diff options
627 files changed, 12849 insertions, 4291 deletions
@@ -121,6 +121,8 @@ Ben Widawsky <bwidawsk@kernel.org> <benjamin.widawsky@intel.com> Benjamin Poirier <benjamin.poirier@gmail.com> <bpoirier@suse.de> Benjamin Tissoires <bentiss@kernel.org> <benjamin.tissoires@gmail.com> Benjamin Tissoires <bentiss@kernel.org> <benjamin.tissoires@redhat.com> +Bingwu Zhang <xtex@aosc.io> <xtexchooser@duck.com> +Bingwu Zhang <xtex@aosc.io> <xtex@xtexx.eu.org> Bjorn Andersson <andersson@kernel.org> <bjorn@kryo.se> Bjorn Andersson <andersson@kernel.org> <bjorn.andersson@linaro.org> Bjorn Andersson <andersson@kernel.org> <bjorn.andersson@sonymobile.com> @@ -529,6 +531,8 @@ Oleksij Rempel <linux@rempel-privat.de> <external.Oleksij.Rempel@de.bosch.com> Oleksij Rempel <linux@rempel-privat.de> <fixed-term.Oleksij.Rempel@de.bosch.com> Oleksij Rempel <o.rempel@pengutronix.de> Oleksij Rempel <o.rempel@pengutronix.de> <ore@pengutronix.de> +Oliver Hartkopp <socketcan@hartkopp.net> <oliver.hartkopp@volkswagen.de> +Oliver Hartkopp <socketcan@hartkopp.net> <oliver@hartkopp.net> Oliver Upton <oliver.upton@linux.dev> <oupton@google.com> OndÅ™ej Jirman <megi@xff.cz> <megous@megous.com> Oza Pawandeep <quic_poza@quicinc.com> <poza@codeaurora.org> diff --git a/Documentation/admin-guide/pm/cpuidle.rst b/Documentation/admin-guide/pm/cpuidle.rst index 19754beb5a4e..eb58d7a5affd 100644 --- a/Documentation/admin-guide/pm/cpuidle.rst +++ b/Documentation/admin-guide/pm/cpuidle.rst @@ -269,27 +269,7 @@ Namely, when invoked to select an idle state for a CPU (i.e. an idle state that the CPU will ask the processor hardware to enter), it attempts to predict the idle duration and uses the predicted value for idle state selection. -It first obtains the time until the closest timer event with the assumption -that the scheduler tick will be stopped. That time, referred to as the *sleep -length* in what follows, is the upper bound on the time before the next CPU -wakeup. It is used to determine the sleep length range, which in turn is needed -to get the sleep length correction factor. - -The ``menu`` governor maintains two arrays of sleep length correction factors. -One of them is used when tasks previously running on the given CPU are waiting -for some I/O operations to complete and the other one is used when that is not -the case. Each array contains several correction factor values that correspond -to different sleep length ranges organized so that each range represented in the -array is approximately 10 times wider than the previous one. - -The correction factor for the given sleep length range (determined before -selecting the idle state for the CPU) is updated after the CPU has been woken -up and the closer the sleep length is to the observed idle duration, the closer -to 1 the correction factor becomes (it must fall between 0 and 1 inclusive). -The sleep length is multiplied by the correction factor for the range that it -falls into to obtain the first approximation of the predicted idle duration. - -Next, the governor uses a simple pattern recognition algorithm to refine its +It first uses a simple pattern recognition algorithm to obtain a preliminary idle duration prediction. Namely, it saves the last 8 observed idle duration values and, when predicting the idle duration next time, it computes the average and variance of them. If the variance is small (smaller than 400 square @@ -301,29 +281,39 @@ Again, if the variance of them is small (in the above sense), the average is taken as the "typical interval" value and so on, until either the "typical interval" is determined or too many data points are disregarded, in which case the "typical interval" is assumed to equal "infinity" (the maximum unsigned -integer value). The "typical interval" computed this way is compared with the -sleep length multiplied by the correction factor and the minimum of the two is -taken as the predicted idle duration. - -Then, the governor computes an extra latency limit to help "interactive" -workloads. It uses the observation that if the exit latency of the selected -idle state is comparable with the predicted idle duration, the total time spent -in that state probably will be very short and the amount of energy to save by -entering it will be relatively small, so likely it is better to avoid the -overhead related to entering that state and exiting it. Thus selecting a -shallower state is likely to be a better option then. The first approximation -of the extra latency limit is the predicted idle duration itself which -additionally is divided by a value depending on the number of tasks that -previously ran on the given CPU and now they are waiting for I/O operations to -complete. The result of that division is compared with the latency limit coming -from the power management quality of service, or `PM QoS <cpu-pm-qos_>`_, -framework and the minimum of the two is taken as the limit for the idle states' -exit latency. +integer value). + +If the "typical interval" computed this way is long enough, the governor obtains +the time until the closest timer event with the assumption that the scheduler +tick will be stopped. That time, referred to as the *sleep length* in what follows, +is the upper bound on the time before the next CPU wakeup. It is used to determine +the sleep length range, which in turn is needed to get the sleep length correction +factor. + +The ``menu`` governor maintains an array containing several correction factor +values that correspond to different sleep length ranges organized so that each +range represented in the array is approximately 10 times wider than the previous +one. + +The correction factor for the given sleep length range (determined before +selecting the idle state for the CPU) is updated after the CPU has been woken +up and the closer the sleep length is to the observed idle duration, the closer +to 1 the correction factor becomes (it must fall between 0 and 1 inclusive). +The sleep length is multiplied by the correction factor for the range that it +falls into to obtain an approximation of the predicted idle duration that is +compared to the "typical interval" determined previously and the minimum of +the two is taken as the idle duration prediction. + +If the "typical interval" value is small, which means that the CPU is likely +to be woken up soon enough, the sleep length computation is skipped as it may +be costly and the idle duration is simply predicted to equal the "typical +interval" value. Now, the governor is ready to walk the list of idle states and choose one of them. For this purpose, it compares the target residency of each state with -the predicted idle duration and the exit latency of it with the computed latency -limit. It selects the state with the target residency closest to the predicted +the predicted idle duration and the exit latency of it with the with the latency +limit coming from the power management quality of service, or `PM QoS <cpu-pm-qos_>`_, +framework. It selects the state with the target residency closest to the predicted idle duration, but still below it, and exit latency that does not exceed the limit. diff --git a/Documentation/devicetree/bindings/display/mediatek/mediatek,dp.yaml b/Documentation/devicetree/bindings/display/mediatek/mediatek,dp.yaml index 2aef1eb32e11..75ce92f4a5fd 100644 --- a/Documentation/devicetree/bindings/display/mediatek/mediatek,dp.yaml +++ b/Documentation/devicetree/bindings/display/mediatek/mediatek,dp.yaml @@ -42,6 +42,9 @@ properties: interrupts: maxItems: 1 + '#sound-dai-cells': + const: 0 + ports: $ref: /schemas/graph.yaml#/properties/ports properties: @@ -85,7 +88,21 @@ required: - ports - max-linkrate-mhz -additionalProperties: false +allOf: + - $ref: /schemas/sound/dai-common.yaml# + - if: + not: + properties: + compatible: + contains: + enum: + - mediatek,mt8188-dp-tx + - mediatek,mt8195-dp-tx + then: + properties: + '#sound-dai-cells': false + +unevaluatedProperties: false examples: - | diff --git a/Documentation/devicetree/bindings/iio/st,st-sensors.yaml b/Documentation/devicetree/bindings/iio/st,st-sensors.yaml index 71c1ee33a393..e955eb8e8797 100644 --- a/Documentation/devicetree/bindings/iio/st,st-sensors.yaml +++ b/Documentation/devicetree/bindings/iio/st,st-sensors.yaml @@ -65,6 +65,7 @@ properties: - st,lsm9ds0-gyro - description: STMicroelectronics Magnetometers enum: + - st,iis2mdc - st,lis2mdl - st,lis3mdl-magn - st,lsm303agr-magn diff --git a/Documentation/devicetree/bindings/net/can/atmel,at91sam9263-can.yaml b/Documentation/devicetree/bindings/net/can/atmel,at91sam9263-can.yaml new file mode 100644 index 000000000000..c818c01a718b --- /dev/null +++ b/Documentation/devicetree/bindings/net/can/atmel,at91sam9263-can.yaml @@ -0,0 +1,58 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/can/atmel,at91sam9263-can.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Microchip AT91 CAN Controller + +maintainers: + - Nicolas Ferre <nicolas.ferre@microchip.com> + +allOf: + - $ref: can-controller.yaml# + +properties: + compatible: + oneOf: + - enum: + - atmel,at91sam9263-can + - atmel,at91sam9x5-can + - items: + - enum: + - microchip,sam9x60-can + - const: atmel,at91sam9x5-can + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + clocks: + maxItems: 1 + + clock-names: + items: + - const: can_clk + +required: + - compatible + - reg + - interrupts + - clocks + - clock-names + +unevaluatedProperties: false + +examples: + - | + #include <dt-bindings/interrupt-controller/irq.h> + #include <dt-bindings/clock/at91.h> + can@f000c000 { + compatible = "atmel,at91sam9263-can"; + reg = <0xf000c000 0x300>; + interrupts = <30 IRQ_TYPE_LEVEL_HIGH 3>; + clocks = <&pmc PMC_TYPE_PERIPHERAL 12>; + clock-names = "can_clk"; + }; diff --git a/Documentation/devicetree/bindings/net/can/atmel-can.txt b/Documentation/devicetree/bindings/net/can/atmel-can.txt deleted file mode 100644 index 218a3b3eb27e..000000000000 --- a/Documentation/devicetree/bindings/net/can/atmel-can.txt +++ /dev/null @@ -1,15 +0,0 @@ -* AT91 CAN * - -Required properties: - - compatible: Should be "atmel,at91sam9263-can", "atmel,at91sam9x5-can" or - "microchip,sam9x60-can" - - reg: Should contain CAN controller registers location and length - - interrupts: Should contain IRQ line for the CAN controller - -Example: - - can0: can@f000c000 { - compatible = "atmel,at91sam9x5-can"; - reg = <0xf000c000 0x300>; - interrupts = <40 4 5> - }; diff --git a/Documentation/devicetree/bindings/net/can/microchip,mpfs-can.yaml b/Documentation/devicetree/bindings/net/can/microchip,mpfs-can.yaml index 01e4d4a54df6..1219c5cb601f 100644 --- a/Documentation/devicetree/bindings/net/can/microchip,mpfs-can.yaml +++ b/Documentation/devicetree/bindings/net/can/microchip,mpfs-can.yaml @@ -15,7 +15,11 @@ allOf: properties: compatible: - const: microchip,mpfs-can + oneOf: + - items: + - const: microchip,pic64gx-can + - const: microchip,mpfs-can + - const: microchip,mpfs-can reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/net/can/st,stm32-bxcan.yaml b/Documentation/devicetree/bindings/net/can/st,stm32-bxcan.yaml index de1d4298893b..c7510b00954a 100644 --- a/Documentation/devicetree/bindings/net/can/st,stm32-bxcan.yaml +++ b/Documentation/devicetree/bindings/net/can/st,stm32-bxcan.yaml @@ -63,7 +63,7 @@ properties: maxItems: 1 st,gcan: - $ref: /schemas/types.yaml#/definitions/phandle-array + $ref: /schemas/types.yaml#/definitions/phandle description: The phandle to the gcan node which allows to access the 512-bytes SRAM memory shared by the two bxCAN cells (CAN1 primary and CAN2 diff --git a/Documentation/devicetree/bindings/net/can/tcan4x5x.txt b/Documentation/devicetree/bindings/net/can/tcan4x5x.txt deleted file mode 100644 index 20c0572c9853..000000000000 --- a/Documentation/devicetree/bindings/net/can/tcan4x5x.txt +++ /dev/null @@ -1,48 +0,0 @@ -Texas Instruments TCAN4x5x CAN Controller -================================================ - -This file provides device node information for the TCAN4x5x interface contains. - -Required properties: - - compatible: - "ti,tcan4552", "ti,tcan4x5x" - "ti,tcan4553", "ti,tcan4x5x" or - "ti,tcan4x5x" - - reg: 0 - - #address-cells: 1 - - #size-cells: 0 - - spi-max-frequency: Maximum frequency of the SPI bus the chip can - operate at should be less than or equal to 18 MHz. - - interrupt-parent: the phandle to the interrupt controller which provides - the interrupt. - - interrupts: interrupt specification for data-ready. - -See Documentation/devicetree/bindings/net/can/bosch,m_can.yaml for additional -required property details. - -Optional properties: - - reset-gpios: Hardwired output GPIO. If not defined then software - reset. - - device-state-gpios: Input GPIO that indicates if the device is in - a sleep state or if the device is active. Not - available with tcan4552/4553. - - device-wake-gpios: Wake up GPIO to wake up the TCAN device. Not - available with tcan4552/4553. - - wakeup-source: Leave the chip running when suspended, and configure - the RX interrupt to wake up the device. - -Example: -tcan4x5x: tcan4x5x@0 { - compatible = "ti,tcan4x5x"; - reg = <0>; - #address-cells = <1>; - #size-cells = <1>; - spi-max-frequency = <10000000>; - bosch,mram-cfg = <0x0 0 0 16 0 0 1 1>; - interrupt-parent = <&gpio1>; - interrupts = <14 IRQ_TYPE_LEVEL_LOW>; - device-state-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>; - device-wake-gpios = <&gpio1 15 GPIO_ACTIVE_HIGH>; - reset-gpios = <&gpio1 27 GPIO_ACTIVE_HIGH>; - wakeup-source; -}; diff --git a/Documentation/devicetree/bindings/net/can/ti,tcan4x5x.yaml b/Documentation/devicetree/bindings/net/can/ti,tcan4x5x.yaml new file mode 100644 index 000000000000..384e15da2713 --- /dev/null +++ b/Documentation/devicetree/bindings/net/can/ti,tcan4x5x.yaml @@ -0,0 +1,199 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/can/ti,tcan4x5x.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Texas Instruments TCAN4x5x CAN Controller + +maintainers: + - Marc Kleine-Budde <mkl@pengutronix.de> + +properties: + compatible: + oneOf: + - items: + - enum: + - ti,tcan4552 + - ti,tcan4553 + - const: ti,tcan4x5x + - const: ti,tcan4x5x + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + description: The GPIO parent interrupt. + + clocks: + maxItems: 1 + + clock-names: + items: + - const: cclk + + reset-gpios: + description: Hardwired output GPIO. If not defined then software reset. + maxItems: 1 + + device-state-gpios: + description: + Input GPIO that indicates if the device is in a sleep state or if the + device is active. Not available with tcan4552/4553. + maxItems: 1 + + device-wake-gpios: + description: + Wake up GPIO to wake up the TCAN device. + Not available with tcan4552/4553. + maxItems: 1 + + bosch,mram-cfg: + description: | + Message RAM configuration data. + Multiple M_CAN instances can share the same Message RAM + and each element(e.g Rx FIFO or Tx Buffer and etc) number + in Message RAM is also configurable, so this property is + telling driver how the shared or private Message RAM are + used by this M_CAN controller. + + The format should be as follows: + <offset sidf_elems xidf_elems rxf0_elems rxf1_elems rxb_elems txe_elems txb_elems> + The 'offset' is an address offset of the Message RAM where + the following elements start from. This is usually set to + 0x0 if you're using a private Message RAM. The remain cells + are used to specify how many elements are used for each FIFO/Buffer. + + M_CAN includes the following elements according to user manual: + 11-bit Filter 0-128 elements / 0-128 words + 29-bit Filter 0-64 elements / 0-128 words + Rx FIFO 0 0-64 elements / 0-1152 words + Rx FIFO 1 0-64 elements / 0-1152 words + Rx Buffers 0-64 elements / 0-1152 words + Tx Event FIFO 0-32 elements / 0-64 words + Tx Buffers 0-32 elements / 0-576 words + + Please refer to 2.4.1 Message RAM Configuration in Bosch + M_CAN user manual for details. + $ref: /schemas/types.yaml#/definitions/int32-array + items: + - description: The 'offset' is an address offset of the Message RAM where + the following elements start from. This is usually set to 0x0 if + you're using a private Message RAM. + default: 0 + - description: 11-bit Filter 0-128 elements / 0-128 words + minimum: 0 + maximum: 128 + - description: 29-bit Filter 0-64 elements / 0-128 words + minimum: 0 + maximum: 64 + - description: Rx FIFO 0 0-64 elements / 0-1152 words + minimum: 0 + maximum: 64 + - description: Rx FIFO 1 0-64 elements / 0-1152 words + minimum: 0 + maximum: 64 + - description: Rx Buffers 0-64 elements / 0-1152 words + minimum: 0 + maximum: 64 + - description: Tx Event FIFO 0-32 elements / 0-64 words + minimum: 0 + maximum: 32 + - description: Tx Buffers 0-32 elements / 0-576 words + minimum: 0 + maximum: 32 + minItems: 1 + + spi-max-frequency: + description: + Must be half or less of "clocks" frequency. + maximum: 18000000 + + ti,nwkrq-voltage-vio: + type: boolean + description: + nWKRQ Pin GPO buffer voltage configuration. + Set nWKRQ to use VIO voltage rail. + When not set nWKRQ will use internal voltage rail. + + wakeup-source: + $ref: /schemas/types.yaml#/definitions/flag + description: + Enable CAN remote wakeup. + +allOf: + - $ref: can-controller.yaml# + - $ref: /schemas/spi/spi-peripheral-props.yaml# + - if: + properties: + compatible: + contains: + enum: + - ti,tcan4552 + - ti,tcan4553 + then: + properties: + device-state-gpios: false + device-wake-gpios: false + +required: + - compatible + - reg + - interrupts + - clocks + - clock-names + - bosch,mram-cfg + +unevaluatedProperties: false + +examples: + - | + #include <dt-bindings/gpio/gpio.h> + #include <dt-bindings/interrupt-controller/irq.h> + + spi { + #address-cells = <1>; + #size-cells = <0>; + + can@0 { + compatible = "ti,tcan4x5x"; + reg = <0>; + clocks = <&can0_osc>; + clock-names = "cclk"; + pinctrl-names = "default"; + pinctrl-0 = <&can0_pins>; + spi-max-frequency = <10000000>; + bosch,mram-cfg = <0x0 0 0 16 0 0 1 1>; + interrupt-parent = <&gpio1>; + interrupts = <14 IRQ_TYPE_LEVEL_LOW>; + device-state-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>; + device-wake-gpios = <&gpio1 15 GPIO_ACTIVE_HIGH>; + reset-gpios = <&gpio1 27 GPIO_ACTIVE_HIGH>; + ti,nwkrq-voltage-vio; + wakeup-source; + }; + }; + - | + #include <dt-bindings/gpio/gpio.h> + #include <dt-bindings/interrupt-controller/irq.h> + + spi { + #address-cells = <1>; + #size-cells = <0>; + + can@0 { + compatible = "ti,tcan4552", "ti,tcan4x5x"; + reg = <0>; + clocks = <&can0_osc>; + clock-names = "cclk"; + pinctrl-names = "default"; + pinctrl-0 = <&can0_pins>; + spi-max-frequency = <10000000>; + bosch,mram-cfg = <0x0 0 0 16 0 0 1 1>; + interrupt-parent = <&gpio1>; + interrupts = <14 IRQ_TYPE_LEVEL_LOW>; + reset-gpios = <&gpio1 27 GPIO_ACTIVE_HIGH>; + wakeup-source; + }; + }; diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml index 60f85fbf4156..259cb211a338 100644 --- a/Documentation/netlink/specs/ethtool.yaml +++ b/Documentation/netlink/specs/ethtool.yaml @@ -332,6 +332,12 @@ attribute-sets: - name: tx-push-buf-len-max type: u32 + - + name: hds-thresh + type: u32 + - + name: hds-thresh-max + type: u32 - name: mm-stat @@ -836,6 +842,9 @@ attribute-sets: - name: tx-err type: uint + - + name: tx-onestep-pkts-unconfirmed + type: uint - name: ts-hwtstamp-provider attr-cnt-name: __ethtool-a-ts-hwtstamp-provider-cnt @@ -1777,6 +1786,8 @@ operations: - rx-push - tx-push-buf-len - tx-push-buf-len-max + - hds-thresh + - hds-thresh-max dump: *ring-get-op - name: rings-set diff --git a/Documentation/networking/devlink/mlx5.rst b/Documentation/networking/devlink/mlx5.rst index 456985407475..41618538fc70 100644 --- a/Documentation/networking/devlink/mlx5.rst +++ b/Documentation/networking/devlink/mlx5.rst @@ -53,6 +53,9 @@ parameters. * ``smfs`` Software managed flow steering. In SMFS mode, the HW steering entities are created and manage through the driver without firmware intervention. + * ``hmfs`` Hardware managed flow steering. In HMFS mode, the driver + is configuring steering rules directly to the HW using Work Queues with + a special new type of WQE (Work Queue Element). SMFS mode is faster and provides better rule insertion rate compared to default DMFS mode. diff --git a/Documentation/networking/diagnostic/twisted_pair_layer1_diagnostics.rst b/Documentation/networking/diagnostic/twisted_pair_layer1_diagnostics.rst index c9be5cc7e113..079e17effadf 100644 --- a/Documentation/networking/diagnostic/twisted_pair_layer1_diagnostics.rst +++ b/Documentation/networking/diagnostic/twisted_pair_layer1_diagnostics.rst @@ -713,17 +713,23 @@ driver supports reporting such events. - **Monitor Error Counters**: - - While some NIC drivers and PHYs provide error counters, there is no unified - set of PHY-specific counters across all hardware. Additionally, not all - PHYs provide useful information related to errors like CRC errors, frame - drops, or link flaps. Therefore, this step is dependent on the specific - hardware and driver support. - - - **Next Steps**: Use `ethtool -S <interface>` to check if your driver - provides useful error counters. In some cases, counters may provide - information about errors like link flaps or physical layer problems (e.g., - excessive CRC errors), but results can vary significantly depending on the - PHY. + - Use `ethtool -S <interface> --all-groups` to retrieve standardized interface + statistics if the driver supports the unified interface: + + - **Command:** `ethtool -S <interface> --all-groups` + + - **Example Output (if supported)**: + + .. code-block:: bash + + phydev-RxFrames: 100391 + phydev-RxErrors: 0 + phydev-TxFrames: 9 + phydev-TxErrors: 0 + + - If the unified interface is not supported, use `ethtool -S <interface>` to + retrieve MAC and PHY counters. Note that non-standardized PHY counter names + vary by driver and must be interpreted accordingly: - **Command:** `ethtool -S <interface>` @@ -740,6 +746,17 @@ driver supports reporting such events. condition) or kernel log messages (e.g., link up/down events) to further diagnose the issue. + - **Compare Counters**: + + - Compare the egress and ingress frame counts reported by the PHY and MAC. + + - A small difference may occur due to sampling rate differences between the + MAC and PHY drivers, or if the PHY and MAC are not always fully + synchronized in their UP or DOWN states. + + - Significant discrepancies indicate potential issues in the data path + between the MAC and PHY. + When All Else Fails... ~~~~~~~~~~~~~~~~~~~~~~ diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index a7ba6368a4d5..3770a2294509 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -899,6 +899,10 @@ Kernel response contents: ``ETHTOOL_A_RINGS_RX_PUSH`` u8 flag of RX Push mode ``ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN`` u32 size of TX push buffer ``ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN_MAX`` u32 max size of TX push buffer + ``ETHTOOL_A_RINGS_HDS_THRESH`` u32 threshold of + header / data split + ``ETHTOOL_A_RINGS_HDS_THRESH_MAX`` u32 max threshold of + header / data split ======================================= ====== =========================== ``ETHTOOL_A_RINGS_TCP_DATA_SPLIT`` indicates whether the device is usable with @@ -941,10 +945,12 @@ Request contents: ``ETHTOOL_A_RINGS_RX_JUMBO`` u32 size of RX jumbo ring ``ETHTOOL_A_RINGS_TX`` u32 size of TX ring ``ETHTOOL_A_RINGS_RX_BUF_LEN`` u32 size of buffers on the ring + ``ETHTOOL_A_RINGS_TCP_DATA_SPLIT`` u8 TCP header / data split ``ETHTOOL_A_RINGS_CQE_SIZE`` u32 Size of TX/RX CQE ``ETHTOOL_A_RINGS_TX_PUSH`` u8 flag of TX Push mode ``ETHTOOL_A_RINGS_RX_PUSH`` u8 flag of RX Push mode ``ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN`` u32 size of TX push buffer + ``ETHTOOL_A_RINGS_HDS_THRESH`` u32 threshold of header / data split ==================================== ====== =========================== Kernel checks that requested ring sizes do not exceed limits reported by @@ -961,6 +967,10 @@ A bigger CQE can have more receive buffer pointers, and in turn the NIC can transfer a bigger frame from wire. Based on the NIC hardware, the overall completion queue size can be adjusted in the driver if CQE size is modified. +``ETHTOOL_A_RINGS_HDS_THRESH`` specifies the threshold value of +header / data split feature. If a received packet size is larger than this +threshold value, header and data will be split. + CHANNELS_GET ============ @@ -1271,11 +1281,17 @@ would be empty (no bit set). Additional hardware timestamping statistics response contents: - ===================================== ====== =================================== - ``ETHTOOL_A_TS_STAT_TX_PKTS`` uint Packets with Tx HW timestamps - ``ETHTOOL_A_TS_STAT_TX_LOST`` uint Tx HW timestamp not arrived count - ``ETHTOOL_A_TS_STAT_TX_ERR`` uint HW error request Tx timestamp count - ===================================== ====== =================================== + ================================================== ====== ===================== + ``ETHTOOL_A_TS_STAT_TX_PKTS`` uint Packets with Tx + HW timestamps + ``ETHTOOL_A_TS_STAT_TX_LOST`` uint Tx HW timestamp + not arrived count + ``ETHTOOL_A_TS_STAT_TX_ERR`` uint HW error request + Tx timestamp count + ``ETHTOOL_A_TS_STAT_TX_ONESTEP_PKTS_UNCONFIRMED`` uint Packets with one-step + HW TX timestamps with + unconfirmed delivery + ================================================== ====== ===================== CABLE_TEST ========== @@ -1616,6 +1632,7 @@ the ``ETHTOOL_A_STATS_GROUPS`` bitset. Currently defined values are: ETHTOOL_STATS_ETH_PHY eth-phy Basic IEEE 802.3 PHY statistics (30.3.2.1.*) ETHTOOL_STATS_ETH_CTRL eth-ctrl Basic IEEE 802.3 MAC Ctrl statistics (30.3.3.*) ETHTOOL_STATS_RMON rmon RMON (RFC 2819) statistics + ETHTOOL_STATS_PHY phy Additional PHY statistics, not defined by IEEE ====================== ======== =============================================== Each group should have a corresponding ``ETHTOOL_A_STATS_GRP`` in the reply. diff --git a/Documentation/networking/mptcp-sysctl.rst b/Documentation/networking/mptcp-sysctl.rst index 95598c21fc8e..dc45c0211353 100644 --- a/Documentation/networking/mptcp-sysctl.rst +++ b/Documentation/networking/mptcp-sysctl.rst @@ -108,3 +108,19 @@ stale_loss_cnt - INTEGER This is a per-namespace sysctl. Default: 4 + +syn_retrans_before_tcp_fallback - INTEGER + The number of SYN + MP_CAPABLE retransmissions before falling back to + TCP, i.e. dropping the MPTCP options. In other words, if all the packets + are dropped on the way, there will be: + + * The initial SYN with MPTCP support + * This number of SYN retransmitted with MPTCP support + * The next SYN retransmissions will be without MPTCP support + + 0 means the first retransmission will be done without MPTCP options. + >= 128 means that all SYN retransmissions will keep the MPTCP options. A + lower number might increase false-positive MPTCP blackholes detections. + This is a per-namespace sysctl. + + Default: 2 diff --git a/Documentation/process/maintainer-netdev.rst b/Documentation/process/maintainer-netdev.rst index 1ae71e31591c..e497729525d5 100644 --- a/Documentation/process/maintainer-netdev.rst +++ b/Documentation/process/maintainer-netdev.rst @@ -470,6 +470,52 @@ in a way which would break what would normally be considered uAPI. new ``netdevsim`` features must be accompanied by selftests under ``tools/testing/selftests/``. +Supported status for drivers +---------------------------- + +.. note: The following requirements apply only to Ethernet NIC drivers. + +Netdev defines additional requirements for drivers which want to acquire +the ``Supported`` status in the MAINTAINERS file. ``Supported`` drivers must +be running all upstream driver tests and reporting the results twice a day. +Drivers which do not comply with this requirement should use the ``Maintained`` +status. There is currently no difference in how ``Supported`` and ``Maintained`` +drivers are treated upstream. + +The exact rules a driver must follow to acquire the ``Supported`` status: + +1. Must run all tests under ``drivers/net`` and ``drivers/net/hw`` targets + of Linux selftests. Running and reporting private / internal tests is + also welcome, but upstream tests are a must. + +2. The minimum run frequency is once every 12 hours. Must test the + designated branch from the selected branch feed. Note that branches + are auto-constructed and exposed to intentional malicious patch posting, + so the test systems must be isolated. + +3. Drivers supporting multiple generations of devices must test at + least one device from each generation. A testbed manifest (exact + format TBD) should describe the device models tested. + +4. The tests must run reliably, if multiple branches are skipped or tests + are failing due to execution environment problems the ``Supported`` + status will be withdrawn. + +5. Test failures due to bugs either in the driver or the test itself, + or lack of support for the feature the test is targgeting are + *not* a basis for losing the ``Supported`` status. + +netdev CI will maintain an official page of supported devices, listing their +recent test results. + +The driver maintainer may arrange for someone else to run the test, +there is no requirement for the person listed as maintainer (or their +employer) to be responsible for running the tests. Collaboration between +vendors, hosting GH CI, other repos under linux-netdev, etc. is most welcome. + +See https://github.com/linux-netdev/nipa/wiki for more information about +netdev CI. Feel free to reach out to maintainers or the list with any questions. + Reviewer guidance ----------------- diff --git a/Documentation/sound/codecs/cs35l56.rst b/Documentation/sound/codecs/cs35l56.rst new file mode 100644 index 000000000000..98c6f6c74394 --- /dev/null +++ b/Documentation/sound/codecs/cs35l56.rst @@ -0,0 +1,292 @@ +.. SPDX-License-Identifier: GPL-2.0-only + +===================================================================== +Audio drivers for Cirrus Logic CS35L54/56/57 Boosted Smart Amplifiers +===================================================================== +:Copyright: 2025 Cirrus Logic, Inc. and + Cirrus Logic International Semiconductor Ltd. + +Contact: patches@opensource.cirrus.com + +Summary +======= + +The high-level summary of this document is: + +**If you have a laptop that uses CS35L54/56/57 amplifiers but audio is not +working, DO NOT ATTEMPT TO USE FIRMWARE AND SETTINGS FROM ANOTHER LAPTOP, +EVEN IF THAT LAPTOP SEEMS SIMILAR.** + +The CS35L54/56/57 amplifiers must be correctly configured for the power +supply voltage, speaker impedance, maximum speaker voltage/current, and +other external hardware connections. + +The amplifiers feature advanced boost technology that increases the voltage +used to drive the speakers, while proprietary speaker protection algorithms +allow these boosted amplifiers to push the limits of the speakers without +causing damage. These **must** be configured correctly. + +Supported Cirrus Logic amplifiers +--------------------------------- + +The cs35l56 drivers support: + +* CS35L54 +* CS35L56 +* CS35L57 + +There are two drivers in the kernel + +*For systems using SoundWire*: sound/soc/codecs/cs35l56.c and associated files + +*For systems using HDA*: sound/pci/hda/cs35l56_hda.c + +Firmware +======== + +The amplifier is controlled and managed by firmware running on the internal +DSP. Firmware files are essential to enable the full capabilities of the +amplifier. + +Firmware is distributed in the linux-firmware repository: +https://gitlab.com/kernel-firmware/linux-firmware.git + +On most SoundWire systems the amplifier has a default minimum capability to +produce audio. However this will be + +* at low volume, to protect the speakers, since the speaker specifications + and power supply voltages are unknown. +* a mono mix of left and right channels. + +On some SoundWire systems that have both CS42L43 and CS35L56/57 the CS35L56/57 +receive their audio from the CS42L43 instead of directly from the host +SoundWire interface. These systems can be identified by the CS42L43 showing +in dmesg as a SoundWire device, but the CS35L56/57 as SPI. On these systems +the firmware is *mandatory* to enable receiving the audio from the CS42L43. + +On HDA systems the firmware is *mandatory* to enable HDA bridge mode. There +will not be any audio from the amplifiers without firmware. + +Cirrus Logic firmware files +--------------------------- + +Each amplifier requires two firmware files. One file has a .wmfw suffix, the +other has a .bin suffix. + +The firmware is customized by the OEM to match the hardware of each laptop, +and the firmware is specific to that laptop. Because of this, there are many +firmware files in linux-firmware for these amplifiers. Firmware files are +**not interchangeable between laptops**. + +Cirrus Logic submits files for known laptops to the upstream linux-firmware +repository. Providing Cirrus Logic is aware of a particular laptop and has +permission from the manufacturer to publish the firmware, it will be pushed +to linux-firmware. You may need to upgrade to a newer release of +linux-firmware to obtain the firmware for your laptop. + +**Important:** the Makefile for linux-firmware creates symlinks that are listed +in the WHENCE file. These symlinks are required for the CS35L56 driver to be +able to load the firmware. + +How do I know which firmware file I should have? +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +All firmware file names are qualified with a unique "system ID". On normal +x86 PCs with PCI audio this is the Vendor Subsystem ID (SSID) of the host +PCI audio interface. + +The SSID can be viewed using the lspci tool:: + + lspci -v -nn | grep -A2 -i audio + 0000:00:1f.3 Audio device [0403]: Intel Corporation Meteor Lake-P HD Audio Controller [8086:7e28] + Subsystem: Dell Meteor Lake-P HD Audio Controller [1028:0c63] + +In this example the SSID is 10280c63. + +The format of the firmware file names is: + + cs35lxx-b0-dsp1-misc-SSID[-spkidX]-ampN + +Where: + + * cs35lxx-b0 is the amplifier model and silicon revision. This information + is logged by the driver during initialization. + * SSID is the 8-digit hexadecimal SSID value. + * ampN is the amplifier number (for example amp1). This is the same as + the prefix on the ALSA control names except that it is always lower-case + in the file name. + * spkidX is an optional part, used for laptops that have firmware + configurations for different makes and models of internal speakers. + +Sound Open Firmware and ALSA topology files +------------------------------------------- + +All SoundWire systems will require a Sound Open Firmware (SOF) for the +host CPU audio DSP, together with an ALSA topology file (.tplg). + +The SOF firmware will usually be provided by the manufacturer of the host +CPU (i.e. Intel or AMD). The .tplg file is normally part of the SOF firmware +release. + +SOF binary builds are available from: https://github.com/thesofproject/sof-bin/releases + +The main SOF source is here: https://github.com/thesofproject + +ALSA-ucm configurations +----------------------- +Typically an appropriate ALSA-ucm configuration file is needed for +use-case managers and audio servers such as PipeWire. + +Configuration files are available from the alsa-ucm-conf repository: +https://git.alsa-project.org/?p=alsa-ucm-conf.git + +Kernel log messages +=================== + +SoundWire +--------- +A successful initialization will look like this (this will be repeated for +each amplifier):: + + [ 7.568374] cs35l56 sdw:0:0:01fa:3556:01:0: supply VDD_P not found, using dummy regulator + [ 7.605208] cs35l56 sdw:0:0:01fa:3556:01:0: supply VDD_IO not found, using dummy regulator + [ 7.605313] cs35l56 sdw:0:0:01fa:3556:01:0: supply VDD_A not found, using dummy regulator + [ 7.939279] cs35l56 sdw:0:0:01fa:3556:01:0: Cirrus Logic CS35L56 Rev B0 OTP3 fw:3.4.4 (patched=0) + [ 7.947844] cs35l56 sdw:0:0:01fa:3556:01:0: Slave 4 state check1: UNATTACHED, status was 1 + [ 8.740280] cs35l56 sdw:0:0:01fa:3556:01:0: supply VDD_B not found, using dummy regulator + [ 8.740552] cs35l56 sdw:0:0:01fa:3556:01:0: supply VDD_AMP not found, using dummy regulator + [ 9.242164] cs35l56 sdw:0:0:01fa:3556:01:0: DSP1: cirrus/cs35l56-b0-dsp1-misc-xxxxxxxx.wmfw: format 3 timestamp 0x66b2b872 + [ 9.242173] cs35l56 sdw:0:0:01fa:3556:01:0: DSP1: cirrus/cs35l56-b0-dsp1-misc-xxxxxxxx.wmfw: Tue 05 Dec 2023 21:37:21 GMT Standard Time + [ 9.991709] cs35l56 sdw:0:0:01fa:3556:01:0: DSP1: Firmware: 1a00d6 vendor: 0x2 v3.11.23, 41 algorithms + [10.039098] cs35l56 sdw:0:0:01fa:3556:01:0: DSP1: cirrus/cs35l56-b0-dsp1-misc-xxxxxxxx-amp1.bin: v3.11.23 + [10.879235] cs35l56 sdw:0:0:01fa:3556:01:0: Slave 4 state check1: UNATTACHED, status was 1 + [11.401536] cs35l56 sdw:0:0:01fa:3556:01:0: Calibration applied + +HDA +--- +A successful initialization will look like this (this will be repeated for +each amplifier):: + + [ 6.306475] cs35l56-hda i2c-CSC3556:00-cs35l56-hda.0: Cirrus Logic CS35L56 Rev B0 OTP3 fw:3.4.4 (patched=0) + [ 6.613892] cs35l56-hda i2c-CSC3556:00-cs35l56-hda.0: DSP system name: 'xxxxxxxx', amp name: 'AMP1' + [ 8.266660] snd_hda_codec_cs8409 ehdaudio0D0: bound i2c-CSC3556:00-cs35l56-hda.0 (ops cs35l56_hda_comp_ops [snd_hda_scodec_cs35l56]) + [ 8.287525] cs35l56-hda i2c-CSC3556:00-cs35l56-hda.0: DSP1: cirrus/cs35l56-b0-dsp1-misc-xxxxxxxx.wmfw: format 3 timestamp 0x66b2b872 + [ 8.287528] cs35l56-hda i2c-CSC3556:00-cs35l56-hda.0: DSP1: cirrus/cs35l56-b0-dsp1-misc-xxxxxxxx.wmfw: Tue 05 Dec 2023 21:37:21 GMT Standard Time + [ 9.984335] cs35l56-hda i2c-CSC3556:00-cs35l56-hda.0: DSP1: Firmware: 1a00d6 vendor: 0x2 v3.11.23, 41 algorithms + [10.085797] cs35l56-hda i2c-CSC3556:00-cs35l56-hda.0: DSP1: cirrus/cs35l56-b0-dsp1-misc-xxxxxxxx-amp1.bin: v3.11.23 + [10.655237] cs35l56-hda i2c-CSC3556:00-cs35l56-hda.0: Calibration applied + +Important messages +~~~~~~~~~~~~~~~~~~ +Cirrus Logic CS35L56 Rev B0 OTP3 fw:3.4.4 (patched=0) + Shows that the driver has been able to read device ID registers from the + amplifier. + + * The actual amplifier type and silicon revision (CS35L56 B0 in this + example) is shown, as read from the amplifier identification registers. + * (patched=0) is normal, and indicates that the amplifier has been hard + reset and is running default ROM firmware. + * (patched=1) means that something has previously downloaded firmware + to the amplifier and the driver does not have control of the RESET + signal to be able to replace this preloaded firmware. This is normal + for systems where the BIOS downloads firmware to the amplifiers + before OS boot. + This status can also be seen if the cs35l56 kernel module is unloaded + and reloaded on a system where the driver does not have control of + RESET. SoundWire systems typically do not give the driver control of + RESET and only a BIOS (re)boot can reset the amplifiers. + +DSP1: cirrus/cs35l56-b0-dsp1-misc-xxxxxxxx.wmfw + Shows that a .wmfw firmware file was found and downloaded. + +DSP1: cirrus/cs35l56-b0-dsp1-misc-xxxxxxxx-amp1.bin + Shows that a .bin firmware file was found and downloaded. + +Calibration applied + Factory calibration data in EFI was written to the amplifier. + +Error messages +============== +This section explains some of the error messages that the driver can log. + +Algorithm coefficient version %d.%d.%d but expected %d.%d.%d + The version of the .bin file content does not match the loaded firmware. + Caused by mismatched .wmfw and .bin file, or .bin file was found but + .wmfw was not. + +No %s for algorithm %x + The version of the .bin file content does not match the loaded firmware. + Caused by mismatched .wmfw and .bin file, or .bin file was found but + .wmfw was not. + +.bin file required but not found + HDA driver did not find a .bin file that matches this hardware. + +Calibration disabled due to missing firmware controls + Driver was not able to write EFI calibration data to firmware registers. + This typically means that either: + + * The driver did not find a suitable wmfw for this hardware, or + * The amplifier has already been patched with firmware by something + previously, and the driver does not have control of a hard RESET line + to be able to reset the amplifier and download the firmware files it + found. This situation is indicated by the device identification + string in the kernel log shows "(patched=1)" + +Failed to write calibration + Same meaning and cause as "Calibration disabled due to missing firmware + controls" + +Failed to read calibration data from EFI + Factory calibration data in EFI is missing, empty or corrupt. + This is most likely to be cause by accidentally deleting the file from + the EFI filesystem. + +No calibration for silicon ID + The factory calibration data in EFI does not match this hardware. + The most likely cause is that an amplifier has been replaced on the + motherboard without going through manufacturer calibration process to + generate calibration data for the new amplifier. + +Did not find any buses for CSCxxxx + Only on HDA systems. The HDA codec driver found an ACPI entry for + Cirrus Logic companion amps, but could not enumerate the ACPI entries for + the I2C/SPI buses. The most likely cause of this is that: + + * The relevant bus driver (I2C or SPI) is not part of the kernel. + * The HDA codec driver was built-in to the kernel but the I2C/SPI + bus driver is a module and so the HDA codec driver cannot call the + bus driver functions. + +init_completion timed out + The SoundWire bus controller (host end) did not enumerate the amplifier. + In other words, the ACPI says there is an amplifier but for some reason + it was not detected on the bus. + +No AF01 node + Indicates an error in ACPI. A SoundWire system should have a Device() + node named "AF01" but it was not found. + +Failed to get spk-id-gpios + ACPI says that the driver should request a GPIO but the driver was not + able to get that GPIO. The most likely cause is that the kernel does not + include the correct GPIO or PINCTRL driver for this system. + +Failed to read spk-id + ACPI says that the driver should request a GPIO but the driver was not + able to read that GPIO. + +Unexpected spk-id element count + AF01 contains more speaker ID GPIO entries than the driver supports + +Overtemp error + Amplifier overheat protection was triggered and the amplifier shut down + to protect itself. + +Amp short error + Amplifier detected a short-circuit on the speaker output pins and shut + down for protection. This would normally indicate a damaged speaker. + +Hibernate wake failed + The driver tried to wake the amplifier from its power-saving state but + did not see the expected responses from the amplifier. This can be caused + by using firmware that does not match the hardware. diff --git a/Documentation/sound/codecs/index.rst b/Documentation/sound/codecs/index.rst new file mode 100644 index 000000000000..2cb95d87bbef --- /dev/null +++ b/Documentation/sound/codecs/index.rst @@ -0,0 +1,9 @@ +.. SPDX-License-Identifier: GPL-2.0 + +Codec-Specific Information +========================== + +.. toctree:: + :maxdepth: 2 + + cs35l56 diff --git a/Documentation/sound/index.rst b/Documentation/sound/index.rst index c437f2a4bc85..51cd736f65b5 100644 --- a/Documentation/sound/index.rst +++ b/Documentation/sound/index.rst @@ -13,6 +13,7 @@ Sound Subsystem Documentation alsa-configuration hd-audio/index cards/index + codecs/index utimers .. only:: subproject and html diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 454c2aaa155e..f15b61317aad 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -1914,6 +1914,9 @@ No flags are specified so far, the corresponding field must be set to zero. #define KVM_IRQ_ROUTING_HV_SINT 4 #define KVM_IRQ_ROUTING_XEN_EVTCHN 5 +On s390, adding a KVM_IRQ_ROUTING_S390_ADAPTER is rejected on ucontrol VMs with +error -EINVAL. + flags: - KVM_MSI_VALID_DEVID: used along with KVM_IRQ_ROUTING_MSI routing entry diff --git a/Documentation/virt/kvm/devices/s390_flic.rst b/Documentation/virt/kvm/devices/s390_flic.rst index ea96559ba501..b784f8016748 100644 --- a/Documentation/virt/kvm/devices/s390_flic.rst +++ b/Documentation/virt/kvm/devices/s390_flic.rst @@ -58,11 +58,15 @@ Groups: Enables async page faults for the guest. So in case of a major page fault the host is allowed to handle this async and continues the guest. + -EINVAL is returned when called on the FLIC of a ucontrol VM. + KVM_DEV_FLIC_APF_DISABLE_WAIT Disables async page faults for the guest and waits until already pending async page faults are done. This is necessary to trigger a completion interrupt for every init interrupt before migrating the interrupt list. + -EINVAL is returned when called on the FLIC of a ucontrol VM. + KVM_DEV_FLIC_ADAPTER_REGISTER Register an I/O adapter interrupt source. Takes a kvm_s390_io_adapter describing the adapter to register:: diff --git a/MAINTAINERS b/MAINTAINERS index 3f3e289b391c..7b8410b2792a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -951,7 +951,7 @@ M: Arthur Kiyanovski <akiyano@amazon.com> R: David Arinzon <darinzon@amazon.com> R: Saeed Bishara <saeedb@amazon.com> L: netdev@vger.kernel.org -S: Supported +S: Maintained F: Documentation/networking/device_drivers/ethernet/amazon/ena.rst F: drivers/net/ethernet/amazon/ @@ -1124,7 +1124,7 @@ AMD PDS CORE DRIVER M: Shannon Nelson <shannon.nelson@amd.com> M: Brett Creeley <brett.creeley@amd.com> L: netdev@vger.kernel.org -S: Supported +S: Maintained F: Documentation/networking/device_drivers/ethernet/amd/pds_core.rst F: drivers/net/ethernet/amd/pds_core/ F: include/linux/pds/ @@ -1196,7 +1196,7 @@ F: drivers/spi/spi-amd.c AMD XGBE DRIVER M: "Shyam Sundar S K" <Shyam-sundar.S-k@amd.com> L: netdev@vger.kernel.org -S: Supported +S: Maintained F: arch/arm64/boot/dts/amd/amd-seattle-xgbe*.dtsi F: drivers/net/ethernet/amd/xgbe/ @@ -1702,14 +1702,14 @@ F: drivers/edac/xgene_edac.c APPLIED MICRO (APM) X-GENE SOC ETHERNET (V2) DRIVER M: Iyappan Subramanian <iyappan@os.amperecomputing.com> M: Keyur Chudgar <keyur@os.amperecomputing.com> -S: Supported +S: Maintained F: drivers/net/ethernet/apm/xgene-v2/ APPLIED MICRO (APM) X-GENE SOC ETHERNET DRIVER M: Iyappan Subramanian <iyappan@os.amperecomputing.com> M: Keyur Chudgar <keyur@os.amperecomputing.com> M: Quan Nguyen <quan@os.amperecomputing.com> -S: Supported +S: Maintained F: Documentation/devicetree/bindings/net/apm-xgene-enet.txt F: Documentation/devicetree/bindings/net/apm-xgene-mdio.txt F: drivers/net/ethernet/apm/xgene/ @@ -1747,7 +1747,7 @@ F: drivers/hwmon/aquacomputer_d5next.c AQUANTIA ETHERNET DRIVER (atlantic) M: Igor Russkikh <irusskikh@marvell.com> L: netdev@vger.kernel.org -S: Supported +S: Maintained W: https://www.marvell.com/ Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: Documentation/networking/device_drivers/ethernet/aquantia/atlantic.rst @@ -1756,7 +1756,7 @@ F: drivers/net/ethernet/aquantia/atlantic/ AQUANTIA ETHERNET DRIVER PTP SUBSYSTEM M: Egor Pomozov <epomozov@marvell.com> L: netdev@vger.kernel.org -S: Supported +S: Maintained W: http://www.aquantia.com F: drivers/net/ethernet/aquantia/atlantic/aq_ptp* @@ -2291,7 +2291,7 @@ F: arch/arm/mach-highbank/ ARM/CAVIUM THUNDER NETWORK DRIVER M: Sunil Goutham <sgoutham@marvell.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) -S: Supported +S: Maintained F: drivers/net/ethernet/cavium/thunder/ ARM/CIRRUS LOGIC BK3 MACHINE SUPPORT @@ -3666,7 +3666,7 @@ F: include/uapi/linux/sonet.h ATMEL MACB ETHERNET DRIVER M: Nicolas Ferre <nicolas.ferre@microchip.com> M: Claudiu Beznea <claudiu.beznea@tuxon.dev> -S: Supported +S: Maintained F: drivers/net/ethernet/cadence/ ATMEL MAXTOUCH DRIVER @@ -4135,7 +4135,6 @@ S: Odd Fixes F: drivers/net/ethernet/netronome/nfp/bpf/ BPF JIT for POWERPC (32-BIT AND 64-BIT) -M: Michael Ellerman <mpe@ellerman.id.au> M: Hari Bathini <hbathini@linux.ibm.com> M: Christophe Leroy <christophe.leroy@csgroup.eu> R: Naveen N Rao <naveen@kernel.org> @@ -4395,7 +4394,7 @@ F: drivers/net/ethernet/broadcom/asp2/ BROADCOM B44 10/100 ETHERNET DRIVER M: Michael Chan <michael.chan@broadcom.com> L: netdev@vger.kernel.org -S: Supported +S: Maintained F: drivers/net/ethernet/broadcom/b44.* BROADCOM B53/SF2 ETHERNET SWITCH DRIVER @@ -4579,7 +4578,7 @@ BROADCOM BNX2 GIGABIT ETHERNET DRIVER M: Rasesh Mody <rmody@marvell.com> M: GR-Linux-NIC-Dev@marvell.com L: netdev@vger.kernel.org -S: Supported +S: Maintained F: drivers/net/ethernet/broadcom/bnx2.* F: drivers/net/ethernet/broadcom/bnx2_* @@ -4603,14 +4602,14 @@ BROADCOM BNX2X 10 GIGABIT ETHERNET DRIVER M: Sudarsana Kalluru <skalluru@marvell.com> M: Manish Chopra <manishc@marvell.com> L: netdev@vger.kernel.org -S: Supported +S: Maintained F: drivers/net/ethernet/broadcom/bnx2x/ BROADCOM BNXT_EN 50 GIGABIT ETHERNET DRIVER M: Michael Chan <michael.chan@broadcom.com> M: Pavan Chebbi <pavan.chebbi@broadcom.com> L: netdev@vger.kernel.org -S: Supported +S: Maintained F: drivers/firmware/broadcom/tee_bnxt_fw.c F: drivers/net/ethernet/broadcom/bnxt/ F: include/linux/firmware/broadcom/tee_bnxt_fw.h @@ -4706,7 +4705,7 @@ M: Doug Berger <opendmb@gmail.com> M: Florian Fainelli <florian.fainelli@broadcom.com> R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com> L: netdev@vger.kernel.org -S: Supported +S: Maintained F: Documentation/devicetree/bindings/net/brcm,bcmgenet.yaml F: Documentation/devicetree/bindings/net/brcm,unimac-mdio.yaml F: drivers/net/ethernet/broadcom/genet/ @@ -4858,7 +4857,7 @@ BROADCOM SYSTEMPORT ETHERNET DRIVER M: Florian Fainelli <florian.fainelli@broadcom.com> R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com> L: netdev@vger.kernel.org -S: Supported +S: Maintained F: Documentation/devicetree/bindings/net/brcm,systemport.yaml F: drivers/net/ethernet/broadcom/bcmsysport.* F: drivers/net/ethernet/broadcom/unimac.h @@ -4867,7 +4866,7 @@ BROADCOM TG3 GIGABIT ETHERNET DRIVER M: Pavan Chebbi <pavan.chebbi@broadcom.com> M: Michael Chan <mchan@broadcom.com> L: netdev@vger.kernel.org -S: Supported +S: Maintained F: drivers/net/ethernet/broadcom/tg3.* BROADCOM VK DRIVER @@ -4889,7 +4888,7 @@ M: Rasesh Mody <rmody@marvell.com> M: Sudarsana Kalluru <skalluru@marvell.com> M: GR-Linux-NIC-Dev@marvell.com L: netdev@vger.kernel.org -S: Supported +S: Maintained F: drivers/net/ethernet/brocade/bna/ BSG (block layer generic sg v4 driver) @@ -5115,6 +5114,7 @@ F: include/uapi/linux/can/gw.h F: include/uapi/linux/can/isotp.h F: include/uapi/linux/can/raw.h F: net/can/ +F: net/sched/em_canid.c CAN-J1939 NETWORK LAYER M: Robin van der Gracht <robin@protonic.nl> @@ -5474,6 +5474,7 @@ L: linux-sound@vger.kernel.org L: patches@opensource.cirrus.com S: Maintained F: Documentation/devicetree/bindings/sound/cirrus,cs* +F: Documentation/sound/codecs/cs* F: drivers/mfd/cs42l43* F: drivers/pinctrl/cirrus/pinctrl-cs42l43* F: drivers/spi/spi-cs42l43* @@ -5577,7 +5578,7 @@ F: drivers/scsi/snic/ CISCO VIC ETHERNET NIC DRIVER M: Christian Benvenuti <benve@cisco.com> M: Satish Kharat <satishkh@cisco.com> -S: Supported +S: Maintained F: drivers/net/ethernet/cisco/enic/ CISCO VIC LOW LATENCY NIC DRIVER @@ -6175,7 +6176,7 @@ F: drivers/media/dvb-frontends/cxd2820r* CXGB3 ETHERNET DRIVER (CXGB3) M: Potnuri Bharat Teja <bharat@chelsio.com> L: netdev@vger.kernel.org -S: Supported +S: Maintained W: http://www.chelsio.com F: drivers/net/ethernet/chelsio/cxgb3/ @@ -6196,14 +6197,14 @@ F: drivers/crypto/chelsio CXGB4 ETHERNET DRIVER (CXGB4) M: Potnuri Bharat Teja <bharat@chelsio.com> L: netdev@vger.kernel.org -S: Supported +S: Maintained W: http://www.chelsio.com F: drivers/net/ethernet/chelsio/cxgb4/ CXGB4 INLINE CRYPTO DRIVER M: Ayush Sawal <ayush.sawal@chelsio.com> L: netdev@vger.kernel.org -S: Supported +S: Maintained W: http://www.chelsio.com F: drivers/net/ethernet/chelsio/inline_crypto/ @@ -6225,7 +6226,7 @@ F: include/uapi/rdma/cxgb4-abi.h CXGB4VF ETHERNET DRIVER (CXGB4VF) M: Potnuri Bharat Teja <bharat@chelsio.com> L: netdev@vger.kernel.org -S: Supported +S: Maintained W: http://www.chelsio.com F: drivers/net/ethernet/chelsio/cxgb4vf/ @@ -8401,7 +8402,7 @@ M: Ajit Khaparde <ajit.khaparde@broadcom.com> M: Sriharsha Basavapatna <sriharsha.basavapatna@broadcom.com> M: Somnath Kotur <somnath.kotur@broadcom.com> L: netdev@vger.kernel.org -S: Supported +S: Maintained W: http://www.emulex.com F: drivers/net/ethernet/emulex/benet/ @@ -9440,7 +9441,7 @@ F: samples/ftrace FUNGIBLE ETHERNET DRIVERS M: Dimitris Michailidis <dmichail@fungible.com> L: netdev@vger.kernel.org -S: Supported +S: Maintained F: drivers/net/ethernet/fungible/ FUSE: FILESYSTEM IN USERSPACE @@ -9745,7 +9746,7 @@ M: Jeroen de Borst <jeroendb@google.com> M: Praveen Kaligineedi <pkaligineedi@google.com> R: Shailend Chand <shailend@google.com> L: netdev@vger.kernel.org -S: Supported +S: Maintained F: Documentation/networking/device_drivers/ethernet/google/gve.rst F: drivers/net/ethernet/google @@ -10966,7 +10967,7 @@ M: Rick Lindsley <ricklind@linux.ibm.com> R: Nick Child <nnac123@linux.ibm.com> R: Thomas Falcon <tlfalcon@linux.ibm.com> L: netdev@vger.kernel.org -S: Supported +S: Maintained F: drivers/net/ethernet/ibm/ibmvnic.* IBM Power VFIO Support @@ -10977,7 +10978,7 @@ F: drivers/vfio/vfio_iommu_spapr_tce.c IBM Power Virtual Ethernet Device Driver M: Nick Child <nnac123@linux.ibm.com> L: netdev@vger.kernel.org -S: Supported +S: Maintained F: drivers/net/ethernet/ibm/ibmveth.* IBM Power Virtual FC Device Drivers @@ -11510,7 +11511,7 @@ INTEL ETHERNET DRIVERS M: Tony Nguyen <anthony.l.nguyen@intel.com> M: Przemek Kitszel <przemyslaw.kitszel@intel.com> L: intel-wired-lan@lists.osuosl.org (moderated for non-subscribers) -S: Supported +S: Maintained W: https://www.intel.com/content/www/us/en/support.html Q: https://patchwork.ozlabs.org/project/intel-wired-lan/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/net-queue.git @@ -12636,7 +12637,7 @@ F: arch/mips/include/uapi/asm/kvm* F: arch/mips/kvm/ KERNEL VIRTUAL MACHINE FOR POWERPC (KVM/powerpc) -M: Michael Ellerman <mpe@ellerman.id.au> +M: Madhavan Srinivasan <maddy@linux.ibm.com> R: Nicholas Piggin <npiggin@gmail.com> L: linuxppc-dev@lists.ozlabs.org L: kvm@vger.kernel.org @@ -13118,7 +13119,7 @@ LIBETH COMMON ETHERNET LIBRARY M: Alexander Lobakin <aleksander.lobakin@intel.com> L: netdev@vger.kernel.org L: intel-wired-lan@lists.osuosl.org (moderated for non-subscribers) -S: Supported +S: Maintained T: git https://github.com/alobakin/linux.git F: drivers/net/ethernet/intel/libeth/ F: include/net/libeth/ @@ -13128,7 +13129,7 @@ LIBIE COMMON INTEL ETHERNET LIBRARY M: Alexander Lobakin <aleksander.lobakin@intel.com> L: intel-wired-lan@lists.osuosl.org (moderated for non-subscribers) L: netdev@vger.kernel.org -S: Supported +S: Maintained T: git https://github.com/alobakin/linux.git F: drivers/net/ethernet/intel/libie/ F: include/linux/net/intel/libie/ @@ -13215,11 +13216,11 @@ X: drivers/macintosh/adb-iop.c X: drivers/macintosh/via-macii.c LINUX FOR POWERPC (32-BIT AND 64-BIT) +M: Madhavan Srinivasan <maddy@linux.ibm.com> M: Michael Ellerman <mpe@ellerman.id.au> R: Nicholas Piggin <npiggin@gmail.com> R: Christophe Leroy <christophe.leroy@csgroup.eu> R: Naveen N Rao <naveen@kernel.org> -M: Madhavan Srinivasan <maddy@linux.ibm.com> L: linuxppc-dev@lists.ozlabs.org S: Supported W: https://github.com/linuxppc/wiki/wiki @@ -13931,7 +13932,7 @@ MARVELL OCTEON ENDPOINT DRIVER M: Veerasenareddy Burru <vburru@marvell.com> M: Sathesh Edara <sedara@marvell.com> L: netdev@vger.kernel.org -S: Supported +S: Maintained F: drivers/net/ethernet/marvell/octeon_ep MARVELL OCTEON ENDPOINT VF DRIVER @@ -13940,7 +13941,7 @@ M: Sathesh Edara <sedara@marvell.com> M: Shinas Rasheed <srasheed@marvell.com> M: Satananda Burla <sburla@marvell.com> L: netdev@vger.kernel.org -S: Supported +S: Maintained F: drivers/net/ethernet/marvell/octeon_ep_vf MARVELL OCTEONTX2 PHYSICAL FUNCTION DRIVER @@ -13950,7 +13951,7 @@ M: Subbaraya Sundeep <sbhatta@marvell.com> M: hariprasad <hkelam@marvell.com> M: Bharat Bhushan <bbhushan2@marvell.com> L: netdev@vger.kernel.org -S: Supported +S: Maintained F: drivers/net/ethernet/marvell/octeontx2/nic/ F: include/linux/soc/marvell/octeontx2/ @@ -13962,7 +13963,7 @@ M: Jerin Jacob <jerinj@marvell.com> M: hariprasad <hkelam@marvell.com> M: Subbaraya Sundeep <sbhatta@marvell.com> L: netdev@vger.kernel.org -S: Supported +S: Maintained F: Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst F: drivers/net/ethernet/marvell/octeontx2/af/ @@ -14850,7 +14851,7 @@ F: drivers/i2c/busses/i2c-mlxbf.c MELLANOX ETHERNET DRIVER (mlx4_en) M: Tariq Toukan <tariqt@nvidia.com> L: netdev@vger.kernel.org -S: Supported +S: Maintained W: https://www.nvidia.com/networking/ Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: drivers/net/ethernet/mellanox/mlx4/en_* @@ -14859,7 +14860,7 @@ MELLANOX ETHERNET DRIVER (mlx5e) M: Saeed Mahameed <saeedm@nvidia.com> M: Tariq Toukan <tariqt@nvidia.com> L: netdev@vger.kernel.org -S: Supported +S: Maintained W: https://www.nvidia.com/networking/ Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: drivers/net/ethernet/mellanox/mlx5/core/en_* @@ -14867,7 +14868,7 @@ F: drivers/net/ethernet/mellanox/mlx5/core/en_* MELLANOX ETHERNET INNOVA DRIVERS R: Boris Pismenny <borisp@nvidia.com> L: netdev@vger.kernel.org -S: Supported +S: Maintained W: https://www.nvidia.com/networking/ Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: drivers/net/ethernet/mellanox/mlx5/core/en_accel/* @@ -14906,7 +14907,7 @@ MELLANOX MLX4 core VPI driver M: Tariq Toukan <tariqt@nvidia.com> L: netdev@vger.kernel.org L: linux-rdma@vger.kernel.org -S: Supported +S: Maintained W: https://www.nvidia.com/networking/ Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: drivers/net/ethernet/mellanox/mlx4/ @@ -14928,7 +14929,7 @@ M: Leon Romanovsky <leonro@nvidia.com> M: Tariq Toukan <tariqt@nvidia.com> L: netdev@vger.kernel.org L: linux-rdma@vger.kernel.org -S: Supported +S: Maintained W: https://www.nvidia.com/networking/ Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: Documentation/networking/device_drivers/ethernet/mellanox/ @@ -15162,7 +15163,7 @@ META ETHERNET DRIVERS M: Alexander Duyck <alexanderduyck@fb.com> M: Jakub Kicinski <kuba@kernel.org> R: kernel-team@meta.com -S: Supported +S: Maintained F: Documentation/networking/device_drivers/ethernet/meta/ F: drivers/net/ethernet/meta/ @@ -16188,7 +16189,7 @@ F: net/sched/sch_netem.c NETERION 10GbE DRIVERS (s2io) M: Jon Mason <jdmason@kudzu.us> L: netdev@vger.kernel.org -S: Supported +S: Maintained F: Documentation/networking/device_drivers/ethernet/neterion/s2io.rst F: drivers/net/ethernet/neterion/ @@ -16513,7 +16514,7 @@ M: Manish Chopra <manishc@marvell.com> M: Rahul Verma <rahulv@marvell.com> M: GR-Linux-NIC-Dev@marvell.com L: netdev@vger.kernel.org -S: Supported +S: Maintained F: drivers/net/ethernet/qlogic/netxen/ NET_FAILOVER MODULE @@ -18290,7 +18291,7 @@ PENSANDO ETHERNET DRIVERS M: Shannon Nelson <shannon.nelson@amd.com> M: Brett Creeley <brett.creeley@amd.com> L: netdev@vger.kernel.org -S: Supported +S: Maintained F: Documentation/networking/device_drivers/ethernet/pensando/ionic.rst F: drivers/net/ethernet/pensando/ @@ -19057,7 +19058,7 @@ F: drivers/scsi/qedi/ QLOGIC QL4xxx ETHERNET DRIVER M: Manish Chopra <manishc@marvell.com> L: netdev@vger.kernel.org -S: Supported +S: Maintained F: drivers/net/ethernet/qlogic/qed/ F: drivers/net/ethernet/qlogic/qede/ F: include/linux/qed/ @@ -19085,7 +19086,7 @@ F: drivers/scsi/qla2xxx/ QLOGIC QLA3XXX NETWORK DRIVER M: GR-Linux-NIC-Dev@marvell.com L: netdev@vger.kernel.org -S: Supported +S: Maintained F: drivers/net/ethernet/qlogic/qla3xxx.* QLOGIC QLA4XXX iSCSI DRIVER @@ -19101,7 +19102,7 @@ M: Shahed Shaikh <shshaikh@marvell.com> M: Manish Chopra <manishc@marvell.com> M: GR-Linux-NIC-Dev@marvell.com L: netdev@vger.kernel.org -S: Supported +S: Maintained F: drivers/net/ethernet/qlogic/qlcnic/ QM1D1B0004 MEDIA DRIVER @@ -19842,7 +19843,7 @@ M: Paul Barker <paul.barker.ct@bp.renesas.com> M: Niklas Söderlund <niklas.soderlund@ragnatech.se> L: netdev@vger.kernel.org L: linux-renesas-soc@vger.kernel.org -S: Supported +S: Maintained F: Documentation/devicetree/bindings/net/renesas,etheravb.yaml F: drivers/net/ethernet/renesas/Kconfig F: drivers/net/ethernet/renesas/Makefile @@ -19862,7 +19863,7 @@ RENESAS ETHERNET TSN DRIVER M: Niklas Söderlund <niklas.soderlund@ragnatech.se> L: netdev@vger.kernel.org L: linux-renesas-soc@vger.kernel.org -S: Supported +S: Maintained F: Documentation/devicetree/bindings/net/renesas,ethertsn.yaml F: drivers/net/ethernet/renesas/rtsn.* @@ -20012,7 +20013,7 @@ RENESAS SUPERH ETHERNET DRIVER M: Niklas Söderlund <niklas.soderlund@ragnatech.se> L: netdev@vger.kernel.org L: linux-renesas-soc@vger.kernel.org -S: Supported +S: Maintained F: Documentation/devicetree/bindings/net/renesas,ether.yaml F: drivers/net/ethernet/renesas/Kconfig F: drivers/net/ethernet/renesas/Makefile @@ -20855,7 +20856,7 @@ F: include/linux/platform_data/spi-s3c64xx.h SAMSUNG SXGBE DRIVERS M: Byungho An <bh74.an@samsung.com> L: netdev@vger.kernel.org -S: Supported +S: Maintained F: drivers/net/ethernet/samsung/sxgbe/ SAMSUNG THERMAL DRIVER @@ -21257,7 +21258,7 @@ M: Edward Cree <ecree.xilinx@gmail.com> M: Martin Habets <habetsm.xilinx@gmail.com> L: netdev@vger.kernel.org L: linux-net-drivers@amd.com -S: Supported +S: Maintained F: Documentation/networking/devlink/sfc.rst F: drivers/net/ethernet/sfc/ @@ -21999,6 +22000,7 @@ W: https://github.com/thesofproject/linux/ F: sound/soc/sof/ SOUND - GENERIC SOUND CARD (Simple-Audio-Card, Audio-Graph-Card) +M: Mark Brown <broonie@kernel.org> M: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> S: Supported L: linux-sound@vger.kernel.org @@ -22738,7 +22740,7 @@ F: include/linux/platform_data/dma-dw.h SYNOPSYS DESIGNWARE ENTERPRISE ETHERNET DRIVER M: Jose Abreu <Jose.Abreu@synopsys.com> L: netdev@vger.kernel.org -S: Supported +S: Maintained F: drivers/net/ethernet/synopsys/ SYNOPSYS DESIGNWARE ETHERNET XPCS DRIVER @@ -23138,7 +23140,7 @@ F: drivers/phy/tegra/xusb* TEHUTI ETHERNET DRIVER M: Andy Gospodarek <andy@greyhouse.net> L: netdev@vger.kernel.org -S: Supported +S: Maintained F: drivers/net/ethernet/tehuti/tehuti.* TEHUTI TN40XX ETHERNET DRIVER @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 13 SUBLEVEL = 0 -EXTRAVERSION = -rc6 +EXTRAVERSION = -rc7 NAME = Baby Opossum Posse # *DOCUMENTATION* diff --git a/arch/arm/boot/dts/nxp/imx/imxrt1050.dtsi b/arch/arm/boot/dts/nxp/imx/imxrt1050.dtsi index dd714d235d5f..b0bad0d1ba36 100644 --- a/arch/arm/boot/dts/nxp/imx/imxrt1050.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imxrt1050.dtsi @@ -87,7 +87,7 @@ reg = <0x402c0000 0x4000>; interrupts = <110>; clocks = <&clks IMXRT1050_CLK_IPG_PDOF>, - <&clks IMXRT1050_CLK_OSC>, + <&clks IMXRT1050_CLK_AHB_PODF>, <&clks IMXRT1050_CLK_USDHC1>; clock-names = "ipg", "ahb", "per"; bus-width = <4>; diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig index 0beecdde55f5..f25eadcba5e6 100644 --- a/arch/arm/configs/imx_v6_v7_defconfig +++ b/arch/arm/configs/imx_v6_v7_defconfig @@ -323,6 +323,7 @@ CONFIG_SND_SOC_IMX_SGTL5000=y CONFIG_SND_SOC_FSL_ASOC_CARD=y CONFIG_SND_SOC_AC97_CODEC=y CONFIG_SND_SOC_CS42XX8_I2C=y +CONFIG_SND_SOC_SPDIF=y CONFIG_SND_SOC_TLV320AIC3X_I2C=y CONFIG_SND_SOC_WM8960=y CONFIG_SND_SOC_WM8962=y diff --git a/arch/arm64/boot/dts/freescale/imx8-ss-audio.dtsi b/arch/arm64/boot/dts/freescale/imx8-ss-audio.dtsi index a60ebb718789..c32a6947ae9c 100644 --- a/arch/arm64/boot/dts/freescale/imx8-ss-audio.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8-ss-audio.dtsi @@ -165,7 +165,7 @@ audio_subsys: bus@59000000 { }; esai0: esai@59010000 { - compatible = "fsl,imx8qm-esai"; + compatible = "fsl,imx8qm-esai", "fsl,imx6ull-esai"; reg = <0x59010000 0x10000>; interrupts = <GIC_SPI 409 IRQ_TYPE_LEVEL_HIGH>; clocks = <&esai0_lpcg IMX_LPCG_CLK_4>, diff --git a/arch/arm64/boot/dts/freescale/imx8qm-ss-audio.dtsi b/arch/arm64/boot/dts/freescale/imx8qm-ss-audio.dtsi index e24e639b98ee..c9b55f02497a 100644 --- a/arch/arm64/boot/dts/freescale/imx8qm-ss-audio.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8qm-ss-audio.dtsi @@ -134,7 +134,7 @@ }; esai1: esai@59810000 { - compatible = "fsl,imx8qm-esai"; + compatible = "fsl,imx8qm-esai", "fsl,imx6ull-esai"; reg = <0x59810000 0x10000>; interrupts = <GIC_SPI 411 IRQ_TYPE_LEVEL_HIGH>; clocks = <&esai1_lpcg IMX_LPCG_CLK_0>, diff --git a/arch/arm64/boot/dts/freescale/imx95.dtsi b/arch/arm64/boot/dts/freescale/imx95.dtsi index d10f62eacfe0..e9c7a8265d71 100644 --- a/arch/arm64/boot/dts/freescale/imx95.dtsi +++ b/arch/arm64/boot/dts/freescale/imx95.dtsi @@ -1673,7 +1673,7 @@ netcmix_blk_ctrl: syscon@4c810000 { compatible = "nxp,imx95-netcmix-blk-ctrl", "syscon"; - reg = <0x0 0x4c810000 0x0 0x10000>; + reg = <0x0 0x4c810000 0x0 0x8>; #clock-cells = <1>; clocks = <&scmi_clk IMX95_CLK_BUSNETCMIX>; assigned-clocks = <&scmi_clk IMX95_CLK_BUSNETCMIX>; diff --git a/arch/arm64/boot/dts/qcom/sa8775p.dtsi b/arch/arm64/boot/dts/qcom/sa8775p.dtsi index 9f315a51a7c1..9da62d7c4d27 100644 --- a/arch/arm64/boot/dts/qcom/sa8775p.dtsi +++ b/arch/arm64/boot/dts/qcom/sa8775p.dtsi @@ -2440,6 +2440,7 @@ qcom,cmb-element-bits = <32>; qcom,cmb-msrs-num = <32>; + status = "disabled"; out-ports { port { @@ -6092,7 +6093,7 @@ <0x0 0x40000000 0x0 0xf20>, <0x0 0x40000f20 0x0 0xa8>, <0x0 0x40001000 0x0 0x4000>, - <0x0 0x40200000 0x0 0x100000>, + <0x0 0x40200000 0x0 0x1fe00000>, <0x0 0x01c03000 0x0 0x1000>, <0x0 0x40005000 0x0 0x2000>; reg-names = "parf", "dbi", "elbi", "atu", "addr_space", @@ -6250,7 +6251,7 @@ <0x0 0x60000000 0x0 0xf20>, <0x0 0x60000f20 0x0 0xa8>, <0x0 0x60001000 0x0 0x4000>, - <0x0 0x60200000 0x0 0x100000>, + <0x0 0x60200000 0x0 0x1fe00000>, <0x0 0x01c13000 0x0 0x1000>, <0x0 0x60005000 0x0 0x2000>; reg-names = "parf", "dbi", "elbi", "atu", "addr_space", diff --git a/arch/arm64/boot/dts/qcom/x1e78100-lenovo-thinkpad-t14s.dts b/arch/arm64/boot/dts/qcom/x1e78100-lenovo-thinkpad-t14s.dts index 975550139e10..66513fc8e67a 100644 --- a/arch/arm64/boot/dts/qcom/x1e78100-lenovo-thinkpad-t14s.dts +++ b/arch/arm64/boot/dts/qcom/x1e78100-lenovo-thinkpad-t14s.dts @@ -773,6 +773,10 @@ status = "okay"; }; +&usb_1_ss0_dwc3 { + dr_mode = "host"; +}; + &usb_1_ss0_dwc3_hs { remote-endpoint = <&pmic_glink_ss0_hs_in>; }; @@ -801,6 +805,10 @@ status = "okay"; }; +&usb_1_ss1_dwc3 { + dr_mode = "host"; +}; + &usb_1_ss1_dwc3_hs { remote-endpoint = <&pmic_glink_ss1_hs_in>; }; diff --git a/arch/arm64/boot/dts/qcom/x1e80100-crd.dts b/arch/arm64/boot/dts/qcom/x1e80100-crd.dts index 39f9d9cdc10d..d51a9bdcf67f 100644 --- a/arch/arm64/boot/dts/qcom/x1e80100-crd.dts +++ b/arch/arm64/boot/dts/qcom/x1e80100-crd.dts @@ -1197,6 +1197,10 @@ status = "okay"; }; +&usb_1_ss0_dwc3 { + dr_mode = "host"; +}; + &usb_1_ss0_dwc3_hs { remote-endpoint = <&pmic_glink_ss0_hs_in>; }; @@ -1225,6 +1229,10 @@ status = "okay"; }; +&usb_1_ss1_dwc3 { + dr_mode = "host"; +}; + &usb_1_ss1_dwc3_hs { remote-endpoint = <&pmic_glink_ss1_hs_in>; }; @@ -1253,6 +1261,10 @@ status = "okay"; }; +&usb_1_ss2_dwc3 { + dr_mode = "host"; +}; + &usb_1_ss2_dwc3_hs { remote-endpoint = <&pmic_glink_ss2_hs_in>; }; diff --git a/arch/arm64/boot/dts/qcom/x1e80100.dtsi b/arch/arm64/boot/dts/qcom/x1e80100.dtsi index 88805629ed2b..7e4f46ad8edd 100644 --- a/arch/arm64/boot/dts/qcom/x1e80100.dtsi +++ b/arch/arm64/boot/dts/qcom/x1e80100.dtsi @@ -2924,7 +2924,7 @@ #address-cells = <3>; #size-cells = <2>; ranges = <0x01000000 0x0 0x00000000 0x0 0x70200000 0x0 0x100000>, - <0x02000000 0x0 0x70300000 0x0 0x70300000 0x0 0x1d00000>; + <0x02000000 0x0 0x70300000 0x0 0x70300000 0x0 0x3d00000>; bus-range = <0x00 0xff>; dma-coherent; @@ -4066,8 +4066,6 @@ dma-coherent; - usb-role-switch; - ports { #address-cells = <1>; #size-cells = <0>; @@ -4321,8 +4319,6 @@ dma-coherent; - usb-role-switch; - ports { #address-cells = <1>; #size-cells = <0>; @@ -4421,8 +4417,6 @@ dma-coherent; - usb-role-switch; - ports { #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi index 0597de415fe0..7d992c3c01ce 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi @@ -333,6 +333,7 @@ power-domain@RK3328_PD_HEVC { reg = <RK3328_PD_HEVC>; + clocks = <&cru SCLK_VENC_CORE>; #power-domain-cells = <0>; }; power-domain@RK3328_PD_VIDEO { diff --git a/arch/arm64/boot/dts/rockchip/rk3568.dtsi b/arch/arm64/boot/dts/rockchip/rk3568.dtsi index ecaefe208e3e..695cccbdab0f 100644 --- a/arch/arm64/boot/dts/rockchip/rk3568.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3568.dtsi @@ -350,6 +350,7 @@ assigned-clocks = <&pmucru CLK_PCIEPHY0_REF>; assigned-clock-rates = <100000000>; resets = <&cru SRST_PIPEPHY0>; + reset-names = "phy"; rockchip,pipe-grf = <&pipegrf>; rockchip,pipe-phy-grf = <&pipe_phy_grf0>; #phy-cells = <1>; diff --git a/arch/arm64/boot/dts/rockchip/rk356x-base.dtsi b/arch/arm64/boot/dts/rockchip/rk356x-base.dtsi index 62be06f3b863..e55390629114 100644 --- a/arch/arm64/boot/dts/rockchip/rk356x-base.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk356x-base.dtsi @@ -1681,6 +1681,7 @@ assigned-clocks = <&pmucru CLK_PCIEPHY1_REF>; assigned-clock-rates = <100000000>; resets = <&cru SRST_PIPEPHY1>; + reset-names = "phy"; rockchip,pipe-grf = <&pipegrf>; rockchip,pipe-phy-grf = <&pipe_phy_grf1>; #phy-cells = <1>; @@ -1697,6 +1698,7 @@ assigned-clocks = <&pmucru CLK_PCIEPHY2_REF>; assigned-clock-rates = <100000000>; resets = <&cru SRST_PIPEPHY2>; + reset-names = "phy"; rockchip,pipe-grf = <&pipegrf>; rockchip,pipe-phy-grf = <&pipe_phy_grf2>; #phy-cells = <1>; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts b/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts index c44d001da169..d597112f1d5b 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts @@ -72,7 +72,7 @@ rfkill { compatible = "rfkill-gpio"; - label = "rfkill-pcie-wlan"; + label = "rfkill-m2-wlan"; radio-type = "wlan"; shutdown-gpios = <&gpio4 RK_PA2 GPIO_ACTIVE_HIGH>; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-nanopi-r6.dtsi b/arch/arm64/boot/dts/rockchip/rk3588s-nanopi-r6.dtsi index 76a6e8e517e9..c9749cb50076 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588s-nanopi-r6.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3588s-nanopi-r6.dtsi @@ -434,6 +434,7 @@ &sdmmc { bus-width = <4>; cap-sd-highspeed; + cd-gpios = <&gpio0 RK_PA4 GPIO_ACTIVE_LOW>; disable-wp; max-frequency = <150000000>; no-mmc; diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index caba3e4bd09e..e75374d682f4 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -783,9 +783,6 @@ static int hyp_ack_unshare(u64 addr, const struct pkvm_mem_transition *tx) if (tx->initiator.id == PKVM_ID_HOST && hyp_page_count((void *)addr)) return -EBUSY; - if (__hyp_ack_skip_pgtable_check(tx)) - return 0; - return __hyp_check_page_state_range(addr, size, PKVM_PAGE_SHARED_BORROWED); } diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index 456102bc0b55..6c5950b9ceac 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -24,6 +24,7 @@ static DEFINE_MUTEX(arm_pmus_lock); static void kvm_pmu_create_perf_event(struct kvm_pmc *pmc); static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc); +static bool kvm_pmu_counter_is_enabled(struct kvm_pmc *pmc); static struct kvm_vcpu *kvm_pmc_to_vcpu(const struct kvm_pmc *pmc) { @@ -327,48 +328,25 @@ u64 kvm_pmu_implemented_counter_mask(struct kvm_vcpu *vcpu) return GENMASK(val - 1, 0) | BIT(ARMV8_PMU_CYCLE_IDX); } -/** - * kvm_pmu_enable_counter_mask - enable selected PMU counters - * @vcpu: The vcpu pointer - * @val: the value guest writes to PMCNTENSET register - * - * Call perf_event_enable to start counting the perf event - */ -void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val) +static void kvm_pmc_enable_perf_event(struct kvm_pmc *pmc) { - int i; - if (!kvm_vcpu_has_pmu(vcpu)) - return; - - if (!(kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E) || !val) + if (!pmc->perf_event) { + kvm_pmu_create_perf_event(pmc); return; + } - for (i = 0; i < KVM_ARMV8_PMU_MAX_COUNTERS; i++) { - struct kvm_pmc *pmc; - - if (!(val & BIT(i))) - continue; - - pmc = kvm_vcpu_idx_to_pmc(vcpu, i); + perf_event_enable(pmc->perf_event); + if (pmc->perf_event->state != PERF_EVENT_STATE_ACTIVE) + kvm_debug("fail to enable perf event\n"); +} - if (!pmc->perf_event) { - kvm_pmu_create_perf_event(pmc); - } else { - perf_event_enable(pmc->perf_event); - if (pmc->perf_event->state != PERF_EVENT_STATE_ACTIVE) - kvm_debug("fail to enable perf event\n"); - } - } +static void kvm_pmc_disable_perf_event(struct kvm_pmc *pmc) +{ + if (pmc->perf_event) + perf_event_disable(pmc->perf_event); } -/** - * kvm_pmu_disable_counter_mask - disable selected PMU counters - * @vcpu: The vcpu pointer - * @val: the value guest writes to PMCNTENCLR register - * - * Call perf_event_disable to stop counting the perf event - */ -void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val) +void kvm_pmu_reprogram_counter_mask(struct kvm_vcpu *vcpu, u64 val) { int i; @@ -376,16 +354,18 @@ void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val) return; for (i = 0; i < KVM_ARMV8_PMU_MAX_COUNTERS; i++) { - struct kvm_pmc *pmc; + struct kvm_pmc *pmc = kvm_vcpu_idx_to_pmc(vcpu, i); if (!(val & BIT(i))) continue; - pmc = kvm_vcpu_idx_to_pmc(vcpu, i); - - if (pmc->perf_event) - perf_event_disable(pmc->perf_event); + if (kvm_pmu_counter_is_enabled(pmc)) + kvm_pmc_enable_perf_event(pmc); + else + kvm_pmc_disable_perf_event(pmc); } + + kvm_vcpu_pmu_restore_guest(vcpu); } /* @@ -626,27 +606,28 @@ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val) if (!kvm_has_feat(vcpu->kvm, ID_AA64DFR0_EL1, PMUVer, V3P5)) val &= ~ARMV8_PMU_PMCR_LP; + /* Request a reload of the PMU to enable/disable affected counters */ + if ((__vcpu_sys_reg(vcpu, PMCR_EL0) ^ val) & ARMV8_PMU_PMCR_E) + kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu); + /* The reset bits don't indicate any state, and shouldn't be saved. */ __vcpu_sys_reg(vcpu, PMCR_EL0) = val & ~(ARMV8_PMU_PMCR_C | ARMV8_PMU_PMCR_P); - if (val & ARMV8_PMU_PMCR_E) { - kvm_pmu_enable_counter_mask(vcpu, - __vcpu_sys_reg(vcpu, PMCNTENSET_EL0)); - } else { - kvm_pmu_disable_counter_mask(vcpu, - __vcpu_sys_reg(vcpu, PMCNTENSET_EL0)); - } - if (val & ARMV8_PMU_PMCR_C) kvm_pmu_set_counter_value(vcpu, ARMV8_PMU_CYCLE_IDX, 0); if (val & ARMV8_PMU_PMCR_P) { - unsigned long mask = kvm_pmu_accessible_counter_mask(vcpu); - mask &= ~BIT(ARMV8_PMU_CYCLE_IDX); + /* + * Unlike other PMU sysregs, the controls in PMCR_EL0 always apply + * to the 'guest' range of counters and never the 'hyp' range. + */ + unsigned long mask = kvm_pmu_implemented_counter_mask(vcpu) & + ~kvm_pmu_hyp_counter_mask(vcpu) & + ~BIT(ARMV8_PMU_CYCLE_IDX); + for_each_set_bit(i, &mask, 32) kvm_pmu_set_pmc_value(kvm_vcpu_idx_to_pmc(vcpu, i), 0, true); } - kvm_vcpu_pmu_restore_guest(vcpu); } static bool kvm_pmu_counter_is_enabled(struct kvm_pmc *pmc) @@ -910,11 +891,11 @@ void kvm_vcpu_reload_pmu(struct kvm_vcpu *vcpu) { u64 mask = kvm_pmu_implemented_counter_mask(vcpu); - kvm_pmu_handle_pmcr(vcpu, kvm_vcpu_read_pmcr(vcpu)); - __vcpu_sys_reg(vcpu, PMOVSSET_EL0) &= mask; __vcpu_sys_reg(vcpu, PMINTENSET_EL1) &= mask; __vcpu_sys_reg(vcpu, PMCNTENSET_EL0) &= mask; + + kvm_pmu_reprogram_counter_mask(vcpu, mask); } int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu) diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index e2a5c2918d9e..634ff18a59a1 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -1208,16 +1208,14 @@ static bool access_pmcnten(struct kvm_vcpu *vcpu, struct sys_reg_params *p, mask = kvm_pmu_accessible_counter_mask(vcpu); if (p->is_write) { val = p->regval & mask; - if (r->Op2 & 0x1) { + if (r->Op2 & 0x1) /* accessing PMCNTENSET_EL0 */ __vcpu_sys_reg(vcpu, PMCNTENSET_EL0) |= val; - kvm_pmu_enable_counter_mask(vcpu, val); - kvm_vcpu_pmu_restore_guest(vcpu); - } else { + else /* accessing PMCNTENCLR_EL0 */ __vcpu_sys_reg(vcpu, PMCNTENSET_EL0) &= ~val; - kvm_pmu_disable_counter_mask(vcpu, val); - } + + kvm_pmu_reprogram_counter_mask(vcpu, val); } else { p->regval = __vcpu_sys_reg(vcpu, PMCNTENSET_EL0); } @@ -2450,6 +2448,26 @@ static unsigned int s1pie_el2_visibility(const struct kvm_vcpu *vcpu, return __el2_visibility(vcpu, rd, s1pie_visibility); } +static bool access_mdcr(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + u64 old = __vcpu_sys_reg(vcpu, MDCR_EL2); + + if (!access_rw(vcpu, p, r)) + return false; + + /* + * Request a reload of the PMU to enable/disable the counters affected + * by HPME. + */ + if ((old ^ __vcpu_sys_reg(vcpu, MDCR_EL2)) & MDCR_EL2_HPME) + kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu); + + return true; +} + + /* * Architected system registers. * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2 @@ -2983,7 +3001,7 @@ static const struct sys_reg_desc sys_reg_descs[] = { EL2_REG(SCTLR_EL2, access_rw, reset_val, SCTLR_EL2_RES1), EL2_REG(ACTLR_EL2, access_rw, reset_val, 0), EL2_REG_VNCR(HCR_EL2, reset_hcr, 0), - EL2_REG(MDCR_EL2, access_rw, reset_val, 0), + EL2_REG(MDCR_EL2, access_mdcr, reset_val, 0), EL2_REG(CPTR_EL2, access_rw, reset_val, CPTR_NVHE_EL2_RES1), EL2_REG_VNCR(HSTR_EL2, reset_val, 0), EL2_REG_VNCR(HFGRTR_EL2, reset_val, 0), diff --git a/arch/powerpc/kvm/e500.h b/arch/powerpc/kvm/e500.h index 6d0d329cbb35..f9acf866c709 100644 --- a/arch/powerpc/kvm/e500.h +++ b/arch/powerpc/kvm/e500.h @@ -34,6 +34,8 @@ enum vcpu_ftr { #define E500_TLB_BITMAP (1 << 30) /* TLB1 entry is mapped by host TLB0 */ #define E500_TLB_TLB0 (1 << 29) +/* entry is writable on the host */ +#define E500_TLB_WRITABLE (1 << 28) /* bits [6-5] MAS2_X1 and MAS2_X0 and [4-0] bits for WIMGE */ #define E500_TLB_MAS2_ATTR (0x7f) diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c index e5a145b578a4..06caf8bbbe2b 100644 --- a/arch/powerpc/kvm/e500_mmu_host.c +++ b/arch/powerpc/kvm/e500_mmu_host.c @@ -45,11 +45,14 @@ static inline unsigned int tlb1_max_shadow_size(void) return host_tlb_params[1].entries - tlbcam_index - 1; } -static inline u32 e500_shadow_mas3_attrib(u32 mas3, int usermode) +static inline u32 e500_shadow_mas3_attrib(u32 mas3, bool writable, int usermode) { /* Mask off reserved bits. */ mas3 &= MAS3_ATTRIB_MASK; + if (!writable) + mas3 &= ~(MAS3_UW|MAS3_SW); + #ifndef CONFIG_KVM_BOOKE_HV if (!usermode) { /* Guest is in supervisor mode, @@ -242,17 +245,18 @@ static inline int tlbe_is_writable(struct kvm_book3e_206_tlb_entry *tlbe) return tlbe->mas7_3 & (MAS3_SW|MAS3_UW); } -static inline bool kvmppc_e500_ref_setup(struct tlbe_ref *ref, +static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref, struct kvm_book3e_206_tlb_entry *gtlbe, - kvm_pfn_t pfn, unsigned int wimg) + kvm_pfn_t pfn, unsigned int wimg, + bool writable) { ref->pfn = pfn; ref->flags = E500_TLB_VALID; + if (writable) + ref->flags |= E500_TLB_WRITABLE; /* Use guest supplied MAS2_G and MAS2_E */ ref->flags |= (gtlbe->mas2 & MAS2_ATTRIB_MASK) | wimg; - - return tlbe_is_writable(gtlbe); } static inline void kvmppc_e500_ref_release(struct tlbe_ref *ref) @@ -305,6 +309,7 @@ static void kvmppc_e500_setup_stlbe( { kvm_pfn_t pfn = ref->pfn; u32 pr = vcpu->arch.shared->msr & MSR_PR; + bool writable = !!(ref->flags & E500_TLB_WRITABLE); BUG_ON(!(ref->flags & E500_TLB_VALID)); @@ -312,7 +317,7 @@ static void kvmppc_e500_setup_stlbe( stlbe->mas1 = MAS1_TSIZE(tsize) | get_tlb_sts(gtlbe) | MAS1_VALID; stlbe->mas2 = (gvaddr & MAS2_EPN) | (ref->flags & E500_TLB_MAS2_ATTR); stlbe->mas7_3 = ((u64)pfn << PAGE_SHIFT) | - e500_shadow_mas3_attrib(gtlbe->mas7_3, pr); + e500_shadow_mas3_attrib(gtlbe->mas7_3, writable, pr); } static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, @@ -321,15 +326,14 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, struct tlbe_ref *ref) { struct kvm_memory_slot *slot; - unsigned long pfn = 0; /* silence GCC warning */ + unsigned int psize; + unsigned long pfn; struct page *page = NULL; unsigned long hva; - int pfnmap = 0; int tsize = BOOK3E_PAGESZ_4K; int ret = 0; unsigned long mmu_seq; struct kvm *kvm = vcpu_e500->vcpu.kvm; - unsigned long tsize_pages = 0; pte_t *ptep; unsigned int wimg = 0; pgd_t *pgdir; @@ -351,110 +355,12 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, slot = gfn_to_memslot(vcpu_e500->vcpu.kvm, gfn); hva = gfn_to_hva_memslot(slot, gfn); - if (tlbsel == 1) { - struct vm_area_struct *vma; - mmap_read_lock(kvm->mm); - - vma = find_vma(kvm->mm, hva); - if (vma && hva >= vma->vm_start && - (vma->vm_flags & VM_PFNMAP)) { - /* - * This VMA is a physically contiguous region (e.g. - * /dev/mem) that bypasses normal Linux page - * management. Find the overlap between the - * vma and the memslot. - */ - - unsigned long start, end; - unsigned long slot_start, slot_end; - - pfnmap = 1; - - start = vma->vm_pgoff; - end = start + - vma_pages(vma); - - pfn = start + ((hva - vma->vm_start) >> PAGE_SHIFT); - - slot_start = pfn - (gfn - slot->base_gfn); - slot_end = slot_start + slot->npages; - - if (start < slot_start) - start = slot_start; - if (end > slot_end) - end = slot_end; - - tsize = (gtlbe->mas1 & MAS1_TSIZE_MASK) >> - MAS1_TSIZE_SHIFT; - - /* - * e500 doesn't implement the lowest tsize bit, - * or 1K pages. - */ - tsize = max(BOOK3E_PAGESZ_4K, tsize & ~1); - - /* - * Now find the largest tsize (up to what the guest - * requested) that will cover gfn, stay within the - * range, and for which gfn and pfn are mutually - * aligned. - */ - - for (; tsize > BOOK3E_PAGESZ_4K; tsize -= 2) { - unsigned long gfn_start, gfn_end; - tsize_pages = 1UL << (tsize - 2); - - gfn_start = gfn & ~(tsize_pages - 1); - gfn_end = gfn_start + tsize_pages; - - if (gfn_start + pfn - gfn < start) - continue; - if (gfn_end + pfn - gfn > end) - continue; - if ((gfn & (tsize_pages - 1)) != - (pfn & (tsize_pages - 1))) - continue; - - gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1); - pfn &= ~(tsize_pages - 1); - break; - } - } else if (vma && hva >= vma->vm_start && - is_vm_hugetlb_page(vma)) { - unsigned long psize = vma_kernel_pagesize(vma); - - tsize = (gtlbe->mas1 & MAS1_TSIZE_MASK) >> - MAS1_TSIZE_SHIFT; - - /* - * Take the largest page size that satisfies both host - * and guest mapping - */ - tsize = min(__ilog2(psize) - 10, tsize); - - /* - * e500 doesn't implement the lowest tsize bit, - * or 1K pages. - */ - tsize = max(BOOK3E_PAGESZ_4K, tsize & ~1); - } - - mmap_read_unlock(kvm->mm); - } - - if (likely(!pfnmap)) { - tsize_pages = 1UL << (tsize + 10 - PAGE_SHIFT); - pfn = __kvm_faultin_pfn(slot, gfn, FOLL_WRITE, NULL, &page); - if (is_error_noslot_pfn(pfn)) { - if (printk_ratelimit()) - pr_err("%s: real page not found for gfn %lx\n", - __func__, (long)gfn); - return -EINVAL; - } - - /* Align guest and physical address to page map boundaries */ - pfn &= ~(tsize_pages - 1); - gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1); + pfn = __kvm_faultin_pfn(slot, gfn, FOLL_WRITE, &writable, &page); + if (is_error_noslot_pfn(pfn)) { + if (printk_ratelimit()) + pr_err("%s: real page not found for gfn %lx\n", + __func__, (long)gfn); + return -EINVAL; } spin_lock(&kvm->mmu_lock); @@ -472,14 +378,13 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, * can't run hence pfn won't change. */ local_irq_save(flags); - ptep = find_linux_pte(pgdir, hva, NULL, NULL); + ptep = find_linux_pte(pgdir, hva, NULL, &psize); if (ptep) { pte_t pte = READ_ONCE(*ptep); if (pte_present(pte)) { wimg = (pte_val(pte) >> PTE_WIMGE_SHIFT) & MAS2_WIMGE_MASK; - local_irq_restore(flags); } else { local_irq_restore(flags); pr_err_ratelimited("%s: pte not present: gfn %lx,pfn %lx\n", @@ -488,10 +393,72 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, goto out; } } - writable = kvmppc_e500_ref_setup(ref, gtlbe, pfn, wimg); + local_irq_restore(flags); + + if (psize && tlbsel == 1) { + unsigned long psize_pages, tsize_pages; + unsigned long start, end; + unsigned long slot_start, slot_end; + + psize_pages = 1UL << (psize - PAGE_SHIFT); + start = pfn & ~(psize_pages - 1); + end = start + psize_pages; + + slot_start = pfn - (gfn - slot->base_gfn); + slot_end = slot_start + slot->npages; + + if (start < slot_start) + start = slot_start; + if (end > slot_end) + end = slot_end; + + tsize = (gtlbe->mas1 & MAS1_TSIZE_MASK) >> + MAS1_TSIZE_SHIFT; + + /* + * Any page size that doesn't satisfy the host mapping + * will fail the start and end tests. + */ + tsize = min(psize - PAGE_SHIFT + BOOK3E_PAGESZ_4K, tsize); + + /* + * e500 doesn't implement the lowest tsize bit, + * or 1K pages. + */ + tsize = max(BOOK3E_PAGESZ_4K, tsize & ~1); + + /* + * Now find the largest tsize (up to what the guest + * requested) that will cover gfn, stay within the + * range, and for which gfn and pfn are mutually + * aligned. + */ + + for (; tsize > BOOK3E_PAGESZ_4K; tsize -= 2) { + unsigned long gfn_start, gfn_end; + tsize_pages = 1UL << (tsize - 2); + + gfn_start = gfn & ~(tsize_pages - 1); + gfn_end = gfn_start + tsize_pages; + + if (gfn_start + pfn - gfn < start) + continue; + if (gfn_end + pfn - gfn > end) + continue; + if ((gfn & (tsize_pages - 1)) != + (pfn & (tsize_pages - 1))) + continue; + + gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1); + pfn &= ~(tsize_pages - 1); + break; + } + } + kvmppc_e500_ref_setup(ref, gtlbe, pfn, wimg, writable); kvmppc_e500_setup_stlbe(&vcpu_e500->vcpu, gtlbe, tsize, ref, gvaddr, stlbe); + writable = tlbe_is_writable(stlbe); /* Clear i-cache for new pages */ kvmppc_mmu_flush_icache(pfn); diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h index 71aabc5c6713..125f5ecd9565 100644 --- a/arch/riscv/include/asm/page.h +++ b/arch/riscv/include/asm/page.h @@ -122,6 +122,7 @@ struct kernel_mapping { extern struct kernel_mapping kernel_map; extern phys_addr_t phys_ram_base; +extern unsigned long vmemmap_start_pfn; #define is_kernel_mapping(x) \ ((x) >= kernel_map.virt_addr && (x) < (kernel_map.virt_addr + kernel_map.size)) diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index d4e99eef90ac..050fdc49b5ad 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -87,7 +87,7 @@ * Define vmemmap for pfn_to_page & page_to_pfn calls. Needed if kernel * is configured with CONFIG_SPARSEMEM_VMEMMAP enabled. */ -#define vmemmap ((struct page *)VMEMMAP_START - (phys_ram_base >> PAGE_SHIFT)) +#define vmemmap ((struct page *)VMEMMAP_START - vmemmap_start_pfn) #define PCI_IO_SIZE SZ_16M #define PCI_IO_END VMEMMAP_START diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h index 6c82318065cf..3d250824178b 100644 --- a/arch/riscv/include/asm/sbi.h +++ b/arch/riscv/include/asm/sbi.h @@ -159,6 +159,7 @@ struct riscv_pmu_snapshot_data { }; #define RISCV_PMU_RAW_EVENT_MASK GENMASK_ULL(47, 0) +#define RISCV_PMU_PLAT_FW_EVENT_MASK GENMASK_ULL(61, 0) #define RISCV_PMU_RAW_EVENT_IDX 0x20000 #define RISCV_PLAT_FW_EVENT 0xFFFF diff --git a/arch/riscv/include/asm/spinlock.h b/arch/riscv/include/asm/spinlock.h index e5121b89acea..52f11bfd0079 100644 --- a/arch/riscv/include/asm/spinlock.h +++ b/arch/riscv/include/asm/spinlock.h @@ -3,8 +3,11 @@ #ifndef __ASM_RISCV_SPINLOCK_H #define __ASM_RISCV_SPINLOCK_H -#ifdef CONFIG_RISCV_COMBO_SPINLOCKS +#ifdef CONFIG_QUEUED_SPINLOCKS #define _Q_PENDING_LOOPS (1 << 9) +#endif + +#ifdef CONFIG_RISCV_COMBO_SPINLOCKS #define __no_arch_spinlock_redefine #include <asm/ticket_spinlock.h> diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index c200d329d4bd..33a5a9f2a0d4 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -23,21 +23,21 @@ REG_S a0, TASK_TI_A0(tp) csrr a0, CSR_CAUSE /* Exclude IRQs */ - blt a0, zero, _new_vmalloc_restore_context_a0 + blt a0, zero, .Lnew_vmalloc_restore_context_a0 REG_S a1, TASK_TI_A1(tp) /* Only check new_vmalloc if we are in page/protection fault */ li a1, EXC_LOAD_PAGE_FAULT - beq a0, a1, _new_vmalloc_kernel_address + beq a0, a1, .Lnew_vmalloc_kernel_address li a1, EXC_STORE_PAGE_FAULT - beq a0, a1, _new_vmalloc_kernel_address + beq a0, a1, .Lnew_vmalloc_kernel_address li a1, EXC_INST_PAGE_FAULT - bne a0, a1, _new_vmalloc_restore_context_a1 + bne a0, a1, .Lnew_vmalloc_restore_context_a1 -_new_vmalloc_kernel_address: +.Lnew_vmalloc_kernel_address: /* Is it a kernel address? */ csrr a0, CSR_TVAL - bge a0, zero, _new_vmalloc_restore_context_a1 + bge a0, zero, .Lnew_vmalloc_restore_context_a1 /* Check if a new vmalloc mapping appeared that could explain the trap */ REG_S a2, TASK_TI_A2(tp) @@ -69,7 +69,7 @@ _new_vmalloc_kernel_address: /* Check the value of new_vmalloc for this cpu */ REG_L a2, 0(a0) and a2, a2, a1 - beq a2, zero, _new_vmalloc_restore_context + beq a2, zero, .Lnew_vmalloc_restore_context /* Atomically reset the current cpu bit in new_vmalloc */ amoxor.d a0, a1, (a0) @@ -83,11 +83,11 @@ _new_vmalloc_kernel_address: csrw CSR_SCRATCH, x0 sret -_new_vmalloc_restore_context: +.Lnew_vmalloc_restore_context: REG_L a2, TASK_TI_A2(tp) -_new_vmalloc_restore_context_a1: +.Lnew_vmalloc_restore_context_a1: REG_L a1, TASK_TI_A1(tp) -_new_vmalloc_restore_context_a0: +.Lnew_vmalloc_restore_context_a0: REG_L a0, TASK_TI_A0(tp) .endm @@ -278,6 +278,7 @@ SYM_CODE_START_NOALIGN(ret_from_exception) #else sret #endif +SYM_INNER_LABEL(ret_from_exception_end, SYM_L_GLOBAL) SYM_CODE_END(ret_from_exception) ASM_NOKPROBE(ret_from_exception) diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c index 1cd461f3d872..47d0ebeec93c 100644 --- a/arch/riscv/kernel/module.c +++ b/arch/riscv/kernel/module.c @@ -23,7 +23,7 @@ struct used_bucket { struct relocation_head { struct hlist_node node; - struct list_head *rel_entry; + struct list_head rel_entry; void *location; }; @@ -634,7 +634,7 @@ process_accumulated_relocations(struct module *me, location = rel_head_iter->location; list_for_each_entry_safe(rel_entry_iter, rel_entry_iter_tmp, - rel_head_iter->rel_entry, + &rel_head_iter->rel_entry, head) { curr_type = rel_entry_iter->type; reloc_handlers[curr_type].reloc_handler( @@ -704,16 +704,7 @@ static int add_relocation_to_accumulate(struct module *me, int type, return -ENOMEM; } - rel_head->rel_entry = - kmalloc(sizeof(struct list_head), GFP_KERNEL); - - if (!rel_head->rel_entry) { - kfree(entry); - kfree(rel_head); - return -ENOMEM; - } - - INIT_LIST_HEAD(rel_head->rel_entry); + INIT_LIST_HEAD(&rel_head->rel_entry); rel_head->location = location; INIT_HLIST_NODE(&rel_head->node); if (!current_head->first) { @@ -722,7 +713,6 @@ static int add_relocation_to_accumulate(struct module *me, int type, if (!bucket) { kfree(entry); - kfree(rel_head->rel_entry); kfree(rel_head); return -ENOMEM; } @@ -735,7 +725,7 @@ static int add_relocation_to_accumulate(struct module *me, int type, } /* Add relocation to head of discovered rel_head */ - list_add_tail(&entry->head, rel_head->rel_entry); + list_add_tail(&entry->head, &rel_head->rel_entry); return 0; } diff --git a/arch/riscv/kernel/probes/kprobes.c b/arch/riscv/kernel/probes/kprobes.c index 380a0e8cecc0..c0738d6c6498 100644 --- a/arch/riscv/kernel/probes/kprobes.c +++ b/arch/riscv/kernel/probes/kprobes.c @@ -30,7 +30,7 @@ static void __kprobes arch_prepare_ss_slot(struct kprobe *p) p->ainsn.api.restore = (unsigned long)p->addr + len; patch_text_nosync(p->ainsn.api.insn, &p->opcode, len); - patch_text_nosync(p->ainsn.api.insn + len, &insn, GET_INSN_LENGTH(insn)); + patch_text_nosync((void *)p->ainsn.api.insn + len, &insn, GET_INSN_LENGTH(insn)); } static void __kprobes arch_prepare_simulate(struct kprobe *p) diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index 153a2db4c5fa..d4355c770c36 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -17,6 +17,7 @@ #ifdef CONFIG_FRAME_POINTER extern asmlinkage void handle_exception(void); +extern unsigned long ret_from_exception_end; static inline int fp_is_valid(unsigned long fp, unsigned long sp) { @@ -71,7 +72,8 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, fp = frame->fp; pc = ftrace_graph_ret_addr(current, &graph_idx, frame->ra, &frame->ra); - if (pc == (unsigned long)handle_exception) { + if (pc >= (unsigned long)handle_exception && + pc < (unsigned long)&ret_from_exception_end) { if (unlikely(!__kernel_text_address(pc) || !fn(arg, pc))) break; diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index 51ebfd23e007..8ff8e8b36524 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -35,7 +35,7 @@ int show_unhandled_signals = 1; -static DEFINE_SPINLOCK(die_lock); +static DEFINE_RAW_SPINLOCK(die_lock); static int copy_code(struct pt_regs *regs, u16 *val, const u16 *insns) { @@ -81,7 +81,7 @@ void die(struct pt_regs *regs, const char *str) oops_enter(); - spin_lock_irqsave(&die_lock, flags); + raw_spin_lock_irqsave(&die_lock, flags); console_verbose(); bust_spinlocks(1); @@ -100,7 +100,7 @@ void die(struct pt_regs *regs, const char *str) bust_spinlocks(0); add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE); - spin_unlock_irqrestore(&die_lock, flags); + raw_spin_unlock_irqrestore(&die_lock, flags); oops_exit(); if (in_interrupt()) diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index fc53ce748c80..8d167e09f1fe 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -33,6 +33,7 @@ #include <asm/pgtable.h> #include <asm/sections.h> #include <asm/soc.h> +#include <asm/sparsemem.h> #include <asm/tlbflush.h> #include "../kernel/head.h" @@ -62,6 +63,13 @@ EXPORT_SYMBOL(pgtable_l5_enabled); phys_addr_t phys_ram_base __ro_after_init; EXPORT_SYMBOL(phys_ram_base); +#ifdef CONFIG_SPARSEMEM_VMEMMAP +#define VMEMMAP_ADDR_ALIGN (1ULL << SECTION_SIZE_BITS) + +unsigned long vmemmap_start_pfn __ro_after_init; +EXPORT_SYMBOL(vmemmap_start_pfn); +#endif + unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss; EXPORT_SYMBOL(empty_zero_page); @@ -240,8 +248,12 @@ static void __init setup_bootmem(void) * Make sure we align the start of the memory on a PMD boundary so that * at worst, we map the linear mapping with PMD mappings. */ - if (!IS_ENABLED(CONFIG_XIP_KERNEL)) + if (!IS_ENABLED(CONFIG_XIP_KERNEL)) { phys_ram_base = memblock_start_of_DRAM() & PMD_MASK; +#ifdef CONFIG_SPARSEMEM_VMEMMAP + vmemmap_start_pfn = round_down(phys_ram_base, VMEMMAP_ADDR_ALIGN) >> PAGE_SHIFT; +#endif + } /* * In 64-bit, any use of __va/__pa before this point is wrong as we @@ -1101,6 +1113,9 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) kernel_map.xiprom_sz = (uintptr_t)(&_exiprom) - (uintptr_t)(&_xiprom); phys_ram_base = CONFIG_PHYS_RAM_BASE; +#ifdef CONFIG_SPARSEMEM_VMEMMAP + vmemmap_start_pfn = round_down(phys_ram_base, VMEMMAP_ADDR_ALIGN) >> PAGE_SHIFT; +#endif kernel_map.phys_addr = (uintptr_t)CONFIG_PHYS_RAM_BASE; kernel_map.size = (uintptr_t)(&_end) - (uintptr_t)(&_start); diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index ea8dce299954..d4f031e086fc 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -2678,9 +2678,13 @@ static int flic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr) kvm_s390_clear_float_irqs(dev->kvm); break; case KVM_DEV_FLIC_APF_ENABLE: + if (kvm_is_ucontrol(dev->kvm)) + return -EINVAL; dev->kvm->arch.gmap->pfault_enabled = 1; break; case KVM_DEV_FLIC_APF_DISABLE_WAIT: + if (kvm_is_ucontrol(dev->kvm)) + return -EINVAL; dev->kvm->arch.gmap->pfault_enabled = 0; /* * Make sure no async faults are in transition when @@ -2894,6 +2898,8 @@ int kvm_set_routing_entry(struct kvm *kvm, switch (ue->type) { /* we store the userspace addresses instead of the guest addresses */ case KVM_IRQ_ROUTING_S390_ADAPTER: + if (kvm_is_ucontrol(kvm)) + return -EINVAL; e->set = set_adapter_int; uaddr = gmap_translate(kvm->arch.gmap, ue->u.adapter.summary_addr); if (uaddr == -EFAULT) diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index 150b9387860a..a687695d8f68 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -854,7 +854,7 @@ unpin: static void unpin_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page, gpa_t gpa) { - hpa_t hpa = (hpa_t) vsie_page->scb_o; + hpa_t hpa = virt_to_phys(vsie_page->scb_o); if (hpa) unpin_guest_page(vcpu->kvm, gpa, hpa); diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index 6bc1eb2a21bd..887b0b8e21e3 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -190,7 +190,8 @@ int ssp_get(struct task_struct *target, const struct user_regset *regset, struct fpu *fpu = &target->thread.fpu; struct cet_user_state *cetregs; - if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK)) + if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK) || + !ssp_active(target, regset)) return -ENODEV; sync_fpstate(fpu); diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c index 9eed0c144dad..9e51242ed125 100644 --- a/arch/x86/kernel/static_call.c +++ b/arch/x86/kernel/static_call.c @@ -175,7 +175,6 @@ EXPORT_SYMBOL_GPL(arch_static_call_transform); noinstr void __static_call_update_early(void *tramp, void *func) { BUG_ON(system_state != SYSTEM_BOOTING); - BUG_ON(!early_boot_irqs_disabled); BUG_ON(static_call_initialized); __text_gen_insn(tramp, JMP32_INSN_OPCODE, tramp, func, JMP32_INSN_SIZE); sync_core(); diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index c6d29f283001..62aa4d66a032 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -1080,7 +1080,8 @@ struct execmem_info __init *execmem_arch_setup(void) start = MODULES_VADDR + offset; - if (IS_ENABLED(CONFIG_ARCH_HAS_EXECMEM_ROX)) { + if (IS_ENABLED(CONFIG_ARCH_HAS_EXECMEM_ROX) && + cpu_feature_enabled(X86_FEATURE_PSE)) { pgprot = PAGE_KERNEL_ROX; flags = EXECMEM_KASAN_SHADOW | EXECMEM_ROX_CACHE; } else { diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 95dd7b795935..cad16c163611 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -6844,16 +6844,24 @@ static struct bfq_queue *bfq_waker_bfqq(struct bfq_queue *bfqq) if (new_bfqq == waker_bfqq) { /* * If waker_bfqq is in the merge chain, and current - * is the only procress. + * is the only process, waker_bfqq can be freed. */ if (bfqq_process_refs(waker_bfqq) == 1) return NULL; - break; + + return waker_bfqq; } new_bfqq = new_bfqq->new_bfqq; } + /* + * If waker_bfqq is not in the merge chain, and it's procress reference + * is 0, waker_bfqq can be freed. + */ + if (bfqq_process_refs(waker_bfqq) == 0) + return NULL; + return waker_bfqq; } diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c index 8274a17872ed..a972831dbd66 100644 --- a/drivers/acpi/acpi_video.c +++ b/drivers/acpi/acpi_video.c @@ -610,16 +610,28 @@ acpi_video_device_lcd_get_level_current(struct acpi_video_device *device, return 0; } +/** + * acpi_video_device_EDID() - Get EDID from ACPI _DDC + * @device: video output device (LCD, CRT, ..) + * @edid: address for returned EDID pointer + * @length: _DDC length to request (must be a multiple of 128) + * + * Get EDID from ACPI _DDC. On success, a pointer to the EDID data is written + * to the @edid address, and the length of the EDID is returned. The caller is + * responsible for freeing the edid pointer. + * + * Return the length of EDID (positive value) on success or error (negative + * value). + */ static int -acpi_video_device_EDID(struct acpi_video_device *device, - union acpi_object **edid, int length) +acpi_video_device_EDID(struct acpi_video_device *device, void **edid, int length) { - int status; + acpi_status status; struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; union acpi_object *obj; union acpi_object arg0 = { ACPI_TYPE_INTEGER }; struct acpi_object_list args = { 1, &arg0 }; - + int ret; *edid = NULL; @@ -636,16 +648,17 @@ acpi_video_device_EDID(struct acpi_video_device *device, obj = buffer.pointer; - if (obj && obj->type == ACPI_TYPE_BUFFER) - *edid = obj; - else { + if (obj && obj->type == ACPI_TYPE_BUFFER) { + *edid = kmemdup(obj->buffer.pointer, obj->buffer.length, GFP_KERNEL); + ret = *edid ? obj->buffer.length : -ENOMEM; + } else { acpi_handle_debug(device->dev->handle, "Invalid _DDC data for length %d\n", length); - status = -EFAULT; - kfree(obj); + ret = -EFAULT; } - return status; + kfree(obj); + return ret; } /* bus */ @@ -1435,9 +1448,7 @@ int acpi_video_get_edid(struct acpi_device *device, int type, int device_id, { struct acpi_video_bus *video; struct acpi_video_device *video_device; - union acpi_object *buffer = NULL; - acpi_status status; - int i, length; + int i, length, ret; if (!device || !acpi_driver_data(device)) return -EINVAL; @@ -1477,16 +1488,10 @@ int acpi_video_get_edid(struct acpi_device *device, int type, int device_id, } for (length = 512; length > 0; length -= 128) { - status = acpi_video_device_EDID(video_device, &buffer, - length); - if (ACPI_SUCCESS(status)) - break; + ret = acpi_video_device_EDID(video_device, edid, length); + if (ret > 0) + return ret; } - if (!length) - continue; - - *edid = buffer->buffer.pointer; - return length; } return -ENODEV; diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index 821867de43be..90aaec923889 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -441,6 +441,13 @@ static const struct dmi_system_id irq1_level_low_skip_override[] = { }, }, { + /* Asus Vivobook X1504VAP */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_BOARD_NAME, "X1504VAP"), + }, + }, + { /* Asus Vivobook X1704VAP */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), @@ -646,6 +653,17 @@ static const struct dmi_system_id irq1_edge_low_force_override[] = { DMI_MATCH(DMI_BOARD_NAME, "GMxHGxx"), }, }, + { + /* + * TongFang GM5HG0A in case of the SKIKK Vanaheim relabel the + * board-name is changed, so check OEM strings instead. Note + * OEM string matches are always exact matches. + * https://bugzilla.kernel.org/show_bug.cgi?id=219614 + */ + .matches = { + DMI_EXACT_MATCH(DMI_OEM_STRING, "GM5HG0A"), + }, + }, { } }; @@ -671,11 +689,11 @@ static bool acpi_dev_irq_override(u32 gsi, u8 triggering, u8 polarity, for (i = 0; i < ARRAY_SIZE(override_table); i++) { const struct irq_override_cmp *entry = &override_table[i]; - if (dmi_check_system(entry->system) && - entry->irq == gsi && + if (entry->irq == gsi && entry->triggering == triggering && entry->polarity == polarity && - entry->shareable == shareable) + entry->shareable == shareable && + dmi_check_system(entry->system)) return entry->override; } diff --git a/drivers/base/topology.c b/drivers/base/topology.c index cf160dd2c27b..b962da263eee 100644 --- a/drivers/base/topology.c +++ b/drivers/base/topology.c @@ -27,9 +27,17 @@ static ssize_t name##_read(struct file *file, struct kobject *kobj, \ loff_t off, size_t count) \ { \ struct device *dev = kobj_to_dev(kobj); \ + cpumask_var_t mask; \ + ssize_t n; \ \ - return cpumap_print_bitmask_to_buf(buf, topology_##mask(dev->id), \ - off, count); \ + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) \ + return -ENOMEM; \ + \ + cpumask_copy(mask, topology_##mask(dev->id)); \ + n = cpumap_print_bitmask_to_buf(buf, mask, off, count); \ + free_cpumask_var(mask); \ + \ + return n; \ } \ \ static ssize_t name##_list_read(struct file *file, struct kobject *kobj, \ @@ -37,9 +45,17 @@ static ssize_t name##_list_read(struct file *file, struct kobject *kobj, \ loff_t off, size_t count) \ { \ struct device *dev = kobj_to_dev(kobj); \ + cpumask_var_t mask; \ + ssize_t n; \ + \ + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) \ + return -ENOMEM; \ + \ + cpumask_copy(mask, topology_##mask(dev->id)); \ + n = cpumap_print_list_to_buf(buf, mask, off, count); \ + free_cpumask_var(mask); \ \ - return cpumap_print_list_to_buf(buf, topology_##mask(dev->id), \ - off, count); \ + return n; \ } define_id_show_func(physical_package_id, "%d"); diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 45df5eeabc5e..7903a4da40ac 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1468,6 +1468,7 @@ static bool zram_meta_alloc(struct zram *zram, u64 disksize) zram->mem_pool = zs_create_pool(zram->disk->disk_name); if (!zram->mem_pool) { vfree(zram->table); + zram->table = NULL; return false; } diff --git a/drivers/bus/mhi/host/pci_generic.c b/drivers/bus/mhi/host/pci_generic.c index 07645ce2119a..56ba4192c89c 100644 --- a/drivers/bus/mhi/host/pci_generic.c +++ b/drivers/bus/mhi/host/pci_generic.c @@ -917,7 +917,7 @@ static int mhi_pci_claim(struct mhi_controller *mhi_cntrl, return err; } - mhi_cntrl->regs = pcim_iomap_region(pdev, 1 << bar_num, pci_name(pdev)); + mhi_cntrl->regs = pcim_iomap_region(pdev, bar_num, pci_name(pdev)); if (IS_ERR(mhi_cntrl->regs)) { err = PTR_ERR(mhi_cntrl->regs); dev_err(&pdev->dev, "failed to map pci region: %d\n", err); diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig index 92a83a9bb2e1..26e98fea991a 100644 --- a/drivers/cpufreq/Kconfig +++ b/drivers/cpufreq/Kconfig @@ -325,8 +325,6 @@ config QORIQ_CPUFREQ This adds the CPUFreq driver support for Freescale QorIQ SoCs which are capable of changing the CPU's frequency dynamically. -endif - config ACPI_CPPC_CPUFREQ tristate "CPUFreq driver based on the ACPI CPPC spec" depends on ACPI_PROCESSOR @@ -355,4 +353,6 @@ config ACPI_CPPC_CPUFREQ_FIE If in doubt, say N. +endif + endmenu diff --git a/drivers/cpuidle/cpuidle-riscv-sbi.c b/drivers/cpuidle/cpuidle-riscv-sbi.c index 14462c092039..0c92a628bbd4 100644 --- a/drivers/cpuidle/cpuidle-riscv-sbi.c +++ b/drivers/cpuidle/cpuidle-riscv-sbi.c @@ -504,12 +504,12 @@ static int sbi_cpuidle_probe(struct platform_device *pdev) int cpu, ret; struct cpuidle_driver *drv; struct cpuidle_device *dev; - struct device_node *np, *pds_node; + struct device_node *pds_node; /* Detect OSI support based on CPU DT nodes */ sbi_cpuidle_use_osi = true; for_each_possible_cpu(cpu) { - np = of_cpu_device_node_get(cpu); + struct device_node *np __free(device_node) = of_cpu_device_node_get(cpu); if (np && of_property_present(np, "power-domains") && of_property_present(np, "power-domain-names")) { diff --git a/drivers/cpuidle/governors/teo.c b/drivers/cpuidle/governors/teo.c index f2992f92d8db..173ddcac540a 100644 --- a/drivers/cpuidle/governors/teo.c +++ b/drivers/cpuidle/governors/teo.c @@ -10,25 +10,27 @@ * DOC: teo-description * * The idea of this governor is based on the observation that on many systems - * timer events are two or more orders of magnitude more frequent than any - * other interrupts, so they are likely to be the most significant cause of CPU - * wakeups from idle states. Moreover, information about what happened in the - * (relatively recent) past can be used to estimate whether or not the deepest - * idle state with target residency within the (known) time till the closest - * timer event, referred to as the sleep length, is likely to be suitable for - * the upcoming CPU idle period and, if not, then which of the shallower idle - * states to choose instead of it. + * timer interrupts are two or more orders of magnitude more frequent than any + * other interrupt types, so they are likely to dominate CPU wakeup patterns. + * Moreover, in principle, the time when the next timer event is going to occur + * can be determined at the idle state selection time, although doing that may + * be costly, so it can be regarded as the most reliable source of information + * for idle state selection. * - * Of course, non-timer wakeup sources are more important in some use cases - * which can be covered by taking a few most recent idle time intervals of the - * CPU into account. However, even in that context it is not necessary to - * consider idle duration values greater than the sleep length, because the - * closest timer will ultimately wake up the CPU anyway unless it is woken up - * earlier. + * Of course, non-timer wakeup sources are more important in some use cases, + * but even then it is generally unnecessary to consider idle duration values + * greater than the time time till the next timer event, referred as the sleep + * length in what follows, because the closest timer will ultimately wake up the + * CPU anyway unless it is woken up earlier. * - * Thus this governor estimates whether or not the prospective idle duration of - * a CPU is likely to be significantly shorter than the sleep length and selects - * an idle state for it accordingly. + * However, since obtaining the sleep length may be costly, the governor first + * checks if it can select a shallow idle state using wakeup pattern information + * from recent times, in which case it can do without knowing the sleep length + * at all. For this purpose, it counts CPU wakeup events and looks for an idle + * state whose target residency has not exceeded the idle duration (measured + * after wakeup) in the majority of relevant recent cases. If the target + * residency of that state is small enough, it may be used right away and the + * sleep length need not be determined. * * The computations carried out by this governor are based on using bins whose * boundaries are aligned with the target residency parameter values of the CPU @@ -39,7 +41,11 @@ * idle state 2, the third bin spans from the target residency of idle state 2 * up to, but not including, the target residency of idle state 3 and so on. * The last bin spans from the target residency of the deepest idle state - * supplied by the driver to infinity. + * supplied by the driver to the scheduler tick period length or to infinity if + * the tick period length is less than the target residency of that state. In + * the latter case, the governor also counts events with the measured idle + * duration between the tick period length and the target residency of the + * deepest idle state. * * Two metrics called "hits" and "intercepts" are associated with each bin. * They are updated every time before selecting an idle state for the given CPU @@ -49,47 +55,46 @@ * sleep length and the idle duration measured after CPU wakeup fall into the * same bin (that is, the CPU appears to wake up "on time" relative to the sleep * length). In turn, the "intercepts" metric reflects the relative frequency of - * situations in which the measured idle duration is so much shorter than the - * sleep length that the bin it falls into corresponds to an idle state - * shallower than the one whose bin is fallen into by the sleep length (these - * situations are referred to as "intercepts" below). + * non-timer wakeup events for which the measured idle duration falls into a bin + * that corresponds to an idle state shallower than the one whose bin is fallen + * into by the sleep length (these events are also referred to as "intercepts" + * below). * * In order to select an idle state for a CPU, the governor takes the following * steps (modulo the possible latency constraint that must be taken into account * too): * - * 1. Find the deepest CPU idle state whose target residency does not exceed - * the current sleep length (the candidate idle state) and compute 2 sums as - * follows: + * 1. Find the deepest enabled CPU idle state (the candidate idle state) and + * compute 2 sums as follows: * - * - The sum of the "hits" and "intercepts" metrics for the candidate state - * and all of the deeper idle states (it represents the cases in which the - * CPU was idle long enough to avoid being intercepted if the sleep length - * had been equal to the current one). + * - The sum of the "hits" metric for all of the idle states shallower than + * the candidate one (it represents the cases in which the CPU was likely + * woken up by a timer). * - * - The sum of the "intercepts" metrics for all of the idle states shallower - * than the candidate one (it represents the cases in which the CPU was not - * idle long enough to avoid being intercepted if the sleep length had been - * equal to the current one). + * - The sum of the "intercepts" metric for all of the idle states shallower + * than the candidate one (it represents the cases in which the CPU was + * likely woken up by a non-timer wakeup source). * - * 2. If the second sum is greater than the first one the CPU is likely to wake - * up early, so look for an alternative idle state to select. + * 2. If the second sum computed in step 1 is greater than a half of the sum of + * both metrics for the candidate state bin and all subsequent bins(if any), + * a shallower idle state is likely to be more suitable, so look for it. * - * - Traverse the idle states shallower than the candidate one in the + * - Traverse the enabled idle states shallower than the candidate one in the * descending order. * * - For each of them compute the sum of the "intercepts" metrics over all * of the idle states between it and the candidate one (including the * former and excluding the latter). * - * - If each of these sums that needs to be taken into account (because the - * check related to it has indicated that the CPU is likely to wake up - * early) is greater than a half of the corresponding sum computed in step - * 1 (which means that the target residency of the state in question had - * not exceeded the idle duration in over a half of the relevant cases), - * select the given idle state instead of the candidate one. + * - If this sum is greater than a half of the second sum computed in step 1, + * use the given idle state as the new candidate one. * - * 3. By default, select the candidate state. + * 3. If the current candidate state is state 0 or its target residency is short + * enough, return it and prevent the scheduler tick from being stopped. + * + * 4. Obtain the sleep length value and check if it is below the target + * residency of the current candidate state, in which case a new shallower + * candidate state needs to be found, so look for it. */ #include <linux/cpuidle.h> diff --git a/drivers/gpio/gpio-loongson-64bit.c b/drivers/gpio/gpio-loongson-64bit.c index 6749d4dd6d64..7f4d78fd800e 100644 --- a/drivers/gpio/gpio-loongson-64bit.c +++ b/drivers/gpio/gpio-loongson-64bit.c @@ -237,9 +237,9 @@ static const struct loongson_gpio_chip_data loongson_gpio_ls2k2000_data1 = { static const struct loongson_gpio_chip_data loongson_gpio_ls2k2000_data2 = { .label = "ls2k2000_gpio", .mode = BIT_CTRL_MODE, - .conf_offset = 0x84, - .in_offset = 0x88, - .out_offset = 0x80, + .conf_offset = 0x4, + .in_offset = 0x8, + .out_offset = 0x0, }; static const struct loongson_gpio_chip_data loongson_gpio_ls3a5000_data = { diff --git a/drivers/gpio/gpio-sim.c b/drivers/gpio/gpio-sim.c index f387dad81f29..686ae3d11ba3 100644 --- a/drivers/gpio/gpio-sim.c +++ b/drivers/gpio/gpio-sim.c @@ -1027,6 +1027,30 @@ static void gpio_sim_device_deactivate(struct gpio_sim_device *dev) dev->pdev = NULL; } +static void +gpio_sim_device_lockup_configfs(struct gpio_sim_device *dev, bool lock) +{ + struct configfs_subsystem *subsys = dev->group.cg_subsys; + struct gpio_sim_bank *bank; + struct gpio_sim_line *line; + + /* + * The device only needs to depend on leaf line entries. This is + * sufficient to lock up all the configfs entries that the + * instantiated, alive device depends on. + */ + list_for_each_entry(bank, &dev->bank_list, siblings) { + list_for_each_entry(line, &bank->line_list, siblings) { + if (lock) + WARN_ON(configfs_depend_item_unlocked( + subsys, &line->group.cg_item)); + else + configfs_undepend_item_unlocked( + &line->group.cg_item); + } + } +} + static ssize_t gpio_sim_device_config_live_store(struct config_item *item, const char *page, size_t count) @@ -1039,14 +1063,24 @@ gpio_sim_device_config_live_store(struct config_item *item, if (ret) return ret; - guard(mutex)(&dev->lock); + if (live) + gpio_sim_device_lockup_configfs(dev, true); - if (live == gpio_sim_device_is_live(dev)) - ret = -EPERM; - else if (live) - ret = gpio_sim_device_activate(dev); - else - gpio_sim_device_deactivate(dev); + scoped_guard(mutex, &dev->lock) { + if (live == gpio_sim_device_is_live(dev)) + ret = -EPERM; + else if (live) + ret = gpio_sim_device_activate(dev); + else + gpio_sim_device_deactivate(dev); + } + + /* + * Undepend is required only if device disablement (live == 0) + * succeeds or if device enablement (live == 1) fails. + */ + if (live == !!ret) + gpio_sim_device_lockup_configfs(dev, false); return ret ?: count; } diff --git a/drivers/gpio/gpio-virtuser.c b/drivers/gpio/gpio-virtuser.c index 91b6352c957c..e89f299f2140 100644 --- a/drivers/gpio/gpio-virtuser.c +++ b/drivers/gpio/gpio-virtuser.c @@ -1410,7 +1410,7 @@ gpio_virtuser_make_lookup_table(struct gpio_virtuser_device *dev) size_t num_entries = gpio_virtuser_get_lookup_count(dev); struct gpio_virtuser_lookup_entry *entry; struct gpio_virtuser_lookup *lookup; - unsigned int i = 0; + unsigned int i = 0, idx; lockdep_assert_held(&dev->lock); @@ -1424,12 +1424,12 @@ gpio_virtuser_make_lookup_table(struct gpio_virtuser_device *dev) return -ENOMEM; list_for_each_entry(lookup, &dev->lookup_list, siblings) { + idx = 0; list_for_each_entry(entry, &lookup->entry_list, siblings) { - table->table[i] = + table->table[i++] = GPIO_LOOKUP_IDX(entry->key, entry->offset < 0 ? U16_MAX : entry->offset, - lookup->con_id, i, entry->flags); - i++; + lookup->con_id, idx++, entry->flags); } } @@ -1439,6 +1439,15 @@ gpio_virtuser_make_lookup_table(struct gpio_virtuser_device *dev) return 0; } +static void +gpio_virtuser_remove_lookup_table(struct gpio_virtuser_device *dev) +{ + gpiod_remove_lookup_table(dev->lookup_table); + kfree(dev->lookup_table->dev_id); + kfree(dev->lookup_table); + dev->lookup_table = NULL; +} + static struct fwnode_handle * gpio_virtuser_make_device_swnode(struct gpio_virtuser_device *dev) { @@ -1487,10 +1496,8 @@ gpio_virtuser_device_activate(struct gpio_virtuser_device *dev) pdevinfo.fwnode = swnode; ret = gpio_virtuser_make_lookup_table(dev); - if (ret) { - fwnode_remove_software_node(swnode); - return ret; - } + if (ret) + goto err_remove_swnode; reinit_completion(&dev->probe_completion); dev->driver_bound = false; @@ -1498,23 +1505,31 @@ gpio_virtuser_device_activate(struct gpio_virtuser_device *dev) pdev = platform_device_register_full(&pdevinfo); if (IS_ERR(pdev)) { + ret = PTR_ERR(pdev); bus_unregister_notifier(&platform_bus_type, &dev->bus_notifier); - fwnode_remove_software_node(swnode); - return PTR_ERR(pdev); + goto err_remove_lookup_table; } wait_for_completion(&dev->probe_completion); bus_unregister_notifier(&platform_bus_type, &dev->bus_notifier); if (!dev->driver_bound) { - platform_device_unregister(pdev); - fwnode_remove_software_node(swnode); - return -ENXIO; + ret = -ENXIO; + goto err_unregister_pdev; } dev->pdev = pdev; return 0; + +err_unregister_pdev: + platform_device_unregister(pdev); +err_remove_lookup_table: + gpio_virtuser_remove_lookup_table(dev); +err_remove_swnode: + fwnode_remove_software_node(swnode); + + return ret; } static void @@ -1526,10 +1541,33 @@ gpio_virtuser_device_deactivate(struct gpio_virtuser_device *dev) swnode = dev_fwnode(&dev->pdev->dev); platform_device_unregister(dev->pdev); + gpio_virtuser_remove_lookup_table(dev); fwnode_remove_software_node(swnode); dev->pdev = NULL; - gpiod_remove_lookup_table(dev->lookup_table); - kfree(dev->lookup_table); +} + +static void +gpio_virtuser_device_lockup_configfs(struct gpio_virtuser_device *dev, bool lock) +{ + struct configfs_subsystem *subsys = dev->group.cg_subsys; + struct gpio_virtuser_lookup_entry *entry; + struct gpio_virtuser_lookup *lookup; + + /* + * The device only needs to depend on leaf lookup entries. This is + * sufficient to lock up all the configfs entries that the + * instantiated, alive device depends on. + */ + list_for_each_entry(lookup, &dev->lookup_list, siblings) { + list_for_each_entry(entry, &lookup->entry_list, siblings) { + if (lock) + WARN_ON(configfs_depend_item_unlocked( + subsys, &entry->group.cg_item)); + else + configfs_undepend_item_unlocked( + &entry->group.cg_item); + } + } } static ssize_t @@ -1544,15 +1582,24 @@ gpio_virtuser_device_config_live_store(struct config_item *item, if (ret) return ret; - guard(mutex)(&dev->lock); + if (live) + gpio_virtuser_device_lockup_configfs(dev, true); - if (live == gpio_virtuser_device_is_live(dev)) - return -EPERM; + scoped_guard(mutex, &dev->lock) { + if (live == gpio_virtuser_device_is_live(dev)) + ret = -EPERM; + else if (live) + ret = gpio_virtuser_device_activate(dev); + else + gpio_virtuser_device_deactivate(dev); + } - if (live) - ret = gpio_virtuser_device_activate(dev); - else - gpio_virtuser_device_deactivate(dev); + /* + * Undepend is required only if device disablement (live == 0) + * succeeds or if device enablement (live == 1) fails. + */ + if (live == !!ret) + gpio_virtuser_device_lockup_configfs(dev, false); return ret ?: count; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c index 7d26a962f811..ff5e52025266 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c @@ -567,7 +567,6 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man, else remaining_size -= size; } - mutex_unlock(&mgr->lock); if (bo->flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS && adjust_dcc_size) { struct drm_buddy_block *dcc_block; @@ -584,6 +583,7 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man, (u64)vres->base.size, &vres->blocks); } + mutex_unlock(&mgr->lock); vres->base.start = 0; size = max_t(u64, amdgpu_vram_mgr_blocks_size(&vres->blocks), diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_debug.c b/drivers/gpu/drm/amd/amdkfd/kfd_debug.c index 312dfa84f29f..a8abc3091801 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_debug.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_debug.c @@ -350,10 +350,27 @@ int kfd_dbg_set_mes_debug_mode(struct kfd_process_device *pdd, bool sq_trap_en) { uint32_t spi_dbg_cntl = pdd->spi_dbg_override | pdd->spi_dbg_launch_mode; uint32_t flags = pdd->process->dbg_flags; + struct amdgpu_device *adev = pdd->dev->adev; + int r; if (!kfd_dbg_is_per_vmid_supported(pdd->dev)) return 0; + if (!pdd->proc_ctx_cpu_ptr) { + r = amdgpu_amdkfd_alloc_gtt_mem(adev, + AMDGPU_MES_PROC_CTX_SIZE, + &pdd->proc_ctx_bo, + &pdd->proc_ctx_gpu_addr, + &pdd->proc_ctx_cpu_ptr, + false); + if (r) { + dev_err(adev->dev, + "failed to allocate process context bo\n"); + return r; + } + memset(pdd->proc_ctx_cpu_ptr, 0, AMDGPU_MES_PROC_CTX_SIZE); + } + return amdgpu_mes_set_shader_debugger(pdd->dev->adev, pdd->proc_ctx_gpu_addr, spi_dbg_cntl, pdd->watch_points, flags, sq_trap_en); } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index d0ee173acf82..edfe0b4788f4 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -1160,7 +1160,8 @@ static void kfd_process_wq_release(struct work_struct *work) */ synchronize_rcu(); ef = rcu_access_pointer(p->ef); - dma_fence_signal(ef); + if (ef) + dma_fence_signal(ef); kfd_process_remove_sysfs(p); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 48be917e7bc5..cd16dae534dc 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -8400,16 +8400,6 @@ static void manage_dm_interrupts(struct amdgpu_device *adev, struct amdgpu_crtc *acrtc, struct dm_crtc_state *acrtc_state) { - /* - * We have no guarantee that the frontend index maps to the same - * backend index - some even map to more than one. - * - * TODO: Use a different interrupt or check DC itself for the mapping. - */ - int irq_type = - amdgpu_display_crtc_idx_to_irq_type( - adev, - acrtc->crtc_id); struct drm_vblank_crtc_config config = {0}; struct dc_crtc_timing *timing; int offdelay; @@ -8435,28 +8425,7 @@ static void manage_dm_interrupts(struct amdgpu_device *adev, drm_crtc_vblank_on_config(&acrtc->base, &config); - - amdgpu_irq_get( - adev, - &adev->pageflip_irq, - irq_type); -#if defined(CONFIG_DRM_AMD_SECURE_DISPLAY) - amdgpu_irq_get( - adev, - &adev->vline0_irq, - irq_type); -#endif } else { -#if defined(CONFIG_DRM_AMD_SECURE_DISPLAY) - amdgpu_irq_put( - adev, - &adev->vline0_irq, - irq_type); -#endif - amdgpu_irq_put( - adev, - &adev->pageflip_irq, - irq_type); drm_crtc_vblank_off(&acrtc->base); } } @@ -11155,8 +11124,8 @@ dm_get_plane_scale(struct drm_plane_state *plane_state, int plane_src_w, plane_src_h; dm_get_oriented_plane_size(plane_state, &plane_src_w, &plane_src_h); - *out_plane_scale_w = plane_state->crtc_w * 1000 / plane_src_w; - *out_plane_scale_h = plane_state->crtc_h * 1000 / plane_src_h; + *out_plane_scale_w = plane_src_w ? plane_state->crtc_w * 1000 / plane_src_w : 0; + *out_plane_scale_h = plane_src_h ? plane_state->crtc_h * 1000 / plane_src_h : 0; } /* diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 49fe7dcf9372..2723558049d6 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -4510,7 +4510,7 @@ static bool commit_minimal_transition_based_on_current_context(struct dc *dc, struct pipe_split_policy_backup policy; struct dc_state *intermediate_context; struct dc_state *old_current_state = dc->current_state; - struct dc_surface_update srf_updates[MAX_SURFACE_NUM] = {0}; + struct dc_surface_update srf_updates[MAX_SURFACES] = {0}; int surface_count; /* diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_state.c b/drivers/gpu/drm/amd/display/dc/core/dc_state.c index e006f816ff2f..1b2cce127981 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_state.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_state.c @@ -483,9 +483,9 @@ bool dc_state_add_plane( if (stream_status == NULL) { dm_error("Existing stream not found; failed to attach surface!\n"); goto out; - } else if (stream_status->plane_count == MAX_SURFACE_NUM) { + } else if (stream_status->plane_count == MAX_SURFACES) { dm_error("Surface: can not attach plane_state %p! Maximum is: %d\n", - plane_state, MAX_SURFACE_NUM); + plane_state, MAX_SURFACES); goto out; } else if (!otg_master_pipe) { goto out; @@ -600,7 +600,7 @@ bool dc_state_rem_all_planes_for_stream( { int i, old_plane_count; struct dc_stream_status *stream_status = NULL; - struct dc_plane_state *del_planes[MAX_SURFACE_NUM] = { 0 }; + struct dc_plane_state *del_planes[MAX_SURFACES] = { 0 }; for (i = 0; i < state->stream_count; i++) if (state->streams[i] == stream) { @@ -875,7 +875,7 @@ bool dc_state_rem_all_phantom_planes_for_stream( { int i, old_plane_count; struct dc_stream_status *stream_status = NULL; - struct dc_plane_state *del_planes[MAX_SURFACE_NUM] = { 0 }; + struct dc_plane_state *del_planes[MAX_SURFACES] = { 0 }; for (i = 0; i < state->stream_count; i++) if (state->streams[i] == phantom_stream) { diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index e9b9126c0401..08c5a315b3a6 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -57,7 +57,7 @@ struct dmub_notification; #define DC_VER "3.2.310" -#define MAX_SURFACES 3 +#define MAX_SURFACES 4 #define MAX_PLANES 6 #define MAX_STREAMS 6 #define MIN_VIEWPORT_SIZE 12 @@ -1398,7 +1398,7 @@ struct dc_scratch_space { * store current value in plane states so we can still recover * a valid current state during dc update. */ - struct dc_plane_state plane_states[MAX_SURFACE_NUM]; + struct dc_plane_state plane_states[MAX_SURFACES]; struct dc_stream_state stream_state; }; diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h index 413970588a26..860506c6bda4 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_stream.h +++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h @@ -56,7 +56,7 @@ struct dc_stream_status { int plane_count; int audio_inst; struct timing_sync_info timing_sync_info; - struct dc_plane_state *plane_states[MAX_SURFACE_NUM]; + struct dc_plane_state *plane_states[MAX_SURFACES]; bool is_abm_supported; struct mall_stream_config mall_stream_config; bool fpo_in_use; diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h index edf4df1d03b5..9466b63644d5 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_types.h @@ -76,7 +76,6 @@ struct dc_perf_trace { unsigned long last_entry_write; }; -#define MAX_SURFACE_NUM 6 #define NUM_PIXEL_FORMATS 10 enum tiling_mode { diff --git a/drivers/gpu/drm/amd/display/dc/dml/dml_inline_defs.h b/drivers/gpu/drm/amd/display/dc/dml/dml_inline_defs.h index 072bd0539605..6b2ab4ec2b5f 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dml_inline_defs.h +++ b/drivers/gpu/drm/amd/display/dc/dml/dml_inline_defs.h @@ -66,11 +66,15 @@ static inline double dml_max5(double a, double b, double c, double d, double e) static inline double dml_ceil(double a, double granularity) { + if (granularity == 0) + return 0; return (double) dcn_bw_ceil2(a, granularity); } static inline double dml_floor(double a, double granularity) { + if (granularity == 0) + return 0; return (double) dcn_bw_floor2(a, granularity); } @@ -114,11 +118,15 @@ static inline double dml_ceil_2(double f) static inline double dml_ceil_ex(double x, double granularity) { + if (granularity == 0) + return 0; return (double) dcn_bw_ceil2(x, granularity); } static inline double dml_floor_ex(double x, double granularity) { + if (granularity == 0) + return 0; return (double) dcn_bw_floor2(x, granularity); } diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_mall_phantom.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_mall_phantom.c index 3d29169dd6bb..6b3b8803e0ae 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_mall_phantom.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_mall_phantom.c @@ -813,7 +813,7 @@ static bool remove_all_phantom_planes_for_stream(struct dml2_context *ctx, struc { int i, old_plane_count; struct dc_stream_status *stream_status = NULL; - struct dc_plane_state *del_planes[MAX_SURFACE_NUM] = { 0 }; + struct dc_plane_state *del_planes[MAX_SURFACES] = { 0 }; for (i = 0; i < context->stream_count; i++) if (context->streams[i] == stream) { diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h index ae3563d71fa0..356d9422b411 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h @@ -303,5 +303,7 @@ int smu_v13_0_set_wbrf_exclusion_ranges(struct smu_context *smu, int smu_v13_0_get_boot_freq_by_index(struct smu_context *smu, enum smu_clk_type clk_type, uint32_t *value); + +void smu_v13_0_interrupt_work(struct smu_context *smu); #endif #endif diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c index 2bfea740dace..2d1e7ebd1bac 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c @@ -1320,11 +1320,11 @@ static int smu_v13_0_set_irq_state(struct amdgpu_device *adev, return 0; } -static int smu_v13_0_ack_ac_dc_interrupt(struct smu_context *smu) +void smu_v13_0_interrupt_work(struct smu_context *smu) { - return smu_cmn_send_smc_msg(smu, - SMU_MSG_ReenableAcDcInterrupt, - NULL); + smu_cmn_send_smc_msg(smu, + SMU_MSG_ReenableAcDcInterrupt, + NULL); } #define THM_11_0__SRCID__THM_DIG_THERM_L2H 0 /* ASIC_TEMP > CG_THERMAL_INT.DIG_THERM_INTH */ @@ -1377,12 +1377,12 @@ static int smu_v13_0_irq_process(struct amdgpu_device *adev, switch (ctxid) { case SMU_IH_INTERRUPT_CONTEXT_ID_AC: dev_dbg(adev->dev, "Switched to AC mode!\n"); - smu_v13_0_ack_ac_dc_interrupt(smu); + schedule_work(&smu->interrupt_work); adev->pm.ac_power = true; break; case SMU_IH_INTERRUPT_CONTEXT_ID_DC: dev_dbg(adev->dev, "Switched to DC mode!\n"); - smu_v13_0_ack_ac_dc_interrupt(smu); + schedule_work(&smu->interrupt_work); adev->pm.ac_power = false; break; case SMU_IH_INTERRUPT_CONTEXT_ID_THERMAL_THROTTLING: diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index 3aa705aae4c0..2a09b27788e8 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -3219,6 +3219,7 @@ static const struct pptable_funcs smu_v13_0_0_ppt_funcs = { .is_asic_wbrf_supported = smu_v13_0_0_wbrf_support_check, .enable_uclk_shadow = smu_v13_0_enable_uclk_shadow, .set_wbrf_exclusion_ranges = smu_v13_0_set_wbrf_exclusion_ranges, + .interrupt_work = smu_v13_0_interrupt_work, }; void smu_v13_0_0_set_ppt_funcs(struct smu_context *smu) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c index aabb94796005..55ef18517b0f 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c @@ -2797,6 +2797,7 @@ static const struct pptable_funcs smu_v13_0_7_ppt_funcs = { .is_asic_wbrf_supported = smu_v13_0_7_wbrf_support_check, .enable_uclk_shadow = smu_v13_0_enable_uclk_shadow, .set_wbrf_exclusion_ranges = smu_v13_0_set_wbrf_exclusion_ranges, + .interrupt_work = smu_v13_0_interrupt_work, }; void smu_v13_0_7_set_ppt_funcs(struct smu_context *smu) diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.c b/drivers/gpu/drm/i915/display/intel_hdcp.c index f57e4dba2873..8fee26d791f4 100644 --- a/drivers/gpu/drm/i915/display/intel_hdcp.c +++ b/drivers/gpu/drm/i915/display/intel_hdcp.c @@ -1158,9 +1158,15 @@ static int intel_hdcp_check_link(struct intel_connector *connector) goto out; } - intel_hdcp_update_value(connector, - DRM_MODE_CONTENT_PROTECTION_DESIRED, - true); + ret = intel_hdcp1_enable(connector); + if (ret) { + drm_err(display->drm, "Failed to enable hdcp (%d)\n", ret); + intel_hdcp_update_value(connector, + DRM_MODE_CONTENT_PROTECTION_DESIRED, + true); + goto out; + } + out: mutex_unlock(&dig_port->hdcp_mutex); mutex_unlock(&hdcp->mutex); diff --git a/drivers/gpu/drm/mediatek/Kconfig b/drivers/gpu/drm/mediatek/Kconfig index f496e6cfdfe0..e47debd60619 100644 --- a/drivers/gpu/drm/mediatek/Kconfig +++ b/drivers/gpu/drm/mediatek/Kconfig @@ -14,9 +14,6 @@ config DRM_MEDIATEK select DRM_BRIDGE_CONNECTOR select DRM_MIPI_DSI select DRM_PANEL - select MEMORY - select MTK_SMI - select PHY_MTK_MIPI_DSI select VIDEOMODE_HELPERS help Choose this option if you have a Mediatek SoCs. @@ -27,7 +24,6 @@ config DRM_MEDIATEK config DRM_MEDIATEK_DP tristate "DRM DPTX Support for MediaTek SoCs" depends on DRM_MEDIATEK - select PHY_MTK_DP select DRM_DISPLAY_HELPER select DRM_DISPLAY_DP_HELPER select DRM_DISPLAY_DP_AUX_BUS @@ -38,6 +34,5 @@ config DRM_MEDIATEK_HDMI tristate "DRM HDMI Support for Mediatek SoCs" depends on DRM_MEDIATEK select SND_SOC_HDMI_CODEC if SND_SOC - select PHY_MTK_HDMI help DRM/KMS HDMI driver for Mediatek SoCs diff --git a/drivers/gpu/drm/mediatek/mtk_crtc.c b/drivers/gpu/drm/mediatek/mtk_crtc.c index eb0e1233ad04..5674f5707cca 100644 --- a/drivers/gpu/drm/mediatek/mtk_crtc.c +++ b/drivers/gpu/drm/mediatek/mtk_crtc.c @@ -112,6 +112,11 @@ static void mtk_drm_finish_page_flip(struct mtk_crtc *mtk_crtc) drm_crtc_handle_vblank(&mtk_crtc->base); +#if IS_REACHABLE(CONFIG_MTK_CMDQ) + if (mtk_crtc->cmdq_client.chan) + return; +#endif + spin_lock_irqsave(&mtk_crtc->config_lock, flags); if (!mtk_crtc->config_updating && mtk_crtc->pending_needs_vblank) { mtk_crtc_finish_page_flip(mtk_crtc); @@ -284,10 +289,8 @@ static void ddp_cmdq_cb(struct mbox_client *cl, void *mssg) state = to_mtk_crtc_state(mtk_crtc->base.state); spin_lock_irqsave(&mtk_crtc->config_lock, flags); - if (mtk_crtc->config_updating) { - spin_unlock_irqrestore(&mtk_crtc->config_lock, flags); + if (mtk_crtc->config_updating) goto ddp_cmdq_cb_out; - } state->pending_config = false; @@ -315,10 +318,15 @@ static void ddp_cmdq_cb(struct mbox_client *cl, void *mssg) mtk_crtc->pending_async_planes = false; } - spin_unlock_irqrestore(&mtk_crtc->config_lock, flags); - ddp_cmdq_cb_out: + if (mtk_crtc->pending_needs_vblank) { + mtk_crtc_finish_page_flip(mtk_crtc); + mtk_crtc->pending_needs_vblank = false; + } + + spin_unlock_irqrestore(&mtk_crtc->config_lock, flags); + mtk_crtc->cmdq_vblank_cnt = 0; wake_up(&mtk_crtc->cb_blocking_queue); } @@ -606,13 +614,18 @@ static void mtk_crtc_update_config(struct mtk_crtc *mtk_crtc, bool needs_vblank) */ mtk_crtc->cmdq_vblank_cnt = 3; + spin_lock_irqsave(&mtk_crtc->config_lock, flags); + mtk_crtc->config_updating = false; + spin_unlock_irqrestore(&mtk_crtc->config_lock, flags); + mbox_send_message(mtk_crtc->cmdq_client.chan, cmdq_handle); mbox_client_txdone(mtk_crtc->cmdq_client.chan, 0); } -#endif +#else spin_lock_irqsave(&mtk_crtc->config_lock, flags); mtk_crtc->config_updating = false; spin_unlock_irqrestore(&mtk_crtc->config_lock, flags); +#endif mutex_unlock(&mtk_crtc->hw_lock); } diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c index f731d4fbe8b6..df82cea4bb79 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c +++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c @@ -460,6 +460,29 @@ static unsigned int mtk_ovl_fmt_convert(struct mtk_disp_ovl *ovl, } } +static void mtk_ovl_afbc_layer_config(struct mtk_disp_ovl *ovl, + unsigned int idx, + struct mtk_plane_pending_state *pending, + struct cmdq_pkt *cmdq_pkt) +{ + unsigned int pitch_msb = pending->pitch >> 16; + unsigned int hdr_pitch = pending->hdr_pitch; + unsigned int hdr_addr = pending->hdr_addr; + + if (pending->modifier != DRM_FORMAT_MOD_LINEAR) { + mtk_ddp_write_relaxed(cmdq_pkt, hdr_addr, &ovl->cmdq_reg, ovl->regs, + DISP_REG_OVL_HDR_ADDR(ovl, idx)); + mtk_ddp_write_relaxed(cmdq_pkt, + OVL_PITCH_MSB_2ND_SUBBUF | pitch_msb, + &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_PITCH_MSB(idx)); + mtk_ddp_write_relaxed(cmdq_pkt, hdr_pitch, &ovl->cmdq_reg, ovl->regs, + DISP_REG_OVL_HDR_PITCH(ovl, idx)); + } else { + mtk_ddp_write_relaxed(cmdq_pkt, pitch_msb, + &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_PITCH_MSB(idx)); + } +} + void mtk_ovl_layer_config(struct device *dev, unsigned int idx, struct mtk_plane_state *state, struct cmdq_pkt *cmdq_pkt) @@ -467,25 +490,14 @@ void mtk_ovl_layer_config(struct device *dev, unsigned int idx, struct mtk_disp_ovl *ovl = dev_get_drvdata(dev); struct mtk_plane_pending_state *pending = &state->pending; unsigned int addr = pending->addr; - unsigned int hdr_addr = pending->hdr_addr; - unsigned int pitch = pending->pitch; - unsigned int hdr_pitch = pending->hdr_pitch; + unsigned int pitch_lsb = pending->pitch & GENMASK(15, 0); unsigned int fmt = pending->format; + unsigned int rotation = pending->rotation; unsigned int offset = (pending->y << 16) | pending->x; unsigned int src_size = (pending->height << 16) | pending->width; unsigned int blend_mode = state->base.pixel_blend_mode; unsigned int ignore_pixel_alpha = 0; unsigned int con; - bool is_afbc = pending->modifier != DRM_FORMAT_MOD_LINEAR; - union overlay_pitch { - struct split_pitch { - u16 lsb; - u16 msb; - } split_pitch; - u32 pitch; - } overlay_pitch; - - overlay_pitch.pitch = pitch; if (!pending->enable) { mtk_ovl_layer_off(dev, idx, cmdq_pkt); @@ -513,22 +525,30 @@ void mtk_ovl_layer_config(struct device *dev, unsigned int idx, ignore_pixel_alpha = OVL_CONST_BLEND; } - if (pending->rotation & DRM_MODE_REFLECT_Y) { + /* + * Treat rotate 180 as flip x + flip y, and XOR the original rotation value + * to flip x + flip y to support both in the same time. + */ + if (rotation & DRM_MODE_ROTATE_180) + rotation ^= DRM_MODE_REFLECT_X | DRM_MODE_REFLECT_Y; + + if (rotation & DRM_MODE_REFLECT_Y) { con |= OVL_CON_VIRT_FLIP; addr += (pending->height - 1) * pending->pitch; } - if (pending->rotation & DRM_MODE_REFLECT_X) { + if (rotation & DRM_MODE_REFLECT_X) { con |= OVL_CON_HORZ_FLIP; addr += pending->pitch - 1; } if (ovl->data->supports_afbc) - mtk_ovl_set_afbc(ovl, cmdq_pkt, idx, is_afbc); + mtk_ovl_set_afbc(ovl, cmdq_pkt, idx, + pending->modifier != DRM_FORMAT_MOD_LINEAR); mtk_ddp_write_relaxed(cmdq_pkt, con, &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_CON(idx)); - mtk_ddp_write_relaxed(cmdq_pkt, overlay_pitch.split_pitch.lsb | ignore_pixel_alpha, + mtk_ddp_write_relaxed(cmdq_pkt, pitch_lsb | ignore_pixel_alpha, &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_PITCH(idx)); mtk_ddp_write_relaxed(cmdq_pkt, src_size, &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_SRC_SIZE(idx)); @@ -537,19 +557,8 @@ void mtk_ovl_layer_config(struct device *dev, unsigned int idx, mtk_ddp_write_relaxed(cmdq_pkt, addr, &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_ADDR(ovl, idx)); - if (is_afbc) { - mtk_ddp_write_relaxed(cmdq_pkt, hdr_addr, &ovl->cmdq_reg, ovl->regs, - DISP_REG_OVL_HDR_ADDR(ovl, idx)); - mtk_ddp_write_relaxed(cmdq_pkt, - OVL_PITCH_MSB_2ND_SUBBUF | overlay_pitch.split_pitch.msb, - &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_PITCH_MSB(idx)); - mtk_ddp_write_relaxed(cmdq_pkt, hdr_pitch, &ovl->cmdq_reg, ovl->regs, - DISP_REG_OVL_HDR_PITCH(ovl, idx)); - } else { - mtk_ddp_write_relaxed(cmdq_pkt, - overlay_pitch.split_pitch.msb, - &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_PITCH_MSB(idx)); - } + if (ovl->data->supports_afbc) + mtk_ovl_afbc_layer_config(ovl, idx, pending, cmdq_pkt); mtk_ovl_set_bit_depth(dev, idx, fmt, cmdq_pkt); mtk_ovl_layer_on(dev, idx, cmdq_pkt); diff --git a/drivers/gpu/drm/mediatek/mtk_dp.c b/drivers/gpu/drm/mediatek/mtk_dp.c index 36713c176cfc..3b0993abfdc3 100644 --- a/drivers/gpu/drm/mediatek/mtk_dp.c +++ b/drivers/gpu/drm/mediatek/mtk_dp.c @@ -543,18 +543,16 @@ static int mtk_dp_set_color_format(struct mtk_dp *mtk_dp, enum dp_pixelformat color_format) { u32 val; - - /* update MISC0 */ - mtk_dp_update_bits(mtk_dp, MTK_DP_ENC0_P0_3034, - color_format << DP_TEST_COLOR_FORMAT_SHIFT, - DP_TEST_COLOR_FORMAT_MASK); + u32 misc0_color; switch (color_format) { case DP_PIXELFORMAT_YUV422: val = PIXEL_ENCODE_FORMAT_DP_ENC0_P0_YCBCR422; + misc0_color = DP_COLOR_FORMAT_YCbCr422; break; case DP_PIXELFORMAT_RGB: val = PIXEL_ENCODE_FORMAT_DP_ENC0_P0_RGB; + misc0_color = DP_COLOR_FORMAT_RGB; break; default: drm_warn(mtk_dp->drm_dev, "Unsupported color format: %d\n", @@ -562,6 +560,11 @@ static int mtk_dp_set_color_format(struct mtk_dp *mtk_dp, return -EINVAL; } + /* update MISC0 */ + mtk_dp_update_bits(mtk_dp, MTK_DP_ENC0_P0_3034, + misc0_color, + DP_TEST_COLOR_FORMAT_MASK); + mtk_dp_update_bits(mtk_dp, MTK_DP_ENC0_P0_303C, val, PIXEL_ENCODE_FORMAT_DP_ENC0_P0_MASK); return 0; @@ -2100,7 +2103,6 @@ static enum drm_connector_status mtk_dp_bdg_detect(struct drm_bridge *bridge) struct mtk_dp *mtk_dp = mtk_dp_from_bridge(bridge); enum drm_connector_status ret = connector_status_disconnected; bool enabled = mtk_dp->enabled; - u8 sink_count = 0; if (!mtk_dp->train_info.cable_plugged_in) return ret; @@ -2115,8 +2117,8 @@ static enum drm_connector_status mtk_dp_bdg_detect(struct drm_bridge *bridge) * function, we just need to check the HPD connection to check * whether we connect to a sink device. */ - drm_dp_dpcd_readb(&mtk_dp->aux, DP_SINK_COUNT, &sink_count); - if (DP_GET_SINK_COUNT(sink_count)) + + if (drm_dp_read_sink_count(&mtk_dp->aux) > 0) ret = connector_status_connected; if (!enabled) @@ -2408,12 +2410,19 @@ mtk_dp_bridge_mode_valid(struct drm_bridge *bridge, { struct mtk_dp *mtk_dp = mtk_dp_from_bridge(bridge); u32 bpp = info->color_formats & DRM_COLOR_FORMAT_YCBCR422 ? 16 : 24; - u32 rate = min_t(u32, drm_dp_max_link_rate(mtk_dp->rx_cap) * - drm_dp_max_lane_count(mtk_dp->rx_cap), - drm_dp_bw_code_to_link_rate(mtk_dp->max_linkrate) * - mtk_dp->max_lanes); + u32 lane_count_min = mtk_dp->train_info.lane_count; + u32 rate = drm_dp_bw_code_to_link_rate(mtk_dp->train_info.link_rate) * + lane_count_min; - if (rate < mode->clock * bpp / 8) + /* + *FEC overhead is approximately 2.4% from DP 1.4a spec 2.2.1.4.2. + *The down-spread amplitude shall either be disabled (0.0%) or up + *to 0.5% from 1.4a 3.5.2.6. Add up to approximately 3% total overhead. + * + *Because rate is already divided by 10, + *mode->clock does not need to be multiplied by 10 + */ + if ((rate * 97 / 100) < (mode->clock * bpp / 8)) return MODE_CLOCK_HIGH; return MODE_OK; @@ -2454,10 +2463,9 @@ static u32 *mtk_dp_bridge_atomic_get_input_bus_fmts(struct drm_bridge *bridge, struct drm_display_mode *mode = &crtc_state->adjusted_mode; struct drm_display_info *display_info = &conn_state->connector->display_info; - u32 rate = min_t(u32, drm_dp_max_link_rate(mtk_dp->rx_cap) * - drm_dp_max_lane_count(mtk_dp->rx_cap), - drm_dp_bw_code_to_link_rate(mtk_dp->max_linkrate) * - mtk_dp->max_lanes); + u32 lane_count_min = mtk_dp->train_info.lane_count; + u32 rate = drm_dp_bw_code_to_link_rate(mtk_dp->train_info.link_rate) * + lane_count_min; *num_input_fmts = 0; @@ -2466,8 +2474,8 @@ static u32 *mtk_dp_bridge_atomic_get_input_bus_fmts(struct drm_bridge *bridge, * datarate of YUV422 and sink device supports YUV422, we output YUV422 * format. Use this condition, we can support more resolution. */ - if ((rate < (mode->clock * 24 / 8)) && - (rate > (mode->clock * 16 / 8)) && + if (((rate * 97 / 100) < (mode->clock * 24 / 8)) && + ((rate * 97 / 100) > (mode->clock * 16 / 8)) && (display_info->color_formats & DRM_COLOR_FORMAT_YCBCR422)) { input_fmts = kcalloc(1, sizeof(*input_fmts), GFP_KERNEL); if (!input_fmts) diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c index 0829ceb9967c..b037616d3342 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c @@ -373,11 +373,12 @@ static bool mtk_drm_get_all_drm_priv(struct device *dev) struct mtk_drm_private *temp_drm_priv; struct device_node *phandle = dev->parent->of_node; const struct of_device_id *of_id; + struct device_node *node; struct device *drm_dev; unsigned int cnt = 0; int i, j; - for_each_child_of_node_scoped(phandle->parent, node) { + for_each_child_of_node(phandle->parent, node) { struct platform_device *pdev; of_id = of_match_node(mtk_drm_of_ids, node); @@ -406,8 +407,10 @@ static bool mtk_drm_get_all_drm_priv(struct device *dev) if (temp_drm_priv->mtk_drm_bound) cnt++; - if (cnt == MAX_CRTC) + if (cnt == MAX_CRTC) { + of_node_put(node); break; + } } if (drm_priv->data->mmsys_dev_num == cnt) { @@ -673,6 +676,8 @@ err_deinit: err_free: private->drm = NULL; drm_dev_put(drm); + for (i = 0; i < private->data->mmsys_dev_num; i++) + private->all_drm_private[i]->drm = NULL; return ret; } @@ -900,7 +905,7 @@ static int mtk_drm_of_ddp_path_build_one(struct device *dev, enum mtk_crtc_path const unsigned int **out_path, unsigned int *out_path_len) { - struct device_node *next, *prev, *vdo = dev->parent->of_node; + struct device_node *next = NULL, *prev, *vdo = dev->parent->of_node; unsigned int temp_path[DDP_COMPONENT_DRM_ID_MAX] = { 0 }; unsigned int *final_ddp_path; unsigned short int idx = 0; @@ -1089,7 +1094,7 @@ static int mtk_drm_probe(struct platform_device *pdev) /* No devicetree graphs support: go with hardcoded paths if present */ dev_dbg(dev, "Using hardcoded paths for MMSYS %u\n", mtk_drm_data->mmsys_id); private->data = mtk_drm_data; - }; + } private->all_drm_private = devm_kmalloc_array(dev, private->data->mmsys_dev_num, sizeof(*private->all_drm_private), diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c index e61b9bc68e9a..40752f232054 100644 --- a/drivers/gpu/drm/mediatek/mtk_dsi.c +++ b/drivers/gpu/drm/mediatek/mtk_dsi.c @@ -139,11 +139,11 @@ #define CLK_HS_POST GENMASK(15, 8) #define CLK_HS_EXIT GENMASK(23, 16) -#define DSI_VM_CMD_CON 0x130 +/* DSI_VM_CMD_CON */ #define VM_CMD_EN BIT(0) #define TS_VFP_EN BIT(5) -#define DSI_SHADOW_DEBUG 0x190U +/* DSI_SHADOW_DEBUG */ #define FORCE_COMMIT BIT(0) #define BYPASS_SHADOW BIT(1) @@ -187,6 +187,8 @@ struct phy; struct mtk_dsi_driver_data { const u32 reg_cmdq_off; + const u32 reg_vm_cmd_off; + const u32 reg_shadow_dbg_off; bool has_shadow_ctl; bool has_size_ctl; bool cmdq_long_packet_ctl; @@ -246,23 +248,22 @@ static void mtk_dsi_phy_timconfig(struct mtk_dsi *dsi) u32 data_rate_mhz = DIV_ROUND_UP(dsi->data_rate, HZ_PER_MHZ); struct mtk_phy_timing *timing = &dsi->phy_timing; - timing->lpx = (80 * data_rate_mhz / (8 * 1000)) + 1; - timing->da_hs_prepare = (59 * data_rate_mhz + 4 * 1000) / 8000 + 1; - timing->da_hs_zero = (163 * data_rate_mhz + 11 * 1000) / 8000 + 1 - + timing->lpx = (60 * data_rate_mhz / (8 * 1000)) + 1; + timing->da_hs_prepare = (80 * data_rate_mhz + 4 * 1000) / 8000; + timing->da_hs_zero = (170 * data_rate_mhz + 10 * 1000) / 8000 + 1 - timing->da_hs_prepare; - timing->da_hs_trail = (78 * data_rate_mhz + 7 * 1000) / 8000 + 1; + timing->da_hs_trail = timing->da_hs_prepare + 1; - timing->ta_go = 4 * timing->lpx; - timing->ta_sure = 3 * timing->lpx / 2; - timing->ta_get = 5 * timing->lpx; - timing->da_hs_exit = (118 * data_rate_mhz / (8 * 1000)) + 1; + timing->ta_go = 4 * timing->lpx - 2; + timing->ta_sure = timing->lpx + 2; + timing->ta_get = 4 * timing->lpx; + timing->da_hs_exit = 2 * timing->lpx + 1; - timing->clk_hs_prepare = (57 * data_rate_mhz / (8 * 1000)) + 1; - timing->clk_hs_post = (65 * data_rate_mhz + 53 * 1000) / 8000 + 1; - timing->clk_hs_trail = (78 * data_rate_mhz + 7 * 1000) / 8000 + 1; - timing->clk_hs_zero = (330 * data_rate_mhz / (8 * 1000)) + 1 - - timing->clk_hs_prepare; - timing->clk_hs_exit = (118 * data_rate_mhz / (8 * 1000)) + 1; + timing->clk_hs_prepare = 70 * data_rate_mhz / (8 * 1000); + timing->clk_hs_post = timing->clk_hs_prepare + 8; + timing->clk_hs_trail = timing->clk_hs_prepare; + timing->clk_hs_zero = timing->clk_hs_trail * 4; + timing->clk_hs_exit = 2 * timing->clk_hs_trail; timcon0 = FIELD_PREP(LPX, timing->lpx) | FIELD_PREP(HS_PREP, timing->da_hs_prepare) | @@ -367,8 +368,8 @@ static void mtk_dsi_set_mode(struct mtk_dsi *dsi) static void mtk_dsi_set_vm_cmd(struct mtk_dsi *dsi) { - mtk_dsi_mask(dsi, DSI_VM_CMD_CON, VM_CMD_EN, VM_CMD_EN); - mtk_dsi_mask(dsi, DSI_VM_CMD_CON, TS_VFP_EN, TS_VFP_EN); + mtk_dsi_mask(dsi, dsi->driver_data->reg_vm_cmd_off, VM_CMD_EN, VM_CMD_EN); + mtk_dsi_mask(dsi, dsi->driver_data->reg_vm_cmd_off, TS_VFP_EN, TS_VFP_EN); } static void mtk_dsi_rxtx_control(struct mtk_dsi *dsi) @@ -714,7 +715,7 @@ static int mtk_dsi_poweron(struct mtk_dsi *dsi) if (dsi->driver_data->has_shadow_ctl) writel(FORCE_COMMIT | BYPASS_SHADOW, - dsi->regs + DSI_SHADOW_DEBUG); + dsi->regs + dsi->driver_data->reg_shadow_dbg_off); mtk_dsi_reset_engine(dsi); mtk_dsi_phy_timconfig(dsi); @@ -1263,26 +1264,36 @@ static void mtk_dsi_remove(struct platform_device *pdev) static const struct mtk_dsi_driver_data mt8173_dsi_driver_data = { .reg_cmdq_off = 0x200, + .reg_vm_cmd_off = 0x130, + .reg_shadow_dbg_off = 0x190 }; static const struct mtk_dsi_driver_data mt2701_dsi_driver_data = { .reg_cmdq_off = 0x180, + .reg_vm_cmd_off = 0x130, + .reg_shadow_dbg_off = 0x190 }; static const struct mtk_dsi_driver_data mt8183_dsi_driver_data = { .reg_cmdq_off = 0x200, + .reg_vm_cmd_off = 0x130, + .reg_shadow_dbg_off = 0x190, .has_shadow_ctl = true, .has_size_ctl = true, }; static const struct mtk_dsi_driver_data mt8186_dsi_driver_data = { .reg_cmdq_off = 0xd00, + .reg_vm_cmd_off = 0x200, + .reg_shadow_dbg_off = 0xc00, .has_shadow_ctl = true, .has_size_ctl = true, }; static const struct mtk_dsi_driver_data mt8188_dsi_driver_data = { .reg_cmdq_off = 0xd00, + .reg_vm_cmd_off = 0x200, + .reg_shadow_dbg_off = 0xc00, .has_shadow_ctl = true, .has_size_ctl = true, .cmdq_long_packet_ctl = true, diff --git a/drivers/gpu/drm/nouveau/nouveau_acpi.c b/drivers/gpu/drm/nouveau/nouveau_acpi.c index 8f0c69aad248..21b56cc7605c 100644 --- a/drivers/gpu/drm/nouveau/nouveau_acpi.c +++ b/drivers/gpu/drm/nouveau/nouveau_acpi.c @@ -384,7 +384,7 @@ nouveau_acpi_edid(struct drm_device *dev, struct drm_connector *connector) if (ret < 0) return NULL; - return kmemdup(edid, EDID_LENGTH, GFP_KERNEL); + return edid; } bool nouveau_acpi_video_backlight_use_native(void) diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c index d6744be01a68..94d468d01253 100644 --- a/drivers/gpu/drm/xe/xe_gt.c +++ b/drivers/gpu/drm/xe/xe_gt.c @@ -387,6 +387,10 @@ int xe_gt_init_early(struct xe_gt *gt) xe_force_wake_init_gt(gt, gt_to_fw(gt)); spin_lock_init(>->global_invl_lock); + err = xe_gt_tlb_invalidation_init_early(gt); + if (err) + return err; + return 0; } @@ -588,10 +592,6 @@ int xe_gt_init(struct xe_gt *gt) xe_hw_fence_irq_init(>->fence_irq[i]); } - err = xe_gt_tlb_invalidation_init(gt); - if (err) - return err; - err = xe_gt_pagefault_init(gt); if (err) return err; diff --git a/drivers/gpu/drm/xe/xe_gt_idle.c b/drivers/gpu/drm/xe/xe_gt_idle.c index fd80afeef56a..ffd3ba7f6656 100644 --- a/drivers/gpu/drm/xe/xe_gt_idle.c +++ b/drivers/gpu/drm/xe/xe_gt_idle.c @@ -122,10 +122,12 @@ void xe_gt_idle_enable_pg(struct xe_gt *gt) if (!xe_gt_is_media_type(gt)) gtidle->powergate_enable |= RENDER_POWERGATE_ENABLE; - for (i = XE_HW_ENGINE_VCS0, j = 0; i <= XE_HW_ENGINE_VCS7; ++i, ++j) { - if ((gt->info.engine_mask & BIT(i))) - gtidle->powergate_enable |= (VDN_HCP_POWERGATE_ENABLE(j) | - VDN_MFXVDENC_POWERGATE_ENABLE(j)); + if (xe->info.platform != XE_DG1) { + for (i = XE_HW_ENGINE_VCS0, j = 0; i <= XE_HW_ENGINE_VCS7; ++i, ++j) { + if ((gt->info.engine_mask & BIT(i))) + gtidle->powergate_enable |= (VDN_HCP_POWERGATE_ENABLE(j) | + VDN_MFXVDENC_POWERGATE_ENABLE(j)); + } } fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT); diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c index 6146d1776bda..0a0af413770e 100644 --- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c +++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c @@ -106,7 +106,7 @@ static void xe_gt_tlb_fence_timeout(struct work_struct *work) } /** - * xe_gt_tlb_invalidation_init - Initialize GT TLB invalidation state + * xe_gt_tlb_invalidation_init_early - Initialize GT TLB invalidation state * @gt: graphics tile * * Initialize GT TLB invalidation state, purely software initialization, should @@ -114,7 +114,7 @@ static void xe_gt_tlb_fence_timeout(struct work_struct *work) * * Return: 0 on success, negative error code on error. */ -int xe_gt_tlb_invalidation_init(struct xe_gt *gt) +int xe_gt_tlb_invalidation_init_early(struct xe_gt *gt) { gt->tlb_invalidation.seqno = 1; INIT_LIST_HEAD(>->tlb_invalidation.pending_fences); diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h index 00b1c6c01e8d..672acfcdf0d7 100644 --- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h +++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h @@ -14,7 +14,8 @@ struct xe_gt; struct xe_guc; struct xe_vma; -int xe_gt_tlb_invalidation_init(struct xe_gt *gt); +int xe_gt_tlb_invalidation_init_early(struct xe_gt *gt); + void xe_gt_tlb_invalidation_reset(struct xe_gt *gt); int xe_gt_tlb_invalidation_ggtt(struct xe_gt *gt); int xe_gt_tlb_invalidation_vma(struct xe_gt *gt, diff --git a/drivers/hwmon/drivetemp.c b/drivers/hwmon/drivetemp.c index 6bdd21aa005a..2a4ec55ddb47 100644 --- a/drivers/hwmon/drivetemp.c +++ b/drivers/hwmon/drivetemp.c @@ -165,6 +165,7 @@ static int drivetemp_scsi_command(struct drivetemp_data *st, { u8 scsi_cmd[MAX_COMMAND_SIZE]; enum req_op op; + int err; memset(scsi_cmd, 0, sizeof(scsi_cmd)); scsi_cmd[0] = ATA_16; @@ -192,8 +193,11 @@ static int drivetemp_scsi_command(struct drivetemp_data *st, scsi_cmd[12] = lba_high; scsi_cmd[14] = ata_command; - return scsi_execute_cmd(st->sdev, scsi_cmd, op, st->smartdata, - ATA_SECT_SIZE, HZ, 5, NULL); + err = scsi_execute_cmd(st->sdev, scsi_cmd, op, st->smartdata, + ATA_SECT_SIZE, HZ, 5, NULL); + if (err > 0) + err = -EIO; + return err; } static int drivetemp_ata_command(struct drivetemp_data *st, u8 feature, diff --git a/drivers/iio/adc/ad4695.c b/drivers/iio/adc/ad4695.c index 595ec4158e73..0146aed9069f 100644 --- a/drivers/iio/adc/ad4695.c +++ b/drivers/iio/adc/ad4695.c @@ -91,6 +91,7 @@ #define AD4695_T_WAKEUP_SW_MS 3 #define AD4695_T_REFBUF_MS 100 #define AD4695_T_REGCONFIG_NS 20 +#define AD4695_T_SCK_CNV_DELAY_NS 80 #define AD4695_REG_ACCESS_SCLK_HZ (10 * MEGA) /* Max number of voltage input channels. */ @@ -132,8 +133,13 @@ struct ad4695_state { unsigned int vref_mv; /* Common mode input pin voltage. */ unsigned int com_mv; - /* 1 per voltage and temperature chan plus 1 xfer to trigger 1st CNV */ - struct spi_transfer buf_read_xfer[AD4695_MAX_CHANNELS + 2]; + /* + * 2 per voltage and temperature chan plus 1 xfer to trigger 1st + * CNV. Excluding the trigger xfer, every 2nd xfer only serves + * to control CS and add a delay between the last SCLK and next + * CNV rising edges. + */ + struct spi_transfer buf_read_xfer[AD4695_MAX_CHANNELS * 2 + 3]; struct spi_message buf_read_msg; /* Raw conversion data received. */ u8 buf[ALIGN((AD4695_MAX_CHANNELS + 2) * AD4695_MAX_CHANNEL_SIZE, @@ -423,7 +429,7 @@ static int ad4695_buffer_preenable(struct iio_dev *indio_dev) u8 temp_chan_bit = st->chip_info->num_voltage_inputs; u32 bit, num_xfer, num_slots; u32 temp_en = 0; - int ret; + int ret, rx_buf_offset = 0; /* * We are using the advanced sequencer since it is the only way to read @@ -449,11 +455,9 @@ static int ad4695_buffer_preenable(struct iio_dev *indio_dev) iio_for_each_active_channel(indio_dev, bit) { xfer = &st->buf_read_xfer[num_xfer]; xfer->bits_per_word = 16; - xfer->rx_buf = &st->buf[(num_xfer - 1) * 2]; + xfer->rx_buf = &st->buf[rx_buf_offset]; xfer->len = 2; - xfer->cs_change = 1; - xfer->cs_change_delay.value = AD4695_T_CONVERT_NS; - xfer->cs_change_delay.unit = SPI_DELAY_UNIT_NSECS; + rx_buf_offset += xfer->len; if (bit == temp_chan_bit) { temp_en = 1; @@ -468,21 +472,44 @@ static int ad4695_buffer_preenable(struct iio_dev *indio_dev) } num_xfer++; + + /* + * We need to add a blank xfer in data reads, to meet the timing + * requirement of a minimum delay between the last SCLK rising + * edge and the CS deassert. + */ + xfer = &st->buf_read_xfer[num_xfer]; + xfer->delay.value = AD4695_T_SCK_CNV_DELAY_NS; + xfer->delay.unit = SPI_DELAY_UNIT_NSECS; + xfer->cs_change = 1; + xfer->cs_change_delay.value = AD4695_T_CONVERT_NS; + xfer->cs_change_delay.unit = SPI_DELAY_UNIT_NSECS; + + num_xfer++; } /* * The advanced sequencer requires that at least 2 slots are enabled. * Since slot 0 is always used for other purposes, we need only 1 - * enabled voltage channel to meet this requirement. If the temperature - * channel is the only enabled channel, we need to add one more slot - * in the sequence but not read from it. + * enabled voltage channel to meet this requirement. If the temperature + * channel is the only enabled channel, we need to add one more slot in + * the sequence but not read from it. This is because the temperature + * sensor is sampled at the end of the channel sequence in advanced + * sequencer mode (see datasheet page 38). + * + * From the iio_for_each_active_channel() block above, we now have an + * xfer with data followed by a blank xfer to allow us to meet the + * timing spec, so move both of those up before adding an extra to + * handle the temperature-only case. */ if (num_slots < 2) { - /* move last xfer so we can insert one more xfer before it */ - st->buf_read_xfer[num_xfer] = *xfer; + /* Move last two xfers */ + st->buf_read_xfer[num_xfer] = st->buf_read_xfer[num_xfer - 1]; + st->buf_read_xfer[num_xfer - 1] = st->buf_read_xfer[num_xfer - 2]; num_xfer++; - /* modify 2nd to last xfer for extra slot */ + /* Modify inserted xfer for extra slot. */ + xfer = &st->buf_read_xfer[num_xfer - 3]; memset(xfer, 0, sizeof(*xfer)); xfer->cs_change = 1; xfer->delay.value = st->chip_info->t_acq_ns; @@ -499,6 +526,12 @@ static int ad4695_buffer_preenable(struct iio_dev *indio_dev) return ret; num_slots++; + + /* + * We still want to point at the last xfer when finished, so + * update the pointer. + */ + xfer = &st->buf_read_xfer[num_xfer - 1]; } /* @@ -583,8 +616,20 @@ out: */ static int ad4695_read_one_sample(struct ad4695_state *st, unsigned int address) { - struct spi_transfer xfer[2] = { }; - int ret, i = 0; + struct spi_transfer xfers[2] = { + { + .speed_hz = AD4695_REG_ACCESS_SCLK_HZ, + .bits_per_word = 16, + .tx_buf = &st->cnv_cmd, + .len = 2, + }, + { + /* Required delay between last SCLK and CNV/CS */ + .delay.value = AD4695_T_SCK_CNV_DELAY_NS, + .delay.unit = SPI_DELAY_UNIT_NSECS, + } + }; + int ret; ret = ad4695_set_single_cycle_mode(st, address); if (ret) @@ -592,29 +637,22 @@ static int ad4695_read_one_sample(struct ad4695_state *st, unsigned int address) /* * Setting the first channel to the temperature channel isn't supported - * in single-cycle mode, so we have to do an extra xfer to read the - * temperature. + * in single-cycle mode, so we have to do an extra conversion to read + * the temperature. */ if (address == AD4695_CMD_TEMP_CHAN) { - /* We aren't reading, so we can make this a short xfer. */ - st->cnv_cmd2 = AD4695_CMD_TEMP_CHAN << 3; - xfer[0].tx_buf = &st->cnv_cmd2; - xfer[0].len = 1; - xfer[0].cs_change = 1; - xfer[0].cs_change_delay.value = AD4695_T_CONVERT_NS; - xfer[0].cs_change_delay.unit = SPI_DELAY_UNIT_NSECS; - - i = 1; + st->cnv_cmd = AD4695_CMD_TEMP_CHAN << 11; + + ret = spi_sync_transfer(st->spi, xfers, ARRAY_SIZE(xfers)); + if (ret) + return ret; } /* Then read the result and exit conversion mode. */ st->cnv_cmd = AD4695_CMD_EXIT_CNV_MODE << 11; - xfer[i].bits_per_word = 16; - xfer[i].tx_buf = &st->cnv_cmd; - xfer[i].rx_buf = &st->raw_data; - xfer[i].len = 2; + xfers[0].rx_buf = &st->raw_data; - return spi_sync_transfer(st->spi, xfer, i + 1); + return spi_sync_transfer(st->spi, xfers, ARRAY_SIZE(xfers)); } static int ad4695_read_raw(struct iio_dev *indio_dev, diff --git a/drivers/iio/adc/ad7124.c b/drivers/iio/adc/ad7124.c index 7314fb32bdec..3d678c420cbf 100644 --- a/drivers/iio/adc/ad7124.c +++ b/drivers/iio/adc/ad7124.c @@ -917,6 +917,9 @@ static int ad7124_setup(struct ad7124_state *st) * set all channels to this default value. */ ad7124_set_channel_odr(st, i, 10); + + /* Disable all channels to prevent unintended conversions. */ + ad_sd_write_reg(&st->sd, AD7124_CHANNEL(i), 2, 0); } ret = ad_sd_write_reg(&st->sd, AD7124_ADC_CONTROL, 2, st->adc_control); diff --git a/drivers/iio/adc/ad7173.c b/drivers/iio/adc/ad7173.c index 8a0c931ca83a..8b03c1e5567e 100644 --- a/drivers/iio/adc/ad7173.c +++ b/drivers/iio/adc/ad7173.c @@ -200,6 +200,7 @@ struct ad7173_channel { struct ad7173_state { struct ad_sigma_delta sd; + struct ad_sigma_delta_info sigma_delta_info; const struct ad7173_device_info *info; struct ad7173_channel *channels; struct regulator_bulk_data regulators[3]; @@ -753,7 +754,7 @@ static int ad7173_disable_one(struct ad_sigma_delta *sd, unsigned int chan) return ad_sd_write_reg(sd, AD7173_REG_CH(chan), 2, 0); } -static struct ad_sigma_delta_info ad7173_sigma_delta_info = { +static const struct ad_sigma_delta_info ad7173_sigma_delta_info = { .set_channel = ad7173_set_channel, .append_status = ad7173_append_status, .disable_all = ad7173_disable_all, @@ -1403,7 +1404,7 @@ static int ad7173_fw_parse_device_config(struct iio_dev *indio_dev) if (ret < 0) return dev_err_probe(dev, ret, "Interrupt 'rdy' is required\n"); - ad7173_sigma_delta_info.irq_line = ret; + st->sigma_delta_info.irq_line = ret; return ad7173_fw_parse_channel_config(indio_dev); } @@ -1436,8 +1437,9 @@ static int ad7173_probe(struct spi_device *spi) spi->mode = SPI_MODE_3; spi_setup(spi); - ad7173_sigma_delta_info.num_slots = st->info->num_configs; - ret = ad_sd_init(&st->sd, indio_dev, spi, &ad7173_sigma_delta_info); + st->sigma_delta_info = ad7173_sigma_delta_info; + st->sigma_delta_info.num_slots = st->info->num_configs; + ret = ad_sd_init(&st->sd, indio_dev, spi, &st->sigma_delta_info); if (ret) return ret; diff --git a/drivers/iio/adc/ad9467.c b/drivers/iio/adc/ad9467.c index d358958ab310..f30119b42ba0 100644 --- a/drivers/iio/adc/ad9467.c +++ b/drivers/iio/adc/ad9467.c @@ -895,7 +895,7 @@ static int ad9467_update_scan_mode(struct iio_dev *indio_dev, return 0; } -static struct iio_info ad9467_info = { +static const struct iio_info ad9467_info = { .read_raw = ad9467_read_raw, .write_raw = ad9467_write_raw, .update_scan_mode = ad9467_update_scan_mode, @@ -903,6 +903,14 @@ static struct iio_info ad9467_info = { .read_avail = ad9467_read_avail, }; +/* Same as above, but without .read_avail */ +static const struct iio_info ad9467_info_no_read_avail = { + .read_raw = ad9467_read_raw, + .write_raw = ad9467_write_raw, + .update_scan_mode = ad9467_update_scan_mode, + .debugfs_reg_access = ad9467_reg_access, +}; + static int ad9467_scale_fill(struct ad9467_state *st) { const struct ad9467_chip_info *info = st->info; @@ -1214,11 +1222,12 @@ static int ad9467_probe(struct spi_device *spi) } if (st->info->num_scales > 1) - ad9467_info.read_avail = ad9467_read_avail; + indio_dev->info = &ad9467_info; + else + indio_dev->info = &ad9467_info_no_read_avail; indio_dev->name = st->info->name; indio_dev->channels = st->info->channels; indio_dev->num_channels = st->info->num_channels; - indio_dev->info = &ad9467_info; ret = ad9467_iio_backend_get(st); if (ret) diff --git a/drivers/iio/adc/at91_adc.c b/drivers/iio/adc/at91_adc.c index a3f0a2321666..5927756b749a 100644 --- a/drivers/iio/adc/at91_adc.c +++ b/drivers/iio/adc/at91_adc.c @@ -979,7 +979,7 @@ static int at91_ts_register(struct iio_dev *idev, return ret; err: - input_free_device(st->ts_input); + input_free_device(input); return ret; } diff --git a/drivers/iio/adc/rockchip_saradc.c b/drivers/iio/adc/rockchip_saradc.c index 240cfa391674..dfd47a6e1f4a 100644 --- a/drivers/iio/adc/rockchip_saradc.c +++ b/drivers/iio/adc/rockchip_saradc.c @@ -368,6 +368,8 @@ static irqreturn_t rockchip_saradc_trigger_handler(int irq, void *p) int ret; int i, j = 0; + memset(&data, 0, sizeof(data)); + mutex_lock(&info->lock); iio_for_each_active_channel(i_dev, i) { diff --git a/drivers/iio/adc/stm32-dfsdm-adc.c b/drivers/iio/adc/stm32-dfsdm-adc.c index 1f9eca2fb2bf..fe11b0d8eab3 100644 --- a/drivers/iio/adc/stm32-dfsdm-adc.c +++ b/drivers/iio/adc/stm32-dfsdm-adc.c @@ -691,11 +691,14 @@ static int stm32_dfsdm_generic_channel_parse_of(struct stm32_dfsdm *dfsdm, return -EINVAL; } - ret = fwnode_property_read_string(node, "label", &ch->datasheet_name); - if (ret < 0) { - dev_err(&indio_dev->dev, - " Error parsing 'label' for idx %d\n", ch->channel); - return ret; + if (fwnode_property_present(node, "label")) { + /* label is optional */ + ret = fwnode_property_read_string(node, "label", &ch->datasheet_name); + if (ret < 0) { + dev_err(&indio_dev->dev, + " Error parsing 'label' for idx %d\n", ch->channel); + return ret; + } } df_ch = &dfsdm->ch_list[ch->channel]; diff --git a/drivers/iio/adc/ti-ads1119.c b/drivers/iio/adc/ti-ads1119.c index e9d9d4d46d38..c268e27eec12 100644 --- a/drivers/iio/adc/ti-ads1119.c +++ b/drivers/iio/adc/ti-ads1119.c @@ -500,12 +500,14 @@ static irqreturn_t ads1119_trigger_handler(int irq, void *private) struct iio_dev *indio_dev = pf->indio_dev; struct ads1119_state *st = iio_priv(indio_dev); struct { - unsigned int sample; + s16 sample; s64 timestamp __aligned(8); } scan; unsigned int index; int ret; + memset(&scan, 0, sizeof(scan)); + if (!iio_trigger_using_own(indio_dev)) { index = find_first_bit(indio_dev->active_scan_mask, iio_get_masklength(indio_dev)); diff --git a/drivers/iio/adc/ti-ads124s08.c b/drivers/iio/adc/ti-ads124s08.c index 425b48d8986f..f452f57f11c9 100644 --- a/drivers/iio/adc/ti-ads124s08.c +++ b/drivers/iio/adc/ti-ads124s08.c @@ -183,9 +183,9 @@ static int ads124s_reset(struct iio_dev *indio_dev) struct ads124s_private *priv = iio_priv(indio_dev); if (priv->reset_gpio) { - gpiod_set_value(priv->reset_gpio, 0); + gpiod_set_value_cansleep(priv->reset_gpio, 0); udelay(200); - gpiod_set_value(priv->reset_gpio, 1); + gpiod_set_value_cansleep(priv->reset_gpio, 1); } else { return ads124s_write_cmd(indio_dev, ADS124S08_CMD_RESET); } diff --git a/drivers/iio/adc/ti-ads1298.c b/drivers/iio/adc/ti-ads1298.c index 36d43495f603..03f762415fa5 100644 --- a/drivers/iio/adc/ti-ads1298.c +++ b/drivers/iio/adc/ti-ads1298.c @@ -613,6 +613,8 @@ static int ads1298_init(struct iio_dev *indio_dev) } indio_dev->name = devm_kasprintf(dev, GFP_KERNEL, "ads129%u%s", indio_dev->num_channels, suffix); + if (!indio_dev->name) + return -ENOMEM; /* Enable internal test signal, double amplitude, double frequency */ ret = regmap_write(priv->regmap, ADS1298_REG_CONFIG2, diff --git a/drivers/iio/adc/ti-ads8688.c b/drivers/iio/adc/ti-ads8688.c index 9b1814f1965a..a31658b760a4 100644 --- a/drivers/iio/adc/ti-ads8688.c +++ b/drivers/iio/adc/ti-ads8688.c @@ -381,7 +381,7 @@ static irqreturn_t ads8688_trigger_handler(int irq, void *p) struct iio_poll_func *pf = p; struct iio_dev *indio_dev = pf->indio_dev; /* Ensure naturally aligned timestamp */ - u16 buffer[ADS8688_MAX_CHANNELS + sizeof(s64)/sizeof(u16)] __aligned(8); + u16 buffer[ADS8688_MAX_CHANNELS + sizeof(s64)/sizeof(u16)] __aligned(8) = { }; int i, j = 0; iio_for_each_active_channel(indio_dev, i) { diff --git a/drivers/iio/dummy/iio_simple_dummy_buffer.c b/drivers/iio/dummy/iio_simple_dummy_buffer.c index 4ca3f1aaff99..288880346707 100644 --- a/drivers/iio/dummy/iio_simple_dummy_buffer.c +++ b/drivers/iio/dummy/iio_simple_dummy_buffer.c @@ -48,7 +48,7 @@ static irqreturn_t iio_simple_dummy_trigger_h(int irq, void *p) int i = 0, j; u16 *data; - data = kmalloc(indio_dev->scan_bytes, GFP_KERNEL); + data = kzalloc(indio_dev->scan_bytes, GFP_KERNEL); if (!data) goto done; diff --git a/drivers/iio/gyro/fxas21002c_core.c b/drivers/iio/gyro/fxas21002c_core.c index 0391c78c2f18..754c8a564ba4 100644 --- a/drivers/iio/gyro/fxas21002c_core.c +++ b/drivers/iio/gyro/fxas21002c_core.c @@ -730,14 +730,21 @@ static irqreturn_t fxas21002c_trigger_handler(int irq, void *p) int ret; mutex_lock(&data->lock); + ret = fxas21002c_pm_get(data); + if (ret < 0) + goto out_unlock; + ret = regmap_bulk_read(data->regmap, FXAS21002C_REG_OUT_X_MSB, data->buffer, CHANNEL_SCAN_MAX * sizeof(s16)); if (ret < 0) - goto out_unlock; + goto out_pm_put; iio_push_to_buffers_with_timestamp(indio_dev, data->buffer, data->timestamp); +out_pm_put: + fxas21002c_pm_put(data); + out_unlock: mutex_unlock(&data->lock); diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600.h b/drivers/iio/imu/inv_icm42600/inv_icm42600.h index 3a07e43e4cf1..18787a43477b 100644 --- a/drivers/iio/imu/inv_icm42600/inv_icm42600.h +++ b/drivers/iio/imu/inv_icm42600/inv_icm42600.h @@ -403,6 +403,7 @@ struct inv_icm42600_sensor_state { typedef int (*inv_icm42600_bus_setup)(struct inv_icm42600_state *); extern const struct regmap_config inv_icm42600_regmap_config; +extern const struct regmap_config inv_icm42600_spi_regmap_config; extern const struct dev_pm_ops inv_icm42600_pm_ops; const struct iio_mount_matrix * diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_core.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_core.c index 561d245c1d64..ef9875d3b79d 100644 --- a/drivers/iio/imu/inv_icm42600/inv_icm42600_core.c +++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_core.c @@ -87,6 +87,21 @@ const struct regmap_config inv_icm42600_regmap_config = { }; EXPORT_SYMBOL_NS_GPL(inv_icm42600_regmap_config, "IIO_ICM42600"); +/* define specific regmap for SPI not supporting burst write */ +const struct regmap_config inv_icm42600_spi_regmap_config = { + .name = "inv_icm42600", + .reg_bits = 8, + .val_bits = 8, + .max_register = 0x4FFF, + .ranges = inv_icm42600_regmap_ranges, + .num_ranges = ARRAY_SIZE(inv_icm42600_regmap_ranges), + .volatile_table = inv_icm42600_regmap_volatile_accesses, + .rd_noinc_table = inv_icm42600_regmap_rd_noinc_accesses, + .cache_type = REGCACHE_RBTREE, + .use_single_write = true, +}; +EXPORT_SYMBOL_NS_GPL(inv_icm42600_spi_regmap_config, "IIO_ICM42600"); + struct inv_icm42600_hw { uint8_t whoami; const char *name; @@ -814,6 +829,8 @@ out_unlock: static int inv_icm42600_resume(struct device *dev) { struct inv_icm42600_state *st = dev_get_drvdata(dev); + struct inv_icm42600_sensor_state *gyro_st = iio_priv(st->indio_gyro); + struct inv_icm42600_sensor_state *accel_st = iio_priv(st->indio_accel); int ret; mutex_lock(&st->lock); @@ -834,9 +851,12 @@ static int inv_icm42600_resume(struct device *dev) goto out_unlock; /* restore FIFO data streaming */ - if (st->fifo.on) + if (st->fifo.on) { + inv_sensors_timestamp_reset(&gyro_st->ts); + inv_sensors_timestamp_reset(&accel_st->ts); ret = regmap_write(st->map, INV_ICM42600_REG_FIFO_CONFIG, INV_ICM42600_FIFO_CONFIG_STREAM); + } out_unlock: mutex_unlock(&st->lock); diff --git a/drivers/iio/imu/inv_icm42600/inv_icm42600_spi.c b/drivers/iio/imu/inv_icm42600/inv_icm42600_spi.c index c55d8e672183..2bd2c4c8e50c 100644 --- a/drivers/iio/imu/inv_icm42600/inv_icm42600_spi.c +++ b/drivers/iio/imu/inv_icm42600/inv_icm42600_spi.c @@ -59,7 +59,8 @@ static int inv_icm42600_probe(struct spi_device *spi) return -EINVAL; chip = (uintptr_t)match; - regmap = devm_regmap_init_spi(spi, &inv_icm42600_regmap_config); + /* use SPI specific regmap */ + regmap = devm_regmap_init_spi(spi, &inv_icm42600_spi_regmap_config); if (IS_ERR(regmap)) return PTR_ERR(regmap); diff --git a/drivers/iio/imu/kmx61.c b/drivers/iio/imu/kmx61.c index 324c38764656..e19c5d3137c6 100644 --- a/drivers/iio/imu/kmx61.c +++ b/drivers/iio/imu/kmx61.c @@ -1193,7 +1193,7 @@ static irqreturn_t kmx61_trigger_handler(int irq, void *p) struct kmx61_data *data = kmx61_get_data(indio_dev); int bit, ret, i = 0; u8 base; - s16 buffer[8]; + s16 buffer[8] = { }; if (indio_dev == data->acc_indio_dev) base = KMX61_ACC_XOUT_L; diff --git a/drivers/iio/inkern.c b/drivers/iio/inkern.c index 136b225b6bc8..9050a59129e6 100644 --- a/drivers/iio/inkern.c +++ b/drivers/iio/inkern.c @@ -500,7 +500,7 @@ struct iio_channel *iio_channel_get_all(struct device *dev) return_ptr(chans); error_free_chans: - for (i = 0; i < nummaps; i++) + for (i = 0; i < mapind; i++) iio_device_put(chans[i].indio_dev); return ERR_PTR(ret); } diff --git a/drivers/iio/light/bh1745.c b/drivers/iio/light/bh1745.c index 56e32689bb97..63bf729df517 100644 --- a/drivers/iio/light/bh1745.c +++ b/drivers/iio/light/bh1745.c @@ -746,6 +746,8 @@ static irqreturn_t bh1745_trigger_handler(int interrupt, void *p) int i; int j = 0; + memset(&scan, 0, sizeof(scan)); + iio_for_each_active_channel(indio_dev, i) { ret = regmap_bulk_read(data->regmap, BH1745_RED_LSB + 2 * i, &value, 2); diff --git a/drivers/iio/light/vcnl4035.c b/drivers/iio/light/vcnl4035.c index 337a1332c2c6..67c94be02018 100644 --- a/drivers/iio/light/vcnl4035.c +++ b/drivers/iio/light/vcnl4035.c @@ -105,7 +105,7 @@ static irqreturn_t vcnl4035_trigger_consumer_handler(int irq, void *p) struct iio_dev *indio_dev = pf->indio_dev; struct vcnl4035_data *data = iio_priv(indio_dev); /* Ensure naturally aligned timestamp */ - u8 buffer[ALIGN(sizeof(u16), sizeof(s64)) + sizeof(s64)] __aligned(8); + u8 buffer[ALIGN(sizeof(u16), sizeof(s64)) + sizeof(s64)] __aligned(8) = { }; int ret; ret = regmap_read(data->regmap, VCNL4035_ALS_DATA, (int *)buffer); diff --git a/drivers/iio/pressure/zpa2326.c b/drivers/iio/pressure/zpa2326.c index 2adea84f5b4d..9db1c94dfc18 100644 --- a/drivers/iio/pressure/zpa2326.c +++ b/drivers/iio/pressure/zpa2326.c @@ -586,6 +586,8 @@ static int zpa2326_fill_sample_buffer(struct iio_dev *indio_dev, } sample; int err; + memset(&sample, 0, sizeof(sample)); + if (test_bit(0, indio_dev->active_scan_mask)) { /* Get current pressure from hardware FIFO. */ err = zpa2326_dequeue_pressure(indio_dev, &sample.pressure); diff --git a/drivers/iio/temperature/tmp006.c b/drivers/iio/temperature/tmp006.c index 0c844137d7aa..02b27f471baa 100644 --- a/drivers/iio/temperature/tmp006.c +++ b/drivers/iio/temperature/tmp006.c @@ -252,6 +252,8 @@ static irqreturn_t tmp006_trigger_handler(int irq, void *p) } scan; s32 ret; + memset(&scan, 0, sizeof(scan)); + ret = i2c_smbus_read_word_data(data->client, TMP006_VOBJECT); if (ret < 0) goto err; diff --git a/drivers/iio/test/Kconfig b/drivers/iio/test/Kconfig index 33cca49c8058..7a181cac3cc9 100644 --- a/drivers/iio/test/Kconfig +++ b/drivers/iio/test/Kconfig @@ -5,7 +5,7 @@ # Keep in alphabetical order config IIO_GTS_KUNIT_TEST - tristate "Test IIO formatting functions" if !KUNIT_ALL_TESTS + tristate "Test IIO gain-time-scale helpers" if !KUNIT_ALL_TESTS depends on KUNIT select IIO_GTS_HELPER select TEST_KUNIT_DEVICE_HELPERS diff --git a/drivers/iio/test/iio-test-rescale.c b/drivers/iio/test/iio-test-rescale.c index cbf13337ed1f..bbc6a2e1c2c1 100644 --- a/drivers/iio/test/iio-test-rescale.c +++ b/drivers/iio/test/iio-test-rescale.c @@ -652,6 +652,8 @@ static void iio_rescale_test_scale(struct kunit *test) int rel_ppm; int ret; + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, buff); + rescale.numerator = t->numerator; rescale.denominator = t->denominator; rescale.offset = t->offset; @@ -681,6 +683,8 @@ static void iio_rescale_test_offset(struct kunit *test) int values[2]; int ret; + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, buff_off); + rescale.numerator = t->numerator; rescale.denominator = t->denominator; rescale.offset = t->offset; diff --git a/drivers/interconnect/icc-clk.c b/drivers/interconnect/icc-clk.c index b956e4050f38..88f311c11020 100644 --- a/drivers/interconnect/icc-clk.c +++ b/drivers/interconnect/icc-clk.c @@ -116,6 +116,11 @@ struct icc_provider *icc_clk_register(struct device *dev, } node->name = devm_kasprintf(dev, GFP_KERNEL, "%s_master", data[i].name); + if (!node->name) { + ret = -ENOMEM; + goto err; + } + node->data = &qp->clocks[i]; icc_node_add(node, provider); /* link to the next node, slave */ @@ -129,6 +134,11 @@ struct icc_provider *icc_clk_register(struct device *dev, } node->name = devm_kasprintf(dev, GFP_KERNEL, "%s_slave", data[i].name); + if (!node->name) { + ret = -ENOMEM; + goto err; + } + /* no data for slave node */ icc_node_add(node, provider); onecell->nodes[j++] = node; diff --git a/drivers/interconnect/qcom/icc-rpm.c b/drivers/interconnect/qcom/icc-rpm.c index a8ed435f696c..ea1042d38128 100644 --- a/drivers/interconnect/qcom/icc-rpm.c +++ b/drivers/interconnect/qcom/icc-rpm.c @@ -503,6 +503,7 @@ int qnoc_probe(struct platform_device *pdev) GFP_KERNEL); if (!data) return -ENOMEM; + data->num_nodes = num_nodes; qp->num_intf_clks = cd_num; for (i = 0; i < cd_num; i++) @@ -597,7 +598,6 @@ regmap_done: data->nodes[i] = node; } - data->num_nodes = num_nodes; clk_bulk_disable_unprepare(qp->num_intf_clks, qp->intf_clks); diff --git a/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c b/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c index e616e3ec2b42..3c1359d8d4e6 100644 --- a/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c +++ b/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c @@ -148,7 +148,7 @@ static int pci1xxxx_gpio_set_config(struct gpio_chip *gpio, unsigned int offset, pci1xxx_assign_bit(priv->reg_base, OPENDRAIN_OFFSET(offset), (offset % 32), true); break; default: - ret = -EOPNOTSUPP; + ret = -ENOTSUPP; break; } spin_unlock_irqrestore(&priv->lock, flags); @@ -277,7 +277,7 @@ static irqreturn_t pci1xxxx_gpio_irq_handler(int irq, void *dev_id) writel(BIT(bit), priv->reg_base + INTR_STATUS_OFFSET(gpiobank)); spin_unlock_irqrestore(&priv->lock, flags); irq = irq_find_mapping(gc->irq.domain, (bit + (gpiobank * 32))); - generic_handle_irq(irq); + handle_nested_irq(irq); } } spin_lock_irqsave(&priv->lock, flags); diff --git a/drivers/net/can/dev/dev.c b/drivers/net/can/dev/dev.c index 681643ab3780..5ec3170b896a 100644 --- a/drivers/net/can/dev/dev.c +++ b/drivers/net/can/dev/dev.c @@ -85,8 +85,6 @@ const char *can_get_state_str(const enum can_state state) default: return "<unknown>"; } - - return "<unknown>"; } EXPORT_SYMBOL_GPL(can_get_state_str); diff --git a/drivers/net/can/grcan.c b/drivers/net/can/grcan.c index cdf0ec9fa7f3..21a61b86f67d 100644 --- a/drivers/net/can/grcan.c +++ b/drivers/net/can/grcan.c @@ -1073,9 +1073,10 @@ static int grcan_open(struct net_device *dev) if (err) goto exit_close_candev; + napi_enable(&priv->napi); + spin_lock_irqsave(&priv->lock, flags); - napi_enable(&priv->napi); grcan_start(dev); if (!(priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY)) netif_start_queue(dev); diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c index fee012b57f33..fa04a7ced02b 100644 --- a/drivers/net/can/kvaser_pciefd.c +++ b/drivers/net/can/kvaser_pciefd.c @@ -999,7 +999,8 @@ static int kvaser_pciefd_setup_can_ctrls(struct kvaser_pciefd *pcie) can->can.ctrlmode_supported = CAN_CTRLMODE_LISTENONLY | CAN_CTRLMODE_FD | CAN_CTRLMODE_FD_NON_ISO | - CAN_CTRLMODE_CC_LEN8_DLC; + CAN_CTRLMODE_CC_LEN8_DLC | + CAN_CTRLMODE_BERR_REPORTING; status = ioread32(can->reg_base + KVASER_PCIEFD_KCAN_STAT_REG); if (!(status & KVASER_PCIEFD_KCAN_STAT_FD)) { @@ -1234,11 +1235,15 @@ static int kvaser_pciefd_handle_data_packet(struct kvaser_pciefd *pcie, } static void kvaser_pciefd_change_state(struct kvaser_pciefd_can *can, + const struct can_berr_counter *bec, struct can_frame *cf, enum can_state new_state, enum can_state tx_state, enum can_state rx_state) { + enum can_state old_state; + + old_state = can->can.state; can_change_state(can->can.dev, cf, tx_state, rx_state); if (new_state == CAN_STATE_BUS_OFF) { @@ -1254,6 +1259,18 @@ static void kvaser_pciefd_change_state(struct kvaser_pciefd_can *can, can_bus_off(ndev); } } + if (old_state == CAN_STATE_BUS_OFF && + new_state == CAN_STATE_ERROR_ACTIVE && + can->can.restart_ms) { + can->can.can_stats.restarts++; + if (cf) + cf->can_id |= CAN_ERR_RESTARTED; + } + if (cf && new_state != CAN_STATE_BUS_OFF) { + cf->can_id |= CAN_ERR_CNT; + cf->data[6] = bec->txerr; + cf->data[7] = bec->rxerr; + } } static void kvaser_pciefd_packet_to_state(struct kvaser_pciefd_rx_packet *p, @@ -1288,7 +1305,7 @@ static int kvaser_pciefd_rx_error_frame(struct kvaser_pciefd_can *can, struct can_berr_counter bec; enum can_state old_state, new_state, tx_state, rx_state; struct net_device *ndev = can->can.dev; - struct sk_buff *skb; + struct sk_buff *skb = NULL; struct can_frame *cf = NULL; old_state = can->can.state; @@ -1297,16 +1314,10 @@ static int kvaser_pciefd_rx_error_frame(struct kvaser_pciefd_can *can, bec.rxerr = FIELD_GET(KVASER_PCIEFD_SPACK_RXERR_MASK, p->header[0]); kvaser_pciefd_packet_to_state(p, &bec, &new_state, &tx_state, &rx_state); - skb = alloc_can_err_skb(ndev, &cf); + if (can->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING) + skb = alloc_can_err_skb(ndev, &cf); if (new_state != old_state) { - kvaser_pciefd_change_state(can, cf, new_state, tx_state, rx_state); - if (old_state == CAN_STATE_BUS_OFF && - new_state == CAN_STATE_ERROR_ACTIVE && - can->can.restart_ms) { - can->can.can_stats.restarts++; - if (skb) - cf->can_id |= CAN_ERR_RESTARTED; - } + kvaser_pciefd_change_state(can, &bec, cf, new_state, tx_state, rx_state); } can->err_rep_cnt++; @@ -1319,18 +1330,19 @@ static int kvaser_pciefd_rx_error_frame(struct kvaser_pciefd_can *can, can->bec.txerr = bec.txerr; can->bec.rxerr = bec.rxerr; - if (!skb) { - ndev->stats.rx_dropped++; - return -ENOMEM; + if (can->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING) { + if (!skb) { + netdev_warn(ndev, "No memory left for err_skb\n"); + ndev->stats.rx_dropped++; + return -ENOMEM; + } + kvaser_pciefd_set_skb_timestamp(can->kv_pcie, skb, p->timestamp); + cf->can_id |= CAN_ERR_BUSERROR | CAN_ERR_CNT; + cf->data[6] = bec.txerr; + cf->data[7] = bec.rxerr; + netif_rx(skb); } - kvaser_pciefd_set_skb_timestamp(can->kv_pcie, skb, p->timestamp); - cf->can_id |= CAN_ERR_BUSERROR | CAN_ERR_CNT; - cf->data[6] = bec.txerr; - cf->data[7] = bec.rxerr; - - netif_rx(skb); - return 0; } @@ -1359,6 +1371,7 @@ static int kvaser_pciefd_handle_status_resp(struct kvaser_pciefd_can *can, { struct can_berr_counter bec; enum can_state old_state, new_state, tx_state, rx_state; + int ret = 0; old_state = can->can.state; @@ -1372,25 +1385,15 @@ static int kvaser_pciefd_handle_status_resp(struct kvaser_pciefd_can *can, struct can_frame *cf; skb = alloc_can_err_skb(ndev, &cf); - if (!skb) { + kvaser_pciefd_change_state(can, &bec, cf, new_state, tx_state, rx_state); + if (skb) { + kvaser_pciefd_set_skb_timestamp(can->kv_pcie, skb, p->timestamp); + netif_rx(skb); + } else { ndev->stats.rx_dropped++; - return -ENOMEM; + netdev_warn(ndev, "No memory left for err_skb\n"); + ret = -ENOMEM; } - - kvaser_pciefd_change_state(can, cf, new_state, tx_state, rx_state); - if (old_state == CAN_STATE_BUS_OFF && - new_state == CAN_STATE_ERROR_ACTIVE && - can->can.restart_ms) { - can->can.can_stats.restarts++; - cf->can_id |= CAN_ERR_RESTARTED; - } - - kvaser_pciefd_set_skb_timestamp(can->kv_pcie, skb, p->timestamp); - - cf->data[6] = bec.txerr; - cf->data[7] = bec.rxerr; - - netif_rx(skb); } can->bec.txerr = bec.txerr; can->bec.rxerr = bec.rxerr; @@ -1398,7 +1401,7 @@ static int kvaser_pciefd_handle_status_resp(struct kvaser_pciefd_can *can, if (bec.txerr || bec.rxerr) mod_timer(&can->bec_poll_timer, KVASER_PCIEFD_BEC_POLL_FREQ); - return 0; + return ret; } static int kvaser_pciefd_handle_status_packet(struct kvaser_pciefd *pcie, diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index 97cd8bbf2e32..d025d4163fd1 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -1785,6 +1785,13 @@ static void m_can_stop(struct net_device *dev) /* set the state as STOPPED */ cdev->can.state = CAN_STATE_STOPPED; + + if (cdev->ops->deinit) { + ret = cdev->ops->deinit(cdev); + if (ret) + netdev_err(dev, "failed to deinitialize: %pe\n", + ERR_PTR(ret)); + } } static int m_can_close(struct net_device *dev) @@ -2466,6 +2473,7 @@ int m_can_class_suspend(struct device *dev) { struct m_can_classdev *cdev = dev_get_drvdata(dev); struct net_device *ndev = cdev->net; + int ret = 0; if (netif_running(ndev)) { netif_stop_queue(ndev); @@ -2478,6 +2486,9 @@ int m_can_class_suspend(struct device *dev) if (cdev->pm_wake_source) { hrtimer_cancel(&cdev->hrtimer); m_can_write(cdev, M_CAN_IE, IR_RF0N); + + if (cdev->ops->deinit) + ret = cdev->ops->deinit(cdev); } else { m_can_stop(ndev); } @@ -2489,7 +2500,7 @@ int m_can_class_suspend(struct device *dev) cdev->can.state = CAN_STATE_SLEEPING; - return 0; + return ret; } EXPORT_SYMBOL_GPL(m_can_class_suspend); @@ -2497,14 +2508,13 @@ int m_can_class_resume(struct device *dev) { struct m_can_classdev *cdev = dev_get_drvdata(dev); struct net_device *ndev = cdev->net; + int ret = 0; pinctrl_pm_select_default_state(dev); cdev->can.state = CAN_STATE_ERROR_ACTIVE; if (netif_running(ndev)) { - int ret; - ret = m_can_clk_start(cdev); if (ret) return ret; @@ -2517,6 +2527,10 @@ int m_can_class_resume(struct device *dev) * again. */ cdev->active_interrupts |= IR_RF0N | IR_TEFN; + + if (cdev->ops->init) + ret = cdev->ops->init(cdev); + m_can_write(cdev, M_CAN_IE, cdev->active_interrupts); } else { ret = m_can_start(ndev); @@ -2530,7 +2544,7 @@ int m_can_class_resume(struct device *dev) netif_start_queue(ndev); } - return 0; + return ret; } EXPORT_SYMBOL_GPL(m_can_class_resume); diff --git a/drivers/net/can/m_can/m_can.h b/drivers/net/can/m_can/m_can.h index ef39e8e527ab..bd4746c63af3 100644 --- a/drivers/net/can/m_can/m_can.h +++ b/drivers/net/can/m_can/m_can.h @@ -68,6 +68,7 @@ struct m_can_ops { int (*write_fifo)(struct m_can_classdev *cdev, int addr_offset, const void *val, size_t val_count); int (*init)(struct m_can_classdev *cdev); + int (*deinit)(struct m_can_classdev *cdev); }; struct m_can_tx_op { diff --git a/drivers/net/can/m_can/tcan4x5x-core.c b/drivers/net/can/m_can/tcan4x5x-core.c index 2f73bf3abad8..e5c162f8c589 100644 --- a/drivers/net/can/m_can/tcan4x5x-core.c +++ b/drivers/net/can/m_can/tcan4x5x-core.c @@ -92,6 +92,8 @@ #define TCAN4X5X_MODE_STANDBY BIT(6) #define TCAN4X5X_MODE_NORMAL BIT(7) +#define TCAN4X5X_NWKRQ_VOLTAGE_VIO BIT(19) + #define TCAN4X5X_DISABLE_WAKE_MSK (BIT(31) | BIT(30)) #define TCAN4X5X_DISABLE_INH_MSK BIT(9) @@ -267,9 +269,24 @@ static int tcan4x5x_init(struct m_can_classdev *cdev) if (ret) return ret; + if (tcan4x5x->nwkrq_voltage_vio) { + ret = regmap_set_bits(tcan4x5x->regmap, TCAN4X5X_CONFIG, + TCAN4X5X_NWKRQ_VOLTAGE_VIO); + if (ret) + return ret; + } + return ret; } +static int tcan4x5x_deinit(struct m_can_classdev *cdev) +{ + struct tcan4x5x_priv *tcan4x5x = cdev_to_priv(cdev); + + return regmap_update_bits(tcan4x5x->regmap, TCAN4X5X_CONFIG, + TCAN4X5X_MODE_SEL_MASK, TCAN4X5X_MODE_STANDBY); +}; + static int tcan4x5x_disable_wake(struct m_can_classdev *cdev) { struct tcan4x5x_priv *tcan4x5x = cdev_to_priv(cdev); @@ -318,6 +335,14 @@ static const struct tcan4x5x_version_info return &tcan4x5x_versions[TCAN4X5X]; } +static void tcan4x5x_get_dt_data(struct m_can_classdev *cdev) +{ + struct tcan4x5x_priv *tcan4x5x = cdev_to_priv(cdev); + + tcan4x5x->nwkrq_voltage_vio = + of_property_read_bool(cdev->dev->of_node, "ti,nwkrq-voltage-vio"); +} + static int tcan4x5x_get_gpios(struct m_can_classdev *cdev, const struct tcan4x5x_version_info *version_info) { @@ -359,6 +384,7 @@ static int tcan4x5x_get_gpios(struct m_can_classdev *cdev, static const struct m_can_ops tcan4x5x_ops = { .init = tcan4x5x_init, + .deinit = tcan4x5x_deinit, .read_reg = tcan4x5x_read_reg, .write_reg = tcan4x5x_write_reg, .write_fifo = tcan4x5x_write_fifo, @@ -392,7 +418,7 @@ static int tcan4x5x_can_probe(struct spi_device *spi) priv->power = NULL; } - m_can_class_get_clocks(mcan_class); + mcan_class->cclk = devm_clk_get(mcan_class->dev, "cclk"); if (IS_ERR(mcan_class->cclk)) { dev_err(&spi->dev, "no CAN clock source defined\n"); freq = TCAN4X5X_EXT_CLK_DEF; @@ -453,6 +479,8 @@ static int tcan4x5x_can_probe(struct spi_device *spi) goto out_power; } + tcan4x5x_get_dt_data(mcan_class); + tcan4x5x_check_wake(priv); ret = tcan4x5x_write_tcan_reg(mcan_class, TCAN4X5X_INT_EN, 0); diff --git a/drivers/net/can/m_can/tcan4x5x.h b/drivers/net/can/m_can/tcan4x5x.h index e62c030d3e1e..203399d5e8cc 100644 --- a/drivers/net/can/m_can/tcan4x5x.h +++ b/drivers/net/can/m_can/tcan4x5x.h @@ -42,6 +42,8 @@ struct tcan4x5x_priv { struct tcan4x5x_map_buf map_buf_rx; struct tcan4x5x_map_buf map_buf_tx; + + bool nwkrq_voltage_vio; }; static inline void diff --git a/drivers/net/can/sun4i_can.c b/drivers/net/can/sun4i_can.c index 4311c1f0eafd..6fcb301ef611 100644 --- a/drivers/net/can/sun4i_can.c +++ b/drivers/net/can/sun4i_can.c @@ -570,7 +570,7 @@ static int sun4i_can_err(struct net_device *dev, u8 isrc, u8 status) else state = CAN_STATE_ERROR_ACTIVE; } - if (skb && state != CAN_STATE_BUS_OFF) { + if (likely(skb) && state != CAN_STATE_BUS_OFF) { cf->can_id |= CAN_ERR_CNT; cf->data[6] = txerr; cf->data[7] = rxerr; diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c index 7d12776ab63e..dcb0bcbe0565 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c @@ -818,7 +818,8 @@ static int kvaser_usb_init_one(struct kvaser_usb *dev, int channel) init_completion(&priv->stop_comp); init_completion(&priv->flush_comp); init_completion(&priv->get_busparams_comp); - priv->can.ctrlmode_supported = CAN_CTRLMODE_CC_LEN8_DLC; + priv->can.ctrlmode_supported = CAN_CTRLMODE_CC_LEN8_DLC | + CAN_CTRLMODE_BERR_REPORTING; priv->dev = dev; priv->netdev = netdev; diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c index 3764b263add3..8e88b5917796 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c @@ -926,6 +926,42 @@ kvaser_usb_hydra_bus_status_to_can_state(const struct kvaser_usb_net_priv *priv, } } +static void kvaser_usb_hydra_change_state(struct kvaser_usb_net_priv *priv, + const struct can_berr_counter *bec, + struct can_frame *cf, + enum can_state new_state) +{ + struct net_device *netdev = priv->netdev; + enum can_state old_state = priv->can.state; + enum can_state tx_state, rx_state; + + tx_state = (bec->txerr >= bec->rxerr) ? + new_state : CAN_STATE_ERROR_ACTIVE; + rx_state = (bec->txerr <= bec->rxerr) ? + new_state : CAN_STATE_ERROR_ACTIVE; + can_change_state(netdev, cf, tx_state, rx_state); + + if (new_state == CAN_STATE_BUS_OFF && old_state < CAN_STATE_BUS_OFF) { + if (priv->can.restart_ms == 0) + kvaser_usb_hydra_send_simple_cmd_async(priv, CMD_STOP_CHIP_REQ); + + can_bus_off(netdev); + } + + if (priv->can.restart_ms && + old_state >= CAN_STATE_BUS_OFF && + new_state < CAN_STATE_BUS_OFF) { + priv->can.can_stats.restarts++; + if (cf) + cf->can_id |= CAN_ERR_RESTARTED; + } + if (cf && new_state != CAN_STATE_BUS_OFF) { + cf->can_id |= CAN_ERR_CNT; + cf->data[6] = bec->txerr; + cf->data[7] = bec->rxerr; + } +} + static void kvaser_usb_hydra_update_state(struct kvaser_usb_net_priv *priv, u8 bus_status, const struct can_berr_counter *bec) @@ -951,41 +987,11 @@ static void kvaser_usb_hydra_update_state(struct kvaser_usb_net_priv *priv, return; skb = alloc_can_err_skb(netdev, &cf); - if (skb) { - enum can_state tx_state, rx_state; - - tx_state = (bec->txerr >= bec->rxerr) ? - new_state : CAN_STATE_ERROR_ACTIVE; - rx_state = (bec->txerr <= bec->rxerr) ? - new_state : CAN_STATE_ERROR_ACTIVE; - can_change_state(netdev, cf, tx_state, rx_state); - } - - if (new_state == CAN_STATE_BUS_OFF && old_state < CAN_STATE_BUS_OFF) { - if (!priv->can.restart_ms) - kvaser_usb_hydra_send_simple_cmd_async - (priv, CMD_STOP_CHIP_REQ); - - can_bus_off(netdev); - } - - if (!skb) { + kvaser_usb_hydra_change_state(priv, bec, cf, new_state); + if (skb) + netif_rx(skb); + else netdev_warn(netdev, "No memory left for err_skb\n"); - return; - } - - if (priv->can.restart_ms && - old_state >= CAN_STATE_BUS_OFF && - new_state < CAN_STATE_BUS_OFF) - priv->can.can_stats.restarts++; - - if (new_state != CAN_STATE_BUS_OFF) { - cf->can_id |= CAN_ERR_CNT; - cf->data[6] = bec->txerr; - cf->data[7] = bec->rxerr; - } - - netif_rx(skb); } static void kvaser_usb_hydra_state_event(const struct kvaser_usb *dev, @@ -1078,9 +1084,8 @@ kvaser_usb_hydra_error_frame(struct kvaser_usb_net_priv *priv, { struct net_device *netdev = priv->netdev; struct net_device_stats *stats = &netdev->stats; - struct can_frame *cf; - struct sk_buff *skb; - struct skb_shared_hwtstamps *shhwtstamps; + struct can_frame *cf = NULL; + struct sk_buff *skb = NULL; struct can_berr_counter bec; enum can_state new_state, old_state; u8 bus_status; @@ -1096,52 +1101,26 @@ kvaser_usb_hydra_error_frame(struct kvaser_usb_net_priv *priv, kvaser_usb_hydra_bus_status_to_can_state(priv, bus_status, &bec, &new_state); - skb = alloc_can_err_skb(netdev, &cf); + if (priv->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING) + skb = alloc_can_err_skb(netdev, &cf); + if (new_state != old_state) + kvaser_usb_hydra_change_state(priv, &bec, cf, new_state); - if (new_state != old_state) { + if (priv->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING) { if (skb) { - enum can_state tx_state, rx_state; - - tx_state = (bec.txerr >= bec.rxerr) ? - new_state : CAN_STATE_ERROR_ACTIVE; - rx_state = (bec.txerr <= bec.rxerr) ? - new_state : CAN_STATE_ERROR_ACTIVE; - - can_change_state(netdev, cf, tx_state, rx_state); - - if (priv->can.restart_ms && - old_state >= CAN_STATE_BUS_OFF && - new_state < CAN_STATE_BUS_OFF) - cf->can_id |= CAN_ERR_RESTARTED; - } - - if (new_state == CAN_STATE_BUS_OFF) { - if (!priv->can.restart_ms) - kvaser_usb_hydra_send_simple_cmd_async - (priv, CMD_STOP_CHIP_REQ); + struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb); - can_bus_off(netdev); + shhwtstamps->hwtstamp = hwtstamp; + cf->can_id |= CAN_ERR_BUSERROR | CAN_ERR_CNT; + cf->data[6] = bec.txerr; + cf->data[7] = bec.rxerr; + netif_rx(skb); + } else { + stats->rx_dropped++; + netdev_warn(netdev, "No memory left for err_skb\n"); } } - if (!skb) { - stats->rx_dropped++; - netdev_warn(netdev, "No memory left for err_skb\n"); - return; - } - - shhwtstamps = skb_hwtstamps(skb); - shhwtstamps->hwtstamp = hwtstamp; - - cf->can_id |= CAN_ERR_BUSERROR; - if (new_state != CAN_STATE_BUS_OFF) { - cf->can_id |= CAN_ERR_CNT; - cf->data[6] = bec.txerr; - cf->data[7] = bec.rxerr; - } - - netif_rx(skb); - priv->bec.txerr = bec.txerr; priv->bec.rxerr = bec.rxerr; } diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c index 6b9122ab1464..6a45adcc45bd 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c @@ -1120,10 +1120,8 @@ kvaser_usb_leaf_rx_error_update_can_state(struct kvaser_usb_net_priv *priv, static void kvaser_usb_leaf_rx_error(const struct kvaser_usb *dev, const struct kvaser_usb_err_summary *es) { - struct can_frame *cf; - struct can_frame tmp_cf = { .can_id = CAN_ERR_FLAG, - .len = CAN_ERR_DLC }; - struct sk_buff *skb; + struct can_frame *cf = NULL; + struct sk_buff *skb = NULL; struct net_device_stats *stats; struct kvaser_usb_net_priv *priv; struct kvaser_usb_net_leaf_priv *leaf; @@ -1143,18 +1141,10 @@ static void kvaser_usb_leaf_rx_error(const struct kvaser_usb *dev, if (!netif_running(priv->netdev)) return; - /* Update all of the CAN interface's state and error counters before - * trying any memory allocation that can actually fail with -ENOMEM. - * - * We send a temporary stack-allocated error CAN frame to - * can_change_state() for the very same reason. - * - * TODO: Split can_change_state() responsibility between updating the - * CAN interface's state and counters, and the setting up of CAN error - * frame ID and data to userspace. Remove stack allocation afterwards. - */ old_state = priv->can.state; - kvaser_usb_leaf_rx_error_update_can_state(priv, es, &tmp_cf); + if (priv->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING) + skb = alloc_can_err_skb(priv->netdev, &cf); + kvaser_usb_leaf_rx_error_update_can_state(priv, es, cf); new_state = priv->can.state; /* If there are errors, request status updates periodically as we do @@ -1168,13 +1158,6 @@ static void kvaser_usb_leaf_rx_error(const struct kvaser_usb *dev, schedule_delayed_work(&leaf->chip_state_req_work, msecs_to_jiffies(500)); - skb = alloc_can_err_skb(priv->netdev, &cf); - if (!skb) { - stats->rx_dropped++; - return; - } - memcpy(cf, &tmp_cf, sizeof(*cf)); - if (new_state != old_state) { if (es->status & (M16C_STATE_BUS_OFF | M16C_STATE_BUS_RESET)) { @@ -1187,11 +1170,20 @@ static void kvaser_usb_leaf_rx_error(const struct kvaser_usb *dev, if (priv->can.restart_ms && old_state == CAN_STATE_BUS_OFF && new_state < CAN_STATE_BUS_OFF) { - cf->can_id |= CAN_ERR_RESTARTED; + if (cf) + cf->can_id |= CAN_ERR_RESTARTED; netif_carrier_on(priv->netdev); } } + if (!skb) { + if (priv->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING) { + stats->rx_dropped++; + netdev_warn(priv->netdev, "No memory left for err_skb\n"); + } + return; + } + switch (dev->driver_info->family) { case KVASER_LEAF: if (es->leaf.error_factor) { diff --git a/drivers/net/dsa/b53/b53_serdes.c b/drivers/net/dsa/b53/b53_serdes.c index 3f8a491ce885..4730982b6840 100644 --- a/drivers/net/dsa/b53/b53_serdes.c +++ b/drivers/net/dsa/b53/b53_serdes.c @@ -99,8 +99,8 @@ static void b53_serdes_an_restart(struct phylink_pcs *pcs) SERDES_MII_BLK, reg); } -static void b53_serdes_get_state(struct phylink_pcs *pcs, - struct phylink_link_state *state) +static void b53_serdes_get_state(struct phylink_pcs *pcs, unsigned int neg_mode, + struct phylink_link_state *state) { struct b53_device *dev = pcs_to_b53_pcs(pcs)->dev; u8 lane = pcs_to_b53_pcs(pcs)->lane; diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index d2d0f091e49e..1c83af805209 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -2994,7 +2994,7 @@ static int mt753x_pcs_validate(struct phylink_pcs *pcs, return 0; } -static void mt7530_pcs_get_state(struct phylink_pcs *pcs, +static void mt7530_pcs_get_state(struct phylink_pcs *pcs, unsigned int neg_mode, struct phylink_link_state *state) { struct mt7530_priv *priv = pcs_to_mt753x_pcs(pcs)->priv; diff --git a/drivers/net/dsa/mv88e6xxx/pcs-6185.c b/drivers/net/dsa/mv88e6xxx/pcs-6185.c index 5a27d047a38e..75ed1fa500a5 100644 --- a/drivers/net/dsa/mv88e6xxx/pcs-6185.c +++ b/drivers/net/dsa/mv88e6xxx/pcs-6185.c @@ -55,6 +55,7 @@ static irqreturn_t mv88e6185_pcs_handle_irq(int irq, void *dev_id) } static void mv88e6185_pcs_get_state(struct phylink_pcs *pcs, + unsigned int neg_mode, struct phylink_link_state *state) { struct mv88e6185_pcs *mpcs = pcs_to_mv88e6185_pcs(pcs); diff --git a/drivers/net/dsa/mv88e6xxx/pcs-6352.c b/drivers/net/dsa/mv88e6xxx/pcs-6352.c index 88f624b65470..143fe21d1834 100644 --- a/drivers/net/dsa/mv88e6xxx/pcs-6352.c +++ b/drivers/net/dsa/mv88e6xxx/pcs-6352.c @@ -158,6 +158,7 @@ static void marvell_c22_pcs_disable(struct phylink_pcs *pcs) } static void marvell_c22_pcs_get_state(struct phylink_pcs *pcs, + unsigned int neg_mode, struct phylink_link_state *state) { struct marvell_c22_pcs *mpcs = pcs_to_marvell_c22_pcs(pcs); diff --git a/drivers/net/dsa/mv88e6xxx/pcs-639x.c b/drivers/net/dsa/mv88e6xxx/pcs-639x.c index d758a6c1b226..026b7bfb7ee5 100644 --- a/drivers/net/dsa/mv88e6xxx/pcs-639x.c +++ b/drivers/net/dsa/mv88e6xxx/pcs-639x.c @@ -257,6 +257,7 @@ static int mv88e639x_sgmii_pcs_post_config(struct phylink_pcs *pcs, } static void mv88e639x_sgmii_pcs_get_state(struct phylink_pcs *pcs, + unsigned int neg_mode, struct phylink_link_state *state) { struct mv88e639x_pcs *mpcs = sgmii_pcs_to_mv88e639x_pcs(pcs); @@ -395,6 +396,7 @@ static void mv88e639x_xg_pcs_disable(struct mv88e639x_pcs *mpcs) } static void mv88e639x_xg_pcs_get_state(struct phylink_pcs *pcs, + unsigned int neg_mode, struct phylink_link_state *state) { struct mv88e639x_pcs *mpcs = xg_pcs_to_mv88e639x_pcs(pcs); @@ -889,6 +891,7 @@ static int mv88e6393x_xg_pcs_post_config(struct phylink_pcs *pcs, } static void mv88e6393x_xg_pcs_get_state(struct phylink_pcs *pcs, + unsigned int neg_mode, struct phylink_link_state *state) { struct mv88e639x_pcs *mpcs = xg_pcs_to_mv88e639x_pcs(pcs); @@ -896,7 +899,7 @@ static void mv88e6393x_xg_pcs_get_state(struct phylink_pcs *pcs, int err; if (state->interface != PHY_INTERFACE_MODE_USXGMII) - return mv88e639x_xg_pcs_get_state(pcs, state); + return mv88e639x_xg_pcs_get_state(pcs, neg_mode, state); state->link = false; diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index 3aa9c997018a..0a4e682a55ef 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -1316,6 +1316,14 @@ static void felix_get_eth_phy_stats(struct dsa_switch *ds, int port, ocelot_port_get_eth_phy_stats(ocelot, port, phy_stats); } +static void felix_get_ts_stats(struct dsa_switch *ds, int port, + struct ethtool_ts_stats *ts_stats) +{ + struct ocelot *ocelot = ds->priv; + + ocelot_port_get_ts_stats(ocelot, port, ts_stats); +} + static void felix_get_strings(struct dsa_switch *ds, int port, u32 stringset, u8 *data) { @@ -2237,6 +2245,7 @@ static const struct dsa_switch_ops felix_switch_ops = { .get_stats64 = felix_get_stats64, .get_pause_stats = felix_get_pause_stats, .get_rmon_stats = felix_get_rmon_stats, + .get_ts_stats = felix_get_ts_stats, .get_eth_ctrl_stats = felix_get_eth_ctrl_stats, .get_eth_mac_stats = felix_get_eth_mac_stats, .get_eth_phy_stats = felix_get_eth_phy_stats, diff --git a/drivers/net/dsa/qca/qca8k-8xxx.c b/drivers/net/dsa/qca/qca8k-8xxx.c index 750fc76a6e11..e8cb4da15dbe 100644 --- a/drivers/net/dsa/qca/qca8k-8xxx.c +++ b/drivers/net/dsa/qca/qca8k-8xxx.c @@ -1491,7 +1491,7 @@ static struct qca8k_pcs *pcs_to_qca8k_pcs(struct phylink_pcs *pcs) return container_of(pcs, struct qca8k_pcs, pcs); } -static void qca8k_pcs_get_state(struct phylink_pcs *pcs, +static void qca8k_pcs_get_state(struct phylink_pcs *pcs, unsigned int neg_mode, struct phylink_link_state *state) { struct qca8k_priv *priv = pcs_to_qca8k_pcs(pcs)->priv; diff --git a/drivers/net/ethernet/amd/pcnet32.c b/drivers/net/ethernet/amd/pcnet32.c index 72db9f9e7bee..c6bd803f5b0c 100644 --- a/drivers/net/ethernet/amd/pcnet32.c +++ b/drivers/net/ethernet/amd/pcnet32.c @@ -462,7 +462,7 @@ static void pcnet32_netif_start(struct net_device *dev) val = lp->a->read_csr(ioaddr, CSR3); val &= 0x00ff; lp->a->write_csr(ioaddr, CSR3, val); - napi_enable(&lp->napi); + napi_enable_locked(&lp->napi); } /* @@ -889,6 +889,7 @@ static int pcnet32_set_ringparam(struct net_device *dev, if (netif_running(dev)) pcnet32_netif_stop(dev); + netdev_lock(dev); spin_lock_irqsave(&lp->lock, flags); lp->a->write_csr(ioaddr, CSR0, CSR0_STOP); /* stop the chip */ @@ -920,6 +921,7 @@ static int pcnet32_set_ringparam(struct net_device *dev, } spin_unlock_irqrestore(&lp->lock, flags); + netdev_unlock(dev); netif_info(lp, drv, dev, "Ring Param Settings: RX: %d, TX: %d\n", lp->rx_ring_size, lp->tx_ring_size); @@ -985,6 +987,7 @@ static int pcnet32_loopback_test(struct net_device *dev, uint64_t * data1) if (netif_running(dev)) pcnet32_netif_stop(dev); + netdev_lock(dev); spin_lock_irqsave(&lp->lock, flags); lp->a->write_csr(ioaddr, CSR0, CSR0_STOP); /* stop the chip */ @@ -1122,6 +1125,7 @@ clean_up: lp->a->write_bcr(ioaddr, 20, 4); /* return to 16bit mode */ } spin_unlock_irqrestore(&lp->lock, flags); + netdev_unlock(dev); return rc; } /* end pcnet32_loopback_test */ @@ -2101,6 +2105,7 @@ static int pcnet32_open(struct net_device *dev) return -EAGAIN; } + netdev_lock(dev); spin_lock_irqsave(&lp->lock, flags); /* Check for a valid station address */ if (!is_valid_ether_addr(dev->dev_addr)) { @@ -2266,7 +2271,7 @@ static int pcnet32_open(struct net_device *dev) goto err_free_ring; } - napi_enable(&lp->napi); + napi_enable_locked(&lp->napi); /* Re-initialize the PCNET32, and start it when done. */ lp->a->write_csr(ioaddr, 1, (lp->init_dma_addr & 0xffff)); @@ -2300,6 +2305,7 @@ static int pcnet32_open(struct net_device *dev) lp->a->read_csr(ioaddr, CSR0)); spin_unlock_irqrestore(&lp->lock, flags); + netdev_unlock(dev); return 0; /* Always succeed */ @@ -2315,6 +2321,7 @@ err_free_ring: err_free_irq: spin_unlock_irqrestore(&lp->lock, flags); + netdev_unlock(dev); free_irq(dev->irq, dev); return rc; } diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c index 6a716337f48b..268399dfcf22 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c @@ -923,7 +923,6 @@ static void xgbe_phy_free_phy_device(struct xgbe_prv_data *pdata) static bool xgbe_phy_finisar_phy_quirks(struct xgbe_prv_data *pdata) { - __ETHTOOL_DECLARE_LINK_MODE_MASK(supported) = { 0, }; struct xgbe_phy_data *phy_data = pdata->phy_data; unsigned int phy_id = phy_data->phydev->phy_id; @@ -945,14 +944,7 @@ static bool xgbe_phy_finisar_phy_quirks(struct xgbe_prv_data *pdata) phy_write(phy_data->phydev, 0x04, 0x0d01); phy_write(phy_data->phydev, 0x00, 0x9140); - linkmode_set_bit_array(phy_10_100_features_array, - ARRAY_SIZE(phy_10_100_features_array), - supported); - linkmode_set_bit_array(phy_gbit_features_array, - ARRAY_SIZE(phy_gbit_features_array), - supported); - - linkmode_copy(phy_data->phydev->supported, supported); + linkmode_copy(phy_data->phydev->supported, PHY_GBIT_FEATURES); phy_support_asym_pause(phy_data->phydev); @@ -964,7 +956,6 @@ static bool xgbe_phy_finisar_phy_quirks(struct xgbe_prv_data *pdata) static bool xgbe_phy_belfuse_phy_quirks(struct xgbe_prv_data *pdata) { - __ETHTOOL_DECLARE_LINK_MODE_MASK(supported) = { 0, }; struct xgbe_phy_data *phy_data = pdata->phy_data; struct xgbe_sfp_eeprom *sfp_eeprom = &phy_data->sfp_eeprom; unsigned int phy_id = phy_data->phydev->phy_id; @@ -1028,13 +1019,7 @@ static bool xgbe_phy_belfuse_phy_quirks(struct xgbe_prv_data *pdata) reg = phy_read(phy_data->phydev, 0x00); phy_write(phy_data->phydev, 0x00, reg & ~0x00800); - linkmode_set_bit_array(phy_10_100_features_array, - ARRAY_SIZE(phy_10_100_features_array), - supported); - linkmode_set_bit_array(phy_gbit_features_array, - ARRAY_SIZE(phy_gbit_features_array), - supported); - linkmode_copy(phy_data->phydev->supported, supported); + linkmode_copy(phy_data->phydev->supported, PHY_GBIT_FEATURES); phy_support_asym_pause(phy_data->phydev); netif_dbg(pdata, drv, pdata->netdev, diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp.h b/drivers/net/ethernet/broadcom/asp2/bcmasp.h index f93cb3da44b0..8fc75bcedb70 100644 --- a/drivers/net/ethernet/broadcom/asp2/bcmasp.h +++ b/drivers/net/ethernet/broadcom/asp2/bcmasp.h @@ -348,8 +348,6 @@ struct bcmasp_intf { /* Used if per intf wol irq */ int wol_irq; unsigned int wol_irq_enabled:1; - - struct ethtool_keee eee; }; #define NUM_NET_FILTERS 32 @@ -601,5 +599,4 @@ int bcmasp_netfilt_get_all_active(struct bcmasp_intf *intf, u32 *rule_locs, void bcmasp_netfilt_suspend(struct bcmasp_intf *intf); -void bcmasp_eee_enable_set(struct bcmasp_intf *intf, bool enable); #endif diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c index 9da5ae29a105..a537c121d3e2 100644 --- a/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c +++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c @@ -348,58 +348,19 @@ static int bcmasp_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, return err; } -void bcmasp_eee_enable_set(struct bcmasp_intf *intf, bool enable) -{ - u32 reg; - - reg = umac_rl(intf, UMC_EEE_CTRL); - if (enable) - reg |= EEE_EN; - else - reg &= ~EEE_EN; - umac_wl(intf, reg, UMC_EEE_CTRL); - - intf->eee.eee_enabled = enable; -} - static int bcmasp_get_eee(struct net_device *dev, struct ethtool_keee *e) { - struct bcmasp_intf *intf = netdev_priv(dev); - struct ethtool_keee *p = &intf->eee; - if (!dev->phydev) return -ENODEV; - e->tx_lpi_enabled = p->tx_lpi_enabled; - e->tx_lpi_timer = umac_rl(intf, UMC_EEE_LPI_TIMER); - return phy_ethtool_get_eee(dev->phydev, e); } static int bcmasp_set_eee(struct net_device *dev, struct ethtool_keee *e) { - struct bcmasp_intf *intf = netdev_priv(dev); - struct ethtool_keee *p = &intf->eee; - int ret; - if (!dev->phydev) return -ENODEV; - if (!p->eee_enabled) { - bcmasp_eee_enable_set(intf, false); - } else { - ret = phy_init_eee(dev->phydev, 0); - if (ret) { - netif_err(intf, hw, dev, - "EEE initialization failed: %d\n", ret); - return ret; - } - - umac_wl(intf, e->tx_lpi_timer, UMC_EEE_LPI_TIMER); - intf->eee.tx_lpi_enabled = e->tx_lpi_enabled; - bcmasp_eee_enable_set(intf, true); - } - return phy_ethtool_set_eee(dev->phydev, e); } diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c index cfd50efbdbc0..45ec1a9214a2 100644 --- a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c +++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c @@ -619,7 +619,6 @@ static void bcmasp_adj_link(struct net_device *dev) struct phy_device *phydev = dev->phydev; u32 cmd_bits = 0, reg; int changed = 0; - bool active; if (intf->old_link != phydev->link) { changed = 1; @@ -677,8 +676,13 @@ static void bcmasp_adj_link(struct net_device *dev) } umac_wl(intf, reg, UMC_CMD); - active = phy_init_eee(phydev, 0) >= 0; - bcmasp_eee_enable_set(intf, active); + umac_wl(intf, phydev->eee_cfg.tx_lpi_timer, UMC_EEE_LPI_TIMER); + reg = umac_rl(intf, UMC_EEE_CTRL); + if (phydev->enable_tx_lpi) + reg |= EEE_EN; + else + reg &= ~EEE_EN; + umac_wl(intf, reg, UMC_EEE_CTRL); } reg = rgmii_rl(intf, RGMII_OOB_CNTRL); @@ -1055,6 +1059,9 @@ static int bcmasp_netif_init(struct net_device *dev, bool phy_connect) /* Indicate that the MAC is responsible for PHY PM */ phydev->mac_managed_pm = true; + + /* Set phylib's copy of the LPI timer */ + phydev->eee_cfg.tx_lpi_timer = umac_rl(intf, UMC_EEE_LPI_TIMER); } umac_reset(intf); @@ -1331,7 +1338,8 @@ static void bcmasp_suspend_to_wol(struct bcmasp_intf *intf) ASP_WAKEUP_INTR2_MASK_CLEAR); } - if (intf->eee.eee_enabled && intf->parent->eee_fixup) + if (ndev->phydev && ndev->phydev->eee_cfg.eee_enabled && + intf->parent->eee_fixup) intf->parent->eee_fixup(intf, true); netif_dbg(intf, wol, ndev, "entered WOL mode\n"); @@ -1373,7 +1381,8 @@ static void bcmasp_resume_from_wol(struct bcmasp_intf *intf) { u32 reg; - if (intf->eee.eee_enabled && intf->parent->eee_fixup) + if (intf->ndev->phydev && intf->ndev->phydev->eee_cfg.eee_enabled && + intf->parent->eee_fixup) intf->parent->eee_fixup(intf, false); reg = umac_rl(intf, UMC_MPD_CTRL); @@ -1404,9 +1413,6 @@ int bcmasp_interface_resume(struct bcmasp_intf *intf) bcmasp_resume_from_wol(intf); - if (intf->eee.eee_enabled) - bcmasp_eee_enable_set(intf, true); - netif_device_attach(dev); return 0; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 884d42db5554..748c9b1ea701 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -81,7 +81,6 @@ MODULE_DESCRIPTION("Broadcom NetXtreme network driver"); #define BNXT_RX_OFFSET (NET_SKB_PAD + NET_IP_ALIGN) #define BNXT_RX_DMA_OFFSET NET_SKB_PAD -#define BNXT_RX_COPY_THRESH 256 #define BNXT_TX_PUSH_THRESH 164 @@ -1343,13 +1342,13 @@ static struct sk_buff *bnxt_copy_data(struct bnxt_napi *bnapi, u8 *data, if (!skb) return NULL; - dma_sync_single_for_cpu(&pdev->dev, mapping, bp->rx_copy_thresh, + dma_sync_single_for_cpu(&pdev->dev, mapping, bp->rx_copybreak, bp->rx_dir); memcpy(skb->data - NET_IP_ALIGN, data - NET_IP_ALIGN, len + NET_IP_ALIGN); - dma_sync_single_for_device(&pdev->dev, mapping, bp->rx_copy_thresh, + dma_sync_single_for_device(&pdev->dev, mapping, bp->rx_copybreak, bp->rx_dir); skb_put(skb, len); @@ -1842,7 +1841,7 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp, return NULL; } - if (len <= bp->rx_copy_thresh) { + if (len <= bp->rx_copybreak) { skb = bnxt_copy_skb(bnapi, data_ptr, len, mapping); if (!skb) { bnxt_abort_tpa(cpr, idx, agg_bufs); @@ -2176,7 +2175,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, } } - if (len <= bp->rx_copy_thresh) { + if (len <= bp->rx_copybreak) { if (!xdp_active) skb = bnxt_copy_skb(bnapi, data_ptr, len, dma_addr); else @@ -4608,6 +4607,12 @@ void bnxt_set_tpa_flags(struct bnxt *bp) bp->flags |= BNXT_FLAG_GRO; } +static void bnxt_init_ring_params(struct bnxt *bp) +{ + bp->rx_copybreak = BNXT_DEFAULT_RX_COPYBREAK; + bp->dev->ethtool->hds_thresh = BNXT_DEFAULT_RX_COPYBREAK; +} + /* bp->rx_ring_size, bp->tx_ring_size, dev->mtu, BNXT_FLAG_{G|L}RO flags must * be set on entry. */ @@ -4622,12 +4627,11 @@ void bnxt_set_ring_params(struct bnxt *bp) rx_space = rx_size + ALIGN(max(NET_SKB_PAD, XDP_PACKET_HEADROOM), 8) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - bp->rx_copy_thresh = BNXT_RX_COPY_THRESH; ring_size = bp->rx_ring_size; bp->rx_agg_ring_size = 0; bp->rx_agg_nr_pages = 0; - if (bp->flags & BNXT_FLAG_TPA) + if (bp->flags & BNXT_FLAG_TPA || bp->flags & BNXT_FLAG_HDS) agg_factor = min_t(u32, 4, 65536 / BNXT_RX_PAGE_SIZE); bp->flags &= ~BNXT_FLAG_JUMBO; @@ -4667,7 +4671,9 @@ void bnxt_set_ring_params(struct bnxt *bp) ALIGN(max(NET_SKB_PAD, XDP_PACKET_HEADROOM), 8) - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); } else { - rx_size = SKB_DATA_ALIGN(BNXT_RX_COPY_THRESH + NET_IP_ALIGN); + rx_size = SKB_DATA_ALIGN(max(BNXT_DEFAULT_RX_COPYBREAK, + bp->rx_copybreak) + + NET_IP_ALIGN); rx_space = rx_size + NET_SKB_PAD + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); } @@ -4708,7 +4714,7 @@ void bnxt_set_ring_params(struct bnxt *bp) /* Changing allocation mode of RX rings. * TODO: Update when extending xdp_rxq_info to support allocation modes. */ -int bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode) +static void __bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode) { struct net_device *dev = bp->dev; @@ -4729,15 +4735,30 @@ int bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode) bp->rx_skb_func = bnxt_rx_page_skb; } bp->rx_dir = DMA_BIDIRECTIONAL; - /* Disable LRO or GRO_HW */ - netdev_update_features(dev); } else { dev->max_mtu = bp->max_mtu; bp->flags &= ~BNXT_FLAG_RX_PAGE_MODE; bp->rx_dir = DMA_FROM_DEVICE; bp->rx_skb_func = bnxt_rx_skb; } - return 0; +} + +void bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode) +{ + __bnxt_set_rx_skb_mode(bp, page_mode); + + if (!page_mode) { + int rx, tx; + + bnxt_get_max_rings(bp, &rx, &tx, true); + if (rx > 1) { + bp->flags &= ~BNXT_FLAG_NO_AGG_RINGS; + bp->dev->hw_features |= NETIF_F_LRO; + } + } + + /* Update LRO and GRO_HW availability */ + netdev_update_features(bp->dev); } static void bnxt_free_vnic_attributes(struct bnxt *bp) @@ -6564,6 +6585,7 @@ static void bnxt_hwrm_update_rss_hash_cfg(struct bnxt *bp) static int bnxt_hwrm_vnic_set_hds(struct bnxt *bp, struct bnxt_vnic_info *vnic) { + u16 hds_thresh = (u16)bp->dev->ethtool->hds_thresh; struct hwrm_vnic_plcmodes_cfg_input *req; int rc; @@ -6573,16 +6595,14 @@ static int bnxt_hwrm_vnic_set_hds(struct bnxt *bp, struct bnxt_vnic_info *vnic) req->flags = cpu_to_le32(VNIC_PLCMODES_CFG_REQ_FLAGS_JUMBO_PLACEMENT); req->enables = cpu_to_le32(VNIC_PLCMODES_CFG_REQ_ENABLES_JUMBO_THRESH_VALID); + req->jumbo_thresh = cpu_to_le16(bp->rx_buf_use_size); - if (BNXT_RX_PAGE_MODE(bp)) { - req->jumbo_thresh = cpu_to_le16(bp->rx_buf_use_size); - } else { + if (!BNXT_RX_PAGE_MODE(bp) && (bp->flags & BNXT_FLAG_AGG_RINGS)) { req->flags |= cpu_to_le32(VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_IPV4 | VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_IPV6); req->enables |= cpu_to_le32(VNIC_PLCMODES_CFG_REQ_ENABLES_HDS_THRESHOLD_VALID); - req->jumbo_thresh = cpu_to_le16(bp->rx_copy_thresh); - req->hds_threshold = cpu_to_le16(bp->rx_copy_thresh); + req->hds_threshold = cpu_to_le16(hds_thresh); } req->vnic_id = cpu_to_le32(vnic->fw_vnic_id); return hwrm_req_send(bp, req); @@ -16259,8 +16279,9 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (bp->max_fltr < BNXT_MAX_FLTR) bp->max_fltr = BNXT_MAX_FLTR; bnxt_init_l2_fltr_tbl(bp); - bnxt_set_rx_skb_mode(bp, false); + __bnxt_set_rx_skb_mode(bp, false); bnxt_set_tpa_flags(bp); + bnxt_init_ring_params(bp); bnxt_set_ring_params(bp); bnxt_rdma_aux_device_init(bp); rc = bnxt_set_dflt_rings(bp, true); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 094c9e95b463..2373f423a523 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -34,6 +34,9 @@ #include <linux/firmware/broadcom/tee_bnxt_fw.h> #endif +#define BNXT_DEFAULT_RX_COPYBREAK 256 +#define BNXT_MAX_RX_COPYBREAK 1024 + extern struct list_head bnxt_block_cb_list; struct page_pool; @@ -2241,8 +2244,6 @@ struct bnxt { #define BNXT_FLAG_TPA (BNXT_FLAG_LRO | BNXT_FLAG_GRO) #define BNXT_FLAG_JUMBO 0x10 #define BNXT_FLAG_STRIP_VLAN 0x20 - #define BNXT_FLAG_AGG_RINGS (BNXT_FLAG_JUMBO | BNXT_FLAG_GRO | \ - BNXT_FLAG_LRO) #define BNXT_FLAG_RFS 0x100 #define BNXT_FLAG_SHARED_RINGS 0x200 #define BNXT_FLAG_PORT_STATS 0x400 @@ -2263,6 +2264,9 @@ struct bnxt { #define BNXT_FLAG_ROCE_MIRROR_CAP 0x4000000 #define BNXT_FLAG_TX_COAL_CMPL 0x8000000 #define BNXT_FLAG_PORT_STATS_EXT 0x10000000 + #define BNXT_FLAG_HDS 0x20000000 + #define BNXT_FLAG_AGG_RINGS (BNXT_FLAG_JUMBO | BNXT_FLAG_GRO | \ + BNXT_FLAG_LRO | BNXT_FLAG_HDS) #define BNXT_FLAG_ALL_CONFIG_FEATS (BNXT_FLAG_TPA | \ BNXT_FLAG_RFS | \ @@ -2347,7 +2351,7 @@ struct bnxt { enum dma_data_direction rx_dir; u32 rx_ring_size; u32 rx_agg_ring_size; - u32 rx_copy_thresh; + u32 rx_copybreak; u32 rx_ring_mask; u32 rx_agg_ring_mask; int rx_nr_pages; @@ -2775,6 +2779,8 @@ struct bnxt { #define SFF_MODULE_ID_QSFP28 0x11 #define BNXT_MAX_PHY_I2C_RESP_SIZE 64 +#define BNXT_HDS_THRESHOLD_MAX 1023 + static inline u32 bnxt_tx_avail(struct bnxt *bp, const struct bnxt_tx_ring_info *txr) { @@ -2859,7 +2865,7 @@ u32 bnxt_fw_health_readl(struct bnxt *bp, int reg_idx); bool bnxt_bs_trace_avail(struct bnxt *bp, u16 type); void bnxt_set_tpa_flags(struct bnxt *bp); void bnxt_set_ring_params(struct bnxt *); -int bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode); +void bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode); void bnxt_insert_usr_fltr(struct bnxt *bp, struct bnxt_filter_base *fltr); void bnxt_del_one_usr_fltr(struct bnxt *bp, struct bnxt_filter_base *fltr); int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp, unsigned long *bmap, diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 75a59dd72bce..65a20931c579 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -833,6 +833,9 @@ static void bnxt_get_ringparam(struct net_device *dev, ering->rx_pending = bp->rx_ring_size; ering->rx_jumbo_pending = bp->rx_agg_ring_size; ering->tx_pending = bp->tx_ring_size; + + kernel_ering->hds_thresh = dev->ethtool->hds_thresh; + kernel_ering->hds_thresh_max = BNXT_HDS_THRESHOLD_MAX; } static int bnxt_set_ringparam(struct net_device *dev, @@ -840,16 +843,35 @@ static int bnxt_set_ringparam(struct net_device *dev, struct kernel_ethtool_ringparam *kernel_ering, struct netlink_ext_ack *extack) { + u8 tcp_data_split = kernel_ering->tcp_data_split; struct bnxt *bp = netdev_priv(dev); + u8 hds_config_mod; if ((ering->rx_pending > BNXT_MAX_RX_DESC_CNT) || (ering->tx_pending > BNXT_MAX_TX_DESC_CNT) || (ering->tx_pending < BNXT_MIN_TX_DESC_CNT)) return -EINVAL; + hds_config_mod = tcp_data_split != dev->ethtool->hds_config; + if (tcp_data_split == ETHTOOL_TCP_DATA_SPLIT_DISABLED && hds_config_mod) + return -EINVAL; + + if (tcp_data_split == ETHTOOL_TCP_DATA_SPLIT_ENABLED && + hds_config_mod && BNXT_RX_PAGE_MODE(bp)) { + NL_SET_ERR_MSG_MOD(extack, "tcp-data-split is disallowed when XDP is attached"); + return -EINVAL; + } + if (netif_running(dev)) bnxt_close_nic(bp, false, false); + if (hds_config_mod) { + if (tcp_data_split == ETHTOOL_TCP_DATA_SPLIT_ENABLED) + bp->flags |= BNXT_FLAG_HDS; + else if (tcp_data_split == ETHTOOL_TCP_DATA_SPLIT_UNKNOWN) + bp->flags &= ~BNXT_FLAG_HDS; + } + bp->rx_ring_size = ering->rx_pending; bp->tx_ring_size = ering->tx_pending; bnxt_set_ring_params(bp); @@ -4162,7 +4184,7 @@ err: static void bnxt_get_pkgver(struct net_device *dev) { struct bnxt *bp = netdev_priv(dev); - char buf[FW_VER_STR_LEN]; + char buf[FW_VER_STR_LEN - 5]; int len; if (!bnxt_get_pkginfo(dev, buf, sizeof(buf))) { @@ -4328,6 +4350,45 @@ static int bnxt_get_eee(struct net_device *dev, struct ethtool_keee *edata) return 0; } +static int bnxt_set_tunable(struct net_device *dev, + const struct ethtool_tunable *tuna, + const void *data) +{ + struct bnxt *bp = netdev_priv(dev); + u32 rx_copybreak; + + switch (tuna->id) { + case ETHTOOL_RX_COPYBREAK: + rx_copybreak = *(u32 *)data; + if (rx_copybreak > BNXT_MAX_RX_COPYBREAK) + return -ERANGE; + if (rx_copybreak != bp->rx_copybreak) { + if (netif_running(dev)) + return -EBUSY; + bp->rx_copybreak = rx_copybreak; + } + return 0; + default: + return -EOPNOTSUPP; + } +} + +static int bnxt_get_tunable(struct net_device *dev, + const struct ethtool_tunable *tuna, void *data) +{ + struct bnxt *bp = netdev_priv(dev); + + switch (tuna->id) { + case ETHTOOL_RX_COPYBREAK: + *(u32 *)data = bp->rx_copybreak; + break; + default: + return -EOPNOTSUPP; + } + + return 0; +} + static int bnxt_read_sfp_module_eeprom_info(struct bnxt *bp, u16 i2c_addr, u16 page_number, u8 bank, u16 start_addr, u16 data_length, @@ -4790,7 +4851,8 @@ static int bnxt_run_loopback(struct bnxt *bp) cpr = &rxr->bnapi->cp_ring; if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) cpr = rxr->rx_cpr; - pkt_size = min(bp->dev->mtu + ETH_HLEN, bp->rx_copy_thresh); + pkt_size = min(bp->dev->mtu + ETH_HLEN, max(BNXT_DEFAULT_RX_COPYBREAK, + bp->rx_copybreak)); skb = netdev_alloc_skb(bp->dev, pkt_size); if (!skb) return -ENOMEM; @@ -5331,6 +5393,8 @@ const struct ethtool_ops bnxt_ethtool_ops = { ETHTOOL_COALESCE_STATS_BLOCK_USECS | ETHTOOL_COALESCE_USE_ADAPTIVE_RX | ETHTOOL_COALESCE_USE_CQE, + .supported_ring_params = ETHTOOL_RING_USE_TCP_DATA_SPLIT | + ETHTOOL_RING_USE_HDS_THRS, .get_link_ksettings = bnxt_get_link_ksettings, .set_link_ksettings = bnxt_set_link_ksettings, .get_fec_stats = bnxt_get_fec_stats, @@ -5372,6 +5436,8 @@ const struct ethtool_ops bnxt_ethtool_ops = { .get_link_ext_stats = bnxt_get_link_ext_stats, .get_eee = bnxt_get_eee, .set_eee = bnxt_set_eee, + .get_tunable = bnxt_get_tunable, + .set_tunable = bnxt_set_tunable, .get_module_info = bnxt_get_module_info, .get_module_eeprom = bnxt_get_module_eeprom, .get_module_eeprom_by_page = bnxt_get_module_eeprom_by_page, diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c index f88b641533fc..e6c64e4bd66c 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c @@ -395,6 +395,10 @@ static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *prog) bp->dev->mtu, BNXT_MAX_PAGE_MODE_MTU); return -EOPNOTSUPP; } + if (prog && bp->flags & BNXT_FLAG_HDS) { + netdev_warn(dev, "XDP is disallowed when HDS is enabled.\n"); + return -EOPNOTSUPP; + } if (!(bp->flags & BNXT_FLAG_SHARED_RINGS)) { netdev_warn(dev, "ethtool rx/tx channels must be combined to support XDP.\n"); return -EOPNOTSUPP; @@ -422,15 +426,8 @@ static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *prog) bnxt_set_rx_skb_mode(bp, true); xdp_features_set_redirect_target(dev, true); } else { - int rx, tx; - xdp_features_clear_redirect_target(dev); bnxt_set_rx_skb_mode(bp, false); - bnxt_get_max_rings(bp, &rx, &tx, true); - if (rx > 1) { - bp->flags &= ~BNXT_FLAG_NO_AGG_RINGS; - bp->dev->hw_features |= NETIF_F_LRO; - } } bp->tx_nr_rings_xdp = tx_xdp; bp->tx_nr_rings = bp->tx_nr_rings_per_tc * tc + tx_xdp; diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 640f500f989d..48496209fb16 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -568,6 +568,7 @@ static void macb_usx_pcs_link_up(struct phylink_pcs *pcs, unsigned int neg_mode, } static void macb_usx_pcs_get_state(struct phylink_pcs *pcs, + unsigned int neg_mode, struct phylink_link_state *state) { struct macb *bp = container_of(pcs, struct macb, phylink_usx_pcs); @@ -598,7 +599,7 @@ static int macb_usx_pcs_config(struct phylink_pcs *pcs, return 0; } -static void macb_pcs_get_state(struct phylink_pcs *pcs, +static void macb_pcs_get_state(struct phylink_pcs *pcs, unsigned int neg_mode, struct phylink_link_state *state) { state->link = 0; diff --git a/drivers/net/ethernet/engleder/tsnep_main.c b/drivers/net/ethernet/engleder/tsnep_main.c index 95a5295d0361..0d030cb0b21c 100644 --- a/drivers/net/ethernet/engleder/tsnep_main.c +++ b/drivers/net/ethernet/engleder/tsnep_main.c @@ -1966,23 +1966,41 @@ failed: static void tsnep_queue_enable(struct tsnep_queue *queue) { + struct tsnep_adapter *adapter = queue->adapter; + + netif_napi_set_irq(&queue->napi, queue->irq); napi_enable(&queue->napi); - tsnep_enable_irq(queue->adapter, queue->irq_mask); + tsnep_enable_irq(adapter, queue->irq_mask); - if (queue->tx) + if (queue->tx) { + netif_queue_set_napi(adapter->netdev, queue->tx->queue_index, + NETDEV_QUEUE_TYPE_TX, &queue->napi); tsnep_tx_enable(queue->tx); + } - if (queue->rx) + if (queue->rx) { + netif_queue_set_napi(adapter->netdev, queue->rx->queue_index, + NETDEV_QUEUE_TYPE_RX, &queue->napi); tsnep_rx_enable(queue->rx); + } } static void tsnep_queue_disable(struct tsnep_queue *queue) { - if (queue->tx) + struct tsnep_adapter *adapter = queue->adapter; + + if (queue->rx) + netif_queue_set_napi(adapter->netdev, queue->rx->queue_index, + NETDEV_QUEUE_TYPE_RX, NULL); + + if (queue->tx) { tsnep_tx_disable(queue->tx, &queue->napi); + netif_queue_set_napi(adapter->netdev, queue->tx->queue_index, + NETDEV_QUEUE_TYPE_TX, NULL); + } napi_disable(&queue->napi); - tsnep_disable_irq(queue->adapter, queue->irq_mask); + tsnep_disable_irq(adapter, queue->irq_mask); /* disable RX after NAPI polling has been disabled, because RX can be * enabled during NAPI polling diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index b2daed55bf6c..68725506a095 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1591,19 +1591,22 @@ static void fec_enet_tx(struct net_device *ndev, int budget) fec_enet_tx_queue(ndev, i, budget); } -static void fec_enet_update_cbd(struct fec_enet_priv_rx_q *rxq, +static int fec_enet_update_cbd(struct fec_enet_priv_rx_q *rxq, struct bufdesc *bdp, int index) { struct page *new_page; dma_addr_t phys_addr; new_page = page_pool_dev_alloc_pages(rxq->page_pool); - WARN_ON(!new_page); - rxq->rx_skb_info[index].page = new_page; + if (unlikely(!new_page)) + return -ENOMEM; + rxq->rx_skb_info[index].page = new_page; rxq->rx_skb_info[index].offset = FEC_ENET_XDP_HEADROOM; phys_addr = page_pool_get_dma_addr(new_page) + FEC_ENET_XDP_HEADROOM; bdp->cbd_bufaddr = cpu_to_fec32(phys_addr); + + return 0; } static u32 @@ -1698,6 +1701,7 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id) int cpu = smp_processor_id(); struct xdp_buff xdp; struct page *page; + __fec32 cbd_bufaddr; u32 sub_len = 4; #if !defined(CONFIG_M5272) @@ -1766,12 +1770,17 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id) index = fec_enet_get_bd_index(bdp, &rxq->bd); page = rxq->rx_skb_info[index].page; + cbd_bufaddr = bdp->cbd_bufaddr; + if (fec_enet_update_cbd(rxq, bdp, index)) { + ndev->stats.rx_dropped++; + goto rx_processing_done; + } + dma_sync_single_for_cpu(&fep->pdev->dev, - fec32_to_cpu(bdp->cbd_bufaddr), + fec32_to_cpu(cbd_bufaddr), pkt_len, DMA_FROM_DEVICE); prefetch(page_address(page)); - fec_enet_update_cbd(rxq, bdp, index); if (xdp_prog) { xdp_buff_clear_frags_flag(&xdp); diff --git a/drivers/net/ethernet/freescale/fman/fman_dtsec.c b/drivers/net/ethernet/freescale/fman/fman_dtsec.c index 85617bb94959..b3e2a596ad2c 100644 --- a/drivers/net/ethernet/freescale/fman/fman_dtsec.c +++ b/drivers/net/ethernet/freescale/fman/fman_dtsec.c @@ -755,12 +755,12 @@ static struct fman_mac *pcs_to_dtsec(struct phylink_pcs *pcs) return container_of(pcs, struct fman_mac, pcs); } -static void dtsec_pcs_get_state(struct phylink_pcs *pcs, +static void dtsec_pcs_get_state(struct phylink_pcs *pcs, unsigned int neg_mode, struct phylink_link_state *state) { struct fman_mac *dtsec = pcs_to_dtsec(pcs); - phylink_mii_c22_pcs_get_state(dtsec->tbidev, state); + phylink_mii_c22_pcs_get_state(dtsec->tbidev, neg_mode, state); } static int dtsec_pcs_config(struct phylink_pcs *pcs, unsigned int neg_mode, diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index a9e54866ae6b..cbfaaa5b7d02 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -1180,7 +1180,7 @@ static void iavf_napi_enable_all(struct iavf_adapter *adapter) q_vector = &adapter->q_vectors[q_idx]; napi = &q_vector->napi; - napi_enable(napi); + napi_enable_locked(napi); } } @@ -1196,7 +1196,7 @@ static void iavf_napi_disable_all(struct iavf_adapter *adapter) for (q_idx = 0; q_idx < q_vectors; q_idx++) { q_vector = &adapter->q_vectors[q_idx]; - napi_disable(&q_vector->napi); + napi_disable_locked(&q_vector->napi); } } @@ -1800,8 +1800,8 @@ static int iavf_alloc_q_vectors(struct iavf_adapter *adapter) q_vector->v_idx = q_idx; q_vector->reg_idx = q_idx; cpumask_copy(&q_vector->affinity_mask, cpu_possible_mask); - netif_napi_add(adapter->netdev, &q_vector->napi, - iavf_napi_poll); + netif_napi_add_locked(adapter->netdev, &q_vector->napi, + iavf_napi_poll); } return 0; @@ -1827,7 +1827,7 @@ static void iavf_free_q_vectors(struct iavf_adapter *adapter) for (q_idx = 0; q_idx < num_q_vectors; q_idx++) { struct iavf_q_vector *q_vector = &adapter->q_vectors[q_idx]; - netif_napi_del(&q_vector->napi); + netif_napi_del_locked(&q_vector->napi); } kfree(adapter->q_vectors); adapter->q_vectors = NULL; @@ -1968,6 +1968,7 @@ err: static void iavf_finish_config(struct work_struct *work) { struct iavf_adapter *adapter; + bool netdev_released = false; int pairs, err; adapter = container_of(work, struct iavf_adapter, finish_config); @@ -1976,7 +1977,7 @@ static void iavf_finish_config(struct work_struct *work) * The dev->lock is needed to update the queue number */ rtnl_lock(); - mutex_lock(&adapter->netdev->lock); + netdev_lock(adapter->netdev); mutex_lock(&adapter->crit_lock); if ((adapter->flags & IAVF_FLAG_SETUP_NETDEV_FEATURES) && @@ -1988,7 +1989,16 @@ static void iavf_finish_config(struct work_struct *work) switch (adapter->state) { case __IAVF_DOWN: + /* Set the real number of queues when reset occurs while + * state == __IAVF_DOWN + */ + pairs = adapter->num_active_queues; + netif_set_real_num_rx_queues(adapter->netdev, pairs); + netif_set_real_num_tx_queues(adapter->netdev, pairs); + if (adapter->netdev->reg_state != NETREG_REGISTERED) { + netdev_unlock(adapter->netdev); + netdev_released = true; err = register_netdevice(adapter->netdev); if (err) { dev_err(&adapter->pdev->dev, "Unable to register netdev (%d)\n", @@ -2003,11 +2013,7 @@ static void iavf_finish_config(struct work_struct *work) goto out; } } - - /* Set the real number of queues when reset occurs while - * state == __IAVF_DOWN - */ - fallthrough; + break; case __IAVF_RUNNING: pairs = adapter->num_active_queues; netif_set_real_num_rx_queues(adapter->netdev, pairs); @@ -2020,7 +2026,8 @@ static void iavf_finish_config(struct work_struct *work) out: mutex_unlock(&adapter->crit_lock); - mutex_unlock(&adapter->netdev->lock); + if (!netdev_released) + netdev_unlock(adapter->netdev); rtnl_unlock(); } @@ -2713,12 +2720,16 @@ static void iavf_watchdog_task(struct work_struct *work) struct iavf_adapter *adapter = container_of(work, struct iavf_adapter, watchdog_task.work); + struct net_device *netdev = adapter->netdev; struct iavf_hw *hw = &adapter->hw; u32 reg_val; + netdev_lock(netdev); if (!mutex_trylock(&adapter->crit_lock)) { - if (adapter->state == __IAVF_REMOVE) + if (adapter->state == __IAVF_REMOVE) { + netdev_unlock(netdev); return; + } goto restart_watchdog; } @@ -2730,30 +2741,35 @@ static void iavf_watchdog_task(struct work_struct *work) case __IAVF_STARTUP: iavf_startup(adapter); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); queue_delayed_work(adapter->wq, &adapter->watchdog_task, msecs_to_jiffies(30)); return; case __IAVF_INIT_VERSION_CHECK: iavf_init_version_check(adapter); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); queue_delayed_work(adapter->wq, &adapter->watchdog_task, msecs_to_jiffies(30)); return; case __IAVF_INIT_GET_RESOURCES: iavf_init_get_resources(adapter); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); queue_delayed_work(adapter->wq, &adapter->watchdog_task, msecs_to_jiffies(1)); return; case __IAVF_INIT_EXTENDED_CAPS: iavf_init_process_extended_caps(adapter); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); queue_delayed_work(adapter->wq, &adapter->watchdog_task, msecs_to_jiffies(1)); return; case __IAVF_INIT_CONFIG_ADAPTER: iavf_init_config_adapter(adapter); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); queue_delayed_work(adapter->wq, &adapter->watchdog_task, msecs_to_jiffies(1)); return; @@ -2765,6 +2781,7 @@ static void iavf_watchdog_task(struct work_struct *work) * as it can loop forever */ mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); return; } if (++adapter->aq_wait_count > IAVF_AQ_MAX_ERR) { @@ -2773,6 +2790,7 @@ static void iavf_watchdog_task(struct work_struct *work) adapter->flags |= IAVF_FLAG_PF_COMMS_FAILED; iavf_shutdown_adminq(hw); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); queue_delayed_work(adapter->wq, &adapter->watchdog_task, (5 * HZ)); return; @@ -2780,6 +2798,7 @@ static void iavf_watchdog_task(struct work_struct *work) /* Try again from failed step*/ iavf_change_state(adapter, adapter->last_state); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); queue_delayed_work(adapter->wq, &adapter->watchdog_task, HZ); return; case __IAVF_COMM_FAILED: @@ -2792,6 +2811,7 @@ static void iavf_watchdog_task(struct work_struct *work) iavf_change_state(adapter, __IAVF_INIT_FAILED); adapter->flags &= ~IAVF_FLAG_PF_COMMS_FAILED; mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); return; } reg_val = rd32(hw, IAVF_VFGEN_RSTAT) & @@ -2811,12 +2831,14 @@ static void iavf_watchdog_task(struct work_struct *work) adapter->aq_required = 0; adapter->current_op = VIRTCHNL_OP_UNKNOWN; mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); queue_delayed_work(adapter->wq, &adapter->watchdog_task, msecs_to_jiffies(10)); return; case __IAVF_RESETTING: mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); queue_delayed_work(adapter->wq, &adapter->watchdog_task, HZ * 2); return; @@ -2847,6 +2869,7 @@ static void iavf_watchdog_task(struct work_struct *work) case __IAVF_REMOVE: default: mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); return; } @@ -2858,12 +2881,14 @@ static void iavf_watchdog_task(struct work_struct *work) dev_err(&adapter->pdev->dev, "Hardware reset detected\n"); iavf_schedule_reset(adapter, IAVF_FLAG_RESET_PENDING); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); queue_delayed_work(adapter->wq, &adapter->watchdog_task, HZ * 2); return; } mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); restart_watchdog: if (adapter->state >= __IAVF_DOWN) queue_work(adapter->wq, &adapter->adminq_task); @@ -2990,12 +3015,12 @@ static void iavf_reset_task(struct work_struct *work) /* When device is being removed it doesn't make sense to run the reset * task, just return in such a case. */ - mutex_lock(&netdev->lock); + netdev_lock(netdev); if (!mutex_trylock(&adapter->crit_lock)) { if (adapter->state != __IAVF_REMOVE) queue_work(adapter->wq, &adapter->reset_task); - mutex_unlock(&netdev->lock); + netdev_unlock(netdev); return; } @@ -3043,7 +3068,7 @@ static void iavf_reset_task(struct work_struct *work) reg_val); iavf_disable_vf(adapter); mutex_unlock(&adapter->crit_lock); - mutex_unlock(&netdev->lock); + netdev_unlock(netdev); return; /* Do not attempt to reinit. It's dead, Jim. */ } @@ -3184,7 +3209,7 @@ continue_reset: wake_up(&adapter->reset_waitqueue); mutex_unlock(&adapter->crit_lock); - mutex_unlock(&netdev->lock); + netdev_unlock(netdev); return; reset_err: @@ -3195,7 +3220,7 @@ reset_err: iavf_disable_vf(adapter); mutex_unlock(&adapter->crit_lock); - mutex_unlock(&netdev->lock); + netdev_unlock(netdev); dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n"); } @@ -3667,10 +3692,10 @@ exit: if (test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section)) return 0; - mutex_lock(&netdev->lock); + netdev_lock(netdev); netif_set_real_num_rx_queues(netdev, total_qps); netif_set_real_num_tx_queues(netdev, total_qps); - mutex_unlock(&netdev->lock); + netdev_unlock(netdev); return ret; } @@ -4340,14 +4365,17 @@ static int iavf_open(struct net_device *netdev) return -EIO; } + netdev_lock(netdev); while (!mutex_trylock(&adapter->crit_lock)) { /* If we are in __IAVF_INIT_CONFIG_ADAPTER state the crit_lock * is already taken and iavf_open is called from an upper * device's notifier reacting on NETDEV_REGISTER event. * We have to leave here to avoid dead lock. */ - if (adapter->state == __IAVF_INIT_CONFIG_ADAPTER) + if (adapter->state == __IAVF_INIT_CONFIG_ADAPTER) { + netdev_unlock(netdev); return -EBUSY; + } usleep_range(500, 1000); } @@ -4396,6 +4424,7 @@ static int iavf_open(struct net_device *netdev) iavf_irq_enable(adapter, true); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); return 0; @@ -4408,6 +4437,7 @@ err_setup_tx: iavf_free_all_tx_resources(adapter); err_unlock: mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); return err; } @@ -4429,10 +4459,12 @@ static int iavf_close(struct net_device *netdev) u64 aq_to_restore; int status; + netdev_lock(netdev); mutex_lock(&adapter->crit_lock); if (adapter->state <= __IAVF_DOWN_PENDING) { mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); return 0; } @@ -4466,6 +4498,7 @@ static int iavf_close(struct net_device *netdev) iavf_free_traffic_irqs(adapter); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); /* We explicitly don't free resources here because the hardware is * still active and can DMA into memory. Resources are cleared in @@ -5342,6 +5375,7 @@ static int iavf_suspend(struct device *dev_d) netif_device_detach(netdev); + netdev_lock(netdev); mutex_lock(&adapter->crit_lock); if (netif_running(netdev)) { @@ -5353,6 +5387,7 @@ static int iavf_suspend(struct device *dev_d) iavf_reset_interrupt_capability(adapter); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); return 0; } @@ -5451,6 +5486,7 @@ static void iavf_remove(struct pci_dev *pdev) if (netdev->reg_state == NETREG_REGISTERED) unregister_netdev(netdev); + netdev_lock(netdev); mutex_lock(&adapter->crit_lock); dev_info(&adapter->pdev->dev, "Removing device\n"); iavf_change_state(adapter, __IAVF_REMOVE); @@ -5487,6 +5523,7 @@ static void iavf_remove(struct pci_dev *pdev) mutex_destroy(&hw->aq.asq_mutex); mutex_unlock(&adapter->crit_lock); mutex_destroy(&adapter->crit_lock); + netdev_unlock(netdev); iounmap(hw->hw_addr); pci_release_regions(pdev); diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink.c b/drivers/net/ethernet/intel/ice/devlink/devlink.c index 1b10682c00b8..d116e2b10bce 100644 --- a/drivers/net/ethernet/intel/ice/devlink/devlink.c +++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c @@ -368,14 +368,18 @@ static int ice_devlink_info_get(struct devlink *devlink, } break; case ICE_VERSION_RUNNING: - err = devlink_info_version_running_put(req, key, ctx->buf); + err = devlink_info_version_running_put_ext(req, key, + ctx->buf, + DEVLINK_INFO_VERSION_TYPE_COMPONENT); if (err) { NL_SET_ERR_MSG_MOD(extack, "Unable to set running version"); goto out_free_ctx; } break; case ICE_VERSION_STORED: - err = devlink_info_version_stored_put(req, key, ctx->buf); + err = devlink_info_version_stored_put_ext(req, key, + ctx->buf, + DEVLINK_INFO_VERSION_TYPE_COMPONENT); if (err) { NL_SET_ERR_MSG_MOD(extack, "Unable to set stored version"); goto out_free_ctx; @@ -1207,9 +1211,15 @@ static int ice_devlink_reinit_up(struct ice_pf *pf) struct ice_vsi *vsi = ice_get_main_vsi(pf); int err; + err = ice_init_hw(&pf->hw); + if (err) { + dev_err(ice_pf_to_dev(pf), "ice_init_hw failed: %d\n", err); + return err; + } + err = ice_init_dev(pf); if (err) - return err; + goto unroll_hw_init; vsi->flags = ICE_VSI_FLAG_INIT; @@ -1232,6 +1242,8 @@ err_load: rtnl_unlock(); err_vsi_cfg: ice_deinit_dev(pf); +unroll_hw_init: + ice_deinit_hw(&pf->hw); return err; } diff --git a/drivers/net/ethernet/intel/ice/devlink/health.c b/drivers/net/ethernet/intel/ice/devlink/health.c index d23ae3aafaa7..ea40f7941259 100644 --- a/drivers/net/ethernet/intel/ice/devlink/health.c +++ b/drivers/net/ethernet/intel/ice/devlink/health.c @@ -1,12 +1,270 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2024, Intel Corporation. */ -#include "health.h" #include "ice.h" +#include "ice_adminq_cmd.h" /* for enum ice_aqc_health_status_elem */ +#include "health.h" #define ICE_DEVLINK_FMSG_PUT_FIELD(fmsg, obj, name) \ devlink_fmsg_put(fmsg, #name, (obj)->name) +#define ICE_HEALTH_STATUS_DATA_SIZE 2 + +struct ice_health_status { + enum ice_aqc_health_status code; + const char *description; + const char *solution; + const char *data_label[ICE_HEALTH_STATUS_DATA_SIZE]; +}; + +/* + * In addition to the health status codes provided below, the firmware might + * generate Health Status Codes that are not pertinent to the end-user. + * For instance, Health Code 0x1002 is triggered when the command fails. + * Such codes should be disregarded by the end-user. + * The below lookup requires to be sorted by code. + */ + +static const char *const ice_common_port_solutions = + "Check your cable connection. Change or replace the module or cable. Manually set speed and duplex."; +static const char *const ice_port_number_label = "Port Number"; +static const char *const ice_update_nvm_solution = "Update to the latest NVM image."; + +static const struct ice_health_status ice_health_status_lookup[] = { + {ICE_AQC_HEALTH_STATUS_ERR_UNKNOWN_MOD_STRICT, "An unsupported module was detected.", + ice_common_port_solutions, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_MOD_TYPE, "Module type is not supported.", + "Change or replace the module or cable.", {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_MOD_QUAL, "Module is not qualified.", + ice_common_port_solutions, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_MOD_COMM, + "Device cannot communicate with the module.", + "Check your cable connection. Change or replace the module or cable. Manually set speed and duplex.", + {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_MOD_CONFLICT, "Unresolved module conflict.", + "Manually set speed/duplex or change the port option. If the problem persists, use a cable/module that is found in the supported modules and cables list for this device.", + {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_MOD_NOT_PRESENT, "Module is not present.", + "Check that the module is inserted correctly. If the problem persists, use a cable/module that is found in the supported modules and cables list for this device.", + {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_INFO_MOD_UNDERUTILIZED, "Underutilized module.", + "Change or replace the module or cable. Change the port option.", + {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_UNKNOWN_MOD_LENIENT, "An unsupported module was detected.", + ice_common_port_solutions, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_INVALID_LINK_CFG, "Invalid link configuration.", + NULL, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_PORT_ACCESS, "Port hardware access error.", + ice_update_nvm_solution, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_PORT_UNREACHABLE, "A port is unreachable.", + "Change the port option. Update to the latest NVM image."}, + {ICE_AQC_HEALTH_STATUS_INFO_PORT_SPEED_MOD_LIMITED, "Port speed is limited due to module.", + "Change the module or configure the port option to match the current module speed. Change the port option.", + {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_PARALLEL_FAULT, + "All configured link modes were attempted but failed to establish link. The device will restart the process to establish link.", + "Check link partner connection and configuration.", + {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_INFO_PORT_SPEED_PHY_LIMITED, + "Port speed is limited by PHY capabilities.", + "Change the module to align to port option.", {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_NETLIST_TOPO, "LOM topology netlist is corrupted.", + ice_update_nvm_solution, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_NETLIST, "Unrecoverable netlist error.", + ice_update_nvm_solution, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_TOPO_CONFLICT, "Port topology conflict.", + "Change the port option. Update to the latest NVM image."}, + {ICE_AQC_HEALTH_STATUS_ERR_LINK_HW_ACCESS, "Unrecoverable hardware access error.", + ice_update_nvm_solution, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_LINK_RUNTIME, "Unrecoverable runtime error.", + ice_update_nvm_solution, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_DNL_INIT, "Link management engine failed to initialize.", + ice_update_nvm_solution, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_ERR_PHY_FW_LOAD, + "Failed to load the firmware image in the external PHY.", + ice_update_nvm_solution, {ice_port_number_label}}, + {ICE_AQC_HEALTH_STATUS_INFO_RECOVERY, "The device is in firmware recovery mode.", + ice_update_nvm_solution, {"Extended Error"}}, + {ICE_AQC_HEALTH_STATUS_ERR_FLASH_ACCESS, "The flash chip cannot be accessed.", + "If issue persists, call customer support.", {"Access Type"}}, + {ICE_AQC_HEALTH_STATUS_ERR_NVM_AUTH, "NVM authentication failed.", + ice_update_nvm_solution}, + {ICE_AQC_HEALTH_STATUS_ERR_OROM_AUTH, "Option ROM authentication failed.", + ice_update_nvm_solution}, + {ICE_AQC_HEALTH_STATUS_ERR_DDP_AUTH, "DDP package authentication failed.", + "Update to latest base driver and DDP package."}, + {ICE_AQC_HEALTH_STATUS_ERR_NVM_COMPAT, "NVM image is incompatible.", + ice_update_nvm_solution}, + {ICE_AQC_HEALTH_STATUS_ERR_OROM_COMPAT, "Option ROM is incompatible.", + ice_update_nvm_solution, {"Expected PCI Device ID", "Expected Module ID"}}, + {ICE_AQC_HEALTH_STATUS_ERR_DCB_MIB, + "Supplied MIB file is invalid. DCB reverted to default configuration.", + "Disable FW-LLDP and check DCBx system configuration.", + {ice_port_number_label, "MIB ID"}}, +}; + +static int ice_health_status_lookup_compare(const void *a, const void *b) +{ + return ((struct ice_health_status *)a)->code - ((struct ice_health_status *)b)->code; +} + +static const struct ice_health_status *ice_get_health_status(u16 code) +{ + struct ice_health_status key = { .code = code }; + + return bsearch(&key, ice_health_status_lookup, ARRAY_SIZE(ice_health_status_lookup), + sizeof(struct ice_health_status), ice_health_status_lookup_compare); +} + +static void ice_describe_status_code(struct devlink_fmsg *fmsg, + struct ice_aqc_health_status_elem *hse) +{ + static const char *const aux_label[] = { "Aux Data 1", "Aux Data 2" }; + const struct ice_health_status *health_code; + u32 internal_data[2]; + u16 status_code; + + status_code = le16_to_cpu(hse->health_status_code); + + devlink_fmsg_put(fmsg, "Syndrome", status_code); + if (status_code) { + internal_data[0] = le32_to_cpu(hse->internal_data1); + internal_data[1] = le32_to_cpu(hse->internal_data2); + + health_code = ice_get_health_status(status_code); + if (!health_code) + return; + + devlink_fmsg_string_pair_put(fmsg, "Description", health_code->description); + if (health_code->solution) + devlink_fmsg_string_pair_put(fmsg, "Possible Solution", + health_code->solution); + + for (size_t i = 0; i < ICE_HEALTH_STATUS_DATA_SIZE; i++) { + if (internal_data[i] != ICE_AQC_HEALTH_STATUS_UNDEFINED_DATA) + devlink_fmsg_u32_pair_put(fmsg, + health_code->data_label[i] ? + health_code->data_label[i] : + aux_label[i], + internal_data[i]); + } + } +} + +static int +ice_port_reporter_diagnose(struct devlink_health_reporter *reporter, struct devlink_fmsg *fmsg, + struct netlink_ext_ack *extack) +{ + struct ice_pf *pf = devlink_health_reporter_priv(reporter); + + ice_describe_status_code(fmsg, &pf->health_reporters.port_status); + return 0; +} + +static int +ice_port_reporter_dump(struct devlink_health_reporter *reporter, struct devlink_fmsg *fmsg, + void *priv_ctx, struct netlink_ext_ack __always_unused *extack) +{ + struct ice_pf *pf = devlink_health_reporter_priv(reporter); + + ice_describe_status_code(fmsg, &pf->health_reporters.port_status); + return 0; +} + +static int +ice_fw_reporter_diagnose(struct devlink_health_reporter *reporter, struct devlink_fmsg *fmsg, + struct netlink_ext_ack *extack) +{ + struct ice_pf *pf = devlink_health_reporter_priv(reporter); + + ice_describe_status_code(fmsg, &pf->health_reporters.fw_status); + return 0; +} + +static int +ice_fw_reporter_dump(struct devlink_health_reporter *reporter, struct devlink_fmsg *fmsg, + void *priv_ctx, struct netlink_ext_ack *extack) +{ + struct ice_pf *pf = devlink_health_reporter_priv(reporter); + + ice_describe_status_code(fmsg, &pf->health_reporters.fw_status); + return 0; +} + +static void ice_config_health_events(struct ice_pf *pf, bool enable) +{ + u8 enable_bits = 0; + int ret; + + if (enable) + enable_bits = ICE_AQC_HEALTH_STATUS_SET_PF_SPECIFIC_MASK | + ICE_AQC_HEALTH_STATUS_SET_GLOBAL_MASK; + + ret = ice_aq_set_health_status_cfg(&pf->hw, enable_bits); + if (ret) + dev_err(ice_pf_to_dev(pf), "Failed to %s firmware health events, err %d aq_err %s\n", + str_enable_disable(enable), ret, + ice_aq_str(pf->hw.adminq.sq_last_status)); +} + +/** + * ice_process_health_status_event - Process the health status event from FW + * @pf: pointer to the PF structure + * @event: event structure containing the Health Status Event opcode + * + * Decode the Health Status Events and print the associated messages + */ +void ice_process_health_status_event(struct ice_pf *pf, struct ice_rq_event_info *event) +{ + const struct ice_aqc_health_status_elem *health_info; + u16 count; + + health_info = (struct ice_aqc_health_status_elem *)event->msg_buf; + count = le16_to_cpu(event->desc.params.get_health_status.health_status_count); + + if (count > (event->buf_len / sizeof(*health_info))) { + dev_err(ice_pf_to_dev(pf), "Received a health status event with invalid element count\n"); + return; + } + + for (size_t i = 0; i < count; i++) { + const struct ice_health_status *health_code; + u16 status_code; + + status_code = le16_to_cpu(health_info->health_status_code); + health_code = ice_get_health_status(status_code); + + if (health_code) { + switch (le16_to_cpu(health_info->event_source)) { + case ICE_AQC_HEALTH_STATUS_GLOBAL: + pf->health_reporters.fw_status = *health_info; + devlink_health_report(pf->health_reporters.fw, + "FW syndrome reported", NULL); + break; + case ICE_AQC_HEALTH_STATUS_PF: + case ICE_AQC_HEALTH_STATUS_PORT: + pf->health_reporters.port_status = *health_info; + devlink_health_report(pf->health_reporters.port, + "Port syndrome reported", NULL); + break; + default: + dev_err(ice_pf_to_dev(pf), "Health code with unknown source\n"); + } + } else { + u32 data1, data2; + u16 source; + + source = le16_to_cpu(health_info->event_source); + data1 = le32_to_cpu(health_info->internal_data1); + data2 = le32_to_cpu(health_info->internal_data2); + dev_dbg(ice_pf_to_dev(pf), + "Received internal health status code 0x%08x, source: 0x%08x, data1: 0x%08x, data2: 0x%08x", + status_code, source, data1, data2); + } + health_info++; + } +} + /** * ice_devlink_health_report - boilerplate to call given @reporter * @@ -203,14 +461,26 @@ ice_init_devlink_rep(struct ice_pf *pf, return rep; } -#define ICE_DEFINE_HEALTH_REPORTER_OPS(_name) \ - static const struct devlink_health_reporter_ops ice_ ## _name ## _reporter_ops = { \ +#define ICE_HEALTH_REPORTER_OPS_FIELD(_name, _field) \ + ._field = ice_##_name##_reporter_##_field, + +#define ICE_DEFINE_HEALTH_REPORTER_OPS_1(_name, _field1) \ + static const struct devlink_health_reporter_ops ice_##_name##_reporter_ops = { \ .name = #_name, \ - .dump = ice_ ## _name ## _reporter_dump, \ -} + ICE_HEALTH_REPORTER_OPS_FIELD(_name, _field1) \ + } + +#define ICE_DEFINE_HEALTH_REPORTER_OPS_2(_name, _field1, _field2) \ + static const struct devlink_health_reporter_ops ice_##_name##_reporter_ops = { \ + .name = #_name, \ + ICE_HEALTH_REPORTER_OPS_FIELD(_name, _field1) \ + ICE_HEALTH_REPORTER_OPS_FIELD(_name, _field2) \ + } -ICE_DEFINE_HEALTH_REPORTER_OPS(mdd); -ICE_DEFINE_HEALTH_REPORTER_OPS(tx_hang); +ICE_DEFINE_HEALTH_REPORTER_OPS_1(mdd, dump); +ICE_DEFINE_HEALTH_REPORTER_OPS_1(tx_hang, dump); +ICE_DEFINE_HEALTH_REPORTER_OPS_2(fw, dump, diagnose); +ICE_DEFINE_HEALTH_REPORTER_OPS_2(port, dump, diagnose); /** * ice_health_init - allocate and init all ice devlink health reporters and @@ -224,6 +494,12 @@ void ice_health_init(struct ice_pf *pf) reps->mdd = ice_init_devlink_rep(pf, &ice_mdd_reporter_ops); reps->tx_hang = ice_init_devlink_rep(pf, &ice_tx_hang_reporter_ops); + + if (ice_is_fw_health_report_supported(&pf->hw)) { + reps->fw = ice_init_devlink_rep(pf, &ice_fw_reporter_ops); + reps->port = ice_init_devlink_rep(pf, &ice_port_reporter_ops); + ice_config_health_events(pf, true); + } } /** @@ -246,6 +522,11 @@ void ice_health_deinit(struct ice_pf *pf) { ice_deinit_devl_reporter(pf->health_reporters.mdd); ice_deinit_devl_reporter(pf->health_reporters.tx_hang); + if (ice_is_fw_health_report_supported(&pf->hw)) { + ice_deinit_devl_reporter(pf->health_reporters.fw); + ice_deinit_devl_reporter(pf->health_reporters.port); + ice_config_health_events(pf, false); + } } static diff --git a/drivers/net/ethernet/intel/ice/devlink/health.h b/drivers/net/ethernet/intel/ice/devlink/health.h index 532277fc57d7..5edfc4d2adce 100644 --- a/drivers/net/ethernet/intel/ice/devlink/health.h +++ b/drivers/net/ethernet/intel/ice/devlink/health.h @@ -13,8 +13,10 @@ * devlink health mechanism for ice driver. */ +struct ice_aqc_health_status_elem; struct ice_pf; struct ice_tx_ring; +struct ice_rq_event_info; enum ice_mdd_src { ICE_MDD_SRC_TX_PQM, @@ -25,17 +27,23 @@ enum ice_mdd_src { /** * struct ice_health - stores ice devlink health reporters and accompanied data - * @tx_hang: devlink health reporter for tx_hang event + * @fw: devlink health reporter for FW Health Status events * @mdd: devlink health reporter for MDD detection event + * @port: devlink health reporter for Port Health Status events + * @tx_hang: devlink health reporter for tx_hang event * @tx_hang_buf: pre-allocated place to put info for Tx hang reporter from * non-sleeping context * @tx_ring: ring that the hang occurred on * @head: descriptor head * @intr: interrupt register value * @vsi_num: VSI owning the queue that the hang occurred on + * @fw_status: buffer for last received FW Status event + * @port_status: buffer for last received Port Status event */ struct ice_health { + struct devlink_health_reporter *fw; struct devlink_health_reporter *mdd; + struct devlink_health_reporter *port; struct devlink_health_reporter *tx_hang; struct_group_tagged(ice_health_tx_hang_buf, tx_hang_buf, struct ice_tx_ring *tx_ring; @@ -43,8 +51,13 @@ struct ice_health { u32 intr; u16 vsi_num; ); + struct ice_aqc_health_status_elem fw_status; + struct ice_aqc_health_status_elem port_status; }; +void ice_process_health_status_event(struct ice_pf *pf, + struct ice_rq_event_info *event); + void ice_health_init(struct ice_pf *pf); void ice_health_deinit(struct ice_pf *pf); void ice_health_clear(struct ice_pf *pf); diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index 73f5fddf3ee9..01536a382e54 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -1672,6 +1672,7 @@ struct ice_aqc_get_port_options_elem { #define ICE_AQC_PORT_OPT_MAX_LANE_25G 5 #define ICE_AQC_PORT_OPT_MAX_LANE_50G 6 #define ICE_AQC_PORT_OPT_MAX_LANE_100G 7 +#define ICE_AQC_PORT_OPT_MAX_LANE_200G 8 u8 global_scid[2]; u8 phy_scid[2]; @@ -1814,6 +1815,7 @@ struct ice_aqc_nvm_pass_comp_tbl { #define ICE_AQ_NVM_PASS_COMP_CAN_BE_UPDATED 0x0 #define ICE_AQ_NVM_PASS_COMP_CAN_MAY_BE_UPDATEABLE 0x1 #define ICE_AQ_NVM_PASS_COMP_CAN_NOT_BE_UPDATED 0x2 +#define ICE_AQ_NVM_PASS_COMP_PARTIAL_CHECK 0x3 u8 component_response_code; /* Response only */ #define ICE_AQ_NVM_PASS_COMP_CAN_BE_UPDATED_CODE 0x0 #define ICE_AQ_NVM_PASS_COMP_STAMP_IDENTICAL_CODE 0x1 @@ -2517,6 +2519,87 @@ enum ice_aqc_fw_logging_mod { ICE_AQC_FW_LOG_ID_MAX, }; +enum ice_aqc_health_status_mask { + ICE_AQC_HEALTH_STATUS_SET_PF_SPECIFIC_MASK = BIT(0), + ICE_AQC_HEALTH_STATUS_SET_ALL_PF_MASK = BIT(1), + ICE_AQC_HEALTH_STATUS_SET_GLOBAL_MASK = BIT(2), +}; + +/* Set Health Status (direct 0xFF20) */ +struct ice_aqc_set_health_status_cfg { + u8 event_source; + u8 reserved[15]; +}; + +enum ice_aqc_health_status { + ICE_AQC_HEALTH_STATUS_ERR_UNKNOWN_MOD_STRICT = 0x101, + ICE_AQC_HEALTH_STATUS_ERR_MOD_TYPE = 0x102, + ICE_AQC_HEALTH_STATUS_ERR_MOD_QUAL = 0x103, + ICE_AQC_HEALTH_STATUS_ERR_MOD_COMM = 0x104, + ICE_AQC_HEALTH_STATUS_ERR_MOD_CONFLICT = 0x105, + ICE_AQC_HEALTH_STATUS_ERR_MOD_NOT_PRESENT = 0x106, + ICE_AQC_HEALTH_STATUS_INFO_MOD_UNDERUTILIZED = 0x107, + ICE_AQC_HEALTH_STATUS_ERR_UNKNOWN_MOD_LENIENT = 0x108, + ICE_AQC_HEALTH_STATUS_ERR_MOD_DIAGNOSTIC_FEATURE = 0x109, + ICE_AQC_HEALTH_STATUS_ERR_INVALID_LINK_CFG = 0x10B, + ICE_AQC_HEALTH_STATUS_ERR_PORT_ACCESS = 0x10C, + ICE_AQC_HEALTH_STATUS_ERR_PORT_UNREACHABLE = 0x10D, + ICE_AQC_HEALTH_STATUS_INFO_PORT_SPEED_MOD_LIMITED = 0x10F, + ICE_AQC_HEALTH_STATUS_ERR_PARALLEL_FAULT = 0x110, + ICE_AQC_HEALTH_STATUS_INFO_PORT_SPEED_PHY_LIMITED = 0x111, + ICE_AQC_HEALTH_STATUS_ERR_NETLIST_TOPO = 0x112, + ICE_AQC_HEALTH_STATUS_ERR_NETLIST = 0x113, + ICE_AQC_HEALTH_STATUS_ERR_TOPO_CONFLICT = 0x114, + ICE_AQC_HEALTH_STATUS_ERR_LINK_HW_ACCESS = 0x115, + ICE_AQC_HEALTH_STATUS_ERR_LINK_RUNTIME = 0x116, + ICE_AQC_HEALTH_STATUS_ERR_DNL_INIT = 0x117, + ICE_AQC_HEALTH_STATUS_ERR_PHY_NVM_PROG = 0x120, + ICE_AQC_HEALTH_STATUS_ERR_PHY_FW_LOAD = 0x121, + ICE_AQC_HEALTH_STATUS_INFO_RECOVERY = 0x500, + ICE_AQC_HEALTH_STATUS_ERR_FLASH_ACCESS = 0x501, + ICE_AQC_HEALTH_STATUS_ERR_NVM_AUTH = 0x502, + ICE_AQC_HEALTH_STATUS_ERR_OROM_AUTH = 0x503, + ICE_AQC_HEALTH_STATUS_ERR_DDP_AUTH = 0x504, + ICE_AQC_HEALTH_STATUS_ERR_NVM_COMPAT = 0x505, + ICE_AQC_HEALTH_STATUS_ERR_OROM_COMPAT = 0x506, + ICE_AQC_HEALTH_STATUS_ERR_NVM_SEC_VIOLATION = 0x507, + ICE_AQC_HEALTH_STATUS_ERR_OROM_SEC_VIOLATION = 0x508, + ICE_AQC_HEALTH_STATUS_ERR_DCB_MIB = 0x509, + ICE_AQC_HEALTH_STATUS_ERR_MNG_TIMEOUT = 0x50A, + ICE_AQC_HEALTH_STATUS_ERR_BMC_RESET = 0x50B, + ICE_AQC_HEALTH_STATUS_ERR_LAST_MNG_FAIL = 0x50C, + ICE_AQC_HEALTH_STATUS_ERR_RESOURCE_ALLOC_FAIL = 0x50D, + ICE_AQC_HEALTH_STATUS_ERR_FW_LOOP = 0x1000, + ICE_AQC_HEALTH_STATUS_ERR_FW_PFR_FAIL = 0x1001, + ICE_AQC_HEALTH_STATUS_ERR_LAST_FAIL_AQ = 0x1002, +}; + +/* Get Health Status (indirect 0xFF22) */ +struct ice_aqc_get_health_status { + __le16 health_status_count; + u8 reserved[6]; + __le32 addr_high; + __le32 addr_low; +}; + +enum ice_aqc_health_status_scope { + ICE_AQC_HEALTH_STATUS_PF = 0x1, + ICE_AQC_HEALTH_STATUS_PORT = 0x2, + ICE_AQC_HEALTH_STATUS_GLOBAL = 0x3, +}; + +#define ICE_AQC_HEALTH_STATUS_UNDEFINED_DATA 0xDEADBEEF + +/* Get Health Status event buffer entry (0xFF22), + * repeated per reported health status. + */ +struct ice_aqc_health_status_elem { + __le16 health_status_code; + __le16 event_source; + __le32 internal_data1; + __le32 internal_data2; +}; + /* Set FW Logging configuration (indirect 0xFF30) * Register for FW Logging (indirect 0xFF31) * Query FW Logging (indirect 0xFF32) @@ -2657,6 +2740,8 @@ struct ice_aq_desc { struct ice_aqc_get_link_status get_link_status; struct ice_aqc_event_lan_overflow lan_overflow; struct ice_aqc_get_link_topo get_link_topo; + struct ice_aqc_set_health_status_cfg set_health_status_cfg; + struct ice_aqc_get_health_status get_health_status; struct ice_aqc_dnl_call_command dnl_call; struct ice_aqc_i2c read_write_i2c; struct ice_aqc_read_i2c_resp read_i2c_resp; @@ -2859,6 +2944,10 @@ enum ice_adminq_opc { /* Standalone Commands/Events */ ice_aqc_opc_event_lan_overflow = 0x1001, + /* System Diagnostic commands */ + ice_aqc_opc_set_health_status_cfg = 0xFF20, + ice_aqc_opc_get_health_status = 0xFF22, + /* FW Logging Commands */ ice_aqc_opc_fw_logs_config = 0xFF30, ice_aqc_opc_fw_logs_register = 0xFF31, diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index f89bc6ede315..7a2a2e8da8fa 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -309,6 +309,42 @@ bool ice_is_e825c(struct ice_hw *hw) } /** + * ice_is_pf_c827 - check if pf contains c827 phy + * @hw: pointer to the hw struct + * + * Return: true if the device has c827 phy. + */ +static bool ice_is_pf_c827(struct ice_hw *hw) +{ + struct ice_aqc_get_link_topo cmd = {}; + u8 node_part_number; + u16 node_handle; + int status; + + if (hw->mac_type != ICE_MAC_E810) + return false; + + if (hw->device_id != ICE_DEV_ID_E810C_QSFP) + return true; + + cmd.addr.topo_params.node_type_ctx = + FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_TYPE_M, ICE_AQC_LINK_TOPO_NODE_TYPE_PHY) | + FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_CTX_M, ICE_AQC_LINK_TOPO_NODE_CTX_PORT); + cmd.addr.topo_params.index = 0; + + status = ice_aq_get_netlist_node(hw, &cmd, &node_part_number, + &node_handle); + + if (status || node_part_number != ICE_AQC_GET_LINK_TOPO_NODE_NR_C827) + return false; + + if (node_handle == E810C_QSFP_C827_0_HANDLE || node_handle == E810C_QSFP_C827_1_HANDLE) + return true; + + return false; +} + +/** * ice_clear_pf_cfg - Clear PF configuration * @hw: pointer to the hardware structure * @@ -1026,6 +1062,33 @@ static void ice_get_itr_intrl_gran(struct ice_hw *hw) } /** + * ice_wait_for_fw - wait for full FW readiness + * @hw: pointer to the hardware structure + * @timeout: milliseconds that can elapse before timing out + * + * Return: 0 on success, -ETIMEDOUT on timeout. + */ +static int ice_wait_for_fw(struct ice_hw *hw, u32 timeout) +{ + int fw_loading; + u32 elapsed = 0; + + while (elapsed <= timeout) { + fw_loading = rd32(hw, GL_MNG_FWSM) & GL_MNG_FWSM_FW_LOADING_M; + + /* firmware was not yet loaded, we have to wait more */ + if (fw_loading) { + elapsed += 100; + msleep(100); + continue; + } + return 0; + } + + return -ETIMEDOUT; +} + +/** * ice_init_hw - main hardware initialization routine * @hw: pointer to the hardware structure */ @@ -1174,8 +1237,19 @@ int ice_init_hw(struct ice_hw *hw) mutex_init(&hw->tnl_lock); ice_init_chk_recipe_reuse_support(hw); - return 0; + /* Some cards require longer initialization times + * due to necessity of loading FW from an external source. + * This can take even half a minute. + */ + if (ice_is_pf_c827(hw)) { + status = ice_wait_for_fw(hw, 30000); + if (status) { + dev_err(ice_hw_to_dev(hw), "ice_wait_for_fw timed out"); + goto err_unroll_fltr_mgmt_struct; + } + } + return 0; err_unroll_fltr_mgmt_struct: ice_cleanup_fltr_mgmt_struct(hw); err_unroll_sched: @@ -2567,6 +2641,7 @@ ice_parse_1588_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p, info->ts_ll_read = ((number & ICE_TS_LL_TX_TS_READ_M) != 0); info->ts_ll_int_read = ((number & ICE_TS_LL_TX_TS_INT_READ_M) != 0); + info->ll_phy_tmr_update = ((number & ICE_TS_LL_PHY_TMR_UPDATE_M) != 0); info->ena_ports = logical_id; info->tmr_own_map = phys_id; @@ -2589,6 +2664,8 @@ ice_parse_1588_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p, info->ts_ll_read); ice_debug(hw, ICE_DBG_INIT, "dev caps: ts_ll_int_read = %u\n", info->ts_ll_int_read); + ice_debug(hw, ICE_DBG_INIT, "dev caps: ll_phy_tmr_update = %u\n", + info->ll_phy_tmr_update); ice_debug(hw, ICE_DBG_INIT, "dev caps: ieee_1588 ena_ports = %u\n", info->ena_ports); ice_debug(hw, ICE_DBG_INIT, "dev caps: tmr_own_map = %u\n", @@ -2729,40 +2806,6 @@ ice_parse_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p, } /** - * ice_is_pf_c827 - check if pf contains c827 phy - * @hw: pointer to the hw struct - */ -bool ice_is_pf_c827(struct ice_hw *hw) -{ - struct ice_aqc_get_link_topo cmd = {}; - u8 node_part_number; - u16 node_handle; - int status; - - if (hw->mac_type != ICE_MAC_E810) - return false; - - if (hw->device_id != ICE_DEV_ID_E810C_QSFP) - return true; - - cmd.addr.topo_params.node_type_ctx = - FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_TYPE_M, ICE_AQC_LINK_TOPO_NODE_TYPE_PHY) | - FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_CTX_M, ICE_AQC_LINK_TOPO_NODE_CTX_PORT); - cmd.addr.topo_params.index = 0; - - status = ice_aq_get_netlist_node(hw, &cmd, &node_part_number, - &node_handle); - - if (status || node_part_number != ICE_AQC_GET_LINK_TOPO_NODE_NR_C827) - return false; - - if (node_handle == E810C_QSFP_C827_0_HANDLE || node_handle == E810C_QSFP_C827_1_HANDLE) - return true; - - return false; -} - -/** * ice_is_phy_rclk_in_netlist * @hw: pointer to the hw struct * @@ -4116,6 +4159,57 @@ ice_aq_set_port_option(struct ice_hw *hw, u8 lport, u8 lport_valid, } /** + * ice_get_phy_lane_number - Get PHY lane number for current adapter + * @hw: pointer to the hw struct + * + * Return: PHY lane number on success, negative error code otherwise. + */ +int ice_get_phy_lane_number(struct ice_hw *hw) +{ + struct ice_aqc_get_port_options_elem *options; + unsigned int lport = 0; + unsigned int lane; + int err; + + options = kcalloc(ICE_AQC_PORT_OPT_MAX, sizeof(*options), GFP_KERNEL); + if (!options) + return -ENOMEM; + + for (lane = 0; lane < ICE_MAX_PORT_PER_PCI_DEV; lane++) { + u8 options_count = ICE_AQC_PORT_OPT_MAX; + u8 speed, active_idx, pending_idx; + bool active_valid, pending_valid; + + err = ice_aq_get_port_options(hw, options, &options_count, lane, + true, &active_idx, &active_valid, + &pending_idx, &pending_valid); + if (err) + goto err; + + if (!active_valid) + continue; + + speed = options[active_idx].max_lane_speed; + /* If we don't get speed for this lane, it's unoccupied */ + if (speed > ICE_AQC_PORT_OPT_MAX_LANE_200G) + continue; + + if (hw->pf_id == lport) { + kfree(options); + return lane; + } + + lport++; + } + + /* PHY lane not found */ + err = -ENXIO; +err: + kfree(options); + return err; +} + +/** * ice_aq_sff_eeprom * @hw: pointer to the HW struct * @lport: bits [7:0] = logical port, bit [8] = logical port valid @@ -5853,6 +5947,44 @@ bool ice_is_phy_caps_an_enabled(struct ice_aqc_get_phy_caps_data *caps) } /** + * ice_is_fw_health_report_supported - checks if firmware supports health events + * @hw: pointer to the hardware structure + * + * Return: true if firmware supports health status reports, + * false otherwise + */ +bool ice_is_fw_health_report_supported(struct ice_hw *hw) +{ + return ice_is_fw_api_min_ver(hw, ICE_FW_API_HEALTH_REPORT_MAJ, + ICE_FW_API_HEALTH_REPORT_MIN, + ICE_FW_API_HEALTH_REPORT_PATCH); +} + +/** + * ice_aq_set_health_status_cfg - Configure FW health events + * @hw: pointer to the HW struct + * @event_source: type of diagnostic events to enable + * + * Configure the health status event types that the firmware will send to this + * PF. The supported event types are: PF-specific, all PFs, and global. + * + * Return: 0 on success, negative error code otherwise. + */ +int ice_aq_set_health_status_cfg(struct ice_hw *hw, u8 event_source) +{ + struct ice_aqc_set_health_status_cfg *cmd; + struct ice_aq_desc desc; + + cmd = &desc.params.set_health_status_cfg; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_health_status_cfg); + + cmd->event_source = event_source; + + return ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); +} + +/** * ice_aq_set_lldp_mib - Set the LLDP MIB * @hw: pointer to the HW struct * @mib_type: Local, Remote or both Local and Remote MIBs diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h index a68bea3934e3..15ba38543738 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.h +++ b/drivers/net/ethernet/intel/ice/ice_common.h @@ -112,7 +112,6 @@ int ice_aq_get_phy_caps(struct ice_port_info *pi, bool qual_mods, u8 report_mode, struct ice_aqc_get_phy_caps_data *caps, struct ice_sq_cd *cd); -bool ice_is_pf_c827(struct ice_hw *hw); bool ice_is_phy_rclk_in_netlist(struct ice_hw *hw); bool ice_is_clock_mux_in_netlist(struct ice_hw *hw); bool ice_is_cgu_in_netlist(struct ice_hw *hw); @@ -142,6 +141,8 @@ int ice_get_link_default_override(struct ice_link_default_override_tlv *ldo, struct ice_port_info *pi); bool ice_is_phy_caps_an_enabled(struct ice_aqc_get_phy_caps_data *caps); +bool ice_is_fw_health_report_supported(struct ice_hw *hw); +int ice_aq_set_health_status_cfg(struct ice_hw *hw, u8 event_source); int ice_aq_get_phy_equalization(struct ice_hw *hw, u16 data_in, u16 op_code, u8 serdes_num, int *output); int @@ -192,6 +193,7 @@ ice_aq_get_port_options(struct ice_hw *hw, int ice_aq_set_port_option(struct ice_hw *hw, u8 lport, u8 lport_valid, u8 new_option); +int ice_get_phy_lane_number(struct ice_hw *hw); int ice_aq_sff_eeprom(struct ice_hw *hw, u16 lport, u8 bus_addr, u16 mem_addr, u8 page, u8 set_page, u8 *data, u8 length, diff --git a/drivers/net/ethernet/intel/ice/ice_fw_update.c b/drivers/net/ethernet/intel/ice/ice_fw_update.c index 2702a0da5c3e..70c201f569ce 100644 --- a/drivers/net/ethernet/intel/ice/ice_fw_update.c +++ b/drivers/net/ethernet/intel/ice/ice_fw_update.c @@ -6,6 +6,7 @@ #include <linux/crc32.h> #include <linux/pldmfw.h> #include "ice.h" +#include "ice_lib.h" #include "ice_fw_update.h" struct ice_fwu_priv { @@ -125,6 +126,10 @@ ice_check_component_response(struct ice_pf *pf, u16 id, u8 response, u8 code, case ICE_AQ_NVM_PASS_COMP_CAN_NOT_BE_UPDATED: dev_info(dev, "firmware has rejected updating %s\n", component); break; + case ICE_AQ_NVM_PASS_COMP_PARTIAL_CHECK: + if (ice_is_recovery_mode(&pf->hw)) + return 0; + break; } switch (code) { @@ -1004,13 +1009,20 @@ int ice_devlink_flash_update(struct devlink *devlink, return -EOPNOTSUPP; } - if (!hw->dev_caps.common_cap.nvm_unified_update) { + if (!hw->dev_caps.common_cap.nvm_unified_update && !ice_is_recovery_mode(hw)) { NL_SET_ERR_MSG_MOD(extack, "Current firmware does not support unified update"); return -EOPNOTSUPP; } memset(&priv, 0, sizeof(priv)); + if (params->component && strcmp(params->component, "fw.mgmt") == 0) { + priv.context.mode = PLDMFW_UPDATE_MODE_SINGLE_COMPONENT; + priv.context.component_identifier = NVM_COMP_ID_NVM; + } else if (params->component) { + return -EOPNOTSUPP; + } + /* the E822 device needs a slightly different ops */ if (hw->mac_type == ICE_MAC_GENERIC) priv.context.ops = &ice_fwu_ops_e822; diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index a7d45a8ce7ac..38a1c8372180 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -1700,6 +1700,12 @@ bool ice_pf_state_is_nominal(struct ice_pf *pf) return true; } +#define ICE_FW_MODE_REC_M BIT(1) +bool ice_is_recovery_mode(struct ice_hw *hw) +{ + return rd32(hw, GL_MNG_FWSM) & ICE_FW_MODE_REC_M; +} + /** * ice_update_eth_stats - Update VSI-specific ethernet statistics counters * @vsi: the VSI to be updated diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h index 10d6fc479a32..eabb35834a24 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_lib.h @@ -90,6 +90,7 @@ void ice_set_q_vector_intrl(struct ice_q_vector *q_vector); bool ice_is_safe_mode(struct ice_pf *pf); bool ice_is_rdma_ena(struct ice_pf *pf); +bool ice_is_recovery_mode(struct ice_hw *hw); bool ice_is_dflt_vsi_in_use(struct ice_port_info *pi); bool ice_is_vsi_dflt_vsi(struct ice_vsi *vsi); int ice_set_dflt_vsi(struct ice_vsi *vsi); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 1701f7143f24..c3a0fb97c5ee 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -1144,7 +1144,7 @@ ice_link_event(struct ice_pf *pf, struct ice_port_info *pi, bool link_up, if (link_up == old_link && link_speed == old_link_speed) return 0; - ice_ptp_link_change(pf, pf->hw.pf_id, link_up); + ice_ptp_link_change(pf, link_up); if (ice_is_dcb_active(pf)) { if (test_bit(ICE_FLAG_DCB_ENA, pf->flags)) @@ -1567,6 +1567,9 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type) case ice_aqc_opc_lldp_set_mib_change: ice_dcb_process_lldp_set_mib_change(pf, &event); break; + case ice_aqc_opc_get_health_status: + ice_process_health_status_event(pf, &event); + break; default: dev_dbg(dev, "%s Receive Queue unknown event 0x%04x ignored\n", qtype, opcode); @@ -2361,6 +2364,18 @@ static void ice_check_media_subtask(struct ice_pf *pf) } } +static void ice_service_task_recovery_mode(struct work_struct *work) +{ + struct ice_pf *pf = container_of(work, struct ice_pf, serv_task); + + set_bit(ICE_ADMINQ_EVENT_PENDING, pf->state); + ice_clean_adminq_subtask(pf); + + ice_service_task_complete(pf); + + mod_timer(&pf->serv_tmr, jiffies + msecs_to_jiffies(100)); +} + /** * ice_service_task - manage and run subtasks * @work: pointer to work_struct contained by the PF struct @@ -4749,55 +4764,12 @@ static void ice_decfg_netdev(struct ice_vsi *vsi) vsi->netdev = NULL; } -/** - * ice_wait_for_fw - wait for full FW readiness - * @hw: pointer to the hardware structure - * @timeout: milliseconds that can elapse before timing out - */ -static int ice_wait_for_fw(struct ice_hw *hw, u32 timeout) -{ - int fw_loading; - u32 elapsed = 0; - - while (elapsed <= timeout) { - fw_loading = rd32(hw, GL_MNG_FWSM) & GL_MNG_FWSM_FW_LOADING_M; - - /* firmware was not yet loaded, we have to wait more */ - if (fw_loading) { - elapsed += 100; - msleep(100); - continue; - } - return 0; - } - - return -ETIMEDOUT; -} - int ice_init_dev(struct ice_pf *pf) { struct device *dev = ice_pf_to_dev(pf); struct ice_hw *hw = &pf->hw; int err; - err = ice_init_hw(hw); - if (err) { - dev_err(dev, "ice_init_hw failed: %d\n", err); - return err; - } - - /* Some cards require longer initialization times - * due to necessity of loading FW from an external source. - * This can take even half a minute. - */ - if (ice_is_pf_c827(hw)) { - err = ice_wait_for_fw(hw, 30000); - if (err) { - dev_err(dev, "ice_wait_for_fw timed out"); - return err; - } - } - ice_init_feature_support(pf); err = ice_init_ddp_config(hw, pf); @@ -4818,7 +4790,7 @@ int ice_init_dev(struct ice_pf *pf) err = ice_init_pf(pf); if (err) { dev_err(dev, "ice_init_pf failed: %d\n", err); - goto err_init_pf; + return err; } pf->hw.udp_tunnel_nic.set_port = ice_udp_tunnel_set_port; @@ -4842,7 +4814,7 @@ int ice_init_dev(struct ice_pf *pf) if (err) { dev_err(dev, "ice_init_interrupt_scheme failed: %d\n", err); err = -EIO; - goto err_init_interrupt_scheme; + goto unroll_pf_init; } /* In case of MSIX we are going to setup the misc vector right here @@ -4853,17 +4825,15 @@ int ice_init_dev(struct ice_pf *pf) err = ice_req_irq_msix_misc(pf); if (err) { dev_err(dev, "setup of misc vector failed: %d\n", err); - goto err_req_irq_msix_misc; + goto unroll_irq_scheme_init; } return 0; -err_req_irq_msix_misc: +unroll_irq_scheme_init: ice_clear_interrupt_scheme(pf); -err_init_interrupt_scheme: +unroll_pf_init: ice_deinit_pf(pf); -err_init_pf: - ice_deinit_hw(hw); return err; } @@ -5259,6 +5229,36 @@ void ice_unload(struct ice_pf *pf) ice_decfg_netdev(vsi); } +static int ice_probe_recovery_mode(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); + int err; + + dev_err(dev, "Firmware recovery mode detected. Limiting functionality. Refer to the Intel(R) Ethernet Adapters and Devices User Guide for details on firmware recovery mode\n"); + + INIT_HLIST_HEAD(&pf->aq_wait_list); + spin_lock_init(&pf->aq_wait_lock); + init_waitqueue_head(&pf->aq_wait_queue); + + timer_setup(&pf->serv_tmr, ice_service_timer, 0); + pf->serv_tmr_period = HZ; + INIT_WORK(&pf->serv_task, ice_service_task_recovery_mode); + clear_bit(ICE_SERVICE_SCHED, pf->state); + err = ice_create_all_ctrlq(&pf->hw); + if (err) + return err; + + scoped_guard(devl, priv_to_devlink(pf)) { + err = ice_init_devlink(pf); + if (err) + return err; + } + + ice_service_task_restart(pf); + + return 0; +} + /** * ice_probe - Device initialization routine * @pdev: PCI device information struct @@ -5322,13 +5322,7 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) } pci_set_master(pdev); - - adapter = ice_adapter_get(pdev); - if (IS_ERR(adapter)) - return PTR_ERR(adapter); - pf->pdev = pdev; - pf->adapter = adapter; pci_set_drvdata(pdev, pf); set_bit(ICE_DOWN, pf->state); /* Disable service task until DOWN bit is cleared */ @@ -5356,29 +5350,47 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) hw->debug_mask = debug; #endif + if (ice_is_recovery_mode(hw)) + return ice_probe_recovery_mode(pf); + + err = ice_init_hw(hw); + if (err) { + dev_err(dev, "ice_init_hw failed: %d\n", err); + return err; + } + + adapter = ice_adapter_get(pdev); + if (IS_ERR(adapter)) { + err = PTR_ERR(adapter); + goto unroll_hw_init; + } + pf->adapter = adapter; + err = ice_init(pf); if (err) - goto err_init; + goto unroll_adapter; devl_lock(priv_to_devlink(pf)); err = ice_load(pf); if (err) - goto err_load; + goto unroll_init; err = ice_init_devlink(pf); if (err) - goto err_init_devlink; + goto unroll_load; devl_unlock(priv_to_devlink(pf)); return 0; -err_init_devlink: +unroll_load: ice_unload(pf); -err_load: +unroll_init: devl_unlock(priv_to_devlink(pf)); ice_deinit(pf); -err_init: +unroll_adapter: ice_adapter_put(pdev); +unroll_hw_init: + ice_deinit_hw(hw); return err; } @@ -5458,6 +5470,14 @@ static void ice_remove(struct pci_dev *pdev) msleep(100); } + if (ice_is_recovery_mode(&pf->hw)) { + ice_service_task_stop(pf); + scoped_guard(devl, priv_to_devlink(pf)) { + ice_deinit_devlink(pf); + } + return; + } + if (test_bit(ICE_FLAG_SRIOV_ENA, pf->flags)) { set_bit(ICE_VF_RESETS_DISABLED, pf->state); ice_free_vfs(pf); @@ -6800,7 +6820,7 @@ static int ice_up_complete(struct ice_vsi *vsi) ice_print_link_msg(vsi, true); netif_tx_start_all_queues(vsi->netdev); netif_carrier_on(vsi->netdev); - ice_ptp_link_change(pf, pf->hw.pf_id, true); + ice_ptp_link_change(pf, true); } /* Perform an initial read of the statistics registers now to @@ -7270,7 +7290,7 @@ int ice_down(struct ice_vsi *vsi) if (vsi->netdev) { vlan_err = ice_vsi_del_vlan_zero(vsi); - ice_ptp_link_change(vsi->back, vsi->back->hw.pf_id, false); + ice_ptp_link_change(vsi->back, false); netif_carrier_off(vsi->netdev); netif_tx_disable(vsi->netdev); } diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index a999fface272..c27f28c1cf04 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -16,28 +16,28 @@ static const char ice_pin_names[][64] = { }; static const struct ice_ptp_pin_desc ice_pin_desc_e82x[] = { - /* name, gpio */ - { TIME_SYNC, { 4, -1 }}, - { ONE_PPS, { -1, 5 }}, + /* name, gpio, delay */ + { TIME_SYNC, { 4, -1 }, { 0, 0 }}, + { ONE_PPS, { -1, 5 }, { 0, 11 }}, }; static const struct ice_ptp_pin_desc ice_pin_desc_e825c[] = { - /* name, gpio */ - { SDP0, { 0, 0 }}, - { SDP1, { 1, 1 }}, - { SDP2, { 2, 2 }}, - { SDP3, { 3, 3 }}, - { TIME_SYNC, { 4, -1 }}, - { ONE_PPS, { -1, 5 }}, + /* name, gpio, delay */ + { SDP0, { 0, 0 }, { 15, 14 }}, + { SDP1, { 1, 1 }, { 15, 14 }}, + { SDP2, { 2, 2 }, { 15, 14 }}, + { SDP3, { 3, 3 }, { 15, 14 }}, + { TIME_SYNC, { 4, -1 }, { 11, 0 }}, + { ONE_PPS, { -1, 5 }, { 0, 9 }}, }; static const struct ice_ptp_pin_desc ice_pin_desc_e810[] = { - /* name, gpio */ - { SDP0, { 0, 0 }}, - { SDP1, { 1, 1 }}, - { SDP2, { 2, 2 }}, - { SDP3, { 3, 3 }}, - { ONE_PPS, { -1, 5 }}, + /* name, gpio, delay */ + { SDP0, { 0, 0 }, { 0, 1 }}, + { SDP1, { 1, 1 }, { 0, 1 }}, + { SDP2, { 2, 2 }, { 0, 1 }}, + { SDP3, { 3, 3 }, { 0, 1 }}, + { ONE_PPS, { -1, 5 }, { 0, 1 }}, }; static const char ice_pin_names_nvm[][64] = { @@ -49,12 +49,12 @@ static const char ice_pin_names_nvm[][64] = { }; static const struct ice_ptp_pin_desc ice_pin_desc_e810_sma[] = { - /* name, gpio */ - { GNSS, { 1, -1 }}, - { SMA1, { 1, 0 }}, - { UFL1, { -1, 0 }}, - { SMA2, { 3, 2 }}, - { UFL2, { 3, -1 }}, + /* name, gpio, delay */ + { GNSS, { 1, -1 }, { 0, 0 }}, + { SMA1, { 1, 0 }, { 0, 1 }}, + { UFL1, { -1, 0 }, { 0, 1 }}, + { SMA2, { 3, 2 }, { 0, 1 }}, + { UFL2, { 3, -1 }, { 0, 0 }}, }; static struct ice_pf *ice_get_ctrl_pf(struct ice_pf *pf) @@ -464,7 +464,9 @@ ice_ptp_is_tx_tracker_up(struct ice_ptp_tx *tx) */ void ice_ptp_req_tx_single_tstamp(struct ice_ptp_tx *tx, u8 idx) { + struct ice_e810_params *params; struct ice_ptp_port *ptp_port; + unsigned long flags; struct sk_buff *skb; struct ice_pf *pf; @@ -473,6 +475,7 @@ void ice_ptp_req_tx_single_tstamp(struct ice_ptp_tx *tx, u8 idx) ptp_port = container_of(tx, struct ice_ptp_port, tx); pf = ptp_port_to_pf(ptp_port); + params = &pf->hw.ptp.phy.e810; /* Drop packets which have waited for more than 2 seconds */ if (time_is_before_jiffies(tx->tstamps[idx].start + 2 * HZ)) { @@ -489,11 +492,17 @@ void ice_ptp_req_tx_single_tstamp(struct ice_ptp_tx *tx, u8 idx) ice_trace(tx_tstamp_fw_req, tx->tstamps[idx].skb, idx); + spin_lock_irqsave(¶ms->atqbal_wq.lock, flags); + + params->atqbal_flags |= ATQBAL_FLAGS_INTR_IN_PROGRESS; + /* Write TS index to read to the PF register so the FW can read it */ - wr32(&pf->hw, PF_SB_ATQBAL, - TS_LL_READ_TS_INTR | FIELD_PREP(TS_LL_READ_TS_IDX, idx) | - TS_LL_READ_TS); + wr32(&pf->hw, REG_LL_PROXY_H, + REG_LL_PROXY_H_TS_INTR_ENA | FIELD_PREP(REG_LL_PROXY_H_TS_IDX, idx) | + REG_LL_PROXY_H_EXEC); tx->last_ll_ts_idx_read = idx; + + spin_unlock_irqrestore(¶ms->atqbal_wq.lock, flags); } /** @@ -504,35 +513,52 @@ void ice_ptp_complete_tx_single_tstamp(struct ice_ptp_tx *tx) { struct skb_shared_hwtstamps shhwtstamps = {}; u8 idx = tx->last_ll_ts_idx_read; + struct ice_e810_params *params; struct ice_ptp_port *ptp_port; u64 raw_tstamp, tstamp; bool drop_ts = false; struct sk_buff *skb; + unsigned long flags; + struct device *dev; struct ice_pf *pf; - u32 val; + u32 reg_ll_high; if (!tx->init || tx->last_ll_ts_idx_read < 0) return; ptp_port = container_of(tx, struct ice_ptp_port, tx); pf = ptp_port_to_pf(ptp_port); + dev = ice_pf_to_dev(pf); + params = &pf->hw.ptp.phy.e810; ice_trace(tx_tstamp_fw_done, tx->tstamps[idx].skb, idx); - val = rd32(&pf->hw, PF_SB_ATQBAL); + spin_lock_irqsave(¶ms->atqbal_wq.lock, flags); + + if (!(params->atqbal_flags & ATQBAL_FLAGS_INTR_IN_PROGRESS)) + dev_dbg(dev, "%s: low latency interrupt request not in progress?\n", + __func__); + + /* Read the low 32 bit value */ + raw_tstamp = rd32(&pf->hw, REG_LL_PROXY_L); + /* Read the status together with high TS part */ + reg_ll_high = rd32(&pf->hw, REG_LL_PROXY_H); + + /* Wake up threads waiting on low latency interface */ + params->atqbal_flags &= ~ATQBAL_FLAGS_INTR_IN_PROGRESS; + + wake_up_locked(¶ms->atqbal_wq); + + spin_unlock_irqrestore(¶ms->atqbal_wq.lock, flags); /* When the bit is cleared, the TS is ready in the register */ - if (val & TS_LL_READ_TS) { + if (reg_ll_high & REG_LL_PROXY_H_EXEC) { dev_err(ice_pf_to_dev(pf), "Failed to get the Tx tstamp - FW not ready"); return; } /* High 8 bit value of the TS is on the bits 16:23 */ - raw_tstamp = FIELD_GET(TS_LL_READ_TS_HIGH, val); - raw_tstamp <<= 32; - - /* Read the low 32 bit value */ - raw_tstamp |= (u64)rd32(&pf->hw, PF_SB_ATQBAH); + raw_tstamp |= ((u64)FIELD_GET(REG_LL_PROXY_H_TS_HIGH, reg_ll_high)) << 32; /* Devices using this interface always verify the timestamp differs * relative to the last cached timestamp value. @@ -1388,10 +1414,9 @@ ice_ptp_port_phy_restart(struct ice_ptp_port *ptp_port) /** * ice_ptp_link_change - Reconfigure PTP after link status change * @pf: Board private structure - * @port: Port for which the PHY start is set * @linkup: Link is up or down */ -void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup) +void ice_ptp_link_change(struct ice_pf *pf, bool linkup) { struct ice_ptp_port *ptp_port; struct ice_hw *hw = &pf->hw; @@ -1399,14 +1424,7 @@ void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup) if (pf->ptp.state != ICE_PTP_READY) return; - if (WARN_ON_ONCE(port >= hw->ptp.num_lports)) - return; - ptp_port = &pf->ptp.port; - if (ice_is_e825c(hw) && hw->ptp.is_2x50g_muxed_topo) - port *= 2; - if (WARN_ON_ONCE(ptp_port->port_num != port)) - return; /* Update cached link status for this port immediately */ ptp_port->link_up = linkup; @@ -1566,18 +1584,29 @@ void ice_ptp_extts_event(struct ice_pf *pf) * Event is defined in GLTSYN_EVNT_0 register */ for (chan = 0; chan < GLTSYN_EVNT_H_IDX_MAX; chan++) { + int pin_desc_idx; + /* Check if channel is enabled */ - if (pf->ptp.ext_ts_irq & (1 << chan)) { - lo = rd32(hw, GLTSYN_EVNT_L(chan, tmr_idx)); - hi = rd32(hw, GLTSYN_EVNT_H(chan, tmr_idx)); - event.timestamp = (((u64)hi) << 32) | lo; - event.type = PTP_CLOCK_EXTTS; - event.index = chan; - - /* Fire event */ - ptp_clock_event(pf->ptp.clock, &event); - pf->ptp.ext_ts_irq &= ~(1 << chan); + if (!(pf->ptp.ext_ts_irq & (1 << chan))) + continue; + + lo = rd32(hw, GLTSYN_EVNT_L(chan, tmr_idx)); + hi = rd32(hw, GLTSYN_EVNT_H(chan, tmr_idx)); + event.timestamp = (u64)hi << 32 | lo; + + /* Add delay compensation */ + pin_desc_idx = ice_ptp_find_pin_idx(pf, PTP_PF_EXTTS, chan); + if (pin_desc_idx >= 0) { + const struct ice_ptp_pin_desc *desc; + + desc = &pf->ptp.ice_pin_desc[pin_desc_idx]; + event.timestamp -= desc->delay[0]; } + + event.type = PTP_CLOCK_EXTTS; + event.index = chan; + pf->ptp.ext_ts_irq &= ~(1 << chan); + ptp_clock_event(pf->ptp.clock, &event); } } @@ -1772,9 +1801,9 @@ static int ice_ptp_write_perout(struct ice_hw *hw, unsigned int chan, static int ice_ptp_cfg_perout(struct ice_pf *pf, struct ptp_perout_request *rq, int on) { + unsigned int gpio_pin, prop_delay_ns; u64 clk, period, start, phase; struct ice_hw *hw = &pf->hw; - unsigned int gpio_pin; int pin_desc_idx; if (rq->flags & ~PTP_PEROUT_PHASE) @@ -1785,6 +1814,7 @@ static int ice_ptp_cfg_perout(struct ice_pf *pf, struct ptp_perout_request *rq, return -EIO; gpio_pin = pf->ptp.ice_pin_desc[pin_desc_idx].gpio[1]; + prop_delay_ns = pf->ptp.ice_pin_desc[pin_desc_idx].delay[1]; period = rq->period.sec * NSEC_PER_SEC + rq->period.nsec; /* If we're disabling the output or period is 0, clear out CLKO and TGT @@ -1816,11 +1846,11 @@ static int ice_ptp_cfg_perout(struct ice_pf *pf, struct ptp_perout_request *rq, * at the next multiple of period, maintaining phase. */ clk = ice_ptp_read_src_clk_reg(pf, NULL); - if (rq->flags & PTP_PEROUT_PHASE || start <= clk - ice_prop_delay(hw)) + if (rq->flags & PTP_PEROUT_PHASE || start <= clk - prop_delay_ns) start = div64_u64(clk + period - 1, period) * period + phase; /* Compensate for propagation delay from the generator to the pin. */ - start -= ice_prop_delay(hw); + start -= prop_delay_ns; return ice_ptp_write_perout(hw, rq->index, gpio_pin, start, period); } @@ -3164,10 +3194,17 @@ void ice_ptp_init(struct ice_pf *pf) { struct ice_ptp *ptp = &pf->ptp; struct ice_hw *hw = &pf->hw; - int err; + int lane_num, err; ptp->state = ICE_PTP_INITIALIZING; + lane_num = ice_get_phy_lane_number(hw); + if (lane_num < 0) { + err = lane_num; + goto err_exit; + } + + ptp->port.port_num = (u8)lane_num; ice_ptp_init_hw(hw); ice_ptp_init_tx_interrupt_mode(pf); @@ -3188,10 +3225,6 @@ void ice_ptp_init(struct ice_pf *pf) if (err) goto err_exit; - ptp->port.port_num = hw->pf_id; - if (ice_is_e825c(hw) && hw->ptp.is_2x50g_muxed_topo) - ptp->port.port_num = hw->pf_id * 2; - err = ice_ptp_init_port(pf, &ptp->port); if (err) goto err_exit; diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.h b/drivers/net/ethernet/intel/ice/ice_ptp.h index 824e73b677a4..a1d0e988c084 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp.h @@ -211,6 +211,7 @@ enum ice_ptp_pin_nvm { * struct ice_ptp_pin_desc - hardware pin description data * @name_idx: index of the name of pin in ice_pin_names * @gpio: the associated GPIO input and output pins + * @delay: input and output signal delays in nanoseconds * * Structure describing a PTP-capable GPIO pin that extends ptp_pin_desc array * for the device. Device families have separate sets of available pins with @@ -219,6 +220,7 @@ enum ice_ptp_pin_nvm { struct ice_ptp_pin_desc { int name_idx; int gpio[2]; + unsigned int delay[2]; }; /** @@ -310,7 +312,7 @@ void ice_ptp_prepare_for_reset(struct ice_pf *pf, enum ice_reset_req reset_type); void ice_ptp_init(struct ice_pf *pf); void ice_ptp_release(struct ice_pf *pf); -void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup); +void ice_ptp_link_change(struct ice_pf *pf, bool linkup); #else /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */ static inline int ice_ptp_set_ts_config(struct ice_pf *pf, struct ifreq *ifr) { @@ -358,7 +360,7 @@ static inline void ice_ptp_prepare_for_reset(struct ice_pf *pf, } static inline void ice_ptp_init(struct ice_pf *pf) { } static inline void ice_ptp_release(struct ice_pf *pf) { } -static inline void ice_ptp_link_change(struct ice_pf *pf, u8 port, bool linkup) +static inline void ice_ptp_link_change(struct ice_pf *pf, bool linkup) { } diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_consts.h b/drivers/net/ethernet/intel/ice/ice_ptp_consts.h index d75f0eddd631..ac46d1183300 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_consts.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp_consts.h @@ -131,7 +131,7 @@ struct ice_eth56g_mac_reg_cfg eth56g_mac_cfg[NUM_ICE_ETH56G_LNK_SPD] = { .rx_offset = { .serdes = 0xffffeb27, /* -10.42424 */ .no_fec = 0xffffcccd, /* -25.6 */ - .fc = 0xfffe0014, /* -255.96 */ + .fc = 0xfffc557b, /* -469.26 */ .sfd = 0x4a4, /* 2.32 */ .bs_ds = 0x32 /* 0.0969697 */ } @@ -341,8 +341,6 @@ const struct ice_time_ref_info_e82x e82x_time_ref[NUM_ICE_TIME_REF_FREQ] = { 823437500, /* 823.4375 MHz PLL */ /* nominal_incval */ 0x136e44fabULL, - /* pps_delay */ - 11, }, /* ICE_TIME_REF_FREQ_122_880 -> 122.88 MHz */ @@ -351,8 +349,6 @@ const struct ice_time_ref_info_e82x e82x_time_ref[NUM_ICE_TIME_REF_FREQ] = { 783360000, /* 783.36 MHz */ /* nominal_incval */ 0x146cc2177ULL, - /* pps_delay */ - 12, }, /* ICE_TIME_REF_FREQ_125_000 -> 125 MHz */ @@ -361,8 +357,6 @@ const struct ice_time_ref_info_e82x e82x_time_ref[NUM_ICE_TIME_REF_FREQ] = { 796875000, /* 796.875 MHz */ /* nominal_incval */ 0x141414141ULL, - /* pps_delay */ - 12, }, /* ICE_TIME_REF_FREQ_153_600 -> 153.6 MHz */ @@ -371,8 +365,6 @@ const struct ice_time_ref_info_e82x e82x_time_ref[NUM_ICE_TIME_REF_FREQ] = { 816000000, /* 816 MHz */ /* nominal_incval */ 0x139b9b9baULL, - /* pps_delay */ - 12, }, /* ICE_TIME_REF_FREQ_156_250 -> 156.25 MHz */ @@ -381,8 +373,6 @@ const struct ice_time_ref_info_e82x e82x_time_ref[NUM_ICE_TIME_REF_FREQ] = { 830078125, /* 830.78125 MHz */ /* nominal_incval */ 0x134679aceULL, - /* pps_delay */ - 11, }, /* ICE_TIME_REF_FREQ_245_760 -> 245.76 MHz */ @@ -391,8 +381,6 @@ const struct ice_time_ref_info_e82x e82x_time_ref[NUM_ICE_TIME_REF_FREQ] = { 783360000, /* 783.36 MHz */ /* nominal_incval */ 0x146cc2177ULL, - /* pps_delay */ - 12, }, }; diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c index 518893f23372..ec91822e9280 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c @@ -391,7 +391,7 @@ static int ice_cfg_cgu_pll_e82x(struct ice_hw *hw, /* Log the current clock configuration */ ice_debug(hw, ICE_DBG_PTP, "Current CGU configuration -- %s, clk_src %s, clk_freq %s, PLL %s\n", - dw24.ts_pll_enable ? "enabled" : "disabled", + str_enabled_disabled(dw24.ts_pll_enable), ice_clk_src_str(dw24.time_ref_sel), ice_clk_freq_str(dw9.time_ref_freq_sel), bwm_lf.plllock_true_lock_cri ? "locked" : "unlocked"); @@ -469,7 +469,7 @@ static int ice_cfg_cgu_pll_e82x(struct ice_hw *hw, /* Log the current clock configuration */ ice_debug(hw, ICE_DBG_PTP, "New CGU configuration -- %s, clk_src %s, clk_freq %s, PLL %s\n", - dw24.ts_pll_enable ? "enabled" : "disabled", + str_enabled_disabled(dw24.ts_pll_enable), ice_clk_src_str(dw24.time_ref_sel), ice_clk_freq_str(dw9.time_ref_freq_sel), bwm_lf.plllock_true_lock_cri ? "locked" : "unlocked"); @@ -546,7 +546,7 @@ static int ice_cfg_cgu_pll_e825c(struct ice_hw *hw, /* Log the current clock configuration */ ice_debug(hw, ICE_DBG_PTP, "Current CGU configuration -- %s, clk_src %s, clk_freq %s, PLL %s\n", - dw24.ts_pll_enable ? "enabled" : "disabled", + str_enabled_disabled(dw24.ts_pll_enable), ice_clk_src_str(dw23.time_ref_sel), ice_clk_freq_str(dw9.time_ref_freq_sel), ro_lock.plllock_true_lock_cri ? "locked" : "unlocked"); @@ -651,7 +651,7 @@ static int ice_cfg_cgu_pll_e825c(struct ice_hw *hw, /* Log the current clock configuration */ ice_debug(hw, ICE_DBG_PTP, "New CGU configuration -- %s, clk_src %s, clk_freq %s, PLL %s\n", - dw24.ts_pll_enable ? "enabled" : "disabled", + str_enabled_disabled(dw24.ts_pll_enable), ice_clk_src_str(dw23.time_ref_sel), ice_clk_freq_str(dw9.time_ref_freq_sel), ro_lock.plllock_true_lock_cri ? "locked" : "unlocked"); @@ -901,30 +901,45 @@ static void ice_ptp_exec_tmr_cmd(struct ice_hw *hw) */ /** + * ice_ptp_get_dest_dev_e825 - get destination PHY for given port number + * @hw: pointer to the HW struct + * @port: destination port + * + * Return: destination sideband queue PHY device. + */ +static enum ice_sbq_msg_dev ice_ptp_get_dest_dev_e825(struct ice_hw *hw, + u8 port) +{ + /* On a single complex E825, PHY 0 is always destination device phy_0 + * and PHY 1 is phy_0_peer. + */ + if (port >= hw->ptp.ports_per_phy) + return eth56g_phy_1; + else + return eth56g_phy_0; +} + +/** * ice_write_phy_eth56g - Write a PHY port register * @hw: pointer to the HW struct - * @phy_idx: PHY index + * @port: destination port * @addr: PHY register address * @val: Value to write * * Return: 0 on success, other error codes when failed to write to PHY */ -static int ice_write_phy_eth56g(struct ice_hw *hw, u8 phy_idx, u32 addr, - u32 val) +static int ice_write_phy_eth56g(struct ice_hw *hw, u8 port, u32 addr, u32 val) { - struct ice_sbq_msg_input phy_msg; + struct ice_sbq_msg_input msg = { + .dest_dev = ice_ptp_get_dest_dev_e825(hw, port), + .opcode = ice_sbq_msg_wr, + .msg_addr_low = lower_16_bits(addr), + .msg_addr_high = upper_16_bits(addr), + .data = val + }; int err; - phy_msg.opcode = ice_sbq_msg_wr; - - phy_msg.msg_addr_low = lower_16_bits(addr); - phy_msg.msg_addr_high = upper_16_bits(addr); - - phy_msg.data = val; - phy_msg.dest_dev = hw->ptp.phy.eth56g.phy_addr[phy_idx]; - - err = ice_sbq_rw_reg(hw, &phy_msg, ICE_AQ_FLAG_RD); - + err = ice_sbq_rw_reg(hw, &msg, ICE_AQ_FLAG_RD); if (err) ice_debug(hw, ICE_DBG_PTP, "PTP failed to send msg to phy %d\n", err); @@ -935,41 +950,36 @@ static int ice_write_phy_eth56g(struct ice_hw *hw, u8 phy_idx, u32 addr, /** * ice_read_phy_eth56g - Read a PHY port register * @hw: pointer to the HW struct - * @phy_idx: PHY index + * @port: destination port * @addr: PHY register address * @val: Value to write * * Return: 0 on success, other error codes when failed to read from PHY */ -static int ice_read_phy_eth56g(struct ice_hw *hw, u8 phy_idx, u32 addr, - u32 *val) +static int ice_read_phy_eth56g(struct ice_hw *hw, u8 port, u32 addr, u32 *val) { - struct ice_sbq_msg_input phy_msg; + struct ice_sbq_msg_input msg = { + .dest_dev = ice_ptp_get_dest_dev_e825(hw, port), + .opcode = ice_sbq_msg_rd, + .msg_addr_low = lower_16_bits(addr), + .msg_addr_high = upper_16_bits(addr) + }; int err; - phy_msg.opcode = ice_sbq_msg_rd; - - phy_msg.msg_addr_low = lower_16_bits(addr); - phy_msg.msg_addr_high = upper_16_bits(addr); - - phy_msg.data = 0; - phy_msg.dest_dev = hw->ptp.phy.eth56g.phy_addr[phy_idx]; - - err = ice_sbq_rw_reg(hw, &phy_msg, ICE_AQ_FLAG_RD); - if (err) { + err = ice_sbq_rw_reg(hw, &msg, ICE_AQ_FLAG_RD); + if (err) ice_debug(hw, ICE_DBG_PTP, "PTP failed to send msg to phy %d\n", err); - return err; - } - - *val = phy_msg.data; + else + *val = msg.data; - return 0; + return err; } /** * ice_phy_res_address_eth56g - Calculate a PHY port register address - * @port: Port number to be written + * @hw: pointer to the HW struct + * @lane: Lane number to be written * @res_type: resource type (register/memory) * @offset: Offset from PHY port register base * @addr: The result address @@ -978,17 +988,19 @@ static int ice_read_phy_eth56g(struct ice_hw *hw, u8 phy_idx, u32 addr, * * %0 - success * * %EINVAL - invalid port number or resource type */ -static int ice_phy_res_address_eth56g(u8 port, enum eth56g_res_type res_type, - u32 offset, u32 *addr) +static int ice_phy_res_address_eth56g(struct ice_hw *hw, u8 lane, + enum eth56g_res_type res_type, + u32 offset, + u32 *addr) { - u8 lane = port % ICE_PORTS_PER_QUAD; - u8 phy = ICE_GET_QUAD_NUM(port); - if (res_type >= NUM_ETH56G_PHY_RES) return -EINVAL; - *addr = eth56g_phy_res[res_type].base[phy] + + /* Lanes 4..7 are in fact 0..3 on a second PHY */ + lane %= hw->ptp.ports_per_phy; + *addr = eth56g_phy_res[res_type].base[0] + lane * eth56g_phy_res[res_type].step + offset; + return 0; } @@ -1008,19 +1020,17 @@ static int ice_phy_res_address_eth56g(u8 port, enum eth56g_res_type res_type, static int ice_write_port_eth56g(struct ice_hw *hw, u8 port, u32 offset, u32 val, enum eth56g_res_type res_type) { - u8 phy_port = port % hw->ptp.ports_per_phy; - u8 phy_idx = port / hw->ptp.ports_per_phy; u32 addr; int err; if (port >= hw->ptp.num_lports) return -EINVAL; - err = ice_phy_res_address_eth56g(phy_port, res_type, offset, &addr); + err = ice_phy_res_address_eth56g(hw, port, res_type, offset, &addr); if (err) return err; - return ice_write_phy_eth56g(hw, phy_idx, addr, val); + return ice_write_phy_eth56g(hw, port, addr, val); } /** @@ -1039,19 +1049,17 @@ static int ice_write_port_eth56g(struct ice_hw *hw, u8 port, u32 offset, static int ice_read_port_eth56g(struct ice_hw *hw, u8 port, u32 offset, u32 *val, enum eth56g_res_type res_type) { - u8 phy_port = port % hw->ptp.ports_per_phy; - u8 phy_idx = port / hw->ptp.ports_per_phy; u32 addr; int err; if (port >= hw->ptp.num_lports) return -EINVAL; - err = ice_phy_res_address_eth56g(phy_port, res_type, offset, &addr); + err = ice_phy_res_address_eth56g(hw, port, res_type, offset, &addr); if (err) return err; - return ice_read_phy_eth56g(hw, phy_idx, addr, val); + return ice_read_phy_eth56g(hw, port, addr, val); } /** @@ -1201,6 +1209,56 @@ static int ice_write_port_mem_eth56g(struct ice_hw *hw, u8 port, u16 offset, } /** + * ice_write_quad_ptp_reg_eth56g - Write a PHY quad register + * @hw: pointer to the HW struct + * @offset: PHY register offset + * @port: Port number + * @val: Value to write + * + * Return: + * * %0 - success + * * %EIO - invalid port number or resource type + * * %other - failed to write to PHY + */ +static int ice_write_quad_ptp_reg_eth56g(struct ice_hw *hw, u8 port, + u32 offset, u32 val) +{ + u32 addr; + + if (port >= hw->ptp.num_lports) + return -EIO; + + addr = eth56g_phy_res[ETH56G_PHY_REG_PTP].base[0] + offset; + + return ice_write_phy_eth56g(hw, port, addr, val); +} + +/** + * ice_read_quad_ptp_reg_eth56g - Read a PHY quad register + * @hw: pointer to the HW struct + * @offset: PHY register offset + * @port: Port number + * @val: Value to read + * + * Return: + * * %0 - success + * * %EIO - invalid port number or resource type + * * %other - failed to read from PHY + */ +static int ice_read_quad_ptp_reg_eth56g(struct ice_hw *hw, u8 port, + u32 offset, u32 *val) +{ + u32 addr; + + if (port >= hw->ptp.num_lports) + return -EIO; + + addr = eth56g_phy_res[ETH56G_PHY_REG_PTP].base[0] + offset; + + return ice_read_phy_eth56g(hw, port, addr, val); +} + +/** * ice_is_64b_phy_reg_eth56g - Check if this is a 64bit PHY register * @low_addr: the low address to check * @high_addr: on return, contains the high address of the 64bit register @@ -1919,7 +1977,6 @@ ice_phy_get_speed_eth56g(struct ice_link_status *li) */ static int ice_phy_cfg_parpcs_eth56g(struct ice_hw *hw, u8 port) { - u8 port_blk = port & ~(ICE_PORTS_PER_QUAD - 1); u32 val; int err; @@ -1934,8 +1991,8 @@ static int ice_phy_cfg_parpcs_eth56g(struct ice_hw *hw, u8 port) switch (ice_phy_get_speed_eth56g(&hw->port_info->phy.link_info)) { case ICE_ETH56G_LNK_SPD_1G: case ICE_ETH56G_LNK_SPD_2_5G: - err = ice_read_ptp_reg_eth56g(hw, port_blk, - PHY_GPCS_CONFIG_REG0, &val); + err = ice_read_quad_ptp_reg_eth56g(hw, port, + PHY_GPCS_CONFIG_REG0, &val); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to read PHY_GPCS_CONFIG_REG0, status: %d", err); @@ -1946,8 +2003,8 @@ static int ice_phy_cfg_parpcs_eth56g(struct ice_hw *hw, u8 port) val |= FIELD_PREP(PHY_GPCS_CONFIG_REG0_TX_THR_M, ICE_ETH56G_NOMINAL_TX_THRESH); - err = ice_write_ptp_reg_eth56g(hw, port_blk, - PHY_GPCS_CONFIG_REG0, val); + err = ice_write_quad_ptp_reg_eth56g(hw, port, + PHY_GPCS_CONFIG_REG0, val); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to write PHY_GPCS_CONFIG_REG0, status: %d", err); @@ -1988,50 +2045,47 @@ static int ice_phy_cfg_parpcs_eth56g(struct ice_hw *hw, u8 port) */ int ice_phy_cfg_ptp_1step_eth56g(struct ice_hw *hw, u8 port) { - u8 port_blk = port & ~(ICE_PORTS_PER_QUAD - 1); - u8 blk_port = port & (ICE_PORTS_PER_QUAD - 1); + u8 quad_lane = port % ICE_PORTS_PER_QUAD; + u32 addr, val, peer_delay; bool enable, sfd_ena; - u32 val, peer_delay; int err; enable = hw->ptp.phy.eth56g.onestep_ena; peer_delay = hw->ptp.phy.eth56g.peer_delay; sfd_ena = hw->ptp.phy.eth56g.sfd_ena; - /* PHY_PTP_1STEP_CONFIG */ - err = ice_read_ptp_reg_eth56g(hw, port_blk, PHY_PTP_1STEP_CONFIG, &val); + addr = PHY_PTP_1STEP_CONFIG; + err = ice_read_quad_ptp_reg_eth56g(hw, port, addr, &val); if (err) return err; if (enable) - val |= blk_port; + val |= BIT(quad_lane); else - val &= ~blk_port; + val &= ~BIT(quad_lane); val &= ~(PHY_PTP_1STEP_T1S_UP64_M | PHY_PTP_1STEP_T1S_DELTA_M); - err = ice_write_ptp_reg_eth56g(hw, port_blk, PHY_PTP_1STEP_CONFIG, val); + err = ice_write_quad_ptp_reg_eth56g(hw, port, addr, val); if (err) return err; - /* PHY_PTP_1STEP_PEER_DELAY */ + addr = PHY_PTP_1STEP_PEER_DELAY(quad_lane); val = FIELD_PREP(PHY_PTP_1STEP_PD_DELAY_M, peer_delay); if (peer_delay) val |= PHY_PTP_1STEP_PD_ADD_PD_M; val |= PHY_PTP_1STEP_PD_DLY_V_M; - err = ice_write_ptp_reg_eth56g(hw, port_blk, - PHY_PTP_1STEP_PEER_DELAY(blk_port), val); + err = ice_write_quad_ptp_reg_eth56g(hw, port, addr, val); if (err) return err; val &= ~PHY_PTP_1STEP_PD_DLY_V_M; - err = ice_write_ptp_reg_eth56g(hw, port_blk, - PHY_PTP_1STEP_PEER_DELAY(blk_port), val); + err = ice_write_quad_ptp_reg_eth56g(hw, port, addr, val); if (err) return err; - /* PHY_MAC_XIF_MODE */ - err = ice_read_mac_reg_eth56g(hw, port, PHY_MAC_XIF_MODE, &val); + addr = PHY_MAC_XIF_MODE; + err = ice_read_mac_reg_eth56g(hw, port, addr, &val); if (err) return err; @@ -2051,7 +2105,7 @@ int ice_phy_cfg_ptp_1step_eth56g(struct ice_hw *hw, u8 port) FIELD_PREP(PHY_MAC_XIF_TS_BIN_MODE_M, enable) | FIELD_PREP(PHY_MAC_XIF_TS_SFD_ENA_M, sfd_ena); - return ice_write_mac_reg_eth56g(hw, port, PHY_MAC_XIF_MODE, val); + return ice_write_mac_reg_eth56g(hw, port, addr, val); } /** @@ -2093,21 +2147,22 @@ static u32 ice_ptp_calc_bitslip_eth56g(struct ice_hw *hw, u8 port, u32 bs, bool fc, bool rs, enum ice_eth56g_link_spd spd) { - u8 port_offset = port & (ICE_PORTS_PER_QUAD - 1); - u8 port_blk = port & ~(ICE_PORTS_PER_QUAD - 1); u32 bitslip; int err; if (!bs || rs) return 0; - if (spd == ICE_ETH56G_LNK_SPD_1G || spd == ICE_ETH56G_LNK_SPD_2_5G) + if (spd == ICE_ETH56G_LNK_SPD_1G || spd == ICE_ETH56G_LNK_SPD_2_5G) { err = ice_read_gpcs_reg_eth56g(hw, port, PHY_GPCS_BITSLIP, &bitslip); - else - err = ice_read_ptp_reg_eth56g(hw, port_blk, - PHY_REG_SD_BIT_SLIP(port_offset), - &bitslip); + } else { + u8 quad_lane = port % ICE_PORTS_PER_QUAD; + u32 addr; + + addr = PHY_REG_SD_BIT_SLIP(quad_lane); + err = ice_read_quad_ptp_reg_eth56g(hw, port, addr, &bitslip); + } if (err) return 0; @@ -2667,59 +2722,29 @@ static int ice_get_phy_tx_tstamp_ready_eth56g(struct ice_hw *hw, u8 port, } /** - * ice_is_muxed_topo - detect breakout 2x50G topology for E825C - * @hw: pointer to the HW struct - * - * Return: true if it's 2x50 breakout topology, false otherwise - */ -static bool ice_is_muxed_topo(struct ice_hw *hw) -{ - u8 link_topo; - bool mux; - u32 val; - - val = rd32(hw, GLGEN_SWITCH_MODE_CONFIG); - mux = FIELD_GET(GLGEN_SWITCH_MODE_CONFIG_25X4_QUAD_M, val); - val = rd32(hw, GLGEN_MAC_LINK_TOPO); - link_topo = FIELD_GET(GLGEN_MAC_LINK_TOPO_LINK_TOPO_M, val); - - return (mux && link_topo == ICE_LINK_TOPO_UP_TO_2_LINKS); -} - -/** - * ice_ptp_init_phy_e825c - initialize PHY parameters + * ice_ptp_init_phy_e825 - initialize PHY parameters * @hw: pointer to the HW struct */ -static void ice_ptp_init_phy_e825c(struct ice_hw *hw) +static void ice_ptp_init_phy_e825(struct ice_hw *hw) { struct ice_ptp_hw *ptp = &hw->ptp; struct ice_eth56g_params *params; - u8 phy; + u32 phy_rev; + int err; ptp->phy_model = ICE_PHY_ETH56G; params = &ptp->phy.eth56g; params->onestep_ena = false; params->peer_delay = 0; params->sfd_ena = false; - params->phy_addr[0] = eth56g_phy_0; - params->phy_addr[1] = eth56g_phy_1; params->num_phys = 2; ptp->ports_per_phy = 4; ptp->num_lports = params->num_phys * ptp->ports_per_phy; ice_sb_access_ena_eth56g(hw, true); - for (phy = 0; phy < params->num_phys; phy++) { - u32 phy_rev; - int err; - - err = ice_read_phy_eth56g(hw, phy, PHY_REG_REVISION, &phy_rev); - if (err || phy_rev != PHY_REVISION_ETH56G) { - ptp->phy_model = ICE_PHY_UNSUP; - return; - } - } - - ptp->is_2x50g_muxed_topo = ice_is_muxed_topo(hw); + err = ice_read_phy_eth56g(hw, hw->pf_id, PHY_REG_REVISION, &phy_rev); + if (err || phy_rev != PHY_REVISION_ETH56G) + ptp->phy_model = ICE_PHY_UNSUP; } /* E822 family functions @@ -2738,10 +2763,9 @@ static void ice_fill_phy_msg_e82x(struct ice_hw *hw, struct ice_sbq_msg_input *msg, u8 port, u16 offset) { - int phy_port, phy, quadtype; + int phy_port, quadtype; phy_port = port % hw->ptp.ports_per_phy; - phy = port / hw->ptp.ports_per_phy; quadtype = ICE_GET_QUAD_NUM(port) % ICE_GET_QUAD_NUM(hw->ptp.ports_per_phy); @@ -2753,12 +2777,7 @@ static void ice_fill_phy_msg_e82x(struct ice_hw *hw, msg->msg_addr_high = P_Q1_H(P_4_BASE + offset, phy_port); } - if (phy == 0) - msg->dest_dev = rmn_0; - else if (phy == 1) - msg->dest_dev = rmn_1; - else - msg->dest_dev = rmn_2; + msg->dest_dev = rmn_0; } /** @@ -4857,33 +4876,46 @@ static int ice_write_phy_reg_e810(struct ice_hw *hw, u32 addr, u32 val) static int ice_read_phy_tstamp_ll_e810(struct ice_hw *hw, u8 idx, u8 *hi, u32 *lo) { + struct ice_e810_params *params = &hw->ptp.phy.e810; + unsigned long flags; u32 val; - u8 i; + int err; + + spin_lock_irqsave(¶ms->atqbal_wq.lock, flags); + + /* Wait for any pending in-progress low latency interrupt */ + err = wait_event_interruptible_locked_irq(params->atqbal_wq, + !(params->atqbal_flags & + ATQBAL_FLAGS_INTR_IN_PROGRESS)); + if (err) { + spin_unlock_irqrestore(¶ms->atqbal_wq.lock, flags); + return err; + } /* Write TS index to read to the PF register so the FW can read it */ - val = FIELD_PREP(TS_LL_READ_TS_IDX, idx) | TS_LL_READ_TS; - wr32(hw, PF_SB_ATQBAL, val); + val = FIELD_PREP(REG_LL_PROXY_H_TS_IDX, idx) | REG_LL_PROXY_H_EXEC; + wr32(hw, REG_LL_PROXY_H, val); /* Read the register repeatedly until the FW provides us the TS */ - for (i = TS_LL_READ_RETRIES; i > 0; i--) { - val = rd32(hw, PF_SB_ATQBAL); + err = read_poll_timeout_atomic(rd32, val, + !FIELD_GET(REG_LL_PROXY_H_EXEC, val), 10, + REG_LL_PROXY_H_TIMEOUT_US, false, hw, + REG_LL_PROXY_H); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to read PTP timestamp using low latency read\n"); + spin_unlock_irqrestore(¶ms->atqbal_wq.lock, flags); + return err; + } - /* When the bit is cleared, the TS is ready in the register */ - if (!(FIELD_GET(TS_LL_READ_TS, val))) { - /* High 8 bit value of the TS is on the bits 16:23 */ - *hi = FIELD_GET(TS_LL_READ_TS_HIGH, val); + /* High 8 bit value of the TS is on the bits 16:23 */ + *hi = FIELD_GET(REG_LL_PROXY_H_TS_HIGH, val); - /* Read the low 32 bit value and set the TS valid bit */ - *lo = rd32(hw, PF_SB_ATQBAH) | TS_VALID; - return 0; - } + /* Read the low 32 bit value and set the TS valid bit */ + *lo = rd32(hw, REG_LL_PROXY_L) | TS_VALID; - udelay(10); - } + spin_unlock_irqrestore(¶ms->atqbal_wq.lock, flags); - /* FW failed to provide the TS in time */ - ice_debug(hw, ICE_DBG_PTP, "Failed to read PTP timestamp using low latency read\n"); - return -EINVAL; + return 0; } /** @@ -5066,6 +5098,55 @@ static int ice_ptp_prep_phy_time_e810(struct ice_hw *hw, u32 time) } /** + * ice_ptp_prep_phy_adj_ll_e810 - Prep PHY ports for a time adjustment + * @hw: pointer to HW struct + * @adj: adjustment value to program + * + * Use the low latency firmware interface to program PHY time adjustment to + * all PHY ports. + * + * Return: 0 on success, -EBUSY on timeout + */ +static int ice_ptp_prep_phy_adj_ll_e810(struct ice_hw *hw, s32 adj) +{ + const u8 tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; + struct ice_e810_params *params = &hw->ptp.phy.e810; + u32 val; + int err; + + spin_lock_irq(¶ms->atqbal_wq.lock); + + /* Wait for any pending in-progress low latency interrupt */ + err = wait_event_interruptible_locked_irq(params->atqbal_wq, + !(params->atqbal_flags & + ATQBAL_FLAGS_INTR_IN_PROGRESS)); + if (err) { + spin_unlock_irq(¶ms->atqbal_wq.lock); + return err; + } + + wr32(hw, REG_LL_PROXY_L, adj); + val = FIELD_PREP(REG_LL_PROXY_H_PHY_TMR_CMD_M, REG_LL_PROXY_H_PHY_TMR_CMD_ADJ) | + FIELD_PREP(REG_LL_PROXY_H_PHY_TMR_IDX_M, tmr_idx) | REG_LL_PROXY_H_EXEC; + wr32(hw, REG_LL_PROXY_H, val); + + /* Read the register repeatedly until the FW indicates completion */ + err = read_poll_timeout_atomic(rd32, val, + !FIELD_GET(REG_LL_PROXY_H_EXEC, val), + 10, REG_LL_PROXY_H_TIMEOUT_US, false, hw, + REG_LL_PROXY_H); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to prepare PHY timer adjustment using low latency interface\n"); + spin_unlock_irq(¶ms->atqbal_wq.lock); + return err; + } + + spin_unlock_irq(¶ms->atqbal_wq.lock); + + return 0; +} + +/** * ice_ptp_prep_phy_adj_e810 - Prep PHY port for a time adjustment * @hw: pointer to HW struct * @adj: adjustment value to program @@ -5083,6 +5164,9 @@ static int ice_ptp_prep_phy_adj_e810(struct ice_hw *hw, s32 adj) u8 tmr_idx; int err; + if (hw->dev_caps.ts_dev_info.ll_phy_tmr_update) + return ice_ptp_prep_phy_adj_ll_e810(hw, adj); + tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; /* Adjustments are represented as signed 2's complement values in @@ -5106,6 +5190,56 @@ static int ice_ptp_prep_phy_adj_e810(struct ice_hw *hw, s32 adj) } /** + * ice_ptp_prep_phy_incval_ll_e810 - Prep PHY ports increment value change + * @hw: pointer to HW struct + * @incval: The new 40bit increment value to prepare + * + * Use the low latency firmware interface to program PHY time increment value + * for all PHY ports. + * + * Return: 0 on success, -EBUSY on timeout + */ +static int ice_ptp_prep_phy_incval_ll_e810(struct ice_hw *hw, u64 incval) +{ + const u8 tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; + struct ice_e810_params *params = &hw->ptp.phy.e810; + u32 val; + int err; + + spin_lock_irq(¶ms->atqbal_wq.lock); + + /* Wait for any pending in-progress low latency interrupt */ + err = wait_event_interruptible_locked_irq(params->atqbal_wq, + !(params->atqbal_flags & + ATQBAL_FLAGS_INTR_IN_PROGRESS)); + if (err) { + spin_unlock_irq(¶ms->atqbal_wq.lock); + return err; + } + + wr32(hw, REG_LL_PROXY_L, lower_32_bits(incval)); + val = FIELD_PREP(REG_LL_PROXY_H_PHY_TMR_CMD_M, REG_LL_PROXY_H_PHY_TMR_CMD_FREQ) | + FIELD_PREP(REG_LL_PROXY_H_TS_HIGH, (u8)upper_32_bits(incval)) | + FIELD_PREP(REG_LL_PROXY_H_PHY_TMR_IDX_M, tmr_idx) | REG_LL_PROXY_H_EXEC; + wr32(hw, REG_LL_PROXY_H, val); + + /* Read the register repeatedly until the FW indicates completion */ + err = read_poll_timeout_atomic(rd32, val, + !FIELD_GET(REG_LL_PROXY_H_EXEC, val), + 10, REG_LL_PROXY_H_TIMEOUT_US, false, hw, + REG_LL_PROXY_H); + if (err) { + ice_debug(hw, ICE_DBG_PTP, "Failed to prepare PHY timer increment using low latency interface\n"); + spin_unlock_irq(¶ms->atqbal_wq.lock); + return err; + } + + spin_unlock_irq(¶ms->atqbal_wq.lock); + + return 0; +} + +/** * ice_ptp_prep_phy_incval_e810 - Prep PHY port increment value change * @hw: pointer to HW struct * @incval: The new 40bit increment value to prepare @@ -5120,6 +5254,9 @@ static int ice_ptp_prep_phy_incval_e810(struct ice_hw *hw, u64 incval) u8 tmr_idx; int err; + if (hw->dev_caps.ts_dev_info.ll_phy_tmr_update) + return ice_ptp_prep_phy_incval_ll_e810(hw, incval); + tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; low = lower_32_bits(incval); high = upper_32_bits(incval); @@ -5404,6 +5541,8 @@ static void ice_ptp_init_phy_e810(struct ice_ptp_hw *ptp) ptp->phy_model = ICE_PHY_E810; ptp->num_lports = 8; ptp->ports_per_phy = 4; + + init_waitqueue_head(&ptp->phy.e810.atqbal_wq); } /* Device agnostic functions @@ -5478,7 +5617,7 @@ void ice_ptp_init_hw(struct ice_hw *hw) else if (ice_is_e810(hw)) ice_ptp_init_phy_e810(ptp); else if (ice_is_e825c(hw)) - ice_ptp_init_phy_e825c(hw); + ice_ptp_init_phy_e825(hw); else ptp->phy_model = ICE_PHY_UNSUP; } diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h index 1cee0f1bba2d..6779ce120515 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h @@ -80,7 +80,6 @@ struct ice_phy_reg_info_eth56g { * struct ice_time_ref_info_e82x * @pll_freq: Frequency of PLL that drives timer ticks in Hz * @nominal_incval: increment to generate nanoseconds in GLTSYN_TIME_L - * @pps_delay: propagation delay of the PPS output signal * * Characteristic information for the various TIME_REF sources possible in the * E822 devices @@ -88,7 +87,6 @@ struct ice_phy_reg_info_eth56g { struct ice_time_ref_info_e82x { u64 pll_freq; u64 nominal_incval; - u8 pps_delay; }; /** @@ -326,8 +324,6 @@ extern const struct ice_vernier_info_e82x e822_vernier[NUM_ICE_PTP_LNK_SPD]; */ #define ICE_E810_PLL_FREQ 812500000 #define ICE_PTP_NOMINAL_INCVAL_E810 0x13b13b13bULL -#define ICE_E810_OUT_PROP_DELAY_NS 1 -#define ICE_E825C_OUT_PROP_DELAY_NS 11 /* Device agnostic functions */ u8 ice_get_ptp_src_clock_index(struct ice_hw *hw); @@ -389,11 +385,6 @@ static inline u64 ice_e82x_nominal_incval(enum ice_time_ref_freq time_ref) return e82x_time_ref[time_ref].nominal_incval; } -static inline u64 ice_e82x_pps_delay(enum ice_time_ref_freq time_ref) -{ - return e82x_time_ref[time_ref].pps_delay; -} - /* E822 Vernier calibration functions */ int ice_stop_phy_timer_e82x(struct ice_hw *hw, u8 port, bool soft_reset); int ice_start_phy_timer_e82x(struct ice_hw *hw, u8 port); @@ -432,20 +423,6 @@ int ice_phy_cfg_ptp_1step_eth56g(struct ice_hw *hw, u8 port); #define ICE_ETH56G_NOMINAL_THRESH4 0x7777 #define ICE_ETH56G_NOMINAL_TX_THRESH 0x6 -static inline u64 ice_prop_delay(const struct ice_hw *hw) -{ - switch (hw->ptp.phy_model) { - case ICE_PHY_ETH56G: - return ICE_E825C_OUT_PROP_DELAY_NS; - case ICE_PHY_E810: - return ICE_E810_OUT_PROP_DELAY_NS; - case ICE_PHY_E82X: - return ice_e82x_pps_delay(ice_e82x_time_ref(hw)); - default: - return 0; - } -} - /** * ice_get_base_incval - Get base clock increment value * @hw: pointer to the HW struct @@ -689,11 +666,18 @@ static inline bool ice_is_dual(struct ice_hw *hw) #define BYTES_PER_IDX_ADDR_L 4 /* Tx timestamp low latency read definitions */ -#define TS_LL_READ_RETRIES 200 -#define TS_LL_READ_TS_HIGH GENMASK(23, 16) -#define TS_LL_READ_TS_IDX GENMASK(29, 24) -#define TS_LL_READ_TS_INTR BIT(30) -#define TS_LL_READ_TS BIT(31) +#define REG_LL_PROXY_H_TIMEOUT_US 2000 +#define REG_LL_PROXY_H_PHY_TMR_CMD_M GENMASK(7, 6) +#define REG_LL_PROXY_H_PHY_TMR_CMD_ADJ 0x1 +#define REG_LL_PROXY_H_PHY_TMR_CMD_FREQ 0x2 +#define REG_LL_PROXY_H_TS_HIGH GENMASK(23, 16) +#define REG_LL_PROXY_H_PHY_TMR_IDX_M BIT(24) +#define REG_LL_PROXY_H_TS_IDX GENMASK(29, 24) +#define REG_LL_PROXY_H_TS_INTR_ENA BIT(30) +#define REG_LL_PROXY_H_EXEC BIT(31) + +#define REG_LL_PROXY_L PF_SB_ATQBAH +#define REG_LL_PROXY_H PF_SB_ATQBAL /* Internal PHY timestamp address */ #define TS_L(a, idx) ((a) + ((idx) * BYTES_PER_IDX_ADDR_L_U)) diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index 0e740342e294..4a91e0aaf0a5 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -4784,7 +4784,8 @@ ice_find_recp(struct ice_hw *hw, struct ice_prot_lkup_ext *lkup_exts, */ if (found && recp[i].tun_type == rinfo->tun_type && recp[i].need_pass_l2 == rinfo->need_pass_l2 && - recp[i].allow_pass_l2 == rinfo->allow_pass_l2) + recp[i].allow_pass_l2 == rinfo->allow_pass_l2 && + recp[i].priority == rinfo->priority) return i; /* Return the recipe ID */ } } diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index adb168860711..33a1a5934c0d 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -18,6 +18,7 @@ #include "ice_sbq_cmd.h" #include "ice_vlan_mode.h" #include "ice_fwlog.h" +#include <linux/wait.h> static inline bool ice_is_tc_ena(unsigned long bitmap, u8 tc) { @@ -368,6 +369,7 @@ struct ice_ts_func_info { #define ICE_TS_TMR1_ENA_M BIT(26) #define ICE_TS_LL_TX_TS_READ_M BIT(28) #define ICE_TS_LL_TX_TS_INT_READ_M BIT(29) +#define ICE_TS_LL_PHY_TMR_UPDATE_M BIT(30) struct ice_ts_dev_info { /* Device specific info */ @@ -382,6 +384,7 @@ struct ice_ts_dev_info { u8 tmr1_ena; u8 ts_ll_read; u8 ts_ll_int_read; + u8 ll_phy_tmr_update; }; #define ICE_NAC_TOPO_PRIMARY_M BIT(0) @@ -848,15 +851,23 @@ struct ice_mbx_data { #define ICE_PORTS_PER_QUAD 4 #define ICE_GET_QUAD_NUM(port) ((port) / ICE_PORTS_PER_QUAD) +#define ATQBAL_FLAGS_INTR_IN_PROGRESS BIT(0) + +struct ice_e810_params { + /* The wait queue lock also protects the low latency interface */ + wait_queue_head_t atqbal_wq; + unsigned int atqbal_flags; +}; + struct ice_eth56g_params { u8 num_phys; - u8 phy_addr[2]; bool onestep_ena; bool sfd_ena; u32 peer_delay; }; union ice_phy_params { + struct ice_e810_params e810; struct ice_eth56g_params eth56g; }; @@ -881,7 +892,6 @@ struct ice_ptp_hw { union ice_phy_params phy; u8 num_lports; u8 ports_per_phy; - bool is_2x50g_muxed_topo; }; /* Port hardware description */ @@ -1216,4 +1226,9 @@ struct ice_aq_get_set_rss_lut_params { #define ICE_FW_API_REPORT_DFLT_CFG_MIN 7 #define ICE_FW_API_REPORT_DFLT_CFG_PATCH 3 +/* AQ API version for Health Status support */ +#define ICE_FW_API_HEALTH_REPORT_MAJ 1 +#define ICE_FW_API_HEALTH_REPORT_MIN 7 +#define ICE_FW_API_HEALTH_REPORT_PATCH 6 + #endif /* _ICE_TYPE_H_ */ diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index fe6261b81540..82f4333fb426 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -284,8 +284,12 @@ MVNETA_TXQ_BUCKET_REFILL_PERIOD)) #define MVNETA_LPI_CTRL_0 0x2cc0 +#define MVNETA_LPI_CTRL_0_TS (0xff << 8) #define MVNETA_LPI_CTRL_1 0x2cc4 -#define MVNETA_LPI_REQUEST_ENABLE BIT(0) +#define MVNETA_LPI_CTRL_1_REQUEST_ENABLE BIT(0) +#define MVNETA_LPI_CTRL_1_REQUEST_FORCE BIT(1) +#define MVNETA_LPI_CTRL_1_MANUAL_MODE BIT(2) +#define MVNETA_LPI_CTRL_1_TW (0xfff << 4) #define MVNETA_LPI_CTRL_2 0x2cc8 #define MVNETA_LPI_STATUS 0x2ccc @@ -541,10 +545,6 @@ struct mvneta_port { struct mvneta_bm_pool *pool_short; int bm_win_id; - bool eee_enabled; - bool eee_active; - bool tx_lpi_enabled; - u64 ethtool_stats[ARRAY_SIZE(mvneta_statistics)]; u32 indir[MVNETA_RSS_LU_TABLE_SIZE]; @@ -3983,7 +3983,7 @@ static unsigned int mvneta_pcs_inband_caps(struct phylink_pcs *pcs, return LINK_INBAND_DISABLE; } -static void mvneta_pcs_get_state(struct phylink_pcs *pcs, +static void mvneta_pcs_get_state(struct phylink_pcs *pcs, unsigned int neg_mode, struct phylink_link_state *state) { struct mvneta_port *pp = mvneta_pcs_to_port(pcs); @@ -4213,18 +4213,6 @@ static int mvneta_mac_finish(struct phylink_config *config, unsigned int mode, return 0; } -static void mvneta_set_eee(struct mvneta_port *pp, bool enable) -{ - u32 lpi_ctl1; - - lpi_ctl1 = mvreg_read(pp, MVNETA_LPI_CTRL_1); - if (enable) - lpi_ctl1 |= MVNETA_LPI_REQUEST_ENABLE; - else - lpi_ctl1 &= ~MVNETA_LPI_REQUEST_ENABLE; - mvreg_write(pp, MVNETA_LPI_CTRL_1, lpi_ctl1); -} - static void mvneta_mac_link_down(struct phylink_config *config, unsigned int mode, phy_interface_t interface) { @@ -4240,9 +4228,6 @@ static void mvneta_mac_link_down(struct phylink_config *config, val |= MVNETA_GMAC_FORCE_LINK_DOWN; mvreg_write(pp, MVNETA_GMAC_AUTONEG_CONFIG, val); } - - pp->eee_active = false; - mvneta_set_eee(pp, false); } static void mvneta_mac_link_up(struct phylink_config *config, @@ -4291,11 +4276,56 @@ static void mvneta_mac_link_up(struct phylink_config *config, } mvneta_port_up(pp); +} - if (phy && pp->eee_enabled) { - pp->eee_active = phy_init_eee(phy, false) >= 0; - mvneta_set_eee(pp, pp->eee_active && pp->tx_lpi_enabled); +static void mvneta_mac_disable_tx_lpi(struct phylink_config *config) +{ + struct mvneta_port *pp = netdev_priv(to_net_dev(config->dev)); + u32 lpi1; + + lpi1 = mvreg_read(pp, MVNETA_LPI_CTRL_1); + lpi1 &= ~(MVNETA_LPI_CTRL_1_REQUEST_ENABLE | + MVNETA_LPI_CTRL_1_REQUEST_FORCE | + MVNETA_LPI_CTRL_1_MANUAL_MODE); + mvreg_write(pp, MVNETA_LPI_CTRL_1, lpi1); +} + +static int mvneta_mac_enable_tx_lpi(struct phylink_config *config, u32 timer, + bool tx_clk_stop) +{ + struct mvneta_port *pp = netdev_priv(to_net_dev(config->dev)); + u32 ts, tw, lpi0, lpi1, status; + + status = mvreg_read(pp, MVNETA_GMAC_STATUS); + if (status & MVNETA_GMAC_SPEED_1000) { + /* At 1G speeds, the timer resolution are 1us, and + * 802.3 says tw is 16.5us. Round up to 17us. + */ + tw = 17; + ts = timer; + } else { + /* At 100M speeds, the timer resolutions are 10us, and + * 802.3 says tw is 30us. + */ + tw = 3; + ts = DIV_ROUND_UP(timer, 10); } + + if (ts > 255) + ts = 255; + + /* Configure ts */ + lpi0 = mvreg_read(pp, MVNETA_LPI_CTRL_0); + lpi0 = u32_replace_bits(lpi0, ts, MVNETA_LPI_CTRL_0_TS); + mvreg_write(pp, MVNETA_LPI_CTRL_0, lpi0); + + /* Configure tw and enable LPI generation */ + lpi1 = mvreg_read(pp, MVNETA_LPI_CTRL_1); + lpi1 = u32_replace_bits(lpi1, tw, MVNETA_LPI_CTRL_1_TW); + lpi1 |= MVNETA_LPI_CTRL_1_REQUEST_ENABLE; + mvreg_write(pp, MVNETA_LPI_CTRL_1, lpi1); + + return 0; } static const struct phylink_mac_ops mvneta_phylink_ops = { @@ -4305,6 +4335,8 @@ static const struct phylink_mac_ops mvneta_phylink_ops = { .mac_finish = mvneta_mac_finish, .mac_link_down = mvneta_mac_link_down, .mac_link_up = mvneta_mac_link_up, + .mac_disable_tx_lpi = mvneta_mac_disable_tx_lpi, + .mac_enable_tx_lpi = mvneta_mac_enable_tx_lpi, }; static int mvneta_mdio_probe(struct mvneta_port *pp) @@ -4392,6 +4424,7 @@ static int mvneta_cpu_online(unsigned int cpu, struct hlist_node *node) if (pp->neta_armada3700) return 0; + netdev_lock(port->napi.dev); spin_lock(&pp->lock); /* * Configuring the driver for a new CPU while the driver is @@ -4418,7 +4451,7 @@ static int mvneta_cpu_online(unsigned int cpu, struct hlist_node *node) /* Mask all ethernet port interrupts */ on_each_cpu(mvneta_percpu_mask_interrupt, pp, true); - napi_enable(&port->napi); + napi_enable_locked(&port->napi); /* * Enable per-CPU interrupts on the CPU that is @@ -4439,6 +4472,8 @@ static int mvneta_cpu_online(unsigned int cpu, struct hlist_node *node) MVNETA_CAUSE_LINK_CHANGE); netif_tx_start_all_queues(pp->dev); spin_unlock(&pp->lock); + netdev_unlock(port->napi.dev); + return 0; } @@ -5106,14 +5141,6 @@ static int mvneta_ethtool_get_eee(struct net_device *dev, struct ethtool_keee *eee) { struct mvneta_port *pp = netdev_priv(dev); - u32 lpi_ctl0; - - lpi_ctl0 = mvreg_read(pp, MVNETA_LPI_CTRL_0); - - eee->eee_enabled = pp->eee_enabled; - eee->eee_active = pp->eee_active; - eee->tx_lpi_enabled = pp->tx_lpi_enabled; - eee->tx_lpi_timer = (lpi_ctl0) >> 8; // * scale; return phylink_ethtool_get_eee(pp->phylink, eee); } @@ -5122,7 +5149,6 @@ static int mvneta_ethtool_set_eee(struct net_device *dev, struct ethtool_keee *eee) { struct mvneta_port *pp = netdev_priv(dev); - u32 lpi_ctl0; /* The Armada 37x documents do not give limits for this other than * it being an 8-bit register. @@ -5130,16 +5156,6 @@ static int mvneta_ethtool_set_eee(struct net_device *dev, if (eee->tx_lpi_enabled && eee->tx_lpi_timer > 255) return -EINVAL; - lpi_ctl0 = mvreg_read(pp, MVNETA_LPI_CTRL_0); - lpi_ctl0 &= ~(0xff << 8); - lpi_ctl0 |= eee->tx_lpi_timer << 8; - mvreg_write(pp, MVNETA_LPI_CTRL_0, lpi_ctl0); - - pp->eee_enabled = eee->eee_enabled; - pp->tx_lpi_enabled = eee->tx_lpi_enabled; - - mvneta_set_eee(pp, eee->tx_lpi_enabled && eee->eee_enabled); - return phylink_ethtool_set_eee(pp->phylink, eee); } @@ -5453,6 +5469,9 @@ static int mvneta_port_power_up(struct mvneta_port *pp, int phy_mode) !phy_interface_mode_is_rgmii(phy_mode)) return -EINVAL; + /* Ensure LPI is disabled */ + mvneta_mac_disable_tx_lpi(&pp->phylink_config); + return 0; } @@ -5544,6 +5563,13 @@ static int mvneta_probe(struct platform_device *pdev) pp->phylink_config.mac_capabilities = MAC_SYM_PAUSE | MAC_10 | MAC_100 | MAC_1000FD | MAC_2500FD; + /* Setup EEE. Choose 250us idle. Only supported in SGMII modes. */ + __set_bit(PHY_INTERFACE_MODE_QSGMII, pp->phylink_config.lpi_interfaces); + __set_bit(PHY_INTERFACE_MODE_SGMII, pp->phylink_config.lpi_interfaces); + pp->phylink_config.lpi_capabilities = MAC_100FD | MAC_1000FD; + pp->phylink_config.lpi_timer_default = 250; + pp->phylink_config.eee_enabled_default = true; + phy_interface_set_rgmii(pp->phylink_config.supported_interfaces); __set_bit(PHY_INTERFACE_MODE_QSGMII, pp->phylink_config.supported_interfaces); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h index 9e02e4367bec..44fe9b68d1c2 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h @@ -481,6 +481,11 @@ #define MVPP22_GMAC_INT_SUM_MASK 0xa4 #define MVPP22_GMAC_INT_SUM_MASK_LINK_STAT BIT(1) #define MVPP22_GMAC_INT_SUM_MASK_PTP BIT(2) +#define MVPP2_GMAC_LPI_CTRL0 0xc0 +#define MVPP2_GMAC_LPI_CTRL0_TS_MASK GENMASK(15, 8) +#define MVPP2_GMAC_LPI_CTRL1 0xc4 +#define MVPP2_GMAC_LPI_CTRL1_REQ_EN BIT(0) +#define MVPP2_GMAC_LPI_CTRL1_TW_MASK GENMASK(15, 4) /* Per-port XGMAC registers. PPv2.2 and PPv2.3, only for GOP port 0, * relative to port->base. diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index f85229a30844..dd76c1b7ed3a 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -5757,6 +5757,28 @@ static int mvpp2_ethtool_set_rxfh(struct net_device *dev, return mvpp2_modify_rxfh_context(dev, NULL, rxfh, extack); } +static int mvpp2_ethtool_get_eee(struct net_device *dev, + struct ethtool_keee *eee) +{ + struct mvpp2_port *port = netdev_priv(dev); + + if (!port->phylink) + return -EOPNOTSUPP; + + return phylink_ethtool_get_eee(port->phylink, eee); +} + +static int mvpp2_ethtool_set_eee(struct net_device *dev, + struct ethtool_keee *eee) +{ + struct mvpp2_port *port = netdev_priv(dev); + + if (!port->phylink) + return -EOPNOTSUPP; + + return phylink_ethtool_set_eee(port->phylink, eee); +} + /* Device ops */ static const struct net_device_ops mvpp2_netdev_ops = { @@ -5802,6 +5824,8 @@ static const struct ethtool_ops mvpp2_eth_tool_ops = { .create_rxfh_context = mvpp2_create_rxfh_context, .modify_rxfh_context = mvpp2_modify_rxfh_context, .remove_rxfh_context = mvpp2_remove_rxfh_context, + .get_eee = mvpp2_ethtool_get_eee, + .set_eee = mvpp2_ethtool_set_eee, }; /* Used for PPv2.1, or PPv2.2 with the old Device Tree binding that @@ -6188,6 +6212,7 @@ static struct mvpp2_port *mvpp2_pcs_gmac_to_port(struct phylink_pcs *pcs) } static void mvpp2_xlg_pcs_get_state(struct phylink_pcs *pcs, + unsigned int neg_mode, struct phylink_link_state *state) { struct mvpp2_port *port = mvpp2_pcs_xlg_to_port(pcs); @@ -6247,6 +6272,7 @@ static unsigned int mvpp2_gmac_pcs_inband_caps(struct phylink_pcs *pcs, } static void mvpp2_gmac_pcs_get_state(struct phylink_pcs *pcs, + unsigned int neg_mode, struct phylink_link_state *state) { struct mvpp2_port *port = mvpp2_pcs_gmac_to_port(pcs); @@ -6672,6 +6698,55 @@ static void mvpp2_mac_link_down(struct phylink_config *config, mvpp2_port_disable(port); } +static void mvpp2_mac_disable_tx_lpi(struct phylink_config *config) +{ + struct mvpp2_port *port = mvpp2_phylink_to_port(config); + + mvpp2_modify(port->base + MVPP2_GMAC_LPI_CTRL1, + MVPP2_GMAC_LPI_CTRL1_REQ_EN, 0); +} + +static int mvpp2_mac_enable_tx_lpi(struct phylink_config *config, u32 timer, + bool tx_clk_stop) +{ + struct mvpp2_port *port = mvpp2_phylink_to_port(config); + u32 ts, tw, lpi1, status; + + status = readl(port->base + MVPP2_GMAC_STATUS0); + if (status & MVPP2_GMAC_STATUS0_GMII_SPEED) { + /* At 1G speeds, the timer resolution are 1us, and + * 802.3 says tw is 16.5us. Round up to 17us. + */ + tw = 17; + ts = timer; + } else { + /* At 100M speeds, the timer resolutions are 10us, and + * 802.3 says tw is 30us. + */ + tw = 3; + ts = DIV_ROUND_UP(timer, 10); + } + + if (ts > 255) + ts = 255; + + /* Configure ts */ + mvpp2_modify(port->base + MVPP2_GMAC_LPI_CTRL0, + MVPP2_GMAC_LPI_CTRL0_TS_MASK, + FIELD_PREP(MVPP2_GMAC_LPI_CTRL0_TS_MASK, ts)); + + lpi1 = readl(port->base + MVPP2_GMAC_LPI_CTRL1); + + /* Configure tw */ + lpi1 = u32_replace_bits(lpi1, tw, MVPP2_GMAC_LPI_CTRL1_TW_MASK); + + /* Enable LPI generation */ + writel(lpi1 | MVPP2_GMAC_LPI_CTRL1_REQ_EN, + port->base + MVPP2_GMAC_LPI_CTRL1); + + return 0; +} + static const struct phylink_mac_ops mvpp2_phylink_ops = { .mac_select_pcs = mvpp2_select_pcs, .mac_prepare = mvpp2_mac_prepare, @@ -6679,6 +6754,8 @@ static const struct phylink_mac_ops mvpp2_phylink_ops = { .mac_finish = mvpp2_mac_finish, .mac_link_up = mvpp2_mac_link_up, .mac_link_down = mvpp2_mac_link_down, + .mac_enable_tx_lpi = mvpp2_mac_enable_tx_lpi, + .mac_disable_tx_lpi = mvpp2_mac_disable_tx_lpi, }; /* Work-around for ACPI */ @@ -6957,6 +7034,15 @@ static int mvpp2_port_probe(struct platform_device *pdev, port->phylink_config.mac_capabilities = MAC_2500FD | MAC_1000FD | MAC_100 | MAC_10; + __set_bit(PHY_INTERFACE_MODE_SGMII, + port->phylink_config.lpi_interfaces); + + port->phylink_config.lpi_capabilities = MAC_1000FD | MAC_100FD; + + /* Setup EEE. Choose 250us idle. */ + port->phylink_config.lpi_timer_default = 250; + port->phylink_config.eee_enabled_default = true; + if (port->priv->global_tx_fc) port->phylink_config.mac_capabilities |= MAC_SYM_PAUSE | MAC_ASYM_PAUSE; @@ -7031,6 +7117,8 @@ static int mvpp2_port_probe(struct platform_device *pdev, goto err_free_port_pcpu; } port->phylink = phylink; + + mvpp2_mac_disable_tx_lpi(&port->phylink_config); } else { dev_warn(&pdev->dev, "Use link irqs for port#%d. FW update required\n", port->id); port->phylink = NULL; diff --git a/drivers/net/ethernet/marvell/prestera/prestera_main.c b/drivers/net/ethernet/marvell/prestera/prestera_main.c index 22ca6ee9665e..440a4c42b405 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_main.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_main.c @@ -280,6 +280,7 @@ prestera_mac_select_pcs(struct phylink_config *config, } static void prestera_pcs_get_state(struct phylink_pcs *pcs, + unsigned int neg_mode, struct phylink_link_state *state) { struct prestera_port *port = container_of(pcs, struct prestera_port, diff --git a/drivers/net/ethernet/mediatek/airoha_eth.c b/drivers/net/ethernet/mediatek/airoha_eth.c index b9f1c42f0a40..415d784de741 100644 --- a/drivers/net/ethernet/mediatek/airoha_eth.c +++ b/drivers/net/ethernet/mediatek/airoha_eth.c @@ -2793,7 +2793,7 @@ static int airoha_qdma_set_tx_ets_sched(struct airoha_gdm_port *port, struct tc_ets_qopt_offload_replace_params *p = &opt->replace_params; enum tx_sched_mode mode = TC_SCH_SP; u16 w[AIROHA_NUM_QOS_QUEUES] = {}; - int i, nstrict = 0; + int i, nstrict = 0, nwrr, qidx; if (p->bands > AIROHA_NUM_QOS_QUEUES) return -EINVAL; @@ -2807,7 +2807,20 @@ static int airoha_qdma_set_tx_ets_sched(struct airoha_gdm_port *port, if (nstrict == AIROHA_NUM_QOS_QUEUES - 1) return -EINVAL; - for (i = 0; i < p->bands - nstrict; i++) + /* EN7581 SoC supports fixed QoS band priority where WRR queues have + * lowest priorities with respect to SP ones. + * e.g: WRR0, WRR1, .., WRRm, SP0, SP1, .., SPn + */ + nwrr = p->bands - nstrict; + qidx = nstrict && nwrr ? nstrict : 0; + for (i = 1; i <= p->bands; i++) { + if (p->priomap[i % AIROHA_NUM_QOS_QUEUES] != qidx) + return -EINVAL; + + qidx = i == nwrr ? 0 : qidx + 1; + } + + for (i = 0; i < nwrr; i++) w[i] = p->weights[nstrict + i]; if (!nstrict) @@ -2840,11 +2853,14 @@ static int airoha_qdma_get_tx_ets_stats(struct airoha_gdm_port *port, static int airoha_tc_setup_qdisc_ets(struct airoha_gdm_port *port, struct tc_ets_qopt_offload *opt) { - int channel = TC_H_MAJ(opt->handle) >> 16; + int channel; if (opt->parent == TC_H_ROOT) return -EINVAL; + channel = TC_H_MAJ(opt->handle) >> 16; + channel = channel % AIROHA_NUM_QOS_CHANNELS; + switch (opt->command) { case TC_ETS_REPLACE: return airoha_qdma_set_tx_ets_sched(port, channel, opt); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index 10a763e668ed..568bbe5f83f5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -60,6 +60,7 @@ mlx5_core-$(CONFIG_MLX5_CLS_ACT) += en/tc/act/act.o en/tc/act/drop.o en/tc/a ifneq ($(CONFIG_MLX5_TC_CT),) mlx5_core-y += en/tc_ct.o en/tc/ct_fs_dmfs.o mlx5_core-$(CONFIG_MLX5_SW_STEERING) += en/tc/ct_fs_smfs.o + mlx5_core-$(CONFIG_MLX5_HW_STEERING) += en/tc/ct_fs_hmfs.o endif mlx5_core-$(CONFIG_MLX5_TC_SAMPLE) += en/tc/sample.o @@ -151,8 +152,9 @@ mlx5_core-$(CONFIG_MLX5_HW_STEERING) += steering/hws/cmd.o \ steering/hws/bwc.o \ steering/hws/debug.o \ steering/hws/vport.o \ - steering/hws/bwc_complex.o - + steering/hws/bwc_complex.o \ + steering/hws/fs_hws_pools.o \ + steering/hws/fs_hws.o # # SF device diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs.h index 62b3f7ff5562..e5b30801314b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs.h @@ -48,4 +48,14 @@ mlx5_ct_fs_smfs_ops_get(void) } #endif /* IS_ENABLED(CONFIG_MLX5_SW_STEERING) */ +#if IS_ENABLED(CONFIG_MLX5_HW_STEERING) +struct mlx5_ct_fs_ops *mlx5_ct_fs_hmfs_ops_get(void); +#else +static inline struct mlx5_ct_fs_ops * +mlx5_ct_fs_hmfs_ops_get(void) +{ + return NULL; +} +#endif /* IS_ENABLED(CONFIG_MLX5_SW_STEERING) */ + #endif /* __MLX5_EN_TC_CT_FS_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_hmfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_hmfs.c new file mode 100644 index 000000000000..a4263137fef5 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_hmfs.c @@ -0,0 +1,292 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2025, NVIDIA CORPORATION & AFFILIATES. */ + +#include "en_tc.h" +#include "en/tc_ct.h" +#include "en/tc_priv.h" +#include "en/tc/ct_fs.h" +#include "fs_core.h" +#include "steering/hws/fs_hws_pools.h" +#include "steering/hws/mlx5hws.h" +#include "steering/hws/table.h" + +struct mlx5_ct_fs_hmfs_matcher { + struct mlx5hws_bwc_matcher *hws_bwc_matcher; + refcount_t ref; +}; + +/* We need {ipv4, ipv6} x {tcp, udp, gre} matchers. */ +#define NUM_MATCHERS (2 * 3) + +struct mlx5_ct_fs_hmfs { + struct mlx5hws_table *ct_tbl; + struct mlx5hws_table *ct_nat_tbl; + struct mlx5_flow_table *ct_nat; + struct mlx5hws_action *fwd_action; + struct mlx5hws_action *last_action; + struct mlx5hws_context *ctx; + struct mutex lock; /* Guards matchers */ + struct mlx5_ct_fs_hmfs_matcher matchers[NUM_MATCHERS]; + struct mlx5_ct_fs_hmfs_matcher matchers_nat[NUM_MATCHERS]; +}; + +struct mlx5_ct_fs_hmfs_rule { + struct mlx5_ct_fs_rule fs_rule; + struct mlx5hws_bwc_rule *hws_bwc_rule; + struct mlx5_ct_fs_hmfs_matcher *hmfs_matcher; + struct mlx5_fc *counter; +}; + +static u32 get_matcher_idx(bool ipv4, bool tcp, bool gre) +{ + return ipv4 * 3 + tcp * 2 + gre; +} + +static int mlx5_ct_fs_hmfs_init(struct mlx5_ct_fs *fs, struct mlx5_flow_table *ct, + struct mlx5_flow_table *ct_nat, struct mlx5_flow_table *post_ct) +{ + u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED; + struct mlx5hws_table *ct_tbl, *ct_nat_tbl, *post_ct_tbl; + struct mlx5_ct_fs_hmfs *fs_hmfs = mlx5_ct_fs_priv(fs); + + ct_tbl = ct->fs_hws_table.hws_table; + ct_nat_tbl = ct_nat->fs_hws_table.hws_table; + post_ct_tbl = post_ct->fs_hws_table.hws_table; + fs_hmfs->ct_nat = ct_nat; + + if (!ct_tbl || !ct_nat_tbl || !post_ct_tbl) { + netdev_warn(fs->netdev, "ct_fs_hmfs: failed to init, missing backing hws tables"); + return -EOPNOTSUPP; + } + + netdev_dbg(fs->netdev, "using hmfs steering"); + + fs_hmfs->ct_tbl = ct_tbl; + fs_hmfs->ct_nat_tbl = ct_nat_tbl; + fs_hmfs->ctx = ct_tbl->ctx; + mutex_init(&fs_hmfs->lock); + + fs_hmfs->fwd_action = mlx5hws_action_create_dest_table(ct_tbl->ctx, post_ct_tbl, flags); + if (!fs_hmfs->fwd_action) { + netdev_warn(fs->netdev, "ct_fs_hmfs: failed to create fwd action\n"); + return -EINVAL; + } + fs_hmfs->last_action = mlx5hws_action_create_last(ct_tbl->ctx, flags); + if (!fs_hmfs->last_action) { + netdev_warn(fs->netdev, "ct_fs_hmfs: failed to create last action\n"); + mlx5hws_action_destroy(fs_hmfs->fwd_action); + return -EINVAL; + } + + return 0; +} + +static void mlx5_ct_fs_hmfs_destroy(struct mlx5_ct_fs *fs) +{ + struct mlx5_ct_fs_hmfs *fs_hmfs = mlx5_ct_fs_priv(fs); + + mlx5hws_action_destroy(fs_hmfs->last_action); + mlx5hws_action_destroy(fs_hmfs->fwd_action); +} + +static struct mlx5hws_bwc_matcher * +mlx5_ct_fs_hmfs_matcher_create(struct mlx5_ct_fs *fs, struct mlx5hws_table *tbl, + struct mlx5_flow_spec *spec, bool ipv4, bool tcp, bool gre) +{ + u8 match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2 | MLX5_MATCH_OUTER_HEADERS; + struct mlx5hws_match_parameters mask = { + .match_buf = spec->match_criteria, + .match_sz = sizeof(spec->match_criteria), + }; + u32 priority = get_matcher_idx(ipv4, tcp, gre); /* Static priority based on params. */ + struct mlx5hws_bwc_matcher *hws_bwc_matcher; + + hws_bwc_matcher = mlx5hws_bwc_matcher_create(tbl, priority, match_criteria_enable, &mask); + if (!hws_bwc_matcher) + return ERR_PTR(-EINVAL); + + return hws_bwc_matcher; +} + +static struct mlx5_ct_fs_hmfs_matcher * +mlx5_ct_fs_hmfs_matcher_get(struct mlx5_ct_fs *fs, struct mlx5_flow_spec *spec, + bool nat, bool ipv4, bool tcp, bool gre) +{ + struct mlx5_ct_fs_hmfs *fs_hmfs = mlx5_ct_fs_priv(fs); + u32 matcher_idx = get_matcher_idx(ipv4, tcp, gre); + struct mlx5_ct_fs_hmfs_matcher *hmfs_matcher; + struct mlx5hws_bwc_matcher *hws_bwc_matcher; + struct mlx5hws_table *tbl; + + hmfs_matcher = nat ? + (fs_hmfs->matchers_nat + matcher_idx) : + (fs_hmfs->matchers + matcher_idx); + + if (refcount_inc_not_zero(&hmfs_matcher->ref)) + return hmfs_matcher; + + mutex_lock(&fs_hmfs->lock); + + /* Retry with lock, as the matcher might be already created by another cpu. */ + if (refcount_inc_not_zero(&hmfs_matcher->ref)) + goto out_unlock; + + tbl = nat ? fs_hmfs->ct_nat_tbl : fs_hmfs->ct_tbl; + + hws_bwc_matcher = mlx5_ct_fs_hmfs_matcher_create(fs, tbl, spec, ipv4, tcp, gre); + if (IS_ERR(hws_bwc_matcher)) { + netdev_warn(fs->netdev, + "ct_fs_hmfs: failed to create bwc matcher (nat %d, ipv4 %d, tcp %d, gre %d), err: %ld\n", + nat, ipv4, tcp, gre, PTR_ERR(hws_bwc_matcher)); + + hmfs_matcher = ERR_CAST(hws_bwc_matcher); + goto out_unlock; + } + + hmfs_matcher->hws_bwc_matcher = hws_bwc_matcher; + refcount_set(&hmfs_matcher->ref, 1); + +out_unlock: + mutex_unlock(&fs_hmfs->lock); + return hmfs_matcher; +} + +static void +mlx5_ct_fs_hmfs_matcher_put(struct mlx5_ct_fs *fs, struct mlx5_ct_fs_hmfs_matcher *hmfs_matcher) +{ + struct mlx5_ct_fs_hmfs *fs_hmfs = mlx5_ct_fs_priv(fs); + + if (!refcount_dec_and_mutex_lock(&hmfs_matcher->ref, &fs_hmfs->lock)) + return; + + mlx5hws_bwc_matcher_destroy(hmfs_matcher->hws_bwc_matcher); + mutex_unlock(&fs_hmfs->lock); +} + +#define NUM_CT_HMFS_RULES 4 + +static void mlx5_ct_fs_hmfs_fill_rule_actions(struct mlx5_ct_fs_hmfs *fs_hmfs, + struct mlx5_flow_attr *attr, + struct mlx5hws_rule_action *rule_actions) +{ + struct mlx5_fs_hws_action *mh_action = &attr->modify_hdr->fs_hws_action; + + memset(rule_actions, 0, NUM_CT_HMFS_RULES * sizeof(*rule_actions)); + rule_actions[0].action = mlx5_fc_get_hws_action(fs_hmfs->ctx, attr->counter); + /* Modify header is special, it may require extra arguments outside the action itself. */ + if (mh_action->mh_data) { + rule_actions[1].modify_header.offset = mh_action->mh_data->offset; + rule_actions[1].modify_header.data = mh_action->mh_data->data; + } + rule_actions[1].action = mh_action->hws_action; + rule_actions[2].action = fs_hmfs->fwd_action; + rule_actions[3].action = fs_hmfs->last_action; +} + +static struct mlx5_ct_fs_rule * +mlx5_ct_fs_hmfs_ct_rule_add(struct mlx5_ct_fs *fs, struct mlx5_flow_spec *spec, + struct mlx5_flow_attr *attr, struct flow_rule *flow_rule) +{ + struct mlx5hws_rule_action rule_actions[NUM_CT_HMFS_RULES]; + struct mlx5_ct_fs_hmfs *fs_hmfs = mlx5_ct_fs_priv(fs); + struct mlx5hws_match_parameters match_params = { + .match_buf = spec->match_value, + .match_sz = ARRAY_SIZE(spec->match_value), + }; + struct mlx5_ct_fs_hmfs_matcher *hmfs_matcher; + struct mlx5_ct_fs_hmfs_rule *hmfs_rule; + bool nat, tcp, ipv4, gre; + int err; + + if (!mlx5e_tc_ct_is_valid_flow_rule(fs->netdev, flow_rule)) + return ERR_PTR(-EOPNOTSUPP); + + hmfs_rule = kzalloc(sizeof(*hmfs_rule), GFP_KERNEL); + if (!hmfs_rule) + return ERR_PTR(-ENOMEM); + + nat = (attr->ft == fs_hmfs->ct_nat); + ipv4 = mlx5e_tc_get_ip_version(spec, true) == 4; + tcp = MLX5_GET(fte_match_param, spec->match_value, + outer_headers.ip_protocol) == IPPROTO_TCP; + gre = MLX5_GET(fte_match_param, spec->match_value, + outer_headers.ip_protocol) == IPPROTO_GRE; + + hmfs_matcher = mlx5_ct_fs_hmfs_matcher_get(fs, spec, nat, ipv4, tcp, gre); + if (IS_ERR(hmfs_matcher)) { + err = PTR_ERR(hmfs_matcher); + goto err_free_rule; + } + hmfs_rule->hmfs_matcher = hmfs_matcher; + + mlx5_ct_fs_hmfs_fill_rule_actions(fs_hmfs, attr, rule_actions); + hmfs_rule->counter = attr->counter; + + hmfs_rule->hws_bwc_rule = + mlx5hws_bwc_rule_create(hmfs_matcher->hws_bwc_matcher, &match_params, + spec->flow_context.flow_source, rule_actions); + if (!hmfs_rule->hws_bwc_rule) { + err = -EINVAL; + goto err_put_matcher; + } + + return &hmfs_rule->fs_rule; + +err_put_matcher: + mlx5_fc_put_hws_action(hmfs_rule->counter); + mlx5_ct_fs_hmfs_matcher_put(fs, hmfs_matcher); +err_free_rule: + kfree(hmfs_rule); + return ERR_PTR(err); +} + +static void mlx5_ct_fs_hmfs_ct_rule_del(struct mlx5_ct_fs *fs, struct mlx5_ct_fs_rule *fs_rule) +{ + struct mlx5_ct_fs_hmfs_rule *hmfs_rule = container_of(fs_rule, + struct mlx5_ct_fs_hmfs_rule, + fs_rule); + mlx5hws_bwc_rule_destroy(hmfs_rule->hws_bwc_rule); + mlx5_fc_put_hws_action(hmfs_rule->counter); + mlx5_ct_fs_hmfs_matcher_put(fs, hmfs_rule->hmfs_matcher); + kfree(hmfs_rule); +} + +static int mlx5_ct_fs_hmfs_ct_rule_update(struct mlx5_ct_fs *fs, struct mlx5_ct_fs_rule *fs_rule, + struct mlx5_flow_spec *spec, struct mlx5_flow_attr *attr) +{ + struct mlx5_ct_fs_hmfs_rule *hmfs_rule = container_of(fs_rule, + struct mlx5_ct_fs_hmfs_rule, + fs_rule); + struct mlx5hws_rule_action rule_actions[NUM_CT_HMFS_RULES]; + struct mlx5_ct_fs_hmfs *fs_hmfs = mlx5_ct_fs_priv(fs); + int err; + + mlx5_ct_fs_hmfs_fill_rule_actions(fs_hmfs, attr, rule_actions); + + err = mlx5hws_bwc_rule_action_update(hmfs_rule->hws_bwc_rule, rule_actions); + if (err) { + mlx5_fc_put_hws_action(attr->counter); + return err; + } + + mlx5_fc_put_hws_action(hmfs_rule->counter); + hmfs_rule->counter = attr->counter; + + return 0; +} + +static struct mlx5_ct_fs_ops hmfs_ops = { + .ct_rule_add = mlx5_ct_fs_hmfs_ct_rule_add, + .ct_rule_del = mlx5_ct_fs_hmfs_ct_rule_del, + .ct_rule_update = mlx5_ct_fs_hmfs_ct_rule_update, + + .init = mlx5_ct_fs_hmfs_init, + .destroy = mlx5_ct_fs_hmfs_destroy, + + .priv_size = sizeof(struct mlx5_ct_fs_hmfs), +}; + +struct mlx5_ct_fs_ops *mlx5_ct_fs_hmfs_ops_get(void) +{ + return &hmfs_ops; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c index 45737d039252..0c97c5899904 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/ct_fs_smfs.c @@ -13,7 +13,6 @@ #define INIT_ERR_PREFIX "ct_fs_smfs init failed" #define ct_dbg(fmt, args...)\ netdev_dbg(fs->netdev, "ct_fs_smfs debug: " fmt "\n", ##args) -#define MLX5_CT_TCP_FLAGS_MASK cpu_to_be16(be32_to_cpu(TCP_FLAG_RST | TCP_FLAG_FIN) >> 16) struct mlx5_ct_fs_smfs_matcher { struct mlx5dr_matcher *dr_matcher; @@ -220,78 +219,6 @@ mlx5_ct_fs_smfs_destroy(struct mlx5_ct_fs *fs) mlx5_smfs_action_destroy(fs_smfs->fwd_action); } -static inline bool -mlx5_tc_ct_valid_used_dissector_keys(const u64 used_keys) -{ -#define DISS_BIT(name) BIT_ULL(FLOW_DISSECTOR_KEY_ ## name) - const u64 basic_keys = DISS_BIT(BASIC) | DISS_BIT(CONTROL) | - DISS_BIT(META); - const u64 ipv4_tcp = basic_keys | DISS_BIT(IPV4_ADDRS) | - DISS_BIT(PORTS) | DISS_BIT(TCP); - const u64 ipv6_tcp = basic_keys | DISS_BIT(IPV6_ADDRS) | - DISS_BIT(PORTS) | DISS_BIT(TCP); - const u64 ipv4_udp = basic_keys | DISS_BIT(IPV4_ADDRS) | - DISS_BIT(PORTS); - const u64 ipv6_udp = basic_keys | DISS_BIT(IPV6_ADDRS) | - DISS_BIT(PORTS); - const u64 ipv4_gre = basic_keys | DISS_BIT(IPV4_ADDRS); - const u64 ipv6_gre = basic_keys | DISS_BIT(IPV6_ADDRS); - - return (used_keys == ipv4_tcp || used_keys == ipv4_udp || used_keys == ipv6_tcp || - used_keys == ipv6_udp || used_keys == ipv4_gre || used_keys == ipv6_gre); -} - -static bool -mlx5_ct_fs_smfs_ct_validate_flow_rule(struct mlx5_ct_fs *fs, struct flow_rule *flow_rule) -{ - struct flow_match_ipv4_addrs ipv4_addrs; - struct flow_match_ipv6_addrs ipv6_addrs; - struct flow_match_control control; - struct flow_match_basic basic; - struct flow_match_ports ports; - struct flow_match_tcp tcp; - - if (!mlx5_tc_ct_valid_used_dissector_keys(flow_rule->match.dissector->used_keys)) { - ct_dbg("rule uses unexpected dissectors (0x%016llx)", - flow_rule->match.dissector->used_keys); - return false; - } - - flow_rule_match_basic(flow_rule, &basic); - flow_rule_match_control(flow_rule, &control); - flow_rule_match_ipv4_addrs(flow_rule, &ipv4_addrs); - flow_rule_match_ipv6_addrs(flow_rule, &ipv6_addrs); - if (basic.key->ip_proto != IPPROTO_GRE) - flow_rule_match_ports(flow_rule, &ports); - if (basic.key->ip_proto == IPPROTO_TCP) - flow_rule_match_tcp(flow_rule, &tcp); - - if (basic.mask->n_proto != htons(0xFFFF) || - (basic.key->n_proto != htons(ETH_P_IP) && basic.key->n_proto != htons(ETH_P_IPV6)) || - basic.mask->ip_proto != 0xFF || - (basic.key->ip_proto != IPPROTO_UDP && basic.key->ip_proto != IPPROTO_TCP && - basic.key->ip_proto != IPPROTO_GRE)) { - ct_dbg("rule uses unexpected basic match (n_proto 0x%04x/0x%04x, ip_proto 0x%02x/0x%02x)", - ntohs(basic.key->n_proto), ntohs(basic.mask->n_proto), - basic.key->ip_proto, basic.mask->ip_proto); - return false; - } - - if (basic.key->ip_proto != IPPROTO_GRE && - (ports.mask->src != htons(0xFFFF) || ports.mask->dst != htons(0xFFFF))) { - ct_dbg("rule uses ports match (src 0x%04x, dst 0x%04x)", - ports.mask->src, ports.mask->dst); - return false; - } - - if (basic.key->ip_proto == IPPROTO_TCP && tcp.mask->flags != MLX5_CT_TCP_FLAGS_MASK) { - ct_dbg("rule uses unexpected tcp match (flags 0x%02x)", tcp.mask->flags); - return false; - } - - return true; -} - static struct mlx5_ct_fs_rule * mlx5_ct_fs_smfs_ct_rule_add(struct mlx5_ct_fs *fs, struct mlx5_flow_spec *spec, struct mlx5_flow_attr *attr, struct flow_rule *flow_rule) @@ -304,7 +231,7 @@ mlx5_ct_fs_smfs_ct_rule_add(struct mlx5_ct_fs *fs, struct mlx5_flow_spec *spec, int num_actions = 0, err; bool nat, tcp, ipv4, gre; - if (!mlx5_ct_fs_smfs_ct_validate_flow_rule(fs, flow_rule)) + if (!mlx5e_tc_ct_is_valid_flow_rule(fs->netdev, flow_rule)) return ERR_PTR(-EOPNOTSUPP); smfs_rule = kzalloc(sizeof(*smfs_rule), GFP_KERNEL); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c index a84ebac2f011..a065e8fafb1d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c @@ -2065,10 +2065,19 @@ mlx5_tc_ct_fs_init(struct mlx5_tc_ct_priv *ct_priv) struct mlx5_ct_fs_ops *fs_ops = mlx5_ct_fs_dmfs_ops_get(); int err; - if (ct_priv->ns_type == MLX5_FLOW_NAMESPACE_FDB && - ct_priv->dev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_SMFS) { - ct_dbg("Using SMFS ct flow steering provider"); - fs_ops = mlx5_ct_fs_smfs_ops_get(); + if (ct_priv->ns_type == MLX5_FLOW_NAMESPACE_FDB) { + if (ct_priv->dev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_HMFS) { + ct_dbg("Using HMFS ct flow steering provider"); + fs_ops = mlx5_ct_fs_hmfs_ops_get(); + } else if (ct_priv->dev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_SMFS) { + ct_dbg("Using SMFS ct flow steering provider"); + fs_ops = mlx5_ct_fs_smfs_ops_get(); + } + + if (!fs_ops) { + ct_dbg("Requested flow steering mode is not enabled."); + return -EOPNOTSUPP; + } } ct_priv->fs = kzalloc(sizeof(*ct_priv->fs) + fs_ops->priv_size, GFP_KERNEL); @@ -2421,3 +2430,74 @@ out_inc_drop: atomic_inc(&ct_priv->debugfs.stats.rx_dropped); return false; } + +static bool mlx5e_tc_ct_valid_used_dissector_keys(const u64 used_keys) +{ +#define DISS_BIT(name) BIT_ULL(FLOW_DISSECTOR_KEY_ ## name) + const u64 basic_keys = DISS_BIT(BASIC) | DISS_BIT(CONTROL) | + DISS_BIT(META); + const u64 ipv4_tcp = basic_keys | DISS_BIT(IPV4_ADDRS) | + DISS_BIT(PORTS) | DISS_BIT(TCP); + const u64 ipv6_tcp = basic_keys | DISS_BIT(IPV6_ADDRS) | + DISS_BIT(PORTS) | DISS_BIT(TCP); + const u64 ipv4_udp = basic_keys | DISS_BIT(IPV4_ADDRS) | + DISS_BIT(PORTS); + const u64 ipv6_udp = basic_keys | DISS_BIT(IPV6_ADDRS) | + DISS_BIT(PORTS); + const u64 ipv4_gre = basic_keys | DISS_BIT(IPV4_ADDRS); + const u64 ipv6_gre = basic_keys | DISS_BIT(IPV6_ADDRS); + + return (used_keys == ipv4_tcp || used_keys == ipv4_udp || used_keys == ipv6_tcp || + used_keys == ipv6_udp || used_keys == ipv4_gre || used_keys == ipv6_gre); +} + +bool mlx5e_tc_ct_is_valid_flow_rule(const struct net_device *dev, struct flow_rule *flow_rule) +{ + struct flow_match_ipv4_addrs ipv4_addrs; + struct flow_match_ipv6_addrs ipv6_addrs; + struct flow_match_control control; + struct flow_match_basic basic; + struct flow_match_ports ports; + struct flow_match_tcp tcp; + + if (!mlx5e_tc_ct_valid_used_dissector_keys(flow_rule->match.dissector->used_keys)) { + netdev_dbg(dev, "ct_debug: rule uses unexpected dissectors (0x%016llx)", + flow_rule->match.dissector->used_keys); + return false; + } + + flow_rule_match_basic(flow_rule, &basic); + flow_rule_match_control(flow_rule, &control); + flow_rule_match_ipv4_addrs(flow_rule, &ipv4_addrs); + flow_rule_match_ipv6_addrs(flow_rule, &ipv6_addrs); + if (basic.key->ip_proto != IPPROTO_GRE) + flow_rule_match_ports(flow_rule, &ports); + if (basic.key->ip_proto == IPPROTO_TCP) + flow_rule_match_tcp(flow_rule, &tcp); + + if (basic.mask->n_proto != htons(0xFFFF) || + (basic.key->n_proto != htons(ETH_P_IP) && basic.key->n_proto != htons(ETH_P_IPV6)) || + basic.mask->ip_proto != 0xFF || + (basic.key->ip_proto != IPPROTO_UDP && basic.key->ip_proto != IPPROTO_TCP && + basic.key->ip_proto != IPPROTO_GRE)) { + netdev_dbg(dev, "ct_debug: rule uses unexpected basic match (n_proto 0x%04x/0x%04x, ip_proto 0x%02x/0x%02x)", + ntohs(basic.key->n_proto), ntohs(basic.mask->n_proto), + basic.key->ip_proto, basic.mask->ip_proto); + return false; + } + + if (basic.key->ip_proto != IPPROTO_GRE && + (ports.mask->src != htons(0xFFFF) || ports.mask->dst != htons(0xFFFF))) { + netdev_dbg(dev, "ct_debug: rule uses ports match (src 0x%04x, dst 0x%04x)", + ports.mask->src, ports.mask->dst); + return false; + } + + if (basic.key->ip_proto == IPPROTO_TCP && tcp.mask->flags != MLX5_CT_TCP_FLAGS_MASK) { + netdev_dbg(dev, "ct_debug: rule uses unexpected tcp match (flags 0x%02x)", + tcp.mask->flags); + return false; + } + + return true; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h index b66c5f98067f..5e9dbdd4a5e9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h @@ -128,6 +128,9 @@ bool mlx5e_tc_ct_restore_flow(struct mlx5_tc_ct_priv *ct_priv, struct sk_buff *skb, u8 zone_restore_id); +#define MLX5_CT_TCP_FLAGS_MASK cpu_to_be16(be32_to_cpu(TCP_FLAG_RST | TCP_FLAG_FIN) >> 16) +bool mlx5e_tc_ct_is_valid_flow_rule(const struct net_device *dev, struct flow_rule *flow_rule); + #else /* CONFIG_MLX5_TC_CT */ static inline struct mlx5_tc_ct_priv * @@ -202,5 +205,12 @@ mlx5e_tc_ct_restore_flow(struct mlx5_tc_ct_priv *ct_priv, return false; } +static inline bool +mlx5e_tc_ct_is_valid_flow_rule(const struct net_device *dev, + struct flow_rule *flow_rule) +{ + return false; +} + #endif /* !IS_ENABLED(CONFIG_MLX5_TC_CT) */ #endif /* __MLX5_EN_TC_CT_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c index 8489b0a0e8bd..501709ac310f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c @@ -717,6 +717,12 @@ static int mlx5e_xfrm_add_state(struct xfrm_state *x, /* check esn */ if (x->props.flags & XFRM_STATE_ESN) mlx5e_ipsec_update_esn_state(sa_entry); + else + /* According to RFC4303, section "3.3.3. Sequence Number Generation", + * the first packet sent using a given SA will contain a sequence + * number of 1. + */ + sa_entry->esn_state.esn = 1; mlx5e_ipsec_build_accel_xfrm_attrs(sa_entry, &sa_entry->attrs); @@ -761,9 +767,12 @@ static int mlx5e_xfrm_add_state(struct xfrm_state *x, MLX5_IPSEC_RESCHED); if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET && - x->props.mode == XFRM_MODE_TUNNEL) - xa_set_mark(&ipsec->sadb, sa_entry->ipsec_obj_id, - MLX5E_IPSEC_TUNNEL_SA); + x->props.mode == XFRM_MODE_TUNNEL) { + xa_lock_bh(&ipsec->sadb); + __xa_set_mark(&ipsec->sadb, sa_entry->ipsec_obj_id, + MLX5E_IPSEC_TUNNEL_SA); + xa_unlock_bh(&ipsec->sadb); + } out: x->xso.offload_handle = (unsigned long)sa_entry; @@ -790,7 +799,6 @@ err_xfrm: static void mlx5e_xfrm_del_state(struct xfrm_state *x) { struct mlx5e_ipsec_sa_entry *sa_entry = to_ipsec_sa_entry(x); - struct mlx5_accel_esp_xfrm_attrs *attrs = &sa_entry->attrs; struct mlx5e_ipsec *ipsec = sa_entry->ipsec; struct mlx5e_ipsec_sa_entry *old; @@ -799,12 +807,6 @@ static void mlx5e_xfrm_del_state(struct xfrm_state *x) old = xa_erase_bh(&ipsec->sadb, sa_entry->ipsec_obj_id); WARN_ON(old != sa_entry); - - if (attrs->mode == XFRM_MODE_TUNNEL && - attrs->type == XFRM_DEV_OFFLOAD_PACKET) - /* Make sure that no ARP requests are running in parallel */ - flush_workqueue(ipsec->wq); - } static void mlx5e_xfrm_free_state(struct xfrm_state *x) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c index 687bd95d2c3e..e7b64679f121 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c @@ -1718,23 +1718,21 @@ static int tx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry) goto err_alloc; } - if (attrs->family == AF_INET) - setup_fte_addr4(spec, &attrs->saddr.a4, &attrs->daddr.a4); - else - setup_fte_addr6(spec, attrs->saddr.a6, attrs->daddr.a6); - setup_fte_no_frags(spec); setup_fte_upper_proto_match(spec, &attrs->upspec); switch (attrs->type) { case XFRM_DEV_OFFLOAD_CRYPTO: + if (attrs->family == AF_INET) + setup_fte_addr4(spec, &attrs->saddr.a4, &attrs->daddr.a4); + else + setup_fte_addr6(spec, attrs->saddr.a6, attrs->daddr.a6); setup_fte_spi(spec, attrs->spi, false); setup_fte_esp(spec); setup_fte_reg_a(spec); break; case XFRM_DEV_OFFLOAD_PACKET: - if (attrs->reqid) - setup_fte_reg_c4(spec, attrs->reqid); + setup_fte_reg_c4(spec, attrs->reqid); err = setup_pkt_reformat(ipsec, attrs, &flow_act); if (err) goto err_pkt_reformat; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c index 53cfa39188cb..820debf3fbbf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c @@ -91,8 +91,9 @@ u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev) EXPORT_SYMBOL_GPL(mlx5_ipsec_device_caps); static void mlx5e_ipsec_packet_setup(void *obj, u32 pdn, - struct mlx5_accel_esp_xfrm_attrs *attrs) + struct mlx5e_ipsec_sa_entry *sa_entry) { + struct mlx5_accel_esp_xfrm_attrs *attrs = &sa_entry->attrs; void *aso_ctx; aso_ctx = MLX5_ADDR_OF(ipsec_obj, obj, ipsec_aso); @@ -120,8 +121,12 @@ static void mlx5e_ipsec_packet_setup(void *obj, u32 pdn, * active. */ MLX5_SET(ipsec_obj, obj, aso_return_reg, MLX5_IPSEC_ASO_REG_C_4_5); - if (attrs->dir == XFRM_DEV_OFFLOAD_OUT) + if (attrs->dir == XFRM_DEV_OFFLOAD_OUT) { MLX5_SET(ipsec_aso, aso_ctx, mode, MLX5_IPSEC_ASO_INC_SN); + if (!attrs->replay_esn.trigger) + MLX5_SET(ipsec_aso, aso_ctx, mode_parameter, + sa_entry->esn_state.esn); + } if (attrs->lft.hard_packet_limit != XFRM_INF) { MLX5_SET(ipsec_aso, aso_ctx, remove_flow_pkt_cnt, @@ -175,7 +180,7 @@ static int mlx5_create_ipsec_obj(struct mlx5e_ipsec_sa_entry *sa_entry) res = &mdev->mlx5e_res.hw_objs; if (attrs->type == XFRM_DEV_OFFLOAD_PACKET) - mlx5e_ipsec_packet_setup(obj, res->pdn, attrs); + mlx5e_ipsec_packet_setup(obj, res->pdn, sa_entry); err = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); if (!err) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 41b5e98a0495..22dc23d991d2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -2716,6 +2716,7 @@ struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev, break; case MLX5_FLOW_NAMESPACE_RDMA_TX: root_ns = steering->rdma_tx_root_ns; + prio = RDMA_TX_BYPASS_PRIO; break; case MLX5_FLOW_NAMESPACE_RDMA_RX_COUNTERS: root_ns = steering->rdma_rx_root_ns; @@ -3535,35 +3536,42 @@ static int mlx5_fs_mode_validate(struct devlink *devlink, u32 id, { struct mlx5_core_dev *dev = devlink_priv(devlink); char *value = val.vstr; - int err = 0; + u8 eswitch_mode; - if (!strcmp(value, "dmfs")) { + if (!strcmp(value, "dmfs")) return 0; - } else if (!strcmp(value, "smfs")) { - u8 eswitch_mode; - bool smfs_cap; - eswitch_mode = mlx5_eswitch_mode(dev); - smfs_cap = mlx5_fs_dr_is_supported(dev); + if (!strcmp(value, "smfs")) { + bool smfs_cap = mlx5_fs_dr_is_supported(dev); if (!smfs_cap) { - err = -EOPNOTSUPP; NL_SET_ERR_MSG_MOD(extack, "Software managed steering is not supported by current device"); + return -EOPNOTSUPP; } + } else if (!strcmp(value, "hmfs")) { + bool hmfs_cap = mlx5_fs_hws_is_supported(dev); - else if (eswitch_mode == MLX5_ESWITCH_OFFLOADS) { + if (!hmfs_cap) { NL_SET_ERR_MSG_MOD(extack, - "Software managed steering is not supported when eswitch offloads enabled."); - err = -EOPNOTSUPP; + "Hardware steering is not supported by current device"); + return -EOPNOTSUPP; } } else { NL_SET_ERR_MSG_MOD(extack, - "Bad parameter: supported values are [\"dmfs\", \"smfs\"]"); - err = -EINVAL; + "Bad parameter: supported values are [\"dmfs\", \"smfs\", \"hmfs\"]"); + return -EINVAL; } - return err; + eswitch_mode = mlx5_eswitch_mode(dev); + if (eswitch_mode == MLX5_ESWITCH_OFFLOADS) { + NL_SET_ERR_MSG_FMT_MOD(extack, + "Moving to %s is not supported when eswitch offloads enabled.", + value); + return -EOPNOTSUPP; + } + + return 0; } static int mlx5_fs_mode_set(struct devlink *devlink, u32 id, @@ -3575,6 +3583,8 @@ static int mlx5_fs_mode_set(struct devlink *devlink, u32 id, if (!strcmp(ctx->val.vstr, "smfs")) mode = MLX5_FLOW_STEERING_MODE_SMFS; + else if (!strcmp(ctx->val.vstr, "hmfs")) + mode = MLX5_FLOW_STEERING_MODE_HMFS; else mode = MLX5_FLOW_STEERING_MODE_DMFS; dev->priv.steering->mode = mode; @@ -3587,10 +3597,17 @@ static int mlx5_fs_mode_get(struct devlink *devlink, u32 id, { struct mlx5_core_dev *dev = devlink_priv(devlink); - if (dev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_SMFS) + switch (dev->priv.steering->mode) { + case MLX5_FLOW_STEERING_MODE_SMFS: strscpy(ctx->val.vstr, "smfs", sizeof(ctx->val.vstr)); - else + break; + case MLX5_FLOW_STEERING_MODE_HMFS: + strscpy(ctx->val.vstr, "hmfs", sizeof(ctx->val.vstr)); + break; + default: strscpy(ctx->val.vstr, "dmfs", sizeof(ctx->val.vstr)); + } + return 0; } @@ -4009,6 +4026,8 @@ int mlx5_flow_namespace_set_mode(struct mlx5_flow_namespace *ns, if (mode == MLX5_FLOW_STEERING_MODE_SMFS) cmds = mlx5_fs_cmd_get_dr_cmds(); + else if (mode == MLX5_FLOW_STEERING_MODE_HMFS) + cmds = mlx5_fs_cmd_get_hws_cmds(); else cmds = mlx5_fs_cmd_get_fw_cmds(); if (!cmds) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index bad2df0715ec..20837e526679 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -38,6 +38,7 @@ #include <linux/rhashtable.h> #include <linux/llist.h> #include <steering/sws/fs_dr.h> +#include <steering/hws/fs_hws.h> #define FDB_TC_MAX_CHAIN 3 #define FDB_FT_CHAIN (FDB_TC_MAX_CHAIN + 1) @@ -64,6 +65,7 @@ struct mlx5_modify_hdr { enum mlx5_flow_resource_owner owner; union { struct mlx5_fs_dr_action fs_dr_action; + struct mlx5_fs_hws_action fs_hws_action; u32 id; }; }; @@ -74,6 +76,7 @@ struct mlx5_pkt_reformat { enum mlx5_flow_resource_owner owner; union { struct mlx5_fs_dr_action fs_dr_action; + struct mlx5_fs_hws_action fs_hws_action; u32 id; }; }; @@ -126,7 +129,8 @@ enum fs_fte_status { enum mlx5_flow_steering_mode { MLX5_FLOW_STEERING_MODE_DMFS, - MLX5_FLOW_STEERING_MODE_SMFS + MLX5_FLOW_STEERING_MODE_SMFS, + MLX5_FLOW_STEERING_MODE_HMFS, }; enum mlx5_flow_steering_capabilty { @@ -190,7 +194,10 @@ struct mlx5_flow_handle { /* Type of children is mlx5_flow_group */ struct mlx5_flow_table { struct fs_node node; - struct mlx5_fs_dr_table fs_dr_table; + union { + struct mlx5_fs_dr_table fs_dr_table; + struct mlx5_fs_hws_table fs_hws_table; + }; u32 id; u16 vport; unsigned int max_fte; @@ -247,7 +254,10 @@ struct fs_fte_dup { /* Type of children is mlx5_flow_rule */ struct fs_fte { struct fs_node node; - struct mlx5_fs_dr_rule fs_dr_rule; + union { + struct mlx5_fs_dr_rule fs_dr_rule; + struct mlx5_fs_hws_rule fs_hws_rule; + }; u32 val[MLX5_ST_SZ_DW_MATCH_PARAM]; struct fs_fte_action act_dests; struct fs_fte_dup *dup; @@ -280,7 +290,10 @@ struct mlx5_flow_group_mask { /* Type of children is fs_fte */ struct mlx5_flow_group { struct fs_node node; - struct mlx5_fs_dr_matcher fs_dr_matcher; + union { + struct mlx5_fs_dr_matcher fs_dr_matcher; + struct mlx5_fs_hws_matcher fs_hws_matcher; + }; struct mlx5_flow_group_mask mask; u32 start_index; u32 max_ftes; @@ -293,7 +306,10 @@ struct mlx5_flow_group { struct mlx5_flow_root_namespace { struct mlx5_flow_namespace ns; enum mlx5_flow_steering_mode mode; - struct mlx5_fs_dr_domain fs_dr_domain; + union { + struct mlx5_fs_dr_domain fs_dr_domain; + struct mlx5_fs_hws_context fs_hws_context; + }; enum fs_flow_table_type table_type; struct mlx5_core_dev *dev; struct mlx5_flow_table *root_ft; @@ -303,6 +319,42 @@ struct mlx5_flow_root_namespace { const struct mlx5_flow_cmds *cmds; }; +enum mlx5_fc_type { + MLX5_FC_TYPE_ACQUIRED = 0, + MLX5_FC_TYPE_LOCAL, +}; + +struct mlx5_fc_cache { + u64 packets; + u64 bytes; + u64 lastuse; +}; + +struct mlx5_fc { + u32 id; + bool aging; + enum mlx5_fc_type type; + struct mlx5_fc_bulk *bulk; + struct mlx5_fc_cache cache; + /* last{packets,bytes} are used for calculating deltas since last reading. */ + u64 lastpackets; + u64 lastbytes; +}; + +struct mlx5_fc_bulk_hws_data { + struct mlx5hws_action *hws_action; + struct mutex lock; /* protects hws_action */ + refcount_t hws_action_refcount; +}; + +struct mlx5_fc_bulk { + struct mlx5_fs_bulk fs_bulk; + u32 base_id; + struct mlx5_fc_bulk_hws_data hws_data; + struct mlx5_fc fcs[]; +}; + +u32 mlx5_fc_get_base_id(struct mlx5_fc *counter); int mlx5_init_fc_stats(struct mlx5_core_dev *dev); void mlx5_cleanup_fc_stats(struct mlx5_core_dev *dev); void mlx5_fc_queue_stats_work(struct mlx5_core_dev *dev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c index d8e1c4ebd364..492775d3d193 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c @@ -44,28 +44,6 @@ #define MLX5_FC_POOL_MAX_THRESHOLD BIT(18) #define MLX5_FC_POOL_USED_BUFF_RATIO 10 -enum mlx5_fc_type { - MLX5_FC_TYPE_ACQUIRED = 0, - MLX5_FC_TYPE_LOCAL, -}; - -struct mlx5_fc_cache { - u64 packets; - u64 bytes; - u64 lastuse; -}; - -struct mlx5_fc { - u32 id; - bool aging; - enum mlx5_fc_type type; - struct mlx5_fc_bulk *bulk; - struct mlx5_fc_cache cache; - /* last{packets,bytes} are used for calculating deltas since last reading. */ - u64 lastpackets; - u64 lastbytes; -}; - struct mlx5_fc_stats { struct xarray counters; @@ -434,13 +412,7 @@ void mlx5_fc_update_sampling_interval(struct mlx5_core_dev *dev, fc_stats->sampling_interval); } -/* Flow counter bluks */ - -struct mlx5_fc_bulk { - struct mlx5_fs_bulk fs_bulk; - u32 base_id; - struct mlx5_fc fcs[]; -}; +/* Flow counter bulks */ static void mlx5_fc_init(struct mlx5_fc *counter, struct mlx5_fc_bulk *bulk, u32 id) @@ -449,7 +421,13 @@ static void mlx5_fc_init(struct mlx5_fc *counter, struct mlx5_fc_bulk *bulk, counter->id = id; } -static struct mlx5_fs_bulk *mlx5_fc_bulk_create(struct mlx5_core_dev *dev) +u32 mlx5_fc_get_base_id(struct mlx5_fc *counter) +{ + return counter->bulk->base_id; +} + +static struct mlx5_fs_bulk *mlx5_fc_bulk_create(struct mlx5_core_dev *dev, + void *pool_ctx) { enum mlx5_fc_bulk_alloc_bitmask alloc_bitmask; struct mlx5_fc_bulk *fc_bulk; @@ -473,6 +451,8 @@ static struct mlx5_fs_bulk *mlx5_fc_bulk_create(struct mlx5_core_dev *dev) for (i = 0; i < bulk_len; i++) mlx5_fc_init(&fc_bulk->fcs[i], fc_bulk, base_id + i); + refcount_set(&fc_bulk->hws_data.hws_action_refcount, 0); + mutex_init(&fc_bulk->hws_data.lock); return &fc_bulk->fs_bulk; fs_bulk_cleanup: @@ -518,7 +498,7 @@ static const struct mlx5_fs_pool_ops mlx5_fc_pool_ops = { static void mlx5_fc_pool_init(struct mlx5_fs_pool *fc_pool, struct mlx5_core_dev *dev) { - mlx5_fs_pool_init(fc_pool, dev, &mlx5_fc_pool_ops); + mlx5_fs_pool_init(fc_pool, dev, &mlx5_fc_pool_ops, NULL); } static void mlx5_fc_pool_cleanup(struct mlx5_fs_pool *fc_pool) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_pool.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_pool.c index b891d7b9e3e0..f6c226664602 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_pool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_pool.c @@ -56,11 +56,12 @@ static int mlx5_fs_bulk_release_index(struct mlx5_fs_bulk *fs_bulk, int index) } void mlx5_fs_pool_init(struct mlx5_fs_pool *pool, struct mlx5_core_dev *dev, - const struct mlx5_fs_pool_ops *ops) + const struct mlx5_fs_pool_ops *ops, void *pool_ctx) { WARN_ON_ONCE(!ops || !ops->bulk_destroy || !ops->bulk_create || !ops->update_threshold); pool->dev = dev; + pool->pool_ctx = pool_ctx; mutex_init(&pool->pool_lock); INIT_LIST_HEAD(&pool->fully_used); INIT_LIST_HEAD(&pool->partially_used); @@ -91,7 +92,7 @@ mlx5_fs_pool_alloc_new_bulk(struct mlx5_fs_pool *fs_pool) struct mlx5_core_dev *dev = fs_pool->dev; struct mlx5_fs_bulk *new_bulk; - new_bulk = fs_pool->ops->bulk_create(dev); + new_bulk = fs_pool->ops->bulk_create(dev, fs_pool->pool_ctx); if (new_bulk) fs_pool->available_units += new_bulk->bulk_len; fs_pool->ops->update_threshold(fs_pool); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_pool.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_pool.h index 3b149863260c..f04ec3107498 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_pool.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_pool.h @@ -21,7 +21,8 @@ struct mlx5_fs_pool; struct mlx5_fs_pool_ops { int (*bulk_destroy)(struct mlx5_core_dev *dev, struct mlx5_fs_bulk *bulk); - struct mlx5_fs_bulk * (*bulk_create)(struct mlx5_core_dev *dev); + struct mlx5_fs_bulk * (*bulk_create)(struct mlx5_core_dev *dev, + void *pool_ctx); void (*update_threshold)(struct mlx5_fs_pool *pool); }; @@ -44,7 +45,7 @@ void mlx5_fs_bulk_cleanup(struct mlx5_fs_bulk *fs_bulk); int mlx5_fs_bulk_get_free_amount(struct mlx5_fs_bulk *bulk); void mlx5_fs_pool_init(struct mlx5_fs_pool *pool, struct mlx5_core_dev *dev, - const struct mlx5_fs_pool_ops *ops); + const struct mlx5_fs_pool_ops *ops, void *pool_ctx); void mlx5_fs_pool_cleanup(struct mlx5_fs_pool *pool); int mlx5_fs_pool_acquire_index(struct mlx5_fs_pool *fs_pool, struct mlx5_fs_pool_index *pool_index); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c index 76ad46bf477d..b253d1673398 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c @@ -281,6 +281,12 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev) return err; } + if (MLX5_CAP_GEN(dev, shampo)) { + err = mlx5_core_get_caps_mode(dev, MLX5_CAP_SHAMPO, HCA_CAP_OPMOD_GET_CUR); + if (err) + return err; + } + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c index 22241f52716c..bde79cac33a9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c @@ -551,7 +551,7 @@ int mlx5_lag_port_sel_create(struct mlx5_lag *ldev, set_tt_map(port_sel, hash_type); err = mlx5_lag_create_definers(ldev, hash_type, ports); if (err) - return err; + goto clear_port_sel; if (port_sel->tunnel) { err = mlx5_lag_create_inner_ttc_table(ldev); @@ -570,6 +570,8 @@ destroy_inner: mlx5_destroy_ttc_table(port_sel->inner.ttc); destroy_definers: mlx5_lag_destroy_definers(ldev); +clear_port_sel: + memset(port_sel, 0, sizeof(*port_sel)); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index a108d8c726f8..ec956c4bcebd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -368,6 +368,10 @@ int mlx5_core_get_caps_mode(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_ty u16 opmod = (cap_type << 1) | (cap_mode & 0x01); int err; + if (WARN_ON(!dev->caps.hca[cap_type])) + /* this cap_type must be added to mlx5_hca_caps_alloc() */ + return -EINVAL; + memset(in, 0, sizeof(in)); out = kzalloc(out_sz, GFP_KERNEL); if (!out) @@ -1790,6 +1794,7 @@ static const int types[] = { MLX5_CAP_MACSEC, MLX5_CAP_ADV_VIRTUALIZATION, MLX5_CAP_CRYPTO, + MLX5_CAP_SHAMPO, }; static void mlx5_hca_caps_free(struct mlx5_core_dev *dev) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c index a96be98be032..b96909fbeb12 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c @@ -257,6 +257,7 @@ static int mlx5_sf_add(struct mlx5_core_dev *dev, struct mlx5_sf_table *table, return 0; esw_err: + mlx5_sf_function_id_erase(table, sf); mlx5_sf_free(table, sf); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c index a8d886e92144..3dbd4efa21a2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c @@ -468,8 +468,22 @@ hws_bwc_matcher_size_maxed_out(struct mlx5hws_bwc_matcher *bwc_matcher) { struct mlx5hws_cmd_query_caps *caps = bwc_matcher->matcher->tbl->ctx->caps; - return bwc_matcher->size_log + MLX5HWS_MATCHER_ASSURED_MAIN_TBL_DEPTH >= - caps->ste_alloc_log_max - 1; + /* check the match RTC size */ + if ((bwc_matcher->size_log + + MLX5HWS_MATCHER_ASSURED_MAIN_TBL_DEPTH + + MLX5HWS_BWC_MATCHER_SIZE_LOG_STEP) > + (caps->ste_alloc_log_max - 1)) + return true; + + /* check the action RTC size */ + if ((bwc_matcher->size_log + + MLX5HWS_BWC_MATCHER_SIZE_LOG_STEP + + ilog2(roundup_pow_of_two(bwc_matcher->matcher->action_ste.max_stes)) + + MLX5HWS_MATCHER_ACTION_RTC_UPDATE_MULT) > + (caps->ste_alloc_log_max - 1)) + return true; + + return false; } static bool diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/debug.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/debug.c index 60ada3143d60..696275fd0ce2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/debug.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/debug.c @@ -148,8 +148,8 @@ static int hws_debug_dump_matcher(struct seq_file *f, struct mlx5hws_matcher *ma matcher->match_ste.rtc_1_id, (int)ste_1_id); - ste = &matcher->action_ste[0].ste; - ste_pool = matcher->action_ste[0].pool; + ste = &matcher->action_ste.ste; + ste_pool = matcher->action_ste.pool; if (ste_pool) { ste_0_id = mlx5hws_pool_chunk_get_base_id(ste_pool, ste); if (tbl_type == MLX5HWS_TABLE_TYPE_FDB) @@ -171,10 +171,8 @@ static int hws_debug_dump_matcher(struct seq_file *f, struct mlx5hws_matcher *ma return ret; seq_printf(f, ",%d,%d,%d,%d,%d,0x%llx,0x%llx\n", - matcher->action_ste[0].rtc_0_id, - (int)ste_0_id, - matcher->action_ste[0].rtc_1_id, - (int)ste_1_id, + matcher->action_ste.rtc_0_id, (int)ste_0_id, + matcher->action_ste.rtc_1_id, (int)ste_1_id, 0, mlx5hws_debug_icm_to_idx(icm_addr_0), mlx5hws_debug_icm_to_idx(icm_addr_1)); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c new file mode 100644 index 000000000000..f34bbbbba1c2 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c @@ -0,0 +1,1377 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2025 NVIDIA Corporation & Affiliates */ + +#include <linux/mlx5/vport.h> +#include <mlx5_core.h> +#include <fs_core.h> +#include <fs_cmd.h> +#include "fs_hws_pools.h" +#include "mlx5hws.h" + +#define MLX5HWS_CTX_MAX_NUM_OF_QUEUES 16 +#define MLX5HWS_CTX_QUEUE_SIZE 256 + +static struct mlx5hws_action * +mlx5_fs_create_action_remove_header_vlan(struct mlx5hws_context *ctx); +static void +mlx5_fs_destroy_pr_pool(struct mlx5_fs_pool *pool, struct xarray *pr_pools, + unsigned long index); +static void +mlx5_fs_destroy_mh_pool(struct mlx5_fs_pool *pool, struct xarray *mh_pools, + unsigned long index); + +static int mlx5_fs_init_hws_actions_pool(struct mlx5_core_dev *dev, + struct mlx5_fs_hws_context *fs_ctx) +{ + u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED; + struct mlx5_fs_hws_actions_pool *hws_pool = &fs_ctx->hws_pool; + struct mlx5hws_action_reformat_header reformat_hdr = {}; + struct mlx5hws_context *ctx = fs_ctx->hws_ctx; + enum mlx5hws_action_type action_type; + int err = -ENOSPC; + + hws_pool->tag_action = mlx5hws_action_create_tag(ctx, flags); + if (!hws_pool->tag_action) + return err; + hws_pool->pop_vlan_action = mlx5hws_action_create_pop_vlan(ctx, flags); + if (!hws_pool->pop_vlan_action) + goto destroy_tag; + hws_pool->push_vlan_action = mlx5hws_action_create_push_vlan(ctx, flags); + if (!hws_pool->push_vlan_action) + goto destroy_pop_vlan; + hws_pool->drop_action = mlx5hws_action_create_dest_drop(ctx, flags); + if (!hws_pool->drop_action) + goto destroy_push_vlan; + action_type = MLX5HWS_ACTION_TYP_REFORMAT_TNL_L2_TO_L2; + hws_pool->decapl2_action = + mlx5hws_action_create_reformat(ctx, action_type, 1, + &reformat_hdr, 0, flags); + if (!hws_pool->decapl2_action) + goto destroy_drop; + hws_pool->remove_hdr_vlan_action = + mlx5_fs_create_action_remove_header_vlan(ctx); + if (!hws_pool->remove_hdr_vlan_action) + goto destroy_decapl2; + err = mlx5_fs_hws_pr_pool_init(&hws_pool->insert_hdr_pool, dev, 0, + MLX5HWS_ACTION_TYP_INSERT_HEADER); + if (err) + goto destroy_remove_hdr; + err = mlx5_fs_hws_pr_pool_init(&hws_pool->dl3tnltol2_pool, dev, 0, + MLX5HWS_ACTION_TYP_REFORMAT_TNL_L3_TO_L2); + if (err) + goto cleanup_insert_hdr; + xa_init(&hws_pool->el2tol3tnl_pools); + xa_init(&hws_pool->el2tol2tnl_pools); + xa_init(&hws_pool->mh_pools); + xa_init(&hws_pool->table_dests); + xa_init(&hws_pool->vport_dests); + xa_init(&hws_pool->vport_vhca_dests); + return 0; + +cleanup_insert_hdr: + mlx5_fs_hws_pr_pool_cleanup(&hws_pool->insert_hdr_pool); +destroy_remove_hdr: + mlx5hws_action_destroy(hws_pool->remove_hdr_vlan_action); +destroy_decapl2: + mlx5hws_action_destroy(hws_pool->decapl2_action); +destroy_drop: + mlx5hws_action_destroy(hws_pool->drop_action); +destroy_push_vlan: + mlx5hws_action_destroy(hws_pool->push_vlan_action); +destroy_pop_vlan: + mlx5hws_action_destroy(hws_pool->pop_vlan_action); +destroy_tag: + mlx5hws_action_destroy(hws_pool->tag_action); + return err; +} + +static void mlx5_fs_cleanup_hws_actions_pool(struct mlx5_fs_hws_context *fs_ctx) +{ + struct mlx5_fs_hws_actions_pool *hws_pool = &fs_ctx->hws_pool; + struct mlx5hws_action *action; + struct mlx5_fs_pool *pool; + unsigned long i; + + xa_for_each(&hws_pool->vport_vhca_dests, i, action) + mlx5hws_action_destroy(action); + xa_destroy(&hws_pool->vport_vhca_dests); + xa_for_each(&hws_pool->vport_dests, i, action) + mlx5hws_action_destroy(action); + xa_destroy(&hws_pool->vport_dests); + xa_destroy(&hws_pool->table_dests); + xa_for_each(&hws_pool->mh_pools, i, pool) + mlx5_fs_destroy_mh_pool(pool, &hws_pool->mh_pools, i); + xa_destroy(&hws_pool->mh_pools); + xa_for_each(&hws_pool->el2tol2tnl_pools, i, pool) + mlx5_fs_destroy_pr_pool(pool, &hws_pool->el2tol2tnl_pools, i); + xa_destroy(&hws_pool->el2tol2tnl_pools); + xa_for_each(&hws_pool->el2tol3tnl_pools, i, pool) + mlx5_fs_destroy_pr_pool(pool, &hws_pool->el2tol3tnl_pools, i); + xa_destroy(&hws_pool->el2tol3tnl_pools); + mlx5_fs_hws_pr_pool_cleanup(&hws_pool->dl3tnltol2_pool); + mlx5_fs_hws_pr_pool_cleanup(&hws_pool->insert_hdr_pool); + mlx5hws_action_destroy(hws_pool->remove_hdr_vlan_action); + mlx5hws_action_destroy(hws_pool->decapl2_action); + mlx5hws_action_destroy(hws_pool->drop_action); + mlx5hws_action_destroy(hws_pool->push_vlan_action); + mlx5hws_action_destroy(hws_pool->pop_vlan_action); + mlx5hws_action_destroy(hws_pool->tag_action); +} + +static int mlx5_cmd_hws_create_ns(struct mlx5_flow_root_namespace *ns) +{ + struct mlx5hws_context_attr hws_ctx_attr = {}; + int err; + + hws_ctx_attr.queues = min_t(int, num_online_cpus(), + MLX5HWS_CTX_MAX_NUM_OF_QUEUES); + hws_ctx_attr.queue_size = MLX5HWS_CTX_QUEUE_SIZE; + + ns->fs_hws_context.hws_ctx = + mlx5hws_context_open(ns->dev, &hws_ctx_attr); + if (!ns->fs_hws_context.hws_ctx) { + mlx5_core_err(ns->dev, "Failed to create hws flow namespace\n"); + return -EINVAL; + } + err = mlx5_fs_init_hws_actions_pool(ns->dev, &ns->fs_hws_context); + if (err) { + mlx5_core_err(ns->dev, "Failed to init hws actions pool\n"); + mlx5hws_context_close(ns->fs_hws_context.hws_ctx); + return err; + } + return 0; +} + +static int mlx5_cmd_hws_destroy_ns(struct mlx5_flow_root_namespace *ns) +{ + mlx5_fs_cleanup_hws_actions_pool(&ns->fs_hws_context); + return mlx5hws_context_close(ns->fs_hws_context.hws_ctx); +} + +static int mlx5_cmd_hws_set_peer(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_root_namespace *peer_ns, + u16 peer_vhca_id) +{ + struct mlx5hws_context *peer_ctx = NULL; + + if (peer_ns) + peer_ctx = peer_ns->fs_hws_context.hws_ctx; + mlx5hws_context_set_peer(ns->fs_hws_context.hws_ctx, peer_ctx, + peer_vhca_id); + return 0; +} + +static int mlx5_fs_set_ft_default_miss(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft, + struct mlx5_flow_table *next_ft) +{ + struct mlx5hws_table *next_tbl; + int err; + + if (!ns->fs_hws_context.hws_ctx) + return -EINVAL; + + /* if no change required, return */ + if (!next_ft && !ft->fs_hws_table.miss_ft_set) + return 0; + + next_tbl = next_ft ? next_ft->fs_hws_table.hws_table : NULL; + err = mlx5hws_table_set_default_miss(ft->fs_hws_table.hws_table, next_tbl); + if (err) { + mlx5_core_err(ns->dev, "Failed setting FT default miss (%d)\n", err); + return err; + } + ft->fs_hws_table.miss_ft_set = !!next_tbl; + return 0; +} + +static int mlx5_fs_add_flow_table_dest_action(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft) +{ + u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED; + struct mlx5_fs_hws_context *fs_ctx = &ns->fs_hws_context; + struct mlx5hws_action *dest_ft_action; + struct xarray *dests_xa; + int err; + + dest_ft_action = mlx5hws_action_create_dest_table_num(fs_ctx->hws_ctx, + ft->id, flags); + if (!dest_ft_action) { + mlx5_core_err(ns->dev, "Failed creating dest table action\n"); + return -ENOMEM; + } + + dests_xa = &fs_ctx->hws_pool.table_dests; + err = xa_insert(dests_xa, ft->id, dest_ft_action, GFP_KERNEL); + if (err) + mlx5hws_action_destroy(dest_ft_action); + return err; +} + +static int mlx5_fs_del_flow_table_dest_action(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft) +{ + struct mlx5_fs_hws_context *fs_ctx = &ns->fs_hws_context; + struct mlx5hws_action *dest_ft_action; + struct xarray *dests_xa; + int err; + + dests_xa = &fs_ctx->hws_pool.table_dests; + dest_ft_action = xa_erase(dests_xa, ft->id); + if (!dest_ft_action) { + mlx5_core_err(ns->dev, "Failed to erase dest ft action\n"); + return -ENOENT; + } + + err = mlx5hws_action_destroy(dest_ft_action); + if (err) + mlx5_core_err(ns->dev, "Failed to destroy dest ft action\n"); + return err; +} + +static int mlx5_cmd_hws_create_flow_table(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft, + struct mlx5_flow_table_attr *ft_attr, + struct mlx5_flow_table *next_ft) +{ + struct mlx5hws_context *ctx = ns->fs_hws_context.hws_ctx; + struct mlx5hws_table_attr tbl_attr = {}; + struct mlx5hws_table *tbl; + int err; + + if (mlx5_fs_cmd_is_fw_term_table(ft)) { + err = mlx5_fs_cmd_get_fw_cmds()->create_flow_table(ns, ft, ft_attr, + next_ft); + if (err) + return err; + err = mlx5_fs_add_flow_table_dest_action(ns, ft); + if (err) + mlx5_fs_cmd_get_fw_cmds()->destroy_flow_table(ns, ft); + return err; + } + + if (ns->table_type != FS_FT_FDB) { + mlx5_core_err(ns->dev, "Table type %d not supported for HWS\n", + ns->table_type); + return -EOPNOTSUPP; + } + + tbl_attr.type = MLX5HWS_TABLE_TYPE_FDB; + tbl_attr.level = ft_attr->level; + tbl = mlx5hws_table_create(ctx, &tbl_attr); + if (!tbl) { + mlx5_core_err(ns->dev, "Failed creating hws flow_table\n"); + return -EINVAL; + } + + ft->fs_hws_table.hws_table = tbl; + ft->id = mlx5hws_table_get_id(tbl); + + if (next_ft) { + err = mlx5_fs_set_ft_default_miss(ns, ft, next_ft); + if (err) + goto destroy_table; + } + + ft->max_fte = INT_MAX; + + err = mlx5_fs_add_flow_table_dest_action(ns, ft); + if (err) + goto clear_ft_miss; + return 0; + +clear_ft_miss: + mlx5_fs_set_ft_default_miss(ns, ft, NULL); +destroy_table: + mlx5hws_table_destroy(tbl); + ft->fs_hws_table.hws_table = NULL; + return err; +} + +static int mlx5_cmd_hws_destroy_flow_table(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft) +{ + int err; + + err = mlx5_fs_del_flow_table_dest_action(ns, ft); + if (err) + mlx5_core_err(ns->dev, "Failed to remove dest action (%d)\n", err); + + if (mlx5_fs_cmd_is_fw_term_table(ft)) + return mlx5_fs_cmd_get_fw_cmds()->destroy_flow_table(ns, ft); + + err = mlx5_fs_set_ft_default_miss(ns, ft, NULL); + if (err) + mlx5_core_err(ns->dev, "Failed to disconnect next table (%d)\n", err); + + err = mlx5hws_table_destroy(ft->fs_hws_table.hws_table); + if (err) + mlx5_core_err(ns->dev, "Failed to destroy flow_table (%d)\n", err); + + return err; +} + +static int mlx5_cmd_hws_modify_flow_table(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft, + struct mlx5_flow_table *next_ft) +{ + if (mlx5_fs_cmd_is_fw_term_table(ft)) + return mlx5_fs_cmd_get_fw_cmds()->modify_flow_table(ns, ft, next_ft); + + return mlx5_fs_set_ft_default_miss(ns, ft, next_ft); +} + +static int mlx5_cmd_hws_update_root_ft(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft, + u32 underlay_qpn, + bool disconnect) +{ + return mlx5_fs_cmd_get_fw_cmds()->update_root_ft(ns, ft, underlay_qpn, + disconnect); +} + +static int mlx5_cmd_hws_create_flow_group(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft, u32 *in, + struct mlx5_flow_group *fg) +{ + struct mlx5hws_match_parameters mask; + struct mlx5hws_bwc_matcher *matcher; + u8 match_criteria_enable; + u32 priority; + + if (mlx5_fs_cmd_is_fw_term_table(ft)) + return mlx5_fs_cmd_get_fw_cmds()->create_flow_group(ns, ft, in, fg); + + mask.match_buf = MLX5_ADDR_OF(create_flow_group_in, in, match_criteria); + mask.match_sz = sizeof(fg->mask.match_criteria); + + match_criteria_enable = MLX5_GET(create_flow_group_in, in, + match_criteria_enable); + priority = MLX5_GET(create_flow_group_in, in, start_flow_index); + matcher = mlx5hws_bwc_matcher_create(ft->fs_hws_table.hws_table, + priority, match_criteria_enable, + &mask); + if (!matcher) { + mlx5_core_err(ns->dev, "Failed creating matcher\n"); + return -EINVAL; + } + + fg->fs_hws_matcher.matcher = matcher; + return 0; +} + +static int mlx5_cmd_hws_destroy_flow_group(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft, + struct mlx5_flow_group *fg) +{ + if (mlx5_fs_cmd_is_fw_term_table(ft)) + return mlx5_fs_cmd_get_fw_cmds()->destroy_flow_group(ns, ft, fg); + + return mlx5hws_bwc_matcher_destroy(fg->fs_hws_matcher.matcher); +} + +static struct mlx5hws_action * +mlx5_fs_get_dest_action_ft(struct mlx5_fs_hws_context *fs_ctx, + struct mlx5_flow_rule *dst) +{ + return xa_load(&fs_ctx->hws_pool.table_dests, dst->dest_attr.ft->id); +} + +static struct mlx5hws_action * +mlx5_fs_get_dest_action_table_num(struct mlx5_fs_hws_context *fs_ctx, + struct mlx5_flow_rule *dst) +{ + u32 table_num = dst->dest_attr.ft_num; + + return xa_load(&fs_ctx->hws_pool.table_dests, table_num); +} + +static struct mlx5hws_action * +mlx5_fs_create_dest_action_table_num(struct mlx5_fs_hws_context *fs_ctx, + struct mlx5_flow_rule *dst) +{ + u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED; + struct mlx5hws_context *ctx = fs_ctx->hws_ctx; + u32 table_num = dst->dest_attr.ft_num; + + return mlx5hws_action_create_dest_table_num(ctx, table_num, flags); +} + +static struct mlx5hws_action * +mlx5_fs_get_dest_action_vport(struct mlx5_fs_hws_context *fs_ctx, + struct mlx5_flow_rule *dst, + bool is_dest_type_uplink) +{ + u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED; + struct mlx5_flow_destination *dest_attr = &dst->dest_attr; + struct mlx5hws_context *ctx = fs_ctx->hws_ctx; + struct mlx5hws_action *dest; + struct xarray *dests_xa; + bool vhca_id_valid; + unsigned long idx; + u16 vport_num; + int err; + + vhca_id_valid = is_dest_type_uplink || + (dest_attr->vport.flags & MLX5_FLOW_DEST_VPORT_VHCA_ID); + vport_num = is_dest_type_uplink ? MLX5_VPORT_UPLINK : dest_attr->vport.num; + if (vhca_id_valid) { + dests_xa = &fs_ctx->hws_pool.vport_vhca_dests; + idx = (unsigned long)dest_attr->vport.vhca_id << 16 | vport_num; + } else { + dests_xa = &fs_ctx->hws_pool.vport_dests; + idx = vport_num; + } +dest_load: + dest = xa_load(dests_xa, idx); + if (dest) + return dest; + + dest = mlx5hws_action_create_dest_vport(ctx, vport_num, vhca_id_valid, + dest_attr->vport.vhca_id, flags); + + err = xa_insert(dests_xa, idx, dest, GFP_KERNEL); + if (err) { + mlx5hws_action_destroy(dest); + dest = NULL; + + if (err == -EBUSY) + /* xarray entry was already stored by another thread */ + goto dest_load; + } + + return dest; +} + +static struct mlx5hws_action * +mlx5_fs_create_dest_action_range(struct mlx5hws_context *ctx, + struct mlx5_flow_rule *dst) +{ + u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED; + struct mlx5_flow_destination *dest_attr = &dst->dest_attr; + + return mlx5hws_action_create_dest_match_range(ctx, + dest_attr->range.field, + dest_attr->range.hit_ft, + dest_attr->range.miss_ft, + dest_attr->range.min, + dest_attr->range.max, + flags); +} + +static struct mlx5hws_action * +mlx5_fs_create_action_dest_array(struct mlx5hws_context *ctx, + struct mlx5hws_action_dest_attr *dests, + u32 num_of_dests, bool ignore_flow_level, + u32 flow_source) +{ + u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED; + + return mlx5hws_action_create_dest_array(ctx, num_of_dests, dests, + ignore_flow_level, + flow_source, flags); +} + +static struct mlx5hws_action * +mlx5_fs_get_action_push_vlan(struct mlx5_fs_hws_context *fs_ctx) +{ + return fs_ctx->hws_pool.push_vlan_action; +} + +static u32 mlx5_fs_calc_vlan_hdr(struct mlx5_fs_vlan *vlan) +{ + u16 n_ethtype = vlan->ethtype; + u8 prio = vlan->prio; + u16 vid = vlan->vid; + + return (u32)n_ethtype << 16 | (u32)(prio) << 12 | (u32)vid; +} + +static struct mlx5hws_action * +mlx5_fs_get_action_pop_vlan(struct mlx5_fs_hws_context *fs_ctx) +{ + return fs_ctx->hws_pool.pop_vlan_action; +} + +static struct mlx5hws_action * +mlx5_fs_get_action_decap_tnl_l2_to_l2(struct mlx5_fs_hws_context *fs_ctx) +{ + return fs_ctx->hws_pool.decapl2_action; +} + +static struct mlx5hws_action * +mlx5_fs_get_dest_action_drop(struct mlx5_fs_hws_context *fs_ctx) +{ + return fs_ctx->hws_pool.drop_action; +} + +static struct mlx5hws_action * +mlx5_fs_get_action_tag(struct mlx5_fs_hws_context *fs_ctx) +{ + return fs_ctx->hws_pool.tag_action; +} + +static struct mlx5hws_action * +mlx5_fs_create_action_last(struct mlx5hws_context *ctx) +{ + u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED; + + return mlx5hws_action_create_last(ctx, flags); +} + +static void mlx5_fs_destroy_fs_action(struct mlx5_fs_hws_rule_action *fs_action) +{ + switch (mlx5hws_action_get_type(fs_action->action)) { + case MLX5HWS_ACTION_TYP_CTR: + mlx5_fc_put_hws_action(fs_action->counter); + break; + default: + mlx5hws_action_destroy(fs_action->action); + } +} + +static void +mlx5_fs_destroy_fs_actions(struct mlx5_fs_hws_rule_action **fs_actions, + int *num_fs_actions) +{ + int i; + + /* Free in reverse order to handle action dependencies */ + for (i = *num_fs_actions - 1; i >= 0; i--) + mlx5_fs_destroy_fs_action(*fs_actions + i); + *num_fs_actions = 0; + kfree(*fs_actions); + *fs_actions = NULL; +} + +/* Splits FTE's actions into cached, rule and destination actions. + * The cached and destination actions are saved on the fte hws rule. + * The rule actions are returned as a parameter, together with their count. + * We want to support a rule with 32 destinations, which means we need to + * account for 32 destinations plus usually a counter plus one more action + * for a multi-destination flow table. + * 32 is SW limitation for array size, keep. HWS limitation is 16M STEs per matcher + */ +#define MLX5_FLOW_CONTEXT_ACTION_MAX 34 +static int mlx5_fs_fte_get_hws_actions(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft, + struct mlx5_flow_group *group, + struct fs_fte *fte, + struct mlx5hws_rule_action **ractions) +{ + struct mlx5_flow_act *fte_action = &fte->act_dests.action; + struct mlx5_fs_hws_context *fs_ctx = &ns->fs_hws_context; + struct mlx5hws_action_dest_attr *dest_actions; + struct mlx5hws_context *ctx = fs_ctx->hws_ctx; + struct mlx5_fs_hws_rule_action *fs_actions; + struct mlx5_core_dev *dev = ns->dev; + struct mlx5hws_action *dest_action; + struct mlx5hws_action *tmp_action; + struct mlx5_fs_hws_pr *pr_data; + struct mlx5_fs_hws_mh *mh_data; + bool delay_encap_set = false; + struct mlx5_flow_rule *dst; + int num_dest_actions = 0; + int num_fs_actions = 0; + int num_actions = 0; + int err; + + *ractions = kcalloc(MLX5_FLOW_CONTEXT_ACTION_MAX, sizeof(**ractions), + GFP_KERNEL); + if (!*ractions) { + err = -ENOMEM; + goto out_err; + } + + fs_actions = kcalloc(MLX5_FLOW_CONTEXT_ACTION_MAX, + sizeof(*fs_actions), GFP_KERNEL); + if (!fs_actions) { + err = -ENOMEM; + goto free_actions_alloc; + } + + dest_actions = kcalloc(MLX5_FLOW_CONTEXT_ACTION_MAX, + sizeof(*dest_actions), GFP_KERNEL); + if (!dest_actions) { + err = -ENOMEM; + goto free_fs_actions_alloc; + } + + /* The order of the actions are must to be kept, only the following + * order is supported by HW steering: + * HWS: decap -> remove_hdr -> pop_vlan -> modify header -> push_vlan + * -> reformat (insert_hdr/encap) -> ctr -> tag -> aso + * -> drop -> FWD:tbl/vport/sampler/tbl_num/range -> dest_array -> last + */ + if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_DECAP) { + tmp_action = mlx5_fs_get_action_decap_tnl_l2_to_l2(fs_ctx); + if (!tmp_action) { + err = -ENOMEM; + goto free_dest_actions_alloc; + } + (*ractions)[num_actions++].action = tmp_action; + } + + if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT) { + int reformat_type = fte_action->pkt_reformat->reformat_type; + + if (fte_action->pkt_reformat->owner == MLX5_FLOW_RESOURCE_OWNER_FW) { + mlx5_core_err(dev, "FW-owned reformat can't be used in HWS rule\n"); + err = -EINVAL; + goto free_actions; + } + + if (reformat_type == MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2) { + pr_data = fte_action->pkt_reformat->fs_hws_action.pr_data; + (*ractions)[num_actions].reformat.offset = pr_data->offset; + (*ractions)[num_actions].reformat.hdr_idx = pr_data->hdr_idx; + (*ractions)[num_actions].reformat.data = pr_data->data; + (*ractions)[num_actions++].action = + fte_action->pkt_reformat->fs_hws_action.hws_action; + } else if (reformat_type == MLX5_REFORMAT_TYPE_REMOVE_HDR) { + (*ractions)[num_actions++].action = + fte_action->pkt_reformat->fs_hws_action.hws_action; + } else { + delay_encap_set = true; + } + } + + if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP) { + tmp_action = mlx5_fs_get_action_pop_vlan(fs_ctx); + if (!tmp_action) { + err = -ENOMEM; + goto free_actions; + } + (*ractions)[num_actions++].action = tmp_action; + } + + if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP_2) { + tmp_action = mlx5_fs_get_action_pop_vlan(fs_ctx); + if (!tmp_action) { + err = -ENOMEM; + goto free_actions; + } + (*ractions)[num_actions++].action = tmp_action; + } + + if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) { + mh_data = fte_action->modify_hdr->fs_hws_action.mh_data; + (*ractions)[num_actions].modify_header.offset = mh_data->offset; + (*ractions)[num_actions].modify_header.data = mh_data->data; + (*ractions)[num_actions++].action = + fte_action->modify_hdr->fs_hws_action.hws_action; + } + + if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH) { + tmp_action = mlx5_fs_get_action_push_vlan(fs_ctx); + if (!tmp_action) { + err = -ENOMEM; + goto free_actions; + } + (*ractions)[num_actions].push_vlan.vlan_hdr = + htonl(mlx5_fs_calc_vlan_hdr(&fte_action->vlan[0])); + (*ractions)[num_actions++].action = tmp_action; + } + + if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2) { + tmp_action = mlx5_fs_get_action_push_vlan(fs_ctx); + if (!tmp_action) { + err = -ENOMEM; + goto free_actions; + } + (*ractions)[num_actions].push_vlan.vlan_hdr = + htonl(mlx5_fs_calc_vlan_hdr(&fte_action->vlan[1])); + (*ractions)[num_actions++].action = tmp_action; + } + + if (delay_encap_set) { + pr_data = fte_action->pkt_reformat->fs_hws_action.pr_data; + (*ractions)[num_actions].reformat.offset = pr_data->offset; + (*ractions)[num_actions].reformat.data = pr_data->data; + (*ractions)[num_actions++].action = + fte_action->pkt_reformat->fs_hws_action.hws_action; + } + + if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) { + list_for_each_entry(dst, &fte->node.children, node.list) { + struct mlx5_fc *counter; + + if (dst->dest_attr.type != + MLX5_FLOW_DESTINATION_TYPE_COUNTER) + continue; + + if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) { + err = -EOPNOTSUPP; + goto free_actions; + } + + counter = dst->dest_attr.counter; + tmp_action = mlx5_fc_get_hws_action(ctx, counter); + if (!tmp_action) { + err = -EINVAL; + goto free_actions; + } + + (*ractions)[num_actions].counter.offset = + mlx5_fc_id(counter) - mlx5_fc_get_base_id(counter); + (*ractions)[num_actions++].action = tmp_action; + fs_actions[num_fs_actions].action = tmp_action; + fs_actions[num_fs_actions++].counter = counter; + } + } + + if (fte->act_dests.flow_context.flow_tag) { + if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) { + err = -EOPNOTSUPP; + goto free_actions; + } + tmp_action = mlx5_fs_get_action_tag(fs_ctx); + if (!tmp_action) { + err = -ENOMEM; + goto free_actions; + } + (*ractions)[num_actions].tag.value = fte->act_dests.flow_context.flow_tag; + (*ractions)[num_actions++].action = tmp_action; + } + + if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_EXECUTE_ASO) { + err = -EOPNOTSUPP; + goto free_actions; + } + + if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_DROP) { + dest_action = mlx5_fs_get_dest_action_drop(fs_ctx); + if (!dest_action) { + err = -ENOMEM; + goto free_actions; + } + dest_actions[num_dest_actions++].dest = dest_action; + } + + if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) { + list_for_each_entry(dst, &fte->node.children, node.list) { + struct mlx5_flow_destination *attr = &dst->dest_attr; + bool type_uplink = + attr->type == MLX5_FLOW_DESTINATION_TYPE_UPLINK; + + if (num_fs_actions == MLX5_FLOW_CONTEXT_ACTION_MAX || + num_dest_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) { + err = -EOPNOTSUPP; + goto free_actions; + } + if (attr->type == MLX5_FLOW_DESTINATION_TYPE_COUNTER) + continue; + + switch (attr->type) { + case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE: + dest_action = mlx5_fs_get_dest_action_ft(fs_ctx, dst); + break; + case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE_NUM: + dest_action = mlx5_fs_get_dest_action_table_num(fs_ctx, + dst); + if (dest_action) + break; + dest_action = mlx5_fs_create_dest_action_table_num(fs_ctx, + dst); + fs_actions[num_fs_actions++].action = dest_action; + break; + case MLX5_FLOW_DESTINATION_TYPE_RANGE: + dest_action = mlx5_fs_create_dest_action_range(ctx, dst); + fs_actions[num_fs_actions++].action = dest_action; + break; + case MLX5_FLOW_DESTINATION_TYPE_UPLINK: + case MLX5_FLOW_DESTINATION_TYPE_VPORT: + dest_action = mlx5_fs_get_dest_action_vport(fs_ctx, dst, + type_uplink); + break; + default: + err = -EOPNOTSUPP; + goto free_actions; + } + if (!dest_action) { + err = -ENOMEM; + goto free_actions; + } + dest_actions[num_dest_actions++].dest = dest_action; + } + } + + if (num_dest_actions == 1) { + if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) { + err = -EOPNOTSUPP; + goto free_actions; + } + (*ractions)[num_actions++].action = dest_actions->dest; + } else if (num_dest_actions > 1) { + u32 flow_source = fte->act_dests.flow_context.flow_source; + bool ignore_flow_level; + + if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX || + num_fs_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) { + err = -EOPNOTSUPP; + goto free_actions; + } + ignore_flow_level = + !!(fte_action->flags & FLOW_ACT_IGNORE_FLOW_LEVEL); + tmp_action = mlx5_fs_create_action_dest_array(ctx, dest_actions, + num_dest_actions, + ignore_flow_level, + flow_source); + if (!tmp_action) { + err = -EOPNOTSUPP; + goto free_actions; + } + fs_actions[num_fs_actions++].action = tmp_action; + (*ractions)[num_actions++].action = tmp_action; + } + + if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX || + num_fs_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) { + err = -EOPNOTSUPP; + goto free_actions; + } + + tmp_action = mlx5_fs_create_action_last(ctx); + if (!tmp_action) { + err = -ENOMEM; + goto free_actions; + } + fs_actions[num_fs_actions++].action = tmp_action; + (*ractions)[num_actions++].action = tmp_action; + + kfree(dest_actions); + + /* Actions created specifically for this rule will be destroyed + * once rule is deleted. + */ + fte->fs_hws_rule.num_fs_actions = num_fs_actions; + fte->fs_hws_rule.hws_fs_actions = fs_actions; + + return 0; + +free_actions: + mlx5_fs_destroy_fs_actions(&fs_actions, &num_fs_actions); +free_dest_actions_alloc: + kfree(dest_actions); +free_fs_actions_alloc: + kfree(fs_actions); +free_actions_alloc: + kfree(*ractions); + *ractions = NULL; +out_err: + return err; +} + +static int mlx5_cmd_hws_create_fte(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft, + struct mlx5_flow_group *group, + struct fs_fte *fte) +{ + struct mlx5hws_match_parameters params; + struct mlx5hws_rule_action *ractions; + struct mlx5hws_bwc_rule *rule; + int err = 0; + + if (mlx5_fs_cmd_is_fw_term_table(ft)) { + /* Packet reformat on terminamtion table not supported yet */ + if (fte->act_dests.action.action & + MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT) + return -EOPNOTSUPP; + return mlx5_fs_cmd_get_fw_cmds()->create_fte(ns, ft, group, fte); + } + + err = mlx5_fs_fte_get_hws_actions(ns, ft, group, fte, &ractions); + if (err) + goto out_err; + + params.match_sz = sizeof(fte->val); + params.match_buf = fte->val; + + rule = mlx5hws_bwc_rule_create(group->fs_hws_matcher.matcher, ¶ms, + fte->act_dests.flow_context.flow_source, + ractions); + kfree(ractions); + if (!rule) { + err = -EINVAL; + goto free_actions; + } + + fte->fs_hws_rule.bwc_rule = rule; + return 0; + +free_actions: + mlx5_fs_destroy_fs_actions(&fte->fs_hws_rule.hws_fs_actions, + &fte->fs_hws_rule.num_fs_actions); +out_err: + mlx5_core_err(ns->dev, "Failed to create hws rule err(%d)\n", err); + return err; +} + +static int mlx5_cmd_hws_delete_fte(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft, + struct fs_fte *fte) +{ + struct mlx5_fs_hws_rule *rule = &fte->fs_hws_rule; + int err; + + if (mlx5_fs_cmd_is_fw_term_table(ft)) + return mlx5_fs_cmd_get_fw_cmds()->delete_fte(ns, ft, fte); + + err = mlx5hws_bwc_rule_destroy(rule->bwc_rule); + rule->bwc_rule = NULL; + + mlx5_fs_destroy_fs_actions(&rule->hws_fs_actions, &rule->num_fs_actions); + + return err; +} + +static int mlx5_cmd_hws_update_fte(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft, + struct mlx5_flow_group *group, + int modify_mask, + struct fs_fte *fte) +{ + int allowed_mask = BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_ACTION) | + BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_DESTINATION_LIST) | + BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_FLOW_COUNTERS); + struct mlx5_fs_hws_rule_action *saved_hws_fs_actions; + struct mlx5hws_rule_action *ractions; + int saved_num_fs_actions; + int ret; + + if (mlx5_fs_cmd_is_fw_term_table(ft)) + return mlx5_fs_cmd_get_fw_cmds()->update_fte(ns, ft, group, + modify_mask, fte); + + if ((modify_mask & ~allowed_mask) != 0) + return -EINVAL; + + saved_hws_fs_actions = fte->fs_hws_rule.hws_fs_actions; + saved_num_fs_actions = fte->fs_hws_rule.num_fs_actions; + + ret = mlx5_fs_fte_get_hws_actions(ns, ft, group, fte, &ractions); + if (ret) + return ret; + + ret = mlx5hws_bwc_rule_action_update(fte->fs_hws_rule.bwc_rule, ractions); + kfree(ractions); + if (ret) + goto restore_actions; + + mlx5_fs_destroy_fs_actions(&saved_hws_fs_actions, &saved_num_fs_actions); + return ret; + +restore_actions: + mlx5_fs_destroy_fs_actions(&fte->fs_hws_rule.hws_fs_actions, + &fte->fs_hws_rule.num_fs_actions); + fte->fs_hws_rule.hws_fs_actions = saved_hws_fs_actions; + fte->fs_hws_rule.num_fs_actions = saved_num_fs_actions; + return ret; +} + +static struct mlx5hws_action * +mlx5_fs_create_action_remove_header_vlan(struct mlx5hws_context *ctx) +{ + u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED; + struct mlx5hws_action_remove_header_attr remove_hdr_vlan = {}; + + /* MAC anchor not supported in HWS reformat, use VLAN anchor */ + remove_hdr_vlan.anchor = MLX5_REFORMAT_CONTEXT_ANCHOR_VLAN_START; + remove_hdr_vlan.offset = 0; + remove_hdr_vlan.size = sizeof(struct vlan_hdr); + return mlx5hws_action_create_remove_header(ctx, &remove_hdr_vlan, flags); +} + +static struct mlx5hws_action * +mlx5_fs_get_action_remove_header_vlan(struct mlx5_fs_hws_context *fs_ctx, + struct mlx5_pkt_reformat_params *params) +{ + if (!params || + params->param_0 != MLX5_REFORMAT_CONTEXT_ANCHOR_MAC_START || + params->param_1 != offsetof(struct vlan_ethhdr, h_vlan_proto) || + params->size != sizeof(struct vlan_hdr)) + return NULL; + + return fs_ctx->hws_pool.remove_hdr_vlan_action; +} + +static int +mlx5_fs_verify_insert_header_params(struct mlx5_core_dev *mdev, + struct mlx5_pkt_reformat_params *params) +{ + if ((!params->data && params->size) || (params->data && !params->size) || + MLX5_CAP_GEN_2(mdev, max_reformat_insert_size) < params->size || + MLX5_CAP_GEN_2(mdev, max_reformat_insert_offset) < params->param_1) { + mlx5_core_err(mdev, "Invalid reformat params for INSERT_HDR\n"); + return -EINVAL; + } + if (params->param_0 != MLX5_FS_INSERT_HDR_VLAN_ANCHOR || + params->param_1 != MLX5_FS_INSERT_HDR_VLAN_OFFSET || + params->size != MLX5_FS_INSERT_HDR_VLAN_SIZE) { + mlx5_core_err(mdev, "Only vlan insert header supported\n"); + return -EOPNOTSUPP; + } + return 0; +} + +static int +mlx5_fs_verify_encap_decap_params(struct mlx5_core_dev *dev, + struct mlx5_pkt_reformat_params *params) +{ + if (params->param_0 || params->param_1) { + mlx5_core_err(dev, "Invalid reformat params\n"); + return -EINVAL; + } + return 0; +} + +static struct mlx5_fs_pool * +mlx5_fs_get_pr_encap_pool(struct mlx5_core_dev *dev, struct xarray *pr_pools, + enum mlx5hws_action_type reformat_type, size_t size) +{ + struct mlx5_fs_pool *pr_pool; + unsigned long index = size; + int err; + + pr_pool = xa_load(pr_pools, index); + if (pr_pool) + return pr_pool; + + pr_pool = kzalloc(sizeof(*pr_pool), GFP_KERNEL); + if (!pr_pool) + return ERR_PTR(-ENOMEM); + err = mlx5_fs_hws_pr_pool_init(pr_pool, dev, size, reformat_type); + if (err) + goto free_pr_pool; + err = xa_insert(pr_pools, index, pr_pool, GFP_KERNEL); + if (err) + goto cleanup_pr_pool; + return pr_pool; + +cleanup_pr_pool: + mlx5_fs_hws_pr_pool_cleanup(pr_pool); +free_pr_pool: + kfree(pr_pool); + return ERR_PTR(err); +} + +static void +mlx5_fs_destroy_pr_pool(struct mlx5_fs_pool *pool, struct xarray *pr_pools, + unsigned long index) +{ + xa_erase(pr_pools, index); + mlx5_fs_hws_pr_pool_cleanup(pool); + kfree(pool); +} + +static int +mlx5_cmd_hws_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns, + struct mlx5_pkt_reformat_params *params, + enum mlx5_flow_namespace_type namespace, + struct mlx5_pkt_reformat *pkt_reformat) +{ + struct mlx5_fs_hws_context *fs_ctx = &ns->fs_hws_context; + struct mlx5_fs_hws_actions_pool *hws_pool; + struct mlx5hws_action *hws_action = NULL; + struct mlx5_fs_hws_pr *pr_data = NULL; + struct mlx5_fs_pool *pr_pool = NULL; + struct mlx5_core_dev *dev = ns->dev; + u8 hdr_idx = 0; + int err; + + if (!params) + return -EINVAL; + + hws_pool = &fs_ctx->hws_pool; + + switch (params->type) { + case MLX5_REFORMAT_TYPE_L2_TO_VXLAN: + case MLX5_REFORMAT_TYPE_L2_TO_NVGRE: + case MLX5_REFORMAT_TYPE_L2_TO_L2_TUNNEL: + if (mlx5_fs_verify_encap_decap_params(dev, params)) + return -EINVAL; + pr_pool = mlx5_fs_get_pr_encap_pool(dev, &hws_pool->el2tol2tnl_pools, + MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L2, + params->size); + if (IS_ERR(pr_pool)) + return PTR_ERR(pr_pool); + break; + case MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL: + if (mlx5_fs_verify_encap_decap_params(dev, params)) + return -EINVAL; + pr_pool = mlx5_fs_get_pr_encap_pool(dev, &hws_pool->el2tol3tnl_pools, + MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L3, + params->size); + if (IS_ERR(pr_pool)) + return PTR_ERR(pr_pool); + break; + case MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2: + if (mlx5_fs_verify_encap_decap_params(dev, params)) + return -EINVAL; + pr_pool = &hws_pool->dl3tnltol2_pool; + hdr_idx = params->size == ETH_HLEN ? + MLX5_FS_DL3TNLTOL2_MAC_HDR_IDX : + MLX5_FS_DL3TNLTOL2_MAC_VLAN_HDR_IDX; + break; + case MLX5_REFORMAT_TYPE_INSERT_HDR: + err = mlx5_fs_verify_insert_header_params(dev, params); + if (err) + return err; + pr_pool = &hws_pool->insert_hdr_pool; + break; + case MLX5_REFORMAT_TYPE_REMOVE_HDR: + hws_action = mlx5_fs_get_action_remove_header_vlan(fs_ctx, params); + if (!hws_action) + mlx5_core_err(dev, "Only vlan remove header supported\n"); + break; + default: + mlx5_core_err(ns->dev, "Packet-reformat not supported(%d)\n", + params->type); + return -EOPNOTSUPP; + } + + if (pr_pool) { + pr_data = mlx5_fs_hws_pr_pool_acquire_pr(pr_pool); + if (IS_ERR_OR_NULL(pr_data)) + return !pr_data ? -EINVAL : PTR_ERR(pr_data); + hws_action = pr_data->bulk->hws_action; + if (!hws_action) { + mlx5_core_err(dev, + "Failed allocating packet-reformat action\n"); + err = -EINVAL; + goto release_pr; + } + pr_data->data = kmemdup(params->data, params->size, GFP_KERNEL); + if (!pr_data->data) { + err = -ENOMEM; + goto release_pr; + } + pr_data->hdr_idx = hdr_idx; + pr_data->data_size = params->size; + pkt_reformat->fs_hws_action.pr_data = pr_data; + } + + pkt_reformat->owner = MLX5_FLOW_RESOURCE_OWNER_SW; + pkt_reformat->fs_hws_action.hws_action = hws_action; + return 0; + +release_pr: + if (pr_pool && pr_data) + mlx5_fs_hws_pr_pool_release_pr(pr_pool, pr_data); + return err; +} + +static void mlx5_cmd_hws_packet_reformat_dealloc(struct mlx5_flow_root_namespace *ns, + struct mlx5_pkt_reformat *pkt_reformat) +{ + struct mlx5_fs_hws_actions_pool *hws_pool = &ns->fs_hws_context.hws_pool; + struct mlx5_core_dev *dev = ns->dev; + struct mlx5_fs_hws_pr *pr_data; + struct mlx5_fs_pool *pr_pool; + + if (pkt_reformat->reformat_type == MLX5_REFORMAT_TYPE_REMOVE_HDR) + return; + + if (!pkt_reformat->fs_hws_action.pr_data) { + mlx5_core_err(ns->dev, "Failed release packet-reformat\n"); + return; + } + pr_data = pkt_reformat->fs_hws_action.pr_data; + + switch (pkt_reformat->reformat_type) { + case MLX5_REFORMAT_TYPE_L2_TO_VXLAN: + case MLX5_REFORMAT_TYPE_L2_TO_NVGRE: + case MLX5_REFORMAT_TYPE_L2_TO_L2_TUNNEL: + pr_pool = mlx5_fs_get_pr_encap_pool(dev, &hws_pool->el2tol2tnl_pools, + MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L2, + pr_data->data_size); + break; + case MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL: + pr_pool = mlx5_fs_get_pr_encap_pool(dev, &hws_pool->el2tol2tnl_pools, + MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L2, + pr_data->data_size); + break; + case MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2: + pr_pool = &hws_pool->dl3tnltol2_pool; + break; + case MLX5_REFORMAT_TYPE_INSERT_HDR: + pr_pool = &hws_pool->insert_hdr_pool; + break; + default: + mlx5_core_err(ns->dev, "Unknown packet-reformat type\n"); + return; + } + if (!pkt_reformat->fs_hws_action.pr_data || IS_ERR(pr_pool)) { + mlx5_core_err(ns->dev, "Failed release packet-reformat\n"); + return; + } + kfree(pr_data->data); + mlx5_fs_hws_pr_pool_release_pr(pr_pool, pr_data); + pkt_reformat->fs_hws_action.pr_data = NULL; +} + +static struct mlx5_fs_pool * +mlx5_fs_create_mh_pool(struct mlx5_core_dev *dev, + struct mlx5hws_action_mh_pattern *pattern, + struct xarray *mh_pools, unsigned long index) +{ + struct mlx5_fs_pool *pool; + int err; + + pool = kzalloc(sizeof(*pool), GFP_KERNEL); + if (!pool) + return ERR_PTR(-ENOMEM); + err = mlx5_fs_hws_mh_pool_init(pool, dev, pattern); + if (err) + goto free_pool; + err = xa_insert(mh_pools, index, pool, GFP_KERNEL); + if (err) + goto cleanup_pool; + return pool; + +cleanup_pool: + mlx5_fs_hws_mh_pool_cleanup(pool); +free_pool: + kfree(pool); + return ERR_PTR(err); +} + +static void +mlx5_fs_destroy_mh_pool(struct mlx5_fs_pool *pool, struct xarray *mh_pools, + unsigned long index) +{ + xa_erase(mh_pools, index); + mlx5_fs_hws_mh_pool_cleanup(pool); + kfree(pool); +} + +static int mlx5_cmd_hws_modify_header_alloc(struct mlx5_flow_root_namespace *ns, + u8 namespace, u8 num_actions, + void *modify_actions, + struct mlx5_modify_hdr *modify_hdr) +{ + struct mlx5_fs_hws_actions_pool *hws_pool = &ns->fs_hws_context.hws_pool; + struct mlx5hws_action_mh_pattern pattern = {}; + struct mlx5_fs_hws_mh *mh_data = NULL; + struct mlx5hws_action *hws_action; + struct mlx5_fs_pool *pool; + unsigned long i, cnt = 0; + bool known_pattern; + int err; + + pattern.sz = MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto) * num_actions; + pattern.data = modify_actions; + + known_pattern = false; + xa_for_each(&hws_pool->mh_pools, i, pool) { + if (mlx5_fs_hws_mh_pool_match(pool, &pattern)) { + known_pattern = true; + break; + } + cnt++; + } + + if (!known_pattern) { + pool = mlx5_fs_create_mh_pool(ns->dev, &pattern, + &hws_pool->mh_pools, cnt); + if (IS_ERR(pool)) + return PTR_ERR(pool); + } + mh_data = mlx5_fs_hws_mh_pool_acquire_mh(pool); + if (IS_ERR(mh_data)) { + err = PTR_ERR(mh_data); + goto destroy_pool; + } + hws_action = mh_data->bulk->hws_action; + mh_data->data = kmemdup(pattern.data, pattern.sz, GFP_KERNEL); + if (!mh_data->data) { + err = -ENOMEM; + goto release_mh; + } + modify_hdr->fs_hws_action.mh_data = mh_data; + modify_hdr->fs_hws_action.fs_pool = pool; + modify_hdr->owner = MLX5_FLOW_RESOURCE_OWNER_SW; + modify_hdr->fs_hws_action.hws_action = hws_action; + + return 0; + +release_mh: + mlx5_fs_hws_mh_pool_release_mh(pool, mh_data); +destroy_pool: + if (!known_pattern) + mlx5_fs_destroy_mh_pool(pool, &hws_pool->mh_pools, cnt); + return err; +} + +static void mlx5_cmd_hws_modify_header_dealloc(struct mlx5_flow_root_namespace *ns, + struct mlx5_modify_hdr *modify_hdr) +{ + struct mlx5_fs_hws_mh *mh_data; + struct mlx5_fs_pool *pool; + + if (!modify_hdr->fs_hws_action.fs_pool || !modify_hdr->fs_hws_action.mh_data) { + mlx5_core_err(ns->dev, "Failed release modify-header\n"); + return; + } + + mh_data = modify_hdr->fs_hws_action.mh_data; + kfree(mh_data->data); + pool = modify_hdr->fs_hws_action.fs_pool; + mlx5_fs_hws_mh_pool_release_mh(pool, mh_data); + modify_hdr->fs_hws_action.mh_data = NULL; +} + +static int mlx5_cmd_hws_create_match_definer(struct mlx5_flow_root_namespace *ns, + u16 format_id, u32 *match_mask) +{ + return -EOPNOTSUPP; +} + +static int mlx5_cmd_hws_destroy_match_definer(struct mlx5_flow_root_namespace *ns, + int definer_id) +{ + return -EOPNOTSUPP; +} + +static u32 mlx5_cmd_hws_get_capabilities(struct mlx5_flow_root_namespace *ns, + enum fs_flow_table_type ft_type) +{ + if (ft_type != FS_FT_FDB) + return 0; + + return MLX5_FLOW_STEERING_CAP_VLAN_PUSH_ON_RX | + MLX5_FLOW_STEERING_CAP_VLAN_POP_ON_TX | + MLX5_FLOW_STEERING_CAP_MATCH_RANGES; +} + +bool mlx5_fs_hws_is_supported(struct mlx5_core_dev *dev) +{ + return mlx5hws_is_supported(dev); +} + +static const struct mlx5_flow_cmds mlx5_flow_cmds_hws = { + .create_flow_table = mlx5_cmd_hws_create_flow_table, + .destroy_flow_table = mlx5_cmd_hws_destroy_flow_table, + .modify_flow_table = mlx5_cmd_hws_modify_flow_table, + .update_root_ft = mlx5_cmd_hws_update_root_ft, + .create_flow_group = mlx5_cmd_hws_create_flow_group, + .destroy_flow_group = mlx5_cmd_hws_destroy_flow_group, + .create_fte = mlx5_cmd_hws_create_fte, + .delete_fte = mlx5_cmd_hws_delete_fte, + .update_fte = mlx5_cmd_hws_update_fte, + .packet_reformat_alloc = mlx5_cmd_hws_packet_reformat_alloc, + .packet_reformat_dealloc = mlx5_cmd_hws_packet_reformat_dealloc, + .modify_header_alloc = mlx5_cmd_hws_modify_header_alloc, + .modify_header_dealloc = mlx5_cmd_hws_modify_header_dealloc, + .create_match_definer = mlx5_cmd_hws_create_match_definer, + .destroy_match_definer = mlx5_cmd_hws_destroy_match_definer, + .create_ns = mlx5_cmd_hws_create_ns, + .destroy_ns = mlx5_cmd_hws_destroy_ns, + .set_peer = mlx5_cmd_hws_set_peer, + .get_capabilities = mlx5_cmd_hws_get_capabilities, +}; + +const struct mlx5_flow_cmds *mlx5_fs_cmd_get_hws_cmds(void) +{ + return &mlx5_flow_cmds_hws; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.h new file mode 100644 index 000000000000..cbddb72d4362 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.h @@ -0,0 +1,80 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2025 NVIDIA Corporation & Affiliates */ + +#ifndef _MLX5_FS_HWS_ +#define _MLX5_FS_HWS_ + +#include "mlx5hws.h" +#include "fs_hws_pools.h" + +struct mlx5_fs_hws_actions_pool { + struct mlx5hws_action *tag_action; + struct mlx5hws_action *pop_vlan_action; + struct mlx5hws_action *push_vlan_action; + struct mlx5hws_action *drop_action; + struct mlx5hws_action *decapl2_action; + struct mlx5hws_action *remove_hdr_vlan_action; + struct mlx5_fs_pool insert_hdr_pool; + struct mlx5_fs_pool dl3tnltol2_pool; + struct xarray el2tol3tnl_pools; + struct xarray el2tol2tnl_pools; + struct xarray mh_pools; + struct xarray table_dests; + struct xarray vport_vhca_dests; + struct xarray vport_dests; +}; + +struct mlx5_fs_hws_context { + struct mlx5hws_context *hws_ctx; + struct mlx5_fs_hws_actions_pool hws_pool; +}; + +struct mlx5_fs_hws_table { + struct mlx5hws_table *hws_table; + bool miss_ft_set; +}; + +struct mlx5_fs_hws_action { + struct mlx5hws_action *hws_action; + struct mlx5_fs_pool *fs_pool; + struct mlx5_fs_hws_pr *pr_data; + struct mlx5_fs_hws_mh *mh_data; +}; + +struct mlx5_fs_hws_matcher { + struct mlx5hws_bwc_matcher *matcher; +}; + +struct mlx5_fs_hws_rule_action { + struct mlx5hws_action *action; + union { + struct mlx5_fc *counter; + }; +}; + +struct mlx5_fs_hws_rule { + struct mlx5hws_bwc_rule *bwc_rule; + struct mlx5_fs_hws_rule_action *hws_fs_actions; + int num_fs_actions; +}; + +#ifdef CONFIG_MLX5_HW_STEERING + +bool mlx5_fs_hws_is_supported(struct mlx5_core_dev *dev); + +const struct mlx5_flow_cmds *mlx5_fs_cmd_get_hws_cmds(void); + +#else + +static inline bool mlx5_fs_hws_is_supported(struct mlx5_core_dev *dev) +{ + return false; +} + +static inline const struct mlx5_flow_cmds *mlx5_fs_cmd_get_hws_cmds(void) +{ + return NULL; +} + +#endif /* CONFIG_MLX5_HWS_STEERING */ +#endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws_pools.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws_pools.c new file mode 100644 index 000000000000..2ae4ac62b0e2 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws_pools.c @@ -0,0 +1,450 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2025 NVIDIA Corporation & Affiliates */ + +#include <mlx5_core.h> +#include "fs_hws_pools.h" + +#define MLX5_FS_HWS_DEFAULT_BULK_LEN 65536 +#define MLX5_FS_HWS_POOL_MAX_THRESHOLD BIT(18) +#define MLX5_FS_HWS_POOL_USED_BUFF_RATIO 10 + +static struct mlx5hws_action * +mlx5_fs_dl3tnltol2_bulk_action_create(struct mlx5hws_context *ctx) +{ + struct mlx5hws_action_reformat_header reformat_hdr[2] = {}; + u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB; + enum mlx5hws_action_type reformat_type; + u32 log_bulk_size; + + reformat_type = MLX5HWS_ACTION_TYP_REFORMAT_TNL_L3_TO_L2; + reformat_hdr[MLX5_FS_DL3TNLTOL2_MAC_HDR_IDX].sz = ETH_HLEN; + reformat_hdr[MLX5_FS_DL3TNLTOL2_MAC_VLAN_HDR_IDX].sz = ETH_HLEN + VLAN_HLEN; + + log_bulk_size = ilog2(MLX5_FS_HWS_DEFAULT_BULK_LEN); + return mlx5hws_action_create_reformat(ctx, reformat_type, 2, + reformat_hdr, log_bulk_size, flags); +} + +static struct mlx5hws_action * +mlx5_fs_el2tol3tnl_bulk_action_create(struct mlx5hws_context *ctx, size_t data_size) +{ + struct mlx5hws_action_reformat_header reformat_hdr = {}; + u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB; + enum mlx5hws_action_type reformat_type; + u32 log_bulk_size; + + reformat_type = MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L3; + reformat_hdr.sz = data_size; + + log_bulk_size = ilog2(MLX5_FS_HWS_DEFAULT_BULK_LEN); + return mlx5hws_action_create_reformat(ctx, reformat_type, 1, + &reformat_hdr, log_bulk_size, flags); +} + +static struct mlx5hws_action * +mlx5_fs_el2tol2tnl_bulk_action_create(struct mlx5hws_context *ctx, size_t data_size) +{ + struct mlx5hws_action_reformat_header reformat_hdr = {}; + u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB; + enum mlx5hws_action_type reformat_type; + u32 log_bulk_size; + + reformat_type = MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L2; + reformat_hdr.sz = data_size; + + log_bulk_size = ilog2(MLX5_FS_HWS_DEFAULT_BULK_LEN); + return mlx5hws_action_create_reformat(ctx, reformat_type, 1, + &reformat_hdr, log_bulk_size, flags); +} + +static struct mlx5hws_action * +mlx5_fs_insert_hdr_bulk_action_create(struct mlx5hws_context *ctx) +{ + struct mlx5hws_action_insert_header insert_hdr = {}; + u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB; + u32 log_bulk_size; + + log_bulk_size = ilog2(MLX5_FS_HWS_DEFAULT_BULK_LEN); + insert_hdr.hdr.sz = MLX5_FS_INSERT_HDR_VLAN_SIZE; + insert_hdr.anchor = MLX5_FS_INSERT_HDR_VLAN_ANCHOR; + insert_hdr.offset = MLX5_FS_INSERT_HDR_VLAN_OFFSET; + + return mlx5hws_action_create_insert_header(ctx, 1, &insert_hdr, + log_bulk_size, flags); +} + +static struct mlx5hws_action * +mlx5_fs_pr_bulk_action_create(struct mlx5_core_dev *dev, + struct mlx5_fs_hws_pr_pool_ctx *pr_pool_ctx) +{ + struct mlx5_flow_root_namespace *root_ns; + struct mlx5hws_context *ctx; + size_t encap_data_size; + + root_ns = mlx5_get_root_namespace(dev, MLX5_FLOW_NAMESPACE_FDB); + if (!root_ns || root_ns->mode != MLX5_FLOW_STEERING_MODE_HMFS) + return NULL; + + ctx = root_ns->fs_hws_context.hws_ctx; + if (!ctx) + return NULL; + + encap_data_size = pr_pool_ctx->encap_data_size; + switch (pr_pool_ctx->reformat_type) { + case MLX5HWS_ACTION_TYP_REFORMAT_TNL_L3_TO_L2: + return mlx5_fs_dl3tnltol2_bulk_action_create(ctx); + case MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L3: + return mlx5_fs_el2tol3tnl_bulk_action_create(ctx, encap_data_size); + case MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L2: + return mlx5_fs_el2tol2tnl_bulk_action_create(ctx, encap_data_size); + case MLX5HWS_ACTION_TYP_INSERT_HEADER: + return mlx5_fs_insert_hdr_bulk_action_create(ctx); + default: + return NULL; + } + return NULL; +} + +static struct mlx5_fs_bulk * +mlx5_fs_hws_pr_bulk_create(struct mlx5_core_dev *dev, void *pool_ctx) +{ + struct mlx5_fs_hws_pr_pool_ctx *pr_pool_ctx; + struct mlx5_fs_hws_pr_bulk *pr_bulk; + int bulk_len; + int i; + + if (!pool_ctx) + return NULL; + pr_pool_ctx = pool_ctx; + bulk_len = MLX5_FS_HWS_DEFAULT_BULK_LEN; + pr_bulk = kvzalloc(struct_size(pr_bulk, prs_data, bulk_len), GFP_KERNEL); + if (!pr_bulk) + return NULL; + + if (mlx5_fs_bulk_init(dev, &pr_bulk->fs_bulk, bulk_len)) + goto free_pr_bulk; + + for (i = 0; i < bulk_len; i++) { + pr_bulk->prs_data[i].bulk = pr_bulk; + pr_bulk->prs_data[i].offset = i; + } + + pr_bulk->hws_action = mlx5_fs_pr_bulk_action_create(dev, pr_pool_ctx); + if (!pr_bulk->hws_action) + goto cleanup_fs_bulk; + + return &pr_bulk->fs_bulk; + +cleanup_fs_bulk: + mlx5_fs_bulk_cleanup(&pr_bulk->fs_bulk); +free_pr_bulk: + kvfree(pr_bulk); + return NULL; +} + +static int +mlx5_fs_hws_pr_bulk_destroy(struct mlx5_core_dev *dev, struct mlx5_fs_bulk *fs_bulk) +{ + struct mlx5_fs_hws_pr_bulk *pr_bulk; + + pr_bulk = container_of(fs_bulk, struct mlx5_fs_hws_pr_bulk, fs_bulk); + if (mlx5_fs_bulk_get_free_amount(fs_bulk) < fs_bulk->bulk_len) { + mlx5_core_err(dev, "Freeing bulk before all reformats were released\n"); + return -EBUSY; + } + + mlx5hws_action_destroy(pr_bulk->hws_action); + mlx5_fs_bulk_cleanup(fs_bulk); + kvfree(pr_bulk); + + return 0; +} + +static void mlx5_hws_pool_update_threshold(struct mlx5_fs_pool *hws_pool) +{ + hws_pool->threshold = min_t(int, MLX5_FS_HWS_POOL_MAX_THRESHOLD, + hws_pool->used_units / MLX5_FS_HWS_POOL_USED_BUFF_RATIO); +} + +static const struct mlx5_fs_pool_ops mlx5_fs_hws_pr_pool_ops = { + .bulk_create = mlx5_fs_hws_pr_bulk_create, + .bulk_destroy = mlx5_fs_hws_pr_bulk_destroy, + .update_threshold = mlx5_hws_pool_update_threshold, +}; + +int mlx5_fs_hws_pr_pool_init(struct mlx5_fs_pool *pr_pool, + struct mlx5_core_dev *dev, size_t encap_data_size, + enum mlx5hws_action_type reformat_type) +{ + struct mlx5_fs_hws_pr_pool_ctx *pr_pool_ctx; + + if (reformat_type != MLX5HWS_ACTION_TYP_INSERT_HEADER && + reformat_type != MLX5HWS_ACTION_TYP_REFORMAT_TNL_L3_TO_L2 && + reformat_type != MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L3 && + reformat_type != MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L2) + return -EOPNOTSUPP; + + pr_pool_ctx = kzalloc(sizeof(*pr_pool_ctx), GFP_KERNEL); + if (!pr_pool_ctx) + return -ENOMEM; + pr_pool_ctx->reformat_type = reformat_type; + pr_pool_ctx->encap_data_size = encap_data_size; + mlx5_fs_pool_init(pr_pool, dev, &mlx5_fs_hws_pr_pool_ops, pr_pool_ctx); + return 0; +} + +void mlx5_fs_hws_pr_pool_cleanup(struct mlx5_fs_pool *pr_pool) +{ + struct mlx5_fs_hws_pr_pool_ctx *pr_pool_ctx; + + mlx5_fs_pool_cleanup(pr_pool); + pr_pool_ctx = pr_pool->pool_ctx; + if (!pr_pool_ctx) + return; + kfree(pr_pool_ctx); +} + +struct mlx5_fs_hws_pr * +mlx5_fs_hws_pr_pool_acquire_pr(struct mlx5_fs_pool *pr_pool) +{ + struct mlx5_fs_pool_index pool_index = {}; + struct mlx5_fs_hws_pr_bulk *pr_bulk; + int err; + + err = mlx5_fs_pool_acquire_index(pr_pool, &pool_index); + if (err) + return ERR_PTR(err); + pr_bulk = container_of(pool_index.fs_bulk, struct mlx5_fs_hws_pr_bulk, + fs_bulk); + return &pr_bulk->prs_data[pool_index.index]; +} + +void mlx5_fs_hws_pr_pool_release_pr(struct mlx5_fs_pool *pr_pool, + struct mlx5_fs_hws_pr *pr_data) +{ + struct mlx5_fs_bulk *fs_bulk = &pr_data->bulk->fs_bulk; + struct mlx5_fs_pool_index pool_index = {}; + struct mlx5_core_dev *dev = pr_pool->dev; + + pool_index.fs_bulk = fs_bulk; + pool_index.index = pr_data->offset; + if (mlx5_fs_pool_release_index(pr_pool, &pool_index)) + mlx5_core_warn(dev, "Attempted to release packet reformat which is not acquired\n"); +} + +struct mlx5hws_action *mlx5_fs_hws_pr_get_action(struct mlx5_fs_hws_pr *pr_data) +{ + return pr_data->bulk->hws_action; +} + +static struct mlx5hws_action * +mlx5_fs_mh_bulk_action_create(struct mlx5hws_context *ctx, + struct mlx5hws_action_mh_pattern *pattern) +{ + u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB; + u32 log_bulk_size; + + log_bulk_size = ilog2(MLX5_FS_HWS_DEFAULT_BULK_LEN); + return mlx5hws_action_create_modify_header(ctx, 1, pattern, + log_bulk_size, flags); +} + +static struct mlx5_fs_bulk * +mlx5_fs_hws_mh_bulk_create(struct mlx5_core_dev *dev, void *pool_ctx) +{ + struct mlx5hws_action_mh_pattern *pattern; + struct mlx5_flow_root_namespace *root_ns; + struct mlx5_fs_hws_mh_bulk *mh_bulk; + struct mlx5hws_context *ctx; + int bulk_len; + + if (!pool_ctx) + return NULL; + + root_ns = mlx5_get_root_namespace(dev, MLX5_FLOW_NAMESPACE_FDB); + if (!root_ns || root_ns->mode != MLX5_FLOW_STEERING_MODE_HMFS) + return NULL; + + ctx = root_ns->fs_hws_context.hws_ctx; + if (!ctx) + return NULL; + + pattern = pool_ctx; + bulk_len = MLX5_FS_HWS_DEFAULT_BULK_LEN; + mh_bulk = kvzalloc(struct_size(mh_bulk, mhs_data, bulk_len), GFP_KERNEL); + if (!mh_bulk) + return NULL; + + if (mlx5_fs_bulk_init(dev, &mh_bulk->fs_bulk, bulk_len)) + goto free_mh_bulk; + + for (int i = 0; i < bulk_len; i++) { + mh_bulk->mhs_data[i].bulk = mh_bulk; + mh_bulk->mhs_data[i].offset = i; + } + + mh_bulk->hws_action = mlx5_fs_mh_bulk_action_create(ctx, pattern); + if (!mh_bulk->hws_action) + goto cleanup_fs_bulk; + + return &mh_bulk->fs_bulk; + +cleanup_fs_bulk: + mlx5_fs_bulk_cleanup(&mh_bulk->fs_bulk); +free_mh_bulk: + kvfree(mh_bulk); + return NULL; +} + +static int +mlx5_fs_hws_mh_bulk_destroy(struct mlx5_core_dev *dev, + struct mlx5_fs_bulk *fs_bulk) +{ + struct mlx5_fs_hws_mh_bulk *mh_bulk; + + mh_bulk = container_of(fs_bulk, struct mlx5_fs_hws_mh_bulk, fs_bulk); + if (mlx5_fs_bulk_get_free_amount(fs_bulk) < fs_bulk->bulk_len) { + mlx5_core_err(dev, "Freeing bulk before all modify header were released\n"); + return -EBUSY; + } + + mlx5hws_action_destroy(mh_bulk->hws_action); + mlx5_fs_bulk_cleanup(fs_bulk); + kvfree(mh_bulk); + + return 0; +} + +static const struct mlx5_fs_pool_ops mlx5_fs_hws_mh_pool_ops = { + .bulk_create = mlx5_fs_hws_mh_bulk_create, + .bulk_destroy = mlx5_fs_hws_mh_bulk_destroy, + .update_threshold = mlx5_hws_pool_update_threshold, +}; + +int mlx5_fs_hws_mh_pool_init(struct mlx5_fs_pool *fs_hws_mh_pool, + struct mlx5_core_dev *dev, + struct mlx5hws_action_mh_pattern *pattern) +{ + struct mlx5hws_action_mh_pattern *pool_pattern; + + pool_pattern = kzalloc(sizeof(*pool_pattern), GFP_KERNEL); + if (!pool_pattern) + return -ENOMEM; + pool_pattern->data = kmemdup(pattern->data, pattern->sz, GFP_KERNEL); + if (!pool_pattern->data) { + kfree(pool_pattern); + return -ENOMEM; + } + pool_pattern->sz = pattern->sz; + mlx5_fs_pool_init(fs_hws_mh_pool, dev, &mlx5_fs_hws_mh_pool_ops, + pool_pattern); + return 0; +} + +void mlx5_fs_hws_mh_pool_cleanup(struct mlx5_fs_pool *fs_hws_mh_pool) +{ + struct mlx5hws_action_mh_pattern *pool_pattern; + + mlx5_fs_pool_cleanup(fs_hws_mh_pool); + pool_pattern = fs_hws_mh_pool->pool_ctx; + if (!pool_pattern) + return; + kfree(pool_pattern->data); + kfree(pool_pattern); +} + +struct mlx5_fs_hws_mh * +mlx5_fs_hws_mh_pool_acquire_mh(struct mlx5_fs_pool *mh_pool) +{ + struct mlx5_fs_pool_index pool_index = {}; + struct mlx5_fs_hws_mh_bulk *mh_bulk; + int err; + + err = mlx5_fs_pool_acquire_index(mh_pool, &pool_index); + if (err) + return ERR_PTR(err); + mh_bulk = container_of(pool_index.fs_bulk, struct mlx5_fs_hws_mh_bulk, + fs_bulk); + return &mh_bulk->mhs_data[pool_index.index]; +} + +void mlx5_fs_hws_mh_pool_release_mh(struct mlx5_fs_pool *mh_pool, + struct mlx5_fs_hws_mh *mh_data) +{ + struct mlx5_fs_bulk *fs_bulk = &mh_data->bulk->fs_bulk; + struct mlx5_fs_pool_index pool_index = {}; + struct mlx5_core_dev *dev = mh_pool->dev; + + pool_index.fs_bulk = fs_bulk; + pool_index.index = mh_data->offset; + if (mlx5_fs_pool_release_index(mh_pool, &pool_index)) + mlx5_core_warn(dev, "Attempted to release modify header which is not acquired\n"); +} + +bool mlx5_fs_hws_mh_pool_match(struct mlx5_fs_pool *mh_pool, + struct mlx5hws_action_mh_pattern *pattern) +{ + struct mlx5hws_action_mh_pattern *pool_pattern; + int num_actions, i; + + pool_pattern = mh_pool->pool_ctx; + if (WARN_ON_ONCE(!pool_pattern)) + return false; + + if (pattern->sz != pool_pattern->sz) + return false; + num_actions = pattern->sz / MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto); + for (i = 0; i < num_actions; i++) { + if ((__force __be32)pattern->data[i] != + (__force __be32)pool_pattern->data[i]) + return false; + } + return true; +} + +struct mlx5hws_action *mlx5_fc_get_hws_action(struct mlx5hws_context *ctx, + struct mlx5_fc *counter) +{ + u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED; + struct mlx5_fc_bulk *fc_bulk = counter->bulk; + struct mlx5_fc_bulk_hws_data *fc_bulk_hws; + + fc_bulk_hws = &fc_bulk->hws_data; + /* try avoid locking if not necessary */ + if (refcount_inc_not_zero(&fc_bulk_hws->hws_action_refcount)) + return fc_bulk_hws->hws_action; + + mutex_lock(&fc_bulk_hws->lock); + if (refcount_inc_not_zero(&fc_bulk_hws->hws_action_refcount)) { + mutex_unlock(&fc_bulk_hws->lock); + return fc_bulk_hws->hws_action; + } + fc_bulk_hws->hws_action = + mlx5hws_action_create_counter(ctx, fc_bulk->base_id, flags); + if (!fc_bulk_hws->hws_action) { + mutex_unlock(&fc_bulk_hws->lock); + return NULL; + } + refcount_set(&fc_bulk_hws->hws_action_refcount, 1); + mutex_unlock(&fc_bulk_hws->lock); + + return fc_bulk_hws->hws_action; +} + +void mlx5_fc_put_hws_action(struct mlx5_fc *counter) +{ + struct mlx5_fc_bulk_hws_data *fc_bulk_hws = &counter->bulk->hws_data; + + /* try avoid locking if not necessary */ + if (refcount_dec_not_one(&fc_bulk_hws->hws_action_refcount)) + return; + + mutex_lock(&fc_bulk_hws->lock); + if (!refcount_dec_and_test(&fc_bulk_hws->hws_action_refcount)) { + mutex_unlock(&fc_bulk_hws->lock); + return; + } + mlx5hws_action_destroy(fc_bulk_hws->hws_action); + fc_bulk_hws->hws_action = NULL; + mutex_unlock(&fc_bulk_hws->lock); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws_pools.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws_pools.h new file mode 100644 index 000000000000..34072551dd21 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws_pools.h @@ -0,0 +1,73 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2025 NVIDIA Corporation & Affiliates */ + +#ifndef __MLX5_FS_HWS_POOLS_H__ +#define __MLX5_FS_HWS_POOLS_H__ + +#include <linux/if_vlan.h> +#include "fs_pool.h" +#include "fs_core.h" + +#define MLX5_FS_INSERT_HDR_VLAN_ANCHOR MLX5_REFORMAT_CONTEXT_ANCHOR_MAC_START +#define MLX5_FS_INSERT_HDR_VLAN_OFFSET offsetof(struct vlan_ethhdr, h_vlan_proto) +#define MLX5_FS_INSERT_HDR_VLAN_SIZE sizeof(struct vlan_hdr) + +enum { + MLX5_FS_DL3TNLTOL2_MAC_HDR_IDX = 0, + MLX5_FS_DL3TNLTOL2_MAC_VLAN_HDR_IDX, +}; + +struct mlx5_fs_hws_pr { + struct mlx5_fs_hws_pr_bulk *bulk; + u32 offset; + u8 hdr_idx; + u8 *data; + size_t data_size; +}; + +struct mlx5_fs_hws_pr_bulk { + struct mlx5_fs_bulk fs_bulk; + struct mlx5hws_action *hws_action; + struct mlx5_fs_hws_pr prs_data[]; +}; + +struct mlx5_fs_hws_pr_pool_ctx { + enum mlx5hws_action_type reformat_type; + size_t encap_data_size; +}; + +struct mlx5_fs_hws_mh { + struct mlx5_fs_hws_mh_bulk *bulk; + u32 offset; + u8 *data; +}; + +struct mlx5_fs_hws_mh_bulk { + struct mlx5_fs_bulk fs_bulk; + struct mlx5_fs_pool *mh_pool; + struct mlx5hws_action *hws_action; + struct mlx5_fs_hws_mh mhs_data[]; +}; + +int mlx5_fs_hws_pr_pool_init(struct mlx5_fs_pool *pr_pool, + struct mlx5_core_dev *dev, size_t encap_data_size, + enum mlx5hws_action_type reformat_type); +void mlx5_fs_hws_pr_pool_cleanup(struct mlx5_fs_pool *pr_pool); + +struct mlx5_fs_hws_pr *mlx5_fs_hws_pr_pool_acquire_pr(struct mlx5_fs_pool *pr_pool); +void mlx5_fs_hws_pr_pool_release_pr(struct mlx5_fs_pool *pr_pool, + struct mlx5_fs_hws_pr *pr_data); +struct mlx5hws_action *mlx5_fs_hws_pr_get_action(struct mlx5_fs_hws_pr *pr_data); +int mlx5_fs_hws_mh_pool_init(struct mlx5_fs_pool *fs_hws_mh_pool, + struct mlx5_core_dev *dev, + struct mlx5hws_action_mh_pattern *pattern); +void mlx5_fs_hws_mh_pool_cleanup(struct mlx5_fs_pool *fs_hws_mh_pool); +struct mlx5_fs_hws_mh *mlx5_fs_hws_mh_pool_acquire_mh(struct mlx5_fs_pool *mh_pool); +void mlx5_fs_hws_mh_pool_release_mh(struct mlx5_fs_pool *mh_pool, + struct mlx5_fs_hws_mh *mh_data); +bool mlx5_fs_hws_mh_pool_match(struct mlx5_fs_pool *mh_pool, + struct mlx5hws_action_mh_pattern *pattern); +struct mlx5hws_action *mlx5_fc_get_hws_action(struct mlx5hws_context *ctx, + struct mlx5_fc *counter); +void mlx5_fc_put_hws_action(struct mlx5_fc *counter); +#endif /* __MLX5_FS_HWS_POOLS_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/internal.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/internal.h index 3c8635f286ce..30ccd635b505 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/internal.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/internal.h @@ -39,7 +39,6 @@ #define mlx5hws_dbg(ctx, arg...) mlx5_core_dbg((ctx)->mdev, ##arg) #define MLX5HWS_TABLE_TYPE_BASE 2 -#define MLX5HWS_ACTION_STE_IDX_ANY 0 static inline bool is_mem_zero(const u8 *mem, size_t size) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.c index 4419c72ad314..b61864b32053 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.c @@ -200,7 +200,7 @@ static void hws_matcher_set_rtc_attr_sz(struct mlx5hws_matcher *matcher, enum mlx5hws_matcher_rtc_type rtc_type, bool is_mirror) { - struct mlx5hws_pool_chunk *ste = &matcher->action_ste[MLX5HWS_ACTION_STE_IDX_ANY].ste; + struct mlx5hws_pool_chunk *ste = &matcher->action_ste.ste; enum mlx5hws_matcher_flow_src flow_src = matcher->attr.optimize_flow_src; bool is_match_rtc = rtc_type == HWS_MATCHER_RTC_TYPE_MATCH; @@ -217,8 +217,7 @@ static void hws_matcher_set_rtc_attr_sz(struct mlx5hws_matcher *matcher, } static int hws_matcher_create_rtc(struct mlx5hws_matcher *matcher, - enum mlx5hws_matcher_rtc_type rtc_type, - u8 action_ste_selector) + enum mlx5hws_matcher_rtc_type rtc_type) { struct mlx5hws_matcher_attr *attr = &matcher->attr; struct mlx5hws_cmd_rtc_create_attr rtc_attr = {0}; @@ -278,14 +277,20 @@ static int hws_matcher_create_rtc(struct mlx5hws_matcher *matcher, break; case HWS_MATCHER_RTC_TYPE_STE_ARRAY: - action_ste = &matcher->action_ste[action_ste_selector]; + action_ste = &matcher->action_ste; rtc_0_id = &action_ste->rtc_0_id; rtc_1_id = &action_ste->rtc_1_id; ste_pool = action_ste->pool; ste = &action_ste->ste; + /* Action RTC size calculation: + * log((max number of rules in matcher) * + * (max number of action STEs per rule) * + * (2 to support writing new STEs for update rule)) + */ ste->order = ilog2(roundup_pow_of_two(action_ste->max_stes)) + - attr->table.sz_row_log; + attr->table.sz_row_log + + MLX5HWS_MATCHER_ACTION_RTC_UPDATE_MULT; rtc_attr.log_size = ste->order; rtc_attr.log_depth = 0; rtc_attr.update_index_mode = MLX5_IFC_RTC_STE_UPDATE_MODE_BY_OFFSET; @@ -350,8 +355,7 @@ free_ste: } static void hws_matcher_destroy_rtc(struct mlx5hws_matcher *matcher, - enum mlx5hws_matcher_rtc_type rtc_type, - u8 action_ste_selector) + enum mlx5hws_matcher_rtc_type rtc_type) { struct mlx5hws_matcher_action_ste *action_ste; struct mlx5hws_table *tbl = matcher->tbl; @@ -367,7 +371,7 @@ static void hws_matcher_destroy_rtc(struct mlx5hws_matcher *matcher, ste = &matcher->match_ste.ste; break; case HWS_MATCHER_RTC_TYPE_STE_ARRAY: - action_ste = &matcher->action_ste[action_ste_selector]; + action_ste = &matcher->action_ste; rtc_0_id = action_ste->rtc_0_id; rtc_1_id = action_ste->rtc_1_id; ste_pool = action_ste->pool; @@ -458,20 +462,13 @@ static int hws_matcher_resize_init(struct mlx5hws_matcher *src_matcher) if (!resize_data) return -ENOMEM; - resize_data->max_stes = src_matcher->action_ste[MLX5HWS_ACTION_STE_IDX_ANY].max_stes; - - resize_data->action_ste[0].stc = src_matcher->action_ste[0].stc; - resize_data->action_ste[0].rtc_0_id = src_matcher->action_ste[0].rtc_0_id; - resize_data->action_ste[0].rtc_1_id = src_matcher->action_ste[0].rtc_1_id; - resize_data->action_ste[0].pool = src_matcher->action_ste[0].max_stes ? - src_matcher->action_ste[0].pool : - NULL; - resize_data->action_ste[1].stc = src_matcher->action_ste[1].stc; - resize_data->action_ste[1].rtc_0_id = src_matcher->action_ste[1].rtc_0_id; - resize_data->action_ste[1].rtc_1_id = src_matcher->action_ste[1].rtc_1_id; - resize_data->action_ste[1].pool = src_matcher->action_ste[1].max_stes ? - src_matcher->action_ste[1].pool : - NULL; + resize_data->max_stes = src_matcher->action_ste.max_stes; + + resize_data->stc = src_matcher->action_ste.stc; + resize_data->rtc_0_id = src_matcher->action_ste.rtc_0_id; + resize_data->rtc_1_id = src_matcher->action_ste.rtc_1_id; + resize_data->pool = src_matcher->action_ste.max_stes ? + src_matcher->action_ste.pool : NULL; /* Place the new resized matcher on the dst matcher's list */ list_add(&resize_data->list_node, &src_matcher->resize_dst->resize_data); @@ -504,49 +501,69 @@ static void hws_matcher_resize_uninit(struct mlx5hws_matcher *matcher) if (resize_data->max_stes) { mlx5hws_action_free_single_stc(matcher->tbl->ctx, matcher->tbl->type, - &resize_data->action_ste[1].stc); - mlx5hws_action_free_single_stc(matcher->tbl->ctx, - matcher->tbl->type, - &resize_data->action_ste[0].stc); + &resize_data->stc); - if (matcher->tbl->type == MLX5HWS_TABLE_TYPE_FDB) { + if (matcher->tbl->type == MLX5HWS_TABLE_TYPE_FDB) mlx5hws_cmd_rtc_destroy(matcher->tbl->ctx->mdev, - resize_data->action_ste[1].rtc_1_id); - mlx5hws_cmd_rtc_destroy(matcher->tbl->ctx->mdev, - resize_data->action_ste[0].rtc_1_id); - } - mlx5hws_cmd_rtc_destroy(matcher->tbl->ctx->mdev, - resize_data->action_ste[1].rtc_0_id); + resize_data->rtc_1_id); + mlx5hws_cmd_rtc_destroy(matcher->tbl->ctx->mdev, - resize_data->action_ste[0].rtc_0_id); - if (resize_data->action_ste[MLX5HWS_ACTION_STE_IDX_ANY].pool) { - mlx5hws_pool_destroy(resize_data->action_ste[1].pool); - mlx5hws_pool_destroy(resize_data->action_ste[0].pool); - } + resize_data->rtc_0_id); + + if (resize_data->pool) + mlx5hws_pool_destroy(resize_data->pool); } kfree(resize_data); } } -static int -hws_matcher_bind_at_idx(struct mlx5hws_matcher *matcher, u8 action_ste_selector) +static int hws_matcher_bind_at(struct mlx5hws_matcher *matcher) { + bool is_jumbo = mlx5hws_matcher_mt_is_jumbo(matcher->mt); struct mlx5hws_cmd_stc_modify_attr stc_attr = {0}; struct mlx5hws_matcher_action_ste *action_ste; struct mlx5hws_table *tbl = matcher->tbl; struct mlx5hws_pool_attr pool_attr = {0}; struct mlx5hws_context *ctx = tbl->ctx; - int ret; + u32 required_stes; + u8 max_stes = 0; + int i, ret; + + if (matcher->flags & MLX5HWS_MATCHER_FLAGS_COLLISION) + return 0; + + for (i = 0; i < matcher->num_of_at; i++) { + struct mlx5hws_action_template *at = &matcher->at[i]; - action_ste = &matcher->action_ste[action_ste_selector]; + ret = hws_matcher_check_and_process_at(matcher, at); + if (ret) { + mlx5hws_err(ctx, "Invalid at %d", i); + return ret; + } + + required_stes = at->num_of_action_stes - (!is_jumbo || at->only_term); + max_stes = max(max_stes, required_stes); + + /* Future: Optimize reparse */ + } + + /* There are no additional STEs required for matcher */ + if (!max_stes) + return 0; + + matcher->action_ste.max_stes = max_stes; + + action_ste = &matcher->action_ste; /* Allocate action STE mempool */ pool_attr.table_type = tbl->type; pool_attr.pool_type = MLX5HWS_POOL_TYPE_STE; pool_attr.flags = MLX5HWS_POOL_FLAGS_FOR_STE_ACTION_POOL; + /* Pool size is similar to action RTC size */ pool_attr.alloc_log_sz = ilog2(roundup_pow_of_two(action_ste->max_stes)) + - matcher->attr.table.sz_row_log; + matcher->attr.table.sz_row_log + + MLX5HWS_MATCHER_ACTION_RTC_UPDATE_MULT; hws_matcher_set_pool_attr(&pool_attr, matcher); action_ste->pool = mlx5hws_pool_create(ctx, &pool_attr); if (!action_ste->pool) { @@ -555,7 +572,7 @@ hws_matcher_bind_at_idx(struct mlx5hws_matcher *matcher, u8 action_ste_selector) } /* Allocate action RTC */ - ret = hws_matcher_create_rtc(matcher, HWS_MATCHER_RTC_TYPE_STE_ARRAY, action_ste_selector); + ret = hws_matcher_create_rtc(matcher, HWS_MATCHER_RTC_TYPE_STE_ARRAY); if (ret) { mlx5hws_err(ctx, "Failed to create action RTC\n"); goto free_ste_pool; @@ -579,18 +596,18 @@ hws_matcher_bind_at_idx(struct mlx5hws_matcher *matcher, u8 action_ste_selector) return 0; free_rtc: - hws_matcher_destroy_rtc(matcher, HWS_MATCHER_RTC_TYPE_STE_ARRAY, action_ste_selector); + hws_matcher_destroy_rtc(matcher, HWS_MATCHER_RTC_TYPE_STE_ARRAY); free_ste_pool: mlx5hws_pool_destroy(action_ste->pool); return ret; } -static void hws_matcher_unbind_at_idx(struct mlx5hws_matcher *matcher, u8 action_ste_selector) +static void hws_matcher_unbind_at(struct mlx5hws_matcher *matcher) { struct mlx5hws_matcher_action_ste *action_ste; struct mlx5hws_table *tbl = matcher->tbl; - action_ste = &matcher->action_ste[action_ste_selector]; + action_ste = &matcher->action_ste; if (!action_ste->max_stes || matcher->flags & MLX5HWS_MATCHER_FLAGS_COLLISION || @@ -598,65 +615,10 @@ static void hws_matcher_unbind_at_idx(struct mlx5hws_matcher *matcher, u8 action return; mlx5hws_action_free_single_stc(tbl->ctx, tbl->type, &action_ste->stc); - hws_matcher_destroy_rtc(matcher, HWS_MATCHER_RTC_TYPE_STE_ARRAY, action_ste_selector); + hws_matcher_destroy_rtc(matcher, HWS_MATCHER_RTC_TYPE_STE_ARRAY); mlx5hws_pool_destroy(action_ste->pool); } -static int hws_matcher_bind_at(struct mlx5hws_matcher *matcher) -{ - bool is_jumbo = mlx5hws_matcher_mt_is_jumbo(matcher->mt); - struct mlx5hws_table *tbl = matcher->tbl; - struct mlx5hws_context *ctx = tbl->ctx; - u32 required_stes; - u8 max_stes = 0; - int i, ret; - - if (matcher->flags & MLX5HWS_MATCHER_FLAGS_COLLISION) - return 0; - - for (i = 0; i < matcher->num_of_at; i++) { - struct mlx5hws_action_template *at = &matcher->at[i]; - - ret = hws_matcher_check_and_process_at(matcher, at); - if (ret) { - mlx5hws_err(ctx, "Invalid at %d", i); - return ret; - } - - required_stes = at->num_of_action_stes - (!is_jumbo || at->only_term); - max_stes = max(max_stes, required_stes); - - /* Future: Optimize reparse */ - } - - /* There are no additional STEs required for matcher */ - if (!max_stes) - return 0; - - matcher->action_ste[0].max_stes = max_stes; - matcher->action_ste[1].max_stes = max_stes; - - ret = hws_matcher_bind_at_idx(matcher, 0); - if (ret) - return ret; - - ret = hws_matcher_bind_at_idx(matcher, 1); - if (ret) - goto free_at_0; - - return 0; - -free_at_0: - hws_matcher_unbind_at_idx(matcher, 0); - return ret; -} - -static void hws_matcher_unbind_at(struct mlx5hws_matcher *matcher) -{ - hws_matcher_unbind_at_idx(matcher, 1); - hws_matcher_unbind_at_idx(matcher, 0); -} - static int hws_matcher_bind_mt(struct mlx5hws_matcher *matcher) { struct mlx5hws_context *ctx = matcher->tbl->ctx; @@ -802,7 +764,7 @@ static int hws_matcher_create_and_connect(struct mlx5hws_matcher *matcher) goto unbind_at; /* Allocate the RTC for the new matcher */ - ret = hws_matcher_create_rtc(matcher, HWS_MATCHER_RTC_TYPE_MATCH, 0); + ret = hws_matcher_create_rtc(matcher, HWS_MATCHER_RTC_TYPE_MATCH); if (ret) goto destroy_end_ft; @@ -814,7 +776,7 @@ static int hws_matcher_create_and_connect(struct mlx5hws_matcher *matcher) return 0; destroy_rtc: - hws_matcher_destroy_rtc(matcher, HWS_MATCHER_RTC_TYPE_MATCH, 0); + hws_matcher_destroy_rtc(matcher, HWS_MATCHER_RTC_TYPE_MATCH); destroy_end_ft: hws_matcher_destroy_end_ft(matcher); unbind_at: @@ -828,7 +790,7 @@ static void hws_matcher_destroy_and_disconnect(struct mlx5hws_matcher *matcher) { hws_matcher_resize_uninit(matcher); hws_matcher_disconnect(matcher); - hws_matcher_destroy_rtc(matcher, HWS_MATCHER_RTC_TYPE_MATCH, 0); + hws_matcher_destroy_rtc(matcher, HWS_MATCHER_RTC_TYPE_MATCH); hws_matcher_destroy_end_ft(matcher); hws_matcher_unbind_at(matcher); hws_matcher_unbind_mt(matcher); @@ -962,10 +924,9 @@ int mlx5hws_matcher_attach_at(struct mlx5hws_matcher *matcher, return ret; required_stes = at->num_of_action_stes - (!is_jumbo || at->only_term); - if (matcher->action_ste[MLX5HWS_ACTION_STE_IDX_ANY].max_stes < required_stes) { + if (matcher->action_ste.max_stes < required_stes) { mlx5hws_dbg(ctx, "Required STEs [%d] exceeds initial action template STE [%d]\n", - required_stes, - matcher->action_ste[MLX5HWS_ACTION_STE_IDX_ANY].max_stes); + required_stes, matcher->action_ste.max_stes); return -ENOMEM; } @@ -1149,8 +1110,7 @@ static int hws_matcher_resize_precheck(struct mlx5hws_matcher *src_matcher, return -EINVAL; } - if (src_matcher->action_ste[MLX5HWS_ACTION_STE_IDX_ANY].max_stes > - dst_matcher->action_ste[0].max_stes) { + if (src_matcher->action_ste.max_stes > dst_matcher->action_ste.max_stes) { mlx5hws_err(ctx, "Src/dst matcher max STEs mismatch\n"); return -EINVAL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.h index 81ff487f57be..020de70270c5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.h @@ -18,6 +18,11 @@ /* Required depth of the main large table */ #define MLX5HWS_MATCHER_ASSURED_MAIN_TBL_DEPTH 2 +/* Action RTC size multiplier that is required in order + * to support rule update for rules with action STEs. + */ +#define MLX5HWS_MATCHER_ACTION_RTC_UPDATE_MULT 1 + enum mlx5hws_matcher_offset { MLX5HWS_MATCHER_OFFSET_TAG_DW1 = 12, MLX5HWS_MATCHER_OFFSET_TAG_DW0 = 13, @@ -52,15 +57,11 @@ struct mlx5hws_matcher_action_ste { u8 max_stes; }; -struct mlx5hws_matcher_resize_data_node { +struct mlx5hws_matcher_resize_data { struct mlx5hws_pool_chunk stc; u32 rtc_0_id; u32 rtc_1_id; struct mlx5hws_pool *pool; -}; - -struct mlx5hws_matcher_resize_data { - struct mlx5hws_matcher_resize_data_node action_ste[2]; u8 max_stes; struct list_head list_node; }; @@ -78,7 +79,7 @@ struct mlx5hws_matcher { struct mlx5hws_matcher *col_matcher; struct mlx5hws_matcher *resize_dst; struct mlx5hws_matcher_match_ste match_ste; - struct mlx5hws_matcher_action_ste action_ste[2]; + struct mlx5hws_matcher_action_ste action_ste; struct list_head list_node; struct list_head resize_data; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.c index 14f6307a1772..a27a2d5ffc7b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.c @@ -129,27 +129,18 @@ static void hws_rule_gen_comp(struct mlx5hws_send_engine *queue, static void hws_rule_save_resize_info(struct mlx5hws_rule *rule, - struct mlx5hws_send_ste_attr *ste_attr, - bool is_update) + struct mlx5hws_send_ste_attr *ste_attr) { if (!mlx5hws_matcher_is_resizable(rule->matcher)) return; - if (likely(!is_update)) { + /* resize_info might already exist (if we're in update flow) */ + if (likely(!rule->resize_info)) { rule->resize_info = kzalloc(sizeof(*rule->resize_info), GFP_KERNEL); if (unlikely(!rule->resize_info)) { pr_warn("HWS: resize info isn't allocated for rule\n"); return; } - - rule->resize_info->max_stes = - rule->matcher->action_ste[MLX5HWS_ACTION_STE_IDX_ANY].max_stes; - rule->resize_info->action_ste_pool[0] = rule->matcher->action_ste[0].max_stes ? - rule->matcher->action_ste[0].pool : - NULL; - rule->resize_info->action_ste_pool[1] = rule->matcher->action_ste[1].max_stes ? - rule->matcher->action_ste[1].pool : - NULL; } memcpy(rule->resize_info->ctrl_seg, ste_attr->wqe_ctrl, @@ -204,15 +195,14 @@ hws_rule_load_delete_info(struct mlx5hws_rule *rule, } } -static int hws_rule_alloc_action_ste_idx(struct mlx5hws_rule *rule, - u8 action_ste_selector) +static int hws_rule_alloc_action_ste(struct mlx5hws_rule *rule) { struct mlx5hws_matcher *matcher = rule->matcher; struct mlx5hws_matcher_action_ste *action_ste; struct mlx5hws_pool_chunk ste = {0}; int ret; - action_ste = &matcher->action_ste[action_ste_selector]; + action_ste = &matcher->action_ste; ste.order = ilog2(roundup_pow_of_two(action_ste->max_stes)); ret = mlx5hws_pool_chunk_alloc(action_ste->pool, &ste); if (unlikely(ret)) { @@ -220,68 +210,29 @@ static int hws_rule_alloc_action_ste_idx(struct mlx5hws_rule *rule, "Failed to allocate STE for rule actions"); return ret; } - rule->action_ste_idx = ste.offset; + + rule->action_ste.pool = matcher->action_ste.pool; + rule->action_ste.num_stes = matcher->action_ste.max_stes; + rule->action_ste.index = ste.offset; return 0; } -static void hws_rule_free_action_ste_idx(struct mlx5hws_rule *rule, - u8 action_ste_selector) +void mlx5hws_rule_free_action_ste(struct mlx5hws_rule_action_ste_info *action_ste) { - struct mlx5hws_matcher *matcher = rule->matcher; struct mlx5hws_pool_chunk ste = {0}; - struct mlx5hws_pool *pool; - u8 max_stes; - - if (mlx5hws_matcher_is_resizable(matcher)) { - /* Free the original action pool if rule was resized */ - max_stes = rule->resize_info->max_stes; - pool = rule->resize_info->action_ste_pool[action_ste_selector]; - } else { - max_stes = matcher->action_ste[action_ste_selector].max_stes; - pool = matcher->action_ste[action_ste_selector].pool; - } - - /* This release is safe only when the rule match part was deleted */ - ste.order = ilog2(roundup_pow_of_two(max_stes)); - ste.offset = rule->action_ste_idx; - - mlx5hws_pool_chunk_free(pool, &ste); -} -static int hws_rule_alloc_action_ste(struct mlx5hws_rule *rule, - struct mlx5hws_rule_attr *attr) -{ - int action_ste_idx; - int ret; - - ret = hws_rule_alloc_action_ste_idx(rule, 0); - if (unlikely(ret)) - return ret; - - action_ste_idx = rule->action_ste_idx; - - ret = hws_rule_alloc_action_ste_idx(rule, 1); - if (unlikely(ret)) { - hws_rule_free_action_ste_idx(rule, 0); - return ret; - } - - /* Both pools have to return the same index */ - if (unlikely(rule->action_ste_idx != action_ste_idx)) { - pr_warn("HWS: allocation of action STE failed - pool indexes mismatch\n"); - return -EINVAL; - } + if (!action_ste->num_stes) + return; - return 0; -} + ste.order = ilog2(roundup_pow_of_two(action_ste->num_stes)); + ste.offset = action_ste->index; -void mlx5hws_rule_free_action_ste(struct mlx5hws_rule *rule) -{ - if (rule->action_ste_idx > -1) { - hws_rule_free_action_ste_idx(rule, 1); - hws_rule_free_action_ste_idx(rule, 0); - } + /* This release is safe only when the rule match STE was deleted + * (when the rule is being deleted) or replaced with the new STE that + * isn't pointing to old action STEs (when the rule is being updated). + */ + mlx5hws_pool_chunk_free(action_ste->pool, &ste); } static void hws_rule_create_init(struct mlx5hws_rule *rule, @@ -298,14 +249,24 @@ static void hws_rule_create_init(struct mlx5hws_rule *rule, /* In update we use these rtc's */ rule->rtc_0 = 0; rule->rtc_1 = 0; - rule->action_ste_selector = 0; + + rule->action_ste.pool = NULL; + rule->action_ste.num_stes = 0; + rule->action_ste.index = -1; + + rule->status = MLX5HWS_RULE_STATUS_CREATING; } else { - rule->action_ste_selector = !rule->action_ste_selector; + rule->status = MLX5HWS_RULE_STATUS_UPDATING; } + /* Initialize the old action STE info - shallow-copy action_ste. + * In create flow this will set old_action_ste fields to initial values. + * In update flow this will save the existing action STE info, + * so that we will later use it to free old STEs. + */ + rule->old_action_ste = rule->action_ste; + rule->pending_wqes = 0; - rule->action_ste_idx = -1; - rule->status = MLX5HWS_RULE_STATUS_CREATING; /* Init default send STE attributes */ ste_attr->gta_opcode = MLX5HWS_WQE_GTA_OP_ACTIVATE; @@ -316,7 +277,7 @@ static void hws_rule_create_init(struct mlx5hws_rule *rule, /* Init default action apply */ apply->tbl_type = tbl->type; apply->common_res = &ctx->common_res; - apply->jump_to_action_stc = matcher->action_ste[0].stc.offset; + apply->jump_to_action_stc = matcher->action_ste.stc.offset; apply->require_dep = 0; } @@ -332,8 +293,6 @@ static void hws_rule_move_init(struct mlx5hws_rule *rule, rule->rtc_1 = 0; rule->pending_wqes = 0; - rule->action_ste_idx = -1; - rule->action_ste_selector = 0; rule->status = MLX5HWS_RULE_STATUS_CREATING; rule->resize_info->state = MLX5HWS_RULE_RESIZE_STATE_WRITING; } @@ -394,21 +353,17 @@ static int hws_rule_create_hws(struct mlx5hws_rule *rule, if (action_stes) { /* Allocate action STEs for rules that need more than match STE */ - if (!is_update) { - ret = hws_rule_alloc_action_ste(rule, attr); - if (ret) { - mlx5hws_err(ctx, "Failed to allocate action memory %d", ret); - mlx5hws_send_abort_new_dep_wqe(queue); - return ret; - } + ret = hws_rule_alloc_action_ste(rule); + if (ret) { + mlx5hws_err(ctx, "Failed to allocate action memory %d", ret); + mlx5hws_send_abort_new_dep_wqe(queue); + return ret; } /* Skip RX/TX based on the dep_wqe init */ - ste_attr.rtc_0 = dep_wqe->rtc_0 ? - matcher->action_ste[rule->action_ste_selector].rtc_0_id : 0; - ste_attr.rtc_1 = dep_wqe->rtc_1 ? - matcher->action_ste[rule->action_ste_selector].rtc_1_id : 0; + ste_attr.rtc_0 = dep_wqe->rtc_0 ? matcher->action_ste.rtc_0_id : 0; + ste_attr.rtc_1 = dep_wqe->rtc_1 ? matcher->action_ste.rtc_1_id : 0; /* Action STEs are written to a specific index last to first */ - ste_attr.direct_index = rule->action_ste_idx + action_stes; + ste_attr.direct_index = rule->action_ste.index + action_stes; apply.next_direct_idx = ste_attr.direct_index; } else { apply.next_direct_idx = 0; @@ -459,7 +414,7 @@ static int hws_rule_create_hws(struct mlx5hws_rule *rule, if (!is_update) hws_rule_save_delete_info(rule, &ste_attr); - hws_rule_save_resize_info(rule, &ste_attr, is_update); + hws_rule_save_resize_info(rule, &ste_attr); mlx5hws_send_engine_inc_rule(queue); if (!attr->burst) @@ -480,7 +435,10 @@ static void hws_rule_destroy_failed_hws(struct mlx5hws_rule *rule, attr->user_data, MLX5HWS_RULE_STATUS_DELETED); /* Rule failed now we can safely release action STEs */ - mlx5hws_rule_free_action_ste(rule); + mlx5hws_rule_free_action_ste(&rule->action_ste); + + /* Perhaps the rule failed updating - release old action STEs as well */ + mlx5hws_rule_free_action_ste(&rule->old_action_ste); /* Clear complex tag */ hws_rule_clear_delete_info(rule); @@ -517,7 +475,8 @@ static int hws_rule_destroy_hws(struct mlx5hws_rule *rule, } /* Rule is not completed yet */ - if (rule->status == MLX5HWS_RULE_STATUS_CREATING) + if (rule->status == MLX5HWS_RULE_STATUS_CREATING || + rule->status == MLX5HWS_RULE_STATUS_UPDATING) return -EBUSY; /* Rule failed and doesn't require cleanup */ @@ -534,7 +493,7 @@ static int hws_rule_destroy_hws(struct mlx5hws_rule *rule, hws_rule_gen_comp(queue, rule, false, attr->user_data, MLX5HWS_RULE_STATUS_DELETED); - mlx5hws_rule_free_action_ste(rule); + mlx5hws_rule_free_action_ste(&rule->action_ste); mlx5hws_rule_clear_resize_info(rule); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.h index 495cdd17e9f3..b5ee94ac449b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.h @@ -15,6 +15,8 @@ enum mlx5hws_rule_status { MLX5HWS_RULE_STATUS_UNKNOWN, MLX5HWS_RULE_STATUS_CREATING, MLX5HWS_RULE_STATUS_CREATED, + MLX5HWS_RULE_STATUS_UPDATING, + MLX5HWS_RULE_STATUS_UPDATED, MLX5HWS_RULE_STATUS_DELETING, MLX5HWS_RULE_STATUS_DELETED, MLX5HWS_RULE_STATUS_FAILING, @@ -41,13 +43,17 @@ struct mlx5hws_rule_match_tag { }; }; +struct mlx5hws_rule_action_ste_info { + struct mlx5hws_pool *pool; + int index; /* STE array index */ + u8 num_stes; +}; + struct mlx5hws_rule_resize_info { - struct mlx5hws_pool *action_ste_pool[2]; u32 rtc_0; u32 rtc_1; u32 rule_idx; u8 state; - u8 max_stes; u8 ctrl_seg[MLX5HWS_WQE_SZ_GTA_CTRL]; /* Ctrl segment of STE: 48 bytes */ u8 data_seg[MLX5HWS_WQE_SZ_GTA_DATA]; /* Data segment of STE: 64 bytes */ }; @@ -58,18 +64,18 @@ struct mlx5hws_rule { struct mlx5hws_rule_match_tag tag; struct mlx5hws_rule_resize_info *resize_info; }; + struct mlx5hws_rule_action_ste_info action_ste; + struct mlx5hws_rule_action_ste_info old_action_ste; u32 rtc_0; /* The RTC into which the STE was inserted */ u32 rtc_1; /* The RTC into which the STE was inserted */ - int action_ste_idx; /* STE array index */ u8 status; /* enum mlx5hws_rule_status */ - u8 action_ste_selector; /* For rule update - which action STE is in use */ u8 pending_wqes; bool skip_delete; /* For complex rules - another rule with same tag * still exists, so don't actually delete this rule. */ }; -void mlx5hws_rule_free_action_ste(struct mlx5hws_rule *rule); +void mlx5hws_rule_free_action_ste(struct mlx5hws_rule_action_ste_info *action_ste); int mlx5hws_rule_move_hws_remove(struct mlx5hws_rule *rule, void *queue, void *user_data); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c index c680b7f984e1..cb6abc4ab7df 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c @@ -377,17 +377,25 @@ static void hws_send_engine_update_rule(struct mlx5hws_send_engine *queue, *status = MLX5HWS_FLOW_OP_ERROR; } else { - /* Increase the status, this only works on good flow as the enum - * is arrange it away creating -> created -> deleting -> deleted + /* Increase the status, this only works on good flow as + * the enum is arranged this way: + * - creating -> created + * - updating -> updated + * - deleting -> deleted */ priv->rule->status++; *status = MLX5HWS_FLOW_OP_SUCCESS; - /* Rule was deleted now we can safely release action STEs - * and clear resize info - */ if (priv->rule->status == MLX5HWS_RULE_STATUS_DELETED) { - mlx5hws_rule_free_action_ste(priv->rule); + /* Rule was deleted, now we can safely release + * action STEs and clear resize info + */ + mlx5hws_rule_free_action_ste(&priv->rule->action_ste); mlx5hws_rule_clear_resize_info(priv->rule); + } else if (priv->rule->status == MLX5HWS_RULE_STATUS_UPDATED) { + /* Rule was updated, free the old action STEs */ + mlx5hws_rule_free_action_ste(&priv->rule->old_action_ste); + /* Update completed - move the rule back to "created" */ + priv->rule->status = MLX5HWS_RULE_STATUS_CREATED; } } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wc.c b/drivers/net/ethernet/mellanox/mlx5/core/wc.c index 1bed75eca97d..740b719e7072 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/wc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/wc.c @@ -382,6 +382,7 @@ err_alloc_bfreg: bool mlx5_wc_support_get(struct mlx5_core_dev *mdev) { + struct mutex *wc_state_lock = &mdev->wc_state_lock; struct mlx5_core_dev *parent = NULL; if (!MLX5_CAP_GEN(mdev, bf)) { @@ -400,32 +401,31 @@ bool mlx5_wc_support_get(struct mlx5_core_dev *mdev) */ goto out; - mutex_lock(&mdev->wc_state_lock); - - if (mdev->wc_state != MLX5_WC_STATE_UNINITIALIZED) - goto unlock; - #ifdef CONFIG_MLX5_SF - if (mlx5_core_is_sf(mdev)) + if (mlx5_core_is_sf(mdev)) { parent = mdev->priv.parent_mdev; + wc_state_lock = &parent->wc_state_lock; + } #endif - if (parent) { - mutex_lock(&parent->wc_state_lock); + mutex_lock(wc_state_lock); + if (mdev->wc_state != MLX5_WC_STATE_UNINITIALIZED) + goto unlock; + + if (parent) { mlx5_core_test_wc(parent); mlx5_core_dbg(mdev, "parent set wc_state=%d\n", parent->wc_state); mdev->wc_state = parent->wc_state; - mutex_unlock(&parent->wc_state_lock); + } else { + mlx5_core_test_wc(mdev); } - mlx5_core_test_wc(mdev); - unlock: - mutex_unlock(&mdev->wc_state_lock); + mutex_unlock(wc_state_lock); out: mlx5_core_dbg(mdev, "wc_state=%d\n", mdev->wc_state); diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index 4a79c0d7e7ad..2bb2b77351bd 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -35,6 +35,7 @@ #include "reg.h" #include "resources.h" #include "../mlxfw/mlxfw.h" +#include "txheader.h" static LIST_HEAD(mlxsw_core_driver_list); static DEFINE_SPINLOCK(mlxsw_core_driver_list_lock); @@ -677,7 +678,7 @@ struct mlxsw_reg_trans { struct list_head bulk_list; struct mlxsw_core *core; struct sk_buff *tx_skb; - struct mlxsw_tx_info tx_info; + struct mlxsw_txhdr_info txhdr_info; struct delayed_work timeout_dw; unsigned int retries; u64 tid; @@ -737,12 +738,11 @@ static int mlxsw_emad_transmit(struct mlxsw_core *mlxsw_core, if (!skb) return -ENOMEM; - trace_devlink_hwmsg(priv_to_devlink(mlxsw_core), false, 0, - skb->data + mlxsw_core->driver->txhdr_len, - skb->len - mlxsw_core->driver->txhdr_len); + trace_devlink_hwmsg(priv_to_devlink(mlxsw_core), false, 0, skb->data, + skb->len); atomic_set(&trans->active, 1); - err = mlxsw_core_skb_transmit(mlxsw_core, skb, &trans->tx_info); + err = mlxsw_core_skb_transmit(mlxsw_core, skb, &trans->txhdr_info); if (err) { dev_kfree_skb(skb); return err; @@ -944,7 +944,7 @@ static struct sk_buff *mlxsw_emad_alloc(const struct mlxsw_core *mlxsw_core, emad_len = (reg_len + sizeof(u32) + MLXSW_EMAD_ETH_HDR_LEN + (MLXSW_EMAD_OP_TLV_LEN + MLXSW_EMAD_END_TLV_LEN) * - sizeof(u32) + mlxsw_core->driver->txhdr_len); + sizeof(u32) + MLXSW_TXHDR_LEN); if (mlxsw_core->emad.enable_string_tlv) emad_len += MLXSW_EMAD_STRING_TLV_LEN * sizeof(u32); if (mlxsw_core->emad.enable_latency_tlv) @@ -984,8 +984,8 @@ static int mlxsw_emad_reg_access(struct mlxsw_core *mlxsw_core, list_add_tail(&trans->bulk_list, bulk_list); trans->core = mlxsw_core; trans->tx_skb = skb; - trans->tx_info.local_port = MLXSW_PORT_CPU_PORT; - trans->tx_info.is_emad = true; + trans->txhdr_info.tx_info.local_port = MLXSW_PORT_CPU_PORT; + trans->txhdr_info.tx_info.is_emad = true; INIT_DELAYED_WORK(&trans->timeout_dw, mlxsw_emad_trans_timeout_work); trans->tid = tid; init_completion(&trans->completion); @@ -995,7 +995,6 @@ static int mlxsw_emad_reg_access(struct mlxsw_core *mlxsw_core, trans->type = type; mlxsw_emad_construct(mlxsw_core, skb, reg, payload, type, trans->tid); - mlxsw_core->driver->txhdr_construct(skb, &trans->tx_info); spin_lock_bh(&mlxsw_core->emad.trans_list_lock); list_add_tail_rcu(&trans->list, &mlxsw_core->emad.trans_list); @@ -2330,10 +2329,10 @@ bool mlxsw_core_skb_transmit_busy(struct mlxsw_core *mlxsw_core, EXPORT_SYMBOL(mlxsw_core_skb_transmit_busy); int mlxsw_core_skb_transmit(struct mlxsw_core *mlxsw_core, struct sk_buff *skb, - const struct mlxsw_tx_info *tx_info) + const struct mlxsw_txhdr_info *txhdr_info) { return mlxsw_core->bus->skb_transmit(mlxsw_core->bus_priv, skb, - tx_info); + txhdr_info); } EXPORT_SYMBOL(mlxsw_core_skb_transmit); diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h index 24c3ff6fcf71..1a871397a6df 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core.h @@ -72,6 +72,12 @@ struct mlxsw_tx_info { bool is_emad; }; +struct mlxsw_txhdr_info { + struct mlxsw_tx_info tx_info; + bool data; + u16 max_fid; /* Used for PTP packets which are sent as data. */ +}; + struct mlxsw_rx_md_info { struct napi_struct *napi; u32 cookie_index; @@ -95,7 +101,7 @@ struct mlxsw_rx_md_info { bool mlxsw_core_skb_transmit_busy(struct mlxsw_core *mlxsw_core, const struct mlxsw_tx_info *tx_info); int mlxsw_core_skb_transmit(struct mlxsw_core *mlxsw_core, struct sk_buff *skb, - const struct mlxsw_tx_info *tx_info); + const struct mlxsw_txhdr_info *txhdr_info); void mlxsw_core_ptp_transmitted(struct mlxsw_core *mlxsw_core, struct sk_buff *skb, u16 local_port); @@ -426,8 +432,6 @@ struct mlxsw_driver { int (*trap_policer_counter_get)(struct mlxsw_core *mlxsw_core, const struct devlink_trap_policer *policer, u64 *p_drops); - void (*txhdr_construct)(struct sk_buff *skb, - const struct mlxsw_tx_info *tx_info); int (*resources_register)(struct mlxsw_core *mlxsw_core); int (*kvd_sizes_get)(struct mlxsw_core *mlxsw_core, const struct mlxsw_config_profile *profile, @@ -440,7 +444,6 @@ struct mlxsw_driver { void (*ptp_transmitted)(struct mlxsw_core *mlxsw_core, struct sk_buff *skb, u16 local_port); - u8 txhdr_len; const struct mlxsw_config_profile *profile; bool sdq_supports_cqe_v2; }; @@ -487,7 +490,7 @@ struct mlxsw_bus { bool (*skb_transmit_busy)(void *bus_priv, const struct mlxsw_tx_info *tx_info); int (*skb_transmit)(void *bus_priv, struct sk_buff *skb, - const struct mlxsw_tx_info *tx_info); + const struct mlxsw_txhdr_info *txhdr_info); int (*cmd_exec)(void *bus_priv, u16 opcode, u8 opcode_mod, u32 in_mod, bool out_mbox_direct, char *in_mbox, size_t in_mbox_size, diff --git a/drivers/net/ethernet/mellanox/mlxsw/i2c.c b/drivers/net/ethernet/mellanox/mlxsw/i2c.c index 1e150ce1c73a..f9f565c1036d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/i2c.c +++ b/drivers/net/ethernet/mellanox/mlxsw/i2c.c @@ -516,7 +516,7 @@ static bool mlxsw_i2c_skb_transmit_busy(void *bus_priv, } static int mlxsw_i2c_skb_transmit(void *bus_priv, struct sk_buff *skb, - const struct mlxsw_tx_info *tx_info) + const struct mlxsw_txhdr_info *txhdr_info) { return 0; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index 0863dca2fc0b..5b44c931b660 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -21,6 +21,7 @@ #include "cmd.h" #include "port.h" #include "resources.h" +#include "txheader.h" #define mlxsw_pci_write32(mlxsw_pci, reg, val) \ iowrite32be(val, (mlxsw_pci)->hw_addr + (MLXSW_PCI_ ## reg)) @@ -2095,6 +2096,39 @@ static void mlxsw_pci_fini(void *bus_priv) mlxsw_pci_free_irq_vectors(mlxsw_pci); } +static int mlxsw_pci_txhdr_construct(struct sk_buff *skb, + const struct mlxsw_txhdr_info *txhdr_info) +{ + const struct mlxsw_tx_info tx_info = txhdr_info->tx_info; + char *txhdr; + + if (skb_cow_head(skb, MLXSW_TXHDR_LEN)) + return -ENOMEM; + + txhdr = skb_push(skb, MLXSW_TXHDR_LEN); + memset(txhdr, 0, MLXSW_TXHDR_LEN); + + mlxsw_tx_hdr_version_set(txhdr, MLXSW_TXHDR_VERSION_1); + mlxsw_tx_hdr_proto_set(txhdr, MLXSW_TXHDR_PROTO_ETH); + mlxsw_tx_hdr_swid_set(txhdr, 0); + + if (unlikely(txhdr_info->data)) { + u16 fid = txhdr_info->max_fid + tx_info.local_port - 1; + + mlxsw_tx_hdr_rx_is_router_set(txhdr, true); + mlxsw_tx_hdr_fid_valid_set(txhdr, true); + mlxsw_tx_hdr_fid_set(txhdr, fid); + mlxsw_tx_hdr_type_set(txhdr, MLXSW_TXHDR_TYPE_DATA); + } else { + mlxsw_tx_hdr_ctl_set(txhdr, MLXSW_TXHDR_ETH_CTL); + mlxsw_tx_hdr_control_tclass_set(txhdr, 1); + mlxsw_tx_hdr_port_mid_set(txhdr, tx_info.local_port); + mlxsw_tx_hdr_type_set(txhdr, MLXSW_TXHDR_TYPE_CONTROL); + } + + return 0; +} + static struct mlxsw_pci_queue * mlxsw_pci_sdq_pick(struct mlxsw_pci *mlxsw_pci, const struct mlxsw_tx_info *tx_info) @@ -2122,7 +2156,7 @@ static bool mlxsw_pci_skb_transmit_busy(void *bus_priv, } static int mlxsw_pci_skb_transmit(void *bus_priv, struct sk_buff *skb, - const struct mlxsw_tx_info *tx_info) + const struct mlxsw_txhdr_info *txhdr_info) { struct mlxsw_pci *mlxsw_pci = bus_priv; struct mlxsw_pci_queue *q; @@ -2131,13 +2165,17 @@ static int mlxsw_pci_skb_transmit(void *bus_priv, struct sk_buff *skb, int i; int err; + err = mlxsw_pci_txhdr_construct(skb, txhdr_info); + if (err) + return err; + if (skb_shinfo(skb)->nr_frags > MLXSW_PCI_WQE_SG_ENTRIES - 1) { err = skb_linearize(skb); if (err) return err; } - q = mlxsw_pci_sdq_pick(mlxsw_pci, tx_info); + q = mlxsw_pci_sdq_pick(mlxsw_pci, &txhdr_info->tx_info); spin_lock_bh(&q->lock); elem_info = mlxsw_pci_queue_elem_info_producer_get(q); if (!elem_info) { @@ -2145,7 +2183,7 @@ static int mlxsw_pci_skb_transmit(void *bus_priv, struct sk_buff *skb, err = -EAGAIN; goto unlock; } - mlxsw_skb_cb(skb)->tx_info = *tx_info; + mlxsw_skb_cb(skb)->tx_info = txhdr_info->tx_info; elem_info->sdq.skb = skb; wqe = elem_info->elem; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index aa71993daf28..d714311fd884 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -107,74 +107,6 @@ static const unsigned char mlxsw_sp2_mac_mask[ETH_ALEN] = { 0xff, 0xff, 0xff, 0xff, 0xf0, 0x00 }; -/* tx_hdr_version - * Tx header version. - * Must be set to 1. - */ -MLXSW_ITEM32(tx, hdr, version, 0x00, 28, 4); - -/* tx_hdr_ctl - * Packet control type. - * 0 - Ethernet control (e.g. EMADs, LACP) - * 1 - Ethernet data - */ -MLXSW_ITEM32(tx, hdr, ctl, 0x00, 26, 2); - -/* tx_hdr_proto - * Packet protocol type. Must be set to 1 (Ethernet). - */ -MLXSW_ITEM32(tx, hdr, proto, 0x00, 21, 3); - -/* tx_hdr_rx_is_router - * Packet is sent from the router. Valid for data packets only. - */ -MLXSW_ITEM32(tx, hdr, rx_is_router, 0x00, 19, 1); - -/* tx_hdr_fid_valid - * Indicates if the 'fid' field is valid and should be used for - * forwarding lookup. Valid for data packets only. - */ -MLXSW_ITEM32(tx, hdr, fid_valid, 0x00, 16, 1); - -/* tx_hdr_swid - * Switch partition ID. Must be set to 0. - */ -MLXSW_ITEM32(tx, hdr, swid, 0x00, 12, 3); - -/* tx_hdr_control_tclass - * Indicates if the packet should use the control TClass and not one - * of the data TClasses. - */ -MLXSW_ITEM32(tx, hdr, control_tclass, 0x00, 6, 1); - -/* tx_hdr_etclass - * Egress TClass to be used on the egress device on the egress port. - */ -MLXSW_ITEM32(tx, hdr, etclass, 0x00, 0, 4); - -/* tx_hdr_port_mid - * Destination local port for unicast packets. - * Destination multicast ID for multicast packets. - * - * Control packets are directed to a specific egress port, while data - * packets are transmitted through the CPU port (0) into the switch partition, - * where forwarding rules are applied. - */ -MLXSW_ITEM32(tx, hdr, port_mid, 0x04, 16, 16); - -/* tx_hdr_fid - * Forwarding ID used for L2 forwarding lookup. Valid only if 'fid_valid' is - * set, otherwise calculated based on the packet's VID using VID to FID mapping. - * Valid for data packets only. - */ -MLXSW_ITEM32(tx, hdr, fid, 0x08, 16, 16); - -/* tx_hdr_type - * 0 - Data packets - * 6 - Control packets - */ -MLXSW_ITEM32(tx, hdr, type, 0x0C, 0, 4); - int mlxsw_sp_flow_counter_get(struct mlxsw_sp *mlxsw_sp, unsigned int counter_index, bool clear, u64 *packets, u64 *bytes) @@ -233,61 +165,6 @@ void mlxsw_sp_flow_counter_free(struct mlxsw_sp *mlxsw_sp, counter_index); } -void mlxsw_sp_txhdr_construct(struct sk_buff *skb, - const struct mlxsw_tx_info *tx_info) -{ - char *txhdr = skb_push(skb, MLXSW_TXHDR_LEN); - - memset(txhdr, 0, MLXSW_TXHDR_LEN); - - mlxsw_tx_hdr_version_set(txhdr, MLXSW_TXHDR_VERSION_1); - mlxsw_tx_hdr_ctl_set(txhdr, MLXSW_TXHDR_ETH_CTL); - mlxsw_tx_hdr_proto_set(txhdr, MLXSW_TXHDR_PROTO_ETH); - mlxsw_tx_hdr_swid_set(txhdr, 0); - mlxsw_tx_hdr_control_tclass_set(txhdr, 1); - mlxsw_tx_hdr_port_mid_set(txhdr, tx_info->local_port); - mlxsw_tx_hdr_type_set(txhdr, MLXSW_TXHDR_TYPE_CONTROL); -} - -int -mlxsw_sp_txhdr_ptp_data_construct(struct mlxsw_core *mlxsw_core, - struct mlxsw_sp_port *mlxsw_sp_port, - struct sk_buff *skb, - const struct mlxsw_tx_info *tx_info) -{ - char *txhdr; - u16 max_fid; - int err; - - if (skb_cow_head(skb, MLXSW_TXHDR_LEN)) { - err = -ENOMEM; - goto err_skb_cow_head; - } - - if (!MLXSW_CORE_RES_VALID(mlxsw_core, FID)) { - err = -EIO; - goto err_res_valid; - } - max_fid = MLXSW_CORE_RES_GET(mlxsw_core, FID); - - txhdr = skb_push(skb, MLXSW_TXHDR_LEN); - memset(txhdr, 0, MLXSW_TXHDR_LEN); - - mlxsw_tx_hdr_version_set(txhdr, MLXSW_TXHDR_VERSION_1); - mlxsw_tx_hdr_proto_set(txhdr, MLXSW_TXHDR_PROTO_ETH); - mlxsw_tx_hdr_rx_is_router_set(txhdr, true); - mlxsw_tx_hdr_fid_valid_set(txhdr, true); - mlxsw_tx_hdr_fid_set(txhdr, max_fid + tx_info->local_port - 1); - mlxsw_tx_hdr_type_set(txhdr, MLXSW_TXHDR_TYPE_DATA); - return 0; - -err_res_valid: -err_skb_cow_head: - this_cpu_inc(mlxsw_sp_port->pcpu_stats->tx_dropped); - dev_kfree_skb_any(skb); - return err; -} - static bool mlxsw_sp_skb_requires_ts(struct sk_buff *skb) { unsigned int type; @@ -299,30 +176,49 @@ static bool mlxsw_sp_skb_requires_ts(struct sk_buff *skb) return !!ptp_parse_header(skb, type); } -static int mlxsw_sp_txhdr_handle(struct mlxsw_core *mlxsw_core, - struct mlxsw_sp_port *mlxsw_sp_port, - struct sk_buff *skb, - const struct mlxsw_tx_info *tx_info) +static void mlxsw_sp_txhdr_info_data_init(struct mlxsw_core *mlxsw_core, + struct sk_buff *skb, + struct mlxsw_txhdr_info *txhdr_info) { - struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); + /* Resource validation was done as part of PTP init. */ + u16 max_fid = MLXSW_CORE_RES_GET(mlxsw_core, FID); + + txhdr_info->data = true; + txhdr_info->max_fid = max_fid; +} - /* In Spectrum-2 and Spectrum-3, PTP events that require a time stamp - * need special handling and cannot be transmitted as regular control - * packets. +static struct sk_buff * +mlxsw_sp_vlan_tag_push(struct mlxsw_sp *mlxsw_sp, struct sk_buff *skb) +{ + /* In some Spectrum ASICs, in order for PTP event packets to have their + * correction field correctly set on the egress port they must be + * transmitted as data packets. Such packets ingress the ASIC via the + * CPU port and must have a VLAN tag, as the CPU port is not configured + * with a PVID. Push the default VLAN (4095), which is configured as + * egress untagged on all the ports. */ - if (unlikely(mlxsw_sp_skb_requires_ts(skb))) - return mlxsw_sp->ptp_ops->txhdr_construct(mlxsw_core, - mlxsw_sp_port, skb, - tx_info); + if (skb_vlan_tagged(skb)) + return skb; - if (skb_cow_head(skb, MLXSW_TXHDR_LEN)) { - this_cpu_inc(mlxsw_sp_port->pcpu_stats->tx_dropped); - dev_kfree_skb_any(skb); - return -ENOMEM; - } + return vlan_insert_tag_set_proto(skb, htons(ETH_P_8021Q), + MLXSW_SP_DEFAULT_VID); +} - mlxsw_sp_txhdr_construct(skb, tx_info); - return 0; +static struct sk_buff * +mlxsw_sp_txhdr_preparations(struct mlxsw_sp *mlxsw_sp, struct sk_buff *skb, + struct mlxsw_txhdr_info *txhdr_info) +{ + if (likely(!mlxsw_sp_skb_requires_ts(skb))) + return skb; + + if (!mlxsw_sp->ptp_ops->tx_as_data) + return skb; + + /* Special handling for PTP events that require a time stamp and cannot + * be transmitted as regular control packets. + */ + mlxsw_sp_txhdr_info_data_init(mlxsw_sp->core, skb, txhdr_info); + return mlxsw_sp_vlan_tag_push(mlxsw_sp, skb); } enum mlxsw_reg_spms_state mlxsw_sp_stp_spms_state(u8 state) @@ -721,16 +617,16 @@ static netdev_tx_t mlxsw_sp_port_xmit(struct sk_buff *skb, struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; struct mlxsw_sp_port_pcpu_stats *pcpu_stats; - const struct mlxsw_tx_info tx_info = { - .local_port = mlxsw_sp_port->local_port, - .is_emad = false, + struct mlxsw_txhdr_info txhdr_info = { + .tx_info.local_port = mlxsw_sp_port->local_port, + .tx_info.is_emad = false, }; u64 len; int err; memset(skb->cb, 0, sizeof(struct mlxsw_skb_cb)); - if (mlxsw_core_skb_transmit_busy(mlxsw_sp->core, &tx_info)) + if (mlxsw_core_skb_transmit_busy(mlxsw_sp->core, &txhdr_info.tx_info)) return NETDEV_TX_BUSY; if (eth_skb_pad(skb)) { @@ -738,10 +634,11 @@ static netdev_tx_t mlxsw_sp_port_xmit(struct sk_buff *skb, return NETDEV_TX_OK; } - err = mlxsw_sp_txhdr_handle(mlxsw_sp->core, mlxsw_sp_port, skb, - &tx_info); - if (err) + skb = mlxsw_sp_txhdr_preparations(mlxsw_sp, skb, &txhdr_info); + if (!skb) { + this_cpu_inc(mlxsw_sp_port->pcpu_stats->tx_dropped); return NETDEV_TX_OK; + } /* TX header is consumed by HW on the way so we shouldn't count its * bytes as being sent. @@ -751,7 +648,7 @@ static netdev_tx_t mlxsw_sp_port_xmit(struct sk_buff *skb, /* Due to a race we might fail here because of a full queue. In that * unlikely case we simply drop the packet. */ - err = mlxsw_core_skb_transmit(mlxsw_sp->core, skb, &tx_info); + err = mlxsw_core_skb_transmit(mlxsw_sp->core, skb, &txhdr_info); if (!err) { pcpu_stats = this_cpu_ptr(mlxsw_sp_port->pcpu_stats); @@ -2792,7 +2689,6 @@ static const struct mlxsw_sp_ptp_ops mlxsw_sp1_ptp_ops = { .get_stats_count = mlxsw_sp1_get_stats_count, .get_stats_strings = mlxsw_sp1_get_stats_strings, .get_stats = mlxsw_sp1_get_stats, - .txhdr_construct = mlxsw_sp_ptp_txhdr_construct, }; static const struct mlxsw_sp_ptp_ops mlxsw_sp2_ptp_ops = { @@ -2811,7 +2707,7 @@ static const struct mlxsw_sp_ptp_ops mlxsw_sp2_ptp_ops = { .get_stats_count = mlxsw_sp2_get_stats_count, .get_stats_strings = mlxsw_sp2_get_stats_strings, .get_stats = mlxsw_sp2_get_stats, - .txhdr_construct = mlxsw_sp2_ptp_txhdr_construct, + .tx_as_data = true, }; static const struct mlxsw_sp_ptp_ops mlxsw_sp4_ptp_ops = { @@ -2830,7 +2726,6 @@ static const struct mlxsw_sp_ptp_ops mlxsw_sp4_ptp_ops = { .get_stats_count = mlxsw_sp2_get_stats_count, .get_stats_strings = mlxsw_sp2_get_stats_strings, .get_stats = mlxsw_sp2_get_stats, - .txhdr_construct = mlxsw_sp_ptp_txhdr_construct, }; struct mlxsw_sp_sample_trigger_node { @@ -3992,11 +3887,9 @@ static struct mlxsw_driver mlxsw_sp1_driver = { .trap_policer_fini = mlxsw_sp_trap_policer_fini, .trap_policer_set = mlxsw_sp_trap_policer_set, .trap_policer_counter_get = mlxsw_sp_trap_policer_counter_get, - .txhdr_construct = mlxsw_sp_txhdr_construct, .resources_register = mlxsw_sp1_resources_register, .kvd_sizes_get = mlxsw_sp_kvd_sizes_get, .ptp_transmitted = mlxsw_sp_ptp_transmitted, - .txhdr_len = MLXSW_TXHDR_LEN, .profile = &mlxsw_sp1_config_profile, .sdq_supports_cqe_v2 = false, }; @@ -4030,10 +3923,8 @@ static struct mlxsw_driver mlxsw_sp2_driver = { .trap_policer_fini = mlxsw_sp_trap_policer_fini, .trap_policer_set = mlxsw_sp_trap_policer_set, .trap_policer_counter_get = mlxsw_sp_trap_policer_counter_get, - .txhdr_construct = mlxsw_sp_txhdr_construct, .resources_register = mlxsw_sp2_resources_register, .ptp_transmitted = mlxsw_sp_ptp_transmitted, - .txhdr_len = MLXSW_TXHDR_LEN, .profile = &mlxsw_sp2_config_profile, .sdq_supports_cqe_v2 = true, }; @@ -4067,10 +3958,8 @@ static struct mlxsw_driver mlxsw_sp3_driver = { .trap_policer_fini = mlxsw_sp_trap_policer_fini, .trap_policer_set = mlxsw_sp_trap_policer_set, .trap_policer_counter_get = mlxsw_sp_trap_policer_counter_get, - .txhdr_construct = mlxsw_sp_txhdr_construct, .resources_register = mlxsw_sp2_resources_register, .ptp_transmitted = mlxsw_sp_ptp_transmitted, - .txhdr_len = MLXSW_TXHDR_LEN, .profile = &mlxsw_sp2_config_profile, .sdq_supports_cqe_v2 = true, }; @@ -4102,10 +3991,8 @@ static struct mlxsw_driver mlxsw_sp4_driver = { .trap_policer_fini = mlxsw_sp_trap_policer_fini, .trap_policer_set = mlxsw_sp_trap_policer_set, .trap_policer_counter_get = mlxsw_sp_trap_policer_counter_get, - .txhdr_construct = mlxsw_sp_txhdr_construct, .resources_register = mlxsw_sp2_resources_register, .ptp_transmitted = mlxsw_sp_ptp_transmitted, - .txhdr_len = MLXSW_TXHDR_LEN, .profile = &mlxsw_sp4_config_profile, .sdq_supports_cqe_v2 = true, }; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 8d3c61287696..b10f80fc651b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -243,10 +243,7 @@ struct mlxsw_sp_ptp_ops { void (*get_stats_strings)(u8 **p); void (*get_stats)(struct mlxsw_sp_port *mlxsw_sp_port, u64 *data, int data_index); - int (*txhdr_construct)(struct mlxsw_core *mlxsw_core, - struct mlxsw_sp_port *mlxsw_sp_port, - struct sk_buff *skb, - const struct mlxsw_tx_info *tx_info); + bool tx_as_data; }; struct mlxsw_sp_fid_core_ops { @@ -711,12 +708,6 @@ int mlxsw_sp_flow_counter_alloc(struct mlxsw_sp *mlxsw_sp, unsigned int *p_counter_index); void mlxsw_sp_flow_counter_free(struct mlxsw_sp *mlxsw_sp, unsigned int counter_index); -void mlxsw_sp_txhdr_construct(struct sk_buff *skb, - const struct mlxsw_tx_info *tx_info); -int mlxsw_sp_txhdr_ptp_data_construct(struct mlxsw_core *mlxsw_core, - struct mlxsw_sp_port *mlxsw_sp_port, - struct sk_buff *skb, - const struct mlxsw_tx_info *tx_info); bool mlxsw_sp_port_dev_check(const struct net_device *dev); struct mlxsw_sp *mlxsw_sp_lower_get(struct net_device *dev); struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find(struct net_device *dev); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c index 69cd689dbc83..5afe6b155ef0 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c @@ -1003,10 +1003,10 @@ static void mlxsw_sp_mr_route_stats_update(struct mlxsw_sp *mlxsw_sp, mr->mr_ops->route_stats(mlxsw_sp, mr_route->route_priv, &packets, &bytes); - if (mr_route->mfc->mfc_un.res.pkt != packets) - mr_route->mfc->mfc_un.res.lastuse = jiffies; - mr_route->mfc->mfc_un.res.pkt = packets; - mr_route->mfc->mfc_un.res.bytes = bytes; + if (atomic_long_read(&mr_route->mfc->mfc_un.res.pkt) != packets) + WRITE_ONCE(mr_route->mfc->mfc_un.res.lastuse, jiffies); + atomic_long_set(&mr_route->mfc->mfc_un.res.pkt, packets); + atomic_long_set(&mr_route->mfc->mfc_un.res.bytes, bytes); } static void mlxsw_sp_mr_stats_update(struct work_struct *work) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c index d94081c7658e..ca8b9d18fbb9 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c @@ -1353,6 +1353,10 @@ struct mlxsw_sp_ptp_state *mlxsw_sp2_ptp_init(struct mlxsw_sp *mlxsw_sp) struct mlxsw_sp2_ptp_state *ptp_state; int err; + /* Max FID will be used in data path, check validity as part of init. */ + if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, FID)) + return ERR_PTR(-EIO); + ptp_state = kzalloc(sizeof(*ptp_state), GFP_KERNEL); if (!ptp_state) return ERR_PTR(-ENOMEM); @@ -1679,43 +1683,3 @@ int mlxsw_sp2_ptp_get_ts_info(struct mlxsw_sp *mlxsw_sp, return 0; } - -int mlxsw_sp_ptp_txhdr_construct(struct mlxsw_core *mlxsw_core, - struct mlxsw_sp_port *mlxsw_sp_port, - struct sk_buff *skb, - const struct mlxsw_tx_info *tx_info) -{ - if (skb_cow_head(skb, MLXSW_TXHDR_LEN)) { - this_cpu_inc(mlxsw_sp_port->pcpu_stats->tx_dropped); - dev_kfree_skb_any(skb); - return -ENOMEM; - } - - mlxsw_sp_txhdr_construct(skb, tx_info); - return 0; -} - -int mlxsw_sp2_ptp_txhdr_construct(struct mlxsw_core *mlxsw_core, - struct mlxsw_sp_port *mlxsw_sp_port, - struct sk_buff *skb, - const struct mlxsw_tx_info *tx_info) -{ - /* In Spectrum-2 and Spectrum-3, in order for PTP event packets to have - * their correction field correctly set on the egress port they must be - * transmitted as data packets. Such packets ingress the ASIC via the - * CPU port and must have a VLAN tag, as the CPU port is not configured - * with a PVID. Push the default VLAN (4095), which is configured as - * egress untagged on all the ports. - */ - if (!skb_vlan_tagged(skb)) { - skb = vlan_insert_tag_set_proto(skb, htons(ETH_P_8021Q), - MLXSW_SP_DEFAULT_VID); - if (!skb) { - this_cpu_inc(mlxsw_sp_port->pcpu_stats->tx_dropped); - return -ENOMEM; - } - } - - return mlxsw_sp_txhdr_ptp_data_construct(mlxsw_core, mlxsw_sp_port, skb, - tx_info); -} diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h index c8aa1452fbb9..102db9060135 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h @@ -49,11 +49,6 @@ void mlxsw_sp1_get_stats_strings(u8 **p); void mlxsw_sp1_get_stats(struct mlxsw_sp_port *mlxsw_sp_port, u64 *data, int data_index); -int mlxsw_sp_ptp_txhdr_construct(struct mlxsw_core *mlxsw_core, - struct mlxsw_sp_port *mlxsw_sp_port, - struct sk_buff *skb, - const struct mlxsw_tx_info *tx_info); - struct mlxsw_sp_ptp_clock * mlxsw_sp2_ptp_clock_init(struct mlxsw_sp *mlxsw_sp, struct device *dev); @@ -78,11 +73,6 @@ int mlxsw_sp2_ptp_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port, int mlxsw_sp2_ptp_get_ts_info(struct mlxsw_sp *mlxsw_sp, struct kernel_ethtool_ts_info *info); -int mlxsw_sp2_ptp_txhdr_construct(struct mlxsw_core *mlxsw_core, - struct mlxsw_sp_port *mlxsw_sp_port, - struct sk_buff *skb, - const struct mlxsw_tx_info *tx_info); - #else static inline struct mlxsw_sp_ptp_clock * @@ -157,15 +147,6 @@ static inline void mlxsw_sp1_get_stats(struct mlxsw_sp_port *mlxsw_sp_port, { } -static inline int -mlxsw_sp_ptp_txhdr_construct(struct mlxsw_core *mlxsw_core, - struct mlxsw_sp_port *mlxsw_sp_port, - struct sk_buff *skb, - const struct mlxsw_tx_info *tx_info) -{ - return -EOPNOTSUPP; -} - static inline struct mlxsw_sp_ptp_clock * mlxsw_sp2_ptp_clock_init(struct mlxsw_sp *mlxsw_sp, struct device *dev) { @@ -211,15 +192,6 @@ mlxsw_sp2_ptp_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port, { return -EOPNOTSUPP; } - -static inline int -mlxsw_sp2_ptp_txhdr_construct(struct mlxsw_core *mlxsw_core, - struct mlxsw_sp_port *mlxsw_sp_port, - struct sk_buff *skb, - const struct mlxsw_tx_info *tx_info) -{ - return -EOPNOTSUPP; -} #endif static inline void mlxsw_sp2_ptp_shaper_work(struct work_struct *work) diff --git a/drivers/net/ethernet/mellanox/mlxsw/txheader.h b/drivers/net/ethernet/mellanox/mlxsw/txheader.h index da51dd9d5e44..e78cba5821b6 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/txheader.h +++ b/drivers/net/ethernet/mellanox/mlxsw/txheader.h @@ -4,6 +4,69 @@ #ifndef _MLXSW_TXHEADER_H #define _MLXSW_TXHEADER_H +/* tx_hdr_version + * Tx header version. + * Must be set to 1. + */ +MLXSW_ITEM32(tx, hdr, version, 0x00, 28, 4); + +/* tx_hdr_ctl + * Packet control type. + * 0 - Ethernet control (e.g. EMADs, LACP) + * 1 - Ethernet data + */ +MLXSW_ITEM32(tx, hdr, ctl, 0x00, 26, 2); + +/* tx_hdr_proto + * Packet protocol type. Must be set to 1 (Ethernet). + */ +MLXSW_ITEM32(tx, hdr, proto, 0x00, 21, 3); + +/* tx_hdr_rx_is_router + * Packet is sent from the router. Valid for data packets only. + */ +MLXSW_ITEM32(tx, hdr, rx_is_router, 0x00, 19, 1); + +/* tx_hdr_fid_valid + * Indicates if the 'fid' field is valid and should be used for + * forwarding lookup. Valid for data packets only. + */ +MLXSW_ITEM32(tx, hdr, fid_valid, 0x00, 16, 1); + +/* tx_hdr_swid + * Switch partition ID. Must be set to 0. + */ +MLXSW_ITEM32(tx, hdr, swid, 0x00, 12, 3); + +/* tx_hdr_control_tclass + * Indicates if the packet should use the control TClass and not one + * of the data TClasses. + */ +MLXSW_ITEM32(tx, hdr, control_tclass, 0x00, 6, 1); + +/* tx_hdr_port_mid + * Destination local port for unicast packets. + * Destination multicast ID for multicast packets. + * + * Control packets are directed to a specific egress port, while data + * packets are transmitted through the CPU port (0) into the switch partition, + * where forwarding rules are applied. + */ +MLXSW_ITEM32(tx, hdr, port_mid, 0x04, 16, 16); + +/* tx_hdr_fid + * Forwarding ID used for L2 forwarding lookup. Valid only if 'fid_valid' is + * set, otherwise calculated based on the packet's VID using VID to FID mapping. + * Valid for data packets only. + */ +MLXSW_ITEM32(tx, hdr, fid, 0x08, 16, 16); + +/* tx_hdr_type + * 0 - Data packets + * 6 - Control packets + */ +MLXSW_ITEM32(tx, hdr, type, 0x0C, 0, 4); + #define MLXSW_TXHDR_LEN 0x10 #define MLXSW_TXHDR_VERSION_0 0 #define MLXSW_TXHDR_VERSION_1 1 diff --git a/drivers/net/ethernet/meta/fbnic/Makefile b/drivers/net/ethernet/meta/fbnic/Makefile index ea6214ca48e7..239b2258ec65 100644 --- a/drivers/net/ethernet/meta/fbnic/Makefile +++ b/drivers/net/ethernet/meta/fbnic/Makefile @@ -13,6 +13,7 @@ fbnic-y := fbnic_csr.o \ fbnic_ethtool.o \ fbnic_fw.o \ fbnic_hw_stats.o \ + fbnic_hwmon.o \ fbnic_irq.o \ fbnic_mac.o \ fbnic_netdev.o \ diff --git a/drivers/net/ethernet/meta/fbnic/fbnic.h b/drivers/net/ethernet/meta/fbnic/fbnic.h index 50f97f5399ff..14751f16e125 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic.h @@ -24,6 +24,7 @@ struct fbnic_dev { struct device *dev; struct net_device *netdev; struct dentry *dbg_fbd; + struct device *hwmon; u32 __iomem *uc_addr0; u32 __iomem *uc_addr4; @@ -41,6 +42,7 @@ struct fbnic_dev { struct fbnic_fw_mbx mbx[FBNIC_IPC_MBX_INDICES]; struct fbnic_fw_cap fw_cap; + struct fbnic_fw_completion *cmpl_data; /* Lock protecting Tx Mailbox queue to prevent possible races */ spinlock_t fw_tx_lock; @@ -149,6 +151,9 @@ void fbnic_devlink_unregister(struct fbnic_dev *fbd); int fbnic_fw_enable_mbx(struct fbnic_dev *fbd); void fbnic_fw_disable_mbx(struct fbnic_dev *fbd); +void fbnic_hwmon_register(struct fbnic_dev *fbd); +void fbnic_hwmon_unregister(struct fbnic_dev *fbd); + int fbnic_pcs_irq_enable(struct fbnic_dev *fbd); void fbnic_pcs_irq_disable(struct fbnic_dev *fbd); diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c index 8f7a2a19ddf8..bbc7c1c0c37e 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c @@ -228,6 +228,63 @@ static void fbnic_mbx_process_tx_msgs(struct fbnic_dev *fbd) tx_mbx->head = head; } +static int fbnic_mbx_map_req_w_cmpl(struct fbnic_dev *fbd, + struct fbnic_tlv_msg *msg, + struct fbnic_fw_completion *cmpl_data) +{ + unsigned long flags; + int err; + + spin_lock_irqsave(&fbd->fw_tx_lock, flags); + + /* If we are already waiting on a completion then abort */ + if (cmpl_data && fbd->cmpl_data) { + err = -EBUSY; + goto unlock_mbx; + } + + /* Record completion location and submit request */ + if (cmpl_data) + fbd->cmpl_data = cmpl_data; + + err = fbnic_mbx_map_msg(fbd, FBNIC_IPC_MBX_TX_IDX, msg, + le16_to_cpu(msg->hdr.len) * sizeof(u32), 1); + + /* If msg failed then clear completion data for next caller */ + if (err && cmpl_data) + fbd->cmpl_data = NULL; + +unlock_mbx: + spin_unlock_irqrestore(&fbd->fw_tx_lock, flags); + + return err; +} + +static void fbnic_fw_release_cmpl_data(struct kref *kref) +{ + struct fbnic_fw_completion *cmpl_data; + + cmpl_data = container_of(kref, struct fbnic_fw_completion, + ref_count); + kfree(cmpl_data); +} + +static struct fbnic_fw_completion * +fbnic_fw_get_cmpl_by_type(struct fbnic_dev *fbd, u32 msg_type) +{ + struct fbnic_fw_completion *cmpl_data = NULL; + unsigned long flags; + + spin_lock_irqsave(&fbd->fw_tx_lock, flags); + if (fbd->cmpl_data && fbd->cmpl_data->msg_type == msg_type) { + cmpl_data = fbd->cmpl_data; + kref_get(&fbd->cmpl_data->ref_count); + } + spin_unlock_irqrestore(&fbd->fw_tx_lock, flags); + + return cmpl_data; +} + /** * fbnic_fw_xmit_simple_msg - Transmit a simple single TLV message w/o data * @fbd: FBNIC device structure @@ -651,6 +708,84 @@ void fbnic_fw_check_heartbeat(struct fbnic_dev *fbd) dev_warn(fbd->dev, "Failed to send heartbeat message\n"); } +/** + * fbnic_fw_xmit_tsene_read_msg - Create and transmit a sensor read request + * @fbd: FBNIC device structure + * @cmpl_data: Completion data structure to store sensor response + * + * Asks the firmware to provide an update with the latest sensor data. + * The response will contain temperature and voltage readings. + * + * Return: 0 on success, negative error value on failure + */ +int fbnic_fw_xmit_tsene_read_msg(struct fbnic_dev *fbd, + struct fbnic_fw_completion *cmpl_data) +{ + struct fbnic_tlv_msg *msg; + int err; + + if (!fbnic_fw_present(fbd)) + return -ENODEV; + + msg = fbnic_tlv_msg_alloc(FBNIC_TLV_MSG_ID_TSENE_READ_REQ); + if (!msg) + return -ENOMEM; + + err = fbnic_mbx_map_req_w_cmpl(fbd, msg, cmpl_data); + if (err) + goto free_message; + + return 0; + +free_message: + free_page((unsigned long)msg); + return err; +} + +static const struct fbnic_tlv_index fbnic_tsene_read_resp_index[] = { + FBNIC_TLV_ATTR_S32(FBNIC_TSENE_THERM), + FBNIC_TLV_ATTR_S32(FBNIC_TSENE_VOLT), + FBNIC_TLV_ATTR_S32(FBNIC_TSENE_ERROR), + FBNIC_TLV_ATTR_LAST +}; + +static int fbnic_fw_parse_tsene_read_resp(void *opaque, + struct fbnic_tlv_msg **results) +{ + struct fbnic_fw_completion *cmpl_data; + struct fbnic_dev *fbd = opaque; + int err = 0; + + /* Verify we have a completion pointer to provide with data */ + cmpl_data = fbnic_fw_get_cmpl_by_type(fbd, + FBNIC_TLV_MSG_ID_TSENE_READ_RESP); + if (!cmpl_data) + return -EINVAL; + + if (results[FBNIC_TSENE_ERROR]) { + err = fbnic_tlv_attr_get_unsigned(results[FBNIC_TSENE_ERROR]); + if (err) + goto exit_complete; + } + + if (!results[FBNIC_TSENE_THERM] || !results[FBNIC_TSENE_VOLT]) { + err = -EINVAL; + goto exit_complete; + } + + cmpl_data->u.tsene.millidegrees = + fbnic_tlv_attr_get_signed(results[FBNIC_TSENE_THERM]); + cmpl_data->u.tsene.millivolts = + fbnic_tlv_attr_get_signed(results[FBNIC_TSENE_VOLT]); + +exit_complete: + cmpl_data->result = err; + complete(&cmpl_data->done); + fbnic_fw_put_cmpl(cmpl_data); + + return err; +} + static const struct fbnic_tlv_parser fbnic_fw_tlv_parser[] = { FBNIC_TLV_PARSER(FW_CAP_RESP, fbnic_fw_cap_resp_index, fbnic_fw_parse_cap_resp), @@ -658,6 +793,9 @@ static const struct fbnic_tlv_parser fbnic_fw_tlv_parser[] = { fbnic_fw_parse_ownership_resp), FBNIC_TLV_PARSER(HEARTBEAT_RESP, fbnic_heartbeat_resp_index, fbnic_fw_parse_heartbeat_resp), + FBNIC_TLV_PARSER(TSENE_READ_RESP, + fbnic_tsene_read_resp_index, + fbnic_fw_parse_tsene_read_resp), FBNIC_TLV_MSG_ERROR }; @@ -802,3 +940,25 @@ void fbnic_get_fw_ver_commit_str(struct fbnic_dev *fbd, char *fw_version, fbnic_mk_full_fw_ver_str(mgmt->version, delim, mgmt->commit, fw_version, str_sz); } + +void fbnic_fw_init_cmpl(struct fbnic_fw_completion *fw_cmpl, + u32 msg_type) +{ + fw_cmpl->msg_type = msg_type; + init_completion(&fw_cmpl->done); + kref_init(&fw_cmpl->ref_count); +} + +void fbnic_fw_clear_compl(struct fbnic_dev *fbd) +{ + unsigned long flags; + + spin_lock_irqsave(&fbd->fw_tx_lock, flags); + fbd->cmpl_data = NULL; + spin_unlock_irqrestore(&fbd->fw_tx_lock, flags); +} + +void fbnic_fw_put_cmpl(struct fbnic_fw_completion *fw_cmpl) +{ + kref_put(&fw_cmpl->ref_count, fbnic_fw_release_cmpl_data); +} diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_fw.h b/drivers/net/ethernet/meta/fbnic/fbnic_fw.h index 221faf8c6756..fe68333d51b1 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_fw.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic_fw.h @@ -44,6 +44,19 @@ struct fbnic_fw_cap { u8 link_fec; }; +struct fbnic_fw_completion { + u32 msg_type; + struct completion done; + struct kref ref_count; + int result; + union { + struct { + s32 millivolts; + s32 millidegrees; + } tsene; + } u; +}; + void fbnic_mbx_init(struct fbnic_dev *fbd); void fbnic_mbx_clean(struct fbnic_dev *fbd); void fbnic_mbx_poll(struct fbnic_dev *fbd); @@ -52,6 +65,12 @@ void fbnic_mbx_flush_tx(struct fbnic_dev *fbd); int fbnic_fw_xmit_ownership_msg(struct fbnic_dev *fbd, bool take_ownership); int fbnic_fw_init_heartbeat(struct fbnic_dev *fbd, bool poll); void fbnic_fw_check_heartbeat(struct fbnic_dev *fbd); +int fbnic_fw_xmit_tsene_read_msg(struct fbnic_dev *fbd, + struct fbnic_fw_completion *cmpl_data); +void fbnic_fw_init_cmpl(struct fbnic_fw_completion *cmpl_data, + u32 msg_type); +void fbnic_fw_clear_compl(struct fbnic_dev *fbd); +void fbnic_fw_put_cmpl(struct fbnic_fw_completion *cmpl_data); #define fbnic_mk_full_fw_ver_str(_rev_id, _delim, _commit, _str, _str_sz) \ do { \ @@ -76,6 +95,8 @@ enum { FBNIC_TLV_MSG_ID_OWNERSHIP_RESP = 0x13, FBNIC_TLV_MSG_ID_HEARTBEAT_REQ = 0x14, FBNIC_TLV_MSG_ID_HEARTBEAT_RESP = 0x15, + FBNIC_TLV_MSG_ID_TSENE_READ_REQ = 0x3C, + FBNIC_TLV_MSG_ID_TSENE_READ_RESP = 0x3D, }; #define FBNIC_FW_CAP_RESP_VERSION_MAJOR CSR_GENMASK(31, 24) @@ -118,6 +139,13 @@ enum { }; enum { + FBNIC_TSENE_THERM = 0x0, + FBNIC_TSENE_VOLT = 0x1, + FBNIC_TSENE_ERROR = 0x2, + FBNIC_TSENE_MSG_MAX +}; + +enum { FBNIC_FW_OWNERSHIP_FLAG = 0x0, FBNIC_FW_OWNERSHIP_MSG_MAX }; diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_hwmon.c b/drivers/net/ethernet/meta/fbnic/fbnic_hwmon.c new file mode 100644 index 000000000000..def8598aceec --- /dev/null +++ b/drivers/net/ethernet/meta/fbnic/fbnic_hwmon.c @@ -0,0 +1,81 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) Meta Platforms, Inc. and affiliates. */ + +#include <linux/hwmon.h> + +#include "fbnic.h" +#include "fbnic_mac.h" + +static int fbnic_hwmon_sensor_id(enum hwmon_sensor_types type) +{ + if (type == hwmon_temp) + return FBNIC_SENSOR_TEMP; + if (type == hwmon_in) + return FBNIC_SENSOR_VOLTAGE; + + return -EOPNOTSUPP; +} + +static umode_t fbnic_hwmon_is_visible(const void *drvdata, + enum hwmon_sensor_types type, + u32 attr, int channel) +{ + if (type == hwmon_temp && attr == hwmon_temp_input) + return 0444; + if (type == hwmon_in && attr == hwmon_in_input) + return 0444; + + return 0; +} + +static int fbnic_hwmon_read(struct device *dev, enum hwmon_sensor_types type, + u32 attr, int channel, long *val) +{ + struct fbnic_dev *fbd = dev_get_drvdata(dev); + const struct fbnic_mac *mac = fbd->mac; + int id; + + id = fbnic_hwmon_sensor_id(type); + return id < 0 ? id : mac->get_sensor(fbd, id, val); +} + +static const struct hwmon_ops fbnic_hwmon_ops = { + .is_visible = fbnic_hwmon_is_visible, + .read = fbnic_hwmon_read, +}; + +static const struct hwmon_channel_info *fbnic_hwmon_info[] = { + HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT), + HWMON_CHANNEL_INFO(in, HWMON_I_INPUT), + NULL +}; + +static const struct hwmon_chip_info fbnic_chip_info = { + .ops = &fbnic_hwmon_ops, + .info = fbnic_hwmon_info, +}; + +void fbnic_hwmon_register(struct fbnic_dev *fbd) +{ + if (!IS_REACHABLE(CONFIG_HWMON)) + return; + + fbd->hwmon = hwmon_device_register_with_info(fbd->dev, "fbnic", + fbd, &fbnic_chip_info, + NULL); + if (IS_ERR(fbd->hwmon)) { + dev_notice(fbd->dev, + "Failed to register hwmon device %pe\n", + fbd->hwmon); + fbd->hwmon = NULL; + } +} + +void fbnic_hwmon_unregister(struct fbnic_dev *fbd) +{ + if (!IS_REACHABLE(CONFIG_HWMON) || !fbd->hwmon) + return; + + hwmon_device_unregister(fbd->hwmon); + fbd->hwmon = NULL; +} diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_mac.c b/drivers/net/ethernet/meta/fbnic/fbnic_mac.c index 7b654d0a6dac..14291401f463 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_mac.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_mac.c @@ -686,6 +686,77 @@ fbnic_mac_get_eth_mac_stats(struct fbnic_dev *fbd, bool reset, MAC_STAT_TX_BROADCAST); } +static int fbnic_mac_get_sensor_asic(struct fbnic_dev *fbd, int id, + long *val) +{ + struct fbnic_fw_completion *fw_cmpl; + int err = 0, retries = 5; + s32 *sensor; + + fw_cmpl = kzalloc(sizeof(*fw_cmpl), GFP_KERNEL); + if (!fw_cmpl) + return -ENOMEM; + + /* Initialize completion and queue it for FW to process */ + fbnic_fw_init_cmpl(fw_cmpl, FBNIC_TLV_MSG_ID_TSENE_READ_RESP); + + switch (id) { + case FBNIC_SENSOR_TEMP: + sensor = &fw_cmpl->u.tsene.millidegrees; + break; + case FBNIC_SENSOR_VOLTAGE: + sensor = &fw_cmpl->u.tsene.millivolts; + break; + default: + err = -EINVAL; + goto exit_free; + } + + err = fbnic_fw_xmit_tsene_read_msg(fbd, fw_cmpl); + if (err) { + dev_err(fbd->dev, + "Failed to transmit TSENE read msg, err %d\n", + err); + goto exit_free; + } + + /* Allow 2 seconds for reply, resend and try up to 5 times */ + while (!wait_for_completion_timeout(&fw_cmpl->done, 2 * HZ)) { + retries--; + + if (retries == 0) { + dev_err(fbd->dev, + "Timed out waiting for TSENE read\n"); + err = -ETIMEDOUT; + goto exit_cleanup; + } + + err = fbnic_fw_xmit_tsene_read_msg(fbd, NULL); + if (err) { + dev_err(fbd->dev, + "Failed to transmit TSENE read msg, err %d\n", + err); + goto exit_cleanup; + } + } + + /* Handle error returned by firmware */ + if (fw_cmpl->result) { + err = fw_cmpl->result; + dev_err(fbd->dev, "%s: Firmware returned error %d\n", + __func__, err); + goto exit_cleanup; + } + + *val = *sensor; +exit_cleanup: + fbnic_fw_clear_compl(fbd); +exit_free: + fbnic_fw_put_cmpl(fw_cmpl); + + return err; +} + static const struct fbnic_mac fbnic_mac_asic = { .init_regs = fbnic_mac_init_regs, .pcs_enable = fbnic_pcs_enable_asic, @@ -695,6 +766,7 @@ static const struct fbnic_mac fbnic_mac_asic = { .get_eth_mac_stats = fbnic_mac_get_eth_mac_stats, .link_down = fbnic_mac_link_down_asic, .link_up = fbnic_mac_link_up_asic, + .get_sensor = fbnic_mac_get_sensor_asic, }; /** diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_mac.h b/drivers/net/ethernet/meta/fbnic/fbnic_mac.h index 476239a9d381..05a591653e09 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_mac.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic_mac.h @@ -47,6 +47,11 @@ enum { #define FBNIC_LINK_MODE_PAM4 (FBNIC_LINK_50R1) #define FBNIC_LINK_MODE_MASK (FBNIC_LINK_AUTO - 1) +enum fbnic_sensor_id { + FBNIC_SENSOR_TEMP, /* Temp in millidegrees Centigrade */ + FBNIC_SENSOR_VOLTAGE, /* Voltage in millivolts */ +}; + /* This structure defines the interface hooks for the MAC. The MAC hooks * will be configured as a const struct provided with a set of function * pointers. @@ -83,6 +88,8 @@ struct fbnic_mac { void (*link_down)(struct fbnic_dev *fbd); void (*link_up)(struct fbnic_dev *fbd, bool tx_pause, bool rx_pause); + + int (*get_sensor)(struct fbnic_dev *fbd, int id, long *val); }; int fbnic_mac_init(struct fbnic_dev *fbd); diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_pci.c b/drivers/net/ethernet/meta/fbnic/fbnic_pci.c index 2c96980d150d..6cbbc2ee3e1f 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_pci.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_pci.c @@ -296,6 +296,8 @@ static int fbnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* Capture snapshot of hardware stats so netdev can calculate delta */ fbnic_reset_hw_stats(fbd); + fbnic_hwmon_register(fbd); + if (!fbd->dsn) { dev_warn(&pdev->dev, "Reading serial number failed\n"); goto init_failure_mode; @@ -358,6 +360,7 @@ static void fbnic_remove(struct pci_dev *pdev) fbnic_netdev_free(fbd); } + fbnic_hwmon_unregister(fbd); fbnic_dbg_fbd_exit(fbd); fbnic_devlink_unregister(fbd); fbnic_fw_disable_mbx(fbd); diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_phylink.c b/drivers/net/ethernet/meta/fbnic/fbnic_phylink.c index 1a5e1e719b30..bb11fc83367d 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_phylink.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_phylink.c @@ -15,7 +15,7 @@ fbnic_pcs_to_net(struct phylink_pcs *pcs) } static void -fbnic_phylink_pcs_get_state(struct phylink_pcs *pcs, +fbnic_phylink_pcs_get_state(struct phylink_pcs *pcs, unsigned int neg_mode, struct phylink_link_state *state) { struct fbnic_net *fbn = fbnic_pcs_to_net(pcs); diff --git a/drivers/net/ethernet/microchip/lan743x_ethtool.c b/drivers/net/ethernet/microchip/lan743x_ethtool.c index 1a1cbd034eda..1459acfb1e61 100644 --- a/drivers/net/ethernet/microchip/lan743x_ethtool.c +++ b/drivers/net/ethernet/microchip/lan743x_ethtool.c @@ -1055,9 +1055,6 @@ static int lan743x_ethtool_get_eee(struct net_device *netdev, { struct lan743x_adapter *adapter = netdev_priv(netdev); - eee->tx_lpi_timer = lan743x_csr_read(adapter, - MAC_EEE_TX_LPI_REQ_DLY_CNT); - return phylink_ethtool_get_eee(adapter->phylink, eee); } @@ -1065,24 +1062,6 @@ static int lan743x_ethtool_set_eee(struct net_device *netdev, struct ethtool_keee *eee) { struct lan743x_adapter *adapter = netdev_priv(netdev); - u32 tx_lpi_timer; - - tx_lpi_timer = lan743x_csr_read(adapter, MAC_EEE_TX_LPI_REQ_DLY_CNT); - if (tx_lpi_timer != eee->tx_lpi_timer) { - u32 mac_cr = lan743x_csr_read(adapter, MAC_CR); - - /* Software should only change this field when Energy Efficient - * Ethernet Enable (EEEEN) is cleared. - * This function will trigger an autonegotiation restart and - * eee will be reenabled during link up if eee was negotiated. - */ - lan743x_mac_eee_enable(adapter, false); - lan743x_csr_write(adapter, MAC_EEE_TX_LPI_REQ_DLY_CNT, - eee->tx_lpi_timer); - - if (mac_cr & MAC_CR_EEE_EN_) - lan743x_mac_eee_enable(adapter, true); - } return phylink_ethtool_set_eee(adapter->phylink, eee); } diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index 4dc5adcda6a3..23760b613d3e 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -2966,7 +2966,7 @@ static int lan743x_phylink_2500basex_config(struct lan743x_adapter *adapter) return lan743x_pcs_power_reset(adapter); } -void lan743x_mac_eee_enable(struct lan743x_adapter *adapter, bool enable) +static void lan743x_mac_eee_enable(struct lan743x_adapter *adapter, bool enable) { u32 mac_cr; @@ -3027,10 +3027,8 @@ static void lan743x_phylink_mac_link_down(struct phylink_config *config, phy_interface_t interface) { struct net_device *netdev = to_net_dev(config->dev); - struct lan743x_adapter *adapter = netdev_priv(netdev); - netif_tx_stop_all_queues(to_net_dev(config->dev)); - lan743x_mac_eee_enable(adapter, false); + netif_tx_stop_all_queues(netdev); } static void lan743x_phylink_mac_link_up(struct phylink_config *config, @@ -3072,16 +3070,40 @@ static void lan743x_phylink_mac_link_up(struct phylink_config *config, cap & FLOW_CTRL_TX, cap & FLOW_CTRL_RX); - if (phydev) - lan743x_mac_eee_enable(adapter, phydev->enable_tx_lpi); - netif_tx_wake_all_queues(netdev); } +static void lan743x_mac_disable_tx_lpi(struct phylink_config *config) +{ + struct net_device *netdev = to_net_dev(config->dev); + struct lan743x_adapter *adapter = netdev_priv(netdev); + + lan743x_mac_eee_enable(adapter, false); +} + +static int lan743x_mac_enable_tx_lpi(struct phylink_config *config, u32 timer, + bool tx_clk_stop) +{ + struct net_device *netdev = to_net_dev(config->dev); + struct lan743x_adapter *adapter = netdev_priv(netdev); + + /* Software should only change this field when Energy Efficient + * Ethernet Enable (EEEEN) is cleared. We ensure that by clearing + * EEEEN during probe, and phylink itself guarantees that + * mac_disable_tx_lpi() will have been previously called. + */ + lan743x_csr_write(adapter, MAC_EEE_TX_LPI_REQ_DLY_CNT, timer); + lan743x_mac_eee_enable(adapter, true); + + return 0; +} + static const struct phylink_mac_ops lan743x_phylink_mac_ops = { .mac_config = lan743x_phylink_mac_config, .mac_link_down = lan743x_phylink_mac_link_down, .mac_link_up = lan743x_phylink_mac_link_up, + .mac_disable_tx_lpi = lan743x_mac_disable_tx_lpi, + .mac_enable_tx_lpi = lan743x_mac_enable_tx_lpi, }; static int lan743x_phylink_create(struct lan743x_adapter *adapter) @@ -3095,6 +3117,9 @@ static int lan743x_phylink_create(struct lan743x_adapter *adapter) adapter->phylink_config.mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | MAC_10 | MAC_100 | MAC_1000FD; + adapter->phylink_config.lpi_capabilities = MAC_100FD | MAC_1000FD; + adapter->phylink_config.lpi_timer_default = + lan743x_csr_read(adapter, MAC_EEE_TX_LPI_REQ_DLY_CNT); lan743x_phy_interface_select(adapter); @@ -3120,6 +3145,10 @@ static int lan743x_phylink_create(struct lan743x_adapter *adapter) phy_interface_set_rgmii(adapter->phylink_config.supported_interfaces); } + memcpy(adapter->phylink_config.lpi_interfaces, + adapter->phylink_config.supported_interfaces, + sizeof(adapter->phylink_config.lpi_interfaces)); + pl = phylink_create(&adapter->phylink_config, NULL, adapter->phy_interface, &lan743x_phylink_mac_ops); @@ -3517,6 +3546,9 @@ static int lan743x_hardware_init(struct lan743x_adapter *adapter, spin_lock_init(&tx->ring_lock); } + /* Ensure EEEEN is clear */ + lan743x_mac_eee_enable(adapter, false); + return 0; } diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h index 8ef897c114d3..7f73d66854be 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.h +++ b/drivers/net/ethernet/microchip/lan743x_main.h @@ -1206,6 +1206,5 @@ void lan743x_hs_syslock_release(struct lan743x_adapter *adapter); void lan743x_mac_flow_ctrl_set_enables(struct lan743x_adapter *adapter, bool tx_enable, bool rx_enable); int lan743x_sgmii_read(struct lan743x_adapter *adapter, u8 mmd, u16 addr); -void lan743x_mac_eee_enable(struct lan743x_adapter *adapter, bool enable); #endif /* _LAN743X_H */ diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h index 25cb2f61986f..1efa584e7107 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h @@ -443,7 +443,7 @@ int lan966x_stats_init(struct lan966x *lan966x); void lan966x_port_config_down(struct lan966x_port *port); void lan966x_port_config_up(struct lan966x_port *port); -void lan966x_port_status_get(struct lan966x_port *port, +void lan966x_port_status_get(struct lan966x_port *port, unsigned int neg_mode, struct phylink_link_state *state); int lan966x_port_pcs_set(struct lan966x_port *port, struct lan966x_port_config *config); diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_phylink.c b/drivers/net/ethernet/microchip/lan966x/lan966x_phylink.c index 1d63903f9006..75188b99e4e7 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_phylink.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_phylink.c @@ -88,11 +88,12 @@ static struct lan966x_port *lan966x_pcs_to_port(struct phylink_pcs *pcs) } static void lan966x_pcs_get_state(struct phylink_pcs *pcs, + unsigned int neg_mode, struct phylink_link_state *state) { struct lan966x_port *port = lan966x_pcs_to_port(pcs); - lan966x_port_status_get(port, state); + lan966x_port_status_get(port, neg_mode, state); } static int lan966x_pcs_config(struct phylink_pcs *pcs, unsigned int neg_mode, diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_port.c b/drivers/net/ethernet/microchip/lan966x/lan966x_port.c index fdfa4040d9ee..cf7de0267c32 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_port.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_port.c @@ -284,7 +284,7 @@ void lan966x_port_config_up(struct lan966x_port *port) lan966x_port_link_up(port); } -void lan966x_port_status_get(struct lan966x_port *port, +void lan966x_port_status_get(struct lan966x_port *port, unsigned int neg_mode, struct phylink_link_state *state) { struct lan966x *lan966x = port->lan966x; @@ -314,7 +314,7 @@ void lan966x_port_status_get(struct lan966x_port *port, bmsr |= BMSR_ANEGCOMPLETE; lp_adv = DEV_PCS1G_ANEG_STATUS_LP_ADV_GET(val); - phylink_mii_c22_pcs_decode_state(state, bmsr, lp_adv); + phylink_mii_c22_pcs_decode_state(state, neg_mode, bmsr, lp_adv); } else { if (!state->link) return; diff --git a/drivers/net/ethernet/microchip/sparx5/Kconfig b/drivers/net/ethernet/microchip/sparx5/Kconfig index 35b057c9d0cb..35e1c0cf345e 100644 --- a/drivers/net/ethernet/microchip/sparx5/Kconfig +++ b/drivers/net/ethernet/microchip/sparx5/Kconfig @@ -28,5 +28,6 @@ config SPARX5_DCB config LAN969X_SWITCH bool "Lan969x switch driver" depends on SPARX5_SWITCH + select PAGE_POOL help This driver supports the lan969x family of network switch devices. diff --git a/drivers/net/ethernet/microchip/sparx5/Makefile b/drivers/net/ethernet/microchip/sparx5/Makefile index 3f34e83246a0..d447f9e84d92 100644 --- a/drivers/net/ethernet/microchip/sparx5/Makefile +++ b/drivers/net/ethernet/microchip/sparx5/Makefile @@ -21,7 +21,8 @@ sparx5-switch-$(CONFIG_LAN969X_SWITCH) += lan969x/lan969x_regs.o \ lan969x/lan969x_calendar.o \ lan969x/lan969x_vcap_ag_api.o \ lan969x/lan969x_vcap_impl.o \ - lan969x/lan969x_rgmii.o + lan969x/lan969x_rgmii.o \ + lan969x/lan969x_fdma.o # Provide include files ccflags-y += -I$(srctree)/drivers/net/ethernet/microchip/vcap diff --git a/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x.c b/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x.c index 396f76b6eea5..f3a9c71bea36 100644 --- a/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x.c +++ b/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x.c @@ -341,6 +341,10 @@ static const struct sparx5_ops lan969x_ops = { .ptp_irq_handler = &lan969x_ptp_irq_handler, .dsm_calendar_calc = &lan969x_dsm_calendar_calc, .port_config_rgmii = &lan969x_port_config_rgmii, + .fdma_init = &lan969x_fdma_init, + .fdma_deinit = &lan969x_fdma_deinit, + .fdma_poll = &lan969x_fdma_napi_poll, + .fdma_xmit = &lan969x_fdma_xmit, }; const struct sparx5_match_data lan969x_desc = { diff --git a/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x.h b/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x.h index 9a7ddebecf1e..529fde3d4deb 100644 --- a/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x.h +++ b/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x.h @@ -72,4 +72,11 @@ int lan969x_dsm_calendar_calc(struct sparx5 *sparx5, u32 taxi, int lan969x_port_config_rgmii(struct sparx5_port *port, struct sparx5_port_config *conf); +/* lan969x_fdma.c */ +int lan969x_fdma_init(struct sparx5 *sparx5); +int lan969x_fdma_deinit(struct sparx5 *sparx5); +int lan969x_fdma_napi_poll(struct napi_struct *napi, int weight); +int lan969x_fdma_xmit(struct sparx5 *sparx5, u32 *ifh, struct sk_buff *skb, + struct net_device *dev); + #endif diff --git a/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x_fdma.c b/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x_fdma.c new file mode 100644 index 000000000000..1282f5c3ee6d --- /dev/null +++ b/drivers/net/ethernet/microchip/sparx5/lan969x/lan969x_fdma.c @@ -0,0 +1,406 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Microchip lan969x Switch driver + * + * Copyright (c) 2025 Microchip Technology Inc. and its subsidiaries. + */ +#include <net/page_pool/helpers.h> + +#include "../sparx5_main.h" +#include "../sparx5_main_regs.h" +#include "../sparx5_port.h" + +#include "fdma_api.h" +#include "lan969x.h" + +#define FDMA_PRIV(fdma) ((struct sparx5 *)((fdma)->priv)) + +static int lan969x_fdma_tx_dataptr_cb(struct fdma *fdma, int dcb, int db, + u64 *dataptr) +{ + *dataptr = FDMA_PRIV(fdma)->tx.dbs[dcb].dma_addr; + + return 0; +} + +static int lan969x_fdma_rx_dataptr_cb(struct fdma *fdma, int dcb, int db, + u64 *dataptr) +{ + struct sparx5_rx *rx = &FDMA_PRIV(fdma)->rx; + struct page *page; + + page = page_pool_dev_alloc_pages(rx->page_pool); + if (unlikely(!page)) + return -ENOMEM; + + rx->page[dcb][db] = page; + + *dataptr = page_pool_get_dma_addr(page); + + return 0; +} + +static int lan969x_fdma_get_next_dcb(struct sparx5_tx *tx) +{ + struct fdma *fdma = &tx->fdma; + + for (int i = 0; i < fdma->n_dcbs; ++i) + if (!tx->dbs[i].used && !fdma_is_last(fdma, &fdma->dcbs[i])) + return i; + + return -ENOSPC; +} + +static void lan969x_fdma_tx_clear_buf(struct sparx5 *sparx5, int weight) +{ + struct fdma *fdma = &sparx5->tx.fdma; + struct sparx5_tx_buf *db; + unsigned long flags; + int i; + + spin_lock_irqsave(&sparx5->tx_lock, flags); + + for (i = 0; i < fdma->n_dcbs; ++i) { + db = &sparx5->tx.dbs[i]; + + if (!db->used) + continue; + + if (!fdma_db_is_done(fdma_db_get(fdma, i, 0))) + continue; + + db->dev->stats.tx_bytes += db->skb->len; + db->dev->stats.tx_packets++; + sparx5->tx.packets++; + + dma_unmap_single(sparx5->dev, + db->dma_addr, + db->skb->len, + DMA_TO_DEVICE); + + if (!db->ptp) + napi_consume_skb(db->skb, weight); + + db->used = false; + } + + spin_unlock_irqrestore(&sparx5->tx_lock, flags); +} + +static void lan969x_fdma_free_pages(struct sparx5_rx *rx) +{ + struct fdma *fdma = &rx->fdma; + + for (int i = 0; i < fdma->n_dcbs; ++i) { + for (int j = 0; j < fdma->n_dbs; ++j) + page_pool_put_full_page(rx->page_pool, + rx->page[i][j], false); + } +} + +static struct sk_buff *lan969x_fdma_rx_get_frame(struct sparx5 *sparx5, + struct sparx5_rx *rx) +{ + const struct sparx5_consts *consts = sparx5->data->consts; + struct fdma *fdma = &rx->fdma; + struct sparx5_port *port; + struct frame_info fi; + struct sk_buff *skb; + struct fdma_db *db; + struct page *page; + + db = &fdma->dcbs[fdma->dcb_index].db[fdma->db_index]; + page = rx->page[fdma->dcb_index][fdma->db_index]; + + sparx5_ifh_parse(sparx5, page_address(page), &fi); + port = fi.src_port < consts->n_ports ? sparx5->ports[fi.src_port] : + NULL; + if (WARN_ON(!port)) + goto free_page; + + skb = build_skb(page_address(page), fdma->db_size); + if (unlikely(!skb)) + goto free_page; + + skb_mark_for_recycle(skb); + skb_put(skb, fdma_db_len_get(db)); + skb_pull(skb, IFH_LEN * sizeof(u32)); + + skb->dev = port->ndev; + + if (likely(!(skb->dev->features & NETIF_F_RXFCS))) + skb_trim(skb, skb->len - ETH_FCS_LEN); + + sparx5_ptp_rxtstamp(sparx5, skb, fi.timestamp); + skb->protocol = eth_type_trans(skb, skb->dev); + + if (test_bit(port->portno, sparx5->bridge_mask)) + skb->offload_fwd_mark = 1; + + skb->dev->stats.rx_bytes += skb->len; + skb->dev->stats.rx_packets++; + + return skb; + +free_page: + page_pool_recycle_direct(rx->page_pool, page); + + return NULL; +} + +static int lan969x_fdma_rx_alloc(struct sparx5 *sparx5) +{ + struct sparx5_rx *rx = &sparx5->rx; + struct fdma *fdma = &rx->fdma; + int err; + + struct page_pool_params pp_params = { + .order = 0, + .flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV, + .pool_size = fdma->n_dcbs * fdma->n_dbs, + .nid = NUMA_NO_NODE, + .dev = sparx5->dev, + .dma_dir = DMA_FROM_DEVICE, + .offset = 0, + .max_len = fdma->db_size - + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)), + }; + + rx->page_pool = page_pool_create(&pp_params); + if (IS_ERR(rx->page_pool)) + return PTR_ERR(rx->page_pool); + + err = fdma_alloc_coherent(sparx5->dev, fdma); + if (err) + return err; + + fdma_dcbs_init(fdma, + FDMA_DCB_INFO_DATAL(fdma->db_size), + FDMA_DCB_STATUS_INTR); + + return 0; +} + +static int lan969x_fdma_tx_alloc(struct sparx5 *sparx5) +{ + struct sparx5_tx *tx = &sparx5->tx; + struct fdma *fdma = &tx->fdma; + int err; + + tx->dbs = kcalloc(fdma->n_dcbs, + sizeof(struct sparx5_tx_buf), + GFP_KERNEL); + if (!tx->dbs) + return -ENOMEM; + + err = fdma_alloc_coherent(sparx5->dev, fdma); + if (err) { + kfree(tx->dbs); + return err; + } + + fdma_dcbs_init(fdma, + FDMA_DCB_INFO_DATAL(fdma->db_size), + FDMA_DCB_STATUS_DONE); + + return 0; +} + +static void lan969x_fdma_rx_init(struct sparx5 *sparx5) +{ + struct fdma *fdma = &sparx5->rx.fdma; + + fdma->channel_id = FDMA_XTR_CHANNEL; + fdma->n_dcbs = FDMA_DCB_MAX; + fdma->n_dbs = 1; + fdma->priv = sparx5; + fdma->size = fdma_get_size(fdma); + fdma->db_size = PAGE_SIZE; + fdma->ops.dataptr_cb = &lan969x_fdma_rx_dataptr_cb; + fdma->ops.nextptr_cb = &fdma_nextptr_cb; + + /* Fetch a netdev for SKB and NAPI use, any will do */ + for (int idx = 0; idx < sparx5->data->consts->n_ports; ++idx) { + struct sparx5_port *port = sparx5->ports[idx]; + + if (port && port->ndev) { + sparx5->rx.ndev = port->ndev; + break; + } + } +} + +static void lan969x_fdma_tx_init(struct sparx5 *sparx5) +{ + struct fdma *fdma = &sparx5->tx.fdma; + + fdma->channel_id = FDMA_INJ_CHANNEL; + fdma->n_dcbs = FDMA_DCB_MAX; + fdma->n_dbs = 1; + fdma->priv = sparx5; + fdma->size = fdma_get_size(fdma); + fdma->db_size = PAGE_SIZE; + fdma->ops.dataptr_cb = &lan969x_fdma_tx_dataptr_cb; + fdma->ops.nextptr_cb = &fdma_nextptr_cb; +} + +int lan969x_fdma_napi_poll(struct napi_struct *napi, int weight) +{ + struct sparx5_rx *rx = container_of(napi, struct sparx5_rx, napi); + struct sparx5 *sparx5 = container_of(rx, struct sparx5, rx); + int old_dcb, dcb_reload, counter = 0; + struct fdma *fdma = &rx->fdma; + struct sk_buff *skb; + + dcb_reload = fdma->dcb_index; + + lan969x_fdma_tx_clear_buf(sparx5, weight); + + /* Process RX data */ + while (counter < weight) { + if (!fdma_has_frames(fdma)) + break; + + skb = lan969x_fdma_rx_get_frame(sparx5, rx); + if (!skb) + break; + + napi_gro_receive(&rx->napi, skb); + + fdma_db_advance(fdma); + counter++; + /* Check if the DCB can be reused */ + if (fdma_dcb_is_reusable(fdma)) + continue; + + fdma_db_reset(fdma); + fdma_dcb_advance(fdma); + } + + /* Allocate new pages and map them */ + while (dcb_reload != fdma->dcb_index) { + old_dcb = dcb_reload; + dcb_reload++; + /* n_dcbs must be a power of 2 */ + dcb_reload &= fdma->n_dcbs - 1; + + fdma_dcb_add(fdma, + old_dcb, + FDMA_DCB_INFO_DATAL(fdma->db_size), + FDMA_DCB_STATUS_INTR); + + sparx5_fdma_reload(sparx5, fdma); + } + + if (counter < weight && napi_complete_done(napi, counter)) + spx5_wr(0xff, sparx5, FDMA_INTR_DB_ENA); + + return counter; +} + +int lan969x_fdma_xmit(struct sparx5 *sparx5, u32 *ifh, struct sk_buff *skb, + struct net_device *dev) +{ + int next_dcb, needed_headroom, needed_tailroom, err; + struct sparx5_tx *tx = &sparx5->tx; + struct fdma *fdma = &tx->fdma; + struct sparx5_tx_buf *db_buf; + u64 status; + + next_dcb = lan969x_fdma_get_next_dcb(tx); + if (next_dcb < 0) + return -EBUSY; + + needed_headroom = max_t(int, IFH_LEN * 4 - skb_headroom(skb), 0); + needed_tailroom = max_t(int, ETH_FCS_LEN - skb_tailroom(skb), 0); + if (needed_headroom || needed_tailroom || skb_header_cloned(skb)) { + err = pskb_expand_head(skb, needed_headroom, needed_tailroom, + GFP_ATOMIC); + if (unlikely(err)) + return err; + } + + skb_push(skb, IFH_LEN * 4); + memcpy(skb->data, ifh, IFH_LEN * 4); + skb_put(skb, ETH_FCS_LEN); + + db_buf = &tx->dbs[next_dcb]; + db_buf->dma_addr = dma_map_single(sparx5->dev, + skb->data, + skb->len, + DMA_TO_DEVICE); + if (dma_mapping_error(sparx5->dev, db_buf->dma_addr)) + return -ENOMEM; + + db_buf->dev = dev; + db_buf->skb = skb; + db_buf->ptp = false; + db_buf->used = true; + + if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP && + SPARX5_SKB_CB(skb)->rew_op == IFH_REW_OP_TWO_STEP_PTP) + db_buf->ptp = true; + + status = FDMA_DCB_STATUS_SOF | + FDMA_DCB_STATUS_EOF | + FDMA_DCB_STATUS_BLOCKO(0) | + FDMA_DCB_STATUS_BLOCKL(skb->len) | + FDMA_DCB_STATUS_INTR; + + fdma_dcb_advance(fdma); + fdma_dcb_add(fdma, next_dcb, 0, status); + + sparx5_fdma_reload(sparx5, fdma); + + return NETDEV_TX_OK; +} + +int lan969x_fdma_init(struct sparx5 *sparx5) +{ + struct sparx5_rx *rx = &sparx5->rx; + int err; + + lan969x_fdma_rx_init(sparx5); + lan969x_fdma_tx_init(sparx5); + sparx5_fdma_injection_mode(sparx5); + + err = dma_set_mask_and_coherent(sparx5->dev, DMA_BIT_MASK(64)); + if (err) { + dev_err(sparx5->dev, "Failed to set 64-bit FDMA mask"); + return err; + } + + err = lan969x_fdma_rx_alloc(sparx5); + if (err) { + dev_err(sparx5->dev, "Failed to allocate RX buffers: %d\n", + err); + return err; + } + + err = lan969x_fdma_tx_alloc(sparx5); + if (err) { + fdma_free_coherent(sparx5->dev, &rx->fdma); + dev_err(sparx5->dev, "Failed to allocate TX buffers: %d\n", + err); + return err; + } + + /* Reset FDMA state */ + spx5_wr(FDMA_CTRL_NRESET_SET(0), sparx5, FDMA_CTRL); + spx5_wr(FDMA_CTRL_NRESET_SET(1), sparx5, FDMA_CTRL); + + return err; +} + +int lan969x_fdma_deinit(struct sparx5 *sparx5) +{ + struct sparx5_rx *rx = &sparx5->rx; + struct sparx5_tx *tx = &sparx5->tx; + + sparx5_fdma_stop(sparx5); + fdma_free_coherent(sparx5->dev, &tx->fdma); + fdma_free_coherent(sparx5->dev, &rx->fdma); + lan969x_fdma_free_pages(rx); + page_pool_destroy(rx->page_pool); + + return 0; +} diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c b/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c index 0027144a2af2..dbe86f937b21 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c @@ -18,9 +18,6 @@ #include "sparx5_main.h" #include "sparx5_port.h" -#define FDMA_XTR_CHANNEL 6 -#define FDMA_INJ_CHANNEL 0 - #define FDMA_XTR_BUFFER_SIZE 2048 #define FDMA_WEIGHT 4 @@ -133,7 +130,7 @@ static void sparx5_fdma_tx_deactivate(struct sparx5 *sparx5, struct sparx5_tx *t sparx5, FDMA_CH_ACTIVATE); } -static void sparx5_fdma_reload(struct sparx5 *sparx5, struct fdma *fdma) +void sparx5_fdma_reload(struct sparx5 *sparx5, struct fdma *fdma) { /* Reload the RX channel */ spx5_wr(BIT(fdma->channel_id), sparx5, FDMA_CH_RELOAD); @@ -183,7 +180,7 @@ static bool sparx5_fdma_rx_get_frame(struct sparx5 *sparx5, struct sparx5_rx *rx return true; } -static int sparx5_fdma_napi_callback(struct napi_struct *napi, int weight) +int sparx5_fdma_napi_callback(struct napi_struct *napi, int weight) { struct sparx5_rx *rx = container_of(napi, struct sparx5_rx, napi); struct sparx5 *sparx5 = container_of(rx, struct sparx5, rx); @@ -213,11 +210,11 @@ static int sparx5_fdma_napi_callback(struct napi_struct *napi, int weight) return counter; } -int sparx5_fdma_xmit(struct sparx5 *sparx5, u32 *ifh, struct sk_buff *skb) +int sparx5_fdma_xmit(struct sparx5 *sparx5, u32 *ifh, struct sk_buff *skb, + struct net_device *dev) { struct sparx5_tx *tx = &sparx5->tx; struct fdma *fdma = &tx->fdma; - static bool first_time = true; void *virt_addr; fdma_dcb_advance(fdma); @@ -238,12 +235,8 @@ int sparx5_fdma_xmit(struct sparx5 *sparx5, u32 *ifh, struct sk_buff *skb) FDMA_DCB_STATUS_BLOCKO(0) | FDMA_DCB_STATUS_BLOCKL(skb->len + IFH_LEN * 4 + 4)); - if (first_time) { - sparx5_fdma_tx_activate(sparx5, tx); - first_time = false; - } else { - sparx5_fdma_reload(sparx5, fdma); - } + sparx5_fdma_reload(sparx5, fdma); + return NETDEV_TX_OK; } @@ -260,10 +253,6 @@ static int sparx5_fdma_rx_alloc(struct sparx5 *sparx5) fdma_dcbs_init(fdma, FDMA_DCB_INFO_DATAL(fdma->db_size), FDMA_DCB_STATUS_INTR); - netif_napi_add_weight(rx->ndev, &rx->napi, sparx5_fdma_napi_callback, - FDMA_WEIGHT); - napi_enable(&rx->napi); - sparx5_fdma_rx_activate(sparx5, rx); return 0; } @@ -348,7 +337,7 @@ irqreturn_t sparx5_fdma_handler(int irq, void *args) return IRQ_HANDLED; } -static void sparx5_fdma_injection_mode(struct sparx5 *sparx5) +void sparx5_fdma_injection_mode(struct sparx5 *sparx5) { const int byte_swap = 1; int portno; @@ -410,7 +399,7 @@ static void sparx5_fdma_injection_mode(struct sparx5 *sparx5) } } -int sparx5_fdma_start(struct sparx5 *sparx5) +int sparx5_fdma_init(struct sparx5 *sparx5) { int err; @@ -443,24 +432,55 @@ int sparx5_fdma_start(struct sparx5 *sparx5) return err; } +int sparx5_fdma_deinit(struct sparx5 *sparx5) +{ + sparx5_fdma_stop(sparx5); + fdma_free_phys(&sparx5->rx.fdma); + fdma_free_phys(&sparx5->tx.fdma); + + return 0; +} + static u32 sparx5_fdma_port_ctrl(struct sparx5 *sparx5) { return spx5_rd(sparx5, FDMA_PORT_CTRL(0)); } +int sparx5_fdma_start(struct sparx5 *sparx5) +{ + const struct sparx5_ops *ops = sparx5->data->ops; + struct sparx5_rx *rx = &sparx5->rx; + struct sparx5_tx *tx = &sparx5->tx; + + netif_napi_add_weight(rx->ndev, + &rx->napi, + ops->fdma_poll, + FDMA_WEIGHT); + + napi_enable(&rx->napi); + + sparx5_fdma_rx_activate(sparx5, rx); + sparx5_fdma_tx_activate(sparx5, tx); + + return 0; +} + int sparx5_fdma_stop(struct sparx5 *sparx5) { + struct sparx5_rx *rx = &sparx5->rx; + struct sparx5_tx *tx = &sparx5->tx; u32 val; - napi_disable(&sparx5->rx.napi); + napi_disable(&rx->napi); + /* Stop the fdma and channel interrupts */ - sparx5_fdma_rx_deactivate(sparx5, &sparx5->rx); - sparx5_fdma_tx_deactivate(sparx5, &sparx5->tx); + sparx5_fdma_rx_deactivate(sparx5, rx); + sparx5_fdma_tx_deactivate(sparx5, tx); + /* Wait for the RX channel to stop */ read_poll_timeout(sparx5_fdma_port_ctrl, val, FDMA_PORT_CTRL_XTR_BUF_IS_EMPTY_GET(val) == 0, 500, 10000, 0, sparx5); - fdma_free_phys(&sparx5->rx.fdma); - fdma_free_phys(&sparx5->tx.fdma); + return 0; } diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c index e68277c38adc..6a0e5b83ecd0 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c @@ -784,15 +784,19 @@ static int sparx5_start(struct sparx5 *sparx5) /* Start Frame DMA with fallback to register based INJ/XTR */ err = -ENXIO; - if (sparx5->fdma_irq >= 0 && is_sparx5(sparx5)) { - if (GCB_CHIP_ID_REV_ID_GET(sparx5->chip_id) > 0) + if (sparx5->fdma_irq >= 0) { + if (GCB_CHIP_ID_REV_ID_GET(sparx5->chip_id) > 0 || + !is_sparx5(sparx5)) err = devm_request_irq(sparx5->dev, sparx5->fdma_irq, sparx5_fdma_handler, 0, "sparx5-fdma", sparx5); - if (!err) - err = sparx5_fdma_start(sparx5); + if (!err) { + err = ops->fdma_init(sparx5); + if (!err) + sparx5_fdma_start(sparx5); + } if (err) sparx5->fdma_irq = -ENXIO; } else { @@ -1026,6 +1030,7 @@ cleanup_pnode: static void mchp_sparx5_remove(struct platform_device *pdev) { struct sparx5 *sparx5 = platform_get_drvdata(pdev); + const struct sparx5_ops *ops = sparx5->data->ops; debugfs_remove_recursive(sparx5->debugfs_root); if (sparx5->xtr_irq) { @@ -1037,7 +1042,7 @@ static void mchp_sparx5_remove(struct platform_device *pdev) sparx5->fdma_irq = -ENXIO; } sparx5_ptp_deinit(sparx5); - sparx5_fdma_stop(sparx5); + ops->fdma_deinit(sparx5); sparx5_cleanup_ports(sparx5); sparx5_vcap_destroy(sparx5); /* Unregister netdevs */ @@ -1092,6 +1097,10 @@ static const struct sparx5_ops sparx5_ops = { .set_port_mux = &sparx5_port_mux_set, .ptp_irq_handler = &sparx5_ptp_irq_handler, .dsm_calendar_calc = &sparx5_dsm_calendar_calc, + .fdma_init = &sparx5_fdma_init, + .fdma_deinit = &sparx5_fdma_deinit, + .fdma_poll = &sparx5_fdma_napi_callback, + .fdma_xmit = &sparx5_fdma_xmit, }; static const struct sparx5_match_data sparx5_desc = { diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h index 3ae760da17e2..fe7d8bcc0cd9 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h @@ -112,6 +112,8 @@ enum sparx5_feature { #define XTR_QUEUE 0 #define INJ_QUEUE 0 +#define FDMA_XTR_CHANNEL 6 +#define FDMA_INJ_CHANNEL 0 #define FDMA_DCB_MAX 64 #define FDMA_RX_DCB_MAX_DBS 15 #define FDMA_TX_DCB_MAX_DBS 1 @@ -157,11 +159,25 @@ struct sparx5_calendar_data { */ struct sparx5_rx { struct fdma fdma; - struct sk_buff *skb[FDMA_DCB_MAX][FDMA_RX_DCB_MAX_DBS]; + struct page_pool *page_pool; + union { + struct sk_buff *skb[FDMA_DCB_MAX][FDMA_RX_DCB_MAX_DBS]; + struct page *page[FDMA_DCB_MAX][FDMA_RX_DCB_MAX_DBS]; + }; dma_addr_t dma; struct napi_struct napi; struct net_device *ndev; u64 packets; + u8 page_order; +}; + +/* Used to store information about TX buffers. */ +struct sparx5_tx_buf { + struct net_device *dev; + struct sk_buff *skb; + dma_addr_t dma_addr; + bool used; + bool ptp; }; /* Frame DMA transmit state: @@ -169,6 +185,7 @@ struct sparx5_rx { */ struct sparx5_tx { struct fdma fdma; + struct sparx5_tx_buf *dbs; u64 packets; u64 dropped; }; @@ -326,6 +343,11 @@ struct sparx5_ops { struct sparx5_calendar_data *data); int (*port_config_rgmii)(struct sparx5_port *port, struct sparx5_port_config *conf); + int (*fdma_init)(struct sparx5 *sparx5); + int (*fdma_deinit)(struct sparx5 *sparx5); + int (*fdma_poll)(struct napi_struct *napi, int weight); + int (*fdma_xmit)(struct sparx5 *sparx5, u32 *ifh, struct sk_buff *skb, + struct net_device *dev); }; struct sparx5_main_io_resource { @@ -436,10 +458,16 @@ int sparx5_manual_injection_mode(struct sparx5 *sparx5); void sparx5_port_inj_timer_setup(struct sparx5_port *port); /* sparx5_fdma.c */ +int sparx5_fdma_init(struct sparx5 *sparx5); +int sparx5_fdma_deinit(struct sparx5 *sparx5); int sparx5_fdma_start(struct sparx5 *sparx5); int sparx5_fdma_stop(struct sparx5 *sparx5); -int sparx5_fdma_xmit(struct sparx5 *sparx5, u32 *ifh, struct sk_buff *skb); +int sparx5_fdma_napi_callback(struct napi_struct *napi, int weight); +int sparx5_fdma_xmit(struct sparx5 *sparx5, u32 *ifh, struct sk_buff *skb, + struct net_device *dev); irqreturn_t sparx5_fdma_handler(int irq, void *args); +void sparx5_fdma_reload(struct sparx5 *sparx5, struct fdma *fdma); +void sparx5_fdma_injection_mode(struct sparx5 *sparx5); /* sparx5_mactable.c */ void sparx5_mact_pull_work(struct work_struct *work); diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c index b6f635d85820..138ac58fae51 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c @@ -232,9 +232,12 @@ netdev_tx_t sparx5_port_xmit_impl(struct sk_buff *skb, struct net_device *dev) struct net_device_stats *stats = &dev->stats; struct sparx5_port *port = netdev_priv(dev); struct sparx5 *sparx5 = port->sparx5; + const struct sparx5_ops *ops; u32 ifh[IFH_LEN]; netdev_tx_t ret; + ops = sparx5->data->ops; + memset(ifh, 0, IFH_LEN * 4); sparx5_set_port_ifh(sparx5, ifh, port->portno); @@ -254,7 +257,7 @@ netdev_tx_t sparx5_port_xmit_impl(struct sk_buff *skb, struct net_device *dev) skb_tx_timestamp(skb); spin_lock(&sparx5->tx_lock); if (sparx5->fdma_irq > 0) - ret = sparx5_fdma_xmit(sparx5, ifh, skb); + ret = ops->fdma_xmit(sparx5, ifh, skb, dev); else ret = sparx5_inject(sparx5, ifh, skb, dev); spin_unlock(&sparx5->tx_lock); @@ -264,6 +267,12 @@ netdev_tx_t sparx5_port_xmit_impl(struct sk_buff *skb, struct net_device *dev) if (ret < 0) goto drop; + if (!is_sparx5(sparx5)) + /* When lan969x and TX_OK, stats and SKB consumption is handled + * in the TX completion loop, so dont go any further. + */ + return NETDEV_TX_OK; + stats->tx_bytes += skb->len; stats->tx_packets++; sparx5->tx.packets++; diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_phylink.c b/drivers/net/ethernet/microchip/sparx5/sparx5_phylink.c index 035d2f1bea0d..cfb4b2e17ace 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_phylink.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_phylink.c @@ -89,7 +89,7 @@ static struct sparx5_port *sparx5_pcs_to_port(struct phylink_pcs *pcs) return container_of(pcs, struct sparx5_port, phylink_pcs); } -static void sparx5_pcs_get_state(struct phylink_pcs *pcs, +static void sparx5_pcs_get_state(struct phylink_pcs *pcs, unsigned int neg_mode, struct phylink_link_state *state) { struct sparx5_port *port = sparx5_pcs_to_port(pcs); diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index 2dc0c6ad54be..be95336ce089 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -1656,9 +1656,9 @@ static int __init mana_driver_init(void) static void __exit mana_driver_exit(void) { - debugfs_remove(mana_debugfs_root); - pci_unregister_driver(&mana_driver); + + debugfs_remove(mana_debugfs_root); } module_init(mana_driver_init); diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c index 8d48468cddd7..7663d196eaf8 100644 --- a/drivers/net/ethernet/mscc/ocelot_net.c +++ b/drivers/net/ethernet/mscc/ocelot_net.c @@ -993,6 +993,16 @@ static int ocelot_port_get_ts_info(struct net_device *dev, return ocelot_get_ts_info(ocelot, port, info); } +static void ocelot_port_ts_stats(struct net_device *dev, + struct ethtool_ts_stats *ts_stats) +{ + struct ocelot_port_private *priv = netdev_priv(dev); + struct ocelot *ocelot = priv->port.ocelot; + int port = priv->port.index; + + ocelot_port_get_ts_stats(ocelot, port, ts_stats); +} + static const struct ethtool_ops ocelot_ethtool_ops = { .get_strings = ocelot_port_get_strings, .get_ethtool_stats = ocelot_port_get_ethtool_stats, @@ -1000,6 +1010,7 @@ static const struct ethtool_ops ocelot_ethtool_ops = { .get_link_ksettings = phy_ethtool_get_link_ksettings, .set_link_ksettings = phy_ethtool_set_link_ksettings, .get_ts_info = ocelot_port_get_ts_info, + .get_ts_stats = ocelot_port_ts_stats, }; static void ocelot_port_attr_stp_state_set(struct ocelot *ocelot, int port, diff --git a/drivers/net/ethernet/mscc/ocelot_ptp.c b/drivers/net/ethernet/mscc/ocelot_ptp.c index 808ce8e68d39..cc1088988da0 100644 --- a/drivers/net/ethernet/mscc/ocelot_ptp.c +++ b/drivers/net/ethernet/mscc/ocelot_ptp.c @@ -680,9 +680,14 @@ static int ocelot_port_queue_ptp_tx_skb(struct ocelot *ocelot, int port, skb_queue_walk_safe(&ocelot_port->tx_skbs, skb, skb_tmp) { if (time_before(OCELOT_SKB_CB(skb)->ptp_tx_time + OCELOT_PTP_TX_TSTAMP_TIMEOUT, jiffies)) { - dev_warn_ratelimited(ocelot->dev, - "port %d invalidating stale timestamp ID %u which seems lost\n", - port, OCELOT_SKB_CB(skb)->ts_id); + u64_stats_update_begin(&ocelot_port->ts_stats->syncp); + ocelot_port->ts_stats->lost++; + u64_stats_update_end(&ocelot_port->ts_stats->syncp); + + dev_dbg_ratelimited(ocelot->dev, + "port %d invalidating stale timestamp ID %u which seems lost\n", + port, OCELOT_SKB_CB(skb)->ts_id); + __skb_unlink(skb, &ocelot_port->tx_skbs); kfree_skb(skb); ocelot->ptp_skbs_in_flight--; @@ -748,13 +753,20 @@ int ocelot_port_txtstamp_request(struct ocelot *ocelot, int port, return 0; ptp_class = ptp_classify_raw(skb); - if (ptp_class == PTP_CLASS_NONE) - return -EINVAL; + if (ptp_class == PTP_CLASS_NONE) { + err = -EINVAL; + goto error; + } /* Store ptp_cmd in OCELOT_SKB_CB(skb)->ptp_cmd */ if (ptp_cmd == IFH_REW_OP_ORIGIN_PTP) { if (ocelot_ptp_is_onestep_sync(skb, ptp_class)) { OCELOT_SKB_CB(skb)->ptp_cmd = ptp_cmd; + + u64_stats_update_begin(&ocelot_port->ts_stats->syncp); + ocelot_port->ts_stats->onestep_pkts_unconfirmed++; + u64_stats_update_end(&ocelot_port->ts_stats->syncp); + return 0; } @@ -764,14 +776,16 @@ int ocelot_port_txtstamp_request(struct ocelot *ocelot, int port, if (ptp_cmd == IFH_REW_OP_TWO_STEP_PTP) { *clone = skb_clone_sk(skb); - if (!(*clone)) - return -ENOMEM; + if (!(*clone)) { + err = -ENOMEM; + goto error; + } /* Store timestamp ID in OCELOT_SKB_CB(clone)->ts_id */ err = ocelot_port_queue_ptp_tx_skb(ocelot, port, *clone); if (err) { kfree_skb(*clone); - return err; + goto error; } skb_shinfo(*clone)->tx_flags |= SKBTX_IN_PROGRESS; @@ -780,6 +794,12 @@ int ocelot_port_txtstamp_request(struct ocelot *ocelot, int port, } return 0; + +error: + u64_stats_update_begin(&ocelot_port->ts_stats->syncp); + ocelot_port->ts_stats->err++; + u64_stats_update_end(&ocelot_port->ts_stats->syncp); + return err; } EXPORT_SYMBOL(ocelot_port_txtstamp_request); @@ -816,6 +836,7 @@ void ocelot_get_txtstamp(struct ocelot *ocelot) while (budget--) { struct skb_shared_hwtstamps shhwtstamps; + struct ocelot_port *ocelot_port; u32 val, id, seqid, txport; struct sk_buff *skb_match; struct timespec64 ts; @@ -832,17 +853,27 @@ void ocelot_get_txtstamp(struct ocelot *ocelot) id = SYS_PTP_STATUS_PTP_MESS_ID_X(val); txport = SYS_PTP_STATUS_PTP_MESS_TXPORT_X(val); seqid = SYS_PTP_STATUS_PTP_MESS_SEQ_ID(val); + ocelot_port = ocelot->ports[txport]; /* Retrieve its associated skb */ skb_match = ocelot_port_dequeue_ptp_tx_skb(ocelot, txport, id, seqid); if (!skb_match) { - dev_warn_ratelimited(ocelot->dev, - "port %d received TX timestamp (seqid %d, ts id %u) for packet previously declared stale\n", - txport, seqid, id); + u64_stats_update_begin(&ocelot_port->ts_stats->syncp); + ocelot_port->ts_stats->err++; + u64_stats_update_end(&ocelot_port->ts_stats->syncp); + + dev_dbg_ratelimited(ocelot->dev, + "port %d received TX timestamp (seqid %d, ts id %u) for packet previously declared stale\n", + txport, seqid, id); + goto next_ts; } + u64_stats_update_begin(&ocelot_port->ts_stats->syncp); + ocelot_port->ts_stats->pkts++; + u64_stats_update_end(&ocelot_port->ts_stats->syncp); + /* Get the h/w timestamp */ ocelot_get_hwtimestamp(ocelot, &ts); diff --git a/drivers/net/ethernet/mscc/ocelot_stats.c b/drivers/net/ethernet/mscc/ocelot_stats.c index c018783757fb..545710dadcf5 100644 --- a/drivers/net/ethernet/mscc/ocelot_stats.c +++ b/drivers/net/ethernet/mscc/ocelot_stats.c @@ -821,6 +821,26 @@ void ocelot_port_get_eth_phy_stats(struct ocelot *ocelot, int port, } EXPORT_SYMBOL_GPL(ocelot_port_get_eth_phy_stats); +void ocelot_port_get_ts_stats(struct ocelot *ocelot, int port, + struct ethtool_ts_stats *ts_stats) +{ + struct ocelot_port *ocelot_port = ocelot->ports[port]; + struct ocelot_ts_stats *stats = ocelot_port->ts_stats; + unsigned int start; + + if (!ocelot->ptp) + return; + + do { + start = u64_stats_fetch_begin(&stats->syncp); + ts_stats->pkts = stats->pkts; + ts_stats->onestep_pkts_unconfirmed = stats->onestep_pkts_unconfirmed; + ts_stats->lost = stats->lost; + ts_stats->err = stats->err; + } while (u64_stats_fetch_retry(&stats->syncp, start)); +} +EXPORT_SYMBOL_GPL(ocelot_port_get_ts_stats); + void ocelot_port_get_stats64(struct ocelot *ocelot, int port, struct rtnl_link_stats64 *stats) { @@ -960,6 +980,23 @@ int ocelot_stats_init(struct ocelot *ocelot) if (!ocelot->stats) return -ENOMEM; + if (ocelot->ptp) { + for (int port = 0; port < ocelot->num_phys_ports; port++) { + struct ocelot_port *ocelot_port = ocelot->ports[port]; + + if (!ocelot_port) + continue; + + ocelot_port->ts_stats = devm_kzalloc(ocelot->dev, + sizeof(*ocelot_port->ts_stats), + GFP_KERNEL); + if (!ocelot_port->ts_stats) + return -ENOMEM; + + u64_stats_init(&ocelot_port->ts_stats->syncp); + } + } + snprintf(queue_name, sizeof(queue_name), "%s-stats", dev_name(ocelot->dev)); ocelot->stats_queue = create_singlethread_workqueue(queue_name); diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c index 9d97cd281f18..c03558adda91 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c @@ -458,7 +458,8 @@ int nfp_bpf_event_output(struct nfp_app_bpf *bpf, const void *data, map_id_full = be64_to_cpu(cbe->map_ptr); map_id = map_id_full; - if (len < sizeof(struct cmsg_bpf_event) + pkt_size + data_size) + if (size_add(pkt_size, data_size) > INT_MAX || + len < sizeof(struct cmsg_bpf_event) + pkt_size + data_size) return -EINVAL; if (cbe->hdr.ver != NFP_CCM_ABI_VERSION) return -EINVAL; diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 4b77f2151204..5a5eba49c651 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -16,7 +16,6 @@ #include <linux/clk.h> #include <linux/delay.h> #include <linux/ethtool.h> -#include <linux/hwmon.h> #include <linux/phy.h> #include <linux/if_vlan.h> #include <linux/in.h> @@ -5368,36 +5367,6 @@ static bool rtl_aspm_is_safe(struct rtl8169_private *tp) return false; } -static int r8169_hwmon_read(struct device *dev, enum hwmon_sensor_types type, - u32 attr, int channel, long *val) -{ - struct rtl8169_private *tp = dev_get_drvdata(dev); - int val_raw; - - val_raw = phy_read_paged(tp->phydev, 0xbd8, 0x12) & 0x3ff; - if (val_raw >= 512) - val_raw -= 1024; - - *val = 1000 * val_raw / 2; - - return 0; -} - -static const struct hwmon_ops r8169_hwmon_ops = { - .visible = 0444, - .read = r8169_hwmon_read, -}; - -static const struct hwmon_channel_info * const r8169_hwmon_info[] = { - HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT), - NULL -}; - -static const struct hwmon_chip_info r8169_hwmon_chip_info = { - .ops = &r8169_hwmon_ops, - .info = r8169_hwmon_info, -}; - static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) { struct rtl8169_private *tp; @@ -5577,12 +5546,6 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (rc) return rc; - /* The temperature sensor is available from RTl8125B */ - if (IS_REACHABLE(CONFIG_HWMON) && tp->mac_version >= RTL_GIGA_MAC_VER_63) - /* ignore errors */ - devm_hwmon_device_register_with_info(&pdev->dev, "nic_temp", tp, - &r8169_hwmon_chip_info, - NULL); rc = register_netdev(dev); if (rc) return rc; diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index ac0f093f647a..bc395294a32d 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -2763,6 +2763,7 @@ static const struct ravb_hw_info ravb_rzv2m_hw_info = { .net_features = NETIF_F_RXCSUM, .stats_len = ARRAY_SIZE(ravb_gstrings_stats), .tccr_mask = TCCR_TSRQ0 | TCCR_TSRQ1 | TCCR_TSRQ2 | TCCR_TSRQ3, + .tx_max_frame_size = SZ_2K, .rx_max_frame_size = SZ_2K, .rx_buffer_size = SZ_2K + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)), diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c index 4ac7a78f4b14..20d3a202bb8d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c @@ -302,15 +302,11 @@ imx_dwmac_parse_dt(struct imx_priv_data *dwmac, struct device *dev) * is required by i.MX8MP, i.MX93. * is optinoal for i.MX8DXL. */ - dwmac->intf_regmap = syscon_regmap_lookup_by_phandle(np, "intf_mode"); + dwmac->intf_regmap = + syscon_regmap_lookup_by_phandle_args(np, "intf_mode", 1, + &dwmac->intf_reg_off); if (IS_ERR(dwmac->intf_regmap)) return PTR_ERR(dwmac->intf_regmap); - - err = of_property_read_u32_index(np, "intf_mode", 1, &dwmac->intf_reg_off); - if (err) { - dev_err(dev, "Can't get intf mode reg offset (%d)\n", err); - return err; - } } return err; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c index eabc4da9e1a9..f25461c292fe 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c @@ -199,16 +199,11 @@ static int sti_dwmac_parse_data(struct sti_dwmac *dwmac, if (res) dwmac->clk_sel_reg = res->start; - regmap = syscon_regmap_lookup_by_phandle(np, "st,syscon"); + regmap = syscon_regmap_lookup_by_phandle_args(np, "st,syscon", + 1, &dwmac->ctrl_reg); if (IS_ERR(regmap)) return PTR_ERR(regmap); - err = of_property_read_u32_index(np, "st,syscon", 1, &dwmac->ctrl_reg); - if (err) { - dev_err(dev, "Can't get sysconfig ctrl offset (%d)\n", err); - return err; - } - err = of_get_phy_mode(np, &dwmac->interface); if (err && err != -ENODEV) { dev_err(dev, "Can't get phy-mode\n"); @@ -313,7 +308,6 @@ static void sti_dwmac_remove(struct platform_device *pdev) clk_disable_unprepare(dwmac->clk); } -#ifdef CONFIG_PM_SLEEP static int sti_dwmac_suspend(struct device *dev) { struct sti_dwmac *dwmac = get_stmmac_bsp_priv(dev); @@ -333,10 +327,9 @@ static int sti_dwmac_resume(struct device *dev) return stmmac_resume(dev); } -#endif /* CONFIG_PM_SLEEP */ -static SIMPLE_DEV_PM_OPS(sti_dwmac_pm_ops, sti_dwmac_suspend, - sti_dwmac_resume); +static DEFINE_SIMPLE_DEV_PM_OPS(sti_dwmac_pm_ops, sti_dwmac_suspend, + sti_dwmac_resume); static const struct sti_dwmac_of_data stih4xx_dwmac_data = { .fix_retime_src = stih4xx_fix_retime_src, @@ -353,7 +346,7 @@ static struct platform_driver sti_dwmac_driver = { .remove = sti_dwmac_remove, .driver = { .name = "sti-dwmac", - .pm = &sti_dwmac_pm_ops, + .pm = pm_sleep_ptr(&sti_dwmac_pm_ops), .of_match_table = sti_dwmac_match, }, }; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c index 1e8bac665cc9..1fcb74e9e3ff 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c @@ -419,16 +419,11 @@ static int stm32_dwmac_parse_data(struct stm32_dwmac *dwmac, } /* Get mode register */ - dwmac->regmap = syscon_regmap_lookup_by_phandle(np, "st,syscon"); + dwmac->regmap = syscon_regmap_lookup_by_phandle_args(np, "st,syscon", + 1, &dwmac->mode_reg); if (IS_ERR(dwmac->regmap)) return PTR_ERR(dwmac->regmap); - err = of_property_read_u32_index(np, "st,syscon", 1, &dwmac->mode_reg); - if (err) { - dev_err(dev, "Can't get sysconfig mode offset (%d)\n", err); - return err; - } - if (dwmac->ops->is_mp2) return 0; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index c36f90a782c5..9ed8620580a8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -420,10 +420,10 @@ static void dwmac4_set_eee_pls(struct mac_device_info *hw, int link) writel(value, ioaddr + GMAC4_LPI_CTRL_STATUS); } -static void dwmac4_set_eee_lpi_entry_timer(struct mac_device_info *hw, int et) +static void dwmac4_set_eee_lpi_entry_timer(struct mac_device_info *hw, u32 et) { void __iomem *ioaddr = hw->pcsr; - int value = et & STMMAC_ET_MAX; + u32 value = et & STMMAC_ET_MAX; int regval; /* Program LPI entry timer value into register */ diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h index 2f7295b6c1c5..0f200b72c225 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.h +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h @@ -363,7 +363,7 @@ struct stmmac_ops { void (*set_eee_mode)(struct mac_device_info *hw, bool en_tx_lpi_clockgating); void (*reset_eee_mode)(struct mac_device_info *hw); - void (*set_eee_lpi_entry_timer)(struct mac_device_info *hw, int et); + void (*set_eee_lpi_entry_timer)(struct mac_device_info *hw, u32 et); void (*set_eee_timer)(struct mac_device_info *hw, int ls, int tw); void (*set_eee_pls)(struct mac_device_info *hw, int link); void (*debug)(struct stmmac_priv *priv, void __iomem *ioaddr, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index 548b28fed9b6..f05cae103d83 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -126,6 +126,7 @@ struct stmmac_rx_queue { unsigned int cur_rx; unsigned int dirty_rx; unsigned int buf_alloc_num; + unsigned int napi_skb_frag_size; dma_addr_t dma_rx_phy; u32 rx_tail_addr; unsigned int state_saved; @@ -305,11 +306,9 @@ struct stmmac_priv { int clk_csr; struct timer_list eee_ctrl_timer; int lpi_irq; - int eee_enabled; - int eee_active; - int tx_lpi_timer; - int tx_lpi_enabled; - int eee_tw_timer; + u32 tx_lpi_timer; + bool eee_enabled; + bool eee_active; bool eee_sw_timer_en; unsigned int mode; unsigned int chain_mode; @@ -405,8 +404,6 @@ void stmmac_dvr_remove(struct device *dev); int stmmac_dvr_probe(struct device *device, struct plat_stmmacenet_data *plat_dat, struct stmmac_resources *res); -void stmmac_disable_eee_mode(struct stmmac_priv *priv); -bool stmmac_eee_init(struct stmmac_priv *priv); int stmmac_reinit_queues(struct net_device *dev, u32 rx_cnt, u32 tx_cnt); int stmmac_reinit_ringparam(struct net_device *dev, u32 rx_size, u32 tx_size); int stmmac_bus_clks_config(struct stmmac_priv *priv, bool enabled); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index 16b4d8c21c90..918a32f8fda8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -654,7 +654,7 @@ static void stmmac_get_ethtool_stats(struct net_device *dev, (*(u32 *)p); } } - if (priv->eee_enabled) { + if (priv->dma_cap.eee) { int val = phylink_get_eee_err(priv->phylink); if (val) priv->xstats.phy_eee_wakeup_error_n = val; @@ -898,9 +898,6 @@ static int stmmac_ethtool_op_get_eee(struct net_device *dev, if (!priv->dma_cap.eee) return -EOPNOTSUPP; - edata->tx_lpi_timer = priv->tx_lpi_timer; - edata->tx_lpi_enabled = priv->tx_lpi_enabled; - return phylink_ethtool_get_eee(priv->phylink, edata); } @@ -908,29 +905,11 @@ static int stmmac_ethtool_op_set_eee(struct net_device *dev, struct ethtool_keee *edata) { struct stmmac_priv *priv = netdev_priv(dev); - int ret; if (!priv->dma_cap.eee) return -EOPNOTSUPP; - if (priv->tx_lpi_enabled != edata->tx_lpi_enabled) - netdev_warn(priv->dev, - "Setting EEE tx-lpi is not supported\n"); - - if (!edata->eee_enabled) - stmmac_disable_eee_mode(priv); - - ret = phylink_ethtool_set_eee(priv->phylink, edata); - if (ret) - return ret; - - if (edata->eee_enabled && - priv->tx_lpi_timer != edata->tx_lpi_timer) { - priv->tx_lpi_timer = edata->tx_lpi_timer; - stmmac_eee_init(priv); - } - - return 0; + return phylink_ethtool_set_eee(priv->phylink, edata); } static u32 stmmac_usec2riwt(u32 usec, struct stmmac_priv *priv) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 038df1b2bb58..d99ad77a8005 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -111,8 +111,8 @@ static const u32 default_msg_level = (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_IFDOWN | NETIF_MSG_TIMER); #define STMMAC_DEFAULT_LPI_TIMER 1000 -static int eee_timer = STMMAC_DEFAULT_LPI_TIMER; -module_param(eee_timer, int, 0644); +static unsigned int eee_timer = STMMAC_DEFAULT_LPI_TIMER; +module_param(eee_timer, uint, 0644); MODULE_PARM_DESC(eee_timer, "LPI tx expiration time in msec"); #define STMMAC_LPI_T(x) (jiffies + usecs_to_jiffies(x)) @@ -194,8 +194,6 @@ static void stmmac_verify_args(void) flow_ctrl = FLOW_OFF; if (unlikely((pause < 0) || (pause > 0xffff))) pause = PAUSE_TIME; - if (eee_timer < 0) - eee_timer = STMMAC_DEFAULT_LPI_TIMER; } static void __stmmac_disable_all_queues(struct stmmac_priv *priv) @@ -392,23 +390,17 @@ static inline u32 stmmac_rx_dirty(struct stmmac_priv *priv, u32 queue) return dirty; } -static void stmmac_lpi_entry_timer_config(struct stmmac_priv *priv, bool en) +static void stmmac_disable_hw_lpi_timer(struct stmmac_priv *priv) { - int tx_lpi_timer; + stmmac_set_eee_lpi_timer(priv, priv->hw, 0); +} - /* Clear/set the SW EEE timer flag based on LPI ET enablement */ - priv->eee_sw_timer_en = en ? 0 : 1; - tx_lpi_timer = en ? priv->tx_lpi_timer : 0; - stmmac_set_eee_lpi_timer(priv, priv->hw, tx_lpi_timer); +static void stmmac_enable_hw_lpi_timer(struct stmmac_priv *priv) +{ + stmmac_set_eee_lpi_timer(priv, priv->hw, priv->tx_lpi_timer); } -/** - * stmmac_enable_eee_mode - check and enter in LPI mode - * @priv: driver private structure - * Description: this function is to verify and enter in LPI mode in case of - * EEE. - */ -static int stmmac_enable_eee_mode(struct stmmac_priv *priv) +static bool stmmac_eee_tx_busy(struct stmmac_priv *priv) { u32 tx_cnt = priv->plat->tx_queues_to_use; u32 queue; @@ -418,29 +410,43 @@ static int stmmac_enable_eee_mode(struct stmmac_priv *priv) struct stmmac_tx_queue *tx_q = &priv->dma_conf.tx_queue[queue]; if (tx_q->dirty_tx != tx_q->cur_tx) - return -EBUSY; /* still unfinished work */ + return true; /* still unfinished work */ + } + + return false; +} + +static void stmmac_restart_sw_lpi_timer(struct stmmac_priv *priv) +{ + mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(priv->tx_lpi_timer)); +} + +/** + * stmmac_try_to_start_sw_lpi - check and enter in LPI mode + * @priv: driver private structure + * Description: this function is to verify and enter in LPI mode in case of + * EEE. + */ +static void stmmac_try_to_start_sw_lpi(struct stmmac_priv *priv) +{ + if (stmmac_eee_tx_busy(priv)) { + stmmac_restart_sw_lpi_timer(priv); + return; } /* Check and enter in LPI mode */ if (!priv->tx_path_in_lpi_mode) stmmac_set_eee_mode(priv, priv->hw, priv->plat->flags & STMMAC_FLAG_EN_TX_LPI_CLOCKGATING); - return 0; } /** - * stmmac_disable_eee_mode - disable and exit from LPI mode + * stmmac_stop_sw_lpi - stop transmitting LPI * @priv: driver private structure - * Description: this function is to exit and disable EEE in case of - * LPI state is true. This is called by the xmit. + * Description: When using software-controlled LPI, stop transmitting LPI state. */ -void stmmac_disable_eee_mode(struct stmmac_priv *priv) +static void stmmac_stop_sw_lpi(struct stmmac_priv *priv) { - if (!priv->eee_sw_timer_en) { - stmmac_lpi_entry_timer_config(priv, 0); - return; - } - stmmac_reset_eee_mode(priv, priv->hw); del_timer_sync(&priv->eee_ctrl_timer); priv->tx_path_in_lpi_mode = false; @@ -457,25 +463,27 @@ static void stmmac_eee_ctrl_timer(struct timer_list *t) { struct stmmac_priv *priv = from_timer(priv, t, eee_ctrl_timer); - if (stmmac_enable_eee_mode(priv)) - mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(priv->tx_lpi_timer)); + stmmac_try_to_start_sw_lpi(priv); } /** * stmmac_eee_init - init EEE * @priv: driver private structure + * @active: indicates whether EEE should be enabled. * Description: * if the GMAC supports the EEE (from the HW cap reg) and the phy device * can also manage EEE, this function enable the LPI state and start related * timer. */ -bool stmmac_eee_init(struct stmmac_priv *priv) +static void stmmac_eee_init(struct stmmac_priv *priv, bool active) { - int eee_tw_timer = priv->eee_tw_timer; + priv->eee_active = active; /* Check if MAC core supports the EEE feature. */ - if (!priv->dma_cap.eee) - return false; + if (!priv->dma_cap.eee) { + priv->eee_enabled = false; + return; + } mutex_lock(&priv->lock); @@ -483,22 +491,24 @@ bool stmmac_eee_init(struct stmmac_priv *priv) if (!priv->eee_active) { if (priv->eee_enabled) { netdev_dbg(priv->dev, "disable EEE\n"); - stmmac_lpi_entry_timer_config(priv, 0); + priv->eee_sw_timer_en = false; + stmmac_disable_hw_lpi_timer(priv); del_timer_sync(&priv->eee_ctrl_timer); - stmmac_set_eee_timer(priv, priv->hw, 0, eee_tw_timer); + stmmac_set_eee_timer(priv, priv->hw, 0, + STMMAC_DEFAULT_TWT_LS); if (priv->hw->xpcs) xpcs_config_eee(priv->hw->xpcs, priv->plat->mult_fact_100ns, false); } + priv->eee_enabled = false; mutex_unlock(&priv->lock); - return false; + return; } if (priv->eee_active && !priv->eee_enabled) { - timer_setup(&priv->eee_ctrl_timer, stmmac_eee_ctrl_timer, 0); stmmac_set_eee_timer(priv, priv->hw, STMMAC_DEFAULT_LIT_LS, - eee_tw_timer); + STMMAC_DEFAULT_TWT_LS); if (priv->hw->xpcs) xpcs_config_eee(priv->hw->xpcs, priv->plat->mult_fact_100ns, @@ -506,18 +516,22 @@ bool stmmac_eee_init(struct stmmac_priv *priv) } if (priv->plat->has_gmac4 && priv->tx_lpi_timer <= STMMAC_ET_MAX) { + /* Use hardware LPI mode */ del_timer_sync(&priv->eee_ctrl_timer); priv->tx_path_in_lpi_mode = false; - stmmac_lpi_entry_timer_config(priv, 1); + priv->eee_sw_timer_en = false; + stmmac_enable_hw_lpi_timer(priv); } else { - stmmac_lpi_entry_timer_config(priv, 0); - mod_timer(&priv->eee_ctrl_timer, - STMMAC_LPI_T(priv->tx_lpi_timer)); + /* Use software LPI mode */ + priv->eee_sw_timer_en = true; + stmmac_disable_hw_lpi_timer(priv); + stmmac_restart_sw_lpi_timer(priv); } + priv->eee_enabled = true; + mutex_unlock(&priv->lock); netdev_dbg(priv->dev, "Energy-Efficient Ethernet initialized\n"); - return true; } /* stmmac_get_tx_hwtstamp - get HW TX timestamps @@ -974,10 +988,8 @@ static void stmmac_mac_link_down(struct phylink_config *config, struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev)); stmmac_mac_set(priv, priv->ioaddr, false); - priv->eee_active = false; - priv->tx_lpi_enabled = false; - priv->eee_enabled = stmmac_eee_init(priv); - stmmac_set_eee_pls(priv, priv->hw, false); + if (priv->dma_cap.eee) + stmmac_set_eee_pls(priv, priv->hw, false); if (stmmac_fpe_supported(priv)) stmmac_fpe_link_state_handle(priv, false); @@ -1084,14 +1096,8 @@ static void stmmac_mac_link_up(struct phylink_config *config, writel(ctrl, priv->ioaddr + MAC_CTRL_REG); stmmac_mac_set(priv, priv->ioaddr, true); - if (phy && priv->dma_cap.eee) { - priv->eee_active = - phy_init_eee(phy, !(priv->plat->flags & - STMMAC_FLAG_RX_CLK_RUNS_IN_LPI)) >= 0; - priv->eee_enabled = stmmac_eee_init(priv); - priv->tx_lpi_enabled = priv->eee_enabled; + if (priv->dma_cap.eee) stmmac_set_eee_pls(priv, priv->hw, true); - } if (stmmac_fpe_supported(priv)) stmmac_fpe_link_state_handle(priv, true); @@ -1100,12 +1106,32 @@ static void stmmac_mac_link_up(struct phylink_config *config, stmmac_hwtstamp_correct_latency(priv, priv); } +static void stmmac_mac_disable_tx_lpi(struct phylink_config *config) +{ + struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev)); + + stmmac_eee_init(priv, false); +} + +static int stmmac_mac_enable_tx_lpi(struct phylink_config *config, u32 timer, + bool tx_clk_stop) +{ + struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev)); + + priv->tx_lpi_timer = timer; + stmmac_eee_init(priv, true); + + return 0; +} + static const struct phylink_mac_ops stmmac_phylink_mac_ops = { .mac_get_caps = stmmac_mac_get_caps, .mac_select_pcs = stmmac_mac_select_pcs, .mac_config = stmmac_mac_config, .mac_link_down = stmmac_mac_link_down, .mac_link_up = stmmac_mac_link_up, + .mac_disable_tx_lpi = stmmac_mac_disable_tx_lpi, + .mac_enable_tx_lpi = stmmac_mac_enable_tx_lpi, }; /** @@ -1178,15 +1204,27 @@ static int stmmac_init_phy(struct net_device *dev) return -ENODEV; } - if (priv->dma_cap.eee) - phy_support_eee(phydev); - ret = phylink_connect_phy(priv->phylink, phydev); } else { fwnode_handle_put(phy_fwnode); ret = phylink_fwnode_phy_connect(priv->phylink, fwnode, 0); } + if (ret == 0) { + struct ethtool_keee eee; + + /* Configure phylib's copy of the LPI timer. Normally, + * phylink_config.lpi_timer_default would do this, but there is + * a chance that userspace could change the eee_timer setting + * via sysfs before the first open. Thus, preserve existing + * behaviour. + */ + if (!phylink_ethtool_get_eee(priv->phylink, &eee)) { + eee.tx_lpi_timer = priv->tx_lpi_timer; + phylink_ethtool_set_eee(priv->phylink, &eee); + } + } + if (!priv->plat->pmt) { struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL }; @@ -1213,6 +1251,9 @@ static int stmmac_phy_setup(struct stmmac_priv *priv) /* Stmmac always requires an RX clock for hardware initialization */ priv->phylink_config.mac_requires_rxc = true; + if (!(priv->plat->flags & STMMAC_FLAG_RX_CLK_RUNS_IN_LPI)) + priv->phylink_config.eee_rx_clk_stop_enable = true; + mdio_bus_data = priv->plat->mdio_bus_data; if (mdio_bus_data) priv->phylink_config.default_an_inband = @@ -1234,6 +1275,19 @@ static int stmmac_phy_setup(struct stmmac_priv *priv) priv->phylink_config.supported_interfaces, pcs->supported_interfaces); + if (priv->dma_cap.eee) { + /* Assume all supported interfaces also support LPI */ + memcpy(priv->phylink_config.lpi_interfaces, + priv->phylink_config.supported_interfaces, + sizeof(priv->phylink_config.lpi_interfaces)); + + /* All full duplex speeds above 100Mbps are supported */ + priv->phylink_config.lpi_capabilities = ~(MAC_1000FD - 1) | + MAC_100FD; + priv->phylink_config.lpi_timer_default = eee_timer * 1000; + priv->phylink_config.eee_enabled_default = true; + } + fwnode = priv->plat->port_node; if (!fwnode) fwnode = dev_fwnode(priv->device); @@ -1320,7 +1374,7 @@ static unsigned int stmmac_rx_offset(struct stmmac_priv *priv) if (stmmac_xdp_is_enabled(priv)) return XDP_PACKET_HEADROOM; - return 0; + return NET_SKB_PAD; } static int stmmac_set_bfsize(int mtu, int bufsize) @@ -2019,22 +2073,26 @@ static int __alloc_dma_rx_desc_resources(struct stmmac_priv *priv, struct stmmac_channel *ch = &priv->channel[queue]; bool xdp_prog = stmmac_xdp_is_enabled(priv); struct page_pool_params pp_params = { 0 }; - unsigned int num_pages; + unsigned int dma_buf_sz_pad, num_pages; unsigned int napi_id; int ret; + dma_buf_sz_pad = stmmac_rx_offset(priv) + dma_conf->dma_buf_sz + + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + num_pages = DIV_ROUND_UP(dma_buf_sz_pad, PAGE_SIZE); + rx_q->queue_index = queue; rx_q->priv_data = priv; + rx_q->napi_skb_frag_size = num_pages * PAGE_SIZE; pp_params.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV; pp_params.pool_size = dma_conf->dma_rx_size; - num_pages = DIV_ROUND_UP(dma_conf->dma_buf_sz, PAGE_SIZE); - pp_params.order = ilog2(num_pages); + pp_params.order = order_base_2(num_pages); pp_params.nid = dev_to_node(priv->device); pp_params.dev = priv->device; pp_params.dma_dir = xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE; pp_params.offset = stmmac_rx_offset(priv); - pp_params.max_len = STMMAC_MAX_RX_BUF_SIZE(num_pages); + pp_params.max_len = dma_conf->dma_buf_sz; rx_q->page_pool = page_pool_create(&pp_params); if (IS_ERR(rx_q->page_pool)) { @@ -2773,11 +2831,8 @@ static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue, xmits = budget; } - if (priv->eee_enabled && !priv->tx_path_in_lpi_mode && - priv->eee_sw_timer_en) { - if (stmmac_enable_eee_mode(priv)) - mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(priv->tx_lpi_timer)); - } + if (priv->eee_sw_timer_en && !priv->tx_path_in_lpi_mode) + stmmac_restart_sw_lpi_timer(priv); /* We still have pending packets, let's call for a new scheduling */ if (tx_q->dirty_tx != tx_q->cur_tx) @@ -3452,12 +3507,6 @@ static int stmmac_hw_setup(struct net_device *dev, bool ptp_register) else if (ptp_register) stmmac_ptp_register(priv); - priv->eee_tw_timer = STMMAC_DEFAULT_TWT_LS; - - /* Convert the timer from msec to usec */ - if (!priv->tx_lpi_timer) - priv->tx_lpi_timer = eee_timer * 1000; - if (priv->use_riwt) { u32 queue; @@ -3924,6 +3973,10 @@ static int __stmmac_open(struct net_device *dev, u32 chan; int ret; + /* Initialise the tx lpi timer, converting from msec to usec */ + if (!priv->tx_lpi_timer) + priv->tx_lpi_timer = eee_timer * 1000; + ret = pm_runtime_resume_and_get(priv->device); if (ret < 0) return ret; @@ -4038,11 +4091,6 @@ static int stmmac_release(struct net_device *dev) /* Free the IRQ lines */ stmmac_free_irq(dev, REQ_IRQ_ERR_ALL, 0); - if (priv->eee_enabled) { - priv->tx_path_in_lpi_mode = false; - del_timer_sync(&priv->eee_ctrl_timer); - } - /* Stop TX/RX DMA and clear the descriptors */ stmmac_stop_all_dma(priv); @@ -4494,7 +4542,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) first_tx = tx_q->cur_tx; if (priv->tx_path_in_lpi_mode && priv->eee_sw_timer_en) - stmmac_disable_eee_mode(priv); + stmmac_stop_sw_lpi(priv); /* Manage oversized TCP frames for GMAC4 device */ if (skb_is_gso(skb) && priv->tso) { @@ -5493,10 +5541,6 @@ read_again: /* Buffer is good. Go on. */ - prefetch(page_address(buf->page) + buf->page_offset); - if (buf->sec_page) - prefetch(page_address(buf->sec_page)); - buf1_len = stmmac_rx_buf1_len(priv, p, status, len); len += buf1_len; buf2_len = stmmac_rx_buf2_len(priv, p, status, len); @@ -5518,6 +5562,8 @@ read_again: dma_sync_single_for_cpu(priv->device, buf->addr, buf1_len, dma_dir); + net_prefetch(page_address(buf->page) + + buf->page_offset); xdp_init_buff(&ctx.xdp, buf_sz, &rx_q->xdp_rxq); xdp_prepare_buff(&ctx.xdp, page_address(buf->page), @@ -5571,22 +5617,26 @@ read_again: } if (!skb) { + unsigned int head_pad_len; + /* XDP program may expand or reduce tail */ buf1_len = ctx.xdp.data_end - ctx.xdp.data; - skb = napi_alloc_skb(&ch->rx_napi, buf1_len); + skb = napi_build_skb(page_address(buf->page), + rx_q->napi_skb_frag_size); if (!skb) { + page_pool_recycle_direct(rx_q->page_pool, + buf->page); rx_dropped++; count++; goto drain_data; } /* XDP program may adjust header */ - skb_copy_to_linear_data(skb, ctx.xdp.data, buf1_len); + head_pad_len = ctx.xdp.data - ctx.xdp.data_hard_start; + skb_reserve(skb, head_pad_len); skb_put(skb, buf1_len); - - /* Data payload copied into SKB, page ready for recycle */ - page_pool_recycle_direct(rx_q->page_pool, buf->page); + skb_mark_for_recycle(skb); buf->page = NULL; } else if (buf1_len) { dma_sync_single_for_cpu(priv->device, buf->addr, @@ -7409,6 +7459,8 @@ int stmmac_dvr_probe(struct device *device, INIT_WORK(&priv->service_task, stmmac_service_task); + timer_setup(&priv->eee_ctrl_timer, stmmac_eee_ctrl_timer, 0); + /* Override with kernel parameters if supplied XXX CRS XXX * this needs to have multiple instances */ @@ -7716,7 +7768,7 @@ int stmmac_suspend(struct device *dev) for (chan = 0; chan < priv->plat->tx_queues_to_use; chan++) hrtimer_cancel(&priv->dma_conf.tx_queue[chan].txtimer); - if (priv->eee_enabled) { + if (priv->eee_sw_timer_en) { priv->tx_path_in_lpi_mode = false; del_timer_sync(&priv->eee_ctrl_timer); } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_xdp.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_xdp.h index 896dc987d4ef..77ce8cfbe976 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_xdp.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_xdp.h @@ -4,7 +4,6 @@ #ifndef _STMMAC_XDP_H_ #define _STMMAC_XDP_H_ -#define STMMAC_MAX_RX_BUF_SIZE(num) (((num) * PAGE_SIZE) - XDP_PACKET_HEADROOM) #define STMMAC_RX_DMA_ATTR (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING) int stmmac_xdp_setup_pool(struct stmmac_priv *priv, struct xsk_buff_pool *pool, diff --git a/drivers/net/ethernet/sunplus/spl2sw_driver.c b/drivers/net/ethernet/sunplus/spl2sw_driver.c index 721d8ed3f302..5e0e4c9ecbb0 100644 --- a/drivers/net/ethernet/sunplus/spl2sw_driver.c +++ b/drivers/net/ethernet/sunplus/spl2sw_driver.c @@ -199,7 +199,7 @@ static const struct net_device_ops netdev_ops = { .ndo_start_xmit = spl2sw_ethernet_start_xmit, .ndo_set_rx_mode = spl2sw_ethernet_set_rx_mode, .ndo_set_mac_address = spl2sw_ethernet_set_mac_address, - .ndo_do_ioctl = phy_do_ioctl, + .ndo_eth_ioctl = phy_do_ioctl, .ndo_tx_timeout = spl2sw_ethernet_tx_timeout, }; diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 5465bf872734..3fd8fc3121dc 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -32,6 +32,7 @@ #include <linux/dma/ti-cppi5.h> #include <linux/dma/k3-udma-glue.h> #include <net/page_pool/helpers.h> +#include <net/dsa.h> #include <net/switchdev.h> #include "cpsw_ale.h" @@ -762,7 +763,7 @@ static int am65_cpsw_nuss_common_open(struct am65_cpsw_common *common) ALE_DEFAULT_THREAD_ID, 0); cpsw_ale_control_set(common->ale, HOST_PORT_NUM, ALE_DEFAULT_THREAD_ENABLE, 1); - /* switch to vlan unaware mode */ + /* switch to vlan aware mode */ cpsw_ale_control_set(common->ale, HOST_PORT_NUM, ALE_VLAN_AWARE, 1); cpsw_ale_control_set(common->ale, HOST_PORT_NUM, ALE_PORT_STATE, ALE_PORT_STATE_FORWARD); @@ -1014,6 +1015,15 @@ static int am65_cpsw_nuss_ndo_slave_open(struct net_device *ndev) common->usage_count++; + /* VLAN aware CPSW mode is incompatible with some DSA tagging schemes. + * Therefore disable VLAN_AWARE mode if any of the ports is a DSA Port. + */ + if (netdev_uses_dsa(ndev)) { + reg = readl(common->cpsw_base + AM65_CPSW_REG_CTL); + reg &= ~AM65_CPSW_CTL_VLAN_AWARE; + writel(reg, common->cpsw_base + AM65_CPSW_REG_CTL); + } + am65_cpsw_port_set_sl_mac(port, ndev->dev_addr); am65_cpsw_port_enable_dscp_map(port); @@ -2559,20 +2569,15 @@ static int am65_cpsw_am654_get_efuse_macid(struct device_node *of_node, { u32 mac_lo, mac_hi, offset; struct regmap *syscon; - int ret; - syscon = syscon_regmap_lookup_by_phandle(of_node, "ti,syscon-efuse"); + syscon = syscon_regmap_lookup_by_phandle_args(of_node, "ti,syscon-efuse", + 1, &offset); if (IS_ERR(syscon)) { if (PTR_ERR(syscon) == -ENODEV) return 0; return PTR_ERR(syscon); } - ret = of_property_read_u32_index(of_node, "ti,syscon-efuse", 1, - &offset); - if (ret) - return ret; - regmap_read(syscon, offset, &mac_lo); regmap_read(syscon, offset + 4, &mac_hi); diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 1e290ee8edfd..0cb6fa6e5b7d 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -686,7 +686,7 @@ static void cpsw_init_host_port(struct cpsw_priv *priv) soft_reset("cpsw", &cpsw->regs->soft_reset); cpsw_ale_start(cpsw->ale); - /* switch to vlan unaware mode */ + /* switch to vlan aware mode */ cpsw_ale_control_set(cpsw->ale, HOST_PORT_NUM, ALE_VLAN_AWARE, CPSW_ALE_VLAN_AWARE); control_reg = readl(&cpsw->regs->control); diff --git a/drivers/net/ethernet/ti/cpsw_ale.c b/drivers/net/ethernet/ti/cpsw_ale.c index 52e4e350b734..5cc72a91f220 100644 --- a/drivers/net/ethernet/ti/cpsw_ale.c +++ b/drivers/net/ethernet/ti/cpsw_ale.c @@ -127,15 +127,15 @@ struct cpsw_ale_dev_id { static inline int cpsw_ale_get_field(u32 *ale_entry, u32 start, u32 bits) { - int idx, idx2; + int idx, idx2, index; u32 hi_val = 0; idx = start / 32; idx2 = (start + bits - 1) / 32; /* Check if bits to be fetched exceed a word */ if (idx != idx2) { - idx2 = 2 - idx2; /* flip */ - hi_val = ale_entry[idx2] << ((idx2 * 32) - start); + index = 2 - idx2; /* flip */ + hi_val = ale_entry[index] << ((idx2 * 32) - start); } start -= idx * 32; idx = 2 - idx; /* flip */ @@ -145,16 +145,16 @@ static inline int cpsw_ale_get_field(u32 *ale_entry, u32 start, u32 bits) static inline void cpsw_ale_set_field(u32 *ale_entry, u32 start, u32 bits, u32 value) { - int idx, idx2; + int idx, idx2, index; value &= BITMASK(bits); idx = start / 32; idx2 = (start + bits - 1) / 32; /* Check if bits to be set exceed a word */ if (idx != idx2) { - idx2 = 2 - idx2; /* flip */ - ale_entry[idx2] &= ~(BITMASK(bits + start - (idx2 * 32))); - ale_entry[idx2] |= (value >> ((idx2 * 32) - start)); + index = 2 - idx2; /* flip */ + ale_entry[index] &= ~(BITMASK(bits + start - (idx2 * 32))); + ale_entry[index] |= (value >> ((idx2 * 32) - start)); } start -= idx * 32; idx = 2 - idx; /* flip */ diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c index be4d90c1cbe7..cec0a90659d9 100644 --- a/drivers/net/ethernet/ti/cpsw_new.c +++ b/drivers/net/ethernet/ti/cpsw_new.c @@ -554,7 +554,7 @@ static void cpsw_init_host_port(struct cpsw_priv *priv) soft_reset("cpsw", &cpsw->regs->soft_reset); cpsw_ale_start(cpsw->ale); - /* switch to vlan unaware mode */ + /* switch to vlan aware mode */ cpsw_ale_control_set(cpsw->ale, HOST_PORT_NUM, ALE_VLAN_AWARE, CPSW_ALE_VLAN_AWARE); control_reg = readl(&cpsw->regs->control); diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c index d76fe6d05e10..00ed97860547 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c @@ -561,61 +561,134 @@ const struct icss_iep_clockops prueth_iep_clockops = { static int icssg_prueth_add_mcast(struct net_device *ndev, const u8 *addr) { - struct prueth_emac *emac = netdev_priv(ndev); - int port_mask = BIT(emac->port_id); + struct net_device *real_dev; + struct prueth_emac *emac; + int port_mask; + u8 vlan_id; - port_mask |= icssg_fdb_lookup(emac, addr, 0); - icssg_fdb_add_del(emac, addr, 0, port_mask, true); - icssg_vtbl_modify(emac, 0, port_mask, port_mask, true); + vlan_id = is_vlan_dev(ndev) ? vlan_dev_vlan_id(ndev) : PRUETH_DFLT_VLAN_MAC; + real_dev = is_vlan_dev(ndev) ? vlan_dev_real_dev(ndev) : ndev; + emac = netdev_priv(real_dev); + + port_mask = BIT(emac->port_id) | icssg_fdb_lookup(emac, addr, vlan_id); + icssg_fdb_add_del(emac, addr, vlan_id, port_mask, true); + icssg_vtbl_modify(emac, vlan_id, port_mask, port_mask, true); return 0; } static int icssg_prueth_del_mcast(struct net_device *ndev, const u8 *addr) { - struct prueth_emac *emac = netdev_priv(ndev); - int port_mask = BIT(emac->port_id); + struct net_device *real_dev; + struct prueth_emac *emac; int other_port_mask; + int port_mask; + u8 vlan_id; + + vlan_id = is_vlan_dev(ndev) ? vlan_dev_vlan_id(ndev) : PRUETH_DFLT_VLAN_MAC; + real_dev = is_vlan_dev(ndev) ? vlan_dev_real_dev(ndev) : ndev; + emac = netdev_priv(real_dev); - other_port_mask = port_mask ^ icssg_fdb_lookup(emac, addr, 0); + port_mask = BIT(emac->port_id); + other_port_mask = port_mask ^ icssg_fdb_lookup(emac, addr, vlan_id); - icssg_fdb_add_del(emac, addr, 0, port_mask, false); - icssg_vtbl_modify(emac, 0, port_mask, port_mask, false); + icssg_fdb_add_del(emac, addr, vlan_id, port_mask, false); + icssg_vtbl_modify(emac, vlan_id, port_mask, port_mask, false); if (other_port_mask) { - icssg_fdb_add_del(emac, addr, 0, other_port_mask, true); - icssg_vtbl_modify(emac, 0, other_port_mask, other_port_mask, true); + icssg_fdb_add_del(emac, addr, vlan_id, other_port_mask, true); + icssg_vtbl_modify(emac, vlan_id, other_port_mask, + other_port_mask, true); } return 0; } -static int icssg_prueth_hsr_add_mcast(struct net_device *ndev, const u8 *addr) +static void icssg_prueth_hsr_fdb_add_del(struct prueth_emac *emac, + const u8 *addr, u8 vid, bool add) { - struct prueth_emac *emac = netdev_priv(ndev); - struct prueth *prueth = emac->prueth; - - icssg_fdb_add_del(emac, addr, prueth->default_vlan, + icssg_fdb_add_del(emac, addr, vid, ICSSG_FDB_ENTRY_P0_MEMBERSHIP | ICSSG_FDB_ENTRY_P1_MEMBERSHIP | ICSSG_FDB_ENTRY_P2_MEMBERSHIP | - ICSSG_FDB_ENTRY_BLOCK, true); + ICSSG_FDB_ENTRY_BLOCK, add); + + if (add) + icssg_vtbl_modify(emac, vid, BIT(emac->port_id), + BIT(emac->port_id), add); +} + +static int icssg_prueth_hsr_add_mcast(struct net_device *ndev, const u8 *addr) +{ + struct net_device *real_dev; + struct prueth_emac *emac; + u8 vlan_id, i; + + vlan_id = is_vlan_dev(ndev) ? vlan_dev_vlan_id(ndev) : PRUETH_DFLT_VLAN_HSR; + real_dev = is_vlan_dev(ndev) ? vlan_dev_real_dev(ndev) : ndev; + + if (is_hsr_master(real_dev)) { + for (i = HSR_PT_SLAVE_A; i < HSR_PT_INTERLINK; i++) { + emac = netdev_priv(hsr_get_port_ndev(real_dev, i)); + if (!emac) + return -EINVAL; + icssg_prueth_hsr_fdb_add_del(emac, addr, vlan_id, + true); + } + } else { + emac = netdev_priv(real_dev); + icssg_prueth_hsr_fdb_add_del(emac, addr, vlan_id, true); + } - icssg_vtbl_modify(emac, emac->port_vlan, BIT(emac->port_id), - BIT(emac->port_id), true); return 0; } static int icssg_prueth_hsr_del_mcast(struct net_device *ndev, const u8 *addr) { - struct prueth_emac *emac = netdev_priv(ndev); - struct prueth *prueth = emac->prueth; + struct net_device *real_dev; + struct prueth_emac *emac; + u8 vlan_id, i; + + vlan_id = is_vlan_dev(ndev) ? vlan_dev_vlan_id(ndev) : PRUETH_DFLT_VLAN_HSR; + real_dev = is_vlan_dev(ndev) ? vlan_dev_real_dev(ndev) : ndev; + + if (is_hsr_master(real_dev)) { + for (i = HSR_PT_SLAVE_A; i < HSR_PT_INTERLINK; i++) { + emac = netdev_priv(hsr_get_port_ndev(real_dev, i)); + if (!emac) + return -EINVAL; + icssg_prueth_hsr_fdb_add_del(emac, addr, vlan_id, + false); + } + } else { + emac = netdev_priv(real_dev); + icssg_prueth_hsr_fdb_add_del(emac, addr, vlan_id, false); + } - icssg_fdb_add_del(emac, addr, prueth->default_vlan, - ICSSG_FDB_ENTRY_P0_MEMBERSHIP | - ICSSG_FDB_ENTRY_P1_MEMBERSHIP | - ICSSG_FDB_ENTRY_P2_MEMBERSHIP | - ICSSG_FDB_ENTRY_BLOCK, false); + return 0; +} + +static int icssg_update_vlan_mcast(struct net_device *vdev, int vid, + void *args) +{ + struct prueth_emac *emac = args; + + if (!vdev || !vid) + return 0; + + netif_addr_lock_bh(vdev); + __hw_addr_sync_multiple(&emac->vlan_mcast_list[vid], &vdev->mc, + vdev->addr_len); + netif_addr_unlock_bh(vdev); + + if (emac->prueth->is_hsr_offload_mode) + __hw_addr_sync_dev(&emac->vlan_mcast_list[vid], vdev, + icssg_prueth_hsr_add_mcast, + icssg_prueth_hsr_del_mcast); + else + __hw_addr_sync_dev(&emac->vlan_mcast_list[vid], vdev, + icssg_prueth_add_mcast, + icssg_prueth_del_mcast); return 0; } @@ -857,12 +930,22 @@ static void emac_ndo_set_rx_mode_work(struct work_struct *work) return; } - if (emac->prueth->is_hsr_offload_mode) + if (emac->prueth->is_hsr_offload_mode) { __dev_mc_sync(ndev, icssg_prueth_hsr_add_mcast, icssg_prueth_hsr_del_mcast); - else + if (rtnl_trylock()) { + vlan_for_each(emac->prueth->hsr_dev, + icssg_update_vlan_mcast, emac); + rtnl_unlock(); + } + } else { __dev_mc_sync(ndev, icssg_prueth_add_mcast, icssg_prueth_del_mcast); + if (rtnl_trylock()) { + vlan_for_each(ndev, icssg_update_vlan_mcast, emac); + rtnl_unlock(); + } + } } /** @@ -907,19 +990,19 @@ static int emac_ndo_vlan_rx_add_vid(struct net_device *ndev, { struct prueth_emac *emac = netdev_priv(ndev); struct prueth *prueth = emac->prueth; + int port_mask = BIT(emac->port_id); int untag_mask = 0; - int port_mask; - if (prueth->is_hsr_offload_mode) { - port_mask = BIT(PRUETH_PORT_HOST) | BIT(emac->port_id); - untag_mask = 0; + if (prueth->is_hsr_offload_mode) + port_mask |= BIT(PRUETH_PORT_HOST); - netdev_dbg(emac->ndev, "VID add vid:%u port_mask:%X untag_mask %X\n", - vid, port_mask, untag_mask); + __hw_addr_init(&emac->vlan_mcast_list[vid]); + netdev_dbg(emac->ndev, "VID add vid:%u port_mask:%X untag_mask %X\n", + vid, port_mask, untag_mask); + + icssg_vtbl_modify(emac, vid, port_mask, untag_mask, true); + icssg_set_pvid(emac->prueth, vid, emac->port_id); - icssg_vtbl_modify(emac, vid, port_mask, untag_mask, true); - icssg_set_pvid(emac->prueth, vid, emac->port_id); - } return 0; } @@ -928,18 +1011,16 @@ static int emac_ndo_vlan_rx_del_vid(struct net_device *ndev, { struct prueth_emac *emac = netdev_priv(ndev); struct prueth *prueth = emac->prueth; + int port_mask = BIT(emac->port_id); int untag_mask = 0; - int port_mask; - if (prueth->is_hsr_offload_mode) { + if (prueth->is_hsr_offload_mode) port_mask = BIT(PRUETH_PORT_HOST); - untag_mask = 0; - netdev_dbg(emac->ndev, "VID del vid:%u port_mask:%X untag_mask %X\n", - vid, port_mask, untag_mask); + netdev_dbg(emac->ndev, "VID del vid:%u port_mask:%X untag_mask %X\n", + vid, port_mask, untag_mask); + icssg_vtbl_modify(emac, vid, port_mask, untag_mask, false); - icssg_vtbl_modify(emac, vid, port_mask, untag_mask, false); - } return 0; } @@ -1254,7 +1335,7 @@ static int prueth_netdevice_port_link(struct net_device *ndev, if (prueth->br_members & BIT(PRUETH_PORT_MII0) && prueth->br_members & BIT(PRUETH_PORT_MII1)) { prueth->is_switch_mode = true; - prueth->default_vlan = 1; + prueth->default_vlan = PRUETH_DFLT_VLAN_SW; emac->port_vlan = prueth->default_vlan; icssg_change_mode(prueth); } @@ -1312,7 +1393,7 @@ static int prueth_hsr_port_link(struct net_device *ndev) NETIF_PRUETH_HSR_OFFLOAD_FEATURES)) return -EOPNOTSUPP; prueth->is_hsr_offload_mode = true; - prueth->default_vlan = 1; + prueth->default_vlan = PRUETH_DFLT_VLAN_HSR; emac0->port_vlan = prueth->default_vlan; emac1->port_vlan = prueth->default_vlan; icssg_change_mode(prueth); diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.h b/drivers/net/ethernet/ti/icssg/icssg_prueth.h index 5473315ea204..329b46e9ee53 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.h +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.h @@ -83,6 +83,12 @@ #define ICSS_CMD_ADD_FILTER 0x7 #define ICSS_CMD_ADD_MAC 0x8 +/* VLAN Filtering Related MACROs */ +#define PRUETH_DFLT_VLAN_HSR 1 +#define PRUETH_DFLT_VLAN_SW 1 +#define PRUETH_DFLT_VLAN_MAC 0 +#define MAX_VLAN_ID 256 + /* In switch mode there are 3 real ports i.e. 3 mac addrs. * however Linux sees only the host side port. The other 2 ports * are the switch ports. @@ -200,6 +206,8 @@ struct prueth_emac { /* RX IRQ Coalescing Related */ struct hrtimer rx_hrtimer; unsigned long rx_pace_timeout_ns; + + struct netdev_hw_addr_list vlan_mcast_list[MAX_VLAN_ID]; }; /** diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c b/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c index 3dc86397c367..64a19ff39562 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c @@ -1031,8 +1031,6 @@ static int prueth_probe(struct platform_device *pdev) (unsigned long)prueth->msmcram.va); prueth->msmcram.size = msmc_ram_size; memset_io(prueth->msmcram.va, 0, msmc_ram_size); - dev_dbg(dev, "sram: pa %llx va %p size %zx\n", prueth->msmcram.pa, - prueth->msmcram.va, prueth->msmcram.size); prueth->iep0 = icss_iep_get_idx(np, 0); if (IS_ERR(prueth->iep0)) { diff --git a/drivers/net/ethernet/via/via-velocity.c b/drivers/net/ethernet/via/via-velocity.c index dd4a07c97eee..5aa93144a4f5 100644 --- a/drivers/net/ethernet/via/via-velocity.c +++ b/drivers/net/ethernet/via/via-velocity.c @@ -2320,7 +2320,8 @@ static int velocity_change_mtu(struct net_device *dev, int new_mtu) if (ret < 0) goto out_free_tmp_vptr_1; - napi_disable(&vptr->napi); + netdev_lock(dev); + napi_disable_locked(&vptr->napi); spin_lock_irqsave(&vptr->lock, flags); @@ -2342,12 +2343,13 @@ static int velocity_change_mtu(struct net_device *dev, int new_mtu) velocity_give_many_rx_descs(vptr); - napi_enable(&vptr->napi); + napi_enable_locked(&vptr->napi); mac_enable_int(vptr->mac_regs); netif_start_queue(dev); spin_unlock_irqrestore(&vptr->lock, flags); + netdev_unlock(dev); velocity_free_rings(tmp_vptr); diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h index d64b8abcf018..a3f4f3e42587 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet.h +++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h @@ -120,6 +120,9 @@ #define XAXIDMA_IRQ_ERROR_MASK 0x00004000 /* Error interrupt */ #define XAXIDMA_IRQ_ALL_MASK 0x00007000 /* All interrupts */ +/* Constant to convert delay counts to microseconds */ +#define XAXIDMA_DELAY_SCALE (125ULL * USEC_PER_SEC) + /* Default TX/RX Threshold and delay timer values for SGDMA mode */ #define XAXIDMA_DFT_TX_THRESHOLD 24 #define XAXIDMA_DFT_TX_USEC 50 diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 0f4b02fe6f85..9e7fa012e4fa 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -238,11 +238,8 @@ static u32 axienet_usec_to_timer(struct axienet_local *lp, u32 coalesce_usec) /* 1 Timeout Interval = 125 * (clock period of SG clock) */ result = DIV64_U64_ROUND_CLOSEST((u64)coalesce_usec * clk_rate, - (u64)125000000); - if (result > 255) - result = 255; - - return result; + XAXIDMA_DELAY_SCALE); + return min(result, FIELD_MAX(XAXIDMA_DELAY_MASK)); } /** @@ -2056,14 +2053,31 @@ axienet_ethtools_set_coalesce(struct net_device *ndev, return -EBUSY; } - if (ecoalesce->rx_max_coalesced_frames) - lp->coalesce_count_rx = ecoalesce->rx_max_coalesced_frames; - if (ecoalesce->rx_coalesce_usecs) - lp->coalesce_usec_rx = ecoalesce->rx_coalesce_usecs; - if (ecoalesce->tx_max_coalesced_frames) - lp->coalesce_count_tx = ecoalesce->tx_max_coalesced_frames; - if (ecoalesce->tx_coalesce_usecs) - lp->coalesce_usec_tx = ecoalesce->tx_coalesce_usecs; + if (ecoalesce->rx_max_coalesced_frames > 255 || + ecoalesce->tx_max_coalesced_frames > 255) { + NL_SET_ERR_MSG(extack, "frames must be less than 256"); + return -EINVAL; + } + + if (!ecoalesce->rx_max_coalesced_frames || + !ecoalesce->tx_max_coalesced_frames) { + NL_SET_ERR_MSG(extack, "frames must be non-zero"); + return -EINVAL; + } + + if ((ecoalesce->rx_max_coalesced_frames > 1 && + !ecoalesce->rx_coalesce_usecs) || + (ecoalesce->tx_max_coalesced_frames > 1 && + !ecoalesce->tx_coalesce_usecs)) { + NL_SET_ERR_MSG(extack, + "usecs must be non-zero when frames is greater than one"); + return -EINVAL; + } + + lp->coalesce_count_rx = ecoalesce->rx_max_coalesced_frames; + lp->coalesce_usec_rx = ecoalesce->rx_coalesce_usecs; + lp->coalesce_count_tx = ecoalesce->tx_max_coalesced_frames; + lp->coalesce_usec_tx = ecoalesce->tx_coalesce_usecs; return 0; } @@ -2331,11 +2345,12 @@ static struct axienet_local *pcs_to_axienet_local(struct phylink_pcs *pcs) } static void axienet_pcs_get_state(struct phylink_pcs *pcs, + unsigned int neg_mode, struct phylink_link_state *state) { struct mdio_device *pcs_phy = pcs_to_axienet_local(pcs)->pcs_phy; - phylink_mii_c22_pcs_get_state(pcs_phy, state); + phylink_mii_c22_pcs_get_state(pcs_phy, neg_mode, state); } static void axienet_pcs_an_restart(struct phylink_pcs *pcs) diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 89a996ad8cd0..d64740bf44ed 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -23,6 +23,8 @@ #include <net/net_namespace.h> #include <net/protocol.h> +#include <net/inet_dscp.h> +#include <net/inet_sock.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/udp.h> @@ -350,7 +352,7 @@ static struct rtable *ip4_route_output_gtp(struct flowi4 *fl4, fl4->flowi4_oif = sk->sk_bound_dev_if; fl4->daddr = daddr; fl4->saddr = saddr; - fl4->flowi4_tos = ip_sock_rt_tos(sk); + fl4->flowi4_tos = inet_dscp_to_dsfield(inet_sk_dscp(inet_sk(sk))); fl4->flowi4_scope = ip_sock_rt_scope(sk); fl4->flowi4_proto = sk->sk_protocol; @@ -1524,8 +1526,8 @@ static int gtp_newlink(struct net *src_net, struct net_device *dev, goto out_encap; } - gn = net_generic(dev_net(dev), gtp_net_id); - list_add_rcu(>p->list, &gn->gtp_dev_list); + gn = net_generic(src_net, gtp_net_id); + list_add(>p->list, &gn->gtp_dev_list); dev->priv_destructor = gtp_destructor; netdev_dbg(dev, "registered new GTP interface\n"); @@ -1551,7 +1553,7 @@ static void gtp_dellink(struct net_device *dev, struct list_head *head) hlist_for_each_entry_safe(pctx, next, >p->tid_hash[i], hlist_tid) pdp_context_delete(pctx); - list_del_rcu(>p->list); + list_del(>p->list); unregister_netdevice_queue(dev, head); } @@ -2271,16 +2273,19 @@ static int gtp_genl_dump_pdp(struct sk_buff *skb, struct gtp_dev *last_gtp = (struct gtp_dev *)cb->args[2], *gtp; int i, j, bucket = cb->args[0], skip = cb->args[1]; struct net *net = sock_net(skb->sk); + struct net_device *dev; struct pdp_ctx *pctx; - struct gtp_net *gn; - - gn = net_generic(net, gtp_net_id); if (cb->args[4]) return 0; rcu_read_lock(); - list_for_each_entry_rcu(gtp, &gn->gtp_dev_list, list) { + for_each_netdev_rcu(net, dev) { + if (dev->rtnl_link_ops != >p_link_ops) + continue; + + gtp = netdev_priv(dev); + if (last_gtp && last_gtp != gtp) continue; else @@ -2475,9 +2480,14 @@ static void __net_exit gtp_net_exit_batch_rtnl(struct list_head *net_list, list_for_each_entry(net, net_list, exit_list) { struct gtp_net *gn = net_generic(net, gtp_net_id); - struct gtp_dev *gtp; + struct gtp_dev *gtp, *gtp_next; + struct net_device *dev; + + for_each_netdev(net, dev) + if (dev->rtnl_link_ops == >p_link_ops) + gtp_dellink(dev, dev_to_kill); - list_for_each_entry(gtp, &gn->gtp_dev_list, list) + list_for_each_entry_safe(gtp, gtp_next, &gn->gtp_dev_list, list) gtp_dellink(gtp->dev, dev_to_kill); } } diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index e690b95b1bbb..234db693cefa 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -464,7 +464,7 @@ struct nvsp_1_message_send_receive_buffer_complete { * LargeOffset SmallOffset */ - struct nvsp_1_receive_buffer_section sections[1]; + struct nvsp_1_receive_buffer_section sections[]; } __packed; /* diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 9afb08dbc350..d6f5b9ea3109 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -866,7 +866,8 @@ static void netvsc_send_completion(struct net_device *ndev, case NVSP_MSG1_TYPE_SEND_RECV_BUF_COMPLETE: if (msglen < sizeof(struct nvsp_message_header) + - sizeof(struct nvsp_1_message_send_receive_buffer_complete)) { + struct_size_t(struct nvsp_1_message_send_receive_buffer_complete, + sections, 1)) { netdev_err(ndev, "nvsp_msg1 length too small: %u\n", msglen); return; diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index ee2c3cf4df36..da3a97a65507 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -799,6 +799,12 @@ static int ipvlan_device_event(struct notifier_block *unused, case NETDEV_PRE_TYPE_CHANGE: /* Forbid underlying device to change its type. */ return NOTIFY_BAD; + + case NETDEV_NOTIFY_PEERS: + case NETDEV_BONDING_FAILOVER: + case NETDEV_RESEND_IGMP: + list_for_each_entry(ipvlan, &port->ipvlans, pnode) + call_netdevice_notifiers(event, ipvlan->dev); } return NOTIFY_DONE; } diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c index 1993b90b1a5f..c8840c3b9a1b 100644 --- a/drivers/net/loopback.c +++ b/drivers/net/loopback.c @@ -264,13 +264,12 @@ static int __init blackhole_netdev_init(void) if (!blackhole_netdev) return -ENOMEM; - rtnl_lock(); + rtnl_net_lock(&init_net); dev_init_scheduler(blackhole_netdev); dev_activate(blackhole_netdev); - rtnl_unlock(); + rtnl_net_unlock(&init_net); blackhole_netdev->flags |= IFF_UP | IFF_RUNNING; - dev_net_set(blackhole_netdev, &init_net); return 0; } diff --git a/drivers/net/netdevsim/ethtool.c b/drivers/net/netdevsim/ethtool.c index 5fe1eaef99b5..12163635b759 100644 --- a/drivers/net/netdevsim/ethtool.c +++ b/drivers/net/netdevsim/ethtool.c @@ -2,7 +2,6 @@ // Copyright (c) 2020 Facebook #include <linux/debugfs.h> -#include <linux/ethtool.h> #include <linux/random.h> #include "netdevsim.h" @@ -72,6 +71,12 @@ static void nsim_get_ringparam(struct net_device *dev, struct netdevsim *ns = netdev_priv(dev); memcpy(ring, &ns->ethtool.ring, sizeof(ns->ethtool.ring)); + kernel_ring->tcp_data_split = dev->ethtool->hds_config; + kernel_ring->hds_thresh = dev->ethtool->hds_thresh; + kernel_ring->hds_thresh_max = NSIM_HDS_THRESHOLD_MAX; + + if (kernel_ring->tcp_data_split == ETHTOOL_TCP_DATA_SPLIT_UNKNOWN) + kernel_ring->tcp_data_split = ETHTOOL_TCP_DATA_SPLIT_ENABLED; } static int nsim_set_ringparam(struct net_device *dev, @@ -103,10 +108,10 @@ nsim_set_channels(struct net_device *dev, struct ethtool_channels *ch) struct netdevsim *ns = netdev_priv(dev); int err; - mutex_lock(&dev->lock); + netdev_lock(dev); err = netif_set_real_num_queues(dev, ch->combined_count, ch->combined_count); - mutex_unlock(&dev->lock); + netdev_unlock(dev); if (err) return err; @@ -161,6 +166,8 @@ static int nsim_get_ts_info(struct net_device *dev, static const struct ethtool_ops nsim_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_ALL_PARAMS, + .supported_ring_params = ETHTOOL_RING_USE_TCP_DATA_SPLIT | + ETHTOOL_RING_USE_HDS_THRS, .get_pause_stats = nsim_get_pause_stats, .get_pauseparam = nsim_get_pauseparam, .set_pauseparam = nsim_set_pauseparam, @@ -182,6 +189,9 @@ static void nsim_ethtool_ring_init(struct netdevsim *ns) ns->ethtool.ring.rx_jumbo_max_pending = 4096; ns->ethtool.ring.rx_mini_max_pending = 4096; ns->ethtool.ring.tx_max_pending = 4096; + + ns->netdev->ethtool->hds_config = ETHTOOL_TCP_DATA_SPLIT_UNKNOWN; + ns->netdev->ethtool->hds_thresh = 0; } void nsim_ethtool_init(struct netdevsim *ns) diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c index d013b6498539..f92b05ccdca9 100644 --- a/drivers/net/netdevsim/netdev.c +++ b/drivers/net/netdevsim/netdev.c @@ -15,6 +15,7 @@ #include <linux/debugfs.h> #include <linux/etherdevice.h> +#include <linux/ethtool_netlink.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/netdevice.h> @@ -54,6 +55,7 @@ static int nsim_forward_skb(struct net_device *dev, struct sk_buff *skb, static netdev_tx_t nsim_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct netdevsim *ns = netdev_priv(dev); + struct ethtool_netdev_state *ethtool; struct net_device *peer_dev; unsigned int len = skb->len; struct netdevsim *peer_ns; @@ -74,6 +76,13 @@ static netdev_tx_t nsim_start_xmit(struct sk_buff *skb, struct net_device *dev) rxq = rxq % peer_dev->num_rx_queues; rq = peer_ns->rq[rxq]; + ethtool = peer_dev->ethtool; + if (skb_is_nonlinear(skb) && + (ethtool->hds_config != ETHTOOL_TCP_DATA_SPLIT_ENABLED || + (ethtool->hds_config == ETHTOOL_TCP_DATA_SPLIT_ENABLED && + ethtool->hds_thresh > len))) + skb_linearize(skb); + skb_tx_timestamp(skb); if (unlikely(nsim_forward_skb(peer_dev, skb, rq) == NET_RX_DROP)) goto out_drop_cnt; diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h index a70f62af4c88..dcf073bc4802 100644 --- a/drivers/net/netdevsim/netdevsim.h +++ b/drivers/net/netdevsim/netdevsim.h @@ -16,6 +16,7 @@ #include <linux/debugfs.h> #include <linux/device.h> #include <linux/ethtool.h> +#include <linux/ethtool_netlink.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/netdevice.h> @@ -36,6 +37,8 @@ #define NSIM_IPSEC_VALID BIT(31) #define NSIM_UDP_TUNNEL_N_PORTS 4 +#define NSIM_HDS_THRESHOLD_MAX 1024 + struct nsim_sa { struct xfrm_state *xs; __be32 ipaddr[4]; diff --git a/drivers/net/pcs/pcs-lynx.c b/drivers/net/pcs/pcs-lynx.c index 6457190ec6e7..e46f588cae7d 100644 --- a/drivers/net/pcs/pcs-lynx.c +++ b/drivers/net/pcs/pcs-lynx.c @@ -100,7 +100,7 @@ static void lynx_pcs_get_state_2500basex(struct mdio_device *pcs, state->duplex = DUPLEX_FULL; } -static void lynx_pcs_get_state(struct phylink_pcs *pcs, +static void lynx_pcs_get_state(struct phylink_pcs *pcs, unsigned int neg_mode, struct phylink_link_state *state) { struct lynx_pcs *lynx = phylink_pcs_to_lynx(pcs); @@ -109,7 +109,7 @@ static void lynx_pcs_get_state(struct phylink_pcs *pcs, case PHY_INTERFACE_MODE_1000BASEX: case PHY_INTERFACE_MODE_SGMII: case PHY_INTERFACE_MODE_QSGMII: - phylink_mii_c22_pcs_get_state(lynx->mdio, state); + phylink_mii_c22_pcs_get_state(lynx->mdio, neg_mode, state); break; case PHY_INTERFACE_MODE_2500BASEX: lynx_pcs_get_state_2500basex(lynx->mdio, state); diff --git a/drivers/net/pcs/pcs-mtk-lynxi.c b/drivers/net/pcs/pcs-mtk-lynxi.c index 4fe0fb6d12a4..7d6261dee534 100644 --- a/drivers/net/pcs/pcs-mtk-lynxi.c +++ b/drivers/net/pcs/pcs-mtk-lynxi.c @@ -105,6 +105,7 @@ static unsigned int mtk_pcs_lynxi_inband_caps(struct phylink_pcs *pcs, } static void mtk_pcs_lynxi_get_state(struct phylink_pcs *pcs, + unsigned int neg_mode, struct phylink_link_state *state) { struct mtk_pcs_lynxi *mpcs = pcs_to_mtk_pcs_lynxi(pcs); @@ -114,7 +115,8 @@ static void mtk_pcs_lynxi_get_state(struct phylink_pcs *pcs, regmap_read(mpcs->regmap, SGMSYS_PCS_CONTROL_1, &bm); regmap_read(mpcs->regmap, SGMSYS_PCS_ADVERTISE, &adv); - phylink_mii_c22_pcs_decode_state(state, FIELD_GET(SGMII_BMSR, bm), + phylink_mii_c22_pcs_decode_state(state, neg_mode, + FIELD_GET(SGMII_BMSR, bm), FIELD_GET(SGMII_LPA, adv)); } diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c index c06b66f40022..1faa37f0e7b9 100644 --- a/drivers/net/pcs/pcs-xpcs.c +++ b/drivers/net/pcs/pcs-xpcs.c @@ -710,7 +710,9 @@ static int xpcs_config_aneg_c37_sgmii(struct dw_xpcs *xpcs, if (ret < 0) return ret; - mask = DW_VR_MII_DIG_CTRL1_MAC_AUTO_SW; + val = 0; + mask = DW_VR_MII_DIG_CTRL1_2G5_EN | DW_VR_MII_DIG_CTRL1_MAC_AUTO_SW; + if (neg_mode == PHYLINK_PCS_NEG_INBAND_ENABLED) val = DW_VR_MII_DIG_CTRL1_MAC_AUTO_SW; @@ -1030,6 +1032,7 @@ static int xpcs_get_state_c37_sgmii(struct dw_xpcs *xpcs, } static int xpcs_get_state_c37_1000basex(struct dw_xpcs *xpcs, + unsigned int neg_mode, struct phylink_link_state *state) { int lpa, bmsr; @@ -1058,7 +1061,7 @@ static int xpcs_get_state_c37_1000basex(struct dw_xpcs *xpcs, } } - phylink_mii_c22_pcs_decode_state(state, bmsr, lpa); + phylink_mii_c22_pcs_decode_state(state, neg_mode, bmsr, lpa); } return 0; @@ -1086,7 +1089,7 @@ static int xpcs_get_state_2500basex(struct dw_xpcs *xpcs, return 0; } -static void xpcs_get_state(struct phylink_pcs *pcs, +static void xpcs_get_state(struct phylink_pcs *pcs, unsigned int neg_mode, struct phylink_link_state *state) { struct dw_xpcs *xpcs = phylink_pcs_to_xpcs(pcs); @@ -1114,7 +1117,7 @@ static void xpcs_get_state(struct phylink_pcs *pcs, "xpcs_get_state_c37_sgmii", ERR_PTR(ret)); break; case DW_AN_C37_1000BASEX: - ret = xpcs_get_state_c37_1000basex(xpcs, state); + ret = xpcs_get_state_c37_1000basex(xpcs, neg_mode, state); if (ret) dev_err(&xpcs->mdiodev->dev, "%s returned %pe\n", "xpcs_get_state_c37_1000basex", ERR_PTR(ret)); diff --git a/drivers/net/pfcp.c b/drivers/net/pfcp.c index 69434fd13f96..68d0d9e92a22 100644 --- a/drivers/net/pfcp.c +++ b/drivers/net/pfcp.c @@ -206,8 +206,8 @@ static int pfcp_newlink(struct net *net, struct net_device *dev, goto exit_del_pfcp_sock; } - pn = net_generic(dev_net(dev), pfcp_net_id); - list_add_rcu(&pfcp->list, &pn->pfcp_dev_list); + pn = net_generic(net, pfcp_net_id); + list_add(&pfcp->list, &pn->pfcp_dev_list); netdev_dbg(dev, "registered new PFCP interface\n"); @@ -224,7 +224,7 @@ static void pfcp_dellink(struct net_device *dev, struct list_head *head) { struct pfcp_dev *pfcp = netdev_priv(dev); - list_del_rcu(&pfcp->list); + list_del(&pfcp->list); unregister_netdevice_queue(dev, head); } @@ -247,11 +247,16 @@ static int __net_init pfcp_net_init(struct net *net) static void __net_exit pfcp_net_exit(struct net *net) { struct pfcp_net *pn = net_generic(net, pfcp_net_id); - struct pfcp_dev *pfcp; + struct pfcp_dev *pfcp, *pfcp_next; + struct net_device *dev; LIST_HEAD(list); rtnl_lock(); - list_for_each_entry(pfcp, &pn->pfcp_dev_list, list) + for_each_netdev(net, dev) + if (dev->rtnl_link_ops == &pfcp_link_ops) + pfcp_dellink(dev, &list); + + list_for_each_entry_safe(pfcp, pfcp_next, &pn->pfcp_dev_list, list) pfcp_dellink(pfcp->dev, &list); unregister_netdevice_many(&list); diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index dc625f2b3ae4..41c15a2c2037 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -287,8 +287,8 @@ config MICROCHIP_PHY config MICROCHIP_T1_PHY tristate "Microchip T1 PHYs" - select MICROCHIP_PHY_RDS_PTP if NETWORK_PHY_TIMESTAMPING && \ - PTP_1588_CLOCK_OPTIONAL + select MICROCHIP_PHY_RDS_PTP if NETWORK_PHY_TIMESTAMPING + depends on PTP_1588_CLOCK_OPTIONAL help Supports the LAN8XXX PHYs. @@ -350,10 +350,7 @@ config QSEMI_PHY help Currently supports the qs6612 -config REALTEK_PHY - tristate "Realtek PHYs" - help - Supports the Realtek 821x PHY. +source "drivers/net/phy/realtek/Kconfig" config RENESAS_PHY tristate "Renesas PHYs" diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile index 39b72b464287..c8dac6e92278 100644 --- a/drivers/net/phy/Makefile +++ b/drivers/net/phy/Makefile @@ -95,7 +95,7 @@ obj-$(CONFIG_NXP_CBTX_PHY) += nxp-cbtx.o obj-$(CONFIG_NXP_TJA11XX_PHY) += nxp-tja11xx.o obj-y += qcom/ obj-$(CONFIG_QSEMI_PHY) += qsemi.o -obj-$(CONFIG_REALTEK_PHY) += realtek.o +obj-$(CONFIG_REALTEK_PHY) += realtek/ obj-$(CONFIG_RENESAS_PHY) += uPD60620.o obj-$(CONFIG_ROCKCHIP_PHY) += rockchip.o obj-$(CONFIG_SMSC_PHY) += smsc.o diff --git a/drivers/net/phy/adin.c b/drivers/net/phy/adin.c index a2a862bae2ed..7fa713ca8d45 100644 --- a/drivers/net/phy/adin.c +++ b/drivers/net/phy/adin.c @@ -1038,7 +1038,7 @@ static struct phy_driver adin_driver[] = { module_phy_driver(adin_driver); -static struct mdio_device_id __maybe_unused adin_tbl[] = { +static const struct mdio_device_id __maybe_unused adin_tbl[] = { { PHY_ID_MATCH_MODEL(PHY_ID_ADIN1200) }, { PHY_ID_MATCH_MODEL(PHY_ID_ADIN1300) }, { } diff --git a/drivers/net/phy/adin1100.c b/drivers/net/phy/adin1100.c index 85f910e2d4fb..6bb469429b9d 100644 --- a/drivers/net/phy/adin1100.c +++ b/drivers/net/phy/adin1100.c @@ -340,7 +340,7 @@ static struct phy_driver adin_driver[] = { module_phy_driver(adin_driver); -static struct mdio_device_id __maybe_unused adin_tbl[] = { +static const struct mdio_device_id __maybe_unused adin_tbl[] = { { PHY_ID_MATCH_MODEL(PHY_ID_ADIN1100) }, { PHY_ID_MATCH_MODEL(PHY_ID_ADIN1110) }, { PHY_ID_MATCH_MODEL(PHY_ID_ADIN2111) }, diff --git a/drivers/net/phy/air_en8811h.c b/drivers/net/phy/air_en8811h.c index 8d076b9609fd..e9fd24cb7270 100644 --- a/drivers/net/phy/air_en8811h.c +++ b/drivers/net/phy/air_en8811h.c @@ -1075,7 +1075,7 @@ static struct phy_driver en8811h_driver[] = { module_phy_driver(en8811h_driver); -static struct mdio_device_id __maybe_unused en8811h_tbl[] = { +static const struct mdio_device_id __maybe_unused en8811h_tbl[] = { { PHY_ID_MATCH_MODEL(EN8811H_PHY_ID) }, { } }; diff --git a/drivers/net/phy/amd.c b/drivers/net/phy/amd.c index 930b15fa6ce9..75b5fe65500a 100644 --- a/drivers/net/phy/amd.c +++ b/drivers/net/phy/amd.c @@ -111,7 +111,7 @@ static struct phy_driver am79c_drivers[] = { module_phy_driver(am79c_drivers); -static struct mdio_device_id __maybe_unused amd_tbl[] = { +static const struct mdio_device_id __maybe_unused amd_tbl[] = { { PHY_ID_AC101L, 0xfffffff0 }, { PHY_ID_AM79C874, 0xfffffff0 }, { } diff --git a/drivers/net/phy/aquantia/aquantia_main.c b/drivers/net/phy/aquantia/aquantia_main.c index bb56a66d2a48..e42ace4e682a 100644 --- a/drivers/net/phy/aquantia/aquantia_main.c +++ b/drivers/net/phy/aquantia/aquantia_main.c @@ -1200,7 +1200,7 @@ static struct phy_driver aqr_driver[] = { module_phy_driver(aqr_driver); -static struct mdio_device_id __maybe_unused aqr_tbl[] = { +static const struct mdio_device_id __maybe_unused aqr_tbl[] = { { PHY_ID_MATCH_MODEL(PHY_ID_AQ1202) }, { PHY_ID_MATCH_MODEL(PHY_ID_AQ2104) }, { PHY_ID_MATCH_MODEL(PHY_ID_AQR105) }, diff --git a/drivers/net/phy/ax88796b.c b/drivers/net/phy/ax88796b.c index eb74a8cf8df1..694df1401aa2 100644 --- a/drivers/net/phy/ax88796b.c +++ b/drivers/net/phy/ax88796b.c @@ -121,7 +121,7 @@ static struct phy_driver asix_driver[] = { module_phy_driver(asix_driver); -static struct mdio_device_id __maybe_unused asix_tbl[] = { +static const struct mdio_device_id __maybe_unused asix_tbl[] = { { PHY_ID_MATCH_EXACT(PHY_ID_ASIX_AX88772A) }, { PHY_ID_MATCH_EXACT(PHY_ID_ASIX_AX88772C) }, { PHY_ID_ASIX_AX88796B, 0xfffffff0 }, diff --git a/drivers/net/phy/bcm-cygnus.c b/drivers/net/phy/bcm-cygnus.c index da8f7cb41b44..15cbef8202bc 100644 --- a/drivers/net/phy/bcm-cygnus.c +++ b/drivers/net/phy/bcm-cygnus.c @@ -278,7 +278,7 @@ static struct phy_driver bcm_cygnus_phy_driver[] = { } }; -static struct mdio_device_id __maybe_unused bcm_cygnus_phy_tbl[] = { +static const struct mdio_device_id __maybe_unused bcm_cygnus_phy_tbl[] = { { PHY_ID_BCM_CYGNUS, 0xfffffff0, }, { PHY_ID_BCM_OMEGA, 0xfffffff0, }, { } diff --git a/drivers/net/phy/bcm54140.c b/drivers/net/phy/bcm54140.c index 2eea3d09b1e6..7969345f6b35 100644 --- a/drivers/net/phy/bcm54140.c +++ b/drivers/net/phy/bcm54140.c @@ -883,7 +883,7 @@ static struct phy_driver bcm54140_drivers[] = { }; module_phy_driver(bcm54140_drivers); -static struct mdio_device_id __maybe_unused bcm54140_tbl[] = { +static const struct mdio_device_id __maybe_unused bcm54140_tbl[] = { { PHY_ID_BCM54140, BCM54140_PHY_ID_MASK }, { } }; diff --git a/drivers/net/phy/bcm63xx.c b/drivers/net/phy/bcm63xx.c index 0eb33be824f1..b46a736a3130 100644 --- a/drivers/net/phy/bcm63xx.c +++ b/drivers/net/phy/bcm63xx.c @@ -93,7 +93,7 @@ static struct phy_driver bcm63xx_driver[] = { module_phy_driver(bcm63xx_driver); -static struct mdio_device_id __maybe_unused bcm63xx_tbl[] = { +static const struct mdio_device_id __maybe_unused bcm63xx_tbl[] = { { 0x00406000, 0xfffffc00 }, { 0x002bdc00, 0xfffffc00 }, { } diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c index 97638ba7ae85..00e8fa14aa77 100644 --- a/drivers/net/phy/bcm7xxx.c +++ b/drivers/net/phy/bcm7xxx.c @@ -929,7 +929,7 @@ static struct phy_driver bcm7xxx_driver[] = { BCM7XXX_16NM_EPHY(PHY_ID_BCM7712, "Broadcom BCM7712"), }; -static struct mdio_device_id __maybe_unused bcm7xxx_tbl[] = { +static const struct mdio_device_id __maybe_unused bcm7xxx_tbl[] = { { PHY_ID_BCM72113, 0xfffffff0 }, { PHY_ID_BCM72116, 0xfffffff0, }, { PHY_ID_BCM72165, 0xfffffff0, }, diff --git a/drivers/net/phy/bcm84881.c b/drivers/net/phy/bcm84881.c index 47405bded677..d7f7cc44c532 100644 --- a/drivers/net/phy/bcm84881.c +++ b/drivers/net/phy/bcm84881.c @@ -262,7 +262,7 @@ static struct phy_driver bcm84881_drivers[] = { module_phy_driver(bcm84881_drivers); /* FIXME: module auto-loading for Clause 45 PHYs seems non-functional */ -static struct mdio_device_id __maybe_unused bcm84881_tbl[] = { +static const struct mdio_device_id __maybe_unused bcm84881_tbl[] = { { 0xae025150, 0xfffffff0 }, { }, }; diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c index ddded162c44c..22edb7e4c1a1 100644 --- a/drivers/net/phy/broadcom.c +++ b/drivers/net/phy/broadcom.c @@ -1717,7 +1717,7 @@ static struct phy_driver broadcom_drivers[] = { module_phy_driver(broadcom_drivers); -static struct mdio_device_id __maybe_unused broadcom_tbl[] = { +static const struct mdio_device_id __maybe_unused broadcom_tbl[] = { { PHY_ID_BCM5411, 0xfffffff0 }, { PHY_ID_BCM5421, 0xfffffff0 }, { PHY_ID_BCM54210E, 0xfffffff0 }, diff --git a/drivers/net/phy/cicada.c b/drivers/net/phy/cicada.c index ef5f412e101f..d87cf8b94cf8 100644 --- a/drivers/net/phy/cicada.c +++ b/drivers/net/phy/cicada.c @@ -145,7 +145,7 @@ static struct phy_driver cis820x_driver[] = { module_phy_driver(cis820x_driver); -static struct mdio_device_id __maybe_unused cicada_tbl[] = { +static const struct mdio_device_id __maybe_unused cicada_tbl[] = { { 0x000fc410, 0x000ffff0 }, { 0x000fc440, 0x000fffc0 }, { } diff --git a/drivers/net/phy/cortina.c b/drivers/net/phy/cortina.c index 40514a94e6ff..3b65f37f1c57 100644 --- a/drivers/net/phy/cortina.c +++ b/drivers/net/phy/cortina.c @@ -87,7 +87,7 @@ static struct phy_driver cortina_driver[] = { module_phy_driver(cortina_driver); -static struct mdio_device_id __maybe_unused cortina_tbl[] = { +static const struct mdio_device_id __maybe_unused cortina_tbl[] = { { PHY_ID_CS4340, 0xffffffff}, {}, }; diff --git a/drivers/net/phy/davicom.c b/drivers/net/phy/davicom.c index 4ac4bce1bf32..fa3692508f16 100644 --- a/drivers/net/phy/davicom.c +++ b/drivers/net/phy/davicom.c @@ -209,7 +209,7 @@ static struct phy_driver dm91xx_driver[] = { module_phy_driver(dm91xx_driver); -static struct mdio_device_id __maybe_unused davicom_tbl[] = { +static const struct mdio_device_id __maybe_unused davicom_tbl[] = { { 0x0181b880, 0x0ffffff0 }, { 0x0181b8b0, 0x0ffffff0 }, { 0x0181b8a0, 0x0ffffff0 }, diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c index 075d2beea716..85e231451093 100644 --- a/drivers/net/phy/dp83640.c +++ b/drivers/net/phy/dp83640.c @@ -1548,7 +1548,7 @@ MODULE_LICENSE("GPL"); module_init(dp83640_init); module_exit(dp83640_exit); -static struct mdio_device_id __maybe_unused dp83640_tbl[] = { +static const struct mdio_device_id __maybe_unused dp83640_tbl[] = { { DP83640_PHY_ID, 0xfffffff0 }, { } }; diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c index 334c17a68edd..6599feca1967 100644 --- a/drivers/net/phy/dp83822.c +++ b/drivers/net/phy/dp83822.c @@ -30,6 +30,9 @@ #define MII_DP83822_FCSCR 0x14 #define MII_DP83822_RCSR 0x17 #define MII_DP83822_RESET_CTRL 0x1f +#define MII_DP83822_MLEDCR 0x25 +#define MII_DP83822_LEDCFG1 0x460 +#define MII_DP83822_IOCTRL1 0x462 #define MII_DP83822_IOCTRL2 0x463 #define MII_DP83822_GENCFG 0x465 #define MII_DP83822_SOR1 0x467 @@ -105,10 +108,26 @@ #define DP83822_RX_CLK_SHIFT BIT(12) #define DP83822_TX_CLK_SHIFT BIT(11) +/* MLEDCR bits */ +#define DP83822_MLEDCR_CFG GENMASK(6, 3) +#define DP83822_MLEDCR_ROUTE GENMASK(1, 0) +#define DP83822_MLEDCR_ROUTE_LED_0 DP83822_MLEDCR_ROUTE + +/* LEDCFG1 bits */ +#define DP83822_LEDCFG1_LED1_CTRL GENMASK(11, 8) +#define DP83822_LEDCFG1_LED3_CTRL GENMASK(7, 4) + +/* IOCTRL1 bits */ +#define DP83822_IOCTRL1_GPIO3_CTRL GENMASK(10, 8) +#define DP83822_IOCTRL1_GPIO3_CTRL_LED3 BIT(0) +#define DP83822_IOCTRL1_GPIO1_CTRL GENMASK(2, 0) +#define DP83822_IOCTRL1_GPIO1_CTRL_LED_1 BIT(0) + /* IOCTRL2 bits */ #define DP83822_IOCTRL2_GPIO2_CLK_SRC GENMASK(6, 4) #define DP83822_IOCTRL2_GPIO2_CTRL GENMASK(2, 0) #define DP83822_IOCTRL2_GPIO2_CTRL_CLK_REF GENMASK(1, 0) +#define DP83822_IOCTRL2_GPIO2_CTRL_MLED BIT(0) #define DP83822_CLK_SRC_MAC_IF 0x0 #define DP83822_CLK_SRC_XI 0x1 @@ -117,6 +136,22 @@ #define DP83822_CLK_SRC_FREE_RUNNING 0x6 #define DP83822_CLK_SRC_RECOVERED 0x7 +#define DP83822_LED_FN_LINK 0x0 /* Link established */ +#define DP83822_LED_FN_RX_TX 0x1 /* Receive or Transmit activity */ +#define DP83822_LED_FN_TX 0x2 /* Transmit activity */ +#define DP83822_LED_FN_RX 0x3 /* Receive activity */ +#define DP83822_LED_FN_COLLISION 0x4 /* Collision detected */ +#define DP83822_LED_FN_LINK_100_BTX 0x5 /* 100 BTX link established */ +#define DP83822_LED_FN_LINK_10_BT 0x6 /* 10BT link established */ +#define DP83822_LED_FN_FULL_DUPLEX 0x7 /* Full duplex */ +#define DP83822_LED_FN_LINK_RX_TX 0x8 /* Link established, blink for rx or tx activity */ +#define DP83822_LED_FN_ACTIVE_STRETCH 0x9 /* Active Stretch Signal */ +#define DP83822_LED_FN_MII_LINK 0xa /* MII LINK (100BT+FD) */ +#define DP83822_LED_FN_LPI_MODE 0xb /* LPI Mode (EEE) */ +#define DP83822_LED_FN_RX_TX_ERR 0xc /* TX/RX MII Error */ +#define DP83822_LED_FN_LINK_LOST 0xd /* Link Lost */ +#define DP83822_LED_FN_PRBS_ERR 0xe /* Blink for PRBS error */ + /* SOR1 mode */ #define DP83822_STRAP_MODE1 0 #define DP83822_STRAP_MODE2 BIT(0) @@ -145,6 +180,13 @@ ADVERTISED_FIBRE | \ ADVERTISED_Pause | ADVERTISED_Asym_Pause) +#define DP83822_MAX_LED_PINS 4 + +#define DP83822_LED_INDEX_LED_0 0 +#define DP83822_LED_INDEX_LED_1_GPIO1 1 +#define DP83822_LED_INDEX_COL_GPIO2 2 +#define DP83822_LED_INDEX_RX_D3_GPIO3 3 + struct dp83822_private { bool fx_signal_det_low; int fx_enabled; @@ -154,6 +196,7 @@ struct dp83822_private { struct ethtool_wolinfo wol; bool set_gpio2_clk_out; u32 gpio2_clk_out; + bool led_pin_enable[DP83822_MAX_LED_PINS]; }; static int dp83822_config_wol(struct phy_device *phydev, @@ -418,6 +461,48 @@ static int dp83822_read_status(struct phy_device *phydev) return 0; } +static int dp83822_config_init_leds(struct phy_device *phydev) +{ + struct dp83822_private *dp83822 = phydev->priv; + int ret; + + if (dp83822->led_pin_enable[DP83822_LED_INDEX_LED_0]) { + ret = phy_modify_mmd(phydev, MDIO_MMD_VEND2, MII_DP83822_MLEDCR, + DP83822_MLEDCR_ROUTE, + FIELD_PREP(DP83822_MLEDCR_ROUTE, + DP83822_MLEDCR_ROUTE_LED_0)); + if (ret) + return ret; + } else if (dp83822->led_pin_enable[DP83822_LED_INDEX_COL_GPIO2]) { + ret = phy_modify_mmd(phydev, MDIO_MMD_VEND2, MII_DP83822_IOCTRL2, + DP83822_IOCTRL2_GPIO2_CTRL, + FIELD_PREP(DP83822_IOCTRL2_GPIO2_CTRL, + DP83822_IOCTRL2_GPIO2_CTRL_MLED)); + if (ret) + return ret; + } + + if (dp83822->led_pin_enable[DP83822_LED_INDEX_LED_1_GPIO1]) { + ret = phy_modify_mmd(phydev, MDIO_MMD_VEND2, MII_DP83822_IOCTRL1, + DP83822_IOCTRL1_GPIO1_CTRL, + FIELD_PREP(DP83822_IOCTRL1_GPIO1_CTRL, + DP83822_IOCTRL1_GPIO1_CTRL_LED_1)); + if (ret) + return ret; + } + + if (dp83822->led_pin_enable[DP83822_LED_INDEX_RX_D3_GPIO3]) { + ret = phy_modify_mmd(phydev, MDIO_MMD_VEND2, MII_DP83822_IOCTRL1, + DP83822_IOCTRL1_GPIO3_CTRL, + FIELD_PREP(DP83822_IOCTRL1_GPIO3_CTRL, + DP83822_IOCTRL1_GPIO3_CTRL_LED3)); + if (ret) + return ret; + } + + return 0; +} + static int dp83822_config_init(struct phy_device *phydev) { struct dp83822_private *dp83822 = phydev->priv; @@ -437,6 +522,10 @@ static int dp83822_config_init(struct phy_device *phydev) FIELD_PREP(DP83822_IOCTRL2_GPIO2_CLK_SRC, dp83822->gpio2_clk_out)); + err = dp83822_config_init_leds(phydev); + if (err) + return err; + if (phy_interface_is_rgmii(phydev)) { rx_int_delay = phy_get_internal_delay(phydev, dev, NULL, 0, true); @@ -631,6 +720,61 @@ static int dp83822_phy_reset(struct phy_device *phydev) } #ifdef CONFIG_OF_MDIO +static int dp83822_of_init_leds(struct phy_device *phydev) +{ + struct device_node *node = phydev->mdio.dev.of_node; + struct dp83822_private *dp83822 = phydev->priv; + struct device_node *leds; + u32 index; + int err; + + if (!node) + return 0; + + leds = of_get_child_by_name(node, "leds"); + if (!leds) + return 0; + + for_each_available_child_of_node_scoped(leds, led) { + err = of_property_read_u32(led, "reg", &index); + if (err) { + of_node_put(leds); + return err; + } + + if (index <= DP83822_LED_INDEX_RX_D3_GPIO3) { + dp83822->led_pin_enable[index] = true; + } else { + of_node_put(leds); + return -EINVAL; + } + } + + of_node_put(leds); + /* LED_0 and COL(GPIO2) use the MLED function. MLED can be routed to + * only one of these two pins at a time. + */ + if (dp83822->led_pin_enable[DP83822_LED_INDEX_LED_0] && + dp83822->led_pin_enable[DP83822_LED_INDEX_COL_GPIO2]) { + phydev_err(phydev, "LED_0 and COL(GPIO2) cannot be used as LED output at the same time\n"); + return -EINVAL; + } + + if (dp83822->led_pin_enable[DP83822_LED_INDEX_COL_GPIO2] && + dp83822->set_gpio2_clk_out) { + phydev_err(phydev, "COL(GPIO2) cannot be used as LED output, already used as clock output\n"); + return -EINVAL; + } + + if (dp83822->led_pin_enable[DP83822_LED_INDEX_RX_D3_GPIO3] && + phydev->interface != PHY_INTERFACE_MODE_RMII) { + phydev_err(phydev, "RX_D3 can only be used as LED output when in RMII mode\n"); + return -EINVAL; + } + + return 0; +} + static int dp83822_of_init(struct phy_device *phydev) { struct dp83822_private *dp83822 = phydev->priv; @@ -671,7 +815,7 @@ static int dp83822_of_init(struct phy_device *phydev) dp83822->set_gpio2_clk_out = true; } - return 0; + return dp83822_of_init_leds(phydev); } static int dp83826_to_dac_minus_one_regval(int percent) @@ -769,7 +913,9 @@ static int dp83822_probe(struct phy_device *phydev) if (ret) return ret; - dp83822_of_init(phydev); + ret = dp83822_of_init(phydev); + if (ret) + return ret; if (dp83822->fx_enabled) phydev->port = PORT_FIBRE; @@ -816,6 +962,130 @@ static int dp83822_resume(struct phy_device *phydev) return 0; } +static int dp83822_led_mode(u8 index, unsigned long rules) +{ + switch (rules) { + case BIT(TRIGGER_NETDEV_LINK): + return DP83822_LED_FN_LINK; + case BIT(TRIGGER_NETDEV_LINK_10): + return DP83822_LED_FN_LINK_10_BT; + case BIT(TRIGGER_NETDEV_LINK_100): + return DP83822_LED_FN_LINK_100_BTX; + case BIT(TRIGGER_NETDEV_FULL_DUPLEX): + return DP83822_LED_FN_FULL_DUPLEX; + case BIT(TRIGGER_NETDEV_TX): + return DP83822_LED_FN_TX; + case BIT(TRIGGER_NETDEV_RX): + return DP83822_LED_FN_RX; + case BIT(TRIGGER_NETDEV_TX) | BIT(TRIGGER_NETDEV_RX): + return DP83822_LED_FN_RX_TX; + case BIT(TRIGGER_NETDEV_TX_ERR) | BIT(TRIGGER_NETDEV_RX_ERR): + return DP83822_LED_FN_RX_TX_ERR; + case BIT(TRIGGER_NETDEV_LINK) | BIT(TRIGGER_NETDEV_TX) | BIT(TRIGGER_NETDEV_RX): + return DP83822_LED_FN_LINK_RX_TX; + default: + return -EOPNOTSUPP; + } +} + +static int dp83822_led_hw_is_supported(struct phy_device *phydev, u8 index, + unsigned long rules) +{ + int mode; + + mode = dp83822_led_mode(index, rules); + if (mode < 0) + return mode; + + return 0; +} + +static int dp83822_led_hw_control_set(struct phy_device *phydev, u8 index, + unsigned long rules) +{ + int mode; + + mode = dp83822_led_mode(index, rules); + if (mode < 0) + return mode; + + if (index == DP83822_LED_INDEX_LED_0 || index == DP83822_LED_INDEX_COL_GPIO2) + return phy_modify_mmd(phydev, MDIO_MMD_VEND2, + MII_DP83822_MLEDCR, DP83822_MLEDCR_CFG, + FIELD_PREP(DP83822_MLEDCR_CFG, mode)); + else if (index == DP83822_LED_INDEX_LED_1_GPIO1) + return phy_modify_mmd(phydev, MDIO_MMD_VEND2, + MII_DP83822_LEDCFG1, + DP83822_LEDCFG1_LED1_CTRL, + FIELD_PREP(DP83822_LEDCFG1_LED1_CTRL, + mode)); + else + return phy_modify_mmd(phydev, MDIO_MMD_VEND2, + MII_DP83822_LEDCFG1, + DP83822_LEDCFG1_LED3_CTRL, + FIELD_PREP(DP83822_LEDCFG1_LED3_CTRL, + mode)); +} + +static int dp83822_led_hw_control_get(struct phy_device *phydev, u8 index, + unsigned long *rules) +{ + int val; + + if (index == DP83822_LED_INDEX_LED_0 || index == DP83822_LED_INDEX_COL_GPIO2) { + val = phy_read_mmd(phydev, MDIO_MMD_VEND2, MII_DP83822_MLEDCR); + if (val < 0) + return val; + + val = FIELD_GET(DP83822_MLEDCR_CFG, val); + } else { + val = phy_read_mmd(phydev, MDIO_MMD_VEND2, MII_DP83822_LEDCFG1); + if (val < 0) + return val; + + if (index == DP83822_LED_INDEX_LED_1_GPIO1) + val = FIELD_GET(DP83822_LEDCFG1_LED1_CTRL, val); + else + val = FIELD_GET(DP83822_LEDCFG1_LED3_CTRL, val); + } + + switch (val) { + case DP83822_LED_FN_LINK: + *rules = BIT(TRIGGER_NETDEV_LINK); + break; + case DP83822_LED_FN_LINK_10_BT: + *rules = BIT(TRIGGER_NETDEV_LINK_10); + break; + case DP83822_LED_FN_LINK_100_BTX: + *rules = BIT(TRIGGER_NETDEV_LINK_100); + break; + case DP83822_LED_FN_FULL_DUPLEX: + *rules = BIT(TRIGGER_NETDEV_FULL_DUPLEX); + break; + case DP83822_LED_FN_TX: + *rules = BIT(TRIGGER_NETDEV_TX); + break; + case DP83822_LED_FN_RX: + *rules = BIT(TRIGGER_NETDEV_RX); + break; + case DP83822_LED_FN_RX_TX: + *rules = BIT(TRIGGER_NETDEV_TX) | BIT(TRIGGER_NETDEV_RX); + break; + case DP83822_LED_FN_RX_TX_ERR: + *rules = BIT(TRIGGER_NETDEV_TX_ERR) | BIT(TRIGGER_NETDEV_RX_ERR); + break; + case DP83822_LED_FN_LINK_RX_TX: + *rules = BIT(TRIGGER_NETDEV_LINK) | BIT(TRIGGER_NETDEV_TX) | + BIT(TRIGGER_NETDEV_RX); + break; + default: + *rules = 0; + break; + } + + return 0; +} + #define DP83822_PHY_DRIVER(_id, _name) \ { \ PHY_ID_MATCH_MODEL(_id), \ @@ -831,6 +1101,9 @@ static int dp83822_resume(struct phy_device *phydev) .handle_interrupt = dp83822_handle_interrupt, \ .suspend = dp83822_suspend, \ .resume = dp83822_resume, \ + .led_hw_is_supported = dp83822_led_hw_is_supported, \ + .led_hw_control_set = dp83822_led_hw_control_set, \ + .led_hw_control_get = dp83822_led_hw_control_get, \ } #define DP83825_PHY_DRIVER(_id, _name) \ @@ -876,7 +1149,7 @@ static struct phy_driver dp83822_driver[] = { }; module_phy_driver(dp83822_driver); -static struct mdio_device_id __maybe_unused dp83822_tbl[] = { +static const struct mdio_device_id __maybe_unused dp83822_tbl[] = { { DP83822_PHY_ID, 0xfffffff0 }, { DP83825I_PHY_ID, 0xfffffff0 }, { DP83826C_PHY_ID, 0xfffffff0 }, diff --git a/drivers/net/phy/dp83848.c b/drivers/net/phy/dp83848.c index 351411f0aa6f..d88b1999d596 100644 --- a/drivers/net/phy/dp83848.c +++ b/drivers/net/phy/dp83848.c @@ -123,7 +123,7 @@ static int dp83848_config_init(struct phy_device *phydev) return 0; } -static struct mdio_device_id __maybe_unused dp83848_tbl[] = { +static const struct mdio_device_id __maybe_unused dp83848_tbl[] = { { TI_DP83848C_PHY_ID, 0xfffffff0 }, { NS_DP83848C_PHY_ID, 0xfffffff0 }, { TI_DP83620_PHY_ID, 0xfffffff0 }, diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c index 4120385c5a79..c1451df430ac 100644 --- a/drivers/net/phy/dp83867.c +++ b/drivers/net/phy/dp83867.c @@ -1210,7 +1210,7 @@ static struct phy_driver dp83867_driver[] = { }; module_phy_driver(dp83867_driver); -static struct mdio_device_id __maybe_unused dp83867_tbl[] = { +static const struct mdio_device_id __maybe_unused dp83867_tbl[] = { { DP83867_PHY_ID, 0xfffffff0 }, { } }; diff --git a/drivers/net/phy/dp83869.c b/drivers/net/phy/dp83869.c index b6b38caf9c0e..a62cd838a9ea 100644 --- a/drivers/net/phy/dp83869.c +++ b/drivers/net/phy/dp83869.c @@ -928,7 +928,7 @@ static struct phy_driver dp83869_driver[] = { }; module_phy_driver(dp83869_driver); -static struct mdio_device_id __maybe_unused dp83869_tbl[] = { +static const struct mdio_device_id __maybe_unused dp83869_tbl[] = { { PHY_ID_MATCH_MODEL(DP83869_PHY_ID) }, { PHY_ID_MATCH_MODEL(DP83561_PHY_ID) }, { } diff --git a/drivers/net/phy/dp83tc811.c b/drivers/net/phy/dp83tc811.c index 7ea32fb77190..e480c2a07450 100644 --- a/drivers/net/phy/dp83tc811.c +++ b/drivers/net/phy/dp83tc811.c @@ -403,7 +403,7 @@ static struct phy_driver dp83811_driver[] = { }; module_phy_driver(dp83811_driver); -static struct mdio_device_id __maybe_unused dp83811_tbl[] = { +static const struct mdio_device_id __maybe_unused dp83811_tbl[] = { { DP83TC811_PHY_ID, 0xfffffff0 }, { }, }; diff --git a/drivers/net/phy/dp83td510.c b/drivers/net/phy/dp83td510.c index 92aa3a2b9744..a42af9c168ec 100644 --- a/drivers/net/phy/dp83td510.c +++ b/drivers/net/phy/dp83td510.c @@ -34,6 +34,29 @@ #define DP83TD510E_CTRL_HW_RESET BIT(15) #define DP83TD510E_CTRL_SW_RESET BIT(14) +/* + * DP83TD510E_PKT_STAT_x registers correspond to similarly named registers + * in the datasheet (PKT_STAT_1 through PKT_STAT_6). These registers store + * 32-bit or 16-bit counters for TX and RX statistics and must be read in + * sequence to ensure the counters are cleared correctly. + * + * - DP83TD510E_PKT_STAT_1: Contains TX packet count bits [15:0]. + * - DP83TD510E_PKT_STAT_2: Contains TX packet count bits [31:16]. + * - DP83TD510E_PKT_STAT_3: Contains TX error packet count. + * - DP83TD510E_PKT_STAT_4: Contains RX packet count bits [15:0]. + * - DP83TD510E_PKT_STAT_5: Contains RX packet count bits [31:16]. + * - DP83TD510E_PKT_STAT_6: Contains RX error packet count. + * + * Keeping the register names as defined in the datasheet helps maintain + * clarity and alignment with the documentation. + */ +#define DP83TD510E_PKT_STAT_1 0x12b +#define DP83TD510E_PKT_STAT_2 0x12c +#define DP83TD510E_PKT_STAT_3 0x12d +#define DP83TD510E_PKT_STAT_4 0x12e +#define DP83TD510E_PKT_STAT_5 0x12f +#define DP83TD510E_PKT_STAT_6 0x130 + #define DP83TD510E_AN_STAT_1 0x60c #define DP83TD510E_MASTER_SLAVE_RESOL_FAIL BIT(15) @@ -58,8 +81,16 @@ static const u16 dp83td510_mse_sqi_map[] = { 0x0000 /* 24dB =< SNR */ }; +struct dp83td510_stats { + u64 tx_pkt_cnt; + u64 tx_err_pkt_cnt; + u64 rx_pkt_cnt; + u64 rx_err_pkt_cnt; +}; + struct dp83td510_priv { bool alcd_test_active; + struct dp83td510_stats stats; }; /* Time Domain Reflectometry (TDR) Functionality of DP83TD510 PHY @@ -177,6 +208,85 @@ struct dp83td510_priv { #define DP83TD510E_ALCD_COMPLETE BIT(15) #define DP83TD510E_ALCD_CABLE_LENGTH GENMASK(10, 0) +/** + * dp83td510_update_stats - Update the PHY statistics for the DP83TD510 PHY. + * @phydev: Pointer to the phy_device structure. + * + * The function reads the PHY statistics registers and updates the statistics + * structure. + * + * Returns: 0 on success or a negative error code on failure. + */ +static int dp83td510_update_stats(struct phy_device *phydev) +{ + struct dp83td510_priv *priv = phydev->priv; + u32 count; + int ret; + + /* The DP83TD510E_PKT_STAT registers are divided into two groups: + * - Group 1 (TX stats): DP83TD510E_PKT_STAT_1 to DP83TD510E_PKT_STAT_3 + * - Group 2 (RX stats): DP83TD510E_PKT_STAT_4 to DP83TD510E_PKT_STAT_6 + * + * Registers in each group are cleared only after reading them in a + * plain sequence (e.g., 1, 2, 3 for Group 1 or 4, 5, 6 for Group 2). + * Any deviation from the sequence, such as reading 1, 2, 1, 2, 3, will + * prevent the group from being cleared. Additionally, the counters + * for a group are frozen as soon as the first register in that group + * is accessed. + */ + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, DP83TD510E_PKT_STAT_1); + if (ret < 0) + return ret; + /* tx_pkt_cnt_15_0 */ + count = ret; + + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, DP83TD510E_PKT_STAT_2); + if (ret < 0) + return ret; + /* tx_pkt_cnt_31_16 */ + count |= ret << 16; + priv->stats.tx_pkt_cnt += count; + + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, DP83TD510E_PKT_STAT_3); + if (ret < 0) + return ret; + /* tx_err_pkt_cnt */ + priv->stats.tx_err_pkt_cnt += ret; + + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, DP83TD510E_PKT_STAT_4); + if (ret < 0) + return ret; + /* rx_pkt_cnt_15_0 */ + count = ret; + + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, DP83TD510E_PKT_STAT_5); + if (ret < 0) + return ret; + /* rx_pkt_cnt_31_16 */ + count |= ret << 16; + priv->stats.rx_pkt_cnt += count; + + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, DP83TD510E_PKT_STAT_6); + if (ret < 0) + return ret; + /* rx_err_pkt_cnt */ + priv->stats.rx_err_pkt_cnt += ret; + + return 0; +} + +static void dp83td510_get_phy_stats(struct phy_device *phydev, + struct ethtool_eth_phy_stats *eth_stats, + struct ethtool_phy_stats *stats) +{ + struct dp83td510_priv *priv = phydev->priv; + + stats->tx_packets = priv->stats.tx_pkt_cnt; + stats->tx_errors = priv->stats.tx_err_pkt_cnt; + stats->rx_packets = priv->stats.rx_pkt_cnt; + stats->rx_errors = priv->stats.rx_err_pkt_cnt; +} + static int dp83td510_config_intr(struct phy_device *phydev) { int ret; @@ -599,13 +709,15 @@ static struct phy_driver dp83td510_driver[] = { .get_sqi_max = dp83td510_get_sqi_max, .cable_test_start = dp83td510_cable_test_start, .cable_test_get_status = dp83td510_cable_test_get_status, + .get_phy_stats = dp83td510_get_phy_stats, + .update_stats = dp83td510_update_stats, .suspend = genphy_suspend, .resume = genphy_resume, } }; module_phy_driver(dp83td510_driver); -static struct mdio_device_id __maybe_unused dp83td510_tbl[] = { +static const struct mdio_device_id __maybe_unused dp83td510_tbl[] = { { PHY_ID_MATCH_MODEL(DP83TD510E_PHY_ID) }, { } }; diff --git a/drivers/net/phy/dp83tg720.c b/drivers/net/phy/dp83tg720.c index 0ef4d7dba065..050f4537d140 100644 --- a/drivers/net/phy/dp83tg720.c +++ b/drivers/net/phy/dp83tg720.c @@ -51,6 +51,9 @@ /* Register 0x0405: Unknown Register */ #define DP83TG720S_UNKNOWN_0405 0x405 +#define DP83TG720S_LINK_QUAL_3 0x547 +#define DP83TG720S_LINK_LOSS_CNT_MASK GENMASK(15, 10) + /* Register 0x0576: TDR Master Link Down Control */ #define DP83TG720S_TDR_MASTER_LINK_DOWN 0x576 @@ -60,6 +63,29 @@ /* In RGMII mode, Enable or disable the internal delay for TXD */ #define DP83TG720S_RGMII_TX_CLK_SEL BIT(0) +/* + * DP83TG720S_PKT_STAT_x registers correspond to similarly named registers + * in the datasheet (PKT_STAT_1 through PKT_STAT_6). These registers store + * 32-bit or 16-bit counters for TX and RX statistics and must be read in + * sequence to ensure the counters are cleared correctly. + * + * - DP83TG720S_PKT_STAT_1: Contains TX packet count bits [15:0]. + * - DP83TG720S_PKT_STAT_2: Contains TX packet count bits [31:16]. + * - DP83TG720S_PKT_STAT_3: Contains TX error packet count. + * - DP83TG720S_PKT_STAT_4: Contains RX packet count bits [15:0]. + * - DP83TG720S_PKT_STAT_5: Contains RX packet count bits [31:16]. + * - DP83TG720S_PKT_STAT_6: Contains RX error packet count. + * + * Keeping the register names as defined in the datasheet helps maintain + * clarity and alignment with the documentation. + */ +#define DP83TG720S_PKT_STAT_1 0x639 +#define DP83TG720S_PKT_STAT_2 0x63a +#define DP83TG720S_PKT_STAT_3 0x63b +#define DP83TG720S_PKT_STAT_4 0x63c +#define DP83TG720S_PKT_STAT_5 0x63d +#define DP83TG720S_PKT_STAT_6 0x63e + /* Register 0x083F: Unknown Register */ #define DP83TG720S_UNKNOWN_083F 0x83f @@ -69,6 +95,113 @@ #define DP83TG720_SQI_MAX 7 +struct dp83tg720_stats { + u64 link_loss_cnt; + u64 tx_pkt_cnt; + u64 tx_err_pkt_cnt; + u64 rx_pkt_cnt; + u64 rx_err_pkt_cnt; +}; + +struct dp83tg720_priv { + struct dp83tg720_stats stats; +}; + +/** + * dp83tg720_update_stats - Update the PHY statistics for the DP83TD510 PHY. + * @phydev: Pointer to the phy_device structure. + * + * The function reads the PHY statistics registers and updates the statistics + * structure. + * + * Returns: 0 on success or a negative error code on failure. + */ +static int dp83tg720_update_stats(struct phy_device *phydev) +{ + struct dp83tg720_priv *priv = phydev->priv; + u32 count; + int ret; + + /* Read the link loss count */ + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, DP83TG720S_LINK_QUAL_3); + if (ret < 0) + return ret; + /* link_loss_cnt */ + count = FIELD_GET(DP83TG720S_LINK_LOSS_CNT_MASK, ret); + priv->stats.link_loss_cnt += count; + + /* The DP83TG720S_PKT_STAT registers are divided into two groups: + * - Group 1 (TX stats): DP83TG720S_PKT_STAT_1 to DP83TG720S_PKT_STAT_3 + * - Group 2 (RX stats): DP83TG720S_PKT_STAT_4 to DP83TG720S_PKT_STAT_6 + * + * Registers in each group are cleared only after reading them in a + * plain sequence (e.g., 1, 2, 3 for Group 1 or 4, 5, 6 for Group 2). + * Any deviation from the sequence, such as reading 1, 2, 1, 2, 3, will + * prevent the group from being cleared. Additionally, the counters + * for a group are frozen as soon as the first register in that group + * is accessed. + */ + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, DP83TG720S_PKT_STAT_1); + if (ret < 0) + return ret; + /* tx_pkt_cnt_15_0 */ + count = ret; + + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, DP83TG720S_PKT_STAT_2); + if (ret < 0) + return ret; + /* tx_pkt_cnt_31_16 */ + count |= ret << 16; + priv->stats.tx_pkt_cnt += count; + + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, DP83TG720S_PKT_STAT_3); + if (ret < 0) + return ret; + /* tx_err_pkt_cnt */ + priv->stats.tx_err_pkt_cnt += ret; + + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, DP83TG720S_PKT_STAT_4); + if (ret < 0) + return ret; + /* rx_pkt_cnt_15_0 */ + count = ret; + + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, DP83TG720S_PKT_STAT_5); + if (ret < 0) + return ret; + /* rx_pkt_cnt_31_16 */ + count |= ret << 16; + priv->stats.rx_pkt_cnt += count; + + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, DP83TG720S_PKT_STAT_6); + if (ret < 0) + return ret; + /* rx_err_pkt_cnt */ + priv->stats.rx_err_pkt_cnt += ret; + + return 0; +} + +static void dp83tg720_get_link_stats(struct phy_device *phydev, + struct ethtool_link_ext_stats *link_stats) +{ + struct dp83tg720_priv *priv = phydev->priv; + + link_stats->link_down_events = priv->stats.link_loss_cnt; +} + +static void dp83tg720_get_phy_stats(struct phy_device *phydev, + struct ethtool_eth_phy_stats *eth_stats, + struct ethtool_phy_stats *stats) +{ + struct dp83tg720_priv *priv = phydev->priv; + + stats->tx_packets = priv->stats.tx_pkt_cnt; + stats->tx_errors = priv->stats.tx_err_pkt_cnt; + stats->rx_packets = priv->stats.rx_pkt_cnt; + stats->rx_errors = priv->stats.rx_err_pkt_cnt; +} + /** * dp83tg720_cable_test_start - Start the cable test for the DP83TG720 PHY. * @phydev: Pointer to the phy_device structure. @@ -182,6 +315,11 @@ static int dp83tg720_cable_test_get_status(struct phy_device *phydev, ethnl_cable_test_result(phydev, ETHTOOL_A_CABLE_PAIR_A, stat); + /* save the current stats before resetting the PHY */ + ret = dp83tg720_update_stats(phydev); + if (ret) + return ret; + return phy_init_hw(phydev); } @@ -217,6 +355,11 @@ static int dp83tg720_read_status(struct phy_device *phydev) phy_sts = phy_read(phydev, DP83TG720S_MII_REG_10); phydev->link = !!(phy_sts & DP83TG720S_LINK_STATUS); if (!phydev->link) { + /* save the current stats before resetting the PHY */ + ret = dp83tg720_update_stats(phydev); + if (ret) + return ret; + /* According to the "DP83TC81x, DP83TG72x Software * Implementation Guide", the PHY needs to be reset after a * link loss or if no link is created after at least 100ms. @@ -341,12 +484,27 @@ static int dp83tg720_config_init(struct phy_device *phydev) return genphy_c45_pma_baset1_read_master_slave(phydev); } +static int dp83tg720_probe(struct phy_device *phydev) +{ + struct device *dev = &phydev->mdio.dev; + struct dp83tg720_priv *priv; + + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + phydev->priv = priv; + + return 0; +} + static struct phy_driver dp83tg720_driver[] = { { PHY_ID_MATCH_MODEL(DP83TG720S_PHY_ID), .name = "TI DP83TG720S", .flags = PHY_POLL_CABLE_TEST, + .probe = dp83tg720_probe, .config_aneg = dp83tg720_config_aneg, .read_status = dp83tg720_read_status, .get_features = genphy_c45_pma_read_ext_abilities, @@ -355,13 +513,16 @@ static struct phy_driver dp83tg720_driver[] = { .get_sqi_max = dp83tg720_get_sqi_max, .cable_test_start = dp83tg720_cable_test_start, .cable_test_get_status = dp83tg720_cable_test_get_status, + .get_link_stats = dp83tg720_get_link_stats, + .get_phy_stats = dp83tg720_get_phy_stats, + .update_stats = dp83tg720_update_stats, .suspend = genphy_suspend, .resume = genphy_resume, } }; module_phy_driver(dp83tg720_driver); -static struct mdio_device_id __maybe_unused dp83tg720_tbl[] = { +static const struct mdio_device_id __maybe_unused dp83tg720_tbl[] = { { PHY_ID_MATCH_MODEL(DP83TG720S_PHY_ID) }, { } }; diff --git a/drivers/net/phy/et1011c.c b/drivers/net/phy/et1011c.c index be1b71d7cab7..6cd8d77586fd 100644 --- a/drivers/net/phy/et1011c.c +++ b/drivers/net/phy/et1011c.c @@ -94,7 +94,7 @@ static struct phy_driver et1011c_driver[] = { { module_phy_driver(et1011c_driver); -static struct mdio_device_id __maybe_unused et1011c_tbl[] = { +static const struct mdio_device_id __maybe_unused et1011c_tbl[] = { { 0x0282f014, 0xfffffff0 }, { } }; diff --git a/drivers/net/phy/icplus.c b/drivers/net/phy/icplus.c index ee438b71a0b4..bbcc7d2b54cd 100644 --- a/drivers/net/phy/icplus.c +++ b/drivers/net/phy/icplus.c @@ -623,7 +623,7 @@ static struct phy_driver icplus_driver[] = { module_phy_driver(icplus_driver); -static struct mdio_device_id __maybe_unused icplus_tbl[] = { +static const struct mdio_device_id __maybe_unused icplus_tbl[] = { { PHY_ID_MATCH_MODEL(IP175C_PHY_ID) }, { PHY_ID_MATCH_MODEL(IP1001_PHY_ID) }, { PHY_ID_MATCH_EXACT(IP101A_PHY_ID) }, diff --git a/drivers/net/phy/intel-xway.c b/drivers/net/phy/intel-xway.c index e6ed2413e514..a44771e8acdc 100644 --- a/drivers/net/phy/intel-xway.c +++ b/drivers/net/phy/intel-xway.c @@ -691,7 +691,7 @@ static struct phy_driver xway_gphy[] = { }; module_phy_driver(xway_gphy); -static struct mdio_device_id __maybe_unused xway_gphy_tbl[] = { +static const struct mdio_device_id __maybe_unused xway_gphy_tbl[] = { { PHY_ID_PHY11G_1_3, 0xffffffff }, { PHY_ID_PHY22F_1_3, 0xffffffff }, { PHY_ID_PHY11G_1_4, 0xffffffff }, diff --git a/drivers/net/phy/lxt.c b/drivers/net/phy/lxt.c index e3bf827b7959..5251a61c8b0f 100644 --- a/drivers/net/phy/lxt.c +++ b/drivers/net/phy/lxt.c @@ -348,7 +348,7 @@ static struct phy_driver lxt97x_driver[] = { module_phy_driver(lxt97x_driver); -static struct mdio_device_id __maybe_unused lxt_tbl[] = { +static const struct mdio_device_id __maybe_unused lxt_tbl[] = { { 0x78100000, 0xfffffff0 }, { 0x001378e0, 0xfffffff0 }, { 0x00137a10, 0xfffffff0 }, diff --git a/drivers/net/phy/marvell-88q2xxx.c b/drivers/net/phy/marvell-88q2xxx.c index 5107f58338af..4494b3e39ce2 100644 --- a/drivers/net/phy/marvell-88q2xxx.c +++ b/drivers/net/phy/marvell-88q2xxx.c @@ -939,7 +939,7 @@ static struct phy_driver mv88q2xxx_driver[] = { module_phy_driver(mv88q2xxx_driver); -static struct mdio_device_id __maybe_unused mv88q2xxx_tbl[] = { +static const struct mdio_device_id __maybe_unused mv88q2xxx_tbl[] = { { MARVELL_PHY_ID_88Q2110, MARVELL_PHY_ID_MASK }, { MARVELL_PHY_ID_88Q2220, MARVELL_PHY_ID_MASK }, { /*sentinel*/ } diff --git a/drivers/net/phy/marvell-88x2222.c b/drivers/net/phy/marvell-88x2222.c index 0b777cdd7078..fad2f54c1eac 100644 --- a/drivers/net/phy/marvell-88x2222.c +++ b/drivers/net/phy/marvell-88x2222.c @@ -613,7 +613,7 @@ static struct phy_driver mv2222_drivers[] = { }; module_phy_driver(mv2222_drivers); -static struct mdio_device_id __maybe_unused mv2222_tbl[] = { +static const struct mdio_device_id __maybe_unused mv2222_tbl[] = { { MARVELL_PHY_ID_88X2222, MARVELL_PHY_ID_MASK }, { } }; diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index ffe223ad9e5f..44e1927de499 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -4189,7 +4189,7 @@ static struct phy_driver marvell_drivers[] = { module_phy_driver(marvell_drivers); -static struct mdio_device_id __maybe_unused marvell_tbl[] = { +static const struct mdio_device_id __maybe_unused marvell_tbl[] = { { MARVELL_PHY_ID_88E1101, MARVELL_PHY_ID_MASK }, { MARVELL_PHY_ID_88E3082, MARVELL_PHY_ID_MASK }, { MARVELL_PHY_ID_88E1112, MARVELL_PHY_ID_MASK }, diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c index 6642eb642d4b..623bdb8466b8 100644 --- a/drivers/net/phy/marvell10g.c +++ b/drivers/net/phy/marvell10g.c @@ -1484,7 +1484,7 @@ static struct phy_driver mv3310_drivers[] = { module_phy_driver(mv3310_drivers); -static struct mdio_device_id __maybe_unused mv3310_tbl[] = { +static const struct mdio_device_id __maybe_unused mv3310_tbl[] = { { MARVELL_PHY_ID_88X3310, MARVELL_PHY_ID_MASK }, { MARVELL_PHY_ID_88E2110, MARVELL_PHY_ID_MASK }, { }, diff --git a/drivers/net/phy/mediatek/mtk-ge-soc.c b/drivers/net/phy/mediatek/mtk-ge-soc.c index 38dc898eaf7b..bdf99b327029 100644 --- a/drivers/net/phy/mediatek/mtk-ge-soc.c +++ b/drivers/net/phy/mediatek/mtk-ge-soc.c @@ -1356,7 +1356,7 @@ static struct phy_driver mtk_socphy_driver[] = { module_phy_driver(mtk_socphy_driver); -static struct mdio_device_id __maybe_unused mtk_socphy_tbl[] = { +static const struct mdio_device_id __maybe_unused mtk_socphy_tbl[] = { { PHY_ID_MATCH_EXACT(MTK_GPHY_ID_MT7981) }, { PHY_ID_MATCH_EXACT(MTK_GPHY_ID_MT7988) }, { } diff --git a/drivers/net/phy/mediatek/mtk-ge.c b/drivers/net/phy/mediatek/mtk-ge.c index ed2617bc20f4..b517ca8573e7 100644 --- a/drivers/net/phy/mediatek/mtk-ge.c +++ b/drivers/net/phy/mediatek/mtk-ge.c @@ -93,7 +93,7 @@ static struct phy_driver mtk_gephy_driver[] = { module_phy_driver(mtk_gephy_driver); -static struct mdio_device_id __maybe_unused mtk_gephy_tbl[] = { +static const struct mdio_device_id __maybe_unused mtk_gephy_tbl[] = { { PHY_ID_MATCH_EXACT(MTK_GPHY_ID_MT7530) }, { PHY_ID_MATCH_EXACT(MTK_GPHY_ID_MT7531) }, { } diff --git a/drivers/net/phy/meson-gxl.c b/drivers/net/phy/meson-gxl.c index bb9b33b6bce2..962ebbbc1348 100644 --- a/drivers/net/phy/meson-gxl.c +++ b/drivers/net/phy/meson-gxl.c @@ -221,7 +221,7 @@ static struct phy_driver meson_gxl_phy[] = { }, }; -static struct mdio_device_id __maybe_unused meson_gxl_tbl[] = { +static const struct mdio_device_id __maybe_unused meson_gxl_tbl[] = { { PHY_ID_MATCH_VENDOR(0x01814400) }, { PHY_ID_MATCH_VENDOR(0x01803301) }, { } diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 0fd1cb676cd5..9c0b1c229af6 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -5689,7 +5689,7 @@ MODULE_DESCRIPTION("Micrel PHY driver"); MODULE_AUTHOR("David J. Choi"); MODULE_LICENSE("GPL"); -static struct mdio_device_id __maybe_unused micrel_tbl[] = { +static const struct mdio_device_id __maybe_unused micrel_tbl[] = { { PHY_ID_KSZ9021, 0x000ffffe }, { PHY_ID_KSZ9031, MICREL_PHY_ID_MASK }, { PHY_ID_KSZ9131, MICREL_PHY_ID_MASK }, diff --git a/drivers/net/phy/microchip.c b/drivers/net/phy/microchip.c index 691969a4910f..0e17cc458efd 100644 --- a/drivers/net/phy/microchip.c +++ b/drivers/net/phy/microchip.c @@ -548,7 +548,7 @@ static struct phy_driver microchip_phy_driver[] = { module_phy_driver(microchip_phy_driver); -static struct mdio_device_id __maybe_unused microchip_tbl[] = { +static const struct mdio_device_id __maybe_unused microchip_tbl[] = { { 0x0007c132, 0xfffffff2 }, { PHY_ID_MATCH_MODEL(PHY_ID_LAN937X_TX) }, { } diff --git a/drivers/net/phy/microchip_rds_ptp.c b/drivers/net/phy/microchip_rds_ptp.c index 2936e46531cf..3e6bf10cdeed 100644 --- a/drivers/net/phy/microchip_rds_ptp.c +++ b/drivers/net/phy/microchip_rds_ptp.c @@ -54,6 +54,243 @@ static int mchp_rds_phy_set_bits_mmd(struct mchp_rds_ptp_clock *clock, return phy_set_bits_mmd(phydev, PTP_MMD(clock), addr, val); } +static int mchp_get_pulsewidth(struct phy_device *phydev, + struct ptp_perout_request *perout_request, + int *pulse_width) +{ + struct timespec64 ts_period; + s64 ts_on_nsec, period_nsec; + struct timespec64 ts_on; + static const s64 sup_on_necs[] = { + 100, /* 100ns */ + 500, /* 500ns */ + 1000, /* 1us */ + 5000, /* 5us */ + 10000, /* 10us */ + 50000, /* 50us */ + 100000, /* 100us */ + 500000, /* 500us */ + 1000000, /* 1ms */ + 5000000, /* 5ms */ + 10000000, /* 10ms */ + 50000000, /* 50ms */ + 100000000, /* 100ms */ + 200000000, /* 200ms */ + }; + + ts_period.tv_sec = perout_request->period.sec; + ts_period.tv_nsec = perout_request->period.nsec; + + ts_on.tv_sec = perout_request->on.sec; + ts_on.tv_nsec = perout_request->on.nsec; + ts_on_nsec = timespec64_to_ns(&ts_on); + period_nsec = timespec64_to_ns(&ts_period); + + if (period_nsec < 200) { + phydev_warn(phydev, "perout period small, minimum is 200ns\n"); + return -EOPNOTSUPP; + } + + for (int i = 0; i < ARRAY_SIZE(sup_on_necs); i++) { + if (ts_on_nsec <= sup_on_necs[i]) { + *pulse_width = i; + break; + } + } + + phydev_info(phydev, "pulse width is %d\n", *pulse_width); + return 0; +} + +static int mchp_general_event_config(struct mchp_rds_ptp_clock *clock, + int pulse_width) +{ + int general_config; + + general_config = mchp_rds_phy_read_mmd(clock, MCHP_RDS_PTP_GEN_CFG, + MCHP_RDS_PTP_CLOCK); + if (general_config < 0) + return general_config; + + general_config &= ~MCHP_RDS_PTP_GEN_CFG_LTC_EVT_MASK; + general_config |= MCHP_RDS_PTP_GEN_CFG_LTC_EVT_SET(pulse_width); + general_config &= ~MCHP_RDS_PTP_GEN_CFG_RELOAD_ADD; + general_config |= MCHP_RDS_PTP_GEN_CFG_POLARITY; + + return mchp_rds_phy_write_mmd(clock, MCHP_RDS_PTP_GEN_CFG, + MCHP_RDS_PTP_CLOCK, general_config); +} + +static int mchp_set_clock_reload(struct mchp_rds_ptp_clock *clock, + s64 period_sec, u32 period_nsec) +{ + int rc; + + rc = mchp_rds_phy_write_mmd(clock, + MCHP_RDS_PTP_CLK_TRGT_RELOAD_SEC_LO, + MCHP_RDS_PTP_CLOCK, + lower_16_bits(period_sec)); + if (rc < 0) + return rc; + + rc = mchp_rds_phy_write_mmd(clock, + MCHP_RDS_PTP_CLK_TRGT_RELOAD_SEC_HI, + MCHP_RDS_PTP_CLOCK, + upper_16_bits(period_sec)); + if (rc < 0) + return rc; + + rc = mchp_rds_phy_write_mmd(clock, + MCHP_RDS_PTP_CLK_TRGT_RELOAD_NS_LO, + MCHP_RDS_PTP_CLOCK, + lower_16_bits(period_nsec)); + if (rc < 0) + return rc; + + return mchp_rds_phy_write_mmd(clock, + MCHP_RDS_PTP_CLK_TRGT_RELOAD_NS_HI, + MCHP_RDS_PTP_CLOCK, + upper_16_bits(period_nsec) & 0x3fff); +} + +static int mchp_set_clock_target(struct mchp_rds_ptp_clock *clock, + s64 start_sec, u32 start_nsec) +{ + int rc; + + /* Set the start time */ + rc = mchp_rds_phy_write_mmd(clock, MCHP_RDS_PTP_CLK_TRGT_SEC_LO, + MCHP_RDS_PTP_CLOCK, + lower_16_bits(start_sec)); + if (rc < 0) + return rc; + + rc = mchp_rds_phy_write_mmd(clock, MCHP_RDS_PTP_CLK_TRGT_SEC_HI, + MCHP_RDS_PTP_CLOCK, + upper_16_bits(start_sec)); + if (rc < 0) + return rc; + + rc = mchp_rds_phy_write_mmd(clock, MCHP_RDS_PTP_CLK_TRGT_NS_LO, + MCHP_RDS_PTP_CLOCK, + lower_16_bits(start_nsec)); + if (rc < 0) + return rc; + + return mchp_rds_phy_write_mmd(clock, MCHP_RDS_PTP_CLK_TRGT_NS_HI, + MCHP_RDS_PTP_CLOCK, + upper_16_bits(start_nsec) & 0x3fff); +} + +static int mchp_rds_ptp_perout_off(struct mchp_rds_ptp_clock *clock) +{ + u16 general_config; + int rc; + + /* Set target to too far in the future, effectively disabling it */ + rc = mchp_set_clock_target(clock, 0xFFFFFFFF, 0); + if (rc < 0) + return rc; + + general_config = mchp_rds_phy_read_mmd(clock, MCHP_RDS_PTP_GEN_CFG, + MCHP_RDS_PTP_CLOCK); + general_config |= MCHP_RDS_PTP_GEN_CFG_RELOAD_ADD; + rc = mchp_rds_phy_write_mmd(clock, MCHP_RDS_PTP_GEN_CFG, + MCHP_RDS_PTP_CLOCK, general_config); + if (rc < 0) + return rc; + + clock->mchp_rds_ptp_event = -1; + + return 0; +} + +static bool mchp_get_event(struct mchp_rds_ptp_clock *clock, int pin) +{ + if (clock->mchp_rds_ptp_event < 0 && pin == clock->event_pin) { + clock->mchp_rds_ptp_event = pin; + return true; + } + + return false; +} + +static int mchp_rds_ptp_perout(struct ptp_clock_info *ptpci, + struct ptp_perout_request *perout, int on) +{ + struct mchp_rds_ptp_clock *clock = container_of(ptpci, + struct mchp_rds_ptp_clock, + caps); + struct phy_device *phydev = clock->phydev; + int ret, event_pin, pulsewidth; + + /* Reject requests with unsupported flags */ + if (perout->flags & ~PTP_PEROUT_DUTY_CYCLE) + return -EOPNOTSUPP; + + event_pin = ptp_find_pin(clock->ptp_clock, PTP_PF_PEROUT, + perout->index); + if (event_pin != clock->event_pin) + return -EINVAL; + + if (!on) { + ret = mchp_rds_ptp_perout_off(clock); + return ret; + } + + if (!mchp_get_event(clock, event_pin)) + return -EINVAL; + + ret = mchp_get_pulsewidth(phydev, perout, &pulsewidth); + if (ret < 0) + return ret; + + /* Configure to pulse every period */ + ret = mchp_general_event_config(clock, pulsewidth); + if (ret < 0) + return ret; + + ret = mchp_set_clock_target(clock, perout->start.sec, + perout->start.nsec); + if (ret < 0) + return ret; + + return mchp_set_clock_reload(clock, perout->period.sec, + perout->period.nsec); +} + +static int mchp_rds_ptpci_enable(struct ptp_clock_info *ptpci, + struct ptp_clock_request *request, int on) +{ + switch (request->type) { + case PTP_CLK_REQ_PEROUT: + return mchp_rds_ptp_perout(ptpci, &request->perout, on); + default: + return -EINVAL; + } +} + +static int mchp_rds_ptpci_verify(struct ptp_clock_info *ptpci, unsigned int pin, + enum ptp_pin_function func, unsigned int chan) +{ + struct mchp_rds_ptp_clock *clock = container_of(ptpci, + struct mchp_rds_ptp_clock, + caps); + + if (!(pin == clock->event_pin && chan == 0)) + return -1; + + switch (func) { + case PTP_PF_NONE: + case PTP_PF_PEROUT: + break; + default: + return -1; + } + + return 0; +} + static int mchp_rds_ptp_flush_fifo(struct mchp_rds_ptp_clock *clock, enum mchp_rds_ptp_fifo_dir dir) { @@ -479,6 +716,16 @@ static int mchp_rds_ptp_ltc_adjtime(struct ptp_clock_info *info, s64 delta) MCHP_RDS_PTP_CMD_CTL_LTC_STEP_NSEC); } + mutex_unlock(&clock->ptp_lock); + info->gettime64(info, &ts); + mutex_lock(&clock->ptp_lock); + + /* Target update is required for pulse generation on events that + * are enabled + */ + if (clock->mchp_rds_ptp_event >= 0) + mchp_set_clock_target(clock, + ts.tv_sec + MCHP_RDS_PTP_BUFFER_TIME, 0); out_unlock: mutex_unlock(&clock->ptp_lock); @@ -989,16 +1236,37 @@ struct mchp_rds_ptp_clock *mchp_rds_ptp_probe(struct phy_device *phydev, u8 mmd, clock->mmd = mmd; mutex_init(&clock->ptp_lock); + clock->pin_config = devm_kmalloc_array(&phydev->mdio.dev, + MCHP_RDS_PTP_N_PIN, + sizeof(*clock->pin_config), + GFP_KERNEL); + if (!clock->pin_config) + return ERR_PTR(-ENOMEM); + + for (int i = 0; i < MCHP_RDS_PTP_N_PIN; ++i) { + struct ptp_pin_desc *p = &clock->pin_config[i]; + + memset(p, 0, sizeof(*p)); + snprintf(p->name, sizeof(p->name), "pin%d", i); + p->index = i; + p->func = PTP_PF_NONE; + } /* Register PTP clock */ clock->caps.owner = THIS_MODULE; snprintf(clock->caps.name, 30, "%s", phydev->drv->name); clock->caps.max_adj = MCHP_RDS_PTP_MAX_ADJ; clock->caps.n_ext_ts = 0; clock->caps.pps = 0; + clock->caps.n_pins = MCHP_RDS_PTP_N_PIN; + clock->caps.n_per_out = MCHP_RDS_PTP_N_PEROUT; + clock->caps.pin_config = clock->pin_config; clock->caps.adjfine = mchp_rds_ptp_ltc_adjfine; clock->caps.adjtime = mchp_rds_ptp_ltc_adjtime; clock->caps.gettime64 = mchp_rds_ptp_ltc_gettime64; clock->caps.settime64 = mchp_rds_ptp_ltc_settime64; + clock->caps.enable = mchp_rds_ptpci_enable; + clock->caps.verify = mchp_rds_ptpci_verify; + clock->caps.getcrosststamp = NULL; clock->ptp_clock = ptp_clock_register(&clock->caps, &phydev->mdio.dev); if (IS_ERR(clock->ptp_clock)) @@ -1021,6 +1289,8 @@ struct mchp_rds_ptp_clock *mchp_rds_ptp_probe(struct phy_device *phydev, u8 mmd, phydev->mii_ts = &clock->mii_ts; + clock->mchp_rds_ptp_event = -1; + /* Timestamp selected by default to keep legacy API */ phydev->default_timestamp = true; diff --git a/drivers/net/phy/microchip_rds_ptp.h b/drivers/net/phy/microchip_rds_ptp.h index e95c065728b5..25af68337b94 100644 --- a/drivers/net/phy/microchip_rds_ptp.h +++ b/drivers/net/phy/microchip_rds_ptp.h @@ -130,6 +130,23 @@ #define MCHP_RDS_PTP_TSU_HARD_RESET 0xc1 #define MCHP_RDS_PTP_TSU_HARDRESET BIT(0) +#define MCHP_RDS_PTP_CLK_TRGT_SEC_HI 0x15 +#define MCHP_RDS_PTP_CLK_TRGT_SEC_LO 0x16 +#define MCHP_RDS_PTP_CLK_TRGT_NS_HI 0x17 +#define MCHP_RDS_PTP_CLK_TRGT_NS_LO 0x18 + +#define MCHP_RDS_PTP_CLK_TRGT_RELOAD_SEC_HI 0x19 +#define MCHP_RDS_PTP_CLK_TRGT_RELOAD_SEC_LO 0x1a +#define MCHP_RDS_PTP_CLK_TRGT_RELOAD_NS_HI 0x1b +#define MCHP_RDS_PTP_CLK_TRGT_RELOAD_NS_LO 0x1c + +#define MCHP_RDS_PTP_GEN_CFG 0x01 +#define MCHP_RDS_PTP_GEN_CFG_LTC_EVT_MASK GENMASK(11, 8) + +#define MCHP_RDS_PTP_GEN_CFG_LTC_EVT_SET(value) (((value) & 0xF) << 4) +#define MCHP_RDS_PTP_GEN_CFG_RELOAD_ADD BIT(0) +#define MCHP_RDS_PTP_GEN_CFG_POLARITY BIT(1) + /* Represents 1ppm adjustment in 2^32 format with * each nsec contains 4 clock cycles in 250MHz. * The value is calculated as following: (1/1000000)/((2^-32)/4) @@ -138,6 +155,10 @@ #define MCHP_RDS_PTP_FIFO_SIZE 8 #define MCHP_RDS_PTP_MAX_ADJ 31249999 +#define MCHP_RDS_PTP_BUFFER_TIME 2 +#define MCHP_RDS_PTP_N_PIN 4 +#define MCHP_RDS_PTP_N_PEROUT 1 + #define BASE_CLK(p) ((p)->clk_base_addr) #define BASE_PORT(p) ((p)->port_base_addr) #define PTP_MMD(p) ((p)->mmd) @@ -176,6 +197,9 @@ struct mchp_rds_ptp_clock { /* Lock for phc */ struct mutex ptp_lock; u8 mmd; + int mchp_rds_ptp_event; + int event_pin; + struct ptp_pin_desc *pin_config; }; struct mchp_rds_ptp_rx_ts { diff --git a/drivers/net/phy/microchip_t1.c b/drivers/net/phy/microchip_t1.c index 73f28463bc35..62b36a318100 100644 --- a/drivers/net/phy/microchip_t1.c +++ b/drivers/net/phy/microchip_t1.c @@ -238,6 +238,9 @@ #define LAN887X_INT_MSK_LINK_UP_MSK BIT(1) #define LAN887X_INT_MSK_LINK_DOWN_MSK BIT(0) +#define LAN887X_MX_CHIP_TOP_REG_CONTROL1 0xF002 +#define LAN887X_MX_CHIP_TOP_REG_CONTROL1_EVT_EN BIT(8) + #define LAN887X_MX_CHIP_TOP_LINK_MSK (LAN887X_INT_MSK_LINK_UP_MSK |\ LAN887X_INT_MSK_LINK_DOWN_MSK) @@ -1286,6 +1289,15 @@ static int lan887x_phy_init(struct phy_device *phydev) if (IS_ERR(priv->clock)) return PTR_ERR(priv->clock); + /* Enable pin mux for EVT */ + phy_modify_mmd(phydev, MDIO_MMD_VEND1, + LAN887X_MX_CHIP_TOP_REG_CONTROL1, + LAN887X_MX_CHIP_TOP_REG_CONTROL1_EVT_EN, + LAN887X_MX_CHIP_TOP_REG_CONTROL1_EVT_EN); + + /* Initialize pin numbers specific to PEROUT */ + priv->clock->event_pin = 3; + priv->init_done = true; } diff --git a/drivers/net/phy/microchip_t1s.c b/drivers/net/phy/microchip_t1s.c index 75d291154b4c..e50a0c102a86 100644 --- a/drivers/net/phy/microchip_t1s.c +++ b/drivers/net/phy/microchip_t1s.c @@ -497,7 +497,7 @@ static struct phy_driver microchip_t1s_driver[] = { module_phy_driver(microchip_t1s_driver); -static struct mdio_device_id __maybe_unused tbl[] = { +static const struct mdio_device_id __maybe_unused tbl[] = { { PHY_ID_MATCH_EXACT(PHY_ID_LAN867X_REVB1) }, { PHY_ID_MATCH_EXACT(PHY_ID_LAN867X_REVC1) }, { PHY_ID_MATCH_EXACT(PHY_ID_LAN867X_REVC2) }, diff --git a/drivers/net/phy/mscc/mscc_main.c b/drivers/net/phy/mscc/mscc_main.c index bee381200ab8..19cf12ee8990 100644 --- a/drivers/net/phy/mscc/mscc_main.c +++ b/drivers/net/phy/mscc/mscc_main.c @@ -2699,7 +2699,7 @@ static struct phy_driver vsc85xx_driver[] = { module_phy_driver(vsc85xx_driver); -static struct mdio_device_id __maybe_unused vsc85xx_tbl[] = { +static const struct mdio_device_id __maybe_unused vsc85xx_tbl[] = { { PHY_ID_MATCH_VENDOR(PHY_VENDOR_MSCC) }, { } }; diff --git a/drivers/net/phy/mxl-gpy.c b/drivers/net/phy/mxl-gpy.c index a8ccf257c109..94d9cb727121 100644 --- a/drivers/net/phy/mxl-gpy.c +++ b/drivers/net/phy/mxl-gpy.c @@ -1274,7 +1274,7 @@ static struct phy_driver gpy_drivers[] = { }; module_phy_driver(gpy_drivers); -static struct mdio_device_id __maybe_unused gpy_tbl[] = { +static const struct mdio_device_id __maybe_unused gpy_tbl[] = { {PHY_ID_MATCH_MODEL(PHY_ID_GPY2xx)}, {PHY_ID_GPY115B, PHY_ID_GPYx15B_MASK}, {PHY_ID_MATCH_MODEL(PHY_ID_GPY115C)}, diff --git a/drivers/net/phy/national.c b/drivers/net/phy/national.c index 9ae9cc6b23c2..7f3ff322892e 100644 --- a/drivers/net/phy/national.c +++ b/drivers/net/phy/national.c @@ -173,7 +173,7 @@ MODULE_DESCRIPTION("NatSemi PHY driver"); MODULE_AUTHOR("Stuart Menefy"); MODULE_LICENSE("GPL"); -static struct mdio_device_id __maybe_unused ns_tbl[] = { +static const struct mdio_device_id __maybe_unused ns_tbl[] = { { DP83865_PHY_ID, 0xfffffff0 }, { } }; diff --git a/drivers/net/phy/ncn26000.c b/drivers/net/phy/ncn26000.c index 5680584f659e..cabdd83c614f 100644 --- a/drivers/net/phy/ncn26000.c +++ b/drivers/net/phy/ncn26000.c @@ -159,7 +159,7 @@ static struct phy_driver ncn26000_driver[] = { module_phy_driver(ncn26000_driver); -static struct mdio_device_id __maybe_unused ncn26000_tbl[] = { +static const struct mdio_device_id __maybe_unused ncn26000_tbl[] = { { PHY_ID_MATCH_MODEL(PHY_ID_NCN26000) }, { } }; diff --git a/drivers/net/phy/nxp-c45-tja11xx.c b/drivers/net/phy/nxp-c45-tja11xx.c index ade544bc007d..323717a4821f 100644 --- a/drivers/net/phy/nxp-c45-tja11xx.c +++ b/drivers/net/phy/nxp-c45-tja11xx.c @@ -2008,7 +2008,7 @@ static struct phy_driver nxp_c45_driver[] = { module_phy_driver(nxp_c45_driver); -static struct mdio_device_id __maybe_unused nxp_c45_tbl[] = { +static const struct mdio_device_id __maybe_unused nxp_c45_tbl[] = { { PHY_ID_MATCH_MODEL(PHY_ID_TJA_1103) }, { PHY_ID_MATCH_MODEL(PHY_ID_TJA_1120) }, { /*sentinel*/ }, diff --git a/drivers/net/phy/nxp-cbtx.c b/drivers/net/phy/nxp-cbtx.c index 3d25491043a3..3286fcb4f47e 100644 --- a/drivers/net/phy/nxp-cbtx.c +++ b/drivers/net/phy/nxp-cbtx.c @@ -215,7 +215,7 @@ static struct phy_driver cbtx_driver[] = { module_phy_driver(cbtx_driver); -static struct mdio_device_id __maybe_unused cbtx_tbl[] = { +static const struct mdio_device_id __maybe_unused cbtx_tbl[] = { { PHY_ID_MATCH_MODEL(PHY_ID_CBTX_SJA1110) }, { }, }; diff --git a/drivers/net/phy/nxp-tja11xx.c b/drivers/net/phy/nxp-tja11xx.c index 2c263ae44b4f..ed7fa26bac8e 100644 --- a/drivers/net/phy/nxp-tja11xx.c +++ b/drivers/net/phy/nxp-tja11xx.c @@ -888,7 +888,7 @@ static struct phy_driver tja11xx_driver[] = { module_phy_driver(tja11xx_driver); -static struct mdio_device_id __maybe_unused tja11xx_tbl[] = { +static const struct mdio_device_id __maybe_unused tja11xx_tbl[] = { { PHY_ID_MATCH_MODEL(PHY_ID_TJA1100) }, { PHY_ID_MATCH_MODEL(PHY_ID_TJA1101) }, { PHY_ID_MATCH_MODEL(PHY_ID_TJA1102) }, diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index e4b04cdaa995..d0c1718e2b16 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -616,6 +616,49 @@ int phy_ethtool_get_stats(struct phy_device *phydev, EXPORT_SYMBOL(phy_ethtool_get_stats); /** + * __phy_ethtool_get_phy_stats - Retrieve standardized PHY statistics + * @phydev: Pointer to the PHY device + * @phy_stats: Pointer to ethtool_eth_phy_stats structure + * @phydev_stats: Pointer to ethtool_phy_stats structure + * + * Fetches PHY statistics using a kernel-defined interface for consistent + * diagnostics. Unlike phy_ethtool_get_stats(), which allows custom stats, + * this function enforces a standardized format for better interoperability. + */ +void __phy_ethtool_get_phy_stats(struct phy_device *phydev, + struct ethtool_eth_phy_stats *phy_stats, + struct ethtool_phy_stats *phydev_stats) +{ + if (!phydev->drv || !phydev->drv->get_phy_stats) + return; + + mutex_lock(&phydev->lock); + phydev->drv->get_phy_stats(phydev, phy_stats, phydev_stats); + mutex_unlock(&phydev->lock); +} + +/** + * __phy_ethtool_get_link_ext_stats - Retrieve extended link statistics for a PHY + * @phydev: Pointer to the PHY device + * @link_stats: Pointer to the structure to store extended link statistics + * + * Populates the ethtool_link_ext_stats structure with link down event counts + * and additional driver-specific link statistics, if available. + */ +void __phy_ethtool_get_link_ext_stats(struct phy_device *phydev, + struct ethtool_link_ext_stats *link_stats) +{ + link_stats->link_down_events = READ_ONCE(phydev->link_down_events); + + if (!phydev->drv || !phydev->drv->get_link_stats) + return; + + mutex_lock(&phydev->lock); + phydev->drv->get_link_stats(phydev, link_stats); + mutex_unlock(&phydev->lock); +} + +/** * phy_ethtool_get_plca_cfg - Get PLCA RS configuration * @phydev: the phy_device struct * @plca_cfg: where to store the retrieved configuration @@ -1399,6 +1442,23 @@ static int phy_enable_interrupts(struct phy_device *phydev) } /** + * phy_update_stats - Update PHY device statistics if supported. + * @phydev: Pointer to the PHY device structure. + * + * If the PHY driver provides an update_stats callback, this function + * invokes it to update the PHY statistics. If not, it returns 0. + * + * Return: 0 on success, or a negative error code if the callback fails. + */ +static int phy_update_stats(struct phy_device *phydev) +{ + if (!phydev->drv->update_stats) + return 0; + + return phydev->drv->update_stats(phydev); +} + +/** * phy_request_interrupt - request and enable interrupt for a PHY device * @phydev: target phy_device struct * @@ -1467,6 +1527,9 @@ static enum phy_state_work _phy_state_machine(struct phy_device *phydev) case PHY_RUNNING: err = phy_check_link_status(phydev); func = &phy_check_link_status; + + if (!err) + err = phy_update_stats(phydev); break; case PHY_CABLETEST: err = phydev->drv->cable_test_get_status(phydev, &finished); @@ -1641,6 +1704,47 @@ void phy_mac_interrupt(struct phy_device *phydev) EXPORT_SYMBOL(phy_mac_interrupt); /** + * phy_eee_tx_clock_stop_capable() - indicate whether the MAC can stop tx clock + * @phydev: target phy_device struct + * + * Indicate whether the MAC can disable the transmit xMII clock while in LPI + * state. Returns 1 if the MAC may stop the transmit clock, 0 if the MAC must + * not stop the transmit clock, or negative error. + */ +int phy_eee_tx_clock_stop_capable(struct phy_device *phydev) +{ + int stat1; + + stat1 = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_STAT1); + if (stat1 < 0) + return stat1; + + return !!(stat1 & MDIO_PCS_STAT1_CLKSTOP_CAP); +} +EXPORT_SYMBOL_GPL(phy_eee_tx_clock_stop_capable); + +/** + * phy_eee_rx_clock_stop() - configure PHY receive clock in LPI + * @phydev: target phy_device struct + * @clk_stop_enable: flag to indicate whether the clock can be stopped + * + * Configure whether the PHY can disable its receive clock during LPI mode, + * See IEEE 802.3 sections 22.2.2.2, 35.2.2.10, and 45.2.3.1.4. + * + * Returns: 0 or negative error. + */ +int phy_eee_rx_clock_stop(struct phy_device *phydev, bool clk_stop_enable) +{ + /* Configure the PHY to stop receiving xMII + * clock while it is signaling LPI. + */ + return phy_modify_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1, + MDIO_PCS_CTRL1_CLKSTOP_EN, + clk_stop_enable ? MDIO_PCS_CTRL1_CLKSTOP_EN : 0); +} +EXPORT_SYMBOL_GPL(phy_eee_rx_clock_stop); + +/** * phy_init_eee - init and check the EEE feature * @phydev: target phy_device struct * @clk_stop_enable: PHY may stop the clock during LPI @@ -1664,11 +1768,7 @@ int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable) return -EPROTONOSUPPORT; if (clk_stop_enable) - /* Configure the PHY to stop receiving xMII - * clock while it is signaling LPI. - */ - ret = phy_set_bits_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1, - MDIO_PCS_CTRL1_CLKSTOP_EN); + ret = phy_eee_rx_clock_stop(phydev, true); return ret < 0 ? ret : 0; } diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index bdc997f59779..46713d27412b 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -60,15 +60,9 @@ EXPORT_SYMBOL_GPL(phy_gbit_features); __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_fibre_features) __ro_after_init; EXPORT_SYMBOL_GPL(phy_gbit_fibre_features); -__ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_all_ports_features) __ro_after_init; -EXPORT_SYMBOL_GPL(phy_gbit_all_ports_features); - __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_features) __ro_after_init; EXPORT_SYMBOL_GPL(phy_10gbit_features); -__ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_fec_features) __ro_after_init; -EXPORT_SYMBOL_GPL(phy_10gbit_fec_features); - const int phy_basic_ports_array[3] = { ETHTOOL_LINK_MODE_Autoneg_BIT, ETHTOOL_LINK_MODE_TP_BIT, @@ -76,12 +70,7 @@ const int phy_basic_ports_array[3] = { }; EXPORT_SYMBOL_GPL(phy_basic_ports_array); -const int phy_fibre_port_array[1] = { - ETHTOOL_LINK_MODE_FIBRE_BIT, -}; -EXPORT_SYMBOL_GPL(phy_fibre_port_array); - -const int phy_all_ports_features_array[7] = { +static const int phy_all_ports_features_array[7] = { ETHTOOL_LINK_MODE_Autoneg_BIT, ETHTOOL_LINK_MODE_TP_BIT, ETHTOOL_LINK_MODE_MII_BIT, @@ -90,7 +79,6 @@ const int phy_all_ports_features_array[7] = { ETHTOOL_LINK_MODE_BNC_BIT, ETHTOOL_LINK_MODE_Backplane_BIT, }; -EXPORT_SYMBOL_GPL(phy_all_ports_features_array); const int phy_10_100_features_array[4] = { ETHTOOL_LINK_MODE_10baseT_Half_BIT, @@ -124,20 +112,6 @@ const int phy_10gbit_features_array[1] = { }; EXPORT_SYMBOL_GPL(phy_10gbit_features_array); -static const int phy_10gbit_fec_features_array[1] = { - ETHTOOL_LINK_MODE_10000baseR_FEC_BIT, -}; - -__ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_full_features) __ro_after_init; -EXPORT_SYMBOL_GPL(phy_10gbit_full_features); - -static const int phy_10gbit_full_features_array[] = { - ETHTOOL_LINK_MODE_10baseT_Full_BIT, - ETHTOOL_LINK_MODE_100baseT_Full_BIT, - ETHTOOL_LINK_MODE_1000baseT_Full_BIT, - ETHTOOL_LINK_MODE_10000baseT_Full_BIT, -}; - static const int phy_eee_cap1_features_array[] = { ETHTOOL_LINK_MODE_100baseT_Full_BIT, ETHTOOL_LINK_MODE_1000baseT_Full_BIT, @@ -199,20 +173,7 @@ static void features_init(void) linkmode_set_bit_array(phy_gbit_features_array, ARRAY_SIZE(phy_gbit_features_array), phy_gbit_fibre_features); - linkmode_set_bit_array(phy_fibre_port_array, - ARRAY_SIZE(phy_fibre_port_array), - phy_gbit_fibre_features); - - /* 10/100 half/full + 1000 half/full + TP/MII/FIBRE/AUI/BNC/Backplane*/ - linkmode_set_bit_array(phy_all_ports_features_array, - ARRAY_SIZE(phy_all_ports_features_array), - phy_gbit_all_ports_features); - linkmode_set_bit_array(phy_10_100_features_array, - ARRAY_SIZE(phy_10_100_features_array), - phy_gbit_all_ports_features); - linkmode_set_bit_array(phy_gbit_features_array, - ARRAY_SIZE(phy_gbit_features_array), - phy_gbit_all_ports_features); + linkmode_set_bit(ETHTOOL_LINK_MODE_FIBRE_BIT, phy_gbit_fibre_features); /* 10/100 half/full + 1000 half/full + 10G full*/ linkmode_set_bit_array(phy_all_ports_features_array, @@ -228,17 +189,6 @@ static void features_init(void) ARRAY_SIZE(phy_10gbit_features_array), phy_10gbit_features); - /* 10/100/1000/10G full */ - linkmode_set_bit_array(phy_all_ports_features_array, - ARRAY_SIZE(phy_all_ports_features_array), - phy_10gbit_full_features); - linkmode_set_bit_array(phy_10gbit_full_features_array, - ARRAY_SIZE(phy_10gbit_full_features_array), - phy_10gbit_full_features); - /* 10G FEC only */ - linkmode_set_bit_array(phy_10gbit_fec_features_array, - ARRAY_SIZE(phy_10gbit_fec_features_array), - phy_10gbit_fec_features); linkmode_set_bit_array(phy_eee_cap1_features_array, ARRAY_SIZE(phy_eee_cap1_features_array), phy_eee_cap1_features); @@ -3800,6 +3750,8 @@ static const struct ethtool_phy_ops phy_ethtool_phy_ops = { static const struct phylib_stubs __phylib_stubs = { .hwtstamp_get = __phy_hwtstamp_get, .hwtstamp_set = __phy_hwtstamp_set, + .get_phy_stats = __phy_ethtool_get_phy_stats, + .get_link_ext_stats = __phy_ethtool_get_link_ext_stats, }; static void phylib_register_stubs(void) diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 31754d5fd659..66eea3f963d3 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -60,6 +60,7 @@ struct phylink { u8 act_link_an_mode; /* Active MLO_AN_xxx mode */ u8 link_port; /* The current non-phy ethtool port */ __ETHTOOL_DECLARE_LINK_MODE_MASK(supported); + __ETHTOOL_DECLARE_LINK_MODE_MASK(supported_lpi); /* The link configuration settings */ struct phylink_link_state link_config; @@ -81,12 +82,20 @@ struct phylink { unsigned int pcs_state; bool link_failed; + bool mac_supports_eee_ops; + bool mac_supports_eee; + bool phy_enable_tx_lpi; + bool mac_enable_tx_lpi; + bool mac_tx_clk_stop; + u32 mac_tx_lpi_timer; struct sfp_bus *sfp_bus; bool sfp_may_have_phy; DECLARE_PHY_INTERFACE_MASK(sfp_interfaces); __ETHTOOL_DECLARE_LINK_MODE_MASK(sfp_support); u8 sfp_port; + + struct eee_config eee_cfg; }; #define phylink_printk(level, pl, fmt, ...) \ @@ -1492,12 +1501,24 @@ static int phylink_change_inband_advert(struct phylink *pl) static void phylink_mac_pcs_get_state(struct phylink *pl, struct phylink_link_state *state) { + struct phylink_pcs *pcs; + bool autoneg; + linkmode_copy(state->advertising, pl->link_config.advertising); linkmode_zero(state->lp_advertising); state->interface = pl->link_config.interface; state->rate_matching = pl->link_config.rate_matching; - if (linkmode_test_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, - state->advertising)) { + state->an_complete = 0; + state->link = 1; + + pcs = pl->pcs; + if (!pcs || pcs->neg_mode) + autoneg = pl->pcs_neg_mode == PHYLINK_PCS_NEG_INBAND_ENABLED; + else + autoneg = linkmode_test_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, + state->advertising); + + if (autoneg) { state->speed = SPEED_UNKNOWN; state->duplex = DUPLEX_UNKNOWN; state->pause = MLO_PAUSE_NONE; @@ -1506,11 +1527,9 @@ static void phylink_mac_pcs_get_state(struct phylink *pl, state->duplex = pl->link_config.duplex; state->pause = pl->link_config.pause; } - state->an_complete = 0; - state->link = 1; - if (pl->pcs) - pl->pcs->ops->pcs_get_state(pl->pcs, state); + if (pcs) + pcs->ops->pcs_get_state(pcs, pl->pcs_neg_mode, state); else state->link = 0; } @@ -1574,6 +1593,39 @@ static const char *phylink_pause_to_str(int pause) } } +static void phylink_deactivate_lpi(struct phylink *pl) +{ + if (pl->mac_enable_tx_lpi) { + pl->mac_enable_tx_lpi = false; + + phylink_dbg(pl, "disabling LPI\n"); + + pl->mac_ops->mac_disable_tx_lpi(pl->config); + } +} + +static void phylink_activate_lpi(struct phylink *pl) +{ + int err; + + if (!test_bit(pl->cur_interface, pl->config->lpi_interfaces)) { + phylink_dbg(pl, "MAC does not support LPI with %s\n", + phy_modes(pl->cur_interface)); + return; + } + + phylink_dbg(pl, "LPI timer %uus, tx clock stop %u\n", + pl->mac_tx_lpi_timer, pl->mac_tx_clk_stop); + + err = pl->mac_ops->mac_enable_tx_lpi(pl->config, pl->mac_tx_lpi_timer, + pl->mac_tx_clk_stop); + if (!err) + pl->mac_enable_tx_lpi = true; + else + phylink_err(pl, "%ps() failed: %pe\n", + pl->mac_ops->mac_enable_tx_lpi, ERR_PTR(err)); +} + static void phylink_link_up(struct phylink *pl, struct phylink_link_state link_state) { @@ -1620,6 +1672,9 @@ static void phylink_link_up(struct phylink *pl, pl->cur_interface, speed, duplex, !!(link_state.pause & MLO_PAUSE_TX), rx_pause); + if (pl->mac_supports_eee && pl->phy_enable_tx_lpi) + phylink_activate_lpi(pl); + if (ndev) netif_carrier_on(ndev); @@ -1636,25 +1691,29 @@ static void phylink_link_down(struct phylink *pl) if (ndev) netif_carrier_off(ndev); + + phylink_deactivate_lpi(pl); + pl->mac_ops->mac_link_down(pl->config, pl->act_link_an_mode, pl->cur_interface); phylink_info(pl, "Link is Down\n"); } +static bool phylink_link_is_up(struct phylink *pl) +{ + return pl->netdev ? netif_carrier_ok(pl->netdev) : pl->old_link_state; +} + static void phylink_resolve(struct work_struct *w) { struct phylink *pl = container_of(w, struct phylink, resolve); struct phylink_link_state link_state; - struct net_device *ndev = pl->netdev; bool mac_config = false; bool retrigger = false; bool cur_link_state; mutex_lock(&pl->state_mutex); - if (pl->netdev) - cur_link_state = netif_carrier_ok(ndev); - else - cur_link_state = pl->old_link_state; + cur_link_state = phylink_link_is_up(pl); if (pl->phylink_disable_state) { pl->link_failed = false; @@ -1898,6 +1957,17 @@ struct phylink *phylink_create(struct phylink_config *config, return ERR_PTR(-EINVAL); } + pl->mac_supports_eee_ops = mac_ops->mac_disable_tx_lpi && + mac_ops->mac_enable_tx_lpi; + pl->mac_supports_eee = pl->mac_supports_eee_ops && + pl->config->lpi_capabilities && + !phy_interface_empty(pl->config->lpi_interfaces); + + /* Set the default EEE configuration */ + pl->eee_cfg.eee_enabled = pl->config->eee_enabled_default; + pl->eee_cfg.tx_lpi_enabled = pl->eee_cfg.eee_enabled; + pl->eee_cfg.tx_lpi_timer = pl->config->lpi_timer_default; + pl->phy_state.interface = iface; pl->link_interface = iface; if (iface == PHY_INTERFACE_MODE_MOCA) @@ -2002,16 +2072,22 @@ static void phylink_phy_change(struct phy_device *phydev, bool up) pl->phy_state.link = up; if (!up) pl->link_failed = true; + + /* Get the LPI state from phylib */ + pl->phy_enable_tx_lpi = phydev->enable_tx_lpi; + pl->mac_tx_lpi_timer = phydev->eee_cfg.tx_lpi_timer; mutex_unlock(&pl->state_mutex); phylink_run_resolve(pl); - phylink_dbg(pl, "phy link %s %s/%s/%s/%s/%s\n", up ? "up" : "down", + phylink_dbg(pl, "phy link %s %s/%s/%s/%s/%s/%slpi\n", + up ? "up" : "down", phy_modes(phydev->interface), phy_speed_to_str(phydev->speed), phy_duplex_to_str(phydev->duplex), phy_rate_matching_to_str(phydev->rate_matching), - phylink_pause_to_str(pl->phy_state.pause)); + phylink_pause_to_str(pl->phy_state.pause), + phydev->enable_tx_lpi ? "" : "no"); } static int phylink_validate_phy(struct phylink *pl, struct phy_device *phy, @@ -2141,6 +2217,36 @@ static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy, /* Restrict the phy advertisement according to the MAC support. */ linkmode_copy(phy->advertising, config.advertising); + + /* If the MAC supports phylink managed EEE, restrict the EEE + * advertisement according to the MAC's LPI capabilities. + */ + if (pl->mac_supports_eee) { + /* If EEE is enabled, then we need to call phy_support_eee() + * to ensure that the advertising mask is appropriately set. + * This also enables EEE at the PHY. + */ + if (pl->eee_cfg.eee_enabled) + phy_support_eee(phy); + + phy->eee_cfg.tx_lpi_enabled = pl->eee_cfg.tx_lpi_enabled; + phy->eee_cfg.tx_lpi_timer = pl->eee_cfg.tx_lpi_timer; + + /* Convert the MAC's LPI capabilities to linkmodes */ + linkmode_zero(pl->supported_lpi); + phylink_caps_to_linkmodes(pl->supported_lpi, + pl->config->lpi_capabilities); + + /* Restrict the PHYs EEE support/advertisement to the modes + * that the MAC supports. + */ + linkmode_and(phy->advertising_eee, phy->advertising_eee, + pl->supported_lpi); + } else if (pl->mac_supports_eee_ops) { + /* MAC supports phylink EEE, but wants EEE always disabled. */ + phy_disable_eee(phy); + } + mutex_unlock(&pl->state_mutex); mutex_unlock(&phy->lock); @@ -2156,7 +2262,13 @@ static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy, if (pl->config->mac_managed_pm) phy->mac_managed_pm = true; - return 0; + /* Allow the MAC to stop its clock if the PHY has the capability */ + pl->mac_tx_clk_stop = phy_eee_tx_clock_stop_capable(phy) > 0; + + /* Explicitly configure whether the PHY is allowed to stop it's + * receive clock. + */ + return phy_eee_rx_clock_stop(phy, pl->config->eee_rx_clk_stop_enable); } static int phylink_attach_phy(struct phylink *pl, struct phy_device *phy, @@ -2313,6 +2425,8 @@ void phylink_disconnect_phy(struct phylink *pl) mutex_lock(&phy->lock); mutex_lock(&pl->state_mutex); pl->phydev = NULL; + pl->phy_enable_tx_lpi = false; + pl->mac_tx_clk_stop = false; mutex_unlock(&pl->state_mutex); mutex_unlock(&phy->lock); flush_work(&pl->resolve); @@ -3067,8 +3181,16 @@ int phylink_ethtool_get_eee(struct phylink *pl, struct ethtool_keee *eee) ASSERT_RTNL(); - if (pl->phydev) + if (pl->mac_supports_eee_ops && !pl->mac_supports_eee) + return ret; + + if (pl->phydev) { ret = phy_ethtool_get_eee(pl->phydev, eee); + /* Restrict supported linkmode mask */ + if (ret == 0 && pl->mac_supports_eee_ops) + linkmode_and(eee->supported, eee->supported, + pl->supported_lpi); + } return ret; } @@ -3081,12 +3203,29 @@ EXPORT_SYMBOL_GPL(phylink_ethtool_get_eee); */ int phylink_ethtool_set_eee(struct phylink *pl, struct ethtool_keee *eee) { + bool mac_eee = pl->mac_supports_eee; int ret = -EOPNOTSUPP; ASSERT_RTNL(); - if (pl->phydev) + phylink_dbg(pl, "mac %s phylink EEE%s, adv %*pbl, LPI%s timer %uus\n", + mac_eee ? "supports" : "does not support", + eee->eee_enabled ? ", enabled" : "", + __ETHTOOL_LINK_MODE_MASK_NBITS, eee->advertised, + eee->tx_lpi_enabled ? " enabled" : "", eee->tx_lpi_timer); + + if (pl->mac_supports_eee_ops && !mac_eee) + return ret; + + if (pl->phydev) { + /* Restrict advertisement mask */ + if (pl->mac_supports_eee_ops) + linkmode_and(eee->advertised, eee->advertised, + pl->supported_lpi); ret = phy_ethtool_set_eee(pl->phydev, eee); + if (ret == 0) + eee_to_eeecfg(&pl->eee_cfg, eee); + } return ret; } @@ -3850,6 +3989,7 @@ static void phylink_decode_usgmii_word(struct phylink_link_state *state, /** * phylink_mii_c22_pcs_decode_state() - Decode MAC PCS state from MII registers * @state: a pointer to a &struct phylink_link_state. + * @neg_mode: link negotiation mode (PHYLINK_PCS_NEG_xxx) * @bmsr: The value of the %MII_BMSR register * @lpa: The value of the %MII_LPA register * @@ -3862,32 +4002,45 @@ static void phylink_decode_usgmii_word(struct phylink_link_state *state, * accessing @bmsr and @lpa cannot be done with MDIO directly. */ void phylink_mii_c22_pcs_decode_state(struct phylink_link_state *state, - u16 bmsr, u16 lpa) + unsigned int neg_mode, u16 bmsr, u16 lpa) { state->link = !!(bmsr & BMSR_LSTATUS); state->an_complete = !!(bmsr & BMSR_ANEGCOMPLETE); - /* If there is no link or autonegotiation is disabled, the LP advertisement - * data is not meaningful, so don't go any further. - */ - if (!state->link || !linkmode_test_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, - state->advertising)) + + /* If the link is down, the advertisement data is undefined. */ + if (!state->link) return; switch (state->interface) { case PHY_INTERFACE_MODE_1000BASEX: - phylink_decode_c37_word(state, lpa, SPEED_1000); + if (neg_mode == PHYLINK_PCS_NEG_INBAND_ENABLED) { + phylink_decode_c37_word(state, lpa, SPEED_1000); + } else { + state->speed = SPEED_1000; + state->duplex = DUPLEX_FULL; + state->pause |= MLO_PAUSE_TX | MLO_PAUSE_RX; + } break; case PHY_INTERFACE_MODE_2500BASEX: - phylink_decode_c37_word(state, lpa, SPEED_2500); + if (neg_mode == PHYLINK_PCS_NEG_INBAND_ENABLED) { + phylink_decode_c37_word(state, lpa, SPEED_2500); + } else { + state->speed = SPEED_2500; + state->duplex = DUPLEX_FULL; + state->pause |= MLO_PAUSE_TX | MLO_PAUSE_RX; + } break; case PHY_INTERFACE_MODE_SGMII: case PHY_INTERFACE_MODE_QSGMII: - phylink_decode_sgmii_word(state, lpa); + if (neg_mode == PHYLINK_PCS_NEG_INBAND_ENABLED) + phylink_decode_sgmii_word(state, lpa); break; + case PHY_INTERFACE_MODE_QUSGMII: - phylink_decode_usgmii_word(state, lpa); + if (neg_mode == PHYLINK_PCS_NEG_INBAND_ENABLED) + phylink_decode_usgmii_word(state, lpa); break; default: @@ -3900,6 +4053,7 @@ EXPORT_SYMBOL_GPL(phylink_mii_c22_pcs_decode_state); /** * phylink_mii_c22_pcs_get_state() - read the MAC PCS state * @pcs: a pointer to a &struct mdio_device. + * @neg_mode: link negotiation mode (PHYLINK_PCS_NEG_xxx) * @state: a pointer to a &struct phylink_link_state. * * Helper for MAC PCS supporting the 802.3 clause 22 register set for @@ -3912,6 +4066,7 @@ EXPORT_SYMBOL_GPL(phylink_mii_c22_pcs_decode_state); * structure. */ void phylink_mii_c22_pcs_get_state(struct mdio_device *pcs, + unsigned int neg_mode, struct phylink_link_state *state) { int bmsr, lpa; @@ -3923,7 +4078,7 @@ void phylink_mii_c22_pcs_get_state(struct mdio_device *pcs, return; } - phylink_mii_c22_pcs_decode_state(state, bmsr, lpa); + phylink_mii_c22_pcs_decode_state(state, neg_mode, bmsr, lpa); } EXPORT_SYMBOL_GPL(phylink_mii_c22_pcs_get_state); diff --git a/drivers/net/phy/qcom/at803x.c b/drivers/net/phy/qcom/at803x.c index 105602581a03..26350b962890 100644 --- a/drivers/net/phy/qcom/at803x.c +++ b/drivers/net/phy/qcom/at803x.c @@ -1098,7 +1098,7 @@ static struct phy_driver at803x_driver[] = { module_phy_driver(at803x_driver); -static struct mdio_device_id __maybe_unused atheros_tbl[] = { +static const struct mdio_device_id __maybe_unused atheros_tbl[] = { { ATH8030_PHY_ID, AT8030_PHY_ID_MASK }, { PHY_ID_MATCH_EXACT(ATH8031_PHY_ID) }, { PHY_ID_MATCH_EXACT(ATH8032_PHY_ID) }, diff --git a/drivers/net/phy/qcom/qca807x.c b/drivers/net/phy/qcom/qca807x.c index bd8a51ec0ecd..3279de857b47 100644 --- a/drivers/net/phy/qcom/qca807x.c +++ b/drivers/net/phy/qcom/qca807x.c @@ -828,7 +828,7 @@ static struct phy_driver qca807x_drivers[] = { }; module_phy_driver(qca807x_drivers); -static struct mdio_device_id __maybe_unused qca807x_tbl[] = { +static const struct mdio_device_id __maybe_unused qca807x_tbl[] = { { PHY_ID_MATCH_EXACT(PHY_ID_QCA8072) }, { PHY_ID_MATCH_EXACT(PHY_ID_QCA8075) }, { } diff --git a/drivers/net/phy/qcom/qca808x.c b/drivers/net/phy/qcom/qca808x.c index 5048304ccc9e..71498c518f0f 100644 --- a/drivers/net/phy/qcom/qca808x.c +++ b/drivers/net/phy/qcom/qca808x.c @@ -655,7 +655,7 @@ static struct phy_driver qca808x_driver[] = { module_phy_driver(qca808x_driver); -static struct mdio_device_id __maybe_unused qca808x_tbl[] = { +static const struct mdio_device_id __maybe_unused qca808x_tbl[] = { { PHY_ID_MATCH_EXACT(QCA8081_PHY_ID) }, { } }; diff --git a/drivers/net/phy/qcom/qca83xx.c b/drivers/net/phy/qcom/qca83xx.c index 7a5039920b9f..bc70ed8efd86 100644 --- a/drivers/net/phy/qcom/qca83xx.c +++ b/drivers/net/phy/qcom/qca83xx.c @@ -259,7 +259,7 @@ static struct phy_driver qca83xx_driver[] = { module_phy_driver(qca83xx_driver); -static struct mdio_device_id __maybe_unused qca83xx_tbl[] = { +static const struct mdio_device_id __maybe_unused qca83xx_tbl[] = { { PHY_ID_MATCH_EXACT(QCA8337_PHY_ID) }, { PHY_ID_MATCH_EXACT(QCA8327_A_PHY_ID) }, { PHY_ID_MATCH_EXACT(QCA8327_B_PHY_ID) }, diff --git a/drivers/net/phy/qsemi.c b/drivers/net/phy/qsemi.c index 30d15f7c9b03..7b70ba6cab66 100644 --- a/drivers/net/phy/qsemi.c +++ b/drivers/net/phy/qsemi.c @@ -155,7 +155,7 @@ static struct phy_driver qs6612_driver[] = { { module_phy_driver(qs6612_driver); -static struct mdio_device_id __maybe_unused qs6612_tbl[] = { +static const struct mdio_device_id __maybe_unused qs6612_tbl[] = { { 0x00181440, 0xfffffff0 }, { } }; diff --git a/drivers/net/phy/realtek/Kconfig b/drivers/net/phy/realtek/Kconfig new file mode 100644 index 000000000000..31935f147d87 --- /dev/null +++ b/drivers/net/phy/realtek/Kconfig @@ -0,0 +1,11 @@ +# SPDX-License-Identifier: GPL-2.0-only +config REALTEK_PHY + tristate "Realtek PHYs" + help + Currently supports RTL821x/RTL822x and fast ethernet PHYs + +config REALTEK_PHY_HWMON + def_bool REALTEK_PHY && HWMON + depends on !(REALTEK_PHY=y && HWMON=m) + help + Optional hwmon support for the temperature sensor diff --git a/drivers/net/phy/realtek/Makefile b/drivers/net/phy/realtek/Makefile new file mode 100644 index 000000000000..dd21cf87f2f1 --- /dev/null +++ b/drivers/net/phy/realtek/Makefile @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 +realtek-y += realtek_main.o +realtek-$(CONFIG_REALTEK_PHY_HWMON) += realtek_hwmon.o +obj-$(CONFIG_REALTEK_PHY) += realtek.o diff --git a/drivers/net/phy/realtek/realtek.h b/drivers/net/phy/realtek/realtek.h new file mode 100644 index 000000000000..a39b44fa18a0 --- /dev/null +++ b/drivers/net/phy/realtek/realtek.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef REALTEK_H +#define REALTEK_H + +#include <linux/phy.h> + +int rtl822x_hwmon_init(struct phy_device *phydev); + +#endif /* REALTEK_H */ diff --git a/drivers/net/phy/realtek/realtek_hwmon.c b/drivers/net/phy/realtek/realtek_hwmon.c new file mode 100644 index 000000000000..1ecb410bb941 --- /dev/null +++ b/drivers/net/phy/realtek/realtek_hwmon.c @@ -0,0 +1,79 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * HWMON support for Realtek PHY's + * + * Author: Heiner Kallweit <hkallweit1@gmail.com> + */ + +#include <linux/hwmon.h> +#include <linux/phy.h> + +#include "realtek.h" + +#define RTL822X_VND2_TSALRM 0xa662 +#define RTL822X_VND2_TSRR 0xbd84 +#define RTL822X_VND2_TSSR 0xb54c + +static int rtl822x_hwmon_get_temp(int raw) +{ + if (raw >= 512) + raw -= 1024; + + return 1000 * raw / 2; +} + +static int rtl822x_hwmon_read(struct device *dev, enum hwmon_sensor_types type, + u32 attr, int channel, long *val) +{ + struct phy_device *phydev = dev_get_drvdata(dev); + int raw; + + switch (attr) { + case hwmon_temp_input: + raw = phy_read_mmd(phydev, MDIO_MMD_VEND2, RTL822X_VND2_TSRR) & 0x3ff; + *val = rtl822x_hwmon_get_temp(raw); + break; + case hwmon_temp_max: + /* Chip reduces speed to 1G if threshold is exceeded */ + raw = phy_read_mmd(phydev, MDIO_MMD_VEND2, RTL822X_VND2_TSSR) >> 6; + *val = rtl822x_hwmon_get_temp(raw); + break; + default: + return -EINVAL; + } + + return 0; +} + +static const struct hwmon_ops rtl822x_hwmon_ops = { + .visible = 0444, + .read = rtl822x_hwmon_read, +}; + +static const struct hwmon_channel_info * const rtl822x_hwmon_info[] = { + HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT | HWMON_T_MAX), + NULL +}; + +static const struct hwmon_chip_info rtl822x_hwmon_chip_info = { + .ops = &rtl822x_hwmon_ops, + .info = rtl822x_hwmon_info, +}; + +int rtl822x_hwmon_init(struct phy_device *phydev) +{ + struct device *hwdev, *dev = &phydev->mdio.dev; + const char *name; + + /* Ensure over-temp alarm is reset. */ + phy_clear_bits_mmd(phydev, MDIO_MMD_VEND2, RTL822X_VND2_TSALRM, 3); + + name = devm_hwmon_sanitize_name(dev, dev_name(dev)); + if (IS_ERR(name)) + return PTR_ERR(name); + + hwdev = devm_hwmon_device_register_with_info(dev, name, phydev, + &rtl822x_hwmon_chip_info, + NULL); + return PTR_ERR_OR_ZERO(hwdev); +} diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek/realtek_main.c index f65d7f1f348e..38149958d95b 100644 --- a/drivers/net/phy/realtek.c +++ b/drivers/net/phy/realtek/realtek_main.c @@ -14,6 +14,8 @@ #include <linux/delay.h> #include <linux/clk.h> +#include "realtek.h" + #define RTL821x_PHYSR 0x11 #define RTL821x_PHYSR_DUPLEX BIT(13) #define RTL821x_PHYSR_SPEED GENMASK(15, 14) @@ -736,7 +738,11 @@ static int rtlgen_read_mmd(struct phy_device *phydev, int devnum, u16 regnum) { int ret; - if (devnum == MDIO_MMD_PCS && regnum == MDIO_PCS_EEE_ABLE) { + if (devnum == MDIO_MMD_VEND2) { + rtl821x_write_page(phydev, regnum >> 4); + ret = __phy_read(phydev, 0x10 + ((regnum & 0xf) >> 1)); + rtl821x_write_page(phydev, 0); + } else if (devnum == MDIO_MMD_PCS && regnum == MDIO_PCS_EEE_ABLE) { rtl821x_write_page(phydev, 0xa5c); ret = __phy_read(phydev, 0x12); rtl821x_write_page(phydev, 0); @@ -760,7 +766,11 @@ static int rtlgen_write_mmd(struct phy_device *phydev, int devnum, u16 regnum, { int ret; - if (devnum == MDIO_MMD_AN && regnum == MDIO_AN_EEE_ADV) { + if (devnum == MDIO_MMD_VEND2) { + rtl821x_write_page(phydev, regnum >> 4); + ret = __phy_write(phydev, 0x10 + ((regnum & 0xf) >> 1), val); + rtl821x_write_page(phydev, 0); + } else if (devnum == MDIO_MMD_AN && regnum == MDIO_AN_EEE_ADV) { rtl821x_write_page(phydev, 0xa5d); ret = __phy_write(phydev, 0x10, val); rtl821x_write_page(phydev, 0); @@ -812,6 +822,15 @@ static int rtl822x_write_mmd(struct phy_device *phydev, int devnum, u16 regnum, return ret; } +static int rtl822x_probe(struct phy_device *phydev) +{ + if (IS_ENABLED(CONFIG_REALTEK_PHY_HWMON) && + phydev->phy_id != RTL_GENERIC_PHYID) + return rtl822x_hwmon_init(phydev); + + return 0; +} + static int rtl822xb_config_init(struct phy_device *phydev) { bool has_2500, has_sgmii; @@ -1511,6 +1530,7 @@ static struct phy_driver realtek_drvs[] = { .match_phy_device = rtl_internal_nbaset_match_phy_device, .name = "Realtek Internal NBASE-T PHY", .flags = PHY_IS_INTERNAL, + .probe = rtl822x_probe, .get_features = rtl822x_get_features, .config_aneg = rtl822x_config_aneg, .read_status = rtl822x_read_status, diff --git a/drivers/net/phy/rockchip.c b/drivers/net/phy/rockchip.c index bb13e75183ee..b338f385e15a 100644 --- a/drivers/net/phy/rockchip.c +++ b/drivers/net/phy/rockchip.c @@ -188,7 +188,7 @@ static struct phy_driver rockchip_phy_driver[] = { module_phy_driver(rockchip_phy_driver); -static struct mdio_device_id __maybe_unused rockchip_phy_tbl[] = { +static const struct mdio_device_id __maybe_unused rockchip_phy_tbl[] = { { INTERNAL_EPHY_ID, 0xfffffff0 }, { } }; diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c index e1853599d9ba..31463b9e5697 100644 --- a/drivers/net/phy/smsc.c +++ b/drivers/net/phy/smsc.c @@ -838,7 +838,7 @@ MODULE_DESCRIPTION("SMSC PHY driver"); MODULE_AUTHOR("Herbert Valerio Riedel"); MODULE_LICENSE("GPL"); -static struct mdio_device_id __maybe_unused smsc_tbl[] = { +static const struct mdio_device_id __maybe_unused smsc_tbl[] = { { 0x0007c0a0, 0xfffffff0 }, { 0x0007c0b0, 0xfffffff0 }, { 0x0007c0c0, 0xfffffff0 }, diff --git a/drivers/net/phy/ste10Xp.c b/drivers/net/phy/ste10Xp.c index 309e4c3496c4..d4835d4c50e0 100644 --- a/drivers/net/phy/ste10Xp.c +++ b/drivers/net/phy/ste10Xp.c @@ -124,7 +124,7 @@ static struct phy_driver ste10xp_pdriver[] = { module_phy_driver(ste10xp_pdriver); -static struct mdio_device_id __maybe_unused ste10Xp_tbl[] = { +static const struct mdio_device_id __maybe_unused ste10Xp_tbl[] = { { STE101P_PHY_ID, 0xfffffff0 }, { STE100P_PHY_ID, 0xffffffff }, { } diff --git a/drivers/net/phy/teranetics.c b/drivers/net/phy/teranetics.c index 8057ea8dbc21..752d4bf7bb99 100644 --- a/drivers/net/phy/teranetics.c +++ b/drivers/net/phy/teranetics.c @@ -87,7 +87,7 @@ static struct phy_driver teranetics_driver[] = { module_phy_driver(teranetics_driver); -static struct mdio_device_id __maybe_unused teranetics_tbl[] = { +static const struct mdio_device_id __maybe_unused teranetics_tbl[] = { { PHY_ID_TN2020, 0xffffffff }, { } }; diff --git a/drivers/net/phy/uPD60620.c b/drivers/net/phy/uPD60620.c index 38834347a427..900cb756c366 100644 --- a/drivers/net/phy/uPD60620.c +++ b/drivers/net/phy/uPD60620.c @@ -90,7 +90,7 @@ static struct phy_driver upd60620_driver[1] = { { module_phy_driver(upd60620_driver); -static struct mdio_device_id __maybe_unused upd60620_tbl[] = { +static const struct mdio_device_id __maybe_unused upd60620_tbl[] = { { UPD60620_PHY_ID, 0xfffffffe }, { } }; diff --git a/drivers/net/phy/vitesse.c b/drivers/net/phy/vitesse.c index 2377179de017..b1b7bbba284e 100644 --- a/drivers/net/phy/vitesse.c +++ b/drivers/net/phy/vitesse.c @@ -674,7 +674,7 @@ static struct phy_driver vsc82xx_driver[] = { module_phy_driver(vsc82xx_driver); -static struct mdio_device_id __maybe_unused vitesse_tbl[] = { +static const struct mdio_device_id __maybe_unused vitesse_tbl[] = { { PHY_ID_VSC8234, 0x000ffff0 }, { PHY_ID_VSC8244, 0x000fffc0 }, { PHY_ID_VSC8572, 0x000ffff0 }, diff --git a/drivers/net/pse-pd/pd692x0.c b/drivers/net/pse-pd/pd692x0.c index 0af7db80b2f8..fc9e23927b3b 100644 --- a/drivers/net/pse-pd/pd692x0.c +++ b/drivers/net/pse-pd/pd692x0.c @@ -431,31 +431,6 @@ static int pd692x0_pi_disable(struct pse_controller_dev *pcdev, int id) return 0; } -static int pd692x0_pi_is_enabled(struct pse_controller_dev *pcdev, int id) -{ - struct pd692x0_priv *priv = to_pd692x0_priv(pcdev); - struct pd692x0_msg msg, buf = {0}; - int ret; - - ret = pd692x0_fw_unavailable(priv); - if (ret) - return ret; - - msg = pd692x0_msg_template_list[PD692X0_MSG_GET_PORT_STATUS]; - msg.sub[2] = id; - ret = pd692x0_sendrecv_msg(priv, &msg, &buf); - if (ret < 0) - return ret; - - if (buf.sub[1]) { - priv->admin_state[id] = ETHTOOL_C33_PSE_ADMIN_STATE_ENABLED; - return 1; - } else { - priv->admin_state[id] = ETHTOOL_C33_PSE_ADMIN_STATE_DISABLED; - return 0; - } -} - struct pd692x0_pse_ext_state_mapping { u32 status_code; enum ethtool_c33_pse_ext_state pse_ext_state; @@ -517,21 +492,38 @@ pd692x0_pse_ext_state_map[] = { { /* sentinel */ } }; -static void -pd692x0_get_ext_state(struct ethtool_c33_pse_ext_state_info *c33_ext_state_info, - u32 status_code) +static int +pd692x0_pi_get_ext_state(struct pse_controller_dev *pcdev, int id, + struct pse_ext_state_info *ext_state_info) { + struct ethtool_c33_pse_ext_state_info *c33_ext_state_info; const struct pd692x0_pse_ext_state_mapping *ext_state_map; + struct pd692x0_priv *priv = to_pd692x0_priv(pcdev); + struct pd692x0_msg msg, buf = {0}; + int ret; + ret = pd692x0_fw_unavailable(priv); + if (ret) + return ret; + + msg = pd692x0_msg_template_list[PD692X0_MSG_GET_PORT_STATUS]; + msg.sub[2] = id; + ret = pd692x0_sendrecv_msg(priv, &msg, &buf); + if (ret < 0) + return ret; + + c33_ext_state_info = &ext_state_info->c33_ext_state_info; ext_state_map = pd692x0_pse_ext_state_map; while (ext_state_map->status_code) { - if (ext_state_map->status_code == status_code) { + if (ext_state_map->status_code == buf.sub[0]) { c33_ext_state_info->c33_pse_ext_state = ext_state_map->pse_ext_state; c33_ext_state_info->__c33_pse_ext_substate = ext_state_map->pse_ext_substate; - return; + return 0; } ext_state_map++; } + + return 0; } struct pd692x0_class_pw { @@ -613,35 +605,36 @@ static int pd692x0_pi_set_pw_from_table(struct device *dev, } static int -pd692x0_pi_get_pw_ranges(struct pse_control_status *st) +pd692x0_pi_get_pw_limit_ranges(struct pse_controller_dev *pcdev, int id, + struct pse_pw_limit_ranges *pw_limit_ranges) { + struct ethtool_c33_pse_pw_limit_range *c33_pw_limit_ranges; const struct pd692x0_class_pw *pw_table; int i; pw_table = pd692x0_class_pw_table; - st->c33_pw_limit_ranges = kcalloc(PD692X0_CLASS_PW_TABLE_SIZE, - sizeof(struct ethtool_c33_pse_pw_limit_range), - GFP_KERNEL); - if (!st->c33_pw_limit_ranges) + c33_pw_limit_ranges = kcalloc(PD692X0_CLASS_PW_TABLE_SIZE, + sizeof(*c33_pw_limit_ranges), + GFP_KERNEL); + if (!c33_pw_limit_ranges) return -ENOMEM; for (i = 0; i < PD692X0_CLASS_PW_TABLE_SIZE; i++, pw_table++) { - st->c33_pw_limit_ranges[i].min = pw_table->class_pw; - st->c33_pw_limit_ranges[i].max = pw_table->class_pw + pw_table->max_added_class_pw; + c33_pw_limit_ranges[i].min = pw_table->class_pw; + c33_pw_limit_ranges[i].max = pw_table->class_pw + + pw_table->max_added_class_pw; } - st->c33_pw_limit_nb_ranges = i; - return 0; + pw_limit_ranges->c33_pw_limit_ranges = c33_pw_limit_ranges; + return i; } -static int pd692x0_ethtool_get_status(struct pse_controller_dev *pcdev, - unsigned long id, - struct netlink_ext_ack *extack, - struct pse_control_status *status) +static int +pd692x0_pi_get_admin_state(struct pse_controller_dev *pcdev, int id, + struct pse_admin_state *admin_state) { struct pd692x0_priv *priv = to_pd692x0_priv(pcdev); struct pd692x0_msg msg, buf = {0}; - u32 class; int ret; ret = pd692x0_fw_unavailable(priv); @@ -654,39 +647,65 @@ static int pd692x0_ethtool_get_status(struct pse_controller_dev *pcdev, if (ret < 0) return ret; - /* Compare Port Status (Communication Protocol Document par. 7.1) */ - if ((buf.sub[0] & 0xf0) == 0x80 || (buf.sub[0] & 0xf0) == 0x90) - status->c33_pw_status = ETHTOOL_C33_PSE_PW_D_STATUS_DELIVERING; - else if (buf.sub[0] == 0x1b || buf.sub[0] == 0x22) - status->c33_pw_status = ETHTOOL_C33_PSE_PW_D_STATUS_SEARCHING; - else if (buf.sub[0] == 0x12) - status->c33_pw_status = ETHTOOL_C33_PSE_PW_D_STATUS_FAULT; - else - status->c33_pw_status = ETHTOOL_C33_PSE_PW_D_STATUS_DISABLED; - if (buf.sub[1]) - status->c33_admin_state = ETHTOOL_C33_PSE_ADMIN_STATE_ENABLED; + admin_state->c33_admin_state = + ETHTOOL_C33_PSE_ADMIN_STATE_ENABLED; else - status->c33_admin_state = ETHTOOL_C33_PSE_ADMIN_STATE_DISABLED; + admin_state->c33_admin_state = + ETHTOOL_C33_PSE_ADMIN_STATE_DISABLED; - priv->admin_state[id] = status->c33_admin_state; + priv->admin_state[id] = admin_state->c33_admin_state; - pd692x0_get_ext_state(&status->c33_ext_state_info, buf.sub[0]); - status->c33_actual_pw = (buf.data[0] << 4 | buf.data[1]) * 100; + return 0; +} - msg = pd692x0_msg_template_list[PD692X0_MSG_GET_PORT_PARAM]; +static int +pd692x0_pi_get_pw_status(struct pse_controller_dev *pcdev, int id, + struct pse_pw_status *pw_status) +{ + struct pd692x0_priv *priv = to_pd692x0_priv(pcdev); + struct pd692x0_msg msg, buf = {0}; + int ret; + + ret = pd692x0_fw_unavailable(priv); + if (ret) + return ret; + + msg = pd692x0_msg_template_list[PD692X0_MSG_GET_PORT_STATUS]; msg.sub[2] = id; - memset(&buf, 0, sizeof(buf)); ret = pd692x0_sendrecv_msg(priv, &msg, &buf); if (ret < 0) return ret; - ret = pd692x0_pi_get_pw_from_table(buf.data[0], buf.data[1]); - if (ret < 0) + /* Compare Port Status (Communication Protocol Document par. 7.1) */ + if ((buf.sub[0] & 0xf0) == 0x80 || (buf.sub[0] & 0xf0) == 0x90) + pw_status->c33_pw_status = + ETHTOOL_C33_PSE_PW_D_STATUS_DELIVERING; + else if (buf.sub[0] == 0x1b || buf.sub[0] == 0x22) + pw_status->c33_pw_status = + ETHTOOL_C33_PSE_PW_D_STATUS_SEARCHING; + else if (buf.sub[0] == 0x12) + pw_status->c33_pw_status = + ETHTOOL_C33_PSE_PW_D_STATUS_FAULT; + else + pw_status->c33_pw_status = + ETHTOOL_C33_PSE_PW_D_STATUS_DISABLED; + + return 0; +} + +static int +pd692x0_pi_get_pw_class(struct pse_controller_dev *pcdev, int id) +{ + struct pd692x0_priv *priv = to_pd692x0_priv(pcdev); + struct pd692x0_msg msg, buf = {0}; + u32 class; + int ret; + + ret = pd692x0_fw_unavailable(priv); + if (ret) return ret; - status->c33_avail_pw_limit = ret; - memset(&buf, 0, sizeof(buf)); msg = pd692x0_msg_template_list[PD692X0_MSG_GET_PORT_CLASS]; msg.sub[2] = id; ret = pd692x0_sendrecv_msg(priv, &msg, &buf); @@ -695,13 +714,29 @@ static int pd692x0_ethtool_get_status(struct pse_controller_dev *pcdev, class = buf.data[3] >> 4; if (class <= 8) - status->c33_pw_class = class; + return class; - ret = pd692x0_pi_get_pw_ranges(status); + return 0; +} + +static int +pd692x0_pi_get_actual_pw(struct pse_controller_dev *pcdev, int id) +{ + struct pd692x0_priv *priv = to_pd692x0_priv(pcdev); + struct pd692x0_msg msg, buf = {0}; + int ret; + + ret = pd692x0_fw_unavailable(priv); + if (ret) + return ret; + + msg = pd692x0_msg_template_list[PD692X0_MSG_GET_PORT_STATUS]; + msg.sub[2] = id; + ret = pd692x0_sendrecv_msg(priv, &msg, &buf); if (ret < 0) return ret; - return 0; + return (buf.data[0] << 4 | buf.data[1]) * 100; } static struct pd692x0_msg_ver pd692x0_get_sw_version(struct pd692x0_priv *priv) @@ -999,13 +1034,12 @@ static int pd692x0_pi_get_voltage(struct pse_controller_dev *pcdev, int id) return (buf.sub[0] << 8 | buf.sub[1]) * 100000; } -static int pd692x0_pi_get_current_limit(struct pse_controller_dev *pcdev, - int id) +static int pd692x0_pi_get_pw_limit(struct pse_controller_dev *pcdev, + int id) { struct pd692x0_priv *priv = to_pd692x0_priv(pcdev); struct pd692x0_msg msg, buf = {0}; - int mW, uV, uA, ret; - s64 tmp_64; + int ret; msg = pd692x0_msg_template_list[PD692X0_MSG_GET_PORT_PARAM]; msg.sub[2] = id; @@ -1013,48 +1047,24 @@ static int pd692x0_pi_get_current_limit(struct pse_controller_dev *pcdev, if (ret < 0) return ret; - ret = pd692x0_pi_get_pw_from_table(buf.data[2], buf.data[3]); - if (ret < 0) - return ret; - mW = ret; - - ret = pd692x0_pi_get_voltage(pcdev, id); - if (ret < 0) - return ret; - uV = ret; - - tmp_64 = mW; - tmp_64 *= 1000000000ull; - /* uA = mW * 1000000000 / uV */ - uA = DIV_ROUND_CLOSEST_ULL(tmp_64, uV); - return uA; + return pd692x0_pi_get_pw_from_table(buf.data[2], buf.data[3]); } -static int pd692x0_pi_set_current_limit(struct pse_controller_dev *pcdev, - int id, int max_uA) +static int pd692x0_pi_set_pw_limit(struct pse_controller_dev *pcdev, + int id, int max_mW) { struct pd692x0_priv *priv = to_pd692x0_priv(pcdev); struct device *dev = &priv->client->dev; struct pd692x0_msg msg, buf = {0}; - int uV, ret, mW; - s64 tmp_64; + int ret; ret = pd692x0_fw_unavailable(priv); if (ret) return ret; - ret = pd692x0_pi_get_voltage(pcdev, id); - if (ret < 0) - return ret; - uV = ret; - msg = pd692x0_msg_template_list[PD692X0_MSG_SET_PORT_PARAM]; msg.sub[2] = id; - tmp_64 = uV; - tmp_64 *= max_uA; - /* mW = uV * uA / 1000000000 */ - mW = DIV_ROUND_CLOSEST_ULL(tmp_64, 1000000000); - ret = pd692x0_pi_set_pw_from_table(dev, &msg, mW); + ret = pd692x0_pi_set_pw_from_table(dev, &msg, max_mW); if (ret) return ret; @@ -1063,13 +1073,17 @@ static int pd692x0_pi_set_current_limit(struct pse_controller_dev *pcdev, static const struct pse_controller_ops pd692x0_ops = { .setup_pi_matrix = pd692x0_setup_pi_matrix, - .ethtool_get_status = pd692x0_ethtool_get_status, + .pi_get_admin_state = pd692x0_pi_get_admin_state, + .pi_get_pw_status = pd692x0_pi_get_pw_status, + .pi_get_ext_state = pd692x0_pi_get_ext_state, + .pi_get_pw_class = pd692x0_pi_get_pw_class, + .pi_get_actual_pw = pd692x0_pi_get_actual_pw, .pi_enable = pd692x0_pi_enable, .pi_disable = pd692x0_pi_disable, - .pi_is_enabled = pd692x0_pi_is_enabled, .pi_get_voltage = pd692x0_pi_get_voltage, - .pi_get_current_limit = pd692x0_pi_get_current_limit, - .pi_set_current_limit = pd692x0_pi_set_current_limit, + .pi_get_pw_limit = pd692x0_pi_get_pw_limit, + .pi_set_pw_limit = pd692x0_pi_set_pw_limit, + .pi_get_pw_limit_ranges = pd692x0_pi_get_pw_limit_ranges, }; #define PD692X0_FW_LINE_MAX_SZ 0xff diff --git a/drivers/net/pse-pd/pse_core.c b/drivers/net/pse-pd/pse_core.c index 2906ce173f66..4f2a54afc4d0 100644 --- a/drivers/net/pse-pd/pse_core.c +++ b/drivers/net/pse-pd/pse_core.c @@ -6,6 +6,7 @@ // #include <linux/device.h> +#include <linux/ethtool.h> #include <linux/of.h> #include <linux/pse-pd/pse.h> #include <linux/regulator/driver.h> @@ -210,16 +211,25 @@ out: static int pse_pi_is_enabled(struct regulator_dev *rdev) { struct pse_controller_dev *pcdev = rdev_get_drvdata(rdev); + struct pse_admin_state admin_state = {0}; const struct pse_controller_ops *ops; int id, ret; ops = pcdev->ops; - if (!ops->pi_is_enabled) + if (!ops->pi_get_admin_state) return -EOPNOTSUPP; id = rdev_get_id(rdev); mutex_lock(&pcdev->lock); - ret = ops->pi_is_enabled(pcdev, id); + ret = ops->pi_get_admin_state(pcdev, id, &admin_state); + if (ret) + goto out; + + if (admin_state.podl_admin_state == ETHTOOL_PODL_PSE_ADMIN_STATE_ENABLED || + admin_state.c33_admin_state == ETHTOOL_C33_PSE_ADMIN_STATE_ENABLED) + ret = 1; + +out: mutex_unlock(&pcdev->lock); return ret; @@ -291,33 +301,25 @@ static int pse_pi_get_voltage(struct regulator_dev *rdev) return ret; } -static int _pse_ethtool_get_status(struct pse_controller_dev *pcdev, - int id, - struct netlink_ext_ack *extack, - struct pse_control_status *status); - static int pse_pi_get_current_limit(struct regulator_dev *rdev) { struct pse_controller_dev *pcdev = rdev_get_drvdata(rdev); const struct pse_controller_ops *ops; - struct netlink_ext_ack extack = {}; - struct pse_control_status st = {}; - int id, uV, ret; + int id, uV, mW, ret; s64 tmp_64; ops = pcdev->ops; id = rdev_get_id(rdev); + if (!ops->pi_get_pw_limit || !ops->pi_get_voltage) + return -EOPNOTSUPP; + mutex_lock(&pcdev->lock); - if (ops->pi_get_current_limit) { - ret = ops->pi_get_current_limit(pcdev, id); + ret = ops->pi_get_pw_limit(pcdev, id); + if (ret < 0) goto out; - } + mW = ret; - /* If pi_get_current_limit() callback not populated get voltage - * from pi_get_voltage() and power limit from ethtool_get_status() - * to calculate current limit. - */ - ret = _pse_pi_get_voltage(rdev); + ret = pse_pi_get_voltage(rdev); if (!ret) { dev_err(pcdev->dev, "Voltage null\n"); ret = -ERANGE; @@ -327,16 +329,7 @@ static int pse_pi_get_current_limit(struct regulator_dev *rdev) goto out; uV = ret; - ret = _pse_ethtool_get_status(pcdev, id, &extack, &st); - if (ret) - goto out; - - if (!st.c33_avail_pw_limit) { - ret = -ENODATA; - goto out; - } - - tmp_64 = st.c33_avail_pw_limit; + tmp_64 = mW; tmp_64 *= 1000000000ull; /* uA = mW * 1000000000 / uV */ ret = DIV_ROUND_CLOSEST_ULL(tmp_64, uV); @@ -351,15 +344,33 @@ static int pse_pi_set_current_limit(struct regulator_dev *rdev, int min_uA, { struct pse_controller_dev *pcdev = rdev_get_drvdata(rdev); const struct pse_controller_ops *ops; - int id, ret; + int id, mW, ret; + s64 tmp_64; ops = pcdev->ops; - if (!ops->pi_set_current_limit) + if (!ops->pi_set_pw_limit || !ops->pi_get_voltage) return -EOPNOTSUPP; + if (max_uA > MAX_PI_CURRENT) + return -ERANGE; + id = rdev_get_id(rdev); mutex_lock(&pcdev->lock); - ret = ops->pi_set_current_limit(pcdev, id, max_uA); + ret = pse_pi_get_voltage(rdev); + if (!ret) { + dev_err(pcdev->dev, "Voltage null\n"); + ret = -ERANGE; + goto out; + } + if (ret < 0) + goto out; + + tmp_64 = ret; + tmp_64 *= max_uA; + /* mW = uA * uV / 1000000000 */ + mW = DIV_ROUND_CLOSEST_ULL(tmp_64, 1000000000); + ret = ops->pi_set_pw_limit(pcdev, id, mW); +out: mutex_unlock(&pcdev->lock); return ret; @@ -403,17 +414,16 @@ devm_pse_pi_regulator_register(struct pse_controller_dev *pcdev, rinit_data->constraints.valid_ops_mask = REGULATOR_CHANGE_STATUS; - if (pcdev->ops->pi_set_current_limit) { + if (pcdev->ops->pi_set_pw_limit) rinit_data->constraints.valid_ops_mask |= REGULATOR_CHANGE_CURRENT; - rinit_data->constraints.max_uA = MAX_PI_CURRENT; - } rinit_data->supply_regulator = "vpwr"; rconfig.dev = pcdev->dev; rconfig.driver_data = pcdev; rconfig.init_data = rinit_data; + rconfig.of_node = pcdev->pi[id].np; rdev = devm_regulator_register(pcdev->dev, rdesc, &rconfig); if (IS_ERR(rdev)) { @@ -444,6 +454,13 @@ int pse_controller_register(struct pse_controller_dev *pcdev) if (!pcdev->nr_lines) pcdev->nr_lines = 1; + if (!pcdev->ops->pi_get_admin_state || + !pcdev->ops->pi_get_pw_status) { + dev_err(pcdev->dev, + "Mandatory status report callbacks are missing"); + return -EINVAL; + } + ret = of_load_pse_pis(pcdev); if (ret) return ret; @@ -736,23 +753,6 @@ out: } EXPORT_SYMBOL_GPL(of_pse_control_get); -static int _pse_ethtool_get_status(struct pse_controller_dev *pcdev, - int id, - struct netlink_ext_ack *extack, - struct pse_control_status *status) -{ - const struct pse_controller_ops *ops; - - ops = pcdev->ops; - if (!ops->ethtool_get_status) { - NL_SET_ERR_MSG(extack, - "PSE driver does not support status report"); - return -EOPNOTSUPP; - } - - return ops->ethtool_get_status(pcdev, id, extack, status); -} - /** * pse_ethtool_get_status - get status of PSE control * @psec: PSE control pointer @@ -763,15 +763,81 @@ static int _pse_ethtool_get_status(struct pse_controller_dev *pcdev, */ int pse_ethtool_get_status(struct pse_control *psec, struct netlink_ext_ack *extack, - struct pse_control_status *status) + struct ethtool_pse_control_status *status) { - int err; + struct pse_admin_state admin_state = {0}; + struct pse_pw_status pw_status = {0}; + const struct pse_controller_ops *ops; + struct pse_controller_dev *pcdev; + int ret; - mutex_lock(&psec->pcdev->lock); - err = _pse_ethtool_get_status(psec->pcdev, psec->id, extack, status); - mutex_unlock(&psec->pcdev->lock); + pcdev = psec->pcdev; + ops = pcdev->ops; + mutex_lock(&pcdev->lock); + ret = ops->pi_get_admin_state(pcdev, psec->id, &admin_state); + if (ret) + goto out; + status->podl_admin_state = admin_state.podl_admin_state; + status->c33_admin_state = admin_state.c33_admin_state; - return err; + ret = ops->pi_get_pw_status(pcdev, psec->id, &pw_status); + if (ret) + goto out; + status->podl_pw_status = pw_status.podl_pw_status; + status->c33_pw_status = pw_status.c33_pw_status; + + if (ops->pi_get_ext_state) { + struct pse_ext_state_info ext_state_info = {0}; + + ret = ops->pi_get_ext_state(pcdev, psec->id, + &ext_state_info); + if (ret) + goto out; + + memcpy(&status->c33_ext_state_info, + &ext_state_info.c33_ext_state_info, + sizeof(status->c33_ext_state_info)); + } + + if (ops->pi_get_pw_class) { + ret = ops->pi_get_pw_class(pcdev, psec->id); + if (ret < 0) + goto out; + + status->c33_pw_class = ret; + } + + if (ops->pi_get_actual_pw) { + ret = ops->pi_get_actual_pw(pcdev, psec->id); + if (ret < 0) + goto out; + + status->c33_actual_pw = ret; + } + + if (ops->pi_get_pw_limit) { + ret = ops->pi_get_pw_limit(pcdev, psec->id); + if (ret < 0) + goto out; + + status->c33_avail_pw_limit = ret; + } + + if (ops->pi_get_pw_limit_ranges) { + struct pse_pw_limit_ranges pw_limit_ranges = {0}; + + ret = ops->pi_get_pw_limit_ranges(pcdev, psec->id, + &pw_limit_ranges); + if (ret < 0) + goto out; + + status->c33_pw_limit_ranges = + pw_limit_ranges.c33_pw_limit_ranges; + status->c33_pw_limit_nb_ranges = ret; + } +out: + mutex_unlock(&psec->pcdev->lock); + return ret; } EXPORT_SYMBOL_GPL(pse_ethtool_get_status); @@ -876,6 +942,9 @@ int pse_ethtool_set_pw_limit(struct pse_control *psec, int uV, uA, ret; s64 tmp_64; + if (pw_limit > MAX_PI_PW) + return -ERANGE; + ret = regulator_get_voltage(psec->ps); if (!ret) { NL_SET_ERR_MSG(extack, diff --git a/drivers/net/pse-pd/pse_regulator.c b/drivers/net/pse-pd/pse_regulator.c index 64ab36974fe0..6ce6773fff31 100644 --- a/drivers/net/pse-pd/pse_regulator.c +++ b/drivers/net/pse-pd/pse_regulator.c @@ -52,17 +52,19 @@ pse_reg_pi_disable(struct pse_controller_dev *pcdev, int id) } static int -pse_reg_pi_is_enabled(struct pse_controller_dev *pcdev, int id) +pse_reg_pi_get_admin_state(struct pse_controller_dev *pcdev, int id, + struct pse_admin_state *admin_state) { struct pse_reg_priv *priv = to_pse_reg(pcdev); - return regulator_is_enabled(priv->ps); + admin_state->podl_admin_state = priv->admin_state; + + return 0; } static int -pse_reg_ethtool_get_status(struct pse_controller_dev *pcdev, unsigned long id, - struct netlink_ext_ack *extack, - struct pse_control_status *status) +pse_reg_pi_get_pw_status(struct pse_controller_dev *pcdev, int id, + struct pse_pw_status *pw_status) { struct pse_reg_priv *priv = to_pse_reg(pcdev); int ret; @@ -72,20 +74,19 @@ pse_reg_ethtool_get_status(struct pse_controller_dev *pcdev, unsigned long id, return ret; if (!ret) - status->podl_pw_status = ETHTOOL_PODL_PSE_PW_D_STATUS_DISABLED; + pw_status->podl_pw_status = + ETHTOOL_PODL_PSE_PW_D_STATUS_DISABLED; else - status->podl_pw_status = + pw_status->podl_pw_status = ETHTOOL_PODL_PSE_PW_D_STATUS_DELIVERING; - status->podl_admin_state = priv->admin_state; - return 0; } static const struct pse_controller_ops pse_reg_ops = { - .ethtool_get_status = pse_reg_ethtool_get_status, + .pi_get_admin_state = pse_reg_pi_get_admin_state, + .pi_get_pw_status = pse_reg_pi_get_pw_status, .pi_enable = pse_reg_pi_enable, - .pi_is_enabled = pse_reg_pi_is_enabled, .pi_disable = pse_reg_pi_disable, }; diff --git a/drivers/net/pse-pd/tps23881.c b/drivers/net/pse-pd/tps23881.c index 8797ca1a8a21..5e9dda2c0eac 100644 --- a/drivers/net/pse-pd/tps23881.c +++ b/drivers/net/pse-pd/tps23881.c @@ -25,20 +25,32 @@ #define TPS23881_REG_GEN_MASK 0x17 #define TPS23881_REG_NBITACC BIT(5) #define TPS23881_REG_PW_EN 0x19 +#define TPS23881_REG_2PAIR_POL1 0x1e #define TPS23881_REG_PORT_MAP 0x26 #define TPS23881_REG_PORT_POWER 0x29 -#define TPS23881_REG_POEPLUS 0x40 +#define TPS23881_REG_4PAIR_POL1 0x2a +#define TPS23881_REG_INPUT_V 0x2e +#define TPS23881_REG_CHAN1_A 0x30 +#define TPS23881_REG_CHAN1_V 0x32 +#define TPS23881_REG_FOLDBACK 0x40 #define TPS23881_REG_TPON BIT(0) #define TPS23881_REG_FWREV 0x41 #define TPS23881_REG_DEVID 0x43 #define TPS23881_REG_DEVID_MASK 0xF0 #define TPS23881_DEVICE_ID 0x02 +#define TPS23881_REG_CHAN1_CLASS 0x4c #define TPS23881_REG_SRAM_CTRL 0x60 #define TPS23881_REG_SRAM_DATA 0x61 +#define TPS23881_UV_STEP 3662 +#define TPS23881_NA_STEP 70190 +#define TPS23881_MW_STEP 500 +#define TPS23881_MIN_PI_PW_LIMIT_MW 2000 + struct tps23881_port_desc { u8 chan[2]; bool is_4p; + int pw_pol; }; struct tps23881_priv { @@ -53,36 +65,123 @@ static struct tps23881_priv *to_tps23881_priv(struct pse_controller_dev *pcdev) return container_of(pcdev, struct tps23881_priv, pcdev); } +/* + * Helper to extract a value from a u16 register value, which is made of two + * u8 registers. The function calculates the bit offset based on the channel + * and extracts the relevant bits using a provided field mask. + * + * @param reg_val: The u16 register value (composed of two u8 registers). + * @param chan: The channel number (0-7). + * @param field_offset: The base bit offset to apply (e.g., 0 or 4). + * @param field_mask: The mask to apply to extract the required bits. + * @return: The extracted value for the specific channel. + */ +static u16 tps23881_calc_val(u16 reg_val, u8 chan, u8 field_offset, + u16 field_mask) +{ + if (chan >= 4) + reg_val >>= 8; + + return (reg_val >> field_offset) & field_mask; +} + +/* + * Helper to combine individual channel values into a u16 register value. + * The function sets the value for a specific channel in the appropriate + * position. + * + * @param reg_val: The current u16 register value. + * @param chan: The channel number (0-7). + * @param field_offset: The base bit offset to apply (e.g., 0 or 4). + * @param field_mask: The mask to apply for the field (e.g., 0x0F). + * @param field_val: The value to set for the specific channel (masked by + * field_mask). + * @return: The updated u16 register value with the channel value set. + */ +static u16 tps23881_set_val(u16 reg_val, u8 chan, u8 field_offset, + u16 field_mask, u16 field_val) +{ + field_val &= field_mask; + + if (chan < 4) { + reg_val &= ~(field_mask << field_offset); + reg_val |= (field_val << field_offset); + } else { + reg_val &= ~(field_mask << (field_offset + 8)); + reg_val |= (field_val << (field_offset + 8)); + } + + return reg_val; +} + +static int +tps23881_pi_set_pw_pol_limit(struct tps23881_priv *priv, int id, u8 pw_pol, + bool is_4p) +{ + struct i2c_client *client = priv->client; + int ret, reg; + u16 val; + u8 chan; + + chan = priv->port[id].chan[0]; + if (!is_4p) { + reg = TPS23881_REG_2PAIR_POL1 + (chan % 4); + } else { + /* One chan is enough to configure the 4p PI power limit */ + if ((chan % 4) < 2) + reg = TPS23881_REG_4PAIR_POL1; + else + reg = TPS23881_REG_4PAIR_POL1 + 1; + } + + ret = i2c_smbus_read_word_data(client, reg); + if (ret < 0) + return ret; + + val = tps23881_set_val(ret, chan, 0, 0xff, pw_pol); + return i2c_smbus_write_word_data(client, reg, val); +} + +static int tps23881_pi_enable_manual_pol(struct tps23881_priv *priv, int id) +{ + struct i2c_client *client = priv->client; + int ret; + u8 chan; + u16 val; + + ret = i2c_smbus_read_byte_data(client, TPS23881_REG_FOLDBACK); + if (ret < 0) + return ret; + + /* No need to test if the chan is PoE4 as setting either bit for a + * 4P configured port disables the automatic configuration on both + * channels. + */ + chan = priv->port[id].chan[0]; + val = tps23881_set_val(ret, chan, 0, BIT(chan % 4), BIT(chan % 4)); + return i2c_smbus_write_byte_data(client, TPS23881_REG_FOLDBACK, val); +} + static int tps23881_pi_enable(struct pse_controller_dev *pcdev, int id) { struct tps23881_priv *priv = to_tps23881_priv(pcdev); struct i2c_client *client = priv->client; u8 chan; u16 val; - int ret; if (id >= TPS23881_MAX_CHANS) return -ERANGE; chan = priv->port[id].chan[0]; - if (chan < 4) - val = BIT(chan); - else - val = BIT(chan + 4); + val = tps23881_set_val(0, chan, 0, BIT(chan % 4), BIT(chan % 4)); if (priv->port[id].is_4p) { chan = priv->port[id].chan[1]; - if (chan < 4) - val |= BIT(chan); - else - val |= BIT(chan + 4); + val = tps23881_set_val(val, chan, 0, BIT(chan % 4), + BIT(chan % 4)); } - ret = i2c_smbus_write_word_data(client, TPS23881_REG_PW_EN, val); - if (ret) - return ret; - - return 0; + return i2c_smbus_write_word_data(client, TPS23881_REG_PW_EN, val); } static int tps23881_pi_disable(struct pse_controller_dev *pcdev, int id) @@ -97,32 +196,67 @@ static int tps23881_pi_disable(struct pse_controller_dev *pcdev, int id) return -ERANGE; chan = priv->port[id].chan[0]; - if (chan < 4) - val = BIT(chan + 4); - else - val = BIT(chan + 8); + val = tps23881_set_val(0, chan, 4, BIT(chan % 4), BIT(chan % 4)); if (priv->port[id].is_4p) { chan = priv->port[id].chan[1]; - if (chan < 4) - val |= BIT(chan + 4); - else - val |= BIT(chan + 8); + val = tps23881_set_val(val, chan, 4, BIT(chan % 4), + BIT(chan % 4)); } ret = i2c_smbus_write_word_data(client, TPS23881_REG_PW_EN, val); if (ret) return ret; - return 0; + /* PWOFF command resets lots of register which need to be + * configured again. According to the datasheet "It may take upwards + * of 5ms after PWOFFn command for all register values to be updated" + */ + mdelay(5); + + /* Enable detection and classification */ + ret = i2c_smbus_read_word_data(client, TPS23881_REG_DET_CLA_EN); + if (ret < 0) + return ret; + + chan = priv->port[id].chan[0]; + val = tps23881_set_val(ret, chan, 0, BIT(chan % 4), BIT(chan % 4)); + val = tps23881_set_val(val, chan, 4, BIT(chan % 4), BIT(chan % 4)); + + if (priv->port[id].is_4p) { + chan = priv->port[id].chan[1]; + val = tps23881_set_val(ret, chan, 0, BIT(chan % 4), + BIT(chan % 4)); + val = tps23881_set_val(val, chan, 4, BIT(chan % 4), + BIT(chan % 4)); + } + + ret = i2c_smbus_write_word_data(client, TPS23881_REG_DET_CLA_EN, val); + if (ret) + return ret; + + /* No power policy */ + if (priv->port[id].pw_pol < 0) + return 0; + + ret = tps23881_pi_enable_manual_pol(priv, id); + if (ret < 0) + return ret; + + /* Set power policy */ + return tps23881_pi_set_pw_pol_limit(priv, id, priv->port[id].pw_pol, + priv->port[id].is_4p); } -static int tps23881_pi_is_enabled(struct pse_controller_dev *pcdev, int id) +static int +tps23881_pi_get_admin_state(struct pse_controller_dev *pcdev, int id, + struct pse_admin_state *admin_state) { struct tps23881_priv *priv = to_tps23881_priv(pcdev); struct i2c_client *client = priv->client; bool enabled; u8 chan; + u16 val; int ret; ret = i2c_smbus_read_word_data(client, TPS23881_REG_PW_STATUS); @@ -130,32 +264,35 @@ static int tps23881_pi_is_enabled(struct pse_controller_dev *pcdev, int id) return ret; chan = priv->port[id].chan[0]; - if (chan < 4) - enabled = ret & BIT(chan); - else - enabled = ret & BIT(chan + 4); + val = tps23881_calc_val(ret, chan, 0, BIT(chan % 4)); + enabled = !!(val); if (priv->port[id].is_4p) { chan = priv->port[id].chan[1]; - if (chan < 4) - enabled &= !!(ret & BIT(chan)); - else - enabled &= !!(ret & BIT(chan + 4)); + val = tps23881_calc_val(ret, chan, 0, BIT(chan % 4)); + enabled &= !!(val); } /* Return enabled status only if both channel are on this state */ - return enabled; + if (enabled) + admin_state->c33_admin_state = + ETHTOOL_C33_PSE_ADMIN_STATE_ENABLED; + else + admin_state->c33_admin_state = + ETHTOOL_C33_PSE_ADMIN_STATE_DISABLED; + + return 0; } -static int tps23881_ethtool_get_status(struct pse_controller_dev *pcdev, - unsigned long id, - struct netlink_ext_ack *extack, - struct pse_control_status *status) +static int +tps23881_pi_get_pw_status(struct pse_controller_dev *pcdev, int id, + struct pse_pw_status *pw_status) { struct tps23881_priv *priv = to_tps23881_priv(pcdev); struct i2c_client *client = priv->client; - bool enabled, delivering; + bool delivering; u8 chan; + u16 val; int ret; ret = i2c_smbus_read_word_data(client, TPS23881_REG_PW_STATUS); @@ -163,40 +300,197 @@ static int tps23881_ethtool_get_status(struct pse_controller_dev *pcdev, return ret; chan = priv->port[id].chan[0]; - if (chan < 4) { - enabled = ret & BIT(chan); - delivering = ret & BIT(chan + 4); - } else { - enabled = ret & BIT(chan + 4); - delivering = ret & BIT(chan + 8); - } + val = tps23881_calc_val(ret, chan, 4, BIT(chan % 4)); + delivering = !!(val); if (priv->port[id].is_4p) { chan = priv->port[id].chan[1]; - if (chan < 4) { - enabled &= !!(ret & BIT(chan)); - delivering &= !!(ret & BIT(chan + 4)); - } else { - enabled &= !!(ret & BIT(chan + 4)); - delivering &= !!(ret & BIT(chan + 8)); - } + val = tps23881_calc_val(ret, chan, 4, BIT(chan % 4)); + delivering &= !!(val); } /* Return delivering status only if both channel are on this state */ if (delivering) - status->c33_pw_status = ETHTOOL_C33_PSE_PW_D_STATUS_DELIVERING; + pw_status->c33_pw_status = + ETHTOOL_C33_PSE_PW_D_STATUS_DELIVERING; else - status->c33_pw_status = ETHTOOL_C33_PSE_PW_D_STATUS_DISABLED; - - /* Return enabled status only if both channel are on this state */ - if (enabled) - status->c33_admin_state = ETHTOOL_C33_PSE_ADMIN_STATE_ENABLED; - else - status->c33_admin_state = ETHTOOL_C33_PSE_ADMIN_STATE_DISABLED; + pw_status->c33_pw_status = + ETHTOOL_C33_PSE_PW_D_STATUS_DISABLED; return 0; } +static int tps23881_pi_get_voltage(struct pse_controller_dev *pcdev, int id) +{ + struct tps23881_priv *priv = to_tps23881_priv(pcdev); + struct i2c_client *client = priv->client; + int ret; + u64 uV; + + ret = i2c_smbus_read_word_data(client, TPS23881_REG_INPUT_V); + if (ret < 0) + return ret; + + uV = ret & 0x3fff; + uV *= TPS23881_UV_STEP; + + return (int)uV; +} + +static int +tps23881_pi_get_chan_current(struct tps23881_priv *priv, u8 chan) +{ + struct i2c_client *client = priv->client; + int reg, ret; + u64 tmp_64; + + /* Registers 0x30 to 0x3d */ + reg = TPS23881_REG_CHAN1_A + (chan % 4) * 4 + (chan >= 4); + ret = i2c_smbus_read_word_data(client, reg); + if (ret < 0) + return ret; + + tmp_64 = ret & 0x3fff; + tmp_64 *= TPS23881_NA_STEP; + /* uA = nA / 1000 */ + tmp_64 = DIV_ROUND_CLOSEST_ULL(tmp_64, 1000); + return (int)tmp_64; +} + +static int tps23881_pi_get_pw_class(struct pse_controller_dev *pcdev, + int id) +{ + struct tps23881_priv *priv = to_tps23881_priv(pcdev); + struct i2c_client *client = priv->client; + int ret, reg; + u8 chan; + + chan = priv->port[id].chan[0]; + reg = TPS23881_REG_CHAN1_CLASS + (chan % 4); + ret = i2c_smbus_read_word_data(client, reg); + if (ret < 0) + return ret; + + return tps23881_calc_val(ret, chan, 4, 0x0f); +} + +static int +tps23881_pi_get_actual_pw(struct pse_controller_dev *pcdev, int id) +{ + struct tps23881_priv *priv = to_tps23881_priv(pcdev); + int ret, uV, uA; + u64 tmp_64; + u8 chan; + + ret = tps23881_pi_get_voltage(&priv->pcdev, id); + if (ret < 0) + return ret; + uV = ret; + + chan = priv->port[id].chan[0]; + ret = tps23881_pi_get_chan_current(priv, chan); + if (ret < 0) + return ret; + uA = ret; + + if (priv->port[id].is_4p) { + chan = priv->port[id].chan[1]; + ret = tps23881_pi_get_chan_current(priv, chan); + if (ret < 0) + return ret; + uA += ret; + } + + tmp_64 = uV; + tmp_64 *= uA; + /* mW = uV * uA / 1000000000 */ + return DIV_ROUND_CLOSEST_ULL(tmp_64, 1000000000); +} + +static int +tps23881_pi_get_pw_limit_chan(struct tps23881_priv *priv, u8 chan) +{ + struct i2c_client *client = priv->client; + int ret, reg; + u16 val; + + reg = TPS23881_REG_2PAIR_POL1 + (chan % 4); + ret = i2c_smbus_read_word_data(client, reg); + if (ret < 0) + return ret; + + val = tps23881_calc_val(ret, chan, 0, 0xff); + return val * TPS23881_MW_STEP; +} + +static int tps23881_pi_get_pw_limit(struct pse_controller_dev *pcdev, int id) +{ + struct tps23881_priv *priv = to_tps23881_priv(pcdev); + int ret, mW; + u8 chan; + + chan = priv->port[id].chan[0]; + ret = tps23881_pi_get_pw_limit_chan(priv, chan); + if (ret < 0) + return ret; + + mW = ret; + if (priv->port[id].is_4p) { + chan = priv->port[id].chan[1]; + ret = tps23881_pi_get_pw_limit_chan(priv, chan); + if (ret < 0) + return ret; + mW += ret; + } + + return mW; +} + +static int tps23881_pi_set_pw_limit(struct pse_controller_dev *pcdev, + int id, int max_mW) +{ + struct tps23881_priv *priv = to_tps23881_priv(pcdev); + u8 pw_pol; + int ret; + + if (max_mW < TPS23881_MIN_PI_PW_LIMIT_MW || MAX_PI_PW < max_mW) { + dev_err(&priv->client->dev, + "power limit %d out of ranges [%d,%d]", + max_mW, TPS23881_MIN_PI_PW_LIMIT_MW, MAX_PI_PW); + return -ERANGE; + } + + ret = tps23881_pi_enable_manual_pol(priv, id); + if (ret < 0) + return ret; + + pw_pol = DIV_ROUND_CLOSEST_ULL(max_mW, TPS23881_MW_STEP); + + /* Save power policy to reconfigure it after a disabled call */ + priv->port[id].pw_pol = pw_pol; + return tps23881_pi_set_pw_pol_limit(priv, id, pw_pol, + priv->port[id].is_4p); +} + +static int +tps23881_pi_get_pw_limit_ranges(struct pse_controller_dev *pcdev, int id, + struct pse_pw_limit_ranges *pw_limit_ranges) +{ + struct ethtool_c33_pse_pw_limit_range *c33_pw_limit_ranges; + + c33_pw_limit_ranges = kzalloc(sizeof(*c33_pw_limit_ranges), + GFP_KERNEL); + if (!c33_pw_limit_ranges) + return -ENOMEM; + + c33_pw_limit_ranges->min = TPS23881_MIN_PI_PW_LIMIT_MW; + c33_pw_limit_ranges->max = MAX_PI_PW; + pw_limit_ranges->c33_pw_limit_ranges = c33_pw_limit_ranges; + + /* Return the number of ranges */ + return 1; +} + /* Parse managers subnode into a array of device node */ static int tps23881_get_of_channels(struct tps23881_priv *priv, @@ -480,7 +774,7 @@ tps23881_write_port_matrix(struct tps23881_priv *priv, struct i2c_client *client = priv->client; u8 pi_id, lgcl_chan, hw_chan; u16 val = 0; - int i, ret; + int i; for (i = 0; i < port_cnt; i++) { pi_id = port_matrix[i].pi_id; @@ -491,6 +785,9 @@ tps23881_write_port_matrix(struct tps23881_priv *priv, if (port_matrix[i].exist) priv->port[pi_id].chan[0] = lgcl_chan; + /* Initialize power policy internal value */ + priv->port[pi_id].pw_pol = -1; + /* Set hardware port matrix for all ports */ val |= hw_chan << (lgcl_chan * 2); @@ -511,11 +808,7 @@ tps23881_write_port_matrix(struct tps23881_priv *priv, } /* Write hardware ports matrix */ - ret = i2c_smbus_write_word_data(client, TPS23881_REG_PORT_MAP, val); - if (ret) - return ret; - - return 0; + return i2c_smbus_write_word_data(client, TPS23881_REG_PORT_MAP, val); } static int @@ -564,11 +857,7 @@ tps23881_set_ports_conf(struct tps23881_priv *priv, val |= BIT(port_matrix[i].lgcl_chan[1]) | BIT(port_matrix[i].lgcl_chan[1] + 4); } - ret = i2c_smbus_write_word_data(client, TPS23881_REG_DET_CLA_EN, val); - if (ret) - return ret; - - return 0; + return i2c_smbus_write_word_data(client, TPS23881_REG_DET_CLA_EN, val); } static int @@ -594,11 +883,7 @@ tps23881_set_ports_matrix(struct tps23881_priv *priv, if (ret) return ret; - ret = tps23881_set_ports_conf(priv, port_matrix); - if (ret) - return ret; - - return 0; + return tps23881_set_ports_conf(priv, port_matrix); } static int tps23881_setup_pi_matrix(struct pse_controller_dev *pcdev) @@ -626,8 +911,14 @@ static const struct pse_controller_ops tps23881_ops = { .setup_pi_matrix = tps23881_setup_pi_matrix, .pi_enable = tps23881_pi_enable, .pi_disable = tps23881_pi_disable, - .pi_is_enabled = tps23881_pi_is_enabled, - .ethtool_get_status = tps23881_ethtool_get_status, + .pi_get_admin_state = tps23881_pi_get_admin_state, + .pi_get_pw_status = tps23881_pi_get_pw_status, + .pi_get_pw_class = tps23881_pi_get_pw_class, + .pi_get_actual_pw = tps23881_pi_get_actual_pw, + .pi_get_voltage = tps23881_pi_get_voltage, + .pi_get_pw_limit = tps23881_pi_get_pw_limit, + .pi_set_pw_limit = tps23881_pi_set_pw_limit, + .pi_get_pw_limit_ranges = tps23881_pi_get_pw_limit_ranges, }; static const char fw_parity_name[] = "ti/tps23881/tps23881-parity-14.bin"; diff --git a/drivers/net/wwan/iosm/iosm_ipc_pcie.c b/drivers/net/wwan/iosm/iosm_ipc_pcie.c index 04517bd3325a..a066977af0be 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_pcie.c +++ b/drivers/net/wwan/iosm/iosm_ipc_pcie.c @@ -6,6 +6,7 @@ #include <linux/acpi.h> #include <linux/bitfield.h> #include <linux/module.h> +#include <linux/suspend.h> #include <net/rtnetlink.h> #include "iosm_ipc_imem.h" @@ -18,6 +19,7 @@ MODULE_LICENSE("GPL v2"); /* WWAN GUID */ static guid_t wwan_acpi_guid = GUID_INIT(0xbad01b75, 0x22a8, 0x4f48, 0x87, 0x92, 0xbd, 0xde, 0x94, 0x67, 0x74, 0x7d); +static bool pci_registered; static void ipc_pcie_resources_release(struct iosm_pcie *ipc_pcie) { @@ -448,7 +450,6 @@ static struct pci_driver iosm_ipc_driver = { }, .id_table = iosm_ipc_ids, }; -module_pci_driver(iosm_ipc_driver); int ipc_pcie_addr_map(struct iosm_pcie *ipc_pcie, unsigned char *data, size_t size, dma_addr_t *mapping, int direction) @@ -530,3 +531,56 @@ void ipc_pcie_kfree_skb(struct iosm_pcie *ipc_pcie, struct sk_buff *skb) IPC_CB(skb)->mapping = 0; dev_kfree_skb(skb); } + +static int pm_notify(struct notifier_block *nb, unsigned long mode, void *_unused) +{ + if (mode == PM_HIBERNATION_PREPARE || mode == PM_RESTORE_PREPARE) { + if (pci_registered) { + pci_unregister_driver(&iosm_ipc_driver); + pci_registered = false; + } + } else if (mode == PM_POST_HIBERNATION || mode == PM_POST_RESTORE) { + if (!pci_registered) { + int ret; + + ret = pci_register_driver(&iosm_ipc_driver); + if (ret) { + pr_err(KBUILD_MODNAME ": unable to re-register PCI driver: %d\n", + ret); + } else { + pci_registered = true; + } + } + } + + return 0; +} + +static struct notifier_block pm_notifier = { + .notifier_call = pm_notify, +}; + +static int __init iosm_ipc_driver_init(void) +{ + int ret; + + ret = pci_register_driver(&iosm_ipc_driver); + if (ret) + return ret; + + pci_registered = true; + + register_pm_notifier(&pm_notifier); + + return 0; +} +module_init(iosm_ipc_driver_init); + +static void __exit iosm_ipc_driver_exit(void) +{ + unregister_pm_notifier(&pm_notifier); + + if (pci_registered) + pci_unregister_driver(&iosm_ipc_driver); +} +module_exit(iosm_ipc_driver_exit); diff --git a/drivers/nfc/nfcmrvl/uart.c b/drivers/nfc/nfcmrvl/uart.c index 956ae92f7573..2037cd6d4f4f 100644 --- a/drivers/nfc/nfcmrvl/uart.c +++ b/drivers/nfc/nfcmrvl/uart.c @@ -5,11 +5,16 @@ * Copyright (C) 2015, Marvell International Ltd. */ -#include <linux/module.h> #include <linux/delay.h> -#include <linux/of_gpio.h> +#include <linux/device.h> +#include <linux/err.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/printk.h> + #include <net/nfc/nci.h> #include <net/nfc/nci_core.h> + #include "nfcmrvl.h" static unsigned int hci_muxed; diff --git a/drivers/nfc/st21nfca/i2c.c b/drivers/nfc/st21nfca/i2c.c index 02c3d11a19c4..6d7861383806 100644 --- a/drivers/nfc/st21nfca/i2c.c +++ b/drivers/nfc/st21nfca/i2c.c @@ -11,7 +11,6 @@ #include <linux/i2c.h> #include <linux/gpio/consumer.h> #include <linux/of_irq.h> -#include <linux/of_gpio.h> #include <linux/acpi.h> #include <linux/interrupt.h> #include <linux/delay.h> diff --git a/drivers/pci/pcie/bwctrl.c b/drivers/pci/pcie/bwctrl.c index b59cacc740fa..0a5e7efbce2c 100644 --- a/drivers/pci/pcie/bwctrl.c +++ b/drivers/pci/pcie/bwctrl.c @@ -303,14 +303,17 @@ static int pcie_bwnotif_probe(struct pcie_device *srv) if (ret) return ret; - ret = devm_request_irq(&srv->device, srv->irq, pcie_bwnotif_irq, - IRQF_SHARED, "PCIe bwctrl", srv); - if (ret) - return ret; - scoped_guard(rwsem_write, &pcie_bwctrl_setspeed_rwsem) { scoped_guard(rwsem_write, &pcie_bwctrl_lbms_rwsem) { - port->link_bwctrl = no_free_ptr(data); + port->link_bwctrl = data; + + ret = request_irq(srv->irq, pcie_bwnotif_irq, + IRQF_SHARED, "PCIe bwctrl", srv); + if (ret) { + port->link_bwctrl = NULL; + return ret; + } + pcie_bwnotif_enable(srv); } } @@ -331,11 +334,15 @@ static void pcie_bwnotif_remove(struct pcie_device *srv) pcie_cooling_device_unregister(data->cdev); - pcie_bwnotif_disable(srv->port); + scoped_guard(rwsem_write, &pcie_bwctrl_setspeed_rwsem) { + scoped_guard(rwsem_write, &pcie_bwctrl_lbms_rwsem) { + pcie_bwnotif_disable(srv->port); + + free_irq(srv->irq, srv); - scoped_guard(rwsem_write, &pcie_bwctrl_setspeed_rwsem) - scoped_guard(rwsem_write, &pcie_bwctrl_lbms_rwsem) srv->port->link_bwctrl = NULL; + } + } } static int pcie_bwnotif_suspend(struct pcie_device *srv) diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c index 1aa303f76cc7..194c153e5d71 100644 --- a/drivers/perf/riscv_pmu_sbi.c +++ b/drivers/perf/riscv_pmu_sbi.c @@ -507,8 +507,7 @@ static int pmu_sbi_event_map(struct perf_event *event, u64 *econfig) { u32 type = event->attr.type; u64 config = event->attr.config; - u64 raw_config_val; - int ret; + int ret = -ENOENT; /* * Ensure we are finished checking standard hardware events for @@ -528,21 +527,23 @@ static int pmu_sbi_event_map(struct perf_event *event, u64 *econfig) case PERF_TYPE_RAW: /* * As per SBI specification, the upper 16 bits must be unused - * for a raw event. + * for a hardware raw event. * Bits 63:62 are used to distinguish between raw events * 00 - Hardware raw event * 10 - SBI firmware events * 11 - Risc-V platform specific firmware event */ - raw_config_val = config & RISCV_PMU_RAW_EVENT_MASK; + switch (config >> 62) { case 0: - ret = RISCV_PMU_RAW_EVENT_IDX; - *econfig = raw_config_val; + /* Return error any bits [48-63] is set as it is not allowed by the spec */ + if (!(config & ~RISCV_PMU_RAW_EVENT_MASK)) { + *econfig = config & RISCV_PMU_RAW_EVENT_MASK; + ret = RISCV_PMU_RAW_EVENT_IDX; + } break; case 2: - ret = (raw_config_val & 0xFFFF) | - (SBI_PMU_EVENT_TYPE_FW << 16); + ret = (config & 0xFFFF) | (SBI_PMU_EVENT_TYPE_FW << 16); break; case 3: /* @@ -551,12 +552,13 @@ static int pmu_sbi_event_map(struct perf_event *event, u64 *econfig) * Event data - raw event encoding */ ret = SBI_PMU_EVENT_TYPE_FW << 16 | RISCV_PLAT_FW_EVENT; - *econfig = raw_config_val; + *econfig = config & RISCV_PMU_PLAT_FW_EVENT_MASK; + break; + default: break; } break; default: - ret = -ENOENT; break; } diff --git a/drivers/platform/x86/amd/pmc/pmc.c b/drivers/platform/x86/amd/pmc/pmc.c index 26b878ee5191..a254debb9256 100644 --- a/drivers/platform/x86/amd/pmc/pmc.c +++ b/drivers/platform/x86/amd/pmc/pmc.c @@ -947,6 +947,10 @@ static int amd_pmc_suspend_handler(struct device *dev) { struct amd_pmc_dev *pdev = dev_get_drvdata(dev); + /* + * Must be called only from the same set of dev_pm_ops handlers + * as i8042_pm_suspend() is called: currently just from .suspend. + */ if (pdev->disable_8042_wakeup && !disable_workarounds) { int rc = amd_pmc_wa_irq1(pdev); @@ -959,7 +963,9 @@ static int amd_pmc_suspend_handler(struct device *dev) return 0; } -static DEFINE_SIMPLE_DEV_PM_OPS(amd_pmc_pm, amd_pmc_suspend_handler, NULL); +static const struct dev_pm_ops amd_pmc_pm = { + .suspend = amd_pmc_suspend_handler, +}; static const struct pci_device_id pmc_pci_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, AMD_CPU_ID_PS) }, diff --git a/drivers/platform/x86/intel/pmc/core_ssram.c b/drivers/platform/x86/intel/pmc/core_ssram.c index 50ebfd586d3f..739569803017 100644 --- a/drivers/platform/x86/intel/pmc/core_ssram.c +++ b/drivers/platform/x86/intel/pmc/core_ssram.c @@ -269,8 +269,12 @@ pmc_core_ssram_get_pmc(struct pmc_dev *pmcdev, int pmc_idx, u32 offset) /* * The secondary PMC BARS (which are behind hidden PCI devices) * are read from fixed offsets in MMIO of the primary PMC BAR. + * If a device is not present, the value will be 0. */ ssram_base = get_base(tmp_ssram, offset); + if (!ssram_base) + return 0; + ssram = ioremap(ssram_base, SSRAM_HDR_SIZE); if (!ssram) return -ENOMEM; diff --git a/drivers/platform/x86/intel/speed_select_if/isst_if_common.c b/drivers/platform/x86/intel/speed_select_if/isst_if_common.c index 1e46e30dae96..dbcd3087aaa4 100644 --- a/drivers/platform/x86/intel/speed_select_if/isst_if_common.c +++ b/drivers/platform/x86/intel/speed_select_if/isst_if_common.c @@ -804,6 +804,7 @@ EXPORT_SYMBOL_GPL(isst_if_cdev_unregister); static const struct x86_cpu_id isst_cpu_ids[] = { X86_MATCH_VFM(INTEL_ATOM_CRESTMONT, SST_HPM_SUPPORTED), X86_MATCH_VFM(INTEL_ATOM_CRESTMONT_X, SST_HPM_SUPPORTED), + X86_MATCH_VFM(INTEL_ATOM_DARKMONT_X, SST_HPM_SUPPORTED), X86_MATCH_VFM(INTEL_EMERALDRAPIDS_X, 0), X86_MATCH_VFM(INTEL_GRANITERAPIDS_D, SST_HPM_SUPPORTED), X86_MATCH_VFM(INTEL_GRANITERAPIDS_X, SST_HPM_SUPPORTED), diff --git a/drivers/platform/x86/intel/tpmi_power_domains.c b/drivers/platform/x86/intel/tpmi_power_domains.c index 603e7ded06a9..2f01cd22a6ee 100644 --- a/drivers/platform/x86/intel/tpmi_power_domains.c +++ b/drivers/platform/x86/intel/tpmi_power_domains.c @@ -81,6 +81,7 @@ static const struct x86_cpu_id tpmi_cpu_ids[] = { X86_MATCH_VFM(INTEL_GRANITERAPIDS_X, NULL), X86_MATCH_VFM(INTEL_ATOM_CRESTMONT_X, NULL), X86_MATCH_VFM(INTEL_ATOM_CRESTMONT, NULL), + X86_MATCH_VFM(INTEL_ATOM_DARKMONT_X, NULL), X86_MATCH_VFM(INTEL_GRANITERAPIDS_D, NULL), X86_MATCH_VFM(INTEL_PANTHERCOVE_X, NULL), {} diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index adee6f60c966..0cc6a0f77b09 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -210,6 +210,9 @@ static int scsi_check_passthrough(struct scsi_cmnd *scmd, struct scsi_sense_hdr sshdr; enum sam_status status; + if (!scmd->result) + return 0; + if (!failures) return 0; diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c index fde7de3b1e55..9b47f91c5b97 100644 --- a/drivers/scsi/scsi_transport_iscsi.c +++ b/drivers/scsi/scsi_transport_iscsi.c @@ -4104,7 +4104,7 @@ iscsi_if_rx(struct sk_buff *skb) } do { /* - * special case for GET_STATS: + * special case for GET_STATS, GET_CHAP and GET_HOST_STATS: * on success - sending reply and stats from * inside of if_recv_msg(), * on error - fall through. @@ -4113,6 +4113,8 @@ iscsi_if_rx(struct sk_buff *skb) break; if (ev->type == ISCSI_UEVENT_GET_CHAP && !err) break; + if (ev->type == ISCSI_UEVENT_GET_HOST_STATS && !err) + break; err = iscsi_if_send_reply(portid, nlh->nlmsg_type, ev, sizeof(*ev)); if (err == -EAGAIN && --retries < 0) { diff --git a/drivers/staging/gpib/Kconfig b/drivers/staging/gpib/Kconfig index 259f3ff33646..81510db3072e 100644 --- a/drivers/staging/gpib/Kconfig +++ b/drivers/staging/gpib/Kconfig @@ -65,6 +65,8 @@ config GPIB_NI_PCI_ISA depends on ISA_BUS || PCI || PCMCIA depends on HAS_IOPORT depends on !X86_PAE + depends on PCMCIA || !PCMCIA + depends on HAS_IOPORT_MAP select GPIB_COMMON select GPIB_NEC7210 help @@ -89,6 +91,7 @@ config GPIB_CB7210 depends on HAS_IOPORT depends on ISA_BUS || PCI || PCMCIA depends on !X86_PAE + depends on PCMCIA || !PCMCIA select GPIB_COMMON select GPIB_NEC7210 help @@ -177,6 +180,7 @@ config GPIB_HP82341 config GPIB_INES tristate "INES" depends on PCI || ISA_BUS || PCMCIA + depends on PCMCIA || !PCMCIA depends on HAS_IOPORT depends on !X86_PAE select GPIB_COMMON @@ -199,8 +203,8 @@ config GPIB_INES called cb7210. config GPIB_PCMCIA - bool "PCMCIA/Cardbus support for NI MC and Ines boards" - depends on PCCARD && (GPIB_NI_PCI_ISA || GPIB_CB7210 || GPIB_INES) + def_bool y + depends on PCMCIA && (GPIB_NI_PCI_ISA || GPIB_CB7210 || GPIB_INES) help Enable PCMCIA/CArdbus support for National Instruments, measurement computing boards and Ines boards. diff --git a/drivers/staging/gpib/agilent_82350b/Makefile b/drivers/staging/gpib/agilent_82350b/Makefile index d9236c92e04b..f24e1e713a63 100644 --- a/drivers/staging/gpib/agilent_82350b/Makefile +++ b/drivers/staging/gpib/agilent_82350b/Makefile @@ -1,2 +1,2 @@ -obj-m += agilent_82350b.o +obj-$(CONFIG_GPIB_AGILENT_82350B) += agilent_82350b.o diff --git a/drivers/staging/gpib/agilent_82350b/agilent_82350b.c b/drivers/staging/gpib/agilent_82350b/agilent_82350b.c index 53006d0cc79c..8e2334fe5c9b 100644 --- a/drivers/staging/gpib/agilent_82350b/agilent_82350b.c +++ b/drivers/staging/gpib/agilent_82350b/agilent_82350b.c @@ -700,7 +700,7 @@ static int agilent_82350b_generic_attach(gpib_board_t *board, const gpib_board_c GPIB_82350A_REGION)); dev_dbg(board->gpib_dev, "%s: gpib base address remapped to 0x%p\n", driver_name, a_priv->gpib_base); - tms_priv->iobase = a_priv->gpib_base + TMS9914_BASE_REG; + tms_priv->mmiobase = a_priv->gpib_base + TMS9914_BASE_REG; a_priv->sram_base = ioremap(pci_resource_start(a_priv->pci_device, SRAM_82350A_REGION), pci_resource_len(a_priv->pci_device, @@ -724,7 +724,7 @@ static int agilent_82350b_generic_attach(gpib_board_t *board, const gpib_board_c pci_resource_len(a_priv->pci_device, GPIB_REGION)); dev_dbg(board->gpib_dev, "%s: gpib base address remapped to 0x%p\n", driver_name, a_priv->gpib_base); - tms_priv->iobase = a_priv->gpib_base + TMS9914_BASE_REG; + tms_priv->mmiobase = a_priv->gpib_base + TMS9914_BASE_REG; a_priv->sram_base = ioremap(pci_resource_start(a_priv->pci_device, SRAM_REGION), pci_resource_len(a_priv->pci_device, SRAM_REGION)); dev_dbg(board->gpib_dev, "%s: sram base address remapped to 0x%p\n", diff --git a/drivers/staging/gpib/agilent_82357a/Makefile b/drivers/staging/gpib/agilent_82357a/Makefile index 4a1d940fce2b..81a55c257a6e 100644 --- a/drivers/staging/gpib/agilent_82357a/Makefile +++ b/drivers/staging/gpib/agilent_82357a/Makefile @@ -1,4 +1,4 @@ -obj-m += agilent_82357a.o +obj-$(CONFIG_GPIB_AGILENT_82357A) += agilent_82357a.o diff --git a/drivers/staging/gpib/cb7210/Makefile b/drivers/staging/gpib/cb7210/Makefile index 22e0214fc17d..cda0725d6487 100644 --- a/drivers/staging/gpib/cb7210/Makefile +++ b/drivers/staging/gpib/cb7210/Makefile @@ -1,4 +1,4 @@ ccflags-$(CONFIG_GPIB_PCMCIA) := -DGPIB_PCMCIA -obj-m += cb7210.o +obj-$(CONFIG_GPIB_CB7210) += cb7210.o diff --git a/drivers/staging/gpib/cb7210/cb7210.c b/drivers/staging/gpib/cb7210/cb7210.c index 63df7f3eb3f3..59e41c97f518 100644 --- a/drivers/staging/gpib/cb7210/cb7210.c +++ b/drivers/staging/gpib/cb7210/cb7210.c @@ -971,12 +971,12 @@ int cb_pci_attach(gpib_board_t *board, const gpib_board_config_t *config) switch (cb_priv->pci_chip) { case PCI_CHIP_AMCC_S5933: cb_priv->amcc_iobase = pci_resource_start(cb_priv->pci_device, 0); - nec_priv->iobase = (void *)(pci_resource_start(cb_priv->pci_device, 1)); + nec_priv->iobase = pci_resource_start(cb_priv->pci_device, 1); cb_priv->fifo_iobase = pci_resource_start(cb_priv->pci_device, 2); break; case PCI_CHIP_QUANCOM: - nec_priv->iobase = (void *)(pci_resource_start(cb_priv->pci_device, 0)); - cb_priv->fifo_iobase = (unsigned long)nec_priv->iobase; + nec_priv->iobase = pci_resource_start(cb_priv->pci_device, 0); + cb_priv->fifo_iobase = nec_priv->iobase; break; default: pr_err("cb7210: bug! unhandled pci_chip=%i\n", cb_priv->pci_chip); @@ -1040,8 +1040,8 @@ int cb_isa_attach(gpib_board_t *board, const gpib_board_config_t *config) return retval; cb_priv = board->private_data; nec_priv = &cb_priv->nec7210_priv; - if (request_region((unsigned long)config->ibbase, cb7210_iosize, "cb7210") == 0) { - pr_err("gpib: ioports starting at 0x%p are already in use\n", config->ibbase); + if (request_region(config->ibbase, cb7210_iosize, "cb7210") == 0) { + pr_err("gpib: ioports starting at 0x%u are already in use\n", config->ibbase); return -EIO; } nec_priv->iobase = config->ibbase; @@ -1471,7 +1471,7 @@ int cb_pcmcia_attach(gpib_board_t *board, const gpib_board_config_t *config) (unsigned long)curr_dev->resource[0]->start); return -EIO; } - nec_priv->iobase = (void *)(unsigned long)curr_dev->resource[0]->start; + nec_priv->iobase = curr_dev->resource[0]->start; cb_priv->fifo_iobase = curr_dev->resource[0]->start; if (request_irq(curr_dev->irq, cb7210_interrupt, IRQF_SHARED, diff --git a/drivers/staging/gpib/cb7210/cb7210.h b/drivers/staging/gpib/cb7210/cb7210.h index 4ad976de2b68..c17cb22585f7 100644 --- a/drivers/staging/gpib/cb7210/cb7210.h +++ b/drivers/staging/gpib/cb7210/cb7210.h @@ -113,9 +113,9 @@ enum hs_regs { HS_STATUS = 0x8, /* HS_STATUS register */ }; -static inline unsigned long nec7210_iobase(const struct cb7210_priv *cb_priv) +static inline u32 nec7210_iobase(const struct cb7210_priv *cb_priv) { - return (unsigned long)(cb_priv->nec7210_priv.iobase); + return cb_priv->nec7210_priv.iobase; } static inline int cb7210_page_in_bits(unsigned int page) diff --git a/drivers/staging/gpib/cec/Makefile b/drivers/staging/gpib/cec/Makefile index f4638628ff29..b7141e23d4e0 100644 --- a/drivers/staging/gpib/cec/Makefile +++ b/drivers/staging/gpib/cec/Makefile @@ -1,3 +1,3 @@ -obj-m += cec_gpib.o +obj-$(CONFIG_GPIB_CEC_PCI) += cec_gpib.o diff --git a/drivers/staging/gpib/cec/cec_gpib.c b/drivers/staging/gpib/cec/cec_gpib.c index 3dc933deb401..9c00a874468c 100644 --- a/drivers/staging/gpib/cec/cec_gpib.c +++ b/drivers/staging/gpib/cec/cec_gpib.c @@ -297,8 +297,8 @@ int cec_pci_attach(gpib_board_t *board, const gpib_board_config_t *config) cec_priv->plx_iobase = pci_resource_start(cec_priv->pci_device, 1); pr_info(" plx9050 base address 0x%lx\n", cec_priv->plx_iobase); - nec_priv->iobase = (void *)(pci_resource_start(cec_priv->pci_device, 3)); - pr_info(" nec7210 base address 0x%p\n", nec_priv->iobase); + nec_priv->iobase = pci_resource_start(cec_priv->pci_device, 3); + pr_info(" nec7210 base address 0x%x\n", nec_priv->iobase); isr_flags |= IRQF_SHARED; if (request_irq(cec_priv->pci_device->irq, cec_interrupt, isr_flags, "pci-gpib", board)) { diff --git a/drivers/staging/gpib/common/gpib_os.c b/drivers/staging/gpib/common/gpib_os.c index 405237d8cb47..0962729d7dfe 100644 --- a/drivers/staging/gpib/common/gpib_os.c +++ b/drivers/staging/gpib/common/gpib_os.c @@ -116,56 +116,6 @@ int io_timed_out(gpib_board_t *board) return 0; } -void writeb_wrapper(unsigned int value, void *address) -{ - writeb(value, address); -}; -EXPORT_SYMBOL(writeb_wrapper); - -void writew_wrapper(unsigned int value, void *address) -{ - writew(value, address); -}; -EXPORT_SYMBOL(writew_wrapper); - -unsigned int readb_wrapper(void *address) -{ - return readb(address); -}; -EXPORT_SYMBOL(readb_wrapper); - -unsigned int readw_wrapper(void *address) -{ - return readw(address); -}; -EXPORT_SYMBOL(readw_wrapper); - -#ifdef CONFIG_HAS_IOPORT -void outb_wrapper(unsigned int value, void *address) -{ - outb(value, (unsigned long)(address)); -}; -EXPORT_SYMBOL(outb_wrapper); - -void outw_wrapper(unsigned int value, void *address) -{ - outw(value, (unsigned long)(address)); -}; -EXPORT_SYMBOL(outw_wrapper); - -unsigned int inb_wrapper(void *address) -{ - return inb((unsigned long)(address)); -}; -EXPORT_SYMBOL(inb_wrapper); - -unsigned int inw_wrapper(void *address) -{ - return inw((unsigned long)(address)); -}; -EXPORT_SYMBOL(inw_wrapper); -#endif - /* this is a function instead of a constant because of Suse * defining HZ to be a function call to get_hz() */ @@ -536,7 +486,7 @@ int dvrsp(gpib_board_t *board, unsigned int pad, int sad, return -1; } - if (pad > MAX_GPIB_PRIMARY_ADDRESS || sad > MAX_GPIB_SECONDARY_ADDRESS) { + if (pad > MAX_GPIB_PRIMARY_ADDRESS || sad > MAX_GPIB_SECONDARY_ADDRESS || sad < -1) { pr_err("gpib: bad address for serial poll"); return -1; } @@ -1623,7 +1573,7 @@ static int iobase_ioctl(gpib_board_config_t *config, unsigned long arg) if (WARN_ON_ONCE(sizeof(void *) > sizeof(base_addr))) return -EFAULT; - config->ibbase = (void *)(unsigned long)(base_addr); + config->ibbase = base_addr; return 0; } diff --git a/drivers/staging/gpib/eastwood/Makefile b/drivers/staging/gpib/eastwood/Makefile index c74056f959d0..384825195f77 100644 --- a/drivers/staging/gpib/eastwood/Makefile +++ b/drivers/staging/gpib/eastwood/Makefile @@ -1,3 +1,3 @@ -obj-m += fluke_gpib.o +obj-$(CONFIG_GPIB_FLUKE) += fluke_gpib.o diff --git a/drivers/staging/gpib/eastwood/fluke_gpib.c b/drivers/staging/gpib/eastwood/fluke_gpib.c index 3f938ab0c84d..5e59d38beb35 100644 --- a/drivers/staging/gpib/eastwood/fluke_gpib.c +++ b/drivers/staging/gpib/eastwood/fluke_gpib.c @@ -1011,12 +1011,12 @@ static int fluke_attach_impl(gpib_board_t *board, const gpib_board_config_t *con } e_priv->gpib_iomem_res = res; - nec_priv->iobase = ioremap(e_priv->gpib_iomem_res->start, + nec_priv->mmiobase = ioremap(e_priv->gpib_iomem_res->start, resource_size(e_priv->gpib_iomem_res)); - pr_info("gpib: iobase %lx remapped to %p, length=%d\n", - (unsigned long)e_priv->gpib_iomem_res->start, - nec_priv->iobase, (int)resource_size(e_priv->gpib_iomem_res)); - if (!nec_priv->iobase) { + pr_info("gpib: mmiobase %llx remapped to %p, length=%d\n", + (u64)e_priv->gpib_iomem_res->start, + nec_priv->mmiobase, (int)resource_size(e_priv->gpib_iomem_res)); + if (!nec_priv->mmiobase) { dev_err(&fluke_gpib_pdev->dev, "Could not map I/O memory\n"); return -ENOMEM; } @@ -1107,7 +1107,7 @@ void fluke_detach(gpib_board_t *board) gpib_free_pseudo_irq(board); nec_priv = &e_priv->nec7210_priv; - if (nec_priv->iobase) { + if (nec_priv->mmiobase) { fluke_paged_write_byte(e_priv, 0, ISR0_IMR0, ISR0_IMR0_PAGE); nec7210_board_reset(nec_priv, board); } diff --git a/drivers/staging/gpib/eastwood/fluke_gpib.h b/drivers/staging/gpib/eastwood/fluke_gpib.h index fcbd42f8f9af..4e2144d45270 100644 --- a/drivers/staging/gpib/eastwood/fluke_gpib.h +++ b/drivers/staging/gpib/eastwood/fluke_gpib.h @@ -72,7 +72,7 @@ static inline uint8_t fluke_read_byte_nolock(struct nec7210_priv *nec_priv, { u8 retval; - retval = readl(nec_priv->iobase + register_num * nec_priv->offset); + retval = readl(nec_priv->mmiobase + register_num * nec_priv->offset); return retval; } @@ -80,7 +80,7 @@ static inline uint8_t fluke_read_byte_nolock(struct nec7210_priv *nec_priv, static inline void fluke_write_byte_nolock(struct nec7210_priv *nec_priv, uint8_t data, int register_num) { - writel(data, nec_priv->iobase + register_num * nec_priv->offset); + writel(data, nec_priv->mmiobase + register_num * nec_priv->offset); } static inline uint8_t fluke_paged_read_byte(struct fluke_priv *e_priv, diff --git a/drivers/staging/gpib/fmh_gpib/fmh_gpib.c b/drivers/staging/gpib/fmh_gpib/fmh_gpib.c index 62791db1c34a..0662b20a45e7 100644 --- a/drivers/staging/gpib/fmh_gpib/fmh_gpib.c +++ b/drivers/staging/gpib/fmh_gpib/fmh_gpib.c @@ -24,6 +24,8 @@ #include <linux/slab.h> MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("GPIB Driver for fmh_gpib_core"); +MODULE_AUTHOR("Frank Mori Hess <fmh6jj@gmail.com>"); static irqreturn_t fmh_gpib_interrupt(int irq, void *arg); static int fmh_gpib_attach_holdoff_all(gpib_board_t *board, const gpib_board_config_t *config); @@ -1419,15 +1421,14 @@ static int fmh_gpib_attach_impl(gpib_board_t *board, const gpib_board_config_t * } e_priv->gpib_iomem_res = res; - nec_priv->iobase = ioremap(e_priv->gpib_iomem_res->start, + nec_priv->mmiobase = ioremap(e_priv->gpib_iomem_res->start, resource_size(e_priv->gpib_iomem_res)); - if (!nec_priv->iobase) { + if (!nec_priv->mmiobase) { dev_err(board->dev, "Could not map I/O memory for gpib\n"); return -ENOMEM; } - dev_info(board->dev, "iobase 0x%lx remapped to %p, length=%ld\n", - (unsigned long)e_priv->gpib_iomem_res->start, - nec_priv->iobase, (unsigned long)resource_size(e_priv->gpib_iomem_res)); + dev_info(board->dev, "iobase %pr remapped to %p\n", + e_priv->gpib_iomem_res, nec_priv->mmiobase); res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dma_fifos"); if (!res) { @@ -1507,14 +1508,14 @@ void fmh_gpib_detach(gpib_board_t *board) free_irq(e_priv->irq, board); if (e_priv->fifo_base) fifos_write(e_priv, 0, FIFO_CONTROL_STATUS_REG); - if (nec_priv->iobase) { + if (nec_priv->mmiobase) { write_byte(nec_priv, 0, ISR0_IMR0_REG); nec7210_board_reset(nec_priv, board); } if (e_priv->fifo_base) iounmap(e_priv->fifo_base); - if (nec_priv->iobase) - iounmap(nec_priv->iobase); + if (nec_priv->mmiobase) + iounmap(nec_priv->mmiobase); if (e_priv->dma_port_res) { release_mem_region(e_priv->dma_port_res->start, resource_size(e_priv->dma_port_res)); @@ -1564,12 +1565,12 @@ static int fmh_gpib_pci_attach_impl(gpib_board_t *board, const gpib_board_config e_priv->gpib_iomem_res = &pci_device->resource[gpib_control_status_pci_resource_index]; e_priv->dma_port_res = &pci_device->resource[gpib_fifo_pci_resource_index]; - nec_priv->iobase = ioremap(pci_resource_start(pci_device, + nec_priv->mmiobase = ioremap(pci_resource_start(pci_device, gpib_control_status_pci_resource_index), pci_resource_len(pci_device, gpib_control_status_pci_resource_index)); dev_info(board->dev, "base address for gpib control/status registers remapped to 0x%p\n", - nec_priv->iobase); + nec_priv->mmiobase); if (e_priv->dma_port_res->flags & IORESOURCE_MEM) { e_priv->fifo_base = ioremap(pci_resource_start(pci_device, @@ -1632,14 +1633,14 @@ void fmh_gpib_pci_detach(gpib_board_t *board) free_irq(e_priv->irq, board); if (e_priv->fifo_base) fifos_write(e_priv, 0, FIFO_CONTROL_STATUS_REG); - if (nec_priv->iobase) { + if (nec_priv->mmiobase) { write_byte(nec_priv, 0, ISR0_IMR0_REG); nec7210_board_reset(nec_priv, board); } if (e_priv->fifo_base) iounmap(e_priv->fifo_base); - if (nec_priv->iobase) - iounmap(nec_priv->iobase); + if (nec_priv->mmiobase) + iounmap(nec_priv->mmiobase); if (e_priv->dma_port_res || e_priv->gpib_iomem_res) pci_release_regions(to_pci_dev(board->dev)); if (board->dev) diff --git a/drivers/staging/gpib/fmh_gpib/fmh_gpib.h b/drivers/staging/gpib/fmh_gpib/fmh_gpib.h index 43bfc89d2a6f..60b1bd6d3c15 100644 --- a/drivers/staging/gpib/fmh_gpib/fmh_gpib.h +++ b/drivers/staging/gpib/fmh_gpib/fmh_gpib.h @@ -127,13 +127,13 @@ static const unsigned int fifo_max_burst_length_mask = 0x00ff; static inline uint8_t gpib_cs_read_byte(struct nec7210_priv *nec_priv, unsigned int register_num) { - return readb(nec_priv->iobase + register_num * nec_priv->offset); + return readb(nec_priv->mmiobase + register_num * nec_priv->offset); } static inline void gpib_cs_write_byte(struct nec7210_priv *nec_priv, uint8_t data, unsigned int register_num) { - writeb(data, nec_priv->iobase + register_num * nec_priv->offset); + writeb(data, nec_priv->mmiobase + register_num * nec_priv->offset); } static inline uint16_t fifos_read(struct fmh_priv *fmh_priv, int register_num) diff --git a/drivers/staging/gpib/gpio/Makefile b/drivers/staging/gpib/gpio/Makefile index a31ded6e5924..00ea52abdda7 100644 --- a/drivers/staging/gpib/gpio/Makefile +++ b/drivers/staging/gpib/gpio/Makefile @@ -1,4 +1,4 @@ -obj-m += gpib_bitbang.o +obj-$(CONFIG_GPIB_GPIO) += gpib_bitbang.o diff --git a/drivers/staging/gpib/gpio/gpib_bitbang.c b/drivers/staging/gpib/gpio/gpib_bitbang.c index a2d562cbd65b..23550502e012 100644 --- a/drivers/staging/gpib/gpio/gpib_bitbang.c +++ b/drivers/staging/gpib/gpio/gpib_bitbang.c @@ -315,7 +315,7 @@ struct bb_priv { enum listener_function_state listener_state; }; -inline long usec_diff(struct timespec64 *a, struct timespec64 *b); +static inline long usec_diff(struct timespec64 *a, struct timespec64 *b); static void bb_buffer_print(unsigned char *buffer, size_t length, int cmd, int eoi); static void set_data_lines(u8 byte); static u8 get_data_lines(void); diff --git a/drivers/staging/gpib/hp_82335/Makefile b/drivers/staging/gpib/hp_82335/Makefile index 8b7a552e9355..305ce44ee48a 100644 --- a/drivers/staging/gpib/hp_82335/Makefile +++ b/drivers/staging/gpib/hp_82335/Makefile @@ -1,4 +1,4 @@ -obj-m += hp82335.o +obj-$(CONFIG_GPIB_HP82335) += hp82335.o diff --git a/drivers/staging/gpib/hp_82335/hp82335.c b/drivers/staging/gpib/hp_82335/hp82335.c index 40afe42aea47..ea78143c7ab6 100644 --- a/drivers/staging/gpib/hp_82335/hp82335.c +++ b/drivers/staging/gpib/hp_82335/hp82335.c @@ -9,6 +9,7 @@ */ #include "hp82335.h" +#include <linux/io.h> #include <linux/ioport.h> #include <linux/sched.h> #include <linux/module.h> @@ -233,7 +234,7 @@ static void hp82335_clear_interrupt(struct hp82335_priv *hp_priv) { struct tms9914_priv *tms_priv = &hp_priv->tms9914_priv; - writeb(0, tms_priv->iobase + HPREG_INTR_CLEAR); + writeb(0, tms_priv->mmiobase + HPREG_INTR_CLEAR); } int hp82335_attach(gpib_board_t *board, const gpib_board_config_t *config) @@ -241,7 +242,7 @@ int hp82335_attach(gpib_board_t *board, const gpib_board_config_t *config) struct hp82335_priv *hp_priv; struct tms9914_priv *tms_priv; int retval; - const unsigned long upper_iomem_base = (unsigned long)config->ibbase + hp82335_rom_size; + const unsigned long upper_iomem_base = config->ibbase + hp82335_rom_size; board->status = 0; @@ -253,7 +254,7 @@ int hp82335_attach(gpib_board_t *board, const gpib_board_config_t *config) tms_priv->write_byte = hp82335_write_byte; tms_priv->offset = 1; - switch ((unsigned long)(config->ibbase)) { + switch (config->ibbase) { case 0xc4000: case 0xc8000: case 0xcc000: @@ -271,7 +272,7 @@ int hp82335_attach(gpib_board_t *board, const gpib_board_config_t *config) case 0xfc000: break; default: - pr_err("hp82335: invalid base io address 0x%p\n", config->ibbase); + pr_err("hp82335: invalid base io address 0x%u\n", config->ibbase); return -EINVAL; } if (!request_mem_region(upper_iomem_base, hp82335_upper_iomem_size, "hp82335")) { @@ -280,9 +281,9 @@ int hp82335_attach(gpib_board_t *board, const gpib_board_config_t *config) return -EBUSY; } hp_priv->raw_iobase = upper_iomem_base; - tms_priv->iobase = ioremap(upper_iomem_base, hp82335_upper_iomem_size); + tms_priv->mmiobase = ioremap(upper_iomem_base, hp82335_upper_iomem_size); pr_info("hp82335: upper half of 82335 iomem region 0x%lx remapped to 0x%p\n", - hp_priv->raw_iobase, tms_priv->iobase); + hp_priv->raw_iobase, tms_priv->mmiobase); retval = request_irq(config->ibirq, hp82335_interrupt, 0, "hp82335", board); if (retval) { @@ -296,7 +297,7 @@ int hp82335_attach(gpib_board_t *board, const gpib_board_config_t *config) hp82335_clear_interrupt(hp_priv); - writeb(INTR_ENABLE, tms_priv->iobase + HPREG_CCR); + writeb(INTR_ENABLE, tms_priv->mmiobase + HPREG_CCR); tms9914_online(board, tms_priv); @@ -312,10 +313,10 @@ void hp82335_detach(gpib_board_t *board) tms_priv = &hp_priv->tms9914_priv; if (hp_priv->irq) free_irq(hp_priv->irq, board); - if (tms_priv->iobase) { - writeb(0, tms_priv->iobase + HPREG_CCR); + if (tms_priv->mmiobase) { + writeb(0, tms_priv->mmiobase + HPREG_CCR); tms9914_board_reset(tms_priv); - iounmap((void *)tms_priv->iobase); + iounmap(tms_priv->mmiobase); } if (hp_priv->raw_iobase) release_mem_region(hp_priv->raw_iobase, hp82335_upper_iomem_size); diff --git a/drivers/staging/gpib/hp_82341/Makefile b/drivers/staging/gpib/hp_82341/Makefile index 1fe7db4f8ca4..21367310a17e 100644 --- a/drivers/staging/gpib/hp_82341/Makefile +++ b/drivers/staging/gpib/hp_82341/Makefile @@ -1,2 +1,2 @@ -obj-m += hp_82341.o +obj-$(CONFIG_GPIB_HP82341) += hp_82341.o diff --git a/drivers/staging/gpib/hp_82341/hp_82341.c b/drivers/staging/gpib/hp_82341/hp_82341.c index 8ad1c885a9fb..71d481e88bd9 100644 --- a/drivers/staging/gpib/hp_82341/hp_82341.c +++ b/drivers/staging/gpib/hp_82341/hp_82341.c @@ -473,12 +473,12 @@ void hp_82341_free_private(gpib_board_t *board) static uint8_t hp_82341_read_byte(struct tms9914_priv *priv, unsigned int register_num) { - return inb((unsigned long)(priv->iobase) + register_num); + return inb(priv->iobase + register_num); } static void hp_82341_write_byte(struct tms9914_priv *priv, uint8_t data, unsigned int register_num) { - outb(data, (unsigned long)(priv->iobase) + register_num); + outb(data, priv->iobase + register_num); } static int hp_82341_find_isapnp_board(struct pnp_dev **dev) @@ -682,8 +682,8 @@ int hp_82341_attach(gpib_board_t *board, const gpib_board_config_t *config) { struct hp_82341_priv *hp_priv; struct tms9914_priv *tms_priv; - unsigned long start_addr; - void *iobase; + u32 start_addr; + u32 iobase; int irq; int i; int retval; @@ -704,7 +704,7 @@ int hp_82341_attach(gpib_board_t *board, const gpib_board_config_t *config) if (retval < 0) return retval; hp_priv->pnp_dev = dev; - iobase = (void *)(pnp_port_start(dev, 0)); + iobase = pnp_port_start(dev, 0); irq = pnp_irq(dev, 0); hp_priv->hw_version = HW_VERSION_82341D; hp_priv->io_region_offset = 0x8; @@ -714,9 +714,9 @@ int hp_82341_attach(gpib_board_t *board, const gpib_board_config_t *config) hp_priv->hw_version = HW_VERSION_82341C; hp_priv->io_region_offset = 0x400; } - pr_info("hp_82341: base io 0x%p\n", iobase); + pr_info("hp_82341: base io 0x%u\n", iobase); for (i = 0; i < hp_82341_num_io_regions; ++i) { - start_addr = (unsigned long)(iobase) + i * hp_priv->io_region_offset; + start_addr = iobase + i * hp_priv->io_region_offset; if (!request_region(start_addr, hp_82341_region_iosize, "hp_82341")) { pr_err("hp_82341: failed to allocate io ports 0x%lx-0x%lx\n", start_addr, @@ -725,7 +725,7 @@ int hp_82341_attach(gpib_board_t *board, const gpib_board_config_t *config) } hp_priv->iobase[i] = start_addr; } - tms_priv->iobase = (void *)(hp_priv->iobase[2]); + tms_priv->iobase = hp_priv->iobase[2]; if (hp_priv->hw_version == HW_VERSION_82341D) { retval = isapnp_cfg_begin(hp_priv->pnp_dev->card->number, hp_priv->pnp_dev->number); diff --git a/drivers/staging/gpib/include/gpibP.h b/drivers/staging/gpib/include/gpibP.h index 5fc42b645ab7..b97da577ba33 100644 --- a/drivers/staging/gpib/include/gpibP.h +++ b/drivers/staging/gpib/include/gpibP.h @@ -16,6 +16,7 @@ #include <linux/fs.h> #include <linux/interrupt.h> +#include <linux/io.h> void gpib_register_driver(gpib_interface_t *interface, struct module *mod); void gpib_unregister_driver(gpib_interface_t *interface); @@ -35,16 +36,5 @@ extern gpib_board_t board_array[GPIB_MAX_NUM_BOARDS]; extern struct list_head registered_drivers; -#include <linux/io.h> - -void writeb_wrapper(unsigned int value, void *address); -unsigned int readb_wrapper(void *address); -void outb_wrapper(unsigned int value, void *address); -unsigned int inb_wrapper(void *address); -void writew_wrapper(unsigned int value, void *address); -unsigned int readw_wrapper(void *address); -void outw_wrapper(unsigned int value, void *address); -unsigned int inw_wrapper(void *address); - #endif // _GPIB_P_H diff --git a/drivers/staging/gpib/include/gpib_types.h b/drivers/staging/gpib/include/gpib_types.h index ee2643da6d71..b41781a55a60 100644 --- a/drivers/staging/gpib/include/gpib_types.h +++ b/drivers/staging/gpib/include/gpib_types.h @@ -31,7 +31,8 @@ typedef struct { void *init_data; int init_data_length; /* IO base address to use for non-pnp cards (set by core, driver should make local copy) */ - void *ibbase; + u32 ibbase; + void __iomem *mmibbase; /* IRQ to use for non-pnp cards (set by core, driver should make local copy) */ unsigned int ibirq; /* dma channel to use for non-pnp cards (set by core, driver should make local copy) */ diff --git a/drivers/staging/gpib/include/nec7210.h b/drivers/staging/gpib/include/nec7210.h index c00aba4ce846..ca998c4a84bf 100644 --- a/drivers/staging/gpib/include/nec7210.h +++ b/drivers/staging/gpib/include/nec7210.h @@ -18,7 +18,10 @@ /* struct used to provide variables local to a nec7210 chip */ struct nec7210_priv { - void *iobase; +#ifdef CONFIG_HAS_IOPORT + u32 iobase; +#endif + void __iomem *mmiobase; unsigned int offset; // offset between successive nec7210 io addresses unsigned int dma_channel; u8 *dma_buffer; diff --git a/drivers/staging/gpib/include/tms9914.h b/drivers/staging/gpib/include/tms9914.h index 456b488212d2..d8c8d1c9b131 100644 --- a/drivers/staging/gpib/include/tms9914.h +++ b/drivers/staging/gpib/include/tms9914.h @@ -20,7 +20,10 @@ enum tms9914_holdoff_mode { /* struct used to provide variables local to a tms9914 chip */ struct tms9914_priv { - void *iobase; +#ifdef CONFIG_HAS_IOPORT + u32 iobase; +#endif + void __iomem *mmiobase; unsigned int offset; // offset between successive tms9914 io addresses unsigned int dma_channel; // software copy of bits written to interrupt mask registers diff --git a/drivers/staging/gpib/ines/Makefile b/drivers/staging/gpib/ines/Makefile index cdcaa59a4e39..6b6e480fd811 100644 --- a/drivers/staging/gpib/ines/Makefile +++ b/drivers/staging/gpib/ines/Makefile @@ -1,4 +1,4 @@ ccflags-$(CONFIG_GPIB_PCMCIA) := -DGPIB_PCMCIA -obj-m += ines_gpib.o +obj-$(CONFIG_GPIB_INES) += ines_gpib.o diff --git a/drivers/staging/gpib/ines/ines.h b/drivers/staging/gpib/ines/ines.h index 7e8302619998..eed038fd3f28 100644 --- a/drivers/staging/gpib/ines/ines.h +++ b/drivers/staging/gpib/ines/ines.h @@ -83,14 +83,14 @@ void ines_set_xfer_counter(struct ines_priv *priv, unsigned int count); /* inb/outb wrappers */ static inline unsigned int ines_inb(struct ines_priv *priv, unsigned int register_number) { - return inb((unsigned long)(priv->nec7210_priv.iobase) + + return inb(priv->nec7210_priv.iobase + register_number * priv->nec7210_priv.offset); } static inline void ines_outb(struct ines_priv *priv, unsigned int value, unsigned int register_number) { - outb(value, (unsigned long)(priv->nec7210_priv.iobase) + + outb(value, priv->nec7210_priv.iobase + register_number * priv->nec7210_priv.offset); } diff --git a/drivers/staging/gpib/ines/ines_gpib.c b/drivers/staging/gpib/ines/ines_gpib.c index 9d8387c3bf01..e18455ba842f 100644 --- a/drivers/staging/gpib/ines/ines_gpib.c +++ b/drivers/staging/gpib/ines/ines_gpib.c @@ -273,10 +273,10 @@ irqreturn_t ines_pci_interrupt(int irq, void *arg) struct nec7210_priv *nec_priv = &priv->nec7210_priv; if (priv->pci_chip_type == PCI_CHIP_QUANCOM) { - if ((inb((unsigned long)nec_priv->iobase + + if ((inb(nec_priv->iobase + QUANCOM_IRQ_CONTROL_STATUS_REG) & QUANCOM_IRQ_ASSERTED_BIT)) - outb(QUANCOM_IRQ_ENABLE_BIT, (unsigned long)(nec_priv->iobase) + + outb(QUANCOM_IRQ_ENABLE_BIT, nec_priv->iobase + QUANCOM_IRQ_CONTROL_STATUS_REG); } @@ -780,8 +780,8 @@ static int ines_common_pci_attach(gpib_board_t *board, const gpib_board_config_t if (pci_request_regions(ines_priv->pci_device, "ines-gpib")) return -1; - nec_priv->iobase = (void *)(pci_resource_start(ines_priv->pci_device, - found_id.gpib_region)); + nec_priv->iobase = pci_resource_start(ines_priv->pci_device, + found_id.gpib_region); ines_priv->pci_chip_type = found_id.pci_chip_type; nec_priv->offset = found_id.io_offset; @@ -840,7 +840,7 @@ static int ines_common_pci_attach(gpib_board_t *board, const gpib_board_config_t } break; case PCI_CHIP_QUANCOM: - outb(QUANCOM_IRQ_ENABLE_BIT, (unsigned long)(nec_priv->iobase) + + outb(QUANCOM_IRQ_ENABLE_BIT, nec_priv->iobase + QUANCOM_IRQ_CONTROL_STATUS_REG); break; case PCI_CHIP_QUICKLOGIC5030: @@ -899,8 +899,8 @@ int ines_isa_attach(gpib_board_t *board, const gpib_board_config_t *config) ines_priv = board->private_data; nec_priv = &ines_priv->nec7210_priv; - if (!request_region((unsigned long)config->ibbase, ines_isa_iosize, "ines_gpib")) { - pr_err("ines_gpib: ioports at 0x%p already in use\n", config->ibbase); + if (!request_region(config->ibbase, ines_isa_iosize, "ines_gpib")) { + pr_err("ines_gpib: ioports at 0x%x already in use\n", config->ibbase); return -1; } nec_priv->iobase = config->ibbase; @@ -931,7 +931,7 @@ void ines_pci_detach(gpib_board_t *board) break; case PCI_CHIP_QUANCOM: if (nec_priv->iobase) - outb(0, (unsigned long)(nec_priv->iobase) + + outb(0, nec_priv->iobase + QUANCOM_IRQ_CONTROL_STATUS_REG); break; default: @@ -960,7 +960,7 @@ void ines_isa_detach(gpib_board_t *board) free_irq(ines_priv->irq, board); if (nec_priv->iobase) { nec7210_board_reset(nec_priv, board); - release_region((unsigned long)(nec_priv->iobase), ines_isa_iosize); + release_region(nec_priv->iobase, ines_isa_iosize); } } ines_free_private(board); @@ -1355,7 +1355,7 @@ int ines_common_pcmcia_attach(gpib_board_t *board) return -1; } - nec_priv->iobase = (void *)(unsigned long)curr_dev->resource[0]->start; + nec_priv->iobase = curr_dev->resource[0]->start; nec7210_board_reset(nec_priv, board); @@ -1410,7 +1410,7 @@ void ines_pcmcia_detach(gpib_board_t *board) free_irq(ines_priv->irq, board); if (nec_priv->iobase) { nec7210_board_reset(nec_priv, board); - release_region((unsigned long)(nec_priv->iobase), ines_pcmcia_iosize); + release_region(nec_priv->iobase, ines_pcmcia_iosize); } } ines_free_private(board); diff --git a/drivers/staging/gpib/lpvo_usb_gpib/Makefile b/drivers/staging/gpib/lpvo_usb_gpib/Makefile index 137511acce63..360553488e6d 100644 --- a/drivers/staging/gpib/lpvo_usb_gpib/Makefile +++ b/drivers/staging/gpib/lpvo_usb_gpib/Makefile @@ -1,3 +1,3 @@ -obj-m += lpvo_usb_gpib.o +obj-$(CONFIG_GPIB_LPVO) += lpvo_usb_gpib.o diff --git a/drivers/staging/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c b/drivers/staging/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c index 267651a15fa0..93a05c792816 100644 --- a/drivers/staging/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c +++ b/drivers/staging/gpib/lpvo_usb_gpib/lpvo_usb_gpib.c @@ -99,8 +99,8 @@ module_param(debug, int, 0644); #define USB_GPIB_DEBUG_ON "\nIBDE\xAA\n" #define USB_GPIB_SET_LISTEN "\nIBDT0\n" #define USB_GPIB_SET_TALK "\nIBDT1\n" -#define USB_GPIB_SET_LINES "\nIBDC\n" -#define USB_GPIB_SET_DATA "\nIBDM\n" +#define USB_GPIB_SET_LINES "\nIBDC.\n" +#define USB_GPIB_SET_DATA "\nIBDM.\n" #define USB_GPIB_READ_LINES "\nIBD?C\n" #define USB_GPIB_READ_DATA "\nIBD?M\n" #define USB_GPIB_READ_BUS "\nIBD??\n" @@ -210,7 +210,7 @@ static int skel_do_release(gpib_board_t *); * (unix time in sec and NANOsec) */ -inline int usec_diff(struct timespec64 *a, struct timespec64 *b) +static inline int usec_diff(struct timespec64 *a, struct timespec64 *b) { return ((a->tv_sec - b->tv_sec) * 1000000 + (a->tv_nsec - b->tv_nsec) / 1000); @@ -436,7 +436,7 @@ static void set_timeout(gpib_board_t *board) static int usb_gpib_attach(gpib_board_t *board, const gpib_board_config_t *config) { int retval, j; - int base = (long)config->ibbase; + u32 base = config->ibbase; char *device_path; int match; struct usb_device *udev; @@ -589,7 +589,7 @@ static int usb_gpib_command(gpib_board_t *board, size_t *bytes_written) { int i, retval; - char command[6] = "IBc\n"; + char command[6] = "IBc.\n"; DIA_LOG(1, "enter %p\n", board); @@ -608,7 +608,7 @@ static int usb_gpib_command(gpib_board_t *board, } /** - * disable_eos() - Disable END on eos byte (END on EOI only) + * usb_gpib_disable_eos() - Disable END on eos byte (END on EOI only) * * @board: the gpib_board data area for this gpib interface * @@ -624,7 +624,7 @@ static void usb_gpib_disable_eos(gpib_board_t *board) } /** - * enable_eos() - Enable END for reads when eos byte is received. + * usb_gpib_enable_eos() - Enable END for reads when eos byte is received. * * @board: the gpib_board data area for this gpib interface * @eos_byte: the 'eos' byte @@ -647,7 +647,7 @@ static int usb_gpib_enable_eos(gpib_board_t *board, } /** - * go_to_standby() - De-assert ATN + * usb_gpib_go_to_standby() - De-assert ATN * * @board: the gpib_board data area for this gpib interface */ @@ -664,7 +664,7 @@ static int usb_gpib_go_to_standby(gpib_board_t *board) } /** - * interface_clear() - Assert or de-assert IFC + * usb_gpib_interface_clear() - Assert or de-assert IFC * * @board: the gpib_board data area for this gpib interface * assert: 1: assert IFC; 0: de-assert IFC diff --git a/drivers/staging/gpib/nec7210/nec7210.c b/drivers/staging/gpib/nec7210/nec7210.c index 1d9951035497..c9a837fad96e 100644 --- a/drivers/staging/gpib/nec7210/nec7210.c +++ b/drivers/staging/gpib/nec7210/nec7210.c @@ -1035,7 +1035,7 @@ EXPORT_SYMBOL(nec7210_board_online); /* wrappers for io */ uint8_t nec7210_ioport_read_byte(struct nec7210_priv *priv, unsigned int register_num) { - return inb((unsigned long)(priv->iobase) + register_num * priv->offset); + return inb(priv->iobase + register_num * priv->offset); } EXPORT_SYMBOL(nec7210_ioport_read_byte); @@ -1047,7 +1047,7 @@ void nec7210_ioport_write_byte(struct nec7210_priv *priv, uint8_t data, unsigned */ nec7210_locking_ioport_write_byte(priv, data, register_num); else - outb(data, (unsigned long)(priv->iobase) + register_num * priv->offset); + outb(data, priv->iobase + register_num * priv->offset); } EXPORT_SYMBOL(nec7210_ioport_write_byte); @@ -1058,7 +1058,7 @@ uint8_t nec7210_locking_ioport_read_byte(struct nec7210_priv *priv, unsigned int unsigned long flags; spin_lock_irqsave(&priv->register_page_lock, flags); - retval = inb((unsigned long)(priv->iobase) + register_num * priv->offset); + retval = inb(priv->iobase + register_num * priv->offset); spin_unlock_irqrestore(&priv->register_page_lock, flags); return retval; } @@ -1072,7 +1072,7 @@ void nec7210_locking_ioport_write_byte(struct nec7210_priv *priv, uint8_t data, spin_lock_irqsave(&priv->register_page_lock, flags); if (register_num == AUXMR) udelay(1); - outb(data, (unsigned long)(priv->iobase) + register_num * priv->offset); + outb(data, priv->iobase + register_num * priv->offset); spin_unlock_irqrestore(&priv->register_page_lock, flags); } EXPORT_SYMBOL(nec7210_locking_ioport_write_byte); @@ -1080,7 +1080,7 @@ EXPORT_SYMBOL(nec7210_locking_ioport_write_byte); uint8_t nec7210_iomem_read_byte(struct nec7210_priv *priv, unsigned int register_num) { - return readb(priv->iobase + register_num * priv->offset); + return readb(priv->mmiobase + register_num * priv->offset); } EXPORT_SYMBOL(nec7210_iomem_read_byte); @@ -1092,7 +1092,7 @@ void nec7210_iomem_write_byte(struct nec7210_priv *priv, uint8_t data, unsigned */ nec7210_locking_iomem_write_byte(priv, data, register_num); else - writeb(data, priv->iobase + register_num * priv->offset); + writeb(data, priv->mmiobase + register_num * priv->offset); } EXPORT_SYMBOL(nec7210_iomem_write_byte); @@ -1102,7 +1102,7 @@ uint8_t nec7210_locking_iomem_read_byte(struct nec7210_priv *priv, unsigned int unsigned long flags; spin_lock_irqsave(&priv->register_page_lock, flags); - retval = readb(priv->iobase + register_num * priv->offset); + retval = readb(priv->mmiobase + register_num * priv->offset); spin_unlock_irqrestore(&priv->register_page_lock, flags); return retval; } @@ -1116,7 +1116,7 @@ void nec7210_locking_iomem_write_byte(struct nec7210_priv *priv, uint8_t data, spin_lock_irqsave(&priv->register_page_lock, flags); if (register_num == AUXMR) udelay(1); - writeb(data, priv->iobase + register_num * priv->offset); + writeb(data, priv->mmiobase + register_num * priv->offset); spin_unlock_irqrestore(&priv->register_page_lock, flags); } EXPORT_SYMBOL(nec7210_locking_iomem_write_byte); diff --git a/drivers/staging/gpib/ni_usb/Makefile b/drivers/staging/gpib/ni_usb/Makefile index e22b3b21a62c..469c5d16add3 100644 --- a/drivers/staging/gpib/ni_usb/Makefile +++ b/drivers/staging/gpib/ni_usb/Makefile @@ -1,4 +1,4 @@ -obj-m += ni_usb_gpib.o +obj-$(CONFIG_GPIB_NI_USB) += ni_usb_gpib.o diff --git a/drivers/staging/gpib/pc2/Makefile b/drivers/staging/gpib/pc2/Makefile index 8148425e0f87..481ee4296e1b 100644 --- a/drivers/staging/gpib/pc2/Makefile +++ b/drivers/staging/gpib/pc2/Makefile @@ -1,5 +1,5 @@ -obj-m += pc2_gpib.o +obj-$(CONFIG_GPIB_PC2) += pc2_gpib.o diff --git a/drivers/staging/gpib/pc2/pc2_gpib.c b/drivers/staging/gpib/pc2/pc2_gpib.c index 7b3b34f47341..d22af25125b1 100644 --- a/drivers/staging/gpib/pc2/pc2_gpib.c +++ b/drivers/staging/gpib/pc2/pc2_gpib.c @@ -426,7 +426,7 @@ int pc2_attach(gpib_board_t *board, const gpib_board_config_t *config) nec_priv = &pc2_priv->nec7210_priv; nec_priv->offset = pc2_reg_offset; - if (request_region((unsigned long)config->ibbase, pc2_iosize, "pc2") == 0) { + if (request_region(config->ibbase, pc2_iosize, "pc2") == 0) { pr_err("gpib: ioports are already in use\n"); return -1; } @@ -471,7 +471,7 @@ void pc2_detach(gpib_board_t *board) free_irq(pc2_priv->irq, board); if (nec_priv->iobase) { nec7210_board_reset(nec_priv, board); - release_region((unsigned long)(nec_priv->iobase), pc2_iosize); + release_region(nec_priv->iobase, pc2_iosize); } if (nec_priv->dma_buffer) { dma_free_coherent(board->dev, nec_priv->dma_buffer_length, @@ -498,14 +498,14 @@ static int pc2a_common_attach(gpib_board_t *board, const gpib_board_config_t *co nec_priv = &pc2_priv->nec7210_priv; nec_priv->offset = pc2a_reg_offset; - switch ((unsigned long)(config->ibbase)) { + switch (config->ibbase) { case 0x02e1: case 0x22e1: case 0x42e1: case 0x62e1: break; default: - pr_err("PCIIa base range invalid, must be one of 0x[0246]2e1, but is 0x%p\n", + pr_err("PCIIa base range invalid, must be one of 0x[0246]2e1, but is 0x%d\n", config->ibbase); return -1; } @@ -522,7 +522,7 @@ static int pc2a_common_attach(gpib_board_t *board, const gpib_board_config_t *co unsigned int err = 0; for (i = 0; i < num_registers; i++) { - if (check_region((unsigned long)config->ibbase + i * pc2a_reg_offset, 1)) + if (check_region(config->ibbase + i * pc2a_reg_offset, 1)) err++; } if (config->ibirq && check_region(pc2a_clear_intr_iobase + config->ibirq, 1)) @@ -533,11 +533,11 @@ static int pc2a_common_attach(gpib_board_t *board, const gpib_board_config_t *co } #endif for (i = 0; i < num_registers; i++) { - if (!request_region((unsigned long)config->ibbase + + if (!request_region(config->ibbase + i * pc2a_reg_offset, 1, "pc2a")) { pr_err("gpib: ioports are already in use"); for (j = 0; j < i; j++) - release_region((unsigned long)(config->ibbase) + + release_region(config->ibbase + j * pc2a_reg_offset, 1); return -1; } @@ -608,7 +608,7 @@ static void pc2a_common_detach(gpib_board_t *board, unsigned int num_registers) if (nec_priv->iobase) { nec7210_board_reset(nec_priv, board); for (i = 0; i < num_registers; i++) - release_region((unsigned long)nec_priv->iobase + + release_region(nec_priv->iobase + i * pc2a_reg_offset, 1); } if (pc2_priv->clear_intr_addr) diff --git a/drivers/staging/gpib/tms9914/Makefile b/drivers/staging/gpib/tms9914/Makefile index 81b7e3cf104c..4705ab07f413 100644 --- a/drivers/staging/gpib/tms9914/Makefile +++ b/drivers/staging/gpib/tms9914/Makefile @@ -1,5 +1,5 @@ -obj-m += tms9914.o +obj-$(CONFIG_GPIB_TMS9914) += tms9914.o diff --git a/drivers/staging/gpib/tms9914/tms9914.c b/drivers/staging/gpib/tms9914/tms9914.c index 152b243b845b..ec8e1d4d762f 100644 --- a/drivers/staging/gpib/tms9914/tms9914.c +++ b/drivers/staging/gpib/tms9914/tms9914.c @@ -866,14 +866,14 @@ EXPORT_SYMBOL_GPL(tms9914_online); // wrapper for inb uint8_t tms9914_ioport_read_byte(struct tms9914_priv *priv, unsigned int register_num) { - return inb((unsigned long)(priv->iobase) + register_num * priv->offset); + return inb(priv->iobase + register_num * priv->offset); } EXPORT_SYMBOL_GPL(tms9914_ioport_read_byte); // wrapper for outb void tms9914_ioport_write_byte(struct tms9914_priv *priv, uint8_t data, unsigned int register_num) { - outb(data, (unsigned long)(priv->iobase) + register_num * priv->offset); + outb(data, priv->iobase + register_num * priv->offset); if (register_num == AUXCR) udelay(1); } @@ -883,14 +883,14 @@ EXPORT_SYMBOL_GPL(tms9914_ioport_write_byte); // wrapper for readb uint8_t tms9914_iomem_read_byte(struct tms9914_priv *priv, unsigned int register_num) { - return readb(priv->iobase + register_num * priv->offset); + return readb(priv->mmiobase + register_num * priv->offset); } EXPORT_SYMBOL_GPL(tms9914_iomem_read_byte); // wrapper for writeb void tms9914_iomem_write_byte(struct tms9914_priv *priv, uint8_t data, unsigned int register_num) { - writeb(data, priv->iobase + register_num * priv->offset); + writeb(data, priv->mmiobase + register_num * priv->offset); if (register_num == AUXCR) udelay(1); } diff --git a/drivers/staging/gpib/tnt4882/Makefile b/drivers/staging/gpib/tnt4882/Makefile index f767c990db7a..a3c3fb96d5ed 100644 --- a/drivers/staging/gpib/tnt4882/Makefile +++ b/drivers/staging/gpib/tnt4882/Makefile @@ -1,5 +1,5 @@ ccflags-$(CONFIG_GPIB_PCMCIA) := -DGPIB_PCMCIA -obj-m += tnt4882.o +obj-$(CONFIG_GPIB_NI_PCI_ISA) += tnt4882.o tnt4882-objs := tnt4882_gpib.o mite.o diff --git a/drivers/staging/gpib/tnt4882/mite.c b/drivers/staging/gpib/tnt4882/mite.c index 0edf34d243e9..4bd352967616 100644 --- a/drivers/staging/gpib/tnt4882/mite.c +++ b/drivers/staging/gpib/tnt4882/mite.c @@ -148,72 +148,3 @@ void mite_list_devices(void) } pr_info("\n"); } - -int mite_bytes_transferred(struct mite_struct *mite, int chan) -{ - int dar, fcr; - - dar = readl(mite->mite_io_addr + MITE_DAR + CHAN_OFFSET(chan)); - fcr = readl(mite->mite_io_addr + MITE_FCR + CHAN_OFFSET(chan)) & 0x000000FF; - return dar - fcr; -} - -int mite_dma_tcr(struct mite_struct *mite) -{ - int tcr; - int lkar; - - lkar = readl(mite->mite_io_addr + CHAN_OFFSET(0) + MITE_LKAR); - tcr = readl(mite->mite_io_addr + CHAN_OFFSET(0) + MITE_TCR); - MDPRINTK("lkar=0x%08x tcr=%d\n", lkar, tcr); - - return tcr; -} - -void mite_dma_disarm(struct mite_struct *mite) -{ - int chor; - - /* disarm */ - chor = CHOR_ABORT; - writel(chor, mite->mite_io_addr + CHAN_OFFSET(0) + MITE_CHOR); -} - -void mite_dump_regs(struct mite_struct *mite) -{ - void *addr = 0; - unsigned long temp = 0; - - pr_info("mite address is =0x%p\n", mite->mite_io_addr); - - addr = mite->mite_io_addr + MITE_CHOR + CHAN_OFFSET(0); - pr_info("mite status[CHOR]at 0x%p =0x%08lx\n", addr, temp = readl(addr)); - //mite_decode(mite_CHOR_strings,temp); - addr = mite->mite_io_addr + MITE_CHCR + CHAN_OFFSET(0); - pr_info("mite status[CHCR]at 0x%p =0x%08lx\n", addr, temp = readl(addr)); - //mite_decode(mite_CHCR_strings,temp); - addr = mite->mite_io_addr + MITE_TCR + CHAN_OFFSET(0); - pr_info("mite status[TCR] at 0x%p =0x%08x\n", addr, readl(addr)); - addr = mite->mite_io_addr + MITE_MCR + CHAN_OFFSET(0); - pr_info("mite status[MCR] at 0x%p =0x%08lx\n", addr, temp = readl(addr)); - //mite_decode(mite_MCR_strings,temp); - addr = mite->mite_io_addr + MITE_MAR + CHAN_OFFSET(0); - pr_info("mite status[MAR] at 0x%p =0x%08x\n", addr, readl(addr)); - addr = mite->mite_io_addr + MITE_DCR + CHAN_OFFSET(0); - pr_info("mite status[DCR] at 0x%p =0x%08lx\n", addr, temp = readl(addr)); - //mite_decode(mite_CR_strings,temp); - addr = mite->mite_io_addr + MITE_DAR + CHAN_OFFSET(0); - pr_info("mite status[DAR] at 0x%p =0x%08x\n", addr, readl(addr)); - addr = mite->mite_io_addr + MITE_LKCR + CHAN_OFFSET(0); - pr_info("mite status[LKCR]at 0x%p =0x%08lx\n", addr, temp = readl(addr)); - //mite_decode(mite_CR_strings,temp); - addr = mite->mite_io_addr + MITE_LKAR + CHAN_OFFSET(0); - pr_info("mite status[LKAR]at 0x%p =0x%08x\n", addr, readl(addr)); - - addr = mite->mite_io_addr + MITE_CHSR + CHAN_OFFSET(0); - pr_info("mite status[CHSR]at 0x%p =0x%08lx\n", addr, temp = readl(addr)); - //mite_decode(mite_CHSR_strings,temp); - addr = mite->mite_io_addr + MITE_FCR + CHAN_OFFSET(0); - pr_info("mite status[FCR] at 0x%p =0x%08x\n\n", addr, readl(addr)); -} - diff --git a/drivers/staging/gpib/tnt4882/mite.h b/drivers/staging/gpib/tnt4882/mite.h index 6454d069b8cc..edb873435b51 100644 --- a/drivers/staging/gpib/tnt4882/mite.h +++ b/drivers/staging/gpib/tnt4882/mite.h @@ -34,9 +34,9 @@ struct mite_struct { struct pci_dev *pcidev; unsigned long mite_phys_addr; - void *mite_io_addr; + void __iomem *mite_io_addr; unsigned long daq_phys_addr; - void *daq_io_addr; + void __iomem *daq_io_addr; int DMA_CheckNearEnd; @@ -61,15 +61,6 @@ int mite_setup(struct mite_struct *mite); void mite_unsetup(struct mite_struct *mite); void mite_list_devices(void); -int mite_dma_tcr(struct mite_struct *mite); - -void mite_dma_arm(struct mite_struct *mite); -void mite_dma_disarm(struct mite_struct *mite); - -void mite_dump_regs(struct mite_struct *mite); -void mite_setregs(struct mite_struct *mite, unsigned long ll_start, int chan, int dir); -int mite_bytes_transferred(struct mite_struct *mite, int chan); - #define CHAN_OFFSET(x) (0x100 * (x)) /* DMA base for chan 0 is 0x500, chan 1 is 0x600 */ diff --git a/drivers/staging/gpib/tnt4882/tnt4882_gpib.c b/drivers/staging/gpib/tnt4882/tnt4882_gpib.c index e49a952fa0d8..ce91c3eb768c 100644 --- a/drivers/staging/gpib/tnt4882/tnt4882_gpib.c +++ b/drivers/staging/gpib/tnt4882/tnt4882_gpib.c @@ -45,10 +45,6 @@ struct tnt4882_priv { unsigned short imr0_bits; unsigned short imr3_bits; unsigned short auxg_bits; // bits written to auxiliary register G - void (*io_writeb)(unsigned int value, void *address); - void (*io_writew)(unsigned int value, void *address); - unsigned int (*io_readb)(void *address); - unsigned int (*io_readw)(void *address); }; // interface functions @@ -104,23 +100,23 @@ static const int atgpib_iosize = 32; /* paged io */ static inline unsigned int tnt_paged_readb(struct tnt4882_priv *priv, unsigned long offset) { - priv->io_writeb(AUX_PAGEIN, priv->nec7210_priv.iobase + AUXMR * priv->nec7210_priv.offset); + iowrite8(AUX_PAGEIN, priv->nec7210_priv.mmiobase + AUXMR * priv->nec7210_priv.offset); udelay(1); - return priv->io_readb(priv->nec7210_priv.iobase + offset); + return ioread8(priv->nec7210_priv.mmiobase + offset); } static inline void tnt_paged_writeb(struct tnt4882_priv *priv, unsigned int value, unsigned long offset) { - priv->io_writeb(AUX_PAGEIN, priv->nec7210_priv.iobase + AUXMR * priv->nec7210_priv.offset); + iowrite8(AUX_PAGEIN, priv->nec7210_priv.mmiobase + AUXMR * priv->nec7210_priv.offset); udelay(1); - priv->io_writeb(value, priv->nec7210_priv.iobase + offset); + iowrite8(value, priv->nec7210_priv.mmiobase + offset); } /* readb/writeb wrappers */ static inline unsigned short tnt_readb(struct tnt4882_priv *priv, unsigned long offset) { - void *address = priv->nec7210_priv.iobase + offset; + void *address = priv->nec7210_priv.mmiobase + offset; unsigned long flags; unsigned short retval; spinlock_t *register_lock = &priv->nec7210_priv.register_page_lock; @@ -134,7 +130,7 @@ static inline unsigned short tnt_readb(struct tnt4882_priv *priv, unsigned long switch (priv->nec7210_priv.type) { case TNT4882: case TNT5004: - retval = priv->io_readb(address); + retval = ioread8(address); break; case NAT4882: retval = tnt_paged_readb(priv, offset - tnt_pagein_offset); @@ -149,7 +145,7 @@ static inline unsigned short tnt_readb(struct tnt4882_priv *priv, unsigned long } break; default: - retval = priv->io_readb(address); + retval = ioread8(address); break; } spin_unlock_irqrestore(register_lock, flags); @@ -158,7 +154,7 @@ static inline unsigned short tnt_readb(struct tnt4882_priv *priv, unsigned long static inline void tnt_writeb(struct tnt4882_priv *priv, unsigned short value, unsigned long offset) { - void *address = priv->nec7210_priv.iobase + offset; + void *address = priv->nec7210_priv.mmiobase + offset; unsigned long flags; spinlock_t *register_lock = &priv->nec7210_priv.register_page_lock; @@ -170,7 +166,7 @@ static inline void tnt_writeb(struct tnt4882_priv *priv, unsigned short value, u switch (priv->nec7210_priv.type) { case TNT4882: case TNT5004: - priv->io_writeb(value, address); + iowrite8(value, address); break; case NAT4882: tnt_paged_writeb(priv, value, offset - tnt_pagein_offset); @@ -183,7 +179,7 @@ static inline void tnt_writeb(struct tnt4882_priv *priv, unsigned short value, u } break; default: - priv->io_writeb(value, address); + iowrite8(value, address); break; } spin_unlock_irqrestore(register_lock, flags); @@ -288,7 +284,7 @@ static int drain_fifo_words(struct tnt4882_priv *tnt_priv, uint8_t *buffer, int while (fifo_word_available(tnt_priv) && count + 2 <= num_bytes) { short word; - word = tnt_priv->io_readw(nec_priv->iobase + FIFOB); + word = ioread16(nec_priv->mmiobase + FIFOB); buffer[count++] = word & 0xff; buffer[count++] = (word >> 8) & 0xff; } @@ -573,7 +569,7 @@ static int generic_write(gpib_board_t *board, uint8_t *buffer, size_t length, word = buffer[count++] & 0xff; if (count < length) word |= (buffer[count++] << 8) & 0xff00; - tnt_priv->io_writew(word, nec_priv->iobase + FIFOB); + iowrite16(word, nec_priv->mmiobase + FIFOB); } // avoid unnecessary HR_NFF interrupts // tnt_priv->imr3_bits |= HR_NFF; @@ -1269,10 +1265,6 @@ int ni_pci_attach(gpib_board_t *board, const gpib_board_config_t *config) if (tnt4882_allocate_private(board)) return -ENOMEM; tnt_priv = board->private_data; - tnt_priv->io_writeb = writeb_wrapper; - tnt_priv->io_readb = readb_wrapper; - tnt_priv->io_writew = writew_wrapper; - tnt_priv->io_readw = readw_wrapper; nec_priv = &tnt_priv->nec7210_priv; nec_priv->type = TNT4882; nec_priv->read_byte = nec7210_locking_iomem_read_byte; @@ -1324,7 +1316,7 @@ int ni_pci_attach(gpib_board_t *board, const gpib_board_config_t *config) return retval; } - nec_priv->iobase = tnt_priv->mite->daq_io_addr; + nec_priv->mmiobase = tnt_priv->mite->daq_io_addr; // get irq if (request_irq(mite_irq(tnt_priv->mite), tnt4882_interrupt, isr_flags, @@ -1359,7 +1351,7 @@ void ni_pci_detach(gpib_board_t *board) if (tnt_priv) { nec_priv = &tnt_priv->nec7210_priv; - if (nec_priv->iobase) + if (nec_priv->mmiobase) tnt4882_board_reset(tnt_priv, board); if (tnt_priv->irq) free_irq(tnt_priv->irq, board); @@ -1400,7 +1392,7 @@ static int ni_isa_attach_common(gpib_board_t *board, const gpib_board_config_t * struct tnt4882_priv *tnt_priv; struct nec7210_priv *nec_priv; int isr_flags = 0; - void *iobase; + u32 iobase; int irq; board->status = 0; @@ -1408,10 +1400,6 @@ static int ni_isa_attach_common(gpib_board_t *board, const gpib_board_config_t * if (tnt4882_allocate_private(board)) return -ENOMEM; tnt_priv = board->private_data; - tnt_priv->io_writeb = outb_wrapper; - tnt_priv->io_readb = inb_wrapper; - tnt_priv->io_writew = outw_wrapper; - tnt_priv->io_readw = inw_wrapper; nec_priv = &tnt_priv->nec7210_priv; nec_priv->type = chipset; nec_priv->read_byte = nec7210_locking_ioport_read_byte; @@ -1427,18 +1415,20 @@ static int ni_isa_attach_common(gpib_board_t *board, const gpib_board_config_t * if (retval < 0) return retval; tnt_priv->pnp_dev = dev; - iobase = (void *)(pnp_port_start(dev, 0)); + iobase = pnp_port_start(dev, 0); irq = pnp_irq(dev, 0); } else { iobase = config->ibbase; irq = config->ibirq; } // allocate ioports - if (!request_region((unsigned long)(iobase), atgpib_iosize, "atgpib")) { + if (!request_region(iobase, atgpib_iosize, "atgpib")) { pr_err("tnt4882: failed to allocate ioports\n"); return -1; } - nec_priv->iobase = iobase; + nec_priv->mmiobase = ioport_map(iobase, atgpib_iosize); + if (!nec_priv->mmiobase) + return -1; // get irq if (request_irq(irq, tnt4882_interrupt, isr_flags, "atgpib", board)) { @@ -1478,8 +1468,10 @@ void ni_isa_detach(gpib_board_t *board) tnt4882_board_reset(tnt_priv, board); if (tnt_priv->irq) free_irq(tnt_priv->irq, board); + if (nec_priv->mmiobase) + ioport_unmap(nec_priv->mmiobase); if (nec_priv->iobase) - release_region((unsigned long)(nec_priv->iobase), atgpib_iosize); + release_region(nec_priv->iobase, atgpib_iosize); if (tnt_priv->pnp_dev) pnp_device_detach(tnt_priv->pnp_dev); } @@ -1817,10 +1809,6 @@ int ni_pcmcia_attach(gpib_board_t *board, const gpib_board_config_t *config) if (tnt4882_allocate_private(board)) return -ENOMEM; tnt_priv = board->private_data; - tnt_priv->io_writeb = outb_wrapper; - tnt_priv->io_readb = inb_wrapper; - tnt_priv->io_writew = outw_wrapper; - tnt_priv->io_readw = inw_wrapper; nec_priv = &tnt_priv->nec7210_priv; nec_priv->type = TNT4882; nec_priv->read_byte = nec7210_locking_ioport_read_byte; @@ -1835,7 +1823,10 @@ int ni_pcmcia_attach(gpib_board_t *board, const gpib_board_config_t *config) return -EIO; } - nec_priv->iobase = (void *)(unsigned long)curr_dev->resource[0]->start; + nec_priv->mmiobase = ioport_map(curr_dev->resource[0]->start, + resource_size(curr_dev->resource[0])); + if (!nec_priv->mmiobase) + return -1; // get irq if (request_irq(curr_dev->irq, tnt4882_interrupt, isr_flags, "tnt4882", board)) { @@ -1860,9 +1851,11 @@ void ni_pcmcia_detach(gpib_board_t *board) nec_priv = &tnt_priv->nec7210_priv; if (tnt_priv->irq) free_irq(tnt_priv->irq, board); + if (nec_priv->mmiobase) + ioport_unmap(nec_priv->mmiobase); if (nec_priv->iobase) { tnt4882_board_reset(tnt_priv, board); - release_region((unsigned long)nec_priv->iobase, pcmcia_gpib_iosize); + release_region(nec_priv->iobase, pcmcia_gpib_iosize); } } tnt4882_free_private(board); diff --git a/drivers/staging/iio/frequency/ad9832.c b/drivers/staging/iio/frequency/ad9832.c index 492612e8f8ba..140ee4f9c137 100644 --- a/drivers/staging/iio/frequency/ad9832.c +++ b/drivers/staging/iio/frequency/ad9832.c @@ -158,7 +158,7 @@ static int ad9832_write_frequency(struct ad9832_state *st, static int ad9832_write_phase(struct ad9832_state *st, unsigned long addr, unsigned long phase) { - if (phase > BIT(AD9832_PHASE_BITS)) + if (phase >= BIT(AD9832_PHASE_BITS)) return -EINVAL; st->phase_data[0] = cpu_to_be16((AD9832_CMD_PHA8BITSW << CMD_SHIFT) | diff --git a/drivers/staging/iio/frequency/ad9834.c b/drivers/staging/iio/frequency/ad9834.c index 47e7d7e6d920..6e99e008c5f4 100644 --- a/drivers/staging/iio/frequency/ad9834.c +++ b/drivers/staging/iio/frequency/ad9834.c @@ -131,7 +131,7 @@ static int ad9834_write_frequency(struct ad9834_state *st, static int ad9834_write_phase(struct ad9834_state *st, unsigned long addr, unsigned long phase) { - if (phase > BIT(AD9834_PHASE_BITS)) + if (phase >= BIT(AD9834_PHASE_BITS)) return -EINVAL; st->data = cpu_to_be16(addr | phase); diff --git a/drivers/thermal/thermal_of.c b/drivers/thermal/thermal_of.c index fab11b98ca49..5ab4ce4daaeb 100644 --- a/drivers/thermal/thermal_of.c +++ b/drivers/thermal/thermal_of.c @@ -160,6 +160,7 @@ static struct device_node *of_thermal_zone_find(struct device_node *sensor, int return ERR_PTR(ret); } + of_node_put(sensor_specs.np); if ((sensor == sensor_specs.np) && id == (sensor_specs.args_count ? sensor_specs.args[0] : 0)) { pr_debug("sensor %pOFn id=%d belongs to %pOFn\n", sensor, id, child); diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c index 5f9f06911795..68baf75bdadc 100644 --- a/drivers/tty/serial/8250/8250_core.c +++ b/drivers/tty/serial/8250/8250_core.c @@ -812,6 +812,9 @@ int serial8250_register_8250_port(const struct uart_8250_port *up) uart->dl_write = up->dl_write; if (uart->port.type != PORT_8250_CIR) { + if (uart_console_registered(&uart->port)) + pm_runtime_get_sync(uart->port.dev); + if (serial8250_isa_config != NULL) serial8250_isa_config(0, &uart->port, &uart->capabilities); diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c index 17f70e4bee43..9c59ec128bb4 100644 --- a/drivers/tty/serial/imx.c +++ b/drivers/tty/serial/imx.c @@ -2692,7 +2692,7 @@ static void imx_uart_enable_wakeup(struct imx_port *sport, bool on) { u32 ucr3; - uart_port_lock(&sport->port); + uart_port_lock_irq(&sport->port); ucr3 = imx_uart_readl(sport, UCR3); if (on) { @@ -2714,7 +2714,7 @@ static void imx_uart_enable_wakeup(struct imx_port *sport, bool on) imx_uart_writel(sport, ucr1, UCR1); } - uart_port_unlock(&sport->port); + uart_port_unlock_irq(&sport->port); } static int imx_uart_suspend_noirq(struct device *dev) diff --git a/drivers/tty/serial/stm32-usart.c b/drivers/tty/serial/stm32-usart.c index 7dc254546075..1ec5d8c3aef8 100644 --- a/drivers/tty/serial/stm32-usart.c +++ b/drivers/tty/serial/stm32-usart.c @@ -1051,14 +1051,14 @@ static void stm32_usart_break_ctl(struct uart_port *port, int break_state) const struct stm32_usart_offsets *ofs = &stm32_port->info->ofs; unsigned long flags; - spin_lock_irqsave(&port->lock, flags); + uart_port_lock_irqsave(port, &flags); if (break_state) stm32_usart_set_bits(port, ofs->rqr, USART_RQR_SBKRQ); else stm32_usart_clr_bits(port, ofs->rqr, USART_RQR_SBKRQ); - spin_unlock_irqrestore(&port->lock, flags); + uart_port_unlock_irqrestore(port, flags); } static int stm32_usart_startup(struct uart_port *port) diff --git a/drivers/usb/chipidea/ci_hdrc_imx.c b/drivers/usb/chipidea/ci_hdrc_imx.c index f2801700be8e..1a7fc638213e 100644 --- a/drivers/usb/chipidea/ci_hdrc_imx.c +++ b/drivers/usb/chipidea/ci_hdrc_imx.c @@ -370,25 +370,29 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev) data->pinctrl = devm_pinctrl_get(dev); if (PTR_ERR(data->pinctrl) == -ENODEV) data->pinctrl = NULL; - else if (IS_ERR(data->pinctrl)) - return dev_err_probe(dev, PTR_ERR(data->pinctrl), + else if (IS_ERR(data->pinctrl)) { + ret = dev_err_probe(dev, PTR_ERR(data->pinctrl), "pinctrl get failed\n"); + goto err_put; + } data->hsic_pad_regulator = devm_regulator_get_optional(dev, "hsic"); if (PTR_ERR(data->hsic_pad_regulator) == -ENODEV) { /* no pad regulator is needed */ data->hsic_pad_regulator = NULL; - } else if (IS_ERR(data->hsic_pad_regulator)) - return dev_err_probe(dev, PTR_ERR(data->hsic_pad_regulator), + } else if (IS_ERR(data->hsic_pad_regulator)) { + ret = dev_err_probe(dev, PTR_ERR(data->hsic_pad_regulator), "Get HSIC pad regulator error\n"); + goto err_put; + } if (data->hsic_pad_regulator) { ret = regulator_enable(data->hsic_pad_regulator); if (ret) { dev_err(dev, "Failed to enable HSIC pad regulator\n"); - return ret; + goto err_put; } } } @@ -402,13 +406,14 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev) dev_err(dev, "pinctrl_hsic_idle lookup failed, err=%ld\n", PTR_ERR(pinctrl_hsic_idle)); - return PTR_ERR(pinctrl_hsic_idle); + ret = PTR_ERR(pinctrl_hsic_idle); + goto err_put; } ret = pinctrl_select_state(data->pinctrl, pinctrl_hsic_idle); if (ret) { dev_err(dev, "hsic_idle select failed, err=%d\n", ret); - return ret; + goto err_put; } data->pinctrl_hsic_active = pinctrl_lookup_state(data->pinctrl, @@ -417,7 +422,8 @@ static int ci_hdrc_imx_probe(struct platform_device *pdev) dev_err(dev, "pinctrl_hsic_active lookup failed, err=%ld\n", PTR_ERR(data->pinctrl_hsic_active)); - return PTR_ERR(data->pinctrl_hsic_active); + ret = PTR_ERR(data->pinctrl_hsic_active); + goto err_put; } } @@ -527,6 +533,8 @@ disable_hsic_regulator: if (pdata.flags & CI_HDRC_PMQOS) cpu_latency_qos_remove_request(&data->pm_qos_req); data->ci_pdev = NULL; +err_put: + put_device(data->usbmisc_data->dev); return ret; } @@ -551,6 +559,7 @@ static void ci_hdrc_imx_remove(struct platform_device *pdev) if (data->hsic_pad_regulator) regulator_disable(data->hsic_pad_regulator); } + put_device(data->usbmisc_data->dev); } static void ci_hdrc_imx_shutdown(struct platform_device *pdev) diff --git a/drivers/usb/class/usblp.c b/drivers/usb/class/usblp.c index 5a2e43331064..ff1a941fd2ed 100644 --- a/drivers/usb/class/usblp.c +++ b/drivers/usb/class/usblp.c @@ -1337,11 +1337,12 @@ static int usblp_set_protocol(struct usblp *usblp, int protocol) if (protocol < USBLP_FIRST_PROTOCOL || protocol > USBLP_LAST_PROTOCOL) return -EINVAL; + alts = usblp->protocol[protocol].alt_setting; + if (alts < 0) + return -EINVAL; + /* Don't unnecessarily set the interface if there's a single alt. */ if (usblp->intf->num_altsetting > 1) { - alts = usblp->protocol[protocol].alt_setting; - if (alts < 0) - return -EINVAL; r = usb_set_interface(usblp->dev, usblp->ifnum, alts); if (r < 0) { printk(KERN_ERR "usblp: can't set desired altsetting %d on interface %d\n", diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 4b93c0bd1d4b..21ac9b464696 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -2663,13 +2663,13 @@ int usb_new_device(struct usb_device *udev) err = sysfs_create_link(&udev->dev.kobj, &port_dev->dev.kobj, "port"); if (err) - goto fail; + goto out_del_dev; err = sysfs_create_link(&port_dev->dev.kobj, &udev->dev.kobj, "device"); if (err) { sysfs_remove_link(&udev->dev.kobj, "port"); - goto fail; + goto out_del_dev; } if (!test_and_set_bit(port1, hub->child_usage_bits)) @@ -2683,6 +2683,8 @@ int usb_new_device(struct usb_device *udev) pm_runtime_put_sync_autosuspend(&udev->dev); return err; +out_del_dev: + device_del(&udev->dev); fail: usb_set_device_state(udev, USB_STATE_NOTATTACHED); pm_runtime_disable(&udev->dev); diff --git a/drivers/usb/core/port.c b/drivers/usb/core/port.c index 45d7af00f8d1..e857e532b35a 100644 --- a/drivers/usb/core/port.c +++ b/drivers/usb/core/port.c @@ -453,10 +453,11 @@ static int usb_port_runtime_suspend(struct device *dev) static void usb_port_shutdown(struct device *dev) { struct usb_port *port_dev = to_usb_port(dev); + struct usb_device *udev = port_dev->child; - if (port_dev->child) { - usb_disable_usb2_hardware_lpm(port_dev->child); - usb_unlocked_disable_lpm(port_dev->child); + if (udev && !udev->port_is_suspended) { + usb_disable_usb2_hardware_lpm(udev); + usb_unlocked_disable_lpm(udev); } } diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index ee73789326bc..f11570c8ffd0 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -464,6 +464,7 @@ #define DWC3_DCTL_TRGTULST_SS_INACT (DWC3_DCTL_TRGTULST(6)) /* These apply for core versions 1.94a and later */ +#define DWC3_DCTL_NYET_THRES_MASK (0xf << 20) #define DWC3_DCTL_NYET_THRES(n) (((n) & 0xf) << 20) #define DWC3_DCTL_KEEP_CONNECT BIT(19) diff --git a/drivers/usb/dwc3/dwc3-am62.c b/drivers/usb/dwc3/dwc3-am62.c index 5e3d1741701f..7d43da5f2897 100644 --- a/drivers/usb/dwc3/dwc3-am62.c +++ b/drivers/usb/dwc3/dwc3-am62.c @@ -309,6 +309,7 @@ static void dwc3_ti_remove(struct platform_device *pdev) pm_runtime_put_sync(dev); pm_runtime_disable(dev); + pm_runtime_dont_use_autosuspend(dev); pm_runtime_set_suspended(dev); } diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 83dc7304d701..31a654c6f15b 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -4195,8 +4195,10 @@ static void dwc3_gadget_conndone_interrupt(struct dwc3 *dwc) WARN_ONCE(DWC3_VER_IS_PRIOR(DWC3, 240A) && dwc->has_lpm_erratum, "LPM Erratum not available on dwc3 revisions < 2.40a\n"); - if (dwc->has_lpm_erratum && !DWC3_VER_IS_PRIOR(DWC3, 240A)) + if (dwc->has_lpm_erratum && !DWC3_VER_IS_PRIOR(DWC3, 240A)) { + reg &= ~DWC3_DCTL_NYET_THRES_MASK; reg |= DWC3_DCTL_NYET_THRES(dwc->lpm_nyet_threshold); + } dwc3_gadget_dctl_write_safe(dwc, reg); } else { diff --git a/drivers/usb/gadget/Kconfig b/drivers/usb/gadget/Kconfig index 566ff0b1282a..76521555e3c1 100644 --- a/drivers/usb/gadget/Kconfig +++ b/drivers/usb/gadget/Kconfig @@ -211,6 +211,8 @@ config USB_F_MIDI config USB_F_MIDI2 tristate + select SND_UMP + select SND_UMP_LEGACY_RAWMIDI config USB_F_HID tristate @@ -445,8 +447,6 @@ config USB_CONFIGFS_F_MIDI2 depends on USB_CONFIGFS depends on SND select USB_LIBCOMPOSITE - select SND_UMP - select SND_UMP_LEGACY_RAWMIDI select USB_F_MIDI2 help The MIDI 2.0 function driver provides the generic emulated diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c index 6499a88d346c..fba2a56dae97 100644 --- a/drivers/usb/gadget/configfs.c +++ b/drivers/usb/gadget/configfs.c @@ -827,11 +827,15 @@ static ssize_t gadget_string_s_store(struct config_item *item, const char *page, { struct gadget_string *string = to_gadget_string(item); int size = min(sizeof(string->string), len + 1); + ssize_t cpy_len; if (len > USB_MAX_STRING_LEN) return -EINVAL; - return strscpy(string->string, page, size); + cpy_len = strscpy(string->string, page, size); + if (cpy_len > 0 && string->string[cpy_len - 1] == '\n') + string->string[cpy_len - 1] = 0; + return len; } CONFIGFS_ATTR(gadget_string_, s); diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index ad79eb0f729b..2dea9e42a0f8 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -2285,7 +2285,7 @@ static int functionfs_bind(struct ffs_data *ffs, struct usb_composite_dev *cdev) struct usb_gadget_strings **lang; int first_id; - if (WARN_ON(ffs->state != FFS_ACTIVE + if ((ffs->state != FFS_ACTIVE || test_and_set_bit(FFS_FL_BOUND, &ffs->flags))) return -EBADFD; diff --git a/drivers/usb/gadget/function/f_uac2.c b/drivers/usb/gadget/function/f_uac2.c index ce5b77f89190..9b324821c93b 100644 --- a/drivers/usb/gadget/function/f_uac2.c +++ b/drivers/usb/gadget/function/f_uac2.c @@ -1185,6 +1185,7 @@ afunc_bind(struct usb_configuration *cfg, struct usb_function *fn) uac2->as_in_alt = 0; } + std_ac_if_desc.bNumEndpoints = 0; if (FUOUT_EN(uac2_opts) || FUIN_EN(uac2_opts)) { uac2->int_ep = usb_ep_autoconfig(gadget, &fs_ep_int_desc); if (!uac2->int_ep) { diff --git a/drivers/usb/gadget/function/u_serial.c b/drivers/usb/gadget/function/u_serial.c index 53d9fc41acc5..bc143a86c2dd 100644 --- a/drivers/usb/gadget/function/u_serial.c +++ b/drivers/usb/gadget/function/u_serial.c @@ -1420,6 +1420,10 @@ void gserial_disconnect(struct gserial *gser) /* REVISIT as above: how best to track this? */ port->port_line_coding = gser->port_line_coding; + /* disable endpoints, aborting down any active I/O */ + usb_ep_disable(gser->out); + usb_ep_disable(gser->in); + port->port_usb = NULL; gser->ioport = NULL; if (port->port.count > 0) { @@ -1431,10 +1435,6 @@ void gserial_disconnect(struct gserial *gser) spin_unlock(&port->port_lock); spin_unlock_irqrestore(&serial_port_lock, flags); - /* disable endpoints, aborting down any active I/O */ - usb_ep_disable(gser->out); - usb_ep_disable(gser->in); - /* finally, free any unused/unusable I/O buffers */ spin_lock_irqsave(&port->port_lock, flags); if (port->port.count == 0) diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c index e6c9006bd568..db109b570c5c 100644 --- a/drivers/usb/host/xhci-plat.c +++ b/drivers/usb/host/xhci-plat.c @@ -290,7 +290,8 @@ int xhci_plat_probe(struct platform_device *pdev, struct device *sysdev, const s hcd->tpl_support = of_usb_host_tpl_support(sysdev->of_node); - if (priv && (priv->quirks & XHCI_SKIP_PHY_INIT)) + if ((priv && (priv->quirks & XHCI_SKIP_PHY_INIT)) || + (xhci->quirks & XHCI_SKIP_PHY_INIT)) hcd->skip_phy_initialization = 1; if (priv && (priv->quirks & XHCI_SG_TRB_CACHE_SIZE_QUIRK)) diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index c24101f0a07a..9960ac2b10b7 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -223,6 +223,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x19CF, 0x3000) }, /* Parrot NMEA GPS Flight Recorder */ { USB_DEVICE(0x1ADB, 0x0001) }, /* Schweitzer Engineering C662 Cable */ { USB_DEVICE(0x1B1C, 0x1C00) }, /* Corsair USB Dongle */ + { USB_DEVICE(0x1B93, 0x1013) }, /* Phoenix Contact UPS Device */ { USB_DEVICE(0x1BA4, 0x0002) }, /* Silicon Labs 358x factory default */ { USB_DEVICE(0x1BE3, 0x07A6) }, /* WAGO 750-923 USB Service Cable */ { USB_DEVICE(0x1D6F, 0x0010) }, /* Seluxit ApS RF Dongle */ diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 64317b390d22..1e2ae0c6c41c 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -621,7 +621,7 @@ static void option_instat_callback(struct urb *urb); /* MeiG Smart Technology products */ #define MEIGSMART_VENDOR_ID 0x2dee -/* MeiG Smart SRM825L based on Qualcomm 315 */ +/* MeiG Smart SRM815/SRM825L based on Qualcomm 315 */ #define MEIGSMART_PRODUCT_SRM825L 0x4d22 /* MeiG Smart SLM320 based on UNISOC UIS8910 */ #define MEIGSMART_PRODUCT_SLM320 0x4d41 @@ -2405,6 +2405,7 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, LUAT_PRODUCT_AIR720U, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SLM320, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SLM770A, 0xff, 0, 0) }, + { USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SRM825L, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SRM825L, 0xff, 0xff, 0x30) }, { USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SRM825L, 0xff, 0xff, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SRM825L, 0xff, 0xff, 0x60) }, @@ -2412,6 +2413,7 @@ static const struct usb_device_id option_ids[] = { .driver_info = NCTRL(1) }, { USB_DEVICE_INTERFACE_CLASS(0x1bbb, 0x0640, 0xff), /* TCL IK512 ECM */ .driver_info = NCTRL(3) }, + { USB_DEVICE_INTERFACE_CLASS(0x2949, 0x8700, 0xff) }, /* Neoway N723-EA */ { } /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, option_ids); diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h index e5ad23d86833..54f0b1c83317 100644 --- a/drivers/usb/storage/unusual_devs.h +++ b/drivers/usb/storage/unusual_devs.h @@ -255,6 +255,13 @@ UNUSUAL_DEV( 0x0421, 0x06aa, 0x1110, 0x1110, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_MAX_SECTORS_64 ), +/* Added by Lubomir Rintel <lkundrak@v3.sk>, a very fine chap */ +UNUSUAL_DEV( 0x0421, 0x06c2, 0x0000, 0x0406, + "Nokia", + "Nokia 208", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_MAX_SECTORS_64 ), + #ifdef NO_SDDR09 UNUSUAL_DEV( 0x0436, 0x0005, 0x0100, 0x0100, "Microtech", diff --git a/drivers/usb/typec/tcpm/maxim_contaminant.c b/drivers/usb/typec/tcpm/maxim_contaminant.c index 22163d8f9eb0..0cdda06592fd 100644 --- a/drivers/usb/typec/tcpm/maxim_contaminant.c +++ b/drivers/usb/typec/tcpm/maxim_contaminant.c @@ -135,7 +135,7 @@ static int max_contaminant_read_resistance_kohm(struct max_tcpci_chip *chip, mv = max_contaminant_read_adc_mv(chip, channel, sleep_msec, raw, true); if (mv < 0) - return ret; + return mv; /* OVP enable */ ret = regmap_update_bits(regmap, TCPC_VENDOR_CC_CTRL2, CCOVPDIS, 0); @@ -157,7 +157,7 @@ static int max_contaminant_read_resistance_kohm(struct max_tcpci_chip *chip, mv = max_contaminant_read_adc_mv(chip, channel, sleep_msec, raw, true); if (mv < 0) - return ret; + return mv; /* Disable current source */ ret = regmap_update_bits(regmap, TCPC_VENDOR_CC_CTRL2, SBURPCTRL, 0); if (ret < 0) diff --git a/drivers/usb/typec/tcpm/tcpci.c b/drivers/usb/typec/tcpm/tcpci.c index ed32583829be..24a6a4354df8 100644 --- a/drivers/usb/typec/tcpm/tcpci.c +++ b/drivers/usb/typec/tcpm/tcpci.c @@ -700,7 +700,7 @@ static int tcpci_init(struct tcpc_dev *tcpc) tcpci->alert_mask = reg; - return tcpci_write16(tcpci, TCPC_ALERT_MASK, reg); + return 0; } irqreturn_t tcpci_irq(struct tcpci *tcpci) @@ -923,22 +923,27 @@ static int tcpci_probe(struct i2c_client *client) chip->data.set_orientation = err; + chip->tcpci = tcpci_register_port(&client->dev, &chip->data); + if (IS_ERR(chip->tcpci)) + return PTR_ERR(chip->tcpci); + err = devm_request_threaded_irq(&client->dev, client->irq, NULL, _tcpci_irq, IRQF_SHARED | IRQF_ONESHOT, dev_name(&client->dev), chip); if (err < 0) - return err; + goto unregister_port; - /* - * Disable irq while registering port. If irq is configured as an edge - * irq this allow to keep track and process the irq as soon as it is enabled. - */ - disable_irq(client->irq); - chip->tcpci = tcpci_register_port(&client->dev, &chip->data); - enable_irq(client->irq); + /* Enable chip interrupts at last */ + err = tcpci_write16(chip->tcpci, TCPC_ALERT_MASK, chip->tcpci->alert_mask); + if (err < 0) + goto unregister_port; - return PTR_ERR_OR_ZERO(chip->tcpci); + return 0; + +unregister_port: + tcpci_unregister_port(chip->tcpci); + return err; } static void tcpci_remove(struct i2c_client *client) diff --git a/drivers/usb/typec/ucsi/ucsi_ccg.c b/drivers/usb/typec/ucsi/ucsi_ccg.c index fcb8e61136cf..740171f24ef9 100644 --- a/drivers/usb/typec/ucsi/ucsi_ccg.c +++ b/drivers/usb/typec/ucsi/ucsi_ccg.c @@ -646,7 +646,7 @@ static int ucsi_ccg_sync_control(struct ucsi *ucsi, u64 command) UCSI_CMD_CONNECTOR_MASK; if (con_index == 0) { ret = -EINVAL; - goto unlock; + goto err_put; } con = &uc->ucsi->connector[con_index - 1]; ucsi_ccg_update_set_new_cam_cmd(uc, con, &command); @@ -654,8 +654,8 @@ static int ucsi_ccg_sync_control(struct ucsi *ucsi, u64 command) ret = ucsi_sync_control_common(ucsi, command); +err_put: pm_runtime_put_sync(uc->dev); -unlock: mutex_unlock(&uc->lock); return ret; diff --git a/drivers/usb/typec/ucsi/ucsi_glink.c b/drivers/usb/typec/ucsi/ucsi_glink.c index 90948cd6d297..fed39d458090 100644 --- a/drivers/usb/typec/ucsi/ucsi_glink.c +++ b/drivers/usb/typec/ucsi/ucsi_glink.c @@ -185,6 +185,11 @@ static void pmic_glink_ucsi_connector_status(struct ucsi_connector *con) struct pmic_glink_ucsi *ucsi = ucsi_get_drvdata(con->ucsi); int orientation; + if (!UCSI_CONSTAT(con, CONNECTED)) { + typec_set_orientation(con->port, TYPEC_ORIENTATION_NONE); + return; + } + if (con->num > PMIC_GLINK_MAX_PORTS || !ucsi->port_orientation[con->num - 1]) return; diff --git a/fs/afs/addr_prefs.c b/fs/afs/addr_prefs.c index a189ff8a5034..c0384201b8fe 100644 --- a/fs/afs/addr_prefs.c +++ b/fs/afs/addr_prefs.c @@ -413,8 +413,10 @@ int afs_proc_addr_prefs_write(struct file *file, char *buf, size_t size) do { argc = afs_split_string(&buf, argv, ARRAY_SIZE(argv)); - if (argc < 0) - return argc; + if (argc < 0) { + ret = argc; + goto done; + } if (argc < 2) goto inval; diff --git a/fs/afs/afs.h b/fs/afs/afs.h index b488072aee87..ec3db00bd081 100644 --- a/fs/afs/afs.h +++ b/fs/afs/afs.h @@ -10,7 +10,7 @@ #include <linux/in.h> -#define AFS_MAXCELLNAME 256 /* Maximum length of a cell name */ +#define AFS_MAXCELLNAME 253 /* Maximum length of a cell name (DNS limited) */ #define AFS_MAXVOLNAME 64 /* Maximum length of a volume name */ #define AFS_MAXNSERVERS 8 /* Maximum servers in a basic volume record */ #define AFS_NMAXNSERVERS 13 /* Maximum servers in a N/U-class volume record */ diff --git a/fs/afs/afs_vl.h b/fs/afs/afs_vl.h index a06296c8827d..b835e25a2c02 100644 --- a/fs/afs/afs_vl.h +++ b/fs/afs/afs_vl.h @@ -13,6 +13,7 @@ #define AFS_VL_PORT 7003 /* volume location service port */ #define VL_SERVICE 52 /* RxRPC service ID for the Volume Location service */ #define YFS_VL_SERVICE 2503 /* Service ID for AuriStor upgraded VL service */ +#define YFS_VL_MAXCELLNAME 256 /* Maximum length of a cell name in YFS protocol */ enum AFSVL_Operations { VLGETENTRYBYID = 503, /* AFS Get VLDB entry by ID */ diff --git a/fs/afs/vl_alias.c b/fs/afs/vl_alias.c index 9f36e14f1c2d..f9e76b604f31 100644 --- a/fs/afs/vl_alias.c +++ b/fs/afs/vl_alias.c @@ -253,6 +253,7 @@ static char *afs_vl_get_cell_name(struct afs_cell *cell, struct key *key) static int yfs_check_canonical_cell_name(struct afs_cell *cell, struct key *key) { struct afs_cell *master; + size_t name_len; char *cell_name; cell_name = afs_vl_get_cell_name(cell, key); @@ -264,8 +265,11 @@ static int yfs_check_canonical_cell_name(struct afs_cell *cell, struct key *key) return 0; } - master = afs_lookup_cell(cell->net, cell_name, strlen(cell_name), - NULL, false); + name_len = strlen(cell_name); + if (!name_len || name_len > AFS_MAXCELLNAME) + master = ERR_PTR(-EOPNOTSUPP); + else + master = afs_lookup_cell(cell->net, cell_name, name_len, NULL, false); kfree(cell_name); if (IS_ERR(master)) return PTR_ERR(master); diff --git a/fs/afs/vlclient.c b/fs/afs/vlclient.c index cac75f89b64a..55dd0fc5aad7 100644 --- a/fs/afs/vlclient.c +++ b/fs/afs/vlclient.c @@ -697,7 +697,7 @@ static int afs_deliver_yfsvl_get_cell_name(struct afs_call *call) return ret; namesz = ntohl(call->tmp); - if (namesz > AFS_MAXCELLNAME) + if (namesz > YFS_VL_MAXCELLNAME) return afs_protocol_error(call, afs_eproto_cellname_len); paddedsz = (namesz + 3) & ~3; call->count = namesz; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 1cccaf9c2b0d..3d0ac8bdb21f 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -797,6 +797,10 @@ static int get_canonical_dev_path(const char *dev_path, char *canonical) if (ret) goto out; resolved_path = d_path(&path, path_buf, PATH_MAX); + if (IS_ERR(resolved_path)) { + ret = PTR_ERR(resolved_path); + goto out; + } ret = strscpy(canonical, resolved_path, PATH_MAX); out: kfree(path_buf); diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index 47dc96dfe386..16e198a26339 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -64,22 +64,13 @@ const struct file_operations *debugfs_real_fops(const struct file *filp) } EXPORT_SYMBOL_GPL(debugfs_real_fops); -/** - * debugfs_file_get - mark the beginning of file data access - * @dentry: the dentry object whose data is being accessed. - * - * Up to a matching call to debugfs_file_put(), any successive call - * into the file removing functions debugfs_remove() and - * debugfs_remove_recursive() will block. Since associated private - * file data may only get freed after a successful return of any of - * the removal functions, you may safely access it after a successful - * call to debugfs_file_get() without worrying about lifetime issues. - * - * If -%EIO is returned, the file has already been removed and thus, - * it is not safe to access any of its data. If, on the other hand, - * it is allowed to access the file data, zero is returned. - */ -int debugfs_file_get(struct dentry *dentry) +enum dbgfs_get_mode { + DBGFS_GET_ALREADY, + DBGFS_GET_REGULAR, + DBGFS_GET_SHORT, +}; + +static int __debugfs_file_get(struct dentry *dentry, enum dbgfs_get_mode mode) { struct debugfs_fsdata *fsd; void *d_fsd; @@ -96,15 +87,17 @@ int debugfs_file_get(struct dentry *dentry) if (!((unsigned long)d_fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT)) { fsd = d_fsd; } else { + if (WARN_ON(mode == DBGFS_GET_ALREADY)) + return -EINVAL; + fsd = kmalloc(sizeof(*fsd), GFP_KERNEL); if (!fsd) return -ENOMEM; - if ((unsigned long)d_fsd & DEBUGFS_FSDATA_IS_SHORT_FOPS_BIT) { + if (mode == DBGFS_GET_SHORT) { fsd->real_fops = NULL; fsd->short_fops = (void *)((unsigned long)d_fsd & - ~(DEBUGFS_FSDATA_IS_REAL_FOPS_BIT | - DEBUGFS_FSDATA_IS_SHORT_FOPS_BIT)); + ~DEBUGFS_FSDATA_IS_REAL_FOPS_BIT); } else { fsd->real_fops = (void *)((unsigned long)d_fsd & ~DEBUGFS_FSDATA_IS_REAL_FOPS_BIT); @@ -138,6 +131,26 @@ int debugfs_file_get(struct dentry *dentry) return 0; } + +/** + * debugfs_file_get - mark the beginning of file data access + * @dentry: the dentry object whose data is being accessed. + * + * Up to a matching call to debugfs_file_put(), any successive call + * into the file removing functions debugfs_remove() and + * debugfs_remove_recursive() will block. Since associated private + * file data may only get freed after a successful return of any of + * the removal functions, you may safely access it after a successful + * call to debugfs_file_get() without worrying about lifetime issues. + * + * If -%EIO is returned, the file has already been removed and thus, + * it is not safe to access any of its data. If, on the other hand, + * it is allowed to access the file data, zero is returned. + */ +int debugfs_file_get(struct dentry *dentry) +{ + return __debugfs_file_get(dentry, DBGFS_GET_ALREADY); +} EXPORT_SYMBOL_GPL(debugfs_file_get); /** @@ -267,7 +280,7 @@ static int open_proxy_open(struct inode *inode, struct file *filp) const struct file_operations *real_fops = NULL; int r; - r = debugfs_file_get(dentry); + r = __debugfs_file_get(dentry, DBGFS_GET_REGULAR); if (r) return r == -EIO ? -ENOENT : r; @@ -424,7 +437,8 @@ static void __full_proxy_fops_init(struct file_operations *proxy_fops, proxy_fops->unlocked_ioctl = full_proxy_unlocked_ioctl; } -static int full_proxy_open(struct inode *inode, struct file *filp) +static int full_proxy_open(struct inode *inode, struct file *filp, + enum dbgfs_get_mode mode) { struct dentry *dentry = F_DENTRY(filp); const struct file_operations *real_fops; @@ -432,7 +446,7 @@ static int full_proxy_open(struct inode *inode, struct file *filp) struct debugfs_fsdata *fsd; int r; - r = debugfs_file_get(dentry); + r = __debugfs_file_get(dentry, mode); if (r) return r == -EIO ? -ENOENT : r; @@ -491,8 +505,22 @@ out: return r; } +static int full_proxy_open_regular(struct inode *inode, struct file *filp) +{ + return full_proxy_open(inode, filp, DBGFS_GET_REGULAR); +} + const struct file_operations debugfs_full_proxy_file_operations = { - .open = full_proxy_open, + .open = full_proxy_open_regular, +}; + +static int full_proxy_open_short(struct inode *inode, struct file *filp) +{ + return full_proxy_open(inode, filp, DBGFS_GET_SHORT); +} + +const struct file_operations debugfs_full_short_proxy_file_operations = { + .open = full_proxy_open_short, }; ssize_t debugfs_attr_read(struct file *file, char __user *buf, diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 38a9c7eb97e6..e752009de929 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -229,7 +229,7 @@ static void debugfs_release_dentry(struct dentry *dentry) return; /* check it wasn't a dir (no fsdata) or automount (no real_fops) */ - if (fsd && fsd->real_fops) { + if (fsd && (fsd->real_fops || fsd->short_fops)) { WARN_ON(!list_empty(&fsd->cancellations)); mutex_destroy(&fsd->cancellations_mtx); } @@ -455,8 +455,7 @@ struct dentry *debugfs_create_file_full(const char *name, umode_t mode, const struct file_operations *fops) { if (WARN_ON((unsigned long)fops & - (DEBUGFS_FSDATA_IS_SHORT_FOPS_BIT | - DEBUGFS_FSDATA_IS_REAL_FOPS_BIT))) + DEBUGFS_FSDATA_IS_REAL_FOPS_BIT)) return ERR_PTR(-EINVAL); return __debugfs_create_file(name, mode, parent, data, @@ -471,15 +470,13 @@ struct dentry *debugfs_create_file_short(const char *name, umode_t mode, const struct debugfs_short_fops *fops) { if (WARN_ON((unsigned long)fops & - (DEBUGFS_FSDATA_IS_SHORT_FOPS_BIT | - DEBUGFS_FSDATA_IS_REAL_FOPS_BIT))) + DEBUGFS_FSDATA_IS_REAL_FOPS_BIT)) return ERR_PTR(-EINVAL); return __debugfs_create_file(name, mode, parent, data, - fops ? &debugfs_full_proxy_file_operations : + fops ? &debugfs_full_short_proxy_file_operations : &debugfs_noop_file_operations, - (const void *)((unsigned long)fops | - DEBUGFS_FSDATA_IS_SHORT_FOPS_BIT)); + fops); } EXPORT_SYMBOL_GPL(debugfs_create_file_short); diff --git a/fs/debugfs/internal.h b/fs/debugfs/internal.h index a3edfa4f0d8e..bbae4a228ef4 100644 --- a/fs/debugfs/internal.h +++ b/fs/debugfs/internal.h @@ -15,6 +15,7 @@ struct file_operations; extern const struct file_operations debugfs_noop_file_operations; extern const struct file_operations debugfs_open_proxy_file_operations; extern const struct file_operations debugfs_full_proxy_file_operations; +extern const struct file_operations debugfs_full_short_proxy_file_operations; struct debugfs_fsdata { const struct file_operations *real_fops; @@ -40,11 +41,6 @@ struct debugfs_fsdata { * pointer gets its lowest bit set. */ #define DEBUGFS_FSDATA_IS_REAL_FOPS_BIT BIT(0) -/* - * A dentry's ->d_fsdata, when pointing to real fops, is with - * short fops instead of full fops. - */ -#define DEBUGFS_FSDATA_IS_SHORT_FOPS_BIT BIT(1) /* Access BITS */ #define DEBUGFS_ALLOW_API BIT(0) diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 88d0946b5bc9..7d92a5479998 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1541,8 +1541,10 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii, */ struct page **pages = kzalloc(max_pages * sizeof(struct page *), GFP_KERNEL); - if (!pages) - return -ENOMEM; + if (!pages) { + ret = -ENOMEM; + goto out; + } while (nbytes < *nbytesp && nr_pages < max_pages) { unsigned nfolios, i; @@ -1557,18 +1559,22 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii, nbytes += ret; - ret += start; - /* Currently, all folios in FUSE are one page */ - nfolios = DIV_ROUND_UP(ret, PAGE_SIZE); + nfolios = DIV_ROUND_UP(ret + start, PAGE_SIZE); + + for (i = 0; i < nfolios; i++) { + struct folio *folio = page_folio(pages[i]); + unsigned int offset = start + + (folio_page_idx(folio, pages[i]) << PAGE_SHIFT); + unsigned int len = min_t(unsigned int, ret, PAGE_SIZE - start); - ap->descs[ap->num_folios].offset = start; - fuse_folio_descs_length_init(ap->descs, ap->num_folios, nfolios); - for (i = 0; i < nfolios; i++) - ap->folios[i + ap->num_folios] = page_folio(pages[i]); + ap->descs[ap->num_folios].offset = offset; + ap->descs[ap->num_folios].length = len; + ap->folios[ap->num_folios] = folio; + start = 0; + ret -= len; + ap->num_folios++; + } - ap->num_folios += nfolios; - ap->descs[ap->num_folios - 1].length -= - (PAGE_SIZE - ret) & (PAGE_SIZE - 1); nr_pages += nfolios; } kfree(pages); @@ -1584,6 +1590,7 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii, else ap->args.out_pages = true; +out: *nbytesp = nbytes; return ret < 0 ? ret : 0; diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 54dc27d92781..d303e6c8900c 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -1138,7 +1138,7 @@ static void iomap_write_delalloc_scan(struct inode *inode, start_byte, end_byte, iomap, punch); /* move offset to start of next folio in range */ - start_byte = folio_next_index(folio) << PAGE_SHIFT; + start_byte = folio_pos(folio) + folio_size(folio); folio_unlock(folio); folio_put(folio); } diff --git a/fs/mount.h b/fs/mount.h index 185fc56afc13..179f690a0c72 100644 --- a/fs/mount.h +++ b/fs/mount.h @@ -38,6 +38,7 @@ struct mount { struct dentry *mnt_mountpoint; struct vfsmount mnt; union { + struct rb_node mnt_node; /* node in the ns->mounts rbtree */ struct rcu_head mnt_rcu; struct llist_node mnt_llist; }; @@ -51,10 +52,7 @@ struct mount { struct list_head mnt_child; /* and going through their mnt_child */ struct list_head mnt_instance; /* mount instance on sb->s_mounts */ const char *mnt_devname; /* Name of device e.g. /dev/dsk/hda1 */ - union { - struct rb_node mnt_node; /* Under ns->mounts */ - struct list_head mnt_list; - }; + struct list_head mnt_list; struct list_head mnt_expire; /* link in fs-specific expiry list */ struct list_head mnt_share; /* circular list of shared mounts */ struct list_head mnt_slave_list;/* list of slave mounts */ @@ -145,11 +143,16 @@ static inline bool is_anon_ns(struct mnt_namespace *ns) return ns->seq == 0; } +static inline bool mnt_ns_attached(const struct mount *mnt) +{ + return !RB_EMPTY_NODE(&mnt->mnt_node); +} + static inline void move_from_ns(struct mount *mnt, struct list_head *dt_list) { - WARN_ON(!(mnt->mnt.mnt_flags & MNT_ONRB)); - mnt->mnt.mnt_flags &= ~MNT_ONRB; + WARN_ON(!mnt_ns_attached(mnt)); rb_erase(&mnt->mnt_node, &mnt->mnt_ns->mounts); + RB_CLEAR_NODE(&mnt->mnt_node); list_add_tail(&mnt->mnt_list, dt_list); } diff --git a/fs/namespace.c b/fs/namespace.c index 6eec7794f707..eac057e56948 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -344,6 +344,7 @@ static struct mount *alloc_vfsmnt(const char *name) INIT_HLIST_NODE(&mnt->mnt_mp_list); INIT_LIST_HEAD(&mnt->mnt_umounting); INIT_HLIST_HEAD(&mnt->mnt_stuck_children); + RB_CLEAR_NODE(&mnt->mnt_node); mnt->mnt.mnt_idmap = &nop_mnt_idmap; } return mnt; @@ -1124,7 +1125,7 @@ static void mnt_add_to_ns(struct mnt_namespace *ns, struct mount *mnt) struct rb_node **link = &ns->mounts.rb_node; struct rb_node *parent = NULL; - WARN_ON(mnt->mnt.mnt_flags & MNT_ONRB); + WARN_ON(mnt_ns_attached(mnt)); mnt->mnt_ns = ns; while (*link) { parent = *link; @@ -1135,7 +1136,6 @@ static void mnt_add_to_ns(struct mnt_namespace *ns, struct mount *mnt) } rb_link_node(&mnt->mnt_node, parent, link); rb_insert_color(&mnt->mnt_node, &ns->mounts); - mnt->mnt.mnt_flags |= MNT_ONRB; } /* @@ -1305,7 +1305,7 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root, } mnt->mnt.mnt_flags = old->mnt.mnt_flags; - mnt->mnt.mnt_flags &= ~(MNT_WRITE_HOLD|MNT_MARKED|MNT_INTERNAL|MNT_ONRB); + mnt->mnt.mnt_flags &= ~(MNT_WRITE_HOLD|MNT_MARKED|MNT_INTERNAL); atomic_inc(&sb->s_active); mnt->mnt.mnt_idmap = mnt_idmap_get(mnt_idmap(&old->mnt)); @@ -1763,7 +1763,7 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how) /* Gather the mounts to umount */ for (p = mnt; p; p = next_mnt(p, mnt)) { p->mnt.mnt_flags |= MNT_UMOUNT; - if (p->mnt.mnt_flags & MNT_ONRB) + if (mnt_ns_attached(p)) move_from_ns(p, &tmp_list); else list_move(&p->mnt_list, &tmp_list); @@ -1912,16 +1912,14 @@ static int do_umount(struct mount *mnt, int flags) event++; if (flags & MNT_DETACH) { - if (mnt->mnt.mnt_flags & MNT_ONRB || - !list_empty(&mnt->mnt_list)) + if (mnt_ns_attached(mnt) || !list_empty(&mnt->mnt_list)) umount_tree(mnt, UMOUNT_PROPAGATE); retval = 0; } else { shrink_submounts(mnt); retval = -EBUSY; if (!propagate_mount_busy(mnt, 2)) { - if (mnt->mnt.mnt_flags & MNT_ONRB || - !list_empty(&mnt->mnt_list)) + if (mnt_ns_attached(mnt) || !list_empty(&mnt->mnt_list)) umount_tree(mnt, UMOUNT_PROPAGATE|UMOUNT_SYNC); retval = 0; } diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c index 173e8b5e6a93..f9421f3e6d37 100644 --- a/fs/netfs/direct_write.c +++ b/fs/netfs/direct_write.c @@ -67,7 +67,7 @@ ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter * * allocate a sufficiently large bvec array and may shorten the * request. */ - if (async || user_backed_iter(iter)) { + if (user_backed_iter(iter)) { n = netfs_extract_user_iter(iter, len, &wreq->iter, 0); if (n < 0) { ret = n; @@ -77,6 +77,11 @@ ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter * wreq->direct_bv_count = n; wreq->direct_bv_unpin = iov_iter_extract_will_pin(iter); } else { + /* If this is a kernel-generated async DIO request, + * assume that any resources the iterator points to + * (eg. a bio_vec array) will persist till the end of + * the op. + */ wreq->iter = *iter; } diff --git a/fs/netfs/read_retry.c b/fs/netfs/read_retry.c index 21b4a54e545e..16b676c68dcd 100644 --- a/fs/netfs/read_retry.c +++ b/fs/netfs/read_retry.c @@ -152,7 +152,8 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) BUG_ON(!len); /* Renegotiate max_len (rsize) */ - if (rreq->netfs_ops->prepare_read(subreq) < 0) { + if (rreq->netfs_ops->prepare_read && + rreq->netfs_ops->prepare_read(subreq) < 0) { trace_netfs_sreq(subreq, netfs_sreq_trace_reprep_failed); __set_bit(NETFS_SREQ_FAILED, &subreq->flags); } diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index 3d8a82cee63e..658bf199d424 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -404,6 +404,8 @@ static ssize_t __read_vmcore(struct iov_iter *iter, loff_t *fpos) if (!iov_iter_count(iter)) return acc; } + + cond_resched(); } return acc; diff --git a/fs/smb/client/namespace.c b/fs/smb/client/namespace.c index 0f788031b740..e3f9213131c4 100644 --- a/fs/smb/client/namespace.c +++ b/fs/smb/client/namespace.c @@ -196,11 +196,28 @@ static struct vfsmount *cifs_do_automount(struct path *path) struct smb3_fs_context tmp; char *full_path; struct vfsmount *mnt; + struct cifs_sb_info *mntpt_sb; + struct cifs_ses *ses; if (IS_ROOT(mntpt)) return ERR_PTR(-ESTALE); - cur_ctx = CIFS_SB(mntpt->d_sb)->ctx; + mntpt_sb = CIFS_SB(mntpt->d_sb); + ses = cifs_sb_master_tcon(mntpt_sb)->ses; + cur_ctx = mntpt_sb->ctx; + + /* + * At this point, the root session should be in the mntpt sb. We should + * bring the sb context passwords in sync with the root session's + * passwords. This would help prevent unnecessary retries and password + * swaps for automounts. + */ + mutex_lock(&ses->session_mutex); + rc = smb3_sync_session_ctx_passwords(mntpt_sb, ses); + mutex_unlock(&ses->session_mutex); + + if (rc) + return ERR_PTR(rc); fc = fs_context_for_submount(path->mnt->mnt_sb->s_type, mntpt); if (IS_ERR(fc)) diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 23e21845f928..772deec5b90f 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -695,6 +695,9 @@ void smb2_send_interim_resp(struct ksmbd_work *work, __le32 status) struct smb2_hdr *rsp_hdr; struct ksmbd_work *in_work = ksmbd_alloc_work_struct(); + if (!in_work) + return; + if (allocate_interim_rsp_buf(in_work)) { pr_err("smb_allocate_rsp_buf failed!\n"); ksmbd_free_work_struct(in_work); @@ -3991,6 +3994,26 @@ static int smb2_populate_readdir_entry(struct ksmbd_conn *conn, int info_level, posix_info->DeviceId = cpu_to_le32(ksmbd_kstat->kstat->rdev); posix_info->HardLinks = cpu_to_le32(ksmbd_kstat->kstat->nlink); posix_info->Mode = cpu_to_le32(ksmbd_kstat->kstat->mode & 0777); + switch (ksmbd_kstat->kstat->mode & S_IFMT) { + case S_IFDIR: + posix_info->Mode |= cpu_to_le32(POSIX_TYPE_DIR << POSIX_FILETYPE_SHIFT); + break; + case S_IFLNK: + posix_info->Mode |= cpu_to_le32(POSIX_TYPE_SYMLINK << POSIX_FILETYPE_SHIFT); + break; + case S_IFCHR: + posix_info->Mode |= cpu_to_le32(POSIX_TYPE_CHARDEV << POSIX_FILETYPE_SHIFT); + break; + case S_IFBLK: + posix_info->Mode |= cpu_to_le32(POSIX_TYPE_BLKDEV << POSIX_FILETYPE_SHIFT); + break; + case S_IFIFO: + posix_info->Mode |= cpu_to_le32(POSIX_TYPE_FIFO << POSIX_FILETYPE_SHIFT); + break; + case S_IFSOCK: + posix_info->Mode |= cpu_to_le32(POSIX_TYPE_SOCKET << POSIX_FILETYPE_SHIFT); + } + posix_info->Inode = cpu_to_le64(ksmbd_kstat->kstat->ino); posix_info->DosAttributes = S_ISDIR(ksmbd_kstat->kstat->mode) ? @@ -5181,6 +5204,26 @@ static int find_file_posix_info(struct smb2_query_info_rsp *rsp, file_info->AllocationSize = cpu_to_le64(stat.blocks << 9); file_info->HardLinks = cpu_to_le32(stat.nlink); file_info->Mode = cpu_to_le32(stat.mode & 0777); + switch (stat.mode & S_IFMT) { + case S_IFDIR: + file_info->Mode |= cpu_to_le32(POSIX_TYPE_DIR << POSIX_FILETYPE_SHIFT); + break; + case S_IFLNK: + file_info->Mode |= cpu_to_le32(POSIX_TYPE_SYMLINK << POSIX_FILETYPE_SHIFT); + break; + case S_IFCHR: + file_info->Mode |= cpu_to_le32(POSIX_TYPE_CHARDEV << POSIX_FILETYPE_SHIFT); + break; + case S_IFBLK: + file_info->Mode |= cpu_to_le32(POSIX_TYPE_BLKDEV << POSIX_FILETYPE_SHIFT); + break; + case S_IFIFO: + file_info->Mode |= cpu_to_le32(POSIX_TYPE_FIFO << POSIX_FILETYPE_SHIFT); + break; + case S_IFSOCK: + file_info->Mode |= cpu_to_le32(POSIX_TYPE_SOCKET << POSIX_FILETYPE_SHIFT); + } + file_info->DeviceId = cpu_to_le32(stat.rdev); /* diff --git a/fs/smb/server/smb2pdu.h b/fs/smb/server/smb2pdu.h index 649dacf7e8c4..17a0b18a8406 100644 --- a/fs/smb/server/smb2pdu.h +++ b/fs/smb/server/smb2pdu.h @@ -502,4 +502,14 @@ static inline void *smb2_get_msg(void *buf) return buf + 4; } +#define POSIX_TYPE_FILE 0 +#define POSIX_TYPE_DIR 1 +#define POSIX_TYPE_SYMLINK 2 +#define POSIX_TYPE_CHARDEV 3 +#define POSIX_TYPE_BLKDEV 4 +#define POSIX_TYPE_FIFO 5 +#define POSIX_TYPE_SOCKET 6 + +#define POSIX_FILETYPE_SHIFT 12 + #endif /* _SMB2PDU_H */ diff --git a/fs/smb/server/transport_rdma.c b/fs/smb/server/transport_rdma.c index 0ef3c9f0bfeb..c3785a5434f9 100644 --- a/fs/smb/server/transport_rdma.c +++ b/fs/smb/server/transport_rdma.c @@ -2283,8 +2283,7 @@ out: ibdev = ib_device_get_by_netdev(netdev, RDMA_DRIVER_UNKNOWN); if (ibdev) { - if (rdma_frwr_is_supported(&ibdev->attrs)) - rdma_capable = true; + rdma_capable = rdma_frwr_is_supported(&ibdev->attrs); ib_device_put(ibdev); } } diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c index 88d167a5f8b7..40f08eac519c 100644 --- a/fs/smb/server/vfs.c +++ b/fs/smb/server/vfs.c @@ -1264,6 +1264,8 @@ int ksmbd_vfs_kern_path_locked(struct ksmbd_work *work, char *name, filepath, flags, path); + if (!is_last) + next[0] = '/'; if (err) goto out2; else if (is_last) @@ -1271,7 +1273,6 @@ int ksmbd_vfs_kern_path_locked(struct ksmbd_work *work, char *name, path_put(parent_path); *parent_path = *path; - next[0] = '/'; remain_len -= filename_len + 1; } diff --git a/fs/xfs/libxfs/xfs_rtgroup.h b/fs/xfs/libxfs/xfs_rtgroup.h index 7e7e491ff06f..2d7822644eff 100644 --- a/fs/xfs/libxfs/xfs_rtgroup.h +++ b/fs/xfs/libxfs/xfs_rtgroup.h @@ -272,7 +272,7 @@ static inline int xfs_initialize_rtgroups(struct xfs_mount *mp, } # define xfs_rtgroup_extents(mp, rgno) (0) -# define xfs_update_last_rtgroup_size(mp, rgno) (-EOPNOTSUPP) +# define xfs_update_last_rtgroup_size(mp, rgno) (0) # define xfs_rtgroup_lock(rtg, gf) ((void)0) # define xfs_rtgroup_unlock(rtg, gf) ((void)0) # define xfs_rtgroup_trans_join(tp, rtg, gf) ((void)0) diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index f11d475898f2..201c26322ede 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -87,8 +87,9 @@ xfs_dquot_detach_buf( } spin_unlock(&qlip->qli_lock); if (bp) { + xfs_buf_lock(bp); list_del_init(&qlip->qli_item.li_bio_list); - xfs_buf_rele(bp); + xfs_buf_relse(bp); } } diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h index e61dd7dd2286..147bd3ee4f7b 100644 --- a/include/kvm/arm_pmu.h +++ b/include/kvm/arm_pmu.h @@ -53,8 +53,7 @@ u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1); void kvm_pmu_vcpu_init(struct kvm_vcpu *vcpu); void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu); void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu); -void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val); -void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val); +void kvm_pmu_reprogram_counter_mask(struct kvm_vcpu *vcpu, u64 val); void kvm_pmu_flush_hwstate(struct kvm_vcpu *vcpu); void kvm_pmu_sync_hwstate(struct kvm_vcpu *vcpu); bool kvm_pmu_should_notify_user(struct kvm_vcpu *vcpu); @@ -127,8 +126,7 @@ static inline u64 kvm_pmu_accessible_counter_mask(struct kvm_vcpu *vcpu) static inline void kvm_pmu_vcpu_init(struct kvm_vcpu *vcpu) {} static inline void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu) {} static inline void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu) {} -static inline void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val) {} -static inline void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val) {} +static inline void kvm_pmu_reprogram_counter_mask(struct kvm_vcpu *vcpu, u64 val) {} static inline void kvm_pmu_flush_hwstate(struct kvm_vcpu *vcpu) {} static inline void kvm_pmu_sync_hwstate(struct kvm_vcpu *vcpu) {} static inline bool kvm_pmu_should_notify_user(struct kvm_vcpu *vcpu) diff --git a/include/linux/bus/stm32_firewall_device.h b/include/linux/bus/stm32_firewall_device.h index 18e0a2fc3816..5178b72bc920 100644 --- a/include/linux/bus/stm32_firewall_device.h +++ b/include/linux/bus/stm32_firewall_device.h @@ -115,7 +115,7 @@ void stm32_firewall_release_access_by_id(struct stm32_firewall *firewall, u32 su #else /* CONFIG_STM32_FIREWALL */ int stm32_firewall_get_firewall(struct device_node *np, struct stm32_firewall *firewall, - unsigned int nb_firewall); + unsigned int nb_firewall) { return -ENODEV; } diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index f711bfd75c4d..64301ddf2f59 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -78,6 +78,9 @@ enum { * @cqe_size: Size of TX/RX completion queue event * @tx_push_buf_len: Size of TX push buffer * @tx_push_buf_max_len: Maximum allowed size of TX push buffer + * @hds_thresh: Packet size threshold for header data split (HDS) + * @hds_thresh_max: Maximum supported setting for @hds_threshold + * */ struct kernel_ethtool_ringparam { u32 rx_buf_len; @@ -87,6 +90,8 @@ struct kernel_ethtool_ringparam { u32 cqe_size; u32 tx_push_buf_len; u32 tx_push_buf_max_len; + u32 hds_thresh; + u32 hds_thresh_max; }; /** @@ -97,6 +102,7 @@ struct kernel_ethtool_ringparam { * @ETHTOOL_RING_USE_RX_PUSH: capture for setting rx_push * @ETHTOOL_RING_USE_TX_PUSH_BUF_LEN: capture for setting tx_push_buf_len * @ETHTOOL_RING_USE_TCP_DATA_SPLIT: capture for setting tcp_data_split + * @ETHTOOL_RING_USE_HDS_THRS: capture for setting header-data-split-thresh */ enum ethtool_supported_ring_param { ETHTOOL_RING_USE_RX_BUF_LEN = BIT(0), @@ -105,6 +111,7 @@ enum ethtool_supported_ring_param { ETHTOOL_RING_USE_RX_PUSH = BIT(3), ETHTOOL_RING_USE_TX_PUSH_BUF_LEN = BIT(4), ETHTOOL_RING_USE_TCP_DATA_SPLIT = BIT(5), + ETHTOOL_RING_USE_HDS_THRS = BIT(6), }; #define __ETH_RSS_HASH_BIT(bit) ((u32)1 << (bit)) @@ -412,6 +419,29 @@ struct ethtool_eth_phy_stats { ); }; +/** + * struct ethtool_phy_stats - PHY-level statistics counters + * @rx_packets: Total successfully received frames + * @rx_bytes: Total successfully received bytes + * @rx_errors: Total received frames with errors (e.g., CRC errors) + * @tx_packets: Total successfully transmitted frames + * @tx_bytes: Total successfully transmitted bytes + * @tx_errors: Total transmitted frames with errors + * + * This structure provides a standardized interface for reporting + * PHY-level statistics counters. It is designed to expose statistics + * commonly provided by PHYs but not explicitly defined in the IEEE + * 802.3 standard. + */ +struct ethtool_phy_stats { + u64 rx_packets; + u64 rx_bytes; + u64 rx_errors; + u64 tx_packets; + u64 tx_bytes; + u64 tx_errors; +}; + /* Basic IEEE 802.3 MAC Ctrl statistics (30.3.3.*), not otherwise exposed * via a more targeted API. */ @@ -529,6 +559,12 @@ struct ethtool_rmon_stats { /** * struct ethtool_ts_stats - HW timestamping statistics * @pkts: Number of packets successfully timestamped by the hardware. + * @onestep_pkts_unconfirmed: Number of PTP packets with one-step TX + * timestamping that were sent, but for which the + * device offers no confirmation whether they made + * it onto the wire and the timestamp was inserted + * in the originTimestamp or correctionField, or + * not. * @lost: Number of hardware timestamping requests where the timestamping * information from the hardware never arrived for submission with * the skb. @@ -541,6 +577,7 @@ struct ethtool_rmon_stats { struct ethtool_ts_stats { struct_group(tx_stats, u64 pkts; + u64 onestep_pkts_unconfirmed; u64 lost; u64 err; ); @@ -1134,12 +1171,16 @@ int ethtool_virtdev_set_link_ksettings(struct net_device *dev, * @rss_ctx: XArray of custom RSS contexts * @rss_lock: Protects entries in @rss_ctx. May be taken from * within RTNL. + * @hds_thresh: HDS Threshold value. + * @hds_config: HDS value from userspace. * @wol_enabled: Wake-on-LAN is enabled * @module_fw_flash_in_progress: Module firmware flashing is in progress. */ struct ethtool_netdev_state { struct xarray rss_ctx; struct mutex rss_lock; + u32 hds_thresh; + u8 hds_config; unsigned wol_enabled:1; unsigned module_fw_flash_in_progress:1; }; @@ -1303,24 +1344,4 @@ struct ethtool_forced_speed_map { void ethtool_forced_speed_maps_init(struct ethtool_forced_speed_map *maps, u32 size); - -/* C33 PSE extended state and substate. */ -struct ethtool_c33_pse_ext_state_info { - enum ethtool_c33_pse_ext_state c33_pse_ext_state; - union { - enum ethtool_c33_pse_ext_substate_error_condition error_condition; - enum ethtool_c33_pse_ext_substate_mr_pse_enable mr_pse_enable; - enum ethtool_c33_pse_ext_substate_option_detect_ted option_detect_ted; - enum ethtool_c33_pse_ext_substate_option_vport_lim option_vport_lim; - enum ethtool_c33_pse_ext_substate_ovld_detected ovld_detected; - enum ethtool_c33_pse_ext_substate_power_not_available power_not_available; - enum ethtool_c33_pse_ext_substate_short_detected short_detected; - u32 __c33_pse_ext_substate; - }; -}; - -struct ethtool_c33_pse_pw_limit_range { - u32 min; - u32 max; -}; #endif /* _LINUX_ETHTOOL_H */ diff --git a/include/linux/if_hsr.h b/include/linux/if_hsr.h index 0404f5bf4f30..d7941fd88032 100644 --- a/include/linux/if_hsr.h +++ b/include/linux/if_hsr.h @@ -13,6 +13,15 @@ enum hsr_version { PRP_V1, }; +enum hsr_port_type { + HSR_PT_NONE = 0, /* Must be 0, used by framereg */ + HSR_PT_SLAVE_A, + HSR_PT_SLAVE_B, + HSR_PT_INTERLINK, + HSR_PT_MASTER, + HSR_PT_PORTS, /* This must be the last item in the enum */ +}; + /* HSR Tag. * As defined in IEC-62439-3:2010, the HSR tag is really { ethertype = 0x88FB, * path, LSDU_size, sequence Nr }. But we let eth_header() create { h_dest, @@ -32,6 +41,8 @@ struct hsr_tag { #if IS_ENABLED(CONFIG_HSR) extern bool is_hsr_master(struct net_device *dev); extern int hsr_get_version(struct net_device *dev, enum hsr_version *ver); +struct net_device *hsr_get_port_ndev(struct net_device *ndev, + enum hsr_port_type pt); #else static inline bool is_hsr_master(struct net_device *dev) { @@ -42,6 +53,12 @@ static inline int hsr_get_version(struct net_device *dev, { return -EINVAL; } + +static inline struct net_device *hsr_get_port_ndev(struct net_device *ndev, + enum hsr_port_type pt) +{ + return ERR_PTR(-EINVAL); +} #endif /* CONFIG_HSR */ #endif /*_LINUX_IF_HSR_H_*/ diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index cc647992f3d1..0c48b20f818a 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1245,6 +1245,7 @@ enum mlx5_cap_type { MLX5_CAP_DEV_EVENT = 0x14, MLX5_CAP_IPSEC, MLX5_CAP_CRYPTO = 0x1a, + MLX5_CAP_SHAMPO = 0x1d, MLX5_CAP_MACSEC = 0x1f, MLX5_CAP_GENERAL_2 = 0x20, MLX5_CAP_PORT_SELECTION = 0x25, @@ -1470,6 +1471,9 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_MACSEC(mdev, cap)\ MLX5_GET(macsec_cap, (mdev)->caps.hca[MLX5_CAP_MACSEC]->cur, cap) +#define MLX5_CAP_SHAMPO(mdev, cap) \ + MLX5_GET(shampo_cap, mdev->caps.hca[MLX5_CAP_SHAMPO]->cur, cap) + enum { MLX5_CMD_STAT_OK = 0x0, MLX5_CMD_STAT_INT_ERR = 0x1, diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index fed666c5bd16..af86097641b0 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -160,9 +160,12 @@ enum { MLX5_REG_MIRC = 0x9162, MLX5_REG_MTPTM = 0x9180, MLX5_REG_MTCTR = 0x9181, + MLX5_REG_MRTCQ = 0x9182, MLX5_REG_SBCAM = 0xB01F, MLX5_REG_RESOURCE_DUMP = 0xC000, + MLX5_REG_NIC_CAP = 0xC00D, MLX5_REG_DTOR = 0xC00E, + MLX5_REG_VHCA_ICM_CTRL = 0xC010, }; enum mlx5_qpts_trust_state { diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 370f533da107..4f3716e124c9 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1830,7 +1830,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 regexp_params[0x1]; u8 uar_sz[0x6]; u8 port_selection_cap[0x1]; - u8 reserved_at_251[0x1]; + u8 nic_cap_reg[0x1]; u8 umem_uid_0[0x1]; u8 reserved_at_253[0x5]; u8 log_pg_sz[0x8]; @@ -2329,7 +2329,9 @@ struct mlx5_ifc_wq_bits { u8 headers_mkey[0x20]; u8 shampo_enable[0x1]; - u8 reserved_at_1e1[0x4]; + u8 reserved_at_1e1[0x1]; + u8 shampo_mode[0x2]; + u8 reserved_at_1e4[0x1]; u8 log_reservation_size[0x3]; u8 reserved_at_1e8[0x5]; u8 log_max_num_of_packets_per_reservation[0x3]; @@ -3327,6 +3329,14 @@ struct mlx5_ifc_dropped_packet_logged_bits { u8 reserved_at_0[0xe0]; }; +struct mlx5_ifc_nic_cap_reg_bits { + u8 reserved_at_0[0x1a]; + u8 vhca_icm_ctrl[0x1]; + u8 reserved_at_1b[0x5]; + + u8 reserved_at_20[0x60]; +}; + struct mlx5_ifc_default_timeout_bits { u8 to_multiplier[0x3]; u8 reserved_at_3[0x9]; @@ -3363,6 +3373,18 @@ struct mlx5_ifc_dtor_reg_bits { u8 reserved_at_1c0[0x20]; }; +struct mlx5_ifc_vhca_icm_ctrl_reg_bits { + u8 vhca_id_valid[0x1]; + u8 reserved_at_1[0xf]; + u8 vhca_id[0x10]; + + u8 reserved_at_20[0xa0]; + + u8 cur_alloc_icm[0x20]; + + u8 reserved_at_e0[0x120]; +}; + enum { MLX5_CQ_ERROR_SYNDROME_CQ_OVERRUN = 0x1, MLX5_CQ_ERROR_SYNDROME_CQ_ACCESS_VIOLATION_ERROR = 0x2, @@ -3701,6 +3723,22 @@ struct mlx5_ifc_crypto_cap_bits { u8 reserved_at_80[0x780]; }; +struct mlx5_ifc_shampo_cap_bits { + u8 reserved_at_0[0x3]; + u8 shampo_log_max_reservation_size[0x5]; + u8 reserved_at_8[0x3]; + u8 shampo_log_min_reservation_size[0x5]; + u8 shampo_min_mss_size[0x10]; + + u8 shampo_header_split[0x1]; + u8 shampo_header_split_data_merge[0x1]; + u8 reserved_at_22[0x1]; + u8 shampo_log_max_headers_entry_size[0x5]; + u8 reserved_at_28[0x18]; + + u8 reserved_at_40[0x7c0]; +}; + union mlx5_ifc_hca_cap_union_bits { struct mlx5_ifc_cmd_hca_cap_bits cmd_hca_cap; struct mlx5_ifc_cmd_hca_cap_2_bits cmd_hca_cap_2; @@ -7025,6 +7063,7 @@ struct mlx5_ifc_alloc_packet_reformat_context_out_bits { enum { MLX5_REFORMAT_CONTEXT_ANCHOR_MAC_START = 0x1, + MLX5_REFORMAT_CONTEXT_ANCHOR_VLAN_START = 0x2, MLX5_REFORMAT_CONTEXT_ANCHOR_IP_START = 0x7, MLX5_REFORMAT_CONTEXT_ANCHOR_TCP_UDP_START = 0x9, }; @@ -10152,7 +10191,21 @@ struct mlx5_ifc_pplm_reg_bits { u8 fec_override_admin_200g_2x[0x10]; u8 fec_override_admin_100g_1x[0x10]; - u8 reserved_at_260[0x20]; + u8 reserved_at_260[0x60]; + + u8 fec_override_cap_1600g_8x[0x10]; + u8 fec_override_cap_800g_4x[0x10]; + + u8 fec_override_cap_400g_2x[0x10]; + u8 fec_override_cap_200g_1x[0x10]; + + u8 fec_override_admin_1600g_8x[0x10]; + u8 fec_override_admin_800g_4x[0x10]; + + u8 fec_override_admin_400g_2x[0x10]; + u8 fec_override_admin_200g_1x[0x10]; + + u8 reserved_at_340[0x80]; }; struct mlx5_ifc_ppcnt_reg_bits { @@ -10526,7 +10579,9 @@ struct mlx5_ifc_mtutc_reg_bits { }; struct mlx5_ifc_pcam_enhanced_features_bits { - u8 reserved_at_0[0x48]; + u8 reserved_at_0[0x1d]; + u8 fec_200G_per_lane_in_pplm[0x1]; + u8 reserved_at_1e[0x2a]; u8 fec_100G_per_lane_in_pplm[0x1]; u8 reserved_at_49[0x1f]; u8 fec_50G_per_lane_in_pplm[0x1]; @@ -10666,7 +10721,8 @@ struct mlx5_ifc_mcam_access_reg_bits3 { u8 regs_63_to_32[0x20]; - u8 regs_31_to_2[0x1e]; + u8 regs_31_to_3[0x1d]; + u8 mrtcq[0x1]; u8 mtctr[0x1]; u8 mtptm[0x1]; }; @@ -13157,4 +13213,12 @@ struct mlx5_ifc_msees_reg_bits { u8 reserved_at_80[0x180]; }; +struct mlx5_ifc_mrtcq_reg_bits { + u8 reserved_at_0[0x40]; + + u8 rt_clock_identity[0x40]; + + u8 reserved_at_80[0x180]; +}; + #endif /* MLX5_IFC_H */ diff --git a/include/linux/module.h b/include/linux/module.h index 94acbacdcdf1..b3a643435357 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -773,7 +773,8 @@ void *__module_writable_address(struct module *mod, void *loc); static inline void *module_writable_address(struct module *mod, void *loc) { - if (!IS_ENABLED(CONFIG_ARCH_HAS_EXECMEM_ROX) || !mod) + if (!IS_ENABLED(CONFIG_ARCH_HAS_EXECMEM_ROX) || !mod || + mod->state != MODULE_STATE_UNFORMED) return loc; return __module_writable_address(mod, loc); } diff --git a/include/linux/mount.h b/include/linux/mount.h index c34c18b4e8f3..04213d8ef837 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -50,7 +50,7 @@ struct path; #define MNT_ATIME_MASK (MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME ) #define MNT_INTERNAL_FLAGS (MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL | \ - MNT_DOOMED | MNT_SYNC_UMOUNT | MNT_MARKED | MNT_ONRB) + MNT_DOOMED | MNT_SYNC_UMOUNT | MNT_MARKED) #define MNT_INTERNAL 0x4000 @@ -64,7 +64,6 @@ struct path; #define MNT_SYNC_UMOUNT 0x2000000 #define MNT_MARKED 0x4000000 #define MNT_UMOUNT 0x8000000 -#define MNT_ONRB 0x10000000 struct vfsmount { struct dentry *mnt_root; /* root of the mounted tree */ diff --git a/include/linux/mroute_base.h b/include/linux/mroute_base.h index 9dd4bf157255..58a2401e4b55 100644 --- a/include/linux/mroute_base.h +++ b/include/linux/mroute_base.h @@ -146,9 +146,9 @@ struct mr_mfc { unsigned long last_assert; int minvif; int maxvif; - unsigned long bytes; - unsigned long pkt; - unsigned long wrong_if; + atomic_long_t bytes; + atomic_long_t pkt; + atomic_long_t wrong_if; unsigned long lastuse; unsigned char ttls[MAXVIFS]; refcount_t refcount; diff --git a/include/linux/net.h b/include/linux/net.h index b75bc534c1b3..0ff950eecc6b 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -343,8 +343,6 @@ static inline bool sendpages_ok(struct page *page, size_t len, size_t offset) int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t len); -int kernel_sendmsg_locked(struct sock *sk, struct msghdr *msg, - struct kvec *vec, size_t num, size_t len); int kernel_recvmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t len, int flags); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1812564b5204..8308d9c75918 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -382,8 +382,9 @@ struct napi_struct { struct sk_buff *skb; struct list_head rx_list; /* Pending GRO_NORMAL skbs */ int rx_count; /* length of rx_list */ - unsigned int napi_id; + unsigned int napi_id; /* protected by netdev_lock */ struct hrtimer timer; + /* all fields past this point are write-protected by netdev_lock */ struct task_struct *thread; unsigned long gro_flush_timeout; unsigned long irq_suspend_timeout; @@ -570,16 +571,11 @@ static inline bool napi_complete(struct napi_struct *n) int dev_set_threaded(struct net_device *dev, bool threaded); -/** - * napi_disable - prevent NAPI from scheduling - * @n: NAPI context - * - * Stop NAPI from being scheduled on this context. - * Waits till any outstanding processing completes. - */ void napi_disable(struct napi_struct *n); +void napi_disable_locked(struct napi_struct *n); void napi_enable(struct napi_struct *n); +void napi_enable_locked(struct napi_struct *n); /** * napi_synchronize - wait until NAPI is not running @@ -2444,8 +2440,27 @@ struct net_device { u32 napi_defer_hard_irqs; /** - * @lock: protects @net_shaper_hierarchy, feel free to use for other - * netdev-scope protection. Ordering: take after rtnl_lock. + * @up: copy of @state's IFF_UP, but safe to read with just @lock. + * May report false negatives while the device is being opened + * or closed (@lock does not protect .ndo_open, or .ndo_close). + */ + bool up; + + /** + * @lock: netdev-scope lock, protects a small selection of fields. + * Should always be taken using netdev_lock() / netdev_unlock() helpers. + * Drivers are free to use it for other protection. + * + * Protects: + * @gro_flush_timeout, @napi_defer_hard_irqs, @napi_list, + * @net_shaper_hierarchy, @reg_state, @threaded + * + * Partially protects (writers must hold both @lock and rtnl_lock): + * @up + * + * Also protects some fields in struct napi_struct. + * + * Ordering: take after rtnl_lock. */ struct mutex lock; @@ -2671,18 +2686,58 @@ void netif_queue_set_napi(struct net_device *dev, unsigned int queue_index, enum netdev_queue_type type, struct napi_struct *napi); -static inline void netif_napi_set_irq(struct napi_struct *napi, int irq) +static inline void netdev_lock(struct net_device *dev) +{ + mutex_lock(&dev->lock); +} + +static inline void netdev_unlock(struct net_device *dev) +{ + mutex_unlock(&dev->lock); +} + +static inline void netdev_assert_locked(struct net_device *dev) +{ + lockdep_assert_held(&dev->lock); +} + +static inline void netdev_assert_locked_or_invisible(struct net_device *dev) +{ + if (dev->reg_state == NETREG_REGISTERED || + dev->reg_state == NETREG_UNREGISTERING) + netdev_assert_locked(dev); +} + +static inline void netif_napi_set_irq_locked(struct napi_struct *napi, int irq) { napi->irq = irq; } +static inline void netif_napi_set_irq(struct napi_struct *napi, int irq) +{ + netdev_lock(napi->dev); + netif_napi_set_irq_locked(napi, irq); + netdev_unlock(napi->dev); +} + /* Default NAPI poll() weight * Device drivers are strongly advised to not use bigger value */ #define NAPI_POLL_WEIGHT 64 -void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi, - int (*poll)(struct napi_struct *, int), int weight); +void netif_napi_add_weight_locked(struct net_device *dev, + struct napi_struct *napi, + int (*poll)(struct napi_struct *, int), + int weight); + +static inline void +netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi, + int (*poll)(struct napi_struct *, int), int weight) +{ + netdev_lock(dev); + netif_napi_add_weight_locked(dev, napi, poll, weight); + netdev_unlock(dev); +} /** * netif_napi_add() - initialize a NAPI context @@ -2701,6 +2756,13 @@ netif_napi_add(struct net_device *dev, struct napi_struct *napi, } static inline void +netif_napi_add_locked(struct net_device *dev, struct napi_struct *napi, + int (*poll)(struct napi_struct *, int)) +{ + netif_napi_add_weight_locked(dev, napi, poll, NAPI_POLL_WEIGHT); +} + +static inline void netif_napi_add_tx_weight(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), @@ -2710,6 +2772,15 @@ netif_napi_add_tx_weight(struct net_device *dev, netif_napi_add_weight(dev, napi, poll, weight); } +static inline void +netif_napi_add_config_locked(struct net_device *dev, struct napi_struct *napi, + int (*poll)(struct napi_struct *, int), int index) +{ + napi->index = index; + napi->config = &dev->napi_config[index]; + netif_napi_add_weight_locked(dev, napi, poll, NAPI_POLL_WEIGHT); +} + /** * netif_napi_add_config - initialize a NAPI context with persistent config * @dev: network device @@ -2721,9 +2792,9 @@ static inline void netif_napi_add_config(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), int index) { - napi->index = index; - napi->config = &dev->napi_config[index]; - netif_napi_add_weight(dev, napi, poll, NAPI_POLL_WEIGHT); + netdev_lock(dev); + netif_napi_add_config_locked(dev, napi, poll, index); + netdev_unlock(dev); } /** @@ -2743,6 +2814,8 @@ static inline void netif_napi_add_tx(struct net_device *dev, netif_napi_add_tx_weight(dev, napi, poll, NAPI_POLL_WEIGHT); } +void __netif_napi_del_locked(struct napi_struct *napi); + /** * __netif_napi_del - remove a NAPI context * @napi: NAPI context @@ -2751,7 +2824,18 @@ static inline void netif_napi_add_tx(struct net_device *dev, * containing @napi. Drivers might want to call this helper to combine * all the needed RCU grace periods into a single one. */ -void __netif_napi_del(struct napi_struct *napi); +static inline void __netif_napi_del(struct napi_struct *napi) +{ + netdev_lock(napi->dev); + __netif_napi_del_locked(napi); + netdev_unlock(napi->dev); +} + +static inline void netif_napi_del_locked(struct napi_struct *napi) +{ + __netif_napi_del_locked(napi); + synchronize_net(); +} /** * netif_napi_del - remove a NAPI context @@ -3238,7 +3322,6 @@ static inline void unregister_netdevice(struct net_device *dev) int netdev_refcnt_read(const struct net_device *dev); void free_netdev(struct net_device *dev); -void init_dummy_netdev(struct net_device *dev); struct net_device *netdev_get_xmit_slave(struct net_device *dev, struct sk_buff *skb, @@ -3252,7 +3335,6 @@ struct net_device *netdev_get_by_index(struct net *net, int ifindex, struct net_device *netdev_get_by_name(struct net *net, const char *name, netdevice_tracker *tracker, gfp_t gfp); struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex); -struct net_device *dev_get_by_napi_id(unsigned int napi_id); void netdev_copy_name(struct net_device *dev, char *name); static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, @@ -4084,6 +4166,7 @@ struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); u8 dev_xdp_prog_count(struct net_device *dev); int dev_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf); +u8 dev_xdp_sb_prog_count(struct net_device *dev); u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode); u32 dev_get_min_mp_channel_count(const struct net_device *dev); @@ -4689,6 +4772,9 @@ int devm_register_netdev(struct device *dev, struct net_device *ndev); /* General hardware address lists handling functions */ int __hw_addr_sync(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr_list *from_list, int addr_len); +int __hw_addr_sync_multiple(struct netdev_hw_addr_list *to_list, + struct netdev_hw_addr_list *from_list, + int addr_len); void __hw_addr_unsync(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr_list *from_list, int addr_len); int __hw_addr_sync_dev(struct netdev_hw_addr_list *list, diff --git a/include/linux/phy.h b/include/linux/phy.h index 5bc71d59910c..19f076a71f94 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -32,19 +32,6 @@ #include <linux/atomic.h> #include <net/eee.h> -#define PHY_DEFAULT_FEATURES (SUPPORTED_Autoneg | \ - SUPPORTED_TP | \ - SUPPORTED_MII) - -#define PHY_10BT_FEATURES (SUPPORTED_10baseT_Half | \ - SUPPORTED_10baseT_Full) - -#define PHY_100BT_FEATURES (SUPPORTED_100baseT_Half | \ - SUPPORTED_100baseT_Full) - -#define PHY_1000BT_FEATURES (SUPPORTED_1000baseT_Half | \ - SUPPORTED_1000baseT_Full) - extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_t1_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_t1s_p2mp_features) __ro_after_init; @@ -62,16 +49,11 @@ extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_eee_cap2_features) __ro_after_init; #define PHY_BASIC_T1S_P2MP_FEATURES ((unsigned long *)&phy_basic_t1s_p2mp_features) #define PHY_GBIT_FEATURES ((unsigned long *)&phy_gbit_features) #define PHY_GBIT_FIBRE_FEATURES ((unsigned long *)&phy_gbit_fibre_features) -#define PHY_GBIT_ALL_PORTS_FEATURES ((unsigned long *)&phy_gbit_all_ports_features) #define PHY_10GBIT_FEATURES ((unsigned long *)&phy_10gbit_features) -#define PHY_10GBIT_FEC_FEATURES ((unsigned long *)&phy_10gbit_fec_features) -#define PHY_10GBIT_FULL_FEATURES ((unsigned long *)&phy_10gbit_full_features) #define PHY_EEE_CAP1_FEATURES ((unsigned long *)&phy_eee_cap1_features) #define PHY_EEE_CAP2_FEATURES ((unsigned long *)&phy_eee_cap2_features) extern const int phy_basic_ports_array[3]; -extern const int phy_fibre_port_array[1]; -extern const int phy_all_ports_features_array[7]; extern const int phy_10_100_features_array[4]; extern const int phy_basic_t1_features_array[3]; extern const int phy_basic_t1s_p2mp_features_array[2]; @@ -1144,6 +1126,53 @@ struct phy_driver { int (*cable_test_get_status)(struct phy_device *dev, bool *finished); /* Get statistics from the PHY using ethtool */ + /** + * @get_phy_stats: Retrieve PHY statistics. + * @dev: The PHY device for which the statistics are retrieved. + * @eth_stats: structure where Ethernet PHY stats will be stored. + * @stats: structure where additional PHY-specific stats will be stored. + * + * Retrieves the supported PHY statistics and populates the provided + * structures. The input structures are pre-initialized with + * `ETHTOOL_STAT_NOT_SET`, and the driver must only modify members + * corresponding to supported statistics. Unmodified members will remain + * set to `ETHTOOL_STAT_NOT_SET` and will not be returned to userspace. + */ + void (*get_phy_stats)(struct phy_device *dev, + struct ethtool_eth_phy_stats *eth_stats, + struct ethtool_phy_stats *stats); + + /** + * @get_link_stats: Retrieve link statistics. + * @dev: The PHY device for which the statistics are retrieved. + * @link_stats: structure where link-specific stats will be stored. + * + * Retrieves link-related statistics for the given PHY device. The input + * structure is pre-initialized with `ETHTOOL_STAT_NOT_SET`, and the + * driver must only modify members corresponding to supported + * statistics. Unmodified members will remain set to + * `ETHTOOL_STAT_NOT_SET` and will not be returned to userspace. + */ + void (*get_link_stats)(struct phy_device *dev, + struct ethtool_link_ext_stats *link_stats); + + /** + * @update_stats: Trigger periodic statistics updates. + * @dev: The PHY device for which statistics updates are triggered. + * + * Periodically gathers statistics from the PHY device to update locally + * maintained 64-bit counters. This is necessary for PHYs that implement + * reduced-width counters (e.g., 16-bit or 32-bit) which can overflow + * more frequently compared to 64-bit counters. By invoking this + * callback, drivers can fetch the current counter values, handle + * overflow detection, and accumulate the results into local 64-bit + * counters for accurate reporting through the `get_phy_stats` and + * `get_link_stats` interfaces. + * + * Return: 0 on success or a negative error code on failure. + */ + int (*update_stats)(struct phy_device *dev); + /** @get_sset_count: Number of statistic counters */ int (*get_sset_count)(struct phy_device *dev); /** @get_strings: Names of the statistic counters */ @@ -1634,6 +1663,9 @@ static inline bool phy_polling_mode(struct phy_device *phydev) if (phydev->drv->flags & PHY_POLL_CABLE_TEST) return true; + if (phydev->drv->update_stats) + return true; + return phydev->irq == PHY_POLL; } @@ -2096,6 +2128,8 @@ int phy_unregister_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask); int phy_unregister_fixup_for_id(const char *bus_id); int phy_unregister_fixup_for_uid(u32 phy_uid, u32 phy_uid_mask); +int phy_eee_tx_clock_stop_capable(struct phy_device *phydev); +int phy_eee_rx_clock_stop(struct phy_device *phydev, bool clk_stop_enable); int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable); int phy_get_eee_err(struct phy_device *phydev); int phy_ethtool_set_eee(struct phy_device *phydev, struct ethtool_keee *data); @@ -2123,6 +2157,13 @@ int phy_ethtool_get_strings(struct phy_device *phydev, u8 *data); int phy_ethtool_get_sset_count(struct phy_device *phydev); int phy_ethtool_get_stats(struct phy_device *phydev, struct ethtool_stats *stats, u64 *data); + +void __phy_ethtool_get_phy_stats(struct phy_device *phydev, + struct ethtool_eth_phy_stats *phy_stats, + struct ethtool_phy_stats *phydev_stats); +void __phy_ethtool_get_link_ext_stats(struct phy_device *phydev, + struct ethtool_link_ext_stats *link_stats); + int phy_ethtool_get_plca_cfg(struct phy_device *phydev, struct phy_plca_cfg *plca_cfg); int phy_ethtool_set_plca_cfg(struct phy_device *phydev, diff --git a/include/linux/phylib_stubs.h b/include/linux/phylib_stubs.h index 1279f48c8a70..9d2d6090c86d 100644 --- a/include/linux/phylib_stubs.h +++ b/include/linux/phylib_stubs.h @@ -5,6 +5,9 @@ #include <linux/rtnetlink.h> +struct ethtool_eth_phy_stats; +struct ethtool_link_ext_stats; +struct ethtool_phy_stats; struct kernel_hwtstamp_config; struct netlink_ext_ack; struct phy_device; @@ -19,6 +22,11 @@ struct phylib_stubs { int (*hwtstamp_set)(struct phy_device *phydev, struct kernel_hwtstamp_config *config, struct netlink_ext_ack *extack); + void (*get_phy_stats)(struct phy_device *phydev, + struct ethtool_eth_phy_stats *phy_stats, + struct ethtool_phy_stats *phydev_stats); + void (*get_link_ext_stats)(struct phy_device *phydev, + struct ethtool_link_ext_stats *link_stats); }; static inline int phy_hwtstamp_get(struct phy_device *phydev, @@ -50,6 +58,29 @@ static inline int phy_hwtstamp_set(struct phy_device *phydev, return phylib_stubs->hwtstamp_set(phydev, config, extack); } +static inline void phy_ethtool_get_phy_stats(struct phy_device *phydev, + struct ethtool_eth_phy_stats *phy_stats, + struct ethtool_phy_stats *phydev_stats) +{ + ASSERT_RTNL(); + + if (!phylib_stubs) + return; + + phylib_stubs->get_phy_stats(phydev, phy_stats, phydev_stats); +} + +static inline void phy_ethtool_get_link_ext_stats(struct phy_device *phydev, + struct ethtool_link_ext_stats *link_stats) +{ + ASSERT_RTNL(); + + if (!phylib_stubs) + return; + + phylib_stubs->get_link_ext_stats(phydev, link_stats); +} + #else static inline int phy_hwtstamp_get(struct phy_device *phydev, @@ -65,4 +96,15 @@ static inline int phy_hwtstamp_set(struct phy_device *phydev, return -EOPNOTSUPP; } +static inline void phy_ethtool_get_phy_stats(struct phy_device *phydev, + struct ethtool_eth_phy_stats *phy_stats, + struct ethtool_phy_stats *phydev_stats) +{ +} + +static inline void phy_ethtool_get_link_ext_stats(struct phy_device *phydev, + struct ethtool_link_ext_stats *link_stats) +{ +} + #endif diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 4b7a20620b49..898b00451bbf 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -5,6 +5,8 @@ #include <linux/spinlock.h> #include <linux/workqueue.h> +#include <net/eee.h> + struct device_node; struct ethtool_cmd; struct fwnode_handle; @@ -143,11 +145,17 @@ enum phylink_op_type { * possible and avoid stopping it during suspend events. * @default_an_inband: if true, defaults to MLO_AN_INBAND rather than * MLO_AN_PHY. A fixed-link specification will override. + * @eee_rx_clk_stop_enable: if true, PHY can stop the receive clock during LPI * @get_fixed_state: callback to execute to determine the fixed link state, * if MAC link is at %MLO_AN_FIXED mode. * @supported_interfaces: bitmap describing which PHY_INTERFACE_MODE_xxx * are supported by the MAC/PCS. + * @lpi_interfaces: bitmap describing which PHY interface modes can support + * LPI signalling. * @mac_capabilities: MAC pause/speed/duplex capabilities. + * @lpi_capabilities: MAC speeds which can support LPI signalling + * @lpi_timer_default: Default EEE LPI timer setting. + * @eee_enabled_default: If set, EEE will be enabled by phylink at creation time */ struct phylink_config { struct device *dev; @@ -156,10 +164,15 @@ struct phylink_config { bool mac_managed_pm; bool mac_requires_rxc; bool default_an_inband; + bool eee_rx_clk_stop_enable; void (*get_fixed_state)(struct phylink_config *config, struct phylink_link_state *state); DECLARE_PHY_INTERFACE_MASK(supported_interfaces); + DECLARE_PHY_INTERFACE_MASK(lpi_interfaces); unsigned long mac_capabilities; + unsigned long lpi_capabilities; + u32 lpi_timer_default; + bool eee_enabled_default; }; void phylink_limit_mac_speed(struct phylink_config *config, u32 max_speed); @@ -173,6 +186,8 @@ void phylink_limit_mac_speed(struct phylink_config *config, u32 max_speed); * @mac_finish: finish a major reconfiguration of the interface. * @mac_link_down: take the link down. * @mac_link_up: allow the link to come up. + * @mac_disable_tx_lpi: disable LPI. + * @mac_enable_tx_lpi: enable and configure LPI. * * The individual methods are described more fully below. */ @@ -193,6 +208,9 @@ struct phylink_mac_ops { struct phy_device *phy, unsigned int mode, phy_interface_t interface, int speed, int duplex, bool tx_pause, bool rx_pause); + void (*mac_disable_tx_lpi)(struct phylink_config *config); + int (*mac_enable_tx_lpi)(struct phylink_config *config, u32 timer, + bool tx_clk_stop); }; #if 0 /* For kernel-doc purposes only. */ @@ -387,6 +405,33 @@ void mac_link_down(struct phylink_config *config, unsigned int mode, void mac_link_up(struct phylink_config *config, struct phy_device *phy, unsigned int mode, phy_interface_t interface, int speed, int duplex, bool tx_pause, bool rx_pause); + +/** + * mac_disable_tx_lpi() - disable LPI generation at the MAC + * @config: a pointer to a &struct phylink_config. + * + * Disable generation of LPI at the MAC, effectively preventing the MAC + * from indicating that it is idle. + */ +void mac_disable_tx_lpi(struct phylink_config *config); + +/** + * mac_enable_tx_lpi() - configure and enable LPI generation at the MAC + * @config: a pointer to a &struct phylink_config. + * @timer: LPI timeout in microseconds. + * @tx_clk_stop: allow xMII transmit clock to be stopped during LPI + * + * Configure the LPI timeout accordingly. This will only be called when + * the link is already up, to cater for situations where the hardware + * needs to be programmed according to the link speed. + * + * Enable LPI generation at the MAC, and configure whether the xMII transmit + * clock may be stopped. + * + * Returns: 0 on success. Please consult with rmk before returning an error. + */ +int mac_enable_tx_lpi(struct phylink_config *config, u32 timer, + bool tx_clk_stop); #endif struct phylink_pcs_ops; @@ -446,7 +491,7 @@ struct phylink_pcs_ops { phy_interface_t interface); int (*pcs_post_config)(struct phylink_pcs *pcs, phy_interface_t interface); - void (*pcs_get_state)(struct phylink_pcs *pcs, + void (*pcs_get_state)(struct phylink_pcs *pcs, unsigned int neg_mode, struct phylink_link_state *state); int (*pcs_config)(struct phylink_pcs *pcs, unsigned int neg_mode, phy_interface_t interface, @@ -505,6 +550,7 @@ void pcs_disable(struct phylink_pcs *pcs); /** * pcs_get_state() - Read the current inband link state from the hardware * @pcs: a pointer to a &struct phylink_pcs. + * @neg_mode: link negotiation mode (PHYLINK_PCS_NEG_xxx) * @state: a pointer to a &struct phylink_link_state. * * Read the current inband link state from the MAC PCS, reporting the @@ -513,8 +559,11 @@ void pcs_disable(struct phylink_pcs *pcs); * negotiation completion state in @state->an_complete, and link up state * in @state->link. If possible, @state->lp_advertising should also be * populated. + * + * Note that the @neg_mode parameter is always the PHYLINK_PCS_NEG_xxx + * state, not MLO_AN_xxx. */ -void pcs_get_state(struct phylink_pcs *pcs, +void pcs_get_state(struct phylink_pcs *pcs, unsigned int neg_mode, struct phylink_link_state *state); /** @@ -689,8 +738,9 @@ static inline int phylink_get_link_timer_ns(phy_interface_t interface) } void phylink_mii_c22_pcs_decode_state(struct phylink_link_state *state, - u16 bmsr, u16 lpa); + unsigned int neg_mode, u16 bmsr, u16 lpa); void phylink_mii_c22_pcs_get_state(struct mdio_device *pcs, + unsigned int neg_mode, struct phylink_link_state *state); int phylink_mii_c22_pcs_encode_advertisement(phy_interface_t interface, const unsigned long *advertising); diff --git a/include/linux/pldmfw.h b/include/linux/pldmfw.h index 0fc831338226..f5047983004f 100644 --- a/include/linux/pldmfw.h +++ b/include/linux/pldmfw.h @@ -125,9 +125,17 @@ struct pldmfw_ops; * a pointer to their own data, used to implement the device specific * operations. */ + +enum pldmfw_update_mode { + PLDMFW_UPDATE_MODE_FULL, + PLDMFW_UPDATE_MODE_SINGLE_COMPONENT, +}; + struct pldmfw { const struct pldmfw_ops *ops; struct device *dev; + u16 component_identifier; + enum pldmfw_update_mode mode; }; bool pldmfw_op_pci_match_record(struct pldmfw *context, struct pldmfw_record *record); diff --git a/include/linux/poll.h b/include/linux/poll.h index d1ea4f3714a8..12bb18e8b978 100644 --- a/include/linux/poll.h +++ b/include/linux/poll.h @@ -25,14 +25,14 @@ struct poll_table_struct; -/* +/* * structures and helpers for f_op->poll implementations */ typedef void (*poll_queue_proc)(struct file *, wait_queue_head_t *, struct poll_table_struct *); /* - * Do not touch the structure directly, use the access functions - * poll_does_not_wait() and poll_requested_events() instead. + * Do not touch the structure directly, use the access function + * poll_requested_events() instead. */ typedef struct poll_table_struct { poll_queue_proc _qproc; @@ -41,18 +41,16 @@ typedef struct poll_table_struct { static inline void poll_wait(struct file * filp, wait_queue_head_t * wait_address, poll_table *p) { - if (p && p->_qproc && wait_address) + if (p && p->_qproc) { p->_qproc(filp, wait_address, p); -} - -/* - * Return true if it is guaranteed that poll will not wait. This is the case - * if the poll() of another file descriptor in the set got an event, so there - * is no need for waiting. - */ -static inline bool poll_does_not_wait(const poll_table *p) -{ - return p == NULL || p->_qproc == NULL; + /* + * This memory barrier is paired in the wq_has_sleeper(). + * See the comment above prepare_to_wait(), we need to + * ensure that subsequent tests in this thread can't be + * reordered with __add_wait_queue() in _qproc() paths. + */ + smp_mb(); + } } /* diff --git a/include/linux/pse-pd/pse.h b/include/linux/pse-pd/pse.h index 591a53e082e6..c773eeb92d04 100644 --- a/include/linux/pse-pd/pse.h +++ b/include/linux/pse-pd/pse.h @@ -5,15 +5,37 @@ #ifndef _LINUX_PSE_CONTROLLER_H #define _LINUX_PSE_CONTROLLER_H -#include <linux/ethtool.h> #include <linux/list.h> #include <uapi/linux/ethtool.h> /* Maximum current in uA according to IEEE 802.3-2022 Table 145-1 */ #define MAX_PI_CURRENT 1920000 +/* Maximum power in mW according to IEEE 802.3-2022 Table 145-16 */ +#define MAX_PI_PW 99900 struct phy_device; struct pse_controller_dev; +struct netlink_ext_ack; + +/* C33 PSE extended state and substate. */ +struct ethtool_c33_pse_ext_state_info { + enum ethtool_c33_pse_ext_state c33_pse_ext_state; + union { + enum ethtool_c33_pse_ext_substate_error_condition error_condition; + enum ethtool_c33_pse_ext_substate_mr_pse_enable mr_pse_enable; + enum ethtool_c33_pse_ext_substate_option_detect_ted option_detect_ted; + enum ethtool_c33_pse_ext_substate_option_vport_lim option_vport_lim; + enum ethtool_c33_pse_ext_substate_ovld_detected ovld_detected; + enum ethtool_c33_pse_ext_substate_power_not_available power_not_available; + enum ethtool_c33_pse_ext_substate_short_detected short_detected; + u32 __c33_pse_ext_substate; + }; +}; + +struct ethtool_c33_pse_pw_limit_range { + u32 min; + u32 max; +}; /** * struct pse_control_config - PSE control/channel configuration. @@ -29,7 +51,52 @@ struct pse_control_config { }; /** - * struct pse_control_status - PSE control/channel status. + * struct pse_admin_state - PSE operational state + * + * @podl_admin_state: operational state of the PoDL PSE + * functions. IEEE 802.3-2018 30.15.1.1.2 aPoDLPSEAdminState + * @c33_admin_state: operational state of the PSE + * functions. IEEE 802.3-2022 30.9.1.1.2 aPSEAdminState + */ +struct pse_admin_state { + enum ethtool_podl_pse_admin_state podl_admin_state; + enum ethtool_c33_pse_admin_state c33_admin_state; +}; + +/** + * struct pse_pw_status - PSE power detection status + * + * @podl_pw_status: power detection status of the PoDL PSE. + * IEEE 802.3-2018 30.15.1.1.3 aPoDLPSEPowerDetectionStatus: + * @c33_pw_status: power detection status of the PSE. + * IEEE 802.3-2022 30.9.1.1.5 aPSEPowerDetectionStatus: + */ +struct pse_pw_status { + enum ethtool_podl_pse_pw_d_status podl_pw_status; + enum ethtool_c33_pse_pw_d_status c33_pw_status; +}; + +/** + * struct pse_ext_state_info - PSE extended state information + * + * @c33_ext_state_info: extended state information of the PSE + */ +struct pse_ext_state_info { + struct ethtool_c33_pse_ext_state_info c33_ext_state_info; +}; + +/** + * struct pse_pw_limit_ranges - PSE power limit configuration range + * + * @c33_pw_limit_ranges: supported power limit configuration range. The driver + * is in charge of the memory allocation. + */ +struct pse_pw_limit_ranges { + struct ethtool_c33_pse_pw_limit_range *c33_pw_limit_ranges; +}; + +/** + * struct ethtool_pse_control_status - PSE control/channel status. * * @podl_admin_state: operational state of the PoDL PSE * functions. IEEE 802.3-2018 30.15.1.1.2 aPoDLPSEAdminState @@ -47,11 +114,11 @@ struct pse_control_config { * @c33_avail_pw_limit: available power limit of the PSE in mW * IEEE 802.3-2022 145.2.5.4 pse_avail_pwr * @c33_pw_limit_ranges: supported power limit configuration range. The driver - * is in charge of the memory allocation. + * is in charge of the memory allocation * @c33_pw_limit_nb_ranges: number of supported power limit configuration * ranges */ -struct pse_control_status { +struct ethtool_pse_control_status { enum ethtool_podl_pse_admin_state podl_admin_state; enum ethtool_podl_pse_pw_d_status podl_pw_status; enum ethtool_c33_pse_admin_state c33_admin_state; @@ -67,40 +134,51 @@ struct pse_control_status { /** * struct pse_controller_ops - PSE controller driver callbacks * - * @ethtool_get_status: get PSE control status for ethtool interface * @setup_pi_matrix: setup PI matrix of the PSE controller - * @pi_is_enabled: Return 1 if the PSE PI is enabled, 0 if not. - * May also return negative errno. + * @pi_get_admin_state: Get the operational state of the PSE PI. This ops + * is mandatory. + * @pi_get_pw_status: Get the power detection status of the PSE PI. This + * ops is mandatory. + * @pi_get_ext_state: Get the extended state of the PSE PI. + * @pi_get_pw_class: Get the power class of the PSE PI. + * @pi_get_actual_pw: Get actual power of the PSE PI in mW. * @pi_enable: Configure the PSE PI as enabled. * @pi_disable: Configure the PSE PI as disabled. * @pi_get_voltage: Return voltage similarly to get_voltage regulator - * callback. - * @pi_get_current_limit: Get the configured current limit similarly to - * get_current_limit regulator callback. - * @pi_set_current_limit: Configure the current limit similarly to - * set_current_limit regulator callback. - * Should not return an error in case of MAX_PI_CURRENT - * current value set. + * callback in uV. + * @pi_get_pw_limit: Get the configured power limit of the PSE PI in mW. + * @pi_set_pw_limit: Configure the power limit of the PSE PI in mW. + * @pi_get_pw_limit_ranges: Get the supported power limit configuration + * range. The driver is in charge of the memory + * allocation and should return the number of + * ranges. */ struct pse_controller_ops { - int (*ethtool_get_status)(struct pse_controller_dev *pcdev, - unsigned long id, struct netlink_ext_ack *extack, - struct pse_control_status *status); int (*setup_pi_matrix)(struct pse_controller_dev *pcdev); - int (*pi_is_enabled)(struct pse_controller_dev *pcdev, int id); + int (*pi_get_admin_state)(struct pse_controller_dev *pcdev, int id, + struct pse_admin_state *admin_state); + int (*pi_get_pw_status)(struct pse_controller_dev *pcdev, int id, + struct pse_pw_status *pw_status); + int (*pi_get_ext_state)(struct pse_controller_dev *pcdev, int id, + struct pse_ext_state_info *ext_state_info); + int (*pi_get_pw_class)(struct pse_controller_dev *pcdev, int id); + int (*pi_get_actual_pw)(struct pse_controller_dev *pcdev, int id); int (*pi_enable)(struct pse_controller_dev *pcdev, int id); int (*pi_disable)(struct pse_controller_dev *pcdev, int id); int (*pi_get_voltage)(struct pse_controller_dev *pcdev, int id); - int (*pi_get_current_limit)(struct pse_controller_dev *pcdev, - int id); - int (*pi_set_current_limit)(struct pse_controller_dev *pcdev, - int id, int max_uA); + int (*pi_get_pw_limit)(struct pse_controller_dev *pcdev, + int id); + int (*pi_set_pw_limit)(struct pse_controller_dev *pcdev, + int id, int max_mW); + int (*pi_get_pw_limit_ranges)(struct pse_controller_dev *pcdev, int id, + struct pse_pw_limit_ranges *pw_limit_ranges); }; struct module; struct device_node; struct of_phandle_args; struct pse_control; +struct ethtool_pse_control_status; /* PSE PI pairset pinout can either be Alternative A or Alternative B */ enum pse_pi_pairset_pinout { @@ -177,15 +255,13 @@ void pse_control_put(struct pse_control *psec); int pse_ethtool_get_status(struct pse_control *psec, struct netlink_ext_ack *extack, - struct pse_control_status *status); + struct ethtool_pse_control_status *status); int pse_ethtool_set_config(struct pse_control *psec, struct netlink_ext_ack *extack, const struct pse_control_config *config); int pse_ethtool_set_pw_limit(struct pse_control *psec, struct netlink_ext_ack *extack, const unsigned int pw_limit); -int pse_ethtool_get_pw_limit(struct pse_control *psec, - struct netlink_ext_ack *extack); bool pse_has_podl(struct pse_control *psec); bool pse_has_c33(struct pse_control *psec); @@ -203,7 +279,7 @@ static inline void pse_control_put(struct pse_control *psec) static inline int pse_ethtool_get_status(struct pse_control *psec, struct netlink_ext_ack *extack, - struct pse_control_status *status) + struct ethtool_pse_control_status *status) { return -EOPNOTSUPP; } @@ -222,12 +298,6 @@ static inline int pse_ethtool_set_pw_limit(struct pse_control *psec, return -EOPNOTSUPP; } -static inline int pse_ethtool_get_pw_limit(struct pse_control *psec, - struct netlink_ext_ack *extack) -{ - return -EOPNOTSUPP; -} - static inline bool pse_has_podl(struct pse_control *psec) { return false; diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index 8c3c372ad735..bcba3935c6f9 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -168,29 +168,6 @@ int devm_regulator_get_enable_read_voltage(struct device *dev, const char *id); void regulator_put(struct regulator *regulator); void devm_regulator_put(struct regulator *regulator); -#if IS_ENABLED(CONFIG_OF) -struct regulator *__must_check of_regulator_get_optional(struct device *dev, - struct device_node *node, - const char *id); -struct regulator *__must_check devm_of_regulator_get_optional(struct device *dev, - struct device_node *node, - const char *id); -#else -static inline struct regulator *__must_check of_regulator_get_optional(struct device *dev, - struct device_node *node, - const char *id) -{ - return ERR_PTR(-ENODEV); -} - -static inline struct regulator *__must_check devm_of_regulator_get_optional(struct device *dev, - struct device_node *node, - const char *id) -{ - return ERR_PTR(-ENODEV); -} -#endif - int regulator_register_supply_alias(struct device *dev, const char *id, struct device *alias_dev, const char *alias_id); @@ -223,8 +200,6 @@ int regulator_disable_deferred(struct regulator *regulator, int ms); int __must_check regulator_bulk_get(struct device *dev, int num_consumers, struct regulator_bulk_data *consumers); -int __must_check of_regulator_bulk_get_all(struct device *dev, struct device_node *np, - struct regulator_bulk_data **consumers); int __must_check devm_regulator_bulk_get(struct device *dev, int num_consumers, struct regulator_bulk_data *consumers); void devm_regulator_bulk_put(struct regulator_bulk_data *consumers); @@ -373,20 +348,6 @@ devm_regulator_get_optional(struct device *dev, const char *id) return ERR_PTR(-ENODEV); } -static inline struct regulator *__must_check of_regulator_get_optional(struct device *dev, - struct device_node *node, - const char *id) -{ - return ERR_PTR(-ENODEV); -} - -static inline struct regulator *__must_check devm_of_regulator_get_optional(struct device *dev, - struct device_node *node, - const char *id) -{ - return ERR_PTR(-ENODEV); -} - static inline void regulator_put(struct regulator *regulator) { } @@ -483,12 +444,6 @@ static inline int devm_regulator_bulk_get(struct device *dev, int num_consumers, return 0; } -static inline int of_regulator_bulk_get_all(struct device *dev, struct device_node *np, - struct regulator_bulk_data **consumers) -{ - return 0; -} - static inline int devm_regulator_bulk_get_const( struct device *dev, int num_consumers, const struct regulator_bulk_data *in_consumers, @@ -700,6 +655,38 @@ regulator_is_equal(struct regulator *reg1, struct regulator *reg2) } #endif +#if IS_ENABLED(CONFIG_OF) && IS_ENABLED(CONFIG_REGULATOR) +struct regulator *__must_check of_regulator_get_optional(struct device *dev, + struct device_node *node, + const char *id); +struct regulator *__must_check devm_of_regulator_get_optional(struct device *dev, + struct device_node *node, + const char *id); +int __must_check of_regulator_bulk_get_all(struct device *dev, struct device_node *np, + struct regulator_bulk_data **consumers); +#else +static inline struct regulator *__must_check of_regulator_get_optional(struct device *dev, + struct device_node *node, + const char *id) +{ + return ERR_PTR(-ENODEV); +} + +static inline struct regulator *__must_check devm_of_regulator_get_optional(struct device *dev, + struct device_node *node, + const char *id) +{ + return ERR_PTR(-ENODEV); +} + +static inline int of_regulator_bulk_get_all(struct device *dev, struct device_node *np, + struct regulator_bulk_data **consumers) +{ + return 0; +} + +#endif + static inline int regulator_set_voltage_triplet(struct regulator *regulator, int min_uV, int target_uV, int max_uV) diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index 341980599c71..e45531455d3b 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -55,10 +55,10 @@ struct seccomp_data; #ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER static inline int secure_computing(void) { return 0; } -static inline int __secure_computing(const struct seccomp_data *sd) { return 0; } #else static inline void secure_computing_strict(int this_syscall) { return; } #endif +static inline int __secure_computing(const struct seccomp_data *sd) { return 0; } static inline long prctl_get_seccomp(void) { diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index cb40f1a1d081..75342022d144 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -247,6 +247,13 @@ static inline bool vma_can_userfault(struct vm_area_struct *vma, vma_is_shmem(vma); } +static inline bool vma_has_uffd_without_event_remap(struct vm_area_struct *vma) +{ + struct userfaultfd_ctx *uffd_ctx = vma->vm_userfaultfd_ctx.ctx; + + return uffd_ctx && (uffd_ctx->features & UFFD_FEATURE_EVENT_REMAP) == 0; +} + extern int dup_userfaultfd(struct vm_area_struct *, struct list_head *); extern void dup_userfaultfd_complete(struct list_head *); void dup_userfaultfd_fail(struct list_head *); @@ -402,6 +409,11 @@ static inline bool userfaultfd_wp_async(struct vm_area_struct *vma) return false; } +static inline bool vma_has_uffd_without_event_remap(struct vm_area_struct *vma) +{ + return false; +} + #endif /* CONFIG_USERFAULTFD */ static inline bool userfaultfd_wp_use_markers(struct vm_area_struct *vma) diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h index c858270141bc..c39a426ebf52 100644 --- a/include/net/busy_poll.h +++ b/include/net/busy_poll.h @@ -174,12 +174,4 @@ static inline void sk_mark_napi_id_once(struct sock *sk, #endif } -static inline void sk_mark_napi_id_once_xdp(struct sock *sk, - const struct xdp_buff *xdp) -{ -#ifdef CONFIG_NET_RX_BUSY_POLL - __sk_mark_napi_id_once(sk, xdp->rxq->napi_id); -#endif -} - #endif /* _LINUX_NET_BUSY_POLL_H */ diff --git a/include/net/devlink.h b/include/net/devlink.h index fc79fe2297a1..b8783126c1ed 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -1535,6 +1535,7 @@ int devl_trylock(struct devlink *devlink); void devl_unlock(struct devlink *devlink); void devl_assert_locked(struct devlink *devlink); bool devl_lock_is_held(struct devlink *devlink); +DEFINE_GUARD(devl, struct devlink *, devl_lock(_T), devl_unlock(_T)); struct ib_device; diff --git a/include/net/dropreason-core.h b/include/net/dropreason-core.h index 3a6602f37978..ed864934e20b 100644 --- a/include/net/dropreason-core.h +++ b/include/net/dropreason-core.h @@ -36,6 +36,7 @@ FN(TCP_OVERWINDOW) \ FN(TCP_OFOMERGE) \ FN(TCP_RFC7323_PAWS) \ + FN(TCP_RFC7323_PAWS_ACK) \ FN(TCP_OLD_SEQUENCE) \ FN(TCP_INVALID_SEQUENCE) \ FN(TCP_INVALID_ACK_SEQUENCE) \ @@ -259,6 +260,11 @@ enum skb_drop_reason { * LINUX_MIB_PAWSESTABREJECTED, LINUX_MIB_PAWSACTIVEREJECTED */ SKB_DROP_REASON_TCP_RFC7323_PAWS, + /** + * @SKB_DROP_REASON_TCP_RFC7323_PAWS_ACK: PAWS check, old ACK packet. + * Corresponds to LINUX_MIB_PAWS_OLD_ACK. + */ + SKB_DROP_REASON_TCP_RFC7323_PAWS_ACK, /** @SKB_DROP_REASON_TCP_OLD_SEQUENCE: Old SEQ field (duplicate packet) */ SKB_DROP_REASON_TCP_OLD_SEQUENCE, /** @SKB_DROP_REASON_TCP_INVALID_SEQUENCE: Not acceptable SEQ field */ diff --git a/include/net/dsa.h b/include/net/dsa.h index 9640d5c67f56..a0a9481c52c2 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -906,6 +906,8 @@ struct dsa_switch_ops { void (*get_rmon_stats)(struct dsa_switch *ds, int port, struct ethtool_rmon_stats *rmon_stats, const struct ethtool_rmon_hist_range **ranges); + void (*get_ts_stats)(struct dsa_switch *ds, int port, + struct ethtool_ts_stats *ts_stats); void (*get_stats64)(struct dsa_switch *ds, int port, struct rtnl_link_stats64 *s); void (*get_pause_stats)(struct dsa_switch *ds, int port, diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 5a2a0df8ad91..0f5eb9db0c62 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -210,6 +210,8 @@ void net_ns_barrier(void); struct ns_common *get_net_ns(struct ns_common *ns); struct net *get_net_ns_by_fd(int fd); +extern struct task_struct *cleanup_net_task; + #else /* CONFIG_NET_NS */ #include <linux/sched.h> #include <linux/nsproxy.h> diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h index 0c1dac318e02..8dcf7c371ee9 100644 --- a/include/net/netfilter/nf_conntrack_ecache.h +++ b/include/net/netfilter/nf_conntrack_ecache.h @@ -12,6 +12,7 @@ #include <linux/netfilter/nf_conntrack_common.h> #include <linux/netfilter/nf_conntrack_tuple_common.h> #include <net/netfilter/nf_conntrack_extend.h> +#include <asm/local64.h> enum nf_ct_ecache_state { NFCT_ECACHE_DESTROY_FAIL, /* tried but failed to send destroy event */ @@ -20,6 +21,9 @@ enum nf_ct_ecache_state { struct nf_conntrack_ecache { unsigned long cache; /* bitops want long */ +#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP + local64_t timestamp; /* event timestamp, in nanoseconds */ +#endif u16 ctmask; /* bitmask of ct events to be delivered */ u16 expmask; /* bitmask of expect events to be delivered */ u32 missed; /* missed events */ @@ -108,6 +112,14 @@ nf_conntrack_event_cache(enum ip_conntrack_events event, struct nf_conn *ct) if (e == NULL) return; +#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP + /* renew only if this is the first cached event, so that the + * timestamp reflects the first, not the last, generated event. + */ + if (local64_read(&e->timestamp) && READ_ONCE(e->cache) == 0) + local64_set(&e->timestamp, ktime_get_real_ns()); +#endif + set_bit(event, &e->cache); #endif } diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helpers.h index 543f54fa3020..582a3d00cbe2 100644 --- a/include/net/page_pool/helpers.h +++ b/include/net/page_pool/helpers.h @@ -307,7 +307,7 @@ static inline long page_pool_unref_page(struct page *page, long nr) static inline void page_pool_ref_netmem(netmem_ref netmem) { - atomic_long_inc(&netmem_to_page(netmem)->pp_ref_count); + atomic_long_inc(netmem_get_pp_ref_count_ref(netmem)); } static inline void page_pool_ref_page(struct page *page) diff --git a/include/net/sock.h b/include/net/sock.h index ccf86c8a7a8a..8036b3b79cd8 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2300,7 +2300,7 @@ static inline bool skwq_has_sleeper(struct socket_wq *wq) } /** - * sock_poll_wait - place memory barrier behind the poll_wait call. + * sock_poll_wait - wrapper for the poll_wait call. * @filp: file * @sock: socket to wait on * @p: poll_table @@ -2310,15 +2310,12 @@ static inline bool skwq_has_sleeper(struct socket_wq *wq) static inline void sock_poll_wait(struct file *filp, struct socket *sock, poll_table *p) { - if (!poll_does_not_wait(p)) { - poll_wait(filp, &sock->wq.wait, p); - /* We need to be sure we are in sync with the - * socket flags modification. - * - * This memory barrier is paired in the wq_has_sleeper. - */ - smp_mb(); - } + /* Provides a barrier we need to be sure we are in sync + * with the socket flags modification. + * + * This memory barrier is paired in the wq_has_sleeper. + */ + poll_wait(filp, &sock->wq.wait, p); } static inline void skb_set_hash_from_sk(struct sk_buff *skb, struct sock *sk) diff --git a/include/net/xdp.h b/include/net/xdp.h index 6da0e746cf75..4dafc5e021f1 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -64,7 +64,6 @@ struct xdp_rxq_info { u32 queue_index; u32 reg_state; struct xdp_mem_info mem; - unsigned int napi_id; u32 frag_size; } ____cacheline_aligned; /* perf critical, avoid false-sharing */ diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h index 86620c818965..784cd34f5bba 100644 --- a/include/net/xdp_sock_drv.h +++ b/include/net/xdp_sock_drv.h @@ -59,15 +59,6 @@ static inline void xsk_pool_fill_cb(struct xsk_buff_pool *pool, xp_fill_cb(pool, desc); } -static inline unsigned int xsk_pool_get_napi_id(struct xsk_buff_pool *pool) -{ -#ifdef CONFIG_NET_RX_BUSY_POLL - return pool->heads[0].xdp.rxq->napi_id; -#else - return 0; -#endif -} - static inline void xsk_pool_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs) { @@ -317,11 +308,6 @@ static inline void xsk_pool_fill_cb(struct xsk_buff_pool *pool, { } -static inline unsigned int xsk_pool_get_napi_id(struct xsk_buff_pool *pool) -{ - return 0; -} - static inline void xsk_pool_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs) { diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 2db9ae0575b6..6db7fc9dbaa4 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -759,6 +759,14 @@ struct ocelot_mm_state { u8 active_preemptible_tcs; }; +struct ocelot_ts_stats { + u64 pkts; + u64 onestep_pkts_unconfirmed; + u64 lost; + u64 err; + struct u64_stats_sync syncp; +}; + struct ocelot_port; struct ocelot_port { @@ -778,6 +786,7 @@ struct ocelot_port { phy_interface_t phy_mode; + struct ocelot_ts_stats *ts_stats; struct sk_buff_head tx_skbs; unsigned int trap_proto; @@ -1023,6 +1032,8 @@ void ocelot_port_get_eth_mac_stats(struct ocelot *ocelot, int port, struct ethtool_eth_mac_stats *mac_stats); void ocelot_port_get_eth_phy_stats(struct ocelot *ocelot, int port, struct ethtool_eth_phy_stats *phy_stats); +void ocelot_port_get_ts_stats(struct ocelot *ocelot, int port, + struct ethtool_ts_stats *ts_stats); int ocelot_get_ts_info(struct ocelot *ocelot, int port, struct kernel_ethtool_ts_info *info); void ocelot_set_ageing_time(struct ocelot *ocelot, unsigned int msecs); diff --git a/include/trace/events/hugetlbfs.h b/include/trace/events/hugetlbfs.h index 8331c904a9ba..59605dfaeeb4 100644 --- a/include/trace/events/hugetlbfs.h +++ b/include/trace/events/hugetlbfs.h @@ -23,7 +23,7 @@ TRACE_EVENT(hugetlbfs_alloc_inode, TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; - __entry->dir = dir->i_ino; + __entry->dir = dir ? dir->i_ino : 0; __entry->mode = mode; ), diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 7e1b3820f91f..d1089b88efc7 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -681,6 +681,7 @@ enum ethtool_link_ext_substate_module { * @ETH_SS_STATS_ETH_MAC: names of IEEE 802.3 MAC statistics * @ETH_SS_STATS_ETH_CTRL: names of IEEE 802.3 MAC Control statistics * @ETH_SS_STATS_RMON: names of RMON statistics + * @ETH_SS_STATS_PHY: names of PHY(dev) statistics * * @ETH_SS_COUNT: number of defined string sets */ @@ -706,6 +707,7 @@ enum ethtool_stringset { ETH_SS_STATS_ETH_MAC, ETH_SS_STATS_ETH_CTRL, ETH_SS_STATS_RMON, + ETH_SS_STATS_PHY, /* add new constants above here */ ETH_SS_COUNT diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 9c909ce733a5..9ff72cfb2e98 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -99,6 +99,7 @@ enum { ETHTOOL_STATS_ETH_MAC, ETHTOOL_STATS_ETH_CTRL, ETHTOOL_STATS_RMON, + ETHTOOL_STATS_PHY, /* add new constants above here */ __ETHTOOL_STATS_CNT @@ -193,6 +194,19 @@ enum { ETHTOOL_A_STATS_RMON_MAX = (__ETHTOOL_A_STATS_RMON_CNT - 1) }; +enum { + /* Basic packet counters if PHY has separate counters from the MAC */ + ETHTOOL_A_STATS_PHY_RX_PKTS, + ETHTOOL_A_STATS_PHY_RX_BYTES, + ETHTOOL_A_STATS_PHY_RX_ERRORS, + ETHTOOL_A_STATS_PHY_TX_PKTS, + ETHTOOL_A_STATS_PHY_TX_BYTES, + ETHTOOL_A_STATS_PHY_TX_ERRORS, + + /* add new constants above here */ + __ETHTOOL_A_STATS_PHY_CNT, + ETHTOOL_A_STATS_PHY_MAX = (__ETHTOOL_A_STATS_PHY_CNT - 1) +}; /* generic netlink info */ #define ETHTOOL_GENL_NAME "ethtool" diff --git a/include/uapi/linux/ethtool_netlink_generated.h b/include/uapi/linux/ethtool_netlink_generated.h index 43993a2d68e5..fe24c3459ac0 100644 --- a/include/uapi/linux/ethtool_netlink_generated.h +++ b/include/uapi/linux/ethtool_netlink_generated.h @@ -155,6 +155,8 @@ enum { ETHTOOL_A_RINGS_RX_PUSH, ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN, ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN_MAX, + ETHTOOL_A_RINGS_HDS_THRESH, + ETHTOOL_A_RINGS_HDS_THRESH_MAX, __ETHTOOL_A_RINGS_CNT, ETHTOOL_A_RINGS_MAX = (__ETHTOOL_A_RINGS_CNT - 1) @@ -380,6 +382,7 @@ enum { ETHTOOL_A_TS_STAT_TX_PKTS, ETHTOOL_A_TS_STAT_TX_LOST, ETHTOOL_A_TS_STAT_TX_ERR, + ETHTOOL_A_TS_STAT_TX_ONESTEP_PKTS_UNCONFIRMED, __ETHTOOL_A_TS_STAT_CNT, ETHTOOL_A_TS_STAT_MAX = (__ETHTOOL_A_TS_STAT_CNT - 1) diff --git a/include/uapi/linux/mdio.h b/include/uapi/linux/mdio.h index f0d3f268240d..6975f182b22c 100644 --- a/include/uapi/linux/mdio.h +++ b/include/uapi/linux/mdio.h @@ -125,6 +125,7 @@ #define MDIO_STAT1_LPOWERABLE 0x0002 /* Low-power ability */ #define MDIO_STAT1_LSTATUS BMSR_LSTATUS #define MDIO_STAT1_FAULT 0x0080 /* Fault */ +#define MDIO_PCS_STAT1_CLKSTOP_CAP 0x0040 #define MDIO_AN_STAT1_LPABLE 0x0001 /* Link partner AN ability */ #define MDIO_AN_STAT1_ABLE BMSR_ANEGCAPABLE #define MDIO_AN_STAT1_RFAULT BMSR_RFAULT diff --git a/include/uapi/linux/netfilter/nfnetlink_conntrack.h b/include/uapi/linux/netfilter/nfnetlink_conntrack.h index c2ac7269acf7..43233af75b9d 100644 --- a/include/uapi/linux/netfilter/nfnetlink_conntrack.h +++ b/include/uapi/linux/netfilter/nfnetlink_conntrack.h @@ -57,6 +57,7 @@ enum ctattr_type { CTA_SYNPROXY, CTA_FILTER, CTA_STATUS_MASK, + CTA_TIMESTAMP_EVENT, __CTA_MAX }; #define CTA_MAX (__CTA_MAX - 1) diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index 2e75674e7d4f..848c7784e684 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -186,6 +186,7 @@ enum LINUX_MIB_TIMEWAITKILLED, /* TimeWaitKilled */ LINUX_MIB_PAWSACTIVEREJECTED, /* PAWSActiveRejected */ LINUX_MIB_PAWSESTABREJECTED, /* PAWSEstabRejected */ + LINUX_MIB_PAWS_OLD_ACK, /* PAWSOldAck */ LINUX_MIB_DELAYEDACKS, /* DelayedACKs */ LINUX_MIB_DELAYEDACKLOCKED, /* DelayedACKLocked */ LINUX_MIB_DELAYEDACKLOST, /* DelayedACKLost */ diff --git a/io_uring/eventfd.c b/io_uring/eventfd.c index fab936d31ba8..100d5da94cb9 100644 --- a/io_uring/eventfd.c +++ b/io_uring/eventfd.c @@ -33,20 +33,18 @@ static void io_eventfd_free(struct rcu_head *rcu) kfree(ev_fd); } -static void io_eventfd_do_signal(struct rcu_head *rcu) +static void io_eventfd_put(struct io_ev_fd *ev_fd) { - struct io_ev_fd *ev_fd = container_of(rcu, struct io_ev_fd, rcu); - - eventfd_signal_mask(ev_fd->cq_ev_fd, EPOLL_URING_WAKE); - if (refcount_dec_and_test(&ev_fd->refs)) - io_eventfd_free(rcu); + call_rcu(&ev_fd->rcu, io_eventfd_free); } -static void io_eventfd_put(struct io_ev_fd *ev_fd) +static void io_eventfd_do_signal(struct rcu_head *rcu) { - if (refcount_dec_and_test(&ev_fd->refs)) - call_rcu(&ev_fd->rcu, io_eventfd_free); + struct io_ev_fd *ev_fd = container_of(rcu, struct io_ev_fd, rcu); + + eventfd_signal_mask(ev_fd->cq_ev_fd, EPOLL_URING_WAKE); + io_eventfd_put(ev_fd); } static void io_eventfd_release(struct io_ev_fd *ev_fd, bool put_ref) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index ff691f37462c..4758f1ba902b 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -1226,10 +1226,7 @@ static void io_req_normal_work_add(struct io_kiocb *req) /* SQPOLL doesn't need the task_work added, it'll run it itself */ if (ctx->flags & IORING_SETUP_SQPOLL) { - struct io_sq_data *sqd = ctx->sq_data; - - if (sqd->thread) - __set_notify_signal(sqd->thread); + __set_notify_signal(tctx->task); return; } @@ -2813,13 +2810,12 @@ static __poll_t io_uring_poll(struct file *file, poll_table *wait) if (unlikely(!ctx->poll_activated)) io_activate_pollwq(ctx); - - poll_wait(file, &ctx->poll_wq, wait); /* - * synchronizes with barrier from wq_has_sleeper call in - * io_commit_cqring + * provides mb() which pairs with barrier from wq_has_sleeper + * call in io_commit_cqring */ - smp_rmb(); + poll_wait(file, &ctx->poll_wq, wait); + if (!io_sqring_full(ctx)) mask |= EPOLLOUT | EPOLLWRNORM; diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h index 12abee607e4a..492cbbf2c23b 100644 --- a/io_uring/io_uring.h +++ b/io_uring/io_uring.h @@ -125,6 +125,9 @@ static inline void io_lockdep_assert_cq_locked(struct io_ring_ctx *ctx) #if defined(CONFIG_PROVE_LOCKING) lockdep_assert(in_task()); + if (ctx->flags & IORING_SETUP_DEFER_TASKRUN) + lockdep_assert_held(&ctx->uring_lock); + if (ctx->flags & IORING_SETUP_IOPOLL) { lockdep_assert_held(&ctx->uring_lock); } else if (!ctx->task_complete) { @@ -136,9 +139,7 @@ static inline void io_lockdep_assert_cq_locked(struct io_ring_ctx *ctx) * Not from an SQE, as those cannot be submitted, but via * updating tagged resources. */ - if (percpu_ref_is_dying(&ctx->refs)) - lockdep_assert(current_work()); - else + if (!percpu_ref_is_dying(&ctx->refs)) lockdep_assert(current == ctx->submitter_task); } #endif diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c index 9e5bd79fd2b5..8961a3c1e73c 100644 --- a/io_uring/sqpoll.c +++ b/io_uring/sqpoll.c @@ -268,8 +268,12 @@ static int io_sq_thread(void *data) DEFINE_WAIT(wait); /* offload context creation failed, just exit */ - if (!current->io_uring) + if (!current->io_uring) { + mutex_lock(&sqd->lock); + sqd->thread = NULL; + mutex_unlock(&sqd->lock); goto err_out; + } snprintf(buf, sizeof(buf), "iou-sqp-%d", sqd->task_pid); set_task_comm(current, buf); diff --git a/io_uring/timeout.c b/io_uring/timeout.c index 362689b17ccc..e9cec9e4dc2f 100644 --- a/io_uring/timeout.c +++ b/io_uring/timeout.c @@ -427,10 +427,12 @@ static int io_timeout_update(struct io_ring_ctx *ctx, __u64 user_data, timeout->off = 0; /* noseq */ data = req->async_data; + data->ts = *ts; + list_add_tail(&timeout->list, &ctx->timeout_list); hrtimer_init(&data->timer, io_timeout_get_clock(data), mode); data->timer.function = io_timeout_fn; - hrtimer_start(&data->timer, timespec64_to_ktime(*ts), mode); + hrtimer_start(&data->timer, timespec64_to_ktime(data->ts), mode); return 0; } diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index f321ed515f3a..0f910c828973 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -197,10 +197,8 @@ static struct cpuset top_cpuset = { /* * There are two global locks guarding cpuset structures - cpuset_mutex and - * callback_lock. We also require taking task_lock() when dereferencing a - * task's cpuset pointer. See "The task_lock() exception", at the end of this - * comment. The cpuset code uses only cpuset_mutex. Other kernel subsystems - * can use cpuset_lock()/cpuset_unlock() to prevent change to cpuset + * callback_lock. The cpuset code uses only cpuset_mutex. Other kernel + * subsystems can use cpuset_lock()/cpuset_unlock() to prevent change to cpuset * structures. Note that cpuset_mutex needs to be a mutex as it is used in * paths that rely on priority inheritance (e.g. scheduler - on RT) for * correctness. @@ -229,9 +227,6 @@ static struct cpuset top_cpuset = { * The cpuset_common_seq_show() handlers only hold callback_lock across * small pieces of code, such as when reading out possibly multi-word * cpumasks and nodemasks. - * - * Accessing a task's cpuset should be done in accordance with the - * guidelines for accessing subsystem state in kernel/cgroup.c */ static DEFINE_MUTEX(cpuset_mutex); @@ -890,7 +885,15 @@ v2: */ if (cgrpv2) { for (i = 0; i < ndoms; i++) { - cpumask_copy(doms[i], csa[i]->effective_cpus); + /* + * The top cpuset may contain some boot time isolated + * CPUs that need to be excluded from the sched domain. + */ + if (csa[i] == &top_cpuset) + cpumask_and(doms[i], csa[i]->effective_cpus, + housekeeping_cpumask(HK_TYPE_DOMAIN)); + else + cpumask_copy(doms[i], csa[i]->effective_cpus); if (dattr) dattr[i] = SD_ATTR_INIT; } @@ -3121,29 +3124,6 @@ ssize_t cpuset_write_resmask(struct kernfs_open_file *of, int retval = -ENODEV; buf = strstrip(buf); - - /* - * CPU or memory hotunplug may leave @cs w/o any execution - * resources, in which case the hotplug code asynchronously updates - * configuration and transfers all tasks to the nearest ancestor - * which can execute. - * - * As writes to "cpus" or "mems" may restore @cs's execution - * resources, wait for the previously scheduled operations before - * proceeding, so that we don't end up keep removing tasks added - * after execution capability is restored. - * - * cpuset_handle_hotplug may call back into cgroup core asynchronously - * via cgroup_transfer_tasks() and waiting for it from a cgroupfs - * operation like this one can lead to a deadlock through kernfs - * active_ref protection. Let's break the protection. Losing the - * protection is okay as we check whether @cs is online after - * grabbing cpuset_mutex anyway. This only happens on the legacy - * hierarchies. - */ - css_get(&cs->css); - kernfs_break_active_protection(of->kn); - cpus_read_lock(); mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) @@ -3176,8 +3156,6 @@ ssize_t cpuset_write_resmask(struct kernfs_open_file *of, out_unlock: mutex_unlock(&cpuset_mutex); cpus_read_unlock(); - kernfs_unbreak_active_protection(of->kn); - css_put(&cs->css); flush_workqueue(cpuset_migrate_mm_wq); return retval ?: nbytes; } diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index fa04b14a7d72..5d71ef85420c 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -1915,6 +1915,7 @@ void uprobe_free_utask(struct task_struct *t) if (!utask) return; + t->utask = NULL; WARN_ON_ONCE(utask->active_uprobe || utask->xol_vaddr); timer_delete_sync(&utask->ri_timer); @@ -1924,7 +1925,6 @@ void uprobe_free_utask(struct task_struct *t) ri = free_ret_instance(ri, true /* cleanup_hprobe */); kfree(utask); - t->utask = NULL; } #define RI_TIMER_PERIOD (HZ / 10) /* 100 ms */ diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 19d2699cf638..19813b387ef9 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -2747,6 +2747,7 @@ static int balance_one(struct rq *rq, struct task_struct *prev) { struct scx_dsp_ctx *dspc = this_cpu_ptr(scx_dsp_ctx); bool prev_on_scx = prev->sched_class == &ext_sched_class; + bool prev_on_rq = prev->scx.flags & SCX_TASK_QUEUED; int nr_loops = SCX_DSP_MAX_LOOPS; lockdep_assert_rq_held(rq); @@ -2779,8 +2780,7 @@ static int balance_one(struct rq *rq, struct task_struct *prev) * See scx_ops_disable_workfn() for the explanation on the * bypassing test. */ - if ((prev->scx.flags & SCX_TASK_QUEUED) && - prev->scx.slice && !scx_rq_bypassing(rq)) { + if (prev_on_rq && prev->scx.slice && !scx_rq_bypassing(rq)) { rq->scx.flags |= SCX_RQ_BAL_KEEP; goto has_tasks; } @@ -2813,6 +2813,10 @@ static int balance_one(struct rq *rq, struct task_struct *prev) flush_dispatch_buf(rq); + if (prev_on_rq && prev->scx.slice) { + rq->scx.flags |= SCX_RQ_BAL_KEEP; + goto has_tasks; + } if (rq->scx.local_dsq.nr) goto has_tasks; if (consume_global_dsq(rq)) @@ -2838,8 +2842,7 @@ no_tasks: * Didn't find another task to run. Keep running @prev unless * %SCX_OPS_ENQ_LAST is in effect. */ - if ((prev->scx.flags & SCX_TASK_QUEUED) && - (!static_branch_unlikely(&scx_ops_enq_last) || + if (prev_on_rq && (!static_branch_unlikely(&scx_ops_enq_last) || scx_rq_bypassing(rq))) { rq->scx.flags |= SCX_RQ_BAL_KEEP; goto has_tasks; @@ -3034,7 +3037,7 @@ static void put_prev_task_scx(struct rq *rq, struct task_struct *p, */ if (p->scx.slice && !scx_rq_bypassing(rq)) { dispatch_enqueue(&rq->scx.local_dsq, p, SCX_ENQ_HEAD); - return; + goto switch_class; } /* @@ -3051,6 +3054,7 @@ static void put_prev_task_scx(struct rq *rq, struct task_struct *p, } } +switch_class: if (next && next->sched_class != &ext_sched_class) switch_class(rq, next); } @@ -3586,16 +3590,8 @@ static void reset_idle_masks(void) cpumask_copy(idle_masks.smt, cpu_online_mask); } -void __scx_update_idle(struct rq *rq, bool idle) +static void update_builtin_idle(int cpu, bool idle) { - int cpu = cpu_of(rq); - - if (SCX_HAS_OP(update_idle) && !scx_rq_bypassing(rq)) { - SCX_CALL_OP(SCX_KF_REST, update_idle, cpu_of(rq), idle); - if (!static_branch_unlikely(&scx_builtin_idle_enabled)) - return; - } - if (idle) cpumask_set_cpu(cpu, idle_masks.cpu); else @@ -3622,6 +3618,57 @@ void __scx_update_idle(struct rq *rq, bool idle) #endif } +/* + * Update the idle state of a CPU to @idle. + * + * If @do_notify is true, ops.update_idle() is invoked to notify the scx + * scheduler of an actual idle state transition (idle to busy or vice + * versa). If @do_notify is false, only the idle state in the idle masks is + * refreshed without invoking ops.update_idle(). + * + * This distinction is necessary, because an idle CPU can be "reserved" and + * awakened via scx_bpf_pick_idle_cpu() + scx_bpf_kick_cpu(), marking it as + * busy even if no tasks are dispatched. In this case, the CPU may return + * to idle without a true state transition. Refreshing the idle masks + * without invoking ops.update_idle() ensures accurate idle state tracking + * while avoiding unnecessary updates and maintaining balanced state + * transitions. + */ +void __scx_update_idle(struct rq *rq, bool idle, bool do_notify) +{ + int cpu = cpu_of(rq); + + lockdep_assert_rq_held(rq); + + /* + * Trigger ops.update_idle() only when transitioning from a task to + * the idle thread and vice versa. + * + * Idle transitions are indicated by do_notify being set to true, + * managed by put_prev_task_idle()/set_next_task_idle(). + */ + if (SCX_HAS_OP(update_idle) && do_notify && !scx_rq_bypassing(rq)) + SCX_CALL_OP(SCX_KF_REST, update_idle, cpu_of(rq), idle); + + /* + * Update the idle masks: + * - for real idle transitions (do_notify == true) + * - for idle-to-idle transitions (indicated by the previous task + * being the idle thread, managed by pick_task_idle()) + * + * Skip updating idle masks if the previous task is not the idle + * thread, since set_next_task_idle() has already handled it when + * transitioning from a task to the idle thread (calling this + * function with do_notify == true). + * + * In this way we can avoid updating the idle masks twice, + * unnecessarily. + */ + if (static_branch_likely(&scx_builtin_idle_enabled)) + if (do_notify || is_idle_task(rq->curr)) + update_builtin_idle(cpu, idle); +} + static void handle_hotplug(struct rq *rq, bool online) { int cpu = cpu_of(rq); @@ -4744,10 +4791,9 @@ static void scx_ops_bypass(bool bypass) */ for_each_possible_cpu(cpu) { struct rq *rq = cpu_rq(cpu); - struct rq_flags rf; struct task_struct *p, *n; - rq_lock(rq, &rf); + raw_spin_rq_lock(rq); if (bypass) { WARN_ON_ONCE(rq->scx.flags & SCX_RQ_BYPASSING); @@ -4763,7 +4809,7 @@ static void scx_ops_bypass(bool bypass) * sees scx_rq_bypassing() before moving tasks to SCX. */ if (!scx_enabled()) { - rq_unlock(rq, &rf); + raw_spin_rq_unlock(rq); continue; } @@ -4783,10 +4829,11 @@ static void scx_ops_bypass(bool bypass) sched_enq_and_set_task(&ctx); } - rq_unlock(rq, &rf); - /* resched to restore ticks and idle state */ - resched_cpu(cpu); + if (cpu_online(cpu) || cpu == smp_processor_id()) + resched_curr(rq); + + raw_spin_rq_unlock(rq); } atomic_dec(&scx_ops_breather_depth); diff --git a/kernel/sched/ext.h b/kernel/sched/ext.h index b1675bb59fc4..4d022d17ac7d 100644 --- a/kernel/sched/ext.h +++ b/kernel/sched/ext.h @@ -57,15 +57,15 @@ static inline void init_sched_ext_class(void) {} #endif /* CONFIG_SCHED_CLASS_EXT */ #if defined(CONFIG_SCHED_CLASS_EXT) && defined(CONFIG_SMP) -void __scx_update_idle(struct rq *rq, bool idle); +void __scx_update_idle(struct rq *rq, bool idle, bool do_notify); -static inline void scx_update_idle(struct rq *rq, bool idle) +static inline void scx_update_idle(struct rq *rq, bool idle, bool do_notify) { if (scx_enabled()) - __scx_update_idle(rq, idle); + __scx_update_idle(rq, idle, do_notify); } #else -static inline void scx_update_idle(struct rq *rq, bool idle) {} +static inline void scx_update_idle(struct rq *rq, bool idle, bool do_notify) {} #endif #ifdef CONFIG_CGROUP_SCHED diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 621696269584..2c85c86b455f 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -452,19 +452,20 @@ static void wakeup_preempt_idle(struct rq *rq, struct task_struct *p, int flags) static void put_prev_task_idle(struct rq *rq, struct task_struct *prev, struct task_struct *next) { dl_server_update_idle_time(rq, prev); - scx_update_idle(rq, false); + scx_update_idle(rq, false, true); } static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool first) { update_idle_core(rq); - scx_update_idle(rq, true); + scx_update_idle(rq, true, true); schedstat_inc(rq->sched_goidle); next->se.exec_start = rq_clock_task(rq); } struct task_struct *pick_task_idle(struct rq *rq) { + scx_update_idle(rq, true, false); return rq->idle; } diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 935a886af40c..0642ea174849 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -940,8 +940,10 @@ static int __trace_kprobe_create(int argc, const char *argv[]) } /* a symbol specified */ symbol = kstrdup(argv[1], GFP_KERNEL); - if (!symbol) - return -ENOMEM; + if (!symbol) { + ret = -ENOMEM; + goto error; + } tmp = strchr(symbol, '%'); if (tmp) { diff --git a/kernel/workqueue.c b/kernel/workqueue.c index f7d8fc204579..9362484a653c 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -2508,6 +2508,7 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq, return; } + WARN_ON_ONCE(cpu != WORK_CPU_UNBOUND && !cpu_online(cpu)); dwork->wq = wq; dwork->cpu = cpu; timer->expires = jiffies + delay; @@ -2533,6 +2534,12 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq, * @dwork: work to queue * @delay: number of jiffies to wait before queueing * + * We queue the delayed_work to a specific CPU, for non-zero delays the + * caller must ensure it is online and can't go away. Callers that fail + * to ensure this, may get @dwork->timer queued to an offlined CPU and + * this will prevent queueing of @dwork->work unless the offlined CPU + * becomes online again. + * * Return: %false if @work was already on a queue, %true otherwise. If * @delay is zero and @dwork is idle, it will be scheduled for immediate * execution. diff --git a/lib/pldmfw/pldmfw.c b/lib/pldmfw/pldmfw.c index 6e1581b9a616..6264e2013f25 100644 --- a/lib/pldmfw/pldmfw.c +++ b/lib/pldmfw/pldmfw.c @@ -481,9 +481,17 @@ static int pldm_parse_components(struct pldmfw_priv *data) component->component_data = data->fw->data + offset; component->component_size = size; + if (data->context->mode == PLDMFW_UPDATE_MODE_SINGLE_COMPONENT && + data->context->component_identifier != component->identifier) + continue; + list_add_tail(&component->entry, &data->components); } + if (data->context->mode == PLDMFW_UPDATE_MODE_SINGLE_COMPONENT && + list_empty(&data->components)) + return -ENOENT; + header_crc_ptr = data->fw->data + data->offset; err = pldm_move_fw_offset(data, sizeof(data->header_crc)); diff --git a/mm/filemap.c b/mm/filemap.c index 33b60d448fca..4f476411a9a2 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1523,7 +1523,7 @@ void folio_end_read(struct folio *folio, bool success) /* Must be in bottom byte for x86 to work */ BUILD_BUG_ON(PG_uptodate > 7); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); - VM_BUG_ON_FOLIO(folio_test_uptodate(folio), folio); + VM_BUG_ON_FOLIO(success && folio_test_uptodate(folio), folio); if (likely(success)) mask |= 1 << PG_uptodate; @@ -2996,7 +2996,7 @@ static inline loff_t folio_seek_hole_data(struct xa_state *xas, if (ops->is_partially_uptodate(folio, offset, bsz) == seek_data) break; - start = (start + bsz) & ~(bsz - 1); + start = (start + bsz) & ~((u64)bsz - 1); offset += bsz; } while (offset < folio_size(folio)); unlock: diff --git a/mm/huge_memory.c b/mm/huge_memory.c index e53d83b3e5cf..db64116a4f84 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2206,6 +2206,16 @@ static pmd_t move_soft_dirty_pmd(pmd_t pmd) return pmd; } +static pmd_t clear_uffd_wp_pmd(pmd_t pmd) +{ + if (pmd_present(pmd)) + pmd = pmd_clear_uffd_wp(pmd); + else if (is_swap_pmd(pmd)) + pmd = pmd_swp_clear_uffd_wp(pmd); + + return pmd; +} + bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, unsigned long new_addr, pmd_t *old_pmd, pmd_t *new_pmd) { @@ -2244,6 +2254,8 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, pgtable_trans_huge_deposit(mm, new_pmd, pgtable); } pmd = move_soft_dirty_pmd(pmd); + if (vma_has_uffd_without_event_remap(vma)) + pmd = clear_uffd_wp_pmd(pmd); set_pmd_at(mm, new_addr, new_pmd, pmd); if (force_flush) flush_pmd_tlb_range(vma, old_addr, old_addr + PMD_SIZE); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index c498874a7170..eaaec19caa7c 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5402,6 +5402,7 @@ static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr, unsigned long new_addr, pte_t *src_pte, pte_t *dst_pte, unsigned long sz) { + bool need_clear_uffd_wp = vma_has_uffd_without_event_remap(vma); struct hstate *h = hstate_vma(vma); struct mm_struct *mm = vma->vm_mm; spinlock_t *src_ptl, *dst_ptl; @@ -5418,7 +5419,18 @@ static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr, spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); pte = huge_ptep_get_and_clear(mm, old_addr, src_pte); - set_huge_pte_at(mm, new_addr, dst_pte, pte, sz); + + if (need_clear_uffd_wp && pte_marker_uffd_wp(pte)) + huge_pte_clear(mm, new_addr, dst_pte, sz); + else { + if (need_clear_uffd_wp) { + if (pte_present(pte)) + pte = huge_pte_clear_uffd_wp(pte); + else if (is_swap_pte(pte)) + pte = pte_swp_clear_uffd_wp(pte); + } + set_huge_pte_at(mm, new_addr, dst_pte, pte, sz); + } if (src_ptl != dst_ptl) spin_unlock(src_ptl); diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 737af23f4f4e..820ba3b5cbfc 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -1093,7 +1093,7 @@ void __ref kmemleak_alloc_percpu(const void __percpu *ptr, size_t size, pr_debug("%s(0x%px, %zu)\n", __func__, ptr, size); if (kmemleak_enabled && ptr && !IS_ERR_PCPU(ptr)) - create_object_percpu((__force unsigned long)ptr, size, 0, gfp); + create_object_percpu((__force unsigned long)ptr, size, 1, gfp); } EXPORT_SYMBOL_GPL(kmemleak_alloc_percpu); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 04f35659717a..162407fbf2bc 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2268,7 +2268,8 @@ struct page *alloc_pages_mpol_noprof(gfp_t gfp, unsigned int order, page = __alloc_pages_noprof(gfp, order, nid, nodemask); - if (unlikely(pol->mode == MPOL_INTERLEAVE) && page) { + if (unlikely(pol->mode == MPOL_INTERLEAVE || + pol->mode == MPOL_WEIGHTED_INTERLEAVE) && page) { /* skip NUMA_INTERLEAVE_HIT update if numa stats is disabled */ if (static_branch_likely(&vm_numa_stat_key) && page_to_nid(page) == nid) { diff --git a/mm/mremap.c b/mm/mremap.c index 60473413836b..cff7f552f909 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -138,6 +138,7 @@ static int move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, struct vm_area_struct *new_vma, pmd_t *new_pmd, unsigned long new_addr, bool need_rmap_locks) { + bool need_clear_uffd_wp = vma_has_uffd_without_event_remap(vma); struct mm_struct *mm = vma->vm_mm; pte_t *old_pte, *new_pte, pte; pmd_t dummy_pmdval; @@ -216,7 +217,18 @@ static int move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, force_flush = true; pte = move_pte(pte, old_addr, new_addr); pte = move_soft_dirty_pte(pte); - set_pte_at(mm, new_addr, new_pte, pte); + + if (need_clear_uffd_wp && pte_marker_uffd_wp(pte)) + pte_clear(mm, new_addr, new_pte); + else { + if (need_clear_uffd_wp) { + if (pte_present(pte)) + pte = pte_clear_uffd_wp(pte); + else if (is_swap_pte(pte)) + pte = pte_swp_clear_uffd_wp(pte); + } + set_pte_at(mm, new_addr, new_pte, pte); + } } arch_leave_lazy_mmu_mode(); @@ -278,6 +290,15 @@ static bool move_normal_pmd(struct vm_area_struct *vma, unsigned long old_addr, if (WARN_ON_ONCE(!pmd_none(*new_pmd))) return false; + /* If this pmd belongs to a uffd vma with remap events disabled, we need + * to ensure that the uffd-wp state is cleared from all pgtables. This + * means recursing into lower page tables in move_page_tables(), and we + * can reuse the existing code if we simply treat the entry as "not + * moved". + */ + if (vma_has_uffd_without_event_remap(vma)) + return false; + /* * We don't have to worry about the ordering of src and dst * ptlocks because exclusive mmap_lock prevents deadlock. @@ -333,6 +354,15 @@ static bool move_normal_pud(struct vm_area_struct *vma, unsigned long old_addr, if (WARN_ON_ONCE(!pud_none(*new_pud))) return false; + /* If this pud belongs to a uffd vma with remap events disabled, we need + * to ensure that the uffd-wp state is cleared from all pgtables. This + * means recursing into lower page tables in move_page_tables(), and we + * can reuse the existing code if we simply treat the entry as "not + * moved". + */ + if (vma_has_uffd_without_event_remap(vma)) + return false; + /* * We don't have to worry about the ordering of src and dst * ptlocks because exclusive mmap_lock prevents deadlock. diff --git a/mm/page-writeback.c b/mm/page-writeback.c index d213ead95675..d9861e42b2bd 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -692,6 +692,8 @@ static unsigned long bdi_ratio_from_pages(unsigned long pages) unsigned long ratio; global_dirty_limits(&background_thresh, &dirty_thresh); + if (!dirty_thresh) + return -EINVAL; ratio = div64_u64(pages * 100ULL * BDI_RATIO_SCALE, dirty_thresh); return ratio; @@ -790,13 +792,15 @@ int bdi_set_min_bytes(struct backing_dev_info *bdi, u64 min_bytes) { int ret; unsigned long pages = min_bytes >> PAGE_SHIFT; - unsigned long min_ratio; + long min_ratio; ret = bdi_check_pages_limit(pages); if (ret) return ret; min_ratio = bdi_ratio_from_pages(pages); + if (min_ratio < 0) + return min_ratio; return __bdi_set_min_ratio(bdi, min_ratio); } @@ -809,13 +813,15 @@ int bdi_set_max_bytes(struct backing_dev_info *bdi, u64 max_bytes) { int ret; unsigned long pages = max_bytes >> PAGE_SHIFT; - unsigned long max_ratio; + long max_ratio; ret = bdi_check_pages_limit(pages); if (ret) return ret; max_ratio = bdi_ratio_from_pages(pages); + if (max_ratio < 0) + return max_ratio; return __bdi_set_max_ratio(bdi, max_ratio); } diff --git a/mm/vmscan.c b/mm/vmscan.c index 9a859b7d18d7..b1ec5ece067e 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -4642,6 +4642,9 @@ retry: reset_batch_size(walk); } + __mod_lruvec_state(lruvec, PGDEMOTE_KSWAPD + reclaimer_offset(), + stat.nr_demoted); + item = PGSTEAL_KSWAPD + reclaimer_offset(); if (!cgroup_reclaim(sc)) __count_vm_events(item, reclaimed); diff --git a/mm/vmstat.c b/mm/vmstat.c index 4d016314a56c..16bfe1c694dd 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -2122,10 +2122,20 @@ static void __init start_shepherd_timer(void) { int cpu; - for_each_possible_cpu(cpu) + for_each_possible_cpu(cpu) { INIT_DEFERRABLE_WORK(per_cpu_ptr(&vmstat_work, cpu), vmstat_update); + /* + * For secondary CPUs during CPU hotplug scenarios, + * vmstat_cpu_online() will enable the work. + * mm/vmstat:online enables and disables vmstat_work + * symmetrically during CPU hotplug events. + */ + if (!cpu_online(cpu)) + disable_delayed_work_sync(&per_cpu(vmstat_work, cpu)); + } + schedule_delayed_work(&shepherd, round_jiffies_relative(sysctl_stat_interval)); } @@ -2148,13 +2158,14 @@ static int vmstat_cpu_online(unsigned int cpu) if (!node_state(cpu_to_node(cpu), N_CPU)) { node_set_state(cpu_to_node(cpu), N_CPU); } + enable_delayed_work(&per_cpu(vmstat_work, cpu)); return 0; } static int vmstat_cpu_down_prep(unsigned int cpu) { - cancel_delayed_work_sync(&per_cpu(vmstat_work, cpu)); + disable_delayed_work_sync(&per_cpu(vmstat_work, cpu)); return 0; } diff --git a/mm/zswap.c b/mm/zswap.c index 5a27af8d86ea..30f5a27a6862 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -251,7 +251,7 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor) struct zswap_pool *pool; char name[38]; /* 'zswap' + 32 char (max) num + \0 */ gfp_t gfp = __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM; - int ret; + int ret, cpu; if (!zswap_has_pool) { /* if either are unset, pool initialization failed, and we @@ -285,6 +285,9 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor) goto error; } + for_each_possible_cpu(cpu) + mutex_init(&per_cpu_ptr(pool->acomp_ctx, cpu)->mutex); + ret = cpuhp_state_add_instance(CPUHP_MM_ZSWP_POOL_PREPARE, &pool->node); if (ret) @@ -821,11 +824,12 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node) struct acomp_req *req; int ret; - mutex_init(&acomp_ctx->mutex); - + mutex_lock(&acomp_ctx->mutex); acomp_ctx->buffer = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu)); - if (!acomp_ctx->buffer) - return -ENOMEM; + if (!acomp_ctx->buffer) { + ret = -ENOMEM; + goto buffer_fail; + } acomp = crypto_alloc_acomp_node(pool->tfm_name, 0, 0, cpu_to_node(cpu)); if (IS_ERR(acomp)) { @@ -855,12 +859,15 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node) acomp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, crypto_req_done, &acomp_ctx->wait); + mutex_unlock(&acomp_ctx->mutex); return 0; req_fail: crypto_free_acomp(acomp_ctx->acomp); acomp_fail: kfree(acomp_ctx->buffer); +buffer_fail: + mutex_unlock(&acomp_ctx->mutex); return ret; } @@ -869,27 +876,43 @@ static int zswap_cpu_comp_dead(unsigned int cpu, struct hlist_node *node) struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node); struct crypto_acomp_ctx *acomp_ctx = per_cpu_ptr(pool->acomp_ctx, cpu); + mutex_lock(&acomp_ctx->mutex); if (!IS_ERR_OR_NULL(acomp_ctx)) { if (!IS_ERR_OR_NULL(acomp_ctx->req)) acomp_request_free(acomp_ctx->req); + acomp_ctx->req = NULL; if (!IS_ERR_OR_NULL(acomp_ctx->acomp)) crypto_free_acomp(acomp_ctx->acomp); kfree(acomp_ctx->buffer); } + mutex_unlock(&acomp_ctx->mutex); return 0; } -/* Prevent CPU hotplug from freeing up the per-CPU acomp_ctx resources */ -static struct crypto_acomp_ctx *acomp_ctx_get_cpu(struct crypto_acomp_ctx __percpu *acomp_ctx) +static struct crypto_acomp_ctx *acomp_ctx_get_cpu_lock(struct zswap_pool *pool) { - cpus_read_lock(); - return raw_cpu_ptr(acomp_ctx); + struct crypto_acomp_ctx *acomp_ctx; + + for (;;) { + acomp_ctx = raw_cpu_ptr(pool->acomp_ctx); + mutex_lock(&acomp_ctx->mutex); + if (likely(acomp_ctx->req)) + return acomp_ctx; + /* + * It is possible that we were migrated to a different CPU after + * getting the per-CPU ctx but before the mutex was acquired. If + * the old CPU got offlined, zswap_cpu_comp_dead() could have + * already freed ctx->req (among other things) and set it to + * NULL. Just try again on the new CPU that we ended up on. + */ + mutex_unlock(&acomp_ctx->mutex); + } } -static void acomp_ctx_put_cpu(void) +static void acomp_ctx_put_unlock(struct crypto_acomp_ctx *acomp_ctx) { - cpus_read_unlock(); + mutex_unlock(&acomp_ctx->mutex); } static bool zswap_compress(struct page *page, struct zswap_entry *entry, @@ -905,9 +928,7 @@ static bool zswap_compress(struct page *page, struct zswap_entry *entry, gfp_t gfp; u8 *dst; - acomp_ctx = acomp_ctx_get_cpu(pool->acomp_ctx); - mutex_lock(&acomp_ctx->mutex); - + acomp_ctx = acomp_ctx_get_cpu_lock(pool); dst = acomp_ctx->buffer; sg_init_table(&input, 1); sg_set_page(&input, page, PAGE_SIZE, 0); @@ -960,8 +981,7 @@ unlock: else if (alloc_ret) zswap_reject_alloc_fail++; - mutex_unlock(&acomp_ctx->mutex); - acomp_ctx_put_cpu(); + acomp_ctx_put_unlock(acomp_ctx); return comp_ret == 0 && alloc_ret == 0; } @@ -972,9 +992,7 @@ static void zswap_decompress(struct zswap_entry *entry, struct folio *folio) struct crypto_acomp_ctx *acomp_ctx; u8 *src; - acomp_ctx = acomp_ctx_get_cpu(entry->pool->acomp_ctx); - mutex_lock(&acomp_ctx->mutex); - + acomp_ctx = acomp_ctx_get_cpu_lock(entry->pool); src = zpool_map_handle(zpool, entry->handle, ZPOOL_MM_RO); /* * If zpool_map_handle is atomic, we cannot reliably utilize its mapped buffer @@ -998,11 +1016,10 @@ static void zswap_decompress(struct zswap_entry *entry, struct folio *folio) acomp_request_set_params(acomp_ctx->req, &input, &output, entry->length, PAGE_SIZE); BUG_ON(crypto_wait_req(crypto_acomp_decompress(acomp_ctx->req), &acomp_ctx->wait)); BUG_ON(acomp_ctx->req->dlen != PAGE_SIZE); - mutex_unlock(&acomp_ctx->mutex); if (src != acomp_ctx->buffer) zpool_unmap_handle(zpool, entry->handle); - acomp_ctx_put_cpu(); + acomp_ctx_put_unlock(acomp_ctx); } /********************************* diff --git a/net/core/dev.c b/net/core/dev.c index 4452ca2c91ea..d7cbe6ff5249 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -92,6 +92,7 @@ #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/ethtool.h> +#include <linux/ethtool_netlink.h> #include <linux/skbuff.h> #include <linux/kthread.h> #include <linux/bpf.h> @@ -180,8 +181,6 @@ static DEFINE_SPINLOCK(napi_hash_lock); static unsigned int napi_gen_id = NR_CPUS; static DEFINE_READ_MOSTLY_HASHTABLE(napi_hash, 8); -static DECLARE_RWSEM(devnet_rename_sem); - static inline void dev_base_seq_inc(struct net *net) { unsigned int val = net->dev_base_seq + 1; @@ -767,7 +766,8 @@ static struct napi_struct *napi_by_id(unsigned int napi_id) } /* must be called under rcu_read_lock(), as we dont take a reference */ -struct napi_struct *netdev_napi_by_id(struct net *net, unsigned int napi_id) +static struct napi_struct * +netdev_napi_by_id(struct net *net, unsigned int napi_id) { struct napi_struct *napi; @@ -784,6 +784,49 @@ struct napi_struct *netdev_napi_by_id(struct net *net, unsigned int napi_id) } /** + * netdev_napi_by_id_lock() - find a device by NAPI ID and lock it + * @net: the applicable net namespace + * @napi_id: ID of a NAPI of a target device + * + * Find a NAPI instance with @napi_id. Lock its device. + * The device must be in %NETREG_REGISTERED state for lookup to succeed. + * netdev_unlock() must be called to release it. + * + * Return: pointer to NAPI, its device with lock held, NULL if not found. + */ +struct napi_struct * +netdev_napi_by_id_lock(struct net *net, unsigned int napi_id) +{ + struct napi_struct *napi; + struct net_device *dev; + + rcu_read_lock(); + napi = netdev_napi_by_id(net, napi_id); + if (!napi || READ_ONCE(napi->dev->reg_state) != NETREG_REGISTERED) { + rcu_read_unlock(); + return NULL; + } + + dev = napi->dev; + dev_hold(dev); + rcu_read_unlock(); + + dev = __netdev_put_lock(dev); + if (!dev) + return NULL; + + rcu_read_lock(); + napi = netdev_napi_by_id(net, napi_id); + if (napi && napi->dev != dev) + napi = NULL; + rcu_read_unlock(); + + if (!napi) + netdev_unlock(dev); + return napi; +} + +/** * __dev_get_by_name - find a device by its name * @net: the applicable net namespace * @name: name to find @@ -957,7 +1000,6 @@ EXPORT_SYMBOL(netdev_get_by_index); * its reference counter increased so the caller must be careful * about locking. The caller must hold RCU lock. */ - struct net_device *dev_get_by_napi_id(unsigned int napi_id) { struct napi_struct *napi; @@ -971,7 +1013,73 @@ struct net_device *dev_get_by_napi_id(unsigned int napi_id) return napi ? napi->dev : NULL; } -EXPORT_SYMBOL(dev_get_by_napi_id); + +/* Release the held reference on the net_device, and if the net_device + * is still registered try to lock the instance lock. If device is being + * unregistered NULL will be returned (but the reference has been released, + * either way!) + * + * This helper is intended for locking net_device after it has been looked up + * using a lockless lookup helper. Lock prevents the instance from going away. + */ +struct net_device *__netdev_put_lock(struct net_device *dev) +{ + netdev_lock(dev); + if (dev->reg_state > NETREG_REGISTERED) { + netdev_unlock(dev); + dev_put(dev); + return NULL; + } + dev_put(dev); + return dev; +} + +/** + * netdev_get_by_index_lock() - find a device by its ifindex + * @net: the applicable net namespace + * @ifindex: index of device + * + * Search for an interface by index. If a valid device + * with @ifindex is found it will be returned with netdev->lock held. + * netdev_unlock() must be called to release it. + * + * Return: pointer to a device with lock held, NULL if not found. + */ +struct net_device *netdev_get_by_index_lock(struct net *net, int ifindex) +{ + struct net_device *dev; + + dev = dev_get_by_index(net, ifindex); + if (!dev) + return NULL; + + return __netdev_put_lock(dev); +} + +struct net_device * +netdev_xa_find_lock(struct net *net, struct net_device *dev, + unsigned long *index) +{ + if (dev) + netdev_unlock(dev); + + do { + rcu_read_lock(); + dev = xa_find(&net->dev_by_index, index, ULONG_MAX, XA_PRESENT); + if (!dev) { + rcu_read_unlock(); + return NULL; + } + dev_hold(dev); + rcu_read_unlock(); + + dev = __netdev_put_lock(dev); + if (dev) + return dev; + + (*index)++; + } while (true); +} static DEFINE_SEQLOCK(netdev_rename_lock); @@ -1240,23 +1348,16 @@ static int dev_get_valid_name(struct net *net, struct net_device *dev, */ int dev_change_name(struct net_device *dev, const char *newname) { + struct net *net = dev_net(dev); unsigned char old_assign_type; char oldname[IFNAMSIZ]; int err = 0; int ret; - struct net *net; - - ASSERT_RTNL(); - BUG_ON(!dev_net(dev)); - net = dev_net(dev); + ASSERT_RTNL_NET(net); - down_write(&devnet_rename_sem); - - if (strncmp(newname, dev->name, IFNAMSIZ) == 0) { - up_write(&devnet_rename_sem); + if (!strncmp(newname, dev->name, IFNAMSIZ)) return 0; - } memcpy(oldname, dev->name, IFNAMSIZ); @@ -1264,10 +1365,8 @@ int dev_change_name(struct net_device *dev, const char *newname) err = dev_get_valid_name(net, dev, newname); write_sequnlock_bh(&netdev_rename_lock); - if (err < 0) { - up_write(&devnet_rename_sem); + if (err < 0) return err; - } if (oldname[0] && !strchr(oldname, '%')) netdev_info(dev, "renamed from %s%s\n", oldname, @@ -1279,14 +1378,13 @@ int dev_change_name(struct net_device *dev, const char *newname) rollback: ret = device_rename(&dev->dev, dev->name); if (ret) { + write_seqlock_bh(&netdev_rename_lock); memcpy(dev->name, oldname, IFNAMSIZ); + write_sequnlock_bh(&netdev_rename_lock); WRITE_ONCE(dev->name_assign_type, old_assign_type); - up_write(&devnet_rename_sem); return ret; } - up_write(&devnet_rename_sem); - netdev_adjacent_rename_links(dev, oldname); netdev_name_node_del(dev->name_node); @@ -1302,7 +1400,6 @@ rollback: /* err >= 0 after dev_alloc_name() or stores the first errno */ if (err >= 0) { err = ret; - down_write(&devnet_rename_sem); write_seqlock_bh(&netdev_rename_lock); memcpy(dev->name, oldname, IFNAMSIZ); write_sequnlock_bh(&netdev_rename_lock); @@ -1510,7 +1607,7 @@ static int __dev_open(struct net_device *dev, struct netlink_ext_ack *extack) if (ret) clear_bit(__LINK_STATE_START, &dev->state); else { - dev->flags |= IFF_UP; + netif_set_up(dev, true); dev_set_rx_mode(dev); dev_activate(dev); add_device_randomness(dev->dev_addr, dev->addr_len); @@ -1589,7 +1686,7 @@ static void __dev_close_many(struct list_head *head) if (ops->ndo_stop) ops->ndo_stop(dev); - dev->flags &= ~IFF_UP; + netif_set_up(dev, false); netpoll_poll_enable(dev); } } @@ -6014,8 +6111,6 @@ void netif_receive_skb_list(struct list_head *head) } EXPORT_SYMBOL(netif_receive_skb_list); -static DEFINE_PER_CPU(struct work_struct, flush_works); - /* Network device is going away, flush any packets still pending */ static void flush_backlog(struct work_struct *work) { @@ -6072,36 +6167,54 @@ static bool flush_required(int cpu) return true; } +struct flush_backlogs { + cpumask_t flush_cpus; + struct work_struct w[]; +}; + +static struct flush_backlogs *flush_backlogs_alloc(void) +{ + return kmalloc(struct_size_t(struct flush_backlogs, w, nr_cpu_ids), + GFP_KERNEL); +} + +static struct flush_backlogs *flush_backlogs_fallback; +static DEFINE_MUTEX(flush_backlogs_mutex); + static void flush_all_backlogs(void) { - static cpumask_t flush_cpus; + struct flush_backlogs *ptr = flush_backlogs_alloc(); unsigned int cpu; - /* since we are under rtnl lock protection we can use static data - * for the cpumask and avoid allocating on stack the possibly - * large mask - */ - ASSERT_RTNL(); + if (!ptr) { + mutex_lock(&flush_backlogs_mutex); + ptr = flush_backlogs_fallback; + } + cpumask_clear(&ptr->flush_cpus); cpus_read_lock(); - cpumask_clear(&flush_cpus); for_each_online_cpu(cpu) { if (flush_required(cpu)) { - queue_work_on(cpu, system_highpri_wq, - per_cpu_ptr(&flush_works, cpu)); - cpumask_set_cpu(cpu, &flush_cpus); + INIT_WORK(&ptr->w[cpu], flush_backlog); + queue_work_on(cpu, system_highpri_wq, &ptr->w[cpu]); + __cpumask_set_cpu(cpu, &ptr->flush_cpus); } } /* we can have in flight packet[s] on the cpus we are not flushing, * synchronize_net() in unregister_netdevice_many() will take care of - * them + * them. */ - for_each_cpu(cpu, &flush_cpus) - flush_work(per_cpu_ptr(&flush_works, cpu)); + for_each_cpu(cpu, &ptr->flush_cpus) + flush_work(&ptr->w[cpu]); cpus_read_unlock(); + + if (ptr != flush_backlogs_fallback) + kfree(ptr); + else + mutex_unlock(&flush_backlogs_mutex); } static void net_rps_send_ipi(struct softnet_data *remsd) @@ -6675,6 +6788,8 @@ int dev_set_threaded(struct net_device *dev, bool threaded) struct napi_struct *napi; int err = 0; + netdev_assert_locked_or_invisible(dev); + if (dev->threaded == threaded) return 0; @@ -6801,9 +6916,12 @@ netif_napi_dev_list_add(struct net_device *dev, struct napi_struct *napi) list_add_rcu(&napi->dev_list, higher); /* adds after higher */ } -void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi, - int (*poll)(struct napi_struct *, int), int weight) +void netif_napi_add_weight_locked(struct net_device *dev, + struct napi_struct *napi, + int (*poll)(struct napi_struct *, int), + int weight) { + netdev_assert_locked(dev); if (WARN_ON(test_and_set_bit(NAPI_STATE_LISTED, &napi->state))) return; @@ -6842,15 +6960,17 @@ void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi, */ if (dev->threaded && napi_kthread_create(napi)) dev->threaded = false; - netif_napi_set_irq(napi, -1); + netif_napi_set_irq_locked(napi, -1); } -EXPORT_SYMBOL(netif_napi_add_weight); +EXPORT_SYMBOL(netif_napi_add_weight_locked); -void napi_disable(struct napi_struct *n) +void napi_disable_locked(struct napi_struct *n) { unsigned long val, new; might_sleep(); + netdev_assert_locked(n->dev); + set_bit(NAPI_STATE_DISABLE, &n->state); val = READ_ONCE(n->state); @@ -6873,16 +6993,25 @@ void napi_disable(struct napi_struct *n) clear_bit(NAPI_STATE_DISABLE, &n->state); } -EXPORT_SYMBOL(napi_disable); +EXPORT_SYMBOL(napi_disable_locked); /** - * napi_enable - enable NAPI scheduling - * @n: NAPI context + * napi_disable() - prevent NAPI from scheduling + * @n: NAPI context * - * Resume NAPI from being scheduled on this context. - * Must be paired with napi_disable. + * Stop NAPI from being scheduled on this context. + * Waits till any outstanding processing completes. + * Takes netdev_lock() for associated net_device. */ -void napi_enable(struct napi_struct *n) +void napi_disable(struct napi_struct *n) +{ + netdev_lock(n->dev); + napi_disable_locked(n); + netdev_unlock(n->dev); +} +EXPORT_SYMBOL(napi_disable); + +void napi_enable_locked(struct napi_struct *n) { unsigned long new, val = READ_ONCE(n->state); @@ -6899,6 +7028,22 @@ void napi_enable(struct napi_struct *n) new |= NAPIF_STATE_THREADED; } while (!try_cmpxchg(&n->state, &val, new)); } +EXPORT_SYMBOL(napi_enable_locked); + +/** + * napi_enable() - enable NAPI scheduling + * @n: NAPI context + * + * Enable scheduling of a NAPI instance. + * Must be paired with napi_disable(). + * Takes netdev_lock() for associated net_device. + */ +void napi_enable(struct napi_struct *n) +{ + netdev_lock(n->dev); + napi_enable_locked(n); + netdev_unlock(n->dev); +} EXPORT_SYMBOL(napi_enable); static void flush_gro_hash(struct napi_struct *napi) @@ -6915,8 +7060,10 @@ static void flush_gro_hash(struct napi_struct *napi) } /* Must be called in process context */ -void __netif_napi_del(struct napi_struct *napi) +void __netif_napi_del_locked(struct napi_struct *napi) { + netdev_assert_locked(napi->dev); + if (!test_and_clear_bit(NAPI_STATE_LISTED, &napi->state)) return; @@ -6936,7 +7083,7 @@ void __netif_napi_del(struct napi_struct *napi) napi->thread = NULL; } } -EXPORT_SYMBOL(__netif_napi_del); +EXPORT_SYMBOL(__netif_napi_del_locked); static int __napi_poll(struct napi_struct *n, bool *repoll) { @@ -9552,11 +9699,31 @@ u8 dev_xdp_prog_count(struct net_device *dev) } EXPORT_SYMBOL_GPL(dev_xdp_prog_count); +u8 dev_xdp_sb_prog_count(struct net_device *dev) +{ + u8 count = 0; + int i; + + for (i = 0; i < __MAX_XDP_MODE; i++) + if (dev->xdp_state[i].prog && + !dev->xdp_state[i].prog->aux->xdp_has_frags) + count++; + return count; +} + int dev_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf) { if (!dev->netdev_ops->ndo_bpf) return -EOPNOTSUPP; + if (dev->ethtool->hds_config == ETHTOOL_TCP_DATA_SPLIT_ENABLED && + bpf->command == XDP_SETUP_PROG && + bpf->prog && !bpf->prog->aux->xdp_has_frags) { + NL_SET_ERR_MSG(bpf->extack, + "unable to propagate XDP to device using tcp-data-split"); + return -EBUSY; + } + if (dev_get_min_mp_channel_count(dev)) { NL_SET_ERR_MSG(bpf->extack, "unable to propagate XDP to device using memory provider"); return -EBUSY; @@ -9594,6 +9761,12 @@ static int dev_xdp_install(struct net_device *dev, enum bpf_xdp_mode mode, struct netdev_bpf xdp; int err; + if (dev->ethtool->hds_config == ETHTOOL_TCP_DATA_SPLIT_ENABLED && + prog && !prog->aux->xdp_has_frags) { + NL_SET_ERR_MSG(extack, "unable to install XDP to device using tcp-data-split"); + return -EBUSY; + } + if (dev_get_min_mp_channel_count(dev)) { NL_SET_ERR_MSG(extack, "unable to install XDP to device using memory provider"); return -EBUSY; @@ -10074,14 +10247,46 @@ static void dev_index_release(struct net *net, int ifindex) WARN_ON(xa_erase(&net->dev_by_index, ifindex)); } +static bool from_cleanup_net(void) +{ +#ifdef CONFIG_NET_NS + return current == cleanup_net_task; +#else + return false; +#endif +} + +static void rtnl_drop_if_cleanup_net(void) +{ + if (from_cleanup_net()) + __rtnl_unlock(); +} + +static void rtnl_acquire_if_cleanup_net(void) +{ + if (from_cleanup_net()) + rtnl_lock(); +} + /* Delayed registration/unregisteration */ LIST_HEAD(net_todo_list); +static LIST_HEAD(net_todo_list_for_cleanup_net); + +/* TODO: net_todo_list/net_todo_list_for_cleanup_net should probably + * be provided by callers, instead of being static, rtnl protected. + */ +static struct list_head *todo_list(void) +{ + return from_cleanup_net() ? &net_todo_list_for_cleanup_net : + &net_todo_list; +} + DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq); atomic_t dev_unreg_count = ATOMIC_INIT(0); static void net_set_todo(struct net_device *dev) { - list_add_tail(&dev->todo_list, &net_todo_list); + list_add_tail(&dev->todo_list, todo_list()); } static netdev_features_t netdev_sync_upper_features(struct net_device *lower, @@ -10670,7 +10875,9 @@ int register_netdevice(struct net_device *dev) ret = netdev_register_kobject(dev); + netdev_lock(dev); WRITE_ONCE(dev->reg_state, ret ? NETREG_UNREGISTERED : NETREG_REGISTERED); + netdev_unlock(dev); if (ret) goto err_uninit_notify; @@ -10738,26 +10945,20 @@ err_free_name: EXPORT_SYMBOL(register_netdevice); /* Initialize the core of a dummy net device. - * This is useful if you are calling this function after alloc_netdev(), - * since it does not memset the net_device fields. + * The setup steps dummy netdevs need which normal netdevs get by going + * through register_netdevice(). */ -static void init_dummy_netdev_core(struct net_device *dev) +static void init_dummy_netdev(struct net_device *dev) { /* make sure we BUG if trying to hit standard * register/unregister code path */ dev->reg_state = NETREG_DUMMY; - /* NAPI wants this */ - INIT_LIST_HEAD(&dev->napi_list); - /* a dummy interface is started by default */ set_bit(__LINK_STATE_PRESENT, &dev->state); set_bit(__LINK_STATE_START, &dev->state); - /* napi_busy_loop stats accounting wants this */ - dev_net_set(dev, &init_net); - /* Note : We dont allocate pcpu_refcnt for dummy devices, * because users of this 'device' dont need to change * its refcount. @@ -10765,28 +10966,6 @@ static void init_dummy_netdev_core(struct net_device *dev) } /** - * init_dummy_netdev - init a dummy network device for NAPI - * @dev: device to init - * - * This takes a network device structure and initializes the minimum - * amount of fields so it can be used to schedule NAPI polls without - * registering a full blown interface. This is to be used by drivers - * that need to tie several hardware interfaces to a single NAPI - * poll scheduler due to HW limitations. - */ -void init_dummy_netdev(struct net_device *dev) -{ - /* Clear everything. Note we don't initialize spinlocks - * as they aren't supposed to be taken by any of the - * NAPI code and this dummy netdev is supposed to be - * only ever used for NAPI polls - */ - memset(dev, 0, sizeof(struct net_device)); - init_dummy_netdev_core(dev); -} -EXPORT_SYMBOL_GPL(init_dummy_netdev); - -/** * register_netdev - register a network device * @dev: device to register * @@ -10957,7 +11136,7 @@ void netdev_run_todo(void) #endif /* Snapshot list, allow later requests */ - list_replace_init(&net_todo_list, &list); + list_replace_init(todo_list(), &list); __rtnl_unlock(); @@ -10972,7 +11151,9 @@ void netdev_run_todo(void) continue; } + netdev_lock(dev); WRITE_ONCE(dev->reg_state, NETREG_UNREGISTERED); + netdev_unlock(dev); linkwatch_sync_dev(dev); } @@ -11387,6 +11568,22 @@ free_dev: } EXPORT_SYMBOL(alloc_netdev_mqs); +static void netdev_napi_exit(struct net_device *dev) +{ + if (!list_empty(&dev->napi_list)) { + struct napi_struct *p, *n; + + netdev_lock(dev); + list_for_each_entry_safe(p, n, &dev->napi_list, dev_list) + __netif_napi_del_locked(p); + netdev_unlock(dev); + + synchronize_net(); + } + + kvfree(dev->napi_config); +} + /** * free_netdev - free network device * @dev: device @@ -11398,8 +11595,6 @@ EXPORT_SYMBOL(alloc_netdev_mqs); */ void free_netdev(struct net_device *dev) { - struct napi_struct *p, *n; - might_sleep(); /* When called immediately after register_netdevice() failed the unwind @@ -11412,8 +11607,6 @@ void free_netdev(struct net_device *dev) return; } - mutex_destroy(&dev->lock); - kfree(dev->ethtool); netif_free_tx_queues(dev); netif_free_rx_queues(dev); @@ -11423,10 +11616,7 @@ void free_netdev(struct net_device *dev) /* Flush device addresses */ dev_addr_flush(dev); - list_for_each_entry_safe(p, n, &dev->napi_list, dev_list) - netif_napi_del(p); - - kvfree(dev->napi_config); + netdev_napi_exit(dev); ref_tracker_dir_exit(&dev->refcnt_tracker); #ifdef CONFIG_PCPU_DEV_REFCNT @@ -11440,6 +11630,8 @@ void free_netdev(struct net_device *dev) netdev_free_phy_link_topology(dev); + mutex_destroy(&dev->lock); + /* Compatibility with error handling in drivers */ if (dev->reg_state == NETREG_UNINITIALIZED || dev->reg_state == NETREG_DUMMY) { @@ -11464,7 +11656,7 @@ EXPORT_SYMBOL(free_netdev); struct net_device *alloc_netdev_dummy(int sizeof_priv) { return alloc_netdev(sizeof_priv, "dummy#", NET_NAME_UNKNOWN, - init_dummy_netdev_core); + init_dummy_netdev); } EXPORT_SYMBOL_GPL(alloc_netdev_dummy); @@ -11477,7 +11669,7 @@ EXPORT_SYMBOL_GPL(alloc_netdev_dummy); void synchronize_net(void) { might_sleep(); - if (rtnl_is_locked()) + if (from_cleanup_net() || rtnl_is_locked()) synchronize_rcu_expedited(); else synchronize_rcu(); @@ -11578,11 +11770,15 @@ void unregister_netdevice_many_notify(struct list_head *head, list_for_each_entry(dev, head, unreg_list) { /* And unlink it from device chain. */ unlist_netdevice(dev); + netdev_lock(dev); WRITE_ONCE(dev->reg_state, NETREG_UNREGISTERING); + netdev_unlock(dev); } - flush_all_backlogs(); + rtnl_drop_if_cleanup_net(); + flush_all_backlogs(); synchronize_net(); + rtnl_acquire_if_cleanup_net(); list_for_each_entry(dev, head, unreg_list) { struct sk_buff *skb = NULL; @@ -11642,7 +11838,9 @@ void unregister_netdevice_many_notify(struct list_head *head, #endif } + rtnl_drop_if_cleanup_net(); synchronize_net(); + rtnl_acquire_if_cleanup_net(); list_for_each_entry(dev, head, unreg_list) { netdev_put(dev, &dev->dev_registered_tracker); @@ -12307,12 +12505,13 @@ static int __init net_dev_init(void) * Initialise the packet receive queues. */ + flush_backlogs_fallback = flush_backlogs_alloc(); + if (!flush_backlogs_fallback) + goto out; + for_each_possible_cpu(i) { - struct work_struct *flush = per_cpu_ptr(&flush_works, i); struct softnet_data *sd = &per_cpu(softnet_data, i); - INIT_WORK(flush, flush_backlog); - skb_queue_head_init(&sd->input_pkt_queue); skb_queue_head_init(&sd->process_queue); #ifdef CONFIG_XFRM_OFFLOAD diff --git a/net/core/dev.h b/net/core/dev.h index 08812a025a9b..a5b166bbd169 100644 --- a/net/core/dev.h +++ b/net/core/dev.h @@ -2,6 +2,7 @@ #ifndef _NET_CORE_DEV_H #define _NET_CORE_DEV_H +#include <linux/cleanup.h> #include <linux/types.h> #include <linux/rwsem.h> #include <linux/netdevice.h> @@ -22,7 +23,22 @@ struct sd_flow_limit { extern int netdev_flow_limit_table_len; -struct napi_struct *netdev_napi_by_id(struct net *net, unsigned int napi_id); +struct napi_struct * +netdev_napi_by_id_lock(struct net *net, unsigned int napi_id); +struct net_device *dev_get_by_napi_id(unsigned int napi_id); + +struct net_device *netdev_get_by_index_lock(struct net *net, int ifindex); +struct net_device *__netdev_put_lock(struct net_device *dev); +struct net_device * +netdev_xa_find_lock(struct net *net, struct net_device *dev, + unsigned long *index); + +DEFINE_FREE(netdev_unlock, struct net_device *, if (_T) netdev_unlock(_T)); + +#define for_each_netdev_lock_scoped(net, var_name, ifindex) \ + for (struct net_device *var_name __free(netdev_unlock) = NULL; \ + (var_name = netdev_xa_find_lock(net, var_name, &ifindex)); \ + ifindex++) #ifdef CONFIG_PROC_FS int __init dev_proc_init(void); @@ -111,6 +127,18 @@ void __dev_notify_flags(struct net_device *dev, unsigned int old_flags, void unregister_netdevice_many_notify(struct list_head *head, u32 portid, const struct nlmsghdr *nlh); +static inline void netif_set_up(struct net_device *dev, bool value) +{ + if (value) + dev->flags |= IFF_UP; + else + dev->flags &= ~IFF_UP; + + netdev_lock(dev); + dev->up = value; + netdev_unlock(dev); +} + static inline void netif_set_gso_max_size(struct net_device *dev, unsigned int size) { diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index 166e404f7c03..90716bd736f3 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -242,9 +242,9 @@ static void __hw_addr_unsync_one(struct netdev_hw_addr_list *to_list, __hw_addr_del_entry(from_list, ha, false, false); } -static int __hw_addr_sync_multiple(struct netdev_hw_addr_list *to_list, - struct netdev_hw_addr_list *from_list, - int addr_len) +int __hw_addr_sync_multiple(struct netdev_hw_addr_list *to_list, + struct netdev_hw_addr_list *from_list, + int addr_len) { int err = 0; struct netdev_hw_addr *ha, *tmp; @@ -260,6 +260,7 @@ static int __hw_addr_sync_multiple(struct netdev_hw_addr_list *to_list, } return err; } +EXPORT_SYMBOL(__hw_addr_sync_multiple); /* This function only works where there is a strict 1-1 relationship * between source and destination of they synch. If you ever need to diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 087a57b7e4fa..4c2098ac9d72 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -543,7 +543,7 @@ static int dev_siocwandev(struct net_device *dev, struct if_settings *ifs) } /* - * Perform the SIOCxIFxxx calls, inside rtnl_lock() + * Perform the SIOCxIFxxx calls, inside rtnl_net_lock() */ static int dev_ifsioc(struct net *net, struct ifreq *ifr, void __user *data, unsigned int cmd) @@ -620,11 +620,14 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, void __user *data, return -ENODEV; if (!netif_is_bridge_master(dev)) return -EOPNOTSUPP; + netdev_hold(dev, &dev_tracker, GFP_KERNEL); - rtnl_unlock(); + rtnl_net_unlock(net); + err = br_ioctl_call(net, netdev_priv(dev), cmd, ifr, NULL); + netdev_put(dev, &dev_tracker); - rtnl_lock(); + rtnl_net_lock(net); return err; case SIOCDEVPRIVATE ... SIOCDEVPRIVATE + 15: @@ -770,9 +773,11 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, dev_load(net, ifr->ifr_name); if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; - rtnl_lock(); + + rtnl_net_lock(net); ret = dev_ifsioc(net, ifr, data, cmd); - rtnl_unlock(); + rtnl_net_unlock(net); + if (colon) *colon = ':'; return ret; @@ -816,9 +821,11 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, case SIOCBONDSLAVEINFOQUERY: case SIOCBONDINFOQUERY: dev_load(net, ifr->ifr_name); - rtnl_lock(); + + rtnl_net_lock(net); ret = dev_ifsioc(net, ifr, data, cmd); - rtnl_unlock(); + rtnl_net_unlock(net); + if (need_copyout) *need_copyout = false; return ret; @@ -841,9 +848,10 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, (cmd >= SIOCDEVPRIVATE && cmd <= SIOCDEVPRIVATE + 15)) { dev_load(net, ifr->ifr_name); - rtnl_lock(); + + rtnl_net_lock(net); ret = dev_ifsioc(net, ifr, data, cmd); - rtnl_unlock(); + rtnl_net_unlock(net); return ret; } return -ENOTTY; diff --git a/net/core/devmem.c b/net/core/devmem.c index 0b6ed7525b22..c971b8aceac8 100644 --- a/net/core/devmem.c +++ b/net/core/devmem.c @@ -8,6 +8,7 @@ */ #include <linux/dma-buf.h> +#include <linux/ethtool_netlink.h> #include <linux/genalloc.h> #include <linux/mm.h> #include <linux/netdevice.h> @@ -140,6 +141,16 @@ int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx, return -ERANGE; } + if (dev->ethtool->hds_config != ETHTOOL_TCP_DATA_SPLIT_ENABLED) { + NL_SET_ERR_MSG(extack, "tcp-data-split is disabled"); + return -EINVAL; + } + + if (dev->ethtool->hds_thresh) { + NL_SET_ERR_MSG(extack, "hds-thresh is not zero"); + return -EINVAL; + } + rxq = __netif_get_rx_queue(dev, rxq_idx); if (rxq->mp_params.mp_priv) { NL_SET_ERR_MSG(extack, "designated queue already memory provider bound"); diff --git a/net/core/filter.c b/net/core/filter.c index b957cf57299e..5b5996901ccc 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -11251,6 +11251,7 @@ BPF_CALL_4(sk_select_reuseport, struct sk_reuseport_kern *, reuse_kern, bool is_sockarray = map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY; struct sock_reuseport *reuse; struct sock *selected_sk; + int err; selected_sk = map->ops->map_lookup_elem(map, key); if (!selected_sk) @@ -11258,10 +11259,6 @@ BPF_CALL_4(sk_select_reuseport, struct sk_reuseport_kern *, reuse_kern, reuse = rcu_dereference(selected_sk->sk_reuseport_cb); if (!reuse) { - /* Lookup in sock_map can return TCP ESTABLISHED sockets. */ - if (sk_is_refcounted(selected_sk)) - sock_put(selected_sk); - /* reuseport_array has only sk with non NULL sk_reuseport_cb. * The only (!reuse) case here is - the sk has already been * unhashed (e.g. by close()), so treat it as -ENOENT. @@ -11269,24 +11266,33 @@ BPF_CALL_4(sk_select_reuseport, struct sk_reuseport_kern *, reuse_kern, * Other maps (e.g. sock_map) do not provide this guarantee and * the sk may never be in the reuseport group to begin with. */ - return is_sockarray ? -ENOENT : -EINVAL; + err = is_sockarray ? -ENOENT : -EINVAL; + goto error; } if (unlikely(reuse->reuseport_id != reuse_kern->reuseport_id)) { struct sock *sk = reuse_kern->sk; - if (sk->sk_protocol != selected_sk->sk_protocol) - return -EPROTOTYPE; - else if (sk->sk_family != selected_sk->sk_family) - return -EAFNOSUPPORT; - - /* Catch all. Likely bound to a different sockaddr. */ - return -EBADFD; + if (sk->sk_protocol != selected_sk->sk_protocol) { + err = -EPROTOTYPE; + } else if (sk->sk_family != selected_sk->sk_family) { + err = -EAFNOSUPPORT; + } else { + /* Catch all. Likely bound to a different sockaddr. */ + err = -EBADFD; + } + goto error; } reuse_kern->selected_sk = selected_sk; return 0; +error: + /* Lookup in sock_map can return TCP ESTABLISHED sockets. */ + if (sk_is_refcounted(selected_sk)) + sock_put(selected_sk); + + return err; } static const struct bpf_func_proto sk_select_reuseport_proto = { diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 2d9afc6e2161..07cb99b114bd 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -36,7 +36,7 @@ static const char fmt_uint[] = "%u\n"; static const char fmt_ulong[] = "%lu\n"; static const char fmt_u64[] = "%llu\n"; -/* Caller holds RTNL or RCU */ +/* Caller holds RTNL, netdev->lock or RCU */ static inline int dev_isalive(const struct net_device *dev) { return READ_ONCE(dev->reg_state) <= NETREG_REGISTERED; @@ -108,6 +108,36 @@ static ssize_t netdev_store(struct device *dev, struct device_attribute *attr, return ret; } +/* Same as netdev_store() but takes netdev_lock() instead of rtnl_lock() */ +static ssize_t +netdev_lock_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t len, + int (*set)(struct net_device *, unsigned long)) +{ + struct net_device *netdev = to_net_dev(dev); + struct net *net = dev_net(netdev); + unsigned long new; + int ret; + + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) + return -EPERM; + + ret = kstrtoul(buf, 0, &new); + if (ret) + return ret; + + netdev_lock(netdev); + + if (dev_isalive(netdev)) { + ret = (*set)(netdev, new); + if (ret == 0) + ret = len; + } + netdev_unlock(netdev); + + return ret; +} + NETDEVICE_SHOW_RO(dev_id, fmt_hex); NETDEVICE_SHOW_RO(dev_port, fmt_dec); NETDEVICE_SHOW_RO(addr_assign_type, fmt_dec); @@ -420,7 +450,7 @@ static ssize_t gro_flush_timeout_store(struct device *dev, if (!capable(CAP_NET_ADMIN)) return -EPERM; - return netdev_store(dev, attr, buf, len, change_gro_flush_timeout); + return netdev_lock_store(dev, attr, buf, len, change_gro_flush_timeout); } NETDEVICE_SHOW_RW(gro_flush_timeout, fmt_ulong); @@ -440,7 +470,8 @@ static ssize_t napi_defer_hard_irqs_store(struct device *dev, if (!capable(CAP_NET_ADMIN)) return -EPERM; - return netdev_store(dev, attr, buf, len, change_napi_defer_hard_irqs); + return netdev_lock_store(dev, attr, buf, len, + change_napi_defer_hard_irqs); } NETDEVICE_SHOW_RW(napi_defer_hard_irqs, fmt_uint); @@ -638,7 +669,7 @@ static ssize_t threaded_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { - return netdev_store(dev, attr, buf, len, modify_napi_threaded); + return netdev_lock_store(dev, attr, buf, len, modify_napi_threaded); } static DEVICE_ATTR_RW(threaded); diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index b5cd3ae4f04c..cb39a12b2f82 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -588,6 +588,8 @@ static void unhash_nsid(struct net *net, struct net *last) static LLIST_HEAD(cleanup_list); +struct task_struct *cleanup_net_task; + static void cleanup_net(struct work_struct *work) { const struct pernet_operations *ops; @@ -596,6 +598,8 @@ static void cleanup_net(struct work_struct *work) LIST_HEAD(net_exit_list); LIST_HEAD(dev_kill_list); + cleanup_net_task = current; + /* Atomically snapshot the list of namespaces to cleanup */ net_kill_list = llist_del_all(&cleanup_list); @@ -670,6 +674,7 @@ static void cleanup_net(struct work_struct *work) put_user_ns(net->user_ns); net_free(net); } + cleanup_net_task = NULL; } /** diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c index a89cbd8d87c3..996ac6a449eb 100644 --- a/net/core/netdev-genl-gen.c +++ b/net/core/netdev-genl-gen.c @@ -197,6 +197,16 @@ static const struct genl_multicast_group netdev_nl_mcgrps[] = { [NETDEV_NLGRP_PAGE_POOL] = { "page-pool", }, }; +static void __netdev_nl_sock_priv_init(void *priv) +{ + netdev_nl_sock_priv_init(priv); +} + +static void __netdev_nl_sock_priv_destroy(void *priv) +{ + netdev_nl_sock_priv_destroy(priv); +} + struct genl_family netdev_nl_family __ro_after_init = { .name = NETDEV_FAMILY_NAME, .version = NETDEV_FAMILY_VERSION, @@ -208,6 +218,6 @@ struct genl_family netdev_nl_family __ro_after_init = { .mcgrps = netdev_nl_mcgrps, .n_mcgrps = ARRAY_SIZE(netdev_nl_mcgrps), .sock_priv_size = sizeof(struct list_head), - .sock_priv_init = (void *)netdev_nl_sock_priv_init, - .sock_priv_destroy = (void *)netdev_nl_sock_priv_destroy, + .sock_priv_init = __netdev_nl_sock_priv_init, + .sock_priv_destroy = __netdev_nl_sock_priv_destroy, }; diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index a3bdaf075b6b..715f85c6b62e 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -167,7 +167,7 @@ netdev_nl_napi_fill_one(struct sk_buff *rsp, struct napi_struct *napi, void *hdr; pid_t pid; - if (!(napi->dev->flags & IFF_UP)) + if (!napi->dev->up) return 0; hdr = genlmsg_iput(rsp, info); @@ -229,20 +229,15 @@ int netdev_nl_napi_get_doit(struct sk_buff *skb, struct genl_info *info) if (!rsp) return -ENOMEM; - rtnl_lock(); - rcu_read_lock(); - - napi = netdev_napi_by_id(genl_info_net(info), napi_id); + napi = netdev_napi_by_id_lock(genl_info_net(info), napi_id); if (napi) { err = netdev_nl_napi_fill_one(rsp, napi, info); + netdev_unlock(napi->dev); } else { NL_SET_BAD_ATTR(info->extack, info->attrs[NETDEV_A_NAPI_ID]); err = -ENOENT; } - rcu_read_unlock(); - rtnl_unlock(); - if (err) { goto err_free_msg; } else if (!rsp->len) { @@ -263,14 +258,21 @@ netdev_nl_napi_dump_one(struct net_device *netdev, struct sk_buff *rsp, struct netdev_nl_dump_ctx *ctx) { struct napi_struct *napi; + unsigned int prev_id; int err = 0; - if (!(netdev->flags & IFF_UP)) + if (!netdev->up) return err; + prev_id = UINT_MAX; list_for_each_entry(napi, &netdev->napi_list, dev_list) { if (napi->napi_id < MIN_NAPI_ID) continue; + + /* Dump continuation below depends on the list being sorted */ + WARN_ON_ONCE(napi->napi_id >= prev_id); + prev_id = napi->napi_id; + if (ctx->napi_id && napi->napi_id >= ctx->napi_id) continue; @@ -294,22 +296,22 @@ int netdev_nl_napi_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) if (info->attrs[NETDEV_A_NAPI_IFINDEX]) ifindex = nla_get_u32(info->attrs[NETDEV_A_NAPI_IFINDEX]); - rtnl_lock(); if (ifindex) { - netdev = __dev_get_by_index(net, ifindex); - if (netdev) + netdev = netdev_get_by_index_lock(net, ifindex); + if (netdev) { err = netdev_nl_napi_dump_one(netdev, skb, info, ctx); - else + netdev_unlock(netdev); + } else { err = -ENODEV; + } } else { - for_each_netdev_dump(net, netdev, ctx->ifindex) { + for_each_netdev_lock_scoped(net, netdev, ctx->ifindex) { err = netdev_nl_napi_dump_one(netdev, skb, info, ctx); if (err < 0) break; ctx->napi_id = 0; } } - rtnl_unlock(); return err; } @@ -350,20 +352,15 @@ int netdev_nl_napi_set_doit(struct sk_buff *skb, struct genl_info *info) napi_id = nla_get_u32(info->attrs[NETDEV_A_NAPI_ID]); - rtnl_lock(); - rcu_read_lock(); - - napi = netdev_napi_by_id(genl_info_net(info), napi_id); + napi = netdev_napi_by_id_lock(genl_info_net(info), napi_id); if (napi) { err = netdev_nl_napi_set_config(napi, info); + netdev_unlock(napi->dev); } else { NL_SET_BAD_ATTR(info->extack, info->attrs[NETDEV_A_NAPI_ID]); err = -ENOENT; } - rcu_read_unlock(); - rtnl_unlock(); - return err; } @@ -435,7 +432,7 @@ netdev_nl_queue_fill(struct sk_buff *rsp, struct net_device *netdev, u32 q_idx, { int err; - if (!(netdev->flags & IFF_UP)) + if (!netdev->up) return -ENOENT; err = netdev_nl_queue_validate(netdev, q_idx, q_type); @@ -467,11 +464,13 @@ int netdev_nl_queue_get_doit(struct sk_buff *skb, struct genl_info *info) rtnl_lock(); - netdev = __dev_get_by_index(genl_info_net(info), ifindex); - if (netdev) + netdev = netdev_get_by_index_lock(genl_info_net(info), ifindex); + if (netdev) { err = netdev_nl_queue_fill(rsp, netdev, q_id, q_type, info); - else + netdev_unlock(netdev); + } else { err = -ENODEV; + } rtnl_unlock(); @@ -492,7 +491,7 @@ netdev_nl_queue_dump_one(struct net_device *netdev, struct sk_buff *rsp, { int err = 0; - if (!(netdev->flags & IFF_UP)) + if (!netdev->up) return err; for (; ctx->rxq_idx < netdev->real_num_rx_queues; ctx->rxq_idx++) { @@ -525,13 +524,15 @@ int netdev_nl_queue_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) rtnl_lock(); if (ifindex) { - netdev = __dev_get_by_index(net, ifindex); - if (netdev) + netdev = netdev_get_by_index_lock(net, ifindex); + if (netdev) { err = netdev_nl_queue_dump_one(netdev, skb, info, ctx); - else + netdev_unlock(netdev); + } else { err = -ENODEV; + } } else { - for_each_netdev_dump(net, netdev, ctx->ifindex) { + for_each_netdev_lock_scoped(net, netdev, ctx->ifindex) { err = netdev_nl_queue_dump_one(netdev, skb, info, ctx); if (err < 0) break; diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 6f2647b000b8..62b4041aae1a 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -627,6 +627,8 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev) const struct net_device_ops *ops; int err; + skb_queue_head_init(&np->skb_pool); + if (ndev->priv_flags & IFF_DISABLE_NETPOLL) { np_err(np, "%s doesn't support polling, aborting\n", ndev->name); @@ -662,6 +664,9 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev) strscpy(np->dev_name, ndev->name, IFNAMSIZ); npinfo->netpoll = np; + /* fill up the skb queue */ + refill_skbs(np); + /* last thing to do is link it to the net device structure */ rcu_assign_pointer(ndev->npinfo, npinfo); @@ -681,8 +686,6 @@ int netpoll_setup(struct netpoll *np) struct in_device *in_dev; int err; - skb_queue_head_init(&np->skb_pool); - rtnl_lock(); if (np->dev_name[0]) { struct net *net = current->nsproxy->net_ns; @@ -782,9 +785,6 @@ put_noaddr: } } - /* fill up the skb queue */ - refill_skbs(np); - err = __netpoll_setup(np, ndev); if (err) goto flush; diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 9733206d6406..a3de752c5178 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -595,13 +595,13 @@ netmem_ref page_pool_alloc_netmems(struct page_pool *pool, gfp_t gfp) return netmem; } EXPORT_SYMBOL(page_pool_alloc_netmems); +ALLOW_ERROR_INJECTION(page_pool_alloc_netmems, NULL); struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp) { return netmem_to_page(page_pool_alloc_netmems(pool, gfp)); } EXPORT_SYMBOL(page_pool_alloc_pages); -ALLOW_ERROR_INJECTION(page_pool_alloc_pages, NULL); /* Calculate distance between two u32 values, valid if distance is below 2^(31) * https://en.wikipedia.org/wiki/Serial_number_arithmetic#General_Solution diff --git a/net/core/pktgen.c b/net/core/pktgen.c index ee95dbb0539a..82b6a2c3c141 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -851,6 +851,9 @@ static ssize_t get_imix_entries(const char __user *buffer, unsigned long weight; unsigned long size; + if (pkt_dev->n_imix_entries >= MAX_IMIX_ENTRIES) + return -E2BIG; + len = num_arg(&buffer[i], max_digits, &size); if (len < 0) return len; @@ -880,9 +883,6 @@ static ssize_t get_imix_entries(const char __user *buffer, i++; pkt_dev->n_imix_entries++; - - if (pkt_dev->n_imix_entries > MAX_IMIX_ENTRIES) - return -E2BIG; } while (c == ' '); return i; diff --git a/net/core/rtnl_net_debug.c b/net/core/rtnl_net_debug.c index f406045cbd0e..7ecd28cc1c22 100644 --- a/net/core/rtnl_net_debug.c +++ b/net/core/rtnl_net_debug.c @@ -27,7 +27,6 @@ static int rtnl_net_debug_event(struct notifier_block *nb, case NETDEV_CHANGEADDR: case NETDEV_PRE_CHANGEADDR: case NETDEV_GOING_DOWN: - case NETDEV_CHANGENAME: case NETDEV_FEAT_CHANGE: case NETDEV_BONDING_FAILOVER: case NETDEV_PRE_UP: @@ -60,18 +59,10 @@ static int rtnl_net_debug_event(struct notifier_block *nb, ASSERT_RTNL(); break; - /* Once an event fully supports RTNL_NET, move it here - * and remove "if (0)" below. - * - * case NETDEV_XXX: - * ASSERT_RTNL_NET(net); - * break; - */ - } - - /* Just to avoid unused-variable error for dev and net. */ - if (0) + case NETDEV_CHANGENAME: ASSERT_RTNL_NET(net); + break; + } return NOTIFY_DONE; } diff --git a/net/core/xdp.c b/net/core/xdp.c index 67b53fc7191e..2c6ab6fb452f 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -186,7 +186,6 @@ int __xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, xdp_rxq_info_init(xdp_rxq); xdp_rxq->dev = dev; xdp_rxq->queue_index = queue_index; - xdp_rxq->napi_id = napi_id; xdp_rxq->frag_size = frag_size; xdp_rxq->reg_state = REG_STATE_REGISTERED; diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 5926159a6f20..be515ba821e2 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -15,6 +15,7 @@ #include <net/icmp.h> #include <net/inet_common.h> +#include <net/inet_dscp.h> #include <net/inet_hashtables.h> #include <net/inet_sock.h> #include <net/protocol.h> @@ -473,7 +474,7 @@ static struct dst_entry* dccp_v4_route_skb(struct net *net, struct sock *sk, .flowi4_oif = inet_iif(skb), .daddr = iph->saddr, .saddr = iph->daddr, - .flowi4_tos = ip_sock_rt_tos(sk), + .flowi4_tos = inet_dscp_to_dsfield(inet_sk_dscp(inet_sk(sk))), .flowi4_scope = ip_sock_rt_scope(sk), .flowi4_proto = sk->sk_protocol, .fl4_sport = dccp_hdr(skb)->dccph_dport, diff --git a/net/dsa/user.c b/net/dsa/user.c index c74f2b2b92de..291ab1b4acc4 100644 --- a/net/dsa/user.c +++ b/net/dsa/user.c @@ -1150,6 +1150,16 @@ dsa_user_get_rmon_stats(struct net_device *dev, ds->ops->get_rmon_stats(ds, dp->index, rmon_stats, ranges); } +static void dsa_user_get_ts_stats(struct net_device *dev, + struct ethtool_ts_stats *ts_stats) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + + if (ds->ops->get_ts_stats) + ds->ops->get_ts_stats(ds, dp->index, ts_stats); +} + static void dsa_user_net_selftest(struct net_device *ndev, struct ethtool_test *etest, u64 *buf) { @@ -2501,6 +2511,7 @@ static const struct ethtool_ops dsa_user_ethtool_ops = { .get_eth_mac_stats = dsa_user_get_eth_mac_stats, .get_eth_ctrl_stats = dsa_user_get_eth_ctrl_stats, .get_rmon_stats = dsa_user_get_rmon_stats, + .get_ts_stats = dsa_user_get_ts_stats, .set_wol = dsa_user_set_wol, .get_wol = dsa_user_get_wol, .set_eee = dsa_user_set_eee, diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 2607aea1fbfb..2bd77c94f9f1 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -869,6 +869,7 @@ int __ethtool_get_ts_info(struct net_device *dev, struct kernel_ethtool_ts_info *info) { struct hwtstamp_provider *hwprov; + int err = 0; rcu_read_lock(); hwprov = rcu_dereference(dev->hwprov); @@ -876,7 +877,6 @@ int __ethtool_get_ts_info(struct net_device *dev, if (!hwprov) { const struct ethtool_ops *ops = dev->ethtool_ops; struct phy_device *phydev = dev->phydev; - int err = 0; ethtool_init_tsinfo(info); if (phy_is_default_hwtstamp(phydev) && @@ -892,8 +892,9 @@ int __ethtool_get_ts_info(struct net_device *dev, return err; } + err = ethtool_get_ts_info_by_phc(dev, info, &hwprov->desc); rcu_read_unlock(); - return ethtool_get_ts_info_by_phc(dev, info, &hwprov->desc); + return err; } bool net_support_hwtstamp_qualifier(struct net_device *dev, diff --git a/net/ethtool/linkstate.c b/net/ethtool/linkstate.c index 34d76e87847d..af19e1bed303 100644 --- a/net/ethtool/linkstate.c +++ b/net/ethtool/linkstate.c @@ -3,6 +3,7 @@ #include "netlink.h" #include "common.h" #include <linux/phy.h> +#include <linux/phylib_stubs.h> struct linkstate_req_info { struct ethnl_req_info base; @@ -26,9 +27,8 @@ const struct nla_policy ethnl_linkstate_get_policy[] = { NLA_POLICY_NESTED(ethnl_header_policy_stats), }; -static int linkstate_get_sqi(struct net_device *dev) +static int linkstate_get_sqi(struct phy_device *phydev) { - struct phy_device *phydev = dev->phydev; int ret; if (!phydev) @@ -46,9 +46,8 @@ static int linkstate_get_sqi(struct net_device *dev) return ret; } -static int linkstate_get_sqi_max(struct net_device *dev) +static int linkstate_get_sqi_max(struct phy_device *phydev) { - struct phy_device *phydev = dev->phydev; int ret; if (!phydev) @@ -100,19 +99,28 @@ static int linkstate_prepare_data(const struct ethnl_req_info *req_base, { struct linkstate_reply_data *data = LINKSTATE_REPDATA(reply_base); struct net_device *dev = reply_base->dev; + struct nlattr **tb = info->attrs; + struct phy_device *phydev; int ret; + phydev = ethnl_req_get_phydev(req_base, tb[ETHTOOL_A_LINKSTATE_HEADER], + info->extack); + if (IS_ERR(phydev)) { + ret = PTR_ERR(phydev); + goto out; + } + ret = ethnl_ops_begin(dev); if (ret < 0) return ret; data->link = __ethtool_get_link(dev); - ret = linkstate_get_sqi(dev); + ret = linkstate_get_sqi(phydev); if (linkstate_sqi_critical_error(ret)) goto out; data->sqi = ret; - ret = linkstate_get_sqi_max(dev); + ret = linkstate_get_sqi_max(phydev); if (linkstate_sqi_critical_error(ret)) goto out; data->sqi_max = ret; @@ -127,9 +135,9 @@ static int linkstate_prepare_data(const struct ethnl_req_info *req_base, sizeof(data->link_stats) / 8); if (req_base->flags & ETHTOOL_FLAG_STATS) { - if (dev->phydev) - data->link_stats.link_down_events = - READ_ONCE(dev->phydev->link_down_events); + if (phydev) + phy_ethtool_get_link_ext_stats(phydev, + &data->link_stats); if (dev->ethtool_ops->get_link_ext_stats) dev->ethtool_ops->get_link_ext_stats(dev, diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 0a09298fff92..ff69ca0715de 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -456,7 +456,7 @@ extern const struct nla_policy ethnl_features_set_policy[ETHTOOL_A_FEATURES_WANT extern const struct nla_policy ethnl_privflags_get_policy[ETHTOOL_A_PRIVFLAGS_HEADER + 1]; extern const struct nla_policy ethnl_privflags_set_policy[ETHTOOL_A_PRIVFLAGS_FLAGS + 1]; extern const struct nla_policy ethnl_rings_get_policy[ETHTOOL_A_RINGS_HEADER + 1]; -extern const struct nla_policy ethnl_rings_set_policy[ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN_MAX + 1]; +extern const struct nla_policy ethnl_rings_set_policy[ETHTOOL_A_RINGS_HDS_THRESH_MAX + 1]; extern const struct nla_policy ethnl_channels_get_policy[ETHTOOL_A_CHANNELS_HEADER + 1]; extern const struct nla_policy ethnl_channels_set_policy[ETHTOOL_A_CHANNELS_COMBINED_COUNT + 1]; extern const struct nla_policy ethnl_coalesce_get_policy[ETHTOOL_A_COALESCE_HEADER + 1]; @@ -511,5 +511,6 @@ extern const char stats_eth_phy_names[__ETHTOOL_A_STATS_ETH_PHY_CNT][ETH_GSTRING extern const char stats_eth_mac_names[__ETHTOOL_A_STATS_ETH_MAC_CNT][ETH_GSTRING_LEN]; extern const char stats_eth_ctrl_names[__ETHTOOL_A_STATS_ETH_CTRL_CNT][ETH_GSTRING_LEN]; extern const char stats_rmon_names[__ETHTOOL_A_STATS_RMON_CNT][ETH_GSTRING_LEN]; +extern const char stats_phy_names[__ETHTOOL_A_STATS_PHY_CNT][ETH_GSTRING_LEN]; #endif /* _NET_ETHTOOL_NETLINK_H */ diff --git a/net/ethtool/pse-pd.c b/net/ethtool/pse-pd.c index a0705edca22a..2819e2ba6be2 100644 --- a/net/ethtool/pse-pd.c +++ b/net/ethtool/pse-pd.c @@ -19,7 +19,7 @@ struct pse_req_info { struct pse_reply_data { struct ethnl_reply_data base; - struct pse_control_status status; + struct ethtool_pse_control_status status; }; #define PSE_REPDATA(__reply_base) \ @@ -80,7 +80,7 @@ static int pse_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct pse_reply_data *data = PSE_REPDATA(reply_base); - const struct pse_control_status *st = &data->status; + const struct ethtool_pse_control_status *st = &data->status; int len = 0; if (st->podl_admin_state > 0) @@ -114,7 +114,7 @@ static int pse_reply_size(const struct ethnl_req_info *req_base, } static int pse_put_pw_limit_ranges(struct sk_buff *skb, - const struct pse_control_status *st) + const struct ethtool_pse_control_status *st) { const struct ethtool_c33_pse_pw_limit_range *pw_limit_ranges; int i; @@ -146,7 +146,7 @@ static int pse_fill_reply(struct sk_buff *skb, const struct ethnl_reply_data *reply_base) { const struct pse_reply_data *data = PSE_REPDATA(reply_base); - const struct pse_control_status *st = &data->status; + const struct ethtool_pse_control_status *st = &data->status; if (st->podl_admin_state > 0 && nla_put_u32(skb, ETHTOOL_A_PODL_PSE_ADMIN_STATE, diff --git a/net/ethtool/rings.c b/net/ethtool/rings.c index b7865a14fdf8..d8cd4e4d7762 100644 --- a/net/ethtool/rings.c +++ b/net/ethtool/rings.c @@ -61,7 +61,9 @@ static int rings_reply_size(const struct ethnl_req_info *req_base, nla_total_size(sizeof(u8)) + /* _RINGS_TX_PUSH */ nla_total_size(sizeof(u8))) + /* _RINGS_RX_PUSH */ nla_total_size(sizeof(u32)) + /* _RINGS_TX_PUSH_BUF_LEN */ - nla_total_size(sizeof(u32)); /* _RINGS_TX_PUSH_BUF_LEN_MAX */ + nla_total_size(sizeof(u32)) + /* _RINGS_TX_PUSH_BUF_LEN_MAX */ + nla_total_size(sizeof(u32)) + /* _RINGS_HDS_THRESH */ + nla_total_size(sizeof(u32)); /* _RINGS_HDS_THRESH_MAX*/ } static int rings_fill_reply(struct sk_buff *skb, @@ -108,7 +110,12 @@ static int rings_fill_reply(struct sk_buff *skb, (nla_put_u32(skb, ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN_MAX, kr->tx_push_buf_max_len) || nla_put_u32(skb, ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN, - kr->tx_push_buf_len)))) + kr->tx_push_buf_len))) || + ((supported_ring_params & ETHTOOL_RING_USE_HDS_THRS) && + (nla_put_u32(skb, ETHTOOL_A_RINGS_HDS_THRESH, + kr->hds_thresh) || + nla_put_u32(skb, ETHTOOL_A_RINGS_HDS_THRESH_MAX, + kr->hds_thresh_max)))) return -EMSGSIZE; return 0; @@ -130,6 +137,7 @@ const struct nla_policy ethnl_rings_set_policy[] = { [ETHTOOL_A_RINGS_TX_PUSH] = NLA_POLICY_MAX(NLA_U8, 1), [ETHTOOL_A_RINGS_RX_PUSH] = NLA_POLICY_MAX(NLA_U8, 1), [ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN] = { .type = NLA_U32 }, + [ETHTOOL_A_RINGS_HDS_THRESH] = { .type = NLA_U32 }, }; static int @@ -155,6 +163,14 @@ ethnl_set_rings_validate(struct ethnl_req_info *req_info, return -EOPNOTSUPP; } + if (tb[ETHTOOL_A_RINGS_HDS_THRESH] && + !(ops->supported_ring_params & ETHTOOL_RING_USE_HDS_THRS)) { + NL_SET_ERR_MSG_ATTR(info->extack, + tb[ETHTOOL_A_RINGS_HDS_THRESH], + "setting hds-thresh is not supported"); + return -EOPNOTSUPP; + } + if (tb[ETHTOOL_A_RINGS_CQE_SIZE] && !(ops->supported_ring_params & ETHTOOL_RING_USE_CQE_SIZE)) { NL_SET_ERR_MSG_ATTR(info->extack, @@ -203,6 +219,7 @@ ethnl_set_rings(struct ethnl_req_info *req_info, struct genl_info *info) dev->ethtool_ops->get_ringparam(dev, &ringparam, &kernel_ringparam, info->extack); + kernel_ringparam.tcp_data_split = dev->ethtool->hds_config; ethnl_update_u32(&ringparam.rx_pending, tb[ETHTOOL_A_RINGS_RX], &mod); ethnl_update_u32(&ringparam.rx_mini_pending, @@ -222,9 +239,32 @@ ethnl_set_rings(struct ethnl_req_info *req_info, struct genl_info *info) tb[ETHTOOL_A_RINGS_RX_PUSH], &mod); ethnl_update_u32(&kernel_ringparam.tx_push_buf_len, tb[ETHTOOL_A_RINGS_TX_PUSH_BUF_LEN], &mod); + ethnl_update_u32(&kernel_ringparam.hds_thresh, + tb[ETHTOOL_A_RINGS_HDS_THRESH], &mod); if (!mod) return 0; + if (kernel_ringparam.tcp_data_split == ETHTOOL_TCP_DATA_SPLIT_ENABLED && + dev_xdp_sb_prog_count(dev)) { + NL_SET_ERR_MSG_ATTR(info->extack, + tb[ETHTOOL_A_RINGS_TCP_DATA_SPLIT], + "tcp-data-split can not be enabled with single buffer XDP"); + return -EINVAL; + } + + if (dev_get_min_mp_channel_count(dev)) { + if (kernel_ringparam.tcp_data_split != + ETHTOOL_TCP_DATA_SPLIT_ENABLED) { + NL_SET_ERR_MSG(info->extack, + "can't disable tcp-data-split while device has memory provider enabled"); + return -EINVAL; + } else if (kernel_ringparam.hds_thresh) { + NL_SET_ERR_MSG(info->extack, + "can't set non-zero hds_thresh while device is memory provider enabled"); + return -EINVAL; + } + } + /* ensure new ring parameters are within limits */ if (ringparam.rx_pending > ringparam.rx_max_pending) err_attr = tb[ETHTOOL_A_RINGS_RX]; @@ -234,6 +274,8 @@ ethnl_set_rings(struct ethnl_req_info *req_info, struct genl_info *info) err_attr = tb[ETHTOOL_A_RINGS_RX_JUMBO]; else if (ringparam.tx_pending > ringparam.tx_max_pending) err_attr = tb[ETHTOOL_A_RINGS_TX]; + else if (kernel_ringparam.hds_thresh > kernel_ringparam.hds_thresh_max) + err_attr = tb[ETHTOOL_A_RINGS_HDS_THRESH]; else err_attr = NULL; if (err_attr) { @@ -252,6 +294,11 @@ ethnl_set_rings(struct ethnl_req_info *req_info, struct genl_info *info) ret = dev->ethtool_ops->set_ringparam(dev, &ringparam, &kernel_ringparam, info->extack); + if (!ret) { + dev->ethtool->hds_config = kernel_ringparam.tcp_data_split; + dev->ethtool->hds_thresh = kernel_ringparam.hds_thresh; + } + return ret < 0 ? ret : 1; } diff --git a/net/ethtool/stats.c b/net/ethtool/stats.c index 912f0c4fff2f..038a2558f052 100644 --- a/net/ethtool/stats.c +++ b/net/ethtool/stats.c @@ -1,5 +1,8 @@ // SPDX-License-Identifier: GPL-2.0-only +#include <linux/phy.h> +#include <linux/phylib_stubs.h> + #include "netlink.h" #include "common.h" #include "bitset.h" @@ -20,6 +23,7 @@ struct stats_reply_data { struct ethtool_eth_mac_stats mac_stats; struct ethtool_eth_ctrl_stats ctrl_stats; struct ethtool_rmon_stats rmon_stats; + struct ethtool_phy_stats phydev_stats; ); const struct ethtool_rmon_hist_range *rmon_ranges; }; @@ -32,6 +36,7 @@ const char stats_std_names[__ETHTOOL_STATS_CNT][ETH_GSTRING_LEN] = { [ETHTOOL_STATS_ETH_MAC] = "eth-mac", [ETHTOOL_STATS_ETH_CTRL] = "eth-ctrl", [ETHTOOL_STATS_RMON] = "rmon", + [ETHTOOL_STATS_PHY] = "phydev", }; const char stats_eth_phy_names[__ETHTOOL_A_STATS_ETH_PHY_CNT][ETH_GSTRING_LEN] = { @@ -76,6 +81,15 @@ const char stats_rmon_names[__ETHTOOL_A_STATS_RMON_CNT][ETH_GSTRING_LEN] = { [ETHTOOL_A_STATS_RMON_JABBER] = "etherStatsJabbers", }; +const char stats_phy_names[__ETHTOOL_A_STATS_PHY_CNT][ETH_GSTRING_LEN] = { + [ETHTOOL_A_STATS_PHY_RX_PKTS] = "RxFrames", + [ETHTOOL_A_STATS_PHY_RX_BYTES] = "RxOctets", + [ETHTOOL_A_STATS_PHY_RX_ERRORS] = "RxErrors", + [ETHTOOL_A_STATS_PHY_TX_PKTS] = "TxFrames", + [ETHTOOL_A_STATS_PHY_TX_BYTES] = "TxOctets", + [ETHTOOL_A_STATS_PHY_TX_ERRORS] = "TxErrors", +}; + const struct nla_policy ethnl_stats_get_policy[ETHTOOL_A_STATS_SRC + 1] = { [ETHTOOL_A_STATS_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), @@ -120,8 +134,15 @@ static int stats_prepare_data(const struct ethnl_req_info *req_base, struct stats_reply_data *data = STATS_REPDATA(reply_base); enum ethtool_mac_stats_src src = req_info->src; struct net_device *dev = reply_base->dev; + struct nlattr **tb = info->attrs; + struct phy_device *phydev; int ret; + phydev = ethnl_req_get_phydev(req_base, tb[ETHTOOL_A_STATS_HEADER], + info->extack); + if (IS_ERR(phydev)) + return PTR_ERR(phydev); + ret = ethnl_ops_begin(dev); if (ret < 0) return ret; @@ -145,6 +166,14 @@ static int stats_prepare_data(const struct ethnl_req_info *req_base, data->ctrl_stats.src = src; data->rmon_stats.src = src; + if ((test_bit(ETHTOOL_STATS_PHY, req_info->stat_mask) || + test_bit(ETHTOOL_STATS_ETH_PHY, req_info->stat_mask)) && + src == ETHTOOL_MAC_STATS_SRC_AGGREGATE) { + if (phydev) + phy_ethtool_get_phy_stats(phydev, &data->phy_stats, + &data->phydev_stats); + } + if (test_bit(ETHTOOL_STATS_ETH_PHY, req_info->stat_mask) && dev->ethtool_ops->get_eth_phy_stats) dev->ethtool_ops->get_eth_phy_stats(dev, &data->phy_stats); @@ -194,6 +223,10 @@ static int stats_reply_size(const struct ethnl_req_info *req_base, nla_total_size(4)) * /* _A_STATS_GRP_HIST_BKT_HI */ ETHTOOL_RMON_HIST_MAX * 2; } + if (test_bit(ETHTOOL_STATS_PHY, req_info->stat_mask)) { + n_stats += sizeof(struct ethtool_phy_stats) / sizeof(u64); + n_grps++; + } len += n_grps * (nla_total_size(0) + /* _A_STATS_GRP */ nla_total_size(4) + /* _A_STATS_GRP_ID */ @@ -247,6 +280,25 @@ static int stats_put_phy_stats(struct sk_buff *skb, return 0; } +static int stats_put_phydev_stats(struct sk_buff *skb, + const struct stats_reply_data *data) +{ + if (stat_put(skb, ETHTOOL_A_STATS_PHY_RX_PKTS, + data->phydev_stats.rx_packets) || + stat_put(skb, ETHTOOL_A_STATS_PHY_RX_BYTES, + data->phydev_stats.rx_bytes) || + stat_put(skb, ETHTOOL_A_STATS_PHY_RX_ERRORS, + data->phydev_stats.rx_errors) || + stat_put(skb, ETHTOOL_A_STATS_PHY_TX_PKTS, + data->phydev_stats.tx_packets) || + stat_put(skb, ETHTOOL_A_STATS_PHY_TX_BYTES, + data->phydev_stats.tx_bytes) || + stat_put(skb, ETHTOOL_A_STATS_PHY_TX_ERRORS, + data->phydev_stats.tx_errors)) + return -EMSGSIZE; + return 0; +} + static int stats_put_mac_stats(struct sk_buff *skb, const struct stats_reply_data *data) { @@ -423,6 +475,9 @@ static int stats_fill_reply(struct sk_buff *skb, if (!ret && test_bit(ETHTOOL_STATS_RMON, req_info->stat_mask)) ret = stats_put_stats(skb, data, ETHTOOL_STATS_RMON, ETH_SS_STATS_RMON, stats_put_rmon_stats); + if (!ret && test_bit(ETHTOOL_STATS_PHY, req_info->stat_mask)) + ret = stats_put_stats(skb, data, ETHTOOL_STATS_PHY, + ETH_SS_STATS_PHY, stats_put_phydev_stats); return ret; } diff --git a/net/ethtool/strset.c b/net/ethtool/strset.c index b3382b3cf325..818cf01f0911 100644 --- a/net/ethtool/strset.c +++ b/net/ethtool/strset.c @@ -105,6 +105,11 @@ static const struct strset_info info_template[] = { .count = __ETHTOOL_A_STATS_RMON_CNT, .strings = stats_rmon_names, }, + [ETH_SS_STATS_PHY] = { + .per_dev = false, + .count = __ETHTOOL_A_STATS_PHY_CNT, + .strings = stats_phy_names, + }, }; struct strset_req_info { diff --git a/net/ethtool/tsinfo.c b/net/ethtool/tsinfo.c index 7e495a41aeec..691be6c445b3 100644 --- a/net/ethtool/tsinfo.c +++ b/net/ethtool/tsinfo.c @@ -186,6 +186,8 @@ static int tsinfo_put_stats(struct sk_buff *skb, if (tsinfo_put_stat(skb, stats->tx_stats.pkts, ETHTOOL_A_TS_STAT_TX_PKTS) || + tsinfo_put_stat(skb, stats->tx_stats.onestep_pkts_unconfirmed, + ETHTOOL_A_TS_STAT_TX_ONESTEP_PKTS_UNCONFIRMED) || tsinfo_put_stat(skb, stats->tx_stats.lost, ETHTOOL_A_TS_STAT_TX_LOST) || tsinfo_put_stat(skb, stats->tx_stats.err, diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index 03eadd6c51fd..b6fb18469439 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -663,6 +663,19 @@ bool is_hsr_master(struct net_device *dev) } EXPORT_SYMBOL(is_hsr_master); +struct net_device *hsr_get_port_ndev(struct net_device *ndev, + enum hsr_port_type pt) +{ + struct hsr_priv *hsr = netdev_priv(ndev); + struct hsr_port *port; + + hsr_for_each_port(hsr, port) + if (port->type == pt) + return port->dev; + return NULL; +} +EXPORT_SYMBOL(hsr_get_port_ndev); + /* Default multicast address for HSR Supervision frames */ static const unsigned char def_multicast_addr[ETH_ALEN] __aligned(2) = { 0x01, 0x15, 0x4e, 0x00, 0x01, 0x00 diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h index 7d7551e6f0b0..7561845b8bf6 100644 --- a/net/hsr/hsr_main.h +++ b/net/hsr/hsr_main.h @@ -121,15 +121,6 @@ struct hsrv1_ethhdr_sp { struct hsr_sup_tag hsr_sup; } __packed; -enum hsr_port_type { - HSR_PT_NONE = 0, /* Must be 0, used by framereg */ - HSR_PT_SLAVE_A, - HSR_PT_SLAVE_B, - HSR_PT_INTERLINK, - HSR_PT_MASTER, - HSR_PT_PORTS, /* This must be the last item in the enum */ -}; - /* PRP Redunancy Control Trailor (RCT). * As defined in IEC-62439-4:2012, the PRP RCT is really { sequence Nr, * Lan indentifier (LanId), LSDU_size and PRP_suffix = 0x88FB }. diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index a020342f618d..ed1b6b44faf8 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -926,7 +926,7 @@ static int ipgre_open(struct net_device *dev) if (ipv4_is_multicast(t->parms.iph.daddr)) { struct flowi4 fl4 = { .flowi4_oif = t->parms.link, - .flowi4_tos = t->parms.iph.tos & INET_DSCP_MASK, + .flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(&t->parms.iph)), .flowi4_scope = RT_SCOPE_UNIVERSE, .flowi4_proto = IPPROTO_GRE, .saddr = t->parms.iph.saddr, diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 99d8faa508e5..21ae7594a852 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -831,7 +831,7 @@ static void ipmr_update_thresholds(struct mr_table *mrt, struct mr_mfc *cache, cache->mfc_un.res.maxvif = vifi + 1; } } - cache->mfc_un.res.lastuse = jiffies; + WRITE_ONCE(cache->mfc_un.res.lastuse, jiffies); } static int vif_add(struct net *net, struct mr_table *mrt, @@ -1681,9 +1681,9 @@ int ipmr_ioctl(struct sock *sk, int cmd, void *arg) rcu_read_lock(); c = ipmr_cache_find(mrt, sr->src.s_addr, sr->grp.s_addr); if (c) { - sr->pktcnt = c->_c.mfc_un.res.pkt; - sr->bytecnt = c->_c.mfc_un.res.bytes; - sr->wrong_if = c->_c.mfc_un.res.wrong_if; + sr->pktcnt = atomic_long_read(&c->_c.mfc_un.res.pkt); + sr->bytecnt = atomic_long_read(&c->_c.mfc_un.res.bytes); + sr->wrong_if = atomic_long_read(&c->_c.mfc_un.res.wrong_if); rcu_read_unlock(); return 0; } @@ -1753,9 +1753,9 @@ int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) rcu_read_lock(); c = ipmr_cache_find(mrt, sr.src.s_addr, sr.grp.s_addr); if (c) { - sr.pktcnt = c->_c.mfc_un.res.pkt; - sr.bytecnt = c->_c.mfc_un.res.bytes; - sr.wrong_if = c->_c.mfc_un.res.wrong_if; + sr.pktcnt = atomic_long_read(&c->_c.mfc_un.res.pkt); + sr.bytecnt = atomic_long_read(&c->_c.mfc_un.res.bytes); + sr.wrong_if = atomic_long_read(&c->_c.mfc_un.res.wrong_if); rcu_read_unlock(); if (copy_to_user(arg, &sr, sizeof(sr))) @@ -1988,9 +1988,9 @@ static void ip_mr_forward(struct net *net, struct mr_table *mrt, int vif, ct; vif = c->_c.mfc_parent; - c->_c.mfc_un.res.pkt++; - c->_c.mfc_un.res.bytes += skb->len; - c->_c.mfc_un.res.lastuse = jiffies; + atomic_long_inc(&c->_c.mfc_un.res.pkt); + atomic_long_add(skb->len, &c->_c.mfc_un.res.bytes); + WRITE_ONCE(c->_c.mfc_un.res.lastuse, jiffies); if (c->mfc_origin == htonl(INADDR_ANY) && true_vifi >= 0) { struct mfc_cache *cache_proxy; @@ -2021,7 +2021,7 @@ static void ip_mr_forward(struct net *net, struct mr_table *mrt, goto dont_forward; } - c->_c.mfc_un.res.wrong_if++; + atomic_long_inc(&c->_c.mfc_un.res.wrong_if); if (true_vifi >= 0 && mrt->mroute_do_assert && /* pimsm uses asserts, when switching from RPT to SPT, @@ -3029,9 +3029,9 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) if (it->cache != &mrt->mfc_unres_queue) { seq_printf(seq, " %8lu %8lu %8lu", - mfc->_c.mfc_un.res.pkt, - mfc->_c.mfc_un.res.bytes, - mfc->_c.mfc_un.res.wrong_if); + atomic_long_read(&mfc->_c.mfc_un.res.pkt), + atomic_long_read(&mfc->_c.mfc_un.res.bytes), + atomic_long_read(&mfc->_c.mfc_un.res.wrong_if)); for (n = mfc->_c.mfc_un.res.minvif; n < mfc->_c.mfc_un.res.maxvif; n++) { if (VIF_EXISTS(mrt, n) && diff --git a/net/ipv4/ipmr_base.c b/net/ipv4/ipmr_base.c index f0af12a2f70b..03b6eee407a2 100644 --- a/net/ipv4/ipmr_base.c +++ b/net/ipv4/ipmr_base.c @@ -263,9 +263,9 @@ int mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, lastuse = READ_ONCE(c->mfc_un.res.lastuse); lastuse = time_after_eq(jiffies, lastuse) ? jiffies - lastuse : 0; - mfcs.mfcs_packets = c->mfc_un.res.pkt; - mfcs.mfcs_bytes = c->mfc_un.res.bytes; - mfcs.mfcs_wrong_if = c->mfc_un.res.wrong_if; + mfcs.mfcs_packets = atomic_long_read(&c->mfc_un.res.pkt); + mfcs.mfcs_bytes = atomic_long_read(&c->mfc_un.res.bytes); + mfcs.mfcs_wrong_if = atomic_long_read(&c->mfc_un.res.wrong_if); if (nla_put_64bit(skb, RTA_MFC_STATS, sizeof(mfcs), &mfcs, RTA_PAD) || nla_put_u64_64bit(skb, RTA_EXPIRES, jiffies_to_clock_t(lastuse), RTA_PAD)) diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 40053a02bae1..affd21a0f572 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -189,6 +189,7 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TWKilled", LINUX_MIB_TIMEWAITKILLED), SNMP_MIB_ITEM("PAWSActive", LINUX_MIB_PAWSACTIVEREJECTED), SNMP_MIB_ITEM("PAWSEstab", LINUX_MIB_PAWSESTABREJECTED), + SNMP_MIB_ITEM("PAWSOldAck", LINUX_MIB_PAWS_OLD_ACK), SNMP_MIB_ITEM("DelayedACKs", LINUX_MIB_DELAYEDACKS), SNMP_MIB_ITEM("DelayedACKLocked", LINUX_MIB_DELAYEDACKLOCKED), SNMP_MIB_ITEM("DelayedACKLost", LINUX_MIB_DELAYEDACKLOST), diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 9f9d4e6ea1b9..577b88a43293 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2446,6 +2446,7 @@ martian_destination: net_warn_ratelimited("martian destination %pI4 from %pI4, dev %s\n", &daddr, &saddr, dev->name); #endif + goto out; e_nobufs: reason = SKB_DROP_REASON_NOMEM; @@ -3269,6 +3270,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct flowi4 fl4 = {}; __be32 dst = 0; __be32 src = 0; + dscp_t dscp; kuid_t uid; u32 iif; int err; @@ -3283,6 +3285,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, dst = nla_get_in_addr_default(tb[RTA_DST], 0); iif = nla_get_u32_default(tb[RTA_IIF], 0); mark = nla_get_u32_default(tb[RTA_MARK], 0); + dscp = inet_dsfield_to_dscp(rtm->rtm_tos); if (tb[RTA_UID]) uid = make_kuid(current_user_ns(), nla_get_u32(tb[RTA_UID])); else @@ -3307,7 +3310,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, fl4.daddr = dst; fl4.saddr = src; - fl4.flowi4_tos = rtm->rtm_tos & INET_DSCP_MASK; + fl4.flowi4_tos = inet_dscp_to_dsfield(dscp); fl4.flowi4_oif = nla_get_u32_default(tb[RTA_OIF], 0); fl4.flowi4_mark = mark; fl4.flowi4_uid = uid; @@ -3331,9 +3334,8 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, fl4.flowi4_iif = iif; /* for rt_fill_info */ skb->dev = dev; skb->mark = mark; - err = ip_route_input_rcu(skb, dst, src, - inet_dsfield_to_dscp(rtm->rtm_tos), - dev, &res) ? -EINVAL : 0; + err = ip_route_input_rcu(skb, dst, src, dscp, dev, + &res) ? -EINVAL : 0; rt = skb_rtable(skb); if (err == 0 && rt->dst.error) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 4811727b8a02..eb82e01da911 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4450,34 +4450,40 @@ static u32 tcp_tsval_replay(const struct sock *sk) return inet_csk(sk)->icsk_rto * 1200 / HZ; } -static int tcp_disordered_ack(const struct sock *sk, const struct sk_buff *skb) +static enum skb_drop_reason tcp_disordered_ack_check(const struct sock *sk, + const struct sk_buff *skb) { const struct tcp_sock *tp = tcp_sk(sk); const struct tcphdr *th = tcp_hdr(skb); - u32 seq = TCP_SKB_CB(skb)->seq; + SKB_DR_INIT(reason, TCP_RFC7323_PAWS); u32 ack = TCP_SKB_CB(skb)->ack_seq; + u32 seq = TCP_SKB_CB(skb)->seq; - return /* 1. Pure ACK with correct sequence number. */ - (th->ack && seq == TCP_SKB_CB(skb)->end_seq && seq == tp->rcv_nxt) && + /* 1. Is this not a pure ACK ? */ + if (!th->ack || seq != TCP_SKB_CB(skb)->end_seq) + return reason; - /* 2. ... and duplicate ACK. */ - ack == tp->snd_una && + /* 2. Is its sequence not the expected one ? */ + if (seq != tp->rcv_nxt) + return before(seq, tp->rcv_nxt) ? + SKB_DROP_REASON_TCP_RFC7323_PAWS_ACK : + reason; - /* 3. ... and does not update window. */ - !tcp_may_update_window(tp, ack, seq, ntohs(th->window) << tp->rx_opt.snd_wscale) && + /* 3. Is this not a duplicate ACK ? */ + if (ack != tp->snd_una) + return reason; - /* 4. ... and sits in replay window. */ - (s32)(tp->rx_opt.ts_recent - tp->rx_opt.rcv_tsval) <= - tcp_tsval_replay(sk); -} + /* 4. Is this updating the window ? */ + if (tcp_may_update_window(tp, ack, seq, ntohs(th->window) << + tp->rx_opt.snd_wscale)) + return reason; -static inline bool tcp_paws_discard(const struct sock *sk, - const struct sk_buff *skb) -{ - const struct tcp_sock *tp = tcp_sk(sk); + /* 5. Is this not in the replay window ? */ + if ((s32)(tp->rx_opt.ts_recent - tp->rx_opt.rcv_tsval) > + tcp_tsval_replay(sk)) + return reason; - return !tcp_paws_check(&tp->rx_opt, TCP_PAWS_WINDOW) && - !tcp_disordered_ack(sk, skb); + return 0; } /* Check segment sequence number for validity. @@ -5949,23 +5955,35 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, SKB_DR(reason); /* RFC1323: H1. Apply PAWS check first. */ - if (tcp_fast_parse_options(sock_net(sk), skb, th, tp) && - tp->rx_opt.saw_tstamp && - tcp_paws_discard(sk, skb)) { - if (!th->rst) { - if (unlikely(th->syn)) - goto syn_challenge; - NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED); - if (!tcp_oow_rate_limited(sock_net(sk), skb, - LINUX_MIB_TCPACKSKIPPEDPAWS, - &tp->last_oow_ack_time)) - tcp_send_dupack(sk, skb); - SKB_DR_SET(reason, TCP_RFC7323_PAWS); - goto discard; - } - /* Reset is accepted even if it did not pass PAWS. */ + if (!tcp_fast_parse_options(sock_net(sk), skb, th, tp) || + !tp->rx_opt.saw_tstamp || + tcp_paws_check(&tp->rx_opt, TCP_PAWS_WINDOW)) + goto step1; + + reason = tcp_disordered_ack_check(sk, skb); + if (!reason) + goto step1; + /* Reset is accepted even if it did not pass PAWS. */ + if (th->rst) + goto step1; + if (unlikely(th->syn)) + goto syn_challenge; + + /* Old ACK are common, increment PAWS_OLD_ACK + * and do not send a dupack. + */ + if (reason == SKB_DROP_REASON_TCP_RFC7323_PAWS_ACK) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWS_OLD_ACK); + goto discard; } + NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED); + if (!tcp_oow_rate_limited(sock_net(sk), skb, + LINUX_MIB_TCPACKSKIPPEDPAWS, + &tp->last_oow_ack_time)) + tcp_send_dupack(sk, skb); + goto discard; +step1: /* Step 1: check sequence number */ reason = tcp_sequence(tp, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq); if (reason) { diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 4bc0a0686fcd..c472c9a57cf6 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -576,7 +576,7 @@ begin: return NULL; } -/* In hash4, rehash can happen in connect(), where hash4_cnt keeps unchanged. */ +/* udp_rehash4() only checks hslot4, and hash4_cnt is not processed. */ static void udp_rehash4(struct udp_table *udptable, struct sock *sk, u16 newhash4) { @@ -625,15 +625,13 @@ void udp_lib_hash4(struct sock *sk, u16 hash) struct net *net = sock_net(sk); struct udp_table *udptable; - /* Connected udp socket can re-connect to another remote address, - * so rehash4 is needed. + /* Connected udp socket can re-connect to another remote address, which + * will be handled by rehash. Thus no need to redo hash4 here. */ - udptable = net->ipv4.udp_table; - if (udp_hashed4(sk)) { - udp_rehash4(udptable, sk, hash); + if (udp_hashed4(sk)) return; - } + udptable = net->ipv4.udp_table; hslot = udp_hashslot(udptable, net, udp_sk(sk)->udp_port_hash); hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash); hslot4 = udp_hashslot4(udptable, hash); @@ -2229,14 +2227,14 @@ void udp_lib_rehash(struct sock *sk, u16 newhash, u16 newhash4) struct udp_table *udptable = udp_get_table_prot(sk); struct udp_hslot *hslot, *hslot2, *nhslot2; + hslot = udp_hashslot(udptable, sock_net(sk), + udp_sk(sk)->udp_port_hash); hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash); nhslot2 = udp_hashslot2(udptable, newhash); udp_sk(sk)->udp_portaddr_hash = newhash; if (hslot2 != nhslot2 || rcu_access_pointer(sk->sk_reuseport_cb)) { - hslot = udp_hashslot(udptable, sock_net(sk), - udp_sk(sk)->udp_port_hash); /* we must lock primary chain too */ spin_lock_bh(&hslot->lock); if (rcu_access_pointer(sk->sk_reuseport_cb)) @@ -2255,19 +2253,29 @@ void udp_lib_rehash(struct sock *sk, u16 newhash, u16 newhash4) spin_unlock(&nhslot2->lock); } - if (udp_hashed4(sk)) { - udp_rehash4(udptable, sk, newhash4); + spin_unlock_bh(&hslot->lock); + } + + /* Now process hash4 if necessary: + * (1) update hslot4; + * (2) update hslot2->hash4_cnt. + * Note that hslot2/hslot4 should be checked separately, as + * either of them may change with the other unchanged. + */ + if (udp_hashed4(sk)) { + spin_lock_bh(&hslot->lock); - if (hslot2 != nhslot2) { - spin_lock(&hslot2->lock); - udp_hash4_dec(hslot2); - spin_unlock(&hslot2->lock); + udp_rehash4(udptable, sk, newhash4); + if (hslot2 != nhslot2) { + spin_lock(&hslot2->lock); + udp_hash4_dec(hslot2); + spin_unlock(&hslot2->lock); - spin_lock(&nhslot2->lock); - udp_hash4_inc(nhslot2); - spin_unlock(&nhslot2->lock); - } + spin_lock(&nhslot2->lock); + udp_hash4_inc(nhslot2); + spin_unlock(&nhslot2->lock); } + spin_unlock_bh(&hslot->lock); } } diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 578ff1336afe..535e9f72514c 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -520,9 +520,9 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) if (it->cache != &mrt->mfc_unres_queue) { seq_printf(seq, " %8lu %8lu %8lu", - mfc->_c.mfc_un.res.pkt, - mfc->_c.mfc_un.res.bytes, - mfc->_c.mfc_un.res.wrong_if); + atomic_long_read(&mfc->_c.mfc_un.res.pkt), + atomic_long_read(&mfc->_c.mfc_un.res.bytes), + atomic_long_read(&mfc->_c.mfc_un.res.wrong_if)); for (n = mfc->_c.mfc_un.res.minvif; n < mfc->_c.mfc_un.res.maxvif; n++) { if (VIF_EXISTS(mrt, n) && @@ -884,7 +884,7 @@ static void ip6mr_update_thresholds(struct mr_table *mrt, cache->mfc_un.res.maxvif = vifi + 1; } } - cache->mfc_un.res.lastuse = jiffies; + WRITE_ONCE(cache->mfc_un.res.lastuse, jiffies); } static int mif6_add(struct net *net, struct mr_table *mrt, @@ -1945,9 +1945,9 @@ int ip6mr_ioctl(struct sock *sk, int cmd, void *arg) c = ip6mr_cache_find(mrt, &sr->src.sin6_addr, &sr->grp.sin6_addr); if (c) { - sr->pktcnt = c->_c.mfc_un.res.pkt; - sr->bytecnt = c->_c.mfc_un.res.bytes; - sr->wrong_if = c->_c.mfc_un.res.wrong_if; + sr->pktcnt = atomic_long_read(&c->_c.mfc_un.res.pkt); + sr->bytecnt = atomic_long_read(&c->_c.mfc_un.res.bytes); + sr->wrong_if = atomic_long_read(&c->_c.mfc_un.res.wrong_if); rcu_read_unlock(); return 0; } @@ -2017,9 +2017,9 @@ int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) rcu_read_lock(); c = ip6mr_cache_find(mrt, &sr.src.sin6_addr, &sr.grp.sin6_addr); if (c) { - sr.pktcnt = c->_c.mfc_un.res.pkt; - sr.bytecnt = c->_c.mfc_un.res.bytes; - sr.wrong_if = c->_c.mfc_un.res.wrong_if; + sr.pktcnt = atomic_long_read(&c->_c.mfc_un.res.pkt); + sr.bytecnt = atomic_long_read(&c->_c.mfc_un.res.bytes); + sr.wrong_if = atomic_long_read(&c->_c.mfc_un.res.wrong_if); rcu_read_unlock(); if (copy_to_user(arg, &sr, sizeof(sr))) @@ -2142,9 +2142,9 @@ static void ip6_mr_forward(struct net *net, struct mr_table *mrt, int true_vifi = ip6mr_find_vif(mrt, dev); vif = c->_c.mfc_parent; - c->_c.mfc_un.res.pkt++; - c->_c.mfc_un.res.bytes += skb->len; - c->_c.mfc_un.res.lastuse = jiffies; + atomic_long_inc(&c->_c.mfc_un.res.pkt); + atomic_long_add(skb->len, &c->_c.mfc_un.res.bytes); + WRITE_ONCE(c->_c.mfc_un.res.lastuse, jiffies); if (ipv6_addr_any(&c->mf6c_origin) && true_vifi >= 0) { struct mfc6_cache *cache_proxy; @@ -2162,7 +2162,7 @@ static void ip6_mr_forward(struct net *net, struct mr_table *mrt, * Wrong interface: drop packet and (maybe) send PIM assert. */ if (rcu_access_pointer(mrt->vif_table[vif].dev) != dev) { - c->_c.mfc_un.res.wrong_if++; + atomic_long_inc(&c->_c.mfc_un.res.wrong_if); if (true_vifi >= 0 && mrt->mroute_do_assert && /* pimsm uses asserts, when switching from RPT to SPT, diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c index b0dd008e2114..3999e0ba2c35 100644 --- a/net/mptcp/ctrl.c +++ b/net/mptcp/ctrl.c @@ -32,6 +32,7 @@ struct mptcp_pernet { unsigned int close_timeout; unsigned int stale_loss_cnt; atomic_t active_disable_times; + u8 syn_retrans_before_tcp_fallback; unsigned long active_disable_stamp; u8 mptcp_enabled; u8 checksum_enabled; @@ -92,6 +93,7 @@ static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet) pernet->mptcp_enabled = 1; pernet->add_addr_timeout = TCP_RTO_MAX; pernet->blackhole_timeout = 3600; + pernet->syn_retrans_before_tcp_fallback = 2; atomic_set(&pernet->active_disable_times, 0); pernet->close_timeout = TCP_TIMEWAIT_LEN; pernet->checksum_enabled = 0; @@ -245,6 +247,12 @@ static struct ctl_table mptcp_sysctl_table[] = { .proc_handler = proc_blackhole_detect_timeout, .extra1 = SYSCTL_ZERO, }, + { + .procname = "syn_retrans_before_tcp_fallback", + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + }, }; static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet) @@ -269,6 +277,7 @@ static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet) /* table[7] is for available_schedulers which is read-only info */ table[8].data = &pernet->close_timeout; table[9].data = &pernet->blackhole_timeout; + table[10].data = &pernet->syn_retrans_before_tcp_fallback; hdr = register_net_sysctl_sz(net, MPTCP_SYSCTL_PATH, table, ARRAY_SIZE(mptcp_sysctl_table)); @@ -392,17 +401,21 @@ void mptcp_active_enable(struct sock *sk) void mptcp_active_detect_blackhole(struct sock *ssk, bool expired) { struct mptcp_subflow_context *subflow; - u32 timeouts; if (!sk_is_mptcp(ssk)) return; - timeouts = inet_csk(ssk)->icsk_retransmits; subflow = mptcp_subflow_ctx(ssk); if (subflow->request_mptcp && ssk->sk_state == TCP_SYN_SENT) { - if (timeouts == 2 || (timeouts < 2 && expired)) { - MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPCAPABLEACTIVEDROP); + struct net *net = sock_net(ssk); + u8 timeouts, to_max; + + timeouts = inet_csk(ssk)->icsk_retransmits; + to_max = mptcp_get_pernet(net)->syn_retrans_before_tcp_fallback; + + if (timeouts == to_max || (timeouts < to_max && expired)) { + MPTCP_INC_STATS(net, MPTCP_MIB_MPCAPABLEACTIVEDROP); subflow->mpc_drop = 1; mptcp_subflow_early_fallback(mptcp_sk(subflow->conn), subflow); } else { diff --git a/net/mptcp/options.c b/net/mptcp/options.c index a62bc874bf1e..123f3f297284 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -607,7 +607,6 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, } opts->ext_copy.use_ack = 1; opts->suboptions = OPTION_MPTCP_DSS; - WRITE_ONCE(msk->old_wspace, __mptcp_space((struct sock *)msk)); /* Add kind/length/subtype/flag overhead if mapping is not populated */ if (dss_size == 0) @@ -1288,7 +1287,7 @@ static void mptcp_set_rwin(struct tcp_sock *tp, struct tcphdr *th) } MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_RCVWNDCONFLICT); } - return; + goto update_wspace; } if (rcv_wnd_new != rcv_wnd_old) { @@ -1313,6 +1312,9 @@ raise_win: th->window = htons(new_win); MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_RCVWNDSHARED); } + +update_wspace: + WRITE_ONCE(msk->old_wspace, tp->rcv_wnd); } __sum16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum) diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index 740a10d669f8..a3d477059b11 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -520,7 +520,7 @@ int mptcp_pm_nl_subflow_destroy_doit(struct sk_buff *skb, struct genl_info *info addr_l.addr.family = AF_INET6; } if (addr_r.family == AF_INET && ipv6_addr_v4mapped(&addr_l.addr.addr6)) { - ipv6_addr_set_v4mapped(addr_r.addr.s_addr, &addr_l.addr.addr6); + ipv6_addr_set_v4mapped(addr_r.addr.s_addr, &addr_r.addr6); addr_r.family = AF_INET6; } #endif diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 1b2e7cbb577f..c44c89ecaca6 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -47,7 +47,7 @@ static void __mptcp_destroy_sock(struct sock *sk); static void mptcp_check_send_data_fin(struct sock *sk); DEFINE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions); -static struct net_device mptcp_napi_dev; +static struct net_device *mptcp_napi_dev; /* Returns end sequence number of the receiver's advertised window */ static u64 mptcp_wnd_end(const struct mptcp_sock *msk) @@ -4147,11 +4147,13 @@ void __init mptcp_proto_init(void) if (percpu_counter_init(&mptcp_sockets_allocated, 0, GFP_KERNEL)) panic("Failed to allocate MPTCP pcpu counter\n"); - init_dummy_netdev(&mptcp_napi_dev); + mptcp_napi_dev = alloc_netdev_dummy(0); + if (!mptcp_napi_dev) + panic("Failed to allocate MPTCP dummy netdev\n"); for_each_possible_cpu(cpu) { delegated = per_cpu_ptr(&mptcp_delegated_actions, cpu); INIT_LIST_HEAD(&delegated->head); - netif_napi_add_tx(&mptcp_napi_dev, &delegated->napi, + netif_napi_add_tx(mptcp_napi_dev, &delegated->napi, mptcp_napi_poll); napi_enable(&delegated->napi); } diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index cd5132fe7d22..0174a5aad279 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -760,10 +760,15 @@ static inline u64 mptcp_data_avail(const struct mptcp_sock *msk) static inline bool mptcp_epollin_ready(const struct sock *sk) { + u64 data_avail = mptcp_data_avail(mptcp_sk(sk)); + + if (!data_avail) + return false; + /* mptcp doesn't have to deal with small skbs in the receive queue, - * at it can always coalesce them + * as it can always coalesce them */ - return (mptcp_data_avail(mptcp_sk(sk)) >= sk->sk_rcvlowat) || + return (data_avail >= sk->sk_rcvlowat) || (mem_cgroup_sockets_enabled && sk->sk_memcg && mem_cgroup_under_socket_pressure(sk->sk_memcg)) || READ_ONCE(tcp_memory_pressure); diff --git a/net/ncsi/internal.h b/net/ncsi/internal.h index ef0f8f73826f..4e0842df5234 100644 --- a/net/ncsi/internal.h +++ b/net/ncsi/internal.h @@ -289,6 +289,7 @@ enum { ncsi_dev_state_config_sp = 0x0301, ncsi_dev_state_config_cis, ncsi_dev_state_config_oem_gma, + ncsi_dev_state_config_apply_mac, ncsi_dev_state_config_clear_vids, ncsi_dev_state_config_svf, ncsi_dev_state_config_ev, @@ -322,6 +323,7 @@ struct ncsi_dev_priv { #define NCSI_DEV_RESHUFFLE 4 #define NCSI_DEV_RESET 8 /* Reset state of NC */ unsigned int gma_flag; /* OEM GMA flag */ + struct sockaddr pending_mac; /* MAC address received from GMA */ spinlock_t lock; /* Protect the NCSI device */ unsigned int package_probe_id;/* Current ID during probe */ unsigned int package_num; /* Number of packages */ diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c index 5cf55bde366d..bf276eaf9330 100644 --- a/net/ncsi/ncsi-manage.c +++ b/net/ncsi/ncsi-manage.c @@ -1038,7 +1038,7 @@ static void ncsi_configure_channel(struct ncsi_dev_priv *ndp) : ncsi_dev_state_config_clear_vids; break; case ncsi_dev_state_config_oem_gma: - nd->state = ncsi_dev_state_config_clear_vids; + nd->state = ncsi_dev_state_config_apply_mac; nca.package = np->id; nca.channel = nc->id; @@ -1050,10 +1050,22 @@ static void ncsi_configure_channel(struct ncsi_dev_priv *ndp) nca.type = NCSI_PKT_CMD_OEM; ret = ncsi_gma_handler(&nca, nc->version.mf_id); } - if (ret < 0) + if (ret < 0) { + nd->state = ncsi_dev_state_config_clear_vids; schedule_work(&ndp->work); + } break; + case ncsi_dev_state_config_apply_mac: + rtnl_lock(); + ret = dev_set_mac_address(dev, &ndp->pending_mac, NULL); + rtnl_unlock(); + if (ret < 0) + netdev_warn(dev, "NCSI: 'Writing MAC address to device failed\n"); + + nd->state = ncsi_dev_state_config_clear_vids; + + fallthrough; case ncsi_dev_state_config_clear_vids: case ncsi_dev_state_config_svf: case ncsi_dev_state_config_ev: diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c index e28be33bdf2c..14bd66909ca4 100644 --- a/net/ncsi/ncsi-rsp.c +++ b/net/ncsi/ncsi-rsp.c @@ -628,16 +628,14 @@ static int ncsi_rsp_handler_snfc(struct ncsi_request *nr) static int ncsi_rsp_handler_oem_gma(struct ncsi_request *nr, int mfr_id) { struct ncsi_dev_priv *ndp = nr->ndp; + struct sockaddr *saddr = &ndp->pending_mac; struct net_device *ndev = ndp->ndev.dev; struct ncsi_rsp_oem_pkt *rsp; - struct sockaddr saddr; u32 mac_addr_off = 0; - int ret = 0; /* Get the response header */ rsp = (struct ncsi_rsp_oem_pkt *)skb_network_header(nr->rsp); - saddr.sa_family = ndev->type; ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE; if (mfr_id == NCSI_OEM_MFR_BCM_ID) mac_addr_off = BCM_MAC_ADDR_OFFSET; @@ -646,22 +644,17 @@ static int ncsi_rsp_handler_oem_gma(struct ncsi_request *nr, int mfr_id) else if (mfr_id == NCSI_OEM_MFR_INTEL_ID) mac_addr_off = INTEL_MAC_ADDR_OFFSET; - memcpy(saddr.sa_data, &rsp->data[mac_addr_off], ETH_ALEN); + saddr->sa_family = ndev->type; + memcpy(saddr->sa_data, &rsp->data[mac_addr_off], ETH_ALEN); if (mfr_id == NCSI_OEM_MFR_BCM_ID || mfr_id == NCSI_OEM_MFR_INTEL_ID) - eth_addr_inc((u8 *)saddr.sa_data); - if (!is_valid_ether_addr((const u8 *)saddr.sa_data)) + eth_addr_inc((u8 *)saddr->sa_data); + if (!is_valid_ether_addr((const u8 *)saddr->sa_data)) return -ENXIO; /* Set the flag for GMA command which should only be called once */ ndp->gma_flag = 1; - rtnl_lock(); - ret = dev_set_mac_address(ndev, &saddr, NULL); - rtnl_unlock(); - if (ret < 0) - netdev_warn(ndev, "NCSI: 'Writing mac address to device failed\n"); - - return ret; + return 0; } /* Response handler for Mellanox card */ diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index c0289f83f96d..20a1727e2457 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1046,28 +1046,35 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, int dest_af, #ifdef CONFIG_PROC_FS struct ip_vs_iter_state { struct seq_net_private p; - struct hlist_head *l; + unsigned int bucket; + unsigned int skip_elems; }; -static void *ip_vs_conn_array(struct seq_file *seq, loff_t pos) +static void *ip_vs_conn_array(struct ip_vs_iter_state *iter) { int idx; struct ip_vs_conn *cp; - struct ip_vs_iter_state *iter = seq->private; - for (idx = 0; idx < ip_vs_conn_tab_size; idx++) { + for (idx = iter->bucket; idx < ip_vs_conn_tab_size; idx++) { + unsigned int skip = 0; + hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[idx], c_list) { /* __ip_vs_conn_get() is not needed by * ip_vs_conn_seq_show and ip_vs_conn_sync_seq_show */ - if (pos-- == 0) { - iter->l = &ip_vs_conn_tab[idx]; + if (skip >= iter->skip_elems) { + iter->bucket = idx; return cp; } + + ++skip; } + + iter->skip_elems = 0; cond_resched_rcu(); } + iter->bucket = idx; return NULL; } @@ -1076,9 +1083,14 @@ static void *ip_vs_conn_seq_start(struct seq_file *seq, loff_t *pos) { struct ip_vs_iter_state *iter = seq->private; - iter->l = NULL; rcu_read_lock(); - return *pos ? ip_vs_conn_array(seq, *pos - 1) :SEQ_START_TOKEN; + if (*pos == 0) { + iter->skip_elems = 0; + iter->bucket = 0; + return SEQ_START_TOKEN; + } + + return ip_vs_conn_array(iter); } static void *ip_vs_conn_seq_next(struct seq_file *seq, void *v, loff_t *pos) @@ -1086,28 +1098,22 @@ static void *ip_vs_conn_seq_next(struct seq_file *seq, void *v, loff_t *pos) struct ip_vs_conn *cp = v; struct ip_vs_iter_state *iter = seq->private; struct hlist_node *e; - struct hlist_head *l = iter->l; - int idx; ++*pos; if (v == SEQ_START_TOKEN) - return ip_vs_conn_array(seq, 0); + return ip_vs_conn_array(iter); /* more on same hash chain? */ e = rcu_dereference(hlist_next_rcu(&cp->c_list)); - if (e) + if (e) { + iter->skip_elems++; return hlist_entry(e, struct ip_vs_conn, c_list); - - idx = l - ip_vs_conn_tab; - while (++idx < ip_vs_conn_tab_size) { - hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[idx], c_list) { - iter->l = &ip_vs_conn_tab[idx]; - return cp; - } - cond_resched_rcu(); } - iter->l = NULL; - return NULL; + + iter->skip_elems = 0; + iter->bucket++; + + return ip_vs_conn_array(iter); } static void ip_vs_conn_seq_stop(struct seq_file *seq, void *v) diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c index 69948e1d6974..af68c64acaab 100644 --- a/net/netfilter/nf_conntrack_ecache.c +++ b/net/netfilter/nf_conntrack_ecache.c @@ -162,6 +162,14 @@ static int __nf_conntrack_eventmask_report(struct nf_conntrack_ecache *e, return ret; } +static void nf_ct_ecache_tstamp_refresh(struct nf_conntrack_ecache *e) +{ +#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP + if (local64_read(&e->timestamp)) + local64_set(&e->timestamp, ktime_get_real_ns()); +#endif +} + int nf_conntrack_eventmask_report(unsigned int events, struct nf_conn *ct, u32 portid, int report) { @@ -186,6 +194,8 @@ int nf_conntrack_eventmask_report(unsigned int events, struct nf_conn *ct, /* This is a resent of a destroy event? If so, skip missed */ missed = e->portid ? 0 : e->missed; + nf_ct_ecache_tstamp_refresh(e); + ret = __nf_conntrack_eventmask_report(e, events, missed, &item); if (unlikely(ret < 0 && (events & (1 << IPCT_DESTROY)))) { /* This is a destroy event that has been triggered by a process, @@ -297,6 +307,18 @@ void nf_conntrack_ecache_work(struct net *net, enum nf_ct_ecache_state state) } } +static void nf_ct_ecache_tstamp_new(const struct nf_conn *ct, struct nf_conntrack_ecache *e) +{ +#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP + u64 ts = 0; + + if (nf_ct_ext_exist(ct, NF_CT_EXT_TSTAMP)) + ts = ktime_get_real_ns(); + + local64_set(&e->timestamp, ts); +#endif +} + bool nf_ct_ecache_ext_add(struct nf_conn *ct, u16 ctmask, u16 expmask, gfp_t gfp) { struct net *net = nf_ct_net(ct); @@ -326,6 +348,7 @@ bool nf_ct_ecache_ext_add(struct nf_conn *ct, u16 ctmask, u16 expmask, gfp_t gfp e = nf_ct_ext_add(ct, NF_CT_EXT_ECACHE, gfp); if (e) { + nf_ct_ecache_tstamp_new(ct, e); e->ctmask = ctmask; e->expmask = expmask; } diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 36168f8b6efa..2277b744eb2c 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -383,6 +383,23 @@ nla_put_failure: #endif #ifdef CONFIG_NF_CONNTRACK_EVENTS +static int +ctnetlink_dump_event_timestamp(struct sk_buff *skb, const struct nf_conn *ct) +{ +#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP + const struct nf_conntrack_ecache *e = nf_ct_ecache_find(ct); + + if (e) { + u64 ts = local64_read(&e->timestamp); + + if (ts) + return nla_put_be64(skb, CTA_TIMESTAMP_EVENT, + cpu_to_be64(ts), CTA_TIMESTAMP_PAD); + } +#endif + return 0; +} + static inline int ctnetlink_label_size(const struct nf_conn *ct) { struct nf_conn_labels *labels = nf_ct_labels_find(ct); @@ -717,6 +734,9 @@ static size_t ctnetlink_nlmsg_size(const struct nf_conn *ct) #endif + ctnetlink_proto_size(ct) + ctnetlink_label_size(ct) +#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP + + nla_total_size(sizeof(u64)) /* CTA_TIMESTAMP_EVENT */ +#endif ; } @@ -838,6 +858,10 @@ ctnetlink_conntrack_event(unsigned int events, const struct nf_ct_event *item) if (ctnetlink_dump_mark(skb, ct, events & (1 << IPCT_MARK))) goto nla_put_failure; #endif + + if (ctnetlink_dump_event_timestamp(skb, ct)) + goto nla_put_failure; + nlmsg_end(skb, nlh); err = nfnetlink_send(skb, net, item->portid, group, item->report, GFP_ATOMIC); @@ -1557,6 +1581,7 @@ static const struct nla_policy ct_nla_policy[CTA_MAX+1] = { .len = NF_CT_LABELS_MAX_SIZE }, [CTA_FILTER] = { .type = NLA_NESTED }, [CTA_STATUS_MASK] = { .type = NLA_U32 }, + [CTA_TIMESTAMP_EVENT] = { .type = NLA_REJECT }, }; static int ctnetlink_flush_iterate(struct nf_conn *ct, void *data) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index c4af283356e7..83f3face8bb3 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2598,9 +2598,8 @@ int nft_chain_add(struct nft_table *table, struct nft_chain *chain) static u64 chain_id; -static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, - u8 policy, u32 flags, - struct netlink_ext_ack *extack) +static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 policy, + u32 flags, struct netlink_ext_ack *extack) { const struct nlattr * const *nla = ctx->nla; struct nft_table *table = ctx->table; @@ -3038,7 +3037,7 @@ static int nf_tables_newchain(struct sk_buff *skb, const struct nfnl_info *info, extack); } - return nf_tables_addchain(&ctx, family, genmask, policy, flags, extack); + return nf_tables_addchain(&ctx, family, policy, flags, extack); } static int nft_delchain_hook(struct nft_ctx *ctx, diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index 0859b8f76764..fa02aab56724 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -363,11 +363,15 @@ static void htable_selective_cleanup(struct xt_hashlimit_htable *ht, bool select unsigned int i; for (i = 0; i < ht->cfg.size; i++) { + struct hlist_head *head = &ht->hash[i]; struct dsthash_ent *dh; struct hlist_node *n; + if (hlist_empty(head)) + continue; + spin_lock_bh(&ht->lock); - hlist_for_each_entry_safe(dh, n, &ht->hash[i], node) { + hlist_for_each_entry_safe(dh, n, head, node) { if (time_after_eq(jiffies, dh->expires) || select_all) dsthash_free(ht, dh); } diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 16e260014684..704c858cf209 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -934,7 +934,9 @@ static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port, { struct vport *vport = ovs_vport_rcu(dp, out_port); - if (likely(vport && netif_carrier_ok(vport->dev))) { + if (likely(vport && + netif_running(vport->dev) && + netif_carrier_ok(vport->dev))) { u16 mru = OVS_CB(skb)->mru; u32 cutlen = OVS_CB(skb)->cutlen; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 300430b8c4d2..5d017c06a96f 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1560,7 +1560,7 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, } if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], q->ops->id)) { - NL_SET_ERR_MSG(extack, "Invalid qdisc name"); + NL_SET_ERR_MSG(extack, "Invalid qdisc name: must match existing qdisc"); return -EINVAL; } @@ -1670,7 +1670,7 @@ replay: } if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], q->ops->id)) { - NL_SET_ERR_MSG(extack, "Invalid qdisc name"); + NL_SET_ERR_MSG(extack, "Invalid qdisc name: must match existing qdisc"); return -EINVAL; } if (q->flags & TCQ_F_INGRESS) { @@ -1746,7 +1746,7 @@ replay: return -EEXIST; } if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], q->ops->id)) { - NL_SET_ERR_MSG(extack, "Invalid qdisc name"); + NL_SET_ERR_MSG(extack, "Invalid qdisc name: must match existing qdisc"); return -EINVAL; } err = qdisc_change(q, tca, extack); diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index bb7dd351bd65..14ab2f4c190a 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -1277,15 +1277,17 @@ static void qdisc_deactivate(struct Qdisc *qdisc) static void dev_deactivate_queue(struct net_device *dev, struct netdev_queue *dev_queue, - void *_qdisc_default) + void *_sync_needed) { - struct Qdisc *qdisc_default = _qdisc_default; + bool *sync_needed = _sync_needed; struct Qdisc *qdisc; qdisc = rtnl_dereference(dev_queue->qdisc); if (qdisc) { + if (qdisc->enqueue) + *sync_needed = true; qdisc_deactivate(qdisc); - rcu_assign_pointer(dev_queue->qdisc, qdisc_default); + rcu_assign_pointer(dev_queue->qdisc, &noop_qdisc); } } @@ -1352,24 +1354,22 @@ static bool some_qdisc_is_busy(struct net_device *dev) */ void dev_deactivate_many(struct list_head *head) { + bool sync_needed = false; struct net_device *dev; list_for_each_entry(dev, head, close_list) { netdev_for_each_tx_queue(dev, dev_deactivate_queue, - &noop_qdisc); + &sync_needed); if (dev_ingress_queue(dev)) dev_deactivate_queue(dev, dev_ingress_queue(dev), - &noop_qdisc); + &sync_needed); netdev_watchdog_down(dev); } - /* Wait for outstanding qdisc-less dev_queue_xmit calls or - * outstanding qdisc enqueuing calls. - * This is avoided if all devices are in dismantle phase : - * Caller will call synchronize_net() for us - */ - synchronize_net(); + /* Wait for outstanding qdisc enqueuing calls. */ + if (sync_needed) + synchronize_net(); list_for_each_entry(dev, head, close_list) { netdev_for_each_tx_queue(dev, dev_reset_queue, NULL); diff --git a/net/shaper/shaper.c b/net/shaper/shaper.c index 15463062fe7b..7101a48bce54 100644 --- a/net/shaper/shaper.c +++ b/net/shaper/shaper.c @@ -40,7 +40,7 @@ static void net_shaper_lock(struct net_shaper_binding *binding) { switch (binding->type) { case NET_SHAPER_BINDING_TYPE_NETDEV: - mutex_lock(&binding->netdev->lock); + netdev_lock(binding->netdev); break; } } @@ -49,7 +49,7 @@ static void net_shaper_unlock(struct net_shaper_binding *binding) { switch (binding->type) { case NET_SHAPER_BINDING_TYPE_NETDEV: - mutex_unlock(&binding->netdev->lock); + netdev_unlock(binding->netdev); break; } } @@ -1398,7 +1398,7 @@ void net_shaper_set_real_num_tx_queues(struct net_device *dev, /* Only drivers implementing shapers support ensure * the lock is acquired in advance. */ - lockdep_assert_held(&dev->lock); + netdev_assert_locked(dev); /* Take action only when decreasing the tx queue number. */ for (i = txq; i < dev->real_num_tx_queues; ++i) { diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index c370efcfe3e8..ca6984541edb 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -2741,7 +2741,7 @@ int smc_accept(struct socket *sock, struct socket *new_sock, release_sock(clcsk); } else if (!atomic_read(&smc_sk(nsk)->conn.bytes_to_rcv)) { lock_sock(nsk); - smc_rx_wait(smc_sk(nsk), &timeo, smc_rx_data_available); + smc_rx_wait(smc_sk(nsk), &timeo, 0, smc_rx_data_available); release_sock(nsk); } } diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index ccf57b7fe602..ac07b963aede 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -2155,7 +2155,7 @@ static int smcr_buf_map_link(struct smc_buf_desc *buf_desc, bool is_rmb, for_each_sg(buf_desc->sgt[lnk->link_idx].sgl, sg, nents, i) { size = min_t(int, PAGE_SIZE - offset, buf_size); sg_set_page(sg, vmalloc_to_page(buf), size, offset); - buf += size / sizeof(*buf); + buf += size; buf_size -= size; offset = 0; } diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c index f0cbe77a80b4..e7f1134453ef 100644 --- a/net/smc/smc_rx.c +++ b/net/smc/smc_rx.c @@ -197,7 +197,7 @@ static int smc_rx_splice(struct pipe_inode_info *pipe, char *src, size_t len, partial[i].offset = offset; partial[i].len = size; partial[i].private = (unsigned long)priv[i]; - buf += size / sizeof(*buf); + buf += size; left -= size; offset = 0; } @@ -238,22 +238,23 @@ out: return -ENOMEM; } -static int smc_rx_data_available_and_no_splice_pend(struct smc_connection *conn) +static int smc_rx_data_available_and_no_splice_pend(struct smc_connection *conn, size_t peeked) { - return atomic_read(&conn->bytes_to_rcv) && + return smc_rx_data_available(conn, peeked) && !atomic_read(&conn->splice_pending); } /* blocks rcvbuf consumer until >=len bytes available or timeout or interrupted * @smc smc socket * @timeo pointer to max seconds to wait, pointer to value 0 for no timeout + * @peeked number of bytes already peeked * @fcrit add'l criterion to evaluate as function pointer * Returns: * 1 if at least 1 byte available in rcvbuf or if socket error/shutdown. * 0 otherwise (nothing in rcvbuf nor timeout, e.g. interrupted). */ -int smc_rx_wait(struct smc_sock *smc, long *timeo, - int (*fcrit)(struct smc_connection *conn)) +int smc_rx_wait(struct smc_sock *smc, long *timeo, size_t peeked, + int (*fcrit)(struct smc_connection *conn, size_t baseline)) { DEFINE_WAIT_FUNC(wait, woken_wake_function); struct smc_connection *conn = &smc->conn; @@ -262,7 +263,7 @@ int smc_rx_wait(struct smc_sock *smc, long *timeo, struct sock *sk = &smc->sk; int rc; - if (fcrit(conn)) + if (fcrit(conn, peeked)) return 1; sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); add_wait_queue(sk_sleep(sk), &wait); @@ -271,7 +272,7 @@ int smc_rx_wait(struct smc_sock *smc, long *timeo, cflags->peer_conn_abort || READ_ONCE(sk->sk_shutdown) & RCV_SHUTDOWN || conn->killed || - fcrit(conn), + fcrit(conn, peeked), &wait); remove_wait_queue(sk_sleep(sk), &wait); sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); @@ -322,11 +323,11 @@ static int smc_rx_recv_urg(struct smc_sock *smc, struct msghdr *msg, int len, return -EAGAIN; } -static bool smc_rx_recvmsg_data_available(struct smc_sock *smc) +static bool smc_rx_recvmsg_data_available(struct smc_sock *smc, size_t peeked) { struct smc_connection *conn = &smc->conn; - if (smc_rx_data_available(conn)) + if (smc_rx_data_available(conn, peeked)) return true; else if (conn->urg_state == SMC_URG_VALID) /* we received a single urgent Byte - skip */ @@ -344,10 +345,10 @@ static bool smc_rx_recvmsg_data_available(struct smc_sock *smc) int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, struct pipe_inode_info *pipe, size_t len, int flags) { - size_t copylen, read_done = 0, read_remaining = len; + size_t copylen, read_done = 0, read_remaining = len, peeked_bytes = 0; size_t chunk_len, chunk_off, chunk_len_sum; struct smc_connection *conn = &smc->conn; - int (*func)(struct smc_connection *conn); + int (*func)(struct smc_connection *conn, size_t baseline); union smc_host_cursor cons; int readable, chunk; char *rcvbuf_base; @@ -384,14 +385,14 @@ int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, if (conn->killed) break; - if (smc_rx_recvmsg_data_available(smc)) + if (smc_rx_recvmsg_data_available(smc, peeked_bytes)) goto copy; if (sk->sk_shutdown & RCV_SHUTDOWN) { /* smc_cdc_msg_recv_action() could have run after * above smc_rx_recvmsg_data_available() */ - if (smc_rx_recvmsg_data_available(smc)) + if (smc_rx_recvmsg_data_available(smc, peeked_bytes)) goto copy; break; } @@ -425,26 +426,28 @@ int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, } } - if (!smc_rx_data_available(conn)) { - smc_rx_wait(smc, &timeo, smc_rx_data_available); + if (!smc_rx_data_available(conn, peeked_bytes)) { + smc_rx_wait(smc, &timeo, peeked_bytes, smc_rx_data_available); continue; } copy: /* initialize variables for 1st iteration of subsequent loop */ /* could be just 1 byte, even after waiting on data above */ - readable = atomic_read(&conn->bytes_to_rcv); + readable = smc_rx_data_available(conn, peeked_bytes); splbytes = atomic_read(&conn->splice_pending); if (!readable || (msg && splbytes)) { if (splbytes) func = smc_rx_data_available_and_no_splice_pend; else func = smc_rx_data_available; - smc_rx_wait(smc, &timeo, func); + smc_rx_wait(smc, &timeo, peeked_bytes, func); continue; } smc_curs_copy(&cons, &conn->local_tx_ctrl.cons, conn); + if ((flags & MSG_PEEK) && peeked_bytes) + smc_curs_add(conn->rmb_desc->len, &cons, peeked_bytes); /* subsequent splice() calls pick up where previous left */ if (splbytes) smc_curs_add(conn->rmb_desc->len, &cons, splbytes); @@ -480,6 +483,8 @@ copy: } read_remaining -= chunk_len; read_done += chunk_len; + if (flags & MSG_PEEK) + peeked_bytes += chunk_len; if (chunk_len_sum == copylen) break; /* either on 1st or 2nd iteration */ diff --git a/net/smc/smc_rx.h b/net/smc/smc_rx.h index db823c97d824..994f5e42d1ba 100644 --- a/net/smc/smc_rx.h +++ b/net/smc/smc_rx.h @@ -21,11 +21,11 @@ void smc_rx_init(struct smc_sock *smc); int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, struct pipe_inode_info *pipe, size_t len, int flags); -int smc_rx_wait(struct smc_sock *smc, long *timeo, - int (*fcrit)(struct smc_connection *conn)); -static inline int smc_rx_data_available(struct smc_connection *conn) +int smc_rx_wait(struct smc_sock *smc, long *timeo, size_t peeked, + int (*fcrit)(struct smc_connection *conn, size_t baseline)); +static inline int smc_rx_data_available(struct smc_connection *conn, size_t peeked) { - return atomic_read(&conn->bytes_to_rcv); + return atomic_read(&conn->bytes_to_rcv) - peeked; } #endif /* SMC_RX_H */ diff --git a/net/socket.c b/net/socket.c index 16402b8be5a7..262a28b59c7f 100644 --- a/net/socket.c +++ b/net/socket.c @@ -110,6 +110,8 @@ #include <linux/ptp_clock_kernel.h> #include <trace/events/sock.h> +#include "core/dev.h" + #ifdef CONFIG_NET_RX_BUSY_POLL unsigned int sysctl_net_busy_read __read_mostly; unsigned int sysctl_net_busy_poll __read_mostly; @@ -774,34 +776,6 @@ int kernel_sendmsg(struct socket *sock, struct msghdr *msg, } EXPORT_SYMBOL(kernel_sendmsg); -/** - * kernel_sendmsg_locked - send a message through @sock (kernel-space) - * @sk: sock - * @msg: message header - * @vec: output s/g array - * @num: output s/g array length - * @size: total message data size - * - * Builds the message data with @vec and sends it through @sock. - * Returns the number of bytes sent, or an error code. - * Caller must hold @sk. - */ - -int kernel_sendmsg_locked(struct sock *sk, struct msghdr *msg, - struct kvec *vec, size_t num, size_t size) -{ - struct socket *sock = sk->sk_socket; - const struct proto_ops *ops = READ_ONCE(sock->ops); - - if (!ops->sendmsg_locked) - return sock_no_sendmsg_locked(sk, msg, size); - - iov_iter_kvec(&msg->msg_iter, ITER_SOURCE, vec, num, size); - - return ops->sendmsg_locked(sk, msg, msg_data_left(msg)); -} -EXPORT_SYMBOL(kernel_sendmsg_locked); - static bool skb_is_err_queue(const struct sk_buff *skb) { /* pkt_type of skbs enqueued on the error queue are set to diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 9ee5a83c5b40..99ca4465f702 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -737,6 +737,10 @@ static int do_tls_setsockopt_conf(struct sock *sk, sockptr_t optval, else ctx->rx_conf = conf; update_sk_prot(sk, ctx); + + if (update) + return 0; + if (tx) { ctx->sk_write_space = sk->sk_write_space; sk->sk_write_space = tls_write_space; diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 5cf8109f672a..fa9d1b49599b 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -491,6 +491,15 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) */ vsk->transport->release(vsk); vsock_deassign_transport(vsk); + + /* transport's release() and destruct() can touch some socket + * state, since we are reassigning the socket to a new transport + * during vsock_connect(), let's reset these fields to have a + * clean state. + */ + sock_reset_flag(sk, SOCK_DONE); + sk->sk_state = TCP_CLOSE; + vsk->peer_shutdown = 0; } /* We increase the module refcnt to prevent the transport unloading @@ -870,6 +879,9 @@ EXPORT_SYMBOL_GPL(vsock_create_connected); s64 vsock_stream_has_data(struct vsock_sock *vsk) { + if (WARN_ON(!vsk->transport)) + return 0; + return vsk->transport->stream_has_data(vsk); } EXPORT_SYMBOL_GPL(vsock_stream_has_data); @@ -878,6 +890,9 @@ s64 vsock_connectible_has_data(struct vsock_sock *vsk) { struct sock *sk = sk_vsock(vsk); + if (WARN_ON(!vsk->transport)) + return 0; + if (sk->sk_type == SOCK_SEQPACKET) return vsk->transport->seqpacket_has_data(vsk); else @@ -887,6 +902,9 @@ EXPORT_SYMBOL_GPL(vsock_connectible_has_data); s64 vsock_stream_has_space(struct vsock_sock *vsk) { + if (WARN_ON(!vsk->transport)) + return 0; + return vsk->transport->stream_has_space(vsk); } EXPORT_SYMBOL_GPL(vsock_stream_has_space); diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 9acc13ab3f82..7f7de6d88096 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -26,6 +26,9 @@ /* Threshold for detecting small packets to copy */ #define GOOD_COPY_LEN 128 +static void virtio_transport_cancel_close_work(struct vsock_sock *vsk, + bool cancel_timeout); + static const struct virtio_transport * virtio_transport_get_ops(struct vsock_sock *vsk) { @@ -1109,6 +1112,8 @@ void virtio_transport_destruct(struct vsock_sock *vsk) { struct virtio_vsock_sock *vvs = vsk->trans; + virtio_transport_cancel_close_work(vsk, true); + kfree(vvs); vsk->trans = NULL; } @@ -1204,17 +1209,11 @@ static void virtio_transport_wait_close(struct sock *sk, long timeout) } } -static void virtio_transport_do_close(struct vsock_sock *vsk, - bool cancel_timeout) +static void virtio_transport_cancel_close_work(struct vsock_sock *vsk, + bool cancel_timeout) { struct sock *sk = sk_vsock(vsk); - sock_set_flag(sk, SOCK_DONE); - vsk->peer_shutdown = SHUTDOWN_MASK; - if (vsock_stream_has_data(vsk) <= 0) - sk->sk_state = TCP_CLOSING; - sk->sk_state_change(sk); - if (vsk->close_work_scheduled && (!cancel_timeout || cancel_delayed_work(&vsk->close_work))) { vsk->close_work_scheduled = false; @@ -1226,6 +1225,20 @@ static void virtio_transport_do_close(struct vsock_sock *vsk, } } +static void virtio_transport_do_close(struct vsock_sock *vsk, + bool cancel_timeout) +{ + struct sock *sk = sk_vsock(vsk); + + sock_set_flag(sk, SOCK_DONE); + vsk->peer_shutdown = SHUTDOWN_MASK; + if (vsock_stream_has_data(vsk) <= 0) + sk->sk_state = TCP_CLOSING; + sk->sk_state_change(sk); + + virtio_transport_cancel_close_work(vsk, cancel_timeout); +} + static void virtio_transport_close_timeout(struct work_struct *work) { struct vsock_sock *vsk = @@ -1628,8 +1641,11 @@ void virtio_transport_recv_pkt(struct virtio_transport *t, lock_sock(sk); - /* Check if sk has been closed before lock_sock */ - if (sock_flag(sk, SOCK_DONE)) { + /* Check if sk has been closed or assigned to another transport before + * lock_sock (note: listener sockets are not assigned to any transport) + */ + if (sock_flag(sk, SOCK_DONE) || + (sk->sk_state != TCP_LISTEN && vsk->transport != &t->transport)) { (void)virtio_transport_reset_no_sock(t, skb); release_sock(sk); sock_put(sk); diff --git a/net/vmw_vsock/vsock_bpf.c b/net/vmw_vsock/vsock_bpf.c index 4aa6e74ec295..f201d9eca1df 100644 --- a/net/vmw_vsock/vsock_bpf.c +++ b/net/vmw_vsock/vsock_bpf.c @@ -77,6 +77,7 @@ static int vsock_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len) { struct sk_psock *psock; + struct vsock_sock *vsk; int copied; psock = sk_psock_get(sk); @@ -84,6 +85,13 @@ static int vsock_bpf_recvmsg(struct sock *sk, struct msghdr *msg, return __vsock_recvmsg(sk, msg, len, flags); lock_sock(sk); + vsk = vsock_sk(sk); + + if (!vsk->transport) { + copied = -ENODEV; + goto out; + } + if (vsock_has_data(sk, psock) && sk_psock_queue_empty(psock)) { release_sock(sk); sk_psock_put(sk, psock); @@ -108,6 +116,7 @@ static int vsock_bpf_recvmsg(struct sock *sk, struct msghdr *msg, copied = sk_msg_recvmsg(sk, psock, msg, len, flags); } +out: release_sock(sk); sk_psock_put(sk, psock); diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 3fa70286c846..89d2bef96469 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -322,7 +322,6 @@ static int xsk_rcv_check(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len) return -ENOSPC; } - sk_mark_napi_id_once_xdp(&xs->sk, xdp); return 0; } @@ -908,11 +907,8 @@ static int __xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len if (unlikely(!xs->tx)) return -ENOBUFS; - if (sk_can_busy_loop(sk)) { - if (xs->zc) - __sk_mark_napi_id_once(sk, xsk_pool_get_napi_id(xs->pool)); + if (sk_can_busy_loop(sk)) sk_busy_loop(sk, 1); /* only support non-blocking sockets */ - } if (xs->zc && xsk_no_wakeup(sk)) return 0; @@ -1298,6 +1294,14 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) xs->queue_id = qid; xp_add_xsk(xs->pool, xs); + if (xs->zc && qid < dev->real_num_rx_queues) { + struct netdev_rx_queue *rxq; + + rxq = __netif_get_rx_queue(dev, qid); + if (rxq->napi) + __sk_mark_napi_id_once(sk, rxq->napi->napi_id); + } + out_unlock: if (err) { dev_put(dev); diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 2c4ae61e7e3a..7e6a71b9d6a3 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -48,7 +48,7 @@ static DEFINE_SPINLOCK(xfrm_input_afinfo_lock); static struct xfrm_input_afinfo const __rcu *xfrm_input_afinfo[2][AF_INET6 + 1]; static struct gro_cells gro_cells; -static struct net_device xfrm_napi_dev; +static struct net_device *xfrm_napi_dev; static DEFINE_PER_CPU(struct xfrm_trans_tasklet, xfrm_trans_tasklet); @@ -825,8 +825,11 @@ void __init xfrm_input_init(void) int err; int i; - init_dummy_netdev(&xfrm_napi_dev); - err = gro_cells_init(&gro_cells, &xfrm_napi_dev); + xfrm_napi_dev = alloc_netdev_dummy(0); + if (!xfrm_napi_dev) + panic("Failed to allocate XFRM dummy netdev\n"); + + err = gro_cells_init(&gro_cells, xfrm_napi_dev); if (err) gro_cells.cells = NULL; diff --git a/scripts/decode_stacktrace.sh b/scripts/decode_stacktrace.sh index 46fa18b80fc1..17abc4e7a985 100755 --- a/scripts/decode_stacktrace.sh +++ b/scripts/decode_stacktrace.sh @@ -286,6 +286,18 @@ handle_line() { last=$(( $last - 1 )) fi + # Extract info after the symbol if present. E.g.: + # func_name+0x54/0x80 (P) + # ^^^ + # The regex assumes only uppercase letters will be used. To be + # extended if needed. + local info_str="" + if [[ ${words[$last]} =~ \([A-Z]*\) ]]; then + info_str=${words[$last]} + unset words[$last] + last=$(( $last - 1 )) + fi + if [[ ${words[$last]} =~ \[([^]]+)\] ]]; then module=${words[$last]} # some traces format is "(%pS)", which like "(foo+0x0/0x1 [bar])" @@ -313,9 +325,9 @@ handle_line() { # Add up the line number to the symbol if [[ -z ${module} ]] then - echo "${words[@]}" "$symbol" + echo "${words[@]}" "$symbol ${info_str}" else - echo "${words[@]}" "$symbol $module" + echo "${words[@]}" "$symbol $module ${info_str}" fi } diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index b74b566f675e..ad66378d7321 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -10641,6 +10641,8 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1e1f, "ASUS Vivobook 15 X1504VAP", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1e51, "ASUS Zephyrus M15", ALC294_FIXUP_ASUS_GU502_PINS), SND_PCI_QUIRK(0x1043, 0x1e5e, "ASUS ROG Strix G513", ALC294_FIXUP_ASUS_G513_PINS), + SND_PCI_QUIRK(0x1043, 0x1e63, "ASUS H7606W", ALC285_FIXUP_ASUS_GU605_SPI_SPEAKER2_TO_DAC1), + SND_PCI_QUIRK(0x1043, 0x1e83, "ASUS GA605W", ALC285_FIXUP_ASUS_GU605_SPI_SPEAKER2_TO_DAC1), SND_PCI_QUIRK(0x1043, 0x1e8e, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x1eb3, "ASUS Ally RCLA72", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x1043, 0x1ed3, "ASUS HN7306W", ALC287_FIXUP_CS35L41_I2C_2), @@ -10930,8 +10932,8 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x38e0, "Yoga Y990 Intel VECO Dual", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x38f8, "Yoga Book 9i", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x38df, "Y990 YG DUAL", ALC287_FIXUP_TAS2781_I2C), - 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, 0x38f9, "Thinkbook 16P Gen5", ALC287_FIXUP_MG_RTKC_CSAMP_CS35L41_I2C_THINKPAD), + SND_PCI_QUIRK(0x17aa, 0x38fa, "Thinkbook 16P Gen5", ALC287_FIXUP_MG_RTKC_CSAMP_CS35L41_I2C_THINKPAD), SND_PCI_QUIRK(0x17aa, 0x38fd, "ThinkBook plus Gen5 Hybrid", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI), SND_PCI_QUIRK(0x17aa, 0x3913, "Lenovo 145", ALC236_FIXUP_LENOVO_INV_DMIC), @@ -10995,6 +10997,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1d72, 0x1901, "RedmiBook 14", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1d72, 0x1945, "Redmi G", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1d72, 0x1947, "RedmiBook Air", ALC255_FIXUP_XIAOMI_HEADSET_MIC), + SND_PCI_QUIRK(0x1f66, 0x0105, "Ayaneo Portable Game Player", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x2782, 0x0214, "VAIO VJFE-CL", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x2782, 0x0228, "Infinix ZERO BOOK 13", ALC269VB_FIXUP_INFINIX_ZERO_BOOK_13), SND_PCI_QUIRK(0x2782, 0x0232, "CHUWI CoreBook XPro", ALC269VB_FIXUP_CHUWI_COREBOOK_XPRO), diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig index 0f2df7c91e18..0b9e87dc2b6c 100644 --- a/sound/soc/codecs/Kconfig +++ b/sound/soc/codecs/Kconfig @@ -2451,6 +2451,7 @@ config SND_SOC_WM8993 config SND_SOC_WM8994 tristate + depends on MFD_WM8994 config SND_SOC_WM8995 tristate diff --git a/sound/soc/codecs/cs42l43.c b/sound/soc/codecs/cs42l43.c index 4236f78beec0..83c21c17fb80 100644 --- a/sound/soc/codecs/cs42l43.c +++ b/sound/soc/codecs/cs42l43.c @@ -2404,6 +2404,7 @@ static int cs42l43_codec_runtime_resume(struct device *dev) static const struct dev_pm_ops cs42l43_codec_pm_ops = { RUNTIME_PM_OPS(NULL, cs42l43_codec_runtime_resume, NULL) + SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, pm_runtime_force_resume) }; static const struct platform_device_id cs42l43_codec_id_table[] = { diff --git a/sound/soc/codecs/es8316.c b/sound/soc/codecs/es8316.c index 61729e5b50a8..f508df01145b 100644 --- a/sound/soc/codecs/es8316.c +++ b/sound/soc/codecs/es8316.c @@ -39,7 +39,9 @@ struct es8316_priv { struct snd_soc_jack *jack; int irq; unsigned int sysclk; - unsigned int allowed_rates[ARRAY_SIZE(supported_mclk_lrck_ratios)]; + /* ES83xx supports halving the MCLK so it supports twice as many rates + */ + unsigned int allowed_rates[ARRAY_SIZE(supported_mclk_lrck_ratios) * 2]; struct snd_pcm_hw_constraint_list sysclk_constraints; bool jd_inverted; }; @@ -386,6 +388,12 @@ static int es8316_set_dai_sysclk(struct snd_soc_dai *codec_dai, if (freq % ratio == 0) es8316->allowed_rates[count++] = freq / ratio; + + /* We also check if the halved MCLK produces a valid rate + * since the codec supports halving the MCLK. + */ + if ((freq / ratio) % 2 == 0) + es8316->allowed_rates[count++] = freq / ratio / 2; } if (count) { diff --git a/sound/soc/codecs/es8326.c b/sound/soc/codecs/es8326.c index a5603b617688..b06eead7e0f6 100644 --- a/sound/soc/codecs/es8326.c +++ b/sound/soc/codecs/es8326.c @@ -616,7 +616,7 @@ static int es8326_mute(struct snd_soc_dai *dai, int mute, int direction) 0x0F, 0x0F); if (es8326->version > ES8326_VERSION_B) { regmap_update_bits(es8326->regmap, ES8326_VMIDSEL, 0x40, 0x40); - regmap_update_bits(es8326->regmap, ES8326_ANA_MICBIAS, 0x70, 0x10); + regmap_update_bits(es8326->regmap, ES8326_ANA_MICBIAS, 0x70, 0x30); } } } else { @@ -631,6 +631,8 @@ static int es8326_mute(struct snd_soc_dai *dai, int mute, int direction) regmap_write(es8326->regmap, ES8326_HPR_OFFSET_INI, offset_r); es8326->calibrated = true; } + regmap_update_bits(es8326->regmap, ES8326_CLK_INV, 0xc0, 0x00); + regmap_update_bits(es8326->regmap, ES8326_CLK_MUX, 0x80, 0x00); if (direction == SNDRV_PCM_STREAM_PLAYBACK) { regmap_update_bits(es8326->regmap, ES8326_DAC_DSM, 0x01, 0x01); usleep_range(1000, 5000); @@ -645,7 +647,7 @@ static int es8326_mute(struct snd_soc_dai *dai, int mute, int direction) } else { msleep(300); if (es8326->version > ES8326_VERSION_B) { - regmap_update_bits(es8326->regmap, ES8326_ANA_MICBIAS, 0x70, 0x50); + regmap_update_bits(es8326->regmap, ES8326_ANA_MICBIAS, 0x70, 0x70); regmap_update_bits(es8326->regmap, ES8326_VMIDSEL, 0x40, 0x00); } regmap_update_bits(es8326->regmap, ES8326_ADC_MUTE, @@ -676,6 +678,10 @@ static int es8326_set_bias_level(struct snd_soc_component *codec, regmap_write(es8326->regmap, ES8326_ANA_PDN, 0x00); regmap_update_bits(es8326->regmap, ES8326_CLK_CTL, 0x20, 0x20); regmap_update_bits(es8326->regmap, ES8326_RESET, 0x02, 0x00); + if (es8326->version > ES8326_VERSION_B) { + regmap_update_bits(es8326->regmap, ES8326_VMIDSEL, 0x40, 0x40); + regmap_update_bits(es8326->regmap, ES8326_ANA_MICBIAS, 0x70, 0x30); + } break; case SND_SOC_BIAS_PREPARE: break; @@ -683,6 +689,12 @@ static int es8326_set_bias_level(struct snd_soc_component *codec, regmap_write(es8326->regmap, ES8326_ANA_PDN, 0x3b); regmap_update_bits(es8326->regmap, ES8326_CLK_CTL, 0x20, 0x00); regmap_write(es8326->regmap, ES8326_SDINOUT1_IO, ES8326_IO_INPUT); + if (es8326->version > ES8326_VERSION_B) { + regmap_update_bits(es8326->regmap, ES8326_VMIDSEL, 0x40, 0x40); + regmap_update_bits(es8326->regmap, ES8326_ANA_MICBIAS, 0x70, 0x10); + } + regmap_update_bits(es8326->regmap, ES8326_CLK_INV, 0xc0, 0xc0); + regmap_update_bits(es8326->regmap, ES8326_CLK_MUX, 0x80, 0x80); break; case SND_SOC_BIAS_OFF: clk_disable_unprepare(es8326->mclk); @@ -773,7 +785,10 @@ static void es8326_jack_button_handler(struct work_struct *work) case 0x6f: case 0x4b: /* button volume up */ - cur_button = SND_JACK_BTN_1; + if ((iface == 0x6f) && (es8326->version > ES8326_VERSION_B)) + cur_button = SND_JACK_BTN_0; + else + cur_button = SND_JACK_BTN_1; break; case 0x27: /* button volume down */ @@ -1082,7 +1097,7 @@ static void es8326_init(struct snd_soc_component *component) regmap_write(es8326->regmap, ES8326_ADC2_SRC, 0x66); es8326_disable_micbias(es8326->component); if (es8326->version > ES8326_VERSION_B) { - regmap_update_bits(es8326->regmap, ES8326_ANA_MICBIAS, 0x73, 0x13); + regmap_update_bits(es8326->regmap, ES8326_ANA_MICBIAS, 0x73, 0x10); regmap_update_bits(es8326->regmap, ES8326_VMIDSEL, 0x40, 0x40); } diff --git a/sound/soc/codecs/tas2781-i2c.c b/sound/soc/codecs/tas2781-i2c.c index fb8cd2284fe8..728bf78ae71f 100644 --- a/sound/soc/codecs/tas2781-i2c.c +++ b/sound/soc/codecs/tas2781-i2c.c @@ -78,7 +78,7 @@ static const struct bulk_reg_val tas2781_cali_start_reg[] = { X2781_CL_STT_VAL(TAS2781_PRM_INT_MASK_REG, 0xfe, false), X2781_CL_STT_VAL(TAS2781_PRM_CLK_CFG_REG, 0xdd, false), X2781_CL_STT_VAL(TAS2781_PRM_RSVD_REG, 0x20, false), - X2781_CL_STT_VAL(TAS2781_PRM_TEST_57_REG, 0x14, false), + X2781_CL_STT_VAL(TAS2781_PRM_TEST_57_REG, 0x14, true), X2781_CL_STT_VAL(TAS2781_PRM_TEST_62_REG, 0x45, true), X2781_CL_STT_VAL(TAS2781_PRM_PVDD_UVLO_REG, 0x03, false), X2781_CL_STT_VAL(TAS2781_PRM_CHNL_0_REG, 0xa8, false), diff --git a/sound/soc/renesas/rcar/adg.c b/sound/soc/renesas/rcar/adg.c index 0f190abf00e7..191f212d338c 100644 --- a/sound/soc/renesas/rcar/adg.c +++ b/sound/soc/renesas/rcar/adg.c @@ -374,12 +374,12 @@ int rsnd_adg_ssi_clk_try_start(struct rsnd_mod *ssi_mod, unsigned int rate) return 0; } -void rsnd_adg_clk_control(struct rsnd_priv *priv, int enable) +int rsnd_adg_clk_control(struct rsnd_priv *priv, int enable) { struct rsnd_adg *adg = rsnd_priv_to_adg(priv); struct rsnd_mod *adg_mod = rsnd_mod_get(adg); struct clk *clk; - int i; + int ret = 0, i; if (enable) { rsnd_mod_bset(adg_mod, BRGCKR, 0x80770000, adg->ckr); @@ -389,18 +389,33 @@ void rsnd_adg_clk_control(struct rsnd_priv *priv, int enable) for_each_rsnd_clkin(clk, adg, i) { if (enable) { - clk_prepare_enable(clk); + ret = clk_prepare_enable(clk); /* * We shouldn't use clk_get_rate() under * atomic context. Let's keep it when * rsnd_adg_clk_enable() was called */ + if (ret < 0) + break; + adg->clkin_rate[i] = clk_get_rate(clk); } else { - clk_disable_unprepare(clk); + if (adg->clkin_rate[i]) + clk_disable_unprepare(clk); + + adg->clkin_rate[i] = 0; } } + + /* + * rsnd_adg_clk_enable() might return error (_disable() will not). + * We need to rollback in such case + */ + if (ret < 0) + rsnd_adg_clk_disable(priv); + + return ret; } static struct clk *rsnd_adg_create_null_clk(struct rsnd_priv *priv, @@ -753,7 +768,10 @@ int rsnd_adg_probe(struct rsnd_priv *priv) if (ret) return ret; - rsnd_adg_clk_enable(priv); + ret = rsnd_adg_clk_enable(priv); + if (ret) + return ret; + rsnd_adg_clk_dbg_info(priv, NULL); return 0; diff --git a/sound/soc/renesas/rcar/core.c b/sound/soc/renesas/rcar/core.c index e2234928c9e8..d3709fd0409e 100644 --- a/sound/soc/renesas/rcar/core.c +++ b/sound/soc/renesas/rcar/core.c @@ -2086,9 +2086,7 @@ static int __maybe_unused rsnd_resume(struct device *dev) { struct rsnd_priv *priv = dev_get_drvdata(dev); - rsnd_adg_clk_enable(priv); - - return 0; + return rsnd_adg_clk_enable(priv); } static const struct dev_pm_ops rsnd_pm_ops = { diff --git a/sound/soc/renesas/rcar/rsnd.h b/sound/soc/renesas/rcar/rsnd.h index 3c164d8e3b16..a5f54b65313c 100644 --- a/sound/soc/renesas/rcar/rsnd.h +++ b/sound/soc/renesas/rcar/rsnd.h @@ -608,7 +608,7 @@ int rsnd_adg_set_cmd_timsel_gen2(struct rsnd_mod *cmd_mod, struct rsnd_dai_stream *io); #define rsnd_adg_clk_enable(priv) rsnd_adg_clk_control(priv, 1) #define rsnd_adg_clk_disable(priv) rsnd_adg_clk_control(priv, 0) -void rsnd_adg_clk_control(struct rsnd_priv *priv, int enable); +int rsnd_adg_clk_control(struct rsnd_priv *priv, int enable); void rsnd_adg_clk_dbg_info(struct rsnd_priv *priv, struct seq_file *m); /* diff --git a/sound/soc/samsung/Kconfig b/sound/soc/samsung/Kconfig index 4b1ea7b2c796..60b4b7b75215 100644 --- a/sound/soc/samsung/Kconfig +++ b/sound/soc/samsung/Kconfig @@ -127,8 +127,9 @@ config SND_SOC_SAMSUNG_TM2_WM5110 config SND_SOC_SAMSUNG_ARIES_WM8994 tristate "SoC I2S Audio support for WM8994 on Aries" - depends on SND_SOC_SAMSUNG && MFD_WM8994 && IIO && EXTCON + depends on SND_SOC_SAMSUNG && I2C && IIO && EXTCON select SND_SOC_BT_SCO + select MFD_WM8994 select SND_SOC_WM8994 select SND_SAMSUNG_I2S help @@ -140,8 +141,9 @@ config SND_SOC_SAMSUNG_ARIES_WM8994 config SND_SOC_SAMSUNG_MIDAS_WM1811 tristate "SoC I2S Audio support for Midas boards" - depends on SND_SOC_SAMSUNG && IIO + depends on SND_SOC_SAMSUNG && I2C && IIO select SND_SAMSUNG_I2S + select MFD_WM8994 select SND_SOC_WM8994 help Say Y if you want to add support for SoC audio on the Midas boards. diff --git a/tools/net/ynl/pyynl/cli.py b/tools/net/ynl/pyynl/cli.py index 41d9fa5c818d..794e3c7dcc65 100755 --- a/tools/net/ynl/pyynl/cli.py +++ b/tools/net/ynl/pyynl/cli.py @@ -3,6 +3,7 @@ import argparse import json +import os import pathlib import pprint import sys @@ -10,6 +11,24 @@ import sys sys.path.append(pathlib.Path(__file__).resolve().parent.as_posix()) from lib import YnlFamily, Netlink, NlError +sys_schema_dir='/usr/share/ynl' +relative_schema_dir='../../../../Documentation/netlink' + +def schema_dir(): + script_dir = os.path.dirname(os.path.abspath(__file__)) + schema_dir = os.path.abspath(f"{script_dir}/{relative_schema_dir}") + if not os.path.isdir(schema_dir): + schema_dir = sys_schema_dir + if not os.path.isdir(schema_dir): + raise Exception(f"Schema directory {schema_dir} does not exist") + return schema_dir + +def spec_dir(): + spec_dir = schema_dir() + '/specs' + if not os.path.isdir(spec_dir): + raise Exception(f"Spec directory {spec_dir} does not exist") + return spec_dir + class YnlEncoder(json.JSONEncoder): def default(self, obj): @@ -32,7 +51,14 @@ def main(): parser = argparse.ArgumentParser(description=description, epilog=epilog) - parser.add_argument('--spec', dest='spec', type=str, required=True) + spec_group = parser.add_mutually_exclusive_group(required=True) + spec_group.add_argument('--family', dest='family', type=str, + help='name of the netlink FAMILY') + spec_group.add_argument('--list-families', action='store_true', + help='list all netlink families supported by YNL (has spec)') + spec_group.add_argument('--spec', dest='spec', type=str, + help='choose the family by SPEC file path') + parser.add_argument('--schema', dest='schema', type=str) parser.add_argument('--no-schema', action='store_true') parser.add_argument('--json', dest='json_text', type=str) @@ -70,6 +96,12 @@ def main(): else: pprint.PrettyPrinter().pprint(msg) + if args.list_families: + for filename in sorted(os.listdir(spec_dir())): + if filename.endswith('.yaml'): + print(filename.removesuffix('.yaml')) + return + if args.no_schema: args.schema = '' @@ -77,7 +109,16 @@ def main(): if args.json_text: attrs = json.loads(args.json_text) - ynl = YnlFamily(args.spec, args.schema, args.process_unknown, + if args.family: + spec = f"{spec_dir()}/{args.family}.yaml" + if args.schema is None and spec.startswith(sys_schema_dir): + args.schema = '' # disable schema validation when installed + else: + spec = args.spec + if not os.path.isfile(spec): + raise Exception(f"Spec file {spec} does not exist") + + ynl = YnlFamily(spec, args.schema, args.process_unknown, recv_size=args.dbg_small_recv) if args.dbg_small_recv: ynl.set_recv_dbg(True) diff --git a/tools/net/ynl/pyynl/ethtool.py b/tools/net/ynl/pyynl/ethtool.py index ebb0a11f67bf..af7fddd7b085 100755 --- a/tools/net/ynl/pyynl/ethtool.py +++ b/tools/net/ynl/pyynl/ethtool.py @@ -11,6 +11,7 @@ import os sys.path.append(pathlib.Path(__file__).resolve().parent.as_posix()) from lib import YnlFamily +from cli import schema_dir, spec_dir def args_to_req(ynl, op_name, args, req): """ @@ -156,10 +157,8 @@ def main(): args = parser.parse_args() script_abs_dir = os.path.dirname(os.path.abspath(sys.argv[0])) - spec = os.path.join(script_abs_dir, - '../../../Documentation/netlink/specs/ethtool.yaml') - schema = os.path.join(script_abs_dir, - '../../../Documentation/netlink/genetlink-legacy.yaml') + spec = os.path.join(spec_dir(), 'ethtool.yaml') + schema = os.path.join(schema_dir(), 'genetlink-legacy.yaml') ynl = YnlFamily(spec, schema) diff --git a/tools/net/ynl/pyynl/ynl_gen_c.py b/tools/net/ynl/pyynl/ynl_gen_c.py index d3a7dfbcf929..c2eabc90dce8 100755 --- a/tools/net/ynl/pyynl/ynl_gen_c.py +++ b/tools/net/ynl/pyynl/ynl_gen_c.py @@ -2411,6 +2411,17 @@ def print_kernel_family_struct_src(family, cw): if not kernel_can_gen_family_struct(family): return + if 'sock-priv' in family.kernel_family: + # Generate "trampolines" to make CFI happy + cw.write_func("static void", f"__{family.c_name}_nl_sock_priv_init", + [f"{family.c_name}_nl_sock_priv_init(priv);"], + ["void *priv"]) + cw.nl() + cw.write_func("static void", f"__{family.c_name}_nl_sock_priv_destroy", + [f"{family.c_name}_nl_sock_priv_destroy(priv);"], + ["void *priv"]) + cw.nl() + cw.block_start(f"struct genl_family {family.ident_name}_nl_family __ro_after_init =") cw.p('.name\t\t= ' + family.fam_key + ',') cw.p('.version\t= ' + family.ver_key + ',') @@ -2428,9 +2439,8 @@ def print_kernel_family_struct_src(family, cw): cw.p(f'.n_mcgrps\t= ARRAY_SIZE({family.c_name}_nl_mcgrps),') if 'sock-priv' in family.kernel_family: cw.p(f'.sock_priv_size\t= sizeof({family.kernel_family["sock-priv"]}),') - # Force cast here, actual helpers take pointer to the real type. - cw.p(f'.sock_priv_init\t= (void *){family.c_name}_nl_sock_priv_init,') - cw.p(f'.sock_priv_destroy = (void *){family.c_name}_nl_sock_priv_destroy,') + cw.p(f'.sock_priv_init\t= __{family.c_name}_nl_sock_priv_init,') + cw.p(f'.sock_priv_destroy = __{family.c_name}_nl_sock_priv_destroy,') cw.block_end(';') diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh index 03c1bdaed2c3..400a696a0d21 100755 --- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh +++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh @@ -86,15 +86,15 @@ echo "" > test/cpuset.cpus # # If isolated CPUs have been reserved at boot time (as shown in -# cpuset.cpus.isolated), these isolated CPUs should be outside of CPUs 0-7 +# cpuset.cpus.isolated), these isolated CPUs should be outside of CPUs 0-8 # that will be used by this script for testing purpose. If not, some of -# the tests may fail incorrectly. These isolated CPUs will also be removed -# before being compared with the expected results. +# the tests may fail incorrectly. These pre-isolated CPUs should stay in +# an isolated state throughout the testing process for now. # BOOT_ISOLCPUS=$(cat $CGROUP2/cpuset.cpus.isolated) if [[ -n "$BOOT_ISOLCPUS" ]] then - [[ $(echo $BOOT_ISOLCPUS | sed -e "s/[,-].*//") -le 7 ]] && + [[ $(echo $BOOT_ISOLCPUS | sed -e "s/[,-].*//") -le 8 ]] && skip_test "Pre-isolated CPUs ($BOOT_ISOLCPUS) overlap CPUs to be tested" echo "Pre-isolated CPUs: $BOOT_ISOLCPUS" fi @@ -684,14 +684,18 @@ check_isolcpus() fi # + # Appending pre-isolated CPUs + # Even though CPU #8 isn't used for testing, it can't be pre-isolated + # to make appending those CPUs easier. + # + [[ -n "$BOOT_ISOLCPUS" ]] && { + EXPECT_VAL=${EXPECT_VAL:+${EXPECT_VAL},}${BOOT_ISOLCPUS} + EXPECT_VAL2=${EXPECT_VAL2:+${EXPECT_VAL2},}${BOOT_ISOLCPUS} + } + + # # Check cpuset.cpus.isolated cpumask # - if [[ -z "$BOOT_ISOLCPUS" ]] - then - ISOLCPUS=$(cat $ISCPUS) - else - ISOLCPUS=$(cat $ISCPUS | sed -e "s/,*$BOOT_ISOLCPUS//") - fi [[ "$EXPECT_VAL2" != "$ISOLCPUS" ]] && { # Take a 50ms pause and try again pause 0.05 @@ -731,8 +735,6 @@ check_isolcpus() fi done [[ "$ISOLCPUS" = *- ]] && ISOLCPUS=${ISOLCPUS}$LASTISOLCPU - [[ -n "BOOT_ISOLCPUS" ]] && - ISOLCPUS=$(echo $ISOLCPUS | sed -e "s/,*$BOOT_ISOLCPUS//") [[ "$EXPECT_VAL" = "$ISOLCPUS" ]] } @@ -836,8 +838,11 @@ run_state_test() # if available [[ -n "$ICPUS" ]] && { check_isolcpus $ICPUS - [[ $? -ne 0 ]] && test_fail $I "isolated CPU" \ - "Expect $ICPUS, get $ISOLCPUS instead" + [[ $? -ne 0 ]] && { + [[ -n "$BOOT_ISOLCPUS" ]] && ICPUS=${ICPUS},${BOOT_ISOLCPUS} + test_fail $I "isolated CPU" \ + "Expect $ICPUS, get $ISOLCPUS instead" + } } reset_cgroup_states # diff --git a/tools/testing/selftests/drivers/net/Makefile b/tools/testing/selftests/drivers/net/Makefile index 469179c18935..137470bdee0c 100644 --- a/tools/testing/selftests/drivers/net/Makefile +++ b/tools/testing/selftests/drivers/net/Makefile @@ -12,6 +12,7 @@ TEST_PROGS := \ queues.py \ stats.py \ shaper.py \ + hds.py \ # end of TEST_PROGS include ../../lib.mk diff --git a/tools/testing/selftests/drivers/net/bonding/Makefile b/tools/testing/selftests/drivers/net/bonding/Makefile index 03a089165d3f..2b10854e4b1e 100644 --- a/tools/testing/selftests/drivers/net/bonding/Makefile +++ b/tools/testing/selftests/drivers/net/bonding/Makefile @@ -10,7 +10,7 @@ TEST_PROGS := \ mode-2-recovery-updelay.sh \ bond_options.sh \ bond-eth-type-change.sh \ - bond_macvlan.sh + bond_macvlan_ipvlan.sh TEST_FILES := \ lag_lib.sh \ diff --git a/tools/testing/selftests/drivers/net/bonding/bond_macvlan.sh b/tools/testing/selftests/drivers/net/bonding/bond_macvlan.sh deleted file mode 100755 index b609fb6231f4..000000000000 --- a/tools/testing/selftests/drivers/net/bonding/bond_macvlan.sh +++ /dev/null @@ -1,99 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 -# -# Test macvlan over balance-alb - -lib_dir=$(dirname "$0") -source ${lib_dir}/bond_topo_2d1c.sh - -m1_ns="m1-$(mktemp -u XXXXXX)" -m2_ns="m1-$(mktemp -u XXXXXX)" -m1_ip4="192.0.2.11" -m1_ip6="2001:db8::11" -m2_ip4="192.0.2.12" -m2_ip6="2001:db8::12" - -cleanup() -{ - ip -n ${m1_ns} link del macv0 - ip netns del ${m1_ns} - ip -n ${m2_ns} link del macv0 - ip netns del ${m2_ns} - - client_destroy - server_destroy - gateway_destroy -} - -check_connection() -{ - local ns=${1} - local target=${2} - local message=${3:-"macvlan_over_bond"} - RET=0 - - - ip netns exec ${ns} ping ${target} -c 4 -i 0.1 &>/dev/null - check_err $? "ping failed" - log_test "$mode: $message" -} - -macvlan_over_bond() -{ - local param="$1" - RET=0 - - # setup new bond mode - bond_reset "${param}" - - ip -n ${s_ns} link add link bond0 name macv0 type macvlan mode bridge - ip -n ${s_ns} link set macv0 netns ${m1_ns} - ip -n ${m1_ns} link set dev macv0 up - ip -n ${m1_ns} addr add ${m1_ip4}/24 dev macv0 - ip -n ${m1_ns} addr add ${m1_ip6}/24 dev macv0 - - ip -n ${s_ns} link add link bond0 name macv0 type macvlan mode bridge - ip -n ${s_ns} link set macv0 netns ${m2_ns} - ip -n ${m2_ns} link set dev macv0 up - ip -n ${m2_ns} addr add ${m2_ip4}/24 dev macv0 - ip -n ${m2_ns} addr add ${m2_ip6}/24 dev macv0 - - sleep 2 - - check_connection "${c_ns}" "${s_ip4}" "IPv4: client->server" - check_connection "${c_ns}" "${s_ip6}" "IPv6: client->server" - check_connection "${c_ns}" "${m1_ip4}" "IPv4: client->macvlan_1" - check_connection "${c_ns}" "${m1_ip6}" "IPv6: client->macvlan_1" - check_connection "${c_ns}" "${m2_ip4}" "IPv4: client->macvlan_2" - check_connection "${c_ns}" "${m2_ip6}" "IPv6: client->macvlan_2" - check_connection "${m1_ns}" "${m2_ip4}" "IPv4: macvlan_1->macvlan_2" - check_connection "${m1_ns}" "${m2_ip6}" "IPv6: macvlan_1->macvlan_2" - - - sleep 5 - - check_connection "${s_ns}" "${c_ip4}" "IPv4: server->client" - check_connection "${s_ns}" "${c_ip6}" "IPv6: server->client" - check_connection "${m1_ns}" "${c_ip4}" "IPv4: macvlan_1->client" - check_connection "${m1_ns}" "${c_ip6}" "IPv6: macvlan_1->client" - check_connection "${m2_ns}" "${c_ip4}" "IPv4: macvlan_2->client" - check_connection "${m2_ns}" "${c_ip6}" "IPv6: macvlan_2->client" - check_connection "${m2_ns}" "${m1_ip4}" "IPv4: macvlan_2->macvlan_2" - check_connection "${m2_ns}" "${m1_ip6}" "IPv6: macvlan_2->macvlan_2" - - ip -n ${c_ns} neigh flush dev eth0 -} - -trap cleanup EXIT - -setup_prepare -ip netns add ${m1_ns} -ip netns add ${m2_ns} - -modes="active-backup balance-tlb balance-alb" - -for mode in $modes; do - macvlan_over_bond "mode $mode" -done - -exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/bonding/bond_macvlan_ipvlan.sh b/tools/testing/selftests/drivers/net/bonding/bond_macvlan_ipvlan.sh new file mode 100755 index 000000000000..c4711272fe45 --- /dev/null +++ b/tools/testing/selftests/drivers/net/bonding/bond_macvlan_ipvlan.sh @@ -0,0 +1,96 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test macvlan/ipvlan over bond + +lib_dir=$(dirname "$0") +source ${lib_dir}/bond_topo_2d1c.sh + +xvlan1_ns="xvlan1-$(mktemp -u XXXXXX)" +xvlan2_ns="xvlan2-$(mktemp -u XXXXXX)" +xvlan1_ip4="192.0.2.11" +xvlan1_ip6="2001:db8::11" +xvlan2_ip4="192.0.2.12" +xvlan2_ip6="2001:db8::12" + +cleanup() +{ + client_destroy + server_destroy + gateway_destroy + + ip netns del ${xvlan1_ns} + ip netns del ${xvlan2_ns} +} + +check_connection() +{ + local ns=${1} + local target=${2} + local message=${3} + RET=0 + + ip netns exec ${ns} ping ${target} -c 4 -i 0.1 &>/dev/null + check_err $? "ping failed" + log_test "${bond_mode}/${xvlan_type}_${xvlan_mode}: ${message}" +} + +xvlan_over_bond() +{ + local param="$1" + local xvlan_type="$2" + local xvlan_mode="$3" + RET=0 + + # setup new bond mode + bond_reset "${param}" + + ip -n ${s_ns} link add link bond0 name ${xvlan_type}0 type ${xvlan_type} mode ${xvlan_mode} + ip -n ${s_ns} link set ${xvlan_type}0 netns ${xvlan1_ns} + ip -n ${xvlan1_ns} link set dev ${xvlan_type}0 up + ip -n ${xvlan1_ns} addr add ${xvlan1_ip4}/24 dev ${xvlan_type}0 + ip -n ${xvlan1_ns} addr add ${xvlan1_ip6}/24 dev ${xvlan_type}0 + + ip -n ${s_ns} link add link bond0 name ${xvlan_type}0 type ${xvlan_type} mode ${xvlan_mode} + ip -n ${s_ns} link set ${xvlan_type}0 netns ${xvlan2_ns} + ip -n ${xvlan2_ns} link set dev ${xvlan_type}0 up + ip -n ${xvlan2_ns} addr add ${xvlan2_ip4}/24 dev ${xvlan_type}0 + ip -n ${xvlan2_ns} addr add ${xvlan2_ip6}/24 dev ${xvlan_type}0 + + sleep 2 + + check_connection "${c_ns}" "${s_ip4}" "IPv4: client->server" + check_connection "${c_ns}" "${s_ip6}" "IPv6: client->server" + check_connection "${c_ns}" "${xvlan1_ip4}" "IPv4: client->${xvlan_type}_1" + check_connection "${c_ns}" "${xvlan1_ip6}" "IPv6: client->${xvlan_type}_1" + check_connection "${c_ns}" "${xvlan2_ip4}" "IPv4: client->${xvlan_type}_2" + check_connection "${c_ns}" "${xvlan2_ip6}" "IPv6: client->${xvlan_type}_2" + check_connection "${xvlan1_ns}" "${xvlan2_ip4}" "IPv4: ${xvlan_type}_1->${xvlan_type}_2" + check_connection "${xvlan1_ns}" "${xvlan2_ip6}" "IPv6: ${xvlan_type}_1->${xvlan_type}_2" + + check_connection "${s_ns}" "${c_ip4}" "IPv4: server->client" + check_connection "${s_ns}" "${c_ip6}" "IPv6: server->client" + check_connection "${xvlan1_ns}" "${c_ip4}" "IPv4: ${xvlan_type}_1->client" + check_connection "${xvlan1_ns}" "${c_ip6}" "IPv6: ${xvlan_type}_1->client" + check_connection "${xvlan2_ns}" "${c_ip4}" "IPv4: ${xvlan_type}_2->client" + check_connection "${xvlan2_ns}" "${c_ip6}" "IPv6: ${xvlan_type}_2->client" + check_connection "${xvlan2_ns}" "${xvlan1_ip4}" "IPv4: ${xvlan_type}_2->${xvlan_type}_1" + check_connection "${xvlan2_ns}" "${xvlan1_ip6}" "IPv6: ${xvlan_type}_2->${xvlan_type}_1" + + ip -n ${c_ns} neigh flush dev eth0 +} + +trap cleanup EXIT + +setup_prepare +ip netns add ${xvlan1_ns} +ip netns add ${xvlan2_ns} + +bond_modes="active-backup balance-tlb balance-alb" + +for bond_mode in ${bond_modes}; do + xvlan_over_bond "mode ${bond_mode}" macvlan bridge + xvlan_over_bond "mode ${bond_mode}" ipvlan l2 +done + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/bonding/config b/tools/testing/selftests/drivers/net/bonding/config index 899d7fb6ea8e..dad4e5fda4db 100644 --- a/tools/testing/selftests/drivers/net/bonding/config +++ b/tools/testing/selftests/drivers/net/bonding/config @@ -3,6 +3,7 @@ CONFIG_BRIDGE=y CONFIG_DUMMY=y CONFIG_IPV6=y CONFIG_MACVLAN=y +CONFIG_IPVLAN=y CONFIG_NET_ACT_GACT=y CONFIG_NET_CLS_FLOWER=y CONFIG_NET_SCH_INGRESS=y diff --git a/tools/testing/selftests/drivers/net/hds.py b/tools/testing/selftests/drivers/net/hds.py new file mode 100755 index 000000000000..394971b25c0b --- /dev/null +++ b/tools/testing/selftests/drivers/net/hds.py @@ -0,0 +1,120 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +import errno +from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_raises, KsftSkipEx +from lib.py import EthtoolFamily, NlError +from lib.py import NetDrvEnv + +def get_hds(cfg, netnl) -> None: + try: + rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}}) + except NlError as e: + raise KsftSkipEx('ring-get not supported by device') + if 'tcp-data-split' not in rings: + raise KsftSkipEx('tcp-data-split not supported by device') + +def get_hds_thresh(cfg, netnl) -> None: + try: + rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}}) + except NlError as e: + raise KsftSkipEx('ring-get not supported by device') + if 'hds-thresh' not in rings: + raise KsftSkipEx('hds-thresh not supported by device') + +def set_hds_enable(cfg, netnl) -> None: + try: + netnl.rings_set({'header': {'dev-index': cfg.ifindex}, 'tcp-data-split': 'enabled'}) + except NlError as e: + if e.error == errno.EINVAL: + raise KsftSkipEx("disabling of HDS not supported by the device") + elif e.error == errno.EOPNOTSUPP: + raise KsftSkipEx("ring-set not supported by the device") + try: + rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}}) + except NlError as e: + raise KsftSkipEx('ring-get not supported by device') + if 'tcp-data-split' not in rings: + raise KsftSkipEx('tcp-data-split not supported by device') + + ksft_eq('enabled', rings['tcp-data-split']) + +def set_hds_disable(cfg, netnl) -> None: + try: + netnl.rings_set({'header': {'dev-index': cfg.ifindex}, 'tcp-data-split': 'disabled'}) + except NlError as e: + if e.error == errno.EINVAL: + raise KsftSkipEx("disabling of HDS not supported by the device") + elif e.error == errno.EOPNOTSUPP: + raise KsftSkipEx("ring-set not supported by the device") + try: + rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}}) + except NlError as e: + raise KsftSkipEx('ring-get not supported by device') + if 'tcp-data-split' not in rings: + raise KsftSkipEx('tcp-data-split not supported by device') + + ksft_eq('disabled', rings['tcp-data-split']) + +def set_hds_thresh_zero(cfg, netnl) -> None: + try: + netnl.rings_set({'header': {'dev-index': cfg.ifindex}, 'hds-thresh': 0}) + except NlError as e: + if e.error == errno.EINVAL: + raise KsftSkipEx("hds-thresh-set not supported by the device") + elif e.error == errno.EOPNOTSUPP: + raise KsftSkipEx("ring-set not supported by the device") + try: + rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}}) + except NlError as e: + raise KsftSkipEx('ring-get not supported by device') + if 'hds-thresh' not in rings: + raise KsftSkipEx('hds-thresh not supported by device') + + ksft_eq(0, rings['hds-thresh']) + +def set_hds_thresh_max(cfg, netnl) -> None: + try: + rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}}) + except NlError as e: + raise KsftSkipEx('ring-get not supported by device') + if 'hds-thresh' not in rings: + raise KsftSkipEx('hds-thresh not supported by device') + try: + netnl.rings_set({'header': {'dev-index': cfg.ifindex}, 'hds-thresh': rings['hds-thresh-max']}) + except NlError as e: + if e.error == errno.EINVAL: + raise KsftSkipEx("hds-thresh-set not supported by the device") + elif e.error == errno.EOPNOTSUPP: + raise KsftSkipEx("ring-set not supported by the device") + rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}}) + ksft_eq(rings['hds-thresh'], rings['hds-thresh-max']) + +def set_hds_thresh_gt(cfg, netnl) -> None: + try: + rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}}) + except NlError as e: + raise KsftSkipEx('ring-get not supported by device') + if 'hds-thresh' not in rings: + raise KsftSkipEx('hds-thresh not supported by device') + if 'hds-thresh-max' not in rings: + raise KsftSkipEx('hds-thresh-max not defined by device') + hds_gt = rings['hds-thresh-max'] + 1 + with ksft_raises(NlError) as e: + netnl.rings_set({'header': {'dev-index': cfg.ifindex}, 'hds-thresh': hds_gt}) + ksft_eq(e.exception.nl_msg.error, -errno.EINVAL) + +def main() -> None: + with NetDrvEnv(__file__, queue_count=3) as cfg: + ksft_run([get_hds, + get_hds_thresh, + set_hds_disable, + set_hds_enable, + set_hds_thresh_zero, + set_hds_thresh_max, + set_hds_thresh_gt], + args=(cfg, EthtoolFamily())) + ksft_exit() + +if __name__ == "__main__": + main() diff --git a/tools/testing/selftests/drivers/net/hw/pp_alloc_fail.py b/tools/testing/selftests/drivers/net/hw/pp_alloc_fail.py index 05b6fbb3fcdd..ad192fef3117 100755 --- a/tools/testing/selftests/drivers/net/hw/pp_alloc_fail.py +++ b/tools/testing/selftests/drivers/net/hw/pp_alloc_fail.py @@ -21,9 +21,9 @@ def _enable_pp_allocation_fail(): if not os.path.exists("/sys/kernel/debug/fail_function"): raise KsftSkipEx("Kernel built without function error injection (or DebugFS)") - if not os.path.exists("/sys/kernel/debug/fail_function/page_pool_alloc_pages"): + if not os.path.exists("/sys/kernel/debug/fail_function/page_pool_alloc_netmems"): with open("/sys/kernel/debug/fail_function/inject", "w") as fp: - fp.write("page_pool_alloc_pages\n") + fp.write("page_pool_alloc_netmems\n") _write_fail_config({ "verbose": 0, @@ -37,7 +37,7 @@ def _disable_pp_allocation_fail(): if not os.path.exists("/sys/kernel/debug/fail_function"): return - if os.path.exists("/sys/kernel/debug/fail_function/page_pool_alloc_pages"): + if os.path.exists("/sys/kernel/debug/fail_function/page_pool_alloc_netmems"): with open("/sys/kernel/debug/fail_function/inject", "w") as fp: fp.write("\n") diff --git a/tools/testing/selftests/drivers/net/mlxsw/rif_bridge.sh b/tools/testing/selftests/drivers/net/mlxsw/rif_bridge.sh index b79542a4dcc7..4a11bf1d514a 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/rif_bridge.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/rif_bridge.sh @@ -12,6 +12,7 @@ ALL_TESTS=" bridge_rif_remaster_port " +REQUIRE_TEAMD="yes" NUM_NETIFS=2 source $lib_dir/lib.sh source $lib_dir/devlink_lib.sh diff --git a/tools/testing/selftests/drivers/net/mlxsw/rif_lag.sh b/tools/testing/selftests/drivers/net/mlxsw/rif_lag.sh index e28f978104f3..b8bbe94f4736 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/rif_lag.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/rif_lag.sh @@ -10,6 +10,7 @@ ALL_TESTS=" lag_rif_nomaster_addr " +REQUIRE_TEAMD="yes" NUM_NETIFS=2 source $lib_dir/lib.sh source $lib_dir/devlink_lib.sh diff --git a/tools/testing/selftests/drivers/net/mlxsw/rif_lag_vlan.sh b/tools/testing/selftests/drivers/net/mlxsw/rif_lag_vlan.sh index 6318cfa6434c..d1a9d379eaf3 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/rif_lag_vlan.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/rif_lag_vlan.sh @@ -10,6 +10,7 @@ ALL_TESTS=" lag_rif_nomaster_addr " +REQUIRE_TEAMD="yes" NUM_NETIFS=2 source $lib_dir/lib.sh source $lib_dir/devlink_lib.sh diff --git a/tools/testing/selftests/drivers/net/netdevsim/tc-mq-visibility.sh b/tools/testing/selftests/drivers/net/netdevsim/tc-mq-visibility.sh index fd13c8cfb7a8..b411fe66510f 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/tc-mq-visibility.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/tc-mq-visibility.sh @@ -58,9 +58,12 @@ for root in mq mqprio; do ethtool -L $NDEV combined 4 n_child_assert 4 "One real queue, rest default" - # Graft some - tcq replace parent 100:1 handle 204: - n_child_assert 3 "Grafted" + # Remove real one + tcq del parent 100:4 handle 204: + + # Replace default with pfifo + tcq replace parent 100:1 handle 205: pfifo limit 1000 + n_child_assert 3 "Deleting real one, replacing default one with pfifo" ethtool -L $NDEV combined 1 n_child_assert 1 "Grafted, one" diff --git a/tools/testing/selftests/kvm/aarch64/set_id_regs.c b/tools/testing/selftests/kvm/aarch64/set_id_regs.c index a79b7f18452d..3a97c160b5fe 100644 --- a/tools/testing/selftests/kvm/aarch64/set_id_regs.c +++ b/tools/testing/selftests/kvm/aarch64/set_id_regs.c @@ -152,7 +152,6 @@ static const struct reg_ftr_bits ftr_id_aa64mmfr0_el1[] = { REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR0_EL1, BIGENDEL0, 0), REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR0_EL1, SNSMEM, 0), REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR0_EL1, BIGEND, 0), - REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR0_EL1, ASIDBITS, 0), REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64MMFR0_EL1, PARANGE, 0), REG_FTR_END, }; diff --git a/tools/testing/selftests/kvm/s390x/ucontrol_test.c b/tools/testing/selftests/kvm/s390x/ucontrol_test.c index 0c112319dab1..135ee22856cf 100644 --- a/tools/testing/selftests/kvm/s390x/ucontrol_test.c +++ b/tools/testing/selftests/kvm/s390x/ucontrol_test.c @@ -210,10 +210,13 @@ TEST_F(uc_kvm, uc_attr_mem_limit) struct kvm_device_attr attr = { .group = KVM_S390_VM_MEM_CTRL, .attr = KVM_S390_VM_MEM_LIMIT_SIZE, - .addr = (unsigned long)&limit, + .addr = (u64)&limit, }; int rc; + rc = ioctl(self->vm_fd, KVM_HAS_DEVICE_ATTR, &attr); + EXPECT_EQ(0, rc); + rc = ioctl(self->vm_fd, KVM_GET_DEVICE_ATTR, &attr); EXPECT_EQ(0, rc); EXPECT_EQ(~0UL, limit); @@ -635,4 +638,171 @@ TEST_F(uc_kvm, uc_skey) uc_assert_diag44(self); } +static char uc_flic_b[PAGE_SIZE]; +static struct kvm_s390_io_adapter uc_flic_ioa = { .id = 0 }; +static struct kvm_s390_io_adapter_req uc_flic_ioam = { .id = 0 }; +static struct kvm_s390_ais_req uc_flic_asim = { .isc = 0 }; +static struct kvm_s390_ais_all uc_flic_asima = { .simm = 0 }; +static struct uc_flic_attr_test { + char *name; + struct kvm_device_attr a; + int hasrc; + int geterrno; + int seterrno; +} uc_flic_attr_tests[] = { + { + .name = "KVM_DEV_FLIC_GET_ALL_IRQS", + .seterrno = EINVAL, + .a = { + .group = KVM_DEV_FLIC_GET_ALL_IRQS, + .addr = (u64)&uc_flic_b, + .attr = PAGE_SIZE, + }, + }, + { + .name = "KVM_DEV_FLIC_ENQUEUE", + .geterrno = EINVAL, + .a = { .group = KVM_DEV_FLIC_ENQUEUE, }, + }, + { + .name = "KVM_DEV_FLIC_CLEAR_IRQS", + .geterrno = EINVAL, + .a = { .group = KVM_DEV_FLIC_CLEAR_IRQS, }, + }, + { + .name = "KVM_DEV_FLIC_ADAPTER_REGISTER", + .geterrno = EINVAL, + .a = { + .group = KVM_DEV_FLIC_ADAPTER_REGISTER, + .addr = (u64)&uc_flic_ioa, + }, + }, + { + .name = "KVM_DEV_FLIC_ADAPTER_MODIFY", + .geterrno = EINVAL, + .seterrno = EINVAL, + .a = { + .group = KVM_DEV_FLIC_ADAPTER_MODIFY, + .addr = (u64)&uc_flic_ioam, + .attr = sizeof(uc_flic_ioam), + }, + }, + { + .name = "KVM_DEV_FLIC_CLEAR_IO_IRQ", + .geterrno = EINVAL, + .seterrno = EINVAL, + .a = { + .group = KVM_DEV_FLIC_CLEAR_IO_IRQ, + .attr = 32, + }, + }, + { + .name = "KVM_DEV_FLIC_AISM", + .geterrno = EINVAL, + .seterrno = ENOTSUP, + .a = { + .group = KVM_DEV_FLIC_AISM, + .addr = (u64)&uc_flic_asim, + }, + }, + { + .name = "KVM_DEV_FLIC_AIRQ_INJECT", + .geterrno = EINVAL, + .a = { .group = KVM_DEV_FLIC_AIRQ_INJECT, }, + }, + { + .name = "KVM_DEV_FLIC_AISM_ALL", + .geterrno = ENOTSUP, + .seterrno = ENOTSUP, + .a = { + .group = KVM_DEV_FLIC_AISM_ALL, + .addr = (u64)&uc_flic_asima, + .attr = sizeof(uc_flic_asima), + }, + }, + { + .name = "KVM_DEV_FLIC_APF_ENABLE", + .geterrno = EINVAL, + .seterrno = EINVAL, + .a = { .group = KVM_DEV_FLIC_APF_ENABLE, }, + }, + { + .name = "KVM_DEV_FLIC_APF_DISABLE_WAIT", + .geterrno = EINVAL, + .seterrno = EINVAL, + .a = { .group = KVM_DEV_FLIC_APF_DISABLE_WAIT, }, + }, +}; + +TEST_F(uc_kvm, uc_flic_attrs) +{ + struct kvm_create_device cd = { .type = KVM_DEV_TYPE_FLIC }; + struct kvm_device_attr attr; + u64 value; + int rc, i; + + rc = ioctl(self->vm_fd, KVM_CREATE_DEVICE, &cd); + ASSERT_EQ(0, rc) TH_LOG("create device failed with err %s (%i)", + strerror(errno), errno); + + for (i = 0; i < ARRAY_SIZE(uc_flic_attr_tests); i++) { + TH_LOG("test %s", uc_flic_attr_tests[i].name); + attr = (struct kvm_device_attr) { + .group = uc_flic_attr_tests[i].a.group, + .attr = uc_flic_attr_tests[i].a.attr, + .addr = uc_flic_attr_tests[i].a.addr, + }; + if (attr.addr == 0) + attr.addr = (u64)&value; + + rc = ioctl(cd.fd, KVM_HAS_DEVICE_ATTR, &attr); + EXPECT_EQ(uc_flic_attr_tests[i].hasrc, !!rc) + TH_LOG("expected dev attr missing %s", + uc_flic_attr_tests[i].name); + + rc = ioctl(cd.fd, KVM_GET_DEVICE_ATTR, &attr); + EXPECT_EQ(!!uc_flic_attr_tests[i].geterrno, !!rc) + TH_LOG("get dev attr rc not expected on %s %s (%i)", + uc_flic_attr_tests[i].name, + strerror(errno), errno); + if (uc_flic_attr_tests[i].geterrno) + EXPECT_EQ(uc_flic_attr_tests[i].geterrno, errno) + TH_LOG("get dev attr errno not expected on %s %s (%i)", + uc_flic_attr_tests[i].name, + strerror(errno), errno); + + rc = ioctl(cd.fd, KVM_SET_DEVICE_ATTR, &attr); + EXPECT_EQ(!!uc_flic_attr_tests[i].seterrno, !!rc) + TH_LOG("set sev attr rc not expected on %s %s (%i)", + uc_flic_attr_tests[i].name, + strerror(errno), errno); + if (uc_flic_attr_tests[i].seterrno) + EXPECT_EQ(uc_flic_attr_tests[i].seterrno, errno) + TH_LOG("set dev attr errno not expected on %s %s (%i)", + uc_flic_attr_tests[i].name, + strerror(errno), errno); + } + + close(cd.fd); +} + +TEST_F(uc_kvm, uc_set_gsi_routing) +{ + struct kvm_irq_routing *routing = kvm_gsi_routing_create(); + struct kvm_irq_routing_entry ue = { + .type = KVM_IRQ_ROUTING_S390_ADAPTER, + .gsi = 1, + .u.adapter = (struct kvm_irq_routing_s390_adapter) { + .ind_addr = 0, + }, + }; + int rc; + + routing->entries[0] = ue; + routing->nr = 1; + rc = ioctl(self->vm_fd, KVM_SET_GSI_ROUTING, routing); + ASSERT_EQ(-1, rc) TH_LOG("err %s (%i)", strerror(errno), errno); + ASSERT_EQ(EINVAL, errno) TH_LOG("err %s (%i)", strerror(errno), errno); +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/mm/cow.c b/tools/testing/selftests/mm/cow.c index 32c6ccc2a6be..1238e1c5aae1 100644 --- a/tools/testing/selftests/mm/cow.c +++ b/tools/testing/selftests/mm/cow.c @@ -758,7 +758,7 @@ static void do_run_with_base_page(test_fn fn, bool swapout) } /* Populate a base page. */ - memset(mem, 0, pagesize); + memset(mem, 1, pagesize); if (swapout) { madvise(mem, pagesize, MADV_PAGEOUT); @@ -824,12 +824,12 @@ static void do_run_with_thp(test_fn fn, enum thp_run thp_run, size_t thpsize) * Try to populate a THP. Touch the first sub-page and test if * we get the last sub-page populated automatically. */ - mem[0] = 0; + mem[0] = 1; if (!pagemap_is_populated(pagemap_fd, mem + thpsize - pagesize)) { ksft_test_result_skip("Did not get a THP populated\n"); goto munmap; } - memset(mem, 0, thpsize); + memset(mem, 1, thpsize); size = thpsize; switch (thp_run) { @@ -1012,7 +1012,7 @@ static void run_with_hugetlb(test_fn fn, const char *desc, size_t hugetlbsize) } /* Populate an huge page. */ - memset(mem, 0, hugetlbsize); + memset(mem, 1, hugetlbsize); /* * We need a total of two hugetlb pages to handle COW/unsharing diff --git a/tools/testing/selftests/net/cmsg_time.sh b/tools/testing/selftests/net/cmsg_time.sh index 1d7e756644bc..478af0aefa97 100755 --- a/tools/testing/selftests/net/cmsg_time.sh +++ b/tools/testing/selftests/net/cmsg_time.sh @@ -34,13 +34,28 @@ BAD=0 TOTAL=0 check_result() { + local ret=$1 + local got=$2 + local exp=$3 + local case=$4 + local xfail=$5 + local xf= + local inc= + + if [ "$xfail" == "xfail" ]; then + xf="(XFAIL)" + inc=0 + else + inc=1 + fi + ((TOTAL++)) - if [ $1 -ne 0 ]; then - echo " Case $4 returned $1, expected 0" - ((BAD++)) + if [ $ret -ne 0 ]; then + echo " Case $case returned $ret, expected 0 $xf" + ((BAD+=inc)) elif [ "$2" != "$3" ]; then - echo " Case $4 returned '$2', expected '$3'" - ((BAD++)) + echo " Case $case returned '$got', expected '$exp' $xf" + ((BAD+=inc)) fi } @@ -66,14 +81,14 @@ for i in "-4 $TGT4" "-6 $TGT6"; do awk '/SND/ { if ($3 > 1000) print "OK"; }') check_result $? "$ts" "OK" "$prot - TXTIME abs" - [ "$KSFT_MACHINE_SLOW" = yes ] && delay=8000 || delay=1000 + [ "$KSFT_MACHINE_SLOW" = yes ] && xfail=xfail - ts=$(ip netns exec $NS ./cmsg_sender -p $p $i 1234 -t -d $delay | + ts=$(ip netns exec $NS ./cmsg_sender -p $p $i 1234 -t -d 1000 | awk '/SND/ {snd=$3} /SCHED/ {sch=$3} - END { if (snd - sch > '$((delay/2))') print "OK"; - else print snd, "-", sch, "<", '$((delay/2))'; }') - check_result $? "$ts" "OK" "$prot - TXTIME rel" + END { if (snd - sch > 500) print "OK"; + else print snd, "-", sch, "<", 500; }') + check_result $? "$ts" "OK" "$prot - TXTIME rel" $xfail done done diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 1fd40bada694..8de80acf249e 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -68,6 +68,7 @@ declare -A NETIFS=( : "${REQUIRE_JQ:=yes}" : "${REQUIRE_MZ:=yes}" : "${REQUIRE_MTOOLS:=no}" +: "${REQUIRE_TEAMD:=no}" # Whether to override MAC addresses on interfaces participating in the test. : "${STABLE_MAC_ADDRS:=no}" @@ -321,6 +322,9 @@ fi if [[ "$REQUIRE_MZ" = "yes" ]]; then require_command $MZ fi +if [[ "$REQUIRE_TEAMD" = "yes" ]]; then + require_command $TEAMD +fi if [[ "$REQUIRE_MTOOLS" = "yes" ]]; then # https://github.com/troglobit/mtools require_command msend diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh index fe4d7c906a70..a20d22d1df36 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh @@ -49,6 +49,7 @@ ALL_TESTS=" test_mirror_gretap_second " +REQUIRE_TEAMD="yes" NUM_NETIFS=6 source lib.sh source mirror_lib.sh diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_lag_lacp.sh b/tools/testing/selftests/net/forwarding/mirror_gre_lag_lacp.sh index 1261e6f46e34..ff7049582d35 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_lag_lacp.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_lag_lacp.sh @@ -53,6 +53,7 @@ ALL_TESTS=" test_mirror_gretap_second " +REQUIRE_TEAMD="yes" NUM_NETIFS=6 source lib.sh source mirror_lib.sh diff --git a/tools/testing/selftests/net/forwarding/router_bridge_1d_lag.sh b/tools/testing/selftests/net/forwarding/router_bridge_1d_lag.sh index e064b946e821..16583a470ec3 100755 --- a/tools/testing/selftests/net/forwarding/router_bridge_1d_lag.sh +++ b/tools/testing/selftests/net/forwarding/router_bridge_1d_lag.sh @@ -109,6 +109,7 @@ ALL_TESTS=" ping_ipv4 ping_ipv6 " +REQUIRE_TEAMD="yes" NUM_NETIFS=8 source lib.sh diff --git a/tools/testing/selftests/net/forwarding/router_bridge_lag.sh b/tools/testing/selftests/net/forwarding/router_bridge_lag.sh index f05ffe213c46..2a4cd1af1b85 100755 --- a/tools/testing/selftests/net/forwarding/router_bridge_lag.sh +++ b/tools/testing/selftests/net/forwarding/router_bridge_lag.sh @@ -76,6 +76,7 @@ ping_ipv4 ping_ipv6 "} +REQUIRE_TEAMD="yes" NUM_NETIFS=8 : ${lib_dir:=.} source $lib_dir/lib.sh diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c index 4209b9569039..414addef9a45 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.c +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c @@ -25,6 +25,8 @@ #include <sys/types.h> #include <sys/mman.h> +#include <arpa/inet.h> + #include <netdb.h> #include <netinet/in.h> @@ -1211,23 +1213,42 @@ static void parse_setsock_options(const char *name) exit(1); } -void xdisconnect(int fd, int addrlen) +void xdisconnect(int fd) { - struct sockaddr_storage empty; + socklen_t addrlen = sizeof(struct sockaddr_storage); + struct sockaddr_storage addr, empty; int msec_sleep = 10; - int queued = 1; - int i; + void *raw_addr; + int i, cmdlen; + char cmd[128]; + + /* get the local address and convert it to string */ + if (getsockname(fd, (struct sockaddr *)&addr, &addrlen) < 0) + xerror("getsockname"); + + if (addr.ss_family == AF_INET) + raw_addr = &(((struct sockaddr_in *)&addr)->sin_addr); + else if (addr.ss_family == AF_INET6) + raw_addr = &(((struct sockaddr_in6 *)&addr)->sin6_addr); + else + xerror("bad family"); + + strcpy(cmd, "ss -M | grep -q "); + cmdlen = strlen(cmd); + if (!inet_ntop(addr.ss_family, raw_addr, &cmd[cmdlen], + sizeof(cmd) - cmdlen)) + xerror("inet_ntop"); shutdown(fd, SHUT_WR); - /* while until the pending data is completely flushed, the later + /* + * wait until the pending data is completely flushed and all + * the MPTCP sockets reached the closed status. * disconnect will bypass/ignore/drop any pending data. */ for (i = 0; ; i += msec_sleep) { - if (ioctl(fd, SIOCOUTQ, &queued) < 0) - xerror("can't query out socket queue: %d", errno); - - if (!queued) + /* closed socket are not listed by 'ss' */ + if (system(cmd) != 0) break; if (i > poll_timeout) @@ -1281,9 +1302,9 @@ again: return ret; if (cfg_truncate > 0) { - xdisconnect(fd, peer->ai_addrlen); + xdisconnect(fd); } else if (--cfg_repeat > 0) { - xdisconnect(fd, peer->ai_addrlen); + xdisconnect(fd); /* the socket could be unblocking at this point, we need the * connect to be blocking diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index b48b4e56826a..5e3c56253274 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -137,7 +137,7 @@ TEST_GROUP="" #shellcheck disable=SC2317 cleanup() { - rm -f "$cin_disconnect" "$cout_disconnect" + rm -f "$cin_disconnect" rm -f "$cin" "$cout" rm -f "$sin" "$sout" rm -f "$capout" @@ -155,7 +155,6 @@ cin=$(mktemp) cout=$(mktemp) capout=$(mktemp) cin_disconnect="$cin".disconnect -cout_disconnect="$cout".disconnect trap cleanup EXIT mptcp_lib_ns_init ns1 ns2 ns3 ns4 @@ -445,12 +444,8 @@ do_transfer() printf "(duration %05sms) " "${duration}" if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then mptcp_lib_pr_fail "client exit code $retc, server $rets" - echo -e "\nnetns ${listener_ns} socket stat for ${port}:" 1>&2 - ip netns exec ${listener_ns} ss -Menita 1>&2 -o "sport = :$port" - cat /tmp/${listener_ns}.out - echo -e "\nnetns ${connector_ns} socket stat for ${port}:" 1>&2 - ip netns exec ${connector_ns} ss -Menita 1>&2 -o "dport = :$port" - [ ${listener_ns} != ${connector_ns} ] && cat /tmp/${connector_ns}.out + mptcp_lib_pr_err_stats "${listener_ns}" "${connector_ns}" "${port}" \ + "/tmp/${listener_ns}.out" "/tmp/${connector_ns}.out" echo cat "$capout" @@ -587,7 +582,7 @@ make_file() mptcp_lib_make_file $name 1024 $ksize dd if=/dev/urandom conv=notrunc of="$name" oflag=append bs=1 count=$rem 2> /dev/null - echo "Created $name (size $(du -b "$name")) containing data sent by $who" + echo "Created $name (size $(stat -c "%s" "$name") B) containing data sent by $who" } run_tests_lo() diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index c07e2bd3a315..13a3b68181ee 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -1039,13 +1039,8 @@ do_transfer() if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then fail_test "client exit code $retc, server $rets" - echo -e "\nnetns ${listener_ns} socket stat for ${port}:" 1>&2 - ip netns exec ${listener_ns} ss -Menita 1>&2 -o "sport = :$port" - cat /tmp/${listener_ns}.out - echo -e "\nnetns ${connector_ns} socket stat for ${port}:" 1>&2 - ip netns exec ${connector_ns} ss -Menita 1>&2 -o "dport = :$port" - cat /tmp/${connector_ns}.out - + mptcp_lib_pr_err_stats "${listener_ns}" "${connector_ns}" "${port}" \ + "/tmp/${listener_ns}.out" "/tmp/${connector_ns}.out" return 1 fi diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh index 975d4d4c862a..051e289d7967 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -107,6 +107,27 @@ mptcp_lib_pr_info() { mptcp_lib_print_info "INFO: ${*}" } +# $1-2: listener/connector ns ; $3 port ; $4-5 listener/connector stat file +mptcp_lib_pr_err_stats() { + local lns="${1}" + local cns="${2}" + local port="${3}" + local lstat="${4}" + local cstat="${5}" + + echo -en "${MPTCP_LIB_COLOR_RED}" + { + printf "\nnetns %s (listener) socket stat for %d:\n" "${lns}" "${port}" + ip netns exec "${lns}" ss -Menitam -o "sport = :${port}" + cat "${lstat}" + + printf "\nnetns %s (connector) socket stat for %d:\n" "${cns}" "${port}" + ip netns exec "${cns}" ss -Menitam -o "dport = :${port}" + [ "${lstat}" != "${cstat}" ] && cat "${cstat}" + } 1>&2 + echo -en "${MPTCP_LIB_COLOR_RESET}" +} + # SELFTESTS_MPTCP_LIB_EXPECT_ALL_FEATURES env var can be set when validating all # features using the last version of the kernel and the selftests to make sure # a test is not being skipped by mistake. diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh index 5e8d5b83e2d0..418a903c3a4d 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh @@ -169,6 +169,11 @@ do_transfer() cmsg+=",TCPINQ" fi + NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \ + nstat -n + NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \ + nstat -n + timeout ${timeout_test} \ ip netns exec ${listener_ns} \ $mptcp_connect -t ${timeout_poll} -l -M 1 -p $port -s ${srv_proto} -c "${cmsg}" \ @@ -189,14 +194,16 @@ do_transfer() wait $spid local rets=$? + NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \ + nstat | grep Tcp > /tmp/${listener_ns}.out + NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \ + nstat | grep Tcp > /tmp/${connector_ns}.out + print_title "Transfer ${ip:2}" if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then mptcp_lib_pr_fail "client exit code $retc, server $rets" - echo -e "\nnetns ${listener_ns} socket stat for ${port}:" 1>&2 - ip netns exec ${listener_ns} ss -Menita 1>&2 -o "sport = :$port" - - echo -e "\nnetns ${connector_ns} socket stat for ${port}:" 1>&2 - ip netns exec ${connector_ns} ss -Menita 1>&2 -o "dport = :$port" + mptcp_lib_pr_err_stats "${listener_ns}" "${connector_ns}" "${port}" \ + "/tmp/${listener_ns}.out" "/tmp/${connector_ns}.out" mptcp_lib_result_fail "transfer ${ip}" diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh index 8fa77c8e9b65..9c2a415976cb 100755 --- a/tools/testing/selftests/net/mptcp/simult_flows.sh +++ b/tools/testing/selftests/net/mptcp/simult_flows.sh @@ -155,6 +155,11 @@ do_transfer() sleep 1 fi + NSTAT_HISTORY=/tmp/${ns3}.nstat ip netns exec ${ns3} \ + nstat -n + NSTAT_HISTORY=/tmp/${ns1}.nstat ip netns exec ${ns1} \ + nstat -n + timeout ${timeout_test} \ ip netns exec ${ns3} \ ./mptcp_connect -jt ${timeout_poll} -l -p $port -T $max_time \ @@ -180,25 +185,27 @@ do_transfer() kill ${cappid_connector} fi + NSTAT_HISTORY=/tmp/${ns3}.nstat ip netns exec ${ns3} \ + nstat | grep Tcp > /tmp/${ns3}.out + NSTAT_HISTORY=/tmp/${ns1}.nstat ip netns exec ${ns1} \ + nstat | grep Tcp > /tmp/${ns1}.out + cmp $sin $cout > /dev/null 2>&1 local cmps=$? cmp $cin $sout > /dev/null 2>&1 local cmpc=$? - printf "%-16s" " max $max_time " if [ $retc -eq 0 ] && [ $rets -eq 0 ] && \ [ $cmpc -eq 0 ] && [ $cmps -eq 0 ]; then + printf "%-16s" " max $max_time " mptcp_lib_pr_ok cat "$capout" return 0 fi - mptcp_lib_pr_fail - echo "client exit code $retc, server $rets" 1>&2 - echo -e "\nnetns ${ns3} socket stat for $port:" 1>&2 - ip netns exec ${ns3} ss -nita 1>&2 -o "sport = :$port" - echo -e "\nnetns ${ns1} socket stat for $port:" 1>&2 - ip netns exec ${ns1} ss -nita 1>&2 -o "dport = :$port" + mptcp_lib_pr_fail "client exit code $retc, server $rets" + mptcp_lib_pr_err_stats "${ns3}" "${ns1}" "${port}" \ + "/tmp/${ns3}.out" "/tmp/${ns1}.out" ls -l $sin $cout ls -l $cin $sout diff --git a/tools/testing/selftests/net/packetdrill/ksft_runner.sh b/tools/testing/selftests/net/packetdrill/ksft_runner.sh index ff989c325eef..e15c43b7359b 100755 --- a/tools/testing/selftests/net/packetdrill/ksft_runner.sh +++ b/tools/testing/selftests/net/packetdrill/ksft_runner.sh @@ -43,6 +43,7 @@ if [[ -n "${KSFT_MACHINE_SLOW}" ]]; then "tcp_timestamping.*.pkt" "tcp_user_timeout_user-timeout-probe.pkt" "tcp_zerocopy_epoll_.*.pkt" + "tcp_tcp_info_tcp-info-*-limited.pkt" ) readonly xfail_regex="^($(printf '%s|' "${xfail_list[@]}"))$" [[ "$script" =~ ${xfail_regex} ]] && failfunc=ktap_test_xfail diff --git a/tools/testing/selftests/riscv/abi/pointer_masking.c b/tools/testing/selftests/riscv/abi/pointer_masking.c index dee41b7ee3e3..059d2e87eb1f 100644 --- a/tools/testing/selftests/riscv/abi/pointer_masking.c +++ b/tools/testing/selftests/riscv/abi/pointer_masking.c @@ -185,8 +185,20 @@ static void test_fork_exec(void) } } +static bool pwrite_wrapper(int fd, void *buf, size_t count, const char *msg) +{ + int ret = pwrite(fd, buf, count, 0); + + if (ret != count) { + ksft_perror(msg); + return false; + } + return true; +} + static void test_tagged_addr_abi_sysctl(void) { + char *err_pwrite_msg = "failed to write to /proc/sys/abi/tagged_addr_disabled\n"; char value; int fd; @@ -200,14 +212,18 @@ static void test_tagged_addr_abi_sysctl(void) } value = '1'; - pwrite(fd, &value, 1, 0); - ksft_test_result(set_tagged_addr_ctrl(min_pmlen, true) == -EINVAL, - "sysctl disabled\n"); + if (!pwrite_wrapper(fd, &value, 1, "write '1'")) + ksft_test_result_fail(err_pwrite_msg); + else + ksft_test_result(set_tagged_addr_ctrl(min_pmlen, true) == -EINVAL, + "sysctl disabled\n"); value = '0'; - pwrite(fd, &value, 1, 0); - ksft_test_result(set_tagged_addr_ctrl(min_pmlen, true) == 0, - "sysctl enabled\n"); + if (!pwrite_wrapper(fd, &value, 1, "write '0'")) + ksft_test_result_fail(err_pwrite_msg); + else + ksft_test_result(set_tagged_addr_ctrl(min_pmlen, true) == 0, + "sysctl enabled\n"); set_tagged_addr_ctrl(0, false); diff --git a/tools/testing/selftests/riscv/vector/v_initval_nolibc.c b/tools/testing/selftests/riscv/vector/v_initval_nolibc.c index 1dd94197da30..6174ffe016dc 100644 --- a/tools/testing/selftests/riscv/vector/v_initval_nolibc.c +++ b/tools/testing/selftests/riscv/vector/v_initval_nolibc.c @@ -25,6 +25,8 @@ int main(void) unsigned long vl; char *datap, *tmp; + ksft_set_plan(1); + datap = malloc(MAX_VSIZE); if (!datap) { ksft_test_result_fail("fail to allocate memory for size = %d\n", MAX_VSIZE); @@ -63,6 +65,8 @@ int main(void) } free(datap); + + ksft_test_result_pass("tests for v_initval_nolibc pass\n"); ksft_exit_pass(); return 0; } diff --git a/tools/testing/selftests/riscv/vector/vstate_prctl.c b/tools/testing/selftests/riscv/vector/vstate_prctl.c index 895177f6bf4c..40b3bffcbb40 100644 --- a/tools/testing/selftests/riscv/vector/vstate_prctl.c +++ b/tools/testing/selftests/riscv/vector/vstate_prctl.c @@ -76,6 +76,8 @@ int main(void) long flag, expected; long rc; + ksft_set_plan(1); + pair.key = RISCV_HWPROBE_KEY_IMA_EXT_0; rc = riscv_hwprobe(&pair, 1, 0, NULL, 0); if (rc < 0) { diff --git a/tools/testing/shared/linux/maple_tree.h b/tools/testing/shared/linux/maple_tree.h index 06c89bdcc515..f67d47d32857 100644 --- a/tools/testing/shared/linux/maple_tree.h +++ b/tools/testing/shared/linux/maple_tree.h @@ -2,6 +2,6 @@ #define atomic_t int32_t #define atomic_inc(x) uatomic_inc(x) #define atomic_read(x) uatomic_read(x) -#define atomic_set(x, y) do {} while (0) +#define atomic_set(x, y) uatomic_set(x, y) #define U8_MAX UCHAR_MAX #include "../../../../include/linux/maple_tree.h" diff --git a/tools/testing/vma/linux/atomic.h b/tools/testing/vma/linux/atomic.h index e01f66f98982..3e1b6adc027b 100644 --- a/tools/testing/vma/linux/atomic.h +++ b/tools/testing/vma/linux/atomic.h @@ -6,7 +6,7 @@ #define atomic_t int32_t #define atomic_inc(x) uatomic_inc(x) #define atomic_read(x) uatomic_read(x) -#define atomic_set(x, y) do {} while (0) +#define atomic_set(x, y) uatomic_set(x, y) #define U8_MAX UCHAR_MAX #endif /* _LINUX_ATOMIC_H */ |