diff options
366 files changed, 8800 insertions, 3125 deletions
diff --git a/.editorconfig b/.editorconfig index 854773350cc5..29a30ccfc07b 100644 --- a/.editorconfig +++ b/.editorconfig @@ -5,7 +5,6 @@ root = true [{*.{awk,c,dts,dtsi,dtso,h,mk,s,S},Kconfig,Makefile,Makefile.*}] charset = utf-8 end_of_line = lf -trim_trailing_whitespace = true insert_final_newline = true indent_style = tab indent_size = 8 @@ -13,7 +12,6 @@ indent_size = 8 [*.{json,py,rs}] charset = utf-8 end_of_line = lf -trim_trailing_whitespace = true insert_final_newline = true indent_style = space indent_size = 4 @@ -26,7 +24,6 @@ indent_size = 8 [*.yaml] charset = utf-8 end_of_line = lf -trim_trailing_whitespace = unset insert_final_newline = true indent_style = space indent_size = 2 @@ -608,6 +608,7 @@ Simon Kelley <[email protected]> Sricharan Ramabadhran <[email protected]> <[email protected]> Srinivas Ramana <[email protected]> <[email protected]> Sriram R <[email protected]> <[email protected]> +Stanislav Fomichev <[email protected]> <[email protected]> Stefan Wahren <[email protected]> <[email protected]> Stéphane Witzmann <[email protected]> Stephen Hemminger <[email protected]> <[email protected]> diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index b600df82669d..11e57ba2985c 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2192,12 +2192,6 @@ Format: 0 | 1 Default set by CONFIG_INIT_ON_FREE_DEFAULT_ON. - init_mlocked_on_free= [MM] Fill freed userspace memory with zeroes if - it was mlock'ed and not explicitly munlock'ed - afterwards. - Format: 0 | 1 - Default set by CONFIG_INIT_MLOCKED_ON_FREE_DEFAULT_ON - init_pkru= [X86] Specify the default memory protection keys rights register contents for all processes. 0x55555554 by default (disallow access to all but pkey 0). Can diff --git a/Documentation/devicetree/bindings/iio/dac/adi,ad3552r.yaml b/Documentation/devicetree/bindings/iio/dac/adi,ad3552r.yaml index 96340a05754c..8265d709094d 100644 --- a/Documentation/devicetree/bindings/iio/dac/adi,ad3552r.yaml +++ b/Documentation/devicetree/bindings/iio/dac/adi,ad3552r.yaml @@ -139,7 +139,7 @@ allOf: Voltage output range of the channel as <minimum, maximum> Required connections: Rfb1x for: 0 to 2.5 V; 0 to 3V; 0 to 5 V; - Rfb2x for: 0 to 10 V; 2.5 to 7.5V; -5 to 5 V; + Rfb2x for: 0 to 10 V; -2.5 to 7.5V; -5 to 5 V; oneOf: - items: - const: 0 diff --git a/Documentation/devicetree/bindings/net/arc_emac.txt b/Documentation/devicetree/bindings/net/arc_emac.txt deleted file mode 100644 index c73a0e9c625e..000000000000 --- a/Documentation/devicetree/bindings/net/arc_emac.txt +++ /dev/null @@ -1,46 +0,0 @@ -* Synopsys ARC EMAC 10/100 Ethernet driver (EMAC) - -Required properties: -- compatible: Should be "snps,arc-emac" -- reg: Address and length of the register set for the device -- interrupts: Should contain the EMAC interrupts -- max-speed: see ethernet.txt file in the same directory. -- phy: see ethernet.txt file in the same directory. - -Optional properties: -- phy-reset-gpios : Should specify the gpio for phy reset -- phy-reset-duration : Reset duration in milliseconds. Should present - only if property "phy-reset-gpios" is available. Missing the property - will have the duration be 1 millisecond. Numbers greater than 1000 are - invalid and 1 millisecond will be used instead. - -Clock handling: -The clock frequency is needed to calculate and set polling period of EMAC. -It must be provided by one of: -- clock-frequency: CPU frequency. -- clocks: reference to the clock supplying the EMAC. - -Child nodes of the driver are the individual PHY devices connected to the -MDIO bus. They must have a "reg" property given the PHY address on the MDIO bus. - -Examples: - - ethernet@c0fc2000 { - compatible = "snps,arc-emac"; - reg = <0xc0fc2000 0x3c>; - interrupts = <6>; - mac-address = [ 00 11 22 33 44 55 ]; - - clock-frequency = <80000000>; - /* or */ - clocks = <&emac_clock>; - - max-speed = <100>; - phy = <&phy0>; - - #address-cells = <1>; - #size-cells = <0>; - phy0: ethernet-phy@0 { - reg = <1>; - }; - }; diff --git a/Documentation/devicetree/bindings/net/fsl,fman-mdio.yaml b/Documentation/devicetree/bindings/net/fsl,fman-mdio.yaml new file mode 100644 index 000000000000..6b2c0aa407a2 --- /dev/null +++ b/Documentation/devicetree/bindings/net/fsl,fman-mdio.yaml @@ -0,0 +1,123 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/fsl,fman-mdio.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Freescale Frame Manager MDIO Device + +maintainers: + - Frank Li <[email protected]> + +description: FMan MDIO Node. + The MDIO is a bus to which the PHY devices are connected. + +properties: + compatible: + enum: + - fsl,fman-mdio + - fsl,fman-xmdio + - fsl,fman-memac-mdio + description: + Must include "fsl,fman-mdio" for 1 Gb/s MDIO from FMan v2. + Must include "fsl,fman-xmdio" for 10 Gb/s MDIO from FMan v2. + Must include "fsl,fman-memac-mdio" for 1/10 Gb/s MDIO from + FMan v3. + + reg: + maxItems: 1 + + clocks: + items: + - description: A reference to the input clock of the controller + from which the MDC frequency is derived. + + interrupts: + maxItems: 1 + + fsl,fman-internal-mdio: + $ref: /schemas/types.yaml#/definitions/flag + description: + Fman has internal MDIO for internal PCS(Physical + Coding Sublayer) PHYs and external MDIO for external PHYs. + The settings and programming routines for internal/external + MDIO are different. Must be included for internal MDIO. + + fsl,erratum-a009885: + $ref: /schemas/types.yaml#/definitions/flag + description: Indicates the presence of the A009885 + erratum describing that the contents of MDIO_DATA may + become corrupt unless it is read within 16 MDC cycles + of MDIO_CFG[BSY] being cleared, when performing an + MDIO read operation. + + fsl,erratum-a011043: + $ref: /schemas/types.yaml#/definitions/flag + description: + Indicates the presence of the A011043 erratum + describing that the MDIO_CFG[MDIO_RD_ER] bit may be falsely + set when reading internal PCS registers. MDIO reads to + internal PCS registers may result in having the + MDIO_CFG[MDIO_RD_ER] bit set, even when there is no error and + read data (MDIO_DATA[MDIO_DATA]) is correct. + Software may get false read error when reading internal + PCS registers through MDIO. As a workaround, all internal + MDIO accesses should ignore the MDIO_CFG[MDIO_RD_ER] bit. + + For internal PHY device on internal mdio bus, a PHY node should be created. + See the definition of the PHY node in booting-without-of.txt for an + example of how to define a PHY (Internal PHY has no interrupt line). + - For "fsl,fman-mdio" compatible internal mdio bus, the PHY is TBI PHY. + - For "fsl,fman-memac-mdio" compatible internal mdio bus, the PHY is PCS PHY. + The PCS PHY address should correspond to the value of the appropriate + MDEV_PORT. + + little-endian: + $ref: /schemas/types.yaml#/definitions/flag + description: + IP block is little-endian mode. The default endian mode is big-endian. + +required: + - compatible + - reg + +allOf: + - $ref: mdio.yaml# + +unevaluatedProperties: false + +examples: + - | + mdio@f1000 { + compatible = "fsl,fman-xmdio"; + reg = <0xf1000 0x1000>; + interrupts = <101 2 0 0>; + }; + + - | + mdio@e3120 { + compatible = "fsl,fman-mdio"; + reg = <0xe3120 0xee0>; + fsl,fman-internal-mdio; + #address-cells = <1>; + #size-cells = <0>; + + tbi-phy@8 { + reg = <0x8>; + device_type = "tbi-phy"; + }; + }; + + - | + mdio@f1000 { + compatible = "fsl,fman-memac-mdio"; + reg = <0xf1000 0x1000>; + fsl,fman-internal-mdio; + #address-cells = <1>; + #size-cells = <0>; + + pcsphy6: ethernet-phy@0 { + reg = <0x0>; + }; + }; + diff --git a/Documentation/devicetree/bindings/net/fsl,fman-muram.yaml b/Documentation/devicetree/bindings/net/fsl,fman-muram.yaml new file mode 100644 index 000000000000..aa71acc7fa5b --- /dev/null +++ b/Documentation/devicetree/bindings/net/fsl,fman-muram.yaml @@ -0,0 +1,40 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/fsl,fman-muram.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Freescale Frame Manager MURAM Device + +maintainers: + - Frank Li <[email protected]> + +description: | + FMan Internal memory - shared between all the FMan modules. + It contains data structures that are common and written to or read by + the modules. + + FMan internal memory is split into the following parts: + Packet buffering (Tx/Rx FIFOs) + Frames internal context + +properties: + compatible: + enum: + - fsl,fman-muram + + reg: + maxItems: 1 + +required: + - compatible + - reg + +additionalProperties: false + +examples: + - | + muram@0 { + compatible = "fsl,fman-muram"; + reg = <0x0 0x28000>; + }; diff --git a/Documentation/devicetree/bindings/net/fsl,fman-port.yaml b/Documentation/devicetree/bindings/net/fsl,fman-port.yaml new file mode 100644 index 000000000000..9de445307830 --- /dev/null +++ b/Documentation/devicetree/bindings/net/fsl,fman-port.yaml @@ -0,0 +1,75 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/fsl,fman-port.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Freescale Frame Manager Port Device + +maintainers: + - Frank Li <[email protected]> + +description: | + The Frame Manager (FMan) supports several types of hardware ports: + Ethernet receiver (RX) + Ethernet transmitter (TX) + Offline/Host command (O/H) + +properties: + compatible: + enum: + - fsl,fman-v2-port-oh + - fsl,fman-v2-port-rx + - fsl,fman-v2-port-tx + - fsl,fman-v3-port-oh + - fsl,fman-v3-port-rx + - fsl,fman-v3-port-tx + + cell-index: + $ref: /schemas/types.yaml#/definitions/uint32 + description: + Specifies the hardware port id. + Each hardware port on the FMan has its own hardware PortID. + Super set of all hardware Port IDs available at FMan Reference + Manual under "FMan Hardware Ports in Freescale Devices" table. + + Each hardware port is assigned a 4KB, port-specific page in + the FMan hardware port memory region (which is part of the + FMan memory map). The first 4 KB in the FMan hardware ports + memory region is used for what are called common registers. + The subsequent 63 4KB pages are allocated to the hardware + ports. + The page of a specific port is determined by the cell-index. + + reg: + items: + - description: There is one reg region describing the port + configuration registers. + + fsl,fman-10g-port: + $ref: /schemas/types.yaml#/definitions/flag + description: The default port rate is 1G. + If this property exists, the port is s 10G port. + + fsl,fman-best-effort-port: + $ref: /schemas/types.yaml#/definitions/flag + description: The default port rate is 1G. + Can be defined only if 10G-support is set. + This property marks a best-effort 10G port (10G port that + may not be capable of line rate). + +required: + - compatible + - reg + - cell-index + +additionalProperties: false + +examples: + - | + port@a8000 { + compatible = "fsl,fman-v2-port-tx"; + reg = <0xa8000 0x1000>; + cell-index = <0x28>; + }; + diff --git a/Documentation/devicetree/bindings/net/fsl,fman.yaml b/Documentation/devicetree/bindings/net/fsl,fman.yaml new file mode 100644 index 000000000000..7908f67413de --- /dev/null +++ b/Documentation/devicetree/bindings/net/fsl,fman.yaml @@ -0,0 +1,204 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/fsl,fman.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Freescale Frame Manager Device + +maintainers: + - Frank Li <[email protected]> + +description: + Due to the fact that the FMan is an aggregation of sub-engines (ports, MACs, + etc.) the FMan node will have child nodes for each of them. + +properties: + compatible: + enum: + - fsl,fman + description: + FMan version can be determined via FM_IP_REV_1 register in the + FMan block. The offset is 0xc4 from the beginning of the + Frame Processing Manager memory map (0xc3000 from the + beginning of the FMan node). + + cell-index: + $ref: /schemas/types.yaml#/definitions/uint32 + description: | + Specifies the index of the FMan unit. + + The cell-index value may be used by the SoC, to identify the + FMan unit in the SoC memory map. In the table below, + there's a description of the cell-index use in each SoC: + + - P1023: + register[bit] FMan unit cell-index + ============================================================ + DEVDISR[1] 1 0 + + - P2041, P3041, P4080 P5020, P5040: + register[bit] FMan unit cell-index + ============================================================ + DCFG_DEVDISR2[6] 1 0 + DCFG_DEVDISR2[14] 2 1 + (Second FM available only in P4080 and P5040) + + - B4860, T1040, T2080, T4240: + register[bit] FMan unit cell-index + ============================================================ + DCFG_CCSR_DEVDISR2[24] 1 0 + DCFG_CCSR_DEVDISR2[25] 2 1 + (Second FM available only in T4240) + + DEVDISR, DCFG_DEVDISR2 and DCFG_CCSR_DEVDISR2 are located in + the specific SoC "Device Configuration/Pin Control" Memory + Map. + + reg: + items: + - description: BMI configuration registers. + - description: QMI configuration registers. + - description: DMA configuration registers. + - description: FPM configuration registers. + - description: FMan controller configuration registers. + minItems: 1 + + ranges: true + + clocks: + maxItems: 1 + + clock-names: + items: + - const: fmanclk + + interrupts: + items: + - description: The first element is associated with the event interrupts. + - description: the second element is associated with the error interrupts. + + fsl,qman-channel-range: + $ref: /schemas/types.yaml#/definitions/uint32-array + description: + Specifies the range of the available dedicated + channels in the FMan. The first cell specifies the beginning + of the range and the second cell specifies the number of + channels + items: + - description: The first cell specifies the beginning of the range. + - description: | + The second cell specifies the number of channels. + Further information available at: + "Work Queue (WQ) Channel Assignments in the QMan" section + in DPAA Reference Manual. + + fsl,qman: + $ref: /schemas/types.yaml#/definitions/phandle + description: See soc/fsl/qman.txt + + fsl,bman: + $ref: /schemas/types.yaml#/definitions/phandle + description: See soc/fsl/bman.txt + + fsl,erratum-a050385: + $ref: /schemas/types.yaml#/definitions/flag + description: A boolean property. Indicates the presence of the + erratum A050385 which indicates that DMA transactions that are + split can result in a FMan lock. + + '#address-cells': + const: 1 + + '#size-cells': + const: 1 + +patternProperties: + '^muram@[a-f0-9]+$': + $ref: fsl,fman-muram.yaml + + '^port@[a-f0-9]+$': + $ref: fsl,fman-port.yaml + + '^ethernet@[a-f0-9]+$': + $ref: fsl,fman-dtsec.yaml + + '^mdio@[a-f0-9]+$': + $ref: fsl,fman-mdio.yaml + + '^phc@[a-f0-9]+$': + $ref: /schemas/ptp/fsl,ptp.yaml + +required: + - compatible + - cell-index + - reg + - ranges + - clocks + - clock-names + - interrupts + - fsl,qman-channel-range + +additionalProperties: false + +examples: + - | + #include <dt-bindings/interrupt-controller/irq.h> + + fman@400000 { + compatible = "fsl,fman"; + reg = <0x400000 0x100000>; + ranges = <0 0x400000 0x100000>; + #address-cells = <1>; + #size-cells = <1>; + cell-index = <1>; + clocks = <&fman_clk>; + clock-names = "fmanclk"; + interrupts = <96 IRQ_TYPE_EDGE_FALLING>, + <16 IRQ_TYPE_EDGE_FALLING>; + fsl,qman-channel-range = <0x40 0xc>; + + muram@0 { + compatible = "fsl,fman-muram"; + reg = <0x0 0x28000>; + }; + + port@81000 { + cell-index = <1>; + compatible = "fsl,fman-v2-port-oh"; + reg = <0x81000 0x1000>; + }; + + fman1_rx_0x8: port@88000 { + cell-index = <0x8>; + compatible = "fsl,fman-v2-port-rx"; + reg = <0x88000 0x1000>; + }; + + fman1_tx_0x28: port@a8000 { + cell-index = <0x28>; + compatible = "fsl,fman-v2-port-tx"; + reg = <0xa8000 0x1000>; + }; + + ethernet@e0000 { + compatible = "fsl,fman-dtsec"; + cell-index = <0>; + reg = <0xe0000 0x1000>; + ptp-timer = <&ptp_timer>; + fsl,fman-ports = <&fman1_rx_0x8 &fman1_tx_0x28>; + tbi-handle = <&tbi5>; + }; + + ptp_timer: phc@fe000 { + compatible = "fsl,fman-ptp-timer"; + reg = <0xfe000 0x1000>; + interrupts = <12 IRQ_TYPE_LEVEL_LOW>; + }; + + mdio@f1000 { + compatible = "fsl,fman-xmdio"; + reg = <0xf1000 0x1000>; + interrupts = <101 IRQ_TYPE_EDGE_FALLING>; + }; + }; diff --git a/Documentation/devicetree/bindings/net/fsl-fman.txt b/Documentation/devicetree/bindings/net/fsl-fman.txt deleted file mode 100644 index bda4b41af074..000000000000 --- a/Documentation/devicetree/bindings/net/fsl-fman.txt +++ /dev/null @@ -1,548 +0,0 @@ -============================================================================= -Freescale Frame Manager Device Bindings - -CONTENTS - - FMan Node - - FMan Port Node - - FMan MURAM Node - - FMan dTSEC/XGEC/mEMAC Node - - FMan IEEE 1588 Node - - FMan MDIO Node - - Example - -============================================================================= -FMan Node - -DESCRIPTION - -Due to the fact that the FMan is an aggregation of sub-engines (ports, MACs, -etc.) the FMan node will have child nodes for each of them. - -PROPERTIES - -- compatible - Usage: required - Value type: <stringlist> - Definition: Must include "fsl,fman" - FMan version can be determined via FM_IP_REV_1 register in the - FMan block. The offset is 0xc4 from the beginning of the - Frame Processing Manager memory map (0xc3000 from the - beginning of the FMan node). - -- cell-index - Usage: required - Value type: <u32> - Definition: Specifies the index of the FMan unit. - - The cell-index value may be used by the SoC, to identify the - FMan unit in the SoC memory map. In the table below, - there's a description of the cell-index use in each SoC: - - - P1023: - register[bit] FMan unit cell-index - ============================================================ - DEVDISR[1] 1 0 - - - P2041, P3041, P4080 P5020, P5040: - register[bit] FMan unit cell-index - ============================================================ - DCFG_DEVDISR2[6] 1 0 - DCFG_DEVDISR2[14] 2 1 - (Second FM available only in P4080 and P5040) - - - B4860, T1040, T2080, T4240: - register[bit] FMan unit cell-index - ============================================================ - DCFG_CCSR_DEVDISR2[24] 1 0 - DCFG_CCSR_DEVDISR2[25] 2 1 - (Second FM available only in T4240) - - DEVDISR, DCFG_DEVDISR2 and DCFG_CCSR_DEVDISR2 are located in - the specific SoC "Device Configuration/Pin Control" Memory - Map. - -- reg - Usage: required - Value type: <prop-encoded-array> - Definition: A standard property. Specifies the offset of the - following configuration registers: - - BMI configuration registers. - - QMI configuration registers. - - DMA configuration registers. - - FPM configuration registers. - - FMan controller configuration registers. - -- ranges - Usage: required - Value type: <prop-encoded-array> - Definition: A standard property. - -- clocks - Usage: required - Value type: <prop-encoded-array> - Definition: phandle for the fman input clock. - -- clock-names - usage: required - Value type: <stringlist> - Definition: "fmanclk" for the fman input clock. - -- interrupts - Usage: required - Value type: <prop-encoded-array> - Definition: A pair of IRQs are specified in this property. - The first element is associated with the event interrupts and - the second element is associated with the error interrupts. - -- fsl,qman-channel-range - Usage: required - Value type: <prop-encoded-array> - Definition: Specifies the range of the available dedicated - channels in the FMan. The first cell specifies the beginning - of the range and the second cell specifies the number of - channels. - Further information available at: - "Work Queue (WQ) Channel Assignments in the QMan" section - in DPAA Reference Manual. - -- fsl,qman -- fsl,bman - Usage: required - Definition: See soc/fsl/qman.txt and soc/fsl/bman.txt - -- fsl,erratum-a050385 - Usage: optional - Value type: boolean - Definition: A boolean property. Indicates the presence of the - erratum A050385 which indicates that DMA transactions that are - split can result in a FMan lock. - -============================================================================= -FMan MURAM Node - -DESCRIPTION - -FMan Internal memory - shared between all the FMan modules. -It contains data structures that are common and written to or read by -the modules. -FMan internal memory is split into the following parts: - Packet buffering (Tx/Rx FIFOs) - Frames internal context - -PROPERTIES - -- compatible - Usage: required - Value type: <stringlist> - Definition: Must include "fsl,fman-muram" - -- ranges - Usage: required - Value type: <prop-encoded-array> - Definition: A standard property. - Specifies the multi-user memory offset and the size within - the FMan. - -EXAMPLE - -muram@0 { - compatible = "fsl,fman-muram"; - ranges = <0 0x000000 0x28000>; -}; - -============================================================================= -FMan Port Node - -DESCRIPTION - -The Frame Manager (FMan) supports several types of hardware ports: - Ethernet receiver (RX) - Ethernet transmitter (TX) - Offline/Host command (O/H) - -PROPERTIES - -- compatible - Usage: required - Value type: <stringlist> - Definition: A standard property. - Must include one of the following: - - "fsl,fman-v2-port-oh" for FManV2 OH ports - - "fsl,fman-v2-port-rx" for FManV2 RX ports - - "fsl,fman-v2-port-tx" for FManV2 TX ports - - "fsl,fman-v3-port-oh" for FManV3 OH ports - - "fsl,fman-v3-port-rx" for FManV3 RX ports - - "fsl,fman-v3-port-tx" for FManV3 TX ports - -- cell-index - Usage: required - Value type: <u32> - Definition: Specifies the hardware port id. - Each hardware port on the FMan has its own hardware PortID. - Super set of all hardware Port IDs available at FMan Reference - Manual under "FMan Hardware Ports in Freescale Devices" table. - - Each hardware port is assigned a 4KB, port-specific page in - the FMan hardware port memory region (which is part of the - FMan memory map). The first 4 KB in the FMan hardware ports - memory region is used for what are called common registers. - The subsequent 63 4KB pages are allocated to the hardware - ports. - The page of a specific port is determined by the cell-index. - -- reg - Usage: required - Value type: <prop-encoded-array> - Definition: There is one reg region describing the port - configuration registers. - -- fsl,fman-10g-port - Usage: optional - Value type: boolean - Definition: The default port rate is 1G. - If this property exists, the port is s 10G port. - -- fsl,fman-best-effort-port - Usage: optional - Value type: boolean - Definition: Can be defined only if 10G-support is set. - This property marks a best-effort 10G port (10G port that - may not be capable of line rate). - -EXAMPLE - -port@a8000 { - cell-index = <0x28>; - compatible = "fsl,fman-v2-port-tx"; - reg = <0xa8000 0x1000>; -}; - -port@88000 { - cell-index = <0x8>; - compatible = "fsl,fman-v2-port-rx"; - reg = <0x88000 0x1000>; -}; - -port@81000 { - cell-index = <0x1>; - compatible = "fsl,fman-v2-port-oh"; - reg = <0x81000 0x1000>; -}; - -============================================================================= -FMan dTSEC/XGEC/mEMAC Node - -Refer to Documentation/devicetree/bindings/net/fsl,fman-dtsec.yaml - -============================================================================ -FMan IEEE 1588 Node - -Refer to Documentation/devicetree/bindings/ptp/ptp-qoriq.txt - -============================================================================= -FMan MDIO Node - -DESCRIPTION - -The MDIO is a bus to which the PHY devices are connected. - -PROPERTIES - -- compatible - Usage: required - Value type: <stringlist> - Definition: A standard property. - Must include "fsl,fman-mdio" for 1 Gb/s MDIO from FMan v2. - Must include "fsl,fman-xmdio" for 10 Gb/s MDIO from FMan v2. - Must include "fsl,fman-memac-mdio" for 1/10 Gb/s MDIO from - FMan v3. - -- reg - Usage: required - Value type: <prop-encoded-array> - Definition: A standard property. - -- clocks - Usage: optional - Value type: <phandle> - Definition: A reference to the input clock of the controller - from which the MDC frequency is derived. - -- clock-frequency - Usage: optional - Value type: <u32> - Definition: Specifies the external MDC frequency, in Hertz, to - be used. Requires that the input clock is specified in the - "clocks" property. See also: mdio.yaml. - -- suppress-preamble - Usage: optional - Value type: <boolean> - Definition: Disable generation of preamble bits. See also: - mdio.yaml. - -- interrupts - Usage: required for external MDIO - Value type: <prop-encoded-array> - Definition: Event interrupt of external MDIO controller. - -- fsl,fman-internal-mdio - Usage: required for internal MDIO - Value type: boolean - Definition: Fman has internal MDIO for internal PCS(Physical - Coding Sublayer) PHYs and external MDIO for external PHYs. - The settings and programming routines for internal/external - MDIO are different. Must be included for internal MDIO. - -- fsl,erratum-a009885 - Usage: optional - Value type: <boolean> - Definition: Indicates the presence of the A009885 - erratum describing that the contents of MDIO_DATA may - become corrupt unless it is read within 16 MDC cycles - of MDIO_CFG[BSY] being cleared, when performing an - MDIO read operation. - -- fsl,erratum-a011043 - Usage: optional - Value type: <boolean> - Definition: Indicates the presence of the A011043 erratum - describing that the MDIO_CFG[MDIO_RD_ER] bit may be falsely - set when reading internal PCS registers. MDIO reads to - internal PCS registers may result in having the - MDIO_CFG[MDIO_RD_ER] bit set, even when there is no error and - read data (MDIO_DATA[MDIO_DATA]) is correct. - Software may get false read error when reading internal - PCS registers through MDIO. As a workaround, all internal - MDIO accesses should ignore the MDIO_CFG[MDIO_RD_ER] bit. - -For internal PHY device on internal mdio bus, a PHY node should be created. -See the definition of the PHY node in booting-without-of.txt for an -example of how to define a PHY (Internal PHY has no interrupt line). -- For "fsl,fman-mdio" compatible internal mdio bus, the PHY is TBI PHY. -- For "fsl,fman-memac-mdio" compatible internal mdio bus, the PHY is PCS PHY. - The PCS PHY address should correspond to the value of the appropriate - MDEV_PORT. - -EXAMPLE - -Example for FMan v2 external MDIO: - -mdio@f1000 { - compatible = "fsl,fman-xmdio"; - reg = <0xf1000 0x1000>; - interrupts = <101 2 0 0>; -}; - -Example for FMan v2 internal MDIO: - -mdio@e3120 { - compatible = "fsl,fman-mdio"; - reg = <0xe3120 0xee0>; - fsl,fman-internal-mdio; - - tbi1: tbi-phy@8 { - reg = <0x8>; - device_type = "tbi-phy"; - }; -}; - -Example for FMan v3 internal MDIO: - -mdio@f1000 { - compatible = "fsl,fman-memac-mdio"; - reg = <0xf1000 0x1000>; - fsl,fman-internal-mdio; - - pcsphy6: ethernet-phy@0 { - reg = <0x0>; - }; -}; - -============================================================================= -Example - -fman@400000 { - #address-cells = <1>; - #size-cells = <1>; - cell-index = <1>; - compatible = "fsl,fman" - ranges = <0 0x400000 0x100000>; - reg = <0x400000 0x100000>; - clocks = <&fman_clk>; - clock-names = "fmanclk"; - interrupts = < - 96 2 0 0 - 16 2 1 1>; - fsl,qman-channel-range = <0x40 0xc>; - - muram@0 { - compatible = "fsl,fman-muram"; - reg = <0x0 0x28000>; - }; - - port@81000 { - cell-index = <1>; - compatible = "fsl,fman-v2-port-oh"; - reg = <0x81000 0x1000>; - }; - - port@82000 { - cell-index = <2>; - compatible = "fsl,fman-v2-port-oh"; - reg = <0x82000 0x1000>; - }; - - port@83000 { - cell-index = <3>; - compatible = "fsl,fman-v2-port-oh"; - reg = <0x83000 0x1000>; - }; - - port@84000 { - cell-index = <4>; - compatible = "fsl,fman-v2-port-oh"; - reg = <0x84000 0x1000>; - }; - - port@85000 { - cell-index = <5>; - compatible = "fsl,fman-v2-port-oh"; - reg = <0x85000 0x1000>; - }; - - port@86000 { - cell-index = <6>; - compatible = "fsl,fman-v2-port-oh"; - reg = <0x86000 0x1000>; - }; - - fman1_rx_0x8: port@88000 { - cell-index = <0x8>; - compatible = "fsl,fman-v2-port-rx"; - reg = <0x88000 0x1000>; - }; - - fman1_rx_0x9: port@89000 { - cell-index = <0x9>; - compatible = "fsl,fman-v2-port-rx"; - reg = <0x89000 0x1000>; - }; - - fman1_rx_0xa: port@8a000 { - cell-index = <0xa>; - compatible = "fsl,fman-v2-port-rx"; - reg = <0x8a000 0x1000>; - }; - - fman1_rx_0xb: port@8b000 { - cell-index = <0xb>; - compatible = "fsl,fman-v2-port-rx"; - reg = <0x8b000 0x1000>; - }; - - fman1_rx_0xc: port@8c000 { - cell-index = <0xc>; - compatible = "fsl,fman-v2-port-rx"; - reg = <0x8c000 0x1000>; - }; - - fman1_rx_0x10: port@90000 { - cell-index = <0x10>; - compatible = "fsl,fman-v2-port-rx"; - reg = <0x90000 0x1000>; - }; - - fman1_tx_0x28: port@a8000 { - cell-index = <0x28>; - compatible = "fsl,fman-v2-port-tx"; - reg = <0xa8000 0x1000>; - }; - - fman1_tx_0x29: port@a9000 { - cell-index = <0x29>; - compatible = "fsl,fman-v2-port-tx"; - reg = <0xa9000 0x1000>; - }; - - fman1_tx_0x2a: port@aa000 { - cell-index = <0x2a>; - compatible = "fsl,fman-v2-port-tx"; - reg = <0xaa000 0x1000>; - }; - - fman1_tx_0x2b: port@ab000 { - cell-index = <0x2b>; - compatible = "fsl,fman-v2-port-tx"; - reg = <0xab000 0x1000>; - }; - - fman1_tx_0x2c: port@ac0000 { - cell-index = <0x2c>; - compatible = "fsl,fman-v2-port-tx"; - reg = <0xac000 0x1000>; - }; - - fman1_tx_0x30: port@b0000 { - cell-index = <0x30>; - compatible = "fsl,fman-v2-port-tx"; - reg = <0xb0000 0x1000>; - }; - - ethernet@e0000 { - compatible = "fsl,fman-dtsec"; - cell-index = <0>; - reg = <0xe0000 0x1000>; - fsl,fman-ports = <&fman1_rx_0x8 &fman1_tx_0x28>; - tbi-handle = <&tbi5>; - }; - - ethernet@e2000 { - compatible = "fsl,fman-dtsec"; - cell-index = <1>; - reg = <0xe2000 0x1000>; - fsl,fman-ports = <&fman1_rx_0x9 &fman1_tx_0x29>; - tbi-handle = <&tbi6>; - }; - - ethernet@e4000 { - compatible = "fsl,fman-dtsec"; - cell-index = <2>; - reg = <0xe4000 0x1000>; - fsl,fman-ports = <&fman1_rx_0xa &fman1_tx_0x2a>; - tbi-handle = <&tbi7>; - }; - - ethernet@e6000 { - compatible = "fsl,fman-dtsec"; - cell-index = <3>; - reg = <0xe6000 0x1000>; - fsl,fman-ports = <&fman1_rx_0xb &fman1_tx_0x2b>; - tbi-handle = <&tbi8>; - }; - - ethernet@e8000 { - compatible = "fsl,fman-dtsec"; - cell-index = <4>; - reg = <0xf0000 0x1000>; - fsl,fman-ports = <&fman1_rx_0xc &fman1_tx_0x2c>; - tbi-handle = <&tbi9>; - - ethernet@f0000 { - cell-index = <8>; - compatible = "fsl,fman-xgec"; - reg = <0xf0000 0x1000>; - fsl,fman-ports = <&fman1_rx_0x10 &fman1_tx_0x30>; - }; - - ptp-timer@fe000 { - compatible = "fsl,fman-ptp-timer"; - reg = <0xfe000 0x1000>; - }; - - mdio@f1000 { - compatible = "fsl,fman-xmdio"; - reg = <0xf1000 0x1000>; - interrupts = <101 2 0 0>; - }; -}; diff --git a/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt b/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt index 047bdf7bdd2f..9c9668c1b6a2 100644 --- a/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt +++ b/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt @@ -86,4 +86,4 @@ Example: * Gianfar PTP clock nodes -Refer to Documentation/devicetree/bindings/ptp/ptp-qoriq.txt +Refer to Documentation/devicetree/bindings/ptp/fsl,ptp.yaml diff --git a/Documentation/devicetree/bindings/net/mscc,miim.yaml b/Documentation/devicetree/bindings/net/mscc,miim.yaml index 5b292e7c9e46..792f26b06b06 100644 --- a/Documentation/devicetree/bindings/net/mscc,miim.yaml +++ b/Documentation/devicetree/bindings/net/mscc,miim.yaml @@ -38,6 +38,16 @@ properties: clock-frequency: true + resets: + items: + - description: + Reset shared with all blocks attached to the Switch Core Register + Bus (CSR) including VRAP slave. + + reset-names: + items: + - const: switch + required: - compatible - reg diff --git a/Documentation/devicetree/bindings/ptp/fsl,ptp.yaml b/Documentation/devicetree/bindings/ptp/fsl,ptp.yaml new file mode 100644 index 000000000000..3bb8615e3e91 --- /dev/null +++ b/Documentation/devicetree/bindings/ptp/fsl,ptp.yaml @@ -0,0 +1,144 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/ptp/fsl,ptp.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Freescale QorIQ 1588 timer based PTP clock + +maintainers: + - Frank Li <[email protected]> + +properties: + compatible: + enum: + - fsl,etsec-ptp + - fsl,fman-ptp-timer + - fsl,dpaa2-ptp + - fsl,enetc-ptp + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + clocks: + maxItems: 1 + + fsl,cksel: + $ref: /schemas/types.yaml#/definitions/uint32 + description: | + Timer reference clock source. + + Reference clock source is determined by the value, which is holded + in CKSEL bits in TMR_CTRL register. "fsl,cksel" property keeps the + value, which will be directly written in those bits, that is why, + according to reference manual, the next clock sources can be used: + + For eTSEC, + <0> - external high precision timer reference clock (TSEC_TMR_CLK + input is used for this purpose); + <1> - eTSEC system clock; + <2> - eTSEC1 transmit clock; + <3> - RTC clock input. + + For DPAA FMan, + <0> - external high precision timer reference clock (TMR_1588_CLK) + <1> - MAC system clock (1/2 FMan clock) + <2> - reserved + <3> - RTC clock oscillator + + fsl,tclk-period: + $ref: /schemas/types.yaml#/definitions/uint32 + description: Timer reference clock period in nanoseconds. + + fsl,tmr-prsc: + $ref: /schemas/types.yaml#/definitions/uint32 + description: Prescaler, divides the output clock. + + fsl,tmr-add: + $ref: /schemas/types.yaml#/definitions/uint32 + description: Frequency compensation value. + + fsl,tmr-fiper1: + $ref: /schemas/types.yaml#/definitions/uint32 + description: Fixed interval period pulse generator. + + fsl,tmr-fiper2: + $ref: /schemas/types.yaml#/definitions/uint32 + description: Fixed interval period pulse generator. + + fsl,tmr-fiper3: + $ref: /schemas/types.yaml#/definitions/uint32 + description: + Fixed interval period pulse generator. + Supported only on DPAA2 and ENETC hardware. + + fsl,max-adj: + $ref: /schemas/types.yaml#/definitions/uint32 + description: | + Maximum frequency adjustment in parts per billion. + + These properties set the operational parameters for the PTP + clock. You must choose these carefully for the clock to work right. + Here is how to figure good values: + + TimerOsc = selected reference clock MHz + tclk_period = desired clock period nanoseconds + NominalFreq = 1000 / tclk_period MHz + FreqDivRatio = TimerOsc / NominalFreq (must be greater that 1.0) + tmr_add = ceil(2^32 / FreqDivRatio) + OutputClock = NominalFreq / tmr_prsc MHz + PulseWidth = 1 / OutputClock microseconds + FiperFreq1 = desired frequency in Hz + FiperDiv1 = 1000000 * OutputClock / FiperFreq1 + tmr_fiper1 = tmr_prsc * tclk_period * FiperDiv1 - tclk_period + max_adj = 1000000000 * (FreqDivRatio - 1.0) - 1 + + The calculation for tmr_fiper2 is the same as for tmr_fiper1. The + driver expects that tmr_fiper1 will be correctly set to produce a 1 + Pulse Per Second (PPS) signal, since this will be offered to the PPS + subsystem to synchronize the Linux clock. + + When this attribute is not used, the IEEE 1588 timer reference clock + will use the eTSEC system clock (for Gianfar) or the MAC system + clock (for DPAA). + + fsl,extts-fifo: + $ref: /schemas/types.yaml#/definitions/flag + description: + The presence of this property indicates hardware + support for the external trigger stamp FIFO + + little-endian: + $ref: /schemas/types.yaml#/definitions/flag + description: + The presence of this property indicates the 1588 timer + support for the external trigger stamp FIFO. + IP block is little-endian mode. The default endian mode + is big-endian. + +required: + - compatible + - reg + +additionalProperties: false + +examples: + - | + #include <dt-bindings/interrupt-controller/irq.h> + + phc@24e00 { + compatible = "fsl,etsec-ptp"; + reg = <0x24e00 0xb0>; + interrupts = <12 IRQ_TYPE_LEVEL_LOW>; + interrupt-parent = <&ipic>; + fsl,cksel = <1>; + fsl,tclk-period = <10>; + fsl,tmr-prsc = <100>; + fsl,tmr-add = <0x999999a4>; + fsl,tmr-fiper1 = <0x3b9ac9f6>; + fsl,tmr-fiper2 = <0x00018696>; + fsl,max-adj = <659999998>; + }; diff --git a/Documentation/devicetree/bindings/ptp/ptp-qoriq.txt b/Documentation/devicetree/bindings/ptp/ptp-qoriq.txt deleted file mode 100644 index 743eda754e65..000000000000 --- a/Documentation/devicetree/bindings/ptp/ptp-qoriq.txt +++ /dev/null @@ -1,87 +0,0 @@ -* Freescale QorIQ 1588 timer based PTP clock - -General Properties: - - - compatible Should be "fsl,etsec-ptp" for eTSEC - Should be "fsl,fman-ptp-timer" for DPAA FMan - Should be "fsl,dpaa2-ptp" for DPAA2 - Should be "fsl,enetc-ptp" for ENETC - - reg Offset and length of the register set for the device - - interrupts There should be at least two interrupts. Some devices - have as many as four PTP related interrupts. - -Clock Properties: - - - fsl,cksel Timer reference clock source. - - fsl,tclk-period Timer reference clock period in nanoseconds. - - fsl,tmr-prsc Prescaler, divides the output clock. - - fsl,tmr-add Frequency compensation value. - - fsl,tmr-fiper1 Fixed interval period pulse generator. - - fsl,tmr-fiper2 Fixed interval period pulse generator. - - fsl,tmr-fiper3 Fixed interval period pulse generator. - Supported only on DPAA2 and ENETC hardware. - - fsl,max-adj Maximum frequency adjustment in parts per billion. - - fsl,extts-fifo The presence of this property indicates hardware - support for the external trigger stamp FIFO. - - little-endian The presence of this property indicates the 1588 timer - IP block is little-endian mode. The default endian mode - is big-endian. - - These properties set the operational parameters for the PTP - clock. You must choose these carefully for the clock to work right. - Here is how to figure good values: - - TimerOsc = selected reference clock MHz - tclk_period = desired clock period nanoseconds - NominalFreq = 1000 / tclk_period MHz - FreqDivRatio = TimerOsc / NominalFreq (must be greater that 1.0) - tmr_add = ceil(2^32 / FreqDivRatio) - OutputClock = NominalFreq / tmr_prsc MHz - PulseWidth = 1 / OutputClock microseconds - FiperFreq1 = desired frequency in Hz - FiperDiv1 = 1000000 * OutputClock / FiperFreq1 - tmr_fiper1 = tmr_prsc * tclk_period * FiperDiv1 - tclk_period - max_adj = 1000000000 * (FreqDivRatio - 1.0) - 1 - - The calculation for tmr_fiper2 is the same as for tmr_fiper1. The - driver expects that tmr_fiper1 will be correctly set to produce a 1 - Pulse Per Second (PPS) signal, since this will be offered to the PPS - subsystem to synchronize the Linux clock. - - Reference clock source is determined by the value, which is holded - in CKSEL bits in TMR_CTRL register. "fsl,cksel" property keeps the - value, which will be directly written in those bits, that is why, - according to reference manual, the next clock sources can be used: - - For eTSEC, - <0> - external high precision timer reference clock (TSEC_TMR_CLK - input is used for this purpose); - <1> - eTSEC system clock; - <2> - eTSEC1 transmit clock; - <3> - RTC clock input. - - For DPAA FMan, - <0> - external high precision timer reference clock (TMR_1588_CLK) - <1> - MAC system clock (1/2 FMan clock) - <2> - reserved - <3> - RTC clock oscillator - - When this attribute is not used, the IEEE 1588 timer reference clock - will use the eTSEC system clock (for Gianfar) or the MAC system - clock (for DPAA). - -Example: - - ptp_clock@24e00 { - compatible = "fsl,etsec-ptp"; - reg = <0x24E00 0xB0>; - interrupts = <12 0x8 13 0x8>; - interrupt-parent = < &ipic >; - fsl,cksel = <1>; - fsl,tclk-period = <10>; - fsl,tmr-prsc = <100>; - fsl,tmr-add = <0x999999A4>; - fsl,tmr-fiper1 = <0x3B9AC9F6>; - fsl,tmr-fiper2 = <0x00018696>; - fsl,max-adj = <659999998>; - }; diff --git a/Documentation/devicetree/bindings/usb/realtek,rts5411.yaml b/Documentation/devicetree/bindings/usb/realtek,rts5411.yaml index 0874fc21f66f..6577a61cc075 100644 --- a/Documentation/devicetree/bindings/usb/realtek,rts5411.yaml +++ b/Documentation/devicetree/bindings/usb/realtek,rts5411.yaml @@ -65,6 +65,7 @@ patternProperties: description: The hard wired USB devices type: object $ref: /schemas/usb/usb-device.yaml + additionalProperties: true required: - peer-hub diff --git a/Documentation/networking/devlink/octeontx2.rst b/Documentation/networking/devlink/octeontx2.rst index 610de99b728a..d33a90dd44bf 100644 --- a/Documentation/networking/devlink/octeontx2.rst +++ b/Documentation/networking/devlink/octeontx2.rst @@ -40,3 +40,19 @@ The ``octeontx2 AF`` driver implements the following driver-specific parameters. - runtime - Use to set the quantum which hardware uses for scheduling among transmit queues. Hardware uses weighted DWRR algorithm to schedule among all transmit queues. + +The ``octeontx2 PF`` driver implements the following driver-specific parameters. + +.. list-table:: Driver-specific parameters implemented + :widths: 5 5 5 85 + + * - Name + - Type + - Mode + - Description + * - ``unicast_filter_count`` + - u8 + - runtime + - Set the maximum number of unicast filters that can be programmed for + the device. This can be used to achieve better device resource + utilization, avoiding over consumption of unused MCAM table entries. diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst index cd5574005dba..d1af04b952f8 100644 --- a/Documentation/networking/index.rst +++ b/Documentation/networking/index.rst @@ -106,6 +106,7 @@ Contents: seg6-sysctl skbuff smc-sysctl + sriov statistics strparser switchdev diff --git a/Documentation/networking/sriov.rst b/Documentation/networking/sriov.rst new file mode 100644 index 000000000000..5deb4ff3154f --- /dev/null +++ b/Documentation/networking/sriov.rst @@ -0,0 +1,25 @@ +.. SPDX-License-Identifier: GPL-2.0 + +=============== +NIC SR-IOV APIs +=============== + +Modern NICs are strongly encouraged to focus on implementing the ``switchdev`` +model (see :ref:`switchdev`) to configure forwarding and security of SR-IOV +functionality. + +Legacy API +========== + +The old SR-IOV API is implemented in ``rtnetlink`` Netlink family as part of +the ``RTM_GETLINK`` and ``RTM_SETLINK`` commands. On the driver side +it consists of a number of ``ndo_set_vf_*`` and ``ndo_get_vf_*`` callbacks. + +Since the legacy APIs do not integrate well with the rest of the stack +the API is considered frozen; no new functionality or extensions +will be accepted. New drivers should not implement the uncommon callbacks; +namely the following callbacks are off limits: + + - ``ndo_get_vf_port`` + - ``ndo_set_vf_port`` + - ``ndo_set_vf_rss_query_en`` diff --git a/Documentation/userspace-api/index.rst b/Documentation/userspace-api/index.rst index 5926115ec0ed..8a251d71fa6e 100644 --- a/Documentation/userspace-api/index.rst +++ b/Documentation/userspace-api/index.rst @@ -32,6 +32,7 @@ Security-related interfaces seccomp_filter landlock lsm + mfd_noexec spec_ctrl tee diff --git a/Documentation/userspace-api/mfd_noexec.rst b/Documentation/userspace-api/mfd_noexec.rst new file mode 100644 index 000000000000..7afcc480e38f --- /dev/null +++ b/Documentation/userspace-api/mfd_noexec.rst @@ -0,0 +1,86 @@ +.. SPDX-License-Identifier: GPL-2.0 + +================================== +Introduction of non-executable mfd +================================== +:Author: + Daniel Verkamp <[email protected]> + Jeff Xu <[email protected]> + +:Contributor: + Aleksa Sarai <[email protected]> + +Since Linux introduced the memfd feature, memfds have always had their +execute bit set, and the memfd_create() syscall doesn't allow setting +it differently. + +However, in a secure-by-default system, such as ChromeOS, (where all +executables should come from the rootfs, which is protected by verified +boot), this executable nature of memfd opens a door for NoExec bypass +and enables “confused deputy attack”. E.g, in VRP bug [1]: cros_vm +process created a memfd to share the content with an external process, +however the memfd is overwritten and used for executing arbitrary code +and root escalation. [2] lists more VRP of this kind. + +On the other hand, executable memfd has its legit use: runc uses memfd’s +seal and executable feature to copy the contents of the binary then +execute them. For such a system, we need a solution to differentiate runc's +use of executable memfds and an attacker's [3]. + +To address those above: + - Let memfd_create() set X bit at creation time. + - Let memfd be sealed for modifying X bit when NX is set. + - Add a new pid namespace sysctl: vm.memfd_noexec to help applications in + migrating and enforcing non-executable MFD. + +User API +======== +``int memfd_create(const char *name, unsigned int flags)`` + +``MFD_NOEXEC_SEAL`` + When MFD_NOEXEC_SEAL bit is set in the ``flags``, memfd is created + with NX. F_SEAL_EXEC is set and the memfd can't be modified to + add X later. MFD_ALLOW_SEALING is also implied. + This is the most common case for the application to use memfd. + +``MFD_EXEC`` + When MFD_EXEC bit is set in the ``flags``, memfd is created with X. + +Note: + ``MFD_NOEXEC_SEAL`` implies ``MFD_ALLOW_SEALING``. In case that + an app doesn't want sealing, it can add F_SEAL_SEAL after creation. + + +Sysctl: +======== +``pid namespaced sysctl vm.memfd_noexec`` + +The new pid namespaced sysctl vm.memfd_noexec has 3 values: + + - 0: MEMFD_NOEXEC_SCOPE_EXEC + memfd_create() without MFD_EXEC nor MFD_NOEXEC_SEAL acts like + MFD_EXEC was set. + + - 1: MEMFD_NOEXEC_SCOPE_NOEXEC_SEAL + memfd_create() without MFD_EXEC nor MFD_NOEXEC_SEAL acts like + MFD_NOEXEC_SEAL was set. + + - 2: MEMFD_NOEXEC_SCOPE_NOEXEC_ENFORCED + memfd_create() without MFD_NOEXEC_SEAL will be rejected. + +The sysctl allows finer control of memfd_create for old software that +doesn't set the executable bit; for example, a container with +vm.memfd_noexec=1 means the old software will create non-executable memfd +by default while new software can create executable memfd by setting +MFD_EXEC. + +The value of vm.memfd_noexec is passed to child namespace at creation +time. In addition, the setting is hierarchical, i.e. during memfd_create, +we will search from current ns to root ns and use the most restrictive +setting. + +[1] https://crbug.com/1305267 + +[2] https://bugs.chromium.org/p/chromium/issues/list?q=type%3Dbug-security%20memfd%20escalation&can=1 + +[3] https://lwn.net/Articles/781013/ diff --git a/Documentation/virt/hyperv/clocks.rst b/Documentation/virt/hyperv/clocks.rst index a56f4837d443..176043265803 100644 --- a/Documentation/virt/hyperv/clocks.rst +++ b/Documentation/virt/hyperv/clocks.rst @@ -62,12 +62,21 @@ shared page with scale and offset values into user space. User space code performs the same algorithm of reading the TSC and applying the scale and offset to get the constant 10 MHz clock. -Linux clockevents are based on Hyper-V synthetic timer 0. While -Hyper-V offers 4 synthetic timers for each CPU, Linux only uses -timer 0. Interrupts from stimer0 are recorded on the "HVS" line in -/proc/interrupts. Clockevents based on the virtualized PIT and -local APIC timer also work, but the Hyper-V synthetic timer is -preferred. +Linux clockevents are based on Hyper-V synthetic timer 0 (stimer0). +While Hyper-V offers 4 synthetic timers for each CPU, Linux only uses +timer 0. In older versions of Hyper-V, an interrupt from stimer0 +results in a VMBus control message that is demultiplexed by +vmbus_isr() as described in the Documentation/virt/hyperv/vmbus.rst +documentation. In newer versions of Hyper-V, stimer0 interrupts can +be mapped to an architectural interrupt, which is referred to as +"Direct Mode". Linux prefers to use Direct Mode when available. Since +x86/x64 doesn't support per-CPU interrupts, Direct Mode statically +allocates an x86 interrupt vector (HYPERV_STIMER0_VECTOR) across all CPUs +and explicitly codes it to call the stimer0 interrupt handler. Hence +interrupts from stimer0 are recorded on the "HVS" line in /proc/interrupts +rather than being associated with a Linux IRQ. Clockevents based on the +virtualized PIT and local APIC timer also work, but Hyper-V stimer0 +is preferred. The driver for the Hyper-V synthetic system clock and timers is drivers/clocksource/hyperv_timer.c. diff --git a/Documentation/virt/hyperv/overview.rst b/Documentation/virt/hyperv/overview.rst index cd493332c88a..77408a89d1a4 100644 --- a/Documentation/virt/hyperv/overview.rst +++ b/Documentation/virt/hyperv/overview.rst @@ -40,7 +40,7 @@ Linux guests communicate with Hyper-V in four different ways: arm64, these synthetic registers must be accessed using explicit hypercalls. -* VMbus: VMbus is a higher-level software construct that is built on +* VMBus: VMBus is a higher-level software construct that is built on the other 3 mechanisms. It is a message passing interface between the Hyper-V host and the Linux guest. It uses memory that is shared between Hyper-V and the guest, along with various signaling @@ -54,8 +54,8 @@ x86/x64 architecture only. .. _Hyper-V Top Level Functional Spec (TLFS): https://docs.microsoft.com/en-us/virtualization/hyper-v-on-windows/tlfs/tlfs -VMbus is not documented. This documentation provides a high-level -overview of VMbus and how it works, but the details can be discerned +VMBus is not documented. This documentation provides a high-level +overview of VMBus and how it works, but the details can be discerned only from the code. Sharing Memory @@ -74,7 +74,7 @@ follows: physical address space. How Hyper-V is told about the GPA or list of GPAs varies. In some cases, a single GPA is written to a synthetic register. In other cases, a GPA or list of GPAs is sent - in a VMbus message. + in a VMBus message. * Hyper-V translates the GPAs into "real" physical memory addresses, and creates a virtual mapping that it can use to access the memory. @@ -133,9 +133,9 @@ only the CPUs actually present in the VM, so Linux does not report any hot-add CPUs. A Linux guest CPU may be taken offline using the normal Linux -mechanisms, provided no VMbus channel interrupts are assigned to -the CPU. See the section on VMbus Interrupts for more details -on how VMbus channel interrupts can be re-assigned to permit +mechanisms, provided no VMBus channel interrupts are assigned to +the CPU. See the section on VMBus Interrupts for more details +on how VMBus channel interrupts can be re-assigned to permit taking a CPU offline. 32-bit and 64-bit @@ -169,14 +169,14 @@ and functionality. Hyper-V indicates feature/function availability via flags in synthetic MSRs that Hyper-V provides to the guest, and the guest code tests these flags. -VMbus has its own protocol version that is negotiated during the -initial VMbus connection from the guest to Hyper-V. This version +VMBus has its own protocol version that is negotiated during the +initial VMBus connection from the guest to Hyper-V. This version number is also output to dmesg during boot. This version number is checked in a few places in the code to determine if specific functionality is present. -Furthermore, each synthetic device on VMbus also has a protocol -version that is separate from the VMbus protocol version. Device +Furthermore, each synthetic device on VMBus also has a protocol +version that is separate from the VMBus protocol version. Device drivers for these synthetic devices typically negotiate the device protocol version, and may test that protocol version to determine if specific device functionality is present. diff --git a/Documentation/virt/hyperv/vmbus.rst b/Documentation/virt/hyperv/vmbus.rst index d2012d9022c5..1dcef6a7fda3 100644 --- a/Documentation/virt/hyperv/vmbus.rst +++ b/Documentation/virt/hyperv/vmbus.rst @@ -1,8 +1,8 @@ .. SPDX-License-Identifier: GPL-2.0 -VMbus +VMBus ===== -VMbus is a software construct provided by Hyper-V to guest VMs. It +VMBus is a software construct provided by Hyper-V to guest VMs. It consists of a control path and common facilities used by synthetic devices that Hyper-V presents to guest VMs. The control path is used to offer synthetic devices to the guest VM and, in some cases, @@ -12,9 +12,9 @@ and the synthetic device implementation that is part of Hyper-V, and signaling primitives to allow Hyper-V and the guest to interrupt each other. -VMbus is modeled in Linux as a bus, with the expected /sys/bus/vmbus -entry in a running Linux guest. The VMbus driver (drivers/hv/vmbus_drv.c) -establishes the VMbus control path with the Hyper-V host, then +VMBus is modeled in Linux as a bus, with the expected /sys/bus/vmbus +entry in a running Linux guest. The VMBus driver (drivers/hv/vmbus_drv.c) +establishes the VMBus control path with the Hyper-V host, then registers itself as a Linux bus driver. It implements the standard bus functions for adding and removing devices to/from the bus. @@ -49,9 +49,9 @@ synthetic NIC is referred to as "netvsc" and the Linux driver for the synthetic SCSI controller is "storvsc". These drivers contain functions with names like "storvsc_connect_to_vsp". -VMbus channels +VMBus channels -------------- -An instance of a synthetic device uses VMbus channels to communicate +An instance of a synthetic device uses VMBus channels to communicate between the VSP and the VSC. Channels are bi-directional and used for passing messages. Most synthetic devices use a single channel, but the synthetic SCSI controller and synthetic NIC may use multiple @@ -73,7 +73,7 @@ write indices and some control flags, followed by the memory for the actual ring. The size of the ring is determined by the VSC in the guest and is specific to each synthetic device. The list of GPAs making up the ring is communicated to the Hyper-V host over the -VMbus control path as a GPA Descriptor List (GPADL). See function +VMBus control path as a GPA Descriptor List (GPADL). See function vmbus_establish_gpadl(). Each ring buffer is mapped into contiguous Linux kernel virtual @@ -102,10 +102,10 @@ resources. For Windows Server 2019 and later, this limit is approximately 1280 Mbytes. For versions prior to Windows Server 2019, the limit is approximately 384 Mbytes. -VMbus messages --------------- -All VMbus messages have a standard header that includes the message -length, the offset of the message payload, some flags, and a +VMBus channel messages +---------------------- +All messages sent in a VMBus channel have a standard header that includes +the message length, the offset of the message payload, some flags, and a transactionID. The portion of the message after the header is unique to each VSP/VSC pair. @@ -137,7 +137,7 @@ control message contains a list of GPAs that describe the data buffer. For example, the storvsc driver uses this approach to specify the data buffers to/from which disk I/O is done. -Three functions exist to send VMbus messages: +Three functions exist to send VMBus channel messages: 1. vmbus_sendpacket(): Control-only messages and messages with embedded data -- no GPAs @@ -154,20 +154,51 @@ Historically, Linux guests have trusted Hyper-V to send well-formed and valid messages, and Linux drivers for synthetic devices did not fully validate messages. With the introduction of processor technologies that fully encrypt guest memory and that allow the -guest to not trust the hypervisor (AMD SNP-SEV, Intel TDX), trusting +guest to not trust the hypervisor (AMD SEV-SNP, Intel TDX), trusting the Hyper-V host is no longer a valid assumption. The drivers for -VMbus synthetic devices are being updated to fully validate any +VMBus synthetic devices are being updated to fully validate any values read from memory that is shared with Hyper-V, which includes -messages from VMbus devices. To facilitate such validation, +messages from VMBus devices. To facilitate such validation, messages read by the guest from the "in" ring buffer are copied to a temporary buffer that is not shared with Hyper-V. Validation is performed in this temporary buffer without the risk of Hyper-V maliciously modifying the message after it is validated but before it is used. -VMbus interrupts +Synthetic Interrupt Controller (synic) +-------------------------------------- +Hyper-V provides each guest CPU with a synthetic interrupt controller +that is used by VMBus for host-guest communication. While each synic +defines 16 synthetic interrupts (SINT), Linux uses only one of the 16 +(VMBUS_MESSAGE_SINT). All interrupts related to communication between +the Hyper-V host and a guest CPU use that SINT. + +The SINT is mapped to a single per-CPU architectural interrupt (i.e, +an 8-bit x86/x64 interrupt vector, or an arm64 PPI INTID). Because +each CPU in the guest has a synic and may receive VMBus interrupts, +they are best modeled in Linux as per-CPU interrupts. This model works +well on arm64 where a single per-CPU Linux IRQ is allocated for +VMBUS_MESSAGE_SINT. This IRQ appears in /proc/interrupts as an IRQ labelled +"Hyper-V VMbus". Since x86/x64 lacks support for per-CPU IRQs, an x86 +interrupt vector is statically allocated (HYPERVISOR_CALLBACK_VECTOR) +across all CPUs and explicitly coded to call vmbus_isr(). In this case, +there's no Linux IRQ, and the interrupts are visible in aggregate in +/proc/interrupts on the "HYP" line. + +The synic provides the means to demultiplex the architectural interrupt into +one or more logical interrupts and route the logical interrupt to the proper +VMBus handler in Linux. This demultiplexing is done by vmbus_isr() and +related functions that access synic data structures. + +The synic is not modeled in Linux as an irq chip or irq domain, +and the demultiplexed logical interrupts are not Linux IRQs. As such, +they don't appear in /proc/interrupts or /proc/irq. The CPU +affinity for one of these logical interrupts is controlled via an +entry under /sys/bus/vmbus as described below. + +VMBus interrupts ---------------- -VMbus provides a mechanism for the guest to interrupt the host when +VMBus provides a mechanism for the guest to interrupt the host when the guest has queued new messages in a ring buffer. The host expects that the guest will send an interrupt only when an "out" ring buffer transitions from empty to non-empty. If the guest sends @@ -176,63 +207,55 @@ unnecessary. If a guest sends an excessive number of unnecessary interrupts, the host may throttle that guest by suspending its execution for a few seconds to prevent a denial-of-service attack. -Similarly, the host will interrupt the guest when it sends a new -message on the VMbus control path, or when a VMbus channel "in" ring -buffer transitions from empty to non-empty. Each CPU in the guest -may receive VMbus interrupts, so they are best modeled as per-CPU -interrupts in Linux. This model works well on arm64 where a single -per-CPU IRQ is allocated for VMbus. Since x86/x64 lacks support for -per-CPU IRQs, an x86 interrupt vector is statically allocated (see -HYPERVISOR_CALLBACK_VECTOR) across all CPUs and explicitly coded to -call the VMbus interrupt service routine. These interrupts are -visible in /proc/interrupts on the "HYP" line. - -The guest CPU that a VMbus channel will interrupt is selected by the +Similarly, the host will interrupt the guest via the synic when +it sends a new message on the VMBus control path, or when a VMBus +channel "in" ring buffer transitions from empty to non-empty due to +the host inserting a new VMBus channel message. The control message stream +and each VMBus channel "in" ring buffer are separate logical interrupts +that are demultiplexed by vmbus_isr(). It demultiplexes by first checking +for channel interrupts by calling vmbus_chan_sched(), which looks at a synic +bitmap to determine which channels have pending interrupts on this CPU. +If multiple channels have pending interrupts for this CPU, they are +processed sequentially. When all channel interrupts have been processed, +vmbus_isr() checks for and processes any messages received on the VMBus +control path. + +The guest CPU that a VMBus channel will interrupt is selected by the guest when the channel is created, and the host is informed of that -selection. VMbus devices are broadly grouped into two categories: +selection. VMBus devices are broadly grouped into two categories: -1. "Slow" devices that need only one VMbus channel. The devices +1. "Slow" devices that need only one VMBus channel. The devices (such as keyboard, mouse, heartbeat, and timesync) generate - relatively few interrupts. Their VMbus channels are all + relatively few interrupts. Their VMBus channels are all assigned to interrupt the VMBUS_CONNECT_CPU, which is always CPU 0. -2. "High speed" devices that may use multiple VMbus channels for +2. "High speed" devices that may use multiple VMBus channels for higher parallelism and performance. These devices include the - synthetic SCSI controller and synthetic NIC. Their VMbus + synthetic SCSI controller and synthetic NIC. Their VMBus channels interrupts are assigned to CPUs that are spread out among the available CPUs in the VM so that interrupts on multiple channels can be processed in parallel. -The assignment of VMbus channel interrupts to CPUs is done in the +The assignment of VMBus channel interrupts to CPUs is done in the function init_vp_index(). This assignment is done outside of the normal Linux interrupt affinity mechanism, so the interrupts are neither "unmanaged" nor "managed" interrupts. -The CPU that a VMbus channel will interrupt can be seen in +The CPU that a VMBus channel will interrupt can be seen in /sys/bus/vmbus/devices/<deviceGUID>/ channels/<channelRelID>/cpu. When running on later versions of Hyper-V, the CPU can be changed -by writing a new value to this sysfs entry. Because the interrupt -assignment is done outside of the normal Linux affinity mechanism, -there are no entries in /proc/irq corresponding to individual -VMbus channel interrupts. +by writing a new value to this sysfs entry. Because VMBus channel +interrupts are not Linux IRQs, there are no entries in /proc/interrupts +or /proc/irq corresponding to individual VMBus channel interrupts. An online CPU in a Linux guest may not be taken offline if it has -VMbus channel interrupts assigned to it. Any such channel +VMBus channel interrupts assigned to it. Any such channel interrupts must first be manually reassigned to another CPU as described above. When no channel interrupts are assigned to the CPU, it can be taken offline. -When a guest CPU receives a VMbus interrupt from the host, the -function vmbus_isr() handles the interrupt. It first checks for -channel interrupts by calling vmbus_chan_sched(), which looks at a -bitmap setup by the host to determine which channels have pending -interrupts on this CPU. If multiple channels have pending -interrupts for this CPU, they are processed sequentially. When all -channel interrupts have been processed, vmbus_isr() checks for and -processes any message received on the VMbus control path. - -The VMbus channel interrupt handling code is designed to work +The VMBus channel interrupt handling code is designed to work correctly even if an interrupt is received on a CPU other than the CPU assigned to the channel. Specifically, the code does not use CPU-based exclusion for correctness. In normal operation, Hyper-V @@ -242,23 +265,23 @@ when Hyper-V will make the transition. The code must work correctly even if there is a time lag before Hyper-V starts interrupting the new CPU. See comments in target_cpu_store(). -VMbus device creation/deletion +VMBus device creation/deletion ------------------------------ Hyper-V and the Linux guest have a separate message-passing path that is used for synthetic device creation and deletion. This -path does not use a VMbus channel. See vmbus_post_msg() and +path does not use a VMBus channel. See vmbus_post_msg() and vmbus_on_msg_dpc(). The first step is for the guest to connect to the generic -Hyper-V VMbus mechanism. As part of establishing this connection, -the guest and Hyper-V agree on a VMbus protocol version they will +Hyper-V VMBus mechanism. As part of establishing this connection, +the guest and Hyper-V agree on a VMBus protocol version they will use. This negotiation allows newer Linux kernels to run on older Hyper-V versions, and vice versa. The guest then tells Hyper-V to "send offers". Hyper-V sends an offer message to the guest for each synthetic device that the VM -is configured to have. Each VMbus device type has a fixed GUID -known as the "class ID", and each VMbus device instance is also +is configured to have. Each VMBus device type has a fixed GUID +known as the "class ID", and each VMBus device instance is also identified by a GUID. The offer message from Hyper-V contains both GUIDs to uniquely (within the VM) identify the device. There is one offer message for each device instance, so a VM with @@ -275,7 +298,7 @@ type based on the class ID, and invokes the correct driver to set up the device. Driver/device matching is performed using the standard Linux mechanism. -The device driver probe function opens the primary VMbus channel to +The device driver probe function opens the primary VMBus channel to the corresponding VSP. It allocates guest memory for the channel ring buffers and shares the ring buffer with the Hyper-V host by giving the host a list of GPAs for the ring buffer memory. See @@ -285,7 +308,7 @@ Once the ring buffer is set up, the device driver and VSP exchange setup messages via the primary channel. These messages may include negotiating the device protocol version to be used between the Linux VSC and the VSP on the Hyper-V host. The setup messages may also -include creating additional VMbus channels, which are somewhat +include creating additional VMBus channels, which are somewhat mis-named as "sub-channels" since they are functionally equivalent to the primary channel once they are created. diff --git a/MAINTAINERS b/MAINTAINERS index 17e3fa3eb6fd..0e3cb040fc16 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3980,7 +3980,7 @@ R: Song Liu <[email protected]> R: Yonghong Song <[email protected]> R: John Fastabend <[email protected]> R: KP Singh <[email protected]> -R: Stanislav Fomichev <[email protected]> +R: Stanislav Fomichev <[email protected]> R: Hao Luo <[email protected]> R: Jiri Olsa <[email protected]> @@ -5296,7 +5296,7 @@ F: drivers/infiniband/hw/usnic/ CLANG CONTROL FLOW INTEGRITY SUPPORT M: Sami Tolvanen <[email protected]> -M: Kees Cook <[email protected]> +M: Kees Cook <[email protected]> R: Nathan Chancellor <[email protected]> S: Supported @@ -8212,7 +8212,7 @@ F: rust/kernel/net/phy.rs EXEC & BINFMT API, ELF R: Eric Biederman <[email protected]> -R: Kees Cook <[email protected]> +R: Kees Cook <[email protected]> S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/execve @@ -8613,7 +8613,7 @@ S: Maintained F: drivers/net/ethernet/nvidia/* FORTIFY_SOURCE -M: Kees Cook <[email protected]> +M: Kees Cook <[email protected]> S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/hardening @@ -8810,14 +8810,14 @@ M: Madalin Bucur <[email protected]> R: Sean Anderson <[email protected]> S: Maintained -F: Documentation/devicetree/bindings/net/fsl-fman.txt +F: Documentation/devicetree/bindings/net/fsl-fman.yaml F: drivers/net/ethernet/freescale/fman FREESCALE QORIQ PTP CLOCK DRIVER M: Yangbo Lu <[email protected]> S: Maintained -F: Documentation/devicetree/bindings/ptp/ptp-qoriq.txt +F: Documentation/devicetree/bindings/ptp/fsl,ptp.yaml F: drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp* F: drivers/net/ethernet/freescale/dpaa2/dprtc* F: drivers/net/ethernet/freescale/enetc/enetc_ptp.c @@ -9103,7 +9103,7 @@ F: include/linux/mfd/gsc.h F: include/linux/platform_data/gsc_hwmon.h GCC PLUGINS -M: Kees Cook <[email protected]> +M: Kees Cook <[email protected]> S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/hardening @@ -9237,7 +9237,7 @@ S: Maintained F: drivers/input/touchscreen/resistive-adc-touch.c GENERIC STRING LIBRARY -M: Kees Cook <[email protected]> +M: Kees Cook <[email protected]> R: Andy Shevchenko <[email protected]> S: Supported @@ -11035,8 +11035,8 @@ F: include/uapi/drm/i915_drm.h INTEL DRM XE DRIVER (Lunar Lake and newer) M: Lucas De Marchi <[email protected]> -M: Oded Gabbay <[email protected]> M: Thomas Hellström <[email protected]> +M: Rodrigo Vivi <[email protected]> S: Supported W: https://drm.pages.freedesktop.org/intel-docs/ @@ -11951,7 +11951,7 @@ F: scripts/package/ F: usr/ KERNEL HARDENING (not covered by other areas) -M: Kees Cook <[email protected]> +M: Kees Cook <[email protected]> R: Gustavo A. R. Silva <[email protected]> S: Supported @@ -12480,7 +12480,7 @@ F: drivers/scsi/53c700* LEAKING_ADDRESSES M: Tycho Andersen <[email protected]> -R: Kees Cook <[email protected]> +R: Kees Cook <[email protected]> S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/hardening @@ -12776,7 +12776,7 @@ F: arch/powerpc/platforms/8xx/ F: arch/powerpc/platforms/83xx/ LINUX KERNEL DUMP TEST MODULE (LKDTM) -M: Kees Cook <[email protected]> +M: Kees Cook <[email protected]> S: Maintained F: drivers/misc/lkdtm/* F: tools/testing/selftests/lkdtm/* @@ -12906,7 +12906,7 @@ Q: http://patchwork.linuxtv.org/project/linux-media/list/ F: drivers/media/usb/dvb-usb-v2/lmedm04* LOADPIN SECURITY MODULE -M: Kees Cook <[email protected]> +M: Kees Cook <[email protected]> S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/hardening F: Documentation/admin-guide/LSM/LoadPin.rst @@ -17998,7 +17998,7 @@ F: tools/testing/selftests/proc/ PROC SYSCTL M: Luis Chamberlain <[email protected]> -M: Kees Cook <[email protected]> +M: Kees Cook <[email protected]> M: Joel Granados <[email protected]> @@ -18054,7 +18054,7 @@ F: Documentation/devicetree/bindings/net/pse-pd/ F: drivers/net/pse-pd/ PSTORE FILESYSTEM -M: Kees Cook <[email protected]> +M: Kees Cook <[email protected]> R: Tony Luck <[email protected]> R: Guilherme G. Piccoli <[email protected]> @@ -19033,6 +19033,14 @@ F: drivers/net/ethernet/renesas/Makefile F: drivers/net/ethernet/renesas/rcar_gen4* F: drivers/net/ethernet/renesas/rswitch* +RENESAS ETHERNET TSN DRIVER +M: Niklas Söderlund <[email protected]> +S: Supported +F: Documentation/devicetree/bindings/net/renesas,ethertsn.yaml +F: drivers/net/ethernet/renesas/rtsn.* + RENESAS IDT821034 ASoC CODEC M: Herve Codina <[email protected]> L: [email protected] (moderated for non-subscribers) @@ -20060,7 +20068,7 @@ F: drivers/media/cec/platform/seco/seco-cec.c F: drivers/media/cec/platform/seco/seco-cec.h SECURE COMPUTING -M: Kees Cook <[email protected]> +M: Kees Cook <[email protected]> R: Andy Lutomirski <[email protected]> R: Will Drewry <[email protected]> S: Supported @@ -22974,7 +22982,7 @@ F: drivers/block/ublk_drv.c F: include/uapi/linux/ublk_cmd.h UBSAN -M: Kees Cook <[email protected]> +M: Kees Cook <[email protected]> R: Marco Elver <[email protected]> R: Andrey Konovalov <[email protected]> R: Andrey Ryabinin <[email protected]> @@ -23976,7 +23984,6 @@ VMALLOC M: Andrew Morton <[email protected]> R: Uladzislau Rezki <[email protected]> R: Christoph Hellwig <[email protected]> -R: Lorenzo Stoakes <[email protected]> S: Maintained W: http://www.linux-mm.org @@ -24812,7 +24819,7 @@ F: drivers/net/hamradio/yam* F: include/linux/yam.h YAMA SECURITY MODULE -M: Kees Cook <[email protected]> +M: Kees Cook <[email protected]> S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/hardening F: Documentation/admin-guide/LSM/Yama.rst @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 10 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc4 NAME = Baby Opossum Posse # *DOCUMENTATION* diff --git a/arch/arm/boot/dts/rockchip/rk3066a.dtsi b/arch/arm/boot/dts/rockchip/rk3066a.dtsi index 30139f21de64..51ae0418a7db 100644 --- a/arch/arm/boot/dts/rockchip/rk3066a.dtsi +++ b/arch/arm/boot/dts/rockchip/rk3066a.dtsi @@ -879,7 +879,3 @@ &wdt { compatible = "rockchip,rk3066-wdt", "snps,dw-wdt"; }; - -&emac { - compatible = "rockchip,rk3066-emac"; -}; diff --git a/arch/arm/boot/dts/rockchip/rk3xxx.dtsi b/arch/arm/boot/dts/rockchip/rk3xxx.dtsi index f37137f298d5..e6a78bcf9163 100644 --- a/arch/arm/boot/dts/rockchip/rk3xxx.dtsi +++ b/arch/arm/boot/dts/rockchip/rk3xxx.dtsi @@ -194,17 +194,14 @@ }; emac: ethernet@10204000 { - compatible = "snps,arc-emac"; + compatible = "rockchip,rk3066-emac"; reg = <0x10204000 0x3c>; interrupts = <GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH>; - - rockchip,grf = <&grf>; - clocks = <&cru HCLK_EMAC>, <&cru SCLK_MAC>; clock-names = "hclk", "macref"; max-speed = <100>; phy-mode = "rmii"; - + rockchip,grf = <&grf>; status = "disabled"; }; diff --git a/arch/arm/include/asm/efi.h b/arch/arm/include/asm/efi.h index 78282ced5038..e408399d5f0e 100644 --- a/arch/arm/include/asm/efi.h +++ b/arch/arm/include/asm/efi.h @@ -14,6 +14,7 @@ #include <asm/mach/map.h> #include <asm/mmu_context.h> #include <asm/ptrace.h> +#include <asm/uaccess.h> #ifdef CONFIG_EFI void efi_init(void); @@ -25,6 +26,18 @@ int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md, boo #define arch_efi_call_virt_setup() efi_virtmap_load() #define arch_efi_call_virt_teardown() efi_virtmap_unload() +#ifdef CONFIG_CPU_TTBR0_PAN +#undef arch_efi_call_virt +#define arch_efi_call_virt(p, f, args...) ({ \ + unsigned int flags = uaccess_save_and_enable(); \ + efi_status_t res = _Generic((p)->f(args), \ + efi_status_t: (p)->f(args), \ + default: ((p)->f(args), EFI_ABORTED)); \ + uaccess_restore(flags); \ + res; \ +}) +#endif + #define ARCH_EFI_IRQ_FLAGS_MASK \ (PSR_J_BIT | PSR_E_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT | \ PSR_T_BIT | MODE_MASK) diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index 4a92096db34e..712718aed5dd 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -9,6 +9,7 @@ #include <linux/efi.h> #include <linux/init.h> +#include <linux/kmemleak.h> #include <linux/screen_info.h> #include <linux/vmalloc.h> @@ -213,6 +214,7 @@ l: if (!p) { return -ENOMEM; } + kmemleak_not_leak(p); efi_rt_stack_top = p + THREAD_SIZE; return 0; } diff --git a/arch/mips/bmips/setup.c b/arch/mips/bmips/setup.c index ec180ab92eaa..66a8ba19c287 100644 --- a/arch/mips/bmips/setup.c +++ b/arch/mips/bmips/setup.c @@ -110,7 +110,8 @@ static void bcm6358_quirks(void) * RAC flush causes kernel panics on BCM6358 when booting from TP1 * because the bootloader is not initializing it properly. */ - bmips_rac_flush_disable = !!(read_c0_brcm_cmt_local() & (1 << 31)); + bmips_rac_flush_disable = !!(read_c0_brcm_cmt_local() & (1 << 31)) || + !!BMIPS_GET_CBR(); } static void bcm6368_quirks(void) diff --git a/arch/mips/pci/ops-rc32434.c b/arch/mips/pci/ops-rc32434.c index 874ed6df9768..34b9323bdabb 100644 --- a/arch/mips/pci/ops-rc32434.c +++ b/arch/mips/pci/ops-rc32434.c @@ -112,8 +112,8 @@ retry: * gives them time to settle */ if (where == PCI_VENDOR_ID) { - if (ret == 0xffffffff || ret == 0x00000000 || - ret == 0x0000ffff || ret == 0xffff0000) { + if (*val == 0xffffffff || *val == 0x00000000 || + *val == 0x0000ffff || *val == 0xffff0000) { if (delay > 4) return 0; delay *= 2; diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h index ba4c05bc24d6..8394718870e1 100644 --- a/arch/parisc/include/asm/cacheflush.h +++ b/arch/parisc/include/asm/cacheflush.h @@ -31,18 +31,17 @@ void flush_cache_all_local(void); void flush_cache_all(void); void flush_cache_mm(struct mm_struct *mm); -void flush_kernel_dcache_page_addr(const void *addr); - #define flush_kernel_dcache_range(start,size) \ flush_kernel_dcache_range_asm((start), (start)+(size)); +/* The only way to flush a vmap range is to flush whole cache */ #define ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE 1 void flush_kernel_vmap_range(void *vaddr, int size); void invalidate_kernel_vmap_range(void *vaddr, int size); -#define flush_cache_vmap(start, end) flush_cache_all() +void flush_cache_vmap(unsigned long start, unsigned long end); #define flush_cache_vmap_early(start, end) do { } while (0) -#define flush_cache_vunmap(start, end) flush_cache_all() +void flush_cache_vunmap(unsigned long start, unsigned long end); void flush_dcache_folio(struct folio *folio); #define flush_dcache_folio flush_dcache_folio @@ -77,17 +76,11 @@ void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); -/* defined in pacache.S exported in cache.c used by flush_anon_page */ -void flush_dcache_page_asm(unsigned long phys_addr, unsigned long vaddr); - #define ARCH_HAS_FLUSH_ANON_PAGE void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr); #define ARCH_HAS_FLUSH_ON_KUNMAP -static inline void kunmap_flush_on_unmap(const void *addr) -{ - flush_kernel_dcache_page_addr(addr); -} +void kunmap_flush_on_unmap(const void *addr); #endif /* _PARISC_CACHEFLUSH_H */ diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index 974accac05cd..babf65751e81 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -448,14 +448,17 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte) return pte; } +static inline pte_t ptep_get(pte_t *ptep) +{ + return READ_ONCE(*ptep); +} +#define ptep_get ptep_get + static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { pte_t pte; - if (!pte_young(*ptep)) - return 0; - - pte = *ptep; + pte = ptep_get(ptep); if (!pte_young(pte)) { return 0; } @@ -463,17 +466,10 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned return 1; } -struct mm_struct; -static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) -{ - pte_t old_pte; - - old_pte = *ptep; - set_pte(ptep, __pte(0)); - - return old_pte; -} +int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); +pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); +struct mm_struct; static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { set_pte(ptep, pte_wrprotect(*ptep)); @@ -511,7 +507,8 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, #define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG -#define __HAVE_ARCH_PTEP_GET_AND_CLEAR +#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH +#define __HAVE_ARCH_PTEP_CLEAR_FLUSH #define __HAVE_ARCH_PTEP_SET_WRPROTECT #define __HAVE_ARCH_PTE_SAME diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c index 422f3e1e6d9c..483bfafd930c 100644 --- a/arch/parisc/kernel/cache.c +++ b/arch/parisc/kernel/cache.c @@ -20,6 +20,7 @@ #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/syscalls.h> +#include <linux/vmalloc.h> #include <asm/pdc.h> #include <asm/cache.h> #include <asm/cacheflush.h> @@ -31,20 +32,31 @@ #include <asm/mmu_context.h> #include <asm/cachectl.h> +#define PTR_PAGE_ALIGN_DOWN(addr) PTR_ALIGN_DOWN(addr, PAGE_SIZE) + +/* + * When nonzero, use _PAGE_ACCESSED bit to try to reduce the number + * of page flushes done flush_cache_page_if_present. There are some + * pros and cons in using this option. It may increase the risk of + * random segmentation faults. + */ +#define CONFIG_FLUSH_PAGE_ACCESSED 0 + int split_tlb __ro_after_init; int dcache_stride __ro_after_init; int icache_stride __ro_after_init; EXPORT_SYMBOL(dcache_stride); +/* Internal implementation in arch/parisc/kernel/pacache.S */ void flush_dcache_page_asm(unsigned long phys_addr, unsigned long vaddr); EXPORT_SYMBOL(flush_dcache_page_asm); void purge_dcache_page_asm(unsigned long phys_addr, unsigned long vaddr); void flush_icache_page_asm(unsigned long phys_addr, unsigned long vaddr); - -/* Internal implementation in arch/parisc/kernel/pacache.S */ void flush_data_cache_local(void *); /* flushes local data-cache only */ void flush_instruction_cache_local(void); /* flushes local code-cache only */ +static void flush_kernel_dcache_page_addr(const void *addr); + /* On some machines (i.e., ones with the Merced bus), there can be * only a single PxTLB broadcast at a time; this must be guaranteed * by software. We need a spinlock around all TLB flushes to ensure @@ -321,6 +333,18 @@ __flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, { if (!static_branch_likely(&parisc_has_cache)) return; + + /* + * The TLB is the engine of coherence on parisc. The CPU is + * entitled to speculate any page with a TLB mapping, so here + * we kill the mapping then flush the page along a special flush + * only alias mapping. This guarantees that the page is no-longer + * in the cache for any process and nor may it be speculatively + * read in (until the user or kernel specifically accesses it, + * of course). + */ + flush_tlb_page(vma, vmaddr); + preempt_disable(); flush_dcache_page_asm(physaddr, vmaddr); if (vma->vm_flags & VM_EXEC) @@ -328,46 +352,44 @@ __flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, preempt_enable(); } -static void flush_user_cache_page(struct vm_area_struct *vma, unsigned long vmaddr) +static void flush_kernel_dcache_page_addr(const void *addr) { - unsigned long flags, space, pgd, prot; -#ifdef CONFIG_TLB_PTLOCK - unsigned long pgd_lock; -#endif + unsigned long vaddr = (unsigned long)addr; + unsigned long flags; - vmaddr &= PAGE_MASK; + /* Purge TLB entry to remove translation on all CPUs */ + purge_tlb_start(flags); + pdtlb(SR_KERNEL, addr); + purge_tlb_end(flags); + /* Use tmpalias flush to prevent data cache move-in */ preempt_disable(); + flush_dcache_page_asm(__pa(vaddr), vaddr); + preempt_enable(); +} - /* Set context for flush */ - local_irq_save(flags); - prot = mfctl(8); - space = mfsp(SR_USER); - pgd = mfctl(25); -#ifdef CONFIG_TLB_PTLOCK - pgd_lock = mfctl(28); -#endif - switch_mm_irqs_off(NULL, vma->vm_mm, NULL); - local_irq_restore(flags); - - flush_user_dcache_range_asm(vmaddr, vmaddr + PAGE_SIZE); - if (vma->vm_flags & VM_EXEC) - flush_user_icache_range_asm(vmaddr, vmaddr + PAGE_SIZE); - flush_tlb_page(vma, vmaddr); +static void flush_kernel_icache_page_addr(const void *addr) +{ + unsigned long vaddr = (unsigned long)addr; + unsigned long flags; - /* Restore previous context */ - local_irq_save(flags); -#ifdef CONFIG_TLB_PTLOCK - mtctl(pgd_lock, 28); -#endif - mtctl(pgd, 25); - mtsp(space, SR_USER); - mtctl(prot, 8); - local_irq_restore(flags); + /* Purge TLB entry to remove translation on all CPUs */ + purge_tlb_start(flags); + pdtlb(SR_KERNEL, addr); + purge_tlb_end(flags); + /* Use tmpalias flush to prevent instruction cache move-in */ + preempt_disable(); + flush_icache_page_asm(__pa(vaddr), vaddr); preempt_enable(); } +void kunmap_flush_on_unmap(const void *addr) +{ + flush_kernel_dcache_page_addr(addr); +} +EXPORT_SYMBOL(kunmap_flush_on_unmap); + void flush_icache_pages(struct vm_area_struct *vma, struct page *page, unsigned int nr) { @@ -375,13 +397,16 @@ void flush_icache_pages(struct vm_area_struct *vma, struct page *page, for (;;) { flush_kernel_dcache_page_addr(kaddr); - flush_kernel_icache_page(kaddr); + flush_kernel_icache_page_addr(kaddr); if (--nr == 0) break; kaddr += PAGE_SIZE; } } +/* + * Walk page directory for MM to find PTEP pointer for address ADDR. + */ static inline pte_t *get_ptep(struct mm_struct *mm, unsigned long addr) { pte_t *ptep = NULL; @@ -410,6 +435,41 @@ static inline bool pte_needs_flush(pte_t pte) == (_PAGE_PRESENT | _PAGE_ACCESSED); } +/* + * Return user physical address. Returns 0 if page is not present. + */ +static inline unsigned long get_upa(struct mm_struct *mm, unsigned long addr) +{ + unsigned long flags, space, pgd, prot, pa; +#ifdef CONFIG_TLB_PTLOCK + unsigned long pgd_lock; +#endif + + /* Save context */ + local_irq_save(flags); + prot = mfctl(8); + space = mfsp(SR_USER); + pgd = mfctl(25); +#ifdef CONFIG_TLB_PTLOCK + pgd_lock = mfctl(28); +#endif + + /* Set context for lpa_user */ + switch_mm_irqs_off(NULL, mm, NULL); + pa = lpa_user(addr); + + /* Restore previous context */ +#ifdef CONFIG_TLB_PTLOCK + mtctl(pgd_lock, 28); +#endif + mtctl(pgd, 25); + mtsp(space, SR_USER); + mtctl(prot, 8); + local_irq_restore(flags); + + return pa; +} + void flush_dcache_folio(struct folio *folio) { struct address_space *mapping = folio_flush_mapping(folio); @@ -458,50 +518,23 @@ void flush_dcache_folio(struct folio *folio) if (addr + nr * PAGE_SIZE > vma->vm_end) nr = (vma->vm_end - addr) / PAGE_SIZE; - if (parisc_requires_coherency()) { - for (i = 0; i < nr; i++) { - pte_t *ptep = get_ptep(vma->vm_mm, - addr + i * PAGE_SIZE); - if (!ptep) - continue; - if (pte_needs_flush(*ptep)) - flush_user_cache_page(vma, - addr + i * PAGE_SIZE); - /* Optimise accesses to the same table? */ - pte_unmap(ptep); - } - } else { + if (old_addr == 0 || (old_addr & (SHM_COLOUR - 1)) + != (addr & (SHM_COLOUR - 1))) { + for (i = 0; i < nr; i++) + __flush_cache_page(vma, + addr + i * PAGE_SIZE, + (pfn + i) * PAGE_SIZE); /* - * The TLB is the engine of coherence on parisc: - * The CPU is entitled to speculate any page - * with a TLB mapping, so here we kill the - * mapping then flush the page along a special - * flush only alias mapping. This guarantees that - * the page is no-longer in the cache for any - * process and nor may it be speculatively read - * in (until the user or kernel specifically - * accesses it, of course) + * Software is allowed to have any number + * of private mappings to a page. */ - for (i = 0; i < nr; i++) - flush_tlb_page(vma, addr + i * PAGE_SIZE); - if (old_addr == 0 || (old_addr & (SHM_COLOUR - 1)) - != (addr & (SHM_COLOUR - 1))) { - for (i = 0; i < nr; i++) - __flush_cache_page(vma, - addr + i * PAGE_SIZE, - (pfn + i) * PAGE_SIZE); - /* - * Software is allowed to have any number - * of private mappings to a page. - */ - if (!(vma->vm_flags & VM_SHARED)) - continue; - if (old_addr) - pr_err("INEQUIVALENT ALIASES 0x%lx and 0x%lx in file %pD\n", - old_addr, addr, vma->vm_file); - if (nr == folio_nr_pages(folio)) - old_addr = addr; - } + if (!(vma->vm_flags & VM_SHARED)) + continue; + if (old_addr) + pr_err("INEQUIVALENT ALIASES 0x%lx and 0x%lx in file %pD\n", + old_addr, addr, vma->vm_file); + if (nr == folio_nr_pages(folio)) + old_addr = addr; } WARN_ON(++count == 4096); } @@ -591,35 +624,28 @@ extern void purge_kernel_dcache_page_asm(unsigned long); extern void clear_user_page_asm(void *, unsigned long); extern void copy_user_page_asm(void *, void *, unsigned long); -void flush_kernel_dcache_page_addr(const void *addr) -{ - unsigned long flags; - - flush_kernel_dcache_page_asm(addr); - purge_tlb_start(flags); - pdtlb(SR_KERNEL, addr); - purge_tlb_end(flags); -} -EXPORT_SYMBOL(flush_kernel_dcache_page_addr); - static void flush_cache_page_if_present(struct vm_area_struct *vma, - unsigned long vmaddr, unsigned long pfn) + unsigned long vmaddr) { +#if CONFIG_FLUSH_PAGE_ACCESSED bool needs_flush = false; - pte_t *ptep; + pte_t *ptep, pte; - /* - * The pte check is racy and sometimes the flush will trigger - * a non-access TLB miss. Hopefully, the page has already been - * flushed. - */ ptep = get_ptep(vma->vm_mm, vmaddr); if (ptep) { - needs_flush = pte_needs_flush(*ptep); + pte = ptep_get(ptep); + needs_flush = pte_needs_flush(pte); pte_unmap(ptep); } if (needs_flush) - flush_cache_page(vma, vmaddr, pfn); + __flush_cache_page(vma, vmaddr, PFN_PHYS(pte_pfn(pte))); +#else + struct mm_struct *mm = vma->vm_mm; + unsigned long physaddr = get_upa(mm, vmaddr); + + if (physaddr) + __flush_cache_page(vma, vmaddr, PAGE_ALIGN_DOWN(physaddr)); +#endif } void copy_user_highpage(struct page *to, struct page *from, @@ -629,7 +655,7 @@ void copy_user_highpage(struct page *to, struct page *from, kfrom = kmap_local_page(from); kto = kmap_local_page(to); - flush_cache_page_if_present(vma, vaddr, page_to_pfn(from)); + __flush_cache_page(vma, vaddr, PFN_PHYS(page_to_pfn(from))); copy_page_asm(kto, kfrom); kunmap_local(kto); kunmap_local(kfrom); @@ -638,16 +664,17 @@ void copy_user_highpage(struct page *to, struct page *from, void copy_to_user_page(struct vm_area_struct *vma, struct page *page, unsigned long user_vaddr, void *dst, void *src, int len) { - flush_cache_page_if_present(vma, user_vaddr, page_to_pfn(page)); + __flush_cache_page(vma, user_vaddr, PFN_PHYS(page_to_pfn(page))); memcpy(dst, src, len); - flush_kernel_dcache_range_asm((unsigned long)dst, (unsigned long)dst + len); + flush_kernel_dcache_page_addr(PTR_PAGE_ALIGN_DOWN(dst)); } void copy_from_user_page(struct vm_area_struct *vma, struct page *page, unsigned long user_vaddr, void *dst, void *src, int len) { - flush_cache_page_if_present(vma, user_vaddr, page_to_pfn(page)); + __flush_cache_page(vma, user_vaddr, PFN_PHYS(page_to_pfn(page))); memcpy(dst, src, len); + flush_kernel_dcache_page_addr(PTR_PAGE_ALIGN_DOWN(src)); } /* __flush_tlb_range() @@ -681,32 +708,10 @@ int __flush_tlb_range(unsigned long sid, unsigned long start, static void flush_cache_pages(struct vm_area_struct *vma, unsigned long start, unsigned long end) { - unsigned long addr, pfn; - pte_t *ptep; - - for (addr = start; addr < end; addr += PAGE_SIZE) { - bool needs_flush = false; - /* - * The vma can contain pages that aren't present. Although - * the pte search is expensive, we need the pte to find the - * page pfn and to check whether the page should be flushed. - */ - ptep = get_ptep(vma->vm_mm, addr); - if (ptep) { - needs_flush = pte_needs_flush(*ptep); - pfn = pte_pfn(*ptep); - pte_unmap(ptep); - } - if (needs_flush) { - if (parisc_requires_coherency()) { - flush_user_cache_page(vma, addr); - } else { - if (WARN_ON(!pfn_valid(pfn))) - return; - __flush_cache_page(vma, addr, PFN_PHYS(pfn)); - } - } - } + unsigned long addr; + + for (addr = start; addr < end; addr += PAGE_SIZE) + flush_cache_page_if_present(vma, addr); } static inline unsigned long mm_total_size(struct mm_struct *mm) @@ -757,21 +762,19 @@ void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned if (WARN_ON(IS_ENABLED(CONFIG_SMP) && arch_irqs_disabled())) return; flush_tlb_range(vma, start, end); - flush_cache_all(); + if (vma->vm_flags & VM_EXEC) + flush_cache_all(); + else + flush_data_cache(); return; } - flush_cache_pages(vma, start, end); + flush_cache_pages(vma, start & PAGE_MASK, end); } void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long pfn) { - if (WARN_ON(!pfn_valid(pfn))) - return; - if (parisc_requires_coherency()) - flush_user_cache_page(vma, vmaddr); - else - __flush_cache_page(vma, vmaddr, PFN_PHYS(pfn)); + __flush_cache_page(vma, vmaddr, PFN_PHYS(pfn)); } void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr) @@ -779,34 +782,133 @@ void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned lon if (!PageAnon(page)) return; - if (parisc_requires_coherency()) { - if (vma->vm_flags & VM_SHARED) - flush_data_cache(); - else - flush_user_cache_page(vma, vmaddr); + __flush_cache_page(vma, vmaddr, PFN_PHYS(page_to_pfn(page))); +} + +int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long addr, + pte_t *ptep) +{ + pte_t pte = ptep_get(ptep); + + if (!pte_young(pte)) + return 0; + set_pte(ptep, pte_mkold(pte)); +#if CONFIG_FLUSH_PAGE_ACCESSED + __flush_cache_page(vma, addr, PFN_PHYS(pte_pfn(pte))); +#endif + return 1; +} + +/* + * After a PTE is cleared, we have no way to flush the cache for + * the physical page. On PA8800 and PA8900 processors, these lines + * can cause random cache corruption. Thus, we must flush the cache + * as well as the TLB when clearing a PTE that's valid. + */ +pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, + pte_t *ptep) +{ + struct mm_struct *mm = (vma)->vm_mm; + pte_t pte = ptep_get_and_clear(mm, addr, ptep); + unsigned long pfn = pte_pfn(pte); + + if (pfn_valid(pfn)) + __flush_cache_page(vma, addr, PFN_PHYS(pfn)); + else if (pte_accessible(mm, pte)) + flush_tlb_page(vma, addr); + + return pte; +} + +/* + * The physical address for pages in the ioremap case can be obtained + * from the vm_struct struct. I wasn't able to successfully handle the + * vmalloc and vmap cases. We have an array of struct page pointers in + * the uninitialized vmalloc case but the flush failed using page_to_pfn. + */ +void flush_cache_vmap(unsigned long start, unsigned long end) +{ + unsigned long addr, physaddr; + struct vm_struct *vm; + + /* Prevent cache move-in */ + flush_tlb_kernel_range(start, end); + + if (end - start >= parisc_cache_flush_threshold) { + flush_cache_all(); return; } - flush_tlb_page(vma, vmaddr); - preempt_disable(); - flush_dcache_page_asm(page_to_phys(page), vmaddr); - preempt_enable(); + if (WARN_ON_ONCE(!is_vmalloc_addr((void *)start))) { + flush_cache_all(); + return; + } + + vm = find_vm_area((void *)start); + if (WARN_ON_ONCE(!vm)) { + flush_cache_all(); + return; + } + + /* The physical addresses of IOREMAP regions are contiguous */ + if (vm->flags & VM_IOREMAP) { + physaddr = vm->phys_addr; + for (addr = start; addr < end; addr += PAGE_SIZE) { + preempt_disable(); + flush_dcache_page_asm(physaddr, start); + flush_icache_page_asm(physaddr, start); + preempt_enable(); + physaddr += PAGE_SIZE; + } + return; + } + + flush_cache_all(); } +EXPORT_SYMBOL(flush_cache_vmap); +/* + * The vm_struct has been retired and the page table is set up. The + * last page in the range is a guard page. Its physical address can't + * be determined using lpa, so there is no way to flush the range + * using flush_dcache_page_asm. + */ +void flush_cache_vunmap(unsigned long start, unsigned long end) +{ + /* Prevent cache move-in */ + flush_tlb_kernel_range(start, end); + flush_data_cache(); +} +EXPORT_SYMBOL(flush_cache_vunmap); + +/* + * On systems with PA8800/PA8900 processors, there is no way to flush + * a vmap range other than using the architected loop to flush the + * entire cache. The page directory is not set up, so we can't use + * fdc, etc. FDCE/FICE don't work to flush a portion of the cache. + * L2 is physically indexed but FDCE/FICE instructions in virtual + * mode output their virtual address on the core bus, not their + * real address. As a result, the L2 cache index formed from the + * virtual address will most likely not be the same as the L2 index + * formed from the real address. + */ void flush_kernel_vmap_range(void *vaddr, int size) { unsigned long start = (unsigned long)vaddr; unsigned long end = start + size; - if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) && - (unsigned long)size >= parisc_cache_flush_threshold) { - flush_tlb_kernel_range(start, end); - flush_data_cache(); + flush_tlb_kernel_range(start, end); + + if (!static_branch_likely(&parisc_has_dcache)) + return; + + /* If interrupts are disabled, we can only do local flush */ + if (WARN_ON(IS_ENABLED(CONFIG_SMP) && arch_irqs_disabled())) { + flush_data_cache_local(NULL); return; } - flush_kernel_dcache_range_asm(start, end); - flush_tlb_kernel_range(start, end); + flush_data_cache(); } EXPORT_SYMBOL(flush_kernel_vmap_range); @@ -818,15 +920,18 @@ void invalidate_kernel_vmap_range(void *vaddr, int size) /* Ensure DMA is complete */ asm_syncdma(); - if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) && - (unsigned long)size >= parisc_cache_flush_threshold) { - flush_tlb_kernel_range(start, end); - flush_data_cache(); + flush_tlb_kernel_range(start, end); + + if (!static_branch_likely(&parisc_has_dcache)) + return; + + /* If interrupts are disabled, we can only do local flush */ + if (WARN_ON(IS_ENABLED(CONFIG_SMP) && arch_irqs_disabled())) { + flush_data_cache_local(NULL); return; } - purge_kernel_dcache_range_asm(start, end); - flush_tlb_kernel_range(start, end); + flush_data_cache(); } EXPORT_SYMBOL(invalidate_kernel_vmap_range); diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c index 182aac6a0f77..48ef5fe5c08a 100644 --- a/arch/s390/boot/startup.c +++ b/arch/s390/boot/startup.c @@ -384,7 +384,7 @@ static void fixup_vmlinux_info(void) void startup_kernel(void) { unsigned long kernel_size = vmlinux.image_size + vmlinux.bss_size; - unsigned long nokaslr_offset_phys = mem_safe_offset(); + unsigned long nokaslr_offset_phys, kaslr_large_page_offset; unsigned long amode31_lma = 0; unsigned long max_physmem_end; unsigned long asce_limit; @@ -393,6 +393,12 @@ void startup_kernel(void) fixup_vmlinux_info(); setup_lpp(); + + /* + * Non-randomized kernel physical start address must be _SEGMENT_SIZE + * aligned (see blow). + */ + nokaslr_offset_phys = ALIGN(mem_safe_offset(), _SEGMENT_SIZE); safe_addr = PAGE_ALIGN(nokaslr_offset_phys + kernel_size); /* @@ -425,10 +431,25 @@ void startup_kernel(void) save_ipl_cert_comp_list(); rescue_initrd(safe_addr, ident_map_size); - if (kaslr_enabled()) - __kaslr_offset_phys = randomize_within_range(kernel_size, THREAD_SIZE, 0, ident_map_size); + /* + * __kaslr_offset_phys must be _SEGMENT_SIZE aligned, so the lower + * 20 bits (the offset within a large page) are zero. Copy the last + * 20 bits of __kaslr_offset, which is THREAD_SIZE aligned, to + * __kaslr_offset_phys. + * + * With this the last 20 bits of __kaslr_offset_phys and __kaslr_offset + * are identical, which is required to allow for large mappings of the + * kernel image. + */ + kaslr_large_page_offset = __kaslr_offset & ~_SEGMENT_MASK; + if (kaslr_enabled()) { + unsigned long end = ident_map_size - kaslr_large_page_offset; + + __kaslr_offset_phys = randomize_within_range(kernel_size, _SEGMENT_SIZE, 0, end); + } if (!__kaslr_offset_phys) __kaslr_offset_phys = nokaslr_offset_phys; + __kaslr_offset_phys |= kaslr_large_page_offset; kaslr_adjust_vmlinux_info(__kaslr_offset_phys); physmem_reserve(RR_VMLINUX, __kaslr_offset_phys, kernel_size); deploy_kernel((void *)__kaslr_offset_phys); diff --git a/arch/s390/boot/vmem.c b/arch/s390/boot/vmem.c index 96d48b7112d4..40cfce2687c4 100644 --- a/arch/s390/boot/vmem.c +++ b/arch/s390/boot/vmem.c @@ -261,21 +261,27 @@ static unsigned long _pa(unsigned long addr, unsigned long size, enum populate_m static bool large_allowed(enum populate_mode mode) { - return (mode == POPULATE_DIRECT) || (mode == POPULATE_IDENTITY); + return (mode == POPULATE_DIRECT) || (mode == POPULATE_IDENTITY) || (mode == POPULATE_KERNEL); } static bool can_large_pud(pud_t *pu_dir, unsigned long addr, unsigned long end, enum populate_mode mode) { + unsigned long size = end - addr; + return machine.has_edat2 && large_allowed(mode) && - IS_ALIGNED(addr, PUD_SIZE) && (end - addr) >= PUD_SIZE; + IS_ALIGNED(addr, PUD_SIZE) && (size >= PUD_SIZE) && + IS_ALIGNED(_pa(addr, size, mode), PUD_SIZE); } static bool can_large_pmd(pmd_t *pm_dir, unsigned long addr, unsigned long end, enum populate_mode mode) { + unsigned long size = end - addr; + return machine.has_edat1 && large_allowed(mode) && - IS_ALIGNED(addr, PMD_SIZE) && (end - addr) >= PMD_SIZE; + IS_ALIGNED(addr, PMD_SIZE) && (size >= PMD_SIZE) && + IS_ALIGNED(_pa(addr, size, mode), PMD_SIZE); } static void pgtable_pte_populate(pmd_t *pmd, unsigned long addr, unsigned long end, diff --git a/arch/s390/boot/vmlinux.lds.S b/arch/s390/boot/vmlinux.lds.S index 1fe5a1d3ff60..a750711d44c8 100644 --- a/arch/s390/boot/vmlinux.lds.S +++ b/arch/s390/boot/vmlinux.lds.S @@ -109,6 +109,7 @@ SECTIONS #ifdef CONFIG_KERNEL_UNCOMPRESSED . = ALIGN(PAGE_SIZE); . += AMODE31_SIZE; /* .amode31 section */ + . = ALIGN(1 << 20); /* _SEGMENT_SIZE */ #else . = ALIGN(8); #endif diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 145342e46ea8..8c4adece8911 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -43,7 +43,6 @@ CONFIG_PROFILING=y CONFIG_KEXEC=y CONFIG_KEXEC_FILE=y CONFIG_KEXEC_SIG=y -CONFIG_CRASH_DUMP=y CONFIG_LIVEPATCH=y CONFIG_MARCH_Z13=y CONFIG_NR_CPUS=512 @@ -51,6 +50,7 @@ CONFIG_NUMA=y CONFIG_HZ_100=y CONFIG_CERT_STORE=y CONFIG_EXPOLINE=y +# CONFIG_EXPOLINE_EXTERN is not set CONFIG_EXPOLINE_AUTO=y CONFIG_CHSC_SCH=y CONFIG_VFIO_CCW=m @@ -76,6 +76,7 @@ CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODULE_UNLOAD_TAINT_TRACKING=y CONFIG_MODVERSIONS=y CONFIG_MODULE_SRCVERSION_ALL=y +CONFIG_MODULE_SIG_SHA256=y CONFIG_BLK_DEV_THROTTLING=y CONFIG_BLK_WBT=y CONFIG_BLK_CGROUP_IOLATENCY=y @@ -100,7 +101,6 @@ CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y CONFIG_TRANSPARENT_HUGEPAGE=y -CONFIG_CMA_DEBUG=y CONFIG_CMA_DEBUGFS=y CONFIG_CMA_SYSFS=y CONFIG_CMA_AREAS=7 @@ -119,6 +119,7 @@ CONFIG_UNIX_DIAG=m CONFIG_XFRM_USER=m CONFIG_NET_KEY=m CONFIG_SMC_DIAG=m +CONFIG_SMC_LO=y CONFIG_INET=y CONFIG_IP_MULTICAST=y CONFIG_IP_ADVANCED_ROUTER=y @@ -133,7 +134,6 @@ CONFIG_IP_MROUTE=y CONFIG_IP_MROUTE_MULTIPLE_TABLES=y CONFIG_IP_PIMSM_V1=y CONFIG_IP_PIMSM_V2=y -CONFIG_SYN_COOKIES=y CONFIG_NET_IPVTI=m CONFIG_INET_AH=m CONFIG_INET_ESP=m @@ -167,6 +167,7 @@ CONFIG_BRIDGE_NETFILTER=m CONFIG_NETFILTER_NETLINK_HOOK=m CONFIG_NF_CONNTRACK=m CONFIG_NF_CONNTRACK_SECMARK=y +CONFIG_NF_CONNTRACK_ZONES=y CONFIG_NF_CONNTRACK_PROCFS=y CONFIG_NF_CONNTRACK_EVENTS=y CONFIG_NF_CONNTRACK_TIMEOUT=y @@ -183,17 +184,39 @@ CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_CT_NETLINK=m CONFIG_NF_CT_NETLINK_TIMEOUT=m +CONFIG_NF_CT_NETLINK_HELPER=m +CONFIG_NETFILTER_NETLINK_GLUE_CT=y CONFIG_NF_TABLES=m CONFIG_NF_TABLES_INET=y +CONFIG_NF_TABLES_NETDEV=y +CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m +CONFIG_NFT_FLOW_OFFLOAD=m +CONFIG_NFT_CONNLIMIT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m +CONFIG_NFT_MASQ=m +CONFIG_NFT_REDIR=m CONFIG_NFT_NAT=m +CONFIG_NFT_TUNNEL=m +CONFIG_NFT_QUEUE=m +CONFIG_NFT_QUOTA=m CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m -CONFIG_NETFILTER_XTABLES_COMPAT=y +CONFIG_NFT_XFRM=m +CONFIG_NFT_SOCKET=m +CONFIG_NFT_OSF=m +CONFIG_NFT_TPROXY=m +CONFIG_NFT_SYNPROXY=m +CONFIG_NFT_DUP_NETDEV=m +CONFIG_NFT_FWD_NETDEV=m +CONFIG_NFT_FIB_NETDEV=m +CONFIG_NFT_REJECT_NETDEV=m +CONFIG_NF_FLOW_TABLE_INET=m +CONFIG_NF_FLOW_TABLE=m +CONFIG_NF_FLOW_TABLE_PROCFS=y CONFIG_NETFILTER_XT_SET=m CONFIG_NETFILTER_XT_TARGET_AUDIT=m CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m @@ -206,8 +229,10 @@ CONFIG_NETFILTER_XT_TARGET_HMARK=m CONFIG_NETFILTER_XT_TARGET_IDLETIMER=m CONFIG_NETFILTER_XT_TARGET_LOG=m CONFIG_NETFILTER_XT_TARGET_MARK=m +CONFIG_NETFILTER_XT_TARGET_NETMAP=m CONFIG_NETFILTER_XT_TARGET_NFLOG=m CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m +CONFIG_NETFILTER_XT_TARGET_REDIRECT=m CONFIG_NETFILTER_XT_TARGET_TEE=m CONFIG_NETFILTER_XT_TARGET_TPROXY=m CONFIG_NETFILTER_XT_TARGET_TRACE=m @@ -216,6 +241,7 @@ CONFIG_NETFILTER_XT_TARGET_TCPMSS=m CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m CONFIG_NETFILTER_XT_MATCH_ADDRTYPE=m CONFIG_NETFILTER_XT_MATCH_BPF=m +CONFIG_NETFILTER_XT_MATCH_CGROUP=m CONFIG_NETFILTER_XT_MATCH_CLUSTER=m CONFIG_NETFILTER_XT_MATCH_COMMENT=m CONFIG_NETFILTER_XT_MATCH_CONNBYTES=m @@ -230,6 +256,7 @@ CONFIG_NETFILTER_XT_MATCH_DSCP=m CONFIG_NETFILTER_XT_MATCH_ESP=m CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m CONFIG_NETFILTER_XT_MATCH_HELPER=m +CONFIG_NETFILTER_XT_MATCH_IPCOMP=m CONFIG_NETFILTER_XT_MATCH_IPRANGE=m CONFIG_NETFILTER_XT_MATCH_IPVS=m CONFIG_NETFILTER_XT_MATCH_LENGTH=m @@ -247,6 +274,7 @@ CONFIG_NETFILTER_XT_MATCH_QUOTA=m CONFIG_NETFILTER_XT_MATCH_RATEEST=m CONFIG_NETFILTER_XT_MATCH_REALM=m CONFIG_NETFILTER_XT_MATCH_RECENT=m +CONFIG_NETFILTER_XT_MATCH_SOCKET=m CONFIG_NETFILTER_XT_MATCH_STATE=m CONFIG_NETFILTER_XT_MATCH_STATISTIC=m CONFIG_NETFILTER_XT_MATCH_STRING=m @@ -302,7 +330,6 @@ CONFIG_IP_NF_TARGET_ECN=m CONFIG_IP_NF_TARGET_TTL=m CONFIG_IP_NF_RAW=m CONFIG_IP_NF_SECURITY=m -CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NFT_FIB_IPV6=m @@ -373,7 +400,6 @@ CONFIG_NET_ACT_POLICE=m CONFIG_NET_ACT_GACT=m CONFIG_GACT_PROB=y CONFIG_NET_ACT_MIRRED=m -CONFIG_NET_ACT_IPT=m CONFIG_NET_ACT_NAT=m CONFIG_NET_ACT_PEDIT=m CONFIG_NET_ACT_SIMP=m @@ -462,6 +488,7 @@ CONFIG_DM_VERITY=m CONFIG_DM_VERITY_VERIFY_ROOTHASH_SIG=y CONFIG_DM_SWITCH=m CONFIG_DM_INTEGRITY=m +CONFIG_DM_VDO=m CONFIG_NETDEVICES=y CONFIG_BONDING=m CONFIG_DUMMY=m @@ -574,7 +601,6 @@ CONFIG_WATCHDOG=y CONFIG_WATCHDOG_NOWAYOUT=y CONFIG_SOFT_WATCHDOG=m CONFIG_DIAG288_WATCHDOG=m -# CONFIG_DRM_DEBUG_MODESET_LOCK is not set CONFIG_FB=y # CONFIG_FB_DEVICE is not set CONFIG_FRAMEBUFFER_CONSOLE=y @@ -645,7 +671,6 @@ CONFIG_MSDOS_FS=m CONFIG_VFAT_FS=m CONFIG_EXFAT_FS=m CONFIG_NTFS_FS=m -CONFIG_NTFS_RW=y CONFIG_PROC_KCORE=y CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y @@ -663,6 +688,7 @@ CONFIG_SQUASHFS_XZ=y CONFIG_SQUASHFS_ZSTD=y CONFIG_ROMFS_FS=m CONFIG_NFS_FS=m +CONFIG_NFS_V2=m CONFIG_NFS_V3_ACL=y CONFIG_NFS_V4=m CONFIG_NFS_SWAP=y @@ -879,6 +905,5 @@ CONFIG_RBTREE_TEST=y CONFIG_INTERVAL_TREE_TEST=m CONFIG_PERCPU_TEST=m CONFIG_ATOMIC64_SELFTEST=y -CONFIG_STRING_SELFTEST=y CONFIG_TEST_BITOPS=m CONFIG_TEST_BPF=m diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index dc237896f99d..6dd11d3b6aaa 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -41,7 +41,6 @@ CONFIG_PROFILING=y CONFIG_KEXEC=y CONFIG_KEXEC_FILE=y CONFIG_KEXEC_SIG=y -CONFIG_CRASH_DUMP=y CONFIG_LIVEPATCH=y CONFIG_MARCH_Z13=y CONFIG_NR_CPUS=512 @@ -49,6 +48,7 @@ CONFIG_NUMA=y CONFIG_HZ_100=y CONFIG_CERT_STORE=y CONFIG_EXPOLINE=y +# CONFIG_EXPOLINE_EXTERN is not set CONFIG_EXPOLINE_AUTO=y CONFIG_CHSC_SCH=y CONFIG_VFIO_CCW=m @@ -71,6 +71,7 @@ CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODULE_UNLOAD_TAINT_TRACKING=y CONFIG_MODVERSIONS=y CONFIG_MODULE_SRCVERSION_ALL=y +CONFIG_MODULE_SIG_SHA256=y CONFIG_BLK_DEV_THROTTLING=y CONFIG_BLK_WBT=y CONFIG_BLK_CGROUP_IOLATENCY=y @@ -110,6 +111,7 @@ CONFIG_UNIX_DIAG=m CONFIG_XFRM_USER=m CONFIG_NET_KEY=m CONFIG_SMC_DIAG=m +CONFIG_SMC_LO=y CONFIG_INET=y CONFIG_IP_MULTICAST=y CONFIG_IP_ADVANCED_ROUTER=y @@ -124,7 +126,6 @@ CONFIG_IP_MROUTE=y CONFIG_IP_MROUTE_MULTIPLE_TABLES=y CONFIG_IP_PIMSM_V1=y CONFIG_IP_PIMSM_V2=y -CONFIG_SYN_COOKIES=y CONFIG_NET_IPVTI=m CONFIG_INET_AH=m CONFIG_INET_ESP=m @@ -158,6 +159,7 @@ CONFIG_BRIDGE_NETFILTER=m CONFIG_NETFILTER_NETLINK_HOOK=m CONFIG_NF_CONNTRACK=m CONFIG_NF_CONNTRACK_SECMARK=y +CONFIG_NF_CONNTRACK_ZONES=y CONFIG_NF_CONNTRACK_PROCFS=y CONFIG_NF_CONNTRACK_EVENTS=y CONFIG_NF_CONNTRACK_TIMEOUT=y @@ -174,17 +176,39 @@ CONFIG_NF_CONNTRACK_SIP=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_CT_NETLINK=m CONFIG_NF_CT_NETLINK_TIMEOUT=m +CONFIG_NF_CT_NETLINK_HELPER=m +CONFIG_NETFILTER_NETLINK_GLUE_CT=y CONFIG_NF_TABLES=m CONFIG_NF_TABLES_INET=y +CONFIG_NF_TABLES_NETDEV=y +CONFIG_NFT_NUMGEN=m CONFIG_NFT_CT=m +CONFIG_NFT_FLOW_OFFLOAD=m +CONFIG_NFT_CONNLIMIT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m +CONFIG_NFT_MASQ=m +CONFIG_NFT_REDIR=m CONFIG_NFT_NAT=m +CONFIG_NFT_TUNNEL=m +CONFIG_NFT_QUEUE=m +CONFIG_NFT_QUOTA=m CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m CONFIG_NFT_FIB_INET=m -CONFIG_NETFILTER_XTABLES_COMPAT=y +CONFIG_NFT_XFRM=m +CONFIG_NFT_SOCKET=m +CONFIG_NFT_OSF=m +CONFIG_NFT_TPROXY=m +CONFIG_NFT_SYNPROXY=m +CONFIG_NFT_DUP_NETDEV=m +CONFIG_NFT_FWD_NETDEV=m +CONFIG_NFT_FIB_NETDEV=m +CONFIG_NFT_REJECT_NETDEV=m +CONFIG_NF_FLOW_TABLE_INET=m +CONFIG_NF_FLOW_TABLE=m +CONFIG_NF_FLOW_TABLE_PROCFS=y CONFIG_NETFILTER_XT_SET=m CONFIG_NETFILTER_XT_TARGET_AUDIT=m CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m @@ -197,8 +221,10 @@ CONFIG_NETFILTER_XT_TARGET_HMARK=m CONFIG_NETFILTER_XT_TARGET_IDLETIMER=m CONFIG_NETFILTER_XT_TARGET_LOG=m CONFIG_NETFILTER_XT_TARGET_MARK=m +CONFIG_NETFILTER_XT_TARGET_NETMAP=m CONFIG_NETFILTER_XT_TARGET_NFLOG=m CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m +CONFIG_NETFILTER_XT_TARGET_REDIRECT=m CONFIG_NETFILTER_XT_TARGET_TEE=m CONFIG_NETFILTER_XT_TARGET_TPROXY=m CONFIG_NETFILTER_XT_TARGET_TRACE=m @@ -207,6 +233,7 @@ CONFIG_NETFILTER_XT_TARGET_TCPMSS=m CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m CONFIG_NETFILTER_XT_MATCH_ADDRTYPE=m CONFIG_NETFILTER_XT_MATCH_BPF=m +CONFIG_NETFILTER_XT_MATCH_CGROUP=m CONFIG_NETFILTER_XT_MATCH_CLUSTER=m CONFIG_NETFILTER_XT_MATCH_COMMENT=m CONFIG_NETFILTER_XT_MATCH_CONNBYTES=m @@ -221,6 +248,7 @@ CONFIG_NETFILTER_XT_MATCH_DSCP=m CONFIG_NETFILTER_XT_MATCH_ESP=m CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m CONFIG_NETFILTER_XT_MATCH_HELPER=m +CONFIG_NETFILTER_XT_MATCH_IPCOMP=m CONFIG_NETFILTER_XT_MATCH_IPRANGE=m CONFIG_NETFILTER_XT_MATCH_IPVS=m CONFIG_NETFILTER_XT_MATCH_LENGTH=m @@ -238,6 +266,7 @@ CONFIG_NETFILTER_XT_MATCH_QUOTA=m CONFIG_NETFILTER_XT_MATCH_RATEEST=m CONFIG_NETFILTER_XT_MATCH_REALM=m CONFIG_NETFILTER_XT_MATCH_RECENT=m +CONFIG_NETFILTER_XT_MATCH_SOCKET=m CONFIG_NETFILTER_XT_MATCH_STATE=m CONFIG_NETFILTER_XT_MATCH_STATISTIC=m CONFIG_NETFILTER_XT_MATCH_STRING=m @@ -293,7 +322,6 @@ CONFIG_IP_NF_TARGET_ECN=m CONFIG_IP_NF_TARGET_TTL=m CONFIG_IP_NF_RAW=m CONFIG_IP_NF_SECURITY=m -CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NFT_FIB_IPV6=m @@ -363,7 +391,6 @@ CONFIG_NET_ACT_POLICE=m CONFIG_NET_ACT_GACT=m CONFIG_GACT_PROB=y CONFIG_NET_ACT_MIRRED=m -CONFIG_NET_ACT_IPT=m CONFIG_NET_ACT_NAT=m CONFIG_NET_ACT_PEDIT=m CONFIG_NET_ACT_SIMP=m @@ -452,6 +479,7 @@ CONFIG_DM_VERITY=m CONFIG_DM_VERITY_VERIFY_ROOTHASH_SIG=y CONFIG_DM_SWITCH=m CONFIG_DM_INTEGRITY=m +CONFIG_DM_VDO=m CONFIG_NETDEVICES=y CONFIG_BONDING=m CONFIG_DUMMY=m @@ -630,7 +658,6 @@ CONFIG_MSDOS_FS=m CONFIG_VFAT_FS=m CONFIG_EXFAT_FS=m CONFIG_NTFS_FS=m -CONFIG_NTFS_RW=y CONFIG_PROC_KCORE=y CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y @@ -649,6 +676,7 @@ CONFIG_SQUASHFS_XZ=y CONFIG_SQUASHFS_ZSTD=y CONFIG_ROMFS_FS=m CONFIG_NFS_FS=m +CONFIG_NFS_V2=m CONFIG_NFS_V3_ACL=y CONFIG_NFS_V4=m CONFIG_NFS_SWAP=y diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index c51f3ec4eb28..8c2b61363bab 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -9,25 +9,22 @@ CONFIG_BPF_SYSCALL=y CONFIG_BLK_DEV_INITRD=y CONFIG_CC_OPTIMIZE_FOR_SIZE=y CONFIG_KEXEC=y -CONFIG_CRASH_DUMP=y CONFIG_MARCH_Z13=y CONFIG_NR_CPUS=2 CONFIG_HZ_100=y # CONFIG_CHSC_SCH is not set # CONFIG_SCM_BUS is not set +# CONFIG_AP is not set # CONFIG_PFAULT is not set # CONFIG_S390_HYPFS is not set # CONFIG_VIRTUALIZATION is not set # CONFIG_S390_GUEST is not set # CONFIG_SECCOMP is not set -# CONFIG_GCC_PLUGINS is not set # CONFIG_BLOCK_LEGACY_AUTOLOAD is not set CONFIG_PARTITION_ADVANCED=y # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set # CONFIG_SWAP is not set # CONFIG_COMPAT_BRK is not set -# CONFIG_COMPACTION is not set -# CONFIG_MIGRATION is not set CONFIG_NET=y # CONFIG_IUCV is not set # CONFIG_PCPU_DEV_REFCNT is not set diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 243ee86cb1b1..f2051644de94 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -105,9 +105,9 @@ vmlinux-objs-$(CONFIG_UNACCEPTED_MEMORY) += $(obj)/mem.o vmlinux-objs-$(CONFIG_EFI) += $(obj)/efi.o vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_mixed.o -vmlinux-objs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a +vmlinux-libs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a -$(obj)/vmlinux: $(vmlinux-objs-y) FORCE +$(obj)/vmlinux: $(vmlinux-objs-y) $(vmlinux-libs-y) FORCE $(call if_changed,ld) OBJCOPYFLAGS_vmlinux.bin := -R .comment -S diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 1dc600fa3ba5..481096177500 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -401,7 +401,6 @@ extern int __init efi_memmap_alloc(unsigned int num_entries, struct efi_memory_map_data *data); extern void __efi_memmap_free(u64 phys, unsigned long size, unsigned long flags); -#define __efi_memmap_free __efi_memmap_free extern int __init efi_memmap_install(struct efi_memory_map_data *data); extern int __init efi_memmap_split_count(efi_memory_desc_t *md, diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 0f9bab92a43d..3a7755c1a441 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -78,10 +78,10 @@ extern int __get_user_bad(void); int __ret_gu; \ register __inttype(*(ptr)) __val_gu asm("%"_ASM_DX); \ __chk_user_ptr(ptr); \ - asm volatile("call __" #fn "_%c4" \ + asm volatile("call __" #fn "_%c[size]" \ : "=a" (__ret_gu), "=r" (__val_gu), \ ASM_CALL_CONSTRAINT \ - : "0" (ptr), "i" (sizeof(*(ptr)))); \ + : "0" (ptr), [size] "i" (sizeof(*(ptr)))); \ instrument_get_user(__val_gu); \ (x) = (__force __typeof__(*(ptr))) __val_gu; \ __builtin_expect(__ret_gu, 0); \ diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S index 10d5ed8b5990..a1cb3a4e6742 100644 --- a/arch/x86/lib/getuser.S +++ b/arch/x86/lib/getuser.S @@ -44,7 +44,11 @@ or %rdx, %rax .else cmp $TASK_SIZE_MAX-\size+1, %eax +.if \size != 8 jae .Lbad_get_user +.else + jae .Lbad_get_user_8 +.endif sbb %edx, %edx /* array_index_mask_nospec() */ and %edx, %eax .endif @@ -154,7 +158,7 @@ SYM_CODE_END(__get_user_handle_exception) #ifdef CONFIG_X86_32 SYM_CODE_START_LOCAL(__get_user_8_handle_exception) ASM_CLAC -bad_get_user_8: +.Lbad_get_user_8: xor %edx,%edx xor %ecx,%ecx mov $(-EFAULT),%_ASM_AX diff --git a/arch/x86/platform/efi/memmap.c b/arch/x86/platform/efi/memmap.c index 4ef20b49eb5e..6ed1935504b9 100644 --- a/arch/x86/platform/efi/memmap.c +++ b/arch/x86/platform/efi/memmap.c @@ -92,12 +92,22 @@ int __init efi_memmap_alloc(unsigned int num_entries, */ int __init efi_memmap_install(struct efi_memory_map_data *data) { + unsigned long size = efi.memmap.desc_size * efi.memmap.nr_map; + unsigned long flags = efi.memmap.flags; + u64 phys = efi.memmap.phys_map; + int ret; + efi_memmap_unmap(); if (efi_enabled(EFI_PARAVIRT)) return 0; - return __efi_memmap_init(data); + ret = __efi_memmap_init(data); + if (ret) + return ret; + + __efi_memmap_free(phys, size, flags); + return 0; } /** diff --git a/block/bio-integrity.c b/block/bio-integrity.c index 2e3e8e04961e..8b528e12136f 100644 --- a/block/bio-integrity.c +++ b/block/bio-integrity.c @@ -144,10 +144,10 @@ void bio_integrity_free(struct bio *bio) struct bio_integrity_payload *bip = bio_integrity(bio); struct bio_set *bs = bio->bi_pool; + if (bip->bip_flags & BIP_INTEGRITY_USER) + return; if (bip->bip_flags & BIP_BLOCK_INTEGRITY) kfree(bvec_virt(bip->bip_vec)); - else if (bip->bip_flags & BIP_INTEGRITY_USER) - bio_integrity_unmap_user(bip); __bio_integrity_free(bs, bip); bio->bi_integrity = NULL; @@ -155,6 +155,28 @@ void bio_integrity_free(struct bio *bio) } /** + * bio_integrity_unmap_free_user - Unmap and free bio user integrity payload + * @bio: bio containing bip to be unmapped and freed + * + * Description: Used to unmap and free the user mapped integrity portion of a + * bio. Submitter attaching the user integrity buffer is responsible for + * unmapping and freeing it during completion. + */ +void bio_integrity_unmap_free_user(struct bio *bio) +{ + struct bio_integrity_payload *bip = bio_integrity(bio); + struct bio_set *bs = bio->bi_pool; + + if (WARN_ON_ONCE(!(bip->bip_flags & BIP_INTEGRITY_USER))) + return; + bio_integrity_unmap_user(bip); + __bio_integrity_free(bs, bip); + bio->bi_integrity = NULL; + bio->bi_opf &= ~REQ_INTEGRITY; +} +EXPORT_SYMBOL(bio_integrity_unmap_free_user); + +/** * bio_integrity_add_page - Attach integrity metadata * @bio: bio to update * @page: page containing integrity metadata diff --git a/block/blk-flush.c b/block/blk-flush.c index c17cf8ed8113..cca4f9131f79 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -185,7 +185,7 @@ static void blk_flush_complete_seq(struct request *rq, /* queue for flush */ if (list_empty(pending)) fq->flush_pending_since = jiffies; - list_move_tail(&rq->queuelist, pending); + list_add_tail(&rq->queuelist, pending); break; case REQ_FSEQ_DATA: @@ -263,6 +263,7 @@ static enum rq_end_io_ret flush_end_io(struct request *flush_rq, unsigned int seq = blk_flush_cur_seq(rq); BUG_ON(seq != REQ_FSEQ_PREFLUSH && seq != REQ_FSEQ_POSTFLUSH); + list_del_init(&rq->queuelist); blk_flush_complete_seq(rq, fq, seq, error); } diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 52abebf56027..08d7dfe8bd93 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -1552,6 +1552,9 @@ static void disk_destroy_zone_wplugs_hash_table(struct gendisk *disk) void disk_free_zone_resources(struct gendisk *disk) { + if (!disk->zone_wplugs_pool) + return; + cancel_work_sync(&disk->zone_wplugs_work); if (disk->zone_wplugs_wq) { diff --git a/block/sed-opal.c b/block/sed-opal.c index 14fe0fef811c..598fd3e7fcc8 100644 --- a/block/sed-opal.c +++ b/block/sed-opal.c @@ -314,7 +314,7 @@ static int read_sed_opal_key(const char *key_name, u_char *buffer, int buflen) &key_type_user, key_name, true); if (IS_ERR(kref)) - ret = PTR_ERR(kref); + return PTR_ERR(kref); key = key_ref_to_ptr(kref); down_read(&key->sem); diff --git a/drivers/acpi/acpica/acevents.h b/drivers/acpi/acpica/acevents.h index ddd072cbc738..2133085deda7 100644 --- a/drivers/acpi/acpica/acevents.h +++ b/drivers/acpi/acpica/acevents.h @@ -191,6 +191,10 @@ void acpi_ev_execute_reg_methods(struct acpi_namespace_node *node, acpi_adr_space_type space_id, u32 function); +void +acpi_ev_execute_orphan_reg_method(struct acpi_namespace_node *node, + acpi_adr_space_type space_id); + acpi_status acpi_ev_execute_reg_method(union acpi_operand_object *region_obj, u32 function); diff --git a/drivers/acpi/acpica/evregion.c b/drivers/acpi/acpica/evregion.c index 18fdf2bc2d49..dc6004daf624 100644 --- a/drivers/acpi/acpica/evregion.c +++ b/drivers/acpi/acpica/evregion.c @@ -20,10 +20,6 @@ extern u8 acpi_gbl_default_address_spaces[]; /* Local prototypes */ -static void -acpi_ev_execute_orphan_reg_method(struct acpi_namespace_node *device_node, - acpi_adr_space_type space_id); - static acpi_status acpi_ev_reg_run(acpi_handle obj_handle, u32 level, void *context, void **return_value); @@ -818,7 +814,7 @@ acpi_ev_reg_run(acpi_handle obj_handle, * ******************************************************************************/ -static void +void acpi_ev_execute_orphan_reg_method(struct acpi_namespace_node *device_node, acpi_adr_space_type space_id) { diff --git a/drivers/acpi/acpica/evxfregn.c b/drivers/acpi/acpica/evxfregn.c index 3197e6303c5b..624361a5f34d 100644 --- a/drivers/acpi/acpica/evxfregn.c +++ b/drivers/acpi/acpica/evxfregn.c @@ -306,3 +306,57 @@ acpi_execute_reg_methods(acpi_handle device, acpi_adr_space_type space_id) } ACPI_EXPORT_SYMBOL(acpi_execute_reg_methods) + +/******************************************************************************* + * + * FUNCTION: acpi_execute_orphan_reg_method + * + * PARAMETERS: device - Handle for the device + * space_id - The address space ID + * + * RETURN: Status + * + * DESCRIPTION: Execute an "orphan" _REG method that appears under an ACPI + * device. This is a _REG method that has no corresponding region + * within the device's scope. + * + ******************************************************************************/ +acpi_status +acpi_execute_orphan_reg_method(acpi_handle device, acpi_adr_space_type space_id) +{ + struct acpi_namespace_node *node; + acpi_status status; + + ACPI_FUNCTION_TRACE(acpi_execute_orphan_reg_method); + + /* Parameter validation */ + + if (!device) { + return_ACPI_STATUS(AE_BAD_PARAMETER); + } + + status = acpi_ut_acquire_mutex(ACPI_MTX_NAMESPACE); + if (ACPI_FAILURE(status)) { + return_ACPI_STATUS(status); + } + + /* Convert and validate the device handle */ + + node = acpi_ns_validate_handle(device); + if (node) { + + /* + * If an "orphan" _REG method is present in the device's scope + * for the given address space ID, run it. + */ + + acpi_ev_execute_orphan_reg_method(node, space_id); + } else { + status = AE_BAD_PARAMETER; + } + + (void)acpi_ut_release_mutex(ACPI_MTX_NAMESPACE); + return_ACPI_STATUS(status); +} + +ACPI_EXPORT_SYMBOL(acpi_execute_orphan_reg_method) diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index 68dd17f96f63..299ec653388c 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -1507,6 +1507,9 @@ static int ec_install_handlers(struct acpi_ec *ec, struct acpi_device *device, if (call_reg && !test_bit(EC_FLAGS_EC_REG_CALLED, &ec->flags)) { acpi_execute_reg_methods(scope_handle, ACPI_ADR_SPACE_EC); + if (scope_handle != ec->handle) + acpi_execute_orphan_reg_method(ec->handle, ACPI_ADR_SPACE_EC); + set_bit(EC_FLAGS_EC_REG_CALLED, &ec->flags); } diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c index d67881b50bca..a0cfc857fb55 100644 --- a/drivers/acpi/thermal.c +++ b/drivers/acpi/thermal.c @@ -168,11 +168,17 @@ static int acpi_thermal_get_polling_frequency(struct acpi_thermal *tz) static int acpi_thermal_temp(struct acpi_thermal *tz, int temp_deci_k) { + int temp; + if (temp_deci_k == THERMAL_TEMP_INVALID) return THERMAL_TEMP_INVALID; - return deci_kelvin_to_millicelsius_with_offset(temp_deci_k, + temp = deci_kelvin_to_millicelsius_with_offset(temp_deci_k, tz->kelvin_offset); + if (temp <= 0) + return THERMAL_TEMP_INVALID; + + return temp; } static bool acpi_thermal_trip_valid(struct acpi_thermal_trip *acpi_trip) diff --git a/drivers/acpi/x86/utils.c b/drivers/acpi/x86/utils.c index 7dca73417e2b..2fe0934dcd64 100644 --- a/drivers/acpi/x86/utils.c +++ b/drivers/acpi/x86/utils.c @@ -206,16 +206,16 @@ bool acpi_device_override_status(struct acpi_device *adev, unsigned long long *s } /* - * AMD systems from Renoir and Lucienne *require* that the NVME controller + * AMD systems from Renoir onwards *require* that the NVME controller * is put into D3 over a Modern Standby / suspend-to-idle cycle. * * This is "typically" accomplished using the `StorageD3Enable` * property in the _DSD that is checked via the `acpi_storage_d3` function - * but this property was introduced after many of these systems launched - * and most OEM systems don't have it in their BIOS. + * but some OEM systems still don't have it in their BIOS. * * The Microsoft documentation for StorageD3Enable mentioned that Windows has - * a hardcoded allowlist for D3 support, which was used for these platforms. + * a hardcoded allowlist for D3 support as well as a registry key to override + * the BIOS, which has been used for these cases. * * This allows quirking on Linux in a similar fashion. * @@ -228,19 +228,15 @@ bool acpi_device_override_status(struct acpi_device *adev, unsigned long long *s * https://bugzilla.kernel.org/show_bug.cgi?id=216773 * https://bugzilla.kernel.org/show_bug.cgi?id=217003 * 2) On at least one HP system StorageD3Enable is missing on the second NVME - disk in the system. + * disk in the system. + * 3) On at least one HP Rembrandt system StorageD3Enable is missing on the only + * NVME device. */ -static const struct x86_cpu_id storage_d3_cpu_ids[] = { - X86_MATCH_VENDOR_FAM_MODEL(AMD, 23, 24, NULL), /* Picasso */ - X86_MATCH_VENDOR_FAM_MODEL(AMD, 23, 96, NULL), /* Renoir */ - X86_MATCH_VENDOR_FAM_MODEL(AMD, 23, 104, NULL), /* Lucienne */ - X86_MATCH_VENDOR_FAM_MODEL(AMD, 25, 80, NULL), /* Cezanne */ - {} -}; - bool force_storage_d3(void) { - return x86_match_cpu(storage_d3_cpu_ids); + if (!cpu_feature_enabled(X86_FEATURE_ZEN)) + return false; + return acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0; } /* diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index cdf29b178ddc..bb4d30d377ae 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1831,11 +1831,11 @@ static unsigned int ata_scsiop_inq_std(struct ata_scsi_args *args, u8 *rbuf) 2 }; - /* set scsi removable (RMB) bit per ata bit, or if the - * AHCI port says it's external (Hotplug-capable, eSATA). + /* + * Set the SCSI Removable Media Bit (RMB) if the ATA removable media + * device bit (obsolete since ATA-8 ACS) is set. */ - if (ata_id_removable(args->id) || - (args->dev->link->ap->pflags & ATA_PFLAG_EXTERNAL)) + if (ata_id_removable(args->id)) hdr[1] |= (1 << 7); if (args->dev->class == ATA_DEV_ZAC) { diff --git a/drivers/base/core.c b/drivers/base/core.c index 131d96c6090b..2b4c0624b704 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -2739,8 +2739,11 @@ static ssize_t uevent_show(struct device *dev, struct device_attribute *attr, if (!env) return -ENOMEM; + /* Synchronize with really_probe() */ + device_lock(dev); /* let the kset specific function add its keys */ retval = kset->uevent_ops->uevent(&dev->kobj, env); + device_unlock(dev); if (retval) goto out; @@ -2845,15 +2848,6 @@ static void devm_attr_group_remove(struct device *dev, void *res) sysfs_remove_group(&dev->kobj, group); } -static void devm_attr_groups_remove(struct device *dev, void *res) -{ - union device_attr_group_devres *devres = res; - const struct attribute_group **groups = devres->groups; - - dev_dbg(dev, "%s: removing groups %p\n", __func__, groups); - sysfs_remove_groups(&dev->kobj, groups); -} - /** * devm_device_add_group - given a device, create a managed attribute group * @dev: The device to create the group for @@ -2886,42 +2880,6 @@ int devm_device_add_group(struct device *dev, const struct attribute_group *grp) } EXPORT_SYMBOL_GPL(devm_device_add_group); -/** - * devm_device_add_groups - create a bunch of managed attribute groups - * @dev: The device to create the group for - * @groups: The attribute groups to create, NULL terminated - * - * This function creates a bunch of managed attribute groups. If an error - * occurs when creating a group, all previously created groups will be - * removed, unwinding everything back to the original state when this - * function was called. It will explicitly warn and error if any of the - * attribute files being created already exist. - * - * Returns 0 on success or error code from sysfs_create_group on failure. - */ -int devm_device_add_groups(struct device *dev, - const struct attribute_group **groups) -{ - union device_attr_group_devres *devres; - int error; - - devres = devres_alloc(devm_attr_groups_remove, - sizeof(*devres), GFP_KERNEL); - if (!devres) - return -ENOMEM; - - error = sysfs_create_groups(&dev->kobj, groups); - if (error) { - devres_free(devres); - return error; - } - - devres->groups = groups; - devres_add(dev, devres); - return 0; -} -EXPORT_SYMBOL_GPL(devm_device_add_groups); - static int device_add_attrs(struct device *dev) { const struct class *class = dev->class; diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 93780f41646b..1153721bc7c2 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -302,6 +302,21 @@ static int lo_read_simple(struct loop_device *lo, struct request *rq, return 0; } +static void loop_clear_limits(struct loop_device *lo, int mode) +{ + struct queue_limits lim = queue_limits_start_update(lo->lo_queue); + + if (mode & FALLOC_FL_ZERO_RANGE) + lim.max_write_zeroes_sectors = 0; + + if (mode & FALLOC_FL_PUNCH_HOLE) { + lim.max_hw_discard_sectors = 0; + lim.discard_granularity = 0; + } + + queue_limits_commit_update(lo->lo_queue, &lim); +} + static int lo_fallocate(struct loop_device *lo, struct request *rq, loff_t pos, int mode) { @@ -320,6 +335,14 @@ static int lo_fallocate(struct loop_device *lo, struct request *rq, loff_t pos, ret = file->f_op->fallocate(file, mode, pos, blk_rq_bytes(rq)); if (unlikely(ret && ret != -EINVAL && ret != -EOPNOTSUPP)) return -EIO; + + /* + * We initially configure the limits in a hope that fallocate is + * supported and clear them here if that turns out not to be true. + */ + if (unlikely(ret == -EOPNOTSUPP)) + loop_clear_limits(lo, mode); + return ret; } diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 22a79a62cc4e..b87aa80a46dd 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -589,10 +589,11 @@ static inline int was_interrupted(int result) } /* - * Returns BLK_STS_RESOURCE if the caller should retry after a delay. Returns - * -EAGAIN if the caller should requeue @cmd. Returns -EIO if sending failed. + * Returns BLK_STS_RESOURCE if the caller should retry after a delay. + * Returns BLK_STS_IOERR if sending failed. */ -static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) +static blk_status_t nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, + int index) { struct request *req = blk_mq_rq_from_pdu(cmd); struct nbd_config *config = nbd->config; @@ -614,13 +615,13 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) type = req_to_nbd_cmd_type(req); if (type == U32_MAX) - return -EIO; + return BLK_STS_IOERR; if (rq_data_dir(req) == WRITE && (config->flags & NBD_FLAG_READ_ONLY)) { dev_err_ratelimited(disk_to_dev(nbd->disk), "Write on read-only\n"); - return -EIO; + return BLK_STS_IOERR; } if (req->cmd_flags & REQ_FUA) @@ -674,11 +675,11 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) nsock->sent = sent; } set_bit(NBD_CMD_REQUEUED, &cmd->flags); - return (__force int)BLK_STS_RESOURCE; + return BLK_STS_RESOURCE; } dev_err_ratelimited(disk_to_dev(nbd->disk), "Send control failed (result %d)\n", result); - return -EAGAIN; + goto requeue; } send_pages: if (type != NBD_CMD_WRITE) @@ -715,12 +716,12 @@ send_pages: nsock->pending = req; nsock->sent = sent; set_bit(NBD_CMD_REQUEUED, &cmd->flags); - return (__force int)BLK_STS_RESOURCE; + return BLK_STS_RESOURCE; } dev_err(disk_to_dev(nbd->disk), "Send data failed (result %d)\n", result); - return -EAGAIN; + goto requeue; } /* * The completion might already have come in, @@ -737,7 +738,16 @@ out: trace_nbd_payload_sent(req, handle); nsock->pending = NULL; nsock->sent = 0; - return 0; + __set_bit(NBD_CMD_INFLIGHT, &cmd->flags); + return BLK_STS_OK; + +requeue: + /* retry on a different socket */ + dev_err_ratelimited(disk_to_dev(nbd->disk), + "Request send failed, requeueing\n"); + nbd_mark_nsock_dead(nbd, nsock, 1); + nbd_requeue_cmd(cmd); + return BLK_STS_OK; } static int nbd_read_reply(struct nbd_device *nbd, struct socket *sock, @@ -1018,7 +1028,7 @@ static blk_status_t nbd_handle_cmd(struct nbd_cmd *cmd, int index) struct nbd_device *nbd = cmd->nbd; struct nbd_config *config; struct nbd_sock *nsock; - int ret; + blk_status_t ret; lockdep_assert_held(&cmd->lock); @@ -1072,28 +1082,11 @@ again: ret = BLK_STS_OK; goto out; } - /* - * Some failures are related to the link going down, so anything that - * returns EAGAIN can be retried on a different socket. - */ ret = nbd_send_cmd(nbd, cmd, index); - /* - * Access to this flag is protected by cmd->lock, thus it's safe to set - * the flag after nbd_send_cmd() succeed to send request to server. - */ - if (!ret) - __set_bit(NBD_CMD_INFLIGHT, &cmd->flags); - else if (ret == -EAGAIN) { - dev_err_ratelimited(disk_to_dev(nbd->disk), - "Request send failed, requeueing\n"); - nbd_mark_nsock_dead(nbd, nsock, 1); - nbd_requeue_cmd(cmd); - ret = BLK_STS_OK; - } out: mutex_unlock(&nsock->tx_lock); nbd_config_put(nbd); - return ret < 0 ? BLK_STS_IOERR : (__force blk_status_t)ret; + return ret; } static blk_status_t nbd_queue_rq(struct blk_mq_hw_ctx *hctx, diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 65d3f79104bd..15de5e3d96fd 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -1302,12 +1302,17 @@ static ssize_t store_no_turbo(struct kobject *a, struct kobj_attribute *b, no_turbo = !!clamp_t(int, input, 0, 1); - if (no_turbo == global.no_turbo) - goto unlock_driver; - - if (global.turbo_disabled) { - pr_notice_once("Turbo disabled by BIOS or unavailable on processor\n"); + WRITE_ONCE(global.turbo_disabled, turbo_is_disabled()); + if (global.turbo_disabled && !no_turbo) { + pr_notice("Turbo disabled by BIOS or unavailable on processor\n"); count = -EPERM; + if (global.no_turbo) + goto unlock_driver; + else + no_turbo = 1; + } + + if (no_turbo == global.no_turbo) { goto unlock_driver; } @@ -1762,7 +1767,7 @@ static u64 atom_get_val(struct cpudata *cpudata, int pstate) u32 vid; val = (u64)pstate << 8; - if (READ_ONCE(global.no_turbo) && !global.turbo_disabled) + if (READ_ONCE(global.no_turbo) && !READ_ONCE(global.turbo_disabled)) val |= (u64)1 << 32; vid_fp = cpudata->vid.min + mul_fp( @@ -1927,7 +1932,7 @@ static u64 core_get_val(struct cpudata *cpudata, int pstate) u64 val; val = (u64)pstate << 8; - if (READ_ONCE(global.no_turbo) && !global.turbo_disabled) + if (READ_ONCE(global.no_turbo) && !READ_ONCE(global.turbo_disabled)) val |= (u64)1 << 32; return val; diff --git a/drivers/firewire/Kconfig b/drivers/firewire/Kconfig index 869598b20e3a..5268b3f0a25a 100644 --- a/drivers/firewire/Kconfig +++ b/drivers/firewire/Kconfig @@ -11,7 +11,7 @@ config FIREWIRE This is the new-generation IEEE 1394 (FireWire) driver stack a.k.a. Juju, a new implementation designed for robustness and simplicity. - See http://ieee1394.wiki.kernel.org/index.php/Juju_Migration + See http://ieee1394.docs.kernel.org/en/latest/migration.html for information about migration from the older Linux 1394 stack to the new driver stack. diff --git a/drivers/firewire/core-card.c b/drivers/firewire/core-card.c index 127d87e3a153..f8b99dd6cd82 100644 --- a/drivers/firewire/core-card.c +++ b/drivers/firewire/core-card.c @@ -222,14 +222,14 @@ static int reset_bus(struct fw_card *card, bool short_reset) int reg = short_reset ? 5 : 1; int bit = short_reset ? PHY_BUS_SHORT_RESET : PHY_BUS_RESET; - trace_bus_reset_initiate(card->generation, short_reset); + trace_bus_reset_initiate(card->index, card->generation, short_reset); return card->driver->update_phy_reg(card, reg, 0, bit); } void fw_schedule_bus_reset(struct fw_card *card, bool delayed, bool short_reset) { - trace_bus_reset_schedule(card->generation, short_reset); + trace_bus_reset_schedule(card->index, card->generation, short_reset); /* We don't try hard to sort out requests of long vs. short resets. */ card->br_short = short_reset; @@ -249,7 +249,7 @@ static void br_work(struct work_struct *work) /* Delay for 2s after last reset per IEEE 1394 clause 8.2.1. */ if (card->reset_jiffies != 0 && time_before64(get_jiffies_64(), card->reset_jiffies + 2 * HZ)) { - trace_bus_reset_postpone(card->generation, card->br_short); + trace_bus_reset_postpone(card->index, card->generation, card->br_short); if (!queue_delayed_work(fw_workqueue, &card->br_work, 2 * HZ)) fw_card_put(card); diff --git a/drivers/firewire/core-cdev.c b/drivers/firewire/core-cdev.c index 55993c9e0b90..9a7dc90330a3 100644 --- a/drivers/firewire/core-cdev.c +++ b/drivers/firewire/core-cdev.c @@ -1559,7 +1559,7 @@ static void outbound_phy_packet_callback(struct fw_packet *packet, struct client *e_client = e->client; u32 rcode; - trace_async_phy_outbound_complete((uintptr_t)packet, status, packet->generation, + trace_async_phy_outbound_complete((uintptr_t)packet, card->index, status, packet->generation, packet->timestamp); switch (status) { @@ -1659,8 +1659,8 @@ static int ioctl_send_phy_packet(struct client *client, union ioctl_arg *arg) memcpy(pp->data, a->data, sizeof(a->data)); } - trace_async_phy_outbound_initiate((uintptr_t)&e->p, e->p.generation, e->p.header[1], - e->p.header[2]); + trace_async_phy_outbound_initiate((uintptr_t)&e->p, card->index, e->p.generation, + e->p.header[1], e->p.header[2]); card->driver->send_request(card, &e->p); diff --git a/drivers/firewire/core-topology.c b/drivers/firewire/core-topology.c index 837cc44d8d9f..8107eebd4296 100644 --- a/drivers/firewire/core-topology.c +++ b/drivers/firewire/core-topology.c @@ -508,7 +508,7 @@ void fw_core_handle_bus_reset(struct fw_card *card, int node_id, int generation, struct fw_node *local_node; unsigned long flags; - trace_bus_reset_handle(generation, node_id, bm_abdicate, self_ids, self_id_count); + trace_bus_reset_handle(card->index, generation, node_id, bm_abdicate, self_ids, self_id_count); spin_lock_irqsave(&card->lock, flags); diff --git a/drivers/firewire/core-transaction.c b/drivers/firewire/core-transaction.c index 571fdff65c2b..76ab6a209768 100644 --- a/drivers/firewire/core-transaction.c +++ b/drivers/firewire/core-transaction.c @@ -174,8 +174,8 @@ static void transmit_complete_callback(struct fw_packet *packet, struct fw_transaction *t = container_of(packet, struct fw_transaction, packet); - trace_async_request_outbound_complete((uintptr_t)t, packet->generation, packet->speed, - status, packet->timestamp); + trace_async_request_outbound_complete((uintptr_t)t, card->index, packet->generation, + packet->speed, status, packet->timestamp); switch (status) { case ACK_COMPLETE: @@ -398,7 +398,8 @@ void __fw_send_request(struct fw_card *card, struct fw_transaction *t, int tcode spin_unlock_irqrestore(&card->lock, flags); - trace_async_request_outbound_initiate((uintptr_t)t, generation, speed, t->packet.header, payload, + trace_async_request_outbound_initiate((uintptr_t)t, card->index, generation, speed, + t->packet.header, payload, tcode_is_read_request(tcode) ? 0 : length / 4); card->driver->send_request(card, &t->packet); @@ -463,7 +464,7 @@ static DECLARE_COMPLETION(phy_config_done); static void transmit_phy_packet_callback(struct fw_packet *packet, struct fw_card *card, int status) { - trace_async_phy_outbound_complete((uintptr_t)packet, packet->generation, status, + trace_async_phy_outbound_complete((uintptr_t)packet, card->index, packet->generation, status, packet->timestamp); complete(&phy_config_done); } @@ -503,7 +504,7 @@ void fw_send_phy_config(struct fw_card *card, phy_config_packet.generation = generation; reinit_completion(&phy_config_done); - trace_async_phy_outbound_initiate((uintptr_t)&phy_config_packet, + trace_async_phy_outbound_initiate((uintptr_t)&phy_config_packet, card->index, phy_config_packet.generation, phy_config_packet.header[1], phy_config_packet.header[2]); @@ -674,7 +675,7 @@ static void free_response_callback(struct fw_packet *packet, { struct fw_request *request = container_of(packet, struct fw_request, response); - trace_async_response_outbound_complete((uintptr_t)request, packet->generation, + trace_async_response_outbound_complete((uintptr_t)request, card->index, packet->generation, packet->speed, status, packet->timestamp); // Decrease the reference count since not at in-flight. @@ -879,9 +880,10 @@ void fw_send_response(struct fw_card *card, // Increase the reference count so that the object is kept during in-flight. fw_request_get(request); - trace_async_response_outbound_initiate((uintptr_t)request, request->response.generation, - request->response.speed, request->response.header, - data, data ? data_length / 4 : 0); + trace_async_response_outbound_initiate((uintptr_t)request, card->index, + request->response.generation, request->response.speed, + request->response.header, data, + data ? data_length / 4 : 0); card->driver->send_response(card, &request->response); } @@ -995,7 +997,7 @@ void fw_core_handle_request(struct fw_card *card, struct fw_packet *p) tcode = async_header_get_tcode(p->header); if (tcode_is_link_internal(tcode)) { - trace_async_phy_inbound((uintptr_t)p, p->generation, p->ack, p->timestamp, + trace_async_phy_inbound((uintptr_t)p, card->index, p->generation, p->ack, p->timestamp, p->header[1], p->header[2]); fw_cdev_handle_phy_packet(card, p); return; @@ -1007,8 +1009,8 @@ void fw_core_handle_request(struct fw_card *card, struct fw_packet *p) return; } - trace_async_request_inbound((uintptr_t)request, p->generation, p->speed, p->ack, - p->timestamp, p->header, request->data, + trace_async_request_inbound((uintptr_t)request, card->index, p->generation, p->speed, + p->ack, p->timestamp, p->header, request->data, tcode_is_read_request(tcode) ? 0 : request->length / 4); offset = async_header_get_offset(p->header); @@ -1078,8 +1080,8 @@ void fw_core_handle_response(struct fw_card *card, struct fw_packet *p) } spin_unlock_irqrestore(&card->lock, flags); - trace_async_response_inbound((uintptr_t)t, p->generation, p->speed, p->ack, p->timestamp, - p->header, data, data_length / 4); + trace_async_response_inbound((uintptr_t)t, card->index, p->generation, p->speed, p->ack, + p->timestamp, p->header, data, data_length / 4); if (!t) { timed_out: diff --git a/drivers/firmware/efi/memmap.c b/drivers/firmware/efi/memmap.c index 3365944f7965..34109fd86c55 100644 --- a/drivers/firmware/efi/memmap.c +++ b/drivers/firmware/efi/memmap.c @@ -15,10 +15,6 @@ #include <asm/early_ioremap.h> #include <asm/efi.h> -#ifndef __efi_memmap_free -#define __efi_memmap_free(phys, size, flags) do { } while (0) -#endif - /** * __efi_memmap_init - Common code for mapping the EFI memory map * @data: EFI memory map data @@ -51,11 +47,6 @@ int __init __efi_memmap_init(struct efi_memory_map_data *data) return -ENOMEM; } - if (efi.memmap.flags & (EFI_MEMMAP_MEMBLOCK | EFI_MEMMAP_SLAB)) - __efi_memmap_free(efi.memmap.phys_map, - efi.memmap.desc_size * efi.memmap.nr_map, - efi.memmap.flags); - map.phys_map = data->phys_map; map.nr_map = data->size / data->desc_size; map.map_end = map.map + data->size; diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index 026444eeb5c6..d0aa277fc3bf 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -450,6 +450,7 @@ config DRM_PRIVACY_SCREEN config DRM_WERROR bool "Compile the drm subsystem with warnings as errors" depends on DRM && EXPERT + depends on !WERROR default n help A kernel build should not cause any compiler warnings, and this diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index 67c234bcf89f..3adaa4670103 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -108,6 +108,7 @@ int amdgpu_gem_object_create(struct amdgpu_device *adev, unsigned long size, memset(&bp, 0, sizeof(bp)); *obj = NULL; + flags |= AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE; bp.size = size; bp.byte_align = alignment; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 8d8c39be6129..c556c8b653fa 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -604,8 +604,6 @@ int amdgpu_bo_create(struct amdgpu_device *adev, if (!amdgpu_bo_support_uswc(bo->flags)) bo->flags &= ~AMDGPU_GEM_CREATE_CPU_GTT_USWC; - bo->flags |= AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE; - bo->tbo.bdev = &adev->mman.bdev; if (bp->domain & (AMDGPU_GEM_DOMAIN_GWS | AMDGPU_GEM_DOMAIN_OA | AMDGPU_GEM_DOMAIN_GDS)) diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_dev.c b/drivers/gpu/drm/arm/display/komeda/komeda_dev.c index 14ee79becacb..5ba62e637a61 100644 --- a/drivers/gpu/drm/arm/display/komeda/komeda_dev.c +++ b/drivers/gpu/drm/arm/display/komeda/komeda_dev.c @@ -12,10 +12,8 @@ #include <linux/platform_device.h> #include <linux/pm_runtime.h> #include <linux/dma-mapping.h> -#ifdef CONFIG_DEBUG_FS #include <linux/debugfs.h> #include <linux/seq_file.h> -#endif #include <drm/drm_print.h> @@ -43,7 +41,6 @@ static int komeda_register_show(struct seq_file *sf, void *x) DEFINE_SHOW_ATTRIBUTE(komeda_register); -#ifdef CONFIG_DEBUG_FS static void komeda_debugfs_init(struct komeda_dev *mdev) { if (!debugfs_initialized()) @@ -55,7 +52,6 @@ static void komeda_debugfs_init(struct komeda_dev *mdev) debugfs_create_x16("err_verbosity", 0664, mdev->debugfs_root, &mdev->err_verbosity); } -#endif static ssize_t core_id_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -265,9 +261,7 @@ struct komeda_dev *komeda_dev_create(struct device *dev) mdev->err_verbosity = KOMEDA_DEV_PRINT_ERR_EVENTS; -#ifdef CONFIG_DEBUG_FS komeda_debugfs_init(mdev); -#endif return mdev; @@ -286,9 +280,7 @@ void komeda_dev_destroy(struct komeda_dev *mdev) sysfs_remove_group(&dev->kobj, &komeda_sysfs_attr_group); -#ifdef CONFIG_DEBUG_FS debugfs_remove_recursive(mdev->debugfs_root); -#endif if (mdev->aclk) clk_prepare_enable(mdev->aclk); diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c b/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c index f3e744172673..f4e76b46ca32 100644 --- a/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c +++ b/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c @@ -259,7 +259,7 @@ komeda_component_get_avail_scaler(struct komeda_component *c, u32 avail_scalers; pipe_st = komeda_pipeline_get_state(c->pipeline, state); - if (!pipe_st) + if (IS_ERR_OR_NULL(pipe_st)) return NULL; avail_scalers = (pipe_st->active_comps & KOMEDA_PIPELINE_SCALERS) ^ diff --git a/drivers/gpu/drm/bridge/panel.c b/drivers/gpu/drm/bridge/panel.c index 32506524d9a2..fe5fb08c9fc4 100644 --- a/drivers/gpu/drm/bridge/panel.c +++ b/drivers/gpu/drm/bridge/panel.c @@ -360,9 +360,12 @@ EXPORT_SYMBOL(drm_panel_bridge_set_orientation); static void devm_drm_panel_bridge_release(struct device *dev, void *res) { - struct drm_bridge **bridge = res; + struct drm_bridge *bridge = *(struct drm_bridge **)res; - drm_panel_bridge_remove(*bridge); + if (!bridge) + return; + + drm_bridge_remove(bridge); } /** diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c index aa93129c3397..2166208a961d 100644 --- a/drivers/gpu/drm/drm_panel_orientation_quirks.c +++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c @@ -202,6 +202,12 @@ static const struct dmi_system_id orientation_data[] = { DMI_MATCH(DMI_BOARD_NAME, "NEXT"), }, .driver_data = (void *)&lcd800x1280_rightside_up, + }, { /* AYA NEO KUN */ + .matches = { + DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "AYANEO"), + DMI_MATCH(DMI_BOARD_NAME, "KUN"), + }, + .driver_data = (void *)&lcd1600x2560_rightside_up, }, { /* Chuwi HiBook (CWI514) */ .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "Hampoo"), diff --git a/drivers/gpu/drm/exynos/exynos_dp.c b/drivers/gpu/drm/exynos/exynos_dp.c index f48c4343f469..3e6d4c6aa877 100644 --- a/drivers/gpu/drm/exynos/exynos_dp.c +++ b/drivers/gpu/drm/exynos/exynos_dp.c @@ -285,7 +285,6 @@ struct platform_driver dp_driver = { .remove_new = exynos_dp_remove, .driver = { .name = "exynos-dp", - .owner = THIS_MODULE, .pm = pm_ptr(&exynos_dp_pm_ops), .of_match_table = exynos_dp_match, }, diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c index fab135308b70..11a720fef32b 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c +++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c @@ -309,6 +309,7 @@ static int vidi_get_modes(struct drm_connector *connector) struct vidi_context *ctx = ctx_from_connector(connector); struct edid *edid; int edid_len; + int count; /* * the edid data comes from user side and it would be set @@ -328,7 +329,11 @@ static int vidi_get_modes(struct drm_connector *connector) drm_connector_update_edid_property(connector, edid); - return drm_add_edid_modes(connector, edid); + count = drm_add_edid_modes(connector, edid); + + kfree(edid); + + return count; } static const struct drm_connector_helper_funcs vidi_connector_helper_funcs = { diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c index e968824a4c72..1e26cd4f8347 100644 --- a/drivers/gpu/drm/exynos/exynos_hdmi.c +++ b/drivers/gpu/drm/exynos/exynos_hdmi.c @@ -887,11 +887,11 @@ static int hdmi_get_modes(struct drm_connector *connector) int ret; if (!hdata->ddc_adpt) - return 0; + goto no_edid; edid = drm_get_edid(connector, hdata->ddc_adpt); if (!edid) - return 0; + goto no_edid; hdata->dvi_mode = !connector->display_info.is_hdmi; DRM_DEV_DEBUG_KMS(hdata->dev, "%s : width[%d] x height[%d]\n", @@ -906,6 +906,9 @@ static int hdmi_get_modes(struct drm_connector *connector) kfree(edid); return ret; + +no_edid: + return drm_add_modes_noedid(connector, 640, 480); } static int hdmi_find_phy_conf(struct hdmi_context *hdata, u32 pixel_clock) diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c index b5f605751b0a..de811e2265da 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c @@ -952,6 +952,13 @@ static void mtk_drm_remove(struct platform_device *pdev) of_node_put(private->comp_node[i]); } +static void mtk_drm_shutdown(struct platform_device *pdev) +{ + struct mtk_drm_private *private = platform_get_drvdata(pdev); + + drm_atomic_helper_shutdown(private->drm); +} + static int mtk_drm_sys_prepare(struct device *dev) { struct mtk_drm_private *private = dev_get_drvdata(dev); @@ -983,6 +990,7 @@ static const struct dev_pm_ops mtk_drm_pm_ops = { static struct platform_driver mtk_drm_platform_driver = { .probe = mtk_drm_probe, .remove_new = mtk_drm_remove, + .shutdown = mtk_drm_shutdown, .driver = { .name = "mediatek-drm", .pm = &mtk_drm_pm_ops, diff --git a/drivers/gpu/drm/nouveau/dispnv04/disp.c b/drivers/gpu/drm/nouveau/dispnv04/disp.c index 13705c5f1497..4b7497a8755c 100644 --- a/drivers/gpu/drm/nouveau/dispnv04/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv04/disp.c @@ -68,7 +68,7 @@ nv04_display_fini(struct drm_device *dev, bool runtime, bool suspend) if (nv_two_heads(dev)) NVWriteCRTC(dev, 1, NV_PCRTC_INTR_EN_0, 0); - if (!runtime) + if (!runtime && !drm->headless) cancel_work_sync(&drm->hpd_work); if (!suspend) diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index 88728a0b2c25..674dc567e179 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -2680,7 +2680,7 @@ nv50_display_fini(struct drm_device *dev, bool runtime, bool suspend) nv50_mstm_fini(nouveau_encoder(encoder)); } - if (!runtime) + if (!runtime && !drm->headless) cancel_work_sync(&drm->hpd_work); } diff --git a/drivers/gpu/drm/nouveau/nouveau_bios.c b/drivers/gpu/drm/nouveau/nouveau_bios.c index 79cfab53f80e..8c3c1f1e01c5 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bios.c +++ b/drivers/gpu/drm/nouveau/nouveau_bios.c @@ -43,11 +43,6 @@ #define BIOSLOG(sip, fmt, arg...) NV_DEBUG(sip->dev, fmt, ##arg) #define LOG_OLD_VALUE(x) -struct init_exec { - bool execute; - bool repeat; -}; - static bool nv_cksum(const uint8_t *data, unsigned int length) { /* diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c index aed5d5b51b43..d4725a968827 100644 --- a/drivers/gpu/drm/nouveau/nouveau_display.c +++ b/drivers/gpu/drm/nouveau/nouveau_display.c @@ -450,6 +450,9 @@ nouveau_display_hpd_resume(struct drm_device *dev) { struct nouveau_drm *drm = nouveau_drm(dev); + if (drm->headless) + return; + spin_lock_irq(&drm->hpd_lock); drm->hpd_pending = ~0; spin_unlock_irq(&drm->hpd_lock); @@ -635,7 +638,7 @@ nouveau_display_fini(struct drm_device *dev, bool suspend, bool runtime) } drm_connector_list_iter_end(&conn_iter); - if (!runtime) + if (!runtime && !drm->headless) cancel_work_sync(&drm->hpd_work); drm_kms_helper_poll_disable(dev); @@ -729,6 +732,7 @@ nouveau_display_create(struct drm_device *dev) /* no display hw */ if (ret == -ENODEV) { ret = 0; + drm->headless = true; goto disp_create_err; } diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h index e239c6bf4afa..25fca98a20bc 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drv.h +++ b/drivers/gpu/drm/nouveau/nouveau_drv.h @@ -276,6 +276,7 @@ struct nouveau_drm { /* modesetting */ struct nvbios vbios; struct nouveau_display *display; + bool headless; struct work_struct hpd_work; spinlock_t hpd_lock; u32 hpd_pending; diff --git a/drivers/gpu/drm/renesas/shmobile/shmob_drm_drv.c b/drivers/gpu/drm/renesas/shmobile/shmob_drm_drv.c index e83c3e52251d..0250d5f00bf1 100644 --- a/drivers/gpu/drm/renesas/shmobile/shmob_drm_drv.c +++ b/drivers/gpu/drm/renesas/shmobile/shmob_drm_drv.c @@ -171,6 +171,13 @@ static void shmob_drm_remove(struct platform_device *pdev) drm_kms_helper_poll_fini(ddev); } +static void shmob_drm_shutdown(struct platform_device *pdev) +{ + struct shmob_drm_device *sdev = platform_get_drvdata(pdev); + + drm_atomic_helper_shutdown(&sdev->ddev); +} + static int shmob_drm_probe(struct platform_device *pdev) { struct shmob_drm_platform_data *pdata = pdev->dev.platform_data; @@ -273,6 +280,7 @@ static const struct of_device_id shmob_drm_of_table[] __maybe_unused = { static struct platform_driver shmob_drm_platform_driver = { .probe = shmob_drm_probe, .remove_new = shmob_drm_remove, + .shutdown = shmob_drm_shutdown, .driver = { .name = "shmob-drm", .of_match_table = of_match_ptr(shmob_drm_of_table), diff --git a/drivers/gpu/drm/xe/xe_gt_idle.c b/drivers/gpu/drm/xe/xe_gt_idle.c index 8fc0f3f6ecc5..944770fb2daf 100644 --- a/drivers/gpu/drm/xe/xe_gt_idle.c +++ b/drivers/gpu/drm/xe/xe_gt_idle.c @@ -147,6 +147,13 @@ static const struct attribute *gt_idle_attrs[] = { static void gt_idle_sysfs_fini(struct drm_device *drm, void *arg) { struct kobject *kobj = arg; + struct xe_gt *gt = kobj_to_gt(kobj->parent); + + if (gt_to_xe(gt)->info.skip_guc_pc) { + XE_WARN_ON(xe_force_wake_get(gt_to_fw(gt), XE_FW_GT)); + xe_gt_idle_disable_c6(gt); + xe_force_wake_put(gt_to_fw(gt), XE_FW_GT); + } sysfs_remove_files(kobj, gt_idle_attrs); kobject_put(kobj); @@ -199,7 +206,7 @@ void xe_gt_idle_enable_c6(struct xe_gt *gt) void xe_gt_idle_disable_c6(struct xe_gt *gt) { xe_device_assert_mem_access(gt_to_xe(gt)); - xe_force_wake_assert_held(gt_to_fw(gt), XE_FORCEWAKE_ALL); + xe_force_wake_assert_held(gt_to_fw(gt), XE_FW_GT); xe_mmio_write32(gt, PG_ENABLE, 0); xe_mmio_write32(gt, RC_CONTROL, 0); diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c index 476d613333a9..6c2cfc54442c 100644 --- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c +++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c @@ -1274,6 +1274,9 @@ static void pf_reset_vf_lmtt(struct xe_device *xe, unsigned int vfid) struct xe_tile *tile; unsigned int tid; + xe_assert(xe, IS_DGFX(xe)); + xe_assert(xe, IS_SRIOV_PF(xe)); + for_each_tile(tile, xe, tid) { lmtt = &tile->sriov.pf.lmtt; xe_lmtt_drop_pages(lmtt, vfid); @@ -1292,6 +1295,9 @@ static int pf_update_vf_lmtt(struct xe_device *xe, unsigned int vfid) unsigned int tid; int err; + xe_assert(xe, IS_DGFX(xe)); + xe_assert(xe, IS_SRIOV_PF(xe)); + total = 0; for_each_tile(tile, xe, tid) total += pf_get_vf_config_lmem(tile->primary_gt, vfid); @@ -1337,6 +1343,7 @@ fail: static void pf_release_vf_config_lmem(struct xe_gt *gt, struct xe_gt_sriov_config *config) { + xe_gt_assert(gt, IS_DGFX(gt_to_xe(gt))); xe_gt_assert(gt, !xe_gt_is_media_type(gt)); lockdep_assert_held(xe_gt_sriov_pf_master_mutex(gt)); @@ -1355,6 +1362,7 @@ static int pf_provision_vf_lmem(struct xe_gt *gt, unsigned int vfid, u64 size) int err; xe_gt_assert(gt, vfid); + xe_gt_assert(gt, IS_DGFX(xe)); xe_gt_assert(gt, !xe_gt_is_media_type(gt)); size = round_up(size, pf_get_lmem_alignment(gt)); @@ -1745,11 +1753,14 @@ static void pf_reset_config_sched(struct xe_gt *gt, struct xe_gt_sriov_config *c static void pf_release_vf_config(struct xe_gt *gt, unsigned int vfid) { struct xe_gt_sriov_config *config = pf_pick_vf_config(gt, vfid); + struct xe_device *xe = gt_to_xe(gt); if (!xe_gt_is_media_type(gt)) { pf_release_vf_config_ggtt(gt, config); - pf_release_vf_config_lmem(gt, config); - pf_update_vf_lmtt(gt_to_xe(gt), vfid); + if (IS_DGFX(xe)) { + pf_release_vf_config_lmem(gt, config); + pf_update_vf_lmtt(xe, vfid); + } } pf_release_config_ctxs(gt, config); pf_release_config_dbs(gt, config); diff --git a/drivers/gpu/drm/xe/xe_guc_pc.c b/drivers/gpu/drm/xe/xe_guc_pc.c index 509649d0e65e..23382ced4ea7 100644 --- a/drivers/gpu/drm/xe/xe_guc_pc.c +++ b/drivers/gpu/drm/xe/xe_guc_pc.c @@ -895,12 +895,6 @@ int xe_guc_pc_stop(struct xe_guc_pc *pc) static void xe_guc_pc_fini(struct drm_device *drm, void *arg) { struct xe_guc_pc *pc = arg; - struct xe_device *xe = pc_to_xe(pc); - - if (xe->info.skip_guc_pc) { - xe_gt_idle_disable_c6(pc_to_gt(pc)); - return; - } XE_WARN_ON(xe_force_wake_get(gt_to_fw(pc_to_gt(pc)), XE_FORCEWAKE_ALL)); XE_WARN_ON(xe_guc_pc_gucrc_disable(pc)); diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c index d42b3f33bd7a..aca7a9af6e84 100644 --- a/drivers/gpu/drm/xe/xe_ring_ops.c +++ b/drivers/gpu/drm/xe/xe_ring_ops.c @@ -80,6 +80,16 @@ static int emit_store_imm_ggtt(u32 addr, u32 value, u32 *dw, int i) return i; } +static int emit_flush_dw(u32 *dw, int i) +{ + dw[i++] = MI_FLUSH_DW | MI_FLUSH_IMM_DW; + dw[i++] = 0; + dw[i++] = 0; + dw[i++] = 0; + + return i; +} + static int emit_flush_imm_ggtt(u32 addr, u32 value, bool invalidate_tlb, u32 *dw, int i) { @@ -234,10 +244,12 @@ static void __emit_job_gen12_simple(struct xe_sched_job *job, struct xe_lrc *lrc i = emit_bb_start(batch_addr, ppgtt_flag, dw, i); - if (job->user_fence.used) + if (job->user_fence.used) { + i = emit_flush_dw(dw, i); i = emit_store_imm_ppgtt_posted(job->user_fence.addr, job->user_fence.value, dw, i); + } i = emit_flush_imm_ggtt(xe_lrc_seqno_ggtt_addr(lrc), seqno, false, dw, i); @@ -293,10 +305,12 @@ static void __emit_job_gen12_video(struct xe_sched_job *job, struct xe_lrc *lrc, i = emit_bb_start(batch_addr, ppgtt_flag, dw, i); - if (job->user_fence.used) + if (job->user_fence.used) { + i = emit_flush_dw(dw, i); i = emit_store_imm_ppgtt_posted(job->user_fence.addr, job->user_fence.value, dw, i); + } i = emit_flush_imm_ggtt(xe_lrc_seqno_ggtt_addr(lrc), seqno, false, dw, i); diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c index a8ad728354cb..e0d676c74f14 100644 --- a/drivers/hv/hv.c +++ b/drivers/hv/hv.c @@ -45,8 +45,8 @@ int hv_init(void) * This involves a hypercall. */ int hv_post_message(union hv_connection_id connection_id, - enum hv_message_type message_type, - void *payload, size_t payload_size) + enum hv_message_type message_type, + void *payload, size_t payload_size) { struct hv_input_post_message *aligned_msg; unsigned long flags; @@ -86,7 +86,7 @@ int hv_post_message(union hv_connection_id connection_id, status = HV_STATUS_INVALID_PARAMETER; } else { status = hv_do_hypercall(HVCALL_POST_MESSAGE, - aligned_msg, NULL); + aligned_msg, NULL); } local_irq_restore(flags); @@ -111,7 +111,7 @@ int hv_synic_alloc(void) hv_context.hv_numa_map = kcalloc(nr_node_ids, sizeof(struct cpumask), GFP_KERNEL); - if (hv_context.hv_numa_map == NULL) { + if (!hv_context.hv_numa_map) { pr_err("Unable to allocate NUMA map\n"); goto err; } @@ -120,11 +120,11 @@ int hv_synic_alloc(void) hv_cpu = per_cpu_ptr(hv_context.cpu_context, cpu); tasklet_init(&hv_cpu->msg_dpc, - vmbus_on_msg_dpc, (unsigned long) hv_cpu); + vmbus_on_msg_dpc, (unsigned long)hv_cpu); if (ms_hyperv.paravisor_present && hv_isolation_type_tdx()) { hv_cpu->post_msg_page = (void *)get_zeroed_page(GFP_ATOMIC); - if (hv_cpu->post_msg_page == NULL) { + if (!hv_cpu->post_msg_page) { pr_err("Unable to allocate post msg page\n"); goto err; } @@ -147,14 +147,14 @@ int hv_synic_alloc(void) if (!ms_hyperv.paravisor_present && !hv_root_partition) { hv_cpu->synic_message_page = (void *)get_zeroed_page(GFP_ATOMIC); - if (hv_cpu->synic_message_page == NULL) { + if (!hv_cpu->synic_message_page) { pr_err("Unable to allocate SYNIC message page\n"); goto err; } hv_cpu->synic_event_page = (void *)get_zeroed_page(GFP_ATOMIC); - if (hv_cpu->synic_event_page == NULL) { + if (!hv_cpu->synic_event_page) { pr_err("Unable to allocate SYNIC event page\n"); free_page((unsigned long)hv_cpu->synic_message_page); @@ -203,14 +203,13 @@ err: return ret; } - void hv_synic_free(void) { int cpu, ret; for_each_present_cpu(cpu) { - struct hv_per_cpu_context *hv_cpu - = per_cpu_ptr(hv_context.cpu_context, cpu); + struct hv_per_cpu_context *hv_cpu = + per_cpu_ptr(hv_context.cpu_context, cpu); /* It's better to leak the page if the encryption fails. */ if (ms_hyperv.paravisor_present && hv_isolation_type_tdx()) { @@ -262,8 +261,8 @@ void hv_synic_free(void) */ void hv_synic_enable_regs(unsigned int cpu) { - struct hv_per_cpu_context *hv_cpu - = per_cpu_ptr(hv_context.cpu_context, cpu); + struct hv_per_cpu_context *hv_cpu = + per_cpu_ptr(hv_context.cpu_context, cpu); union hv_synic_simp simp; union hv_synic_siefp siefp; union hv_synic_sint shared_sint; @@ -277,8 +276,8 @@ void hv_synic_enable_regs(unsigned int cpu) /* Mask out vTOM bit. ioremap_cache() maps decrypted */ u64 base = (simp.base_simp_gpa << HV_HYP_PAGE_SHIFT) & ~ms_hyperv.shared_gpa_boundary; - hv_cpu->synic_message_page - = (void *)ioremap_cache(base, HV_HYP_PAGE_SIZE); + hv_cpu->synic_message_page = + (void *)ioremap_cache(base, HV_HYP_PAGE_SIZE); if (!hv_cpu->synic_message_page) pr_err("Fail to map synic message page.\n"); } else { @@ -296,8 +295,8 @@ void hv_synic_enable_regs(unsigned int cpu) /* Mask out vTOM bit. ioremap_cache() maps decrypted */ u64 base = (siefp.base_siefp_gpa << HV_HYP_PAGE_SHIFT) & ~ms_hyperv.shared_gpa_boundary; - hv_cpu->synic_event_page - = (void *)ioremap_cache(base, HV_HYP_PAGE_SIZE); + hv_cpu->synic_event_page = + (void *)ioremap_cache(base, HV_HYP_PAGE_SIZE); if (!hv_cpu->synic_event_page) pr_err("Fail to map synic event page.\n"); } else { @@ -348,8 +347,8 @@ int hv_synic_init(unsigned int cpu) */ void hv_synic_disable_regs(unsigned int cpu) { - struct hv_per_cpu_context *hv_cpu - = per_cpu_ptr(hv_context.cpu_context, cpu); + struct hv_per_cpu_context *hv_cpu = + per_cpu_ptr(hv_context.cpu_context, cpu); union hv_synic_sint shared_sint; union hv_synic_simp simp; union hv_synic_siefp siefp; diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c index e000fa3b9f97..0e7427c2baf5 100644 --- a/drivers/hv/hv_balloon.c +++ b/drivers/hv/hv_balloon.c @@ -25,6 +25,7 @@ #include <linux/notifier.h> #include <linux/percpu_counter.h> #include <linux/page_reporting.h> +#include <linux/sizes.h> #include <linux/hyperv.h> #include <asm/hyperv-tlfs.h> @@ -41,8 +42,6 @@ * Begin protocol definitions. */ - - /* * Protocol versions. The low word is the minor version, the high word the major * version. @@ -71,8 +70,6 @@ enum { DYNMEM_PROTOCOL_VERSION_CURRENT = DYNMEM_PROTOCOL_VERSION_WIN10 }; - - /* * Message Types */ @@ -101,7 +98,6 @@ enum dm_message_type { DM_VERSION_1_MAX = 12 }; - /* * Structures defining the dynamic memory management * protocol. @@ -115,7 +111,6 @@ union dm_version { __u32 version; } __packed; - union dm_caps { struct { __u64 balloon:1; @@ -148,8 +143,6 @@ union dm_mem_page_range { __u64 page_range; } __packed; - - /* * The header for all dynamic memory messages: * @@ -174,7 +167,6 @@ struct dm_message { __u8 data[]; /* enclosed message */ } __packed; - /* * Specific message types supporting the dynamic memory protocol. */ @@ -271,7 +263,6 @@ struct dm_status { __u32 io_diff; } __packed; - /* * Message to ask the guest to allocate memory - balloon up message. * This message is sent from the host to the guest. The guest may not be @@ -286,14 +277,13 @@ struct dm_balloon { __u32 reservedz; } __packed; - /* * Balloon response message; this message is sent from the guest * to the host in response to the balloon message. * * reservedz: Reserved; must be set to zero. * more_pages: If FALSE, this is the last message of the transaction. - * if TRUE there will atleast one more message from the guest. + * if TRUE there will be at least one more message from the guest. * * range_count: The number of ranges in the range array. * @@ -314,7 +304,7 @@ struct dm_balloon_response { * to the guest to give guest more memory. * * more_pages: If FALSE, this is the last message of the transaction. - * if TRUE there will atleast one more message from the guest. + * if TRUE there will be at least one more message from the guest. * * reservedz: Reserved; must be set to zero. * @@ -342,7 +332,6 @@ struct dm_unballoon_response { struct dm_header hdr; } __packed; - /* * Hot add request message. Message sent from the host to the guest. * @@ -390,7 +379,6 @@ enum dm_info_type { MAX_INFO_TYPE }; - /* * Header for the information message. */ @@ -425,11 +413,11 @@ struct dm_info_msg { * The range start_pfn : end_pfn specifies the range * that the host has asked us to hot add. The range * start_pfn : ha_end_pfn specifies the range that we have - * currently hot added. We hot add in multiples of 128M - * chunks; it is possible that we may not be able to bring - * online all the pages in the region. The range + * currently hot added. We hot add in chunks equal to the + * memory block size; it is possible that we may not be able + * to bring online all the pages in the region. The range * covered_start_pfn:covered_end_pfn defines the pages that can - * be brough online. + * be brought online. */ struct hv_hotadd_state { @@ -480,10 +468,10 @@ static unsigned long last_post_time; static int hv_hypercall_multi_failure; -module_param(hot_add, bool, (S_IRUGO | S_IWUSR)); +module_param(hot_add, bool, 0644); MODULE_PARM_DESC(hot_add, "If set attempt memory hot_add"); -module_param(pressure_report_delay, uint, (S_IRUGO | S_IWUSR)); +module_param(pressure_report_delay, uint, 0644); MODULE_PARM_DESC(pressure_report_delay, "Delay in secs in reporting pressure"); static atomic_t trans_id = ATOMIC_INIT(0); @@ -502,11 +490,13 @@ enum hv_dm_state { DM_INIT_ERROR }; - static __u8 recv_buffer[HV_HYP_PAGE_SIZE]; static __u8 balloon_up_send_buffer[HV_HYP_PAGE_SIZE]; + +static unsigned long ha_pages_in_chunk; +#define HA_BYTES_IN_CHUNK (ha_pages_in_chunk << PAGE_SHIFT) + #define PAGES_IN_2M (2 * 1024 * 1024 / PAGE_SIZE) -#define HA_CHUNK (128 * 1024 * 1024 / PAGE_SIZE) struct hv_dynmem_device { struct hv_device *dev; @@ -595,12 +585,12 @@ static inline bool has_pfn_is_backed(struct hv_hotadd_state *has, struct hv_hotadd_gap *gap; /* The page is not backed. */ - if ((pfn < has->covered_start_pfn) || (pfn >= has->covered_end_pfn)) + if (pfn < has->covered_start_pfn || pfn >= has->covered_end_pfn) return false; /* Check for gaps. */ list_for_each_entry(gap, &has->gap_list, list) { - if ((pfn >= gap->start_pfn) && (pfn < gap->end_pfn)) + if (pfn >= gap->start_pfn && pfn < gap->end_pfn) return false; } @@ -724,28 +714,21 @@ static void hv_mem_hot_add(unsigned long start, unsigned long size, unsigned long processed_pfn; unsigned long total_pfn = pfn_count; - for (i = 0; i < (size/HA_CHUNK); i++) { - start_pfn = start + (i * HA_CHUNK); + for (i = 0; i < (size/ha_pages_in_chunk); i++) { + start_pfn = start + (i * ha_pages_in_chunk); scoped_guard(spinlock_irqsave, &dm_device.ha_lock) { - has->ha_end_pfn += HA_CHUNK; - - if (total_pfn > HA_CHUNK) { - processed_pfn = HA_CHUNK; - total_pfn -= HA_CHUNK; - } else { - processed_pfn = total_pfn; - total_pfn = 0; - } - - has->covered_end_pfn += processed_pfn; + has->ha_end_pfn += ha_pages_in_chunk; + processed_pfn = umin(total_pfn, ha_pages_in_chunk); + total_pfn -= processed_pfn; + has->covered_end_pfn += processed_pfn; } reinit_completion(&dm_device.ol_waitevent); nid = memory_add_physaddr_to_nid(PFN_PHYS(start_pfn)); ret = add_memory(nid, PFN_PHYS((start_pfn)), - (HA_CHUNK << PAGE_SHIFT), MHP_MERGE_RESOURCE); + HA_BYTES_IN_CHUNK, MHP_MERGE_RESOURCE); if (ret) { pr_err("hot_add memory failed error is %d\n", ret); @@ -760,7 +743,7 @@ static void hv_mem_hot_add(unsigned long start, unsigned long size, do_hot_add = false; } scoped_guard(spinlock_irqsave, &dm_device.ha_lock) { - has->ha_end_pfn -= HA_CHUNK; + has->ha_end_pfn -= ha_pages_in_chunk; has->covered_end_pfn -= processed_pfn; } break; @@ -787,8 +770,8 @@ static void hv_online_page(struct page *pg, unsigned int order) guard(spinlock_irqsave)(&dm_device.ha_lock); list_for_each_entry(has, &dm_device.ha_region_list, list) { /* The page belongs to a different HAS. */ - if ((pfn < has->start_pfn) || - (pfn + (1UL << order) > has->end_pfn)) + if (pfn < has->start_pfn || + (pfn + (1UL << order) > has->end_pfn)) continue; hv_bring_pgs_online(has, pfn, 1UL << order); @@ -800,7 +783,7 @@ static int pfn_covered(unsigned long start_pfn, unsigned long pfn_cnt) { struct hv_hotadd_state *has; struct hv_hotadd_gap *gap; - unsigned long residual, new_inc; + unsigned long residual; int ret = 0; guard(spinlock_irqsave)(&dm_device.ha_lock); @@ -836,15 +819,9 @@ static int pfn_covered(unsigned long start_pfn, unsigned long pfn_cnt) * our current limit; extend it. */ if ((start_pfn + pfn_cnt) > has->end_pfn) { + /* Extend the region by multiples of ha_pages_in_chunk */ residual = (start_pfn + pfn_cnt - has->end_pfn); - /* - * Extend the region by multiples of HA_CHUNK. - */ - new_inc = (residual / HA_CHUNK) * HA_CHUNK; - if (residual % HA_CHUNK) - new_inc += HA_CHUNK; - - has->end_pfn += new_inc; + has->end_pfn += ALIGN(residual, ha_pages_in_chunk); } ret = 1; @@ -855,7 +832,7 @@ static int pfn_covered(unsigned long start_pfn, unsigned long pfn_cnt) } static unsigned long handle_pg_range(unsigned long pg_start, - unsigned long pg_count) + unsigned long pg_count) { unsigned long start_pfn = pg_start; unsigned long pfn_cnt = pg_count; @@ -866,7 +843,7 @@ static unsigned long handle_pg_range(unsigned long pg_start, unsigned long res = 0, flags; pr_debug("Hot adding %lu pages starting at pfn 0x%lx.\n", pg_count, - pg_start); + pg_start); spin_lock_irqsave(&dm_device.ha_lock, flags); list_for_each_entry(has, &dm_device.ha_region_list, list) { @@ -902,22 +879,19 @@ static unsigned long handle_pg_range(unsigned long pg_start, if (start_pfn > has->start_pfn && online_section_nr(pfn_to_section_nr(start_pfn))) hv_bring_pgs_online(has, start_pfn, pgs_ol); - } - if ((has->ha_end_pfn < has->end_pfn) && (pfn_cnt > 0)) { + if (has->ha_end_pfn < has->end_pfn && pfn_cnt > 0) { /* * We have some residual hot add range * that needs to be hot added; hot add * it now. Hot add a multiple of - * HA_CHUNK that fully covers the pages + * ha_pages_in_chunk that fully covers the pages * we have. */ size = (has->end_pfn - has->ha_end_pfn); if (pfn_cnt <= size) { - size = ((pfn_cnt / HA_CHUNK) * HA_CHUNK); - if (pfn_cnt % HA_CHUNK) - size += HA_CHUNK; + size = ALIGN(pfn_cnt, ha_pages_in_chunk); } else { pfn_cnt = size; } @@ -1010,10 +984,7 @@ static void hot_add_req(struct work_struct *dummy) rg_start = dm->ha_wrk.ha_region_range.finfo.start_page; rg_sz = dm->ha_wrk.ha_region_range.finfo.page_cnt; - if ((rg_start == 0) && (!dm->host_specified_ha_region)) { - unsigned long region_size; - unsigned long region_start; - + if (rg_start == 0 && !dm->host_specified_ha_region) { /* * The host has not specified the hot-add region. * Based on the hot-add page range being specified, @@ -1021,19 +992,13 @@ static void hot_add_req(struct work_struct *dummy) * that need to be hot-added while ensuring the alignment * and size requirements of Linux as it relates to hot-add. */ - region_size = (pfn_cnt / HA_CHUNK) * HA_CHUNK; - if (pfn_cnt % HA_CHUNK) - region_size += HA_CHUNK; - - region_start = (pg_start / HA_CHUNK) * HA_CHUNK; - - rg_start = region_start; - rg_sz = region_size; + rg_start = ALIGN_DOWN(pg_start, ha_pages_in_chunk); + rg_sz = ALIGN(pfn_cnt, ha_pages_in_chunk); } if (do_hot_add) resp.page_count = process_hot_add(pg_start, pfn_cnt, - rg_start, rg_sz); + rg_start, rg_sz); dm->num_pages_added += resp.page_count; #endif @@ -1211,11 +1176,10 @@ static void post_status(struct hv_dynmem_device *dm) sizeof(struct dm_status), (unsigned long)NULL, VM_PKT_DATA_INBAND, 0); - } static void free_balloon_pages(struct hv_dynmem_device *dm, - union dm_mem_page_range *range_array) + union dm_mem_page_range *range_array) { int num_pages = range_array->finfo.page_cnt; __u64 start_frame = range_array->finfo.start_page; @@ -1231,8 +1195,6 @@ static void free_balloon_pages(struct hv_dynmem_device *dm, } } - - static unsigned int alloc_balloon_pages(struct hv_dynmem_device *dm, unsigned int num_pages, struct dm_balloon_response *bl_resp, @@ -1278,7 +1240,6 @@ static unsigned int alloc_balloon_pages(struct hv_dynmem_device *dm, page_to_pfn(pg); bl_resp->range_array[i].finfo.page_cnt = alloc_unit; bl_resp->hdr.size += sizeof(union dm_mem_page_range); - } return i * alloc_unit; @@ -1332,7 +1293,7 @@ static void balloon_up(struct work_struct *dummy) if (num_ballooned == 0 || num_ballooned == num_pages) { pr_debug("Ballooned %u out of %u requested pages.\n", - num_pages, dm_device.balloon_wrk.num_pages); + num_pages, dm_device.balloon_wrk.num_pages); bl_resp->more_pages = 0; done = true; @@ -1366,16 +1327,15 @@ static void balloon_up(struct work_struct *dummy) for (i = 0; i < bl_resp->range_count; i++) free_balloon_pages(&dm_device, - &bl_resp->range_array[i]); + &bl_resp->range_array[i]); done = true; } } - } static void balloon_down(struct hv_dynmem_device *dm, - struct dm_unballoon_request *req) + struct dm_unballoon_request *req) { union dm_mem_page_range *range_array = req->range_array; int range_count = req->range_count; @@ -1389,7 +1349,7 @@ static void balloon_down(struct hv_dynmem_device *dm, } pr_debug("Freed %u ballooned pages.\n", - prev_pages_ballooned - dm->num_pages_ballooned); + prev_pages_ballooned - dm->num_pages_ballooned); if (req->more_pages == 1) return; @@ -1414,8 +1374,7 @@ static int dm_thread_func(void *dm_dev) struct hv_dynmem_device *dm = dm_dev; while (!kthread_should_stop()) { - wait_for_completion_interruptible_timeout( - &dm_device.config_event, 1*HZ); + wait_for_completion_interruptible_timeout(&dm_device.config_event, 1 * HZ); /* * The host expects us to post information on the memory * pressure every second. @@ -1439,9 +1398,8 @@ static int dm_thread_func(void *dm_dev) return 0; } - static void version_resp(struct hv_dynmem_device *dm, - struct dm_version_response *vresp) + struct dm_version_response *vresp) { struct dm_version_request version_req; int ret; @@ -1502,7 +1460,7 @@ version_error: } static void cap_resp(struct hv_dynmem_device *dm, - struct dm_capabilities_resp_msg *cap_resp) + struct dm_capabilities_resp_msg *cap_resp) { if (!cap_resp->is_accepted) { pr_err("Capabilities not accepted by host\n"); @@ -1535,7 +1493,7 @@ static void balloon_onchannelcallback(void *context) switch (dm_hdr->type) { case DM_VERSION_RESPONSE: version_resp(dm, - (struct dm_version_response *)dm_msg); + (struct dm_version_response *)dm_msg); break; case DM_CAPABILITIES_RESPONSE: @@ -1565,7 +1523,7 @@ static void balloon_onchannelcallback(void *context) dm->state = DM_BALLOON_DOWN; balloon_down(dm, - (struct dm_unballoon_request *)recv_buffer); + (struct dm_unballoon_request *)recv_buffer); break; case DM_MEM_HOT_ADD_REQUEST: @@ -1603,17 +1561,15 @@ static void balloon_onchannelcallback(void *context) default: pr_warn_ratelimited("Unhandled message: type: %d\n", dm_hdr->type); - } } - } #define HV_LARGE_REPORTING_ORDER 9 #define HV_LARGE_REPORTING_LEN (HV_HYP_PAGE_SIZE << \ HV_LARGE_REPORTING_ORDER) static int hv_free_page_report(struct page_reporting_dev_info *pr_dev_info, - struct scatterlist *sgl, unsigned int nents) + struct scatterlist *sgl, unsigned int nents) { unsigned long flags; struct hv_memory_hint *hint; @@ -1648,7 +1604,7 @@ static int hv_free_page_report(struct page_reporting_dev_info *pr_dev_info, */ /* page reporting for pages 2MB or higher */ - if (order >= HV_LARGE_REPORTING_ORDER ) { + if (order >= HV_LARGE_REPORTING_ORDER) { range->page.largepage = 1; range->page_size = HV_GPA_PAGE_RANGE_PAGE_SIZE_2MB; range->base_large_pfn = page_to_hvpfn( @@ -1662,23 +1618,21 @@ static int hv_free_page_report(struct page_reporting_dev_info *pr_dev_info, range->page.additional_pages = (sg->length / HV_HYP_PAGE_SIZE) - 1; } - } status = hv_do_rep_hypercall(HV_EXT_CALL_MEMORY_HEAT_HINT, nents, 0, hint, NULL); local_irq_restore(flags); if (!hv_result_success(status)) { - pr_err("Cold memory discard hypercall failed with status %llx\n", - status); + status); if (hv_hypercall_multi_failure > 0) hv_hypercall_multi_failure++; if (hv_result(status) == HV_STATUS_INVALID_PARAMETER) { pr_err("Underlying Hyper-V does not support order less than 9. Hypercall failed\n"); pr_err("Defaulting to page_reporting_order %d\n", - pageblock_order); + pageblock_order); page_reporting_order = pageblock_order; hv_hypercall_multi_failure++; return -EINVAL; @@ -1712,7 +1666,7 @@ static void enable_page_reporting(void) pr_err("Failed to enable cold memory discard: %d\n", ret); } else { pr_info("Cold memory discard hint enabled with order %d\n", - page_reporting_order); + page_reporting_order); } } @@ -1795,7 +1749,7 @@ static int balloon_connect_vsp(struct hv_device *dev) if (ret) goto out; - t = wait_for_completion_timeout(&dm_device.host_event, 5*HZ); + t = wait_for_completion_timeout(&dm_device.host_event, 5 * HZ); if (t == 0) { ret = -ETIMEDOUT; goto out; @@ -1831,10 +1785,13 @@ static int balloon_connect_vsp(struct hv_device *dev) cap_msg.caps.cap_bits.hot_add = hot_add_enabled(); /* - * Specify our alignment requirements as it relates - * memory hot-add. Specify 128MB alignment. + * Specify our alignment requirements for memory hot-add. The value is + * the log base 2 of the number of megabytes in a chunk. For example, + * with 256 MiB chunks, the value is 8. The number of MiB in a chunk + * must be a power of 2. */ - cap_msg.caps.cap_bits.hot_add_alignment = 7; + cap_msg.caps.cap_bits.hot_add_alignment = + ilog2(HA_BYTES_IN_CHUNK / SZ_1M); /* * Currently the host does not use these @@ -1850,7 +1807,7 @@ static int balloon_connect_vsp(struct hv_device *dev) if (ret) goto out; - t = wait_for_completion_timeout(&dm_device.host_event, 5*HZ); + t = wait_for_completion_timeout(&dm_device.host_event, 5 * HZ); if (t == 0) { ret = -ETIMEDOUT; goto out; @@ -1891,8 +1848,8 @@ static int hv_balloon_debug_show(struct seq_file *f, void *offset) char *sname; seq_printf(f, "%-22s: %u.%u\n", "host_version", - DYNMEM_MAJOR_VERSION(dm->version), - DYNMEM_MINOR_VERSION(dm->version)); + DYNMEM_MAJOR_VERSION(dm->version), + DYNMEM_MINOR_VERSION(dm->version)); seq_printf(f, "%-22s:", "capabilities"); if (ballooning_enabled()) @@ -1941,10 +1898,10 @@ static int hv_balloon_debug_show(struct seq_file *f, void *offset) seq_printf(f, "%-22s: %u\n", "pages_ballooned", dm->num_pages_ballooned); seq_printf(f, "%-22s: %lu\n", "total_pages_committed", - get_pages_committed(dm)); + get_pages_committed(dm)); seq_printf(f, "%-22s: %llu\n", "max_dynamic_page_count", - dm->max_dynamic_page_count); + dm->max_dynamic_page_count); return 0; } @@ -1954,7 +1911,7 @@ DEFINE_SHOW_ATTRIBUTE(hv_balloon_debug); static void hv_balloon_debugfs_init(struct hv_dynmem_device *b) { debugfs_create_file("hv-balloon", 0444, NULL, b, - &hv_balloon_debug_fops); + &hv_balloon_debug_fops); } static void hv_balloon_debugfs_exit(struct hv_dynmem_device *b) @@ -1984,8 +1941,23 @@ static int balloon_probe(struct hv_device *dev, hot_add = false; #ifdef CONFIG_MEMORY_HOTPLUG + /* + * Hot-add must operate in chunks that are of size equal to the + * memory block size because that's what the core add_memory() + * interface requires. The Hyper-V interface requires that the memory + * block size be a power of 2, which is guaranteed by the check in + * memory_dev_init(). + */ + ha_pages_in_chunk = memory_block_size_bytes() / PAGE_SIZE; do_hot_add = hot_add; #else + /* + * Without MEMORY_HOTPLUG, the guest returns a failure status for all + * hot add requests from Hyper-V, and the chunk size is used only to + * specify alignment to Hyper-V as required by the host/guest protocol. + * Somewhat arbitrarily, use 128 MiB. + */ + ha_pages_in_chunk = SZ_128M / PAGE_SIZE; do_hot_add = false; #endif dm_device.dev = dev; @@ -2097,7 +2069,6 @@ static int balloon_suspend(struct hv_device *hv_dev) tasklet_enable(&hv_dev->channel->callback_event); return 0; - } static int balloon_resume(struct hv_device *dev) @@ -2156,7 +2127,6 @@ static struct hv_driver balloon_drv = { static int __init init_balloon_drv(void) { - return vmbus_driver_register(&balloon_drv); } diff --git a/drivers/i2c/busses/i2c-at91-slave.c b/drivers/i2c/busses/i2c-at91-slave.c index d6eeea5166c0..131a67d9d4a6 100644 --- a/drivers/i2c/busses/i2c-at91-slave.c +++ b/drivers/i2c/busses/i2c-at91-slave.c @@ -106,8 +106,7 @@ static int at91_unreg_slave(struct i2c_client *slave) static u32 at91_twi_func(struct i2c_adapter *adapter) { - return I2C_FUNC_SLAVE | I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL - | I2C_FUNC_SMBUS_READ_BLOCK_DATA; + return I2C_FUNC_SLAVE; } static const struct i2c_algorithm at91_twi_algorithm_slave = { diff --git a/drivers/i2c/busses/i2c-designware-slave.c b/drivers/i2c/busses/i2c-designware-slave.c index 2e079cf20bb5..78e2c47e3d7d 100644 --- a/drivers/i2c/busses/i2c-designware-slave.c +++ b/drivers/i2c/busses/i2c-designware-slave.c @@ -220,7 +220,7 @@ static const struct i2c_algorithm i2c_dw_algo = { void i2c_dw_configure_slave(struct dw_i2c_dev *dev) { - dev->functionality = I2C_FUNC_SLAVE | DW_IC_DEFAULT_FUNCTIONALITY; + dev->functionality = I2C_FUNC_SLAVE; dev->slave_cfg = DW_IC_CON_RX_FIFO_FULL_HLD_CTRL | DW_IC_CON_RESTART_EN | DW_IC_CON_STOP_DET_IFADDRESSED; diff --git a/drivers/iio/adc/ad7173.c b/drivers/iio/adc/ad7173.c index a7826bba0852..b26d4575e256 100644 --- a/drivers/iio/adc/ad7173.c +++ b/drivers/iio/adc/ad7173.c @@ -145,6 +145,7 @@ struct ad7173_device_info { unsigned int id; char *name; bool has_temp; + bool has_input_buf; bool has_int_ref; bool has_ref2; u8 num_gpios; @@ -212,18 +213,21 @@ static const struct ad7173_device_info ad7173_device_info[] = { .num_configs = 4, .num_gpios = 2, .has_temp = true, + .has_input_buf = true, .has_int_ref = true, .clock = 2 * HZ_PER_MHZ, .sinc5_data_rates = ad7173_sinc5_data_rates, .num_sinc5_data_rates = ARRAY_SIZE(ad7173_sinc5_data_rates), }, [ID_AD7172_4] = { + .name = "ad7172-4", .id = AD7172_4_ID, .num_inputs = 9, .num_channels = 8, .num_configs = 8, .num_gpios = 4, .has_temp = false, + .has_input_buf = true, .has_ref2 = true, .clock = 2 * HZ_PER_MHZ, .sinc5_data_rates = ad7173_sinc5_data_rates, @@ -237,6 +241,7 @@ static const struct ad7173_device_info ad7173_device_info[] = { .num_configs = 8, .num_gpios = 4, .has_temp = true, + .has_input_buf = true, .has_int_ref = true, .has_ref2 = true, .clock = 2 * HZ_PER_MHZ, @@ -251,18 +256,21 @@ static const struct ad7173_device_info ad7173_device_info[] = { .num_configs = 4, .num_gpios = 2, .has_temp = true, + .has_input_buf = true, .has_int_ref = true, .clock = 16 * HZ_PER_MHZ, .sinc5_data_rates = ad7175_sinc5_data_rates, .num_sinc5_data_rates = ARRAY_SIZE(ad7175_sinc5_data_rates), }, [ID_AD7175_8] = { + .name = "ad7175-8", .id = AD7175_8_ID, .num_inputs = 17, .num_channels = 16, .num_configs = 8, .num_gpios = 4, .has_temp = true, + .has_input_buf = true, .has_int_ref = true, .has_ref2 = true, .clock = 16 * HZ_PER_MHZ, @@ -277,18 +285,21 @@ static const struct ad7173_device_info ad7173_device_info[] = { .num_configs = 4, .num_gpios = 2, .has_temp = false, + .has_input_buf = false, .has_int_ref = true, .clock = 16 * HZ_PER_MHZ, .sinc5_data_rates = ad7175_sinc5_data_rates, .num_sinc5_data_rates = ARRAY_SIZE(ad7175_sinc5_data_rates), }, [ID_AD7177_2] = { + .name = "ad7177-2", .id = AD7177_ID, .num_inputs = 5, .num_channels = 4, .num_configs = 4, .num_gpios = 2, .has_temp = true, + .has_input_buf = true, .has_int_ref = true, .clock = 16 * HZ_PER_MHZ, .odr_start_value = AD7177_ODR_START_VALUE, @@ -532,6 +543,7 @@ static int ad7173_append_status(struct ad_sigma_delta *sd, bool append) unsigned int interface_mode = st->interface_mode; int ret; + interface_mode &= ~AD7173_INTERFACE_DATA_STAT; interface_mode |= AD7173_INTERFACE_DATA_STAT_EN(append); ret = ad_sd_write_reg(&st->sd, AD7173_REG_INTERFACE_MODE, 2, interface_mode); if (ret) @@ -705,7 +717,7 @@ static int ad7173_write_raw(struct iio_dev *indio_dev, { struct ad7173_state *st = iio_priv(indio_dev); struct ad7173_channel_config *cfg; - unsigned int freq, i, reg; + unsigned int freq, i; int ret; ret = iio_device_claim_direct_mode(indio_dev); @@ -721,16 +733,7 @@ static int ad7173_write_raw(struct iio_dev *indio_dev, cfg = &st->channels[chan->address].cfg; cfg->odr = i; - - if (!cfg->live) - break; - - ret = ad_sd_read_reg(&st->sd, AD7173_REG_FILTER(cfg->cfg_slot), 2, ®); - if (ret) - break; - reg &= ~AD7173_FILTER_ODR0_MASK; - reg |= FIELD_PREP(AD7173_FILTER_ODR0_MASK, i); - ret = ad_sd_write_reg(&st->sd, AD7173_REG_FILTER(cfg->cfg_slot), 2, reg); + cfg->live = false; break; default: @@ -792,8 +795,7 @@ static const struct iio_chan_spec ad7173_channel_template = { .type = IIO_VOLTAGE, .indexed = 1, .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | - BIT(IIO_CHAN_INFO_SCALE), - .info_mask_shared_by_all = BIT(IIO_CHAN_INFO_SAMP_FREQ), + BIT(IIO_CHAN_INFO_SCALE) | BIT(IIO_CHAN_INFO_SAMP_FREQ), .scan_type = { .sign = 'u', .realbits = 24, @@ -804,12 +806,11 @@ static const struct iio_chan_spec ad7173_channel_template = { static const struct iio_chan_spec ad7173_temp_iio_channel_template = { .type = IIO_TEMP, - .indexed = 1, .channel = AD7173_AIN_TEMP_POS, .channel2 = AD7173_AIN_TEMP_NEG, .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | - BIT(IIO_CHAN_INFO_SCALE) | BIT(IIO_CHAN_INFO_OFFSET), - .info_mask_shared_by_all = BIT(IIO_CHAN_INFO_SAMP_FREQ), + BIT(IIO_CHAN_INFO_SCALE) | BIT(IIO_CHAN_INFO_OFFSET) | + BIT(IIO_CHAN_INFO_SAMP_FREQ), .scan_type = { .sign = 'u', .realbits = 24, @@ -932,7 +933,7 @@ static int ad7173_fw_parse_channel_config(struct iio_dev *indio_dev) AD7173_CH_ADDRESS(chan_arr[chan_index].channel, chan_arr[chan_index].channel2); chan_st_priv->cfg.bipolar = false; - chan_st_priv->cfg.input_buf = true; + chan_st_priv->cfg.input_buf = st->info->has_input_buf; chan_st_priv->cfg.ref_sel = AD7173_SETUP_REF_SEL_INT_REF; st->adc_mode |= AD7173_ADC_MODE_REF_EN; @@ -989,7 +990,7 @@ static int ad7173_fw_parse_channel_config(struct iio_dev *indio_dev) chan_st_priv->ain = AD7173_CH_ADDRESS(ain[0], ain[1]); chan_st_priv->chan_reg = chan_index; - chan_st_priv->cfg.input_buf = true; + chan_st_priv->cfg.input_buf = st->info->has_input_buf; chan_st_priv->cfg.odr = 0; chan_st_priv->cfg.bipolar = fwnode_property_read_bool(child, "bipolar"); diff --git a/drivers/iio/adc/ad9467.c b/drivers/iio/adc/ad9467.c index e85b763b9ffc..8f5b9c3f6e3d 100644 --- a/drivers/iio/adc/ad9467.c +++ b/drivers/iio/adc/ad9467.c @@ -243,11 +243,11 @@ static void __ad9467_get_scale(struct ad9467_state *st, int index, } static const struct iio_chan_spec ad9434_channels[] = { - AD9467_CHAN(0, 0, 12, 'S'), + AD9467_CHAN(0, 0, 12, 's'), }; static const struct iio_chan_spec ad9467_channels[] = { - AD9467_CHAN(0, 0, 16, 'S'), + AD9467_CHAN(0, 0, 16, 's'), }; static const struct ad9467_chip_info ad9467_chip_tbl = { diff --git a/drivers/iio/common/inv_sensors/inv_sensors_timestamp.c b/drivers/iio/common/inv_sensors/inv_sensors_timestamp.c index fa205f17bd90..f44458c380d9 100644 --- a/drivers/iio/common/inv_sensors/inv_sensors_timestamp.c +++ b/drivers/iio/common/inv_sensors/inv_sensors_timestamp.c @@ -60,11 +60,15 @@ EXPORT_SYMBOL_NS_GPL(inv_sensors_timestamp_init, IIO_INV_SENSORS_TIMESTAMP); int inv_sensors_timestamp_update_odr(struct inv_sensors_timestamp *ts, uint32_t period, bool fifo) { + uint32_t mult; + /* when FIFO is on, prevent odr change if one is already pending */ if (fifo && ts->new_mult != 0) return -EAGAIN; - ts->new_mult = period / ts->chip.clock_period; + mult = period / ts->chip.clock_period; + if (mult != ts->mult) + ts->new_mult = mult; return 0; } diff --git a/drivers/iio/dac/ad5592r-base.c b/drivers/iio/dac/ad5592r-base.c index 076bc9ecfb49..4763402dbcd6 100644 --- a/drivers/iio/dac/ad5592r-base.c +++ b/drivers/iio/dac/ad5592r-base.c @@ -415,7 +415,7 @@ static int ad5592r_read_raw(struct iio_dev *iio_dev, s64 tmp = *val * (3767897513LL / 25LL); *val = div_s64_rem(tmp, 1000000000LL, val2); - return IIO_VAL_INT_PLUS_MICRO; + return IIO_VAL_INT_PLUS_NANO; } mutex_lock(&st->lock); diff --git a/drivers/iio/imu/bmi323/bmi323_core.c b/drivers/iio/imu/bmi323/bmi323_core.c index 5d42ab9b176a..67d74a1a1b26 100644 --- a/drivers/iio/imu/bmi323/bmi323_core.c +++ b/drivers/iio/imu/bmi323/bmi323_core.c @@ -1391,7 +1391,7 @@ static irqreturn_t bmi323_trigger_handler(int irq, void *p) &data->buffer.channels, ARRAY_SIZE(data->buffer.channels)); if (ret) - return IRQ_NONE; + goto out; } else { for_each_set_bit(bit, indio_dev->active_scan_mask, BMI323_CHAN_MAX) { @@ -1400,13 +1400,14 @@ static irqreturn_t bmi323_trigger_handler(int irq, void *p) &data->buffer.channels[index++], BMI323_BYTES_PER_SAMPLE); if (ret) - return IRQ_NONE; + goto out; } } iio_push_to_buffers_with_timestamp(indio_dev, &data->buffer, iio_get_time_ns(indio_dev)); +out: iio_trigger_notify_done(indio_dev->trig); return IRQ_HANDLED; diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c index 83d8504ebfff..4b2566693614 100644 --- a/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c +++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_accel.c @@ -130,10 +130,6 @@ static int inv_icm42600_accel_update_scan_mode(struct iio_dev *indio_dev, /* update data FIFO write */ inv_sensors_timestamp_apply_odr(ts, 0, 0, 0); ret = inv_icm42600_buffer_set_fifo_en(st, fifo_en | st->fifo.en); - if (ret) - goto out_unlock; - - ret = inv_icm42600_buffer_update_watermark(st); out_unlock: mutex_unlock(&st->lock); diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c index 63b85ec88c13..a8cf74c84c3c 100644 --- a/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c +++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.c @@ -222,10 +222,15 @@ int inv_icm42600_buffer_update_watermark(struct inv_icm42600_state *st) latency_accel = period_accel * wm_accel; /* 0 value for watermark means that the sensor is turned off */ + if (wm_gyro == 0 && wm_accel == 0) + return 0; + if (latency_gyro == 0) { watermark = wm_accel; + st->fifo.watermark.eff_accel = wm_accel; } else if (latency_accel == 0) { watermark = wm_gyro; + st->fifo.watermark.eff_gyro = wm_gyro; } else { /* compute the smallest latency that is a multiple of both */ if (latency_gyro <= latency_accel) @@ -241,6 +246,13 @@ int inv_icm42600_buffer_update_watermark(struct inv_icm42600_state *st) watermark = latency / period; if (watermark < 1) watermark = 1; + /* update effective watermark */ + st->fifo.watermark.eff_gyro = latency / period_gyro; + if (st->fifo.watermark.eff_gyro < 1) + st->fifo.watermark.eff_gyro = 1; + st->fifo.watermark.eff_accel = latency / period_accel; + if (st->fifo.watermark.eff_accel < 1) + st->fifo.watermark.eff_accel = 1; } /* compute watermark value in bytes */ @@ -514,7 +526,7 @@ int inv_icm42600_buffer_fifo_parse(struct inv_icm42600_state *st) /* handle gyroscope timestamp and FIFO data parsing */ if (st->fifo.nb.gyro > 0) { ts = &gyro_st->ts; - inv_sensors_timestamp_interrupt(ts, st->fifo.nb.gyro, + inv_sensors_timestamp_interrupt(ts, st->fifo.watermark.eff_gyro, st->timestamp.gyro); ret = inv_icm42600_gyro_parse_fifo(st->indio_gyro); if (ret) @@ -524,7 +536,7 @@ int inv_icm42600_buffer_fifo_parse(struct inv_icm42600_state *st) /* handle accelerometer timestamp and FIFO data parsing */ if (st->fifo.nb.accel > 0) { ts = &accel_st->ts; - inv_sensors_timestamp_interrupt(ts, st->fifo.nb.accel, + inv_sensors_timestamp_interrupt(ts, st->fifo.watermark.eff_accel, st->timestamp.accel); ret = inv_icm42600_accel_parse_fifo(st->indio_accel); if (ret) @@ -577,6 +589,9 @@ int inv_icm42600_buffer_init(struct inv_icm42600_state *st) unsigned int val; int ret; + st->fifo.watermark.eff_gyro = 1; + st->fifo.watermark.eff_accel = 1; + /* * Default FIFO configuration (bits 7 to 5) * - use invalid value diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.h b/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.h index 8b85ee333bf8..f6c85daf42b0 100644 --- a/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.h +++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_buffer.h @@ -32,6 +32,8 @@ struct inv_icm42600_fifo { struct { unsigned int gyro; unsigned int accel; + unsigned int eff_gyro; + unsigned int eff_accel; } watermark; size_t count; struct { diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_core.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_core.c index 96116a68ab29..62fdae530334 100644 --- a/drivers/iio/imu/inv_icm42600/inv_icm42600_core.c +++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_core.c @@ -537,6 +537,7 @@ static int inv_icm42600_irq_init(struct inv_icm42600_state *st, int irq, if (ret) return ret; + irq_type |= IRQF_ONESHOT; return devm_request_threaded_irq(dev, irq, inv_icm42600_irq_timestamp, inv_icm42600_irq_handler, irq_type, "inv_icm42600", st); diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c index e6f8de80128c..938af5b640b0 100644 --- a/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c +++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_gyro.c @@ -130,10 +130,6 @@ static int inv_icm42600_gyro_update_scan_mode(struct iio_dev *indio_dev, /* update data FIFO write */ inv_sensors_timestamp_apply_odr(ts, 0, 0, 0); ret = inv_icm42600_buffer_set_fifo_en(st, fifo_en | st->fifo.en); - if (ret) - goto out_unlock; - - ret = inv_icm42600_buffer_update_watermark(st); out_unlock: mutex_unlock(&st->lock); diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c index 0dc0f22a5582..3d3b27f28c9d 100644 --- a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c +++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c @@ -100,8 +100,8 @@ irqreturn_t inv_mpu6050_read_fifo(int irq, void *p) goto end_session; /* Each FIFO data contains all sensors, so same number for FIFO and sensor data */ fifo_period = NSEC_PER_SEC / INV_MPU6050_DIVIDER_TO_FIFO_RATE(st->chip_config.divider); - inv_sensors_timestamp_interrupt(&st->timestamp, nb, pf->timestamp); - inv_sensors_timestamp_apply_odr(&st->timestamp, fifo_period, nb, 0); + inv_sensors_timestamp_interrupt(&st->timestamp, 1, pf->timestamp); + inv_sensors_timestamp_apply_odr(&st->timestamp, fifo_period, 1, 0); /* clear internal data buffer for avoiding kernel data leak */ memset(data, 0, sizeof(data)); diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c index 1b603567ccc8..84273660ca2e 100644 --- a/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c +++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c @@ -300,6 +300,7 @@ int inv_mpu6050_probe_trigger(struct iio_dev *indio_dev, int irq_type) if (!st->trig) return -ENOMEM; + irq_type |= IRQF_ONESHOT; ret = devm_request_threaded_irq(&indio_dev->dev, st->irq, &inv_mpu6050_interrupt_timestamp, &inv_mpu6050_interrupt_handle, diff --git a/drivers/iio/inkern.c b/drivers/iio/inkern.c index 52d773261828..485e6fc44a04 100644 --- a/drivers/iio/inkern.c +++ b/drivers/iio/inkern.c @@ -721,7 +721,7 @@ int iio_read_channel_processed_scale(struct iio_channel *chan, int *val, return ret; *val *= scale; - return 0; + return ret; } else { ret = iio_channel_read(chan, val, NULL, IIO_CHAN_INFO_RAW); if (ret < 0) diff --git a/drivers/iio/pressure/bmp280-core.c b/drivers/iio/pressure/bmp280-core.c index 09f53d987c7d..221fa2c552ae 100644 --- a/drivers/iio/pressure/bmp280-core.c +++ b/drivers/iio/pressure/bmp280-core.c @@ -1394,12 +1394,12 @@ static int bmp580_read_temp(struct bmp280_data *data, int *val, int *val2) /* * Temperature is returned in Celsius degrees in fractional - * form down 2^16. We rescale by x1000 to return milli Celsius - * to respect IIO ABI. + * form down 2^16. We rescale by x1000 to return millidegrees + * Celsius to respect IIO ABI. */ - *val = raw_temp * 1000; - *val2 = 16; - return IIO_VAL_FRACTIONAL_LOG2; + raw_temp = sign_extend32(raw_temp, 23); + *val = ((s64)raw_temp * 1000) / (1 << 16); + return IIO_VAL_INT; } static int bmp580_read_press(struct bmp280_data *data, int *val, int *val2) diff --git a/drivers/iio/temperature/mlx90635.c b/drivers/iio/temperature/mlx90635.c index 1f5c962c1818..f7f88498ba0e 100644 --- a/drivers/iio/temperature/mlx90635.c +++ b/drivers/iio/temperature/mlx90635.c @@ -947,9 +947,9 @@ static int mlx90635_probe(struct i2c_client *client) "failed to allocate regmap\n"); regmap_ee = devm_regmap_init_i2c(client, &mlx90635_regmap_ee); - if (IS_ERR(regmap)) - return dev_err_probe(&client->dev, PTR_ERR(regmap), - "failed to allocate regmap\n"); + if (IS_ERR(regmap_ee)) + return dev_err_probe(&client->dev, PTR_ERR(regmap_ee), + "failed to allocate EEPROM regmap\n"); mlx90635 = iio_priv(indio_dev); i2c_set_clientdata(client, indio_dev); diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index 27e293727095..161248067776 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -3362,7 +3362,7 @@ int amd_iommu_reenable(int mode) return 0; } -int __init amd_iommu_enable_faulting(unsigned int cpu) +int amd_iommu_enable_faulting(unsigned int cpu) { /* We enable MSI later when PCI is initialized */ return 0; diff --git a/drivers/leds/led-class.c b/drivers/leds/led-class.c index 24fcff682b24..ba1be15cfd8e 100644 --- a/drivers/leds/led-class.c +++ b/drivers/leds/led-class.c @@ -552,12 +552,6 @@ int led_classdev_register_ext(struct device *parent, led_init_core(led_cdev); #ifdef CONFIG_LEDS_TRIGGERS - /* - * If no default trigger was given and hw_control_trigger is set, - * make it the default trigger. - */ - if (!led_cdev->default_trigger && led_cdev->hw_control_trigger) - led_cdev->default_trigger = led_cdev->hw_control_trigger; led_trigger_set_default(led_cdev); #endif diff --git a/drivers/mfd/axp20x.c b/drivers/mfd/axp20x.c index f2c0f144c0fc..dacd3c96c9f5 100644 --- a/drivers/mfd/axp20x.c +++ b/drivers/mfd/axp20x.c @@ -210,6 +210,7 @@ static const struct regmap_access_table axp313a_volatile_table = { static const struct regmap_range axp717_writeable_ranges[] = { regmap_reg_range(AXP717_IRQ0_EN, AXP717_IRQ4_EN), + regmap_reg_range(AXP717_IRQ0_STATE, AXP717_IRQ4_STATE), regmap_reg_range(AXP717_DCDC_OUTPUT_CONTROL, AXP717_CPUSLDO_CONTROL), }; diff --git a/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gp.c b/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gp.c index 32af2b14ff34..34c9be437432 100644 --- a/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gp.c +++ b/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gp.c @@ -69,8 +69,10 @@ static int gp_aux_bus_probe(struct pci_dev *pdev, const struct pci_device_id *id aux_bus->aux_device_wrapper[1] = kzalloc(sizeof(*aux_bus->aux_device_wrapper[1]), GFP_KERNEL); - if (!aux_bus->aux_device_wrapper[1]) - return -ENOMEM; + if (!aux_bus->aux_device_wrapper[1]) { + retval = -ENOMEM; + goto err_aux_dev_add_0; + } retval = ida_alloc(&gp_client_ida, GFP_KERNEL); if (retval < 0) @@ -111,6 +113,7 @@ static int gp_aux_bus_probe(struct pci_dev *pdev, const struct pci_device_id *id err_aux_dev_add_1: auxiliary_device_uninit(&aux_bus->aux_device_wrapper[1]->aux_dev); + goto err_aux_dev_add_0; err_aux_dev_init_1: ida_free(&gp_client_ida, aux_bus->aux_device_wrapper[1]->aux_dev.id); @@ -120,6 +123,7 @@ err_ida_alloc_1: err_aux_dev_add_0: auxiliary_device_uninit(&aux_bus->aux_device_wrapper[0]->aux_dev); + goto err_ret; err_aux_dev_init_0: ida_free(&gp_client_ida, aux_bus->aux_device_wrapper[0]->aux_dev.id); @@ -127,6 +131,7 @@ err_aux_dev_init_0: err_ida_alloc_0: kfree(aux_bus->aux_device_wrapper[0]); +err_ret: return retval; } diff --git a/drivers/misc/mei/main.c b/drivers/misc/mei/main.c index 79e6f3c1341f..40c3fe26f76d 100644 --- a/drivers/misc/mei/main.c +++ b/drivers/misc/mei/main.c @@ -329,7 +329,7 @@ static ssize_t mei_write(struct file *file, const char __user *ubuf, } if (!mei_cl_is_connected(cl)) { - cl_err(dev, cl, "is not connected"); + cl_dbg(dev, cl, "is not connected"); rets = -ENODEV; goto out; } diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c index 7f59dd38c32f..6589635f8ba3 100644 --- a/drivers/misc/mei/pci-me.c +++ b/drivers/misc/mei/pci-me.c @@ -385,8 +385,10 @@ static int mei_me_pci_resume(struct device *device) } err = mei_restart(dev); - if (err) + if (err) { + free_irq(pdev->irq, dev); return err; + } /* Start timer if stopped in suspend */ schedule_delayed_work(&dev->timer_work, HZ); diff --git a/drivers/misc/mei/platform-vsc.c b/drivers/misc/mei/platform-vsc.c index b543e6b9f3cf..1ec65d87488a 100644 --- a/drivers/misc/mei/platform-vsc.c +++ b/drivers/misc/mei/platform-vsc.c @@ -399,41 +399,32 @@ static void mei_vsc_remove(struct platform_device *pdev) static int mei_vsc_suspend(struct device *dev) { - struct mei_device *mei_dev = dev_get_drvdata(dev); - struct mei_vsc_hw *hw = mei_dev_to_vsc_hw(mei_dev); + struct mei_device *mei_dev; + int ret = 0; - mei_stop(mei_dev); + mei_dev = dev_get_drvdata(dev); + if (!mei_dev) + return -ENODEV; - mei_disable_interrupts(mei_dev); + mutex_lock(&mei_dev->device_lock); - vsc_tp_free_irq(hw->tp); + if (!mei_write_is_idle(mei_dev)) + ret = -EAGAIN; - return 0; + mutex_unlock(&mei_dev->device_lock); + + return ret; } static int mei_vsc_resume(struct device *dev) { - struct mei_device *mei_dev = dev_get_drvdata(dev); - struct mei_vsc_hw *hw = mei_dev_to_vsc_hw(mei_dev); - int ret; - - ret = vsc_tp_request_irq(hw->tp); - if (ret) - return ret; - - ret = mei_restart(mei_dev); - if (ret) - goto err_free; + struct mei_device *mei_dev; - /* start timer if stopped in suspend */ - schedule_delayed_work(&mei_dev->timer_work, HZ); + mei_dev = dev_get_drvdata(dev); + if (!mei_dev) + return -ENODEV; return 0; - -err_free: - vsc_tp_free_irq(hw->tp); - - return ret; } static DEFINE_SIMPLE_DEV_PM_OPS(mei_vsc_pm_ops, mei_vsc_suspend, mei_vsc_resume); diff --git a/drivers/misc/mei/vsc-fw-loader.c b/drivers/misc/mei/vsc-fw-loader.c index ffa4ccd96a10..596a9d695dfc 100644 --- a/drivers/misc/mei/vsc-fw-loader.c +++ b/drivers/misc/mei/vsc-fw-loader.c @@ -252,7 +252,7 @@ static int vsc_get_sensor_name(struct vsc_fw_loader *fw_loader, { struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER }; union acpi_object obj = { - .type = ACPI_TYPE_INTEGER, + .integer.type = ACPI_TYPE_INTEGER, .integer.value = 1, }; struct acpi_object_list arg_list = { diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 2818e24e2a51..debb554b60ed 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -3906,6 +3906,13 @@ static int ksz_hsr_join(struct dsa_switch *ds, int port, struct net_device *hsr, return -EOPNOTSUPP; } + /* KSZ9477 can only perform HSR offloading for up to two ports */ + if (hweight8(dev->hsr_ports) >= 2) { + NL_SET_ERR_MSG_MOD(extack, + "Cannot offload more than two ports - using software HSR"); + return -EOPNOTSUPP; + } + /* Self MAC address filtering, to avoid frames traversing * the HSR ring more than once. */ diff --git a/drivers/net/dsa/qca/qca8k-common.c b/drivers/net/dsa/qca/qca8k-common.c index 7f80035c5441..560c74c4ac3d 100644 --- a/drivers/net/dsa/qca/qca8k-common.c +++ b/drivers/net/dsa/qca/qca8k-common.c @@ -614,11 +614,57 @@ void qca8k_port_stp_state_set(struct dsa_switch *ds, int port, u8 state) qca8k_port_configure_learning(ds, port, learning); } +static int qca8k_update_port_member(struct qca8k_priv *priv, int port, + const struct net_device *bridge_dev, + bool join) +{ + bool isolated = !!(priv->port_isolated_map & BIT(port)), other_isolated; + struct dsa_port *dp = dsa_to_port(priv->ds, port), *other_dp; + u32 port_mask = BIT(dp->cpu_dp->index); + int i, ret; + + for (i = 0; i < QCA8K_NUM_PORTS; i++) { + if (i == port) + continue; + if (dsa_is_cpu_port(priv->ds, i)) + continue; + + other_dp = dsa_to_port(priv->ds, i); + if (!dsa_port_offloads_bridge_dev(other_dp, bridge_dev)) + continue; + + other_isolated = !!(priv->port_isolated_map & BIT(i)); + + /* Add/remove this port to/from the portvlan mask of the other + * ports in the bridge + */ + if (join && !(isolated && other_isolated)) { + port_mask |= BIT(i); + ret = regmap_set_bits(priv->regmap, + QCA8K_PORT_LOOKUP_CTRL(i), + BIT(port)); + } else { + ret = regmap_clear_bits(priv->regmap, + QCA8K_PORT_LOOKUP_CTRL(i), + BIT(port)); + } + + if (ret) + return ret; + } + + /* Add/remove all other ports to/from this port's portvlan mask */ + ret = qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(port), + QCA8K_PORT_LOOKUP_MEMBER, port_mask); + + return ret; +} + int qca8k_port_pre_bridge_flags(struct dsa_switch *ds, int port, struct switchdev_brport_flags flags, struct netlink_ext_ack *extack) { - if (flags.mask & ~BR_LEARNING) + if (flags.mask & ~(BR_LEARNING | BR_ISOLATED)) return -EINVAL; return 0; @@ -628,6 +674,7 @@ int qca8k_port_bridge_flags(struct dsa_switch *ds, int port, struct switchdev_brport_flags flags, struct netlink_ext_ack *extack) { + struct qca8k_priv *priv = ds->priv; int ret; if (flags.mask & BR_LEARNING) { @@ -637,6 +684,20 @@ int qca8k_port_bridge_flags(struct dsa_switch *ds, int port, return ret; } + if (flags.mask & BR_ISOLATED) { + struct dsa_port *dp = dsa_to_port(ds, port); + struct net_device *bridge_dev = dsa_port_bridge_dev_get(dp); + + if (flags.val & BR_ISOLATED) + priv->port_isolated_map |= BIT(port); + else + priv->port_isolated_map &= ~BIT(port); + + ret = qca8k_update_port_member(priv, port, bridge_dev, true); + if (ret) + return ret; + } + return 0; } @@ -646,62 +707,21 @@ int qca8k_port_bridge_join(struct dsa_switch *ds, int port, struct netlink_ext_ack *extack) { struct qca8k_priv *priv = ds->priv; - int port_mask, cpu_port; - int i, ret; - - cpu_port = dsa_to_port(ds, port)->cpu_dp->index; - port_mask = BIT(cpu_port); - - for (i = 0; i < QCA8K_NUM_PORTS; i++) { - if (dsa_is_cpu_port(ds, i)) - continue; - if (!dsa_port_offloads_bridge(dsa_to_port(ds, i), &bridge)) - continue; - /* Add this port to the portvlan mask of the other ports - * in the bridge - */ - ret = regmap_set_bits(priv->regmap, - QCA8K_PORT_LOOKUP_CTRL(i), - BIT(port)); - if (ret) - return ret; - if (i != port) - port_mask |= BIT(i); - } - /* Add all other ports to this ports portvlan mask */ - ret = qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(port), - QCA8K_PORT_LOOKUP_MEMBER, port_mask); - - return ret; + return qca8k_update_port_member(priv, port, bridge.dev, true); } void qca8k_port_bridge_leave(struct dsa_switch *ds, int port, struct dsa_bridge bridge) { struct qca8k_priv *priv = ds->priv; - int cpu_port, i; - - cpu_port = dsa_to_port(ds, port)->cpu_dp->index; - - for (i = 0; i < QCA8K_NUM_PORTS; i++) { - if (dsa_is_cpu_port(ds, i)) - continue; - if (!dsa_port_offloads_bridge(dsa_to_port(ds, i), &bridge)) - continue; - /* Remove this port to the portvlan mask of the other ports - * in the bridge - */ - regmap_clear_bits(priv->regmap, - QCA8K_PORT_LOOKUP_CTRL(i), - BIT(port)); - } + int err; - /* Set the cpu port to be the only one in the portvlan mask of - * this port - */ - qca8k_rmw(priv, QCA8K_PORT_LOOKUP_CTRL(port), - QCA8K_PORT_LOOKUP_MEMBER, BIT(cpu_port)); + err = qca8k_update_port_member(priv, port, bridge.dev, false); + if (err) + dev_err(priv->dev, + "Failed to update switch config for bridge leave: %d\n", + err); } void qca8k_port_fast_age(struct dsa_switch *ds, int port) diff --git a/drivers/net/dsa/qca/qca8k.h b/drivers/net/dsa/qca/qca8k.h index 2184d8d2d5a9..3664a2e2f1f6 100644 --- a/drivers/net/dsa/qca/qca8k.h +++ b/drivers/net/dsa/qca/qca8k.h @@ -451,6 +451,7 @@ struct qca8k_priv { * Bit 1: port enabled. Bit 0: port disabled. */ u8 port_enabled_map; + u8 port_isolated_map; struct qca8k_ports_config ports_config; struct regmap *regmap; struct mii_bus *bus; diff --git a/drivers/net/ethernet/arc/Kconfig b/drivers/net/ethernet/arc/Kconfig index 0a67612af228..0d400a7d8d91 100644 --- a/drivers/net/ethernet/arc/Kconfig +++ b/drivers/net/ethernet/arc/Kconfig @@ -23,16 +23,6 @@ config ARC_EMAC_CORE select PHYLIB select CRC32 -config ARC_EMAC - tristate "ARC EMAC support" - select ARC_EMAC_CORE - depends on OF_IRQ - depends on ARC || COMPILE_TEST - help - On some legacy ARC (Synopsys) FPGA boards such as ARCAngel4/ML50x - non-standard on-chip ethernet device ARC EMAC 10/100 is used. - Say Y here if you have such a board. If unsure, say N. - config EMAC_ROCKCHIP tristate "Rockchip EMAC support" select ARC_EMAC_CORE diff --git a/drivers/net/ethernet/arc/Makefile b/drivers/net/ethernet/arc/Makefile index d63ada577c8e..23586eefec44 100644 --- a/drivers/net/ethernet/arc/Makefile +++ b/drivers/net/ethernet/arc/Makefile @@ -5,5 +5,4 @@ arc_emac-objs := emac_main.o emac_mdio.o obj-$(CONFIG_ARC_EMAC_CORE) += arc_emac.o -obj-$(CONFIG_ARC_EMAC) += emac_arc.o obj-$(CONFIG_EMAC_ROCKCHIP) += emac_rockchip.o diff --git a/drivers/net/ethernet/arc/emac_arc.c b/drivers/net/ethernet/arc/emac_arc.c deleted file mode 100644 index a3afddb23ee8..000000000000 --- a/drivers/net/ethernet/arc/emac_arc.c +++ /dev/null @@ -1,88 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/** - * DOC: emac_arc.c - ARC EMAC specific glue layer - * - * Copyright (C) 2014 Romain Perier - * - * Romain Perier <[email protected]> - */ - -#include <linux/etherdevice.h> -#include <linux/module.h> -#include <linux/of_net.h> -#include <linux/platform_device.h> - -#include "emac.h" - -#define DRV_NAME "emac_arc" - -static int emac_arc_probe(struct platform_device *pdev) -{ - struct device *dev = &pdev->dev; - struct arc_emac_priv *priv; - phy_interface_t interface; - struct net_device *ndev; - int err; - - if (!dev->of_node) - return -ENODEV; - - ndev = alloc_etherdev(sizeof(struct arc_emac_priv)); - if (!ndev) - return -ENOMEM; - platform_set_drvdata(pdev, ndev); - SET_NETDEV_DEV(ndev, dev); - - priv = netdev_priv(ndev); - priv->drv_name = DRV_NAME; - - err = of_get_phy_mode(dev->of_node, &interface); - if (err) { - if (err == -ENODEV) - interface = PHY_INTERFACE_MODE_MII; - else - goto out_netdev; - } - - priv->clk = devm_clk_get(dev, "hclk"); - if (IS_ERR(priv->clk)) { - dev_err(dev, "failed to retrieve host clock from device tree\n"); - err = -EINVAL; - goto out_netdev; - } - - err = arc_emac_probe(ndev, interface); -out_netdev: - if (err) - free_netdev(ndev); - return err; -} - -static void emac_arc_remove(struct platform_device *pdev) -{ - struct net_device *ndev = platform_get_drvdata(pdev); - - arc_emac_remove(ndev); - free_netdev(ndev); -} - -static const struct of_device_id emac_arc_dt_ids[] = { - { .compatible = "snps,arc-emac" }, - { /* Sentinel */ } -}; -MODULE_DEVICE_TABLE(of, emac_arc_dt_ids); - -static struct platform_driver emac_arc_driver = { - .probe = emac_arc_probe, - .remove_new = emac_arc_remove, - .driver = { - .name = DRV_NAME, - .of_match_table = emac_arc_dt_ids, - }, -}; - -module_platform_driver(emac_arc_driver); - -MODULE_AUTHOR("Romain Perier <[email protected]>"); -MODULE_DESCRIPTION("ARC EMAC platform driver"); -MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 7dc00c0d8992..1bd0c5973252 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -736,11 +736,6 @@ tx_done: return NETDEV_TX_OK; tx_dma_error: - if (BNXT_TX_PTP_IS_SET(lflags)) { - atomic64_inc(&bp->ptp_cfg->stats.ts_err); - atomic_inc(&bp->ptp_cfg->tx_avail); - } - last_frag = i; /* start back at beginning and unmap skb */ @@ -762,6 +757,10 @@ tx_dma_error: tx_free: dev_kfree_skb_any(skb); tx_kick_pending: + if (BNXT_TX_PTP_IS_SET(lflags)) { + atomic64_inc(&bp->ptp_cfg->stats.ts_err); + atomic_inc(&bp->ptp_cfg->tx_avail); + } if (txr->kick_pending) bnxt_txr_db_kick(bp, txr, txr->tx_prod); txr->tx_buf_ring[txr->tx_prod].skb = NULL; @@ -3317,37 +3316,12 @@ static void bnxt_free_tx_skbs(struct bnxt *bp) } } -static void bnxt_free_one_rx_ring_skbs(struct bnxt *bp, int ring_nr) +static void bnxt_free_one_rx_ring(struct bnxt *bp, struct bnxt_rx_ring_info *rxr) { - struct bnxt_rx_ring_info *rxr = &bp->rx_ring[ring_nr]; struct pci_dev *pdev = bp->pdev; - struct bnxt_tpa_idx_map *map; - int i, max_idx, max_agg_idx; + int i, max_idx; max_idx = bp->rx_nr_pages * RX_DESC_CNT; - max_agg_idx = bp->rx_agg_nr_pages * RX_DESC_CNT; - if (!rxr->rx_tpa) - goto skip_rx_tpa_free; - - for (i = 0; i < bp->max_tpa; i++) { - struct bnxt_tpa_info *tpa_info = &rxr->rx_tpa[i]; - u8 *data = tpa_info->data; - - if (!data) - continue; - - dma_unmap_single_attrs(&pdev->dev, tpa_info->mapping, - bp->rx_buf_use_size, bp->rx_dir, - DMA_ATTR_WEAK_ORDERING); - - tpa_info->data = NULL; - - skb_free_frag(data); - } - -skip_rx_tpa_free: - if (!rxr->rx_buf_ring) - goto skip_rx_buf_free; for (i = 0; i < max_idx; i++) { struct bnxt_sw_rx_bd *rx_buf = &rxr->rx_buf_ring[i]; @@ -3367,12 +3341,15 @@ skip_rx_tpa_free: skb_free_frag(data); } } +} -skip_rx_buf_free: - if (!rxr->rx_agg_ring) - goto skip_rx_agg_free; +static void bnxt_free_one_rx_agg_ring(struct bnxt *bp, struct bnxt_rx_ring_info *rxr) +{ + int i, max_idx; + + max_idx = bp->rx_agg_nr_pages * RX_DESC_CNT; - for (i = 0; i < max_agg_idx; i++) { + for (i = 0; i < max_idx; i++) { struct bnxt_sw_rx_agg_bd *rx_agg_buf = &rxr->rx_agg_ring[i]; struct page *page = rx_agg_buf->page; @@ -3384,6 +3361,45 @@ skip_rx_buf_free: page_pool_recycle_direct(rxr->page_pool, page); } +} + +static void bnxt_free_one_rx_ring_skbs(struct bnxt *bp, int ring_nr) +{ + struct bnxt_rx_ring_info *rxr = &bp->rx_ring[ring_nr]; + struct pci_dev *pdev = bp->pdev; + struct bnxt_tpa_idx_map *map; + int i; + + if (!rxr->rx_tpa) + goto skip_rx_tpa_free; + + for (i = 0; i < bp->max_tpa; i++) { + struct bnxt_tpa_info *tpa_info = &rxr->rx_tpa[i]; + u8 *data = tpa_info->data; + + if (!data) + continue; + + dma_unmap_single_attrs(&pdev->dev, tpa_info->mapping, + bp->rx_buf_use_size, bp->rx_dir, + DMA_ATTR_WEAK_ORDERING); + + tpa_info->data = NULL; + + skb_free_frag(data); + } + +skip_rx_tpa_free: + if (!rxr->rx_buf_ring) + goto skip_rx_buf_free; + + bnxt_free_one_rx_ring(bp, rxr); + +skip_rx_buf_free: + if (!rxr->rx_agg_ring) + goto skip_rx_agg_free; + + bnxt_free_one_rx_agg_ring(bp, rxr); skip_rx_agg_free: map = rxr->rx_tpa_idx_map; @@ -3980,6 +3996,62 @@ static int bnxt_alloc_cp_rings(struct bnxt *bp) return 0; } +static void bnxt_init_rx_ring_struct(struct bnxt *bp, + struct bnxt_rx_ring_info *rxr) +{ + struct bnxt_ring_mem_info *rmem; + struct bnxt_ring_struct *ring; + + ring = &rxr->rx_ring_struct; + rmem = &ring->ring_mem; + rmem->nr_pages = bp->rx_nr_pages; + rmem->page_size = HW_RXBD_RING_SIZE; + rmem->pg_arr = (void **)rxr->rx_desc_ring; + rmem->dma_arr = rxr->rx_desc_mapping; + rmem->vmem_size = SW_RXBD_RING_SIZE * bp->rx_nr_pages; + rmem->vmem = (void **)&rxr->rx_buf_ring; + + ring = &rxr->rx_agg_ring_struct; + rmem = &ring->ring_mem; + rmem->nr_pages = bp->rx_agg_nr_pages; + rmem->page_size = HW_RXBD_RING_SIZE; + rmem->pg_arr = (void **)rxr->rx_agg_desc_ring; + rmem->dma_arr = rxr->rx_agg_desc_mapping; + rmem->vmem_size = SW_RXBD_AGG_RING_SIZE * bp->rx_agg_nr_pages; + rmem->vmem = (void **)&rxr->rx_agg_ring; +} + +static void bnxt_reset_rx_ring_struct(struct bnxt *bp, + struct bnxt_rx_ring_info *rxr) +{ + struct bnxt_ring_mem_info *rmem; + struct bnxt_ring_struct *ring; + int i; + + rxr->page_pool->p.napi = NULL; + rxr->page_pool = NULL; + + ring = &rxr->rx_ring_struct; + rmem = &ring->ring_mem; + rmem->pg_tbl = NULL; + rmem->pg_tbl_map = 0; + for (i = 0; i < rmem->nr_pages; i++) { + rmem->pg_arr[i] = NULL; + rmem->dma_arr[i] = 0; + } + *rmem->vmem = NULL; + + ring = &rxr->rx_agg_ring_struct; + rmem = &ring->ring_mem; + rmem->pg_tbl = NULL; + rmem->pg_tbl_map = 0; + for (i = 0; i < rmem->nr_pages; i++) { + rmem->pg_arr[i] = NULL; + rmem->dma_arr[i] = 0; + } + *rmem->vmem = NULL; +} + static void bnxt_init_ring_struct(struct bnxt *bp) { int i, j; @@ -4062,37 +4134,55 @@ static void bnxt_init_rxbd_pages(struct bnxt_ring_struct *ring, u32 type) } } -static int bnxt_alloc_one_rx_ring(struct bnxt *bp, int ring_nr) +static void bnxt_alloc_one_rx_ring_skb(struct bnxt *bp, + struct bnxt_rx_ring_info *rxr, + int ring_nr) { - struct bnxt_rx_ring_info *rxr = &bp->rx_ring[ring_nr]; - struct net_device *dev = bp->dev; u32 prod; int i; prod = rxr->rx_prod; for (i = 0; i < bp->rx_ring_size; i++) { if (bnxt_alloc_rx_data(bp, rxr, prod, GFP_KERNEL)) { - netdev_warn(dev, "init'ed rx ring %d with %d/%d skbs only\n", + netdev_warn(bp->dev, "init'ed rx ring %d with %d/%d skbs only\n", ring_nr, i, bp->rx_ring_size); break; } prod = NEXT_RX(prod); } rxr->rx_prod = prod; +} - if (!(bp->flags & BNXT_FLAG_AGG_RINGS)) - return 0; +static void bnxt_alloc_one_rx_ring_page(struct bnxt *bp, + struct bnxt_rx_ring_info *rxr, + int ring_nr) +{ + u32 prod; + int i; prod = rxr->rx_agg_prod; for (i = 0; i < bp->rx_agg_ring_size; i++) { if (bnxt_alloc_rx_page(bp, rxr, prod, GFP_KERNEL)) { - netdev_warn(dev, "init'ed rx ring %d with %d/%d pages only\n", + netdev_warn(bp->dev, "init'ed rx ring %d with %d/%d pages only\n", ring_nr, i, bp->rx_ring_size); break; } prod = NEXT_RX_AGG(prod); } rxr->rx_agg_prod = prod; +} + +static int bnxt_alloc_one_rx_ring(struct bnxt *bp, int ring_nr) +{ + struct bnxt_rx_ring_info *rxr = &bp->rx_ring[ring_nr]; + int i; + + bnxt_alloc_one_rx_ring_skb(bp, rxr, ring_nr); + + if (!(bp->flags & BNXT_FLAG_AGG_RINGS)) + return 0; + + bnxt_alloc_one_rx_ring_page(bp, rxr, ring_nr); if (rxr->rx_tpa) { dma_addr_t mapping; @@ -4111,9 +4201,9 @@ static int bnxt_alloc_one_rx_ring(struct bnxt *bp, int ring_nr) return 0; } -static int bnxt_init_one_rx_ring(struct bnxt *bp, int ring_nr) +static void bnxt_init_one_rx_ring_rxbd(struct bnxt *bp, + struct bnxt_rx_ring_info *rxr) { - struct bnxt_rx_ring_info *rxr; struct bnxt_ring_struct *ring; u32 type; @@ -4123,28 +4213,43 @@ static int bnxt_init_one_rx_ring(struct bnxt *bp, int ring_nr) if (NET_IP_ALIGN == 2) type |= RX_BD_FLAGS_SOP; - rxr = &bp->rx_ring[ring_nr]; ring = &rxr->rx_ring_struct; bnxt_init_rxbd_pages(ring, type); - - netif_queue_set_napi(bp->dev, ring_nr, NETDEV_QUEUE_TYPE_RX, - &rxr->bnapi->napi); - - if (BNXT_RX_PAGE_MODE(bp) && bp->xdp_prog) { - bpf_prog_add(bp->xdp_prog, 1); - rxr->xdp_prog = bp->xdp_prog; - } ring->fw_ring_id = INVALID_HW_RING_ID; +} + +static void bnxt_init_one_rx_agg_ring_rxbd(struct bnxt *bp, + struct bnxt_rx_ring_info *rxr) +{ + struct bnxt_ring_struct *ring; + u32 type; ring = &rxr->rx_agg_ring_struct; ring->fw_ring_id = INVALID_HW_RING_ID; - if ((bp->flags & BNXT_FLAG_AGG_RINGS)) { type = ((u32)BNXT_RX_PAGE_SIZE << RX_BD_LEN_SHIFT) | RX_BD_TYPE_RX_AGG_BD | RX_BD_FLAGS_SOP; bnxt_init_rxbd_pages(ring, type); } +} + +static int bnxt_init_one_rx_ring(struct bnxt *bp, int ring_nr) +{ + struct bnxt_rx_ring_info *rxr; + + rxr = &bp->rx_ring[ring_nr]; + bnxt_init_one_rx_ring_rxbd(bp, rxr); + + netif_queue_set_napi(bp->dev, ring_nr, NETDEV_QUEUE_TYPE_RX, + &rxr->bnapi->napi); + + if (BNXT_RX_PAGE_MODE(bp) && bp->xdp_prog) { + bpf_prog_add(bp->xdp_prog, 1); + rxr->xdp_prog = bp->xdp_prog; + } + + bnxt_init_one_rx_agg_ring_rxbd(bp, rxr); return bnxt_alloc_one_rx_ring(bp, ring_nr); } @@ -6869,6 +6974,48 @@ static void bnxt_set_db(struct bnxt *bp, struct bnxt_db_info *db, u32 ring_type, bnxt_set_db_mask(bp, db, ring_type); } +static int bnxt_hwrm_rx_ring_alloc(struct bnxt *bp, + struct bnxt_rx_ring_info *rxr) +{ + struct bnxt_ring_struct *ring = &rxr->rx_ring_struct; + struct bnxt_napi *bnapi = rxr->bnapi; + u32 type = HWRM_RING_ALLOC_RX; + u32 map_idx = bnapi->index; + int rc; + + rc = hwrm_ring_alloc_send_msg(bp, ring, type, map_idx); + if (rc) + return rc; + + bnxt_set_db(bp, &rxr->rx_db, type, map_idx, ring->fw_ring_id); + bp->grp_info[map_idx].rx_fw_ring_id = ring->fw_ring_id; + + return 0; +} + +static int bnxt_hwrm_rx_agg_ring_alloc(struct bnxt *bp, + struct bnxt_rx_ring_info *rxr) +{ + struct bnxt_ring_struct *ring = &rxr->rx_agg_ring_struct; + u32 type = HWRM_RING_ALLOC_AGG; + u32 grp_idx = ring->grp_idx; + u32 map_idx; + int rc; + + map_idx = grp_idx + bp->rx_nr_rings; + rc = hwrm_ring_alloc_send_msg(bp, ring, type, map_idx); + if (rc) + return rc; + + bnxt_set_db(bp, &rxr->rx_agg_db, type, map_idx, + ring->fw_ring_id); + bnxt_db_write(bp, &rxr->rx_agg_db, rxr->rx_agg_prod); + bnxt_db_write(bp, &rxr->rx_db, rxr->rx_prod); + bp->grp_info[grp_idx].agg_fw_ring_id = ring->fw_ring_id; + + return 0; +} + static int bnxt_hwrm_ring_alloc(struct bnxt *bp) { bool agg_rings = !!(bp->flags & BNXT_FLAG_AGG_RINGS); @@ -6934,24 +7081,21 @@ static int bnxt_hwrm_ring_alloc(struct bnxt *bp) bnxt_set_db(bp, &txr->tx_db, type, map_idx, ring->fw_ring_id); } - type = HWRM_RING_ALLOC_RX; for (i = 0; i < bp->rx_nr_rings; i++) { struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i]; - struct bnxt_ring_struct *ring = &rxr->rx_ring_struct; - struct bnxt_napi *bnapi = rxr->bnapi; - u32 map_idx = bnapi->index; - rc = hwrm_ring_alloc_send_msg(bp, ring, type, map_idx); + rc = bnxt_hwrm_rx_ring_alloc(bp, rxr); if (rc) goto err_out; - bnxt_set_db(bp, &rxr->rx_db, type, map_idx, ring->fw_ring_id); /* If we have agg rings, post agg buffers first. */ if (!agg_rings) bnxt_db_write(bp, &rxr->rx_db, rxr->rx_prod); - bp->grp_info[map_idx].rx_fw_ring_id = ring->fw_ring_id; if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) { struct bnxt_cp_ring_info *cpr2 = rxr->rx_cpr; + struct bnxt_napi *bnapi = rxr->bnapi; u32 type2 = HWRM_RING_ALLOC_CMPL; + struct bnxt_ring_struct *ring; + u32 map_idx = bnapi->index; ring = &cpr2->cp_ring_struct; ring->handle = BNXT_SET_NQ_HDL(cpr2); @@ -6965,23 +7109,10 @@ static int bnxt_hwrm_ring_alloc(struct bnxt *bp) } if (agg_rings) { - type = HWRM_RING_ALLOC_AGG; for (i = 0; i < bp->rx_nr_rings; i++) { - struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i]; - struct bnxt_ring_struct *ring = - &rxr->rx_agg_ring_struct; - u32 grp_idx = ring->grp_idx; - u32 map_idx = grp_idx + bp->rx_nr_rings; - - rc = hwrm_ring_alloc_send_msg(bp, ring, type, map_idx); + rc = bnxt_hwrm_rx_agg_ring_alloc(bp, &bp->rx_ring[i]); if (rc) goto err_out; - - bnxt_set_db(bp, &rxr->rx_agg_db, type, map_idx, - ring->fw_ring_id); - bnxt_db_write(bp, &rxr->rx_agg_db, rxr->rx_agg_prod); - bnxt_db_write(bp, &rxr->rx_db, rxr->rx_prod); - bp->grp_info[grp_idx].agg_fw_ring_id = ring->fw_ring_id; } } err_out: @@ -7021,6 +7152,50 @@ exit: return 0; } +static void bnxt_hwrm_rx_ring_free(struct bnxt *bp, + struct bnxt_rx_ring_info *rxr, + bool close_path) +{ + struct bnxt_ring_struct *ring = &rxr->rx_ring_struct; + u32 grp_idx = rxr->bnapi->index; + u32 cmpl_ring_id; + + if (ring->fw_ring_id == INVALID_HW_RING_ID) + return; + + cmpl_ring_id = bnxt_cp_ring_for_rx(bp, rxr); + hwrm_ring_free_send_msg(bp, ring, + RING_FREE_REQ_RING_TYPE_RX, + close_path ? cmpl_ring_id : + INVALID_HW_RING_ID); + ring->fw_ring_id = INVALID_HW_RING_ID; + bp->grp_info[grp_idx].rx_fw_ring_id = INVALID_HW_RING_ID; +} + +static void bnxt_hwrm_rx_agg_ring_free(struct bnxt *bp, + struct bnxt_rx_ring_info *rxr, + bool close_path) +{ + struct bnxt_ring_struct *ring = &rxr->rx_agg_ring_struct; + u32 grp_idx = rxr->bnapi->index; + u32 type, cmpl_ring_id; + + if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) + type = RING_FREE_REQ_RING_TYPE_RX_AGG; + else + type = RING_FREE_REQ_RING_TYPE_RX; + + if (ring->fw_ring_id == INVALID_HW_RING_ID) + return; + + cmpl_ring_id = bnxt_cp_ring_for_rx(bp, rxr); + hwrm_ring_free_send_msg(bp, ring, type, + close_path ? cmpl_ring_id : + INVALID_HW_RING_ID); + ring->fw_ring_id = INVALID_HW_RING_ID; + bp->grp_info[grp_idx].agg_fw_ring_id = INVALID_HW_RING_ID; +} + static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path) { u32 type; @@ -7045,42 +7220,8 @@ static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path) } for (i = 0; i < bp->rx_nr_rings; i++) { - struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i]; - struct bnxt_ring_struct *ring = &rxr->rx_ring_struct; - u32 grp_idx = rxr->bnapi->index; - - if (ring->fw_ring_id != INVALID_HW_RING_ID) { - u32 cmpl_ring_id = bnxt_cp_ring_for_rx(bp, rxr); - - hwrm_ring_free_send_msg(bp, ring, - RING_FREE_REQ_RING_TYPE_RX, - close_path ? cmpl_ring_id : - INVALID_HW_RING_ID); - ring->fw_ring_id = INVALID_HW_RING_ID; - bp->grp_info[grp_idx].rx_fw_ring_id = - INVALID_HW_RING_ID; - } - } - - if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) - type = RING_FREE_REQ_RING_TYPE_RX_AGG; - else - type = RING_FREE_REQ_RING_TYPE_RX; - for (i = 0; i < bp->rx_nr_rings; i++) { - struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i]; - struct bnxt_ring_struct *ring = &rxr->rx_agg_ring_struct; - u32 grp_idx = rxr->bnapi->index; - - if (ring->fw_ring_id != INVALID_HW_RING_ID) { - u32 cmpl_ring_id = bnxt_cp_ring_for_rx(bp, rxr); - - hwrm_ring_free_send_msg(bp, ring, type, - close_path ? cmpl_ring_id : - INVALID_HW_RING_ID); - ring->fw_ring_id = INVALID_HW_RING_ID; - bp->grp_info[grp_idx].agg_fw_ring_id = - INVALID_HW_RING_ID; - } + bnxt_hwrm_rx_ring_free(bp, &bp->rx_ring[i], close_path); + bnxt_hwrm_rx_agg_ring_free(bp, &bp->rx_ring[i], close_path); } /* The completion rings are about to be freed. After that the @@ -9004,6 +9145,7 @@ static int __bnxt_hwrm_func_qcaps(struct bnxt *bp) memcpy(vf->mac_addr, resp->mac_address, ETH_ALEN); #endif } + bp->tso_max_segs = le16_to_cpu(resp->max_tso_segs); hwrm_func_qcaps_exit: hwrm_req_drop(bp, req); @@ -14828,6 +14970,224 @@ static const struct netdev_stat_ops bnxt_stat_ops = { .get_base_stats = bnxt_get_base_stats, }; +static int bnxt_alloc_rx_agg_bmap(struct bnxt *bp, struct bnxt_rx_ring_info *rxr) +{ + u16 mem_size; + + rxr->rx_agg_bmap_size = bp->rx_agg_ring_mask + 1; + mem_size = rxr->rx_agg_bmap_size / 8; + rxr->rx_agg_bmap = kzalloc(mem_size, GFP_KERNEL); + if (!rxr->rx_agg_bmap) + return -ENOMEM; + + return 0; +} + +static int bnxt_queue_mem_alloc(struct net_device *dev, void *qmem, int idx) +{ + struct bnxt_rx_ring_info *rxr, *clone; + struct bnxt *bp = netdev_priv(dev); + struct bnxt_ring_struct *ring; + int rc; + + rxr = &bp->rx_ring[idx]; + clone = qmem; + memcpy(clone, rxr, sizeof(*rxr)); + bnxt_init_rx_ring_struct(bp, clone); + bnxt_reset_rx_ring_struct(bp, clone); + + clone->rx_prod = 0; + clone->rx_agg_prod = 0; + clone->rx_sw_agg_prod = 0; + clone->rx_next_cons = 0; + + rc = bnxt_alloc_rx_page_pool(bp, clone, rxr->page_pool->p.nid); + if (rc) + return rc; + + ring = &clone->rx_ring_struct; + rc = bnxt_alloc_ring(bp, &ring->ring_mem); + if (rc) + goto err_free_rx_ring; + + if (bp->flags & BNXT_FLAG_AGG_RINGS) { + ring = &clone->rx_agg_ring_struct; + rc = bnxt_alloc_ring(bp, &ring->ring_mem); + if (rc) + goto err_free_rx_agg_ring; + + rc = bnxt_alloc_rx_agg_bmap(bp, clone); + if (rc) + goto err_free_rx_agg_ring; + } + + bnxt_init_one_rx_ring_rxbd(bp, clone); + bnxt_init_one_rx_agg_ring_rxbd(bp, clone); + + bnxt_alloc_one_rx_ring_skb(bp, clone, idx); + if (bp->flags & BNXT_FLAG_AGG_RINGS) + bnxt_alloc_one_rx_ring_page(bp, clone, idx); + + return 0; + +err_free_rx_agg_ring: + bnxt_free_ring(bp, &clone->rx_agg_ring_struct.ring_mem); +err_free_rx_ring: + bnxt_free_ring(bp, &clone->rx_ring_struct.ring_mem); + clone->page_pool->p.napi = NULL; + page_pool_destroy(clone->page_pool); + clone->page_pool = NULL; + return rc; +} + +static void bnxt_queue_mem_free(struct net_device *dev, void *qmem) +{ + struct bnxt_rx_ring_info *rxr = qmem; + struct bnxt *bp = netdev_priv(dev); + struct bnxt_ring_struct *ring; + + bnxt_free_one_rx_ring(bp, rxr); + bnxt_free_one_rx_agg_ring(bp, rxr); + + /* At this point, this NAPI instance has another page pool associated + * with it. Disconnect here before freeing the old page pool to avoid + * warnings. + */ + rxr->page_pool->p.napi = NULL; + page_pool_destroy(rxr->page_pool); + rxr->page_pool = NULL; + + ring = &rxr->rx_ring_struct; + bnxt_free_ring(bp, &ring->ring_mem); + + ring = &rxr->rx_agg_ring_struct; + bnxt_free_ring(bp, &ring->ring_mem); + + kfree(rxr->rx_agg_bmap); + rxr->rx_agg_bmap = NULL; +} + +static void bnxt_copy_rx_ring(struct bnxt *bp, + struct bnxt_rx_ring_info *dst, + struct bnxt_rx_ring_info *src) +{ + struct bnxt_ring_mem_info *dst_rmem, *src_rmem; + struct bnxt_ring_struct *dst_ring, *src_ring; + int i; + + dst_ring = &dst->rx_ring_struct; + dst_rmem = &dst_ring->ring_mem; + src_ring = &src->rx_ring_struct; + src_rmem = &src_ring->ring_mem; + + WARN_ON(dst_rmem->nr_pages != src_rmem->nr_pages); + WARN_ON(dst_rmem->page_size != src_rmem->page_size); + WARN_ON(dst_rmem->flags != src_rmem->flags); + WARN_ON(dst_rmem->depth != src_rmem->depth); + WARN_ON(dst_rmem->vmem_size != src_rmem->vmem_size); + WARN_ON(dst_rmem->ctx_mem != src_rmem->ctx_mem); + + dst_rmem->pg_tbl = src_rmem->pg_tbl; + dst_rmem->pg_tbl_map = src_rmem->pg_tbl_map; + *dst_rmem->vmem = *src_rmem->vmem; + for (i = 0; i < dst_rmem->nr_pages; i++) { + dst_rmem->pg_arr[i] = src_rmem->pg_arr[i]; + dst_rmem->dma_arr[i] = src_rmem->dma_arr[i]; + } + + if (!(bp->flags & BNXT_FLAG_AGG_RINGS)) + return; + + dst_ring = &dst->rx_agg_ring_struct; + dst_rmem = &dst_ring->ring_mem; + src_ring = &src->rx_agg_ring_struct; + src_rmem = &src_ring->ring_mem; + + WARN_ON(dst_rmem->nr_pages != src_rmem->nr_pages); + WARN_ON(dst_rmem->page_size != src_rmem->page_size); + WARN_ON(dst_rmem->flags != src_rmem->flags); + WARN_ON(dst_rmem->depth != src_rmem->depth); + WARN_ON(dst_rmem->vmem_size != src_rmem->vmem_size); + WARN_ON(dst_rmem->ctx_mem != src_rmem->ctx_mem); + WARN_ON(dst->rx_agg_bmap_size != src->rx_agg_bmap_size); + + dst_rmem->pg_tbl = src_rmem->pg_tbl; + dst_rmem->pg_tbl_map = src_rmem->pg_tbl_map; + *dst_rmem->vmem = *src_rmem->vmem; + for (i = 0; i < dst_rmem->nr_pages; i++) { + dst_rmem->pg_arr[i] = src_rmem->pg_arr[i]; + dst_rmem->dma_arr[i] = src_rmem->dma_arr[i]; + } + + dst->rx_agg_bmap = src->rx_agg_bmap; +} + +static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx) +{ + struct bnxt *bp = netdev_priv(dev); + struct bnxt_rx_ring_info *rxr, *clone; + struct bnxt_cp_ring_info *cpr; + int rc; + + rxr = &bp->rx_ring[idx]; + clone = qmem; + + rxr->rx_prod = clone->rx_prod; + rxr->rx_agg_prod = clone->rx_agg_prod; + rxr->rx_sw_agg_prod = clone->rx_sw_agg_prod; + rxr->rx_next_cons = clone->rx_next_cons; + rxr->page_pool = clone->page_pool; + + bnxt_copy_rx_ring(bp, rxr, clone); + + rc = bnxt_hwrm_rx_ring_alloc(bp, rxr); + if (rc) + return rc; + rc = bnxt_hwrm_rx_agg_ring_alloc(bp, rxr); + if (rc) + goto err_free_hwrm_rx_ring; + + bnxt_db_write(bp, &rxr->rx_db, rxr->rx_prod); + if (bp->flags & BNXT_FLAG_AGG_RINGS) + bnxt_db_write(bp, &rxr->rx_agg_db, rxr->rx_agg_prod); + + napi_enable(&rxr->bnapi->napi); + + cpr = &rxr->bnapi->cp_ring; + cpr->sw_stats->rx.rx_resets++; + + return 0; + +err_free_hwrm_rx_ring: + bnxt_hwrm_rx_ring_free(bp, rxr, false); + return rc; +} + +static int bnxt_queue_stop(struct net_device *dev, void *qmem, int idx) +{ + struct bnxt *bp = netdev_priv(dev); + struct bnxt_rx_ring_info *rxr; + + rxr = &bp->rx_ring[idx]; + napi_disable(&rxr->bnapi->napi); + bnxt_hwrm_rx_ring_free(bp, rxr, false); + bnxt_hwrm_rx_agg_ring_free(bp, rxr, false); + rxr->rx_next_cons = 0; + + memcpy(qmem, rxr, sizeof(*rxr)); + bnxt_init_rx_ring_struct(bp, qmem); + + return 0; +} + +static const struct netdev_queue_mgmt_ops bnxt_queue_mgmt_ops = { + .ndo_queue_mem_size = sizeof(struct bnxt_rx_ring_info), + .ndo_queue_mem_alloc = bnxt_queue_mem_alloc, + .ndo_queue_mem_free = bnxt_queue_mem_free, + .ndo_queue_start = bnxt_queue_start, + .ndo_queue_stop = bnxt_queue_stop, +}; + static void bnxt_remove_one(struct pci_dev *pdev) { struct net_device *dev = pci_get_drvdata(pdev); @@ -15293,6 +15653,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) dev->stat_ops = &bnxt_stat_ops; dev->watchdog_timeo = BNXT_TX_TIMEOUT; dev->ethtool_ops = &bnxt_ethtool_ops; + dev->queue_mgmt_ops = &bnxt_queue_mgmt_ops; pci_set_drvdata(pdev, dev); rc = bnxt_alloc_hwrm_resources(bp); @@ -15371,6 +15732,8 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) dev->priv_flags |= IFF_UNICAST_FLT; netif_set_tso_max_size(dev, GSO_MAX_SIZE); + if (bp->tso_max_segs) + netif_set_tso_max_segs(dev, bp->tso_max_segs); dev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | NETDEV_XDP_ACT_RX_SG; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index bbc7edccd5a4..9cf0acfa04e5 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -2318,6 +2318,7 @@ struct bnxt { u8 rss_hash_key_updated:1; u16 max_mtu; + u16 tso_max_segs; u8 max_tc; u8 max_lltc; /* lossless TCs */ struct bnxt_queue_info q_info[BNXT_MAX_QUEUE]; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h index 06ea86c80be1..f219709f9563 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h @@ -2,7 +2,7 @@ * * Copyright (c) 2014-2016 Broadcom Corporation * Copyright (c) 2014-2018 Broadcom Limited - * Copyright (c) 2018-2023 Broadcom Inc. + * Copyright (c) 2018-2024 Broadcom Inc. * * 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 @@ -500,7 +500,11 @@ struct cmd_nums { #define HWRM_TFC_IF_TBL_GET 0x399UL #define HWRM_TFC_TBL_SCOPE_CONFIG_GET 0x39aUL #define HWRM_TFC_RESC_USAGE_QUERY 0x39bUL + #define HWRM_QUEUE_PFCWD_TIMEOUT_QCAPS 0x39cUL + #define HWRM_QUEUE_PFCWD_TIMEOUT_CFG 0x39dUL + #define HWRM_QUEUE_PFCWD_TIMEOUT_QCFG 0x39eUL #define HWRM_SV 0x400UL + #define HWRM_DBG_LOG_BUFFER_FLUSH 0xff0fUL #define HWRM_DBG_READ_DIRECT 0xff10UL #define HWRM_DBG_READ_INDIRECT 0xff11UL #define HWRM_DBG_WRITE_DIRECT 0xff12UL @@ -609,8 +613,8 @@ struct hwrm_err_output { #define HWRM_VERSION_MAJOR 1 #define HWRM_VERSION_MINOR 10 #define HWRM_VERSION_UPDATE 3 -#define HWRM_VERSION_RSVD 39 -#define HWRM_VERSION_STR "1.10.3.39" +#define HWRM_VERSION_RSVD 44 +#define HWRM_VERSION_STR "1.10.3.44" /* hwrm_ver_get_input (size:192b/24B) */ struct hwrm_ver_get_input { @@ -664,6 +668,7 @@ struct hwrm_ver_get_output { #define VER_GET_RESP_DEV_CAPS_CFG_CFA_TFLIB_SUPPORTED 0x2000UL #define VER_GET_RESP_DEV_CAPS_CFG_CFA_TRUFLOW_SUPPORTED 0x4000UL #define VER_GET_RESP_DEV_CAPS_CFG_SECURE_BOOT_CAPABLE 0x8000UL + #define VER_GET_RESP_DEV_CAPS_CFG_SECURE_SOC_CAPABLE 0x10000UL u8 roce_fw_maj_8b; u8 roce_fw_min_8b; u8 roce_fw_bld_8b; @@ -843,7 +848,9 @@ struct hwrm_async_event_cmpl { #define ASYNC_EVENT_CMPL_EVENT_ID_HW_DOORBELL_RECOVERY_READ_ERROR 0x49UL #define ASYNC_EVENT_CMPL_EVENT_ID_CTX_ERROR 0x4aUL #define ASYNC_EVENT_CMPL_EVENT_ID_UDCC_SESSION_CHANGE 0x4bUL - #define ASYNC_EVENT_CMPL_EVENT_ID_MAX_RGTR_EVENT_ID 0x4cUL + #define ASYNC_EVENT_CMPL_EVENT_ID_DBG_BUF_PRODUCER 0x4cUL + #define ASYNC_EVENT_CMPL_EVENT_ID_PEER_MMAP_CHANGE 0x4dUL + #define ASYNC_EVENT_CMPL_EVENT_ID_MAX_RGTR_EVENT_ID 0x4eUL #define ASYNC_EVENT_CMPL_EVENT_ID_FW_TRACE_MSG 0xfeUL #define ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR 0xffUL #define ASYNC_EVENT_CMPL_EVENT_ID_LAST ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR @@ -1326,13 +1333,13 @@ struct hwrm_async_event_cmpl_error_report_base { u8 timestamp_lo; __le16 timestamp_hi; __le32 event_data1; - #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_MASK 0xffUL - #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_SFT 0 - #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_RESERVED 0x0UL - #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_PAUSE_STORM 0x1UL - #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_INVALID_SIGNAL 0x2UL - #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_NVM 0x3UL - #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_DOORBELL_DROP_THRESHOLD 0x4UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_MASK 0xffUL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_SFT 0 + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_RESERVED 0x0UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_PAUSE_STORM 0x1UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_INVALID_SIGNAL 0x2UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_NVM 0x3UL + #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_DOORBELL_DROP_THRESHOLD 0x4UL #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_THERMAL_THRESHOLD 0x5UL #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_DUAL_DATA_RATE_NOT_SUPPORTED 0x6UL #define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_LAST ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_DUAL_DATA_RATE_NOT_SUPPORTED @@ -1814,6 +1821,9 @@ struct hwrm_func_qcaps_output { #define FUNC_QCAPS_RESP_FLAGS_EXT2_SW_MAX_RESOURCE_LIMITS_SUPPORTED 0x800000UL #define FUNC_QCAPS_RESP_FLAGS_EXT2_TF_INGRESS_NIC_FLOW_SUPPORTED 0x1000000UL #define FUNC_QCAPS_RESP_FLAGS_EXT2_LPBK_STATS_SUPPORTED 0x2000000UL + #define FUNC_QCAPS_RESP_FLAGS_EXT2_TF_EGRESS_NIC_FLOW_SUPPORTED 0x4000000UL + #define FUNC_QCAPS_RESP_FLAGS_EXT2_MULTI_LOSSLESS_QUEUES_SUPPORTED 0x8000000UL + #define FUNC_QCAPS_RESP_FLAGS_EXT2_PEER_MMAP_SUPPORTED 0x10000000UL __le16 tunnel_disable_flag; #define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_VXLAN 0x1UL #define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_NGE 0x2UL @@ -1828,7 +1838,7 @@ struct hwrm_func_qcaps_output { #define FUNC_QCAPS_RESP_XID_PARTITION_CAP_RX_CK 0x2UL u8 device_serial_number[8]; __le16 ctxs_per_partition; - u8 unused_2[2]; + __le16 max_tso_segs; __le32 roce_vf_max_av; __le32 roce_vf_max_cq; __le32 roce_vf_max_mrw; @@ -2449,6 +2459,7 @@ struct hwrm_func_drv_rgtr_input { #define FUNC_DRV_RGTR_REQ_FLAGS_NPAR_1_2_SUPPORT 0x200UL #define FUNC_DRV_RGTR_REQ_FLAGS_ASYM_QUEUE_CFG_SUPPORT 0x400UL #define FUNC_DRV_RGTR_REQ_FLAGS_TF_INGRESS_NIC_FLOW_MODE 0x800UL + #define FUNC_DRV_RGTR_REQ_FLAGS_TF_EGRESS_NIC_FLOW_MODE 0x1000UL __le32 enables; #define FUNC_DRV_RGTR_REQ_ENABLES_OS_TYPE 0x1UL #define FUNC_DRV_RGTR_REQ_ENABLES_VER 0x2UL @@ -3660,22 +3671,24 @@ struct hwrm_func_backing_store_cfg_v2_input { __le16 target_id; __le64 resp_addr; __le16 type; - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_QP 0x0UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRQ 0x1UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CQ 0x2UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_VNIC 0x3UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_STAT 0x4UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SP_TQM_RING 0x5UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_FP_TQM_RING 0x6UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_MRAV 0xeUL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TIM 0xfUL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_MP_TQM_RING 0x15UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SQ_DB_SHADOW 0x16UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RQ_DB_SHADOW 0x17UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRQ_DB_SHADOW 0x18UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CQ_DB_SHADOW 0x19UL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TBL_SCOPE 0x1cUL - #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_XID_PARTITION 0x1dUL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_QP 0x0UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRQ 0x1UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CQ 0x2UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_VNIC 0x3UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_STAT 0x4UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SP_TQM_RING 0x5UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_FP_TQM_RING 0x6UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_MRAV 0xeUL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TIM 0xfUL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TX_CK 0x13UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RX_CK 0x14UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_MP_TQM_RING 0x15UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SQ_DB_SHADOW 0x16UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RQ_DB_SHADOW 0x17UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRQ_DB_SHADOW 0x18UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CQ_DB_SHADOW 0x19UL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TBL_SCOPE 0x1cUL + #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_XID_PARTITION 0x1dUL #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRT_TRACE 0x1eUL #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRT2_TRACE 0x1fUL #define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CRT_TRACE 0x20UL @@ -3772,18 +3785,20 @@ struct hwrm_func_backing_store_qcfg_v2_output { __le16 seq_id; __le16 resp_len; __le16 type; - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_QP 0x0UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SRQ 0x1UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CQ 0x2UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_VNIC 0x3UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_STAT 0x4UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SP_TQM_RING 0x5UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_FP_TQM_RING 0x6UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_MRAV 0xeUL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TIM 0xfUL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_MP_TQM_RING 0x15UL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TBL_SCOPE 0x1cUL - #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_XID_PARTITION 0x1dUL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_QP 0x0UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SRQ 0x1UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CQ 0x2UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_VNIC 0x3UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_STAT 0x4UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SP_TQM_RING 0x5UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_FP_TQM_RING 0x6UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_MRAV 0xeUL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TIM 0xfUL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TX_CK 0x13UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_RX_CK 0x14UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_MP_TQM_RING 0x15UL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TBL_SCOPE 0x1cUL + #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_XID_PARTITION 0x1dUL #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SRT_TRACE 0x1eUL #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SRT2_TRACE 0x1fUL #define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CRT_TRACE 0x20UL @@ -3876,22 +3891,24 @@ struct hwrm_func_backing_store_qcaps_v2_input { __le16 target_id; __le64 resp_addr; __le16 type; - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_QP 0x0UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRQ 0x1UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CQ 0x2UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_VNIC 0x3UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_STAT 0x4UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SP_TQM_RING 0x5UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_FP_TQM_RING 0x6UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MRAV 0xeUL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TIM 0xfUL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MP_TQM_RING 0x15UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SQ_DB_SHADOW 0x16UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RQ_DB_SHADOW 0x17UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRQ_DB_SHADOW 0x18UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CQ_DB_SHADOW 0x19UL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TBL_SCOPE 0x1cUL - #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_XID_PARTITION 0x1dUL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_QP 0x0UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRQ 0x1UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CQ 0x2UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_VNIC 0x3UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_STAT 0x4UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SP_TQM_RING 0x5UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_FP_TQM_RING 0x6UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MRAV 0xeUL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TIM 0xfUL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TX_CK 0x13UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RX_CK 0x14UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MP_TQM_RING 0x15UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SQ_DB_SHADOW 0x16UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RQ_DB_SHADOW 0x17UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRQ_DB_SHADOW 0x18UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CQ_DB_SHADOW 0x19UL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TBL_SCOPE 0x1cUL + #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_XID_PARTITION 0x1dUL #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRT_TRACE 0x1eUL #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRT2_TRACE 0x1fUL #define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CRT_TRACE 0x20UL @@ -3911,22 +3928,24 @@ struct hwrm_func_backing_store_qcaps_v2_output { __le16 seq_id; __le16 resp_len; __le16 type; - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_QP 0x0UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRQ 0x1UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CQ 0x2UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_VNIC 0x3UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_STAT 0x4UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SP_TQM_RING 0x5UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_FP_TQM_RING 0x6UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_MRAV 0xeUL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TIM 0xfUL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_MP_TQM_RING 0x15UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SQ_DB_SHADOW 0x16UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RQ_DB_SHADOW 0x17UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRQ_DB_SHADOW 0x18UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CQ_DB_SHADOW 0x19UL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TBL_SCOPE 0x1cUL - #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_XID_PARTITION 0x1dUL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_QP 0x0UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRQ 0x1UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CQ 0x2UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_VNIC 0x3UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_STAT 0x4UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SP_TQM_RING 0x5UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_FP_TQM_RING 0x6UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_MRAV 0xeUL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TIM 0xfUL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TX_CK 0x13UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RX_CK 0x14UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_MP_TQM_RING 0x15UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SQ_DB_SHADOW 0x16UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RQ_DB_SHADOW 0x17UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRQ_DB_SHADOW 0x18UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CQ_DB_SHADOW 0x19UL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TBL_SCOPE 0x1cUL + #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_XID_PARTITION 0x1dUL #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRT_TRACE 0x1eUL #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRT2_TRACE 0x1fUL #define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CRT_TRACE 0x20UL @@ -4202,7 +4221,8 @@ struct hwrm_port_phy_cfg_input { #define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_100GB_PAM4_112 0x3eaUL #define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_200GB_PAM4_112 0x7d2UL #define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_400GB_PAM4_112 0xfa2UL - #define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_LAST PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_400GB_PAM4_112 + #define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_800GB_PAM4_112 0x1f42UL + #define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_LAST PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_800GB_PAM4_112 __le16 auto_link_speeds2_mask; #define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_1GB 0x1UL #define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_10GB 0x2UL @@ -4217,6 +4237,7 @@ struct hwrm_port_phy_cfg_input { #define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_100GB_PAM4_112 0x400UL #define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_200GB_PAM4_112 0x800UL #define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_400GB_PAM4_112 0x1000UL + #define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_800GB_PAM4_112 0x2000UL u8 unused_2[6]; }; @@ -4292,6 +4313,7 @@ struct hwrm_port_phy_qcfg_output { #define PORT_PHY_QCFG_RESP_LINK_SPEED_100GB 0x3e8UL #define PORT_PHY_QCFG_RESP_LINK_SPEED_200GB 0x7d0UL #define PORT_PHY_QCFG_RESP_LINK_SPEED_400GB 0xfa0UL + #define PORT_PHY_QCFG_RESP_LINK_SPEED_800GB 0x1f40UL #define PORT_PHY_QCFG_RESP_LINK_SPEED_10MB 0xffffUL #define PORT_PHY_QCFG_RESP_LINK_SPEED_LAST PORT_PHY_QCFG_RESP_LINK_SPEED_10MB u8 duplex_cfg; @@ -4451,7 +4473,13 @@ struct hwrm_port_phy_qcfg_output { #define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASESR4 0x35UL #define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASELR4 0x36UL #define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASEER4 0x37UL - #define PORT_PHY_QCFG_RESP_PHY_TYPE_LAST PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASEER4 + #define PORT_PHY_QCFG_RESP_PHY_TYPE_800G_BASECR8 0x38UL + #define PORT_PHY_QCFG_RESP_PHY_TYPE_800G_BASESR8 0x39UL + #define PORT_PHY_QCFG_RESP_PHY_TYPE_800G_BASELR8 0x3aUL + #define PORT_PHY_QCFG_RESP_PHY_TYPE_800G_BASEER8 0x3bUL + #define PORT_PHY_QCFG_RESP_PHY_TYPE_800G_BASEFR8 0x3cUL + #define PORT_PHY_QCFG_RESP_PHY_TYPE_800G_BASEDR8 0x3dUL + #define PORT_PHY_QCFG_RESP_PHY_TYPE_LAST PORT_PHY_QCFG_RESP_PHY_TYPE_800G_BASEDR8 u8 media_type; #define PORT_PHY_QCFG_RESP_MEDIA_TYPE_UNKNOWN 0x0UL #define PORT_PHY_QCFG_RESP_MEDIA_TYPE_TP 0x1UL @@ -5049,33 +5077,43 @@ struct hwrm_port_qstats_ext_output { u8 valid; }; -/* hwrm_port_lpbk_qstats_input (size:128b/16B) */ +/* hwrm_port_lpbk_qstats_input (size:256b/32B) */ struct hwrm_port_lpbk_qstats_input { __le16 req_type; __le16 cmpl_ring; __le16 seq_id; __le16 target_id; __le64 resp_addr; + __le16 lpbk_stat_size; + u8 flags; + #define PORT_LPBK_QSTATS_REQ_FLAGS_COUNTER_MASK 0x1UL + u8 unused_0[5]; + __le64 lpbk_stat_host_addr; }; -/* hwrm_port_lpbk_qstats_output (size:768b/96B) */ +/* hwrm_port_lpbk_qstats_output (size:128b/16B) */ struct hwrm_port_lpbk_qstats_output { __le16 error_code; __le16 req_type; __le16 seq_id; __le16 resp_len; + __le16 lpbk_stat_size; + u8 unused_0[5]; + u8 valid; +}; + +/* port_lpbk_stats (size:640b/80B) */ +struct port_lpbk_stats { __le64 lpbk_ucast_frames; __le64 lpbk_mcast_frames; __le64 lpbk_bcast_frames; __le64 lpbk_ucast_bytes; __le64 lpbk_mcast_bytes; __le64 lpbk_bcast_bytes; - __le64 tx_stat_discard; - __le64 tx_stat_error; - __le64 rx_stat_discard; - __le64 rx_stat_error; - u8 unused_0[7]; - u8 valid; + __le64 lpbk_tx_discards; + __le64 lpbk_tx_errors; + __le64 lpbk_rx_discards; + __le64 lpbk_rx_errors; }; /* hwrm_port_ecn_qstats_input (size:256b/32B) */ @@ -5140,13 +5178,15 @@ struct hwrm_port_clr_stats_output { u8 valid; }; -/* hwrm_port_lpbk_clr_stats_input (size:128b/16B) */ +/* hwrm_port_lpbk_clr_stats_input (size:192b/24B) */ struct hwrm_port_lpbk_clr_stats_input { __le16 req_type; __le16 cmpl_ring; __le16 seq_id; __le16 target_id; __le64 resp_addr; + __le16 port_id; + u8 unused_0[6]; }; /* hwrm_port_lpbk_clr_stats_output (size:128b/16B) */ @@ -5287,10 +5327,11 @@ struct hwrm_port_phy_qcaps_output { #define PORT_PHY_QCAPS_RESP_SUPPORTED_PAM4_SPEEDS_FORCE_MODE_100G 0x2UL #define PORT_PHY_QCAPS_RESP_SUPPORTED_PAM4_SPEEDS_FORCE_MODE_200G 0x4UL __le16 flags2; - #define PORT_PHY_QCAPS_RESP_FLAGS2_PAUSE_UNSUPPORTED 0x1UL - #define PORT_PHY_QCAPS_RESP_FLAGS2_PFC_UNSUPPORTED 0x2UL - #define PORT_PHY_QCAPS_RESP_FLAGS2_BANK_ADDR_SUPPORTED 0x4UL - #define PORT_PHY_QCAPS_RESP_FLAGS2_SPEEDS2_SUPPORTED 0x8UL + #define PORT_PHY_QCAPS_RESP_FLAGS2_PAUSE_UNSUPPORTED 0x1UL + #define PORT_PHY_QCAPS_RESP_FLAGS2_PFC_UNSUPPORTED 0x2UL + #define PORT_PHY_QCAPS_RESP_FLAGS2_BANK_ADDR_SUPPORTED 0x4UL + #define PORT_PHY_QCAPS_RESP_FLAGS2_SPEEDS2_SUPPORTED 0x8UL + #define PORT_PHY_QCAPS_RESP_FLAGS2_REMOTE_LPBK_UNSUPPORTED 0x10UL u8 internal_port_cnt; u8 unused_0; __le16 supported_speeds2_force_mode; @@ -7443,17 +7484,17 @@ struct hwrm_cfa_l2_filter_cfg_input { __le16 target_id; __le64 resp_addr; __le32 flags; - #define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH 0x1UL - #define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_TX 0x0UL - #define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_RX 0x1UL - #define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_LAST CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_RX - #define CFA_L2_FILTER_CFG_REQ_FLAGS_DROP 0x2UL - #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_MASK 0xcUL - #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_SFT 2 - #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_NO_ROCE_L2 (0x0UL << 2) - #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_L2 (0x1UL << 2) - #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_ROCE (0x2UL << 2) - #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_LAST CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_ROCE + #define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH 0x1UL + #define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_TX 0x0UL + #define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_RX 0x1UL + #define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_LAST CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_RX + #define CFA_L2_FILTER_CFG_REQ_FLAGS_DROP 0x2UL + #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_MASK 0xcUL + #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_SFT 2 + #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_NO_ROCE_L2 (0x0UL << 2) + #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_L2 (0x1UL << 2) + #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_ROCE (0x2UL << 2) + #define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_LAST CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_ROCE #define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_MASK 0x30UL #define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_SFT 4 #define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_NO_UPDATE (0x0UL << 4) @@ -8520,17 +8561,17 @@ struct hwrm_tunnel_dst_port_query_input { __le16 target_id; __le64 resp_addr; u8 tunnel_type; - #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN 0x1UL - #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_GENEVE 0x5UL - #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_V4 0x9UL - #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_IPGRE_V1 0xaUL - #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_L2_ETYPE 0xbUL - #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL - #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_CUSTOM_GRE 0xdUL - #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ECPRI 0xeUL - #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_SRV6 0xfUL - #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_GPE 0x10UL - #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_GRE 0x11UL + #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN 0x1UL + #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_GENEVE 0x5UL + #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_V4 0x9UL + #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_IPGRE_V1 0xaUL + #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_L2_ETYPE 0xbUL + #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL + #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_CUSTOM_GRE 0xdUL + #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ECPRI 0xeUL + #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_SRV6 0xfUL + #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_GPE 0x10UL + #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_GRE 0x11UL #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR 0x12UL #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES01 0x13UL #define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES02 0x14UL @@ -8576,17 +8617,17 @@ struct hwrm_tunnel_dst_port_alloc_input { __le16 target_id; __le64 resp_addr; u8 tunnel_type; - #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN 0x1UL - #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_GENEVE 0x5UL - #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4 0x9UL - #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1 0xaUL - #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE 0xbUL - #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL - #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_CUSTOM_GRE 0xdUL - #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ECPRI 0xeUL - #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_SRV6 0xfUL - #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE 0x10UL - #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_GRE 0x11UL + #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN 0x1UL + #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_GENEVE 0x5UL + #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4 0x9UL + #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1 0xaUL + #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE 0xbUL + #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL + #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_CUSTOM_GRE 0xdUL + #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ECPRI 0xeUL + #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_SRV6 0xfUL + #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE 0x10UL + #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_GRE 0x11UL #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR 0x12UL #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES01 0x13UL #define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES02 0x14UL @@ -8635,17 +8676,17 @@ struct hwrm_tunnel_dst_port_free_input { __le16 target_id; __le64 resp_addr; u8 tunnel_type; - #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN 0x1UL - #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GENEVE 0x5UL - #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_V4 0x9UL - #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_IPGRE_V1 0xaUL - #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_L2_ETYPE 0xbUL - #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL - #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_CUSTOM_GRE 0xdUL - #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ECPRI 0xeUL - #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_SRV6 0xfUL - #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_GPE 0x10UL - #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GRE 0x11UL + #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN 0x1UL + #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GENEVE 0x5UL + #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_V4 0x9UL + #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_IPGRE_V1 0xaUL + #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_L2_ETYPE 0xbUL + #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL + #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_CUSTOM_GRE 0xdUL + #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ECPRI 0xeUL + #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_SRV6 0xfUL + #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_GPE 0x10UL + #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GRE 0x11UL #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR 0x12UL #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES01 0x13UL #define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES02 0x14UL @@ -9109,6 +9150,7 @@ struct hwrm_struct_hdr { #define STRUCT_HDR_STRUCT_ID_LLDP_GENERIC 0x424UL #define STRUCT_HDR_STRUCT_ID_LLDP_DEVICE 0x426UL #define STRUCT_HDR_STRUCT_ID_POWER_BKUP 0x427UL + #define STRUCT_HDR_STRUCT_ID_PEER_MMAP 0x429UL #define STRUCT_HDR_STRUCT_ID_AFM_OPAQUE 0x1UL #define STRUCT_HDR_STRUCT_ID_PORT_DESCRIPTION 0xaUL #define STRUCT_HDR_STRUCT_ID_RSS_V2 0x64UL @@ -9758,6 +9800,9 @@ struct hwrm_dbg_coredump_initiate_input { __le16 instance; __le16 unused_0; u8 seg_flags; + #define DBG_COREDUMP_INITIATE_REQ_SEG_FLAGS_LIVE_DATA 0x1UL + #define DBG_COREDUMP_INITIATE_REQ_SEG_FLAGS_CRASH_DATA 0x2UL + #define DBG_COREDUMP_INITIATE_REQ_SEG_FLAGS_COLLECT_CTX_L1_CACHE 0x4UL u8 unused_1[7]; }; @@ -10433,13 +10478,13 @@ struct hwrm_selftest_irq_output { /* dbc_dbc (size:64b/8B) */ struct dbc_dbc { - u32 index; + __le32 index; #define DBC_DBC_INDEX_MASK 0xffffffUL #define DBC_DBC_INDEX_SFT 0 #define DBC_DBC_EPOCH 0x1000000UL #define DBC_DBC_TOGGLE_MASK 0x6000000UL #define DBC_DBC_TOGGLE_SFT 25 - u32 type_path_xid; + __le32 type_path_xid; #define DBC_DBC_XID_MASK 0xfffffUL #define DBC_DBC_XID_SFT 0 #define DBC_DBC_PATH_MASK 0x3000000UL diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 881ece735dcf..fb19295529a2 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1361,6 +1361,12 @@ fec_stop(struct net_device *ndev) writel(FEC_ECR_ETHEREN, fep->hwp + FEC_ECNTRL); writel(rmii_mode, fep->hwp + FEC_R_CNTRL); } + + if (fep->bufdesc_ex) { + val = readl(fep->hwp + FEC_ECNTRL); + val |= FEC_ECR_EN1588; + writel(val, fep->hwp + FEC_ECNTRL); + } } static void diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.c b/drivers/net/ethernet/intel/ice/ice_ddp.c index ce5034ed2b24..f182179529b7 100644 --- a/drivers/net/ethernet/intel/ice/ice_ddp.c +++ b/drivers/net/ethernet/intel/ice/ice_ddp.c @@ -1339,6 +1339,7 @@ ice_dwnld_cfg_bufs_no_lock(struct ice_hw *hw, struct ice_buf *bufs, u32 start, for (i = 0; i < count; i++) { bool last = false; + int try_cnt = 0; int status; bh = (struct ice_buf_hdr *)(bufs + start + i); @@ -1346,8 +1347,26 @@ ice_dwnld_cfg_bufs_no_lock(struct ice_hw *hw, struct ice_buf *bufs, u32 start, if (indicate_last) last = ice_is_last_download_buffer(bh, i, count); - status = ice_aq_download_pkg(hw, bh, ICE_PKG_BUF_SIZE, last, - &offset, &info, NULL); + while (1) { + status = ice_aq_download_pkg(hw, bh, ICE_PKG_BUF_SIZE, + last, &offset, &info, + NULL); + if (hw->adminq.sq_last_status != ICE_AQ_RC_ENOSEC && + hw->adminq.sq_last_status != ICE_AQ_RC_EBADSIG) + break; + + try_cnt++; + + if (try_cnt == 5) + break; + + msleep(20); + } + + if (try_cnt) + dev_dbg(ice_hw_to_dev(hw), + "ice_aq_download_pkg number of retries: %d\n", + try_cnt); /* Save AQ status from download package */ if (status) { diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 7d9a4e856f61..643384c9fbf4 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -805,6 +805,9 @@ void ice_print_link_msg(struct ice_vsi *vsi, bool isup) } switch (vsi->port_info->phy.link_info.link_speed) { + case ICE_AQ_LINK_SPEED_200GB: + speed = "200 G"; + break; case ICE_AQ_LINK_SPEED_100GB: speed = "100 G"; break; @@ -5564,7 +5567,7 @@ static int ice_suspend(struct device *dev) */ disabled = ice_service_task_stop(pf); - ice_unplug_aux_dev(pf); + ice_deinit_rdma(pf); /* Already suspended?, then there is nothing to do */ if (test_and_set_bit(ICE_SUSPENDED, pf->state)) { @@ -5644,6 +5647,11 @@ static int ice_resume(struct device *dev) if (ret) dev_err(dev, "Cannot restore interrupt scheme: %d\n", ret); + ret = ice_init_rdma(pf); + if (ret) + dev_err(dev, "Reinitialize RDMA during resume failed: %d\n", + ret); + clear_bit(ICE_DOWN, pf->state); /* Now perform PF reset and rebuild */ reset_type = ICE_RESET_PFR; diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index 94d6670d0901..1191031b2a43 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -1899,7 +1899,8 @@ ice_aq_alloc_free_vsi_list(struct ice_hw *hw, u16 *vsi_list_id, lkup_type == ICE_SW_LKUP_ETHERTYPE_MAC || lkup_type == ICE_SW_LKUP_PROMISC || lkup_type == ICE_SW_LKUP_PROMISC_VLAN || - lkup_type == ICE_SW_LKUP_DFLT) { + lkup_type == ICE_SW_LKUP_DFLT || + lkup_type == ICE_SW_LKUP_LAST) { sw_buf->res_type = cpu_to_le16(ICE_AQC_RES_TYPE_VSI_LIST_REP); } else if (lkup_type == ICE_SW_LKUP_VLAN) { if (opc == ice_aqc_opc_alloc_res) @@ -2922,7 +2923,8 @@ ice_update_vsi_list_rule(struct ice_hw *hw, u16 *vsi_handle_arr, u16 num_vsi, lkup_type == ICE_SW_LKUP_ETHERTYPE_MAC || lkup_type == ICE_SW_LKUP_PROMISC || lkup_type == ICE_SW_LKUP_PROMISC_VLAN || - lkup_type == ICE_SW_LKUP_DFLT) + lkup_type == ICE_SW_LKUP_DFLT || + lkup_type == ICE_SW_LKUP_LAST) rule_type = remove ? ICE_AQC_SW_RULES_T_VSI_LIST_CLEAR : ICE_AQC_SW_RULES_T_VSI_LIST_SET; else if (lkup_type == ICE_SW_LKUP_VLAN) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index fce2930ae6af..3af03a211c3c 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -9139,6 +9139,10 @@ static int igb_mii_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) return -EIO; break; case SIOCSMIIREG: + if (igb_write_phy_reg(&adapter->hw, data->reg_num & 0x1F, + data->val_in)) + return -EIO; + break; default: return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index e91486c48de3..671368d2c77e 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -4014,7 +4014,10 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi, } } - skb = build_skb(data, frag_size); + if (frag_size) + skb = build_skb(data, frag_size); + else + skb = slab_build_skb(data); if (!skb) { netdev_warn(port->dev, "skb build failed\n"); goto err_drop_frame; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile index 5664f768cb0c..64a97a0a10ed 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile +++ b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile @@ -9,10 +9,9 @@ obj-$(CONFIG_OCTEONTX2_VF) += rvu_nicvf.o otx2_ptp.o rvu_nicpf-y := otx2_pf.o otx2_common.o otx2_txrx.o otx2_ethtool.o \ otx2_flows.o otx2_tc.o cn10k.o otx2_dmac_flt.o \ otx2_devlink.o qos_sq.o qos.o -rvu_nicvf-y := otx2_vf.o otx2_devlink.o +rvu_nicvf-y := otx2_vf.o rvu_nicpf-$(CONFIG_DCB) += otx2_dcbnl.o -rvu_nicvf-$(CONFIG_DCB) += otx2_dcbnl.o rvu_nicpf-$(CONFIG_MACSEC) += cn10k_macsec.o ccflags-y += -I$(srctree)/drivers/net/ethernet/marvell/octeontx2/af diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h index 24fbbef265a6..f27a3456ae64 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h @@ -346,12 +346,9 @@ struct otx2_flow_config { u16 *def_ent; u16 nr_flows; #define OTX2_DEFAULT_FLOWCOUNT 16 -#define OTX2_MAX_UNICAST_FLOWS 8 +#define OTX2_DEFAULT_UNICAST_FLOWS 4 #define OTX2_MAX_VLAN_FLOWS 1 #define OTX2_MAX_TC_FLOWS OTX2_DEFAULT_FLOWCOUNT -#define OTX2_MCAM_COUNT (OTX2_DEFAULT_FLOWCOUNT + \ - OTX2_MAX_UNICAST_FLOWS + \ - OTX2_MAX_VLAN_FLOWS) u16 unicast_offset; u16 rx_vlan_offset; u16 vf_vlan_offset; @@ -365,6 +362,7 @@ struct otx2_flow_config { u16 max_flows; refcount_t mark_flows; struct list_head flow_list_tc; + u8 ucast_flt_cnt; bool ntuple; }; @@ -1067,6 +1065,7 @@ int otx2_handle_ntuple_tc_features(struct net_device *netdev, int otx2_smq_flush(struct otx2_nic *pfvf, int smq); void otx2_free_bufs(struct otx2_nic *pfvf, struct otx2_pool *pool, u64 iova, int size); +int otx2_mcam_entry_init(struct otx2_nic *pfvf); /* tc support */ int otx2_init_tc(struct otx2_nic *nic); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c index 28fb643d2917..aa01110f04a3 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c @@ -54,6 +54,7 @@ int otx2_pfc_txschq_config(struct otx2_nic *pfvf) return 0; } +EXPORT_SYMBOL(otx2_pfc_txschq_config); static int otx2_pfc_txschq_alloc_one(struct otx2_nic *pfvf, u8 prio) { @@ -122,6 +123,7 @@ int otx2_pfc_txschq_alloc(struct otx2_nic *pfvf) return 0; } +EXPORT_SYMBOL(otx2_pfc_txschq_alloc); static int otx2_pfc_txschq_stop_one(struct otx2_nic *pfvf, u8 prio) { @@ -260,6 +262,7 @@ update_sq_smq_map: return 0; } +EXPORT_SYMBOL(otx2_pfc_txschq_update); int otx2_pfc_txschq_stop(struct otx2_nic *pfvf) { @@ -282,6 +285,7 @@ int otx2_pfc_txschq_stop(struct otx2_nic *pfvf) return 0; } +EXPORT_SYMBOL(otx2_pfc_txschq_stop); int otx2_config_priority_flow_ctrl(struct otx2_nic *pfvf) { @@ -321,6 +325,7 @@ unlock: mutex_unlock(&pfvf->mbox.lock); return err; } +EXPORT_SYMBOL(otx2_config_priority_flow_ctrl); void otx2_update_bpid_in_rqctx(struct otx2_nic *pfvf, int vlan_prio, int qidx, bool pfc_enable) @@ -385,6 +390,7 @@ out: "Updating BPIDs in CQ and Aura contexts of RQ%d failed with err %d\n", qidx, err); } +EXPORT_SYMBOL(otx2_update_bpid_in_rqctx); static int otx2_dcbnl_ieee_getpfc(struct net_device *dev, struct ieee_pfc *pfc) { @@ -472,3 +478,4 @@ int otx2_dcbnl_set_ops(struct net_device *dev) return 0; } +EXPORT_SYMBOL(otx2_dcbnl_set_ops); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c index 99ddf31269d9..53f14aa944bd 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c @@ -64,9 +64,68 @@ static int otx2_dl_mcam_count_get(struct devlink *devlink, u32 id, return 0; } +static int otx2_dl_ucast_flt_cnt_set(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) +{ + struct otx2_devlink *otx2_dl = devlink_priv(devlink); + struct otx2_nic *pfvf = otx2_dl->pfvf; + int err; + + pfvf->flow_cfg->ucast_flt_cnt = ctx->val.vu8; + + otx2_mcam_flow_del(pfvf); + err = otx2_mcam_entry_init(pfvf); + if (err) + return err; + + return 0; +} + +static int otx2_dl_ucast_flt_cnt_get(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx) +{ + struct otx2_devlink *otx2_dl = devlink_priv(devlink); + struct otx2_nic *pfvf = otx2_dl->pfvf; + + ctx->val.vu8 = pfvf->flow_cfg ? pfvf->flow_cfg->ucast_flt_cnt : 0; + + return 0; +} + +static int otx2_dl_ucast_flt_cnt_validate(struct devlink *devlink, u32 id, + union devlink_param_value val, + struct netlink_ext_ack *extack) +{ + struct otx2_devlink *otx2_dl = devlink_priv(devlink); + struct otx2_nic *pfvf = otx2_dl->pfvf; + + /* Check for UNICAST filter support*/ + if (!(pfvf->flags & OTX2_FLAG_UCAST_FLTR_SUPPORT)) { + NL_SET_ERR_MSG_MOD(extack, + "Unicast filter not enabled"); + return -EINVAL; + } + + if (!pfvf->flow_cfg) { + NL_SET_ERR_MSG_MOD(extack, + "pfvf->flow_cfg not initialized"); + return -EINVAL; + } + + if (pfvf->flow_cfg->nr_flows) { + NL_SET_ERR_MSG_MOD(extack, + "Cannot modify count when there are active rules"); + return -EINVAL; + } + + return 0; +} + enum otx2_dl_param_id { OTX2_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX, OTX2_DEVLINK_PARAM_ID_MCAM_COUNT, + OTX2_DEVLINK_PARAM_ID_UCAST_FLT_CNT, }; static const struct devlink_param otx2_dl_params[] = { @@ -75,6 +134,11 @@ static const struct devlink_param otx2_dl_params[] = { BIT(DEVLINK_PARAM_CMODE_RUNTIME), otx2_dl_mcam_count_get, otx2_dl_mcam_count_set, otx2_dl_mcam_count_validate), + DEVLINK_PARAM_DRIVER(OTX2_DEVLINK_PARAM_ID_UCAST_FLT_CNT, + "unicast_filter_count", DEVLINK_PARAM_TYPE_U8, + BIT(DEVLINK_PARAM_CMODE_RUNTIME), + otx2_dl_ucast_flt_cnt_get, otx2_dl_ucast_flt_cnt_set, + otx2_dl_ucast_flt_cnt_validate), }; static const struct devlink_ops otx2_devlink_ops = { @@ -113,6 +177,7 @@ err_dl: devlink_free(dl); return err; } +EXPORT_SYMBOL(otx2_register_dl); void otx2_unregister_dl(struct otx2_nic *pfvf) { @@ -124,3 +189,4 @@ void otx2_unregister_dl(struct otx2_nic *pfvf) ARRAY_SIZE(otx2_dl_params)); devlink_free(dl); } +EXPORT_SYMBOL(otx2_unregister_dl); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c index bc5819237ed7..98c31a16c70b 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c @@ -12,8 +12,6 @@ #define OTX2_DEFAULT_ACTION 0x1 -static int otx2_mcam_entry_init(struct otx2_nic *pfvf); - struct otx2_flow { struct ethtool_rx_flow_spec flow_spec; struct list_head list; @@ -161,7 +159,7 @@ exit: } EXPORT_SYMBOL(otx2_alloc_mcam_entries); -static int otx2_mcam_entry_init(struct otx2_nic *pfvf) +int otx2_mcam_entry_init(struct otx2_nic *pfvf) { struct otx2_flow_config *flow_cfg = pfvf->flow_cfg; struct npc_get_field_status_req *freq; @@ -172,7 +170,7 @@ static int otx2_mcam_entry_init(struct otx2_nic *pfvf) int ent, count; vf_vlan_max_flows = pfvf->total_vfs * OTX2_PER_VF_VLAN_FLOWS; - count = OTX2_MAX_UNICAST_FLOWS + + count = flow_cfg->ucast_flt_cnt + OTX2_MAX_VLAN_FLOWS + vf_vlan_max_flows; flow_cfg->def_ent = devm_kmalloc_array(pfvf->dev, count, @@ -214,7 +212,7 @@ static int otx2_mcam_entry_init(struct otx2_nic *pfvf) flow_cfg->vf_vlan_offset = 0; flow_cfg->unicast_offset = vf_vlan_max_flows; flow_cfg->rx_vlan_offset = flow_cfg->unicast_offset + - OTX2_MAX_UNICAST_FLOWS; + flow_cfg->ucast_flt_cnt; pfvf->flags |= OTX2_FLAG_UCAST_FLTR_SUPPORT; /* Check if NPC_DMAC field is supported @@ -255,6 +253,7 @@ static int otx2_mcam_entry_init(struct otx2_nic *pfvf) refcount_set(&flow_cfg->mark_flows, 1); return 0; } +EXPORT_SYMBOL(otx2_mcam_entry_init); /* TODO : revisit on size */ #define OTX2_DMAC_FLTR_BITMAP_SZ (4 * 2048 + 32) @@ -302,6 +301,8 @@ int otx2_mcam_flow_init(struct otx2_nic *pf) INIT_LIST_HEAD(&pf->flow_cfg->flow_list); INIT_LIST_HEAD(&pf->flow_cfg->flow_list_tc); + pf->flow_cfg->ucast_flt_cnt = OTX2_DEFAULT_UNICAST_FLOWS; + /* Allocate bare minimum number of MCAM entries needed for * unicast and ntuple filters. */ @@ -314,7 +315,7 @@ int otx2_mcam_flow_init(struct otx2_nic *pf) return 0; pf->mac_table = devm_kzalloc(pf->dev, sizeof(struct otx2_mac_table) - * OTX2_MAX_UNICAST_FLOWS, GFP_KERNEL); + * pf->flow_cfg->ucast_flt_cnt, GFP_KERNEL); if (!pf->mac_table) return -ENOMEM; @@ -356,7 +357,7 @@ static int otx2_do_add_macfilter(struct otx2_nic *pf, const u8 *mac) return -ENOMEM; /* dont have free mcam entries or uc list is greater than alloted */ - if (netdev_uc_count(pf->netdev) > OTX2_MAX_UNICAST_FLOWS) + if (netdev_uc_count(pf->netdev) > pf->flow_cfg->ucast_flt_cnt) return -ENOMEM; mutex_lock(&pf->mbox.lock); @@ -367,7 +368,7 @@ static int otx2_do_add_macfilter(struct otx2_nic *pf, const u8 *mac) } /* unicast offset starts with 32 0..31 for ntuple */ - for (i = 0; i < OTX2_MAX_UNICAST_FLOWS; i++) { + for (i = 0; i < pf->flow_cfg->ucast_flt_cnt; i++) { if (pf->mac_table[i].inuse) continue; ether_addr_copy(pf->mac_table[i].addr, mac); @@ -410,7 +411,7 @@ static bool otx2_get_mcamentry_for_mac(struct otx2_nic *pf, const u8 *mac, { int i; - for (i = 0; i < OTX2_MAX_UNICAST_FLOWS; i++) { + for (i = 0; i < pf->flow_cfg->ucast_flt_cnt; i++) { if (!pf->mac_table[i].inuse) continue; @@ -1394,6 +1395,7 @@ int otx2_destroy_mcam_flows(struct otx2_nic *pfvf) } pfvf->flags &= ~OTX2_FLAG_MCAM_ENTRIES_ALLOC; + flow_cfg->max_flows = 0; mutex_unlock(&pfvf->mbox.lock); return 0; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index f5bce3e326cc..ff05ea20409a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -1714,7 +1714,7 @@ static void otx2_do_set_rx_mode(struct otx2_nic *pf) return; if ((netdev->flags & IFF_PROMISC) || - (netdev_uc_count(netdev) > OTX2_MAX_UNICAST_FLOWS)) { + (netdev_uc_count(netdev) > pf->flow_cfg->ucast_flt_cnt)) { promisc = true; } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c index a16e9f244117..929b4eac25d9 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c @@ -1174,8 +1174,11 @@ bool otx2_sq_append_skb(struct net_device *netdev, struct otx2_snd_queue *sq, if (skb_shinfo(skb)->gso_size && !is_hw_tso_supported(pfvf, skb)) { /* Insert vlan tag before giving pkt to tso */ - if (skb_vlan_tag_present(skb)) + if (skb_vlan_tag_present(skb)) { skb = __vlan_hwaccel_push_inside(skb); + if (!skb) + return true; + } otx2_sq_append_tso(pfvf, sq, skb, qidx); return true; } diff --git a/drivers/net/ethernet/microchip/lan743x_ethtool.c b/drivers/net/ethernet/microchip/lan743x_ethtool.c index d0f4ff4ee075..0d1740d64676 100644 --- a/drivers/net/ethernet/microchip/lan743x_ethtool.c +++ b/drivers/net/ethernet/microchip/lan743x_ethtool.c @@ -1127,8 +1127,12 @@ static void lan743x_ethtool_get_wol(struct net_device *netdev, if (netdev->phydev) phy_ethtool_get_wol(netdev->phydev, wol); - wol->supported |= WAKE_BCAST | WAKE_UCAST | WAKE_MCAST | - WAKE_MAGIC | WAKE_PHY | WAKE_ARP; + if (wol->supported != adapter->phy_wol_supported) + netif_warn(adapter, drv, adapter->netdev, + "PHY changed its supported WOL! old=%x, new=%x\n", + adapter->phy_wol_supported, wol->supported); + + wol->supported |= MAC_SUPPORTED_WAKES; if (adapter->is_pci11x1x) wol->supported |= WAKE_MAGICSECURE; @@ -1143,7 +1147,39 @@ static int lan743x_ethtool_set_wol(struct net_device *netdev, { struct lan743x_adapter *adapter = netdev_priv(netdev); + /* WAKE_MAGICSEGURE is a modifier of and only valid together with + * WAKE_MAGIC + */ + if ((wol->wolopts & WAKE_MAGICSECURE) && !(wol->wolopts & WAKE_MAGIC)) + return -EINVAL; + + if (netdev->phydev) { + struct ethtool_wolinfo phy_wol; + int ret; + + phy_wol.wolopts = wol->wolopts & adapter->phy_wol_supported; + + /* If WAKE_MAGICSECURE was requested, filter out WAKE_MAGIC + * for PHYs that do not support WAKE_MAGICSECURE + */ + if (wol->wolopts & WAKE_MAGICSECURE && + !(adapter->phy_wol_supported & WAKE_MAGICSECURE)) + phy_wol.wolopts &= ~WAKE_MAGIC; + + ret = phy_ethtool_set_wol(netdev->phydev, &phy_wol); + if (ret && (ret != -EOPNOTSUPP)) + return ret; + + if (ret == -EOPNOTSUPP) + adapter->phy_wolopts = 0; + else + adapter->phy_wolopts = phy_wol.wolopts; + } else { + adapter->phy_wolopts = 0; + } + adapter->wolopts = 0; + wol->wolopts &= ~adapter->phy_wolopts; if (wol->wolopts & WAKE_UCAST) adapter->wolopts |= WAKE_UCAST; if (wol->wolopts & WAKE_MCAST) @@ -1164,10 +1200,10 @@ static int lan743x_ethtool_set_wol(struct net_device *netdev, memset(adapter->sopass, 0, sizeof(u8) * SOPASS_MAX); } + wol->wolopts = adapter->wolopts | adapter->phy_wolopts; device_set_wakeup_enable(&adapter->pdev->dev, (bool)wol->wolopts); - return netdev->phydev ? phy_ethtool_set_wol(netdev->phydev, wol) - : -ENETDOWN; + return 0; } #endif /* CONFIG_PM */ diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index 6be8a43c908a..e418539565b1 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -3118,6 +3118,17 @@ static int lan743x_netdev_open(struct net_device *netdev) if (ret) goto close_tx; } + +#ifdef CONFIG_PM + if (adapter->netdev->phydev) { + struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL }; + + phy_ethtool_get_wol(netdev->phydev, &wol); + adapter->phy_wol_supported = wol.supported; + adapter->phy_wolopts = wol.wolopts; + } +#endif + return 0; close_tx: @@ -3575,7 +3586,7 @@ static void lan743x_pm_set_wol(struct lan743x_adapter *adapter) /* clear wake settings */ pmtctl = lan743x_csr_read(adapter, PMT_CTL); - pmtctl |= PMT_CTL_WUPS_MASK_; + pmtctl |= PMT_CTL_WUPS_MASK_ | PMT_CTL_RES_CLR_WKP_MASK_; pmtctl &= ~(PMT_CTL_GPIO_WAKEUP_EN_ | PMT_CTL_EEE_WAKEUP_EN_ | PMT_CTL_WOL_EN_ | PMT_CTL_MAC_D3_RX_CLK_OVR_ | PMT_CTL_RX_FCT_RFE_D3_CLK_OVR_ | PMT_CTL_ETH_PHY_WAKE_EN_); @@ -3587,10 +3598,9 @@ static void lan743x_pm_set_wol(struct lan743x_adapter *adapter) pmtctl |= PMT_CTL_ETH_PHY_D3_COLD_OVR_ | PMT_CTL_ETH_PHY_D3_OVR_; - if (adapter->wolopts & WAKE_PHY) { - pmtctl |= PMT_CTL_ETH_PHY_EDPD_PLL_CTL_; + if (adapter->phy_wolopts) pmtctl |= PMT_CTL_ETH_PHY_WAKE_EN_; - } + if (adapter->wolopts & WAKE_MAGIC) { wucsr |= MAC_WUCSR_MPEN_; macrx |= MAC_RX_RXEN_; @@ -3686,7 +3696,7 @@ static int lan743x_pm_suspend(struct device *dev) lan743x_csr_write(adapter, MAC_WUCSR2, 0); lan743x_csr_write(adapter, MAC_WK_SRC, 0xFFFFFFFF); - if (adapter->wolopts) + if (adapter->wolopts || adapter->phy_wolopts) lan743x_pm_set_wol(adapter); if (adapter->is_pci11x1x) { @@ -3710,6 +3720,7 @@ static int lan743x_pm_resume(struct device *dev) struct pci_dev *pdev = to_pci_dev(dev); struct net_device *netdev = pci_get_drvdata(pdev); struct lan743x_adapter *adapter = netdev_priv(netdev); + u32 data; int ret; pci_set_power_state(pdev, PCI_D0); @@ -3728,6 +3739,30 @@ static int lan743x_pm_resume(struct device *dev) return ret; } + ret = lan743x_csr_read(adapter, MAC_WK_SRC); + netif_dbg(adapter, drv, adapter->netdev, + "Wakeup source : 0x%08X\n", ret); + + /* Clear the wol configuration and status bits. Note that + * the status bits are "Write One to Clear (W1C)" + */ + data = MAC_WUCSR_EEE_TX_WAKE_ | MAC_WUCSR_EEE_RX_WAKE_ | + MAC_WUCSR_RFE_WAKE_FR_ | MAC_WUCSR_PFDA_FR_ | MAC_WUCSR_WUFR_ | + MAC_WUCSR_MPR_ | MAC_WUCSR_BCAST_FR_; + lan743x_csr_write(adapter, MAC_WUCSR, data); + + data = MAC_WUCSR2_NS_RCD_ | MAC_WUCSR2_ARP_RCD_ | + MAC_WUCSR2_IPV6_TCPSYN_RCD_ | MAC_WUCSR2_IPV4_TCPSYN_RCD_; + lan743x_csr_write(adapter, MAC_WUCSR2, data); + + data = MAC_WK_SRC_ETH_PHY_WK_ | MAC_WK_SRC_IPV6_TCPSYN_RCD_WK_ | + MAC_WK_SRC_IPV4_TCPSYN_RCD_WK_ | MAC_WK_SRC_EEE_TX_WK_ | + MAC_WK_SRC_EEE_RX_WK_ | MAC_WK_SRC_RFE_FR_WK_ | + MAC_WK_SRC_PFDA_FR_WK_ | MAC_WK_SRC_MP_FR_WK_ | + MAC_WK_SRC_BCAST_FR_WK_ | MAC_WK_SRC_WU_FR_WK_ | + MAC_WK_SRC_WK_FR_SAVED_; + lan743x_csr_write(adapter, MAC_WK_SRC, data); + /* open netdev when netdev is at running state while resume. * For instance, it is true when system wakesup after pm-suspend * However, it is false when system wakes up after suspend GUI menu @@ -3736,9 +3771,6 @@ static int lan743x_pm_resume(struct device *dev) lan743x_netdev_open(netdev); netif_device_attach(netdev); - ret = lan743x_csr_read(adapter, MAC_WK_SRC); - netif_info(adapter, drv, adapter->netdev, - "Wakeup source : 0x%08X\n", ret); return 0; } diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h index 645bc048e52e..3b2585a384e2 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.h +++ b/drivers/net/ethernet/microchip/lan743x_main.h @@ -61,6 +61,7 @@ #define PMT_CTL_RX_FCT_RFE_D3_CLK_OVR_ BIT(18) #define PMT_CTL_GPIO_WAKEUP_EN_ BIT(15) #define PMT_CTL_EEE_WAKEUP_EN_ BIT(13) +#define PMT_CTL_RES_CLR_WKP_MASK_ GENMASK(9, 8) #define PMT_CTL_READY_ BIT(7) #define PMT_CTL_ETH_PHY_RST_ BIT(4) #define PMT_CTL_WOL_EN_ BIT(3) @@ -227,12 +228,31 @@ #define MAC_WUCSR (0x140) #define MAC_MP_SO_EN_ BIT(21) #define MAC_WUCSR_RFE_WAKE_EN_ BIT(14) +#define MAC_WUCSR_EEE_TX_WAKE_ BIT(13) +#define MAC_WUCSR_EEE_RX_WAKE_ BIT(11) +#define MAC_WUCSR_RFE_WAKE_FR_ BIT(9) +#define MAC_WUCSR_PFDA_FR_ BIT(7) +#define MAC_WUCSR_WUFR_ BIT(6) +#define MAC_WUCSR_MPR_ BIT(5) +#define MAC_WUCSR_BCAST_FR_ BIT(4) #define MAC_WUCSR_PFDA_EN_ BIT(3) #define MAC_WUCSR_WAKE_EN_ BIT(2) #define MAC_WUCSR_MPEN_ BIT(1) #define MAC_WUCSR_BCST_EN_ BIT(0) #define MAC_WK_SRC (0x144) +#define MAC_WK_SRC_ETH_PHY_WK_ BIT(17) +#define MAC_WK_SRC_IPV6_TCPSYN_RCD_WK_ BIT(16) +#define MAC_WK_SRC_IPV4_TCPSYN_RCD_WK_ BIT(15) +#define MAC_WK_SRC_EEE_TX_WK_ BIT(14) +#define MAC_WK_SRC_EEE_RX_WK_ BIT(13) +#define MAC_WK_SRC_RFE_FR_WK_ BIT(12) +#define MAC_WK_SRC_PFDA_FR_WK_ BIT(11) +#define MAC_WK_SRC_MP_FR_WK_ BIT(10) +#define MAC_WK_SRC_BCAST_FR_WK_ BIT(9) +#define MAC_WK_SRC_WU_FR_WK_ BIT(8) +#define MAC_WK_SRC_WK_FR_SAVED_ BIT(7) + #define MAC_MP_SO_HI (0x148) #define MAC_MP_SO_LO (0x14C) @@ -295,6 +315,10 @@ #define RFE_INDX(index) (0x580 + (index << 2)) #define MAC_WUCSR2 (0x600) +#define MAC_WUCSR2_NS_RCD_ BIT(7) +#define MAC_WUCSR2_ARP_RCD_ BIT(6) +#define MAC_WUCSR2_IPV6_TCPSYN_RCD_ BIT(5) +#define MAC_WUCSR2_IPV4_TCPSYN_RCD_ BIT(4) #define SGMII_ACC (0x720) #define SGMII_ACC_SGMII_BZY_ BIT(31) @@ -1018,6 +1042,8 @@ enum lan743x_sgmii_lsd { LINK_2500_SLAVE }; +#define MAC_SUPPORTED_WAKES (WAKE_BCAST | WAKE_UCAST | WAKE_MCAST | \ + WAKE_MAGIC | WAKE_ARP) struct lan743x_adapter { struct net_device *netdev; struct mii_bus *mdiobus; @@ -1025,6 +1051,8 @@ struct lan743x_adapter { #ifdef CONFIG_PM u32 wolopts; u8 sopass[SOPASS_MAX]; + u32 phy_wolopts; + u32 phy_wol_supported; #endif struct pci_dev *pdev; struct lan743x_csr csr; diff --git a/drivers/net/ethernet/qualcomm/qca_debug.c b/drivers/net/ethernet/qualcomm/qca_debug.c index ff3b89e9028e..ad06da0fdaa0 100644 --- a/drivers/net/ethernet/qualcomm/qca_debug.c +++ b/drivers/net/ethernet/qualcomm/qca_debug.c @@ -98,10 +98,8 @@ qcaspi_info_show(struct seq_file *s, void *what) seq_printf(s, "IRQ : %d\n", qca->spi_dev->irq); - seq_printf(s, "INTR REQ : %u\n", - qca->intr_req); - seq_printf(s, "INTR SVC : %u\n", - qca->intr_svc); + seq_printf(s, "INTR : %lx\n", + qca->intr); seq_printf(s, "SPI max speed : %lu\n", (unsigned long)qca->spi_dev->max_speed_hz); diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c index 5799ecc88a87..8f7ce6b51a1c 100644 --- a/drivers/net/ethernet/qualcomm/qca_spi.c +++ b/drivers/net/ethernet/qualcomm/qca_spi.c @@ -35,6 +35,8 @@ #define MAX_DMA_BURST_LEN 5000 +#define SPI_INTR 0 + /* Modules parameters */ #define QCASPI_CLK_SPEED_MIN 1000000 #define QCASPI_CLK_SPEED_MAX 16000000 @@ -579,14 +581,14 @@ qcaspi_spi_thread(void *data) continue; } - if ((qca->intr_req == qca->intr_svc) && + if (!test_bit(SPI_INTR, &qca->intr) && !qca->txr.skb[qca->txr.head]) schedule(); set_current_state(TASK_RUNNING); - netdev_dbg(qca->net_dev, "have work to do. int: %d, tx_skb: %p\n", - qca->intr_req - qca->intr_svc, + netdev_dbg(qca->net_dev, "have work to do. int: %lu, tx_skb: %p\n", + qca->intr, qca->txr.skb[qca->txr.head]); qcaspi_qca7k_sync(qca, QCASPI_EVENT_UPDATE); @@ -600,8 +602,7 @@ qcaspi_spi_thread(void *data) msleep(QCASPI_QCA7K_REBOOT_TIME_MS); } - if (qca->intr_svc != qca->intr_req) { - qca->intr_svc = qca->intr_req; + if (test_and_clear_bit(SPI_INTR, &qca->intr)) { start_spi_intr_handling(qca, &intr_cause); if (intr_cause & SPI_INT_CPU_ON) { @@ -663,7 +664,7 @@ qcaspi_intr_handler(int irq, void *data) { struct qcaspi *qca = data; - qca->intr_req++; + set_bit(SPI_INTR, &qca->intr); if (qca->spi_thread) wake_up_process(qca->spi_thread); @@ -679,8 +680,7 @@ qcaspi_netdev_open(struct net_device *dev) if (!qca) return -EINVAL; - qca->intr_req = 1; - qca->intr_svc = 0; + set_bit(SPI_INTR, &qca->intr); qca->sync = QCASPI_SYNC_UNKNOWN; qcafrm_fsm_init_spi(&qca->frm_handle); diff --git a/drivers/net/ethernet/qualcomm/qca_spi.h b/drivers/net/ethernet/qualcomm/qca_spi.h index d59cb2352cee..8f4808695e82 100644 --- a/drivers/net/ethernet/qualcomm/qca_spi.h +++ b/drivers/net/ethernet/qualcomm/qca_spi.h @@ -81,8 +81,7 @@ struct qcaspi { struct qcafrm_handle frm_handle; struct sk_buff *rx_skb; - unsigned int intr_req; - unsigned int intr_svc; + unsigned long intr; u16 reset_count; #ifdef CONFIG_DEBUG_FS diff --git a/drivers/net/ethernet/renesas/Kconfig b/drivers/net/ethernet/renesas/Kconfig index 83de7e56da61..9b7559c88bee 100644 --- a/drivers/net/ethernet/renesas/Kconfig +++ b/drivers/net/ethernet/renesas/Kconfig @@ -59,4 +59,14 @@ config RENESAS_GEN4_PTP help Renesas R-Car Gen4 gPTP device driver. +config RTSN + tristate "Renesas Ethernet-TSN support" + depends on ARCH_RENESAS || COMPILE_TEST + depends on PTP_1588_CLOCK + select CRC32 + select PHYLIB + select RENESAS_GEN4_PTP + help + Renesas Ethernet-TSN device driver. + endif # NET_VENDOR_RENESAS diff --git a/drivers/net/ethernet/renesas/Makefile b/drivers/net/ethernet/renesas/Makefile index 9070acfd6aaf..f65fc76f8b4d 100644 --- a/drivers/net/ethernet/renesas/Makefile +++ b/drivers/net/ethernet/renesas/Makefile @@ -11,3 +11,5 @@ obj-$(CONFIG_RAVB) += ravb.o obj-$(CONFIG_RENESAS_ETHER_SWITCH) += rswitch.o obj-$(CONFIG_RENESAS_GEN4_PTP) += rcar_gen4_ptp.o + +obj-$(CONFIG_RTSN) += rtsn.o diff --git a/drivers/net/ethernet/renesas/rtsn.c b/drivers/net/ethernet/renesas/rtsn.c new file mode 100644 index 000000000000..ad69d47463cb --- /dev/null +++ b/drivers/net/ethernet/renesas/rtsn.c @@ -0,0 +1,1391 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* Renesas Ethernet-TSN device driver + * + * Copyright (C) 2022 Renesas Electronics Corporation + * Copyright (C) 2023 Niklas Söderlund <[email protected]> + */ + +#include <linux/clk.h> +#include <linux/dma-mapping.h> +#include <linux/etherdevice.h> +#include <linux/ethtool.h> +#include <linux/module.h> +#include <linux/net_tstamp.h> +#include <linux/of.h> +#include <linux/of_mdio.h> +#include <linux/of_net.h> +#include <linux/phy.h> +#include <linux/platform_device.h> +#include <linux/pm_runtime.h> +#include <linux/reset.h> +#include <linux/spinlock.h> + +#include "rtsn.h" +#include "rcar_gen4_ptp.h" + +struct rtsn_private { + struct net_device *ndev; + struct platform_device *pdev; + void __iomem *base; + struct rcar_gen4_ptp_private *ptp_priv; + struct clk *clk; + struct reset_control *reset; + + u32 num_tx_ring; + u32 num_rx_ring; + u32 tx_desc_bat_size; + dma_addr_t tx_desc_bat_dma; + struct rtsn_desc *tx_desc_bat; + u32 rx_desc_bat_size; + dma_addr_t rx_desc_bat_dma; + struct rtsn_desc *rx_desc_bat; + dma_addr_t tx_desc_dma; + dma_addr_t rx_desc_dma; + struct rtsn_ext_desc *tx_ring; + struct rtsn_ext_ts_desc *rx_ring; + struct sk_buff **tx_skb; + struct sk_buff **rx_skb; + spinlock_t lock; /* Register access lock */ + u32 cur_tx; + u32 dirty_tx; + u32 cur_rx; + u32 dirty_rx; + u8 ts_tag; + struct napi_struct napi; + struct rtnl_link_stats64 stats; + + struct mii_bus *mii; + phy_interface_t iface; + int link; + int speed; + + int tx_data_irq; + int rx_data_irq; +}; + +static u32 rtsn_read(struct rtsn_private *priv, enum rtsn_reg reg) +{ + return ioread32(priv->base + reg); +} + +static void rtsn_write(struct rtsn_private *priv, enum rtsn_reg reg, u32 data) +{ + iowrite32(data, priv->base + reg); +} + +static void rtsn_modify(struct rtsn_private *priv, enum rtsn_reg reg, + u32 clear, u32 set) +{ + rtsn_write(priv, reg, (rtsn_read(priv, reg) & ~clear) | set); +} + +static int rtsn_reg_wait(struct rtsn_private *priv, enum rtsn_reg reg, + u32 mask, u32 expected) +{ + u32 val; + + return readl_poll_timeout(priv->base + reg, val, + (val & mask) == expected, + RTSN_INTERVAL_US, RTSN_TIMEOUT_US); +} + +static void rtsn_ctrl_data_irq(struct rtsn_private *priv, bool enable) +{ + if (enable) { + rtsn_write(priv, TDIE0, TDIE_TDID_TDX(TX_CHAIN_IDX)); + rtsn_write(priv, RDIE0, RDIE_RDID_RDX(RX_CHAIN_IDX)); + } else { + rtsn_write(priv, TDID0, TDIE_TDID_TDX(TX_CHAIN_IDX)); + rtsn_write(priv, RDID0, RDIE_RDID_RDX(RX_CHAIN_IDX)); + } +} + +static void rtsn_get_timestamp(struct rtsn_private *priv, struct timespec64 *ts) +{ + struct rcar_gen4_ptp_private *ptp_priv = priv->ptp_priv; + + ptp_priv->info.gettime64(&ptp_priv->info, ts); +} + +static int rtsn_tx_free(struct net_device *ndev, bool free_txed_only) +{ + struct rtsn_private *priv = netdev_priv(ndev); + struct rtsn_ext_desc *desc; + struct sk_buff *skb; + int free_num = 0; + int entry, size; + + for (; priv->cur_tx - priv->dirty_tx > 0; priv->dirty_tx++) { + entry = priv->dirty_tx % priv->num_tx_ring; + desc = &priv->tx_ring[entry]; + if (free_txed_only && (desc->die_dt & DT_MASK) != DT_FEMPTY) + break; + + dma_rmb(); + size = le16_to_cpu(desc->info_ds) & TX_DS; + skb = priv->tx_skb[entry]; + if (skb) { + if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) { + struct skb_shared_hwtstamps shhwtstamps; + struct timespec64 ts; + + rtsn_get_timestamp(priv, &ts); + memset(&shhwtstamps, 0, sizeof(shhwtstamps)); + shhwtstamps.hwtstamp = timespec64_to_ktime(ts); + skb_tstamp_tx(skb, &shhwtstamps); + } + dma_unmap_single(ndev->dev.parent, + le32_to_cpu(desc->dptr), + size, DMA_TO_DEVICE); + dev_kfree_skb_any(priv->tx_skb[entry]); + free_num++; + + priv->stats.tx_packets++; + priv->stats.tx_bytes += size; + } + + desc->die_dt = DT_EEMPTY; + } + + desc = &priv->tx_ring[priv->num_tx_ring]; + desc->die_dt = DT_LINK; + + return free_num; +} + +static int rtsn_rx(struct net_device *ndev, int budget) +{ + struct rtsn_private *priv = netdev_priv(ndev); + unsigned int ndescriptors; + unsigned int rx_packets; + unsigned int i; + bool get_ts; + + get_ts = priv->ptp_priv->tstamp_rx_ctrl & + RCAR_GEN4_RXTSTAMP_TYPE_V2_L2_EVENT; + + ndescriptors = priv->dirty_rx + priv->num_rx_ring - priv->cur_rx; + rx_packets = 0; + for (i = 0; i < ndescriptors; i++) { + const unsigned int entry = priv->cur_rx % priv->num_rx_ring; + struct rtsn_ext_ts_desc *desc = &priv->rx_ring[entry]; + struct sk_buff *skb; + dma_addr_t dma_addr; + u16 pkt_len; + + /* Stop processing descriptors if budget is consumed. */ + if (rx_packets >= budget) + break; + + /* Stop processing descriptors on first empty. */ + if ((desc->die_dt & DT_MASK) == DT_FEMPTY) + break; + + dma_rmb(); + pkt_len = le16_to_cpu(desc->info_ds) & RX_DS; + + skb = priv->rx_skb[entry]; + priv->rx_skb[entry] = NULL; + dma_addr = le32_to_cpu(desc->dptr); + dma_unmap_single(ndev->dev.parent, dma_addr, PKT_BUF_SZ, + DMA_FROM_DEVICE); + + /* Get timestamp if enabled. */ + if (get_ts) { + struct skb_shared_hwtstamps *shhwtstamps; + struct timespec64 ts; + + shhwtstamps = skb_hwtstamps(skb); + memset(shhwtstamps, 0, sizeof(*shhwtstamps)); + + ts.tv_sec = (u64)le32_to_cpu(desc->ts_sec); + ts.tv_nsec = le32_to_cpu(desc->ts_nsec & cpu_to_le32(0x3fffffff)); + + shhwtstamps->hwtstamp = timespec64_to_ktime(ts); + } + + skb_put(skb, pkt_len); + skb->protocol = eth_type_trans(skb, ndev); + napi_gro_receive(&priv->napi, skb); + + /* Update statistics. */ + priv->stats.rx_packets++; + priv->stats.rx_bytes += pkt_len; + + /* Update counters. */ + priv->cur_rx++; + rx_packets++; + } + + /* Refill the RX ring buffers */ + for (; priv->cur_rx - priv->dirty_rx > 0; priv->dirty_rx++) { + const unsigned int entry = priv->dirty_rx % priv->num_rx_ring; + struct rtsn_ext_ts_desc *desc = &priv->rx_ring[entry]; + struct sk_buff *skb; + dma_addr_t dma_addr; + + desc->info_ds = cpu_to_le16(PKT_BUF_SZ); + + if (!priv->rx_skb[entry]) { + skb = napi_alloc_skb(&priv->napi, + PKT_BUF_SZ + RTSN_ALIGN - 1); + if (!skb) + break; + skb_reserve(skb, NET_IP_ALIGN); + dma_addr = dma_map_single(ndev->dev.parent, skb->data, + le16_to_cpu(desc->info_ds), + DMA_FROM_DEVICE); + if (dma_mapping_error(ndev->dev.parent, dma_addr)) + desc->info_ds = cpu_to_le16(0); + desc->dptr = cpu_to_le32(dma_addr); + skb_checksum_none_assert(skb); + priv->rx_skb[entry] = skb; + } + + dma_wmb(); + desc->die_dt = DT_FEMPTY | D_DIE; + } + + priv->rx_ring[priv->num_rx_ring].die_dt = DT_LINK; + + return rx_packets; +} + +static int rtsn_poll(struct napi_struct *napi, int budget) +{ + struct rtsn_private *priv; + struct net_device *ndev; + unsigned long flags; + int work_done; + + ndev = napi->dev; + priv = netdev_priv(ndev); + + /* Processing RX Descriptor Ring */ + work_done = rtsn_rx(ndev, budget); + + /* Processing TX Descriptor Ring */ + spin_lock_irqsave(&priv->lock, flags); + rtsn_tx_free(ndev, true); + netif_wake_subqueue(ndev, 0); + spin_unlock_irqrestore(&priv->lock, flags); + + /* Re-enable TX/RX interrupts */ + if (work_done < budget && napi_complete_done(napi, work_done)) { + spin_lock_irqsave(&priv->lock, flags); + rtsn_ctrl_data_irq(priv, true); + spin_unlock_irqrestore(&priv->lock, flags); + } + + return work_done; +} + +static int rtsn_desc_alloc(struct rtsn_private *priv) +{ + struct device *dev = &priv->pdev->dev; + unsigned int i; + + priv->tx_desc_bat_size = sizeof(struct rtsn_desc) * TX_NUM_CHAINS; + priv->tx_desc_bat = dma_alloc_coherent(dev, priv->tx_desc_bat_size, + &priv->tx_desc_bat_dma, + GFP_KERNEL); + + if (!priv->tx_desc_bat) + return -ENOMEM; + + for (i = 0; i < TX_NUM_CHAINS; i++) + priv->tx_desc_bat[i].die_dt = DT_EOS; + + priv->rx_desc_bat_size = sizeof(struct rtsn_desc) * RX_NUM_CHAINS; + priv->rx_desc_bat = dma_alloc_coherent(dev, priv->rx_desc_bat_size, + &priv->rx_desc_bat_dma, + GFP_KERNEL); + + if (!priv->rx_desc_bat) + return -ENOMEM; + + for (i = 0; i < RX_NUM_CHAINS; i++) + priv->rx_desc_bat[i].die_dt = DT_EOS; + + return 0; +} + +static void rtsn_desc_free(struct rtsn_private *priv) +{ + if (priv->tx_desc_bat) + dma_free_coherent(&priv->pdev->dev, priv->tx_desc_bat_size, + priv->tx_desc_bat, priv->tx_desc_bat_dma); + priv->tx_desc_bat = NULL; + + if (priv->rx_desc_bat) + dma_free_coherent(&priv->pdev->dev, priv->rx_desc_bat_size, + priv->rx_desc_bat, priv->rx_desc_bat_dma); + priv->rx_desc_bat = NULL; +} + +static void rtsn_chain_free(struct rtsn_private *priv) +{ + struct device *dev = &priv->pdev->dev; + + dma_free_coherent(dev, + sizeof(struct rtsn_ext_desc) * (priv->num_tx_ring + 1), + priv->tx_ring, priv->tx_desc_dma); + priv->tx_ring = NULL; + + dma_free_coherent(dev, + sizeof(struct rtsn_ext_ts_desc) * (priv->num_rx_ring + 1), + priv->rx_ring, priv->rx_desc_dma); + priv->rx_ring = NULL; + + kfree(priv->tx_skb); + priv->tx_skb = NULL; + + kfree(priv->rx_skb); + priv->rx_skb = NULL; +} + +static int rtsn_chain_init(struct rtsn_private *priv, int tx_size, int rx_size) +{ + struct net_device *ndev = priv->ndev; + struct sk_buff *skb; + int i; + + priv->num_tx_ring = tx_size; + priv->num_rx_ring = rx_size; + + priv->tx_skb = kcalloc(tx_size, sizeof(*priv->tx_skb), GFP_KERNEL); + priv->rx_skb = kcalloc(rx_size, sizeof(*priv->rx_skb), GFP_KERNEL); + + if (!priv->rx_skb || !priv->tx_skb) + goto error; + + for (i = 0; i < rx_size; i++) { + skb = netdev_alloc_skb(ndev, PKT_BUF_SZ + RTSN_ALIGN - 1); + if (!skb) + goto error; + skb_reserve(skb, NET_IP_ALIGN); + priv->rx_skb[i] = skb; + } + + /* Allocate TX, RX descriptors */ + priv->tx_ring = dma_alloc_coherent(ndev->dev.parent, + sizeof(struct rtsn_ext_desc) * (tx_size + 1), + &priv->tx_desc_dma, GFP_KERNEL); + priv->rx_ring = dma_alloc_coherent(ndev->dev.parent, + sizeof(struct rtsn_ext_ts_desc) * (rx_size + 1), + &priv->rx_desc_dma, GFP_KERNEL); + + if (!priv->tx_ring || !priv->rx_ring) + goto error; + + return 0; +error: + rtsn_chain_free(priv); + + return -ENOMEM; +} + +static void rtsn_chain_format(struct rtsn_private *priv) +{ + struct net_device *ndev = priv->ndev; + struct rtsn_ext_ts_desc *rx_desc; + struct rtsn_ext_desc *tx_desc; + struct rtsn_desc *bat_desc; + dma_addr_t dma_addr; + unsigned int i; + + priv->cur_tx = 0; + priv->cur_rx = 0; + priv->dirty_rx = 0; + priv->dirty_tx = 0; + + /* TX */ + memset(priv->tx_ring, 0, sizeof(*tx_desc) * priv->num_tx_ring); + for (i = 0, tx_desc = priv->tx_ring; i < priv->num_tx_ring; i++, tx_desc++) + tx_desc->die_dt = DT_EEMPTY | D_DIE; + + tx_desc->dptr = cpu_to_le32((u32)priv->tx_desc_dma); + tx_desc->die_dt = DT_LINK; + + bat_desc = &priv->tx_desc_bat[TX_CHAIN_IDX]; + bat_desc->die_dt = DT_LINK; + bat_desc->dptr = cpu_to_le32((u32)priv->tx_desc_dma); + + /* RX */ + memset(priv->rx_ring, 0, sizeof(*rx_desc) * priv->num_rx_ring); + for (i = 0, rx_desc = priv->rx_ring; i < priv->num_rx_ring; i++, rx_desc++) { + dma_addr = dma_map_single(ndev->dev.parent, + priv->rx_skb[i]->data, PKT_BUF_SZ, + DMA_FROM_DEVICE); + if (!dma_mapping_error(ndev->dev.parent, dma_addr)) + rx_desc->info_ds = cpu_to_le16(PKT_BUF_SZ); + rx_desc->dptr = cpu_to_le32((u32)dma_addr); + rx_desc->die_dt = DT_FEMPTY | D_DIE; + } + rx_desc->dptr = cpu_to_le32((u32)priv->rx_desc_dma); + rx_desc->die_dt = DT_LINK; + + bat_desc = &priv->rx_desc_bat[RX_CHAIN_IDX]; + bat_desc->die_dt = DT_LINK; + bat_desc->dptr = cpu_to_le32((u32)priv->rx_desc_dma); +} + +static int rtsn_dmac_init(struct rtsn_private *priv) +{ + int ret; + + ret = rtsn_chain_init(priv, TX_CHAIN_SIZE, RX_CHAIN_SIZE); + if (ret) + return ret; + + rtsn_chain_format(priv); + + return 0; +} + +static enum rtsn_mode rtsn_read_mode(struct rtsn_private *priv) +{ + return (rtsn_read(priv, OSR) & OSR_OPS) >> 1; +} + +static int rtsn_wait_mode(struct rtsn_private *priv, enum rtsn_mode mode) +{ + unsigned int i; + + /* Need to busy loop as mode changes can happen in atomic context. */ + for (i = 0; i < RTSN_TIMEOUT_US / RTSN_INTERVAL_US; i++) { + if (rtsn_read_mode(priv) == mode) + return 0; + + udelay(RTSN_INTERVAL_US); + } + + return -ETIMEDOUT; +} + +static int rtsn_change_mode(struct rtsn_private *priv, enum rtsn_mode mode) +{ + int ret; + + rtsn_write(priv, OCR, mode); + ret = rtsn_wait_mode(priv, mode); + if (ret) + netdev_err(priv->ndev, "Failed to switch operation mode\n"); + return ret; +} + +static int rtsn_get_data_irq_status(struct rtsn_private *priv) +{ + u32 val; + + val = rtsn_read(priv, TDIS0) | TDIS_TDS(TX_CHAIN_IDX); + val |= rtsn_read(priv, RDIS0) | RDIS_RDS(RX_CHAIN_IDX); + + return val; +} + +static irqreturn_t rtsn_irq(int irq, void *dev_id) +{ + struct rtsn_private *priv = dev_id; + int ret = IRQ_NONE; + + spin_lock(&priv->lock); + + if (rtsn_get_data_irq_status(priv)) { + /* Clear TX/RX irq status */ + rtsn_write(priv, TDIS0, TDIS_TDS(TX_CHAIN_IDX)); + rtsn_write(priv, RDIS0, RDIS_RDS(RX_CHAIN_IDX)); + + if (napi_schedule_prep(&priv->napi)) { + /* Disable TX/RX interrupts */ + rtsn_ctrl_data_irq(priv, false); + + __napi_schedule(&priv->napi); + } + + ret = IRQ_HANDLED; + } + + spin_unlock(&priv->lock); + + return ret; +} + +static int rtsn_request_irq(unsigned int irq, irq_handler_t handler, + unsigned long flags, struct rtsn_private *priv, + const char *ch) +{ + char *name; + int ret; + + name = devm_kasprintf(&priv->pdev->dev, GFP_KERNEL, "%s:%s", + priv->ndev->name, ch); + if (!name) + return -ENOMEM; + + ret = request_irq(irq, handler, flags, name, priv); + if (ret) + netdev_err(priv->ndev, "Cannot request IRQ %s\n", name); + + return ret; +} + +static void rtsn_free_irqs(struct rtsn_private *priv) +{ + free_irq(priv->tx_data_irq, priv); + free_irq(priv->rx_data_irq, priv); +} + +static int rtsn_request_irqs(struct rtsn_private *priv) +{ + int ret; + + priv->rx_data_irq = platform_get_irq_byname(priv->pdev, "rx"); + if (priv->rx_data_irq < 0) + return priv->rx_data_irq; + + priv->tx_data_irq = platform_get_irq_byname(priv->pdev, "tx"); + if (priv->tx_data_irq < 0) + return priv->tx_data_irq; + + ret = rtsn_request_irq(priv->tx_data_irq, rtsn_irq, 0, priv, "tx"); + if (ret) + return ret; + + ret = rtsn_request_irq(priv->rx_data_irq, rtsn_irq, 0, priv, "rx"); + if (ret) { + free_irq(priv->tx_data_irq, priv); + return ret; + } + + return 0; +} + +static int rtsn_reset(struct rtsn_private *priv) +{ + reset_control_reset(priv->reset); + mdelay(1); + + return rtsn_wait_mode(priv, OCR_OPC_DISABLE); +} + +static int rtsn_axibmi_init(struct rtsn_private *priv) +{ + int ret; + + ret = rtsn_reg_wait(priv, RR, RR_RST, RR_RST_COMPLETE); + if (ret) + return ret; + + /* Set AXIWC */ + rtsn_write(priv, AXIWC, AXIWC_DEFAULT); + + /* Set AXIRC */ + rtsn_write(priv, AXIRC, AXIRC_DEFAULT); + + /* TX Descriptor chain setting */ + rtsn_write(priv, TATLS0, TATLS0_TEDE | TATLS0_TATEN(TX_CHAIN_IDX)); + rtsn_write(priv, TATLS1, priv->tx_desc_bat_dma + TX_CHAIN_ADDR_OFFSET); + rtsn_write(priv, TATLR, TATLR_TATL); + + ret = rtsn_reg_wait(priv, TATLR, TATLR_TATL, 0); + if (ret) + return ret; + + /* RX Descriptor chain setting */ + rtsn_write(priv, RATLS0, + RATLS0_RETS | RATLS0_REDE | RATLS0_RATEN(RX_CHAIN_IDX)); + rtsn_write(priv, RATLS1, priv->rx_desc_bat_dma + RX_CHAIN_ADDR_OFFSET); + rtsn_write(priv, RATLR, RATLR_RATL); + + ret = rtsn_reg_wait(priv, RATLR, RATLR_RATL, 0); + if (ret) + return ret; + + /* Enable TX/RX interrupts */ + rtsn_ctrl_data_irq(priv, true); + + return 0; +} + +static void rtsn_mhd_init(struct rtsn_private *priv) +{ + /* TX General setting */ + rtsn_write(priv, TGC1, TGC1_STTV_DEFAULT | TGC1_TQTM_SFM); + rtsn_write(priv, TMS0, TMS_MFS_MAX); + + /* RX Filter IP */ + rtsn_write(priv, CFCR0, CFCR_SDID(RX_CHAIN_IDX)); + rtsn_write(priv, FMSCR, FMSCR_FMSIE(RX_CHAIN_IDX)); +} + +static int rtsn_get_phy_params(struct rtsn_private *priv) +{ + int ret; + + ret = of_get_phy_mode(priv->pdev->dev.of_node, &priv->iface); + if (ret) + return ret; + + switch (priv->iface) { + case PHY_INTERFACE_MODE_MII: + priv->speed = 100; + break; + case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_RXID: + case PHY_INTERFACE_MODE_RGMII_TXID: + priv->speed = 1000; + break; + default: + return -EOPNOTSUPP; + } + + return 0; +} + +static void rtsn_set_phy_interface(struct rtsn_private *priv) +{ + u32 val; + + switch (priv->iface) { + case PHY_INTERFACE_MODE_MII: + val = MPIC_PIS_MII; + break; + case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_RXID: + case PHY_INTERFACE_MODE_RGMII_TXID: + val = MPIC_PIS_GMII; + break; + default: + return; + } + + rtsn_modify(priv, MPIC, MPIC_PIS_MASK, val); +} + +static void rtsn_set_rate(struct rtsn_private *priv) +{ + u32 val; + + switch (priv->speed) { + case 10: + val = MPIC_LSC_10M; + break; + case 100: + val = MPIC_LSC_100M; + break; + case 1000: + val = MPIC_LSC_1G; + break; + default: + return; + } + + rtsn_modify(priv, MPIC, MPIC_LSC_MASK, val); +} + +static int rtsn_rmac_init(struct rtsn_private *priv) +{ + const u8 *mac_addr = priv->ndev->dev_addr; + int ret; + + /* Set MAC address */ + rtsn_write(priv, MRMAC0, (mac_addr[0] << 8) | mac_addr[1]); + rtsn_write(priv, MRMAC1, (mac_addr[2] << 24) | (mac_addr[3] << 16) | + (mac_addr[4] << 8) | mac_addr[5]); + + /* Set xMII type */ + rtsn_set_phy_interface(priv); + rtsn_set_rate(priv); + + /* Enable MII */ + rtsn_modify(priv, MPIC, MPIC_PSMCS_MASK | MPIC_PSMHT_MASK, + MPIC_PSMCS_DEFAULT | MPIC_PSMHT_DEFAULT); + + /* Link verification */ + rtsn_modify(priv, MLVC, MLVC_PLV, MLVC_PLV); + ret = rtsn_reg_wait(priv, MLVC, MLVC_PLV, 0); + if (ret) + return ret; + + return ret; +} + +static int rtsn_hw_init(struct rtsn_private *priv) +{ + int ret; + + ret = rtsn_reset(priv); + if (ret) + return ret; + + /* Change to CONFIG mode */ + ret = rtsn_change_mode(priv, OCR_OPC_CONFIG); + if (ret) + return ret; + + ret = rtsn_axibmi_init(priv); + if (ret) + return ret; + + rtsn_mhd_init(priv); + + ret = rtsn_rmac_init(priv); + if (ret) + return ret; + + ret = rtsn_change_mode(priv, OCR_OPC_DISABLE); + if (ret) + return ret; + + /* Change to OPERATION mode */ + ret = rtsn_change_mode(priv, OCR_OPC_OPERATION); + + return ret; +} + +static int rtsn_mii_access(struct mii_bus *bus, bool read, int phyad, + int regad, u16 data) +{ + struct rtsn_private *priv = bus->priv; + u32 val; + int ret; + + val = MPSM_PDA(phyad) | MPSM_PRA(regad) | MPSM_PSME; + + if (!read) + val |= MPSM_PSMAD | MPSM_PRD_SET(data); + + rtsn_write(priv, MPSM, val); + + ret = rtsn_reg_wait(priv, MPSM, MPSM_PSME, 0); + if (ret) + return ret; + + if (read) + ret = MPSM_PRD_GET(rtsn_read(priv, MPSM)); + + return ret; +} + +static int rtsn_mii_read(struct mii_bus *bus, int addr, int regnum) +{ + return rtsn_mii_access(bus, true, addr, regnum, 0); +} + +static int rtsn_mii_write(struct mii_bus *bus, int addr, int regnum, u16 val) +{ + return rtsn_mii_access(bus, false, addr, regnum, val); +} + +static int rtsn_mdio_alloc(struct rtsn_private *priv) +{ + struct platform_device *pdev = priv->pdev; + struct device *dev = &pdev->dev; + struct device_node *mdio_node; + struct mii_bus *mii; + int ret; + + mii = mdiobus_alloc(); + if (!mii) + return -ENOMEM; + + mdio_node = of_get_child_by_name(dev->of_node, "mdio"); + if (!mdio_node) { + ret = -ENODEV; + goto out_free_bus; + } + + /* Enter config mode before registering the MDIO bus */ + ret = rtsn_reset(priv); + if (ret) + goto out_free_bus; + + ret = rtsn_change_mode(priv, OCR_OPC_CONFIG); + if (ret) + goto out_free_bus; + + rtsn_modify(priv, MPIC, MPIC_PSMCS_MASK | MPIC_PSMHT_MASK, + MPIC_PSMCS_DEFAULT | MPIC_PSMHT_DEFAULT); + + /* Register the MDIO bus */ + mii->name = "rtsn_mii"; + snprintf(mii->id, MII_BUS_ID_SIZE, "%s-%x", + pdev->name, pdev->id); + mii->priv = priv; + mii->read = rtsn_mii_read; + mii->write = rtsn_mii_write; + mii->parent = dev; + + ret = of_mdiobus_register(mii, mdio_node); + of_node_put(mdio_node); + if (ret) + goto out_free_bus; + + priv->mii = mii; + + return 0; + +out_free_bus: + mdiobus_free(mii); + return ret; +} + +static void rtsn_mdio_free(struct rtsn_private *priv) +{ + mdiobus_unregister(priv->mii); + mdiobus_free(priv->mii); + priv->mii = NULL; +} + +static void rtsn_adjust_link(struct net_device *ndev) +{ + struct rtsn_private *priv = netdev_priv(ndev); + struct phy_device *phydev = ndev->phydev; + bool new_state = false; + unsigned long flags; + + spin_lock_irqsave(&priv->lock, flags); + + if (phydev->link) { + if (phydev->speed != priv->speed) { + new_state = true; + priv->speed = phydev->speed; + } + + if (!priv->link) { + new_state = true; + priv->link = phydev->link; + } + } else if (priv->link) { + new_state = true; + priv->link = 0; + priv->speed = 0; + } + + if (new_state) { + /* Need to transition to CONFIG mode before reconfiguring and + * then back to the original mode. Any state change to/from + * CONFIG or OPERATION must go over DISABLED to stop Rx/Tx. + */ + enum rtsn_mode orgmode = rtsn_read_mode(priv); + + /* Transit to CONFIG */ + if (orgmode != OCR_OPC_CONFIG) { + if (orgmode != OCR_OPC_DISABLE && + rtsn_change_mode(priv, OCR_OPC_DISABLE)) + goto out; + if (rtsn_change_mode(priv, OCR_OPC_CONFIG)) + goto out; + } + + rtsn_set_rate(priv); + + /* Transition to original mode */ + if (orgmode != OCR_OPC_CONFIG) { + if (rtsn_change_mode(priv, OCR_OPC_DISABLE)) + goto out; + if (orgmode != OCR_OPC_DISABLE && + rtsn_change_mode(priv, orgmode)) + goto out; + } + } +out: + spin_unlock_irqrestore(&priv->lock, flags); + + if (new_state) + phy_print_status(phydev); +} + +static int rtsn_phy_init(struct rtsn_private *priv) +{ + struct device_node *np = priv->ndev->dev.parent->of_node; + struct phy_device *phydev; + struct device_node *phy; + + priv->link = 0; + + phy = of_parse_phandle(np, "phy-handle", 0); + if (!phy) + return -ENOENT; + + phydev = of_phy_connect(priv->ndev, phy, rtsn_adjust_link, 0, + priv->iface); + of_node_put(phy); + if (!phydev) + return -ENOENT; + + /* Only support full-duplex mode */ + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_10baseT_Half_BIT); + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_100baseT_Half_BIT); + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_1000baseT_Half_BIT); + + phy_attached_info(phydev); + + return 0; +} + +static void rtsn_phy_deinit(struct rtsn_private *priv) +{ + phy_disconnect(priv->ndev->phydev); + priv->ndev->phydev = NULL; +} + +static int rtsn_init(struct rtsn_private *priv) +{ + int ret; + + ret = rtsn_desc_alloc(priv); + if (ret) + return ret; + + ret = rtsn_dmac_init(priv); + if (ret) + goto error_free_desc; + + ret = rtsn_hw_init(priv); + if (ret) + goto error_free_chain; + + ret = rtsn_phy_init(priv); + if (ret) + goto error_free_chain; + + ret = rtsn_request_irqs(priv); + if (ret) + goto error_free_phy; + + return 0; +error_free_phy: + rtsn_phy_deinit(priv); +error_free_chain: + rtsn_chain_free(priv); +error_free_desc: + rtsn_desc_free(priv); + return ret; +} + +static void rtsn_deinit(struct rtsn_private *priv) +{ + rtsn_free_irqs(priv); + rtsn_phy_deinit(priv); + rtsn_chain_free(priv); + rtsn_desc_free(priv); +} + +static void rtsn_parse_mac_address(struct device_node *np, + struct net_device *ndev) +{ + struct rtsn_private *priv = netdev_priv(ndev); + u8 addr[ETH_ALEN]; + u32 mrmac0; + u32 mrmac1; + + /* Try to read address from Device Tree. */ + if (!of_get_mac_address(np, addr)) { + eth_hw_addr_set(ndev, addr); + return; + } + + /* Try to read address from device. */ + mrmac0 = rtsn_read(priv, MRMAC0); + mrmac1 = rtsn_read(priv, MRMAC1); + + addr[0] = (mrmac0 >> 8) & 0xff; + addr[1] = (mrmac0 >> 0) & 0xff; + addr[2] = (mrmac1 >> 24) & 0xff; + addr[3] = (mrmac1 >> 16) & 0xff; + addr[4] = (mrmac1 >> 8) & 0xff; + addr[5] = (mrmac1 >> 0) & 0xff; + + if (is_valid_ether_addr(addr)) { + eth_hw_addr_set(ndev, addr); + return; + } + + /* Fallback to a random address */ + eth_hw_addr_random(ndev); +} + +static int rtsn_open(struct net_device *ndev) +{ + struct rtsn_private *priv = netdev_priv(ndev); + int ret; + + napi_enable(&priv->napi); + + ret = rtsn_init(priv); + if (ret) { + napi_disable(&priv->napi); + return ret; + } + + phy_start(ndev->phydev); + + netif_start_queue(ndev); + + return 0; +} + +static int rtsn_stop(struct net_device *ndev) +{ + struct rtsn_private *priv = netdev_priv(ndev); + + phy_stop(priv->ndev->phydev); + napi_disable(&priv->napi); + rtsn_change_mode(priv, OCR_OPC_DISABLE); + rtsn_deinit(priv); + + return 0; +} + +static netdev_tx_t rtsn_start_xmit(struct sk_buff *skb, struct net_device *ndev) +{ + struct rtsn_private *priv = netdev_priv(ndev); + struct rtsn_ext_desc *desc; + int ret = NETDEV_TX_OK; + unsigned long flags; + dma_addr_t dma_addr; + int entry; + + spin_lock_irqsave(&priv->lock, flags); + + /* Drop packet if it won't fit in a single descriptor. */ + if (skb->len >= TX_DS) { + priv->stats.tx_dropped++; + priv->stats.tx_errors++; + goto out; + } + + if (priv->cur_tx - priv->dirty_tx > priv->num_tx_ring) { + netif_stop_subqueue(ndev, 0); + ret = NETDEV_TX_BUSY; + goto out; + } + + if (skb_put_padto(skb, ETH_ZLEN)) + goto out; + + dma_addr = dma_map_single(ndev->dev.parent, skb->data, skb->len, + DMA_TO_DEVICE); + if (dma_mapping_error(ndev->dev.parent, dma_addr)) { + dev_kfree_skb_any(skb); + goto out; + } + + entry = priv->cur_tx % priv->num_tx_ring; + priv->tx_skb[entry] = skb; + desc = &priv->tx_ring[entry]; + desc->dptr = cpu_to_le32(dma_addr); + desc->info_ds = cpu_to_le16(skb->len); + desc->info1 = cpu_to_le64(skb->len); + + if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) { + skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; + priv->ts_tag++; + desc->info_ds |= cpu_to_le16(TXC); + desc->info = priv->ts_tag; + } + + skb_tx_timestamp(skb); + dma_wmb(); + + desc->die_dt = DT_FSINGLE | D_DIE; + priv->cur_tx++; + + /* Start xmit */ + rtsn_write(priv, TRCR0, BIT(TX_CHAIN_IDX)); +out: + spin_unlock_irqrestore(&priv->lock, flags); + return ret; +} + +static void rtsn_get_stats64(struct net_device *ndev, + struct rtnl_link_stats64 *storage) +{ + struct rtsn_private *priv = netdev_priv(ndev); + *storage = priv->stats; +} + +static int rtsn_do_ioctl(struct net_device *ndev, struct ifreq *ifr, int cmd) +{ + if (!netif_running(ndev)) + return -ENODEV; + + return phy_do_ioctl_running(ndev, ifr, cmd); +} + +static int rtsn_hwtstamp_get(struct net_device *ndev, + struct kernel_hwtstamp_config *config) +{ + struct rcar_gen4_ptp_private *ptp_priv; + struct rtsn_private *priv; + + if (!netif_running(ndev)) + return -ENODEV; + + priv = netdev_priv(ndev); + ptp_priv = priv->ptp_priv; + + config->flags = 0; + + config->tx_type = + ptp_priv->tstamp_tx_ctrl ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF; + + switch (ptp_priv->tstamp_rx_ctrl & RCAR_GEN4_RXTSTAMP_TYPE) { + case RCAR_GEN4_RXTSTAMP_TYPE_V2_L2_EVENT: + config->rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT; + break; + case RCAR_GEN4_RXTSTAMP_TYPE_ALL: + config->rx_filter = HWTSTAMP_FILTER_ALL; + break; + default: + config->rx_filter = HWTSTAMP_FILTER_NONE; + break; + } + + return 0; +} + +static int rtsn_hwtstamp_set(struct net_device *ndev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) +{ + struct rcar_gen4_ptp_private *ptp_priv; + struct rtsn_private *priv; + u32 tstamp_rx_ctrl; + u32 tstamp_tx_ctrl; + + if (!netif_running(ndev)) + return -ENODEV; + + priv = netdev_priv(ndev); + ptp_priv = priv->ptp_priv; + + if (config->flags) + return -EINVAL; + + switch (config->tx_type) { + case HWTSTAMP_TX_OFF: + tstamp_tx_ctrl = 0; + break; + case HWTSTAMP_TX_ON: + tstamp_tx_ctrl = RCAR_GEN4_TXTSTAMP_ENABLED; + break; + default: + return -ERANGE; + } + + switch (config->rx_filter) { + case HWTSTAMP_FILTER_NONE: + tstamp_rx_ctrl = 0; + break; + case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: + tstamp_rx_ctrl = RCAR_GEN4_RXTSTAMP_ENABLED | + RCAR_GEN4_RXTSTAMP_TYPE_V2_L2_EVENT; + break; + default: + config->rx_filter = HWTSTAMP_FILTER_ALL; + tstamp_rx_ctrl = RCAR_GEN4_RXTSTAMP_ENABLED | + RCAR_GEN4_RXTSTAMP_TYPE_ALL; + break; + } + + ptp_priv->tstamp_tx_ctrl = tstamp_tx_ctrl; + ptp_priv->tstamp_rx_ctrl = tstamp_rx_ctrl; + + return 0; +} + +static const struct net_device_ops rtsn_netdev_ops = { + .ndo_open = rtsn_open, + .ndo_stop = rtsn_stop, + .ndo_start_xmit = rtsn_start_xmit, + .ndo_get_stats64 = rtsn_get_stats64, + .ndo_eth_ioctl = rtsn_do_ioctl, + .ndo_validate_addr = eth_validate_addr, + .ndo_set_mac_address = eth_mac_addr, + .ndo_hwtstamp_set = rtsn_hwtstamp_set, + .ndo_hwtstamp_get = rtsn_hwtstamp_get, +}; + +static int rtsn_get_ts_info(struct net_device *ndev, + struct ethtool_ts_info *info) +{ + struct rtsn_private *priv = netdev_priv(ndev); + + info->phc_index = ptp_clock_index(priv->ptp_priv->clock); + info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_RX_SOFTWARE | + SOF_TIMESTAMPING_SOFTWARE | + SOF_TIMESTAMPING_TX_HARDWARE | + SOF_TIMESTAMPING_RX_HARDWARE | + SOF_TIMESTAMPING_RAW_HARDWARE; + info->tx_types = BIT(HWTSTAMP_TX_OFF) | BIT(HWTSTAMP_TX_ON); + info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) | BIT(HWTSTAMP_FILTER_ALL); + + return 0; +} + +static const struct ethtool_ops rtsn_ethtool_ops = { + .nway_reset = phy_ethtool_nway_reset, + .get_link = ethtool_op_get_link, + .get_ts_info = rtsn_get_ts_info, + .get_link_ksettings = phy_ethtool_get_link_ksettings, + .set_link_ksettings = phy_ethtool_set_link_ksettings, +}; + +static const struct of_device_id rtsn_match_table[] = { + { .compatible = "renesas,r8a779g0-ethertsn", }, + { /* Sentinel */ } +}; + +MODULE_DEVICE_TABLE(of, rtsn_match_table); + +static int rtsn_probe(struct platform_device *pdev) +{ + struct rtsn_private *priv; + struct net_device *ndev; + struct resource *res; + int ret; + + ndev = alloc_etherdev_mqs(sizeof(struct rtsn_private), TX_NUM_CHAINS, + RX_NUM_CHAINS); + if (!ndev) + return -ENOMEM; + + priv = netdev_priv(ndev); + priv->pdev = pdev; + priv->ndev = ndev; + priv->ptp_priv = rcar_gen4_ptp_alloc(pdev); + + spin_lock_init(&priv->lock); + platform_set_drvdata(pdev, priv); + + priv->clk = devm_clk_get(&pdev->dev, NULL); + if (IS_ERR(priv->clk)) { + ret = PTR_ERR(priv->clk); + goto error_free; + } + + priv->reset = devm_reset_control_get(&pdev->dev, NULL); + if (IS_ERR(priv->reset)) { + ret = PTR_ERR(priv->reset); + goto error_free; + } + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "tsnes"); + if (!res) { + dev_err(&pdev->dev, "Can't find tsnes resource\n"); + ret = -EINVAL; + goto error_free; + } + + priv->base = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(priv->base)) { + ret = PTR_ERR(priv->base); + goto error_free; + } + + SET_NETDEV_DEV(ndev, &pdev->dev); + + ndev->features = NETIF_F_RXCSUM; + ndev->hw_features = NETIF_F_RXCSUM; + ndev->base_addr = res->start; + ndev->netdev_ops = &rtsn_netdev_ops; + ndev->ethtool_ops = &rtsn_ethtool_ops; + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "gptp"); + if (!res) { + dev_err(&pdev->dev, "Can't find gptp resource\n"); + ret = -EINVAL; + goto error_free; + } + + priv->ptp_priv->addr = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(priv->ptp_priv->addr)) { + ret = PTR_ERR(priv->ptp_priv->addr); + goto error_free; + } + + ret = rtsn_get_phy_params(priv); + if (ret) + goto error_free; + + pm_runtime_enable(&pdev->dev); + pm_runtime_get_sync(&pdev->dev); + + netif_napi_add(ndev, &priv->napi, rtsn_poll); + + rtsn_parse_mac_address(pdev->dev.of_node, ndev); + + dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + + device_set_wakeup_capable(&pdev->dev, 1); + + ret = rcar_gen4_ptp_register(priv->ptp_priv, RCAR_GEN4_PTP_REG_LAYOUT, + clk_get_rate(priv->clk)); + if (ret) + goto error_pm; + + ret = rtsn_mdio_alloc(priv); + if (ret) + goto error_ptp; + + ret = register_netdev(ndev); + if (ret) + goto error_mdio; + + netdev_info(ndev, "MAC address %pM\n", ndev->dev_addr); + + return 0; + +error_mdio: + rtsn_mdio_free(priv); +error_ptp: + rcar_gen4_ptp_unregister(priv->ptp_priv); +error_pm: + netif_napi_del(&priv->napi); + rtsn_change_mode(priv, OCR_OPC_DISABLE); + pm_runtime_put_sync(&pdev->dev); + pm_runtime_disable(&pdev->dev); +error_free: + free_netdev(ndev); + + return ret; +} + +static int rtsn_remove(struct platform_device *pdev) +{ + struct rtsn_private *priv = platform_get_drvdata(pdev); + + unregister_netdev(priv->ndev); + rtsn_mdio_free(priv); + rcar_gen4_ptp_unregister(priv->ptp_priv); + rtsn_change_mode(priv, OCR_OPC_DISABLE); + netif_napi_del(&priv->napi); + + pm_runtime_put_sync(&pdev->dev); + pm_runtime_disable(&pdev->dev); + + free_netdev(priv->ndev); + + return 0; +} + +static struct platform_driver rtsn_driver = { + .probe = rtsn_probe, + .remove = rtsn_remove, + .driver = { + .name = "rtsn", + .of_match_table = rtsn_match_table, + } +}; +module_platform_driver(rtsn_driver); + +MODULE_AUTHOR("Phong Hoang, Niklas Söderlund"); +MODULE_DESCRIPTION("Renesas Ethernet-TSN device driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/renesas/rtsn.h b/drivers/net/ethernet/renesas/rtsn.h new file mode 100644 index 000000000000..3183e80d7e6b --- /dev/null +++ b/drivers/net/ethernet/renesas/rtsn.h @@ -0,0 +1,464 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* Renesas Ethernet-TSN device driver + * + * Copyright (C) 2022 Renesas Electronics Corporation + * Copyright (C) 2023 Niklas Söderlund <[email protected]> + */ + +#ifndef __RTSN_H__ +#define __RTSN_H__ + +#include <linux/types.h> + +#define AXIBMI 0x0000 +#define TSNMHD 0x1000 +#define RMSO 0x2000 +#define RMRO 0x3800 + +enum rtsn_reg { + AXIWC = AXIBMI + 0x0000, + AXIRC = AXIBMI + 0x0004, + TDPC0 = AXIBMI + 0x0010, + TFT = AXIBMI + 0x0090, + TATLS0 = AXIBMI + 0x00a0, + TATLS1 = AXIBMI + 0x00a4, + TATLR = AXIBMI + 0x00a8, + RATLS0 = AXIBMI + 0x00b0, + RATLS1 = AXIBMI + 0x00b4, + RATLR = AXIBMI + 0x00b8, + TSA0 = AXIBMI + 0x00c0, + TSS0 = AXIBMI + 0x00c4, + TRCR0 = AXIBMI + 0x0140, + RIDAUAS0 = AXIBMI + 0x0180, + RR = AXIBMI + 0x0200, + TATS = AXIBMI + 0x0210, + TATSR0 = AXIBMI + 0x0214, + TATSR1 = AXIBMI + 0x0218, + TATSR2 = AXIBMI + 0x021c, + RATS = AXIBMI + 0x0220, + RATSR0 = AXIBMI + 0x0224, + RATSR1 = AXIBMI + 0x0228, + RATSR2 = AXIBMI + 0x022c, + RIDASM0 = AXIBMI + 0x0240, + RIDASAM0 = AXIBMI + 0x0244, + RIDACAM0 = AXIBMI + 0x0248, + EIS0 = AXIBMI + 0x0300, + EIE0 = AXIBMI + 0x0304, + EID0 = AXIBMI + 0x0308, + EIS1 = AXIBMI + 0x0310, + EIE1 = AXIBMI + 0x0314, + EID1 = AXIBMI + 0x0318, + TCEIS0 = AXIBMI + 0x0340, + TCEIE0 = AXIBMI + 0x0344, + TCEID0 = AXIBMI + 0x0348, + RFSEIS0 = AXIBMI + 0x04c0, + RFSEIE0 = AXIBMI + 0x04c4, + RFSEID0 = AXIBMI + 0x04c8, + RFEIS0 = AXIBMI + 0x0540, + RFEIE0 = AXIBMI + 0x0544, + RFEID0 = AXIBMI + 0x0548, + RCEIS0 = AXIBMI + 0x05c0, + RCEIE0 = AXIBMI + 0x05c4, + RCEID0 = AXIBMI + 0x05c8, + RIDAOIS = AXIBMI + 0x0640, + RIDAOIE = AXIBMI + 0x0644, + RIDAOID = AXIBMI + 0x0648, + TSFEIS = AXIBMI + 0x06c0, + TSFEIE = AXIBMI + 0x06c4, + TSFEID = AXIBMI + 0x06c8, + TSCEIS = AXIBMI + 0x06d0, + TSCEIE = AXIBMI + 0x06d4, + TSCEID = AXIBMI + 0x06d8, + DIS = AXIBMI + 0x0b00, + DIE = AXIBMI + 0x0b04, + DID = AXIBMI + 0x0b08, + TDIS0 = AXIBMI + 0x0b10, + TDIE0 = AXIBMI + 0x0b14, + TDID0 = AXIBMI + 0x0b18, + RDIS0 = AXIBMI + 0x0b90, + RDIE0 = AXIBMI + 0x0b94, + RDID0 = AXIBMI + 0x0b98, + TSDIS = AXIBMI + 0x0c10, + TSDIE = AXIBMI + 0x0c14, + TSDID = AXIBMI + 0x0c18, + GPOUT = AXIBMI + 0x6000, + + OCR = TSNMHD + 0x0000, + OSR = TSNMHD + 0x0004, + SWR = TSNMHD + 0x0008, + SIS = TSNMHD + 0x000c, + GIS = TSNMHD + 0x0010, + GIE = TSNMHD + 0x0014, + GID = TSNMHD + 0x0018, + TIS1 = TSNMHD + 0x0020, + TIE1 = TSNMHD + 0x0024, + TID1 = TSNMHD + 0x0028, + TIS2 = TSNMHD + 0x0030, + TIE2 = TSNMHD + 0x0034, + TID2 = TSNMHD + 0x0038, + RIS = TSNMHD + 0x0040, + RIE = TSNMHD + 0x0044, + RID = TSNMHD + 0x0048, + TGC1 = TSNMHD + 0x0050, + TGC2 = TSNMHD + 0x0054, + TFS0 = TSNMHD + 0x0060, + TCF0 = TSNMHD + 0x0070, + TCR1 = TSNMHD + 0x0080, + TCR2 = TSNMHD + 0x0084, + TCR3 = TSNMHD + 0x0088, + TCR4 = TSNMHD + 0x008c, + TMS0 = TSNMHD + 0x0090, + TSR1 = TSNMHD + 0x00b0, + TSR2 = TSNMHD + 0x00b4, + TSR3 = TSNMHD + 0x00b8, + TSR4 = TSNMHD + 0x00bc, + TSR5 = TSNMHD + 0x00c0, + RGC = TSNMHD + 0x00d0, + RDFCR = TSNMHD + 0x00d4, + RCFCR = TSNMHD + 0x00d8, + REFCNCR = TSNMHD + 0x00dc, + RSR1 = TSNMHD + 0x00e0, + RSR2 = TSNMHD + 0x00e4, + RSR3 = TSNMHD + 0x00e8, + TCIS = TSNMHD + 0x01e0, + TCIE = TSNMHD + 0x01e4, + TCID = TSNMHD + 0x01e8, + TPTPC = TSNMHD + 0x01f0, + TTML = TSNMHD + 0x01f4, + TTJ = TSNMHD + 0x01f8, + TCC = TSNMHD + 0x0200, + TCS = TSNMHD + 0x0204, + TGS = TSNMHD + 0x020c, + TACST0 = TSNMHD + 0x0210, + TACST1 = TSNMHD + 0x0214, + TACST2 = TSNMHD + 0x0218, + TALIT0 = TSNMHD + 0x0220, + TALIT1 = TSNMHD + 0x0224, + TALIT2 = TSNMHD + 0x0228, + TAEN0 = TSNMHD + 0x0230, + TAEN1 = TSNMHD + 0x0234, + TASFE = TSNMHD + 0x0240, + TACLL0 = TSNMHD + 0x0250, + TACLL1 = TSNMHD + 0x0254, + TACLL2 = TSNMHD + 0x0258, + CACC = TSNMHD + 0x0260, + CCS = TSNMHD + 0x0264, + CAIV0 = TSNMHD + 0x0270, + CAUL0 = TSNMHD + 0x0290, + TOCST0 = TSNMHD + 0x0300, + TOCST1 = TSNMHD + 0x0304, + TOCST2 = TSNMHD + 0x0308, + TOLIT0 = TSNMHD + 0x0310, + TOLIT1 = TSNMHD + 0x0314, + TOLIT2 = TSNMHD + 0x0318, + TOEN0 = TSNMHD + 0x0320, + TOEN1 = TSNMHD + 0x0324, + TOSFE = TSNMHD + 0x0330, + TCLR0 = TSNMHD + 0x0340, + TCLR1 = TSNMHD + 0x0344, + TCLR2 = TSNMHD + 0x0348, + TSMS = TSNMHD + 0x0350, + COCC = TSNMHD + 0x0360, + COIV0 = TSNMHD + 0x03b0, + COUL0 = TSNMHD + 0x03d0, + QSTMACU0 = TSNMHD + 0x0400, + QSTMACD0 = TSNMHD + 0x0404, + QSTMAMU0 = TSNMHD + 0x0408, + QSTMAMD0 = TSNMHD + 0x040c, + QSFTVL0 = TSNMHD + 0x0410, + QSFTVLM0 = TSNMHD + 0x0414, + QSFTMSD0 = TSNMHD + 0x0418, + QSFTGMI0 = TSNMHD + 0x041c, + QSFTLS = TSNMHD + 0x0600, + QSFTLIS = TSNMHD + 0x0604, + QSFTLIE = TSNMHD + 0x0608, + QSFTLID = TSNMHD + 0x060c, + QSMSMC = TSNMHD + 0x0610, + QSGTMC = TSNMHD + 0x0614, + QSEIS = TSNMHD + 0x0618, + QSEIE = TSNMHD + 0x061c, + QSEID = TSNMHD + 0x0620, + QGACST0 = TSNMHD + 0x0630, + QGACST1 = TSNMHD + 0x0634, + QGACST2 = TSNMHD + 0x0638, + QGALIT1 = TSNMHD + 0x0640, + QGALIT2 = TSNMHD + 0x0644, + QGAEN0 = TSNMHD + 0x0648, + QGAEN1 = TSNMHD + 0x074c, + QGIGS = TSNMHD + 0x0650, + QGGC = TSNMHD + 0x0654, + QGATL0 = TSNMHD + 0x0664, + QGATL1 = TSNMHD + 0x0668, + QGATL2 = TSNMHD + 0x066c, + QGOCST0 = TSNMHD + 0x0670, + QGOCST1 = TSNMHD + 0x0674, + QGOCST2 = TSNMHD + 0x0678, + QGOLIT0 = TSNMHD + 0x067c, + QGOLIT1 = TSNMHD + 0x0680, + QGOLIT2 = TSNMHD + 0x0684, + QGOEN0 = TSNMHD + 0x0688, + QGOEN1 = TSNMHD + 0x068c, + QGTRO = TSNMHD + 0x0690, + QGTR1 = TSNMHD + 0x0694, + QGTR2 = TSNMHD + 0x0698, + QGFSMS = TSNMHD + 0x069c, + QTMIS = TSNMHD + 0x06e0, + QTMIE = TSNMHD + 0x06e4, + QTMID = TSNMHD + 0x06e8, + QMEC = TSNMHD + 0x0700, + QMMC = TSNMHD + 0x0704, + QRFDC = TSNMHD + 0x0708, + QYFDC = TSNMHD + 0x070c, + QVTCMC0 = TSNMHD + 0x0710, + QMCBSC0 = TSNMHD + 0x0750, + QMCIRC0 = TSNMHD + 0x0790, + QMEBSC0 = TSNMHD + 0x07d0, + QMEIRC0 = TSNMHD + 0x0710, + QMCFC = TSNMHD + 0x0850, + QMEIS = TSNMHD + 0x0860, + QMEIE = TSNMHD + 0x0864, + QMEID = TSNMHD + 0x086c, + QSMFC0 = TSNMHD + 0x0870, + QMSPPC0 = TSNMHD + 0x08b0, + QMSRPC0 = TSNMHD + 0x08f0, + QGPPC0 = TSNMHD + 0x0930, + QGRPC0 = TSNMHD + 0x0950, + QMDPC0 = TSNMHD + 0x0970, + QMGPC0 = TSNMHD + 0x09b0, + QMYPC0 = TSNMHD + 0x09f0, + QMRPC0 = TSNMHD + 0x0a30, + MQSTMACU = TSNMHD + 0x0a70, + MQSTMACD = TSNMHD + 0x0a74, + MQSTMAMU = TSNMHD + 0x0a78, + MQSTMAMD = TSNMHD + 0x0a7c, + MQSFTVL = TSNMHD + 0x0a80, + MQSFTVLM = TSNMHD + 0x0a84, + MQSFTMSD = TSNMHD + 0x0a88, + MQSFTGMI = TSNMHD + 0x0a8c, + + CFCR0 = RMSO + 0x0800, + FMSCR = RMSO + 0x0c10, + + MMC = RMRO + 0x0000, + MPSM = RMRO + 0x0010, + MPIC = RMRO + 0x0014, + MTFFC = RMRO + 0x0020, + MTPFC = RMRO + 0x0024, + MTATC0 = RMRO + 0x0040, + MRGC = RMRO + 0x0080, + MRMAC0 = RMRO + 0x0084, + MRMAC1 = RMRO + 0x0088, + MRAFC = RMRO + 0x008c, + MRSCE = RMRO + 0x0090, + MRSCP = RMRO + 0x0094, + MRSCC = RMRO + 0x0098, + MRFSCE = RMRO + 0x009c, + MRFSCP = RMRO + 0x00a0, + MTRC = RMRO + 0x00a4, + MPFC = RMRO + 0x0100, + MLVC = RMRO + 0x0340, + MEEEC = RMRO + 0x0350, + MLBC = RMRO + 0x0360, + MGMR = RMRO + 0x0400, + MMPFTCT = RMRO + 0x0410, + MAPFTCT = RMRO + 0x0414, + MPFRCT = RMRO + 0x0418, + MFCICT = RMRO + 0x041c, + MEEECT = RMRO + 0x0420, + MEIS = RMRO + 0x0500, + MEIE = RMRO + 0x0504, + MEID = RMRO + 0x0508, + MMIS0 = RMRO + 0x0510, + MMIE0 = RMRO + 0x0514, + MMID0 = RMRO + 0x0518, + MMIS1 = RMRO + 0x0520, + MMIE1 = RMRO + 0x0524, + MMID1 = RMRO + 0x0528, + MMIS2 = RMRO + 0x0530, + MMIE2 = RMRO + 0x0534, + MMID2 = RMRO + 0x0538, + MXMS = RMRO + 0x0600, + +}; + +/* AXIBMI */ +#define RR_RATRR BIT(0) +#define RR_TATRR BIT(1) +#define RR_RST (RR_RATRR | RR_TATRR) +#define RR_RST_COMPLETE 0x03 + +#define AXIWC_DEFAULT 0xffff +#define AXIRC_DEFAULT 0xffff + +#define TATLS0_TEDE BIT(1) +#define TATLS0_TATEN_SHIFT 24 +#define TATLS0_TATEN(n) ((n) << TATLS0_TATEN_SHIFT) +#define TATLR_TATL BIT(31) + +#define RATLS0_RETS BIT(2) +#define RATLS0_REDE BIT(3) +#define RATLS0_RATEN_SHIFT 24 +#define RATLS0_RATEN(n) ((n) << RATLS0_RATEN_SHIFT) +#define RATLR_RATL BIT(31) + +#define DIE_DID_TDICX(n) BIT((n)) +#define DIE_DID_RDICX(n) BIT((n) + 8) +#define TDIE_TDID_TDX(n) BIT(n) +#define RDIE_RDID_RDX(n) BIT(n) +#define TDIS_TDS(n) BIT(n) +#define RDIS_RDS(n) BIT(n) + +/* MHD */ +#define OSR_OPS 0x07 +#define SWR_SWR BIT(0) + +#define TGC1_TQTM_SFM 0xff00 +#define TGC1_STTV_DEFAULT 0x03 + +#define TMS_MFS_MAX 0x2800 + +/* RMAC System */ +#define CFCR_SDID(n) ((n) << 16) +#define FMSCR_FMSIE(n) ((n) << 0) + +/* RMAC */ +#define MPIC_PIS_MASK GENMASK(1, 0) +#define MPIC_PIS_MII 0 +#define MPIC_PIS_RMII 0x01 +#define MPIC_PIS_GMII 0x02 +#define MPIC_PIS_RGMII 0x03 +#define MPIC_LSC_SHIFT 2 +#define MPIC_LSC_MASK GENMASK(3, MPIC_LSC_SHIFT) +#define MPIC_LSC_10M (0 << MPIC_LSC_SHIFT) +#define MPIC_LSC_100M (0x01 << MPIC_LSC_SHIFT) +#define MPIC_LSC_1G (0x02 << MPIC_LSC_SHIFT) +#define MPIC_PSMCS_SHIFT 16 +#define MPIC_PSMCS_MASK GENMASK(21, MPIC_PSMCS_SHIFT) +#define MPIC_PSMCS_DEFAULT (0x0a << MPIC_PSMCS_SHIFT) +#define MPIC_PSMHT_SHIFT 24 +#define MPIC_PSMHT_MASK GENMASK(26, MPIC_PSMHT_SHIFT) +#define MPIC_PSMHT_DEFAULT (0x07 << MPIC_PSMHT_SHIFT) + +#define MLVC_PASE BIT(8) +#define MLVC_PSE BIT(16) +#define MLVC_PLV BIT(17) + +#define MPSM_PSME BIT(0) +#define MPSM_PSMAD BIT(1) +#define MPSM_PDA_SHIFT 3 +#define MPSM_PDA_MASK GENMASK(7, 3) +#define MPSM_PDA(n) (((n) << MPSM_PDA_SHIFT) & MPSM_PDA_MASK) +#define MPSM_PRA_SHIFT 8 +#define MPSM_PRA_MASK GENMASK(12, 8) +#define MPSM_PRA(n) (((n) << MPSM_PRA_SHIFT) & MPSM_PRA_MASK) +#define MPSM_PRD_SHIFT 16 +#define MPSM_PRD_SET(n) ((n) << MPSM_PRD_SHIFT) +#define MPSM_PRD_GET(n) ((n) >> MPSM_PRD_SHIFT) + +#define GPOUT_RDM BIT(13) +#define GPOUT_TDM BIT(14) + +/* RTSN */ +#define RTSN_INTERVAL_US 1000 +#define RTSN_TIMEOUT_US 1000000 + +#define TX_NUM_CHAINS 1 +#define RX_NUM_CHAINS 1 + +#define TX_CHAIN_SIZE 1024 +#define RX_CHAIN_SIZE 1024 + +#define TX_CHAIN_IDX 0 +#define RX_CHAIN_IDX 0 + +#define TX_CHAIN_ADDR_OFFSET (sizeof(struct rtsn_desc) * TX_CHAIN_IDX) +#define RX_CHAIN_ADDR_OFFSET (sizeof(struct rtsn_desc) * RX_CHAIN_IDX) + +#define PKT_BUF_SZ 1584 +#define RTSN_ALIGN 128 + +enum rtsn_mode { + OCR_OPC_DISABLE, + OCR_OPC_CONFIG, + OCR_OPC_OPERATION, +}; + +/* Descriptors */ +enum RX_DS_CC_BIT { + RX_DS = 0x0fff, /* Data size */ + RX_TR = 0x1000, /* Truncation indication */ + RX_EI = 0x2000, /* Error indication */ + RX_PS = 0xc000, /* Padding selection */ +}; + +enum TX_FS_TAGL_BIT { + TX_DS = 0x0fff, /* Data size */ + TX_TAGL = 0xf000, /* Frame tag LSBs */ +}; + +enum DIE_DT { + /* HW/SW arbitration */ + DT_FEMPTY_IS = 0x10, + DT_FEMPTY_IC = 0x20, + DT_FEMPTY_ND = 0x30, + DT_FEMPTY = 0x40, + DT_FEMPTY_START = 0x50, + DT_FEMPTY_MID = 0x60, + DT_FEMPTY_END = 0x70, + + /* Frame data */ + DT_FSINGLE = 0x80, + DT_FSTART = 0x90, + DT_FMID = 0xa0, + DT_FEND = 0xb0, + + /* Chain control */ + DT_LEMPTY = 0xc0, + DT_EEMPTY = 0xd0, + DT_LINK = 0xe0, + DT_EOS = 0xf0, + + DT_MASK = 0xf0, + D_DIE = 0x08, +}; + +struct rtsn_desc { + __le16 info_ds; + __u8 info; + u8 die_dt; + __le32 dptr; +} __packed; + +struct rtsn_ts_desc { + __le16 info_ds; + __u8 info; + u8 die_dt; + __le32 dptr; + __le32 ts_nsec; + __le32 ts_sec; +} __packed; + +struct rtsn_ext_desc { + __le16 info_ds; + __u8 info; + u8 die_dt; + __le32 dptr; + __le64 info1; +} __packed; + +struct rtsn_ext_ts_desc { + __le16 info_ds; + __u8 info; + u8 die_dt; + __le32 dptr; + __le64 info1; + __le32 ts_nsec; + __le32 ts_sec; +} __packed; + +enum EXT_INFO_DS_BIT { + TXC = 0x4000, +}; + +#endif diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c index f05bd757dfe5..5ef52ef2698f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c @@ -218,6 +218,7 @@ static void timestamp_interrupt(struct stmmac_priv *priv) { u32 num_snapshot, ts_status, tsync_int; struct ptp_clock_event event; + u32 acr_value, channel; unsigned long flags; u64 ptp_time; int i; @@ -243,12 +244,15 @@ static void timestamp_interrupt(struct stmmac_priv *priv) num_snapshot = (ts_status & GMAC_TIMESTAMP_ATSNS_MASK) >> GMAC_TIMESTAMP_ATSNS_SHIFT; + acr_value = readl(priv->ptpaddr + PTP_ACR); + channel = ilog2(FIELD_GET(PTP_ACR_MASK, acr_value)); + for (i = 0; i < num_snapshot; i++) { read_lock_irqsave(&priv->ptp_lock, flags); get_ptptime(priv->ptpaddr, &ptp_time); read_unlock_irqrestore(&priv->ptp_lock, flags); event.type = PTP_CLOCK_EXTTS; - event.index = 0; + event.index = channel; event.timestamp = ptp_time; ptp_clock_event(priv->ptp_clock, &event); } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 54797edc9b38..ad868e8d195d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -764,8 +764,8 @@ EXPORT_SYMBOL_GPL(stmmac_get_platform_resources); * Description: Call the platform's init callback (if any) and propagate * the return value. */ -int stmmac_pltfr_init(struct platform_device *pdev, - struct plat_stmmacenet_data *plat) +static int stmmac_pltfr_init(struct platform_device *pdev, + struct plat_stmmacenet_data *plat) { int ret = 0; @@ -774,7 +774,6 @@ int stmmac_pltfr_init(struct platform_device *pdev, return ret; } -EXPORT_SYMBOL_GPL(stmmac_pltfr_init); /** * stmmac_pltfr_exit @@ -782,13 +781,12 @@ EXPORT_SYMBOL_GPL(stmmac_pltfr_init); * @plat: driver data platform structure * Description: Call the platform's exit callback (if any). */ -void stmmac_pltfr_exit(struct platform_device *pdev, - struct plat_stmmacenet_data *plat) +static void stmmac_pltfr_exit(struct platform_device *pdev, + struct plat_stmmacenet_data *plat) { if (plat->exit) plat->exit(pdev, plat->bsp_priv); } -EXPORT_SYMBOL_GPL(stmmac_pltfr_exit); /** * stmmac_pltfr_probe diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.h index bb6fc7e59aed..72dc1a32e46d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.h @@ -17,11 +17,6 @@ devm_stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac); int stmmac_get_platform_resources(struct platform_device *pdev, struct stmmac_resources *stmmac_res); -int stmmac_pltfr_init(struct platform_device *pdev, - struct plat_stmmacenet_data *plat); -void stmmac_pltfr_exit(struct platform_device *pdev, - struct plat_stmmacenet_data *plat); - int stmmac_pltfr_probe(struct platform_device *pdev, struct plat_stmmacenet_data *plat, struct stmmac_resources *res); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c index 1562fbdd0a04..996f2bcd07a2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c @@ -358,24 +358,28 @@ static int tc_setup_cbs(struct stmmac_priv *priv, port_transmit_rate_kbps = qopt->idleslope - qopt->sendslope; - /* Port Transmit Rate and Speed Divider */ - switch (div_s64(port_transmit_rate_kbps, 1000)) { - case SPEED_10000: - case SPEED_5000: - ptr = 32; - break; - case SPEED_2500: - case SPEED_1000: - ptr = 8; - break; - case SPEED_100: - ptr = 4; - break; - default: - netdev_err(priv->dev, - "Invalid portTransmitRate %lld (idleSlope - sendSlope)\n", - port_transmit_rate_kbps); - return -EINVAL; + if (qopt->enable) { + /* Port Transmit Rate and Speed Divider */ + switch (div_s64(port_transmit_rate_kbps, 1000)) { + case SPEED_10000: + case SPEED_5000: + ptr = 32; + break; + case SPEED_2500: + case SPEED_1000: + ptr = 8; + break; + case SPEED_100: + ptr = 4; + break; + default: + netdev_err(priv->dev, + "Invalid portTransmitRate %lld (idleSlope - sendSlope)\n", + port_transmit_rate_kbps); + return -EINVAL; + } + } else { + ptr = 0; } mode_to_use = priv->plat->tx_queues_cfg[queue].mode_to_use; diff --git a/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c b/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c index cc3bec42ed8e..abe5921dde02 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c @@ -43,6 +43,11 @@ static const struct wx_stats wx_gstrings_stats[] = { WX_STAT("alloc_rx_buff_failed", alloc_rx_buff_failed), }; +static const struct wx_stats wx_gstrings_fdir_stats[] = { + WX_STAT("fdir_match", stats.fdirmatch), + WX_STAT("fdir_miss", stats.fdirmiss), +}; + /* drivers allocates num_tx_queues and num_rx_queues symmetrically so * we set the num_rx_queues to evaluate to num_tx_queues. This is * used because we do not have a good way to get the max number of @@ -55,13 +60,17 @@ static const struct wx_stats wx_gstrings_stats[] = { (WX_NUM_TX_QUEUES + WX_NUM_RX_QUEUES) * \ (sizeof(struct wx_queue_stats) / sizeof(u64))) #define WX_GLOBAL_STATS_LEN ARRAY_SIZE(wx_gstrings_stats) +#define WX_FDIR_STATS_LEN ARRAY_SIZE(wx_gstrings_fdir_stats) #define WX_STATS_LEN (WX_GLOBAL_STATS_LEN + WX_QUEUE_STATS_LEN) int wx_get_sset_count(struct net_device *netdev, int sset) { + struct wx *wx = netdev_priv(netdev); + switch (sset) { case ETH_SS_STATS: - return WX_STATS_LEN; + return (wx->mac.type == wx_mac_sp) ? + WX_STATS_LEN + WX_FDIR_STATS_LEN : WX_STATS_LEN; default: return -EOPNOTSUPP; } @@ -70,6 +79,7 @@ EXPORT_SYMBOL(wx_get_sset_count); void wx_get_strings(struct net_device *netdev, u32 stringset, u8 *data) { + struct wx *wx = netdev_priv(netdev); u8 *p = data; int i; @@ -77,6 +87,10 @@ void wx_get_strings(struct net_device *netdev, u32 stringset, u8 *data) case ETH_SS_STATS: for (i = 0; i < WX_GLOBAL_STATS_LEN; i++) ethtool_puts(&p, wx_gstrings_stats[i].stat_string); + if (wx->mac.type == wx_mac_sp) { + for (i = 0; i < WX_FDIR_STATS_LEN; i++) + ethtool_puts(&p, wx_gstrings_fdir_stats[i].stat_string); + } for (i = 0; i < netdev->num_tx_queues; i++) { ethtool_sprintf(&p, "tx_queue_%u_packets", i); ethtool_sprintf(&p, "tx_queue_%u_bytes", i); @@ -96,7 +110,7 @@ void wx_get_ethtool_stats(struct net_device *netdev, struct wx *wx = netdev_priv(netdev); struct wx_ring *ring; unsigned int start; - int i, j; + int i, j, k; char *p; wx_update_stats(wx); @@ -107,6 +121,13 @@ void wx_get_ethtool_stats(struct net_device *netdev, sizeof(u64)) ? *(u64 *)p : *(u32 *)p; } + if (wx->mac.type == wx_mac_sp) { + for (k = 0; k < WX_FDIR_STATS_LEN; k++) { + p = (char *)wx + wx_gstrings_fdir_stats[k].stat_offset; + data[i++] = *(u64 *)p; + } + } + for (j = 0; j < netdev->num_tx_queues; j++) { ring = wx->tx_ring[j]; if (!ring) { @@ -172,17 +193,21 @@ EXPORT_SYMBOL(wx_get_pause_stats); void wx_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *info) { + unsigned int stats_len = WX_STATS_LEN; struct wx *wx = netdev_priv(netdev); + if (wx->mac.type == wx_mac_sp) + stats_len += WX_FDIR_STATS_LEN; + strscpy(info->driver, wx->driver_name, sizeof(info->driver)); strscpy(info->fw_version, wx->eeprom_id, sizeof(info->fw_version)); strscpy(info->bus_info, pci_name(wx->pdev), sizeof(info->bus_info)); if (wx->num_tx_queues <= WX_NUM_TX_QUEUES) { - info->n_stats = WX_STATS_LEN - + info->n_stats = stats_len - (WX_NUM_TX_QUEUES - wx->num_tx_queues) * (sizeof(struct wx_queue_stats) / sizeof(u64)) * 2; } else { - info->n_stats = WX_STATS_LEN; + info->n_stats = stats_len; } } EXPORT_SYMBOL(wx_get_drvinfo); @@ -383,6 +408,9 @@ void wx_get_channels(struct net_device *dev, /* record RSS queues */ ch->combined_count = wx->ring_feature[RING_F_RSS].indices; + + if (test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags)) + ch->combined_count = wx->ring_feature[RING_F_FDIR].indices; } EXPORT_SYMBOL(wx_get_channels); @@ -400,6 +428,9 @@ int wx_set_channels(struct net_device *dev, if (count > wx_max_channels(wx)) return -EINVAL; + if (test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags)) + wx->ring_feature[RING_F_FDIR].limit = count; + wx->ring_feature[RING_F_RSS].limit = count; return 0; diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.c b/drivers/net/ethernet/wangxun/libwx/wx_hw.c index 7c4b6881a93f..44cd7a5866c1 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_hw.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.c @@ -1147,8 +1147,15 @@ static void wx_enable_rx(struct wx *wx) static void wx_set_rxpba(struct wx *wx) { u32 rxpktsize, txpktsize, txpbthresh; + u32 pbsize = wx->mac.rx_pb_size; - rxpktsize = wx->mac.rx_pb_size << WX_RDB_PB_SZ_SHIFT; + if (test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags)) { + if (test_bit(WX_FLAG_FDIR_HASH, wx->flags) || + test_bit(WX_FLAG_FDIR_PERFECT, wx->flags)) + pbsize -= 64; /* Default 64KB */ + } + + rxpktsize = pbsize << WX_RDB_PB_SZ_SHIFT; wr32(wx, WX_RDB_PB_SZ(0), rxpktsize); /* Only support an equally distributed Tx packet buffer strategy. */ @@ -1261,7 +1268,7 @@ static void wx_configure_port(struct wx *wx) * Stops the receive data path and waits for the HW to internally empty * the Rx security block **/ -static int wx_disable_sec_rx_path(struct wx *wx) +int wx_disable_sec_rx_path(struct wx *wx) { u32 secrx; @@ -1271,6 +1278,7 @@ static int wx_disable_sec_rx_path(struct wx *wx) return read_poll_timeout(rd32, secrx, secrx & WX_RSC_ST_RSEC_RDY, 1000, 40000, false, wx, WX_RSC_ST); } +EXPORT_SYMBOL(wx_disable_sec_rx_path); /** * wx_enable_sec_rx_path - Enables the receive data path @@ -1278,11 +1286,12 @@ static int wx_disable_sec_rx_path(struct wx *wx) * * Enables the receive data path. **/ -static void wx_enable_sec_rx_path(struct wx *wx) +void wx_enable_sec_rx_path(struct wx *wx) { wr32m(wx, WX_RSC_CTL, WX_RSC_CTL_RX_DIS, 0); WX_WRITE_FLUSH(wx); } +EXPORT_SYMBOL(wx_enable_sec_rx_path); static void wx_vlan_strip_control(struct wx *wx, bool enable) { @@ -1499,6 +1508,13 @@ static void wx_configure_tx_ring(struct wx *wx, txdctl |= ring->count / 128 << WX_PX_TR_CFG_TR_SIZE_SHIFT; txdctl |= 0x20 << WX_PX_TR_CFG_WTHRESH_SHIFT; + ring->atr_count = 0; + if (test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags) && + test_bit(WX_FLAG_FDIR_HASH, wx->flags)) + ring->atr_sample_rate = wx->atr_sample_rate; + else + ring->atr_sample_rate = 0; + /* reinitialize tx_buffer_info */ memset(ring->tx_buffer_info, 0, sizeof(struct wx_tx_buffer) * ring->count); @@ -1732,7 +1748,9 @@ void wx_configure(struct wx *wx) wx_set_rx_mode(wx->netdev); wx_restore_vlan(wx); - wx_enable_sec_rx_path(wx); + + if (test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags)) + wx->configure_fdir(wx); wx_configure_tx(wx); wx_configure_rx(wx); @@ -1959,6 +1977,7 @@ int wx_sw_init(struct wx *wx) } bitmap_zero(wx->state, WX_STATE_NBITS); + bitmap_zero(wx->flags, WX_PF_FLAGS_NBITS); return 0; } @@ -2333,6 +2352,11 @@ void wx_update_stats(struct wx *wx) hwstats->b2ogprc += rd32(wx, WX_RDM_BMC2OS_CNT); hwstats->rdmdrop += rd32(wx, WX_RDM_DRP_PKT); + if (wx->mac.type == wx_mac_sp) { + hwstats->fdirmatch += rd32(wx, WX_RDB_FDIR_MATCH); + hwstats->fdirmiss += rd32(wx, WX_RDB_FDIR_MISS); + } + for (i = 0; i < wx->mac.max_rx_queues; i++) hwstats->qmprc += rd32(wx, WX_PX_MPRC(i)); } diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.h b/drivers/net/ethernet/wangxun/libwx/wx_hw.h index 9e219fa717a2..11fb33349482 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_hw.h +++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.h @@ -28,6 +28,8 @@ void wx_mac_set_default_filter(struct wx *wx, u8 *addr); void wx_flush_sw_mac_table(struct wx *wx); int wx_set_mac(struct net_device *netdev, void *p); void wx_disable_rx(struct wx *wx); +int wx_disable_sec_rx_path(struct wx *wx); +void wx_enable_sec_rx_path(struct wx *wx); void wx_set_rx_mode(struct net_device *netdev); int wx_change_mtu(struct net_device *netdev, int new_mtu); void wx_disable_rx_queue(struct wx *wx, struct wx_ring *ring); diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_lib.c index 68bde91b67a0..ac0e1d42fe55 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_lib.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.c @@ -148,10 +148,11 @@ static struct wx_dec_ptype wx_ptype_lookup[256] = { [0xFD] = WX_PTT(IP, IPV6, IGMV, IPV6, SCTP, PAY4), }; -static struct wx_dec_ptype wx_decode_ptype(const u8 ptype) +struct wx_dec_ptype wx_decode_ptype(const u8 ptype) { return wx_ptype_lookup[ptype]; } +EXPORT_SYMBOL(wx_decode_ptype); /* wx_test_staterr - tests bits in Rx descriptor status and error fields */ static __le32 wx_test_staterr(union wx_rx_desc *rx_desc, @@ -1453,6 +1454,7 @@ static void wx_tx_csum(struct wx_ring *tx_ring, struct wx_tx_buffer *first, static netdev_tx_t wx_xmit_frame_ring(struct sk_buff *skb, struct wx_ring *tx_ring) { + struct wx *wx = netdev_priv(tx_ring->netdev); u16 count = TXD_USE_COUNT(skb_headlen(skb)); struct wx_tx_buffer *first; u8 hdr_len = 0, ptype; @@ -1498,6 +1500,10 @@ static netdev_tx_t wx_xmit_frame_ring(struct sk_buff *skb, goto out_drop; else if (!tso) wx_tx_csum(tx_ring, first, ptype); + + if (test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags) && tx_ring->atr_sample_rate) + wx->atr(tx_ring, first, ptype); + wx_tx_map(tx_ring, first, hdr_len); return NETDEV_TX_OK; @@ -1574,8 +1580,27 @@ static void wx_set_rss_queues(struct wx *wx) f = &wx->ring_feature[RING_F_RSS]; f->indices = f->limit; - wx->num_rx_queues = f->limit; - wx->num_tx_queues = f->limit; + if (!(test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags))) + goto out; + + clear_bit(WX_FLAG_FDIR_HASH, wx->flags); + + /* Use Flow Director in addition to RSS to ensure the best + * distribution of flows across cores, even when an FDIR flow + * isn't matched. + */ + if (f->indices > 1) { + f = &wx->ring_feature[RING_F_FDIR]; + + f->indices = f->limit; + + if (!(test_bit(WX_FLAG_FDIR_PERFECT, wx->flags))) + set_bit(WX_FLAG_FDIR_HASH, wx->flags); + } + +out: + wx->num_rx_queues = f->indices; + wx->num_tx_queues = f->indices; } static void wx_set_num_queues(struct wx *wx) @@ -2680,6 +2705,7 @@ int wx_set_features(struct net_device *netdev, netdev_features_t features) { netdev_features_t changed = netdev->features ^ features; struct wx *wx = netdev_priv(netdev); + bool need_reset = false; if (features & NETIF_F_RXHASH) { wr32m(wx, WX_RDB_RA_CTL, WX_RDB_RA_CTL_RSS_EN, @@ -2697,6 +2723,36 @@ int wx_set_features(struct net_device *netdev, netdev_features_t features) else if (changed & (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER)) wx_set_rx_mode(netdev); + if (!(test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags))) + return 0; + + /* Check if Flow Director n-tuple support was enabled or disabled. If + * the state changed, we need to reset. + */ + switch (features & NETIF_F_NTUPLE) { + case NETIF_F_NTUPLE: + /* turn off ATR, enable perfect filters and reset */ + if (!(test_and_set_bit(WX_FLAG_FDIR_PERFECT, wx->flags))) + need_reset = true; + + clear_bit(WX_FLAG_FDIR_HASH, wx->flags); + break; + default: + /* turn off perfect filters, enable ATR and reset */ + if (test_and_clear_bit(WX_FLAG_FDIR_PERFECT, wx->flags)) + need_reset = true; + + /* We cannot enable ATR if RSS is disabled */ + if (wx->ring_feature[RING_F_RSS].limit <= 1) + break; + + set_bit(WX_FLAG_FDIR_HASH, wx->flags); + break; + } + + if (need_reset) + wx->do_reset(netdev); + return 0; } EXPORT_SYMBOL(wx_set_features); diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.h b/drivers/net/ethernet/wangxun/libwx/wx_lib.h index c41b29ea812f..fdeb0c315b75 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_lib.h +++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.h @@ -7,6 +7,7 @@ #ifndef _WX_LIB_H_ #define _WX_LIB_H_ +struct wx_dec_ptype wx_decode_ptype(const u8 ptype); void wx_alloc_rx_buffers(struct wx_ring *rx_ring, u16 cleaned_count); u16 wx_desc_unused(struct wx_ring *ring); netdev_tx_t wx_xmit_frame(struct sk_buff *skb, diff --git a/drivers/net/ethernet/wangxun/libwx/wx_type.h b/drivers/net/ethernet/wangxun/libwx/wx_type.h index 5aaf7b1fa2db..e0b7866f96ec 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_type.h +++ b/drivers/net/ethernet/wangxun/libwx/wx_type.h @@ -157,6 +157,8 @@ #define WX_RDB_RA_CTL_RSS_IPV6_TCP BIT(21) #define WX_RDB_RA_CTL_RSS_IPV4_UDP BIT(22) #define WX_RDB_RA_CTL_RSS_IPV6_UDP BIT(23) +#define WX_RDB_FDIR_MATCH 0x19558 +#define WX_RDB_FDIR_MISS 0x1955C /******************************* PSR Registers *******************************/ /* psr control */ @@ -503,6 +505,34 @@ enum WX_MSCA_CMD_value { #define WX_PTYPE_TYP_TCP 0x04 #define WX_PTYPE_TYP_SCTP 0x05 +/* Packet type non-ip values */ +enum wx_l2_ptypes { + WX_PTYPE_L2_ABORTED = (WX_PTYPE_PKT_MAC), + WX_PTYPE_L2_MAC = (WX_PTYPE_PKT_MAC | WX_PTYPE_TYP_MAC), + + WX_PTYPE_L2_IPV4_FRAG = (WX_PTYPE_PKT_IP | WX_PTYPE_TYP_IPFRAG), + WX_PTYPE_L2_IPV4 = (WX_PTYPE_PKT_IP | WX_PTYPE_TYP_IP), + WX_PTYPE_L2_IPV4_UDP = (WX_PTYPE_PKT_IP | WX_PTYPE_TYP_UDP), + WX_PTYPE_L2_IPV4_TCP = (WX_PTYPE_PKT_IP | WX_PTYPE_TYP_TCP), + WX_PTYPE_L2_IPV4_SCTP = (WX_PTYPE_PKT_IP | WX_PTYPE_TYP_SCTP), + WX_PTYPE_L2_IPV6_FRAG = (WX_PTYPE_PKT_IP | WX_PTYPE_PKT_IPV6 | + WX_PTYPE_TYP_IPFRAG), + WX_PTYPE_L2_IPV6 = (WX_PTYPE_PKT_IP | WX_PTYPE_PKT_IPV6 | + WX_PTYPE_TYP_IP), + WX_PTYPE_L2_IPV6_UDP = (WX_PTYPE_PKT_IP | WX_PTYPE_PKT_IPV6 | + WX_PTYPE_TYP_UDP), + WX_PTYPE_L2_IPV6_TCP = (WX_PTYPE_PKT_IP | WX_PTYPE_PKT_IPV6 | + WX_PTYPE_TYP_TCP), + WX_PTYPE_L2_IPV6_SCTP = (WX_PTYPE_PKT_IP | WX_PTYPE_PKT_IPV6 | + WX_PTYPE_TYP_SCTP), + + WX_PTYPE_L2_TUN4_MAC = (WX_PTYPE_TUN_IPV4 | WX_PTYPE_PKT_IGM), + WX_PTYPE_L2_TUN6_MAC = (WX_PTYPE_TUN_IPV6 | WX_PTYPE_PKT_IGM), +}; + +#define WX_PTYPE_PKT(_pt) ((_pt) & 0x30) +#define WX_PTYPE_TYPL4(_pt) ((_pt) & 0x07) + #define WX_RXD_PKTTYPE(_rxd) \ ((le32_to_cpu((_rxd)->wb.lower.lo_dword.data) >> 9) & 0xFF) #define WX_RXD_IPV6EX(_rxd) \ @@ -552,6 +582,9 @@ enum wx_tx_flags { WX_TX_FLAGS_OUTER_IPV4 = 0x100, WX_TX_FLAGS_LINKSEC = 0x200, WX_TX_FLAGS_IPSEC = 0x400, + + /* software defined flags */ + WX_TX_FLAGS_SW_VLAN = 0x40, }; /* VLAN info */ @@ -900,7 +933,13 @@ struct wx_ring { */ u16 next_to_use; u16 next_to_clean; - u16 next_to_alloc; + union { + u16 next_to_alloc; + struct { + u8 atr_sample_rate; + u8 atr_count; + }; + }; struct wx_queue_stats stats; struct u64_stats_sync syncp; @@ -939,6 +978,7 @@ struct wx_ring_feature { enum wx_ring_f_enum { RING_F_NONE = 0, RING_F_RSS, + RING_F_FDIR, RING_F_ARRAY_SIZE /* must be last in enum set */ }; @@ -980,15 +1020,26 @@ struct wx_hw_stats { u64 crcerrs; u64 rlec; u64 qmprc; + u64 fdirmatch; + u64 fdirmiss; }; enum wx_state { WX_STATE_RESETTING, WX_STATE_NBITS, /* must be last */ }; + +enum wx_pf_flags { + WX_FLAG_FDIR_CAPABLE, + WX_FLAG_FDIR_HASH, + WX_FLAG_FDIR_PERFECT, + WX_PF_FLAGS_NBITS /* must be last */ +}; + struct wx { unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; DECLARE_BITMAP(state, WX_STATE_NBITS); + DECLARE_BITMAP(flags, WX_PF_FLAGS_NBITS); void *priv; u8 __iomem *hw_addr; @@ -1077,6 +1128,9 @@ struct wx { u64 hw_csum_rx_error; u64 alloc_rx_buff_failed; + u32 atr_sample_rate; + void (*atr)(struct wx_ring *ring, struct wx_tx_buffer *first, u8 ptype); + void (*configure_fdir)(struct wx *wx); void (*do_reset)(struct net_device *netdev); }; diff --git a/drivers/net/ethernet/wangxun/txgbe/Makefile b/drivers/net/ethernet/wangxun/txgbe/Makefile index 42718875277c..f74576fe7062 100644 --- a/drivers/net/ethernet/wangxun/txgbe/Makefile +++ b/drivers/net/ethernet/wangxun/txgbe/Makefile @@ -10,4 +10,5 @@ txgbe-objs := txgbe_main.o \ txgbe_hw.o \ txgbe_phy.o \ txgbe_irq.o \ + txgbe_fdir.o \ txgbe_ethtool.o diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.c index 31fde3fa7c6b..d98314b26c19 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.c @@ -9,6 +9,7 @@ #include "../libwx/wx_type.h" #include "../libwx/wx_lib.h" #include "txgbe_type.h" +#include "txgbe_fdir.h" #include "txgbe_ethtool.h" static int txgbe_set_ringparam(struct net_device *netdev, @@ -79,6 +80,430 @@ static int txgbe_set_channels(struct net_device *dev, return txgbe_setup_tc(dev, netdev_get_num_tc(dev)); } +static int txgbe_get_ethtool_fdir_entry(struct txgbe *txgbe, + struct ethtool_rxnfc *cmd) +{ + struct ethtool_rx_flow_spec *fsp = + (struct ethtool_rx_flow_spec *)&cmd->fs; + union txgbe_atr_input *mask = &txgbe->fdir_mask; + struct txgbe_fdir_filter *rule = NULL; + struct hlist_node *node; + + /* report total rule count */ + cmd->data = (1024 << TXGBE_FDIR_PBALLOC_64K) - 2; + + hlist_for_each_entry_safe(rule, node, &txgbe->fdir_filter_list, + fdir_node) { + if (fsp->location <= rule->sw_idx) + break; + } + + if (!rule || fsp->location != rule->sw_idx) + return -EINVAL; + + /* set flow type field */ + switch (rule->filter.formatted.flow_type) { + case TXGBE_ATR_FLOW_TYPE_TCPV4: + fsp->flow_type = TCP_V4_FLOW; + break; + case TXGBE_ATR_FLOW_TYPE_UDPV4: + fsp->flow_type = UDP_V4_FLOW; + break; + case TXGBE_ATR_FLOW_TYPE_SCTPV4: + fsp->flow_type = SCTP_V4_FLOW; + break; + case TXGBE_ATR_FLOW_TYPE_IPV4: + fsp->flow_type = IP_USER_FLOW; + fsp->h_u.usr_ip4_spec.ip_ver = ETH_RX_NFC_IP4; + fsp->h_u.usr_ip4_spec.proto = 0; + fsp->m_u.usr_ip4_spec.proto = 0; + break; + default: + return -EINVAL; + } + + fsp->h_u.tcp_ip4_spec.psrc = rule->filter.formatted.src_port; + fsp->m_u.tcp_ip4_spec.psrc = mask->formatted.src_port; + fsp->h_u.tcp_ip4_spec.pdst = rule->filter.formatted.dst_port; + fsp->m_u.tcp_ip4_spec.pdst = mask->formatted.dst_port; + fsp->h_u.tcp_ip4_spec.ip4src = rule->filter.formatted.src_ip[0]; + fsp->m_u.tcp_ip4_spec.ip4src = mask->formatted.src_ip[0]; + fsp->h_u.tcp_ip4_spec.ip4dst = rule->filter.formatted.dst_ip[0]; + fsp->m_u.tcp_ip4_spec.ip4dst = mask->formatted.dst_ip[0]; + fsp->h_ext.vlan_etype = rule->filter.formatted.flex_bytes; + fsp->m_ext.vlan_etype = mask->formatted.flex_bytes; + fsp->h_ext.data[1] = htonl(rule->filter.formatted.vm_pool); + fsp->m_ext.data[1] = htonl(mask->formatted.vm_pool); + fsp->flow_type |= FLOW_EXT; + + /* record action */ + if (rule->action == TXGBE_RDB_FDIR_DROP_QUEUE) + fsp->ring_cookie = RX_CLS_FLOW_DISC; + else + fsp->ring_cookie = rule->action; + + return 0; +} + +static int txgbe_get_ethtool_fdir_all(struct txgbe *txgbe, + struct ethtool_rxnfc *cmd, + u32 *rule_locs) +{ + struct txgbe_fdir_filter *rule; + struct hlist_node *node; + int cnt = 0; + + /* report total rule count */ + cmd->data = (1024 << TXGBE_FDIR_PBALLOC_64K) - 2; + + hlist_for_each_entry_safe(rule, node, &txgbe->fdir_filter_list, + fdir_node) { + if (cnt == cmd->rule_cnt) + return -EMSGSIZE; + rule_locs[cnt] = rule->sw_idx; + cnt++; + } + + cmd->rule_cnt = cnt; + + return 0; +} + +static int txgbe_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, + u32 *rule_locs) +{ + struct wx *wx = netdev_priv(dev); + struct txgbe *txgbe = wx->priv; + int ret = -EOPNOTSUPP; + + switch (cmd->cmd) { + case ETHTOOL_GRXRINGS: + cmd->data = wx->num_rx_queues; + ret = 0; + break; + case ETHTOOL_GRXCLSRLCNT: + cmd->rule_cnt = txgbe->fdir_filter_count; + ret = 0; + break; + case ETHTOOL_GRXCLSRULE: + ret = txgbe_get_ethtool_fdir_entry(txgbe, cmd); + break; + case ETHTOOL_GRXCLSRLALL: + ret = txgbe_get_ethtool_fdir_all(txgbe, cmd, (u32 *)rule_locs); + break; + default: + break; + } + + return ret; +} + +static int txgbe_flowspec_to_flow_type(struct ethtool_rx_flow_spec *fsp, + u8 *flow_type) +{ + switch (fsp->flow_type & ~FLOW_EXT) { + case TCP_V4_FLOW: + *flow_type = TXGBE_ATR_FLOW_TYPE_TCPV4; + break; + case UDP_V4_FLOW: + *flow_type = TXGBE_ATR_FLOW_TYPE_UDPV4; + break; + case SCTP_V4_FLOW: + *flow_type = TXGBE_ATR_FLOW_TYPE_SCTPV4; + break; + case IP_USER_FLOW: + switch (fsp->h_u.usr_ip4_spec.proto) { + case IPPROTO_TCP: + *flow_type = TXGBE_ATR_FLOW_TYPE_TCPV4; + break; + case IPPROTO_UDP: + *flow_type = TXGBE_ATR_FLOW_TYPE_UDPV4; + break; + case IPPROTO_SCTP: + *flow_type = TXGBE_ATR_FLOW_TYPE_SCTPV4; + break; + case 0: + if (!fsp->m_u.usr_ip4_spec.proto) { + *flow_type = TXGBE_ATR_FLOW_TYPE_IPV4; + break; + } + fallthrough; + default: + return -EINVAL; + } + break; + default: + return -EINVAL; + } + + return 0; +} + +static bool txgbe_match_ethtool_fdir_entry(struct txgbe *txgbe, + struct txgbe_fdir_filter *input) +{ + struct txgbe_fdir_filter *rule = NULL; + struct hlist_node *node2; + + hlist_for_each_entry_safe(rule, node2, &txgbe->fdir_filter_list, + fdir_node) { + if (rule->filter.formatted.bkt_hash == + input->filter.formatted.bkt_hash && + rule->action == input->action) { + wx_dbg(txgbe->wx, "FDIR entry already exist\n"); + return true; + } + } + return false; +} + +static int txgbe_update_ethtool_fdir_entry(struct txgbe *txgbe, + struct txgbe_fdir_filter *input, + u16 sw_idx) +{ + struct hlist_node *node = NULL, *parent = NULL; + struct txgbe_fdir_filter *rule; + struct wx *wx = txgbe->wx; + bool deleted = false; + int err; + + hlist_for_each_entry_safe(rule, node, &txgbe->fdir_filter_list, + fdir_node) { + /* hash found, or no matching entry */ + if (rule->sw_idx >= sw_idx) + break; + parent = node; + } + + /* if there is an old rule occupying our place remove it */ + if (rule && rule->sw_idx == sw_idx) { + /* hardware filters are only configured when interface is up, + * and we should not issue filter commands while the interface + * is down + */ + if (netif_running(wx->netdev) && + (!input || rule->filter.formatted.bkt_hash != + input->filter.formatted.bkt_hash)) { + err = txgbe_fdir_erase_perfect_filter(wx, + &rule->filter, + sw_idx); + if (err) + return -EINVAL; + } + + hlist_del(&rule->fdir_node); + kfree(rule); + txgbe->fdir_filter_count--; + deleted = true; + } + + /* If we weren't given an input, then this was a request to delete a + * filter. We should return -EINVAL if the filter wasn't found, but + * return 0 if the rule was successfully deleted. + */ + if (!input) + return deleted ? 0 : -EINVAL; + + /* initialize node and set software index */ + INIT_HLIST_NODE(&input->fdir_node); + + /* add filter to the list */ + if (parent) + hlist_add_behind(&input->fdir_node, parent); + else + hlist_add_head(&input->fdir_node, + &txgbe->fdir_filter_list); + + /* update counts */ + txgbe->fdir_filter_count++; + + return 0; +} + +static int txgbe_add_ethtool_fdir_entry(struct txgbe *txgbe, + struct ethtool_rxnfc *cmd) +{ + struct ethtool_rx_flow_spec *fsp = + (struct ethtool_rx_flow_spec *)&cmd->fs; + struct txgbe_fdir_filter *input; + union txgbe_atr_input mask; + struct wx *wx = txgbe->wx; + int err = -EINVAL; + u16 ptype = 0; + u8 queue; + + if (!(test_bit(WX_FLAG_FDIR_PERFECT, wx->flags))) + return -EOPNOTSUPP; + + /* ring_cookie is a masked into a set of queues and txgbe pools or + * we use drop index + */ + if (fsp->ring_cookie == RX_CLS_FLOW_DISC) { + queue = TXGBE_RDB_FDIR_DROP_QUEUE; + } else { + u32 ring = ethtool_get_flow_spec_ring(fsp->ring_cookie); + + if (ring >= wx->num_rx_queues) + return -EINVAL; + + /* Map the ring onto the absolute queue index */ + queue = wx->rx_ring[ring]->reg_idx; + } + + /* Don't allow indexes to exist outside of available space */ + if (fsp->location >= ((1024 << TXGBE_FDIR_PBALLOC_64K) - 2)) { + wx_err(wx, "Location out of range\n"); + return -EINVAL; + } + + input = kzalloc(sizeof(*input), GFP_ATOMIC); + if (!input) + return -ENOMEM; + + memset(&mask, 0, sizeof(union txgbe_atr_input)); + + /* set SW index */ + input->sw_idx = fsp->location; + + /* record flow type */ + if (txgbe_flowspec_to_flow_type(fsp, + &input->filter.formatted.flow_type)) { + wx_err(wx, "Unrecognized flow type\n"); + goto err_out; + } + + mask.formatted.flow_type = TXGBE_ATR_L4TYPE_IPV6_MASK | + TXGBE_ATR_L4TYPE_MASK; + + if (input->filter.formatted.flow_type == TXGBE_ATR_FLOW_TYPE_IPV4) + mask.formatted.flow_type &= TXGBE_ATR_L4TYPE_IPV6_MASK; + + /* Copy input into formatted structures */ + input->filter.formatted.src_ip[0] = fsp->h_u.tcp_ip4_spec.ip4src; + mask.formatted.src_ip[0] = fsp->m_u.tcp_ip4_spec.ip4src; + input->filter.formatted.dst_ip[0] = fsp->h_u.tcp_ip4_spec.ip4dst; + mask.formatted.dst_ip[0] = fsp->m_u.tcp_ip4_spec.ip4dst; + input->filter.formatted.src_port = fsp->h_u.tcp_ip4_spec.psrc; + mask.formatted.src_port = fsp->m_u.tcp_ip4_spec.psrc; + input->filter.formatted.dst_port = fsp->h_u.tcp_ip4_spec.pdst; + mask.formatted.dst_port = fsp->m_u.tcp_ip4_spec.pdst; + + if (fsp->flow_type & FLOW_EXT) { + input->filter.formatted.vm_pool = + (unsigned char)ntohl(fsp->h_ext.data[1]); + mask.formatted.vm_pool = + (unsigned char)ntohl(fsp->m_ext.data[1]); + input->filter.formatted.flex_bytes = + fsp->h_ext.vlan_etype; + mask.formatted.flex_bytes = fsp->m_ext.vlan_etype; + } + + switch (input->filter.formatted.flow_type) { + case TXGBE_ATR_FLOW_TYPE_TCPV4: + ptype = WX_PTYPE_L2_IPV4_TCP; + break; + case TXGBE_ATR_FLOW_TYPE_UDPV4: + ptype = WX_PTYPE_L2_IPV4_UDP; + break; + case TXGBE_ATR_FLOW_TYPE_SCTPV4: + ptype = WX_PTYPE_L2_IPV4_SCTP; + break; + case TXGBE_ATR_FLOW_TYPE_IPV4: + ptype = WX_PTYPE_L2_IPV4; + break; + default: + break; + } + + input->filter.formatted.vlan_id = htons(ptype); + if (mask.formatted.flow_type & TXGBE_ATR_L4TYPE_MASK) + mask.formatted.vlan_id = htons(0xFFFF); + else + mask.formatted.vlan_id = htons(0xFFF8); + + /* determine if we need to drop or route the packet */ + if (fsp->ring_cookie == RX_CLS_FLOW_DISC) + input->action = TXGBE_RDB_FDIR_DROP_QUEUE; + else + input->action = fsp->ring_cookie; + + spin_lock(&txgbe->fdir_perfect_lock); + + if (hlist_empty(&txgbe->fdir_filter_list)) { + /* save mask and program input mask into HW */ + memcpy(&txgbe->fdir_mask, &mask, sizeof(mask)); + err = txgbe_fdir_set_input_mask(wx, &mask); + if (err) + goto err_unlock; + } else if (memcmp(&txgbe->fdir_mask, &mask, sizeof(mask))) { + wx_err(wx, "Hardware only supports one mask per port. To change the mask you must first delete all the rules.\n"); + goto err_unlock; + } + + /* apply mask and compute/store hash */ + txgbe_atr_compute_perfect_hash(&input->filter, &mask); + + /* check if new entry does not exist on filter list */ + if (txgbe_match_ethtool_fdir_entry(txgbe, input)) + goto err_unlock; + + /* only program filters to hardware if the net device is running, as + * we store the filters in the Rx buffer which is not allocated when + * the device is down + */ + if (netif_running(wx->netdev)) { + err = txgbe_fdir_write_perfect_filter(wx, &input->filter, + input->sw_idx, queue); + if (err) + goto err_unlock; + } + + txgbe_update_ethtool_fdir_entry(txgbe, input, input->sw_idx); + + spin_unlock(&txgbe->fdir_perfect_lock); + + return 0; +err_unlock: + spin_unlock(&txgbe->fdir_perfect_lock); +err_out: + kfree(input); + return err; +} + +static int txgbe_del_ethtool_fdir_entry(struct txgbe *txgbe, + struct ethtool_rxnfc *cmd) +{ + struct ethtool_rx_flow_spec *fsp = + (struct ethtool_rx_flow_spec *)&cmd->fs; + int err = 0; + + spin_lock(&txgbe->fdir_perfect_lock); + err = txgbe_update_ethtool_fdir_entry(txgbe, NULL, fsp->location); + spin_unlock(&txgbe->fdir_perfect_lock); + + return err; +} + +static int txgbe_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) +{ + struct wx *wx = netdev_priv(dev); + struct txgbe *txgbe = wx->priv; + int ret = -EOPNOTSUPP; + + switch (cmd->cmd) { + case ETHTOOL_SRXCLSRLINS: + ret = txgbe_add_ethtool_fdir_entry(txgbe, cmd); + break; + case ETHTOOL_SRXCLSRLDEL: + ret = txgbe_del_ethtool_fdir_entry(txgbe, cmd); + break; + default: + break; + } + + return ret; +} + static const struct ethtool_ops txgbe_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_TX_MAX_FRAMES_IRQ, @@ -100,6 +525,8 @@ static const struct ethtool_ops txgbe_ethtool_ops = { .set_coalesce = wx_set_coalesce, .get_channels = wx_get_channels, .set_channels = txgbe_set_channels, + .get_rxnfc = txgbe_get_rxnfc, + .set_rxnfc = txgbe_set_rxnfc, .get_msglevel = wx_get_msglevel, .set_msglevel = wx_set_msglevel, }; diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_fdir.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_fdir.c new file mode 100644 index 000000000000..ef50efbaec0f --- /dev/null +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_fdir.c @@ -0,0 +1,643 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2015 - 2024 Beijing WangXun Technology Co., Ltd. */ + +#include <linux/string.h> +#include <linux/types.h> +#include <linux/pci.h> + +#include "../libwx/wx_type.h" +#include "../libwx/wx_lib.h" +#include "../libwx/wx_hw.h" +#include "txgbe_type.h" +#include "txgbe_fdir.h" + +/* These defines allow us to quickly generate all of the necessary instructions + * in the function below by simply calling out TXGBE_COMPUTE_SIG_HASH_ITERATION + * for values 0 through 15 + */ +#define TXGBE_ATR_COMMON_HASH_KEY \ + (TXGBE_ATR_BUCKET_HASH_KEY & TXGBE_ATR_SIGNATURE_HASH_KEY) +#define TXGBE_COMPUTE_SIG_HASH_ITERATION(_n) \ +do { \ + u32 n = (_n); \ + if (TXGBE_ATR_COMMON_HASH_KEY & (0x01 << n)) \ + common_hash ^= lo_hash_dword >> n; \ + else if (TXGBE_ATR_BUCKET_HASH_KEY & (0x01 << n)) \ + bucket_hash ^= lo_hash_dword >> n; \ + else if (TXGBE_ATR_SIGNATURE_HASH_KEY & (0x01 << n)) \ + sig_hash ^= lo_hash_dword << (16 - n); \ + if (TXGBE_ATR_COMMON_HASH_KEY & (0x01 << (n + 16))) \ + common_hash ^= hi_hash_dword >> n; \ + else if (TXGBE_ATR_BUCKET_HASH_KEY & (0x01 << (n + 16))) \ + bucket_hash ^= hi_hash_dword >> n; \ + else if (TXGBE_ATR_SIGNATURE_HASH_KEY & (0x01 << (n + 16))) \ + sig_hash ^= hi_hash_dword << (16 - n); \ +} while (0) + +/** + * txgbe_atr_compute_sig_hash - Compute the signature hash + * @input: input bitstream to compute the hash on + * @common: compressed common input dword + * @hash: pointer to the computed hash + * + * This function is almost identical to the function above but contains + * several optimizations such as unwinding all of the loops, letting the + * compiler work out all of the conditional ifs since the keys are static + * defines, and computing two keys at once since the hashed dword stream + * will be the same for both keys. + **/ +static void txgbe_atr_compute_sig_hash(union txgbe_atr_hash_dword input, + union txgbe_atr_hash_dword common, + u32 *hash) +{ + u32 sig_hash = 0, bucket_hash = 0, common_hash = 0; + u32 hi_hash_dword, lo_hash_dword, flow_vm_vlan; + u32 i; + + /* record the flow_vm_vlan bits as they are a key part to the hash */ + flow_vm_vlan = ntohl(input.dword); + + /* generate common hash dword */ + hi_hash_dword = ntohl(common.dword); + + /* low dword is word swapped version of common */ + lo_hash_dword = (hi_hash_dword >> 16) | (hi_hash_dword << 16); + + /* apply flow ID/VM pool/VLAN ID bits to hash words */ + hi_hash_dword ^= flow_vm_vlan ^ (flow_vm_vlan >> 16); + + /* Process bits 0 and 16 */ + TXGBE_COMPUTE_SIG_HASH_ITERATION(0); + + /* apply flow ID/VM pool/VLAN ID bits to lo hash dword, we had to + * delay this because bit 0 of the stream should not be processed + * so we do not add the VLAN until after bit 0 was processed + */ + lo_hash_dword ^= flow_vm_vlan ^ (flow_vm_vlan << 16); + + /* Process remaining 30 bit of the key */ + for (i = 1; i <= 15; i++) + TXGBE_COMPUTE_SIG_HASH_ITERATION(i); + + /* combine common_hash result with signature and bucket hashes */ + bucket_hash ^= common_hash; + bucket_hash &= TXGBE_ATR_HASH_MASK; + + sig_hash ^= common_hash << 16; + sig_hash &= TXGBE_ATR_HASH_MASK << 16; + + /* return completed signature hash */ + *hash = sig_hash ^ bucket_hash; +} + +#define TXGBE_COMPUTE_BKT_HASH_ITERATION(_n) \ +do { \ + u32 n = (_n); \ + if (TXGBE_ATR_BUCKET_HASH_KEY & (0x01 << n)) \ + bucket_hash ^= lo_hash_dword >> n; \ + if (TXGBE_ATR_BUCKET_HASH_KEY & (0x01 << (n + 16))) \ + bucket_hash ^= hi_hash_dword >> n; \ +} while (0) + +/** + * txgbe_atr_compute_perfect_hash - Compute the perfect filter hash + * @input: input bitstream to compute the hash on + * @input_mask: mask for the input bitstream + * + * This function serves two main purposes. First it applies the input_mask + * to the atr_input resulting in a cleaned up atr_input data stream. + * Secondly it computes the hash and stores it in the bkt_hash field at + * the end of the input byte stream. This way it will be available for + * future use without needing to recompute the hash. + **/ +void txgbe_atr_compute_perfect_hash(union txgbe_atr_input *input, + union txgbe_atr_input *input_mask) +{ + u32 hi_hash_dword, lo_hash_dword, flow_vm_vlan; + u32 bucket_hash = 0; + __be32 hi_dword = 0; + u32 i = 0; + + /* Apply masks to input data */ + for (i = 0; i < 11; i++) + input->dword_stream[i] &= input_mask->dword_stream[i]; + + /* record the flow_vm_vlan bits as they are a key part to the hash */ + flow_vm_vlan = ntohl(input->dword_stream[0]); + + /* generate common hash dword */ + for (i = 1; i <= 10; i++) + hi_dword ^= input->dword_stream[i]; + hi_hash_dword = ntohl(hi_dword); + + /* low dword is word swapped version of common */ + lo_hash_dword = (hi_hash_dword >> 16) | (hi_hash_dword << 16); + + /* apply flow ID/VM pool/VLAN ID bits to hash words */ + hi_hash_dword ^= flow_vm_vlan ^ (flow_vm_vlan >> 16); + + /* Process bits 0 and 16 */ + TXGBE_COMPUTE_BKT_HASH_ITERATION(0); + + /* apply flow ID/VM pool/VLAN ID bits to lo hash dword, we had to + * delay this because bit 0 of the stream should not be processed + * so we do not add the VLAN until after bit 0 was processed + */ + lo_hash_dword ^= flow_vm_vlan ^ (flow_vm_vlan << 16); + + /* Process remaining 30 bit of the key */ + for (i = 1; i <= 15; i++) + TXGBE_COMPUTE_BKT_HASH_ITERATION(i); + + /* Limit hash to 13 bits since max bucket count is 8K. + * Store result at the end of the input stream. + */ + input->formatted.bkt_hash = (__force __be16)(bucket_hash & 0x1FFF); +} + +static int txgbe_fdir_check_cmd_complete(struct wx *wx) +{ + u32 val; + + return read_poll_timeout_atomic(rd32, val, + !(val & TXGBE_RDB_FDIR_CMD_CMD_MASK), + 10, 100, false, + wx, TXGBE_RDB_FDIR_CMD); +} + +/** + * txgbe_fdir_add_signature_filter - Adds a signature hash filter + * @wx: pointer to hardware structure + * @input: unique input dword + * @common: compressed common input dword + * @queue: queue index to direct traffic to + * + * @return: 0 on success and negative on failure + **/ +static int txgbe_fdir_add_signature_filter(struct wx *wx, + union txgbe_atr_hash_dword input, + union txgbe_atr_hash_dword common, + u8 queue) +{ + u32 fdirhashcmd, fdircmd; + u8 flow_type; + int err; + + /* Get the flow_type in order to program FDIRCMD properly + * lowest 2 bits are FDIRCMD.L4TYPE, third lowest bit is FDIRCMD.IPV6 + * fifth is FDIRCMD.TUNNEL_FILTER + */ + flow_type = input.formatted.flow_type; + switch (flow_type) { + case TXGBE_ATR_FLOW_TYPE_TCPV4: + case TXGBE_ATR_FLOW_TYPE_UDPV4: + case TXGBE_ATR_FLOW_TYPE_SCTPV4: + case TXGBE_ATR_FLOW_TYPE_TCPV6: + case TXGBE_ATR_FLOW_TYPE_UDPV6: + case TXGBE_ATR_FLOW_TYPE_SCTPV6: + break; + default: + wx_err(wx, "Error on flow type input\n"); + return -EINVAL; + } + + /* configure FDIRCMD register */ + fdircmd = TXGBE_RDB_FDIR_CMD_CMD_ADD_FLOW | + TXGBE_RDB_FDIR_CMD_FILTER_UPDATE | + TXGBE_RDB_FDIR_CMD_LAST | TXGBE_RDB_FDIR_CMD_QUEUE_EN; + fdircmd |= TXGBE_RDB_FDIR_CMD_FLOW_TYPE(flow_type); + fdircmd |= TXGBE_RDB_FDIR_CMD_RX_QUEUE(queue); + + txgbe_atr_compute_sig_hash(input, common, &fdirhashcmd); + fdirhashcmd |= TXGBE_RDB_FDIR_HASH_BUCKET_VALID; + wr32(wx, TXGBE_RDB_FDIR_HASH, fdirhashcmd); + wr32(wx, TXGBE_RDB_FDIR_CMD, fdircmd); + + wx_dbg(wx, "Tx Queue=%x hash=%x\n", queue, (u32)fdirhashcmd); + + err = txgbe_fdir_check_cmd_complete(wx); + if (err) + wx_err(wx, "Flow Director command did not complete!\n"); + + return err; +} + +void txgbe_atr(struct wx_ring *ring, struct wx_tx_buffer *first, u8 ptype) +{ + union txgbe_atr_hash_dword common = { .dword = 0 }; + union txgbe_atr_hash_dword input = { .dword = 0 }; + struct wx_q_vector *q_vector = ring->q_vector; + struct wx_dec_ptype dptype; + union network_header { + struct ipv6hdr *ipv6; + struct iphdr *ipv4; + void *raw; + } hdr; + struct tcphdr *th; + + /* if ring doesn't have a interrupt vector, cannot perform ATR */ + if (!q_vector) + return; + + ring->atr_count++; + dptype = wx_decode_ptype(ptype); + if (dptype.etype) { + if (WX_PTYPE_TYPL4(ptype) != WX_PTYPE_TYP_TCP) + return; + hdr.raw = (void *)skb_inner_network_header(first->skb); + th = inner_tcp_hdr(first->skb); + } else { + if (WX_PTYPE_PKT(ptype) != WX_PTYPE_PKT_IP || + WX_PTYPE_TYPL4(ptype) != WX_PTYPE_TYP_TCP) + return; + hdr.raw = (void *)skb_network_header(first->skb); + th = tcp_hdr(first->skb); + } + + /* skip this packet since it is invalid or the socket is closing */ + if (!th || th->fin) + return; + + /* sample on all syn packets or once every atr sample count */ + if (!th->syn && ring->atr_count < ring->atr_sample_rate) + return; + + /* reset sample count */ + ring->atr_count = 0; + + /* src and dst are inverted, think how the receiver sees them + * + * The input is broken into two sections, a non-compressed section + * containing vm_pool, vlan_id, and flow_type. The rest of the data + * is XORed together and stored in the compressed dword. + */ + input.formatted.vlan_id = htons((u16)ptype); + + /* since src port and flex bytes occupy the same word XOR them together + * and write the value to source port portion of compressed dword + */ + if (first->tx_flags & WX_TX_FLAGS_SW_VLAN) + common.port.src ^= th->dest ^ first->skb->protocol; + else if (first->tx_flags & WX_TX_FLAGS_HW_VLAN) + common.port.src ^= th->dest ^ first->skb->vlan_proto; + else + common.port.src ^= th->dest ^ first->protocol; + common.port.dst ^= th->source; + + if (WX_PTYPE_PKT_IPV6 & WX_PTYPE_PKT(ptype)) { + input.formatted.flow_type = TXGBE_ATR_FLOW_TYPE_TCPV6; + common.ip ^= hdr.ipv6->saddr.s6_addr32[0] ^ + hdr.ipv6->saddr.s6_addr32[1] ^ + hdr.ipv6->saddr.s6_addr32[2] ^ + hdr.ipv6->saddr.s6_addr32[3] ^ + hdr.ipv6->daddr.s6_addr32[0] ^ + hdr.ipv6->daddr.s6_addr32[1] ^ + hdr.ipv6->daddr.s6_addr32[2] ^ + hdr.ipv6->daddr.s6_addr32[3]; + } else { + input.formatted.flow_type = TXGBE_ATR_FLOW_TYPE_TCPV4; + common.ip ^= hdr.ipv4->saddr ^ hdr.ipv4->daddr; + } + + /* This assumes the Rx queue and Tx queue are bound to the same CPU */ + txgbe_fdir_add_signature_filter(q_vector->wx, input, common, + ring->queue_index); +} + +int txgbe_fdir_set_input_mask(struct wx *wx, union txgbe_atr_input *input_mask) +{ + u32 fdirm = 0, fdirtcpm = 0, flex = 0; + + /* Program the relevant mask registers. If src/dst_port or src/dst_addr + * are zero, then assume a full mask for that field. Also assume that + * a VLAN of 0 is unspecified, so mask that out as well. L4type + * cannot be masked out in this implementation. + * + * This also assumes IPv4 only. IPv6 masking isn't supported at this + * point in time. + */ + + /* verify bucket hash is cleared on hash generation */ + if (input_mask->formatted.bkt_hash) + wx_dbg(wx, "bucket hash should always be 0 in mask\n"); + + /* Program FDIRM and verify partial masks */ + switch (input_mask->formatted.vm_pool & 0x7F) { + case 0x0: + fdirm |= TXGBE_RDB_FDIR_OTHER_MSK_POOL; + break; + case 0x7F: + break; + default: + wx_err(wx, "Error on vm pool mask\n"); + return -EINVAL; + } + + switch (input_mask->formatted.flow_type & TXGBE_ATR_L4TYPE_MASK) { + case 0x0: + fdirm |= TXGBE_RDB_FDIR_OTHER_MSK_L4P; + if (input_mask->formatted.dst_port || + input_mask->formatted.src_port) { + wx_err(wx, "Error on src/dst port mask\n"); + return -EINVAL; + } + break; + case TXGBE_ATR_L4TYPE_MASK: + break; + default: + wx_err(wx, "Error on flow type mask\n"); + return -EINVAL; + } + + /* Now mask VM pool and destination IPv6 - bits 5 and 2 */ + wr32(wx, TXGBE_RDB_FDIR_OTHER_MSK, fdirm); + + flex = rd32(wx, TXGBE_RDB_FDIR_FLEX_CFG(0)); + flex &= ~TXGBE_RDB_FDIR_FLEX_CFG_FIELD0; + flex |= (TXGBE_RDB_FDIR_FLEX_CFG_BASE_MAC | + TXGBE_RDB_FDIR_FLEX_CFG_OFST(0x6)); + + switch ((__force u16)input_mask->formatted.flex_bytes & 0xFFFF) { + case 0x0000: + /* Mask Flex Bytes */ + flex |= TXGBE_RDB_FDIR_FLEX_CFG_MSK; + break; + case 0xFFFF: + break; + default: + wx_err(wx, "Error on flexible byte mask\n"); + return -EINVAL; + } + wr32(wx, TXGBE_RDB_FDIR_FLEX_CFG(0), flex); + + /* store the TCP/UDP port masks, bit reversed from port layout */ + fdirtcpm = ntohs(input_mask->formatted.dst_port); + fdirtcpm <<= TXGBE_RDB_FDIR_PORT_DESTINATION_SHIFT; + fdirtcpm |= ntohs(input_mask->formatted.src_port); + + /* write both the same so that UDP and TCP use the same mask */ + wr32(wx, TXGBE_RDB_FDIR_TCP_MSK, ~fdirtcpm); + wr32(wx, TXGBE_RDB_FDIR_UDP_MSK, ~fdirtcpm); + wr32(wx, TXGBE_RDB_FDIR_SCTP_MSK, ~fdirtcpm); + + /* store source and destination IP masks (little-enian) */ + wr32(wx, TXGBE_RDB_FDIR_SA4_MSK, + ntohl(~input_mask->formatted.src_ip[0])); + wr32(wx, TXGBE_RDB_FDIR_DA4_MSK, + ntohl(~input_mask->formatted.dst_ip[0])); + + return 0; +} + +int txgbe_fdir_write_perfect_filter(struct wx *wx, + union txgbe_atr_input *input, + u16 soft_id, u8 queue) +{ + u32 fdirport, fdirvlan, fdirhash, fdircmd; + int err = 0; + + /* currently IPv6 is not supported, must be programmed with 0 */ + wr32(wx, TXGBE_RDB_FDIR_IP6(2), ntohl(input->formatted.src_ip[0])); + wr32(wx, TXGBE_RDB_FDIR_IP6(1), ntohl(input->formatted.src_ip[1])); + wr32(wx, TXGBE_RDB_FDIR_IP6(0), ntohl(input->formatted.src_ip[2])); + + /* record the source address (little-endian) */ + wr32(wx, TXGBE_RDB_FDIR_SA, ntohl(input->formatted.src_ip[0])); + + /* record the first 32 bits of the destination address + * (little-endian) + */ + wr32(wx, TXGBE_RDB_FDIR_DA, ntohl(input->formatted.dst_ip[0])); + + /* record source and destination port (little-endian)*/ + fdirport = ntohs(input->formatted.dst_port); + fdirport <<= TXGBE_RDB_FDIR_PORT_DESTINATION_SHIFT; + fdirport |= ntohs(input->formatted.src_port); + wr32(wx, TXGBE_RDB_FDIR_PORT, fdirport); + + /* record packet type and flex_bytes (little-endian) */ + fdirvlan = ntohs(input->formatted.flex_bytes); + fdirvlan <<= TXGBE_RDB_FDIR_FLEX_FLEX_SHIFT; + fdirvlan |= ntohs(input->formatted.vlan_id); + wr32(wx, TXGBE_RDB_FDIR_FLEX, fdirvlan); + + /* configure FDIRHASH register */ + fdirhash = (__force u32)input->formatted.bkt_hash | + TXGBE_RDB_FDIR_HASH_BUCKET_VALID | + TXGBE_RDB_FDIR_HASH_SIG_SW_INDEX(soft_id); + wr32(wx, TXGBE_RDB_FDIR_HASH, fdirhash); + + /* flush all previous writes to make certain registers are + * programmed prior to issuing the command + */ + WX_WRITE_FLUSH(wx); + + /* configure FDIRCMD register */ + fdircmd = TXGBE_RDB_FDIR_CMD_CMD_ADD_FLOW | + TXGBE_RDB_FDIR_CMD_FILTER_UPDATE | + TXGBE_RDB_FDIR_CMD_LAST | TXGBE_RDB_FDIR_CMD_QUEUE_EN; + if (queue == TXGBE_RDB_FDIR_DROP_QUEUE) + fdircmd |= TXGBE_RDB_FDIR_CMD_DROP; + fdircmd |= TXGBE_RDB_FDIR_CMD_FLOW_TYPE(input->formatted.flow_type); + fdircmd |= TXGBE_RDB_FDIR_CMD_RX_QUEUE(queue); + fdircmd |= TXGBE_RDB_FDIR_CMD_VT_POOL(input->formatted.vm_pool); + + wr32(wx, TXGBE_RDB_FDIR_CMD, fdircmd); + err = txgbe_fdir_check_cmd_complete(wx); + if (err) + wx_err(wx, "Flow Director command did not complete!\n"); + + return err; +} + +int txgbe_fdir_erase_perfect_filter(struct wx *wx, + union txgbe_atr_input *input, + u16 soft_id) +{ + u32 fdirhash, fdircmd; + int err = 0; + + /* configure FDIRHASH register */ + fdirhash = (__force u32)input->formatted.bkt_hash; + fdirhash |= TXGBE_RDB_FDIR_HASH_SIG_SW_INDEX(soft_id); + wr32(wx, TXGBE_RDB_FDIR_HASH, fdirhash); + + /* flush hash to HW */ + WX_WRITE_FLUSH(wx); + + /* Query if filter is present */ + wr32(wx, TXGBE_RDB_FDIR_CMD, TXGBE_RDB_FDIR_CMD_CMD_QUERY_REM_FILT); + + err = txgbe_fdir_check_cmd_complete(wx); + if (err) { + wx_err(wx, "Flow Director command did not complete!\n"); + return err; + } + + fdircmd = rd32(wx, TXGBE_RDB_FDIR_CMD); + /* if filter exists in hardware then remove it */ + if (fdircmd & TXGBE_RDB_FDIR_CMD_FILTER_VALID) { + wr32(wx, TXGBE_RDB_FDIR_HASH, fdirhash); + WX_WRITE_FLUSH(wx); + wr32(wx, TXGBE_RDB_FDIR_CMD, + TXGBE_RDB_FDIR_CMD_CMD_REMOVE_FLOW); + } + + return 0; +} + +/** + * txgbe_fdir_enable - Initialize Flow Director control registers + * @wx: pointer to hardware structure + * @fdirctrl: value to write to flow director control register + **/ +static void txgbe_fdir_enable(struct wx *wx, u32 fdirctrl) +{ + u32 val; + int ret; + + /* Prime the keys for hashing */ + wr32(wx, TXGBE_RDB_FDIR_HKEY, TXGBE_ATR_BUCKET_HASH_KEY); + wr32(wx, TXGBE_RDB_FDIR_SKEY, TXGBE_ATR_SIGNATURE_HASH_KEY); + + wr32(wx, TXGBE_RDB_FDIR_CTL, fdirctrl); + WX_WRITE_FLUSH(wx); + ret = read_poll_timeout(rd32, val, val & TXGBE_RDB_FDIR_CTL_INIT_DONE, + 1000, 10000, false, wx, TXGBE_RDB_FDIR_CTL); + + if (ret < 0) + wx_dbg(wx, "Flow Director poll time exceeded!\n"); +} + +/** + * txgbe_init_fdir_signature -Initialize Flow Director sig filters + * @wx: pointer to hardware structure + **/ +static void txgbe_init_fdir_signature(struct wx *wx) +{ + u32 fdirctrl = TXGBE_FDIR_PBALLOC_64K; + u32 flex = 0; + + flex = rd32(wx, TXGBE_RDB_FDIR_FLEX_CFG(0)); + flex &= ~TXGBE_RDB_FDIR_FLEX_CFG_FIELD0; + + flex |= (TXGBE_RDB_FDIR_FLEX_CFG_BASE_MAC | + TXGBE_RDB_FDIR_FLEX_CFG_OFST(0x6)); + wr32(wx, TXGBE_RDB_FDIR_FLEX_CFG(0), flex); + + /* Continue setup of fdirctrl register bits: + * Move the flexible bytes to use the ethertype - shift 6 words + * Set the maximum length per hash bucket to 0xA filters + * Send interrupt when 64 filters are left + */ + fdirctrl |= TXGBE_RDB_FDIR_CTL_HASH_BITS(0xF) | + TXGBE_RDB_FDIR_CTL_MAX_LENGTH(0xA) | + TXGBE_RDB_FDIR_CTL_FULL_THRESH(4); + + /* write hashes and fdirctrl register, poll for completion */ + txgbe_fdir_enable(wx, fdirctrl); +} + +/** + * txgbe_init_fdir_perfect - Initialize Flow Director perfect filters + * @wx: pointer to hardware structure + **/ +static void txgbe_init_fdir_perfect(struct wx *wx) +{ + u32 fdirctrl = TXGBE_FDIR_PBALLOC_64K; + + /* Continue setup of fdirctrl register bits: + * Turn perfect match filtering on + * Report hash in RSS field of Rx wb descriptor + * Initialize the drop queue + * Move the flexible bytes to use the ethertype - shift 6 words + * Set the maximum length per hash bucket to 0xA filters + * Send interrupt when 64 (0x4 * 16) filters are left + */ + fdirctrl |= TXGBE_RDB_FDIR_CTL_PERFECT_MATCH | + TXGBE_RDB_FDIR_CTL_DROP_Q(TXGBE_RDB_FDIR_DROP_QUEUE) | + TXGBE_RDB_FDIR_CTL_HASH_BITS(0xF) | + TXGBE_RDB_FDIR_CTL_MAX_LENGTH(0xA) | + TXGBE_RDB_FDIR_CTL_FULL_THRESH(4); + + /* write hashes and fdirctrl register, poll for completion */ + txgbe_fdir_enable(wx, fdirctrl); +} + +static void txgbe_fdir_filter_restore(struct wx *wx) +{ + struct txgbe_fdir_filter *filter; + struct txgbe *txgbe = wx->priv; + struct hlist_node *node; + u8 queue = 0; + int ret = 0; + + spin_lock(&txgbe->fdir_perfect_lock); + + if (!hlist_empty(&txgbe->fdir_filter_list)) + ret = txgbe_fdir_set_input_mask(wx, &txgbe->fdir_mask); + + if (ret) + goto unlock; + + hlist_for_each_entry_safe(filter, node, + &txgbe->fdir_filter_list, fdir_node) { + if (filter->action == TXGBE_RDB_FDIR_DROP_QUEUE) { + queue = TXGBE_RDB_FDIR_DROP_QUEUE; + } else { + u32 ring = ethtool_get_flow_spec_ring(filter->action); + + if (ring >= wx->num_rx_queues) { + wx_err(wx, "FDIR restore failed, ring:%u\n", + ring); + continue; + } + + /* Map the ring onto the absolute queue index */ + queue = wx->rx_ring[ring]->reg_idx; + } + + ret = txgbe_fdir_write_perfect_filter(wx, + &filter->filter, + filter->sw_idx, + queue); + if (ret) + wx_err(wx, "FDIR restore failed, index:%u\n", + filter->sw_idx); + } + +unlock: + spin_unlock(&txgbe->fdir_perfect_lock); +} + +void txgbe_configure_fdir(struct wx *wx) +{ + wx_disable_sec_rx_path(wx); + + if (test_bit(WX_FLAG_FDIR_HASH, wx->flags)) { + txgbe_init_fdir_signature(wx); + } else if (test_bit(WX_FLAG_FDIR_PERFECT, wx->flags)) { + txgbe_init_fdir_perfect(wx); + txgbe_fdir_filter_restore(wx); + } + + wx_enable_sec_rx_path(wx); +} + +void txgbe_fdir_filter_exit(struct wx *wx) +{ + struct txgbe_fdir_filter *filter; + struct txgbe *txgbe = wx->priv; + struct hlist_node *node; + + spin_lock(&txgbe->fdir_perfect_lock); + + hlist_for_each_entry_safe(filter, node, + &txgbe->fdir_filter_list, fdir_node) { + hlist_del(&filter->fdir_node); + kfree(filter); + } + txgbe->fdir_filter_count = 0; + + spin_unlock(&txgbe->fdir_perfect_lock); +} diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_fdir.h b/drivers/net/ethernet/wangxun/txgbe/txgbe_fdir.h new file mode 100644 index 000000000000..1f44ce60becb --- /dev/null +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_fdir.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2015 - 2024 Beijing WangXun Technology Co., Ltd. */ + +#ifndef _TXGBE_FDIR_H_ +#define _TXGBE_FDIR_H_ + +void txgbe_atr_compute_perfect_hash(union txgbe_atr_input *input, + union txgbe_atr_input *input_mask); +void txgbe_atr(struct wx_ring *ring, struct wx_tx_buffer *first, u8 ptype); +int txgbe_fdir_set_input_mask(struct wx *wx, union txgbe_atr_input *input_mask); +int txgbe_fdir_write_perfect_filter(struct wx *wx, + union txgbe_atr_input *input, + u16 soft_id, u8 queue); +int txgbe_fdir_erase_perfect_filter(struct wx *wx, + union txgbe_atr_input *input, + u16 soft_id); +void txgbe_configure_fdir(struct wx *wx); +void txgbe_fdir_filter_exit(struct wx *wx); + +#endif /* _TXGBE_FDIR_H_ */ diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c index 8c7a74981b90..41e9ebf11e41 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c @@ -18,6 +18,7 @@ #include "txgbe_hw.h" #include "txgbe_phy.h" #include "txgbe_irq.h" +#include "txgbe_fdir.h" #include "txgbe_ethtool.h" char txgbe_driver_name[] = "txgbe"; @@ -257,6 +258,14 @@ static int txgbe_sw_init(struct wx *wx) num_online_cpus()); wx->rss_enabled = true; + wx->ring_feature[RING_F_FDIR].limit = min_t(int, TXGBE_MAX_FDIR_INDICES, + num_online_cpus()); + set_bit(WX_FLAG_FDIR_CAPABLE, wx->flags); + set_bit(WX_FLAG_FDIR_HASH, wx->flags); + wx->atr_sample_rate = TXGBE_DEFAULT_ATR_SAMPLE_RATE; + wx->atr = txgbe_atr; + wx->configure_fdir = txgbe_configure_fdir; + /* enable itr by default in dynamic mode */ wx->rx_itr_setting = 1; wx->tx_itr_setting = 1; @@ -274,6 +283,12 @@ static int txgbe_sw_init(struct wx *wx) return 0; } +static void txgbe_init_fdir(struct txgbe *txgbe) +{ + txgbe->fdir_filter_count = 0; + spin_lock_init(&txgbe->fdir_perfect_lock); +} + /** * txgbe_open - Called when a network interface is made active * @netdev: network interface device structure @@ -352,6 +367,7 @@ static int txgbe_close(struct net_device *netdev) txgbe_down(wx); wx_free_irq(wx); wx_free_resources(wx); + txgbe_fdir_filter_exit(wx); wx_control_hw(wx, false); return 0; @@ -660,6 +676,8 @@ static int txgbe_probe(struct pci_dev *pdev, txgbe->wx = wx; wx->priv = txgbe; + txgbe_init_fdir(txgbe); + err = txgbe_setup_misc_irq(txgbe); if (err) goto err_release_hw; diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h index f434a7865cb7..959102c4c379 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h @@ -89,6 +89,55 @@ #define TXGBE_XPCS_IDA_ADDR 0x13000 #define TXGBE_XPCS_IDA_DATA 0x13004 +/********************************* Flow Director *****************************/ +#define TXGBE_RDB_FDIR_DROP_QUEUE 127 +#define TXGBE_RDB_FDIR_CTL 0x19500 +#define TXGBE_RDB_FDIR_CTL_INIT_DONE BIT(3) +#define TXGBE_RDB_FDIR_CTL_PERFECT_MATCH BIT(4) +#define TXGBE_RDB_FDIR_CTL_DROP_Q(v) FIELD_PREP(GENMASK(14, 8), v) +#define TXGBE_RDB_FDIR_CTL_HASH_BITS(v) FIELD_PREP(GENMASK(23, 20), v) +#define TXGBE_RDB_FDIR_CTL_MAX_LENGTH(v) FIELD_PREP(GENMASK(27, 24), v) +#define TXGBE_RDB_FDIR_CTL_FULL_THRESH(v) FIELD_PREP(GENMASK(31, 28), v) +#define TXGBE_RDB_FDIR_IP6(_i) (0x1950C + ((_i) * 4)) /* 0-2 */ +#define TXGBE_RDB_FDIR_SA 0x19518 +#define TXGBE_RDB_FDIR_DA 0x1951C +#define TXGBE_RDB_FDIR_PORT 0x19520 +#define TXGBE_RDB_FDIR_PORT_DESTINATION_SHIFT 16 +#define TXGBE_RDB_FDIR_FLEX 0x19524 +#define TXGBE_RDB_FDIR_FLEX_FLEX_SHIFT 16 +#define TXGBE_RDB_FDIR_HASH 0x19528 +#define TXGBE_RDB_FDIR_HASH_SIG_SW_INDEX(v) FIELD_PREP(GENMASK(31, 16), v) +#define TXGBE_RDB_FDIR_HASH_BUCKET_VALID BIT(15) +#define TXGBE_RDB_FDIR_CMD 0x1952C +#define TXGBE_RDB_FDIR_CMD_CMD_MASK GENMASK(1, 0) +#define TXGBE_RDB_FDIR_CMD_CMD(v) FIELD_PREP(GENMASK(1, 0), v) +#define TXGBE_RDB_FDIR_CMD_CMD_ADD_FLOW TXGBE_RDB_FDIR_CMD_CMD(1) +#define TXGBE_RDB_FDIR_CMD_CMD_REMOVE_FLOW TXGBE_RDB_FDIR_CMD_CMD(2) +#define TXGBE_RDB_FDIR_CMD_CMD_QUERY_REM_FILT TXGBE_RDB_FDIR_CMD_CMD(3) +#define TXGBE_RDB_FDIR_CMD_FILTER_VALID BIT(2) +#define TXGBE_RDB_FDIR_CMD_FILTER_UPDATE BIT(3) +#define TXGBE_RDB_FDIR_CMD_FLOW_TYPE(v) FIELD_PREP(GENMASK(6, 5), v) +#define TXGBE_RDB_FDIR_CMD_DROP BIT(9) +#define TXGBE_RDB_FDIR_CMD_LAST BIT(11) +#define TXGBE_RDB_FDIR_CMD_QUEUE_EN BIT(15) +#define TXGBE_RDB_FDIR_CMD_RX_QUEUE(v) FIELD_PREP(GENMASK(22, 16), v) +#define TXGBE_RDB_FDIR_CMD_VT_POOL(v) FIELD_PREP(GENMASK(29, 24), v) +#define TXGBE_RDB_FDIR_DA4_MSK 0x1953C +#define TXGBE_RDB_FDIR_SA4_MSK 0x19540 +#define TXGBE_RDB_FDIR_TCP_MSK 0x19544 +#define TXGBE_RDB_FDIR_UDP_MSK 0x19548 +#define TXGBE_RDB_FDIR_SCTP_MSK 0x19560 +#define TXGBE_RDB_FDIR_HKEY 0x19568 +#define TXGBE_RDB_FDIR_SKEY 0x1956C +#define TXGBE_RDB_FDIR_OTHER_MSK 0x19570 +#define TXGBE_RDB_FDIR_OTHER_MSK_POOL BIT(2) +#define TXGBE_RDB_FDIR_OTHER_MSK_L4P BIT(3) +#define TXGBE_RDB_FDIR_FLEX_CFG(_i) (0x19580 + ((_i) * 4)) +#define TXGBE_RDB_FDIR_FLEX_CFG_FIELD0 GENMASK(7, 0) +#define TXGBE_RDB_FDIR_FLEX_CFG_BASE_MAC FIELD_PREP(GENMASK(1, 0), 0) +#define TXGBE_RDB_FDIR_FLEX_CFG_MSK BIT(2) +#define TXGBE_RDB_FDIR_FLEX_CFG_OFST(v) FIELD_PREP(GENMASK(7, 3), v) + /* Checksum and EEPROM pointers */ #define TXGBE_EEPROM_LAST_WORD 0x800 #define TXGBE_EEPROM_CHECKSUM 0x2F @@ -112,6 +161,98 @@ #define TXGBE_SP_RX_PB_SIZE 512 #define TXGBE_SP_TDB_PB_SZ (160 * 1024) /* 160KB Packet Buffer */ +#define TXGBE_DEFAULT_ATR_SAMPLE_RATE 20 + +/* Software ATR hash keys */ +#define TXGBE_ATR_BUCKET_HASH_KEY 0x3DAD14E2 +#define TXGBE_ATR_SIGNATURE_HASH_KEY 0x174D3614 + +/* Software ATR input stream values and masks */ +#define TXGBE_ATR_HASH_MASK 0x7fff +#define TXGBE_ATR_L4TYPE_MASK 0x3 +#define TXGBE_ATR_L4TYPE_UDP 0x1 +#define TXGBE_ATR_L4TYPE_TCP 0x2 +#define TXGBE_ATR_L4TYPE_SCTP 0x3 +#define TXGBE_ATR_L4TYPE_IPV6_MASK 0x4 +#define TXGBE_ATR_L4TYPE_TUNNEL_MASK 0x10 + +enum txgbe_atr_flow_type { + TXGBE_ATR_FLOW_TYPE_IPV4 = 0x0, + TXGBE_ATR_FLOW_TYPE_UDPV4 = 0x1, + TXGBE_ATR_FLOW_TYPE_TCPV4 = 0x2, + TXGBE_ATR_FLOW_TYPE_SCTPV4 = 0x3, + TXGBE_ATR_FLOW_TYPE_IPV6 = 0x4, + TXGBE_ATR_FLOW_TYPE_UDPV6 = 0x5, + TXGBE_ATR_FLOW_TYPE_TCPV6 = 0x6, + TXGBE_ATR_FLOW_TYPE_SCTPV6 = 0x7, + TXGBE_ATR_FLOW_TYPE_TUNNELED_IPV4 = 0x10, + TXGBE_ATR_FLOW_TYPE_TUNNELED_UDPV4 = 0x11, + TXGBE_ATR_FLOW_TYPE_TUNNELED_TCPV4 = 0x12, + TXGBE_ATR_FLOW_TYPE_TUNNELED_SCTPV4 = 0x13, + TXGBE_ATR_FLOW_TYPE_TUNNELED_IPV6 = 0x14, + TXGBE_ATR_FLOW_TYPE_TUNNELED_UDPV6 = 0x15, + TXGBE_ATR_FLOW_TYPE_TUNNELED_TCPV6 = 0x16, + TXGBE_ATR_FLOW_TYPE_TUNNELED_SCTPV6 = 0x17, +}; + +/* Flow Director ATR input struct. */ +union txgbe_atr_input { + /* Byte layout in order, all values with MSB first: + * + * vm_pool - 1 byte + * flow_type - 1 byte + * vlan_id - 2 bytes + * dst_ip - 16 bytes + * src_ip - 16 bytes + * src_port - 2 bytes + * dst_port - 2 bytes + * flex_bytes - 2 bytes + * bkt_hash - 2 bytes + */ + struct { + u8 vm_pool; + u8 flow_type; + __be16 vlan_id; + __be32 dst_ip[4]; + __be32 src_ip[4]; + __be16 src_port; + __be16 dst_port; + __be16 flex_bytes; + __be16 bkt_hash; + } formatted; + __be32 dword_stream[11]; +}; + +/* Flow Director compressed ATR hash input struct */ +union txgbe_atr_hash_dword { + struct { + u8 vm_pool; + u8 flow_type; + __be16 vlan_id; + } formatted; + __be32 ip; + struct { + __be16 src; + __be16 dst; + } port; + __be16 flex_bytes; + __be32 dword; +}; + +enum txgbe_fdir_pballoc_type { + TXGBE_FDIR_PBALLOC_NONE = 0, + TXGBE_FDIR_PBALLOC_64K = 1, + TXGBE_FDIR_PBALLOC_128K = 2, + TXGBE_FDIR_PBALLOC_256K = 3, +}; + +struct txgbe_fdir_filter { + struct hlist_node fdir_node; + union txgbe_atr_input filter; + u16 sw_idx; + u16 action; +}; + /* TX/RX descriptor defines */ #define TXGBE_DEFAULT_TXD 512 #define TXGBE_DEFAULT_TX_WORK 256 @@ -196,6 +337,12 @@ struct txgbe { struct gpio_chip *gpio; unsigned int gpio_irq; unsigned int link_irq; + + /* flow director */ + struct hlist_head fdir_filter_list; + union txgbe_atr_input fdir_mask; + int fdir_filter_count; + spinlock_t fdir_perfect_lock; /* spinlock for FDIR */ }; #endif /* _TXGBE_TYPE_H_ */ diff --git a/drivers/net/mdio/mdio-mscc-miim.c b/drivers/net/mdio/mdio-mscc-miim.c index c29377c85307..62c47e0dd142 100644 --- a/drivers/net/mdio/mdio-mscc-miim.c +++ b/drivers/net/mdio/mdio-mscc-miim.c @@ -19,6 +19,7 @@ #include <linux/platform_device.h> #include <linux/property.h> #include <linux/regmap.h> +#include <linux/reset.h> #define MSCC_MIIM_REG_STATUS 0x0 #define MSCC_MIIM_STATUS_STAT_PENDING BIT(2) @@ -271,10 +272,17 @@ static int mscc_miim_probe(struct platform_device *pdev) struct device_node *np = pdev->dev.of_node; struct regmap *mii_regmap, *phy_regmap; struct device *dev = &pdev->dev; + struct reset_control *reset; struct mscc_miim_dev *miim; struct mii_bus *bus; int ret; + reset = devm_reset_control_get_optional_shared(dev, "switch"); + if (IS_ERR(reset)) + return dev_err_probe(dev, PTR_ERR(reset), "Failed to get reset\n"); + + reset_control_reset(reset); + mii_regmap = ocelot_regmap_from_resource(pdev, 0, &mscc_miim_regmap_config); if (IS_ERR(mii_regmap)) diff --git a/drivers/net/phy/dp83tg720.c b/drivers/net/phy/dp83tg720.c index 326c9770a6dc..c706429b225a 100644 --- a/drivers/net/phy/dp83tg720.c +++ b/drivers/net/phy/dp83tg720.c @@ -17,6 +17,11 @@ #define DP83TG720S_PHY_RESET 0x1f #define DP83TG720S_HW_RESET BIT(15) +#define DP83TG720S_LPS_CFG3 0x18c +/* Power modes are documented as bit fields but used as values */ +/* Power Mode 0 is Normal mode */ +#define DP83TG720S_LPS_CFG3_PWR_MODE_0 BIT(0) + #define DP83TG720S_RGMII_DELAY_CTRL 0x602 /* In RGMII mode, Enable or disable the internal delay for RXD */ #define DP83TG720S_RGMII_RX_CLK_SEL BIT(1) @@ -31,11 +36,20 @@ static int dp83tg720_config_aneg(struct phy_device *phydev) { + int ret; + /* Autoneg is not supported and this PHY supports only one speed. * We need to care only about master/slave configuration if it was * changed by user. */ - return genphy_c45_pma_baset1_setup_master_slave(phydev); + ret = genphy_c45_pma_baset1_setup_master_slave(phydev); + if (ret) + return ret; + + /* Re-read role configuration to make changes visible even if + * the link is in administrative down state. + */ + return genphy_c45_pma_baset1_read_master_slave(phydev); } static int dp83tg720_read_status(struct phy_device *phydev) @@ -64,6 +78,8 @@ static int dp83tg720_read_status(struct phy_device *phydev) return ret; /* After HW reset we need to restore master/slave configuration. + * genphy_c45_pma_baset1_read_master_slave() call will be done + * by the dp83tg720_config_aneg() function. */ ret = dp83tg720_config_aneg(phydev); if (ret) @@ -154,10 +170,24 @@ static int dp83tg720_config_init(struct phy_device *phydev) */ usleep_range(1000, 2000); - if (phy_interface_is_rgmii(phydev)) - return dp83tg720_config_rgmii_delay(phydev); + if (phy_interface_is_rgmii(phydev)) { + ret = dp83tg720_config_rgmii_delay(phydev); + if (ret) + return ret; + } + + /* In case the PHY is bootstrapped in managed mode, we need to + * wake it. + */ + ret = phy_write_mmd(phydev, MDIO_MMD_VEND2, DP83TG720S_LPS_CFG3, + DP83TG720S_LPS_CFG3_PWR_MODE_0); + if (ret) + return ret; - return 0; + /* Make role configuration visible for ethtool on init and after + * rest. + */ + return genphy_c45_pma_baset1_read_master_slave(phydev); } static struct phy_driver dp83tg720_driver[] = { diff --git a/drivers/net/phy/mxl-gpy.c b/drivers/net/phy/mxl-gpy.c index b2d36a3a96f1..e5f8ac4b4604 100644 --- a/drivers/net/phy/mxl-gpy.c +++ b/drivers/net/phy/mxl-gpy.c @@ -107,6 +107,7 @@ struct gpy_priv { u8 fw_major; u8 fw_minor; + u32 wolopts; /* It takes 3 seconds to fully switch out of loopback mode before * it can safely re-enter loopback mode. Record the time when @@ -221,6 +222,15 @@ static int gpy_hwmon_register(struct phy_device *phydev) } #endif +static int gpy_ack_interrupt(struct phy_device *phydev) +{ + int ret; + + /* Clear all pending interrupts */ + ret = phy_read(phydev, PHY_ISTAT); + return ret < 0 ? ret : 0; +} + static int gpy_mbox_read(struct phy_device *phydev, u32 addr) { struct gpy_priv *priv = phydev->priv; @@ -262,16 +272,8 @@ out: static int gpy_config_init(struct phy_device *phydev) { - int ret; - - /* Mask all interrupts */ - ret = phy_write(phydev, PHY_IMASK, 0); - if (ret) - return ret; - - /* Clear all pending interrupts */ - ret = phy_read(phydev, PHY_ISTAT); - return ret < 0 ? ret : 0; + /* Nothing to configure. Configuration Requirement Placeholder */ + return 0; } static int gpy21x_config_init(struct phy_device *phydev) @@ -627,11 +629,23 @@ static int gpy_read_status(struct phy_device *phydev) static int gpy_config_intr(struct phy_device *phydev) { + struct gpy_priv *priv = phydev->priv; u16 mask = 0; + int ret; + + ret = gpy_ack_interrupt(phydev); + if (ret) + return ret; if (phydev->interrupts == PHY_INTERRUPT_ENABLED) mask = PHY_IMASK_MASK; + if (priv->wolopts & WAKE_MAGIC) + mask |= PHY_IMASK_WOL; + + if (priv->wolopts & WAKE_PHY) + mask |= PHY_IMASK_LSTC; + return phy_write(phydev, PHY_IMASK, mask); } @@ -678,6 +692,7 @@ static int gpy_set_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol) { struct net_device *attach_dev = phydev->attached_dev; + struct gpy_priv *priv = phydev->priv; int ret; if (wol->wolopts & WAKE_MAGIC) { @@ -725,6 +740,8 @@ static int gpy_set_wol(struct phy_device *phydev, ret = phy_read(phydev, PHY_ISTAT); if (ret < 0) return ret; + + priv->wolopts |= WAKE_MAGIC; } else { /* Disable magic packet matching */ ret = phy_clear_bits_mmd(phydev, MDIO_MMD_VEND2, @@ -732,6 +749,13 @@ static int gpy_set_wol(struct phy_device *phydev, WOL_EN); if (ret < 0) return ret; + + /* Disable the WOL interrupt */ + ret = phy_clear_bits(phydev, PHY_IMASK, PHY_IMASK_WOL); + if (ret < 0) + return ret; + + priv->wolopts &= ~WAKE_MAGIC; } if (wol->wolopts & WAKE_PHY) { @@ -748,9 +772,11 @@ static int gpy_set_wol(struct phy_device *phydev, if (ret & (PHY_IMASK_MASK & ~PHY_IMASK_LSTC)) phy_trigger_machine(phydev); + priv->wolopts |= WAKE_PHY; return 0; } + priv->wolopts &= ~WAKE_PHY; /* Disable the link state change interrupt */ return phy_clear_bits(phydev, PHY_IMASK, PHY_IMASK_LSTC); } @@ -758,18 +784,10 @@ static int gpy_set_wol(struct phy_device *phydev, static void gpy_get_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol) { - int ret; + struct gpy_priv *priv = phydev->priv; wol->supported = WAKE_MAGIC | WAKE_PHY; - wol->wolopts = 0; - - ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, VPSPEC2_WOL_CTL); - if (ret & WOL_EN) - wol->wolopts |= WAKE_MAGIC; - - ret = phy_read(phydev, PHY_IMASK); - if (ret & PHY_IMASK_LSTC) - wol->wolopts |= WAKE_PHY; + wol->wolopts = priv->wolopts; } static int gpy_loopback(struct phy_device *phydev, bool enable) diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index 51c295e1e823..c2fb736f78b2 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -174,7 +174,6 @@ struct ax88179_data { u32 wol_supported; u32 wolopts; u8 disconnecting; - u8 initialized; }; struct ax88179_int_data { @@ -1678,12 +1677,21 @@ static int ax88179_reset(struct usbnet *dev) static int ax88179_net_reset(struct usbnet *dev) { - struct ax88179_data *ax179_data = dev->driver_priv; + u16 tmp16; - if (ax179_data->initialized) + ax88179_read_cmd(dev, AX_ACCESS_PHY, AX88179_PHY_ID, GMII_PHY_PHYSR, + 2, &tmp16); + if (tmp16) { + ax88179_read_cmd(dev, AX_ACCESS_MAC, AX_MEDIUM_STATUS_MODE, + 2, 2, &tmp16); + if (!(tmp16 & AX_MEDIUM_RECEIVE_EN)) { + tmp16 |= AX_MEDIUM_RECEIVE_EN; + ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_MEDIUM_STATUS_MODE, + 2, 2, &tmp16); + } + } else { ax88179_reset(dev); - else - ax179_data->initialized = 1; + } return 0; } diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c index 97afd7335d86..01a3b2417a54 100644 --- a/drivers/net/usb/rtl8150.c +++ b/drivers/net/usb/rtl8150.c @@ -778,7 +778,8 @@ static int rtl8150_get_link_ksettings(struct net_device *netdev, struct ethtool_link_ksettings *ecmd) { rtl8150_t *dev = netdev_priv(netdev); - short lpa, bmcr; + short lpa = 0; + short bmcr = 0; u32 supported; supported = (SUPPORTED_10baseT_Half | diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 9f9b86874173..b1f8b720733e 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -1388,6 +1388,10 @@ static struct sk_buff *receive_small_xdp(struct net_device *dev, if (unlikely(hdr->hdr.gso_type)) goto err_xdp; + /* Partially checksummed packets must be dropped. */ + if (unlikely(hdr->hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM)) + goto err_xdp; + buflen = SKB_DATA_ALIGN(GOOD_PACKET_LEN + headroom) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); @@ -1705,6 +1709,10 @@ static void *mergeable_xdp_get_buf(struct virtnet_info *vi, if (unlikely(hdr->hdr.gso_type)) return NULL; + /* Partially checksummed packets must be dropped. */ + if (unlikely(hdr->hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM)) + return NULL; + /* Now XDP core assumes frag size is PAGE_SIZE, but buffers * with headroom may add hole in truesize, which * make their length exceed PAGE_SIZE. So we disabled the @@ -1971,6 +1979,7 @@ static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq, struct net_device *dev = vi->dev; struct sk_buff *skb; struct virtio_net_common_hdr *hdr; + u8 flags; if (unlikely(len < vi->hdr_len + ETH_HLEN)) { pr_debug("%s: short packet %i\n", dev->name, len); @@ -1979,6 +1988,15 @@ static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq, return; } + /* 1. Save the flags early, as the XDP program might overwrite them. + * These flags ensure packets marked as VIRTIO_NET_HDR_F_DATA_VALID + * stay valid after XDP processing. + * 2. XDP doesn't work with partially checksummed packets (refer to + * virtnet_xdp_set()), so packets marked as + * VIRTIO_NET_HDR_F_NEEDS_CSUM get dropped during XDP processing. + */ + flags = ((struct virtio_net_common_hdr *)buf)->hdr.flags; + if (vi->mergeable_rx_bufs) skb = receive_mergeable(dev, vi, rq, buf, ctx, len, xdp_xmit, stats); @@ -1994,7 +2012,7 @@ static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq, if (dev->features & NETIF_F_RXHASH && vi->has_rss_hash_report) virtio_skb_set_hash(&hdr->hash_v1_hdr, skb); - if (hdr->hdr.flags & VIRTIO_NET_HDR_F_DATA_VALID) + if (flags & VIRTIO_NET_HDR_F_DATA_VALID) skb->ip_summed = CHECKSUM_UNNECESSARY; if (virtio_net_hdr_to_skb(skb, &hdr->hdr, @@ -5699,8 +5717,16 @@ static int virtnet_probe(struct virtio_device *vdev) dev->features |= dev->hw_features & NETIF_F_ALL_TSO; /* (!csum && gso) case will be fixed by register_netdev() */ } - if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_CSUM)) - dev->features |= NETIF_F_RXCSUM; + + /* 1. With VIRTIO_NET_F_GUEST_CSUM negotiation, the driver doesn't + * need to calculate checksums for partially checksummed packets, + * as they're considered valid by the upper layer. + * 2. Without VIRTIO_NET_F_GUEST_CSUM negotiation, the driver only + * receives fully checksummed packets. The device may assist in + * validating these packets' checksums, so the driver won't have to. + */ + dev->features |= NETIF_F_RXCSUM; + if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) || virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO6)) dev->features |= NETIF_F_GRO_HW; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index 88bc0baabf7e..d511e88af6f3 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -4762,7 +4762,7 @@ static int iwl_mvm_roc_station(struct iwl_mvm *mvm, if (fw_ver == IWL_FW_CMD_VER_UNKNOWN) { ret = iwl_mvm_send_aux_roc_cmd(mvm, channel, vif, duration); - } else if (fw_ver == 3) { + } else if (fw_ver >= 3) { ret = iwl_mvm_roc_add_cmd(mvm, channel, vif, duration, ROC_ACTIVITY_HOTSPOT); } else { diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c index 23a860055354..8e0df31f1b3e 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c @@ -1830,7 +1830,7 @@ iwl_mvm_umac_scan_cfg_channels_v7_6g(struct iwl_mvm *mvm, */ if (!iwl_mvm_is_scan_fragmented(params->type)) { if (!cfg80211_channel_is_psc(params->channels[i]) || - flags & IWL_UHB_CHAN_CFG_FLAG_PSC_CHAN_NO_LISTEN) { + psc_no_listen) { if (unsolicited_probe_on_chan) { max_s_ssids = 2; max_bssids = 6; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c index 8ee4498f4245..31bc80cdcb7d 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c @@ -1238,6 +1238,7 @@ void iwl_mvm_stop_roc(struct iwl_mvm *mvm, struct ieee80211_vif *vif) if (te_data->id >= SESSION_PROTECT_CONF_MAX_ID) { IWL_DEBUG_TE(mvm, "No remain on channel event\n"); + mutex_unlock(&mvm->mutex); return; } @@ -1253,6 +1254,7 @@ void iwl_mvm_stop_roc(struct iwl_mvm *mvm, struct ieee80211_vif *vif) te_data = iwl_mvm_get_roc_te(mvm); if (!te_data) { IWL_WARN(mvm, "No remain on channel event\n"); + mutex_unlock(&mvm->mutex); return; } diff --git a/drivers/net/wireless/mediatek/mt76/debugfs.c b/drivers/net/wireless/mediatek/mt76/debugfs.c index ae83be572b94..b6a2746c187d 100644 --- a/drivers/net/wireless/mediatek/mt76/debugfs.c +++ b/drivers/net/wireless/mediatek/mt76/debugfs.c @@ -33,8 +33,8 @@ mt76_napi_threaded_set(void *data, u64 val) if (!mt76_is_mmio(dev)) return -EOPNOTSUPP; - if (dev->napi_dev.threaded != val) - return dev_set_threaded(&dev->napi_dev, val); + if (dev->napi_dev->threaded != val) + return dev_set_threaded(dev->napi_dev, val); return 0; } @@ -44,7 +44,7 @@ mt76_napi_threaded_get(void *data, u64 *val) { struct mt76_dev *dev = data; - *val = dev->napi_dev.threaded; + *val = dev->napi_dev->threaded; return 0; } diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c index f4f88c444e21..5f46d6daeaa7 100644 --- a/drivers/net/wireless/mediatek/mt76/dma.c +++ b/drivers/net/wireless/mediatek/mt76/dma.c @@ -916,7 +916,7 @@ int mt76_dma_rx_poll(struct napi_struct *napi, int budget) struct mt76_dev *dev; int qid, done = 0, cur; - dev = container_of(napi->dev, struct mt76_dev, napi_dev); + dev = mt76_priv(napi->dev); qid = napi - dev->napi; rcu_read_lock(); @@ -940,18 +940,35 @@ static int mt76_dma_init(struct mt76_dev *dev, int (*poll)(struct napi_struct *napi, int budget)) { + struct mt76_dev **priv; int i; - init_dummy_netdev(&dev->napi_dev); - init_dummy_netdev(&dev->tx_napi_dev); - snprintf(dev->napi_dev.name, sizeof(dev->napi_dev.name), "%s", + dev->napi_dev = alloc_netdev_dummy(sizeof(struct mt76_dev *)); + if (!dev->napi_dev) + return -ENOMEM; + + /* napi_dev private data points to mt76_dev parent, so, mt76_dev + * can be retrieved given napi_dev + */ + priv = netdev_priv(dev->napi_dev); + *priv = dev; + + dev->tx_napi_dev = alloc_netdev_dummy(sizeof(struct mt76_dev *)); + if (!dev->tx_napi_dev) { + free_netdev(dev->napi_dev); + return -ENOMEM; + } + priv = netdev_priv(dev->tx_napi_dev); + *priv = dev; + + snprintf(dev->napi_dev->name, sizeof(dev->napi_dev->name), "%s", wiphy_name(dev->hw->wiphy)); - dev->napi_dev.threaded = 1; + dev->napi_dev->threaded = 1; init_completion(&dev->mmio.wed_reset); init_completion(&dev->mmio.wed_reset_complete); mt76_for_each_q_rx(dev, i) { - netif_napi_add(&dev->napi_dev, &dev->napi[i], poll); + netif_napi_add(dev->napi_dev, &dev->napi[i], poll); mt76_dma_rx_fill(dev, &dev->q_rx[i], false); napi_enable(&dev->napi[i]); } @@ -1019,5 +1036,7 @@ void mt76_dma_cleanup(struct mt76_dev *dev) mt76_free_pending_txwi(dev); mt76_free_pending_rxwi(dev); + free_netdev(dev->napi_dev); + free_netdev(dev->tx_napi_dev); } EXPORT_SYMBOL_GPL(mt76_dma_cleanup); diff --git a/drivers/net/wireless/mediatek/mt76/dma.h b/drivers/net/wireless/mediatek/mt76/dma.h index 1de5a2b20f74..e3ddc7a83757 100644 --- a/drivers/net/wireless/mediatek/mt76/dma.h +++ b/drivers/net/wireless/mediatek/mt76/dma.h @@ -116,4 +116,13 @@ mt76_dma_should_drop_buf(bool *drop, u32 ctrl, u32 buf1, u32 info) } } +static inline void *mt76_priv(struct net_device *dev) +{ + struct mt76_dev **priv; + + priv = netdev_priv(dev); + + return *priv; +} + #endif diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h index 11b9f22ca7f3..15f83b5adac7 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76.h +++ b/drivers/net/wireless/mediatek/mt76/mt76.h @@ -831,8 +831,8 @@ struct mt76_dev { struct mt76_mcu mcu; - struct net_device napi_dev; - struct net_device tx_napi_dev; + struct net_device *napi_dev; + struct net_device *tx_napi_dev; spinlock_t rx_lock; struct napi_struct napi[__MT_RXQ_MAX]; struct sk_buff_head rx_skb[__MT_RXQ_MAX]; diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/dma.c b/drivers/net/wireless/mediatek/mt76/mt7603/dma.c index 14304b063715..ea017f22fff2 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7603/dma.c +++ b/drivers/net/wireless/mediatek/mt76/mt7603/dma.c @@ -242,7 +242,7 @@ int mt7603_dma_init(struct mt7603_dev *dev) if (ret) return ret; - netif_napi_add_tx(&dev->mt76.tx_napi_dev, &dev->mt76.tx_napi, + netif_napi_add_tx(dev->mt76.tx_napi_dev, &dev->mt76.tx_napi, mt7603_poll_tx); napi_enable(&dev->mt76.tx_napi); diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/dma.c b/drivers/net/wireless/mediatek/mt76/mt7615/dma.c index e7135b2f1742..bcf7864312d7 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/dma.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/dma.c @@ -67,7 +67,7 @@ static int mt7615_poll_tx(struct napi_struct *napi, int budget) { struct mt7615_dev *dev; - dev = container_of(napi, struct mt7615_dev, mt76.tx_napi); + dev = mt76_priv(napi->dev); if (!mt76_connac_pm_ref(&dev->mphy, &dev->pm)) { napi_complete(napi); queue_work(dev->mt76.wq, &dev->pm.wake_work); @@ -89,7 +89,7 @@ static int mt7615_poll_rx(struct napi_struct *napi, int budget) struct mt7615_dev *dev; int done; - dev = container_of(napi->dev, struct mt7615_dev, mt76.napi_dev); + dev = mt76_priv(napi->dev); if (!mt76_connac_pm_ref(&dev->mphy, &dev->pm)) { napi_complete(napi); @@ -282,7 +282,7 @@ int mt7615_dma_init(struct mt7615_dev *dev) if (ret < 0) return ret; - netif_napi_add_tx(&dev->mt76.tx_napi_dev, &dev->mt76.tx_napi, + netif_napi_add_tx(dev->mt76.tx_napi_dev, &dev->mt76.tx_napi, mt7615_poll_tx); napi_enable(&dev->mt76.tx_napi); diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c index e5ad635d3c56..35b7ebc2c9c6 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c @@ -239,7 +239,7 @@ int mt76x02_dma_init(struct mt76x02_dev *dev) if (ret) return ret; - netif_napi_add_tx(&dev->mt76.tx_napi_dev, &dev->mt76.tx_napi, + netif_napi_add_tx(dev->mt76.tx_napi_dev, &dev->mt76.tx_napi, mt76x02_poll_tx); napi_enable(&dev->mt76.tx_napi); diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/dma.c b/drivers/net/wireless/mediatek/mt76/mt7915/dma.c index 0baa82c8df5a..0c62272fe7d0 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/dma.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/dma.c @@ -578,7 +578,7 @@ int mt7915_dma_init(struct mt7915_dev *dev, struct mt7915_phy *phy2) if (ret < 0) return ret; - netif_napi_add_tx(&dev->mt76.tx_napi_dev, &dev->mt76.tx_napi, + netif_napi_add_tx(dev->mt76.tx_napi_dev, &dev->mt76.tx_napi, mt7915_poll_tx); napi_enable(&dev->mt76.tx_napi); diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c index f768e9389ac6..e75e7b6d3aaf 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c @@ -219,7 +219,7 @@ static int mt7921_dma_init(struct mt792x_dev *dev) if (ret < 0) return ret; - netif_napi_add_tx(&dev->mt76.tx_napi_dev, &dev->mt76.tx_napi, + netif_napi_add_tx(dev->mt76.tx_napi_dev, &dev->mt76.tx_napi, mt792x_poll_tx); napi_enable(&dev->mt76.tx_napi); diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/pci.c b/drivers/net/wireless/mediatek/mt76/mt7925/pci.c index 07b74d492ce1..577574fb7a1e 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/pci.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/pci.c @@ -254,7 +254,7 @@ static int mt7925_dma_init(struct mt792x_dev *dev) if (ret < 0) return ret; - netif_napi_add_tx(&dev->mt76.tx_napi_dev, &dev->mt76.tx_napi, + netif_napi_add_tx(dev->mt76.tx_napi_dev, &dev->mt76.tx_napi, mt792x_poll_tx); napi_enable(&dev->mt76.tx_napi); diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_dma.c b/drivers/net/wireless/mediatek/mt76/mt792x_dma.c index 5cc2d59b774a..6f9db782338e 100644 --- a/drivers/net/wireless/mediatek/mt76/mt792x_dma.c +++ b/drivers/net/wireless/mediatek/mt76/mt792x_dma.c @@ -340,7 +340,7 @@ int mt792x_poll_rx(struct napi_struct *napi, int budget) struct mt792x_dev *dev; int done; - dev = container_of(napi->dev, struct mt792x_dev, mt76.napi_dev); + dev = mt76_priv(napi->dev); if (!mt76_connac_pm_ref(&dev->mphy, &dev->pm)) { napi_complete(napi); diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/dma.c b/drivers/net/wireless/mediatek/mt76/mt7996/dma.c index 73e633d0d700..69a7d9b2e38b 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/dma.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/dma.c @@ -641,7 +641,7 @@ int mt7996_dma_init(struct mt7996_dev *dev) if (ret < 0) return ret; - netif_napi_add_tx(&dev->mt76.tx_napi_dev, &dev->mt76.tx_napi, + netif_napi_add_tx(dev->mt76.tx_napi_dev, &dev->mt76.tx_napi, mt7996_poll_tx); napi_enable(&dev->mt76.tx_napi); diff --git a/drivers/nfc/microread/i2c.c b/drivers/nfc/microread/i2c.c index 642df4e0ce24..113b2e306e35 100644 --- a/drivers/nfc/microread/i2c.c +++ b/drivers/nfc/microread/i2c.c @@ -277,7 +277,7 @@ static void microread_i2c_remove(struct i2c_client *client) } static const struct i2c_device_id microread_i2c_id[] = { - { MICROREAD_I2C_DRIVER_NAME, 0}, + { MICROREAD_I2C_DRIVER_NAME }, { } }; MODULE_DEVICE_TABLE(i2c, microread_i2c_id); diff --git a/drivers/nfc/nfcmrvl/i2c.c b/drivers/nfc/nfcmrvl/i2c.c index 74553134c1b1..39ecf2aeda80 100644 --- a/drivers/nfc/nfcmrvl/i2c.c +++ b/drivers/nfc/nfcmrvl/i2c.c @@ -252,7 +252,7 @@ static const struct of_device_id of_nfcmrvl_i2c_match[] __maybe_unused = { MODULE_DEVICE_TABLE(of, of_nfcmrvl_i2c_match); static const struct i2c_device_id nfcmrvl_i2c_id_table[] = { - { "nfcmrvl_i2c", 0 }, + { "nfcmrvl_i2c" }, {} }; MODULE_DEVICE_TABLE(i2c, nfcmrvl_i2c_id_table); diff --git a/drivers/nfc/nxp-nci/i2c.c b/drivers/nfc/nxp-nci/i2c.c index 3ae4b41c59ac..a8aced0b8010 100644 --- a/drivers/nfc/nxp-nci/i2c.c +++ b/drivers/nfc/nxp-nci/i2c.c @@ -322,7 +322,7 @@ static void nxp_nci_i2c_remove(struct i2c_client *client) } static const struct i2c_device_id nxp_nci_i2c_id_table[] = { - {"nxp-nci_i2c", 0}, + { "nxp-nci_i2c" }, {} }; MODULE_DEVICE_TABLE(i2c, nxp_nci_i2c_id_table); diff --git a/drivers/nfc/pn533/i2c.c b/drivers/nfc/pn533/i2c.c index 438ab9553f7a..132c050a365d 100644 --- a/drivers/nfc/pn533/i2c.c +++ b/drivers/nfc/pn533/i2c.c @@ -249,7 +249,7 @@ static const struct of_device_id of_pn533_i2c_match[] __maybe_unused = { MODULE_DEVICE_TABLE(of, of_pn533_i2c_match); static const struct i2c_device_id pn533_i2c_id_table[] = { - { PN533_I2C_DRIVER_NAME, 0 }, + { PN533_I2C_DRIVER_NAME }, {} }; MODULE_DEVICE_TABLE(i2c, pn533_i2c_id_table); diff --git a/drivers/nfc/pn544/i2c.c b/drivers/nfc/pn544/i2c.c index 3f6d74832bac..9fe664960b38 100644 --- a/drivers/nfc/pn544/i2c.c +++ b/drivers/nfc/pn544/i2c.c @@ -44,7 +44,7 @@ PN544_HCI_I2C_LLC_MAX_PAYLOAD) static const struct i2c_device_id pn544_hci_i2c_id_table[] = { - {"pn544", 0}, + { "pn544" }, {} }; diff --git a/drivers/nfc/s3fwrn5/i2c.c b/drivers/nfc/s3fwrn5/i2c.c index 720d4a72493c..536c566e3f59 100644 --- a/drivers/nfc/s3fwrn5/i2c.c +++ b/drivers/nfc/s3fwrn5/i2c.c @@ -245,7 +245,7 @@ static void s3fwrn5_i2c_remove(struct i2c_client *client) } static const struct i2c_device_id s3fwrn5_i2c_id_table[] = { - {S3FWRN5_I2C_DRIVER_NAME, 0}, + { S3FWRN5_I2C_DRIVER_NAME }, {} }; MODULE_DEVICE_TABLE(i2c, s3fwrn5_i2c_id_table); diff --git a/drivers/nfc/st-nci/i2c.c b/drivers/nfc/st-nci/i2c.c index d20a337e90b4..416770adbeba 100644 --- a/drivers/nfc/st-nci/i2c.c +++ b/drivers/nfc/st-nci/i2c.c @@ -257,7 +257,7 @@ static void st_nci_i2c_remove(struct i2c_client *client) } static const struct i2c_device_id st_nci_i2c_id_table[] = { - {ST_NCI_DRIVER_NAME, 0}, + { ST_NCI_DRIVER_NAME }, {} }; MODULE_DEVICE_TABLE(i2c, st_nci_i2c_id_table); diff --git a/drivers/nfc/st21nfca/i2c.c b/drivers/nfc/st21nfca/i2c.c index 064a63db288b..02c3d11a19c4 100644 --- a/drivers/nfc/st21nfca/i2c.c +++ b/drivers/nfc/st21nfca/i2c.c @@ -573,7 +573,7 @@ static void st21nfca_hci_i2c_remove(struct i2c_client *client) } static const struct i2c_device_id st21nfca_hci_i2c_id_table[] = { - {ST21NFCA_HCI_DRIVER_NAME, 0}, + { ST21NFCA_HCI_DRIVER_NAME }, {} }; MODULE_DEVICE_TABLE(i2c, st21nfca_hci_i2c_id_table); diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index f5d150c62955..782090ce0bc1 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -998,6 +998,7 @@ void nvme_cleanup_cmd(struct request *req) clear_bit_unlock(0, &ctrl->discard_page_busy); else kfree(bvec_virt(&req->special_vec)); + req->rq_flags &= ~RQF_SPECIAL_PAYLOAD; } } EXPORT_SYMBOL_GPL(nvme_cleanup_cmd); @@ -3959,12 +3960,13 @@ static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl, mutex_lock(&ctrl->namespaces_lock); list_for_each_entry_safe(ns, next, &ctrl->namespaces, list) { - if (ns->head->ns_id > nsid) - list_splice_init_rcu(&ns->list, &rm_list, - synchronize_rcu); + if (ns->head->ns_id > nsid) { + list_del_rcu(&ns->list); + synchronize_srcu(&ctrl->srcu); + list_add_tail_rcu(&ns->list, &rm_list); + } } mutex_unlock(&ctrl->namespaces_lock); - synchronize_srcu(&ctrl->srcu); list_for_each_entry_safe(ns, next, &rm_list, list) nvme_ns_remove(ns); diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index 9d9d2a127c4e..8b69427a4476 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -111,6 +111,13 @@ static struct request *nvme_alloc_user_request(struct request_queue *q, return req; } +static void nvme_unmap_bio(struct bio *bio) +{ + if (bio_integrity(bio)) + bio_integrity_unmap_free_user(bio); + blk_rq_unmap_user(bio); +} + static int nvme_map_user_request(struct request *req, u64 ubuffer, unsigned bufflen, void __user *meta_buffer, unsigned meta_len, u32 meta_seed, struct io_uring_cmd *ioucmd, unsigned int flags) @@ -157,7 +164,7 @@ static int nvme_map_user_request(struct request *req, u64 ubuffer, out_unmap: if (bio) - blk_rq_unmap_user(bio); + nvme_unmap_bio(bio); out: blk_mq_free_request(req); return ret; @@ -195,7 +202,7 @@ static int nvme_submit_user_cmd(struct request_queue *q, if (result) *result = le64_to_cpu(nvme_req(req)->result.u64); if (bio) - blk_rq_unmap_user(bio); + nvme_unmap_bio(bio); blk_mq_free_request(req); if (effects) @@ -406,7 +413,7 @@ static void nvme_uring_task_cb(struct io_uring_cmd *ioucmd, struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd); if (pdu->bio) - blk_rq_unmap_user(pdu->bio); + nvme_unmap_bio(pdu->bio); io_uring_cmd_done(ioucmd, pdu->status, pdu->result, issue_flags); } @@ -432,7 +439,7 @@ static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req, */ if (blk_rq_is_poll(req)) { if (pdu->bio) - blk_rq_unmap_user(pdu->bio); + nvme_unmap_bio(pdu->bio); io_uring_cmd_iopoll_done(ioucmd, pdu->result, pdu->status); } else { io_uring_cmd_do_in_task_lazy(ioucmd, nvme_uring_task_cb); diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 06f0c587f343..4ff460ba2826 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -957,6 +957,7 @@ bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq, req->metadata_sg_cnt = 0; req->transfer_len = 0; req->metadata_len = 0; + req->cqe->result.u64 = 0; req->cqe->status = 0; req->cqe->sq_head = 0; req->ns = NULL; diff --git a/drivers/nvme/target/fabrics-cmd-auth.c b/drivers/nvme/target/fabrics-cmd-auth.c index d61b8c6ff3b2..cb34d644ed08 100644 --- a/drivers/nvme/target/fabrics-cmd-auth.c +++ b/drivers/nvme/target/fabrics-cmd-auth.c @@ -333,7 +333,6 @@ done: pr_debug("%s: ctrl %d qid %d nvme status %x error loc %d\n", __func__, ctrl->cntlid, req->sq->qid, status, req->error_loc); - req->cqe->result.u64 = 0; if (req->sq->dhchap_step != NVME_AUTH_DHCHAP_MESSAGE_SUCCESS2 && req->sq->dhchap_step != NVME_AUTH_DHCHAP_MESSAGE_FAILURE2) { unsigned long auth_expire_secs = ctrl->kato ? ctrl->kato : 120; @@ -516,8 +515,6 @@ void nvmet_execute_auth_receive(struct nvmet_req *req) status = nvmet_copy_to_sgl(req, 0, d, al); kfree(d); done: - req->cqe->result.u64 = 0; - if (req->sq->dhchap_step == NVME_AUTH_DHCHAP_MESSAGE_SUCCESS2) nvmet_auth_sq_free(req->sq); else if (req->sq->dhchap_step == NVME_AUTH_DHCHAP_MESSAGE_FAILURE1) { diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c index 042b379cbb36..69d77d34bec1 100644 --- a/drivers/nvme/target/fabrics-cmd.c +++ b/drivers/nvme/target/fabrics-cmd.c @@ -226,9 +226,6 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req) if (status) goto out; - /* zero out initial completion result, assign values as needed */ - req->cqe->result.u32 = 0; - if (c->recfmt != 0) { pr_warn("invalid connect version (%d).\n", le16_to_cpu(c->recfmt)); @@ -305,9 +302,6 @@ static void nvmet_execute_io_connect(struct nvmet_req *req) if (status) goto out; - /* zero out initial completion result, assign values as needed */ - req->cqe->result.u32 = 0; - if (c->recfmt != 0) { pr_warn("invalid connect version (%d).\n", le16_to_cpu(c->recfmt)); diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c index bb4a69d538fd..f003782d4ecf 100644 --- a/drivers/nvme/target/passthru.c +++ b/drivers/nvme/target/passthru.c @@ -226,13 +226,13 @@ static void nvmet_passthru_execute_cmd_work(struct work_struct *w) req->cmd->common.opcode == nvme_admin_identify) { switch (req->cmd->identify.cns) { case NVME_ID_CNS_CTRL: - nvmet_passthru_override_id_ctrl(req); + status = nvmet_passthru_override_id_ctrl(req); break; case NVME_ID_CNS_NS: - nvmet_passthru_override_id_ns(req); + status = nvmet_passthru_override_id_ns(req); break; case NVME_ID_CNS_NS_DESC_LIST: - nvmet_passthru_override_id_descs(req); + status = nvmet_passthru_override_id_descs(req); break; } } else if (status < 0) diff --git a/drivers/parport/parport_amiga.c b/drivers/parport/parport_amiga.c index e6dc857aac3f..e06c7b2aac5c 100644 --- a/drivers/parport/parport_amiga.c +++ b/drivers/parport/parport_amiga.c @@ -229,7 +229,13 @@ static void __exit amiga_parallel_remove(struct platform_device *pdev) parport_put_port(port); } -static struct platform_driver amiga_parallel_driver = { +/* + * amiga_parallel_remove() lives in .exit.text. For drivers registered via + * module_platform_driver_probe() this is ok because they cannot get unbound at + * runtime. So mark the driver struct with __refdata to prevent modpost + * triggering a section mismatch warning. + */ +static struct platform_driver amiga_parallel_driver __refdata = { .remove_new = __exit_p(amiga_parallel_remove), .driver = { .name = "amiga-parallel", diff --git a/drivers/ptp/ptp_sysfs.c b/drivers/ptp/ptp_sysfs.c index a15460aaa03b..6b1b8f57cd95 100644 --- a/drivers/ptp/ptp_sysfs.c +++ b/drivers/ptp/ptp_sysfs.c @@ -296,8 +296,7 @@ static ssize_t max_vclocks_store(struct device *dev, if (max < ptp->n_vclocks) goto out; - size = sizeof(int) * max; - vclock_index = kzalloc(size, GFP_KERNEL); + vclock_index = kcalloc(max, sizeof(int), GFP_KERNEL); if (!vclock_index) { err = -ENOMEM; goto out; diff --git a/drivers/ras/amd/atl/internal.h b/drivers/ras/amd/atl/internal.h index 5de69e0bb0f9..196c1c8b578c 100644 --- a/drivers/ras/amd/atl/internal.h +++ b/drivers/ras/amd/atl/internal.h @@ -224,7 +224,7 @@ int df_indirect_read_broadcast(u16 node, u8 func, u16 reg, u32 *lo); int get_df_system_info(void); int determine_node_id(struct addr_ctx *ctx, u8 socket_num, u8 die_num); -int get_addr_hash_mi300(void); +int get_umc_info_mi300(void); int get_address_map(struct addr_ctx *ctx); diff --git a/drivers/ras/amd/atl/system.c b/drivers/ras/amd/atl/system.c index 701349e84942..6979fa3d4fe2 100644 --- a/drivers/ras/amd/atl/system.c +++ b/drivers/ras/amd/atl/system.c @@ -127,7 +127,7 @@ static int df4_determine_df_rev(u32 reg) if (reg == DF_FUNC0_ID_MI300) { df_cfg.flags.heterogeneous = 1; - if (get_addr_hash_mi300()) + if (get_umc_info_mi300()) return -EINVAL; } diff --git a/drivers/ras/amd/atl/umc.c b/drivers/ras/amd/atl/umc.c index 59b6169093f7..a1b4accf7b96 100644 --- a/drivers/ras/amd/atl/umc.c +++ b/drivers/ras/amd/atl/umc.c @@ -68,6 +68,8 @@ struct xor_bits { }; #define NUM_BANK_BITS 4 +#define NUM_COL_BITS 5 +#define NUM_SID_BITS 2 static struct { /* UMC::CH::AddrHashBank */ @@ -80,7 +82,22 @@ static struct { u8 bank_xor; } addr_hash; +static struct { + u8 bank[NUM_BANK_BITS]; + u8 col[NUM_COL_BITS]; + u8 sid[NUM_SID_BITS]; + u8 num_row_lo; + u8 num_row_hi; + u8 row_lo; + u8 row_hi; + u8 pc; +} bit_shifts; + #define MI300_UMC_CH_BASE 0x90000 +#define MI300_ADDR_CFG (MI300_UMC_CH_BASE + 0x30) +#define MI300_ADDR_SEL (MI300_UMC_CH_BASE + 0x40) +#define MI300_COL_SEL_LO (MI300_UMC_CH_BASE + 0x50) +#define MI300_ADDR_SEL_2 (MI300_UMC_CH_BASE + 0xA4) #define MI300_ADDR_HASH_BANK0 (MI300_UMC_CH_BASE + 0xC8) #define MI300_ADDR_HASH_PC (MI300_UMC_CH_BASE + 0xE0) #define MI300_ADDR_HASH_PC2 (MI300_UMC_CH_BASE + 0xE4) @@ -90,17 +107,42 @@ static struct { #define ADDR_HASH_ROW_XOR GENMASK(31, 14) #define ADDR_HASH_BANK_XOR GENMASK(5, 0) +#define ADDR_CFG_NUM_ROW_LO GENMASK(11, 8) +#define ADDR_CFG_NUM_ROW_HI GENMASK(15, 12) + +#define ADDR_SEL_BANK0 GENMASK(3, 0) +#define ADDR_SEL_BANK1 GENMASK(7, 4) +#define ADDR_SEL_BANK2 GENMASK(11, 8) +#define ADDR_SEL_BANK3 GENMASK(15, 12) +#define ADDR_SEL_BANK4 GENMASK(20, 16) +#define ADDR_SEL_ROW_LO GENMASK(27, 24) +#define ADDR_SEL_ROW_HI GENMASK(31, 28) + +#define COL_SEL_LO_COL0 GENMASK(3, 0) +#define COL_SEL_LO_COL1 GENMASK(7, 4) +#define COL_SEL_LO_COL2 GENMASK(11, 8) +#define COL_SEL_LO_COL3 GENMASK(15, 12) +#define COL_SEL_LO_COL4 GENMASK(19, 16) + +#define ADDR_SEL_2_BANK5 GENMASK(4, 0) +#define ADDR_SEL_2_CHAN GENMASK(15, 12) + /* * Read UMC::CH::AddrHash{Bank,PC,PC2} registers to get XOR bits used - * for hashing. Do this during module init, since the values will not - * change during run time. + * for hashing. + * + * Also, read UMC::CH::Addr{Cfg,Sel,Sel2} and UMC::CH:ColSelLo registers to + * get the values needed to reconstruct the normalized address. Apply additional + * offsets to the raw register values, as needed. + * + * Do this during module init, since the values will not change during run time. * * These registers are instantiated for each UMC across each AMD Node. * However, they should be identically programmed due to the fixed hardware * design of MI300 systems. So read the values from Node 0 UMC 0 and keep a * single global structure for simplicity. */ -int get_addr_hash_mi300(void) +int get_umc_info_mi300(void) { u32 temp; int ret; @@ -130,6 +172,44 @@ int get_addr_hash_mi300(void) addr_hash.bank_xor = FIELD_GET(ADDR_HASH_BANK_XOR, temp); + ret = amd_smn_read(0, MI300_ADDR_CFG, &temp); + if (ret) + return ret; + + bit_shifts.num_row_hi = FIELD_GET(ADDR_CFG_NUM_ROW_HI, temp); + bit_shifts.num_row_lo = 10 + FIELD_GET(ADDR_CFG_NUM_ROW_LO, temp); + + ret = amd_smn_read(0, MI300_ADDR_SEL, &temp); + if (ret) + return ret; + + bit_shifts.bank[0] = 5 + FIELD_GET(ADDR_SEL_BANK0, temp); + bit_shifts.bank[1] = 5 + FIELD_GET(ADDR_SEL_BANK1, temp); + bit_shifts.bank[2] = 5 + FIELD_GET(ADDR_SEL_BANK2, temp); + bit_shifts.bank[3] = 5 + FIELD_GET(ADDR_SEL_BANK3, temp); + /* Use BankBit4 for the SID0 position. */ + bit_shifts.sid[0] = 5 + FIELD_GET(ADDR_SEL_BANK4, temp); + bit_shifts.row_lo = 12 + FIELD_GET(ADDR_SEL_ROW_LO, temp); + bit_shifts.row_hi = 24 + FIELD_GET(ADDR_SEL_ROW_HI, temp); + + ret = amd_smn_read(0, MI300_COL_SEL_LO, &temp); + if (ret) + return ret; + + bit_shifts.col[0] = 2 + FIELD_GET(COL_SEL_LO_COL0, temp); + bit_shifts.col[1] = 2 + FIELD_GET(COL_SEL_LO_COL1, temp); + bit_shifts.col[2] = 2 + FIELD_GET(COL_SEL_LO_COL2, temp); + bit_shifts.col[3] = 2 + FIELD_GET(COL_SEL_LO_COL3, temp); + bit_shifts.col[4] = 2 + FIELD_GET(COL_SEL_LO_COL4, temp); + + ret = amd_smn_read(0, MI300_ADDR_SEL_2, &temp); + if (ret) + return ret; + + /* Use BankBit5 for the SID1 position. */ + bit_shifts.sid[1] = 5 + FIELD_GET(ADDR_SEL_2_BANK5, temp); + bit_shifts.pc = 5 + FIELD_GET(ADDR_SEL_2_CHAN, temp); + return 0; } @@ -146,9 +226,6 @@ int get_addr_hash_mi300(void) * The MCA address format is as follows: * MCA_ADDR[27:0] = {S[1:0], P[0], R[14:0], B[3:0], C[4:0], Z[0]} * - * The normalized address format is fixed in hardware and is as follows: - * NA[30:0] = {S[1:0], R[13:0], C4, B[1:0], B[3:2], C[3:2], P, C[1:0], Z[4:0]} - * * Additionally, the PC and Bank bits may be hashed. This must be accounted for before * reconstructing the normalized address. */ @@ -158,18 +235,10 @@ int get_addr_hash_mi300(void) #define MI300_UMC_MCA_PC BIT(25) #define MI300_UMC_MCA_SID GENMASK(27, 26) -#define MI300_NA_COL_1_0 GENMASK(6, 5) -#define MI300_NA_PC BIT(7) -#define MI300_NA_COL_3_2 GENMASK(9, 8) -#define MI300_NA_BANK_3_2 GENMASK(11, 10) -#define MI300_NA_BANK_1_0 GENMASK(13, 12) -#define MI300_NA_COL_4 BIT(14) -#define MI300_NA_ROW GENMASK(28, 15) -#define MI300_NA_SID GENMASK(30, 29) - static unsigned long convert_dram_to_norm_addr_mi300(unsigned long addr) { - u16 i, col, row, bank, pc, sid, temp; + u16 i, col, row, bank, pc, sid; + u32 temp; col = FIELD_GET(MI300_UMC_MCA_COL, addr); bank = FIELD_GET(MI300_UMC_MCA_BANK, addr); @@ -189,49 +258,48 @@ static unsigned long convert_dram_to_norm_addr_mi300(unsigned long addr) /* Calculate hash for PC bit. */ if (addr_hash.pc.xor_enable) { - /* Bits SID[1:0] act as Bank[6:5] for PC hash, so apply them here. */ - bank |= sid << 5; - temp = bitwise_xor_bits(col & addr_hash.pc.col_xor); temp ^= bitwise_xor_bits(row & addr_hash.pc.row_xor); - temp ^= bitwise_xor_bits(bank & addr_hash.bank_xor); + /* Bits SID[1:0] act as Bank[5:4] for PC hash, so apply them here. */ + temp ^= bitwise_xor_bits((bank | sid << NUM_BANK_BITS) & addr_hash.bank_xor); pc ^= temp; - - /* Drop SID bits for the sake of debug printing later. */ - bank &= 0x1F; } /* Reconstruct the normalized address starting with NA[4:0] = 0 */ addr = 0; - /* NA[6:5] = Column[1:0] */ - temp = col & 0x3; - addr |= FIELD_PREP(MI300_NA_COL_1_0, temp); - - /* NA[7] = PC */ - addr |= FIELD_PREP(MI300_NA_PC, pc); - - /* NA[9:8] = Column[3:2] */ - temp = (col >> 2) & 0x3; - addr |= FIELD_PREP(MI300_NA_COL_3_2, temp); + /* Column bits */ + for (i = 0; i < NUM_COL_BITS; i++) { + temp = (col >> i) & 0x1; + addr |= temp << bit_shifts.col[i]; + } - /* NA[11:10] = Bank[3:2] */ - temp = (bank >> 2) & 0x3; - addr |= FIELD_PREP(MI300_NA_BANK_3_2, temp); + /* Bank bits */ + for (i = 0; i < NUM_BANK_BITS; i++) { + temp = (bank >> i) & 0x1; + addr |= temp << bit_shifts.bank[i]; + } - /* NA[13:12] = Bank[1:0] */ - temp = bank & 0x3; - addr |= FIELD_PREP(MI300_NA_BANK_1_0, temp); + /* Row lo bits */ + for (i = 0; i < bit_shifts.num_row_lo; i++) { + temp = (row >> i) & 0x1; + addr |= temp << (i + bit_shifts.row_lo); + } - /* NA[14] = Column[4] */ - temp = (col >> 4) & 0x1; - addr |= FIELD_PREP(MI300_NA_COL_4, temp); + /* Row hi bits */ + for (i = 0; i < bit_shifts.num_row_hi; i++) { + temp = (row >> (i + bit_shifts.num_row_lo)) & 0x1; + addr |= temp << (i + bit_shifts.row_hi); + } - /* NA[28:15] = Row[13:0] */ - addr |= FIELD_PREP(MI300_NA_ROW, row); + /* PC bit */ + addr |= pc << bit_shifts.pc; - /* NA[30:29] = SID[1:0] */ - addr |= FIELD_PREP(MI300_NA_SID, sid); + /* SID bits */ + for (i = 0; i < NUM_SID_BITS; i++) { + temp = (sid >> i) & 0x1; + addr |= temp << bit_shifts.sid[i]; + } pr_debug("Addr=0x%016lx", addr); pr_debug("Bank=%u Row=%u Column=%u PC=%u SID=%u", bank, row, col, pc, sid); diff --git a/drivers/scsi/mpi3mr/mpi3mr_app.c b/drivers/scsi/mpi3mr/mpi3mr_app.c index 1638109a68a0..cd261b48eb46 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_app.c +++ b/drivers/scsi/mpi3mr/mpi3mr_app.c @@ -2163,10 +2163,72 @@ persistent_id_show(struct device *dev, struct device_attribute *attr, } static DEVICE_ATTR_RO(persistent_id); +/** + * sas_ncq_prio_supported_show - Indicate if device supports NCQ priority + * @dev: pointer to embedded device + * @attr: sas_ncq_prio_supported attribute descriptor + * @buf: the buffer returned + * + * A sysfs 'read-only' sdev attribute, only works with SATA devices + */ +static ssize_t +sas_ncq_prio_supported_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct scsi_device *sdev = to_scsi_device(dev); + + return sysfs_emit(buf, "%d\n", sas_ata_ncq_prio_supported(sdev)); +} +static DEVICE_ATTR_RO(sas_ncq_prio_supported); + +/** + * sas_ncq_prio_enable_show - send prioritized io commands to device + * @dev: pointer to embedded device + * @attr: sas_ncq_prio_enable attribute descriptor + * @buf: the buffer returned + * + * A sysfs 'read/write' sdev attribute, only works with SATA devices + */ +static ssize_t +sas_ncq_prio_enable_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct scsi_device *sdev = to_scsi_device(dev); + struct mpi3mr_sdev_priv_data *sdev_priv_data = sdev->hostdata; + + if (!sdev_priv_data) + return 0; + + return sysfs_emit(buf, "%d\n", sdev_priv_data->ncq_prio_enable); +} + +static ssize_t +sas_ncq_prio_enable_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct scsi_device *sdev = to_scsi_device(dev); + struct mpi3mr_sdev_priv_data *sdev_priv_data = sdev->hostdata; + bool ncq_prio_enable = 0; + + if (kstrtobool(buf, &ncq_prio_enable)) + return -EINVAL; + + if (!sas_ata_ncq_prio_supported(sdev)) + return -EINVAL; + + sdev_priv_data->ncq_prio_enable = ncq_prio_enable; + + return strlen(buf); +} +static DEVICE_ATTR_RW(sas_ncq_prio_enable); + static struct attribute *mpi3mr_dev_attrs[] = { &dev_attr_sas_address.attr, &dev_attr_device_handle.attr, &dev_attr_persistent_id.attr, + &dev_attr_sas_ncq_prio_supported.attr, + &dev_attr_sas_ncq_prio_enable.attr, NULL, }; diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 1320e06727df..b2bcf4a27ddc 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -8512,6 +8512,12 @@ mpt3sas_base_attach(struct MPT3SAS_ADAPTER *ioc) ioc->pd_handles_sz = (ioc->facts.MaxDevHandle / 8); if (ioc->facts.MaxDevHandle % 8) ioc->pd_handles_sz++; + /* + * pd_handles_sz should have, at least, the minimal room for + * set_bit()/test_bit(), otherwise out-of-memory touch may occur. + */ + ioc->pd_handles_sz = ALIGN(ioc->pd_handles_sz, sizeof(unsigned long)); + ioc->pd_handles = kzalloc(ioc->pd_handles_sz, GFP_KERNEL); if (!ioc->pd_handles) { @@ -8529,6 +8535,13 @@ mpt3sas_base_attach(struct MPT3SAS_ADAPTER *ioc) ioc->pend_os_device_add_sz = (ioc->facts.MaxDevHandle / 8); if (ioc->facts.MaxDevHandle % 8) ioc->pend_os_device_add_sz++; + + /* + * pend_os_device_add_sz should have, at least, the minimal room for + * set_bit()/test_bit(), otherwise out-of-memory may occur. + */ + ioc->pend_os_device_add_sz = ALIGN(ioc->pend_os_device_add_sz, + sizeof(unsigned long)); ioc->pend_os_device_add = kzalloc(ioc->pend_os_device_add_sz, GFP_KERNEL); if (!ioc->pend_os_device_add) { @@ -8820,6 +8833,12 @@ _base_check_ioc_facts_changes(struct MPT3SAS_ADAPTER *ioc) if (ioc->facts.MaxDevHandle % 8) pd_handles_sz++; + /* + * pd_handles should have, at least, the minimal room for + * set_bit()/test_bit(), otherwise out-of-memory touch may + * occur. + */ + pd_handles_sz = ALIGN(pd_handles_sz, sizeof(unsigned long)); pd_handles = krealloc(ioc->pd_handles, pd_handles_sz, GFP_KERNEL); if (!pd_handles) { diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h index bf100a4ebfc3..fe1e96fda284 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.h +++ b/drivers/scsi/mpt3sas/mpt3sas_base.h @@ -2048,9 +2048,6 @@ void mpt3sas_setup_direct_io(struct MPT3SAS_ADAPTER *ioc, struct scsi_cmnd *scmd, struct _raid_device *raid_device, Mpi25SCSIIORequest_t *mpi_request); -/* NCQ Prio Handling Check */ -bool scsih_ncq_prio_supp(struct scsi_device *sdev); - void mpt3sas_setup_debugfs(struct MPT3SAS_ADAPTER *ioc); void mpt3sas_destroy_debugfs(struct MPT3SAS_ADAPTER *ioc); void mpt3sas_init_debugfs(void); diff --git a/drivers/scsi/mpt3sas/mpt3sas_ctl.c b/drivers/scsi/mpt3sas/mpt3sas_ctl.c index 1c9fd26195b8..87784c96249a 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_ctl.c +++ b/drivers/scsi/mpt3sas/mpt3sas_ctl.c @@ -4088,7 +4088,7 @@ sas_ncq_prio_supported_show(struct device *dev, { struct scsi_device *sdev = to_scsi_device(dev); - return sysfs_emit(buf, "%d\n", scsih_ncq_prio_supp(sdev)); + return sysfs_emit(buf, "%d\n", sas_ata_ncq_prio_supported(sdev)); } static DEVICE_ATTR_RO(sas_ncq_prio_supported); @@ -4123,7 +4123,7 @@ sas_ncq_prio_enable_store(struct device *dev, if (kstrtobool(buf, &ncq_prio_enable)) return -EINVAL; - if (!scsih_ncq_prio_supp(sdev)) + if (!sas_ata_ncq_prio_supported(sdev)) return -EINVAL; sas_device_priv_data->ncq_prio_enable = ncq_prio_enable; diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index 12d08d8ba538..870ec2cb4af4 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -12571,29 +12571,6 @@ scsih_pci_mmio_enabled(struct pci_dev *pdev) return PCI_ERS_RESULT_RECOVERED; } -/** - * scsih_ncq_prio_supp - Check for NCQ command priority support - * @sdev: scsi device struct - * - * This is called when a user indicates they would like to enable - * ncq command priorities. This works only on SATA devices. - */ -bool scsih_ncq_prio_supp(struct scsi_device *sdev) -{ - struct scsi_vpd *vpd; - bool ncq_prio_supp = false; - - rcu_read_lock(); - vpd = rcu_dereference(sdev->vpd_pg89); - if (!vpd || vpd->len < 214) - goto out; - - ncq_prio_supp = (vpd->data[213] >> 4) & 1; -out: - rcu_read_unlock(); - - return ncq_prio_supp; -} /* * The pci device ids are defined in mpi/mpi2_cnfg.h. */ diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c index f0464db3f9de..ee69bd35889d 100644 --- a/drivers/scsi/scsi.c +++ b/drivers/scsi/scsi.c @@ -673,6 +673,13 @@ void scsi_cdl_check(struct scsi_device *sdev) sdev->use_10_for_rw = 0; sdev->cdl_supported = 1; + + /* + * If the device supports CDL, make sure that the current drive + * feature status is consistent with the user controlled + * cdl_enable state. + */ + scsi_cdl_enable(sdev, sdev->cdl_enable); } else { sdev->cdl_supported = 0; } diff --git a/drivers/scsi/scsi_transport_sas.c b/drivers/scsi/scsi_transport_sas.c index 424a89513814..4e33f1661e4c 100644 --- a/drivers/scsi/scsi_transport_sas.c +++ b/drivers/scsi/scsi_transport_sas.c @@ -416,6 +416,29 @@ unsigned int sas_is_tlr_enabled(struct scsi_device *sdev) } EXPORT_SYMBOL_GPL(sas_is_tlr_enabled); +/** + * sas_ata_ncq_prio_supported - Check for ATA NCQ command priority support + * @sdev: SCSI device + * + * Check if an ATA device supports NCQ priority using VPD page 89h (ATA + * Information). Since this VPD page is implemented only for ATA devices, + * this function always returns false for SCSI devices. + */ +bool sas_ata_ncq_prio_supported(struct scsi_device *sdev) +{ + struct scsi_vpd *vpd; + bool ncq_prio_supported = false; + + rcu_read_lock(); + vpd = rcu_dereference(sdev->vpd_pg89); + if (vpd && vpd->len >= 214) + ncq_prio_supported = (vpd->data[213] >> 4) & 1; + rcu_read_unlock(); + + return ncq_prio_supported; +} +EXPORT_SYMBOL_GPL(sas_ata_ncq_prio_supported); + /* * SAS Phy attributes */ diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index f6c822c9cbd2..37dd6ead72a4 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -3565,16 +3565,23 @@ static bool sd_validate_opt_xfer_size(struct scsi_disk *sdkp, static void sd_read_block_zero(struct scsi_disk *sdkp) { - unsigned int buf_len = sdkp->device->sector_size; - char *buffer, cmd[10] = { }; + struct scsi_device *sdev = sdkp->device; + unsigned int buf_len = sdev->sector_size; + u8 *buffer, cmd[16] = { }; buffer = kmalloc(buf_len, GFP_KERNEL); if (!buffer) return; - cmd[0] = READ_10; - put_unaligned_be32(0, &cmd[2]); /* Logical block address 0 */ - put_unaligned_be16(1, &cmd[7]); /* Transfer 1 logical block */ + if (sdev->use_16_for_rw) { + cmd[0] = READ_16; + put_unaligned_be64(0, &cmd[2]); /* Logical block address 0 */ + put_unaligned_be32(1, &cmd[10]);/* Transfer 1 logical block */ + } else { + cmd[0] = READ_10; + put_unaligned_be32(0, &cmd[2]); /* Logical block address 0 */ + put_unaligned_be16(1, &cmd[7]); /* Transfer 1 logical block */ + } scsi_execute_cmd(sdkp->device, cmd, REQ_OP_DRV_IN, buffer, buf_len, SD_TIMEOUT, sdkp->max_retries, NULL); diff --git a/drivers/soc/tegra/fuse/fuse-tegra.c b/drivers/soc/tegra/fuse/fuse-tegra.c index b6bfd6729df3..d27667283846 100644 --- a/drivers/soc/tegra/fuse/fuse-tegra.c +++ b/drivers/soc/tegra/fuse/fuse-tegra.c @@ -127,8 +127,8 @@ static void tegra_fuse_print_sku_info(struct tegra_sku_info *tegra_sku_info) static int tegra_fuse_add_lookups(struct tegra_fuse *fuse) { - fuse->lookups = kmemdup_array(fuse->soc->lookups, sizeof(*fuse->lookups), - fuse->soc->num_lookups, GFP_KERNEL); + fuse->lookups = kmemdup_array(fuse->soc->lookups, fuse->soc->num_lookups, + sizeof(*fuse->lookups), GFP_KERNEL); if (!fuse->lookups) return -ENOMEM; diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c index 297af1d80b12..69daeba974f2 100644 --- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c +++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c @@ -1759,7 +1759,7 @@ static int vchiq_probe(struct platform_device *pdev) if (err) goto failed_platform_init; - vchiq_debugfs_init(); + vchiq_debugfs_init(&mgmt->state); dev_dbg(&pdev->dev, "arm: platform initialised - version %d (min %d)\n", VCHIQ_VERSION, VCHIQ_VERSION_MIN); diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_debugfs.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_debugfs.c index 54e7bf029d9a..1f74d0bb33ba 100644 --- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_debugfs.c +++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_debugfs.c @@ -42,9 +42,9 @@ static int debugfs_trace_show(struct seq_file *f, void *offset) static int vchiq_dump_show(struct seq_file *f, void *offset) { - struct vchiq_instance *instance = f->private; + struct vchiq_state *state = f->private; - vchiq_dump_state(f, instance->state); + vchiq_dump_state(f, state); return 0; } @@ -121,12 +121,12 @@ void vchiq_debugfs_remove_instance(struct vchiq_instance *instance) debugfs_remove_recursive(node->dentry); } -void vchiq_debugfs_init(void) +void vchiq_debugfs_init(struct vchiq_state *state) { vchiq_dbg_dir = debugfs_create_dir("vchiq", NULL); vchiq_dbg_clients = debugfs_create_dir("clients", vchiq_dbg_dir); - debugfs_create_file("state", S_IFREG | 0444, vchiq_dbg_dir, NULL, + debugfs_create_file("state", S_IFREG | 0444, vchiq_dbg_dir, state, &vchiq_dump_fops); } diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_debugfs.h b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_debugfs.h index e9bf055a4ca9..fabffd81b1ec 100644 --- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_debugfs.h +++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_debugfs.h @@ -10,7 +10,7 @@ struct vchiq_debugfs_node { struct dentry *dentry; }; -void vchiq_debugfs_init(void); +void vchiq_debugfs_init(struct vchiq_state *state); void vchiq_debugfs_deinit(void); diff --git a/drivers/thermal/gov_step_wise.c b/drivers/thermal/gov_step_wise.c index e0fdc497bfcc..65974fe8be0d 100644 --- a/drivers/thermal/gov_step_wise.c +++ b/drivers/thermal/gov_step_wise.c @@ -93,6 +93,23 @@ static void thermal_zone_trip_update(struct thermal_zone_device *tz, if (instance->initialized && old_target == instance->target) continue; + if (trip->type == THERMAL_TRIP_PASSIVE) { + /* + * If the target state for this thermal instance + * changes from THERMAL_NO_TARGET to something else, + * ensure that the zone temperature will be updated + * (assuming enabled passive cooling) until it becomes + * THERMAL_NO_TARGET again, or the cooling device may + * not be reset to its initial state. + */ + if (old_target == THERMAL_NO_TARGET && + instance->target != THERMAL_NO_TARGET) + tz->passive++; + else if (old_target != THERMAL_NO_TARGET && + instance->target == THERMAL_NO_TARGET) + tz->passive--; + } + instance->initialized = true; mutex_lock(&instance->cdev->lock); diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index 30567b499455..d70e76dd3c94 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -999,9 +999,17 @@ __thermal_cooling_device_register(struct device_node *np, if (ret) goto out_cdev_type; + /* + * The cooling device's current state is only needed for debug + * initialization below, so a failure to get it does not cause + * the entire cooling device initialization to fail. However, + * the debug will not work for the device if its initial state + * cannot be determined and drivers are responsible for ensuring + * that this will not happen. + */ ret = cdev->ops->get_cur_state(cdev, ¤t_state); if (ret) - goto out_cdev_type; + current_state = ULONG_MAX; thermal_cooling_device_setup_sysfs(cdev); @@ -1016,7 +1024,8 @@ __thermal_cooling_device_register(struct device_node *np, return ERR_PTR(ret); } - thermal_debug_cdev_add(cdev, current_state); + if (current_state <= cdev->max_state) + thermal_debug_cdev_add(cdev, current_state); /* Add 'this' new cdev to the global cdev list */ mutex_lock(&thermal_list_lock); diff --git a/drivers/thunderbolt/debugfs.c b/drivers/thunderbolt/debugfs.c index 193e9dfc983b..70b52aac3d97 100644 --- a/drivers/thunderbolt/debugfs.c +++ b/drivers/thunderbolt/debugfs.c @@ -943,8 +943,9 @@ static void margining_port_init(struct tb_port *port) debugfs_create_file("run", 0600, dir, port, &margining_run_fops); debugfs_create_file("results", 0600, dir, port, &margining_results_fops); debugfs_create_file("test", 0600, dir, port, &margining_test_fops); - if (independent_voltage_margins(usb4) || - (supports_time(usb4) && independent_time_margins(usb4))) + if (independent_voltage_margins(usb4) == USB4_MARGIN_CAP_0_VOLTAGE_HL || + (supports_time(usb4) && + independent_time_margins(usb4) == USB4_MARGIN_CAP_1_TIME_LR)) debugfs_create_file("margin", 0600, dir, port, &margining_margin_fops); } diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c index f252d0b5a434..5e9ca4376d68 100644 --- a/drivers/tty/n_tty.c +++ b/drivers/tty/n_tty.c @@ -1619,15 +1619,25 @@ static void __receive_buf(struct tty_struct *tty, const u8 *cp, const u8 *fp, else if (ldata->raw || (L_EXTPROC(tty) && !preops)) n_tty_receive_buf_raw(tty, cp, fp, count); else if (tty->closing && !L_EXTPROC(tty)) { - if (la_count > 0) + if (la_count > 0) { n_tty_receive_buf_closing(tty, cp, fp, la_count, true); - if (count > la_count) - n_tty_receive_buf_closing(tty, cp, fp, count - la_count, false); + cp += la_count; + if (fp) + fp += la_count; + count -= la_count; + } + if (count > 0) + n_tty_receive_buf_closing(tty, cp, fp, count, false); } else { - if (la_count > 0) + if (la_count > 0) { n_tty_receive_buf_standard(tty, cp, fp, la_count, true); - if (count > la_count) - n_tty_receive_buf_standard(tty, cp, fp, count - la_count, false); + cp += la_count; + if (fp) + fp += la_count; + count -= la_count; + } + if (count > 0) + n_tty_receive_buf_standard(tty, cp, fp, count, false); flush_echoes(tty); if (tty->ops->flush_chars) diff --git a/drivers/tty/serial/8250/8250_dw.c b/drivers/tty/serial/8250/8250_dw.c index ba9f4dc4e71d..fb809e32c6ae 100644 --- a/drivers/tty/serial/8250/8250_dw.c +++ b/drivers/tty/serial/8250/8250_dw.c @@ -55,6 +55,34 @@ #define DW_UART_QUIRK_SKIP_SET_RATE BIT(2) #define DW_UART_QUIRK_IS_DMA_FC BIT(3) #define DW_UART_QUIRK_APMC0D08 BIT(4) +#define DW_UART_QUIRK_CPR_VALUE BIT(5) + +struct dw8250_platform_data { + u8 usr_reg; + u32 cpr_value; + unsigned int quirks; +}; + +struct dw8250_data { + struct dw8250_port_data data; + const struct dw8250_platform_data *pdata; + + int msr_mask_on; + int msr_mask_off; + struct clk *clk; + struct clk *pclk; + struct notifier_block clk_notifier; + struct work_struct clk_work; + struct reset_control *rst; + + unsigned int skip_autocfg:1; + unsigned int uart_16550_compatible:1; +}; + +static inline struct dw8250_data *to_dw8250_data(struct dw8250_port_data *data) +{ + return container_of(data, struct dw8250_data, data); +} static inline struct dw8250_data *clk_to_dw8250_data(struct notifier_block *nb) { @@ -432,6 +460,10 @@ static void dw8250_prepare_rx_dma(struct uart_8250_port *p) static void dw8250_quirks(struct uart_port *p, struct dw8250_data *data) { unsigned int quirks = data->pdata ? data->pdata->quirks : 0; + u32 cpr_value = data->pdata ? data->pdata->cpr_value : 0; + + if (quirks & DW_UART_QUIRK_CPR_VALUE) + data->data.cpr_value = cpr_value; #ifdef CONFIG_64BIT if (quirks & DW_UART_QUIRK_OCTEON) { @@ -714,8 +746,8 @@ static const struct dw8250_platform_data dw8250_armada_38x_data = { static const struct dw8250_platform_data dw8250_renesas_rzn1_data = { .usr_reg = DW_UART_USR, - .cpr_val = 0x00012f32, - .quirks = DW_UART_QUIRK_IS_DMA_FC, + .cpr_value = 0x00012f32, + .quirks = DW_UART_QUIRK_CPR_VALUE | DW_UART_QUIRK_IS_DMA_FC, }; static const struct dw8250_platform_data dw8250_starfive_jh7100_data = { diff --git a/drivers/tty/serial/8250/8250_dwlib.c b/drivers/tty/serial/8250/8250_dwlib.c index 3e33ddf7bc80..5a2520943dfd 100644 --- a/drivers/tty/serial/8250/8250_dwlib.c +++ b/drivers/tty/serial/8250/8250_dwlib.c @@ -242,7 +242,6 @@ static const struct serial_rs485 dw8250_rs485_supported = { void dw8250_setup_port(struct uart_port *p) { struct dw8250_port_data *pd = p->private_data; - struct dw8250_data *data = to_dw8250_data(pd); struct uart_8250_port *up = up_to_u8250p(p); u32 reg, old_dlf; @@ -278,7 +277,7 @@ void dw8250_setup_port(struct uart_port *p) reg = dw8250_readl_ext(p, DW_UART_CPR); if (!reg) { - reg = data->pdata->cpr_val; + reg = pd->cpr_value; dev_dbg(p->dev, "CPR is not available, using 0x%08x instead\n", reg); } if (!reg) diff --git a/drivers/tty/serial/8250/8250_dwlib.h b/drivers/tty/serial/8250/8250_dwlib.h index f13e91f2cace..7dd2a8e7b780 100644 --- a/drivers/tty/serial/8250/8250_dwlib.h +++ b/drivers/tty/serial/8250/8250_dwlib.h @@ -2,15 +2,10 @@ /* Synopsys DesignWare 8250 library header file. */ #include <linux/io.h> -#include <linux/notifier.h> #include <linux/types.h> -#include <linux/workqueue.h> #include "8250.h" -struct clk; -struct reset_control; - struct dw8250_port_data { /* Port properties */ int line; @@ -19,42 +14,16 @@ struct dw8250_port_data { struct uart_8250_dma dma; /* Hardware configuration */ + u32 cpr_value; u8 dlf_size; /* RS485 variables */ bool hw_rs485_support; }; -struct dw8250_platform_data { - u8 usr_reg; - u32 cpr_val; - unsigned int quirks; -}; - -struct dw8250_data { - struct dw8250_port_data data; - const struct dw8250_platform_data *pdata; - - int msr_mask_on; - int msr_mask_off; - struct clk *clk; - struct clk *pclk; - struct notifier_block clk_notifier; - struct work_struct clk_work; - struct reset_control *rst; - - unsigned int skip_autocfg:1; - unsigned int uart_16550_compatible:1; -}; - void dw8250_do_set_termios(struct uart_port *p, struct ktermios *termios, const struct ktermios *old); void dw8250_setup_port(struct uart_port *p); -static inline struct dw8250_data *to_dw8250_data(struct dw8250_port_data *data) -{ - return container_of(data, struct dw8250_data, data); -} - static inline u32 dw8250_readl_ext(struct uart_port *p, int offset) { if (p->iotype == UPIO_MEM32BE) diff --git a/drivers/tty/serial/8250/8250_pxa.c b/drivers/tty/serial/8250/8250_pxa.c index f1a51b00b1b9..ba96fa913e7f 100644 --- a/drivers/tty/serial/8250/8250_pxa.c +++ b/drivers/tty/serial/8250/8250_pxa.c @@ -125,6 +125,7 @@ static int serial_pxa_probe(struct platform_device *pdev) uart.port.iotype = UPIO_MEM32; uart.port.regshift = 2; uart.port.fifosize = 64; + uart.tx_loadsz = 32; uart.dl_write = serial_pxa_dl_write; ret = serial8250_register_8250_port(&uart); diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig index 4fdd7857ef4d..28e4beeabf8f 100644 --- a/drivers/tty/serial/Kconfig +++ b/drivers/tty/serial/Kconfig @@ -1023,8 +1023,9 @@ config SERIAL_SCCNXP_CONSOLE help Support for console on SCCNXP serial ports. -config SERIAL_SC16IS7XX_CORE +config SERIAL_SC16IS7XX tristate "NXP SC16IS7xx UART support" + depends on SPI_MASTER || I2C select SERIAL_CORE select SERIAL_SC16IS7XX_SPI if SPI_MASTER select SERIAL_SC16IS7XX_I2C if I2C diff --git a/drivers/tty/serial/Makefile b/drivers/tty/serial/Makefile index faa45f2b8bb0..6ff74f0a9530 100644 --- a/drivers/tty/serial/Makefile +++ b/drivers/tty/serial/Makefile @@ -75,7 +75,7 @@ obj-$(CONFIG_SERIAL_SA1100) += sa1100.o obj-$(CONFIG_SERIAL_SAMSUNG) += samsung_tty.o obj-$(CONFIG_SERIAL_SB1250_DUART) += sb1250-duart.o obj-$(CONFIG_SERIAL_SCCNXP) += sccnxp.o -obj-$(CONFIG_SERIAL_SC16IS7XX_CORE) += sc16is7xx.o +obj-$(CONFIG_SERIAL_SC16IS7XX) += sc16is7xx.o obj-$(CONFIG_SERIAL_SC16IS7XX_SPI) += sc16is7xx_spi.o obj-$(CONFIG_SERIAL_SC16IS7XX_I2C) += sc16is7xx_i2c.o obj-$(CONFIG_SERIAL_SH_SCI) += sh-sci.o diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index 2c1a0254d3f4..0c4d60976663 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -622,7 +622,7 @@ static ssize_t uart_write(struct tty_struct *tty, const u8 *buf, size_t count) return -EL3HLT; port = uart_port_lock(state, flags); - if (WARN_ON_ONCE(!state->port.xmit_buf)) { + if (!state->port.xmit_buf) { uart_port_unlock(port, flags); return 0; } diff --git a/drivers/tty/serial/serial_port.c b/drivers/tty/serial/serial_port.c index 91a338d3cb34..d35f1d24156c 100644 --- a/drivers/tty/serial/serial_port.c +++ b/drivers/tty/serial/serial_port.c @@ -64,6 +64,13 @@ static int serial_port_runtime_suspend(struct device *dev) if (port->flags & UPF_DEAD) return 0; + /* + * Nothing to do on pm_runtime_force_suspend(), see + * DEFINE_RUNTIME_DEV_PM_OPS. + */ + if (!pm_runtime_enabled(dev)) + return 0; + uart_port_lock_irqsave(port, &flags); if (!port_dev->tx_enabled) { uart_port_unlock_irqrestore(port, flags); diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 0cf07194bbe8..e5e9da61f15d 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -1366,7 +1366,7 @@ static int ufshcd_clock_scaling_prepare(struct ufs_hba *hba, u64 timeout_us) * make sure that there are no outstanding requests when * clock scaling is in progress */ - ufshcd_scsi_block_requests(hba); + blk_mq_quiesce_tagset(&hba->host->tag_set); mutex_lock(&hba->wb_mutex); down_write(&hba->clk_scaling_lock); @@ -1375,7 +1375,7 @@ static int ufshcd_clock_scaling_prepare(struct ufs_hba *hba, u64 timeout_us) ret = -EBUSY; up_write(&hba->clk_scaling_lock); mutex_unlock(&hba->wb_mutex); - ufshcd_scsi_unblock_requests(hba); + blk_mq_unquiesce_tagset(&hba->host->tag_set); goto out; } @@ -1396,7 +1396,7 @@ static void ufshcd_clock_scaling_unprepare(struct ufs_hba *hba, int err, bool sc mutex_unlock(&hba->wb_mutex); - ufshcd_scsi_unblock_requests(hba); + blk_mq_unquiesce_tagset(&hba->host->tag_set); ufshcd_release(hba); } diff --git a/drivers/usb/Makefile b/drivers/usb/Makefile index 3a9a0dd4be70..949eca0adebe 100644 --- a/drivers/usb/Makefile +++ b/drivers/usb/Makefile @@ -35,6 +35,7 @@ obj-$(CONFIG_USB_R8A66597_HCD) += host/ obj-$(CONFIG_USB_FSL_USB2) += host/ obj-$(CONFIG_USB_FOTG210_HCD) += host/ obj-$(CONFIG_USB_MAX3421_HCD) += host/ +obj-$(CONFIG_USB_XEN_HCD) += host/ obj-$(CONFIG_USB_C67X00_HCD) += c67x00/ diff --git a/drivers/usb/chipidea/core.c b/drivers/usb/chipidea/core.c index bada13f704b6..835bf2428dc6 100644 --- a/drivers/usb/chipidea/core.c +++ b/drivers/usb/chipidea/core.c @@ -1084,6 +1084,10 @@ static int ci_hdrc_probe(struct platform_device *pdev) return -ENODEV; } + ret = ci_ulpi_init(ci); + if (ret) + return ret; + if (ci->platdata->phy) { ci->phy = ci->platdata->phy; } else if (ci->platdata->usb_phy) { @@ -1138,10 +1142,6 @@ static int ci_hdrc_probe(struct platform_device *pdev) goto ulpi_exit; } - ret = ci_ulpi_init(ci); - if (ret) - return ret; - ci->hw_bank.phys = res->start; ci->irq = platform_get_irq(pdev, 0); diff --git a/drivers/usb/chipidea/ulpi.c b/drivers/usb/chipidea/ulpi.c index 89fb51e2c3de..dfec07e8ae1d 100644 --- a/drivers/usb/chipidea/ulpi.c +++ b/drivers/usb/chipidea/ulpi.c @@ -68,6 +68,11 @@ int ci_ulpi_init(struct ci_hdrc *ci) if (ci->platdata->phy_mode != USBPHY_INTERFACE_MODE_ULPI) return 0; + /* + * Set PORTSC correctly so we can read/write ULPI registers for + * identification purposes + */ + hw_phymode_configure(ci); ci->ulpi_ops.read = ci_ulpi_read; ci->ulpi_ops.write = ci_ulpi_write; diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c index c553decb5461..6830be4419e2 100644 --- a/drivers/usb/class/cdc-wdm.c +++ b/drivers/usb/class/cdc-wdm.c @@ -266,14 +266,14 @@ static void wdm_int_callback(struct urb *urb) dev_err(&desc->intf->dev, "Stall on int endpoint\n"); goto sw; /* halt is cleared in work */ default: - dev_err(&desc->intf->dev, + dev_err_ratelimited(&desc->intf->dev, "nonzero urb status received: %d\n", status); break; } } if (urb->actual_length < sizeof(struct usb_cdc_notification)) { - dev_err(&desc->intf->dev, "wdm_int_callback - %d bytes\n", + dev_err_ratelimited(&desc->intf->dev, "wdm_int_callback - %d bytes\n", urb->actual_length); goto exit; } diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index e3366f4d82b9..1ff7d901fede 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -1623,6 +1623,7 @@ static void __usb_hcd_giveback_urb(struct urb *urb) struct usb_hcd *hcd = bus_to_hcd(urb->dev->bus); struct usb_anchor *anchor = urb->anchor; int status = urb->unlinked; + unsigned long flags; urb->hcpriv = NULL; if (unlikely((urb->transfer_flags & URB_SHORT_NOT_OK) && @@ -1640,13 +1641,14 @@ static void __usb_hcd_giveback_urb(struct urb *urb) /* pass ownership to the completion handler */ urb->status = status; /* - * This function can be called in task context inside another remote - * coverage collection section, but kcov doesn't support that kind of - * recursion yet. Only collect coverage in softirq context for now. + * Only collect coverage in the softirq context and disable interrupts + * to avoid scenarios with nested remote coverage collection sections + * that KCOV does not support. + * See the comment next to kcov_remote_start_usb_softirq() for details. */ - kcov_remote_start_usb_softirq((u64)urb->dev->bus->busnum); + flags = kcov_remote_start_usb_softirq((u64)urb->dev->bus->busnum); urb->complete(urb); - kcov_remote_stop_softirq(); + kcov_remote_stop_softirq(flags); usb_anchor_resume_wakeups(anchor); atomic_dec(&urb->use_count); diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index c040d816e626..05881153883e 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -36,6 +36,7 @@ #define PCI_VENDOR_ID_ETRON 0x1b6f #define PCI_DEVICE_ID_EJ168 0x7023 +#define PCI_DEVICE_ID_EJ188 0x7052 #define PCI_DEVICE_ID_INTEL_LYNXPOINT_XHCI 0x8c31 #define PCI_DEVICE_ID_INTEL_LYNXPOINT_LP_XHCI 0x9c31 @@ -395,6 +396,12 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) xhci->quirks |= XHCI_RESET_ON_RESUME; xhci->quirks |= XHCI_BROKEN_STREAMS; } + if (pdev->vendor == PCI_VENDOR_ID_ETRON && + pdev->device == PCI_DEVICE_ID_EJ188) { + xhci->quirks |= XHCI_RESET_ON_RESUME; + xhci->quirks |= XHCI_BROKEN_STREAMS; + } + if (pdev->vendor == PCI_VENDOR_ID_RENESAS && pdev->device == 0x0014) { xhci->quirks |= XHCI_ZERO_64B_REGS; diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 9e90d2952760..fd0cde3d1569 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -1031,13 +1031,27 @@ static int xhci_invalidate_cancelled_tds(struct xhci_virt_ep *ep) break; case TD_DIRTY: /* TD is cached, clear it */ case TD_HALTED: + case TD_CLEARING_CACHE_DEFERRED: + if (cached_td) { + if (cached_td->urb->stream_id != td->urb->stream_id) { + /* Multiple streams case, defer move dq */ + xhci_dbg(xhci, + "Move dq deferred: stream %u URB %p\n", + td->urb->stream_id, td->urb); + td->cancel_status = TD_CLEARING_CACHE_DEFERRED; + break; + } + + /* Should never happen, but clear the TD if it does */ + xhci_warn(xhci, + "Found multiple active URBs %p and %p in stream %u?\n", + td->urb, cached_td->urb, + td->urb->stream_id); + td_to_noop(xhci, ring, cached_td, false); + cached_td->cancel_status = TD_CLEARED; + } + td->cancel_status = TD_CLEARING_CACHE; - if (cached_td) - /* FIXME stream case, several stopped rings */ - xhci_dbg(xhci, - "Move dq past stream %u URB %p instead of stream %u URB %p\n", - td->urb->stream_id, td->urb, - cached_td->urb->stream_id, cached_td->urb); cached_td = td; break; } @@ -1057,10 +1071,16 @@ static int xhci_invalidate_cancelled_tds(struct xhci_virt_ep *ep) if (err) { /* Failed to move past cached td, just set cached TDs to no-op */ list_for_each_entry_safe(td, tmp_td, &ep->cancelled_td_list, cancelled_td_list) { - if (td->cancel_status != TD_CLEARING_CACHE) + /* + * Deferred TDs need to have the deq pointer set after the above command + * completes, so if that failed we just give up on all of them (and + * complain loudly since this could cause issues due to caching). + */ + if (td->cancel_status != TD_CLEARING_CACHE && + td->cancel_status != TD_CLEARING_CACHE_DEFERRED) continue; - xhci_dbg(xhci, "Failed to clear cancelled cached URB %p, mark clear anyway\n", - td->urb); + xhci_warn(xhci, "Failed to clear cancelled cached URB %p, mark clear anyway\n", + td->urb); td_to_noop(xhci, ring, td, false); td->cancel_status = TD_CLEARED; } @@ -1346,6 +1366,7 @@ static void xhci_handle_cmd_set_deq(struct xhci_hcd *xhci, int slot_id, struct xhci_ep_ctx *ep_ctx; struct xhci_slot_ctx *slot_ctx; struct xhci_td *td, *tmp_td; + bool deferred = false; ep_index = TRB_TO_EP_INDEX(le32_to_cpu(trb->generic.field[3])); stream_id = TRB_TO_STREAM_ID(le32_to_cpu(trb->generic.field[2])); @@ -1432,6 +1453,8 @@ static void xhci_handle_cmd_set_deq(struct xhci_hcd *xhci, int slot_id, xhci_dbg(ep->xhci, "%s: Giveback cancelled URB %p TD\n", __func__, td->urb); xhci_td_cleanup(ep->xhci, td, ep_ring, td->status); + } else if (td->cancel_status == TD_CLEARING_CACHE_DEFERRED) { + deferred = true; } else { xhci_dbg(ep->xhci, "%s: Keep cancelled URB %p TD as cancel_status is %d\n", __func__, td->urb, td->cancel_status); @@ -1441,8 +1464,17 @@ cleanup: ep->ep_state &= ~SET_DEQ_PENDING; ep->queued_deq_seg = NULL; ep->queued_deq_ptr = NULL; - /* Restart any rings with pending URBs */ - ring_doorbell_for_active_rings(xhci, slot_id, ep_index); + + if (deferred) { + /* We have more streams to clear */ + xhci_dbg(ep->xhci, "%s: Pending TDs to clear, continuing with invalidation\n", + __func__); + xhci_invalidate_cancelled_tds(ep); + } else { + /* Restart any rings with pending URBs */ + xhci_dbg(ep->xhci, "%s: All TDs cleared, ring doorbell\n", __func__); + ring_doorbell_for_active_rings(xhci, slot_id, ep_index); + } } static void xhci_handle_cmd_reset_ep(struct xhci_hcd *xhci, int slot_id, @@ -2524,9 +2556,8 @@ static int process_bulk_intr_td(struct xhci_hcd *xhci, struct xhci_virt_ep *ep, goto finish_td; case COMP_STOPPED_LENGTH_INVALID: /* stopped on ep trb with invalid length, exclude it */ - ep_trb_len = 0; - remaining = 0; - break; + td->urb->actual_length = sum_trb_lengths(xhci, ep_ring, ep_trb); + goto finish_td; case COMP_USB_TRANSACTION_ERROR: if (xhci->quirks & XHCI_NO_SOFT_RETRY || (ep->err_count++ > MAX_SOFT_RETRY) || diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 30415158ed3c..78d014c4d884 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -1276,6 +1276,7 @@ enum xhci_cancelled_td_status { TD_DIRTY = 0, TD_HALTED, TD_CLEARING_CACHE, + TD_CLEARING_CACHE_DEFERRED, TD_CLEARED, }; diff --git a/drivers/usb/storage/alauda.c b/drivers/usb/storage/alauda.c index 115f05a6201a..40d34cc28344 100644 --- a/drivers/usb/storage/alauda.c +++ b/drivers/usb/storage/alauda.c @@ -105,6 +105,8 @@ struct alauda_info { unsigned char sense_key; unsigned long sense_asc; /* additional sense code */ unsigned long sense_ascq; /* additional sense code qualifier */ + + bool media_initialized; }; #define short_pack(lsb,msb) ( ((u16)(lsb)) | ( ((u16)(msb))<<8 ) ) @@ -476,11 +478,12 @@ static int alauda_check_media(struct us_data *us) } /* Check for media change */ - if (status[0] & 0x08) { + if (status[0] & 0x08 || !info->media_initialized) { usb_stor_dbg(us, "Media change detected\n"); alauda_free_maps(&MEDIA_INFO(us)); - alauda_init_media(us); - + rc = alauda_init_media(us); + if (rc == USB_STOR_TRANSPORT_GOOD) + info->media_initialized = true; info->sense_key = UNIT_ATTENTION; info->sense_asc = 0x28; info->sense_ascq = 0x00; diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 8a1af08f71b6..5d4da962acc8 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -3014,8 +3014,10 @@ static int tcpm_register_source_caps(struct tcpm_port *port) memcpy(caps.pdo, port->source_caps, sizeof(u32) * port->nr_source_caps); caps.role = TYPEC_SOURCE; - if (cap) + if (cap) { usb_power_delivery_unregister_capabilities(cap); + port->partner_source_caps = NULL; + } cap = usb_power_delivery_register_capabilities(port->partner_pd, &caps); if (IS_ERR(cap)) @@ -6172,6 +6174,7 @@ static void _tcpm_pd_hard_reset(struct tcpm_port *port) port->tcpc->set_bist_data(port->tcpc, false); switch (port->state) { + case TOGGLING: case ERROR_RECOVERY: case PORT_RESET: case PORT_RESET_WAIT_OFF: diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index cb52e7b0a2c5..2cc7aedd490f 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -153,8 +153,13 @@ static int ucsi_exec_command(struct ucsi *ucsi, u64 cmd) } if (cci & UCSI_CCI_ERROR) { - if (cmd == UCSI_GET_ERROR_STATUS) + if (cmd == UCSI_GET_ERROR_STATUS) { + ret = ucsi_acknowledge(ucsi, false); + if (ret) + return ret; + return -EIO; + } return ucsi_read_error(ucsi); } diff --git a/drivers/usb/typec/ucsi/ucsi_glink.c b/drivers/usb/typec/ucsi/ucsi_glink.c index f7546bb488c3..985a880e86da 100644 --- a/drivers/usb/typec/ucsi/ucsi_glink.c +++ b/drivers/usb/typec/ucsi/ucsi_glink.c @@ -14,7 +14,7 @@ #include <linux/soc/qcom/pmic_glink.h> #include "ucsi.h" -#define PMIC_GLINK_MAX_PORTS 2 +#define PMIC_GLINK_MAX_PORTS 3 #define UCSI_BUF_SIZE 48 diff --git a/drivers/vfio/device_cdev.c b/drivers/vfio/device_cdev.c index e75da0a70d1f..bb1817bd4ff3 100644 --- a/drivers/vfio/device_cdev.c +++ b/drivers/vfio/device_cdev.c @@ -39,6 +39,13 @@ int vfio_device_fops_cdev_open(struct inode *inode, struct file *filep) filep->private_data = df; + /* + * Use the pseudo fs inode on the device to link all mmaps + * to the same address space, allowing us to unmap all vmas + * associated to this device using unmap_mapping_range(). + */ + filep->f_mapping = device->inode->i_mapping; + return 0; err_put_registration: diff --git a/drivers/vfio/group.c b/drivers/vfio/group.c index 610a429c6191..ded364588d29 100644 --- a/drivers/vfio/group.c +++ b/drivers/vfio/group.c @@ -286,6 +286,13 @@ static struct file *vfio_device_open_file(struct vfio_device *device) */ filep->f_mode |= (FMODE_PREAD | FMODE_PWRITE); + /* + * Use the pseudo fs inode on the device to link all mmaps + * to the same address space, allowing us to unmap all vmas + * associated to this device using unmap_mapping_range(). + */ + filep->f_mapping = device->inode->i_mapping; + if (device->group->type == VFIO_NO_IOMMU) dev_warn(device->dev, "vfio-noiommu device opened by user " "(%s:%d)\n", current->comm, task_pid_nr(current)); diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index 80cae87fff36..987c7921affa 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -1610,100 +1610,20 @@ ssize_t vfio_pci_core_write(struct vfio_device *core_vdev, const char __user *bu } EXPORT_SYMBOL_GPL(vfio_pci_core_write); -/* Return 1 on zap and vma_lock acquired, 0 on contention (only with @try) */ -static int vfio_pci_zap_and_vma_lock(struct vfio_pci_core_device *vdev, bool try) +static void vfio_pci_zap_bars(struct vfio_pci_core_device *vdev) { - struct vfio_pci_mmap_vma *mmap_vma, *tmp; + struct vfio_device *core_vdev = &vdev->vdev; + loff_t start = VFIO_PCI_INDEX_TO_OFFSET(VFIO_PCI_BAR0_REGION_INDEX); + loff_t end = VFIO_PCI_INDEX_TO_OFFSET(VFIO_PCI_ROM_REGION_INDEX); + loff_t len = end - start; - /* - * Lock ordering: - * vma_lock is nested under mmap_lock for vm_ops callback paths. - * The memory_lock semaphore is used by both code paths calling - * into this function to zap vmas and the vm_ops.fault callback - * to protect the memory enable state of the device. - * - * When zapping vmas we need to maintain the mmap_lock => vma_lock - * ordering, which requires using vma_lock to walk vma_list to - * acquire an mm, then dropping vma_lock to get the mmap_lock and - * reacquiring vma_lock. This logic is derived from similar - * requirements in uverbs_user_mmap_disassociate(). - * - * mmap_lock must always be the top-level lock when it is taken. - * Therefore we can only hold the memory_lock write lock when - * vma_list is empty, as we'd need to take mmap_lock to clear - * entries. vma_list can only be guaranteed empty when holding - * vma_lock, thus memory_lock is nested under vma_lock. - * - * This enables the vm_ops.fault callback to acquire vma_lock, - * followed by memory_lock read lock, while already holding - * mmap_lock without risk of deadlock. - */ - while (1) { - struct mm_struct *mm = NULL; - - if (try) { - if (!mutex_trylock(&vdev->vma_lock)) - return 0; - } else { - mutex_lock(&vdev->vma_lock); - } - while (!list_empty(&vdev->vma_list)) { - mmap_vma = list_first_entry(&vdev->vma_list, - struct vfio_pci_mmap_vma, - vma_next); - mm = mmap_vma->vma->vm_mm; - if (mmget_not_zero(mm)) - break; - - list_del(&mmap_vma->vma_next); - kfree(mmap_vma); - mm = NULL; - } - if (!mm) - return 1; - mutex_unlock(&vdev->vma_lock); - - if (try) { - if (!mmap_read_trylock(mm)) { - mmput(mm); - return 0; - } - } else { - mmap_read_lock(mm); - } - if (try) { - if (!mutex_trylock(&vdev->vma_lock)) { - mmap_read_unlock(mm); - mmput(mm); - return 0; - } - } else { - mutex_lock(&vdev->vma_lock); - } - list_for_each_entry_safe(mmap_vma, tmp, - &vdev->vma_list, vma_next) { - struct vm_area_struct *vma = mmap_vma->vma; - - if (vma->vm_mm != mm) - continue; - - list_del(&mmap_vma->vma_next); - kfree(mmap_vma); - - zap_vma_ptes(vma, vma->vm_start, - vma->vm_end - vma->vm_start); - } - mutex_unlock(&vdev->vma_lock); - mmap_read_unlock(mm); - mmput(mm); - } + unmap_mapping_range(core_vdev->inode->i_mapping, start, len, true); } void vfio_pci_zap_and_down_write_memory_lock(struct vfio_pci_core_device *vdev) { - vfio_pci_zap_and_vma_lock(vdev, false); down_write(&vdev->memory_lock); - mutex_unlock(&vdev->vma_lock); + vfio_pci_zap_bars(vdev); } u16 vfio_pci_memory_lock_and_enable(struct vfio_pci_core_device *vdev) @@ -1725,99 +1645,56 @@ void vfio_pci_memory_unlock_and_restore(struct vfio_pci_core_device *vdev, u16 c up_write(&vdev->memory_lock); } -/* Caller holds vma_lock */ -static int __vfio_pci_add_vma(struct vfio_pci_core_device *vdev, - struct vm_area_struct *vma) -{ - struct vfio_pci_mmap_vma *mmap_vma; - - mmap_vma = kmalloc(sizeof(*mmap_vma), GFP_KERNEL_ACCOUNT); - if (!mmap_vma) - return -ENOMEM; - - mmap_vma->vma = vma; - list_add(&mmap_vma->vma_next, &vdev->vma_list); - - return 0; -} - -/* - * Zap mmaps on open so that we can fault them in on access and therefore - * our vma_list only tracks mappings accessed since last zap. - */ -static void vfio_pci_mmap_open(struct vm_area_struct *vma) -{ - zap_vma_ptes(vma, vma->vm_start, vma->vm_end - vma->vm_start); -} - -static void vfio_pci_mmap_close(struct vm_area_struct *vma) +static unsigned long vma_to_pfn(struct vm_area_struct *vma) { struct vfio_pci_core_device *vdev = vma->vm_private_data; - struct vfio_pci_mmap_vma *mmap_vma; + int index = vma->vm_pgoff >> (VFIO_PCI_OFFSET_SHIFT - PAGE_SHIFT); + u64 pgoff; - mutex_lock(&vdev->vma_lock); - list_for_each_entry(mmap_vma, &vdev->vma_list, vma_next) { - if (mmap_vma->vma == vma) { - list_del(&mmap_vma->vma_next); - kfree(mmap_vma); - break; - } - } - mutex_unlock(&vdev->vma_lock); + pgoff = vma->vm_pgoff & + ((1U << (VFIO_PCI_OFFSET_SHIFT - PAGE_SHIFT)) - 1); + + return (pci_resource_start(vdev->pdev, index) >> PAGE_SHIFT) + pgoff; } static vm_fault_t vfio_pci_mmap_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct vfio_pci_core_device *vdev = vma->vm_private_data; - struct vfio_pci_mmap_vma *mmap_vma; - vm_fault_t ret = VM_FAULT_NOPAGE; + unsigned long pfn, pgoff = vmf->pgoff - vma->vm_pgoff; + unsigned long addr = vma->vm_start; + vm_fault_t ret = VM_FAULT_SIGBUS; + + pfn = vma_to_pfn(vma); - mutex_lock(&vdev->vma_lock); down_read(&vdev->memory_lock); - /* - * Memory region cannot be accessed if the low power feature is engaged - * or memory access is disabled. - */ - if (vdev->pm_runtime_engaged || !__vfio_pci_memory_enabled(vdev)) { - ret = VM_FAULT_SIGBUS; - goto up_out; - } + if (vdev->pm_runtime_engaged || !__vfio_pci_memory_enabled(vdev)) + goto out_unlock; + + ret = vmf_insert_pfn(vma, vmf->address, pfn + pgoff); + if (ret & VM_FAULT_ERROR) + goto out_unlock; /* - * We populate the whole vma on fault, so we need to test whether - * the vma has already been mapped, such as for concurrent faults - * to the same vma. io_remap_pfn_range() will trigger a BUG_ON if - * we ask it to fill the same range again. + * Pre-fault the remainder of the vma, abort further insertions and + * supress error if fault is encountered during pre-fault. */ - list_for_each_entry(mmap_vma, &vdev->vma_list, vma_next) { - if (mmap_vma->vma == vma) - goto up_out; - } - - if (io_remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff, - vma->vm_end - vma->vm_start, - vma->vm_page_prot)) { - ret = VM_FAULT_SIGBUS; - zap_vma_ptes(vma, vma->vm_start, vma->vm_end - vma->vm_start); - goto up_out; - } + for (; addr < vma->vm_end; addr += PAGE_SIZE, pfn++) { + if (addr == vmf->address) + continue; - if (__vfio_pci_add_vma(vdev, vma)) { - ret = VM_FAULT_OOM; - zap_vma_ptes(vma, vma->vm_start, vma->vm_end - vma->vm_start); + if (vmf_insert_pfn(vma, addr, pfn) & VM_FAULT_ERROR) + break; } -up_out: +out_unlock: up_read(&vdev->memory_lock); - mutex_unlock(&vdev->vma_lock); + return ret; } static const struct vm_operations_struct vfio_pci_mmap_ops = { - .open = vfio_pci_mmap_open, - .close = vfio_pci_mmap_close, .fault = vfio_pci_mmap_fault, }; @@ -1880,11 +1757,12 @@ int vfio_pci_core_mmap(struct vfio_device *core_vdev, struct vm_area_struct *vma vma->vm_private_data = vdev; vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); - vma->vm_pgoff = (pci_resource_start(pdev, index) >> PAGE_SHIFT) + pgoff; + vma->vm_page_prot = pgprot_decrypted(vma->vm_page_prot); /* - * See remap_pfn_range(), called from vfio_pci_fault() but we can't - * change vm_flags within the fault handler. Set them now. + * Set vm_flags now, they should not be changed in the fault handler. + * We want the same flags and page protection (decrypted above) as + * io_remap_pfn_range() would set. * * VM_ALLOW_ANY_UNCACHED: The VMA flag is implemented for ARM64, * allowing KVM stage 2 device mapping attributes to use Normal-NC @@ -2202,8 +2080,6 @@ int vfio_pci_core_init_dev(struct vfio_device *core_vdev) mutex_init(&vdev->ioeventfds_lock); INIT_LIST_HEAD(&vdev->dummy_resources_list); INIT_LIST_HEAD(&vdev->ioeventfds_list); - mutex_init(&vdev->vma_lock); - INIT_LIST_HEAD(&vdev->vma_list); INIT_LIST_HEAD(&vdev->sriov_pfs_item); init_rwsem(&vdev->memory_lock); xa_init(&vdev->ctx); @@ -2219,7 +2095,6 @@ void vfio_pci_core_release_dev(struct vfio_device *core_vdev) mutex_destroy(&vdev->igate); mutex_destroy(&vdev->ioeventfds_lock); - mutex_destroy(&vdev->vma_lock); kfree(vdev->region); kfree(vdev->pm_save); } @@ -2497,26 +2372,15 @@ unwind: return ret; } -/* - * We need to get memory_lock for each device, but devices can share mmap_lock, - * therefore we need to zap and hold the vma_lock for each device, and only then - * get each memory_lock. - */ static int vfio_pci_dev_set_hot_reset(struct vfio_device_set *dev_set, struct vfio_pci_group_info *groups, struct iommufd_ctx *iommufd_ctx) { - struct vfio_pci_core_device *cur_mem; - struct vfio_pci_core_device *cur_vma; - struct vfio_pci_core_device *cur; + struct vfio_pci_core_device *vdev; struct pci_dev *pdev; - bool is_mem = true; int ret; mutex_lock(&dev_set->lock); - cur_mem = list_first_entry(&dev_set->device_list, - struct vfio_pci_core_device, - vdev.dev_set_list); pdev = vfio_pci_dev_set_resettable(dev_set); if (!pdev) { @@ -2533,7 +2397,7 @@ static int vfio_pci_dev_set_hot_reset(struct vfio_device_set *dev_set, if (ret) goto err_unlock; - list_for_each_entry(cur_vma, &dev_set->device_list, vdev.dev_set_list) { + list_for_each_entry(vdev, &dev_set->device_list, vdev.dev_set_list) { bool owned; /* @@ -2557,38 +2421,38 @@ static int vfio_pci_dev_set_hot_reset(struct vfio_device_set *dev_set, * Otherwise, reset is not allowed. */ if (iommufd_ctx) { - int devid = vfio_iommufd_get_dev_id(&cur_vma->vdev, + int devid = vfio_iommufd_get_dev_id(&vdev->vdev, iommufd_ctx); owned = (devid > 0 || devid == -ENOENT); } else { - owned = vfio_dev_in_groups(&cur_vma->vdev, groups); + owned = vfio_dev_in_groups(&vdev->vdev, groups); } if (!owned) { ret = -EINVAL; - goto err_undo; + break; } /* - * Locking multiple devices is prone to deadlock, runaway and - * unwind if we hit contention. + * Take the memory write lock for each device and zap BAR + * mappings to prevent the user accessing the device while in + * reset. Locking multiple devices is prone to deadlock, + * runaway and unwind if we hit contention. */ - if (!vfio_pci_zap_and_vma_lock(cur_vma, true)) { + if (!down_write_trylock(&vdev->memory_lock)) { ret = -EBUSY; - goto err_undo; + break; } + + vfio_pci_zap_bars(vdev); } - cur_vma = NULL; - list_for_each_entry(cur_mem, &dev_set->device_list, vdev.dev_set_list) { - if (!down_write_trylock(&cur_mem->memory_lock)) { - ret = -EBUSY; - goto err_undo; - } - mutex_unlock(&cur_mem->vma_lock); + if (!list_entry_is_head(vdev, + &dev_set->device_list, vdev.dev_set_list)) { + vdev = list_prev_entry(vdev, vdev.dev_set_list); + goto err_undo; } - cur_mem = NULL; /* * The pci_reset_bus() will reset all the devices in the bus. @@ -2599,25 +2463,22 @@ static int vfio_pci_dev_set_hot_reset(struct vfio_device_set *dev_set, * cause the PCI config space reset without restoring the original * state (saved locally in 'vdev->pm_save'). */ - list_for_each_entry(cur, &dev_set->device_list, vdev.dev_set_list) - vfio_pci_set_power_state(cur, PCI_D0); + list_for_each_entry(vdev, &dev_set->device_list, vdev.dev_set_list) + vfio_pci_set_power_state(vdev, PCI_D0); ret = pci_reset_bus(pdev); + vdev = list_last_entry(&dev_set->device_list, + struct vfio_pci_core_device, vdev.dev_set_list); + err_undo: - list_for_each_entry(cur, &dev_set->device_list, vdev.dev_set_list) { - if (cur == cur_mem) - is_mem = false; - if (cur == cur_vma) - break; - if (is_mem) - up_write(&cur->memory_lock); - else - mutex_unlock(&cur->vma_lock); - } + list_for_each_entry_from_reverse(vdev, &dev_set->device_list, + vdev.dev_set_list) + up_write(&vdev->memory_lock); + + list_for_each_entry(vdev, &dev_set->device_list, vdev.dev_set_list) + pm_runtime_put(&vdev->pdev->dev); - list_for_each_entry(cur, &dev_set->device_list, vdev.dev_set_list) - pm_runtime_put(&cur->pdev->dev); err_unlock: mutex_unlock(&dev_set->lock); return ret; diff --git a/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c index e97d796a54fb..a5a62d9d963f 100644 --- a/drivers/vfio/vfio_main.c +++ b/drivers/vfio/vfio_main.c @@ -22,8 +22,10 @@ #include <linux/list.h> #include <linux/miscdevice.h> #include <linux/module.h> +#include <linux/mount.h> #include <linux/mutex.h> #include <linux/pci.h> +#include <linux/pseudo_fs.h> #include <linux/rwsem.h> #include <linux/sched.h> #include <linux/slab.h> @@ -43,9 +45,13 @@ #define DRIVER_AUTHOR "Alex Williamson <[email protected]>" #define DRIVER_DESC "VFIO - User Level meta-driver" +#define VFIO_MAGIC 0x5646494f /* "VFIO" */ + static struct vfio { struct class *device_class; struct ida device_ida; + struct vfsmount *vfs_mount; + int fs_count; } vfio; #ifdef CONFIG_VFIO_NOIOMMU @@ -186,6 +192,8 @@ static void vfio_device_release(struct device *dev) if (device->ops->release) device->ops->release(device); + iput(device->inode); + simple_release_fs(&vfio.vfs_mount, &vfio.fs_count); kvfree(device); } @@ -228,6 +236,34 @@ out_free: } EXPORT_SYMBOL_GPL(_vfio_alloc_device); +static int vfio_fs_init_fs_context(struct fs_context *fc) +{ + return init_pseudo(fc, VFIO_MAGIC) ? 0 : -ENOMEM; +} + +static struct file_system_type vfio_fs_type = { + .name = "vfio", + .owner = THIS_MODULE, + .init_fs_context = vfio_fs_init_fs_context, + .kill_sb = kill_anon_super, +}; + +static struct inode *vfio_fs_inode_new(void) +{ + struct inode *inode; + int ret; + + ret = simple_pin_fs(&vfio_fs_type, &vfio.vfs_mount, &vfio.fs_count); + if (ret) + return ERR_PTR(ret); + + inode = alloc_anon_inode(vfio.vfs_mount->mnt_sb); + if (IS_ERR(inode)) + simple_release_fs(&vfio.vfs_mount, &vfio.fs_count); + + return inode; +} + /* * Initialize a vfio_device so it can be registered to vfio core. */ @@ -246,6 +282,11 @@ static int vfio_init_device(struct vfio_device *device, struct device *dev, init_completion(&device->comp); device->dev = dev; device->ops = ops; + device->inode = vfio_fs_inode_new(); + if (IS_ERR(device->inode)) { + ret = PTR_ERR(device->inode); + goto out_inode; + } if (ops->init) { ret = ops->init(device); @@ -260,6 +301,9 @@ static int vfio_init_device(struct vfio_device *device, struct device *dev, return 0; out_uninit: + iput(device->inode); + simple_release_fs(&vfio.vfs_mount, &vfio.fs_count); +out_inode: vfio_release_device_set(device); ida_free(&vfio.device_ida, device->index); return ret; diff --git a/fs/jfs/xattr.c b/fs/jfs/xattr.c index 0fb7afac298e..9987055293b3 100644 --- a/fs/jfs/xattr.c +++ b/fs/jfs/xattr.c @@ -557,9 +557,11 @@ static int ea_get(struct inode *inode, struct ea_buffer *ea_buf, int min_size) size_check: if (EALIST_SIZE(ea_buf->xattr) != ea_size) { + int size = min_t(int, EALIST_SIZE(ea_buf->xattr), ea_size); + printk(KERN_ERR "ea_get: invalid extended attribute\n"); print_hex_dump(KERN_ERR, "", DUMP_PREFIX_ADDRESS, 16, 1, - ea_buf->xattr, ea_size, 1); + ea_buf->xattr, size, 1); ea_release(inode, ea_buf); rc = -EIO; goto clean_up; diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index 604fea3a26ff..86807086b2df 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -479,12 +479,6 @@ bail: return status; } - -struct ocfs2_triggers { - struct jbd2_buffer_trigger_type ot_triggers; - int ot_offset; -}; - static inline struct ocfs2_triggers *to_ocfs2_trigger(struct jbd2_buffer_trigger_type *triggers) { return container_of(triggers, struct ocfs2_triggers, ot_triggers); @@ -548,85 +542,76 @@ static void ocfs2_db_frozen_trigger(struct jbd2_buffer_trigger_type *triggers, static void ocfs2_abort_trigger(struct jbd2_buffer_trigger_type *triggers, struct buffer_head *bh) { + struct ocfs2_triggers *ot = to_ocfs2_trigger(triggers); + mlog(ML_ERROR, "ocfs2_abort_trigger called by JBD2. bh = 0x%lx, " "bh->b_blocknr = %llu\n", (unsigned long)bh, (unsigned long long)bh->b_blocknr); - ocfs2_error(bh->b_assoc_map->host->i_sb, + ocfs2_error(ot->sb, "JBD2 has aborted our journal, ocfs2 cannot continue\n"); } -static struct ocfs2_triggers di_triggers = { - .ot_triggers = { - .t_frozen = ocfs2_frozen_trigger, - .t_abort = ocfs2_abort_trigger, - }, - .ot_offset = offsetof(struct ocfs2_dinode, i_check), -}; - -static struct ocfs2_triggers eb_triggers = { - .ot_triggers = { - .t_frozen = ocfs2_frozen_trigger, - .t_abort = ocfs2_abort_trigger, - }, - .ot_offset = offsetof(struct ocfs2_extent_block, h_check), -}; - -static struct ocfs2_triggers rb_triggers = { - .ot_triggers = { - .t_frozen = ocfs2_frozen_trigger, - .t_abort = ocfs2_abort_trigger, - }, - .ot_offset = offsetof(struct ocfs2_refcount_block, rf_check), -}; - -static struct ocfs2_triggers gd_triggers = { - .ot_triggers = { - .t_frozen = ocfs2_frozen_trigger, - .t_abort = ocfs2_abort_trigger, - }, - .ot_offset = offsetof(struct ocfs2_group_desc, bg_check), -}; - -static struct ocfs2_triggers db_triggers = { - .ot_triggers = { - .t_frozen = ocfs2_db_frozen_trigger, - .t_abort = ocfs2_abort_trigger, - }, -}; +static void ocfs2_setup_csum_triggers(struct super_block *sb, + enum ocfs2_journal_trigger_type type, + struct ocfs2_triggers *ot) +{ + BUG_ON(type >= OCFS2_JOURNAL_TRIGGER_COUNT); -static struct ocfs2_triggers xb_triggers = { - .ot_triggers = { - .t_frozen = ocfs2_frozen_trigger, - .t_abort = ocfs2_abort_trigger, - }, - .ot_offset = offsetof(struct ocfs2_xattr_block, xb_check), -}; + switch (type) { + case OCFS2_JTR_DI: + ot->ot_triggers.t_frozen = ocfs2_frozen_trigger; + ot->ot_offset = offsetof(struct ocfs2_dinode, i_check); + break; + case OCFS2_JTR_EB: + ot->ot_triggers.t_frozen = ocfs2_frozen_trigger; + ot->ot_offset = offsetof(struct ocfs2_extent_block, h_check); + break; + case OCFS2_JTR_RB: + ot->ot_triggers.t_frozen = ocfs2_frozen_trigger; + ot->ot_offset = offsetof(struct ocfs2_refcount_block, rf_check); + break; + case OCFS2_JTR_GD: + ot->ot_triggers.t_frozen = ocfs2_frozen_trigger; + ot->ot_offset = offsetof(struct ocfs2_group_desc, bg_check); + break; + case OCFS2_JTR_DB: + ot->ot_triggers.t_frozen = ocfs2_db_frozen_trigger; + break; + case OCFS2_JTR_XB: + ot->ot_triggers.t_frozen = ocfs2_frozen_trigger; + ot->ot_offset = offsetof(struct ocfs2_xattr_block, xb_check); + break; + case OCFS2_JTR_DQ: + ot->ot_triggers.t_frozen = ocfs2_dq_frozen_trigger; + break; + case OCFS2_JTR_DR: + ot->ot_triggers.t_frozen = ocfs2_frozen_trigger; + ot->ot_offset = offsetof(struct ocfs2_dx_root_block, dr_check); + break; + case OCFS2_JTR_DL: + ot->ot_triggers.t_frozen = ocfs2_frozen_trigger; + ot->ot_offset = offsetof(struct ocfs2_dx_leaf, dl_check); + break; + case OCFS2_JTR_NONE: + /* To make compiler happy... */ + return; + } -static struct ocfs2_triggers dq_triggers = { - .ot_triggers = { - .t_frozen = ocfs2_dq_frozen_trigger, - .t_abort = ocfs2_abort_trigger, - }, -}; + ot->ot_triggers.t_abort = ocfs2_abort_trigger; + ot->sb = sb; +} -static struct ocfs2_triggers dr_triggers = { - .ot_triggers = { - .t_frozen = ocfs2_frozen_trigger, - .t_abort = ocfs2_abort_trigger, - }, - .ot_offset = offsetof(struct ocfs2_dx_root_block, dr_check), -}; +void ocfs2_initialize_journal_triggers(struct super_block *sb, + struct ocfs2_triggers triggers[]) +{ + enum ocfs2_journal_trigger_type type; -static struct ocfs2_triggers dl_triggers = { - .ot_triggers = { - .t_frozen = ocfs2_frozen_trigger, - .t_abort = ocfs2_abort_trigger, - }, - .ot_offset = offsetof(struct ocfs2_dx_leaf, dl_check), -}; + for (type = OCFS2_JTR_DI; type < OCFS2_JOURNAL_TRIGGER_COUNT; type++) + ocfs2_setup_csum_triggers(sb, type, &triggers[type]); +} static int __ocfs2_journal_access(handle_t *handle, struct ocfs2_caching_info *ci, @@ -708,56 +693,91 @@ static int __ocfs2_journal_access(handle_t *handle, int ocfs2_journal_access_di(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *bh, int type) { - return __ocfs2_journal_access(handle, ci, bh, &di_triggers, type); + struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci)); + + return __ocfs2_journal_access(handle, ci, bh, + &osb->s_journal_triggers[OCFS2_JTR_DI], + type); } int ocfs2_journal_access_eb(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *bh, int type) { - return __ocfs2_journal_access(handle, ci, bh, &eb_triggers, type); + struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci)); + + return __ocfs2_journal_access(handle, ci, bh, + &osb->s_journal_triggers[OCFS2_JTR_EB], + type); } int ocfs2_journal_access_rb(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *bh, int type) { - return __ocfs2_journal_access(handle, ci, bh, &rb_triggers, + struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci)); + + return __ocfs2_journal_access(handle, ci, bh, + &osb->s_journal_triggers[OCFS2_JTR_RB], type); } int ocfs2_journal_access_gd(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *bh, int type) { - return __ocfs2_journal_access(handle, ci, bh, &gd_triggers, type); + struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci)); + + return __ocfs2_journal_access(handle, ci, bh, + &osb->s_journal_triggers[OCFS2_JTR_GD], + type); } int ocfs2_journal_access_db(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *bh, int type) { - return __ocfs2_journal_access(handle, ci, bh, &db_triggers, type); + struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci)); + + return __ocfs2_journal_access(handle, ci, bh, + &osb->s_journal_triggers[OCFS2_JTR_DB], + type); } int ocfs2_journal_access_xb(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *bh, int type) { - return __ocfs2_journal_access(handle, ci, bh, &xb_triggers, type); + struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci)); + + return __ocfs2_journal_access(handle, ci, bh, + &osb->s_journal_triggers[OCFS2_JTR_XB], + type); } int ocfs2_journal_access_dq(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *bh, int type) { - return __ocfs2_journal_access(handle, ci, bh, &dq_triggers, type); + struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci)); + + return __ocfs2_journal_access(handle, ci, bh, + &osb->s_journal_triggers[OCFS2_JTR_DQ], + type); } int ocfs2_journal_access_dr(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *bh, int type) { - return __ocfs2_journal_access(handle, ci, bh, &dr_triggers, type); + struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci)); + + return __ocfs2_journal_access(handle, ci, bh, + &osb->s_journal_triggers[OCFS2_JTR_DR], + type); } int ocfs2_journal_access_dl(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *bh, int type) { - return __ocfs2_journal_access(handle, ci, bh, &dl_triggers, type); + struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci)); + + return __ocfs2_journal_access(handle, ci, bh, + &osb->s_journal_triggers[OCFS2_JTR_DL], + type); } int ocfs2_journal_access(handle_t *handle, struct ocfs2_caching_info *ci, @@ -778,13 +798,15 @@ void ocfs2_journal_dirty(handle_t *handle, struct buffer_head *bh) if (!is_handle_aborted(handle)) { journal_t *journal = handle->h_transaction->t_journal; - mlog(ML_ERROR, "jbd2_journal_dirty_metadata failed. " - "Aborting transaction and journal.\n"); + mlog(ML_ERROR, "jbd2_journal_dirty_metadata failed: " + "handle type %u started at line %u, credits %u/%u " + "errcode %d. Aborting transaction and journal.\n", + handle->h_type, handle->h_line_no, + handle->h_requested_credits, + jbd2_handle_buffer_credits(handle), status); handle->h_err = status; jbd2_journal_abort_handle(handle); jbd2_journal_abort(journal, status); - ocfs2_abort(bh->b_assoc_map->host->i_sb, - "Journal already aborted.\n"); } } } diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index a503c553bab2..8fe826143d7b 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -284,6 +284,30 @@ enum ocfs2_mount_options #define OCFS2_OSB_ERROR_FS 0x0004 #define OCFS2_DEFAULT_ATIME_QUANTUM 60 +struct ocfs2_triggers { + struct jbd2_buffer_trigger_type ot_triggers; + int ot_offset; + struct super_block *sb; +}; + +enum ocfs2_journal_trigger_type { + OCFS2_JTR_DI, + OCFS2_JTR_EB, + OCFS2_JTR_RB, + OCFS2_JTR_GD, + OCFS2_JTR_DB, + OCFS2_JTR_XB, + OCFS2_JTR_DQ, + OCFS2_JTR_DR, + OCFS2_JTR_DL, + OCFS2_JTR_NONE /* This must be the last entry */ +}; + +#define OCFS2_JOURNAL_TRIGGER_COUNT OCFS2_JTR_NONE + +void ocfs2_initialize_journal_triggers(struct super_block *sb, + struct ocfs2_triggers triggers[]); + struct ocfs2_journal; struct ocfs2_slot_info; struct ocfs2_recovery_map; @@ -351,6 +375,9 @@ struct ocfs2_super struct ocfs2_journal *journal; unsigned long osb_commit_interval; + /* Journal triggers for checksum */ + struct ocfs2_triggers s_journal_triggers[OCFS2_JOURNAL_TRIGGER_COUNT]; + struct delayed_work la_enable_wq; /* diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 8aabaed2c1cb..afee70125ae3 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -1075,9 +1075,11 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) debugfs_create_file("fs_state", S_IFREG|S_IRUSR, osb->osb_debug_root, osb, &ocfs2_osb_debug_fops); - if (ocfs2_meta_ecc(osb)) + if (ocfs2_meta_ecc(osb)) { + ocfs2_initialize_journal_triggers(sb, osb->s_journal_triggers); ocfs2_blockcheck_stats_debugfs_install( &osb->osb_ecc_stats, osb->osb_debug_root); + } status = ocfs2_mount_volume(sb); if (status < 0) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index b6c5a8ea3887..e7e07891781b 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -630,6 +630,12 @@ smb2_get_name(const char *src, const int maxlen, struct nls_table *local_nls) return name; } + if (*name == '\\') { + pr_err("not allow directory name included leading slash\n"); + kfree(name); + return ERR_PTR(-EINVAL); + } + ksmbd_conv_path_to_unix(name); ksmbd_strip_last_slash(name); return name; @@ -2361,7 +2367,8 @@ static int smb2_set_ea(struct smb2_ea_info *eabuf, unsigned int buf_len, if (rc > 0) { rc = ksmbd_vfs_remove_xattr(idmap, path, - attr_name); + attr_name, + get_write); if (rc < 0) { ksmbd_debug(SMB, @@ -2376,7 +2383,7 @@ static int smb2_set_ea(struct smb2_ea_info *eabuf, unsigned int buf_len, } else { rc = ksmbd_vfs_setxattr(idmap, path, attr_name, value, le16_to_cpu(eabuf->EaValueLength), - 0, true); + 0, get_write); if (rc < 0) { ksmbd_debug(SMB, "ksmbd_vfs_setxattr is failed(%d)\n", @@ -2468,7 +2475,7 @@ static int smb2_remove_smb_xattrs(const struct path *path) !strncmp(&name[XATTR_USER_PREFIX_LEN], STREAM_PREFIX, STREAM_PREFIX_LEN)) { err = ksmbd_vfs_remove_xattr(idmap, path, - name); + name, true); if (err) ksmbd_debug(SMB, "remove xattr failed : %s\n", name); @@ -2842,20 +2849,11 @@ int smb2_open(struct ksmbd_work *work) } if (req->NameLength) { - if ((req->CreateOptions & FILE_DIRECTORY_FILE_LE) && - *(char *)req->Buffer == '\\') { - pr_err("not allow directory name included leading slash\n"); - rc = -EINVAL; - goto err_out2; - } - name = smb2_get_name((char *)req + le16_to_cpu(req->NameOffset), le16_to_cpu(req->NameLength), work->conn->local_nls); if (IS_ERR(name)) { rc = PTR_ERR(name); - if (rc != -ENOMEM) - rc = -ENOENT; name = NULL; goto err_out2; } diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c index 51b1b0bed616..9e859ba010cf 100644 --- a/fs/smb/server/vfs.c +++ b/fs/smb/server/vfs.c @@ -1058,16 +1058,21 @@ int ksmbd_vfs_fqar_lseek(struct ksmbd_file *fp, loff_t start, loff_t length, } int ksmbd_vfs_remove_xattr(struct mnt_idmap *idmap, - const struct path *path, char *attr_name) + const struct path *path, char *attr_name, + bool get_write) { int err; - err = mnt_want_write(path->mnt); - if (err) - return err; + if (get_write == true) { + err = mnt_want_write(path->mnt); + if (err) + return err; + } err = vfs_removexattr(idmap, path->dentry, attr_name); - mnt_drop_write(path->mnt); + + if (get_write == true) + mnt_drop_write(path->mnt); return err; } @@ -1380,7 +1385,7 @@ int ksmbd_vfs_remove_sd_xattrs(struct mnt_idmap *idmap, const struct path *path) ksmbd_debug(SMB, "%s, len %zd\n", name, strlen(name)); if (!strncmp(name, XATTR_NAME_SD, XATTR_NAME_SD_LEN)) { - err = ksmbd_vfs_remove_xattr(idmap, path, name); + err = ksmbd_vfs_remove_xattr(idmap, path, name, true); if (err) ksmbd_debug(SMB, "remove xattr failed : %s\n", name); } diff --git a/fs/smb/server/vfs.h b/fs/smb/server/vfs.h index cfe1c8092f23..cb76f4b5bafe 100644 --- a/fs/smb/server/vfs.h +++ b/fs/smb/server/vfs.h @@ -114,7 +114,8 @@ int ksmbd_vfs_setxattr(struct mnt_idmap *idmap, int ksmbd_vfs_xattr_stream_name(char *stream_name, char **xattr_stream_name, size_t *xattr_stream_name_size, int s_type); int ksmbd_vfs_remove_xattr(struct mnt_idmap *idmap, - const struct path *path, char *attr_name); + const struct path *path, char *attr_name, + bool get_write); int ksmbd_vfs_kern_path_locked(struct ksmbd_work *work, char *name, unsigned int flags, struct path *parent_path, struct path *path, bool caseless); diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c index 6cb599cd287e..8b2e37c8716e 100644 --- a/fs/smb/server/vfs_cache.c +++ b/fs/smb/server/vfs_cache.c @@ -254,7 +254,8 @@ static void __ksmbd_inode_close(struct ksmbd_file *fp) ci->m_flags &= ~S_DEL_ON_CLS_STREAM; err = ksmbd_vfs_remove_xattr(file_mnt_idmap(filp), &filp->f_path, - fp->stream.name); + fp->stream.name, + true); if (err) pr_err("remove xattr failed : %s\n", fp->stream.name); diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index 09e4bf949bf8..6b56f0f6d4c1 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -1038,11 +1038,12 @@ xfs_log_sb( * and hence we don't need have to update it here. */ if (xfs_has_lazysbcount(mp)) { - mp->m_sb.sb_icount = percpu_counter_sum(&mp->m_icount); + mp->m_sb.sb_icount = percpu_counter_sum_positive(&mp->m_icount); mp->m_sb.sb_ifree = min_t(uint64_t, - percpu_counter_sum(&mp->m_ifree), + percpu_counter_sum_positive(&mp->m_ifree), mp->m_sb.sb_icount); - mp->m_sb.sb_fdblocks = percpu_counter_sum(&mp->m_fdblocks); + mp->m_sb.sb_fdblocks = + percpu_counter_sum_positive(&mp->m_fdblocks); } xfs_sb_to_disk(bp->b_addr, &mp->m_sb); diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index 94d0fc3bd412..80dc36f9d527 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -663,6 +663,10 @@ ACPI_EXTERNAL_RETURN_STATUS(acpi_status acpi_adr_space_type space_id)) ACPI_EXTERNAL_RETURN_STATUS(acpi_status + acpi_execute_orphan_reg_method(acpi_handle device, + acpi_adr_space_type + space_id)) +ACPI_EXTERNAL_RETURN_STATUS(acpi_status acpi_remove_address_space_handler(acpi_handle device, acpi_adr_space_type diff --git a/include/linux/bio.h b/include/linux/bio.h index d5379548d684..818e93612947 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -731,6 +731,7 @@ static inline bool bioset_initialized(struct bio_set *bs) bip_for_each_vec(_bvl, _bio->bi_integrity, _iter) int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t len, u32 seed); +void bio_integrity_unmap_free_user(struct bio *bio); extern struct bio_integrity_payload *bio_integrity_alloc(struct bio *, gfp_t, unsigned int); extern int bio_integrity_add_page(struct bio *, struct page *, unsigned int, unsigned int); extern bool bio_integrity_prep(struct bio *); @@ -807,6 +808,9 @@ static inline int bio_integrity_map_user(struct bio *bio, void __user *ubuf, { return -EINVAL; } +static inline void bio_integrity_unmap_free_user(struct bio *bio) +{ +} #endif /* CONFIG_BLK_DEV_INTEGRITY */ diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 50aa87f8d77f..e4070fb02b11 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -746,6 +746,8 @@ struct bpf_verifier_env { /* Same as scratched_regs but for stack slots */ u64 scratched_stack_slots; u64 prev_log_pos, prev_insn_print_pos; + /* buffer used to temporary hold constants as scalar registers */ + struct bpf_reg_state fake_reg[2]; /* buffer used to generate temporary string representations, * e.g., in reg_type_str() to generate reg_type string */ diff --git a/include/linux/btf.h b/include/linux/btf.h index f9e56fd12a9f..7c3e40c3295e 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -82,7 +82,7 @@ * as to avoid issues such as the compiler inlining or eliding either a static * kfunc, or a global kfunc in an LTO build. */ -#define __bpf_kfunc __used noinline +#define __bpf_kfunc __used __retain noinline #define __bpf_kfunc_start_defs() \ __diag_push(); \ diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 93600de3800b..f14c275950b5 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -143,6 +143,29 @@ static inline void __chk_io_ptr(const volatile void __iomem *ptr) { } # define __preserve_most #endif +/* + * Annotating a function/variable with __retain tells the compiler to place + * the object in its own section and set the flag SHF_GNU_RETAIN. This flag + * instructs the linker to retain the object during garbage-cleanup or LTO + * phases. + * + * Note that the __used macro is also used to prevent functions or data + * being optimized out, but operates at the compiler/IR-level and may still + * allow unintended removal of objects during linking. + * + * Optional: only supported since gcc >= 11, clang >= 13 + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-retain-function-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#retain + */ +#if __has_attribute(__retain__) && \ + (defined(CONFIG_LD_DEAD_CODE_DATA_ELIMINATION) || \ + defined(CONFIG_LTO_CLANG)) +# define __retain __attribute__((__retain__)) +#else +# define __retain +#endif + /* Compiler specific macros. */ #ifdef __clang__ #include <linux/compiler-clang.h> diff --git a/include/linux/device.h b/include/linux/device.h index fc3bd7116ab9..ace039151cb8 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1220,8 +1220,6 @@ static inline void device_remove_group(struct device *dev, return device_remove_groups(dev, groups); } -int __must_check devm_device_add_groups(struct device *dev, - const struct attribute_group **groups); int __must_check devm_device_add_group(struct device *dev, const struct attribute_group *grp); diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 7a6b190c7da7..b48570eaa449 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -648,7 +648,7 @@ struct io_kiocb { struct io_rsrc_node *rsrc_node; atomic_t refs; - atomic_t poll_refs; + bool cancel_seq_set; struct io_task_work io_task_work; /* for polled requests, i.e. IORING_OP_POLL_ADD and async armed poll */ struct hlist_node hash_node; @@ -657,6 +657,7 @@ struct io_kiocb { /* opcode allocated if it needs to store data for async defer */ void *async_data; /* linked requests, IFF REQ_F_HARDLINK or REQ_F_LINK are set */ + atomic_t poll_refs; struct io_kiocb *link; /* custom credentials, valid IFF REQ_F_CREDS is set */ const struct cred *creds; diff --git a/include/linux/kcov.h b/include/linux/kcov.h index b851ba415e03..75a2fb8b16c3 100644 --- a/include/linux/kcov.h +++ b/include/linux/kcov.h @@ -21,6 +21,8 @@ enum kcov_mode { KCOV_MODE_TRACE_PC = 2, /* Collecting comparison operands mode. */ KCOV_MODE_TRACE_CMP = 3, + /* The process owns a KCOV remote reference. */ + KCOV_MODE_REMOTE = 4, }; #define KCOV_IN_CTXSW (1 << 30) @@ -55,21 +57,47 @@ static inline void kcov_remote_start_usb(u64 id) /* * The softirq flavor of kcov_remote_*() functions is introduced as a temporary - * work around for kcov's lack of nested remote coverage sections support in - * task context. Adding support for nested sections is tracked in: - * https://bugzilla.kernel.org/show_bug.cgi?id=210337 + * workaround for KCOV's lack of nested remote coverage sections support. + * + * Adding support is tracked in https://bugzilla.kernel.org/show_bug.cgi?id=210337. + * + * kcov_remote_start_usb_softirq(): + * + * 1. Only collects coverage when called in the softirq context. This allows + * avoiding nested remote coverage collection sections in the task context. + * For example, USB/IP calls usb_hcd_giveback_urb() in the task context + * within an existing remote coverage collection section. Thus, KCOV should + * not attempt to start collecting coverage within the coverage collection + * section in __usb_hcd_giveback_urb() in this case. + * + * 2. Disables interrupts for the duration of the coverage collection section. + * This allows avoiding nested remote coverage collection sections in the + * softirq context (a softirq might occur during the execution of a work in + * the BH workqueue, which runs with in_serving_softirq() > 0). + * For example, usb_giveback_urb_bh() runs in the BH workqueue with + * interrupts enabled, so __usb_hcd_giveback_urb() might be interrupted in + * the middle of its remote coverage collection section, and the interrupt + * handler might invoke __usb_hcd_giveback_urb() again. */ -static inline void kcov_remote_start_usb_softirq(u64 id) +static inline unsigned long kcov_remote_start_usb_softirq(u64 id) { - if (in_serving_softirq()) + unsigned long flags = 0; + + if (in_serving_softirq()) { + local_irq_save(flags); kcov_remote_start_usb(id); + } + + return flags; } -static inline void kcov_remote_stop_softirq(void) +static inline void kcov_remote_stop_softirq(unsigned long flags) { - if (in_serving_softirq()) + if (in_serving_softirq()) { kcov_remote_stop(); + local_irq_restore(flags); + } } #ifdef CONFIG_64BIT @@ -103,8 +131,11 @@ static inline u64 kcov_common_handle(void) } static inline void kcov_remote_start_common(u64 id) {} static inline void kcov_remote_start_usb(u64 id) {} -static inline void kcov_remote_start_usb_softirq(u64 id) {} -static inline void kcov_remote_stop_softirq(void) {} +static inline unsigned long kcov_remote_start_usb_softirq(u64 id) +{ + return 0; +} +static inline void kcov_remote_stop_softirq(unsigned long flags) {} #endif /* CONFIG_KCOV */ #endif /* _LINUX_KCOV_H */ diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index f804b76cde44..44488b1ab9a9 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -413,7 +413,7 @@ LSM_HOOK(void, LSM_RET_VOID, key_post_create_or_update, struct key *keyring, #ifdef CONFIG_AUDIT LSM_HOOK(int, 0, audit_rule_init, u32 field, u32 op, char *rulestr, - void **lsmrule) + void **lsmrule, gfp_t gfp) LSM_HOOK(int, 0, audit_rule_known, struct audit_krule *krule) LSM_HOOK(int, 0, audit_rule_match, u32 secid, u32 field, u32 op, void *lsmrule) LSM_HOOK(void, LSM_RET_VOID, audit_rule_free, void *lsmrule) diff --git a/include/linux/mm.h b/include/linux/mm.h index 9849dfda44d4..9a5652c5fadd 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3776,14 +3776,7 @@ DECLARE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_FREE_DEFAULT_ON, init_on_free); static inline bool want_init_on_free(void) { return static_branch_maybe(CONFIG_INIT_ON_FREE_DEFAULT_ON, - &init_on_free); -} - -DECLARE_STATIC_KEY_MAYBE(CONFIG_INIT_MLOCKED_ON_FREE_DEFAULT_ON, init_mlocked_on_free); -static inline bool want_init_mlocked_on_free(void) -{ - return static_branch_maybe(CONFIG_INIT_MLOCKED_ON_FREE_DEFAULT_ON, - &init_mlocked_on_free); + &init_on_free); } extern bool _debug_pagealloc_enabled_early; diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index ee633712bba0..59f1df0cde5a 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -381,6 +381,10 @@ static inline void mapping_set_large_folios(struct address_space *mapping) */ static inline bool mapping_large_folio_support(struct address_space *mapping) { + /* AS_LARGE_FOLIO_SUPPORT is only reasonable for pagecache folios */ + VM_WARN_ONCE((unsigned long)mapping & PAGE_MAPPING_ANON, + "Anonymous mapping always supports large folio"); + return IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && test_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags); } diff --git a/include/linux/pgalloc_tag.h b/include/linux/pgalloc_tag.h index 86ba5d33e43b..9cacadbd61f8 100644 --- a/include/linux/pgalloc_tag.h +++ b/include/linux/pgalloc_tag.h @@ -37,6 +37,9 @@ static inline union codetag_ref *get_page_tag_ref(struct page *page) static inline void put_page_tag_ref(union codetag_ref *ref) { + if (WARN_ON(!ref)) + return; + page_ext_put(page_ext_from_codetag_ref(ref)); } @@ -102,9 +105,11 @@ static inline struct alloc_tag *pgalloc_tag_get(struct page *page) union codetag_ref *ref = get_page_tag_ref(page); alloc_tag_sub_check(ref); - if (ref && ref->ct) - tag = ct_to_alloc_tag(ref->ct); - put_page_tag_ref(ref); + if (ref) { + if (ref->ct) + tag = ct_to_alloc_tag(ref->ct); + put_page_tag_ref(ref); + } } return tag; diff --git a/include/linux/security.h b/include/linux/security.h index 21cf70346b33..de3af33e6ff5 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -2048,7 +2048,8 @@ static inline void security_key_post_create_or_update(struct key *keyring, #ifdef CONFIG_AUDIT #ifdef CONFIG_SECURITY -int security_audit_rule_init(u32 field, u32 op, char *rulestr, void **lsmrule); +int security_audit_rule_init(u32 field, u32 op, char *rulestr, void **lsmrule, + gfp_t gfp); int security_audit_rule_known(struct audit_krule *krule); int security_audit_rule_match(u32 secid, u32 field, u32 op, void *lsmrule); void security_audit_rule_free(void *lsmrule); @@ -2056,7 +2057,7 @@ void security_audit_rule_free(void *lsmrule); #else static inline int security_audit_rule_init(u32 field, u32 op, char *rulestr, - void **lsmrule) + void **lsmrule, gfp_t gfp) { return 0; } diff --git a/include/linux/string.h b/include/linux/string.h index 60168aa2af07..9edace076ddb 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -289,7 +289,7 @@ extern void *kmemdup_noprof(const void *src, size_t len, gfp_t gfp) __realloc_si extern void *kvmemdup(const void *src, size_t len, gfp_t gfp) __realloc_size(2); extern char *kmemdup_nul(const char *s, size_t len, gfp_t gfp); -extern void *kmemdup_array(const void *src, size_t element_size, size_t count, gfp_t gfp) +extern void *kmemdup_array(const void *src, size_t count, size_t element_size, gfp_t gfp) __realloc_size(2, 3); /* lib/argv_split.c */ diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index a7d725fbf739..c4e64dc11206 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -750,6 +750,15 @@ static inline int sysfs_emit_at(char *buf, int at, const char *fmt, ...) { return 0; } + +static inline ssize_t sysfs_bin_attr_simple_read(struct file *file, + struct kobject *kobj, + struct bin_attribute *attr, + char *buf, loff_t off, + size_t count) +{ + return 0; +} #endif /* CONFIG_SYSFS */ static inline int __must_check sysfs_create_file(struct kobject *kobj, diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 8b1a29820409..000a6cab2d31 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -64,6 +64,7 @@ struct vfio_device { struct completion comp; struct iommufd_access *iommufd_access; void (*put_kvm)(struct kvm *kvm); + struct inode *inode; #if IS_ENABLED(CONFIG_IOMMUFD) struct iommufd_device *iommufd_device; u8 iommufd_attached:1; diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index a2c8b8bba711..f87067438ed4 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -93,8 +93,6 @@ struct vfio_pci_core_device { struct list_head sriov_pfs_item; struct vfio_pci_core_device *sriov_pf_core_dev; struct notifier_block nb; - struct mutex vma_lock; - struct list_head vma_list; struct rw_semaphore memory_lock; }; diff --git a/include/net/netns/netfilter.h b/include/net/netns/netfilter.h index 02bbdc577f8e..a6a0bf4a247e 100644 --- a/include/net/netns/netfilter.h +++ b/include/net/netns/netfilter.h @@ -15,6 +15,9 @@ struct netns_nf { const struct nf_logger __rcu *nf_loggers[NFPROTO_NUMPROTO]; #ifdef CONFIG_SYSCTL struct ctl_table_header *nf_log_dir_header; +#ifdef CONFIG_LWTUNNEL + struct ctl_table_header *nf_lwtnl_dir_header; +#endif #endif struct nf_hook_entries __rcu *hooks_ipv4[NF_INET_NUMHOOKS]; struct nf_hook_entries __rcu *hooks_ipv6[NF_INET_NUMHOOKS]; diff --git a/include/scsi/scsi_transport_sas.h b/include/scsi/scsi_transport_sas.h index 0e75b9277c8c..e3b6ce3cbf88 100644 --- a/include/scsi/scsi_transport_sas.h +++ b/include/scsi/scsi_transport_sas.h @@ -200,6 +200,8 @@ unsigned int sas_is_tlr_enabled(struct scsi_device *); void sas_disable_tlr(struct scsi_device *); void sas_enable_tlr(struct scsi_device *); +bool sas_ata_ncq_prio_supported(struct scsi_device *sdev); + extern struct sas_rphy *sas_end_device_alloc(struct sas_port *); extern struct sas_rphy *sas_expander_alloc(struct sas_port *, enum sas_device_type); void sas_rphy_free(struct sas_rphy *); diff --git a/include/trace/events/firewire.h b/include/trace/events/firewire.h index d695a560673f..5ccc0d91b220 100644 --- a/include/trace/events/firewire.h +++ b/include/trace/events/firewire.h @@ -36,10 +36,11 @@ #define QUADLET_SIZE 4 DECLARE_EVENT_CLASS(async_outbound_initiate_template, - TP_PROTO(u64 transaction, unsigned int generation, unsigned int scode, const u32 *header, const u32 *data, unsigned int data_count), - TP_ARGS(transaction, generation, scode, header, data, data_count), + TP_PROTO(u64 transaction, unsigned int card_index, unsigned int generation, unsigned int scode, const u32 *header, const u32 *data, unsigned int data_count), + TP_ARGS(transaction, card_index, generation, scode, header, data, data_count), TP_STRUCT__entry( __field(u64, transaction) + __field(u8, card_index) __field(u8, generation) __field(u8, scode) __array(u32, header, ASYNC_HEADER_QUADLET_COUNT) @@ -47,6 +48,7 @@ DECLARE_EVENT_CLASS(async_outbound_initiate_template, ), TP_fast_assign( __entry->transaction = transaction; + __entry->card_index = card_index; __entry->generation = generation; __entry->scode = scode; memcpy(__entry->header, header, QUADLET_SIZE * ASYNC_HEADER_QUADLET_COUNT); @@ -54,8 +56,9 @@ DECLARE_EVENT_CLASS(async_outbound_initiate_template, ), // This format is for the request subaction. TP_printk( - "transaction=0x%llx generation=%u scode=%u dst_id=0x%04x tlabel=%u tcode=%u src_id=0x%04x offset=0x%012llx header=%s data=%s", + "transaction=0x%llx card_index=%u generation=%u scode=%u dst_id=0x%04x tlabel=%u tcode=%u src_id=0x%04x offset=0x%012llx header=%s data=%s", __entry->transaction, + __entry->card_index, __entry->generation, __entry->scode, ASYNC_HEADER_GET_DESTINATION(__entry->header), @@ -71,10 +74,11 @@ DECLARE_EVENT_CLASS(async_outbound_initiate_template, // The value of status is one of ack codes and rcodes specific to Linux FireWire subsystem. DECLARE_EVENT_CLASS(async_outbound_complete_template, - TP_PROTO(u64 transaction, unsigned int generation, unsigned int scode, unsigned int status, unsigned int timestamp), - TP_ARGS(transaction, generation, scode, status, timestamp), + TP_PROTO(u64 transaction, unsigned int card_index, unsigned int generation, unsigned int scode, unsigned int status, unsigned int timestamp), + TP_ARGS(transaction, card_index, generation, scode, status, timestamp), TP_STRUCT__entry( __field(u64, transaction) + __field(u8, card_index) __field(u8, generation) __field(u8, scode) __field(u8, status) @@ -82,14 +86,16 @@ DECLARE_EVENT_CLASS(async_outbound_complete_template, ), TP_fast_assign( __entry->transaction = transaction; + __entry->card_index = card_index; __entry->generation = generation; __entry->scode = scode; __entry->status = status; __entry->timestamp = timestamp; ), TP_printk( - "transaction=0x%llx generation=%u scode=%u status=%u timestamp=0x%04x", + "transaction=0x%llx card_index=%u generation=%u scode=%u status=%u timestamp=0x%04x", __entry->transaction, + __entry->card_index, __entry->generation, __entry->scode, __entry->status, @@ -99,10 +105,11 @@ DECLARE_EVENT_CLASS(async_outbound_complete_template, // The value of status is one of ack codes and rcodes specific to Linux FireWire subsystem. DECLARE_EVENT_CLASS(async_inbound_template, - TP_PROTO(u64 transaction, unsigned int generation, unsigned int scode, unsigned int status, unsigned int timestamp, const u32 *header, const u32 *data, unsigned int data_count), - TP_ARGS(transaction, generation, scode, status, timestamp, header, data, data_count), + TP_PROTO(u64 transaction, unsigned int card_index, unsigned int generation, unsigned int scode, unsigned int status, unsigned int timestamp, const u32 *header, const u32 *data, unsigned int data_count), + TP_ARGS(transaction, card_index, generation, scode, status, timestamp, header, data, data_count), TP_STRUCT__entry( __field(u64, transaction) + __field(u8, card_index) __field(u8, generation) __field(u8, scode) __field(u8, status) @@ -112,6 +119,7 @@ DECLARE_EVENT_CLASS(async_inbound_template, ), TP_fast_assign( __entry->transaction = transaction; + __entry->card_index = card_index; __entry->generation = generation; __entry->scode = scode; __entry->status = status; @@ -121,8 +129,9 @@ DECLARE_EVENT_CLASS(async_inbound_template, ), // This format is for the response subaction. TP_printk( - "transaction=0x%llx generation=%u scode=%u status=%u timestamp=0x%04x dst_id=0x%04x tlabel=%u tcode=%u src_id=0x%04x rcode=%u header=%s data=%s", + "transaction=0x%llx card_index=%u generation=%u scode=%u status=%u timestamp=0x%04x dst_id=0x%04x tlabel=%u tcode=%u src_id=0x%04x rcode=%u header=%s data=%s", __entry->transaction, + __entry->card_index, __entry->generation, __entry->scode, __entry->status, @@ -139,26 +148,27 @@ DECLARE_EVENT_CLASS(async_inbound_template, ); DEFINE_EVENT(async_outbound_initiate_template, async_request_outbound_initiate, - TP_PROTO(u64 transaction, unsigned int generation, unsigned int scode, const u32 *header, const u32 *data, unsigned int data_count), - TP_ARGS(transaction, generation, scode, header, data, data_count) + TP_PROTO(u64 transaction, unsigned int card_index, unsigned int generation, unsigned int scode, const u32 *header, const u32 *data, unsigned int data_count), + TP_ARGS(transaction, card_index, generation, scode, header, data, data_count) ); DEFINE_EVENT(async_outbound_complete_template, async_request_outbound_complete, - TP_PROTO(u64 transaction, unsigned int generation, unsigned int scode, unsigned int status, unsigned int timestamp), - TP_ARGS(transaction, generation, scode, status, timestamp) + TP_PROTO(u64 transaction, unsigned int card_index, unsigned int generation, unsigned int scode, unsigned int status, unsigned int timestamp), + TP_ARGS(transaction, card_index, generation, scode, status, timestamp) ); DEFINE_EVENT(async_inbound_template, async_response_inbound, - TP_PROTO(u64 transaction, unsigned int generation, unsigned int scode, unsigned int status, unsigned int timestamp, const u32 *header, const u32 *data, unsigned int data_count), - TP_ARGS(transaction, generation, scode, status, timestamp, header, data, data_count) + TP_PROTO(u64 transaction, unsigned int card_index, unsigned int generation, unsigned int scode, unsigned int status, unsigned int timestamp, const u32 *header, const u32 *data, unsigned int data_count), + TP_ARGS(transaction, card_index, generation, scode, status, timestamp, header, data, data_count) ); DEFINE_EVENT_PRINT(async_inbound_template, async_request_inbound, - TP_PROTO(u64 transaction, unsigned int generation, unsigned int scode, unsigned int status, unsigned int timestamp, const u32 *header, const u32 *data, unsigned int data_count), - TP_ARGS(transaction, generation, scode, status, timestamp, header, data, data_count), + TP_PROTO(u64 transaction, unsigned int card_index, unsigned int generation, unsigned int scode, unsigned int status, unsigned int timestamp, const u32 *header, const u32 *data, unsigned int data_count), + TP_ARGS(transaction, card_index, generation, scode, status, timestamp, header, data, data_count), TP_printk( - "transaction=0x%llx generation=%u scode=%u status=%u timestamp=0x%04x dst_id=0x%04x tlabel=%u tcode=%u src_id=0x%04x offset=0x%012llx header=%s data=%s", + "transaction=0x%llx card_index=%u generation=%u scode=%u status=%u timestamp=0x%04x dst_id=0x%04x tlabel=%u tcode=%u src_id=0x%04x offset=0x%012llx header=%s data=%s", __entry->transaction, + __entry->card_index, __entry->generation, __entry->scode, __entry->status, @@ -175,11 +185,12 @@ DEFINE_EVENT_PRINT(async_inbound_template, async_request_inbound, ); DEFINE_EVENT_PRINT(async_outbound_initiate_template, async_response_outbound_initiate, - TP_PROTO(u64 transaction, unsigned int generation, unsigned int scode, const u32 *header, const u32 *data, unsigned int data_count), - TP_ARGS(transaction, generation, scode, header, data, data_count), + TP_PROTO(u64 transaction, unsigned int card_index, unsigned int generation, unsigned int scode, const u32 *header, const u32 *data, unsigned int data_count), + TP_ARGS(transaction, card_index, generation, scode, header, data, data_count), TP_printk( - "transaction=0x%llx generation=%u scode=%u dst_id=0x%04x tlabel=%u tcode=%u src_id=0x%04x rcode=%u header=%s data=%s", + "transaction=0x%llx card_index=%u generation=%u scode=%u dst_id=0x%04x tlabel=%u tcode=%u src_id=0x%04x rcode=%u header=%s data=%s", __entry->transaction, + __entry->card_index, __entry->generation, __entry->scode, ASYNC_HEADER_GET_DESTINATION(__entry->header), @@ -194,8 +205,8 @@ DEFINE_EVENT_PRINT(async_outbound_initiate_template, async_response_outbound_ini ); DEFINE_EVENT(async_outbound_complete_template, async_response_outbound_complete, - TP_PROTO(u64 transaction, unsigned int generation, unsigned int scode, unsigned int status, unsigned int timestamp), - TP_ARGS(transaction, generation, scode, status, timestamp) + TP_PROTO(u64 transaction, unsigned int card_index, unsigned int generation, unsigned int scode, unsigned int status, unsigned int timestamp), + TP_ARGS(transaction, card_index, generation, scode, status, timestamp) ); #undef ASYNC_HEADER_GET_DESTINATION @@ -206,23 +217,26 @@ DEFINE_EVENT(async_outbound_complete_template, async_response_outbound_complete, #undef ASYNC_HEADER_GET_RCODE TRACE_EVENT(async_phy_outbound_initiate, - TP_PROTO(u64 packet, unsigned int generation, u32 first_quadlet, u32 second_quadlet), - TP_ARGS(packet, generation, first_quadlet, second_quadlet), + TP_PROTO(u64 packet, unsigned int card_index, unsigned int generation, u32 first_quadlet, u32 second_quadlet), + TP_ARGS(packet, card_index, generation, first_quadlet, second_quadlet), TP_STRUCT__entry( __field(u64, packet) + __field(u8, card_index) __field(u8, generation) __field(u32, first_quadlet) __field(u32, second_quadlet) ), TP_fast_assign( __entry->packet = packet; + __entry->card_index = card_index; __entry->generation = generation; __entry->first_quadlet = first_quadlet; __entry->second_quadlet = second_quadlet ), TP_printk( - "packet=0x%llx generation=%u first_quadlet=0x%08x second_quadlet=0x%08x", + "packet=0x%llx card_index=%u generation=%u first_quadlet=0x%08x second_quadlet=0x%08x", __entry->packet, + __entry->card_index, __entry->generation, __entry->first_quadlet, __entry->second_quadlet @@ -230,23 +244,26 @@ TRACE_EVENT(async_phy_outbound_initiate, ); TRACE_EVENT(async_phy_outbound_complete, - TP_PROTO(u64 packet, unsigned int generation, unsigned int status, unsigned int timestamp), - TP_ARGS(packet, generation, status, timestamp), + TP_PROTO(u64 packet, unsigned int card_index, unsigned int generation, unsigned int status, unsigned int timestamp), + TP_ARGS(packet, card_index, generation, status, timestamp), TP_STRUCT__entry( __field(u64, packet) + __field(u8, card_index) __field(u8, generation) __field(u8, status) __field(u16, timestamp) ), TP_fast_assign( __entry->packet = packet; + __entry->card_index = card_index; __entry->generation = generation; __entry->status = status; __entry->timestamp = timestamp; ), TP_printk( - "packet=0x%llx generation=%u status=%u timestamp=0x%04x", + "packet=0x%llx card_index=%u generation=%u status=%u timestamp=0x%04x", __entry->packet, + __entry->card_index, __entry->generation, __entry->status, __entry->timestamp @@ -254,10 +271,11 @@ TRACE_EVENT(async_phy_outbound_complete, ); TRACE_EVENT(async_phy_inbound, - TP_PROTO(u64 packet, unsigned int generation, unsigned int status, unsigned int timestamp, u32 first_quadlet, u32 second_quadlet), - TP_ARGS(packet, generation, status, timestamp, first_quadlet, second_quadlet), + TP_PROTO(u64 packet, unsigned int card_index, unsigned int generation, unsigned int status, unsigned int timestamp, u32 first_quadlet, u32 second_quadlet), + TP_ARGS(packet, card_index, generation, status, timestamp, first_quadlet, second_quadlet), TP_STRUCT__entry( __field(u64, packet) + __field(u8, card_index) __field(u8, generation) __field(u8, status) __field(u16, timestamp) @@ -273,8 +291,9 @@ TRACE_EVENT(async_phy_inbound, __entry->second_quadlet = second_quadlet ), TP_printk( - "packet=0x%llx generation=%u status=%u timestamp=0x%04x first_quadlet=0x%08x second_quadlet=0x%08x", + "packet=0x%llx card_index=%u generation=%u status=%u timestamp=0x%04x first_quadlet=0x%08x second_quadlet=0x%08x", __entry->packet, + __entry->card_index, __entry->generation, __entry->status, __entry->timestamp, @@ -284,55 +303,61 @@ TRACE_EVENT(async_phy_inbound, ); DECLARE_EVENT_CLASS(bus_reset_arrange_template, - TP_PROTO(unsigned int generation, bool short_reset), - TP_ARGS(generation, short_reset), + TP_PROTO(unsigned int card_index, unsigned int generation, bool short_reset), + TP_ARGS(card_index, generation, short_reset), TP_STRUCT__entry( + __field(u8, card_index) __field(u8, generation) __field(bool, short_reset) ), TP_fast_assign( + __entry->card_index = card_index; __entry->generation = generation; __entry->short_reset = short_reset; ), TP_printk( - "generation=%u short_reset=%s", + "card_index=%u generation=%u short_reset=%s", + __entry->card_index, __entry->generation, __entry->short_reset ? "true" : "false" ) ); DEFINE_EVENT(bus_reset_arrange_template, bus_reset_initiate, - TP_PROTO(unsigned int generation, bool short_reset), - TP_ARGS(generation, short_reset) + TP_PROTO(unsigned int card_index, unsigned int generation, bool short_reset), + TP_ARGS(card_index, generation, short_reset) ); DEFINE_EVENT(bus_reset_arrange_template, bus_reset_schedule, - TP_PROTO(unsigned int generation, bool short_reset), - TP_ARGS(generation, short_reset) + TP_PROTO(unsigned int card_index, unsigned int generation, bool short_reset), + TP_ARGS(card_index, generation, short_reset) ); DEFINE_EVENT(bus_reset_arrange_template, bus_reset_postpone, - TP_PROTO(unsigned int generation, bool short_reset), - TP_ARGS(generation, short_reset) + TP_PROTO(unsigned int card_index, unsigned int generation, bool short_reset), + TP_ARGS(card_index, generation, short_reset) ); TRACE_EVENT(bus_reset_handle, - TP_PROTO(unsigned int generation, unsigned int node_id, bool bm_abdicate, u32 *self_ids, unsigned int self_id_count), - TP_ARGS(generation, node_id, bm_abdicate, self_ids, self_id_count), + TP_PROTO(unsigned int card_index, unsigned int generation, unsigned int node_id, bool bm_abdicate, u32 *self_ids, unsigned int self_id_count), + TP_ARGS(card_index, generation, node_id, bm_abdicate, self_ids, self_id_count), TP_STRUCT__entry( + __field(u8, card_index) __field(u8, generation) __field(u8, node_id) __field(bool, bm_abdicate) __dynamic_array(u32, self_ids, self_id_count) ), TP_fast_assign( + __entry->card_index = card_index; __entry->generation = generation; __entry->node_id = node_id; __entry->bm_abdicate = bm_abdicate; memcpy(__get_dynamic_array(self_ids), self_ids, __get_dynamic_array_len(self_ids)); ), TP_printk( - "generation=%u node_id=0x%04x bm_abdicate=%s self_ids=%s", + "card_index=%u generation=%u node_id=0x%04x bm_abdicate=%s self_ids=%s", + __entry->card_index, __entry->generation, __entry->node_id, __entry->bm_abdicate ? "true" : "false", diff --git a/init/Kconfig b/init/Kconfig index 72404c1f2157..febdea2afc3b 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -883,7 +883,7 @@ config GCC10_NO_ARRAY_BOUNDS config CC_NO_ARRAY_BOUNDS bool - default y if CC_IS_GCC && GCC_VERSION >= 100000 && GCC10_NO_ARRAY_BOUNDS + default y if CC_IS_GCC && GCC_VERSION >= 90000 && GCC10_NO_ARRAY_BOUNDS # Currently, disable -Wstringop-overflow for GCC globally. config GCC_NO_STRINGOP_OVERFLOW diff --git a/io_uring/cancel.h b/io_uring/cancel.h index 76b32e65c03c..b33995e00ba9 100644 --- a/io_uring/cancel.h +++ b/io_uring/cancel.h @@ -27,10 +27,10 @@ bool io_cancel_req_match(struct io_kiocb *req, struct io_cancel_data *cd); static inline bool io_cancel_match_sequence(struct io_kiocb *req, int sequence) { - if ((req->flags & REQ_F_CANCEL_SEQ) && sequence == req->work.cancel_seq) + if (req->cancel_seq_set && sequence == req->work.cancel_seq) return true; - req->flags |= REQ_F_CANCEL_SEQ; + req->cancel_seq_set = true; req->work.cancel_seq = sequence; return false; } diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 816e93e7f949..154b25b8a613 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2058,6 +2058,7 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, req->file = NULL; req->rsrc_node = NULL; req->task = current; + req->cancel_seq_set = false; if (unlikely(opcode >= IORING_OP_LAST)) { req->opcode = 0; diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c index 65417c9553b1..edb9c5baf2e2 100644 --- a/io_uring/rsrc.c +++ b/io_uring/rsrc.c @@ -249,6 +249,7 @@ __cold static int io_rsrc_ref_quiesce(struct io_rsrc_data *data, ret = io_run_task_work_sig(ctx); if (ret < 0) { + __set_current_state(TASK_RUNNING); mutex_lock(&ctx->uring_lock); if (list_empty(&ctx->rsrc_ref_list)) ret = 0; diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index be8c680121e4..d6ef4f4f9cba 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -529,7 +529,8 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, entry->rule.buflen += f_val; f->lsm_str = str; err = security_audit_rule_init(f->type, f->op, str, - (void **)&f->lsm_rule); + (void **)&f->lsm_rule, + GFP_KERNEL); /* Keep currently invalid fields around in case they * become valid after a policy reload. */ if (err == -EINVAL) { @@ -799,7 +800,7 @@ static inline int audit_dupe_lsm_field(struct audit_field *df, /* our own (refreshed) copy of lsm_rule */ ret = security_audit_rule_init(df->type, df->op, df->lsm_str, - (void **)&df->lsm_rule); + (void **)&df->lsm_rule, GFP_KERNEL); /* Keep currently invalid fields around in case they * become valid after a policy reload. */ if (ret == -EINVAL) { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 20ac9cfd54dd..c955f98c9a2b 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4549,11 +4549,12 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, state->stack[spi].spilled_ptr.id = 0; } else if (!reg && !(off % BPF_REG_SIZE) && is_bpf_st_mem(insn) && env->bpf_capable) { - struct bpf_reg_state fake_reg = {}; + struct bpf_reg_state *tmp_reg = &env->fake_reg[0]; - __mark_reg_known(&fake_reg, insn->imm); - fake_reg.type = SCALAR_VALUE; - save_register_state(env, state, spi, &fake_reg, size); + memset(tmp_reg, 0, sizeof(*tmp_reg)); + __mark_reg_known(tmp_reg, insn->imm); + tmp_reg->type = SCALAR_VALUE; + save_register_state(env, state, spi, tmp_reg, size); } else if (reg && is_spillable_regtype(reg->type)) { /* register containing pointer is being spilled into stack */ if (size != BPF_REG_SIZE) { @@ -15113,7 +15114,6 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, struct bpf_reg_state *regs = this_branch->frame[this_branch->curframe]->regs; struct bpf_reg_state *dst_reg, *other_branch_regs, *src_reg = NULL; struct bpf_reg_state *eq_branch_regs; - struct bpf_reg_state fake_reg = {}; u8 opcode = BPF_OP(insn->code); bool is_jmp32; int pred = -1; @@ -15179,7 +15179,8 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, verbose(env, "BPF_JMP/JMP32 uses reserved fields\n"); return -EINVAL; } - src_reg = &fake_reg; + src_reg = &env->fake_reg[0]; + memset(src_reg, 0, sizeof(*src_reg)); src_reg->type = SCALAR_VALUE; __mark_reg_known(src_reg, insn->imm); } @@ -15239,10 +15240,16 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, &other_branch_regs[insn->src_reg], dst_reg, src_reg, opcode, is_jmp32); } else /* BPF_SRC(insn->code) == BPF_K */ { + /* reg_set_min_max() can mangle the fake_reg. Make a copy + * so that these are two different memory locations. The + * src_reg is not used beyond here in context of K. + */ + memcpy(&env->fake_reg[1], &env->fake_reg[0], + sizeof(env->fake_reg[0])); err = reg_set_min_max(env, &other_branch_regs[insn->dst_reg], - src_reg /* fake one */, - dst_reg, src_reg /* same fake one */, + &env->fake_reg[0], + dst_reg, &env->fake_reg[1], opcode, is_jmp32); } if (err) @@ -20313,7 +20320,7 @@ patch_map_ops_generic: goto next_insn; } -#ifdef CONFIG_X86_64 +#if defined(CONFIG_X86_64) && !defined(CONFIG_UML) /* Implement bpf_get_smp_processor_id() inline. */ if (insn->imm == BPF_FUNC_get_smp_processor_id && prog->jit_requested && bpf_jit_supports_percpu_insn()) { diff --git a/kernel/gcov/gcc_4_7.c b/kernel/gcov/gcc_4_7.c index 74a4ef1da9ad..fd75b4a484d7 100644 --- a/kernel/gcov/gcc_4_7.c +++ b/kernel/gcov/gcc_4_7.c @@ -18,7 +18,9 @@ #include <linux/mm.h> #include "gcov.h" -#if (__GNUC__ >= 10) +#if (__GNUC__ >= 14) +#define GCOV_COUNTERS 9 +#elif (__GNUC__ >= 10) #define GCOV_COUNTERS 8 #elif (__GNUC__ >= 7) #define GCOV_COUNTERS 9 diff --git a/kernel/kcov.c b/kernel/kcov.c index c3124f6d5536..f0a69d402066 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -632,6 +632,7 @@ static int kcov_ioctl_locked(struct kcov *kcov, unsigned int cmd, return -EINVAL; kcov->mode = mode; t->kcov = kcov; + t->kcov_mode = KCOV_MODE_REMOTE; kcov->t = t; kcov->remote = true; kcov->remote_size = remote_arg->area_size; diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index dc48fecfa1dc..25f3cf679b35 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -218,6 +218,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns) */ do { clear_thread_flag(TIF_SIGPENDING); + clear_thread_flag(TIF_NOTIFY_SIGNAL); rc = kernel_wait4(-1, NULL, __WALL, NULL); } while (rc != -ECHILD); diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index d88b13076b79..a47bcf71defc 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -178,26 +178,6 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast) } } -#ifdef CONFIG_NO_HZ_FULL -static void giveup_do_timer(void *info) -{ - int cpu = *(unsigned int *)info; - - WARN_ON(tick_do_timer_cpu != smp_processor_id()); - - tick_do_timer_cpu = cpu; -} - -static void tick_take_do_timer_from_boot(void) -{ - int cpu = smp_processor_id(); - int from = tick_do_timer_boot_cpu; - - if (from >= 0 && from != cpu) - smp_call_function_single(from, giveup_do_timer, &cpu, 1); -} -#endif - /* * Setup the tick device */ @@ -221,19 +201,25 @@ static void tick_setup_device(struct tick_device *td, tick_next_period = ktime_get(); #ifdef CONFIG_NO_HZ_FULL /* - * The boot CPU may be nohz_full, in which case set - * tick_do_timer_boot_cpu so the first housekeeping - * secondary that comes up will take do_timer from - * us. + * The boot CPU may be nohz_full, in which case the + * first housekeeping secondary will take do_timer() + * from it. */ if (tick_nohz_full_cpu(cpu)) tick_do_timer_boot_cpu = cpu; - } else if (tick_do_timer_boot_cpu != -1 && - !tick_nohz_full_cpu(cpu)) { - tick_take_do_timer_from_boot(); + } else if (tick_do_timer_boot_cpu != -1 && !tick_nohz_full_cpu(cpu)) { tick_do_timer_boot_cpu = -1; - WARN_ON(READ_ONCE(tick_do_timer_cpu) != cpu); + /* + * The boot CPU will stay in periodic (NOHZ disabled) + * mode until clocksource_done_booting() called after + * smp_init() selects a high resolution clocksource and + * timekeeping_notify() kicks the NOHZ stuff alive. + * + * So this WRITE_ONCE can only race with the READ_ONCE + * check in tick_periodic() but this race is harmless. + */ + WRITE_ONCE(tick_do_timer_cpu, cpu); #endif } diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 166ad5444eea..721c3b221048 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -1136,7 +1136,7 @@ config PREEMPTIRQ_DELAY_TEST config SYNTH_EVENT_GEN_TEST tristate "Test module for in-kernel synthetic event generation" - depends on SYNTH_EVENTS + depends on SYNTH_EVENTS && m help This option creates a test module to check the base functionality of in-kernel synthetic event definition and @@ -1149,7 +1149,7 @@ config SYNTH_EVENT_GEN_TEST config KPROBE_EVENT_GEN_TEST tristate "Test module for in-kernel kprobe event generation" - depends on KPROBE_EVENTS + depends on KPROBE_EVENTS && m help This option creates a test module to check the base functionality of in-kernel kprobe event definition. diff --git a/lib/Kconfig b/lib/Kconfig index d33a268bc256..b0a76dff5c18 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -539,13 +539,7 @@ config CPUMASK_OFFSTACK stack overflow. config FORCE_NR_CPUS - bool "Set number of CPUs at compile time" - depends on SMP && EXPERT && !COMPILE_TEST - help - Say Yes if you have NR_CPUS set to an actual number of possible - CPUs in your system, not to a default value. This forces the core - code to rely on compile-time value and optimize kernel routines - better. + def_bool !SMP config CPU_RMAP bool diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c index 11ed973ac359..c347b8b72d78 100644 --- a/lib/alloc_tag.c +++ b/lib/alloc_tag.c @@ -227,6 +227,7 @@ struct page_ext_operations page_alloc_tagging_ops = { }; EXPORT_SYMBOL(page_alloc_tagging_ops); +#ifdef CONFIG_SYSCTL static struct ctl_table memory_allocation_profiling_sysctls[] = { { .procname = "mem_profiling", @@ -241,6 +242,17 @@ static struct ctl_table memory_allocation_profiling_sysctls[] = { { } }; +static void __init sysctl_init(void) +{ + if (!mem_profiling_support) + memory_allocation_profiling_sysctls[0].mode = 0444; + + register_sysctl_init("vm", memory_allocation_profiling_sysctls); +} +#else /* CONFIG_SYSCTL */ +static inline void sysctl_init(void) {} +#endif /* CONFIG_SYSCTL */ + static int __init alloc_tag_init(void) { const struct codetag_type_desc desc = { @@ -253,9 +265,7 @@ static int __init alloc_tag_init(void) if (IS_ERR(alloc_tag_cttype)) return PTR_ERR(alloc_tag_cttype); - if (!mem_profiling_support) - memory_allocation_profiling_sysctls[0].mode = 0444; - register_sysctl_init("vm", memory_allocation_profiling_sysctls); + sysctl_init(); procfs_init(); return 0; diff --git a/lib/fortify_kunit.c b/lib/fortify_kunit.c index f9cc467334ce..e17d520f532c 100644 --- a/lib/fortify_kunit.c +++ b/lib/fortify_kunit.c @@ -374,7 +374,7 @@ static const char * const test_strs[] = { for (i = 0; i < ARRAY_SIZE(test_strs); i++) { \ len = strlen(test_strs[i]); \ KUNIT_EXPECT_EQ(test, __builtin_constant_p(len), 0); \ - checker(len, kmemdup_array(test_strs[i], len, 1, gfp), \ + checker(len, kmemdup_array(test_strs[i], 1, len, gfp), \ kfree(p)); \ checker(len, kmemdup(test_strs[i], len, gfp), \ kfree(p)); \ diff --git a/lib/overflow_kunit.c b/lib/overflow_kunit.c index 4ef31b0bb74d..d305b0c054bb 100644 --- a/lib/overflow_kunit.c +++ b/lib/overflow_kunit.c @@ -1178,14 +1178,28 @@ struct foo { s16 array[] __counted_by(counter); }; +struct bar { + int a; + u32 counter; + s16 array[]; +}; + static void DEFINE_FLEX_test(struct kunit *test) { - DEFINE_RAW_FLEX(struct foo, two, array, 2); + /* Using _RAW_ on a __counted_by struct will initialize "counter" to zero */ + DEFINE_RAW_FLEX(struct foo, two_but_zero, array, 2); +#if __has_attribute(__counted_by__) + int expected_raw_size = sizeof(struct foo); +#else + int expected_raw_size = sizeof(struct foo) + 2 * sizeof(s16); +#endif + /* Without annotation, it will always be on-stack size. */ + DEFINE_RAW_FLEX(struct bar, two, array, 2); DEFINE_FLEX(struct foo, eight, array, counter, 8); DEFINE_FLEX(struct foo, empty, array, counter, 0); - KUNIT_EXPECT_EQ(test, __struct_size(two), - sizeof(struct foo) + sizeof(s16) + sizeof(s16)); + KUNIT_EXPECT_EQ(test, __struct_size(two_but_zero), expected_raw_size); + KUNIT_EXPECT_EQ(test, __struct_size(two), sizeof(struct bar) + 2 * sizeof(s16)); KUNIT_EXPECT_EQ(test, __struct_size(eight), 24); KUNIT_EXPECT_EQ(test, __struct_size(empty), sizeof(struct foo)); } diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c index b104a353b532..e4969fb54da3 100644 --- a/mm/debug_vm_pgtable.c +++ b/mm/debug_vm_pgtable.c @@ -40,22 +40,7 @@ * Please refer Documentation/mm/arch_pgtable_helpers.rst for the semantics * expectations that are being validated here. All future changes in here * or the documentation need to be in sync. - * - * On s390 platform, the lower 4 bits are used to identify given page table - * entry type. But these bits might affect the ability to clear entries with - * pxx_clear() because of how dynamic page table folding works on s390. So - * while loading up the entries do not change the lower 4 bits. It does not - * have affect any other platform. Also avoid the 62nd bit on ppc64 that is - * used to mark a pte entry. */ -#define S390_SKIP_MASK GENMASK(3, 0) -#if __BITS_PER_LONG == 64 -#define PPC64_SKIP_MASK GENMASK(62, 62) -#else -#define PPC64_SKIP_MASK 0x0 -#endif -#define ARCH_SKIP_MASK (S390_SKIP_MASK | PPC64_SKIP_MASK) -#define RANDOM_ORVALUE (GENMASK(BITS_PER_LONG - 1, 0) & ~ARCH_SKIP_MASK) #define RANDOM_NZVALUE GENMASK(7, 0) struct pgtable_debug_args { @@ -511,8 +496,7 @@ static void __init pud_clear_tests(struct pgtable_debug_args *args) return; pr_debug("Validating PUD clear\n"); - pud = __pud(pud_val(pud) | RANDOM_ORVALUE); - WRITE_ONCE(*args->pudp, pud); + WARN_ON(pud_none(pud)); pud_clear(args->pudp); pud = READ_ONCE(*args->pudp); WARN_ON(!pud_none(pud)); @@ -548,8 +532,7 @@ static void __init p4d_clear_tests(struct pgtable_debug_args *args) return; pr_debug("Validating P4D clear\n"); - p4d = __p4d(p4d_val(p4d) | RANDOM_ORVALUE); - WRITE_ONCE(*args->p4dp, p4d); + WARN_ON(p4d_none(p4d)); p4d_clear(args->p4dp); p4d = READ_ONCE(*args->p4dp); WARN_ON(!p4d_none(p4d)); @@ -582,8 +565,7 @@ static void __init pgd_clear_tests(struct pgtable_debug_args *args) return; pr_debug("Validating PGD clear\n"); - pgd = __pgd(pgd_val(pgd) | RANDOM_ORVALUE); - WRITE_ONCE(*args->pgdp, pgd); + WARN_ON(pgd_none(pgd)); pgd_clear(args->pgdp); pgd = READ_ONCE(*args->pgdp); WARN_ON(!pgd_none(pgd)); @@ -634,10 +616,8 @@ static void __init pte_clear_tests(struct pgtable_debug_args *args) if (WARN_ON(!args->ptep)) return; -#ifndef CONFIG_RISCV - pte = __pte(pte_val(pte) | RANDOM_ORVALUE); -#endif set_pte_at(args->mm, args->vaddr, args->ptep, pte); + WARN_ON(pte_none(pte)); flush_dcache_page(page); barrier(); ptep_clear(args->mm, args->vaddr, args->ptep); @@ -650,8 +630,7 @@ static void __init pmd_clear_tests(struct pgtable_debug_args *args) pmd_t pmd = READ_ONCE(*args->pmdp); pr_debug("Validating PMD clear\n"); - pmd = __pmd(pmd_val(pmd) | RANDOM_ORVALUE); - WRITE_ONCE(*args->pmdp, pmd); + WARN_ON(pmd_none(pmd)); pmd_clear(args->pmdp); pmd = READ_ONCE(*args->pmdp); WARN_ON(!pmd_none(pmd)); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 89932fd0f62e..db7946a0a28c 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -3009,30 +3009,36 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, if (new_order >= folio_order(folio)) return -EINVAL; - /* Cannot split anonymous THP to order-1 */ - if (new_order == 1 && folio_test_anon(folio)) { - VM_WARN_ONCE(1, "Cannot split to order-1 folio"); - return -EINVAL; - } - - if (new_order) { - /* Only swapping a whole PMD-mapped folio is supported */ - if (folio_test_swapcache(folio)) + if (folio_test_anon(folio)) { + /* order-1 is not supported for anonymous THP. */ + if (new_order == 1) { + VM_WARN_ONCE(1, "Cannot split to order-1 folio"); return -EINVAL; + } + } else if (new_order) { /* Split shmem folio to non-zero order not supported */ if (shmem_mapping(folio->mapping)) { VM_WARN_ONCE(1, "Cannot split shmem folio to non-0 order"); return -EINVAL; } - /* No split if the file system does not support large folio */ - if (!mapping_large_folio_support(folio->mapping)) { + /* + * No split if the file system does not support large folio. + * Note that we might still have THPs in such mappings due to + * CONFIG_READ_ONLY_THP_FOR_FS. But in that case, the mapping + * does not actually support large folios properly. + */ + if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && + !mapping_large_folio_support(folio->mapping)) { VM_WARN_ONCE(1, "Cannot split file folio to non-0 order"); return -EINVAL; } } + /* Only swapping a whole PMD-mapped folio is supported */ + if (folio_test_swapcache(folio) && new_order) + return -EINVAL; is_hzp = is_huge_zero_folio(folio); if (is_hzp) { diff --git a/mm/internal.h b/mm/internal.h index b2c75b12014e..c72c306761a4 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -588,7 +588,6 @@ extern void __putback_isolated_page(struct page *page, unsigned int order, extern void memblock_free_pages(struct page *page, unsigned long pfn, unsigned int order); extern void __free_pages_core(struct page *page, unsigned int order); -extern void kernel_init_pages(struct page *page, int numpages); /* * This will have no effect, other than possibly generating a warning, if the diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 36793e509f47..71fe2a95b8bd 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -7745,8 +7745,7 @@ void __mem_cgroup_uncharge_folios(struct folio_batch *folios) * @new: Replacement folio. * * Charge @new as a replacement folio for @old. @old will - * be uncharged upon free. This is only used by the page cache - * (in replace_page_cache_folio()). + * be uncharged upon free. * * Both folios must be locked, @new->mapping must be set up. */ diff --git a/mm/memory.c b/mm/memory.c index 0f47a533014e..25a77c4fe4a0 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1507,12 +1507,6 @@ static __always_inline void zap_present_folio_ptes(struct mmu_gather *tlb, if (unlikely(folio_mapcount(folio) < 0)) print_bad_pte(vma, addr, ptent, page); } - - if (want_init_mlocked_on_free() && folio_test_mlocked(folio) && - !delay_rmap && folio_test_anon(folio)) { - kernel_init_pages(page, folio_nr_pages(folio)); - } - if (unlikely(__tlb_remove_folio_pages(tlb, page, nr, delay_rmap))) { *force_flush = true; *force_break = true; @@ -5106,10 +5100,16 @@ static void numa_rebuild_large_mapping(struct vm_fault *vmf, struct vm_area_stru bool ignore_writable, bool pte_write_upgrade) { int nr = pte_pfn(fault_pte) - folio_pfn(folio); - unsigned long start = max(vmf->address - nr * PAGE_SIZE, vma->vm_start); - unsigned long end = min(vmf->address + (folio_nr_pages(folio) - nr) * PAGE_SIZE, vma->vm_end); - pte_t *start_ptep = vmf->pte - (vmf->address - start) / PAGE_SIZE; - unsigned long addr; + unsigned long start, end, addr = vmf->address; + unsigned long addr_start = addr - (nr << PAGE_SHIFT); + unsigned long pt_start = ALIGN_DOWN(addr, PMD_SIZE); + pte_t *start_ptep; + + /* Stay within the VMA and within the page table. */ + start = max3(addr_start, pt_start, vma->vm_start); + end = min3(addr_start + folio_size(folio), pt_start + PMD_SIZE, + vma->vm_end); + start_ptep = vmf->pte - ((addr - start) >> PAGE_SHIFT); /* Restore all PTEs' mapping of the large folio */ for (addr = start; addr != end; start_ptep++, addr += PAGE_SIZE) { diff --git a/mm/migrate.c b/mm/migrate.c index dd04f578c19c..2cc5a68f6843 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1654,7 +1654,12 @@ static int migrate_pages_batch(struct list_head *from, /* * The rare folio on the deferred split list should - * be split now. It should not count as a failure. + * be split now. It should not count as a failure: + * but increment nr_failed because, without doing so, + * migrate_pages() may report success with (split but + * unmigrated) pages still on its fromlist; whereas it + * always reports success when its fromlist is empty. + * * Only check it without removing it from the list. * Since the folio can be on deferred_split_scan() * local list and removing it can cause the local list @@ -1669,6 +1674,7 @@ static int migrate_pages_batch(struct list_head *from, if (nr_pages > 2 && !list_empty(&folio->_deferred_list)) { if (try_split_folio(folio, split_folios) == 0) { + nr_failed++; stats->nr_thp_split += is_thp; stats->nr_split++; continue; diff --git a/mm/mm_init.c b/mm/mm_init.c index f72b852bd5b8..3ec04933f7fd 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -2523,9 +2523,6 @@ EXPORT_SYMBOL(init_on_alloc); DEFINE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_FREE_DEFAULT_ON, init_on_free); EXPORT_SYMBOL(init_on_free); -DEFINE_STATIC_KEY_MAYBE(CONFIG_INIT_MLOCKED_ON_FREE_DEFAULT_ON, init_mlocked_on_free); -EXPORT_SYMBOL(init_mlocked_on_free); - static bool _init_on_alloc_enabled_early __read_mostly = IS_ENABLED(CONFIG_INIT_ON_ALLOC_DEFAULT_ON); static int __init early_init_on_alloc(char *buf) @@ -2543,14 +2540,6 @@ static int __init early_init_on_free(char *buf) } early_param("init_on_free", early_init_on_free); -static bool _init_mlocked_on_free_enabled_early __read_mostly - = IS_ENABLED(CONFIG_INIT_MLOCKED_ON_FREE_DEFAULT_ON); -static int __init early_init_mlocked_on_free(char *buf) -{ - return kstrtobool(buf, &_init_mlocked_on_free_enabled_early); -} -early_param("init_mlocked_on_free", early_init_mlocked_on_free); - DEFINE_STATIC_KEY_MAYBE(CONFIG_DEBUG_VM, check_pages_enabled); /* @@ -2578,21 +2567,12 @@ static void __init mem_debugging_and_hardening_init(void) } #endif - if ((_init_on_alloc_enabled_early || _init_on_free_enabled_early || - _init_mlocked_on_free_enabled_early) && + if ((_init_on_alloc_enabled_early || _init_on_free_enabled_early) && page_poisoning_requested) { pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, " - "will take precedence over init_on_alloc, init_on_free " - "and init_mlocked_on_free\n"); + "will take precedence over init_on_alloc and init_on_free\n"); _init_on_alloc_enabled_early = false; _init_on_free_enabled_early = false; - _init_mlocked_on_free_enabled_early = false; - } - - if (_init_mlocked_on_free_enabled_early && _init_on_free_enabled_early) { - pr_info("mem auto-init: init_on_free is on, " - "will take precedence over init_mlocked_on_free\n"); - _init_mlocked_on_free_enabled_early = false; } if (_init_on_alloc_enabled_early) { @@ -2609,17 +2589,9 @@ static void __init mem_debugging_and_hardening_init(void) static_branch_disable(&init_on_free); } - if (_init_mlocked_on_free_enabled_early) { - want_check_pages = true; - static_branch_enable(&init_mlocked_on_free); - } else { - static_branch_disable(&init_mlocked_on_free); - } - - if (IS_ENABLED(CONFIG_KMSAN) && (_init_on_alloc_enabled_early || - _init_on_free_enabled_early || _init_mlocked_on_free_enabled_early)) - pr_info("mem auto-init: please make sure init_on_alloc, init_on_free and " - "init_mlocked_on_free are disabled when running KMSAN\n"); + if (IS_ENABLED(CONFIG_KMSAN) && + (_init_on_alloc_enabled_early || _init_on_free_enabled_early)) + pr_info("mem auto-init: please make sure init_on_alloc and init_on_free are disabled when running KMSAN\n"); #ifdef CONFIG_DEBUG_PAGEALLOC if (debug_pagealloc_enabled()) { @@ -2658,10 +2630,9 @@ static void __init report_meminit(void) else stack = "off"; - pr_info("mem auto-init: stack:%s, heap alloc:%s, heap free:%s, mlocked free:%s\n", + pr_info("mem auto-init: stack:%s, heap alloc:%s, heap free:%s\n", stack, want_init_on_alloc(GFP_KERNEL) ? "on" : "off", - want_init_on_free() ? "on" : "off", - want_init_mlocked_on_free() ? "on" : "off"); + want_init_on_free() ? "on" : "off"); if (want_init_on_free()) pr_info("mem auto-init: clearing system memory may take some time...\n"); } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 222299b5c0e6..7300aa9f14b0 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1016,7 +1016,7 @@ static inline bool should_skip_kasan_poison(struct page *page) return page_kasan_tag(page) == KASAN_TAG_KERNEL; } -void kernel_init_pages(struct page *page, int numpages) +static void kernel_init_pages(struct page *page, int numpages) { int i; diff --git a/mm/page_table_check.c b/mm/page_table_check.c index 4169576bed72..509c6ef8de40 100644 --- a/mm/page_table_check.c +++ b/mm/page_table_check.c @@ -73,6 +73,9 @@ static void page_table_check_clear(unsigned long pfn, unsigned long pgcnt) page = pfn_to_page(pfn); page_ext = page_ext_get(page); + if (!page_ext) + return; + BUG_ON(PageSlab(page)); anon = PageAnon(page); @@ -110,6 +113,9 @@ static void page_table_check_set(unsigned long pfn, unsigned long pgcnt, page = pfn_to_page(pfn); page_ext = page_ext_get(page); + if (!page_ext) + return; + BUG_ON(PageSlab(page)); anon = PageAnon(page); @@ -140,7 +146,10 @@ void __page_table_check_zero(struct page *page, unsigned int order) BUG_ON(PageSlab(page)); page_ext = page_ext_get(page); - BUG_ON(!page_ext); + + if (!page_ext) + return; + for (i = 0; i < (1ul << order); i++) { struct page_table_check *ptc = get_page_table_check(page_ext); diff --git a/mm/shmem.c b/mm/shmem.c index f5d60436b604..a8b181a63402 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1786,7 +1786,7 @@ static int shmem_replace_folio(struct folio **foliop, gfp_t gfp, xa_lock_irq(&swap_mapping->i_pages); error = shmem_replace_entry(swap_mapping, swap_index, old, new); if (!error) { - mem_cgroup_migrate(old, new); + mem_cgroup_replace_folio(old, new); __lruvec_stat_mod_folio(new, NR_FILE_PAGES, 1); __lruvec_stat_mod_folio(new, NR_SHMEM, 1); __lruvec_stat_mod_folio(old, NR_FILE_PAGES, -1); diff --git a/mm/util.c b/mm/util.c index 6c3e6710e4de..fe723241b66f 100644 --- a/mm/util.c +++ b/mm/util.c @@ -139,14 +139,14 @@ EXPORT_SYMBOL(kmemdup_noprof); * kmemdup_array - duplicate a given array. * * @src: array to duplicate. - * @element_size: size of each element of array. * @count: number of elements to duplicate from array. + * @element_size: size of each element of array. * @gfp: GFP mask to use. * * Return: duplicated array of @src or %NULL in case of error, * result is physically contiguous. Use kfree() to free. */ -void *kmemdup_array(const void *src, size_t element_size, size_t count, gfp_t gfp) +void *kmemdup_array(const void *src, size_t count, size_t element_size, gfp_t gfp) { return kmemdup(src, size_mul(element_size, count), gfp); } diff --git a/net/core/filter.c b/net/core/filter.c index 7c46ecba3b01..b077e7467946 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1665,6 +1665,11 @@ static DEFINE_PER_CPU(struct bpf_scratchpad, bpf_sp); static inline int __bpf_try_make_writable(struct sk_buff *skb, unsigned int write_len) { +#ifdef CONFIG_DEBUG_NET + /* Avoid a splat in pskb_may_pull_reason() */ + if (write_len > INT_MAX) + return -EINVAL; +#endif return skb_ensure_writable(skb, write_len); } diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 4f7a61688d18..6a823ba906c6 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -693,11 +693,16 @@ EXPORT_SYMBOL_GPL(__put_net); * get_net_ns - increment the refcount of the network namespace * @ns: common namespace (net) * - * Returns the net's common namespace. + * Returns the net's common namespace or ERR_PTR() if ref is zero. */ struct ns_common *get_net_ns(struct ns_common *ns) { - return &get_net(container_of(ns, struct net, ns))->ns; + struct net *net; + + net = maybe_get_net(container_of(ns, struct net, ns)); + if (net) + return &net->ns; + return ERR_PTR(-EINVAL); } EXPORT_SYMBOL_GPL(get_net_ns); diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index 1f6ae6379e0f..05f9515d2c05 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -59,22 +59,22 @@ XDP_METADATA_KFUNC_xxx nla_put_u64_64bit(rsp, NETDEV_A_DEV_XDP_RX_METADATA_FEATURES, xdp_rx_meta, NETDEV_A_DEV_PAD) || nla_put_u64_64bit(rsp, NETDEV_A_DEV_XSK_FEATURES, - xsk_features, NETDEV_A_DEV_PAD)) { - genlmsg_cancel(rsp, hdr); - return -EINVAL; - } + xsk_features, NETDEV_A_DEV_PAD)) + goto err_cancel_msg; if (netdev->xdp_features & NETDEV_XDP_ACT_XSK_ZEROCOPY) { if (nla_put_u32(rsp, NETDEV_A_DEV_XDP_ZC_MAX_SEGS, - netdev->xdp_zc_max_segs)) { - genlmsg_cancel(rsp, hdr); - return -EINVAL; - } + netdev->xdp_zc_max_segs)) + goto err_cancel_msg; } genlmsg_end(rsp, hdr); return 0; + +err_cancel_msg: + genlmsg_cancel(rsp, hdr); + return -EMSGSIZE; } static void diff --git a/net/core/sock.c b/net/core/sock.c index 69baddcfbd8c..9abc4fe25953 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -3751,6 +3751,9 @@ void sk_common_release(struct sock *sk) sk->sk_prot->unhash(sk); + if (sk->sk_socket) + sk->sk_socket->sk = NULL; + /* * In this point socket cannot receive new packets, but it is possible * that some packets are in flight because some CPU runs receiver and diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 3a95c0f13ce3..8cc0e2f4159d 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -1810,6 +1810,29 @@ static int cipso_v4_genopt(unsigned char *buf, u32 buf_len, return CIPSO_V4_HDR_LEN + ret_val; } +static int cipso_v4_get_actual_opt_len(const unsigned char *data, int len) +{ + int iter = 0, optlen = 0; + + /* determining the new total option length is tricky because of + * the padding necessary, the only thing i can think to do at + * this point is walk the options one-by-one, skipping the + * padding at the end to determine the actual option size and + * from there we can determine the new total option length + */ + while (iter < len) { + if (data[iter] == IPOPT_END) { + break; + } else if (data[iter] == IPOPT_NOP) { + iter++; + } else { + iter += data[iter + 1]; + optlen = iter; + } + } + return optlen; +} + /** * cipso_v4_sock_setattr - Add a CIPSO option to a socket * @sk: the socket @@ -1986,7 +2009,6 @@ static int cipso_v4_delopt(struct ip_options_rcu __rcu **opt_ptr) u8 cipso_len; u8 cipso_off; unsigned char *cipso_ptr; - int iter; int optlen_new; cipso_off = opt->opt.cipso - sizeof(struct iphdr); @@ -2006,19 +2028,8 @@ static int cipso_v4_delopt(struct ip_options_rcu __rcu **opt_ptr) memmove(cipso_ptr, cipso_ptr + cipso_len, opt->opt.optlen - cipso_off - cipso_len); - /* determining the new total option length is tricky because of - * the padding necessary, the only thing i can think to do at - * this point is walk the options one-by-one, skipping the - * padding at the end to determine the actual option size and - * from there we can determine the new total option length */ - iter = 0; - optlen_new = 0; - while (iter < opt->opt.optlen) - if (opt->opt.__data[iter] != IPOPT_NOP) { - iter += opt->opt.__data[iter + 1]; - optlen_new = iter; - } else - iter++; + optlen_new = cipso_v4_get_actual_opt_len(opt->opt.__data, + opt->opt.optlen); hdr_delta = opt->opt.optlen; opt->opt.optlen = (optlen_new + 3) & ~3; hdr_delta -= opt->opt.optlen; @@ -2238,7 +2249,8 @@ int cipso_v4_skbuff_setattr(struct sk_buff *skb, */ int cipso_v4_skbuff_delattr(struct sk_buff *skb) { - int ret_val; + int ret_val, cipso_len, hdr_len_actual, new_hdr_len_actual, new_hdr_len, + hdr_len_delta; struct iphdr *iph; struct ip_options *opt = &IPCB(skb)->opt; unsigned char *cipso_ptr; @@ -2251,16 +2263,37 @@ int cipso_v4_skbuff_delattr(struct sk_buff *skb) if (ret_val < 0) return ret_val; - /* the easiest thing to do is just replace the cipso option with noop - * options since we don't change the size of the packet, although we - * still need to recalculate the checksum */ - iph = ip_hdr(skb); cipso_ptr = (unsigned char *)iph + opt->cipso; - memset(cipso_ptr, IPOPT_NOOP, cipso_ptr[1]); + cipso_len = cipso_ptr[1]; + + hdr_len_actual = sizeof(struct iphdr) + + cipso_v4_get_actual_opt_len((unsigned char *)(iph + 1), + opt->optlen); + new_hdr_len_actual = hdr_len_actual - cipso_len; + new_hdr_len = (new_hdr_len_actual + 3) & ~3; + hdr_len_delta = (iph->ihl << 2) - new_hdr_len; + + /* 1. shift any options after CIPSO to the left */ + memmove(cipso_ptr, cipso_ptr + cipso_len, + new_hdr_len_actual - opt->cipso); + /* 2. move the whole IP header to its new place */ + memmove((unsigned char *)iph + hdr_len_delta, iph, new_hdr_len_actual); + /* 3. adjust the skb layout */ + skb_pull(skb, hdr_len_delta); + skb_reset_network_header(skb); + iph = ip_hdr(skb); + /* 4. re-fill new padding with IPOPT_END (may now be longer) */ + memset((unsigned char *)iph + new_hdr_len_actual, IPOPT_END, + new_hdr_len - new_hdr_len_actual); + + opt->optlen -= hdr_len_delta; opt->cipso = 0; opt->is_changed = 1; - + if (hdr_len_delta != 0) { + iph->ihl = new_hdr_len >> 2; + iph_set_totlen(iph, skb->len); + } ip_send_check(iph); return 0; diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c index 0de863aa5f66..85531437890c 100644 --- a/net/ipv4/tcp_ao.c +++ b/net/ipv4/tcp_ao.c @@ -1972,8 +1972,10 @@ static int tcp_ao_info_cmd(struct sock *sk, unsigned short int family, first = true; } - if (cmd.ao_required && tcp_ao_required_verify(sk)) - return -EKEYREJECTED; + if (cmd.ao_required && tcp_ao_required_verify(sk)) { + err = -EKEYREJECTED; + goto out; + } /* For sockets in TCP_CLOSED it's possible set keys that aren't * matching the future peer (address/port/VRF/etc), diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index f513d1f927ad..bfd390c86d84 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6305,6 +6305,7 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, skb_rbtree_walk_from(data) tcp_mark_skb_lost(sk, data); tcp_xmit_retransmit_queue(sk); + tp->retrans_stamp = 0; NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVEFAIL); return true; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index d9c9a542a414..eb111d20615c 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -2514,7 +2514,8 @@ int __init fib6_init(void) goto out_kmem_cache_create; ret = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETROUTE, NULL, - inet6_dump_fib, RTNL_FLAG_DUMP_UNLOCKED); + inet6_dump_fib, RTNL_FLAG_DUMP_UNLOCKED | + RTNL_FLAG_DUMP_SPLIT_NLM_DONE); if (ret) goto out_unregister_subsys; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 6c9fc4fc9334..5b107f241cdb 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -636,6 +636,8 @@ static void rt6_probe(struct fib6_nh *fib6_nh) rcu_read_lock(); last_probe = READ_ONCE(fib6_nh->last_probe); idev = __in6_dev_get(dev); + if (!idev) + goto out; neigh = __ipv6_neigh_lookup_noref(dev, nh_gw); if (neigh) { if (READ_ONCE(neigh->nud_state) & NUD_VALID) @@ -3601,7 +3603,7 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, if (!dev) goto out; - if (idev->cnf.disable_ipv6) { + if (!idev || idev->cnf.disable_ipv6) { NL_SET_ERR_MSG(extack, "IPv6 is disabled on nexthop device"); err = -EACCES; goto out; diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index 24e2b4b494cb..c434940131b1 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -941,8 +941,8 @@ static int input_action_end_dx6(struct sk_buff *skb, if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled)) return NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, - dev_net(skb->dev), NULL, skb, NULL, - skb_dst(skb)->dev, input_action_end_dx6_finish); + dev_net(skb->dev), NULL, skb, skb->dev, + NULL, input_action_end_dx6_finish); return input_action_end_dx6_finish(dev_net(skb->dev), NULL, skb); drop: @@ -991,8 +991,8 @@ static int input_action_end_dx4(struct sk_buff *skb, if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled)) return NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, - dev_net(skb->dev), NULL, skb, NULL, - skb_dst(skb)->dev, input_action_end_dx4_finish); + dev_net(skb->dev), NULL, skb, skb->dev, + NULL, input_action_end_dx4_finish); return input_action_end_dx4_finish(dev_net(skb->dev), NULL, skb); drop: diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index cc885d3aa9e5..2f1ea5f999a2 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -56,12 +56,18 @@ static int xfrm6_get_saddr(struct net *net, int oif, { struct dst_entry *dst; struct net_device *dev; + struct inet6_dev *idev; dst = xfrm6_dst_lookup(net, 0, oif, NULL, daddr, mark); if (IS_ERR(dst)) return -EHOSTUNREACH; - dev = ip6_dst_idev(dst)->dev; + idev = ip6_dst_idev(dst); + if (!idev) { + dst_release(dst); + return -EHOSTUNREACH; + } + dev = idev->dev; ipv6_dev_get_saddr(dev_net(dev), dev, &daddr->in6, 0, &saddr->in6); dst_release(dst); return 0; diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 88a34db265d8..be4bcbf291a1 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -39,7 +39,6 @@ #include <linux/ip.h> #include <linux/udp.h> #include <linux/l2tp.h> -#include <linux/hash.h> #include <linux/sort.h> #include <linux/file.h> #include <linux/nsproxy.h> @@ -107,11 +106,23 @@ struct l2tp_net { /* Lock for write access to l2tp_tunnel_idr */ spinlock_t l2tp_tunnel_idr_lock; struct idr l2tp_tunnel_idr; - struct hlist_head l2tp_session_hlist[L2TP_HASH_SIZE_2]; - /* Lock for write access to l2tp_session_hlist */ - spinlock_t l2tp_session_hlist_lock; + /* Lock for write access to l2tp_v[23]_session_idr/htable */ + spinlock_t l2tp_session_idr_lock; + struct idr l2tp_v2_session_idr; + struct idr l2tp_v3_session_idr; + struct hlist_head l2tp_v3_session_htable[16]; }; +static inline u32 l2tp_v2_session_key(u16 tunnel_id, u16 session_id) +{ + return ((u32)tunnel_id) << 16 | session_id; +} + +static inline unsigned long l2tp_v3_session_hashkey(struct sock *sk, u32 session_id) +{ + return ((unsigned long)sk) + session_id; +} + #if IS_ENABLED(CONFIG_IPV6) static bool l2tp_sk_is_v6(struct sock *sk) { @@ -125,29 +136,6 @@ static inline struct l2tp_net *l2tp_pernet(const struct net *net) return net_generic(net, l2tp_net_id); } -/* Session hash global list for L2TPv3. - * The session_id SHOULD be random according to RFC3931, but several - * L2TP implementations use incrementing session_ids. So we do a real - * hash on the session_id, rather than a simple bitmask. - */ -static inline struct hlist_head * -l2tp_session_id_hash_2(struct l2tp_net *pn, u32 session_id) -{ - return &pn->l2tp_session_hlist[hash_32(session_id, L2TP_HASH_BITS_2)]; -} - -/* Session hash list. - * The session_id SHOULD be random according to RFC2661, but several - * L2TP implementations (Cisco and Microsoft) use incrementing - * session_ids. So we do a real hash on the session_id, rather than a - * simple bitmask. - */ -static inline struct hlist_head * -l2tp_session_id_hash(struct l2tp_tunnel *tunnel, u32 session_id) -{ - return &tunnel->session_hlist[hash_32(session_id, L2TP_HASH_BITS)]; -} - static void l2tp_tunnel_free(struct l2tp_tunnel *tunnel) { trace_free_tunnel(tunnel); @@ -240,66 +228,82 @@ struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth) } EXPORT_SYMBOL_GPL(l2tp_tunnel_get_nth); -struct l2tp_session *l2tp_tunnel_get_session(struct l2tp_tunnel *tunnel, - u32 session_id) +struct l2tp_session *l2tp_v3_session_get(const struct net *net, struct sock *sk, u32 session_id) { - struct hlist_head *session_list; + const struct l2tp_net *pn = l2tp_pernet(net); struct l2tp_session *session; - session_list = l2tp_session_id_hash(tunnel, session_id); - rcu_read_lock_bh(); - hlist_for_each_entry_rcu(session, session_list, hlist) - if (session->session_id == session_id) { - l2tp_session_inc_refcount(session); - rcu_read_unlock_bh(); + session = idr_find(&pn->l2tp_v3_session_idr, session_id); + if (session && !hash_hashed(&session->hlist) && + refcount_inc_not_zero(&session->ref_count)) { + rcu_read_unlock_bh(); + return session; + } - return session; + /* If we get here and session is non-NULL, the session_id + * collides with one in another tunnel. If sk is non-NULL, + * find the session matching sk. + */ + if (session && sk) { + unsigned long key = l2tp_v3_session_hashkey(sk, session->session_id); + + hash_for_each_possible_rcu(pn->l2tp_v3_session_htable, session, + hlist, key) { + if (session->tunnel->sock == sk && + refcount_inc_not_zero(&session->ref_count)) { + rcu_read_unlock_bh(); + return session; + } } + } rcu_read_unlock_bh(); return NULL; } -EXPORT_SYMBOL_GPL(l2tp_tunnel_get_session); +EXPORT_SYMBOL_GPL(l2tp_v3_session_get); -struct l2tp_session *l2tp_session_get(const struct net *net, u32 session_id) +struct l2tp_session *l2tp_v2_session_get(const struct net *net, u16 tunnel_id, u16 session_id) { - struct hlist_head *session_list; + u32 session_key = l2tp_v2_session_key(tunnel_id, session_id); + const struct l2tp_net *pn = l2tp_pernet(net); struct l2tp_session *session; - session_list = l2tp_session_id_hash_2(l2tp_pernet(net), session_id); - rcu_read_lock_bh(); - hlist_for_each_entry_rcu(session, session_list, global_hlist) - if (session->session_id == session_id) { - l2tp_session_inc_refcount(session); - rcu_read_unlock_bh(); - - return session; - } + session = idr_find(&pn->l2tp_v2_session_idr, session_key); + if (session && refcount_inc_not_zero(&session->ref_count)) { + rcu_read_unlock_bh(); + return session; + } rcu_read_unlock_bh(); return NULL; } +EXPORT_SYMBOL_GPL(l2tp_v2_session_get); + +struct l2tp_session *l2tp_session_get(const struct net *net, struct sock *sk, int pver, + u32 tunnel_id, u32 session_id) +{ + if (pver == L2TP_HDR_VER_2) + return l2tp_v2_session_get(net, tunnel_id, session_id); + else + return l2tp_v3_session_get(net, sk, session_id); +} EXPORT_SYMBOL_GPL(l2tp_session_get); struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth) { - int hash; struct l2tp_session *session; int count = 0; rcu_read_lock_bh(); - for (hash = 0; hash < L2TP_HASH_SIZE; hash++) { - hlist_for_each_entry_rcu(session, &tunnel->session_hlist[hash], hlist) { - if (++count > nth) { - l2tp_session_inc_refcount(session); - rcu_read_unlock_bh(); - return session; - } + list_for_each_entry_rcu(session, &tunnel->session_list, list) { + if (++count > nth) { + l2tp_session_inc_refcount(session); + rcu_read_unlock_bh(); + return session; } } - rcu_read_unlock_bh(); return NULL; @@ -313,86 +317,186 @@ struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net, const char *ifname) { struct l2tp_net *pn = l2tp_pernet(net); - int hash; + unsigned long tunnel_id, tmp; struct l2tp_session *session; + struct l2tp_tunnel *tunnel; rcu_read_lock_bh(); - for (hash = 0; hash < L2TP_HASH_SIZE_2; hash++) { - hlist_for_each_entry_rcu(session, &pn->l2tp_session_hlist[hash], global_hlist) { - if (!strcmp(session->ifname, ifname)) { - l2tp_session_inc_refcount(session); - rcu_read_unlock_bh(); - - return session; + idr_for_each_entry_ul(&pn->l2tp_tunnel_idr, tunnel, tmp, tunnel_id) { + if (tunnel) { + list_for_each_entry_rcu(session, &tunnel->session_list, list) { + if (!strcmp(session->ifname, ifname)) { + l2tp_session_inc_refcount(session); + rcu_read_unlock_bh(); + + return session; + } } } } - rcu_read_unlock_bh(); return NULL; } EXPORT_SYMBOL_GPL(l2tp_session_get_by_ifname); +static void l2tp_session_coll_list_add(struct l2tp_session_coll_list *clist, + struct l2tp_session *session) +{ + l2tp_session_inc_refcount(session); + WARN_ON_ONCE(session->coll_list); + session->coll_list = clist; + spin_lock(&clist->lock); + list_add(&session->clist, &clist->list); + spin_unlock(&clist->lock); +} + +static int l2tp_session_collision_add(struct l2tp_net *pn, + struct l2tp_session *session1, + struct l2tp_session *session2) +{ + struct l2tp_session_coll_list *clist; + + lockdep_assert_held(&pn->l2tp_session_idr_lock); + + if (!session2) + return -EEXIST; + + /* If existing session is in IP-encap tunnel, refuse new session */ + if (session2->tunnel->encap == L2TP_ENCAPTYPE_IP) + return -EEXIST; + + clist = session2->coll_list; + if (!clist) { + /* First collision. Allocate list to manage the collided sessions + * and add the existing session to the list. + */ + clist = kmalloc(sizeof(*clist), GFP_ATOMIC); + if (!clist) + return -ENOMEM; + + spin_lock_init(&clist->lock); + INIT_LIST_HEAD(&clist->list); + refcount_set(&clist->ref_count, 1); + l2tp_session_coll_list_add(clist, session2); + } + + /* If existing session isn't already in the session hlist, add it. */ + if (!hash_hashed(&session2->hlist)) + hash_add(pn->l2tp_v3_session_htable, &session2->hlist, + session2->hlist_key); + + /* Add new session to the hlist and collision list */ + hash_add(pn->l2tp_v3_session_htable, &session1->hlist, + session1->hlist_key); + refcount_inc(&clist->ref_count); + l2tp_session_coll_list_add(clist, session1); + + return 0; +} + +static void l2tp_session_collision_del(struct l2tp_net *pn, + struct l2tp_session *session) +{ + struct l2tp_session_coll_list *clist = session->coll_list; + unsigned long session_key = session->session_id; + struct l2tp_session *session2; + + lockdep_assert_held(&pn->l2tp_session_idr_lock); + + hash_del(&session->hlist); + + if (clist) { + /* Remove session from its collision list. If there + * are other sessions with the same ID, replace this + * session's IDR entry with that session, otherwise + * remove the IDR entry. If this is the last session, + * the collision list data is freed. + */ + spin_lock(&clist->lock); + list_del_init(&session->clist); + session2 = list_first_entry_or_null(&clist->list, struct l2tp_session, clist); + if (session2) { + void *old = idr_replace(&pn->l2tp_v3_session_idr, session2, session_key); + + WARN_ON_ONCE(IS_ERR_VALUE(old)); + } else { + void *removed = idr_remove(&pn->l2tp_v3_session_idr, session_key); + + WARN_ON_ONCE(removed != session); + } + session->coll_list = NULL; + spin_unlock(&clist->lock); + if (refcount_dec_and_test(&clist->ref_count)) + kfree(clist); + l2tp_session_dec_refcount(session); + } +} + int l2tp_session_register(struct l2tp_session *session, struct l2tp_tunnel *tunnel) { - struct l2tp_session *session_walk; - struct hlist_head *g_head; - struct hlist_head *head; - struct l2tp_net *pn; + struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net); + u32 session_key; int err; - head = l2tp_session_id_hash(tunnel, session->session_id); - - spin_lock_bh(&tunnel->hlist_lock); + spin_lock_bh(&tunnel->list_lock); if (!tunnel->acpt_newsess) { err = -ENODEV; goto err_tlock; } - hlist_for_each_entry(session_walk, head, hlist) - if (session_walk->session_id == session->session_id) { - err = -EEXIST; - goto err_tlock; - } - if (tunnel->version == L2TP_HDR_VER_3) { - pn = l2tp_pernet(tunnel->l2tp_net); - g_head = l2tp_session_id_hash_2(pn, session->session_id); - - spin_lock_bh(&pn->l2tp_session_hlist_lock); - + session_key = session->session_id; + spin_lock_bh(&pn->l2tp_session_idr_lock); + err = idr_alloc_u32(&pn->l2tp_v3_session_idr, NULL, + &session_key, session_key, GFP_ATOMIC); /* IP encap expects session IDs to be globally unique, while - * UDP encap doesn't. + * UDP encap doesn't. This isn't per the RFC, which says that + * sessions are identified only by the session ID, but is to + * support existing userspace which depends on it. */ - hlist_for_each_entry(session_walk, g_head, global_hlist) - if (session_walk->session_id == session->session_id && - (session_walk->tunnel->encap == L2TP_ENCAPTYPE_IP || - tunnel->encap == L2TP_ENCAPTYPE_IP)) { - err = -EEXIST; - goto err_tlock_pnlock; - } + if (err == -ENOSPC && tunnel->encap == L2TP_ENCAPTYPE_UDP) { + struct l2tp_session *session2; - l2tp_tunnel_inc_refcount(tunnel); - hlist_add_head_rcu(&session->global_hlist, g_head); - - spin_unlock_bh(&pn->l2tp_session_hlist_lock); + session2 = idr_find(&pn->l2tp_v3_session_idr, + session_key); + err = l2tp_session_collision_add(pn, session, session2); + } + spin_unlock_bh(&pn->l2tp_session_idr_lock); } else { - l2tp_tunnel_inc_refcount(tunnel); + session_key = l2tp_v2_session_key(tunnel->tunnel_id, + session->session_id); + spin_lock_bh(&pn->l2tp_session_idr_lock); + err = idr_alloc_u32(&pn->l2tp_v2_session_idr, NULL, + &session_key, session_key, GFP_ATOMIC); + spin_unlock_bh(&pn->l2tp_session_idr_lock); } - hlist_add_head_rcu(&session->hlist, head); - spin_unlock_bh(&tunnel->hlist_lock); + if (err) { + if (err == -ENOSPC) + err = -EEXIST; + goto err_tlock; + } + + l2tp_tunnel_inc_refcount(tunnel); + + list_add(&session->list, &tunnel->session_list); + spin_unlock_bh(&tunnel->list_lock); + + spin_lock_bh(&pn->l2tp_session_idr_lock); + if (tunnel->version == L2TP_HDR_VER_3) + idr_replace(&pn->l2tp_v3_session_idr, session, session_key); + else + idr_replace(&pn->l2tp_v2_session_idr, session, session_key); + spin_unlock_bh(&pn->l2tp_session_idr_lock); trace_register_session(session); return 0; -err_tlock_pnlock: - spin_unlock_bh(&pn->l2tp_session_hlist_lock); err_tlock: - spin_unlock_bh(&tunnel->hlist_lock); + spin_unlock_bh(&tunnel->list_lock); return err; } @@ -785,19 +889,14 @@ static void l2tp_session_queue_purge(struct l2tp_session *session) } } -/* Internal UDP receive frame. Do the real work of receiving an L2TP data frame - * here. The skb is not on a list when we get here. - * Returns 0 if the packet was a data packet and was successfully passed on. - * Returns 1 if the packet was not a good data packet and could not be - * forwarded. All such packets are passed up to userspace to deal with. - */ -static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) +/* UDP encapsulation receive handler. See net/ipv4/udp.c for details. */ +int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) { struct l2tp_session *session = NULL; - struct l2tp_tunnel *orig_tunnel = tunnel; + struct l2tp_tunnel *tunnel = NULL; + struct net *net = sock_net(sk); unsigned char *ptr, *optr; u16 hdrflags; - u32 tunnel_id, session_id; u16 version; int length; @@ -807,11 +906,8 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) __skb_pull(skb, sizeof(struct udphdr)); /* Short packet? */ - if (!pskb_may_pull(skb, L2TP_HDR_SIZE_MAX)) { - pr_debug_ratelimited("%s: recv short packet (len=%d)\n", - tunnel->name, skb->len); - goto invalid; - } + if (!pskb_may_pull(skb, L2TP_HDR_SIZE_MAX)) + goto pass; /* Point to L2TP header */ optr = skb->data; @@ -834,6 +930,8 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) ptr += 2; if (version == L2TP_HDR_VER_2) { + u16 tunnel_id, session_id; + /* If length is present, skip it */ if (hdrflags & L2TP_HDRFLAG_L) ptr += 2; @@ -841,49 +939,35 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) /* Extract tunnel and session ID */ tunnel_id = ntohs(*(__be16 *)ptr); ptr += 2; - - if (tunnel_id != tunnel->tunnel_id) { - /* We are receiving trafic for another tunnel, probably - * because we have several tunnels between the same - * IP/port quadruple, look it up. - */ - struct l2tp_tunnel *alt_tunnel; - - alt_tunnel = l2tp_tunnel_get(tunnel->l2tp_net, tunnel_id); - if (!alt_tunnel) - goto pass; - tunnel = alt_tunnel; - } - session_id = ntohs(*(__be16 *)ptr); ptr += 2; + + session = l2tp_v2_session_get(net, tunnel_id, session_id); } else { + u32 session_id; + ptr += 2; /* skip reserved bits */ - tunnel_id = tunnel->tunnel_id; session_id = ntohl(*(__be32 *)ptr); ptr += 4; - } - /* Check protocol version */ - if (version != tunnel->version) { - pr_debug_ratelimited("%s: recv protocol version mismatch: got %d expected %d\n", - tunnel->name, version, tunnel->version); - goto invalid; + session = l2tp_v3_session_get(net, sk, session_id); } - /* Find the session context */ - session = l2tp_tunnel_get_session(tunnel, session_id); if (!session || !session->recv_skb) { if (session) l2tp_session_dec_refcount(session); /* Not found? Pass to userspace to deal with */ - pr_debug_ratelimited("%s: no session found (%u/%u). Passing up.\n", - tunnel->name, tunnel_id, session_id); goto pass; } - if (tunnel->version == L2TP_HDR_VER_3 && + tunnel = session->tunnel; + + /* Check protocol version */ + if (version != tunnel->version) + goto invalid; + + if (version == L2TP_HDR_VER_3 && l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) { l2tp_session_dec_refcount(session); goto invalid; @@ -892,9 +976,6 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) l2tp_recv_common(session, skb, ptr, optr, hdrflags, length); l2tp_session_dec_refcount(session); - if (tunnel != orig_tunnel) - l2tp_tunnel_dec_refcount(tunnel); - return 0; invalid: @@ -904,51 +985,14 @@ pass: /* Put UDP header back */ __skb_push(skb, sizeof(struct udphdr)); - if (tunnel != orig_tunnel) - l2tp_tunnel_dec_refcount(tunnel); - - return 1; -} - -/* UDP encapsulation receive and error receive handlers. - * See net/ipv4/udp.c for details. - * - * Note that these functions are called from inside an - * RCU-protected region, but without the socket being locked. - * - * Hence we use rcu_dereference_sk_user_data to access the - * tunnel data structure rather the usual l2tp_sk_to_tunnel - * accessor function. - */ -int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) -{ - struct l2tp_tunnel *tunnel; - - tunnel = rcu_dereference_sk_user_data(sk); - if (!tunnel) - goto pass_up; - if (WARN_ON(tunnel->magic != L2TP_TUNNEL_MAGIC)) - goto pass_up; - - if (l2tp_udp_recv_core(tunnel, skb)) - goto pass_up; - - return 0; - -pass_up: return 1; } EXPORT_SYMBOL_GPL(l2tp_udp_encap_recv); +/* UDP encapsulation receive error handler. See net/ipv4/udp.c for details. */ static void l2tp_udp_encap_err_recv(struct sock *sk, struct sk_buff *skb, int err, __be16 port, u32 info, u8 *payload) { - struct l2tp_tunnel *tunnel; - - tunnel = rcu_dereference_sk_user_data(sk); - if (!tunnel || tunnel->fd < 0) - return; - sk->sk_err = err; sk_error_report(sk); @@ -1206,26 +1250,36 @@ end: return; } -/* Remove an l2tp session from l2tp_core's hash lists. */ +/* Remove an l2tp session from l2tp_core's lists. */ static void l2tp_session_unhash(struct l2tp_session *session) { struct l2tp_tunnel *tunnel = session->tunnel; - /* Remove the session from core hashes */ if (tunnel) { - /* Remove from the per-tunnel hash */ - spin_lock_bh(&tunnel->hlist_lock); - hlist_del_init_rcu(&session->hlist); - spin_unlock_bh(&tunnel->hlist_lock); - - /* For L2TPv3 we have a per-net hash: remove from there, too */ - if (tunnel->version != L2TP_HDR_VER_2) { - struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net); - - spin_lock_bh(&pn->l2tp_session_hlist_lock); - hlist_del_init_rcu(&session->global_hlist); - spin_unlock_bh(&pn->l2tp_session_hlist_lock); + struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net); + struct l2tp_session *removed = session; + + /* Remove from the per-tunnel list */ + spin_lock_bh(&tunnel->list_lock); + list_del_init(&session->list); + spin_unlock_bh(&tunnel->list_lock); + + /* Remove from per-net IDR */ + spin_lock_bh(&pn->l2tp_session_idr_lock); + if (tunnel->version == L2TP_HDR_VER_3) { + if (hash_hashed(&session->hlist)) + l2tp_session_collision_del(pn, session); + else + removed = idr_remove(&pn->l2tp_v3_session_idr, + session->session_id); + } else { + u32 session_key = l2tp_v2_session_key(tunnel->tunnel_id, + session->session_id); + removed = idr_remove(&pn->l2tp_v2_session_idr, + session_key); } + WARN_ON_ONCE(removed && removed != session); + spin_unlock_bh(&pn->l2tp_session_idr_lock); synchronize_rcu(); } @@ -1236,28 +1290,19 @@ static void l2tp_session_unhash(struct l2tp_session *session) static void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel) { struct l2tp_session *session; - int hash; + struct list_head __rcu *pos; + struct list_head *tmp; - spin_lock_bh(&tunnel->hlist_lock); + spin_lock_bh(&tunnel->list_lock); tunnel->acpt_newsess = false; - for (hash = 0; hash < L2TP_HASH_SIZE; hash++) { -again: - hlist_for_each_entry_rcu(session, &tunnel->session_hlist[hash], hlist) { - hlist_del_init_rcu(&session->hlist); - - spin_unlock_bh(&tunnel->hlist_lock); - l2tp_session_delete(session); - spin_lock_bh(&tunnel->hlist_lock); - - /* Now restart from the beginning of this hash - * chain. We always remove a session from the - * list so we are guaranteed to make forward - * progress. - */ - goto again; - } + list_for_each_safe(pos, tmp, &tunnel->session_list) { + session = list_entry(pos, struct l2tp_session, list); + list_del_init(&session->list); + spin_unlock_bh(&tunnel->list_lock); + l2tp_session_delete(session); + spin_lock_bh(&tunnel->list_lock); } - spin_unlock_bh(&tunnel->hlist_lock); + spin_unlock_bh(&tunnel->list_lock); } /* Tunnel socket destroy hook for UDP encapsulation */ @@ -1451,8 +1496,9 @@ int l2tp_tunnel_create(int fd, int version, u32 tunnel_id, u32 peer_tunnel_id, tunnel->magic = L2TP_TUNNEL_MAGIC; sprintf(&tunnel->name[0], "tunl %u", tunnel_id); - spin_lock_init(&tunnel->hlist_lock); + spin_lock_init(&tunnel->list_lock); tunnel->acpt_newsess = true; + INIT_LIST_HEAD(&tunnel->session_list); tunnel->encap = encap; @@ -1462,8 +1508,6 @@ int l2tp_tunnel_create(int fd, int version, u32 tunnel_id, u32 peer_tunnel_id, /* Init delete workqueue struct */ INIT_WORK(&tunnel->del_work, l2tp_tunnel_del_work); - INIT_LIST_HEAD(&tunnel->list); - err = 0; err: if (tunnelp) @@ -1651,8 +1695,10 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn skb_queue_head_init(&session->reorder_q); + session->hlist_key = l2tp_v3_session_hashkey(tunnel->sock, session->session_id); INIT_HLIST_NODE(&session->hlist); - INIT_HLIST_NODE(&session->global_hlist); + INIT_LIST_HEAD(&session->clist); + INIT_LIST_HEAD(&session->list); if (cfg) { session->pwtype = cfg->pw_type; @@ -1685,15 +1731,13 @@ EXPORT_SYMBOL_GPL(l2tp_session_create); static __net_init int l2tp_init_net(struct net *net) { struct l2tp_net *pn = net_generic(net, l2tp_net_id); - int hash; idr_init(&pn->l2tp_tunnel_idr); spin_lock_init(&pn->l2tp_tunnel_idr_lock); - for (hash = 0; hash < L2TP_HASH_SIZE_2; hash++) - INIT_HLIST_HEAD(&pn->l2tp_session_hlist[hash]); - - spin_lock_init(&pn->l2tp_session_hlist_lock); + idr_init(&pn->l2tp_v2_session_idr); + idr_init(&pn->l2tp_v3_session_idr); + spin_lock_init(&pn->l2tp_session_idr_lock); return 0; } @@ -1703,7 +1747,6 @@ static __net_exit void l2tp_exit_net(struct net *net) struct l2tp_net *pn = l2tp_pernet(net); struct l2tp_tunnel *tunnel = NULL; unsigned long tunnel_id, tmp; - int hash; rcu_read_lock_bh(); idr_for_each_entry_ul(&pn->l2tp_tunnel_idr, tunnel, tmp, tunnel_id) { @@ -1716,8 +1759,8 @@ static __net_exit void l2tp_exit_net(struct net *net) flush_workqueue(l2tp_wq); rcu_barrier(); - for (hash = 0; hash < L2TP_HASH_SIZE_2; hash++) - WARN_ON_ONCE(!hlist_empty(&pn->l2tp_session_hlist[hash])); + idr_destroy(&pn->l2tp_v2_session_idr); + idr_destroy(&pn->l2tp_v3_session_idr); idr_destroy(&pn->l2tp_tunnel_idr); } diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 91ebf0a3f499..8ac81bc1bc6f 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -19,14 +19,6 @@ #define L2TP_TUNNEL_MAGIC 0x42114DDA #define L2TP_SESSION_MAGIC 0x0C04EB7D -/* Per tunnel session hash table size */ -#define L2TP_HASH_BITS 4 -#define L2TP_HASH_SIZE BIT(L2TP_HASH_BITS) - -/* System-wide session hash table size */ -#define L2TP_HASH_BITS_2 8 -#define L2TP_HASH_SIZE_2 BIT(L2TP_HASH_BITS_2) - struct sk_buff; struct l2tp_stats { @@ -61,10 +53,15 @@ struct l2tp_session_cfg { char *ifname; }; +struct l2tp_session_coll_list { + spinlock_t lock; /* for access to list */ + struct list_head list; + refcount_t ref_count; +}; + /* Represents a session (pseudowire) instance. * Tracks runtime state including cookies, dataplane packet sequencing, and IO statistics. - * Is linked into a per-tunnel session hashlist; and in the case of an L2TPv3 session into - * an additional per-net ("global") hashlist. + * Is linked into a per-tunnel session list and a per-net ("global") IDR tree. */ #define L2TP_SESSION_NAME_MAX 32 struct l2tp_session { @@ -88,8 +85,12 @@ struct l2tp_session { u32 nr_oos; /* NR of last OOS packet */ int nr_oos_count; /* for OOS recovery */ int nr_oos_count_max; - struct hlist_node hlist; /* hash list node */ + struct list_head list; /* per-tunnel list node */ refcount_t ref_count; + struct hlist_node hlist; /* per-net session hlist */ + unsigned long hlist_key; /* key for session hlist */ + struct l2tp_session_coll_list *coll_list; /* session collision list */ + struct list_head clist; /* for coll_list */ char name[L2TP_SESSION_NAME_MAX]; /* for logging */ char ifname[IFNAMSIZ]; @@ -102,7 +103,6 @@ struct l2tp_session { int reorder_skip; /* set if skip to next nr */ enum l2tp_pwtype pwtype; struct l2tp_stats stats; - struct hlist_node global_hlist; /* global hash list node */ /* Session receive handler for data packets. * Each pseudowire implementation should implement this callback in order to @@ -114,7 +114,7 @@ struct l2tp_session { /* Session close handler. * Each pseudowire implementation may implement this callback in order to carry * out pseudowire-specific shutdown actions. - * The callback is called by core after unhashing the session and purging its + * The callback is called by core after unlisting the session and purging its * reorder queue. */ void (*session_close)(struct l2tp_session *session); @@ -150,7 +150,7 @@ struct l2tp_tunnel_cfg { /* Represents a tunnel instance. * Tracks runtime state including IO statistics. * Holds the tunnel socket (either passed from userspace or directly created by the kernel). - * Maintains a hashlist of sessions belonging to the tunnel instance. + * Maintains a list of sessions belonging to the tunnel instance. * Is linked into a per-net list of tunnels. */ #define L2TP_TUNNEL_NAME_MAX 20 @@ -160,12 +160,11 @@ struct l2tp_tunnel { unsigned long dead; struct rcu_head rcu; - spinlock_t hlist_lock; /* write-protection for session_hlist */ + spinlock_t list_lock; /* write-protection for session_list */ bool acpt_newsess; /* indicates whether this tunnel accepts - * new sessions. Protected by hlist_lock. + * new sessions. Protected by list_lock. */ - struct hlist_head session_hlist[L2TP_HASH_SIZE]; - /* hashed list of sessions, hashed by id */ + struct list_head session_list; /* list of sessions */ u32 tunnel_id; u32 peer_tunnel_id; int version; /* 2=>L2TPv2, 3=>L2TPv3 */ @@ -174,7 +173,6 @@ struct l2tp_tunnel { enum l2tp_encap_type encap; struct l2tp_stats stats; - struct list_head list; /* list node on per-namespace list of tunnels */ struct net *l2tp_net; /* the net we belong to */ refcount_t ref_count; @@ -224,10 +222,11 @@ void l2tp_session_dec_refcount(struct l2tp_session *session); */ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id); struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth); -struct l2tp_session *l2tp_tunnel_get_session(struct l2tp_tunnel *tunnel, - u32 session_id); -struct l2tp_session *l2tp_session_get(const struct net *net, u32 session_id); +struct l2tp_session *l2tp_v3_session_get(const struct net *net, struct sock *sk, u32 session_id); +struct l2tp_session *l2tp_v2_session_get(const struct net *net, u16 tunnel_id, u16 session_id); +struct l2tp_session *l2tp_session_get(const struct net *net, struct sock *sk, int pver, + u32 tunnel_id, u32 session_id); struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth); struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net, const char *ifname); diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c index 4595b56d175d..8755ae521154 100644 --- a/net/l2tp/l2tp_debugfs.c +++ b/net/l2tp/l2tp_debugfs.c @@ -123,17 +123,14 @@ static void l2tp_dfs_seq_tunnel_show(struct seq_file *m, void *v) struct l2tp_tunnel *tunnel = v; struct l2tp_session *session; int session_count = 0; - int hash; rcu_read_lock_bh(); - for (hash = 0; hash < L2TP_HASH_SIZE; hash++) { - hlist_for_each_entry_rcu(session, &tunnel->session_hlist[hash], hlist) { - /* Session ID of zero is a dummy/reserved value used by pppol2tp */ - if (session->session_id == 0) - continue; + list_for_each_entry_rcu(session, &tunnel->session_list, list) { + /* Session ID of zero is a dummy/reserved value used by pppol2tp */ + if (session->session_id == 0) + continue; - session_count++; - } + session_count++; } rcu_read_unlock_bh(); diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 19c8cc5289d5..e48aa177d74c 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -140,7 +140,7 @@ static int l2tp_ip_recv(struct sk_buff *skb) } /* Ok, this is a data packet. Lookup the session. */ - session = l2tp_session_get(net, session_id); + session = l2tp_v3_session_get(net, NULL, session_id); if (!session) goto discard; diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 8780ec64f376..d217ff1f229e 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -150,7 +150,7 @@ static int l2tp_ip6_recv(struct sk_buff *skb) } /* Ok, this is a data packet. Lookup the session. */ - session = l2tp_session_get(net, session_id); + session = l2tp_v3_session_get(net, NULL, session_id); if (!session) goto discard; diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index a901fd14fe3b..d105030520f9 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -61,7 +61,8 @@ static struct l2tp_session *l2tp_nl_session_get(struct genl_info *info) session_id = nla_get_u32(info->attrs[L2TP_ATTR_SESSION_ID]); tunnel = l2tp_tunnel_get(net, tunnel_id); if (tunnel) { - session = l2tp_tunnel_get_session(tunnel, session_id); + session = l2tp_session_get(net, tunnel->sock, tunnel->version, + tunnel_id, session_id); l2tp_tunnel_dec_refcount(tunnel); } } @@ -635,7 +636,8 @@ static int l2tp_nl_cmd_session_create(struct sk_buff *skb, struct genl_info *inf &cfg); if (ret >= 0) { - session = l2tp_tunnel_get_session(tunnel, session_id); + session = l2tp_session_get(net, tunnel->sock, tunnel->version, + tunnel_id, session_id); if (session) { ret = l2tp_session_notify(&l2tp_nl_family, info, session, L2TP_CMD_SESSION_CREATE); diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 6146e4e67bbb..3596290047b2 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -753,7 +753,8 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, if (tunnel->peer_tunnel_id == 0) tunnel->peer_tunnel_id = info.peer_tunnel_id; - session = l2tp_tunnel_get_session(tunnel, info.session_id); + session = l2tp_session_get(sock_net(sk), tunnel->sock, tunnel->version, + info.tunnel_id, info.session_id); if (session) { drop_refcnt = true; @@ -1045,7 +1046,8 @@ static int pppol2tp_tunnel_copy_stats(struct pppol2tp_ioc_stats *stats, /* If session_id is set, search the corresponding session in the * context of this tunnel and record the session's statistics. */ - session = l2tp_tunnel_get_session(tunnel, stats->session_id); + session = l2tp_session_get(tunnel->l2tp_net, tunnel->sock, tunnel->version, + tunnel->tunnel_id, stats->session_id); if (!session) return -EBADR; diff --git a/net/mac80211/driver-ops.c b/net/mac80211/driver-ops.c index dce37ba8ebe3..254d745832cb 100644 --- a/net/mac80211/driver-ops.c +++ b/net/mac80211/driver-ops.c @@ -311,6 +311,18 @@ int drv_assign_vif_chanctx(struct ieee80211_local *local, might_sleep(); lockdep_assert_wiphy(local->hw.wiphy); + /* + * We should perhaps push emulate chanctx down and only + * make it call ->config() when the chanctx is actually + * assigned here (and unassigned below), but that's yet + * another change to all drivers to add assign/unassign + * emulation callbacks. Maybe later. + */ + if (sdata->vif.type == NL80211_IFTYPE_MONITOR && + local->emulate_chanctx && + !ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) + return 0; + if (!check_sdata_in_driver(sdata)) return -EIO; @@ -338,6 +350,11 @@ void drv_unassign_vif_chanctx(struct ieee80211_local *local, might_sleep(); lockdep_assert_wiphy(local->hw.wiphy); + if (sdata->vif.type == NL80211_IFTYPE_MONITOR && + local->emulate_chanctx && + !ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) + return; + if (!check_sdata_in_driver(sdata)) return; diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index d1a49ee4a194..e31ce8d7649d 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -686,6 +686,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do ieee80211_del_virtual_monitor(local); ieee80211_recalc_idle(local); + ieee80211_recalc_offload(local); if (!(sdata->u.mntr.flags & MONITOR_FLAG_ACTIVE)) break; @@ -1121,9 +1122,6 @@ int ieee80211_add_virtual_monitor(struct ieee80211_local *local) struct ieee80211_sub_if_data *sdata; int ret; - if (!ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) - return 0; - ASSERT_RTNL(); lockdep_assert_wiphy(local->hw.wiphy); @@ -1145,11 +1143,13 @@ int ieee80211_add_virtual_monitor(struct ieee80211_local *local) ieee80211_set_default_queues(sdata); - ret = drv_add_interface(local, sdata); - if (WARN_ON(ret)) { - /* ok .. stupid driver, it asked for this! */ - kfree(sdata); - return ret; + if (ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) { + ret = drv_add_interface(local, sdata); + if (WARN_ON(ret)) { + /* ok .. stupid driver, it asked for this! */ + kfree(sdata); + return ret; + } } set_bit(SDATA_STATE_RUNNING, &sdata->state); @@ -1187,9 +1187,6 @@ void ieee80211_del_virtual_monitor(struct ieee80211_local *local) { struct ieee80211_sub_if_data *sdata; - if (!ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) - return; - ASSERT_RTNL(); lockdep_assert_wiphy(local->hw.wiphy); @@ -1209,7 +1206,8 @@ void ieee80211_del_virtual_monitor(struct ieee80211_local *local) ieee80211_link_release_channel(&sdata->deflink); - drv_remove_interface(local, sdata); + if (ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) + drv_remove_interface(local, sdata); kfree(sdata); } diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index 8ecc4b710b0e..b5f2df61c7f6 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -358,7 +358,8 @@ static bool ieee80211_prep_hw_scan(struct ieee80211_sub_if_data *sdata) struct cfg80211_scan_request *req; struct cfg80211_chan_def chandef; u8 bands_used = 0; - int i, ielen, n_chans; + int i, ielen; + u32 *n_chans; u32 flags = 0; req = rcu_dereference_protected(local->scan_req, @@ -368,34 +369,34 @@ static bool ieee80211_prep_hw_scan(struct ieee80211_sub_if_data *sdata) return false; if (ieee80211_hw_check(&local->hw, SINGLE_SCAN_ON_ALL_BANDS)) { + local->hw_scan_req->req.n_channels = req->n_channels; + for (i = 0; i < req->n_channels; i++) { local->hw_scan_req->req.channels[i] = req->channels[i]; bands_used |= BIT(req->channels[i]->band); } - - n_chans = req->n_channels; } else { do { if (local->hw_scan_band == NUM_NL80211_BANDS) return false; - n_chans = 0; + n_chans = &local->hw_scan_req->req.n_channels; + *n_chans = 0; for (i = 0; i < req->n_channels; i++) { if (req->channels[i]->band != local->hw_scan_band) continue; - local->hw_scan_req->req.channels[n_chans] = + local->hw_scan_req->req.channels[(*n_chans)++] = req->channels[i]; - n_chans++; + bands_used |= BIT(req->channels[i]->band); } local->hw_scan_band++; - } while (!n_chans); + } while (!*n_chans); } - local->hw_scan_req->req.n_channels = n_chans; ieee80211_prepare_scan_chandef(&chandef); if (req->flags & NL80211_SCAN_FLAG_MIN_PREQ_CONTENT) diff --git a/net/mac80211/util.c b/net/mac80211/util.c index c73ff7dfbdba..94171b9f2b1d 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1843,7 +1843,7 @@ int ieee80211_reconfig(struct ieee80211_local *local) /* add interfaces */ sdata = wiphy_dereference(local->hw.wiphy, local->monitor_sdata); - if (sdata) { + if (sdata && ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) { /* in HW restart it exists already */ WARN_ON(local->resuming); res = drv_add_interface(local, sdata); diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 3126911f5042..b00fc285b334 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -815,12 +815,21 @@ int __init netfilter_init(void) if (ret < 0) goto err; +#ifdef CONFIG_LWTUNNEL + ret = netfilter_lwtunnel_init(); + if (ret < 0) + goto err_lwtunnel_pernet; +#endif ret = netfilter_log_init(); if (ret < 0) - goto err_pernet; + goto err_log_pernet; return 0; -err_pernet: +err_log_pernet: +#ifdef CONFIG_LWTUNNEL + netfilter_lwtunnel_fini(); +err_lwtunnel_pernet: +#endif unregister_pernet_subsys(&netfilter_net_ops); err: return ret; diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index c7ae4d9bf3d2..61431690cbd5 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -53,12 +53,13 @@ MODULE_DESCRIPTION("core IP set support"); MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_IPSET); /* When the nfnl mutex or ip_set_ref_lock is held: */ -#define ip_set_dereference(p) \ - rcu_dereference_protected(p, \ +#define ip_set_dereference(inst) \ + rcu_dereference_protected((inst)->ip_set_list, \ lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET) || \ - lockdep_is_held(&ip_set_ref_lock)) + lockdep_is_held(&ip_set_ref_lock) || \ + (inst)->is_deleted) #define ip_set(inst, id) \ - ip_set_dereference((inst)->ip_set_list)[id] + ip_set_dereference(inst)[id] #define ip_set_ref_netlink(inst,id) \ rcu_dereference_raw((inst)->ip_set_list)[id] #define ip_set_dereference_nfnl(p) \ @@ -1133,7 +1134,7 @@ static int ip_set_create(struct sk_buff *skb, const struct nfnl_info *info, if (!list) goto cleanup; /* nfnl mutex is held, both lists are valid */ - tmp = ip_set_dereference(inst->ip_set_list); + tmp = ip_set_dereference(inst); memcpy(list, tmp, sizeof(struct ip_set *) * inst->ip_set_max); rcu_assign_pointer(inst->ip_set_list, list); /* Make sure all current packets have passed through */ diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 74112e9c5dab..6c40bdf8b05a 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -22,9 +22,6 @@ #include <net/netfilter/nf_conntrack_acct.h> #include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/nf_conntrack_timestamp.h> -#ifdef CONFIG_LWTUNNEL -#include <net/netfilter/nf_hooks_lwtunnel.h> -#endif #include <linux/rculist_nulls.h> static bool enable_hooks __read_mostly; @@ -612,9 +609,6 @@ enum nf_ct_sysctl_index { NF_SYSCTL_CT_PROTO_TIMEOUT_GRE, NF_SYSCTL_CT_PROTO_TIMEOUT_GRE_STREAM, #endif -#ifdef CONFIG_LWTUNNEL - NF_SYSCTL_CT_LWTUNNEL, -#endif NF_SYSCTL_CT_LAST_SYSCTL, }; @@ -946,15 +940,6 @@ static struct ctl_table nf_ct_sysctl_table[] = { .proc_handler = proc_dointvec_jiffies, }, #endif -#ifdef CONFIG_LWTUNNEL - [NF_SYSCTL_CT_LWTUNNEL] = { - .procname = "nf_hooks_lwtunnel", - .data = NULL, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = nf_hooks_lwtunnel_sysctl_handler, - }, -#endif }; static struct ctl_table nf_ct_netfilter_table[] = { diff --git a/net/netfilter/nf_hooks_lwtunnel.c b/net/netfilter/nf_hooks_lwtunnel.c index 00e89ffd78f6..7cdb59bb4459 100644 --- a/net/netfilter/nf_hooks_lwtunnel.c +++ b/net/netfilter/nf_hooks_lwtunnel.c @@ -3,6 +3,9 @@ #include <linux/sysctl.h> #include <net/lwtunnel.h> #include <net/netfilter/nf_hooks_lwtunnel.h> +#include <linux/netfilter.h> + +#include "nf_internals.h" static inline int nf_hooks_lwtunnel_get(void) { @@ -50,4 +53,68 @@ int nf_hooks_lwtunnel_sysctl_handler(struct ctl_table *table, int write, return ret; } EXPORT_SYMBOL_GPL(nf_hooks_lwtunnel_sysctl_handler); + +static struct ctl_table nf_lwtunnel_sysctl_table[] = { + { + .procname = "nf_hooks_lwtunnel", + .data = NULL, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = nf_hooks_lwtunnel_sysctl_handler, + }, +}; + +static int __net_init nf_lwtunnel_net_init(struct net *net) +{ + struct ctl_table_header *hdr; + struct ctl_table *table; + + table = nf_lwtunnel_sysctl_table; + if (!net_eq(net, &init_net)) { + table = kmemdup(nf_lwtunnel_sysctl_table, + sizeof(nf_lwtunnel_sysctl_table), + GFP_KERNEL); + if (!table) + goto err_alloc; + } + + hdr = register_net_sysctl_sz(net, "net/netfilter", table, + ARRAY_SIZE(nf_lwtunnel_sysctl_table)); + if (!hdr) + goto err_reg; + + net->nf.nf_lwtnl_dir_header = hdr; + + return 0; +err_reg: + if (!net_eq(net, &init_net)) + kfree(table); +err_alloc: + return -ENOMEM; +} + +static void __net_exit nf_lwtunnel_net_exit(struct net *net) +{ + const struct ctl_table *table; + + table = net->nf.nf_lwtnl_dir_header->ctl_table_arg; + unregister_net_sysctl_table(net->nf.nf_lwtnl_dir_header); + if (!net_eq(net, &init_net)) + kfree(table); +} + +static struct pernet_operations nf_lwtunnel_net_ops = { + .init = nf_lwtunnel_net_init, + .exit = nf_lwtunnel_net_exit, +}; + +int __init netfilter_lwtunnel_init(void) +{ + return register_pernet_subsys(&nf_lwtunnel_net_ops); +} + +void netfilter_lwtunnel_fini(void) +{ + unregister_pernet_subsys(&nf_lwtunnel_net_ops); +} #endif /* CONFIG_SYSCTL */ diff --git a/net/netfilter/nf_internals.h b/net/netfilter/nf_internals.h index 832ae64179f0..25403023060b 100644 --- a/net/netfilter/nf_internals.h +++ b/net/netfilter/nf_internals.h @@ -29,6 +29,12 @@ void nf_queue_nf_hook_drop(struct net *net); /* nf_log.c */ int __init netfilter_log_init(void); +#ifdef CONFIG_LWTUNNEL +/* nf_hooks_lwtunnel.c */ +int __init netfilter_lwtunnel_init(void); +void netfilter_lwtunnel_fini(void); +#endif + /* core.c */ void nf_hook_entries_delete_raw(struct nf_hook_entries __rcu **pp, const struct nf_hook_ops *reg); diff --git a/net/netrom/nr_timer.c b/net/netrom/nr_timer.c index 4e7c968cde2d..5e3ca068f04e 100644 --- a/net/netrom/nr_timer.c +++ b/net/netrom/nr_timer.c @@ -121,7 +121,8 @@ static void nr_heartbeat_expiry(struct timer_list *t) is accepted() it isn't 'dead' so doesn't get removed. */ if (sock_flag(sk, SOCK_DESTROY) || (sk->sk_state == TCP_LISTEN && sock_flag(sk, SOCK_DEAD))) { - sock_hold(sk); + if (sk->sk_state == TCP_LISTEN) + sock_hold(sk); bh_unlock_sock(sk); nr_destroy_socket(sk); goto out; diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 7458b3154426..2714c4ed928e 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -830,7 +830,6 @@ int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index, u32 max; if (*index) { -again: rcu_read_lock(); p = idr_find(&idrinfo->action_idr, *index); @@ -839,7 +838,7 @@ again: * index but did not assign the pointer yet. */ rcu_read_unlock(); - goto again; + return -EAGAIN; } if (!p) { diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index baac083fd8f1..2a96d9c1db65 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -41,21 +41,26 @@ static struct workqueue_struct *act_ct_wq; static struct rhashtable zones_ht; static DEFINE_MUTEX(zones_mutex); +struct zones_ht_key { + struct net *net; + u16 zone; +}; + struct tcf_ct_flow_table { struct rhash_head node; /* In zones tables */ struct rcu_work rwork; struct nf_flowtable nf_ft; refcount_t ref; - u16 zone; + struct zones_ht_key key; bool dying; }; static const struct rhashtable_params zones_params = { .head_offset = offsetof(struct tcf_ct_flow_table, node), - .key_offset = offsetof(struct tcf_ct_flow_table, zone), - .key_len = sizeof_field(struct tcf_ct_flow_table, zone), + .key_offset = offsetof(struct tcf_ct_flow_table, key), + .key_len = sizeof_field(struct tcf_ct_flow_table, key), .automatic_shrinking = true, }; @@ -316,11 +321,12 @@ static struct nf_flowtable_type flowtable_ct = { static int tcf_ct_flow_table_get(struct net *net, struct tcf_ct_params *params) { + struct zones_ht_key key = { .net = net, .zone = params->zone }; struct tcf_ct_flow_table *ct_ft; int err = -ENOMEM; mutex_lock(&zones_mutex); - ct_ft = rhashtable_lookup_fast(&zones_ht, ¶ms->zone, zones_params); + ct_ft = rhashtable_lookup_fast(&zones_ht, &key, zones_params); if (ct_ft && refcount_inc_not_zero(&ct_ft->ref)) goto out_unlock; @@ -329,7 +335,7 @@ static int tcf_ct_flow_table_get(struct net *net, struct tcf_ct_params *params) goto err_alloc; refcount_set(&ct_ft->ref, 1); - ct_ft->zone = params->zone; + ct_ft->key = key; err = rhashtable_insert_fast(&zones_ht, &ct_ft->node, zones_params); if (err) goto err_insert; diff --git a/net/tipc/node.c b/net/tipc/node.c index c1e890a82434..500320e5ca47 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -2105,6 +2105,7 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b) } else { n = tipc_node_find_by_id(net, ehdr->id); } + skb_dst_force(skb); tipc_crypto_rcv(net, (n) ? n->crypto_rx : NULL, &skb, b); if (!skb) return; diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 2f2a3163968a..0222ede0feb6 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -3416,10 +3416,14 @@ int cfg80211_wext_siwscan(struct net_device *dev, wiphy = &rdev->wiphy; /* Determine number of channels, needed to allocate creq */ - if (wreq && wreq->num_channels) + if (wreq && wreq->num_channels) { + /* Passed from userspace so should be checked */ + if (unlikely(wreq->num_channels > IW_MAX_FREQUENCIES)) + return -EINVAL; n_channels = wreq->num_channels; - else + } else { n_channels = ieee80211_get_num_supported_channels(wiphy); + } creq = kzalloc(sizeof(*creq) + sizeof(struct cfg80211_ssid) + n_channels * sizeof(void *), @@ -3493,8 +3497,10 @@ int cfg80211_wext_siwscan(struct net_device *dev, memcpy(creq->ssids[0].ssid, wreq->essid, wreq->essid_len); creq->ssids[0].ssid_len = wreq->essid_len; } - if (wreq->scan_type == IW_SCAN_TYPE_PASSIVE) + if (wreq->scan_type == IW_SCAN_TYPE_PASSIVE) { + creq->ssids = NULL; creq->n_ssids = 0; + } } for (i = 0; i < NUM_NL80211_BANDS; i++) diff --git a/security/Kconfig.hardening b/security/Kconfig.hardening index effbf5982be1..2cff851ebfd7 100644 --- a/security/Kconfig.hardening +++ b/security/Kconfig.hardening @@ -255,21 +255,6 @@ config INIT_ON_FREE_DEFAULT_ON touching "cold" memory areas. Most cases see 3-5% impact. Some synthetic workloads have measured as high as 8%. -config INIT_MLOCKED_ON_FREE_DEFAULT_ON - bool "Enable mlocked memory zeroing on free" - depends on !KMSAN - help - This config has the effect of setting "init_mlocked_on_free=1" - on the kernel command line. If it is enabled, all mlocked process - memory is zeroed when freed. This restriction to mlocked memory - improves performance over "init_on_free" but can still be used to - protect confidential data like key material from content exposures - to other processes, as well as live forensics and cold boot attacks. - Any non-mlocked memory is not cleared before it is reassigned. This - configuration can be overwritten by setting "init_mlocked_on_free=0" - on the command line. The "init_on_free" boot option takes - precedence over "init_mlocked_on_free". - config CC_HAS_ZERO_CALL_USED_REGS def_bool $(cc-option,-fzero-call-used-regs=used-gpr) # https://github.com/ClangBuiltLinux/linux/issues/1766 diff --git a/security/apparmor/audit.c b/security/apparmor/audit.c index 45beb1c5f747..6b5181c668b5 100644 --- a/security/apparmor/audit.c +++ b/security/apparmor/audit.c @@ -217,7 +217,7 @@ void aa_audit_rule_free(void *vrule) } } -int aa_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule) +int aa_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule, gfp_t gfp) { struct aa_audit_rule *rule; @@ -230,14 +230,14 @@ int aa_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule) return -EINVAL; } - rule = kzalloc(sizeof(struct aa_audit_rule), GFP_KERNEL); + rule = kzalloc(sizeof(struct aa_audit_rule), gfp); if (!rule) return -ENOMEM; /* Currently rules are treated as coming from the root ns */ rule->label = aa_label_parse(&root_ns->unconfined->label, rulestr, - GFP_KERNEL, true, false); + gfp, true, false); if (IS_ERR(rule->label)) { int err = PTR_ERR(rule->label); aa_audit_rule_free(rule); diff --git a/security/apparmor/include/audit.h b/security/apparmor/include/audit.h index acbb03b9bd25..0c8cc86b417b 100644 --- a/security/apparmor/include/audit.h +++ b/security/apparmor/include/audit.h @@ -200,7 +200,7 @@ static inline int complain_error(int error) } void aa_audit_rule_free(void *vrule); -int aa_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule); +int aa_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule, gfp_t gfp); int aa_audit_rule_known(struct audit_krule *rule); int aa_audit_rule_match(u32 sid, u32 field, u32 op, void *vrule); diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h index 3e568126cd48..c51e24d24d1e 100644 --- a/security/integrity/ima/ima.h +++ b/security/integrity/ima/ima.h @@ -546,7 +546,7 @@ static inline void ima_free_modsig(struct modsig *modsig) #else static inline int ima_filter_rule_init(u32 field, u32 op, char *rulestr, - void **lsmrule) + void **lsmrule, gfp_t gfp) { return -EINVAL; } diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c index c0556907c2e6..09da8e639239 100644 --- a/security/integrity/ima/ima_policy.c +++ b/security/integrity/ima/ima_policy.c @@ -401,7 +401,8 @@ static void ima_free_rule(struct ima_rule_entry *entry) kfree(entry); } -static struct ima_rule_entry *ima_lsm_copy_rule(struct ima_rule_entry *entry) +static struct ima_rule_entry *ima_lsm_copy_rule(struct ima_rule_entry *entry, + gfp_t gfp) { struct ima_rule_entry *nentry; int i; @@ -410,7 +411,7 @@ static struct ima_rule_entry *ima_lsm_copy_rule(struct ima_rule_entry *entry) * Immutable elements are copied over as pointers and data; only * lsm rules can change */ - nentry = kmemdup(entry, sizeof(*nentry), GFP_KERNEL); + nentry = kmemdup(entry, sizeof(*nentry), gfp); if (!nentry) return NULL; @@ -425,7 +426,8 @@ static struct ima_rule_entry *ima_lsm_copy_rule(struct ima_rule_entry *entry) ima_filter_rule_init(nentry->lsm[i].type, Audit_equal, nentry->lsm[i].args_p, - &nentry->lsm[i].rule); + &nentry->lsm[i].rule, + gfp); if (!nentry->lsm[i].rule) pr_warn("rule for LSM \'%s\' is undefined\n", nentry->lsm[i].args_p); @@ -438,7 +440,7 @@ static int ima_lsm_update_rule(struct ima_rule_entry *entry) int i; struct ima_rule_entry *nentry; - nentry = ima_lsm_copy_rule(entry); + nentry = ima_lsm_copy_rule(entry, GFP_KERNEL); if (!nentry) return -ENOMEM; @@ -664,7 +666,7 @@ retry: } if (rc == -ESTALE && !rule_reinitialized) { - lsm_rule = ima_lsm_copy_rule(rule); + lsm_rule = ima_lsm_copy_rule(rule, GFP_ATOMIC); if (lsm_rule) { rule_reinitialized = true; goto retry; @@ -1140,7 +1142,8 @@ static int ima_lsm_rule_init(struct ima_rule_entry *entry, entry->lsm[lsm_rule].type = audit_type; result = ima_filter_rule_init(entry->lsm[lsm_rule].type, Audit_equal, entry->lsm[lsm_rule].args_p, - &entry->lsm[lsm_rule].rule); + &entry->lsm[lsm_rule].rule, + GFP_KERNEL); if (!entry->lsm[lsm_rule].rule) { pr_warn("rule for LSM \'%s\' is undefined\n", entry->lsm[lsm_rule].args_p); diff --git a/security/security.c b/security/security.c index e5da848c50b9..e5ca08789f74 100644 --- a/security/security.c +++ b/security/security.c @@ -5332,15 +5332,17 @@ void security_key_post_create_or_update(struct key *keyring, struct key *key, * @op: rule operator * @rulestr: rule context * @lsmrule: receive buffer for audit rule struct + * @gfp: GFP flag used for kmalloc * * Allocate and initialize an LSM audit rule structure. * * Return: Return 0 if @lsmrule has been successfully set, -EINVAL in case of * an invalid rule. */ -int security_audit_rule_init(u32 field, u32 op, char *rulestr, void **lsmrule) +int security_audit_rule_init(u32 field, u32 op, char *rulestr, void **lsmrule, + gfp_t gfp) { - return call_int_hook(audit_rule_init, field, op, rulestr, lsmrule); + return call_int_hook(audit_rule_init, field, op, rulestr, lsmrule, gfp); } /** diff --git a/security/selinux/include/audit.h b/security/selinux/include/audit.h index 52aca71210b4..29c7d4c86f6d 100644 --- a/security/selinux/include/audit.h +++ b/security/selinux/include/audit.h @@ -21,12 +21,14 @@ * @op: the operator the rule uses * @rulestr: the text "target" of the rule * @rule: pointer to the new rule structure returned via this + * @gfp: GFP flag used for kmalloc * * Returns 0 if successful, -errno if not. On success, the rule structure * will be allocated internally. The caller must free this structure with * selinux_audit_rule_free() after use. */ -int selinux_audit_rule_init(u32 field, u32 op, char *rulestr, void **rule); +int selinux_audit_rule_init(u32 field, u32 op, char *rulestr, void **rule, + gfp_t gfp); /** * selinux_audit_rule_free - free an selinux audit rule structure. diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c index f20e1968b7f7..e33e55384b75 100644 --- a/security/selinux/ss/services.c +++ b/security/selinux/ss/services.c @@ -3507,7 +3507,8 @@ void selinux_audit_rule_free(void *vrule) } } -int selinux_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule) +int selinux_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule, + gfp_t gfp) { struct selinux_state *state = &selinux_state; struct selinux_policy *policy; @@ -3548,7 +3549,7 @@ int selinux_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule) return -EINVAL; } - tmprule = kzalloc(sizeof(struct selinux_audit_rule), GFP_KERNEL); + tmprule = kzalloc(sizeof(struct selinux_audit_rule), gfp); if (!tmprule) return -ENOMEM; context_init(&tmprule->au_ctxt); diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index 70ba2841e181..f5cbec1e6a92 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -4693,11 +4693,13 @@ static int smack_post_notification(const struct cred *w_cred, * @op: required testing operator (=, !=, >, <, ...) * @rulestr: smack label to be audited * @vrule: pointer to save our own audit rule representation + * @gfp: type of the memory for the allocation * * Prepare to audit cases where (@field @op @rulestr) is true. * The label to be audited is created if necessay. */ -static int smack_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule) +static int smack_audit_rule_init(u32 field, u32 op, char *rulestr, void **vrule, + gfp_t gfp) { struct smack_known *skp; char **rule = (char **)vrule; diff --git a/security/yama/yama_lsm.c b/security/yama/yama_lsm.c index b6684a074a59..39944a859ff6 100644 --- a/security/yama/yama_lsm.c +++ b/security/yama/yama_lsm.c @@ -111,6 +111,7 @@ static void report_access(const char *access, struct task_struct *target, /** * yama_relation_cleanup - remove invalid entries from the relation list + * @work: unused * */ static void yama_relation_cleanup(struct work_struct *work) diff --git a/sound/core/seq/seq_ump_convert.c b/sound/core/seq/seq_ump_convert.c index 171fb75267af..d81f776a4c3d 100644 --- a/sound/core/seq/seq_ump_convert.c +++ b/sound/core/seq/seq_ump_convert.c @@ -1075,6 +1075,8 @@ static const struct seq_ev_to_ump seq_ev_ump_encoders[] = { system_ev_to_ump_midi1, system_ev_to_ump_midi2 }, { SNDRV_SEQ_EVENT_SENSING, UMP_SYSTEM_STATUS_ACTIVE_SENSING, system_ev_to_ump_midi1, system_ev_to_ump_midi2 }, + { SNDRV_SEQ_EVENT_RESET, UMP_SYSTEM_STATUS_RESET, + system_ev_to_ump_midi1, system_ev_to_ump_midi2 }, }; static const struct seq_ev_to_ump *find_ump_encoder(int type) diff --git a/sound/hda/intel-dsp-config.c b/sound/hda/intel-dsp-config.c index 537863447358..478d2b50c571 100644 --- a/sound/hda/intel-dsp-config.c +++ b/sound/hda/intel-dsp-config.c @@ -18,7 +18,7 @@ static int dsp_driver; module_param(dsp_driver, int, 0444); -MODULE_PARM_DESC(dsp_driver, "Force the DSP driver for Intel DSP (0=auto, 1=legacy, 2=SST, 3=SOF)"); +MODULE_PARM_DESC(dsp_driver, "Force the DSP driver for Intel DSP (0=auto, 1=legacy, 2=SST, 3=SOF, 4=AVS)"); #define FLAG_SST BIT(0) #define FLAG_SOF BIT(1) diff --git a/sound/oss/dmasound/dmasound_core.c b/sound/oss/dmasound/dmasound_core.c index 164335d3c200..4b1baf4dd50e 100644 --- a/sound/oss/dmasound/dmasound_core.c +++ b/sound/oss/dmasound/dmasound_core.c @@ -204,6 +204,7 @@ module_param(numWriteBufs, int, 0); static unsigned int writeBufSize = DEFAULT_BUFF_SIZE ; /* in bytes */ module_param(writeBufSize, int, 0); +MODULE_DESCRIPTION("Atari/Amiga/Q40 core DMA sound driver"); MODULE_LICENSE("GPL"); static int sq_unit = -1; diff --git a/sound/pci/hda/Kconfig b/sound/pci/hda/Kconfig index 0da625533afc..e59df40a0007 100644 --- a/sound/pci/hda/Kconfig +++ b/sound/pci/hda/Kconfig @@ -162,6 +162,7 @@ config SND_HDA_SCODEC_CS35L56_I2C depends on ACPI || COMPILE_TEST depends on SND_SOC select FW_CS_DSP + select SERIAL_MULTI_INSTANTIATE select SND_HDA_GENERIC select SND_SOC_CS35L56_SHARED select SND_HDA_SCODEC_CS35L56 @@ -178,6 +179,7 @@ config SND_HDA_SCODEC_CS35L56_SPI depends on ACPI || COMPILE_TEST depends on SND_SOC select FW_CS_DSP + select SERIAL_MULTI_INSTANTIATE select SND_HDA_GENERIC select SND_SOC_CS35L56_SHARED select SND_HDA_SCODEC_CS35L56 diff --git a/sound/pci/hda/cs35l41_hda.c b/sound/pci/hda/cs35l41_hda.c index 6c49e5c6cd20..031703f010be 100644 --- a/sound/pci/hda/cs35l41_hda.c +++ b/sound/pci/hda/cs35l41_hda.c @@ -1495,7 +1495,7 @@ static void cs35l41_hda_unbind(struct device *dev, struct device *master, void * if (comps[cs35l41->index].dev == dev) { memset(&comps[cs35l41->index], 0, sizeof(*comps)); sleep_flags = lock_system_sleep(); - device_link_remove(&comps->codec->core.dev, cs35l41->dev); + device_link_remove(&cs35l41->codec->core.dev, cs35l41->dev); unlock_system_sleep(sleep_flags); } } @@ -2019,6 +2019,8 @@ void cs35l41_hda_remove(struct device *dev) { struct cs35l41_hda *cs35l41 = dev_get_drvdata(dev); + component_del(cs35l41->dev, &cs35l41_hda_comp_ops); + pm_runtime_get_sync(cs35l41->dev); pm_runtime_dont_use_autosuspend(cs35l41->dev); pm_runtime_disable(cs35l41->dev); @@ -2026,8 +2028,6 @@ void cs35l41_hda_remove(struct device *dev) if (cs35l41->halo_initialized) cs35l41_remove_dsp(cs35l41); - component_del(cs35l41->dev, &cs35l41_hda_comp_ops); - acpi_dev_put(cs35l41->dacpi); pm_runtime_put_noidle(cs35l41->dev); diff --git a/sound/pci/hda/cs35l41_hda_property.c b/sound/pci/hda/cs35l41_hda_property.c index 6a7a6d486916..51998d1c72ff 100644 --- a/sound/pci/hda/cs35l41_hda_property.c +++ b/sound/pci/hda/cs35l41_hda_property.c @@ -128,6 +128,10 @@ static const struct cs35l41_config cs35l41_config_table[] = { { "17AA38B5", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 0, 0, 0 }, { "17AA38B6", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 0, 0, 0 }, { "17AA38B7", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 0, 0, 0 }, + { "17AA38C7", 4, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, CS35L41_LEFT, CS35L41_RIGHT }, 0, 2, -1, 1000, 4500, 24 }, + { "17AA38C8", 4, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, CS35L41_LEFT, CS35L41_RIGHT }, 0, 2, -1, 1000, 4500, 24 }, + { "17AA38F9", 2, EXTERNAL, { CS35L41_RIGHT, CS35L41_LEFT, 0, 0 }, 0, 2, -1, 0, 0, 0 }, + { "17AA38FA", 2, EXTERNAL, { CS35L41_RIGHT, CS35L41_LEFT, 0, 0 }, 0, 2, -1, 0, 0, 0 }, {} }; @@ -529,6 +533,10 @@ static const struct cs35l41_prop_model cs35l41_prop_model_table[] = { { "CSC3551", "17AA38B5", generic_dsd_config }, { "CSC3551", "17AA38B6", generic_dsd_config }, { "CSC3551", "17AA38B7", generic_dsd_config }, + { "CSC3551", "17AA38C7", generic_dsd_config }, + { "CSC3551", "17AA38C8", generic_dsd_config }, + { "CSC3551", "17AA38F9", generic_dsd_config }, + { "CSC3551", "17AA38FA", generic_dsd_config }, {} }; diff --git a/sound/pci/hda/cs35l56_hda.c b/sound/pci/hda/cs35l56_hda.c index 11b0570ff56d..e134ede6c5aa 100644 --- a/sound/pci/hda/cs35l56_hda.c +++ b/sound/pci/hda/cs35l56_hda.c @@ -735,6 +735,8 @@ static void cs35l56_hda_unbind(struct device *dev, struct device *master, void * if (comps[cs35l56->index].dev == dev) memset(&comps[cs35l56->index], 0, sizeof(*comps)); + cs35l56->codec = NULL; + dev_dbg(cs35l56->base.dev, "Unbound\n"); } @@ -840,6 +842,9 @@ static int cs35l56_hda_system_resume(struct device *dev) cs35l56->suspended = false; + if (!cs35l56->codec) + return 0; + ret = cs35l56_is_fw_reload_needed(&cs35l56->base); dev_dbg(cs35l56->base.dev, "fw_reload_needed: %d\n", ret); if (ret > 0) { @@ -1072,12 +1077,12 @@ void cs35l56_hda_remove(struct device *dev) { struct cs35l56_hda *cs35l56 = dev_get_drvdata(dev); + component_del(cs35l56->base.dev, &cs35l56_hda_comp_ops); + pm_runtime_dont_use_autosuspend(cs35l56->base.dev); pm_runtime_get_sync(cs35l56->base.dev); pm_runtime_disable(cs35l56->base.dev); - component_del(cs35l56->base.dev, &cs35l56_hda_comp_ops); - cs_dsp_remove(&cs35l56->cs_dsp); kfree(cs35l56->system_name); diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index aa76d1c88589..e2dbcf8f5bcf 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -583,10 +583,14 @@ static void alc_shutup_pins(struct hda_codec *codec) switch (codec->core.vendor_id) { case 0x10ec0236: case 0x10ec0256: + case 0x10ec0257: case 0x19e58326: case 0x10ec0283: + case 0x10ec0285: case 0x10ec0286: + case 0x10ec0287: case 0x10ec0288: + case 0x10ec0295: case 0x10ec0298: alc_headset_mic_no_shutup(codec); break; @@ -7520,6 +7524,7 @@ enum { ALC285_FIXUP_ASUS_GU605_SPI_SPEAKER2_TO_DAC1, ALC287_FIXUP_LENOVO_THKPAD_WH_ALC1318, ALC256_FIXUP_CHROME_BOOK, + ALC287_FIXUP_LENOVO_14ARP8_LEGION_IAH7, }; /* A special fixup for Lenovo C940 and Yoga Duet 7; @@ -7559,6 +7564,21 @@ static void alc287_fixup_lenovo_14irp8_duetitl(struct hda_codec *codec, __snd_hda_apply_fixup(codec, id, action, 0); } +/* Similar to above the Lenovo Yoga Pro 7 14ARP8 PCI SSID matches the codec SSID of the + Legion Y9000X 2022 IAH7.*/ +static void alc287_fixup_lenovo_14arp8_legion_iah7(struct hda_codec *codec, + const struct hda_fixup *fix, + int action) +{ + int id; + + if (codec->core.subsystem_id == 0x17aa386e) + id = ALC287_FIXUP_CS35L41_I2C_2; /* Legion Y9000X 2022 IAH7 */ + else + id = ALC285_FIXUP_SPEAKER2_TO_DAC1; /* Yoga Pro 7 14ARP8 */ + __snd_hda_apply_fixup(codec, id, action, 0); +} + /* Another hilarious PCI SSID conflict with Lenovo Legion Pro 7 16ARX8H (with * TAS2781 codec) and Legion 7i 16IAX7 (with CS35L41 codec); * we apply a corresponding fixup depending on the codec SSID instead @@ -9658,6 +9678,10 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK, }, + [ALC287_FIXUP_LENOVO_14ARP8_LEGION_IAH7] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc287_fixup_lenovo_14arp8_legion_iah7, + }, [ALC287_FIXUP_YOGA9_14IMH9_BASS_SPK_PIN] = { .type = HDA_FIXUP_FUNC, .v.func = alc287_fixup_yoga9_14iap7_bass_spk_pin, @@ -10194,6 +10218,10 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8c70, "HP EliteBook 835 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c71, "HP EliteBook 845 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c72, "HP EliteBook 865 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8c7b, "HP ProBook 445 G11", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8c7c, "HP ProBook 445 G11", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8c7d, "HP ProBook 465 G11", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8c7e, "HP ProBook 465 G11", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8c89, "HP ProBook 460 G11", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c8a, "HP EliteBook 630", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c8c, "HP EliteBook 660", ALC236_FIXUP_HP_GPIO_LED), @@ -10502,7 +10530,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x3813, "Legion 7i 15IMHG05", ALC287_FIXUP_LEGION_15IMHG05_SPEAKERS), SND_PCI_QUIRK(0x17aa, 0x3818, "Lenovo C940 / Yoga Duet 7", ALC298_FIXUP_LENOVO_C940_DUET7), SND_PCI_QUIRK(0x17aa, 0x3819, "Lenovo 13s Gen2 ITL", ALC287_FIXUP_13S_GEN2_SPEAKERS), - SND_PCI_QUIRK(0x17aa, 0x3820, "Yoga Duet 7 13ITL6", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS), + SND_PCI_QUIRK(0x17aa, 0x3820, "IdeaPad 330-17IKB 81DM", ALC269_FIXUP_ASPIRE_HEADSET_MIC), SND_PCI_QUIRK(0x17aa, 0x3824, "Legion Y9000X 2020", ALC285_FIXUP_LEGION_Y9000X_SPEAKERS), SND_PCI_QUIRK(0x17aa, 0x3827, "Ideapad S740", ALC285_FIXUP_IDEAPAD_S740_COEF), SND_PCI_QUIRK(0x17aa, 0x3834, "Lenovo IdeaPad Slim 9i 14ITL5", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS), @@ -10516,7 +10544,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x3865, "Lenovo 13X", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x3866, "Lenovo 13X", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x3869, "Lenovo Yoga7 14IAL7", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN), - SND_PCI_QUIRK(0x17aa, 0x386e, "Legion Y9000X 2022 IAH7", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x17aa, 0x386e, "Legion Y9000X 2022 IAH7 / Yoga Pro 7 14ARP8", ALC287_FIXUP_LENOVO_14ARP8_LEGION_IAH7), SND_PCI_QUIRK(0x17aa, 0x386f, "Legion Pro 7/7i", ALC287_FIXUP_LENOVO_LEGION_7), SND_PCI_QUIRK(0x17aa, 0x3870, "Lenovo Yoga 7 14ARB7", ALC287_FIXUP_YOGA7_14ARB7_I2C), SND_PCI_QUIRK(0x17aa, 0x3877, "Lenovo Legion 7 Slim 16ARHA7", ALC287_FIXUP_CS35L41_I2C_2), @@ -10540,10 +10568,14 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x38be, "Yoga S980-14.5 proX YC Dual", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x38bf, "Yoga S980-14.5 proX LX Dual", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x38c3, "Y980 DUAL", ALC287_FIXUP_TAS2781_I2C), + SND_PCI_QUIRK(0x17aa, 0x38c7, "Thinkbook 13x Gen 4", ALC287_FIXUP_CS35L41_I2C_4), + SND_PCI_QUIRK(0x17aa, 0x38c8, "Thinkbook 13x Gen 4", ALC287_FIXUP_CS35L41_I2C_4), SND_PCI_QUIRK(0x17aa, 0x38cb, "Y790 YG DUAL", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x38cd, "Y790 VECO DUAL", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x38d2, "Lenovo Yoga 9 14IMH9", ALC287_FIXUP_YOGA9_14IMH9_BASS_SPK_PIN), SND_PCI_QUIRK(0x17aa, 0x38d7, "Lenovo Yoga 9 14IMH9", ALC287_FIXUP_YOGA9_14IMH9_BASS_SPK_PIN), + SND_PCI_QUIRK(0x17aa, 0x38f9, "Thinkbook 16P Gen5", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x17aa, 0x38fa, "Thinkbook 16P Gen5", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI), SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC), SND_PCI_QUIRK(0x17aa, 0x3978, "Lenovo B50-70", ALC269_FIXUP_DMIC_THINKPAD_ACPI), @@ -10581,6 +10613,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1b7d, 0xa831, "Ordissimo EVE2 ", ALC269VB_FIXUP_ORDISSIMO_EVE2), /* Also known as Malata PC-B1303 */ SND_PCI_QUIRK(0x1c06, 0x2013, "Lemote A1802", ALC269_FIXUP_LEMOTE_A1802), SND_PCI_QUIRK(0x1c06, 0x2015, "Lemote A190X", ALC269_FIXUP_LEMOTE_A190X), + SND_PCI_QUIRK(0x1c6c, 0x122a, "Positivo N14AP7", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x1c6c, 0x1251, "Positivo N14KP6-TG", ALC288_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1d05, 0x1132, "TongFang PHxTxX1", ALC256_FIXUP_SET_COEF_DEFAULTS), SND_PCI_QUIRK(0x1d05, 0x1096, "TongFang GMxMRxx", ALC269_FIXUP_NO_SHUTUP), @@ -10605,7 +10638,6 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x8086, 0x2081, "Intel NUC 10", ALC256_FIXUP_INTEL_NUC10), SND_PCI_QUIRK(0x8086, 0x3038, "Intel NUC 13", ALC295_FIXUP_CHROME_BOOK), SND_PCI_QUIRK(0xf111, 0x0001, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), - SND_PCI_QUIRK(0xf111, 0x0005, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0xf111, 0x0006, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), #if 0 diff --git a/sound/pci/hda/tas2781_hda_i2c.c b/sound/pci/hda/tas2781_hda_i2c.c index 75f7674c66ee..fdee6592c502 100644 --- a/sound/pci/hda/tas2781_hda_i2c.c +++ b/sound/pci/hda/tas2781_hda_i2c.c @@ -777,11 +777,11 @@ static void tas2781_hda_remove(struct device *dev) { struct tas2781_hda *tas_hda = dev_get_drvdata(dev); + component_del(tas_hda->dev, &tas2781_hda_comp_ops); + pm_runtime_get_sync(tas_hda->dev); pm_runtime_disable(tas_hda->dev); - component_del(tas_hda->dev, &tas2781_hda_comp_ops); - pm_runtime_put_noidle(tas_hda->dev); tasdevice_remove(tas_hda->priv); diff --git a/tools/hv/Makefile b/tools/hv/Makefile index bb52871da341..2e60e2c212cd 100644 --- a/tools/hv/Makefile +++ b/tools/hv/Makefile @@ -17,6 +17,7 @@ endif MAKEFLAGS += -r override CFLAGS += -O2 -Wall -g -D_GNU_SOURCE -I$(OUTPUT)include +override CFLAGS += -Wno-address-of-packed-member ALL_TARGETS := hv_kvp_daemon hv_vss_daemon ifneq ($(ARCH), aarch64) diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c index 6816ff064516..9dc3687bc406 100644 --- a/tools/testing/selftests/bpf/prog_tests/verifier.c +++ b/tools/testing/selftests/bpf/prog_tests/verifier.c @@ -53,6 +53,7 @@ #include "verifier_movsx.skel.h" #include "verifier_netfilter_ctx.skel.h" #include "verifier_netfilter_retcode.skel.h" +#include "verifier_or_jmp32_k.skel.h" #include "verifier_precision.skel.h" #include "verifier_prevent_map_lookup.skel.h" #include "verifier_raw_stack.skel.h" @@ -171,6 +172,7 @@ void test_verifier_meta_access(void) { RUN(verifier_meta_access); } void test_verifier_movsx(void) { RUN(verifier_movsx); } void test_verifier_netfilter_ctx(void) { RUN(verifier_netfilter_ctx); } void test_verifier_netfilter_retcode(void) { RUN(verifier_netfilter_retcode); } +void test_verifier_or_jmp32_k(void) { RUN(verifier_or_jmp32_k); } void test_verifier_precision(void) { RUN(verifier_precision); } void test_verifier_prevent_map_lookup(void) { RUN(verifier_prevent_map_lookup); } void test_verifier_raw_stack(void) { RUN(verifier_raw_stack); } diff --git a/tools/testing/selftests/bpf/progs/verifier_or_jmp32_k.c b/tools/testing/selftests/bpf/progs/verifier_or_jmp32_k.c new file mode 100644 index 000000000000..f37713a265ac --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_or_jmp32_k.c @@ -0,0 +1,41 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +SEC("socket") +__description("or_jmp32_k: bit ops + branch on unknown value") +__failure +__msg("R0 invalid mem access 'scalar'") +__naked void or_jmp32_k(void) +{ + asm volatile (" \ + r0 = 0xffffffff; \ + r0 /= 1; \ + r1 = 0; \ + w1 = -1; \ + w1 >>= 1; \ + w0 &= w1; \ + w0 |= 2; \ + if w0 != 0x7ffffffd goto l1; \ + r0 = 1; \ + exit; \ +l3: \ + r0 = 5; \ + *(u64*)(r0 - 8) = r0; \ + exit; \ +l2: \ + w0 -= 0xe; \ + if w0 == 1 goto l3; \ + r0 = 4; \ + exit; \ +l1: \ + w0 -= 0x7ffffff0; \ + if w0 s>= 0xe goto l2; \ + r0 = 3; \ + exit; \ +" ::: __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/drivers/net/virtio_net/config b/tools/testing/selftests/drivers/net/virtio_net/config index f35de0542b60..bcf7555eaffe 100644 --- a/tools/testing/selftests/drivers/net/virtio_net/config +++ b/tools/testing/selftests/drivers/net/virtio_net/config @@ -1,2 +1,8 @@ -CONFIG_VIRTIO_NET=y +CONFIG_BPF_SYSCALL=y +CONFIG_CGROUP_BPF=y +CONFIG_IPV6=y +CONFIG_IPV6_MULTIPLE_TABLES=y +CONFIG_NET_L3_MASTER_DEV=y +CONFIG_NET_VRF=m CONFIG_VIRTIO_DEBUG=y +CONFIG_VIRTIO_NET=y diff --git a/tools/testing/selftests/fchmodat2/Makefile b/tools/testing/selftests/fchmodat2/Makefile index 71ec34bf1501..4373cea79b79 100644 --- a/tools/testing/selftests/fchmodat2/Makefile +++ b/tools/testing/selftests/fchmodat2/Makefile @@ -1,6 +1,15 @@ # SPDX-License-Identifier: GPL-2.0-or-later -CFLAGS += -Wall -O2 -g -fsanitize=address -fsanitize=undefined -static-libasan $(KHDR_INCLUDES) +CFLAGS += -Wall -O2 -g -fsanitize=address -fsanitize=undefined $(KHDR_INCLUDES) + +# gcc requires -static-libasan in order to ensure that Address Sanitizer's +# library is the first one loaded. However, clang already statically links the +# Address Sanitizer if -fsanitize is specified. Therefore, simply omit +# -static-libasan for clang builds. +ifeq ($(LLVM),) + CFLAGS += -static-libasan +endif + TEST_GEN_PROGS := fchmodat2_test include ../lib.mk diff --git a/tools/testing/selftests/filesystems/statmount/statmount_test.c b/tools/testing/selftests/filesystems/statmount/statmount_test.c index e6d7c4f1c85b..e8c019d72cbf 100644 --- a/tools/testing/selftests/filesystems/statmount/statmount_test.c +++ b/tools/testing/selftests/filesystems/statmount/statmount_test.c @@ -125,8 +125,16 @@ static uint32_t old_root_id, old_parent_id; static void cleanup_namespace(void) { - fchdir(orig_root); - chroot("."); + int ret; + + ret = fchdir(orig_root); + if (ret == -1) + ksft_perror("fchdir to original root"); + + ret = chroot("."); + if (ret == -1) + ksft_perror("chroot to original root"); + umount2(root_mntpoint, MNT_DETACH); rmdir(root_mntpoint); } diff --git a/tools/testing/selftests/mm/map_fixed_noreplace.c b/tools/testing/selftests/mm/map_fixed_noreplace.c index b74813fdc951..d53de2486080 100644 --- a/tools/testing/selftests/mm/map_fixed_noreplace.c +++ b/tools/testing/selftests/mm/map_fixed_noreplace.c @@ -67,7 +67,8 @@ int main(void) dump_maps(); ksft_exit_fail_msg("Error: munmap failed!?\n"); } - ksft_test_result_pass("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); + ksft_print_msg("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); + ksft_test_result_pass("mmap() 5*PAGE_SIZE at base\n"); addr = base_addr + page_size; size = 3 * page_size; @@ -76,7 +77,8 @@ int main(void) dump_maps(); ksft_exit_fail_msg("Error: first mmap() failed unexpectedly\n"); } - ksft_test_result_pass("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); + ksft_print_msg("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); + ksft_test_result_pass("mmap() 3*PAGE_SIZE at base+PAGE_SIZE\n"); /* * Exact same mapping again: @@ -93,7 +95,8 @@ int main(void) dump_maps(); ksft_exit_fail_msg("Error:1: mmap() succeeded when it shouldn't have\n"); } - ksft_test_result_pass("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); + ksft_print_msg("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); + ksft_test_result_pass("mmap() 5*PAGE_SIZE at base\n"); /* * Second mapping contained within first: @@ -111,7 +114,8 @@ int main(void) dump_maps(); ksft_exit_fail_msg("Error:2: mmap() succeeded when it shouldn't have\n"); } - ksft_test_result_pass("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); + ksft_print_msg("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); + ksft_test_result_pass("mmap() 2*PAGE_SIZE at base+PAGE_SIZE\n"); /* * Overlap end of existing mapping: @@ -128,7 +132,8 @@ int main(void) dump_maps(); ksft_exit_fail_msg("Error:3: mmap() succeeded when it shouldn't have\n"); } - ksft_test_result_pass("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); + ksft_print_msg("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); + ksft_test_result_pass("mmap() 2*PAGE_SIZE at base+(3*PAGE_SIZE)\n"); /* * Overlap start of existing mapping: @@ -145,7 +150,8 @@ int main(void) dump_maps(); ksft_exit_fail_msg("Error:4: mmap() succeeded when it shouldn't have\n"); } - ksft_test_result_pass("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); + ksft_print_msg("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); + ksft_test_result_pass("mmap() 2*PAGE_SIZE bytes at base\n"); /* * Adjacent to start of existing mapping: @@ -162,7 +168,8 @@ int main(void) dump_maps(); ksft_exit_fail_msg("Error:5: mmap() failed when it shouldn't have\n"); } - ksft_test_result_pass("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); + ksft_print_msg("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); + ksft_test_result_pass("mmap() PAGE_SIZE at base\n"); /* * Adjacent to end of existing mapping: @@ -179,7 +186,8 @@ int main(void) dump_maps(); ksft_exit_fail_msg("Error:6: mmap() failed when it shouldn't have\n"); } - ksft_test_result_pass("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); + ksft_print_msg("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); + ksft_test_result_pass("mmap() PAGE_SIZE at base+(4*PAGE_SIZE)\n"); addr = base_addr; size = 5 * page_size; diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 6da63d1831c1..bc3925200637 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -43,6 +43,8 @@ TEST_PROGS += srv6_hl2encap_red_l2vpn_test.sh TEST_PROGS += srv6_end_next_csid_l3vpn_test.sh TEST_PROGS += srv6_end_x_next_csid_l3vpn_test.sh TEST_PROGS += srv6_end_flavors_test.sh +TEST_PROGS += srv6_end_dx4_netfilter_test.sh +TEST_PROGS += srv6_end_dx6_netfilter_test.sh TEST_PROGS += vrf_strict_mode_test.sh TEST_PROGS += arp_ndisc_evict_nocarrier.sh TEST_PROGS += ndisc_unsolicited_na_test.sh diff --git a/tools/testing/selftests/net/amt.sh b/tools/testing/selftests/net/amt.sh index 7e7ed6c558da..d458b45c775b 100755 --- a/tools/testing/selftests/net/amt.sh +++ b/tools/testing/selftests/net/amt.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # SPDX-License-Identifier: GPL-2.0 # Author: Taehee Yoo <[email protected]> diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index 04de7a6ba6f3..d4891f7a2bfa 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -101,3 +101,5 @@ CONFIG_NETFILTER_XT_MATCH_POLICY=m CONFIG_CRYPTO_ARIA=y CONFIG_XFRM_INTERFACE=m CONFIG_XFRM_USER=m +CONFIG_IP_NF_MATCH_RPFILTER=m +CONFIG_IP6_NF_MATCH_RPFILTER=m diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh index 9e2981f2d7f5..9cb05978269d 100755 --- a/tools/testing/selftests/net/mptcp/userspace_pm.sh +++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh @@ -160,10 +160,12 @@ make_connection() local is_v6=$1 local app_port=$app4_port local connect_addr="10.0.1.1" + local client_addr="10.0.1.2" local listen_addr="0.0.0.0" if [ "$is_v6" = "v6" ] then connect_addr="dead:beef:1::1" + client_addr="dead:beef:1::2" listen_addr="::" app_port=$app6_port else @@ -206,6 +208,7 @@ make_connection() [ "$server_serverside" = 1 ] then test_pass + print_title "Connection info: ${client_addr}:${client_port} -> ${connect_addr}:${app_port}" else test_fail "Expected tokens (c:${client_token} - s:${server_token}) and server (c:${client_serverside} - s:${server_serverside})" mptcp_lib_result_print_all_tap @@ -297,7 +300,7 @@ test_announce() ip netns exec "$ns2"\ ./pm_nl_ctl ann 10.0.2.2 token "$client4_token" id $client_addr_id dev\ ns2eth1 - print_test "ADD_ADDR id:${client_addr_id} 10.0.2.2 (ns2) => ns1, reuse port" + print_test "ADD_ADDR id:client 10.0.2.2 (ns2) => ns1, reuse port" sleep 0.5 verify_announce_event $server_evts $ANNOUNCED $server4_token "10.0.2.2" $client_addr_id \ "$client4_port" @@ -306,7 +309,7 @@ test_announce() :>"$server_evts" ip netns exec "$ns2" ./pm_nl_ctl ann\ dead:beef:2::2 token "$client6_token" id $client_addr_id dev ns2eth1 - print_test "ADD_ADDR6 id:${client_addr_id} dead:beef:2::2 (ns2) => ns1, reuse port" + print_test "ADD_ADDR6 id:client dead:beef:2::2 (ns2) => ns1, reuse port" sleep 0.5 verify_announce_event "$server_evts" "$ANNOUNCED" "$server6_token" "dead:beef:2::2"\ "$client_addr_id" "$client6_port" "v6" @@ -316,7 +319,7 @@ test_announce() client_addr_id=$((client_addr_id+1)) ip netns exec "$ns2" ./pm_nl_ctl ann 10.0.2.2 token "$client4_token" id\ $client_addr_id dev ns2eth1 port $new4_port - print_test "ADD_ADDR id:${client_addr_id} 10.0.2.2 (ns2) => ns1, new port" + print_test "ADD_ADDR id:client+1 10.0.2.2 (ns2) => ns1, new port" sleep 0.5 verify_announce_event "$server_evts" "$ANNOUNCED" "$server4_token" "10.0.2.2"\ "$client_addr_id" "$new4_port" @@ -327,7 +330,7 @@ test_announce() # ADD_ADDR from the server to client machine reusing the subflow port ip netns exec "$ns1" ./pm_nl_ctl ann 10.0.2.1 token "$server4_token" id\ $server_addr_id dev ns1eth2 - print_test "ADD_ADDR id:${server_addr_id} 10.0.2.1 (ns1) => ns2, reuse port" + print_test "ADD_ADDR id:server 10.0.2.1 (ns1) => ns2, reuse port" sleep 0.5 verify_announce_event "$client_evts" "$ANNOUNCED" "$client4_token" "10.0.2.1"\ "$server_addr_id" "$app4_port" @@ -336,7 +339,7 @@ test_announce() :>"$client_evts" ip netns exec "$ns1" ./pm_nl_ctl ann dead:beef:2::1 token "$server6_token" id\ $server_addr_id dev ns1eth2 - print_test "ADD_ADDR6 id:${server_addr_id} dead:beef:2::1 (ns1) => ns2, reuse port" + print_test "ADD_ADDR6 id:server dead:beef:2::1 (ns1) => ns2, reuse port" sleep 0.5 verify_announce_event "$client_evts" "$ANNOUNCED" "$client6_token" "dead:beef:2::1"\ "$server_addr_id" "$app6_port" "v6" @@ -346,7 +349,7 @@ test_announce() server_addr_id=$((server_addr_id+1)) ip netns exec "$ns1" ./pm_nl_ctl ann 10.0.2.1 token "$server4_token" id\ $server_addr_id dev ns1eth2 port $new4_port - print_test "ADD_ADDR id:${server_addr_id} 10.0.2.1 (ns1) => ns2, new port" + print_test "ADD_ADDR id:server+1 10.0.2.1 (ns1) => ns2, new port" sleep 0.5 verify_announce_event "$client_evts" "$ANNOUNCED" "$client4_token" "10.0.2.1"\ "$server_addr_id" "$new4_port" @@ -380,7 +383,7 @@ test_remove() local invalid_token=$(( client4_token - 1 )) ip netns exec "$ns2" ./pm_nl_ctl rem token $invalid_token id\ $client_addr_id > /dev/null 2>&1 - print_test "RM_ADDR id:${client_addr_id} ns2 => ns1, invalid token" + print_test "RM_ADDR id:client ns2 => ns1, invalid token" local type type=$(mptcp_lib_evts_get_info type "$server_evts") if [ "$type" = "" ] @@ -394,7 +397,7 @@ test_remove() local invalid_id=$(( client_addr_id + 1 )) ip netns exec "$ns2" ./pm_nl_ctl rem token "$client4_token" id\ $invalid_id > /dev/null 2>&1 - print_test "RM_ADDR id:${invalid_id} ns2 => ns1, invalid id" + print_test "RM_ADDR id:client+1 ns2 => ns1, invalid id" type=$(mptcp_lib_evts_get_info type "$server_evts") if [ "$type" = "" ] then @@ -407,7 +410,7 @@ test_remove() :>"$server_evts" ip netns exec "$ns2" ./pm_nl_ctl rem token "$client4_token" id\ $client_addr_id - print_test "RM_ADDR id:${client_addr_id} ns2 => ns1" + print_test "RM_ADDR id:client ns2 => ns1" sleep 0.5 verify_remove_event "$server_evts" "$REMOVED" "$server4_token" "$client_addr_id" @@ -416,7 +419,7 @@ test_remove() client_addr_id=$(( client_addr_id - 1 )) ip netns exec "$ns2" ./pm_nl_ctl rem token "$client4_token" id\ $client_addr_id - print_test "RM_ADDR id:${client_addr_id} ns2 => ns1" + print_test "RM_ADDR id:client-1 ns2 => ns1" sleep 0.5 verify_remove_event "$server_evts" "$REMOVED" "$server4_token" "$client_addr_id" @@ -424,7 +427,7 @@ test_remove() :>"$server_evts" ip netns exec "$ns2" ./pm_nl_ctl rem token "$client6_token" id\ $client_addr_id - print_test "RM_ADDR6 id:${client_addr_id} ns2 => ns1" + print_test "RM_ADDR6 id:client-1 ns2 => ns1" sleep 0.5 verify_remove_event "$server_evts" "$REMOVED" "$server6_token" "$client_addr_id" @@ -434,7 +437,7 @@ test_remove() # RM_ADDR from the server to client machine ip netns exec "$ns1" ./pm_nl_ctl rem token "$server4_token" id\ $server_addr_id - print_test "RM_ADDR id:${server_addr_id} ns1 => ns2" + print_test "RM_ADDR id:server ns1 => ns2" sleep 0.5 verify_remove_event "$client_evts" "$REMOVED" "$client4_token" "$server_addr_id" @@ -443,7 +446,7 @@ test_remove() server_addr_id=$(( server_addr_id - 1 )) ip netns exec "$ns1" ./pm_nl_ctl rem token "$server4_token" id\ $server_addr_id - print_test "RM_ADDR id:${server_addr_id} ns1 => ns2" + print_test "RM_ADDR id:server-1 ns1 => ns2" sleep 0.5 verify_remove_event "$client_evts" "$REMOVED" "$client4_token" "$server_addr_id" @@ -451,7 +454,7 @@ test_remove() :>"$client_evts" ip netns exec "$ns1" ./pm_nl_ctl rem token "$server6_token" id\ $server_addr_id - print_test "RM_ADDR6 id:${server_addr_id} ns1 => ns2" + print_test "RM_ADDR6 id:server-1 ns1 => ns2" sleep 0.5 verify_remove_event "$client_evts" "$REMOVED" "$client6_token" "$server_addr_id" } @@ -479,8 +482,14 @@ verify_subflow_events() local locid local remid local info + local e_dport_txt - info="${e_saddr} (${e_from}) => ${e_daddr}:${e_dport} (${e_to})" + # only display the fixed ports + if [ "${e_dport}" -ge "${app4_port}" ] && [ "${e_dport}" -le "${app6_port}" ]; then + e_dport_txt=":${e_dport}" + fi + + info="${e_saddr} (${e_from}) => ${e_daddr}${e_dport_txt} (${e_to})" if [ "$e_type" = "$SUB_ESTABLISHED" ] then @@ -766,7 +775,7 @@ test_subflows_v4_v6_mix() :>"$client_evts" ip netns exec "$ns1" ./pm_nl_ctl ann 10.0.2.1 token "$server6_token" id\ $server_addr_id dev ns1eth2 - print_test "ADD_ADDR4 id:${server_addr_id} 10.0.2.1 (ns1) => ns2, reuse port" + print_test "ADD_ADDR4 id:server 10.0.2.1 (ns1) => ns2, reuse port" sleep 0.5 verify_announce_event "$client_evts" "$ANNOUNCED" "$client6_token" "10.0.2.1"\ "$server_addr_id" "$app6_port" @@ -861,7 +870,7 @@ test_listener() local listener_pid=$! sleep 0.5 - print_test "CREATE_LISTENER 10.0.2.2:$client4_port" + print_test "CREATE_LISTENER 10.0.2.2 (client port)" verify_listener_events $client_evts $LISTENER_CREATED $AF_INET 10.0.2.2 $client4_port # ADD_ADDR from client to server machine reusing the subflow port @@ -878,13 +887,14 @@ test_listener() mptcp_lib_kill_wait $listener_pid sleep 0.5 - print_test "CLOSE_LISTENER 10.0.2.2:$client4_port" + print_test "CLOSE_LISTENER 10.0.2.2 (client port)" verify_listener_events $client_evts $LISTENER_CLOSED $AF_INET 10.0.2.2 $client4_port } print_title "Make connections" make_connection make_connection "v6" +print_title "Will be using address IDs ${client_addr_id} (client) and ${server_addr_id} (server)" test_announce test_remove diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh index 5cae53543849..15bca0708717 100755 --- a/tools/testing/selftests/net/openvswitch/openvswitch.sh +++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # SPDX-License-Identifier: GPL-2.0 # # OVS kernel module self tests diff --git a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py index 1dd057afd3fb..9f8dec2f6539 100644 --- a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py +++ b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py @@ -531,7 +531,7 @@ class ovsactions(nla): for flat_act in parse_flat_map: if parse_starts_block(actstr, flat_act[0], False): actstr = actstr[len(flat_act[0]):] - self["attrs"].append([flat_act[1]]) + self["attrs"].append([flat_act[1], True]) actstr = actstr[strspn(actstr, ", ") :] parsed = True diff --git a/tools/testing/selftests/net/srv6_end_dx4_netfilter_test.sh b/tools/testing/selftests/net/srv6_end_dx4_netfilter_test.sh new file mode 100755 index 000000000000..e23210aa547f --- /dev/null +++ b/tools/testing/selftests/net/srv6_end_dx4_netfilter_test.sh @@ -0,0 +1,335 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# author: Jianguo Wu <[email protected]> +# +# Mostly copied from tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh. +# +# This script is designed for testing the support of netfilter hooks for +# SRv6 End.DX4 behavior. +# +# Hereafter a network diagram is shown, where one tenants (named 100) offer +# IPv4 L3 VPN services allowing hosts to communicate with each other across +# an IPv6 network. +# +# Routers rt-1 and rt-2 implement IPv4 L3 VPN services leveraging the SRv6 +# architecture. The key components for such VPNs are: a) SRv6 Encap behavior, +# b) SRv6 End.DX4 behavior. +# +# To explain how an IPv4 L3 VPN based on SRv6 works, let us briefly consider an +# example where, within the same domain of tenant 100, the host hs-1 pings +# the host hs-2. +# +# First of all, L2 reachability of the host hs-2 is taken into account by +# the router rt-1 which acts as an arp proxy. +# +# When the host hs-1 sends an IPv4 packet destined to hs-2, the router rt-1 +# receives the packet on the internal veth-t100 interface, rt-1 contains the +# SRv6 Encap route for encapsulating the IPv4 packet in a IPv6 plus the Segment +# Routing Header (SRH) packet. This packet is sent through the (IPv6) core +# network up to the router rt-2 that receives it on veth0 interface. +# +# The rt-2 router uses the 'localsid' routing table to process incoming +# IPv6+SRH packets which belong to the VPN of the tenant 100. For each of these +# packets, the SRv6 End.DX4 behavior removes the outer IPv6+SRH headers and +# routs the packet to the specified nexthop. Afterwards, the packet is sent to +# the host hs-2 through the veth-t100 interface. +# +# The ping response follows the same processing but this time the role of rt-1 +# and rt-2 are swapped. +# +# And when net.netfilter.nf_hooks_lwtunnel is set to 1 in rt-1 or rt-2, and a +# rpfilter iptables rule is added, SRv6 packets will go through netfilter PREROUTING +# hooks. +# +# +# +-------------------+ +-------------------+ +# | | | | +# | hs-1 netns | | hs-2 netns | +# | | | | +# | +-------------+ | | +-------------+ | +# | | veth0 | | | | veth0 | | +# | | 10.0.0.1/24 | | | | 10.0.0.2/24 | | +# | +-------------+ | | +-------------+ | +# | . | | . | +# +-------------------+ +-------------------+ +# . . +# . . +# . . +# +-----------------------------------+ +-----------------------------------+ +# | . | | . | +# | +---------------+ | | +---------------- | +# | | veth-t100 | | | | veth-t100 | | +# | | 10.0.0.11/24 | +----------+ | | +----------+ | 10.0.0.22/24 | | +# | +-------+-------+ | route | | | | route | +-------+-------- | +# | | table | | | | table | | +# | +----------+ | | +----------+ | +# | +--------------+ | | +--------------+ | +# | | veth0 | | | | veth0 | | +# | | 2001:11::1/64 |.|...|.| 2001:11::2/64 | | +# | +--------------+ | | +--------------+ | +# | | | | +# | rt-1 netns | | rt-2 netns | +# | | | | +# +-----------------------------------+ +-----------------------------------+ +# +# ~~~~~~~~~~~~~~~~~~~~~~~~~ +# | Network configuration | +# ~~~~~~~~~~~~~~~~~~~~~~~~~ +# +# rt-1: localsid table +# +----------------------------------------------------------------+ +# |SID |Action | +# +----------------------------------------------------------------+ +# |fc00:21:100::6004|apply SRv6 End.DX4 nh4 10.0.0.1 dev veth-t100 | +# +----------------------------------------------------------------+ +# +# rt-1: route table +# +---------------------------------------------------+ +# |host |Action | +# +---------------------------------------------------+ +# |10.0.0.2 |apply seg6 encap segs fc00:12:100::6004| +# +---------------------------------------------------+ +# |10.0.0.0/24|forward to dev veth_t100 | +# +---------------------------------------------------+ +# +# +# rt-2: localsid table +# +---------------------------------------------------------------+ +# |SID |Action | +# +---------------------------------------------------------------+ +# |fc00:12:100::6004|apply SRv6 End.DX4 nh4 10.0.0.2 dev veth-t100| +# +---------------------------------------------------------------+ +# +# rt-2: route table +# +---------------------------------------------------+ +# |host |Action | +# +---------------------------------------------------+ +# |10.0.0.1 |apply seg6 encap segs fc00:21:100::6004| +# +---------------------------------------------------+ +# |10.0.0.0/24|forward to dev veth_t100 | +# +---------------------------------------------------+ +# + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +readonly IPv6_RT_NETWORK=2001:11 +readonly IPv4_HS_NETWORK=10.0.0 +readonly SID_LOCATOR=fc00 + +PING_TIMEOUT_SEC=4 + +ret=0 + +PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no} + +log_test() +{ + local rc=$1 + local expected=$2 + local msg="$3" + + if [ ${rc} -eq ${expected} ]; then + nsuccess=$((nsuccess+1)) + printf "\n TEST: %-60s [ OK ]\n" "${msg}" + else + ret=1 + nfail=$((nfail+1)) + printf "\n TEST: %-60s [FAIL]\n" "${msg}" + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi + fi +} + +print_log_test_results() +{ + if [ "$TESTS" != "none" ]; then + printf "\nTests passed: %3d\n" ${nsuccess} + printf "Tests failed: %3d\n" ${nfail} + fi +} + +log_section() +{ + echo + echo "################################################################################" + echo "TEST SECTION: $*" + echo "################################################################################" +} + +cleanup() +{ + ip link del veth-rt-1 2>/dev/null || true + ip link del veth-rt-2 2>/dev/null || true + + # destroy routers rt-* and hosts hs-* + for ns in $(ip netns show | grep -E 'rt-*|hs-*'); do + ip netns del ${ns} || true + done +} + +# Setup the basic networking for the routers +setup_rt_networking() +{ + local rt=$1 + local nsname=rt-${rt} + + ip netns add ${nsname} + + ip netns exec ${nsname} sysctl -wq net.ipv6.conf.all.accept_dad=0 + ip netns exec ${nsname} sysctl -wq net.ipv6.conf.default.accept_dad=0 + + ip link set veth-rt-${rt} netns ${nsname} + ip -netns ${nsname} link set veth-rt-${rt} name veth0 + + ip -netns ${nsname} addr add ${IPv6_RT_NETWORK}::${rt}/64 dev veth0 nodad + ip -netns ${nsname} link set veth0 up + ip -netns ${nsname} link set lo up + + ip netns exec ${nsname} sysctl -wq net.ipv4.ip_forward=1 + ip netns exec ${nsname} sysctl -wq net.ipv6.conf.all.forwarding=1 +} + +setup_rt_netfilter() +{ + local rt=$1 + local nsname=rt-${rt} + + ip netns exec ${nsname} sysctl -wq net.netfilter.nf_hooks_lwtunnel=1 + ip netns exec ${nsname} iptables -t raw -A PREROUTING -m rpfilter --invert -j DROP +} + +setup_hs() +{ + local hs=$1 + local rt=$2 + local tid=$3 + local hsname=hs-${hs} + local rtname=rt-${rt} + local rtveth=veth-t${tid} + + # set the networking for the host + ip netns add ${hsname} + + ip -netns ${hsname} link add veth0 type veth peer name ${rtveth} + ip -netns ${hsname} link set ${rtveth} netns ${rtname} + ip -netns ${hsname} addr add ${IPv4_HS_NETWORK}.${hs}/24 dev veth0 + ip -netns ${hsname} link set veth0 up + ip -netns ${hsname} link set lo up + + ip -netns ${rtname} addr add ${IPv4_HS_NETWORK}.${rt}${hs}/24 dev ${rtveth} + ip -netns ${rtname} link set ${rtveth} up + + ip netns exec ${rtname} sysctl -wq net.ipv4.conf.${rtveth}.proxy_arp=1 +} + +setup_vpn_config() +{ + local hssrc=$1 + local rtsrc=$2 + local hsdst=$3 + local rtdst=$4 + local tid=$5 + + local hssrc_name=hs-t${tid}-${hssrc} + local hsdst_name=hs-t${tid}-${hsdst} + local rtsrc_name=rt-${rtsrc} + local rtdst_name=rt-${rtdst} + local vpn_sid=${SID_LOCATOR}:${hssrc}${hsdst}:${tid}::6004 + + # set the encap route for encapsulating packets which arrive from the + # host hssrc and destined to the access router rtsrc. + ip -netns ${rtsrc_name} -4 route add ${IPv4_HS_NETWORK}.${hsdst}/32 \ + encap seg6 mode encap segs ${vpn_sid} dev veth0 + ip -netns ${rtsrc_name} -6 route add ${vpn_sid}/128 \ + via 2001:11::${rtdst} dev veth0 + + # set the decap route for decapsulating packets which arrive from + # the rtdst router and destined to the hsdst host. + ip -netns ${rtdst_name} -6 route add ${vpn_sid}/128 \ + encap seg6local action End.DX4 nh4 ${IPv4_HS_NETWORK}.${hsdst} dev veth-t${tid} +} + +setup() +{ + ip link add veth-rt-1 type veth peer name veth-rt-2 + # setup the networking for router rt-1 and router rt-2 + setup_rt_networking 1 + setup_rt_networking 2 + + # setup two hosts for the tenant 100. + # - host hs-1 is directly connected to the router rt-1; + # - host hs-2 is directly connected to the router rt-2. + setup_hs 1 1 100 + setup_hs 2 2 100 + + # setup the IPv4 L3 VPN which connects the host hs-1 and host hs-2. + setup_vpn_config 1 1 2 2 100 #args: src_host src_router dst_host dst_router tenant + setup_vpn_config 2 2 1 1 100 +} + +check_hs_connectivity() +{ + local hssrc=$1 + local hsdst=$2 + local tid=$3 + + ip netns exec hs-${hssrc} ping -c 1 -W ${PING_TIMEOUT_SEC} \ + ${IPv4_HS_NETWORK}.${hsdst} >/dev/null 2>&1 +} + +check_and_log_hs_connectivity() +{ + local hssrc=$1 + local hsdst=$2 + local tid=$3 + + check_hs_connectivity ${hssrc} ${hsdst} ${tid} + log_test $? 0 "Hosts connectivity: hs-${hssrc} -> hs-${hsdst} (tenant ${tid})" +} + +host_tests() +{ + log_section "SRv6 VPN connectivity test among hosts in the same tenant" + + check_and_log_hs_connectivity 1 2 100 + check_and_log_hs_connectivity 2 1 100 +} + +router_netfilter_tests() +{ + log_section "SRv6 VPN connectivity test with netfilter enabled in routers" + setup_rt_netfilter 1 + setup_rt_netfilter 2 + + check_and_log_hs_connectivity 1 2 100 + check_and_log_hs_connectivity 2 1 100 +} + +if [ "$(id -u)" -ne 0 ];then + echo "SKIP: Need root privileges" + exit $ksft_skip +fi + +if [ ! -x "$(command -v ip)" ]; then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +cleanup &>/dev/null + +setup + +host_tests +router_netfilter_tests + +print_log_test_results + +cleanup &>/dev/null + +exit ${ret} diff --git a/tools/testing/selftests/net/srv6_end_dx6_netfilter_test.sh b/tools/testing/selftests/net/srv6_end_dx6_netfilter_test.sh new file mode 100755 index 000000000000..9e69a2ed5bc3 --- /dev/null +++ b/tools/testing/selftests/net/srv6_end_dx6_netfilter_test.sh @@ -0,0 +1,340 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# author: Jianguo Wu <[email protected]> +# +# Mostly copied from tools/testing/selftests/net/srv6_end_dt6_l3vpn_test.sh. +# +# This script is designed for testing the support of netfilter hooks for +# SRv6 End.DX4 behavior. +# +# Hereafter a network diagram is shown, where one tenants (named 100) offer +# IPv6 L3 VPN services allowing hosts to communicate with each other across +# an IPv6 network. +# +# Routers rt-1 and rt-2 implement IPv6 L3 VPN services leveraging the SRv6 +# architecture. The key components for such VPNs are: a) SRv6 Encap behavior, +# b) SRv6 End.DX4 behavior. +# +# To explain how an IPv6 L3 VPN based on SRv6 works, let us briefly consider an +# example where, within the same domain of tenant 100, the host hs-1 pings +# the host hs-2. +# +# First of all, L2 reachability of the host hs-2 is taken into account by +# the router rt-1 which acts as an arp proxy. +# +# When the host hs-1 sends an IPv6 packet destined to hs-2, the router rt-1 +# receives the packet on the internal veth-t100 interface, rt-1 contains the +# SRv6 Encap route for encapsulating the IPv6 packet in a IPv6 plus the Segment +# Routing Header (SRH) packet. This packet is sent through the (IPv6) core +# network up to the router rt-2 that receives it on veth0 interface. +# +# The rt-2 router uses the 'localsid' routing table to process incoming +# IPv6+SRH packets which belong to the VPN of the tenant 100. For each of these +# packets, the SRv6 End.DX4 behavior removes the outer IPv6+SRH headers and +# routs the packet to the specified nexthop. Afterwards, the packet is sent to +# the host hs-2 through the veth-t100 interface. +# +# The ping response follows the same processing but this time the role of rt-1 +# and rt-2 are swapped. +# +# And when net.netfilter.nf_hooks_lwtunnel is set to 1 in rt-1 or rt-2, and a +# rpfilter iptables rule is added, SRv6 packets will go through netfilter PREROUTING +# hooks. +# +# +# +-------------------+ +-------------------+ +# | | | | +# | hs-1 netns | | hs-2 netns | +# | | | | +# | +-------------+ | | +-------------+ | +# | | veth0 | | | | veth0 | | +# | | cafe::1/64 | | | | cafe::2/64 | | +# | +-------------+ | | +-------------+ | +# | . | | . | +# +-------------------+ +-------------------+ +# . . +# . . +# . . +# +-----------------------------------+ +-----------------------------------+ +# | . | | . | +# | +---------------+ | | +---------------- | +# | | veth-t100 | | | | veth-t100 | | +# | | cafe::11/64 | +----------+ | | +----------+ | cafe::22/64 | | +# | +-------+-------+ | route | | | | route | +-------+-------- | +# | | table | | | | table | | +# | +----------+ | | +----------+ | +# | +--------------+ | | +--------------+ | +# | | veth0 | | | | veth0 | | +# | | 2001:11::1/64 |.|...|.| 2001:11::2/64 | | +# | +--------------+ | | +--------------+ | +# | | | | +# | rt-1 netns | | rt-2 netns | +# | | | | +# +-----------------------------------+ +-----------------------------------+ +# +# ~~~~~~~~~~~~~~~~~~~~~~~~~ +# | Network configuration | +# ~~~~~~~~~~~~~~~~~~~~~~~~~ +# +# rt-1: localsid table +# +----------------------------------------------------------------+ +# |SID |Action | +# +----------------------------------------------------------------+ +# |fc00:21:100::6004|apply SRv6 End.DX6 nh6 cafe::1 dev veth-t100 | +# +----------------------------------------------------------------+ +# +# rt-1: route table +# +---------------------------------------------------+ +# |host |Action | +# +---------------------------------------------------+ +# |cafe::2 |apply seg6 encap segs fc00:12:100::6004| +# +---------------------------------------------------+ +# |cafe::/64 |forward to dev veth_t100 | +# +---------------------------------------------------+ +# +# +# rt-2: localsid table +# +---------------------------------------------------------------+ +# |SID |Action | +# +---------------------------------------------------------------+ +# |fc00:12:100::6004|apply SRv6 End.DX6 nh6 cafe::2 dev veth-t100 | +# +---------------------------------------------------------------+ +# +# rt-2: route table +# +---------------------------------------------------+ +# |host |Action | +# +---------------------------------------------------+ +# |cafe::1 |apply seg6 encap segs fc00:21:100::6004| +# +---------------------------------------------------+ +# |cafe::/64 |forward to dev veth_t100 | +# +---------------------------------------------------+ +# + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +readonly IPv6_RT_NETWORK=2001:11 +readonly IPv6_HS_NETWORK=cafe +readonly SID_LOCATOR=fc00 + +PING_TIMEOUT_SEC=4 + +ret=0 + +PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no} + +log_test() +{ + local rc=$1 + local expected=$2 + local msg="$3" + + if [ ${rc} -eq ${expected} ]; then + nsuccess=$((nsuccess+1)) + printf "\n TEST: %-60s [ OK ]\n" "${msg}" + else + ret=1 + nfail=$((nfail+1)) + printf "\n TEST: %-60s [FAIL]\n" "${msg}" + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + echo + echo "hit enter to continue, 'q' to quit" + read a + [ "$a" = "q" ] && exit 1 + fi + fi +} + +print_log_test_results() +{ + if [ "$TESTS" != "none" ]; then + printf "\nTests passed: %3d\n" ${nsuccess} + printf "Tests failed: %3d\n" ${nfail} + fi +} + +log_section() +{ + echo + echo "################################################################################" + echo "TEST SECTION: $*" + echo "################################################################################" +} + +cleanup() +{ + ip link del veth-rt-1 2>/dev/null || true + ip link del veth-rt-2 2>/dev/null || true + + # destroy routers rt-* and hosts hs-* + for ns in $(ip netns show | grep -E 'rt-*|hs-*'); do + ip netns del ${ns} || true + done +} + +# Setup the basic networking for the routers +setup_rt_networking() +{ + local rt=$1 + local nsname=rt-${rt} + + ip netns add ${nsname} + + ip netns exec ${nsname} sysctl -wq net.ipv6.conf.all.accept_dad=0 + ip netns exec ${nsname} sysctl -wq net.ipv6.conf.default.accept_dad=0 + + ip link set veth-rt-${rt} netns ${nsname} + ip -netns ${nsname} link set veth-rt-${rt} name veth0 + + ip -netns ${nsname} addr add ${IPv6_RT_NETWORK}::${rt}/64 dev veth0 nodad + ip -netns ${nsname} link set veth0 up + ip -netns ${nsname} link set lo up + + ip netns exec ${nsname} sysctl -wq net.ipv6.conf.all.forwarding=1 +} + +setup_rt_netfilter() +{ + local rt=$1 + local nsname=rt-${rt} + + ip netns exec ${nsname} sysctl -wq net.netfilter.nf_hooks_lwtunnel=1 + ip netns exec ${nsname} ip6tables -t raw -A PREROUTING -m rpfilter --invert -j DROP +} + +setup_hs() +{ + local hs=$1 + local rt=$2 + local tid=$3 + local hsname=hs-${hs} + local rtname=rt-${rt} + local rtveth=veth-t${tid} + + # set the networking for the host + ip netns add ${hsname} + + ip -netns ${hsname} link add veth0 type veth peer name ${rtveth} + ip -netns ${hsname} link set ${rtveth} netns ${rtname} + ip -netns ${hsname} addr add ${IPv6_HS_NETWORK}::${hs}/64 dev veth0 nodad + ip -netns ${hsname} link set veth0 up + ip -netns ${hsname} link set lo up + + ip -netns ${rtname} addr add ${IPv6_HS_NETWORK}::${rt}${hs}/64 dev ${rtveth} + ip -netns ${rtname} link set ${rtveth} up + + ip netns exec ${rtname} sysctl -wq net.ipv6.conf.all.accept_dad=0 + ip netns exec ${rtname} sysctl -wq net.ipv6.conf.default.accept_dad=0 + + ip netns exec ${rtname} sysctl -wq net.ipv6.conf.${rtveth}.proxy_ndp=1 +} + +setup_vpn_config() +{ + local hssrc=$1 + local rtsrc=$2 + local hsdst=$3 + local rtdst=$4 + local tid=$5 + + local hssrc_name=hs-t${tid}-${hssrc} + local hsdst_name=hs-t${tid}-${hsdst} + local rtsrc_name=rt-${rtsrc} + local rtdst_name=rt-${rtdst} + local rtveth=veth-t${tid} + local vpn_sid=${SID_LOCATOR}:${hssrc}${hsdst}:${tid}::6004 + + ip -netns ${rtsrc_name} -6 neigh add proxy ${IPv6_HS_NETWORK}::${hsdst} dev ${rtveth} + + # set the encap route for encapsulating packets which arrive from the + # host hssrc and destined to the access router rtsrc. + ip -netns ${rtsrc_name} -6 route add ${IPv6_HS_NETWORK}::${hsdst}/128 \ + encap seg6 mode encap segs ${vpn_sid} dev veth0 + ip -netns ${rtsrc_name} -6 route add ${vpn_sid}/128 \ + via 2001:11::${rtdst} dev veth0 + + # set the decap route for decapsulating packets which arrive from + # the rtdst router and destined to the hsdst host. + ip -netns ${rtdst_name} -6 route add ${vpn_sid}/128 \ + encap seg6local action End.DX6 nh6 ${IPv6_HS_NETWORK}::${hsdst} dev veth-t${tid} +} + +setup() +{ + ip link add veth-rt-1 type veth peer name veth-rt-2 + # setup the networking for router rt-1 and router rt-2 + setup_rt_networking 1 + setup_rt_networking 2 + + # setup two hosts for the tenant 100. + # - host hs-1 is directly connected to the router rt-1; + # - host hs-2 is directly connected to the router rt-2. + setup_hs 1 1 100 + setup_hs 2 2 100 + + # setup the IPv4 L3 VPN which connects the host hs-1 and host hs-2. + setup_vpn_config 1 1 2 2 100 #args: src_host src_router dst_host dst_router tenant + setup_vpn_config 2 2 1 1 100 +} + +check_hs_connectivity() +{ + local hssrc=$1 + local hsdst=$2 + local tid=$3 + + ip netns exec hs-${hssrc} ping -6 -c 1 -W ${PING_TIMEOUT_SEC} \ + ${IPv6_HS_NETWORK}::${hsdst} >/dev/null 2>&1 +} + +check_and_log_hs_connectivity() +{ + local hssrc=$1 + local hsdst=$2 + local tid=$3 + + check_hs_connectivity ${hssrc} ${hsdst} ${tid} + log_test $? 0 "Hosts connectivity: hs-${hssrc} -> hs-${hsdst} (tenant ${tid})" +} + +host_tests() +{ + log_section "SRv6 VPN connectivity test among hosts in the same tenant" + + check_and_log_hs_connectivity 1 2 100 + check_and_log_hs_connectivity 2 1 100 +} + +router_netfilter_tests() +{ + log_section "SRv6 VPN connectivity test with netfilter enabled in routers" + setup_rt_netfilter 1 + setup_rt_netfilter 2 + + check_and_log_hs_connectivity 1 2 100 + check_and_log_hs_connectivity 2 1 100 +} + +if [ "$(id -u)" -ne 0 ];then + echo "SKIP: Need root privileges" + exit $ksft_skip +fi + +if [ ! -x "$(command -v ip)" ]; then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +cleanup &>/dev/null + +setup + +host_tests +router_netfilter_tests + +print_log_test_results + +cleanup &>/dev/null + +exit ${ret} diff --git a/tools/testing/selftests/openat2/Makefile b/tools/testing/selftests/openat2/Makefile index 254d676a2689..185dc76ebb5f 100644 --- a/tools/testing/selftests/openat2/Makefile +++ b/tools/testing/selftests/openat2/Makefile @@ -1,8 +1,18 @@ # SPDX-License-Identifier: GPL-2.0-or-later -CFLAGS += -Wall -O2 -g -fsanitize=address -fsanitize=undefined -static-libasan +CFLAGS += -Wall -O2 -g -fsanitize=address -fsanitize=undefined TEST_GEN_PROGS := openat2_test resolve_test rename_attack_test +# gcc requires -static-libasan in order to ensure that Address Sanitizer's +# library is the first one loaded. However, clang already statically links the +# Address Sanitizer if -fsanitize is specified. Therefore, simply omit +# -static-libasan for clang builds. +ifeq ($(LLVM),) + CFLAGS += -static-libasan +endif + +LOCAL_HDRS += helpers.h + include ../lib.mk -$(TEST_GEN_PROGS): helpers.c helpers.h +$(TEST_GEN_PROGS): helpers.c diff --git a/tools/testing/selftests/seccomp/seccomp_benchmark.c b/tools/testing/selftests/seccomp/seccomp_benchmark.c index b83099160fbc..94886c82ae60 100644 --- a/tools/testing/selftests/seccomp/seccomp_benchmark.c +++ b/tools/testing/selftests/seccomp/seccomp_benchmark.c @@ -194,14 +194,14 @@ int main(int argc, char *argv[]) ksft_set_plan(7); ksft_print_msg("Running on:\n"); - ksft_print_msg(""); + ksft_print_msg("%s", ""); system("uname -a"); ksft_print_msg("Current BPF sysctl settings:\n"); /* Avoid using "sysctl" which may not be installed. */ - ksft_print_msg(""); + ksft_print_msg("%s", ""); system("grep -H . /proc/sys/net/core/bpf_jit_enable"); - ksft_print_msg(""); + ksft_print_msg("%s", ""); system("grep -H . /proc/sys/net/core/bpf_jit_harden"); affinity(); |