 cm) +static inline int ethnl_cable_test_fault_length_with_src(struct phy_device *phydev, + u8 pair, u32 cm, u32 src) { return -EOPNOTSUPP; } @@ -119,4 +121,19 @@ static inline bool ethtool_dev_mm_supported(struct net_device *dev) } #endif /* IS_ENABLED(CONFIG_ETHTOOL_NETLINK) */ + +static inline int ethnl_cable_test_result(struct phy_device *phydev, u8 pair, + u8 result) +{ + return ethnl_cable_test_result_with_src(phydev, pair, result, + ETHTOOL_A_CABLE_INF_SRC_TDR); +} + +static inline int ethnl_cable_test_fault_length(struct phy_device *phydev, + u8 pair, u32 cm) +{ + return ethnl_cable_test_fault_length_with_src(phydev, pair, cm, + ETHTOOL_A_CABLE_INF_SRC_TDR); +} + #endif /* _LINUX_ETHTOOL_NETLINK_H_ */ diff --git a/include/linux/filter.h b/include/linux/filter.h index b6672ff61407..64e1506fefb8 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1616,7 +1616,7 @@ extern struct static_key_false bpf_sk_lookup_enabled; _all_pass || _selected_sk ? SK_PASS : SK_DROP; \ }) -static inline bool bpf_sk_lookup_run_v4(struct net *net, int protocol, +static inline bool bpf_sk_lookup_run_v4(const struct net *net, int protocol, const __be32 saddr, const __be16 sport, const __be32 daddr, const u16 dport, const int ifindex, struct sock **psk) @@ -1653,7 +1653,7 @@ static inline bool bpf_sk_lookup_run_v4(struct net *net, int protocol, } #if IS_ENABLED(CONFIG_IPV6) -static inline bool bpf_sk_lookup_run_v6(struct net *net, int protocol, +static inline bool bpf_sk_lookup_run_v6(const struct net *net, int protocol, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, diff --git a/include/linux/if_rmnet.h b/include/linux/if_rmnet.h index 839d1e48b85e..c44bf6e80ecb 100644 --- a/include/linux/if_rmnet.h +++ b/include/linux/if_rmnet.h @@ -42,7 +42,7 @@ struct rmnet_map_ul_csum_header { /* csum_info field: * OFFSET: where (offset in bytes) to insert computed checksum - * UDP: 1 = UDP checksum (zero checkum means no checksum) + * UDP: 1 = UDP checksum (zero checksum means no checksum) * ENABLED: 1 = checksum computation requested */ #define MAP_CSUM_UL_OFFSET_MASK GENMASK(13, 0) diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 383a0ea2ab91..a6e2aadbb91b 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -89,6 +89,7 @@ struct ipv6_devconf { __u8 ioam6_enabled; __u8 ndisc_evict_nocarrier; __u8 ra_honor_pio_life; + __u8 ra_honor_pio_pflag; struct ctl_table_header *sysctl_header; }; diff --git a/include/linux/linkmode.h b/include/linux/linkmode.h index d94bfd9ac8cc..3b9de09871f6 100644 --- a/include/linux/linkmode.h +++ b/include/linux/linkmode.h @@ -37,8 +37,9 @@ static inline bool linkmode_empty(const unsigned long *src) return bitmap_empty(src, __ETHTOOL_LINK_MODE_MASK_NBITS); } -static inline int linkmode_andnot(unsigned long *dst, const unsigned long *src1, - const unsigned long *src2) +static inline bool linkmode_andnot(unsigned long *dst, + const unsigned long *src1, + const unsigned long *src2) { return bitmap_andnot(dst, src1, src2, __ETHTOOL_LINK_MODE_MASK_NBITS); } diff --git a/include/linux/mii.h b/include/linux/mii.h index d5a959ce4877..b8f26d4513c3 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -140,7 +140,7 @@ static inline u32 ethtool_adv_to_mii_adv_t(u32 ethadv) * settings to phy autonegotiation advertisements for the * MII_ADVERTISE register. */ -static inline u32 linkmode_adv_to_mii_adv_t(unsigned long *advertising) +static inline u32 linkmode_adv_to_mii_adv_t(const unsigned long *advertising) { u32 result = 0; @@ -215,7 +215,8 @@ static inline u32 ethtool_adv_to_mii_ctrl1000_t(u32 ethadv) * settings to phy autonegotiation advertisements for the * MII_CTRL1000 register when in 1000T mode. */ -static inline u32 linkmode_adv_to_mii_ctrl1000_t(unsigned long *advertising) +static inline u32 +linkmode_adv_to_mii_ctrl1000_t(const unsigned long *advertising) { u32 result = 0; @@ -453,7 +454,7 @@ static inline void mii_ctrl1000_mod_linkmode_adv_t(unsigned long *advertising, * A small helper function that translates linkmode advertising to LVL * pause capabilities. */ -static inline u32 linkmode_adv_to_lcl_adv_t(unsigned long *advertising) +static inline u32 linkmode_adv_to_lcl_adv_t(const unsigned long *advertising) { u32 lcl_adv = 0; diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index ba875a619b97..a94bc9e3af96 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1243,7 +1243,8 @@ enum mlx5_pcam_feature_groups { enum mlx5_mcam_reg_groups { MLX5_MCAM_REGS_FIRST_128 = 0x0, MLX5_MCAM_REGS_0x9100_0x917F = 0x2, - MLX5_MCAM_REGS_NUM = 0x3, + MLX5_MCAM_REGS_0x9180_0x91FF = 0x3, + MLX5_MCAM_REGS_NUM = 0x4, }; enum mlx5_mcam_feature_groups { @@ -1392,6 +1393,10 @@ enum mlx5_qcam_feature_groups { MLX5_GET(mcam_reg, (mdev)->caps.mcam[MLX5_MCAM_REGS_0x9100_0x917F], \ mng_access_reg_cap_mask.access_regs2.reg) +#define MLX5_CAP_MCAM_REG3(mdev, reg) \ + MLX5_GET(mcam_reg, (mdev)->caps.mcam[MLX5_MCAM_REGS_0x9180_0x91FF], \ + mng_access_reg_cap_mask.access_regs3.reg) + #define MLX5_CAP_MCAM_FEATURE(mdev, fld) \ MLX5_GET(mcam_reg, (mdev)->caps.mcam, mng_feature_cap_mask.enhanced_features.fld) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index a96438ded15f..9f42834f57c5 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -159,6 +159,8 @@ enum { MLX5_REG_MSECQ = 0x9155, MLX5_REG_MSEES = 0x9156, MLX5_REG_MIRC = 0x9162, + MLX5_REG_MTPTM = 0x9180, + MLX5_REG_MTCTR = 0x9181, MLX5_REG_SBCAM = 0xB01F, MLX5_REG_RESOURCE_DUMP = 0xC000, MLX5_REG_DTOR = 0xC00E, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index cab228cf51c6..234ad6f16e92 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -10401,6 +10401,18 @@ struct mlx5_ifc_mcam_access_reg_bits2 { u8 regs_31_to_0[0x20]; }; +struct mlx5_ifc_mcam_access_reg_bits3 { + u8 regs_127_to_96[0x20]; + + u8 regs_95_to_64[0x20]; + + u8 regs_63_to_32[0x20]; + + u8 regs_31_to_2[0x1e]; + u8 mtctr[0x1]; + u8 mtptm[0x1]; +}; + struct mlx5_ifc_mcam_reg_bits { u8 reserved_at_0[0x8]; u8 feature_group[0x8]; @@ -10413,6 +10425,7 @@ struct mlx5_ifc_mcam_reg_bits { struct mlx5_ifc_mcam_access_reg_bits access_regs; struct mlx5_ifc_mcam_access_reg_bits1 access_regs1; struct mlx5_ifc_mcam_access_reg_bits2 access_regs2; + struct mlx5_ifc_mcam_access_reg_bits3 access_regs3; u8 reserved_at_0[0x80]; } mng_access_reg_cap_mask; @@ -11166,6 +11179,34 @@ struct mlx5_ifc_mtmp_reg_bits { u8 sensor_name_lo[0x20]; }; +struct mlx5_ifc_mtptm_reg_bits { + u8 reserved_at_0[0x10]; + u8 psta[0x1]; + u8 reserved_at_11[0xf]; + + u8 reserved_at_20[0x60]; +}; + +enum { + MLX5_MTCTR_REQUEST_NOP = 0x0, + MLX5_MTCTR_REQUEST_PTM_ROOT_CLOCK = 0x1, + MLX5_MTCTR_REQUEST_FREE_RUNNING_COUNTER = 0x2, + MLX5_MTCTR_REQUEST_REAL_TIME_CLOCK = 0x3, +}; + +struct mlx5_ifc_mtctr_reg_bits { + u8 first_clock_timestamp_request[0x8]; + u8 second_clock_timestamp_request[0x8]; + u8 reserved_at_10[0x10]; + + u8 first_clock_valid[0x1]; + u8 second_clock_valid[0x1]; + u8 reserved_at_22[0x1e]; + + u8 first_clock_timestamp[0x40]; + u8 second_clock_timestamp[0x40]; +}; + union mlx5_ifc_ports_control_registers_document_bits { struct mlx5_ifc_bufferx_reg_bits bufferx_reg; struct mlx5_ifc_eth_2819_cntrs_grp_data_layout_bits eth_2819_cntrs_grp_data_layout; @@ -11230,6 +11271,8 @@ union mlx5_ifc_ports_control_registers_document_bits { struct mlx5_ifc_mrtc_reg_bits mrtc_reg; struct mlx5_ifc_mtcap_reg_bits mtcap_reg; struct mlx5_ifc_mtmp_reg_bits mtmp_reg; + struct mlx5_ifc_mtptm_reg_bits mtptm_reg; + struct mlx5_ifc_mtctr_reg_bits mtctr_reg; u8 reserved_at_0[0x60e0]; }; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 607009150b5f..fce70990b209 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -40,7 +40,6 @@ #include <net/dcbnl.h> #endif #include <net/netprio_cgroup.h> - #include <linux/netdev_features.h> #include <linux/neighbour.h> #include <linux/netdevice_xmit.h> @@ -81,6 +80,7 @@ struct xdp_frame; struct xdp_metadata_ops; struct xdp_md; struct ethtool_netdev_state; +struct phy_link_topology; typedef u32 xdp_features_t; @@ -645,9 +645,6 @@ struct netdev_queue { #ifdef CONFIG_SYSFS struct kobject kobj; #endif -#if defined(CONFIG_XPS) && defined(CONFIG_NUMA) - int numa_node; -#endif unsigned long tx_maxrate; /* * Number of TX timeouts for this queue @@ -660,13 +657,13 @@ struct netdev_queue { #ifdef CONFIG_XDP_SOCKETS struct xsk_buff_pool *pool; #endif - /* NAPI instance for the queue - * Readers and writers must hold RTNL - */ - struct napi_struct *napi; + /* * write-mostly part */ +#ifdef CONFIG_BQL + struct dql dql; +#endif spinlock_t _xmit_lock ____cacheline_aligned_in_smp; int xmit_lock_owner; /* @@ -676,8 +673,16 @@ struct netdev_queue { unsigned long state; -#ifdef CONFIG_BQL - struct dql dql; +/* + * slow- / control-path part + */ + /* NAPI instance for the queue + * Readers and writers must hold RTNL + */ + struct napi_struct *napi; + +#if defined(CONFIG_XPS) && defined(CONFIG_NUMA) + int numa_node; #endif } ____cacheline_aligned_in_smp; @@ -1232,7 +1237,7 @@ struct netdev_net_notifier { * int (*ndo_fdb_del)(struct ndmsg *ndm, struct nlattr *tb[], * struct net_device *dev, * const unsigned char *addr, u16 vid) - * Deletes the FDB entry from dev coresponding to addr. + * Deletes the FDB entry from dev corresponding to addr. * int (*ndo_fdb_del_bulk)(struct nlmsghdr *nlh, struct net_device *dev, * struct netlink_ext_ack *extack); * int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb, @@ -1689,38 +1694,6 @@ enum netdev_priv_flags { IFF_SEE_ALL_HWTSTAMP_REQUESTS = BIT_ULL(33), }; -#define IFF_802_1Q_VLAN IFF_802_1Q_VLAN -#define IFF_EBRIDGE IFF_EBRIDGE -#define IFF_BONDING IFF_BONDING -#define IFF_ISATAP IFF_ISATAP -#define IFF_WAN_HDLC IFF_WAN_HDLC -#define IFF_XMIT_DST_RELEASE IFF_XMIT_DST_RELEASE -#define IFF_DONT_BRIDGE IFF_DONT_BRIDGE -#define IFF_DISABLE_NETPOLL IFF_DISABLE_NETPOLL -#define IFF_MACVLAN_PORT IFF_MACVLAN_PORT -#define IFF_BRIDGE_PORT IFF_BRIDGE_PORT -#define IFF_OVS_DATAPATH IFF_OVS_DATAPATH -#define IFF_TX_SKB_SHARING IFF_TX_SKB_SHARING -#define IFF_UNICAST_FLT IFF_UNICAST_FLT -#define IFF_TEAM_PORT IFF_TEAM_PORT -#define IFF_SUPP_NOFCS IFF_SUPP_NOFCS -#define IFF_LIVE_ADDR_CHANGE IFF_LIVE_ADDR_CHANGE -#define IFF_MACVLAN IFF_MACVLAN -#define IFF_XMIT_DST_RELEASE_PERM IFF_XMIT_DST_RELEASE_PERM -#define IFF_L3MDEV_MASTER IFF_L3MDEV_MASTER -#define IFF_NO_QUEUE IFF_NO_QUEUE -#define IFF_OPENVSWITCH IFF_OPENVSWITCH -#define IFF_L3MDEV_SLAVE IFF_L3MDEV_SLAVE -#define IFF_TEAM IFF_TEAM -#define IFF_RXFH_CONFIGURED IFF_RXFH_CONFIGURED -#define IFF_PHONY_HEADROOM IFF_PHONY_HEADROOM -#define IFF_MACSEC IFF_MACSEC -#define IFF_NO_RX_HANDLER IFF_NO_RX_HANDLER -#define IFF_FAILOVER IFF_FAILOVER -#define IFF_FAILOVER_SLAVE IFF_FAILOVER_SLAVE -#define IFF_L3MDEV_RX_HANDLER IFF_L3MDEV_RX_HANDLER -#define IFF_TX_SKB_NO_LINEAR IFF_TX_SKB_NO_LINEAR - /* Specifies the type of the struct net_device::ml_priv pointer */ enum netdev_ml_priv_type { ML_PRIV_NONE, @@ -1978,6 +1951,7 @@ enum netdev_reg_state { * @fcoe_ddp_xid: Max exchange id for FCoE LRO by ddp * * @priomap: XXX: need comments on this one + * @link_topo: Physical link topology tracking attached PHYs * @phydev: Physical device may attach itself * for hardware timestamping * @sfp_bus: attached &struct sfp_bus structure. @@ -2369,6 +2343,7 @@ struct net_device { #if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) struct netprio_map __rcu *priomap; #endif + struct phy_link_topology *link_topo; struct phy_device *phydev; struct sfp_bus *sfp_bus; struct lock_class_key *qdisc_tx_busylock; @@ -3539,7 +3514,7 @@ static inline void netdev_tx_completed_queue(struct netdev_queue *dev_queue, dql_completed(&dev_queue->dql, bytes); /* - * Without the memory barrier there is a small possiblity that + * Without the memory barrier there is a small possibility that * netdev_tx_sent_queue will miss the update and cause the queue to * be stopped forever */ @@ -3950,6 +3925,7 @@ struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); u8 dev_xdp_prog_count(struct net_device *dev); +int dev_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf); u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode); int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb); @@ -4607,7 +4583,7 @@ void dev_uc_flush(struct net_device *dev); void dev_uc_init(struct net_device *dev); /** - * __dev_uc_sync - Synchonize device's unicast list + * __dev_uc_sync - Synchronize device's unicast list * @dev: device to sync * @sync: function to call if address should be added * @unsync: function to call if address should be removed @@ -4651,7 +4627,7 @@ void dev_mc_flush(struct net_device *dev); void dev_mc_init(struct net_device *dev); /** - * __dev_mc_sync - Synchonize device's multicast list + * __dev_mc_sync - Synchronize device's multicast list * @dev: device to sync * @sync: function to call if address should be added * @unsync: function to call if address should be removed diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index bd19c4b91e31..cd4e28db0cbd 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -64,6 +64,7 @@ int netpoll_setup(struct netpoll *np); void __netpoll_cleanup(struct netpoll *np); void __netpoll_free(struct netpoll *np); void netpoll_cleanup(struct netpoll *np); +void do_netpoll_cleanup(struct netpoll *np); netdev_tx_t netpoll_send_skb(struct netpoll *np, struct sk_buff *skb); #ifdef CONFIG_NETPOLL diff --git a/include/linux/phy.h b/include/linux/phy.h index 6b7d40d49129..a98bc91a0cde 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -554,6 +554,9 @@ struct macsec_ops; * @drv: Pointer to the driver for this PHY instance * @devlink: Create a link between phy dev and mac dev, if the external phy * used by current mac interface is managed by another mac interface. + * @phyindex: Unique id across the phy's parent tree of phys to address the PHY + * from userspace, similar to ifindex. A zero index means the PHY + * wasn't assigned an id yet. * @phy_id: UID for this device found during discovery * @c45_ids: 802.3-c45 Device Identifiers if is_c45. * @is_c45: Set to true if this PHY uses clause 45 addressing. @@ -656,6 +659,7 @@ struct phy_device { struct device_link *devlink; + u32 phyindex; u32 phy_id; struct phy_c45_device_ids c45_ids; @@ -1777,6 +1781,8 @@ 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 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, diff --git a/include/linux/phy_link_topology.h b/include/linux/phy_link_topology.h new file mode 100644 index 000000000000..68a59e25821c --- /dev/null +++ b/include/linux/phy_link_topology.h @@ -0,0 +1,82 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * PHY device list allow maintaining a list of PHY devices that are + * part of a netdevice's link topology. PHYs can for example be chained, + * as is the case when using a PHY that exposes an SFP module, on which an + * SFP transceiver that embeds a PHY is connected. + * + * This list can then be used by userspace to leverage individual PHY + * capabilities. + */ +#ifndef __PHY_LINK_TOPOLOGY_H +#define __PHY_LINK_TOPOLOGY_H + +#include <linux/ethtool.h> +#include <linux/netdevice.h> + +struct xarray; +struct phy_device; +struct sfp_bus; + +struct phy_link_topology { + struct xarray phys; + u32 next_phy_index; +}; + +struct phy_device_node { + enum phy_upstream upstream_type; + + union { + struct net_device *netdev; + struct phy_device *phydev; + } upstream; + + struct sfp_bus *parent_sfp_bus; + + struct phy_device *phy; +}; + +#if IS_ENABLED(CONFIG_PHYLIB) +int phy_link_topo_add_phy(struct net_device *dev, + struct phy_device *phy, + enum phy_upstream upt, void *upstream); + +void phy_link_topo_del_phy(struct net_device *dev, struct phy_device *phy); + +static inline struct phy_device * +phy_link_topo_get_phy(struct net_device *dev, u32 phyindex) +{ + struct phy_link_topology *topo = dev->link_topo; + struct phy_device_node *pdn; + + if (!topo) + return NULL; + + pdn = xa_load(&topo->phys, phyindex); + if (pdn) + return pdn->phy; + + return NULL; +} + +#else +static inline int phy_link_topo_add_phy(struct net_device *dev, + struct phy_device *phy, + enum phy_upstream upt, void *upstream) +{ + return 0; +} + +static inline void phy_link_topo_del_phy(struct net_device *dev, + struct phy_device *phy) +{ +} + +static inline struct phy_device * +phy_link_topo_get_phy(struct net_device *dev, u32 phyindex) +{ + return NULL; +} +#endif + +#endif /* __PHY_LINK_TOPOLOGY_H */ diff --git a/include/linux/platform_data/microchip-ksz.h b/include/linux/platform_data/microchip-ksz.h index 8c659db4da6b..d074019474f5 100644 --- a/include/linux/platform_data/microchip-ksz.h +++ b/include/linux/platform_data/microchip-ksz.h @@ -28,6 +28,8 @@ enum ksz_chip_id { KSZ8794_CHIP_ID = 0x8794, KSZ8765_CHIP_ID = 0x8765, KSZ8830_CHIP_ID = 0x8830, + KSZ8864_CHIP_ID = 0x8864, + KSZ8895_CHIP_ID = 0x8895, KSZ9477_CHIP_ID = 0x00947700, KSZ9896_CHIP_ID = 0x00989600, KSZ9897_CHIP_ID = 0x00989700, diff --git a/include/linux/sfp.h b/include/linux/sfp.h index b14be59550e3..60c65cea74f6 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -550,7 +550,7 @@ struct sfp_upstream_ops { void (*link_down)(void *priv); void (*link_up)(void *priv); int (*connect_phy)(void *priv, struct phy_device *); - void (*disconnect_phy)(void *priv); + void (*disconnect_phy)(void *priv, struct phy_device *); }; #if IS_ENABLED(CONFIG_SFP) @@ -576,6 +576,7 @@ struct sfp_bus *sfp_bus_find_fwnode(const struct fwnode_handle *fwnode); int sfp_bus_add_upstream(struct sfp_bus *bus, void *upstream, const struct sfp_upstream_ops *ops); void sfp_bus_del_upstream(struct sfp_bus *bus); +const char *sfp_get_name(struct sfp_bus *bus); #else static inline int sfp_parse_port(struct sfp_bus *bus, const struct sfp_eeprom_id *id, @@ -654,6 +655,11 @@ static inline int sfp_bus_add_upstream(struct sfp_bus *bus, void *upstream, static inline void sfp_bus_del_upstream(struct sfp_bus *bus) { } + +static inline const char *sfp_get_name(struct sfp_bus *bus) +{ + return NULL; +} #endif #endif diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 29c3ea5b6e93..cf8f6ce06742 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1225,7 +1225,7 @@ static inline bool skb_unref(struct sk_buff *skb) { if (unlikely(!skb)) return false; - if (likely(refcount_read(&skb->users) == 1)) + if (!IS_ENABLED(CONFIG_DEBUG_NET) && likely(refcount_read(&skb->users) == 1)) smp_rmb(); else if (likely(!refcount_dec_and_test(&skb->users))) return false; diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 84e13bd5df28..338991c08f00 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -100,6 +100,7 @@ struct stmmac_dma_cfg { bool eame; bool multi_msi_en; bool dche; + bool atds; }; #define AXI_BLEN 7 diff --git a/include/linux/sungem_phy.h b/include/linux/sungem_phy.h index c505f30e8b68..eecc7eb63bfb 100644 --- a/include/linux/sungem_phy.h +++ b/include/linux/sungem_phy.h @@ -40,7 +40,7 @@ enum { /* An instance of a PHY, partially borrowed from mii_if_info */ struct mii_phy { - struct mii_phy_def* def; + const struct mii_phy_def *def; u32 advertising; int mii_id; diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 4b16844c6bc2..306137a15d07 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -118,7 +118,9 @@ struct virtio_admin_cmd { * struct virtio_device - representation of a device using virtio * @index: unique position on the virtio bus * @failed: saved value for VIRTIO_CONFIG_S_FAILED bit (for restore) - * @config_enabled: configuration change reporting enabled + * @config_core_enabled: configuration change reporting enabled by core + * @config_driver_disabled: configuration change reporting disabled by + * a driver * @config_change_pending: configuration change reported while disabled * @config_lock: protects configuration change reporting * @vqs_list_lock: protects @vqs. @@ -135,7 +137,8 @@ struct virtio_admin_cmd { struct virtio_device { int index; bool failed; - bool config_enabled; + bool config_core_enabled; + bool config_driver_disabled; bool config_change_pending; spinlock_t config_lock; spinlock_t vqs_list_lock; @@ -166,6 +169,10 @@ void __virtqueue_break(struct virtqueue *_vq); void __virtqueue_unbreak(struct virtqueue *_vq); void virtio_config_changed(struct virtio_device *dev); + +void virtio_config_driver_disable(struct virtio_device *dev); +void virtio_config_driver_enable(struct virtio_device *dev); + #ifdef CONFIG_PM_SLEEP int virtio_device_freeze(struct virtio_device *dev); int virtio_device_restore(struct virtio_device *dev); diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index c82089dee0c8..0387d64e2c66 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -133,6 +133,7 @@ struct virtio_vsock_sock { u32 tx_cnt; u32 peer_fwd_cnt; u32 peer_buf_alloc; + size_t bytes_unsent; /* Protected by rx_lock */ u32 fwd_cnt; @@ -193,6 +194,11 @@ s64 virtio_transport_stream_has_data(struct vsock_sock *vsk); s64 virtio_transport_stream_has_space(struct vsock_sock *vsk); u32 virtio_transport_seqpacket_has_data(struct vsock_sock *vsk); +ssize_t virtio_transport_unsent_bytes(struct vsock_sock *vsk); + +void virtio_transport_consume_skb_sent(struct sk_buff *skb, + bool consume); + int virtio_transport_do_socket_init(struct vsock_sock *vsk, struct vsock_sock *psk); int diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 62a407db1bf5..363dd63babe7 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -37,10 +37,14 @@ struct prefix_info { struct __packed { #if defined(__BIG_ENDIAN_BITFIELD) __u8 onlink : 1, - autoconf : 1, - reserved : 6; + autoconf : 1, + routeraddr : 1, + preferpd : 1, + reserved : 4; #elif defined(__LITTLE_ENDIAN_BITFIELD) - __u8 reserved : 6, + __u8 reserved : 4, + preferpd : 1, + routeraddr : 1, autoconf : 1, onlink : 1; #else @@ -183,10 +187,12 @@ static inline int addrconf_ifid_eui48(u8 *eui, struct net_device *dev) return 0; } +#define INFINITY_LIFE_TIME 0xFFFFFFFF + static inline unsigned long addrconf_timeout_fixup(u32 timeout, unsigned int unit) { - if (timeout == 0xffffffff) + if (timeout == INFINITY_LIFE_TIME) return ~0UL; /* @@ -327,7 +333,7 @@ static inline struct inet6_dev *__in6_dev_get(const struct net_device *dev) /** * __in6_dev_stats_get - get inet6_dev pointer for stats * @dev: network device - * @skb: skb for original incoming interface if neeeded + * @skb: skb for original incoming interface if needed * * Caller must hold rcu_read_lock or RTNL, because this function * does not take a reference on the inet6_dev. diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index 24d970f7a4fa..9e85424c8343 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -169,6 +169,9 @@ struct vsock_transport { void (*notify_buffer_size)(struct vsock_sock *, u64 *); int (*notify_set_rcvlowat)(struct vsock_sock *vsk, int val); + /* SIOCOUTQ ioctl */ + ssize_t (*unsent_bytes)(struct vsock_sock *vsk); + /* Shutdown. */ int (*shutdown)(struct vsock_sock *, int); diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h index 9ce5ac2bfbad..2053cd8e788a 100644 --- a/include/net/bond_3ad.h +++ b/include/net/bond_3ad.h @@ -231,7 +231,10 @@ typedef struct port { mux_states_t sm_mux_state; /* state machine mux state */ u16 sm_mux_timer_counter; /* state machine mux timer counter */ tx_states_t sm_tx_state; /* state machine tx state */ - u16 sm_tx_timer_counter; /* state machine tx timer counter(allways on - enter to transmit state 3 time per second) */ + u16 sm_tx_timer_counter; /* state machine tx timer counter + * (always on - enter to transmit + * state 3 time per second) + */ u16 sm_churn_actor_timer_counter; u16 sm_churn_partner_timer_counter; u32 churn_actor_count; diff --git a/include/net/bond_alb.h b/include/net/bond_alb.h index 9dc082b2d543..e5945427f38d 100644 --- a/include/net/bond_alb.h +++ b/include/net/bond_alb.h @@ -53,7 +53,7 @@ struct slave; struct tlb_client_info { - struct slave *tx_slave; /* A pointer to slave used for transmiting + struct slave *tx_slave; /* A pointer to slave used for transmitting * packets to a Client that the Hash function * gave this entry index. */ diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h index 522f1da8b747..f03040baaefd 100644 --- a/include/net/busy_poll.h +++ b/include/net/busy_poll.h @@ -131,7 +131,7 @@ static inline void skb_mark_napi_id(struct sk_buff *skb, #endif } -/* used in the protocol hanlder to propagate the napi_id to the socket */ +/* used in the protocol handler to propagate the napi_id to the socket */ static inline void sk_mark_napi_id(struct sock *sk, const struct sk_buff *skb) { #ifdef CONFIG_NET_RX_BUSY_POLL diff --git a/include/net/caif/caif_layer.h b/include/net/caif/caif_layer.h index 0f45d875905f..053e7c6a6a66 100644 --- a/include/net/caif/caif_layer.h +++ b/include/net/caif/caif_layer.h @@ -20,7 +20,7 @@ struct caif_payload_info; * @assert: expression to evaluate. * * This function will print a error message and a do WARN_ON if the - * assertion failes. Normally this will do a stack up at the current location. + * assertion fails. Normally this will do a stack up at the current location. */ #define caif_assert(assert) \ do { \ @@ -116,7 +116,7 @@ enum caif_direction { * @dn: Pointer down to the layer below. * @node: List node used when layer participate in a list. * @receive: Packet receive function. - * @transmit: Packet transmit funciton. + * @transmit: Packet transmit function. * @ctrlcmd: Used for control signalling upwards in the stack. * @modemcmd: Used for control signaling downwards in the stack. * @id: The identity of this layer diff --git a/include/net/caif/cfpkt.h b/include/net/caif/cfpkt.h index 44d914a50369..acf664227d96 100644 --- a/include/net/caif/cfpkt.h +++ b/include/net/caif/cfpkt.h @@ -18,7 +18,7 @@ struct cfpkt *cfpkt_create(u16 len); /* * Destroy a CAIF Packet. - * pkt Packet to be destoyed. + * pkt Packet to be destroyed. */ void cfpkt_destroy(struct cfpkt *pkt); diff --git a/include/net/dropreason-core.h b/include/net/dropreason-core.h index 9707ab54fdd5..4748680e8c88 100644 --- a/include/net/dropreason-core.h +++ b/include/net/dropreason-core.h @@ -155,8 +155,8 @@ enum skb_drop_reason { /** @SKB_DROP_REASON_SOCKET_RCVBUFF: socket receive buff is full */ SKB_DROP_REASON_SOCKET_RCVBUFF, /** - * @SKB_DROP_REASON_PROTO_MEM: proto memory limition, such as udp packet - * drop out of udp_memory_allocated. + * @SKB_DROP_REASON_PROTO_MEM: proto memory limitation, such as + * udp packet drop out of udp_memory_allocated. */ SKB_DROP_REASON_PROTO_MEM, /** @@ -217,7 +217,7 @@ enum skb_drop_reason { */ SKB_DROP_REASON_TCP_ZEROWINDOW, /** - * @SKB_DROP_REASON_TCP_OLD_DATA: the TCP data reveived is already + * @SKB_DROP_REASON_TCP_OLD_DATA: the TCP data received is already * received before (spurious retrans may happened), see * LINUX_MIB_DELAYEDACKLOST */ diff --git a/include/net/dst.h b/include/net/dst.h index 0aa331bd2fdb..0f303cc60252 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -341,7 +341,7 @@ static inline void __skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev, skb->dev = dev; /* - * Clear hash so that we can recalulate the hash for the + * Clear hash so that we can recalculate the hash for the * encapsulated packet, unless we have already determine the hash * over the L4 4-tuple. */ diff --git a/include/net/dst_cache.h b/include/net/dst_cache.h index b4a55d2d5e71..1961699598e2 100644 --- a/include/net/dst_cache.h +++ b/include/net/dst_cache.h @@ -102,7 +102,7 @@ int dst_cache_init(struct dst_cache *dst_cache, gfp_t gfp); * @dst_cache: the cache * * No synchronization is enforced: it must be called only when the cache - * is unsed. + * is unused. */ void dst_cache_destroy(struct dst_cache *dst_cache); diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h index 4160731dcb6e..84c15402931c 100644 --- a/include/net/dst_metadata.h +++ b/include/net/dst_metadata.h @@ -163,8 +163,11 @@ static inline struct metadata_dst *tun_dst_unclone(struct sk_buff *skb) if (!new_md) return ERR_PTR(-ENOMEM); - memcpy(&new_md->u.tun_info, &md_dst->u.tun_info, - sizeof(struct ip_tunnel_info) + md_size); + unsafe_memcpy(&new_md->u.tun_info, &md_dst->u.tun_info, + sizeof(struct ip_tunnel_info) + md_size, + /* metadata_dst_alloc() reserves room (md_size bytes) for + * options right after the ip_tunnel_info struct. + */); #ifdef CONFIG_DST_CACHE /* Unclone the dst cache if there is one */ if (new_md->u.tun_info.dst_cache.cache) { diff --git a/include/net/erspan.h b/include/net/erspan.h index 6cb4cbd6a48f..c6209e7b6c96 100644 --- a/include/net/erspan.h +++ b/include/net/erspan.h @@ -89,7 +89,7 @@ enum erspan_encap_type { ERSPAN_ENCAP_NOVLAN = 0x0, /* originally without VLAN tag */ ERSPAN_ENCAP_ISL = 0x1, /* originally ISL encapsulated */ ERSPAN_ENCAP_8021Q = 0x2, /* originally 802.1Q encapsulated */ - ERSPAN_ENCAP_INFRAME = 0x3, /* VLAN tag perserved in frame */ + ERSPAN_ENCAP_INFRAME = 0x3, /* VLAN tag preserved in frame */ }; #define ERSPAN_V1_MDSIZE 4 @@ -192,7 +192,7 @@ static inline void erspan_build_header(struct sk_buff *skb, enc_type = ERSPAN_ENCAP_NOVLAN; /* If mirrored packet has vlan tag, extract tci and - * perserve vlan header in the mirrored frame. + * preserve vlan header in the mirrored frame. */ if (eth->h_proto == htons(ETH_P_8021Q)) { qp = (struct qtag_prefix *)(skb->data + 2 * ETH_ALEN); diff --git a/include/net/hwbm.h b/include/net/hwbm.h index aa495decec35..bdbe91c609ff 100644 --- a/include/net/hwbm.h +++ b/include/net/hwbm.h @@ -11,9 +11,9 @@ struct hwbm_pool { int frag_size; /* Number of buffers currently used by this pool */ int buf_num; - /* constructor called during alocation */ + /* constructor called during allocation */ int (*construct)(struct hwbm_pool *bm_pool, void *buf); - /* protect acces to the buffer counter*/ + /* protect access to the buffer counter*/ struct mutex buf_lock; /* private data */ void *priv; diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h index 533a7337865a..74dd90ff5f12 100644 --- a/include/net/inet6_hashtables.h +++ b/include/net/inet6_hashtables.h @@ -40,7 +40,7 @@ static inline unsigned int __inet6_ehashfn(const u32 lhash, * * The sockhash lock must be held as a reader here. */ -struct sock *__inet6_lookup_established(struct net *net, +struct sock *__inet6_lookup_established(const struct net *net, struct inet_hashinfo *hashinfo, const struct in6_addr *saddr, const __be16 sport, @@ -56,7 +56,7 @@ inet6_ehashfn_t inet6_ehashfn; INDIRECT_CALLABLE_DECLARE(inet6_ehashfn_t udp6_ehashfn); -struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk, +struct sock *inet6_lookup_reuseport(const struct net *net, struct sock *sk, struct sk_buff *skb, int doff, const struct in6_addr *saddr, __be16 sport, @@ -64,7 +64,7 @@ struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk, unsigned short hnum, inet6_ehashfn_t *ehashfn); -struct sock *inet6_lookup_listener(struct net *net, +struct sock *inet6_lookup_listener(const struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const struct in6_addr *saddr, @@ -73,7 +73,7 @@ struct sock *inet6_lookup_listener(struct net *net, const unsigned short hnum, const int dif, const int sdif); -struct sock *inet6_lookup_run_sk_lookup(struct net *net, +struct sock *inet6_lookup_run_sk_lookup(const struct net *net, int protocol, struct sk_buff *skb, int doff, const struct in6_addr *saddr, @@ -82,7 +82,7 @@ struct sock *inet6_lookup_run_sk_lookup(struct net *net, const u16 hnum, const int dif, inet6_ehashfn_t *ehashfn); -static inline struct sock *__inet6_lookup(struct net *net, +static inline struct sock *__inet6_lookup(const struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const struct in6_addr *saddr, @@ -167,7 +167,7 @@ static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo, iif, sdif, refcounted); } -struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo, +struct sock *inet6_lookup(const struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const __be16 dport, @@ -175,7 +175,7 @@ struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo, int inet6_hash(struct sock *sk); -static inline bool inet6_match(struct net *net, const struct sock *sk, +static inline bool inet6_match(const struct net *net, const struct sock *sk, const struct in6_addr *saddr, const struct in6_addr *daddr, const __portpair ports, diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 7f1b38458743..5eea47f135a4 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -304,7 +304,7 @@ int __inet_hash(struct sock *sk, struct sock *osk); int inet_hash(struct sock *sk); void inet_unhash(struct sock *sk); -struct sock *__inet_lookup_listener(struct net *net, +struct sock *__inet_lookup_listener(const struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const __be32 saddr, const __be16 sport, @@ -351,7 +351,7 @@ static inline struct sock *inet_lookup_listener(struct net *net, ((__force __u64)(__be32)(__saddr))) #endif /* __BIG_ENDIAN */ -static inline bool inet_match(struct net *net, const struct sock *sk, +static inline bool inet_match(const struct net *net, const struct sock *sk, const __addrpair cookie, const __portpair ports, int dif, int sdif) { @@ -368,7 +368,7 @@ static inline bool inet_match(struct net *net, const struct sock *sk, /* Sockets in TCP_CLOSE state are _always_ taken out of the hash, so we need * not check it for lookups anymore, thanks Alexey. -DaveM */ -struct sock *__inet_lookup_established(struct net *net, +struct sock *__inet_lookup_established(const struct net *net, struct inet_hashinfo *hashinfo, const __be32 saddr, const __be16 sport, const __be32 daddr, const u16 hnum, @@ -382,13 +382,13 @@ inet_ehashfn_t inet_ehashfn; INDIRECT_CALLABLE_DECLARE(inet_ehashfn_t udp_ehashfn); -struct sock *inet_lookup_reuseport(struct net *net, struct sock *sk, +struct sock *inet_lookup_reuseport(const struct net *net, struct sock *sk, struct sk_buff *skb, int doff, __be32 saddr, __be16 sport, __be32 daddr, unsigned short hnum, inet_ehashfn_t *ehashfn); -struct sock *inet_lookup_run_sk_lookup(struct net *net, +struct sock *inet_lookup_run_sk_lookup(const struct net *net, int protocol, struct sk_buff *skb, int doff, __be32 saddr, __be16 sport, diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index f9ddd47dc4f8..394c3b66065e 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -150,7 +150,8 @@ static inline bool inet_bound_dev_eq(bool l3mdev_accept, int bound_dev_if, return bound_dev_if == dif || bound_dev_if == sdif; } -static inline bool inet_sk_bound_dev_eq(struct net *net, int bound_dev_if, +static inline bool inet_sk_bound_dev_eq(const struct net *net, + int bound_dev_if, int dif, int sdif) { #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index f88b68269012..beb533a0e880 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -58,7 +58,7 @@ struct inet_timewait_sock { #define tw_dr __tw_common.skc_tw_dr __u32 tw_mark; - volatile unsigned char tw_substate; + unsigned char tw_substate; unsigned char tw_rcv_wscale; /* Socket demultiplex comparisons on incoming packets. */ diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 72af2f223e59..269ec10f63e4 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -22,6 +22,7 @@ #include <linux/percpu.h> #include <linux/notifier.h> #include <linux/refcount.h> +#include <linux/in_route.h> struct fib_config { u8 fc_dst_len; @@ -434,6 +435,11 @@ static inline bool fib4_rules_early_flow_dissect(struct net *net, #endif /* CONFIG_IP_MULTIPLE_TABLES */ +static inline bool fib_dscp_masked_match(dscp_t dscp, const struct flowi4 *fl4) +{ + return dscp == inet_dsfield_to_dscp(RT_TOS(fl4->flowi4_tos)); +} + /* Exported by fib_frontend.c */ extern const struct nla_policy rtm_ipv4_policy[]; void ip_fib_init(void); diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 1db2417b8ff5..6194fbb564c6 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -573,7 +573,7 @@ static inline u8 ip_tunnel_get_ttl(const struct iphdr *iph, return 0; } -/* Propogate ECN bits out */ +/* Propagate ECN bits out */ static inline u8 ip_tunnel_ecn_encap(u8 tos, const struct iphdr *iph, const struct sk_buff *skb) { diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 88a8e554f7a1..248bfb26e2af 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -851,7 +851,7 @@ static inline int __ipv6_addr_diff32(const void *token1, const void *token2, int * we should *never* get to this point since that * would mean the addrs are equal * - * However, we do get to it 8) And exacly, when + * However, we do get to it 8) And exactly, when * addresses are equal 8) * * ip route add 1111::/128 via ... @@ -973,7 +973,7 @@ static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb, hash = skb_get_hash_flowi6(skb, fl6); /* Since this is being sent on the wire obfuscate hash a bit - * to minimize possbility that any useful information to an + * to minimize possibility that any useful information to an * attacker is leaked. Only lower 20 bits are relevant. */ hash = rol32(hash, 16); @@ -1365,4 +1365,16 @@ static inline void ip6_sock_set_recvpktinfo(struct sock *sk) release_sock(sk); } +#define IPV6_ADDR_WORDS 4 + +static inline void ipv6_addr_cpu_to_be32(__be32 *dst, const u32 *src) +{ + cpu_to_be32_array(dst, src, IPV6_ADDR_WORDS); +} + +static inline void ipv6_addr_be32_to_cpu(u32 *dst, const __be32 *src) +{ + be32_to_cpu_array(dst, src, IPV6_ADDR_WORDS); +} + #endif /* _NET_IPV6_H */ diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h index 11cefd50704d..8a3465c8c2c5 100644 --- a/include/net/ipv6_stubs.h +++ b/include/net/ipv6_stubs.h @@ -82,7 +82,7 @@ extern const struct ipv6_stub *ipv6_stub __read_mostly; struct ipv6_bpf_stub { int (*inet6_bind)(struct sock *sk, struct sockaddr *uaddr, int addr_len, u32 flags); - struct sock *(*udp6_lib_lookup)(struct net *net, + struct sock *(*udp6_lib_lookup)(const struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, int dif, int sdif, struct udp_table *tbl, diff --git a/include/net/iucv/iucv.h b/include/net/iucv/iucv.h index 4d114e6d6d23..dd9e93c12260 100644 --- a/include/net/iucv/iucv.h +++ b/include/net/iucv/iucv.h @@ -15,7 +15,7 @@ * To explore any of the IUCV functions, one must first register their * program using iucv_register(). Once your program has successfully * completed a register, it can exploit the other functions. - * For furthur reference on all IUCV functionality, refer to the + * For further reference on all IUCV functionality, refer to the * CP Programming Services book, also available on the web thru * www.vm.ibm.com/pubs, manual # SC24-6084 * diff --git a/include/net/llc_pdu.h b/include/net/llc_pdu.h index 1d55ba7c45be..86681f29bda7 100644 --- a/include/net/llc_pdu.h +++ b/include/net/llc_pdu.h @@ -254,7 +254,7 @@ static inline void llc_pdu_header_init(struct sk_buff *skb, u8 type, } /** - * llc_pdu_decode_sa - extracs source address (MAC) of input frame + * llc_pdu_decode_sa - extracts, source address (MAC) of input frame * @skb: input skb that source address must be extracted from it. * @sa: pointer to source address (6 byte array). * diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index 7caa334f4888..1f869624811d 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -38,9 +38,21 @@ enum TRI_STATE { #define COMP_ENTRY_SIZE 64 -#define RX_BUFFERS_PER_QUEUE 512 +/* This Max value for RX buffers is derived from __alloc_page()'s max page + * allocation calculation. It allows maximum 2^(MAX_ORDER -1) pages. RX buffer + * size beyond this value gets rejected by __alloc_page() call. + */ +#define MAX_RX_BUFFERS_PER_QUEUE 8192 +#define DEF_RX_BUFFERS_PER_QUEUE 512 +#define MIN_RX_BUFFERS_PER_QUEUE 128 -#define MAX_SEND_BUFFERS_PER_QUEUE 256 +/* This max value for TX buffers is derived as the maximum allocatable + * pages supported on host per guest through testing. TX buffer size beyond + * this value is rejected by the hardware. + */ +#define MAX_TX_BUFFERS_PER_QUEUE 16384 +#define DEF_TX_BUFFERS_PER_QUEUE 256 +#define MIN_TX_BUFFERS_PER_QUEUE 128 #define EQ_SIZE (8 * MANA_PAGE_SIZE) @@ -286,7 +298,7 @@ struct mana_recv_buf_oob { void *buf_va; bool from_pool; /* allocated from a page pool */ - /* SGL of the buffer going to be sent has part of the work request. */ + /* SGL of the buffer going to be sent as part of the work request. */ u32 num_sge; struct gdma_sge sgl[MAX_RX_WQE_SGL_ENTRIES]; @@ -438,6 +450,9 @@ struct mana_port_context { unsigned int max_queues; unsigned int num_queues; + unsigned int rx_queue_size; + unsigned int tx_queue_size; + mana_handle_t port_handle; mana_handle_t pf_filter_handle; @@ -473,6 +488,8 @@ 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_pre_alloc_rxbufs(struct mana_port_context *apc, int mtu); +void mana_pre_dealloc_rxbufs(struct mana_port_context *apc); extern const struct ethtool_ops mana_ethtool_ops; diff --git a/include/net/ndisc.h b/include/net/ndisc.h index 7a533d5b1d59..3c88d5bc5eed 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -147,11 +147,6 @@ void __ndisc_fill_addr_option(struct sk_buff *skb, int type, const void *data, * The following hooks can be defined; unless noted otherwise, they are * optional and can be filled with a null pointer. * - * int (*is_useropt)(u8 nd_opt_type): - * This function is called when IPv6 decide RA userspace options. if - * this function returns 1 then the option given by nd_opt_type will - * be handled as userspace option additional to the IPv6 options. - * * int (*parse_options)(const struct net_device *dev, * struct nd_opt_hdr *nd_opt, * struct ndisc_options *ndopts): @@ -200,7 +195,6 @@ void __ndisc_fill_addr_option(struct sk_buff *skb, int type, const void *data, * addresses. E.g. 802.15.4 6LoWPAN. */ struct ndisc_ops { - int (*is_useropt)(u8 nd_opt_type); int (*parse_options)(const struct net_device *dev, struct nd_opt_hdr *nd_opt, struct ndisc_options *ndopts); @@ -224,15 +218,6 @@ struct ndisc_ops { }; #if IS_ENABLED(CONFIG_IPV6) -static inline int ndisc_ops_is_useropt(const struct net_device *dev, - u8 nd_opt_type) -{ - if (dev->ndisc_ops && dev->ndisc_ops->is_useropt) - return dev->ndisc_ops->is_useropt(nd_opt_type); - else - return 0; -} - static inline int ndisc_ops_parse_options(const struct net_device *dev, struct nd_opt_hdr *nd_opt, struct ndisc_options *ndopts) diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 20c34bd7a077..e67b483cc8bb 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -451,8 +451,8 @@ struct pernet_operations { /* Following method is called with RTNL held. */ void (*exit_batch_rtnl)(struct list_head *net_exit_list, struct list_head *dev_kill_list); - unsigned int *id; - size_t size; + unsigned int * const id; + const size_t size; }; /* diff --git a/include/net/netfilter/nf_conntrack_count.h b/include/net/netfilter/nf_conntrack_count.h index e227d997fc71..1b58b5b91ff6 100644 --- a/include/net/netfilter/nf_conntrack_count.h +++ b/include/net/netfilter/nf_conntrack_count.h @@ -15,10 +15,8 @@ struct nf_conncount_list { unsigned int count; /* length of list */ }; -struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int family, - unsigned int keylen); -void nf_conncount_destroy(struct net *net, unsigned int family, - struct nf_conncount_data *data); +struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int keylen); +void nf_conncount_destroy(struct net *net, struct nf_conncount_data *data); unsigned int nf_conncount_count(struct net *net, struct nf_conncount_data *data, diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 1bfdd16890fa..1cc33d946d41 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -221,6 +221,7 @@ struct nft_ctx { u8 family; u8 level; bool report; + DECLARE_BITMAP(reg_inited, NFT_REG32_NUM); }; enum nft_data_desc_flags { @@ -254,7 +255,8 @@ static inline enum nft_registers nft_type_to_reg(enum nft_data_types type) int nft_parse_u32_check(const struct nlattr *attr, int max, u32 *dest); int nft_dump_register(struct sk_buff *skb, unsigned int attr, unsigned int reg); -int nft_parse_register_load(const struct nlattr *attr, u8 *sreg, u32 len); +int nft_parse_register_load(const struct nft_ctx *ctx, + const struct nlattr *attr, u8 *sreg, u32 len); int nft_parse_register_store(const struct nft_ctx *ctx, const struct nlattr *attr, u8 *dreg, const struct nft_data *data, @@ -1674,6 +1676,7 @@ struct nft_trans_rule { struct nft_trans_set { struct nft_trans_binding nft_trans_binding; + struct list_head list_trans_newset; struct nft_set *set; u32 set_id; u32 gc_int; @@ -1875,6 +1878,7 @@ static inline int nft_request_module(struct net *net, const char *fmt, ...) { re struct nftables_pernet { struct list_head tables; struct list_head commit_list; + struct list_head commit_set_list; struct list_head binding_list; struct list_head module_list; struct list_head notify_list; diff --git a/include/net/netlabel.h b/include/net/netlabel.h index 654bc777d2a7..529160f76cac 100644 --- a/include/net/netlabel.h +++ b/include/net/netlabel.h @@ -30,7 +30,7 @@ struct calipso_doi; /* * NetLabel - A management interface for maintaining network packet label - * mapping tables for explicit packet labling protocols. + * mapping tables for explicit packet labeling protocols. * * Network protocols such as CIPSO and RIPSO require a label translation layer * to convert the label on the packet into something meaningful on the host diff --git a/include/net/netlink.h b/include/net/netlink.h index e78ce008e07c..db6af207287c 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -827,7 +827,7 @@ nlmsg_parse_deprecated_strict(const struct nlmsghdr *nlh, int hdrlen, /** * nlmsg_find_attr - find a specific attribute in a netlink message * @nlh: netlink message header - * @hdrlen: length of familiy specific header + * @hdrlen: length of family specific header * @attrtype: type of attribute to look for * * Returns the first attribute which matches the specified type. @@ -849,7 +849,7 @@ static inline struct nlattr *nlmsg_find_attr(const struct nlmsghdr *nlh, * * Validates all attributes in the specified attribute stream against the * specified policy. Validation is done in liberal mode. - * See documenation of struct nla_policy for more details. + * See documentation of struct nla_policy for more details. * * Returns 0 on success or a negative error code. */ @@ -872,7 +872,7 @@ static inline int nla_validate_deprecated(const struct nlattr *head, int len, * * Validates all attributes in the specified attribute stream against the * specified policy. Validation is done in strict mode. - * See documenation of struct nla_policy for more details. + * See documentation of struct nla_policy for more details. * * Returns 0 on success or a negative error code. */ @@ -887,7 +887,7 @@ static inline int nla_validate(const struct nlattr *head, int len, int maxtype, /** * nlmsg_validate_deprecated - validate a netlink message including attributes * @nlh: netlinket message header - * @hdrlen: length of familiy specific header + * @hdrlen: length of family specific header * @maxtype: maximum attribute type to be expected * @policy: validation policy * @extack: extended ACK report struct @@ -933,7 +933,7 @@ static inline u32 nlmsg_seq(const struct nlmsghdr *nlh) * nlmsg_for_each_attr - iterate over a stream of attributes * @pos: loop counter, set to current attribute * @nlh: netlink message header - * @hdrlen: length of familiy specific header + * @hdrlen: length of family specific header * @rem: initialized to len, holds bytes currently remaining in stream */ #define nlmsg_for_each_attr(pos, nlh, hdrlen, rem) \ @@ -1034,7 +1034,7 @@ static inline struct sk_buff *nlmsg_new_large(size_t payload) * @skb: socket buffer the message is stored in * @nlh: netlink message header * - * Corrects the netlink message header to include the appeneded + * Corrects the netlink message header to include the appended * attributes. Only necessary if attributes have been added to * the message. */ @@ -1954,7 +1954,7 @@ static inline struct nlattr *nla_nest_start(struct sk_buff *skb, int attrtype) * @start: container attribute * * Corrects the container attribute header to include the all - * appeneded attributes. + * appended attributes. * * Returns the total data length of the skb. */ @@ -1987,7 +1987,7 @@ static inline void nla_nest_cancel(struct sk_buff *skb, struct nlattr *start) * * Validates all attributes in the nested attribute stream against the * specified policy. Attributes with a type exceeding maxtype will be - * ignored. See documenation of struct nla_policy for more details. + * ignored. See documentation of struct nla_policy for more details. * * Returns 0 on success or a negative error code. */ diff --git a/include/net/netns/sctp.h b/include/net/netns/sctp.h index 7eff3d981b89..d25cd7a9c5ff 100644 --- a/include/net/netns/sctp.h +++ b/include/net/netns/sctp.h @@ -125,14 +125,14 @@ struct netns_sctp { int pf_expose; /* - * Policy for preforming sctp/socket accounting + * Policy for performing sctp/socket accounting * 0 - do socket level accounting, all assocs share sk_sndbuf * 1 - do sctp accounting, each asoc may use sk_sndbuf bytes */ int sndbuf_policy; /* - * Policy for preforming sctp/socket accounting + * Policy for performing sctp/socket accounting * 0 - do socket level accounting, all assocs share sk_rcvbuf * 1 - do sctp accounting, each asoc may use sk_rcvbuf bytes */ diff --git a/include/net/nexthop.h b/include/net/nexthop.h index 68463aebcc05..d9fb44e8b321 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -105,7 +105,7 @@ struct nh_grp_entry_stats { struct nh_grp_entry { struct nexthop *nh; struct nh_grp_entry_stats __percpu *stats; - u8 weight; + u16 weight; union { struct { @@ -192,7 +192,7 @@ struct nh_notifier_single_info { }; struct nh_notifier_grp_entry_info { - u8 weight; + u16 weight; struct nh_notifier_single_info nh; }; diff --git a/include/net/nfc/nci.h b/include/net/nfc/nci.h index e82f55f543bb..dc36519d16aa 100644 --- a/include/net/nfc/nci.h +++ b/include/net/nfc/nci.h @@ -332,7 +332,7 @@ struct nci_core_init_rsp_1 { __le32 nfcc_features; __u8 num_supported_rf_interfaces; __u8 supported_rf_interfaces[]; /* variable size array */ - /* continuted in nci_core_init_rsp_2 */ + /* continued in nci_core_init_rsp_2 */ } __packed; struct nci_core_init_rsp_2 { diff --git a/include/net/nfc/nfc.h b/include/net/nfc/nfc.h index 3d07abacf08b..3a3781838c67 100644 --- a/include/net/nfc/nfc.h +++ b/include/net/nfc/nfc.h @@ -80,7 +80,7 @@ struct nfc_ops { #define NFC_ATR_REQ_GT_OFFSET 14 /** - * struct nfc_target - NFC target descriptiom + * struct nfc_target - NFC target description * * @sens_res: 2 bytes describing the target SENS_RES response, if the target * is a type A one. The %sens_res most significant byte must be byte 2 @@ -230,10 +230,10 @@ static inline void nfc_set_parent_dev(struct nfc_dev *nfc_dev, } /** - * nfc_set_drvdata - set driver specifc data + * nfc_set_drvdata - set driver specific data * * @dev: The nfc device - * @data: Pointer to driver specifc data + * @data: Pointer to driver specific data */ static inline void nfc_set_drvdata(struct nfc_dev *dev, void *data) { @@ -241,7 +241,7 @@ static inline void nfc_set_drvdata(struct nfc_dev *dev, void *data) } /** - * nfc_get_drvdata - get driver specifc data + * nfc_get_drvdata - get driver specific data * * @dev: The nfc device */ diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 41297bd38dff..4880b3a7aced 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -491,7 +491,7 @@ int __tcf_em_tree_match(struct sk_buff *, struct tcf_ematch_tree *, struct tcf_pkt_info *); /** - * tcf_em_tree_match - evaulate an ematch tree + * tcf_em_tree_match - evaluate an ematch tree * * @skb: socket buffer of the packet in question * @tree: ematch tree to be used for evaluation diff --git a/include/net/red.h b/include/net/red.h index 802287d52c9e..159a09359fc0 100644 --- a/include/net/red.h +++ b/include/net/red.h @@ -40,7 +40,7 @@ max_P should be small (not 1), usually 0.01..0.02 is good value. max_P is chosen as a number, so that max_P/(th_max-th_min) - is a negative power of two in order arithmetics to contain + is a negative power of two in order arithmetic to contain only shifts. @@ -159,7 +159,7 @@ static inline u32 red_maxp(u8 Plog) static inline void red_set_vars(struct red_vars *v) { /* Reset average queue length, the value is strictly bound - * to the parameters below, reseting hurts a bit but leaving + * to the parameters below, resetting hurts a bit but leaving * it might result in an unreasonable qavg for a while. --TGR */ v->qavg = 0; @@ -340,7 +340,7 @@ static inline unsigned long red_calc_qavg_no_idle_time(const struct red_parms *p { /* * NOTE: v->qavg is fixed point number with point at Wlog. - * The formula below is equvalent to floating point + * The formula below is equivalent to floating point * version: * * qavg = qavg*(1-W) + backlog*W; @@ -375,7 +375,7 @@ static inline int red_mark_probability(const struct red_parms *p, OK. qR is random number in the interval (0..1/max_P)*(qth_max-qth_min) i.e. 0..(2^Plog). If we used floating point - arithmetics, it would be: (2^Plog)*rnd_num, + arithmetic, it would be: (2^Plog)*rnd_num, where rnd_num is less 1. Taking into account, that qavg have fixed diff --git a/include/net/regulatory.h b/include/net/regulatory.h index a103f4c8cf75..6633627f6e76 100644 --- a/include/net/regulatory.h +++ b/include/net/regulatory.h @@ -121,7 +121,7 @@ struct regulatory_request { * @REGULATORY_DISABLE_BEACON_HINTS: enable this if your driver needs to * ensure that passive scan flags and beaconing flags may not be lifted by * cfg80211 due to regulatory beacon hints. For more information on beacon - * hints read the documenation for regulatory_hint_found_beacon() + * hints read the documentation for regulatory_hint_found_beacon() * @REGULATORY_COUNTRY_IE_FOLLOW_POWER: for devices that have a preference * that even though they may have programmed their own custom power * setting prior to wiphy registration, they want to ensure their channel diff --git a/include/net/rstreason.h b/include/net/rstreason.h index 2575c85d7f7a..69cb2e52b7da 100644 --- a/include/net/rstreason.h +++ b/include/net/rstreason.h @@ -17,6 +17,12 @@ FN(TCP_ABORT_ON_DATA) \ FN(TCP_TIMEWAIT_SOCKET) \ FN(INVALID_SYN) \ + FN(TCP_ABORT_ON_CLOSE) \ + FN(TCP_ABORT_ON_LINGER) \ + FN(TCP_ABORT_ON_MEMORY) \ + FN(TCP_STATE) \ + FN(TCP_KEEPALIVE_TIMEOUT) \ + FN(TCP_DISCONNECT_WITH_DATA) \ FN(MPTCP_RST_EUNSPEC) \ FN(MPTCP_RST_EMPTCP) \ FN(MPTCP_RST_ERESOURCE) \ @@ -84,6 +90,39 @@ enum sk_rst_reason { * an error, send a reset" */ SK_RST_REASON_INVALID_SYN, + /** + * @SK_RST_REASON_TCP_ABORT_ON_CLOSE: abort on close + * corresponding to LINUX_MIB_TCPABORTONCLOSE + */ + SK_RST_REASON_TCP_ABORT_ON_CLOSE, + /** + * @SK_RST_REASON_TCP_ABORT_ON_LINGER: abort on linger + * corresponding to LINUX_MIB_TCPABORTONLINGER + */ + SK_RST_REASON_TCP_ABORT_ON_LINGER, + /** + * @SK_RST_REASON_TCP_ABORT_ON_MEMORY: abort on memory + * corresponding to LINUX_MIB_TCPABORTONMEMORY + */ + SK_RST_REASON_TCP_ABORT_ON_MEMORY, + /** + * @SK_RST_REASON_TCP_STATE: abort on tcp state + * Please see RFC 9293 for all possible reset conditions + */ + SK_RST_REASON_TCP_STATE, + /** + * @SK_RST_REASON_TCP_KEEPALIVE_TIMEOUT: time to timeout + * When we have already run out of all the chances, which means + * keepalive timeout, we have to reset the connection + */ + SK_RST_REASON_TCP_KEEPALIVE_TIMEOUT, + /** + * @SK_RST_REASON_TCP_DISCONNECT_WITH_DATA: disconnect when write + * queue is not empty + * It means user has written data into the write queue when doing + * disconnecting, so we have to send an RST. + */ + SK_RST_REASON_TCP_DISCONNECT_WITH_DATA, /* Copy from include/uapi/linux/mptcp.h. * These reset fields will not be changed since they adhere to diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index a2310fa995f6..84e6b9fd5610 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -28,7 +28,7 @@ #define __net_sctp_h__ /* Header Strategy. - * Start getting some control over the header file depencies: + * Start getting some control over the header file dependencies: * includes * constants * structs diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index f24a1bbcb3ef..31248cfdfb23 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -521,7 +521,7 @@ struct sctp_datamsg { refcount_t refcnt; /* When is this message no longer interesting to the peer? */ unsigned long expires_at; - /* Did the messenge fail to send? */ + /* Did the message fail to send? */ int send_error; u8 send_failed:1, can_delay:1, /* should this message be Nagle delayed */ @@ -792,7 +792,7 @@ struct sctp_transport { */ hb_sent:1, - /* Is the Path MTU update pending on this tranport */ + /* Is the Path MTU update pending on this transport */ pmtu_pending:1, dst_pending_confirm:1, /* need to confirm neighbour */ @@ -1223,7 +1223,7 @@ enum sctp_endpoint_type { }; /* - * A common base class to bridge the implmentation view of a + * A common base class to bridge the implementation view of a * socket (usually listening) endpoint versus an association's * local endpoint. * This common structure is useful for several purposes: @@ -1353,7 +1353,7 @@ struct sctp_endpoint { struct rcu_head rcu; }; -/* Recover the outter endpoint structure. */ +/* Recover the outer endpoint structure. */ static inline struct sctp_endpoint *sctp_ep(struct sctp_ep_common *base) { struct sctp_endpoint *ep; @@ -1906,7 +1906,7 @@ struct sctp_association { __u32 rwnd_over; /* Keeps treack of rwnd pressure. This happens when we have - * a window, but not recevie buffer (i.e small packets). This one + * a window, but not receive buffer (i.e small packets). This one * is releases slowly (1 PMTU at a time ). */ __u32 rwnd_press; @@ -1994,7 +1994,7 @@ struct sctp_association { /* ADDIP Section 5.2 Upon reception of an ASCONF Chunk. * - * This is needed to implement itmes E1 - E4 of the updated + * This is needed to implement items E1 - E4 of the updated * spec. Here is the justification: * * Since the peer may bundle multiple ASCONF chunks toward us, @@ -2005,7 +2005,7 @@ struct sctp_association { /* These ASCONF chunks are waiting to be sent. * - * These chunaks can't be pushed to outqueue until receiving + * These chunks can't be pushed to outqueue until receiving * ASCONF_ACK for the previous ASCONF indicated by * addip_last_asconf, so as to guarantee that only one ASCONF * is in flight at any time. @@ -2059,13 +2059,13 @@ struct sctp_association { struct sctp_transport *new_transport; /* SCTP AUTH: list of the endpoint shared keys. These - * keys are provided out of band by the user applicaton + * keys are provided out of band by the user application * and can't change during the lifetime of the association */ struct list_head endpoint_shared_keys; /* SCTP AUTH: - * The current generated assocaition shared key (secret) + * The current generated association shared key (secret) */ struct sctp_auth_bytes *asoc_shared_key; struct sctp_shared_key *shkey; @@ -2121,7 +2121,7 @@ enum { SCTP_ASSOC_EYECATCHER = 0xa550c123, }; -/* Recover the outter association structure. */ +/* Recover the outer association structure. */ static inline struct sctp_association *sctp_assoc(struct sctp_ep_common *base) { struct sctp_association *asoc; diff --git a/include/net/sock.h b/include/net/sock.h index cce23ac4d514..f51d61fab059 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1624,7 +1624,7 @@ bool __lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock); * lock_sock_fast - fast version of lock_sock * @sk: socket * - * This version should be used for very small section, where process wont block + * This version should be used for very small section, where process won't block * return false if fast path is taken: * * sk_lock.slock locked, owned = 0, BH disabled @@ -2546,7 +2546,7 @@ struct sock_skb_cb { /* Store sock_skb_cb at the end of skb->cb[] so protocol families * using skb->cb[] would keep using it directly and utilize its - * alignement guarantee. + * alignment guarantee. */ #define SOCK_SKB_CB_OFFSET ((sizeof_field(struct sk_buff, cb) - \ sizeof(struct sock_skb_cb))) diff --git a/include/net/sock_reuseport.h b/include/net/sock_reuseport.h index 6ec140b0a61b..6e4faf3ee76f 100644 --- a/include/net/sock_reuseport.h +++ b/include/net/sock_reuseport.h @@ -26,7 +26,7 @@ struct sock_reuseport { unsigned int bind_inany:1; unsigned int has_conns:1; struct bpf_prog __rcu *prog; /* optional BPF sock selector */ - struct sock *socks[]; /* array of sock pointers */ + struct sock *socks[] __counted_by(max_socks); }; extern int reuseport_alloc(struct sock *sk, bool bind_inany); diff --git a/include/net/udp.h b/include/net/udp.h index c4e05b14b648..61222545ab1c 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -79,7 +79,8 @@ struct udp_table { extern struct udp_table udp_table; void udp_table_init(struct udp_table *, const char *); static inline struct udp_hslot *udp_hashslot(struct udp_table *table, - struct net *net, unsigned int num) + const struct net *net, + unsigned int num) { return &table->hash[udp_hashfn(net, num, table->mask)]; } @@ -231,7 +232,7 @@ static inline __be16 udp_flow_src_port(struct net *net, struct sk_buff *skb, } /* Since this is being sent on the wire obfuscate hash a bit - * to minimize possbility that any useful information to an + * to minimize possibility that any useful information to an * attacker is leaked. Only upper 16 bits are relevant in the * computation for 16 bit port value. */ @@ -245,7 +246,7 @@ static inline int udp_rqueue_get(struct sock *sk) return sk_rmem_alloc_get(sk) - READ_ONCE(udp_sk(sk)->forward_deficit); } -static inline bool udp_sk_bound_dev_eq(struct net *net, int bound_dev_if, +static inline bool udp_sk_bound_dev_eq(const struct net *net, int bound_dev_if, int dif, int sdif) { #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) @@ -296,18 +297,19 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname, int udp_lib_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen, int (*push_pending_frames)(struct sock *)); -struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, +struct sock *udp4_lib_lookup(const struct net *net, __be32 saddr, __be16 sport, __be32 daddr, __be16 dport, int dif); -struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, +struct sock *__udp4_lib_lookup(const struct net *net, __be32 saddr, + __be16 sport, __be32 daddr, __be16 dport, int dif, int sdif, struct udp_table *tbl, struct sk_buff *skb); struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb, __be16 sport, __be16 dport); -struct sock *udp6_lib_lookup(struct net *net, +struct sock *udp6_lib_lookup(const struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, int dif); -struct sock *__udp6_lib_lookup(struct net *net, +struct sock *__udp6_lib_lookup(const struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, int dif, int sdif, struct udp_table *tbl, diff --git a/include/net/x25.h b/include/net/x25.h index 597eb53c471e..5e833cfc864e 100644 --- a/include/net/x25.h +++ b/include/net/x25.h @@ -81,7 +81,7 @@ enum { #define X25_DEFAULT_WINDOW_SIZE 2 /* Default Window Size */ #define X25_DEFAULT_PACKET_SIZE X25_PS128 /* Default Packet Size */ -#define X25_DEFAULT_THROUGHPUT 0x0A /* Deafult Throughput */ +#define X25_DEFAULT_THROUGHPUT 0x0A /* Default Throughput */ #define X25_DEFAULT_REVERSE 0x00 /* Default Reverse Charging */ #define X25_SMODULUS 8 diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 35bcf52dbc65..e05b39e39c3f 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2851,7 +2851,7 @@ union bpf_attr { * **TCP_SYNCNT**, **TCP_USER_TIMEOUT**, **TCP_NOTSENT_LOWAT**, * **TCP_NODELAY**, **TCP_MAXSEG**, **TCP_WINDOW_CLAMP**, * **TCP_THIN_LINEAR_TIMEOUTS**, **TCP_BPF_DELACK_MAX**, - * **TCP_BPF_RTO_MIN**. + * **TCP_BPF_RTO_MIN**, **TCP_BPF_SOCK_OPS_CB_FLAGS**. * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. * * **IPPROTO_IPV6**, which supports the following *optname*\ s: * **IPV6_TCLASS**, **IPV6_AUTOFLOWLABEL**. @@ -7080,6 +7080,7 @@ enum { TCP_BPF_SYN = 1005, /* Copy the TCP header */ TCP_BPF_SYN_IP = 1006, /* Copy the IP[46] and TCP header */ 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 */ }; enum { diff --git a/include/uapi/linux/dpll.h b/include/uapi/linux/dpll.h index 0c13d7f1a1bc..b0654ade7b7e 100644 --- a/include/uapi/linux/dpll.h +++ b/include/uapi/linux/dpll.h @@ -210,6 +210,9 @@ enum dpll_a_pin { DPLL_A_PIN_PHASE_ADJUST, DPLL_A_PIN_PHASE_OFFSET, DPLL_A_PIN_FRACTIONAL_FREQUENCY_OFFSET, + DPLL_A_PIN_ESYNC_FREQUENCY, + DPLL_A_PIN_ESYNC_FREQUENCY_SUPPORTED, + DPLL_A_PIN_ESYNC_PULSE, __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 4a0a6e703483..c405ed63acfa 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -2533,4 +2533,20 @@ struct ethtool_link_settings { * __u32 map_lp_advertising[link_mode_masks_nwords]; */ }; + +/** + * enum phy_upstream - Represents the upstream component a given PHY device + * is connected to, as in what is on the other end of the MII bus. Most PHYs + * will be attached to an Ethernet MAC controller, but in some cases, there's + * an intermediate PHY used as a media-converter, which will driver another + * MII interface as its output. + * @PHY_UPSTREAM_MAC: Upstream component is a MAC (a switch port, + * or ethernet controller) + * @PHY_UPSTREAM_PHY: Upstream component is a PHY (likely a media converter) + */ +enum phy_upstream { + PHY_UPSTREAM_MAC, + PHY_UPSTREAM_PHY, +}; + #endif /* _UAPI_LINUX_ETHTOOL_H */ diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 6d5bdcc67631..283305f6b063 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -58,6 +58,7 @@ enum { ETHTOOL_MSG_MM_GET, ETHTOOL_MSG_MM_SET, ETHTOOL_MSG_MODULE_FW_FLASH_ACT, + ETHTOOL_MSG_PHY_GET, /* add new constants above here */ __ETHTOOL_MSG_USER_CNT, @@ -111,6 +112,8 @@ enum { ETHTOOL_MSG_MM_GET_REPLY, ETHTOOL_MSG_MM_NTF, ETHTOOL_MSG_MODULE_FW_FLASH_NTF, + ETHTOOL_MSG_PHY_GET_REPLY, + ETHTOOL_MSG_PHY_NTF, /* add new constants above here */ __ETHTOOL_MSG_KERNEL_CNT, @@ -134,6 +137,7 @@ enum { ETHTOOL_A_HEADER_DEV_INDEX, /* u32 */ ETHTOOL_A_HEADER_DEV_NAME, /* string */ ETHTOOL_A_HEADER_FLAGS, /* u32 - ETHTOOL_FLAG_* */ + ETHTOOL_A_HEADER_PHY_INDEX, /* u32 */ /* add new constants above here */ __ETHTOOL_A_HEADER_CNT, @@ -556,6 +560,10 @@ enum { * a regular 100 Ohm cable and a part with the abnormal impedance value */ ETHTOOL_A_CABLE_RESULT_CODE_IMPEDANCE_MISMATCH, + /* TDR not possible due to high noise level */ + ETHTOOL_A_CABLE_RESULT_CODE_NOISE, + /* TDR resolution not possible / out of distance */ + ETHTOOL_A_CABLE_RESULT_CODE_RESOLUTION_NOT_POSSIBLE, }; enum { @@ -565,10 +573,20 @@ enum { ETHTOOL_A_CABLE_PAIR_D, }; +/* Information source for specific results. */ +enum { + ETHTOOL_A_CABLE_INF_SRC_UNSPEC, + /* Results provided by the Time Domain Reflectometry (TDR) */ + ETHTOOL_A_CABLE_INF_SRC_TDR, + /* Results provided by the Active Link Cable Diagnostic (ALCD) */ + ETHTOOL_A_CABLE_INF_SRC_ALCD, +}; + enum { ETHTOOL_A_CABLE_RESULT_UNSPEC, ETHTOOL_A_CABLE_RESULT_PAIR, /* u8 ETHTOOL_A_CABLE_PAIR_ */ ETHTOOL_A_CABLE_RESULT_CODE, /* u8 ETHTOOL_A_CABLE_RESULT_CODE_ */ + ETHTOOL_A_CABLE_RESULT_SRC, /* u32 ETHTOOL_A_CABLE_INF_SRC_ */ __ETHTOOL_A_CABLE_RESULT_CNT, ETHTOOL_A_CABLE_RESULT_MAX = (__ETHTOOL_A_CABLE_RESULT_CNT - 1) @@ -578,6 +596,7 @@ enum { ETHTOOL_A_CABLE_FAULT_LENGTH_UNSPEC, ETHTOOL_A_CABLE_FAULT_LENGTH_PAIR, /* u8 ETHTOOL_A_CABLE_PAIR_ */ ETHTOOL_A_CABLE_FAULT_LENGTH_CM, /* u32 */ + ETHTOOL_A_CABLE_FAULT_LENGTH_SRC, /* u32 ETHTOOL_A_CABLE_INF_SRC_ */ __ETHTOOL_A_CABLE_FAULT_LENGTH_CNT, ETHTOOL_A_CABLE_FAULT_LENGTH_MAX = (__ETHTOOL_A_CABLE_FAULT_LENGTH_CNT - 1) @@ -965,6 +984,7 @@ enum { ETHTOOL_A_RSS_INDIR, /* binary */ ETHTOOL_A_RSS_HKEY, /* binary */ ETHTOOL_A_RSS_INPUT_XFRM, /* u32 */ + ETHTOOL_A_RSS_START_CONTEXT, /* u32 */ __ETHTOOL_A_RSS_CNT, ETHTOOL_A_RSS_MAX = (__ETHTOOL_A_RSS_CNT - 1), @@ -1049,6 +1069,22 @@ enum { ETHTOOL_A_MODULE_FW_FLASH_MAX = (__ETHTOOL_A_MODULE_FW_FLASH_CNT - 1) }; +enum { + ETHTOOL_A_PHY_UNSPEC, + ETHTOOL_A_PHY_HEADER, /* nest - _A_HEADER_* */ + ETHTOOL_A_PHY_INDEX, /* u32 */ + ETHTOOL_A_PHY_DRVNAME, /* string */ + ETHTOOL_A_PHY_NAME, /* string */ + ETHTOOL_A_PHY_UPSTREAM_TYPE, /* u32 */ + ETHTOOL_A_PHY_UPSTREAM_INDEX, /* u32 */ + ETHTOOL_A_PHY_UPSTREAM_SFP_NAME, /* string */ + ETHTOOL_A_PHY_DOWNSTREAM_SFP_NAME, /* string */ + + /* add new constants above here */ + __ETHTOOL_A_PHY_CNT, + ETHTOOL_A_PHY_MAX = (__ETHTOOL_A_PHY_CNT - 1) +}; + /* generic netlink info */ #define ETHTOOL_GENL_NAME "ethtool" #define ETHTOOL_GENL_VERSION 1 diff --git a/include/uapi/linux/if_packet.h b/include/uapi/linux/if_packet.h index 9efc42382fdb..1d2718dd9647 100644 --- a/include/uapi/linux/if_packet.h +++ b/include/uapi/linux/if_packet.h @@ -230,8 +230,8 @@ struct tpacket_hdr_v1 { * ts_first_pkt: * Is always the time-stamp when the block was opened. * Case a) ZERO packets - * No packets to deal with but atleast you know the - * time-interval of this block. + * No packets to deal with but at least you know + * the time-interval of this block. * Case b) Non-zero packets * Use the ts of the first packet in the block. * @@ -265,7 +265,8 @@ enum tpacket_versions { - struct tpacket_hdr - pad to TPACKET_ALIGNMENT=16 - struct sockaddr_ll - - Gap, chosen so that packet data (Start+tp_net) alignes to TPACKET_ALIGNMENT=16 + - Gap, chosen so that packet data (Start+tp_net) aligns to + TPACKET_ALIGNMENT=16 - Start+tp_mac: [ Optional MAC header ] - Start+tp_net: Packet data, aligned to TPACKET_ALIGNMENT=16. - Pad to align to TPACKET_ALIGNMENT=16 diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h index d358add1611c..5d32d53508d9 100644 --- a/include/uapi/linux/in.h +++ b/include/uapi/linux/in.h @@ -141,7 +141,7 @@ struct in_addr { */ #define IP_PMTUDISC_INTERFACE 4 /* weaker version of IP_PMTUDISC_INTERFACE, which allows packets to get - * fragmented if they exeed the interface mtu + * fragmented if they exceed the interface mtu */ #define IP_PMTUDISC_OMIT 5 diff --git a/include/uapi/linux/in_route.h b/include/uapi/linux/in_route.h index 0cc2c23b47f8..10bdd7e7107f 100644 --- a/include/uapi/linux/in_route.h +++ b/include/uapi/linux/in_route.h @@ -2,6 +2,8 @@ #ifndef _LINUX_IN_ROUTE_H #define _LINUX_IN_ROUTE_H +#include <linux/ip.h> + /* IPv4 routing cache flags */ #define RTCF_DEAD RTNH_F_DEAD diff --git a/include/uapi/linux/inet_diag.h b/include/uapi/linux/inet_diag.h index 50655de04c9b..86bb2e8b17c9 100644 --- a/include/uapi/linux/inet_diag.h +++ b/include/uapi/linux/inet_diag.h @@ -143,7 +143,7 @@ enum { INET_DIAG_SHUTDOWN, /* - * Next extenstions cannot be requested in struct inet_diag_req_v2: + * Next extensions cannot be requested in struct inet_diag_req_v2: * its field idiag_ext has only 8 bits. */ diff --git a/include/uapi/linux/ioam6_iptunnel.h b/include/uapi/linux/ioam6_iptunnel.h index 38f6a8fdfd34..8aef21e4a8c1 100644 --- a/include/uapi/linux/ioam6_iptunnel.h +++ b/include/uapi/linux/ioam6_iptunnel.h @@ -50,6 +50,12 @@ enum { IOAM6_IPTUNNEL_FREQ_K, /* u32 */ IOAM6_IPTUNNEL_FREQ_N, /* u32 */ + /* Tunnel src address. + * For encap,auto modes. + * Optional (automatic if not provided). + */ + IOAM6_IPTUNNEL_SRC, /* struct in6_addr */ + __IOAM6_IPTUNNEL_MAX, }; diff --git a/include/uapi/linux/nexthop.h b/include/uapi/linux/nexthop.h index dd8787f9cf39..bc49baf4a267 100644 --- a/include/uapi/linux/nexthop.h +++ b/include/uapi/linux/nexthop.h @@ -16,10 +16,15 @@ struct nhmsg { struct nexthop_grp { __u32 id; /* nexthop id - must exist */ __u8 weight; /* weight of this nexthop */ - __u8 resvd1; + __u8 weight_high; /* high order bits of weight */ __u16 resvd2; }; +static inline __u16 nexthop_grp_weight(const struct nexthop_grp *entry) +{ + return ((entry->weight_high << 8) | entry->weight) + 1; +} + enum { NEXTHOP_GRP_TYPE_MPATH, /* hash-threshold nexthop group * default type if not specified @@ -33,6 +38,9 @@ enum { #define NHA_OP_FLAG_DUMP_STATS BIT(0) #define NHA_OP_FLAG_DUMP_HW_STATS BIT(1) +/* Response OP_FLAGS. */ +#define NHA_OP_FLAG_RESP_GRP_RESVD_0 BIT(31) /* Dump clears resvd fields. */ + enum { NHA_UNSPEC, NHA_ID, /* u32; id for nexthop. id == 0 means auto-assign */ diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index d36d9cdf0c00..2c32080416b5 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -246,16 +246,19 @@ struct tc_u32_key { }; struct tc_u32_sel { - unsigned char flags; - unsigned char offshift; - unsigned char nkeys; - - __be16 offmask; - __u16 off; - short offoff; - - short hoff; - __be32 hmask; + /* New members MUST be added within the __struct_group() macro below. */ + __struct_group(tc_u32_sel_hdr, hdr, /* no attrs */, + unsigned char flags; + unsigned char offshift; + unsigned char nkeys; + + __be16 offmask; + __u16 off; + short offoff; + + short hoff; + __be32 hmask; + ); struct tc_u32_key keys[]; }; diff --git a/include/uapi/linux/smc.h b/include/uapi/linux/smc.h index b531e3ef011a..1f58cb0c266b 100644 --- a/include/uapi/linux/smc.h +++ b/include/uapi/linux/smc.h @@ -127,6 +127,8 @@ enum { SMC_NLA_LGR_R_NET_COOKIE, /* u64 */ SMC_NLA_LGR_R_PAD, /* flag */ SMC_NLA_LGR_R_BUF_TYPE, /* u8 */ + SMC_NLA_LGR_R_SNDBUF_ALLOC, /* uint */ + SMC_NLA_LGR_R_RMB_ALLOC, /* uint */ __SMC_NLA_LGR_R_MAX, SMC_NLA_LGR_R_MAX = __SMC_NLA_LGR_R_MAX - 1 }; @@ -162,6 +164,8 @@ enum { SMC_NLA_LGR_D_V2_COMMON, /* nest */ SMC_NLA_LGR_D_EXT_GID, /* u64 */ SMC_NLA_LGR_D_PEER_EXT_GID, /* u64 */ + SMC_NLA_LGR_D_SNDBUF_ALLOC, /* uint */ + SMC_NLA_LGR_D_DMB_ALLOC, /* uint */ __SMC_NLA_LGR_D_MAX, SMC_NLA_LGR_D_MAX = __SMC_NLA_LGR_D_MAX - 1 }; @@ -249,6 +253,8 @@ enum { SMC_NLA_STATS_T_TX_BYTES, /* u64 */ SMC_NLA_STATS_T_RX_CNT, /* u64 */ SMC_NLA_STATS_T_TX_CNT, /* u64 */ + SMC_NLA_STATS_T_RX_RMB_USAGE, /* uint */ + SMC_NLA_STATS_T_TX_RMB_USAGE, /* uint */ __SMC_NLA_STATS_T_MAX, SMC_NLA_STATS_T_MAX = __SMC_NLA_STATS_T_MAX - 1 }; diff --git a/net/6lowpan/ndisc.c b/net/6lowpan/ndisc.c index 16be8f8b2f8c..c40b98f7743c 100644 --- a/net/6lowpan/ndisc.c +++ b/net/6lowpan/ndisc.c @@ -11,11 +11,6 @@ #include "6lowpan_i.h" -static int lowpan_ndisc_is_useropt(u8 nd_opt_type) -{ - return nd_opt_type == ND_OPT_6CO; -} - #if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN) #define NDISC_802154_SHORT_ADDR_LENGTH 1 static int lowpan_ndisc_parse_802154_options(const struct net_device *dev, @@ -222,7 +217,6 @@ static void lowpan_ndisc_prefix_rcv_add_addr(struct net *net, #endif const struct ndisc_ops lowpan_ndisc_ops = { - .is_useropt = lowpan_ndisc_is_useropt, #if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN) .parse_options = lowpan_ndisc_parse_options, .update = lowpan_ndisc_update, diff --git a/net/bridge/netfilter/nft_meta_bridge.c b/net/bridge/netfilter/nft_meta_bridge.c index bd4d1b4d745f..4d8e15927217 100644 --- a/net/bridge/netfilter/nft_meta_bridge.c +++ b/net/bridge/netfilter/nft_meta_bridge.c @@ -142,7 +142,7 @@ static int nft_meta_bridge_set_init(const struct nft_ctx *ctx, } priv->len = len; - err = nft_parse_register_load(tb[NFTA_META_SREG], &priv->sreg, len); + err = nft_parse_register_load(ctx, tb[NFTA_META_SREG], &priv->sreg, len); if (err < 0) return err; diff --git a/net/caif/cfpkt_skbuff.c b/net/caif/cfpkt_skbuff.c index 2ae8cfa3df88..96236d21b18e 100644 --- a/net/caif/cfpkt_skbuff.c +++ b/net/caif/cfpkt_skbuff.c @@ -298,10 +298,8 @@ struct cfpkt *cfpkt_append(struct cfpkt *dstpkt, if (unlikely(is_erronous(dstpkt) || is_erronous(addpkt))) { return dstpkt; } - if (expectlen > addlen) - neededtailspace = expectlen; - else - neededtailspace = addlen; + + neededtailspace = max(expectlen, addlen); if (dst->tail + neededtailspace > dst->end) { /* Create a dumplicate of 'dst' with more tail space */ diff --git a/net/core/dev.c b/net/core/dev.c index f66e61407883..63987b8b7c85 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -158,6 +158,7 @@ #include <net/page_pool/types.h> #include <net/page_pool/helpers.h> #include <net/rps.h> +#include <linux/phy_link_topology.h> #include "dev.h" #include "net-sysfs.h" @@ -3386,6 +3387,7 @@ int skb_crc32c_csum_help(struct sk_buff *skb) out: return ret; } +EXPORT_SYMBOL(skb_crc32c_csum_help); __be16 skb_network_protocol(struct sk_buff *skb, int *depth) { @@ -3705,7 +3707,7 @@ struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *d next = skb->next; skb_mark_not_on_list(skb); - /* in case skb wont be segmented, point to itself */ + /* in case skb won't be segmented, point to itself */ skb->prev = skb; skb = validate_xmit_skb(skb, dev, again); @@ -9369,6 +9371,15 @@ u8 dev_xdp_prog_count(struct net_device *dev) } EXPORT_SYMBOL_GPL(dev_xdp_prog_count); +int dev_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf) +{ + if (!dev->netdev_ops->ndo_bpf) + return -EOPNOTSUPP; + + return dev->netdev_ops->ndo_bpf(dev, bpf); +} +EXPORT_SYMBOL_GPL(dev_xdp_propagate); + u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode) { struct bpf_prog *prog = dev_xdp_prog(dev, mode); @@ -10321,6 +10332,17 @@ static void netdev_do_free_pcpu_stats(struct net_device *dev) } } +static void netdev_free_phy_link_topology(struct net_device *dev) +{ + struct phy_link_topology *topo = dev->link_topo; + + if (IS_ENABLED(CONFIG_PHYLIB) && topo) { + xa_destroy(&topo->phys); + kfree(topo); + dev->link_topo = NULL; + } +} + /** * register_netdevice() - register a network device * @dev: device to register @@ -10868,7 +10890,7 @@ noinline void netdev_core_stats_inc(struct net_device *dev, u32 offset) return; } - field = (__force unsigned long __percpu *)((__force void *)p + offset); + field = (unsigned long __percpu *)((void __percpu *)p + offset); this_cpu_inc(*field); } EXPORT_SYMBOL_GPL(netdev_core_stats_inc); @@ -11099,6 +11121,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, #ifdef CONFIG_NET_SCHED hash_init(dev->qdisc_hash); #endif + dev->priv_flags = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM; setup(dev); @@ -11191,6 +11214,8 @@ void free_netdev(struct net_device *dev) free_percpu(dev->xdp_bulkq); dev->xdp_bulkq = NULL; + netdev_free_phy_link_topology(dev); + /* Compatibility with error handling in drivers */ if (dev->reg_state == NETREG_UNINITIALIZED || dev->reg_state == NETREG_DUMMY) { @@ -11407,7 +11432,7 @@ void unregister_netdevice_many_notify(struct list_head *head, * @head: list of devices * * Note: As most callers use a stack allocated list_head, - * we force a list_del() to make sure stack wont be corrupted later. + * we force a list_del() to make sure stack won't be corrupted later. */ void unregister_netdevice_many(struct list_head *head) { @@ -11465,7 +11490,7 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, if (dev->features & NETIF_F_NETNS_LOCAL) goto out; - /* Ensure the device has been registrered */ + /* Ensure the device has been registered */ if (dev->reg_state != NETREG_REGISTERED) goto out; diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index baa63dee2829..166e404f7c03 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -262,7 +262,7 @@ static int __hw_addr_sync_multiple(struct netdev_hw_addr_list *to_list, } /* This function only works where there is a strict 1-1 relationship - * between source and destionation of they synch. If you ever need to + * between source and destination of they synch. If you ever need to * sync addresses to more then 1 destination, you need to use * __hw_addr_sync_multiple(). */ @@ -299,8 +299,8 @@ void __hw_addr_unsync(struct netdev_hw_addr_list *to_list, EXPORT_SYMBOL(__hw_addr_unsync); /** - * __hw_addr_sync_dev - Synchonize device's multicast list - * @list: address list to syncronize + * __hw_addr_sync_dev - Synchronize device's multicast list + * @list: address list to synchronize * @dev: device to sync * @sync: function to call if address should be added * @unsync: function to call if address should be removed diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 6ebffbc63236..5a4eb744758c 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -72,7 +72,7 @@ int fib_default_rule_add(struct fib_rules_ops *ops, r->suppress_prefixlen = -1; r->suppress_ifgroup = -1; - /* The lock is not required here, the list in unreacheable + /* The lock is not required here, the list in unreachable * at the moment this function is called */ list_add_tail(&r->list, &ops->rules_list); return 0; @@ -1205,8 +1205,7 @@ static void notify_rule_change(int event, struct fib_rule *rule, rtnl_notify(skb, net, pid, ops->nlgroup, nlh, GFP_KERNEL); return; errout: - if (err < 0) - rtnl_set_sk_err(net, ops->nlgroup, err); + rtnl_set_sk_err(net, ops->nlgroup, err); } static void attach_rules(struct list_head *rules, struct net_device *dev) diff --git a/net/core/filter.c b/net/core/filter.c index f3c72cf86099..f09d875cc053 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -84,6 +84,7 @@ #include <net/netkit.h> #include <linux/un.h> #include <net/xdp_sock_drv.h> +#include <net/inet_dscp.h> #include "dev.h" @@ -3189,6 +3190,7 @@ BPF_CALL_3(bpf_skb_vlan_push, struct sk_buff *, skb, __be16, vlan_proto, bpf_push_mac_rcsum(skb); ret = skb_vlan_push(skb, vlan_proto, vlan_tci); bpf_pull_mac_rcsum(skb); + skb_reset_mac_len(skb); bpf_compute_data_pointers(skb); return ret; @@ -5278,6 +5280,11 @@ static int bpf_sol_tcp_setsockopt(struct sock *sk, int optname, return -EINVAL; inet_csk(sk)->icsk_rto_min = timeout; break; + case TCP_BPF_SOCK_OPS_CB_FLAGS: + if (val & ~(BPF_SOCK_OPS_ALL_CB_FLAGS)) + return -EINVAL; + tp->bpf_sock_ops_cb_flags = val; + break; default: return -EINVAL; } @@ -5366,6 +5373,17 @@ static int sol_tcp_sockopt(struct sock *sk, int optname, if (*optlen < 1) return -EINVAL; break; + case TCP_BPF_SOCK_OPS_CB_FLAGS: + if (*optlen != sizeof(int)) + return -EINVAL; + if (getopt) { + struct tcp_sock *tp = tcp_sk(sk); + int cb_flags = tp->bpf_sock_ops_cb_flags; + + memcpy(optval, &cb_flags, *optlen); + return 0; + } + return bpf_sol_tcp_setsockopt(sk, optname, optval, *optlen); default: if (getopt) return -EINVAL; @@ -5899,7 +5917,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, fl4.flowi4_iif = params->ifindex; fl4.flowi4_oif = 0; } - fl4.flowi4_tos = params->tos & IPTOS_RT_MASK; + fl4.flowi4_tos = params->tos & INET_DSCP_MASK; fl4.flowi4_scope = RT_SCOPE_UNIVERSE; fl4.flowi4_flags = 0; diff --git a/net/core/gro.c b/net/core/gro.c index b3b43de1a650..3abad1b567dd 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -374,7 +374,7 @@ static void gro_list_prepare(const struct list_head *head, skb_mac_header(skb), maclen); - /* in most common scenarions 'slow_gro' is 0 + /* in most common scenarios 'slow_gro' is 0 * otherwise we are already on some slower paths * either skip all the infrequent tests altogether or * avoid trying too hard to skip each of them individually diff --git a/net/core/neighbour.c b/net/core/neighbour.c index a6fe88eca939..77b819cd995b 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -3530,8 +3530,7 @@ static void __neigh_notify(struct neighbour *n, int type, int flags, rtnl_notify(skb, net, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC); return; errout: - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_NEIGH, err); + rtnl_set_sk_err(net, RTNLGRP_NEIGH, err); } void neigh_app_ns(struct neighbour *n) diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 6a823ba906c6..11e4dd4f09ed 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -125,7 +125,7 @@ static int ops_init(const struct pernet_operations *ops, struct net *net) int err = -ENOMEM; void *data = NULL; - if (ops->id && ops->size) { + if (ops->id) { data = kzalloc(ops->size, GFP_KERNEL); if (!data) goto out; @@ -140,7 +140,7 @@ static int ops_init(const struct pernet_operations *ops, struct net *net) if (!err) return 0; - if (ops->id && ops->size) { + if (ops->id) { ng = rcu_dereference_protected(net->gen, lockdep_is_held(&pernet_ops_rwsem)); ng->ptr[*ops->id] = NULL; @@ -182,7 +182,8 @@ static void ops_free_list(const struct pernet_operations *ops, struct list_head *net_exit_list) { struct net *net; - if (ops->size && ops->id) { + + if (ops->id) { list_for_each_entry(net, net_exit_list, exit_list) kfree(net_generic(net, *ops->id)); } @@ -308,16 +309,38 @@ struct net *get_net_ns_by_id(const struct net *net, int id) } EXPORT_SYMBOL_GPL(get_net_ns_by_id); +static __net_init void preinit_net_sysctl(struct net *net) +{ + net->core.sysctl_somaxconn = SOMAXCONN; + /* Limits per socket sk_omem_alloc usage. + * TCP zerocopy regular usage needs 128 KB. + */ + net->core.sysctl_optmem_max = 128 * 1024; + net->core.sysctl_txrehash = SOCK_TXREHASH_ENABLED; +} + /* init code that must occur even if setup_net() is not called. */ -static __net_init void preinit_net(struct net *net) +static __net_init void preinit_net(struct net *net, struct user_namespace *user_ns) { + refcount_set(&net->passive, 1); + refcount_set(&net->ns.count, 1); + ref_tracker_dir_init(&net->refcnt_tracker, 128, "net refcnt"); ref_tracker_dir_init(&net->notrefcnt_tracker, 128, "net notrefcnt"); + + get_random_bytes(&net->hash_mix, sizeof(u32)); + net->dev_base_seq = 1; + net->user_ns = user_ns; + + idr_init(&net->netns_ids); + spin_lock_init(&net->nsid_lock); + mutex_init(&net->ipv4.ra_mutex); + preinit_net_sysctl(net); } /* * setup_net runs the initializers for the network namespace object. */ -static __net_init int setup_net(struct net *net, struct user_namespace *user_ns) +static __net_init int setup_net(struct net *net) { /* Must be called with pernet_ops_rwsem held */ const struct pernet_operations *ops, *saved_ops; @@ -325,19 +348,9 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns) LIST_HEAD(dev_kill_list); int error = 0; - refcount_set(&net->ns.count, 1); - ref_tracker_dir_init(&net->refcnt_tracker, 128, "net refcnt"); - - refcount_set(&net->passive, 1); - get_random_bytes(&net->hash_mix, sizeof(u32)); preempt_disable(); net->net_cookie = gen_cookie_next(&net_cookie); preempt_enable(); - net->dev_base_seq = 1; - net->user_ns = user_ns; - idr_init(&net->netns_ids); - spin_lock_init(&net->nsid_lock); - mutex_init(&net->ipv4.ra_mutex); list_for_each_entry(ops, &pernet_list, list) { error = ops_init(ops, net); @@ -382,32 +395,6 @@ out_undo: goto out; } -static int __net_init net_defaults_init_net(struct net *net) -{ - net->core.sysctl_somaxconn = SOMAXCONN; - /* Limits per socket sk_omem_alloc usage. - * TCP zerocopy regular usage needs 128 KB. - */ - net->core.sysctl_optmem_max = 128 * 1024; - net->core.sysctl_txrehash = SOCK_TXREHASH_ENABLED; - - return 0; -} - -static struct pernet_operations net_defaults_ops = { - .init = net_defaults_init_net, -}; - -static __init int net_defaults_init(void) -{ - if (register_pernet_subsys(&net_defaults_ops)) - panic("Cannot initialize net default settings"); - - return 0; -} - -core_initcall(net_defaults_init); - #ifdef CONFIG_NET_NS static struct ucounts *inc_net_namespaces(struct user_namespace *ns) { @@ -496,8 +483,7 @@ struct net *copy_net_ns(unsigned long flags, goto dec_ucounts; } - preinit_net(net); - refcount_set(&net->passive, 1); + preinit_net(net, user_ns); net->ucounts = ucounts; get_user_ns(user_ns); @@ -505,7 +491,7 @@ struct net *copy_net_ns(unsigned long flags, if (rv < 0) goto put_userns; - rv = setup_net(net, user_ns); + rv = setup_net(net); up_read(&pernet_ops_rwsem); @@ -1199,9 +1185,10 @@ void __init net_ns_init(void) #ifdef CONFIG_KEYS init_net.key_domain = &init_net_key_domain; #endif + preinit_net(&init_net, &init_user_ns); + down_write(&pernet_ops_rwsem); - preinit_net(&init_net); - if (setup_net(&init_net, &init_user_ns)) + if (setup_net(&init_net)) panic("Could not setup the initial network namespace"); init_net_initialized = true; @@ -1244,7 +1231,7 @@ static int __register_pernet_operations(struct list_head *list, LIST_HEAD(net_exit_list); list_add_tail(&ops->list, list); - if (ops->init || (ops->id && ops->size)) { + if (ops->init || ops->id) { /* We held write locked pernet_ops_rwsem, and parallel * setup_net() and cleanup_net() are not possible. */ @@ -1310,6 +1297,9 @@ static int register_pernet_operations(struct list_head *list, { int error; + if (WARN_ON(!!ops->id ^ !!ops->size)) + return -EINVAL; + if (ops->id) { error = ida_alloc_min(&net_generic_ids, MIN_PERNET_OPS_ID, GFP_KERNEL); diff --git a/net/core/netpoll.c b/net/core/netpoll.c index d657b042d5a0..e0720ee6fa62 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -162,7 +162,7 @@ static void poll_one_napi(struct napi_struct *napi) if (test_and_set_bit(NAPI_STATE_NPSVC, &napi->state)) return; - /* We explicilty pass the polling call a budget of 0 to + /* We explicitly pass the polling call a budget of 0 to * indicate that we are clearing the Tx path only. */ work = napi->poll(napi, 0); @@ -624,12 +624,9 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev) const struct net_device_ops *ops; int err; - np->dev = ndev; - strscpy(np->dev_name, ndev->name, IFNAMSIZ); - if (ndev->priv_flags & IFF_DISABLE_NETPOLL) { np_err(np, "%s doesn't support polling, aborting\n", - np->dev_name); + ndev->name); err = -ENOTSUPP; goto out; } @@ -647,7 +644,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev) refcount_set(&npinfo->refcnt, 1); - ops = np->dev->netdev_ops; + ops = ndev->netdev_ops; if (ops->ndo_netpoll_setup) { err = ops->ndo_netpoll_setup(ndev, npinfo); if (err) @@ -658,6 +655,8 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev) refcount_inc(&npinfo->refcnt); } + np->dev = ndev; + strscpy(np->dev_name, ndev->name, IFNAMSIZ); npinfo->netpoll = np; /* last thing to do is link it to the net device structure */ @@ -675,6 +674,7 @@ EXPORT_SYMBOL_GPL(__netpoll_setup); int netpoll_setup(struct netpoll *np) { struct net_device *ndev = NULL; + bool ip_overwritten = false; struct in_device *in_dev; int err; @@ -739,6 +739,7 @@ put_noaddr: } np->local_ip.ip = ifa->ifa_local; + ip_overwritten = true; np_info(np, "local IP %pI4\n", &np->local_ip.ip); } else { #if IS_ENABLED(CONFIG_IPV6) @@ -755,6 +756,7 @@ put_noaddr: !!(ipv6_addr_type(&np->remote_ip.in6) & IPV6_ADDR_LINKLOCAL)) continue; np->local_ip.in6 = ifp->addr; + ip_overwritten = true; err = 0; break; } @@ -785,6 +787,9 @@ put_noaddr: return 0; put: + DEBUG_NET_WARN_ON_ONCE(np->dev); + if (ip_overwritten) + memset(&np->local_ip, 0, sizeof(np->local_ip)); netdev_put(ndev, &np->dev_tracker); unlock: rtnl_unlock(); @@ -851,14 +856,20 @@ void __netpoll_free(struct netpoll *np) } EXPORT_SYMBOL_GPL(__netpoll_free); +void do_netpoll_cleanup(struct netpoll *np) +{ + __netpoll_cleanup(np); + netdev_put(np->dev, &np->dev_tracker); + np->dev = NULL; +} +EXPORT_SYMBOL(do_netpoll_cleanup); + void netpoll_cleanup(struct netpoll *np) { rtnl_lock(); if (!np->dev) goto out; - __netpoll_cleanup(np); - netdev_put(np->dev, &np->dev_tracker); - np->dev = NULL; + do_netpoll_cleanup(np); out: rtnl_unlock(); } diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 197a50ef8e2e..34f68ef74b8f 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -69,7 +69,7 @@ * * By design there should only be *one* "controlling" process. In practice * multiple write accesses gives unpredictable result. Understood by "write" - * to /proc gives result code thats should be read be the "writer". + * to /proc gives result code that should be read be the "writer". * For practical use this should be no problem. * * Note when adding devices to a specific CPU there good idea to also assign @@ -2371,11 +2371,11 @@ static void get_ipsec_sa(struct pktgen_dev *pkt_dev, int flow) if (pkt_dev->spi) { /* We need as quick as possible to find the right SA - * Searching with minimum criteria to archieve this. + * Searching with minimum criteria to achieve, this. */ x = xfrm_state_lookup_byspi(pn->net, htonl(pkt_dev->spi), AF_INET); } else { - /* slow path: we dont already have xfrm_state */ + /* slow path: we don't already have xfrm_state */ x = xfrm_stateonly_find(pn->net, DUMMY_MARK, 0, (xfrm_address_t *)&pkt_dev->cur_daddr, (xfrm_address_t *)&pkt_dev->cur_saddr, @@ -3838,8 +3838,8 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) pkt_dev->ipsmode = XFRM_MODE_TRANSPORT; pkt_dev->ipsproto = IPPROTO_ESP; - /* xfrm tunnel mode needs additional dst to extract outter - * ip header protocol/ttl/id field, here creat a phony one. + /* xfrm tunnel mode needs additional dst to extract outer + * ip header protocol/ttl/id field, here create a phony one. * instead of looking for a valid rt, which definitely hurting * performance under such circumstance. */ diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 73fd7f543fd0..cd9487a12d1a 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -4087,8 +4087,7 @@ struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, } return skb; errout: - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_LINK, err); + rtnl_set_sk_err(net, RTNLGRP_LINK, err); return NULL; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 83f8cd8aa2d1..a52638363ea5 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -314,8 +314,8 @@ void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask) fragsz = SKB_DATA_ALIGN(fragsz); local_lock_nested_bh(&napi_alloc_cache.bh_lock); - data = __page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC, - align_mask); + data = __page_frag_alloc_align(&nc->page, fragsz, + GFP_ATOMIC | __GFP_NOWARN, align_mask); local_unlock_nested_bh(&napi_alloc_cache.bh_lock); return data; @@ -330,7 +330,8 @@ void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align_mask) struct page_frag_cache *nc = this_cpu_ptr(&netdev_alloc_cache); fragsz = SKB_DATA_ALIGN(fragsz); - data = __page_frag_alloc_align(nc, fragsz, GFP_ATOMIC, + data = __page_frag_alloc_align(nc, fragsz, + GFP_ATOMIC | __GFP_NOWARN, align_mask); } else { local_bh_disable(); @@ -349,7 +350,7 @@ static struct sk_buff *napi_skb_cache_get(void) 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_ATOMIC | __GFP_NOWARN, NAPI_SKB_CACHE_BULK, nc->skb_cache); if (unlikely(!nc->skb_count)) { @@ -418,7 +419,8 @@ struct sk_buff *slab_build_skb(void *data) struct sk_buff *skb; unsigned int size; - skb = kmem_cache_alloc(net_hotdata.skbuff_cache, GFP_ATOMIC); + skb = kmem_cache_alloc(net_hotdata.skbuff_cache, + GFP_ATOMIC | __GFP_NOWARN); if (unlikely(!skb)) return NULL; @@ -469,7 +471,8 @@ struct sk_buff *__build_skb(void *data, unsigned int frag_size) { struct sk_buff *skb; - skb = kmem_cache_alloc(net_hotdata.skbuff_cache, GFP_ATOMIC); + skb = kmem_cache_alloc(net_hotdata.skbuff_cache, + GFP_ATOMIC | __GFP_NOWARN); if (unlikely(!skb)) return NULL; @@ -4169,8 +4172,7 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen) /* Actual merge is delayed until the point when we know we can * commit all, so that we don't have to undo partial changes */ - if (!to || - !skb_can_coalesce(tgt, to, skb_frag_page(fragfrom), + if (!skb_can_coalesce(tgt, to, skb_frag_page(fragfrom), skb_frag_off(fragfrom))) { merge = -1; } else { @@ -5161,7 +5163,7 @@ EXPORT_SYMBOL_GPL(skb_to_sgvec); * 3. sg_unmark_end * 4. skb_to_sgvec(payload2) * - * When mapping mutilple payload conditionally, skb_to_sgvec_nomark + * When mapping multiple payload conditionally, skb_to_sgvec_nomark * is more preferable. */ int skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg, @@ -6019,7 +6021,7 @@ EXPORT_SYMBOL(skb_try_coalesce); * @skb: buffer to clean * @xnet: packet is crossing netns * - * skb_scrub_packet can be used after encapsulating or decapsulting a packet + * skb_scrub_packet can be used after encapsulating or decapsulating a packet * into/from a tunnel. Some information have to be cleared during these * operations. * skb_scrub_packet can also be used to clean a skb before injecting it in @@ -6241,7 +6243,7 @@ int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) return err; skb->protocol = skb->vlan_proto; - skb->mac_len += VLAN_HLEN; + skb->network_header -= VLAN_HLEN; skb_postpush_rcsum(skb, skb->data + (2 * ETH_ALEN), VLAN_HLEN); } diff --git a/net/core/sock.c b/net/core/sock.c index 9abc4fe25953..468b1239606c 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2048,7 +2048,7 @@ static inline void sock_lock_init(struct sock *sk) /* * Copy all fields from osk to nsk but nsk->sk_refcnt must not change yet, - * even temporarly, because of RCU lookups. sk_node should also be left as is. + * even temporarily, because of RCU lookups. sk_node should also be left as is. * We must not copy fields between sk_dontcopy_begin and sk_dontcopy_end */ static void sock_copy(struct sock *nsk, const struct sock *osk) @@ -2538,7 +2538,7 @@ void skb_set_owner_w(struct sk_buff *skb, struct sock *sk) skb_set_hash_from_sk(skb, sk); /* * We used to take a refcount on sk, but following operation - * is enough to guarantee sk_free() wont free this sock until + * 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); @@ -3697,7 +3697,7 @@ EXPORT_SYMBOL(sock_recv_errqueue); * * FIX: POSIX 1003.1g is very ambiguous here. It states that * asynchronous errors should be reported by getsockopt. We assume - * this means if you specify SO_ERROR (otherwise whats the point of it). + * this means if you specify SO_ERROR (otherwise what is the point of it). */ int sock_common_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c index 5a165286e4d8..4211710393a8 100644 --- a/net/core/sock_reuseport.c +++ b/net/core/sock_reuseport.c @@ -173,10 +173,9 @@ static bool __reuseport_detach_closed_sock(struct sock *sk, static struct sock_reuseport *__reuseport_alloc(unsigned int max_socks) { - unsigned int size = sizeof(struct sock_reuseport) + - sizeof(struct sock *) * max_socks; - struct sock_reuseport *reuse = kzalloc(size, GFP_ATOMIC); + struct sock_reuseport *reuse; + reuse = kzalloc(struct_size(reuse, socks, max_socks), GFP_ATOMIC); if (!reuse) return NULL; diff --git a/net/core/utils.c b/net/core/utils.c index c994e95172ac..27f4cffaae05 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * Generic address resultion entity + * Generic address resolution entity * * Authors: * net_random Alan Cox diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c index ee7b272ab715..1f46de394f2e 100644 --- a/net/dsa/tag_ksz.c +++ b/net/dsa/tag_ksz.c @@ -111,9 +111,10 @@ static struct sk_buff *ksz_common_rcv(struct sk_buff *skb, * DA(6bytes)|SA(6bytes)|....|Data(nbytes)|tag0(1byte)|FCS(4bytes) * --------------------------------------------------------------------------- * tag0 : zero-based value represents port - * (eg, 0x00=port1, 0x02=port3, 0x06=port7) + * (eg, 0x0=port1, 0x2=port3, 0x3=port4) */ +#define KSZ8795_TAIL_TAG_EG_PORT_M GENMASK(1, 0) #define KSZ8795_TAIL_TAG_OVERRIDE BIT(6) #define KSZ8795_TAIL_TAG_LOOKUP BIT(7) @@ -141,7 +142,8 @@ static struct sk_buff *ksz8795_rcv(struct sk_buff *skb, struct net_device *dev) { u8 *tag = skb_tail_pointer(skb) - KSZ_EGRESS_TAG_LEN; - return ksz_common_rcv(skb, dev, tag[0] & 7, KSZ_EGRESS_TAG_LEN); + return ksz_common_rcv(skb, dev, tag[0] & KSZ8795_TAIL_TAG_EG_PORT_M, + KSZ_EGRESS_TAG_LEN); } static const struct dsa_device_ops ksz8795_netdev_ops = { diff --git a/net/ethtool/Makefile b/net/ethtool/Makefile index 9a190635fe95..9b540644ba31 100644 --- a/net/ethtool/Makefile +++ b/net/ethtool/Makefile @@ -8,4 +8,5 @@ ethtool_nl-y := netlink.o bitset.o strset.o linkinfo.o linkmodes.o rss.o \ linkstate.o debug.o wol.o features.o privflags.o rings.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 mm.o + module.o cmis_fw_update.o cmis_cdb.o pse-pd.o plca.o mm.o \ + phy.o diff --git a/net/ethtool/cabletest.c b/net/ethtool/cabletest.c index f6f136ec7ddf..f22051f33868 100644 --- a/net/ethtool/cabletest.c +++ b/net/ethtool/cabletest.c @@ -13,7 +13,7 @@ const struct nla_policy ethnl_cable_test_act_policy[] = { [ETHTOOL_A_CABLE_TEST_HEADER] = - NLA_POLICY_NESTED(ethnl_header_policy), + NLA_POLICY_NESTED(ethnl_header_policy_phy), }; static int ethnl_cable_test_started(struct phy_device *phydev, u8 cmd) @@ -58,6 +58,7 @@ int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info) struct ethnl_req_info req_info = {}; const struct ethtool_phy_ops *ops; struct nlattr **tb = info->attrs; + struct phy_device *phydev; struct net_device *dev; int ret; @@ -69,12 +70,16 @@ int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info) return ret; dev = req_info.dev; - if (!dev->phydev) { + + rtnl_lock(); + phydev = ethnl_req_get_phydev(&req_info, + tb[ETHTOOL_A_CABLE_TEST_HEADER], + info->extack); + if (IS_ERR_OR_NULL(phydev)) { ret = -EOPNOTSUPP; - goto out_dev_put; + goto out_rtnl; } - rtnl_lock(); ops = ethtool_phy_ops; if (!ops || !ops->start_cable_test) { ret = -EOPNOTSUPP; @@ -85,17 +90,15 @@ int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info) if (ret < 0) goto out_rtnl; - ret = ops->start_cable_test(dev->phydev, info->extack); + ret = ops->start_cable_test(phydev, info->extack); ethnl_ops_complete(dev); if (!ret) - ethnl_cable_test_started(dev->phydev, - ETHTOOL_MSG_CABLE_TEST_NTF); + ethnl_cable_test_started(phydev, ETHTOOL_MSG_CABLE_TEST_NTF); out_rtnl: rtnl_unlock(); -out_dev_put: ethnl_parse_header_dev_put(&req_info); return ret; } @@ -160,7 +163,8 @@ void ethnl_cable_test_finished(struct phy_device *phydev) } EXPORT_SYMBOL_GPL(ethnl_cable_test_finished); -int ethnl_cable_test_result(struct phy_device *phydev, u8 pair, u8 result) +int ethnl_cable_test_result_with_src(struct phy_device *phydev, u8 pair, + u8 result, u32 src) { struct nlattr *nest; int ret = -EMSGSIZE; @@ -173,6 +177,10 @@ int ethnl_cable_test_result(struct phy_device *phydev, u8 pair, u8 result) goto err; if (nla_put_u8(phydev->skb, ETHTOOL_A_CABLE_RESULT_CODE, result)) goto err; + if (src != ETHTOOL_A_CABLE_INF_SRC_UNSPEC) { + if (nla_put_u32(phydev->skb, ETHTOOL_A_CABLE_RESULT_SRC, src)) + goto err; + } nla_nest_end(phydev->skb, nest); return 0; @@ -181,9 +189,10 @@ err: nla_nest_cancel(phydev->skb, nest); return ret; } -EXPORT_SYMBOL_GPL(ethnl_cable_test_result); +EXPORT_SYMBOL_GPL(ethnl_cable_test_result_with_src); -int ethnl_cable_test_fault_length(struct phy_device *phydev, u8 pair, u32 cm) +int ethnl_cable_test_fault_length_with_src(struct phy_device *phydev, u8 pair, + u32 cm, u32 src) { struct nlattr *nest; int ret = -EMSGSIZE; @@ -197,6 +206,11 @@ int ethnl_cable_test_fault_length(struct phy_device *phydev, u8 pair, u32 cm) goto err; if (nla_put_u32(phydev->skb, ETHTOOL_A_CABLE_FAULT_LENGTH_CM, cm)) goto err; + if (src != ETHTOOL_A_CABLE_INF_SRC_UNSPEC) { + if (nla_put_u32(phydev->skb, ETHTOOL_A_CABLE_FAULT_LENGTH_SRC, + src)) + goto err; + } nla_nest_end(phydev->skb, nest); return 0; @@ -205,7 +219,7 @@ err: nla_nest_cancel(phydev->skb, nest); return ret; } -EXPORT_SYMBOL_GPL(ethnl_cable_test_fault_length); +EXPORT_SYMBOL_GPL(ethnl_cable_test_fault_length_with_src); static const struct nla_policy cable_test_tdr_act_cfg_policy[] = { [ETHTOOL_A_CABLE_TEST_TDR_CFG_FIRST] = { .type = NLA_U32 }, @@ -216,7 +230,7 @@ static const struct nla_policy cable_test_tdr_act_cfg_policy[] = { const struct nla_policy ethnl_cable_test_tdr_act_policy[] = { [ETHTOOL_A_CABLE_TEST_TDR_HEADER] = - NLA_POLICY_NESTED(ethnl_header_policy), + NLA_POLICY_NESTED(ethnl_header_policy_phy), [ETHTOOL_A_CABLE_TEST_TDR_CFG] = { .type = NLA_NESTED }, }; @@ -305,6 +319,7 @@ int ethnl_act_cable_test_tdr(struct sk_buff *skb, struct genl_info *info) struct ethnl_req_info req_info = {}; const struct ethtool_phy_ops *ops; struct nlattr **tb = info->attrs; + struct phy_device *phydev; struct phy_tdr_config cfg; struct net_device *dev; int ret; @@ -317,10 +332,6 @@ int ethnl_act_cable_test_tdr(struct sk_buff *skb, struct genl_info *info) return ret; dev = req_info.dev; - if (!dev->phydev) { - ret = -EOPNOTSUPP; - goto out_dev_put; - } ret = ethnl_act_cable_test_tdr_cfg(tb[ETHTOOL_A_CABLE_TEST_TDR_CFG], info, &cfg); @@ -328,6 +339,14 @@ int ethnl_act_cable_test_tdr(struct sk_buff *skb, struct genl_info *info) goto out_dev_put; rtnl_lock(); + phydev = ethnl_req_get_phydev(&req_info, + tb[ETHTOOL_A_CABLE_TEST_TDR_HEADER], + info->extack); + if (IS_ERR_OR_NULL(phydev)) { + ret = -EOPNOTSUPP; + goto out_rtnl; + } + ops = ethtool_phy_ops; if (!ops || !ops->start_cable_test_tdr) { ret = -EOPNOTSUPP; @@ -338,12 +357,12 @@ int ethnl_act_cable_test_tdr(struct sk_buff *skb, struct genl_info *info) if (ret < 0) goto out_rtnl; - ret = ops->start_cable_test_tdr(dev->phydev, info->extack, &cfg); + ret = ops->start_cable_test_tdr(phydev, info->extack, &cfg); ethnl_ops_complete(dev); if (!ret) - ethnl_cable_test_started(dev->phydev, + ethnl_cable_test_started(phydev, ETHTOOL_MSG_CABLE_TEST_TDR_NTF); out_rtnl: diff --git a/net/ethtool/channels.c b/net/ethtool/channels.c index cee188da54f8..ca4f80282448 100644 --- a/net/ethtool/channels.c +++ b/net/ethtool/channels.c @@ -114,8 +114,7 @@ ethnl_set_channels(struct ethnl_req_info *req_info, struct genl_info *info) struct net_device *dev = req_info->dev; struct ethtool_channels channels = {}; struct nlattr **tb = info->attrs; - u32 err_attr, max_rxfh_in_use; - u64 max_rxnfc_in_use; + u32 err_attr; int ret; dev->ethtool_ops->get_channels(dev, &channels); @@ -166,20 +165,9 @@ ethnl_set_channels(struct ethnl_req_info *req_info, struct genl_info *info) return -EINVAL; } - /* ensure the new Rx count fits within the configured Rx flow - * indirection table/rxnfc settings - */ - if (ethtool_get_max_rxnfc_channel(dev, &max_rxnfc_in_use)) - max_rxnfc_in_use = 0; - max_rxfh_in_use = ethtool_get_max_rxfh_channel(dev); - if (channels.combined_count + channels.rx_count <= max_rxfh_in_use) { - GENL_SET_ERR_MSG_FMT(info, "requested channel counts are too low for existing indirection table (%d)", max_rxfh_in_use); - return -EINVAL; - } - if (channels.combined_count + channels.rx_count <= max_rxnfc_in_use) { - GENL_SET_ERR_MSG(info, "requested channel counts are too low for existing ntuple filter settings"); - return -EINVAL; - } + ret = ethtool_check_max_channel(dev, channels, info); + if (ret) + return ret; /* Disabling channels, query zero-copy AF_XDP sockets */ from_channel = channels.combined_count + diff --git a/net/ethtool/cmis.h b/net/ethtool/cmis.h index e71cc3e1b7eb..3e7c293af78c 100644 --- a/net/ethtool/cmis.h +++ b/net/ethtool/cmis.h @@ -108,7 +108,6 @@ void ethtool_cmis_cdb_check_completion_flag(u8 cmis_rev, u8 *flags); void ethtool_cmis_page_init(struct ethtool_module_eeprom *page_data, u8 page, u32 offset, u32 length); -void ethtool_cmis_page_fini(struct ethtool_module_eeprom *page_data); struct ethtool_cmis_cdb * ethtool_cmis_cdb_init(struct net_device *dev, diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 07032babd1b6..7257ae272296 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -6,6 +6,7 @@ #include <linux/rtnetlink.h> #include <linux/ptp_clock_kernel.h> +#include "netlink.h" #include "common.h" const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] = { @@ -539,7 +540,7 @@ static int ethtool_get_rxnfc_rule_count(struct net_device *dev) return info.rule_cnt; } -int ethtool_get_max_rxnfc_channel(struct net_device *dev, u64 *max) +static int ethtool_get_max_rxnfc_channel(struct net_device *dev, u64 *max) { const struct ethtool_ops *ops = dev->ethtool_ops; struct ethtool_rxnfc *info; @@ -609,7 +610,7 @@ static u32 ethtool_get_max_rss_ctx_channel(struct net_device *dev) return max_ring; } -u32 ethtool_get_max_rxfh_channel(struct net_device *dev) +static u32 ethtool_get_max_rxfh_channel(struct net_device *dev) { struct ethtool_rxfh_param rxfh = {}; u32 dev_size, current_max; @@ -650,10 +651,39 @@ out_free: return current_max; } +int ethtool_check_max_channel(struct net_device *dev, + struct ethtool_channels channels, + struct genl_info *info) +{ + u64 max_rxnfc_in_use; + u32 max_rxfh_in_use; + + /* ensure the new Rx count fits within the configured Rx flow + * indirection table/rxnfc settings + */ + if (ethtool_get_max_rxnfc_channel(dev, &max_rxnfc_in_use)) + max_rxnfc_in_use = 0; + max_rxfh_in_use = ethtool_get_max_rxfh_channel(dev); + if (channels.combined_count + channels.rx_count <= max_rxfh_in_use) { + if (info) + GENL_SET_ERR_MSG_FMT(info, "requested channel counts are too low for existing indirection table (%d)", max_rxfh_in_use); + return -EINVAL; + } + if (channels.combined_count + channels.rx_count <= max_rxnfc_in_use) { + if (info) + GENL_SET_ERR_MSG(info, "requested channel counts are too low for existing ntuple filter settings"); + return -EINVAL; + } + + return 0; +} + int ethtool_check_ops(const struct ethtool_ops *ops) { if (WARN_ON(ops->set_coalesce && !ops->supported_coalesce_params)) return -EINVAL; + if (WARN_ON(ops->rxfh_max_num_contexts == 1)) + return -EINVAL; /* NOTE: sufficiently insane drivers may swap ethtool_ops at runtime, * the fact that ops are checked at registration time does not * mean the ops attached to a netdev later on are sane. diff --git a/net/ethtool/common.h b/net/ethtool/common.h index 863806fcf01a..d55d5201b085 100644 --- a/net/ethtool/common.h +++ b/net/ethtool/common.h @@ -20,6 +20,8 @@ struct link_mode_info { u8 duplex; }; +struct genl_info; + extern const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]; extern const char @@ -42,8 +44,9 @@ int __ethtool_get_link(struct net_device *dev); bool convert_legacy_settings_to_link_ksettings( struct ethtool_link_ksettings *link_ksettings, const struct ethtool_cmd *legacy_settings); -u32 ethtool_get_max_rxfh_channel(struct net_device *dev); -int ethtool_get_max_rxnfc_channel(struct net_device *dev, u64 *max); +int ethtool_check_max_channel(struct net_device *dev, + struct ethtool_channels channels, + struct genl_info *info); int __ethtool_get_ts_info(struct net_device *dev, struct kernel_ethtool_ts_info *info); extern const struct ethtool_phy_ops *ethtool_phy_ops; diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index ae041f51cd2d..65cfe76dafbe 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -1230,7 +1230,8 @@ static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev, if (rxfh.rsvd8[0] || rxfh.rsvd8[1] || rxfh.rsvd32) return -EINVAL; /* Most drivers don't handle rss_context, check it's 0 as well */ - if (rxfh.rss_context && !ops->cap_rss_ctx_supported) + if (rxfh.rss_context && !(ops->cap_rss_ctx_supported || + ops->create_rxfh_context)) return -EOPNOTSUPP; rxfh.indir_size = rxfh_dev.indir_size; @@ -1263,10 +1264,15 @@ static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev, if (rxfh_dev.indir) memcpy(rxfh_dev.indir, ethtool_rxfh_context_indir(ctx), indir_bytes); - if (rxfh_dev.key) - memcpy(rxfh_dev.key, ethtool_rxfh_context_key(ctx), - user_key_size); - rxfh_dev.hfunc = ctx->hfunc; + if (!ops->rxfh_per_ctx_key) { + rxfh_dev.key_size = 0; + } else { + if (rxfh_dev.key) + memcpy(rxfh_dev.key, + ethtool_rxfh_context_key(ctx), + user_key_size); + rxfh_dev.hfunc = ctx->hfunc; + } rxfh_dev.input_xfrm = ctx->input_xfrm; ret = 0; } else { @@ -1284,6 +1290,11 @@ static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev, sizeof(rxfh.input_xfrm))) { ret = -EFAULT; } else if (copy_to_user(useraddr + + offsetof(struct ethtool_rxfh, key_size), + &rxfh_dev.key_size, + sizeof(rxfh.key_size))) { + ret = -EFAULT; + } else if (copy_to_user(useraddr + offsetof(struct ethtool_rxfh, rss_config[0]), rss_config, total_size)) { ret = -EFAULT; @@ -1360,7 +1371,8 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, if (rxfh.rsvd8[0] || rxfh.rsvd8[1] || rxfh.rsvd32) return -EINVAL; /* Most drivers don't handle rss_context, check it's 0 as well */ - if (rxfh.rss_context && !ops->cap_rss_ctx_supported) + if (rxfh.rss_context && !(ops->cap_rss_ctx_supported || + ops->create_rxfh_context)) return -EOPNOTSUPP; /* Check input data transformation capabilities */ if (rxfh.input_xfrm && rxfh.input_xfrm != RXH_XFRM_SYM_XOR && @@ -1390,6 +1402,13 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, indir_bytes = dev_indir_size * sizeof(rxfh_dev.indir[0]); + /* Check settings which may be global rather than per RSS-context */ + if (rxfh.rss_context && !ops->rxfh_per_ctx_key) + if (rxfh.key_size || + (rxfh.hfunc && rxfh.hfunc != ETH_RSS_HASH_NO_CHANGE) || + (rxfh.input_xfrm && rxfh.input_xfrm != RXH_XFRM_NO_CHANGE)) + return -EOPNOTSUPP; + rss_config = kzalloc(indir_bytes + dev_key_size, GFP_USER); if (!rss_config) return -ENOMEM; @@ -2072,8 +2091,6 @@ static noinline_for_stack int ethtool_set_channels(struct net_device *dev, { struct ethtool_channels channels, curr = { .cmd = ETHTOOL_GCHANNELS }; u16 from_channel, to_channel; - u64 max_rxnfc_in_use; - u32 max_rxfh_in_use; unsigned int i; int ret; @@ -2103,14 +2120,9 @@ static noinline_for_stack int ethtool_set_channels(struct net_device *dev, (!channels.rx_count || !channels.tx_count)) return -EINVAL; - /* ensure the new Rx count fits within the configured Rx flow - * indirection table/rxnfc settings */ - if (ethtool_get_max_rxnfc_channel(dev, &max_rxnfc_in_use)) - max_rxnfc_in_use = 0; - max_rxfh_in_use = ethtool_get_max_rxfh_channel(dev); - if (channels.combined_count + channels.rx_count <= - max_t(u64, max_rxnfc_in_use, max_rxfh_in_use)) - return -EINVAL; + ret = ethtool_check_max_channel(dev, channels, NULL); + if (ret) + return ret; /* Disabling channels, query zero-copy AF_XDP sockets */ from_channel = channels.combined_count + diff --git a/net/ethtool/linkinfo.c b/net/ethtool/linkinfo.c index 5c317d23787b..30b8ce275159 100644 --- a/net/ethtool/linkinfo.c +++ b/net/ethtool/linkinfo.c @@ -35,7 +35,7 @@ static int linkinfo_prepare_data(const struct ethnl_req_info *req_base, if (ret < 0) return ret; ret = __ethtool_get_link_ksettings(dev, &data->ksettings); - if (ret < 0 && info) + if (ret < 0) GENL_SET_ERR_MSG(info, "failed to retrieve link settings"); ethnl_ops_complete(dev); diff --git a/net/ethtool/linkmodes.c b/net/ethtool/linkmodes.c index b2591db49f7d..259cd9ef1f2a 100644 --- a/net/ethtool/linkmodes.c +++ b/net/ethtool/linkmodes.c @@ -40,7 +40,7 @@ static int linkmodes_prepare_data(const struct ethnl_req_info *req_base, return ret; ret = __ethtool_get_link_ksettings(dev, &data->ksettings); - if (ret < 0 && info) { + if (ret < 0) { GENL_SET_ERR_MSG(info, "failed to retrieve link settings"); goto out; } diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index cb1eea00e349..e3f0ef6b851b 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -2,6 +2,7 @@ #include <net/sock.h> #include <linux/ethtool_netlink.h> +#include <linux/phy_link_topology.h> #include <linux/pm_runtime.h> #include "netlink.h" #include "module_fw.h" @@ -31,6 +32,24 @@ const struct nla_policy ethnl_header_policy_stats[] = { ETHTOOL_FLAGS_STATS), }; +const struct nla_policy ethnl_header_policy_phy[] = { + [ETHTOOL_A_HEADER_DEV_INDEX] = { .type = NLA_U32 }, + [ETHTOOL_A_HEADER_DEV_NAME] = { .type = NLA_NUL_STRING, + .len = ALTIFNAMSIZ - 1 }, + [ETHTOOL_A_HEADER_FLAGS] = NLA_POLICY_MASK(NLA_U32, + ETHTOOL_FLAGS_BASIC), + [ETHTOOL_A_HEADER_PHY_INDEX] = NLA_POLICY_MIN(NLA_U32, 1), +}; + +const struct nla_policy ethnl_header_policy_phy_stats[] = { + [ETHTOOL_A_HEADER_DEV_INDEX] = { .type = NLA_U32 }, + [ETHTOOL_A_HEADER_DEV_NAME] = { .type = NLA_NUL_STRING, + .len = ALTIFNAMSIZ - 1 }, + [ETHTOOL_A_HEADER_FLAGS] = NLA_POLICY_MASK(NLA_U32, + ETHTOOL_FLAGS_STATS), + [ETHTOOL_A_HEADER_PHY_INDEX] = NLA_POLICY_MIN(NLA_U32, 1), +}; + int ethnl_sock_priv_set(struct sk_buff *skb, struct net_device *dev, u32 portid, enum ethnl_sock_type type) { @@ -119,7 +138,7 @@ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info, const struct nlattr *header, struct net *net, struct netlink_ext_ack *extack, bool require_dev) { - struct nlattr *tb[ARRAY_SIZE(ethnl_header_policy)]; + struct nlattr *tb[ARRAY_SIZE(ethnl_header_policy_phy)]; const struct nlattr *devname_attr; struct net_device *dev = NULL; u32 flags = 0; @@ -134,7 +153,7 @@ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info, /* No validation here, command policy should have a nested policy set * for the header, therefore validation should have already been done. */ - ret = nla_parse_nested(tb, ARRAY_SIZE(ethnl_header_policy) - 1, header, + ret = nla_parse_nested(tb, ARRAY_SIZE(ethnl_header_policy_phy) - 1, header, NULL, extack); if (ret < 0) return ret; @@ -175,11 +194,45 @@ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info, return -EINVAL; } + if (tb[ETHTOOL_A_HEADER_PHY_INDEX]) { + if (dev) { + req_info->phy_index = nla_get_u32(tb[ETHTOOL_A_HEADER_PHY_INDEX]); + } else { + NL_SET_ERR_MSG_ATTR(extack, header, + "phy_index set without a netdev"); + return -EINVAL; + } + } + req_info->dev = dev; req_info->flags = flags; return 0; } +struct phy_device *ethnl_req_get_phydev(const struct ethnl_req_info *req_info, + const struct nlattr *header, + struct netlink_ext_ack *extack) +{ + struct phy_device *phydev; + + ASSERT_RTNL(); + + if (!req_info->dev) + return NULL; + + if (!req_info->phy_index) + return req_info->dev->phydev; + + phydev = phy_link_topo_get_phy(req_info->dev, req_info->phy_index); + if (!phydev) { + NL_SET_ERR_MSG_ATTR(extack, header, + "no phy matching phyindex"); + return ERR_PTR(-ENODEV); + } + + return phydev; +} + /** * ethnl_fill_reply_header() - Put common header into a reply message * @skb: skb with the message @@ -1128,6 +1181,8 @@ static const struct genl_ops ethtool_genl_ops[] = { { .cmd = ETHTOOL_MSG_RSS_GET, .doit = ethnl_default_doit, + .start = ethnl_rss_dump_start, + .dumpit = ethnl_rss_dumpit, .policy = ethnl_rss_get_policy, .maxattr = ARRAY_SIZE(ethnl_rss_get_policy) - 1, }, @@ -1179,6 +1234,15 @@ static const struct genl_ops ethtool_genl_ops[] = { .policy = ethnl_module_fw_flash_act_policy, .maxattr = ARRAY_SIZE(ethnl_module_fw_flash_act_policy) - 1, }, + { + .cmd = ETHTOOL_MSG_PHY_GET, + .doit = ethnl_phy_doit, + .start = ethnl_phy_start, + .dumpit = ethnl_phy_dumpit, + .done = ethnl_phy_done, + .policy = ethnl_phy_get_policy, + .maxattr = ARRAY_SIZE(ethnl_phy_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 46ec273a87c5..203b08eb6c6f 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -251,6 +251,9 @@ static inline unsigned int ethnl_reply_header_size(void) * @dev: network device the request is for (may be null) * @dev_tracker: refcount tracker for @dev reference * @flags: request flags common for all request types + * @phy_index: phy_device index connected to @dev this request is for. Can be + * 0 if the request doesn't target a phy, or if the @dev's attached + * phy is targeted. * * This is a common base for request specific structures holding data from * parsed userspace request. These always embed struct ethnl_req_info at @@ -260,6 +263,7 @@ struct ethnl_req_info { struct net_device *dev; netdevice_tracker dev_tracker; u32 flags; + u32 phy_index; }; static inline void ethnl_parse_header_dev_put(struct ethnl_req_info *req_info) @@ -268,6 +272,27 @@ static inline void ethnl_parse_header_dev_put(struct ethnl_req_info *req_info) } /** + * ethnl_req_get_phydev() - Gets the phy_device targeted by this request, + * if any. Must be called under rntl_lock(). + * @req_info: The ethnl request to get the phy from. + * @header: The netlink header, used for error reporting. + * @extack: The netlink extended ACK, for error reporting. + * + * The caller must hold RTNL, until it's done interacting with the returned + * phy_device. + * + * Return: A phy_device pointer corresponding either to the passed phy_index + * if one is provided. If not, the phy_device attached to the + * net_device targeted by this request is returned. If there's no + * targeted net_device, or no phy_device is attached, NULL is + * returned. If the provided phy_index is invalid, an error pointer + * is returned. + */ +struct phy_device *ethnl_req_get_phydev(const struct ethnl_req_info *req_info, + const struct nlattr *header, + struct netlink_ext_ack *extack); + +/** * struct ethnl_reply_data - base type of reply data for GET requests * @dev: device for current reply message; in single shot requests it is * equal to ðnl_req_info.dev; in dumps it's different for each @@ -409,9 +434,12 @@ extern const struct ethnl_request_ops ethnl_rss_request_ops; extern const struct ethnl_request_ops ethnl_plca_cfg_request_ops; 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 nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_FLAGS + 1]; extern const struct nla_policy ethnl_header_policy_stats[ETHTOOL_A_HEADER_FLAGS + 1]; +extern const struct nla_policy ethnl_header_policy_phy[ETHTOOL_A_HEADER_PHY_INDEX + 1]; +extern const struct nla_policy ethnl_header_policy_phy_stats[ETHTOOL_A_HEADER_PHY_INDEX + 1]; extern const struct nla_policy ethnl_strset_get_policy[ETHTOOL_A_STRSET_COUNTS_ONLY + 1]; extern const struct nla_policy ethnl_linkinfo_get_policy[ETHTOOL_A_LINKINFO_HEADER + 1]; extern const struct nla_policy ethnl_linkinfo_set_policy[ETHTOOL_A_LINKINFO_TP_MDIX_CTRL + 1]; @@ -449,13 +477,14 @@ extern const struct nla_policy ethnl_module_get_policy[ETHTOOL_A_MODULE_HEADER + extern const struct nla_policy ethnl_module_set_policy[ETHTOOL_A_MODULE_POWER_MODE_POLICY + 1]; extern const struct nla_policy ethnl_pse_get_policy[ETHTOOL_A_PSE_HEADER + 1]; extern const struct nla_policy ethnl_pse_set_policy[ETHTOOL_A_PSE_MAX + 1]; -extern const struct nla_policy ethnl_rss_get_policy[ETHTOOL_A_RSS_CONTEXT + 1]; +extern const struct nla_policy ethnl_rss_get_policy[ETHTOOL_A_RSS_START_CONTEXT + 1]; extern const struct nla_policy ethnl_plca_get_cfg_policy[ETHTOOL_A_PLCA_HEADER + 1]; extern const struct nla_policy ethnl_plca_set_cfg_policy[ETHTOOL_A_PLCA_MAX + 1]; extern const struct nla_policy ethnl_plca_get_status_policy[ETHTOOL_A_PLCA_HEADER + 1]; extern const struct nla_policy ethnl_mm_get_policy[ETHTOOL_A_MM_HEADER + 1]; extern const struct nla_policy ethnl_mm_set_policy[ETHTOOL_A_MM_MAX + 1]; extern const struct nla_policy ethnl_module_fw_flash_act_policy[ETHTOOL_A_MODULE_FW_FLASH_PASSWORD + 1]; +extern const struct nla_policy ethnl_phy_get_policy[ETHTOOL_A_PHY_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); @@ -464,6 +493,12 @@ int ethnl_tunnel_info_doit(struct sk_buff *skb, struct genl_info *info); int ethnl_tunnel_info_start(struct netlink_callback *cb); int ethnl_tunnel_info_dumpit(struct sk_buff *skb, struct netlink_callback *cb); int ethnl_act_module_fw_flash(struct sk_buff *skb, struct genl_info *info); +int ethnl_rss_dump_start(struct netlink_callback *cb); +int ethnl_rss_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int ethnl_phy_start(struct netlink_callback *cb); +int ethnl_phy_doit(struct sk_buff *skb, struct genl_info *info); +int ethnl_phy_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int ethnl_phy_done(struct netlink_callback *cb); extern const char stats_std_names[__ETHTOOL_STATS_CNT][ETH_GSTRING_LEN]; extern const char stats_eth_phy_names[__ETHTOOL_A_STATS_ETH_PHY_CNT][ETH_GSTRING_LEN]; diff --git a/net/ethtool/phy.c b/net/ethtool/phy.c new file mode 100644 index 000000000000..560dd039c662 --- /dev/null +++ b/net/ethtool/phy.c @@ -0,0 +1,308 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2023 Bootlin + * + */ +#include "common.h" +#include "netlink.h" + +#include <linux/phy.h> +#include <linux/phy_link_topology.h> +#include <linux/sfp.h> + +struct phy_req_info { + struct ethnl_req_info base; + struct phy_device_node *pdn; +}; + +#define PHY_REQINFO(__req_base) \ + container_of(__req_base, struct phy_req_info, base) + +const struct nla_policy ethnl_phy_get_policy[ETHTOOL_A_PHY_HEADER + 1] = { + [ETHTOOL_A_PHY_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), +}; + +/* Caller holds rtnl */ +static ssize_t +ethnl_phy_reply_size(const struct ethnl_req_info *req_base, + struct netlink_ext_ack *extack) +{ + struct phy_req_info *req_info = PHY_REQINFO(req_base); + struct phy_device_node *pdn = req_info->pdn; + struct phy_device *phydev = pdn->phy; + size_t size = 0; + + ASSERT_RTNL(); + + /* ETHTOOL_A_PHY_INDEX */ + size += nla_total_size(sizeof(u32)); + + /* ETHTOOL_A_DRVNAME */ + if (phydev->drv) + size += nla_total_size(strlen(phydev->drv->name) + 1); + + /* ETHTOOL_A_NAME */ + size += nla_total_size(strlen(dev_name(&phydev->mdio.dev)) + 1); + + /* ETHTOOL_A_PHY_UPSTREAM_TYPE */ + size += nla_total_size(sizeof(u32)); + + if (phy_on_sfp(phydev)) { + const char *upstream_sfp_name = sfp_get_name(pdn->parent_sfp_bus); + + /* ETHTOOL_A_PHY_UPSTREAM_SFP_NAME */ + if (upstream_sfp_name) + size += nla_total_size(strlen(upstream_sfp_name) + 1); + + /* ETHTOOL_A_PHY_UPSTREAM_INDEX */ + size += nla_total_size(sizeof(u32)); + } + + /* ETHTOOL_A_PHY_DOWNSTREAM_SFP_NAME */ + if (phydev->sfp_bus) { + const char *sfp_name = sfp_get_name(phydev->sfp_bus); + + if (sfp_name) + size += nla_total_size(strlen(sfp_name) + 1); + } + + return size; +} + +static int +ethnl_phy_fill_reply(const struct ethnl_req_info *req_base, struct sk_buff *skb) +{ + struct phy_req_info *req_info = PHY_REQINFO(req_base); + struct phy_device_node *pdn = req_info->pdn; + struct phy_device *phydev = pdn->phy; + enum phy_upstream ptype; + + ptype = pdn->upstream_type; + + if (nla_put_u32(skb, ETHTOOL_A_PHY_INDEX, phydev->phyindex) || + nla_put_string(skb, ETHTOOL_A_PHY_NAME, dev_name(&phydev->mdio.dev)) || + nla_put_u32(skb, ETHTOOL_A_PHY_UPSTREAM_TYPE, ptype)) + return -EMSGSIZE; + + if (phydev->drv && + nla_put_string(skb, ETHTOOL_A_PHY_DRVNAME, phydev->drv->name)) + return -EMSGSIZE; + + if (ptype == PHY_UPSTREAM_PHY) { + struct phy_device *upstream = pdn->upstream.phydev; + const char *sfp_upstream_name; + + /* Parent index */ + if (nla_put_u32(skb, ETHTOOL_A_PHY_UPSTREAM_INDEX, upstream->phyindex)) + return -EMSGSIZE; + + if (pdn->parent_sfp_bus) { + sfp_upstream_name = sfp_get_name(pdn->parent_sfp_bus); + if (sfp_upstream_name && + nla_put_string(skb, ETHTOOL_A_PHY_UPSTREAM_SFP_NAME, + sfp_upstream_name)) + return -EMSGSIZE; + } + } + + if (phydev->sfp_bus) { + const char *sfp_name = sfp_get_name(phydev->sfp_bus); + + if (sfp_name && + nla_put_string(skb, ETHTOOL_A_PHY_DOWNSTREAM_SFP_NAME, + sfp_name)) + return -EMSGSIZE; + } + + return 0; +} + +static int ethnl_phy_parse_request(struct ethnl_req_info *req_base, + struct nlattr **tb, + struct netlink_ext_ack *extack) +{ + struct phy_link_topology *topo = req_base->dev->link_topo; + struct phy_req_info *req_info = PHY_REQINFO(req_base); + struct phy_device *phydev; + + phydev = ethnl_req_get_phydev(req_base, tb[ETHTOOL_A_PHY_HEADER], + extack); + if (!phydev) + return 0; + + if (IS_ERR(phydev)) + return PTR_ERR(phydev); + + if (!topo) + return 0; + + req_info->pdn = xa_load(&topo->phys, phydev->phyindex); + + return 0; +} + +int ethnl_phy_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct phy_req_info req_info = {}; + struct nlattr **tb = info->attrs; + struct sk_buff *rskb; + void *reply_payload; + int reply_len; + int ret; + + ret = ethnl_parse_header_dev_get(&req_info.base, + tb[ETHTOOL_A_PHY_HEADER], + genl_info_net(info), info->extack, + true); + if (ret < 0) + return ret; + + rtnl_lock(); + + ret = ethnl_phy_parse_request(&req_info.base, tb, info->extack); + if (ret < 0) + goto err_unlock_rtnl; + + /* No PHY, return early */ + if (!req_info.pdn->phy) + goto err_unlock_rtnl; + + ret = ethnl_phy_reply_size(&req_info.base, info->extack); + if (ret < 0) + goto err_unlock_rtnl; + reply_len = ret + ethnl_reply_header_size(); + + rskb = ethnl_reply_init(reply_len, req_info.base.dev, + ETHTOOL_MSG_PHY_GET_REPLY, + ETHTOOL_A_PHY_HEADER, + info, &reply_payload); + if (!rskb) { + ret = -ENOMEM; + goto err_unlock_rtnl; + } + + ret = ethnl_phy_fill_reply(&req_info.base, rskb); + if (ret) + goto err_free_msg; + + rtnl_unlock(); + ethnl_parse_header_dev_put(&req_info.base); + genlmsg_end(rskb, reply_payload); + + return genlmsg_reply(rskb, info); + +err_free_msg: + nlmsg_free(rskb); +err_unlock_rtnl: + rtnl_unlock(); + ethnl_parse_header_dev_put(&req_info.base); + return ret; +} + +struct ethnl_phy_dump_ctx { + struct phy_req_info *phy_req_info; + unsigned long ifindex; + unsigned long phy_index; +}; + +int ethnl_phy_start(struct netlink_callback *cb) +{ + const struct genl_info *info = genl_info_dump(cb); + struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx; + int ret; + + BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx)); + + ctx->phy_req_info = kzalloc(sizeof(*ctx->phy_req_info), GFP_KERNEL); + if (!ctx->phy_req_info) + return -ENOMEM; + + ret = ethnl_parse_header_dev_get(&ctx->phy_req_info->base, + info->attrs[ETHTOOL_A_PHY_HEADER], + sock_net(cb->skb->sk), cb->extack, + false); + ctx->ifindex = 0; + ctx->phy_index = 0; + + if (ret) + kfree(ctx->phy_req_info); + + return ret; +} + +int ethnl_phy_done(struct netlink_callback *cb) +{ + struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx; + + if (ctx->phy_req_info->base.dev) + ethnl_parse_header_dev_put(&ctx->phy_req_info->base); + + kfree(ctx->phy_req_info); + + return 0; +} + +static int ethnl_phy_dump_one_dev(struct sk_buff *skb, struct net_device *dev, + struct netlink_callback *cb) +{ + struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx; + struct phy_req_info *pri = ctx->phy_req_info; + struct phy_device_node *pdn; + int ret = 0; + void *ehdr; + + pri->base.dev = dev; + + if (!dev->link_topo) + return 0; + + xa_for_each_start(&dev->link_topo->phys, ctx->phy_index, pdn, ctx->phy_index) { + ehdr = ethnl_dump_put(skb, cb, ETHTOOL_MSG_PHY_GET_REPLY); + if (!ehdr) { + ret = -EMSGSIZE; + break; + } + + ret = ethnl_fill_reply_header(skb, dev, ETHTOOL_A_PHY_HEADER); + if (ret < 0) { + genlmsg_cancel(skb, ehdr); + break; + } + + pri->pdn = pdn; + ret = ethnl_phy_fill_reply(&pri->base, skb); + if (ret < 0) { + genlmsg_cancel(skb, ehdr); + break; + } + + genlmsg_end(skb, ehdr); + } + + return ret; +} + +int ethnl_phy_dumpit(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx; + struct net *net = sock_net(skb->sk); + struct net_device *dev; + int ret = 0; + + rtnl_lock(); + + if (ctx->phy_req_info->base.dev) { + ret = ethnl_phy_dump_one_dev(skb, ctx->phy_req_info->base.dev, cb); + } else { + for_each_netdev_dump(net, dev, ctx->ifindex) { + ret = ethnl_phy_dump_one_dev(skb, dev, cb); + if (ret) + break; + + ctx->phy_index = 0; + } + } + rtnl_unlock(); + + return ret; +} diff --git a/net/ethtool/plca.c b/net/ethtool/plca.c index b1e2e3b5027f..d95d92f173a6 100644 --- a/net/ethtool/plca.c +++ b/net/ethtool/plca.c @@ -25,7 +25,7 @@ struct plca_reply_data { const struct nla_policy ethnl_plca_get_cfg_policy[] = { [ETHTOOL_A_PLCA_HEADER] = - NLA_POLICY_NESTED(ethnl_header_policy), + NLA_POLICY_NESTED(ethnl_header_policy_phy), }; static void plca_update_sint(int *dst, struct nlattr **tb, u32 attrid, @@ -58,10 +58,14 @@ static int plca_get_cfg_prepare_data(const struct ethnl_req_info *req_base, struct plca_reply_data *data = PLCA_REPDATA(reply_base); struct net_device *dev = reply_base->dev; const struct ethtool_phy_ops *ops; + struct nlattr **tb = info->attrs; + struct phy_device *phydev; int ret; + phydev = ethnl_req_get_phydev(req_base, tb[ETHTOOL_A_PLCA_HEADER], + info->extack); // check that the PHY device is available and connected - if (!dev->phydev) { + if (IS_ERR_OR_NULL(phydev)) { ret = -EOPNOTSUPP; goto out; } @@ -80,7 +84,7 @@ static int plca_get_cfg_prepare_data(const struct ethnl_req_info *req_base, memset(&data->plca_cfg, 0xff, sizeof_field(struct plca_reply_data, plca_cfg)); - ret = ops->get_plca_cfg(dev->phydev, &data->plca_cfg); + ret = ops->get_plca_cfg(phydev, &data->plca_cfg); ethnl_ops_complete(dev); out: @@ -129,7 +133,7 @@ static int plca_get_cfg_fill_reply(struct sk_buff *skb, const struct nla_policy ethnl_plca_set_cfg_policy[] = { [ETHTOOL_A_PLCA_HEADER] = - NLA_POLICY_NESTED(ethnl_header_policy), + NLA_POLICY_NESTED(ethnl_header_policy_phy), [ETHTOOL_A_PLCA_ENABLED] = NLA_POLICY_MAX(NLA_U8, 1), [ETHTOOL_A_PLCA_NODE_ID] = NLA_POLICY_MAX(NLA_U32, 255), [ETHTOOL_A_PLCA_NODE_CNT] = NLA_POLICY_RANGE(NLA_U32, 1, 255), @@ -141,15 +145,17 @@ const struct nla_policy ethnl_plca_set_cfg_policy[] = { static int ethnl_set_plca(struct ethnl_req_info *req_info, struct genl_info *info) { - struct net_device *dev = req_info->dev; const struct ethtool_phy_ops *ops; struct nlattr **tb = info->attrs; struct phy_plca_cfg plca_cfg; + struct phy_device *phydev; bool mod = false; int ret; + phydev = ethnl_req_get_phydev(req_info, tb[ETHTOOL_A_PLCA_HEADER], + info->extack); // check that the PHY device is available and connected - if (!dev->phydev) + if (IS_ERR_OR_NULL(phydev)) return -EOPNOTSUPP; ops = ethtool_phy_ops; @@ -168,7 +174,7 @@ ethnl_set_plca(struct ethnl_req_info *req_info, struct genl_info *info) if (!mod) return 0; - ret = ops->set_plca_cfg(dev->phydev, &plca_cfg, info->extack); + ret = ops->set_plca_cfg(phydev, &plca_cfg, info->extack); return ret < 0 ? ret : 1; } @@ -191,7 +197,7 @@ const struct ethnl_request_ops ethnl_plca_cfg_request_ops = { const struct nla_policy ethnl_plca_get_status_policy[] = { [ETHTOOL_A_PLCA_HEADER] = - NLA_POLICY_NESTED(ethnl_header_policy), + NLA_POLICY_NESTED(ethnl_header_policy_phy), }; static int plca_get_status_prepare_data(const struct ethnl_req_info *req_base, @@ -201,10 +207,14 @@ static int plca_get_status_prepare_data(const struct ethnl_req_info *req_base, struct plca_reply_data *data = PLCA_REPDATA(reply_base); struct net_device *dev = reply_base->dev; const struct ethtool_phy_ops *ops; + struct nlattr **tb = info->attrs; + struct phy_device *phydev; int ret; + phydev = ethnl_req_get_phydev(req_base, tb[ETHTOOL_A_PLCA_HEADER], + info->extack); // check that the PHY device is available and connected - if (!dev->phydev) { + if (IS_ERR_OR_NULL(phydev)) { ret = -EOPNOTSUPP; goto out; } @@ -223,7 +233,7 @@ static int plca_get_status_prepare_data(const struct ethnl_req_info *req_base, memset(&data->plca_st, 0xff, sizeof_field(struct plca_reply_data, plca_st)); - ret = ops->get_plca_status(dev->phydev, &data->plca_st); + ret = ops->get_plca_status(phydev, &data->plca_st); ethnl_ops_complete(dev); out: return ret; diff --git a/net/ethtool/pse-pd.c b/net/ethtool/pse-pd.c index ff81aa749784..507cb21d6bf0 100644 --- a/net/ethtool/pse-pd.c +++ b/net/ethtool/pse-pd.c @@ -28,17 +28,15 @@ struct pse_reply_data { /* PSE_GET */ const struct nla_policy ethnl_pse_get_policy[ETHTOOL_A_PSE_HEADER + 1] = { - [ETHTOOL_A_PSE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), + [ETHTOOL_A_PSE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy_phy), }; -static int pse_get_pse_attributes(struct net_device *dev, +static int pse_get_pse_attributes(struct phy_device *phydev, struct netlink_ext_ack *extack, struct pse_reply_data *data) { - struct phy_device *phydev = dev->phydev; - if (!phydev) { - NL_SET_ERR_MSG(extack, "No PHY is attached"); + NL_SET_ERR_MSG(extack, "No PHY found"); return -EOPNOTSUPP; } @@ -58,13 +56,20 @@ static int pse_prepare_data(const struct ethnl_req_info *req_base, { struct pse_reply_data *data = PSE_REPDATA(reply_base); struct net_device *dev = reply_base->dev; + struct nlattr **tb = info->attrs; + struct phy_device *phydev; int ret; ret = ethnl_ops_begin(dev); if (ret < 0) return ret; - ret = pse_get_pse_attributes(dev, info->extack, data); + phydev = ethnl_req_get_phydev(req_base, tb[ETHTOOL_A_PSE_HEADER], + info->extack); + if (IS_ERR(phydev)) + return -ENODEV; + + ret = pse_get_pse_attributes(phydev, info->extack, data); ethnl_ops_complete(dev); @@ -206,7 +211,7 @@ static void pse_cleanup_data(struct ethnl_reply_data *reply_base) /* PSE_SET */ const struct nla_policy ethnl_pse_set_policy[ETHTOOL_A_PSE_MAX + 1] = { - [ETHTOOL_A_PSE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), + [ETHTOOL_A_PSE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy_phy), [ETHTOOL_A_PODL_PSE_ADMIN_CONTROL] = NLA_POLICY_RANGE(NLA_U32, ETHTOOL_PODL_PSE_ADMIN_STATE_DISABLED, ETHTOOL_PODL_PSE_ADMIN_STATE_ENABLED), @@ -219,12 +224,12 @@ const struct nla_policy ethnl_pse_set_policy[ETHTOOL_A_PSE_MAX + 1] = { static int ethnl_set_pse_validate(struct ethnl_req_info *req_info, struct genl_info *info) { - struct net_device *dev = req_info->dev; struct nlattr **tb = info->attrs; struct phy_device *phydev; - phydev = dev->phydev; - if (!phydev) { + phydev = ethnl_req_get_phydev(req_info, tb[ETHTOOL_A_PSE_HEADER], + info->extack); + if (IS_ERR_OR_NULL(phydev)) { NL_SET_ERR_MSG(info->extack, "No PHY is attached"); return -EOPNOTSUPP; } @@ -255,12 +260,14 @@ ethnl_set_pse_validate(struct ethnl_req_info *req_info, struct genl_info *info) static int ethnl_set_pse(struct ethnl_req_info *req_info, struct genl_info *info) { - struct net_device *dev = req_info->dev; struct nlattr **tb = info->attrs; struct phy_device *phydev; int ret = 0; - phydev = dev->phydev; + phydev = ethnl_req_get_phydev(req_info, tb[ETHTOOL_A_PSE_HEADER], + info->extack); + if (IS_ERR_OR_NULL(phydev)) + return -ENODEV; if (tb[ETHTOOL_A_C33_PSE_AVAIL_PW_LIMIT]) { unsigned int pw_limit; diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c index 5c4c4505ab9a..e07386275e14 100644 --- a/net/ethtool/rss.c +++ b/net/ethtool/rss.c @@ -10,6 +10,7 @@ struct rss_req_info { struct rss_reply_data { struct ethnl_reply_data base; + bool no_key_fields; u32 indir_size; u32 hkey_size; u32 hfunc; @@ -27,6 +28,7 @@ struct rss_reply_data { const struct nla_policy ethnl_rss_get_policy[] = { [ETHTOOL_A_RSS_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_RSS_CONTEXT] = { .type = NLA_U32 }, + [ETHTOOL_A_RSS_START_CONTEXT] = { .type = NLA_U32 }, }; static int @@ -37,18 +39,18 @@ rss_parse_request(struct ethnl_req_info *req_info, struct nlattr **tb, if (tb[ETHTOOL_A_RSS_CONTEXT]) request->rss_context = nla_get_u32(tb[ETHTOOL_A_RSS_CONTEXT]); + if (tb[ETHTOOL_A_RSS_START_CONTEXT]) { + NL_SET_BAD_ATTR(extack, tb[ETHTOOL_A_RSS_START_CONTEXT]); + return -EINVAL; + } return 0; } static int -rss_prepare_data(const struct ethnl_req_info *req_base, - struct ethnl_reply_data *reply_base, - const struct genl_info *info) +rss_prepare_get(const struct rss_req_info *request, struct net_device *dev, + struct rss_reply_data *data, const struct genl_info *info) { - struct rss_reply_data *data = RSS_REPDATA(reply_base); - struct rss_req_info *request = RSS_REQINFO(req_base); - struct net_device *dev = reply_base->dev; struct ethtool_rxfh_param rxfh = {}; const struct ethtool_ops *ops; u32 total_size, indir_bytes; @@ -56,12 +58,6 @@ rss_prepare_data(const struct ethnl_req_info *req_base, int ret; ops = dev->ethtool_ops; - if (!ops->get_rxfh) - return -EOPNOTSUPP; - - /* Some drivers don't handle rss_context */ - if (request->rss_context && !ops->cap_rss_ctx_supported) - return -EOPNOTSUPP; ret = ethnl_ops_begin(dev); if (ret < 0) @@ -91,7 +87,6 @@ rss_prepare_data(const struct ethnl_req_info *req_base, rxfh.indir = data->indir_table; rxfh.key_size = data->hkey_size; rxfh.key = data->hkey; - rxfh.rss_context = request->rss_context; ret = ops->get_rxfh(dev, &rxfh); if (ret) @@ -105,6 +100,67 @@ out_ops: } static int +rss_prepare_ctx(const struct rss_req_info *request, struct net_device *dev, + struct rss_reply_data *data, const struct genl_info *info) +{ + struct ethtool_rxfh_context *ctx; + u32 total_size, indir_bytes; + u8 *rss_config; + + ctx = xa_load(&dev->ethtool->rss_ctx, request->rss_context); + if (!ctx) + return -ENOENT; + + data->indir_size = ctx->indir_size; + data->hkey_size = ctx->key_size; + data->hfunc = ctx->hfunc; + data->input_xfrm = ctx->input_xfrm; + + indir_bytes = data->indir_size * sizeof(u32); + total_size = indir_bytes + data->hkey_size; + rss_config = kzalloc(total_size, GFP_KERNEL); + if (!rss_config) + return -ENOMEM; + + data->indir_table = (u32 *)rss_config; + memcpy(data->indir_table, ethtool_rxfh_context_indir(ctx), indir_bytes); + + if (data->hkey_size) { + data->hkey = rss_config + indir_bytes; + memcpy(data->hkey, ethtool_rxfh_context_key(ctx), + data->hkey_size); + } + + return 0; +} + +static int +rss_prepare_data(const struct ethnl_req_info *req_base, + struct ethnl_reply_data *reply_base, + const struct genl_info *info) +{ + struct rss_reply_data *data = RSS_REPDATA(reply_base); + struct rss_req_info *request = RSS_REQINFO(req_base); + struct net_device *dev = reply_base->dev; + const struct ethtool_ops *ops; + + ops = dev->ethtool_ops; + if (!ops->get_rxfh) + return -EOPNOTSUPP; + + /* Some drivers don't handle rss_context */ + if (request->rss_context) { + if (!ops->cap_rss_ctx_supported && !ops->create_rxfh_context) + return -EOPNOTSUPP; + + data->no_key_fields = !ops->rxfh_per_ctx_key; + return rss_prepare_ctx(request, dev, data, info); + } + + return rss_prepare_get(request, dev, data, info); +} + +static int rss_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { @@ -131,13 +187,18 @@ rss_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, nla_put_u32(skb, ETHTOOL_A_RSS_CONTEXT, request->rss_context)) return -EMSGSIZE; + if ((data->indir_size && + nla_put(skb, ETHTOOL_A_RSS_INDIR, + sizeof(u32) * data->indir_size, data->indir_table))) + return -EMSGSIZE; + + if (data->no_key_fields) + return 0; + if ((data->hfunc && nla_put_u32(skb, ETHTOOL_A_RSS_HFUNC, data->hfunc)) || (data->input_xfrm && nla_put_u32(skb, ETHTOOL_A_RSS_INPUT_XFRM, data->input_xfrm)) || - (data->indir_size && - nla_put(skb, ETHTOOL_A_RSS_INDIR, - sizeof(u32) * data->indir_size, data->indir_table)) || (data->hkey_size && nla_put(skb, ETHTOOL_A_RSS_HKEY, data->hkey_size, data->hkey))) return -EMSGSIZE; @@ -152,6 +213,146 @@ static void rss_cleanup_data(struct ethnl_reply_data *reply_base) kfree(data->indir_table); } +struct rss_nl_dump_ctx { + unsigned long ifindex; + unsigned long ctx_idx; + + /* User wants to only dump contexts from given ifindex */ + unsigned int match_ifindex; + unsigned int start_ctx; +}; + +static struct rss_nl_dump_ctx *rss_dump_ctx(struct netlink_callback *cb) +{ + NL_ASSERT_DUMP_CTX_FITS(struct rss_nl_dump_ctx); + + return (struct rss_nl_dump_ctx *)cb->ctx; +} + +int ethnl_rss_dump_start(struct netlink_callback *cb) +{ + const struct genl_info *info = genl_info_dump(cb); + struct rss_nl_dump_ctx *ctx = rss_dump_ctx(cb); + struct ethnl_req_info req_info = {}; + struct nlattr **tb = info->attrs; + int ret; + + /* Filtering by context not supported */ + if (tb[ETHTOOL_A_RSS_CONTEXT]) { + NL_SET_BAD_ATTR(info->extack, tb[ETHTOOL_A_RSS_CONTEXT]); + return -EINVAL; + } + if (tb[ETHTOOL_A_RSS_START_CONTEXT]) { + ctx->start_ctx = nla_get_u32(tb[ETHTOOL_A_RSS_START_CONTEXT]); + ctx->ctx_idx = ctx->start_ctx; + } + + ret = ethnl_parse_header_dev_get(&req_info, + tb[ETHTOOL_A_RSS_HEADER], + sock_net(cb->skb->sk), cb->extack, + false); + if (req_info.dev) { + ctx->match_ifindex = req_info.dev->ifindex; + ctx->ifindex = ctx->match_ifindex; + ethnl_parse_header_dev_put(&req_info); + req_info.dev = NULL; + } + + return ret; +} + +static int +rss_dump_one_ctx(struct sk_buff *skb, struct netlink_callback *cb, + struct net_device *dev, u32 rss_context) +{ + const struct genl_info *info = genl_info_dump(cb); + struct rss_reply_data data = {}; + struct rss_req_info req = {}; + void *ehdr; + int ret; + + req.rss_context = rss_context; + + ehdr = ethnl_dump_put(skb, cb, ETHTOOL_MSG_RSS_GET_REPLY); + if (!ehdr) + return -EMSGSIZE; + + ret = ethnl_fill_reply_header(skb, dev, ETHTOOL_A_RSS_HEADER); + if (ret < 0) + goto err_cancel; + + /* Context 0 is not currently storred or cached in the XArray */ + if (!rss_context) + ret = rss_prepare_get(&req, dev, &data, info); + else + ret = rss_prepare_ctx(&req, dev, &data, info); + if (ret) + goto err_cancel; + + ret = rss_fill_reply(skb, &req.base, &data.base); + if (ret) + goto err_cleanup; + genlmsg_end(skb, ehdr); + + rss_cleanup_data(&data.base); + return 0; + +err_cleanup: + rss_cleanup_data(&data.base); +err_cancel: + genlmsg_cancel(skb, ehdr); + return ret; +} + +static int +rss_dump_one_dev(struct sk_buff *skb, struct netlink_callback *cb, + struct net_device *dev) +{ + struct rss_nl_dump_ctx *ctx = rss_dump_ctx(cb); + int ret; + + if (!dev->ethtool_ops->get_rxfh) + return 0; + + if (!ctx->ctx_idx) { + ret = rss_dump_one_ctx(skb, cb, dev, 0); + if (ret) + return ret; + ctx->ctx_idx++; + } + + for (; xa_find(&dev->ethtool->rss_ctx, &ctx->ctx_idx, + ULONG_MAX, XA_PRESENT); ctx->ctx_idx++) { + ret = rss_dump_one_ctx(skb, cb, dev, ctx->ctx_idx); + if (ret) + return ret; + } + ctx->ctx_idx = ctx->start_ctx; + + return 0; +} + +int ethnl_rss_dumpit(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct rss_nl_dump_ctx *ctx = rss_dump_ctx(cb); + struct net *net = sock_net(skb->sk); + struct net_device *dev; + int ret = 0; + + rtnl_lock(); + for_each_netdev_dump(net, dev, ctx->ifindex) { + if (ctx->match_ifindex && ctx->match_ifindex != ctx->ifindex) + break; + + ret = rss_dump_one_dev(skb, cb, dev); + if (ret) + break; + } + rtnl_unlock(); + + return ret; +} + const struct ethnl_request_ops ethnl_rss_request_ops = { .request_cmd = ETHTOOL_MSG_RSS_GET, .reply_cmd = ETHTOOL_MSG_RSS_GET_REPLY, diff --git a/net/ethtool/strset.c b/net/ethtool/strset.c index c678b484a079..b3382b3cf325 100644 --- a/net/ethtool/strset.c +++ b/net/ethtool/strset.c @@ -126,7 +126,7 @@ struct strset_reply_data { const struct nla_policy ethnl_strset_get_policy[] = { [ETHTOOL_A_STRSET_HEADER] = - NLA_POLICY_NESTED(ethnl_header_policy), + NLA_POLICY_NESTED(ethnl_header_policy_phy), [ETHTOOL_A_STRSET_STRINGSETS] = { .type = NLA_NESTED }, [ETHTOOL_A_STRSET_COUNTS_ONLY] = { .type = NLA_FLAG }, }; @@ -233,17 +233,18 @@ static void strset_cleanup_data(struct ethnl_reply_data *reply_base) } static int strset_prepare_set(struct strset_info *info, struct net_device *dev, - unsigned int id, bool counts_only) + struct phy_device *phydev, unsigned int id, + bool counts_only) { const struct ethtool_phy_ops *phy_ops = ethtool_phy_ops; const struct ethtool_ops *ops = dev->ethtool_ops; void *strings; int count, ret; - if (id == ETH_SS_PHY_STATS && dev->phydev && + if (id == ETH_SS_PHY_STATS && phydev && !ops->get_ethtool_phy_stats && phy_ops && phy_ops->get_sset_count) - ret = phy_ops->get_sset_count(dev->phydev); + ret = phy_ops->get_sset_count(phydev); else if (ops->get_sset_count && ops->get_strings) ret = ops->get_sset_count(dev, id); else @@ -258,10 +259,10 @@ static int strset_prepare_set(struct strset_info *info, struct net_device *dev, strings = kcalloc(count, ETH_GSTRING_LEN, GFP_KERNEL); if (!strings) return -ENOMEM; - if (id == ETH_SS_PHY_STATS && dev->phydev && + if (id == ETH_SS_PHY_STATS && phydev && !ops->get_ethtool_phy_stats && phy_ops && phy_ops->get_strings) - phy_ops->get_strings(dev->phydev, strings); + phy_ops->get_strings(phydev, strings); else ops->get_strings(dev, id, strings); info->strings = strings; @@ -279,6 +280,8 @@ static int strset_prepare_data(const struct ethnl_req_info *req_base, const struct strset_req_info *req_info = STRSET_REQINFO(req_base); struct strset_reply_data *data = STRSET_REPDATA(reply_base); struct net_device *dev = reply_base->dev; + struct nlattr **tb = info->attrs; + struct phy_device *phydev; unsigned int i; int ret; @@ -289,14 +292,20 @@ static int strset_prepare_data(const struct ethnl_req_info *req_base, for (i = 0; i < ETH_SS_COUNT; i++) { if ((req_info->req_ids & (1U << i)) && data->sets[i].per_dev) { - if (info) - GENL_SET_ERR_MSG(info, "requested per device strings without dev"); + GENL_SET_ERR_MSG(info, "requested per device strings without dev"); return -EINVAL; } } return 0; } + phydev = ethnl_req_get_phydev(req_base, tb[ETHTOOL_A_HEADER_FLAGS], + info->extack); + + /* phydev can be NULL, check for errors only */ + if (IS_ERR(phydev)) + return PTR_ERR(phydev); + ret = ethnl_ops_begin(dev); if (ret < 0) goto err_strset; @@ -305,7 +314,7 @@ static int strset_prepare_data(const struct ethnl_req_info *req_base, !data->sets[i].per_dev) continue; - ret = strset_prepare_set(&data->sets[i], dev, i, + ret = strset_prepare_set(&data->sets[i], dev, phydev, i, req_info->counts_only); if (ret < 0) goto err_ops; diff --git a/net/handshake/netlink.c b/net/handshake/netlink.c index 89637e732866..7e46d130dce2 100644 --- a/net/handshake/netlink.c +++ b/net/handshake/netlink.c @@ -153,7 +153,7 @@ int handshake_nl_done_doit(struct sk_buff *skb, struct genl_info *info) if (!req) { err = -EBUSY; trace_handshake_cmd_done_err(net, req, sock->sk, err); - fput(sock->file); + sockfd_put(sock); return err; } @@ -164,7 +164,7 @@ int handshake_nl_done_doit(struct sk_buff *skb, struct genl_info *info) status = nla_get_u32(info->attrs[HANDSHAKE_A_DONE_STATUS]); handshake_complete(req, status, info); - fput(sock->file); + sockfd_put(sock); return 0; } diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 8e94ed7c56a0..6d2c97f8e9ef 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -661,7 +661,8 @@ config TCP_CONG_CDG For further details see: D.A. Hayes and G. Armitage. "Revisiting TCP congestion control using - delay gradients." In Networking 2011. Preprint: http://goo.gl/No3vdg + delay gradients." In Networking 2011. Preprint: + http://caia.swin.edu.au/cv/dahayes/content/networking2011-cdg-preprint.pdf config TCP_CONG_BBR tristate "BBR TCP" diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index d96f3e452fef..ab76744383cf 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -216,17 +216,27 @@ static void devinet_sysctl_unregister(struct in_device *idev) /* Locks all the inet devices. */ -static struct in_ifaddr *inet_alloc_ifa(void) +static struct in_ifaddr *inet_alloc_ifa(struct in_device *in_dev) { - return kzalloc(sizeof(struct in_ifaddr), GFP_KERNEL_ACCOUNT); + struct in_ifaddr *ifa; + + ifa = kzalloc(sizeof(*ifa), GFP_KERNEL_ACCOUNT); + if (!ifa) + return NULL; + + in_dev_hold(in_dev); + ifa->ifa_dev = in_dev; + + INIT_HLIST_NODE(&ifa->hash); + + return ifa; } static void inet_rcu_free_ifa(struct rcu_head *head) { struct in_ifaddr *ifa = container_of(head, struct in_ifaddr, rcu_head); - if (ifa->ifa_dev) - in_dev_put(ifa->ifa_dev); + in_dev_put(ifa->ifa_dev); kfree(ifa); } @@ -574,17 +584,9 @@ static int inet_set_ifa(struct net_device *dev, struct in_ifaddr *ifa) ASSERT_RTNL(); - if (!in_dev) { - inet_free_ifa(ifa); - return -ENOBUFS; - } ipv4_devconf_setall(in_dev); neigh_parms_data_state_setall(in_dev->arp_parms); - if (ifa->ifa_dev != in_dev) { - WARN_ON(ifa->ifa_dev); - in_dev_hold(in_dev); - ifa->ifa_dev = in_dev; - } + if (ipv4_is_loopback(ifa->ifa_local)) ifa->ifa_scope = RT_SCOPE_HOST; return inet_insert_ifa(ifa); @@ -701,8 +703,6 @@ errout: return err; } -#define INFINITY_LIFE_TIME 0xFFFFFFFF - static void check_lifetime(struct work_struct *work) { unsigned long now, next, next_sec, next_sched; @@ -875,7 +875,7 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh, if (!in_dev) goto errout; - ifa = inet_alloc_ifa(); + ifa = inet_alloc_ifa(in_dev); if (!ifa) /* * A potential indev allocation can be left alive, it stays @@ -885,19 +885,15 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh, ipv4_devconf_setall(in_dev); neigh_parms_data_state_setall(in_dev->arp_parms); - in_dev_hold(in_dev); if (!tb[IFA_ADDRESS]) tb[IFA_ADDRESS] = tb[IFA_LOCAL]; - INIT_HLIST_NODE(&ifa->hash); ifa->ifa_prefixlen = ifm->ifa_prefixlen; ifa->ifa_mask = inet_make_mask(ifm->ifa_prefixlen); ifa->ifa_flags = tb[IFA_FLAGS] ? nla_get_u32(tb[IFA_FLAGS]) : ifm->ifa_flags; ifa->ifa_scope = ifm->ifa_scope; - ifa->ifa_dev = in_dev; - ifa->ifa_local = nla_get_in_addr(tb[IFA_LOCAL]); ifa->ifa_address = nla_get_in_addr(tb[IFA_ADDRESS]); @@ -1184,10 +1180,12 @@ int devinet_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr) if (!ifa) { ret = -ENOBUFS; - ifa = inet_alloc_ifa(); + if (!in_dev) + break; + ifa = inet_alloc_ifa(in_dev); if (!ifa) break; - INIT_HLIST_NODE(&ifa->hash); + if (colon) memcpy(ifa->ifa_label, ifr->ifr_name, IFNAMSIZ); else @@ -1586,16 +1584,13 @@ static int inetdev_event(struct notifier_block *this, unsigned long event, if (!inetdev_valid_mtu(dev->mtu)) break; if (dev->flags & IFF_LOOPBACK) { - struct in_ifaddr *ifa = inet_alloc_ifa(); + struct in_ifaddr *ifa = inet_alloc_ifa(in_dev); if (ifa) { - INIT_HLIST_NODE(&ifa->hash); ifa->ifa_local = ifa->ifa_address = htonl(INADDR_LOOPBACK); ifa->ifa_prefixlen = 8; ifa->ifa_mask = inet_make_mask(8); - in_dev_hold(in_dev); - ifa->ifa_dev = in_dev; ifa->ifa_scope = RT_SCOPE_HOST; memcpy(ifa->ifa_label, dev->name, IFNAMSIZ); set_ifa_lifetime(ifa, INFINITY_LIFE_TIME, @@ -1948,8 +1943,7 @@ static void rtmsg_ifa(int event, struct in_ifaddr *ifa, struct nlmsghdr *nlh, rtnl_notify(skb, net, portid, RTNLGRP_IPV4_IFADDR, nlh, GFP_KERNEL); return; errout: - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_IPV4_IFADDR, err); + rtnl_set_sk_err(net, RTNLGRP_IPV4_IFADDR, err); } static size_t inet_get_link_af_size(const struct net_device *dev, @@ -2145,8 +2139,7 @@ void inet_netconf_notify_devconf(struct net *net, int event, int type, rtnl_notify(skb, net, 0, RTNLGRP_IPV4_NETCONF, NULL, GFP_KERNEL); return; errout: - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_IPV4_NETCONF, err); + rtnl_set_sk_err(net, RTNLGRP_IPV4_NETCONF, err); } static const struct nla_policy devconf_ipv4_policy[NETCONFA_MAX+1] = { diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 7ad2cafb9276..793e6781399a 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -293,7 +293,7 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb) .flowi4_iif = LOOPBACK_IFINDEX, .flowi4_l3mdev = l3mdev_master_ifindex_rcu(dev), .daddr = ip_hdr(skb)->saddr, - .flowi4_tos = ip_hdr(skb)->tos & IPTOS_RT_MASK, + .flowi4_tos = ip_hdr(skb)->tos & INET_DSCP_MASK, .flowi4_scope = scope, .flowi4_mark = vmark ? skb->mark : 0, }; @@ -1343,7 +1343,7 @@ static void nl_fib_lookup(struct net *net, struct fib_result_nl *frn) struct flowi4 fl4 = { .flowi4_mark = frn->fl_mark, .daddr = frn->fl_addr, - .flowi4_tos = frn->fl_tos, + .flowi4_tos = frn->fl_tos & INET_DSCP_MASK, .flowi4_scope = frn->fl_scope, }; struct fib_table *tb; diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 5bdd1c016009..c26776b71e97 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -186,7 +186,7 @@ INDIRECT_CALLABLE_SCOPE int fib4_rule_match(struct fib_rule *rule, ((daddr ^ r->dst) & r->dstmask)) return 0; - if (r->dscp && r->dscp != inet_dsfield_to_dscp(fl4->flowi4_tos)) + if (r->dscp && !fib_dscp_masked_match(r->dscp, fl4)) return 0; if (rule->ip_proto && (rule->ip_proto != fl4->flowi4_proto)) diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 2b57cd2b96e2..ba2df3d2ac15 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -543,8 +543,7 @@ void rtmsg_fib(int event, __be32 key, struct fib_alias *fa, info->nlh, GFP_KERNEL); return; errout: - if (err < 0) - rtnl_set_sk_err(info->nl_net, RTNLGRP_IPV4_ROUTE, err); + rtnl_set_sk_err(info->nl_net, RTNLGRP_IPV4_ROUTE, err); } static int fib_detect_death(struct fib_info *fi, int order, @@ -2066,8 +2065,7 @@ static void fib_select_default(const struct flowi4 *flp, struct fib_result *res) if (fa->fa_slen != slen) continue; - if (fa->fa_dscp && - fa->fa_dscp != inet_dsfield_to_dscp(flp->flowi4_tos)) + if (fa->fa_dscp && !fib_dscp_masked_match(fa->fa_dscp, flp)) continue; if (fa->tb_id != tb->tb_id) continue; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 8f30e3f00b7f..09e31757e96c 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1580,8 +1580,7 @@ found: if (index >= (1ul << fa->fa_slen)) continue; } - if (fa->fa_dscp && - inet_dscp_to_dsfield(fa->fa_dscp) != flp->flowi4_tos) + if (fa->fa_dscp && !fib_dscp_masked_match(fa->fa_dscp, flp)) continue; /* Paired with WRITE_ONCE() in fib_release_info() */ if (READ_ONCE(fi->fib_dead)) diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index ab6d0d98dbc3..b8f56d03fcbb 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -545,7 +545,7 @@ static struct rtable *icmp_route_lookup(struct net *net, orefdst = skb_in->_skb_refdst; /* save old refdst */ skb_dst_set(skb_in, NULL); err = ip_route_input(skb_in, fl4_dec.daddr, fl4_dec.saddr, - RT_TOS(tos), rt2->dst.dev); + tos, rt2->dst.dev); dst_release(&rt2->dst); rt2 = skb_rtable(skb_in); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 64d07b842e73..ce4d77f49243 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -236,7 +236,7 @@ static bool inet_bhash2_conflict(const struct sock *sk, #define sk_for_each_bound_bhash(__sk, __tb2, __tb) \ hlist_for_each_entry(__tb2, &(__tb)->bhash2, bhash_node) \ - sk_for_each_bound(sk2, &(__tb2)->owners) + sk_for_each_bound((__sk), &(__tb2)->owners) /* This should be called only when the tb and tb2 hashbuckets' locks are held */ static int inet_csk_bind_conflict(const struct sock *sk, diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 9712cdb8087c..67639309163d 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -442,7 +442,7 @@ static int inet_twsk_diag_fill(struct sock *sk, inet_diag_msg_common_fill(r, sk); r->idiag_retrans = 0; - r->idiag_state = tw->tw_substate; + r->idiag_state = READ_ONCE(tw->tw_substate); r->idiag_timer = 3; tmo = tw->tw_timer.expires - jiffies; r->idiag_expires = jiffies_delta_to_msecs(tmo); @@ -1209,7 +1209,7 @@ next_chunk: if (num < s_num) goto next_normal; state = (sk->sk_state == TCP_TIME_WAIT) ? - inet_twsk(sk)->tw_substate : sk->sk_state; + READ_ONCE(inet_twsk(sk)->tw_substate) : sk->sk_state; if (!(idiag_states & (1 << state))) goto next_normal; if (r->sdiag_family != AF_UNSPEC && diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 48d0d494185b..9bfcfd016e18 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -310,7 +310,7 @@ inet_lhash2_bucket_sk(struct inet_hashinfo *h, struct sock *sk) return inet_lhash2_bucket(h, hash); } -static inline int compute_score(struct sock *sk, struct net *net, +static inline int compute_score(struct sock *sk, const struct net *net, const unsigned short hnum, const __be32 daddr, const int dif, const int sdif) { @@ -348,7 +348,7 @@ static inline int compute_score(struct sock *sk, struct net *net, * Return: NULL if sk doesn't have SO_REUSEPORT set, otherwise a pointer to * the selected sock or an error. */ -struct sock *inet_lookup_reuseport(struct net *net, struct sock *sk, +struct sock *inet_lookup_reuseport(const struct net *net, struct sock *sk, struct sk_buff *skb, int doff, __be32 saddr, __be16 sport, __be32 daddr, unsigned short hnum, @@ -374,7 +374,7 @@ EXPORT_SYMBOL_GPL(inet_lookup_reuseport); */ /* called with rcu_read_lock() : No refcount taken on the socket */ -static struct sock *inet_lhash2_lookup(struct net *net, +static struct sock *inet_lhash2_lookup(const struct net *net, struct inet_listen_hashbucket *ilb2, struct sk_buff *skb, int doff, const __be32 saddr, __be16 sport, @@ -401,7 +401,7 @@ static struct sock *inet_lhash2_lookup(struct net *net, return result; } -struct sock *inet_lookup_run_sk_lookup(struct net *net, +struct sock *inet_lookup_run_sk_lookup(const struct net *net, int protocol, struct sk_buff *skb, int doff, __be32 saddr, __be16 sport, @@ -423,7 +423,7 @@ struct sock *inet_lookup_run_sk_lookup(struct net *net, return sk; } -struct sock *__inet_lookup_listener(struct net *net, +struct sock *__inet_lookup_listener(const struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const __be32 saddr, __be16 sport, @@ -488,7 +488,7 @@ void sock_edemux(struct sk_buff *skb) } EXPORT_SYMBOL(sock_edemux); -struct sock *__inet_lookup_established(struct net *net, +struct sock *__inet_lookup_established(const struct net *net, struct inet_hashinfo *hashinfo, const __be32 saddr, const __be16 sport, const __be32 daddr, const u16 hnum, diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 6c750bd13dd8..b0eda745e3bc 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -62,6 +62,7 @@ #include <net/fib_rules.h> #include <linux/netconf.h> #include <net/rtnh.h> +#include <net/inet_dscp.h> #include <linux/nospec.h> @@ -2080,7 +2081,7 @@ static struct mr_table *ipmr_rt_fib_lookup(struct net *net, struct sk_buff *skb) struct flowi4 fl4 = { .daddr = iph->daddr, .saddr = iph->saddr, - .flowi4_tos = RT_TOS(iph->tos), + .flowi4_tos = iph->tos & INET_DSCP_MASK, .flowi4_oif = (rt_is_output_route(rt) ? skb->dev->ifindex : 0), .flowi4_iif = (rt_is_output_route(rt) ? @@ -2406,8 +2407,7 @@ static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc, errout: kfree_skb(skb); - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_IPV4_MROUTE, err); + rtnl_set_sk_err(net, RTNLGRP_IPV4_MROUTE, err); } static size_t igmpmsg_netlink_msgsize(size_t payloadlen) diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c index ded5bef02f77..1ce7a1655b97 100644 --- a/net/ipv4/netfilter/ipt_rpfilter.c +++ b/net/ipv4/netfilter/ipt_rpfilter.c @@ -8,6 +8,7 @@ #include <linux/module.h> #include <linux/skbuff.h> #include <linux/netdevice.h> +#include <net/inet_dscp.h> #include <linux/ip.h> #include <net/ip.h> #include <net/ip_fib.h> @@ -75,7 +76,7 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) flow.daddr = iph->saddr; flow.saddr = rpfilter_get_saddr(iph->daddr); flow.flowi4_mark = info->flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0; - flow.flowi4_tos = iph->tos & IPTOS_RT_MASK; + flow.flowi4_tos = iph->tos & INET_DSCP_MASK; flow.flowi4_scope = RT_SCOPE_UNIVERSE; flow.flowi4_l3mdev = l3mdev_master_ifindex_rcu(xt_in(par)); flow.flowi4_uid = sock_net_uid(xt_net(par), NULL); diff --git a/net/ipv4/netfilter/nft_dup_ipv4.c b/net/ipv4/netfilter/nft_dup_ipv4.c index a522c3a3be52..ef5dd88107dd 100644 --- a/net/ipv4/netfilter/nft_dup_ipv4.c +++ b/net/ipv4/netfilter/nft_dup_ipv4.c @@ -40,13 +40,13 @@ static int nft_dup_ipv4_init(const struct nft_ctx *ctx, if (tb[NFTA_DUP_SREG_ADDR] == NULL) return -EINVAL; - err = nft_parse_register_load(tb[NFTA_DUP_SREG_ADDR], &priv->sreg_addr, + err = nft_parse_register_load(ctx, tb[NFTA_DUP_SREG_ADDR], &priv->sreg_addr, sizeof(struct in_addr)); if (err < 0) return err; if (tb[NFTA_DUP_SREG_DEV]) - err = nft_parse_register_load(tb[NFTA_DUP_SREG_DEV], + err = nft_parse_register_load(ctx, tb[NFTA_DUP_SREG_DEV], &priv->sreg_dev, sizeof(int)); return err; diff --git a/net/ipv4/netfilter/nft_fib_ipv4.c b/net/ipv4/netfilter/nft_fib_ipv4.c index 9eee535c64dd..00da1332bbf1 100644 --- a/net/ipv4/netfilter/nft_fib_ipv4.c +++ b/net/ipv4/netfilter/nft_fib_ipv4.c @@ -10,6 +10,7 @@ #include <net/netfilter/nf_tables.h> #include <net/netfilter/nft_fib.h> +#include <net/inet_dscp.h> #include <net/ip_fib.h> #include <net/route.h> @@ -22,8 +23,6 @@ static __be32 get_saddr(__be32 addr) return addr; } -#define DSCP_BITS 0xfc - void nft_fib4_eval_type(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { @@ -110,7 +109,7 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs, if (priv->flags & NFTA_FIB_F_MARK) fl4.flowi4_mark = pkt->skb->mark; - fl4.flowi4_tos = iph->tos & DSCP_BITS; + fl4.flowi4_tos = iph->tos & INET_DSCP_MASK; if (priv->flags & NFTA_FIB_F_DADDR) { fl4.daddr = iph->daddr; diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 6b9787ee8601..93aaea0006ba 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -865,15 +865,18 @@ out: } static int nla_put_nh_group(struct sk_buff *skb, struct nexthop *nh, - u32 op_flags) + u32 op_flags, u32 *resp_op_flags) { struct nh_group *nhg = rtnl_dereference(nh->nh_grp); struct nexthop_grp *p; size_t len = nhg->num_nh * sizeof(*p); struct nlattr *nla; u16 group_type = 0; + u16 weight; int i; + *resp_op_flags |= NHA_OP_FLAG_RESP_GRP_RESVD_0; + if (nhg->hash_threshold) group_type = NEXTHOP_GRP_TYPE_MPATH; else if (nhg->resilient) @@ -888,9 +891,12 @@ static int nla_put_nh_group(struct sk_buff *skb, struct nexthop *nh, p = nla_data(nla); for (i = 0; i < nhg->num_nh; ++i) { + weight = nhg->nh_entries[i].weight - 1; + *p++ = (struct nexthop_grp) { .id = nhg->nh_entries[i].nh->id, - .weight = nhg->nh_entries[i].weight - 1, + .weight = weight, + .weight_high = weight >> 8, }; } @@ -934,10 +940,12 @@ static int nh_fill_node(struct sk_buff *skb, struct nexthop *nh, if (nh->is_group) { struct nh_group *nhg = rtnl_dereference(nh->nh_grp); + u32 resp_op_flags = 0; if (nhg->fdb_nh && nla_put_flag(skb, NHA_FDB)) goto nla_put_failure; - if (nla_put_nh_group(skb, nh, op_flags)) + if (nla_put_nh_group(skb, nh, op_flags, &resp_op_flags) || + nla_put_u32(skb, NHA_OP_FLAGS, resp_op_flags)) goto nla_put_failure; goto out; } @@ -1050,7 +1058,9 @@ static size_t nh_nlmsg_size(struct nexthop *nh) sz += nla_total_size(4); /* NHA_ID */ if (nh->is_group) - sz += nh_nlmsg_size_grp(nh); + sz += nh_nlmsg_size_grp(nh) + + nla_total_size(4) + /* NHA_OP_FLAGS */ + 0; else sz += nh_nlmsg_size_single(nh); @@ -1080,8 +1090,7 @@ static void nexthop_notify(int event, struct nexthop *nh, struct nl_info *info) info->nlh, gfp_any()); return; errout: - if (err < 0) - rtnl_set_sk_err(info->nl_net, RTNLGRP_NEXTHOP, err); + rtnl_set_sk_err(info->nl_net, RTNLGRP_NEXTHOP, err); } static unsigned long nh_res_bucket_used_time(const struct nh_res_bucket *bucket) @@ -1201,8 +1210,7 @@ static void nexthop_bucket_notify(struct nh_res_table *res_table, rtnl_notify(skb, nh->net, 0, RTNLGRP_NEXTHOP, NULL, GFP_KERNEL); return; errout: - if (err < 0) - rtnl_set_sk_err(nh->net, RTNLGRP_NEXTHOP, err); + rtnl_set_sk_err(nh->net, RTNLGRP_NEXTHOP, err); } static bool valid_group_nh(struct nexthop *nh, unsigned int npaths, @@ -1280,11 +1288,14 @@ static int nh_check_attr_group(struct net *net, nhg = nla_data(tb[NHA_GROUP]); for (i = 0; i < len; ++i) { - if (nhg[i].resvd1 || nhg[i].resvd2) { - NL_SET_ERR_MSG(extack, "Reserved fields in nexthop_grp must be 0"); + if (nhg[i].resvd2) { + NL_SET_ERR_MSG(extack, "Reserved field in nexthop_grp must be 0"); return -EINVAL; } - if (nhg[i].weight > 254) { + if (nexthop_grp_weight(&nhg[i]) == 0) { + /* 0xffff got passed in, representing weight of 0x10000, + * which is too heavy. + */ NL_SET_ERR_MSG(extack, "Invalid value for weight"); return -EINVAL; } @@ -1880,9 +1891,9 @@ static void nh_res_table_cancel_upkeep(struct nh_res_table *res_table) static void nh_res_group_rebalance(struct nh_group *nhg, struct nh_res_table *res_table) { - int prev_upper_bound = 0; - int total = 0; - int w = 0; + u16 prev_upper_bound = 0; + u32 total = 0; + u32 w = 0; int i; INIT_LIST_HEAD(&res_table->uw_nh_entries); @@ -1892,11 +1903,12 @@ static void nh_res_group_rebalance(struct nh_group *nhg, for (i = 0; i < nhg->num_nh; ++i) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; - int upper_bound; + u16 upper_bound; + u64 btw; w += nhge->weight; - upper_bound = DIV_ROUND_CLOSEST(res_table->num_nh_buckets * w, - total); + btw = ((u64)res_table->num_nh_buckets) * w; + upper_bound = DIV_ROUND_CLOSEST_ULL(btw, total); nhge->res.wants_buckets = upper_bound - prev_upper_bound; prev_upper_bound = upper_bound; @@ -1962,8 +1974,8 @@ static void replace_nexthop_grp_res(struct nh_group *oldg, static void nh_hthr_group_rebalance(struct nh_group *nhg) { - int total = 0; - int w = 0; + u32 total = 0; + u32 w = 0; int i; for (i = 0; i < nhg->num_nh; ++i) @@ -1971,7 +1983,7 @@ static void nh_hthr_group_rebalance(struct nh_group *nhg) for (i = 0; i < nhg->num_nh; ++i) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; - int upper_bound; + u32 upper_bound; w += nhge->weight; upper_bound = DIV_ROUND_CLOSEST_ULL((u64)w << 31, total) - 1; @@ -2713,7 +2725,8 @@ static struct nexthop *nexthop_create_group(struct net *net, goto out_no_nh; } nhg->nh_entries[i].nh = nhe; - nhg->nh_entries[i].weight = entry[i].weight + 1; + nhg->nh_entries[i].weight = nexthop_grp_weight(&entry[i]); + list_add(&nhg->nh_entries[i].nh_list, &nhe->grp_list); nhg->nh_entries[i].nh_parent = nh; } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 13c0f1d455f3..f6972b24664a 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1263,7 +1263,7 @@ void ip_rt_get_source(u8 *addr, struct sk_buff *skb, struct rtable *rt) struct flowi4 fl4 = { .daddr = iph->daddr, .saddr = iph->saddr, - .flowi4_tos = iph->tos & IPTOS_RT_MASK, + .flowi4_tos = iph->tos & INET_DSCP_MASK, .flowi4_oif = rt->dst.dev->ifindex, .flowi4_iif = skb->dev->ifindex, .flowi4_mark = skb->mark, @@ -2160,7 +2160,7 @@ int ip_route_use_hint(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (rt->rt_type != RTN_LOCAL) goto skip_validate_source; - tos &= IPTOS_RT_MASK; + tos &= INET_DSCP_MASK; err = fib_validate_source(skb, saddr, daddr, tos, 0, dev, in_dev, &tag); if (err < 0) goto martian_source; @@ -2470,7 +2470,7 @@ int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr, struct fib_result res; int err; - tos &= IPTOS_RT_MASK; + tos &= INET_DSCP_MASK; rcu_read_lock(); err = ip_route_input_rcu(skb, daddr, saddr, tos, dev, &res); rcu_read_unlock(); @@ -3286,7 +3286,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, skb->dev = dev; skb->mark = mark; err = ip_route_input_rcu(skb, dst, src, - rtm->rtm_tos & IPTOS_RT_MASK, dev, + rtm->rtm_tos & INET_DSCP_MASK, dev, &res); rt = skb_rtable(skb); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 831a18dc7aa6..8a5680b4e786 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2833,7 +2833,7 @@ void __tcp_close(struct sock *sk, long timeout) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONCLOSE); tcp_set_state(sk, TCP_CLOSE); tcp_send_active_reset(sk, sk->sk_allocation, - SK_RST_REASON_NOT_SPECIFIED); + SK_RST_REASON_TCP_ABORT_ON_CLOSE); } else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) { /* Check zero linger _after_ checking for unread data. */ sk->sk_prot->disconnect(sk, 0); @@ -2908,7 +2908,7 @@ adjudge_to_death: if (READ_ONCE(tp->linger2) < 0) { tcp_set_state(sk, TCP_CLOSE); tcp_send_active_reset(sk, GFP_ATOMIC, - SK_RST_REASON_NOT_SPECIFIED); + SK_RST_REASON_TCP_ABORT_ON_LINGER); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONLINGER); } else { @@ -2927,7 +2927,7 @@ adjudge_to_death: if (tcp_check_oom(sk, 0)) { tcp_set_state(sk, TCP_CLOSE); tcp_send_active_reset(sk, GFP_ATOMIC, - SK_RST_REASON_NOT_SPECIFIED); + SK_RST_REASON_TCP_ABORT_ON_MEMORY); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY); } else if (!check_net(sock_net(sk))) { @@ -3025,13 +3025,16 @@ int tcp_disconnect(struct sock *sk, int flags) inet_csk_listen_stop(sk); } else if (unlikely(tp->repair)) { WRITE_ONCE(sk->sk_err, ECONNABORTED); - } else if (tcp_need_reset(old_state) || - (tp->snd_nxt != tp->write_seq && - (1 << old_state) & (TCPF_CLOSING | TCPF_LAST_ACK))) { + } else if (tcp_need_reset(old_state)) { + tcp_send_active_reset(sk, gfp_any(), SK_RST_REASON_TCP_STATE); + WRITE_ONCE(sk->sk_err, ECONNRESET); + } else if (tp->snd_nxt != tp->write_seq && + (1 << old_state) & (TCPF_CLOSING | TCPF_LAST_ACK)) { /* The last check adjusts for discrepancy of Linux wrt. RFC * states */ - tcp_send_active_reset(sk, gfp_any(), SK_RST_REASON_NOT_SPECIFIED); + tcp_send_active_reset(sk, gfp_any(), + SK_RST_REASON_TCP_DISCONNECT_WITH_DATA); WRITE_ONCE(sk->sk_err, ECONNRESET); } else if (old_state == TCP_SYN_SENT) WRITE_ONCE(sk->sk_err, ECONNRESET); @@ -4655,7 +4658,7 @@ int tcp_abort(struct sock *sk, int err) if (tcp_need_reset(sk->sk_state)) tcp_send_active_reset(sk, GFP_ATOMIC, - SK_RST_REASON_NOT_SPECIFIED); + SK_RST_REASON_TCP_STATE); tcp_done_with_error(sk, err); bh_unlock_sock(sk); diff --git a/net/ipv4/tcp_htcp.c b/net/ipv4/tcp_htcp.c index 52b1f2665dfa..81b96331b2bb 100644 --- a/net/ipv4/tcp_htcp.c +++ b/net/ipv4/tcp_htcp.c @@ -185,7 +185,7 @@ static inline void htcp_alpha_update(struct htcp *ca) u32 scale = (HZ << 3) / (10 * minRTT); /* clamping ratio to interval [0.5,10]<<3 */ - scale = min(max(scale, 1U << 2), 10U << 3); + scale = clamp(scale, 1U << 2, 10U << 3); factor = (factor << 3) / scale; if (!factor) factor = 1; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a4e510846905..eb631e66ee03 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -120,6 +120,9 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) struct tcp_sock *tp = tcp_sk(sk); int ts_recent_stamp; + if (READ_ONCE(tw->tw_substate) == TCP_FIN_WAIT2) + reuse = 0; + if (reuse == 2) { /* Still does not detect *everything* that goes through * lo, since we require a loopback src or dst address @@ -1070,7 +1073,7 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb) } tcp_v4_send_ack(sk, skb, - tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, + tcptw->tw_snd_nxt, READ_ONCE(tcptw->tw_rcv_nxt), tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, tcp_tw_tsval(tcptw), READ_ONCE(tcptw->tw_ts_recent), @@ -2945,7 +2948,7 @@ static void get_timewait4_sock(const struct inet_timewait_sock *tw, seq_printf(f, "%4d: %08X:%04X %08X:%04X" " %02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK", - i, src, srcp, dest, destp, tw->tw_substate, 0, 0, + i, src, srcp, dest, destp, READ_ONCE(tw->tw_substate), 0, 0, 3, jiffies_delta_to_clock_t(delta), 0, 0, 0, 0, refcount_read(&tw->tw_refcnt), tw); } diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index b01eb6d94413..95669935494e 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -617,9 +617,13 @@ static struct genl_family tcp_metrics_nl_family; static const struct nla_policy tcp_metrics_nl_policy[TCP_METRICS_ATTR_MAX + 1] = { [TCP_METRICS_ATTR_ADDR_IPV4] = { .type = NLA_U32, }, - [TCP_METRICS_ATTR_ADDR_IPV6] = { .type = NLA_BINARY, - .len = sizeof(struct in6_addr), }, + [TCP_METRICS_ATTR_ADDR_IPV6] = + NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), + [TCP_METRICS_ATTR_SADDR_IPV4] = { .type = NLA_U32, }, + [TCP_METRICS_ATTR_SADDR_IPV6] = + NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), + /* Following attributes are not received for GET/DEL, * we keep them for reference */ @@ -811,8 +815,6 @@ static int __parse_nl_addr(struct genl_info *info, struct inetpeer_addr *addr, if (a) { struct in6_addr in6; - if (nla_len(a) != sizeof(struct in6_addr)) - return -EINVAL; in6 = nla_get_in6_addr(a); inetpeer_set_addr_v6(addr, &in6); if (hash) diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index a19a9dbd3409..ad562272db2e 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -52,16 +52,17 @@ tcp_timewait_check_oow_rate_limit(struct inet_timewait_sock *tw, return TCP_TW_SUCCESS; } -static void twsk_rcv_nxt_update(struct tcp_timewait_sock *tcptw, u32 seq) +static void twsk_rcv_nxt_update(struct tcp_timewait_sock *tcptw, u32 seq, + u32 rcv_nxt) { #ifdef CONFIG_TCP_AO struct tcp_ao_info *ao; ao = rcu_dereference(tcptw->ao_info); - if (unlikely(ao && seq < tcptw->tw_rcv_nxt)) + if (unlikely(ao && seq < rcv_nxt)) WRITE_ONCE(ao->rcv_sne, ao->rcv_sne + 1); #endif - tcptw->tw_rcv_nxt = seq; + WRITE_ONCE(tcptw->tw_rcv_nxt, seq); } /* @@ -98,8 +99,9 @@ enum tcp_tw_status tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, const struct tcphdr *th, u32 *tw_isn) { - struct tcp_options_received tmp_opt; struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw); + u32 rcv_nxt = READ_ONCE(tcptw->tw_rcv_nxt); + struct tcp_options_received tmp_opt; bool paws_reject = false; int ts_recent_stamp; @@ -117,26 +119,26 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, } } - if (tw->tw_substate == TCP_FIN_WAIT2) { + if (READ_ONCE(tw->tw_substate) == TCP_FIN_WAIT2) { /* Just repeat all the checks of tcp_rcv_state_process() */ /* Out of window, send ACK */ if (paws_reject || !tcp_in_window(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq, - tcptw->tw_rcv_nxt, - tcptw->tw_rcv_nxt + tcptw->tw_rcv_wnd)) + rcv_nxt, + rcv_nxt + tcptw->tw_rcv_wnd)) return tcp_timewait_check_oow_rate_limit( tw, skb, LINUX_MIB_TCPACKSKIPPEDFINWAIT2); if (th->rst) goto kill; - if (th->syn && !before(TCP_SKB_CB(skb)->seq, tcptw->tw_rcv_nxt)) + if (th->syn && !before(TCP_SKB_CB(skb)->seq, rcv_nxt)) return TCP_TW_RST; /* Dup ACK? */ if (!th->ack || - !after(TCP_SKB_CB(skb)->end_seq, tcptw->tw_rcv_nxt) || + !after(TCP_SKB_CB(skb)->end_seq, rcv_nxt) || TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq) { inet_twsk_put(tw); return TCP_TW_SUCCESS; @@ -146,12 +148,13 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, * reset. */ if (!th->fin || - TCP_SKB_CB(skb)->end_seq != tcptw->tw_rcv_nxt + 1) + TCP_SKB_CB(skb)->end_seq != rcv_nxt + 1) return TCP_TW_RST; /* FIN arrived, enter true time-wait state. */ - tw->tw_substate = TCP_TIME_WAIT; - twsk_rcv_nxt_update(tcptw, TCP_SKB_CB(skb)->end_seq); + WRITE_ONCE(tw->tw_substate, TCP_TIME_WAIT); + twsk_rcv_nxt_update(tcptw, TCP_SKB_CB(skb)->end_seq, + rcv_nxt); if (tmp_opt.saw_tstamp) { WRITE_ONCE(tcptw->tw_ts_recent_stamp, @@ -182,7 +185,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, */ if (!paws_reject && - (TCP_SKB_CB(skb)->seq == tcptw->tw_rcv_nxt && + (TCP_SKB_CB(skb)->seq == rcv_nxt && (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq || th->rst))) { /* In window segment, it may be only reset or bare ack. */ @@ -229,7 +232,7 @@ kill: */ if (th->syn && !th->rst && !th->ack && !paws_reject && - (after(TCP_SKB_CB(skb)->seq, tcptw->tw_rcv_nxt) || + (after(TCP_SKB_CB(skb)->seq, rcv_nxt) || (tmp_opt.saw_tstamp && (s32)(READ_ONCE(tcptw->tw_ts_recent) - tmp_opt.rcv_tsval) < 0))) { u32 isn = tcptw->tw_snd_nxt + 65535 + 2; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 16c48df8df4c..cdd0def14427 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3649,7 +3649,7 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority, /* skb of trace_tcp_send_reset() keeps the skb that caused RST, * skb here is different to the troublesome skb, so use NULL */ - trace_tcp_send_reset(sk, NULL, SK_RST_REASON_NOT_SPECIFIED); + trace_tcp_send_reset(sk, NULL, reason); } /* Send a crossed SYN-ACK during socket establishment. diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 4d40615dc8fc..86169127e4d1 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -125,7 +125,7 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset) do_reset = true; if (do_reset) tcp_send_active_reset(sk, GFP_ATOMIC, - SK_RST_REASON_NOT_SPECIFIED); + SK_RST_REASON_TCP_ABORT_ON_MEMORY); tcp_done(sk); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY); return 1; @@ -779,7 +779,7 @@ static void tcp_keepalive_timer (struct timer_list *t) goto out; } } - tcp_send_active_reset(sk, GFP_ATOMIC, SK_RST_REASON_NOT_SPECIFIED); + tcp_send_active_reset(sk, GFP_ATOMIC, SK_RST_REASON_TCP_STATE); goto death; } @@ -807,7 +807,7 @@ static void tcp_keepalive_timer (struct timer_list *t) (user_timeout == 0 && icsk->icsk_probes_out >= keepalive_probes(tp))) { tcp_send_active_reset(sk, GFP_ATOMIC, - SK_RST_REASON_NOT_SPECIFIED); + SK_RST_REASON_TCP_KEEPALIVE_TIMEOUT); tcp_write_err(sk); goto out; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 49c622e743e8..8accbf4cb295 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -115,6 +115,7 @@ #include <net/addrconf.h> #include <net/udp_tunnel.h> #include <net/gro.h> +#include <net/inet_dscp.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6_stubs.h> #endif @@ -365,7 +366,7 @@ int udp_v4_get_port(struct sock *sk, unsigned short snum) return udp_lib_get_port(sk, snum, hash2_nulladdr); } -static int compute_score(struct sock *sk, struct net *net, +static int compute_score(struct sock *sk, const struct net *net, __be32 saddr, __be16 sport, __be32 daddr, unsigned short hnum, int dif, int sdif) @@ -420,7 +421,7 @@ u32 udp_ehashfn(const struct net *net, const __be32 laddr, const __u16 lport, } /* called with rcu_read_lock() */ -static struct sock *udp4_lib_lookup2(struct net *net, +static struct sock *udp4_lib_lookup2(const struct net *net, __be32 saddr, __be16 sport, __be32 daddr, unsigned int hnum, int dif, int sdif, @@ -480,7 +481,7 @@ rescore: /* UDP is nearly always wildcards out the wazoo, it makes no sense to try * harder than this. -DaveM */ -struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, +struct sock *__udp4_lib_lookup(const struct net *net, __be32 saddr, __be16 sport, __be32 daddr, __be16 dport, int dif, int sdif, struct udp_table *udptable, struct sk_buff *skb) { @@ -561,7 +562,7 @@ struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb, * Does increment socket refcount. */ #if IS_ENABLED(CONFIG_NF_TPROXY_IPV4) || IS_ENABLED(CONFIG_NF_SOCKET_IPV4) -struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, +struct sock *udp4_lib_lookup(const struct net *net, __be32 saddr, __be16 sport, __be32 daddr, __be16 dport, int dif) { struct sock *sk; @@ -2618,7 +2619,7 @@ int udp_v4_early_demux(struct sk_buff *skb) if (!inet_sk(sk)->inet_daddr && in_dev) return ip_mc_validate_source(skb, iph->daddr, iph->saddr, - iph->tos & IPTOS_RT_MASK, + iph->tos & INET_DSCP_MASK, skb->dev, in_dev, &itag); } return 0; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index f70d8757af1a..d680beb91b0a 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -92,8 +92,6 @@ #include <linux/export.h> #include <linux/ioam6.h> -#define INFINITY_LIFE_TIME 0xFFFFFFFF - #define IPV6_MAX_STRLEN \ sizeof("ffff:ffff:ffff:ffff:ffff:ffff:255.255.255.255") @@ -239,6 +237,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .ioam6_id_wide = IOAM6_DEFAULT_IF_ID_WIDE, .ndisc_evict_nocarrier = 1, .ra_honor_pio_life = 0, + .ra_honor_pio_pflag = 0, }; static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { @@ -302,6 +301,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .ioam6_id_wide = IOAM6_DEFAULT_IF_ID_WIDE, .ndisc_evict_nocarrier = 1, .ra_honor_pio_life = 0, + .ra_honor_pio_pflag = 0, }; /* Check if link is ready: is it up and is a valid qdisc available */ @@ -2762,6 +2762,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) u32 addr_flags = 0; struct inet6_dev *in6_dev; struct net *net = dev_net(dev); + bool ignore_autoconf = false; pinfo = (struct prefix_info *) opt; @@ -2864,7 +2865,8 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) /* Try to figure out our local address for this prefix */ - if (pinfo->autoconf && in6_dev->cnf.autoconf) { + ignore_autoconf = READ_ONCE(in6_dev->cnf.ra_honor_pio_pflag) && pinfo->preferpd; + if (pinfo->autoconf && in6_dev->cnf.autoconf && !ignore_autoconf) { struct in6_addr addr; bool tokenized = false, dev_addr_generated = false; @@ -5617,8 +5619,7 @@ static void inet6_ifa_notify(int event, struct inet6_ifaddr *ifa) rtnl_notify(skb, net, 0, RTNLGRP_IPV6_IFADDR, NULL, GFP_ATOMIC); return; errout: - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_IPV6_IFADDR, err); + rtnl_set_sk_err(net, RTNLGRP_IPV6_IFADDR, err); } static void ipv6_store_devconf(const struct ipv6_devconf *cnf, @@ -6173,8 +6174,7 @@ void inet6_ifinfo_notify(int event, struct inet6_dev *idev) rtnl_notify(skb, net, 0, RTNLGRP_IPV6_IFINFO, NULL, GFP_ATOMIC); return; errout: - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_IPV6_IFINFO, err); + rtnl_set_sk_err(net, RTNLGRP_IPV6_IFINFO, err); } static inline size_t inet6_prefix_nlmsg_size(void) @@ -6241,8 +6241,7 @@ static void inet6_prefix_notify(int event, struct inet6_dev *idev, rtnl_notify(skb, net, 0, RTNLGRP_IPV6_PREFIX, NULL, GFP_ATOMIC); return; errout: - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_IPV6_PREFIX, err); + rtnl_set_sk_err(net, RTNLGRP_IPV6_PREFIX, err); } static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) @@ -6926,6 +6925,15 @@ static const struct ctl_table addrconf_sysctl[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, + { + .procname = "ra_honor_pio_pflag", + .data = &ipv6_devconf.ra_honor_pio_pflag, + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, #ifdef CONFIG_IPV6_ROUTER_PREF { .procname = "accept_ra_rtr_pref", diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 6db71bb1cd30..9ec05e354baa 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -46,7 +46,7 @@ EXPORT_SYMBOL_GPL(inet6_ehashfn); * * The sockhash lock must be held as a reader here. */ -struct sock *__inet6_lookup_established(struct net *net, +struct sock *__inet6_lookup_established(const struct net *net, struct inet_hashinfo *hashinfo, const struct in6_addr *saddr, const __be16 sport, @@ -89,7 +89,7 @@ found: } EXPORT_SYMBOL(__inet6_lookup_established); -static inline int compute_score(struct sock *sk, struct net *net, +static inline int compute_score(struct sock *sk, const struct net *net, const unsigned short hnum, const struct in6_addr *daddr, const int dif, const int sdif) @@ -126,7 +126,7 @@ static inline int compute_score(struct sock *sk, struct net *net, * Return: NULL if sk doesn't have SO_REUSEPORT set, otherwise a pointer to * the selected sock or an error. */ -struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk, +struct sock *inet6_lookup_reuseport(const struct net *net, struct sock *sk, struct sk_buff *skb, int doff, const struct in6_addr *saddr, __be16 sport, @@ -147,7 +147,7 @@ struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk, EXPORT_SYMBOL_GPL(inet6_lookup_reuseport); /* called with rcu_read_lock() */ -static struct sock *inet6_lhash2_lookup(struct net *net, +static struct sock *inet6_lhash2_lookup(const struct net *net, struct inet_listen_hashbucket *ilb2, struct sk_buff *skb, int doff, const struct in6_addr *saddr, @@ -174,7 +174,7 @@ static struct sock *inet6_lhash2_lookup(struct net *net, return result; } -struct sock *inet6_lookup_run_sk_lookup(struct net *net, +struct sock *inet6_lookup_run_sk_lookup(const struct net *net, int protocol, struct sk_buff *skb, int doff, const struct in6_addr *saddr, @@ -199,7 +199,7 @@ struct sock *inet6_lookup_run_sk_lookup(struct net *net, } EXPORT_SYMBOL_GPL(inet6_lookup_run_sk_lookup); -struct sock *inet6_lookup_listener(struct net *net, +struct sock *inet6_lookup_listener(const struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const struct in6_addr *saddr, @@ -243,7 +243,8 @@ done: } EXPORT_SYMBOL_GPL(inet6_lookup_listener); -struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo, +struct sock *inet6_lookup(const struct net *net, + struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const __be16 dport, diff --git a/net/ipv6/ioam6_iptunnel.c b/net/ipv6/ioam6_iptunnel.c index bf7120ecea1e..e34e1ff24546 100644 --- a/net/ipv6/ioam6_iptunnel.c +++ b/net/ipv6/ioam6_iptunnel.c @@ -42,8 +42,10 @@ struct ioam6_lwt { struct ioam6_lwt_freq freq; atomic_t pkt_cnt; u8 mode; + bool has_tunsrc; + struct in6_addr tunsrc; struct in6_addr tundst; - struct ioam6_lwt_encap tuninfo; + struct ioam6_lwt_encap tuninfo; }; static const struct netlink_range_validation freq_range = { @@ -72,8 +74,10 @@ static const struct nla_policy ioam6_iptunnel_policy[IOAM6_IPTUNNEL_MAX + 1] = { [IOAM6_IPTUNNEL_MODE] = NLA_POLICY_RANGE(NLA_U8, IOAM6_IPTUNNEL_MODE_MIN, IOAM6_IPTUNNEL_MODE_MAX), + [IOAM6_IPTUNNEL_SRC] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), [IOAM6_IPTUNNEL_DST] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), - [IOAM6_IPTUNNEL_TRACE] = NLA_POLICY_EXACT_LEN(sizeof(struct ioam6_trace_hdr)), + [IOAM6_IPTUNNEL_TRACE] = NLA_POLICY_EXACT_LEN( + sizeof(struct ioam6_trace_hdr)), }; static bool ioam6_validate_trace_hdr(struct ioam6_trace_hdr *trace) @@ -143,6 +147,11 @@ static int ioam6_build_state(struct net *net, struct nlattr *nla, else mode = nla_get_u8(tb[IOAM6_IPTUNNEL_MODE]); + if (tb[IOAM6_IPTUNNEL_SRC] && mode == IOAM6_IPTUNNEL_MODE_INLINE) { + NL_SET_ERR_MSG(extack, "no tunnel src expected with this mode"); + return -EINVAL; + } + if (!tb[IOAM6_IPTUNNEL_DST] && mode != IOAM6_IPTUNNEL_MODE_INLINE) { NL_SET_ERR_MSG(extack, "this mode needs a tunnel destination"); return -EINVAL; @@ -167,16 +176,29 @@ static int ioam6_build_state(struct net *net, struct nlattr *nla, ilwt = ioam6_lwt_state(lwt); err = dst_cache_init(&ilwt->cache, GFP_ATOMIC); - if (err) { - kfree(lwt); - return err; - } + if (err) + goto free_lwt; atomic_set(&ilwt->pkt_cnt, 0); ilwt->freq.k = freq_k; ilwt->freq.n = freq_n; ilwt->mode = mode; + + if (!tb[IOAM6_IPTUNNEL_SRC]) { + ilwt->has_tunsrc = false; + } else { + ilwt->has_tunsrc = true; + ilwt->tunsrc = nla_get_in6_addr(tb[IOAM6_IPTUNNEL_SRC]); + + if (ipv6_addr_any(&ilwt->tunsrc)) { + NL_SET_ERR_MSG_ATTR(extack, tb[IOAM6_IPTUNNEL_SRC], + "invalid tunnel source address"); + err = -EINVAL; + goto free_cache; + } + } + if (tb[IOAM6_IPTUNNEL_DST]) ilwt->tundst = nla_get_in6_addr(tb[IOAM6_IPTUNNEL_DST]); @@ -201,6 +223,11 @@ static int ioam6_build_state(struct net *net, struct nlattr *nla, *ts = lwt; return 0; +free_cache: + dst_cache_destroy(&ilwt->cache); +free_lwt: + kfree(lwt); + return err; } static int ioam6_do_fill(struct net *net, struct sk_buff *skb) @@ -256,6 +283,8 @@ static int ioam6_do_inline(struct net *net, struct sk_buff *skb, static int ioam6_do_encap(struct net *net, struct sk_buff *skb, struct ioam6_lwt_encap *tuninfo, + bool has_tunsrc, + struct in6_addr *tunsrc, struct in6_addr *tundst) { struct dst_entry *dst = skb_dst(skb); @@ -285,8 +314,12 @@ static int ioam6_do_encap(struct net *net, struct sk_buff *skb, hdr->nexthdr = NEXTHDR_HOP; hdr->payload_len = cpu_to_be16(skb->len - sizeof(*hdr)); hdr->daddr = *tundst; - ipv6_dev_get_saddr(net, dst->dev, &hdr->daddr, - IPV6_PREFER_SRC_PUBLIC, &hdr->saddr); + + if (has_tunsrc) + memcpy(&hdr->saddr, tunsrc, sizeof(*tunsrc)); + else + ipv6_dev_get_saddr(net, dst->dev, &hdr->daddr, + IPV6_PREFER_SRC_PUBLIC, &hdr->saddr); skb_postpush_rcsum(skb, hdr, len); @@ -328,7 +361,9 @@ do_inline: case IOAM6_IPTUNNEL_MODE_ENCAP: do_encap: /* Encapsulation (ip6ip6) */ - err = ioam6_do_encap(net, skb, &ilwt->tuninfo, &ilwt->tundst); + err = ioam6_do_encap(net, skb, &ilwt->tuninfo, + ilwt->has_tunsrc, &ilwt->tunsrc, + &ilwt->tundst); if (unlikely(err)) goto drop; @@ -414,6 +449,13 @@ static int ioam6_fill_encap_info(struct sk_buff *skb, goto ret; if (ilwt->mode != IOAM6_IPTUNNEL_MODE_INLINE) { + if (ilwt->has_tunsrc) { + err = nla_put_in6_addr(skb, IOAM6_IPTUNNEL_SRC, + &ilwt->tunsrc); + if (err) + goto ret; + } + err = nla_put_in6_addr(skb, IOAM6_IPTUNNEL_DST, &ilwt->tundst); if (err) goto ret; @@ -435,8 +477,12 @@ static int ioam6_encap_nlsize(struct lwtunnel_state *lwtstate) nla_total_size(sizeof(ilwt->mode)) + nla_total_size(sizeof(ilwt->tuninfo.traceh)); - if (ilwt->mode != IOAM6_IPTUNNEL_MODE_INLINE) + if (ilwt->mode != IOAM6_IPTUNNEL_MODE_INLINE) { + if (ilwt->has_tunsrc) + nlsize += nla_total_size(sizeof(ilwt->tunsrc)); + nlsize += nla_total_size(sizeof(ilwt->tundst)); + } return nlsize; } @@ -451,17 +497,21 @@ static int ioam6_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b) return (ilwt_a->freq.k != ilwt_b->freq.k || ilwt_a->freq.n != ilwt_b->freq.n || ilwt_a->mode != ilwt_b->mode || + ilwt_a->has_tunsrc != ilwt_b->has_tunsrc || (ilwt_a->mode != IOAM6_IPTUNNEL_MODE_INLINE && !ipv6_addr_equal(&ilwt_a->tundst, &ilwt_b->tundst)) || + (ilwt_a->mode != IOAM6_IPTUNNEL_MODE_INLINE && + ilwt_a->has_tunsrc && + !ipv6_addr_equal(&ilwt_a->tunsrc, &ilwt_b->tunsrc)) || trace_a->namespace_id != trace_b->namespace_id); } static const struct lwtunnel_encap_ops ioam6_iptun_ops = { .build_state = ioam6_build_state, .destroy_state = ioam6_destroy_state, - .output = ioam6_output, + .output = ioam6_output, .fill_encap = ioam6_fill_encap_info, - .get_encap_size = ioam6_encap_nlsize, + .get_encap_size = ioam6_encap_nlsize, .cmp_encap = ioam6_encap_cmp, .owner = THIS_MODULE, }; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index dd342e6ecf3f..e3ee93c562c3 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -2431,8 +2431,7 @@ static void mr6_netlink_event(struct mr_table *mrt, struct mfc6_cache *mfc, errout: kfree_skb(skb); - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_IPV6_MROUTE, err); + rtnl_set_sk_err(net, RTNLGRP_IPV6_MROUTE, err); } static size_t mrt6msg_netlink_msgsize(size_t payloadlen) diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index cd342d5015c6..1e225e6489ea 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -985,7 +985,7 @@ int ipv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, int err; if (level == SOL_IP && sk->sk_type != SOCK_RAW) - return udp_prot.setsockopt(sk, level, optname, optval, optlen); + return ip_setsockopt(sk, level, optname, optval, optlen); if (level != SOL_IPV6) return -ENOPROTOOPT; @@ -1475,7 +1475,7 @@ int ipv6_getsockopt(struct sock *sk, int level, int optname, int err; if (level == SOL_IP && sk->sk_type != SOCK_RAW) - return udp_prot.getsockopt(sk, level, optname, optval, optlen); + return ip_getsockopt(sk, level, optname, optval, optlen); if (level != SOL_IPV6) return -ENOPROTOOPT; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 7ba01d8cfbae..b244dbf61d5f 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -586,7 +586,8 @@ int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf, const struct in6_addr *group; struct ipv6_mc_socklist *pmc; struct ip6_sf_socklist *psl; - int i, count, copycount; + unsigned int count; + int i, copycount; group = &((struct sockaddr_in6 *)&gsf->gf_group)->sin6_addr; @@ -610,7 +611,7 @@ int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf, psl = sock_dereference(pmc->sflist, sk); count = psl ? psl->sl_count : 0; - copycount = count < gsf->gf_numsrc ? count : gsf->gf_numsrc; + copycount = min(count, gsf->gf_numsrc); gsf->gf_numsrc = count; for (i = 0; i < copycount; i++) { struct sockaddr_in6 *psin6; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index b8eec1b6cc2c..1e42e40fb379 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -200,9 +200,9 @@ static inline int ndisc_is_useropt(const struct net_device *dev, return opt->nd_opt_type == ND_OPT_PREFIX_INFO || opt->nd_opt_type == ND_OPT_RDNSS || opt->nd_opt_type == ND_OPT_DNSSL || + opt->nd_opt_type == ND_OPT_6CO || opt->nd_opt_type == ND_OPT_CAPTIVE_PORTAL || - opt->nd_opt_type == ND_OPT_PREF64 || - ndisc_ops_is_useropt(dev, opt->nd_opt_type); + opt->nd_opt_type == ND_OPT_PREF64; } static struct nd_opt_hdr *ndisc_next_useropt(const struct net_device *dev, diff --git a/net/ipv6/netfilter/nft_dup_ipv6.c b/net/ipv6/netfilter/nft_dup_ipv6.c index c82f3fdd4a65..492a811828a7 100644 --- a/net/ipv6/netfilter/nft_dup_ipv6.c +++ b/net/ipv6/netfilter/nft_dup_ipv6.c @@ -38,13 +38,13 @@ static int nft_dup_ipv6_init(const struct nft_ctx *ctx, if (tb[NFTA_DUP_SREG_ADDR] == NULL) return -EINVAL; - err = nft_parse_register_load(tb[NFTA_DUP_SREG_ADDR], &priv->sreg_addr, + err = nft_parse_register_load(ctx, tb[NFTA_DUP_SREG_ADDR], &priv->sreg_addr, sizeof(struct in6_addr)); if (err < 0) return err; if (tb[NFTA_DUP_SREG_DEV]) - err = nft_parse_register_load(tb[NFTA_DUP_SREG_DEV], + err = nft_parse_register_load(ctx, tb[NFTA_DUP_SREG_DEV], &priv->sreg_dev, sizeof(int)); return err; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 219701caba1e..7e7de29ad05f 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -6193,8 +6193,7 @@ void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info, info->nlh, gfp_any()); return; errout: - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err); + rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err); } void fib6_rt_update(struct net *net, struct fib6_info *rt, @@ -6220,8 +6219,7 @@ void fib6_rt_update(struct net *net, struct fib6_info *rt, info->nlh, gfp_any()); return; errout: - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err); + rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err); } void fib6_info_hw_flags_set(struct net *net, struct fib6_info *f6i, diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 200fea92f12f..d71ab4e1efe1 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1193,7 +1193,8 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) #endif } - tcp_v6_send_ack(sk, skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, + tcp_v6_send_ack(sk, skb, tcptw->tw_snd_nxt, + READ_ONCE(tcptw->tw_rcv_nxt), tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, tcp_tw_tsval(tcptw), READ_ONCE(tcptw->tw_ts_recent), tw->tw_bound_dev_if, @@ -2258,7 +2259,7 @@ static void get_timewait6_sock(struct seq_file *seq, src->s6_addr32[2], src->s6_addr32[3], srcp, dest->s6_addr32[0], dest->s6_addr32[1], dest->s6_addr32[2], dest->s6_addr32[3], destp, - tw->tw_substate, 0, 0, + READ_ONCE(tw->tw_substate), 0, 0, 3, jiffies_delta_to_clock_t(delta), 0, 0, 0, 0, refcount_read(&tw->tw_refcnt), tw); } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 6602a2e9cdb5..52dfbb2ff1a8 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -114,7 +114,7 @@ void udp_v6_rehash(struct sock *sk) udp_lib_rehash(sk, new_hash); } -static int compute_score(struct sock *sk, struct net *net, +static int compute_score(struct sock *sk, const struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, unsigned short hnum, int dif, int sdif) @@ -160,7 +160,7 @@ static int compute_score(struct sock *sk, struct net *net, } /* called with rcu_read_lock() */ -static struct sock *udp6_lib_lookup2(struct net *net, +static struct sock *udp6_lib_lookup2(const struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, unsigned int hnum, int dif, int sdif, struct udp_hslot *hslot2, @@ -217,7 +217,7 @@ rescore: } /* rcu_read_lock() must be held */ -struct sock *__udp6_lib_lookup(struct net *net, +struct sock *__udp6_lib_lookup(const struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, int dif, int sdif, struct udp_table *udptable, @@ -300,7 +300,7 @@ struct sock *udp6_lib_lookup_skb(const struct sk_buff *skb, * Does increment socket refcount. */ #if IS_ENABLED(CONFIG_NF_TPROXY_IPV6) || IS_ENABLED(CONFIG_NF_SOCKET_IPV6) -struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport, +struct sock *udp6_lib_lookup(const struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, int dif) { struct sock *sk; diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 2e86f520f799..32102d1ed4cd 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -117,12 +117,12 @@ struct l2tp_net { struct hlist_head l2tp_v3_session_htable[16]; }; -static inline u32 l2tp_v2_session_key(u16 tunnel_id, u16 session_id) +static u32 l2tp_v2_session_key(u16 tunnel_id, u16 session_id) { return ((u32)tunnel_id) << 16 | session_id; } -static inline unsigned long l2tp_v3_session_hashkey(struct sock *sk, u32 session_id) +static unsigned long l2tp_v3_session_hashkey(struct sock *sk, u32 session_id) { return ((unsigned long)sk) + session_id; } @@ -135,63 +135,81 @@ static bool l2tp_sk_is_v6(struct sock *sk) } #endif -static inline struct l2tp_net *l2tp_pernet(const struct net *net) +static struct l2tp_net *l2tp_pernet(const struct net *net) { return net_generic(net, l2tp_net_id); } static void l2tp_tunnel_free(struct l2tp_tunnel *tunnel) { + struct sock *sk = tunnel->sock; + trace_free_tunnel(tunnel); - sock_put(tunnel->sock); - /* the tunnel is freed in the socket destructor */ + + if (sk) { + /* Disable udp encapsulation */ + switch (tunnel->encap) { + case L2TP_ENCAPTYPE_UDP: + /* No longer an encapsulation socket. See net/ipv4/udp.c */ + WRITE_ONCE(udp_sk(sk)->encap_type, 0); + udp_sk(sk)->encap_rcv = NULL; + udp_sk(sk)->encap_destroy = NULL; + break; + case L2TP_ENCAPTYPE_IP: + break; + } + + tunnel->sock = NULL; + sock_put(sk); + } + + kfree_rcu(tunnel, rcu); } static void l2tp_session_free(struct l2tp_session *session) { trace_free_session(session); if (session->tunnel) - l2tp_tunnel_dec_refcount(session->tunnel); - kfree(session); + l2tp_tunnel_put(session->tunnel); + kfree_rcu(session, rcu); } -struct l2tp_tunnel *l2tp_sk_to_tunnel(struct sock *sk) +struct l2tp_tunnel *l2tp_sk_to_tunnel(const struct sock *sk) { - struct l2tp_tunnel *tunnel = sk->sk_user_data; + const struct net *net = sock_net(sk); + unsigned long tunnel_id, tmp; + struct l2tp_tunnel *tunnel; + struct l2tp_net *pn; - if (tunnel) - if (WARN_ON(tunnel->magic != L2TP_TUNNEL_MAGIC)) - return NULL; + rcu_read_lock_bh(); + pn = l2tp_pernet(net); + idr_for_each_entry_ul(&pn->l2tp_tunnel_idr, tunnel, tmp, tunnel_id) { + if (tunnel && + tunnel->sock == sk && + refcount_inc_not_zero(&tunnel->ref_count)) { + rcu_read_unlock_bh(); + return tunnel; + } + } + rcu_read_unlock_bh(); - return tunnel; + return NULL; } EXPORT_SYMBOL_GPL(l2tp_sk_to_tunnel); -void l2tp_tunnel_inc_refcount(struct l2tp_tunnel *tunnel) -{ - refcount_inc(&tunnel->ref_count); -} -EXPORT_SYMBOL_GPL(l2tp_tunnel_inc_refcount); - -void l2tp_tunnel_dec_refcount(struct l2tp_tunnel *tunnel) +void l2tp_tunnel_put(struct l2tp_tunnel *tunnel) { if (refcount_dec_and_test(&tunnel->ref_count)) l2tp_tunnel_free(tunnel); } -EXPORT_SYMBOL_GPL(l2tp_tunnel_dec_refcount); +EXPORT_SYMBOL_GPL(l2tp_tunnel_put); -void l2tp_session_inc_refcount(struct l2tp_session *session) -{ - refcount_inc(&session->ref_count); -} -EXPORT_SYMBOL_GPL(l2tp_session_inc_refcount); - -void l2tp_session_dec_refcount(struct l2tp_session *session) +void l2tp_session_put(struct l2tp_session *session) { if (refcount_dec_and_test(&session->ref_count)) l2tp_session_free(session); } -EXPORT_SYMBOL_GPL(l2tp_session_dec_refcount); +EXPORT_SYMBOL_GPL(l2tp_session_put); /* Lookup a tunnel. A new reference is held on the returned tunnel. */ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id) @@ -211,26 +229,27 @@ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id) } EXPORT_SYMBOL_GPL(l2tp_tunnel_get); -struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth) +struct l2tp_tunnel *l2tp_tunnel_get_next(const struct net *net, unsigned long *key) { struct l2tp_net *pn = l2tp_pernet(net); - unsigned long tunnel_id, tmp; - struct l2tp_tunnel *tunnel; - int count = 0; + struct l2tp_tunnel *tunnel = NULL; rcu_read_lock_bh(); - idr_for_each_entry_ul(&pn->l2tp_tunnel_idr, tunnel, tmp, tunnel_id) { - if (tunnel && ++count > nth && - refcount_inc_not_zero(&tunnel->ref_count)) { +again: + tunnel = idr_get_next_ul(&pn->l2tp_tunnel_idr, key); + if (tunnel) { + if (refcount_inc_not_zero(&tunnel->ref_count)) { rcu_read_unlock_bh(); return tunnel; } + (*key)++; + goto again; } rcu_read_unlock_bh(); return NULL; } -EXPORT_SYMBOL_GPL(l2tp_tunnel_get_nth); +EXPORT_SYMBOL_GPL(l2tp_tunnel_get_next); struct l2tp_session *l2tp_v3_session_get(const struct net *net, struct sock *sk, u32 session_id) { @@ -254,7 +273,15 @@ struct l2tp_session *l2tp_v3_session_get(const struct net *net, struct sock *sk, hash_for_each_possible_rcu(pn->l2tp_v3_session_htable, session, hlist, key) { - if (session->tunnel->sock == sk && + /* session->tunnel may be NULL if another thread is in + * l2tp_session_register and has added an item to + * l2tp_v3_session_htable but hasn't yet added the + * session to its tunnel's session_list. + */ + struct l2tp_tunnel *tunnel = READ_ONCE(session->tunnel); + + if (session->session_id == session_id && + tunnel && tunnel->sock == sk && refcount_inc_not_zero(&session->ref_count)) { rcu_read_unlock_bh(); return session; @@ -295,24 +322,109 @@ struct l2tp_session *l2tp_session_get(const struct net *net, struct sock *sk, in } EXPORT_SYMBOL_GPL(l2tp_session_get); -struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth) +static struct l2tp_session *l2tp_v2_session_get_next(const struct net *net, + u16 tid, + unsigned long *key) { - struct l2tp_session *session; - int count = 0; + struct l2tp_net *pn = l2tp_pernet(net); + struct l2tp_session *session = NULL; + + /* Start searching within the range of the tid */ + if (*key == 0) + *key = l2tp_v2_session_key(tid, 0); rcu_read_lock_bh(); - list_for_each_entry_rcu(session, &tunnel->session_list, list) { - if (++count > nth) { - l2tp_session_inc_refcount(session); +again: + session = idr_get_next_ul(&pn->l2tp_v2_session_idr, key); + if (session) { + struct l2tp_tunnel *tunnel = READ_ONCE(session->tunnel); + + /* ignore sessions with id 0 as they are internal for pppol2tp */ + if (session->session_id == 0) { + (*key)++; + goto again; + } + + if (tunnel && tunnel->tunnel_id == tid && + refcount_inc_not_zero(&session->ref_count)) { rcu_read_unlock_bh(); return session; } + + (*key)++; + if (tunnel->tunnel_id == tid) + goto again; } rcu_read_unlock_bh(); return NULL; } -EXPORT_SYMBOL_GPL(l2tp_session_get_nth); + +static struct l2tp_session *l2tp_v3_session_get_next(const struct net *net, + u32 tid, struct sock *sk, + unsigned long *key) +{ + struct l2tp_net *pn = l2tp_pernet(net); + struct l2tp_session *session = NULL; + + rcu_read_lock_bh(); +again: + session = idr_get_next_ul(&pn->l2tp_v3_session_idr, key); + if (session && !hash_hashed(&session->hlist)) { + struct l2tp_tunnel *tunnel = READ_ONCE(session->tunnel); + + if (tunnel && tunnel->tunnel_id == tid && + refcount_inc_not_zero(&session->ref_count)) { + rcu_read_unlock_bh(); + return session; + } + + (*key)++; + goto again; + } + + /* If we get here and session is non-NULL, the IDR entry may be one + * where the session_id collides with one in another tunnel. Check + * session_htable for a match. There can only be one session of a given + * ID per tunnel so we can return as soon as a match is found. + */ + if (session && hash_hashed(&session->hlist)) { + unsigned long hkey = l2tp_v3_session_hashkey(sk, session->session_id); + u32 sid = session->session_id; + + hash_for_each_possible_rcu(pn->l2tp_v3_session_htable, session, + hlist, hkey) { + struct l2tp_tunnel *tunnel = READ_ONCE(session->tunnel); + + if (session->session_id == sid && + tunnel && tunnel->tunnel_id == tid && + refcount_inc_not_zero(&session->ref_count)) { + rcu_read_unlock_bh(); + return session; + } + } + + /* If no match found, the colliding session ID isn't in our + * tunnel so try the next session ID. + */ + (*key)++; + goto again; + } + + rcu_read_unlock_bh(); + + return NULL; +} + +struct l2tp_session *l2tp_session_get_next(const struct net *net, struct sock *sk, int pver, + u32 tunnel_id, unsigned long *key) +{ + if (pver == L2TP_HDR_VER_2) + return l2tp_v2_session_get_next(net, tunnel_id, key); + else + return l2tp_v3_session_get_next(net, tunnel_id, sk, key); +} +EXPORT_SYMBOL_GPL(l2tp_session_get_next); /* Lookup a session by interface name. * This is very inefficient but is only used by management interfaces. @@ -330,7 +442,7 @@ struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net, if (tunnel) { list_for_each_entry_rcu(session, &tunnel->session_list, list) { if (!strcmp(session->ifname, ifname)) { - l2tp_session_inc_refcount(session); + refcount_inc(&session->ref_count); rcu_read_unlock_bh(); return session; @@ -347,7 +459,7 @@ EXPORT_SYMBOL_GPL(l2tp_session_get_by_ifname); static void l2tp_session_coll_list_add(struct l2tp_session_coll_list *clist, struct l2tp_session *session) { - l2tp_session_inc_refcount(session); + refcount_inc(&session->ref_count); WARN_ON_ONCE(session->coll_list); session->coll_list = clist; spin_lock(&clist->lock); @@ -387,12 +499,12 @@ static int l2tp_session_collision_add(struct l2tp_net *pn, /* If existing session isn't already in the session hlist, add it. */ if (!hash_hashed(&session2->hlist)) - hash_add(pn->l2tp_v3_session_htable, &session2->hlist, - session2->hlist_key); + hash_add_rcu(pn->l2tp_v3_session_htable, &session2->hlist, + session2->hlist_key); /* Add new session to the hlist and collision list */ - hash_add(pn->l2tp_v3_session_htable, &session1->hlist, - session1->hlist_key); + hash_add_rcu(pn->l2tp_v3_session_htable, &session1->hlist, + session1->hlist_key); refcount_inc(&clist->ref_count); l2tp_session_coll_list_add(clist, session1); @@ -408,7 +520,7 @@ static void l2tp_session_collision_del(struct l2tp_net *pn, lockdep_assert_held(&pn->l2tp_session_idr_lock); - hash_del(&session->hlist); + hash_del_rcu(&session->hlist); if (clist) { /* Remove session from its collision list. If there @@ -433,7 +545,7 @@ static void l2tp_session_collision_del(struct l2tp_net *pn, spin_unlock(&clist->lock); if (refcount_dec_and_test(&clist->ref_count)) kfree(clist); - l2tp_session_dec_refcount(session); + l2tp_session_put(session); } } @@ -442,6 +554,7 @@ int l2tp_session_register(struct l2tp_session *session, { struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net); struct l2tp_session *other_session = NULL; + void *old = NULL; u32 session_key; int err; @@ -481,16 +594,23 @@ int l2tp_session_register(struct l2tp_session *session, goto out; } - l2tp_tunnel_inc_refcount(tunnel); - list_add(&session->list, &tunnel->session_list); + refcount_inc(&tunnel->ref_count); + WRITE_ONCE(session->tunnel, tunnel); + list_add_rcu(&session->list, &tunnel->session_list); + /* this makes session available to lockless getters */ if (tunnel->version == L2TP_HDR_VER_3) { if (!other_session) - idr_replace(&pn->l2tp_v3_session_idr, session, session_key); + old = idr_replace(&pn->l2tp_v3_session_idr, session, session_key); } else { - idr_replace(&pn->l2tp_v2_session_idr, session, session_key); + old = idr_replace(&pn->l2tp_v2_session_idr, session, session_key); } + /* old should be NULL, unless something removed or modified + * the IDR entry after our idr_alloc_32 above (which shouldn't + * happen). + */ + WARN_ON_ONCE(old); out: spin_unlock_bh(&pn->l2tp_session_idr_lock); spin_unlock_bh(&tunnel->list_lock); @@ -797,7 +917,8 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, if (!session->lns_mode && !session->send_seq) { trace_session_seqnum_lns_enable(session); session->send_seq = 1; - l2tp_session_set_header_len(session, tunnel->version); + l2tp_session_set_header_len(session, tunnel->version, + tunnel->encap); } } else { /* No sequence numbers. @@ -818,7 +939,8 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, if (!session->lns_mode && session->send_seq) { trace_session_seqnum_lns_disable(session); session->send_seq = 0; - l2tp_session_set_header_len(session, tunnel->version); + l2tp_session_set_header_len(session, tunnel->version, + tunnel->encap); } else if (session->send_seq) { pr_debug_ratelimited("%s: recv data has no seq numbers when required. Discarding.\n", session->name); @@ -955,7 +1077,7 @@ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) if (!session || !session->recv_skb) { if (session) - l2tp_session_dec_refcount(session); + l2tp_session_put(session); /* Not found? Pass to userspace to deal with */ goto pass; @@ -969,12 +1091,12 @@ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) if (version == L2TP_HDR_VER_3 && l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) { - l2tp_session_dec_refcount(session); + l2tp_session_put(session); goto invalid; } l2tp_recv_common(session, skb, ptr, optr, hdrflags, length); - l2tp_session_dec_refcount(session); + l2tp_session_put(session); return 0; @@ -1218,44 +1340,6 @@ EXPORT_SYMBOL_GPL(l2tp_xmit_skb); * Tinnel and session create/destroy. *****************************************************************************/ -/* Tunnel socket destruct hook. - * The tunnel context is deleted only when all session sockets have been - * closed. - */ -static void l2tp_tunnel_destruct(struct sock *sk) -{ - struct l2tp_tunnel *tunnel = l2tp_sk_to_tunnel(sk); - - if (!tunnel) - goto end; - - /* Disable udp encapsulation */ - switch (tunnel->encap) { - case L2TP_ENCAPTYPE_UDP: - /* No longer an encapsulation socket. See net/ipv4/udp.c */ - WRITE_ONCE(udp_sk(sk)->encap_type, 0); - udp_sk(sk)->encap_rcv = NULL; - udp_sk(sk)->encap_destroy = NULL; - break; - case L2TP_ENCAPTYPE_IP: - break; - } - - /* Remove hooks into tunnel socket */ - write_lock_bh(&sk->sk_callback_lock); - sk->sk_destruct = tunnel->old_sk_destruct; - sk->sk_user_data = NULL; - write_unlock_bh(&sk->sk_callback_lock); - - /* Call the original destructor */ - if (sk->sk_destruct) - (*sk->sk_destruct)(sk); - - kfree_rcu(tunnel, rcu); -end: - return; -} - /* Remove an l2tp session from l2tp_core's lists. */ static void l2tp_session_unhash(struct l2tp_session *session) { @@ -1288,8 +1372,6 @@ static void l2tp_session_unhash(struct l2tp_session *session) spin_unlock_bh(&pn->l2tp_session_idr_lock); spin_unlock_bh(&tunnel->list_lock); - - synchronize_rcu(); } } @@ -1301,28 +1383,21 @@ static void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel) spin_lock_bh(&tunnel->list_lock); tunnel->acpt_newsess = false; - for (;;) { - session = list_first_entry_or_null(&tunnel->session_list, - struct l2tp_session, list); - if (!session) - break; - l2tp_session_inc_refcount(session); - list_del_init(&session->list); - spin_unlock_bh(&tunnel->list_lock); + list_for_each_entry(session, &tunnel->session_list, list) l2tp_session_delete(session); - spin_lock_bh(&tunnel->list_lock); - l2tp_session_dec_refcount(session); - } spin_unlock_bh(&tunnel->list_lock); } /* Tunnel socket destroy hook for UDP encapsulation */ static void l2tp_udp_encap_destroy(struct sock *sk) { - struct l2tp_tunnel *tunnel = l2tp_sk_to_tunnel(sk); + struct l2tp_tunnel *tunnel; - if (tunnel) + tunnel = l2tp_sk_to_tunnel(sk); + if (tunnel) { l2tp_tunnel_delete(tunnel); + l2tp_tunnel_put(tunnel); + } } static void l2tp_tunnel_remove(struct net *net, struct l2tp_tunnel *tunnel) @@ -1356,10 +1431,10 @@ static void l2tp_tunnel_del_work(struct work_struct *work) l2tp_tunnel_remove(tunnel->l2tp_net, tunnel); /* drop initial ref */ - l2tp_tunnel_dec_refcount(tunnel); + l2tp_tunnel_put(tunnel); /* drop workqueue ref */ - l2tp_tunnel_dec_refcount(tunnel); + l2tp_tunnel_put(tunnel); } /* Create a socket for the tunnel, if one isn't set up by @@ -1505,7 +1580,6 @@ int l2tp_tunnel_create(int fd, int version, u32 tunnel_id, u32 peer_tunnel_id, tunnel->tunnel_id = tunnel_id; tunnel->peer_tunnel_id = peer_tunnel_id; - tunnel->magic = L2TP_TUNNEL_MAGIC; sprintf(&tunnel->name[0], "tunl %u", tunnel_id); spin_lock_init(&tunnel->list_lock); tunnel->acpt_newsess = true; @@ -1531,6 +1605,8 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_create); static int l2tp_validate_socket(const struct sock *sk, const struct net *net, enum l2tp_encap_type encap) { + struct l2tp_tunnel *tunnel; + if (!net_eq(sock_net(sk), net)) return -EINVAL; @@ -1544,8 +1620,14 @@ static int l2tp_validate_socket(const struct sock *sk, const struct net *net, (encap == L2TP_ENCAPTYPE_IP && sk->sk_protocol != IPPROTO_L2TP)) return -EPROTONOSUPPORT; - if (sk->sk_user_data) + if (encap == L2TP_ENCAPTYPE_UDP && sk->sk_user_data) + return -EBUSY; + + tunnel = l2tp_sk_to_tunnel(sk); + if (tunnel) { + l2tp_tunnel_put(tunnel); return -EBUSY; + } return 0; } @@ -1584,12 +1666,10 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, ret = l2tp_validate_socket(sk, net, tunnel->encap); if (ret < 0) goto err_inval_sock; - rcu_assign_sk_user_data(sk, tunnel); write_unlock_bh(&sk->sk_callback_lock); if (tunnel->encap == L2TP_ENCAPTYPE_UDP) { struct udp_tunnel_sock_cfg udp_cfg = { - .sk_user_data = tunnel, .encap_type = UDP_ENCAP_L2TPINUDP, .encap_rcv = l2tp_udp_encap_recv, .encap_err_rcv = l2tp_udp_encap_err_recv, @@ -1599,8 +1679,6 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, setup_udp_tunnel_sock(net, sock, &udp_cfg); } - tunnel->old_sk_destruct = sk->sk_destruct; - sk->sk_destruct = &l2tp_tunnel_destruct; sk->sk_allocation = GFP_ATOMIC; release_sock(sk); @@ -1639,7 +1717,7 @@ void l2tp_tunnel_delete(struct l2tp_tunnel *tunnel) { if (!test_and_set_bit(0, &tunnel->dead)) { trace_delete_tunnel(tunnel); - l2tp_tunnel_inc_refcount(tunnel); + refcount_inc(&tunnel->ref_count); queue_work(l2tp_wq, &tunnel->del_work); } } @@ -1647,23 +1725,37 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_delete); void l2tp_session_delete(struct l2tp_session *session) { - if (test_and_set_bit(0, &session->dead)) - return; + if (!test_and_set_bit(0, &session->dead)) { + trace_delete_session(session); + refcount_inc(&session->ref_count); + queue_work(l2tp_wq, &session->del_work); + } +} +EXPORT_SYMBOL_GPL(l2tp_session_delete); + +/* Workqueue session deletion function */ +static void l2tp_session_del_work(struct work_struct *work) +{ + struct l2tp_session *session = container_of(work, struct l2tp_session, + del_work); - trace_delete_session(session); l2tp_session_unhash(session); l2tp_session_queue_purge(session); if (session->session_close) (*session->session_close)(session); - l2tp_session_dec_refcount(session); + /* drop initial ref */ + l2tp_session_put(session); + + /* drop workqueue ref */ + l2tp_session_put(session); } -EXPORT_SYMBOL_GPL(l2tp_session_delete); /* We come here whenever a session's send_seq, cookie_len or * l2specific_type parameters are set. */ -void l2tp_session_set_header_len(struct l2tp_session *session, int version) +void l2tp_session_set_header_len(struct l2tp_session *session, int version, + enum l2tp_encap_type encap) { if (version == L2TP_HDR_VER_2) { session->hdr_len = 6; @@ -1672,7 +1764,7 @@ void l2tp_session_set_header_len(struct l2tp_session *session, int version) } else { session->hdr_len = 4 + session->cookie_len; session->hdr_len += l2tp_get_l2specific_len(session); - if (session->tunnel->encap == L2TP_ENCAPTYPE_UDP) + if (encap == L2TP_ENCAPTYPE_UDP) session->hdr_len += 4; } } @@ -1686,7 +1778,6 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn session = kzalloc(sizeof(*session) + priv_size, GFP_KERNEL); if (session) { session->magic = L2TP_SESSION_MAGIC; - session->tunnel = tunnel; session->session_id = session_id; session->peer_session_id = peer_session_id; @@ -1710,6 +1801,7 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn INIT_HLIST_NODE(&session->hlist); INIT_LIST_HEAD(&session->clist); INIT_LIST_HEAD(&session->list); + INIT_WORK(&session->del_work, l2tp_session_del_work); if (cfg) { session->pwtype = cfg->pw_type; @@ -1724,7 +1816,7 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn memcpy(&session->peer_cookie[0], &cfg->peer_cookie[0], cfg->peer_cookie_len); } - l2tp_session_set_header_len(session, tunnel->version); + l2tp_session_set_header_len(session, tunnel->version, tunnel->encap); refcount_set(&session->ref_count, 1); @@ -1753,7 +1845,7 @@ static __net_init int l2tp_init_net(struct net *net) return 0; } -static __net_exit void l2tp_exit_net(struct net *net) +static __net_exit void l2tp_pre_exit_net(struct net *net) { struct l2tp_net *pn = l2tp_pernet(net); struct l2tp_tunnel *tunnel = NULL; @@ -1766,18 +1858,34 @@ static __net_exit void l2tp_exit_net(struct net *net) } rcu_read_unlock_bh(); - if (l2tp_wq) - flush_workqueue(l2tp_wq); - rcu_barrier(); + if (l2tp_wq) { + /* Run all TUNNEL_DELETE work items just queued. */ + __flush_workqueue(l2tp_wq); + + /* Each TUNNEL_DELETE work item will queue a SESSION_DELETE + * work item for each session in the tunnel. Flush the + * workqueue again to process these. + */ + __flush_workqueue(l2tp_wq); + } +} + +static __net_exit void l2tp_exit_net(struct net *net) +{ + struct l2tp_net *pn = l2tp_pernet(net); + WARN_ON_ONCE(!idr_is_empty(&pn->l2tp_v2_session_idr)); idr_destroy(&pn->l2tp_v2_session_idr); + WARN_ON_ONCE(!idr_is_empty(&pn->l2tp_v3_session_idr)); idr_destroy(&pn->l2tp_v3_session_idr); + WARN_ON_ONCE(!idr_is_empty(&pn->l2tp_tunnel_idr)); idr_destroy(&pn->l2tp_tunnel_idr); } static struct pernet_operations l2tp_net_ops = { .init = l2tp_init_net, .exit = l2tp_exit_net, + .pre_exit = l2tp_pre_exit_net, .id = &l2tp_net_id, .size = sizeof(struct l2tp_net), }; diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 8ac81bc1bc6f..ffd8ced3a51f 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -16,7 +16,6 @@ #endif /* Random numbers used for internal consistency checks of tunnel and session structures */ -#define L2TP_TUNNEL_MAGIC 0x42114DDA #define L2TP_SESSION_MAGIC 0x0C04EB7D struct sk_buff; @@ -67,6 +66,7 @@ struct l2tp_session_coll_list { struct l2tp_session { int magic; /* should be L2TP_SESSION_MAGIC */ long dead; + struct rcu_head rcu; struct l2tp_tunnel *tunnel; /* back pointer to tunnel context */ u32 session_id; @@ -103,6 +103,7 @@ struct l2tp_session { int reorder_skip; /* set if skip to next nr */ enum l2tp_pwtype pwtype; struct l2tp_stats stats; + struct work_struct del_work; /* Session receive handler for data packets. * Each pseudowire implementation should implement this callback in order to @@ -155,8 +156,6 @@ struct l2tp_tunnel_cfg { */ #define L2TP_TUNNEL_NAME_MAX 20 struct l2tp_tunnel { - int magic; /* Should be L2TP_TUNNEL_MAGIC */ - unsigned long dead; struct rcu_head rcu; @@ -176,7 +175,6 @@ struct l2tp_tunnel { struct net *l2tp_net; /* the net we belong to */ refcount_t ref_count; - void (*old_sk_destruct)(struct sock *sk); struct sock *sock; /* parent socket */ int fd; /* parent fd, if tunnel socket was created * by userspace @@ -211,23 +209,22 @@ static inline void *l2tp_session_priv(struct l2tp_session *session) } /* Tunnel and session refcounts */ -void l2tp_tunnel_inc_refcount(struct l2tp_tunnel *tunnel); -void l2tp_tunnel_dec_refcount(struct l2tp_tunnel *tunnel); -void l2tp_session_inc_refcount(struct l2tp_session *session); -void l2tp_session_dec_refcount(struct l2tp_session *session); +void l2tp_tunnel_put(struct l2tp_tunnel *tunnel); +void l2tp_session_put(struct l2tp_session *session); /* Tunnel and session lookup. * These functions take a reference on the instances they return, so * the caller must ensure that the reference is dropped appropriately. */ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id); -struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth); +struct l2tp_tunnel *l2tp_tunnel_get_next(const struct net *net, unsigned long *key); struct l2tp_session *l2tp_v3_session_get(const struct net *net, struct sock *sk, u32 session_id); struct l2tp_session *l2tp_v2_session_get(const struct net *net, u16 tunnel_id, u16 session_id); struct l2tp_session *l2tp_session_get(const struct net *net, struct sock *sk, int pver, u32 tunnel_id, u32 session_id); -struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth); +struct l2tp_session *l2tp_session_get_next(const struct net *net, struct sock *sk, int pver, + u32 tunnel_id, unsigned long *key); struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net, const char *ifname); @@ -260,7 +257,8 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb); /* Transmit path helpers for sending packets over the tunnel socket. */ -void l2tp_session_set_header_len(struct l2tp_session *session, int version); +void l2tp_session_set_header_len(struct l2tp_session *session, int version, + enum l2tp_encap_type encap); int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb); /* Pseudowire management. @@ -273,10 +271,7 @@ void l2tp_nl_unregister_ops(enum l2tp_pwtype pw_type); /* IOCTL helper for IP encap modules. */ int l2tp_ioctl(struct sock *sk, int cmd, int *karg); -/* Extract the tunnel structure from a socket's sk_user_data pointer, - * validating the tunnel magic feather. - */ -struct l2tp_tunnel *l2tp_sk_to_tunnel(struct sock *sk); +struct l2tp_tunnel *l2tp_sk_to_tunnel(const struct sock *sk); static inline int l2tp_get_l2specific_len(struct l2tp_session *session) { diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c index 8755ae521154..2d0c8275a3a8 100644 --- a/net/l2tp/l2tp_debugfs.c +++ b/net/l2tp/l2tp_debugfs.c @@ -34,8 +34,8 @@ static struct dentry *rootdir; struct l2tp_dfs_seq_data { struct net *net; netns_tracker ns_tracker; - int tunnel_idx; /* current tunnel */ - int session_idx; /* index of session within current tunnel */ + unsigned long tkey; /* lookup key of current tunnel */ + unsigned long skey; /* lookup key of current session */ struct l2tp_tunnel *tunnel; struct l2tp_session *session; /* NULL means get next tunnel */ }; @@ -44,23 +44,25 @@ static void l2tp_dfs_next_tunnel(struct l2tp_dfs_seq_data *pd) { /* Drop reference taken during previous invocation */ if (pd->tunnel) - l2tp_tunnel_dec_refcount(pd->tunnel); + l2tp_tunnel_put(pd->tunnel); - pd->tunnel = l2tp_tunnel_get_nth(pd->net, pd->tunnel_idx); - pd->tunnel_idx++; + pd->tunnel = l2tp_tunnel_get_next(pd->net, &pd->tkey); + pd->tkey++; } static void l2tp_dfs_next_session(struct l2tp_dfs_seq_data *pd) { /* Drop reference taken during previous invocation */ if (pd->session) - l2tp_session_dec_refcount(pd->session); + l2tp_session_put(pd->session); - pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx); - pd->session_idx++; + pd->session = l2tp_session_get_next(pd->net, pd->tunnel->sock, + pd->tunnel->version, + pd->tunnel->tunnel_id, &pd->skey); + pd->skey++; if (!pd->session) { - pd->session_idx = 0; + pd->skey = 0; l2tp_dfs_next_tunnel(pd); } } @@ -109,11 +111,11 @@ static void l2tp_dfs_seq_stop(struct seq_file *p, void *v) * or l2tp_dfs_next_tunnel(). */ if (pd->session) { - l2tp_session_dec_refcount(pd->session); + l2tp_session_put(pd->session); pd->session = NULL; } if (pd->tunnel) { - l2tp_tunnel_dec_refcount(pd->tunnel); + l2tp_tunnel_put(pd->tunnel); pd->tunnel = NULL; } } diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index 8ba00ad433c2..15a862f33f76 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -72,31 +72,19 @@ static netdev_tx_t l2tp_eth_dev_xmit(struct sk_buff *skb, struct net_device *dev unsigned int len = skb->len; int ret = l2tp_xmit_skb(session, skb); - if (likely(ret == NET_XMIT_SUCCESS)) { - DEV_STATS_ADD(dev, tx_bytes, len); - DEV_STATS_INC(dev, tx_packets); - } else { + if (likely(ret == NET_XMIT_SUCCESS)) + dev_sw_netstats_tx_add(dev, 1, len); + else DEV_STATS_INC(dev, tx_dropped); - } - return NETDEV_TX_OK; -} -static void l2tp_eth_get_stats64(struct net_device *dev, - struct rtnl_link_stats64 *stats) -{ - stats->tx_bytes = DEV_STATS_READ(dev, tx_bytes); - stats->tx_packets = DEV_STATS_READ(dev, tx_packets); - stats->tx_dropped = DEV_STATS_READ(dev, tx_dropped); - stats->rx_bytes = DEV_STATS_READ(dev, rx_bytes); - stats->rx_packets = DEV_STATS_READ(dev, rx_packets); - stats->rx_errors = DEV_STATS_READ(dev, rx_errors); + return NETDEV_TX_OK; } static const struct net_device_ops l2tp_eth_netdev_ops = { .ndo_init = l2tp_eth_dev_init, .ndo_uninit = l2tp_eth_dev_uninit, .ndo_start_xmit = l2tp_eth_dev_xmit, - .ndo_get_stats64 = l2tp_eth_get_stats64, + .ndo_get_stats64 = dev_get_tstats64, .ndo_set_mac_address = eth_mac_addr, }; @@ -112,6 +100,7 @@ static void l2tp_eth_dev_setup(struct net_device *dev) dev->features |= NETIF_F_LLTX; dev->netdev_ops = &l2tp_eth_netdev_ops; dev->needs_free_netdev = true; + dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; } static void l2tp_eth_dev_recv(struct l2tp_session *session, struct sk_buff *skb, int data_len) @@ -138,12 +127,11 @@ static void l2tp_eth_dev_recv(struct l2tp_session *session, struct sk_buff *skb, if (!dev) goto error_rcu; - if (dev_forward_skb(dev, skb) == NET_RX_SUCCESS) { - DEV_STATS_INC(dev, rx_packets); - DEV_STATS_ADD(dev, rx_bytes, data_len); - } else { + if (dev_forward_skb(dev, skb) == NET_RX_SUCCESS) + dev_sw_netstats_rx_add(dev, data_len); + else DEV_STATS_INC(dev, rx_errors); - } + rcu_read_unlock(); return; @@ -283,7 +271,7 @@ static int l2tp_eth_create(struct net *net, struct l2tp_tunnel *tunnel, spriv = l2tp_session_priv(session); - l2tp_session_inc_refcount(session); + refcount_inc(&session->ref_count); rtnl_lock(); @@ -301,7 +289,7 @@ static int l2tp_eth_create(struct net *net, struct l2tp_tunnel *tunnel, if (rc < 0) { rtnl_unlock(); l2tp_session_delete(session); - l2tp_session_dec_refcount(session); + l2tp_session_put(session); free_netdev(dev); return rc; @@ -312,17 +300,17 @@ static int l2tp_eth_create(struct net *net, struct l2tp_tunnel *tunnel, rtnl_unlock(); - l2tp_session_dec_refcount(session); + l2tp_session_put(session); __module_get(THIS_MODULE); return 0; err_sess_dev: - l2tp_session_dec_refcount(session); + l2tp_session_put(session); free_netdev(dev); err_sess: - kfree(session); + l2tp_session_put(session); err: return rc; } diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index e48aa177d74c..4bc24fddfd52 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -22,9 +22,19 @@ #include <net/tcp_states.h> #include <net/protocol.h> #include <net/xfrm.h> +#include <net/net_namespace.h> +#include <net/netns/generic.h> #include "l2tp_core.h" +/* per-net private data for this module */ +static unsigned int l2tp_ip_net_id; +struct l2tp_ip_net { + rwlock_t l2tp_ip_lock; + struct hlist_head l2tp_ip_table; + struct hlist_head l2tp_ip_bind_table; +}; + struct l2tp_ip_sock { /* inet_sock has to be the first member of l2tp_ip_sock */ struct inet_sock inet; @@ -33,21 +43,23 @@ struct l2tp_ip_sock { u32 peer_conn_id; }; -static DEFINE_RWLOCK(l2tp_ip_lock); -static struct hlist_head l2tp_ip_table; -static struct hlist_head l2tp_ip_bind_table; - -static inline struct l2tp_ip_sock *l2tp_ip_sk(const struct sock *sk) +static struct l2tp_ip_sock *l2tp_ip_sk(const struct sock *sk) { return (struct l2tp_ip_sock *)sk; } +static struct l2tp_ip_net *l2tp_ip_pernet(const struct net *net) +{ + return net_generic(net, l2tp_ip_net_id); +} + static struct sock *__l2tp_ip_bind_lookup(const struct net *net, __be32 laddr, __be32 raddr, int dif, u32 tunnel_id) { + struct l2tp_ip_net *pn = l2tp_ip_pernet(net); struct sock *sk; - sk_for_each_bound(sk, &l2tp_ip_bind_table) { + sk_for_each_bound(sk, &pn->l2tp_ip_bind_table) { const struct l2tp_ip_sock *l2tp = l2tp_ip_sk(sk); const struct inet_sock *inet = inet_sk(sk); int bound_dev_if; @@ -113,6 +125,7 @@ found: static int l2tp_ip_recv(struct sk_buff *skb) { struct net *net = dev_net(skb->dev); + struct l2tp_ip_net *pn; struct sock *sk; u32 session_id; u32 tunnel_id; @@ -121,6 +134,8 @@ static int l2tp_ip_recv(struct sk_buff *skb) struct l2tp_tunnel *tunnel = NULL; struct iphdr *iph; + pn = l2tp_ip_pernet(net); + if (!pskb_may_pull(skb, 4)) goto discard; @@ -152,7 +167,7 @@ static int l2tp_ip_recv(struct sk_buff *skb) goto discard_sess; l2tp_recv_common(session, skb, ptr, optr, 0, skb->len); - l2tp_session_dec_refcount(session); + l2tp_session_put(session); return 0; @@ -167,15 +182,15 @@ pass_up: tunnel_id = ntohl(*(__be32 *)&skb->data[4]); iph = (struct iphdr *)skb_network_header(skb); - read_lock_bh(&l2tp_ip_lock); + read_lock_bh(&pn->l2tp_ip_lock); sk = __l2tp_ip_bind_lookup(net, iph->daddr, iph->saddr, inet_iif(skb), tunnel_id); if (!sk) { - read_unlock_bh(&l2tp_ip_lock); + read_unlock_bh(&pn->l2tp_ip_lock); goto discard; } sock_hold(sk); - read_unlock_bh(&l2tp_ip_lock); + read_unlock_bh(&pn->l2tp_ip_lock); if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_put; @@ -185,7 +200,7 @@ pass_up: return sk_receive_skb(sk, skb, 1); discard_sess: - l2tp_session_dec_refcount(session); + l2tp_session_put(session); goto discard; discard_put: @@ -198,21 +213,25 @@ discard: static int l2tp_ip_hash(struct sock *sk) { + struct l2tp_ip_net *pn = l2tp_ip_pernet(sock_net(sk)); + if (sk_unhashed(sk)) { - write_lock_bh(&l2tp_ip_lock); - sk_add_node(sk, &l2tp_ip_table); - write_unlock_bh(&l2tp_ip_lock); + write_lock_bh(&pn->l2tp_ip_lock); + sk_add_node(sk, &pn->l2tp_ip_table); + write_unlock_bh(&pn->l2tp_ip_lock); } return 0; } static void l2tp_ip_unhash(struct sock *sk) { + struct l2tp_ip_net *pn = l2tp_ip_pernet(sock_net(sk)); + if (sk_unhashed(sk)) return; - write_lock_bh(&l2tp_ip_lock); + write_lock_bh(&pn->l2tp_ip_lock); sk_del_node_init(sk); - write_unlock_bh(&l2tp_ip_lock); + write_unlock_bh(&pn->l2tp_ip_lock); } static int l2tp_ip_open(struct sock *sk) @@ -226,23 +245,26 @@ static int l2tp_ip_open(struct sock *sk) static void l2tp_ip_close(struct sock *sk, long timeout) { - write_lock_bh(&l2tp_ip_lock); + struct l2tp_ip_net *pn = l2tp_ip_pernet(sock_net(sk)); + + write_lock_bh(&pn->l2tp_ip_lock); hlist_del_init(&sk->sk_bind_node); sk_del_node_init(sk); - write_unlock_bh(&l2tp_ip_lock); + write_unlock_bh(&pn->l2tp_ip_lock); sk_common_release(sk); } static void l2tp_ip_destroy_sock(struct sock *sk) { - struct l2tp_tunnel *tunnel = l2tp_sk_to_tunnel(sk); - struct sk_buff *skb; + struct l2tp_tunnel *tunnel; - while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL) - kfree_skb(skb); + __skb_queue_purge(&sk->sk_write_queue); - if (tunnel) + tunnel = l2tp_sk_to_tunnel(sk); + if (tunnel) { l2tp_tunnel_delete(tunnel); + l2tp_tunnel_put(tunnel); + } } static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) @@ -250,6 +272,7 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) struct inet_sock *inet = inet_sk(sk); struct sockaddr_l2tpip *addr = (struct sockaddr_l2tpip *)uaddr; struct net *net = sock_net(sk); + struct l2tp_ip_net *pn; int ret; int chk_addr_ret; @@ -280,10 +303,11 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST) inet->inet_saddr = 0; /* Use device */ - write_lock_bh(&l2tp_ip_lock); + pn = l2tp_ip_pernet(net); + write_lock_bh(&pn->l2tp_ip_lock); if (__l2tp_ip_bind_lookup(net, addr->l2tp_addr.s_addr, 0, sk->sk_bound_dev_if, addr->l2tp_conn_id)) { - write_unlock_bh(&l2tp_ip_lock); + write_unlock_bh(&pn->l2tp_ip_lock); ret = -EADDRINUSE; goto out; } @@ -291,9 +315,9 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) sk_dst_reset(sk); l2tp_ip_sk(sk)->conn_id = addr->l2tp_conn_id; - sk_add_bind_node(sk, &l2tp_ip_bind_table); + sk_add_bind_node(sk, &pn->l2tp_ip_bind_table); sk_del_node_init(sk); - write_unlock_bh(&l2tp_ip_lock); + write_unlock_bh(&pn->l2tp_ip_lock); ret = 0; sock_reset_flag(sk, SOCK_ZAPPED); @@ -307,6 +331,7 @@ out: static int l2tp_ip_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct sockaddr_l2tpip *lsa = (struct sockaddr_l2tpip *)uaddr; + struct l2tp_ip_net *pn = l2tp_ip_pernet(sock_net(sk)); int rc; if (addr_len < sizeof(*lsa)) @@ -329,10 +354,10 @@ static int l2tp_ip_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len l2tp_ip_sk(sk)->peer_conn_id = lsa->l2tp_conn_id; - write_lock_bh(&l2tp_ip_lock); + write_lock_bh(&pn->l2tp_ip_lock); hlist_del_init(&sk->sk_bind_node); - sk_add_bind_node(sk, &l2tp_ip_bind_table); - write_unlock_bh(&l2tp_ip_lock); + sk_add_bind_node(sk, &pn->l2tp_ip_bind_table); + write_unlock_bh(&pn->l2tp_ip_lock); out_sk: release_sock(sk); @@ -637,25 +662,58 @@ static struct net_protocol l2tp_ip_protocol __read_mostly = { .handler = l2tp_ip_recv, }; +static __net_init int l2tp_ip_init_net(struct net *net) +{ + struct l2tp_ip_net *pn = net_generic(net, l2tp_ip_net_id); + + rwlock_init(&pn->l2tp_ip_lock); + INIT_HLIST_HEAD(&pn->l2tp_ip_table); + INIT_HLIST_HEAD(&pn->l2tp_ip_bind_table); + return 0; +} + +static __net_exit void l2tp_ip_exit_net(struct net *net) +{ + struct l2tp_ip_net *pn = l2tp_ip_pernet(net); + + write_lock_bh(&pn->l2tp_ip_lock); + WARN_ON_ONCE(hlist_count_nodes(&pn->l2tp_ip_table) != 0); + WARN_ON_ONCE(hlist_count_nodes(&pn->l2tp_ip_bind_table) != 0); + write_unlock_bh(&pn->l2tp_ip_lock); +} + +static struct pernet_operations l2tp_ip_net_ops = { + .init = l2tp_ip_init_net, + .exit = l2tp_ip_exit_net, + .id = &l2tp_ip_net_id, + .size = sizeof(struct l2tp_ip_net), +}; + static int __init l2tp_ip_init(void) { int err; pr_info("L2TP IP encapsulation support (L2TPv3)\n"); + err = register_pernet_device(&l2tp_ip_net_ops); + if (err) + goto out; + err = proto_register(&l2tp_ip_prot, 1); if (err != 0) - goto out; + goto out1; err = inet_add_protocol(&l2tp_ip_protocol, IPPROTO_L2TP); if (err) - goto out1; + goto out2; inet_register_protosw(&l2tp_ip_protosw); return 0; -out1: +out2: proto_unregister(&l2tp_ip_prot); +out1: + unregister_pernet_device(&l2tp_ip_net_ops); out: return err; } @@ -665,6 +723,7 @@ static void __exit l2tp_ip_exit(void) inet_unregister_protosw(&l2tp_ip_protosw); inet_del_protocol(&l2tp_ip_protocol, IPPROTO_L2TP); proto_unregister(&l2tp_ip_prot); + unregister_pernet_device(&l2tp_ip_net_ops); } module_init(l2tp_ip_init); diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index d217ff1f229e..f4c1da070826 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -22,6 +22,8 @@ #include <net/tcp_states.h> #include <net/protocol.h> #include <net/xfrm.h> +#include <net/net_namespace.h> +#include <net/netns/generic.h> #include <net/transp_v6.h> #include <net/addrconf.h> @@ -29,6 +31,14 @@ #include "l2tp_core.h" +/* per-net private data for this module */ +static unsigned int l2tp_ip6_net_id; +struct l2tp_ip6_net { + rwlock_t l2tp_ip6_lock; + struct hlist_head l2tp_ip6_table; + struct hlist_head l2tp_ip6_bind_table; +}; + struct l2tp_ip6_sock { /* inet_sock has to be the first member of l2tp_ip6_sock */ struct inet_sock inet; @@ -39,23 +49,25 @@ struct l2tp_ip6_sock { struct ipv6_pinfo inet6; }; -static DEFINE_RWLOCK(l2tp_ip6_lock); -static struct hlist_head l2tp_ip6_table; -static struct hlist_head l2tp_ip6_bind_table; - -static inline struct l2tp_ip6_sock *l2tp_ip6_sk(const struct sock *sk) +static struct l2tp_ip6_sock *l2tp_ip6_sk(const struct sock *sk) { return (struct l2tp_ip6_sock *)sk; } +static struct l2tp_ip6_net *l2tp_ip6_pernet(const struct net *net) +{ + return net_generic(net, l2tp_ip6_net_id); +} + static struct sock *__l2tp_ip6_bind_lookup(const struct net *net, const struct in6_addr *laddr, const struct in6_addr *raddr, int dif, u32 tunnel_id) { + struct l2tp_ip6_net *pn = l2tp_ip6_pernet(net); struct sock *sk; - sk_for_each_bound(sk, &l2tp_ip6_bind_table) { + sk_for_each_bound(sk, &pn->l2tp_ip6_bind_table) { const struct in6_addr *sk_laddr = inet6_rcv_saddr(sk); const struct in6_addr *sk_raddr = &sk->sk_v6_daddr; const struct l2tp_ip6_sock *l2tp = l2tp_ip6_sk(sk); @@ -123,6 +135,7 @@ found: static int l2tp_ip6_recv(struct sk_buff *skb) { struct net *net = dev_net(skb->dev); + struct l2tp_ip6_net *pn; struct sock *sk; u32 session_id; u32 tunnel_id; @@ -131,6 +144,8 @@ static int l2tp_ip6_recv(struct sk_buff *skb) struct l2tp_tunnel *tunnel = NULL; struct ipv6hdr *iph; + pn = l2tp_ip6_pernet(net); + if (!pskb_may_pull(skb, 4)) goto discard; @@ -162,7 +177,7 @@ static int l2tp_ip6_recv(struct sk_buff *skb) goto discard_sess; l2tp_recv_common(session, skb, ptr, optr, 0, skb->len); - l2tp_session_dec_refcount(session); + l2tp_session_put(session); return 0; @@ -177,15 +192,15 @@ pass_up: tunnel_id = ntohl(*(__be32 *)&skb->data[4]); iph = ipv6_hdr(skb); - read_lock_bh(&l2tp_ip6_lock); + read_lock_bh(&pn->l2tp_ip6_lock); sk = __l2tp_ip6_bind_lookup(net, &iph->daddr, &iph->saddr, inet6_iif(skb), tunnel_id); if (!sk) { - read_unlock_bh(&l2tp_ip6_lock); + read_unlock_bh(&pn->l2tp_ip6_lock); goto discard; } sock_hold(sk); - read_unlock_bh(&l2tp_ip6_lock); + read_unlock_bh(&pn->l2tp_ip6_lock); if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_put; @@ -195,7 +210,7 @@ pass_up: return sk_receive_skb(sk, skb, 1); discard_sess: - l2tp_session_dec_refcount(session); + l2tp_session_put(session); goto discard; discard_put: @@ -208,21 +223,25 @@ discard: static int l2tp_ip6_hash(struct sock *sk) { + struct l2tp_ip6_net *pn = l2tp_ip6_pernet(sock_net(sk)); + if (sk_unhashed(sk)) { - write_lock_bh(&l2tp_ip6_lock); - sk_add_node(sk, &l2tp_ip6_table); - write_unlock_bh(&l2tp_ip6_lock); + write_lock_bh(&pn->l2tp_ip6_lock); + sk_add_node(sk, &pn->l2tp_ip6_table); + write_unlock_bh(&pn->l2tp_ip6_lock); } return 0; } static void l2tp_ip6_unhash(struct sock *sk) { + struct l2tp_ip6_net *pn = l2tp_ip6_pernet(sock_net(sk)); + if (sk_unhashed(sk)) return; - write_lock_bh(&l2tp_ip6_lock); + write_lock_bh(&pn->l2tp_ip6_lock); sk_del_node_init(sk); - write_unlock_bh(&l2tp_ip6_lock); + write_unlock_bh(&pn->l2tp_ip6_lock); } static int l2tp_ip6_open(struct sock *sk) @@ -236,24 +255,29 @@ static int l2tp_ip6_open(struct sock *sk) static void l2tp_ip6_close(struct sock *sk, long timeout) { - write_lock_bh(&l2tp_ip6_lock); + struct l2tp_ip6_net *pn = l2tp_ip6_pernet(sock_net(sk)); + + write_lock_bh(&pn->l2tp_ip6_lock); hlist_del_init(&sk->sk_bind_node); sk_del_node_init(sk); - write_unlock_bh(&l2tp_ip6_lock); + write_unlock_bh(&pn->l2tp_ip6_lock); sk_common_release(sk); } static void l2tp_ip6_destroy_sock(struct sock *sk) { - struct l2tp_tunnel *tunnel = l2tp_sk_to_tunnel(sk); + struct l2tp_tunnel *tunnel; lock_sock(sk); ip6_flush_pending_frames(sk); release_sock(sk); - if (tunnel) + tunnel = l2tp_sk_to_tunnel(sk); + if (tunnel) { l2tp_tunnel_delete(tunnel); + l2tp_tunnel_put(tunnel); + } } static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) @@ -262,11 +286,14 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) struct ipv6_pinfo *np = inet6_sk(sk); struct sockaddr_l2tpip6 *addr = (struct sockaddr_l2tpip6 *)uaddr; struct net *net = sock_net(sk); + struct l2tp_ip6_net *pn; __be32 v4addr = 0; int bound_dev_if; int addr_type; int err; + pn = l2tp_ip6_pernet(net); + if (addr->l2tp_family != AF_INET6) return -EINVAL; if (addr_len < sizeof(*addr)) @@ -324,10 +351,10 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) } rcu_read_unlock(); - write_lock_bh(&l2tp_ip6_lock); + write_lock_bh(&pn->l2tp_ip6_lock); if (__l2tp_ip6_bind_lookup(net, &addr->l2tp_addr, NULL, bound_dev_if, addr->l2tp_conn_id)) { - write_unlock_bh(&l2tp_ip6_lock); + write_unlock_bh(&pn->l2tp_ip6_lock); err = -EADDRINUSE; goto out_unlock; } @@ -340,9 +367,9 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) l2tp_ip6_sk(sk)->conn_id = addr->l2tp_conn_id; - sk_add_bind_node(sk, &l2tp_ip6_bind_table); + sk_add_bind_node(sk, &pn->l2tp_ip6_bind_table); sk_del_node_init(sk); - write_unlock_bh(&l2tp_ip6_lock); + write_unlock_bh(&pn->l2tp_ip6_lock); sock_reset_flag(sk, SOCK_ZAPPED); release_sock(sk); @@ -364,6 +391,7 @@ static int l2tp_ip6_connect(struct sock *sk, struct sockaddr *uaddr, struct in6_addr *daddr; int addr_type; int rc; + struct l2tp_ip6_net *pn; if (addr_len < sizeof(*lsa)) return -EINVAL; @@ -395,10 +423,11 @@ static int l2tp_ip6_connect(struct sock *sk, struct sockaddr *uaddr, l2tp_ip6_sk(sk)->peer_conn_id = lsa->l2tp_conn_id; - write_lock_bh(&l2tp_ip6_lock); + pn = l2tp_ip6_pernet(sock_net(sk)); + write_lock_bh(&pn->l2tp_ip6_lock); hlist_del_init(&sk->sk_bind_node); - sk_add_bind_node(sk, &l2tp_ip6_bind_table); - write_unlock_bh(&l2tp_ip6_lock); + sk_add_bind_node(sk, &pn->l2tp_ip6_bind_table); + write_unlock_bh(&pn->l2tp_ip6_lock); out_sk: release_sock(sk); @@ -765,25 +794,58 @@ static struct inet6_protocol l2tp_ip6_protocol __read_mostly = { .handler = l2tp_ip6_recv, }; +static __net_init int l2tp_ip6_init_net(struct net *net) +{ + struct l2tp_ip6_net *pn = net_generic(net, l2tp_ip6_net_id); + + rwlock_init(&pn->l2tp_ip6_lock); + INIT_HLIST_HEAD(&pn->l2tp_ip6_table); + INIT_HLIST_HEAD(&pn->l2tp_ip6_bind_table); + return 0; +} + +static __net_exit void l2tp_ip6_exit_net(struct net *net) +{ + struct l2tp_ip6_net *pn = l2tp_ip6_pernet(net); + + write_lock_bh(&pn->l2tp_ip6_lock); + WARN_ON_ONCE(hlist_count_nodes(&pn->l2tp_ip6_table) != 0); + WARN_ON_ONCE(hlist_count_nodes(&pn->l2tp_ip6_bind_table) != 0); + write_unlock_bh(&pn->l2tp_ip6_lock); +} + +static struct pernet_operations l2tp_ip6_net_ops = { + .init = l2tp_ip6_init_net, + .exit = l2tp_ip6_exit_net, + .id = &l2tp_ip6_net_id, + .size = sizeof(struct l2tp_ip6_net), +}; + static int __init l2tp_ip6_init(void) { int err; pr_info("L2TP IP encapsulation support for IPv6 (L2TPv3)\n"); + err = register_pernet_device(&l2tp_ip6_net_ops); + if (err) + goto out; + err = proto_register(&l2tp_ip6_prot, 1); if (err != 0) - goto out; + goto out1; err = inet6_add_protocol(&l2tp_ip6_protocol, IPPROTO_L2TP); if (err) - goto out1; + goto out2; inet6_register_protosw(&l2tp_ip6_protosw); return 0; -out1: +out2: proto_unregister(&l2tp_ip6_prot); +out1: + unregister_pernet_device(&l2tp_ip6_net_ops); out: return err; } @@ -793,6 +855,7 @@ static void __exit l2tp_ip6_exit(void) inet6_unregister_protosw(&l2tp_ip6_protosw); inet6_del_protocol(&l2tp_ip6_protocol, IPPROTO_L2TP); proto_unregister(&l2tp_ip6_prot); + unregister_pernet_device(&l2tp_ip6_net_ops); } module_init(l2tp_ip6_init); diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index d105030520f9..284f1dec1b56 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -63,7 +63,7 @@ static struct l2tp_session *l2tp_nl_session_get(struct genl_info *info) if (tunnel) { session = l2tp_session_get(net, tunnel->sock, tunnel->version, tunnel_id, session_id); - l2tp_tunnel_dec_refcount(tunnel); + l2tp_tunnel_put(tunnel); } } @@ -242,7 +242,7 @@ static int l2tp_nl_cmd_tunnel_create(struct sk_buff *skb, struct genl_info *info if (ret < 0) goto out; - l2tp_tunnel_inc_refcount(tunnel); + refcount_inc(&tunnel->ref_count); ret = l2tp_tunnel_register(tunnel, net, &cfg); if (ret < 0) { kfree(tunnel); @@ -250,7 +250,7 @@ static int l2tp_nl_cmd_tunnel_create(struct sk_buff *skb, struct genl_info *info } ret = l2tp_tunnel_notify(&l2tp_nl_family, info, tunnel, L2TP_CMD_TUNNEL_CREATE); - l2tp_tunnel_dec_refcount(tunnel); + l2tp_tunnel_put(tunnel); out: return ret; @@ -280,7 +280,7 @@ static int l2tp_nl_cmd_tunnel_delete(struct sk_buff *skb, struct genl_info *info l2tp_tunnel_delete(tunnel); - l2tp_tunnel_dec_refcount(tunnel); + l2tp_tunnel_put(tunnel); out: return ret; @@ -308,7 +308,7 @@ static int l2tp_nl_cmd_tunnel_modify(struct sk_buff *skb, struct genl_info *info ret = l2tp_tunnel_notify(&l2tp_nl_family, info, tunnel, L2TP_CMD_TUNNEL_MODIFY); - l2tp_tunnel_dec_refcount(tunnel); + l2tp_tunnel_put(tunnel); out: return ret; @@ -479,42 +479,48 @@ static int l2tp_nl_cmd_tunnel_get(struct sk_buff *skb, struct genl_info *info) if (ret < 0) goto err_nlmsg_tunnel; - l2tp_tunnel_dec_refcount(tunnel); + l2tp_tunnel_put(tunnel); return genlmsg_unicast(net, msg, info->snd_portid); err_nlmsg_tunnel: - l2tp_tunnel_dec_refcount(tunnel); + l2tp_tunnel_put(tunnel); err_nlmsg: nlmsg_free(msg); err: return ret; } +struct l2tp_nl_cb_data { + unsigned long tkey; + unsigned long skey; +}; + static int l2tp_nl_cmd_tunnel_dump(struct sk_buff *skb, struct netlink_callback *cb) { - int ti = cb->args[0]; + struct l2tp_nl_cb_data *cbd = (void *)&cb->ctx[0]; + unsigned long key = cbd->tkey; struct l2tp_tunnel *tunnel; struct net *net = sock_net(skb->sk); for (;;) { - tunnel = l2tp_tunnel_get_nth(net, ti); + tunnel = l2tp_tunnel_get_next(net, &key); if (!tunnel) goto out; if (l2tp_nl_tunnel_send(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, tunnel, L2TP_CMD_TUNNEL_GET) < 0) { - l2tp_tunnel_dec_refcount(tunnel); + l2tp_tunnel_put(tunnel); goto out; } - l2tp_tunnel_dec_refcount(tunnel); + l2tp_tunnel_put(tunnel); - ti++; + key++; } out: - cb->args[0] = ti; + cbd->tkey = key; return skb->len; } @@ -641,12 +647,12 @@ static int l2tp_nl_cmd_session_create(struct sk_buff *skb, struct genl_info *inf if (session) { ret = l2tp_session_notify(&l2tp_nl_family, info, session, L2TP_CMD_SESSION_CREATE); - l2tp_session_dec_refcount(session); + l2tp_session_put(session); } } out_tunnel: - l2tp_tunnel_dec_refcount(tunnel); + l2tp_tunnel_put(tunnel); out: return ret; } @@ -671,7 +677,7 @@ static int l2tp_nl_cmd_session_delete(struct sk_buff *skb, struct genl_info *inf if (l2tp_nl_cmd_ops[pw_type] && l2tp_nl_cmd_ops[pw_type]->session_delete) l2tp_nl_cmd_ops[pw_type]->session_delete(session); - l2tp_session_dec_refcount(session); + l2tp_session_put(session); out: return ret; @@ -692,8 +698,10 @@ static int l2tp_nl_cmd_session_modify(struct sk_buff *skb, struct genl_info *inf session->recv_seq = nla_get_u8(info->attrs[L2TP_ATTR_RECV_SEQ]); if (info->attrs[L2TP_ATTR_SEND_SEQ]) { + struct l2tp_tunnel *tunnel = session->tunnel; + session->send_seq = nla_get_u8(info->attrs[L2TP_ATTR_SEND_SEQ]); - l2tp_session_set_header_len(session, session->tunnel->version); + l2tp_session_set_header_len(session, tunnel->version, tunnel->encap); } if (info->attrs[L2TP_ATTR_LNS_MODE]) @@ -705,7 +713,7 @@ static int l2tp_nl_cmd_session_modify(struct sk_buff *skb, struct genl_info *inf ret = l2tp_session_notify(&l2tp_nl_family, info, session, L2TP_CMD_SESSION_MODIFY); - l2tp_session_dec_refcount(session); + l2tp_session_put(session); out: return ret; @@ -816,57 +824,59 @@ static int l2tp_nl_cmd_session_get(struct sk_buff *skb, struct genl_info *info) ret = genlmsg_unicast(genl_info_net(info), msg, info->snd_portid); - l2tp_session_dec_refcount(session); + l2tp_session_put(session); return ret; err_ref_msg: nlmsg_free(msg); err_ref: - l2tp_session_dec_refcount(session); + l2tp_session_put(session); err: return ret; } static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback *cb) { + struct l2tp_nl_cb_data *cbd = (void *)&cb->ctx[0]; struct net *net = sock_net(skb->sk); struct l2tp_session *session; struct l2tp_tunnel *tunnel = NULL; - int ti = cb->args[0]; - int si = cb->args[1]; + unsigned long tkey = cbd->tkey; + unsigned long skey = cbd->skey; for (;;) { if (!tunnel) { - tunnel = l2tp_tunnel_get_nth(net, ti); + tunnel = l2tp_tunnel_get_next(net, &tkey); if (!tunnel) goto out; } - session = l2tp_session_get_nth(tunnel, si); + session = l2tp_session_get_next(net, tunnel->sock, tunnel->version, + tunnel->tunnel_id, &skey); if (!session) { - ti++; - l2tp_tunnel_dec_refcount(tunnel); + tkey++; + l2tp_tunnel_put(tunnel); tunnel = NULL; - si = 0; + skey = 0; continue; } if (l2tp_nl_session_send(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, session, L2TP_CMD_SESSION_GET) < 0) { - l2tp_session_dec_refcount(session); - l2tp_tunnel_dec_refcount(tunnel); + l2tp_session_put(session); + l2tp_tunnel_put(tunnel); break; } - l2tp_session_dec_refcount(session); + l2tp_session_put(session); - si++; + skey++; } out: - cb->args[0] = ti; - cb->args[1] = si; + cbd->tkey = tkey; + cbd->skey = skey; return skb->len; } diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 3596290047b2..53baf2dd5d5d 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -119,7 +119,6 @@ struct pppol2tp_session { struct mutex sk_lock; /* Protects .sk */ struct sock __rcu *sk; /* Pointer to the session PPPoX socket */ struct sock *__sk; /* Copy of .sk, for cleanup */ - struct rcu_head rcu; /* For asynchronous release */ }; static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb); @@ -150,27 +149,23 @@ static struct sock *pppol2tp_session_get_sock(struct l2tp_session *session) /* Helpers to obtain tunnel/session contexts from sockets. */ -static inline struct l2tp_session *pppol2tp_sock_to_session(struct sock *sk) +static struct l2tp_session *pppol2tp_sock_to_session(struct sock *sk) { struct l2tp_session *session; if (!sk) return NULL; - sock_hold(sk); - session = (struct l2tp_session *)(sk->sk_user_data); - if (!session) { - sock_put(sk); - goto out; - } - if (WARN_ON(session->magic != L2TP_SESSION_MAGIC)) { - session = NULL; - sock_put(sk); - goto out; + rcu_read_lock(); + session = rcu_dereference_sk_user_data(sk); + if (session && refcount_inc_not_zero(&session->ref_count)) { + rcu_read_unlock(); + WARN_ON_ONCE(session->magic != L2TP_SESSION_MAGIC); + return session; } + rcu_read_unlock(); -out: - return session; + return NULL; } /***************************************************************************** @@ -318,12 +313,12 @@ static int pppol2tp_sendmsg(struct socket *sock, struct msghdr *m, l2tp_xmit_skb(session, skb); local_bh_enable(); - sock_put(sk); + l2tp_session_put(session); return total_len; error_put_sess: - sock_put(sk); + l2tp_session_put(session); error: return error; } @@ -377,12 +372,12 @@ static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb) l2tp_xmit_skb(session, skb); local_bh_enable(); - sock_put(sk); + l2tp_session_put(session); return 1; abort_put_sess: - sock_put(sk); + l2tp_session_put(session); abort: /* Free the original skb */ kfree_skb(skb); @@ -393,29 +388,32 @@ abort: * Session (and tunnel control) socket create/destroy. *****************************************************************************/ -static void pppol2tp_put_sk(struct rcu_head *head) -{ - struct pppol2tp_session *ps; - - ps = container_of(head, typeof(*ps), rcu); - sock_put(ps->__sk); -} - /* Really kill the session socket. (Called from sock_put() if * refcnt == 0.) */ static void pppol2tp_session_destruct(struct sock *sk) { - struct l2tp_session *session = sk->sk_user_data; - skb_queue_purge(&sk->sk_receive_queue); skb_queue_purge(&sk->sk_write_queue); +} - if (session) { - sk->sk_user_data = NULL; - if (WARN_ON(session->magic != L2TP_SESSION_MAGIC)) - return; - l2tp_session_dec_refcount(session); +static void pppol2tp_session_close(struct l2tp_session *session) +{ + struct pppol2tp_session *ps; + + ps = l2tp_session_priv(session); + mutex_lock(&ps->sk_lock); + ps->__sk = rcu_dereference_protected(ps->sk, + lockdep_is_held(&ps->sk_lock)); + RCU_INIT_POINTER(ps->sk, NULL); + mutex_unlock(&ps->sk_lock); + if (ps->__sk) { + /* detach socket */ + rcu_assign_sk_user_data(ps->__sk, NULL); + sock_put(ps->__sk); + + /* drop ref taken when we referenced socket via sk_user_data */ + l2tp_session_put(session); } } @@ -444,30 +442,13 @@ static int pppol2tp_release(struct socket *sock) session = pppol2tp_sock_to_session(sk); if (session) { - struct pppol2tp_session *ps; - l2tp_session_delete(session); - - ps = l2tp_session_priv(session); - mutex_lock(&ps->sk_lock); - ps->__sk = rcu_dereference_protected(ps->sk, - lockdep_is_held(&ps->sk_lock)); - RCU_INIT_POINTER(ps->sk, NULL); - mutex_unlock(&ps->sk_lock); - call_rcu(&ps->rcu, pppol2tp_put_sk); - - /* Rely on the sock_put() call at the end of the function for - * dropping the reference held by pppol2tp_sock_to_session(). - * The last reference will be dropped by pppol2tp_put_sk(). - */ + /* drop ref taken by pppol2tp_sock_to_session */ + l2tp_session_put(session); } release_sock(sk); - /* This will delete the session context via - * pppol2tp_session_destruct() if the socket's refcnt drops to - * zero. - */ sock_put(sk); return 0; @@ -506,6 +487,7 @@ static int pppol2tp_create(struct net *net, struct socket *sock, int kern) goto out; sock_init_data(sock, sk); + sock_set_flag(sk, SOCK_RCU_FREE); sock->state = SS_UNCONNECTED; sock->ops = &pppol2tp_ops; @@ -542,6 +524,7 @@ static void pppol2tp_session_init(struct l2tp_session *session) struct pppol2tp_session *ps; session->recv_skb = pppol2tp_recv; + session->session_close = pppol2tp_session_close; if (IS_ENABLED(CONFIG_L2TP_DEBUGFS)) session->show = pppol2tp_show; @@ -685,7 +668,7 @@ static struct l2tp_tunnel *pppol2tp_tunnel_get(struct net *net, if (error < 0) return ERR_PTR(error); - l2tp_tunnel_inc_refcount(tunnel); + refcount_inc(&tunnel->ref_count); error = l2tp_tunnel_register(tunnel, net, &tcfg); if (error < 0) { kfree(tunnel); @@ -701,7 +684,7 @@ static struct l2tp_tunnel *pppol2tp_tunnel_get(struct net *net, /* Error if socket is not prepped */ if (!tunnel->sock) { - l2tp_tunnel_dec_refcount(tunnel); + l2tp_tunnel_put(tunnel); return ERR_PTR(-ENOENT); } } @@ -787,18 +770,20 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, goto end; } + drop_refcnt = true; + pppol2tp_session_init(session); ps = l2tp_session_priv(session); - l2tp_session_inc_refcount(session); + refcount_inc(&session->ref_count); mutex_lock(&ps->sk_lock); error = l2tp_session_register(session, tunnel); if (error < 0) { mutex_unlock(&ps->sk_lock); - kfree(session); + l2tp_session_put(session); goto end; } - drop_refcnt = true; + new_session = true; } @@ -830,12 +815,13 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, out_no_ppp: /* This is how we get the session context from the socket. */ - sk->sk_user_data = session; + sock_hold(sk); + rcu_assign_sk_user_data(sk, session); rcu_assign_pointer(ps->sk, sk); mutex_unlock(&ps->sk_lock); /* Keep the reference we've grabbed on the session: sk doesn't expect - * the session to disappear. pppol2tp_session_destruct() is responsible + * the session to disappear. pppol2tp_session_close() is responsible * for dropping it. */ drop_refcnt = false; @@ -850,8 +836,8 @@ end: l2tp_tunnel_delete(tunnel); } if (drop_refcnt) - l2tp_session_dec_refcount(session); - l2tp_tunnel_dec_refcount(tunnel); + l2tp_session_put(session); + l2tp_tunnel_put(tunnel); release_sock(sk); return error; @@ -891,7 +877,7 @@ static int pppol2tp_session_create(struct net *net, struct l2tp_tunnel *tunnel, return 0; err_sess: - kfree(session); + l2tp_session_put(session); err: return error; } @@ -1002,7 +988,7 @@ static int pppol2tp_getname(struct socket *sock, struct sockaddr *uaddr, error = len; - sock_put(sk); + l2tp_session_put(session); end: return error; } @@ -1052,12 +1038,12 @@ static int pppol2tp_tunnel_copy_stats(struct pppol2tp_ioc_stats *stats, return -EBADR; if (session->pwtype != L2TP_PWTYPE_PPP) { - l2tp_session_dec_refcount(session); + l2tp_session_put(session); return -EBADR; } pppol2tp_copy_stats(stats, &session->stats); - l2tp_session_dec_refcount(session); + l2tp_session_put(session); return 0; } @@ -1205,7 +1191,8 @@ static int pppol2tp_session_setsockopt(struct sock *sk, po->chan.hdrlen = val ? PPPOL2TP_L2TP_HDR_SIZE_SEQ : PPPOL2TP_L2TP_HDR_SIZE_NOSEQ; } - l2tp_session_set_header_len(session, session->tunnel->version); + l2tp_session_set_header_len(session, session->tunnel->version, + session->tunnel->encap); break; case PPPOL2TP_SO_LNSMODE: @@ -1274,7 +1261,7 @@ static int pppol2tp_setsockopt(struct socket *sock, int level, int optname, err = pppol2tp_session_setsockopt(sk, session, optname, val); } - sock_put(sk); + l2tp_session_put(session); end: return err; } @@ -1395,7 +1382,7 @@ static int pppol2tp_getsockopt(struct socket *sock, int level, int optname, err = 0; end_put_sess: - sock_put(sk); + l2tp_session_put(session); end: return err; } @@ -1406,14 +1393,12 @@ end: * L2TPv2, we dump only L2TPv2 tunnels and sessions here. *****************************************************************************/ -static unsigned int pppol2tp_net_id; - #ifdef CONFIG_PROC_FS struct pppol2tp_seq_data { struct seq_net_private p; - int tunnel_idx; /* current tunnel */ - int session_idx; /* index of session within current tunnel */ + unsigned long tkey; /* lookup key of current tunnel */ + unsigned long skey; /* lookup key of current session */ struct l2tp_tunnel *tunnel; struct l2tp_session *session; /* NULL means get next tunnel */ }; @@ -1422,17 +1407,17 @@ static void pppol2tp_next_tunnel(struct net *net, struct pppol2tp_seq_data *pd) { /* Drop reference taken during previous invocation */ if (pd->tunnel) - l2tp_tunnel_dec_refcount(pd->tunnel); + l2tp_tunnel_put(pd->tunnel); for (;;) { - pd->tunnel = l2tp_tunnel_get_nth(net, pd->tunnel_idx); - pd->tunnel_idx++; + pd->tunnel = l2tp_tunnel_get_next(net, &pd->tkey); + pd->tkey++; /* Only accept L2TPv2 tunnels */ if (!pd->tunnel || pd->tunnel->version == 2) return; - l2tp_tunnel_dec_refcount(pd->tunnel); + l2tp_tunnel_put(pd->tunnel); } } @@ -1440,13 +1425,15 @@ static void pppol2tp_next_session(struct net *net, struct pppol2tp_seq_data *pd) { /* Drop reference taken during previous invocation */ if (pd->session) - l2tp_session_dec_refcount(pd->session); + l2tp_session_put(pd->session); - pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx); - pd->session_idx++; + pd->session = l2tp_session_get_next(net, pd->tunnel->sock, + pd->tunnel->version, + pd->tunnel->tunnel_id, &pd->skey); + pd->skey++; if (!pd->session) { - pd->session_idx = 0; + pd->skey = 0; pppol2tp_next_tunnel(net, pd); } } @@ -1498,11 +1485,11 @@ static void pppol2tp_seq_stop(struct seq_file *p, void *v) * or pppol2tp_next_tunnel(). */ if (pd->session) { - l2tp_session_dec_refcount(pd->session); + l2tp_session_put(pd->session); pd->session = NULL; } if (pd->tunnel) { - l2tp_tunnel_dec_refcount(pd->tunnel); + l2tp_tunnel_put(pd->tunnel); pd->tunnel = NULL; } } @@ -1513,7 +1500,7 @@ static void pppol2tp_seq_tunnel_show(struct seq_file *m, void *v) seq_printf(m, "\nTUNNEL '%s', %c %d\n", tunnel->name, - (tunnel == tunnel->sock->sk_user_data) ? 'Y' : 'N', + tunnel->sock ? 'Y' : 'N', refcount_read(&tunnel->ref_count) - 1); seq_printf(m, " %08x %ld/%ld/%ld %ld/%ld/%ld\n", 0, @@ -1641,7 +1628,6 @@ static __net_exit void pppol2tp_exit_net(struct net *net) static struct pernet_operations pppol2tp_net_ops = { .init = pppol2tp_init_net, .exit = pppol2tp_exit_net, - .id = &pppol2tp_net_id, }; /***************************************************************************** diff --git a/net/mctp/af_mctp.c b/net/mctp/af_mctp.c index de52a9191da0..43288b408fde 100644 --- a/net/mctp/af_mctp.c +++ b/net/mctp/af_mctp.c @@ -486,6 +486,9 @@ static int mctp_ioctl_droptag(struct mctp_sock *msk, bool tagv2, tag = ctl.tag & MCTP_TAG_MASK; rc = -EINVAL; + if (ctl.peer_addr == MCTP_ADDR_NULL) + ctl.peer_addr = MCTP_ADDR_ANY; + spin_lock_irqsave(&net->mctp.keys_lock, flags); hlist_for_each_entry_safe(key, tmp, &msk->keys, sklist) { /* we do an irqsave here, even though we know the irq state, diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 0e6c94a8c2bc..aba983531ed3 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -1201,8 +1201,7 @@ static void mpls_netconf_notify_devconf(struct net *net, int event, rtnl_notify(skb, net, 0, RTNLGRP_MPLS_NETCONF, NULL, GFP_KERNEL); return; errout: - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_MPLS_NETCONF, err); + rtnl_set_sk_err(net, RTNLGRP_MPLS_NETCONF, err); } static const struct nla_policy devconf_mpls_policy[NETCONFA_MAX + 1] = { @@ -2278,8 +2277,7 @@ static void rtmsg_lfib(int event, u32 label, struct mpls_route *rt, return; errout: - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_MPLS_ROUTE, err); + rtnl_set_sk_err(net, RTNLGRP_MPLS_ROUTE, err); } static int mpls_valid_getroute_req(struct sk_buff *skb, diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c index 4385fd3b13be..6e73da94af7f 100644 --- a/net/mpls/mpls_iptunnel.c +++ b/net/mpls/mpls_iptunnel.c @@ -106,7 +106,7 @@ static int mpls_xmit(struct sk_buff *skb) hh_len = 0; /* Ensure there is enough space for the headers in the skb */ - if (skb_cow(skb, hh_len + new_header_size)) + if (skb_cow_head(skb, hh_len + new_header_size)) goto drop; skb_set_inner_protocol(skb, skb->protocol); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 3b22313d1b86..3735b20f2626 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -1154,7 +1154,6 @@ static inline void mptcp_pm_close_subflow(struct mptcp_sock *msk) spin_unlock_bh(&msk->pm.lock); } -void mptcp_sockopt_sync(struct mptcp_sock *msk, struct sock *ssk); void mptcp_sockopt_sync_locked(struct mptcp_sock *msk, struct sock *ssk); static inline struct mptcp_ext *mptcp_get_ext(const struct sk_buff *skb) diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c index 34ba14e59e95..4890af4dc263 100644 --- a/net/netfilter/nf_conncount.c +++ b/net/netfilter/nf_conncount.c @@ -522,11 +522,10 @@ unsigned int nf_conncount_count(struct net *net, } EXPORT_SYMBOL_GPL(nf_conncount_count); -struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int family, - unsigned int keylen) +struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int keylen) { struct nf_conncount_data *data; - int ret, i; + int i; if (keylen % sizeof(u32) || keylen / sizeof(u32) > MAX_KEYLEN || @@ -539,12 +538,6 @@ struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int family if (!data) return ERR_PTR(-ENOMEM); - ret = nf_ct_netns_get(net, family); - if (ret < 0) { - kfree(data); - return ERR_PTR(ret); - } - for (i = 0; i < ARRAY_SIZE(data->root); ++i) data->root[i] = RB_ROOT; @@ -581,13 +574,11 @@ static void destroy_tree(struct rb_root *r) } } -void nf_conncount_destroy(struct net *net, unsigned int family, - struct nf_conncount_data *data) +void nf_conncount_destroy(struct net *net, struct nf_conncount_data *data) { unsigned int i; cancel_work_sync(&data->gc_work); - nf_ct_netns_put(net, family); for (i = 0; i < ARRAY_SIZE(data->root); ++i) destroy_tree(&data->root[i]); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 0a2f79346958..904f2e25b4a4 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -146,6 +146,8 @@ static void nft_ctx_init(struct nft_ctx *ctx, ctx->report = nlmsg_report(nlh); ctx->flags = nlh->nlmsg_flags; ctx->seq = nlh->nlmsg_seq; + + bitmap_zero(ctx->reg_inited, NFT_REG32_NUM); } static struct nft_trans *nft_trans_alloc_gfp(const struct nft_ctx *ctx, @@ -393,6 +395,7 @@ static void nft_trans_commit_list_add_tail(struct net *net, struct nft_trans *tr { struct nftables_pernet *nft_net = nft_pernet(net); struct nft_trans_binding *binding; + struct nft_trans_set *trans_set; list_add_tail(&trans->list, &nft_net->commit_list); @@ -402,9 +405,13 @@ static void nft_trans_commit_list_add_tail(struct net *net, struct nft_trans *tr switch (trans->msg_type) { case NFT_MSG_NEWSET: + trans_set = nft_trans_container_set(trans); + if (!nft_trans_set_update(trans) && nft_set_is_anonymous(nft_trans_set(trans))) list_add_tail(&binding->binding_list, &nft_net->binding_list); + + list_add_tail(&trans_set->list_trans_newset, &nft_net->commit_set_list); break; case NFT_MSG_NEWCHAIN: if (!nft_trans_chain_update(trans) && @@ -611,6 +618,7 @@ static int __nft_trans_set_add(const struct nft_ctx *ctx, int msg_type, trans_set = nft_trans_container_set(trans); INIT_LIST_HEAD(&trans_set->nft_trans_binding.binding_list); + INIT_LIST_HEAD(&trans_set->list_trans_newset); if (msg_type == NFT_MSG_NEWSET && ctx->nla[NFTA_SET_ID] && !desc) { nft_trans_set_id(trans) = @@ -4485,17 +4493,16 @@ static struct nft_set *nft_set_lookup_byid(const struct net *net, { struct nftables_pernet *nft_net = nft_pernet(net); u32 id = ntohl(nla_get_be32(nla)); - struct nft_trans *trans; + struct nft_trans_set *trans; - list_for_each_entry(trans, &nft_net->commit_list, list) { - if (trans->msg_type == NFT_MSG_NEWSET) { - struct nft_set *set = nft_trans_set(trans); + /* its likely the id we need is at the tail, not at start */ + list_for_each_entry_reverse(trans, &nft_net->commit_set_list, list_trans_newset) { + struct nft_set *set = trans->set; - if (id == nft_trans_set_id(trans) && - set->table == table && - nft_active_genmask(set, genmask)) - return set; - } + if (id == trans->set_id && + set->table == table && + nft_active_genmask(set, genmask)) + return set; } return ERR_PTR(-ENOENT); } @@ -10447,6 +10454,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nft_flow_rule_destroy(nft_trans_flow_rule(trans)); break; case NFT_MSG_NEWSET: + list_del(&nft_trans_container_set(trans)->list_trans_newset); if (nft_trans_set_update(trans)) { struct nft_set *set = nft_trans_set(trans); @@ -10755,6 +10763,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_trans_destroy(trans); break; case NFT_MSG_NEWSET: + list_del(&nft_trans_container_set(trans)->list_trans_newset); if (nft_trans_set_update(trans)) { nft_trans_destroy(trans); break; @@ -10782,7 +10791,10 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) break; } te = nft_trans_container_elem(trans); - nft_setelem_remove(net, te->set, te->elem_priv); + if (!te->set->ops->abort || + nft_setelem_is_catchall(te->set, te->elem_priv)) + nft_setelem_remove(net, te->set, te->elem_priv); + if (!nft_setelem_is_catchall(te->set, te->elem_priv)) atomic_dec(&te->set->nelems); @@ -10850,6 +10862,8 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) } } + WARN_ON_ONCE(!list_empty(&nft_net->commit_set_list)); + nft_set_abort_update(&set_update_list); synchronize_rcu(); @@ -11026,10 +11040,11 @@ static int nft_validate_register_load(enum nft_registers reg, unsigned int len) return 0; } -int nft_parse_register_load(const struct nlattr *attr, u8 *sreg, u32 len) +int nft_parse_register_load(const struct nft_ctx *ctx, + const struct nlattr *attr, u8 *sreg, u32 len) { - u32 reg; - int err; + int err, invalid_reg; + u32 reg, next_register; err = nft_parse_register(attr, ®); if (err < 0) @@ -11039,11 +11054,36 @@ int nft_parse_register_load(const struct nlattr *attr, u8 *sreg, u32 len) if (err < 0) return err; + next_register = DIV_ROUND_UP(len, NFT_REG32_SIZE) + reg; + + /* Can't happen: nft_validate_register_load() should have failed */ + if (WARN_ON_ONCE(next_register > NFT_REG32_NUM)) + return -EINVAL; + + /* find first register that did not see an earlier store. */ + invalid_reg = find_next_zero_bit(ctx->reg_inited, NFT_REG32_NUM, reg); + + /* invalid register within the range that we're loading from? */ + if (invalid_reg < next_register) + return -ENODATA; + *sreg = reg; return 0; } EXPORT_SYMBOL_GPL(nft_parse_register_load); +static void nft_saw_register_store(const struct nft_ctx *__ctx, + int reg, unsigned int len) +{ + unsigned int registers = DIV_ROUND_UP(len, NFT_REG32_SIZE); + struct nft_ctx *ctx = (struct nft_ctx *)__ctx; + + if (WARN_ON_ONCE(len == 0 || reg < 0)) + return; + + bitmap_set(ctx->reg_inited, reg, registers); +} + static int nft_validate_register_store(const struct nft_ctx *ctx, enum nft_registers reg, const struct nft_data *data, @@ -11065,7 +11105,7 @@ static int nft_validate_register_store(const struct nft_ctx *ctx, return err; } - return 0; + break; default: if (type != NFT_DATA_VALUE) return -EINVAL; @@ -11078,8 +11118,11 @@ static int nft_validate_register_store(const struct nft_ctx *ctx, sizeof_field(struct nft_regs, data)) return -ERANGE; - return 0; + break; } + + nft_saw_register_store(ctx, reg, len); + return 0; } int nft_parse_register_store(const struct nft_ctx *ctx, @@ -11519,6 +11562,7 @@ static int __net_init nf_tables_init_net(struct net *net) INIT_LIST_HEAD(&nft_net->tables); INIT_LIST_HEAD(&nft_net->commit_list); + INIT_LIST_HEAD(&nft_net->commit_set_list); INIT_LIST_HEAD(&nft_net->binding_list); INIT_LIST_HEAD(&nft_net->module_list); INIT_LIST_HEAD(&nft_net->notify_list); @@ -11549,6 +11593,7 @@ static void __net_exit nf_tables_exit_net(struct net *net) gc_seq = nft_gc_seq_begin(nft_net); WARN_ON_ONCE(!list_empty(&nft_net->commit_list)); + WARN_ON_ONCE(!list_empty(&nft_net->commit_set_list)); if (!list_empty(&nft_net->module_list)) nf_tables_module_autoload_cleanup(net); diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index a48d5f0e2f3e..75598520b0fa 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -256,7 +256,7 @@ nft_do_chain(struct nft_pktinfo *pkt, void *priv) const struct net *net = nft_net(pkt); const struct nft_expr *expr, *last; const struct nft_rule_dp *rule; - struct nft_regs regs = {}; + struct nft_regs regs; unsigned int stackptr = 0; struct nft_jumpstack jumpstack[NFT_JUMP_STACK_SIZE]; bool genbit = READ_ONCE(net->nft.gencursor); diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 932b3ddb34f1..7784ec094097 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -402,27 +402,27 @@ replay_abort: { nfnl_unlock(subsys_id); netlink_ack(oskb, nlh, -EOPNOTSUPP, NULL); - return kfree_skb(skb); + return consume_skb(skb); } } if (!ss->valid_genid || !ss->commit || !ss->abort) { nfnl_unlock(subsys_id); netlink_ack(oskb, nlh, -EOPNOTSUPP, NULL); - return kfree_skb(skb); + return consume_skb(skb); } if (!try_module_get(ss->owner)) { nfnl_unlock(subsys_id); netlink_ack(oskb, nlh, -EOPNOTSUPP, NULL); - return kfree_skb(skb); + return consume_skb(skb); } if (!ss->valid_genid(net, genid)) { module_put(ss->owner); nfnl_unlock(subsys_id); netlink_ack(oskb, nlh, -ERESTART, NULL); - return kfree_skb(skb); + return consume_skb(skb); } nfnl_unlock(subsys_id); @@ -567,7 +567,7 @@ done: if (status & NFNL_BATCH_REPLAY) { ss->abort(net, oskb, NFNL_ABORT_AUTOLOAD); nfnl_err_reset(&err_list); - kfree_skb(skb); + consume_skb(skb); module_put(ss->owner); goto replay; } else if (status == NFNL_BATCH_DONE) { @@ -593,7 +593,7 @@ done: err = ss->abort(net, oskb, abort_action); if (err == -EAGAIN) { nfnl_err_reset(&err_list); - kfree_skb(skb); + consume_skb(skb); module_put(ss->owner); status |= NFNL_BATCH_FAILURE; goto replay_abort; @@ -601,7 +601,7 @@ done: } nfnl_err_deliver(&err_list, oskb); - kfree_skb(skb); + consume_skb(skb); module_put(ss->owner); } diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index e0716da256bf..d2773ce9b585 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -540,6 +540,14 @@ nla_put_failure: return -1; } +static int nf_queue_checksum_help(struct sk_buff *entskb) +{ + if (skb_csum_is_sctp(entskb)) + return skb_crc32c_csum_help(entskb); + + return skb_checksum_help(entskb); +} + static struct sk_buff * nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, struct nf_queue_entry *entry, @@ -602,7 +610,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, case NFQNL_COPY_PACKET: if (!(queue->flags & NFQA_CFG_F_GSO) && entskb->ip_summed == CHECKSUM_PARTIAL && - skb_checksum_help(entskb)) + nf_queue_checksum_help(entskb)) return NULL; data_len = READ_ONCE(queue->copy_range); @@ -1014,7 +1022,7 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) break; } - if ((queue->flags & NFQA_CFG_F_GSO) || !skb_is_gso(skb)) + if (!skb_is_gso(skb) || ((queue->flags & NFQA_CFG_F_GSO) && !skb_is_gso_sctp(skb))) return __nfqnl_enqueue_packet(net, queue, entry); nf_bridge_adjust_skb_data(skb); diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c index ca857afbf061..7de95674fd8c 100644 --- a/net/netfilter/nft_bitwise.c +++ b/net/netfilter/nft_bitwise.c @@ -171,7 +171,7 @@ static int nft_bitwise_init(const struct nft_ctx *ctx, priv->len = len; - err = nft_parse_register_load(tb[NFTA_BITWISE_SREG], &priv->sreg, + err = nft_parse_register_load(ctx, tb[NFTA_BITWISE_SREG], &priv->sreg, priv->len); if (err < 0) return err; @@ -365,7 +365,7 @@ static int nft_bitwise_fast_init(const struct nft_ctx *ctx, struct nft_bitwise_fast_expr *priv = nft_expr_priv(expr); int err; - err = nft_parse_register_load(tb[NFTA_BITWISE_SREG], &priv->sreg, + err = nft_parse_register_load(ctx, tb[NFTA_BITWISE_SREG], &priv->sreg, sizeof(u32)); if (err < 0) return err; diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c index f6e791a68101..2f82a444d21b 100644 --- a/net/netfilter/nft_byteorder.c +++ b/net/netfilter/nft_byteorder.c @@ -139,7 +139,7 @@ static int nft_byteorder_init(const struct nft_ctx *ctx, priv->len = len; - err = nft_parse_register_load(tb[NFTA_BYTEORDER_SREG], &priv->sreg, + err = nft_parse_register_load(ctx, tb[NFTA_BYTEORDER_SREG], &priv->sreg, priv->len); if (err < 0) return err; diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c index cd4652259095..2605f43737bc 100644 --- a/net/netfilter/nft_cmp.c +++ b/net/netfilter/nft_cmp.c @@ -83,7 +83,7 @@ static int nft_cmp_init(const struct nft_ctx *ctx, const struct nft_expr *expr, if (err < 0) return err; - err = nft_parse_register_load(tb[NFTA_CMP_SREG], &priv->sreg, desc.len); + err = nft_parse_register_load(ctx, tb[NFTA_CMP_SREG], &priv->sreg, desc.len); if (err < 0) return err; @@ -222,7 +222,7 @@ static int nft_cmp_fast_init(const struct nft_ctx *ctx, if (err < 0) return err; - err = nft_parse_register_load(tb[NFTA_CMP_SREG], &priv->sreg, desc.len); + err = nft_parse_register_load(ctx, tb[NFTA_CMP_SREG], &priv->sreg, desc.len); if (err < 0) return err; @@ -323,7 +323,7 @@ static int nft_cmp16_fast_init(const struct nft_ctx *ctx, if (err < 0) return err; - err = nft_parse_register_load(tb[NFTA_CMP_SREG], &priv->sreg, desc.len); + err = nft_parse_register_load(ctx, tb[NFTA_CMP_SREG], &priv->sreg, desc.len); if (err < 0) return err; diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 452ed94c3a4d..67a41cd2baaf 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -606,7 +606,7 @@ static int nft_ct_set_init(const struct nft_ctx *ctx, } priv->len = len; - err = nft_parse_register_load(tb[NFTA_CT_SREG], &priv->sreg, len); + err = nft_parse_register_load(ctx, tb[NFTA_CT_SREG], &priv->sreg, len); if (err < 0) goto err1; diff --git a/net/netfilter/nft_dup_netdev.c b/net/netfilter/nft_dup_netdev.c index e5739a59ebf1..0573f96ce079 100644 --- a/net/netfilter/nft_dup_netdev.c +++ b/net/netfilter/nft_dup_netdev.c @@ -40,7 +40,7 @@ static int nft_dup_netdev_init(const struct nft_ctx *ctx, if (tb[NFTA_DUP_SREG_DEV] == NULL) return -EINVAL; - return nft_parse_register_load(tb[NFTA_DUP_SREG_DEV], &priv->sreg_dev, + return nft_parse_register_load(ctx, tb[NFTA_DUP_SREG_DEV], &priv->sreg_dev, sizeof(int)); } diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index b4ada3ab2167..6920df754265 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -215,7 +215,7 @@ static int nft_dynset_init(const struct nft_ctx *ctx, return err; } - err = nft_parse_register_load(tb[NFTA_DYNSET_SREG_KEY], &priv->sreg_key, + err = nft_parse_register_load(ctx, tb[NFTA_DYNSET_SREG_KEY], &priv->sreg_key, set->klen); if (err < 0) return err; @@ -226,7 +226,7 @@ static int nft_dynset_init(const struct nft_ctx *ctx, if (set->dtype == NFT_DATA_VERDICT) return -EOPNOTSUPP; - err = nft_parse_register_load(tb[NFTA_DYNSET_SREG_DATA], + err = nft_parse_register_load(ctx, tb[NFTA_DYNSET_SREG_DATA], &priv->sreg_data, set->dlen); if (err < 0) return err; diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index 6eb571d0c3fd..6bfd33516241 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -588,7 +588,7 @@ static int nft_exthdr_tcp_set_init(const struct nft_ctx *ctx, priv->flags = flags; priv->op = op; - return nft_parse_register_load(tb[NFTA_EXTHDR_SREG], &priv->sreg, + return nft_parse_register_load(ctx, tb[NFTA_EXTHDR_SREG], &priv->sreg, priv->len); } diff --git a/net/netfilter/nft_fwd_netdev.c b/net/netfilter/nft_fwd_netdev.c index 358e742afad7..c83a794025f9 100644 --- a/net/netfilter/nft_fwd_netdev.c +++ b/net/netfilter/nft_fwd_netdev.c @@ -52,7 +52,7 @@ static int nft_fwd_netdev_init(const struct nft_ctx *ctx, if (tb[NFTA_FWD_SREG_DEV] == NULL) return -EINVAL; - return nft_parse_register_load(tb[NFTA_FWD_SREG_DEV], &priv->sreg_dev, + return nft_parse_register_load(ctx, tb[NFTA_FWD_SREG_DEV], &priv->sreg_dev, sizeof(int)); } @@ -178,12 +178,12 @@ static int nft_fwd_neigh_init(const struct nft_ctx *ctx, return -EOPNOTSUPP; } - err = nft_parse_register_load(tb[NFTA_FWD_SREG_DEV], &priv->sreg_dev, + err = nft_parse_register_load(ctx, tb[NFTA_FWD_SREG_DEV], &priv->sreg_dev, sizeof(int)); if (err < 0) return err; - return nft_parse_register_load(tb[NFTA_FWD_SREG_ADDR], &priv->sreg_addr, + return nft_parse_register_load(ctx, tb[NFTA_FWD_SREG_ADDR], &priv->sreg_addr, addr_len); } diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c index 868d68302d22..5d034bbb6913 100644 --- a/net/netfilter/nft_hash.c +++ b/net/netfilter/nft_hash.c @@ -92,7 +92,7 @@ static int nft_jhash_init(const struct nft_ctx *ctx, priv->len = len; - err = nft_parse_register_load(tb[NFTA_HASH_SREG], &priv->sreg, len); + err = nft_parse_register_load(ctx, tb[NFTA_HASH_SREG], &priv->sreg, len); if (err < 0) return err; diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index f3080fa1b226..580e4b1deb9b 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -113,7 +113,7 @@ static int nft_lookup_init(const struct nft_ctx *ctx, if (IS_ERR(set)) return PTR_ERR(set); - err = nft_parse_register_load(tb[NFTA_LOOKUP_SREG], &priv->sreg, + err = nft_parse_register_load(ctx, tb[NFTA_LOOKUP_SREG], &priv->sreg, set->klen); if (err < 0) return err; diff --git a/net/netfilter/nft_masq.c b/net/netfilter/nft_masq.c index 8a14aaca93bb..cb43c72a8c2a 100644 --- a/net/netfilter/nft_masq.c +++ b/net/netfilter/nft_masq.c @@ -52,13 +52,13 @@ static int nft_masq_init(const struct nft_ctx *ctx, priv->flags = ntohl(nla_get_be32(tb[NFTA_MASQ_FLAGS])); if (tb[NFTA_MASQ_REG_PROTO_MIN]) { - err = nft_parse_register_load(tb[NFTA_MASQ_REG_PROTO_MIN], + err = nft_parse_register_load(ctx, tb[NFTA_MASQ_REG_PROTO_MIN], &priv->sreg_proto_min, plen); if (err < 0) return err; if (tb[NFTA_MASQ_REG_PROTO_MAX]) { - err = nft_parse_register_load(tb[NFTA_MASQ_REG_PROTO_MAX], + err = nft_parse_register_load(ctx, tb[NFTA_MASQ_REG_PROTO_MAX], &priv->sreg_proto_max, plen); if (err < 0) diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index 9139ce38ea7b..0214ad1ced2f 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -657,7 +657,7 @@ int nft_meta_set_init(const struct nft_ctx *ctx, } priv->len = len; - err = nft_parse_register_load(tb[NFTA_META_SREG], &priv->sreg, len); + err = nft_parse_register_load(ctx, tb[NFTA_META_SREG], &priv->sreg, len); if (err < 0) return err; diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index 808f5802c270..983dd937fe02 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -214,13 +214,13 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, priv->family = family; if (tb[NFTA_NAT_REG_ADDR_MIN]) { - err = nft_parse_register_load(tb[NFTA_NAT_REG_ADDR_MIN], + err = nft_parse_register_load(ctx, tb[NFTA_NAT_REG_ADDR_MIN], &priv->sreg_addr_min, alen); if (err < 0) return err; if (tb[NFTA_NAT_REG_ADDR_MAX]) { - err = nft_parse_register_load(tb[NFTA_NAT_REG_ADDR_MAX], + err = nft_parse_register_load(ctx, tb[NFTA_NAT_REG_ADDR_MAX], &priv->sreg_addr_max, alen); if (err < 0) @@ -234,13 +234,13 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, plen = sizeof_field(struct nf_nat_range, min_proto.all); if (tb[NFTA_NAT_REG_PROTO_MIN]) { - err = nft_parse_register_load(tb[NFTA_NAT_REG_PROTO_MIN], + err = nft_parse_register_load(ctx, tb[NFTA_NAT_REG_PROTO_MIN], &priv->sreg_proto_min, plen); if (err < 0) return err; if (tb[NFTA_NAT_REG_PROTO_MAX]) { - err = nft_parse_register_load(tb[NFTA_NAT_REG_PROTO_MAX], + err = nft_parse_register_load(ctx, tb[NFTA_NAT_REG_PROTO_MAX], &priv->sreg_proto_max, plen); if (err < 0) diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c index 509011b1ef59..09da7a3f9f96 100644 --- a/net/netfilter/nft_objref.c +++ b/net/netfilter/nft_objref.c @@ -143,7 +143,7 @@ static int nft_objref_map_init(const struct nft_ctx *ctx, if (!(set->flags & NFT_SET_OBJECT)) return -EINVAL; - err = nft_parse_register_load(tb[NFTA_OBJREF_SET_SREG], &priv->sreg, + err = nft_parse_register_load(ctx, tb[NFTA_OBJREF_SET_SREG], &priv->sreg, set->klen); if (err < 0) return err; diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 50429cbd42da..330609a76fb2 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -981,7 +981,7 @@ static int nft_payload_set_init(const struct nft_ctx *ctx, } priv->csum_type = csum_type; - return nft_parse_register_load(tb[NFTA_PAYLOAD_SREG], &priv->sreg, + return nft_parse_register_load(ctx, tb[NFTA_PAYLOAD_SREG], &priv->sreg, priv->len); } diff --git a/net/netfilter/nft_queue.c b/net/netfilter/nft_queue.c index b2b8127c8d43..44e6817e6e29 100644 --- a/net/netfilter/nft_queue.c +++ b/net/netfilter/nft_queue.c @@ -136,7 +136,7 @@ static int nft_queue_sreg_init(const struct nft_ctx *ctx, struct nft_queue *priv = nft_expr_priv(expr); int err; - err = nft_parse_register_load(tb[NFTA_QUEUE_SREG_QNUM], + err = nft_parse_register_load(ctx, tb[NFTA_QUEUE_SREG_QNUM], &priv->sreg_qnum, sizeof(u32)); if (err < 0) return err; diff --git a/net/netfilter/nft_range.c b/net/netfilter/nft_range.c index 51ae64cd268f..ea382f7bbd78 100644 --- a/net/netfilter/nft_range.c +++ b/net/netfilter/nft_range.c @@ -83,7 +83,7 @@ static int nft_range_init(const struct nft_ctx *ctx, const struct nft_expr *expr goto err2; } - err = nft_parse_register_load(tb[NFTA_RANGE_SREG], &priv->sreg, + err = nft_parse_register_load(ctx, tb[NFTA_RANGE_SREG], &priv->sreg, desc_from.len); if (err < 0) goto err2; diff --git a/net/netfilter/nft_redir.c b/net/netfilter/nft_redir.c index a58bd8d291ff..6568cc264078 100644 --- a/net/netfilter/nft_redir.c +++ b/net/netfilter/nft_redir.c @@ -51,13 +51,13 @@ static int nft_redir_init(const struct nft_ctx *ctx, plen = sizeof_field(struct nf_nat_range, min_proto.all); if (tb[NFTA_REDIR_REG_PROTO_MIN]) { - err = nft_parse_register_load(tb[NFTA_REDIR_REG_PROTO_MIN], + err = nft_parse_register_load(ctx, tb[NFTA_REDIR_REG_PROTO_MIN], &priv->sreg_proto_min, plen); if (err < 0) return err; if (tb[NFTA_REDIR_REG_PROTO_MAX]) { - err = nft_parse_register_load(tb[NFTA_REDIR_REG_PROTO_MAX], + err = nft_parse_register_load(ctx, tb[NFTA_REDIR_REG_PROTO_MAX], &priv->sreg_proto_max, plen); if (err < 0) diff --git a/net/netfilter/nft_tproxy.c b/net/netfilter/nft_tproxy.c index 71412adb73d4..1b691393d8b1 100644 --- a/net/netfilter/nft_tproxy.c +++ b/net/netfilter/nft_tproxy.c @@ -254,14 +254,14 @@ static int nft_tproxy_init(const struct nft_ctx *ctx, } if (tb[NFTA_TPROXY_REG_ADDR]) { - err = nft_parse_register_load(tb[NFTA_TPROXY_REG_ADDR], + err = nft_parse_register_load(ctx, tb[NFTA_TPROXY_REG_ADDR], &priv->sreg_addr, alen); if (err < 0) return err; } if (tb[NFTA_TPROXY_REG_PORT]) { - err = nft_parse_register_load(tb[NFTA_TPROXY_REG_PORT], + err = nft_parse_register_load(ctx, tb[NFTA_TPROXY_REG_PORT], &priv->sreg_port, sizeof(u16)); if (err < 0) return err; diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c index 5d04ef80a61d..0e762277bcf8 100644 --- a/net/netfilter/xt_connlimit.c +++ b/net/netfilter/xt_connlimit.c @@ -86,6 +86,7 @@ static int connlimit_mt_check(const struct xt_mtchk_param *par) { struct xt_connlimit_info *info = par->matchinfo; unsigned int keylen; + int ret; keylen = sizeof(u32); if (par->family == NFPROTO_IPV6) @@ -93,8 +94,17 @@ static int connlimit_mt_check(const struct xt_mtchk_param *par) else keylen += sizeof(struct in_addr); + ret = nf_ct_netns_get(par->net, par->family); + if (ret < 0) { + pr_info_ratelimited("cannot load conntrack support for proto=%u\n", + par->family); + return ret; + } + /* init private data */ - info->data = nf_conncount_init(par->net, par->family, keylen); + info->data = nf_conncount_init(par->net, keylen); + if (IS_ERR(info->data)) + nf_ct_netns_put(par->net, par->family); return PTR_ERR_OR_ZERO(info->data); } @@ -103,7 +113,8 @@ static void connlimit_mt_destroy(const struct xt_mtdtor_param *par) { const struct xt_connlimit_info *info = par->matchinfo; - nf_conncount_destroy(par->net, par->family, info->data); + nf_conncount_destroy(par->net, info->data); + nf_ct_netns_put(par->net, par->family); } static struct xt_match connlimit_mt_reg __read_mostly = { diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h index 9751e29d4bbb..5b0e4e62ab8b 100644 --- a/net/netlink/af_netlink.h +++ b/net/netlink/af_netlink.h @@ -41,7 +41,6 @@ struct netlink_sock { struct netlink_callback cb; struct mutex nl_cb_mutex; - struct mutex *dump_cb_mutex; void (*netlink_rcv)(struct sk_buff *skb); int (*netlink_bind)(struct net *net, int group); void (*netlink_unbind)(struct net *net, int group); diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 101f9a23792c..16e260014684 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -237,14 +237,18 @@ static int pop_vlan(struct sk_buff *skb, struct sw_flow_key *key) static int push_vlan(struct sk_buff *skb, struct sw_flow_key *key, const struct ovs_action_push_vlan *vlan) { + int err; + if (skb_vlan_tag_present(skb)) { invalidate_flow_key(key); } else { key->eth.vlan.tci = vlan->vlan_tci; key->eth.vlan.tpid = vlan->vlan_tpid; } - return skb_vlan_push(skb, vlan->vlan_tpid, - ntohs(vlan->vlan_tci) & ~VLAN_CFI_MASK); + err = skb_vlan_push(skb, vlan->vlan_tpid, + ntohs(vlan->vlan_tci) & ~VLAN_CFI_MASK); + skb_reset_mac_len(skb); + return err; } /* 'src' is already properly masked. */ diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 8eb1d644b741..3bb4810234aa 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -1368,11 +1368,8 @@ bool ovs_ct_verify(struct net *net, enum ovs_key_attr attr) attr == OVS_KEY_ATTR_CT_MARK) return true; if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && - attr == OVS_KEY_ATTR_CT_LABELS) { - struct ovs_net *ovs_net = net_generic(net, ovs_net_id); - - return ovs_net->xt_label; - } + attr == OVS_KEY_ATTR_CT_LABELS) + return true; return false; } @@ -1381,6 +1378,7 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr, const struct sw_flow_key *key, struct sw_flow_actions **sfa, bool log) { + unsigned int n_bits = sizeof(struct ovs_key_ct_labels) * BITS_PER_BYTE; struct ovs_conntrack_info ct_info; const char *helper = NULL; u16 family; @@ -1409,6 +1407,12 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr, return -ENOMEM; } + if (nf_connlabels_get(net, n_bits - 1)) { + nf_ct_tmpl_free(ct_info.ct); + OVS_NLERR(log, "Failed to set connlabel length"); + return -EOPNOTSUPP; + } + if (ct_info.timeout[0]) { if (nf_ct_set_timeout(net, ct_info.ct, family, key->ip.proto, ct_info.timeout)) @@ -1577,6 +1581,7 @@ static void __ovs_ct_free_action(struct ovs_conntrack_info *ct_info) if (ct_info->ct) { if (ct_info->timeout[0]) nf_ct_destroy_timeout(ct_info->ct); + nf_connlabels_put(nf_ct_net(ct_info->ct)); nf_ct_tmpl_free(ct_info->ct); } } @@ -1603,8 +1608,7 @@ static int ovs_ct_limit_init(struct net *net, struct ovs_net *ovs_net) for (i = 0; i < CT_LIMIT_HASH_BUCKETS; i++) INIT_HLIST_HEAD(&ovs_net->ct_limit_info->limits[i]); - ovs_net->ct_limit_info->data = - nf_conncount_init(net, NFPROTO_INET, sizeof(u32)); + ovs_net->ct_limit_info->data = nf_conncount_init(net, sizeof(u32)); if (IS_ERR(ovs_net->ct_limit_info->data)) { err = PTR_ERR(ovs_net->ct_limit_info->data); @@ -1621,7 +1625,7 @@ static void ovs_ct_limit_exit(struct net *net, struct ovs_net *ovs_net) const struct ovs_ct_limit_info *info = ovs_net->ct_limit_info; int i; - nf_conncount_destroy(net, NFPROTO_INET, info->data); + nf_conncount_destroy(net, info->data); for (i = 0; i < CT_LIMIT_HASH_BUCKETS; ++i) { struct hlist_head *head = &info->limits[i]; struct ovs_ct_limit *ct_limit; @@ -2002,17 +2006,9 @@ struct genl_family dp_ct_limit_genl_family __ro_after_init = { int ovs_ct_init(struct net *net) { - unsigned int n_bits = sizeof(struct ovs_key_ct_labels) * BITS_PER_BYTE; +#if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) struct ovs_net *ovs_net = net_generic(net, ovs_net_id); - if (nf_connlabels_get(net, n_bits - 1)) { - ovs_net->xt_label = false; - OVS_NLERR(true, "Failed to set connlabel length"); - } else { - ovs_net->xt_label = true; - } - -#if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) return ovs_ct_limit_init(net, ovs_net); #else return 0; @@ -2021,12 +2017,9 @@ int ovs_ct_init(struct net *net) void ovs_ct_exit(struct net *net) { +#if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) struct ovs_net *ovs_net = net_generic(net, ovs_net_id); -#if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) ovs_ct_limit_exit(net, ovs_net); #endif - - if (ovs_net->xt_label) - nf_connlabels_put(net); } diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index 9ca6231ea647..365b9bb7f546 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -160,9 +160,6 @@ struct ovs_net { #if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) struct ovs_ct_limit_info *ct_limit_info; #endif - - /* Module reference for configuring conntrack. */ - bool xt_label; }; /** diff --git a/net/rds/Kconfig b/net/rds/Kconfig index 75cd696963b2..f007730aa2bb 100644 --- a/net/rds/Kconfig +++ b/net/rds/Kconfig @@ -26,3 +26,12 @@ config RDS_DEBUG bool "RDS debugging messages" depends on RDS default n + +config GCOV_PROFILE_RDS + bool "Enable GCOV profiling on RDS" + depends on GCOV_KERNEL + help + Enable GCOV profiling on RDS for checking which functions/lines + are executed. + + If unsure, say N. diff --git a/net/rds/Makefile b/net/rds/Makefile index 8fdc118e2927..3af1ca1d965c 100644 --- a/net/rds/Makefile +++ b/net/rds/Makefile @@ -15,3 +15,8 @@ rds_tcp-y := tcp.o tcp_connect.o tcp_listen.o tcp_recv.o \ tcp_send.o tcp_stats.o ccflags-$(CONFIG_RDS_DEBUG) := -DRDS_DEBUG + +# for GCOV coverage profiling +ifdef CONFIG_GCOV_PROFILE_RDS +GCOV_PROFILE := y +endif diff --git a/net/rds/ib.h b/net/rds/ib.h index 2ba71102b1f1..8ef3178ed4d6 100644 --- a/net/rds/ib.h +++ b/net/rds/ib.h @@ -369,9 +369,6 @@ int rds_ib_conn_alloc(struct rds_connection *conn, gfp_t gfp); void rds_ib_conn_free(void *arg); int rds_ib_conn_path_connect(struct rds_conn_path *cp); void rds_ib_conn_path_shutdown(struct rds_conn_path *cp); -void rds_ib_state_change(struct sock *sk); -int rds_ib_listen_init(void); -void rds_ib_listen_stop(void); __printf(2, 3) void __rds_ib_conn_error(struct rds_connection *conn, const char *, ...); int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id, @@ -402,7 +399,6 @@ void rds_ib_inc_free(struct rds_incoming *inc); int rds_ib_inc_copy_to_user(struct rds_incoming *inc, struct iov_iter *to); void rds_ib_recv_cqe_handler(struct rds_ib_connection *ic, struct ib_wc *wc, struct rds_ib_ack_state *state); -void rds_ib_recv_tasklet_fn(unsigned long data); void rds_ib_recv_init_ring(struct rds_ib_connection *ic); void rds_ib_recv_clear_ring(struct rds_ib_connection *ic); void rds_ib_recv_init_ack(struct rds_ib_connection *ic); diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 08de24658f4f..80d682f89b23 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -856,7 +856,6 @@ bool rxrpc_new_incoming_call(struct rxrpc_local *local, struct rxrpc_connection *conn, struct sockaddr_rxrpc *peer_srx, struct sk_buff *skb); -void rxrpc_accept_incoming_calls(struct rxrpc_local *); int rxrpc_user_charge_accept(struct rxrpc_sock *, unsigned long); /* @@ -969,7 +968,6 @@ void rxrpc_connect_client_calls(struct rxrpc_local *local); void rxrpc_expose_client_call(struct rxrpc_call *); void rxrpc_disconnect_client_call(struct rxrpc_bundle *, struct rxrpc_call *); void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle); -void rxrpc_put_client_conn(struct rxrpc_connection *, enum rxrpc_conn_trace); void rxrpc_discard_expired_client_conns(struct rxrpc_local *local); void rxrpc_clean_up_local_conns(struct rxrpc_local *); diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 3ba8e7e739b5..2197eb625658 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -44,8 +44,6 @@ static DEFINE_MUTEX(zones_mutex); struct zones_ht_key { struct net *net; u16 zone; - /* Note : pad[] must be the last field. */ - u8 pad[]; }; struct tcf_ct_flow_table { @@ -62,7 +60,7 @@ struct tcf_ct_flow_table { static const struct rhashtable_params zones_params = { .head_offset = offsetof(struct tcf_ct_flow_table, node), .key_offset = offsetof(struct tcf_ct_flow_table, key), - .key_len = offsetof(struct zones_ht_key, pad), + .key_len = offsetofend(struct zones_ht_key, zone), .automatic_shrinking = true, }; diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index 22f4b1e8ade9..383bf18b6862 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -96,6 +96,7 @@ out: if (skb_at_tc_ingress(skb)) skb_pull_rcsum(skb, skb->mac_len); + skb_reset_mac_len(skb); return action; drop: diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 8e3093938cd2..0316217b7687 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -1466,10 +1466,6 @@ connect_abort: static int smc_connect_check_aclc(struct smc_init_info *ini, struct smc_clc_msg_accept_confirm *aclc) { - if (aclc->hdr.typev1 != SMC_TYPE_R && - aclc->hdr.typev1 != SMC_TYPE_D) - return SMC_CLC_DECL_MODEUNSUPP; - if (aclc->hdr.version >= SMC_V2) { if ((aclc->hdr.typev1 == SMC_TYPE_R && !smcr_indicated(ini->smc_type_v2)) || @@ -1523,10 +1519,6 @@ static int __smc_connect(struct smc_sock *smc) ini->smcd_version &= ~SMC_V1; ini->smcr_version = 0; ini->smc_type_v1 = SMC_TYPE_N; - if (!ini->smcd_version) { - rc = SMC_CLC_DECL_GETVLANERR; - goto fallback; - } } rc = smc_find_proposal_devices(smc, ini); diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h index 467effb50cd6..5625fda2960b 100644 --- a/net/smc/smc_clc.h +++ b/net/smc/smc_clc.h @@ -145,6 +145,8 @@ struct smc_clc_v2_extension { ); u8 user_eids[][SMC_MAX_EID_LEN]; }; +static_assert(offsetof(struct smc_clc_v2_extension, user_eids) == sizeof(struct smc_clc_v2_extension_fixed), + "struct member likely outside of struct_group_tagged()"); struct smc_clc_msg_proposal_prefix { /* prefix part of clc proposal message*/ __be32 outgoing_subnet; /* subnet mask */ @@ -169,6 +171,8 @@ struct smc_clc_smcd_v2_extension { ); struct smc_clc_smcd_gid_chid gidchid[]; }; +static_assert(offsetof(struct smc_clc_smcd_v2_extension, gidchid) == sizeof(struct smc_clc_smcd_v2_extension_fixed), + "struct member likely outside of struct_group_tagged()"); struct smc_clc_msg_proposal { /* clc proposal message sent by Linux */ struct smc_clc_msg_hdr hdr; diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 3b95828d9976..4e694860ece4 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -221,6 +221,35 @@ static void smc_lgr_unregister_conn(struct smc_connection *conn) write_unlock_bh(&lgr->conns_lock); } +static void smc_lgr_buf_list_add(struct smc_link_group *lgr, + bool is_rmb, + struct list_head *buf_list, + struct smc_buf_desc *buf_desc) +{ + list_add(&buf_desc->list, buf_list); + if (is_rmb) { + lgr->alloc_rmbs += buf_desc->len; + lgr->alloc_rmbs += + lgr->is_smcd ? sizeof(struct smcd_cdc_msg) : 0; + } else { + lgr->alloc_sndbufs += buf_desc->len; + } +} + +static void smc_lgr_buf_list_del(struct smc_link_group *lgr, + bool is_rmb, + struct smc_buf_desc *buf_desc) +{ + list_del(&buf_desc->list); + if (is_rmb) { + lgr->alloc_rmbs -= buf_desc->len; + lgr->alloc_rmbs -= + lgr->is_smcd ? sizeof(struct smcd_cdc_msg) : 0; + } else { + lgr->alloc_sndbufs -= buf_desc->len; + } +} + int smc_nl_get_sys_info(struct sk_buff *skb, struct netlink_callback *cb) { struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); @@ -363,6 +392,10 @@ static int smc_nl_fill_lgr(struct smc_link_group *lgr, smc_target[SMC_MAX_PNETID_LEN] = 0; if (nla_put_string(skb, SMC_NLA_LGR_R_PNETID, smc_target)) goto errattr; + if (nla_put_uint(skb, SMC_NLA_LGR_R_SNDBUF_ALLOC, lgr->alloc_sndbufs)) + goto errattr; + if (nla_put_uint(skb, SMC_NLA_LGR_R_RMB_ALLOC, lgr->alloc_rmbs)) + goto errattr; if (lgr->smc_version > SMC_V1) { v2_attrs = nla_nest_start(skb, SMC_NLA_LGR_R_V2_COMMON); if (!v2_attrs) @@ -541,6 +574,10 @@ static int smc_nl_fill_smcd_lgr(struct smc_link_group *lgr, goto errattr; if (nla_put_u32(skb, SMC_NLA_LGR_D_CHID, smc_ism_get_chid(lgr->smcd))) goto errattr; + if (nla_put_uint(skb, SMC_NLA_LGR_D_SNDBUF_ALLOC, lgr->alloc_sndbufs)) + goto errattr; + if (nla_put_uint(skb, SMC_NLA_LGR_D_DMB_ALLOC, lgr->alloc_rmbs)) + goto errattr; memcpy(smc_pnet, lgr->smcd->pnetid, SMC_MAX_PNETID_LEN); smc_pnet[SMC_MAX_PNETID_LEN] = 0; if (nla_put_string(skb, SMC_NLA_LGR_D_PNETID, smc_pnet)) @@ -1138,7 +1175,7 @@ static void smcr_buf_unuse(struct smc_buf_desc *buf_desc, bool is_rmb, lock = is_rmb ? &lgr->rmbs_lock : &lgr->sndbufs_lock; down_write(lock); - list_del(&buf_desc->list); + smc_lgr_buf_list_del(lgr, is_rmb, buf_desc); up_write(lock); smc_buf_free(lgr, is_rmb, buf_desc); @@ -1166,22 +1203,30 @@ static void smcd_buf_detach(struct smc_connection *conn) static void smc_buf_unuse(struct smc_connection *conn, struct smc_link_group *lgr) { + struct smc_sock *smc = container_of(conn, struct smc_sock, conn); + bool is_smcd = lgr->is_smcd; + int bufsize; + if (conn->sndbuf_desc) { - if (!lgr->is_smcd && conn->sndbuf_desc->is_vm) { + bufsize = conn->sndbuf_desc->len; + if (!is_smcd && conn->sndbuf_desc->is_vm) { smcr_buf_unuse(conn->sndbuf_desc, false, lgr); } else { - memzero_explicit(conn->sndbuf_desc->cpu_addr, conn->sndbuf_desc->len); + memzero_explicit(conn->sndbuf_desc->cpu_addr, bufsize); WRITE_ONCE(conn->sndbuf_desc->used, 0); } + SMC_STAT_RMB_SIZE(smc, is_smcd, false, false, bufsize); } if (conn->rmb_desc) { - if (!lgr->is_smcd) { + bufsize = conn->rmb_desc->len; + if (!is_smcd) { smcr_buf_unuse(conn->rmb_desc, true, lgr); } else { - memzero_explicit(conn->rmb_desc->cpu_addr, - conn->rmb_desc->len + sizeof(struct smcd_cdc_msg)); + bufsize += sizeof(struct smcd_cdc_msg); + memzero_explicit(conn->rmb_desc->cpu_addr, bufsize); WRITE_ONCE(conn->rmb_desc->used, 0); } + SMC_STAT_RMB_SIZE(smc, is_smcd, true, false, bufsize); } } @@ -1377,7 +1422,7 @@ static void __smc_lgr_free_bufs(struct smc_link_group *lgr, bool is_rmb) buf_list = &lgr->sndbufs[i]; list_for_each_entry_safe(buf_desc, bf_desc, buf_list, list) { - list_del(&buf_desc->list); + smc_lgr_buf_list_del(lgr, is_rmb, buf_desc); smc_buf_free(lgr, is_rmb, buf_desc); } } @@ -2250,7 +2295,7 @@ int smcr_buf_reg_lgr(struct smc_link *lnk) } static struct smc_buf_desc *smcr_new_buf_create(struct smc_link_group *lgr, - bool is_rmb, int bufsize) + int bufsize) { struct smc_buf_desc *buf_desc; @@ -2390,7 +2435,7 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) buf_desc = smc_buf_get_slot(bufsize_comp, lock, buf_list); if (buf_desc) { buf_desc->is_dma_need_sync = 0; - SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, bufsize); + SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, true, bufsize); SMC_STAT_BUF_REUSE(smc, is_smcd, is_rmb); break; /* found reusable slot */ } @@ -2398,7 +2443,7 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) if (is_smcd) buf_desc = smcd_new_buf_create(lgr, is_rmb, bufsize); else - buf_desc = smcr_new_buf_create(lgr, is_rmb, bufsize); + buf_desc = smcr_new_buf_create(lgr, bufsize); if (PTR_ERR(buf_desc) == -ENOMEM) break; @@ -2411,10 +2456,10 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) } SMC_STAT_RMB_ALLOC(smc, is_smcd, is_rmb); - SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, bufsize); + SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, true, bufsize); buf_desc->used = 1; down_write(lock); - list_add(&buf_desc->list, buf_list); + smc_lgr_buf_list_add(lgr, is_rmb, buf_list, buf_desc); up_write(lock); break; /* found */ } @@ -2496,7 +2541,8 @@ create_rmb: rc = __smc_buf_create(smc, is_smcd, true); if (rc && smc->conn.sndbuf_desc) { down_write(&smc->conn.lgr->sndbufs_lock); - list_del(&smc->conn.sndbuf_desc->list); + smc_lgr_buf_list_del(smc->conn.lgr, false, + smc->conn.sndbuf_desc); up_write(&smc->conn.lgr->sndbufs_lock); smc_buf_free(smc->conn.lgr, false, smc->conn.sndbuf_desc); smc->conn.sndbuf_desc = NULL; diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index d93cf51dbd7c..0db4e5f79ac4 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -281,6 +281,8 @@ struct smc_link_group { struct rw_semaphore sndbufs_lock; /* protects tx buffers */ struct list_head rmbs[SMC_RMBE_SIZES]; /* rx buffers */ struct rw_semaphore rmbs_lock; /* protects rx buffers */ + u64 alloc_sndbufs; /* stats of tx buffers */ + u64 alloc_rmbs; /* stats of rx buffers */ u8 id[SMC_LGR_ID_SIZE]; /* unique lgr id */ struct delayed_work free_work; /* delayed freeing of an lgr */ diff --git a/net/smc/smc_loopback.h b/net/smc/smc_loopback.h index 6dd4292dae56..04dc6808d2e1 100644 --- a/net/smc/smc_loopback.h +++ b/net/smc/smc_loopback.h @@ -15,7 +15,6 @@ #define _SMC_LOOPBACK_H #include <linux/device.h> -#include <linux/err.h> #include <net/smc.h> #if IS_ENABLED(CONFIG_SMC_LO) diff --git a/net/smc/smc_stats.c b/net/smc/smc_stats.c index ca14c0f3a07d..e71b17d1e21c 100644 --- a/net/smc/smc_stats.c +++ b/net/smc/smc_stats.c @@ -218,6 +218,12 @@ static int smc_nl_fill_stats_tech_data(struct sk_buff *skb, smc_tech->tx_bytes, SMC_NLA_STATS_PAD)) goto errattr; + if (nla_put_uint(skb, SMC_NLA_STATS_T_RX_RMB_USAGE, + smc_tech->rx_rmbuse)) + goto errattr; + if (nla_put_uint(skb, SMC_NLA_STATS_T_TX_RMB_USAGE, + smc_tech->tx_rmbuse)) + goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_RX_CNT, smc_tech->rx_cnt, SMC_NLA_STATS_PAD)) diff --git a/net/smc/smc_stats.h b/net/smc/smc_stats.h index e19177ce4092..571f9d9e7814 100644 --- a/net/smc/smc_stats.h +++ b/net/smc/smc_stats.h @@ -79,6 +79,8 @@ struct smc_stats_tech { u64 tx_bytes; u64 rx_cnt; u64 tx_cnt; + u64 rx_rmbuse; + u64 tx_rmbuse; }; struct smc_stats { @@ -135,38 +137,46 @@ do { \ } \ while (0) -#define SMC_STAT_RMB_SIZE_SUB(_smc_stats, _tech, k, _len) \ +#define SMC_STAT_RMB_SIZE_SUB(_smc_stats, _tech, k, _is_add, _len) \ do { \ + typeof(_smc_stats) stats = (_smc_stats); \ + typeof(_is_add) is_a = (_is_add); \ typeof(_len) _l = (_len); \ typeof(_tech) t = (_tech); \ int _pos; \ int m = SMC_BUF_MAX - 1; \ if (_l <= 0) \ break; \ - _pos = fls((_l - 1) >> 13); \ - _pos = (_pos <= m) ? _pos : m; \ - this_cpu_inc((*(_smc_stats)).smc[t].k ## _rmbsize.buf[_pos]); \ + if (is_a) { \ + _pos = fls((_l - 1) >> 13); \ + _pos = (_pos <= m) ? _pos : m; \ + this_cpu_inc((*stats).smc[t].k ## _rmbsize.buf[_pos]); \ + this_cpu_add((*stats).smc[t].k ## _rmbuse, _l); \ + } else { \ + this_cpu_sub((*stats).smc[t].k ## _rmbuse, _l); \ + } \ } \ while (0) #define SMC_STAT_RMB_SUB(_smc_stats, type, t, key) \ this_cpu_inc((*(_smc_stats)).smc[t].rmb ## _ ## key.type ## _cnt) -#define SMC_STAT_RMB_SIZE(_smc, _is_smcd, _is_rx, _len) \ +#define SMC_STAT_RMB_SIZE(_smc, _is_smcd, _is_rx, _is_add, _len) \ do { \ struct net *_net = sock_net(&(_smc)->sk); \ struct smc_stats __percpu *_smc_stats = _net->smc.smc_stats; \ + typeof(_is_add) is_add = (_is_add); \ typeof(_is_smcd) is_d = (_is_smcd); \ typeof(_is_rx) is_r = (_is_rx); \ typeof(_len) l = (_len); \ if ((is_d) && (is_r)) \ - SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_D, rx, l); \ + SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_D, rx, is_add, l); \ if ((is_d) && !(is_r)) \ - SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_D, tx, l); \ + SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_D, tx, is_add, l); \ if (!(is_d) && (is_r)) \ - SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_R, rx, l); \ + SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_R, rx, is_add, l); \ if (!(is_d) && !(is_r)) \ - SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_R, tx, l); \ + SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_R, tx, is_add, l); \ } \ while (0) diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 5a526ebafeb4..3c9e25f6a1d2 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -163,8 +163,12 @@ static int bearer_name_validate(const char *name, /* return bearer name components, if necessary */ if (name_parts) { - strcpy(name_parts->media_name, media_name); - strcpy(name_parts->if_name, if_name); + if (strscpy(name_parts->media_name, media_name, + TIPC_MAX_MEDIA_NAME) < 0) + return 0; + if (strscpy(name_parts->if_name, if_name, + TIPC_MAX_IF_NAME) < 0) + return 0; } return 1; } diff --git a/net/tipc/monitor.c b/net/tipc/monitor.c index 77a3d016cade..e2f19627e43d 100644 --- a/net/tipc/monitor.c +++ b/net/tipc/monitor.c @@ -149,7 +149,7 @@ static int dom_size(int peers) while ((i * i) < peers) i++; - return i < MAX_MON_DOMAIN ? i : MAX_MON_DOMAIN; + return min(i, MAX_MON_DOMAIN); } static void map_set(u64 *up_map, int i, unsigned int v) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 0be0dcb07f7b..a1894019ebd5 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -693,10 +693,7 @@ static void unix_release_sock(struct sock *sk, int embrion) unix_state_unlock(sk); #if IS_ENABLED(CONFIG_AF_UNIX_OOB) - if (u->oob_skb) { - kfree_skb(u->oob_skb); - u->oob_skb = NULL; - } + u->oob_skb = NULL; #endif wake_up_interruptible_all(&u->peer_wait); @@ -2226,13 +2223,9 @@ static int queue_oob(struct socket *sock, struct msghdr *msg, struct sock *other } maybe_add_creds(skb, sock, other); - skb_get(skb); - scm_stat_add(other, skb); spin_lock(&other->sk_receive_queue.lock); - if (ousk->oob_skb) - consume_skb(ousk->oob_skb); WRITE_ONCE(ousk->oob_skb, skb); __skb_queue_tail(&other->sk_receive_queue, skb); spin_unlock(&other->sk_receive_queue.lock); @@ -2640,8 +2633,6 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state) if (!(state->flags & MSG_PEEK)) WRITE_ONCE(u->oob_skb, NULL); - else - skb_get(oob_skb); spin_unlock(&sk->sk_receive_queue.lock); unix_state_unlock(sk); @@ -2651,8 +2642,6 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state) if (!(state->flags & MSG_PEEK)) UNIXCB(oob_skb).consumed += 1; - consume_skb(oob_skb); - mutex_unlock(&u->iolock); if (chunk < 0) @@ -2694,12 +2683,10 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk, if (copied) { skb = NULL; } else if (!(flags & MSG_PEEK)) { - if (sock_flag(sk, SOCK_URGINLINE)) { - WRITE_ONCE(u->oob_skb, NULL); - consume_skb(skb); - } else { + WRITE_ONCE(u->oob_skb, NULL); + + if (!sock_flag(sk, SOCK_URGINLINE)) { __skb_unlink(skb, &sk->sk_receive_queue); - WRITE_ONCE(u->oob_skb, NULL); unlinked_skb = skb; skb = skb_peek(&sk->sk_receive_queue); } @@ -2710,10 +2697,7 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk, spin_unlock(&sk->sk_receive_queue.lock); - if (unlinked_skb) { - WARN_ON_ONCE(skb_unref(unlinked_skb)); - kfree_skb(unlinked_skb); - } + kfree_skb(unlinked_skb); } return skb; } @@ -2756,7 +2740,6 @@ static int unix_stream_read_skb(struct sock *sk, skb_read_actor_t recv_actor) unix_state_unlock(sk); if (drop) { - WARN_ON_ONCE(skb_unref(skb)); kfree_skb(skb); return -EAGAIN; } diff --git a/net/unix/garbage.c b/net/unix/garbage.c index 06d94ad999e9..0068e758be4d 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -337,18 +337,6 @@ static bool unix_vertex_dead(struct unix_vertex *vertex) return true; } -static void unix_collect_queue(struct unix_sock *u, struct sk_buff_head *hitlist) -{ - skb_queue_splice_init(&u->sk.sk_receive_queue, hitlist); - -#if IS_ENABLED(CONFIG_AF_UNIX_OOB) - if (u->oob_skb) { - WARN_ON_ONCE(skb_unref(u->oob_skb)); - u->oob_skb = NULL; - } -#endif -} - static void unix_collect_skb(struct list_head *scc, struct sk_buff_head *hitlist) { struct unix_vertex *vertex; @@ -371,11 +359,11 @@ static void unix_collect_skb(struct list_head *scc, struct sk_buff_head *hitlist struct sk_buff_head *embryo_queue = &skb->sk->sk_receive_queue; spin_lock(&embryo_queue->lock); - unix_collect_queue(unix_sk(skb->sk), hitlist); + skb_queue_splice_init(embryo_queue, hitlist); spin_unlock(&embryo_queue->lock); } } else { - unix_collect_queue(u, hitlist); + skb_queue_splice_init(queue, hitlist); } spin_unlock(&queue->lock); diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 0ff9b2dd86ba..35681adedd9a 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -112,6 +112,7 @@ #include <net/sock.h> #include <net/af_vsock.h> #include <uapi/linux/vm_sockets.h> +#include <uapi/asm-generic/ioctls.h> static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr); static void vsock_sk_destruct(struct sock *sk); @@ -1295,6 +1296,57 @@ int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, } EXPORT_SYMBOL_GPL(vsock_dgram_recvmsg); +static int vsock_do_ioctl(struct socket *sock, unsigned int cmd, + int __user *arg) +{ + struct sock *sk = sock->sk; + struct vsock_sock *vsk; + int ret; + + vsk = vsock_sk(sk); + + switch (cmd) { + case SIOCOUTQ: { + ssize_t n_bytes; + + if (!vsk->transport || !vsk->transport->unsent_bytes) { + ret = -EOPNOTSUPP; + break; + } + + if (sock_type_connectible(sk->sk_type) && sk->sk_state == TCP_LISTEN) { + ret = -EINVAL; + break; + } + + n_bytes = vsk->transport->unsent_bytes(vsk); + if (n_bytes < 0) { + ret = n_bytes; + break; + } + + ret = put_user(n_bytes, arg); + break; + } + default: + ret = -ENOIOCTLCMD; + } + + return ret; +} + +static int vsock_ioctl(struct socket *sock, unsigned int cmd, + unsigned long arg) +{ + int ret; + + lock_sock(sock->sk); + ret = vsock_do_ioctl(sock, cmd, (int __user *)arg); + release_sock(sock->sk); + + return ret; +} + static const struct proto_ops vsock_dgram_ops = { .family = PF_VSOCK, .owner = THIS_MODULE, @@ -1305,7 +1357,7 @@ static const struct proto_ops vsock_dgram_ops = { .accept = sock_no_accept, .getname = vsock_getname, .poll = vsock_poll, - .ioctl = sock_no_ioctl, + .ioctl = vsock_ioctl, .listen = sock_no_listen, .shutdown = vsock_shutdown, .sendmsg = vsock_dgram_sendmsg, @@ -2294,7 +2346,7 @@ static const struct proto_ops vsock_stream_ops = { .accept = vsock_accept, .getname = vsock_getname, .poll = vsock_poll, - .ioctl = sock_no_ioctl, + .ioctl = vsock_ioctl, .listen = vsock_listen, .shutdown = vsock_shutdown, .setsockopt = vsock_connectible_setsockopt, @@ -2316,7 +2368,7 @@ static const struct proto_ops vsock_seqpacket_ops = { .accept = vsock_accept, .getname = vsock_getname, .poll = vsock_poll, - .ioctl = sock_no_ioctl, + .ioctl = vsock_ioctl, .listen = vsock_listen, .shutdown = vsock_shutdown, .setsockopt = vsock_connectible_setsockopt, diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 64a07acfef12..e0160da4ef43 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -311,7 +311,7 @@ static void virtio_transport_tx_work(struct work_struct *work) virtqueue_disable_cb(vq); while ((skb = virtqueue_get_buf(vq, &len)) != NULL) { - consume_skb(skb); + virtio_transport_consume_skb_sent(skb, true); added = true; } } while (!virtqueue_enable_cb(vq)); @@ -540,6 +540,8 @@ static struct virtio_transport virtio_transport = { .notify_buffer_size = virtio_transport_notify_buffer_size, .notify_set_rcvlowat = virtio_transport_notify_set_rcvlowat, + .unsent_bytes = virtio_transport_unsent_bytes, + .read_skb = virtio_transport_read_skb, }, diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 16ff976a86e3..884ee128851e 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -463,6 +463,26 @@ void virtio_transport_inc_tx_pkt(struct virtio_vsock_sock *vvs, struct sk_buff * } EXPORT_SYMBOL_GPL(virtio_transport_inc_tx_pkt); +void virtio_transport_consume_skb_sent(struct sk_buff *skb, bool consume) +{ + struct sock *s = skb->sk; + + if (s && skb->len) { + struct vsock_sock *vs = vsock_sk(s); + struct virtio_vsock_sock *vvs; + + vvs = vs->trans; + + spin_lock_bh(&vvs->tx_lock); + vvs->bytes_unsent -= skb->len; + spin_unlock_bh(&vvs->tx_lock); + } + + if (consume) + consume_skb(skb); +} +EXPORT_SYMBOL_GPL(virtio_transport_consume_skb_sent); + u32 virtio_transport_get_credit(struct virtio_vsock_sock *vvs, u32 credit) { u32 ret; @@ -475,6 +495,7 @@ u32 virtio_transport_get_credit(struct virtio_vsock_sock *vvs, u32 credit) if (ret > credit) ret = credit; vvs->tx_cnt += ret; + vvs->bytes_unsent += ret; spin_unlock_bh(&vvs->tx_lock); return ret; @@ -488,6 +509,7 @@ void virtio_transport_put_credit(struct virtio_vsock_sock *vvs, u32 credit) spin_lock_bh(&vvs->tx_lock); vvs->tx_cnt -= credit; + vvs->bytes_unsent -= credit; spin_unlock_bh(&vvs->tx_lock); } EXPORT_SYMBOL_GPL(virtio_transport_put_credit); @@ -1090,6 +1112,19 @@ void virtio_transport_destruct(struct vsock_sock *vsk) } EXPORT_SYMBOL_GPL(virtio_transport_destruct); +ssize_t virtio_transport_unsent_bytes(struct vsock_sock *vsk) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + size_t ret; + + spin_lock_bh(&vvs->tx_lock); + ret = vvs->bytes_unsent; + spin_unlock_bh(&vvs->tx_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(virtio_transport_unsent_bytes); + static int virtio_transport_reset(struct vsock_sock *vsk, struct sk_buff *skb) { diff --git a/net/vmw_vsock/vsock_loopback.c b/net/vmw_vsock/vsock_loopback.c index 6dea6119f5b2..6e78927a598e 100644 --- a/net/vmw_vsock/vsock_loopback.c +++ b/net/vmw_vsock/vsock_loopback.c @@ -98,6 +98,8 @@ static struct virtio_transport loopback_transport = { .notify_buffer_size = virtio_transport_notify_buffer_size, .notify_set_rcvlowat = virtio_transport_notify_set_rcvlowat, + .unsent_bytes = virtio_transport_unsent_bytes, + .read_skb = virtio_transport_read_skb, }, @@ -123,6 +125,10 @@ static void vsock_loopback_work(struct work_struct *work) spin_unlock_bh(&vsock->pkt_queue.lock); while ((skb = __skb_dequeue(&pkts))) { + /* Decrement the bytes_unsent counter without deallocating skb + * It is freed by the receiver. + */ + virtio_transport_consume_skb_sent(skb, false); virtio_transport_deliver_tap_pkt(skb); virtio_transport_recv_pkt(&loopback_transport, skb); } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 35bcf52dbc65..e05b39e39c3f 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -2851,7 +2851,7 @@ union bpf_attr { * **TCP_SYNCNT**, **TCP_USER_TIMEOUT**, **TCP_NOTSENT_LOWAT**, * **TCP_NODELAY**, **TCP_MAXSEG**, **TCP_WINDOW_CLAMP**, * **TCP_THIN_LINEAR_TIMEOUTS**, **TCP_BPF_DELACK_MAX**, - * **TCP_BPF_RTO_MIN**. + * **TCP_BPF_RTO_MIN**, **TCP_BPF_SOCK_OPS_CB_FLAGS**. * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. * * **IPPROTO_IPV6**, which supports the following *optname*\ s: * **IPV6_TCLASS**, **IPV6_AUTOFLOWLABEL**. @@ -7080,6 +7080,7 @@ enum { TCP_BPF_SYN = 1005, /* Copy the TCP header */ TCP_BPF_SYN_IP = 1006, /* Copy the IP[46] and TCP header */ 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 */ }; enum { diff --git a/tools/net/ynl/lib/ynl.c b/tools/net/ynl/lib/ynl.c index fcb18a5a6d70..e16cef160bc2 100644 --- a/tools/net/ynl/lib/ynl.c +++ b/tools/net/ynl/lib/ynl.c @@ -696,14 +696,14 @@ ynl_sock_create(const struct ynl_family *yf, struct ynl_error *yse) addr.nl_family = AF_NETLINK; if (bind(ys->socket, (struct sockaddr *)&addr, sizeof(addr)) < 0) { __perr(yse, "unable to bind to a socket address"); - goto err_close_sock;; + goto err_close_sock; } memset(&addr, 0, sizeof(addr)); addrlen = sizeof(addr); if (getsockname(ys->socket, (struct sockaddr *)&addr, &addrlen) < 0) { __perr(yse, "unable to read socket address"); - goto err_close_sock;; + goto err_close_sock; } ys->portid = addr.nl_pid; ys->seq = random(); diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py index 51529fabd517..717530bc9c52 100755 --- a/tools/net/ynl/ynl-gen-c.py +++ b/tools/net/ynl/ynl-gen-c.py @@ -2668,13 +2668,15 @@ def main(): cw.p('#define ' + hdr_prot) cw.nl() + hdr_file=os.path.basename(args.out_file[:-2]) + ".h" + if args.mode == 'kernel': cw.p('#include <net/netlink.h>') cw.p('#include <net/genetlink.h>') cw.nl() if not args.header: if args.out_file: - cw.p(f'#include "{os.path.basename(args.out_file[:-2])}.h"') + cw.p(f'#include "{hdr_file}"') cw.nl() headers = ['uapi/' + parsed.uapi_header] headers += parsed.kernel_family.get('headers', []) @@ -2686,7 +2688,7 @@ def main(): if family_contains_bitfield32(parsed): cw.p('#include <linux/netlink.h>') else: - cw.p(f'#include "{parsed.name}-user.h"') + cw.p(f'#include "{hdr_file}"') cw.p('#include "ynl.h"') headers = [parsed.uapi_header] for definition in parsed['definitions']: diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index bc8fe9e8f7f2..a5f1c0c27dff 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -68,6 +68,7 @@ TARGETS += net/mptcp TARGETS += net/openvswitch TARGETS += net/tcp_ao TARGETS += net/netfilter +TARGETS += net/rds TARGETS += nsfs TARGETS += perf_events TARGETS += pidfd diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c index 9e5f38739104..6b3078dd5645 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c @@ -378,8 +378,8 @@ struct test tests[] = { .iph_inner.ihl = 5, .iph_inner.protocol = IPPROTO_TCP, .iph_inner.tot_len = - __bpf_constant_htons(MAGIC_BYTES) - - sizeof(struct iphdr), + __bpf_constant_htons(MAGIC_BYTES - + sizeof(struct iphdr)), .tcp.doff = 5, .tcp.source = 80, .tcp.dest = 8080, @@ -407,8 +407,8 @@ struct test tests[] = { .iph_inner.ihl = 5, .iph_inner.protocol = IPPROTO_TCP, .iph_inner.tot_len = - __bpf_constant_htons(MAGIC_BYTES) - - sizeof(struct iphdr), + __bpf_constant_htons(MAGIC_BYTES - + sizeof(struct iphdr)), .tcp.doff = 5, .tcp.source = 80, .tcp.dest = 8080, @@ -436,8 +436,8 @@ struct test tests[] = { .iph_inner.ihl = 5, .iph_inner.protocol = IPPROTO_TCP, .iph_inner.tot_len = - __bpf_constant_htons(MAGIC_BYTES) - - sizeof(struct iphdr), + __bpf_constant_htons(MAGIC_BYTES - + sizeof(struct iphdr)), .tcp.doff = 5, .tcp.source = 99, .tcp.dest = 9090, diff --git a/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c b/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c index 7d4a9b3d3722..e12255121c15 100644 --- a/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c +++ b/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c @@ -154,6 +154,51 @@ err_out: close(sfd); } +static void test_nonstandard_opt(int family) +{ + struct setget_sockopt__bss *bss = skel->bss; + struct bpf_link *getsockopt_link = NULL; + int sfd = -1, fd = -1, cfd = -1, flags; + socklen_t flagslen = sizeof(flags); + + memset(bss, 0, sizeof(*bss)); + + sfd = start_server(family, SOCK_STREAM, + family == AF_INET6 ? addr6_str : addr4_str, 0, 0); + if (!ASSERT_GE(sfd, 0, "start_server")) + return; + + fd = connect_to_fd(sfd, 0); + if (!ASSERT_GE(fd, 0, "connect_to_fd_server")) + goto err_out; + + /* cgroup/getsockopt prog will intercept getsockopt() below and + * retrieve the tcp socket bpf_sock_ops_cb_flags value for the + * accept()ed socket; this was set earlier in the passive established + * callback for the accept()ed socket via bpf_setsockopt(). + */ + getsockopt_link = bpf_program__attach_cgroup(skel->progs._getsockopt, cg_fd); + if (!ASSERT_OK_PTR(getsockopt_link, "getsockopt prog")) + goto err_out; + + cfd = accept(sfd, NULL, 0); + if (!ASSERT_GE(cfd, 0, "accept")) + goto err_out; + + if (!ASSERT_OK(getsockopt(cfd, SOL_TCP, TCP_BPF_SOCK_OPS_CB_FLAGS, &flags, &flagslen), + "getsockopt_flags")) + goto err_out; + ASSERT_EQ(flags & BPF_SOCK_OPS_STATE_CB_FLAG, BPF_SOCK_OPS_STATE_CB_FLAG, + "cb_flags_set"); +err_out: + close(sfd); + if (fd != -1) + close(fd); + if (cfd != -1) + close(cfd); + bpf_link__destroy(getsockopt_link); +} + void test_setget_sockopt(void) { cg_fd = test__join_cgroup(CG_NAME); @@ -191,6 +236,8 @@ void test_setget_sockopt(void) test_udp(AF_INET); test_ktls(AF_INET6); test_ktls(AF_INET); + test_nonstandard_opt(AF_INET); + test_nonstandard_opt(AF_INET6); done: setget_sockopt__destroy(skel); diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index 1337153eb0ad..82bfb266741c 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -451,11 +451,11 @@ out: #define MAX_EVENTS 10 static void test_sockmap_skb_verdict_shutdown(void) { + int n, err, map, verdict, c1 = -1, p1 = -1; struct epoll_event ev, events[MAX_EVENTS]; - int n, err, map, verdict, s, c1 = -1, p1 = -1; struct test_sockmap_pass_prog *skel; - int epollfd; int zero = 0; + int epollfd; char b; skel = test_sockmap_pass_prog__open_and_load(); @@ -469,10 +469,7 @@ static void test_sockmap_skb_verdict_shutdown(void) if (!ASSERT_OK(err, "bpf_prog_attach")) goto out; - s = socket_loopback(AF_INET, SOCK_STREAM); - if (s < 0) - goto out; - err = create_pair(s, AF_INET, SOCK_STREAM, &c1, &p1); + err = create_pair(AF_INET, SOCK_STREAM, &c1, &p1); if (err < 0) goto out; @@ -506,8 +503,8 @@ out: static void test_sockmap_skb_verdict_fionread(bool pass_prog) { + int err, map, verdict, c0 = -1, c1 = -1, p0 = -1, p1 = -1; int expected, zero = 0, sent, recvd, avail; - int err, map, verdict, s, c0 = -1, c1 = -1, p0 = -1, p1 = -1; struct test_sockmap_pass_prog *pass = NULL; struct test_sockmap_drop_prog *drop = NULL; char buf[256] = "0123456789"; @@ -534,11 +531,8 @@ static void test_sockmap_skb_verdict_fionread(bool pass_prog) if (!ASSERT_OK(err, "bpf_prog_attach")) goto out; - s = socket_loopback(AF_INET, SOCK_STREAM); - if (!ASSERT_GT(s, -1, "socket_loopback(s)")) - goto out; - err = create_socket_pairs(s, AF_INET, SOCK_STREAM, &c0, &c1, &p0, &p1); - if (!ASSERT_OK(err, "create_socket_pairs(s)")) + err = create_socket_pairs(AF_INET, SOCK_STREAM, &c0, &c1, &p0, &p1); + if (!ASSERT_OK(err, "create_socket_pairs()")) goto out; err = bpf_map_update_elem(map, &zero, &c1, BPF_NOEXIST); @@ -570,16 +564,12 @@ out: static void test_sockmap_skb_verdict_peek_helper(int map) { - int err, s, c1, p1, zero = 0, sent, recvd, avail; + int err, c1, p1, zero = 0, sent, recvd, avail; char snd[256] = "0123456789"; char rcv[256] = "0"; - s = socket_loopback(AF_INET, SOCK_STREAM); - if (!ASSERT_GT(s, -1, "socket_loopback(s)")) - return; - - err = create_pair(s, AF_INET, SOCK_STREAM, &c1, &p1); - if (!ASSERT_OK(err, "create_pairs(s)")) + err = create_pair(AF_INET, SOCK_STREAM, &c1, &p1); + if (!ASSERT_OK(err, "create_pair()")) return; err = bpf_map_update_elem(map, &zero, &c1, BPF_NOEXIST); diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h index e880f97bc44d..38e35c72bdaa 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h @@ -3,6 +3,9 @@ #include <linux/vm_sockets.h> +/* include/linux/net.h */ +#define SOCK_TYPE_MASK 0xf + #define IO_TIMEOUT_SEC 30 #define MAX_STRERR_LEN 256 #define MAX_TEST_NAME 80 @@ -14,6 +17,17 @@ #define __always_unused __attribute__((__unused__)) +/* include/linux/cleanup.h */ +#define __get_and_null(p, nullvalue) \ + ({ \ + __auto_type __ptr = &(p); \ + __auto_type __val = *__ptr; \ + *__ptr = nullvalue; \ + __val; \ + }) + +#define take_fd(fd) __get_and_null(fd, -EBADF) + #define _FAIL(errnum, fmt...) \ ({ \ error_at_line(0, (errnum), __func__, __LINE__, fmt); \ @@ -179,6 +193,14 @@ __ret; \ }) +static inline void close_fd(int *fd) +{ + if (*fd >= 0) + xclose(*fd); +} + +#define __close_fd __attribute__((cleanup(close_fd))) + static inline int poll_connect(int fd, unsigned int timeout_sec) { struct timeval timeout = { .tv_sec = timeout_sec }; @@ -312,54 +334,6 @@ static inline int add_to_sockmap(int sock_mapfd, int fd1, int fd2) return xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST); } -static inline int create_pair(int s, int family, int sotype, int *c, int *p) -{ - struct sockaddr_storage addr; - socklen_t len; - int err = 0; - - len = sizeof(addr); - err = xgetsockname(s, sockaddr(&addr), &len); - if (err) - return err; - - *c = xsocket(family, sotype, 0); - if (*c < 0) - return errno; - err = xconnect(*c, sockaddr(&addr), len); - if (err) { - err = errno; - goto close_cli0; - } - - *p = xaccept_nonblock(s, NULL, NULL); - if (*p < 0) { - err = errno; - goto close_cli0; - } - return err; -close_cli0: - close(*c); - return err; -} - -static inline int create_socket_pairs(int s, int family, int sotype, - int *c0, int *c1, int *p0, int *p1) -{ - int err; - - err = create_pair(s, family, sotype, c0, p0); - if (err) - return err; - - err = create_pair(s, family, sotype, c1, p1); - if (err) { - close(*c0); - close(*p0); - } - return err; -} - static inline int enable_reuseport(int s, int progfd) { int err, one = 1; @@ -412,5 +386,84 @@ static inline int socket_loopback(int family, int sotype) return socket_loopback_reuseport(family, sotype, -1); } +static inline int create_pair(int family, int sotype, int *p0, int *p1) +{ + __close_fd int s, c = -1, p = -1; + struct sockaddr_storage addr; + socklen_t len = sizeof(addr); + int err; + + s = socket_loopback(family, sotype); + if (s < 0) + return s; + + err = xgetsockname(s, sockaddr(&addr), &len); + if (err) + return err; + + c = xsocket(family, sotype, 0); + if (c < 0) + return c; + + err = connect(c, sockaddr(&addr), len); + if (err) { + if (errno != EINPROGRESS) { + FAIL_ERRNO("connect"); + return err; + } + + err = poll_connect(c, IO_TIMEOUT_SEC); + if (err) { + FAIL_ERRNO("poll_connect"); + return err; + } + } + + switch (sotype & SOCK_TYPE_MASK) { + case SOCK_DGRAM: + err = xgetsockname(c, sockaddr(&addr), &len); + if (err) + return err; + + err = xconnect(s, sockaddr(&addr), len); + if (err) + return err; + + *p0 = take_fd(s); + break; + case SOCK_STREAM: + case SOCK_SEQPACKET: + p = xaccept_nonblock(s, NULL, NULL); + if (p < 0) + return p; + + *p0 = take_fd(p); + break; + default: + FAIL("Unsupported socket type %#x", sotype); + return -EOPNOTSUPP; + } + + *p1 = take_fd(c); + return 0; +} + +static inline int create_socket_pairs(int family, int sotype, int *c0, int *c1, + int *p0, int *p1) +{ + int err; + + err = create_pair(family, sotype, c0, p0); + if (err) + return err; + + err = create_pair(family, sotype, c1, p1); + if (err) { + close(*c0); + close(*p0); + } + + return err; +} #endif // __SOCKMAP_HELPERS__ diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c index 9ce0e0e0b7da..da5a6fb03b69 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c @@ -677,7 +677,7 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd, int verd_mapfd, enum redir_mode mode) { const char *log_prefix = redir_mode_str(mode); - int s, c0, c1, p0, p1; + int c0, c1, p0, p1; unsigned int pass; int err, n; u32 key; @@ -685,13 +685,10 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd, zero_verdict_count(verd_mapfd); - s = socket_loopback(family, sotype | SOCK_NONBLOCK); - if (s < 0) - return; - - err = create_socket_pairs(s, family, sotype, &c0, &c1, &p0, &p1); + err = create_socket_pairs(family, sotype | SOCK_NONBLOCK, &c0, &c1, + &p0, &p1); if (err) - goto close_srv; + return; err = add_to_sockmap(sock_mapfd, p0, p1); if (err) @@ -722,8 +719,6 @@ close: xclose(c1); xclose(p0); xclose(c0); -close_srv: - xclose(s); } static void test_skb_redir_to_connected(struct test_sockmap_listen *skel, @@ -909,7 +904,7 @@ static void test_msg_redir_to_listening_with_link(struct test_sockmap_listen *sk static void redir_partial(int family, int sotype, int sock_map, int parser_map) { - int s, c0 = -1, c1 = -1, p0 = -1, p1 = -1; + int c0 = -1, c1 = -1, p0 = -1, p1 = -1; int err, n, key, value; char buf[] = "abc"; @@ -919,13 +914,10 @@ static void redir_partial(int family, int sotype, int sock_map, int parser_map) if (err) return; - s = socket_loopback(family, sotype | SOCK_NONBLOCK); - if (s < 0) - goto clean_parser_map; - - err = create_socket_pairs(s, family, sotype, &c0, &c1, &p0, &p1); + err = create_socket_pairs(family, sotype | SOCK_NONBLOCK, &c0, &c1, + &p0, &p1); if (err) - goto close_srv; + goto clean_parser_map; err = add_to_sockmap(sock_map, p0, p1); if (err) @@ -944,8 +936,6 @@ close: xclose(p0); xclose(c1); xclose(p1); -close_srv: - xclose(s); clean_parser_map: key = 0; @@ -1500,49 +1490,7 @@ static void test_unix_redir(struct test_sockmap_listen *skel, struct bpf_map *ma /* Returns two connected loopback vsock sockets */ static int vsock_socketpair_connectible(int sotype, int *v0, int *v1) { - struct sockaddr_storage addr; - socklen_t len = sizeof(addr); - int s, p, c; - - s = socket_loopback(AF_VSOCK, sotype); - if (s < 0) - return -1; - - c = xsocket(AF_VSOCK, sotype | SOCK_NONBLOCK, 0); - if (c == -1) - goto close_srv; - - if (getsockname(s, sockaddr(&addr), &len) < 0) - goto close_cli; - - if (connect(c, sockaddr(&addr), len) < 0 && errno != EINPROGRESS) { - FAIL_ERRNO("connect"); - goto close_cli; - } - - len = sizeof(addr); - p = accept_timeout(s, sockaddr(&addr), &len, IO_TIMEOUT_SEC); - if (p < 0) - goto close_cli; - - if (poll_connect(c, IO_TIMEOUT_SEC) < 0) { - FAIL_ERRNO("poll_connect"); - goto close_acc; - } - - *v0 = p; - *v1 = c; - - return 0; - -close_acc: - close(p); -close_cli: - close(c); -close_srv: - close(s); - - return -1; + return create_pair(AF_VSOCK, sotype | SOCK_NONBLOCK, v0, v1); } static void vsock_unix_redir_connectible(int sock_mapfd, int verd_mapfd, @@ -1691,44 +1639,7 @@ static void test_reuseport(struct test_sockmap_listen *skel, static int inet_socketpair(int family, int type, int *s, int *c) { - struct sockaddr_storage addr; - socklen_t len; - int p0, c0; - int err; - - p0 = socket_loopback(family, type | SOCK_NONBLOCK); - if (p0 < 0) - return p0; - - len = sizeof(addr); - err = xgetsockname(p0, sockaddr(&addr), &len); - if (err) - goto close_peer0; - - c0 = xsocket(family, type | SOCK_NONBLOCK, 0); - if (c0 < 0) { - err = c0; - goto close_peer0; - } - err = xconnect(c0, sockaddr(&addr), len); - if (err) - goto close_cli0; - err = xgetsockname(c0, sockaddr(&addr), &len); - if (err) - goto close_cli0; - err = xconnect(p0, sockaddr(&addr), len); - if (err) - goto close_cli0; - - *s = p0; - *c = c0; - return 0; - -close_cli0: - xclose(c0); -close_peer0: - xclose(p0); - return err; + return create_pair(family, type | SOCK_NONBLOCK, s, c); } static void udp_redir_to_connected(int family, int sock_mapfd, int verd_mapfd, @@ -1795,11 +1706,11 @@ static void inet_unix_redir_to_connected(int family, int type, int sock_mapfd, int sfd[2]; int err; - if (socketpair(AF_UNIX, SOCK_DGRAM | SOCK_NONBLOCK, 0, sfd)) + if (socketpair(AF_UNIX, type | SOCK_NONBLOCK, 0, sfd)) return; c0 = sfd[0], p0 = sfd[1]; - err = inet_socketpair(family, SOCK_DGRAM, &p1, &c1); + err = inet_socketpair(family, type, &p1, &c1); if (err) goto close; @@ -1847,7 +1758,7 @@ static void unix_inet_redir_to_connected(int family, int type, int sock_mapfd, int sfd[2]; int err; - err = inet_socketpair(family, SOCK_DGRAM, &p0, &c0); + err = inet_socketpair(family, type, &p0, &c0); if (err) return; @@ -1882,7 +1793,7 @@ static void unix_inet_skb_redir_to_connected(struct test_sockmap_listen *skel, unix_inet_redir_to_connected(family, SOCK_DGRAM, sock_map, -1, verdict_map, REDIR_EGRESS, NO_FLAGS); - unix_inet_redir_to_connected(family, SOCK_DGRAM, + unix_inet_redir_to_connected(family, SOCK_STREAM, sock_map, -1, verdict_map, REDIR_EGRESS, NO_FLAGS); diff --git a/tools/testing/selftests/bpf/progs/setget_sockopt.c b/tools/testing/selftests/bpf/progs/setget_sockopt.c index 60518aed1ffc..6dd4318debbf 100644 --- a/tools/testing/selftests/bpf/progs/setget_sockopt.c +++ b/tools/testing/selftests/bpf/progs/setget_sockopt.c @@ -59,6 +59,8 @@ static const struct sockopt_test sol_tcp_tests[] = { { .opt = TCP_THIN_LINEAR_TIMEOUTS, .flip = 1, }, { .opt = TCP_USER_TIMEOUT, .new = 123400, .expected = 123400, }, { .opt = TCP_NOTSENT_LOWAT, .new = 1314, .expected = 1314, }, + { .opt = TCP_BPF_SOCK_OPS_CB_FLAGS, .new = BPF_SOCK_OPS_ALL_CB_FLAGS, + .expected = BPF_SOCK_OPS_ALL_CB_FLAGS, }, { .opt = 0, }, }; @@ -353,11 +355,30 @@ int BPF_PROG(socket_post_create, struct socket *sock, int family, return 1; } +SEC("cgroup/getsockopt") +int _getsockopt(struct bpf_sockopt *ctx) +{ + struct bpf_sock *sk = ctx->sk; + int *optval = ctx->optval; + struct tcp_sock *tp; + + if (!sk || ctx->level != SOL_TCP || ctx->optname != TCP_BPF_SOCK_OPS_CB_FLAGS) + return 1; + + tp = bpf_core_cast(sk, struct tcp_sock); + if (ctx->optval + sizeof(int) <= ctx->optval_end) { + *optval = tp->bpf_sock_ops_cb_flags; + ctx->retval = 0; + } + return 1; +} + SEC("sockops") int skops_sockopt(struct bpf_sock_ops *skops) { struct bpf_sock *bpf_sk = skops->sk; struct sock *sk; + int flags; if (!bpf_sk) return 1; @@ -384,9 +405,8 @@ int skops_sockopt(struct bpf_sock_ops *skops) nr_passive += !(bpf_test_sockopt(skops, sk) || test_tcp_maxseg(skops, sk) || test_tcp_saved_syn(skops, sk)); - bpf_sock_ops_cb_flags_set(skops, - skops->bpf_sock_ops_cb_flags | - BPF_SOCK_OPS_STATE_CB_FLAG); + flags = skops->bpf_sock_ops_cb_flags | BPF_SOCK_OPS_STATE_CB_FLAG; + bpf_setsockopt(skops, SOL_TCP, TCP_BPF_SOCK_OPS_CB_FLAGS, &flags, sizeof(flags)); break; case BPF_SOCK_OPS_STATE_CB: if (skops->args[1] == BPF_TCP_CLOSE_WAIT) diff --git a/tools/testing/selftests/bpf/progs/test_tcp_custom_syncookie.c b/tools/testing/selftests/bpf/progs/test_tcp_custom_syncookie.c index 44ee0d037f95..eb5cca1fce16 100644 --- a/tools/testing/selftests/bpf/progs/test_tcp_custom_syncookie.c +++ b/tools/testing/selftests/bpf/progs/test_tcp_custom_syncookie.c @@ -486,17 +486,10 @@ static int tcp_validate_cookie(struct tcp_syncookie *ctx) goto err; mssind = (cookie & (3 << 6)) >> 6; - if (ctx->ipv4) { - if (mssind > ARRAY_SIZE(msstab4)) - goto err; - + if (ctx->ipv4) ctx->attrs.mss = msstab4[mssind]; - } else { - if (mssind > ARRAY_SIZE(msstab6)) - goto err; - + else ctx->attrs.mss = msstab6[mssind]; - } ctx->attrs.snd_wscale = cookie & BPF_SYNCOOKIE_WSCALE_MASK; ctx->attrs.rcv_wscale = ctx->attrs.snd_wscale; diff --git a/tools/testing/selftests/drivers/net/Makefile b/tools/testing/selftests/drivers/net/Makefile index e54f382bcb02..39fb97a8c1df 100644 --- a/tools/testing/selftests/drivers/net/Makefile +++ b/tools/testing/selftests/drivers/net/Makefile @@ -1,8 +1,11 @@ # SPDX-License-Identifier: GPL-2.0 -TEST_INCLUDES := $(wildcard lib/py/*.py) +TEST_INCLUDES := $(wildcard lib/py/*.py) \ + ../../net/net_helper.sh \ + ../../net/lib.sh \ TEST_PROGS := \ + netcons_basic.sh \ ping.py \ queues.py \ stats.py \ diff --git a/tools/testing/selftests/drivers/net/config b/tools/testing/selftests/drivers/net/config index f6a58ce8a230..a2d8af60876d 100644 --- a/tools/testing/selftests/drivers/net/config +++ b/tools/testing/selftests/drivers/net/config @@ -1,2 +1,6 @@ CONFIG_IPV6=y CONFIG_NETDEVSIM=m +CONFIG_CONFIGFS_FS=y +CONFIG_NETCONSOLE=m +CONFIG_NETCONSOLE_DYNAMIC=y +CONFIG_NETCONSOLE_EXTENDED_LOG=y diff --git a/tools/testing/selftests/drivers/net/hw/pp_alloc_fail.py b/tools/testing/selftests/drivers/net/hw/pp_alloc_fail.py index 026d98976c35..05b6fbb3fcdd 100755 --- a/tools/testing/selftests/drivers/net/hw/pp_alloc_fail.py +++ b/tools/testing/selftests/drivers/net/hw/pp_alloc_fail.py @@ -1,6 +1,7 @@ #!/usr/bin/env python3 # SPDX-License-Identifier: GPL-2.0 +import errno import time import os from lib.py import ksft_run, ksft_exit, ksft_pr @@ -61,7 +62,7 @@ def test_pp_alloc(cfg, netdevnl): try: stats = get_stats() except NlError as e: - if e.nl_msg.error == -95: + if e.nl_msg.error == -errno.EOPNOTSUPP: stats = {} else: raise diff --git a/tools/testing/selftests/drivers/net/hw/rss_ctx.py b/tools/testing/selftests/drivers/net/hw/rss_ctx.py index 011508ca604b..9d7adb3cf33b 100755 --- a/tools/testing/selftests/drivers/net/hw/rss_ctx.py +++ b/tools/testing/selftests/drivers/net/hw/rss_ctx.py @@ -3,7 +3,7 @@ import datetime import random -from lib.py import ksft_run, ksft_pr, ksft_exit, ksft_eq, ksft_ge, ksft_lt +from lib.py import ksft_run, ksft_pr, ksft_exit, ksft_eq, ksft_ne, ksft_ge, ksft_lt from lib.py import NetDrvEpEnv from lib.py import EthtoolFamily, NetdevFamily from lib.py import KsftSkipEx @@ -90,10 +90,10 @@ def _send_traffic_check(cfg, port, name, params): ksft_ge(directed, 20000, f"traffic on {name}: " + str(cnts)) if params.get('noise'): ksft_lt(sum(cnts[i] for i in params['noise']), directed / 2, - "traffic on other queues:" + str(cnts)) + f"traffic on other queues ({name})':" + str(cnts)) if params.get('empty'): ksft_eq(sum(cnts[i] for i in params['empty']), 0, - "traffic on inactive queues: " + str(cnts)) + f"traffic on inactive queues ({name}): " + str(cnts)) def test_rss_key_indir(cfg): @@ -302,6 +302,78 @@ def test_hitless_key_update(cfg): ksft_eq(carrier1 - carrier0, 0) +def test_rss_context_dump(cfg): + """ + Test dumping RSS contexts. This tests mostly exercises the kernel APIs. + """ + + # Get a random key of the right size + data = get_rss(cfg) + if 'rss-hash-key' in data: + key_data = _rss_key_rand(len(data['rss-hash-key'])) + key = _rss_key_str(key_data) + else: + key_data = [] + key = "ba:ad" + + ids = [] + try: + ids.append(ethtool_create(cfg, "-X", f"context new")) + defer(ethtool, f"-X {cfg.ifname} context {ids[-1]} delete") + + ids.append(ethtool_create(cfg, "-X", f"context new weight 1 1")) + defer(ethtool, f"-X {cfg.ifname} context {ids[-1]} delete") + + ids.append(ethtool_create(cfg, "-X", f"context new hkey {key}")) + defer(ethtool, f"-X {cfg.ifname} context {ids[-1]} delete") + except CmdExitFailure: + if not ids: + raise KsftSkipEx("Unable to add any contexts") + ksft_pr(f"Added only {len(ids)} out of 3 contexts") + + expect_tuples = set([(cfg.ifname, -1)] + [(cfg.ifname, ctx_id) for ctx_id in ids]) + + # Dump all + ctxs = cfg.ethnl.rss_get({}, dump=True) + tuples = [(c['header']['dev-name'], c.get('context', -1)) for c in ctxs] + ksft_eq(len(tuples), len(set(tuples)), "duplicates in context dump") + ctx_tuples = set([ctx for ctx in tuples if ctx[0] == cfg.ifname]) + ksft_eq(expect_tuples, ctx_tuples) + + # Sanity-check the results + for data in ctxs: + ksft_ne(set(data['indir']), {0}, "indir table is all zero") + ksft_ne(set(data.get('hkey', [1])), {0}, "key is all zero") + + # More specific checks + if len(ids) > 1 and data.get('context') == ids[1]: + ksft_eq(set(data['indir']), {0, 1}, + "ctx1 - indir table mismatch") + if len(ids) > 2 and data.get('context') == ids[2]: + ksft_eq(data['hkey'], bytes(key_data), "ctx2 - key mismatch") + + # Ifindex filter + ctxs = cfg.ethnl.rss_get({'header': {'dev-name': cfg.ifname}}, dump=True) + tuples = [(c['header']['dev-name'], c.get('context', -1)) for c in ctxs] + ctx_tuples = set(tuples) + ksft_eq(len(tuples), len(ctx_tuples), "duplicates in context dump") + ksft_eq(expect_tuples, ctx_tuples) + + # Skip ctx 0 + expect_tuples.remove((cfg.ifname, -1)) + + ctxs = cfg.ethnl.rss_get({'start-context': 1}, dump=True) + tuples = [(c['header']['dev-name'], c.get('context', -1)) for c in ctxs] + ksft_eq(len(tuples), len(set(tuples)), "duplicates in context dump") + ctx_tuples = set([ctx for ctx in tuples if ctx[0] == cfg.ifname]) + ksft_eq(expect_tuples, ctx_tuples) + + # And finally both with ifindex and skip main + ctxs = cfg.ethnl.rss_get({'header': {'dev-name': cfg.ifname}, 'start-context': 1}, dump=True) + ctx_tuples = set([(c['header']['dev-name'], c.get('context', -1)) for c in ctxs]) + ksft_eq(expect_tuples, ctx_tuples) + + def test_rss_context(cfg, ctx_cnt=1, create_with_cfg=None): """ Test separating traffic into RSS contexts. @@ -542,7 +614,7 @@ def main() -> None: ksft_run([test_rss_key_indir, test_rss_queue_reconfigure, test_rss_resize, test_hitless_key_update, test_rss_context, test_rss_context4, test_rss_context32, - test_rss_context_queue_reconfigure, + test_rss_context_dump, test_rss_context_queue_reconfigure, test_rss_context_overlap, test_rss_context_overlap2, test_rss_context_out_of_order, test_rss_context4_create_with_cfg], args=(cfg, )) diff --git a/tools/testing/selftests/drivers/net/lib/py/env.py b/tools/testing/selftests/drivers/net/lib/py/env.py index a5e800b8f103..1ea9bb695e94 100644 --- a/tools/testing/selftests/drivers/net/lib/py/env.py +++ b/tools/testing/selftests/drivers/net/lib/py/env.py @@ -4,6 +4,7 @@ import os import time from pathlib import Path from lib.py import KsftSkipEx, KsftXfailEx +from lib.py import ksft_setup from lib.py import cmd, ethtool, ip from lib.py import NetNS, NetdevSimDev from .remote import Remote @@ -14,7 +15,7 @@ def _load_env_file(src_path): src_dir = Path(src_path).parent.resolve() if not (src_dir / "net.config").exists(): - return env + return ksft_setup(env) with open((src_dir / "net.config").as_posix(), 'r') as fp: for line in fp.readlines(): @@ -30,7 +31,7 @@ def _load_env_file(src_path): if len(pair) != 2: raise Exception("Can't parse configuration line:", full_file) env[pair[0]] = pair[1] - return env + return ksft_setup(env) class NetDrvEnv: diff --git a/tools/testing/selftests/drivers/net/netcons_basic.sh b/tools/testing/selftests/drivers/net/netcons_basic.sh new file mode 100755 index 000000000000..06021b2059b7 --- /dev/null +++ b/tools/testing/selftests/drivers/net/netcons_basic.sh @@ -0,0 +1,234 @@ +#!/usr/bin/env bash +# SPDX-License-Identifier: GPL-2.0 + +# This test creates two netdevsim virtual interfaces, assigns one of them (the +# "destination interface") to a new namespace, and assigns IP addresses to both +# interfaces. +# +# It listens on the destination interface using socat and configures a dynamic +# target on netconsole, pointing to the destination IP address. +# +# Finally, it checks whether the message was received properly on the +# destination interface. Note that this test may pollute the kernel log buffer +# (dmesg) and relies on dynamic configuration and namespaces being configured. +# +# Author: Breno Leitao <leitao@debian.org> + +set -euo pipefail + +SCRIPTDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")") + +# Simple script to test dynamic targets in netconsole +SRCIF="" # to be populated later +SRCIP=192.168.1.1 +DSTIF="" # to be populated later +DSTIP=192.168.1.2 + +PORT="6666" +MSG="netconsole selftest" +TARGET=$(mktemp -u netcons_XXXXX) +DEFAULT_PRINTK_VALUES=$(cat /proc/sys/kernel/printk) +NETCONS_CONFIGFS="/sys/kernel/config/netconsole" +NETCONS_PATH="${NETCONS_CONFIGFS}"/"${TARGET}" +# NAMESPACE will be populated by setup_ns with a random value +NAMESPACE="" + +# IDs for netdevsim +NSIM_DEV_1_ID=$((256 + RANDOM % 256)) +NSIM_DEV_2_ID=$((512 + RANDOM % 256)) + +# Used to create and delete namespaces +source "${SCRIPTDIR}"/../../net/lib.sh +source "${SCRIPTDIR}"/../../net/net_helper.sh + +# Create netdevsim interfaces +create_ifaces() { + local NSIM_DEV_SYS_NEW=/sys/bus/netdevsim/new_device + + echo "$NSIM_DEV_2_ID" > "$NSIM_DEV_SYS_NEW" + echo "$NSIM_DEV_1_ID" > "$NSIM_DEV_SYS_NEW" + udevadm settle 2> /dev/null || true + + local NSIM1=/sys/bus/netdevsim/devices/netdevsim"$NSIM_DEV_1_ID" + local NSIM2=/sys/bus/netdevsim/devices/netdevsim"$NSIM_DEV_2_ID" + + # These are global variables + SRCIF=$(find "$NSIM1"/net -maxdepth 1 -type d ! \ + -path "$NSIM1"/net -exec basename {} \;) + DSTIF=$(find "$NSIM2"/net -maxdepth 1 -type d ! \ + -path "$NSIM2"/net -exec basename {} \;) +} + +link_ifaces() { + local NSIM_DEV_SYS_LINK="/sys/bus/netdevsim/link_device" + local SRCIF_IFIDX=$(cat /sys/class/net/"$SRCIF"/ifindex) + local DSTIF_IFIDX=$(cat /sys/class/net/"$DSTIF"/ifindex) + + exec {NAMESPACE_FD}</var/run/netns/"${NAMESPACE}" + exec {INITNS_FD}</proc/self/ns/net + + # Bind the dst interface to namespace + ip link set "${DSTIF}" netns "${NAMESPACE}" + + # Linking one device to the other one (on the other namespace} + if ! echo "${INITNS_FD}:$SRCIF_IFIDX $NAMESPACE_FD:$DSTIF_IFIDX" > $NSIM_DEV_SYS_LINK + then + echo "linking netdevsim1 with netdevsim2 should succeed" + cleanup + exit "${ksft_skip}" + fi +} + +function configure_ip() { + # Configure the IPs for both interfaces + ip netns exec "${NAMESPACE}" ip addr add "${DSTIP}"/24 dev "${DSTIF}" + ip netns exec "${NAMESPACE}" ip link set "${DSTIF}" up + + ip addr add "${SRCIP}"/24 dev "${SRCIF}" + ip link set "${SRCIF}" up +} + +function set_network() { + # setup_ns function is coming from lib.sh + setup_ns NAMESPACE + + # Create both interfaces, and assign the destination to a different + # namespace + create_ifaces + + # Link both interfaces back to back + link_ifaces + + configure_ip +} + +function create_dynamic_target() { + DSTMAC=$(ip netns exec "${NAMESPACE}" \ + ip link show "${DSTIF}" | awk '/ether/ {print $2}') + + # Create a dynamic target + mkdir "${NETCONS_PATH}" + + echo "${DSTIP}" > "${NETCONS_PATH}"/remote_ip + echo "${SRCIP}" > "${NETCONS_PATH}"/local_ip + echo "${DSTMAC}" > "${NETCONS_PATH}"/remote_mac + echo "${SRCIF}" > "${NETCONS_PATH}"/dev_name + + echo 1 > "${NETCONS_PATH}"/enabled +} + +function cleanup() { + local NSIM_DEV_SYS_DEL="/sys/bus/netdevsim/del_device" + + # delete netconsole dynamic reconfiguration + echo 0 > "${NETCONS_PATH}"/enabled + # Remove the configfs entry + rmdir "${NETCONS_PATH}" + + # Delete netdevsim devices + echo "$NSIM_DEV_2_ID" > "$NSIM_DEV_SYS_DEL" + echo "$NSIM_DEV_1_ID" > "$NSIM_DEV_SYS_DEL" + + # this is coming from lib.sh + cleanup_all_ns + + # Restoring printk configurations + echo "${DEFAULT_PRINTK_VALUES}" > /proc/sys/kernel/printk +} + +function listen_port_and_save_to() { + local OUTPUT=${1} + # Just wait for 2 seconds + timeout 2 ip netns exec "${NAMESPACE}" \ + socat UDP-LISTEN:"${PORT}",fork "${OUTPUT}" +} + +function validate_result() { + local TMPFILENAME="$1" + + # Check if the file exists + if [ ! -f "$TMPFILENAME" ]; then + echo "FAIL: File was not generated." >&2 + exit "${ksft_fail}" + fi + + if ! grep -q "${MSG}" "${TMPFILENAME}"; then + echo "FAIL: ${MSG} not found in ${TMPFILENAME}" >&2 + cat "${TMPFILENAME}" >&2 + exit "${ksft_fail}" + fi + + # Delete the file once it is validated, otherwise keep it + # for debugging purposes + rm "${TMPFILENAME}" + exit "${ksft_pass}" +} + +function check_for_dependencies() { + if [ "$(id -u)" -ne 0 ]; then + echo "This test must be run as root" >&2 + exit "${ksft_skip}" + fi + + if ! which socat > /dev/null ; then + echo "SKIP: socat(1) is not available" >&2 + exit "${ksft_skip}" + fi + + if ! which ip > /dev/null ; then + echo "SKIP: ip(1) is not available" >&2 + exit "${ksft_skip}" + fi + + if ! which udevadm > /dev/null ; then + echo "SKIP: udevadm(1) is not available" >&2 + exit "${ksft_skip}" + fi + + if [ ! -d "${NETCONS_CONFIGFS}" ]; then + echo "SKIP: directory ${NETCONS_CONFIGFS} does not exist. Check if NETCONSOLE_DYNAMIC is enabled" >&2 + exit "${ksft_skip}" + fi + + if ip link show "${DSTIF}" 2> /dev/null; then + echo "SKIP: interface ${DSTIF} exists in the system. Not overwriting it." >&2 + exit "${ksft_skip}" + fi + + if ip addr list | grep -E "inet.*(${SRCIP}|${DSTIP})" 2> /dev/null; then + echo "SKIP: IPs already in use. Skipping it" >&2 + exit "${ksft_skip}" + fi +} + +# ========== # +# Start here # +# ========== # +modprobe netdevsim 2> /dev/null || true +modprobe netconsole 2> /dev/null || true + +# The content of kmsg will be save to the following file +OUTPUT_FILE="/tmp/${TARGET}" + +# Check for basic system dependency and exit if not found +check_for_dependencies +# Set current loglevel to KERN_INFO(6), and default to KERN_NOTICE(5) +echo "6 5" > /proc/sys/kernel/printk +# Remove the namespace, interfaces and netconsole target on exit +trap cleanup EXIT +# Create one namespace and two interfaces +set_network +# Create a dynamic target for netconsole +create_dynamic_target +# Listed for netconsole port inside the namespace and destination interface +listen_port_and_save_to "${OUTPUT_FILE}" & +# Wait for socat to start and listen to the port. +wait_local_port_listen "${NAMESPACE}" "${PORT}" udp +# Send the message +echo "${MSG}: ${TARGET}" > /dev/kmsg +# Wait until socat saves the file to disk +busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}" + +# Make sure the message was received in the dst part +# and exit +validate_result "${OUTPUT_FILE}" diff --git a/tools/testing/selftests/drivers/net/stats.py b/tools/testing/selftests/drivers/net/stats.py index 820b8e0a22c6..63e3c045a3b2 100755 --- a/tools/testing/selftests/drivers/net/stats.py +++ b/tools/testing/selftests/drivers/net/stats.py @@ -1,10 +1,13 @@ #!/usr/bin/env python3 # SPDX-License-Identifier: GPL-2.0 +import errno from lib.py import ksft_run, ksft_exit, ksft_pr from lib.py import ksft_ge, ksft_eq, ksft_in, ksft_true, ksft_raises, KsftSkipEx, KsftXfailEx +from lib.py import ksft_disruptive from lib.py import EthtoolFamily, NetdevFamily, RtnlFamily, NlError from lib.py import NetDrvEnv +from lib.py import ip, defer ethnl = EthtoolFamily() netfam = NetdevFamily() @@ -17,7 +20,7 @@ def check_pause(cfg) -> None: try: ethnl.pause_get({"header": {"dev-index": cfg.ifindex}}) except NlError as e: - if e.error == 95: + if e.error == errno.EOPNOTSUPP: raise KsftXfailEx("pause not supported by the device") raise @@ -32,7 +35,7 @@ def check_fec(cfg) -> None: try: ethnl.fec_get({"header": {"dev-index": cfg.ifindex}}) except NlError as e: - if e.error == 95: + if e.error == errno.EOPNOTSUPP: raise KsftXfailEx("FEC not supported by the device") raise @@ -117,7 +120,7 @@ def qstat_by_ifindex(cfg) -> None: # loopback has no stats with ksft_raises(NlError) as cm: netfam.qstats_get({"ifindex": 1}, dump=True) - ksft_eq(cm.exception.nl_msg.error, -95) + ksft_eq(cm.exception.nl_msg.error, -errno.EOPNOTSUPP) ksft_eq(cm.exception.nl_msg.extack['bad-attr'], '.ifindex') # Try to get stats for lowest unused ifindex but not 0 @@ -133,9 +136,31 @@ def qstat_by_ifindex(cfg) -> None: ksft_eq(cm.exception.nl_msg.extack['bad-attr'], '.ifindex') +@ksft_disruptive +def check_down(cfg) -> None: + try: + qstat = netfam.qstats_get({"ifindex": cfg.ifindex}, dump=True)[0] + except NlError as e: + if e.error == errno.EOPNOTSUPP: + raise KsftSkipEx("qstats not supported by the device") + raise + + ip(f"link set dev {cfg.dev['ifname']} down") + defer(ip, f"link set dev {cfg.dev['ifname']} up") + + qstat2 = netfam.qstats_get({"ifindex": cfg.ifindex}, dump=True)[0] + for k, v in qstat.items(): + ksft_ge(qstat2[k], qstat[k], comment=f"{k} went backwards on device down") + + # exercise per-queue API to make sure that "device down" state + # is handled correctly and doesn't crash + netfam.qstats_get({"ifindex": cfg.ifindex, "scope": "queue"}, dump=True) + + def main() -> None: with NetDrvEnv(__file__) as cfg: - ksft_run([check_pause, check_fec, pkt_byte_sum, qstat_by_ifindex], + ksft_run([check_pause, check_fec, pkt_byte_sum, qstat_by_ifindex, + check_down], args=(cfg, )) ksft_exit() diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index 386ebd829df5..899dbad0104b 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -4304,14 +4304,7 @@ elif [ "$TESTS" = "ipv6" ]; then TESTS="$TESTS_IPV6" fi -# nettest can be run from PATH or from same directory as this selftest -if ! which nettest >/dev/null; then - PATH=$PWD:$PATH - if ! which nettest >/dev/null; then - echo "'nettest' command not found; skipping tests" - exit $ksft_skip - fi -fi +check_gen_prog "nettest" declare -i nfail=0 declare -i nsuccess=0 diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index ac0b2c6a5761..77c83d9508d3 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -78,7 +78,12 @@ log_test() else ret=1 nfail=$((nfail+1)) - printf "TEST: %-60s [FAIL]\n" "${msg}" + if [[ $rc -eq $ksft_skip ]]; then + printf "TEST: %-60s [SKIP]\n" "${msg}" + else + printf "TEST: %-60s [FAIL]\n" "${msg}" + fi + if [ "$VERBOSE" = "1" ]; then echo " rc=$rc, expected $expected" fi @@ -923,6 +928,29 @@ ipv6_grp_fcnal() ipv6_grp_refs log_test $? 0 "Nexthop group replace refcounts" + + # + # 16-bit weights. + # + run_cmd "$IP nexthop add id 62 via 2001:db8:91::2 dev veth1" + run_cmd "$IP nexthop add id 63 via 2001:db8:91::3 dev veth1" + run_cmd "$IP nexthop add id 64 via 2001:db8:91::4 dev veth1" + run_cmd "$IP nexthop add id 65 via 2001:db8:91::5 dev veth1" + run_cmd "$IP nexthop add id 66 dev veth1" + + run_cmd "$IP nexthop add id 103 group 62,1000" + if [[ $? == 0 ]]; then + local GRP="id 103 group 62,254/63,255/64,256/65,257/66,65535" + run_cmd "$IP nexthop replace $GRP" + check_nexthop "id 103" "$GRP" + rc=$? + else + rc=$ksft_skip + fi + + $IP nexthop flush >/dev/null 2>&1 + + log_test $rc 0 "16-bit weights" } ipv6_res_grp_fcnal() @@ -987,6 +1015,31 @@ ipv6_res_grp_fcnal() check_nexthop_bucket "list id 102" \ "id 102 index 0 nhid 63 id 102 index 1 nhid 62 id 102 index 2 nhid 62 id 102 index 3 nhid 62" log_test $? 0 "Nexthop buckets updated after replace - nECMP" + + # + # 16-bit weights. + # + run_cmd "$IP nexthop add id 62 via 2001:db8:91::2 dev veth1" + run_cmd "$IP nexthop add id 63 via 2001:db8:91::3 dev veth1" + run_cmd "$IP nexthop add id 64 via 2001:db8:91::4 dev veth1" + run_cmd "$IP nexthop add id 65 via 2001:db8:91::5 dev veth1" + run_cmd "$IP nexthop add id 66 dev veth1" + + run_cmd "$IP nexthop add id 103 group 62,1000 type resilient buckets 32" + if [[ $? == 0 ]]; then + local GRP="id 103 group 62,254/63,255/64,256/65,257/66,65535 $(: + )type resilient buckets 32 idle_timer 0 $(: + )unbalanced_timer 0" + run_cmd "$IP nexthop replace $GRP" + check_nexthop "id 103" "$GRP unbalanced_time 0" + rc=$? + else + rc=$ksft_skip + fi + + $IP nexthop flush >/dev/null 2>&1 + + log_test $rc 0 "16-bit weights" } ipv6_fcnal_runtime() diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh index 7c01f58a20de..53c5c1ad437e 100755 --- a/tools/testing/selftests/net/fib_rule_tests.sh +++ b/tools/testing/selftests/net/fib_rule_tests.sh @@ -35,18 +35,13 @@ log_test() local expected=$2 local msg="$3" - $IP rule show | grep -q l3mdev - if [ $? -eq 0 ]; then - msg="$msg (VRF)" - fi - if [ ${rc} -eq ${expected} ]; then nsuccess=$((nsuccess+1)) - printf "\n TEST: %-60s [ OK ]\n" "${msg}" + printf " TEST: %-60s [ OK ]\n" "${msg}" else ret=1 nfail=$((nfail+1)) - printf "\n TEST: %-60s [FAIL]\n" "${msg}" + printf " TEST: %-60s [FAIL]\n" "${msg}" if [ "${PAUSE_ON_FAIL}" = "yes" ]; then echo echo "hit enter to continue, 'q' to quit" @@ -56,39 +51,6 @@ log_test() fi } -log_section() -{ - echo - echo "######################################################################" - echo "TEST SECTION: $*" - echo "######################################################################" -} - -check_nettest() -{ - if which nettest > /dev/null 2>&1; then - return 0 - fi - - # Add the selftest directory to PATH if not already done - if [ "${SELFTEST_PATH}" = "" ]; then - SELFTEST_PATH="$(dirname $0)" - PATH="${PATH}:${SELFTEST_PATH}" - - # Now retry with the new path - if which nettest > /dev/null 2>&1; then - return 0 - fi - - if [ "${ret}" -eq 0 ]; then - ret="${ksft_skip}" - fi - echo "nettest not found (try 'make -C ${SELFTEST_PATH} nettest')" - fi - - return 1 -} - setup() { set -e @@ -187,12 +149,17 @@ fib_rule6_test_match_n_redirect() { local match="$1" local getmatch="$2" - local description="$3" + local getnomatch="$3" + local description="$4" + local nomatch_description="$5" $IP -6 rule add $match table $RTABLE $IP -6 route get $GW_IP6 $getmatch | grep -q "table $RTABLE" log_test $? 0 "rule6 check: $description" + $IP -6 route get $GW_IP6 $getnomatch 2>&1 | grep -q "table $RTABLE" + log_test $? 1 "rule6 check: $nomatch_description" + fib_rule6_del_by_pref "$match" log_test $? 0 "rule6 del by pref: $description" } @@ -213,18 +180,27 @@ fib_rule6_test_reject() fib_rule6_test() { + local ext_name=$1; shift + local getnomatch local getmatch local match local cnt + echo + echo "IPv6 FIB rule tests $ext_name" + # setup the fib rule redirect route $IP -6 route add table $RTABLE default via $GW_IP6 dev $DEV onlink match="oif $DEV" - fib_rule6_test_match_n_redirect "$match" "$match" "oif redirect to table" + getnomatch="oif lo" + fib_rule6_test_match_n_redirect "$match" "$match" "$getnomatch" \ + "oif redirect to table" "oif no redirect to table" match="from $SRC_IP6 iif $DEV" - fib_rule6_test_match_n_redirect "$match" "$match" "iif redirect to table" + getnomatch="from $SRC_IP6 iif lo" + fib_rule6_test_match_n_redirect "$match" "$match" "$getnomatch" \ + "iif redirect to table" "iif no redirect to table" # Reject dsfield (tos) options which have ECN bits set for cnt in $(seq 1 3); do @@ -238,44 +214,72 @@ fib_rule6_test() # Using option 'tos' instead of 'dsfield' as old iproute2 # versions don't support 'dsfield' in ip rule show. getmatch="tos $cnt" + getnomatch="tos 0x20" fib_rule6_test_match_n_redirect "$match" "$getmatch" \ - "$getmatch redirect to table" + "$getnomatch" "$getmatch redirect to table" \ + "$getnomatch no redirect to table" + done + + # Re-test TOS matching, but with input routes since they are handled + # differently from output routes. + match="tos 0x10" + for cnt in "0x10" "0x11" "0x12" "0x13"; do + getmatch="tos $cnt" + getnomatch="tos 0x20" + fib_rule6_test_match_n_redirect "$match" \ + "from $SRC_IP6 iif $DEV $getmatch" \ + "from $SRC_IP6 iif $DEV $getnomatch" \ + "iif $getmatch redirect to table" \ + "iif $getnomatch no redirect to table" done match="fwmark 0x64" getmatch="mark 0x64" - fib_rule6_test_match_n_redirect "$match" "$getmatch" "fwmark redirect to table" + getnomatch="mark 0x63" + fib_rule6_test_match_n_redirect "$match" "$getmatch" "$getnomatch" \ + "fwmark redirect to table" "fwmark no redirect to table" fib_check_iproute_support "uidrange" "uid" if [ $? -eq 0 ]; then match="uidrange 100-100" getmatch="uid 100" - fib_rule6_test_match_n_redirect "$match" "$getmatch" "uid redirect to table" + getnomatch="uid 101" + fib_rule6_test_match_n_redirect "$match" "$getmatch" \ + "$getnomatch" "uid redirect to table" \ + "uid no redirect to table" fi fib_check_iproute_support "sport" "sport" if [ $? -eq 0 ]; then match="sport 666 dport 777" - fib_rule6_test_match_n_redirect "$match" "$match" "sport and dport redirect to table" + getnomatch="sport 667 dport 778" + fib_rule6_test_match_n_redirect "$match" "$match" \ + "$getnomatch" "sport and dport redirect to table" \ + "sport and dport no redirect to table" fi fib_check_iproute_support "ipproto" "ipproto" if [ $? -eq 0 ]; then match="ipproto tcp" - fib_rule6_test_match_n_redirect "$match" "$match" "ipproto match" + getnomatch="ipproto udp" + fib_rule6_test_match_n_redirect "$match" "$match" \ + "$getnomatch" "ipproto tcp match" "ipproto udp no match" fi fib_check_iproute_support "ipproto" "ipproto" if [ $? -eq 0 ]; then match="ipproto ipv6-icmp" - fib_rule6_test_match_n_redirect "$match" "$match" "ipproto ipv6-icmp match" + getnomatch="ipproto tcp" + fib_rule6_test_match_n_redirect "$match" "$match" \ + "$getnomatch" "ipproto ipv6-icmp match" \ + "ipproto ipv6-tcp no match" fi } fib_rule6_vrf_test() { setup_vrf - fib_rule6_test + fib_rule6_test "- with VRF" cleanup_vrf } @@ -285,10 +289,8 @@ fib_rule6_connect_test() { local dsfield - if ! check_nettest; then - echo "SKIP: Could not run test without nettest tool" - return - fi + echo + echo "IPv6 FIB rule connect tests" setup_peer $IP -6 rule add dsfield 0x04 table $RTABLE_PEER @@ -306,6 +308,16 @@ fib_rule6_connect_test() log_test $? 0 "rule6 dsfield tcp connect (dsfield ${dsfield})" done + # Check that UDP and TCP connections fail when using a DS Field that + # does not match the previously configured FIB rule. + nettest -q -6 -B -t 5 -N $testns -O $peerns -U -D \ + -Q 0x20 -l 2001:db8::1:11 -r 2001:db8::1:11 + log_test $? 1 "rule6 dsfield udp no connect (dsfield 0x20)" + + nettest -q -6 -B -t 5 -N $testns -O $peerns -Q 0x20 \ + -l 2001:db8::1:11 -r 2001:db8::1:11 + log_test $? 1 "rule6 dsfield tcp no connect (dsfield 0x20)" + $IP -6 rule del dsfield 0x04 table $RTABLE_PEER cleanup_peer } @@ -326,12 +338,17 @@ fib_rule4_test_match_n_redirect() { local match="$1" local getmatch="$2" - local description="$3" + local getnomatch="$3" + local description="$4" + local nomatch_description="$5" $IP rule add $match table $RTABLE $IP route get $GW_IP4 $getmatch | grep -q "table $RTABLE" log_test $? 0 "rule4 check: $description" + $IP route get $GW_IP4 $getnomatch 2>&1 | grep -q "table $RTABLE" + log_test $? 1 "rule4 check: $nomatch_description" + fib_rule4_del_by_pref "$match" log_test $? 0 "rule4 del by pref: $description" } @@ -352,23 +369,31 @@ fib_rule4_test_reject() fib_rule4_test() { + local ext_name=$1; shift + local getnomatch local getmatch local match local cnt + echo + echo "IPv4 FIB rule tests $ext_name" + # setup the fib rule redirect route $IP route add table $RTABLE default via $GW_IP4 dev $DEV onlink match="oif $DEV" - fib_rule4_test_match_n_redirect "$match" "$match" "oif redirect to table" + getnomatch="oif lo" + fib_rule4_test_match_n_redirect "$match" "$match" "$getnomatch" \ + "oif redirect to table" "oif no redirect to table" - # need enable forwarding and disable rp_filter temporarily as all the - # addresses are in the same subnet and egress device == ingress device. + # Enable forwarding and disable rp_filter as all the addresses are in + # the same subnet and egress device == ingress device. ip netns exec $testns sysctl -qw net.ipv4.ip_forward=1 ip netns exec $testns sysctl -qw net.ipv4.conf.$DEV.rp_filter=0 match="from $SRC_IP iif $DEV" - fib_rule4_test_match_n_redirect "$match" "$match" "iif redirect to table" - ip netns exec $testns sysctl -qw net.ipv4.ip_forward=0 + getnomatch="from $SRC_IP iif lo" + fib_rule4_test_match_n_redirect "$match" "$match" "$getnomatch" \ + "iif redirect to table" "iif no redirect to table" # Reject dsfield (tos) options which have ECN bits set for cnt in $(seq 1 3); do @@ -382,44 +407,73 @@ fib_rule4_test() # Using option 'tos' instead of 'dsfield' as old iproute2 # versions don't support 'dsfield' in ip rule show. getmatch="tos $cnt" + getnomatch="tos 0x20" fib_rule4_test_match_n_redirect "$match" "$getmatch" \ - "$getmatch redirect to table" + "$getnomatch" "$getmatch redirect to table" \ + "$getnomatch no redirect to table" + done + + # Re-test TOS matching, but with input routes since they are handled + # differently from output routes. + match="tos 0x10" + for cnt in "0x10" "0x11" "0x12" "0x13"; do + getmatch="tos $cnt" + getnomatch="tos 0x20" + fib_rule4_test_match_n_redirect "$match" \ + "from $SRC_IP iif $DEV $getmatch" \ + "from $SRC_IP iif $DEV $getnomatch" \ + "iif $getmatch redirect to table" \ + "iif $getnomatch no redirect to table" done match="fwmark 0x64" getmatch="mark 0x64" - fib_rule4_test_match_n_redirect "$match" "$getmatch" "fwmark redirect to table" + getnomatch="mark 0x63" + fib_rule4_test_match_n_redirect "$match" "$getmatch" "$getnomatch" \ + "fwmark redirect to table" "fwmark no redirect to table" fib_check_iproute_support "uidrange" "uid" if [ $? -eq 0 ]; then match="uidrange 100-100" getmatch="uid 100" - fib_rule4_test_match_n_redirect "$match" "$getmatch" "uid redirect to table" + getnomatch="uid 101" + fib_rule4_test_match_n_redirect "$match" "$getmatch" \ + "$getnomatch" "uid redirect to table" \ + "uid no redirect to table" fi fib_check_iproute_support "sport" "sport" if [ $? -eq 0 ]; then match="sport 666 dport 777" - fib_rule4_test_match_n_redirect "$match" "$match" "sport and dport redirect to table" + getnomatch="sport 667 dport 778" + fib_rule4_test_match_n_redirect "$match" "$match" \ + "$getnomatch" "sport and dport redirect to table" \ + "sport and dport no redirect to table" fi fib_check_iproute_support "ipproto" "ipproto" if [ $? -eq 0 ]; then match="ipproto tcp" - fib_rule4_test_match_n_redirect "$match" "$match" "ipproto tcp match" + getnomatch="ipproto udp" + fib_rule4_test_match_n_redirect "$match" "$match" \ + "$getnomatch" "ipproto tcp match" \ + "ipproto udp no match" fi fib_check_iproute_support "ipproto" "ipproto" if [ $? -eq 0 ]; then match="ipproto icmp" - fib_rule4_test_match_n_redirect "$match" "$match" "ipproto icmp match" + getnomatch="ipproto tcp" + fib_rule4_test_match_n_redirect "$match" "$match" \ + "$getnomatch" "ipproto icmp match" \ + "ipproto tcp no match" fi } fib_rule4_vrf_test() { setup_vrf - fib_rule4_test + fib_rule4_test "- with VRF" cleanup_vrf } @@ -429,10 +483,8 @@ fib_rule4_connect_test() { local dsfield - if ! check_nettest; then - echo "SKIP: Could not run test without nettest tool" - return - fi + echo + echo "IPv4 FIB rule connect tests" setup_peer $IP -4 rule add dsfield 0x04 table $RTABLE_PEER @@ -450,17 +502,19 @@ fib_rule4_connect_test() log_test $? 0 "rule4 dsfield tcp connect (dsfield ${dsfield})" done + # Check that UDP and TCP connections fail when using a DS Field that + # does not match the previously configured FIB rule. + nettest -q -B -t 5 -N $testns -O $peerns -D -U -Q 0x20 \ + -l 198.51.100.11 -r 198.51.100.11 + log_test $? 1 "rule4 dsfield udp no connect (dsfield 0x20)" + + nettest -q -B -t 5 -N $testns -O $peerns -Q 0x20 \ + -l 198.51.100.11 -r 198.51.100.11 + log_test $? 1 "rule4 dsfield tcp no connect (dsfield 0x20)" + $IP -4 rule del dsfield 0x04 table $RTABLE_PEER cleanup_peer } - -run_fibrule_tests() -{ - log_section "IPv4 fib rule" - fib_rule4_test - log_section "IPv6 fib rule" - fib_rule6_test -} ################################################################################ # usage @@ -495,6 +549,8 @@ if [ ! -x "$(command -v ip)" ]; then exit $ksft_skip fi +check_gen_prog "nettest" + # start clean cleanup &> /dev/null setup diff --git a/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh b/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh index 1783c10215e5..7d531f7091e6 100755 --- a/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh +++ b/tools/testing/selftests/net/forwarding/custom_multipath_hash.sh @@ -224,10 +224,10 @@ send_dst_ipv6() send_flowlabel() { # Generate 16384 echo requests, each with a random flow label. - for _ in $(seq 1 16384); do - ip vrf exec v$h1 \ - $PING6 2001:db8:4::2 -F 0 -c 1 -q >/dev/null 2>&1 - done + ip vrf exec v$h1 sh -c \ + "for _ in {1..16384}; do \ + $PING6 2001:db8:4::2 -F 0 -c 1 -q >/dev/null 2>&1; \ + done" } send_src_udp6() diff --git a/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh b/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh index 9788bd0f6e8b..dda11a4a9450 100755 --- a/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh +++ b/tools/testing/selftests/net/forwarding/gre_custom_multipath_hash.sh @@ -319,10 +319,10 @@ send_dst_ipv6() send_flowlabel() { # Generate 16384 echo requests, each with a random flow label. - for _ in $(seq 1 16384); do - ip vrf exec v$h1 \ - $PING6 2001:db8:2::2 -F 0 -c 1 -q >/dev/null 2>&1 - done + ip vrf exec v$h1 sh -c \ + "for _ in {1..16384}; do \ + $PING6 2001:db8:2::2 -F 0 -c 1 -q >/dev/null 2>&1; \ + done" } send_src_udp6() diff --git a/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh b/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh index 2ab9eaaa5532..e28b4a079e52 100755 --- a/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh +++ b/tools/testing/selftests/net/forwarding/ip6gre_custom_multipath_hash.sh @@ -321,10 +321,10 @@ send_dst_ipv6() send_flowlabel() { # Generate 16384 echo requests, each with a random flow label. - for _ in $(seq 1 16384); do - ip vrf exec v$h1 \ - $PING6 2001:db8:2::2 -F 0 -c 1 -q >/dev/null 2>&1 - done + ip vrf exec v$h1 sh -c \ + "for _ in {1..16384}; do \ + $PING6 2001:db8:2::2 -F 0 -c 1 -q >/dev/null 2>&1; \ + done" } send_src_udp6() diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 718d04a4f72d..c992e385159c 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -514,6 +514,13 @@ xfail_on_slow() fi } +omit_on_slow() +{ + if [[ $KSFT_MACHINE_SLOW != yes ]]; then + "$@" + fi +} + xfail_on_veth() { local dev=$1; shift diff --git a/tools/testing/selftests/net/forwarding/router_mpath_nh.sh b/tools/testing/selftests/net/forwarding/router_mpath_nh.sh index 2ba44247c60a..a7d8399c8d4f 100755 --- a/tools/testing/selftests/net/forwarding/router_mpath_nh.sh +++ b/tools/testing/selftests/net/forwarding/router_mpath_nh.sh @@ -40,6 +40,7 @@ ALL_TESTS=" ping_ipv4 ping_ipv6 multipath_test + multipath16_test ping_ipv4_blackhole ping_ipv6_blackhole nh_stats_test_v4 @@ -226,9 +227,11 @@ routing_nh_obj() multipath4_test() { - local desc="$1" - local weight_rp12=$2 - local weight_rp13=$3 + local desc=$1; shift + local weight_rp12=$1; shift + local weight_rp13=$1; shift + local ports=${1-sp=1024,dp=0-32768}; shift + local t0_rp12 t0_rp13 t1_rp12 t1_rp13 local packets_rp12 packets_rp13 @@ -242,7 +245,8 @@ multipath4_test() t0_rp13=$(link_stats_tx_packets_get $rp13) ip vrf exec vrf-h1 $MZ $h1 -q -p 64 -A 192.0.2.2 -B 198.51.100.2 \ - -d $MZ_DELAY -t udp "sp=1024,dp=0-32768" + -d $MZ_DELAY -t udp "$ports" + sleep 1 t1_rp12=$(link_stats_tx_packets_get $rp12) t1_rp13=$(link_stats_tx_packets_get $rp13) @@ -258,9 +262,11 @@ multipath4_test() multipath6_test() { - local desc="$1" - local weight_rp12=$2 - local weight_rp13=$3 + local desc=$1; shift + local weight_rp12=$1; shift + local weight_rp13=$1; shift + local ports=${1-sp=1024,dp=0-32768}; shift + local t0_rp12 t0_rp13 t1_rp12 t1_rp13 local packets_rp12 packets_rp13 @@ -275,7 +281,8 @@ multipath6_test() t0_rp13=$(link_stats_tx_packets_get $rp13) $MZ $h1 -6 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:2::2 \ - -d $MZ_DELAY -t udp "sp=1024,dp=0-32768" + -d $MZ_DELAY -t udp "$ports" + sleep 1 t1_rp12=$(link_stats_tx_packets_get $rp12) t1_rp13=$(link_stats_tx_packets_get $rp13) @@ -313,6 +320,23 @@ multipath_test() multipath6_test "Weighted MP 11:45" 11 45 } +multipath16_test() +{ + check_nhgw16 104 || return + + log_info "Running 16-bit IPv4 multipath tests" + multipath4_test "65535:65535" 65535 65535 + multipath4_test "128:512" 128 512 + omit_on_slow \ + multipath4_test "255:65535" 255 65535 sp=1024-1026,dp=0-65535 + + log_info "Running 16-bit IPv6 multipath tests" + multipath6_test "65535:65535" 65535 65535 + multipath6_test "128:512" 128 512 + omit_on_slow \ + multipath6_test "255:65535" 255 65535 sp=1024-1026,dp=0-65535 +} + ping_ipv4_blackhole() { RET=0 diff --git a/tools/testing/selftests/net/forwarding/router_mpath_nh_lib.sh b/tools/testing/selftests/net/forwarding/router_mpath_nh_lib.sh index 2903294d8bca..507b2852dabe 100644 --- a/tools/testing/selftests/net/forwarding/router_mpath_nh_lib.sh +++ b/tools/testing/selftests/net/forwarding/router_mpath_nh_lib.sh @@ -117,3 +117,16 @@ __nh_stats_test_v6() $MZ -6 $h1 -A 2001:db8:1::2 -B 2001:db8:2::2 sysctl_restore net.ipv6.fib_multipath_hash_policy } + +check_nhgw16() +{ + local nhid=$1; shift + + ip nexthop replace id 9999 group "$nhid,65535" &>/dev/null + if (( $? )); then + log_test_skip "16-bit multipath tests" \ + "iproute2 or the kernel do not support 16-bit next hop weights" + return 1 + fi + ip nexthop del id 9999 ||: +} diff --git a/tools/testing/selftests/net/forwarding/router_mpath_nh_res.sh b/tools/testing/selftests/net/forwarding/router_mpath_nh_res.sh index cd9e346436fc..88ddae05b39d 100755 --- a/tools/testing/selftests/net/forwarding/router_mpath_nh_res.sh +++ b/tools/testing/selftests/net/forwarding/router_mpath_nh_res.sh @@ -40,6 +40,7 @@ ALL_TESTS=" ping_ipv4 ping_ipv6 multipath_test + multipath16_test nh_stats_test_v4 nh_stats_test_v6 " @@ -228,9 +229,11 @@ routing_nh_obj() multipath4_test() { - local desc="$1" - local weight_rp12=$2 - local weight_rp13=$3 + local desc=$1; shift + local weight_rp12=$1; shift + local weight_rp13=$1; shift + local ports=${1-sp=1024,dp=0-32768}; shift + local t0_rp12 t0_rp13 t1_rp12 t1_rp13 local packets_rp12 packets_rp13 @@ -243,7 +246,8 @@ multipath4_test() t0_rp13=$(link_stats_tx_packets_get $rp13) ip vrf exec vrf-h1 $MZ $h1 -q -p 64 -A 192.0.2.2 -B 198.51.100.2 \ - -d $MZ_DELAY -t udp "sp=1024,dp=0-32768" + -d $MZ_DELAY -t udp "$ports" + sleep 1 t1_rp12=$(link_stats_tx_packets_get $rp12) t1_rp13=$(link_stats_tx_packets_get $rp13) @@ -258,9 +262,11 @@ multipath4_test() multipath6_l4_test() { - local desc="$1" - local weight_rp12=$2 - local weight_rp13=$3 + local desc=$1; shift + local weight_rp12=$1; shift + local weight_rp13=$1; shift + local ports=${1-sp=1024,dp=0-32768}; shift + local t0_rp12 t0_rp13 t1_rp12 t1_rp13 local packets_rp12 packets_rp13 @@ -273,7 +279,8 @@ multipath6_l4_test() t0_rp13=$(link_stats_tx_packets_get $rp13) $MZ $h1 -6 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:2::2 \ - -d $MZ_DELAY -t udp "sp=1024,dp=0-32768" + -d $MZ_DELAY -t udp "$ports" + sleep 1 t1_rp12=$(link_stats_tx_packets_get $rp12) t1_rp13=$(link_stats_tx_packets_get $rp13) @@ -371,6 +378,41 @@ multipath_test() ip nexthop replace id 106 group 104,1/105,1 type resilient } +multipath16_test() +{ + check_nhgw16 104 || return + + log_info "Running 16-bit IPv4 multipath tests" + ip nexthop replace id 103 group 101/102 type resilient idle_timer 0 + + ip nexthop replace id 103 group 101,65535/102,65535 type resilient + multipath4_test "65535:65535" 65535 65535 + + ip nexthop replace id 103 group 101,128/102,512 type resilient + multipath4_test "128:512" 128 512 + + ip nexthop replace id 103 group 101,255/102,65535 type resilient + omit_on_slow \ + multipath4_test "255:65535" 255 65535 sp=1024-1026,dp=0-65535 + + ip nexthop replace id 103 group 101,1/102,1 type resilient + + log_info "Running 16-bit IPv6 L4 hash multipath tests" + ip nexthop replace id 106 group 104/105 type resilient idle_timer 0 + + ip nexthop replace id 106 group 104,65535/105,65535 type resilient + multipath6_l4_test "65535:65535" 65535 65535 + + ip nexthop replace id 106 group 104,128/105,512 type resilient + multipath6_l4_test "128:512" 128 512 + + ip nexthop replace id 106 group 104,255/105,65535 type resilient + omit_on_slow \ + multipath6_l4_test "255:65535" 255 65535 sp=1024-1026,dp=0-65535 + + ip nexthop replace id 106 group 104,1/105,1 type resilient +} + nh_stats_test_v4() { __nh_stats_test_v4 resilient diff --git a/tools/testing/selftests/net/forwarding/router_multipath.sh b/tools/testing/selftests/net/forwarding/router_multipath.sh index e2be354167a1..46f365b557b7 100755 --- a/tools/testing/selftests/net/forwarding/router_multipath.sh +++ b/tools/testing/selftests/net/forwarding/router_multipath.sh @@ -180,6 +180,7 @@ multipath4_test() ip vrf exec vrf-h1 $MZ $h1 -q -p 64 -A 192.0.2.2 -B 198.51.100.2 \ -d $MZ_DELAY -t udp "sp=1024,dp=0-32768" + sleep 1 t1_rp12=$(link_stats_tx_packets_get $rp12) t1_rp13=$(link_stats_tx_packets_get $rp13) @@ -217,6 +218,7 @@ multipath6_test() $MZ $h1 -6 -q -p 64 -A 2001:db8:1::2 -B 2001:db8:2::2 \ -d $MZ_DELAY -t udp "sp=1024,dp=0-32768" + sleep 1 t1_rp12=$(link_stats_tx_packets_get $rp12) t1_rp13=$(link_stats_tx_packets_get $rp13) diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh index 589629636502..ea89e558672d 100755 --- a/tools/testing/selftests/net/forwarding/tc_actions.sh +++ b/tools/testing/selftests/net/forwarding/tc_actions.sh @@ -4,7 +4,8 @@ ALL_TESTS="gact_drop_and_ok_test mirred_egress_redirect_test \ mirred_egress_mirror_test matchall_mirred_egress_mirror_test \ gact_trap_test mirred_egress_to_ingress_test \ - mirred_egress_to_ingress_tcp_test" + mirred_egress_to_ingress_tcp_test \ + ingress_2nd_vlan_push egress_2nd_vlan_push" NUM_NETIFS=4 source tc_common.sh source lib.sh @@ -244,6 +245,49 @@ mirred_egress_to_ingress_tcp_test() log_test "mirred_egress_to_ingress_tcp ($tcflags)" } +ingress_2nd_vlan_push() +{ + tc filter add dev $swp1 ingress pref 20 chain 0 handle 20 flower \ + $tcflags num_of_vlans 1 \ + action vlan push id 100 protocol 0x8100 action goto chain 5 + tc filter add dev $swp1 ingress pref 30 chain 5 handle 30 flower \ + $tcflags num_of_vlans 2 \ + cvlan_ethtype 0x800 action pass + + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ + -t ip -Q 10 -q + + tc_check_packets "dev $swp1 ingress" 30 1 + check_err $? "No double-vlan packets received" + + tc filter del dev $swp1 ingress pref 20 chain 0 handle 20 flower + tc filter del dev $swp1 ingress pref 30 chain 5 handle 30 flower + + log_test "ingress_2nd_vlan_push ($tcflags)" +} + +egress_2nd_vlan_push() +{ + tc filter add dev $h1 egress pref 20 chain 0 handle 20 flower \ + $tcflags num_of_vlans 0 \ + action vlan push id 10 protocol 0x8100 \ + pipe action vlan push id 100 protocol 0x8100 action goto chain 5 + tc filter add dev $h1 egress pref 30 chain 5 handle 30 flower \ + $tcflags num_of_vlans 2 \ + cvlan_ethtype 0x800 action pass + + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ + -t ip -q + + tc_check_packets "dev $h1 egress" 30 1 + check_err $? "No double-vlan packets received" + + tc filter del dev $h1 egress pref 20 chain 0 handle 20 flower + tc filter del dev $h1 egress pref 30 chain 5 handle 30 flower + + log_test "egress_2nd_vlan_push ($tcflags)" +} + setup_prepare() { h1=${NETIFS[p1]} diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index 8ee4489238ca..be8707bfb46e 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -125,6 +125,21 @@ slowwait_for_counter() slowwait "$timeout" until_counter_is ">= $((base + delta))" "$@" } +# Check for existence of tools which are built as part of selftests +# but may also already exist in $PATH +check_gen_prog() +{ + local prog_name=$1; shift + + if ! which $prog_name >/dev/null 2>/dev/null; then + PATH=$PWD:$PATH + if ! which $prog_name >/dev/null; then + echo "'$prog_name' command not found; skipping tests" + exit $ksft_skip + fi + fi +} + remove_ns_list() { local item=$1 diff --git a/tools/testing/selftests/net/lib/py/ksft.py b/tools/testing/selftests/net/lib/py/ksft.py index f26c20df9db4..477ae76de93d 100644 --- a/tools/testing/selftests/net/lib/py/ksft.py +++ b/tools/testing/selftests/net/lib/py/ksft.py @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 import builtins +import functools import inspect import sys import time @@ -10,6 +11,7 @@ from .utils import global_defer_queue KSFT_RESULT = None KSFT_RESULT_ALL = True +KSFT_DISRUPTIVE = True class KsftFailEx(Exception): @@ -32,8 +34,18 @@ def _fail(*args): global KSFT_RESULT KSFT_RESULT = False - frame = inspect.stack()[2] - ksft_pr("At " + frame.filename + " line " + str(frame.lineno) + ":") + stack = inspect.stack() + started = False + for frame in reversed(stack[2:]): + # Start printing from the test case function + if not started: + if frame.function == 'ksft_run': + started = True + continue + + ksft_pr("Check| At " + frame.filename + ", line " + str(frame.lineno) + + ", in " + frame.function + ":") + ksft_pr("Check| " + frame.code_context[0].strip()) ksft_pr(*args) @@ -43,6 +55,12 @@ def ksft_eq(a, b, comment=""): _fail("Check failed", a, "!=", b, comment) +def ksft_ne(a, b, comment=""): + global KSFT_RESULT + if a == b: + _fail("Check failed", a, "==", b, comment) + + def ksft_true(a, comment=""): if not a: _fail("Check failed", a, "does not eval to True", comment) @@ -127,6 +145,44 @@ def ksft_flush_defer(): KSFT_RESULT = False +def ksft_disruptive(func): + """ + Decorator that marks the test as disruptive (e.g. the test + that can down the interface). Disruptive tests can be skipped + by passing DISRUPTIVE=False environment variable. + """ + + @functools.wraps(func) + def wrapper(*args, **kwargs): + if not KSFT_DISRUPTIVE: + raise KsftSkipEx(f"marked as disruptive") + return func(*args, **kwargs) + return wrapper + + +def ksft_setup(env): + """ + Setup test framework global state from the environment. + """ + + def get_bool(env, name): + value = env.get(name, "").lower() + if value in ["yes", "true"]: + return True + if value in ["no", "false"]: + return False + try: + return bool(int(value)) + except: + raise Exception(f"failed to parse {name}") + + if "DISRUPTIVE" in env: + global KSFT_DISRUPTIVE + KSFT_DISRUPTIVE = get_bool(env, "DISRUPTIVE") + + return env + + def ksft_run(cases=None, globs=None, case_pfx=None, args=()): cases = cases or [] diff --git a/tools/testing/selftests/net/netdevice.sh b/tools/testing/selftests/net/netdevice.sh index e3afcb424710..438f7b2acc5f 100755 --- a/tools/testing/selftests/net/netdevice.sh +++ b/tools/testing/selftests/net/netdevice.sh @@ -67,8 +67,12 @@ kci_net_setup() return $ksft_skip fi - # TODO what ipaddr to set ? DHCP ? - echo "SKIP: $netdev: set IP address" + if [ "$veth_created" ]; then + echo "XFAIL: $netdev: set IP address unsupported for veth*" + else + # TODO what ipaddr to set ? DHCP ? + echo "SKIP: $netdev: set IP address" + fi return $ksft_skip } @@ -86,7 +90,7 @@ kci_netdev_ethtool_test() ret=$? if [ $ret -ne 0 ];then if [ $ret -eq "$1" ];then - echo "SKIP: $netdev: ethtool $2 not supported" + echo "XFAIL: $netdev: ethtool $2 not supported" return $ksft_skip else echo "FAIL: $netdev: ethtool $2" @@ -124,11 +128,45 @@ kci_netdev_ethtool() return 1 fi echo "PASS: $netdev: ethtool list features" - #TODO for each non fixed features, try to turn them on/off + + while read -r FEATURE VALUE FIXED; do + [ "$FEATURE" != "Features" ] || continue # Skip "Features" + [ "$FIXED" != "[fixed]" ] || continue # Skip fixed features + feature="${FEATURE%:*}" + + ethtool --offload "$netdev" "$feature" off + if [ $? -eq 0 ]; then + echo "PASS: $netdev: Turned off feature: $feature" + else + echo "FAIL: $netdev: Failed to turn off feature:" \ + "$feature" + fi + + ethtool --offload "$netdev" "$feature" on + if [ $? -eq 0 ]; then + echo "PASS: $netdev: Turned on feature: $feature" + else + echo "FAIL: $netdev: Failed to turn on feature:" \ + "$feature" + fi + + #restore the feature to its initial state + ethtool --offload "$netdev" "$feature" "$VALUE" + if [ $? -eq 0 ]; then + echo "PASS: $netdev: Restore feature $feature" \ + "to initial state $VALUE" + else + echo "FAIL: $netdev: Failed to restore feature" \ + "$feature to initial state $VALUE" + fi + + done < "$TMP_ETHTOOL_FEATURES" + rm "$TMP_ETHTOOL_FEATURES" kci_netdev_ethtool_test 74 'dump' "ethtool -d $netdev" kci_netdev_ethtool_test 94 'stats' "ethtool -S $netdev" + return 0 } @@ -196,10 +234,24 @@ if [ ! -e "$TMP_LIST_NETDEV" ];then fi ip link show |grep '^[0-9]' | grep -oE '[[:space:]].*eth[0-9]*:|[[:space:]].*enp[0-9]s[0-9]:' | cut -d\ -f2 | cut -d: -f1> "$TMP_LIST_NETDEV" + +if [ ! -s "$TMP_LIST_NETDEV" ]; then + echo "No valid network device found, creating veth pair" + ip link add veth0 type veth peer name veth1 + echo "veth0" > "$TMP_LIST_NETDEV" + veth_created=1 +fi + while read netdev do kci_test_netdev "$netdev" done < "$TMP_LIST_NETDEV" +#clean up veth interface pair if it was created +if [ "$veth_created" ]; then + ip link delete veth0 + echo "Removed veth pair" +fi + rm "$TMP_LIST_NETDEV" exit 0 diff --git a/tools/testing/selftests/net/netfilter/config b/tools/testing/selftests/net/netfilter/config index 63ef80ef47a4..b2dd4db45215 100644 --- a/tools/testing/selftests/net/netfilter/config +++ b/tools/testing/selftests/net/netfilter/config @@ -87,3 +87,5 @@ CONFIG_XFRM_USER=m CONFIG_XFRM_STATISTICS=y CONFIG_NET_PKTGEN=m CONFIG_TUN=m +CONFIG_INET_DIAG=m +CONFIG_SCTP_DIAG=m diff --git a/tools/testing/selftests/net/netfilter/nft_queue.sh b/tools/testing/selftests/net/netfilter/nft_queue.sh index c61d23a8c88d..9e5f423bff09 100755 --- a/tools/testing/selftests/net/netfilter/nft_queue.sh +++ b/tools/testing/selftests/net/netfilter/nft_queue.sh @@ -25,6 +25,9 @@ cleanup() } checktool "nft --version" "test without nft tool" +checktool "socat -h" "run test without socat" + +modprobe -q sctp trap cleanup EXIT @@ -36,7 +39,9 @@ TMPFILE2=$(mktemp) TMPFILE3=$(mktemp) TMPINPUT=$(mktemp) -dd conv=sparse status=none if=/dev/zero bs=1M count=200 of="$TMPINPUT" +COUNT=200 +[ "$KSFT_MACHINE_SLOW" = "yes" ] && COUNT=25 +dd conv=sparse status=none if=/dev/zero bs=1M count=$COUNT of="$TMPINPUT" if ! ip link add veth0 netns "$nsrouter" type veth peer name eth0 netns "$ns1" > /dev/null 2>&1; then echo "SKIP: No virtual ethernet pair device support in kernel" @@ -265,7 +270,6 @@ test_tcp_forward() test_tcp_localhost() { - dd conv=sparse status=none if=/dev/zero bs=1M count=200 of="$TMPINPUT" timeout 5 ip netns exec "$nsrouter" socat -u TCP-LISTEN:12345 STDOUT >/dev/null & local rpid=$! @@ -375,6 +379,82 @@ EOF wait 2>/dev/null } +sctp_listener_ready() +{ + ss -S -N "$1" -ln -o "sport = :12345" | grep -q 12345 +} + +test_sctp_forward() +{ + ip netns exec "$nsrouter" nft -f /dev/stdin <<EOF +flush ruleset +table inet sctpq { + chain forward { + type filter hook forward priority 0; policy accept; + sctp dport 12345 queue num 10 + } +} +EOF + timeout 60 ip netns exec "$ns2" socat -u SCTP-LISTEN:12345 STDOUT > "$TMPFILE1" & + local rpid=$! + + busywait "$BUSYWAIT_TIMEOUT" sctp_listener_ready "$ns2" + + ip netns exec "$nsrouter" ./nf_queue -q 10 -G -t "$timeout" & + local nfqpid=$! + + ip netns exec "$ns1" socat -u STDIN SCTP:10.0.2.99:12345 <"$TMPINPUT" >/dev/null + + if ! ip netns exec "$nsrouter" nft delete table inet sctpq; then + echo "FAIL: Could not delete sctpq table" + exit 1 + fi + + wait "$rpid" && echo "PASS: sctp and nfqueue in forward chain" + + if ! diff -u "$TMPINPUT" "$TMPFILE1" ; then + echo "FAIL: lost packets?!" 1>&2 + exit 1 + fi +} + +test_sctp_output() +{ + ip netns exec "$ns1" nft -f /dev/stdin <<EOF +table inet sctpq { + chain output { + type filter hook output priority 0; policy accept; + sctp dport 12345 queue num 11 + } +} +EOF + # reduce test file size, software segmentation causes sk wmem increase. + dd conv=sparse status=none if=/dev/zero bs=1M count=50 of="$TMPINPUT" + + timeout 60 ip netns exec "$ns2" socat -u SCTP-LISTEN:12345 STDOUT > "$TMPFILE1" & + local rpid=$! + + busywait "$BUSYWAIT_TIMEOUT" sctp_listener_ready "$ns2" + + ip netns exec "$ns1" ./nf_queue -q 11 -t "$timeout" & + local nfqpid=$! + + ip netns exec "$ns1" socat -u STDIN SCTP:10.0.2.99:12345 <"$TMPINPUT" >/dev/null + + if ! ip netns exec "$ns1" nft delete table inet sctpq; then + echo "FAIL: Could not delete sctpq table" + exit 1 + fi + + # must wait before checking completeness of output file. + wait "$rpid" && echo "PASS: sctp and nfqueue in output chain with GSO" + + if ! diff -u "$TMPINPUT" "$TMPFILE1" ; then + echo "FAIL: lost packets?!" 1>&2 + exit 1 + fi +} + test_queue_removal() { read tainted_then < /proc/sys/kernel/tainted @@ -443,11 +523,16 @@ test_queue 10 # same. We queue to a second program as well. load_ruleset "filter2" 20 test_queue 20 +ip netns exec "$ns1" nft flush ruleset test_tcp_forward test_tcp_localhost test_tcp_localhost_connectclose test_tcp_localhost_requeue +test_sctp_forward +test_sctp_output + +# should be last, adds vrf device in ns1 and changes routes test_icmp_vrf test_queue_removal diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index 5175c0c83a23..569bce8b6383 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -681,13 +681,7 @@ setup_xfrm() { } setup_nettest_xfrm() { - if ! which nettest >/dev/null; then - PATH=$PWD:$PATH - if ! which nettest >/dev/null; then - echo "'nettest' command not found; skipping tests" - return 1 - fi - fi + check_gen_prog "nettest" [ ${1} -eq 6 ] && proto="-6" || proto="" port=${2} @@ -1447,7 +1441,7 @@ test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception() { size=$(du -sb $tmpoutfile) size=${size%%/tmp/*} - [ $size -ne 1048576 ] && err "File size $size mismatches exepcted value in locally bridged vxlan test" && return 1 + [ $size -ne 1048576 ] && err "File size $size mismatches expected value in locally bridged vxlan test" && return 1 done rm -f "$tmpoutfile" diff --git a/tools/testing/selftests/net/rds/Makefile b/tools/testing/selftests/net/rds/Makefile new file mode 100644 index 000000000000..da9714bc7aad --- /dev/null +++ b/tools/testing/selftests/net/rds/Makefile @@ -0,0 +1,12 @@ +# SPDX-License-Identifier: GPL-2.0 + +all: + @echo mk_build_dir="$(shell pwd)" > include.sh + +TEST_PROGS := run.sh \ + include.sh \ + test.py + +EXTRA_CLEAN := /tmp/rds_logs + +include ../../lib.mk diff --git a/tools/testing/selftests/net/rds/README.txt b/tools/testing/selftests/net/rds/README.txt new file mode 100644 index 000000000000..cbde2951ab13 --- /dev/null +++ b/tools/testing/selftests/net/rds/README.txt @@ -0,0 +1,41 @@ +RDS self-tests +============== + +These scripts provide a coverage test for RDS-TCP by creating two +network namespaces and running rds packets between them. A loopback +network is provisioned with optional probability of packet loss or +corruption. A workload of 50000 hashes, each 64 characters in size, +are passed over an RDS socket on this test network. A passing test means +the RDS-TCP stack was able to recover properly. The provided config.sh +can be used to compile the kernel with the necessary gcov options. The +kernel may optionally be configured to omit the coverage report as well. + +USAGE: + run.sh [-d logdir] [-l packet_loss] [-c packet_corruption] + [-u packet_duplcate] + +OPTIONS: + -d Log directory. Defaults to tools/testing/selftests/net/rds/rds_logs + + -l Simulates a percentage of packet loss + + -c Simulates a percentage of packet corruption + + -u Simulates a percentage of packet duplication. + +EXAMPLE: + + # Create a suitable gcov enabled .config + tools/testing/selftests/net/rds/config.sh -g + + # Alternatly create a gcov disabled .config + tools/testing/selftests/net/rds/config.sh + + # build the kernel + vng --build --config tools/testing/selftests/net/config + + # launch the tests in a VM + vng -v --rwdir ./ --run . --user root --cpus 4 -- \ + "export PYTHONPATH=tools/testing/selftests/net/; tools/testing/selftests/net/rds/run.sh" + +An HTML coverage report will be output in tools/testing/selftests/net/rds/rds_logs/coverage/. diff --git a/tools/testing/selftests/net/rds/config.sh b/tools/testing/selftests/net/rds/config.sh new file mode 100755 index 000000000000..791c8dbe1095 --- /dev/null +++ b/tools/testing/selftests/net/rds/config.sh @@ -0,0 +1,53 @@ +#! /bin/bash +# SPDX-License-Identifier: GPL-2.0 + +set -e +set -u +set -x + +unset KBUILD_OUTPUT + +GENERATE_GCOV_REPORT=0 +while getopts "g" opt; do + case ${opt} in + g) + GENERATE_GCOV_REPORT=1 + ;; + :) + echo "USAGE: config.sh [-g]" + exit 1 + ;; + ?) + echo "Invalid option: -${OPTARG}." + exit 1 + ;; + esac +done + +CONF_FILE="tools/testing/selftests/net/config" + +# no modules +scripts/config --file "$CONF_FILE" --disable CONFIG_MODULES + +# enable RDS +scripts/config --file "$CONF_FILE" --enable CONFIG_RDS +scripts/config --file "$CONF_FILE" --enable CONFIG_RDS_TCP + +if [ "$GENERATE_GCOV_REPORT" -eq 1 ]; then + # instrument RDS and only RDS + scripts/config --file "$CONF_FILE" --enable CONFIG_GCOV_KERNEL + scripts/config --file "$CONF_FILE" --disable GCOV_PROFILE_ALL + scripts/config --file "$CONF_FILE" --enable GCOV_PROFILE_RDS +else + scripts/config --file "$CONF_FILE" --disable CONFIG_GCOV_KERNEL + scripts/config --file "$CONF_FILE" --disable GCOV_PROFILE_ALL + scripts/config --file "$CONF_FILE" --disable GCOV_PROFILE_RDS +fi + +# need network namespaces to run tests with veth network interfaces +scripts/config --file "$CONF_FILE" --enable CONFIG_NET_NS +scripts/config --file "$CONF_FILE" --enable CONFIG_VETH + +# simulate packet loss +scripts/config --file "$CONF_FILE" --enable CONFIG_NET_SCH_NETEM + diff --git a/tools/testing/selftests/net/rds/run.sh b/tools/testing/selftests/net/rds/run.sh new file mode 100755 index 000000000000..8aee244f582a --- /dev/null +++ b/tools/testing/selftests/net/rds/run.sh @@ -0,0 +1,224 @@ +#! /bin/bash +# SPDX-License-Identifier: GPL-2.0 + +set -e +set -u + +unset KBUILD_OUTPUT + +current_dir="$(realpath "$(dirname "$0")")" +build_dir="$current_dir" + +build_include="$current_dir/include.sh" +if test -f "$build_include"; then + # this include will define "$mk_build_dir" as the location the test was + # built. We will need this if the tests are installed in a location + # other than the kernel source + + source "$build_include" + build_dir="$mk_build_dir" +fi + +# This test requires kernel source and the *.gcda data therein +# Locate the top level of the kernel source, and the net/rds +# subfolder with the appropriate *.gcno object files +ksrc_dir="$(realpath "$build_dir"/../../../../../)" +kconfig="$ksrc_dir/.config" +obj_dir="$ksrc_dir/net/rds" + +GCOV_CMD=gcov + +#check to see if the host has the required packages to generate a gcov report +check_gcov_env() +{ + if ! which "$GCOV_CMD" > /dev/null 2>&1; then + echo "Warning: Could not find gcov. " + GENERATE_GCOV_REPORT=0 + return + fi + + # the gcov version must match the gcc version + GCC_VER=$(gcc -dumpfullversion) + GCOV_VER=$($GCOV_CMD -v | grep gcov | awk '{print $3}'| awk 'BEGIN {FS="-"}{print $1}') + if [ "$GCOV_VER" != "$GCC_VER" ]; then + #attempt to find a matching gcov version + GCOV_CMD=gcov-$(gcc -dumpversion) + + if ! which "$GCOV_CMD" > /dev/null 2>&1; then + echo "Warning: Could not find an appropriate gcov installation. \ + gcov version must match gcc version" + GENERATE_GCOV_REPORT=0 + return + fi + + #recheck version number of found gcov executable + GCOV_VER=$($GCOV_CMD -v | grep gcov | awk '{print $3}'| \ + awk 'BEGIN {FS="-"}{print $1}') + if [ "$GCOV_VER" != "$GCC_VER" ]; then + echo "Warning: Could not find an appropriate gcov installation. \ + gcov version must match gcc version" + GENERATE_GCOV_REPORT=0 + else + echo "Warning: Mismatched gcc and gcov detected. Using $GCOV_CMD" + fi + fi +} + +# Check to see if the kconfig has the required configs to generate a coverage report +check_gcov_conf() +{ + if ! grep -x "CONFIG_GCOV_PROFILE_RDS=y" "$kconfig" > /dev/null 2>&1; then + echo "INFO: CONFIG_GCOV_PROFILE_RDS should be enabled for coverage reports" + GENERATE_GCOV_REPORT=0 + fi + if ! grep -x "CONFIG_GCOV_KERNEL=y" "$kconfig" > /dev/null 2>&1; then + echo "INFO: CONFIG_GCOV_KERNEL should be enabled for coverage reports" + GENERATE_GCOV_REPORT=0 + fi + if grep -x "CONFIG_GCOV_PROFILE_ALL=y" "$kconfig" > /dev/null 2>&1; then + echo "INFO: CONFIG_GCOV_PROFILE_ALL should be disabled for coverage reports" + GENERATE_GCOV_REPORT=0 + fi + + if [ "$GENERATE_GCOV_REPORT" -eq 0 ]; then + echo "To enable gcov reports, please run "\ + "\"tools/testing/selftests/net/rds/config.sh -g\" and rebuild the kernel" + else + # if we have the required kernel configs, proceed to check the environment to + # ensure we have the required gcov packages + check_gcov_env + fi +} + +# Kselftest framework requirement - SKIP code is 4. +check_conf_enabled() { + if ! grep -x "$1=y" "$kconfig" > /dev/null 2>&1; then + echo "selftests: [SKIP] This test requires $1 enabled" + echo "Please run tools/testing/selftests/net/rds/config.sh and rebuild the kernel" + exit 4 + fi +} +check_conf_disabled() { + if grep -x "$1=y" "$kconfig" > /dev/null 2>&1; then + echo "selftests: [SKIP] This test requires $1 disabled" + echo "Please run tools/testing/selftests/net/rds/config.sh and rebuild the kernel" + exit 4 + fi +} +check_conf() { + check_conf_enabled CONFIG_NET_SCH_NETEM + check_conf_enabled CONFIG_VETH + check_conf_enabled CONFIG_NET_NS + check_conf_enabled CONFIG_RDS_TCP + check_conf_enabled CONFIG_RDS + check_conf_disabled CONFIG_MODULES +} + +check_env() +{ + if ! test -d "$obj_dir"; then + echo "selftests: [SKIP] This test requires a kernel source tree" + exit 4 + fi + if ! test -e "$kconfig"; then + echo "selftests: [SKIP] This test requires a configured kernel source tree" + exit 4 + fi + if ! which strace > /dev/null 2>&1; then + echo "selftests: [SKIP] Could not run test without strace" + exit 4 + fi + if ! which tcpdump > /dev/null 2>&1; then + echo "selftests: [SKIP] Could not run test without tcpdump" + exit 4 + fi + + if ! which python3 > /dev/null 2>&1; then + echo "selftests: [SKIP] Could not run test without python3" + exit 4 + fi + + python_major=$(python3 -c "import sys; print(sys.version_info[0])") + python_minor=$(python3 -c "import sys; print(sys.version_info[1])") + if [[ python_major -lt 3 || ( python_major -eq 3 && python_minor -lt 9 ) ]] ; then + echo "selftests: [SKIP] Could not run test without at least python3.9" + python3 -V + exit 4 + fi +} + +LOG_DIR="$current_dir"/rds_logs +PLOSS=0 +PCORRUPT=0 +PDUP=0 +GENERATE_GCOV_REPORT=1 +while getopts "d:l:c:u:" opt; do + case ${opt} in + d) + LOG_DIR=${OPTARG} + ;; + l) + PLOSS=${OPTARG} + ;; + c) + PCORRUPT=${OPTARG} + ;; + u) + PDUP=${OPTARG} + ;; + :) + echo "USAGE: run.sh [-d logdir] [-l packet_loss] [-c packet_corruption]" \ + "[-u packet_duplcate] [-g]" + exit 1 + ;; + ?) + echo "Invalid option: -${OPTARG}." + exit 1 + ;; + esac +done + + +check_env +check_conf +check_gcov_conf + + +rm -fr "$LOG_DIR" +TRACE_FILE="${LOG_DIR}/rds-strace.txt" +COVR_DIR="${LOG_DIR}/coverage/" +mkdir -p "$LOG_DIR" +mkdir -p "$COVR_DIR" + +set +e +echo running RDS tests... +echo Traces will be logged to "$TRACE_FILE" +rm -f "$TRACE_FILE" +strace -T -tt -o "$TRACE_FILE" python3 "$(dirname "$0")/test.py" --timeout 400 -d "$LOG_DIR" \ + -l "$PLOSS" -c "$PCORRUPT" -u "$PDUP" + +test_rc=$? +dmesg > "${LOG_DIR}/dmesg.out" + +if [ "$GENERATE_GCOV_REPORT" -eq 1 ]; then + echo saving coverage data... + (set +x; cd /sys/kernel/debug/gcov; find ./* -name '*.gcda' | \ + while read -r f + do + cat < "/sys/kernel/debug/gcov/$f" > "/$f" + done) + + echo running gcovr... + gcovr -s --html-details --gcov-executable "$GCOV_CMD" --gcov-ignore-parse-errors \ + -o "${COVR_DIR}/gcovr" "${ksrc_dir}/net/rds/" +else + echo "Coverage report will be skipped" +fi + +if [ "$test_rc" -eq 0 ]; then + echo "PASS: Test completed successfully" +else + echo "FAIL: Test failed" +fi + +exit "$test_rc" diff --git a/tools/testing/selftests/net/rds/test.py b/tools/testing/selftests/net/rds/test.py new file mode 100644 index 000000000000..e6bb109bcead --- /dev/null +++ b/tools/testing/selftests/net/rds/test.py @@ -0,0 +1,262 @@ +#! /usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +import argparse +import ctypes +import errno +import hashlib +import os +import select +import signal +import socket +import subprocess +import sys +import atexit +from pwd import getpwuid +from os import stat +from lib.py import ip + + +libc = ctypes.cdll.LoadLibrary('libc.so.6') +setns = libc.setns + +net0 = 'net0' +net1 = 'net1' + +veth0 = 'veth0' +veth1 = 'veth1' + +# Helper function for creating a socket inside a network namespace. +# We need this because otherwise RDS will detect that the two TCP +# sockets are on the same interface and use the loop transport instead +# of the TCP transport. +def netns_socket(netns, *args): + u0, u1 = socket.socketpair(socket.AF_UNIX, socket.SOCK_SEQPACKET) + + child = os.fork() + if child == 0: + # change network namespace + with open(f'/var/run/netns/{netns}') as f: + try: + ret = setns(f.fileno(), 0) + except IOError as e: + print(e.errno) + print(e) + + # create socket in target namespace + s = socket.socket(*args) + + # send resulting socket to parent + socket.send_fds(u0, [], [s.fileno()]) + + sys.exit(0) + + # receive socket from child + _, s, _, _ = socket.recv_fds(u1, 0, 1) + os.waitpid(child, 0) + u0.close() + u1.close() + return socket.fromfd(s[0], *args) + +def signal_handler(sig, frame): + print('Test timed out') + sys.exit(1) + +#Parse out command line arguments. We take an optional +# timeout parameter and an optional log output folder +parser = argparse.ArgumentParser(description="init script args", + formatter_class=argparse.ArgumentDefaultsHelpFormatter) +parser.add_argument("-d", "--logdir", action="store", + help="directory to store logs", default="/tmp") +parser.add_argument('--timeout', help="timeout to terminate hung test", + type=int, default=0) +parser.add_argument('-l', '--loss', help="Simulate tcp packet loss", + type=int, default=0) +parser.add_argument('-c', '--corruption', help="Simulate tcp packet corruption", + type=int, default=0) +parser.add_argument('-u', '--duplicate', help="Simulate tcp packet duplication", + type=int, default=0) +args = parser.parse_args() +logdir=args.logdir +packet_loss=str(args.loss)+'%' +packet_corruption=str(args.corruption)+'%' +packet_duplicate=str(args.duplicate)+'%' + +ip(f"netns add {net0}") +ip(f"netns add {net1}") +ip(f"link add type veth") + +addrs = [ + # we technically don't need different port numbers, but this will + # help identify traffic in the network analyzer + ('10.0.0.1', 10000), + ('10.0.0.2', 20000), +] + +# move interfaces to separate namespaces so they can no longer be +# bound directly; this prevents rds from switching over from the tcp +# transport to the loop transport. +ip(f"link set {veth0} netns {net0} up") +ip(f"link set {veth1} netns {net1} up") + + + +# add addresses +ip(f"-n {net0} addr add {addrs[0][0]}/32 dev {veth0}") +ip(f"-n {net1} addr add {addrs[1][0]}/32 dev {veth1}") + +# add routes +ip(f"-n {net0} route add {addrs[1][0]}/32 dev {veth0}") +ip(f"-n {net1} route add {addrs[0][0]}/32 dev {veth1}") + +# sanity check that our two interfaces/addresses are correctly set up +# and communicating by doing a single ping +ip(f"netns exec {net0} ping -c 1 {addrs[1][0]}") + +# Start a packet capture on each network +for net in [net0, net1]: + tcpdump_pid = os.fork() + if tcpdump_pid == 0: + pcap = logdir+'/'+net+'.pcap' + subprocess.check_call(['touch', pcap]) + user = getpwuid(stat(pcap).st_uid).pw_name + ip(f"netns exec {net} /usr/sbin/tcpdump -Z {user} -i any -w {pcap}") + sys.exit(0) + +# simulate packet loss, duplication and corruption +for net, iface in [(net0, veth0), (net1, veth1)]: + ip(f"netns exec {net} /usr/sbin/tc qdisc add dev {iface} root netem \ + corrupt {packet_corruption} loss {packet_loss} duplicate \ + {packet_duplicate}") + +# add a timeout +if args.timeout > 0: + signal.alarm(args.timeout) + signal.signal(signal.SIGALRM, signal_handler) + +sockets = [ + netns_socket(net0, socket.AF_RDS, socket.SOCK_SEQPACKET), + netns_socket(net1, socket.AF_RDS, socket.SOCK_SEQPACKET), +] + +for s, addr in zip(sockets, addrs): + s.bind(addr) + s.setblocking(0) + +fileno_to_socket = { + s.fileno(): s for s in sockets +} + +addr_to_socket = { + addr: s for addr, s in zip(addrs, sockets) +} + +socket_to_addr = { + s: addr for addr, s in zip(addrs, sockets) +} + +send_hashes = {} +recv_hashes = {} + +ep = select.epoll() + +for s in sockets: + ep.register(s, select.EPOLLRDNORM) + +n = 50000 +nr_send = 0 +nr_recv = 0 + +while nr_send < n: + # Send as much as we can without blocking + print("sending...", nr_send, nr_recv) + while nr_send < n: + send_data = hashlib.sha256( + f'packet {nr_send}'.encode('utf-8')).hexdigest().encode('utf-8') + + # pseudo-random send/receive pattern + sender = sockets[nr_send % 2] + receiver = sockets[1 - (nr_send % 3) % 2] + + try: + sender.sendto(send_data, socket_to_addr[receiver]) + send_hashes.setdefault((sender.fileno(), receiver.fileno()), + hashlib.sha256()).update(f'<{send_data}>'.encode('utf-8')) + nr_send = nr_send + 1 + except BlockingIOError as e: + break + except OSError as e: + if e.errno in [errno.ENOBUFS, errno.ECONNRESET, errno.EPIPE]: + break + raise + + # Receive as much as we can without blocking + print("receiving...", nr_send, nr_recv) + while nr_recv < nr_send: + for fileno, eventmask in ep.poll(): + receiver = fileno_to_socket[fileno] + + if eventmask & select.EPOLLRDNORM: + while True: + try: + recv_data, address = receiver.recvfrom(1024) + sender = addr_to_socket[address] + recv_hashes.setdefault((sender.fileno(), + receiver.fileno()), hashlib.sha256()).update( + f'<{recv_data}>'.encode('utf-8')) + nr_recv = nr_recv + 1 + except BlockingIOError as e: + break + + # exercise net/rds/tcp.c:rds_tcp_sysctl_reset() + for net in [net0, net1]: + ip(f"netns exec {net} /usr/sbin/sysctl net.rds.tcp.rds_tcp_rcvbuf=10000") + ip(f"netns exec {net} /usr/sbin/sysctl net.rds.tcp.rds_tcp_sndbuf=10000") + +print("done", nr_send, nr_recv) + +# the Python socket module doesn't know these +RDS_INFO_FIRST = 10000 +RDS_INFO_LAST = 10017 + +nr_success = 0 +nr_error = 0 + +for s in sockets: + for optname in range(RDS_INFO_FIRST, RDS_INFO_LAST + 1): + # Sigh, the Python socket module doesn't allow us to pass + # buffer lengths greater than 1024 for some reason. RDS + # wants multiple pages. + try: + s.getsockopt(socket.SOL_RDS, optname, 1024) + nr_success = nr_success + 1 + except OSError as e: + nr_error = nr_error + 1 + if e.errno == errno.ENOSPC: + # ignore + pass + +print(f"getsockopt(): {nr_success}/{nr_error}") + +print("Stopping network packet captures") +subprocess.check_call(['killall', '-q', 'tcpdump']) + +# We're done sending and receiving stuff, now let's check if what +# we received is what we sent. +for (sender, receiver), send_hash in send_hashes.items(): + recv_hash = recv_hashes.get((sender, receiver)) + + if recv_hash is None: + print("FAIL: No data received") + sys.exit(1) + + if send_hash.hexdigest() != recv_hash.hexdigest(): + print("FAIL: Send/recv mismatch") + print("hash expected:", send_hash.hexdigest()) + print("hash received:", recv_hash.hexdigest()) + sys.exit(1) + + print(f"{sender}/{receiver}: ok") + +print("Success") +sys.exit(0) diff --git a/tools/testing/selftests/net/tcp_ao/Makefile b/tools/testing/selftests/net/tcp_ao/Makefile index bd88b90b902b..5b0205c70c39 100644 --- a/tools/testing/selftests/net/tcp_ao/Makefile +++ b/tools/testing/selftests/net/tcp_ao/Makefile @@ -31,7 +31,8 @@ CFLAGS += $(KHDR_INCLUDES) CFLAGS += -iquote ./lib/ -I ../../../../include/ # Library -LIBSRC := kconfig.c netlink.c proc.c repair.c setup.c sock.c utils.c +LIBSRC := ftrace.c ftrace-tcp.c kconfig.c netlink.c +LIBSRC += proc.c repair.c setup.c sock.c utils.c LIBOBJ := $(LIBSRC:%.c=$(LIBDIR)/%.o) EXTRA_CLEAN += $(LIBOBJ) $(LIB) diff --git a/tools/testing/selftests/net/tcp_ao/bench-lookups.c b/tools/testing/selftests/net/tcp_ao/bench-lookups.c index a1e6e007c291..6736484996a3 100644 --- a/tools/testing/selftests/net/tcp_ao/bench-lookups.c +++ b/tools/testing/selftests/net/tcp_ao/bench-lookups.c @@ -355,6 +355,6 @@ static void *client_fn(void *arg) int main(int argc, char *argv[]) { - test_init(30, server_fn, client_fn); + test_init(31, server_fn, client_fn); return 0; } diff --git a/tools/testing/selftests/net/tcp_ao/config b/tools/testing/selftests/net/tcp_ao/config index d3277a9de987..3605e38711cb 100644 --- a/tools/testing/selftests/net/tcp_ao/config +++ b/tools/testing/selftests/net/tcp_ao/config @@ -7,4 +7,5 @@ CONFIG_NET_L3_MASTER_DEV=y CONFIG_NET_VRF=y CONFIG_TCP_AO=y CONFIG_TCP_MD5SIG=y +CONFIG_TRACEPOINTS=y CONFIG_VETH=m diff --git a/tools/testing/selftests/net/tcp_ao/connect-deny.c b/tools/testing/selftests/net/tcp_ao/connect-deny.c index 185a2f6e5ff3..d418162d335f 100644 --- a/tools/testing/selftests/net/tcp_ao/connect-deny.c +++ b/tools/testing/selftests/net/tcp_ao/connect-deny.c @@ -71,10 +71,12 @@ static void try_accept(const char *tst_name, unsigned int port, const char *pwd, } } + synchronize_threads(); /* before counter checks */ if (pwd && test_get_tcp_ao_counters(lsk, &ao_cnt2)) test_error("test_get_tcp_ao_counters()"); close(lsk); + if (pwd) test_tcp_ao_counters_cmp(tst_name, &ao_cnt1, &ao_cnt2, cnt_expected); @@ -84,10 +86,10 @@ static void try_accept(const char *tst_name, unsigned int port, const char *pwd, after_cnt = netstat_get_one(cnt_name, NULL); if (after_cnt <= before_cnt) { - test_fail("%s: %s counter did not increase: %zu <= %zu", + test_fail("%s: %s counter did not increase: %" PRIu64 " <= %" PRIu64, tst_name, cnt_name, after_cnt, before_cnt); } else { - test_ok("%s: counter %s increased %zu => %zu", + test_ok("%s: counter %s increased %" PRIu64 " => %" PRIu64, tst_name, cnt_name, before_cnt, after_cnt); } @@ -180,6 +182,7 @@ static void try_connect(const char *tst_name, unsigned int port, timeout = fault(TIMEOUT) ? TEST_RETRANSMIT_SEC : TEST_TIMEOUT_SEC; ret = _test_connect_socket(sk, this_ip_dest, port, timeout); + synchronize_threads(); /* before counter checks */ if (ret < 0) { if (fault(KEYREJECT) && ret == -EKEYREJECTED) { test_ok("%s: connect() was prevented", tst_name); @@ -212,30 +215,44 @@ out: static void *client_fn(void *arg) { - union tcp_addr wrong_addr, network_addr; + union tcp_addr wrong_addr, network_addr, addr_any = {}; unsigned int port = test_server_port; if (inet_pton(TEST_FAMILY, TEST_WRONG_IP, &wrong_addr) != 1) test_error("Can't convert ip address %s", TEST_WRONG_IP); + trace_ao_event_expect(TCP_AO_KEY_NOT_FOUND, this_ip_addr, this_ip_dest, + -1, port, 0, 0, 1, 0, 0, 0, 100, 100, -1); try_connect("Non-AO server + AO client", port++, DEFAULT_TEST_PASSWORD, this_ip_dest, -1, 100, 100, 0, FAULT_TIMEOUT); + trace_hash_event_expect(TCP_HASH_AO_REQUIRED, this_ip_addr, this_ip_dest, + -1, port, 0, 0, 1, 0, 0, 0); try_connect("AO server + Non-AO client", port++, NULL, this_ip_dest, -1, 100, 100, 0, FAULT_TIMEOUT); + trace_ao_event_expect(TCP_AO_MISMATCH, this_ip_addr, this_ip_dest, + -1, port, 0, 0, 1, 0, 0, 0, 100, 100, -1); try_connect("Wrong password", port++, DEFAULT_TEST_PASSWORD, this_ip_dest, -1, 100, 100, 0, FAULT_TIMEOUT); + trace_ao_event_expect(TCP_AO_KEY_NOT_FOUND, this_ip_addr, this_ip_dest, + -1, port, 0, 0, 1, 0, 0, 0, 100, 100, -1); try_connect("Wrong rcv id", port++, DEFAULT_TEST_PASSWORD, this_ip_dest, -1, 100, 100, 0, FAULT_TIMEOUT); + trace_ao_event_sk_expect(TCP_AO_SYNACK_NO_KEY, this_ip_dest, addr_any, + port, 0, 100, 100); try_connect("Wrong snd id", port++, DEFAULT_TEST_PASSWORD, this_ip_dest, -1, 100, 100, 0, FAULT_TIMEOUT); + trace_ao_event_expect(TCP_AO_WRONG_MACLEN, this_ip_addr, this_ip_dest, + -1, port, 0, 0, 1, 0, 0, 0, 100, 100, -1); try_connect("Different maclen", port++, DEFAULT_TEST_PASSWORD, this_ip_dest, -1, 100, 100, 0, FAULT_TIMEOUT); + trace_ao_event_expect(TCP_AO_KEY_NOT_FOUND, this_ip_addr, this_ip_dest, + -1, port, 0, 0, 1, 0, 0, 0, 100, 100, -1); try_connect("Server: Wrong addr", port++, DEFAULT_TEST_PASSWORD, this_ip_dest, -1, 100, 100, 0, FAULT_TIMEOUT); @@ -259,6 +276,6 @@ static void *client_fn(void *arg) int main(int argc, char *argv[]) { - test_init(21, server_fn, client_fn); + test_init(22, server_fn, client_fn); return 0; } diff --git a/tools/testing/selftests/net/tcp_ao/connect.c b/tools/testing/selftests/net/tcp_ao/connect.c index 81653b47f303..f1d8d29e393f 100644 --- a/tools/testing/selftests/net/tcp_ao/connect.c +++ b/tools/testing/selftests/net/tcp_ao/connect.c @@ -67,14 +67,14 @@ static void *client_fn(void *arg) netstat_free(ns_after); if (nr_packets > (after_aogood - before_aogood)) { - test_fail("TCPAOGood counter mismatch: %zu > (%zu - %zu)", + test_fail("TCPAOGood counter mismatch: %zu > (%" PRIu64 " - %" PRIu64 ")", nr_packets, after_aogood, before_aogood); return NULL; } if (test_tcp_ao_counters_cmp("connect", &ao1, &ao2, TEST_CNT_GOOD)) return NULL; - test_ok("connect TCPAOGood %" PRIu64 "/%" PRIu64 "/%" PRIu64 " => %" PRIu64 "/%" PRIu64 "/%" PRIu64 ", sent %" PRIu64, + test_ok("connect TCPAOGood %" PRIu64 "/%" PRIu64 "/%" PRIu64 " => %" PRIu64 "/%" PRIu64 "/%" PRIu64 ", sent %zu", before_aogood, ao1.ao_info_pkt_good, ao1.key_cnts[0].pkt_good, after_aogood, ao2.ao_info_pkt_good, @@ -85,6 +85,6 @@ static void *client_fn(void *arg) int main(int argc, char *argv[]) { - test_init(1, server_fn, client_fn); + test_init(2, server_fn, client_fn); return 0; } diff --git a/tools/testing/selftests/net/tcp_ao/icmps-discard.c b/tools/testing/selftests/net/tcp_ao/icmps-discard.c index d69bcba3c929..a1614f0d8c44 100644 --- a/tools/testing/selftests/net/tcp_ao/icmps-discard.c +++ b/tools/testing/selftests/net/tcp_ao/icmps-discard.c @@ -444,6 +444,6 @@ static void *client_fn(void *arg) int main(int argc, char *argv[]) { - test_init(3, server_fn, client_fn); + test_init(4, server_fn, client_fn); return 0; } diff --git a/tools/testing/selftests/net/tcp_ao/key-management.c b/tools/testing/selftests/net/tcp_ao/key-management.c index 24e62120b792..d4385b52c10b 100644 --- a/tools/testing/selftests/net/tcp_ao/key-management.c +++ b/tools/testing/selftests/net/tcp_ao/key-management.c @@ -965,7 +965,7 @@ static void end_client(const char *tst_name, int sk, unsigned int nr_keys, synchronize_threads(); /* 5: counters */ } -static void try_unmatched_keys(int sk, int *rnext_index) +static void try_unmatched_keys(int sk, int *rnext_index, unsigned int port) { struct test_key *key; unsigned int i = 0; @@ -1013,6 +1013,9 @@ static void try_unmatched_keys(int sk, int *rnext_index) test_error("all keys on server match the client"); if (test_set_key(sk, -1, key->server_keyid)) test_error("Can't change the current key"); + trace_ao_event_expect(TCP_AO_RNEXT_REQUEST, this_ip_addr, this_ip_dest, + -1, port, 0, -1, -1, -1, -1, -1, + -1, key->server_keyid, -1); if (test_client_verify(sk, msg_len, nr_packets, TEST_TIMEOUT_SEC)) test_fail("verify failed"); *rnext_index = i; @@ -1054,6 +1057,10 @@ static void check_current_back(const char *tst_name, unsigned int port, return; if (test_set_key(sk, collection.keys[rotate_to_index].client_keyid, -1)) test_error("Can't change the current key"); + trace_ao_event_expect(TCP_AO_RNEXT_REQUEST, this_ip_dest, this_ip_addr, + port, -1, 0, -1, -1, -1, -1, -1, + collection.keys[rotate_to_index].client_keyid, + collection.keys[current_index].client_keyid, -1); if (test_client_verify(sk, msg_len, nr_packets, TEST_TIMEOUT_SEC)) test_fail("verify failed"); /* There is a race here: between setting the current_key with @@ -1085,6 +1092,11 @@ static void roll_over_keys(const char *tst_name, unsigned int port, for (i = rnext_index + 1; rotations > 0; i++, rotations--) { if (i >= collection.nr_keys) i = 0; + trace_ao_event_expect(TCP_AO_RNEXT_REQUEST, + this_ip_addr, this_ip_dest, + -1, port, 0, -1, -1, -1, -1, -1, + i == 0 ? -1 : collection.keys[i - 1].server_keyid, + collection.keys[i].server_keyid, -1); if (test_set_key(sk, -1, collection.keys[i].server_keyid)) test_error("Can't change the Rnext key"); if (test_client_verify(sk, msg_len, nr_packets, TEST_TIMEOUT_SEC)) { @@ -1124,7 +1136,7 @@ static void try_client_match(const char *tst_name, unsigned int port, rnext_index, msg_len, nr_packets); if (sk < 0) return; - try_unmatched_keys(sk, &rnext_index); + try_unmatched_keys(sk, &rnext_index, port); end_client(tst_name, sk, nr_keys, current_index, rnext_index, NULL); } @@ -1181,6 +1193,6 @@ static void *client_fn(void *arg) int main(int argc, char *argv[]) { - test_init(120, server_fn, client_fn); + test_init(121, server_fn, client_fn); return 0; } diff --git a/tools/testing/selftests/net/tcp_ao/lib/aolib.h b/tools/testing/selftests/net/tcp_ao/lib/aolib.h index fbc7f6111815..db44e77428dd 100644 --- a/tools/testing/selftests/net/tcp_ao/lib/aolib.h +++ b/tools/testing/selftests/net/tcp_ao/lib/aolib.h @@ -37,17 +37,58 @@ extern void __test_xfail(const char *buf); extern void __test_error(const char *buf); extern void __test_skip(const char *buf); -__attribute__((__format__(__printf__, 2, 3))) -static inline void __test_print(void (*fn)(const char *), const char *fmt, ...) +static inline char *test_snprintf(const char *fmt, va_list vargs) { -#define TEST_MSG_BUFFER_SIZE 4096 - char buf[TEST_MSG_BUFFER_SIZE]; - va_list arg; - - va_start(arg, fmt); - vsnprintf(buf, sizeof(buf), fmt, arg); - va_end(arg); - fn(buf); + char *ret = NULL; + size_t size = 0; + va_list tmp; + int n = 0; + + va_copy(tmp, vargs); + n = vsnprintf(ret, size, fmt, tmp); + if (n < 0) + return NULL; + + size = n + 1; + ret = malloc(size); + if (!ret) + return NULL; + + n = vsnprintf(ret, size, fmt, vargs); + if (n < 0 || n > size - 1) { + free(ret); + return NULL; + } + return ret; +} + +static __printf(1, 2) inline char *test_sprintf(const char *fmt, ...) +{ + va_list vargs; + char *ret; + + va_start(vargs, fmt); + ret = test_snprintf(fmt, vargs); + va_end(vargs); + + return ret; +} + +static __printf(2, 3) inline void __test_print(void (*fn)(const char *), + const char *fmt, ...) +{ + va_list vargs; + char *msg; + + va_start(vargs, fmt); + msg = test_snprintf(fmt, vargs); + va_end(vargs); + + if (!msg) + return; + + fn(msg); + free(msg); } #define test_print(fmt, ...) \ @@ -103,6 +144,7 @@ enum test_needs_kconfig { KCONFIG_TCP_AO, /* required */ KCONFIG_TCP_MD5, /* optional, for TCP-MD5 features */ KCONFIG_NET_VRF, /* optional, for L3/VRF testing */ + KCONFIG_FTRACE, /* optional, for tracepoints checks */ __KCONFIG_LAST__ }; extern bool kernel_config_has(enum test_needs_kconfig k); @@ -142,6 +184,8 @@ static inline void test_init2(unsigned int ntests, __test_init(ntests, family, prefix, taddr1, taddr2, peer1, peer2); } extern void test_add_destructor(void (*d)(void)); +extern void test_init_ftrace(int nsfd1, int nsfd2); +extern int test_setup_tracing(void); /* To adjust optmem socket limit, approximately estimate a number, * that is bigger than sizeof(struct tcp_ao_key). @@ -216,12 +260,17 @@ static inline void test_init(unsigned int ntests, } extern void synchronize_threads(void); extern void switch_ns(int fd); +extern int switch_save_ns(int fd); +extern void switch_close_ns(int fd); extern __thread union tcp_addr this_ip_addr; extern __thread union tcp_addr this_ip_dest; extern int test_family; extern void randomize_buffer(void *buf, size_t buflen); +extern __printf(3, 4) int test_echo(const char *fname, bool append, + const char *fmt, ...); + extern int open_netns(void); extern int unshare_open_netns(void); extern const char veth_name[]; @@ -602,4 +651,115 @@ static inline int test_add_repaired_key(int sk, return test_verify_socket_key(sk, &tmp); } +#define DEFAULT_FTRACE_BUFFER_KB 10000 +#define DEFAULT_TRACER_LINES_ARR 200 +struct test_ftracer; +extern uint64_t ns_cookie1, ns_cookie2; + +enum ftracer_op { + FTRACER_LINE_DISCARD = 0, + FTRACER_LINE_PRESERVE, + FTRACER_EXIT, +}; + +extern struct test_ftracer *create_ftracer(const char *name, + enum ftracer_op (*process_line)(const char *line), + void (*destructor)(struct test_ftracer *tracer), + bool (*expecting_more)(void), + size_t lines_buf_sz, size_t buffer_size_kb); +extern int setup_trace_event(struct test_ftracer *tracer, + const char *event, const char *filter); +extern void destroy_ftracer(struct test_ftracer *tracer); +extern const size_t tracer_get_savedlines_nr(struct test_ftracer *tracer); +extern const char **tracer_get_savedlines(struct test_ftracer *tracer); + +enum trace_events { + /* TCP_HASH_EVENT */ + TCP_HASH_BAD_HEADER = 0, + TCP_HASH_MD5_REQUIRED, + TCP_HASH_MD5_UNEXPECTED, + TCP_HASH_MD5_MISMATCH, + TCP_HASH_AO_REQUIRED, + /* TCP_AO_EVENT */ + TCP_AO_HANDSHAKE_FAILURE, + TCP_AO_WRONG_MACLEN, + TCP_AO_MISMATCH, + TCP_AO_KEY_NOT_FOUND, + TCP_AO_RNEXT_REQUEST, + /* TCP_AO_EVENT_SK */ + TCP_AO_SYNACK_NO_KEY, + /* TCP_AO_EVENT_SNE */ + TCP_AO_SND_SNE_UPDATE, + TCP_AO_RCV_SNE_UPDATE, + __MAX_TRACE_EVENTS +}; + +extern int __trace_event_expect(enum trace_events type, int family, + union tcp_addr src, union tcp_addr dst, + int src_port, int dst_port, int L3index, + int fin, int syn, int rst, int psh, int ack, + int keyid, int rnext, int maclen, int sne); + +static inline void trace_hash_event_expect(enum trace_events type, + union tcp_addr src, union tcp_addr dst, + int src_port, int dst_port, int L3index, + int fin, int syn, int rst, int psh, int ack) +{ + int err; + + err = __trace_event_expect(type, TEST_FAMILY, src, dst, + src_port, dst_port, L3index, + fin, syn, rst, psh, ack, + -1, -1, -1, -1); + if (err) + test_error("Couldn't add a trace event: %d", err); +} + +static inline void trace_ao_event_expect(enum trace_events type, + union tcp_addr src, union tcp_addr dst, + int src_port, int dst_port, int L3index, + int fin, int syn, int rst, int psh, int ack, + int keyid, int rnext, int maclen) +{ + int err; + + err = __trace_event_expect(type, TEST_FAMILY, src, dst, + src_port, dst_port, L3index, + fin, syn, rst, psh, ack, + keyid, rnext, maclen, -1); + if (err) + test_error("Couldn't add a trace event: %d", err); +} + +static inline void trace_ao_event_sk_expect(enum trace_events type, + union tcp_addr src, union tcp_addr dst, + int src_port, int dst_port, + int keyid, int rnext) +{ + int err; + + err = __trace_event_expect(type, TEST_FAMILY, src, dst, + src_port, dst_port, -1, + -1, -1, -1, -1, -1, + keyid, rnext, -1, -1); + if (err) + test_error("Couldn't add a trace event: %d", err); +} + +static inline void trace_ao_event_sne_expect(enum trace_events type, + union tcp_addr src, union tcp_addr dst, + int src_port, int dst_port, int sne) +{ + int err; + + err = __trace_event_expect(type, TEST_FAMILY, src, dst, + src_port, dst_port, -1, + -1, -1, -1, -1, -1, + -1, -1, -1, sne); + if (err) + test_error("Couldn't add a trace event: %d", err); +} + +extern int setup_aolib_ftracer(void); + #endif /* _AOLIB_H_ */ diff --git a/tools/testing/selftests/net/tcp_ao/lib/ftrace-tcp.c b/tools/testing/selftests/net/tcp_ao/lib/ftrace-tcp.c new file mode 100644 index 000000000000..24380c68fec6 --- /dev/null +++ b/tools/testing/selftests/net/tcp_ao/lib/ftrace-tcp.c @@ -0,0 +1,559 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <inttypes.h> +#include <pthread.h> +#include "aolib.h" + +static const char *trace_event_names[__MAX_TRACE_EVENTS] = { + /* TCP_HASH_EVENT */ + "tcp_hash_bad_header", + "tcp_hash_md5_required", + "tcp_hash_md5_unexpected", + "tcp_hash_md5_mismatch", + "tcp_hash_ao_required", + /* TCP_AO_EVENT */ + "tcp_ao_handshake_failure", + "tcp_ao_wrong_maclen", + "tcp_ao_mismatch", + "tcp_ao_key_not_found", + "tcp_ao_rnext_request", + /* TCP_AO_EVENT_SK */ + "tcp_ao_synack_no_key", + /* TCP_AO_EVENT_SNE */ + "tcp_ao_snd_sne_update", + "tcp_ao_rcv_sne_update" +}; + +struct expected_trace_point { + /* required */ + enum trace_events type; + int family; + union tcp_addr src; + union tcp_addr dst; + + /* optional */ + int src_port; + int dst_port; + int L3index; + + int fin; + int syn; + int rst; + int psh; + int ack; + + int keyid; + int rnext; + int maclen; + int sne; + + size_t matched; +}; + +static struct expected_trace_point *exp_tps; +static size_t exp_tps_nr; +static size_t exp_tps_size; +static pthread_mutex_t exp_tps_mutex = PTHREAD_MUTEX_INITIALIZER; + +int __trace_event_expect(enum trace_events type, int family, + union tcp_addr src, union tcp_addr dst, + int src_port, int dst_port, int L3index, + int fin, int syn, int rst, int psh, int ack, + int keyid, int rnext, int maclen, int sne) +{ + struct expected_trace_point new_tp = { + .type = type, + .family = family, + .src = src, + .dst = dst, + .src_port = src_port, + .dst_port = dst_port, + .L3index = L3index, + .fin = fin, + .syn = syn, + .rst = rst, + .psh = psh, + .ack = ack, + .keyid = keyid, + .rnext = rnext, + .maclen = maclen, + .sne = sne, + .matched = 0, + }; + int ret = 0; + + if (!kernel_config_has(KCONFIG_FTRACE)) + return 0; + + pthread_mutex_lock(&exp_tps_mutex); + if (exp_tps_nr == exp_tps_size) { + struct expected_trace_point *tmp; + + if (exp_tps_size == 0) + exp_tps_size = 10; + else + exp_tps_size = exp_tps_size * 1.6; + + tmp = reallocarray(exp_tps, exp_tps_size, sizeof(exp_tps[0])); + if (!tmp) { + ret = -ENOMEM; + goto out; + } + exp_tps = tmp; + } + exp_tps[exp_tps_nr] = new_tp; + exp_tps_nr++; +out: + pthread_mutex_unlock(&exp_tps_mutex); + return ret; +} + +static void free_expected_events(void) +{ + /* We're from the process destructor - not taking the mutex */ + exp_tps_size = 0; + exp_tps = NULL; + free(exp_tps); +} + +struct trace_point { + int family; + union tcp_addr src; + union tcp_addr dst; + unsigned int src_port; + unsigned int dst_port; + int L3index; + unsigned int fin:1, + syn:1, + rst:1, + psh:1, + ack:1; + + unsigned int keyid; + unsigned int rnext; + unsigned int maclen; + + unsigned int sne; +}; + +static bool lookup_expected_event(int event_type, struct trace_point *e) +{ + size_t i; + + pthread_mutex_lock(&exp_tps_mutex); + for (i = 0; i < exp_tps_nr; i++) { + struct expected_trace_point *p = &exp_tps[i]; + size_t sk_size; + + if (p->type != event_type) + continue; + if (p->family != e->family) + continue; + if (p->family == AF_INET) + sk_size = sizeof(p->src.a4); + else + sk_size = sizeof(p->src.a6); + if (memcmp(&p->src, &e->src, sk_size)) + continue; + if (memcmp(&p->dst, &e->dst, sk_size)) + continue; + if (p->src_port >= 0 && p->src_port != e->src_port) + continue; + if (p->dst_port >= 0 && p->dst_port != e->dst_port) + continue; + if (p->L3index >= 0 && p->L3index != e->L3index) + continue; + + if (p->fin >= 0 && p->fin != e->fin) + continue; + if (p->syn >= 0 && p->syn != e->syn) + continue; + if (p->rst >= 0 && p->rst != e->rst) + continue; + if (p->psh >= 0 && p->psh != e->psh) + continue; + if (p->ack >= 0 && p->ack != e->ack) + continue; + + if (p->keyid >= 0 && p->keyid != e->keyid) + continue; + if (p->rnext >= 0 && p->rnext != e->rnext) + continue; + if (p->maclen >= 0 && p->maclen != e->maclen) + continue; + if (p->sne >= 0 && p->sne != e->sne) + continue; + p->matched++; + pthread_mutex_unlock(&exp_tps_mutex); + return true; + } + pthread_mutex_unlock(&exp_tps_mutex); + return false; +} + +static int check_event_type(const char *line) +{ + size_t i; + + /* + * This should have been a set or hashmap, but it's a selftest, + * so... KISS. + */ + for (i = 0; i < __MAX_TRACE_EVENTS; i++) { + if (!strncmp(trace_event_names[i], line, strlen(trace_event_names[i]))) + return i; + } + return -1; +} + +static bool event_has_flags(enum trace_events event) +{ + switch (event) { + case TCP_HASH_BAD_HEADER: + case TCP_HASH_MD5_REQUIRED: + case TCP_HASH_MD5_UNEXPECTED: + case TCP_HASH_MD5_MISMATCH: + case TCP_HASH_AO_REQUIRED: + case TCP_AO_HANDSHAKE_FAILURE: + case TCP_AO_WRONG_MACLEN: + case TCP_AO_MISMATCH: + case TCP_AO_KEY_NOT_FOUND: + case TCP_AO_RNEXT_REQUEST: + return true; + default: + return false; + } +} + +static int tracer_ip_split(int family, char *src, char **addr, char **port) +{ + char *p; + + if (family == AF_INET) { + /* fomat is <addr>:port, i.e.: 10.0.254.1:7015 */ + *addr = src; + p = strchr(src, ':'); + if (!p) { + test_print("Couldn't parse trace event addr:port %s", src); + return -EINVAL; + } + *p++ = '\0'; + *port = p; + return 0; + } + if (family != AF_INET6) + return -EAFNOSUPPORT; + + /* format is [<addr>]:port, i.e.: [2001:db8:254::1]:7013 */ + *addr = strchr(src, '['); + p = strchr(src, ']'); + + if (!p || !*addr) { + test_print("Couldn't parse trace event [addr]:port %s", src); + return -EINVAL; + } + + *addr = *addr + 1; /* '[' */ + *p++ = '\0'; /* ']' */ + if (*p != ':') { + test_print("Couldn't parse trace event :port %s", p); + return -EINVAL; + } + *p++ = '\0'; /* ':' */ + *port = p; + return 0; +} + +static int tracer_scan_address(int family, char *src, + union tcp_addr *dst, unsigned int *port) +{ + char *addr, *port_str; + int ret; + + ret = tracer_ip_split(family, src, &addr, &port_str); + if (ret) + return ret; + + if (inet_pton(family, addr, dst) != 1) { + test_print("Couldn't parse trace event addr %s", addr); + return -EINVAL; + } + errno = 0; + *port = (unsigned int)strtoul(port_str, NULL, 10); + if (errno != 0) { + test_print("Couldn't parse trace event port %s", port_str); + return -errno; + } + return 0; +} + +static int tracer_scan_event(const char *line, enum trace_events event, + struct trace_point *out) +{ + char *src = NULL, *dst = NULL, *family = NULL; + char fin, syn, rst, psh, ack; + int nr_matched, ret = 0; + uint64_t netns_cookie; + + switch (event) { + case TCP_HASH_BAD_HEADER: + case TCP_HASH_MD5_REQUIRED: + case TCP_HASH_MD5_UNEXPECTED: + case TCP_HASH_MD5_MISMATCH: + case TCP_HASH_AO_REQUIRED: { + nr_matched = sscanf(line, "%*s net=%" PRIu64 " state%*s family=%ms src=%ms dest=%ms L3index=%d [%c%c%c%c%c]", + &netns_cookie, &family, + &src, &dst, &out->L3index, + &fin, &syn, &rst, &psh, &ack); + if (nr_matched != 10) + test_print("Couldn't parse trace event, matched = %d/10", + nr_matched); + break; + } + case TCP_AO_HANDSHAKE_FAILURE: + case TCP_AO_WRONG_MACLEN: + case TCP_AO_MISMATCH: + case TCP_AO_KEY_NOT_FOUND: + case TCP_AO_RNEXT_REQUEST: { + nr_matched = sscanf(line, "%*s net=%" PRIu64 " state%*s family=%ms src=%ms dest=%ms L3index=%d [%c%c%c%c%c] keyid=%u rnext=%u maclen=%u", + &netns_cookie, &family, + &src, &dst, &out->L3index, + &fin, &syn, &rst, &psh, &ack, + &out->keyid, &out->rnext, &out->maclen); + if (nr_matched != 13) + test_print("Couldn't parse trace event, matched = %d/13", + nr_matched); + break; + } + case TCP_AO_SYNACK_NO_KEY: { + nr_matched = sscanf(line, "%*s net=%" PRIu64 " state%*s family=%ms src=%ms dest=%ms keyid=%u rnext=%u", + &netns_cookie, &family, + &src, &dst, &out->keyid, &out->rnext); + if (nr_matched != 6) + test_print("Couldn't parse trace event, matched = %d/6", + nr_matched); + break; + } + case TCP_AO_SND_SNE_UPDATE: + case TCP_AO_RCV_SNE_UPDATE: { + nr_matched = sscanf(line, "%*s net=%" PRIu64 " state%*s family=%ms src=%ms dest=%ms sne=%u", + &netns_cookie, &family, + &src, &dst, &out->sne); + if (nr_matched != 5) + test_print("Couldn't parse trace event, matched = %d/5", + nr_matched); + break; + } + default: + return -1; + } + + if (family) { + if (!strcmp(family, "AF_INET")) { + out->family = AF_INET; + } else if (!strcmp(family, "AF_INET6")) { + out->family = AF_INET6; + } else { + test_print("Couldn't parse trace event family %s", family); + ret = -EINVAL; + goto out_free; + } + } + + if (event_has_flags(event)) { + out->fin = (fin == 'F'); + out->syn = (syn == 'S'); + out->rst = (rst == 'R'); + out->psh = (psh == 'P'); + out->ack = (ack == '.'); + + if ((fin != 'F' && fin != ' ') || + (syn != 'S' && syn != ' ') || + (rst != 'R' && rst != ' ') || + (psh != 'P' && psh != ' ') || + (ack != '.' && ack != ' ')) { + test_print("Couldn't parse trace event flags %c%c%c%c%c", + fin, syn, rst, psh, ack); + ret = -EINVAL; + goto out_free; + } + } + + if (src && tracer_scan_address(out->family, src, &out->src, &out->src_port)) { + ret = -EINVAL; + goto out_free; + } + + if (dst && tracer_scan_address(out->family, dst, &out->dst, &out->dst_port)) { + ret = -EINVAL; + goto out_free; + } + + if (netns_cookie != ns_cookie1 && netns_cookie != ns_cookie2) { + test_print("Net namespace filter for trace event didn't work: %" PRIu64 " != %" PRIu64 " OR %" PRIu64, + netns_cookie, ns_cookie1, ns_cookie2); + ret = -EINVAL; + } + +out_free: + free(src); + free(dst); + free(family); + return ret; +} + +static enum ftracer_op aolib_tracer_process_event(const char *line) +{ + int event_type = check_event_type(line); + struct trace_point tmp = {}; + + if (event_type < 0) + return FTRACER_LINE_PRESERVE; + + if (tracer_scan_event(line, event_type, &tmp)) + return FTRACER_LINE_PRESERVE; + + return lookup_expected_event(event_type, &tmp) ? + FTRACER_LINE_DISCARD : FTRACER_LINE_PRESERVE; +} + +static void dump_trace_event(struct expected_trace_point *e) +{ + char src[INET6_ADDRSTRLEN], dst[INET6_ADDRSTRLEN]; + + if (!inet_ntop(e->family, &e->src, src, INET6_ADDRSTRLEN)) + test_error("inet_ntop()"); + if (!inet_ntop(e->family, &e->dst, dst, INET6_ADDRSTRLEN)) + test_error("inet_ntop()"); + test_print("trace event filter %s [%s:%d => %s:%d, L3index %d, flags: %s%s%s%s%s, keyid: %d, rnext: %d, maclen: %d, sne: %d] = %zu", + trace_event_names[e->type], + src, e->src_port, dst, e->dst_port, e->L3index, + (e->fin > 0) ? "F" : (e->fin == 0) ? "!F" : "", + (e->syn > 0) ? "S" : (e->syn == 0) ? "!S" : "", + (e->rst > 0) ? "R" : (e->rst == 0) ? "!R" : "", + (e->psh > 0) ? "P" : (e->psh == 0) ? "!P" : "", + (e->ack > 0) ? "." : (e->ack == 0) ? "!." : "", + e->keyid, e->rnext, e->maclen, e->sne, e->matched); +} + +static void print_match_stats(bool unexpected_events) +{ + size_t matches_per_type[__MAX_TRACE_EVENTS] = {}; + bool expected_but_none = false; + size_t i, total_matched = 0; + char *stat_line = NULL; + + for (i = 0; i < exp_tps_nr; i++) { + struct expected_trace_point *e = &exp_tps[i]; + + total_matched += e->matched; + matches_per_type[e->type] += e->matched; + if (!e->matched) + expected_but_none = true; + } + for (i = 0; i < __MAX_TRACE_EVENTS; i++) { + if (!matches_per_type[i]) + continue; + stat_line = test_sprintf("%s%s[%zu] ", stat_line ?: "", + trace_event_names[i], + matches_per_type[i]); + if (!stat_line) + test_error("test_sprintf()"); + } + + if (unexpected_events || expected_but_none) { + for (i = 0; i < exp_tps_nr; i++) + dump_trace_event(&exp_tps[i]); + } + + if (unexpected_events) + return; + + if (expected_but_none) + test_fail("Some trace events were expected, but didn't occur"); + else if (total_matched) + test_ok("Trace events matched expectations: %zu %s", + total_matched, stat_line); + else + test_ok("No unexpected trace events during the test run"); +} + +#define dump_events(fmt, ...) \ + __test_print(__test_msg, fmt, ##__VA_ARGS__) +static void check_free_events(struct test_ftracer *tracer) +{ + const char **lines; + size_t nr; + + if (!kernel_config_has(KCONFIG_FTRACE)) { + test_skip("kernel config doesn't have ftrace - no checks"); + return; + } + + nr = tracer_get_savedlines_nr(tracer); + lines = tracer_get_savedlines(tracer); + print_match_stats(!!nr); + if (!nr) + return; + + errno = 0; + test_xfail("Trace events [%zu] were not expected:", nr); + while (nr) + dump_events("\t%s", lines[--nr]); +} + +static int setup_tcp_trace_events(struct test_ftracer *tracer) +{ + char *filter; + size_t i; + int ret; + + filter = test_sprintf("net_cookie == %zu || net_cookie == %zu", + ns_cookie1, ns_cookie2); + if (!filter) + return -ENOMEM; + + for (i = 0; i < __MAX_TRACE_EVENTS; i++) { + char *event_name = test_sprintf("tcp/%s", trace_event_names[i]); + + if (!event_name) { + ret = -ENOMEM; + break; + } + ret = setup_trace_event(tracer, event_name, filter); + free(event_name); + if (ret) + break; + } + + free(filter); + return ret; +} + +static void aolib_tracer_destroy(struct test_ftracer *tracer) +{ + check_free_events(tracer); + free_expected_events(); +} + +static bool aolib_tracer_expecting_more(void) +{ + size_t i; + + for (i = 0; i < exp_tps_nr; i++) + if (!exp_tps[i].matched) + return true; + return false; +} + +int setup_aolib_ftracer(void) +{ + struct test_ftracer *f; + + f = create_ftracer("aolib", aolib_tracer_process_event, + aolib_tracer_destroy, aolib_tracer_expecting_more, + DEFAULT_FTRACE_BUFFER_KB, DEFAULT_TRACER_LINES_ARR); + if (!f) + return -1; + + return setup_tcp_trace_events(f); +} diff --git a/tools/testing/selftests/net/tcp_ao/lib/ftrace.c b/tools/testing/selftests/net/tcp_ao/lib/ftrace.c new file mode 100644 index 000000000000..e4d0b173bc94 --- /dev/null +++ b/tools/testing/selftests/net/tcp_ao/lib/ftrace.c @@ -0,0 +1,543 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <inttypes.h> +#include <pthread.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <sys/mount.h> +#include <sys/time.h> +#include <unistd.h> +#include "../../../../../include/linux/kernel.h" +#include "aolib.h" + +static char ftrace_path[] = "ksft-ftrace-XXXXXX"; +static bool ftrace_mounted; +uint64_t ns_cookie1, ns_cookie2; + +struct test_ftracer { + pthread_t tracer_thread; + int error; + char *instance_path; + FILE *trace_pipe; + + enum ftracer_op (*process_line)(const char *line); + void (*destructor)(struct test_ftracer *tracer); + bool (*expecting_more)(void); + + char **saved_lines; + size_t saved_lines_size; + size_t next_line_ind; + + pthread_cond_t met_all_expected; + pthread_mutex_t met_all_expected_lock; + + struct test_ftracer *next; +}; + +static struct test_ftracer *ftracers; +static pthread_mutex_t ftracers_lock = PTHREAD_MUTEX_INITIALIZER; + +static int mount_ftrace(void) +{ + if (!mkdtemp(ftrace_path)) + test_error("Can't create temp dir"); + + if (mount("tracefs", ftrace_path, "tracefs", 0, "rw")) + return -errno; + + ftrace_mounted = true; + + return 0; +} + +static void unmount_ftrace(void) +{ + if (ftrace_mounted && umount(ftrace_path)) + test_print("Failed on cleanup: can't unmount tracefs: %m"); + + if (rmdir(ftrace_path)) + test_error("Failed on cleanup: can't remove ftrace dir %s", + ftrace_path); +} + +struct opts_list_t { + char *opt_name; + struct opts_list_t *next; +}; + +static int disable_trace_options(const char *ftrace_path) +{ + struct opts_list_t *opts_list = NULL; + char *fopts, *line = NULL; + size_t buf_len = 0; + ssize_t line_len; + int ret = 0; + FILE *opts; + + fopts = test_sprintf("%s/%s", ftrace_path, "trace_options"); + if (!fopts) + return -ENOMEM; + + opts = fopen(fopts, "r+"); + if (!opts) { + ret = -errno; + goto out_free; + } + + while ((line_len = getline(&line, &buf_len, opts)) != -1) { + struct opts_list_t *tmp; + + if (!strncmp(line, "no", 2)) + continue; + + tmp = malloc(sizeof(*tmp)); + if (!tmp) { + ret = -ENOMEM; + goto out_free_opts_list; + } + tmp->next = opts_list; + tmp->opt_name = test_sprintf("no%s", line); + if (!tmp->opt_name) { + ret = -ENOMEM; + free(tmp); + goto out_free_opts_list; + } + opts_list = tmp; + } + + while (opts_list) { + struct opts_list_t *tmp = opts_list; + + fseek(opts, 0, SEEK_SET); + fwrite(tmp->opt_name, 1, strlen(tmp->opt_name), opts); + + opts_list = opts_list->next; + free(tmp->opt_name); + free(tmp); + } + +out_free_opts_list: + while (opts_list) { + struct opts_list_t *tmp = opts_list; + + opts_list = opts_list->next; + free(tmp->opt_name); + free(tmp); + } + free(line); + fclose(opts); +out_free: + free(fopts); + return ret; +} + +static int setup_buffer_size(const char *ftrace_path, size_t sz) +{ + char *fbuf_size = test_sprintf("%s/buffer_size_kb", ftrace_path); + int ret; + + if (!fbuf_size) + return -1; + + ret = test_echo(fbuf_size, 0, "%zu", sz); + free(fbuf_size); + return ret; +} + +static int setup_ftrace_instance(struct test_ftracer *tracer, const char *name) +{ + char *tmp; + + tmp = test_sprintf("%s/instances/ksft-%s-XXXXXX", ftrace_path, name); + if (!tmp) + return -ENOMEM; + + tracer->instance_path = mkdtemp(tmp); + if (!tracer->instance_path) { + free(tmp); + return -errno; + } + + return 0; +} + +static void remove_ftrace_instance(struct test_ftracer *tracer) +{ + if (rmdir(tracer->instance_path)) + test_print("Failed on cleanup: can't remove ftrace instance %s", + tracer->instance_path); + free(tracer->instance_path); +} + +static void tracer_cleanup(void *arg) +{ + struct test_ftracer *tracer = arg; + + fclose(tracer->trace_pipe); +} + +static void tracer_set_error(struct test_ftracer *tracer, int error) +{ + if (!tracer->error) + tracer->error = error; +} + +const size_t tracer_get_savedlines_nr(struct test_ftracer *tracer) +{ + return tracer->next_line_ind; +} + +const char **tracer_get_savedlines(struct test_ftracer *tracer) +{ + return (const char **)tracer->saved_lines; +} + +static void *tracer_thread_func(void *arg) +{ + struct test_ftracer *tracer = arg; + + pthread_cleanup_push(tracer_cleanup, arg); + + while (tracer->next_line_ind < tracer->saved_lines_size) { + char **lp = &tracer->saved_lines[tracer->next_line_ind]; + enum ftracer_op op; + size_t buf_len = 0; + ssize_t line_len; + + line_len = getline(lp, &buf_len, tracer->trace_pipe); + if (line_len == -1) + break; + + pthread_setcancelstate(PTHREAD_CANCEL_DISABLE, NULL); + op = tracer->process_line(*lp); + pthread_setcancelstate(PTHREAD_CANCEL_ENABLE, NULL); + + if (tracer->expecting_more) { + pthread_mutex_lock(&tracer->met_all_expected_lock); + if (!tracer->expecting_more()) + pthread_cond_signal(&tracer->met_all_expected); + pthread_mutex_unlock(&tracer->met_all_expected_lock); + } + + if (op == FTRACER_LINE_DISCARD) + continue; + if (op == FTRACER_EXIT) + break; + if (op != FTRACER_LINE_PRESERVE) + test_error("unexpected tracer command %d", op); + + tracer->next_line_ind++; + buf_len = 0; + } + test_print("too many lines in ftracer buffer %zu, exiting tracer", + tracer->next_line_ind); + + pthread_cleanup_pop(1); + return NULL; +} + +static int setup_trace_thread(struct test_ftracer *tracer) +{ + int ret = 0; + char *path; + + path = test_sprintf("%s/trace_pipe", tracer->instance_path); + if (!path) + return -ENOMEM; + + tracer->trace_pipe = fopen(path, "r"); + if (!tracer->trace_pipe) { + ret = -errno; + goto out_free; + } + + if (pthread_create(&tracer->tracer_thread, NULL, + tracer_thread_func, (void *)tracer)) { + ret = -errno; + fclose(tracer->trace_pipe); + } + +out_free: + free(path); + return ret; +} + +static void stop_trace_thread(struct test_ftracer *tracer) +{ + void *res; + + if (pthread_cancel(tracer->tracer_thread)) { + test_print("Can't stop tracer pthread: %m"); + tracer_set_error(tracer, -errno); + } + if (pthread_join(tracer->tracer_thread, &res)) { + test_print("Can't join tracer pthread: %m"); + tracer_set_error(tracer, -errno); + } + if (res != PTHREAD_CANCELED) { + test_print("Tracer thread wasn't canceled"); + tracer_set_error(tracer, -errno); + } + if (tracer->error) + test_fail("tracer errored by %s", strerror(tracer->error)); +} + +static void final_wait_for_events(struct test_ftracer *tracer, + unsigned timeout_sec) +{ + struct timespec timeout; + struct timeval now; + int ret = 0; + + if (!tracer->expecting_more) + return; + + pthread_mutex_lock(&tracer->met_all_expected_lock); + gettimeofday(&now, NULL); + timeout.tv_sec = now.tv_sec + timeout_sec; + timeout.tv_nsec = now.tv_usec * 1000; + + while (tracer->expecting_more() && ret != ETIMEDOUT) + ret = pthread_cond_timedwait(&tracer->met_all_expected, + &tracer->met_all_expected_lock, &timeout); + pthread_mutex_unlock(&tracer->met_all_expected_lock); +} + +int setup_trace_event(struct test_ftracer *tracer, + const char *event, const char *filter) +{ + char *enable_path, *filter_path, *instance = tracer->instance_path; + int ret; + + enable_path = test_sprintf("%s/events/%s/enable", instance, event); + if (!enable_path) + return -ENOMEM; + + filter_path = test_sprintf("%s/events/%s/filter", instance, event); + if (!filter_path) { + ret = -ENOMEM; + goto out_free; + } + + ret = test_echo(filter_path, 0, "%s", filter); + if (!ret) + ret = test_echo(enable_path, 0, "1"); + +out_free: + free(filter_path); + free(enable_path); + return ret; +} + +struct test_ftracer *create_ftracer(const char *name, + enum ftracer_op (*process_line)(const char *line), + void (*destructor)(struct test_ftracer *tracer), + bool (*expecting_more)(void), + size_t lines_buf_sz, size_t buffer_size_kb) +{ + struct test_ftracer *tracer; + int err; + + /* XXX: separate __create_ftracer() helper and do here + * if (!kernel_config_has(KCONFIG_FTRACE)) + * return NULL; + */ + + tracer = malloc(sizeof(*tracer)); + if (!tracer) { + test_print("malloc()"); + return NULL; + } + + memset(tracer, 0, sizeof(*tracer)); + + err = setup_ftrace_instance(tracer, name); + if (err) { + test_print("setup_ftrace_instance(): %d", err); + goto err_free; + } + + err = disable_trace_options(tracer->instance_path); + if (err) { + test_print("disable_trace_options(): %d", err); + goto err_remove; + } + + err = setup_buffer_size(tracer->instance_path, buffer_size_kb); + if (err) { + test_print("disable_trace_options(): %d", err); + goto err_remove; + } + + tracer->saved_lines = calloc(lines_buf_sz, sizeof(tracer->saved_lines[0])); + if (!tracer->saved_lines) { + test_print("calloc()"); + goto err_remove; + } + tracer->saved_lines_size = lines_buf_sz; + + tracer->process_line = process_line; + tracer->destructor = destructor; + tracer->expecting_more = expecting_more; + + err = pthread_cond_init(&tracer->met_all_expected, NULL); + if (err) { + test_print("pthread_cond_init(): %d", err); + goto err_free_lines; + } + + err = pthread_mutex_init(&tracer->met_all_expected_lock, NULL); + if (err) { + test_print("pthread_mutex_init(): %d", err); + goto err_cond_destroy; + } + + err = setup_trace_thread(tracer); + if (err) { + test_print("setup_trace_thread(): %d", err); + goto err_mutex_destroy; + } + + pthread_mutex_lock(&ftracers_lock); + tracer->next = ftracers; + ftracers = tracer; + pthread_mutex_unlock(&ftracers_lock); + + return tracer; + +err_mutex_destroy: + pthread_mutex_destroy(&tracer->met_all_expected_lock); +err_cond_destroy: + pthread_cond_destroy(&tracer->met_all_expected); +err_free_lines: + free(tracer->saved_lines); +err_remove: + remove_ftrace_instance(tracer); +err_free: + free(tracer); + return NULL; +} + +static void __destroy_ftracer(struct test_ftracer *tracer) +{ + size_t i; + + final_wait_for_events(tracer, TEST_TIMEOUT_SEC); + stop_trace_thread(tracer); + remove_ftrace_instance(tracer); + if (tracer->destructor) + tracer->destructor(tracer); + for (i = 0; i < tracer->saved_lines_size; i++) + free(tracer->saved_lines[i]); + pthread_cond_destroy(&tracer->met_all_expected); + pthread_mutex_destroy(&tracer->met_all_expected_lock); + free(tracer); +} + +void destroy_ftracer(struct test_ftracer *tracer) +{ + pthread_mutex_lock(&ftracers_lock); + if (tracer == ftracers) { + ftracers = tracer->next; + } else { + struct test_ftracer *f = ftracers; + + while (f->next != tracer) { + if (!f->next) + test_error("tracers list corruption or double free %p", tracer); + f = f->next; + } + f->next = tracer->next; + } + tracer->next = NULL; + pthread_mutex_unlock(&ftracers_lock); + __destroy_ftracer(tracer); +} + +static void destroy_all_ftracers(void) +{ + struct test_ftracer *f; + + pthread_mutex_lock(&ftracers_lock); + f = ftracers; + ftracers = NULL; + pthread_mutex_unlock(&ftracers_lock); + + while (f) { + struct test_ftracer *n = f->next; + + f->next = NULL; + __destroy_ftracer(f); + f = n; + } +} + +static void test_unset_tracing(void) +{ + destroy_all_ftracers(); + unmount_ftrace(); +} + +int test_setup_tracing(void) +{ + /* + * Just a basic protection - this should be called only once from + * lib/kconfig. Not thread safe, which is fine as it's early, before + * threads are created. + */ + static int already_set; + int err; + + if (already_set) + return -1; + + /* Needs net-namespace cookies for filters */ + if (ns_cookie1 == ns_cookie2) { + test_print("net-namespace cookies: %" PRIu64 " == %" PRIu64 ", can't set up tracing", + ns_cookie1, ns_cookie2); + return -1; + } + + already_set = 1; + + test_add_destructor(test_unset_tracing); + + err = mount_ftrace(); + if (err) { + test_print("failed to mount_ftrace(): %d", err); + return err; + } + + return setup_aolib_ftracer(); +} + +static int get_ns_cookie(int nsfd, uint64_t *out) +{ + int old_ns = switch_save_ns(nsfd); + socklen_t size = sizeof(*out); + int sk; + + sk = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP); + if (sk < 0) { + test_print("socket(): %m"); + return -errno; + } + + if (getsockopt(sk, SOL_SOCKET, SO_NETNS_COOKIE, out, &size)) { + test_print("getsockopt(SO_NETNS_COOKIE): %m"); + close(sk); + return -errno; + } + + close(sk); + switch_close_ns(old_ns); + return 0; +} + +void test_init_ftrace(int nsfd1, int nsfd2) +{ + get_ns_cookie(nsfd1, &ns_cookie1); + get_ns_cookie(nsfd2, &ns_cookie2); + /* Populate kernel config state */ + kernel_config_has(KCONFIG_FTRACE); +} diff --git a/tools/testing/selftests/net/tcp_ao/lib/kconfig.c b/tools/testing/selftests/net/tcp_ao/lib/kconfig.c index f279ffc3843b..9f1c175846f8 100644 --- a/tools/testing/selftests/net/tcp_ao/lib/kconfig.c +++ b/tools/testing/selftests/net/tcp_ao/lib/kconfig.c @@ -6,7 +6,7 @@ #include "aolib.h" struct kconfig_t { - int _errno; /* the returned error if not supported */ + int _error; /* negative errno if not supported */ int (*check_kconfig)(int *error); }; @@ -62,7 +62,7 @@ static int has_tcp_ao(int *err) memcpy(&tmp.addr, &addr, sizeof(addr)); *err = 0; if (setsockopt(sk, IPPROTO_TCP, TCP_AO_ADD_KEY, &tmp, sizeof(tmp)) < 0) { - *err = errno; + *err = -errno; if (errno != ENOPROTOOPT) ret = -errno; } @@ -87,7 +87,7 @@ static int has_tcp_md5(int *err) */ *err = 0; if (test_set_md5(sk, addr_any, 0, -1, DEFAULT_TEST_PASSWORD)) { - *err = errno; + *err = -errno; if (errno != ENOPROTOOPT && errno == ENOMEM) { test_print("setsockopt(TCP_MD5SIG_EXT): %m"); ret = -errno; @@ -116,13 +116,21 @@ static int has_vrfs(int *err) return ret; } +static int has_ftrace(int *err) +{ + *err = test_setup_tracing(); + return 0; +} + +#define KCONFIG_UNKNOWN 1 static pthread_mutex_t kconfig_lock = PTHREAD_MUTEX_INITIALIZER; static struct kconfig_t kconfig[__KCONFIG_LAST__] = { - { -1, has_net_ns }, - { -1, has_veth }, - { -1, has_tcp_ao }, - { -1, has_tcp_md5 }, - { -1, has_vrfs }, + { KCONFIG_UNKNOWN, has_net_ns }, + { KCONFIG_UNKNOWN, has_veth }, + { KCONFIG_UNKNOWN, has_tcp_ao }, + { KCONFIG_UNKNOWN, has_tcp_md5 }, + { KCONFIG_UNKNOWN, has_vrfs }, + { KCONFIG_UNKNOWN, has_ftrace }, }; const char *tests_skip_reason[__KCONFIG_LAST__] = { @@ -131,6 +139,7 @@ const char *tests_skip_reason[__KCONFIG_LAST__] = { "Tests require TCP-AO support (CONFIG_TCP_AO)", "setsockopt(TCP_MD5SIG_EXT) is not supported (CONFIG_TCP_MD5)", "VRFs are not supported (CONFIG_NET_VRF)", + "Ftrace points are not supported (CONFIG_TRACEPOINTS)", }; bool kernel_config_has(enum test_needs_kconfig k) @@ -138,11 +147,11 @@ bool kernel_config_has(enum test_needs_kconfig k) bool ret; pthread_mutex_lock(&kconfig_lock); - if (kconfig[k]._errno == -1) { - if (kconfig[k].check_kconfig(&kconfig[k]._errno)) + if (kconfig[k]._error == KCONFIG_UNKNOWN) { + if (kconfig[k].check_kconfig(&kconfig[k]._error)) test_error("Failed to initialize kconfig %u", k); } - ret = kconfig[k]._errno == 0; + ret = kconfig[k]._error == 0; pthread_mutex_unlock(&kconfig_lock); return ret; } diff --git a/tools/testing/selftests/net/tcp_ao/lib/setup.c b/tools/testing/selftests/net/tcp_ao/lib/setup.c index e408b9243b2c..a27cc03c9fbd 100644 --- a/tools/testing/selftests/net/tcp_ao/lib/setup.c +++ b/tools/testing/selftests/net/tcp_ao/lib/setup.c @@ -111,7 +111,7 @@ static void sig_int(int signo) int open_netns(void) { - const char *netns_path = "/proc/self/ns/net"; + const char *netns_path = "/proc/thread-self/ns/net"; int fd; fd = open(netns_path, O_RDONLY); @@ -142,6 +142,13 @@ int switch_save_ns(int new_ns) return ret; } +void switch_close_ns(int fd) +{ + if (setns(fd, CLONE_NEWNET)) + test_error("setns()"); + close(fd); +} + static int nsfd_outside = -1; static int nsfd_parent = -1; static int nsfd_child = -1; @@ -243,9 +250,9 @@ void __test_init(unsigned int ntests, int family, unsigned int prefix, test_print("rand seed %u", (unsigned int)seed); srand(seed); - ksft_print_header(); init_namespaces(); + test_init_ftrace(nsfd_parent, nsfd_child); if (add_veth(veth_name, nsfd_parent, nsfd_child)) test_error("Failed to add veth"); @@ -296,7 +303,7 @@ static bool is_optmem_namespaced(void) int old_ns = switch_save_ns(nsfd_child); optmem_ns = !access(optmem_file, F_OK); - switch_ns(old_ns); + switch_close_ns(old_ns); } return !!optmem_ns; } @@ -317,7 +324,7 @@ size_t test_get_optmem(void) test_error("can't read from %s", optmem_file); fclose(foptmem); if (!is_optmem_namespaced()) - switch_ns(old_ns); + switch_close_ns(old_ns); return ret; } @@ -339,7 +346,7 @@ static void __test_set_optmem(size_t new, size_t *old) test_error("can't write %zu to %s", new, optmem_file); fclose(foptmem); if (!is_optmem_namespaced()) - switch_ns(old_ns); + switch_close_ns(old_ns); } static void test_revert_optmem(void) diff --git a/tools/testing/selftests/net/tcp_ao/lib/sock.c b/tools/testing/selftests/net/tcp_ao/lib/sock.c index 15aeb0963058..0ffda966c677 100644 --- a/tools/testing/selftests/net/tcp_ao/lib/sock.c +++ b/tools/testing/selftests/net/tcp_ao/lib/sock.c @@ -379,7 +379,6 @@ int test_get_tcp_ao_counters(int sk, struct tcp_ao_counters *out) key_dump[0].nkeys = nr_keys; key_dump[0].get_all = 1; - key_dump[0].get_all = 1; err = getsockopt(sk, IPPROTO_TCP, TCP_AO_GET_KEYS, key_dump, &key_dump_sz); if (err) { diff --git a/tools/testing/selftests/net/tcp_ao/lib/utils.c b/tools/testing/selftests/net/tcp_ao/lib/utils.c index 372daca525f5..bdf5522c9213 100644 --- a/tools/testing/selftests/net/tcp_ao/lib/utils.c +++ b/tools/testing/selftests/net/tcp_ao/lib/utils.c @@ -21,6 +21,32 @@ void randomize_buffer(void *buf, size_t buflen) } } +__printf(3, 4) int test_echo(const char *fname, bool append, + const char *fmt, ...) +{ + size_t len, written; + va_list vargs; + char *msg; + FILE *f; + + f = fopen(fname, append ? "a" : "w"); + if (!f) + return -errno; + + va_start(vargs, fmt); + msg = test_snprintf(fmt, vargs); + va_end(vargs); + if (!msg) { + fclose(f); + return -1; + } + len = strlen(msg); + written = fwrite(msg, 1, len, f); + fclose(f); + free(msg); + return written == len ? 0 : -1; +} + const struct sockaddr_in6 addr_any6 = { .sin6_family = AF_INET6, }; diff --git a/tools/testing/selftests/net/tcp_ao/restore.c b/tools/testing/selftests/net/tcp_ao/restore.c index 8fdc808df325..ecc6f1e3a414 100644 --- a/tools/testing/selftests/net/tcp_ao/restore.c +++ b/tools/testing/selftests/net/tcp_ao/restore.c @@ -64,6 +64,7 @@ static void try_server_run(const char *tst_name, unsigned int port, else test_ok("%s: server alive", tst_name); } + synchronize_threads(); /* 3: counters checks */ if (test_get_tcp_ao_counters(sk, &ao2)) test_error("test_get_tcp_ao_counters()"); after_cnt = netstat_get_one(cnt_name, NULL); @@ -71,10 +72,10 @@ static void try_server_run(const char *tst_name, unsigned int port, test_tcp_ao_counters_cmp(tst_name, &ao1, &ao2, cnt_expected); if (after_cnt <= before_cnt) { - test_fail("%s: %s counter did not increase: %zu <= %zu", + test_fail("%s: %s counter did not increase: %" PRIu64 " <= %" PRIu64, tst_name, cnt_name, after_cnt, before_cnt); } else { - test_ok("%s: counter %s increased %zu => %zu", + test_ok("%s: counter %s increased %" PRIu64 " => %" PRIu64, tst_name, cnt_name, before_cnt, after_cnt); } @@ -82,7 +83,7 @@ static void try_server_run(const char *tst_name, unsigned int port, * Before close() as that will send FIN and move the peer in TCP_CLOSE * and that will prevent reading AO counters from the peer's socket. */ - synchronize_threads(); /* 3: verified => closed */ + synchronize_threads(); /* 4: verified => closed */ out: close(sk); } @@ -176,6 +177,7 @@ static void test_sk_restore(const char *tst_name, unsigned int server_port, else test_ok("%s: post-migrate connection is alive", tst_name); } + synchronize_threads(); /* 3: counters checks */ if (test_get_tcp_ao_counters(sk, &ao2)) test_error("test_get_tcp_ao_counters()"); after_cnt = netstat_get_one(cnt_name, NULL); @@ -183,13 +185,13 @@ static void test_sk_restore(const char *tst_name, unsigned int server_port, test_tcp_ao_counters_cmp(tst_name, &ao1, &ao2, cnt_expected); if (after_cnt <= before_cnt) { - test_fail("%s: %s counter did not increase: %zu <= %zu", + test_fail("%s: %s counter did not increase: %" PRIu64 " <= %" PRIu64, tst_name, cnt_name, after_cnt, before_cnt); } else { - test_ok("%s: counter %s increased %zu => %zu", + test_ok("%s: counter %s increased %" PRIu64 " => %" PRIu64, tst_name, cnt_name, before_cnt, after_cnt); } - synchronize_threads(); /* 3: verified => closed */ + synchronize_threads(); /* 4: verified => closed */ close(sk); } @@ -206,22 +208,36 @@ static void *client_fn(void *arg) test_get_sk_checkpoint(port, &saddr, &tcp_img, &ao_img); ao_img.snt_isn += 1; + trace_ao_event_expect(TCP_AO_MISMATCH, this_ip_addr, this_ip_dest, + -1, port, 0, -1, -1, -1, -1, -1, 100, 100, -1); + trace_ao_event_expect(TCP_AO_MISMATCH, this_ip_dest, this_ip_addr, + port, -1, 0, -1, -1, -1, -1, -1, 100, 100, -1); test_sk_restore("TCP-AO with wrong send ISN", port++, &saddr, &tcp_img, &ao_img, FAULT_TIMEOUT, TEST_CNT_BAD); test_get_sk_checkpoint(port, &saddr, &tcp_img, &ao_img); ao_img.rcv_isn += 1; + trace_ao_event_expect(TCP_AO_MISMATCH, this_ip_addr, this_ip_dest, + -1, port, 0, -1, -1, -1, -1, -1, 100, 100, -1); + trace_ao_event_expect(TCP_AO_MISMATCH, this_ip_dest, this_ip_addr, + port, -1, 0, -1, -1, -1, -1, -1, 100, 100, -1); test_sk_restore("TCP-AO with wrong receive ISN", port++, &saddr, &tcp_img, &ao_img, FAULT_TIMEOUT, TEST_CNT_BAD); test_get_sk_checkpoint(port, &saddr, &tcp_img, &ao_img); ao_img.snd_sne += 1; + trace_ao_event_expect(TCP_AO_MISMATCH, this_ip_addr, this_ip_dest, + -1, port, 0, -1, -1, -1, -1, -1, 100, 100, -1); + /* not expecting server => client mismatches as only snd sne is broken */ test_sk_restore("TCP-AO with wrong send SEQ ext number", port++, &saddr, &tcp_img, &ao_img, FAULT_TIMEOUT, TEST_CNT_NS_BAD | TEST_CNT_GOOD); test_get_sk_checkpoint(port, &saddr, &tcp_img, &ao_img); ao_img.rcv_sne += 1; + /* not expecting client => server mismatches as only rcv sne is broken */ + trace_ao_event_expect(TCP_AO_MISMATCH, this_ip_dest, this_ip_addr, + port, -1, 0, -1, -1, -1, -1, -1, 100, 100, -1); test_sk_restore("TCP-AO with wrong receive SEQ ext number", port++, &saddr, &tcp_img, &ao_img, FAULT_TIMEOUT, TEST_CNT_NS_GOOD | TEST_CNT_BAD); @@ -231,6 +247,6 @@ static void *client_fn(void *arg) int main(int argc, char *argv[]) { - test_init(20, server_fn, client_fn); + test_init(21, server_fn, client_fn); return 0; } diff --git a/tools/testing/selftests/net/tcp_ao/rst.c b/tools/testing/selftests/net/tcp_ao/rst.c index a2fe88d35ac0..6364facaa63e 100644 --- a/tools/testing/selftests/net/tcp_ao/rst.c +++ b/tools/testing/selftests/net/tcp_ao/rst.c @@ -455,6 +455,6 @@ static void *client_fn(void *arg) int main(int argc, char *argv[]) { - test_init(14, server_fn, client_fn); + test_init(15, server_fn, client_fn); return 0; } diff --git a/tools/testing/selftests/net/tcp_ao/self-connect.c b/tools/testing/selftests/net/tcp_ao/self-connect.c index a5698b0a3718..3ecd2b58de6a 100644 --- a/tools/testing/selftests/net/tcp_ao/self-connect.c +++ b/tools/testing/selftests/net/tcp_ao/self-connect.c @@ -87,7 +87,7 @@ static void tcp_self_connect(const char *tst, unsigned int port, netstat_free(ns_after); if (after_aogood <= before_aogood) { - test_fail("%s: TCPAOGood counter mismatch: %zu <= %zu", + test_fail("%s: TCPAOGood counter mismatch: %" PRIu64 " <= %" PRIu64, tst, after_aogood, before_aogood); close(sk); return; @@ -148,7 +148,7 @@ static void tcp_self_connect(const char *tst, unsigned int port, netstat_free(ns_after); close(sk); if (after_aogood <= before_aogood) { - test_fail("%s: TCPAOGood counter mismatch: %zu <= %zu", + test_fail("%s: TCPAOGood counter mismatch: %" PRIu64 " <= %" PRIu64, tst, after_aogood, before_aogood); return; } @@ -163,17 +163,26 @@ static void *client_fn(void *arg) setup_lo_intf("lo"); tcp_self_connect("self-connect(same keyids)", port++, false, false); + + /* expecting rnext to change based on the first segment RNext != Current */ + trace_ao_event_expect(TCP_AO_RNEXT_REQUEST, local_addr, local_addr, + port, port, 0, -1, -1, -1, -1, -1, 7, 5, -1); tcp_self_connect("self-connect(different keyids)", port++, true, false); tcp_self_connect("self-connect(restore)", port, false, true); - port += 2; + port += 2; /* restore test restores over different port */ + trace_ao_event_expect(TCP_AO_RNEXT_REQUEST, local_addr, local_addr, + port, port, 0, -1, -1, -1, -1, -1, 7, 5, -1); + /* intentionally on restore they are added to the socket in different order */ + trace_ao_event_expect(TCP_AO_RNEXT_REQUEST, local_addr, local_addr, + port + 1, port + 1, 0, -1, -1, -1, -1, -1, 5, 7, -1); tcp_self_connect("self-connect(restore, different keyids)", port, true, true); - port += 2; + port += 2; /* restore test restores over different port */ return NULL; } int main(int argc, char *argv[]) { - test_init(4, client_fn, NULL); + test_init(5, client_fn, NULL); return 0; } diff --git a/tools/testing/selftests/net/tcp_ao/seq-ext.c b/tools/testing/selftests/net/tcp_ao/seq-ext.c index ad4e77d6823e..8901a6785dc8 100644 --- a/tools/testing/selftests/net/tcp_ao/seq-ext.c +++ b/tools/testing/selftests/net/tcp_ao/seq-ext.c @@ -116,7 +116,15 @@ static void *server_fn(void *arg) sk = test_sk_restore(&img, &ao_img, &saddr, this_ip_dest, client_new_port, &ao1); - synchronize_threads(); /* 5: verify counters during SEQ-number rollover */ + trace_ao_event_sne_expect(TCP_AO_SND_SNE_UPDATE, this_ip_addr, + this_ip_dest, test_server_port + 1, client_new_port, 1); + trace_ao_event_sne_expect(TCP_AO_SND_SNE_UPDATE, this_ip_dest, + this_ip_addr, client_new_port, test_server_port + 1, 1); + trace_ao_event_sne_expect(TCP_AO_RCV_SNE_UPDATE, this_ip_addr, + this_ip_dest, test_server_port + 1, client_new_port, 1); + trace_ao_event_sne_expect(TCP_AO_RCV_SNE_UPDATE, this_ip_dest, + this_ip_addr, client_new_port, test_server_port + 1, 1); + synchronize_threads(); /* 5: verify the connection during SEQ-number rollover */ bytes = test_server_run(sk, quota, TEST_TIMEOUT_SEC); if (bytes != quota) { if (bytes > 0) @@ -127,6 +135,7 @@ static void *server_fn(void *arg) test_ok("server alive"); } + synchronize_threads(); /* 6: verify counters after SEQ-number rollover */ if (test_get_tcp_ao_counters(sk, &ao2)) test_error("test_get_tcp_ao_counters()"); after_good = netstat_get_one("TCPAOGood", NULL); @@ -134,15 +143,15 @@ static void *server_fn(void *arg) test_tcp_ao_counters_cmp(NULL, &ao1, &ao2, TEST_CNT_GOOD); if (after_good <= before_good) { - test_fail("TCPAOGood counter did not increase: %zu <= %zu", + test_fail("TCPAOGood counter did not increase: %" PRIu64 " <= %" PRIu64, after_good, before_good); } else { - test_ok("TCPAOGood counter increased %zu => %zu", + test_ok("TCPAOGood counter increased %" PRIu64 " => %" PRIu64, before_good, after_good); } after_bad = netstat_get_one("TCPAOBad", NULL); if (after_bad) - test_fail("TCPAOBad counter is non-zero: %zu", after_bad); + test_fail("TCPAOBad counter is non-zero: %" PRIu64, after_bad); else test_ok("TCPAOBad counter didn't increase"); test_enable_repair(sk); @@ -206,12 +215,13 @@ static void *client_fn(void *arg) sk = test_sk_restore(&img, &ao_img, &saddr, this_ip_dest, test_server_port + 1, &ao1); - synchronize_threads(); /* 5: verify counters during SEQ-number rollover */ + synchronize_threads(); /* 5: verify the connection during SEQ-number rollover */ if (test_client_verify(sk, msg_len, nr_packets, TEST_TIMEOUT_SEC)) test_fail("post-migrate verify failed"); else test_ok("post-migrate connection alive"); + synchronize_threads(); /* 5: verify counters after SEQ-number rollover */ if (test_get_tcp_ao_counters(sk, &ao2)) test_error("test_get_tcp_ao_counters()"); after_good = netstat_get_one("TCPAOGood", NULL); @@ -219,15 +229,15 @@ static void *client_fn(void *arg) test_tcp_ao_counters_cmp(NULL, &ao1, &ao2, TEST_CNT_GOOD); if (after_good <= before_good) { - test_fail("TCPAOGood counter did not increase: %zu <= %zu", + test_fail("TCPAOGood counter did not increase: %" PRIu64 " <= %" PRIu64, after_good, before_good); } else { - test_ok("TCPAOGood counter increased %zu => %zu", + test_ok("TCPAOGood counter increased %" PRIu64 " => %" PRIu64, before_good, after_good); } after_bad = netstat_get_one("TCPAOBad", NULL); if (after_bad) - test_fail("TCPAOBad counter is non-zero: %zu", after_bad); + test_fail("TCPAOBad counter is non-zero: %" PRIu64, after_bad); else test_ok("TCPAOBad counter didn't increase"); @@ -240,6 +250,6 @@ static void *client_fn(void *arg) int main(int argc, char *argv[]) { - test_init(7, server_fn, client_fn); + test_init(8, server_fn, client_fn); return 0; } diff --git a/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c b/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c index 517930f9721b..084db4ecdff6 100644 --- a/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c +++ b/tools/testing/selftests/net/tcp_ao/setsockopt-closed.c @@ -30,8 +30,8 @@ static void test_vefify_ao_info(int sk, struct tcp_ao_info_opt *info, #define __cmp_ao(member) \ do { \ if (info->member != tmp.member) { \ - test_fail("%s: getsockopt(): " __stringify(member) " %zu != %zu", \ - tst, (size_t)info->member, (size_t)tmp.member); \ + test_fail("%s: getsockopt(): " __stringify(member) " %" PRIu64 " != %" PRIu64, \ + tst, (uint64_t)info->member, (uint64_t)tmp.member); \ return; \ } \ } while(0) @@ -830,6 +830,6 @@ static void *client_fn(void *arg) int main(int argc, char *argv[]) { - test_init(120, client_fn, NULL); + test_init(121, client_fn, NULL); return 0; } diff --git a/tools/testing/selftests/net/tcp_ao/unsigned-md5.c b/tools/testing/selftests/net/tcp_ao/unsigned-md5.c index 6b59a652159f..f779e5892bc1 100644 --- a/tools/testing/selftests/net/tcp_ao/unsigned-md5.c +++ b/tools/testing/selftests/net/tcp_ao/unsigned-md5.c @@ -70,6 +70,7 @@ static void try_accept(const char *tst_name, unsigned int port, timeout = fault(TIMEOUT) ? TEST_RETRANSMIT_SEC : TEST_TIMEOUT_SEC; err = test_wait_fd(lsk, timeout, 0); + synchronize_threads(); /* connect()/accept() timeouts */ if (err == -ETIMEDOUT) { if (!fault(TIMEOUT)) test_fail("timed out for accept()"); @@ -100,10 +101,10 @@ static void try_accept(const char *tst_name, unsigned int port, after_cnt = netstat_get_one(cnt_name, NULL); if (after_cnt <= before_cnt) { - test_fail("%s: %s counter did not increase: %zu <= %zu", + test_fail("%s: %s counter did not increase: %" PRIu64 " <= %" PRIu64, tst_name, cnt_name, after_cnt, before_cnt); } else { - test_ok("%s: counter %s increased %zu => %zu", + test_ok("%s: counter %s increased %" PRIu64 " => %" PRIu64, tst_name, cnt_name, before_cnt, after_cnt); } if (ao_addr) @@ -283,6 +284,7 @@ static void try_connect(const char *tst_name, unsigned int port, timeout = fault(TIMEOUT) ? TEST_RETRANSMIT_SEC : TEST_TIMEOUT_SEC; ret = _test_connect_socket(sk, this_ip_dest, port, timeout); + synchronize_threads(); /* connect()/accept() timeouts */ if (ret < 0) { if (fault(KEYREJECT) && ret == -EKEYREJECTED) test_ok("%s: connect() was prevented", tst_name); @@ -451,6 +453,7 @@ static void try_to_add(const char *tst_name, unsigned int port, timeout = fault(TIMEOUT) ? TEST_RETRANSMIT_SEC : TEST_TIMEOUT_SEC; ret = _test_connect_socket(sk, this_ip_dest, port, timeout); + synchronize_threads(); /* connect()/accept() timeouts */ if (ret <= 0) { test_error("%s: connect() returned %d", tst_name, ret); goto out; @@ -671,24 +674,38 @@ static void *client_fn(void *arg) try_connect("AO server (INADDR_ANY): AO client", port++, NULL, 0, &addr_any, 0, 100, 100, 0, 0, 0, &this_ip_addr); + trace_hash_event_expect(TCP_HASH_MD5_UNEXPECTED, this_ip_addr, + this_ip_dest, -1, port, 0, 0, 1, 0, 0, 0); try_connect("AO server (INADDR_ANY): MD5 client", port++, &addr_any, 0, NULL, 0, 100, 100, 0, FAULT_TIMEOUT, 1, &this_ip_addr); + trace_hash_event_expect(TCP_HASH_AO_REQUIRED, this_ip_addr, + this_ip_dest, -1, port, 0, 0, 1, 0, 0, 0); try_connect("AO server (INADDR_ANY): unsigned client", port++, NULL, 0, NULL, 0, 100, 100, 0, FAULT_TIMEOUT, 0, &this_ip_addr); try_connect("AO server (AO_REQUIRED): AO client", port++, NULL, 0, &addr_any, 0, 100, 100, 0, 0, 0, &this_ip_addr); + trace_hash_event_expect(TCP_HASH_AO_REQUIRED, client2, + this_ip_dest, -1, port, 0, 0, 1, 0, 0, 0); try_connect("AO server (AO_REQUIRED): unsigned client", port++, NULL, 0, NULL, 0, 100, 100, 0, FAULT_TIMEOUT, 0, &client2); + trace_ao_event_expect(TCP_AO_KEY_NOT_FOUND, this_ip_addr, this_ip_dest, + -1, port, 0, 0, 1, 0, 0, 0, 100, 100, -1); try_connect("MD5 server (INADDR_ANY): AO client", port++, NULL, 0, &addr_any, 0, 100, 100, 0, FAULT_TIMEOUT, 1, &this_ip_addr); try_connect("MD5 server (INADDR_ANY): MD5 client", port++, &addr_any, 0, NULL, 0, 100, 100, 0, 0, 1, &this_ip_addr); + trace_hash_event_expect(TCP_HASH_MD5_REQUIRED, this_ip_addr, + this_ip_dest, -1, port, 0, 0, 1, 0, 0, 0); try_connect("MD5 server (INADDR_ANY): no sign client", port++, NULL, 0, NULL, 0, 100, 100, 0, FAULT_TIMEOUT, 1, &this_ip_addr); + trace_ao_event_expect(TCP_AO_KEY_NOT_FOUND, this_ip_addr, this_ip_dest, + -1, port, 0, 0, 1, 0, 0, 0, 100, 100, -1); try_connect("no sign server: AO client", port++, NULL, 0, &addr_any, 0, 100, 100, 0, FAULT_TIMEOUT, 0, &this_ip_addr); + trace_hash_event_expect(TCP_HASH_MD5_UNEXPECTED, this_ip_addr, + this_ip_dest, -1, port, 0, 0, 1, 0, 0, 0); try_connect("no sign server: MD5 client", port++, &addr_any, 0, NULL, 0, 100, 100, 0, FAULT_TIMEOUT, 1, &this_ip_addr); try_connect("no sign server: no sign client", port++, NULL, 0, @@ -696,25 +713,37 @@ static void *client_fn(void *arg) try_connect("AO+MD5 server: AO client (matching)", port++, NULL, 0, &addr_any, 0, 100, 100, 0, 0, 1, &client2); + trace_ao_event_expect(TCP_AO_KEY_NOT_FOUND, this_ip_addr, this_ip_dest, + -1, port, 0, 0, 1, 0, 0, 0, 100, 100, -1); try_connect("AO+MD5 server: AO client (misconfig, matching MD5)", port++, NULL, 0, &addr_any, 0, 100, 100, 0, FAULT_TIMEOUT, 1, &this_ip_addr); + trace_ao_event_expect(TCP_AO_KEY_NOT_FOUND, client3, this_ip_dest, + -1, port, 0, 0, 1, 0, 0, 0, 100, 100, -1); try_connect("AO+MD5 server: AO client (misconfig, non-matching)", port++, NULL, 0, &addr_any, 0, 100, 100, 0, FAULT_TIMEOUT, 1, &client3); try_connect("AO+MD5 server: MD5 client (matching)", port++, &addr_any, 0, NULL, 0, 100, 100, 0, 0, 1, &this_ip_addr); + trace_hash_event_expect(TCP_HASH_MD5_UNEXPECTED, client2, + this_ip_dest, -1, port, 0, 0, 1, 0, 0, 0); try_connect("AO+MD5 server: MD5 client (misconfig, matching AO)", port++, &addr_any, 0, NULL, 0, 100, 100, 0, FAULT_TIMEOUT, 1, &client2); + trace_hash_event_expect(TCP_HASH_MD5_UNEXPECTED, client3, + this_ip_dest, -1, port, 0, 0, 1, 0, 0, 0); try_connect("AO+MD5 server: MD5 client (misconfig, non-matching)", port++, &addr_any, 0, NULL, 0, 100, 100, 0, FAULT_TIMEOUT, 1, &client3); try_connect("AO+MD5 server: no sign client (unmatched)", port++, NULL, 0, NULL, 0, 100, 100, 0, 0, 1, &client3); + trace_hash_event_expect(TCP_HASH_AO_REQUIRED, client2, + this_ip_dest, -1, port, 0, 0, 1, 0, 0, 0); try_connect("AO+MD5 server: no sign client (misconfig, matching AO)", port++, NULL, 0, NULL, 0, 100, 100, 0, FAULT_TIMEOUT, 1, &client2); + trace_hash_event_expect(TCP_HASH_MD5_REQUIRED, this_ip_addr, + this_ip_dest, -1, port, 0, 0, 1, 0, 0, 0); try_connect("AO+MD5 server: no sign client (misconfig, matching MD5)", port++, NULL, 0, NULL, 0, 100, 100, 0, FAULT_TIMEOUT, 1, &this_ip_addr); @@ -736,6 +765,6 @@ static void *client_fn(void *arg) int main(int argc, char *argv[]) { - test_init(72, server_fn, client_fn); + test_init(73, server_fn, client_fn); return 0; } diff --git a/tools/testing/selftests/net/unicast_extensions.sh b/tools/testing/selftests/net/unicast_extensions.sh index f52aa5f7da52..3e751234ccfe 100755 --- a/tools/testing/selftests/net/unicast_extensions.sh +++ b/tools/testing/selftests/net/unicast_extensions.sh @@ -30,14 +30,7 @@ source lib.sh -# nettest can be run from PATH or from same directory as this selftest -if ! which nettest >/dev/null; then - PATH=$PWD:$PATH - if ! which nettest >/dev/null; then - echo "'nettest' command not found; skipping tests" - exit $ksft_skip - fi -fi +check_gen_prog "nettest" result=0 diff --git a/tools/testing/selftests/net/vrf_route_leaking.sh b/tools/testing/selftests/net/vrf_route_leaking.sh index 152171fb1fc8..e9c2f71da207 100755 --- a/tools/testing/selftests/net/vrf_route_leaking.sh +++ b/tools/testing/selftests/net/vrf_route_leaking.sh @@ -59,7 +59,6 @@ # while it is forwarded between different vrfs. source lib.sh -PATH=$PWD:$PWD/tools/testing/selftests/net:$PATH VERBOSE=0 PAUSE_ON_FAIL=no DEFAULT_TTYPE=sym @@ -636,6 +635,8 @@ EOF # Some systems don't have a ping6 binary anymore command -v ping6 > /dev/null 2>&1 && ping6=$(command -v ping6) || ping6=$(command -v ping) +check_gen_prog "nettest" + TESTS_IPV4="ipv4_ping_ttl ipv4_traceroute ipv4_ping_frag ipv4_ping_local ipv4_tcp_local ipv4_udp_local ipv4_ping_ttl_asym ipv4_traceroute_asym" TESTS_IPV6="ipv6_ping_ttl ipv6_traceroute ipv6_ping_local ipv6_tcp_local ipv6_udp_local diff --git a/tools/testing/vsock/util.c b/tools/testing/vsock/util.c index 554b290fefdc..a3d448a075e3 100644 --- a/tools/testing/vsock/util.c +++ b/tools/testing/vsock/util.c @@ -139,7 +139,7 @@ int vsock_bind_connect(unsigned int cid, unsigned int port, unsigned int bind_po } /* Connect to <cid, port> and return the file descriptor. */ -static int vsock_connect(unsigned int cid, unsigned int port, int type) +int vsock_connect(unsigned int cid, unsigned int port, int type) { union { struct sockaddr sa; @@ -226,8 +226,8 @@ static int vsock_listen(unsigned int cid, unsigned int port, int type) /* Listen on <cid, port> and return the first incoming connection. The remote * address is stored to clientaddrp. clientaddrp may be NULL. */ -static int vsock_accept(unsigned int cid, unsigned int port, - struct sockaddr_vm *clientaddrp, int type) +int vsock_accept(unsigned int cid, unsigned int port, + struct sockaddr_vm *clientaddrp, int type) { union { struct sockaddr sa; diff --git a/tools/testing/vsock/util.h b/tools/testing/vsock/util.h index e95e62485959..fff22d4a14c0 100644 --- a/tools/testing/vsock/util.h +++ b/tools/testing/vsock/util.h @@ -39,6 +39,9 @@ struct test_case { void init_signals(void); unsigned int parse_cid(const char *str); unsigned int parse_port(const char *str); +int vsock_connect(unsigned int cid, unsigned int port, int type); +int vsock_accept(unsigned int cid, unsigned int port, + struct sockaddr_vm *clientaddrp, int type); int vsock_stream_connect(unsigned int cid, unsigned int port); int vsock_bind_connect(unsigned int cid, unsigned int port, unsigned int bind_port, int type); diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c index f851f8961247..8d38dbf8f41f 100644 --- a/tools/testing/vsock/vsock_test.c +++ b/tools/testing/vsock/vsock_test.c @@ -20,6 +20,8 @@ #include <sys/mman.h> #include <poll.h> #include <signal.h> +#include <sys/ioctl.h> +#include <linux/sockios.h> #include "vsock_test_zerocopy.h" #include "timeout.h" @@ -1238,6 +1240,79 @@ static void test_double_bind_connect_client(const struct test_opts *opts) } } +#define MSG_BUF_IOCTL_LEN 64 +static void test_unsent_bytes_server(const struct test_opts *opts, int type) +{ + unsigned char buf[MSG_BUF_IOCTL_LEN]; + int client_fd; + + client_fd = vsock_accept(VMADDR_CID_ANY, opts->peer_port, NULL, type); + if (client_fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + recv_buf(client_fd, buf, sizeof(buf), 0, sizeof(buf)); + control_writeln("RECEIVED"); + + close(client_fd); +} + +static void test_unsent_bytes_client(const struct test_opts *opts, int type) +{ + unsigned char buf[MSG_BUF_IOCTL_LEN]; + int ret, fd, sock_bytes_unsent; + + fd = vsock_connect(opts->peer_cid, opts->peer_port, type); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + for (int i = 0; i < sizeof(buf); i++) + buf[i] = rand() & 0xFF; + + send_buf(fd, buf, sizeof(buf), 0, sizeof(buf)); + control_expectln("RECEIVED"); + + ret = ioctl(fd, SIOCOUTQ, &sock_bytes_unsent); + if (ret < 0) { + if (errno == EOPNOTSUPP) { + fprintf(stderr, "Test skipped, SIOCOUTQ not supported.\n"); + } else { + perror("ioctl"); + exit(EXIT_FAILURE); + } + } else if (ret == 0 && sock_bytes_unsent != 0) { + fprintf(stderr, + "Unexpected 'SIOCOUTQ' value, expected 0, got %i\n", + sock_bytes_unsent); + exit(EXIT_FAILURE); + } + + close(fd); +} + +static void test_stream_unsent_bytes_client(const struct test_opts *opts) +{ + test_unsent_bytes_client(opts, SOCK_STREAM); +} + +static void test_stream_unsent_bytes_server(const struct test_opts *opts) +{ + test_unsent_bytes_server(opts, SOCK_STREAM); +} + +static void test_seqpacket_unsent_bytes_client(const struct test_opts *opts) +{ + test_unsent_bytes_client(opts, SOCK_SEQPACKET); +} + +static void test_seqpacket_unsent_bytes_server(const struct test_opts *opts) +{ + test_unsent_bytes_server(opts, SOCK_SEQPACKET); +} + #define RCVLOWAT_CREDIT_UPD_BUF_SIZE (1024 * 128) /* This define is the same as in 'include/linux/virtio_vsock.h': * it is used to decide when to send credit update message during @@ -1523,6 +1598,16 @@ static struct test_case test_cases[] = { .run_client = test_stream_rcvlowat_def_cred_upd_client, .run_server = test_stream_cred_upd_on_low_rx_bytes, }, + { + .name = "SOCK_STREAM ioctl(SIOCOUTQ) 0 unsent bytes", + .run_client = test_stream_unsent_bytes_client, + .run_server = test_stream_unsent_bytes_server, + }, + { + .name = "SOCK_SEQPACKET ioctl(SIOCOUTQ) 0 unsent bytes", + .run_client = test_seqpacket_unsent_bytes_client, + .run_server = test_seqpacket_unsent_bytes_server, + }, {}, }; |