diff options
298 files changed, 4657 insertions, 5095 deletions
diff --git a/Documentation/devicetree/bindings/net/dsa/mediatek,mt7530.yaml b/Documentation/devicetree/bindings/net/dsa/mediatek,mt7530.yaml new file mode 100644 index 000000000000..a3bf432960d8 --- /dev/null +++ b/Documentation/devicetree/bindings/net/dsa/mediatek,mt7530.yaml @@ -0,0 +1,404 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/dsa/mediatek,mt7530.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Mediatek MT7530 Ethernet switch + +maintainers: + - Sean Wang <sean.wang@mediatek.com> + - Landen Chao <Landen.Chao@mediatek.com> + - DENG Qingfang <dqfext@gmail.com> + +description: | + Port 5 of mt7530 and mt7621 switch is muxed between: + 1. GMAC5: GMAC5 can interface with another external MAC or PHY. + 2. PHY of port 0 or port 4: PHY interfaces with an external MAC like 2nd GMAC + of the SOC. Used in many setups where port 0/4 becomes the WAN port. + Note: On a MT7621 SOC with integrated switch: 2nd GMAC can only connected to + GMAC5 when the gpios for RGMII2 (GPIO 22-33) are not used and not + connected to external component! + + Port 5 modes/configurations: + 1. Port 5 is disabled and isolated: An external phy can interface to the 2nd + GMAC of the SOC. + In the case of a build-in MT7530 switch, port 5 shares the RGMII bus with 2nd + GMAC and an optional external phy. Mind the GPIO/pinctl settings of the SOC! + 2. Port 5 is muxed to PHY of port 0/4: Port 0/4 interfaces with 2nd GMAC. + It is a simple MAC to PHY interface, port 5 needs to be setup for xMII mode + and RGMII delay. + 3. Port 5 is muxed to GMAC5 and can interface to an external phy. + Port 5 becomes an extra switch port. + Only works on platform where external phy TX<->RX lines are swapped. + Like in the Ubiquiti ER-X-SFP. + 4. Port 5 is muxed to GMAC5 and interfaces with the 2nd GAMC as 2nd CPU port. + Currently a 2nd CPU port is not supported by DSA code. + + Depending on how the external PHY is wired: + 1. normal: The PHY can only connect to 2nd GMAC but not to the switch + 2. swapped: RGMII TX, RX are swapped; external phy interface with the switch as + a ethernet port. But can't interface to the 2nd GMAC. + + Based on the DT the port 5 mode is configured. + + Driver tries to lookup the phy-handle of the 2nd GMAC of the master device. + When phy-handle matches PHY of port 0 or 4 then port 5 set-up as mode 2. + phy-mode must be set, see also example 2 below! + * mt7621: phy-mode = "rgmii-txid"; + * mt7623: phy-mode = "rgmii"; + + CPU-Ports need a phy-mode property: + Allowed values on mt7530 and mt7621: + - "rgmii" + - "trgmii" + On mt7531: + - "1000base-x" + - "2500base-x" + - "rgmii" + - "sgmii" + + +properties: + compatible: + enum: + - mediatek,mt7530 + - mediatek,mt7531 + - mediatek,mt7621 + + core-supply: + description: + Phandle to the regulator node necessary for the core power. + + "#gpio-cells": + const: 2 + + gpio-controller: + type: boolean + description: + if defined, MT7530's LED controller will run on GPIO mode. + + "#interrupt-cells": + const: 1 + + interrupt-controller: true + + interrupts: + maxItems: 1 + + io-supply: + description: + Phandle to the regulator node necessary for the I/O power. + See Documentation/devicetree/bindings/regulator/mt6323-regulator.txt + for details for the regulator setup on these boards. + + mediatek,mcm: + type: boolean + description: + if defined, indicates that either MT7530 is the part on multi-chip + module belong to MT7623A has or the remotely standalone chip as the + function MT7623N reference board provided for. + + reset-gpios: + maxItems: 1 + + reset-names: + const: mcm + + resets: + description: + Phandle pointing to the system reset controller with line index for + the ethsys. + maxItems: 1 + +patternProperties: + "^(ethernet-)?ports$": + type: object + + patternProperties: + "^(ethernet-)?port@[0-9]+$": + type: object + description: Ethernet switch ports + + unevaluatedProperties: false + + properties: + reg: + description: + Port address described must be 5 or 6 for CPU port and from 0 + to 5 for user ports. + + allOf: + - $ref: dsa-port.yaml# + - if: + properties: + label: + items: + - const: cpu + then: + required: + - reg + - phy-mode + +required: + - compatible + - reg + +allOf: + - $ref: "dsa.yaml#" + - if: + required: + - mediatek,mcm + then: + required: + - resets + - reset-names + + - dependencies: + interrupt-controller: [ interrupts ] + + - if: + properties: + compatible: + items: + - const: mediatek,mt7530 + then: + required: + - core-supply + - io-supply + +unevaluatedProperties: false + +examples: + - | + #include <dt-bindings/gpio/gpio.h> + mdio { + #address-cells = <1>; + #size-cells = <0>; + switch@0 { + compatible = "mediatek,mt7530"; + reg = <0>; + + core-supply = <&mt6323_vpa_reg>; + io-supply = <&mt6323_vemc3v3_reg>; + reset-gpios = <&pio 33 GPIO_ACTIVE_HIGH>; + + ethernet-ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + label = "lan0"; + }; + + port@1 { + reg = <1>; + label = "lan1"; + }; + + port@2 { + reg = <2>; + label = "lan2"; + }; + + port@3 { + reg = <3>; + label = "lan3"; + }; + + port@4 { + reg = <4>; + label = "wan"; + }; + + port@6 { + reg = <6>; + label = "cpu"; + ethernet = <&gmac0>; + phy-mode = "trgmii"; + fixed-link { + speed = <1000>; + full-duplex; + }; + }; + }; + }; + }; + + - | + //Example 2: MT7621: Port 4 is WAN port: 2nd GMAC -> Port 5 -> PHY port 4. + + ethernet { + #address-cells = <1>; + #size-cells = <0>; + gmac0: mac@0 { + compatible = "mediatek,eth-mac"; + reg = <0>; + phy-mode = "rgmii"; + + fixed-link { + speed = <1000>; + full-duplex; + pause; + }; + }; + + gmac1: mac@1 { + compatible = "mediatek,eth-mac"; + reg = <1>; + phy-mode = "rgmii-txid"; + phy-handle = <&phy4>; + }; + + mdio: mdio-bus { + #address-cells = <1>; + #size-cells = <0>; + + /* Internal phy */ + phy4: ethernet-phy@4 { + reg = <4>; + }; + + mt7530: switch@1f { + compatible = "mediatek,mt7621"; + reg = <0x1f>; + mediatek,mcm; + + resets = <&rstctrl 2>; + reset-names = "mcm"; + + ethernet-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + label = "lan0"; + }; + + port@1 { + reg = <1>; + label = "lan1"; + }; + + port@2 { + reg = <2>; + label = "lan2"; + }; + + port@3 { + reg = <3>; + label = "lan3"; + }; + + /* Commented out. Port 4 is handled by 2nd GMAC. + port@4 { + reg = <4>; + label = "lan4"; + }; + */ + + port@6 { + reg = <6>; + label = "cpu"; + ethernet = <&gmac0>; + phy-mode = "rgmii"; + + fixed-link { + speed = <1000>; + full-duplex; + pause; + }; + }; + }; + }; + }; + }; + + - | + //Example 3: MT7621: Port 5 is connected to external PHY: Port 5 -> external PHY. + + ethernet { + #address-cells = <1>; + #size-cells = <0>; + gmac_0: mac@0 { + compatible = "mediatek,eth-mac"; + reg = <0>; + phy-mode = "rgmii"; + + fixed-link { + speed = <1000>; + full-duplex; + pause; + }; + }; + + mdio0: mdio-bus { + #address-cells = <1>; + #size-cells = <0>; + + /* External phy */ + ephy5: ethernet-phy@7 { + reg = <7>; + }; + + switch@1f { + compatible = "mediatek,mt7621"; + reg = <0x1f>; + mediatek,mcm; + + resets = <&rstctrl 2>; + reset-names = "mcm"; + + ethernet-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + label = "lan0"; + }; + + port@1 { + reg = <1>; + label = "lan1"; + }; + + port@2 { + reg = <2>; + label = "lan2"; + }; + + port@3 { + reg = <3>; + label = "lan3"; + }; + + port@4 { + reg = <4>; + label = "lan4"; + }; + + port@5 { + reg = <5>; + label = "lan5"; + phy-mode = "rgmii"; + phy-handle = <&ephy5>; + }; + + cpu_port0: port@6 { + reg = <6>; + label = "cpu"; + ethernet = <&gmac_0>; + phy-mode = "rgmii"; + + fixed-link { + speed = <1000>; + full-duplex; + pause; + }; + }; + }; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/net/dsa/mt7530.txt b/Documentation/devicetree/bindings/net/dsa/mt7530.txt deleted file mode 100644 index 18247ebfc487..000000000000 --- a/Documentation/devicetree/bindings/net/dsa/mt7530.txt +++ /dev/null @@ -1,327 +0,0 @@ -Mediatek MT7530 Ethernet switch -================================ - -Required properties: - -- compatible: may be compatible = "mediatek,mt7530" - or compatible = "mediatek,mt7621" - or compatible = "mediatek,mt7531" -- #address-cells: Must be 1. -- #size-cells: Must be 0. -- mediatek,mcm: Boolean; if defined, indicates that either MT7530 is the part - on multi-chip module belong to MT7623A has or the remotely standalone - chip as the function MT7623N reference board provided for. - -If compatible mediatek,mt7530 is set then the following properties are required - -- core-supply: Phandle to the regulator node necessary for the core power. -- io-supply: Phandle to the regulator node necessary for the I/O power. - See Documentation/devicetree/bindings/regulator/mt6323-regulator.txt - for details for the regulator setup on these boards. - -If the property mediatek,mcm isn't defined, following property is required - -- reset-gpios: Should be a gpio specifier for a reset line. - -Else, following properties are required - -- resets : Phandle pointing to the system reset controller with - line index for the ethsys. -- reset-names : Should be set to "mcm". - -Required properties for the child nodes within ports container: - -- reg: Port address described must be 6 for CPU port and from 0 to 5 for - user ports. -- phy-mode: String, the following values are acceptable for port labeled - "cpu": - If compatible mediatek,mt7530 or mediatek,mt7621 is set, - must be either "trgmii" or "rgmii" - If compatible mediatek,mt7531 is set, - must be either "sgmii", "1000base-x" or "2500base-x" - -Port 5 of mt7530 and mt7621 switch is muxed between: -1. GMAC5: GMAC5 can interface with another external MAC or PHY. -2. PHY of port 0 or port 4: PHY interfaces with an external MAC like 2nd GMAC - of the SOC. Used in many setups where port 0/4 becomes the WAN port. - Note: On a MT7621 SOC with integrated switch: 2nd GMAC can only connected to - GMAC5 when the gpios for RGMII2 (GPIO 22-33) are not used and not - connected to external component! - -Port 5 modes/configurations: -1. Port 5 is disabled and isolated: An external phy can interface to the 2nd - GMAC of the SOC. - In the case of a build-in MT7530 switch, port 5 shares the RGMII bus with 2nd - GMAC and an optional external phy. Mind the GPIO/pinctl settings of the SOC! -2. Port 5 is muxed to PHY of port 0/4: Port 0/4 interfaces with 2nd GMAC. - It is a simple MAC to PHY interface, port 5 needs to be setup for xMII mode - and RGMII delay. -3. Port 5 is muxed to GMAC5 and can interface to an external phy. - Port 5 becomes an extra switch port. - Only works on platform where external phy TX<->RX lines are swapped. - Like in the Ubiquiti ER-X-SFP. -4. Port 5 is muxed to GMAC5 and interfaces with the 2nd GAMC as 2nd CPU port. - Currently a 2nd CPU port is not supported by DSA code. - -Depending on how the external PHY is wired: -1. normal: The PHY can only connect to 2nd GMAC but not to the switch -2. swapped: RGMII TX, RX are swapped; external phy interface with the switch as - a ethernet port. But can't interface to the 2nd GMAC. - -Based on the DT the port 5 mode is configured. - -Driver tries to lookup the phy-handle of the 2nd GMAC of the master device. -When phy-handle matches PHY of port 0 or 4 then port 5 set-up as mode 2. -phy-mode must be set, see also example 2 below! - * mt7621: phy-mode = "rgmii-txid"; - * mt7623: phy-mode = "rgmii"; - -Optional properties: - -- gpio-controller: Boolean; if defined, MT7530's LED controller will run on - GPIO mode. -- #gpio-cells: Must be 2 if gpio-controller is defined. -- interrupt-controller: Boolean; Enables the internal interrupt controller. - -If interrupt-controller is defined, the following properties are required. - -- #interrupt-cells: Must be 1. -- interrupts: Parent interrupt for the interrupt controller. - -See Documentation/devicetree/bindings/net/dsa/dsa.txt for a list of additional -required, optional properties and how the integrated switch subnodes must -be specified. - -Example: - - &mdio0 { - switch@0 { - compatible = "mediatek,mt7530"; - #address-cells = <1>; - #size-cells = <0>; - reg = <0>; - - core-supply = <&mt6323_vpa_reg>; - io-supply = <&mt6323_vemc3v3_reg>; - reset-gpios = <&pio 33 0>; - - ports { - #address-cells = <1>; - #size-cells = <0>; - reg = <0>; - port@0 { - reg = <0>; - label = "lan0"; - }; - - port@1 { - reg = <1>; - label = "lan1"; - }; - - port@2 { - reg = <2>; - label = "lan2"; - }; - - port@3 { - reg = <3>; - label = "lan3"; - }; - - port@4 { - reg = <4>; - label = "wan"; - }; - - port@6 { - reg = <6>; - label = "cpu"; - ethernet = <&gmac0>; - phy-mode = "trgmii"; - fixed-link { - speed = <1000>; - full-duplex; - }; - }; - }; - }; - }; - -Example 2: MT7621: Port 4 is WAN port: 2nd GMAC -> Port 5 -> PHY port 4. - -ð { - gmac0: mac@0 { - compatible = "mediatek,eth-mac"; - reg = <0>; - phy-mode = "rgmii"; - - fixed-link { - speed = <1000>; - full-duplex; - pause; - }; - }; - - gmac1: mac@1 { - compatible = "mediatek,eth-mac"; - reg = <1>; - phy-mode = "rgmii-txid"; - phy-handle = <&phy4>; - }; - - mdio: mdio-bus { - #address-cells = <1>; - #size-cells = <0>; - - /* Internal phy */ - phy4: ethernet-phy@4 { - reg = <4>; - }; - - mt7530: switch@1f { - compatible = "mediatek,mt7621"; - #address-cells = <1>; - #size-cells = <0>; - reg = <0x1f>; - pinctrl-names = "default"; - mediatek,mcm; - - resets = <&rstctrl 2>; - reset-names = "mcm"; - - ports { - #address-cells = <1>; - #size-cells = <0>; - - port@0 { - reg = <0>; - label = "lan0"; - }; - - port@1 { - reg = <1>; - label = "lan1"; - }; - - port@2 { - reg = <2>; - label = "lan2"; - }; - - port@3 { - reg = <3>; - label = "lan3"; - }; - -/* Commented out. Port 4 is handled by 2nd GMAC. - port@4 { - reg = <4>; - label = "lan4"; - }; -*/ - - cpu_port0: port@6 { - reg = <6>; - label = "cpu"; - ethernet = <&gmac0>; - phy-mode = "rgmii"; - - fixed-link { - speed = <1000>; - full-duplex; - pause; - }; - }; - }; - }; - }; -}; - -Example 3: MT7621: Port 5 is connected to external PHY: Port 5 -> external PHY. - -ð { - gmac0: mac@0 { - compatible = "mediatek,eth-mac"; - reg = <0>; - phy-mode = "rgmii"; - - fixed-link { - speed = <1000>; - full-duplex; - pause; - }; - }; - - mdio: mdio-bus { - #address-cells = <1>; - #size-cells = <0>; - - /* External phy */ - ephy5: ethernet-phy@7 { - reg = <7>; - }; - - mt7530: switch@1f { - compatible = "mediatek,mt7621"; - #address-cells = <1>; - #size-cells = <0>; - reg = <0x1f>; - pinctrl-names = "default"; - mediatek,mcm; - - resets = <&rstctrl 2>; - reset-names = "mcm"; - - ports { - #address-cells = <1>; - #size-cells = <0>; - - port@0 { - reg = <0>; - label = "lan0"; - }; - - port@1 { - reg = <1>; - label = "lan1"; - }; - - port@2 { - reg = <2>; - label = "lan2"; - }; - - port@3 { - reg = <3>; - label = "lan3"; - }; - - port@4 { - reg = <4>; - label = "lan4"; - }; - - port@5 { - reg = <5>; - label = "lan5"; - phy-mode = "rgmii"; - phy-handle = <&ephy5>; - }; - - cpu_port0: port@6 { - reg = <6>; - label = "cpu"; - ethernet = <&gmac0>; - phy-mode = "rgmii"; - - fixed-link { - speed = <1000>; - full-duplex; - pause; - }; - }; - }; - }; - }; -}; diff --git a/Documentation/devicetree/bindings/net/xlnx,emaclite.yaml b/Documentation/devicetree/bindings/net/xlnx,emaclite.yaml new file mode 100644 index 000000000000..92d8ade988f6 --- /dev/null +++ b/Documentation/devicetree/bindings/net/xlnx,emaclite.yaml @@ -0,0 +1,63 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/xlnx,emaclite.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Xilinx Emaclite Ethernet controller + +maintainers: + - Radhey Shyam Pandey <radhey.shyam.pandey@amd.com> + - Harini Katakam <harini.katakam@amd.com> + +allOf: + - $ref: ethernet-controller.yaml# + +properties: + compatible: + enum: + - xlnx,opb-ethernetlite-1.01.a + - xlnx,opb-ethernetlite-1.01.b + - xlnx,xps-ethernetlite-1.00.a + - xlnx,xps-ethernetlite-2.00.a + - xlnx,xps-ethernetlite-2.01.a + - xlnx,xps-ethernetlite-3.00.a + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + phy-handle: true + + local-mac-address: true + + xlnx,tx-ping-pong: + type: boolean + description: hardware supports tx ping pong buffer. + + xlnx,rx-ping-pong: + type: boolean + description: hardware supports rx ping pong buffer. + +required: + - compatible + - reg + - interrupts + - phy-handle + +additionalProperties: false + +examples: + - | + axi_ethernetlite_1: ethernet@40e00000 { + compatible = "xlnx,xps-ethernetlite-3.00.a"; + reg = <0x40e00000 0x10000>; + interrupt-parent = <&axi_intc_1>; + interrupts = <1>; + local-mac-address = [00 00 00 00 00 00]; + phy-handle = <&phy0>; + xlnx,rx-ping-pong; + xlnx,tx-ping-pong; + }; diff --git a/Documentation/networking/tls.rst b/Documentation/networking/tls.rst index 8cb2cd4e2a80..be8e10c14b05 100644 --- a/Documentation/networking/tls.rst +++ b/Documentation/networking/tls.rst @@ -214,6 +214,31 @@ of calling send directly after a handshake using gnutls. Since it doesn't implement a full record layer, control messages are not supported. +Optional optimizations +---------------------- + +There are certain condition-specific optimizations the TLS ULP can make, +if requested. Those optimizations are either not universally beneficial +or may impact correctness, hence they require an opt-in. +All options are set per-socket using setsockopt(), and their +state can be checked using getsockopt() and via socket diag (``ss``). + +TLS_TX_ZEROCOPY_RO +~~~~~~~~~~~~~~~~~~ + +For device offload only. Allow sendfile() data to be transmitted directly +to the NIC without making an in-kernel copy. This allows true zero-copy +behavior when device offload is enabled. + +The application must make sure that the data is not modified between being +submitted and transmission completing. In other words this is mostly +applicable if the data sent on a socket via sendfile() is read-only. + +Modifying the data may result in different versions of the data being used +for the original TCP transmission and TCP retransmissions. To the receiver +this will look like TLS records had been tampered with and will result +in record authentication failures. + Statistics ========== diff --git a/MAINTAINERS b/MAINTAINERS index f52543aedd61..ca95b1833b97 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -171,7 +171,6 @@ F: drivers/scsi/53c700* 6LOWPAN GENERIC (BTLE/IEEE 802.15.4) M: Alexander Aring <alex.aring@gmail.com> -M: Jukka Rissanen <jukka.rissanen@linux.intel.com> L: linux-bluetooth@vger.kernel.org L: linux-wpan@vger.kernel.org S: Maintained diff --git a/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts b/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts index 40cf2236c0b6..7df8cfb1d3b9 100644 --- a/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts +++ b/arch/arm64/boot/dts/rockchip/rk3568-bpi-r2-pro.dts @@ -394,6 +394,54 @@ status = "disabled"; }; +&mdio0 { + #address-cells = <1>; + #size-cells = <0>; + + switch@0 { + compatible = "mediatek,mt7531"; + reg = <0>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@1 { + reg = <1>; + label = "lan0"; + }; + + port@2 { + reg = <2>; + label = "lan1"; + }; + + port@3 { + reg = <3>; + label = "lan2"; + }; + + port@4 { + reg = <4>; + label = "lan3"; + }; + + port@5 { + reg = <5>; + label = "cpu"; + ethernet = <&gmac0>; + phy-mode = "rgmii"; + + fixed-link { + speed = <1000>; + full-duplex; + pause; + }; + }; + }; + }; +}; + &mdio1 { rgmii_phy1: ethernet-phy@0 { compatible = "ethernet-phy-ieee802.3-c22"; diff --git a/drivers/infiniband/hw/mlx5/dm.c b/drivers/infiniband/hw/mlx5/dm.c index 001d766cf291..3669c90b2dad 100644 --- a/drivers/infiniband/hw/mlx5/dm.c +++ b/drivers/infiniband/hw/mlx5/dm.c @@ -336,9 +336,15 @@ err_copy: static enum mlx5_sw_icm_type get_icm_type(int uapi_type) { - return uapi_type == MLX5_IB_UAPI_DM_TYPE_STEERING_SW_ICM ? - MLX5_SW_ICM_TYPE_STEERING : - MLX5_SW_ICM_TYPE_HEADER_MODIFY; + switch (uapi_type) { + case MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_SW_ICM: + return MLX5_SW_ICM_TYPE_HEADER_MODIFY; + case MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_PATTERN_SW_ICM: + return MLX5_SW_ICM_TYPE_HEADER_MODIFY_PATTERN; + case MLX5_IB_UAPI_DM_TYPE_STEERING_SW_ICM: + default: + return MLX5_SW_ICM_TYPE_STEERING; + } } static struct ib_dm *handle_alloc_dm_sw_icm(struct ib_ucontext *ctx, @@ -347,11 +353,32 @@ static struct ib_dm *handle_alloc_dm_sw_icm(struct ib_ucontext *ctx, int type) { struct mlx5_core_dev *dev = to_mdev(ctx->device)->mdev; - enum mlx5_sw_icm_type icm_type = get_icm_type(type); + enum mlx5_sw_icm_type icm_type; struct mlx5_ib_dm_icm *dm; u64 act_size; int err; + if (!capable(CAP_SYS_RAWIO) || !capable(CAP_NET_RAW)) + return ERR_PTR(-EPERM); + + switch (type) { + case MLX5_IB_UAPI_DM_TYPE_STEERING_SW_ICM: + case MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_SW_ICM: + if (!(MLX5_CAP_FLOWTABLE_NIC_RX(dev, sw_owner) || + MLX5_CAP_FLOWTABLE_NIC_TX(dev, sw_owner) || + MLX5_CAP_FLOWTABLE_NIC_RX(dev, sw_owner_v2) || + MLX5_CAP_FLOWTABLE_NIC_TX(dev, sw_owner_v2))) + return ERR_PTR(-EOPNOTSUPP); + break; + case MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_PATTERN_SW_ICM: + if (!MLX5_CAP_FLOWTABLE_NIC_RX(dev, sw_owner_v2) || + !MLX5_CAP_FLOWTABLE_NIC_TX(dev, sw_owner_v2)) + return ERR_PTR(-EOPNOTSUPP); + break; + default: + return ERR_PTR(-EOPNOTSUPP); + } + dm = kzalloc(sizeof(*dm), GFP_KERNEL); if (!dm) return ERR_PTR(-ENOMEM); @@ -359,19 +386,6 @@ static struct ib_dm *handle_alloc_dm_sw_icm(struct ib_ucontext *ctx, dm->base.type = type; dm->base.ibdm.device = ctx->device; - if (!capable(CAP_SYS_RAWIO) || !capable(CAP_NET_RAW)) { - err = -EPERM; - goto free; - } - - if (!(MLX5_CAP_FLOWTABLE_NIC_RX(dev, sw_owner) || - MLX5_CAP_FLOWTABLE_NIC_TX(dev, sw_owner) || - MLX5_CAP_FLOWTABLE_NIC_RX(dev, sw_owner_v2) || - MLX5_CAP_FLOWTABLE_NIC_TX(dev, sw_owner_v2))) { - err = -EOPNOTSUPP; - goto free; - } - /* Allocation size must a multiple of the basic block size * and a power of 2. */ @@ -379,6 +393,8 @@ static struct ib_dm *handle_alloc_dm_sw_icm(struct ib_ucontext *ctx, act_size = roundup_pow_of_two(act_size); dm->base.size = act_size; + icm_type = get_icm_type(type); + err = mlx5_dm_sw_icm_alloc(dev, icm_type, act_size, attr->alignment, to_mucontext(ctx)->devx_uid, &dm->base.dev_addr, &dm->obj_id); @@ -420,8 +436,8 @@ struct ib_dm *mlx5_ib_alloc_dm(struct ib_device *ibdev, case MLX5_IB_UAPI_DM_TYPE_MEMIC: return handle_alloc_dm_memic(context, attr, attrs); case MLX5_IB_UAPI_DM_TYPE_STEERING_SW_ICM: - return handle_alloc_dm_sw_icm(context, attr, attrs, type); case MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_SW_ICM: + case MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_PATTERN_SW_ICM: return handle_alloc_dm_sw_icm(context, attr, attrs, type); default: return ERR_PTR(-EOPNOTSUPP); @@ -474,6 +490,7 @@ static int mlx5_ib_dealloc_dm(struct ib_dm *ibdm, return 0; case MLX5_IB_UAPI_DM_TYPE_STEERING_SW_ICM: case MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_SW_ICM: + case MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_PATTERN_SW_ICM: return mlx5_dm_icm_dealloc(ctx, to_icm(ibdm)); default: return -EOPNOTSUPP; diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 1e7653c997b5..aedfd7ff4846 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -1083,6 +1083,7 @@ struct ib_mr *mlx5_ib_reg_dm_mr(struct ib_pd *pd, struct ib_dm *dm, break; case MLX5_IB_UAPI_DM_TYPE_STEERING_SW_ICM: case MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_SW_ICM: + case MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_PATTERN_SW_ICM: if (attr->access_flags & ~MLX5_IB_DM_SW_ICM_ALLOWED_ACCESS) return ERR_PTR(-EINVAL); diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index f85372adf042..3d427183ec8e 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -6218,45 +6218,33 @@ int bond_create(struct net *net, const char *name) { struct net_device *bond_dev; struct bonding *bond; - struct alb_bond_info *bond_info; - int res; + int res = -ENOMEM; rtnl_lock(); bond_dev = alloc_netdev_mq(sizeof(struct bonding), name ? name : "bond%d", NET_NAME_UNKNOWN, bond_setup, tx_queues); - if (!bond_dev) { - pr_err("%s: eek! can't alloc netdev!\n", name); - rtnl_unlock(); - return -ENOMEM; - } + if (!bond_dev) + goto out; - /* - * Initialize rx_hashtbl_used_head to RLB_NULL_INDEX. - * It is set to 0 by default which is wrong. - */ bond = netdev_priv(bond_dev); - bond_info = &(BOND_ALB_INFO(bond)); - bond_info->rx_hashtbl_used_head = RLB_NULL_INDEX; - dev_net_set(bond_dev, net); bond_dev->rtnl_link_ops = &bond_link_ops; res = register_netdevice(bond_dev); if (res < 0) { free_netdev(bond_dev); - rtnl_unlock(); - - return res; + goto out; } netif_carrier_off(bond_dev); bond_work_init_all(bond); +out: rtnl_unlock(); - return 0; + return res; } static int __net_init bond_net_init(struct net *net) diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c index 6f404f9c34e3..5a6f44455b95 100644 --- a/drivers/net/bonding/bond_netlink.c +++ b/drivers/net/bonding/bond_netlink.c @@ -151,7 +151,8 @@ static int bond_slave_changelink(struct net_device *bond_dev, snprintf(queue_id_str, sizeof(queue_id_str), "%s:%u\n", slave_dev->name, queue_id); bond_opt_initstr(&newval, queue_id_str); - err = __bond_opt_set(bond, BOND_OPT_QUEUE_ID, &newval); + err = __bond_opt_set(bond, BOND_OPT_QUEUE_ID, &newval, + data[IFLA_BOND_SLAVE_QUEUE_ID], extack); if (err) return err; } @@ -175,7 +176,8 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[], int mode = nla_get_u8(data[IFLA_BOND_MODE]); bond_opt_initval(&newval, mode); - err = __bond_opt_set(bond, BOND_OPT_MODE, &newval); + err = __bond_opt_set(bond, BOND_OPT_MODE, &newval, + data[IFLA_BOND_MODE], extack); if (err) return err; } @@ -192,7 +194,8 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[], active_slave = slave_dev->name; } bond_opt_initstr(&newval, active_slave); - err = __bond_opt_set(bond, BOND_OPT_ACTIVE_SLAVE, &newval); + err = __bond_opt_set(bond, BOND_OPT_ACTIVE_SLAVE, &newval, + data[IFLA_BOND_ACTIVE_SLAVE], extack); if (err) return err; } @@ -200,7 +203,8 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[], miimon = nla_get_u32(data[IFLA_BOND_MIIMON]); bond_opt_initval(&newval, miimon); - err = __bond_opt_set(bond, BOND_OPT_MIIMON, &newval); + err = __bond_opt_set(bond, BOND_OPT_MIIMON, &newval, + data[IFLA_BOND_MIIMON], extack); if (err) return err; } @@ -208,7 +212,8 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[], int updelay = nla_get_u32(data[IFLA_BOND_UPDELAY]); bond_opt_initval(&newval, updelay); - err = __bond_opt_set(bond, BOND_OPT_UPDELAY, &newval); + err = __bond_opt_set(bond, BOND_OPT_UPDELAY, &newval, + data[IFLA_BOND_UPDELAY], extack); if (err) return err; } @@ -216,7 +221,8 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[], int downdelay = nla_get_u32(data[IFLA_BOND_DOWNDELAY]); bond_opt_initval(&newval, downdelay); - err = __bond_opt_set(bond, BOND_OPT_DOWNDELAY, &newval); + err = __bond_opt_set(bond, BOND_OPT_DOWNDELAY, &newval, + data[IFLA_BOND_DOWNDELAY], extack); if (err) return err; } @@ -224,7 +230,8 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[], int delay = nla_get_u32(data[IFLA_BOND_PEER_NOTIF_DELAY]); bond_opt_initval(&newval, delay); - err = __bond_opt_set(bond, BOND_OPT_PEER_NOTIF_DELAY, &newval); + err = __bond_opt_set(bond, BOND_OPT_PEER_NOTIF_DELAY, &newval, + data[IFLA_BOND_PEER_NOTIF_DELAY], extack); if (err) return err; } @@ -232,7 +239,8 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[], int use_carrier = nla_get_u8(data[IFLA_BOND_USE_CARRIER]); bond_opt_initval(&newval, use_carrier); - err = __bond_opt_set(bond, BOND_OPT_USE_CARRIER, &newval); + err = __bond_opt_set(bond, BOND_OPT_USE_CARRIER, &newval, + data[IFLA_BOND_USE_CARRIER], extack); if (err) return err; } @@ -240,12 +248,14 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[], int arp_interval = nla_get_u32(data[IFLA_BOND_ARP_INTERVAL]); if (arp_interval && miimon) { - netdev_err(bond->dev, "ARP monitoring cannot be used with MII monitoring\n"); + NL_SET_ERR_MSG_ATTR(extack, data[IFLA_BOND_ARP_INTERVAL], + "ARP monitoring cannot be used with MII monitoring"); return -EINVAL; } bond_opt_initval(&newval, arp_interval); - err = __bond_opt_set(bond, BOND_OPT_ARP_INTERVAL, &newval); + err = __bond_opt_set(bond, BOND_OPT_ARP_INTERVAL, &newval, + data[IFLA_BOND_ARP_INTERVAL], extack); if (err) return err; } @@ -264,7 +274,9 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[], bond_opt_initval(&newval, (__force u64)target); err = __bond_opt_set(bond, BOND_OPT_ARP_TARGETS, - &newval); + &newval, + data[IFLA_BOND_ARP_IP_TARGET], + extack); if (err) break; i++; @@ -292,7 +304,9 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[], bond_opt_initextra(&newval, &addr6, sizeof(addr6)); err = __bond_opt_set(bond, BOND_OPT_NS_TARGETS, - &newval); + &newval, + data[IFLA_BOND_NS_IP6_TARGET], + extack); if (err) break; i++; @@ -307,12 +321,14 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[], int arp_validate = nla_get_u32(data[IFLA_BOND_ARP_VALIDATE]); if (arp_validate && miimon) { - netdev_err(bond->dev, "ARP validating cannot be used with MII monitoring\n"); + NL_SET_ERR_MSG_ATTR(extack, data[IFLA_BOND_ARP_INTERVAL], + "ARP validating cannot be used with MII monitoring"); return -EINVAL; } bond_opt_initval(&newval, arp_validate); - err = __bond_opt_set(bond, BOND_OPT_ARP_VALIDATE, &newval); + err = __bond_opt_set(bond, BOND_OPT_ARP_VALIDATE, &newval, + data[IFLA_BOND_ARP_VALIDATE], extack); if (err) return err; } @@ -321,7 +337,8 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[], nla_get_u32(data[IFLA_BOND_ARP_ALL_TARGETS]); bond_opt_initval(&newval, arp_all_targets); - err = __bond_opt_set(bond, BOND_OPT_ARP_ALL_TARGETS, &newval); + err = __bond_opt_set(bond, BOND_OPT_ARP_ALL_TARGETS, &newval, + data[IFLA_BOND_ARP_ALL_TARGETS], extack); if (err) return err; } @@ -335,7 +352,8 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[], primary = dev->name; bond_opt_initstr(&newval, primary); - err = __bond_opt_set(bond, BOND_OPT_PRIMARY, &newval); + err = __bond_opt_set(bond, BOND_OPT_PRIMARY, &newval, + data[IFLA_BOND_PRIMARY], extack); if (err) return err; } @@ -344,7 +362,8 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[], nla_get_u8(data[IFLA_BOND_PRIMARY_RESELECT]); bond_opt_initval(&newval, primary_reselect); - err = __bond_opt_set(bond, BOND_OPT_PRIMARY_RESELECT, &newval); + err = __bond_opt_set(bond, BOND_OPT_PRIMARY_RESELECT, &newval, + data[IFLA_BOND_PRIMARY_RESELECT], extack); if (err) return err; } @@ -353,7 +372,8 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[], nla_get_u8(data[IFLA_BOND_FAIL_OVER_MAC]); bond_opt_initval(&newval, fail_over_mac); - err = __bond_opt_set(bond, BOND_OPT_FAIL_OVER_MAC, &newval); + err = __bond_opt_set(bond, BOND_OPT_FAIL_OVER_MAC, &newval, + data[IFLA_BOND_FAIL_OVER_MAC], extack); if (err) return err; } @@ -362,7 +382,8 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[], nla_get_u8(data[IFLA_BOND_XMIT_HASH_POLICY]); bond_opt_initval(&newval, xmit_hash_policy); - err = __bond_opt_set(bond, BOND_OPT_XMIT_HASH, &newval); + err = __bond_opt_set(bond, BOND_OPT_XMIT_HASH, &newval, + data[IFLA_BOND_XMIT_HASH_POLICY], extack); if (err) return err; } @@ -371,7 +392,8 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[], nla_get_u32(data[IFLA_BOND_RESEND_IGMP]); bond_opt_initval(&newval, resend_igmp); - err = __bond_opt_set(bond, BOND_OPT_RESEND_IGMP, &newval); + err = __bond_opt_set(bond, BOND_OPT_RESEND_IGMP, &newval, + data[IFLA_BOND_RESEND_IGMP], extack); if (err) return err; } @@ -380,7 +402,8 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[], nla_get_u8(data[IFLA_BOND_NUM_PEER_NOTIF]); bond_opt_initval(&newval, num_peer_notif); - err = __bond_opt_set(bond, BOND_OPT_NUM_PEER_NOTIF, &newval); + err = __bond_opt_set(bond, BOND_OPT_NUM_PEER_NOTIF, &newval, + data[IFLA_BOND_NUM_PEER_NOTIF], extack); if (err) return err; } @@ -389,7 +412,8 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[], nla_get_u8(data[IFLA_BOND_ALL_SLAVES_ACTIVE]); bond_opt_initval(&newval, all_slaves_active); - err = __bond_opt_set(bond, BOND_OPT_ALL_SLAVES_ACTIVE, &newval); + err = __bond_opt_set(bond, BOND_OPT_ALL_SLAVES_ACTIVE, &newval, + data[IFLA_BOND_ALL_SLAVES_ACTIVE], extack); if (err) return err; } @@ -398,7 +422,8 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[], nla_get_u32(data[IFLA_BOND_MIN_LINKS]); bond_opt_initval(&newval, min_links); - err = __bond_opt_set(bond, BOND_OPT_MINLINKS, &newval); + err = __bond_opt_set(bond, BOND_OPT_MINLINKS, &newval, + data[IFLA_BOND_MIN_LINKS], extack); if (err) return err; } @@ -407,7 +432,8 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[], nla_get_u32(data[IFLA_BOND_LP_INTERVAL]); bond_opt_initval(&newval, lp_interval); - err = __bond_opt_set(bond, BOND_OPT_LP_INTERVAL, &newval); + err = __bond_opt_set(bond, BOND_OPT_LP_INTERVAL, &newval, + data[IFLA_BOND_LP_INTERVAL], extack); if (err) return err; } @@ -416,7 +442,8 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[], nla_get_u32(data[IFLA_BOND_PACKETS_PER_SLAVE]); bond_opt_initval(&newval, packets_per_slave); - err = __bond_opt_set(bond, BOND_OPT_PACKETS_PER_SLAVE, &newval); + err = __bond_opt_set(bond, BOND_OPT_PACKETS_PER_SLAVE, &newval, + data[IFLA_BOND_PACKETS_PER_SLAVE], extack); if (err) return err; } @@ -425,7 +452,8 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[], int lacp_active = nla_get_u8(data[IFLA_BOND_AD_LACP_ACTIVE]); bond_opt_initval(&newval, lacp_active); - err = __bond_opt_set(bond, BOND_OPT_LACP_ACTIVE, &newval); + err = __bond_opt_set(bond, BOND_OPT_LACP_ACTIVE, &newval, + data[IFLA_BOND_AD_LACP_ACTIVE], extack); if (err) return err; } @@ -435,7 +463,8 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[], nla_get_u8(data[IFLA_BOND_AD_LACP_RATE]); bond_opt_initval(&newval, lacp_rate); - err = __bond_opt_set(bond, BOND_OPT_LACP_RATE, &newval); + err = __bond_opt_set(bond, BOND_OPT_LACP_RATE, &newval, + data[IFLA_BOND_AD_LACP_RATE], extack); if (err) return err; } @@ -444,7 +473,8 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[], nla_get_u8(data[IFLA_BOND_AD_SELECT]); bond_opt_initval(&newval, ad_select); - err = __bond_opt_set(bond, BOND_OPT_AD_SELECT, &newval); + err = __bond_opt_set(bond, BOND_OPT_AD_SELECT, &newval, + data[IFLA_BOND_AD_SELECT], extack); if (err) return err; } @@ -453,7 +483,8 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[], nla_get_u16(data[IFLA_BOND_AD_ACTOR_SYS_PRIO]); bond_opt_initval(&newval, actor_sys_prio); - err = __bond_opt_set(bond, BOND_OPT_AD_ACTOR_SYS_PRIO, &newval); + err = __bond_opt_set(bond, BOND_OPT_AD_ACTOR_SYS_PRIO, &newval, + data[IFLA_BOND_AD_ACTOR_SYS_PRIO], extack); if (err) return err; } @@ -462,7 +493,8 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[], nla_get_u16(data[IFLA_BOND_AD_USER_PORT_KEY]); bond_opt_initval(&newval, port_key); - err = __bond_opt_set(bond, BOND_OPT_AD_USER_PORT_KEY, &newval); + err = __bond_opt_set(bond, BOND_OPT_AD_USER_PORT_KEY, &newval, + data[IFLA_BOND_AD_USER_PORT_KEY], extack); if (err) return err; } @@ -472,7 +504,8 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[], bond_opt_initval(&newval, nla_get_u64(data[IFLA_BOND_AD_ACTOR_SYSTEM])); - err = __bond_opt_set(bond, BOND_OPT_AD_ACTOR_SYSTEM, &newval); + err = __bond_opt_set(bond, BOND_OPT_AD_ACTOR_SYSTEM, &newval, + data[IFLA_BOND_AD_ACTOR_SYSTEM], extack); if (err) return err; } @@ -480,7 +513,8 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[], int dynamic_lb = nla_get_u8(data[IFLA_BOND_TLB_DYNAMIC_LB]); bond_opt_initval(&newval, dynamic_lb); - err = __bond_opt_set(bond, BOND_OPT_TLB_DYNAMIC_LB, &newval); + err = __bond_opt_set(bond, BOND_OPT_TLB_DYNAMIC_LB, &newval, + data[IFLA_BOND_TLB_DYNAMIC_LB], extack); if (err) return err; } @@ -489,7 +523,8 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[], int missed_max = nla_get_u8(data[IFLA_BOND_MISSED_MAX]); bond_opt_initval(&newval, missed_max); - err = __bond_opt_set(bond, BOND_OPT_MISSED_MAX, &newval); + err = __bond_opt_set(bond, BOND_OPT_MISSED_MAX, &newval, + data[IFLA_BOND_MISSED_MAX], extack); if (err) return err; } diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index 1f8323ad5282..96eef19cffc4 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -632,27 +632,35 @@ static int bond_opt_check_deps(struct bonding *bond, } static void bond_opt_dep_print(struct bonding *bond, - const struct bond_option *opt) + const struct bond_option *opt, + struct nlattr *bad_attr, + struct netlink_ext_ack *extack) { const struct bond_opt_value *modeval; struct bond_params *params; params = &bond->params; modeval = bond_opt_get_val(BOND_OPT_MODE, params->mode); - if (test_bit(params->mode, &opt->unsuppmodes)) + if (test_bit(params->mode, &opt->unsuppmodes)) { netdev_err(bond->dev, "option %s: mode dependency failed, not supported in mode %s(%llu)\n", opt->name, modeval->string, modeval->value); + NL_SET_ERR_MSG_ATTR(extack, bad_attr, + "option not supported in mode"); + } } static void bond_opt_error_interpret(struct bonding *bond, const struct bond_option *opt, - int error, const struct bond_opt_value *val) + int error, const struct bond_opt_value *val, + struct nlattr *bad_attr, + struct netlink_ext_ack *extack) { const struct bond_opt_value *minval, *maxval; char *p; switch (error) { case -EINVAL: + NL_SET_ERR_MSG_ATTR(extack, bad_attr, "invalid option value"); if (val) { if (val->string) { /* sometimes RAWVAL opts may have new lines */ @@ -674,13 +682,17 @@ static void bond_opt_error_interpret(struct bonding *bond, opt->name, minval ? minval->value : 0, maxval->value); break; case -EACCES: - bond_opt_dep_print(bond, opt); + bond_opt_dep_print(bond, opt, bad_attr, extack); break; case -ENOTEMPTY: + NL_SET_ERR_MSG_ATTR(extack, bad_attr, + "unable to set option because the bond device has slaves"); netdev_err(bond->dev, "option %s: unable to set because the bond device has slaves\n", opt->name); break; case -EBUSY: + NL_SET_ERR_MSG_ATTR(extack, bad_attr, + "unable to set option because the bond is up"); netdev_err(bond->dev, "option %s: unable to set because the bond device is up\n", opt->name); break; @@ -691,6 +703,8 @@ static void bond_opt_error_interpret(struct bonding *bond, *p = '\0'; netdev_err(bond->dev, "option %s: interface %s does not exist!\n", opt->name, val->string); + NL_SET_ERR_MSG_ATTR(extack, bad_attr, + "interface does not exist"); } break; default: @@ -703,13 +717,17 @@ static void bond_opt_error_interpret(struct bonding *bond, * @bond: target bond device * @option: option to set * @val: value to set it to + * @bad_attr: netlink attribue that caused the error + * @extack: extended netlink error structure, used when an error message + * needs to be returned to the caller via netlink * * This function is used to change the bond's option value, it can be * used for both enabling/changing an option and for disabling it. RTNL lock * must be obtained before calling this function. */ int __bond_opt_set(struct bonding *bond, - unsigned int option, struct bond_opt_value *val) + unsigned int option, struct bond_opt_value *val, + struct nlattr *bad_attr, struct netlink_ext_ack *extack) { const struct bond_opt_value *retval = NULL; const struct bond_option *opt; @@ -731,7 +749,7 @@ int __bond_opt_set(struct bonding *bond, ret = opt->set(bond, retval); out: if (ret) - bond_opt_error_interpret(bond, opt, ret, val); + bond_opt_error_interpret(bond, opt, ret, val, bad_attr, extack); return ret; } @@ -753,7 +771,7 @@ int __bond_opt_set_notify(struct bonding *bond, ASSERT_RTNL(); - ret = __bond_opt_set(bond, option, val); + ret = __bond_opt_set(bond, option, val, NULL, NULL); if (!ret && (bond->dev->reg_state == NETREG_REGISTERED)) call_netdevice_notifiers(NETDEV_CHANGEINFODATA, bond->dev); diff --git a/drivers/net/dsa/microchip/ksz8.h b/drivers/net/dsa/microchip/ksz8.h index 03da369675c6..cae76f5e7787 100644 --- a/drivers/net/dsa/microchip/ksz8.h +++ b/drivers/net/dsa/microchip/ksz8.h @@ -7,7 +7,8 @@ #ifndef __KSZ8XXX_H #define __KSZ8XXX_H -#include <linux/kernel.h> + +#include <linux/types.h> enum ksz_regs { REG_IND_CTRL_0, diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 2b02d823d497..835807911be0 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -1038,6 +1038,7 @@ static int mt7530_port_enable(struct dsa_switch *ds, int port, struct phy_device *phy) { + struct dsa_port *dp = dsa_to_port(ds, port); struct mt7530_priv *priv = ds->priv; mutex_lock(&priv->reg_mutex); @@ -1046,7 +1047,11 @@ mt7530_port_enable(struct dsa_switch *ds, int port, * restore the port matrix if the port is the member of a certain * bridge. */ - priv->ports[port].pm |= PCR_MATRIX(BIT(MT7530_CPU_PORT)); + if (dsa_port_is_user(dp)) { + struct dsa_port *cpu_dp = dp->cpu_dp; + + priv->ports[port].pm |= PCR_MATRIX(BIT(cpu_dp->index)); + } priv->ports[port].enable = true; mt7530_rmw(priv, MT7530_PCR_P(port), PCR_MATRIX_MASK, priv->ports[port].pm); @@ -1195,7 +1200,8 @@ mt7530_port_bridge_join(struct dsa_switch *ds, int port, struct netlink_ext_ack *extack) { struct dsa_port *dp = dsa_to_port(ds, port), *other_dp; - u32 port_bitmap = BIT(MT7530_CPU_PORT); + struct dsa_port *cpu_dp = dp->cpu_dp; + u32 port_bitmap = BIT(cpu_dp->index); struct mt7530_priv *priv = ds->priv; mutex_lock(&priv->reg_mutex); @@ -1272,9 +1278,12 @@ mt7530_port_set_vlan_unaware(struct dsa_switch *ds, int port) * the CPU port get out of VLAN filtering mode. */ if (all_user_ports_removed) { - mt7530_write(priv, MT7530_PCR_P(MT7530_CPU_PORT), + struct dsa_port *dp = dsa_to_port(ds, port); + struct dsa_port *cpu_dp = dp->cpu_dp; + + mt7530_write(priv, MT7530_PCR_P(cpu_dp->index), PCR_MATRIX(dsa_user_ports(priv->ds))); - mt7530_write(priv, MT7530_PVC_P(MT7530_CPU_PORT), PORT_SPEC_TAG + mt7530_write(priv, MT7530_PVC_P(cpu_dp->index), PORT_SPEC_TAG | PVC_EG_TAG(MT7530_VLAN_EG_CONSISTENT)); } } @@ -1312,6 +1321,7 @@ mt7530_port_bridge_leave(struct dsa_switch *ds, int port, struct dsa_bridge bridge) { struct dsa_port *dp = dsa_to_port(ds, port), *other_dp; + struct dsa_port *cpu_dp = dp->cpu_dp; struct mt7530_priv *priv = ds->priv; mutex_lock(&priv->reg_mutex); @@ -1340,8 +1350,8 @@ mt7530_port_bridge_leave(struct dsa_switch *ds, int port, */ if (priv->ports[port].enable) mt7530_rmw(priv, MT7530_PCR_P(port), PCR_MATRIX_MASK, - PCR_MATRIX(BIT(MT7530_CPU_PORT))); - priv->ports[port].pm = PCR_MATRIX(BIT(MT7530_CPU_PORT)); + PCR_MATRIX(BIT(cpu_dp->index))); + priv->ports[port].pm = PCR_MATRIX(BIT(cpu_dp->index)); /* When a port is removed from the bridge, the port would be set up * back to the default as is at initial boot which is a VLAN-unaware @@ -1508,6 +1518,9 @@ static int mt7530_port_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering, struct netlink_ext_ack *extack) { + struct dsa_port *dp = dsa_to_port(ds, port); + struct dsa_port *cpu_dp = dp->cpu_dp; + if (vlan_filtering) { /* The port is being kept as VLAN-unaware port when bridge is * set up with vlan_filtering not being set, Otherwise, the @@ -1515,7 +1528,7 @@ mt7530_port_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering, * for becoming a VLAN-aware port. */ mt7530_port_set_vlan_aware(ds, port); - mt7530_port_set_vlan_aware(ds, MT7530_CPU_PORT); + mt7530_port_set_vlan_aware(ds, cpu_dp->index); } else { mt7530_port_set_vlan_unaware(ds, port); } @@ -1527,11 +1540,11 @@ static void mt7530_hw_vlan_add(struct mt7530_priv *priv, struct mt7530_hw_vlan_entry *entry) { + struct dsa_port *dp = dsa_to_port(priv->ds, entry->port); u8 new_members; u32 val; - new_members = entry->old_members | BIT(entry->port) | - BIT(MT7530_CPU_PORT); + new_members = entry->old_members | BIT(entry->port); /* Validate the entry with independent learning, create egress tag per * VLAN and joining the port as one of the port members. @@ -1542,22 +1555,20 @@ mt7530_hw_vlan_add(struct mt7530_priv *priv, /* Decide whether adding tag or not for those outgoing packets from the * port inside the VLAN. - */ - val = entry->untagged ? MT7530_VLAN_EGRESS_UNTAG : - MT7530_VLAN_EGRESS_TAG; - mt7530_rmw(priv, MT7530_VAWD2, - ETAG_CTRL_P_MASK(entry->port), - ETAG_CTRL_P(entry->port, val)); - - /* CPU port is always taken as a tagged port for serving more than one + * CPU port is always taken as a tagged port for serving more than one * VLANs across and also being applied with egress type stack mode for * that VLAN tags would be appended after hardware special tag used as * DSA tag. */ + if (dsa_port_is_cpu(dp)) + val = MT7530_VLAN_EGRESS_STACK; + else if (entry->untagged) + val = MT7530_VLAN_EGRESS_UNTAG; + else + val = MT7530_VLAN_EGRESS_TAG; mt7530_rmw(priv, MT7530_VAWD2, - ETAG_CTRL_P_MASK(MT7530_CPU_PORT), - ETAG_CTRL_P(MT7530_CPU_PORT, - MT7530_VLAN_EGRESS_STACK)); + ETAG_CTRL_P_MASK(entry->port), + ETAG_CTRL_P(entry->port, val)); } static void @@ -1576,11 +1587,7 @@ mt7530_hw_vlan_del(struct mt7530_priv *priv, return; } - /* If certain member apart from CPU port is still alive in the VLAN, - * the entry would be kept valid. Otherwise, the entry is got to be - * disabled. - */ - if (new_members && new_members != BIT(MT7530_CPU_PORT)) { + if (new_members) { val = IVL_MAC | VTAG_EN | PORT_MEM(new_members) | VLAN_VALID; mt7530_write(priv, MT7530_VAWD1, val); @@ -2098,11 +2105,12 @@ static int mt7530_setup(struct dsa_switch *ds) { struct mt7530_priv *priv = ds->priv; + struct device_node *dn = NULL; struct device_node *phy_node; struct device_node *mac_np; struct mt7530_dummy_poll p; phy_interface_t interface; - struct device_node *dn; + struct dsa_port *cpu_dp; u32 id, val; int ret, i; @@ -2110,7 +2118,19 @@ mt7530_setup(struct dsa_switch *ds) * controller also is the container for two GMACs nodes representing * as two netdev instances. */ - dn = dsa_to_port(ds, MT7530_CPU_PORT)->master->dev.of_node->parent; + dsa_switch_for_each_cpu_port(cpu_dp, ds) { + dn = cpu_dp->master->dev.of_node->parent; + /* It doesn't matter which CPU port is found first, + * their masters should share the same parent OF node + */ + break; + } + + if (!dn) { + dev_err(ds->dev, "parent OF node of DSA master not found"); + return -EINVAL; + } + ds->assisted_learning_on_cpu_port = true; ds->mtu_enforcement_ingress = true; @@ -2272,6 +2292,7 @@ mt7531_setup(struct dsa_switch *ds) { struct mt7530_priv *priv = ds->priv; struct mt7530_dummy_poll p; + struct dsa_port *cpu_dp; u32 val, id; int ret, i; @@ -2344,8 +2365,11 @@ mt7531_setup(struct dsa_switch *ds) CORE_PLL_GROUP4, val); /* BPDU to CPU port */ - mt7530_rmw(priv, MT7531_CFC, MT7531_CPU_PMAP_MASK, - BIT(MT7530_CPU_PORT)); + dsa_switch_for_each_cpu_port(cpu_dp, ds) { + mt7530_rmw(priv, MT7531_CFC, MT7531_CPU_PMAP_MASK, + BIT(cpu_dp->index)); + break; + } mt7530_rmw(priv, MT753X_BPC, MT753X_BPDU_PORT_FW_MASK, MT753X_BPDU_CPU_ONLY); diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h index 71e36b69b96d..e509af95c354 100644 --- a/drivers/net/dsa/mt7530.h +++ b/drivers/net/dsa/mt7530.h @@ -8,7 +8,6 @@ #define MT7530_NUM_PORTS 7 #define MT7530_NUM_PHYS 5 -#define MT7530_CPU_PORT 6 #define MT7530_NUM_FDB_RECORDS 2048 #define MT7530_ALL_MEMBERS 0xff diff --git a/drivers/net/eql.c b/drivers/net/eql.c index 557ca8ff9dec..ca3e4700a813 100644 --- a/drivers/net/eql.c +++ b/drivers/net/eql.c @@ -225,7 +225,7 @@ static void eql_kill_one_slave(slave_queue_t *queue, slave_t *slave) list_del(&slave->list); queue->num_slaves--; slave->dev->flags &= ~IFF_SLAVE; - dev_put_track(slave->dev, &slave->dev_tracker); + netdev_put(slave->dev, &slave->dev_tracker); kfree(slave); } @@ -399,7 +399,7 @@ static int __eql_insert_slave(slave_queue_t *queue, slave_t *slave) if (duplicate_slave) eql_kill_one_slave(queue, duplicate_slave); - dev_hold_track(slave->dev, &slave->dev_tracker, GFP_ATOMIC); + netdev_hold(slave->dev, &slave->dev_tracker, GFP_ATOMIC); list_add(&slave->list, &queue->all_slaves); queue->num_slaves++; slave->dev->flags |= IFF_SLAVE; diff --git a/drivers/net/ethernet/altera/altera_utils.h b/drivers/net/ethernet/altera/altera_utils.h index b7d772f2dcbb..3c2e32fb7389 100644 --- a/drivers/net/ethernet/altera/altera_utils.h +++ b/drivers/net/ethernet/altera/altera_utils.h @@ -3,11 +3,12 @@ * Copyright (C) 2014 Altera Corporation. All rights reserved */ -#include <linux/kernel.h> - #ifndef __ALTERA_UTILS_H__ #define __ALTERA_UTILS_H__ +#include <linux/compiler.h> +#include <linux/types.h> + void tse_set_bit(void __iomem *ioaddr, size_t offs, u32 bit_mask); void tse_clear_bit(void __iomem *ioaddr, size_t offs, u32 bit_mask); int tse_bit_is_set(void __iomem *ioaddr, size_t offs, u32 bit_mask); diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c index 698438a2ee0f..514d61dd91c7 100644 --- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c +++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c @@ -388,7 +388,7 @@ static int bcm_enet_receive_queue(struct net_device *dev, int budget) priv->rx_buf_size, DMA_FROM_DEVICE); priv->rx_buf[desc_idx] = NULL; - skb = build_skb(buf, priv->rx_frag_size); + skb = napi_build_skb(buf, priv->rx_frag_size); if (unlikely(!skb)) { skb_free_frag(buf); dev->stats.rx_dropped++; @@ -468,7 +468,7 @@ static int bcm_enet_tx_reclaim(struct net_device *dev, int force) dev->stats.tx_errors++; bytes += skb->len; - dev_kfree_skb(skb); + napi_consume_skb(skb, !force); released++; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c index ddf2f3963abe..c4ed43604ddc 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c @@ -307,7 +307,7 @@ int bnxt_set_vf_bw(struct net_device *dev, int vf_id, int min_tx_rate, return -EINVAL; } - if (min_tx_rate > pf_link_speed || min_tx_rate > max_tx_rate) { + if (min_tx_rate > pf_link_speed) { netdev_info(bp->dev, "min tx rate %d is invalid for VF %d\n", min_tx_rate, vf_id); return -EINVAL; diff --git a/drivers/net/ethernet/cadence/macb_ptp.c b/drivers/net/ethernet/cadence/macb_ptp.c index 9559c16078f9..e6cb20aaa76a 100644 --- a/drivers/net/ethernet/cadence/macb_ptp.c +++ b/drivers/net/ethernet/cadence/macb_ptp.c @@ -434,7 +434,7 @@ int gem_get_hwtst(struct net_device *dev, struct ifreq *rq) return 0; } -static int gem_ptp_set_one_step_sync(struct macb *bp, u8 enable) +static void gem_ptp_set_one_step_sync(struct macb *bp, u8 enable) { u32 reg_val; @@ -444,8 +444,6 @@ static int gem_ptp_set_one_step_sync(struct macb *bp, u8 enable) macb_writel(bp, NCR, reg_val | MACB_BIT(OSSMODE)); else macb_writel(bp, NCR, reg_val & ~MACB_BIT(OSSMODE)); - - return 0; } int gem_set_hwtst(struct net_device *dev, struct ifreq *ifr, int cmd) @@ -468,8 +466,7 @@ int gem_set_hwtst(struct net_device *dev, struct ifreq *ifr, int cmd) case HWTSTAMP_TX_OFF: break; case HWTSTAMP_TX_ONESTEP_SYNC: - if (gem_ptp_set_one_step_sync(bp, 1) != 0) - return -ERANGE; + gem_ptp_set_one_step_sync(bp, 1); tx_bd_control = TSTAMP_ALL_FRAMES; break; case HWTSTAMP_TX_ON: diff --git a/drivers/net/ethernet/huawei/hinic/hinic_sriov.c b/drivers/net/ethernet/huawei/hinic/hinic_sriov.c index 01e7d3c0b68e..df555847afb5 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_sriov.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_sriov.c @@ -852,12 +852,6 @@ int hinic_ndo_set_vf_bw(struct net_device *netdev, return -EINVAL; } - if (max_tx_rate < min_tx_rate) { - netif_err(nic_dev, drv, netdev, "Max rate %d must be greater than or equal to min rate %d\n", - max_tx_rate, min_tx_rate); - return -EINVAL; - } - err = hinic_port_link_state(nic_dev, &link_state); if (err) { netif_err(nic_dev, drv, netdev, diff --git a/drivers/net/ethernet/intel/e1000/e1000_hw.c b/drivers/net/ethernet/intel/e1000/e1000_hw.c index 1042e79a1397..f8860f24ede0 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_hw.c +++ b/drivers/net/ethernet/intel/e1000/e1000_hw.c @@ -4376,7 +4376,7 @@ void e1000_rar_set(struct e1000_hw *hw, u8 *addr, u32 index) /** * e1000_write_vfta - Writes a value to the specified offset in the VLAN filter table. * @hw: Struct containing variables accessed by shared code - * @offset: Offset in VLAN filer table to write + * @offset: Offset in VLAN filter table to write * @value: Value to write into VLAN filter table */ void e1000_write_vfta(struct e1000_hw *hw, u32 offset, u32 value) @@ -4396,7 +4396,7 @@ void e1000_write_vfta(struct e1000_hw *hw, u32 offset, u32 value) } /** - * e1000_clear_vfta - Clears the VLAN filer table + * e1000_clear_vfta - Clears the VLAN filter table * @hw: Struct containing variables accessed by shared code */ static void e1000_clear_vfta(struct e1000_hw *hw) diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c index 30ca9ee1900b..f2fba6e1d0f7 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c @@ -1825,7 +1825,7 @@ static void fm10k_sm_mbx_process_error(struct fm10k_mbx_info *mbx) fm10k_sm_mbx_connect_reset(mbx); break; case FM10K_STATE_CONNECT: - /* try connnecting at lower version */ + /* try connecting at lower version */ if (mbx->remote) { while (mbx->local > 1) mbx->local--; diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 18558a019353..57f4ec4f8d2f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -565,6 +565,7 @@ struct i40e_pf { #define I40E_FLAG_DISABLE_FW_LLDP BIT(24) #define I40E_FLAG_RS_FEC BIT(25) #define I40E_FLAG_BASE_R_FEC BIT(26) +#define I40E_FLAG_VF_VLAN_PRUNING BIT(27) /* TOTAL_PORT_SHUTDOWN * Allows to physically disable the link on the NIC's port. * If enabled, (after link down request from the OS) diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 19704f5c8291..552aad6ae1ca 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -457,6 +457,8 @@ static const struct i40e_priv_flags i40e_gstrings_priv_flags[] = { I40E_PRIV_FLAG("disable-fw-lldp", I40E_FLAG_DISABLE_FW_LLDP, 0), I40E_PRIV_FLAG("rs-fec", I40E_FLAG_RS_FEC, 0), I40E_PRIV_FLAG("base-r-fec", I40E_FLAG_BASE_R_FEC, 0), + I40E_PRIV_FLAG("vf-vlan-pruning", + I40E_FLAG_VF_VLAN_PRUNING, 0), }; #define I40E_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40e_gstrings_priv_flags) @@ -5294,6 +5296,13 @@ flags_complete: return -EOPNOTSUPP; } + if ((changed_flags & I40E_FLAG_VF_VLAN_PRUNING) && + pf->num_alloc_vfs) { + dev_warn(&pf->pdev->dev, + "Changing vf-vlan-pruning flag while VF(s) are active is not supported\n"); + return -EOPNOTSUPP; + } + if ((changed_flags & new_flags & I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED) && (new_flags & I40E_FLAG_MFP_ENABLED)) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 72576bb3e94d..83e0cf475ebd 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -1369,6 +1369,114 @@ static int i40e_correct_mac_vlan_filters(struct i40e_vsi *vsi, } /** + * i40e_get_vf_new_vlan - Get new vlan id on a vf + * @vsi: the vsi to configure + * @new_mac: new mac filter to be added + * @f: existing mac filter, replaced with new_mac->f if new_mac is not NULL + * @vlan_filters: the number of active VLAN filters + * @trusted: flag if the VF is trusted + * + * Get new VLAN id based on current VLAN filters, trust, PVID + * and vf-vlan-prune-disable flag. + * + * Returns the value of the new vlan filter or + * the old value if no new filter is needed. + */ +static s16 i40e_get_vf_new_vlan(struct i40e_vsi *vsi, + struct i40e_new_mac_filter *new_mac, + struct i40e_mac_filter *f, + int vlan_filters, + bool trusted) +{ + s16 pvid = le16_to_cpu(vsi->info.pvid); + struct i40e_pf *pf = vsi->back; + bool is_any; + + if (new_mac) + f = new_mac->f; + + if (pvid && f->vlan != pvid) + return pvid; + + is_any = (trusted || + !(pf->flags & I40E_FLAG_VF_VLAN_PRUNING)); + + if ((vlan_filters && f->vlan == I40E_VLAN_ANY) || + (!is_any && !vlan_filters && f->vlan == I40E_VLAN_ANY) || + (is_any && !vlan_filters && f->vlan == 0)) { + if (is_any) + return I40E_VLAN_ANY; + else + return 0; + } + + return f->vlan; +} + +/** + * i40e_correct_vf_mac_vlan_filters - Correct non-VLAN VF filters if necessary + * @vsi: the vsi to configure + * @tmp_add_list: list of filters ready to be added + * @tmp_del_list: list of filters ready to be deleted + * @vlan_filters: the number of active VLAN filters + * @trusted: flag if the VF is trusted + * + * Correct VF VLAN filters based on current VLAN filters, trust, PVID + * and vf-vlan-prune-disable flag. + * + * In case of memory allocation failure return -ENOMEM. Otherwise, return 0. + * + * This function is only expected to be called from within + * i40e_sync_vsi_filters. + * + * NOTE: This function expects to be called while under the + * mac_filter_hash_lock + */ +static int i40e_correct_vf_mac_vlan_filters(struct i40e_vsi *vsi, + struct hlist_head *tmp_add_list, + struct hlist_head *tmp_del_list, + int vlan_filters, + bool trusted) +{ + struct i40e_mac_filter *f, *add_head; + struct i40e_new_mac_filter *new_mac; + struct hlist_node *h; + int bkt, new_vlan; + + hlist_for_each_entry(new_mac, tmp_add_list, hlist) { + new_mac->f->vlan = i40e_get_vf_new_vlan(vsi, new_mac, NULL, + vlan_filters, trusted); + } + + hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) { + new_vlan = i40e_get_vf_new_vlan(vsi, NULL, f, vlan_filters, + trusted); + if (new_vlan != f->vlan) { + add_head = i40e_add_filter(vsi, f->macaddr, new_vlan); + if (!add_head) + return -ENOMEM; + /* Create a temporary i40e_new_mac_filter */ + new_mac = kzalloc(sizeof(*new_mac), GFP_ATOMIC); + if (!new_mac) + return -ENOMEM; + new_mac->f = add_head; + new_mac->state = add_head->state; + + /* Add the new filter to the tmp list */ + hlist_add_head(&new_mac->hlist, tmp_add_list); + + /* Put the original filter into the delete list */ + f->state = I40E_FILTER_REMOVE; + hash_del(&f->hlist); + hlist_add_head(&f->hlist, tmp_del_list); + } + } + + vsi->has_vlan_filter = !!vlan_filters; + return 0; +} + +/** * i40e_rm_default_mac_filter - Remove the default MAC filter set by NVM * @vsi: the PF Main VSI - inappropriate for any other VSI * @macaddr: the MAC address @@ -2423,10 +2531,14 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) vlan_filters++; } - retval = i40e_correct_mac_vlan_filters(vsi, - &tmp_add_list, - &tmp_del_list, - vlan_filters); + if (vsi->type != I40E_VSI_SRIOV) + retval = i40e_correct_mac_vlan_filters + (vsi, &tmp_add_list, &tmp_del_list, + vlan_filters); + else + retval = i40e_correct_vf_mac_vlan_filters + (vsi, &tmp_add_list, &tmp_del_list, + vlan_filters, pf->vf[vsi->vf_id].trusted); hlist_for_each_entry(new, &tmp_add_list, hlist) netdev_hw_addr_refcnt(new->f, vsi->netdev, 1); @@ -2855,8 +2967,21 @@ int i40e_add_vlan_all_mac(struct i40e_vsi *vsi, s16 vid) int bkt; hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) { - if (f->state == I40E_FILTER_REMOVE) + /* If we're asked to add a filter that has been marked for + * removal, it is safe to simply restore it to active state. + * __i40e_del_filter will have simply deleted any filters which + * were previously marked NEW or FAILED, so if it is currently + * marked REMOVE it must have previously been ACTIVE. Since we + * haven't yet run the sync filters task, just restore this + * filter to the ACTIVE state so that the sync task leaves it + * in place. + */ + if (f->state == I40E_FILTER_REMOVE && f->vlan == vid) { + f->state = I40E_FILTER_ACTIVE; + continue; + } else if (f->state == I40E_FILTER_REMOVE) { continue; + } add_f = i40e_add_filter(vsi, f->macaddr, vid); if (!add_f) { dev_info(&vsi->back->pdev->dev, diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 7bc1174edf6b..b7967105a549 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -2509,6 +2509,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) hard_start = page_address(rx_buffer->page) + rx_buffer->page_offset - offset; xdp_prepare_buff(&xdp, hard_start, offset, size, true); + xdp_buff_clear_frags_flag(&xdp); #if (PAGE_SIZE > 4096) /* At larger PAGE_SIZE, frame_sz depend on len size */ xdp.frame_sz = i40e_rx_frame_truesize(rx_ring, size); @@ -3713,35 +3714,55 @@ u16 i40e_lan_select_queue(struct net_device *netdev, static int i40e_xmit_xdp_ring(struct xdp_frame *xdpf, struct i40e_ring *xdp_ring) { - u16 i = xdp_ring->next_to_use; - struct i40e_tx_buffer *tx_bi; - struct i40e_tx_desc *tx_desc; + struct skb_shared_info *sinfo = xdp_get_shared_info_from_frame(xdpf); + u8 nr_frags = unlikely(xdp_frame_has_frags(xdpf)) ? sinfo->nr_frags : 0; + u16 i = 0, index = xdp_ring->next_to_use; + struct i40e_tx_buffer *tx_head = &xdp_ring->tx_bi[index]; + struct i40e_tx_buffer *tx_bi = tx_head; + struct i40e_tx_desc *tx_desc = I40E_TX_DESC(xdp_ring, index); void *data = xdpf->data; u32 size = xdpf->len; - dma_addr_t dma; - if (!unlikely(I40E_DESC_UNUSED(xdp_ring))) { + if (unlikely(I40E_DESC_UNUSED(xdp_ring) < 1 + nr_frags)) { xdp_ring->tx_stats.tx_busy++; return I40E_XDP_CONSUMED; } - dma = dma_map_single(xdp_ring->dev, data, size, DMA_TO_DEVICE); - if (dma_mapping_error(xdp_ring->dev, dma)) - return I40E_XDP_CONSUMED; - tx_bi = &xdp_ring->tx_bi[i]; - tx_bi->bytecount = size; - tx_bi->gso_segs = 1; - tx_bi->xdpf = xdpf; + tx_head->bytecount = xdp_get_frame_len(xdpf); + tx_head->gso_segs = 1; + tx_head->xdpf = xdpf; - /* record length, and DMA address */ - dma_unmap_len_set(tx_bi, len, size); - dma_unmap_addr_set(tx_bi, dma, dma); + for (;;) { + dma_addr_t dma; - tx_desc = I40E_TX_DESC(xdp_ring, i); - tx_desc->buffer_addr = cpu_to_le64(dma); - tx_desc->cmd_type_offset_bsz = build_ctob(I40E_TX_DESC_CMD_ICRC - | I40E_TXD_CMD, - 0, size, 0); + dma = dma_map_single(xdp_ring->dev, data, size, DMA_TO_DEVICE); + if (dma_mapping_error(xdp_ring->dev, dma)) + goto unmap; + + /* record length, and DMA address */ + dma_unmap_len_set(tx_bi, len, size); + dma_unmap_addr_set(tx_bi, dma, dma); + + tx_desc->buffer_addr = cpu_to_le64(dma); + tx_desc->cmd_type_offset_bsz = + build_ctob(I40E_TX_DESC_CMD_ICRC, 0, size, 0); + + if (++index == xdp_ring->count) + index = 0; + + if (i == nr_frags) + break; + + tx_bi = &xdp_ring->tx_bi[index]; + tx_desc = I40E_TX_DESC(xdp_ring, index); + + data = skb_frag_address(&sinfo->frags[i]); + size = skb_frag_size(&sinfo->frags[i]); + i++; + } + + tx_desc->cmd_type_offset_bsz |= + cpu_to_le64(I40E_TXD_CMD << I40E_TXD_QW1_CMD_SHIFT); /* Make certain all of the status bits have been updated * before next_to_watch is written. @@ -3749,14 +3770,30 @@ static int i40e_xmit_xdp_ring(struct xdp_frame *xdpf, smp_wmb(); xdp_ring->xdp_tx_active++; - i++; - if (i == xdp_ring->count) - i = 0; - tx_bi->next_to_watch = tx_desc; - xdp_ring->next_to_use = i; + tx_head->next_to_watch = tx_desc; + xdp_ring->next_to_use = index; return I40E_XDP_TX; + +unmap: + for (;;) { + tx_bi = &xdp_ring->tx_bi[index]; + if (dma_unmap_len(tx_bi, len)) + dma_unmap_page(xdp_ring->dev, + dma_unmap_addr(tx_bi, dma), + dma_unmap_len(tx_bi, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_bi, len, 0); + if (tx_bi == tx_head) + break; + + if (!index) + index += xdp_ring->count; + index--; + } + + return I40E_XDP_CONSUMED; } /** diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 033ea71763e3..d01fb592778c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -4349,6 +4349,7 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id, /* duplicate request, so just return success */ goto error_pvid; + i40e_vlan_stripping_enable(vsi); i40e_vc_reset_vf(vf, true); /* During reset the VF got a new VSI, so refresh a pointer. */ vsi = pf->vsi[vf->lan_vsi_idx]; @@ -4364,7 +4365,7 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id, * MAC addresses deleted. */ if ((!(vlan_id || qos) || - vlanprio != le16_to_cpu(vsi->info.pvid)) && + vlanprio != le16_to_cpu(vsi->info.pvid)) && vsi->info.pvid) { ret = i40e_add_vlan_all_mac(vsi, I40E_VLAN_ANY); if (ret) { @@ -4727,6 +4728,11 @@ int i40e_ndo_set_vf_trust(struct net_device *netdev, int vf_id, bool setting) goto out; vf->trusted = setting; + + /* request PF to sync mac/vlan filters for the VF */ + set_bit(__I40E_MACVLAN_SYNC_PENDING, pf->state); + pf->vsi[vf->lan_vsi_idx]->flags |= I40E_VSI_FLAG_FILTER_CHANGED; + i40e_vc_reset_vf(vf, true); dev_info(&pf->pdev->dev, "VF %u is now %strusted\n", vf_id, setting ? "" : "un"); diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index 49aed3e506a6..fda1198d2c00 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -146,7 +146,8 @@ struct iavf_mac_filter { u8 remove:1; /* filter needs to be removed */ u8 add:1; /* filter needs to be added */ u8 is_primary:1; /* filter is a default VF MAC */ - u8 padding:4; + u8 add_handled:1; /* received response for filter add */ + u8 padding:3; }; }; @@ -248,6 +249,7 @@ struct iavf_adapter { struct work_struct adminq_task; struct delayed_work client_task; wait_queue_head_t down_waitqueue; + wait_queue_head_t vc_waitqueue; struct iavf_q_vector *q_vectors; struct list_head vlan_filter_list; struct list_head mac_filter_list; @@ -292,6 +294,7 @@ struct iavf_adapter { #define IAVF_FLAG_QUEUES_DISABLED BIT(17) #define IAVF_FLAG_SETUP_NETDEV_FEATURES BIT(18) #define IAVF_FLAG_REINIT_MSIX_NEEDED BIT(20) +#define IAVF_FLAG_INITIAL_MAC_SET BIT(23) /* duplicates for common code */ #define IAVF_FLAG_DCB_ENABLED 0 /* flags for admin queue service task */ @@ -559,6 +562,8 @@ void iavf_enable_vlan_stripping_v2(struct iavf_adapter *adapter, u16 tpid); void iavf_disable_vlan_stripping_v2(struct iavf_adapter *adapter, u16 tpid); void iavf_enable_vlan_insertion_v2(struct iavf_adapter *adapter, u16 tpid); void iavf_disable_vlan_insertion_v2(struct iavf_adapter *adapter, u16 tpid); +int iavf_replace_primary_mac(struct iavf_adapter *adapter, + const u8 *new_mac); void iavf_set_vlan_offload_features(struct iavf_adapter *adapter, netdev_features_t prev_features, diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index f3ecb3bca33d..541103909ef4 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -983,6 +983,7 @@ struct iavf_mac_filter *iavf_add_filter(struct iavf_adapter *adapter, list_add_tail(&f->list, &adapter->mac_filter_list); f->add = true; + f->add_handled = false; f->is_new_mac = true; f->is_primary = ether_addr_equal(macaddr, adapter->hw.mac.addr); adapter->aq_required |= IAVF_FLAG_AQ_ADD_MAC_FILTER; @@ -994,47 +995,132 @@ struct iavf_mac_filter *iavf_add_filter(struct iavf_adapter *adapter, } /** - * iavf_set_mac - NDO callback to set port mac address - * @netdev: network interface device structure - * @p: pointer to an address structure + * iavf_replace_primary_mac - Replace current primary address + * @adapter: board private structure + * @new_mac: new MAC address to be applied * - * Returns 0 on success, negative on failure + * Replace current dev_addr and send request to PF for removal of previous + * primary MAC address filter and addition of new primary MAC filter. + * Return 0 for success, -ENOMEM for failure. + * + * Do not call this with mac_vlan_list_lock! **/ -static int iavf_set_mac(struct net_device *netdev, void *p) +int iavf_replace_primary_mac(struct iavf_adapter *adapter, + const u8 *new_mac) { - struct iavf_adapter *adapter = netdev_priv(netdev); struct iavf_hw *hw = &adapter->hw; struct iavf_mac_filter *f; - struct sockaddr *addr = p; - - if (!is_valid_ether_addr(addr->sa_data)) - return -EADDRNOTAVAIL; - - if (ether_addr_equal(netdev->dev_addr, addr->sa_data)) - return 0; spin_lock_bh(&adapter->mac_vlan_list_lock); + list_for_each_entry(f, &adapter->mac_filter_list, list) { + f->is_primary = false; + } + f = iavf_find_filter(adapter, hw->mac.addr); if (f) { f->remove = true; - f->is_primary = true; adapter->aq_required |= IAVF_FLAG_AQ_DEL_MAC_FILTER; } - f = iavf_add_filter(adapter, addr->sa_data); + f = iavf_add_filter(adapter, new_mac); + if (f) { + /* Always send the request to add if changing primary MAC + * even if filter is already present on the list + */ f->is_primary = true; - ether_addr_copy(hw->mac.addr, addr->sa_data); + f->add = true; + adapter->aq_required |= IAVF_FLAG_AQ_ADD_MAC_FILTER; + ether_addr_copy(hw->mac.addr, new_mac); } spin_unlock_bh(&adapter->mac_vlan_list_lock); /* schedule the watchdog task to immediately process the request */ - if (f) + if (f) { queue_work(iavf_wq, &adapter->watchdog_task.work); + return 0; + } + return -ENOMEM; +} + +/** + * iavf_is_mac_set_handled - wait for a response to set MAC from PF + * @netdev: network interface device structure + * @macaddr: MAC address to set + * + * Returns true on success, false on failure + */ +static bool iavf_is_mac_set_handled(struct net_device *netdev, + const u8 *macaddr) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + struct iavf_mac_filter *f; + bool ret = false; + + spin_lock_bh(&adapter->mac_vlan_list_lock); + + f = iavf_find_filter(adapter, macaddr); - return (f == NULL) ? -ENOMEM : 0; + if (!f || (!f->add && f->add_handled)) + ret = true; + + spin_unlock_bh(&adapter->mac_vlan_list_lock); + + return ret; +} + +/** + * iavf_set_mac - NDO callback to set port MAC address + * @netdev: network interface device structure + * @p: pointer to an address structure + * + * Returns 0 on success, negative on failure + */ +static int iavf_set_mac(struct net_device *netdev, void *p) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + struct sockaddr *addr = p; + bool handle_mac = iavf_is_mac_set_handled(netdev, addr->sa_data); + int ret; + + if (!is_valid_ether_addr(addr->sa_data)) + return -EADDRNOTAVAIL; + + ret = iavf_replace_primary_mac(adapter, addr->sa_data); + + if (ret) + return ret; + + /* If this is an initial set MAC during VF spawn do not wait */ + if (adapter->flags & IAVF_FLAG_INITIAL_MAC_SET) { + adapter->flags &= ~IAVF_FLAG_INITIAL_MAC_SET; + return 0; + } + + if (handle_mac) + goto done; + + ret = wait_event_interruptible_timeout(adapter->vc_waitqueue, false, msecs_to_jiffies(2500)); + + /* If ret < 0 then it means wait was interrupted. + * If ret == 0 then it means we got a timeout. + * else it means we got response for set MAC from PF, + * check if netdev MAC was updated to requested MAC, + * if yes then set MAC succeeded otherwise it failed return -EACCES + */ + if (ret < 0) + return ret; + + if (!ret) + return -EAGAIN; + +done: + if (!ether_addr_equal(netdev->dev_addr, addr->sa_data)) + return -EACCES; + + return 0; } /** @@ -2451,6 +2537,8 @@ static void iavf_init_config_adapter(struct iavf_adapter *adapter) ether_addr_copy(netdev->perm_addr, adapter->hw.mac.addr); } + adapter->flags |= IAVF_FLAG_INITIAL_MAC_SET; + adapter->tx_desc_count = IAVF_DEFAULT_TXD; adapter->rx_desc_count = IAVF_DEFAULT_RXD; err = iavf_init_interrupt_scheme(adapter); @@ -4681,6 +4769,9 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* Setup the wait queue for indicating transition to down status */ init_waitqueue_head(&adapter->down_waitqueue); + /* Setup the wait queue for indicating virtchannel events */ + init_waitqueue_head(&adapter->vc_waitqueue); + return 0; err_ioremap: diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 782450d5c12f..e2b4ba98f71e 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -598,6 +598,8 @@ static void iavf_mac_add_ok(struct iavf_adapter *adapter) spin_lock_bh(&adapter->mac_vlan_list_lock); list_for_each_entry_safe(f, ftmp, &adapter->mac_filter_list, list) { f->is_new_mac = false; + if (!f->add && !f->add_handled) + f->add_handled = true; } spin_unlock_bh(&adapter->mac_vlan_list_lock); } @@ -618,6 +620,9 @@ static void iavf_mac_add_reject(struct iavf_adapter *adapter) if (f->remove && ether_addr_equal(f->macaddr, netdev->dev_addr)) f->remove = false; + if (!f->add && !f->add_handled) + f->add_handled = true; + if (f->is_new_mac) { list_del(&f->list); kfree(f); @@ -1932,6 +1937,7 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, iavf_mac_add_reject(adapter); /* restore administratively set MAC address */ ether_addr_copy(adapter->hw.mac.addr, netdev->dev_addr); + wake_up(&adapter->vc_waitqueue); break; case VIRTCHNL_OP_DEL_VLAN: dev_err(&adapter->pdev->dev, "Failed to delete VLAN filter, error %s\n", @@ -2091,7 +2097,13 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, if (!v_retval) iavf_mac_add_ok(adapter); if (!ether_addr_equal(netdev->dev_addr, adapter->hw.mac.addr)) - eth_hw_addr_set(netdev, adapter->hw.mac.addr); + if (!ether_addr_equal(netdev->dev_addr, + adapter->hw.mac.addr)) { + netif_addr_lock_bh(netdev); + eth_hw_addr_set(netdev, adapter->hw.mac.addr); + netif_addr_unlock_bh(netdev); + } + wake_up(&adapter->vc_waitqueue); break; case VIRTCHNL_OP_GET_STATS: { struct iavf_eth_stats *stats = @@ -2121,10 +2133,11 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, /* restore current mac address */ ether_addr_copy(adapter->hw.mac.addr, netdev->dev_addr); } else { + netif_addr_lock_bh(netdev); /* refresh current mac address if changed */ - eth_hw_addr_set(netdev, adapter->hw.mac.addr); ether_addr_copy(netdev->perm_addr, adapter->hw.mac.addr); + netif_addr_unlock_bh(netdev); } spin_lock_bh(&adapter->mac_vlan_list_lock); iavf_add_filter(adapter, adapter->hw.mac.addr); @@ -2160,6 +2173,10 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, } fallthrough; case VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS: { + struct iavf_mac_filter *f; + bool was_mac_changed; + u64 aq_required = 0; + if (v_opcode == VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS) memcpy(&adapter->vlan_v2_caps, msg, min_t(u16, msglen, @@ -2167,6 +2184,46 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, iavf_process_config(adapter); adapter->flags |= IAVF_FLAG_SETUP_NETDEV_FEATURES; + was_mac_changed = !ether_addr_equal(netdev->dev_addr, + adapter->hw.mac.addr); + + spin_lock_bh(&adapter->mac_vlan_list_lock); + + /* re-add all MAC filters */ + list_for_each_entry(f, &adapter->mac_filter_list, list) { + if (was_mac_changed && + ether_addr_equal(netdev->dev_addr, f->macaddr)) + ether_addr_copy(f->macaddr, + adapter->hw.mac.addr); + + f->is_new_mac = true; + f->add = true; + f->add_handled = false; + f->remove = false; + } + + /* re-add all VLAN filters */ + if (VLAN_FILTERING_ALLOWED(adapter)) { + struct iavf_vlan_filter *vlf; + + if (!list_empty(&adapter->vlan_filter_list)) { + list_for_each_entry(vlf, + &adapter->vlan_filter_list, + list) + vlf->add = true; + + aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER; + } + } + + spin_unlock_bh(&adapter->mac_vlan_list_lock); + + netif_addr_lock_bh(netdev); + eth_hw_addr_set(netdev, adapter->hw.mac.addr); + netif_addr_unlock_bh(netdev); + + adapter->aq_required |= IAVF_FLAG_AQ_ADD_MAC_FILTER | + aq_required; } break; case VIRTCHNL_OP_ENABLE_QUEUES: diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c index 5d10c4f84a36..ead6d50fc0ad 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c @@ -852,7 +852,7 @@ ice_create_init_fdir_rule(struct ice_pf *pf, enum ice_fltr_ptype flow) if (!seg) return -ENOMEM; - tun_seg = devm_kcalloc(dev, sizeof(*seg), ICE_FD_HW_SEG_MAX, + tun_seg = devm_kcalloc(dev, ICE_FD_HW_SEG_MAX, sizeof(*tun_seg), GFP_KERNEL); if (!tun_seg) { devm_kfree(dev, seg); @@ -1214,7 +1214,7 @@ ice_cfg_fdir_xtrct_seq(struct ice_pf *pf, struct ethtool_rx_flow_spec *fsp, if (!seg) return -ENOMEM; - tun_seg = devm_kcalloc(dev, sizeof(*seg), ICE_FD_HW_SEG_MAX, + tun_seg = devm_kcalloc(dev, ICE_FD_HW_SEG_MAX, sizeof(*tun_seg), GFP_KERNEL); if (!tun_seg) { devm_kfree(dev, seg); diff --git a/drivers/net/ethernet/intel/ice/ice_gnss.c b/drivers/net/ethernet/intel/ice/ice_gnss.c index 57586a2e6dec..c6d755f707aa 100644 --- a/drivers/net/ethernet/intel/ice/ice_gnss.c +++ b/drivers/net/ethernet/intel/ice/ice_gnss.c @@ -17,13 +17,13 @@ static void ice_gnss_read(struct kthread_work *work) struct gnss_serial *gnss = container_of(work, struct gnss_serial, read_work.work); struct ice_aqc_link_topo_addr link_topo; - u8 i2c_params, bytes_read; + unsigned int i, bytes_read, data_len; struct tty_port *port; struct ice_pf *pf; struct ice_hw *hw; __be16 data_len_b; char *buf = NULL; - u16 i, data_len; + u8 i2c_params; int err = 0; pf = gnss->back; @@ -65,7 +65,7 @@ static void ice_gnss_read(struct kthread_work *work) mdelay(10); } - data_len = min(data_len, (u16)PAGE_SIZE); + data_len = min_t(typeof(data_len), data_len, PAGE_SIZE); data_len = tty_buffer_request_room(port, data_len); if (!data_len) { err = -ENOMEM; @@ -74,9 +74,10 @@ static void ice_gnss_read(struct kthread_work *work) /* Read received data */ for (i = 0; i < data_len; i += bytes_read) { - u16 bytes_left = data_len - i; + unsigned int bytes_left = data_len - i; - bytes_read = min_t(typeof(bytes_left), bytes_left, ICE_MAX_I2C_DATA_SIZE); + bytes_read = min_t(typeof(bytes_left), bytes_left, + ICE_MAX_I2C_DATA_SIZE); err = ice_aq_read_i2c(hw, link_topo, ICE_GNSS_UBX_I2C_BUS_ADDR, cpu_to_le16(ICE_GNSS_UBX_EMPTY_DATA), diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 454e01ae09b9..b28fb8eacffb 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -887,6 +887,9 @@ static void ice_set_dflt_vsi_ctx(struct ice_hw *hw, struct ice_vsi_ctx *ctxt) (ICE_AQ_VSI_OUTER_TAG_VLAN_8100 << ICE_AQ_VSI_OUTER_TAG_TYPE_S) & ICE_AQ_VSI_OUTER_TAG_TYPE_M; + ctxt->info.outer_vlan_flags |= + FIELD_PREP(ICE_AQ_VSI_OUTER_VLAN_EMODE_M, + ICE_AQ_VSI_OUTER_VLAN_EMODE_NOTHING); } /* Have 1:1 UP mapping for both ingress/egress tables */ table |= ICE_UP_TABLE_TRANSLATE(0, 0); @@ -2403,7 +2406,7 @@ static void ice_set_agg_vsi(struct ice_vsi *vsi) agg_id); return; } - /* aggregator node is created, store the neeeded info */ + /* aggregator node is created, store the needed info */ agg_node->valid = true; agg_node->agg_id = agg_id; } diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c index bb1721f1321d..86093b2511d8 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.c +++ b/drivers/net/ethernet/intel/ice/ice_sriov.c @@ -1593,16 +1593,6 @@ ice_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate, goto out_put_vf; } - /* when max_tx_rate is zero that means no max Tx rate limiting, so only - * check if max_tx_rate is non-zero - */ - if (max_tx_rate && min_tx_rate > max_tx_rate) { - dev_err(dev, "Cannot set min Tx rate %d Mbps greater than max Tx rate %d Mbps\n", - min_tx_rate, max_tx_rate); - ret = -EINVAL; - goto out_put_vf; - } - if (min_tx_rate && ice_is_dcb_active(pf)) { dev_err(dev, "DCB on PF is currently enabled. VF min Tx rate limiting not allowed on this PF.\n"); ret = -EOPNOTSUPP; diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index 4547bc1f7cee..b2b5d2ee83a5 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -360,6 +360,54 @@ static u16 ice_vc_get_max_frame_size(struct ice_vf *vf) } /** + * ice_vc_get_vlan_caps + * @hw: pointer to the hw + * @vf: pointer to the VF info + * @vsi: pointer to the VSI + * @driver_caps: current driver caps + * + * Return 0 if there is no VLAN caps supported, or VLAN caps value + */ +static u32 +ice_vc_get_vlan_caps(struct ice_hw *hw, struct ice_vf *vf, struct ice_vsi *vsi, + u32 driver_caps) +{ + if (ice_is_eswitch_mode_switchdev(vf->pf)) + /* In switchdev setting VLAN from VF isn't supported */ + return 0; + + if (driver_caps & VIRTCHNL_VF_OFFLOAD_VLAN_V2) { + /* VLAN offloads based on current device configuration */ + return VIRTCHNL_VF_OFFLOAD_VLAN_V2; + } else if (driver_caps & VIRTCHNL_VF_OFFLOAD_VLAN) { + /* allow VF to negotiate VIRTCHNL_VF_OFFLOAD explicitly for + * these two conditions, which amounts to guest VLAN filtering + * and offloads being based on the inner VLAN or the + * inner/single VLAN respectively and don't allow VF to + * negotiate VIRTCHNL_VF_OFFLOAD in any other cases + */ + if (ice_is_dvm_ena(hw) && ice_vf_is_port_vlan_ena(vf)) { + return VIRTCHNL_VF_OFFLOAD_VLAN; + } else if (!ice_is_dvm_ena(hw) && + !ice_vf_is_port_vlan_ena(vf)) { + /* configure backward compatible support for VFs that + * only support VIRTCHNL_VF_OFFLOAD_VLAN, the PF is + * configured in SVM, and no port VLAN is configured + */ + ice_vf_vsi_cfg_svm_legacy_vlan_mode(vsi); + return VIRTCHNL_VF_OFFLOAD_VLAN; + } else if (ice_is_dvm_ena(hw)) { + /* configure software offloaded VLAN support when DVM + * is enabled, but no port VLAN is enabled + */ + ice_vf_vsi_cfg_dvm_legacy_vlan_mode(vsi); + } + } + + return 0; +} + +/** * ice_vc_get_vf_res_msg * @vf: pointer to the VF info * @msg: pointer to the msg buffer @@ -402,33 +450,8 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) goto err; } - if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_VLAN_V2) { - /* VLAN offloads based on current device configuration */ - vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_VLAN_V2; - } else if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_VLAN) { - /* allow VF to negotiate VIRTCHNL_VF_OFFLOAD explicitly for - * these two conditions, which amounts to guest VLAN filtering - * and offloads being based on the inner VLAN or the - * inner/single VLAN respectively and don't allow VF to - * negotiate VIRTCHNL_VF_OFFLOAD in any other cases - */ - if (ice_is_dvm_ena(hw) && ice_vf_is_port_vlan_ena(vf)) { - vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_VLAN; - } else if (!ice_is_dvm_ena(hw) && - !ice_vf_is_port_vlan_ena(vf)) { - vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_VLAN; - /* configure backward compatible support for VFs that - * only support VIRTCHNL_VF_OFFLOAD_VLAN, the PF is - * configured in SVM, and no port VLAN is configured - */ - ice_vf_vsi_cfg_svm_legacy_vlan_mode(vsi); - } else if (ice_is_dvm_ena(hw)) { - /* configure software offloaded VLAN support when DVM - * is enabled, but no port VLAN is enabled - */ - ice_vf_vsi_cfg_dvm_legacy_vlan_mode(vsi); - } - } + vfres->vf_cap_flags |= ice_vc_get_vlan_caps(hw, vf, vsi, + vf->driver_caps); if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_PF) { vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_PF; @@ -3528,42 +3551,6 @@ ice_vc_repr_del_mac(struct ice_vf __always_unused *vf, u8 __always_unused *msg) VIRTCHNL_STATUS_SUCCESS, NULL, 0); } -static int ice_vc_repr_add_vlan(struct ice_vf *vf, u8 __always_unused *msg) -{ - dev_dbg(ice_pf_to_dev(vf->pf), - "Can't add VLAN in switchdev mode for VF %d\n", vf->vf_id); - return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ADD_VLAN, - VIRTCHNL_STATUS_SUCCESS, NULL, 0); -} - -static int ice_vc_repr_del_vlan(struct ice_vf *vf, u8 __always_unused *msg) -{ - dev_dbg(ice_pf_to_dev(vf->pf), - "Can't delete VLAN in switchdev mode for VF %d\n", vf->vf_id); - return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_DEL_VLAN, - VIRTCHNL_STATUS_SUCCESS, NULL, 0); -} - -static int ice_vc_repr_ena_vlan_stripping(struct ice_vf *vf) -{ - dev_dbg(ice_pf_to_dev(vf->pf), - "Can't enable VLAN stripping in switchdev mode for VF %d\n", - vf->vf_id); - return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ENABLE_VLAN_STRIPPING, - VIRTCHNL_STATUS_ERR_NOT_SUPPORTED, - NULL, 0); -} - -static int ice_vc_repr_dis_vlan_stripping(struct ice_vf *vf) -{ - dev_dbg(ice_pf_to_dev(vf->pf), - "Can't disable VLAN stripping in switchdev mode for VF %d\n", - vf->vf_id); - return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_DISABLE_VLAN_STRIPPING, - VIRTCHNL_STATUS_ERR_NOT_SUPPORTED, - NULL, 0); -} - static int ice_vc_repr_cfg_promiscuous_mode(struct ice_vf *vf, u8 __always_unused *msg) { @@ -3590,10 +3577,10 @@ static const struct ice_virtchnl_ops ice_virtchnl_repr_ops = { .config_rss_lut = ice_vc_config_rss_lut, .get_stats_msg = ice_vc_get_stats_msg, .cfg_promiscuous_mode_msg = ice_vc_repr_cfg_promiscuous_mode, - .add_vlan_msg = ice_vc_repr_add_vlan, - .remove_vlan_msg = ice_vc_repr_del_vlan, - .ena_vlan_stripping = ice_vc_repr_ena_vlan_stripping, - .dis_vlan_stripping = ice_vc_repr_dis_vlan_stripping, + .add_vlan_msg = ice_vc_add_vlan_msg, + .remove_vlan_msg = ice_vc_remove_vlan_msg, + .ena_vlan_stripping = ice_vc_ena_vlan_stripping, + .dis_vlan_stripping = ice_vc_dis_vlan_stripping, .handle_rss_cfg_msg = ice_vc_handle_rss_cfg, .add_fdir_fltr_msg = ice_vc_add_fdir_fltr, .del_fdir_fltr_msg = ice_vc_del_fdir_fltr, diff --git a/drivers/net/ethernet/intel/igb/e1000_defines.h b/drivers/net/ethernet/intel/igb/e1000_defines.h index ca5429774994..fa028928482f 100644 --- a/drivers/net/ethernet/intel/igb/e1000_defines.h +++ b/drivers/net/ethernet/intel/igb/e1000_defines.h @@ -1033,9 +1033,6 @@ #define E1000_VFTA_ENTRY_MASK 0x7F #define E1000_VFTA_ENTRY_BIT_SHIFT_MASK 0x1F -/* DMA Coalescing register fields */ -#define E1000_PCIEMISC_LX_DECISION 0x00000080 /* Lx power on DMA coal */ - /* Tx Rate-Scheduler Config fields */ #define E1000_RTTBCNRC_RS_ENA 0x80000000 #define E1000_RTTBCNRC_RF_DEC_MASK 0x00003FFF diff --git a/drivers/net/ethernet/intel/igb/e1000_regs.h b/drivers/net/ethernet/intel/igb/e1000_regs.h index 9cb49980ec2d..eb9f6da9208a 100644 --- a/drivers/net/ethernet/intel/igb/e1000_regs.h +++ b/drivers/net/ethernet/intel/igb/e1000_regs.h @@ -116,7 +116,6 @@ #define E1000_DMCRTRH 0x05DD0 /* Receive Packet Rate Threshold */ #define E1000_DMCCNT 0x05DD4 /* Current Rx Count */ #define E1000_FCRTC 0x02170 /* Flow Control Rx high watermark */ -#define E1000_PCIEMISC 0x05BB8 /* PCIE misc config register */ /* TX Rate Limit Registers */ #define E1000_RTTDQSEL 0x3604 /* Tx Desc Plane Queue Select - WO */ diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_hw.c b/drivers/net/ethernet/intel/ixgb/ixgb_hw.c index c8d1e815ec6b..98bd3267b99b 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_hw.c +++ b/drivers/net/ethernet/intel/ixgb/ixgb_hw.c @@ -576,7 +576,7 @@ ixgb_rar_set(struct ixgb_hw *hw, * Writes a value to the specified offset in the VLAN filter table. * * hw - Struct containing variables accessed by shared code - * offset - Offset in VLAN filer table to write + * offset - Offset in VLAN filter table to write * value - Value to write into VLAN filter table *****************************************************************************/ void @@ -588,7 +588,7 @@ ixgb_write_vfta(struct ixgb_hw *hw, } /****************************************************************************** - * Clears the VLAN filer table + * Clears the VLAN filter table * * hw - Struct containing variables accessed by shared code *****************************************************************************/ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index 921a4d977d65..48444ab9e0b1 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -167,12 +167,46 @@ enum ixgbe_tx_flags { #define IXGBE_82599_VF_DEVICE_ID 0x10ED #define IXGBE_X540_VF_DEVICE_ID 0x1515 +#define UPDATE_VF_COUNTER_32bit(reg, last_counter, counter) \ + { \ + u32 current_counter = IXGBE_READ_REG(hw, reg); \ + if (current_counter < last_counter) \ + counter += 0x100000000LL; \ + last_counter = current_counter; \ + counter &= 0xFFFFFFFF00000000LL; \ + counter |= current_counter; \ + } + +#define UPDATE_VF_COUNTER_36bit(reg_lsb, reg_msb, last_counter, counter) \ + { \ + u64 current_counter_lsb = IXGBE_READ_REG(hw, reg_lsb); \ + u64 current_counter_msb = IXGBE_READ_REG(hw, reg_msb); \ + u64 current_counter = (current_counter_msb << 32) | \ + current_counter_lsb; \ + if (current_counter < last_counter) \ + counter += 0x1000000000LL; \ + last_counter = current_counter; \ + counter &= 0xFFFFFFF000000000LL; \ + counter |= current_counter; \ + } + +struct vf_stats { + u64 gprc; + u64 gorc; + u64 gptc; + u64 gotc; + u64 mprc; +}; + struct vf_data_storage { struct pci_dev *vfdev; unsigned char vf_mac_addresses[ETH_ALEN]; u16 vf_mc_hashes[IXGBE_MAX_VF_MC_ENTRIES]; u16 num_vf_mc_hashes; bool clear_to_send; + struct vf_stats vfstats; + struct vf_stats last_vfstats; + struct vf_stats saved_rst_vfstats; bool pf_set_mac; u16 pf_vlan; /* When set, guest VLAN config not allowed. */ u16 pf_qos; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c index 95c92fe890a1..100388968e4d 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c @@ -879,7 +879,7 @@ static s32 ixgbe_set_vfta_82598(struct ixgbe_hw *hw, u32 vlan, u32 vind, * ixgbe_clear_vfta_82598 - Clear VLAN filter table * @hw: pointer to hardware structure * - * Clears the VLAN filer table, and the VMDq index associated with the filter + * Clears the VLAN filter table, and the VMDq index associated with the filter **/ static s32 ixgbe_clear_vfta_82598(struct ixgbe_hw *hw) { diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c index 4c26c4b92f07..38c4609bd429 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c @@ -3237,7 +3237,7 @@ vfta_update: * ixgbe_clear_vfta_generic - Clear VLAN filter table * @hw: pointer to hardware structure * - * Clears the VLAN filer table, and the VMDq index associated with the filter + * Clears the VLAN filter table, and the VMDq index associated with the filter **/ s32 ixgbe_clear_vfta_generic(struct ixgbe_hw *hw) { diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 77c2e70b0860..5c62e9963650 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -5549,6 +5549,47 @@ static int ixgbe_non_sfp_link_config(struct ixgbe_hw *hw) return ret; } +/** + * ixgbe_clear_vf_stats_counters - Clear out VF stats after reset + * @adapter: board private structure + * + * On a reset we need to clear out the VF stats or accounting gets + * messed up because they're not clear on read. + **/ +static void ixgbe_clear_vf_stats_counters(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + int i; + + for (i = 0; i < adapter->num_vfs; i++) { + adapter->vfinfo[i].last_vfstats.gprc = + IXGBE_READ_REG(hw, IXGBE_PVFGPRC(i)); + adapter->vfinfo[i].saved_rst_vfstats.gprc += + adapter->vfinfo[i].vfstats.gprc; + adapter->vfinfo[i].vfstats.gprc = 0; + adapter->vfinfo[i].last_vfstats.gptc = + IXGBE_READ_REG(hw, IXGBE_PVFGPTC(i)); + adapter->vfinfo[i].saved_rst_vfstats.gptc += + adapter->vfinfo[i].vfstats.gptc; + adapter->vfinfo[i].vfstats.gptc = 0; + adapter->vfinfo[i].last_vfstats.gorc = + IXGBE_READ_REG(hw, IXGBE_PVFGORC_LSB(i)); + adapter->vfinfo[i].saved_rst_vfstats.gorc += + adapter->vfinfo[i].vfstats.gorc; + adapter->vfinfo[i].vfstats.gorc = 0; + adapter->vfinfo[i].last_vfstats.gotc = + IXGBE_READ_REG(hw, IXGBE_PVFGOTC_LSB(i)); + adapter->vfinfo[i].saved_rst_vfstats.gotc += + adapter->vfinfo[i].vfstats.gotc; + adapter->vfinfo[i].vfstats.gotc = 0; + adapter->vfinfo[i].last_vfstats.mprc = + IXGBE_READ_REG(hw, IXGBE_PVFMPRC(i)); + adapter->vfinfo[i].saved_rst_vfstats.mprc += + adapter->vfinfo[i].vfstats.mprc; + adapter->vfinfo[i].vfstats.mprc = 0; + } +} + static void ixgbe_setup_gpie(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; @@ -5684,6 +5725,7 @@ static void ixgbe_up_complete(struct ixgbe_adapter *adapter) adapter->link_check_timeout = jiffies; mod_timer(&adapter->service_timer, jiffies); + ixgbe_clear_vf_stats_counters(adapter); /* Set PF Reset Done bit so PF/VF Mail Ops can work */ ctrl_ext = IXGBE_READ_REG(hw, IXGBE_CTRL_EXT); ctrl_ext |= IXGBE_CTRL_EXT_PFRSTD; @@ -7271,6 +7313,32 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter) netdev->stats.rx_length_errors = hwstats->rlec; netdev->stats.rx_crc_errors = hwstats->crcerrs; netdev->stats.rx_missed_errors = total_mpc; + + /* VF Stats Collection - skip while resetting because these + * are not clear on read and otherwise you'll sometimes get + * crazy values. + */ + if (!test_bit(__IXGBE_RESETTING, &adapter->state)) { + for (i = 0; i < adapter->num_vfs; i++) { + UPDATE_VF_COUNTER_32bit(IXGBE_PVFGPRC(i), + adapter->vfinfo[i].last_vfstats.gprc, + adapter->vfinfo[i].vfstats.gprc); + UPDATE_VF_COUNTER_32bit(IXGBE_PVFGPTC(i), + adapter->vfinfo[i].last_vfstats.gptc, + adapter->vfinfo[i].vfstats.gptc); + UPDATE_VF_COUNTER_36bit(IXGBE_PVFGORC_LSB(i), + IXGBE_PVFGORC_MSB(i), + adapter->vfinfo[i].last_vfstats.gorc, + adapter->vfinfo[i].vfstats.gorc); + UPDATE_VF_COUNTER_36bit(IXGBE_PVFGOTC_LSB(i), + IXGBE_PVFGOTC_MSB(i), + adapter->vfinfo[i].last_vfstats.gotc, + adapter->vfinfo[i].vfstats.gotc); + UPDATE_VF_COUNTER_32bit(IXGBE_PVFMPRC(i), + adapter->vfinfo[i].last_vfstats.mprc, + adapter->vfinfo[i].vfstats.mprc); + } + } } /** @@ -9022,6 +9090,23 @@ static void ixgbe_get_stats64(struct net_device *netdev, stats->rx_missed_errors = netdev->stats.rx_missed_errors; } +static int ixgbe_ndo_get_vf_stats(struct net_device *netdev, int vf, + struct ifla_vf_stats *vf_stats) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + + if (vf < 0 || vf >= adapter->num_vfs) + return -EINVAL; + + vf_stats->rx_packets = adapter->vfinfo[vf].vfstats.gprc; + vf_stats->rx_bytes = adapter->vfinfo[vf].vfstats.gorc; + vf_stats->tx_packets = adapter->vfinfo[vf].vfstats.gptc; + vf_stats->tx_bytes = adapter->vfinfo[vf].vfstats.gotc; + vf_stats->multicast = adapter->vfinfo[vf].vfstats.mprc; + + return 0; +} + #ifdef CONFIG_IXGBE_DCB /** * ixgbe_validate_rtr - verify 802.1Qp to Rx packet buffer mapping is valid. @@ -10338,6 +10423,7 @@ static const struct net_device_ops ixgbe_netdev_ops = { .ndo_set_vf_rss_query_en = ixgbe_ndo_set_vf_rss_query_en, .ndo_set_vf_trust = ixgbe_ndo_set_vf_trust, .ndo_get_vf_config = ixgbe_ndo_get_vf_config, + .ndo_get_vf_stats = ixgbe_ndo_get_vf_stats, .ndo_get_stats64 = ixgbe_get_stats64, .ndo_setup_tc = __ixgbe_setup_tc, #ifdef IXGBE_FCOE diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c index d4e63f0644c3..67e49aac50fe 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c @@ -77,7 +77,7 @@ static int __ixgbe_enable_sriov(struct ixgbe_adapter *adapter, IXGBE_WRITE_REG(hw, IXGBE_PFDTXGSWC, IXGBE_PFDTXGSWC_VT_LBEN); adapter->bridge_mode = BRIDGE_MODE_VEB; - /* limit trafffic classes based on VFs enabled */ + /* limit traffic classes based on VFs enabled */ if ((adapter->hw.mac.type == ixgbe_mac_82599EB) && (num_vfs < 16)) { adapter->dcb_cfg.num_tcs.pg_tcs = MAX_TRAFFIC_CLASS; adapter->dcb_cfg.num_tcs.pfc_tcs = MAX_TRAFFIC_CLASS; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h index 6da9880d766a..7f7ea468ffa9 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h @@ -2533,6 +2533,13 @@ enum { #define IXGBE_PVFTXDCTL(P) (0x06028 + (0x40 * (P))) #define IXGBE_PVFTDWBAL(P) (0x06038 + (0x40 * (P))) #define IXGBE_PVFTDWBAH(P) (0x0603C + (0x40 * (P))) +#define IXGBE_PVFGPRC(x) (0x0101C + (0x40 * (x))) +#define IXGBE_PVFGPTC(x) (0x08300 + (0x04 * (x))) +#define IXGBE_PVFGORC_LSB(x) (0x01020 + (0x40 * (x))) +#define IXGBE_PVFGORC_MSB(x) (0x0D020 + (0x40 * (x))) +#define IXGBE_PVFGOTC_LSB(x) (0x08400 + (0x08 * (x))) +#define IXGBE_PVFGOTC_MSB(x) (0x08404 + (0x08 * (x))) +#define IXGBE_PVFMPRC(x) (0x0D01C + (0x40 * (x))) #define IXGBE_PVFTDWBALn(q_per_pool, vf_number, vf_q_index) \ (IXGBE_PVFTDWBAL((q_per_pool)*(vf_number) + (vf_q_index))) diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 59c9a10f83ba..6beb3d4873a3 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -1444,8 +1444,8 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget, int done = 0, bytes = 0; while (done < budget) { + unsigned int pktlen, *rxdcsum; struct net_device *netdev; - unsigned int pktlen; dma_addr_t dma_addr; u32 hash, reason; int mac = 0; @@ -1512,7 +1512,13 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget, pktlen = RX_DMA_GET_PLEN0(trxd.rxd2); skb->dev = netdev; skb_put(skb, pktlen); - if (trxd.rxd4 & eth->soc->txrx.rx_dma_l4_valid) + + if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) + rxdcsum = &trxd.rxd3; + else + rxdcsum = &trxd.rxd4; + + if (*rxdcsum & eth->soc->txrx.rx_dma_l4_valid) skb->ip_summed = CHECKSUM_UNNECESSARY; else skb_checksum_none_assert(skb); @@ -3761,6 +3767,7 @@ static const struct mtk_soc_data mt7986_data = { .txd_size = sizeof(struct mtk_tx_dma_v2), .rxd_size = sizeof(struct mtk_rx_dma_v2), .rx_irq_done_mask = MTK_RX_DONE_INT_V2, + .rx_dma_l4_valid = RX_DMA_L4_VALID_V2, .dma_max_len = MTK_TX_DMA_BUF_LEN_V2, .dma_len_offset = 8, }, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index 2ccf7bef9b05..735dc805dad7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -479,6 +479,30 @@ static int mlx5_set_extended_dest(struct mlx5_core_dev *dev, return 0; } + +static void +mlx5_cmd_set_fte_flow_meter(struct fs_fte *fte, void *in_flow_context) +{ + void *exe_aso_ctrl; + void *execute_aso; + + execute_aso = MLX5_ADDR_OF(flow_context, in_flow_context, + execute_aso[0]); + MLX5_SET(execute_aso, execute_aso, valid, 1); + MLX5_SET(execute_aso, execute_aso, aso_object_id, + fte->action.exe_aso.object_id); + + exe_aso_ctrl = MLX5_ADDR_OF(execute_aso, execute_aso, exe_aso_ctrl); + MLX5_SET(exe_aso_ctrl_flow_meter, exe_aso_ctrl, return_reg_id, + fte->action.exe_aso.return_reg_id); + MLX5_SET(exe_aso_ctrl_flow_meter, exe_aso_ctrl, aso_type, + fte->action.exe_aso.type); + MLX5_SET(exe_aso_ctrl_flow_meter, exe_aso_ctrl, init_color, + fte->action.exe_aso.flow_meter.init_color); + MLX5_SET(exe_aso_ctrl_flow_meter, exe_aso_ctrl, meter_id, + fte->action.exe_aso.flow_meter.meter_idx); +} + static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev, int opmod, int modify_mask, struct mlx5_flow_table *ft, @@ -663,6 +687,15 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev, list_size); } + if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_EXECUTE_ASO) { + if (fte->action.exe_aso.type == MLX5_EXE_ASO_FLOW_METER) { + mlx5_cmd_set_fte_flow_meter(fte, in_flow_context); + } else { + err = -EOPNOTSUPP; + goto err_out; + } + } + err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out)); err_out: kvfree(in); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 21e5c709b2d3..f1b908d40fa6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -2895,6 +2895,14 @@ static int create_fdb_bypass(struct mlx5_flow_steering *steering) return 0; } +static void cleanup_fdb_root_ns(struct mlx5_flow_steering *steering) +{ + cleanup_root_ns(steering->fdb_root_ns); + steering->fdb_root_ns = NULL; + kfree(steering->fdb_sub_ns); + steering->fdb_sub_ns = NULL; +} + static int init_fdb_root_ns(struct mlx5_flow_steering *steering) { struct fs_prio *maj_prio; @@ -2945,10 +2953,7 @@ static int init_fdb_root_ns(struct mlx5_flow_steering *steering) return 0; out_err: - cleanup_root_ns(steering->fdb_root_ns); - kfree(steering->fdb_sub_ns); - steering->fdb_sub_ns = NULL; - steering->fdb_root_ns = NULL; + cleanup_fdb_root_ns(steering); return err; } @@ -3108,10 +3113,7 @@ void mlx5_fs_core_cleanup(struct mlx5_core_dev *dev) struct mlx5_flow_steering *steering = dev->priv.steering; cleanup_root_ns(steering->root_ns); - cleanup_root_ns(steering->fdb_root_ns); - steering->fdb_root_ns = NULL; - kfree(steering->fdb_sub_ns); - steering->fdb_sub_ns = NULL; + cleanup_fdb_root_ns(steering); cleanup_root_ns(steering->port_sel_root_ns); cleanup_root_ns(steering->sniffer_rx_root_ns); cleanup_root_ns(steering->sniffer_tx_root_ns); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/dm.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/dm.c index 3d5e57ff558c..7e02cbe8c3b9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/dm.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/dm.c @@ -12,13 +12,16 @@ struct mlx5_dm { spinlock_t lock; unsigned long *steering_sw_icm_alloc_blocks; unsigned long *header_modify_sw_icm_alloc_blocks; + unsigned long *header_modify_pattern_sw_icm_alloc_blocks; }; struct mlx5_dm *mlx5_dm_create(struct mlx5_core_dev *dev) { + u64 header_modify_pattern_icm_blocks = 0; u64 header_modify_icm_blocks = 0; u64 steering_icm_blocks = 0; struct mlx5_dm *dm; + bool support_v2; if (!(MLX5_CAP_GEN_64(dev, general_obj_types) & MLX5_GENERAL_OBJ_TYPES_CAP_SW_ICM)) return NULL; @@ -53,8 +56,27 @@ struct mlx5_dm *mlx5_dm_create(struct mlx5_core_dev *dev) goto err_modify_hdr; } + support_v2 = MLX5_CAP_FLOWTABLE_NIC_RX(dev, sw_owner_v2) && + MLX5_CAP_FLOWTABLE_NIC_TX(dev, sw_owner_v2) && + MLX5_CAP64_DEV_MEM(dev, header_modify_pattern_sw_icm_start_address); + + if (support_v2) { + header_modify_pattern_icm_blocks = + BIT(MLX5_CAP_DEV_MEM(dev, log_header_modify_pattern_sw_icm_size) - + MLX5_LOG_SW_ICM_BLOCK_SIZE(dev)); + + dm->header_modify_pattern_sw_icm_alloc_blocks = + kcalloc(BITS_TO_LONGS(header_modify_pattern_icm_blocks), + sizeof(unsigned long), GFP_KERNEL); + if (!dm->header_modify_pattern_sw_icm_alloc_blocks) + goto err_pattern; + } + return dm; +err_pattern: + kfree(dm->header_modify_sw_icm_alloc_blocks); + err_modify_hdr: kfree(dm->steering_sw_icm_alloc_blocks); @@ -86,6 +108,14 @@ void mlx5_dm_cleanup(struct mlx5_core_dev *dev) kfree(dm->header_modify_sw_icm_alloc_blocks); } + if (dm->header_modify_pattern_sw_icm_alloc_blocks) { + WARN_ON(!bitmap_empty(dm->header_modify_pattern_sw_icm_alloc_blocks, + BIT(MLX5_CAP_DEV_MEM(dev, + log_header_modify_pattern_sw_icm_size) - + MLX5_LOG_SW_ICM_BLOCK_SIZE(dev)))); + kfree(dm->header_modify_pattern_sw_icm_alloc_blocks); + } + kfree(dm); } @@ -130,6 +160,13 @@ int mlx5_dm_sw_icm_alloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type, log_header_modify_sw_icm_size); block_map = dm->header_modify_sw_icm_alloc_blocks; break; + case MLX5_SW_ICM_TYPE_HEADER_MODIFY_PATTERN: + icm_start_addr = MLX5_CAP64_DEV_MEM(dev, + header_modify_pattern_sw_icm_start_address); + log_icm_size = MLX5_CAP_DEV_MEM(dev, + log_header_modify_pattern_sw_icm_size); + block_map = dm->header_modify_pattern_sw_icm_alloc_blocks; + break; default: return -EINVAL; } @@ -203,6 +240,11 @@ int mlx5_dm_sw_icm_dealloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type icm_start_addr = MLX5_CAP64_DEV_MEM(dev, header_modify_sw_icm_start_address); block_map = dm->header_modify_sw_icm_alloc_blocks; break; + case MLX5_SW_ICM_TYPE_HEADER_MODIFY_PATTERN: + icm_start_addr = MLX5_CAP64_DEV_MEM(dev, + header_modify_pattern_sw_icm_start_address); + block_map = dm->header_modify_pattern_sw_icm_alloc_blocks; + break; default: return -EINVAL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index c9b4e50a593e..2078d9f03a5f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -314,13 +314,6 @@ struct mlx5_reg_host_endianness { u8 rsvd[15]; }; -#define CAP_MASK(pos, size) ((u64)((1 << (size)) - 1) << (pos)) - -enum { - MLX5_CAP_BITS_RW_MASK = CAP_MASK(MLX5_CAP_OFF_CMDIF_CSUM, 2) | - MLX5_DEV_CAP_FLAG_DCT, -}; - static u16 to_fw_pkey_sz(struct mlx5_core_dev *dev, u32 size) { switch (size) { diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c index 84621b4cb15b..b03e1c66bac0 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c @@ -19,8 +19,6 @@ #include "mlxbf_gige.h" #include "mlxbf_gige_regs.h" -#define DRV_NAME "mlxbf_gige" - /* Allocate SKB whose payload pointer aligns with the Bluefield * hardware DMA limitation, i.e. DMA operation can't cross * a 4KB boundary. A maximum packet size of 2KB is assumed in the @@ -427,7 +425,7 @@ static struct platform_driver mlxbf_gige_driver = { .remove = mlxbf_gige_remove, .shutdown = mlxbf_gige_shutdown, .driver = { - .name = DRV_NAME, + .name = KBUILD_MODNAME, .acpi_match_table = ACPI_PTR(mlxbf_gige_acpi_match), }, }; diff --git a/drivers/net/ethernet/mellanox/mlxsw/Makefile b/drivers/net/ethernet/mellanox/mlxsw/Makefile index 1a465fd5d8b3..c57e293cca25 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/Makefile +++ b/drivers/net/ethernet/mellanox/mlxsw/Makefile @@ -12,7 +12,6 @@ mlxsw_i2c-objs := i2c.o obj-$(CONFIG_MLXSW_SPECTRUM) += mlxsw_spectrum.o mlxsw_spectrum-objs := spectrum.o spectrum_buffers.o \ spectrum_switchdev.o spectrum_router.o \ - spectrum_router_xm.o \ spectrum1_kvdl.o spectrum2_kvdl.o \ spectrum_kvdl.o \ spectrum_acl_tcam.o spectrum_acl_ctcam.o \ diff --git a/drivers/net/ethernet/mellanox/mlxsw/cmd.h b/drivers/net/ethernet/mellanox/mlxsw/cmd.h index 51b260d54237..91f68fb0b420 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/cmd.h +++ b/drivers/net/ethernet/mellanox/mlxsw/cmd.h @@ -343,23 +343,6 @@ static inline int mlxsw_cmd_boardinfo(struct mlxsw_core *mlxsw_core, 0, 0, false, out_mbox, MLXSW_CMD_MBOX_SIZE); } -/* cmd_mbox_xm_num_local_ports - * Number of local_ports connected to the xm. - * Each local port is a 4x - * Spectrum-2/3: 25G - * Spectrum-4: 50G - */ -MLXSW_ITEM32(cmd_mbox, boardinfo, xm_num_local_ports, 0x00, 4, 3); - -/* cmd_mbox_xm_exists - * An XM (eXtanded Mezanine, e.g. used for the XLT) is connected on the board. - */ -MLXSW_ITEM32(cmd_mbox, boardinfo, xm_exists, 0x00, 0, 1); - -/* cmd_mbox_xm_local_port_entry - */ -MLXSW_ITEM_BIT_ARRAY(cmd_mbox, boardinfo, xm_local_port_entry, 0x04, 4, 8); - /* cmd_mbox_boardinfo_intapin * When PCIe interrupt messages are being used, this value is used for clearing * an interrupt. When using MSI-X, this register is not used. @@ -674,12 +657,6 @@ MLXSW_ITEM32(cmd_mbox, config_profile, set_kvd_hash_double_size, 0x0C, 26, 1); */ MLXSW_ITEM32(cmd_mbox, config_profile, set_cqe_version, 0x08, 0, 1); -/* cmd_mbox_config_set_kvh_xlt_cache_mode - * Capability bit. Setting a bit to 1 configures the profile - * according to the mailbox contents. - */ -MLXSW_ITEM32(cmd_mbox, config_profile, set_kvh_xlt_cache_mode, 0x08, 3, 1); - /* cmd_mbox_config_profile_max_vepa_channels * Maximum number of VEPA channels per port (0 through 16) * 0 - multi-channel VEPA is disabled @@ -806,13 +783,6 @@ MLXSW_ITEM32(cmd_mbox, config_profile, adaptive_routing_group_cap, 0x4C, 0, 16); */ MLXSW_ITEM32(cmd_mbox, config_profile, arn, 0x50, 31, 1); -/* cmd_mbox_config_profile_kvh_xlt_cache_mode - * KVH XLT cache mode: - * 0 - XLT can use all KVH as best-effort - * 1 - XLT cache uses 1/2 KVH - */ -MLXSW_ITEM32(cmd_mbox, config_profile, kvh_xlt_cache_mode, 0x50, 8, 4); - /* cmd_mbox_config_kvd_linear_size * KVD Linear Size * Valid for Spectrum only diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index fc52832241b3..ab1cebf227fb 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -3151,18 +3151,6 @@ mlxsw_core_port_linecard_get(struct mlxsw_core *mlxsw_core, return mlxsw_core_port->linecard; } -bool mlxsw_core_port_is_xm(const struct mlxsw_core *mlxsw_core, u16 local_port) -{ - const struct mlxsw_bus_info *bus_info = mlxsw_core->bus_info; - int i; - - for (i = 0; i < bus_info->xm_local_ports_count; i++) - if (bus_info->xm_local_ports[i] == local_port) - return true; - return false; -} -EXPORT_SYMBOL(mlxsw_core_port_is_xm); - void mlxsw_core_ports_remove_selected(struct mlxsw_core *mlxsw_core, bool (*selector)(void *priv, u16 local_port), void *priv) diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h index c2a891287047..d1e8b8b8d0c1 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core.h @@ -261,7 +261,6 @@ mlxsw_core_port_devlink_port_get(struct mlxsw_core *mlxsw_core, struct mlxsw_linecard * mlxsw_core_port_linecard_get(struct mlxsw_core *mlxsw_core, u16 local_port); -bool mlxsw_core_port_is_xm(const struct mlxsw_core *mlxsw_core, u16 local_port); void mlxsw_core_ports_remove_selected(struct mlxsw_core *mlxsw_core, bool (*selector)(void *priv, u16 local_port), @@ -296,8 +295,7 @@ struct mlxsw_config_profile { used_max_pkey:1, used_ar_sec:1, used_adaptive_routing_group_cap:1, - used_kvd_sizes:1, - used_kvh_xlt_cache_mode:1; + used_kvd_sizes:1; u8 max_vepa_channels; u16 max_mid; u16 max_pgt; @@ -319,7 +317,6 @@ struct mlxsw_config_profile { u32 kvd_linear_size; u8 kvd_hash_single_parts; u8 kvd_hash_double_parts; - u8 kvh_xlt_cache_mode; struct mlxsw_swid_config swid_config[MLXSW_CONFIG_PROFILE_SWID_COUNT]; }; @@ -478,8 +475,6 @@ struct mlxsw_fw_rev { u16 can_reset_minor; }; -#define MLXSW_BUS_INFO_XM_LOCAL_PORTS_MAX 4 - struct mlxsw_bus_info { const char *device_kind; const char *device_name; @@ -488,10 +483,7 @@ struct mlxsw_bus_info { u8 vsd[MLXSW_CMD_BOARDINFO_VSD_LEN]; u8 psid[MLXSW_CMD_BOARDINFO_PSID_LEN]; u8 low_frequency:1, - read_frc_capable:1, - xm_exists:1; - u8 xm_local_ports_count; - u8 xm_local_ports[MLXSW_BUS_INFO_XM_LOCAL_PORTS_MAX]; + read_frc_capable:1; }; struct mlxsw_hwmon; diff --git a/drivers/net/ethernet/mellanox/mlxsw/minimal.c b/drivers/net/ethernet/mellanox/mlxsw/minimal.c index d9660d4cce96..d9bf584234a6 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/minimal.c +++ b/drivers/net/ethernet/mellanox/mlxsw/minimal.c @@ -359,8 +359,7 @@ static int mlxsw_m_ports_create(struct mlxsw_m *mlxsw_m) /* Create port objects for each valid entry */ devl_lock(devlink); for (i = 0; i < mlxsw_m->max_ports; i++) { - if (mlxsw_m->module_to_port[i] > 0 && - !mlxsw_core_port_is_xm(mlxsw_m->core, i)) { + if (mlxsw_m->module_to_port[i] > 0) { err = mlxsw_m_port_create(mlxsw_m, mlxsw_m->module_to_port[i], i); diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index f91dde4df152..8dd2479c7937 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -1252,12 +1252,6 @@ static int mlxsw_pci_config_profile(struct mlxsw_pci *mlxsw_pci, char *mbox, mlxsw_cmd_mbox_config_profile_kvd_hash_double_size_set(mbox, MLXSW_RES_GET(res, KVD_DOUBLE_SIZE)); } - if (profile->used_kvh_xlt_cache_mode) { - mlxsw_cmd_mbox_config_profile_set_kvh_xlt_cache_mode_set( - mbox, 1); - mlxsw_cmd_mbox_config_profile_kvh_xlt_cache_mode_set( - mbox, profile->kvh_xlt_cache_mode); - } for (i = 0; i < MLXSW_CONFIG_PROFILE_SWID_COUNT; i++) mlxsw_pci_config_profile_swid_config(mlxsw_pci, mbox, i, @@ -1271,30 +1265,6 @@ static int mlxsw_pci_config_profile(struct mlxsw_pci *mlxsw_pci, char *mbox, return mlxsw_cmd_config_profile_set(mlxsw_pci->core, mbox); } -static int mlxsw_pci_boardinfo_xm_process(struct mlxsw_pci *mlxsw_pci, - struct mlxsw_bus_info *bus_info, - char *mbox) -{ - int count = mlxsw_cmd_mbox_boardinfo_xm_num_local_ports_get(mbox); - int i; - - if (!mlxsw_cmd_mbox_boardinfo_xm_exists_get(mbox)) - return 0; - - bus_info->xm_exists = true; - - if (count > MLXSW_BUS_INFO_XM_LOCAL_PORTS_MAX) { - dev_err(&mlxsw_pci->pdev->dev, "Invalid number of XM local ports\n"); - return -EINVAL; - } - bus_info->xm_local_ports_count = count; - for (i = 0; i < count; i++) - bus_info->xm_local_ports[i] = - mlxsw_cmd_mbox_boardinfo_xm_local_port_entry_get(mbox, - i); - return 0; -} - static int mlxsw_pci_boardinfo(struct mlxsw_pci *mlxsw_pci, char *mbox) { struct mlxsw_bus_info *bus_info = &mlxsw_pci->bus_info; @@ -1306,8 +1276,7 @@ static int mlxsw_pci_boardinfo(struct mlxsw_pci *mlxsw_pci, char *mbox) return err; mlxsw_cmd_mbox_boardinfo_vsd_memcpy_from(mbox, bus_info->vsd); mlxsw_cmd_mbox_boardinfo_psid_memcpy_from(mbox, bus_info->psid); - - return mlxsw_pci_boardinfo_xm_process(mlxsw_pci, bus_info, mbox); + return 0; } static int mlxsw_pci_fw_area_init(struct mlxsw_pci *mlxsw_pci, char *mbox, diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 93af6c974ece..d830a35755a8 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -7848,11 +7848,10 @@ static inline void mlxsw_reg_ralue_pack4(char *payload, enum mlxsw_reg_ralxx_protocol protocol, enum mlxsw_reg_ralue_op op, u16 virtual_router, u8 prefix_len, - u32 *dip) + u32 dip) { mlxsw_reg_ralue_pack(payload, protocol, op, virtual_router, prefix_len); - if (dip) - mlxsw_reg_ralue_dip4_set(payload, *dip); + mlxsw_reg_ralue_dip4_set(payload, dip); } static inline void mlxsw_reg_ralue_pack6(char *payload, @@ -7862,8 +7861,7 @@ static inline void mlxsw_reg_ralue_pack6(char *payload, const void *dip) { mlxsw_reg_ralue_pack(payload, protocol, op, virtual_router, prefix_len); - if (dip) - mlxsw_reg_ralue_dip6_memcpy_to(payload, dip); + mlxsw_reg_ralue_dip6_memcpy_to(payload, dip); } static inline void @@ -8926,658 +8924,6 @@ mlxsw_reg_rmft2_ipv6_pack(char *payload, bool v, u16 offset, u16 virtual_router, mlxsw_reg_rmft2_sip6_mask_memcpy_to(payload, (void *)&sip6_mask); } -/* RXLTE - Router XLT Enable Register - * ---------------------------------- - * The RXLTE enables XLT (eXtended Lookup Table) LPM lookups if a capable - * XM is present on the system. - */ - -#define MLXSW_REG_RXLTE_ID 0x8050 -#define MLXSW_REG_RXLTE_LEN 0x0C - -MLXSW_REG_DEFINE(rxlte, MLXSW_REG_RXLTE_ID, MLXSW_REG_RXLTE_LEN); - -/* reg_rxlte_virtual_router - * Virtual router ID associated with the router interface. - * Range is 0..cap_max_virtual_routers-1 - * Access: Index - */ -MLXSW_ITEM32(reg, rxlte, virtual_router, 0x00, 0, 16); - -enum mlxsw_reg_rxlte_protocol { - MLXSW_REG_RXLTE_PROTOCOL_IPV4, - MLXSW_REG_RXLTE_PROTOCOL_IPV6, -}; - -/* reg_rxlte_protocol - * Access: Index - */ -MLXSW_ITEM32(reg, rxlte, protocol, 0x04, 0, 4); - -/* reg_rxlte_lpm_xlt_en - * Access: RW - */ -MLXSW_ITEM32(reg, rxlte, lpm_xlt_en, 0x08, 0, 1); - -static inline void mlxsw_reg_rxlte_pack(char *payload, u16 virtual_router, - enum mlxsw_reg_rxlte_protocol protocol, - bool lpm_xlt_en) -{ - MLXSW_REG_ZERO(rxlte, payload); - mlxsw_reg_rxlte_virtual_router_set(payload, virtual_router); - mlxsw_reg_rxlte_protocol_set(payload, protocol); - mlxsw_reg_rxlte_lpm_xlt_en_set(payload, lpm_xlt_en); -} - -/* RXLTM - Router XLT M select Register - * ------------------------------------ - * The RXLTM configures and selects the M for the XM lookups. - */ - -#define MLXSW_REG_RXLTM_ID 0x8051 -#define MLXSW_REG_RXLTM_LEN 0x14 - -MLXSW_REG_DEFINE(rxltm, MLXSW_REG_RXLTM_ID, MLXSW_REG_RXLTM_LEN); - -/* reg_rxltm_m0_val_v6 - * Global M0 value For IPv6. - * Range 0..128 - * Access: RW - */ -MLXSW_ITEM32(reg, rxltm, m0_val_v6, 0x10, 16, 8); - -/* reg_rxltm_m0_val_v4 - * Global M0 value For IPv4. - * Range 0..32 - * Access: RW - */ -MLXSW_ITEM32(reg, rxltm, m0_val_v4, 0x10, 0, 6); - -static inline void mlxsw_reg_rxltm_pack(char *payload, u8 m0_val_v4, u8 m0_val_v6) -{ - MLXSW_REG_ZERO(rxltm, payload); - mlxsw_reg_rxltm_m0_val_v6_set(payload, m0_val_v6); - mlxsw_reg_rxltm_m0_val_v4_set(payload, m0_val_v4); -} - -/* RLCMLD - Router LPM Cache ML Delete Register - * -------------------------------------------- - * The RLCMLD register is used to bulk delete the XLT-LPM cache ML entries. - * This can be used by SW when L is increased or decreased, thus need to - * remove entries with old ML values. - */ - -#define MLXSW_REG_RLCMLD_ID 0x8055 -#define MLXSW_REG_RLCMLD_LEN 0x30 - -MLXSW_REG_DEFINE(rlcmld, MLXSW_REG_RLCMLD_ID, MLXSW_REG_RLCMLD_LEN); - -enum mlxsw_reg_rlcmld_select { - MLXSW_REG_RLCMLD_SELECT_ML_ENTRIES, - MLXSW_REG_RLCMLD_SELECT_M_ENTRIES, - MLXSW_REG_RLCMLD_SELECT_M_AND_ML_ENTRIES, -}; - -/* reg_rlcmld_select - * Which entries to delete. - * Access: Index - */ -MLXSW_ITEM32(reg, rlcmld, select, 0x00, 16, 2); - -enum mlxsw_reg_rlcmld_filter_fields { - MLXSW_REG_RLCMLD_FILTER_FIELDS_BY_PROTOCOL = 0x04, - MLXSW_REG_RLCMLD_FILTER_FIELDS_BY_VIRTUAL_ROUTER = 0x08, - MLXSW_REG_RLCMLD_FILTER_FIELDS_BY_DIP = 0x10, -}; - -/* reg_rlcmld_filter_fields - * If a bit is '0' then the relevant field is ignored. - * Access: Index - */ -MLXSW_ITEM32(reg, rlcmld, filter_fields, 0x00, 0, 8); - -enum mlxsw_reg_rlcmld_protocol { - MLXSW_REG_RLCMLD_PROTOCOL_UC_IPV4, - MLXSW_REG_RLCMLD_PROTOCOL_UC_IPV6, -}; - -/* reg_rlcmld_protocol - * Access: Index - */ -MLXSW_ITEM32(reg, rlcmld, protocol, 0x08, 0, 4); - -/* reg_rlcmld_virtual_router - * Virtual router ID. - * Range is 0..cap_max_virtual_routers-1 - * Access: Index - */ -MLXSW_ITEM32(reg, rlcmld, virtual_router, 0x0C, 0, 16); - -/* reg_rlcmld_dip - * The prefix of the route or of the marker that the object of the LPM - * is compared with. The most significant bits of the dip are the prefix. - * Access: Index - */ -MLXSW_ITEM32(reg, rlcmld, dip4, 0x1C, 0, 32); -MLXSW_ITEM_BUF(reg, rlcmld, dip6, 0x10, 16); - -/* reg_rlcmld_dip_mask - * per bit: - * 0: no match - * 1: match - * Access: Index - */ -MLXSW_ITEM32(reg, rlcmld, dip_mask4, 0x2C, 0, 32); -MLXSW_ITEM_BUF(reg, rlcmld, dip_mask6, 0x20, 16); - -static inline void __mlxsw_reg_rlcmld_pack(char *payload, - enum mlxsw_reg_rlcmld_select select, - enum mlxsw_reg_rlcmld_protocol protocol, - u16 virtual_router) -{ - u8 filter_fields = MLXSW_REG_RLCMLD_FILTER_FIELDS_BY_PROTOCOL | - MLXSW_REG_RLCMLD_FILTER_FIELDS_BY_VIRTUAL_ROUTER | - MLXSW_REG_RLCMLD_FILTER_FIELDS_BY_DIP; - - MLXSW_REG_ZERO(rlcmld, payload); - mlxsw_reg_rlcmld_select_set(payload, select); - mlxsw_reg_rlcmld_filter_fields_set(payload, filter_fields); - mlxsw_reg_rlcmld_protocol_set(payload, protocol); - mlxsw_reg_rlcmld_virtual_router_set(payload, virtual_router); -} - -static inline void mlxsw_reg_rlcmld_pack4(char *payload, - enum mlxsw_reg_rlcmld_select select, - u16 virtual_router, - u32 dip, u32 dip_mask) -{ - __mlxsw_reg_rlcmld_pack(payload, select, - MLXSW_REG_RLCMLD_PROTOCOL_UC_IPV4, - virtual_router); - mlxsw_reg_rlcmld_dip4_set(payload, dip); - mlxsw_reg_rlcmld_dip_mask4_set(payload, dip_mask); -} - -static inline void mlxsw_reg_rlcmld_pack6(char *payload, - enum mlxsw_reg_rlcmld_select select, - u16 virtual_router, - const void *dip, const void *dip_mask) -{ - __mlxsw_reg_rlcmld_pack(payload, select, - MLXSW_REG_RLCMLD_PROTOCOL_UC_IPV6, - virtual_router); - mlxsw_reg_rlcmld_dip6_memcpy_to(payload, dip); - mlxsw_reg_rlcmld_dip_mask6_memcpy_to(payload, dip_mask); -} - -/* RLPMCE - Router LPM Cache Enable Register - * ----------------------------------------- - * Allows disabling the LPM cache. Can be changed on the fly. - */ - -#define MLXSW_REG_RLPMCE_ID 0x8056 -#define MLXSW_REG_RLPMCE_LEN 0x4 - -MLXSW_REG_DEFINE(rlpmce, MLXSW_REG_RLPMCE_ID, MLXSW_REG_RLPMCE_LEN); - -/* reg_rlpmce_flush - * Flush: - * 0: do not flush the cache (default) - * 1: flush (clear) the cache - * Access: WO - */ -MLXSW_ITEM32(reg, rlpmce, flush, 0x00, 4, 1); - -/* reg_rlpmce_disable - * LPM cache: - * 0: enabled (default) - * 1: disabled - * Access: RW - */ -MLXSW_ITEM32(reg, rlpmce, disable, 0x00, 0, 1); - -static inline void mlxsw_reg_rlpmce_pack(char *payload, bool flush, - bool disable) -{ - MLXSW_REG_ZERO(rlpmce, payload); - mlxsw_reg_rlpmce_flush_set(payload, flush); - mlxsw_reg_rlpmce_disable_set(payload, disable); -} - -/* Note that XLTQ, XMDR, XRMT and XRALXX register positions violate the rule - * of ordering register definitions by the ID. However, XRALXX pack helpers are - * using RALXX pack helpers, RALXX registers have higher IDs. - * Also XMDR is using RALUE enums. XLRQ and XRMT are just put alongside with the - * related registers. - */ - -/* XLTQ - XM Lookup Table Query Register - * ------------------------------------- - */ -#define MLXSW_REG_XLTQ_ID 0x7802 -#define MLXSW_REG_XLTQ_LEN 0x2C - -MLXSW_REG_DEFINE(xltq, MLXSW_REG_XLTQ_ID, MLXSW_REG_XLTQ_LEN); - -enum mlxsw_reg_xltq_xm_device_id { - MLXSW_REG_XLTQ_XM_DEVICE_ID_UNKNOWN, - MLXSW_REG_XLTQ_XM_DEVICE_ID_XLT = 0xCF71, -}; - -/* reg_xltq_xm_device_id - * XM device ID. - * Access: RO - */ -MLXSW_ITEM32(reg, xltq, xm_device_id, 0x04, 0, 16); - -/* reg_xltq_xlt_cap_ipv4_lpm - * Access: RO - */ -MLXSW_ITEM32(reg, xltq, xlt_cap_ipv4_lpm, 0x10, 0, 1); - -/* reg_xltq_xlt_cap_ipv6_lpm - * Access: RO - */ -MLXSW_ITEM32(reg, xltq, xlt_cap_ipv6_lpm, 0x10, 1, 1); - -/* reg_xltq_cap_xlt_entries - * Number of XLT entries - * Note: SW must not fill more than 80% in order to avoid overflow - * Access: RO - */ -MLXSW_ITEM32(reg, xltq, cap_xlt_entries, 0x20, 0, 32); - -/* reg_xltq_cap_xlt_mtable - * XLT M-Table max size - * Access: RO - */ -MLXSW_ITEM32(reg, xltq, cap_xlt_mtable, 0x24, 0, 32); - -static inline void mlxsw_reg_xltq_pack(char *payload) -{ - MLXSW_REG_ZERO(xltq, payload); -} - -static inline void mlxsw_reg_xltq_unpack(char *payload, u16 *xm_device_id, bool *xlt_cap_ipv4_lpm, - bool *xlt_cap_ipv6_lpm, u32 *cap_xlt_entries, - u32 *cap_xlt_mtable) -{ - *xm_device_id = mlxsw_reg_xltq_xm_device_id_get(payload); - *xlt_cap_ipv4_lpm = mlxsw_reg_xltq_xlt_cap_ipv4_lpm_get(payload); - *xlt_cap_ipv6_lpm = mlxsw_reg_xltq_xlt_cap_ipv6_lpm_get(payload); - *cap_xlt_entries = mlxsw_reg_xltq_cap_xlt_entries_get(payload); - *cap_xlt_mtable = mlxsw_reg_xltq_cap_xlt_mtable_get(payload); -} - -/* XMDR - XM Direct Register - * ------------------------- - * The XMDR allows direct access to the XM device via the switch. - * Working in synchronous mode. FW waits for response from the XLT - * for each command. FW acks the XMDR accordingly. - */ -#define MLXSW_REG_XMDR_ID 0x7803 -#define MLXSW_REG_XMDR_BASE_LEN 0x20 -#define MLXSW_REG_XMDR_TRANS_LEN 0x80 -#define MLXSW_REG_XMDR_LEN (MLXSW_REG_XMDR_BASE_LEN + \ - MLXSW_REG_XMDR_TRANS_LEN) - -MLXSW_REG_DEFINE(xmdr, MLXSW_REG_XMDR_ID, MLXSW_REG_XMDR_LEN); - -/* reg_xmdr_bulk_entry - * Bulk_entry - * 0: Last entry - immediate flush of XRT-cache - * 1: Bulk entry - do not flush the XRT-cache - * Access: OP - */ -MLXSW_ITEM32(reg, xmdr, bulk_entry, 0x04, 8, 1); - -/* reg_xmdr_num_rec - * Number of records for Direct access to XM - * Supported: 0..4 commands (except NOP which is a filler) - * 0 commands is reserved when bulk_entry = 1. - * 0 commands is allowed when bulk_entry = 0 for immediate XRT-cache flush. - * Access: OP - */ -MLXSW_ITEM32(reg, xmdr, num_rec, 0x04, 0, 4); - -/* reg_xmdr_reply_vect - * Reply Vector - * Bit i for command index i+1 - * values per bit: - * 0: failed - * 1: succeeded - * e.g. if commands 1, 2, 4 succeeded and command 3 failed then binary - * value will be 0b1011 - * Access: RO - */ -MLXSW_ITEM_BIT_ARRAY(reg, xmdr, reply_vect, 0x08, 4, 1); - -static inline void mlxsw_reg_xmdr_pack(char *payload, bool bulk_entry) -{ - MLXSW_REG_ZERO(xmdr, payload); - mlxsw_reg_xmdr_bulk_entry_set(payload, bulk_entry); -} - -enum mlxsw_reg_xmdr_c_cmd_id { - MLXSW_REG_XMDR_C_CMD_ID_LT_ROUTE_V4 = 0x30, - MLXSW_REG_XMDR_C_CMD_ID_LT_ROUTE_V6 = 0x31, -}; - -#define MLXSW_REG_XMDR_C_LT_ROUTE_V4_LEN 32 -#define MLXSW_REG_XMDR_C_LT_ROUTE_V6_LEN 48 - -/* reg_xmdr_c_cmd_id - */ -MLXSW_ITEM32(reg, xmdr_c, cmd_id, 0x00, 24, 8); - -/* reg_xmdr_c_seq_number - */ -MLXSW_ITEM32(reg, xmdr_c, seq_number, 0x00, 12, 12); - -enum mlxsw_reg_xmdr_c_ltr_op { - /* Activity is set */ - MLXSW_REG_XMDR_C_LTR_OP_WRITE = 0, - /* There is no update mask. All fields are updated. */ - MLXSW_REG_XMDR_C_LTR_OP_UPDATE = 1, - MLXSW_REG_XMDR_C_LTR_OP_DELETE = 2, -}; - -/* reg_xmdr_c_ltr_op - * Operation. - */ -MLXSW_ITEM32(reg, xmdr_c, ltr_op, 0x04, 24, 8); - -/* reg_xmdr_c_ltr_trap_action - * Trap action. - * Values are defined in enum mlxsw_reg_ralue_trap_action. - */ -MLXSW_ITEM32(reg, xmdr_c, ltr_trap_action, 0x04, 20, 4); - -enum mlxsw_reg_xmdr_c_ltr_trap_id_num { - MLXSW_REG_XMDR_C_LTR_TRAP_ID_NUM_RTR_INGRESS0, - MLXSW_REG_XMDR_C_LTR_TRAP_ID_NUM_RTR_INGRESS1, - MLXSW_REG_XMDR_C_LTR_TRAP_ID_NUM_RTR_INGRESS2, - MLXSW_REG_XMDR_C_LTR_TRAP_ID_NUM_RTR_INGRESS3, -}; - -/* reg_xmdr_c_ltr_trap_id_num - * Trap-ID number. - */ -MLXSW_ITEM32(reg, xmdr_c, ltr_trap_id_num, 0x04, 16, 4); - -/* reg_xmdr_c_ltr_virtual_router - * Virtual Router ID. - * Range is 0..cap_max_virtual_routers-1 - */ -MLXSW_ITEM32(reg, xmdr_c, ltr_virtual_router, 0x04, 0, 16); - -/* reg_xmdr_c_ltr_prefix_len - * Number of bits in the prefix of the LPM route. - */ -MLXSW_ITEM32(reg, xmdr_c, ltr_prefix_len, 0x08, 24, 8); - -/* reg_xmdr_c_ltr_bmp_len - * The best match prefix length in the case that there is no match for - * longer prefixes. - * If (entry_type != MARKER_ENTRY), bmp_len must be equal to prefix_len - */ -MLXSW_ITEM32(reg, xmdr_c, ltr_bmp_len, 0x08, 16, 8); - -/* reg_xmdr_c_ltr_entry_type - * Entry type. - * Values are defined in enum mlxsw_reg_ralue_entry_type. - */ -MLXSW_ITEM32(reg, xmdr_c, ltr_entry_type, 0x08, 4, 4); - -enum mlxsw_reg_xmdr_c_ltr_action_type { - MLXSW_REG_XMDR_C_LTR_ACTION_TYPE_LOCAL, - MLXSW_REG_XMDR_C_LTR_ACTION_TYPE_REMOTE, - MLXSW_REG_XMDR_C_LTR_ACTION_TYPE_IP2ME, -}; - -/* reg_xmdr_c_ltr_action_type - * Action Type. - */ -MLXSW_ITEM32(reg, xmdr_c, ltr_action_type, 0x08, 0, 4); - -/* reg_xmdr_c_ltr_erif - * Egress Router Interface. - * Only relevant in case of LOCAL action. - */ -MLXSW_ITEM32(reg, xmdr_c, ltr_erif, 0x10, 0, 16); - -/* reg_xmdr_c_ltr_adjacency_index - * Points to the first entry of the group-based ECMP. - * Only relevant in case of REMOTE action. - */ -MLXSW_ITEM32(reg, xmdr_c, ltr_adjacency_index, 0x10, 0, 24); - -#define MLXSW_REG_XMDR_C_LTR_POINTER_TO_TUNNEL_DISABLED_MAGIC 0xFFFFFF - -/* reg_xmdr_c_ltr_pointer_to_tunnel - * Only relevant in case of IP2ME action. - */ -MLXSW_ITEM32(reg, xmdr_c, ltr_pointer_to_tunnel, 0x10, 0, 24); - -/* reg_xmdr_c_ltr_ecmp_size - * Amount of sequential entries starting - * from the adjacency_index (the number of ECMPs). - * The valid range is 1-64, 512, 1024, 2048 and 4096. - * Only relevant in case of REMOTE action. - */ -MLXSW_ITEM32(reg, xmdr_c, ltr_ecmp_size, 0x14, 0, 32); - -/* reg_xmdr_c_ltr_dip* - * The prefix of the route or of the marker that the object of the LPM - * is compared with. The most significant bits of the dip are the prefix. - * The least significant bits must be '0' if the prefix_len is smaller - * than 128 for IPv6 or smaller than 32 for IPv4. - */ -MLXSW_ITEM32(reg, xmdr_c, ltr_dip4, 0x1C, 0, 32); -MLXSW_ITEM_BUF(reg, xmdr_c, ltr_dip6, 0x1C, 16); - -static inline void -mlxsw_reg_xmdr_c_ltr_pack(char *xmdr_payload, unsigned int trans_offset, - enum mlxsw_reg_xmdr_c_cmd_id cmd_id, u16 seq_number, - enum mlxsw_reg_xmdr_c_ltr_op op, u16 virtual_router, - u8 prefix_len) -{ - char *payload = xmdr_payload + MLXSW_REG_XMDR_BASE_LEN + trans_offset; - u8 num_rec = mlxsw_reg_xmdr_num_rec_get(xmdr_payload); - - mlxsw_reg_xmdr_num_rec_set(xmdr_payload, num_rec + 1); - - mlxsw_reg_xmdr_c_cmd_id_set(payload, cmd_id); - mlxsw_reg_xmdr_c_seq_number_set(payload, seq_number); - mlxsw_reg_xmdr_c_ltr_op_set(payload, op); - mlxsw_reg_xmdr_c_ltr_virtual_router_set(payload, virtual_router); - mlxsw_reg_xmdr_c_ltr_prefix_len_set(payload, prefix_len); - mlxsw_reg_xmdr_c_ltr_entry_type_set(payload, - MLXSW_REG_RALUE_ENTRY_TYPE_ROUTE_ENTRY); - mlxsw_reg_xmdr_c_ltr_bmp_len_set(payload, prefix_len); -} - -static inline unsigned int -mlxsw_reg_xmdr_c_ltr_pack4(char *xmdr_payload, unsigned int trans_offset, - u16 seq_number, enum mlxsw_reg_xmdr_c_ltr_op op, - u16 virtual_router, u8 prefix_len, u32 *dip) -{ - char *payload = xmdr_payload + MLXSW_REG_XMDR_BASE_LEN + trans_offset; - - mlxsw_reg_xmdr_c_ltr_pack(xmdr_payload, trans_offset, - MLXSW_REG_XMDR_C_CMD_ID_LT_ROUTE_V4, - seq_number, op, virtual_router, prefix_len); - if (dip) - mlxsw_reg_xmdr_c_ltr_dip4_set(payload, *dip); - return MLXSW_REG_XMDR_C_LT_ROUTE_V4_LEN; -} - -static inline unsigned int -mlxsw_reg_xmdr_c_ltr_pack6(char *xmdr_payload, unsigned int trans_offset, - u16 seq_number, enum mlxsw_reg_xmdr_c_ltr_op op, - u16 virtual_router, u8 prefix_len, const void *dip) -{ - char *payload = xmdr_payload + MLXSW_REG_XMDR_BASE_LEN + trans_offset; - - mlxsw_reg_xmdr_c_ltr_pack(xmdr_payload, trans_offset, - MLXSW_REG_XMDR_C_CMD_ID_LT_ROUTE_V6, - seq_number, op, virtual_router, prefix_len); - if (dip) - mlxsw_reg_xmdr_c_ltr_dip6_memcpy_to(payload, dip); - return MLXSW_REG_XMDR_C_LT_ROUTE_V6_LEN; -} - -static inline void -mlxsw_reg_xmdr_c_ltr_act_remote_pack(char *xmdr_payload, unsigned int trans_offset, - enum mlxsw_reg_ralue_trap_action trap_action, - enum mlxsw_reg_xmdr_c_ltr_trap_id_num trap_id_num, - u32 adjacency_index, u16 ecmp_size) -{ - char *payload = xmdr_payload + MLXSW_REG_XMDR_BASE_LEN + trans_offset; - - mlxsw_reg_xmdr_c_ltr_action_type_set(payload, MLXSW_REG_XMDR_C_LTR_ACTION_TYPE_REMOTE); - mlxsw_reg_xmdr_c_ltr_trap_action_set(payload, trap_action); - mlxsw_reg_xmdr_c_ltr_trap_id_num_set(payload, trap_id_num); - mlxsw_reg_xmdr_c_ltr_adjacency_index_set(payload, adjacency_index); - mlxsw_reg_xmdr_c_ltr_ecmp_size_set(payload, ecmp_size); -} - -static inline void -mlxsw_reg_xmdr_c_ltr_act_local_pack(char *xmdr_payload, unsigned int trans_offset, - enum mlxsw_reg_ralue_trap_action trap_action, - enum mlxsw_reg_xmdr_c_ltr_trap_id_num trap_id_num, u16 erif) -{ - char *payload = xmdr_payload + MLXSW_REG_XMDR_BASE_LEN + trans_offset; - - mlxsw_reg_xmdr_c_ltr_action_type_set(payload, MLXSW_REG_XMDR_C_LTR_ACTION_TYPE_LOCAL); - mlxsw_reg_xmdr_c_ltr_trap_action_set(payload, trap_action); - mlxsw_reg_xmdr_c_ltr_trap_id_num_set(payload, trap_id_num); - mlxsw_reg_xmdr_c_ltr_erif_set(payload, erif); -} - -static inline void mlxsw_reg_xmdr_c_ltr_act_ip2me_pack(char *xmdr_payload, - unsigned int trans_offset) -{ - char *payload = xmdr_payload + MLXSW_REG_XMDR_BASE_LEN + trans_offset; - - mlxsw_reg_xmdr_c_ltr_action_type_set(payload, MLXSW_REG_XMDR_C_LTR_ACTION_TYPE_IP2ME); - mlxsw_reg_xmdr_c_ltr_pointer_to_tunnel_set(payload, - MLXSW_REG_XMDR_C_LTR_POINTER_TO_TUNNEL_DISABLED_MAGIC); -} - -static inline void mlxsw_reg_xmdr_c_ltr_act_ip2me_tun_pack(char *xmdr_payload, - unsigned int trans_offset, - u32 pointer_to_tunnel) -{ - char *payload = xmdr_payload + MLXSW_REG_XMDR_BASE_LEN + trans_offset; - - mlxsw_reg_xmdr_c_ltr_action_type_set(payload, MLXSW_REG_XMDR_C_LTR_ACTION_TYPE_IP2ME); - mlxsw_reg_xmdr_c_ltr_pointer_to_tunnel_set(payload, pointer_to_tunnel); -} - -/* XRMT - XM Router M Table Register - * --------------------------------- - * The XRMT configures the M-Table for the XLT-LPM. - */ -#define MLXSW_REG_XRMT_ID 0x7810 -#define MLXSW_REG_XRMT_LEN 0x14 - -MLXSW_REG_DEFINE(xrmt, MLXSW_REG_XRMT_ID, MLXSW_REG_XRMT_LEN); - -/* reg_xrmt_index - * Index in M-Table. - * Range 0..cap_xlt_mtable-1 - * Access: Index - */ -MLXSW_ITEM32(reg, xrmt, index, 0x04, 0, 20); - -/* reg_xrmt_l0_val - * Access: RW - */ -MLXSW_ITEM32(reg, xrmt, l0_val, 0x10, 24, 8); - -static inline void mlxsw_reg_xrmt_pack(char *payload, u32 index, u8 l0_val) -{ - MLXSW_REG_ZERO(xrmt, payload); - mlxsw_reg_xrmt_index_set(payload, index); - mlxsw_reg_xrmt_l0_val_set(payload, l0_val); -} - -/* XRALTA - XM Router Algorithmic LPM Tree Allocation Register - * ----------------------------------------------------------- - * The XRALTA is used to allocate the XLT LPM trees. - * - * This register embeds original RALTA register. - */ -#define MLXSW_REG_XRALTA_ID 0x7811 -#define MLXSW_REG_XRALTA_LEN 0x08 -#define MLXSW_REG_XRALTA_RALTA_OFFSET 0x04 - -MLXSW_REG_DEFINE(xralta, MLXSW_REG_XRALTA_ID, MLXSW_REG_XRALTA_LEN); - -static inline void mlxsw_reg_xralta_pack(char *payload, bool alloc, - enum mlxsw_reg_ralxx_protocol protocol, - u8 tree_id) -{ - char *ralta_payload = payload + MLXSW_REG_XRALTA_RALTA_OFFSET; - - MLXSW_REG_ZERO(xralta, payload); - mlxsw_reg_ralta_pack(ralta_payload, alloc, protocol, tree_id); -} - -/* XRALST - XM Router Algorithmic LPM Structure Tree Register - * ---------------------------------------------------------- - * The XRALST is used to set and query the structure of an XLT LPM tree. - * - * This register embeds original RALST register. - */ -#define MLXSW_REG_XRALST_ID 0x7812 -#define MLXSW_REG_XRALST_LEN 0x108 -#define MLXSW_REG_XRALST_RALST_OFFSET 0x04 - -MLXSW_REG_DEFINE(xralst, MLXSW_REG_XRALST_ID, MLXSW_REG_XRALST_LEN); - -static inline void mlxsw_reg_xralst_pack(char *payload, u8 root_bin, u8 tree_id) -{ - char *ralst_payload = payload + MLXSW_REG_XRALST_RALST_OFFSET; - - MLXSW_REG_ZERO(xralst, payload); - mlxsw_reg_ralst_pack(ralst_payload, root_bin, tree_id); -} - -static inline void mlxsw_reg_xralst_bin_pack(char *payload, u8 bin_number, - u8 left_child_bin, - u8 right_child_bin) -{ - char *ralst_payload = payload + MLXSW_REG_XRALST_RALST_OFFSET; - - mlxsw_reg_ralst_bin_pack(ralst_payload, bin_number, left_child_bin, - right_child_bin); -} - -/* XRALTB - XM Router Algorithmic LPM Tree Binding Register - * -------------------------------------------------------- - * The XRALTB register is used to bind virtual router and protocol - * to an allocated LPM tree. - * - * This register embeds original RALTB register. - */ -#define MLXSW_REG_XRALTB_ID 0x7813 -#define MLXSW_REG_XRALTB_LEN 0x08 -#define MLXSW_REG_XRALTB_RALTB_OFFSET 0x04 - -MLXSW_REG_DEFINE(xraltb, MLXSW_REG_XRALTB_ID, MLXSW_REG_XRALTB_LEN); - -static inline void mlxsw_reg_xraltb_pack(char *payload, u16 virtual_router, - enum mlxsw_reg_ralxx_protocol protocol, - u8 tree_id) -{ - char *raltb_payload = payload + MLXSW_REG_XRALTB_RALTB_OFFSET; - - MLXSW_REG_ZERO(xraltb, payload); - mlxsw_reg_raltb_pack(raltb_payload, virtual_router, protocol, tree_id); -} - /* MFCR - Management Fan Control Register * -------------------------------------- * This register controls the settings of the Fan Speed PWM mechanism. @@ -13084,16 +12430,6 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = { MLXSW_REG(rigr2), MLXSW_REG(recr2), MLXSW_REG(rmft2), - MLXSW_REG(rxlte), - MLXSW_REG(rxltm), - MLXSW_REG(rlcmld), - MLXSW_REG(rlpmce), - MLXSW_REG(xltq), - MLXSW_REG(xmdr), - MLXSW_REG(xrmt), - MLXSW_REG(xralta), - MLXSW_REG(xralst), - MLXSW_REG(xraltb), MLXSW_REG(mfcr), MLXSW_REG(mfsc), MLXSW_REG(mfsm), diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index cafd206e8d7e..c949005f56dc 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -2105,9 +2105,6 @@ static int mlxsw_sp_port_module_info_init(struct mlxsw_sp *mlxsw_sp) return -ENOMEM; for (i = 1; i < max_ports; i++) { - if (mlxsw_core_port_is_xm(mlxsw_sp->core, i)) - continue; - port_mapping = &mlxsw_sp->port_mapping[i]; err = mlxsw_sp_port_module_info_get(mlxsw_sp, i, port_mapping); if (err) @@ -3410,8 +3407,6 @@ static const struct mlxsw_config_profile mlxsw_sp2_config_profile = { .max_ib_mc = 0, .used_max_pkey = 1, .max_pkey = 0, - .used_kvh_xlt_cache_mode = 1, - .kvh_xlt_cache_mode = 1, .swid_config = { { .used_type = 1, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 9dbb573d53ea..e3f52019cbcb 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -443,65 +443,12 @@ struct mlxsw_sp_fib_entry_decap { u32 tunnel_index; }; -static struct mlxsw_sp_fib_entry_priv * -mlxsw_sp_fib_entry_priv_create(const struct mlxsw_sp_router_ll_ops *ll_ops) -{ - struct mlxsw_sp_fib_entry_priv *priv; - - if (!ll_ops->fib_entry_priv_size) - /* No need to have priv */ - return NULL; - - priv = kzalloc(sizeof(*priv) + ll_ops->fib_entry_priv_size, GFP_KERNEL); - if (!priv) - return ERR_PTR(-ENOMEM); - refcount_set(&priv->refcnt, 1); - return priv; -} - -static void -mlxsw_sp_fib_entry_priv_destroy(struct mlxsw_sp_fib_entry_priv *priv) -{ - kfree(priv); -} - -static void mlxsw_sp_fib_entry_priv_hold(struct mlxsw_sp_fib_entry_priv *priv) -{ - refcount_inc(&priv->refcnt); -} - -static void mlxsw_sp_fib_entry_priv_put(struct mlxsw_sp_fib_entry_priv *priv) -{ - if (!priv || !refcount_dec_and_test(&priv->refcnt)) - return; - mlxsw_sp_fib_entry_priv_destroy(priv); -} - -static void mlxsw_sp_fib_entry_op_ctx_priv_hold(struct mlxsw_sp_fib_entry_op_ctx *op_ctx, - struct mlxsw_sp_fib_entry_priv *priv) -{ - if (!priv) - return; - mlxsw_sp_fib_entry_priv_hold(priv); - list_add(&priv->list, &op_ctx->fib_entry_priv_list); -} - -static void mlxsw_sp_fib_entry_op_ctx_priv_put_all(struct mlxsw_sp_fib_entry_op_ctx *op_ctx) -{ - struct mlxsw_sp_fib_entry_priv *priv, *tmp; - - list_for_each_entry_safe(priv, tmp, &op_ctx->fib_entry_priv_list, list) - mlxsw_sp_fib_entry_priv_put(priv); - INIT_LIST_HEAD(&op_ctx->fib_entry_priv_list); -} - struct mlxsw_sp_fib_entry { struct mlxsw_sp_fib_node *fib_node; enum mlxsw_sp_fib_entry_type type; struct list_head nexthop_group_node; struct mlxsw_sp_nexthop_group *nh_group; struct mlxsw_sp_fib_entry_decap decap; /* Valid for decap entries. */ - struct mlxsw_sp_fib_entry_priv *priv; }; struct mlxsw_sp_fib4_entry { @@ -537,7 +484,6 @@ struct mlxsw_sp_fib { struct mlxsw_sp_vr *vr; struct mlxsw_sp_lpm_tree *lpm_tree; enum mlxsw_sp_l3proto proto; - const struct mlxsw_sp_router_ll_ops *ll_ops; }; struct mlxsw_sp_vr { @@ -551,45 +497,16 @@ struct mlxsw_sp_vr { refcount_t ul_rif_refcnt; }; -static int mlxsw_sp_router_ll_basic_init(struct mlxsw_sp *mlxsw_sp, u16 vr_id, - enum mlxsw_sp_l3proto proto) -{ - return 0; -} - -static int mlxsw_sp_router_ll_basic_ralta_write(struct mlxsw_sp *mlxsw_sp, char *xralta_pl) -{ - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralta), - xralta_pl + MLXSW_REG_XRALTA_RALTA_OFFSET); -} - -static int mlxsw_sp_router_ll_basic_ralst_write(struct mlxsw_sp *mlxsw_sp, char *xralst_pl) -{ - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralst), - xralst_pl + MLXSW_REG_XRALST_RALST_OFFSET); -} - -static int mlxsw_sp_router_ll_basic_raltb_write(struct mlxsw_sp *mlxsw_sp, char *xraltb_pl) -{ - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), - xraltb_pl + MLXSW_REG_XRALTB_RALTB_OFFSET); -} - static const struct rhashtable_params mlxsw_sp_fib_ht_params; static struct mlxsw_sp_fib *mlxsw_sp_fib_create(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr, enum mlxsw_sp_l3proto proto) { - const struct mlxsw_sp_router_ll_ops *ll_ops = mlxsw_sp->router->proto_ll_ops[proto]; struct mlxsw_sp_lpm_tree *lpm_tree; struct mlxsw_sp_fib *fib; int err; - err = ll_ops->init(mlxsw_sp, vr->id, proto); - if (err) - return ERR_PTR(err); - lpm_tree = mlxsw_sp->router->lpm.proto_trees[proto]; fib = kzalloc(sizeof(*fib), GFP_KERNEL); if (!fib) @@ -601,7 +518,6 @@ static struct mlxsw_sp_fib *mlxsw_sp_fib_create(struct mlxsw_sp *mlxsw_sp, fib->proto = proto; fib->vr = vr; fib->lpm_tree = lpm_tree; - fib->ll_ops = ll_ops; mlxsw_sp_lpm_tree_hold(lpm_tree); err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, fib, lpm_tree->id); if (err) @@ -640,36 +556,33 @@ mlxsw_sp_lpm_tree_find_unused(struct mlxsw_sp *mlxsw_sp) } static int mlxsw_sp_lpm_tree_alloc(struct mlxsw_sp *mlxsw_sp, - const struct mlxsw_sp_router_ll_ops *ll_ops, struct mlxsw_sp_lpm_tree *lpm_tree) { - char xralta_pl[MLXSW_REG_XRALTA_LEN]; + char ralta_pl[MLXSW_REG_RALTA_LEN]; - mlxsw_reg_xralta_pack(xralta_pl, true, - (enum mlxsw_reg_ralxx_protocol) lpm_tree->proto, - lpm_tree->id); - return ll_ops->ralta_write(mlxsw_sp, xralta_pl); + mlxsw_reg_ralta_pack(ralta_pl, true, + (enum mlxsw_reg_ralxx_protocol) lpm_tree->proto, + lpm_tree->id); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralta), ralta_pl); } static void mlxsw_sp_lpm_tree_free(struct mlxsw_sp *mlxsw_sp, - const struct mlxsw_sp_router_ll_ops *ll_ops, struct mlxsw_sp_lpm_tree *lpm_tree) { - char xralta_pl[MLXSW_REG_XRALTA_LEN]; + char ralta_pl[MLXSW_REG_RALTA_LEN]; - mlxsw_reg_xralta_pack(xralta_pl, false, - (enum mlxsw_reg_ralxx_protocol) lpm_tree->proto, - lpm_tree->id); - ll_ops->ralta_write(mlxsw_sp, xralta_pl); + mlxsw_reg_ralta_pack(ralta_pl, false, + (enum mlxsw_reg_ralxx_protocol) lpm_tree->proto, + lpm_tree->id); + mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralta), ralta_pl); } static int mlxsw_sp_lpm_tree_left_struct_set(struct mlxsw_sp *mlxsw_sp, - const struct mlxsw_sp_router_ll_ops *ll_ops, struct mlxsw_sp_prefix_usage *prefix_usage, struct mlxsw_sp_lpm_tree *lpm_tree) { - char xralst_pl[MLXSW_REG_XRALST_LEN]; + char ralst_pl[MLXSW_REG_RALST_LEN]; u8 root_bin = 0; u8 prefix; u8 last_prefix = MLXSW_REG_RALST_BIN_NO_CHILD; @@ -677,20 +590,19 @@ mlxsw_sp_lpm_tree_left_struct_set(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_prefix_usage_for_each(prefix, prefix_usage) root_bin = prefix; - mlxsw_reg_xralst_pack(xralst_pl, root_bin, lpm_tree->id); + mlxsw_reg_ralst_pack(ralst_pl, root_bin, lpm_tree->id); mlxsw_sp_prefix_usage_for_each(prefix, prefix_usage) { if (prefix == 0) continue; - mlxsw_reg_xralst_bin_pack(xralst_pl, prefix, last_prefix, - MLXSW_REG_RALST_BIN_NO_CHILD); + mlxsw_reg_ralst_bin_pack(ralst_pl, prefix, last_prefix, + MLXSW_REG_RALST_BIN_NO_CHILD); last_prefix = prefix; } - return ll_ops->ralst_write(mlxsw_sp, xralst_pl); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralst), ralst_pl); } static struct mlxsw_sp_lpm_tree * mlxsw_sp_lpm_tree_create(struct mlxsw_sp *mlxsw_sp, - const struct mlxsw_sp_router_ll_ops *ll_ops, struct mlxsw_sp_prefix_usage *prefix_usage, enum mlxsw_sp_l3proto proto) { @@ -701,11 +613,12 @@ mlxsw_sp_lpm_tree_create(struct mlxsw_sp *mlxsw_sp, if (!lpm_tree) return ERR_PTR(-EBUSY); lpm_tree->proto = proto; - err = mlxsw_sp_lpm_tree_alloc(mlxsw_sp, ll_ops, lpm_tree); + err = mlxsw_sp_lpm_tree_alloc(mlxsw_sp, lpm_tree); if (err) return ERR_PTR(err); - err = mlxsw_sp_lpm_tree_left_struct_set(mlxsw_sp, ll_ops, prefix_usage, lpm_tree); + err = mlxsw_sp_lpm_tree_left_struct_set(mlxsw_sp, prefix_usage, + lpm_tree); if (err) goto err_left_struct_set; memcpy(&lpm_tree->prefix_usage, prefix_usage, @@ -716,15 +629,14 @@ mlxsw_sp_lpm_tree_create(struct mlxsw_sp *mlxsw_sp, return lpm_tree; err_left_struct_set: - mlxsw_sp_lpm_tree_free(mlxsw_sp, ll_ops, lpm_tree); + mlxsw_sp_lpm_tree_free(mlxsw_sp, lpm_tree); return ERR_PTR(err); } static void mlxsw_sp_lpm_tree_destroy(struct mlxsw_sp *mlxsw_sp, - const struct mlxsw_sp_router_ll_ops *ll_ops, struct mlxsw_sp_lpm_tree *lpm_tree) { - mlxsw_sp_lpm_tree_free(mlxsw_sp, ll_ops, lpm_tree); + mlxsw_sp_lpm_tree_free(mlxsw_sp, lpm_tree); } static struct mlxsw_sp_lpm_tree * @@ -732,7 +644,6 @@ mlxsw_sp_lpm_tree_get(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_prefix_usage *prefix_usage, enum mlxsw_sp_l3proto proto) { - const struct mlxsw_sp_router_ll_ops *ll_ops = mlxsw_sp->router->proto_ll_ops[proto]; struct mlxsw_sp_lpm_tree *lpm_tree; int i; @@ -746,7 +657,7 @@ mlxsw_sp_lpm_tree_get(struct mlxsw_sp *mlxsw_sp, return lpm_tree; } } - return mlxsw_sp_lpm_tree_create(mlxsw_sp, ll_ops, prefix_usage, proto); + return mlxsw_sp_lpm_tree_create(mlxsw_sp, prefix_usage, proto); } static void mlxsw_sp_lpm_tree_hold(struct mlxsw_sp_lpm_tree *lpm_tree) @@ -757,11 +668,8 @@ static void mlxsw_sp_lpm_tree_hold(struct mlxsw_sp_lpm_tree *lpm_tree) static void mlxsw_sp_lpm_tree_put(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_lpm_tree *lpm_tree) { - const struct mlxsw_sp_router_ll_ops *ll_ops = - mlxsw_sp->router->proto_ll_ops[lpm_tree->proto]; - if (--lpm_tree->ref_count == 0) - mlxsw_sp_lpm_tree_destroy(mlxsw_sp, ll_ops, lpm_tree); + mlxsw_sp_lpm_tree_destroy(mlxsw_sp, lpm_tree); } #define MLXSW_SP_LPM_TREE_MIN 1 /* tree 0 is reserved */ @@ -851,23 +759,23 @@ static struct mlxsw_sp_vr *mlxsw_sp_vr_find_unused(struct mlxsw_sp *mlxsw_sp) static int mlxsw_sp_vr_lpm_tree_bind(struct mlxsw_sp *mlxsw_sp, const struct mlxsw_sp_fib *fib, u8 tree_id) { - char xraltb_pl[MLXSW_REG_XRALTB_LEN]; + char raltb_pl[MLXSW_REG_RALTB_LEN]; - mlxsw_reg_xraltb_pack(xraltb_pl, fib->vr->id, - (enum mlxsw_reg_ralxx_protocol) fib->proto, - tree_id); - return fib->ll_ops->raltb_write(mlxsw_sp, xraltb_pl); + mlxsw_reg_raltb_pack(raltb_pl, fib->vr->id, + (enum mlxsw_reg_ralxx_protocol) fib->proto, + tree_id); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), raltb_pl); } static int mlxsw_sp_vr_lpm_tree_unbind(struct mlxsw_sp *mlxsw_sp, const struct mlxsw_sp_fib *fib) { - char xraltb_pl[MLXSW_REG_XRALTB_LEN]; + char raltb_pl[MLXSW_REG_RALTB_LEN]; /* Bind to tree 0 which is default */ - mlxsw_reg_xraltb_pack(xraltb_pl, fib->vr->id, - (enum mlxsw_reg_ralxx_protocol) fib->proto, 0); - return fib->ll_ops->raltb_write(mlxsw_sp, xraltb_pl); + mlxsw_reg_raltb_pack(raltb_pl, fib->vr->id, + (enum mlxsw_reg_ralxx_protocol) fib->proto, 0); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), raltb_pl); } static u32 mlxsw_sp_fix_tb_id(u32 tb_id) @@ -5778,14 +5686,13 @@ mlxsw_sp_fib_entry_hw_flags_clear(struct mlxsw_sp *mlxsw_sp, static void mlxsw_sp_fib_entry_hw_flags_refresh(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_entry *fib_entry, - enum mlxsw_sp_fib_entry_op op) + enum mlxsw_reg_ralue_op op) { switch (op) { - case MLXSW_SP_FIB_ENTRY_OP_WRITE: - case MLXSW_SP_FIB_ENTRY_OP_UPDATE: + case MLXSW_REG_RALUE_OP_WRITE_WRITE: mlxsw_sp_fib_entry_hw_flags_set(mlxsw_sp, fib_entry); break; - case MLXSW_SP_FIB_ENTRY_OP_DELETE: + case MLXSW_REG_RALUE_OP_WRITE_DELETE: mlxsw_sp_fib_entry_hw_flags_clear(mlxsw_sp, fib_entry); break; default: @@ -5793,140 +5700,39 @@ mlxsw_sp_fib_entry_hw_flags_refresh(struct mlxsw_sp *mlxsw_sp, } } -struct mlxsw_sp_fib_entry_op_ctx_basic { - char ralue_pl[MLXSW_REG_RALUE_LEN]; -}; - static void -mlxsw_sp_router_ll_basic_fib_entry_pack(struct mlxsw_sp_fib_entry_op_ctx *op_ctx, - enum mlxsw_sp_l3proto proto, - enum mlxsw_sp_fib_entry_op op, - u16 virtual_router, u8 prefix_len, - unsigned char *addr, - struct mlxsw_sp_fib_entry_priv *priv) +mlxsw_sp_fib_entry_ralue_pack(char *ralue_pl, + const struct mlxsw_sp_fib_entry *fib_entry, + enum mlxsw_reg_ralue_op op) { - struct mlxsw_sp_fib_entry_op_ctx_basic *op_ctx_basic = (void *) op_ctx->ll_priv; - enum mlxsw_reg_ralxx_protocol ralxx_proto; - char *ralue_pl = op_ctx_basic->ralue_pl; - enum mlxsw_reg_ralue_op ralue_op; - - ralxx_proto = (enum mlxsw_reg_ralxx_protocol) proto; + struct mlxsw_sp_fib *fib = fib_entry->fib_node->fib; + enum mlxsw_reg_ralxx_protocol proto; + u32 *p_dip; - switch (op) { - case MLXSW_SP_FIB_ENTRY_OP_WRITE: - case MLXSW_SP_FIB_ENTRY_OP_UPDATE: - ralue_op = MLXSW_REG_RALUE_OP_WRITE_WRITE; - break; - case MLXSW_SP_FIB_ENTRY_OP_DELETE: - ralue_op = MLXSW_REG_RALUE_OP_WRITE_DELETE; - break; - default: - WARN_ON_ONCE(1); - return; - } + proto = (enum mlxsw_reg_ralxx_protocol) fib->proto; - switch (proto) { + switch (fib->proto) { case MLXSW_SP_L3_PROTO_IPV4: - mlxsw_reg_ralue_pack4(ralue_pl, ralxx_proto, ralue_op, - virtual_router, prefix_len, (u32 *) addr); + p_dip = (u32 *) fib_entry->fib_node->key.addr; + mlxsw_reg_ralue_pack4(ralue_pl, proto, op, fib->vr->id, + fib_entry->fib_node->key.prefix_len, + *p_dip); break; case MLXSW_SP_L3_PROTO_IPV6: - mlxsw_reg_ralue_pack6(ralue_pl, ralxx_proto, ralue_op, - virtual_router, prefix_len, addr); + mlxsw_reg_ralue_pack6(ralue_pl, proto, op, fib->vr->id, + fib_entry->fib_node->key.prefix_len, + fib_entry->fib_node->key.addr); break; } } -static void -mlxsw_sp_router_ll_basic_fib_entry_act_remote_pack(struct mlxsw_sp_fib_entry_op_ctx *op_ctx, - enum mlxsw_reg_ralue_trap_action trap_action, - u16 trap_id, u32 adjacency_index, u16 ecmp_size) -{ - struct mlxsw_sp_fib_entry_op_ctx_basic *op_ctx_basic = (void *) op_ctx->ll_priv; - - mlxsw_reg_ralue_act_remote_pack(op_ctx_basic->ralue_pl, trap_action, - trap_id, adjacency_index, ecmp_size); -} - -static void -mlxsw_sp_router_ll_basic_fib_entry_act_local_pack(struct mlxsw_sp_fib_entry_op_ctx *op_ctx, - enum mlxsw_reg_ralue_trap_action trap_action, - u16 trap_id, u16 local_erif) -{ - struct mlxsw_sp_fib_entry_op_ctx_basic *op_ctx_basic = (void *) op_ctx->ll_priv; - - mlxsw_reg_ralue_act_local_pack(op_ctx_basic->ralue_pl, trap_action, - trap_id, local_erif); -} - -static void -mlxsw_sp_router_ll_basic_fib_entry_act_ip2me_pack(struct mlxsw_sp_fib_entry_op_ctx *op_ctx) -{ - struct mlxsw_sp_fib_entry_op_ctx_basic *op_ctx_basic = (void *) op_ctx->ll_priv; - - mlxsw_reg_ralue_act_ip2me_pack(op_ctx_basic->ralue_pl); -} - -static void -mlxsw_sp_router_ll_basic_fib_entry_act_ip2me_tun_pack(struct mlxsw_sp_fib_entry_op_ctx *op_ctx, - u32 tunnel_ptr) -{ - struct mlxsw_sp_fib_entry_op_ctx_basic *op_ctx_basic = (void *) op_ctx->ll_priv; - - mlxsw_reg_ralue_act_ip2me_tun_pack(op_ctx_basic->ralue_pl, tunnel_ptr); -} - -static int -mlxsw_sp_router_ll_basic_fib_entry_commit(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry_op_ctx *op_ctx, - bool *postponed_for_bulk) -{ - struct mlxsw_sp_fib_entry_op_ctx_basic *op_ctx_basic = (void *) op_ctx->ll_priv; - - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), - op_ctx_basic->ralue_pl); -} - -static bool -mlxsw_sp_router_ll_basic_fib_entry_is_committed(struct mlxsw_sp_fib_entry_priv *priv) -{ - return true; -} - -static void mlxsw_sp_fib_entry_pack(struct mlxsw_sp_fib_entry_op_ctx *op_ctx, - struct mlxsw_sp_fib_entry *fib_entry, - enum mlxsw_sp_fib_entry_op op) -{ - struct mlxsw_sp_fib *fib = fib_entry->fib_node->fib; - - mlxsw_sp_fib_entry_op_ctx_priv_hold(op_ctx, fib_entry->priv); - fib->ll_ops->fib_entry_pack(op_ctx, fib->proto, op, fib->vr->id, - fib_entry->fib_node->key.prefix_len, - fib_entry->fib_node->key.addr, - fib_entry->priv); -} - -static int mlxsw_sp_fib_entry_commit(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry_op_ctx *op_ctx, - const struct mlxsw_sp_router_ll_ops *ll_ops) -{ - bool postponed_for_bulk = false; - int err; - - err = ll_ops->fib_entry_commit(mlxsw_sp, op_ctx, &postponed_for_bulk); - if (!postponed_for_bulk) - mlxsw_sp_fib_entry_op_ctx_priv_put_all(op_ctx); - return err; -} - static int mlxsw_sp_fib_entry_op_remote(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry_op_ctx *op_ctx, struct mlxsw_sp_fib_entry *fib_entry, - enum mlxsw_sp_fib_entry_op op) + enum mlxsw_reg_ralue_op op) { - const struct mlxsw_sp_router_ll_ops *ll_ops = fib_entry->fib_node->fib->ll_ops; struct mlxsw_sp_nexthop_group *nh_group = fib_entry->nh_group; struct mlxsw_sp_nexthop_group_info *nhgi = nh_group->nhgi; + char ralue_pl[MLXSW_REG_RALUE_LEN]; enum mlxsw_reg_ralue_trap_action trap_action; u16 trap_id = 0; u32 adjacency_index = 0; @@ -5949,20 +5755,19 @@ static int mlxsw_sp_fib_entry_op_remote(struct mlxsw_sp *mlxsw_sp, trap_id = MLXSW_TRAP_ID_RTR_INGRESS0; } - mlxsw_sp_fib_entry_pack(op_ctx, fib_entry, op); - ll_ops->fib_entry_act_remote_pack(op_ctx, trap_action, trap_id, - adjacency_index, ecmp_size); - return mlxsw_sp_fib_entry_commit(mlxsw_sp, op_ctx, ll_ops); + mlxsw_sp_fib_entry_ralue_pack(ralue_pl, fib_entry, op); + mlxsw_reg_ralue_act_remote_pack(ralue_pl, trap_action, trap_id, + adjacency_index, ecmp_size); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl); } static int mlxsw_sp_fib_entry_op_local(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry_op_ctx *op_ctx, struct mlxsw_sp_fib_entry *fib_entry, - enum mlxsw_sp_fib_entry_op op) + enum mlxsw_reg_ralue_op op) { - const struct mlxsw_sp_router_ll_ops *ll_ops = fib_entry->fib_node->fib->ll_ops; struct mlxsw_sp_rif *rif = fib_entry->nh_group->nhgi->nh_rif; enum mlxsw_reg_ralue_trap_action trap_action; + char ralue_pl[MLXSW_REG_RALUE_LEN]; u16 trap_id = 0; u16 rif_index = 0; @@ -5974,64 +5779,61 @@ static int mlxsw_sp_fib_entry_op_local(struct mlxsw_sp *mlxsw_sp, trap_id = MLXSW_TRAP_ID_RTR_INGRESS0; } - mlxsw_sp_fib_entry_pack(op_ctx, fib_entry, op); - ll_ops->fib_entry_act_local_pack(op_ctx, trap_action, trap_id, rif_index); - return mlxsw_sp_fib_entry_commit(mlxsw_sp, op_ctx, ll_ops); + mlxsw_sp_fib_entry_ralue_pack(ralue_pl, fib_entry, op); + mlxsw_reg_ralue_act_local_pack(ralue_pl, trap_action, trap_id, + rif_index); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl); } static int mlxsw_sp_fib_entry_op_trap(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry_op_ctx *op_ctx, struct mlxsw_sp_fib_entry *fib_entry, - enum mlxsw_sp_fib_entry_op op) + enum mlxsw_reg_ralue_op op) { - const struct mlxsw_sp_router_ll_ops *ll_ops = fib_entry->fib_node->fib->ll_ops; + char ralue_pl[MLXSW_REG_RALUE_LEN]; - mlxsw_sp_fib_entry_pack(op_ctx, fib_entry, op); - ll_ops->fib_entry_act_ip2me_pack(op_ctx); - return mlxsw_sp_fib_entry_commit(mlxsw_sp, op_ctx, ll_ops); + mlxsw_sp_fib_entry_ralue_pack(ralue_pl, fib_entry, op); + mlxsw_reg_ralue_act_ip2me_pack(ralue_pl); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl); } static int mlxsw_sp_fib_entry_op_blackhole(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry_op_ctx *op_ctx, struct mlxsw_sp_fib_entry *fib_entry, - enum mlxsw_sp_fib_entry_op op) + enum mlxsw_reg_ralue_op op) { - const struct mlxsw_sp_router_ll_ops *ll_ops = fib_entry->fib_node->fib->ll_ops; enum mlxsw_reg_ralue_trap_action trap_action; + char ralue_pl[MLXSW_REG_RALUE_LEN]; trap_action = MLXSW_REG_RALUE_TRAP_ACTION_DISCARD_ERROR; - mlxsw_sp_fib_entry_pack(op_ctx, fib_entry, op); - ll_ops->fib_entry_act_local_pack(op_ctx, trap_action, 0, 0); - return mlxsw_sp_fib_entry_commit(mlxsw_sp, op_ctx, ll_ops); + mlxsw_sp_fib_entry_ralue_pack(ralue_pl, fib_entry, op); + mlxsw_reg_ralue_act_local_pack(ralue_pl, trap_action, 0, 0); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl); } static int mlxsw_sp_fib_entry_op_unreachable(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry_op_ctx *op_ctx, struct mlxsw_sp_fib_entry *fib_entry, - enum mlxsw_sp_fib_entry_op op) + enum mlxsw_reg_ralue_op op) { - const struct mlxsw_sp_router_ll_ops *ll_ops = fib_entry->fib_node->fib->ll_ops; enum mlxsw_reg_ralue_trap_action trap_action; + char ralue_pl[MLXSW_REG_RALUE_LEN]; u16 trap_id; trap_action = MLXSW_REG_RALUE_TRAP_ACTION_TRAP; trap_id = MLXSW_TRAP_ID_RTR_INGRESS1; - mlxsw_sp_fib_entry_pack(op_ctx, fib_entry, op); - ll_ops->fib_entry_act_local_pack(op_ctx, trap_action, trap_id, 0); - return mlxsw_sp_fib_entry_commit(mlxsw_sp, op_ctx, ll_ops); + mlxsw_sp_fib_entry_ralue_pack(ralue_pl, fib_entry, op); + mlxsw_reg_ralue_act_local_pack(ralue_pl, trap_action, trap_id, 0); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl); } static int mlxsw_sp_fib_entry_op_ipip_decap(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry_op_ctx *op_ctx, struct mlxsw_sp_fib_entry *fib_entry, - enum mlxsw_sp_fib_entry_op op) + enum mlxsw_reg_ralue_op op) { - const struct mlxsw_sp_router_ll_ops *ll_ops = fib_entry->fib_node->fib->ll_ops; struct mlxsw_sp_ipip_entry *ipip_entry = fib_entry->decap.ipip_entry; const struct mlxsw_sp_ipip_ops *ipip_ops; + char ralue_pl[MLXSW_REG_RALUE_LEN]; int err; if (WARN_ON(!ipip_entry)) @@ -6043,55 +5845,54 @@ mlxsw_sp_fib_entry_op_ipip_decap(struct mlxsw_sp *mlxsw_sp, if (err) return err; - mlxsw_sp_fib_entry_pack(op_ctx, fib_entry, op); - ll_ops->fib_entry_act_ip2me_tun_pack(op_ctx, - fib_entry->decap.tunnel_index); - return mlxsw_sp_fib_entry_commit(mlxsw_sp, op_ctx, ll_ops); + mlxsw_sp_fib_entry_ralue_pack(ralue_pl, fib_entry, op); + mlxsw_reg_ralue_act_ip2me_tun_pack(ralue_pl, + fib_entry->decap.tunnel_index); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl); } static int mlxsw_sp_fib_entry_op_nve_decap(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry_op_ctx *op_ctx, struct mlxsw_sp_fib_entry *fib_entry, - enum mlxsw_sp_fib_entry_op op) + enum mlxsw_reg_ralue_op op) { - const struct mlxsw_sp_router_ll_ops *ll_ops = fib_entry->fib_node->fib->ll_ops; + char ralue_pl[MLXSW_REG_RALUE_LEN]; - mlxsw_sp_fib_entry_pack(op_ctx, fib_entry, op); - ll_ops->fib_entry_act_ip2me_tun_pack(op_ctx, - fib_entry->decap.tunnel_index); - return mlxsw_sp_fib_entry_commit(mlxsw_sp, op_ctx, ll_ops); + mlxsw_sp_fib_entry_ralue_pack(ralue_pl, fib_entry, op); + mlxsw_reg_ralue_act_ip2me_tun_pack(ralue_pl, + fib_entry->decap.tunnel_index); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl); } static int __mlxsw_sp_fib_entry_op(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry_op_ctx *op_ctx, struct mlxsw_sp_fib_entry *fib_entry, - enum mlxsw_sp_fib_entry_op op) + enum mlxsw_reg_ralue_op op) { switch (fib_entry->type) { case MLXSW_SP_FIB_ENTRY_TYPE_REMOTE: - return mlxsw_sp_fib_entry_op_remote(mlxsw_sp, op_ctx, fib_entry, op); + return mlxsw_sp_fib_entry_op_remote(mlxsw_sp, fib_entry, op); case MLXSW_SP_FIB_ENTRY_TYPE_LOCAL: - return mlxsw_sp_fib_entry_op_local(mlxsw_sp, op_ctx, fib_entry, op); + return mlxsw_sp_fib_entry_op_local(mlxsw_sp, fib_entry, op); case MLXSW_SP_FIB_ENTRY_TYPE_TRAP: - return mlxsw_sp_fib_entry_op_trap(mlxsw_sp, op_ctx, fib_entry, op); + return mlxsw_sp_fib_entry_op_trap(mlxsw_sp, fib_entry, op); case MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE: - return mlxsw_sp_fib_entry_op_blackhole(mlxsw_sp, op_ctx, fib_entry, op); + return mlxsw_sp_fib_entry_op_blackhole(mlxsw_sp, fib_entry, op); case MLXSW_SP_FIB_ENTRY_TYPE_UNREACHABLE: - return mlxsw_sp_fib_entry_op_unreachable(mlxsw_sp, op_ctx, fib_entry, op); + return mlxsw_sp_fib_entry_op_unreachable(mlxsw_sp, fib_entry, + op); case MLXSW_SP_FIB_ENTRY_TYPE_IPIP_DECAP: - return mlxsw_sp_fib_entry_op_ipip_decap(mlxsw_sp, op_ctx, fib_entry, op); + return mlxsw_sp_fib_entry_op_ipip_decap(mlxsw_sp, + fib_entry, op); case MLXSW_SP_FIB_ENTRY_TYPE_NVE_DECAP: - return mlxsw_sp_fib_entry_op_nve_decap(mlxsw_sp, op_ctx, fib_entry, op); + return mlxsw_sp_fib_entry_op_nve_decap(mlxsw_sp, fib_entry, op); } return -EINVAL; } static int mlxsw_sp_fib_entry_op(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry_op_ctx *op_ctx, struct mlxsw_sp_fib_entry *fib_entry, - enum mlxsw_sp_fib_entry_op op) + enum mlxsw_reg_ralue_op op) { - int err = __mlxsw_sp_fib_entry_op(mlxsw_sp, op_ctx, fib_entry, op); + int err = __mlxsw_sp_fib_entry_op(mlxsw_sp, fib_entry, op); if (err) return err; @@ -6101,35 +5902,18 @@ static int mlxsw_sp_fib_entry_op(struct mlxsw_sp *mlxsw_sp, return err; } -static int __mlxsw_sp_fib_entry_update(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry_op_ctx *op_ctx, - struct mlxsw_sp_fib_entry *fib_entry, - bool is_new) -{ - return mlxsw_sp_fib_entry_op(mlxsw_sp, op_ctx, fib_entry, - is_new ? MLXSW_SP_FIB_ENTRY_OP_WRITE : - MLXSW_SP_FIB_ENTRY_OP_UPDATE); -} - static int mlxsw_sp_fib_entry_update(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_entry *fib_entry) { - struct mlxsw_sp_fib_entry_op_ctx *op_ctx = mlxsw_sp->router->ll_op_ctx; - - mlxsw_sp_fib_entry_op_ctx_clear(op_ctx); - return __mlxsw_sp_fib_entry_update(mlxsw_sp, op_ctx, fib_entry, false); + return mlxsw_sp_fib_entry_op(mlxsw_sp, fib_entry, + MLXSW_REG_RALUE_OP_WRITE_WRITE); } static int mlxsw_sp_fib_entry_del(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry_op_ctx *op_ctx, struct mlxsw_sp_fib_entry *fib_entry) { - const struct mlxsw_sp_router_ll_ops *ll_ops = fib_entry->fib_node->fib->ll_ops; - - if (!ll_ops->fib_entry_is_committed(fib_entry->priv)) - return 0; - return mlxsw_sp_fib_entry_op(mlxsw_sp, op_ctx, fib_entry, - MLXSW_SP_FIB_ENTRY_OP_DELETE); + return mlxsw_sp_fib_entry_op(mlxsw_sp, fib_entry, + MLXSW_REG_RALUE_OP_WRITE_DELETE); } static int @@ -6224,12 +6008,6 @@ mlxsw_sp_fib4_entry_create(struct mlxsw_sp *mlxsw_sp, return ERR_PTR(-ENOMEM); fib_entry = &fib4_entry->common; - fib_entry->priv = mlxsw_sp_fib_entry_priv_create(fib_node->fib->ll_ops); - if (IS_ERR(fib_entry->priv)) { - err = PTR_ERR(fib_entry->priv); - goto err_fib_entry_priv_create; - } - err = mlxsw_sp_nexthop4_group_get(mlxsw_sp, fib_entry, fen_info->fi); if (err) goto err_nexthop4_group_get; @@ -6258,8 +6036,6 @@ err_fib4_entry_type_set: err_nexthop_group_vr_link: mlxsw_sp_nexthop4_group_put(mlxsw_sp, &fib4_entry->common); err_nexthop4_group_get: - mlxsw_sp_fib_entry_priv_put(fib_entry->priv); -err_fib_entry_priv_create: kfree(fib4_entry); return ERR_PTR(err); } @@ -6274,7 +6050,6 @@ static void mlxsw_sp_fib4_entry_destroy(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_nexthop_group_vr_unlink(fib4_entry->common.nh_group, fib_node->fib); mlxsw_sp_nexthop4_group_put(mlxsw_sp, &fib4_entry->common); - mlxsw_sp_fib_entry_priv_put(fib4_entry->common.priv); kfree(fib4_entry); } @@ -6512,16 +6287,14 @@ static void mlxsw_sp_fib_node_put(struct mlxsw_sp *mlxsw_sp, } static int mlxsw_sp_fib_node_entry_link(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry_op_ctx *op_ctx, struct mlxsw_sp_fib_entry *fib_entry) { struct mlxsw_sp_fib_node *fib_node = fib_entry->fib_node; - bool is_new = !fib_node->fib_entry; int err; fib_node->fib_entry = fib_entry; - err = __mlxsw_sp_fib_entry_update(mlxsw_sp, op_ctx, fib_entry, is_new); + err = mlxsw_sp_fib_entry_update(mlxsw_sp, fib_entry); if (err) goto err_fib_entry_update; @@ -6532,25 +6305,14 @@ err_fib_entry_update: return err; } -static int __mlxsw_sp_fib_node_entry_unlink(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry_op_ctx *op_ctx, - struct mlxsw_sp_fib_entry *fib_entry) +static void +mlxsw_sp_fib_node_entry_unlink(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry *fib_entry) { struct mlxsw_sp_fib_node *fib_node = fib_entry->fib_node; - int err; - err = mlxsw_sp_fib_entry_del(mlxsw_sp, op_ctx, fib_entry); + mlxsw_sp_fib_entry_del(mlxsw_sp, fib_entry); fib_node->fib_entry = NULL; - return err; -} - -static void mlxsw_sp_fib_node_entry_unlink(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry *fib_entry) -{ - struct mlxsw_sp_fib_entry_op_ctx *op_ctx = mlxsw_sp->router->ll_op_ctx; - - mlxsw_sp_fib_entry_op_ctx_clear(op_ctx); - __mlxsw_sp_fib_node_entry_unlink(mlxsw_sp, op_ctx, fib_entry); } static bool mlxsw_sp_fib4_allow_replace(struct mlxsw_sp_fib4_entry *fib4_entry) @@ -6572,7 +6334,6 @@ static bool mlxsw_sp_fib4_allow_replace(struct mlxsw_sp_fib4_entry *fib4_entry) static int mlxsw_sp_router_fib4_replace(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry_op_ctx *op_ctx, const struct fib_entry_notifier_info *fen_info) { struct mlxsw_sp_fib4_entry *fib4_entry, *fib4_replaced; @@ -6607,7 +6368,7 @@ mlxsw_sp_router_fib4_replace(struct mlxsw_sp *mlxsw_sp, } replaced = fib_node->fib_entry; - err = mlxsw_sp_fib_node_entry_link(mlxsw_sp, op_ctx, &fib4_entry->common); + err = mlxsw_sp_fib_node_entry_link(mlxsw_sp, &fib4_entry->common); if (err) { dev_warn(mlxsw_sp->bus_info->dev, "Failed to link FIB entry to node\n"); goto err_fib_node_entry_link; @@ -6632,23 +6393,20 @@ err_fib4_entry_create: return err; } -static int mlxsw_sp_router_fib4_del(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry_op_ctx *op_ctx, - struct fib_entry_notifier_info *fen_info) +static void mlxsw_sp_router_fib4_del(struct mlxsw_sp *mlxsw_sp, + struct fib_entry_notifier_info *fen_info) { struct mlxsw_sp_fib4_entry *fib4_entry; struct mlxsw_sp_fib_node *fib_node; - int err; fib4_entry = mlxsw_sp_fib4_entry_lookup(mlxsw_sp, fen_info); if (!fib4_entry) - return 0; + return; fib_node = fib4_entry->common.fib_node; - err = __mlxsw_sp_fib_node_entry_unlink(mlxsw_sp, op_ctx, &fib4_entry->common); + mlxsw_sp_fib_node_entry_unlink(mlxsw_sp, &fib4_entry->common); mlxsw_sp_fib4_entry_destroy(mlxsw_sp, fib4_entry); mlxsw_sp_fib_node_put(mlxsw_sp, fib_node); - return err; } static bool mlxsw_sp_fib6_rt_should_ignore(const struct fib6_info *rt) @@ -6946,9 +6704,9 @@ static void mlxsw_sp_nexthop6_group_put(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_nexthop6_group_destroy(mlxsw_sp, nh_grp); } -static int mlxsw_sp_nexthop6_group_update(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry_op_ctx *op_ctx, - struct mlxsw_sp_fib6_entry *fib6_entry) +static int +mlxsw_sp_nexthop6_group_update(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib6_entry *fib6_entry) { struct mlxsw_sp_nexthop_group *old_nh_grp = fib6_entry->common.nh_group; struct mlxsw_sp_fib_node *fib_node = fib6_entry->common.fib_node; @@ -6971,8 +6729,7 @@ static int mlxsw_sp_nexthop6_group_update(struct mlxsw_sp *mlxsw_sp, * currently associated with it in the device's table is that * of the old group. Start using the new one instead. */ - err = __mlxsw_sp_fib_entry_update(mlxsw_sp, op_ctx, - &fib6_entry->common, false); + err = mlxsw_sp_fib_entry_update(mlxsw_sp, &fib6_entry->common); if (err) goto err_fib_entry_update; @@ -6996,7 +6753,6 @@ err_nexthop6_group_get: static int mlxsw_sp_fib6_entry_nexthop_add(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry_op_ctx *op_ctx, struct mlxsw_sp_fib6_entry *fib6_entry, struct fib6_info **rt_arr, unsigned int nrt6) { @@ -7014,7 +6770,7 @@ mlxsw_sp_fib6_entry_nexthop_add(struct mlxsw_sp *mlxsw_sp, fib6_entry->nrt6++; } - err = mlxsw_sp_nexthop6_group_update(mlxsw_sp, op_ctx, fib6_entry); + err = mlxsw_sp_nexthop6_group_update(mlxsw_sp, fib6_entry); if (err) goto err_rt6_unwind; @@ -7033,7 +6789,6 @@ err_rt6_unwind: static void mlxsw_sp_fib6_entry_nexthop_del(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry_op_ctx *op_ctx, struct mlxsw_sp_fib6_entry *fib6_entry, struct fib6_info **rt_arr, unsigned int nrt6) { @@ -7051,7 +6806,7 @@ mlxsw_sp_fib6_entry_nexthop_del(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_rt6_destroy(mlxsw_sp_rt6); } - mlxsw_sp_nexthop6_group_update(mlxsw_sp, op_ctx, fib6_entry); + mlxsw_sp_nexthop6_group_update(mlxsw_sp, fib6_entry); } static int @@ -7137,12 +6892,6 @@ mlxsw_sp_fib6_entry_create(struct mlxsw_sp *mlxsw_sp, return ERR_PTR(-ENOMEM); fib_entry = &fib6_entry->common; - fib_entry->priv = mlxsw_sp_fib_entry_priv_create(fib_node->fib->ll_ops); - if (IS_ERR(fib_entry->priv)) { - err = PTR_ERR(fib_entry->priv); - goto err_fib_entry_priv_create; - } - INIT_LIST_HEAD(&fib6_entry->rt6_list); for (i = 0; i < nrt6; i++) { @@ -7184,8 +6933,6 @@ err_rt6_unwind: list_del(&mlxsw_sp_rt6->list); mlxsw_sp_rt6_destroy(mlxsw_sp_rt6); } - mlxsw_sp_fib_entry_priv_put(fib_entry->priv); -err_fib_entry_priv_create: kfree(fib6_entry); return ERR_PTR(err); } @@ -7208,7 +6955,6 @@ static void mlxsw_sp_fib6_entry_destroy(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_nexthop6_group_put(mlxsw_sp, &fib6_entry->common); mlxsw_sp_fib6_entry_rt_destroy_all(fib6_entry); WARN_ON(fib6_entry->nrt6); - mlxsw_sp_fib_entry_priv_put(fib6_entry->common.priv); kfree(fib6_entry); } @@ -7266,8 +7012,8 @@ static bool mlxsw_sp_fib6_allow_replace(struct mlxsw_sp_fib6_entry *fib6_entry) } static int mlxsw_sp_router_fib6_replace(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry_op_ctx *op_ctx, - struct fib6_info **rt_arr, unsigned int nrt6) + struct fib6_info **rt_arr, + unsigned int nrt6) { struct mlxsw_sp_fib6_entry *fib6_entry, *fib6_replaced; struct mlxsw_sp_fib_entry *replaced; @@ -7306,7 +7052,7 @@ static int mlxsw_sp_router_fib6_replace(struct mlxsw_sp *mlxsw_sp, } replaced = fib_node->fib_entry; - err = mlxsw_sp_fib_node_entry_link(mlxsw_sp, op_ctx, &fib6_entry->common); + err = mlxsw_sp_fib_node_entry_link(mlxsw_sp, &fib6_entry->common); if (err) goto err_fib_node_entry_link; @@ -7330,8 +7076,8 @@ err_fib6_entry_create: } static int mlxsw_sp_router_fib6_append(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry_op_ctx *op_ctx, - struct fib6_info **rt_arr, unsigned int nrt6) + struct fib6_info **rt_arr, + unsigned int nrt6) { struct mlxsw_sp_fib6_entry *fib6_entry; struct mlxsw_sp_fib_node *fib_node; @@ -7359,7 +7105,8 @@ static int mlxsw_sp_router_fib6_append(struct mlxsw_sp *mlxsw_sp, fib6_entry = container_of(fib_node->fib_entry, struct mlxsw_sp_fib6_entry, common); - err = mlxsw_sp_fib6_entry_nexthop_add(mlxsw_sp, op_ctx, fib6_entry, rt_arr, nrt6); + err = mlxsw_sp_fib6_entry_nexthop_add(mlxsw_sp, fib6_entry, rt_arr, + nrt6); if (err) goto err_fib6_entry_nexthop_add; @@ -7370,17 +7117,16 @@ err_fib6_entry_nexthop_add: return err; } -static int mlxsw_sp_router_fib6_del(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry_op_ctx *op_ctx, - struct fib6_info **rt_arr, unsigned int nrt6) +static void mlxsw_sp_router_fib6_del(struct mlxsw_sp *mlxsw_sp, + struct fib6_info **rt_arr, + unsigned int nrt6) { struct mlxsw_sp_fib6_entry *fib6_entry; struct mlxsw_sp_fib_node *fib_node; struct fib6_info *rt = rt_arr[0]; - int err; if (mlxsw_sp_fib6_rt_should_ignore(rt)) - return 0; + return; /* Multipath routes are first added to the FIB trie and only then * notified. If we vetoed the addition, we will get a delete @@ -7389,22 +7135,22 @@ static int mlxsw_sp_router_fib6_del(struct mlxsw_sp *mlxsw_sp, */ fib6_entry = mlxsw_sp_fib6_entry_lookup(mlxsw_sp, rt); if (!fib6_entry) - return 0; + return; /* If not all the nexthops are deleted, then only reduce the nexthop * group. */ if (nrt6 != fib6_entry->nrt6) { - mlxsw_sp_fib6_entry_nexthop_del(mlxsw_sp, op_ctx, fib6_entry, rt_arr, nrt6); - return 0; + mlxsw_sp_fib6_entry_nexthop_del(mlxsw_sp, fib6_entry, rt_arr, + nrt6); + return; } fib_node = fib6_entry->common.fib_node; - err = __mlxsw_sp_fib_node_entry_unlink(mlxsw_sp, op_ctx, &fib6_entry->common); + mlxsw_sp_fib_node_entry_unlink(mlxsw_sp, &fib6_entry->common); mlxsw_sp_fib6_entry_destroy(mlxsw_sp, fib6_entry); mlxsw_sp_fib_node_put(mlxsw_sp, fib_node); - return err; } static struct mlxsw_sp_mr_table * @@ -7557,15 +7303,15 @@ static void mlxsw_sp_router_fib_flush(struct mlxsw_sp *mlxsw_sp) } } -struct mlxsw_sp_fib6_event { +struct mlxsw_sp_fib6_event_work { struct fib6_info **rt_arr; unsigned int nrt6; }; -struct mlxsw_sp_fib_event { - struct list_head list; /* node in fib queue */ +struct mlxsw_sp_fib_event_work { + struct work_struct work; union { - struct mlxsw_sp_fib6_event fib6_event; + struct mlxsw_sp_fib6_event_work fib6_work; struct fib_entry_notifier_info fen_info; struct fib_rule_notifier_info fr_info; struct fib_nh_notifier_info fnh_info; @@ -7574,12 +7320,11 @@ struct mlxsw_sp_fib_event { }; struct mlxsw_sp *mlxsw_sp; unsigned long event; - int family; }; static int -mlxsw_sp_router_fib6_event_init(struct mlxsw_sp_fib6_event *fib6_event, - struct fib6_entry_notifier_info *fen6_info) +mlxsw_sp_router_fib6_work_init(struct mlxsw_sp_fib6_event_work *fib6_work, + struct fib6_entry_notifier_info *fen6_info) { struct fib6_info *rt = fen6_info->rt; struct fib6_info **rt_arr; @@ -7593,8 +7338,8 @@ mlxsw_sp_router_fib6_event_init(struct mlxsw_sp_fib6_event *fib6_event, if (!rt_arr) return -ENOMEM; - fib6_event->rt_arr = rt_arr; - fib6_event->nrt6 = nrt6; + fib6_work->rt_arr = rt_arr; + fib6_work->nrt6 = nrt6; rt_arr[0] = rt; fib6_info_hold(rt); @@ -7616,242 +7361,182 @@ mlxsw_sp_router_fib6_event_init(struct mlxsw_sp_fib6_event *fib6_event, } static void -mlxsw_sp_router_fib6_event_fini(struct mlxsw_sp_fib6_event *fib6_event) +mlxsw_sp_router_fib6_work_fini(struct mlxsw_sp_fib6_event_work *fib6_work) { int i; - for (i = 0; i < fib6_event->nrt6; i++) - mlxsw_sp_rt6_release(fib6_event->rt_arr[i]); - kfree(fib6_event->rt_arr); + for (i = 0; i < fib6_work->nrt6; i++) + mlxsw_sp_rt6_release(fib6_work->rt_arr[i]); + kfree(fib6_work->rt_arr); } -static void mlxsw_sp_router_fib4_event_process(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry_op_ctx *op_ctx, - struct mlxsw_sp_fib_event *fib_event) +static void mlxsw_sp_router_fib4_event_work(struct work_struct *work) { + struct mlxsw_sp_fib_event_work *fib_work = + container_of(work, struct mlxsw_sp_fib_event_work, work); + struct mlxsw_sp *mlxsw_sp = fib_work->mlxsw_sp; int err; + mutex_lock(&mlxsw_sp->router->lock); mlxsw_sp_span_respin(mlxsw_sp); - switch (fib_event->event) { + switch (fib_work->event) { case FIB_EVENT_ENTRY_REPLACE: - err = mlxsw_sp_router_fib4_replace(mlxsw_sp, op_ctx, &fib_event->fen_info); + err = mlxsw_sp_router_fib4_replace(mlxsw_sp, + &fib_work->fen_info); if (err) { - mlxsw_sp_fib_entry_op_ctx_priv_put_all(op_ctx); dev_warn(mlxsw_sp->bus_info->dev, "FIB replace failed.\n"); mlxsw_sp_fib4_offload_failed_flag_set(mlxsw_sp, - &fib_event->fen_info); + &fib_work->fen_info); } - fib_info_put(fib_event->fen_info.fi); + fib_info_put(fib_work->fen_info.fi); break; case FIB_EVENT_ENTRY_DEL: - err = mlxsw_sp_router_fib4_del(mlxsw_sp, op_ctx, &fib_event->fen_info); - if (err) - mlxsw_sp_fib_entry_op_ctx_priv_put_all(op_ctx); - fib_info_put(fib_event->fen_info.fi); + mlxsw_sp_router_fib4_del(mlxsw_sp, &fib_work->fen_info); + fib_info_put(fib_work->fen_info.fi); break; case FIB_EVENT_NH_ADD: case FIB_EVENT_NH_DEL: - mlxsw_sp_nexthop4_event(mlxsw_sp, fib_event->event, fib_event->fnh_info.fib_nh); - fib_info_put(fib_event->fnh_info.fib_nh->nh_parent); + mlxsw_sp_nexthop4_event(mlxsw_sp, fib_work->event, + fib_work->fnh_info.fib_nh); + fib_info_put(fib_work->fnh_info.fib_nh->nh_parent); break; } + mutex_unlock(&mlxsw_sp->router->lock); + kfree(fib_work); } -static void mlxsw_sp_router_fib6_event_process(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry_op_ctx *op_ctx, - struct mlxsw_sp_fib_event *fib_event) +static void mlxsw_sp_router_fib6_event_work(struct work_struct *work) { - struct mlxsw_sp_fib6_event *fib6_event = &fib_event->fib6_event; + struct mlxsw_sp_fib_event_work *fib_work = + container_of(work, struct mlxsw_sp_fib_event_work, work); + struct mlxsw_sp_fib6_event_work *fib6_work = &fib_work->fib6_work; + struct mlxsw_sp *mlxsw_sp = fib_work->mlxsw_sp; int err; + mutex_lock(&mlxsw_sp->router->lock); mlxsw_sp_span_respin(mlxsw_sp); - switch (fib_event->event) { + switch (fib_work->event) { case FIB_EVENT_ENTRY_REPLACE: - err = mlxsw_sp_router_fib6_replace(mlxsw_sp, op_ctx, fib_event->fib6_event.rt_arr, - fib_event->fib6_event.nrt6); + err = mlxsw_sp_router_fib6_replace(mlxsw_sp, + fib6_work->rt_arr, + fib6_work->nrt6); if (err) { - mlxsw_sp_fib_entry_op_ctx_priv_put_all(op_ctx); dev_warn(mlxsw_sp->bus_info->dev, "FIB replace failed.\n"); mlxsw_sp_fib6_offload_failed_flag_set(mlxsw_sp, - fib6_event->rt_arr, - fib6_event->nrt6); + fib6_work->rt_arr, + fib6_work->nrt6); } - mlxsw_sp_router_fib6_event_fini(&fib_event->fib6_event); + mlxsw_sp_router_fib6_work_fini(fib6_work); break; case FIB_EVENT_ENTRY_APPEND: - err = mlxsw_sp_router_fib6_append(mlxsw_sp, op_ctx, fib_event->fib6_event.rt_arr, - fib_event->fib6_event.nrt6); + err = mlxsw_sp_router_fib6_append(mlxsw_sp, + fib6_work->rt_arr, + fib6_work->nrt6); if (err) { - mlxsw_sp_fib_entry_op_ctx_priv_put_all(op_ctx); dev_warn(mlxsw_sp->bus_info->dev, "FIB append failed.\n"); mlxsw_sp_fib6_offload_failed_flag_set(mlxsw_sp, - fib6_event->rt_arr, - fib6_event->nrt6); + fib6_work->rt_arr, + fib6_work->nrt6); } - mlxsw_sp_router_fib6_event_fini(&fib_event->fib6_event); + mlxsw_sp_router_fib6_work_fini(fib6_work); break; case FIB_EVENT_ENTRY_DEL: - err = mlxsw_sp_router_fib6_del(mlxsw_sp, op_ctx, fib_event->fib6_event.rt_arr, - fib_event->fib6_event.nrt6); - if (err) - mlxsw_sp_fib_entry_op_ctx_priv_put_all(op_ctx); - mlxsw_sp_router_fib6_event_fini(&fib_event->fib6_event); + mlxsw_sp_router_fib6_del(mlxsw_sp, + fib6_work->rt_arr, + fib6_work->nrt6); + mlxsw_sp_router_fib6_work_fini(fib6_work); break; } + mutex_unlock(&mlxsw_sp->router->lock); + kfree(fib_work); } -static void mlxsw_sp_router_fibmr_event_process(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_event *fib_event) +static void mlxsw_sp_router_fibmr_event_work(struct work_struct *work) { + struct mlxsw_sp_fib_event_work *fib_work = + container_of(work, struct mlxsw_sp_fib_event_work, work); + struct mlxsw_sp *mlxsw_sp = fib_work->mlxsw_sp; bool replace; int err; rtnl_lock(); mutex_lock(&mlxsw_sp->router->lock); - switch (fib_event->event) { + switch (fib_work->event) { case FIB_EVENT_ENTRY_REPLACE: case FIB_EVENT_ENTRY_ADD: - replace = fib_event->event == FIB_EVENT_ENTRY_REPLACE; + replace = fib_work->event == FIB_EVENT_ENTRY_REPLACE; - err = mlxsw_sp_router_fibmr_add(mlxsw_sp, &fib_event->men_info, replace); + err = mlxsw_sp_router_fibmr_add(mlxsw_sp, &fib_work->men_info, + replace); if (err) dev_warn(mlxsw_sp->bus_info->dev, "MR entry add failed.\n"); - mr_cache_put(fib_event->men_info.mfc); + mr_cache_put(fib_work->men_info.mfc); break; case FIB_EVENT_ENTRY_DEL: - mlxsw_sp_router_fibmr_del(mlxsw_sp, &fib_event->men_info); - mr_cache_put(fib_event->men_info.mfc); + mlxsw_sp_router_fibmr_del(mlxsw_sp, &fib_work->men_info); + mr_cache_put(fib_work->men_info.mfc); break; case FIB_EVENT_VIF_ADD: err = mlxsw_sp_router_fibmr_vif_add(mlxsw_sp, - &fib_event->ven_info); + &fib_work->ven_info); if (err) dev_warn(mlxsw_sp->bus_info->dev, "MR VIF add failed.\n"); - dev_put(fib_event->ven_info.dev); + dev_put(fib_work->ven_info.dev); break; case FIB_EVENT_VIF_DEL: - mlxsw_sp_router_fibmr_vif_del(mlxsw_sp, &fib_event->ven_info); - dev_put(fib_event->ven_info.dev); + mlxsw_sp_router_fibmr_vif_del(mlxsw_sp, + &fib_work->ven_info); + dev_put(fib_work->ven_info.dev); break; } mutex_unlock(&mlxsw_sp->router->lock); rtnl_unlock(); + kfree(fib_work); } -static void mlxsw_sp_router_fib_event_work(struct work_struct *work) -{ - struct mlxsw_sp_router *router = container_of(work, struct mlxsw_sp_router, fib_event_work); - struct mlxsw_sp_fib_entry_op_ctx *op_ctx = router->ll_op_ctx; - struct mlxsw_sp *mlxsw_sp = router->mlxsw_sp; - struct mlxsw_sp_fib_event *next_fib_event; - struct mlxsw_sp_fib_event *fib_event; - int last_family = AF_UNSPEC; - LIST_HEAD(fib_event_queue); - - spin_lock_bh(&router->fib_event_queue_lock); - list_splice_init(&router->fib_event_queue, &fib_event_queue); - spin_unlock_bh(&router->fib_event_queue_lock); - - /* Router lock is held here to make sure per-instance - * operation context is not used in between FIB4/6 events - * processing. - */ - mutex_lock(&router->lock); - mlxsw_sp_fib_entry_op_ctx_clear(op_ctx); - list_for_each_entry_safe(fib_event, next_fib_event, - &fib_event_queue, list) { - /* Check if the next entry in the queue exists and it is - * of the same type (family and event) as the currect one. - * In that case it is permitted to do the bulking - * of multiple FIB entries to a single register write. - */ - op_ctx->bulk_ok = !list_is_last(&fib_event->list, &fib_event_queue) && - fib_event->family == next_fib_event->family && - fib_event->event == next_fib_event->event; - op_ctx->event = fib_event->event; - - /* In case family of this and the previous entry are different, context - * reinitialization is going to be needed now, indicate that. - * Note that since last_family is initialized to AF_UNSPEC, this is always - * going to happen for the first entry processed in the work. - */ - if (fib_event->family != last_family) - op_ctx->initialized = false; - - switch (fib_event->family) { - case AF_INET: - mlxsw_sp_router_fib4_event_process(mlxsw_sp, op_ctx, - fib_event); - break; - case AF_INET6: - mlxsw_sp_router_fib6_event_process(mlxsw_sp, op_ctx, - fib_event); - break; - case RTNL_FAMILY_IP6MR: - case RTNL_FAMILY_IPMR: - /* Unlock here as inside FIBMR the lock is taken again - * under RTNL. The per-instance operation context - * is not used by FIBMR. - */ - mutex_unlock(&router->lock); - mlxsw_sp_router_fibmr_event_process(mlxsw_sp, - fib_event); - mutex_lock(&router->lock); - break; - default: - WARN_ON_ONCE(1); - } - last_family = fib_event->family; - kfree(fib_event); - cond_resched(); - } - WARN_ON_ONCE(!list_empty(&router->ll_op_ctx->fib_entry_priv_list)); - mutex_unlock(&router->lock); -} - -static void mlxsw_sp_router_fib4_event(struct mlxsw_sp_fib_event *fib_event, +static void mlxsw_sp_router_fib4_event(struct mlxsw_sp_fib_event_work *fib_work, struct fib_notifier_info *info) { struct fib_entry_notifier_info *fen_info; struct fib_nh_notifier_info *fnh_info; - switch (fib_event->event) { + switch (fib_work->event) { case FIB_EVENT_ENTRY_REPLACE: case FIB_EVENT_ENTRY_DEL: fen_info = container_of(info, struct fib_entry_notifier_info, info); - fib_event->fen_info = *fen_info; + fib_work->fen_info = *fen_info; /* Take reference on fib_info to prevent it from being - * freed while event is queued. Release it afterwards. + * freed while work is queued. Release it afterwards. */ - fib_info_hold(fib_event->fen_info.fi); + fib_info_hold(fib_work->fen_info.fi); break; case FIB_EVENT_NH_ADD: case FIB_EVENT_NH_DEL: fnh_info = container_of(info, struct fib_nh_notifier_info, info); - fib_event->fnh_info = *fnh_info; - fib_info_hold(fib_event->fnh_info.fib_nh->nh_parent); + fib_work->fnh_info = *fnh_info; + fib_info_hold(fib_work->fnh_info.fib_nh->nh_parent); break; } } -static int mlxsw_sp_router_fib6_event(struct mlxsw_sp_fib_event *fib_event, +static int mlxsw_sp_router_fib6_event(struct mlxsw_sp_fib_event_work *fib_work, struct fib_notifier_info *info) { struct fib6_entry_notifier_info *fen6_info; int err; - switch (fib_event->event) { + switch (fib_work->event) { case FIB_EVENT_ENTRY_REPLACE: case FIB_EVENT_ENTRY_APPEND: case FIB_EVENT_ENTRY_DEL: fen6_info = container_of(info, struct fib6_entry_notifier_info, info); - err = mlxsw_sp_router_fib6_event_init(&fib_event->fib6_event, - fen6_info); + err = mlxsw_sp_router_fib6_work_init(&fib_work->fib6_work, + fen6_info); if (err) return err; break; @@ -7861,20 +7546,20 @@ static int mlxsw_sp_router_fib6_event(struct mlxsw_sp_fib_event *fib_event, } static void -mlxsw_sp_router_fibmr_event(struct mlxsw_sp_fib_event *fib_event, +mlxsw_sp_router_fibmr_event(struct mlxsw_sp_fib_event_work *fib_work, struct fib_notifier_info *info) { - switch (fib_event->event) { + switch (fib_work->event) { case FIB_EVENT_ENTRY_REPLACE: case FIB_EVENT_ENTRY_ADD: case FIB_EVENT_ENTRY_DEL: - memcpy(&fib_event->men_info, info, sizeof(fib_event->men_info)); - mr_cache_hold(fib_event->men_info.mfc); + memcpy(&fib_work->men_info, info, sizeof(fib_work->men_info)); + mr_cache_hold(fib_work->men_info.mfc); break; case FIB_EVENT_VIF_ADD: case FIB_EVENT_VIF_DEL: - memcpy(&fib_event->ven_info, info, sizeof(fib_event->ven_info)); - dev_hold(fib_event->ven_info.dev); + memcpy(&fib_work->ven_info, info, sizeof(fib_work->ven_info)); + dev_hold(fib_work->ven_info.dev); break; } } @@ -7928,7 +7613,7 @@ static int mlxsw_sp_router_fib_rule_event(unsigned long event, static int mlxsw_sp_router_fib_event(struct notifier_block *nb, unsigned long event, void *ptr) { - struct mlxsw_sp_fib_event *fib_event; + struct mlxsw_sp_fib_event_work *fib_work; struct fib_notifier_info *info = ptr; struct mlxsw_sp_router *router; int err; @@ -7960,39 +7645,37 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb, break; } - fib_event = kzalloc(sizeof(*fib_event), GFP_ATOMIC); - if (!fib_event) + fib_work = kzalloc(sizeof(*fib_work), GFP_ATOMIC); + if (!fib_work) return NOTIFY_BAD; - fib_event->mlxsw_sp = router->mlxsw_sp; - fib_event->event = event; - fib_event->family = info->family; + fib_work->mlxsw_sp = router->mlxsw_sp; + fib_work->event = event; switch (info->family) { case AF_INET: - mlxsw_sp_router_fib4_event(fib_event, info); + INIT_WORK(&fib_work->work, mlxsw_sp_router_fib4_event_work); + mlxsw_sp_router_fib4_event(fib_work, info); break; case AF_INET6: - err = mlxsw_sp_router_fib6_event(fib_event, info); + INIT_WORK(&fib_work->work, mlxsw_sp_router_fib6_event_work); + err = mlxsw_sp_router_fib6_event(fib_work, info); if (err) goto err_fib_event; break; case RTNL_FAMILY_IP6MR: case RTNL_FAMILY_IPMR: - mlxsw_sp_router_fibmr_event(fib_event, info); + INIT_WORK(&fib_work->work, mlxsw_sp_router_fibmr_event_work); + mlxsw_sp_router_fibmr_event(fib_work, info); break; } - /* Enqueue the event and trigger the work */ - spin_lock_bh(&router->fib_event_queue_lock); - list_add_tail(&fib_event->list, &router->fib_event_queue); - spin_unlock_bh(&router->fib_event_queue_lock); - mlxsw_core_schedule_work(&router->fib_event_work); + mlxsw_core_schedule_work(&fib_work->work); return NOTIFY_DONE; err_fib_event: - kfree(fib_event); + kfree(fib_work); return NOTIFY_BAD; } @@ -10533,46 +10216,6 @@ static void __mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp) mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rgcr), rgcr_pl); } -static const struct mlxsw_sp_router_ll_ops mlxsw_sp_router_ll_basic_ops = { - .init = mlxsw_sp_router_ll_basic_init, - .ralta_write = mlxsw_sp_router_ll_basic_ralta_write, - .ralst_write = mlxsw_sp_router_ll_basic_ralst_write, - .raltb_write = mlxsw_sp_router_ll_basic_raltb_write, - .fib_entry_op_ctx_size = sizeof(struct mlxsw_sp_fib_entry_op_ctx_basic), - .fib_entry_pack = mlxsw_sp_router_ll_basic_fib_entry_pack, - .fib_entry_act_remote_pack = mlxsw_sp_router_ll_basic_fib_entry_act_remote_pack, - .fib_entry_act_local_pack = mlxsw_sp_router_ll_basic_fib_entry_act_local_pack, - .fib_entry_act_ip2me_pack = mlxsw_sp_router_ll_basic_fib_entry_act_ip2me_pack, - .fib_entry_act_ip2me_tun_pack = mlxsw_sp_router_ll_basic_fib_entry_act_ip2me_tun_pack, - .fib_entry_commit = mlxsw_sp_router_ll_basic_fib_entry_commit, - .fib_entry_is_committed = mlxsw_sp_router_ll_basic_fib_entry_is_committed, -}; - -static int mlxsw_sp_router_ll_op_ctx_init(struct mlxsw_sp_router *router) -{ - size_t max_size = 0; - int i; - - for (i = 0; i < MLXSW_SP_L3_PROTO_MAX; i++) { - size_t size = router->proto_ll_ops[i]->fib_entry_op_ctx_size; - - if (size > max_size) - max_size = size; - } - router->ll_op_ctx = kzalloc(sizeof(*router->ll_op_ctx) + max_size, - GFP_KERNEL); - if (!router->ll_op_ctx) - return -ENOMEM; - INIT_LIST_HEAD(&router->ll_op_ctx->fib_entry_priv_list); - return 0; -} - -static void mlxsw_sp_router_ll_op_ctx_fini(struct mlxsw_sp_router *router) -{ - WARN_ON(!list_empty(&router->ll_op_ctx->fib_entry_priv_list)); - kfree(router->ll_op_ctx); -} - static int mlxsw_sp_lb_rif_init(struct mlxsw_sp *mlxsw_sp) { u16 lb_rif_index; @@ -10646,23 +10289,9 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, if (err) goto err_router_ops_init; - err = mlxsw_sp_router_xm_init(mlxsw_sp); - if (err) - goto err_xm_init; - - router->proto_ll_ops[MLXSW_SP_L3_PROTO_IPV4] = mlxsw_sp_router_xm_ipv4_is_supported(mlxsw_sp) ? - &mlxsw_sp_router_ll_xm_ops : - &mlxsw_sp_router_ll_basic_ops; - router->proto_ll_ops[MLXSW_SP_L3_PROTO_IPV6] = &mlxsw_sp_router_ll_basic_ops; - - err = mlxsw_sp_router_ll_op_ctx_init(router); - if (err) - goto err_ll_op_ctx_init; - INIT_LIST_HEAD(&mlxsw_sp->router->nh_res_grp_list); INIT_DELAYED_WORK(&mlxsw_sp->router->nh_grp_activity_dw, mlxsw_sp_nh_grp_activity_work); - INIT_LIST_HEAD(&mlxsw_sp->router->nexthop_neighs_list); err = __mlxsw_sp_router_init(mlxsw_sp); if (err) @@ -10715,10 +10344,6 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, if (err) goto err_dscp_init; - INIT_WORK(&router->fib_event_work, mlxsw_sp_router_fib_event_work); - INIT_LIST_HEAD(&router->fib_event_queue); - spin_lock_init(&router->fib_event_queue_lock); - router->inetaddr_nb.notifier_call = mlxsw_sp_inetaddr_event; err = register_inetaddr_notifier(&router->inetaddr_nb); if (err) @@ -10773,7 +10398,6 @@ err_register_inet6addr_notifier: unregister_inetaddr_notifier(&router->inetaddr_nb); err_register_inetaddr_notifier: mlxsw_core_flush_owq(); - WARN_ON(!list_empty(&router->fib_event_queue)); err_dscp_init: err_mp_hash_init: mlxsw_sp_neigh_fini(mlxsw_sp); @@ -10797,10 +10421,6 @@ err_rifs_init: __mlxsw_sp_router_fini(mlxsw_sp); err_router_init: cancel_delayed_work_sync(&mlxsw_sp->router->nh_grp_activity_dw); - mlxsw_sp_router_ll_op_ctx_fini(router); -err_ll_op_ctx_init: - mlxsw_sp_router_xm_fini(mlxsw_sp); -err_xm_init: err_router_ops_init: mutex_destroy(&mlxsw_sp->router->lock); kfree(mlxsw_sp->router); @@ -10819,7 +10439,6 @@ void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp) unregister_inet6addr_notifier(&mlxsw_sp->router->inet6addr_nb); unregister_inetaddr_notifier(&mlxsw_sp->router->inetaddr_nb); mlxsw_core_flush_owq(); - WARN_ON(!list_empty(&mlxsw_sp->router->fib_event_queue)); mlxsw_sp_neigh_fini(mlxsw_sp); mlxsw_sp_lb_rif_fini(mlxsw_sp); mlxsw_sp_vrs_fini(mlxsw_sp); @@ -10831,8 +10450,6 @@ void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp) mlxsw_sp_rifs_fini(mlxsw_sp); __mlxsw_sp_router_fini(mlxsw_sp); cancel_delayed_work_sync(&mlxsw_sp->router->nh_grp_activity_dw); - mlxsw_sp_router_ll_op_ctx_fini(mlxsw_sp->router); - mlxsw_sp_router_xm_fini(mlxsw_sp); mutex_destroy(&mlxsw_sp->router->lock); kfree(mlxsw_sp->router); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h index 37411b74c3e6..f7510be1cf2d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h @@ -15,27 +15,6 @@ struct mlxsw_sp_router_nve_decap { u8 valid:1; }; -struct mlxsw_sp_fib_entry_op_ctx { - u8 bulk_ok:1, /* Indicate to the low-level op it is ok to bulk - * the actual entry with the one that is the next - * in queue. - */ - initialized:1; /* Bit that the low-level op sets in case - * the context priv is initialized. - */ - struct list_head fib_entry_priv_list; - unsigned long event; - unsigned long ll_priv[]; -}; - -static inline void -mlxsw_sp_fib_entry_op_ctx_clear(struct mlxsw_sp_fib_entry_op_ctx *op_ctx) -{ - WARN_ON_ONCE(!list_empty(&op_ctx->fib_entry_priv_list)); - memset(op_ctx, 0, sizeof(*op_ctx)); - INIT_LIST_HEAD(&op_ctx->fib_entry_priv_list); -} - struct mlxsw_sp_router { struct mlxsw_sp *mlxsw_sp; struct mlxsw_sp_rif **rifs; @@ -72,14 +51,8 @@ struct mlxsw_sp_router { const struct mlxsw_sp_ipip_ops **ipip_ops_arr; struct mlxsw_sp_router_nve_decap nve_decap_config; struct mutex lock; /* Protects shared router resources */ - struct work_struct fib_event_work; - struct list_head fib_event_queue; - spinlock_t fib_event_queue_lock; /* Protects fib event queue list */ - /* One set of ops for each protocol: IPv4 and IPv6 */ - const struct mlxsw_sp_router_ll_ops *proto_ll_ops[MLXSW_SP_L3_PROTO_MAX]; struct mlxsw_sp_fib_entry_op_ctx *ll_op_ctx; u16 lb_rif_index; - struct mlxsw_sp_router_xm *xm; const struct mlxsw_sp_adj_grp_size_range *adj_grp_size_ranges; size_t adj_grp_size_ranges_count; struct delayed_work nh_grp_activity_dw; @@ -89,48 +62,6 @@ struct mlxsw_sp_router { u32 adj_trap_index; }; -struct mlxsw_sp_fib_entry_priv { - refcount_t refcnt; - struct list_head list; /* Member in op_ctx->fib_entry_priv_list */ - unsigned long priv[]; -}; - -enum mlxsw_sp_fib_entry_op { - MLXSW_SP_FIB_ENTRY_OP_WRITE, - MLXSW_SP_FIB_ENTRY_OP_UPDATE, - MLXSW_SP_FIB_ENTRY_OP_DELETE, -}; - -/* Low-level router ops. Basically this is to handle the different - * register sets to work with ordinary and XM trees and FIB entries. - */ -struct mlxsw_sp_router_ll_ops { - int (*init)(struct mlxsw_sp *mlxsw_sp, u16 vr_id, - enum mlxsw_sp_l3proto proto); - int (*ralta_write)(struct mlxsw_sp *mlxsw_sp, char *xralta_pl); - int (*ralst_write)(struct mlxsw_sp *mlxsw_sp, char *xralst_pl); - int (*raltb_write)(struct mlxsw_sp *mlxsw_sp, char *xraltb_pl); - size_t fib_entry_op_ctx_size; - size_t fib_entry_priv_size; - void (*fib_entry_pack)(struct mlxsw_sp_fib_entry_op_ctx *op_ctx, - enum mlxsw_sp_l3proto proto, enum mlxsw_sp_fib_entry_op op, - u16 virtual_router, u8 prefix_len, unsigned char *addr, - struct mlxsw_sp_fib_entry_priv *priv); - void (*fib_entry_act_remote_pack)(struct mlxsw_sp_fib_entry_op_ctx *op_ctx, - enum mlxsw_reg_ralue_trap_action trap_action, - u16 trap_id, u32 adjacency_index, u16 ecmp_size); - void (*fib_entry_act_local_pack)(struct mlxsw_sp_fib_entry_op_ctx *op_ctx, - enum mlxsw_reg_ralue_trap_action trap_action, - u16 trap_id, u16 local_erif); - void (*fib_entry_act_ip2me_pack)(struct mlxsw_sp_fib_entry_op_ctx *op_ctx); - void (*fib_entry_act_ip2me_tun_pack)(struct mlxsw_sp_fib_entry_op_ctx *op_ctx, - u32 tunnel_ptr); - int (*fib_entry_commit)(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry_op_ctx *op_ctx, - bool *postponed_for_bulk); - bool (*fib_entry_is_committed)(struct mlxsw_sp_fib_entry_priv *priv); -}; - struct mlxsw_sp_rif_ipip_lb; struct mlxsw_sp_rif_ipip_lb_config { enum mlxsw_reg_ritr_loopback_ipip_type lb_ipipt; @@ -232,10 +163,4 @@ int mlxsw_sp_ipip_ecn_decap_init(struct mlxsw_sp *mlxsw_sp); struct net_device * mlxsw_sp_ipip_netdev_ul_dev_get(const struct net_device *ol_dev); -extern const struct mlxsw_sp_router_ll_ops mlxsw_sp_router_ll_xm_ops; - -int mlxsw_sp_router_xm_init(struct mlxsw_sp *mlxsw_sp); -void mlxsw_sp_router_xm_fini(struct mlxsw_sp *mlxsw_sp); -bool mlxsw_sp_router_xm_ipv4_is_supported(const struct mlxsw_sp *mlxsw_sp); - #endif /* _MLXSW_ROUTER_H_*/ diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router_xm.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router_xm.c deleted file mode 100644 index d213af723a2a..000000000000 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router_xm.c +++ /dev/null @@ -1,812 +0,0 @@ -// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 -/* Copyright (c) 2020 Mellanox Technologies. All rights reserved */ - -#include <linux/kernel.h> -#include <linux/types.h> -#include <linux/rhashtable.h> - -#include "spectrum.h" -#include "core.h" -#include "reg.h" -#include "spectrum_router.h" - -#define MLXSW_SP_ROUTER_XM_M_VAL 16 - -static const u8 mlxsw_sp_router_xm_m_val[] = { - [MLXSW_SP_L3_PROTO_IPV4] = MLXSW_SP_ROUTER_XM_M_VAL, - [MLXSW_SP_L3_PROTO_IPV6] = 0, /* Currently unused. */ -}; - -#define MLXSW_SP_ROUTER_XM_L_VAL_MAX 16 - -struct mlxsw_sp_router_xm { - bool ipv4_supported; - bool ipv6_supported; - unsigned int entries_size; - struct rhashtable ltable_ht; - struct rhashtable flush_ht; /* Stores items about to be flushed from cache */ - unsigned int flush_count; - bool flush_all_mode; -}; - -struct mlxsw_sp_router_xm_ltable_node { - struct rhash_head ht_node; /* Member of router_xm->ltable_ht */ - u16 mindex; - u8 current_lvalue; - refcount_t refcnt; - unsigned int lvalue_ref[MLXSW_SP_ROUTER_XM_L_VAL_MAX + 1]; -}; - -static const struct rhashtable_params mlxsw_sp_router_xm_ltable_ht_params = { - .key_offset = offsetof(struct mlxsw_sp_router_xm_ltable_node, mindex), - .head_offset = offsetof(struct mlxsw_sp_router_xm_ltable_node, ht_node), - .key_len = sizeof(u16), - .automatic_shrinking = true, -}; - -struct mlxsw_sp_router_xm_flush_info { - bool all; - enum mlxsw_sp_l3proto proto; - u16 virtual_router; - u8 prefix_len; - unsigned char addr[sizeof(struct in6_addr)]; -}; - -struct mlxsw_sp_router_xm_fib_entry { - bool committed; - struct mlxsw_sp_router_xm_ltable_node *ltable_node; /* Parent node */ - u16 mindex; /* Store for processing from commit op */ - u8 lvalue; - struct mlxsw_sp_router_xm_flush_info flush_info; -}; - -#define MLXSW_SP_ROUTE_LL_XM_ENTRIES_MAX \ - (MLXSW_REG_XMDR_TRANS_LEN / MLXSW_REG_XMDR_C_LT_ROUTE_V4_LEN) - -struct mlxsw_sp_fib_entry_op_ctx_xm { - bool initialized; - char xmdr_pl[MLXSW_REG_XMDR_LEN]; - unsigned int trans_offset; /* Offset of the current command within one - * transaction of XMDR register. - */ - unsigned int trans_item_len; /* The current command length. This is used - * to advance 'trans_offset' when the next - * command is appended. - */ - unsigned int entries_count; - struct mlxsw_sp_router_xm_fib_entry *entries[MLXSW_SP_ROUTE_LL_XM_ENTRIES_MAX]; -}; - -static int mlxsw_sp_router_ll_xm_init(struct mlxsw_sp *mlxsw_sp, u16 vr_id, - enum mlxsw_sp_l3proto proto) -{ - char rxlte_pl[MLXSW_REG_RXLTE_LEN]; - - mlxsw_reg_rxlte_pack(rxlte_pl, vr_id, - (enum mlxsw_reg_rxlte_protocol) proto, true); - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rxlte), rxlte_pl); -} - -static int mlxsw_sp_router_ll_xm_ralta_write(struct mlxsw_sp *mlxsw_sp, char *xralta_pl) -{ - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(xralta), xralta_pl); -} - -static int mlxsw_sp_router_ll_xm_ralst_write(struct mlxsw_sp *mlxsw_sp, char *xralst_pl) -{ - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(xralst), xralst_pl); -} - -static int mlxsw_sp_router_ll_xm_raltb_write(struct mlxsw_sp *mlxsw_sp, char *xraltb_pl) -{ - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(xraltb), xraltb_pl); -} - -static u16 mlxsw_sp_router_ll_xm_mindex_get4(const u32 addr) -{ - /* Currently the M-index is set to linear mode. That means it is defined - * as 16 MSB of IP address. - */ - return addr >> MLXSW_SP_ROUTER_XM_L_VAL_MAX; -} - -static u16 mlxsw_sp_router_ll_xm_mindex_get6(const unsigned char *addr) -{ - WARN_ON_ONCE(1); - return 0; /* currently unused */ -} - -static void mlxsw_sp_router_ll_xm_op_ctx_check_init(struct mlxsw_sp_fib_entry_op_ctx *op_ctx, - struct mlxsw_sp_fib_entry_op_ctx_xm *op_ctx_xm) -{ - if (op_ctx->initialized) - return; - op_ctx->initialized = true; - - mlxsw_reg_xmdr_pack(op_ctx_xm->xmdr_pl, true); - op_ctx_xm->trans_offset = 0; - op_ctx_xm->entries_count = 0; -} - -static void mlxsw_sp_router_ll_xm_fib_entry_pack(struct mlxsw_sp_fib_entry_op_ctx *op_ctx, - enum mlxsw_sp_l3proto proto, - enum mlxsw_sp_fib_entry_op op, - u16 virtual_router, u8 prefix_len, - unsigned char *addr, - struct mlxsw_sp_fib_entry_priv *priv) -{ - struct mlxsw_sp_fib_entry_op_ctx_xm *op_ctx_xm = (void *) op_ctx->ll_priv; - struct mlxsw_sp_router_xm_fib_entry *fib_entry = (void *) priv->priv; - struct mlxsw_sp_router_xm_flush_info *flush_info; - enum mlxsw_reg_xmdr_c_ltr_op xmdr_c_ltr_op; - unsigned int len; - - mlxsw_sp_router_ll_xm_op_ctx_check_init(op_ctx, op_ctx_xm); - - switch (op) { - case MLXSW_SP_FIB_ENTRY_OP_WRITE: - xmdr_c_ltr_op = MLXSW_REG_XMDR_C_LTR_OP_WRITE; - break; - case MLXSW_SP_FIB_ENTRY_OP_UPDATE: - xmdr_c_ltr_op = MLXSW_REG_XMDR_C_LTR_OP_UPDATE; - break; - case MLXSW_SP_FIB_ENTRY_OP_DELETE: - xmdr_c_ltr_op = MLXSW_REG_XMDR_C_LTR_OP_DELETE; - break; - default: - WARN_ON_ONCE(1); - return; - } - - switch (proto) { - case MLXSW_SP_L3_PROTO_IPV4: - len = mlxsw_reg_xmdr_c_ltr_pack4(op_ctx_xm->xmdr_pl, op_ctx_xm->trans_offset, - op_ctx_xm->entries_count, xmdr_c_ltr_op, - virtual_router, prefix_len, (u32 *) addr); - fib_entry->mindex = mlxsw_sp_router_ll_xm_mindex_get4(*((u32 *) addr)); - break; - case MLXSW_SP_L3_PROTO_IPV6: - len = mlxsw_reg_xmdr_c_ltr_pack6(op_ctx_xm->xmdr_pl, op_ctx_xm->trans_offset, - op_ctx_xm->entries_count, xmdr_c_ltr_op, - virtual_router, prefix_len, addr); - fib_entry->mindex = mlxsw_sp_router_ll_xm_mindex_get6(addr); - break; - default: - WARN_ON_ONCE(1); - return; - } - if (!op_ctx_xm->trans_offset) - op_ctx_xm->trans_item_len = len; - else - WARN_ON_ONCE(op_ctx_xm->trans_item_len != len); - - op_ctx_xm->entries[op_ctx_xm->entries_count] = fib_entry; - - fib_entry->lvalue = prefix_len > mlxsw_sp_router_xm_m_val[proto] ? - prefix_len - mlxsw_sp_router_xm_m_val[proto] : 0; - - flush_info = &fib_entry->flush_info; - flush_info->proto = proto; - flush_info->virtual_router = virtual_router; - flush_info->prefix_len = prefix_len; - if (addr) - memcpy(flush_info->addr, addr, sizeof(flush_info->addr)); - else - memset(flush_info->addr, 0, sizeof(flush_info->addr)); -} - -static void -mlxsw_sp_router_ll_xm_fib_entry_act_remote_pack(struct mlxsw_sp_fib_entry_op_ctx *op_ctx, - enum mlxsw_reg_ralue_trap_action trap_action, - u16 trap_id, u32 adjacency_index, u16 ecmp_size) -{ - struct mlxsw_sp_fib_entry_op_ctx_xm *op_ctx_xm = (void *) op_ctx->ll_priv; - - mlxsw_reg_xmdr_c_ltr_act_remote_pack(op_ctx_xm->xmdr_pl, op_ctx_xm->trans_offset, - trap_action, trap_id, adjacency_index, ecmp_size); -} - -static void -mlxsw_sp_router_ll_xm_fib_entry_act_local_pack(struct mlxsw_sp_fib_entry_op_ctx *op_ctx, - enum mlxsw_reg_ralue_trap_action trap_action, - u16 trap_id, u16 local_erif) -{ - struct mlxsw_sp_fib_entry_op_ctx_xm *op_ctx_xm = (void *) op_ctx->ll_priv; - - mlxsw_reg_xmdr_c_ltr_act_local_pack(op_ctx_xm->xmdr_pl, op_ctx_xm->trans_offset, - trap_action, trap_id, local_erif); -} - -static void -mlxsw_sp_router_ll_xm_fib_entry_act_ip2me_pack(struct mlxsw_sp_fib_entry_op_ctx *op_ctx) -{ - struct mlxsw_sp_fib_entry_op_ctx_xm *op_ctx_xm = (void *) op_ctx->ll_priv; - - mlxsw_reg_xmdr_c_ltr_act_ip2me_pack(op_ctx_xm->xmdr_pl, op_ctx_xm->trans_offset); -} - -static void -mlxsw_sp_router_ll_xm_fib_entry_act_ip2me_tun_pack(struct mlxsw_sp_fib_entry_op_ctx *op_ctx, - u32 tunnel_ptr) -{ - struct mlxsw_sp_fib_entry_op_ctx_xm *op_ctx_xm = (void *) op_ctx->ll_priv; - - mlxsw_reg_xmdr_c_ltr_act_ip2me_tun_pack(op_ctx_xm->xmdr_pl, op_ctx_xm->trans_offset, - tunnel_ptr); -} - -static struct mlxsw_sp_router_xm_ltable_node * -mlxsw_sp_router_xm_ltable_node_get(struct mlxsw_sp_router_xm *router_xm, u16 mindex) -{ - struct mlxsw_sp_router_xm_ltable_node *ltable_node; - int err; - - ltable_node = rhashtable_lookup_fast(&router_xm->ltable_ht, &mindex, - mlxsw_sp_router_xm_ltable_ht_params); - if (ltable_node) { - refcount_inc(<able_node->refcnt); - return ltable_node; - } - ltable_node = kzalloc(sizeof(*ltable_node), GFP_KERNEL); - if (!ltable_node) - return ERR_PTR(-ENOMEM); - ltable_node->mindex = mindex; - refcount_set(<able_node->refcnt, 1); - - err = rhashtable_insert_fast(&router_xm->ltable_ht, <able_node->ht_node, - mlxsw_sp_router_xm_ltable_ht_params); - if (err) - goto err_insert; - - return ltable_node; - -err_insert: - kfree(ltable_node); - return ERR_PTR(err); -} - -static void mlxsw_sp_router_xm_ltable_node_put(struct mlxsw_sp_router_xm *router_xm, - struct mlxsw_sp_router_xm_ltable_node *ltable_node) -{ - if (!refcount_dec_and_test(<able_node->refcnt)) - return; - rhashtable_remove_fast(&router_xm->ltable_ht, <able_node->ht_node, - mlxsw_sp_router_xm_ltable_ht_params); - kfree(ltable_node); -} - -static int mlxsw_sp_router_xm_ltable_lvalue_set(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_router_xm_ltable_node *ltable_node) -{ - char xrmt_pl[MLXSW_REG_XRMT_LEN]; - - mlxsw_reg_xrmt_pack(xrmt_pl, ltable_node->mindex, ltable_node->current_lvalue); - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(xrmt), xrmt_pl); -} - -struct mlxsw_sp_router_xm_flush_node { - struct rhash_head ht_node; /* Member of router_xm->flush_ht */ - struct list_head list; - struct mlxsw_sp_router_xm_flush_info flush_info; - struct delayed_work dw; - struct mlxsw_sp *mlxsw_sp; - unsigned long start_jiffies; - unsigned int reuses; /* By how many flush calls this was reused. */ - refcount_t refcnt; -}; - -static const struct rhashtable_params mlxsw_sp_router_xm_flush_ht_params = { - .key_offset = offsetof(struct mlxsw_sp_router_xm_flush_node, flush_info), - .head_offset = offsetof(struct mlxsw_sp_router_xm_flush_node, ht_node), - .key_len = sizeof(struct mlxsw_sp_router_xm_flush_info), - .automatic_shrinking = true, -}; - -static struct mlxsw_sp_router_xm_flush_node * -mlxsw_sp_router_xm_cache_flush_node_create(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_router_xm_flush_info *flush_info) -{ - struct mlxsw_sp_router_xm *router_xm = mlxsw_sp->router->xm; - struct mlxsw_sp_router_xm_flush_node *flush_node; - int err; - - flush_node = kzalloc(sizeof(*flush_node), GFP_KERNEL); - if (!flush_node) - return ERR_PTR(-ENOMEM); - - flush_node->flush_info = *flush_info; - err = rhashtable_insert_fast(&router_xm->flush_ht, &flush_node->ht_node, - mlxsw_sp_router_xm_flush_ht_params); - if (err) { - kfree(flush_node); - return ERR_PTR(err); - } - router_xm->flush_count++; - flush_node->mlxsw_sp = mlxsw_sp; - flush_node->start_jiffies = jiffies; - refcount_set(&flush_node->refcnt, 1); - return flush_node; -} - -static void -mlxsw_sp_router_xm_cache_flush_node_hold(struct mlxsw_sp_router_xm_flush_node *flush_node) -{ - if (!flush_node) - return; - refcount_inc(&flush_node->refcnt); -} - -static void -mlxsw_sp_router_xm_cache_flush_node_put(struct mlxsw_sp_router_xm_flush_node *flush_node) -{ - if (!flush_node || !refcount_dec_and_test(&flush_node->refcnt)) - return; - kfree(flush_node); -} - -static void -mlxsw_sp_router_xm_cache_flush_node_destroy(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_router_xm_flush_node *flush_node) -{ - struct mlxsw_sp_router_xm *router_xm = mlxsw_sp->router->xm; - - router_xm->flush_count--; - rhashtable_remove_fast(&router_xm->flush_ht, &flush_node->ht_node, - mlxsw_sp_router_xm_flush_ht_params); - mlxsw_sp_router_xm_cache_flush_node_put(flush_node); -} - -static u32 mlxsw_sp_router_xm_flush_mask4(u8 prefix_len) -{ - return GENMASK(31, 32 - prefix_len); -} - -static unsigned char *mlxsw_sp_router_xm_flush_mask6(u8 prefix_len) -{ - static unsigned char mask[sizeof(struct in6_addr)]; - - memset(mask, 0, sizeof(mask)); - memset(mask, 0xff, prefix_len / 8); - mask[prefix_len / 8] = GENMASK(8, 8 - prefix_len % 8); - return mask; -} - -#define MLXSW_SP_ROUTER_XM_CACHE_PARALLEL_FLUSHES_LIMIT 15 -#define MLXSW_SP_ROUTER_XM_CACHE_FLUSH_ALL_MIN_REUSES 15 -#define MLXSW_SP_ROUTER_XM_CACHE_DELAY 50 /* usecs */ -#define MLXSW_SP_ROUTER_XM_CACHE_MAX_WAIT (MLXSW_SP_ROUTER_XM_CACHE_DELAY * 10) - -static void mlxsw_sp_router_xm_cache_flush_work(struct work_struct *work) -{ - struct mlxsw_sp_router_xm_flush_info *flush_info; - struct mlxsw_sp_router_xm_flush_node *flush_node; - char rlcmld_pl[MLXSW_REG_RLCMLD_LEN]; - enum mlxsw_reg_rlcmld_select select; - struct mlxsw_sp *mlxsw_sp; - u32 addr4; - int err; - - flush_node = container_of(work, struct mlxsw_sp_router_xm_flush_node, - dw.work); - mlxsw_sp = flush_node->mlxsw_sp; - flush_info = &flush_node->flush_info; - - if (flush_info->all) { - char rlpmce_pl[MLXSW_REG_RLPMCE_LEN]; - - mlxsw_reg_rlpmce_pack(rlpmce_pl, true, false); - err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rlpmce), - rlpmce_pl); - if (err) - dev_err(mlxsw_sp->bus_info->dev, "Failed to flush XM cache\n"); - - if (flush_node->reuses < - MLXSW_SP_ROUTER_XM_CACHE_FLUSH_ALL_MIN_REUSES) - /* Leaving flush-all mode. */ - mlxsw_sp->router->xm->flush_all_mode = false; - goto out; - } - - select = MLXSW_REG_RLCMLD_SELECT_M_AND_ML_ENTRIES; - - switch (flush_info->proto) { - case MLXSW_SP_L3_PROTO_IPV4: - addr4 = *((u32 *) flush_info->addr); - addr4 &= mlxsw_sp_router_xm_flush_mask4(flush_info->prefix_len); - - /* In case the flush prefix length is bigger than M-value, - * it makes no sense to flush M entries. So just flush - * the ML entries. - */ - if (flush_info->prefix_len > MLXSW_SP_ROUTER_XM_M_VAL) - select = MLXSW_REG_RLCMLD_SELECT_ML_ENTRIES; - - mlxsw_reg_rlcmld_pack4(rlcmld_pl, select, - flush_info->virtual_router, addr4, - mlxsw_sp_router_xm_flush_mask4(flush_info->prefix_len)); - break; - case MLXSW_SP_L3_PROTO_IPV6: - mlxsw_reg_rlcmld_pack6(rlcmld_pl, select, - flush_info->virtual_router, flush_info->addr, - mlxsw_sp_router_xm_flush_mask6(flush_info->prefix_len)); - break; - default: - WARN_ON(true); - goto out; - } - err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rlcmld), rlcmld_pl); - if (err) - dev_err(mlxsw_sp->bus_info->dev, "Failed to flush XM cache\n"); - -out: - mlxsw_sp_router_xm_cache_flush_node_destroy(mlxsw_sp, flush_node); -} - -static bool -mlxsw_sp_router_xm_cache_flush_may_cancel(struct mlxsw_sp_router_xm_flush_node *flush_node) -{ - unsigned long max_wait = usecs_to_jiffies(MLXSW_SP_ROUTER_XM_CACHE_MAX_WAIT); - unsigned long delay = usecs_to_jiffies(MLXSW_SP_ROUTER_XM_CACHE_DELAY); - - /* In case there is the same flushing work pending, check - * if we can consolidate with it. We can do it up to MAX_WAIT. - * Cancel the delayed work. If the work was still pending. - */ - if (time_is_before_jiffies(flush_node->start_jiffies + max_wait - delay) && - cancel_delayed_work_sync(&flush_node->dw)) - return true; - return false; -} - -static int -mlxsw_sp_router_xm_cache_flush_schedule(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_router_xm_flush_info *flush_info) -{ - unsigned long delay = usecs_to_jiffies(MLXSW_SP_ROUTER_XM_CACHE_DELAY); - struct mlxsw_sp_router_xm_flush_info flush_all_info = {.all = true}; - struct mlxsw_sp_router_xm *router_xm = mlxsw_sp->router->xm; - struct mlxsw_sp_router_xm_flush_node *flush_node; - - /* Check if the queued number of flushes reached critical amount after - * which it is better to just flush the whole cache. - */ - if (router_xm->flush_count == MLXSW_SP_ROUTER_XM_CACHE_PARALLEL_FLUSHES_LIMIT) - /* Entering flush-all mode. */ - router_xm->flush_all_mode = true; - - if (router_xm->flush_all_mode) - flush_info = &flush_all_info; - - rcu_read_lock(); - flush_node = rhashtable_lookup_fast(&router_xm->flush_ht, flush_info, - mlxsw_sp_router_xm_flush_ht_params); - /* Take a reference so the object is not freed before possible - * delayed work cancel could be done. - */ - mlxsw_sp_router_xm_cache_flush_node_hold(flush_node); - rcu_read_unlock(); - - if (flush_node && mlxsw_sp_router_xm_cache_flush_may_cancel(flush_node)) { - flush_node->reuses++; - mlxsw_sp_router_xm_cache_flush_node_put(flush_node); - /* Original work was within wait period and was canceled. - * That means that the reference is still held and the - * flush_node_put() call above did not free the flush_node. - * Reschedule it with fresh delay. - */ - goto schedule_work; - } else { - mlxsw_sp_router_xm_cache_flush_node_put(flush_node); - } - - flush_node = mlxsw_sp_router_xm_cache_flush_node_create(mlxsw_sp, flush_info); - if (IS_ERR(flush_node)) - return PTR_ERR(flush_node); - INIT_DELAYED_WORK(&flush_node->dw, mlxsw_sp_router_xm_cache_flush_work); - -schedule_work: - mlxsw_core_schedule_dw(&flush_node->dw, delay); - return 0; -} - -static int -mlxsw_sp_router_xm_ml_entry_add(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_router_xm_fib_entry *fib_entry) -{ - struct mlxsw_sp_router_xm *router_xm = mlxsw_sp->router->xm; - struct mlxsw_sp_router_xm_ltable_node *ltable_node; - u8 lvalue = fib_entry->lvalue; - int err; - - ltable_node = mlxsw_sp_router_xm_ltable_node_get(router_xm, - fib_entry->mindex); - if (IS_ERR(ltable_node)) - return PTR_ERR(ltable_node); - if (lvalue > ltable_node->current_lvalue) { - /* The L-value is bigger then the one currently set, update. */ - ltable_node->current_lvalue = lvalue; - err = mlxsw_sp_router_xm_ltable_lvalue_set(mlxsw_sp, - ltable_node); - if (err) - goto err_lvalue_set; - - /* The L value for prefix/M is increased. - * Therefore, all entries in M and ML caches matching - * {prefix/M, proto, VR} need to be flushed. Set the flush - * prefix length to M to achieve that. - */ - fib_entry->flush_info.prefix_len = MLXSW_SP_ROUTER_XM_M_VAL; - } - - ltable_node->lvalue_ref[lvalue]++; - fib_entry->ltable_node = ltable_node; - - return 0; - -err_lvalue_set: - mlxsw_sp_router_xm_ltable_node_put(router_xm, ltable_node); - return err; -} - -static void -mlxsw_sp_router_xm_ml_entry_del(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_router_xm_fib_entry *fib_entry) -{ - struct mlxsw_sp_router_xm_ltable_node *ltable_node = - fib_entry->ltable_node; - struct mlxsw_sp_router_xm *router_xm = mlxsw_sp->router->xm; - u8 lvalue = fib_entry->lvalue; - - ltable_node->lvalue_ref[lvalue]--; - if (lvalue == ltable_node->current_lvalue && lvalue && - !ltable_node->lvalue_ref[lvalue]) { - u8 new_lvalue = lvalue - 1; - - /* Find the biggest L-value left out there. */ - while (new_lvalue > 0 && !ltable_node->lvalue_ref[lvalue]) - new_lvalue--; - - ltable_node->current_lvalue = new_lvalue; - mlxsw_sp_router_xm_ltable_lvalue_set(mlxsw_sp, ltable_node); - - /* The L value for prefix/M is decreased. - * Therefore, all entries in M and ML caches matching - * {prefix/M, proto, VR} need to be flushed. Set the flush - * prefix length to M to achieve that. - */ - fib_entry->flush_info.prefix_len = MLXSW_SP_ROUTER_XM_M_VAL; - } - mlxsw_sp_router_xm_ltable_node_put(router_xm, ltable_node); -} - -static int -mlxsw_sp_router_xm_ml_entries_add(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry_op_ctx_xm *op_ctx_xm) -{ - struct mlxsw_sp_router_xm_fib_entry *fib_entry; - int err; - int i; - - for (i = 0; i < op_ctx_xm->entries_count; i++) { - fib_entry = op_ctx_xm->entries[i]; - err = mlxsw_sp_router_xm_ml_entry_add(mlxsw_sp, fib_entry); - if (err) - goto rollback; - } - return 0; - -rollback: - for (i--; i >= 0; i--) { - fib_entry = op_ctx_xm->entries[i]; - mlxsw_sp_router_xm_ml_entry_del(mlxsw_sp, fib_entry); - } - return err; -} - -static void -mlxsw_sp_router_xm_ml_entries_del(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry_op_ctx_xm *op_ctx_xm) -{ - struct mlxsw_sp_router_xm_fib_entry *fib_entry; - int i; - - for (i = 0; i < op_ctx_xm->entries_count; i++) { - fib_entry = op_ctx_xm->entries[i]; - mlxsw_sp_router_xm_ml_entry_del(mlxsw_sp, fib_entry); - } -} - -static void -mlxsw_sp_router_xm_ml_entries_cache_flush(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry_op_ctx_xm *op_ctx_xm) -{ - struct mlxsw_sp_router_xm_fib_entry *fib_entry; - int err; - int i; - - for (i = 0; i < op_ctx_xm->entries_count; i++) { - fib_entry = op_ctx_xm->entries[i]; - err = mlxsw_sp_router_xm_cache_flush_schedule(mlxsw_sp, - &fib_entry->flush_info); - if (err) - dev_err(mlxsw_sp->bus_info->dev, "Failed to flush XM cache\n"); - } -} - -static int mlxsw_sp_router_ll_xm_fib_entry_commit(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry_op_ctx *op_ctx, - bool *postponed_for_bulk) -{ - struct mlxsw_sp_fib_entry_op_ctx_xm *op_ctx_xm = (void *) op_ctx->ll_priv; - struct mlxsw_sp_router_xm_fib_entry *fib_entry; - u8 num_rec; - int err; - int i; - - op_ctx_xm->trans_offset += op_ctx_xm->trans_item_len; - op_ctx_xm->entries_count++; - - /* Check if bulking is possible and there is still room for another - * FIB entry record. The size of 'trans_item_len' is either size of IPv4 - * command or size of IPv6 command. Not possible to mix those in a - * single XMDR write. - */ - if (op_ctx->bulk_ok && - op_ctx_xm->trans_offset + op_ctx_xm->trans_item_len <= MLXSW_REG_XMDR_TRANS_LEN) { - if (postponed_for_bulk) - *postponed_for_bulk = true; - return 0; - } - - if (op_ctx->event == FIB_EVENT_ENTRY_REPLACE) { - /* The L-table is updated inside. It has to be done before - * the prefix is inserted. - */ - err = mlxsw_sp_router_xm_ml_entries_add(mlxsw_sp, op_ctx_xm); - if (err) - goto out; - } - - err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(xmdr), op_ctx_xm->xmdr_pl); - if (err) - goto out; - num_rec = mlxsw_reg_xmdr_num_rec_get(op_ctx_xm->xmdr_pl); - if (num_rec > op_ctx_xm->entries_count) { - dev_err(mlxsw_sp->bus_info->dev, "Invalid XMDR number of records\n"); - err = -EIO; - goto out; - } - for (i = 0; i < num_rec; i++) { - if (!mlxsw_reg_xmdr_reply_vect_get(op_ctx_xm->xmdr_pl, i)) { - dev_err(mlxsw_sp->bus_info->dev, "Command send over XMDR failed\n"); - err = -EIO; - goto out; - } else { - fib_entry = op_ctx_xm->entries[i]; - fib_entry->committed = true; - } - } - - if (op_ctx->event == FIB_EVENT_ENTRY_DEL) - /* The L-table is updated inside. It has to be done after - * the prefix was removed. - */ - mlxsw_sp_router_xm_ml_entries_del(mlxsw_sp, op_ctx_xm); - - /* At the very end, do the XLT cache flushing to evict stale - * M and ML cache entries after prefixes were inserted/removed. - */ - mlxsw_sp_router_xm_ml_entries_cache_flush(mlxsw_sp, op_ctx_xm); - -out: - /* Next pack call is going to do reinitialization */ - op_ctx->initialized = false; - return err; -} - -static bool mlxsw_sp_router_ll_xm_fib_entry_is_committed(struct mlxsw_sp_fib_entry_priv *priv) -{ - struct mlxsw_sp_router_xm_fib_entry *fib_entry = (void *) priv->priv; - - return fib_entry->committed; -} - -const struct mlxsw_sp_router_ll_ops mlxsw_sp_router_ll_xm_ops = { - .init = mlxsw_sp_router_ll_xm_init, - .ralta_write = mlxsw_sp_router_ll_xm_ralta_write, - .ralst_write = mlxsw_sp_router_ll_xm_ralst_write, - .raltb_write = mlxsw_sp_router_ll_xm_raltb_write, - .fib_entry_op_ctx_size = sizeof(struct mlxsw_sp_fib_entry_op_ctx_xm), - .fib_entry_priv_size = sizeof(struct mlxsw_sp_router_xm_fib_entry), - .fib_entry_pack = mlxsw_sp_router_ll_xm_fib_entry_pack, - .fib_entry_act_remote_pack = mlxsw_sp_router_ll_xm_fib_entry_act_remote_pack, - .fib_entry_act_local_pack = mlxsw_sp_router_ll_xm_fib_entry_act_local_pack, - .fib_entry_act_ip2me_pack = mlxsw_sp_router_ll_xm_fib_entry_act_ip2me_pack, - .fib_entry_act_ip2me_tun_pack = mlxsw_sp_router_ll_xm_fib_entry_act_ip2me_tun_pack, - .fib_entry_commit = mlxsw_sp_router_ll_xm_fib_entry_commit, - .fib_entry_is_committed = mlxsw_sp_router_ll_xm_fib_entry_is_committed, -}; - -#define MLXSW_SP_ROUTER_XM_MINDEX_SIZE (64 * 1024) - -int mlxsw_sp_router_xm_init(struct mlxsw_sp *mlxsw_sp) -{ - struct mlxsw_sp_router_xm *router_xm; - char rxltm_pl[MLXSW_REG_RXLTM_LEN]; - char xltq_pl[MLXSW_REG_XLTQ_LEN]; - u32 mindex_size; - u16 device_id; - int err; - - if (!mlxsw_sp->bus_info->xm_exists) - return 0; - - router_xm = kzalloc(sizeof(*router_xm), GFP_KERNEL); - if (!router_xm) - return -ENOMEM; - - mlxsw_reg_xltq_pack(xltq_pl); - err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(xltq), xltq_pl); - if (err) - goto err_xltq_query; - mlxsw_reg_xltq_unpack(xltq_pl, &device_id, &router_xm->ipv4_supported, - &router_xm->ipv6_supported, &router_xm->entries_size, &mindex_size); - - if (device_id != MLXSW_REG_XLTQ_XM_DEVICE_ID_XLT) { - dev_err(mlxsw_sp->bus_info->dev, "Invalid XM device id\n"); - err = -EINVAL; - goto err_device_id_check; - } - - if (mindex_size != MLXSW_SP_ROUTER_XM_MINDEX_SIZE) { - dev_err(mlxsw_sp->bus_info->dev, "Unexpected M-index size\n"); - err = -EINVAL; - goto err_mindex_size_check; - } - - mlxsw_reg_rxltm_pack(rxltm_pl, mlxsw_sp_router_xm_m_val[MLXSW_SP_L3_PROTO_IPV4], - mlxsw_sp_router_xm_m_val[MLXSW_SP_L3_PROTO_IPV6]); - err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rxltm), rxltm_pl); - if (err) - goto err_rxltm_write; - - err = rhashtable_init(&router_xm->ltable_ht, &mlxsw_sp_router_xm_ltable_ht_params); - if (err) - goto err_ltable_ht_init; - - err = rhashtable_init(&router_xm->flush_ht, &mlxsw_sp_router_xm_flush_ht_params); - if (err) - goto err_flush_ht_init; - - mlxsw_sp->router->xm = router_xm; - return 0; - -err_flush_ht_init: - rhashtable_destroy(&router_xm->ltable_ht); -err_ltable_ht_init: -err_rxltm_write: -err_mindex_size_check: -err_device_id_check: -err_xltq_query: - kfree(router_xm); - return err; -} - -void mlxsw_sp_router_xm_fini(struct mlxsw_sp *mlxsw_sp) -{ - struct mlxsw_sp_router_xm *router_xm = mlxsw_sp->router->xm; - - if (!mlxsw_sp->bus_info->xm_exists) - return; - - rhashtable_destroy(&router_xm->flush_ht); - rhashtable_destroy(&router_xm->ltable_ht); - kfree(router_xm); -} - -bool mlxsw_sp_router_xm_ipv4_is_supported(const struct mlxsw_sp *mlxsw_sp) -{ - struct mlxsw_sp_router_xm *router_xm = mlxsw_sp->router->xm; - - return router_xm && router_xm->ipv4_supported; -} diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_switchdev.c b/drivers/net/ethernet/microchip/sparx5/sparx5_switchdev.c index 3429660cd2e5..40ef9fad3a77 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_switchdev.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_switchdev.c @@ -394,12 +394,10 @@ static int sparx5_handle_port_mdb_add(struct net_device *dev, struct sparx5 *spx5 = port->sparx5; u16 pgid_idx, vid; u32 mact_entry; + bool is_host; int res, err; - if (netif_is_bridge_master(v->obj.orig_dev)) { - sparx5_mact_learn(spx5, PGID_CPU, v->addr, v->vid); - return 0; - } + is_host = netif_is_bridge_master(v->obj.orig_dev); /* When VLAN unaware the vlan value is not parsed and we receive vid 0. * Fall back to bridge vid 1. @@ -416,17 +414,33 @@ static int sparx5_handle_port_mdb_add(struct net_device *dev, /* MC_IDX starts after the port masks in the PGID table */ pgid_idx += SPX5_PORTS; - sparx5_pgid_update_mask(port, pgid_idx, true); + + if (is_host) + spx5_rmw(ANA_AC_PGID_MISC_CFG_PGID_CPU_COPY_ENA_SET(1), + ANA_AC_PGID_MISC_CFG_PGID_CPU_COPY_ENA, spx5, + ANA_AC_PGID_MISC_CFG(pgid_idx)); + else + sparx5_pgid_update_mask(port, pgid_idx, true); + } else { err = sparx5_pgid_alloc_mcast(spx5, &pgid_idx); if (err) { netdev_warn(dev, "multicast pgid table full\n"); return err; } - sparx5_pgid_update_mask(port, pgid_idx, true); + + if (is_host) + spx5_rmw(ANA_AC_PGID_MISC_CFG_PGID_CPU_COPY_ENA_SET(1), + ANA_AC_PGID_MISC_CFG_PGID_CPU_COPY_ENA, spx5, + ANA_AC_PGID_MISC_CFG(pgid_idx)); + else + sparx5_pgid_update_mask(port, pgid_idx, true); + err = sparx5_mact_learn(spx5, pgid_idx, v->addr, vid); + if (err) { netdev_warn(dev, "could not learn mac address %pM\n", v->addr); + sparx5_pgid_free(spx5, pgid_idx); sparx5_pgid_update_mask(port, pgid_idx, false); return err; } @@ -463,13 +477,8 @@ static int sparx5_handle_port_mdb_del(struct net_device *dev, struct sparx5_port *port = netdev_priv(dev); struct sparx5 *spx5 = port->sparx5; u16 pgid_idx, vid; - u32 mact_entry, res, pgid_entry[3]; - int err; - - if (netif_is_bridge_master(v->obj.orig_dev)) { - sparx5_mact_forget(spx5, v->addr, v->vid); - return 0; - } + u32 mact_entry, res, pgid_entry[3], misc_cfg; + bool host_ena; if (!br_vlan_enabled(spx5->hw_bridge_dev)) vid = 1; @@ -483,15 +492,21 @@ static int sparx5_handle_port_mdb_del(struct net_device *dev, /* MC_IDX starts after the port masks in the PGID table */ pgid_idx += SPX5_PORTS; - sparx5_pgid_update_mask(port, pgid_idx, false); + + if (netif_is_bridge_master(v->obj.orig_dev)) + spx5_rmw(ANA_AC_PGID_MISC_CFG_PGID_CPU_COPY_ENA_SET(0), + ANA_AC_PGID_MISC_CFG_PGID_CPU_COPY_ENA, spx5, + ANA_AC_PGID_MISC_CFG(pgid_idx)); + else + sparx5_pgid_update_mask(port, pgid_idx, false); + + misc_cfg = spx5_rd(spx5, ANA_AC_PGID_MISC_CFG(pgid_idx)); + host_ena = ANA_AC_PGID_MISC_CFG_PGID_CPU_COPY_ENA_GET(misc_cfg); sparx5_pgid_read_mask(spx5, pgid_idx, pgid_entry); - if (bitmap_empty((unsigned long *)pgid_entry, SPX5_PORTS)) { - /* No ports are in MC group. Remove entry */ - err = sparx5_mdb_del_entry(dev, spx5, v->addr, vid, pgid_idx); - if (err) - return err; - } + if (bitmap_empty((unsigned long *)pgid_entry, SPX5_PORTS) && !host_ena) + /* No ports or CPU are in MC group. Remove entry */ + return sparx5_mdb_del_entry(dev, spx5, v->addr, vid, pgid_idx); } return 0; diff --git a/drivers/net/ethernet/microsoft/mana/gdma.h b/drivers/net/ethernet/microsoft/mana/gdma.h index 41ecd156e95f..4a6efe6ada08 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma.h +++ b/drivers/net/ethernet/microsoft/mana/gdma.h @@ -348,6 +348,7 @@ struct gdma_context { struct completion eq_test_event; u32 test_event_eq_id; + bool is_pf; void __iomem *bar0_va; void __iomem *shm_base; void __iomem *db_page_base; @@ -469,6 +470,15 @@ struct gdma_eqe { #define GDMA_REG_DB_PAGE_SIZE 0x10 #define GDMA_REG_SHM_OFFSET 0x18 +#define GDMA_PF_REG_DB_PAGE_SIZE 0xD0 +#define GDMA_PF_REG_DB_PAGE_OFF 0xC8 +#define GDMA_PF_REG_SHM_OFF 0x70 + +#define GDMA_SRIOV_REG_CFG_BASE_OFF 0x108 + +#define MANA_PF_DEVICE_ID 0x00B9 +#define MANA_VF_DEVICE_ID 0x00BA + struct gdma_posted_wqe_info { u32 wqe_size_in_bu; }; diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index 49b85ca578b0..5f9240182351 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -18,7 +18,24 @@ static u64 mana_gd_r64(struct gdma_context *g, u64 offset) return readq(g->bar0_va + offset); } -static void mana_gd_init_registers(struct pci_dev *pdev) +static void mana_gd_init_pf_regs(struct pci_dev *pdev) +{ + struct gdma_context *gc = pci_get_drvdata(pdev); + void __iomem *sriov_base_va; + u64 sriov_base_off; + + gc->db_page_size = mana_gd_r32(gc, GDMA_PF_REG_DB_PAGE_SIZE) & 0xFFFF; + gc->db_page_base = gc->bar0_va + + mana_gd_r64(gc, GDMA_PF_REG_DB_PAGE_OFF); + + sriov_base_off = mana_gd_r64(gc, GDMA_SRIOV_REG_CFG_BASE_OFF); + + sriov_base_va = gc->bar0_va + sriov_base_off; + gc->shm_base = sriov_base_va + + mana_gd_r64(gc, sriov_base_off + GDMA_PF_REG_SHM_OFF); +} + +static void mana_gd_init_vf_regs(struct pci_dev *pdev) { struct gdma_context *gc = pci_get_drvdata(pdev); @@ -30,6 +47,16 @@ static void mana_gd_init_registers(struct pci_dev *pdev) gc->shm_base = gc->bar0_va + mana_gd_r64(gc, GDMA_REG_SHM_OFFSET); } +static void mana_gd_init_registers(struct pci_dev *pdev) +{ + struct gdma_context *gc = pci_get_drvdata(pdev); + + if (gc->is_pf) + mana_gd_init_pf_regs(pdev); + else + mana_gd_init_vf_regs(pdev); +} + static int mana_gd_query_max_resources(struct pci_dev *pdev) { struct gdma_context *gc = pci_get_drvdata(pdev); @@ -1304,6 +1331,11 @@ static void mana_gd_cleanup(struct pci_dev *pdev) mana_gd_remove_irqs(pdev); } +static bool mana_is_pf(unsigned short dev_id) +{ + return dev_id == MANA_PF_DEVICE_ID; +} + static int mana_gd_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { struct gdma_context *gc; @@ -1340,10 +1372,10 @@ static int mana_gd_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (!bar0_va) goto free_gc; + gc->is_pf = mana_is_pf(pdev->device); gc->bar0_va = bar0_va; gc->dev = &pdev->dev; - err = mana_gd_setup(pdev); if (err) goto unmap_bar; @@ -1438,7 +1470,8 @@ static void mana_gd_shutdown(struct pci_dev *pdev) #endif static const struct pci_device_id mana_id_table[] = { - { PCI_DEVICE(PCI_VENDOR_ID_MICROSOFT, 0x00BA) }, + { PCI_DEVICE(PCI_VENDOR_ID_MICROSOFT, MANA_PF_DEVICE_ID) }, + { PCI_DEVICE(PCI_VENDOR_ID_MICROSOFT, MANA_VF_DEVICE_ID) }, { } }; diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c index 078d6a5a0768..543a5d5c304f 100644 --- a/drivers/net/ethernet/microsoft/mana/hw_channel.c +++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c @@ -158,6 +158,14 @@ static void mana_hwc_init_event_handler(void *ctx, struct gdma_queue *q_self, hwc->rxq->msg_buf->gpa_mkey = val; hwc->txq->msg_buf->gpa_mkey = val; break; + + case HWC_INIT_DATA_PF_DEST_RQ_ID: + hwc->pf_dest_vrq_id = val; + break; + + case HWC_INIT_DATA_PF_DEST_CQ_ID: + hwc->pf_dest_vrcq_id = val; + break; } break; @@ -773,10 +781,13 @@ void mana_hwc_destroy_channel(struct gdma_context *gc) int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len, const void *req, u32 resp_len, void *resp) { + struct gdma_context *gc = hwc->gdma_dev->gdma_context; struct hwc_work_request *tx_wr; struct hwc_wq *txq = hwc->txq; struct gdma_req_hdr *req_msg; struct hwc_caller_ctx *ctx; + u32 dest_vrcq = 0; + u32 dest_vrq = 0; u16 msg_id; int err; @@ -803,7 +814,12 @@ int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len, tx_wr->msg_size = req_len; - err = mana_hwc_post_tx_wqe(txq, tx_wr, 0, 0, false); + if (gc->is_pf) { + dest_vrq = hwc->pf_dest_vrq_id; + dest_vrcq = hwc->pf_dest_vrcq_id; + } + + err = mana_hwc_post_tx_wqe(txq, tx_wr, dest_vrq, dest_vrcq, false); if (err) { dev_err(hwc->dev, "HWC: Failed to post send WQE: %d\n", err); goto out; diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.h b/drivers/net/ethernet/microsoft/mana/hw_channel.h index 31c6e83c454a..6a757a6e2732 100644 --- a/drivers/net/ethernet/microsoft/mana/hw_channel.h +++ b/drivers/net/ethernet/microsoft/mana/hw_channel.h @@ -20,6 +20,8 @@ #define HWC_INIT_DATA_MAX_NUM_CQS 7 #define HWC_INIT_DATA_PDID 8 #define HWC_INIT_DATA_GPA_MKEY 9 +#define HWC_INIT_DATA_PF_DEST_RQ_ID 10 +#define HWC_INIT_DATA_PF_DEST_CQ_ID 11 /* Structures labeled with "HW DATA" are exchanged with the hardware. All of * them are naturally aligned and hence don't need __packed. @@ -178,6 +180,9 @@ struct hw_channel_context { struct semaphore sema; struct gdma_resource inflight_msg_res; + u32 pf_dest_vrq_id; + u32 pf_dest_vrcq_id; + struct hwc_caller_ctx *caller_ctx; }; diff --git a/drivers/net/ethernet/microsoft/mana/mana.h b/drivers/net/ethernet/microsoft/mana/mana.h index d36405af9432..d58be64374c8 100644 --- a/drivers/net/ethernet/microsoft/mana/mana.h +++ b/drivers/net/ethernet/microsoft/mana/mana.h @@ -53,12 +53,14 @@ struct mana_stats_rx { u64 bytes; u64 xdp_drop; u64 xdp_tx; + u64 xdp_redirect; struct u64_stats_sync syncp; }; struct mana_stats_tx { u64 packets; u64 bytes; + u64 xdp_xmit; struct u64_stats_sync syncp; }; @@ -311,6 +313,8 @@ struct mana_rxq { struct bpf_prog __rcu *bpf_prog; struct xdp_rxq_info xdp_rxq; struct page *xdp_save_page; + bool xdp_flush; + int xdp_rc; /* XDP redirect return code */ /* MUST BE THE LAST MEMBER: * Each receive buffer has an associated mana_recv_buf_oob. @@ -374,6 +378,7 @@ struct mana_port_context { unsigned int num_queues; mana_handle_t port_handle; + mana_handle_t pf_filter_handle; u16 port_idx; @@ -395,6 +400,8 @@ int mana_probe(struct gdma_dev *gd, bool resuming); void mana_remove(struct gdma_dev *gd, bool suspending); void mana_xdp_tx(struct sk_buff *skb, struct net_device *ndev); +int mana_xdp_xmit(struct net_device *ndev, int n, struct xdp_frame **frames, + u32 flags); u32 mana_run_xdp(struct net_device *ndev, struct mana_rxq *rxq, struct xdp_buff *xdp, void *buf_va, uint pkt_len); struct bpf_prog *mana_xdp_get(struct mana_port_context *apc); @@ -420,6 +427,12 @@ enum mana_command_code { MANA_FENCE_RQ = 0x20006, MANA_CONFIG_VPORT_RX = 0x20007, MANA_QUERY_VPORT_CONFIG = 0x20008, + + /* Privileged commands for the PF mode */ + MANA_REGISTER_FILTER = 0x28000, + MANA_DEREGISTER_FILTER = 0x28001, + MANA_REGISTER_HW_PORT = 0x28003, + MANA_DEREGISTER_HW_PORT = 0x28004, }; /* Query Device Configuration */ @@ -547,6 +560,63 @@ struct mana_cfg_rx_steer_resp { struct gdma_resp_hdr hdr; }; /* HW DATA */ +/* Register HW vPort */ +struct mana_register_hw_vport_req { + struct gdma_req_hdr hdr; + u16 attached_gfid; + u8 is_pf_default_vport; + u8 reserved1; + u8 allow_all_ether_types; + u8 reserved2; + u8 reserved3; + u8 reserved4; +}; /* HW DATA */ + +struct mana_register_hw_vport_resp { + struct gdma_resp_hdr hdr; + mana_handle_t hw_vport_handle; +}; /* HW DATA */ + +/* Deregister HW vPort */ +struct mana_deregister_hw_vport_req { + struct gdma_req_hdr hdr; + mana_handle_t hw_vport_handle; +}; /* HW DATA */ + +struct mana_deregister_hw_vport_resp { + struct gdma_resp_hdr hdr; +}; /* HW DATA */ + +/* Register filter */ +struct mana_register_filter_req { + struct gdma_req_hdr hdr; + mana_handle_t vport; + u8 mac_addr[6]; + u8 reserved1; + u8 reserved2; + u8 reserved3; + u8 reserved4; + u16 reserved5; + u32 reserved6; + u32 reserved7; + u32 reserved8; +}; /* HW DATA */ + +struct mana_register_filter_resp { + struct gdma_resp_hdr hdr; + mana_handle_t filter_handle; +}; /* HW DATA */ + +/* Deregister filter */ +struct mana_deregister_filter_req { + struct gdma_req_hdr hdr; + mana_handle_t filter_handle; +}; /* HW DATA */ + +struct mana_deregister_filter_resp { + struct gdma_resp_hdr hdr; +}; /* HW DATA */ + #define MANA_MAX_NUM_QUEUES 64 #define MANA_SHORT_VPORT_OFFSET_MAX ((1U << 8) - 1) diff --git a/drivers/net/ethernet/microsoft/mana/mana_bpf.c b/drivers/net/ethernet/microsoft/mana/mana_bpf.c index 1d2f948b5c00..421fd39ff3a8 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_bpf.c +++ b/drivers/net/ethernet/microsoft/mana/mana_bpf.c @@ -32,9 +32,55 @@ void mana_xdp_tx(struct sk_buff *skb, struct net_device *ndev) ndev->stats.tx_dropped++; } +static int mana_xdp_xmit_fm(struct net_device *ndev, struct xdp_frame *frame, + u16 q_idx) +{ + struct sk_buff *skb; + + skb = xdp_build_skb_from_frame(frame, ndev); + if (unlikely(!skb)) + return -ENOMEM; + + skb_set_queue_mapping(skb, q_idx); + + mana_xdp_tx(skb, ndev); + + return 0; +} + +int mana_xdp_xmit(struct net_device *ndev, int n, struct xdp_frame **frames, + u32 flags) +{ + struct mana_port_context *apc = netdev_priv(ndev); + struct mana_stats_tx *tx_stats; + int i, count = 0; + u16 q_idx; + + if (unlikely(!apc->port_is_up)) + return 0; + + q_idx = smp_processor_id() % ndev->real_num_tx_queues; + + for (i = 0; i < n; i++) { + if (mana_xdp_xmit_fm(ndev, frames[i], q_idx)) + break; + + count++; + } + + tx_stats = &apc->tx_qp[q_idx].txq.stats; + + u64_stats_update_begin(&tx_stats->syncp); + tx_stats->xdp_xmit += count; + u64_stats_update_end(&tx_stats->syncp); + + return count; +} + u32 mana_run_xdp(struct net_device *ndev, struct mana_rxq *rxq, struct xdp_buff *xdp, void *buf_va, uint pkt_len) { + struct mana_stats_rx *rx_stats; struct bpf_prog *prog; u32 act = XDP_PASS; @@ -49,12 +95,30 @@ u32 mana_run_xdp(struct net_device *ndev, struct mana_rxq *rxq, act = bpf_prog_run_xdp(prog, xdp); + rx_stats = &rxq->stats; + switch (act) { case XDP_PASS: case XDP_TX: case XDP_DROP: break; + case XDP_REDIRECT: + rxq->xdp_rc = xdp_do_redirect(ndev, xdp, prog); + if (!rxq->xdp_rc) { + rxq->xdp_flush = true; + + u64_stats_update_begin(&rx_stats->syncp); + rx_stats->packets++; + rx_stats->bytes += pkt_len; + rx_stats->xdp_redirect++; + u64_stats_update_end(&rx_stats->syncp); + + break; + } + + fallthrough; + case XDP_ABORTED: trace_xdp_exception(ndev, prog, act); break; diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index b1d773823232..9259a74eca40 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -6,6 +6,7 @@ #include <linux/inetdevice.h> #include <linux/etherdevice.h> #include <linux/ethtool.h> +#include <linux/filter.h> #include <linux/mm.h> #include <net/checksum.h> @@ -382,6 +383,7 @@ static const struct net_device_ops mana_devops = { .ndo_validate_addr = eth_validate_addr, .ndo_get_stats64 = mana_get_stats64, .ndo_bpf = mana_bpf, + .ndo_xdp_xmit = mana_xdp_xmit, }; static void mana_cleanup_port_context(struct mana_port_context *apc) @@ -446,6 +448,119 @@ static int mana_verify_resp_hdr(const struct gdma_resp_hdr *resp_hdr, return 0; } +static int mana_pf_register_hw_vport(struct mana_port_context *apc) +{ + struct mana_register_hw_vport_resp resp = {}; + struct mana_register_hw_vport_req req = {}; + int err; + + mana_gd_init_req_hdr(&req.hdr, MANA_REGISTER_HW_PORT, + sizeof(req), sizeof(resp)); + req.attached_gfid = 1; + req.is_pf_default_vport = 1; + req.allow_all_ether_types = 1; + + err = mana_send_request(apc->ac, &req, sizeof(req), &resp, + sizeof(resp)); + if (err) { + netdev_err(apc->ndev, "Failed to register hw vPort: %d\n", err); + return err; + } + + err = mana_verify_resp_hdr(&resp.hdr, MANA_REGISTER_HW_PORT, + sizeof(resp)); + if (err || resp.hdr.status) { + netdev_err(apc->ndev, "Failed to register hw vPort: %d, 0x%x\n", + err, resp.hdr.status); + return err ? err : -EPROTO; + } + + apc->port_handle = resp.hw_vport_handle; + return 0; +} + +static void mana_pf_deregister_hw_vport(struct mana_port_context *apc) +{ + struct mana_deregister_hw_vport_resp resp = {}; + struct mana_deregister_hw_vport_req req = {}; + int err; + + mana_gd_init_req_hdr(&req.hdr, MANA_DEREGISTER_HW_PORT, + sizeof(req), sizeof(resp)); + req.hw_vport_handle = apc->port_handle; + + err = mana_send_request(apc->ac, &req, sizeof(req), &resp, + sizeof(resp)); + if (err) { + netdev_err(apc->ndev, "Failed to unregister hw vPort: %d\n", + err); + return; + } + + err = mana_verify_resp_hdr(&resp.hdr, MANA_DEREGISTER_HW_PORT, + sizeof(resp)); + if (err || resp.hdr.status) + netdev_err(apc->ndev, + "Failed to deregister hw vPort: %d, 0x%x\n", + err, resp.hdr.status); +} + +static int mana_pf_register_filter(struct mana_port_context *apc) +{ + struct mana_register_filter_resp resp = {}; + struct mana_register_filter_req req = {}; + int err; + + mana_gd_init_req_hdr(&req.hdr, MANA_REGISTER_FILTER, + sizeof(req), sizeof(resp)); + req.vport = apc->port_handle; + memcpy(req.mac_addr, apc->mac_addr, ETH_ALEN); + + err = mana_send_request(apc->ac, &req, sizeof(req), &resp, + sizeof(resp)); + if (err) { + netdev_err(apc->ndev, "Failed to register filter: %d\n", err); + return err; + } + + err = mana_verify_resp_hdr(&resp.hdr, MANA_REGISTER_FILTER, + sizeof(resp)); + if (err || resp.hdr.status) { + netdev_err(apc->ndev, "Failed to register filter: %d, 0x%x\n", + err, resp.hdr.status); + return err ? err : -EPROTO; + } + + apc->pf_filter_handle = resp.filter_handle; + return 0; +} + +static void mana_pf_deregister_filter(struct mana_port_context *apc) +{ + struct mana_deregister_filter_resp resp = {}; + struct mana_deregister_filter_req req = {}; + int err; + + mana_gd_init_req_hdr(&req.hdr, MANA_DEREGISTER_FILTER, + sizeof(req), sizeof(resp)); + req.filter_handle = apc->pf_filter_handle; + + err = mana_send_request(apc->ac, &req, sizeof(req), &resp, + sizeof(resp)); + if (err) { + netdev_err(apc->ndev, "Failed to unregister filter: %d\n", + err); + return; + } + + err = mana_verify_resp_hdr(&resp.hdr, MANA_DEREGISTER_FILTER, + sizeof(resp)); + if (err || resp.hdr.status) + netdev_err(apc->ndev, + "Failed to deregister filter: %d, 0x%x\n", + err, resp.hdr.status); +} + static int mana_query_device_cfg(struct mana_context *ac, u32 proto_major_ver, u32 proto_minor_ver, u32 proto_micro_ver, u16 *max_num_vports) @@ -1007,6 +1122,9 @@ static void mana_rx_skb(void *buf_va, struct mana_rxcomp_oob *cqe, act = mana_run_xdp(ndev, rxq, &xdp, buf_va, pkt_len); + if (act == XDP_REDIRECT && !rxq->xdp_rc) + return; + if (act != XDP_PASS && act != XDP_TX) goto drop_xdp; @@ -1162,11 +1280,14 @@ drop: static void mana_poll_rx_cq(struct mana_cq *cq) { struct gdma_comp *comp = cq->gdma_comp_buf; + struct mana_rxq *rxq = cq->rxq; int comp_read, i; comp_read = mana_gd_poll_cq(cq->gdma_cq, comp, CQE_POLLING_BUFFER); WARN_ON_ONCE(comp_read > CQE_POLLING_BUFFER); + rxq->xdp_flush = false; + for (i = 0; i < comp_read; i++) { if (WARN_ON_ONCE(comp[i].is_sq)) return; @@ -1175,8 +1296,11 @@ static void mana_poll_rx_cq(struct mana_cq *cq) if (WARN_ON_ONCE(comp[i].wq_num != cq->rxq->gdma_id)) return; - mana_process_rx_cqe(cq->rxq, cq, &comp[i]); + mana_process_rx_cqe(rxq, cq, &comp[i]); } + + if (rxq->xdp_flush) + xdp_do_flush(); } static void mana_cq_handler(void *context, struct gdma_queue *gdma_queue) @@ -1653,6 +1777,7 @@ out: static void mana_destroy_vport(struct mana_port_context *apc) { + struct gdma_dev *gd = apc->ac->gdma_dev; struct mana_rxq *rxq; u32 rxq_idx; @@ -1666,6 +1791,9 @@ static void mana_destroy_vport(struct mana_port_context *apc) } mana_destroy_txq(apc); + + if (gd->gdma_context->is_pf) + mana_pf_deregister_hw_vport(apc); } static int mana_create_vport(struct mana_port_context *apc, @@ -1676,6 +1804,12 @@ static int mana_create_vport(struct mana_port_context *apc, apc->default_rxobj = INVALID_MANA_HANDLE; + if (gd->gdma_context->is_pf) { + err = mana_pf_register_hw_vport(apc); + if (err) + return err; + } + err = mana_cfg_vport(apc, gd->pdid, gd->doorbell); if (err) return err; @@ -1755,6 +1889,7 @@ reset_apc: int mana_alloc_queues(struct net_device *ndev) { struct mana_port_context *apc = netdev_priv(ndev); + struct gdma_dev *gd = apc->ac->gdma_dev; int err; err = mana_create_vport(apc, ndev); @@ -1781,6 +1916,12 @@ int mana_alloc_queues(struct net_device *ndev) if (err) goto destroy_vport; + if (gd->gdma_context->is_pf) { + err = mana_pf_register_filter(apc); + if (err) + goto destroy_vport; + } + mana_chn_setxdp(apc, mana_xdp_get(apc)); return 0; @@ -1825,6 +1966,7 @@ int mana_attach(struct net_device *ndev) static int mana_dealloc_queues(struct net_device *ndev) { struct mana_port_context *apc = netdev_priv(ndev); + struct gdma_dev *gd = apc->ac->gdma_dev; struct mana_txq *txq; int i, err; @@ -1833,6 +1975,9 @@ static int mana_dealloc_queues(struct net_device *ndev) mana_chn_setxdp(apc, NULL); + if (gd->gdma_context->is_pf) + mana_pf_deregister_filter(apc); + /* No packet can be transmitted now since apc->port_is_up is false. * There is still a tiny chance that mana_poll_tx_cq() can re-enable * a txq because it may not timely see apc->port_is_up being cleared @@ -1915,6 +2060,7 @@ static int mana_probe_port(struct mana_context *ac, int port_idx, apc->max_queues = gc->max_num_queues; apc->num_queues = gc->max_num_queues; apc->port_handle = INVALID_MANA_HANDLE; + apc->pf_filter_handle = INVALID_MANA_HANDLE; apc->port_idx = port_idx; ndev->netdev_ops = &mana_devops; diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c index e13f2453eabb..c530db76880f 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c +++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c @@ -23,7 +23,7 @@ static int mana_get_sset_count(struct net_device *ndev, int stringset) if (stringset != ETH_SS_STATS) return -EINVAL; - return ARRAY_SIZE(mana_eth_stats) + num_queues * 6; + return ARRAY_SIZE(mana_eth_stats) + num_queues * 8; } static void mana_get_strings(struct net_device *ndev, u32 stringset, u8 *data) @@ -50,6 +50,8 @@ static void mana_get_strings(struct net_device *ndev, u32 stringset, u8 *data) p += ETH_GSTRING_LEN; sprintf(p, "rx_%d_xdp_tx", i); p += ETH_GSTRING_LEN; + sprintf(p, "rx_%d_xdp_redirect", i); + p += ETH_GSTRING_LEN; } for (i = 0; i < num_queues; i++) { @@ -57,6 +59,8 @@ static void mana_get_strings(struct net_device *ndev, u32 stringset, u8 *data) p += ETH_GSTRING_LEN; sprintf(p, "tx_%d_bytes", i); p += ETH_GSTRING_LEN; + sprintf(p, "tx_%d_xdp_xmit", i); + p += ETH_GSTRING_LEN; } } @@ -70,6 +74,8 @@ static void mana_get_ethtool_stats(struct net_device *ndev, struct mana_stats_tx *tx_stats; unsigned int start; u64 packets, bytes; + u64 xdp_redirect; + u64 xdp_xmit; u64 xdp_drop; u64 xdp_tx; int q, i = 0; @@ -89,12 +95,14 @@ static void mana_get_ethtool_stats(struct net_device *ndev, bytes = rx_stats->bytes; xdp_drop = rx_stats->xdp_drop; xdp_tx = rx_stats->xdp_tx; + xdp_redirect = rx_stats->xdp_redirect; } while (u64_stats_fetch_retry_irq(&rx_stats->syncp, start)); data[i++] = packets; data[i++] = bytes; data[i++] = xdp_drop; data[i++] = xdp_tx; + data[i++] = xdp_redirect; } for (q = 0; q < num_queues; q++) { @@ -104,10 +112,12 @@ static void mana_get_ethtool_stats(struct net_device *ndev, start = u64_stats_fetch_begin_irq(&tx_stats->syncp); packets = tx_stats->packets; bytes = tx_stats->bytes; + xdp_xmit = tx_stats->xdp_xmit; } while (u64_stats_fetch_retry_irq(&tx_stats->syncp, start)); data[i++] = packets; data[i++] = bytes; + data[i++] = xdp_xmit; } } diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c index 0147de405365..b456e81a73a4 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/action.c +++ b/drivers/net/ethernet/netronome/nfp/flower/action.c @@ -674,9 +674,9 @@ nfp_fl_set_ip6_hop_limit_flow_label(u32 off, __be32 exact, __be32 mask, fl_hl_mask->hop_limit; break; case round_down(offsetof(struct ipv6hdr, flow_lbl), 4): - if (mask & ~IPV6_FLOW_LABEL_MASK || - exact & ~IPV6_FLOW_LABEL_MASK) { - NL_SET_ERR_MSG_MOD(extack, "unsupported offload: invalid pedit IPv6 flow label action"); + if (mask & ~IPV6_FLOWINFO_MASK || + exact & ~IPV6_FLOWINFO_MASK) { + NL_SET_ERR_MSG_MOD(extack, "unsupported offload: invalid pedit IPv6 flow info action"); return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h index 68e8a2fb1a29..2df2af1da716 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h +++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h @@ -96,8 +96,6 @@ #define NFP_FL_PUSH_VLAN_PRIO GENMASK(15, 13) #define NFP_FL_PUSH_VLAN_VID GENMASK(11, 0) -#define IPV6_FLOW_LABEL_MASK cpu_to_be32(0x000fffff) - /* LAG ports */ #define NFP_FL_LAG_OUT 0xC0DE0000 diff --git a/drivers/net/ethernet/netronome/nfp/nfd3/dp.c b/drivers/net/ethernet/netronome/nfp/nfd3/dp.c index 7db56abaa582..f9410d59146d 100644 --- a/drivers/net/ethernet/netronome/nfp/nfd3/dp.c +++ b/drivers/net/ethernet/netronome/nfp/nfd3/dp.c @@ -282,7 +282,7 @@ netdev_tx_t nfp_nfd3_tx(struct sk_buff *skb, struct net_device *netdev) txd = &tx_ring->txds[wr_idx]; txd->offset_eop = (nr_frags ? 0 : NFD3_DESC_TX_EOP) | md_bytes; txd->dma_len = cpu_to_le16(skb_headlen(skb)); - nfp_desc_set_dma_addr(txd, dma_addr); + nfp_desc_set_dma_addr_40b(txd, dma_addr); txd->data_len = cpu_to_le16(skb->len); txd->flags = 0; @@ -320,7 +320,7 @@ netdev_tx_t nfp_nfd3_tx(struct sk_buff *skb, struct net_device *netdev) txd = &tx_ring->txds[wr_idx]; txd->dma_len = cpu_to_le16(fsize); - nfp_desc_set_dma_addr(txd, dma_addr); + nfp_desc_set_dma_addr_40b(txd, dma_addr); txd->offset_eop = md_bytes | ((f == nr_frags - 1) ? NFD3_DESC_TX_EOP : 0); txd->vals8[1] = second_half; @@ -562,8 +562,12 @@ nfp_nfd3_rx_give_one(const struct nfp_net_dp *dp, /* Fill freelist descriptor */ rx_ring->rxds[wr_idx].fld.reserved = 0; rx_ring->rxds[wr_idx].fld.meta_len_dd = 0; - nfp_desc_set_dma_addr(&rx_ring->rxds[wr_idx].fld, - dma_addr + dp->rx_dma_off); + /* DMA address is expanded to 48-bit width in freelist for NFP3800, + * so the *_48b macro is used accordingly, it's also OK to fill + * a 40-bit address since the top 8 bits are get set to 0. + */ + nfp_desc_set_dma_addr_48b(&rx_ring->rxds[wr_idx].fld, + dma_addr + dp->rx_dma_off); rx_ring->wr_p++; if (!(rx_ring->wr_p % NFP_NET_FL_BATCH)) { @@ -817,7 +821,7 @@ nfp_nfd3_tx_xdp_buf(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring, txd = &tx_ring->txds[wr_idx]; txd->offset_eop = NFD3_DESC_TX_EOP; txd->dma_len = cpu_to_le16(pkt_len); - nfp_desc_set_dma_addr(txd, rxbuf->dma_addr + dma_off); + nfp_desc_set_dma_addr_40b(txd, rxbuf->dma_addr + dma_off); txd->data_len = cpu_to_le16(pkt_len); txd->flags = 0; @@ -1193,7 +1197,7 @@ nfp_nfd3_ctrl_tx_one(struct nfp_net *nn, struct nfp_net_r_vector *r_vec, txd = &tx_ring->txds[wr_idx]; txd->offset_eop = meta_len | NFD3_DESC_TX_EOP; txd->dma_len = cpu_to_le16(skb_headlen(skb)); - nfp_desc_set_dma_addr(txd, dma_addr); + nfp_desc_set_dma_addr_40b(txd, dma_addr); txd->data_len = cpu_to_le16(skb->len); txd->flags = 0; diff --git a/drivers/net/ethernet/netronome/nfp/nfd3/rings.c b/drivers/net/ethernet/netronome/nfp/nfd3/rings.c index 47604d5e25eb..f31eabdc0631 100644 --- a/drivers/net/ethernet/netronome/nfp/nfd3/rings.c +++ b/drivers/net/ethernet/netronome/nfp/nfd3/rings.c @@ -260,6 +260,7 @@ const struct nfp_dp_ops nfp_nfd3_ops = { .version = NFP_NFD_VER_NFD3, .tx_min_desc_per_pkt = 1, .cap_mask = NFP_NFD3_CFG_CTRL_SUPPORTED, + .dma_mask = DMA_BIT_MASK(40), .poll = nfp_nfd3_poll, .xsk_poll = nfp_nfd3_xsk_poll, .ctrl_poll = nfp_nfd3_ctrl_poll, diff --git a/drivers/net/ethernet/netronome/nfp/nfd3/xsk.c b/drivers/net/ethernet/netronome/nfp/nfd3/xsk.c index c16c4b42ecfd..454fea4c8be2 100644 --- a/drivers/net/ethernet/netronome/nfp/nfd3/xsk.c +++ b/drivers/net/ethernet/netronome/nfp/nfd3/xsk.c @@ -40,7 +40,7 @@ nfp_nfd3_xsk_tx_xdp(const struct nfp_net_dp *dp, struct nfp_net_r_vector *r_vec, txd = &tx_ring->txds[wr_idx]; txd->offset_eop = NFD3_DESC_TX_EOP; txd->dma_len = cpu_to_le16(pkt_len); - nfp_desc_set_dma_addr(txd, xrxbuf->dma_addr + pkt_off); + nfp_desc_set_dma_addr_40b(txd, xrxbuf->dma_addr + pkt_off); txd->data_len = cpu_to_le16(pkt_len); txd->flags = 0; @@ -361,10 +361,8 @@ static void nfp_nfd3_xsk_tx(struct nfp_net_tx_ring *tx_ring) /* Build TX descriptor. */ txd = &tx_ring->txds[wr_idx]; - nfp_desc_set_dma_addr(txd, - xsk_buff_raw_get_dma(xsk_pool, - desc[i].addr - )); + nfp_desc_set_dma_addr_40b(txd, + xsk_buff_raw_get_dma(xsk_pool, desc[i].addr)); txd->offset_eop = NFD3_DESC_TX_EOP; txd->dma_len = cpu_to_le16(desc[i].len); txd->data_len = cpu_to_le16(desc[i].len); diff --git a/drivers/net/ethernet/netronome/nfp/nfdk/dp.c b/drivers/net/ethernet/netronome/nfp/nfdk/dp.c index e509d6dcba5c..300637e576a8 100644 --- a/drivers/net/ethernet/netronome/nfp/nfdk/dp.c +++ b/drivers/net/ethernet/netronome/nfp/nfdk/dp.c @@ -314,7 +314,7 @@ netdev_tx_t nfp_nfdk_tx(struct sk_buff *skb, struct net_device *netdev) FIELD_PREP(NFDK_DESC_TX_TYPE_HEAD, type); txd->dma_len_type = cpu_to_le16(dlen_type); - nfp_nfdk_tx_desc_set_dma_addr(txd, dma_addr); + nfp_desc_set_dma_addr_48b(txd, dma_addr); /* starts at bit 0 */ BUILD_BUG_ON(!(NFDK_DESC_TX_DMA_LEN_HEAD & 1)); @@ -339,7 +339,7 @@ netdev_tx_t nfp_nfdk_tx(struct sk_buff *skb, struct net_device *netdev) dlen_type = FIELD_PREP(NFDK_DESC_TX_DMA_LEN, dma_len); txd->dma_len_type = cpu_to_le16(dlen_type); - nfp_nfdk_tx_desc_set_dma_addr(txd, dma_addr); + nfp_desc_set_dma_addr_48b(txd, dma_addr); dma_len -= dlen_type; dma_addr += dlen_type + 1; @@ -595,8 +595,8 @@ nfp_nfdk_rx_give_one(const struct nfp_net_dp *dp, /* Fill freelist descriptor */ rx_ring->rxds[wr_idx].fld.reserved = 0; rx_ring->rxds[wr_idx].fld.meta_len_dd = 0; - nfp_desc_set_dma_addr(&rx_ring->rxds[wr_idx].fld, - dma_addr + dp->rx_dma_off); + nfp_desc_set_dma_addr_48b(&rx_ring->rxds[wr_idx].fld, + dma_addr + dp->rx_dma_off); rx_ring->wr_p++; if (!(rx_ring->wr_p % NFP_NET_FL_BATCH)) { @@ -929,7 +929,7 @@ nfp_nfdk_tx_xdp_buf(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring, FIELD_PREP(NFDK_DESC_TX_TYPE_HEAD, type); txd->dma_len_type = cpu_to_le16(dlen_type); - nfp_nfdk_tx_desc_set_dma_addr(txd, dma_addr); + nfp_desc_set_dma_addr_48b(txd, dma_addr); tmp_dlen = dlen_type & NFDK_DESC_TX_DMA_LEN_HEAD; dma_len -= tmp_dlen; @@ -940,7 +940,7 @@ nfp_nfdk_tx_xdp_buf(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring, dma_len -= 1; dlen_type = FIELD_PREP(NFDK_DESC_TX_DMA_LEN, dma_len); txd->dma_len_type = cpu_to_le16(dlen_type); - nfp_nfdk_tx_desc_set_dma_addr(txd, dma_addr); + nfp_desc_set_dma_addr_48b(txd, dma_addr); dlen_type &= NFDK_DESC_TX_DMA_LEN; dma_len -= dlen_type; @@ -1332,7 +1332,7 @@ nfp_nfdk_ctrl_tx_one(struct nfp_net *nn, struct nfp_net_r_vector *r_vec, FIELD_PREP(NFDK_DESC_TX_TYPE_HEAD, type); txd->dma_len_type = cpu_to_le16(dlen_type); - nfp_nfdk_tx_desc_set_dma_addr(txd, dma_addr); + nfp_desc_set_dma_addr_48b(txd, dma_addr); tmp_dlen = dlen_type & NFDK_DESC_TX_DMA_LEN_HEAD; dma_len -= tmp_dlen; @@ -1343,7 +1343,7 @@ nfp_nfdk_ctrl_tx_one(struct nfp_net *nn, struct nfp_net_r_vector *r_vec, dma_len -= 1; dlen_type = FIELD_PREP(NFDK_DESC_TX_DMA_LEN, dma_len); txd->dma_len_type = cpu_to_le16(dlen_type); - nfp_nfdk_tx_desc_set_dma_addr(txd, dma_addr); + nfp_desc_set_dma_addr_48b(txd, dma_addr); dlen_type &= NFDK_DESC_TX_DMA_LEN; dma_len -= dlen_type; diff --git a/drivers/net/ethernet/netronome/nfp/nfdk/rings.c b/drivers/net/ethernet/netronome/nfp/nfdk/rings.c index 301f11108826..f4d94ae0a349 100644 --- a/drivers/net/ethernet/netronome/nfp/nfdk/rings.c +++ b/drivers/net/ethernet/netronome/nfp/nfdk/rings.c @@ -181,6 +181,7 @@ const struct nfp_dp_ops nfp_nfdk_ops = { .version = NFP_NFD_VER_NFDK, .tx_min_desc_per_pkt = NFDK_TX_DESC_PER_SIMPLE_PKT, .cap_mask = NFP_NFDK_CFG_CTRL_SUPPORTED, + .dma_mask = DMA_BIT_MASK(48), .poll = nfp_nfdk_poll, .ctrl_poll = nfp_nfdk_ctrl_poll, .xmit = nfp_nfdk_tx, diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h index 3dd3a92d2e7f..b07cea8e354c 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h @@ -115,7 +115,7 @@ struct nfp_nfdk_tx_buf; #define D_IDX(ring, idx) ((idx) & ((ring)->cnt - 1)) /* Convenience macro for writing dma address into RX/TX descriptors */ -#define nfp_desc_set_dma_addr(desc, dma_addr) \ +#define nfp_desc_set_dma_addr_40b(desc, dma_addr) \ do { \ __typeof__(desc) __d = (desc); \ dma_addr_t __addr = (dma_addr); \ @@ -124,13 +124,13 @@ struct nfp_nfdk_tx_buf; __d->dma_addr_hi = upper_32_bits(__addr) & 0xff; \ } while (0) -#define nfp_nfdk_tx_desc_set_dma_addr(desc, dma_addr) \ - do { \ - __typeof__(desc) __d = (desc); \ - dma_addr_t __addr = (dma_addr); \ - \ - __d->dma_addr_hi = cpu_to_le16(upper_32_bits(__addr) & 0xff); \ - __d->dma_addr_lo = cpu_to_le32(lower_32_bits(__addr)); \ +#define nfp_desc_set_dma_addr_48b(desc, dma_addr) \ + do { \ + __typeof__(desc) __d = (desc); \ + dma_addr_t __addr = (dma_addr); \ + \ + __d->dma_addr_hi = cpu_to_le16(upper_32_bits(__addr)); \ + __d->dma_addr_lo = cpu_to_le32(lower_32_bits(__addr)); \ } while (0) /** @@ -225,8 +225,8 @@ struct nfp_net_tx_ring { struct nfp_net_rx_desc { union { struct { - u8 dma_addr_hi; /* High bits of the buf address */ - __le16 reserved; /* Must be zero */ + __le16 dma_addr_hi; /* High bits of the buf address */ + u8 reserved; /* Must be zero */ u8 meta_len_dd; /* Must be zero */ __le32 dma_addr_lo; /* Low bits of the buffer address */ diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 4e56a99087fa..57f284eefeb3 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -2040,6 +2040,7 @@ nfp_net_alloc(struct pci_dev *pdev, const struct nfp_dev_info *dev_info, void __iomem *ctrl_bar, bool needs_netdev, unsigned int max_tx_rings, unsigned int max_rx_rings) { + u64 dma_mask = dma_get_mask(&pdev->dev); struct nfp_net *nn; int err; @@ -2085,6 +2086,14 @@ nfp_net_alloc(struct pci_dev *pdev, const struct nfp_dev_info *dev_info, goto err_free_nn; } + if ((dma_mask & nn->dp.ops->dma_mask) != dma_mask) { + dev_err(&pdev->dev, + "DMA mask of loaded firmware: %llx, required DMA mask: %llx\n", + nn->dp.ops->dma_mask, dma_mask); + err = -EINVAL; + goto err_free_nn; + } + nn->max_tx_rings = max_tx_rings; nn->max_rx_rings = max_rx_rings; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_dp.h b/drivers/net/ethernet/netronome/nfp/nfp_net_dp.h index c934cc2d3208..83becb338478 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_dp.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_dp.h @@ -117,6 +117,7 @@ enum nfp_nfd_version { * @version: Indicate dp type * @tx_min_desc_per_pkt: Minimal TX descs needed for each packet * @cap_mask: Mask of supported features + * @dma_mask: DMA addressing capability * @poll: Napi poll for normal rx/tx * @xsk_poll: Napi poll when xsk is enabled * @ctrl_poll: Tasklet poll for ctrl rx/tx @@ -134,6 +135,7 @@ struct nfp_dp_ops { enum nfp_nfd_version version; unsigned int tx_min_desc_per_pkt; u32 cap_mask; + u64 dma_mask; int (*poll)(struct napi_struct *napi, int budget); int (*xsk_poll)(struct napi_struct *napi, int budget); diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_xsk.c b/drivers/net/ethernet/netronome/nfp/nfp_net_xsk.c index 86829446c637..aea507aed49d 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_xsk.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_xsk.c @@ -70,8 +70,12 @@ void nfp_net_xsk_rx_ring_fill_freelist(struct nfp_net_rx_ring *rx_ring) nfp_net_xsk_rx_bufs_stash(rx_ring, wr_idx, xdp); - nfp_desc_set_dma_addr(&rx_ring->rxds[wr_idx].fld, - rx_ring->xsk_rxbufs[wr_idx].dma_addr); + /* DMA address is expanded to 48-bit width in freelist for NFP3800, + * so the *_48b macro is used accordingly, it's also OK to fill + * a 40-bit address since the top 8 bits are get set to 0. + */ + nfp_desc_set_dma_addr_48b(&rx_ring->rxds[wr_idx].fld, + rx_ring->xsk_rxbufs[wr_idx].dma_addr); rx_ring->wr_p++; wr_ptr_add++; diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/crc32.h b/drivers/net/ethernet/netronome/nfp/nfpcore/crc32.h index afab6f0fc564..6ad43c7cefe6 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/crc32.h +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/crc32.h @@ -4,7 +4,6 @@ #ifndef NFP_CRC32_H #define NFP_CRC32_H -#include <linux/kernel.h> #include <linux/crc32.h> /** diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_dev.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_dev.c index 28384d6d1c6f..0725b51c2a95 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_dev.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_dev.c @@ -9,7 +9,7 @@ const struct nfp_dev_info nfp_dev_info[NFP_DEV_CNT] = { [NFP_DEV_NFP3800] = { - .dma_mask = DMA_BIT_MASK(40), + .dma_mask = DMA_BIT_MASK(48), .qc_idx_mask = GENMASK(8, 0), .qc_addr_offset = 0x400000, .min_qc_size = 512, @@ -21,7 +21,7 @@ const struct nfp_dev_info nfp_dev_info[NFP_DEV_CNT] = { .qc_area_sz = 0x100000, }, [NFP_DEV_NFP3800_VF] = { - .dma_mask = DMA_BIT_MASK(40), + .dma_mask = DMA_BIT_MASK(48), .qc_idx_mask = GENMASK(8, 0), .qc_addr_offset = 0, .min_qc_size = 512, diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c index e90fa97c0ae6..8dd7aa08ecfb 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c @@ -1869,8 +1869,7 @@ int qlcnic_sriov_set_vf_tx_rate(struct net_device *netdev, int vf, if (!min_tx_rate) min_tx_rate = QLC_VF_MIN_TX_RATE; - if (max_tx_rate && - (max_tx_rate >= 10000 || max_tx_rate < min_tx_rate)) { + if (max_tx_rate && max_tx_rate >= 10000) { netdev_err(netdev, "Invalid max Tx rate, allowed range is [%d - %d]", min_tx_rate, QLC_VF_MAX_TX_RATE); @@ -1880,8 +1879,7 @@ int qlcnic_sriov_set_vf_tx_rate(struct net_device *netdev, int vf, if (!max_tx_rate) max_tx_rate = 10000; - if (min_tx_rate && - (min_tx_rate > max_tx_rate || min_tx_rate < QLC_VF_MIN_TX_RATE)) { + if (min_tx_rate && min_tx_rate < QLC_VF_MIN_TX_RATE) { netdev_err(netdev, "Invalid min Tx rate, allowed range is [%d - %d]", QLC_VF_MIN_TX_RATE, max_tx_rate); diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig index 929cfc22cd0c..c4bca16dae57 100644 --- a/drivers/net/ethernet/stmicro/stmmac/Kconfig +++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig @@ -83,6 +83,7 @@ config DWMAC_IPQ806X default ARCH_QCOM depends on OF && (ARCH_QCOM || COMPILE_TEST) select MFD_SYSCON + select QCOM_SOCINFO help Support for QCA IPQ806X DWMAC Ethernet. diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c index f7dc8458cde8..e888c8a9c830 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c @@ -27,6 +27,8 @@ #include <linux/stmmac.h> #include <linux/of_mdio.h> #include <linux/module.h> +#include <linux/sys_soc.h> +#include <linux/bitfield.h> #include "stmmac_platform.h" @@ -64,6 +66,17 @@ #define NSS_COMMON_CLK_DIV_SGMII_100 4 #define NSS_COMMON_CLK_DIV_SGMII_10 49 +#define QSGMII_PCS_ALL_CH_CTL 0x80 +#define QSGMII_PCS_CH_SPEED_FORCE BIT(1) +#define QSGMII_PCS_CH_SPEED_10 0x0 +#define QSGMII_PCS_CH_SPEED_100 BIT(2) +#define QSGMII_PCS_CH_SPEED_1000 BIT(3) +#define QSGMII_PCS_CH_SPEED_MASK (QSGMII_PCS_CH_SPEED_FORCE | \ + QSGMII_PCS_CH_SPEED_10 | \ + QSGMII_PCS_CH_SPEED_100 | \ + QSGMII_PCS_CH_SPEED_1000) +#define QSGMII_PCS_CH_SPEED_SHIFT(x) ((x) * 4) + #define QSGMII_PCS_CAL_LCKDT_CTL 0x120 #define QSGMII_PCS_CAL_LCKDT_CTL_RST BIT(19) @@ -75,11 +88,20 @@ #define QSGMII_PHY_RX_SIGNAL_DETECT_EN BIT(2) #define QSGMII_PHY_TX_DRIVER_EN BIT(3) #define QSGMII_PHY_QSGMII_EN BIT(7) -#define QSGMII_PHY_PHASE_LOOP_GAIN_OFFSET 12 -#define QSGMII_PHY_RX_DC_BIAS_OFFSET 18 -#define QSGMII_PHY_RX_INPUT_EQU_OFFSET 20 -#define QSGMII_PHY_CDR_PI_SLEW_OFFSET 22 -#define QSGMII_PHY_TX_DRV_AMP_OFFSET 28 +#define QSGMII_PHY_DEEMPHASIS_LVL_MASK GENMASK(11, 10) +#define QSGMII_PHY_DEEMPHASIS_LVL(x) FIELD_PREP(QSGMII_PHY_DEEMPHASIS_LVL_MASK, (x)) +#define QSGMII_PHY_PHASE_LOOP_GAIN_MASK GENMASK(14, 12) +#define QSGMII_PHY_PHASE_LOOP_GAIN(x) FIELD_PREP(QSGMII_PHY_PHASE_LOOP_GAIN_MASK, (x)) +#define QSGMII_PHY_RX_DC_BIAS_MASK GENMASK(19, 18) +#define QSGMII_PHY_RX_DC_BIAS(x) FIELD_PREP(QSGMII_PHY_RX_DC_BIAS_MASK, (x)) +#define QSGMII_PHY_RX_INPUT_EQU_MASK GENMASK(21, 20) +#define QSGMII_PHY_RX_INPUT_EQU(x) FIELD_PREP(QSGMII_PHY_RX_INPUT_EQU_MASK, (x)) +#define QSGMII_PHY_CDR_PI_SLEW_MASK GENMASK(23, 22) +#define QSGMII_PHY_CDR_PI_SLEW(x) FIELD_PREP(QSGMII_PHY_CDR_PI_SLEW_MASK, (x)) +#define QSGMII_PHY_TX_SLEW_MASK GENMASK(27, 26) +#define QSGMII_PHY_TX_SLEW(x) FIELD_PREP(QSGMII_PHY_TX_SLEW_MASK, (x)) +#define QSGMII_PHY_TX_DRV_AMP_MASK GENMASK(31, 28) +#define QSGMII_PHY_TX_DRV_AMP(x) FIELD_PREP(QSGMII_PHY_TX_DRV_AMP_MASK, (x)) struct ipq806x_gmac { struct platform_device *pdev; @@ -242,6 +264,113 @@ static void ipq806x_gmac_fix_mac_speed(void *priv, unsigned int speed) ipq806x_gmac_set_speed(gmac, speed); } +static int +ipq806x_gmac_configure_qsgmii_pcs_speed(struct ipq806x_gmac *gmac) +{ + struct platform_device *pdev = gmac->pdev; + struct device *dev = &pdev->dev; + struct device_node *dn; + int link_speed; + int val = 0; + int ret; + + /* Some bootloader may apply wrong configuration and cause + * not functioning port. If fixed link is not set, + * reset the force speed bit. + */ + if (!of_phy_is_fixed_link(pdev->dev.of_node)) + goto write; + + dn = of_get_child_by_name(pdev->dev.of_node, "fixed-link"); + ret = of_property_read_u32(dn, "speed", &link_speed); + of_node_put(dn); + if (ret) { + dev_err(dev, "found fixed-link node with no speed"); + return ret; + } + + val = QSGMII_PCS_CH_SPEED_FORCE; + + switch (link_speed) { + case SPEED_1000: + val |= QSGMII_PCS_CH_SPEED_1000; + break; + case SPEED_100: + val |= QSGMII_PCS_CH_SPEED_100; + break; + case SPEED_10: + val |= QSGMII_PCS_CH_SPEED_10; + break; + } + +write: + regmap_update_bits(gmac->qsgmii_csr, QSGMII_PCS_ALL_CH_CTL, + QSGMII_PCS_CH_SPEED_MASK << + QSGMII_PCS_CH_SPEED_SHIFT(gmac->id), + val << + QSGMII_PCS_CH_SPEED_SHIFT(gmac->id)); + + return 0; +} + +static const struct soc_device_attribute ipq806x_gmac_soc_v1[] = { + { + .revision = "1.*", + }, + { + /* sentinel */ + } +}; + +static int +ipq806x_gmac_configure_qsgmii_params(struct ipq806x_gmac *gmac) +{ + struct platform_device *pdev = gmac->pdev; + const struct soc_device_attribute *soc; + struct device *dev = &pdev->dev; + u32 qsgmii_param; + + switch (gmac->id) { + case 1: + soc = soc_device_match(ipq806x_gmac_soc_v1); + + if (soc) + qsgmii_param = QSGMII_PHY_TX_DRV_AMP(0xc) | + QSGMII_PHY_TX_SLEW(0x2) | + QSGMII_PHY_DEEMPHASIS_LVL(0x2); + else + qsgmii_param = QSGMII_PHY_TX_DRV_AMP(0xd) | + QSGMII_PHY_TX_SLEW(0x0) | + QSGMII_PHY_DEEMPHASIS_LVL(0x0); + + qsgmii_param |= QSGMII_PHY_RX_DC_BIAS(0x2); + break; + case 2: + case 3: + qsgmii_param = QSGMII_PHY_RX_DC_BIAS(0x3) | + QSGMII_PHY_TX_DRV_AMP(0xc); + break; + default: /* gmac 0 can't be set in SGMII mode */ + dev_err(dev, "gmac id %d can't be in SGMII mode", gmac->id); + return -EINVAL; + } + + /* Common params across all gmac id */ + qsgmii_param |= QSGMII_PHY_CDR_EN | + QSGMII_PHY_RX_FRONT_EN | + QSGMII_PHY_RX_SIGNAL_DETECT_EN | + QSGMII_PHY_TX_DRIVER_EN | + QSGMII_PHY_QSGMII_EN | + QSGMII_PHY_PHASE_LOOP_GAIN(0x4) | + QSGMII_PHY_RX_INPUT_EQU(0x1) | + QSGMII_PHY_CDR_PI_SLEW(0x2); + + regmap_write(gmac->qsgmii_csr, QSGMII_PHY_SGMII_CTL(gmac->id), + qsgmii_param); + + return 0; +} + static int ipq806x_gmac_probe(struct platform_device *pdev) { struct plat_stmmacenet_data *plat_dat; @@ -328,17 +457,13 @@ static int ipq806x_gmac_probe(struct platform_device *pdev) regmap_write(gmac->nss_common, NSS_COMMON_CLK_GATE, val); if (gmac->phy_mode == PHY_INTERFACE_MODE_SGMII) { - regmap_write(gmac->qsgmii_csr, QSGMII_PHY_SGMII_CTL(gmac->id), - QSGMII_PHY_CDR_EN | - QSGMII_PHY_RX_FRONT_EN | - QSGMII_PHY_RX_SIGNAL_DETECT_EN | - QSGMII_PHY_TX_DRIVER_EN | - QSGMII_PHY_QSGMII_EN | - 0x4ul << QSGMII_PHY_PHASE_LOOP_GAIN_OFFSET | - 0x3ul << QSGMII_PHY_RX_DC_BIAS_OFFSET | - 0x1ul << QSGMII_PHY_RX_INPUT_EQU_OFFSET | - 0x2ul << QSGMII_PHY_CDR_PI_SLEW_OFFSET | - 0xCul << QSGMII_PHY_TX_DRV_AMP_OFFSET); + err = ipq806x_gmac_configure_qsgmii_params(gmac); + if (err) + goto err_remove_config_dt; + + err = ipq806x_gmac_configure_qsgmii_pcs_speed(gmac); + if (err) + goto err_remove_config_dt; } plat_dat->has_gmac = true; diff --git a/drivers/net/ipa/gsi.c b/drivers/net/ipa/gsi.c index 9cfe84319ee4..df8af1f00fc8 100644 --- a/drivers/net/ipa/gsi.c +++ b/drivers/net/ipa/gsi.c @@ -823,7 +823,7 @@ static void gsi_channel_program(struct gsi_channel *channel, bool doorbell) /* Now update the scratch registers for GPI protocol */ gpi = &scr.gpi; - gpi->max_outstanding_tre = gsi_channel_trans_tre_max(gsi, channel_id) * + gpi->max_outstanding_tre = channel->trans_tre_max * GSI_RING_ELEMENT_SIZE; gpi->outstanding_threshold = 2 * GSI_RING_ELEMENT_SIZE; @@ -991,75 +991,66 @@ void gsi_resume(struct gsi *gsi) enable_irq(gsi->irq); } -/** - * gsi_channel_tx_queued() - Report queued TX transfers for a channel - * @channel: Channel for which to report - * - * Report to the network stack the number of bytes and transactions that - * have been queued to hardware since last call. This and the next function - * supply information used by the network stack for throttling. - * - * For each channel we track the number of transactions used and bytes of - * data those transactions represent. We also track what those values are - * each time this function is called. Subtracting the two tells us - * the number of bytes and transactions that have been added between - * successive calls. - * - * Calling this each time we ring the channel doorbell allows us to - * provide accurate information to the network stack about how much - * work we've given the hardware at any point in time. - */ -void gsi_channel_tx_queued(struct gsi_channel *channel) +void gsi_trans_tx_committed(struct gsi_trans *trans) { + struct gsi_channel *channel = &trans->gsi->channel[trans->channel_id]; + + channel->trans_count++; + channel->byte_count += trans->len; + + trans->trans_count = channel->trans_count; + trans->byte_count = channel->byte_count; +} + +void gsi_trans_tx_queued(struct gsi_trans *trans) +{ + u32 channel_id = trans->channel_id; + struct gsi *gsi = trans->gsi; + struct gsi_channel *channel; u32 trans_count; u32 byte_count; + channel = &gsi->channel[channel_id]; + byte_count = channel->byte_count - channel->queued_byte_count; trans_count = channel->trans_count - channel->queued_trans_count; channel->queued_byte_count = channel->byte_count; channel->queued_trans_count = channel->trans_count; - ipa_gsi_channel_tx_queued(channel->gsi, gsi_channel_id(channel), - trans_count, byte_count); + ipa_gsi_channel_tx_queued(gsi, channel_id, trans_count, byte_count); } /** - * gsi_channel_tx_update() - Report completed TX transfers - * @channel: Channel that has completed transmitting packets - * @trans: Last transation known to be complete - * - * Compute the number of transactions and bytes that have been transferred - * over a TX channel since the given transaction was committed. Report this - * information to the network stack. - * - * At the time a transaction is committed, we record its channel's - * committed transaction and byte counts *in the transaction*. - * Completions are signaled by the hardware with an interrupt, and - * we can determine the latest completed transaction at that time. + * gsi_trans_tx_completed() - Report completed TX transactions + * @trans: TX channel transaction that has completed * - * The difference between the byte/transaction count recorded in - * the transaction and the count last time we recorded a completion - * tells us exactly how much data has been transferred between - * completions. + * Report that a transaction on a TX channel has completed. At the time a + * transaction is committed, we record *in the transaction* its channel's + * committed transaction and byte counts. Transactions are completed in + * order, and the difference between the channel's byte/transaction count + * when the transaction was committed and when it completes tells us + * exactly how much data has been transferred while the transaction was + * pending. * - * Calling this each time we learn of a newly-completed transaction - * allows us to provide accurate information to the network stack - * about how much work has been completed by the hardware at a given - * point in time. + * We report this information to the network stack, which uses it to manage + * the rate at which data is sent to hardware. */ -static void -gsi_channel_tx_update(struct gsi_channel *channel, struct gsi_trans *trans) +static void gsi_trans_tx_completed(struct gsi_trans *trans) { - u64 byte_count = trans->byte_count + trans->len; - u64 trans_count = trans->trans_count + 1; + u32 channel_id = trans->channel_id; + struct gsi *gsi = trans->gsi; + struct gsi_channel *channel; + u32 trans_count; + u32 byte_count; + + channel = &gsi->channel[channel_id]; + trans_count = trans->trans_count - channel->compl_trans_count; + byte_count = trans->byte_count - channel->compl_byte_count; - byte_count -= channel->compl_byte_count; - channel->compl_byte_count += byte_count; - trans_count -= channel->compl_trans_count; channel->compl_trans_count += trans_count; + channel->compl_byte_count += byte_count; - ipa_gsi_channel_tx_completed(channel->gsi, gsi_channel_id(channel), - trans_count, byte_count); + ipa_gsi_channel_tx_completed(gsi, channel_id, trans_count, byte_count); } /* Channel control interrupt handler */ @@ -1327,17 +1318,29 @@ static int gsi_irq_init(struct gsi *gsi, struct platform_device *pdev) } /* Return the transaction associated with a transfer completion event */ -static struct gsi_trans *gsi_event_trans(struct gsi_channel *channel, - struct gsi_event *event) +static struct gsi_trans * +gsi_event_trans(struct gsi *gsi, struct gsi_event *event) { + u32 channel_id = event->chid; + struct gsi_channel *channel; + struct gsi_trans *trans; u32 tre_offset; u32 tre_index; + channel = &gsi->channel[channel_id]; + if (WARN(!channel->gsi, "event has bad channel %u\n", channel_id)) + return NULL; + /* Event xfer_ptr records the TRE it's associated with */ tre_offset = lower_32_bits(le64_to_cpu(event->xfer_ptr)); tre_index = gsi_ring_index(&channel->tre_ring, tre_offset); - return gsi_channel_trans_mapped(channel, tre_index); + trans = gsi_channel_trans_mapped(channel, tre_index); + + if (WARN(!trans, "channel %u event with no transaction\n", channel_id)) + return NULL; + + return trans; } /** @@ -1367,8 +1370,6 @@ static void gsi_evt_ring_rx_update(struct gsi_evt_ring *evt_ring, u32 index) struct gsi_event *event_done; struct gsi_event *event; struct gsi_trans *trans; - u32 trans_count = 0; - u32 byte_count = 0; u32 event_avail; u32 old_index; @@ -1381,7 +1382,9 @@ static void gsi_evt_ring_rx_update(struct gsi_evt_ring *evt_ring, u32 index) */ old_index = ring->index; event = gsi_ring_virt(ring, old_index); - trans = gsi_event_trans(channel, event); + trans = gsi_event_trans(channel->gsi, event); + if (!trans) + return; /* Compute the number of events to process before we wrap, * and determine when we'll be done processing events. @@ -1390,8 +1393,6 @@ static void gsi_evt_ring_rx_update(struct gsi_evt_ring *evt_ring, u32 index) event_done = gsi_ring_virt(ring, index); do { trans->len = __le16_to_cpu(event->len); - byte_count += trans->len; - trans_count++; /* Move on to the next event and transaction */ if (--event_avail) @@ -1400,10 +1401,6 @@ static void gsi_evt_ring_rx_update(struct gsi_evt_ring *evt_ring, u32 index) event = gsi_ring_virt(ring, 0); trans = gsi_trans_pool_next(&trans_info->pool, trans); } while (event != event_done); - - /* We record RX bytes when they are received */ - channel->byte_count += byte_count; - channel->trans_count += trans_count; } /* Initialize a ring, including allocating DMA memory for its entries */ @@ -1493,7 +1490,9 @@ static struct gsi_trans *gsi_channel_update(struct gsi_channel *channel) return NULL; /* Get the transaction for the latest completed event. */ - trans = gsi_event_trans(channel, gsi_ring_virt(ring, index - 1)); + trans = gsi_event_trans(gsi, gsi_ring_virt(ring, index - 1)); + if (!trans) + return NULL; /* For RX channels, update each completed transaction with the number * of bytes that were actually received. For TX channels, report @@ -1501,7 +1500,7 @@ static struct gsi_trans *gsi_channel_update(struct gsi_channel *channel) * up the network stack. */ if (channel->toward_ipa) - gsi_channel_tx_update(channel, trans); + gsi_trans_tx_completed(trans); else gsi_evt_ring_rx_update(evt_ring, index); @@ -2001,9 +2000,10 @@ static void gsi_channel_evt_ring_exit(struct gsi_channel *channel) gsi_evt_ring_id_free(gsi, evt_ring_id); } -static bool gsi_channel_data_valid(struct gsi *gsi, +static bool gsi_channel_data_valid(struct gsi *gsi, bool command, const struct ipa_gsi_endpoint_data *data) { + const struct gsi_channel_data *channel_data; u32 channel_id = data->channel_id; struct device *dev = gsi->dev; @@ -2019,10 +2019,24 @@ static bool gsi_channel_data_valid(struct gsi *gsi, return false; } - if (!data->channel.tlv_count || - data->channel.tlv_count > GSI_TLV_MAX) { + if (command && !data->toward_ipa) { + dev_err(dev, "command channel %u is not TX\n", channel_id); + return false; + } + + channel_data = &data->channel; + + if (!channel_data->tlv_count || + channel_data->tlv_count > GSI_TLV_MAX) { dev_err(dev, "channel %u bad tlv_count %u; must be 1..%u\n", - channel_id, data->channel.tlv_count, GSI_TLV_MAX); + channel_id, channel_data->tlv_count, GSI_TLV_MAX); + return false; + } + + if (command && IPA_COMMAND_TRANS_TRE_MAX > channel_data->tlv_count) { + dev_err(dev, "command TRE max too big for channel %u (%u > %u)\n", + channel_id, IPA_COMMAND_TRANS_TRE_MAX, + channel_data->tlv_count); return false; } @@ -2031,22 +2045,22 @@ static bool gsi_channel_data_valid(struct gsi *gsi, * gsi_channel_tre_max() is computed, tre_count has to be almost * twice the TLV FIFO size to satisfy this requirement. */ - if (data->channel.tre_count < 2 * data->channel.tlv_count - 1) { + if (channel_data->tre_count < 2 * channel_data->tlv_count - 1) { dev_err(dev, "channel %u TLV count %u exceeds TRE count %u\n", - channel_id, data->channel.tlv_count, - data->channel.tre_count); + channel_id, channel_data->tlv_count, + channel_data->tre_count); return false; } - if (!is_power_of_2(data->channel.tre_count)) { + if (!is_power_of_2(channel_data->tre_count)) { dev_err(dev, "channel %u bad tre_count %u; not power of 2\n", - channel_id, data->channel.tre_count); + channel_id, channel_data->tre_count); return false; } - if (!is_power_of_2(data->channel.event_count)) { + if (!is_power_of_2(channel_data->event_count)) { dev_err(dev, "channel %u bad event_count %u; not power of 2\n", - channel_id, data->channel.event_count); + channel_id, channel_data->event_count); return false; } @@ -2062,7 +2076,7 @@ static int gsi_channel_init_one(struct gsi *gsi, u32 tre_count; int ret; - if (!gsi_channel_data_valid(gsi, data)) + if (!gsi_channel_data_valid(gsi, command, data)) return -EINVAL; /* Worst case we need an event for every outstanding TRE */ @@ -2080,7 +2094,7 @@ static int gsi_channel_init_one(struct gsi *gsi, channel->gsi = gsi; channel->toward_ipa = data->toward_ipa; channel->command = command; - channel->tlv_count = data->channel.tlv_count; + channel->trans_tre_max = data->channel.tlv_count; channel->tre_count = tre_count; channel->event_count = data->channel.event_count; @@ -2295,13 +2309,5 @@ u32 gsi_channel_tre_max(struct gsi *gsi, u32 channel_id) struct gsi_channel *channel = &gsi->channel[channel_id]; /* Hardware limit is channel->tre_count - 1 */ - return channel->tre_count - (channel->tlv_count - 1); -} - -/* Returns the maximum number of TREs in a single transaction for a channel */ -u32 gsi_channel_trans_tre_max(struct gsi *gsi, u32 channel_id) -{ - struct gsi_channel *channel = &gsi->channel[channel_id]; - - return channel->tlv_count; + return channel->tre_count - (channel->trans_tre_max - 1); } diff --git a/drivers/net/ipa/gsi.h b/drivers/net/ipa/gsi.h index 5d66116b46b0..bad1a78a96ed 100644 --- a/drivers/net/ipa/gsi.h +++ b/drivers/net/ipa/gsi.h @@ -110,16 +110,16 @@ struct gsi_channel { bool toward_ipa; bool command; /* AP command TX channel or not */ - u8 tlv_count; /* # entries in TLV FIFO */ + u8 trans_tre_max; /* max TREs in a transaction */ u16 tre_count; u16 event_count; struct gsi_ring tre_ring; u32 evt_ring_id; + /* The following counts are used only for TX endpoints */ u64 byte_count; /* total # bytes transferred */ u64 trans_count; /* total # transactions */ - /* The following counts are used only for TX endpoints */ u64 queued_byte_count; /* last reported queued byte count */ u64 queued_trans_count; /* ...and queued trans count */ u64 compl_byte_count; /* last reported completed byte count */ @@ -189,15 +189,6 @@ void gsi_teardown(struct gsi *gsi); u32 gsi_channel_tre_max(struct gsi *gsi, u32 channel_id); /** - * gsi_channel_trans_tre_max() - Maximum TREs in a single transaction - * @gsi: GSI pointer - * @channel_id: Channel whose limit is to be returned - * - * Return: The maximum TRE count per transaction on the channel - */ -u32 gsi_channel_trans_tre_max(struct gsi *gsi, u32 channel_id); - -/** * gsi_channel_start() - Start an allocated GSI channel * @gsi: GSI pointer * @channel_id: Channel to start diff --git a/drivers/net/ipa/gsi_private.h b/drivers/net/ipa/gsi_private.h index ea333a244cf5..74cbc287fc71 100644 --- a/drivers/net/ipa/gsi_private.h +++ b/drivers/net/ipa/gsi_private.h @@ -105,14 +105,21 @@ void gsi_channel_doorbell(struct gsi_channel *channel); void *gsi_ring_virt(struct gsi_ring *ring, u32 index); /** - * gsi_channel_tx_queued() - Report the number of bytes queued to hardware - * @channel: Channel whose bytes have been queued + * gsi_trans_tx_committed() - Record bytes committed for transmit + * @trans: TX endpoint transaction being committed * - * This arranges for the the number of transactions and bytes for - * transfer that have been queued to hardware to be reported. It - * passes this information up the network stack so it can be used to - * throttle transmissions. + * Report that a TX transaction has been committed. It updates some + * statistics used to manage transmit rates. */ -void gsi_channel_tx_queued(struct gsi_channel *channel); +void gsi_trans_tx_committed(struct gsi_trans *trans); + +/** + * gsi_trans_tx_queued() - Report a queued TX channel transaction + * @trans: Transaction being passed to hardware + * + * Report to the network stack that a TX transaction is being supplied + * to the hardware. + */ +void gsi_trans_tx_queued(struct gsi_trans *trans); #endif /* _GSI_PRIVATE_H_ */ diff --git a/drivers/net/ipa/gsi_trans.c b/drivers/net/ipa/gsi_trans.c index 55f8fe7d2668..a110be72f70b 100644 --- a/drivers/net/ipa/gsi_trans.c +++ b/drivers/net/ipa/gsi_trans.c @@ -340,7 +340,7 @@ struct gsi_trans *gsi_channel_trans_alloc(struct gsi *gsi, u32 channel_id, struct gsi_trans_info *trans_info; struct gsi_trans *trans; - if (WARN_ON(tre_count > gsi_channel_trans_tre_max(gsi, channel_id))) + if (WARN_ON(tre_count > channel->trans_tre_max)) return NULL; trans_info = &channel->trans_info; @@ -355,7 +355,7 @@ struct gsi_trans *gsi_channel_trans_alloc(struct gsi *gsi, u32 channel_id, trans = gsi_trans_pool_alloc(&trans_info->pool, 1); trans->gsi = gsi; trans->channel_id = channel_id; - trans->tre_count = tre_count; + trans->rsvd_count = tre_count; init_completion(&trans->completion); /* Allocate the scatterlist and (if requested) info entries. */ @@ -405,17 +405,17 @@ void gsi_trans_free(struct gsi_trans *trans) /* Releasing the reserved TREs implicitly frees the sgl[] and * (if present) info[] arrays, plus the transaction itself. */ - gsi_trans_tre_release(trans_info, trans->tre_count); + gsi_trans_tre_release(trans_info, trans->rsvd_count); } /* Add an immediate command to a transaction */ void gsi_trans_cmd_add(struct gsi_trans *trans, void *buf, u32 size, dma_addr_t addr, enum ipa_cmd_opcode opcode) { - u32 which = trans->used++; + u32 which = trans->used_count++; struct scatterlist *sg; - WARN_ON(which >= trans->tre_count); + WARN_ON(which >= trans->rsvd_count); /* Commands are quite different from data transfer requests. * Their payloads come from a pool whose memory is allocated @@ -446,9 +446,9 @@ int gsi_trans_page_add(struct gsi_trans *trans, struct page *page, u32 size, struct scatterlist *sg = &trans->sgl[0]; int ret; - if (WARN_ON(trans->tre_count != 1)) + if (WARN_ON(trans->rsvd_count != 1)) return -EINVAL; - if (WARN_ON(trans->used)) + if (WARN_ON(trans->used_count)) return -EINVAL; sg_set_page(sg, page, size, offset); @@ -456,7 +456,7 @@ int gsi_trans_page_add(struct gsi_trans *trans, struct page *page, u32 size, if (!ret) return -ENOMEM; - trans->used++; /* Transaction now owns the (DMA mapped) page */ + trans->used_count++; /* Transaction now owns the (DMA mapped) page */ return 0; } @@ -465,25 +465,26 @@ int gsi_trans_page_add(struct gsi_trans *trans, struct page *page, u32 size, int gsi_trans_skb_add(struct gsi_trans *trans, struct sk_buff *skb) { struct scatterlist *sg = &trans->sgl[0]; - u32 used; + u32 used_count; int ret; - if (WARN_ON(trans->tre_count != 1)) + if (WARN_ON(trans->rsvd_count != 1)) return -EINVAL; - if (WARN_ON(trans->used)) + if (WARN_ON(trans->used_count)) return -EINVAL; /* skb->len will not be 0 (checked early) */ ret = skb_to_sgvec(skb, sg, 0, skb->len); if (ret < 0) return ret; - used = ret; + used_count = ret; - ret = dma_map_sg(trans->gsi->dev, sg, used, trans->direction); + ret = dma_map_sg(trans->gsi->dev, sg, used_count, trans->direction); if (!ret) return -ENOMEM; - trans->used += used; /* Transaction now owns the (DMA mapped) skb */ + /* Transaction now owns the (DMA mapped) skb */ + trans->used_count += used_count; return 0; } @@ -549,7 +550,7 @@ static void gsi_trans_tre_fill(struct gsi_tre *dest_tre, dma_addr_t addr, static void __gsi_trans_commit(struct gsi_trans *trans, bool ring_db) { struct gsi_channel *channel = &trans->gsi->channel[trans->channel_id]; - struct gsi_ring *ring = &channel->tre_ring; + struct gsi_ring *tre_ring = &channel->tre_ring; enum ipa_cmd_opcode opcode = IPA_CMD_NONE; bool bei = channel->toward_ipa; struct gsi_tre *dest_tre; @@ -559,7 +560,7 @@ static void __gsi_trans_commit(struct gsi_trans *trans, bool ring_db) u32 avail; u32 i; - WARN_ON(!trans->used); + WARN_ON(!trans->used_count); /* Consume the entries. If we cross the end of the ring while * filling them we'll switch to the beginning to finish. @@ -567,35 +568,30 @@ static void __gsi_trans_commit(struct gsi_trans *trans, bool ring_db) * transfer request, whose opcode is IPA_CMD_NONE. */ cmd_opcode = channel->command ? &trans->cmd_opcode[0] : NULL; - avail = ring->count - ring->index % ring->count; - dest_tre = gsi_ring_virt(ring, ring->index); - for_each_sg(trans->sgl, sg, trans->used, i) { - bool last_tre = i == trans->used - 1; + avail = tre_ring->count - tre_ring->index % tre_ring->count; + dest_tre = gsi_ring_virt(tre_ring, tre_ring->index); + for_each_sg(trans->sgl, sg, trans->used_count, i) { + bool last_tre = i == trans->used_count - 1; dma_addr_t addr = sg_dma_address(sg); u32 len = sg_dma_len(sg); byte_count += len; if (!avail--) - dest_tre = gsi_ring_virt(ring, 0); + dest_tre = gsi_ring_virt(tre_ring, 0); if (cmd_opcode) opcode = *cmd_opcode++; gsi_trans_tre_fill(dest_tre, addr, len, last_tre, bei, opcode); dest_tre++; } - ring->index += trans->used; - - if (channel->toward_ipa) { - /* We record TX bytes when they are sent */ - trans->len = byte_count; - trans->trans_count = channel->trans_count; - trans->byte_count = channel->byte_count; - channel->trans_count++; - channel->byte_count += byte_count; - } + tre_ring->index += trans->used_count; + + trans->len = byte_count; + if (channel->toward_ipa) + gsi_trans_tx_committed(trans); /* Associate the last TRE with the transaction */ - gsi_channel_trans_map(channel, ring->index - 1, trans); + gsi_channel_trans_map(channel, tre_ring->index - 1, trans); gsi_trans_move_pending(trans); @@ -603,7 +599,7 @@ static void __gsi_trans_commit(struct gsi_trans *trans, bool ring_db) if (ring_db || !atomic_read(&channel->trans_info.tre_avail)) { /* Report what we're handing off to hardware for TX channels */ if (channel->toward_ipa) - gsi_channel_tx_queued(channel); + gsi_trans_tx_queued(trans); gsi_channel_doorbell(channel); } } @@ -611,7 +607,7 @@ static void __gsi_trans_commit(struct gsi_trans *trans, bool ring_db) /* Commit a GSI transaction */ void gsi_trans_commit(struct gsi_trans *trans, bool ring_db) { - if (trans->used) + if (trans->used_count) __gsi_trans_commit(trans, ring_db); else gsi_trans_free(trans); @@ -620,7 +616,7 @@ void gsi_trans_commit(struct gsi_trans *trans, bool ring_db) /* Commit a GSI transaction and wait for it to complete */ void gsi_trans_commit_wait(struct gsi_trans *trans) { - if (!trans->used) + if (!trans->used_count) goto out_trans_free; refcount_inc(&trans->refcount); @@ -638,7 +634,7 @@ void gsi_trans_complete(struct gsi_trans *trans) { /* If the entire SGL was mapped when added, unmap it now */ if (trans->direction != DMA_NONE) - dma_unmap_sg(trans->gsi->dev, trans->sgl, trans->used, + dma_unmap_sg(trans->gsi->dev, trans->sgl, trans->used_count, trans->direction); ipa_gsi_trans_complete(trans); @@ -675,7 +671,7 @@ void gsi_channel_trans_cancel_pending(struct gsi_channel *channel) int gsi_trans_read_byte(struct gsi *gsi, u32 channel_id, dma_addr_t addr) { struct gsi_channel *channel = &gsi->channel[channel_id]; - struct gsi_ring *ring = &channel->tre_ring; + struct gsi_ring *tre_ring = &channel->tre_ring; struct gsi_trans_info *trans_info; struct gsi_tre *dest_tre; @@ -687,10 +683,10 @@ int gsi_trans_read_byte(struct gsi *gsi, u32 channel_id, dma_addr_t addr) /* Now fill the the reserved TRE and tell the hardware */ - dest_tre = gsi_ring_virt(ring, ring->index); + dest_tre = gsi_ring_virt(tre_ring, tre_ring->index); gsi_trans_tre_fill(dest_tre, addr, 1, true, false, IPA_CMD_NONE); - ring->index++; + tre_ring->index++; gsi_channel_doorbell(channel); return 0; @@ -745,14 +741,10 @@ int gsi_channel_trans_init(struct gsi *gsi, u32 channel_id) * element is used to fill a single TRE when the transaction is * committed. So we need as many scatterlist elements as the * maximum number of TREs that can be outstanding. - * - * All TREs in a transaction must fit within the channel's TLV FIFO. - * A transaction on a channel can allocate as many TREs as that but - * no more. */ ret = gsi_trans_pool_init(&trans_info->sg_pool, sizeof(struct scatterlist), - tre_max, channel->tlv_count); + tre_max, channel->trans_tre_max); if (ret) goto err_trans_pool_exit; diff --git a/drivers/net/ipa/gsi_trans.h b/drivers/net/ipa/gsi_trans.h index 020c3b32de1d..7084507830c2 100644 --- a/drivers/net/ipa/gsi_trans.h +++ b/drivers/net/ipa/gsi_trans.h @@ -33,9 +33,9 @@ struct gsi_trans_pool; * @gsi: GSI pointer * @channel_id: Channel number transaction is associated with * @cancelled: If set by the core code, transaction was cancelled - * @tre_count: Number of TREs reserved for this transaction - * @used: Number of TREs *used* (could be less than tre_count) - * @len: Total # of transfer bytes represented in sgl[] (set by core) + * @rsvd_count: Number of TREs reserved for this transaction + * @used_count: Number of TREs *used* (could be less than rsvd_count) + * @len: Number of bytes sent or received by the transaction * @data: Preserved but not touched by the core transaction code * @cmd_opcode: Array of command opcodes (command channel only) * @sgl: An array of scatter/gather entries managed by core code @@ -45,8 +45,9 @@ struct gsi_trans_pool; * @byte_count: TX channel byte count recorded when transaction committed * @trans_count: Channel transaction count when committed (for BQL accounting) * - * The size used for some fields in this structure were chosen to ensure - * the full structure size is no larger than 128 bytes. + * The @len field is set when the transaction is committed. For RX + * transactions it is updated later to reflect the actual number of bytes + * received. */ struct gsi_trans { struct list_head links; /* gsi_channel lists */ @@ -56,8 +57,8 @@ struct gsi_trans { bool cancelled; /* true if transaction was cancelled */ - u8 tre_count; /* # TREs requested */ - u8 used; /* # entries used in sgl[] */ + u8 rsvd_count; /* # TREs requested */ + u8 used_count; /* # entries used in sgl[] */ u32 len; /* total # bytes across sgl[] */ union { diff --git a/drivers/net/ipa/ipa_cmd.c b/drivers/net/ipa/ipa_cmd.c index e58cd4478fd3..6dea40259b60 100644 --- a/drivers/net/ipa/ipa_cmd.c +++ b/drivers/net/ipa/ipa_cmd.c @@ -353,13 +353,13 @@ int ipa_cmd_pool_init(struct gsi_channel *channel, u32 tre_max) /* This is as good a place as any to validate build constants */ ipa_cmd_validate_build(); - /* Even though command payloads are allocated one at a time, - * a single transaction can require up to tlv_count of them, - * so we treat them as if that many can be allocated at once. + /* Command payloads are allocated one at a time, but a single + * transaction can require up to the maximum supported by the + * channel; treat them as if they were allocated all at once. */ return gsi_trans_pool_init_dma(dev, &trans_info->cmd_pool, sizeof(union ipa_cmd_payload), - tre_max, channel->tlv_count); + tre_max, channel->trans_tre_max); } void ipa_cmd_pool_exit(struct gsi_channel *channel) diff --git a/drivers/net/ipa/ipa_endpoint.c b/drivers/net/ipa/ipa_endpoint.c index d3b3255ac3d1..66d2bfdf9e42 100644 --- a/drivers/net/ipa/ipa_endpoint.c +++ b/drivers/net/ipa/ipa_endpoint.c @@ -1020,7 +1020,7 @@ int ipa_endpoint_skb_tx(struct ipa_endpoint *endpoint, struct sk_buff *skb) * If not, see if we can linearize it before giving up. */ nr_frags = skb_shinfo(skb)->nr_frags; - if (1 + nr_frags > endpoint->trans_tre_max) { + if (nr_frags > endpoint->skb_frag_max) { if (skb_linearize(skb)) return -E2BIG; nr_frags = 0; @@ -1368,18 +1368,14 @@ static void ipa_endpoint_status_parse(struct ipa_endpoint *endpoint, } } -/* Complete a TX transaction, command or from ipa_endpoint_skb_tx() */ -static void ipa_endpoint_tx_complete(struct ipa_endpoint *endpoint, - struct gsi_trans *trans) -{ -} - -/* Complete transaction initiated in ipa_endpoint_replenish_one() */ -static void ipa_endpoint_rx_complete(struct ipa_endpoint *endpoint, - struct gsi_trans *trans) +void ipa_endpoint_trans_complete(struct ipa_endpoint *endpoint, + struct gsi_trans *trans) { struct page *page; + if (endpoint->toward_ipa) + return; + if (trans->cancelled) goto done; @@ -1393,15 +1389,6 @@ done: ipa_endpoint_replenish(endpoint); } -void ipa_endpoint_trans_complete(struct ipa_endpoint *endpoint, - struct gsi_trans *trans) -{ - if (endpoint->toward_ipa) - ipa_endpoint_tx_complete(endpoint, trans); - else - ipa_endpoint_rx_complete(endpoint, trans); -} - void ipa_endpoint_trans_release(struct ipa_endpoint *endpoint, struct gsi_trans *trans) { @@ -1721,7 +1708,7 @@ static void ipa_endpoint_setup_one(struct ipa_endpoint *endpoint) if (endpoint->ee_id != GSI_EE_AP) return; - endpoint->trans_tre_max = gsi_channel_trans_tre_max(gsi, channel_id); + endpoint->skb_frag_max = gsi->channel[channel_id].trans_tre_max - 1; if (!endpoint->toward_ipa) { /* RX transactions require a single TRE, so the maximum * backlog is the same as the maximum outstanding TREs. diff --git a/drivers/net/ipa/ipa_endpoint.h b/drivers/net/ipa/ipa_endpoint.h index 01790c60bee8..28e0a7386fd7 100644 --- a/drivers/net/ipa/ipa_endpoint.h +++ b/drivers/net/ipa/ipa_endpoint.h @@ -142,7 +142,7 @@ enum ipa_replenish_flag { * @endpoint_id: IPA endpoint number * @toward_ipa: Endpoint direction (true = TX, false = RX) * @config: Default endpoint configuration - * @trans_tre_max: Maximum number of TRE descriptors per transaction + * @skb_frag_max: Maximum allowed number of TX SKB fragments * @evt_ring_id: GSI event ring used by the endpoint * @netdev: Network device pointer, if endpoint uses one * @replenish_flags: Replenishing state flags @@ -157,7 +157,7 @@ struct ipa_endpoint { bool toward_ipa; struct ipa_endpoint_config config; - u32 trans_tre_max; + u32 skb_frag_max; /* Used for netdev TX only */ u32 evt_ring_id; /* Net device this endpoint is associated with, if any */ diff --git a/drivers/net/ipvlan/ipvlan.h b/drivers/net/ipvlan/ipvlan.h index 3837c897832e..de94921cbef9 100644 --- a/drivers/net/ipvlan/ipvlan.h +++ b/drivers/net/ipvlan/ipvlan.h @@ -47,11 +47,11 @@ typedef enum { } ipvl_hdr_type; struct ipvl_pcpu_stats { - u64 rx_pkts; - u64 rx_bytes; - u64 rx_mcast; - u64 tx_pkts; - u64 tx_bytes; + u64_stats_t rx_pkts; + u64_stats_t rx_bytes; + u64_stats_t rx_mcast; + u64_stats_t tx_pkts; + u64_stats_t tx_bytes; struct u64_stats_sync syncp; u32 rx_errs; u32 tx_drps; diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index 6ffb27419e64..dfeb5b392e64 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -19,10 +19,10 @@ void ipvlan_count_rx(const struct ipvl_dev *ipvlan, pcptr = this_cpu_ptr(ipvlan->pcpu_stats); u64_stats_update_begin(&pcptr->syncp); - pcptr->rx_pkts++; - pcptr->rx_bytes += len; + u64_stats_inc(&pcptr->rx_pkts); + u64_stats_add(&pcptr->rx_bytes, len); if (mcast) - pcptr->rx_mcast++; + u64_stats_inc(&pcptr->rx_mcast); u64_stats_update_end(&pcptr->syncp); } else { this_cpu_inc(ipvlan->pcpu_stats->rx_errs); diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index aa28a29e228c..49ba8a50dfb1 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -224,8 +224,8 @@ static netdev_tx_t ipvlan_start_xmit(struct sk_buff *skb, pcptr = this_cpu_ptr(ipvlan->pcpu_stats); u64_stats_update_begin(&pcptr->syncp); - pcptr->tx_pkts++; - pcptr->tx_bytes += skblen; + u64_stats_inc(&pcptr->tx_pkts); + u64_stats_add(&pcptr->tx_bytes, skblen); u64_stats_update_end(&pcptr->syncp); } else { this_cpu_inc(ipvlan->pcpu_stats->tx_drps); @@ -300,11 +300,11 @@ static void ipvlan_get_stats64(struct net_device *dev, pcptr = per_cpu_ptr(ipvlan->pcpu_stats, idx); do { strt= u64_stats_fetch_begin_irq(&pcptr->syncp); - rx_pkts = pcptr->rx_pkts; - rx_bytes = pcptr->rx_bytes; - rx_mcast = pcptr->rx_mcast; - tx_pkts = pcptr->tx_pkts; - tx_bytes = pcptr->tx_bytes; + rx_pkts = u64_stats_read(&pcptr->rx_pkts); + rx_bytes = u64_stats_read(&pcptr->rx_bytes); + rx_mcast = u64_stats_read(&pcptr->rx_mcast); + tx_pkts = u64_stats_read(&pcptr->tx_pkts); + tx_bytes = u64_stats_read(&pcptr->tx_bytes); } while (u64_stats_fetch_retry_irq(&pcptr->syncp, strt)); @@ -315,8 +315,8 @@ static void ipvlan_get_stats64(struct net_device *dev, s->tx_bytes += tx_bytes; /* u32 values are updated without syncp protection. */ - rx_errs += pcptr->rx_errs; - tx_drps += pcptr->tx_drps; + rx_errs += READ_ONCE(pcptr->rx_errs); + tx_drps += READ_ONCE(pcptr->tx_drps); } s->rx_errors = rx_errs; s->rx_dropped = rx_errs; diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 817577e713d7..c881e1bf6f6e 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -523,8 +523,8 @@ static void count_tx(struct net_device *dev, int ret, int len) struct pcpu_sw_netstats *stats = this_cpu_ptr(dev->tstats); u64_stats_update_begin(&stats->syncp); - stats->tx_packets++; - stats->tx_bytes += len; + u64_stats_inc(&stats->tx_packets); + u64_stats_add(&stats->tx_bytes, len); u64_stats_update_end(&stats->syncp); } } @@ -825,8 +825,8 @@ static void count_rx(struct net_device *dev, int len) struct pcpu_sw_netstats *stats = this_cpu_ptr(dev->tstats); u64_stats_update_begin(&stats->syncp); - stats->rx_packets++; - stats->rx_bytes += len; + u64_stats_inc(&stats->rx_packets); + u64_stats_add(&stats->rx_bytes, len); u64_stats_update_end(&stats->syncp); } @@ -3462,7 +3462,7 @@ static int macsec_dev_init(struct net_device *dev) memcpy(dev->broadcast, real_dev->broadcast, dev->addr_len); /* Get macsec's reference to real_dev */ - dev_hold_track(real_dev, &macsec->dev_tracker, GFP_KERNEL); + netdev_hold(real_dev, &macsec->dev_tracker, GFP_KERNEL); return 0; } @@ -3710,7 +3710,7 @@ static void macsec_free_netdev(struct net_device *dev) free_percpu(macsec->secy.tx_sc.stats); /* Get rid of the macsec's reference to real_dev */ - dev_put_track(macsec->real_dev, &macsec->dev_tracker); + netdev_put(macsec->real_dev, &macsec->dev_tracker); } static void macsec_setup(struct net_device *dev) diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index eff75beb1395..1080d6ebff63 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -575,8 +575,8 @@ static netdev_tx_t macvlan_start_xmit(struct sk_buff *skb, pcpu_stats = this_cpu_ptr(vlan->pcpu_stats); u64_stats_update_begin(&pcpu_stats->syncp); - pcpu_stats->tx_packets++; - pcpu_stats->tx_bytes += len; + u64_stats_inc(&pcpu_stats->tx_packets); + u64_stats_add(&pcpu_stats->tx_bytes, len); u64_stats_update_end(&pcpu_stats->syncp); } else { this_cpu_inc(vlan->pcpu_stats->tx_dropped); @@ -915,7 +915,7 @@ static int macvlan_init(struct net_device *dev) port->count += 1; /* Get macvlan's reference to lowerdev */ - dev_hold_track(lowerdev, &vlan->dev_tracker, GFP_KERNEL); + netdev_hold(lowerdev, &vlan->dev_tracker, GFP_KERNEL); return 0; } @@ -949,11 +949,11 @@ static void macvlan_dev_get_stats64(struct net_device *dev, p = per_cpu_ptr(vlan->pcpu_stats, i); do { start = u64_stats_fetch_begin_irq(&p->syncp); - rx_packets = p->rx_packets; - rx_bytes = p->rx_bytes; - rx_multicast = p->rx_multicast; - tx_packets = p->tx_packets; - tx_bytes = p->tx_bytes; + rx_packets = u64_stats_read(&p->rx_packets); + rx_bytes = u64_stats_read(&p->rx_bytes); + rx_multicast = u64_stats_read(&p->rx_multicast); + tx_packets = u64_stats_read(&p->tx_packets); + tx_bytes = u64_stats_read(&p->tx_bytes); } while (u64_stats_fetch_retry_irq(&p->syncp, start)); stats->rx_packets += rx_packets; @@ -964,8 +964,8 @@ static void macvlan_dev_get_stats64(struct net_device *dev, /* rx_errors & tx_dropped are u32, updated * without syncp protection. */ - rx_errors += p->rx_errors; - tx_dropped += p->tx_dropped; + rx_errors += READ_ONCE(p->rx_errors); + tx_dropped += READ_ONCE(p->tx_dropped); } stats->rx_errors = rx_errors; stats->rx_dropped = rx_errors; @@ -1185,7 +1185,7 @@ static void macvlan_dev_free(struct net_device *dev) struct macvlan_dev *vlan = netdev_priv(dev); /* Get rid of the macvlan's reference to lowerdev */ - dev_put_track(vlan->lowerdev, &vlan->dev_tracker); + netdev_put(vlan->lowerdev, &vlan->dev_tracker); } void macvlan_common_setup(struct net_device *dev) diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c index ab8cd5551020..ddac61d79145 100644 --- a/drivers/net/netconsole.c +++ b/drivers/net/netconsole.c @@ -721,7 +721,7 @@ restart: __netpoll_cleanup(&nt->np); spin_lock_irqsave(&target_list_lock, flags); - dev_put_track(nt->np.dev, &nt->np.dev_tracker); + netdev_put(nt->np.dev, &nt->np.dev_tracker); nt->np.dev = NULL; nt->enabled = false; stopped = true; diff --git a/drivers/net/phy/fixed_phy.c b/drivers/net/phy/fixed_phy.c index 03abe6233bbb..aef739c20ac4 100644 --- a/drivers/net/phy/fixed_phy.c +++ b/drivers/net/phy/fixed_phy.c @@ -353,6 +353,7 @@ static int __init fixed_mdio_bus_init(void) fmb->mii_bus->parent = &pdev->dev; fmb->mii_bus->read = &fixed_mdio_read; fmb->mii_bus->write = &fixed_mdio_write; + fmb->mii_bus->phy_mask = ~0; ret = mdiobus_register(fmb->mii_bus); if (ret) diff --git a/drivers/net/phy/marvell-88x2222.c b/drivers/net/phy/marvell-88x2222.c index d8b31d4d2a73..f070776ca904 100644 --- a/drivers/net/phy/marvell-88x2222.c +++ b/drivers/net/phy/marvell-88x2222.c @@ -490,6 +490,7 @@ static int mv2222_sfp_insert(void *upstream, const struct sfp_eeprom_id *id) dev = &phydev->mdio.dev; sfp_parse_support(phydev->sfp_bus, id, sfp_supported); + phydev->port = sfp_parse_port(phydev->sfp_bus, id, sfp_supported); sfp_interface = sfp_select_interface(phydev->sfp_bus, sfp_supported); dev_info(dev, "%s SFP module inserted\n", phy_modes(sfp_interface)); @@ -526,6 +527,7 @@ static void mv2222_sfp_remove(void *upstream) priv->line_interface = PHY_INTERFACE_MODE_NA; linkmode_zero(priv->supported); + phydev->port = PORT_NONE; } static void mv2222_sfp_link_up(void *upstream) diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index b07dde6f0abf..aac133a1e27a 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -749,10 +749,10 @@ static rx_handler_result_t team_handle_frame(struct sk_buff **pskb) pcpu_stats = this_cpu_ptr(team->pcpu_stats); u64_stats_update_begin(&pcpu_stats->syncp); - pcpu_stats->rx_packets++; - pcpu_stats->rx_bytes += skb->len; + u64_stats_inc(&pcpu_stats->rx_packets); + u64_stats_add(&pcpu_stats->rx_bytes, skb->len); if (skb->pkt_type == PACKET_MULTICAST) - pcpu_stats->rx_multicast++; + u64_stats_inc(&pcpu_stats->rx_multicast); u64_stats_update_end(&pcpu_stats->syncp); skb->dev = team->dev; @@ -1720,8 +1720,8 @@ static netdev_tx_t team_xmit(struct sk_buff *skb, struct net_device *dev) pcpu_stats = this_cpu_ptr(team->pcpu_stats); u64_stats_update_begin(&pcpu_stats->syncp); - pcpu_stats->tx_packets++; - pcpu_stats->tx_bytes += len; + u64_stats_inc(&pcpu_stats->tx_packets); + u64_stats_add(&pcpu_stats->tx_bytes, len); u64_stats_update_end(&pcpu_stats->syncp); } else { this_cpu_inc(team->pcpu_stats->tx_dropped); @@ -1854,11 +1854,11 @@ team_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) p = per_cpu_ptr(team->pcpu_stats, i); do { start = u64_stats_fetch_begin_irq(&p->syncp); - rx_packets = p->rx_packets; - rx_bytes = p->rx_bytes; - rx_multicast = p->rx_multicast; - tx_packets = p->tx_packets; - tx_bytes = p->tx_bytes; + rx_packets = u64_stats_read(&p->rx_packets); + rx_bytes = u64_stats_read(&p->rx_bytes); + rx_multicast = u64_stats_read(&p->rx_multicast); + tx_packets = u64_stats_read(&p->tx_packets); + tx_bytes = u64_stats_read(&p->tx_bytes); } while (u64_stats_fetch_retry_irq(&p->syncp, start)); stats->rx_packets += rx_packets; @@ -1870,9 +1870,9 @@ team_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) * rx_dropped, tx_dropped & rx_nohandler are u32, * updated without syncp protection. */ - rx_dropped += p->rx_dropped; - tx_dropped += p->tx_dropped; - rx_nohandler += p->rx_nohandler; + rx_dropped += READ_ONCE(p->rx_dropped); + tx_dropped += READ_ONCE(p->tx_dropped); + rx_nohandler += READ_ONCE(p->rx_nohandler); } stats->rx_dropped = rx_dropped; stats->tx_dropped = tx_dropped; diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index bd03e16f98a1..35110814ba22 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -2088,6 +2088,11 @@ static const struct usb_device_id products[] = { USB_DEVICE(0x0424, 0x9E08), .driver_info = (unsigned long) &smsc95xx_info, }, + { + /* Microchip's EVB-LAN8670-USB 10BASE-T1S Ethernet Device */ + USB_DEVICE(0x184F, 0x0051), + .driver_info = (unsigned long)&smsc95xx_info, + }, { }, /* END */ }; MODULE_DEVICE_TABLE(usb, products); diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 1cb6dab3e2d0..dc79811535c2 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -337,8 +337,8 @@ void usbnet_skb_return (struct usbnet *dev, struct sk_buff *skb) skb->protocol = eth_type_trans (skb, dev->net); flags = u64_stats_update_begin_irqsave(&stats64->syncp); - stats64->rx_packets++; - stats64->rx_bytes += skb->len; + u64_stats_inc(&stats64->rx_packets); + u64_stats_add(&stats64->rx_bytes, skb->len); u64_stats_update_end_irqrestore(&stats64->syncp, flags); netif_dbg(dev, rx_status, dev->net, "< rx, len %zu, type 0x%x\n", @@ -1258,8 +1258,8 @@ static void tx_complete (struct urb *urb) unsigned long flags; flags = u64_stats_update_begin_irqsave(&stats64->syncp); - stats64->tx_packets += entry->packets; - stats64->tx_bytes += entry->length; + u64_stats_add(&stats64->tx_packets, entry->packets); + u64_stats_add(&stats64->tx_bytes, entry->length); u64_stats_update_end_irqrestore(&stats64->syncp, flags); } else { dev->net->stats.tx_errors++; diff --git a/drivers/net/vmxnet3/Makefile b/drivers/net/vmxnet3/Makefile index 7a38925f4165..a666a88ac1ff 100644 --- a/drivers/net/vmxnet3/Makefile +++ b/drivers/net/vmxnet3/Makefile @@ -2,7 +2,7 @@ # # Linux driver for VMware's vmxnet3 ethernet NIC. # -# Copyright (C) 2007-2021, VMware, Inc. All Rights Reserved. +# Copyright (C) 2007-2022, VMware, Inc. All Rights Reserved. # # This program is free software; you can redistribute it and/or modify it # under the terms of the GNU General Public License as published by the diff --git a/drivers/net/vmxnet3/upt1_defs.h b/drivers/net/vmxnet3/upt1_defs.h index f9f3a23d1698..41c0660a0c54 100644 --- a/drivers/net/vmxnet3/upt1_defs.h +++ b/drivers/net/vmxnet3/upt1_defs.h @@ -1,7 +1,7 @@ /* * Linux driver for VMware's vmxnet3 ethernet NIC. * - * Copyright (C) 2008-2021, VMware, Inc. All Rights Reserved. + * Copyright (C) 2008-2022, VMware, Inc. All Rights Reserved. * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by the diff --git a/drivers/net/vmxnet3/vmxnet3_defs.h b/drivers/net/vmxnet3/vmxnet3_defs.h index 74d4e8bc4abc..41d6767283a6 100644 --- a/drivers/net/vmxnet3/vmxnet3_defs.h +++ b/drivers/net/vmxnet3/vmxnet3_defs.h @@ -1,7 +1,7 @@ /* * Linux driver for VMware's vmxnet3 ethernet NIC. * - * Copyright (C) 2008-2021, VMware, Inc. All Rights Reserved. + * Copyright (C) 2008-2022, VMware, Inc. All Rights Reserved. * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by the @@ -40,7 +40,13 @@ enum { VMXNET3_REG_MACL = 0x28, /* MAC Address Low */ VMXNET3_REG_MACH = 0x30, /* MAC Address High */ VMXNET3_REG_ICR = 0x38, /* Interrupt Cause Register */ - VMXNET3_REG_ECR = 0x40 /* Event Cause Register */ + VMXNET3_REG_ECR = 0x40, /* Event Cause Register */ + VMXNET3_REG_DCR = 0x48, /* Device capability register, + * from 0x48 to 0x80 + */ + VMXNET3_REG_PTCR = 0x88, /* Passthru capbility register + * from 0x88 to 0xb0 + */ }; /* BAR 0 */ @@ -51,8 +57,18 @@ enum { VMXNET3_REG_RXPROD2 = 0xA00 /* Rx Producer Index for ring 2 */ }; -#define VMXNET3_PT_REG_SIZE 4096 /* BAR 0 */ -#define VMXNET3_VD_REG_SIZE 4096 /* BAR 1 */ +/* For Large PT BAR, the following offset to DB register */ +enum { + VMXNET3_REG_LB_TXPROD = 0x1000, /* Tx Producer Index */ + VMXNET3_REG_LB_RXPROD = 0x1400, /* Rx Producer Index for ring 1 */ + VMXNET3_REG_LB_RXPROD2 = 0x1800, /* Rx Producer Index for ring 2 */ +}; + +#define VMXNET3_PT_REG_SIZE 4096 /* BAR 0 */ +#define VMXNET3_LARGE_PT_REG_SIZE 8192 /* large PT pages */ +#define VMXNET3_VD_REG_SIZE 4096 /* BAR 1 */ +#define VMXNET3_LARGE_BAR0_REG_SIZE (4096 * 4096) /* LARGE BAR 0 */ +#define VMXNET3_OOB_REG_SIZE (4094 * 4096) /* OOB pages */ #define VMXNET3_REG_ALIGN 8 /* All registers are 8-byte aligned. */ #define VMXNET3_REG_ALIGN_MASK 0x7 @@ -83,6 +99,9 @@ enum { VMXNET3_CMD_SET_COALESCE, VMXNET3_CMD_REGISTER_MEMREGS, VMXNET3_CMD_SET_RSS_FIELDS, + VMXNET3_CMD_RESERVED4, + VMXNET3_CMD_RESERVED5, + VMXNET3_CMD_SET_RING_BUFFER_SIZE, VMXNET3_CMD_FIRST_GET = 0xF00D0000, VMXNET3_CMD_GET_QUEUE_STATUS = VMXNET3_CMD_FIRST_GET, @@ -101,6 +120,9 @@ enum { VMXNET3_CMD_GET_RESERVED2, VMXNET3_CMD_GET_RESERVED3, VMXNET3_CMD_GET_MAX_QUEUES_CONF, + VMXNET3_CMD_GET_RESERVED4, + VMXNET3_CMD_GET_MAX_CAPABILITIES, + VMXNET3_CMD_GET_DCR0_REG, }; /* @@ -126,17 +148,17 @@ struct Vmxnet3_TxDesc { #ifdef __BIG_ENDIAN_BITFIELD u32 msscof:14; /* MSS, checksum offset, flags */ - u32 ext1:1; + u32 ext1:1; /* set to 1 to indicate inner csum/tso, vmxnet3 v7 */ u32 dtype:1; /* descriptor type */ - u32 oco:1; + u32 oco:1; /* Outer csum offload */ u32 gen:1; /* generation bit */ u32 len:14; #else u32 len:14; u32 gen:1; /* generation bit */ - u32 oco:1; + u32 oco:1; /* Outer csum offload */ u32 dtype:1; /* descriptor type */ - u32 ext1:1; + u32 ext1:1; /* set to 1 to indicate inner csum/tso, vmxnet3 v7 */ u32 msscof:14; /* MSS, checksum offset, flags */ #endif /* __BIG_ENDIAN_BITFIELD */ @@ -240,11 +262,13 @@ struct Vmxnet3_RxCompDesc { u32 rqID:10; /* rx queue/ring ID */ u32 sop:1; /* Start of Packet */ u32 eop:1; /* End of Packet */ - u32 ext1:2; + u32 ext1:2; /* bit 0: indicating v4/v6/.. is for inner header */ + /* bit 1: indicating rssType is based on inner header */ u32 rxdIdx:12; /* Index of the RxDesc */ #else u32 rxdIdx:12; /* Index of the RxDesc */ - u32 ext1:2; + u32 ext1:2; /* bit 0: indicating v4/v6/.. is for inner header */ + /* bit 1: indicating rssType is based on inner header */ u32 eop:1; /* End of Packet */ u32 sop:1; /* Start of Packet */ u32 rqID:10; /* rx queue/ring ID */ @@ -378,6 +402,8 @@ union Vmxnet3_GenericDesc { /* max # of tx descs for a non-tso pkt */ #define VMXNET3_MAX_TXD_PER_PKT 16 +/* max # of tx descs for a tso pkt */ +#define VMXNET3_MAX_TSO_TXD_PER_PKT 24 /* Max size of a single rx buffer */ #define VMXNET3_MAX_RX_BUF_SIZE ((1 << 14) - 1) @@ -724,6 +750,13 @@ enum Vmxnet3_RSSField { VMXNET3_RSS_FIELDS_ESPIP6 = 0x0020, }; +struct Vmxnet3_RingBufferSize { + __le16 ring1BufSizeType0; + __le16 ring1BufSizeType1; + __le16 ring2BufSizeType1; + __le16 pad; +}; + /* If the command data <= 16 bytes, use the shared memory directly. * otherwise, use variable length configuration descriptor. */ @@ -731,6 +764,7 @@ union Vmxnet3_CmdInfo { struct Vmxnet3_VariableLenConfDesc varConf; struct Vmxnet3_SetPolling setPolling; enum Vmxnet3_RSSField setRssFields; + struct Vmxnet3_RingBufferSize ringBufSize; __le64 data[2]; }; @@ -801,4 +835,30 @@ struct Vmxnet3_DriverShared { #define VMXNET3_LINK_UP (10000 << 16 | 1) /* 10 Gbps, up */ #define VMXNET3_LINK_DOWN 0 +#define VMXNET3_DCR_ERROR 31 /* error when bit 31 of DCR is set */ +#define VMXNET3_CAP_UDP_RSS 0 /* bit 0 of DCR 0 */ +#define VMXNET3_CAP_ESP_RSS_IPV4 1 /* bit 1 of DCR 0 */ +#define VMXNET3_CAP_GENEVE_CHECKSUM_OFFLOAD 2 /* bit 2 of DCR 0 */ +#define VMXNET3_CAP_GENEVE_TSO 3 /* bit 3 of DCR 0 */ +#define VMXNET3_CAP_VXLAN_CHECKSUM_OFFLOAD 4 /* bit 4 of DCR 0 */ +#define VMXNET3_CAP_VXLAN_TSO 5 /* bit 5 of DCR 0 */ +#define VMXNET3_CAP_GENEVE_OUTER_CHECKSUM_OFFLOAD 6 /* bit 6 of DCR 0 */ +#define VMXNET3_CAP_VXLAN_OUTER_CHECKSUM_OFFLOAD 7 /* bit 7 of DCR 0 */ +#define VMXNET3_CAP_PKT_STEERING_IPV4 8 /* bit 8 of DCR 0 */ +#define VMXNET3_CAP_VERSION_4_MAX VMXNET3_CAP_PKT_STEERING_IPV4 +#define VMXNET3_CAP_ESP_RSS_IPV6 9 /* bit 9 of DCR 0 */ +#define VMXNET3_CAP_VERSION_5_MAX VMXNET3_CAP_ESP_RSS_IPV6 +#define VMXNET3_CAP_ESP_OVER_UDP_RSS 10 /* bit 10 of DCR 0 */ +#define VMXNET3_CAP_INNER_RSS 11 /* bit 11 of DCR 0 */ +#define VMXNET3_CAP_INNER_ESP_RSS 12 /* bit 12 of DCR 0 */ +#define VMXNET3_CAP_CRC32_HASH_FUNC 13 /* bit 13 of DCR 0 */ +#define VMXNET3_CAP_VERSION_6_MAX VMXNET3_CAP_CRC32_HASH_FUNC +#define VMXNET3_CAP_OAM_FILTER 14 /* bit 14 of DCR 0 */ +#define VMXNET3_CAP_ESP_QS 15 /* bit 15 of DCR 0 */ +#define VMXNET3_CAP_LARGE_BAR 16 /* bit 16 of DCR 0 */ +#define VMXNET3_CAP_OOORX_COMP 17 /* bit 17 of DCR 0 */ +#define VMXNET3_CAP_VERSION_7_MAX 18 +/* when new capability is introduced, update VMXNET3_CAP_MAX */ +#define VMXNET3_CAP_MAX VMXNET3_CAP_VERSION_7_MAX + #endif /* _VMXNET3_DEFS_H_ */ diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index 93e8d119d45f..1565e1808a19 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -1,7 +1,7 @@ /* * Linux driver for VMware's vmxnet3 ethernet NIC. * - * Copyright (C) 2008-2021, VMware, Inc. All Rights Reserved. + * Copyright (C) 2008-2022, VMware, Inc. All Rights Reserved. * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by the @@ -130,6 +130,20 @@ vmxnet3_tq_stop(struct vmxnet3_tx_queue *tq, struct vmxnet3_adapter *adapter) netif_stop_subqueue(adapter->netdev, (tq - adapter->tx_queue)); } +/* Check if capability is supported by UPT device or + * UPT is even requested + */ +bool +vmxnet3_check_ptcapability(u32 cap_supported, u32 cap) +{ + if (cap_supported & (1UL << VMXNET3_DCR_ERROR) || + cap_supported & (1UL << cap)) { + return true; + } + + return false; +} + /* * Check the link state. This may start or stop the tx queue. @@ -571,6 +585,7 @@ vmxnet3_rq_alloc_rx_buf(struct vmxnet3_rx_queue *rq, u32 ring_idx, rbi = rbi_base + ring->next2fill; gd = ring->base + ring->next2fill; + rbi->comp_state = VMXNET3_RXD_COMP_PENDING; if (rbi->buf_type == VMXNET3_RX_BUF_SKB) { if (rbi->skb == NULL) { @@ -630,8 +645,10 @@ vmxnet3_rq_alloc_rx_buf(struct vmxnet3_rx_queue *rq, u32 ring_idx, /* Fill the last buffer but dont mark it ready, or else the * device will think that the queue is full */ - if (num_allocated == num_to_alloc) + if (num_allocated == num_to_alloc) { + rbi->comp_state = VMXNET3_RXD_COMP_DONE; break; + } gd->dword[2] |= cpu_to_le32(ring->gen << VMXNET3_RXD_GEN_SHIFT); num_allocated++; @@ -1044,6 +1061,23 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, } tq->stats.copy_skb_header++; } + if (unlikely(count > VMXNET3_MAX_TSO_TXD_PER_PKT)) { + /* tso pkts must not use more than + * VMXNET3_MAX_TSO_TXD_PER_PKT entries + */ + if (skb_linearize(skb) != 0) { + tq->stats.drop_too_many_frags++; + goto drop_pkt; + } + tq->stats.linearized++; + + /* recalculate the # of descriptors to use */ + count = VMXNET3_TXD_NEEDED(skb_headlen(skb)) + 1; + if (unlikely(count > VMXNET3_MAX_TSO_TXD_PER_PKT)) { + tq->stats.drop_too_many_frags++; + goto drop_pkt; + } + } if (skb->encapsulation) { vmxnet3_prepare_inner_tso(skb, &ctx); } else { @@ -1127,7 +1161,12 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, if (ctx.mss) { if (VMXNET3_VERSION_GE_4(adapter) && skb->encapsulation) { gdesc->txd.hlen = ctx.l4_offset + ctx.l4_hdr_size; - gdesc->txd.om = VMXNET3_OM_ENCAP; + if (VMXNET3_VERSION_GE_7(adapter)) { + gdesc->txd.om = VMXNET3_OM_TSO; + gdesc->txd.ext1 = 1; + } else { + gdesc->txd.om = VMXNET3_OM_ENCAP; + } gdesc->txd.msscof = ctx.mss; if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM) @@ -1144,8 +1183,15 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, skb->encapsulation) { gdesc->txd.hlen = ctx.l4_offset + ctx.l4_hdr_size; - gdesc->txd.om = VMXNET3_OM_ENCAP; - gdesc->txd.msscof = 0; /* Reserved */ + if (VMXNET3_VERSION_GE_7(adapter)) { + gdesc->txd.om = VMXNET3_OM_CSUM; + gdesc->txd.msscof = ctx.l4_offset + + skb->csum_offset; + gdesc->txd.ext1 = 1; + } else { + gdesc->txd.om = VMXNET3_OM_ENCAP; + gdesc->txd.msscof = 0; /* Reserved */ + } } else { gdesc->txd.hlen = ctx.l4_offset; gdesc->txd.om = VMXNET3_OM_CSUM; @@ -1193,7 +1239,7 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, if (tx_num_deferred >= le32_to_cpu(tq->shared->txThreshold)) { tq->shared->txNumDeferred = 0; VMXNET3_WRITE_BAR0_REG(adapter, - VMXNET3_REG_TXPROD + tq->qid * 8, + adapter->tx_prod_offset + tq->qid * 8, tq->tx_ring.next2fill); } @@ -1345,14 +1391,15 @@ static int vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq, struct vmxnet3_adapter *adapter, int quota) { - static const u32 rxprod_reg[2] = { - VMXNET3_REG_RXPROD, VMXNET3_REG_RXPROD2 + u32 rxprod_reg[2] = { + adapter->rx_prod_offset, adapter->rx_prod2_offset }; u32 num_pkts = 0; bool skip_page_frags = false; struct Vmxnet3_RxCompDesc *rcd; struct vmxnet3_rx_ctx *ctx = &rq->rx_ctx; u16 segCnt = 0, mss = 0; + int comp_offset, fill_offset; #ifdef __BIG_ENDIAN_BITFIELD struct Vmxnet3_RxDesc rxCmdDesc; struct Vmxnet3_RxCompDesc rxComp; @@ -1625,9 +1672,15 @@ not_lro: rcd_done: /* device may have skipped some rx descs */ - ring->next2comp = idx; - num_to_alloc = vmxnet3_cmd_ring_desc_avail(ring); ring = rq->rx_ring + ring_idx; + rbi->comp_state = VMXNET3_RXD_COMP_DONE; + + comp_offset = vmxnet3_cmd_ring_desc_avail(ring); + fill_offset = (idx > ring->next2fill ? 0 : ring->size) + + idx - ring->next2fill - 1; + if (!ring->isOutOfOrder || fill_offset >= comp_offset) + ring->next2comp = idx; + num_to_alloc = vmxnet3_cmd_ring_desc_avail(ring); /* Ensure that the writes to rxd->gen bits will be observed * after all other writes to rxd objects. @@ -1635,18 +1688,38 @@ rcd_done: dma_wmb(); while (num_to_alloc) { - vmxnet3_getRxDesc(rxd, &ring->base[ring->next2fill].rxd, - &rxCmdDesc); - BUG_ON(!rxd->addr); + rbi = rq->buf_info[ring_idx] + ring->next2fill; + if (!(adapter->dev_caps[0] & (1UL << VMXNET3_CAP_OOORX_COMP))) + goto refill_buf; + if (ring_idx == 0) { + /* ring0 Type1 buffers can get skipped; re-fill them */ + if (rbi->buf_type != VMXNET3_RX_BUF_SKB) + goto refill_buf; + } + if (rbi->comp_state == VMXNET3_RXD_COMP_DONE) { +refill_buf: + vmxnet3_getRxDesc(rxd, &ring->base[ring->next2fill].rxd, + &rxCmdDesc); + WARN_ON(!rxd->addr); + + /* Recv desc is ready to be used by the device */ + rxd->gen = ring->gen; + vmxnet3_cmd_ring_adv_next2fill(ring); + rbi->comp_state = VMXNET3_RXD_COMP_PENDING; + num_to_alloc--; + } else { + /* rx completion hasn't occurred */ + ring->isOutOfOrder = 1; + break; + } + } - /* Recv desc is ready to be used by the device */ - rxd->gen = ring->gen; - vmxnet3_cmd_ring_adv_next2fill(ring); - num_to_alloc--; + if (num_to_alloc == 0) { + ring->isOutOfOrder = 0; } /* if needed, update the register */ - if (unlikely(rq->shared->updateRxProd)) { + if (unlikely(rq->shared->updateRxProd) && (ring->next2fill & 0xf) == 0) { VMXNET3_WRITE_BAR0_REG(adapter, rxprod_reg[ring_idx] + rq->qid * 8, ring->next2fill); @@ -1810,6 +1883,7 @@ vmxnet3_rq_init(struct vmxnet3_rx_queue *rq, memset(rq->rx_ring[i].base, 0, rq->rx_ring[i].size * sizeof(struct Vmxnet3_RxDesc)); rq->rx_ring[i].gen = VMXNET3_INIT_GEN; + rq->rx_ring[i].isOutOfOrder = 0; } if (vmxnet3_rq_alloc_rx_buf(rq, 0, rq->rx_ring[0].size - 1, adapter) == 0) { @@ -2000,8 +2074,17 @@ vmxnet3_poll_rx_only(struct napi_struct *napi, int budget) rxd_done = vmxnet3_rq_rx_complete(rq, adapter, budget); if (rxd_done < budget) { + struct Vmxnet3_RxCompDesc *rcd; +#ifdef __BIG_ENDIAN_BITFIELD + struct Vmxnet3_RxCompDesc rxComp; +#endif napi_complete_done(napi, rxd_done); vmxnet3_enable_intr(adapter, rq->comp_ring.intr_idx); + /* after unmasking the interrupt, check if any descriptors were completed */ + vmxnet3_getRxComp(rcd, &rq->comp_ring.base[rq->comp_ring.next2proc].rcd, + &rxComp); + if (rcd->gen == rq->comp_ring.gen && napi_reschedule(napi)) + vmxnet3_disable_intr(adapter, rq->comp_ring.intr_idx); } return rxd_done; } @@ -2627,6 +2710,23 @@ vmxnet3_setup_driver_shared(struct vmxnet3_adapter *adapter) } static void +vmxnet3_init_bufsize(struct vmxnet3_adapter *adapter) +{ + struct Vmxnet3_DriverShared *shared = adapter->shared; + union Vmxnet3_CmdInfo *cmdInfo = &shared->cu.cmdInfo; + unsigned long flags; + + if (!VMXNET3_VERSION_GE_7(adapter)) + return; + + cmdInfo->ringBufSize = adapter->ringBufSize; + spin_lock_irqsave(&adapter->cmd_lock, flags); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, + VMXNET3_CMD_SET_RING_BUFFER_SIZE); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); +} + +static void vmxnet3_init_coalesce(struct vmxnet3_adapter *adapter) { struct Vmxnet3_DriverShared *shared = adapter->shared; @@ -2671,6 +2771,36 @@ vmxnet3_init_rssfields(struct vmxnet3_adapter *adapter) adapter->rss_fields = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD); } else { + if (VMXNET3_VERSION_GE_7(adapter)) { + if ((adapter->rss_fields & VMXNET3_RSS_FIELDS_UDPIP4 || + adapter->rss_fields & VMXNET3_RSS_FIELDS_UDPIP6) && + vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_UDP_RSS)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_UDP_RSS; + } else { + adapter->dev_caps[0] &= ~(1UL << VMXNET3_CAP_UDP_RSS); + } + + if ((adapter->rss_fields & VMXNET3_RSS_FIELDS_ESPIP4) && + vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_ESP_RSS_IPV4)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_ESP_RSS_IPV4; + } else { + adapter->dev_caps[0] &= ~(1UL << VMXNET3_CAP_ESP_RSS_IPV4); + } + + if ((adapter->rss_fields & VMXNET3_RSS_FIELDS_ESPIP6) && + vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_ESP_RSS_IPV6)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_ESP_RSS_IPV6; + } else { + adapter->dev_caps[0] &= ~(1UL << VMXNET3_CAP_ESP_RSS_IPV6); + } + + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_DCR, adapter->dev_caps[0]); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, VMXNET3_CMD_GET_DCR0_REG); + adapter->dev_caps[0] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD); + } cmdInfo->setRssFields = adapter->rss_fields; VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, VMXNET3_CMD_SET_RSS_FIELDS); @@ -2734,14 +2864,15 @@ vmxnet3_activate_dev(struct vmxnet3_adapter *adapter) goto activate_err; } + vmxnet3_init_bufsize(adapter); vmxnet3_init_coalesce(adapter); vmxnet3_init_rssfields(adapter); for (i = 0; i < adapter->num_rx_queues; i++) { VMXNET3_WRITE_BAR0_REG(adapter, - VMXNET3_REG_RXPROD + i * VMXNET3_REG_ALIGN, + adapter->rx_prod_offset + i * VMXNET3_REG_ALIGN, adapter->rx_queue[i].rx_ring[0].next2fill); - VMXNET3_WRITE_BAR0_REG(adapter, (VMXNET3_REG_RXPROD2 + + VMXNET3_WRITE_BAR0_REG(adapter, (adapter->rx_prod2_offset + (i * VMXNET3_REG_ALIGN)), adapter->rx_queue[i].rx_ring[1].next2fill); } @@ -2907,19 +3038,29 @@ static void vmxnet3_adjust_rx_ring_size(struct vmxnet3_adapter *adapter) { size_t sz, i, ring0_size, ring1_size, comp_size; - if (adapter->netdev->mtu <= VMXNET3_MAX_SKB_BUF_SIZE - - VMXNET3_MAX_ETH_HDR_SIZE) { - adapter->skb_buf_size = adapter->netdev->mtu + - VMXNET3_MAX_ETH_HDR_SIZE; - if (adapter->skb_buf_size < VMXNET3_MIN_T0_BUF_SIZE) - adapter->skb_buf_size = VMXNET3_MIN_T0_BUF_SIZE; - - adapter->rx_buf_per_pkt = 1; + /* With version7 ring1 will have only T0 buffers */ + if (!VMXNET3_VERSION_GE_7(adapter)) { + if (adapter->netdev->mtu <= VMXNET3_MAX_SKB_BUF_SIZE - + VMXNET3_MAX_ETH_HDR_SIZE) { + adapter->skb_buf_size = adapter->netdev->mtu + + VMXNET3_MAX_ETH_HDR_SIZE; + if (adapter->skb_buf_size < VMXNET3_MIN_T0_BUF_SIZE) + adapter->skb_buf_size = VMXNET3_MIN_T0_BUF_SIZE; + + adapter->rx_buf_per_pkt = 1; + } else { + adapter->skb_buf_size = VMXNET3_MAX_SKB_BUF_SIZE; + sz = adapter->netdev->mtu - VMXNET3_MAX_SKB_BUF_SIZE + + VMXNET3_MAX_ETH_HDR_SIZE; + adapter->rx_buf_per_pkt = 1 + (sz + PAGE_SIZE - 1) / PAGE_SIZE; + } } else { - adapter->skb_buf_size = VMXNET3_MAX_SKB_BUF_SIZE; - sz = adapter->netdev->mtu - VMXNET3_MAX_SKB_BUF_SIZE + - VMXNET3_MAX_ETH_HDR_SIZE; - adapter->rx_buf_per_pkt = 1 + (sz + PAGE_SIZE - 1) / PAGE_SIZE; + adapter->skb_buf_size = min((int)adapter->netdev->mtu + VMXNET3_MAX_ETH_HDR_SIZE, + VMXNET3_MAX_SKB_BUF_SIZE); + adapter->rx_buf_per_pkt = 1; + adapter->ringBufSize.ring1BufSizeType0 = cpu_to_le16(adapter->skb_buf_size); + adapter->ringBufSize.ring1BufSizeType1 = 0; + adapter->ringBufSize.ring2BufSizeType1 = cpu_to_le16(PAGE_SIZE); } /* @@ -2935,6 +3076,11 @@ vmxnet3_adjust_rx_ring_size(struct vmxnet3_adapter *adapter) ring1_size = (ring1_size + sz - 1) / sz * sz; ring1_size = min_t(u32, ring1_size, VMXNET3_RX_RING2_MAX_SIZE / sz * sz); + /* For v7 and later, keep ring size power of 2 for UPT */ + if (VMXNET3_VERSION_GE_7(adapter)) { + ring0_size = rounddown_pow_of_two(ring0_size); + ring1_size = rounddown_pow_of_two(ring1_size); + } comp_size = ring0_size + ring1_size; for (i = 0; i < adapter->num_rx_queues; i++) { @@ -3185,6 +3331,47 @@ vmxnet3_declare_features(struct vmxnet3_adapter *adapter) NETIF_F_GSO_UDP_TUNNEL_CSUM; } + if (VMXNET3_VERSION_GE_7(adapter)) { + unsigned long flags; + + if (vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_GENEVE_CHECKSUM_OFFLOAD)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_GENEVE_CHECKSUM_OFFLOAD; + } + if (vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_VXLAN_CHECKSUM_OFFLOAD)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_VXLAN_CHECKSUM_OFFLOAD; + } + if (vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_GENEVE_TSO)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_GENEVE_TSO; + } + if (vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_VXLAN_TSO)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_VXLAN_TSO; + } + if (vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_GENEVE_OUTER_CHECKSUM_OFFLOAD)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_GENEVE_OUTER_CHECKSUM_OFFLOAD; + } + if (vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_VXLAN_OUTER_CHECKSUM_OFFLOAD)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_VXLAN_OUTER_CHECKSUM_OFFLOAD; + } + + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_DCR, adapter->dev_caps[0]); + spin_lock_irqsave(&adapter->cmd_lock, flags); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, VMXNET3_CMD_GET_DCR0_REG); + adapter->dev_caps[0] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + + if (!(adapter->dev_caps[0] & (1UL << VMXNET3_CAP_GENEVE_OUTER_CHECKSUM_OFFLOAD)) && + !(adapter->dev_caps[0] & (1UL << VMXNET3_CAP_VXLAN_OUTER_CHECKSUM_OFFLOAD))) { + netdev->hw_enc_features &= ~NETIF_F_GSO_UDP_TUNNEL_CSUM; + netdev->features &= ~NETIF_F_GSO_UDP_TUNNEL_CSUM; + } + } + netdev->vlan_features = netdev->hw_features & ~(NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX); @@ -3472,7 +3659,12 @@ vmxnet3_probe_device(struct pci_dev *pdev, goto err_alloc_pci; ver = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_VRRS); - if (ver & (1 << VMXNET3_REV_6)) { + if (ver & (1 << VMXNET3_REV_7)) { + VMXNET3_WRITE_BAR1_REG(adapter, + VMXNET3_REG_VRRS, + 1 << VMXNET3_REV_7); + adapter->version = VMXNET3_REV_7 + 1; + } else if (ver & (1 << VMXNET3_REV_6)) { VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_VRRS, 1 << VMXNET3_REV_6); @@ -3520,6 +3712,39 @@ vmxnet3_probe_device(struct pci_dev *pdev, goto err_ver; } + if (VMXNET3_VERSION_GE_7(adapter)) { + adapter->devcap_supported[0] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_DCR); + adapter->ptcap_supported[0] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_PTCR); + if (adapter->devcap_supported[0] & (1UL << VMXNET3_CAP_LARGE_BAR)) { + adapter->dev_caps[0] = adapter->devcap_supported[0] & + (1UL << VMXNET3_CAP_LARGE_BAR); + } + if (!(adapter->ptcap_supported[0] & (1UL << VMXNET3_DCR_ERROR)) && + adapter->ptcap_supported[0] & (1UL << VMXNET3_CAP_OOORX_COMP) && + adapter->devcap_supported[0] & (1UL << VMXNET3_CAP_OOORX_COMP)) { + adapter->dev_caps[0] |= adapter->devcap_supported[0] & + (1UL << VMXNET3_CAP_OOORX_COMP); + } + if (adapter->dev_caps[0]) + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_DCR, adapter->dev_caps[0]); + + spin_lock_irqsave(&adapter->cmd_lock, flags); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, VMXNET3_CMD_GET_DCR0_REG); + adapter->dev_caps[0] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + } + + if (VMXNET3_VERSION_GE_7(adapter) && + adapter->dev_caps[0] & (1UL << VMXNET3_CAP_LARGE_BAR)) { + adapter->tx_prod_offset = VMXNET3_REG_LB_TXPROD; + adapter->rx_prod_offset = VMXNET3_REG_LB_RXPROD; + adapter->rx_prod2_offset = VMXNET3_REG_LB_RXPROD2; + } else { + adapter->tx_prod_offset = VMXNET3_REG_TXPROD; + adapter->rx_prod_offset = VMXNET3_REG_RXPROD; + adapter->rx_prod2_offset = VMXNET3_REG_RXPROD2; + } + if (VMXNET3_VERSION_GE_6(adapter)) { spin_lock_irqsave(&adapter->cmd_lock, flags); VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, diff --git a/drivers/net/vmxnet3/vmxnet3_ethtool.c b/drivers/net/vmxnet3/vmxnet3_ethtool.c index 3172d46c0335..ce3993282c0f 100644 --- a/drivers/net/vmxnet3/vmxnet3_ethtool.c +++ b/drivers/net/vmxnet3/vmxnet3_ethtool.c @@ -1,7 +1,7 @@ /* * Linux driver for VMware's vmxnet3 ethernet NIC. * - * Copyright (C) 2008-2021, VMware, Inc. All Rights Reserved. + * Copyright (C) 2008-2022, VMware, Inc. All Rights Reserved. * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by the @@ -298,7 +298,7 @@ netdev_features_t vmxnet3_features_check(struct sk_buff *skb, return features; } -static void vmxnet3_enable_encap_offloads(struct net_device *netdev) +static void vmxnet3_enable_encap_offloads(struct net_device *netdev, netdev_features_t features) { struct vmxnet3_adapter *adapter = netdev_priv(netdev); @@ -306,8 +306,50 @@ static void vmxnet3_enable_encap_offloads(struct net_device *netdev) netdev->hw_enc_features |= NETIF_F_SG | NETIF_F_RXCSUM | NETIF_F_HW_CSUM | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_TSO | NETIF_F_TSO6 | - NETIF_F_LRO | NETIF_F_GSO_UDP_TUNNEL | - NETIF_F_GSO_UDP_TUNNEL_CSUM; + NETIF_F_LRO; + if (features & NETIF_F_GSO_UDP_TUNNEL) + netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL; + if (features & NETIF_F_GSO_UDP_TUNNEL_CSUM) + netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL_CSUM; + } + if (VMXNET3_VERSION_GE_7(adapter)) { + unsigned long flags; + + if (vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_GENEVE_CHECKSUM_OFFLOAD)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_GENEVE_CHECKSUM_OFFLOAD; + } + if (vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_VXLAN_CHECKSUM_OFFLOAD)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_VXLAN_CHECKSUM_OFFLOAD; + } + if (vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_GENEVE_TSO)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_GENEVE_TSO; + } + if (vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_VXLAN_TSO)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_VXLAN_TSO; + } + if (vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_GENEVE_OUTER_CHECKSUM_OFFLOAD)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_GENEVE_OUTER_CHECKSUM_OFFLOAD; + } + if (vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_VXLAN_OUTER_CHECKSUM_OFFLOAD)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_VXLAN_OUTER_CHECKSUM_OFFLOAD; + } + + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_DCR, adapter->dev_caps[0]); + spin_lock_irqsave(&adapter->cmd_lock, flags); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, VMXNET3_CMD_GET_DCR0_REG); + adapter->dev_caps[0] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + + if (!(adapter->dev_caps[0] & (1UL << VMXNET3_CAP_GENEVE_OUTER_CHECKSUM_OFFLOAD)) && + !(adapter->dev_caps[0] & (1UL << VMXNET3_CAP_VXLAN_OUTER_CHECKSUM_OFFLOAD))) { + netdev->hw_enc_features &= ~NETIF_F_GSO_UDP_TUNNEL_CSUM; + } } } @@ -322,6 +364,22 @@ static void vmxnet3_disable_encap_offloads(struct net_device *netdev) NETIF_F_LRO | NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_UDP_TUNNEL_CSUM); } + if (VMXNET3_VERSION_GE_7(adapter)) { + unsigned long flags; + + adapter->dev_caps[0] &= ~(1UL << VMXNET3_CAP_GENEVE_CHECKSUM_OFFLOAD | + 1UL << VMXNET3_CAP_VXLAN_CHECKSUM_OFFLOAD | + 1UL << VMXNET3_CAP_GENEVE_TSO | + 1UL << VMXNET3_CAP_VXLAN_TSO | + 1UL << VMXNET3_CAP_GENEVE_OUTER_CHECKSUM_OFFLOAD | + 1UL << VMXNET3_CAP_VXLAN_OUTER_CHECKSUM_OFFLOAD); + + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_DCR, adapter->dev_caps[0]); + spin_lock_irqsave(&adapter->cmd_lock, flags); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, VMXNET3_CMD_GET_DCR0_REG); + adapter->dev_caps[0] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + } } int vmxnet3_set_features(struct net_device *netdev, netdev_features_t features) @@ -357,8 +415,8 @@ int vmxnet3_set_features(struct net_device *netdev, netdev_features_t features) adapter->shared->devRead.misc.uptFeatures &= ~UPT1_F_RXVLAN; - if ((features & tun_offload_mask) != 0 && !udp_tun_enabled) { - vmxnet3_enable_encap_offloads(netdev); + if ((features & tun_offload_mask) != 0) { + vmxnet3_enable_encap_offloads(netdev, features); adapter->shared->devRead.misc.uptFeatures |= UPT1_F_RXINNEROFLD; } else if ((features & tun_offload_mask) == 0 && @@ -462,7 +520,7 @@ vmxnet3_get_regs(struct net_device *netdev, struct ethtool_regs *regs, void *p) for (i = 0; i < adapter->num_tx_queues; i++) { struct vmxnet3_tx_queue *tq = &adapter->tx_queue[i]; - buf[j++] = VMXNET3_READ_BAR0_REG(adapter, VMXNET3_REG_TXPROD + + buf[j++] = VMXNET3_READ_BAR0_REG(adapter, adapter->tx_prod_offset + i * VMXNET3_REG_ALIGN); buf[j++] = VMXNET3_GET_ADDR_LO(tq->tx_ring.basePA); @@ -490,9 +548,9 @@ vmxnet3_get_regs(struct net_device *netdev, struct ethtool_regs *regs, void *p) for (i = 0; i < adapter->num_rx_queues; i++) { struct vmxnet3_rx_queue *rq = &adapter->rx_queue[i]; - buf[j++] = VMXNET3_READ_BAR0_REG(adapter, VMXNET3_REG_RXPROD + + buf[j++] = VMXNET3_READ_BAR0_REG(adapter, adapter->rx_prod_offset + i * VMXNET3_REG_ALIGN); - buf[j++] = VMXNET3_READ_BAR0_REG(adapter, VMXNET3_REG_RXPROD2 + + buf[j++] = VMXNET3_READ_BAR0_REG(adapter, adapter->rx_prod2_offset + i * VMXNET3_REG_ALIGN); buf[j++] = VMXNET3_GET_ADDR_LO(rq->rx_ring[0].basePA); @@ -660,6 +718,13 @@ vmxnet3_set_ringparam(struct net_device *netdev, new_rx_ring2_size = min_t(u32, new_rx_ring2_size, VMXNET3_RX_RING2_MAX_SIZE); + /* For v7 and later, keep ring size power of 2 for UPT */ + if (VMXNET3_VERSION_GE_7(adapter)) { + new_tx_ring_size = rounddown_pow_of_two(new_tx_ring_size); + new_rx_ring_size = rounddown_pow_of_two(new_rx_ring_size); + new_rx_ring2_size = rounddown_pow_of_two(new_rx_ring2_size); + } + /* rx data ring buffer size has to be a multiple of * VMXNET3_RXDATA_DESC_SIZE_ALIGN */ @@ -913,6 +978,39 @@ vmxnet3_set_rss_hash_opt(struct net_device *netdev, union Vmxnet3_CmdInfo *cmdInfo = &shared->cu.cmdInfo; unsigned long flags; + if (VMXNET3_VERSION_GE_7(adapter)) { + if ((rss_fields & VMXNET3_RSS_FIELDS_UDPIP4 || + rss_fields & VMXNET3_RSS_FIELDS_UDPIP6) && + vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_UDP_RSS)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_UDP_RSS; + } else { + adapter->dev_caps[0] &= ~(1UL << VMXNET3_CAP_UDP_RSS); + } + if ((rss_fields & VMXNET3_RSS_FIELDS_ESPIP4) && + vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_ESP_RSS_IPV4)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_ESP_RSS_IPV4; + } else { + adapter->dev_caps[0] &= ~(1UL << VMXNET3_CAP_ESP_RSS_IPV4); + } + if ((rss_fields & VMXNET3_RSS_FIELDS_ESPIP6) && + vmxnet3_check_ptcapability(adapter->ptcap_supported[0], + VMXNET3_CAP_ESP_RSS_IPV6)) { + adapter->dev_caps[0] |= 1UL << VMXNET3_CAP_ESP_RSS_IPV6; + } else { + adapter->dev_caps[0] &= ~(1UL << VMXNET3_CAP_ESP_RSS_IPV6); + } + + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_DCR, + adapter->dev_caps[0]); + spin_lock_irqsave(&adapter->cmd_lock, flags); + VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, + VMXNET3_CMD_GET_DCR0_REG); + adapter->dev_caps[0] = VMXNET3_READ_BAR1_REG(adapter, + VMXNET3_REG_CMD); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); + } spin_lock_irqsave(&adapter->cmd_lock, flags); cmdInfo->setRssFields = rss_fields; VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h index 7027ff483fa5..3367db23aa13 100644 --- a/drivers/net/vmxnet3/vmxnet3_int.h +++ b/drivers/net/vmxnet3/vmxnet3_int.h @@ -1,7 +1,7 @@ /* * Linux driver for VMware's vmxnet3 ethernet NIC. * - * Copyright (C) 2008-2021, VMware, Inc. All Rights Reserved. + * Copyright (C) 2008-2022, VMware, Inc. All Rights Reserved. * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by the @@ -69,18 +69,19 @@ /* * Version numbers */ -#define VMXNET3_DRIVER_VERSION_STRING "1.6.0.0-k" +#define VMXNET3_DRIVER_VERSION_STRING "1.7.0.0-k" /* Each byte of this 32-bit integer encodes a version number in * VMXNET3_DRIVER_VERSION_STRING. */ -#define VMXNET3_DRIVER_VERSION_NUM 0x01060000 +#define VMXNET3_DRIVER_VERSION_NUM 0x01070000 #if defined(CONFIG_PCI_MSI) /* RSS only makes sense if MSI-X is supported. */ #define VMXNET3_RSS #endif +#define VMXNET3_REV_7 6 /* Vmxnet3 Rev. 7 */ #define VMXNET3_REV_6 5 /* Vmxnet3 Rev. 6 */ #define VMXNET3_REV_5 4 /* Vmxnet3 Rev. 5 */ #define VMXNET3_REV_4 3 /* Vmxnet3 Rev. 4 */ @@ -135,6 +136,7 @@ struct vmxnet3_cmd_ring { u32 next2fill; u32 next2comp; u8 gen; + u8 isOutOfOrder; dma_addr_t basePA; }; @@ -259,9 +261,13 @@ enum vmxnet3_rx_buf_type { VMXNET3_RX_BUF_PAGE = 2 }; +#define VMXNET3_RXD_COMP_PENDING 0 +#define VMXNET3_RXD_COMP_DONE 1 + struct vmxnet3_rx_buf_info { enum vmxnet3_rx_buf_type buf_type; u16 len; + u8 comp_state; union { struct sk_buff *skb; struct page *page; @@ -402,6 +408,13 @@ struct vmxnet3_adapter { dma_addr_t pm_conf_pa; dma_addr_t rss_conf_pa; bool queuesExtEnabled; + struct Vmxnet3_RingBufferSize ringBufSize; + u32 devcap_supported[8]; + u32 ptcap_supported[8]; + u32 dev_caps[8]; + u16 tx_prod_offset; + u16 rx_prod_offset; + u16 rx_prod2_offset; }; #define VMXNET3_WRITE_BAR0_REG(adapter, reg, val) \ @@ -431,11 +444,13 @@ struct vmxnet3_adapter { (adapter->version >= VMXNET3_REV_5 + 1) #define VMXNET3_VERSION_GE_6(adapter) \ (adapter->version >= VMXNET3_REV_6 + 1) +#define VMXNET3_VERSION_GE_7(adapter) \ + (adapter->version >= VMXNET3_REV_7 + 1) /* must be a multiple of VMXNET3_RING_SIZE_ALIGN */ #define VMXNET3_DEF_TX_RING_SIZE 512 #define VMXNET3_DEF_RX_RING_SIZE 1024 -#define VMXNET3_DEF_RX_RING2_SIZE 256 +#define VMXNET3_DEF_RX_RING2_SIZE 512 #define VMXNET3_DEF_RXDATA_DESC_SIZE 128 @@ -494,6 +509,7 @@ void vmxnet3_set_ethtool_ops(struct net_device *netdev); void vmxnet3_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats); +bool vmxnet3_check_ptcapability(u32 cap_supported, u32 cap); extern char vmxnet3_driver_name[]; #endif diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index cfc30ce4c6e1..40445a12c682 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -814,8 +814,8 @@ static void vrf_rt6_release(struct net_device *dev, struct net_vrf *vrf) */ if (rt6) { dst = &rt6->dst; - dev_replace_track(dst->dev, net->loopback_dev, - &dst->dev_tracker, GFP_KERNEL); + netdev_ref_replace(dst->dev, net->loopback_dev, + &dst->dev_tracker, GFP_KERNEL); dst->dev = net->loopback_dev; dst_release(dst); } @@ -1061,8 +1061,8 @@ static void vrf_rtable_release(struct net_device *dev, struct net_vrf *vrf) */ if (rth) { dst = &rth->dst; - dev_replace_track(dst->dev, net->loopback_dev, - &dst->dev_tracker, GFP_KERNEL); + netdev_ref_replace(dst->dev, net->loopback_dev, + &dst->dev_tracker, GFP_KERNEL); dst->dev = net->loopback_dev; dst_release(dst); } diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index 265d4a0245e7..8b0710b576c2 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -2385,15 +2385,15 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, vxlan_snoop(dev, &loopback, eth_hdr(skb)->h_source, 0, vni); u64_stats_update_begin(&tx_stats->syncp); - tx_stats->tx_packets++; - tx_stats->tx_bytes += len; + u64_stats_inc(&tx_stats->tx_packets); + u64_stats_add(&tx_stats->tx_bytes, len); u64_stats_update_end(&tx_stats->syncp); vxlan_vnifilter_count(src_vxlan, vni, NULL, VXLAN_VNI_STATS_TX, len); if (__netif_rx(skb) == NET_RX_SUCCESS) { u64_stats_update_begin(&rx_stats->syncp); - rx_stats->rx_packets++; - rx_stats->rx_bytes += len; + u64_stats_inc(&rx_stats->rx_packets); + u64_stats_add(&rx_stats->rx_bytes, len); u64_stats_update_end(&rx_stats->syncp); vxlan_vnifilter_count(dst_vxlan, vni, NULL, VXLAN_VNI_STATS_RX, len); diff --git a/drivers/net/wan/farsync.h b/drivers/net/wan/farsync.h index 5f43568a9715..63908dbbb02d 100644 --- a/drivers/net/wan/farsync.h +++ b/drivers/net/wan/farsync.h @@ -43,7 +43,7 @@ * This version number is incremented with each official release of the * package and is a simplified number for normal user reference. * Individual files are tracked by the version control system and may - * have individual versions (or IDs) that move much faster than the + * have individual versions (or IDs) that move much faster than * the release version as individual updates are tracked. */ #define FST_USER_VERSION "1.04" diff --git a/drivers/net/wireguard/receive.c b/drivers/net/wireguard/receive.c index 7b8df406c773..7135d51d2d87 100644 --- a/drivers/net/wireguard/receive.c +++ b/drivers/net/wireguard/receive.c @@ -19,15 +19,8 @@ /* Must be called with bh disabled. */ static void update_rx_stats(struct wg_peer *peer, size_t len) { - struct pcpu_sw_netstats *tstats = - get_cpu_ptr(peer->device->dev->tstats); - - u64_stats_update_begin(&tstats->syncp); - ++tstats->rx_packets; - tstats->rx_bytes += len; + dev_sw_netstats_rx_add(peer->device->dev, len); peer->rx_bytes += len; - u64_stats_update_end(&tstats->syncp); - put_cpu_ptr(tstats); } #define SKB_TYPE_LE32(skb) (((struct message_header *)(skb)->data)->type) diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 2f746eb64507..bd408d260e9c 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -290,8 +290,7 @@ static inline int hwsim_net_set_netgroup(struct net *net) { struct hwsim_net *hwsim_net = net_generic(net, hwsim_net_id); - hwsim_net->netgroup = ida_simple_get(&hwsim_netgroup_ida, - 0, 0, GFP_KERNEL); + hwsim_net->netgroup = ida_alloc(&hwsim_netgroup_ida, GFP_KERNEL); return hwsim_net->netgroup >= 0 ? 0 : -ENOMEM; } @@ -4733,7 +4732,7 @@ static void __net_exit hwsim_exit_net(struct net *net) NULL); } - ida_simple_remove(&hwsim_netgroup_ida, hwsim_net_get_netgroup(net)); + ida_free(&hwsim_netgroup_ida, hwsim_net_get_netgroup(net)); } static struct pernet_operations hwsim_net_ops = { diff --git a/drivers/net/wireless/microchip/wilc1000/cfg80211.c b/drivers/net/wireless/microchip/wilc1000/cfg80211.c index 8d8378bafd9b..1ac4684fab25 100644 --- a/drivers/net/wireless/microchip/wilc1000/cfg80211.c +++ b/drivers/net/wireless/microchip/wilc1000/cfg80211.c @@ -20,9 +20,11 @@ static const struct ieee80211_txrx_stypes wilc_wfi_cfg80211_mgmt_types[NUM_NL80211_IFTYPES] = { [NL80211_IFTYPE_STATION] = { - .tx = 0xffff, + .tx = BIT(IEEE80211_STYPE_ACTION >> 4) | + BIT(IEEE80211_STYPE_AUTH >> 4), .rx = BIT(IEEE80211_STYPE_ACTION >> 4) | - BIT(IEEE80211_STYPE_PROBE_REQ >> 4) + BIT(IEEE80211_STYPE_PROBE_REQ >> 4) | + BIT(IEEE80211_STYPE_AUTH >> 4) }, [NL80211_IFTYPE_AP] = { .tx = 0xffff, @@ -305,6 +307,7 @@ static int connect(struct wiphy *wiphy, struct net_device *dev, int ret; u32 i; u8 security = WILC_FW_SEC_NO; + enum mfptype mfp_type = WILC_FW_MFP_NONE; enum authtype auth_type = WILC_FW_AUTH_ANY; u32 cipher_group; struct cfg80211_bss *bss; @@ -313,32 +316,9 @@ static int connect(struct wiphy *wiphy, struct net_device *dev, vif->connecting = true; - memset(priv->wep_key, 0, sizeof(priv->wep_key)); - memset(priv->wep_key_len, 0, sizeof(priv->wep_key_len)); - cipher_group = sme->crypto.cipher_group; if (cipher_group != 0) { - if (cipher_group == WLAN_CIPHER_SUITE_WEP40) { - security = WILC_FW_SEC_WEP; - - priv->wep_key_len[sme->key_idx] = sme->key_len; - memcpy(priv->wep_key[sme->key_idx], sme->key, - sme->key_len); - - wilc_set_wep_default_keyid(vif, sme->key_idx); - wilc_add_wep_key_bss_sta(vif, sme->key, sme->key_len, - sme->key_idx); - } else if (cipher_group == WLAN_CIPHER_SUITE_WEP104) { - security = WILC_FW_SEC_WEP_EXTENDED; - - priv->wep_key_len[sme->key_idx] = sme->key_len; - memcpy(priv->wep_key[sme->key_idx], sme->key, - sme->key_len); - - wilc_set_wep_default_keyid(vif, sme->key_idx); - wilc_add_wep_key_bss_sta(vif, sme->key, sme->key_len, - sme->key_idx); - } else if (sme->crypto.wpa_versions & NL80211_WPA_VERSION_2) { + if (sme->crypto.wpa_versions & NL80211_WPA_VERSION_2) { if (cipher_group == WLAN_CIPHER_SUITE_TKIP) security = WILC_FW_SEC_WPA2_TKIP; else @@ -373,8 +353,14 @@ static int connect(struct wiphy *wiphy, struct net_device *dev, auth_type = WILC_FW_AUTH_OPEN_SYSTEM; break; - case NL80211_AUTHTYPE_SHARED_KEY: - auth_type = WILC_FW_AUTH_SHARED_KEY; + case NL80211_AUTHTYPE_SAE: + auth_type = WILC_FW_AUTH_SAE; + if (sme->ssid_len) { + memcpy(vif->auth.ssid.ssid, sme->ssid, sme->ssid_len); + vif->auth.ssid.ssid_len = sme->ssid_len; + } + vif->auth.key_mgmt_suite = cpu_to_be32(sme->crypto.akm_suites[0]); + ether_addr_copy(vif->auth.bssid, sme->bssid); break; default: @@ -384,6 +370,10 @@ static int connect(struct wiphy *wiphy, struct net_device *dev, if (sme->crypto.n_akm_suites) { if (sme->crypto.akm_suites[0] == WLAN_AKM_SUITE_8021X) auth_type = WILC_FW_AUTH_IEEE8021; + else if (sme->crypto.akm_suites[0] == WLAN_AKM_SUITE_PSK_SHA256) + auth_type = WILC_FW_AUTH_OPEN_SYSTEM_SHA256; + else if (sme->crypto.akm_suites[0] == WLAN_AKM_SUITE_8021X_SHA256) + auth_type = WILC_FW_AUTH_IEE8021X_SHA256; } if (wfi_drv->usr_scan_req.scan_result) { @@ -427,6 +417,13 @@ static int connect(struct wiphy *wiphy, struct net_device *dev, wfi_drv->conn_info.arg = priv; wfi_drv->conn_info.param = join_params; + if (sme->mfp == NL80211_MFP_OPTIONAL) + mfp_type = WILC_FW_MFP_OPTIONAL; + else if (sme->mfp == NL80211_MFP_REQUIRED) + mfp_type = WILC_FW_MFP_REQUIRED; + + wfi_drv->conn_info.mfp_type = mfp_type; + ret = wilc_set_join_req(vif, bss->bssid, sme->ie, sme->ie_len); if (ret) { netdev_err(dev, "wilc_set_join_req(): Error\n"); @@ -487,14 +484,6 @@ static int disconnect(struct wiphy *wiphy, struct net_device *dev, return ret; } -static inline void wilc_wfi_cfg_copy_wep_info(struct wilc_priv *priv, - u8 key_index, - struct key_params *params) -{ - priv->wep_key_len[key_index] = params->key_len; - memcpy(priv->wep_key[key_index], params->key, params->key_len); -} - static int wilc_wfi_cfg_allocate_wpa_entry(struct wilc_priv *priv, u8 idx) { if (!priv->wilc_gtk[idx]) { @@ -514,6 +503,18 @@ static int wilc_wfi_cfg_allocate_wpa_entry(struct wilc_priv *priv, u8 idx) return 0; } +static int wilc_wfi_cfg_allocate_wpa_igtk_entry(struct wilc_priv *priv, u8 idx) +{ + idx -= 4; + if (!priv->wilc_igtk[idx]) { + priv->wilc_igtk[idx] = kzalloc(sizeof(*priv->wilc_igtk[idx]), + GFP_KERNEL); + if (!priv->wilc_igtk[idx]) + return -ENOMEM; + } + return 0; +} + static int wilc_wfi_cfg_copy_wpa_info(struct wilc_wfi_key *key_info, struct key_params *params) { @@ -550,35 +551,9 @@ static int add_key(struct wiphy *wiphy, struct net_device *netdev, u8 key_index, u8 op_mode; struct wilc_vif *vif = netdev_priv(netdev); struct wilc_priv *priv = &vif->priv; + struct wilc_wfi_key *key; switch (params->cipher) { - case WLAN_CIPHER_SUITE_WEP40: - case WLAN_CIPHER_SUITE_WEP104: - if (priv->wdev.iftype == NL80211_IFTYPE_AP) { - wilc_wfi_cfg_copy_wep_info(priv, key_index, params); - - if (params->cipher == WLAN_CIPHER_SUITE_WEP40) - mode = WILC_FW_SEC_WEP; - else - mode = WILC_FW_SEC_WEP_EXTENDED; - - ret = wilc_add_wep_key_bss_ap(vif, params->key, - params->key_len, - key_index, mode, - WILC_FW_AUTH_OPEN_SYSTEM); - break; - } - if (memcmp(params->key, priv->wep_key[key_index], - params->key_len)) { - wilc_wfi_cfg_copy_wep_info(priv, key_index, params); - - ret = wilc_add_wep_key_bss_sta(vif, params->key, - params->key_len, - key_index); - } - - break; - case WLAN_CIPHER_SUITE_TKIP: case WLAN_CIPHER_SUITE_CCMP: if (priv->wdev.iftype == NL80211_IFTYPE_AP || @@ -640,6 +615,26 @@ static int add_key(struct wiphy *wiphy, struct net_device *netdev, u8 key_index, key_index); break; + case WLAN_CIPHER_SUITE_AES_CMAC: + ret = wilc_wfi_cfg_allocate_wpa_igtk_entry(priv, key_index); + if (ret) + return -ENOMEM; + + key = priv->wilc_igtk[key_index - 4]; + ret = wilc_wfi_cfg_copy_wpa_info(key, params); + if (ret) + return -ENOMEM; + + if (priv->wdev.iftype == NL80211_IFTYPE_AP || + priv->wdev.iftype == NL80211_IFTYPE_P2P_GO) + op_mode = WILC_AP_MODE; + else + op_mode = WILC_STATION_MODE; + + ret = wilc_add_igtk(vif, params->key, keylen, params->seq, + params->seq_len, mac_addr, op_mode, + key_index); + break; default: netdev_err(netdev, "%s: Unsupported cipher\n", __func__); @@ -657,30 +652,34 @@ static int del_key(struct wiphy *wiphy, struct net_device *netdev, struct wilc_vif *vif = netdev_priv(netdev); struct wilc_priv *priv = &vif->priv; - if (priv->wilc_gtk[key_index]) { - kfree(priv->wilc_gtk[key_index]->key); - priv->wilc_gtk[key_index]->key = NULL; - kfree(priv->wilc_gtk[key_index]->seq); - priv->wilc_gtk[key_index]->seq = NULL; - - kfree(priv->wilc_gtk[key_index]); - priv->wilc_gtk[key_index] = NULL; - } - - if (priv->wilc_ptk[key_index]) { - kfree(priv->wilc_ptk[key_index]->key); - priv->wilc_ptk[key_index]->key = NULL; - kfree(priv->wilc_ptk[key_index]->seq); - priv->wilc_ptk[key_index]->seq = NULL; - kfree(priv->wilc_ptk[key_index]); - priv->wilc_ptk[key_index] = NULL; - } - - if (key_index <= 3 && priv->wep_key_len[key_index]) { - memset(priv->wep_key[key_index], 0, - priv->wep_key_len[key_index]); - priv->wep_key_len[key_index] = 0; - wilc_remove_wep_key(vif, key_index); + if (!pairwise && (key_index == 4 || key_index == 5)) { + key_index -= 4; + if (priv->wilc_igtk[key_index]) { + kfree(priv->wilc_igtk[key_index]->key); + priv->wilc_igtk[key_index]->key = NULL; + kfree(priv->wilc_igtk[key_index]->seq); + priv->wilc_igtk[key_index]->seq = NULL; + kfree(priv->wilc_igtk[key_index]); + priv->wilc_igtk[key_index] = NULL; + } + } else { + if (priv->wilc_gtk[key_index]) { + kfree(priv->wilc_gtk[key_index]->key); + priv->wilc_gtk[key_index]->key = NULL; + kfree(priv->wilc_gtk[key_index]->seq); + priv->wilc_gtk[key_index]->seq = NULL; + + kfree(priv->wilc_gtk[key_index]); + priv->wilc_gtk[key_index] = NULL; + } + if (priv->wilc_ptk[key_index]) { + kfree(priv->wilc_ptk[key_index]->key); + priv->wilc_ptk[key_index]->key = NULL; + kfree(priv->wilc_ptk[key_index]->seq); + priv->wilc_ptk[key_index]->seq = NULL; + kfree(priv->wilc_ptk[key_index]); + priv->wilc_ptk[key_index] = NULL; + } } return 0; @@ -695,11 +694,20 @@ static int get_key(struct wiphy *wiphy, struct net_device *netdev, u8 key_index, struct key_params key_params; if (!pairwise) { - key_params.key = priv->wilc_gtk[key_index]->key; - key_params.cipher = priv->wilc_gtk[key_index]->cipher; - key_params.key_len = priv->wilc_gtk[key_index]->key_len; - key_params.seq = priv->wilc_gtk[key_index]->seq; - key_params.seq_len = priv->wilc_gtk[key_index]->seq_len; + if (key_index == 4 || key_index == 5) { + key_index -= 4; + key_params.key = priv->wilc_igtk[key_index]->key; + key_params.cipher = priv->wilc_igtk[key_index]->cipher; + key_params.key_len = priv->wilc_igtk[key_index]->key_len; + key_params.seq = priv->wilc_igtk[key_index]->seq; + key_params.seq_len = priv->wilc_igtk[key_index]->seq_len; + } else { + key_params.key = priv->wilc_gtk[key_index]->key; + key_params.cipher = priv->wilc_gtk[key_index]->cipher; + key_params.key_len = priv->wilc_gtk[key_index]->key_len; + key_params.seq = priv->wilc_gtk[key_index]->seq; + key_params.seq_len = priv->wilc_gtk[key_index]->seq_len; + } } else { key_params.key = priv->wilc_ptk[key_index]->key; key_params.cipher = priv->wilc_ptk[key_index]->cipher; @@ -713,14 +721,19 @@ static int get_key(struct wiphy *wiphy, struct net_device *netdev, u8 key_index, return 0; } +/* wiphy_new_nm() will WARNON if not present */ static int set_default_key(struct wiphy *wiphy, struct net_device *netdev, u8 key_index, bool unicast, bool multicast) { - struct wilc_vif *vif = netdev_priv(netdev); + return 0; +} - wilc_set_wep_default_keyid(vif, key_index); +static int set_default_mgmt_key(struct wiphy *wiphy, struct net_device *netdev, + u8 key_index) +{ + struct wilc_vif *vif = netdev_priv(netdev); - return 0; + return wilc_set_default_mgmt_key_index(vif, key_index); } static int get_station(struct wiphy *wiphy, struct net_device *dev, @@ -977,6 +990,18 @@ static inline void wilc_wfi_cfg_parse_ch_attr(u8 *buf, u32 len, u8 sta_ch) } } +bool wilc_wfi_mgmt_frame_rx(struct wilc_vif *vif, u8 *buff, u32 size) +{ + struct wilc *wl = vif->wilc; + struct wilc_priv *priv = &vif->priv; + int freq, ret; + + freq = ieee80211_channel_to_frequency(wl->op_ch, NL80211_BAND_2GHZ); + ret = cfg80211_rx_mgmt(&priv->wdev, freq, 0, buff, size, 0); + + return ret; +} + void wilc_wfi_p2p_rx(struct wilc_vif *vif, u8 *buff, u32 size) { struct wilc *wl = vif->wilc; @@ -1162,8 +1187,14 @@ static int mgmt_tx(struct wiphy *wiphy, goto out_txq_add_pkt; } - if (!ieee80211_is_public_action((struct ieee80211_hdr *)buf, len)) + if (!ieee80211_is_public_action((struct ieee80211_hdr *)buf, len)) { + if (chan) + wilc_set_mac_chnl_num(vif, chan->hw_value); + else + wilc_set_mac_chnl_num(vif, vif->wilc->op_ch); + goto out_set_timeout; + } d = (struct wilc_p2p_pub_act_frame *)(&mgmt->u.action); if (d->oui_type != WLAN_OUI_TYPE_WFA_P2P || @@ -1230,6 +1261,7 @@ void wilc_update_mgmt_frame_registrations(struct wiphy *wiphy, struct wilc_vif *vif = netdev_priv(wdev->netdev); u32 presp_bit = BIT(IEEE80211_STYPE_PROBE_REQ >> 4); u32 action_bit = BIT(IEEE80211_STYPE_ACTION >> 4); + u32 pauth_bit = BIT(IEEE80211_STYPE_AUTH >> 4); if (wl->initialized) { bool prev = vif->mgmt_reg_stypes & presp_bit; @@ -1243,10 +1275,26 @@ void wilc_update_mgmt_frame_registrations(struct wiphy *wiphy, if (now != prev) wilc_frame_register(vif, IEEE80211_STYPE_ACTION, now); + + prev = vif->mgmt_reg_stypes & pauth_bit; + now = upd->interface_stypes & pauth_bit; + if (now != prev) + wilc_frame_register(vif, IEEE80211_STYPE_AUTH, now); } vif->mgmt_reg_stypes = - upd->interface_stypes & (presp_bit | action_bit); + upd->interface_stypes & (presp_bit | action_bit | pauth_bit); +} + +static int external_auth(struct wiphy *wiphy, struct net_device *dev, + struct cfg80211_external_auth_params *auth) +{ + struct wilc_vif *vif = netdev_priv(dev); + + if (auth->status == WLAN_STATUS_SUCCESS) + wilc_set_external_auth_param(vif, auth); + + return 0; } static int set_cqm_rssi_config(struct wiphy *wiphy, struct net_device *dev, @@ -1647,6 +1695,7 @@ static const struct cfg80211_ops wilc_cfg80211_ops = { .del_key = del_key, .get_key = get_key, .set_default_key = set_default_key, + .set_default_mgmt_key = set_default_mgmt_key, .add_virtual_intf = add_virtual_intf, .del_virtual_intf = del_virtual_intf, .change_virtual_intf = change_virtual_intf, @@ -1662,6 +1711,7 @@ static const struct cfg80211_ops wilc_cfg80211_ops = { .change_bss = change_bss, .set_wiphy_params = set_wiphy_params, + .external_auth = external_auth, .set_pmksa = set_pmksa, .del_pmksa = del_pmksa, .flush_pmksa = flush_pmksa, @@ -1804,7 +1854,7 @@ struct wilc *wilc_create_wiphy(struct device *dev) BIT(NL80211_IFTYPE_P2P_GO) | BIT(NL80211_IFTYPE_P2P_CLIENT); wiphy->flags |= WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL; - + wiphy->features |= NL80211_FEATURE_SAE; set_wiphy_dev(wiphy, dev); wl->wiphy = wiphy; ret = wiphy_register(wiphy); diff --git a/drivers/net/wireless/microchip/wilc1000/fw.h b/drivers/net/wireless/microchip/wilc1000/fw.h index 1114530d03e4..5c5cac4aab02 100644 --- a/drivers/net/wireless/microchip/wilc1000/fw.h +++ b/drivers/net/wireless/microchip/wilc1000/fw.h @@ -41,21 +41,23 @@ struct wilc_drv_handler { u8 mode; } __packed; -struct wilc_wep_key { - u8 index; +struct wilc_sta_wpa_ptk { + u8 mac_addr[ETH_ALEN]; u8 key_len; u8 key[]; } __packed; -struct wilc_sta_wpa_ptk { +struct wilc_ap_wpa_ptk { u8 mac_addr[ETH_ALEN]; + u8 index; u8 key_len; u8 key[]; } __packed; -struct wilc_ap_wpa_ptk { - u8 mac_addr[ETH_ALEN]; +struct wilc_wpa_igtk { u8 index; + u8 pn_len; + u8 pn[6]; u8 key_len; u8 key[]; } __packed; @@ -116,4 +118,13 @@ struct wilc_join_bss_param { struct wilc_noa_opp_enable opp_en; }; } __packed; + +struct wilc_external_auth_param { + u8 action; + u8 bssid[ETH_ALEN]; + u8 ssid[IEEE80211_MAX_SSID_LEN]; + u8 ssid_len; + __le32 key_mgmt_suites; + __le16 status; +} __packed; #endif diff --git a/drivers/net/wireless/microchip/wilc1000/hif.c b/drivers/net/wireless/microchip/wilc1000/hif.c index 71b44cfe0dfc..4038a254465f 100644 --- a/drivers/net/wireless/microchip/wilc1000/hif.c +++ b/drivers/net/wireless/microchip/wilc1000/hif.c @@ -271,12 +271,19 @@ error: static int wilc_send_connect_wid(struct wilc_vif *vif) { int result = 0; - struct wid wid_list[4]; + struct wid wid_list[5]; u32 wid_cnt = 0; struct host_if_drv *hif_drv = vif->hif_drv; struct wilc_conn_info *conn_attr = &hif_drv->conn_info; struct wilc_join_bss_param *bss_param = conn_attr->param; + + wid_list[wid_cnt].id = WID_SET_MFP; + wid_list[wid_cnt].type = WID_CHAR; + wid_list[wid_cnt].size = sizeof(char); + wid_list[wid_cnt].val = (s8 *)&conn_attr->mfp_type; + wid_cnt++; + wid_list[wid_cnt].id = WID_INFO_ELEMENT_ASSOCIATE; wid_list[wid_cnt].type = WID_BIN_DATA; wid_list[wid_cnt].val = conn_attr->req_ies; @@ -306,7 +313,10 @@ static int wilc_send_connect_wid(struct wilc_vif *vif) netdev_err(vif->ndev, "failed to send config packet\n"); goto error; } else { - hif_drv->hif_state = HOST_IF_WAITING_CONN_RESP; + if (conn_attr->auth_type == WILC_FW_AUTH_SAE) + hif_drv->hif_state = HOST_IF_EXTERNAL_AUTH; + else + hif_drv->hif_state = HOST_IF_WAITING_CONN_RESP; } return 0; @@ -665,7 +675,12 @@ static void handle_rcvd_gnrl_async_info(struct work_struct *work) goto free_msg; } - if (hif_drv->hif_state == HOST_IF_WAITING_CONN_RESP) { + + if (hif_drv->hif_state == HOST_IF_EXTERNAL_AUTH) { + cfg80211_external_auth_request(vif->ndev, &vif->auth, + GFP_KERNEL); + hif_drv->hif_state = HOST_IF_WAITING_CONN_RESP; + } else if (hif_drv->hif_state == HOST_IF_WAITING_CONN_RESP) { host_int_parse_assoc_resp_info(vif, mac_info->status); } else if (mac_info->status == WILC_MAC_STATUS_DISCONNECTED) { if (hif_drv->hif_state == HOST_IF_CONNECTED) { @@ -710,7 +725,8 @@ int wilc_disconnect(struct wilc_vif *vif) } if (conn_info->conn_result) { - if (hif_drv->hif_state == HOST_IF_WAITING_CONN_RESP) + if (hif_drv->hif_state == HOST_IF_WAITING_CONN_RESP || + hif_drv->hif_state == HOST_IF_EXTERNAL_AUTH) del_timer(&hif_drv->connect_timer); conn_info->conn_result(CONN_DISCONN_EVENT_DISCONN_NOTIF, 0, @@ -986,6 +1002,31 @@ void wilc_set_wowlan_trigger(struct wilc_vif *vif, bool enabled) pr_err("Failed to send wowlan trigger config packet\n"); } +int wilc_set_external_auth_param(struct wilc_vif *vif, + struct cfg80211_external_auth_params *auth) +{ + int ret; + struct wid wid; + struct wilc_external_auth_param *param; + + wid.id = WID_EXTERNAL_AUTH_PARAM; + wid.type = WID_BIN_DATA; + wid.size = sizeof(*param); + param = kzalloc(sizeof(*param), GFP_KERNEL); + if (!param) + return -EINVAL; + + wid.val = (u8 *)param; + param->action = auth->action; + ether_addr_copy(param->bssid, auth->bssid); + memcpy(param->ssid, auth->ssid.ssid, auth->ssid.ssid_len); + param->ssid_len = auth->ssid.ssid_len; + ret = wilc_send_config_pkt(vif, WILC_SET_CFG, &wid, 1); + + kfree(param); + return ret; +} + static void handle_scan_timer(struct work_struct *work) { struct host_if_msg *msg = container_of(work, struct host_if_msg, work); @@ -1038,108 +1079,6 @@ static void timer_connect_cb(struct timer_list *t) kfree(msg); } -int wilc_remove_wep_key(struct wilc_vif *vif, u8 index) -{ - struct wid wid; - int result; - - wid.id = WID_REMOVE_WEP_KEY; - wid.type = WID_STR; - wid.size = sizeof(char); - wid.val = &index; - - result = wilc_send_config_pkt(vif, WILC_SET_CFG, &wid, 1); - if (result) - netdev_err(vif->ndev, - "Failed to send remove wep key config packet\n"); - return result; -} - -int wilc_set_wep_default_keyid(struct wilc_vif *vif, u8 index) -{ - struct wid wid; - int result; - - wid.id = WID_KEY_ID; - wid.type = WID_CHAR; - wid.size = sizeof(char); - wid.val = &index; - result = wilc_send_config_pkt(vif, WILC_SET_CFG, &wid, 1); - if (result) - netdev_err(vif->ndev, - "Failed to send wep default key config packet\n"); - - return result; -} - -int wilc_add_wep_key_bss_sta(struct wilc_vif *vif, const u8 *key, u8 len, - u8 index) -{ - struct wid wid; - int result; - struct wilc_wep_key *wep_key; - - wid.id = WID_ADD_WEP_KEY; - wid.type = WID_STR; - wid.size = sizeof(*wep_key) + len; - wep_key = kzalloc(wid.size, GFP_KERNEL); - if (!wep_key) - return -ENOMEM; - - wid.val = (u8 *)wep_key; - - wep_key->index = index; - wep_key->key_len = len; - memcpy(wep_key->key, key, len); - - result = wilc_send_config_pkt(vif, WILC_SET_CFG, &wid, 1); - if (result) - netdev_err(vif->ndev, - "Failed to add wep key config packet\n"); - - kfree(wep_key); - return result; -} - -int wilc_add_wep_key_bss_ap(struct wilc_vif *vif, const u8 *key, u8 len, - u8 index, u8 mode, enum authtype auth_type) -{ - struct wid wid_list[3]; - int result; - struct wilc_wep_key *wep_key; - - wid_list[0].id = WID_11I_MODE; - wid_list[0].type = WID_CHAR; - wid_list[0].size = sizeof(char); - wid_list[0].val = &mode; - - wid_list[1].id = WID_AUTH_TYPE; - wid_list[1].type = WID_CHAR; - wid_list[1].size = sizeof(char); - wid_list[1].val = (s8 *)&auth_type; - - wid_list[2].id = WID_WEP_KEY_VALUE; - wid_list[2].type = WID_STR; - wid_list[2].size = sizeof(*wep_key) + len; - wep_key = kzalloc(wid_list[2].size, GFP_KERNEL); - if (!wep_key) - return -ENOMEM; - - wid_list[2].val = (u8 *)wep_key; - - wep_key->index = index; - wep_key->key_len = len; - memcpy(wep_key->key, key, len); - result = wilc_send_config_pkt(vif, WILC_SET_CFG, wid_list, - ARRAY_SIZE(wid_list)); - if (result) - netdev_err(vif->ndev, - "Failed to add wep ap key config packet\n"); - - kfree(wep_key); - return result; -} - int wilc_add_ptk(struct wilc_vif *vif, const u8 *ptk, u8 ptk_key_len, const u8 *mac_addr, const u8 *rx_mic, const u8 *tx_mic, u8 mode, u8 cipher_mode, u8 index) @@ -1211,6 +1150,36 @@ int wilc_add_ptk(struct wilc_vif *vif, const u8 *ptk, u8 ptk_key_len, return result; } +int wilc_add_igtk(struct wilc_vif *vif, const u8 *igtk, u8 igtk_key_len, + const u8 *pn, u8 pn_len, const u8 *mac_addr, u8 mode, u8 index) +{ + int result = 0; + u8 t_key_len = igtk_key_len; + struct wid wid; + struct wilc_wpa_igtk *key_buf; + + key_buf = kzalloc(sizeof(*key_buf) + t_key_len, GFP_KERNEL); + if (!key_buf) + return -ENOMEM; + + key_buf->index = index; + + memcpy(&key_buf->pn[0], pn, pn_len); + key_buf->pn_len = pn_len; + + memcpy(&key_buf->key[0], igtk, igtk_key_len); + key_buf->key_len = t_key_len; + + wid.id = WID_ADD_IGTK; + wid.type = WID_STR; + wid.size = sizeof(*key_buf) + t_key_len; + wid.val = (s8 *)key_buf; + result = wilc_send_config_pkt(vif, WILC_SET_CFG, &wid, 1); + kfree(key_buf); + + return result; +} + int wilc_add_rx_gtk(struct wilc_vif *vif, const u8 *rx_gtk, u8 gtk_key_len, u8 index, u32 key_rsc_len, const u8 *key_rsc, const u8 *rx_mic, const u8 *tx_mic, u8 mode, @@ -1749,6 +1718,10 @@ void wilc_frame_register(struct wilc_vif *vif, u16 frame_type, bool reg) reg_frame.reg_id = WILC_FW_PROBE_REQ_IDX; break; + case IEEE80211_STYPE_AUTH: + reg_frame.reg_id = WILC_FW_AUTH_REQ_IDX; + break; + default: break; } @@ -1996,3 +1969,20 @@ int wilc_get_tx_power(struct wilc_vif *vif, u8 *tx_power) return wilc_send_config_pkt(vif, WILC_GET_CFG, &wid, 1); } + +int wilc_set_default_mgmt_key_index(struct wilc_vif *vif, u8 index) +{ + struct wid wid; + int result; + + wid.id = WID_DEFAULT_MGMT_KEY_ID; + wid.type = WID_CHAR; + wid.size = sizeof(char); + wid.val = &index; + result = wilc_send_config_pkt(vif, WILC_SET_CFG, &wid, 1); + if (result) + netdev_err(vif->ndev, + "Failed to send default mgmt key index\n"); + + return result; +} diff --git a/drivers/net/wireless/microchip/wilc1000/hif.h b/drivers/net/wireless/microchip/wilc1000/hif.h index 77616fc77575..d8dd94dcfe14 100644 --- a/drivers/net/wireless/microchip/wilc1000/hif.h +++ b/drivers/net/wireless/microchip/wilc1000/hif.h @@ -47,6 +47,7 @@ enum host_if_state { HOST_IF_WAITING_CONN_RESP = 3, HOST_IF_CONNECTED = 4, HOST_IF_P2P_LISTEN = 5, + HOST_IF_EXTERNAL_AUTH = 6, HOST_IF_FORCE_32BIT = 0xFFFFFFFF }; @@ -107,6 +108,7 @@ struct wilc_conn_info { u8 bssid[ETH_ALEN]; u8 security; enum authtype auth_type; + enum mfptype mfp_type; u8 ch; u8 *req_ies; size_t req_ies_len; @@ -151,15 +153,12 @@ struct host_if_drv { }; struct wilc_vif; -int wilc_remove_wep_key(struct wilc_vif *vif, u8 index); -int wilc_set_wep_default_keyid(struct wilc_vif *vif, u8 index); -int wilc_add_wep_key_bss_sta(struct wilc_vif *vif, const u8 *key, u8 len, - u8 index); -int wilc_add_wep_key_bss_ap(struct wilc_vif *vif, const u8 *key, u8 len, - u8 index, u8 mode, enum authtype auth_type); int wilc_add_ptk(struct wilc_vif *vif, const u8 *ptk, u8 ptk_key_len, const u8 *mac_addr, const u8 *rx_mic, const u8 *tx_mic, u8 mode, u8 cipher_mode, u8 index); +int wilc_add_igtk(struct wilc_vif *vif, const u8 *igtk, u8 igtk_key_len, + const u8 *pn, u8 pn_len, const u8 *mac_addr, u8 mode, + u8 index); s32 wilc_get_inactive_time(struct wilc_vif *vif, const u8 *mac, u32 *out_val); int wilc_add_rx_gtk(struct wilc_vif *vif, const u8 *rx_gtk, u8 gtk_key_len, @@ -208,9 +207,12 @@ int wilc_get_vif_idx(struct wilc_vif *vif); int wilc_set_tx_power(struct wilc_vif *vif, u8 tx_power); int wilc_get_tx_power(struct wilc_vif *vif, u8 *tx_power); void wilc_set_wowlan_trigger(struct wilc_vif *vif, bool enabled); +int wilc_set_external_auth_param(struct wilc_vif *vif, + struct cfg80211_external_auth_params *param); void wilc_scan_complete_received(struct wilc *wilc, u8 *buffer, u32 length); void wilc_network_info_received(struct wilc *wilc, u8 *buffer, u32 length); void wilc_gnrl_async_info_received(struct wilc *wilc, u8 *buffer, u32 length); void *wilc_parse_join_bss_param(struct cfg80211_bss *bss, struct cfg80211_crypto_settings *crypto); +int wilc_set_default_mgmt_key_index(struct wilc_vif *vif, u8 index); #endif diff --git a/drivers/net/wireless/microchip/wilc1000/netdev.c b/drivers/net/wireless/microchip/wilc1000/netdev.c index 3c292e3464c2..fcc4e61592ee 100644 --- a/drivers/net/wireless/microchip/wilc1000/netdev.c +++ b/drivers/net/wireless/microchip/wilc1000/netdev.c @@ -835,15 +835,24 @@ void wilc_frmw_to_host(struct wilc *wilc, u8 *buff, u32 size, } } -void wilc_wfi_mgmt_rx(struct wilc *wilc, u8 *buff, u32 size) +void wilc_wfi_mgmt_rx(struct wilc *wilc, u8 *buff, u32 size, bool is_auth) { int srcu_idx; struct wilc_vif *vif; srcu_idx = srcu_read_lock(&wilc->srcu); list_for_each_entry_rcu(vif, &wilc->vif_list, list) { + struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)buff; u16 type = le16_to_cpup((__le16 *)buff); u32 type_bit = BIT(type >> 4); + u32 auth_bit = BIT(IEEE80211_STYPE_AUTH >> 4); + + if ((vif->mgmt_reg_stypes & auth_bit && + ieee80211_is_auth(mgmt->frame_control)) && + vif->iftype == WILC_STATION_MODE && is_auth) { + wilc_wfi_mgmt_frame_rx(vif, buff, size); + break; + } if (vif->priv.p2p_listen_state && vif->mgmt_reg_stypes & type_bit) diff --git a/drivers/net/wireless/microchip/wilc1000/netdev.h b/drivers/net/wireless/microchip/wilc1000/netdev.h index a067274c2014..822e65d00f53 100644 --- a/drivers/net/wireless/microchip/wilc1000/netdev.h +++ b/drivers/net/wireless/microchip/wilc1000/netdev.h @@ -45,12 +45,6 @@ struct wilc_wfi_key { u32 cipher; }; -struct wilc_wfi_wep_key { - u8 *key; - u8 key_len; - u8 key_idx; -}; - struct sta_info { u8 sta_associated_bss[WILC_MAX_NUM_STA][ETH_ALEN]; }; @@ -63,8 +57,6 @@ struct wilc_wfi_p2p_listen_params { }; static const u32 wilc_cipher_suites[] = { - WLAN_CIPHER_SUITE_WEP40, - WLAN_CIPHER_SUITE_WEP104, WLAN_CIPHER_SUITE_TKIP, WLAN_CIPHER_SUITE_CCMP, WLAN_CIPHER_SUITE_AES_CMAC @@ -132,13 +124,12 @@ struct wilc_priv { struct net_device *dev; struct host_if_drv *hif_drv; struct wilc_pmkid_attr pmkid_list; - u8 wep_key[4][WLAN_KEY_LEN_WEP104]; - u8 wep_key_len[4]; /* The real interface that the monitor is on */ struct net_device *real_ndev; struct wilc_wfi_key *wilc_gtk[WILC_MAX_NUM_STA]; struct wilc_wfi_key *wilc_ptk[WILC_MAX_NUM_STA]; + struct wilc_wfi_key *wilc_igtk[2]; u8 wilc_groupkey; /* mutexes */ @@ -195,6 +186,7 @@ struct wilc_vif { struct wilc_priv priv; struct list_head list; struct cfg80211_bss *bss; + struct cfg80211_external_auth_params auth; }; struct wilc_tx_queue_status { @@ -288,7 +280,7 @@ struct wilc_wfi_mon_priv { void wilc_frmw_to_host(struct wilc *wilc, u8 *buff, u32 size, u32 pkt_offset); void wilc_mac_indicate(struct wilc *wilc); void wilc_netdev_cleanup(struct wilc *wilc); -void wilc_wfi_mgmt_rx(struct wilc *wilc, u8 *buff, u32 size); +void wilc_wfi_mgmt_rx(struct wilc *wilc, u8 *buff, u32 size, bool is_auth); void wilc_wlan_set_bssid(struct net_device *wilc_netdev, const u8 *bssid, u8 mode); struct wilc_vif *wilc_netdev_ifc_init(struct wilc *wl, const char *name, diff --git a/drivers/net/wireless/microchip/wilc1000/spi.c b/drivers/net/wireless/microchip/wilc1000/spi.c index 18420e954402..2ae8dd3411ac 100644 --- a/drivers/net/wireless/microchip/wilc1000/spi.c +++ b/drivers/net/wireless/microchip/wilc1000/spi.c @@ -191,11 +191,11 @@ static void wilc_wlan_power(struct wilc *wilc, bool on) /* assert ENABLE: */ gpiod_set_value(gpios->enable, 1); mdelay(5); - /* deassert RESET: */ - gpiod_set_value(gpios->reset, 0); - } else { /* assert RESET: */ gpiod_set_value(gpios->reset, 1); + } else { + /* deassert RESET: */ + gpiod_set_value(gpios->reset, 0); /* deassert ENABLE: */ gpiod_set_value(gpios->enable, 0); } diff --git a/drivers/net/wireless/microchip/wilc1000/wlan.c b/drivers/net/wireless/microchip/wilc1000/wlan.c index 48441f0389ca..f3f504d12873 100644 --- a/drivers/net/wireless/microchip/wilc1000/wlan.c +++ b/drivers/net/wireless/microchip/wilc1000/wlan.c @@ -968,7 +968,8 @@ static void wilc_wlan_handle_rx_buff(struct wilc *wilc, u8 *buffer, int size) if (pkt_offset & IS_MANAGMEMENT) { buff_ptr += HOST_HDR_OFFSET; - wilc_wfi_mgmt_rx(wilc, buff_ptr, pkt_len); + wilc_wfi_mgmt_rx(wilc, buff_ptr, pkt_len, + pkt_offset & IS_MGMT_AUTH_PKT); } else { if (!is_cfg_packet) { wilc_frmw_to_host(wilc, buff_ptr, pkt_len, diff --git a/drivers/net/wireless/microchip/wilc1000/wlan.h b/drivers/net/wireless/microchip/wilc1000/wlan.h index eb7978166d73..b45e72789a0e 100644 --- a/drivers/net/wireless/microchip/wilc1000/wlan.h +++ b/drivers/net/wireless/microchip/wilc1000/wlan.h @@ -305,6 +305,7 @@ #define IS_MANAGMEMENT 0x100 #define IS_MANAGMEMENT_CALLBACK 0x080 #define IS_MGMT_STATUS_SUCCES 0x040 +#define IS_MGMT_AUTH_PKT 0x010 #define WILC_WID_TYPE GENMASK(15, 12) #define WILC_VMM_ENTRY_FULL_RETRY 1 @@ -423,6 +424,7 @@ int wilc_wlan_get_num_conn_ifcs(struct wilc *wilc); netdev_tx_t wilc_mac_xmit(struct sk_buff *skb, struct net_device *dev); void wilc_wfi_p2p_rx(struct wilc_vif *vif, u8 *buff, u32 size); +bool wilc_wfi_mgmt_frame_rx(struct wilc_vif *vif, u8 *buff, u32 size); void host_wakeup_notify(struct wilc *wilc); void host_sleep_notify(struct wilc *wilc); void chip_allow_sleep(struct wilc *wilc); diff --git a/drivers/net/wireless/microchip/wilc1000/wlan_if.h b/drivers/net/wireless/microchip/wilc1000/wlan_if.h index 6eb7eb4ac294..df2f5a63bdf6 100644 --- a/drivers/net/wireless/microchip/wilc1000/wlan_if.h +++ b/drivers/net/wireless/microchip/wilc1000/wlan_if.h @@ -85,7 +85,16 @@ enum authtype { WILC_FW_AUTH_OPEN_SYSTEM = 1, WILC_FW_AUTH_SHARED_KEY = 2, WILC_FW_AUTH_ANY = 3, - WILC_FW_AUTH_IEEE8021 = 5 + WILC_FW_AUTH_IEEE8021 = 5, + WILC_FW_AUTH_SAE = 7, + WILC_FW_AUTH_IEE8021X_SHA256 = 9, + WILC_FW_AUTH_OPEN_SYSTEM_SHA256 = 13 +}; + +enum mfptype { + WILC_FW_MFP_NONE = 0x0, + WILC_FW_MFP_OPTIONAL = 0x1, + WILC_FW_MFP_REQUIRED = 0x2 }; enum site_survey { @@ -176,7 +185,8 @@ enum { enum { WILC_FW_ACTION_FRM_IDX = 0, - WILC_FW_PROBE_REQ_IDX = 1 + WILC_FW_PROBE_REQ_IDX = 1, + WILC_FW_AUTH_REQ_IDX = 2 }; enum wid_type { @@ -657,6 +667,9 @@ enum { WID_LOG_TERMINAL_SWITCH = 0x00CD, WID_TX_POWER = 0x00CE, WID_WOWLAN_TRIGGER = 0X00CF, + WID_SET_MFP = 0x00D0, + + WID_DEFAULT_MGMT_KEY_ID = 0x00D2, /* EMAC Short WID list */ /* RTS Threshold */ /* @@ -746,6 +759,7 @@ enum { WID_REMOVE_KEY = 0x301E, WID_ASSOC_REQ_INFO = 0x301F, WID_ASSOC_RES_INFO = 0x3020, + WID_ADD_IGTK = 0x3022, WID_MANUFACTURER = 0x3026, /* Added for CAPI tool */ WID_MODEL_NAME = 0x3027, /* Added for CAPI tool */ WID_MODEL_NUM = 0x3028, /* Added for CAPI tool */ @@ -789,7 +803,7 @@ enum { WID_ADD_BEACON = 0x408a, WID_SETUP_MULTICAST_FILTER = 0x408b, - + WID_EXTERNAL_AUTH_PARAM = 0x408d, /* Miscellaneous WIDs */ WID_ALL = 0x7FFE, WID_MAX = 0xFFFF diff --git a/drivers/net/wireless/ray_cs.c b/drivers/net/wireless/ray_cs.c index 87e98ab068ed..1f57a0055bbd 100644 --- a/drivers/net/wireless/ray_cs.c +++ b/drivers/net/wireless/ray_cs.c @@ -1643,38 +1643,34 @@ static void authenticate_timeout(struct timer_list *t) /*===========================================================================*/ static int parse_addr(char *in_str, UCHAR *out) { + int i, k; int len; - int i, j, k; - int status; if (in_str == NULL) return 0; - if ((len = strlen(in_str)) < 2) + len = strnlen(in_str, ADDRLEN * 2 + 1) - 1; + if (len < 1) return 0; memset(out, 0, ADDRLEN); - status = 1; - j = len - 1; - if (j > 12) - j = 12; i = 5; - while (j > 0) { - if ((k = hex_to_bin(in_str[j--])) != -1) + while (len > 0) { + if ((k = hex_to_bin(in_str[len--])) != -1) out[i] = k; else return 0; - if (j == 0) + if (len == 0) break; - if ((k = hex_to_bin(in_str[j--])) != -1) + if ((k = hex_to_bin(in_str[len--])) != -1) out[i] += k << 4; else return 0; if (!i--) break; } - return status; + return 1; } /*===========================================================================*/ diff --git a/drivers/net/wireless/realtek/rtlwifi/debug.c b/drivers/net/wireless/realtek/rtlwifi/debug.c index 901cdfe3723c..0b1bc04cb6ad 100644 --- a/drivers/net/wireless/realtek/rtlwifi/debug.c +++ b/drivers/net/wireless/realtek/rtlwifi/debug.c @@ -329,8 +329,8 @@ static ssize_t rtl_debugfs_set_write_h2c(struct file *filp, tmp_len = (count > sizeof(tmp) - 1 ? sizeof(tmp) - 1 : count); - if (!buffer || copy_from_user(tmp, buffer, tmp_len)) - return count; + if (copy_from_user(tmp, buffer, tmp_len)) + return -EFAULT; tmp[tmp_len] = '\0'; @@ -340,8 +340,8 @@ static ssize_t rtl_debugfs_set_write_h2c(struct file *filp, &h2c_data[4], &h2c_data[5], &h2c_data[6], &h2c_data[7]); - if (h2c_len <= 0) - return count; + if (h2c_len == 0) + return -EINVAL; for (i = 0; i < h2c_len; i++) h2c_data_packed[i] = (u8)h2c_data[i]; diff --git a/drivers/net/wireless/realtek/rtw88/debug.c b/drivers/net/wireless/realtek/rtw88/debug.c index 1a52ff585fbc..7cde6bcf253b 100644 --- a/drivers/net/wireless/realtek/rtw88/debug.c +++ b/drivers/net/wireless/realtek/rtw88/debug.c @@ -269,11 +269,7 @@ static int rtw_debugfs_get_rsvd_page(struct seq_file *m, void *v) for (i = 0 ; i < buf_size ; i += 8) { if (i % page_size == 0) seq_printf(m, "PAGE %d\n", (i + offset) / page_size); - seq_printf(m, "%2.2x %2.2x %2.2x %2.2x %2.2x %2.2x %2.2x %2.2x\n", - *(buf + i), *(buf + i + 1), - *(buf + i + 2), *(buf + i + 3), - *(buf + i + 4), *(buf + i + 5), - *(buf + i + 6), *(buf + i + 7)); + seq_printf(m, "%8ph\n", buf + i); } vfree(buf); diff --git a/drivers/net/wireless/realtek/rtw88/main.c b/drivers/net/wireless/realtek/rtw88/main.c index efabd5b1bf5b..a44b1810165d 100644 --- a/drivers/net/wireless/realtek/rtw88/main.c +++ b/drivers/net/wireless/realtek/rtw88/main.c @@ -1383,9 +1383,12 @@ void rtw_core_scan_start(struct rtw_dev *rtwdev, struct rtw_vif *rtwvif, void rtw_core_scan_complete(struct rtw_dev *rtwdev, struct ieee80211_vif *vif, bool hw_scan) { - struct rtw_vif *rtwvif = (struct rtw_vif *)vif->drv_priv; + struct rtw_vif *rtwvif = vif ? (struct rtw_vif *)vif->drv_priv : NULL; u32 config = 0; + if (!rtwvif) + return; + clear_bit(RTW_FLAG_SCANNING, rtwdev->flags); clear_bit(RTW_FLAG_DIG_DISABLE, rtwdev->flags); diff --git a/drivers/net/wireless/realtek/rtw88/rtw8723d.c b/drivers/net/wireless/realtek/rtw88/rtw8723d.c index 93cce44df531..993bd6b1d723 100644 --- a/drivers/net/wireless/realtek/rtw88/rtw8723d.c +++ b/drivers/net/wireless/realtek/rtw88/rtw8723d.c @@ -2701,7 +2701,7 @@ static const struct rtw_reg_domain coex_info_hw_regs_8723d[] = { {0x953, BIT(1), RTW_REG_DOMAIN_MAC8}, }; -struct rtw_chip_info rtw8723d_hw_spec = { +const struct rtw_chip_info rtw8723d_hw_spec = { .ops = &rtw8723d_ops, .id = RTW_CHIP_TYPE_8723D, .fw_name = "rtw88/rtw8723d_fw.bin", diff --git a/drivers/net/wireless/realtek/rtw88/rtw8723d.h b/drivers/net/wireless/realtek/rtw88/rtw8723d.h index 41d35174a542..4641f6e047b4 100644 --- a/drivers/net/wireless/realtek/rtw88/rtw8723d.h +++ b/drivers/net/wireless/realtek/rtw88/rtw8723d.h @@ -72,6 +72,8 @@ struct rtw8723d_efuse { struct rtw8723de_efuse e; }; +extern const struct rtw_chip_info rtw8723d_hw_spec; + /* phy status page0 */ #define GET_PHY_STAT_P0_PWDB(phy_stat) \ le32_get_bits(*((__le32 *)(phy_stat) + 0x00), GENMASK(15, 8)) diff --git a/drivers/net/wireless/realtek/rtw88/rtw8723de.c b/drivers/net/wireless/realtek/rtw88/rtw8723de.c index 2dd689441e8d..abbaafa32851 100644 --- a/drivers/net/wireless/realtek/rtw88/rtw8723de.c +++ b/drivers/net/wireless/realtek/rtw88/rtw8723de.c @@ -5,7 +5,7 @@ #include <linux/module.h> #include <linux/pci.h> #include "pci.h" -#include "rtw8723de.h" +#include "rtw8723d.h" static const struct pci_device_id rtw_8723de_id_table[] = { { diff --git a/drivers/net/wireless/realtek/rtw88/rtw8723de.h b/drivers/net/wireless/realtek/rtw88/rtw8723de.h deleted file mode 100644 index 2b4894846a07..000000000000 --- a/drivers/net/wireless/realtek/rtw88/rtw8723de.h +++ /dev/null @@ -1,10 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ -/* Copyright(c) 2018-2019 Realtek Corporation - */ - -#ifndef __RTW_8723DE_H_ -#define __RTW_8723DE_H_ - -extern struct rtw_chip_info rtw8723d_hw_spec; - -#endif diff --git a/drivers/net/wireless/realtek/rtw88/rtw8821c.c b/drivers/net/wireless/realtek/rtw88/rtw8821c.c index ffee39ea5df6..42841f5d502c 100644 --- a/drivers/net/wireless/realtek/rtw88/rtw8821c.c +++ b/drivers/net/wireless/realtek/rtw88/rtw8821c.c @@ -1877,7 +1877,7 @@ static const struct rtw_reg_domain coex_info_hw_regs_8821c[] = { {0x60A, MASKBYTE0, RTW_REG_DOMAIN_MAC8}, }; -struct rtw_chip_info rtw8821c_hw_spec = { +const struct rtw_chip_info rtw8821c_hw_spec = { .ops = &rtw8821c_ops, .id = RTW_CHIP_TYPE_8821C, .fw_name = "rtw88/rtw8821c_fw.bin", diff --git a/drivers/net/wireless/realtek/rtw88/rtw8821c.h b/drivers/net/wireless/realtek/rtw88/rtw8821c.h index d9fbddd7b0f3..2698801fc35d 100644 --- a/drivers/net/wireless/realtek/rtw88/rtw8821c.h +++ b/drivers/net/wireless/realtek/rtw88/rtw8821c.h @@ -84,6 +84,8 @@ _rtw_write32s_mask(struct rtw_dev *rtwdev, u32 addr, u32 mask, u32 data) rtw_write32_mask(rtwdev, addr + 0x200, mask, data); } +extern const struct rtw_chip_info rtw8821c_hw_spec; + #define rtw_write32s_mask(rtwdev, addr, mask, data) \ do { \ BUILD_BUG_ON((addr) < 0xC00 || (addr) >= 0xD00); \ diff --git a/drivers/net/wireless/realtek/rtw88/rtw8821ce.c b/drivers/net/wireless/realtek/rtw88/rtw8821ce.c index 56d22f9de904..f3d971feda04 100644 --- a/drivers/net/wireless/realtek/rtw88/rtw8821ce.c +++ b/drivers/net/wireless/realtek/rtw88/rtw8821ce.c @@ -5,7 +5,7 @@ #include <linux/module.h> #include <linux/pci.h> #include "pci.h" -#include "rtw8821ce.h" +#include "rtw8821c.h" static const struct pci_device_id rtw_8821ce_id_table[] = { { diff --git a/drivers/net/wireless/realtek/rtw88/rtw8821ce.h b/drivers/net/wireless/realtek/rtw88/rtw8821ce.h deleted file mode 100644 index 54142acca534..000000000000 --- a/drivers/net/wireless/realtek/rtw88/rtw8821ce.h +++ /dev/null @@ -1,10 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ -/* Copyright(c) 2018-2019 Realtek Corporation - */ - -#ifndef __RTW_8821CE_H_ -#define __RTW_8821CE_H_ - -extern struct rtw_chip_info rtw8821c_hw_spec; - -#endif diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822b.c b/drivers/net/wireless/realtek/rtw88/rtw8822b.c index dccd722b8e62..321848870561 100644 --- a/drivers/net/wireless/realtek/rtw88/rtw8822b.c +++ b/drivers/net/wireless/realtek/rtw88/rtw8822b.c @@ -2497,7 +2497,7 @@ static struct rtw_hw_reg_offset rtw8822b_edcca_th[] = { [EDCCA_TH_H2L_IDX] = {{.addr = 0x8a4, .mask = MASKBYTE1}, .offset = 0}, }; -struct rtw_chip_info rtw8822b_hw_spec = { +const struct rtw_chip_info rtw8822b_hw_spec = { .ops = &rtw8822b_ops, .id = RTW_CHIP_TYPE_8822B, .fw_name = "rtw88/rtw8822b_fw.bin", diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822b.h b/drivers/net/wireless/realtek/rtw88/rtw8822b.h index 3fff8b881854..01d3644e0c94 100644 --- a/drivers/net/wireless/realtek/rtw88/rtw8822b.h +++ b/drivers/net/wireless/realtek/rtw88/rtw8822b.h @@ -187,4 +187,6 @@ _rtw_write32s_mask(struct rtw_dev *rtwdev, u32 addr, u32 mask, u32 data) #define REG_ANTWT 0x1904 #define REG_IQKFAILMSK 0x1bf0 +extern const struct rtw_chip_info rtw8822b_hw_spec; + #endif diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822be.c b/drivers/net/wireless/realtek/rtw88/rtw8822be.c index 62ee7e62cac0..4994950776cd 100644 --- a/drivers/net/wireless/realtek/rtw88/rtw8822be.c +++ b/drivers/net/wireless/realtek/rtw88/rtw8822be.c @@ -5,7 +5,7 @@ #include <linux/module.h> #include <linux/pci.h> #include "pci.h" -#include "rtw8822be.h" +#include "rtw8822b.h" static const struct pci_device_id rtw_8822be_id_table[] = { { diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822be.h b/drivers/net/wireless/realtek/rtw88/rtw8822be.h deleted file mode 100644 index 6668460d664d..000000000000 --- a/drivers/net/wireless/realtek/rtw88/rtw8822be.h +++ /dev/null @@ -1,10 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ -/* Copyright(c) 2018-2019 Realtek Corporation - */ - -#ifndef __RTW_8822BE_H_ -#define __RTW_8822BE_H_ - -extern struct rtw_chip_info rtw8822b_hw_spec; - -#endif diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822c.c b/drivers/net/wireless/realtek/rtw88/rtw8822c.c index c043b5c520b9..09f9e4adcf34 100644 --- a/drivers/net/wireless/realtek/rtw88/rtw8822c.c +++ b/drivers/net/wireless/realtek/rtw88/rtw8822c.c @@ -5310,7 +5310,7 @@ static const struct rtw_reg_domain coex_info_hw_regs_8822c[] = { {0xc50, MASKBYTE0, RTW_REG_DOMAIN_MAC8}, }; -struct rtw_chip_info rtw8822c_hw_spec = { +const struct rtw_chip_info rtw8822c_hw_spec = { .ops = &rtw8822c_ops, .id = RTW_CHIP_TYPE_8822C, .fw_name = "rtw88/rtw8822c_fw.bin", diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822c.h b/drivers/net/wireless/realtek/rtw88/rtw8822c.h index 8201955e1f21..479d5d769c52 100644 --- a/drivers/net/wireless/realtek/rtw88/rtw8822c.h +++ b/drivers/net/wireless/realtek/rtw88/rtw8822c.h @@ -118,6 +118,8 @@ enum rtw8822c_dpk_one_shot_action { void rtw8822c_parse_tbl_dpk(struct rtw_dev *rtwdev, const struct rtw_table *tbl); +extern const struct rtw_chip_info rtw8822c_hw_spec; + #define RTW_DECL_TABLE_DPK(name) \ const struct rtw_table name ## _tbl = { \ .data = name, \ diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822ce.c b/drivers/net/wireless/realtek/rtw88/rtw8822ce.c index 3845b1333dc3..e26c6bc82936 100644 --- a/drivers/net/wireless/realtek/rtw88/rtw8822ce.c +++ b/drivers/net/wireless/realtek/rtw88/rtw8822ce.c @@ -5,7 +5,7 @@ #include <linux/module.h> #include <linux/pci.h> #include "pci.h" -#include "rtw8822ce.h" +#include "rtw8822c.h" static const struct pci_device_id rtw_8822ce_id_table[] = { { diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822ce.h b/drivers/net/wireless/realtek/rtw88/rtw8822ce.h deleted file mode 100644 index fee32d7a4504..000000000000 --- a/drivers/net/wireless/realtek/rtw88/rtw8822ce.h +++ /dev/null @@ -1,10 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ -/* Copyright(c) 2018-2019 Realtek Corporation - */ - -#ifndef __RTW_8822CE_H_ -#define __RTW_8822CE_H_ - -extern struct rtw_chip_info rtw8822c_hw_spec; - -#endif diff --git a/drivers/net/wireless/realtek/rtw89/cam.c b/drivers/net/wireless/realtek/rtw89/cam.c index 8a26adeb23fb..db3c55f0ccd0 100644 --- a/drivers/net/wireless/realtek/rtw89/cam.c +++ b/drivers/net/wireless/realtek/rtw89/cam.c @@ -602,11 +602,18 @@ int rtw89_cam_fill_bssid_cam_info(struct rtw89_dev *rtwdev, struct ieee80211_vif *vif = rtwvif_to_vif(rtwvif); struct rtw89_bssid_cam_entry *bssid_cam = &rtwvif->bssid_cam; u8 bss_color = vif->bss_conf.he_bss_color.color; + u8 bss_mask; + + if (vif->bss_conf.nontransmitted) + bss_mask = RTW89_BSSID_MATCH_5_BYTES; + else + bss_mask = RTW89_BSSID_MATCH_ALL; FWCMD_SET_ADDR_BSSID_IDX(cmd, bssid_cam->bssid_cam_idx); FWCMD_SET_ADDR_BSSID_OFFSET(cmd, bssid_cam->offset); FWCMD_SET_ADDR_BSSID_LEN(cmd, bssid_cam->len); FWCMD_SET_ADDR_BSSID_VALID(cmd, bssid_cam->valid); + FWCMD_SET_ADDR_BSSID_MASK(cmd, bss_mask); FWCMD_SET_ADDR_BSSID_BB_SEL(cmd, bssid_cam->phy_idx); FWCMD_SET_ADDR_BSSID_BSS_COLOR(cmd, bss_color); diff --git a/drivers/net/wireless/realtek/rtw89/cam.h b/drivers/net/wireless/realtek/rtw89/cam.h index a3931d3e40d2..74a6c4748d64 100644 --- a/drivers/net/wireless/realtek/rtw89/cam.h +++ b/drivers/net/wireless/realtek/rtw89/cam.h @@ -9,6 +9,9 @@ #define RTW89_SEC_CAM_LEN 20 +#define RTW89_BSSID_MATCH_ALL GENMASK(5, 0) +#define RTW89_BSSID_MATCH_5_BYTES GENMASK(4, 0) + static inline void FWCMD_SET_ADDR_IDX(void *cmd, u32 value) { le32p_replace_bits((__le32 *)(cmd) + 1, value, GENMASK(7, 0)); @@ -309,6 +312,11 @@ static inline void FWCMD_SET_ADDR_BSSID_BB_SEL(void *cmd, u32 value) le32p_replace_bits((__le32 *)(cmd) + 13, value, BIT(1)); } +static inline void FWCMD_SET_ADDR_BSSID_MASK(void *cmd, u32 value) +{ + le32p_replace_bits((__le32 *)(cmd) + 13, value, GENMASK(7, 2)); +} + static inline void FWCMD_SET_ADDR_BSSID_BSS_COLOR(void *cmd, u32 value) { le32p_replace_bits((__le32 *)(cmd) + 13, value, GENMASK(13, 8)); diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c index a6a90572e74b..d2f2a3d65ef6 100644 --- a/drivers/net/wireless/realtek/rtw89/core.c +++ b/drivers/net/wireless/realtek/rtw89/core.c @@ -1343,6 +1343,47 @@ struct rtw89_vif_rx_stats_iter_data { const u8 *bssid; }; +static void rtw89_stats_trigger_frame(struct rtw89_dev *rtwdev, + struct ieee80211_vif *vif, + struct sk_buff *skb) +{ + struct rtw89_vif *rtwvif = (struct rtw89_vif *)vif->drv_priv; + struct ieee80211_trigger *tf = (struct ieee80211_trigger *)skb->data; + u8 *pos, *end, type; + u16 aid; + + if (!ether_addr_equal(vif->bss_conf.bssid, tf->ta) || + rtwvif->wifi_role != RTW89_WIFI_ROLE_STATION || + rtwvif->net_type == RTW89_NET_TYPE_NO_LINK) + return; + + type = le64_get_bits(tf->common_info, IEEE80211_TRIGGER_TYPE_MASK); + if (type != IEEE80211_TRIGGER_TYPE_BASIC) + return; + + end = (u8 *)tf + skb->len; + pos = tf->variable; + + while (end - pos >= RTW89_TF_BASIC_USER_INFO_SZ) { + aid = RTW89_GET_TF_USER_INFO_AID12(pos); + rtw89_debug(rtwdev, RTW89_DBG_TXRX, + "[TF] aid: %d, ul_mcs: %d, rua: %d\n", + aid, RTW89_GET_TF_USER_INFO_UL_MCS(pos), + RTW89_GET_TF_USER_INFO_RUA(pos)); + + if (aid == RTW89_TF_PAD) + break; + + if (aid == vif->bss_conf.aid) { + rtwvif->stats.rx_tf_acc++; + rtwdev->stats.rx_tf_acc++; + break; + } + + pos += RTW89_TF_BASIC_USER_INFO_SZ; + } +} + static void rtw89_vif_rx_stats_iter(void *data, u8 *mac, struct ieee80211_vif *vif) { @@ -1355,6 +1396,11 @@ static void rtw89_vif_rx_stats_iter(void *data, u8 *mac, struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; const u8 *bssid = iter_data->bssid; + if (ieee80211_is_trigger(hdr->frame_control)) { + rtw89_stats_trigger_frame(rtwdev, vif, skb); + return; + } + if (!ether_addr_equal(vif->bss_conf.bssid, bssid)) return; @@ -1608,7 +1654,7 @@ static void rtw89_core_update_rx_status(struct rtw89_dev *rtwdev, if (rtwdev->scanning && RTW89_CHK_FW_FEATURE(SCAN_OFFLOAD, &rtwdev->fw)) { - u8 chan = hal->current_channel; + u8 chan = hal->current_primary_channel; u8 band = hal->current_band_type; enum nl80211_band nl_band; @@ -2023,6 +2069,8 @@ static bool rtw89_traffic_stats_calc(struct rtw89_dev *rtwdev, stats->rx_unicast = 0; stats->tx_cnt = 0; stats->rx_cnt = 0; + stats->rx_tf_periodic = stats->rx_tf_acc; + stats->rx_tf_acc = 0; if (tx_tfc_lv != stats->tx_tfc_lv || rx_tfc_lv != stats->rx_tfc_lv) return true; @@ -2875,7 +2923,10 @@ void rtw89_core_scan_start(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif, void rtw89_core_scan_complete(struct rtw89_dev *rtwdev, struct ieee80211_vif *vif, bool hw_scan) { - struct rtw89_vif *rtwvif = (struct rtw89_vif *)vif->drv_priv; + struct rtw89_vif *rtwvif = vif ? (struct rtw89_vif *)vif->drv_priv : NULL; + + if (!rtwvif) + return; ether_addr_copy(rtwvif->mac_addr, vif->addr); rtw89_fw_h2c_cam(rtwdev, rtwvif, NULL, NULL); @@ -3008,6 +3059,7 @@ static int rtw89_core_register_hw(struct rtw89_dev *rtwdev) ieee80211_hw_set(hw, SUPPORTS_PS); ieee80211_hw_set(hw, SUPPORTS_DYNAMIC_PS); ieee80211_hw_set(hw, SINGLE_SCAN_ON_ALL_BANDS); + ieee80211_hw_set(hw, SUPPORTS_MULTI_BSSID); hw->wiphy->interface_modes = BIT(NL80211_IFTYPE_STATION) | BIT(NL80211_IFTYPE_AP); diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h index e8a77225a90f..239d47d0ec6d 100644 --- a/drivers/net/wireless/realtek/rtw89/core.h +++ b/drivers/net/wireless/realtek/rtw89/core.h @@ -55,6 +55,16 @@ enum htc_om_channel_width { #define RTW89_HTC_MASK_HTC_OM_DL_MU_MIMO_RR BIT(16) #define RTW89_HTC_MASK_HTC_OM_UL_MU_DATA_DIS BIT(17) +#define RTW89_TF_PAD GENMASK(11, 0) +#define RTW89_TF_BASIC_USER_INFO_SZ 6 + +#define RTW89_GET_TF_USER_INFO_AID12(data) \ + le32_get_bits(*((const __le32 *)(data)), GENMASK(11, 0)) +#define RTW89_GET_TF_USER_INFO_RUA(data) \ + le32_get_bits(*((const __le32 *)(data)), GENMASK(19, 12)) +#define RTW89_GET_TF_USER_INFO_UL_MCS(data) \ + le32_get_bits(*((const __le32 *)(data)), GENMASK(24, 21)) + enum rtw89_subband { RTW89_CH_2G = 0, RTW89_CH_5G_BAND_1 = 1, @@ -943,6 +953,10 @@ struct rtw89_traffic_stats { u32 rx_throughput; u32 tx_throughput_raw; u32 rx_throughput_raw; + + u32 rx_tf_acc; + u32 rx_tf_periodic; + enum rtw89_tfc_lv tx_tfc_lv; enum rtw89_tfc_lv rx_tfc_lv; struct ewma_tp tx_ewma_tp; @@ -2550,9 +2564,24 @@ enum rtw89_sar_sources { RTW89_SAR_SOURCE_NR, }; +enum rtw89_sar_subband { + RTW89_SAR_2GHZ_SUBBAND, + RTW89_SAR_5GHZ_SUBBAND_1_2, /* U-NII-1 and U-NII-2 */ + RTW89_SAR_5GHZ_SUBBAND_2_E, /* U-NII-2-Extended */ + RTW89_SAR_5GHZ_SUBBAND_3, /* U-NII-3 */ + RTW89_SAR_6GHZ_SUBBAND_5_L, /* U-NII-5 lower part */ + RTW89_SAR_6GHZ_SUBBAND_5_H, /* U-NII-5 higher part */ + RTW89_SAR_6GHZ_SUBBAND_6, /* U-NII-6 */ + RTW89_SAR_6GHZ_SUBBAND_7_L, /* U-NII-7 lower part */ + RTW89_SAR_6GHZ_SUBBAND_7_H, /* U-NII-7 higher part */ + RTW89_SAR_6GHZ_SUBBAND_8, /* U-NII-8 */ + + RTW89_SAR_SUBBAND_NR, +}; + struct rtw89_sar_cfg_common { - bool set[RTW89_SUBBAND_NR]; - s32 cfg[RTW89_SUBBAND_NR]; + bool set[RTW89_SAR_SUBBAND_NR]; + s32 cfg[RTW89_SAR_SUBBAND_NR]; }; struct rtw89_sar_info { @@ -2646,6 +2675,10 @@ struct rtw89_lck_info { u8 thermal[RF_PATH_MAX]; }; +struct rtw89_rx_dck_info { + u8 thermal[RF_PATH_MAX]; +}; + struct rtw89_iqk_info { bool lok_cor_fail[RTW89_IQK_CHS_NR][RTW89_IQK_PATH_NR]; bool lok_fin_fail[RTW89_IQK_CHS_NR][RTW89_IQK_PATH_NR]; @@ -2776,13 +2809,20 @@ enum rtw89_multi_cfo_mode { enum rtw89_phy_cfo_status { RTW89_PHY_DCFO_STATE_NORMAL = 0, RTW89_PHY_DCFO_STATE_ENHANCE = 1, + RTW89_PHY_DCFO_STATE_HOLD = 2, RTW89_PHY_DCFO_STATE_MAX }; +enum rtw89_phy_cfo_ul_ofdma_acc_mode { + RTW89_CFO_UL_OFDMA_ACC_DISABLE = 0, + RTW89_CFO_UL_OFDMA_ACC_ENABLE = 1 +}; + struct rtw89_cfo_tracking_info { u16 cfo_timer_ms; bool cfo_trig_by_timer_en; enum rtw89_phy_cfo_status phy_cfo_status; + enum rtw89_phy_cfo_ul_ofdma_acc_mode cfo_ul_ofdma_acc_mode; u8 phy_cfo_trk_cnt; bool is_adjust; enum rtw89_multi_cfo_mode rtw89_multi_cfo_mode; @@ -3125,6 +3165,7 @@ struct rtw89_dev { struct rtw89_dpk_info dpk; struct rtw89_mcc_info mcc; struct rtw89_lck_info lck; + struct rtw89_rx_dck_info rx_dck; bool is_tssi_mode[RF_PATH_MAX]; bool is_bt_iqk_timeout; diff --git a/drivers/net/wireless/realtek/rtw89/debug.c b/drivers/net/wireless/realtek/rtw89/debug.c index 7820bc3ab3b4..f00f81916f2f 100644 --- a/drivers/net/wireless/realtek/rtw89/debug.c +++ b/drivers/net/wireless/realtek/rtw89/debug.c @@ -2376,7 +2376,8 @@ static int rtw89_debug_priv_phy_info_get(struct seq_file *m, void *v) seq_printf(m, "TP TX: %u [%u] Mbps (lv: %d), RX: %u [%u] Mbps (lv: %d)\n", stats->tx_throughput, stats->tx_throughput_raw, stats->tx_tfc_lv, stats->rx_throughput, stats->rx_throughput_raw, stats->rx_tfc_lv); - seq_printf(m, "Beacon: %u\n", pkt_stat->beacon_nr); + seq_printf(m, "Beacon: %u, TF: %u\n", pkt_stat->beacon_nr, + stats->rx_tf_periodic); seq_printf(m, "Avg packet length: TX=%u, RX=%u\n", stats->tx_avg_len, stats->rx_avg_len); diff --git a/drivers/net/wireless/realtek/rtw89/debug.h b/drivers/net/wireless/realtek/rtw89/debug.h index de72155ad1fe..561b04faf703 100644 --- a/drivers/net/wireless/realtek/rtw89/debug.h +++ b/drivers/net/wireless/realtek/rtw89/debug.h @@ -24,6 +24,7 @@ enum rtw89_debug_mask { RTW89_DBG_BTC = BIT(13), RTW89_DBG_BF = BIT(14), RTW89_DBG_HW_SCAN = BIT(15), + RTW89_DBG_SAR = BIT(16), }; enum rtw89_debug_mac_reg_sel { diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c index 4718aced1428..2d9c3157d878 100644 --- a/drivers/net/wireless/realtek/rtw89/fw.c +++ b/drivers/net/wireless/realtek/rtw89/fw.c @@ -2257,7 +2257,7 @@ static int rtw89_hw_scan_add_chan_list(struct rtw89_dev *rtwdev, list_add_tail(&ch_info->list, &chan_list); off_chan_time += ch_info->period; } - rtw89_fw_h2c_scan_list_offload(rtwdev, list_len, &chan_list); + ret = rtw89_fw_h2c_scan_list_offload(rtwdev, list_len, &chan_list); out: list_for_each_entry_safe(ch_info, tmp, &chan_list, list) { @@ -2339,6 +2339,9 @@ void rtw89_hw_scan_complete(struct rtw89_dev *rtwdev, struct ieee80211_vif *vif, rtwvif->scan_req = NULL; rtwvif->scan_ies = NULL; rtwdev->scan_info.scanning_vif = NULL; + + if (rtwvif->net_type != RTW89_NET_TYPE_NO_LINK) + rtw89_store_op_chan(rtwdev, false); } void rtw89_hw_scan_abort(struct rtw89_dev *rtwdev, struct ieee80211_vif *vif) @@ -2365,20 +2368,27 @@ int rtw89_hw_scan_offload(struct rtw89_dev *rtwdev, struct ieee80211_vif *vif, if (ret) goto out; } - rtw89_fw_h2c_scan_offload(rtwdev, &opt, rtwvif); + ret = rtw89_fw_h2c_scan_offload(rtwdev, &opt, rtwvif); out: return ret; } -void rtw89_store_op_chan(struct rtw89_dev *rtwdev) +void rtw89_store_op_chan(struct rtw89_dev *rtwdev, bool backup) { struct rtw89_hw_scan_info *scan_info = &rtwdev->scan_info; struct rtw89_hal *hal = &rtwdev->hal; - scan_info->op_pri_ch = hal->current_primary_channel; - scan_info->op_chan = hal->current_channel; - scan_info->op_bw = hal->current_band_width; - scan_info->op_band = hal->current_band_type; + if (backup) { + scan_info->op_pri_ch = hal->current_primary_channel; + scan_info->op_chan = hal->current_channel; + scan_info->op_bw = hal->current_band_width; + scan_info->op_band = hal->current_band_type; + } else { + hal->current_primary_channel = scan_info->op_pri_ch; + hal->current_channel = scan_info->op_chan; + hal->current_band_width = scan_info->op_bw; + hal->current_band_type = scan_info->op_band; + } } #define H2C_FW_CPU_EXCEPTION_LEN 4 diff --git a/drivers/net/wireless/realtek/rtw89/fw.h b/drivers/net/wireless/realtek/rtw89/fw.h index 95a55c4213db..e75ad22aa85d 100644 --- a/drivers/net/wireless/realtek/rtw89/fw.h +++ b/drivers/net/wireless/realtek/rtw89/fw.h @@ -2633,17 +2633,14 @@ int rtw89_fw_msg_reg(struct rtw89_dev *rtwdev, struct rtw89_mac_c2h_info *c2h_info); int rtw89_fw_h2c_fw_log(struct rtw89_dev *rtwdev, bool enable); void rtw89_fw_st_dbg_dump(struct rtw89_dev *rtwdev); -void rtw89_store_op_chan(struct rtw89_dev *rtwdev); +void rtw89_store_op_chan(struct rtw89_dev *rtwdev, bool backup); void rtw89_hw_scan_start(struct rtw89_dev *rtwdev, struct ieee80211_vif *vif, struct ieee80211_scan_request *req); void rtw89_hw_scan_complete(struct rtw89_dev *rtwdev, struct ieee80211_vif *vif, bool aborted); int rtw89_hw_scan_offload(struct rtw89_dev *rtwdev, struct ieee80211_vif *vif, bool enable); -void rtw89_hw_scan_status_report(struct rtw89_dev *rtwdev, struct sk_buff *skb); -void rtw89_hw_scan_chan_switch(struct rtw89_dev *rtwdev, struct sk_buff *skb); void rtw89_hw_scan_abort(struct rtw89_dev *rtwdev, struct ieee80211_vif *vif); -void rtw89_store_op_chan(struct rtw89_dev *rtwdev); int rtw89_fw_h2c_trigger_cpu_exception(struct rtw89_dev *rtwdev); #endif diff --git a/drivers/net/wireless/realtek/rtw89/mac.c b/drivers/net/wireless/realtek/rtw89/mac.c index 3cf892912c1d..93124b815825 100644 --- a/drivers/net/wireless/realtek/rtw89/mac.c +++ b/drivers/net/wireless/realtek/rtw89/mac.c @@ -3681,17 +3681,20 @@ rtw89_mac_c2h_scanofld_rsp(struct rtw89_dev *rtwdev, struct sk_buff *c2h, rtw89_hw_scan_complete(rtwdev, vif, false); break; case RTW89_SCAN_ENTER_CH_NOTIFY: - if (rtw89_is_op_chan(rtwdev, band, chan)) + hal->prev_band_type = hal->current_band_type; + hal->current_band_type = band; + hal->prev_primary_channel = hal->current_primary_channel; + hal->current_primary_channel = chan; + hal->current_channel = chan; + hal->current_band_width = RTW89_CHANNEL_WIDTH_20; + if (rtw89_is_op_chan(rtwdev, band, chan)) { + rtw89_store_op_chan(rtwdev, false); ieee80211_wake_queues(rtwdev->hw); + } break; default: return; } - - hal->prev_band_type = hal->current_band_type; - hal->prev_primary_channel = hal->current_channel; - hal->current_channel = chan; - hal->current_band_type = band; } static void diff --git a/drivers/net/wireless/realtek/rtw89/mac.h b/drivers/net/wireless/realtek/rtw89/mac.h index 9f511c8d8a37..f66619354734 100644 --- a/drivers/net/wireless/realtek/rtw89/mac.h +++ b/drivers/net/wireless/realtek/rtw89/mac.h @@ -666,6 +666,7 @@ enum mac_ax_err_info { MAC_AX_ERR_L2_ERR_APB_BBRF_TO_RX4281 = 0x2360, MAC_AX_ERR_L2_ERR_APB_BBRF_TO_OTHERS = 0x2370, MAC_AX_ERR_L2_RESET_DONE = 0x2400, + MAC_AX_ERR_L2_ERR_WDT_TIMEOUT_INT = 0x2599, MAC_AX_ERR_CPU_EXCEPTION = 0x3000, MAC_AX_ERR_ASSERTION = 0x4000, MAC_AX_GET_ERR_MAX, diff --git a/drivers/net/wireless/realtek/rtw89/mac80211.c b/drivers/net/wireless/realtek/rtw89/mac80211.c index f24e4a208376..6d0c62c545a7 100644 --- a/drivers/net/wireless/realtek/rtw89/mac80211.c +++ b/drivers/net/wireless/realtek/rtw89/mac80211.c @@ -350,7 +350,7 @@ static void rtw89_ops_bss_info_changed(struct ieee80211_hw *hw, rtw89_phy_set_bss_color(rtwdev, vif); rtw89_chip_cfg_txpwr_ul_tb_offset(rtwdev, vif); rtw89_mac_port_update(rtwdev, rtwvif); - rtw89_store_op_chan(rtwdev); + rtw89_store_op_chan(rtwdev, true); } else { /* Abort ongoing scan if cancel_scan isn't issued * when disconnected by peer diff --git a/drivers/net/wireless/realtek/rtw89/pci.c b/drivers/net/wireless/realtek/rtw89/pci.c index 0ef7821b2e0f..25872dfb4da1 100644 --- a/drivers/net/wireless/realtek/rtw89/pci.c +++ b/drivers/net/wireless/realtek/rtw89/pci.c @@ -738,6 +738,9 @@ static irqreturn_t rtw89_pci_interrupt_threadfn(int irq, void *dev) if (unlikely(isrs.halt_c2h_isrs & B_AX_HALT_C2H_INT_EN)) rtw89_ser_notify(rtwdev, rtw89_mac_get_err_status(rtwdev)); + if (unlikely(isrs.halt_c2h_isrs & B_AX_WDT_TIMEOUT_INT_EN)) + rtw89_ser_notify(rtwdev, MAC_AX_ERR_L2_ERR_WDT_TIMEOUT_INT); + if (unlikely(rtwpci->under_recovery)) goto enable_intr; @@ -3126,7 +3129,7 @@ static void rtw89_pci_recovery_intr_mask_v1(struct rtw89_dev *rtwdev) struct rtw89_pci *rtwpci = (struct rtw89_pci *)rtwdev->priv; rtwpci->ind_intrs = B_AX_HS0ISR_IND_INT_EN; - rtwpci->halt_c2h_intrs = B_AX_HALT_C2H_INT_EN; + rtwpci->halt_c2h_intrs = B_AX_HALT_C2H_INT_EN | B_AX_WDT_TIMEOUT_INT_EN; rtwpci->intrs[0] = 0; rtwpci->intrs[1] = 0; } @@ -3138,7 +3141,7 @@ static void rtw89_pci_default_intr_mask_v1(struct rtw89_dev *rtwdev) rtwpci->ind_intrs = B_AX_HCI_AXIDMA_INT_EN | B_AX_HS1ISR_IND_INT_EN | B_AX_HS0ISR_IND_INT_EN; - rtwpci->halt_c2h_intrs = B_AX_HALT_C2H_INT_EN; + rtwpci->halt_c2h_intrs = B_AX_HALT_C2H_INT_EN | B_AX_WDT_TIMEOUT_INT_EN; rtwpci->intrs[0] = B_AX_TXDMA_STUCK_INT_EN | B_AX_RXDMA_INT_EN | B_AX_RXP1DMA_INT_EN | @@ -3155,7 +3158,7 @@ static void rtw89_pci_low_power_intr_mask_v1(struct rtw89_dev *rtwdev) rtwpci->ind_intrs = B_AX_HS1ISR_IND_INT_EN | B_AX_HS0ISR_IND_INT_EN; - rtwpci->halt_c2h_intrs = B_AX_HALT_C2H_INT_EN; + rtwpci->halt_c2h_intrs = B_AX_HALT_C2H_INT_EN | B_AX_WDT_TIMEOUT_INT_EN; rtwpci->intrs[0] = 0; rtwpci->intrs[1] = B_AX_GPIO18_INT_EN; } diff --git a/drivers/net/wireless/realtek/rtw89/pci.h b/drivers/net/wireless/realtek/rtw89/pci.h index bb585ed19190..a118647213e3 100644 --- a/drivers/net/wireless/realtek/rtw89/pci.h +++ b/drivers/net/wireless/realtek/rtw89/pci.h @@ -94,6 +94,7 @@ /* Interrupts */ #define R_AX_HIMR0 0x01A0 +#define B_AX_WDT_TIMEOUT_INT_EN BIT(22) #define B_AX_HALT_C2H_INT_EN BIT(21) #define R_AX_HISR0 0x01A4 diff --git a/drivers/net/wireless/realtek/rtw89/phy.c b/drivers/net/wireless/realtek/rtw89/phy.c index 762cdba9d3cf..217aacb6e8c1 100644 --- a/drivers/net/wireless/realtek/rtw89/phy.c +++ b/drivers/net/wireless/realtek/rtw89/phy.c @@ -2151,6 +2151,7 @@ static void rtw89_phy_cfo_init(struct rtw89_dev *rtwdev) cfo->cfo_trig_by_timer_en = false; cfo->phy_cfo_trk_cnt = 0; cfo->phy_cfo_status = RTW89_PHY_DCFO_STATE_NORMAL; + cfo->cfo_ul_ofdma_acc_mode = RTW89_CFO_UL_OFDMA_ACC_ENABLE; } static void rtw89_phy_cfo_crystal_cap_adjust(struct rtw89_dev *rtwdev, @@ -2419,6 +2420,13 @@ void rtw89_phy_cfo_track(struct rtw89_dev *rtwdev) { struct rtw89_cfo_tracking_info *cfo = &rtwdev->cfo_tracking; struct rtw89_traffic_stats *stats = &rtwdev->stats; + bool is_ul_ofdma = false, ofdma_acc_en = false; + + if (stats->rx_tf_periodic > CFO_TF_CNT_TH) + is_ul_ofdma = true; + if (cfo->cfo_ul_ofdma_acc_mode == RTW89_CFO_UL_OFDMA_ACC_ENABLE && + is_ul_ofdma) + ofdma_acc_en = true; switch (cfo->phy_cfo_status) { case RTW89_PHY_DCFO_STATE_NORMAL: @@ -2430,16 +2438,26 @@ void rtw89_phy_cfo_track(struct rtw89_dev *rtwdev) } break; case RTW89_PHY_DCFO_STATE_ENHANCE: - if (cfo->phy_cfo_trk_cnt >= CFO_PERIOD_CNT) { + if (stats->tx_throughput <= CFO_TP_LOWER) + cfo->phy_cfo_status = RTW89_PHY_DCFO_STATE_NORMAL; + else if (ofdma_acc_en && + cfo->phy_cfo_trk_cnt >= CFO_PERIOD_CNT) + cfo->phy_cfo_status = RTW89_PHY_DCFO_STATE_HOLD; + else + cfo->phy_cfo_trk_cnt++; + + if (cfo->phy_cfo_status == RTW89_PHY_DCFO_STATE_NORMAL) { cfo->phy_cfo_trk_cnt = 0; cfo->cfo_trig_by_timer_en = false; } - if (cfo->cfo_trig_by_timer_en == 1) - cfo->phy_cfo_trk_cnt++; + break; + case RTW89_PHY_DCFO_STATE_HOLD: if (stats->tx_throughput <= CFO_TP_LOWER) { cfo->phy_cfo_status = RTW89_PHY_DCFO_STATE_NORMAL; cfo->phy_cfo_trk_cnt = 0; cfo->cfo_trig_by_timer_en = false; + } else { + cfo->phy_cfo_trk_cnt++; } break; default: diff --git a/drivers/net/wireless/realtek/rtw89/phy.h b/drivers/net/wireless/realtek/rtw89/phy.h index 291660154d58..e20636f54b55 100644 --- a/drivers/net/wireless/realtek/rtw89/phy.h +++ b/drivers/net/wireless/realtek/rtw89/phy.h @@ -62,6 +62,7 @@ #define CFO_COMP_PERIOD 250 #define CFO_COMP_WEIGHT 8 #define MAX_CFO_TOLERANCE 30 +#define CFO_TF_CNT_TH 300 #define CCX_MAX_PERIOD 2097 #define CCX_MAX_PERIOD_UNIT 32 diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852c.c b/drivers/net/wireless/realtek/rtw89/rtw8852c.c index 64840c8d9efe..b697aef2faf2 100644 --- a/drivers/net/wireless/realtek/rtw89/rtw8852c.c +++ b/drivers/net/wireless/realtek/rtw89/rtw8852c.c @@ -1861,6 +1861,7 @@ static void rtw8852c_rfk_track(struct rtw89_dev *rtwdev) { rtw8852c_dpk_track(rtwdev); rtw8852c_lck_track(rtwdev); + rtw8852c_rx_dck_track(rtwdev); } static u32 rtw8852c_bb_cal_txpwr_ref(struct rtw89_dev *rtwdev, diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852c_rfk.c b/drivers/net/wireless/realtek/rtw89/rtw8852c_rfk.c index dfb9caba9bc4..4186d825d19b 100644 --- a/drivers/net/wireless/realtek/rtw89/rtw8852c_rfk.c +++ b/drivers/net/wireless/realtek/rtw89/rtw8852c_rfk.c @@ -3864,6 +3864,7 @@ void rtw8852c_iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx) void rtw8852c_rx_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy, bool is_afe) { + struct rtw89_rx_dck_info *rx_dck = &rtwdev->rx_dck; u8 path, kpath; u32 rf_reg5; @@ -3883,6 +3884,7 @@ void rtw8852c_rx_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy, bool is_a rtw89_write_rf(rtwdev, path, RR_RSV1, RR_RSV1_RST, 0x0); rtw89_write_rf(rtwdev, path, RR_MOD, RR_MOD_MASK, RR_MOD_V_RX); _set_rx_dck(rtwdev, phy, path, is_afe); + rx_dck->thermal[path] = ewma_thermal_read(&rtwdev->phystat.avg_thermal[path]); rtw89_write_rf(rtwdev, path, RR_RSV1, RFREG_MASK, rf_reg5); if (rtwdev->is_tssi_mode[path]) @@ -3891,6 +3893,31 @@ void rtw8852c_rx_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy, bool is_a } } +#define RTW8852C_RX_DCK_TH 8 + +void rtw8852c_rx_dck_track(struct rtw89_dev *rtwdev) +{ + struct rtw89_rx_dck_info *rx_dck = &rtwdev->rx_dck; + u8 cur_thermal; + int delta; + int path; + + for (path = 0; path < RF_PATH_NUM_8852C; path++) { + cur_thermal = + ewma_thermal_read(&rtwdev->phystat.avg_thermal[path]); + delta = abs((int)cur_thermal - rx_dck->thermal[path]); + + rtw89_debug(rtwdev, RTW89_DBG_RFK_TRACK, + "[RX_DCK] path=%d current thermal=0x%x delta=0x%x\n", + path, cur_thermal, delta); + + if (delta >= RTW8852C_RX_DCK_TH) { + rtw8852c_rx_dck(rtwdev, RTW89_PHY_0, false); + return; + } + } +} + void rtw8852c_dpk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx) { u32 tx_en; diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852c_rfk.h b/drivers/net/wireless/realtek/rtw89/rtw8852c_rfk.h index c32756f0c01a..5118a49da8d3 100644 --- a/drivers/net/wireless/realtek/rtw89/rtw8852c_rfk.h +++ b/drivers/net/wireless/realtek/rtw89/rtw8852c_rfk.h @@ -12,6 +12,7 @@ void rtw8852c_rck(struct rtw89_dev *rtwdev); void rtw8852c_dack(struct rtw89_dev *rtwdev); void rtw8852c_iqk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx); void rtw8852c_rx_dck(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy_idx, bool is_afe); +void rtw8852c_rx_dck_track(struct rtw89_dev *rtwdev); void rtw8852c_dpk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy); void rtw8852c_dpk_track(struct rtw89_dev *rtwdev); void rtw8852c_tssi(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy); diff --git a/drivers/net/wireless/realtek/rtw89/sar.c b/drivers/net/wireless/realtek/rtw89/sar.c index 097c87899cea..eb2d3ec28775 100644 --- a/drivers/net/wireless/realtek/rtw89/sar.c +++ b/drivers/net/wireless/realtek/rtw89/sar.c @@ -5,15 +5,122 @@ #include "debug.h" #include "sar.h" +static enum rtw89_sar_subband rtw89_sar_get_subband(struct rtw89_dev *rtwdev, + u32 center_freq) +{ + switch (center_freq) { + default: + rtw89_debug(rtwdev, RTW89_DBG_SAR, + "center freq: %u to SAR subband is unhandled\n", + center_freq); + fallthrough; + case 2412 ... 2484: + return RTW89_SAR_2GHZ_SUBBAND; + case 5180 ... 5320: + return RTW89_SAR_5GHZ_SUBBAND_1_2; + case 5500 ... 5720: + return RTW89_SAR_5GHZ_SUBBAND_2_E; + case 5745 ... 5825: + return RTW89_SAR_5GHZ_SUBBAND_3; + case 5955 ... 6155: + return RTW89_SAR_6GHZ_SUBBAND_5_L; + case 6175 ... 6415: + return RTW89_SAR_6GHZ_SUBBAND_5_H; + case 6435 ... 6515: + return RTW89_SAR_6GHZ_SUBBAND_6; + case 6535 ... 6695: + return RTW89_SAR_6GHZ_SUBBAND_7_L; + case 6715 ... 6855: + return RTW89_SAR_6GHZ_SUBBAND_7_H; + + /* freq 6875 (ch 185, 20MHz) spans RTW89_SAR_6GHZ_SUBBAND_7_H + * and RTW89_SAR_6GHZ_SUBBAND_8, so directly describe it with + * struct rtw89_sar_span in the following. + */ + + case 6895 ... 7115: + return RTW89_SAR_6GHZ_SUBBAND_8; + } +} + +struct rtw89_sar_span { + enum rtw89_sar_subband subband_low; + enum rtw89_sar_subband subband_high; +}; + +#define RTW89_SAR_SPAN_VALID(span) ((span)->subband_high) + +#define RTW89_SAR_6GHZ_SPAN_HEAD 6145 +#define RTW89_SAR_6GHZ_SPAN_IDX(center_freq) \ + ((((int)(center_freq) - RTW89_SAR_6GHZ_SPAN_HEAD) / 5) / 2) + +#define RTW89_DECL_SAR_6GHZ_SPAN(center_freq, subband_l, subband_h) \ + [RTW89_SAR_6GHZ_SPAN_IDX(center_freq)] = { \ + .subband_low = RTW89_SAR_6GHZ_ ## subband_l, \ + .subband_high = RTW89_SAR_6GHZ_ ## subband_h, \ + } + +/* Since 6GHz SAR subbands are not edge aligned, some cases span two SAR + * subbands. In the following, we describe each of them with rtw89_sar_span. + */ +static const struct rtw89_sar_span rtw89_sar_overlapping_6ghz[] = { + RTW89_DECL_SAR_6GHZ_SPAN(6145, SUBBAND_5_L, SUBBAND_5_H), + RTW89_DECL_SAR_6GHZ_SPAN(6165, SUBBAND_5_L, SUBBAND_5_H), + RTW89_DECL_SAR_6GHZ_SPAN(6185, SUBBAND_5_L, SUBBAND_5_H), + RTW89_DECL_SAR_6GHZ_SPAN(6505, SUBBAND_6, SUBBAND_7_L), + RTW89_DECL_SAR_6GHZ_SPAN(6525, SUBBAND_6, SUBBAND_7_L), + RTW89_DECL_SAR_6GHZ_SPAN(6545, SUBBAND_6, SUBBAND_7_L), + RTW89_DECL_SAR_6GHZ_SPAN(6665, SUBBAND_7_L, SUBBAND_7_H), + RTW89_DECL_SAR_6GHZ_SPAN(6705, SUBBAND_7_L, SUBBAND_7_H), + RTW89_DECL_SAR_6GHZ_SPAN(6825, SUBBAND_7_H, SUBBAND_8), + RTW89_DECL_SAR_6GHZ_SPAN(6865, SUBBAND_7_H, SUBBAND_8), + RTW89_DECL_SAR_6GHZ_SPAN(6875, SUBBAND_7_H, SUBBAND_8), + RTW89_DECL_SAR_6GHZ_SPAN(6885, SUBBAND_7_H, SUBBAND_8), +}; + static int rtw89_query_sar_config_common(struct rtw89_dev *rtwdev, s32 *cfg) { struct rtw89_sar_cfg_common *rtwsar = &rtwdev->sar.cfg_common; - enum rtw89_subband subband = rtwdev->hal.current_subband; + struct rtw89_hal *hal = &rtwdev->hal; + enum rtw89_band band = hal->current_band_type; + u32 center_freq = hal->current_freq; + const struct rtw89_sar_span *span = NULL; + enum rtw89_sar_subband subband_l, subband_h; + int idx; + + if (band == RTW89_BAND_6G) { + idx = RTW89_SAR_6GHZ_SPAN_IDX(center_freq); + /* To decrease size of rtw89_sar_overlapping_6ghz[], + * RTW89_SAR_6GHZ_SPAN_IDX() truncates the leading NULLs + * to make first span as index 0 of the table. So, if center + * frequency is less than the first one, it will get netative. + */ + if (idx >= 0 && idx < ARRAY_SIZE(rtw89_sar_overlapping_6ghz)) + span = &rtw89_sar_overlapping_6ghz[idx]; + } + + if (span && RTW89_SAR_SPAN_VALID(span)) { + subband_l = span->subband_low; + subband_h = span->subband_high; + } else { + subband_l = rtw89_sar_get_subband(rtwdev, center_freq); + subband_h = subband_l; + } + + rtw89_debug(rtwdev, RTW89_DBG_SAR, + "for {band %u, center_freq %u}, SAR subband: {%u, %u}\n", + band, center_freq, subband_l, subband_h); - if (!rtwsar->set[subband]) + if (!rtwsar->set[subband_l] && !rtwsar->set[subband_h]) return -ENODATA; - *cfg = rtwsar->cfg[subband]; + if (!rtwsar->set[subband_l]) + *cfg = rtwsar->cfg[subband_h]; + else if (!rtwsar->set[subband_h]) + *cfg = rtwsar->cfg[subband_l]; + else + *cfg = min(rtwsar->cfg[subband_l], rtwsar->cfg[subband_h]); + return 0; } @@ -128,21 +235,20 @@ exit: return ret; } -static const u8 rtw89_common_sar_subband_map[] = { - RTW89_CH_2G, - RTW89_CH_5G_BAND_1, - RTW89_CH_5G_BAND_3, - RTW89_CH_5G_BAND_4, -}; - static const struct cfg80211_sar_freq_ranges rtw89_common_sar_freq_ranges[] = { { .start_freq = 2412, .end_freq = 2484, }, { .start_freq = 5180, .end_freq = 5320, }, { .start_freq = 5500, .end_freq = 5720, }, { .start_freq = 5745, .end_freq = 5825, }, + { .start_freq = 5955, .end_freq = 6155, }, + { .start_freq = 6175, .end_freq = 6415, }, + { .start_freq = 6435, .end_freq = 6515, }, + { .start_freq = 6535, .end_freq = 6695, }, + { .start_freq = 6715, .end_freq = 6875, }, + { .start_freq = 6875, .end_freq = 7115, }, }; -static_assert(ARRAY_SIZE(rtw89_common_sar_subband_map) == +static_assert(RTW89_SAR_SUBBAND_NR == ARRAY_SIZE(rtw89_common_sar_freq_ranges)); const struct cfg80211_sar_capa rtw89_sar_capa = { @@ -159,7 +265,6 @@ int rtw89_ops_set_sar_specs(struct ieee80211_hw *hw, u8 fct; u32 freq_start; u32 freq_end; - u32 band; s32 power; u32 i, idx; @@ -175,15 +280,14 @@ int rtw89_ops_set_sar_specs(struct ieee80211_hw *hw, freq_start = rtw89_common_sar_freq_ranges[idx].start_freq; freq_end = rtw89_common_sar_freq_ranges[idx].end_freq; - band = rtw89_common_sar_subband_map[idx]; power = sar->sub_specs[i].power; - rtw89_info(rtwdev, "On freq %u to %u, ", freq_start, freq_end); - rtw89_info(rtwdev, "set SAR power limit %d (unit: 1/%lu dBm)\n", - power, BIT(fct)); + rtw89_debug(rtwdev, RTW89_DBG_SAR, + "On freq %u to %u, set SAR limit %d (unit: 1/%lu dBm)\n", + freq_start, freq_end, power, BIT(fct)); - sar_common.set[band] = true; - sar_common.cfg[band] = power; + sar_common.set[idx] = true; + sar_common.cfg[idx] = power; } return rtw89_apply_sar_common(rtwdev, &sar_common); diff --git a/drivers/net/wireless/silabs/wfx/fwio.c b/drivers/net/wireless/silabs/wfx/fwio.c index 3d1b8a135dc0..52c7f560b062 100644 --- a/drivers/net/wireless/silabs/wfx/fwio.c +++ b/drivers/net/wireless/silabs/wfx/fwio.c @@ -286,8 +286,7 @@ static int load_firmware_secure(struct wfx_dev *wdev) error: kfree(buf); - if (fw) - release_firmware(fw); + release_firmware(fw); if (ret) print_boot_status(wdev); return ret; diff --git a/drivers/net/wireless/st/cw1200/bh.c b/drivers/net/wireless/st/cw1200/bh.c index 10e019cddcc6..3b4ded2ac801 100644 --- a/drivers/net/wireless/st/cw1200/bh.c +++ b/drivers/net/wireless/st/cw1200/bh.c @@ -327,18 +327,12 @@ static int cw1200_bh_rx_helper(struct cw1200_common *priv, if (WARN_ON(wsm_handle_rx(priv, wsm_id, wsm, &skb_rx))) goto err; - if (skb_rx) { - dev_kfree_skb(skb_rx); - skb_rx = NULL; - } + dev_kfree_skb(skb_rx); return 0; err: - if (skb_rx) { - dev_kfree_skb(skb_rx); - skb_rx = NULL; - } + dev_kfree_skb(skb_rx); return -1; } diff --git a/drivers/net/wireless/virt_wifi.c b/drivers/net/wireless/virt_wifi.c index 514f2c1124b6..ba14d83353a4 100644 --- a/drivers/net/wireless/virt_wifi.c +++ b/drivers/net/wireless/virt_wifi.c @@ -654,7 +654,7 @@ static int __init virt_wifi_init_module(void) { int err; - /* Guaranteed to be locallly-administered and not multicast. */ + /* Guaranteed to be locally-administered and not multicast. */ eth_random_addr(fake_router_bssid); err = register_netdevice_notifier(&virt_wifi_notifier); diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h index d9dea4829c86..8174d7b2966c 100644 --- a/drivers/net/xen-netback/common.h +++ b/drivers/net/xen-netback/common.h @@ -48,7 +48,6 @@ #include <linux/debugfs.h> typedef unsigned int pending_ring_idx_t; -#define INVALID_PENDING_RING_IDX (~0U) struct pending_tx_info { struct xen_netif_tx_request req; /* tx request */ @@ -82,8 +81,6 @@ struct xenvif_rx_meta { /* Discriminate from any valid pending_idx value. */ #define INVALID_PENDING_IDX 0xFFFF -#define MAX_BUFFER_OFFSET XEN_PAGE_SIZE - #define MAX_PENDING_REQS XEN_NETIF_TX_RING_SIZE /* The maximum number of frags is derived from the size of a grant (same @@ -367,11 +364,6 @@ void xenvif_free(struct xenvif *vif); int xenvif_xenbus_init(void); void xenvif_xenbus_fini(void); -int xenvif_schedulable(struct xenvif *vif); - -int xenvif_queue_stopped(struct xenvif_queue *queue); -void xenvif_wake_queue(struct xenvif_queue *queue); - /* (Un)Map communication rings. */ void xenvif_unmap_frontend_data_rings(struct xenvif_queue *queue); int xenvif_map_frontend_data_rings(struct xenvif_queue *queue, @@ -394,7 +386,6 @@ int xenvif_dealloc_kthread(void *data); irqreturn_t xenvif_ctrl_irq_fn(int irq, void *data); bool xenvif_have_rx_work(struct xenvif_queue *queue, bool test_kthread); -void xenvif_rx_action(struct xenvif_queue *queue); void xenvif_rx_queue_tail(struct xenvif_queue *queue, struct sk_buff *skb); void xenvif_carrier_on(struct xenvif *vif); @@ -403,9 +394,6 @@ void xenvif_carrier_on(struct xenvif *vif); void xenvif_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *ubuf, bool zerocopy_success); -/* Unmap a pending page and release it back to the guest */ -void xenvif_idx_unmap(struct xenvif_queue *queue, u16 pending_idx); - static inline pending_ring_idx_t nr_pending_reqs(struct xenvif_queue *queue) { return MAX_PENDING_REQS - diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index 8e035374a370..fb32ae82d9b0 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -69,7 +69,7 @@ void xenvif_skb_zerocopy_complete(struct xenvif_queue *queue) wake_up(&queue->dealloc_wq); } -int xenvif_schedulable(struct xenvif *vif) +static int xenvif_schedulable(struct xenvif *vif) { return netif_running(vif->dev) && test_bit(VIF_STATUS_CONNECTED, &vif->status) && @@ -177,20 +177,6 @@ irqreturn_t xenvif_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } -int xenvif_queue_stopped(struct xenvif_queue *queue) -{ - struct net_device *dev = queue->vif->dev; - unsigned int id = queue->id; - return netif_tx_queue_stopped(netdev_get_tx_queue(dev, id)); -} - -void xenvif_wake_queue(struct xenvif_queue *queue) -{ - struct net_device *dev = queue->vif->dev; - unsigned int id = queue->id; - netif_tx_wake_queue(netdev_get_tx_queue(dev, id)); -} - static u16 xenvif_select_queue(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev) { diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index d93814c14a23..fc61a4418737 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -112,6 +112,8 @@ static void make_tx_response(struct xenvif_queue *queue, s8 st); static void push_tx_responses(struct xenvif_queue *queue); +static void xenvif_idx_unmap(struct xenvif_queue *queue, u16 pending_idx); + static inline int tx_work_todo(struct xenvif_queue *queue); static inline unsigned long idx_to_pfn(struct xenvif_queue *queue, @@ -1418,7 +1420,7 @@ static void push_tx_responses(struct xenvif_queue *queue) notify_remote_via_irq(queue->tx_irq); } -void xenvif_idx_unmap(struct xenvif_queue *queue, u16 pending_idx) +static void xenvif_idx_unmap(struct xenvif_queue *queue, u16 pending_idx) { int ret; struct gnttab_unmap_grant_ref tx_unmap_op; diff --git a/drivers/net/xen-netback/rx.c b/drivers/net/xen-netback/rx.c index dbac4c03d21a..8df2c736fd23 100644 --- a/drivers/net/xen-netback/rx.c +++ b/drivers/net/xen-netback/rx.c @@ -486,7 +486,7 @@ static void xenvif_rx_skb(struct xenvif_queue *queue) #define RX_BATCH_SIZE 64 -void xenvif_rx_action(struct xenvif_queue *queue) +static void xenvif_rx_action(struct xenvif_queue *queue) { struct sk_buff_head completed_skbs; unsigned int work_done = 0; diff --git a/drivers/ptp/ptp_ocp.c b/drivers/ptp/ptp_ocp.c index 4519ef42b458..e59ea2173aac 100644 --- a/drivers/ptp/ptp_ocp.c +++ b/drivers/ptp/ptp_ocp.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2020 Facebook */ +#include <linux/bits.h> #include <linux/err.h> #include <linux/kernel.h> #include <linux/module.h> @@ -88,10 +89,10 @@ struct tod_reg { #define TOD_CTRL_DISABLE_FMT_A BIT(17) #define TOD_CTRL_DISABLE_FMT_B BIT(16) #define TOD_CTRL_ENABLE BIT(0) -#define TOD_CTRL_GNSS_MASK ((1U << 4) - 1) +#define TOD_CTRL_GNSS_MASK GENMASK(3, 0) #define TOD_CTRL_GNSS_SHIFT 24 -#define TOD_STATUS_UTC_MASK 0xff +#define TOD_STATUS_UTC_MASK GENMASK(7, 0) #define TOD_STATUS_UTC_VALID BIT(8) #define TOD_STATUS_LEAP_ANNOUNCE BIT(12) #define TOD_STATUS_LEAP_VALID BIT(16) @@ -205,7 +206,7 @@ struct frequency_reg { #define FREQ_STATUS_VALID BIT(31) #define FREQ_STATUS_ERROR BIT(30) #define FREQ_STATUS_OVERRUN BIT(29) -#define FREQ_STATUS_MASK (BIT(24) - 1) +#define FREQ_STATUS_MASK GENMASK(23, 0) struct ptp_ocp_flash_info { const char *name; @@ -674,9 +675,9 @@ static const struct ocp_selector ptp_ocp_clock[] = { { } }; +#define SMA_DISABLE BIT(16) #define SMA_ENABLE BIT(15) -#define SMA_SELECT_MASK ((1U << 15) - 1) -#define SMA_DISABLE 0x10000 +#define SMA_SELECT_MASK GENMASK(14, 0) static const struct ocp_selector ptp_ocp_sma_in[] = { { .name = "10Mhz", .value = 0x0000 }, @@ -2154,7 +2155,7 @@ ptp_ocp_fb_set_pins(struct ptp_ocp *bp) struct ptp_pin_desc *config; int i; - config = kzalloc(sizeof(*config) * 4, GFP_KERNEL); + config = kcalloc(4, sizeof(*config), GFP_KERNEL); if (!config) return -ENOMEM; @@ -3440,7 +3441,7 @@ ptp_ocp_tod_status_show(struct seq_file *s, void *data) val = ioread32(&bp->tod->utc_status); seq_printf(s, "UTC status register: 0x%08X\n", val); - seq_printf(s, "UTC offset: %d valid:%d\n", + seq_printf(s, "UTC offset: %ld valid:%d\n", val & TOD_STATUS_UTC_MASK, val & TOD_STATUS_UTC_VALID ? 1 : 0); seq_printf(s, "Leap second info valid:%d, Leap second announce %d\n", val & TOD_STATUS_LEAP_VALID ? 1 : 0, @@ -3700,10 +3701,8 @@ ptp_ocp_detach(struct ptp_ocp *bp) serial8250_unregister_port(bp->mac_port); if (bp->nmea_port != -1) serial8250_unregister_port(bp->nmea_port); - if (bp->spi_flash) - platform_device_unregister(bp->spi_flash); - if (bp->i2c_ctrl) - platform_device_unregister(bp->i2c_ctrl); + platform_device_unregister(bp->spi_flash); + platform_device_unregister(bp->i2c_ctrl); if (bp->i2c_clk) clk_hw_unregister_fixed_rate(bp->i2c_clk); if (bp->n_irqs) @@ -3773,7 +3772,6 @@ ptp_ocp_probe(struct pci_dev *pdev, const struct pci_device_id *id) out: ptp_ocp_detach(bp); - pci_set_drvdata(pdev, NULL); out_disable: pci_disable_device(pdev); out_free: @@ -3789,7 +3787,6 @@ ptp_ocp_remove(struct pci_dev *pdev) devlink_unregister(devlink); ptp_ocp_detach(bp); - pci_set_drvdata(pdev, NULL); pci_disable_device(pdev); devlink_free(devlink); diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 75d40acb60c1..5c65ae6b8154 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -76,6 +76,7 @@ #define IEEE80211_STYPE_ACTION 0x00D0 /* control */ +#define IEEE80211_STYPE_TRIGGER 0x0020 #define IEEE80211_STYPE_CTL_EXT 0x0060 #define IEEE80211_STYPE_BACK_REQ 0x0080 #define IEEE80211_STYPE_BACK 0x0090 @@ -295,6 +296,17 @@ static inline u16 ieee80211_sn_sub(u16 sn1, u16 sn2) #define IEEE80211_HT_CTL_LEN 4 +/* trigger type within common_info of trigger frame */ +#define IEEE80211_TRIGGER_TYPE_MASK 0xf +#define IEEE80211_TRIGGER_TYPE_BASIC 0x0 +#define IEEE80211_TRIGGER_TYPE_BFRP 0x1 +#define IEEE80211_TRIGGER_TYPE_MU_BAR 0x2 +#define IEEE80211_TRIGGER_TYPE_MU_RTS 0x3 +#define IEEE80211_TRIGGER_TYPE_BSRP 0x4 +#define IEEE80211_TRIGGER_TYPE_GCR_MU_BAR 0x5 +#define IEEE80211_TRIGGER_TYPE_BQRP 0x6 +#define IEEE80211_TRIGGER_TYPE_NFRP 0x7 + struct ieee80211_hdr { __le16 frame_control; __le16 duration_id; @@ -324,6 +336,15 @@ struct ieee80211_qos_hdr { __le16 qos_ctrl; } __packed __aligned(2); +struct ieee80211_trigger { + __le16 frame_control; + __le16 duration; + u8 ra[ETH_ALEN]; + u8 ta[ETH_ALEN]; + __le64 common_info; + u8 variable[]; +} __packed __aligned(2); + /** * ieee80211_has_tods - check if IEEE80211_FCTL_TODS is set * @fc: frame control bytes in little-endian byteorder @@ -730,6 +751,16 @@ static inline bool ieee80211_is_qos_nullfunc(__le16 fc) } /** + * ieee80211_is_trigger - check if frame is trigger frame + * @fc: frame control field in little-endian byteorder + */ +static inline bool ieee80211_is_trigger(__le16 fc) +{ + return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == + cpu_to_le16(IEEE80211_FTYPE_CTL | IEEE80211_STYPE_TRIGGER); +} + +/** * ieee80211_is_any_nullfunc - check if frame is regular or QoS nullfunc frame * @fc: frame control bytes in little-endian byteorder */ diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index b42294739063..523025106a64 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -46,10 +46,10 @@ static inline void macvlan_count_rx(const struct macvlan_dev *vlan, pcpu_stats = get_cpu_ptr(vlan->pcpu_stats); u64_stats_update_begin(&pcpu_stats->syncp); - pcpu_stats->rx_packets++; - pcpu_stats->rx_bytes += len; + u64_stats_inc(&pcpu_stats->rx_packets); + u64_stats_add(&pcpu_stats->rx_bytes, len); if (multicast) - pcpu_stats->rx_multicast++; + u64_stats_inc(&pcpu_stats->rx_multicast); u64_stats_update_end(&pcpu_stats->syncp); put_cpu_ptr(vlan->pcpu_stats); } else { diff --git a/include/linux/if_team.h b/include/linux/if_team.h index add607943c95..fc985e5c739d 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -12,11 +12,11 @@ #include <uapi/linux/if_team.h> struct team_pcpu_stats { - u64 rx_packets; - u64 rx_bytes; - u64 rx_multicast; - u64 tx_packets; - u64 tx_bytes; + u64_stats_t rx_packets; + u64_stats_t rx_bytes; + u64_stats_t rx_multicast; + u64_stats_t tx_packets; + u64_stats_t tx_bytes; struct u64_stats_sync syncp; u32 rx_dropped; u32 tx_dropped; diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 2be4dd7e90a9..e00c4ee81ff7 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -118,11 +118,11 @@ static inline void vlan_drop_rx_stag_filter_info(struct net_device *dev) * @tx_dropped: number of tx drops */ struct vlan_pcpu_stats { - u64 rx_packets; - u64 rx_bytes; - u64 rx_multicast; - u64 tx_packets; - u64 tx_bytes; + u64_stats_t rx_packets; + u64_stats_t rx_bytes; + u64_stats_t rx_multicast; + u64_stats_t tx_packets; + u64_stats_t tx_bytes; struct u64_stats_sync syncp; u32 rx_errors; u32 tx_dropped; diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 604b85dd770a..b5f58fd37a0f 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -387,21 +387,6 @@ enum { }; enum { - MLX5_DEV_CAP_FLAG_XRC = 1LL << 3, - MLX5_DEV_CAP_FLAG_BAD_PKEY_CNTR = 1LL << 8, - MLX5_DEV_CAP_FLAG_BAD_QKEY_CNTR = 1LL << 9, - MLX5_DEV_CAP_FLAG_APM = 1LL << 17, - MLX5_DEV_CAP_FLAG_ATOMIC = 1LL << 18, - MLX5_DEV_CAP_FLAG_BLOCK_MCAST = 1LL << 23, - MLX5_DEV_CAP_FLAG_ON_DMND_PG = 1LL << 24, - MLX5_DEV_CAP_FLAG_CQ_MODER = 1LL << 29, - MLX5_DEV_CAP_FLAG_RESIZE_CQ = 1LL << 30, - MLX5_DEV_CAP_FLAG_DCT = 1LL << 37, - MLX5_DEV_CAP_FLAG_SIG_HAND_OVER = 1LL << 40, - MLX5_DEV_CAP_FLAG_CMDIF_CSUM = 3LL << 46, -}; - -enum { MLX5_ROCE_VERSION_1 = 0, MLX5_ROCE_VERSION_2 = 2, }; @@ -455,6 +440,7 @@ enum { MLX5_OPCODE_UMR = 0x25, + MLX5_OPCODE_ACCESS_ASO = 0x2d, }; enum { @@ -496,10 +482,6 @@ enum { }; enum { - MLX5_CAP_OFF_CMDIF_CSUM = 46, -}; - -enum { /* * Max wqe size for rdma read is 512 bytes, so this * limits our max_sge_rd as the wqe needs to fit: @@ -840,7 +822,10 @@ struct mlx5_cqe64 { __be32 timestamp_l; __be32 sop_drop_qpn; __be16 wqe_counter; - u8 signature; + union { + u8 signature; + u8 validity_iteration_count; + }; u8 op_own; }; @@ -872,6 +857,11 @@ enum { MLX5_CQE_FORMAT_CSUM_STRIDX = 0x3, }; +enum { + MLX5_CQE_COMPRESS_LAYOUT_BASIC = 0, + MLX5_CQE_COMPRESS_LAYOUT_ENHANCED = 1, +}; + #define MLX5_MINI_CQE_ARRAY_SIZE 8 static inline u8 mlx5_get_cqe_format(struct mlx5_cqe64 *cqe) @@ -884,6 +874,12 @@ static inline u8 get_cqe_opcode(struct mlx5_cqe64 *cqe) return cqe->op_own >> 4; } +static inline u8 get_cqe_enhanced_num_mini_cqes(struct mlx5_cqe64 *cqe) +{ + /* num_of_mini_cqes is zero based */ + return get_cqe_opcode(cqe) + 1; +} + static inline u8 get_cqe_lro_tcppsh(struct mlx5_cqe64 *cqe) { return (cqe->lro.tcppsh_abort_dupack >> 6) & 1; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 5040cd774c5a..76d7661e3e63 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -676,6 +676,7 @@ struct mlx5e_resources { enum mlx5_sw_icm_type { MLX5_SW_ICM_TYPE_STEERING, MLX5_SW_ICM_TYPE_HEADER_MODIFY, + MLX5_SW_ICM_TYPE_HEADER_MODIFY_PATTERN, }; #define MLX5_MAX_RESERVED_GIDS 8 diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 8135713b0d2d..ece3e35622d7 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -212,6 +212,19 @@ struct mlx5_flow_group * mlx5_create_flow_group(struct mlx5_flow_table *ft, u32 *in); void mlx5_destroy_flow_group(struct mlx5_flow_group *fg); +struct mlx5_exe_aso { + u32 object_id; + u8 type; + u8 return_reg_id; + union { + u32 ctrl_data; + struct { + u8 meter_idx; + u8 init_color; + } flow_meter; + }; +}; + struct mlx5_fs_vlan { u16 ethtype; u16 vid; @@ -237,6 +250,7 @@ struct mlx5_flow_act { struct mlx5_fs_vlan vlan[MLX5_FS_VLAN_DEPTH]; struct ib_counters *counters; struct mlx5_flow_group *fg; + struct mlx5_exe_aso exe_aso; }; #define MLX5_DECLARE_FLOW_ACT(name) \ diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index fd7d083a34d3..8e87eb47f9dc 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -442,7 +442,9 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 max_modify_header_actions[0x8]; u8 max_ft_level[0x8]; - u8 reserved_at_40[0x20]; + u8 reserved_at_40[0x6]; + u8 execute_aso[0x1]; + u8 reserved_at_47[0x19]; u8 reserved_at_60[0x2]; u8 reformat_insert[0x1]; @@ -940,7 +942,17 @@ struct mlx5_ifc_qos_cap_bits { u8 max_tsar_bw_share[0x20]; - u8 reserved_at_100[0x700]; + u8 reserved_at_100[0x20]; + + u8 reserved_at_120[0x3]; + u8 log_meter_aso_granularity[0x5]; + u8 reserved_at_128[0x3]; + u8 log_meter_aso_max_alloc[0x5]; + u8 reserved_at_130[0x3]; + u8 log_max_num_meter_aso[0x5]; + u8 reserved_at_138[0x8]; + + u8 reserved_at_140[0x6c0]; }; struct mlx5_ifc_debug_cap_bits { @@ -1086,11 +1098,14 @@ struct mlx5_ifc_device_mem_cap_bits { u8 log_sw_icm_alloc_granularity[0x6]; u8 log_steering_sw_icm_size[0x8]; - u8 reserved_at_120[0x20]; + u8 reserved_at_120[0x18]; + u8 log_header_modify_pattern_sw_icm_size[0x8]; u8 header_modify_sw_icm_start_address[0x40]; - u8 reserved_at_180[0x80]; + u8 reserved_at_180[0x40]; + + u8 header_modify_pattern_sw_icm_start_address[0x40]; u8 memic_operations[0x20]; @@ -1426,7 +1441,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_120[0xa]; u8 log_max_ra_req_dc[0x6]; - u8 reserved_at_130[0xa]; + u8 reserved_at_130[0x9]; + u8 vnic_env_cq_overrun[0x1]; u8 log_max_ra_res_dc[0x6]; u8 reserved_at_140[0x5]; @@ -1621,7 +1637,11 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 nic_receive_steering_discard[0x1]; u8 receive_discard_vport_down[0x1]; u8 transmit_discard_vport_down[0x1]; - u8 reserved_at_343[0x5]; + u8 eq_overrun_count[0x1]; + u8 reserved_at_344[0x1]; + u8 invalid_command_count[0x1]; + u8 quota_exceeded_count[0x1]; + u8 reserved_at_347[0x1]; u8 log_max_flow_counter_bulk[0x8]; u8 max_flow_counter_15_0[0x10]; @@ -1719,7 +1739,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_max_dci_errored_streams[0x5]; u8 reserved_at_598[0x8]; - u8 reserved_at_5a0[0x13]; + u8 reserved_at_5a0[0x10]; + u8 enhanced_cqe_compression[0x1]; + u8 reserved_at_5b1[0x2]; u8 log_max_dek[0x5]; u8 reserved_at_5b8[0x4]; u8 mini_cqe_resp_stride_index[0x1]; @@ -3277,6 +3299,7 @@ enum { MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2 = 0x800, MLX5_FLOW_CONTEXT_ACTION_IPSEC_DECRYPT = 0x1000, MLX5_FLOW_CONTEXT_ACTION_IPSEC_ENCRYPT = 0x2000, + MLX5_FLOW_CONTEXT_ACTION_EXECUTE_ASO = 0x4000, }; enum { @@ -3292,6 +3315,38 @@ struct mlx5_ifc_vlan_bits { u8 vid[0xc]; }; +enum { + MLX5_FLOW_METER_COLOR_RED = 0x0, + MLX5_FLOW_METER_COLOR_YELLOW = 0x1, + MLX5_FLOW_METER_COLOR_GREEN = 0x2, + MLX5_FLOW_METER_COLOR_UNDEFINED = 0x3, +}; + +enum { + MLX5_EXE_ASO_FLOW_METER = 0x2, +}; + +struct mlx5_ifc_exe_aso_ctrl_flow_meter_bits { + u8 return_reg_id[0x4]; + u8 aso_type[0x4]; + u8 reserved_at_8[0x14]; + u8 action[0x1]; + u8 init_color[0x2]; + u8 meter_id[0x1]; +}; + +union mlx5_ifc_exe_aso_ctrl { + struct mlx5_ifc_exe_aso_ctrl_flow_meter_bits exe_aso_ctrl_flow_meter; +}; + +struct mlx5_ifc_execute_aso_bits { + u8 valid[0x1]; + u8 reserved_at_1[0x7]; + u8 aso_object_id[0x18]; + + union mlx5_ifc_exe_aso_ctrl exe_aso_ctrl; +}; + struct mlx5_ifc_flow_context_bits { struct mlx5_ifc_vlan_bits push_vlan; @@ -3323,7 +3378,9 @@ struct mlx5_ifc_flow_context_bits { struct mlx5_ifc_fte_match_param_bits match_value; - u8 reserved_at_1200[0x600]; + struct mlx5_ifc_execute_aso_bits execute_aso[4]; + + u8 reserved_at_1300[0x500]; union mlx5_ifc_dest_format_struct_flow_counter_list_auto_bits destination[]; }; @@ -3391,11 +3448,21 @@ struct mlx5_ifc_vnic_diagnostic_statistics_bits { u8 transmit_discard_vport_down[0x40]; - u8 reserved_at_140[0xa0]; + u8 async_eq_overrun[0x20]; + + u8 comp_eq_overrun[0x20]; + + u8 reserved_at_180[0x20]; + + u8 invalid_command[0x20]; + + u8 quota_exceeded_command[0x20]; u8 internal_rq_out_of_buffer[0x20]; - u8 reserved_at_200[0xe00]; + u8 cq_overrun[0x20]; + + u8 reserved_at_220[0xde0]; }; struct mlx5_ifc_traffic_counter_bits { @@ -4074,7 +4141,8 @@ struct mlx5_ifc_cqc_bits { u8 cqe_comp_en[0x1]; u8 mini_cqe_res_format[0x2]; u8 st[0x4]; - u8 reserved_at_18[0x8]; + u8 reserved_at_18[0x6]; + u8 cqe_compression_layout[0x2]; u8 reserved_at_20[0x20]; @@ -5970,7 +6038,9 @@ struct mlx5_ifc_general_obj_in_cmd_hdr_bits { u8 obj_id[0x20]; - u8 reserved_at_60[0x20]; + u8 reserved_at_60[0x3]; + u8 log_obj_range[0x5]; + u8 reserved_at_68[0x18]; }; struct mlx5_ifc_general_obj_out_cmd_hdr_bits { @@ -11370,12 +11440,14 @@ enum { MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY = BIT_ULL(0xc), MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_IPSEC = BIT_ULL(0x13), MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_SAMPLER = BIT_ULL(0x20), + MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_FLOW_METER_ASO = BIT_ULL(0x24), }; enum { MLX5_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY = 0xc, MLX5_GENERAL_OBJECT_TYPES_IPSEC = 0x13, MLX5_GENERAL_OBJECT_TYPES_SAMPLER = 0x20, + MLX5_GENERAL_OBJECT_TYPES_FLOW_METER_ASO = 0x24, }; enum { @@ -11448,6 +11520,61 @@ struct mlx5_ifc_create_encryption_key_in_bits { struct mlx5_ifc_encryption_key_obj_bits encryption_key_object; }; +enum { + MLX5_FLOW_METER_MODE_BYTES_IP_LENGTH = 0x0, + MLX5_FLOW_METER_MODE_BYTES_CALC_WITH_L2 = 0x1, + MLX5_FLOW_METER_MODE_BYTES_CALC_WITH_L2_IPG = 0x2, + MLX5_FLOW_METER_MODE_NUM_PACKETS = 0x3, +}; + +struct mlx5_ifc_flow_meter_parameters_bits { + u8 valid[0x1]; + u8 bucket_overflow[0x1]; + u8 start_color[0x2]; + u8 both_buckets_on_green[0x1]; + u8 reserved_at_5[0x1]; + u8 meter_mode[0x2]; + u8 reserved_at_8[0x18]; + + u8 reserved_at_20[0x20]; + + u8 reserved_at_40[0x3]; + u8 cbs_exponent[0x5]; + u8 cbs_mantissa[0x8]; + u8 reserved_at_50[0x3]; + u8 cir_exponent[0x5]; + u8 cir_mantissa[0x8]; + + u8 reserved_at_60[0x20]; + + u8 reserved_at_80[0x3]; + u8 ebs_exponent[0x5]; + u8 ebs_mantissa[0x8]; + u8 reserved_at_90[0x3]; + u8 eir_exponent[0x5]; + u8 eir_mantissa[0x8]; + + u8 reserved_at_a0[0x60]; +}; + +struct mlx5_ifc_flow_meter_aso_obj_bits { + u8 modify_field_select[0x40]; + + u8 reserved_at_40[0x40]; + + u8 reserved_at_80[0x8]; + u8 meter_aso_access_pd[0x18]; + + u8 reserved_at_a0[0x160]; + + struct mlx5_ifc_flow_meter_parameters_bits flow_meter_parameters[2]; +}; + +struct mlx5_ifc_create_flow_meter_aso_obj_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr; + struct mlx5_ifc_flow_meter_aso_obj_bits flow_meter_aso_obj; +}; + struct mlx5_ifc_sampler_obj_bits { u8 modify_field_select[0x40]; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f615a66c89e9..89afa4f7747d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2636,10 +2636,10 @@ struct packet_offload { /* often modified stats are per-CPU, other are shared (netdev->stats) */ struct pcpu_sw_netstats { - u64 rx_packets; - u64 rx_bytes; - u64 tx_packets; - u64 tx_bytes; + u64_stats_t rx_packets; + u64_stats_t rx_bytes; + u64_stats_t tx_packets; + u64_stats_t tx_bytes; struct u64_stats_sync syncp; } __aligned(4 * sizeof(u64)); @@ -2656,8 +2656,8 @@ static inline void dev_sw_netstats_rx_add(struct net_device *dev, unsigned int l struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); u64_stats_update_begin(&tstats->syncp); - tstats->rx_bytes += len; - tstats->rx_packets++; + u64_stats_add(&tstats->rx_bytes, len); + u64_stats_inc(&tstats->rx_packets); u64_stats_update_end(&tstats->syncp); } @@ -2668,8 +2668,8 @@ static inline void dev_sw_netstats_tx_add(struct net_device *dev, struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); u64_stats_update_begin(&tstats->syncp); - tstats->tx_bytes += len; - tstats->tx_packets += packets; + u64_stats_add(&tstats->tx_bytes, len); + u64_stats_add(&tstats->tx_packets, packets); u64_stats_update_end(&tstats->syncp); } @@ -3981,8 +3981,8 @@ static inline void netdev_tracker_free(struct net_device *dev, #endif } -static inline void dev_hold_track(struct net_device *dev, - netdevice_tracker *tracker, gfp_t gfp) +static inline void netdev_hold(struct net_device *dev, + netdevice_tracker *tracker, gfp_t gfp) { if (dev) { __dev_hold(dev); @@ -3990,8 +3990,8 @@ static inline void dev_hold_track(struct net_device *dev, } } -static inline void dev_put_track(struct net_device *dev, - netdevice_tracker *tracker) +static inline void netdev_put(struct net_device *dev, + netdevice_tracker *tracker) { if (dev) { netdev_tracker_free(dev, tracker); @@ -4004,11 +4004,11 @@ static inline void dev_put_track(struct net_device *dev, * @dev: network device * * Hold reference to device to keep it from being freed. - * Try using dev_hold_track() instead. + * Try using netdev_hold() instead. */ static inline void dev_hold(struct net_device *dev) { - dev_hold_track(dev, NULL, GFP_ATOMIC); + netdev_hold(dev, NULL, GFP_ATOMIC); } /** @@ -4016,17 +4016,17 @@ static inline void dev_hold(struct net_device *dev) * @dev: network device * * Release reference to device to allow it to be freed. - * Try using dev_put_track() instead. + * Try using netdev_put() instead. */ static inline void dev_put(struct net_device *dev) { - dev_put_track(dev, NULL); + netdev_put(dev, NULL); } -static inline void dev_replace_track(struct net_device *odev, - struct net_device *ndev, - netdevice_tracker *tracker, - gfp_t gfp) +static inline void netdev_ref_replace(struct net_device *odev, + struct net_device *ndev, + netdevice_tracker *tracker, + gfp_t gfp) { if (odev) netdev_tracker_free(odev, tracker); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index d3d10556f0fa..82edf0359ab3 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -43,6 +43,7 @@ #include <linux/netfilter/nf_conntrack_common.h> #endif #include <net/net_debug.h> +#include <net/dropreason.h> /** * DOC: skb checksums @@ -337,184 +338,6 @@ struct sk_buff_head { struct sk_buff; -/* The reason of skb drop, which is used in kfree_skb_reason(). - * en...maybe they should be splited by group? - * - * Each item here should also be in 'TRACE_SKB_DROP_REASON', which is - * used to translate the reason to string. - */ -enum skb_drop_reason { - SKB_NOT_DROPPED_YET = 0, - SKB_DROP_REASON_NOT_SPECIFIED, /* drop reason is not specified */ - SKB_DROP_REASON_NO_SOCKET, /* socket not found */ - SKB_DROP_REASON_PKT_TOO_SMALL, /* packet size is too small */ - SKB_DROP_REASON_TCP_CSUM, /* TCP checksum error */ - SKB_DROP_REASON_SOCKET_FILTER, /* dropped by socket filter */ - SKB_DROP_REASON_UDP_CSUM, /* UDP checksum error */ - SKB_DROP_REASON_NETFILTER_DROP, /* dropped by netfilter */ - SKB_DROP_REASON_OTHERHOST, /* packet don't belong to current - * host (interface is in promisc - * mode) - */ - SKB_DROP_REASON_IP_CSUM, /* IP checksum error */ - SKB_DROP_REASON_IP_INHDR, /* there is something wrong with - * IP header (see - * IPSTATS_MIB_INHDRERRORS) - */ - SKB_DROP_REASON_IP_RPFILTER, /* IP rpfilter validate failed. - * see the document for rp_filter - * in ip-sysctl.rst for more - * information - */ - SKB_DROP_REASON_UNICAST_IN_L2_MULTICAST, /* destination address of L2 - * is multicast, but L3 is - * unicast. - */ - SKB_DROP_REASON_XFRM_POLICY, /* xfrm policy check failed */ - SKB_DROP_REASON_IP_NOPROTO, /* no support for IP protocol */ - SKB_DROP_REASON_SOCKET_RCVBUFF, /* socket receive buff is full */ - SKB_DROP_REASON_PROTO_MEM, /* proto memory limition, such as - * udp packet drop out of - * udp_memory_allocated. - */ - SKB_DROP_REASON_TCP_MD5NOTFOUND, /* no MD5 hash and one - * expected, corresponding - * to LINUX_MIB_TCPMD5NOTFOUND - */ - SKB_DROP_REASON_TCP_MD5UNEXPECTED, /* MD5 hash and we're not - * expecting one, corresponding - * to LINUX_MIB_TCPMD5UNEXPECTED - */ - SKB_DROP_REASON_TCP_MD5FAILURE, /* MD5 hash and its wrong, - * corresponding to - * LINUX_MIB_TCPMD5FAILURE - */ - SKB_DROP_REASON_SOCKET_BACKLOG, /* failed to add skb to socket - * backlog (see - * LINUX_MIB_TCPBACKLOGDROP) - */ - SKB_DROP_REASON_TCP_FLAGS, /* TCP flags invalid */ - SKB_DROP_REASON_TCP_ZEROWINDOW, /* TCP receive window size is zero, - * see LINUX_MIB_TCPZEROWINDOWDROP - */ - SKB_DROP_REASON_TCP_OLD_DATA, /* the TCP data reveived is already - * received before (spurious retrans - * may happened), see - * LINUX_MIB_DELAYEDACKLOST - */ - SKB_DROP_REASON_TCP_OVERWINDOW, /* the TCP data is out of window, - * the seq of the first byte exceed - * the right edges of receive - * window - */ - SKB_DROP_REASON_TCP_OFOMERGE, /* the data of skb is already in - * the ofo queue, corresponding to - * LINUX_MIB_TCPOFOMERGE - */ - SKB_DROP_REASON_TCP_RFC7323_PAWS, /* PAWS check, corresponding to - * LINUX_MIB_PAWSESTABREJECTED - */ - SKB_DROP_REASON_TCP_INVALID_SEQUENCE, /* Not acceptable SEQ field */ - SKB_DROP_REASON_TCP_RESET, /* Invalid RST packet */ - SKB_DROP_REASON_TCP_INVALID_SYN, /* Incoming packet has unexpected SYN flag */ - SKB_DROP_REASON_TCP_CLOSE, /* TCP socket in CLOSE state */ - SKB_DROP_REASON_TCP_FASTOPEN, /* dropped by FASTOPEN request socket */ - SKB_DROP_REASON_TCP_OLD_ACK, /* TCP ACK is old, but in window */ - SKB_DROP_REASON_TCP_TOO_OLD_ACK, /* TCP ACK is too old */ - SKB_DROP_REASON_TCP_ACK_UNSENT_DATA, /* TCP ACK for data we haven't sent yet */ - SKB_DROP_REASON_TCP_OFO_QUEUE_PRUNE, /* pruned from TCP OFO queue */ - SKB_DROP_REASON_TCP_OFO_DROP, /* data already in receive queue */ - SKB_DROP_REASON_IP_OUTNOROUTES, /* route lookup failed */ - SKB_DROP_REASON_BPF_CGROUP_EGRESS, /* dropped by - * BPF_PROG_TYPE_CGROUP_SKB - * eBPF program - */ - SKB_DROP_REASON_IPV6DISABLED, /* IPv6 is disabled on the device */ - SKB_DROP_REASON_NEIGH_CREATEFAIL, /* failed to create neigh - * entry - */ - SKB_DROP_REASON_NEIGH_FAILED, /* neigh entry in failed state */ - SKB_DROP_REASON_NEIGH_QUEUEFULL, /* arp_queue for neigh - * entry is full - */ - SKB_DROP_REASON_NEIGH_DEAD, /* neigh entry is dead */ - SKB_DROP_REASON_TC_EGRESS, /* dropped in TC egress HOOK */ - SKB_DROP_REASON_QDISC_DROP, /* dropped by qdisc when packet - * outputting (failed to enqueue to - * current qdisc) - */ - SKB_DROP_REASON_CPU_BACKLOG, /* failed to enqueue the skb to - * the per CPU backlog queue. This - * can be caused by backlog queue - * full (see netdev_max_backlog in - * net.rst) or RPS flow limit - */ - SKB_DROP_REASON_XDP, /* dropped by XDP in input path */ - SKB_DROP_REASON_TC_INGRESS, /* dropped in TC ingress HOOK */ - SKB_DROP_REASON_UNHANDLED_PROTO, /* protocol not implemented - * or not supported - */ - SKB_DROP_REASON_SKB_CSUM, /* sk_buff checksum computation - * error - */ - SKB_DROP_REASON_SKB_GSO_SEG, /* gso segmentation error */ - SKB_DROP_REASON_SKB_UCOPY_FAULT, /* failed to copy data from - * user space, e.g., via - * zerocopy_sg_from_iter() - * or skb_orphan_frags_rx() - */ - SKB_DROP_REASON_DEV_HDR, /* device driver specific - * header/metadata is invalid - */ - /* the device is not ready to xmit/recv due to any of its data - * structure that is not up/ready/initialized, e.g., the IFF_UP is - * not set, or driver specific tun->tfiles[txq] is not initialized - */ - SKB_DROP_REASON_DEV_READY, - SKB_DROP_REASON_FULL_RING, /* ring buffer is full */ - SKB_DROP_REASON_NOMEM, /* error due to OOM */ - SKB_DROP_REASON_HDR_TRUNC, /* failed to trunc/extract the header - * from networking data, e.g., failed - * to pull the protocol header from - * frags via pskb_may_pull() - */ - SKB_DROP_REASON_TAP_FILTER, /* dropped by (ebpf) filter directly - * attached to tun/tap, e.g., via - * TUNSETFILTEREBPF - */ - SKB_DROP_REASON_TAP_TXFILTER, /* dropped by tx filter implemented - * at tun/tap, e.g., check_filter() - */ - SKB_DROP_REASON_ICMP_CSUM, /* ICMP checksum error */ - SKB_DROP_REASON_INVALID_PROTO, /* the packet doesn't follow RFC - * 2211, such as a broadcasts - * ICMP_TIMESTAMP - */ - SKB_DROP_REASON_IP_INADDRERRORS, /* host unreachable, corresponding - * to IPSTATS_MIB_INADDRERRORS - */ - SKB_DROP_REASON_IP_INNOROUTES, /* network unreachable, corresponding - * to IPSTATS_MIB_INADDRERRORS - */ - SKB_DROP_REASON_PKT_TOO_BIG, /* packet size is too big (maybe exceed - * the MTU) - */ - SKB_DROP_REASON_MAX, -}; - -#define SKB_DR_INIT(name, reason) \ - enum skb_drop_reason name = SKB_DROP_REASON_##reason -#define SKB_DR(name) \ - SKB_DR_INIT(name, NOT_SPECIFIED) -#define SKB_DR_SET(name, reason) \ - (name = SKB_DROP_REASON_##reason) -#define SKB_DR_OR(name, reason) \ - do { \ - if (name == SKB_DROP_REASON_NOT_SPECIFIED || \ - name == SKB_NOT_DROPPED_YET) \ - SKB_DR_SET(name, reason); \ - } while (0) - /* To allow 64K frame to be packed as single skb without frag_list we * require 64K/PAGE_SIZE pages plus 1 additional page to allow for * buffers which do not start on a page boundary. diff --git a/include/linux/socket.h b/include/linux/socket.h index 17311ad9f9af..414b8c7bb8f7 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -428,10 +428,6 @@ extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size, extern int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags, struct sockaddr __user *addr, int addr_len); -extern int __sys_accept4_file(struct file *file, unsigned file_flags, - struct sockaddr __user *upeer_sockaddr, - int __user *upeer_addrlen, int flags, - unsigned long nofile); extern struct file *do_accept(struct file *file, unsigned file_flags, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags); diff --git a/include/net/bond_options.h b/include/net/bond_options.h index 61b49063791c..1618b76f4903 100644 --- a/include/net/bond_options.h +++ b/include/net/bond_options.h @@ -107,7 +107,8 @@ struct bond_option { }; int __bond_opt_set(struct bonding *bond, unsigned int option, - struct bond_opt_value *val); + struct bond_opt_value *val, + struct nlattr *bad_attr, struct netlink_ext_ack *extack); int __bond_opt_set_notify(struct bonding *bond, unsigned int option, struct bond_opt_value *val); int bond_opt_tryset_rtnl(struct bonding *bond, unsigned int option, char *buf); diff --git a/include/net/dropreason.h b/include/net/dropreason.h new file mode 100644 index 000000000000..fae9b40e54fa --- /dev/null +++ b/include/net/dropreason.h @@ -0,0 +1,256 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef _LINUX_DROPREASON_H +#define _LINUX_DROPREASON_H + +/** + * enum skb_drop_reason - the reasons of skb drops + * + * The reason of skb drop, which is used in kfree_skb_reason(). + */ +enum skb_drop_reason { + /** + * @SKB_NOT_DROPPED_YET: skb is not dropped yet (used for no-drop case) + */ + SKB_NOT_DROPPED_YET = 0, + /** @SKB_DROP_REASON_NOT_SPECIFIED: drop reason is not specified */ + SKB_DROP_REASON_NOT_SPECIFIED, + /** @SKB_DROP_REASON_NO_SOCKET: socket not found */ + SKB_DROP_REASON_NO_SOCKET, + /** @SKB_DROP_REASON_PKT_TOO_SMALL: packet size is too small */ + SKB_DROP_REASON_PKT_TOO_SMALL, + /** @SKB_DROP_REASON_TCP_CSUM: TCP checksum error */ + SKB_DROP_REASON_TCP_CSUM, + /** @SKB_DROP_REASON_SOCKET_FILTER: dropped by socket filter */ + SKB_DROP_REASON_SOCKET_FILTER, + /** @SKB_DROP_REASON_UDP_CSUM: UDP checksum error */ + SKB_DROP_REASON_UDP_CSUM, + /** @SKB_DROP_REASON_NETFILTER_DROP: dropped by netfilter */ + SKB_DROP_REASON_NETFILTER_DROP, + /** + * @SKB_DROP_REASON_OTHERHOST: packet don't belong to current host + * (interface is in promisc mode) + */ + SKB_DROP_REASON_OTHERHOST, + /** @SKB_DROP_REASON_IP_CSUM: IP checksum error */ + SKB_DROP_REASON_IP_CSUM, + /** + * @SKB_DROP_REASON_IP_INHDR: there is something wrong with IP header (see + * IPSTATS_MIB_INHDRERRORS) + */ + SKB_DROP_REASON_IP_INHDR, + /** + * @SKB_DROP_REASON_IP_RPFILTER: IP rpfilter validate failed. see the + * document for rp_filter in ip-sysctl.rst for more information + */ + SKB_DROP_REASON_IP_RPFILTER, + /** + * @SKB_DROP_REASON_UNICAST_IN_L2_MULTICAST: destination address of L2 is + * multicast, but L3 is unicast. + */ + SKB_DROP_REASON_UNICAST_IN_L2_MULTICAST, + /** @SKB_DROP_REASON_XFRM_POLICY: xfrm policy check failed */ + SKB_DROP_REASON_XFRM_POLICY, + /** @SKB_DROP_REASON_IP_NOPROTO: no support for IP protocol */ + SKB_DROP_REASON_IP_NOPROTO, + /** @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, + /** + * @SKB_DROP_REASON_TCP_MD5NOTFOUND: no MD5 hash and one expected, + * corresponding to LINUX_MIB_TCPMD5NOTFOUND + */ + SKB_DROP_REASON_TCP_MD5NOTFOUND, + /** + * @SKB_DROP_REASON_TCP_MD5UNEXPECTED: MD5 hash and we're not expecting + * one, corresponding to LINUX_MIB_TCPMD5UNEXPECTED + */ + SKB_DROP_REASON_TCP_MD5UNEXPECTED, + /** + * @SKB_DROP_REASON_TCP_MD5FAILURE: MD5 hash and its wrong, corresponding + * to LINUX_MIB_TCPMD5FAILURE + */ + SKB_DROP_REASON_TCP_MD5FAILURE, + /** + * @SKB_DROP_REASON_SOCKET_BACKLOG: failed to add skb to socket backlog ( + * see LINUX_MIB_TCPBACKLOGDROP) + */ + SKB_DROP_REASON_SOCKET_BACKLOG, + /** @SKB_DROP_REASON_TCP_FLAGS: TCP flags invalid */ + SKB_DROP_REASON_TCP_FLAGS, + /** + * @SKB_DROP_REASON_TCP_ZEROWINDOW: TCP receive window size is zero, + * see LINUX_MIB_TCPZEROWINDOWDROP + */ + SKB_DROP_REASON_TCP_ZEROWINDOW, + /** + * @SKB_DROP_REASON_TCP_OLD_DATA: the TCP data reveived is already + * received before (spurious retrans may happened), see + * LINUX_MIB_DELAYEDACKLOST + */ + SKB_DROP_REASON_TCP_OLD_DATA, + /** + * @SKB_DROP_REASON_TCP_OVERWINDOW: the TCP data is out of window, + * the seq of the first byte exceed the right edges of receive + * window + */ + SKB_DROP_REASON_TCP_OVERWINDOW, + /** + * @SKB_DROP_REASON_TCP_OFOMERGE: the data of skb is already in the ofo + * queue, corresponding to LINUX_MIB_TCPOFOMERGE + */ + SKB_DROP_REASON_TCP_OFOMERGE, + /** + * @SKB_DROP_REASON_TCP_RFC7323_PAWS: PAWS check, corresponding to + * LINUX_MIB_PAWSESTABREJECTED + */ + SKB_DROP_REASON_TCP_RFC7323_PAWS, + /** @SKB_DROP_REASON_TCP_INVALID_SEQUENCE: Not acceptable SEQ field */ + SKB_DROP_REASON_TCP_INVALID_SEQUENCE, + /** @SKB_DROP_REASON_TCP_RESET: Invalid RST packet */ + SKB_DROP_REASON_TCP_RESET, + /** + * @SKB_DROP_REASON_TCP_INVALID_SYN: Incoming packet has unexpected + * SYN flag + */ + SKB_DROP_REASON_TCP_INVALID_SYN, + /** @SKB_DROP_REASON_TCP_CLOSE: TCP socket in CLOSE state */ + SKB_DROP_REASON_TCP_CLOSE, + /** @SKB_DROP_REASON_TCP_FASTOPEN: dropped by FASTOPEN request socket */ + SKB_DROP_REASON_TCP_FASTOPEN, + /** @SKB_DROP_REASON_TCP_OLD_ACK: TCP ACK is old, but in window */ + SKB_DROP_REASON_TCP_OLD_ACK, + /** @SKB_DROP_REASON_TCP_TOO_OLD_ACK: TCP ACK is too old */ + SKB_DROP_REASON_TCP_TOO_OLD_ACK, + /** + * @SKB_DROP_REASON_TCP_ACK_UNSENT_DATA: TCP ACK for data we haven't + * sent yet + */ + SKB_DROP_REASON_TCP_ACK_UNSENT_DATA, + /** @SKB_DROP_REASON_TCP_OFO_QUEUE_PRUNE: pruned from TCP OFO queue */ + SKB_DROP_REASON_TCP_OFO_QUEUE_PRUNE, + /** @SKB_DROP_REASON_TCP_OFO_DROP: data already in receive queue */ + SKB_DROP_REASON_TCP_OFO_DROP, + /** @SKB_DROP_REASON_IP_OUTNOROUTES: route lookup failed */ + SKB_DROP_REASON_IP_OUTNOROUTES, + /** + * @SKB_DROP_REASON_BPF_CGROUP_EGRESS: dropped by BPF_PROG_TYPE_CGROUP_SKB + * eBPF program + */ + SKB_DROP_REASON_BPF_CGROUP_EGRESS, + /** @SKB_DROP_REASON_IPV6DISABLED: IPv6 is disabled on the device */ + SKB_DROP_REASON_IPV6DISABLED, + /** @SKB_DROP_REASON_NEIGH_CREATEFAIL: failed to create neigh entry */ + SKB_DROP_REASON_NEIGH_CREATEFAIL, + /** @SKB_DROP_REASON_NEIGH_FAILED: neigh entry in failed state */ + SKB_DROP_REASON_NEIGH_FAILED, + /** @SKB_DROP_REASON_NEIGH_QUEUEFULL: arp_queue for neigh entry is full */ + SKB_DROP_REASON_NEIGH_QUEUEFULL, + /** @SKB_DROP_REASON_NEIGH_DEAD: neigh entry is dead */ + SKB_DROP_REASON_NEIGH_DEAD, + /** @SKB_DROP_REASON_TC_EGRESS: dropped in TC egress HOOK */ + SKB_DROP_REASON_TC_EGRESS, + /** + * @SKB_DROP_REASON_QDISC_DROP: dropped by qdisc when packet outputting ( + * failed to enqueue to current qdisc) + */ + SKB_DROP_REASON_QDISC_DROP, + /** + * @SKB_DROP_REASON_CPU_BACKLOG: failed to enqueue the skb to the per CPU + * backlog queue. This can be caused by backlog queue full (see + * netdev_max_backlog in net.rst) or RPS flow limit + */ + SKB_DROP_REASON_CPU_BACKLOG, + /** @SKB_DROP_REASON_XDP: dropped by XDP in input path */ + SKB_DROP_REASON_XDP, + /** @SKB_DROP_REASON_TC_INGRESS: dropped in TC ingress HOOK */ + SKB_DROP_REASON_TC_INGRESS, + /** @SKB_DROP_REASON_UNHANDLED_PROTO: protocol not implemented or not supported */ + SKB_DROP_REASON_UNHANDLED_PROTO, + /** @SKB_DROP_REASON_SKB_CSUM: sk_buff checksum computation error */ + SKB_DROP_REASON_SKB_CSUM, + /** @SKB_DROP_REASON_SKB_GSO_SEG: gso segmentation error */ + SKB_DROP_REASON_SKB_GSO_SEG, + /** + * @SKB_DROP_REASON_SKB_UCOPY_FAULT: failed to copy data from user space, + * e.g., via zerocopy_sg_from_iter() or skb_orphan_frags_rx() + */ + SKB_DROP_REASON_SKB_UCOPY_FAULT, + /** @SKB_DROP_REASON_DEV_HDR: device driver specific header/metadata is invalid */ + SKB_DROP_REASON_DEV_HDR, + /** + * @SKB_DROP_REASON_DEV_READY: the device is not ready to xmit/recv due to + * any of its data structure that is not up/ready/initialized, + * e.g., the IFF_UP is not set, or driver specific tun->tfiles[txq] + * is not initialized + */ + SKB_DROP_REASON_DEV_READY, + /** @SKB_DROP_REASON_FULL_RING: ring buffer is full */ + SKB_DROP_REASON_FULL_RING, + /** @SKB_DROP_REASON_NOMEM: error due to OOM */ + SKB_DROP_REASON_NOMEM, + /** + * @SKB_DROP_REASON_HDR_TRUNC: failed to trunc/extract the header from + * networking data, e.g., failed to pull the protocol header from + * frags via pskb_may_pull() + */ + SKB_DROP_REASON_HDR_TRUNC, + /** + * @SKB_DROP_REASON_TAP_FILTER: dropped by (ebpf) filter directly attached + * to tun/tap, e.g., via TUNSETFILTEREBPF + */ + SKB_DROP_REASON_TAP_FILTER, + /** + * @SKB_DROP_REASON_TAP_TXFILTER: dropped by tx filter implemented at + * tun/tap, e.g., check_filter() + */ + SKB_DROP_REASON_TAP_TXFILTER, + /** @SKB_DROP_REASON_ICMP_CSUM: ICMP checksum error */ + SKB_DROP_REASON_ICMP_CSUM, + /** + * @SKB_DROP_REASON_INVALID_PROTO: the packet doesn't follow RFC 2211, + * such as a broadcasts ICMP_TIMESTAMP + */ + SKB_DROP_REASON_INVALID_PROTO, + /** + * @SKB_DROP_REASON_IP_INADDRERRORS: host unreachable, corresponding to + * IPSTATS_MIB_INADDRERRORS + */ + SKB_DROP_REASON_IP_INADDRERRORS, + /** + * @SKB_DROP_REASON_IP_INNOROUTES: network unreachable, corresponding to + * IPSTATS_MIB_INADDRERRORS + */ + SKB_DROP_REASON_IP_INNOROUTES, + /** + * @SKB_DROP_REASON_PKT_TOO_BIG: packet size is too big (maybe exceed the + * MTU) + */ + SKB_DROP_REASON_PKT_TOO_BIG, + /** + * @SKB_DROP_REASON_MAX: the maximum of drop reason, which shouldn't be + * used as a real 'reason' + */ + SKB_DROP_REASON_MAX, +}; + +#define SKB_DR_INIT(name, reason) \ + enum skb_drop_reason name = SKB_DROP_REASON_##reason +#define SKB_DR(name) \ + SKB_DR_INIT(name, NOT_SPECIFIED) +#define SKB_DR_SET(name, reason) \ + (name = SKB_DROP_REASON_##reason) +#define SKB_DR_OR(name, reason) \ + do { \ + if (name == SKB_DROP_REASON_NOT_SPECIFIED || \ + name == SKB_NOT_DROPPED_YET) \ + SKB_DR_SET(name, reason); \ + } while (0) + +extern const char * const drop_reasons[]; + +#endif diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index c24fa934221d..70cbc4a72669 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -456,8 +456,8 @@ static inline void iptunnel_xmit_stats(struct net_device *dev, int pkt_len) struct pcpu_sw_netstats *tstats = get_cpu_ptr(dev->tstats); u64_stats_update_begin(&tstats->syncp); - tstats->tx_bytes += pkt_len; - tstats->tx_packets++; + u64_stats_add(&tstats->tx_bytes, pkt_len); + u64_stats_inc(&tstats->tx_packets); u64_stats_update_end(&tstats->syncp); put_cpu_ptr(tstats); } else { diff --git a/include/net/mac80211.h b/include/net/mac80211.h index ebadb2103968..5c9e97eca739 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1959,36 +1959,6 @@ struct ieee80211_key_seq { }; /** - * struct ieee80211_cipher_scheme - cipher scheme - * - * This structure contains a cipher scheme information defining - * the secure packet crypto handling. - * - * @cipher: a cipher suite selector - * @iftype: a cipher iftype bit mask indicating an allowed cipher usage - * @hdr_len: a length of a security header used the cipher - * @pn_len: a length of a packet number in the security header - * @pn_off: an offset of pn from the beginning of the security header - * @key_idx_off: an offset of key index byte in the security header - * @key_idx_mask: a bit mask of key_idx bits - * @key_idx_shift: a bit shift needed to get key_idx - * key_idx value calculation: - * (sec_header_base[key_idx_off] & key_idx_mask) >> key_idx_shift - * @mic_len: a mic length in bytes - */ -struct ieee80211_cipher_scheme { - u32 cipher; - u16 iftype; - u8 hdr_len; - u8 pn_len; - u8 pn_off; - u8 key_idx_off; - u8 key_idx_mask; - u8 key_idx_shift; - u8 mic_len; -}; - -/** * enum set_key_cmd - key command * * Used with the set_key() callback in &struct ieee80211_ops, this @@ -2664,9 +2634,6 @@ enum ieee80211_hw_flags { * deliver to a WMM STA during any Service Period triggered by the WMM STA. * Use IEEE80211_WMM_IE_STA_QOSINFO_SP_* for correct values. * - * @n_cipher_schemes: a size of an array of cipher schemes definitions. - * @cipher_schemes: a pointer to an array of cipher scheme definitions - * supported by HW. * @max_nan_de_entries: maximum number of NAN DE functions supported by the * device. * @@ -2716,8 +2683,6 @@ struct ieee80211_hw { netdev_features_t netdev_features; u8 uapsd_queues; u8 uapsd_max_sp_len; - u8 n_cipher_schemes; - const struct ieee80211_cipher_scheme *cipher_schemes; u8 max_nan_de_entries; u8 tx_sk_pacing_shift; u8 weight_multiplier; diff --git a/include/net/sock.h b/include/net/sock.h index 72ca97ccb460..5bed1ea7a722 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -609,7 +609,7 @@ void sock_net_set(struct sock *sk, struct net *net) int sk_set_peek_off(struct sock *sk, int val); -static inline int sk_peek_offset(struct sock *sk, int flags) +static inline int sk_peek_offset(const struct sock *sk, int flags) { if (unlikely(flags & MSG_PEEK)) { return READ_ONCE(sk->sk_peek_off); @@ -849,7 +849,7 @@ static inline void sk_add_bind_node(struct sock *sk, ({ tpos = (typeof(*tpos) *)((void *)pos - offset); 1;}); \ pos = rcu_dereference(hlist_next_rcu(pos))) -static inline struct user_namespace *sk_user_ns(struct sock *sk) +static inline struct user_namespace *sk_user_ns(const struct sock *sk) { /* Careful only use this in a context where these parameters * can not change and must all be valid, such as recvmsg from @@ -895,7 +895,7 @@ enum sock_flags { #define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)) -static inline void sock_copy_flags(struct sock *nsk, struct sock *osk) +static inline void sock_copy_flags(struct sock *nsk, const struct sock *osk) { nsk->sk_flags = osk->sk_flags; } @@ -1240,6 +1240,7 @@ struct proto { void (*enter_memory_pressure)(struct sock *sk); void (*leave_memory_pressure)(struct sock *sk); atomic_long_t *memory_allocated; /* Current allocated memory. */ + int __percpu *per_cpu_fw_alloc; struct percpu_counter *sockets_allocated; /* Current number of sockets. */ /* @@ -1383,21 +1384,46 @@ static inline bool sk_under_memory_pressure(const struct sock *sk) } static inline long -sk_memory_allocated(const struct sock *sk) +proto_memory_allocated(const struct proto *prot) { - return atomic_long_read(sk->sk_prot->memory_allocated); + return max(0L, atomic_long_read(prot->memory_allocated)); } static inline long +sk_memory_allocated(const struct sock *sk) +{ + return proto_memory_allocated(sk->sk_prot); +} + +/* 1 MB per cpu, in page units */ +#define SK_MEMORY_PCPU_RESERVE (1 << (20 - PAGE_SHIFT)) + +static inline void sk_memory_allocated_add(struct sock *sk, int amt) { - return atomic_long_add_return(amt, sk->sk_prot->memory_allocated); + int local_reserve; + + preempt_disable(); + local_reserve = __this_cpu_add_return(*sk->sk_prot->per_cpu_fw_alloc, amt); + if (local_reserve >= SK_MEMORY_PCPU_RESERVE) { + __this_cpu_sub(*sk->sk_prot->per_cpu_fw_alloc, local_reserve); + atomic_long_add(local_reserve, sk->sk_prot->memory_allocated); + } + preempt_enable(); } static inline void sk_memory_allocated_sub(struct sock *sk, int amt) { - atomic_long_sub(amt, sk->sk_prot->memory_allocated); + int local_reserve; + + preempt_disable(); + local_reserve = __this_cpu_sub_return(*sk->sk_prot->per_cpu_fw_alloc, amt); + if (local_reserve <= -SK_MEMORY_PCPU_RESERVE) { + __this_cpu_sub(*sk->sk_prot->per_cpu_fw_alloc, local_reserve); + atomic_long_add(local_reserve, sk->sk_prot->memory_allocated); + } + preempt_enable(); } #define SK_ALLOC_PERCPU_COUNTER_BATCH 16 @@ -1426,12 +1452,6 @@ proto_sockets_allocated_sum_positive(struct proto *prot) return percpu_counter_sum_positive(prot->sockets_allocated); } -static inline long -proto_memory_allocated(struct proto *prot) -{ - return atomic_long_read(prot->memory_allocated); -} - static inline bool proto_memory_pressure(struct proto *prot) { @@ -1518,30 +1538,18 @@ int __sk_mem_schedule(struct sock *sk, int size, int kind); void __sk_mem_reduce_allocated(struct sock *sk, int amount); void __sk_mem_reclaim(struct sock *sk, int amount); -/* We used to have PAGE_SIZE here, but systems with 64KB pages - * do not necessarily have 16x time more memory than 4KB ones. - */ -#define SK_MEM_QUANTUM 4096 -#define SK_MEM_QUANTUM_SHIFT ilog2(SK_MEM_QUANTUM) #define SK_MEM_SEND 0 #define SK_MEM_RECV 1 -/* sysctl_mem values are in pages, we convert them in SK_MEM_QUANTUM units */ +/* sysctl_mem values are in pages */ static inline long sk_prot_mem_limits(const struct sock *sk, int index) { - long val = sk->sk_prot->sysctl_mem[index]; - -#if PAGE_SIZE > SK_MEM_QUANTUM - val <<= PAGE_SHIFT - SK_MEM_QUANTUM_SHIFT; -#elif PAGE_SIZE < SK_MEM_QUANTUM - val >>= SK_MEM_QUANTUM_SHIFT - PAGE_SHIFT; -#endif - return val; + return sk->sk_prot->sysctl_mem[index]; } static inline int sk_mem_pages(int amt) { - return (amt + SK_MEM_QUANTUM - 1) >> SK_MEM_QUANTUM_SHIFT; + return (amt + PAGE_SIZE - 1) >> PAGE_SHIFT; } static inline bool sk_has_account(struct sock *sk) @@ -1552,19 +1560,23 @@ static inline bool sk_has_account(struct sock *sk) static inline bool sk_wmem_schedule(struct sock *sk, int size) { + int delta; + if (!sk_has_account(sk)) return true; - return size <= sk->sk_forward_alloc || - __sk_mem_schedule(sk, size, SK_MEM_SEND); + delta = size - sk->sk_forward_alloc; + return delta <= 0 || __sk_mem_schedule(sk, delta, SK_MEM_SEND); } static inline bool sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size) { + int delta; + if (!sk_has_account(sk)) return true; - return size <= sk->sk_forward_alloc || - __sk_mem_schedule(sk, size, SK_MEM_RECV) || + delta = size - sk->sk_forward_alloc; + return delta <= 0 || __sk_mem_schedule(sk, delta, SK_MEM_RECV) || skb_pfmemalloc(skb); } @@ -1590,7 +1602,7 @@ static inline void sk_mem_reclaim(struct sock *sk) reclaimable = sk->sk_forward_alloc - sk_unused_reserved_mem(sk); - if (reclaimable >= SK_MEM_QUANTUM) + if (reclaimable >= (int)PAGE_SIZE) __sk_mem_reclaim(sk, reclaimable); } @@ -1600,19 +1612,6 @@ static inline void sk_mem_reclaim_final(struct sock *sk) sk_mem_reclaim(sk); } -static inline void sk_mem_reclaim_partial(struct sock *sk) -{ - int reclaimable; - - if (!sk_has_account(sk)) - return; - - reclaimable = sk->sk_forward_alloc - sk_unused_reserved_mem(sk); - - if (reclaimable > SK_MEM_QUANTUM) - __sk_mem_reclaim(sk, reclaimable - 1); -} - static inline void sk_mem_charge(struct sock *sk, int size) { if (!sk_has_account(sk)) @@ -1620,29 +1619,17 @@ static inline void sk_mem_charge(struct sock *sk, int size) sk->sk_forward_alloc -= size; } -/* the following macros control memory reclaiming in sk_mem_uncharge() +/* the following macros control memory reclaiming in mptcp_rmem_uncharge() */ #define SK_RECLAIM_THRESHOLD (1 << 21) #define SK_RECLAIM_CHUNK (1 << 20) static inline void sk_mem_uncharge(struct sock *sk, int size) { - int reclaimable; - if (!sk_has_account(sk)) return; sk->sk_forward_alloc += size; - reclaimable = sk->sk_forward_alloc - sk_unused_reserved_mem(sk); - - /* Avoid a possible overflow. - * TCP send queues can make this happen, if sk_mem_reclaim() - * is not called and more than 2 GBytes are released at once. - * - * If we reach 2 MBytes, reclaim 1 MBytes right now, there is - * no need to hold that much forward allocation anyway. - */ - if (unlikely(reclaimable >= SK_RECLAIM_THRESHOLD)) - __sk_mem_reclaim(sk, SK_RECLAIM_CHUNK); + sk_mem_reclaim(sk); } /* diff --git a/include/net/tcp.h b/include/net/tcp.h index 1e99f5c61f84..4794cae4577e 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -253,6 +253,8 @@ extern long sysctl_tcp_mem[3]; #define TCP_RACK_NO_DUPTHRESH 0x4 /* Do not use DUPACK threshold in RACK */ extern atomic_long_t tcp_memory_allocated; +DECLARE_PER_CPU(int, tcp_memory_per_cpu_fw_alloc); + extern struct percpu_counter tcp_sockets_allocated; extern unsigned long tcp_memory_pressure; diff --git a/include/net/udp.h b/include/net/udp.h index b83a00330566..b60eea2e3fae 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -95,6 +95,7 @@ static inline struct udp_hslot *udp_hashslot2(struct udp_table *table, extern struct proto udp_prot; extern atomic_long_t udp_memory_allocated; +DECLARE_PER_CPU(int, udp_memory_per_cpu_fw_alloc); /* sysctl variables for udp */ extern long sysctl_udp_mem[3]; diff --git a/include/net/xfrm.h b/include/net/xfrm.h index c39d910d4b45..9287712ad977 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1923,7 +1923,7 @@ static inline void xfrm_dev_state_free(struct xfrm_state *x) if (dev->xfrmdev_ops->xdo_dev_state_free) dev->xfrmdev_ops->xdo_dev_state_free(x); xso->dev = NULL; - dev_put_track(dev, &xso->dev_tracker); + netdev_put(dev, &xso->dev_tracker); } } #else diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index a477bf907498..45264e4bb254 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -9,92 +9,6 @@ #include <linux/netdevice.h> #include <linux/tracepoint.h> -#define TRACE_SKB_DROP_REASON \ - EM(SKB_DROP_REASON_NOT_SPECIFIED, NOT_SPECIFIED) \ - EM(SKB_DROP_REASON_NO_SOCKET, NO_SOCKET) \ - EM(SKB_DROP_REASON_PKT_TOO_SMALL, PKT_TOO_SMALL) \ - EM(SKB_DROP_REASON_TCP_CSUM, TCP_CSUM) \ - EM(SKB_DROP_REASON_SOCKET_FILTER, SOCKET_FILTER) \ - EM(SKB_DROP_REASON_UDP_CSUM, UDP_CSUM) \ - EM(SKB_DROP_REASON_NETFILTER_DROP, NETFILTER_DROP) \ - EM(SKB_DROP_REASON_OTHERHOST, OTHERHOST) \ - EM(SKB_DROP_REASON_IP_CSUM, IP_CSUM) \ - EM(SKB_DROP_REASON_IP_INHDR, IP_INHDR) \ - EM(SKB_DROP_REASON_IP_RPFILTER, IP_RPFILTER) \ - EM(SKB_DROP_REASON_UNICAST_IN_L2_MULTICAST, \ - UNICAST_IN_L2_MULTICAST) \ - EM(SKB_DROP_REASON_XFRM_POLICY, XFRM_POLICY) \ - EM(SKB_DROP_REASON_IP_NOPROTO, IP_NOPROTO) \ - EM(SKB_DROP_REASON_SOCKET_RCVBUFF, SOCKET_RCVBUFF) \ - EM(SKB_DROP_REASON_PROTO_MEM, PROTO_MEM) \ - EM(SKB_DROP_REASON_TCP_MD5NOTFOUND, TCP_MD5NOTFOUND) \ - EM(SKB_DROP_REASON_TCP_MD5UNEXPECTED, \ - TCP_MD5UNEXPECTED) \ - EM(SKB_DROP_REASON_TCP_MD5FAILURE, TCP_MD5FAILURE) \ - EM(SKB_DROP_REASON_SOCKET_BACKLOG, SOCKET_BACKLOG) \ - EM(SKB_DROP_REASON_TCP_FLAGS, TCP_FLAGS) \ - EM(SKB_DROP_REASON_TCP_ZEROWINDOW, TCP_ZEROWINDOW) \ - EM(SKB_DROP_REASON_TCP_OLD_DATA, TCP_OLD_DATA) \ - EM(SKB_DROP_REASON_TCP_OVERWINDOW, TCP_OVERWINDOW) \ - EM(SKB_DROP_REASON_TCP_OFOMERGE, TCP_OFOMERGE) \ - EM(SKB_DROP_REASON_TCP_OFO_DROP, TCP_OFO_DROP) \ - EM(SKB_DROP_REASON_TCP_RFC7323_PAWS, TCP_RFC7323_PAWS) \ - EM(SKB_DROP_REASON_TCP_INVALID_SEQUENCE, \ - TCP_INVALID_SEQUENCE) \ - EM(SKB_DROP_REASON_TCP_RESET, TCP_RESET) \ - EM(SKB_DROP_REASON_TCP_INVALID_SYN, TCP_INVALID_SYN) \ - EM(SKB_DROP_REASON_TCP_CLOSE, TCP_CLOSE) \ - EM(SKB_DROP_REASON_TCP_FASTOPEN, TCP_FASTOPEN) \ - EM(SKB_DROP_REASON_TCP_OLD_ACK, TCP_OLD_ACK) \ - EM(SKB_DROP_REASON_TCP_TOO_OLD_ACK, TCP_TOO_OLD_ACK) \ - EM(SKB_DROP_REASON_TCP_ACK_UNSENT_DATA, \ - TCP_ACK_UNSENT_DATA) \ - EM(SKB_DROP_REASON_TCP_OFO_QUEUE_PRUNE, \ - TCP_OFO_QUEUE_PRUNE) \ - EM(SKB_DROP_REASON_IP_OUTNOROUTES, IP_OUTNOROUTES) \ - EM(SKB_DROP_REASON_BPF_CGROUP_EGRESS, \ - BPF_CGROUP_EGRESS) \ - EM(SKB_DROP_REASON_IPV6DISABLED, IPV6DISABLED) \ - EM(SKB_DROP_REASON_NEIGH_CREATEFAIL, NEIGH_CREATEFAIL) \ - EM(SKB_DROP_REASON_NEIGH_FAILED, NEIGH_FAILED) \ - EM(SKB_DROP_REASON_NEIGH_QUEUEFULL, NEIGH_QUEUEFULL) \ - EM(SKB_DROP_REASON_NEIGH_DEAD, NEIGH_DEAD) \ - EM(SKB_DROP_REASON_TC_EGRESS, TC_EGRESS) \ - EM(SKB_DROP_REASON_QDISC_DROP, QDISC_DROP) \ - EM(SKB_DROP_REASON_CPU_BACKLOG, CPU_BACKLOG) \ - EM(SKB_DROP_REASON_XDP, XDP) \ - EM(SKB_DROP_REASON_TC_INGRESS, TC_INGRESS) \ - EM(SKB_DROP_REASON_UNHANDLED_PROTO, UNHANDLED_PROTO) \ - EM(SKB_DROP_REASON_SKB_CSUM, SKB_CSUM) \ - EM(SKB_DROP_REASON_SKB_GSO_SEG, SKB_GSO_SEG) \ - EM(SKB_DROP_REASON_SKB_UCOPY_FAULT, SKB_UCOPY_FAULT) \ - EM(SKB_DROP_REASON_DEV_HDR, DEV_HDR) \ - EM(SKB_DROP_REASON_DEV_READY, DEV_READY) \ - EM(SKB_DROP_REASON_FULL_RING, FULL_RING) \ - EM(SKB_DROP_REASON_NOMEM, NOMEM) \ - EM(SKB_DROP_REASON_HDR_TRUNC, HDR_TRUNC) \ - EM(SKB_DROP_REASON_TAP_FILTER, TAP_FILTER) \ - EM(SKB_DROP_REASON_TAP_TXFILTER, TAP_TXFILTER) \ - EM(SKB_DROP_REASON_ICMP_CSUM, ICMP_CSUM) \ - EM(SKB_DROP_REASON_INVALID_PROTO, INVALID_PROTO) \ - EM(SKB_DROP_REASON_IP_INADDRERRORS, IP_INADDRERRORS) \ - EM(SKB_DROP_REASON_IP_INNOROUTES, IP_INNOROUTES) \ - EM(SKB_DROP_REASON_PKT_TOO_BIG, PKT_TOO_BIG) \ - EMe(SKB_DROP_REASON_MAX, MAX) - -#undef EM -#undef EMe - -#define EM(a, b) TRACE_DEFINE_ENUM(a); -#define EMe(a, b) TRACE_DEFINE_ENUM(a); - -TRACE_SKB_DROP_REASON - -#undef EM -#undef EMe -#define EM(a, b) { a, #b }, -#define EMe(a, b) { a, #b } - /* * Tracepoint for free an sk_buff: */ @@ -121,8 +35,7 @@ TRACE_EVENT(kfree_skb, TP_printk("skbaddr=%p protocol=%u location=%p reason: %s", __entry->skbaddr, __entry->protocol, __entry->location, - __print_symbolic(__entry->reason, - TRACE_SKB_DROP_REASON)) + drop_reasons[__entry->reason]) ); TRACE_EVENT(consume_skb, diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index d9490e3062a7..98f905f16411 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -5874,7 +5874,7 @@ enum nl80211_ap_sme_features { * @NL80211_FEATURE_INACTIVITY_TIMER: This driver takes care of freeing up * the connected inactive stations in AP mode. * @NL80211_FEATURE_CELL_BASE_REG_HINTS: This driver has been tested - * to work properly to suppport receiving regulatory hints from + * to work properly to support receiving regulatory hints from * cellular base stations. * @NL80211_FEATURE_P2P_DEVICE_NEEDS_CHANNEL: (no longer available, only * here to reserve the value for API/ABI compatibility) diff --git a/include/uapi/rdma/mlx5_user_ioctl_verbs.h b/include/uapi/rdma/mlx5_user_ioctl_verbs.h index a21ca8ece8db..7af9e09ea556 100644 --- a/include/uapi/rdma/mlx5_user_ioctl_verbs.h +++ b/include/uapi/rdma/mlx5_user_ioctl_verbs.h @@ -63,6 +63,7 @@ enum mlx5_ib_uapi_dm_type { MLX5_IB_UAPI_DM_TYPE_MEMIC, MLX5_IB_UAPI_DM_TYPE_STEERING_SW_ICM, MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_SW_ICM, + MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_PATTERN_SW_ICM, }; enum mlx5_ib_uapi_devx_create_event_channel_flags { diff --git a/net/6lowpan/nhc.c b/net/6lowpan/nhc.c index d6bbbd4ab38b..7b374595328d 100644 --- a/net/6lowpan/nhc.c +++ b/net/6lowpan/nhc.c @@ -12,77 +12,26 @@ #include "nhc.h" -static struct rb_root rb_root = RB_ROOT; -static struct lowpan_nhc *lowpan_nexthdr_nhcs[NEXTHDR_MAX + 1]; +static const struct lowpan_nhc *lowpan_nexthdr_nhcs[NEXTHDR_MAX + 1]; static DEFINE_SPINLOCK(lowpan_nhc_lock); -static int lowpan_nhc_insert(struct lowpan_nhc *nhc) +static const struct lowpan_nhc *lowpan_nhc_by_nhcid(struct sk_buff *skb) { - struct rb_node **new = &rb_root.rb_node, *parent = NULL; - - /* Figure out where to put new node */ - while (*new) { - struct lowpan_nhc *this = rb_entry(*new, struct lowpan_nhc, - node); - int result, len_dif, len; - - len_dif = nhc->idlen - this->idlen; - - if (nhc->idlen < this->idlen) - len = nhc->idlen; - else - len = this->idlen; - - result = memcmp(nhc->id, this->id, len); - if (!result) - result = len_dif; - - parent = *new; - if (result < 0) - new = &((*new)->rb_left); - else if (result > 0) - new = &((*new)->rb_right); - else - return -EEXIST; - } + const struct lowpan_nhc *nhc; + int i; + u8 id; - /* Add new node and rebalance tree. */ - rb_link_node(&nhc->node, parent, new); - rb_insert_color(&nhc->node, &rb_root); + if (!pskb_may_pull(skb, 1)) + return NULL; - return 0; -} + id = *skb->data; -static void lowpan_nhc_remove(struct lowpan_nhc *nhc) -{ - rb_erase(&nhc->node, &rb_root); -} + for (i = 0; i < NEXTHDR_MAX + 1; i++) { + nhc = lowpan_nexthdr_nhcs[i]; + if (!nhc) + continue; -static struct lowpan_nhc *lowpan_nhc_by_nhcid(const struct sk_buff *skb) -{ - struct rb_node *node = rb_root.rb_node; - const u8 *nhcid_skb_ptr = skb->data; - - while (node) { - struct lowpan_nhc *nhc = rb_entry(node, struct lowpan_nhc, - node); - u8 nhcid_skb_ptr_masked[LOWPAN_NHC_MAX_ID_LEN]; - int result, i; - - if (nhcid_skb_ptr + nhc->idlen > skb->data + skb->len) - return NULL; - - /* copy and mask afterwards the nhid value from skb */ - memcpy(nhcid_skb_ptr_masked, nhcid_skb_ptr, nhc->idlen); - for (i = 0; i < nhc->idlen; i++) - nhcid_skb_ptr_masked[i] &= nhc->idmask[i]; - - result = memcmp(nhcid_skb_ptr_masked, nhc->id, nhc->idlen); - if (result < 0) - node = node->rb_left; - else if (result > 0) - node = node->rb_right; - else + if ((id & nhc->idmask) == nhc->id) return nhc; } @@ -92,7 +41,7 @@ static struct lowpan_nhc *lowpan_nhc_by_nhcid(const struct sk_buff *skb) int lowpan_nhc_check_compression(struct sk_buff *skb, const struct ipv6hdr *hdr, u8 **hc_ptr) { - struct lowpan_nhc *nhc; + const struct lowpan_nhc *nhc; int ret = 0; spin_lock_bh(&lowpan_nhc_lock); @@ -110,7 +59,7 @@ int lowpan_nhc_do_compression(struct sk_buff *skb, const struct ipv6hdr *hdr, u8 **hc_ptr) { int ret; - struct lowpan_nhc *nhc; + const struct lowpan_nhc *nhc; spin_lock_bh(&lowpan_nhc_lock); @@ -153,7 +102,7 @@ int lowpan_nhc_do_uncompression(struct sk_buff *skb, const struct net_device *dev, struct ipv6hdr *hdr) { - struct lowpan_nhc *nhc; + const struct lowpan_nhc *nhc; int ret; spin_lock_bh(&lowpan_nhc_lock); @@ -189,18 +138,9 @@ int lowpan_nhc_do_uncompression(struct sk_buff *skb, return 0; } -int lowpan_nhc_add(struct lowpan_nhc *nhc) +int lowpan_nhc_add(const struct lowpan_nhc *nhc) { - int ret; - - if (!nhc->idlen || !nhc->idsetup) - return -EINVAL; - - WARN_ONCE(nhc->idlen > LOWPAN_NHC_MAX_ID_LEN, - "LOWPAN_NHC_MAX_ID_LEN should be updated to %zd.\n", - nhc->idlen); - - nhc->idsetup(nhc); + int ret = 0; spin_lock_bh(&lowpan_nhc_lock); @@ -209,10 +149,6 @@ int lowpan_nhc_add(struct lowpan_nhc *nhc) goto out; } - ret = lowpan_nhc_insert(nhc); - if (ret < 0) - goto out; - lowpan_nexthdr_nhcs[nhc->nexthdr] = nhc; out: spin_unlock_bh(&lowpan_nhc_lock); @@ -220,11 +156,10 @@ out: } EXPORT_SYMBOL(lowpan_nhc_add); -void lowpan_nhc_del(struct lowpan_nhc *nhc) +void lowpan_nhc_del(const struct lowpan_nhc *nhc) { spin_lock_bh(&lowpan_nhc_lock); - lowpan_nhc_remove(nhc); lowpan_nexthdr_nhcs[nhc->nexthdr] = NULL; spin_unlock_bh(&lowpan_nhc_lock); diff --git a/net/6lowpan/nhc.h b/net/6lowpan/nhc.h index 67951c40734b..ab7b4977c32b 100644 --- a/net/6lowpan/nhc.h +++ b/net/6lowpan/nhc.h @@ -16,24 +16,20 @@ * @_name: const char * of common header compression name. * @_nexthdr: ipv6 nexthdr field for the header compression. * @_nexthdrlen: ipv6 nexthdr len for the reserved space. - * @_idsetup: callback to setup id and mask values. - * @_idlen: len for the next header id and mask, should be always the same. + * @_id: one byte nhc id value. + * @_idmask: one byte nhc id mask value. * @_uncompress: callback for uncompression call. * @_compress: callback for compression call. */ #define LOWPAN_NHC(__nhc, _name, _nexthdr, \ - _hdrlen, _idsetup, _idlen, \ + _hdrlen, _id, _idmask, \ _uncompress, _compress) \ -static u8 __nhc##_val[_idlen]; \ -static u8 __nhc##_mask[_idlen]; \ -static struct lowpan_nhc __nhc = { \ +static const struct lowpan_nhc __nhc = { \ .name = _name, \ .nexthdr = _nexthdr, \ .nexthdrlen = _hdrlen, \ - .id = __nhc##_val, \ - .idmask = __nhc##_mask, \ - .idlen = _idlen, \ - .idsetup = _idsetup, \ + .id = _id, \ + .idmask = _idmask, \ .uncompress = _uncompress, \ .compress = _compress, \ } @@ -53,27 +49,21 @@ module_exit(__nhc##_exit); /** * struct lowpan_nhc - hold 6lowpan next hdr compression ifnformation * - * @node: holder for the rbtree. * @name: name of the specific next header compression * @nexthdr: next header value of the protocol which should be compressed. * @nexthdrlen: ipv6 nexthdr len for the reserved space. - * @id: array for nhc id. Note this need to be in network byteorder. - * @mask: array for nhc id mask. Note this need to be in network byteorder. - * @len: the length of the next header id and mask. - * @setup: callback to setup fill the next header id value and mask. + * @id: one byte nhc id value. + * @idmask: one byte nhc id mask value. * @compress: callback to do the header compression. * @uncompress: callback to do the header uncompression. */ struct lowpan_nhc { - struct rb_node node; const char *name; - const u8 nexthdr; - const size_t nexthdrlen; - u8 *id; - u8 *idmask; - const size_t idlen; + u8 nexthdr; + size_t nexthdrlen; + u8 id; + u8 idmask; - void (*idsetup)(struct lowpan_nhc *nhc); int (*uncompress)(struct sk_buff *skb, size_t needed); int (*compress)(struct sk_buff *skb, u8 **hc_ptr); }; @@ -126,14 +116,14 @@ int lowpan_nhc_do_uncompression(struct sk_buff *skb, * * @nhc: nhc which should be add. */ -int lowpan_nhc_add(struct lowpan_nhc *nhc); +int lowpan_nhc_add(const struct lowpan_nhc *nhc); /** * lowpan_nhc_del - delete a next header compression from framework * * @nhc: nhc which should be delete. */ -void lowpan_nhc_del(struct lowpan_nhc *nhc); +void lowpan_nhc_del(const struct lowpan_nhc *nhc); /** * lowpan_nhc_init - adding all default nhcs diff --git a/net/6lowpan/nhc_dest.c b/net/6lowpan/nhc_dest.c index 4768a9459212..0cbcc7806469 100644 --- a/net/6lowpan/nhc_dest.c +++ b/net/6lowpan/nhc_dest.c @@ -6,18 +6,11 @@ #include "nhc.h" -#define LOWPAN_NHC_DEST_IDLEN 1 #define LOWPAN_NHC_DEST_ID_0 0xe6 #define LOWPAN_NHC_DEST_MASK_0 0xfe -static void dest_nhid_setup(struct lowpan_nhc *nhc) -{ - nhc->id[0] = LOWPAN_NHC_DEST_ID_0; - nhc->idmask[0] = LOWPAN_NHC_DEST_MASK_0; -} - LOWPAN_NHC(nhc_dest, "RFC6282 Destination Options", NEXTHDR_DEST, 0, - dest_nhid_setup, LOWPAN_NHC_DEST_IDLEN, NULL, NULL); + LOWPAN_NHC_DEST_ID_0, LOWPAN_NHC_DEST_MASK_0, NULL, NULL); module_lowpan_nhc(nhc_dest); MODULE_DESCRIPTION("6LoWPAN next header RFC6282 Destination Options compression"); diff --git a/net/6lowpan/nhc_fragment.c b/net/6lowpan/nhc_fragment.c index be85f07715bd..9414552df0ac 100644 --- a/net/6lowpan/nhc_fragment.c +++ b/net/6lowpan/nhc_fragment.c @@ -5,18 +5,11 @@ #include "nhc.h" -#define LOWPAN_NHC_FRAGMENT_IDLEN 1 #define LOWPAN_NHC_FRAGMENT_ID_0 0xe4 #define LOWPAN_NHC_FRAGMENT_MASK_0 0xfe -static void fragment_nhid_setup(struct lowpan_nhc *nhc) -{ - nhc->id[0] = LOWPAN_NHC_FRAGMENT_ID_0; - nhc->idmask[0] = LOWPAN_NHC_FRAGMENT_MASK_0; -} - LOWPAN_NHC(nhc_fragment, "RFC6282 Fragment", NEXTHDR_FRAGMENT, 0, - fragment_nhid_setup, LOWPAN_NHC_FRAGMENT_IDLEN, NULL, NULL); + LOWPAN_NHC_FRAGMENT_ID_0, LOWPAN_NHC_FRAGMENT_MASK_0, NULL, NULL); module_lowpan_nhc(nhc_fragment); MODULE_DESCRIPTION("6LoWPAN next header RFC6282 Fragment compression"); diff --git a/net/6lowpan/nhc_ghc_ext_dest.c b/net/6lowpan/nhc_ghc_ext_dest.c index a9137f1733be..e4745ddd10a8 100644 --- a/net/6lowpan/nhc_ghc_ext_dest.c +++ b/net/6lowpan/nhc_ghc_ext_dest.c @@ -5,18 +5,11 @@ #include "nhc.h" -#define LOWPAN_GHC_EXT_DEST_IDLEN 1 #define LOWPAN_GHC_EXT_DEST_ID_0 0xb6 #define LOWPAN_GHC_EXT_DEST_MASK_0 0xfe -static void dest_ghid_setup(struct lowpan_nhc *nhc) -{ - nhc->id[0] = LOWPAN_GHC_EXT_DEST_ID_0; - nhc->idmask[0] = LOWPAN_GHC_EXT_DEST_MASK_0; -} - LOWPAN_NHC(ghc_ext_dest, "RFC7400 Destination Extension Header", NEXTHDR_DEST, - 0, dest_ghid_setup, LOWPAN_GHC_EXT_DEST_IDLEN, NULL, NULL); + 0, LOWPAN_GHC_EXT_DEST_ID_0, LOWPAN_GHC_EXT_DEST_MASK_0, NULL, NULL); module_lowpan_nhc(ghc_ext_dest); MODULE_DESCRIPTION("6LoWPAN generic header destination extension compression"); diff --git a/net/6lowpan/nhc_ghc_ext_frag.c b/net/6lowpan/nhc_ghc_ext_frag.c index d49b745918e0..220e5abfa946 100644 --- a/net/6lowpan/nhc_ghc_ext_frag.c +++ b/net/6lowpan/nhc_ghc_ext_frag.c @@ -5,19 +5,12 @@ #include "nhc.h" -#define LOWPAN_GHC_EXT_FRAG_IDLEN 1 #define LOWPAN_GHC_EXT_FRAG_ID_0 0xb4 #define LOWPAN_GHC_EXT_FRAG_MASK_0 0xfe -static void frag_ghid_setup(struct lowpan_nhc *nhc) -{ - nhc->id[0] = LOWPAN_GHC_EXT_FRAG_ID_0; - nhc->idmask[0] = LOWPAN_GHC_EXT_FRAG_MASK_0; -} - LOWPAN_NHC(ghc_ext_frag, "RFC7400 Fragmentation Extension Header", - NEXTHDR_FRAGMENT, 0, frag_ghid_setup, - LOWPAN_GHC_EXT_FRAG_IDLEN, NULL, NULL); + NEXTHDR_FRAGMENT, 0, LOWPAN_GHC_EXT_FRAG_ID_0, + LOWPAN_GHC_EXT_FRAG_MASK_0, NULL, NULL); module_lowpan_nhc(ghc_ext_frag); MODULE_DESCRIPTION("6LoWPAN generic header fragmentation extension compression"); diff --git a/net/6lowpan/nhc_ghc_ext_hop.c b/net/6lowpan/nhc_ghc_ext_hop.c index 3beedf5140a3..9b0de4da7379 100644 --- a/net/6lowpan/nhc_ghc_ext_hop.c +++ b/net/6lowpan/nhc_ghc_ext_hop.c @@ -5,18 +5,11 @@ #include "nhc.h" -#define LOWPAN_GHC_EXT_HOP_IDLEN 1 #define LOWPAN_GHC_EXT_HOP_ID_0 0xb0 #define LOWPAN_GHC_EXT_HOP_MASK_0 0xfe -static void hop_ghid_setup(struct lowpan_nhc *nhc) -{ - nhc->id[0] = LOWPAN_GHC_EXT_HOP_ID_0; - nhc->idmask[0] = LOWPAN_GHC_EXT_HOP_MASK_0; -} - LOWPAN_NHC(ghc_ext_hop, "RFC7400 Hop-by-Hop Extension Header", NEXTHDR_HOP, 0, - hop_ghid_setup, LOWPAN_GHC_EXT_HOP_IDLEN, NULL, NULL); + LOWPAN_GHC_EXT_HOP_ID_0, LOWPAN_GHC_EXT_HOP_MASK_0, NULL, NULL); module_lowpan_nhc(ghc_ext_hop); MODULE_DESCRIPTION("6LoWPAN generic header hop-by-hop extension compression"); diff --git a/net/6lowpan/nhc_ghc_ext_route.c b/net/6lowpan/nhc_ghc_ext_route.c index 70dc0ea3cf66..3e86faec59c9 100644 --- a/net/6lowpan/nhc_ghc_ext_route.c +++ b/net/6lowpan/nhc_ghc_ext_route.c @@ -5,18 +5,11 @@ #include "nhc.h" -#define LOWPAN_GHC_EXT_ROUTE_IDLEN 1 #define LOWPAN_GHC_EXT_ROUTE_ID_0 0xb2 #define LOWPAN_GHC_EXT_ROUTE_MASK_0 0xfe -static void route_ghid_setup(struct lowpan_nhc *nhc) -{ - nhc->id[0] = LOWPAN_GHC_EXT_ROUTE_ID_0; - nhc->idmask[0] = LOWPAN_GHC_EXT_ROUTE_MASK_0; -} - LOWPAN_NHC(ghc_ext_route, "RFC7400 Routing Extension Header", NEXTHDR_ROUTING, - 0, route_ghid_setup, LOWPAN_GHC_EXT_ROUTE_IDLEN, NULL, NULL); + 0, LOWPAN_GHC_EXT_ROUTE_ID_0, LOWPAN_GHC_EXT_ROUTE_MASK_0, NULL, NULL); module_lowpan_nhc(ghc_ext_route); MODULE_DESCRIPTION("6LoWPAN generic header routing extension compression"); diff --git a/net/6lowpan/nhc_ghc_icmpv6.c b/net/6lowpan/nhc_ghc_icmpv6.c index 339ceffc25a9..1634f3eb0be8 100644 --- a/net/6lowpan/nhc_ghc_icmpv6.c +++ b/net/6lowpan/nhc_ghc_icmpv6.c @@ -5,18 +5,11 @@ #include "nhc.h" -#define LOWPAN_GHC_ICMPV6_IDLEN 1 #define LOWPAN_GHC_ICMPV6_ID_0 0xdf #define LOWPAN_GHC_ICMPV6_MASK_0 0xff -static void icmpv6_ghid_setup(struct lowpan_nhc *nhc) -{ - nhc->id[0] = LOWPAN_GHC_ICMPV6_ID_0; - nhc->idmask[0] = LOWPAN_GHC_ICMPV6_MASK_0; -} - LOWPAN_NHC(ghc_icmpv6, "RFC7400 ICMPv6", NEXTHDR_ICMP, 0, - icmpv6_ghid_setup, LOWPAN_GHC_ICMPV6_IDLEN, NULL, NULL); + LOWPAN_GHC_ICMPV6_ID_0, LOWPAN_GHC_ICMPV6_MASK_0, NULL, NULL); module_lowpan_nhc(ghc_icmpv6); MODULE_DESCRIPTION("6LoWPAN generic header ICMPv6 compression"); diff --git a/net/6lowpan/nhc_ghc_udp.c b/net/6lowpan/nhc_ghc_udp.c index f47fec601e73..4ac4813b77ad 100644 --- a/net/6lowpan/nhc_ghc_udp.c +++ b/net/6lowpan/nhc_ghc_udp.c @@ -5,18 +5,11 @@ #include "nhc.h" -#define LOWPAN_GHC_UDP_IDLEN 1 #define LOWPAN_GHC_UDP_ID_0 0xd0 #define LOWPAN_GHC_UDP_MASK_0 0xf8 -static void udp_ghid_setup(struct lowpan_nhc *nhc) -{ - nhc->id[0] = LOWPAN_GHC_UDP_ID_0; - nhc->idmask[0] = LOWPAN_GHC_UDP_MASK_0; -} - LOWPAN_NHC(ghc_udp, "RFC7400 UDP", NEXTHDR_UDP, 0, - udp_ghid_setup, LOWPAN_GHC_UDP_IDLEN, NULL, NULL); + LOWPAN_GHC_UDP_ID_0, LOWPAN_GHC_UDP_MASK_0, NULL, NULL); module_lowpan_nhc(ghc_udp); MODULE_DESCRIPTION("6LoWPAN generic header UDP compression"); diff --git a/net/6lowpan/nhc_hop.c b/net/6lowpan/nhc_hop.c index 158fc1906327..182087dfd09d 100644 --- a/net/6lowpan/nhc_hop.c +++ b/net/6lowpan/nhc_hop.c @@ -5,18 +5,11 @@ #include "nhc.h" -#define LOWPAN_NHC_HOP_IDLEN 1 #define LOWPAN_NHC_HOP_ID_0 0xe0 #define LOWPAN_NHC_HOP_MASK_0 0xfe -static void hop_nhid_setup(struct lowpan_nhc *nhc) -{ - nhc->id[0] = LOWPAN_NHC_HOP_ID_0; - nhc->idmask[0] = LOWPAN_NHC_HOP_MASK_0; -} - LOWPAN_NHC(nhc_hop, "RFC6282 Hop-by-Hop Options", NEXTHDR_HOP, 0, - hop_nhid_setup, LOWPAN_NHC_HOP_IDLEN, NULL, NULL); + LOWPAN_NHC_HOP_ID_0, LOWPAN_NHC_HOP_MASK_0, NULL, NULL); module_lowpan_nhc(nhc_hop); MODULE_DESCRIPTION("6LoWPAN next header RFC6282 Hop-by-Hop Options compression"); diff --git a/net/6lowpan/nhc_ipv6.c b/net/6lowpan/nhc_ipv6.c index 08b7589e5b38..20242360b1d4 100644 --- a/net/6lowpan/nhc_ipv6.c +++ b/net/6lowpan/nhc_ipv6.c @@ -5,18 +5,11 @@ #include "nhc.h" -#define LOWPAN_NHC_IPV6_IDLEN 1 #define LOWPAN_NHC_IPV6_ID_0 0xee #define LOWPAN_NHC_IPV6_MASK_0 0xfe -static void ipv6_nhid_setup(struct lowpan_nhc *nhc) -{ - nhc->id[0] = LOWPAN_NHC_IPV6_ID_0; - nhc->idmask[0] = LOWPAN_NHC_IPV6_MASK_0; -} - -LOWPAN_NHC(nhc_ipv6, "RFC6282 IPv6", NEXTHDR_IPV6, 0, ipv6_nhid_setup, - LOWPAN_NHC_IPV6_IDLEN, NULL, NULL); +LOWPAN_NHC(nhc_ipv6, "RFC6282 IPv6", NEXTHDR_IPV6, 0, LOWPAN_NHC_IPV6_ID_0, + LOWPAN_NHC_IPV6_MASK_0, NULL, NULL); module_lowpan_nhc(nhc_ipv6); MODULE_DESCRIPTION("6LoWPAN next header RFC6282 IPv6 compression"); diff --git a/net/6lowpan/nhc_mobility.c b/net/6lowpan/nhc_mobility.c index ac8fca689828..1c31d872c804 100644 --- a/net/6lowpan/nhc_mobility.c +++ b/net/6lowpan/nhc_mobility.c @@ -5,18 +5,11 @@ #include "nhc.h" -#define LOWPAN_NHC_MOBILITY_IDLEN 1 #define LOWPAN_NHC_MOBILITY_ID_0 0xe8 #define LOWPAN_NHC_MOBILITY_MASK_0 0xfe -static void mobility_nhid_setup(struct lowpan_nhc *nhc) -{ - nhc->id[0] = LOWPAN_NHC_MOBILITY_ID_0; - nhc->idmask[0] = LOWPAN_NHC_MOBILITY_MASK_0; -} - LOWPAN_NHC(nhc_mobility, "RFC6282 Mobility", NEXTHDR_MOBILITY, 0, - mobility_nhid_setup, LOWPAN_NHC_MOBILITY_IDLEN, NULL, NULL); + LOWPAN_NHC_MOBILITY_ID_0, LOWPAN_NHC_MOBILITY_MASK_0, NULL, NULL); module_lowpan_nhc(nhc_mobility); MODULE_DESCRIPTION("6LoWPAN next header RFC6282 Mobility compression"); diff --git a/net/6lowpan/nhc_routing.c b/net/6lowpan/nhc_routing.c index 1c174023de42..dae03ebf7021 100644 --- a/net/6lowpan/nhc_routing.c +++ b/net/6lowpan/nhc_routing.c @@ -5,18 +5,11 @@ #include "nhc.h" -#define LOWPAN_NHC_ROUTING_IDLEN 1 #define LOWPAN_NHC_ROUTING_ID_0 0xe2 #define LOWPAN_NHC_ROUTING_MASK_0 0xfe -static void routing_nhid_setup(struct lowpan_nhc *nhc) -{ - nhc->id[0] = LOWPAN_NHC_ROUTING_ID_0; - nhc->idmask[0] = LOWPAN_NHC_ROUTING_MASK_0; -} - LOWPAN_NHC(nhc_routing, "RFC6282 Routing", NEXTHDR_ROUTING, 0, - routing_nhid_setup, LOWPAN_NHC_ROUTING_IDLEN, NULL, NULL); + LOWPAN_NHC_ROUTING_ID_0, LOWPAN_NHC_ROUTING_MASK_0, NULL, NULL); module_lowpan_nhc(nhc_routing); MODULE_DESCRIPTION("6LoWPAN next header RFC6282 Routing compression"); diff --git a/net/6lowpan/nhc_udp.c b/net/6lowpan/nhc_udp.c index 33f17bd8cda7..0a506c77283d 100644 --- a/net/6lowpan/nhc_udp.c +++ b/net/6lowpan/nhc_udp.c @@ -14,7 +14,6 @@ #define LOWPAN_NHC_UDP_MASK 0xF8 #define LOWPAN_NHC_UDP_ID 0xF0 -#define LOWPAN_NHC_UDP_IDLEN 1 #define LOWPAN_NHC_UDP_4BIT_PORT 0xF0B0 #define LOWPAN_NHC_UDP_4BIT_MASK 0xFFF0 @@ -169,14 +168,8 @@ static int udp_compress(struct sk_buff *skb, u8 **hc_ptr) return 0; } -static void udp_nhid_setup(struct lowpan_nhc *nhc) -{ - nhc->id[0] = LOWPAN_NHC_UDP_ID; - nhc->idmask[0] = LOWPAN_NHC_UDP_MASK; -} - LOWPAN_NHC(nhc_udp, "RFC6282 UDP", NEXTHDR_UDP, sizeof(struct udphdr), - udp_nhid_setup, LOWPAN_NHC_UDP_IDLEN, udp_uncompress, udp_compress); + LOWPAN_NHC_UDP_ID, LOWPAN_NHC_UDP_MASK, udp_uncompress, udp_compress); module_lowpan_nhc(nhc_udp); MODULE_DESCRIPTION("6LoWPAN next header RFC6282 UDP compression"); diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index acf8c791f320..5aa8144101dc 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -63,10 +63,10 @@ bool vlan_do_receive(struct sk_buff **skbp) rx_stats = this_cpu_ptr(vlan_dev_priv(vlan_dev)->vlan_pcpu_stats); u64_stats_update_begin(&rx_stats->syncp); - rx_stats->rx_packets++; - rx_stats->rx_bytes += skb->len; + u64_stats_inc(&rx_stats->rx_packets); + u64_stats_add(&rx_stats->rx_bytes, skb->len); if (skb->pkt_type == PACKET_MULTICAST) - rx_stats->rx_multicast++; + u64_stats_inc(&rx_stats->rx_multicast); u64_stats_update_end(&rx_stats->syncp); return true; diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 839f2020b015..035812b0461c 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -128,8 +128,8 @@ static netdev_tx_t vlan_dev_hard_start_xmit(struct sk_buff *skb, stats = this_cpu_ptr(vlan->vlan_pcpu_stats); u64_stats_update_begin(&stats->syncp); - stats->tx_packets++; - stats->tx_bytes += len; + u64_stats_inc(&stats->tx_packets); + u64_stats_add(&stats->tx_bytes, len); u64_stats_update_end(&stats->syncp); } else { this_cpu_inc(vlan->vlan_pcpu_stats->tx_dropped); @@ -615,7 +615,7 @@ static int vlan_dev_init(struct net_device *dev) return -ENOMEM; /* Get vlan's reference to real_dev */ - dev_hold_track(real_dev, &vlan->dev_tracker, GFP_KERNEL); + netdev_hold(real_dev, &vlan->dev_tracker, GFP_KERNEL); return 0; } @@ -713,11 +713,11 @@ static void vlan_dev_get_stats64(struct net_device *dev, p = per_cpu_ptr(vlan_dev_priv(dev)->vlan_pcpu_stats, i); do { start = u64_stats_fetch_begin_irq(&p->syncp); - rxpackets = p->rx_packets; - rxbytes = p->rx_bytes; - rxmulticast = p->rx_multicast; - txpackets = p->tx_packets; - txbytes = p->tx_bytes; + rxpackets = u64_stats_read(&p->rx_packets); + rxbytes = u64_stats_read(&p->rx_bytes); + rxmulticast = u64_stats_read(&p->rx_multicast); + txpackets = u64_stats_read(&p->tx_packets); + txbytes = u64_stats_read(&p->tx_bytes); } while (u64_stats_fetch_retry_irq(&p->syncp, start)); stats->rx_packets += rxpackets; @@ -726,8 +726,8 @@ static void vlan_dev_get_stats64(struct net_device *dev, stats->tx_packets += txpackets; stats->tx_bytes += txbytes; /* rx_errors & tx_dropped are u32 */ - rx_errors += p->rx_errors; - tx_dropped += p->tx_dropped; + rx_errors += READ_ONCE(p->rx_errors); + tx_dropped += READ_ONCE(p->tx_dropped); } stats->rx_errors = rx_errors; stats->tx_dropped = tx_dropped; @@ -852,7 +852,7 @@ static void vlan_dev_free(struct net_device *dev) vlan->vlan_pcpu_stats = NULL; /* Get rid of the vlan's reference to real_dev */ - dev_put_track(vlan->real_dev, &vlan->dev_tracker); + netdev_put(vlan->real_dev, &vlan->dev_tracker); } void vlan_setup(struct net_device *dev) diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 4c7030ed8d33..bbac3cb4dc99 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -102,7 +102,8 @@ again: ax25_disconnect(s, ENETUNREACH); s->ax25_dev = NULL; if (sk->sk_socket) { - dev_put_track(ax25_dev->dev, &ax25_dev->dev_tracker); + netdev_put(ax25_dev->dev, + &ax25_dev->dev_tracker); ax25_dev_put(ax25_dev); } ax25_cb_del(s); @@ -1065,7 +1066,7 @@ static int ax25_release(struct socket *sock) del_timer_sync(&ax25->t3timer); del_timer_sync(&ax25->idletimer); } - dev_put_track(ax25_dev->dev, &ax25_dev->dev_tracker); + netdev_put(ax25_dev->dev, &ax25_dev->dev_tracker); ax25_dev_put(ax25_dev); } @@ -1146,7 +1147,7 @@ static int ax25_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) if (ax25_dev) { ax25_fillin_cb(ax25, ax25_dev); - dev_hold_track(ax25_dev->dev, &ax25_dev->dev_tracker, GFP_ATOMIC); + netdev_hold(ax25_dev->dev, &ax25_dev->dev_tracker, GFP_ATOMIC); } done: diff --git a/net/ax25/ax25_dev.c b/net/ax25/ax25_dev.c index 95a76d571c44..ab88b6ac5401 100644 --- a/net/ax25/ax25_dev.c +++ b/net/ax25/ax25_dev.c @@ -60,7 +60,7 @@ void ax25_dev_device_up(struct net_device *dev) refcount_set(&ax25_dev->refcount, 1); dev->ax25_ptr = ax25_dev; ax25_dev->dev = dev; - dev_hold_track(dev, &ax25_dev->dev_tracker, GFP_ATOMIC); + netdev_hold(dev, &ax25_dev->dev_tracker, GFP_ATOMIC); ax25_dev->forward = NULL; ax25_dev->device_up = true; @@ -136,7 +136,7 @@ unlock_put: spin_unlock_bh(&ax25_dev_lock); ax25_dev_put(ax25_dev); dev->ax25_ptr = NULL; - dev_put_track(dev, &ax25_dev->dev_tracker); + netdev_put(dev, &ax25_dev->dev_tracker); ax25_dev_put(ax25_dev); } @@ -205,7 +205,7 @@ void __exit ax25_dev_free(void) ax25_dev = ax25_dev_list; while (ax25_dev != NULL) { s = ax25_dev; - dev_put_track(ax25_dev->dev, &ax25_dev->dev_tracker); + netdev_put(ax25_dev->dev, &ax25_dev->dev_tracker); ax25_dev = ax25_dev->next; kfree(s); } diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 47fcbade7389..a84a7cfb9d6d 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -274,7 +274,7 @@ static void destroy_nbp(struct net_bridge_port *p) p->br = NULL; p->dev = NULL; - dev_put_track(dev, &p->dev_tracker); + netdev_put(dev, &p->dev_tracker); kobject_put(&p->kobj); } @@ -423,7 +423,7 @@ static struct net_bridge_port *new_nbp(struct net_bridge *br, return ERR_PTR(-ENOMEM); p->br = br; - dev_hold_track(dev, &p->dev_tracker, GFP_KERNEL); + netdev_hold(dev, &p->dev_tracker, GFP_KERNEL); p->dev = dev; p->path_cost = port_cost(dev); p->priority = 0x8000 >> BR_PORT_BITS; @@ -434,7 +434,7 @@ static struct net_bridge_port *new_nbp(struct net_bridge *br, br_stp_port_timer_init(p); err = br_multicast_add_port(p); if (err) { - dev_put_track(dev, &p->dev_tracker); + netdev_put(dev, &p->dev_tracker); kfree(p); p = ERR_PTR(err); } @@ -615,7 +615,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev, err = dev_set_allmulti(dev, 1); if (err) { br_multicast_del_port(p); - dev_put_track(dev, &p->dev_tracker); + netdev_put(dev, &p->dev_tracker); kfree(p); /* kobject not yet init'd, manually free */ goto err1; } @@ -725,7 +725,7 @@ err3: sysfs_remove_link(br->ifobj, p->dev->name); err2: br_multicast_del_port(p); - dev_put_track(dev, &p->dev_tracker); + netdev_put(dev, &p->dev_tracker); kobject_put(&p->kobj); dev_set_allmulti(dev, -1); err1: diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index fdcc641fc89a..589ff497d50c 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -1025,8 +1025,8 @@ static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, NL_SET_ERR_MSG_MOD(extack, "Port belongs to a different bridge device"); return -EINVAL; } - if (p->state == BR_STATE_DISABLED) { - NL_SET_ERR_MSG_MOD(extack, "Port is in disabled state"); + if (p->state == BR_STATE_DISABLED && entry->state != MDB_PERMANENT) { + NL_SET_ERR_MSG_MOD(extack, "Port is in disabled state and entry is not permanent"); return -EINVAL; } vg = nbp_vlan_group(p); @@ -1086,9 +1086,6 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry, if (!p->key.port || p->key.port->dev->ifindex != entry->ifindex) continue; - if (p->key.port->state == BR_STATE_DISABLED) - goto unlock; - br_multicast_del_pg(mp, p, pp); err = 0; break; @@ -1124,8 +1121,14 @@ static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, return -ENODEV; p = br_port_get_rtnl(pdev); - if (!p || p->br != br || p->state == BR_STATE_DISABLED) + if (!p) { + NL_SET_ERR_MSG_MOD(extack, "Net device is not a bridge port"); + return -EINVAL; + } + if (p->br != br) { + NL_SET_ERR_MSG_MOD(extack, "Port belongs to a different bridge device"); return -EINVAL; + } vg = nbp_vlan_group(p); } else { vg = br_vlan_group(br); diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index bb01776d2d88..1ef14a099c6b 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -1770,10 +1770,10 @@ static int br_fill_linkxstats(struct sk_buff *skb, if (v->vid == pvid) vxi.flags |= BRIDGE_VLAN_INFO_PVID; br_vlan_get_stats(v, &stats); - vxi.rx_bytes = stats.rx_bytes; - vxi.rx_packets = stats.rx_packets; - vxi.tx_bytes = stats.tx_bytes; - vxi.tx_packets = stats.tx_packets; + vxi.rx_bytes = u64_stats_read(&stats.rx_bytes); + vxi.rx_packets = u64_stats_read(&stats.rx_packets); + vxi.tx_bytes = u64_stats_read(&stats.tx_bytes); + vxi.tx_packets = u64_stats_read(&stats.tx_packets); if (nla_put(skb, BRIDGE_XSTATS_VLAN, sizeof(vxi), &vxi)) goto nla_put_failure; diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 0f5e75ccac79..6e53dc991409 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -505,8 +505,8 @@ struct sk_buff *br_handle_vlan(struct net_bridge *br, if (br_opt_get(br, BROPT_VLAN_STATS_ENABLED)) { stats = this_cpu_ptr(v->stats); u64_stats_update_begin(&stats->syncp); - stats->tx_bytes += skb->len; - stats->tx_packets++; + u64_stats_add(&stats->tx_bytes, skb->len); + u64_stats_inc(&stats->tx_packets); u64_stats_update_end(&stats->syncp); } @@ -624,8 +624,8 @@ static bool __allowed_ingress(const struct net_bridge *br, if (br_opt_get(br, BROPT_VLAN_STATS_ENABLED)) { stats = this_cpu_ptr(v->stats); u64_stats_update_begin(&stats->syncp); - stats->rx_bytes += skb->len; - stats->rx_packets++; + u64_stats_add(&stats->rx_bytes, skb->len); + u64_stats_inc(&stats->rx_packets); u64_stats_update_end(&stats->syncp); } @@ -1379,16 +1379,16 @@ void br_vlan_get_stats(const struct net_bridge_vlan *v, cpu_stats = per_cpu_ptr(v->stats, i); do { start = u64_stats_fetch_begin_irq(&cpu_stats->syncp); - rxpackets = cpu_stats->rx_packets; - rxbytes = cpu_stats->rx_bytes; - txbytes = cpu_stats->tx_bytes; - txpackets = cpu_stats->tx_packets; + rxpackets = u64_stats_read(&cpu_stats->rx_packets); + rxbytes = u64_stats_read(&cpu_stats->rx_bytes); + txbytes = u64_stats_read(&cpu_stats->tx_bytes); + txpackets = u64_stats_read(&cpu_stats->tx_packets); } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start)); - stats->rx_packets += rxpackets; - stats->rx_bytes += rxbytes; - stats->tx_bytes += txbytes; - stats->tx_packets += txpackets; + u64_stats_add(&stats->rx_packets, rxpackets); + u64_stats_add(&stats->rx_bytes, rxbytes); + u64_stats_add(&stats->tx_bytes, txbytes); + u64_stats_add(&stats->tx_packets, txpackets); } } @@ -1779,14 +1779,18 @@ static bool br_vlan_stats_fill(struct sk_buff *skb, return false; br_vlan_get_stats(v, &stats); - if (nla_put_u64_64bit(skb, BRIDGE_VLANDB_STATS_RX_BYTES, stats.rx_bytes, + if (nla_put_u64_64bit(skb, BRIDGE_VLANDB_STATS_RX_BYTES, + u64_stats_read(&stats.rx_bytes), BRIDGE_VLANDB_STATS_PAD) || nla_put_u64_64bit(skb, BRIDGE_VLANDB_STATS_RX_PACKETS, - stats.rx_packets, BRIDGE_VLANDB_STATS_PAD) || - nla_put_u64_64bit(skb, BRIDGE_VLANDB_STATS_TX_BYTES, stats.tx_bytes, + u64_stats_read(&stats.rx_packets), + BRIDGE_VLANDB_STATS_PAD) || + nla_put_u64_64bit(skb, BRIDGE_VLANDB_STATS_TX_BYTES, + u64_stats_read(&stats.tx_bytes), BRIDGE_VLANDB_STATS_PAD) || nla_put_u64_64bit(skb, BRIDGE_VLANDB_STATS_TX_PACKETS, - stats.tx_packets, BRIDGE_VLANDB_STATS_PAD)) + u64_stats_read(&stats.tx_packets), + BRIDGE_VLANDB_STATS_PAD)) goto out_err; nla_nest_end(skb, nest); diff --git a/net/core/.gitignore b/net/core/.gitignore new file mode 100644 index 000000000000..df1e74372cce --- /dev/null +++ b/net/core/.gitignore @@ -0,0 +1 @@ +dropreason_str.c diff --git a/net/core/Makefile b/net/core/Makefile index a8e4f737692b..e8ce3bd283a6 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -4,7 +4,8 @@ # obj-y := sock.o request_sock.o skbuff.o datagram.o stream.o scm.o \ - gen_stats.o gen_estimator.o net_namespace.o secure_seq.o flow_dissector.o + gen_stats.o gen_estimator.o net_namespace.o secure_seq.o \ + flow_dissector.o dropreason_str.o obj-$(CONFIG_SYSCTL) += sysctl_net_core.o @@ -39,3 +40,23 @@ obj-$(CONFIG_NET_SOCK_MSG) += skmsg.o obj-$(CONFIG_BPF_SYSCALL) += sock_map.o obj-$(CONFIG_BPF_SYSCALL) += bpf_sk_storage.o obj-$(CONFIG_OF) += of_net.o + +clean-files := dropreason_str.c + +quiet_cmd_dropreason_str = GEN $@ +cmd_dropreason_str = awk -F ',' 'BEGIN{ print "\#include <net/dropreason.h>\n"; \ + print "const char * const drop_reasons[] = {" }\ + /^enum skb_drop/ { dr=1; }\ + /^\};/ { dr=0; }\ + /^\tSKB_DROP_REASON_/ {\ + if (dr) {\ + sub(/\tSKB_DROP_REASON_/, "", $$1);\ + printf "\t[SKB_DROP_REASON_%s] = \"%s\",\n", $$1, $$1;\ + }\ + }\ + END{ print "};" }' $< > $@ + +$(obj)/dropreason_str.c: $(srctree)/include/net/dropreason.h + $(call cmd,dropreason_str) + +$(obj)/dropreason_str.o: $(obj)/dropreason_str.c diff --git a/net/core/datagram.c b/net/core/datagram.c index 50f4faeea76c..35791f86bd1a 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -320,7 +320,6 @@ EXPORT_SYMBOL(skb_recv_datagram); void skb_free_datagram(struct sock *sk, struct sk_buff *skb) { consume_skb(skb); - sk_mem_reclaim_partial(sk); } EXPORT_SYMBOL(skb_free_datagram); @@ -336,7 +335,6 @@ void __skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb, int len) slow = lock_sock_fast(sk); sk_peek_offset_bwd(sk, len); skb_orphan(skb); - sk_mem_reclaim_partial(sk); unlock_sock_fast(sk, slow); /* skb is now orphaned, can be freed outside of locked section */ @@ -396,7 +394,6 @@ int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags) NULL); kfree_skb(skb); - sk_mem_reclaim_partial(sk); return err; } EXPORT_SYMBOL(skb_kill_datagram); diff --git a/net/core/dev.c b/net/core/dev.c index 08ce317fcec8..8958c4227b67 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3925,7 +3925,7 @@ int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *skb) skb->pkt_type = PACKET_LOOPBACK; if (skb->ip_summed == CHECKSUM_NONE) skb->ip_summed = CHECKSUM_UNNECESSARY; - WARN_ON(!skb_dst(skb)); + DEBUG_NET_WARN_ON_ONCE(!skb_dst(skb)); skb_dst_force(skb); netif_rx(skb); return 0; @@ -6351,6 +6351,23 @@ int dev_set_threaded(struct net_device *dev, bool threaded) } EXPORT_SYMBOL(dev_set_threaded); +/* Double check that napi_get_frags() allocates skbs with + * skb->head being backed by slab, not a page fragment. + * This is to make sure bug fixed in 3226b158e67c + * ("net: avoid 32 x truesize under-estimation for tiny skbs") + * does not accidentally come back. + */ +static void napi_get_frags_check(struct napi_struct *napi) +{ + struct sk_buff *skb; + + local_bh_disable(); + skb = napi_get_frags(napi); + WARN_ON_ONCE(skb && skb->head_frag); + napi_free_frags(napi); + local_bh_enable(); +} + void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), int weight) { @@ -6378,6 +6395,7 @@ void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi, set_bit(NAPI_STATE_NPSVC, &napi->state); list_add_rcu(&napi->dev_list, &dev->napi_list); napi_hash_add(napi); + napi_get_frags_check(napi); /* Create kthread for this napi if dev->threaded is set. * Clear dev->threaded if kthread creation failed so that * threaded mode will not be enabled in napi_enable(). @@ -7463,7 +7481,7 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev, adj->ref_nr = 1; adj->private = private; adj->ignore = false; - dev_hold_track(adj_dev, &adj->dev_tracker, GFP_KERNEL); + netdev_hold(adj_dev, &adj->dev_tracker, GFP_KERNEL); pr_debug("Insert adjacency: dev %s adj_dev %s adj->ref_nr %d; dev_hold on %s\n", dev->name, adj_dev->name, adj->ref_nr, adj_dev->name); @@ -7492,7 +7510,7 @@ remove_symlinks: if (netdev_adjacent_is_neigh_list(dev, adj_dev, dev_list)) netdev_adjacent_sysfs_del(dev, adj_dev->name, dev_list); free_adj: - dev_put_track(adj_dev, &adj->dev_tracker); + netdev_put(adj_dev, &adj->dev_tracker); kfree(adj); return ret; @@ -7534,7 +7552,7 @@ static void __netdev_adjacent_dev_remove(struct net_device *dev, list_del_rcu(&adj->list); pr_debug("adjacency: dev_put for %s, because link removed from %s to %s\n", adj_dev->name, dev->name, adj_dev->name); - dev_put_track(adj_dev, &adj->dev_tracker); + netdev_put(adj_dev, &adj->dev_tracker); kfree_rcu(adj, rcu); } @@ -10062,7 +10080,7 @@ int register_netdevice(struct net_device *dev) dev_init_scheduler(dev); - dev_hold_track(dev, &dev->dev_registered_tracker, GFP_KERNEL); + netdev_hold(dev, &dev->dev_registered_tracker, GFP_KERNEL); list_netdevice(dev); add_device_randomness(dev->dev_addr, dev->addr_len); @@ -10459,23 +10477,23 @@ void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s, int cpu; for_each_possible_cpu(cpu) { + u64 rx_packets, rx_bytes, tx_packets, tx_bytes; const struct pcpu_sw_netstats *stats; - struct pcpu_sw_netstats tmp; unsigned int start; stats = per_cpu_ptr(netstats, cpu); do { start = u64_stats_fetch_begin_irq(&stats->syncp); - tmp.rx_packets = stats->rx_packets; - tmp.rx_bytes = stats->rx_bytes; - tmp.tx_packets = stats->tx_packets; - tmp.tx_bytes = stats->tx_bytes; + rx_packets = u64_stats_read(&stats->rx_packets); + rx_bytes = u64_stats_read(&stats->rx_bytes); + tx_packets = u64_stats_read(&stats->tx_packets); + tx_bytes = u64_stats_read(&stats->tx_bytes); } while (u64_stats_fetch_retry_irq(&stats->syncp, start)); - s->rx_packets += tmp.rx_packets; - s->rx_bytes += tmp.rx_bytes; - s->tx_packets += tmp.tx_packets; - s->tx_bytes += tmp.tx_bytes; + s->rx_packets += rx_packets; + s->rx_bytes += rx_bytes; + s->tx_packets += tx_packets; + s->tx_bytes += tx_bytes; } } EXPORT_SYMBOL_GPL(dev_fetch_sw_netstats); @@ -10868,7 +10886,7 @@ void unregister_netdevice_many(struct list_head *head) synchronize_net(); list_for_each_entry(dev, head, unreg_list) { - dev_put_track(dev, &dev->dev_registered_tracker); + netdev_put(dev, &dev->dev_registered_tracker); net_set_todo(dev); } diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 4f6be442ae7e..7674bb9f3076 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -384,10 +384,10 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, void __user *data, return -ENODEV; if (!netif_is_bridge_master(dev)) return -EOPNOTSUPP; - dev_hold_track(dev, &dev_tracker, GFP_KERNEL); + netdev_hold(dev, &dev_tracker, GFP_KERNEL); rtnl_unlock(); err = br_ioctl_call(net, netdev_priv(dev), cmd, ifr, NULL); - dev_put_track(dev, &dev_tracker); + netdev_put(dev, &dev_tracker); rtnl_lock(); return err; diff --git a/net/core/devlink.c b/net/core/devlink.c index 5cc88490f18f..db61f3a341cb 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -7946,8 +7946,8 @@ static int devlink_nl_cmd_health_reporter_test_doit(struct sk_buff *skb, } struct devlink_stats { - u64 rx_bytes; - u64 rx_packets; + u64_stats_t rx_bytes; + u64_stats_t rx_packets; struct u64_stats_sync syncp; }; @@ -8104,12 +8104,12 @@ static void devlink_trap_stats_read(struct devlink_stats __percpu *trap_stats, cpu_stats = per_cpu_ptr(trap_stats, i); do { start = u64_stats_fetch_begin_irq(&cpu_stats->syncp); - rx_packets = cpu_stats->rx_packets; - rx_bytes = cpu_stats->rx_bytes; + rx_packets = u64_stats_read(&cpu_stats->rx_packets); + rx_bytes = u64_stats_read(&cpu_stats->rx_bytes); } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start)); - stats->rx_packets += rx_packets; - stats->rx_bytes += rx_bytes; + u64_stats_add(&stats->rx_packets, rx_packets); + u64_stats_add(&stats->rx_bytes, rx_bytes); } } @@ -8127,11 +8127,13 @@ devlink_trap_group_stats_put(struct sk_buff *msg, return -EMSGSIZE; if (nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_PACKETS, - stats.rx_packets, DEVLINK_ATTR_PAD)) + u64_stats_read(&stats.rx_packets), + DEVLINK_ATTR_PAD)) goto nla_put_failure; if (nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_BYTES, - stats.rx_bytes, DEVLINK_ATTR_PAD)) + u64_stats_read(&stats.rx_bytes), + DEVLINK_ATTR_PAD)) goto nla_put_failure; nla_nest_end(msg, attr); @@ -8171,11 +8173,13 @@ static int devlink_trap_stats_put(struct sk_buff *msg, struct devlink *devlink, goto nla_put_failure; if (nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_PACKETS, - stats.rx_packets, DEVLINK_ATTR_PAD)) + u64_stats_read(&stats.rx_packets), + DEVLINK_ATTR_PAD)) goto nla_put_failure; if (nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_BYTES, - stats.rx_bytes, DEVLINK_ATTR_PAD)) + u64_stats_read(&stats.rx_bytes), + DEVLINK_ATTR_PAD)) goto nla_put_failure; nla_nest_end(msg, attr); @@ -11641,8 +11645,8 @@ devlink_trap_stats_update(struct devlink_stats __percpu *trap_stats, stats = this_cpu_ptr(trap_stats); u64_stats_update_begin(&stats->syncp); - stats->rx_bytes += skb_len; - stats->rx_packets++; + u64_stats_add(&stats->rx_bytes, skb_len); + u64_stats_inc(&stats->rx_packets); u64_stats_update_end(&stats->syncp); } diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 41cac0e4834e..75501e1bdd25 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -48,19 +48,6 @@ static int trace_state = TRACE_OFF; static bool monitor_hw; -#undef EM -#undef EMe - -#define EM(a, b) [a] = #b, -#define EMe(a, b) [a] = #b - -/* drop_reasons is used to translate 'enum skb_drop_reason' to string, - * which is reported to user space. - */ -static const char * const drop_reasons[] = { - TRACE_SKB_DROP_REASON -}; - /* net_dm_mutex * * An overall lock guarding every operation coming from userspace. @@ -68,7 +55,7 @@ static const char * const drop_reasons[] = { static DEFINE_MUTEX(net_dm_mutex); struct net_dm_stats { - u64 dropped; + u64_stats_t dropped; struct u64_stats_sync syncp; }; @@ -543,7 +530,7 @@ static void net_dm_packet_trace_kfree_skb_hit(void *ignore, unlock_free: spin_unlock_irqrestore(&data->drop_queue.lock, flags); u64_stats_update_begin(&data->stats.syncp); - data->stats.dropped++; + u64_stats_inc(&data->stats.dropped); u64_stats_update_end(&data->stats.syncp); consume_skb(nskb); } @@ -877,7 +864,8 @@ net_dm_hw_metadata_copy(const struct devlink_trap_metadata *metadata) } hw_metadata->input_dev = metadata->input_dev; - dev_hold_track(hw_metadata->input_dev, &hw_metadata->dev_tracker, GFP_ATOMIC); + netdev_hold(hw_metadata->input_dev, &hw_metadata->dev_tracker, + GFP_ATOMIC); return hw_metadata; @@ -893,7 +881,7 @@ free_hw_metadata: static void net_dm_hw_metadata_free(struct devlink_trap_metadata *hw_metadata) { - dev_put_track(hw_metadata->input_dev, &hw_metadata->dev_tracker); + netdev_put(hw_metadata->input_dev, &hw_metadata->dev_tracker); kfree(hw_metadata->fa_cookie); kfree(hw_metadata->trap_name); kfree(hw_metadata->trap_group_name); @@ -998,7 +986,7 @@ net_dm_hw_trap_packet_probe(void *ignore, const struct devlink *devlink, unlock_free: spin_unlock_irqrestore(&hw_data->drop_queue.lock, flags); u64_stats_update_begin(&hw_data->stats.syncp); - hw_data->stats.dropped++; + u64_stats_inc(&hw_data->stats.dropped); u64_stats_update_end(&hw_data->stats.syncp); net_dm_hw_metadata_free(n_hw_metadata); free: @@ -1445,10 +1433,10 @@ static void net_dm_stats_read(struct net_dm_stats *stats) do { start = u64_stats_fetch_begin_irq(&cpu_stats->syncp); - dropped = cpu_stats->dropped; + dropped = u64_stats_read(&cpu_stats->dropped); } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start)); - stats->dropped += dropped; + u64_stats_add(&stats->dropped, dropped); } } @@ -1464,7 +1452,7 @@ static int net_dm_stats_put(struct sk_buff *msg) return -EMSGSIZE; if (nla_put_u64_64bit(msg, NET_DM_ATTR_STATS_DROPPED, - stats.dropped, NET_DM_ATTR_PAD)) + u64_stats_read(&stats.dropped), NET_DM_ATTR_PAD)) goto nla_put_failure; nla_nest_end(msg, attr); @@ -1489,10 +1477,10 @@ static void net_dm_hw_stats_read(struct net_dm_stats *stats) do { start = u64_stats_fetch_begin_irq(&cpu_stats->syncp); - dropped = cpu_stats->dropped; + dropped = u64_stats_read(&cpu_stats->dropped); } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start)); - stats->dropped += dropped; + u64_stats_add(&stats->dropped, dropped); } } @@ -1508,7 +1496,7 @@ static int net_dm_hw_stats_put(struct sk_buff *msg) return -EMSGSIZE; if (nla_put_u64_64bit(msg, NET_DM_ATTR_STATS_DROPPED, - stats.dropped, NET_DM_ATTR_PAD)) + u64_stats_read(&stats.dropped), NET_DM_ATTR_PAD)) goto nla_put_failure; nla_nest_end(msg, attr); diff --git a/net/core/dst.c b/net/core/dst.c index d16c2c9bfebd..bc9c9be4e080 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -49,7 +49,7 @@ void dst_init(struct dst_entry *dst, struct dst_ops *ops, unsigned short flags) { dst->dev = dev; - dev_hold_track(dev, &dst->dev_tracker, GFP_ATOMIC); + netdev_hold(dev, &dst->dev_tracker, GFP_ATOMIC); dst->ops = ops; dst_init_metrics(dst, dst_default_metrics.metrics, true); dst->expires = 0UL; @@ -117,7 +117,7 @@ struct dst_entry *dst_destroy(struct dst_entry * dst) if (dst->ops->destroy) dst->ops->destroy(dst); - dev_put_track(dst->dev, &dst->dev_tracker); + netdev_put(dst->dev, &dst->dev_tracker); lwtstate_put(dst->lwtstate); @@ -159,8 +159,8 @@ void dst_dev_put(struct dst_entry *dst) dst->input = dst_discard; dst->output = dst_discard_out; dst->dev = blackhole_netdev; - dev_replace_track(dev, blackhole_netdev, &dst->dev_tracker, - GFP_ATOMIC); + netdev_ref_replace(dev, blackhole_netdev, &dst->dev_tracker, + GFP_ATOMIC); } EXPORT_SYMBOL(dst_dev_put); diff --git a/net/core/failover.c b/net/core/failover.c index dcaa92a85ea2..864d2d83eff4 100644 --- a/net/core/failover.c +++ b/net/core/failover.c @@ -252,7 +252,7 @@ struct failover *failover_register(struct net_device *dev, return ERR_PTR(-ENOMEM); rcu_assign_pointer(failover->ops, ops); - dev_hold_track(dev, &failover->dev_tracker, GFP_KERNEL); + netdev_hold(dev, &failover->dev_tracker, GFP_KERNEL); dev->priv_flags |= IFF_FAILOVER; rcu_assign_pointer(failover->failover_dev, dev); @@ -285,7 +285,7 @@ void failover_unregister(struct failover *failover) failover_dev->name); failover_dev->priv_flags &= ~IFF_FAILOVER; - dev_put_track(failover_dev, &failover->dev_tracker); + netdev_put(failover_dev, &failover->dev_tracker); spin_lock(&failover_lock); list_del(&failover->list); diff --git a/net/core/link_watch.c b/net/core/link_watch.c index a244d3bade7d..aa6cb1f90966 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -110,7 +110,7 @@ static void linkwatch_add_event(struct net_device *dev) spin_lock_irqsave(&lweventlist_lock, flags); if (list_empty(&dev->link_watch_list)) { list_add_tail(&dev->link_watch_list, &lweventlist); - dev_hold_track(dev, &dev->linkwatch_dev_tracker, GFP_ATOMIC); + netdev_hold(dev, &dev->linkwatch_dev_tracker, GFP_ATOMIC); } spin_unlock_irqrestore(&lweventlist_lock, flags); } diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 54625287ee5b..d8ec70622ecb 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -624,7 +624,7 @@ ___neigh_create(struct neigh_table *tbl, const void *pkey, memcpy(n->primary_key, pkey, key_len); n->dev = dev; - dev_hold_track(dev, &n->dev_tracker, GFP_ATOMIC); + netdev_hold(dev, &n->dev_tracker, GFP_ATOMIC); /* Protocol specific setup. */ if (tbl->constructor && (error = tbl->constructor(n)) < 0) { @@ -770,10 +770,10 @@ struct pneigh_entry * pneigh_lookup(struct neigh_table *tbl, write_pnet(&n->net, net); memcpy(n->key, pkey, key_len); n->dev = dev; - dev_hold_track(dev, &n->dev_tracker, GFP_KERNEL); + netdev_hold(dev, &n->dev_tracker, GFP_KERNEL); if (tbl->pconstructor && tbl->pconstructor(n)) { - dev_put_track(dev, &n->dev_tracker); + netdev_put(dev, &n->dev_tracker); kfree(n); n = NULL; goto out; @@ -805,7 +805,7 @@ int pneigh_delete(struct neigh_table *tbl, struct net *net, const void *pkey, write_unlock_bh(&tbl->lock); if (tbl->pdestructor) tbl->pdestructor(n); - dev_put_track(n->dev, &n->dev_tracker); + netdev_put(n->dev, &n->dev_tracker); kfree(n); return 0; } @@ -838,7 +838,7 @@ static int pneigh_ifdown_and_unlock(struct neigh_table *tbl, n->next = NULL; if (tbl->pdestructor) tbl->pdestructor(n); - dev_put_track(n->dev, &n->dev_tracker); + netdev_put(n->dev, &n->dev_tracker); kfree(n); } return -ENOENT; @@ -879,7 +879,7 @@ void neigh_destroy(struct neighbour *neigh) if (dev->netdev_ops->ndo_neigh_destroy) dev->netdev_ops->ndo_neigh_destroy(dev, neigh); - dev_put_track(dev, &neigh->dev_tracker); + netdev_put(dev, &neigh->dev_tracker); neigh_parms_put(neigh->parms); neigh_dbg(2, "neigh %p is destroyed\n", neigh); @@ -1671,13 +1671,13 @@ struct neigh_parms *neigh_parms_alloc(struct net_device *dev, refcount_set(&p->refcnt, 1); p->reachable_time = neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME)); - dev_hold_track(dev, &p->dev_tracker, GFP_KERNEL); + netdev_hold(dev, &p->dev_tracker, GFP_KERNEL); p->dev = dev; write_pnet(&p->net, net); p->sysctl_table = NULL; if (ops->ndo_neigh_setup && ops->ndo_neigh_setup(dev, p)) { - dev_put_track(dev, &p->dev_tracker); + netdev_put(dev, &p->dev_tracker); kfree(p); return NULL; } @@ -1708,7 +1708,7 @@ void neigh_parms_release(struct neigh_table *tbl, struct neigh_parms *parms) list_del(&parms->list); parms->dead = 1; write_unlock_bh(&tbl->lock); - dev_put_track(parms->dev, &parms->dev_tracker); + netdev_put(parms->dev, &parms->dev_tracker); call_rcu(&parms->rcu_head, neigh_rcu_free_parms); } EXPORT_SYMBOL(neigh_parms_release); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index e319e242dddf..d49fc974e630 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -1016,7 +1016,7 @@ static void rx_queue_release(struct kobject *kobj) #endif memset(kobj, 0, sizeof(*kobj)); - dev_put_track(queue->dev, &queue->dev_tracker); + netdev_put(queue->dev, &queue->dev_tracker); } static const void *rx_queue_namespace(struct kobject *kobj) @@ -1056,7 +1056,7 @@ static int rx_queue_add_kobject(struct net_device *dev, int index) /* Kobject_put later will trigger rx_queue_release call which * decreases dev refcount: Take that reference here */ - dev_hold_track(queue->dev, &queue->dev_tracker, GFP_KERNEL); + netdev_hold(queue->dev, &queue->dev_tracker, GFP_KERNEL); kobj->kset = dev->queues_kset; error = kobject_init_and_add(kobj, &rx_queue_ktype, NULL, @@ -1619,7 +1619,7 @@ static void netdev_queue_release(struct kobject *kobj) struct netdev_queue *queue = to_netdev_queue(kobj); memset(kobj, 0, sizeof(*kobj)); - dev_put_track(queue->dev, &queue->dev_tracker); + netdev_put(queue->dev, &queue->dev_tracker); } static const void *netdev_queue_namespace(struct kobject *kobj) @@ -1659,7 +1659,7 @@ static int netdev_queue_add_kobject(struct net_device *dev, int index) /* Kobject_put later will trigger netdev_queue_release call * which decreases dev refcount: Take that reference here */ - dev_hold_track(queue->dev, &queue->dev_tracker, GFP_KERNEL); + netdev_hold(queue->dev, &queue->dev_tracker, GFP_KERNEL); kobj->kset = dev->queues_kset; error = kobject_init_and_add(kobj, &netdev_queue_ktype, NULL, diff --git a/net/core/netpoll.c b/net/core/netpoll.c index db724463e7cd..5d27067b72d5 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -853,7 +853,7 @@ void netpoll_cleanup(struct netpoll *np) if (!np->dev) goto out; __netpoll_cleanup(np); - dev_put_track(np->dev, &np->dev_tracker); + netdev_put(np->dev, &np->dev_tracker); np->dev = NULL; out: rtnl_unlock(); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 84b62cd7bc57..88906ba6d9a7 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -2100,7 +2100,7 @@ static int pktgen_setup_dev(const struct pktgen_net *pn, /* Clean old setups */ if (pkt_dev->odev) { - dev_put_track(pkt_dev->odev, &pkt_dev->dev_tracker); + netdev_put(pkt_dev->odev, &pkt_dev->dev_tracker); pkt_dev->odev = NULL; } @@ -3807,7 +3807,7 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) return add_dev_to_thread(t, pkt_dev); out2: - dev_put_track(pkt_dev->odev, &pkt_dev->dev_tracker); + netdev_put(pkt_dev->odev, &pkt_dev->dev_tracker); out1: #ifdef CONFIG_XFRM free_SAs(pkt_dev); @@ -3901,7 +3901,7 @@ static int pktgen_remove_device(struct pktgen_thread *t, /* Dis-associate from the interface */ if (pkt_dev->odev) { - dev_put_track(pkt_dev->odev, &pkt_dev->dev_tracker); + netdev_put(pkt_dev->odev, &pkt_dev->dev_tracker); pkt_dev->odev = NULL; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 5b3559cb1d82..00bf35ee8205 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -91,6 +91,9 @@ static struct kmem_cache *skbuff_ext_cache __ro_after_init; int sysctl_max_skb_frags __read_mostly = MAX_SKB_FRAGS; EXPORT_SYMBOL(sysctl_max_skb_frags); +/* The array 'drop_reasons' is auto-generated in dropreason_str.c */ +EXPORT_SYMBOL(drop_reasons); + /** * skb_panic - private function for out-of-line support * @skb: buffer @@ -172,13 +175,14 @@ static struct sk_buff *napi_skb_cache_get(void) struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); struct sk_buff *skb; - if (unlikely(!nc->skb_count)) + if (unlikely(!nc->skb_count)) { nc->skb_count = kmem_cache_alloc_bulk(skbuff_head_cache, GFP_ATOMIC, NAPI_SKB_CACHE_BULK, nc->skb_cache); - if (unlikely(!nc->skb_count)) - return NULL; + if (unlikely(!nc->skb_count)) + return NULL; + } skb = nc->skb_cache[--nc->skb_count]; kasan_unpoison_object_data(skbuff_head_cache, skb); @@ -557,6 +561,7 @@ struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len, struct sk_buff *skb; void *data; + DEBUG_NET_WARN_ON_ONCE(!in_softirq()); len += NET_SKB_PAD + NET_IP_ALIGN; /* If requested length is either too small or too big, @@ -725,7 +730,7 @@ void skb_release_head_state(struct sk_buff *skb) { skb_dst_drop(skb); if (skb->destructor) { - WARN_ON(in_hardirq()); + DEBUG_NET_WARN_ON_ONCE(in_hardirq()); skb->destructor(skb); } #if IS_ENABLED(CONFIG_NF_CONNTRACK) @@ -978,7 +983,7 @@ void napi_consume_skb(struct sk_buff *skb, int budget) return; } - lockdep_assert_in_softirq(); + DEBUG_NET_WARN_ON_ONCE(!in_softirq()); if (!skb_unref(skb)) return; diff --git a/net/core/sock.c b/net/core/sock.c index 2ff40dd0a7a6..92a0296ccb18 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -991,7 +991,7 @@ EXPORT_SYMBOL(sock_set_mark); static void sock_release_reserved_memory(struct sock *sk, int bytes) { /* Round down bytes to multiple of pages */ - bytes &= ~(SK_MEM_QUANTUM - 1); + bytes = round_down(bytes, PAGE_SIZE); WARN_ON(bytes > sk->sk_reserved_mem); sk->sk_reserved_mem -= bytes; @@ -1019,7 +1019,8 @@ static int sock_reserve_memory(struct sock *sk, int bytes) return -ENOMEM; /* pre-charge to forward_alloc */ - allocated = sk_memory_allocated_add(sk, pages); + sk_memory_allocated_add(sk, pages); + allocated = sk_memory_allocated(sk); /* If the system goes into memory pressure with this * precharge, give up and return error. */ @@ -1028,9 +1029,9 @@ static int sock_reserve_memory(struct sock *sk, int bytes) mem_cgroup_uncharge_skmem(sk->sk_memcg, pages); return -ENOMEM; } - sk->sk_forward_alloc += pages << SK_MEM_QUANTUM_SHIFT; + sk->sk_forward_alloc += pages << PAGE_SHIFT; - sk->sk_reserved_mem += pages << SK_MEM_QUANTUM_SHIFT; + sk->sk_reserved_mem += pages << PAGE_SHIFT; return 0; } @@ -2844,7 +2845,7 @@ void __release_sock(struct sock *sk) do { next = skb->next; prefetch(next); - WARN_ON_ONCE(skb_dst_is_noref(skb)); + DEBUG_NET_WARN_ON_ONCE(skb_dst_is_noref(skb)); skb_mark_not_on_list(skb); sk_backlog_rcv(sk, skb); @@ -2906,11 +2907,13 @@ EXPORT_SYMBOL(sk_wait_data); */ int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind) { - struct proto *prot = sk->sk_prot; - long allocated = sk_memory_allocated_add(sk, amt); bool memcg_charge = mem_cgroup_sockets_enabled && sk->sk_memcg; + struct proto *prot = sk->sk_prot; bool charged = true; + long allocated; + sk_memory_allocated_add(sk, amt); + allocated = sk_memory_allocated(sk); if (memcg_charge && !(charged = mem_cgroup_charge_skmem(sk->sk_memcg, amt, gfp_memcg_charge()))) @@ -2987,7 +2990,6 @@ suppress_allocation: return 0; } -EXPORT_SYMBOL(__sk_mem_raise_allocated); /** * __sk_mem_schedule - increase sk_forward_alloc and memory_allocated @@ -3003,10 +3005,10 @@ int __sk_mem_schedule(struct sock *sk, int size, int kind) { int ret, amt = sk_mem_pages(size); - sk->sk_forward_alloc += amt << SK_MEM_QUANTUM_SHIFT; + sk->sk_forward_alloc += amt << PAGE_SHIFT; ret = __sk_mem_raise_allocated(sk, size, amt, kind); if (!ret) - sk->sk_forward_alloc -= amt << SK_MEM_QUANTUM_SHIFT; + sk->sk_forward_alloc -= amt << PAGE_SHIFT; return ret; } EXPORT_SYMBOL(__sk_mem_schedule); @@ -3029,17 +3031,16 @@ void __sk_mem_reduce_allocated(struct sock *sk, int amount) (sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0))) sk_leave_memory_pressure(sk); } -EXPORT_SYMBOL(__sk_mem_reduce_allocated); /** * __sk_mem_reclaim - reclaim sk_forward_alloc and memory_allocated * @sk: socket - * @amount: number of bytes (rounded down to a SK_MEM_QUANTUM multiple) + * @amount: number of bytes (rounded down to a PAGE_SIZE multiple) */ void __sk_mem_reclaim(struct sock *sk, int amount) { - amount >>= SK_MEM_QUANTUM_SHIFT; - sk->sk_forward_alloc -= amount << SK_MEM_QUANTUM_SHIFT; + amount >>= PAGE_SHIFT; + sk->sk_forward_alloc -= amount << PAGE_SHIFT; __sk_mem_reduce_allocated(sk, amount); } EXPORT_SYMBOL(__sk_mem_reclaim); @@ -3798,6 +3799,10 @@ int proto_register(struct proto *prot, int alloc_slab) pr_err("%s: missing sysctl_mem\n", prot->name); return -EINVAL; } + if (prot->memory_allocated && !prot->per_cpu_fw_alloc) { + pr_err("%s: missing per_cpu_fw_alloc\n", prot->name); + return -EINVAL; + } if (alloc_slab) { prot->slab = kmem_cache_create_usercopy(prot->name, prot->obj_size, 0, diff --git a/net/core/stream.c b/net/core/stream.c index 06b36c730ce8..ccc083cdef23 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -196,13 +196,13 @@ void sk_stream_kill_queues(struct sock *sk) __skb_queue_purge(&sk->sk_receive_queue); /* Next, the write queue. */ - WARN_ON(!skb_queue_empty(&sk->sk_write_queue)); + WARN_ON_ONCE(!skb_queue_empty(&sk->sk_write_queue)); /* Account for returned memory. */ sk_mem_reclaim_final(sk); - WARN_ON(sk->sk_wmem_queued); - WARN_ON(sk->sk_forward_alloc); + WARN_ON_ONCE(sk->sk_wmem_queued); + WARN_ON_ONCE(sk->sk_forward_alloc); /* It is _impossible_ for the backlog to contain anything * when we get here. All user references to this socket diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index dc92a67baea3..aa4f43f52499 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -149,6 +149,7 @@ static DEFINE_RWLOCK(dn_hash_lock); static struct hlist_head dn_sk_hash[DN_SK_HASH_SIZE]; static struct hlist_head dn_wild_sk; static atomic_long_t decnet_memory_allocated; +static DEFINE_PER_CPU(int, decnet_memory_per_cpu_fw_alloc); static int __dn_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen, int flags); @@ -454,7 +455,10 @@ static struct proto dn_proto = { .owner = THIS_MODULE, .enter_memory_pressure = dn_enter_memory_pressure, .memory_pressure = &dn_memory_pressure, + .memory_allocated = &decnet_memory_allocated, + .per_cpu_fw_alloc = &decnet_memory_per_cpu_fw_alloc, + .sysctl_mem = sysctl_decnet_mem, .sysctl_wmem = sysctl_decnet_wmem, .sysctl_rmem = sysctl_decnet_rmem, diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 801a5d445833..2e1ac638d135 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -935,10 +935,10 @@ static void dsa_slave_get_ethtool_stats(struct net_device *dev, s = per_cpu_ptr(dev->tstats, i); do { start = u64_stats_fetch_begin_irq(&s->syncp); - tx_packets = s->tx_packets; - tx_bytes = s->tx_bytes; - rx_packets = s->rx_packets; - rx_bytes = s->rx_bytes; + tx_packets = u64_stats_read(&s->tx_packets); + tx_bytes = u64_stats_read(&s->tx_bytes); + rx_packets = u64_stats_read(&s->rx_packets); + rx_bytes = u64_stats_read(&s->rx_bytes); } while (u64_stats_fetch_retry_irq(&s->syncp, start)); data[0] += tx_packets; data[1] += tx_bytes; diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 326e14ee05db..6a7308de192d 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -369,22 +369,9 @@ EXPORT_SYMBOL(ethtool_convert_legacy_u32_to_link_mode); bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, const unsigned long *src) { - bool retval = true; - - /* TODO: following test will soon always be true */ - if (__ETHTOOL_LINK_MODE_MASK_NBITS > 32) { - __ETHTOOL_DECLARE_LINK_MODE_MASK(ext); - - linkmode_zero(ext); - bitmap_fill(ext, 32); - bitmap_complement(ext, ext, __ETHTOOL_LINK_MODE_MASK_NBITS); - if (linkmode_intersects(ext, src)) { - /* src mask goes beyond bit 31 */ - retval = false; - } - } *legacy_u32 = src[0]; - return retval; + return find_next_bit(src, __ETHTOOL_LINK_MODE_MASK_NBITS, 32) == + __ETHTOOL_LINK_MODE_MASK_NBITS; } EXPORT_SYMBOL(ethtool_convert_link_mode_to_legacy_u32); @@ -2010,7 +1997,7 @@ static int ethtool_phys_id(struct net_device *dev, void __user *useraddr) * removal of the device. */ busy = true; - dev_hold_track(dev, &dev_tracker, GFP_KERNEL); + netdev_hold(dev, &dev_tracker, GFP_KERNEL); rtnl_unlock(); if (rc == 0) { @@ -2034,7 +2021,7 @@ static int ethtool_phys_id(struct net_device *dev, void __user *useraddr) } rtnl_lock(); - dev_put_track(dev, &dev_tracker); + netdev_put(dev, &dev_tracker); busy = false; (void) ops->set_phys_id(dev, ETHTOOL_ID_INACTIVE); diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index 5fe8f4ae2ceb..e26079e11835 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -402,7 +402,7 @@ static int ethnl_default_doit(struct sk_buff *skb, struct genl_info *info) ops->cleanup_data(reply_data); genlmsg_end(rskb, reply_payload); - dev_put_track(req_info->dev, &req_info->dev_tracker); + netdev_put(req_info->dev, &req_info->dev_tracker); kfree(reply_data); kfree(req_info); return genlmsg_reply(rskb, info); @@ -414,7 +414,7 @@ err_cleanup: if (ops->cleanup_data) ops->cleanup_data(reply_data); err_dev: - dev_put_track(req_info->dev, &req_info->dev_tracker); + netdev_put(req_info->dev, &req_info->dev_tracker); kfree(reply_data); kfree(req_info); return ret; @@ -550,7 +550,7 @@ static int ethnl_default_start(struct netlink_callback *cb) * same parser as for non-dump (doit) requests is used, it * would take reference to the device if it finds one */ - dev_put_track(req_info->dev, &req_info->dev_tracker); + netdev_put(req_info->dev, &req_info->dev_tracker); req_info->dev = NULL; } if (ret < 0) diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 7919ddb2371c..c0d587611854 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -237,7 +237,7 @@ struct ethnl_req_info { static inline void ethnl_parse_header_dev_put(struct ethnl_req_info *req_info) { - dev_put_track(req_info->dev, &req_info->dev_tracker); + netdev_put(req_info->dev, &req_info->dev_tracker); } /** diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 93da9f783bec..30e0e8992085 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -148,10 +148,10 @@ void inet_sock_destruct(struct sock *sk) return; } - WARN_ON(atomic_read(&sk->sk_rmem_alloc)); - WARN_ON(refcount_read(&sk->sk_wmem_alloc)); - WARN_ON(sk->sk_wmem_queued); - WARN_ON(sk_forward_alloc_get(sk)); + WARN_ON_ONCE(atomic_read(&sk->sk_rmem_alloc)); + WARN_ON_ONCE(refcount_read(&sk->sk_wmem_alloc)); + WARN_ON_ONCE(sk->sk_wmem_queued); + WARN_ON_ONCE(sk_forward_alloc_get(sk)); kfree(rcu_dereference_protected(inet->inet_opt, 1)); dst_release(rcu_dereference_protected(sk->sk_dst_cache, 1)); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index b2366ad540e6..92b778e423df 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -244,7 +244,7 @@ void in_dev_finish_destroy(struct in_device *idev) #ifdef NET_REFCNT_DEBUG pr_debug("%s: %p=%s\n", __func__, idev, dev ? dev->name : "NIL"); #endif - dev_put_track(dev, &idev->dev_tracker); + netdev_put(dev, &idev->dev_tracker); if (!idev->dead) pr_err("Freeing alive in_device %p\n", idev); else @@ -272,7 +272,7 @@ static struct in_device *inetdev_init(struct net_device *dev) if (IPV4_DEVCONF(in_dev->cnf, FORWARDING)) dev_disable_lro(dev); /* Reference in_dev->dev */ - dev_hold_track(dev, &in_dev->dev_tracker, GFP_KERNEL); + netdev_hold(dev, &in_dev->dev_tracker, GFP_KERNEL); /* Account for reference dev->ip_ptr (below) */ refcount_set(&in_dev->refcnt, 1); diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index a57ba23571c9..a5439a8414d4 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -211,7 +211,7 @@ static void rt_fibinfo_free_cpus(struct rtable __rcu * __percpu *rtp) void fib_nh_common_release(struct fib_nh_common *nhc) { - dev_put_track(nhc->nhc_dev, &nhc->nhc_dev_tracker); + netdev_put(nhc->nhc_dev, &nhc->nhc_dev_tracker); lwtstate_put(nhc->nhc_lwtstate); rt_fibinfo_free_cpus(nhc->nhc_pcpu_rth_output); rt_fibinfo_free(&nhc->nhc_rth_input); @@ -1057,7 +1057,8 @@ static int fib_check_nh_v6_gw(struct net *net, struct fib_nh *nh, err = ipv6_stub->fib6_nh_init(net, &fib6_nh, &cfg, GFP_KERNEL, extack); if (!err) { nh->fib_nh_dev = fib6_nh.fib_nh_dev; - dev_hold_track(nh->fib_nh_dev, &nh->fib_nh_dev_tracker, GFP_KERNEL); + netdev_hold(nh->fib_nh_dev, &nh->fib_nh_dev_tracker, + GFP_KERNEL); nh->fib_nh_oif = nh->fib_nh_dev->ifindex; nh->fib_nh_scope = RT_SCOPE_LINK; @@ -1141,7 +1142,7 @@ static int fib_check_nh_v4_gw(struct net *net, struct fib_nh *nh, u32 table, if (!netif_carrier_ok(dev)) nh->fib_nh_flags |= RTNH_F_LINKDOWN; nh->fib_nh_dev = dev; - dev_hold_track(dev, &nh->fib_nh_dev_tracker, GFP_ATOMIC); + netdev_hold(dev, &nh->fib_nh_dev_tracker, GFP_ATOMIC); nh->fib_nh_scope = RT_SCOPE_LINK; return 0; } @@ -1195,7 +1196,7 @@ static int fib_check_nh_v4_gw(struct net *net, struct fib_nh *nh, u32 table, "No egress device for nexthop gateway"); goto out; } - dev_hold_track(dev, &nh->fib_nh_dev_tracker, GFP_ATOMIC); + netdev_hold(dev, &nh->fib_nh_dev_tracker, GFP_ATOMIC); if (!netif_carrier_ok(dev)) nh->fib_nh_flags |= RTNH_F_LINKDOWN; err = (dev->flags & IFF_UP) ? 0 : -ENETDOWN; @@ -1229,7 +1230,7 @@ static int fib_check_nh_nongw(struct net *net, struct fib_nh *nh, } nh->fib_nh_dev = in_dev->dev; - dev_hold_track(nh->fib_nh_dev, &nh->fib_nh_dev_tracker, GFP_ATOMIC); + netdev_hold(nh->fib_nh_dev, &nh->fib_nh_dev_tracker, GFP_ATOMIC); nh->fib_nh_scope = RT_SCOPE_HOST; if (!netif_carrier_ok(nh->fib_nh_dev)) nh->fib_nh_flags |= RTNH_F_LINKDOWN; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 13e6329784fb..8324e541d193 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -691,7 +691,7 @@ static int vif_delete(struct mr_table *mrt, int vifi, int notify, if (v->flags & (VIFF_TUNNEL | VIFF_REGISTER) && !notify) unregister_netdevice_queue(dev, head); - dev_put_track(dev, &v->dev_tracker); + netdev_put(dev, &v->dev_tracker); return 0; } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 356f535f3443..2d16bcc7d346 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1550,9 +1550,8 @@ void rt_flush_dev(struct net_device *dev) if (rt->dst.dev != dev) continue; rt->dst.dev = blackhole_netdev; - dev_replace_track(dev, blackhole_netdev, - &rt->dst.dev_tracker, - GFP_ATOMIC); + netdev_ref_replace(dev, blackhole_netdev, + &rt->dst.dev_tracker, GFP_ATOMIC); list_move(&rt->rt_uncached, &ul->quarantine); } spin_unlock_bh(&ul->lock); @@ -2851,7 +2850,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or new->output = dst_discard_out; new->dev = net->loopback_dev; - dev_hold_track(new->dev, &new->dev_tracker, GFP_ATOMIC); + netdev_hold(new->dev, &new->dev_tracker, GFP_ATOMIC); rt->rt_is_input = ort->rt_is_input; rt->rt_iif = ort->rt_iif; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 028513d3e2a2..0db0ec6b0a96 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -294,6 +294,8 @@ EXPORT_SYMBOL(sysctl_tcp_mem); atomic_long_t tcp_memory_allocated ____cacheline_aligned_in_smp; /* Current allocated memory. */ EXPORT_SYMBOL(tcp_memory_allocated); +DEFINE_PER_CPU(int, tcp_memory_per_cpu_fw_alloc); +EXPORT_PER_CPU_SYMBOL_GPL(tcp_memory_per_cpu_fw_alloc); #if IS_ENABLED(CONFIG_SMC) DEFINE_STATIC_KEY_FALSE(tcp_have_smc); @@ -856,9 +858,6 @@ struct sk_buff *tcp_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp, { struct sk_buff *skb; - if (unlikely(tcp_under_memory_pressure(sk))) - sk_mem_reclaim_partial(sk); - skb = alloc_skb_fclone(size + MAX_TCP_HEADER, gfp); if (likely(skb)) { bool mem_scheduled; @@ -2762,8 +2761,6 @@ void __tcp_close(struct sock *sk, long timeout) __kfree_skb(skb); } - sk_mem_reclaim(sk); - /* If socket has been already reset (e.g. in tcp_reset()) - kill it. */ if (sk->sk_state == TCP_CLOSE) goto adjudge_to_death; @@ -2871,7 +2868,6 @@ adjudge_to_death: } } if (sk->sk_state != TCP_CLOSE) { - sk_mem_reclaim(sk); if (tcp_check_oom(sk, 0)) { tcp_set_state(sk, TCP_CLOSE); tcp_send_active_reset(sk, GFP_ATOMIC); @@ -2949,7 +2945,6 @@ void tcp_write_queue_purge(struct sock *sk) } tcp_rtx_queue_purge(sk); INIT_LIST_HEAD(&tcp_sk(sk)->tsorted_sent_queue); - sk_mem_reclaim(sk); tcp_clear_all_retrans_hints(tcp_sk(sk)); tcp_sk(sk)->packets_out = 0; inet_csk(sk)->icsk_backoff = 0; @@ -4651,11 +4646,11 @@ void __init tcp_init(void) max_wshare = min(4UL*1024*1024, limit); max_rshare = min(6UL*1024*1024, limit); - init_net.ipv4.sysctl_tcp_wmem[0] = SK_MEM_QUANTUM; + init_net.ipv4.sysctl_tcp_wmem[0] = PAGE_SIZE; init_net.ipv4.sysctl_tcp_wmem[1] = 16*1024; init_net.ipv4.sysctl_tcp_wmem[2] = max(64*1024, max_wshare); - init_net.ipv4.sysctl_tcp_rmem[0] = SK_MEM_QUANTUM; + init_net.ipv4.sysctl_tcp_rmem[0] = PAGE_SIZE; init_net.ipv4.sysctl_tcp_rmem[1] = 131072; init_net.ipv4.sysctl_tcp_rmem[2] = max(131072, max_rshare); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 2e2a9ece9af2..fdc7beb81b68 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -805,7 +805,6 @@ static void tcp_event_data_recv(struct sock *sk, struct sk_buff *skb) * restart window, so that we send ACKs quickly. */ tcp_incr_quickack(sk, TCP_MAX_QUICKACKS); - sk_mem_reclaim(sk); } } icsk->icsk_ack.lrcvtime = now; @@ -4390,7 +4389,6 @@ void tcp_fin(struct sock *sk) skb_rbtree_purge(&tp->out_of_order_queue); if (tcp_is_sack(tp)) tcp_sack_reset(&tp->rx_opt); - sk_mem_reclaim(sk); if (!sock_flag(sk, SOCK_DEAD)) { sk->sk_state_change(sk); @@ -5287,7 +5285,7 @@ new_range: before(TCP_SKB_CB(skb)->end_seq, start)) { /* Do not attempt collapsing tiny skbs */ if (range_truesize != head->truesize || - end - start >= SKB_WITH_OVERHEAD(SK_MEM_QUANTUM)) { + end - start >= SKB_WITH_OVERHEAD(PAGE_SIZE)) { tcp_collapse(sk, NULL, &tp->out_of_order_queue, head, skb, start, end); } else { @@ -5336,7 +5334,6 @@ static bool tcp_prune_ofo_queue(struct sock *sk) tcp_drop_reason(sk, rb_to_skb(node), SKB_DROP_REASON_TCP_OFO_QUEUE_PRUNE); if (!prev || goal <= 0) { - sk_mem_reclaim(sk); if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf && !tcp_under_memory_pressure(sk)) break; @@ -5383,7 +5380,6 @@ static int tcp_prune_queue(struct sock *sk) skb_peek(&sk->sk_receive_queue), NULL, tp->copied_seq, tp->rcv_nxt); - sk_mem_reclaim(sk); if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf) return 0; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index fe8f23b95d32..fda811a5251f 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -3045,7 +3045,10 @@ struct proto tcp_prot = { .stream_memory_free = tcp_stream_memory_free, .sockets_allocated = &tcp_sockets_allocated, .orphan_count = &tcp_orphan_count, + .memory_allocated = &tcp_memory_allocated, + .per_cpu_fw_alloc = &tcp_memory_per_cpu_fw_alloc, + .memory_pressure = &tcp_memory_pressure, .sysctl_mem = sysctl_tcp_mem, .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_tcp_wmem), diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 1c054431e358..8ab98e1aca67 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3367,7 +3367,7 @@ void sk_forced_mem_schedule(struct sock *sk, int size) if (size <= sk->sk_forward_alloc) return; amt = sk_mem_pages(size); - sk->sk_forward_alloc += amt * SK_MEM_QUANTUM; + sk->sk_forward_alloc += amt << PAGE_SHIFT; sk_memory_allocated_add(sk, amt); if (mem_cgroup_sockets_enabled && sk->sk_memcg) diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 20cf4a98c69d..2208755e8efc 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -290,15 +290,13 @@ void tcp_delack_timer_handler(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); - sk_mem_reclaim_partial(sk); - if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) || !(icsk->icsk_ack.pending & ICSK_ACK_TIMER)) - goto out; + return; if (time_after(icsk->icsk_ack.timeout, jiffies)) { sk_reset_timer(sk, &icsk->icsk_delack_timer, icsk->icsk_ack.timeout); - goto out; + return; } icsk->icsk_ack.pending &= ~ICSK_ACK_TIMER; @@ -317,10 +315,6 @@ void tcp_delack_timer_handler(struct sock *sk) tcp_send_ack(sk); __NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKS); } - -out: - if (tcp_under_memory_pressure(sk)) - sk_mem_reclaim(sk); } @@ -600,11 +594,11 @@ void tcp_write_timer_handler(struct sock *sk) if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) || !icsk->icsk_pending) - goto out; + return; if (time_after(icsk->icsk_timeout, jiffies)) { sk_reset_timer(sk, &icsk->icsk_retransmit_timer, icsk->icsk_timeout); - goto out; + return; } tcp_mstamp_refresh(tcp_sk(sk)); @@ -626,9 +620,6 @@ void tcp_write_timer_handler(struct sock *sk) tcp_probe_timer(sk); break; } - -out: - sk_mem_reclaim(sk); } static void tcp_write_timer(struct timer_list *t) @@ -743,8 +734,6 @@ static void tcp_keepalive_timer (struct timer_list *t) elapsed = keepalive_time_when(tp) - elapsed; } - sk_mem_reclaim(sk); - resched: inet_csk_reset_keepalive_timer (sk, elapsed); goto out; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index aa9f2ec3dc46..6172b4750a88 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -125,6 +125,8 @@ EXPORT_SYMBOL(sysctl_udp_mem); atomic_long_t udp_memory_allocated ____cacheline_aligned_in_smp; EXPORT_SYMBOL(udp_memory_allocated); +DEFINE_PER_CPU(int, udp_memory_per_cpu_fw_alloc); +EXPORT_PER_CPU_SYMBOL_GPL(udp_memory_per_cpu_fw_alloc); #define MAX_UDP_PORTS 65536 #define PORTS_PER_CHAIN (MAX_UDP_PORTS / UDP_HTABLE_SIZE_MIN) @@ -1461,11 +1463,11 @@ static void udp_rmem_release(struct sock *sk, int size, int partial, sk->sk_forward_alloc += size; - amt = (sk->sk_forward_alloc - partial) & ~(SK_MEM_QUANTUM - 1); + amt = (sk->sk_forward_alloc - partial) & ~(PAGE_SIZE - 1); sk->sk_forward_alloc -= amt; if (amt) - __sk_mem_reduce_allocated(sk, amt >> SK_MEM_QUANTUM_SHIFT); + __sk_mem_reduce_allocated(sk, amt >> PAGE_SHIFT); atomic_sub(size, &sk->sk_rmem_alloc); @@ -1558,7 +1560,7 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb) spin_lock(&list->lock); if (size >= sk->sk_forward_alloc) { amt = sk_mem_pages(size); - delta = amt << SK_MEM_QUANTUM_SHIFT; + delta = amt << PAGE_SHIFT; if (!__sk_mem_raise_allocated(sk, delta, amt, SK_MEM_RECV)) { err = -ENOBUFS; spin_unlock(&list->lock); @@ -2946,6 +2948,8 @@ struct proto udp_prot = { .psock_update_sk_prot = udp_bpf_update_proto, #endif .memory_allocated = &udp_memory_allocated, + .per_cpu_fw_alloc = &udp_memory_per_cpu_fw_alloc, + .sysctl_mem = sysctl_udp_mem, .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_udp_wmem_min), .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_udp_rmem_min), @@ -3263,8 +3267,8 @@ EXPORT_SYMBOL(udp_flow_hashrnd); static void __udp_sysctl_init(struct net *net) { - net->ipv4.sysctl_udp_rmem_min = SK_MEM_QUANTUM; - net->ipv4.sysctl_udp_wmem_min = SK_MEM_QUANTUM; + net->ipv4.sysctl_udp_rmem_min = PAGE_SIZE; + net->ipv4.sysctl_udp_wmem_min = PAGE_SIZE; #ifdef CONFIG_NET_L3_MASTER_DEV net->ipv4.sysctl_udp_l3mdev_accept = 0; diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c index cd1cd68adeec..6e08a76ae1e7 100644 --- a/net/ipv4/udplite.c +++ b/net/ipv4/udplite.c @@ -51,7 +51,10 @@ struct proto udplite_prot = { .unhash = udp_lib_unhash, .rehash = udp_v4_rehash, .get_port = udp_v4_get_port, + .memory_allocated = &udp_memory_allocated, + .per_cpu_fw_alloc = &udp_memory_per_cpu_fw_alloc, + .sysctl_mem = sysctl_udp_mem, .obj_size = sizeof(struct udp_sock), .h.udp_table = &udplite_table, diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 6fde0b184791..3d0dfa6cf9f9 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -75,7 +75,7 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, xdst->u.rt.rt_iif = fl4->flowi4_iif; xdst->u.dst.dev = dev; - dev_hold_track(dev, &xdst->u.dst.dev_tracker, GFP_ATOMIC); + netdev_hold(dev, &xdst->u.dst.dev_tracker, GFP_ATOMIC); /* Sheit... I remember I did this right. Apparently, * it was magically lost, so this code needs audit */ diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 1b1932502e9e..3497ad1362c0 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -398,13 +398,13 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev) if (ndev->cnf.forwarding) dev_disable_lro(dev); /* We refer to the device */ - dev_hold_track(dev, &ndev->dev_tracker, GFP_KERNEL); + netdev_hold(dev, &ndev->dev_tracker, GFP_KERNEL); if (snmp6_alloc_dev(ndev) < 0) { netdev_dbg(dev, "%s: cannot allocate memory for statistics\n", __func__); neigh_parms_release(&nd_tbl, ndev->nd_parms); - dev_put_track(dev, &ndev->dev_tracker); + netdev_put(dev, &ndev->dev_tracker); kfree(ndev); return ERR_PTR(err); } diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c index 881d1477d24a..507a8353a6bd 100644 --- a/net/ipv6/addrconf_core.c +++ b/net/ipv6/addrconf_core.c @@ -263,7 +263,7 @@ void in6_dev_finish_destroy(struct inet6_dev *idev) #ifdef NET_REFCNT_DEBUG pr_debug("%s: %s\n", __func__, dev ? dev->name : "NIL"); #endif - dev_put_track(dev, &idev->dev_tracker); + netdev_put(dev, &idev->dev_tracker); if (!idev->dead) { pr_warn("Freeing alive inet6 device %p\n", idev); return; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 4e37f7c29900..3e22cbe5966a 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -398,7 +398,7 @@ static void ip6erspan_tunnel_uninit(struct net_device *dev) ip6erspan_tunnel_unlink_md(ign, t); ip6gre_tunnel_unlink(ign, t); dst_cache_reset(&t->dst_cache); - dev_put_track(dev, &t->dev_tracker); + netdev_put(dev, &t->dev_tracker); } static void ip6gre_tunnel_uninit(struct net_device *dev) @@ -411,7 +411,7 @@ static void ip6gre_tunnel_uninit(struct net_device *dev) if (ign->fb_tunnel_dev == dev) WRITE_ONCE(ign->fb_tunnel_dev, NULL); dst_cache_reset(&t->dst_cache); - dev_put_track(dev, &t->dev_tracker); + netdev_put(dev, &t->dev_tracker); } @@ -1495,7 +1495,7 @@ static int ip6gre_tunnel_init_common(struct net_device *dev) } ip6gre_tnl_init_features(dev); - dev_hold_track(dev, &tunnel->dev_tracker, GFP_KERNEL); + netdev_hold(dev, &tunnel->dev_tracker, GFP_KERNEL); return 0; cleanup_dst_cache_init: @@ -1887,7 +1887,7 @@ static int ip6erspan_tap_init(struct net_device *dev) dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; ip6erspan_tnl_link_config(tunnel, 1); - dev_hold_track(dev, &tunnel->dev_tracker, GFP_KERNEL); + netdev_hold(dev, &tunnel->dev_tracker, GFP_KERNEL); return 0; cleanup_dst_cache_init: diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 19325b7600bb..c7279f205817 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -381,7 +381,7 @@ ip6_tnl_dev_uninit(struct net_device *dev) else ip6_tnl_unlink(ip6n, t); dst_cache_reset(&t->dst_cache); - dev_put_track(dev, &t->dev_tracker); + netdev_put(dev, &t->dev_tracker); } /** @@ -796,7 +796,6 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb, struct sk_buff *skb), bool log_ecn_err) { - struct pcpu_sw_netstats *tstats; const struct ipv6hdr *ipv6h = ipv6_hdr(skb); int err; @@ -856,11 +855,7 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb, } } - tstats = this_cpu_ptr(tunnel->dev->tstats); - u64_stats_update_begin(&tstats->syncp); - tstats->rx_packets++; - tstats->rx_bytes += skb->len; - u64_stats_update_end(&tstats->syncp); + dev_sw_netstats_rx_add(tunnel->dev, skb->len); skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(tunnel->dev))); @@ -1889,7 +1884,7 @@ ip6_tnl_dev_init_gen(struct net_device *dev) dev->min_mtu = ETH_MIN_MTU; dev->max_mtu = IP6_MAX_MTU - dev->hard_header_len; - dev_hold_track(dev, &t->dev_tracker, GFP_KERNEL); + netdev_hold(dev, &t->dev_tracker, GFP_KERNEL); return 0; destroy_dst: diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 3a434d75925c..8fe59a79e800 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -293,7 +293,7 @@ static void vti6_dev_uninit(struct net_device *dev) RCU_INIT_POINTER(ip6n->tnls_wc[0], NULL); else vti6_tnl_unlink(ip6n, t); - dev_put_track(dev, &t->dev_tracker); + netdev_put(dev, &t->dev_tracker); } static int vti6_input_proto(struct sk_buff *skb, int nexthdr, __be32 spi, @@ -936,7 +936,7 @@ static inline int vti6_dev_init_gen(struct net_device *dev) dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; - dev_hold_track(dev, &t->dev_tracker, GFP_KERNEL); + netdev_hold(dev, &t->dev_tracker, GFP_KERNEL); return 0; } diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 4e74bc61a3db..d4aad41c9849 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -741,7 +741,7 @@ static int mif6_delete(struct mr_table *mrt, int vifi, int notify, if ((v->flags & MIFF_REGISTER) && !notify) unregister_netdevice_queue(dev, head); - dev_put_track(dev, &v->dev_tracker); + netdev_put(dev, &v->dev_tracker); return 0; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index d25dc83bac62..0be01a4d48c1 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -182,9 +182,9 @@ static void rt6_uncached_list_flush_dev(struct net_device *dev) if (rt_dev == dev) { rt->dst.dev = blackhole_netdev; - dev_replace_track(rt_dev, blackhole_netdev, - &rt->dst.dev_tracker, - GFP_ATOMIC); + netdev_ref_replace(rt_dev, blackhole_netdev, + &rt->dst.dev_tracker, + GFP_ATOMIC); handled = true; } if (handled) @@ -607,7 +607,7 @@ static void rt6_probe_deferred(struct work_struct *w) addrconf_addr_solict_mult(&work->target, &mcaddr); ndisc_send_ns(work->dev, &work->target, &mcaddr, NULL, 0); - dev_put_track(work->dev, &work->dev_tracker); + netdev_put(work->dev, &work->dev_tracker); kfree(work); } @@ -661,7 +661,7 @@ static void rt6_probe(struct fib6_nh *fib6_nh) } else { INIT_WORK(&work->work, rt6_probe_deferred); work->target = *nh_gw; - dev_hold_track(dev, &work->dev_tracker, GFP_ATOMIC); + netdev_hold(dev, &work->dev_tracker, GFP_ATOMIC); work->dev = dev; schedule_work(&work->work); } diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index c0b138c20992..fab89fd978f0 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -521,7 +521,7 @@ static void ipip6_tunnel_uninit(struct net_device *dev) ipip6_tunnel_del_prl(tunnel, NULL); } dst_cache_reset(&tunnel->dst_cache); - dev_put_track(dev, &tunnel->dev_tracker); + netdev_put(dev, &tunnel->dev_tracker); } static int ipip6_err(struct sk_buff *skb, u32 info) @@ -686,8 +686,6 @@ static int ipip6_rcv(struct sk_buff *skb) tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, iph->saddr, iph->daddr, sifindex); if (tunnel) { - struct pcpu_sw_netstats *tstats; - if (tunnel->parms.iph.protocol != IPPROTO_IPV6 && tunnel->parms.iph.protocol != 0) goto out; @@ -724,11 +722,7 @@ static int ipip6_rcv(struct sk_buff *skb) } } - tstats = this_cpu_ptr(tunnel->dev->tstats); - u64_stats_update_begin(&tstats->syncp); - tstats->rx_packets++; - tstats->rx_bytes += skb->len; - u64_stats_update_end(&tstats->syncp); + dev_sw_netstats_rx_add(tunnel->dev, skb->len); netif_rx(skb); @@ -1463,7 +1457,7 @@ static int ipip6_tunnel_init(struct net_device *dev) dev->tstats = NULL; return err; } - dev_hold_track(dev, &tunnel->dev_tracker, GFP_KERNEL); + netdev_hold(dev, &tunnel->dev_tracker, GFP_KERNEL); return 0; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index f37dd4aa91c6..c72448ba6dc9 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -2159,7 +2159,10 @@ struct proto tcpv6_prot = { .leave_memory_pressure = tcp_leave_memory_pressure, .stream_memory_free = tcp_stream_memory_free, .sockets_allocated = &tcp_sockets_allocated, + .memory_allocated = &tcp_memory_allocated, + .per_cpu_fw_alloc = &tcp_memory_per_cpu_fw_alloc, + .memory_pressure = &tcp_memory_pressure, .orphan_count = &tcp_orphan_count, .sysctl_mem = sysctl_tcp_mem, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 55afd7f39c04..be074f07073a 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1740,7 +1740,10 @@ struct proto udpv6_prot = { #ifdef CONFIG_BPF_SYSCALL .psock_update_sk_prot = udp_bpf_update_proto, #endif + .memory_allocated = &udp_memory_allocated, + .per_cpu_fw_alloc = &udp_memory_per_cpu_fw_alloc, + .sysctl_mem = sysctl_udp_mem, .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_udp_wmem_min), .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_udp_rmem_min), diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c index fbb700d3f437..b70725856259 100644 --- a/net/ipv6/udplite.c +++ b/net/ipv6/udplite.c @@ -48,7 +48,10 @@ struct proto udplitev6_prot = { .unhash = udp_lib_unhash, .rehash = udp_v6_rehash, .get_port = udp_v6_get_port, + .memory_allocated = &udp_memory_allocated, + .per_cpu_fw_alloc = &udp_memory_per_cpu_fw_alloc, + .sysctl_mem = sysctl_udp_mem, .obj_size = sizeof(struct udp6_sock), .h.udp_table = &udplite_table, diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index e64e427a51cf..4a4b0e49ec92 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -73,11 +73,11 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, struct rt6_info *rt = (struct rt6_info *)xdst->route; xdst->u.dst.dev = dev; - dev_hold_track(dev, &xdst->u.dst.dev_tracker, GFP_ATOMIC); + netdev_hold(dev, &xdst->u.dst.dev_tracker, GFP_ATOMIC); xdst->u.rt6.rt6i_idev = in6_dev_get(dev); if (!xdst->u.rt6.rt6i_idev) { - dev_put_track(dev, &xdst->u.dst.dev_tracker); + netdev_put(dev, &xdst->u.dst.dev_tracker); return -ENODEV; } diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index a0385ddbffcf..498a0c35b7bb 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -278,8 +278,6 @@ static void iucv_sock_destruct(struct sock *sk) skb_queue_purge(&sk->sk_receive_queue); skb_queue_purge(&sk->sk_error_queue); - sk_mem_reclaim(sk); - if (!sock_flag(sk, SOCK_DEAD)) { pr_err("Attempt to release alive iucv socket %p\n", sk); return; diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 7f555d2e5357..da7fe94bea2e 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -224,7 +224,7 @@ static int llc_ui_release(struct socket *sock) } else { release_sock(sk); } - dev_put_track(llc->dev, &llc->dev_tracker); + netdev_put(llc->dev, &llc->dev_tracker); sock_put(sk); llc_sk_free(sk); out: diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index f7896f257e1b..881efbfb96f6 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -5,7 +5,7 @@ * Copyright 2006-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2015 Intel Mobile Communications GmbH * Copyright (C) 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018-2021 Intel Corporation + * Copyright (C) 2018-2022 Intel Corporation */ #include <linux/ieee80211.h> @@ -438,7 +438,6 @@ static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev, struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; struct sta_info *sta = NULL; - const struct ieee80211_cipher_scheme *cs = NULL; struct ieee80211_key *key; int err; @@ -456,23 +455,12 @@ static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev, if (WARN_ON_ONCE(fips_enabled)) return -EINVAL; break; - case WLAN_CIPHER_SUITE_CCMP: - case WLAN_CIPHER_SUITE_CCMP_256: - case WLAN_CIPHER_SUITE_AES_CMAC: - case WLAN_CIPHER_SUITE_BIP_CMAC_256: - case WLAN_CIPHER_SUITE_BIP_GMAC_128: - case WLAN_CIPHER_SUITE_BIP_GMAC_256: - case WLAN_CIPHER_SUITE_GCMP: - case WLAN_CIPHER_SUITE_GCMP_256: - break; default: - cs = ieee80211_cs_get(local, params->cipher, sdata->vif.type); break; } key = ieee80211_key_alloc(params->cipher, key_idx, params->key_len, - params->key, params->seq_len, params->seq, - cs); + params->key, params->seq_len, params->seq); if (IS_ERR(key)) return PTR_ERR(key); @@ -537,9 +525,6 @@ static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev, break; } - if (sta) - sta->cipher_scheme = cs; - err = ieee80211_key_link(key, sdata, sta); out_unlock: @@ -548,33 +533,53 @@ static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev, return err; } +static struct ieee80211_key * +ieee80211_lookup_key(struct ieee80211_sub_if_data *sdata, + u8 key_idx, bool pairwise, const u8 *mac_addr) +{ + struct ieee80211_local *local = sdata->local; + struct sta_info *sta; + + if (mac_addr) { + sta = sta_info_get_bss(sdata, mac_addr); + if (!sta) + return NULL; + + if (pairwise && key_idx < NUM_DEFAULT_KEYS) + return rcu_dereference_check_key_mtx(local, + sta->ptk[key_idx]); + + if (!pairwise && + key_idx < NUM_DEFAULT_KEYS + + NUM_DEFAULT_MGMT_KEYS + + NUM_DEFAULT_BEACON_KEYS) + return rcu_dereference_check_key_mtx(local, + sta->deflink.gtk[key_idx]); + + return NULL; + } + + if (key_idx < NUM_DEFAULT_KEYS + + NUM_DEFAULT_MGMT_KEYS + + NUM_DEFAULT_BEACON_KEYS) + return rcu_dereference_check_key_mtx(local, + sdata->keys[key_idx]); + + return NULL; +} + static int ieee80211_del_key(struct wiphy *wiphy, struct net_device *dev, u8 key_idx, bool pairwise, const u8 *mac_addr) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; - struct sta_info *sta; - struct ieee80211_key *key = NULL; + struct ieee80211_key *key; int ret; mutex_lock(&local->sta_mtx); mutex_lock(&local->key_mtx); - if (mac_addr) { - ret = -ENOENT; - - sta = sta_info_get_bss(sdata, mac_addr); - if (!sta) - goto out_unlock; - - if (pairwise) - key = key_mtx_dereference(local, sta->ptk[key_idx]); - else - key = key_mtx_dereference(local, - sta->deflink.gtk[key_idx]); - } else - key = key_mtx_dereference(local, sdata->keys[key_idx]); - + key = ieee80211_lookup_key(sdata, key_idx, pairwise, mac_addr); if (!key) { ret = -ENOENT; goto out_unlock; @@ -597,10 +602,9 @@ static int ieee80211_get_key(struct wiphy *wiphy, struct net_device *dev, struct key_params *params)) { struct ieee80211_sub_if_data *sdata; - struct sta_info *sta = NULL; u8 seq[6] = {0}; struct key_params params; - struct ieee80211_key *key = NULL; + struct ieee80211_key *key; u64 pn64; u32 iv32; u16 iv16; @@ -611,20 +615,7 @@ static int ieee80211_get_key(struct wiphy *wiphy, struct net_device *dev, rcu_read_lock(); - if (mac_addr) { - sta = sta_info_get_bss(sdata, mac_addr); - if (!sta) - goto out; - - if (pairwise && key_idx < NUM_DEFAULT_KEYS) - key = rcu_dereference(sta->ptk[key_idx]); - else if (!pairwise && - key_idx < NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS + - NUM_DEFAULT_BEACON_KEYS) - key = rcu_dereference(sta->deflink.gtk[key_idx]); - } else - key = rcu_dereference(sdata->keys[key_idx]); - + key = ieee80211_lookup_key(sdata, key_idx, pairwise, mac_addr); if (!key) goto out; @@ -1207,9 +1198,6 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, params->crypto.control_port_over_nl80211; sdata->control_port_no_preauth = params->crypto.control_port_no_preauth; - sdata->encrypt_headroom = ieee80211_cs_headroom(sdata->local, - ¶ms->crypto, - sdata->vif.type); list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) { vlan->control_port_protocol = @@ -1220,10 +1208,6 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, params->crypto.control_port_over_nl80211; vlan->control_port_no_preauth = params->crypto.control_port_no_preauth; - vlan->encrypt_headroom = - ieee80211_cs_headroom(sdata->local, - ¶ms->crypto, - vlan->vif.type); } sdata->vif.bss_conf.dtim_period = params->dtim_period; diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 86ef0a46a68c..1cf331572de1 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -5,7 +5,7 @@ * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2007-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2015 Intel Mobile Communications GmbH - * Copyright (C) 2018-2021 Intel Corporation + * Copyright (C) 2018-2022 Intel Corporation */ #ifndef IEEE80211_I_H @@ -944,7 +944,6 @@ struct ieee80211_sub_if_data { bool control_port_no_encrypt; bool control_port_no_preauth; bool control_port_over_nl80211; - int encrypt_headroom; atomic_t num_tx_queued; struct ieee80211_tx_queue_params tx_conf[IEEE80211_NUM_ACS]; @@ -2483,14 +2482,6 @@ void ieee80211_dfs_radar_detected_work(struct work_struct *work); int ieee80211_send_action_csa(struct ieee80211_sub_if_data *sdata, struct cfg80211_csa_settings *csa_settings); -bool ieee80211_cs_valid(const struct ieee80211_cipher_scheme *cs); -bool ieee80211_cs_list_valid(const struct ieee80211_cipher_scheme *cs, int n); -const struct ieee80211_cipher_scheme * -ieee80211_cs_get(struct ieee80211_local *local, u32 cipher, - enum nl80211_iftype iftype); -int ieee80211_cs_headroom(struct ieee80211_local *local, - struct cfg80211_crypto_settings *crypto, - enum nl80211_iftype iftype); void ieee80211_recalc_dtim(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata); int ieee80211_check_combinations(struct ieee80211_sub_if_data *sdata, diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 41531478437c..fb8d102fca48 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -8,7 +8,7 @@ * Copyright 2008, Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (c) 2016 Intel Deutschland GmbH - * Copyright (C) 2018-2021 Intel Corporation + * Copyright (C) 2018-2022 Intel Corporation */ #include <linux/slab.h> #include <linux/kernel.h> @@ -1036,8 +1036,6 @@ int ieee80211_add_virtual_monitor(struct ieee80211_local *local) wiphy_name(local->hw.wiphy)); sdata->wdev.iftype = NL80211_IFTYPE_MONITOR; - sdata->encrypt_headroom = IEEE80211_ENCRYPT_HEADROOM; - ieee80211_set_default_queues(sdata); ret = drv_add_interface(local, sdata); @@ -1644,7 +1642,6 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata, sdata->control_port_no_encrypt = false; sdata->control_port_over_nl80211 = false; sdata->control_port_no_preauth = false; - sdata->encrypt_headroom = IEEE80211_ENCRYPT_HEADROOM; sdata->vif.bss_conf.idle = true; sdata->vif.bss_conf.txpower = INT_MIN; /* unset */ @@ -2116,8 +2113,6 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, sdata->ap_power_level = IEEE80211_UNSET_POWER_LEVEL; sdata->user_power_level = local->user_power_level; - sdata->encrypt_headroom = IEEE80211_ENCRYPT_HEADROOM; - /* setup type-dependent data */ ieee80211_setup_sdata(sdata, type); diff --git a/net/mac80211/key.c b/net/mac80211/key.c index 0fcf8aebedc4..c3476de4b14d 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -6,7 +6,7 @@ * Copyright 2007-2008 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2015-2017 Intel Deutschland GmbH - * Copyright 2018-2020 Intel Corporation + * Copyright 2018-2020, 2022 Intel Corporation */ #include <linux/if_ether.h> @@ -531,8 +531,7 @@ static int ieee80211_key_replace(struct ieee80211_sub_if_data *sdata, struct ieee80211_key * ieee80211_key_alloc(u32 cipher, int idx, size_t key_len, const u8 *key_data, - size_t seq_len, const u8 *seq, - const struct ieee80211_cipher_scheme *cs) + size_t seq_len, const u8 *seq) { struct ieee80211_key *key; int i, j, err; @@ -675,21 +674,6 @@ ieee80211_key_alloc(u32 cipher, int idx, size_t key_len, return ERR_PTR(err); } break; - default: - if (cs) { - if (seq_len && seq_len != cs->pn_len) { - kfree(key); - return ERR_PTR(-EINVAL); - } - - key->conf.iv_len = cs->hdr_len; - key->conf.icv_len = cs->mic_len; - for (i = 0; i < IEEE80211_NUM_TIDS + 1; i++) - for (j = 0; j < seq_len; j++) - key->u.gen.rx_pn[i][j] = - seq[seq_len - j - 1]; - key->flags |= KEY_FLAG_CIPHER_SCHEME; - } } memcpy(key->conf.key, key_data, key_len); INIT_LIST_HEAD(&key->list); @@ -1294,7 +1278,7 @@ ieee80211_gtk_rekey_add(struct ieee80211_vif *vif, key = ieee80211_key_alloc(keyconf->cipher, keyconf->keyidx, keyconf->keylen, keyconf->key, - 0, NULL, NULL); + 0, NULL); if (IS_ERR(key)) return ERR_CAST(key); diff --git a/net/mac80211/key.h b/net/mac80211/key.h index 1e326c89d721..e994dcea1ce3 100644 --- a/net/mac80211/key.h +++ b/net/mac80211/key.h @@ -2,7 +2,7 @@ /* * Copyright 2002-2004, Instant802 Networks, Inc. * Copyright 2005, Devicescape Software, Inc. - * Copyright (C) 2019 Intel Corporation + * Copyright (C) 2019, 2022 Intel Corporation */ #ifndef IEEE80211_KEY_H @@ -30,12 +30,10 @@ struct sta_info; * @KEY_FLAG_UPLOADED_TO_HARDWARE: Indicates that this key is present * in the hardware for TX crypto hardware acceleration. * @KEY_FLAG_TAINTED: Key is tainted and packets should be dropped. - * @KEY_FLAG_CIPHER_SCHEME: This key is for a hardware cipher scheme */ enum ieee80211_internal_key_flags { KEY_FLAG_UPLOADED_TO_HARDWARE = BIT(0), KEY_FLAG_TAINTED = BIT(1), - KEY_FLAG_CIPHER_SCHEME = BIT(2), }; enum ieee80211_internal_tkip_state { @@ -140,8 +138,7 @@ struct ieee80211_key { struct ieee80211_key * ieee80211_key_alloc(u32 cipher, int idx, size_t key_len, const u8 *key_data, - size_t seq_len, const u8 *seq, - const struct ieee80211_cipher_scheme *cs); + size_t seq_len, const u8 *seq); /* * Insert a key into data structures (sdata, sta if necessary) * to make it used, free old key. On failure, also free the new key. @@ -166,6 +163,8 @@ void ieee80211_reenable_keys(struct ieee80211_sub_if_data *sdata); #define key_mtx_dereference(local, ref) \ rcu_dereference_protected(ref, lockdep_is_held(&((local)->key_mtx))) +#define rcu_dereference_check_key_mtx(local, ref) \ + rcu_dereference_check(ref, lockdep_is_held(&((local)->key_mtx))) void ieee80211_delayed_tailroom_dec(struct work_struct *wk); diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 5a385d4146b9..4f3e93c0819b 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -5,7 +5,7 @@ * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2017 Intel Deutschland GmbH - * Copyright (C) 2018-2021 Intel Corporation + * Copyright (C) 2018-2022 Intel Corporation */ #include <net/mac80211.h> @@ -778,7 +778,7 @@ static int ieee80211_init_cipher_suites(struct ieee80211_local *local) { bool have_wep = !fips_enabled; /* FIPS does not permit the use of RC4 */ bool have_mfp = ieee80211_hw_check(&local->hw, MFP_CAPABLE); - int n_suites = 0, r = 0, w = 0; + int r = 0, w = 0; u32 *suites; static const u32 cipher_suites[] = { /* keep WEP first, it may be removed below */ @@ -824,10 +824,9 @@ static int ieee80211_init_cipher_suites(struct ieee80211_local *local) continue; suites[w++] = suite; } - } else if (!local->hw.cipher_schemes) { - /* If the driver doesn't have cipher schemes, there's nothing - * else to do other than assign the (software supported and - * perhaps offloaded) cipher suites. + } else { + /* assign the (software supported and perhaps offloaded) + * cipher suites */ local->hw.wiphy->cipher_suites = cipher_suites; local->hw.wiphy->n_cipher_suites = ARRAY_SIZE(cipher_suites); @@ -842,58 +841,6 @@ static int ieee80211_init_cipher_suites(struct ieee80211_local *local) /* not dynamically allocated, so just return */ return 0; - } else { - const struct ieee80211_cipher_scheme *cs; - - cs = local->hw.cipher_schemes; - - /* Driver specifies cipher schemes only (but not cipher suites - * including the schemes) - * - * We start counting ciphers defined by schemes, TKIP, CCMP, - * CCMP-256, GCMP, and GCMP-256 - */ - n_suites = local->hw.n_cipher_schemes + 5; - - /* check if we have WEP40 and WEP104 */ - if (have_wep) - n_suites += 2; - - /* check if we have AES_CMAC, BIP-CMAC-256, BIP-GMAC-128, - * BIP-GMAC-256 - */ - if (have_mfp) - n_suites += 4; - - suites = kmalloc_array(n_suites, sizeof(u32), GFP_KERNEL); - if (!suites) - return -ENOMEM; - - suites[w++] = WLAN_CIPHER_SUITE_CCMP; - suites[w++] = WLAN_CIPHER_SUITE_CCMP_256; - suites[w++] = WLAN_CIPHER_SUITE_TKIP; - suites[w++] = WLAN_CIPHER_SUITE_GCMP; - suites[w++] = WLAN_CIPHER_SUITE_GCMP_256; - - if (have_wep) { - suites[w++] = WLAN_CIPHER_SUITE_WEP40; - suites[w++] = WLAN_CIPHER_SUITE_WEP104; - } - - if (have_mfp) { - suites[w++] = WLAN_CIPHER_SUITE_AES_CMAC; - suites[w++] = WLAN_CIPHER_SUITE_BIP_CMAC_256; - suites[w++] = WLAN_CIPHER_SUITE_BIP_GMAC_128; - suites[w++] = WLAN_CIPHER_SUITE_BIP_GMAC_256; - } - - for (r = 0; r < local->hw.n_cipher_schemes; r++) { - suites[w++] = cs[r].cipher; - if (WARN_ON(cs[r].pn_len > IEEE80211_MAX_PN_LEN)) { - kfree(suites); - return -EINVAL; - } - } } local->hw.wiphy->cipher_suites = suites; @@ -1168,12 +1115,6 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) if (local->hw.wiphy->max_scan_ie_len) local->hw.wiphy->max_scan_ie_len -= local->scan_ies_len; - if (WARN_ON(!ieee80211_cs_list_valid(local->hw.cipher_schemes, - local->hw.n_cipher_schemes))) { - result = -EINVAL; - goto fail_workqueue; - } - result = ieee80211_init_cipher_suites(local); if (result < 0) goto fail_workqueue; diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 58ebdcd69d05..45e7c1b307bc 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2008, 2009 open80211s Ltd. - * Copyright (C) 2019, 2021 Intel Corporation + * Copyright (C) 2019, 2021-2022 Intel Corporation * Author: Luis Carlos Cobo <luisca@cozybit.com> */ @@ -247,13 +247,13 @@ int mesh_path_error_tx(struct ieee80211_sub_if_data *sdata, return -EAGAIN; skb = dev_alloc_skb(local->tx_headroom + - sdata->encrypt_headroom + + IEEE80211_ENCRYPT_HEADROOM + IEEE80211_ENCRYPT_TAILROOM + hdr_len + 2 + 15 /* PERR IE */); if (!skb) return -1; - skb_reserve(skb, local->tx_headroom + sdata->encrypt_headroom); + skb_reserve(skb, local->tx_headroom + IEEE80211_ENCRYPT_HEADROOM); mgmt = skb_put_zero(skb, hdr_len); mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_ACTION); diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 58d48dcae030..6d5ad71ef02c 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -8,7 +8,7 @@ * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015 - 2017 Intel Deutschland GmbH - * Copyright (C) 2018 - 2021 Intel Corporation + * Copyright (C) 2018 - 2022 Intel Corporation */ #include <linux/delay.h> @@ -2496,8 +2496,6 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, memset(ifmgd->tx_tspec, 0, sizeof(ifmgd->tx_tspec)); cancel_delayed_work_sync(&ifmgd->tx_tspec_wk); - sdata->encrypt_headroom = IEEE80211_ENCRYPT_HEADROOM; - bss_conf->pwr_reduction = 0; bss_conf->tx_pwr_env_num = 0; memset(bss_conf->tx_pwr_env, 0, sizeof(bss_conf->tx_pwr_env)); @@ -6071,8 +6069,6 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, sdata->control_port_over_nl80211 = req->crypto.control_port_over_nl80211; sdata->control_port_no_preauth = req->crypto.control_port_no_preauth; - sdata->encrypt_headroom = ieee80211_cs_headroom(local, &req->crypto, - sdata->vif.type); /* kick off associate process */ diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 3c08ae04ddbc..a9f4e90ad893 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -6,7 +6,7 @@ * Copyright 2007-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright(c) 2015 - 2017 Intel Deutschland GmbH - * Copyright (C) 2018-2021 Intel Corporation + * Copyright (C) 2018-2022 Intel Corporation */ #include <linux/jiffies.h> @@ -1009,43 +1009,20 @@ static int ieee80211_get_mmie_keyidx(struct sk_buff *skb) return -1; } -static int ieee80211_get_keyid(struct sk_buff *skb, - const struct ieee80211_cipher_scheme *cs) +static int ieee80211_get_keyid(struct sk_buff *skb) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; - __le16 fc; - int hdrlen; - int minlen; - u8 key_idx_off; - u8 key_idx_shift; + __le16 fc = hdr->frame_control; + int hdrlen = ieee80211_hdrlen(fc); u8 keyid; - fc = hdr->frame_control; - hdrlen = ieee80211_hdrlen(fc); - - if (cs) { - minlen = hdrlen + cs->hdr_len; - key_idx_off = hdrlen + cs->key_idx_off; - key_idx_shift = cs->key_idx_shift; - } else { - /* WEP, TKIP, CCMP and GCMP */ - minlen = hdrlen + IEEE80211_WEP_IV_LEN; - key_idx_off = hdrlen + 3; - key_idx_shift = 6; - } - - if (unlikely(skb->len < minlen)) + /* WEP, TKIP, CCMP and GCMP */ + if (unlikely(skb->len < hdrlen + IEEE80211_WEP_IV_LEN)) return -EINVAL; - skb_copy_bits(skb, key_idx_off, &keyid, 1); + skb_copy_bits(skb, hdrlen + 3, &keyid, 1); - if (cs) - keyid &= cs->key_idx_mask; - keyid >>= key_idx_shift; - - /* cs could use more than the usual two bits for the keyid */ - if (unlikely(keyid >= NUM_DEFAULT_KEYS)) - return -EINVAL; + keyid >>= 6; return keyid; } @@ -1916,7 +1893,6 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) struct ieee80211_key *ptk_idx = NULL; int mmie_keyidx = -1; __le16 fc; - const struct ieee80211_cipher_scheme *cs = NULL; if (ieee80211_is_ext(hdr->frame_control)) return RX_CONTINUE; @@ -1959,8 +1935,7 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) if (ieee80211_has_protected(fc) && !(status->flag & RX_FLAG_IV_STRIPPED)) { - cs = rx->sta->cipher_scheme; - keyid = ieee80211_get_keyid(rx->skb, cs); + keyid = ieee80211_get_keyid(rx->skb); if (unlikely(keyid < 0)) return RX_DROP_UNUSABLE; @@ -2065,7 +2040,7 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) (status->flag & RX_FLAG_IV_STRIPPED)) return RX_CONTINUE; - keyidx = ieee80211_get_keyid(rx->skb, cs); + keyidx = ieee80211_get_keyid(rx->skb); if (unlikely(keyidx < 0)) return RX_DROP_UNUSABLE; @@ -2131,7 +2106,7 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) result = ieee80211_crypto_gcmp_decrypt(rx); break; default: - result = ieee80211_crypto_hw_decrypt(rx); + result = RX_DROP_UNUSABLE; } /* the hdr variable is invalid after the decrypt handlers */ @@ -2945,7 +2920,7 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) tailroom = IEEE80211_ENCRYPT_TAILROOM; fwd_skb = skb_copy_expand(skb, local->tx_headroom + - sdata->encrypt_headroom, + IEEE80211_ENCRYPT_HEADROOM, tailroom, GFP_ATOMIC); if (!fwd_skb) goto out; diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 35c390bedfba..aa6950aa49a9 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -3,7 +3,7 @@ * Copyright 2002-2005, Devicescape Software, Inc. * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright(c) 2015-2017 Intel Deutschland GmbH - * Copyright(c) 2020-2021 Intel Corporation + * Copyright(c) 2020-2022 Intel Corporation */ #ifndef STA_INFO_H @@ -616,7 +616,6 @@ struct link_sta_info { * taken from HT/VHT capabilities or VHT operating mode notification * @known_smps_mode: the smps_mode the client thinks we are in. Relevant for * AP only. - * @cipher_scheme: optional cipher scheme for this station * @cparams: CoDel parameters for this station. * @reserved_tid: reserved TID (if any, otherwise IEEE80211_TID_UNRESERVED) * @fast_tx: TX fastpath information @@ -700,7 +699,6 @@ struct sta_info { #endif enum ieee80211_smps_mode known_smps_mode; - const struct ieee80211_cipher_scheme *cipher_scheme; struct codel_params cparams; diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 0e4efc08c762..37fe72bb5ab0 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -5,7 +5,7 @@ * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2007 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH - * Copyright (C) 2018-2021 Intel Corporation + * Copyright (C) 2018-2022 Intel Corporation * * Transmit and frame generation functions. */ @@ -882,7 +882,7 @@ static int ieee80211_fragment(struct ieee80211_tx_data *tx, rem -= fraglen; tmp = dev_alloc_skb(local->tx_headroom + frag_threshold + - tx->sdata->encrypt_headroom + + IEEE80211_ENCRYPT_HEADROOM + IEEE80211_ENCRYPT_TAILROOM); if (!tmp) return -ENOMEM; @@ -890,7 +890,7 @@ static int ieee80211_fragment(struct ieee80211_tx_data *tx, __skb_queue_tail(&tx->skbs, tmp); skb_reserve(tmp, - local->tx_headroom + tx->sdata->encrypt_headroom); + local->tx_headroom + IEEE80211_ENCRYPT_HEADROOM); /* copy control information */ memcpy(tmp->cb, skb->cb, sizeof(tmp->cb)); @@ -1040,8 +1040,6 @@ ieee80211_tx_h_encrypt(struct ieee80211_tx_data *tx) case WLAN_CIPHER_SUITE_GCMP: case WLAN_CIPHER_SUITE_GCMP_256: return ieee80211_crypto_gcmp_encrypt(tx); - default: - return ieee80211_crypto_hw_encrypt(tx); } return TX_DROP; @@ -2013,7 +2011,7 @@ void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, headroom = local->tx_headroom; if (encrypt != ENCRYPT_NO) - headroom += sdata->encrypt_headroom; + headroom += IEEE80211_ENCRYPT_HEADROOM; headroom -= skb_headroom(skb); headroom = max_t(int, 0, headroom); @@ -2867,7 +2865,7 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata, */ if (head_need > 0 || skb_cloned(skb)) { - head_need += sdata->encrypt_headroom; + head_need += IEEE80211_ENCRYPT_HEADROOM; head_need += local->tx_headroom; head_need = max_t(int, 0, head_need); if (ieee80211_skb_resize(sdata, skb, head_need, ENCRYPT_DATA)) { @@ -3128,15 +3126,6 @@ void ieee80211_check_fast_xmit(struct sta_info *sta) /* we don't know how to generate IVs for this at all */ if (WARN_ON(gen_iv)) goto out; - /* pure hardware keys are OK, of course */ - if (!(build.key->flags & KEY_FLAG_CIPHER_SCHEME)) - break; - /* cipher scheme might require space allocation */ - if (iv_spc && - build.key->conf.iv_len > IEEE80211_FAST_XMIT_MAX_IV) - goto out; - if (iv_spc) - build.hdr_len += build.key->conf.iv_len; } fc |= cpu_to_le16(IEEE80211_FCTL_PROTECTED); diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 1e26b5235add..9e6c4dcef280 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -6,7 +6,7 @@ * Copyright 2007 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018-2021 Intel Corporation + * Copyright (C) 2018-2022 Intel Corporation * * utilities for mac80211 */ @@ -4212,74 +4212,6 @@ int ieee80211_send_action_csa(struct ieee80211_sub_if_data *sdata, return 0; } -bool ieee80211_cs_valid(const struct ieee80211_cipher_scheme *cs) -{ - return !(cs == NULL || cs->cipher == 0 || - cs->hdr_len < cs->pn_len + cs->pn_off || - cs->hdr_len <= cs->key_idx_off || - cs->key_idx_shift > 7 || - cs->key_idx_mask == 0); -} - -bool ieee80211_cs_list_valid(const struct ieee80211_cipher_scheme *cs, int n) -{ - int i; - - /* Ensure we have enough iftype bitmap space for all iftype values */ - WARN_ON((NUM_NL80211_IFTYPES / 8 + 1) > sizeof(cs[0].iftype)); - - for (i = 0; i < n; i++) - if (!ieee80211_cs_valid(&cs[i])) - return false; - - return true; -} - -const struct ieee80211_cipher_scheme * -ieee80211_cs_get(struct ieee80211_local *local, u32 cipher, - enum nl80211_iftype iftype) -{ - const struct ieee80211_cipher_scheme *l = local->hw.cipher_schemes; - int n = local->hw.n_cipher_schemes; - int i; - const struct ieee80211_cipher_scheme *cs = NULL; - - for (i = 0; i < n; i++) { - if (l[i].cipher == cipher) { - cs = &l[i]; - break; - } - } - - if (!cs || !(cs->iftype & BIT(iftype))) - return NULL; - - return cs; -} - -int ieee80211_cs_headroom(struct ieee80211_local *local, - struct cfg80211_crypto_settings *crypto, - enum nl80211_iftype iftype) -{ - const struct ieee80211_cipher_scheme *cs; - int headroom = IEEE80211_ENCRYPT_HEADROOM; - int i; - - for (i = 0; i < crypto->n_ciphers_pairwise; i++) { - cs = ieee80211_cs_get(local, crypto->ciphers_pairwise[i], - iftype); - - if (cs && headroom < cs->hdr_len) - headroom = cs->hdr_len; - } - - cs = ieee80211_cs_get(local, crypto->cipher_group, iftype); - if (cs && headroom < cs->hdr_len) - headroom = cs->hdr_len; - - return headroom; -} - static bool ieee80211_extend_noa_desc(struct ieee80211_noa_data *data, u32 tsf, int i) { diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c index 5fd8a3e8b5b4..93ec2f349748 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -3,7 +3,7 @@ * Copyright 2002-2004, Instant802 Networks, Inc. * Copyright 2008, Jouni Malinen <j@w1.fi> * Copyright (C) 2016-2017 Intel Deutschland GmbH - * Copyright (C) 2020-2021 Intel Corporation + * Copyright (C) 2020-2022 Intel Corporation */ #include <linux/netdevice.h> @@ -778,102 +778,6 @@ ieee80211_crypto_gcmp_decrypt(struct ieee80211_rx_data *rx) return RX_CONTINUE; } -static ieee80211_tx_result -ieee80211_crypto_cs_encrypt(struct ieee80211_tx_data *tx, - struct sk_buff *skb) -{ - struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; - struct ieee80211_key *key = tx->key; - struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); - int hdrlen; - u8 *pos, iv_len = key->conf.iv_len; - - if (info->control.hw_key && - !(info->control.hw_key->flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE)) { - /* hwaccel has no need for preallocated head room */ - return TX_CONTINUE; - } - - if (unlikely(skb_headroom(skb) < iv_len && - pskb_expand_head(skb, iv_len, 0, GFP_ATOMIC))) - return TX_DROP; - - hdrlen = ieee80211_hdrlen(hdr->frame_control); - - pos = skb_push(skb, iv_len); - memmove(pos, pos + iv_len, hdrlen); - - return TX_CONTINUE; -} - -static inline int ieee80211_crypto_cs_pn_compare(u8 *pn1, u8 *pn2, int len) -{ - int i; - - /* pn is little endian */ - for (i = len - 1; i >= 0; i--) { - if (pn1[i] < pn2[i]) - return -1; - else if (pn1[i] > pn2[i]) - return 1; - } - - return 0; -} - -static ieee80211_rx_result -ieee80211_crypto_cs_decrypt(struct ieee80211_rx_data *rx) -{ - struct ieee80211_key *key = rx->key; - struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)rx->skb->data; - const struct ieee80211_cipher_scheme *cs = NULL; - int hdrlen = ieee80211_hdrlen(hdr->frame_control); - struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(rx->skb); - int data_len; - u8 *rx_pn; - u8 *skb_pn; - u8 qos_tid; - - if (!rx->sta || !rx->sta->cipher_scheme || - !(status->flag & RX_FLAG_DECRYPTED)) - return RX_DROP_UNUSABLE; - - if (!ieee80211_is_data(hdr->frame_control)) - return RX_CONTINUE; - - cs = rx->sta->cipher_scheme; - - data_len = rx->skb->len - hdrlen - cs->hdr_len; - - if (data_len < 0) - return RX_DROP_UNUSABLE; - - if (ieee80211_is_data_qos(hdr->frame_control)) - qos_tid = ieee80211_get_tid(hdr); - else - qos_tid = 0; - - if (skb_linearize(rx->skb)) - return RX_DROP_UNUSABLE; - - rx_pn = key->u.gen.rx_pn[qos_tid]; - skb_pn = rx->skb->data + hdrlen + cs->pn_off; - - if (ieee80211_crypto_cs_pn_compare(skb_pn, rx_pn, cs->pn_len) <= 0) - return RX_DROP_UNUSABLE; - - memcpy(rx_pn, skb_pn, cs->pn_len); - - /* remove security header and MIC */ - if (pskb_trim(rx->skb, rx->skb->len - cs->mic_len)) - return RX_DROP_UNUSABLE; - - memmove(rx->skb->data + cs->hdr_len, rx->skb->data, hdrlen); - skb_pull(rx->skb, cs->hdr_len); - - return RX_CONTINUE; -} - static void bip_aad(struct sk_buff *skb, u8 *aad) { __le16 mask_fc; @@ -1212,38 +1116,3 @@ ieee80211_crypto_aes_gmac_decrypt(struct ieee80211_rx_data *rx) return RX_CONTINUE; } - -ieee80211_tx_result -ieee80211_crypto_hw_encrypt(struct ieee80211_tx_data *tx) -{ - struct sk_buff *skb; - struct ieee80211_tx_info *info = NULL; - ieee80211_tx_result res; - - skb_queue_walk(&tx->skbs, skb) { - info = IEEE80211_SKB_CB(skb); - - /* handle hw-only algorithm */ - if (!info->control.hw_key) - return TX_DROP; - - if (tx->key->flags & KEY_FLAG_CIPHER_SCHEME) { - res = ieee80211_crypto_cs_encrypt(tx, skb); - if (res != TX_CONTINUE) - return res; - } - } - - ieee80211_tx_set_protected(tx); - - return TX_CONTINUE; -} - -ieee80211_rx_result -ieee80211_crypto_hw_decrypt(struct ieee80211_rx_data *rx) -{ - if (rx->sta && rx->sta->cipher_scheme) - return ieee80211_crypto_cs_decrypt(rx); - - return RX_DROP_UNUSABLE; -} diff --git a/net/mac80211/wpa.h b/net/mac80211/wpa.h index af3272284e85..a9a81abb5479 100644 --- a/net/mac80211/wpa.h +++ b/net/mac80211/wpa.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright 2002-2004, Instant802 Networks, Inc. + * Copyright (C) 2022 Intel Corporation */ #ifndef WPA_H @@ -39,10 +40,6 @@ ieee80211_tx_result ieee80211_crypto_aes_gmac_encrypt(struct ieee80211_tx_data *tx); ieee80211_rx_result ieee80211_crypto_aes_gmac_decrypt(struct ieee80211_rx_data *rx); -ieee80211_tx_result -ieee80211_crypto_hw_encrypt(struct ieee80211_tx_data *tx); -ieee80211_rx_result -ieee80211_crypto_hw_decrypt(struct ieee80211_rx_data *rx); ieee80211_tx_result ieee80211_crypto_gcmp_encrypt(struct ieee80211_tx_data *tx); diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 17e13396024a..e0fb9f96c45c 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -167,8 +167,8 @@ static bool mptcp_ooo_try_coalesce(struct mptcp_sock *msk, struct sk_buff *to, static void __mptcp_rmem_reclaim(struct sock *sk, int amount) { - amount >>= SK_MEM_QUANTUM_SHIFT; - mptcp_sk(sk)->rmem_fwd_alloc -= amount << SK_MEM_QUANTUM_SHIFT; + amount >>= PAGE_SHIFT; + mptcp_sk(sk)->rmem_fwd_alloc -= amount << PAGE_SHIFT; __sk_mem_reduce_allocated(sk, amount); } @@ -327,7 +327,7 @@ static bool mptcp_rmem_schedule(struct sock *sk, struct sock *ssk, int size) return true; amt = sk_mem_pages(size); - amount = amt << SK_MEM_QUANTUM_SHIFT; + amount = amt << PAGE_SHIFT; msk->rmem_fwd_alloc += amount; if (!__sk_mem_raise_allocated(sk, size, amt, SK_MEM_RECV)) { if (ssk->sk_forward_alloc < amount) { @@ -972,10 +972,10 @@ static void __mptcp_mem_reclaim_partial(struct sock *sk) lockdep_assert_held_once(&sk->sk_lock.slock); - if (reclaimable > SK_MEM_QUANTUM) + if (reclaimable > (int)PAGE_SIZE) __mptcp_rmem_reclaim(sk, reclaimable - 1); - sk_mem_reclaim_partial(sk); + sk_mem_reclaim(sk); } static void mptcp_mem_reclaim_partial(struct sock *sk) @@ -3437,7 +3437,10 @@ static struct proto mptcp_prot = { .get_port = mptcp_get_port, .forward_alloc_get = mptcp_forward_alloc_get, .sockets_allocated = &mptcp_sockets_allocated, + .memory_allocated = &tcp_memory_allocated, + .per_cpu_fw_alloc = &tcp_memory_per_cpu_fw_alloc, + .memory_pressure = &tcp_memory_pressure, .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_tcp_wmem), .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_tcp_rmem), diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c index b498dac4e1e0..2f61d5bdce1a 100644 --- a/net/openvswitch/vport-netdev.c +++ b/net/openvswitch/vport-netdev.c @@ -115,7 +115,7 @@ error_master_upper_dev_unlink: error_unlock: rtnl_unlock(); error_put: - dev_put_track(vport->dev, &vport->dev_tracker); + netdev_put(vport->dev, &vport->dev_tracker); error_free_vport: ovs_vport_free(vport); return ERR_PTR(err); @@ -137,7 +137,7 @@ static void vport_netdev_free(struct rcu_head *rcu) { struct vport *vport = container_of(rcu, struct vport, rcu); - dev_put_track(vport->dev, &vport->dev_tracker); + netdev_put(vport->dev, &vport->dev_tracker); ovs_vport_free(vport); } @@ -173,7 +173,7 @@ void ovs_netdev_tunnel_destroy(struct vport *vport) */ if (vport->dev->reg_state == NETREG_REGISTERED) rtnl_delete_link(vport->dev); - dev_put_track(vport->dev, &vport->dev_tracker); + netdev_put(vport->dev, &vport->dev_tracker); vport->dev = NULL; rtnl_unlock(); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index ca6e92a22923..d08c4728523b 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3134,7 +3134,7 @@ static int packet_release(struct socket *sock) packet_cached_dev_reset(po); if (po->prot_hook.dev) { - dev_put_track(po->prot_hook.dev, &po->prot_hook.dev_tracker); + netdev_put(po->prot_hook.dev, &po->prot_hook.dev_tracker); po->prot_hook.dev = NULL; } spin_unlock(&po->bind_lock); @@ -3235,15 +3235,15 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex, WRITE_ONCE(po->num, proto); po->prot_hook.type = proto; - dev_put_track(po->prot_hook.dev, &po->prot_hook.dev_tracker); + netdev_put(po->prot_hook.dev, &po->prot_hook.dev_tracker); if (unlikely(unlisted)) { po->prot_hook.dev = NULL; WRITE_ONCE(po->ifindex, -1); packet_cached_dev_reset(po); } else { - dev_hold_track(dev, &po->prot_hook.dev_tracker, - GFP_ATOMIC); + netdev_hold(dev, &po->prot_hook.dev_tracker, + GFP_ATOMIC); po->prot_hook.dev = dev; WRITE_ONCE(po->ifindex, dev ? dev->ifindex : 0); packet_cached_dev_assign(po, dev); @@ -4167,8 +4167,8 @@ static int packet_notifier(struct notifier_block *this, if (msg == NETDEV_UNREGISTER) { packet_cached_dev_reset(po); WRITE_ONCE(po->ifindex, -1); - dev_put_track(po->prot_hook.dev, - &po->prot_hook.dev_tracker); + netdev_put(po->prot_hook.dev, + &po->prot_hook.dev_tracker); po->prot_hook.dev = NULL; } spin_unlock(&po->bind_lock); diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index ebb92fb072ab..a1d70cf86843 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -79,7 +79,7 @@ static void tcf_mirred_release(struct tc_action *a) /* last reference to action, no need to lock */ dev = rcu_dereference_protected(m->tcfm_dev, 1); - dev_put_track(dev, &m->tcfm_dev_tracker); + netdev_put(dev, &m->tcfm_dev_tracker); } static const struct nla_policy mirred_policy[TCA_MIRRED_MAX + 1] = { @@ -181,7 +181,7 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, mac_header_xmit = dev_is_mac_header_xmit(ndev); odev = rcu_replace_pointer(m->tcfm_dev, ndev, lockdep_is_held(&m->tcf_lock)); - dev_put_track(odev, &m->tcfm_dev_tracker); + netdev_put(odev, &m->tcfm_dev_tracker); netdev_tracker_alloc(ndev, &m->tcfm_dev_tracker, GFP_ATOMIC); m->tcfm_mac_header_xmit = mac_header_xmit; } @@ -402,7 +402,7 @@ static int mirred_device_event(struct notifier_block *unused, list_for_each_entry(m, &mirred_list, tcfm_list) { spin_lock_bh(&m->tcf_lock); if (tcf_mirred_dev_dereference(m) == dev) { - dev_put_track(dev, &m->tcfm_dev_tracker); + netdev_put(dev, &m->tcfm_dev_tracker); /* Note : no rcu grace period necessary, as * net_device are already rcu protected. */ diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index e3c0e8ea2dbb..bf87b50837a8 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1292,7 +1292,7 @@ err_out5: if (ops->destroy) ops->destroy(sch); err_out3: - dev_put_track(dev, &sch->dev_tracker); + netdev_put(dev, &sch->dev_tracker); qdisc_free(sch); err_out2: module_put(ops->owner); diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index dba0b3e24af5..cc6eabee2830 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -541,7 +541,7 @@ static void dev_watchdog(struct timer_list *t) spin_unlock(&dev->tx_global_lock); if (release) - dev_put_track(dev, &dev->watchdog_dev_tracker); + netdev_put(dev, &dev->watchdog_dev_tracker); } void __netdev_watchdog_up(struct net_device *dev) @@ -551,7 +551,8 @@ void __netdev_watchdog_up(struct net_device *dev) dev->watchdog_timeo = 5*HZ; if (!mod_timer(&dev->watchdog_timer, round_jiffies(jiffies + dev->watchdog_timeo))) - dev_hold_track(dev, &dev->watchdog_dev_tracker, GFP_ATOMIC); + netdev_hold(dev, &dev->watchdog_dev_tracker, + GFP_ATOMIC); } } EXPORT_SYMBOL_GPL(__netdev_watchdog_up); @@ -565,7 +566,7 @@ static void dev_watchdog_down(struct net_device *dev) { netif_tx_lock_bh(dev); if (del_timer(&dev->watchdog_timer)) - dev_put_track(dev, &dev->watchdog_dev_tracker); + netdev_put(dev, &dev->watchdog_dev_tracker); netif_tx_unlock_bh(dev); } @@ -975,7 +976,7 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, sch->enqueue = ops->enqueue; sch->dequeue = ops->dequeue; sch->dev_queue = dev_queue; - dev_hold_track(dev, &sch->dev_tracker, GFP_KERNEL); + netdev_hold(dev, &sch->dev_tracker, GFP_KERNEL); refcount_set(&sch->refcnt, 1); return sch; @@ -1067,7 +1068,7 @@ static void qdisc_destroy(struct Qdisc *qdisc) ops->destroy(qdisc); module_put(ops->owner); - dev_put_track(qdisc_dev(qdisc), &qdisc->dev_tracker); + netdev_put(qdisc_dev(qdisc), &qdisc->dev_tracker); trace_qdisc_destroy(qdisc); diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 35928fefae33..fa500ea3a1f1 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -1523,11 +1523,11 @@ static __init int sctp_init(void) limit = (sysctl_sctp_mem[1]) << (PAGE_SHIFT - 7); max_share = min(4UL*1024*1024, limit); - sysctl_sctp_rmem[0] = SK_MEM_QUANTUM; /* give each asoc 1 page min */ + sysctl_sctp_rmem[0] = PAGE_SIZE; /* give each asoc 1 page min */ sysctl_sctp_rmem[1] = 1500 * SKB_TRUESIZE(1); sysctl_sctp_rmem[2] = max(sysctl_sctp_rmem[1], max_share); - sysctl_sctp_wmem[0] = SK_MEM_QUANTUM; + sysctl_sctp_wmem[0] = PAGE_SIZE; sysctl_sctp_wmem[1] = 16*1024; sysctl_sctp_wmem[2] = max(64*1024, max_share); diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 52edee1322fc..f6ee7f4040c1 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -6590,8 +6590,6 @@ static int sctp_eat_data(const struct sctp_association *asoc, pr_debug("%s: under pressure, reneging for tsn:%u\n", __func__, tsn); deliver = SCTP_CMD_RENEGE; - } else { - sk_mem_reclaim(sk); } } diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 6d37d2dfb3da..171f1a35d205 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -93,6 +93,7 @@ static int sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, static unsigned long sctp_memory_pressure; static atomic_long_t sctp_memory_allocated; +static DEFINE_PER_CPU(int, sctp_memory_per_cpu_fw_alloc); struct percpu_counter sctp_sockets_allocated; static void sctp_enter_memory_pressure(struct sock *sk) @@ -1823,9 +1824,6 @@ static int sctp_sendmsg_to_asoc(struct sctp_association *asoc, if (sctp_wspace(asoc) < (int)msg_len) sctp_prsctp_prune(asoc, sinfo, msg_len - sctp_wspace(asoc)); - if (sk_under_memory_pressure(sk)) - sk_mem_reclaim(sk); - if (sctp_wspace(asoc) <= 0 || !sk_wmem_schedule(sk, msg_len)) { timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); err = sctp_wait_for_sndbuf(asoc, &timeo, msg_len); @@ -9194,8 +9192,6 @@ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p, goto do_error; if (signal_pending(current)) goto do_interrupted; - if (sk_under_memory_pressure(sk)) - sk_mem_reclaim(sk); if ((int)msg_len <= sctp_wspace(asoc) && sk_wmem_schedule(sk, msg_len)) break; @@ -9657,7 +9653,10 @@ struct proto sctp_prot = { .sysctl_wmem = sysctl_sctp_wmem, .memory_pressure = &sctp_memory_pressure, .enter_memory_pressure = sctp_enter_memory_pressure, + .memory_allocated = &sctp_memory_allocated, + .per_cpu_fw_alloc = &sctp_memory_per_cpu_fw_alloc, + .sockets_allocated = &sctp_sockets_allocated, }; @@ -9700,7 +9699,10 @@ struct proto sctpv6_prot = { .sysctl_wmem = sysctl_sctp_wmem, .memory_pressure = &sctp_memory_pressure, .enter_memory_pressure = sctp_enter_memory_pressure, + .memory_allocated = &sctp_memory_allocated, + .per_cpu_fw_alloc = &sctp_memory_per_cpu_fw_alloc, + .sockets_allocated = &sctp_sockets_allocated, }; #endif /* IS_ENABLED(CONFIG_IPV6) */ diff --git a/net/sctp/stream_interleave.c b/net/sctp/stream_interleave.c index 6b13f737ebf2..bb22b71df7a3 100644 --- a/net/sctp/stream_interleave.c +++ b/net/sctp/stream_interleave.c @@ -979,8 +979,6 @@ static void sctp_renege_events(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk, if (freed >= needed && sctp_ulpevent_idata(ulpq, chunk, gfp) <= 0) sctp_intl_start_pd(ulpq, gfp); - - sk_mem_reclaim(asoc->base.sk); } static void sctp_intl_stream_abort_pd(struct sctp_ulpq *ulpq, __u16 sid, diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c index 407fed46931b..0a8510a0c5e6 100644 --- a/net/sctp/ulpqueue.c +++ b/net/sctp/ulpqueue.c @@ -1100,12 +1100,8 @@ void sctp_ulpq_renege(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk, else if (retval == 1) sctp_ulpq_reasm_drain(ulpq); } - - sk_mem_reclaim(asoc->base.sk); } - - /* Notify the application if an association is aborted and in * partial delivery mode. Send up any pending received messages. */ diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 7055ed10e316..4c3bf6db7038 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -120,7 +120,8 @@ static int smc_pnet_remove_by_pnetid(struct net *net, char *pnet_name) smc_pnet_match(pnetelem->pnet_name, pnet_name)) { list_del(&pnetelem->list); if (pnetelem->type == SMC_PNET_ETH && pnetelem->ndev) { - dev_put_track(pnetelem->ndev, &pnetelem->dev_tracker); + netdev_put(pnetelem->ndev, + &pnetelem->dev_tracker); pr_warn_ratelimited("smc: net device %s " "erased user defined " "pnetid %.16s\n", @@ -196,7 +197,7 @@ static int smc_pnet_add_by_ndev(struct net_device *ndev) list_for_each_entry_safe(pnetelem, tmp_pe, &pnettable->pnetlist, list) { if (pnetelem->type == SMC_PNET_ETH && !pnetelem->ndev && !strncmp(pnetelem->eth_name, ndev->name, IFNAMSIZ)) { - dev_hold_track(ndev, &pnetelem->dev_tracker, GFP_ATOMIC); + netdev_hold(ndev, &pnetelem->dev_tracker, GFP_ATOMIC); pnetelem->ndev = ndev; rc = 0; pr_warn_ratelimited("smc: adding net device %s with " @@ -227,7 +228,7 @@ static int smc_pnet_remove_by_ndev(struct net_device *ndev) mutex_lock(&pnettable->lock); list_for_each_entry_safe(pnetelem, tmp_pe, &pnettable->pnetlist, list) { if (pnetelem->type == SMC_PNET_ETH && pnetelem->ndev == ndev) { - dev_put_track(pnetelem->ndev, &pnetelem->dev_tracker); + netdev_put(pnetelem->ndev, &pnetelem->dev_tracker); pnetelem->ndev = NULL; rc = 0; pr_warn_ratelimited("smc: removing net device %s with " diff --git a/net/socket.c b/net/socket.c index 2bc8773d9dc5..1b6f5e2ebef5 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1878,10 +1878,8 @@ out_fd: return ERR_PTR(err); } -int __sys_accept4_file(struct file *file, unsigned file_flags, - struct sockaddr __user *upeer_sockaddr, - int __user *upeer_addrlen, int flags, - unsigned long nofile) +static int __sys_accept4_file(struct file *file, struct sockaddr __user *upeer_sockaddr, + int __user *upeer_addrlen, int flags) { struct file *newfile; int newfd; @@ -1892,11 +1890,11 @@ int __sys_accept4_file(struct file *file, unsigned file_flags, if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; - newfd = __get_unused_fd_flags(flags, nofile); + newfd = get_unused_fd_flags(flags); if (unlikely(newfd < 0)) return newfd; - newfile = do_accept(file, file_flags, upeer_sockaddr, upeer_addrlen, + newfile = do_accept(file, 0, upeer_sockaddr, upeer_addrlen, flags); if (IS_ERR(newfile)) { put_unused_fd(newfd); @@ -1926,9 +1924,8 @@ int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, f = fdget(fd); if (f.file) { - ret = __sys_accept4_file(f.file, 0, upeer_sockaddr, - upeer_addrlen, flags, - rlimit(RLIMIT_NOFILE)); + ret = __sys_accept4_file(f.file, upeer_sockaddr, + upeer_addrlen, flags); fdput(f); } diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 474f76383033..8cc42aea19c7 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -64,7 +64,7 @@ void switchdev_deferred_process(void) while ((dfitem = switchdev_deferred_dequeue())) { dfitem->func(dfitem->dev, dfitem->data); - dev_put_track(dfitem->dev, &dfitem->dev_tracker); + netdev_put(dfitem->dev, &dfitem->dev_tracker); kfree(dfitem); } } @@ -91,7 +91,7 @@ static int switchdev_deferred_enqueue(struct net_device *dev, dfitem->dev = dev; dfitem->func = func; memcpy(dfitem->data, data, data_len); - dev_hold_track(dev, &dfitem->dev_tracker, GFP_ATOMIC); + netdev_hold(dev, &dfitem->dev_tracker, GFP_ATOMIC); spin_lock_bh(&deferred_lock); list_add_tail(&dfitem->list, &deferred); spin_unlock_bh(&deferred_lock); diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 932c87b98eca..35cac7733fd3 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -788,7 +788,7 @@ int tipc_attach_loopback(struct net *net) if (!dev) return -ENODEV; - dev_hold_track(dev, &tn->loopback_pt.dev_tracker, GFP_KERNEL); + netdev_hold(dev, &tn->loopback_pt.dev_tracker, GFP_KERNEL); tn->loopback_pt.dev = dev; tn->loopback_pt.type = htons(ETH_P_TIPC); tn->loopback_pt.func = tipc_loopback_rcv_pkt; @@ -801,7 +801,7 @@ void tipc_detach_loopback(struct net *net) struct tipc_net *tn = tipc_net(net); dev_remove_pack(&tn->loopback_pt); - dev_put_track(net->loopback_dev, &tn->loopback_pt.dev_tracker); + netdev_put(net->loopback_dev, &tn->loopback_pt.dev_tracker); } /* Caller should hold rtnl_lock to protect the bearer */ diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 2206e6f8902d..3453e0053f76 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -302,7 +302,7 @@ static void __unix_remove_socket(struct sock *sk) static void __unix_insert_socket(struct sock *sk) { - WARN_ON(!sk_unhashed(sk)); + DEBUG_NET_WARN_ON_ONCE(!sk_unhashed(sk)); sk_add_node(sk, &unix_socket_table[sk->sk_hash]); } @@ -554,9 +554,9 @@ static void unix_sock_destructor(struct sock *sk) u->oob_skb = NULL; } #endif - WARN_ON(refcount_read(&sk->sk_wmem_alloc)); - WARN_ON(!sk_unhashed(sk)); - WARN_ON(sk->sk_socket); + DEBUG_NET_WARN_ON_ONCE(refcount_read(&sk->sk_wmem_alloc)); + DEBUG_NET_WARN_ON_ONCE(!sk_unhashed(sk)); + DEBUG_NET_WARN_ON_ONCE(sk->sk_socket); if (!sock_flag(sk, SOCK_DEAD)) { pr_info("Attempt to release alive unix socket: %p\n", sk); return; diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 35c7e89b2e7d..637ca8838436 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -275,7 +275,7 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, xso->dev = NULL; xso->dir = 0; xso->real_dev = NULL; - dev_put_track(dev, &xso->dev_tracker); + netdev_put(dev, &xso->dev_tracker); if (err != -EOPNOTSUPP) return err; |