diff options
638 files changed, 12638 insertions, 4509 deletions
@@ -226,6 +226,7 @@ Fangrui Song <i@maskray.me> <maskray@google.com> Felipe W Damasio <felipewd@terra.com.br> Felix Kuhling <fxkuehl@gmx.de> Felix Moeller <felix@derklecks.de> +Feng Tang <feng.79.tang@gmail.com> <feng.tang@intel.com> Fenglin Wu <quic_fenglinw@quicinc.com> <fenglinw@codeaurora.org> Filipe Lautert <filipe@icewall.org> Finn Thain <fthain@linux-m68k.org> <fthain@telegraphics.com.au> @@ -317,6 +318,8 @@ Jayachandran C <c.jayachandran@gmail.com> <jnair@caviumnetworks.com> Jean Tourrilhes <jt@hpl.hp.com> Jeevan Shriram <quic_jshriram@quicinc.com> <jshriram@codeaurora.org> Jeff Garzik <jgarzik@pretzel.yyz.us> +Jeff Johnson <jeff.johnson@oss.qualcomm.com> <jjohnson@codeaurora.org> +Jeff Johnson <jeff.johnson@oss.qualcomm.com> <quic_jjohnson@quicinc.com> Jeff Layton <jlayton@kernel.org> <jlayton@poochiereds.net> Jeff Layton <jlayton@kernel.org> <jlayton@primarydata.com> Jeff Layton <jlayton@kernel.org> <jlayton@redhat.com> @@ -531,6 +534,7 @@ Nicholas Piggin <npiggin@gmail.com> <npiggin@kernel.dk> Nicholas Piggin <npiggin@gmail.com> <npiggin@suse.de> Nicholas Piggin <npiggin@gmail.com> <nickpiggin@yahoo.com.au> Nicholas Piggin <npiggin@gmail.com> <piggin@cyberone.com.au> +Nick Desaulniers <nick.desaulniers+lkml@gmail.com> <ndesaulniers@google.com> Nicolas Ferre <nicolas.ferre@microchip.com> <nicolas.ferre@atmel.com> Nicolas Pitre <nico@fluxnic.net> <nicolas.pitre@linaro.org> Nicolas Pitre <nico@fluxnic.net> <nico@linaro.org> diff --git a/Documentation/arch/arm64/gcs.rst b/Documentation/arch/arm64/gcs.rst index 1f65a3193e77..226c0b008456 100644 --- a/Documentation/arch/arm64/gcs.rst +++ b/Documentation/arch/arm64/gcs.rst @@ -37,7 +37,7 @@ intended to be exhaustive. shadow stacks rather than GCS. * Support for GCS is reported to userspace via HWCAP_GCS in the aux vector - AT_HWCAP2 entry. + AT_HWCAP entry. * GCS is enabled per thread. While there is support for disabling GCS at runtime this should be done with great care. diff --git a/Documentation/devicetree/bindings/clock/qcom,gpucc.yaml b/Documentation/devicetree/bindings/clock/qcom,gpucc.yaml index 0858fd635282..4cdff6161bf0 100644 --- a/Documentation/devicetree/bindings/clock/qcom,gpucc.yaml +++ b/Documentation/devicetree/bindings/clock/qcom,gpucc.yaml @@ -8,6 +8,7 @@ title: Qualcomm Graphics Clock & Reset Controller maintainers: - Taniya Das <quic_tdas@quicinc.com> + - Imran Shaik <quic_imrashai@quicinc.com> description: | Qualcomm graphics clock control module provides the clocks, resets and power @@ -23,10 +24,12 @@ description: | include/dt-bindings/clock/qcom,gpucc-sm8150.h include/dt-bindings/clock/qcom,gpucc-sm8250.h include/dt-bindings/clock/qcom,gpucc-sm8350.h + include/dt-bindings/clock/qcom,qcs8300-gpucc.h properties: compatible: enum: + - qcom,qcs8300-gpucc - qcom,sdm845-gpucc - qcom,sa8775p-gpucc - qcom,sc7180-gpucc diff --git a/Documentation/devicetree/bindings/clock/qcom,sa8775p-camcc.yaml b/Documentation/devicetree/bindings/clock/qcom,sa8775p-camcc.yaml index 36a60d8f5ae3..81623f59d11d 100644 --- a/Documentation/devicetree/bindings/clock/qcom,sa8775p-camcc.yaml +++ b/Documentation/devicetree/bindings/clock/qcom,sa8775p-camcc.yaml @@ -8,16 +8,20 @@ title: Qualcomm Camera Clock & Reset Controller on SA8775P maintainers: - Taniya Das <quic_tdas@quicinc.com> + - Imran Shaik <quic_imrashai@quicinc.com> description: | Qualcomm camera clock control module provides the clocks, resets and power domains on SA8775p. - See also: include/dt-bindings/clock/qcom,sa8775p-camcc.h + See also: + include/dt-bindings/clock/qcom,qcs8300-camcc.h + include/dt-bindings/clock/qcom,sa8775p-camcc.h properties: compatible: enum: + - qcom,qcs8300-camcc - qcom,sa8775p-camcc clocks: diff --git a/Documentation/devicetree/bindings/clock/qcom,sa8775p-videocc.yaml b/Documentation/devicetree/bindings/clock/qcom,sa8775p-videocc.yaml index 928131bff4c1..07e5d811d816 100644 --- a/Documentation/devicetree/bindings/clock/qcom,sa8775p-videocc.yaml +++ b/Documentation/devicetree/bindings/clock/qcom,sa8775p-videocc.yaml @@ -18,6 +18,7 @@ description: | properties: compatible: enum: + - qcom,qcs8300-videocc - qcom,sa8775p-videocc clocks: diff --git a/Documentation/devicetree/bindings/display/panel/powertip,hx8238a.yaml b/Documentation/devicetree/bindings/display/panel/powertip,hx8238a.yaml new file mode 100644 index 000000000000..b7d74faeb5d5 --- /dev/null +++ b/Documentation/devicetree/bindings/display/panel/powertip,hx8238a.yaml @@ -0,0 +1,29 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/display/panel/powertip,hx8238a.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Powertip Electronic Technology Co. 320 x 240 LCD panel + +maintainers: + - Lukasz Majewski <lukma@denx.de> + +allOf: + - $ref: panel-dpi.yaml# + +properties: + compatible: + items: + - const: powertip,hx8238a + - {} # panel-dpi, but not listed here to avoid false select + + height-mm: true + panel-timing: true + port: true + power-supply: true + width-mm: true + +additionalProperties: false + +... diff --git a/Documentation/devicetree/bindings/display/panel/powertip,st7272.yaml b/Documentation/devicetree/bindings/display/panel/powertip,st7272.yaml new file mode 100644 index 000000000000..f3622800f13f --- /dev/null +++ b/Documentation/devicetree/bindings/display/panel/powertip,st7272.yaml @@ -0,0 +1,29 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/display/panel/powertip,st7272.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Powertip Electronic Technology Co. 320 x 240 LCD panel + +maintainers: + - Lukasz Majewski <lukma@denx.de> + +allOf: + - $ref: panel-dpi.yaml# + +properties: + compatible: + items: + - const: powertip,st7272 + - {} # panel-dpi, but not listed here to avoid false select + + height-mm: true + panel-timing: true + port: true + power-supply: true + width-mm: true + +additionalProperties: false + +... diff --git a/Documentation/devicetree/bindings/display/ti/ti,am65x-dss.yaml b/Documentation/devicetree/bindings/display/ti/ti,am65x-dss.yaml index 55e3e490d0e6..31c4ffcb599c 100644 --- a/Documentation/devicetree/bindings/display/ti/ti,am65x-dss.yaml +++ b/Documentation/devicetree/bindings/display/ti/ti,am65x-dss.yaml @@ -23,7 +23,7 @@ properties: compatible: enum: - ti,am625-dss - - ti,am62a7,dss + - ti,am62a7-dss - ti,am65x-dss reg: diff --git a/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml b/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml index 97dd1a7c5ed2..73252fe56fe6 100644 --- a/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml +++ b/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml @@ -10,9 +10,6 @@ title: maintainers: - Marc Kleine-Budde <mkl@pengutronix.de> -allOf: - - $ref: can-controller.yaml# - properties: compatible: oneOf: @@ -28,6 +25,7 @@ properties: - fsl,vf610-flexcan - fsl,ls1021ar2-flexcan - fsl,lx2160ar1-flexcan + - nxp,s32g2-flexcan - items: - enum: - fsl,imx53-flexcan @@ -43,12 +41,21 @@ properties: - enum: - fsl,ls1028ar1-flexcan - const: fsl,lx2160ar1-flexcan + - items: + - enum: + - nxp,s32g3-flexcan + - const: nxp,s32g2-flexcan reg: maxItems: 1 interrupts: - maxItems: 1 + minItems: 1 + maxItems: 4 + + interrupt-names: + minItems: 1 + maxItems: 4 clocks: maxItems: 2 @@ -136,6 +143,35 @@ required: - reg - interrupts +allOf: + - $ref: can-controller.yaml# + - if: + properties: + compatible: + contains: + const: nxp,s32g2-flexcan + then: + properties: + interrupts: + items: + - description: Message Buffer interrupt for mailboxes 0-7 and Enhanced RX FIFO + - description: Device state change + - description: Bus Error detection + - description: Message Buffer interrupt for mailboxes 8-127 + interrupt-names: + items: + - const: mb-0 + - const: state + - const: berr + - const: mb-1 + required: + - interrupt-names + else: + properties: + interrupts: + maxItems: 1 + interrupt-names: false + additionalProperties: false examples: diff --git a/Documentation/devicetree/bindings/net/can/microchip,mcp251xfd.yaml b/Documentation/devicetree/bindings/net/can/microchip,mcp251xfd.yaml index 2a98b26630cb..c155c9c6db39 100644 --- a/Documentation/devicetree/bindings/net/can/microchip,mcp251xfd.yaml +++ b/Documentation/devicetree/bindings/net/can/microchip,mcp251xfd.yaml @@ -40,7 +40,7 @@ properties: microchip,rx-int-gpios: description: - GPIO phandle of GPIO connected to to INT1 pin of the MCP251XFD, which + GPIO phandle of GPIO connected to INT1 pin of the MCP251XFD, which signals a pending RX interrupt. maxItems: 1 diff --git a/Documentation/devicetree/bindings/net/dsa/brcm,b53.yaml b/Documentation/devicetree/bindings/net/dsa/brcm,b53.yaml index 4c78c546343f..d6c957a33b48 100644 --- a/Documentation/devicetree/bindings/net/dsa/brcm,b53.yaml +++ b/Documentation/devicetree/bindings/net/dsa/brcm,b53.yaml @@ -16,6 +16,7 @@ properties: compatible: oneOf: - const: brcm,bcm5325 + - const: brcm,bcm53101 - const: brcm,bcm53115 - const: brcm,bcm53125 - const: brcm,bcm53128 @@ -77,6 +78,7 @@ allOf: contains: enum: - brcm,bcm5325 + - brcm,bcm53101 - brcm,bcm53115 - brcm,bcm53125 - brcm,bcm53128 diff --git a/Documentation/devicetree/bindings/net/ethernet-phy.yaml b/Documentation/devicetree/bindings/net/ethernet-phy.yaml index 2c71454ae8e3..824bbe4333b7 100644 --- a/Documentation/devicetree/bindings/net/ethernet-phy.yaml +++ b/Documentation/devicetree/bindings/net/ethernet-phy.yaml @@ -232,6 +232,12 @@ properties: PHY's that have configurable TX internal delays. If this property is present then the PHY applies the TX delay. + tx-amplitude-100base-tx-percent: + description: + Transmit amplitude gain applied for 100BASE-TX. 100% matches 2V + peak-to-peak specified in ANSI X3.263. When omitted, the PHYs default + will be left as is. + leds: type: object diff --git a/Documentation/devicetree/bindings/net/realtek,rtl9301-mdio.yaml b/Documentation/devicetree/bindings/net/realtek,rtl9301-mdio.yaml new file mode 100644 index 000000000000..02e4e33e9969 --- /dev/null +++ b/Documentation/devicetree/bindings/net/realtek,rtl9301-mdio.yaml @@ -0,0 +1,86 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/realtek,rtl9301-mdio.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Realtek RTL9300 MDIO Controller + +maintainers: + - Chris Packham <chris.packham@alliedtelesis.co.nz> + +properties: + compatible: + oneOf: + - items: + - enum: + - realtek,rtl9302b-mdio + - realtek,rtl9302c-mdio + - realtek,rtl9303-mdio + - const: realtek,rtl9301-mdio + - const: realtek,rtl9301-mdio + + '#address-cells': + const: 1 + + '#size-cells': + const: 0 + + reg: + maxItems: 1 + +patternProperties: + '^mdio-bus@[0-3]$': + $ref: mdio.yaml# + + properties: + reg: + maxItems: 1 + + required: + - reg + + patternProperties: + '^ethernet-phy@[a-f0-9]+$': + type: object + $ref: ethernet-phy.yaml# + unevaluatedProperties: false + + unevaluatedProperties: false + +required: + - compatible + - reg + +unevaluatedProperties: false + +examples: + - | + mdio-controller@ca00 { + compatible = "realtek,rtl9301-mdio"; + reg = <0xca00 0x200>; + #address-cells = <1>; + #size-cells = <0>; + + mdio-bus@0 { + reg = <0>; + #address-cells = <1>; + #size-cells = <0>; + + ethernet-phy@0 { + compatible = "ethernet-phy-ieee802.3-c45"; + reg = <0>; + }; + }; + + mdio-bus@1 { + reg = <1>; + #address-cells = <1>; + #size-cells = <0>; + + ethernet-phy@0 { + compatible = "ethernet-phy-ieee802.3-c45"; + reg = <0>; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/mfd/realtek,rtl9301-switch.yaml b/Documentation/devicetree/bindings/net/realtek,rtl9301-switch.yaml index f053303ab1e6..80eabc170669 100644 --- a/Documentation/devicetree/bindings/mfd/realtek,rtl9301-switch.yaml +++ b/Documentation/devicetree/bindings/net/realtek,rtl9301-switch.yaml @@ -1,7 +1,7 @@ # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) %YAML 1.2 --- -$id: http://devicetree.org/schemas/mfd/realtek,rtl9301-switch.yaml# +$id: http://devicetree.org/schemas/net/realtek,rtl9301-switch.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# title: Realtek Switch with Internal CPU @@ -14,6 +14,8 @@ description: number of different peripherals are accessed through a common register block, represented here as a syscon node. +$ref: ethernet-switch.yaml#/$defs/ethernet-ports + properties: compatible: items: @@ -28,12 +30,23 @@ properties: reg: maxItems: 1 + interrupts: + maxItems: 2 + + interrupt-names: + items: + - const: switch + - const: nic + '#address-cells': const: 1 '#size-cells': const: 1 + ethernet-ports: + type: object + patternProperties: 'reboot@[0-9a-f]+$': $ref: /schemas/power/reset/syscon-reboot.yaml# @@ -41,9 +54,14 @@ patternProperties: 'i2c@[0-9a-f]+$': $ref: /schemas/i2c/realtek,rtl9301-i2c.yaml# + 'mdio-controller@[0-9a-f]+$': + $ref: realtek,rtl9301-mdio.yaml# + required: - compatible - reg + - interrupts + - interrupt-names additionalProperties: false @@ -52,6 +70,9 @@ examples: ethernet-switch@1b000000 { compatible = "realtek,rtl9301-switch", "syscon", "simple-mfd"; reg = <0x1b000000 0x10000>; + interrupt-parent = <&intc>; + interrupts = <23>, <24>; + interrupt-names = "switch", "nic"; #address-cells = <1>; #size-cells = <1>; @@ -110,5 +131,45 @@ examples: }; }; }; + + mdio-controller@ca00 { + compatible = "realtek,rtl9301-mdio"; + reg = <0xca00 0x200>; + #address-cells = <1>; + #size-cells = <0>; + + mdio-bus@0 { + reg = <0>; + #address-cells = <1>; + #size-cells = <0>; + + phy1: ethernet-phy@0 { + reg = <0>; + }; + }; + mdio-bus@1 { + reg = <1>; + #address-cells = <1>; + #size-cells = <0>; + + phy2: ethernet-phy@0 { + reg = <0>; + }; + }; + }; + + ethernet-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + phy-handle = <&phy1>; + }; + port@1 { + reg = <1>; + phy-handle = <&phy2>; + }; + }; }; diff --git a/Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml b/Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml index d37f544ab8aa..39c209249c9c 100644 --- a/Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml +++ b/Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml @@ -36,6 +36,7 @@ properties: - qcom,qcs404-qfprom - qcom,qcs615-qfprom - qcom,qcs8300-qfprom + - qcom,sar2130p-qfprom - qcom,sc7180-qfprom - qcom,sc7280-qfprom - qcom,sc8280xp-qfprom diff --git a/Documentation/devicetree/bindings/regulator/qcom,smd-rpm-regulator.yaml b/Documentation/devicetree/bindings/regulator/qcom,smd-rpm-regulator.yaml index f2fd2df68a9e..b7241ce975b9 100644 --- a/Documentation/devicetree/bindings/regulator/qcom,smd-rpm-regulator.yaml +++ b/Documentation/devicetree/bindings/regulator/qcom,smd-rpm-regulator.yaml @@ -22,7 +22,7 @@ description: Each sub-node is identified using the node's name, with valid values listed for each of the pmics below. - For mp5496, s1, s2 + For mp5496, s1, s2, l2, l5 For pm2250, s1, s2, s3, s4, l1, l2, l3, l4, l5, l6, l7, l8, l9, l10, l11, l12, l13, l14, l15, l16, l17, l18, l19, l20, l21, l22 diff --git a/Documentation/driver-api/infrastructure.rst b/Documentation/driver-api/infrastructure.rst index 3d52dfdfa9fd..35e36fee4238 100644 --- a/Documentation/driver-api/infrastructure.rst +++ b/Documentation/driver-api/infrastructure.rst @@ -41,6 +41,12 @@ Device Drivers Base .. kernel-doc:: drivers/base/class.c :export: +.. kernel-doc:: include/linux/device/faux.h + :internal: + +.. kernel-doc:: drivers/base/faux.c + :export: + .. kernel-doc:: drivers/base/node.c :internal: diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index 5f6f84630b16..36f1152bfac3 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -281,6 +281,9 @@ attribute-sets: processing, if event polling finds events type: uint - + name: xsk-info + attributes: [] + - name: queue attributes: - @@ -298,6 +301,9 @@ attribute-sets: - name: type doc: Queue type as rx, tx. Each queue type defines a separate ID space. + XDP TX queues allocated in the kernel are not linked to NAPIs and + thus not listed. AF_XDP queues will have more information set in + the xsk attribute. type: u32 enum: queue-type - @@ -313,7 +319,11 @@ attribute-sets: doc: io_uring memory provider information. type: nest nested-attributes: io-uring-provider-info - + - + name: xsk + doc: XSK information for this queue, if any. + type: nest + nested-attributes: xsk-info - name: qstats doc: | @@ -461,6 +471,8 @@ attribute-sets: name: tx-needs-csum doc: | Number of packets that required the device to calculate the checksum. + This counter includes the number of GSO wire packets for which device + calculated the L4 checksum. type: uint - name: tx-hw-gso-packets @@ -656,6 +668,7 @@ operations: - ifindex - dmabuf - io-uring + - xsk dump: request: attributes: diff --git a/Documentation/netlink/specs/rt_rule.yaml b/Documentation/netlink/specs/rt_rule.yaml index a9debac3058a..b30c924087fa 100644 --- a/Documentation/netlink/specs/rt_rule.yaml +++ b/Documentation/netlink/specs/rt_rule.yaml @@ -182,6 +182,14 @@ attribute-sets: type: u32 byte-order: big-endian display-hint: hex + - + name: sport-mask + type: u16 + display-hint: hex + - + name: dport-mask + type: u16 + display-hint: hex operations: enum-model: directional @@ -215,6 +223,8 @@ operations: - dscp - flowlabel - flowlabel-mask + - sport-mask + - dport-mask - name: newrule-ntf doc: Notify a rule creation diff --git a/Documentation/networking/j1939.rst b/Documentation/networking/j1939.rst index 544bad175aae..45f02efe3df5 100644 --- a/Documentation/networking/j1939.rst +++ b/Documentation/networking/j1939.rst @@ -66,6 +66,90 @@ the library exclusively, or by the in-kernel system exclusively. J1939 concepts ============== +Data Sent to the J1939 Stack +---------------------------- + +The data buffers sent to the J1939 stack from user space are not CAN frames +themselves. Instead, they are payloads that the J1939 stack converts into +proper CAN frames based on the size of the buffer and the type of transfer. The +size of the buffer influences how the stack processes the data and determines +the internal code path used for the transfer. + +**Handling of Different Buffer Sizes:** + +- **Buffers with a size of 8 bytes or less:** + + - These are handled as simple sessions internally within the stack. + + - The stack converts the buffer directly into a single CAN frame without + fragmentation. + + - This type of transfer does not require an actual client (receiver) on the + receiving side. + +- **Buffers up to 1785 bytes:** + + - These are automatically handled as J1939 Transport Protocol (TP) transfers. + + - Internally, the stack splits the buffer into multiple 8-byte CAN frames. + + - TP transfers can be unicast or broadcast. + + - **Broadcast TP:** Does not require a receiver on the other side and can be + used in broadcast scenarios. + + - **Unicast TP:** Requires an active receiver (client) on the other side to + acknowledge the transfer. + +- **Buffers from 1786 bytes up to 111 MiB:** + + - These are handled as ISO 11783 Extended Transport Protocol (ETP) transfers. + + - ETP transfers are used for larger payloads and are split into multiple CAN + frames internally. + + - **ETP transfers (unicast):** Require a receiver on the other side to + process the incoming data and acknowledge each step of the transfer. + + - ETP transfers cannot be broadcast like TP transfers, and always require a + receiver for operation. + +**Non-Blocking Operation with `MSG_DONTWAIT`:** + +The J1939 stack supports non-blocking operation when used in combination with +the `MSG_DONTWAIT` flag. In this mode, the stack attempts to take as much data +as the available memory for the socket allows. It returns the amount of data +that was successfully taken, and it is the responsibility of user space to +monitor this value and handle partial transfers. + +- If the stack cannot take the entire buffer, it returns the number of bytes + successfully taken, and user space should handle the remainder. + +- **Error handling:** When using `MSG_DONTWAIT`, the user must rely on the + error queue to detect transfer errors. See the **SO_J1939_ERRQUEUE** section + for details on how to subscribe to error notifications. Without the error + queue, there is no other way for user space to be notified of transfer errors + during non-blocking operations. + +**Behavior and Requirements:** + +- **Simple transfers (<= 8 bytes):** Do not require a receiver on the other + side, making them easy to send without needing address claiming or + coordination with a destination. + +- **Unicast TP/ETP:** Requires a receiver on the other side to complete the + transfer. The receiver must acknowledge the transfer for the session to + proceed successfully. + +- **Broadcast TP:** Allows sending data without a receiver, but only works for + TP transfers. ETP cannot be broadcast and always needs a receiving client. + +These different behaviors depend heavily on the size of the buffer provided to +the stack, and the appropriate transport mechanism (TP or ETP) is selected +based on the payload size. The stack automatically manages the fragmentation +and reassembly of large payloads and ensures that the correct CAN frames are +generated and transmitted for each session. + PGN --- @@ -338,6 +422,459 @@ with ``cmsg_level == SOL_J1939 && cmsg_type == SCM_J1939_DEST_ADDR``, } } +setsockopt(2) +^^^^^^^^^^^^^ + +The ``setsockopt(2)`` function is used to configure various socket-level +options for J1939 communication. The following options are supported: + +``SO_J1939_FILTER`` +~~~~~~~~~~~~~~~~~~~ + +The ``SO_J1939_FILTER`` option is essential when the default behavior of +``bind(2)`` and ``connect(2)`` is insufficient for specific use cases. By +default, ``bind(2)`` and ``connect(2)`` allow a socket to be associated with a +single unicast or broadcast address. However, there are scenarios where finer +control over the incoming messages is required, such as filtering by Parameter +Group Number (PGN) rather than by addresses. + +For example, in a system where multiple types of J1939 messages are being +transmitted, a process might only be interested in a subset of those messages, +such as specific PGNs, and not want to receive all messages destined for its +address or broadcast to the bus. + +By applying the ``SO_J1939_FILTER`` option, you can filter messages based on: + +- **Source Address (SA)**: Filter messages coming from specific source + addresses. + +- **Source Name**: Filter messages coming from ECUs with specific NAME + identifiers. + +- **Parameter Group Number (PGN)**: Focus on receiving messages with specific + PGNs, filtering out irrelevant ones. + +This filtering mechanism is particularly useful when: + +- You want to receive a subset of messages based on their PGNs, even if the + address is the same. + +- You need to handle both broadcast and unicast messages but only care about + certain message types or parameters. + +- The ``bind(2)`` and ``connect(2)`` functions only allow binding to a single + address, which might not be sufficient if the process needs to handle multiple + PGNs but does not want to open multiple sockets. + +To remove existing filters, you can pass ``optval == NULL`` or ``optlen == 0`` +to ``setsockopt(2)``. This will clear all currently set filters. If you want to +**update** the set of filters, you must pass the updated filter set to +``setsockopt(2)``, as the new filter set will **replace** the old one entirely. +This behavior ensures that any previous filter configuration is discarded and +only the new set is applied. + +Example of removing all filters: + +.. code-block:: c + + setsockopt(sock, SOL_CAN_J1939, SO_J1939_FILTER, NULL, 0); + +**Maximum number of filters:** The maximum amount of filters that can be +applied using ``SO_J1939_FILTER`` is defined by ``J1939_FILTER_MAX``, which is +set to 512. This means you can configure up to 512 individual filters to match +your specific filtering needs. + +Practical use case: **Monitoring Address Claiming** + +One practical use case is monitoring the J1939 address claiming process by +filtering for specific PGNs related to address claiming. This allows a process +to monitor and handle address claims without processing unrelated messages. + +Example: + +.. code-block:: c + + struct j1939_filter filt[] = { + { + .pgn = J1939_PGN_ADDRESS_CLAIMED, + .pgn_mask = J1939_PGN_PDU1_MAX, + }, { + .pgn = J1939_PGN_REQUEST, + .pgn_mask = J1939_PGN_PDU1_MAX, + }, { + .pgn = J1939_PGN_ADDRESS_COMMANDED, + .pgn_mask = J1939_PGN_MAX, + }, + }; + setsockopt(sock, SOL_CAN_J1939, SO_J1939_FILTER, &filt, sizeof(filt)); + +In this example, the socket will only receive messages with the PGNs related to +address claiming: ``J1939_PGN_ADDRESS_CLAIMED``, ``J1939_PGN_REQUEST``, and +``J1939_PGN_ADDRESS_COMMANDED``. This is particularly useful in scenarios where +you want to monitor and process address claims without being overwhelmed by +other traffic on the J1939 network. + +``SO_J1939_PROMISC`` +~~~~~~~~~~~~~~~~~~~~ + +The ``SO_J1939_PROMISC`` option enables socket-level promiscuous mode. When +this option is enabled, the socket will receive all J1939 traffic, regardless +of any filters set by ``bind()`` or ``connect()``. This is analogous to +enabling promiscuous mode for an Ethernet interface, where all traffic on the +network segment is captured. + +However, **`SO_J1939_FILTER` has a higher priority** compared to +``SO_J1939_PROMISC``. This means that even in promiscuous mode, you can reduce +the number of packets received by applying specific filters with +`SO_J1939_FILTER`. The filters will limit which packets are passed to the +socket, allowing for more refined traffic selection while promiscuous mode is +active. + +The acceptable value size for this option is ``sizeof(int)``, and the value is +only differentiated between `0` and non-zero. A value of `0` disables +promiscuous mode, while any non-zero value enables it. + +This combination can be useful for debugging or monitoring specific types of +traffic while still capturing a broad set of messages. + +Example: + +.. code-block:: c + + int value = 1; + setsockopt(sock, SOL_CAN_J1939, SO_J1939_PROMISC, &value, sizeof(value)); + +In this example, setting ``value`` to any non-zero value (e.g., `1`) enables +promiscuous mode, allowing the socket to receive all J1939 traffic on the +network. + +``SO_BROADCAST`` +~~~~~~~~~~~~~~~~ + +The ``SO_BROADCAST`` option enables the sending and receiving of broadcast +messages. By default, broadcast messages are disabled for J1939 sockets. When +this option is enabled, the socket will be allowed to send and receive +broadcast packets on the J1939 network. + +Due to the nature of the CAN bus as a shared medium, all messages transmitted +on the bus are visible to all participants. In the context of J1939, +broadcasting refers to using a specific destination address field, where the +destination address is set to a value that indicates the message is intended +for all participants (usually a global address such as 0xFF). Enabling the +broadcast option allows the socket to send and receive such broadcast messages. + +The acceptable value size for this option is ``sizeof(int)``, and the value is +only differentiated between `0` and non-zero. A value of `0` disables the +ability to send and receive broadcast messages, while any non-zero value +enables it. + +Example: + +.. code-block:: c + + int value = 1; + setsockopt(sock, SOL_SOCKET, SO_BROADCAST, &value, sizeof(value)); + +In this example, setting ``value`` to any non-zero value (e.g., `1`) enables +the socket to send and receive broadcast messages. + +``SO_J1939_SEND_PRIO`` +~~~~~~~~~~~~~~~~~~~~~~ + +The ``SO_J1939_SEND_PRIO`` option sets the priority of outgoing J1939 messages +for the socket. In J1939, messages can have different priorities, and lower +numerical values indicate higher priority. This option allows the user to +control the priority of messages sent from the socket by adjusting the priority +bits in the CAN identifier. + +The acceptable value **size** for this option is ``sizeof(int)``, and the value +is expected to be in the range of 0 to 7, where `0` is the highest priority, +and `7` is the lowest. By default, the priority is set to `6` if this option is +not explicitly configured. + +Note that the priority values `0` and `1` can only be set if the process has +the `CAP_NET_ADMIN` capability. These are reserved for high-priority traffic +and require administrative privileges. + +Example: + +.. code-block:: c + + int prio = 3; // Priority value between 0 (highest) and 7 (lowest) + setsockopt(sock, SOL_CAN_J1939, SO_J1939_SEND_PRIO, &prio, sizeof(prio)); + +In this example, the priority is set to `3`, meaning the outgoing messages will +be sent with a moderate priority level. + +``SO_J1939_ERRQUEUE`` +~~~~~~~~~~~~~~~~~~~~~ + +The ``SO_J1939_ERRQUEUE`` option enables the socket to receive error messages +from the error queue, providing diagnostic information about transmission +failures, protocol violations, or other issues that occur during J1939 +communication. Once this option is set, user space is required to handle +``MSG_ERRQUEUE`` messages. + +Setting ``SO_J1939_ERRQUEUE`` to ``0`` will purge any currently present error +messages in the error queue. When enabled, error messages can be retrieved +using the ``recvmsg(2)`` system call. + +When subscribing to the error queue, the following error events can be +accessed: + +- **``J1939_EE_INFO_TX_ABORT``**: Transmission abort errors. +- **``J1939_EE_INFO_RX_RTS``**: Reception of RTS (Request to Send) control + frames. +- **``J1939_EE_INFO_RX_DPO``**: Reception of data packets with Data Page Offset + (DPO). +- **``J1939_EE_INFO_RX_ABORT``**: Reception abort errors. + +The error queue can be used to correlate errors with specific message transfer +sessions using the session ID (``tskey``). The session ID is assigned via the +``SOF_TIMESTAMPING_OPT_ID`` flag, which is set by enabling the +``SO_TIMESTAMPING`` option. + +If ``SO_J1939_ERRQUEUE`` is activated, the user is required to pull messages +from the error queue, meaning that using plain ``recv(2)`` is not sufficient +anymore. The user must use ``recvmsg(2)`` with appropriate flags to handle +error messages. Failure to do so can result in the socket becoming blocked with +unprocessed error messages in the queue. + +It is **recommended** that ``SO_J1939_ERRQUEUE`` be used in combination with +``SO_TIMESTAMPING`` in most cases. This enables proper error handling along +with session tracking and timestamping, providing a more detailed analysis of +message transfers and errors. + +The acceptable value **size** for this option is ``sizeof(int)``, and the value +is only differentiated between ``0`` and non-zero. A value of ``0`` disables +error queue reception and purges any existing error messages, while any +non-zero value enables it. + +Example: + +.. code-block:: c + + int enable = 1; // Enable error queue reception + setsockopt(sock, SOL_CAN_J1939, SO_J1939_ERRQUEUE, &enable, sizeof(enable)); + + // Enable timestamping with session tracking via tskey + int timestamping = SOF_TIMESTAMPING_OPT_ID | SOF_TIMESTAMPING_TX_ACK | + SOF_TIMESTAMPING_TX_SCHED | + SOF_TIMESTAMPING_RX_SOFTWARE | SOF_TIMESTAMPING_OPT_CMSG; + setsockopt(sock, SOL_SOCKET, SO_TIMESTAMPING, ×tamping, + sizeof(timestamping)); + +When enabled, error messages can be retrieved using ``recvmsg(2)``. By +combining ``SO_J1939_ERRQUEUE`` with ``SO_TIMESTAMPING`` (with +``SOF_TIMESTAMPING_OPT_ID`` and ``SOF_TIMESTAMPING_OPT_CMSG`` enabled), the +user can track message transfers, retrieve precise timestamps, and correlate +errors with specific sessions. + +For more information on enabling timestamps and session tracking, refer to the +`SO_TIMESTAMPING` section. + +``SO_TIMESTAMPING`` +~~~~~~~~~~~~~~~~~~~ + +The ``SO_TIMESTAMPING`` option allows the socket to receive timestamps for +various events related to message transmissions and receptions in J1939. This +option is often used in combination with ``SO_J1939_ERRQUEUE`` to provide +detailed diagnostic information, session tracking, and precise timing data for +message transfers. + +In J1939, all payloads provided by user space, regardless of size, are +processed by the kernel as **sessions**. This includes both single-frame +messages (up to 8 bytes) and multi-frame protocols such as the Transport +Protocol (TP) and Extended Transport Protocol (ETP). Even for small, +single-frame messages, the kernel creates a session to manage the transmission +and reception. The concept of sessions allows the kernel to manage various +aspects of the protocol, such as reassembling multi-frame messages and tracking +the status of transmissions. + +When receiving extended error messages from the error queue, the error +information is delivered through a `struct sock_extended_err`, accessible via +the control message (``cmsg``) retrieved using the ``recvmsg(2)`` system call. + +There are two typical origins for the extended error messages in J1939: + +1. ``serr->ee_origin == SO_EE_ORIGIN_TIMESTAMPING``: + + In this case, the `serr->ee_info` field will contain one of the following + timestamp types: + + - ``SCM_TSTAMP_SCHED``: This timestamp is valid for Extended Transport + Protocol (ETP) transfers and simple transfers (8 bytes or less). It + indicates when a message or set of frames has been scheduled for + transmission. + + - For simple transfers (8 bytes or less), it marks the point when the + message is queued and ready to be sent onto the CAN bus. + + - For ETP transfers, it is sent after receiving a CTS (Clear to Send) + frame on the sender side, indicating that a new set of frames has been + scheduled for transmission. + + - The Transport Protocol (TP) case is currently not implemented for this + timestamp. + + - On the receiver side, the counterpart to this event for ETP is + represented by the ``J1939_EE_INFO_RX_DPO`` message, which indicates the + reception of a Data Page Offset (DPO) control frame. + + - ``SCM_TSTAMP_ACK``: This timestamp indicates the acknowledgment of the + message or session. + + - For simple transfers (8 bytes or less), it marks when the message has + been sent and an echo confirmation has been received from the CAN + controller, indicating that the frame was transmitted onto the bus. + + - For multi-frame transfers (TP or ETP), it signifies that the entire + session has been acknowledged, typically after receiving the End of + Message Acknowledgment (EOMA) packet. + +2. ``serr->ee_origin == SO_EE_ORIGIN_LOCAL``: + + In this case, the `serr->ee_info` field will contain one of the following + J1939 stack-specific message types: + + - ``J1939_EE_INFO_TX_ABORT``: This message indicates that the transmission + of a message or session was aborted. The cause of the abort can come from + various sources: + + - **CAN stack failure**: The J1939 stack was unable to pass the frame to + the CAN framework for transmission. + + - **Echo failure**: The J1939 stack did not receive an echo confirmation + from the CAN controller, meaning the frame may not have been successfully + transmitted to the CAN bus. + + - **Protocol-level issues**: For multi-frame transfers (TP/ETP), this + could include protocol-related errors, such as an abort signaled by the + receiver or a timeout at the protocol level, which causes the session to + terminate prematurely. + + - The corresponding error code is stored in ``serr->ee_data`` + (``session->err`` on kernel side), providing additional details about + the specific reason for the abort. + + - ``J1939_EE_INFO_RX_RTS``: This message indicates that the J1939 stack has + received a Request to Send (RTS) control frame, signaling the start of a + multi-frame transfer using the Transport Protocol (TP) or Extended + Transport Protocol (ETP). + + - It informs the receiver that the sender is ready to transmit a + multi-frame message and includes details about the total message size + and the number of frames to be sent. + + - Statistics such as ``J1939_NLA_TOTAL_SIZE``, ``J1939_NLA_PGN``, + ``J1939_NLA_SRC_NAME``, and ``J1939_NLA_DEST_NAME`` are provided along + with the ``J1939_EE_INFO_RX_RTS`` message, giving detailed information + about the incoming transfer. + + - ``J1939_EE_INFO_RX_DPO``: This message indicates that the J1939 stack has + received a Data Page Offset (DPO) control frame, which is part of the + Extended Transport Protocol (ETP). + + - The DPO frame signals the continuation of an ETP multi-frame message by + indicating the offset position in the data being transferred. It helps + the receiver manage large data sets by identifying which portion of the + message is being received. + + - It is typically paired with a corresponding ``SCM_TSTAMP_SCHED`` event + on the sender side, which indicates when the next set of frames is + scheduled for transmission. + + - This event includes statistics such as ``J1939_NLA_BYTES_ACKED``, which + tracks the number of bytes acknowledged up to that point in the session. + + - ``J1939_EE_INFO_RX_ABORT``: This message indicates that the reception of a + multi-frame message (Transport Protocol or Extended Transport Protocol) has + been aborted. + + - The abort can be triggered by protocol-level errors such as timeouts, an + unexpected frame, or a specific abort request from the sender. + + - This message signals that the receiver cannot continue processing the + transfer, and the session is terminated. + + - The corresponding error code is stored in ``serr->ee_data`` + (``session->err`` on kernel side ), providing further details about the + reason for the abort, such as protocol violations or timeouts. + + - After receiving this message, the receiver discards the partially received + frames, and the multi-frame session is considered incomplete. + +In both cases, if ``SOF_TIMESTAMPING_OPT_ID`` is enabled, ``serr->ee_data`` +will be set to the session’s unique identifier (``session->tskey``). This +allows user space to track message transfers by their session identifier across +multiple frames or stages. + +In all other cases, ``serr->ee_errno`` will be set to ``ENOMSG``, except for +the ``J1939_EE_INFO_TX_ABORT`` and ``J1939_EE_INFO_RX_ABORT`` cases, where the +kernel sets ``serr->ee_data`` to the error stored in ``session->err``. All +protocol-specific errors are converted to standard kernel error values and +stored in ``session->err``. These error values are unified across system calls +and ``serr->ee_errno``. Some of the known error values are described in the +`Error Codes in the J1939 Stack` section. + +When the `J1939_EE_INFO_RX_RTS` message is provided, it will include the +following statistics for multi-frame messages (TP and ETP): + + - ``J1939_NLA_TOTAL_SIZE``: Total size of the message in the session. + - ``J1939_NLA_PGN``: Parameter Group Number (PGN) identifying the message type. + - ``J1939_NLA_SRC_NAME``: 64-bit name of the source ECU. + - ``J1939_NLA_DEST_NAME``: 64-bit name of the destination ECU. + - ``J1939_NLA_SRC_ADDR``: 8-bit source address of the sending ECU. + - ``J1939_NLA_DEST_ADDR``: 8-bit destination address of the receiving ECU. + +- For other messages (including single-frame messages), only the following + statistic is included: + + - ``J1939_NLA_BYTES_ACKED``: Number of bytes successfully acknowledged in the + session. + +The key flags for ``SO_TIMESTAMPING`` include: + +- ``SOF_TIMESTAMPING_OPT_ID``: Enables the use of a unique session identifier + (``tskey``) for each transfer. This identifier helps track message transfers + and errors as distinct sessions in user space. When this option is enabled, + ``serr->ee_data`` will be set to ``session->tskey``. + +- ``SOF_TIMESTAMPING_OPT_CMSG``: Sends timestamp information through control + messages (``struct scm_timestamping``), allowing the application to retrieve + timestamps alongside the data. + +- ``SOF_TIMESTAMPING_TX_SCHED``: Provides the timestamp for when a message is + scheduled for transmission (``SCM_TSTAMP_SCHED``). + +- ``SOF_TIMESTAMPING_TX_ACK``: Provides the timestamp for when a message + transmission is fully acknowledged (``SCM_TSTAMP_ACK``). + +- ``SOF_TIMESTAMPING_RX_SOFTWARE``: Provides timestamps for reception-related + events (e.g., ``J1939_EE_INFO_RX_RTS``, ``J1939_EE_INFO_RX_DPO``, + ``J1939_EE_INFO_RX_ABORT``). + +These flags enable detailed monitoring of message lifecycles, including +transmission scheduling, acknowledgments, reception timestamps, and gathering +detailed statistics about the communication session, especially for multi-frame +payloads like TP and ETP. + +Example: + +.. code-block:: c + + // Enable timestamping with various options, including session tracking and + // statistics + int sock_opt = SOF_TIMESTAMPING_OPT_CMSG | + SOF_TIMESTAMPING_TX_ACK | + SOF_TIMESTAMPING_TX_SCHED | + SOF_TIMESTAMPING_OPT_ID | + SOF_TIMESTAMPING_RX_SOFTWARE; + + setsockopt(sock, SOL_SOCKET, SO_TIMESTAMPING, &sock_opt, sizeof(sock_opt)); + + + Dynamic Addressing ------------------ @@ -458,3 +995,141 @@ Send: }; sendto(sock, dat, sizeof(dat), 0, (const struct sockaddr *)&saddr, sizeof(saddr)); + + +Error Codes in the J1939 Stack +------------------------------ + +This section lists all potential kernel error codes that can be exposed to user +space when interacting with the J1939 stack. It includes both standard error +codes and those derived from protocol-specific abort codes. + +- ``EAGAIN``: Operation would block; retry may succeed. One common reason is + that an active TP or ETP session exists, and an attempt was made to start a + new overlapping TP or ETP session between the same peers. + +- ``ENETDOWN``: Network is down. This occurs when the CAN interface is switched + to the "down" state. + +- ``ENOBUFS``: No buffer space available. This error occurs when the CAN + interface's transmit (TX) queue is full, and no more messages can be queued. + +- ``EOVERFLOW``: Value too large for defined data type. In J1939, this can + happen if the requested data lies outside of the queued buffer. For example, + if a CTS (Clear to Send) requests an offset not available in the kernel buffer + because user space did not provide enough data. + +- ``EBUSY``: Device or resource is busy. For example, this occurs if an + identical session is already active and the stack is unable to recover from + the condition. + +- ``EACCES``: Permission denied. This error can occur, for example, when + attempting to send broadcast messages, but the socket is not configured with + ``SO_BROADCAST``. + +- ``EADDRNOTAVAIL``: Address not available. This error occurs in cases such as: + + - When attempting to use ``getsockname(2)`` to retrieve the peer's address, + but the socket is not connected. + + - When trying to send data to or from a NAME, but address claiming for the + NAME was not performed or detected by the stack. + +- ``EBADFD``: File descriptor in bad state. This error can occur if: + + - Attempting to send data to an unbound socket. + + - The socket is bound but has no source name, and the source address is + ``J1939_NO_ADDR``. + + - The ``can_ifindex`` is incorrect. + +- ``EFAULT``: Bad address. Occurs mostly when the stack can't copy from or to a + sockptr, when there is insufficient data from user space, or when the buffer + provided by user space is not large enough for the requested data. + +- ``EINTR``: A signal occurred before any data was transmitted; see ``signal(7)``. + +- ``EINVAL``: Invalid argument passed. For example: + + - ``msg->msg_namelen`` is less than ``J1939_MIN_NAMELEN``. + + - ``addr->can_family`` is not equal to ``AF_CAN``. + + - An incorrect PGN was provided. + +- ``ENODEV``: No such device. This happens when the CAN network device cannot + be found for the provided ``can_ifindex`` or if ``can_ifindex`` is 0. + +- ``ENOMEM``: Out of memory. Typically related to issues with memory allocation + in the stack. + +- ``ENOPROTOOPT``: Protocol not available. This can occur when using + ``getsockopt(2)`` or ``setsockopt(2)`` if the requested socket option is not + available. + +- ``EDESTADDRREQ``: Destination address required. This error occurs: + + - In the case of ``connect(2)``, if the ``struct sockaddr *uaddr`` is ``NULL``. + + - In the case of ``send*(2)``, if there is an attempt to send an ETP message + to a broadcast address. + +- ``EDOM``: Argument out of domain. This error may happen if attempting to send + a TP or ETP message to a PGN that is reserved for control PGNs for TP or ETP + operations. + +- ``EIO``: I/O error. This can occur if the amount of data provided to the + socket for a TP or ETP session does not match the announced amount of data for + the session. + +- ``ENOENT``: No such file or directory. This can happen when the stack + attempts to transfer CTS or EOMA but cannot find a matching receiving socket + anymore. + +- ``ENOIOCTLCMD``: No ioctls are available for the socket layer. + +- ``EPERM``: Operation not permitted. For example, this can occur if a + requested action requires ``CAP_NET_ADMIN`` privileges. + +- ``ENETUNREACH``: Network unreachable. Most likely, this occurs when frames + cannot be transmitted to the CAN bus. + +- ``ETIME``: Timer expired. This can happen if a timeout occurs while + attempting to send a simple message, for example, when an echo message from + the controller is not received. + +- ``EPROTO``: Protocol error. + + - Used for various protocol-level errors in J1939, including: + + - Duplicate sequence number. + + - Unexpected EDPO or ECTS packet. + + - Invalid PGN or offset in EDPO/ECTS. + + - Number of EDPO packets exceeded CTS allowance. + + - Any other protocol-level error. + +- ``EMSGSIZE``: Message too long. + +- ``ENOMSG``: No message available. + +- ``EALREADY``: The ECU is already engaged in one or more connection-managed + sessions and cannot support another. + +- ``EHOSTUNREACH``: A timeout occurred, and the session was aborted. + +- ``EBADMSG``: CTS (Clear to Send) messages were received during an active data + transfer, causing an abort. + +- ``ENOTRECOVERABLE``: The maximum retransmission request limit was reached, + and the session cannot recover. + +- ``ENOTCONN``: An unexpected data transfer packet was received. + +- ``EILSEQ``: A bad sequence number was received, and the software could not + recover. + diff --git a/Documentation/networking/napi.rst b/Documentation/networking/napi.rst index f970a2be271a..d0e3953cae6a 100644 --- a/Documentation/networking/napi.rst +++ b/Documentation/networking/napi.rst @@ -171,12 +171,43 @@ a channel as an IRQ/NAPI which services queues of a given type. For example, a configuration of 1 ``rx``, 1 ``tx`` and 1 ``combined`` channel is expected to utilize 3 interrupts, 2 Rx and 2 Tx queues. +Persistent NAPI config +---------------------- + +Drivers often allocate and free NAPI instances dynamically. This leads to loss +of NAPI-related user configuration each time NAPI instances are reallocated. +The netif_napi_add_config() API prevents this loss of configuration by +associating each NAPI instance with a persistent NAPI configuration based on +a driver defined index value, like a queue number. + +Using this API allows for persistent NAPI IDs (among other settings), which can +be beneficial to userspace programs using ``SO_INCOMING_NAPI_ID``. See the +sections below for other NAPI configuration settings. + +Drivers should try to use netif_napi_add_config() whenever possible. + User API ======== User interactions with NAPI depend on NAPI instance ID. The instance IDs are only visible to the user thru the ``SO_INCOMING_NAPI_ID`` socket option. -It's not currently possible to query IDs used by a given device. + +Users can query NAPI IDs for a device or device queue using netlink. This can +be done programmatically in a user application or by using a script included in +the kernel source tree: ``tools/net/ynl/pyynl/cli.py``. + +For example, using the script to dump all of the queues for a device (which +will reveal each queue's NAPI ID): + +.. code-block:: bash + + $ kernel-source/tools/net/ynl/pyynl/cli.py \ + --spec Documentation/netlink/specs/netdev.yaml \ + --dump queue-get \ + --json='{"ifindex": 2}' + +See ``Documentation/netlink/specs/netdev.yaml`` for more details on +available operations and attributes. Software IRQ coalescing ----------------------- diff --git a/Documentation/process/embargoed-hardware-issues.rst b/Documentation/process/embargoed-hardware-issues.rst index daebce49cfdf..0e19d2f0d6bb 100644 --- a/Documentation/process/embargoed-hardware-issues.rst +++ b/Documentation/process/embargoed-hardware-issues.rst @@ -308,7 +308,7 @@ an involved disclosed party. The current ambassadors list: Google Kees Cook <keescook@chromium.org> - LLVM Nick Desaulniers <ndesaulniers@google.com> + LLVM Nick Desaulniers <nick.desaulniers+lkml@gmail.com> ============= ======================================================== If you want your organization to be added to the ambassadors list, please diff --git a/Documentation/translations/sp_SP/process/embargoed-hardware-issues.rst b/Documentation/translations/sp_SP/process/embargoed-hardware-issues.rst index 7d4d694967c7..9d444b9c46d3 100644 --- a/Documentation/translations/sp_SP/process/embargoed-hardware-issues.rst +++ b/Documentation/translations/sp_SP/process/embargoed-hardware-issues.rst @@ -287,7 +287,7 @@ revelada involucrada. La lista de embajadores actuales: Google Kees Cook <keescook@chromium.org> - LLVM Nick Desaulniers <ndesaulniers@google.com> + LLVM Nick Desaulniers <nick.desaulniers+lkml@gmail.com> ============= ======================================================== Si quiere que su organización se añada a la lista de embajadores, por diff --git a/MAINTAINERS b/MAINTAINERS index de81a3d68396..b0cd54818bb3 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3858,13 +3858,6 @@ W: https://ez.analog.com/linux-software-drivers F: Documentation/devicetree/bindings/pwm/adi,axi-pwmgen.yaml F: drivers/pwm/pwm-axi-pwmgen.c -AXXIA I2C CONTROLLER -M: Krzysztof Adamski <krzysztof.adamski@nokia.com> -L: linux-i2c@vger.kernel.org -S: Maintained -F: Documentation/devicetree/bindings/i2c/i2c-axxia.txt -F: drivers/i2c/busses/i2c-axxia.c - AZ6007 DVB DRIVER M: Mauro Carvalho Chehab <mchehab@kernel.org> L: linux-media@vger.kernel.org @@ -5662,7 +5655,7 @@ F: .clang-format CLANG/LLVM BUILD SUPPORT M: Nathan Chancellor <nathan@kernel.org> -R: Nick Desaulniers <ndesaulniers@google.com> +R: Nick Desaulniers <nick.desaulniers+lkml@gmail.com> R: Bill Wendling <morbo@google.com> R: Justin Stitt <justinstitt@google.com> L: llvm@lists.linux.dev @@ -7115,8 +7108,10 @@ F: rust/kernel/device.rs F: rust/kernel/device_id.rs F: rust/kernel/devres.rs F: rust/kernel/driver.rs +F: rust/kernel/faux.rs F: rust/kernel/platform.rs F: samples/rust/rust_driver_platform.rs +F: samples/rust/rust_driver_faux.rs DRIVERS FOR OMAP ADAPTIVE VOLTAGE SCALING (AVS) M: Nishanth Menon <nm@ti.com> @@ -9834,8 +9829,7 @@ F: drivers/input/touchscreen/goodix* GOOGLE ETHERNET DRIVERS M: Jeroen de Borst <jeroendb@google.com> -M: Praveen Kaligineedi <pkaligineedi@google.com> -R: Shailend Chand <shailend@google.com> +M: Harshitha Ramamurthy <hramamurthy@google.com> L: netdev@vger.kernel.org S: Maintained F: Documentation/networking/device_drivers/ethernet/google/gve.rst @@ -10821,7 +10815,7 @@ S: Odd Fixes F: drivers/tty/hvc/ I2C ACPI SUPPORT -M: Mika Westerberg <mika.westerberg@linux.intel.com> +M: Mika Westerberg <westeri@kernel.org> L: linux-i2c@vger.kernel.org L: linux-acpi@vger.kernel.org S: Maintained @@ -16477,6 +16471,12 @@ F: net/ethtool/cabletest.c F: tools/testing/selftests/drivers/net/*/ethtool* K: cable_test +NETWORKING [ETHTOOL MAC MERGE] +M: Vladimir Oltean <vladimir.oltean@nxp.com> +F: net/ethtool/mm.c +F: tools/testing/selftests/drivers/net/hw/ethtool_mm.sh +K: ethtool_mm + NETWORKING [GENERAL] M: "David S. Miller" <davem@davemloft.net> M: Eric Dumazet <edumazet@google.com> @@ -19508,6 +19508,15 @@ L: dmaengine@vger.kernel.org S: Supported F: drivers/dma/qcom/hidma* +QUALCOMM I2C QCOM GENI DRIVER +M: Mukesh Kumar Savaliya <quic_msavaliy@quicinc.com> +M: Viken Dadhaniya <quic_vdadhani@quicinc.com> +L: linux-i2c@vger.kernel.org +L: linux-arm-msm@vger.kernel.org +S: Maintained +F: Documentation/devicetree/bindings/i2c/qcom,i2c-geni-qcom.yaml +F: drivers/i2c/busses/i2c-qcom-geni.c + QUALCOMM I2C CCI DRIVER M: Loic Poulain <loic.poulain@linaro.org> M: Robert Foss <rfoss@kernel.org> @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 14 SUBLEVEL = 0 -EXTRAVERSION = -rc2 +EXTRAVERSION = -rc3 NAME = Baby Opossum Posse # *DOCUMENTATION* @@ -1120,8 +1120,8 @@ LDFLAGS_vmlinux += --orphan-handling=$(CONFIG_LD_ORPHAN_WARN_LEVEL) endif # Align the bit size of userspace programs with the kernel -KBUILD_USERCFLAGS += $(filter -m32 -m64 --target=%, $(KBUILD_CFLAGS)) -KBUILD_USERLDFLAGS += $(filter -m32 -m64 --target=%, $(KBUILD_CFLAGS)) +KBUILD_USERCFLAGS += $(filter -m32 -m64 --target=%, $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS)) +KBUILD_USERLDFLAGS += $(filter -m32 -m64 --target=%, $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS)) # make the checker run with the right architecture CHECKFLAGS += --arch=$(ARCH) @@ -1421,18 +1421,13 @@ ifneq ($(wildcard $(resolve_btfids_O)),) $(Q)$(MAKE) -sC $(srctree)/tools/bpf/resolve_btfids O=$(resolve_btfids_O) clean endif -# Clear a bunch of variables before executing the submake -ifeq ($(quiet),silent_) -tools_silent=s -endif - tools/: FORCE $(Q)mkdir -p $(objtree)/tools - $(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(tools_silent) $(filter --j% -j,$(MAKEFLAGS))" O=$(abspath $(objtree)) subdir=tools -C $(srctree)/tools/ + $(Q)$(MAKE) LDFLAGS= O=$(abspath $(objtree)) subdir=tools -C $(srctree)/tools/ tools/%: FORCE $(Q)mkdir -p $(objtree)/tools - $(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(tools_silent) $(filter --j% -j,$(MAKEFLAGS))" O=$(abspath $(objtree)) subdir=tools -C $(srctree)/tools/ $* + $(Q)$(MAKE) LDFLAGS= O=$(abspath $(objtree)) subdir=tools -C $(srctree)/tools/ $* # --------------------------------------------------------------------------- # Kernel selftest diff --git a/arch/alpha/include/asm/hwrpb.h b/arch/alpha/include/asm/hwrpb.h index fc76f36265ad..db831cf8de10 100644 --- a/arch/alpha/include/asm/hwrpb.h +++ b/arch/alpha/include/asm/hwrpb.h @@ -135,7 +135,7 @@ struct crb_struct { /* virtual->physical map */ unsigned long map_entries; unsigned long map_pages; - struct vf_map_struct map[1]; + struct vf_map_struct map[]; }; struct memclust_struct { diff --git a/arch/alpha/include/uapi/asm/ptrace.h b/arch/alpha/include/uapi/asm/ptrace.h index 5ca45934fcbb..72ed913a910f 100644 --- a/arch/alpha/include/uapi/asm/ptrace.h +++ b/arch/alpha/include/uapi/asm/ptrace.h @@ -42,6 +42,8 @@ struct pt_regs { unsigned long trap_a0; unsigned long trap_a1; unsigned long trap_a2; +/* This makes the stack 16-byte aligned as GCC expects */ + unsigned long __pad0; /* These are saved by PAL-code: */ unsigned long ps; unsigned long pc; diff --git a/arch/alpha/kernel/asm-offsets.c b/arch/alpha/kernel/asm-offsets.c index 4cfeae42c79a..e9dad60b147f 100644 --- a/arch/alpha/kernel/asm-offsets.c +++ b/arch/alpha/kernel/asm-offsets.c @@ -19,9 +19,13 @@ static void __used foo(void) DEFINE(TI_STATUS, offsetof(struct thread_info, status)); BLANK(); + DEFINE(SP_OFF, offsetof(struct pt_regs, ps)); DEFINE(SIZEOF_PT_REGS, sizeof(struct pt_regs)); BLANK(); + DEFINE(SWITCH_STACK_SIZE, sizeof(struct switch_stack)); + BLANK(); + DEFINE(HAE_CACHE, offsetof(struct alpha_machine_vector, hae_cache)); DEFINE(HAE_REG, offsetof(struct alpha_machine_vector, hae_register)); } diff --git a/arch/alpha/kernel/entry.S b/arch/alpha/kernel/entry.S index dd26062d75b3..f4d41b4538c2 100644 --- a/arch/alpha/kernel/entry.S +++ b/arch/alpha/kernel/entry.S @@ -15,10 +15,6 @@ .set noat .cfi_sections .debug_frame -/* Stack offsets. */ -#define SP_OFF 184 -#define SWITCH_STACK_SIZE 64 - .macro CFI_START_OSF_FRAME func .align 4 .globl \func @@ -198,8 +194,8 @@ CFI_END_OSF_FRAME entArith CFI_START_OSF_FRAME entMM SAVE_ALL /* save $9 - $15 so the inline exception code can manipulate them. */ - subq $sp, 56, $sp - .cfi_adjust_cfa_offset 56 + subq $sp, 64, $sp + .cfi_adjust_cfa_offset 64 stq $9, 0($sp) stq $10, 8($sp) stq $11, 16($sp) @@ -214,7 +210,7 @@ CFI_START_OSF_FRAME entMM .cfi_rel_offset $13, 32 .cfi_rel_offset $14, 40 .cfi_rel_offset $15, 48 - addq $sp, 56, $19 + addq $sp, 64, $19 /* handle the fault */ lda $8, 0x3fff bic $sp, $8, $8 @@ -227,7 +223,7 @@ CFI_START_OSF_FRAME entMM ldq $13, 32($sp) ldq $14, 40($sp) ldq $15, 48($sp) - addq $sp, 56, $sp + addq $sp, 64, $sp .cfi_restore $9 .cfi_restore $10 .cfi_restore $11 @@ -235,7 +231,7 @@ CFI_START_OSF_FRAME entMM .cfi_restore $13 .cfi_restore $14 .cfi_restore $15 - .cfi_adjust_cfa_offset -56 + .cfi_adjust_cfa_offset -64 /* finish up the syscall as normal. */ br ret_from_sys_call CFI_END_OSF_FRAME entMM @@ -382,8 +378,8 @@ entUnaUser: .cfi_restore $0 .cfi_adjust_cfa_offset -256 SAVE_ALL /* setup normal kernel stack */ - lda $sp, -56($sp) - .cfi_adjust_cfa_offset 56 + lda $sp, -64($sp) + .cfi_adjust_cfa_offset 64 stq $9, 0($sp) stq $10, 8($sp) stq $11, 16($sp) @@ -399,7 +395,7 @@ entUnaUser: .cfi_rel_offset $14, 40 .cfi_rel_offset $15, 48 lda $8, 0x3fff - addq $sp, 56, $19 + addq $sp, 64, $19 bic $sp, $8, $8 jsr $26, do_entUnaUser ldq $9, 0($sp) @@ -409,7 +405,7 @@ entUnaUser: ldq $13, 32($sp) ldq $14, 40($sp) ldq $15, 48($sp) - lda $sp, 56($sp) + lda $sp, 64($sp) .cfi_restore $9 .cfi_restore $10 .cfi_restore $11 @@ -417,7 +413,7 @@ entUnaUser: .cfi_restore $13 .cfi_restore $14 .cfi_restore $15 - .cfi_adjust_cfa_offset -56 + .cfi_adjust_cfa_offset -64 br ret_from_sys_call CFI_END_OSF_FRAME entUna diff --git a/arch/alpha/kernel/pci_iommu.c b/arch/alpha/kernel/pci_iommu.c index 681f56089d9c..dc91de50f906 100644 --- a/arch/alpha/kernel/pci_iommu.c +++ b/arch/alpha/kernel/pci_iommu.c @@ -13,6 +13,7 @@ #include <linux/log2.h> #include <linux/dma-map-ops.h> #include <linux/iommu-helper.h> +#include <linux/string_choices.h> #include <asm/io.h> #include <asm/hwrpb.h> @@ -212,7 +213,7 @@ static int pci_dac_dma_supported(struct pci_dev *dev, u64 mask) /* If both conditions above are met, we are fine. */ DBGA("pci_dac_dma_supported %s from %ps\n", - ok ? "yes" : "no", __builtin_return_address(0)); + str_yes_no(ok), __builtin_return_address(0)); return ok; } diff --git a/arch/alpha/kernel/traps.c b/arch/alpha/kernel/traps.c index a9a38c80c4a7..7004397937cf 100644 --- a/arch/alpha/kernel/traps.c +++ b/arch/alpha/kernel/traps.c @@ -649,7 +649,7 @@ s_reg_to_mem (unsigned long s_reg) static int unauser_reg_offsets[32] = { R(r0), R(r1), R(r2), R(r3), R(r4), R(r5), R(r6), R(r7), R(r8), /* r9 ... r15 are stored in front of regs. */ - -56, -48, -40, -32, -24, -16, -8, + -64, -56, -48, -40, -32, -24, -16, /* padding at -8 */ R(r16), R(r17), R(r18), R(r19), R(r20), R(r21), R(r22), R(r23), R(r24), R(r25), R(r26), R(r27), R(r28), R(gp), diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c index 8c9850437e67..a9816bbc9f34 100644 --- a/arch/alpha/mm/fault.c +++ b/arch/alpha/mm/fault.c @@ -78,8 +78,8 @@ __load_new_mm_context(struct mm_struct *next_mm) /* Macro for exception fixup code to access integer registers. */ #define dpf_reg(r) \ - (((unsigned long *)regs)[(r) <= 8 ? (r) : (r) <= 15 ? (r)-16 : \ - (r) <= 18 ? (r)+10 : (r)-10]) + (((unsigned long *)regs)[(r) <= 8 ? (r) : (r) <= 15 ? (r)-17 : \ + (r) <= 18 ? (r)+11 : (r)-10]) asmlinkage void do_page_fault(unsigned long address, unsigned long mmcsr, diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index fcdd0ed3eca8..940343beb3d4 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -225,7 +225,6 @@ config ARM64 select HAVE_FUNCTION_ERROR_INJECTION select HAVE_FUNCTION_GRAPH_FREGS select HAVE_FUNCTION_GRAPH_TRACER - select HAVE_FUNCTION_GRAPH_RETVAL select HAVE_GCC_PLUGINS select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && \ HW_PERF_EVENTS && HAVE_PERF_EVENTS_NMI diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 358c68565bfd..2b25d671365f 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -48,7 +48,11 @@ KBUILD_CFLAGS += $(CC_FLAGS_NO_FPU) \ KBUILD_CFLAGS += $(call cc-disable-warning, psabi) KBUILD_AFLAGS += $(compat_vdso) +ifeq ($(call test-ge, $(CONFIG_RUSTC_VERSION), 108500),y) +KBUILD_RUSTFLAGS += --target=aarch64-unknown-none-softfloat +else KBUILD_RUSTFLAGS += --target=aarch64-unknown-none -Ctarget-feature="-neon" +endif KBUILD_CFLAGS += $(call cc-option,-mabi=lp64) KBUILD_AFLAGS += $(call cc-option,-mabi=lp64) diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 47f2cf408eed..78ec1ef2cfe8 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -605,48 +605,6 @@ static __always_inline void kvm_incr_pc(struct kvm_vcpu *vcpu) __cpacr_to_cptr_set(clr, set));\ } while (0) -static __always_inline void kvm_write_cptr_el2(u64 val) -{ - if (has_vhe() || has_hvhe()) - write_sysreg(val, cpacr_el1); - else - write_sysreg(val, cptr_el2); -} - -/* Resets the value of cptr_el2 when returning to the host. */ -static __always_inline void __kvm_reset_cptr_el2(struct kvm *kvm) -{ - u64 val; - - if (has_vhe()) { - val = (CPACR_EL1_FPEN | CPACR_EL1_ZEN_EL1EN); - if (cpus_have_final_cap(ARM64_SME)) - val |= CPACR_EL1_SMEN_EL1EN; - } else if (has_hvhe()) { - val = CPACR_EL1_FPEN; - - if (!kvm_has_sve(kvm) || !guest_owns_fp_regs()) - val |= CPACR_EL1_ZEN; - if (cpus_have_final_cap(ARM64_SME)) - val |= CPACR_EL1_SMEN; - } else { - val = CPTR_NVHE_EL2_RES1; - - if (kvm_has_sve(kvm) && guest_owns_fp_regs()) - val |= CPTR_EL2_TZ; - if (!cpus_have_final_cap(ARM64_SME)) - val |= CPTR_EL2_TSM; - } - - kvm_write_cptr_el2(val); -} - -#ifdef __KVM_NVHE_HYPERVISOR__ -#define kvm_reset_cptr_el2(v) __kvm_reset_cptr_el2(kern_hyp_va((v)->kvm)) -#else -#define kvm_reset_cptr_el2(v) __kvm_reset_cptr_el2((v)->kvm) -#endif - /* * Returns a 'sanitised' view of CPTR_EL2, translating from nVHE to the VHE * format if E2H isn't set. diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 7cfa024de4e3..3a7ec98ef123 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -100,7 +100,7 @@ static inline void push_hyp_memcache(struct kvm_hyp_memcache *mc, static inline void *pop_hyp_memcache(struct kvm_hyp_memcache *mc, void *(*to_va)(phys_addr_t phys)) { - phys_addr_t *p = to_va(mc->head); + phys_addr_t *p = to_va(mc->head & PAGE_MASK); if (!mc->nr_pages) return NULL; @@ -615,8 +615,6 @@ struct cpu_sve_state { struct kvm_host_data { #define KVM_HOST_DATA_FLAG_HAS_SPE 0 #define KVM_HOST_DATA_FLAG_HAS_TRBE 1 -#define KVM_HOST_DATA_FLAG_HOST_SVE_ENABLED 2 -#define KVM_HOST_DATA_FLAG_HOST_SME_ENABLED 3 #define KVM_HOST_DATA_FLAG_TRBE_ENABLED 4 #define KVM_HOST_DATA_FLAG_EL1_TRACING_CONFIGURED 5 unsigned long flags; @@ -624,23 +622,13 @@ struct kvm_host_data { struct kvm_cpu_context host_ctxt; /* - * All pointers in this union are hyp VA. + * Hyp VA. * sve_state is only used in pKVM and if system_supports_sve(). */ - union { - struct user_fpsimd_state *fpsimd_state; - struct cpu_sve_state *sve_state; - }; - - union { - /* HYP VA pointer to the host storage for FPMR */ - u64 *fpmr_ptr; - /* - * Used by pKVM only, as it needs to provide storage - * for the host - */ - u64 fpmr; - }; + struct cpu_sve_state *sve_state; + + /* Used by pKVM only. */ + u64 fpmr; /* Ownership of the FP regs */ enum { diff --git a/arch/arm64/kernel/cacheinfo.c b/arch/arm64/kernel/cacheinfo.c index d9c9218fa1fd..309942b06c5b 100644 --- a/arch/arm64/kernel/cacheinfo.c +++ b/arch/arm64/kernel/cacheinfo.c @@ -101,16 +101,18 @@ int populate_cache_leaves(unsigned int cpu) unsigned int level, idx; enum cache_type type; struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); - struct cacheinfo *this_leaf = this_cpu_ci->info_list; + struct cacheinfo *infos = this_cpu_ci->info_list; for (idx = 0, level = 1; level <= this_cpu_ci->num_levels && - idx < this_cpu_ci->num_leaves; idx++, level++) { + idx < this_cpu_ci->num_leaves; level++) { type = get_cache_type(level); if (type == CACHE_TYPE_SEPARATE) { - ci_leaf_init(this_leaf++, CACHE_TYPE_DATA, level); - ci_leaf_init(this_leaf++, CACHE_TYPE_INST, level); + if (idx + 1 >= this_cpu_ci->num_leaves) + break; + ci_leaf_init(&infos[idx++], CACHE_TYPE_DATA, level); + ci_leaf_init(&infos[idx++], CACHE_TYPE_INST, level); } else { - ci_leaf_init(this_leaf++, type, level); + ci_leaf_init(&infos[idx++], type, level); } } return 0; diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 4eb7c6698ae4..d561cf3b8ac7 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -3091,6 +3091,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64ISAR0_EL1, TS, FLAGM, CAP_HWCAP, KERNEL_HWCAP_FLAGM), HWCAP_CAP(ID_AA64ISAR0_EL1, TS, FLAGM2, CAP_HWCAP, KERNEL_HWCAP_FLAGM2), HWCAP_CAP(ID_AA64ISAR0_EL1, RNDR, IMP, CAP_HWCAP, KERNEL_HWCAP_RNG), + HWCAP_CAP(ID_AA64ISAR3_EL1, FPRCVT, IMP, CAP_HWCAP, KERNEL_HWCAP_FPRCVT), HWCAP_CAP(ID_AA64PFR0_EL1, FP, IMP, CAP_HWCAP, KERNEL_HWCAP_FP), HWCAP_CAP(ID_AA64PFR0_EL1, FP, FP16, CAP_HWCAP, KERNEL_HWCAP_FPHP), HWCAP_CAP(ID_AA64PFR0_EL1, AdvSIMD, IMP, CAP_HWCAP, KERNEL_HWCAP_ASIMD), @@ -3180,8 +3181,6 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64SMFR0_EL1, SF8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8FMA), HWCAP_CAP(ID_AA64SMFR0_EL1, SF8DP4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP4), HWCAP_CAP(ID_AA64SMFR0_EL1, SF8DP2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP2), - HWCAP_CAP(ID_AA64SMFR0_EL1, SF8MM8, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8MM8), - HWCAP_CAP(ID_AA64SMFR0_EL1, SF8MM4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8MM4), HWCAP_CAP(ID_AA64SMFR0_EL1, SBitPerm, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SBITPERM), HWCAP_CAP(ID_AA64SMFR0_EL1, AES, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_AES), HWCAP_CAP(ID_AA64SMFR0_EL1, SFEXPA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SFEXPA), @@ -3192,6 +3191,8 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64FPFR0_EL1, F8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_F8FMA), HWCAP_CAP(ID_AA64FPFR0_EL1, F8DP4, IMP, CAP_HWCAP, KERNEL_HWCAP_F8DP4), HWCAP_CAP(ID_AA64FPFR0_EL1, F8DP2, IMP, CAP_HWCAP, KERNEL_HWCAP_F8DP2), + HWCAP_CAP(ID_AA64FPFR0_EL1, F8MM8, IMP, CAP_HWCAP, KERNEL_HWCAP_F8MM8), + HWCAP_CAP(ID_AA64FPFR0_EL1, F8MM4, IMP, CAP_HWCAP, KERNEL_HWCAP_F8MM4), HWCAP_CAP(ID_AA64FPFR0_EL1, F8E4M3, IMP, CAP_HWCAP, KERNEL_HWCAP_F8E4M3), HWCAP_CAP(ID_AA64FPFR0_EL1, F8E5M2, IMP, CAP_HWCAP, KERNEL_HWCAP_F8E5M2), #ifdef CONFIG_ARM64_POE diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 2b601d88762d..8370d55f0353 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -1695,31 +1695,6 @@ void fpsimd_signal_preserve_current_state(void) } /* - * Called by KVM when entering the guest. - */ -void fpsimd_kvm_prepare(void) -{ - if (!system_supports_sve()) - return; - - /* - * KVM does not save host SVE state since we can only enter - * the guest from a syscall so the ABI means that only the - * non-saved SVE state needs to be saved. If we have left - * SVE enabled for performance reasons then update the task - * state to be FPSIMD only. - */ - get_cpu_fpsimd_context(); - - if (test_and_clear_thread_flag(TIF_SVE)) { - sve_to_fpsimd(current); - current->thread.fp_type = FP_STATE_FPSIMD; - } - - put_cpu_fpsimd_context(); -} - -/* * Associate current's FPSIMD context with this cpu * The caller must have ownership of the cpu FPSIMD context before calling * this function. diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index 1a2c72f3e7f8..cb180684d10d 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -194,12 +194,19 @@ static void amu_fie_setup(const struct cpumask *cpus) int cpu; /* We are already set since the last insmod of cpufreq driver */ - if (unlikely(cpumask_subset(cpus, amu_fie_cpus))) + if (cpumask_available(amu_fie_cpus) && + unlikely(cpumask_subset(cpus, amu_fie_cpus))) return; - for_each_cpu(cpu, cpus) { + for_each_cpu(cpu, cpus) if (!freq_counters_valid(cpu)) return; + + if (!cpumask_available(amu_fie_cpus) && + !zalloc_cpumask_var(&amu_fie_cpus, GFP_KERNEL)) { + WARN_ONCE(1, "Failed to allocate FIE cpumask for CPUs[%*pbl]\n", + cpumask_pr_args(cpus)); + return; } cpumask_or(amu_fie_cpus, amu_fie_cpus, cpus); @@ -237,17 +244,8 @@ static struct notifier_block init_amu_fie_notifier = { static int __init init_amu_fie(void) { - int ret; - - if (!zalloc_cpumask_var(&amu_fie_cpus, GFP_KERNEL)) - return -ENOMEM; - - ret = cpufreq_register_notifier(&init_amu_fie_notifier, + return cpufreq_register_notifier(&init_amu_fie_notifier, CPUFREQ_POLICY_NOTIFIER); - if (ret) - free_cpumask_var(amu_fie_cpus); - - return ret; } core_initcall(init_amu_fie); diff --git a/arch/arm64/kernel/vdso/vdso.lds.S b/arch/arm64/kernel/vdso/vdso.lds.S index 4ec32e86a8da..47ad6944f9f0 100644 --- a/arch/arm64/kernel/vdso/vdso.lds.S +++ b/arch/arm64/kernel/vdso/vdso.lds.S @@ -41,6 +41,7 @@ SECTIONS */ /DISCARD/ : { *(.note.GNU-stack .note.gnu.property) + *(.ARM.attributes) } .note : { *(.note.*) } :text :note diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index f84c71f04d9e..e73326bd3ff7 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -162,6 +162,7 @@ SECTIONS /DISCARD/ : { *(.interp .dynamic) *(.dynsym .dynstr .hash .gnu.hash) + *(.ARM.attributes) } . = KIMAGE_VADDR; diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c index 231c0cd9c7b4..70802e4c91cf 100644 --- a/arch/arm64/kvm/arch_timer.c +++ b/arch/arm64/kvm/arch_timer.c @@ -447,21 +447,19 @@ static void kvm_timer_update_status(struct arch_timer_context *ctx, bool level) static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level, struct arch_timer_context *timer_ctx) { - int ret; - kvm_timer_update_status(timer_ctx, new_level); timer_ctx->irq.level = new_level; trace_kvm_timer_update_irq(vcpu->vcpu_id, timer_irq(timer_ctx), timer_ctx->irq.level); - if (!userspace_irqchip(vcpu->kvm)) { - ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu, - timer_irq(timer_ctx), - timer_ctx->irq.level, - timer_ctx); - WARN_ON(ret); - } + if (userspace_irqchip(vcpu->kvm)) + return; + + kvm_vgic_inject_irq(vcpu->kvm, vcpu, + timer_irq(timer_ctx), + timer_ctx->irq.level, + timer_ctx); } /* Only called for a fully emulated timer */ diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 071a7d75be68..b8e55a441282 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -2481,14 +2481,6 @@ static void finalize_init_hyp_mode(void) per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->sve_state = kern_hyp_va(sve_state); } - } else { - for_each_possible_cpu(cpu) { - struct user_fpsimd_state *fpsimd_state; - - fpsimd_state = &per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->host_ctxt.fp_regs; - per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->fpsimd_state = - kern_hyp_va(fpsimd_state); - } } } diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index 4d3d1a2eb157..7f6e43d25691 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -54,50 +54,18 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu) if (!system_supports_fpsimd()) return; - fpsimd_kvm_prepare(); - /* - * We will check TIF_FOREIGN_FPSTATE just before entering the - * guest in kvm_arch_vcpu_ctxflush_fp() and override this to - * FP_STATE_FREE if the flag set. + * Ensure that any host FPSIMD/SVE/SME state is saved and unbound such + * that the host kernel is responsible for restoring this state upon + * return to userspace, and the hyp code doesn't need to save anything. + * + * When the host may use SME, fpsimd_save_and_flush_cpu_state() ensures + * that PSTATE.{SM,ZA} == {0,0}. */ - *host_data_ptr(fp_owner) = FP_STATE_HOST_OWNED; - *host_data_ptr(fpsimd_state) = kern_hyp_va(¤t->thread.uw.fpsimd_state); - *host_data_ptr(fpmr_ptr) = kern_hyp_va(¤t->thread.uw.fpmr); - - host_data_clear_flag(HOST_SVE_ENABLED); - if (read_sysreg(cpacr_el1) & CPACR_EL1_ZEN_EL0EN) - host_data_set_flag(HOST_SVE_ENABLED); - - if (system_supports_sme()) { - host_data_clear_flag(HOST_SME_ENABLED); - if (read_sysreg(cpacr_el1) & CPACR_EL1_SMEN_EL0EN) - host_data_set_flag(HOST_SME_ENABLED); - - /* - * If PSTATE.SM is enabled then save any pending FP - * state and disable PSTATE.SM. If we leave PSTATE.SM - * enabled and the guest does not enable SME via - * CPACR_EL1.SMEN then operations that should be valid - * may generate SME traps from EL1 to EL1 which we - * can't intercept and which would confuse the guest. - * - * Do the same for PSTATE.ZA in the case where there - * is state in the registers which has not already - * been saved, this is very unlikely to happen. - */ - if (read_sysreg_s(SYS_SVCR) & (SVCR_SM_MASK | SVCR_ZA_MASK)) { - *host_data_ptr(fp_owner) = FP_STATE_FREE; - fpsimd_save_and_flush_cpu_state(); - } - } + fpsimd_save_and_flush_cpu_state(); + *host_data_ptr(fp_owner) = FP_STATE_FREE; - /* - * If normal guests gain SME support, maintain this behavior for pKVM - * guests, which don't support SME. - */ - WARN_ON(is_protected_kvm_enabled() && system_supports_sme() && - read_sysreg_s(SYS_SVCR)); + WARN_ON_ONCE(system_supports_sme() && read_sysreg_s(SYS_SVCR)); } /* @@ -162,52 +130,7 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu) local_irq_save(flags); - /* - * If we have VHE then the Hyp code will reset CPACR_EL1 to - * the default value and we need to reenable SME. - */ - if (has_vhe() && system_supports_sme()) { - /* Also restore EL0 state seen on entry */ - if (host_data_test_flag(HOST_SME_ENABLED)) - sysreg_clear_set(CPACR_EL1, 0, CPACR_EL1_SMEN); - else - sysreg_clear_set(CPACR_EL1, - CPACR_EL1_SMEN_EL0EN, - CPACR_EL1_SMEN_EL1EN); - isb(); - } - if (guest_owns_fp_regs()) { - if (vcpu_has_sve(vcpu)) { - u64 zcr = read_sysreg_el1(SYS_ZCR); - - /* - * If the vCPU is in the hyp context then ZCR_EL1 is - * loaded with its vEL2 counterpart. - */ - __vcpu_sys_reg(vcpu, vcpu_sve_zcr_elx(vcpu)) = zcr; - - /* - * Restore the VL that was saved when bound to the CPU, - * which is the maximum VL for the guest. Because the - * layout of the data when saving the sve state depends - * on the VL, we need to use a consistent (i.e., the - * maximum) VL. - * Note that this means that at guest exit ZCR_EL1 is - * not necessarily the same as on guest entry. - * - * ZCR_EL2 holds the guest hypervisor's VL when running - * a nested guest, which could be smaller than the - * max for the vCPU. Similar to above, we first need to - * switch to a VL consistent with the layout of the - * vCPU's SVE state. KVM support for NV implies VHE, so - * using the ZCR_EL1 alias is safe. - */ - if (!has_vhe() || (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu))) - sve_cond_update_zcr_vq(vcpu_sve_max_vq(vcpu) - 1, - SYS_ZCR_EL1); - } - /* * Flush (save and invalidate) the fpsimd/sve state so that if * the host tries to use fpsimd/sve, it's not using stale data @@ -219,18 +142,6 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu) * when needed. */ fpsimd_save_and_flush_cpu_state(); - } else if (has_vhe() && system_supports_sve()) { - /* - * The FPSIMD/SVE state in the CPU has not been touched, and we - * have SVE (and VHE): CPACR_EL1 (alias CPTR_EL2) has been - * reset by kvm_reset_cptr_el2() in the Hyp code, disabling SVE - * for EL0. To avoid spurious traps, restore the trap state - * seen by kvm_arch_vcpu_load_fp(): - */ - if (host_data_test_flag(HOST_SVE_ENABLED)) - sysreg_clear_set(CPACR_EL1, 0, CPACR_EL1_ZEN_EL0EN); - else - sysreg_clear_set(CPACR_EL1, CPACR_EL1_ZEN_EL0EN, 0); } local_irq_restore(flags); diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S index 4433a234aa9b..9f4e8d68ab50 100644 --- a/arch/arm64/kvm/hyp/entry.S +++ b/arch/arm64/kvm/hyp/entry.S @@ -44,6 +44,11 @@ alternative_if ARM64_HAS_RAS_EXTN alternative_else_nop_endif mrs x1, isr_el1 cbz x1, 1f + + // Ensure that __guest_enter() always provides a context + // synchronization event so that callers don't need ISBs for anything + // that would usually be synchonized by the ERET. + isb mov x0, #ARM_EXCEPTION_IRQ ret diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index f838a45665f2..23bbe28eaaf9 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -326,7 +326,7 @@ static inline bool __populate_fault_info(struct kvm_vcpu *vcpu) return __get_fault_info(vcpu->arch.fault.esr_el2, &vcpu->arch.fault); } -static bool kvm_hyp_handle_mops(struct kvm_vcpu *vcpu, u64 *exit_code) +static inline bool kvm_hyp_handle_mops(struct kvm_vcpu *vcpu, u64 *exit_code) { *vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR); arm64_mops_reset_regs(vcpu_gp_regs(vcpu), vcpu->arch.fault.esr_el2); @@ -375,7 +375,87 @@ static inline void __hyp_sve_save_host(void) true); } -static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu); +static inline void fpsimd_lazy_switch_to_guest(struct kvm_vcpu *vcpu) +{ + u64 zcr_el1, zcr_el2; + + if (!guest_owns_fp_regs()) + return; + + if (vcpu_has_sve(vcpu)) { + /* A guest hypervisor may restrict the effective max VL. */ + if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)) + zcr_el2 = __vcpu_sys_reg(vcpu, ZCR_EL2); + else + zcr_el2 = vcpu_sve_max_vq(vcpu) - 1; + + write_sysreg_el2(zcr_el2, SYS_ZCR); + + zcr_el1 = __vcpu_sys_reg(vcpu, vcpu_sve_zcr_elx(vcpu)); + write_sysreg_el1(zcr_el1, SYS_ZCR); + } +} + +static inline void fpsimd_lazy_switch_to_host(struct kvm_vcpu *vcpu) +{ + u64 zcr_el1, zcr_el2; + + if (!guest_owns_fp_regs()) + return; + + /* + * When the guest owns the FP regs, we know that guest+hyp traps for + * any FPSIMD/SVE/SME features exposed to the guest have been disabled + * by either fpsimd_lazy_switch_to_guest() or kvm_hyp_handle_fpsimd() + * prior to __guest_entry(). As __guest_entry() guarantees a context + * synchronization event, we don't need an ISB here to avoid taking + * traps for anything that was exposed to the guest. + */ + if (vcpu_has_sve(vcpu)) { + zcr_el1 = read_sysreg_el1(SYS_ZCR); + __vcpu_sys_reg(vcpu, vcpu_sve_zcr_elx(vcpu)) = zcr_el1; + + /* + * The guest's state is always saved using the guest's max VL. + * Ensure that the host has the guest's max VL active such that + * the host can save the guest's state lazily, but don't + * artificially restrict the host to the guest's max VL. + */ + if (has_vhe()) { + zcr_el2 = vcpu_sve_max_vq(vcpu) - 1; + write_sysreg_el2(zcr_el2, SYS_ZCR); + } else { + zcr_el2 = sve_vq_from_vl(kvm_host_sve_max_vl) - 1; + write_sysreg_el2(zcr_el2, SYS_ZCR); + + zcr_el1 = vcpu_sve_max_vq(vcpu) - 1; + write_sysreg_el1(zcr_el1, SYS_ZCR); + } + } +} + +static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu) +{ + /* + * Non-protected kvm relies on the host restoring its sve state. + * Protected kvm restores the host's sve state as not to reveal that + * fpsimd was used by a guest nor leak upper sve bits. + */ + if (system_supports_sve()) { + __hyp_sve_save_host(); + + /* Re-enable SVE traps if not supported for the guest vcpu. */ + if (!vcpu_has_sve(vcpu)) + cpacr_clear_set(CPACR_EL1_ZEN, 0); + + } else { + __fpsimd_save_state(host_data_ptr(host_ctxt.fp_regs)); + } + + if (kvm_has_fpmr(kern_hyp_va(vcpu->kvm))) + *host_data_ptr(fpmr) = read_sysreg_s(SYS_FPMR); +} + /* * We trap the first access to the FP/SIMD to save the host context and @@ -383,7 +463,7 @@ static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu); * If FP/SIMD is not implemented, handle the trap and inject an undefined * instruction exception to the guest. Similarly for trapped SVE accesses. */ -static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code) +static inline bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code) { bool sve_guest; u8 esr_ec; @@ -425,7 +505,7 @@ static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code) isb(); /* Write out the host state if it's in the registers */ - if (host_owns_fp_regs()) + if (is_protected_kvm_enabled() && host_owns_fp_regs()) kvm_hyp_save_fpsimd_host(vcpu); /* Restore the guest state */ @@ -501,9 +581,22 @@ static inline bool handle_tx2_tvm(struct kvm_vcpu *vcpu) return true; } +/* Open-coded version of timer_get_offset() to allow for kern_hyp_va() */ +static inline u64 hyp_timer_get_offset(struct arch_timer_context *ctxt) +{ + u64 offset = 0; + + if (ctxt->offset.vm_offset) + offset += *kern_hyp_va(ctxt->offset.vm_offset); + if (ctxt->offset.vcpu_offset) + offset += *kern_hyp_va(ctxt->offset.vcpu_offset); + + return offset; +} + static inline u64 compute_counter_value(struct arch_timer_context *ctxt) { - return arch_timer_read_cntpct_el0() - timer_get_offset(ctxt); + return arch_timer_read_cntpct_el0() - hyp_timer_get_offset(ctxt); } static bool kvm_handle_cntxct(struct kvm_vcpu *vcpu) @@ -587,7 +680,7 @@ static bool handle_ampere1_tcr(struct kvm_vcpu *vcpu) return true; } -static bool kvm_hyp_handle_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code) +static inline bool kvm_hyp_handle_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code) { if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM) && handle_tx2_tvm(vcpu)) @@ -607,7 +700,7 @@ static bool kvm_hyp_handle_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code) return false; } -static bool kvm_hyp_handle_cp15_32(struct kvm_vcpu *vcpu, u64 *exit_code) +static inline bool kvm_hyp_handle_cp15_32(struct kvm_vcpu *vcpu, u64 *exit_code) { if (static_branch_unlikely(&vgic_v3_cpuif_trap) && __vgic_v3_perform_cpuif_access(vcpu) == 1) @@ -616,19 +709,18 @@ static bool kvm_hyp_handle_cp15_32(struct kvm_vcpu *vcpu, u64 *exit_code) return false; } -static bool kvm_hyp_handle_memory_fault(struct kvm_vcpu *vcpu, u64 *exit_code) +static inline bool kvm_hyp_handle_memory_fault(struct kvm_vcpu *vcpu, + u64 *exit_code) { if (!__populate_fault_info(vcpu)) return true; return false; } -static bool kvm_hyp_handle_iabt_low(struct kvm_vcpu *vcpu, u64 *exit_code) - __alias(kvm_hyp_handle_memory_fault); -static bool kvm_hyp_handle_watchpt_low(struct kvm_vcpu *vcpu, u64 *exit_code) - __alias(kvm_hyp_handle_memory_fault); +#define kvm_hyp_handle_iabt_low kvm_hyp_handle_memory_fault +#define kvm_hyp_handle_watchpt_low kvm_hyp_handle_memory_fault -static bool kvm_hyp_handle_dabt_low(struct kvm_vcpu *vcpu, u64 *exit_code) +static inline bool kvm_hyp_handle_dabt_low(struct kvm_vcpu *vcpu, u64 *exit_code) { if (kvm_hyp_handle_memory_fault(vcpu, exit_code)) return true; @@ -658,23 +750,16 @@ static bool kvm_hyp_handle_dabt_low(struct kvm_vcpu *vcpu, u64 *exit_code) typedef bool (*exit_handler_fn)(struct kvm_vcpu *, u64 *); -static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu); - -static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code); - /* * Allow the hypervisor to handle the exit with an exit handler if it has one. * * Returns true if the hypervisor handled the exit, and control should go back * to the guest, or false if it hasn't. */ -static inline bool kvm_hyp_handle_exit(struct kvm_vcpu *vcpu, u64 *exit_code) +static inline bool kvm_hyp_handle_exit(struct kvm_vcpu *vcpu, u64 *exit_code, + const exit_handler_fn *handlers) { - const exit_handler_fn *handlers = kvm_get_exit_handler_array(vcpu); - exit_handler_fn fn; - - fn = handlers[kvm_vcpu_trap_get_class(vcpu)]; - + exit_handler_fn fn = handlers[kvm_vcpu_trap_get_class(vcpu)]; if (fn) return fn(vcpu, exit_code); @@ -704,20 +789,9 @@ static inline void synchronize_vcpu_pstate(struct kvm_vcpu *vcpu, u64 *exit_code * the guest, false when we should restore the host state and return to the * main run loop. */ -static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) +static inline bool __fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code, + const exit_handler_fn *handlers) { - /* - * Save PSTATE early so that we can evaluate the vcpu mode - * early on. - */ - synchronize_vcpu_pstate(vcpu, exit_code); - - /* - * Check whether we want to repaint the state one way or - * another. - */ - early_exit_filter(vcpu, exit_code); - if (ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ) vcpu->arch.fault.esr_el2 = read_sysreg_el2(SYS_ESR); @@ -747,7 +821,7 @@ static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) goto exit; /* Check if there's an exit handler and allow it to handle the exit. */ - if (kvm_hyp_handle_exit(vcpu, exit_code)) + if (kvm_hyp_handle_exit(vcpu, exit_code, handlers)) goto guest; exit: /* Return to the host kernel and handle the exit */ diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c index 6e12c070832f..2c37680d954c 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c @@ -5,6 +5,7 @@ */ #include <hyp/adjust_pc.h> +#include <hyp/switch.h> #include <asm/pgtable-types.h> #include <asm/kvm_asm.h> @@ -83,7 +84,7 @@ static void fpsimd_sve_sync(struct kvm_vcpu *vcpu) if (system_supports_sve()) __hyp_sve_restore_host(); else - __fpsimd_restore_state(*host_data_ptr(fpsimd_state)); + __fpsimd_restore_state(host_data_ptr(host_ctxt.fp_regs)); if (has_fpmr) write_sysreg_s(*host_data_ptr(fpmr), SYS_FPMR); @@ -224,8 +225,12 @@ static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt) sync_hyp_vcpu(hyp_vcpu); } else { + struct kvm_vcpu *vcpu = kern_hyp_va(host_vcpu); + /* The host is fully trusted, run its vCPU directly. */ - ret = __kvm_vcpu_run(kern_hyp_va(host_vcpu)); + fpsimd_lazy_switch_to_guest(vcpu); + ret = __kvm_vcpu_run(vcpu); + fpsimd_lazy_switch_to_host(vcpu); } out: cpu_reg(host_ctxt, 1) = ret; @@ -675,12 +680,6 @@ void handle_trap(struct kvm_cpu_context *host_ctxt) case ESR_ELx_EC_SMC64: handle_host_smc(host_ctxt); break; - case ESR_ELx_EC_SVE: - cpacr_clear_set(0, CPACR_EL1_ZEN); - isb(); - sve_cond_update_zcr_vq(sve_vq_from_vl(kvm_host_sve_max_vl) - 1, - SYS_ZCR_EL2); - break; case ESR_ELx_EC_IABT_LOW: case ESR_ELx_EC_DABT_LOW: handle_host_mem_abort(host_ctxt); diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index 7ad7b133b81a..19c3c631708c 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -943,10 +943,10 @@ static int __check_host_shared_guest(struct pkvm_hyp_vm *vm, u64 *__phys, u64 ip ret = kvm_pgtable_get_leaf(&vm->pgt, ipa, &pte, &level); if (ret) return ret; - if (level != KVM_PGTABLE_LAST_LEVEL) - return -E2BIG; if (!kvm_pte_valid(pte)) return -ENOENT; + if (level != KVM_PGTABLE_LAST_LEVEL) + return -E2BIG; state = guest_get_page_state(pte, ipa); if (state != PKVM_PAGE_SHARED_BORROWED) @@ -998,63 +998,73 @@ unlock: return ret; } -int __pkvm_host_relax_perms_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_pgtable_prot prot) +static void assert_host_shared_guest(struct pkvm_hyp_vm *vm, u64 ipa) { - struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu); - u64 ipa = hyp_pfn_to_phys(gfn); u64 phys; int ret; - if (prot & ~KVM_PGTABLE_PROT_RWX) - return -EINVAL; + if (!IS_ENABLED(CONFIG_NVHE_EL2_DEBUG)) + return; host_lock_component(); guest_lock_component(vm); ret = __check_host_shared_guest(vm, &phys, ipa); - if (!ret) - ret = kvm_pgtable_stage2_relax_perms(&vm->pgt, ipa, prot, 0); guest_unlock_component(vm); host_unlock_component(); - return ret; + WARN_ON(ret && ret != -ENOENT); } -int __pkvm_host_wrprotect_guest(u64 gfn, struct pkvm_hyp_vm *vm) +int __pkvm_host_relax_perms_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_pgtable_prot prot) { + struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu); u64 ipa = hyp_pfn_to_phys(gfn); - u64 phys; int ret; - host_lock_component(); - guest_lock_component(vm); + if (pkvm_hyp_vm_is_protected(vm)) + return -EPERM; - ret = __check_host_shared_guest(vm, &phys, ipa); - if (!ret) - ret = kvm_pgtable_stage2_wrprotect(&vm->pgt, ipa, PAGE_SIZE); + if (prot & ~KVM_PGTABLE_PROT_RWX) + return -EINVAL; + assert_host_shared_guest(vm, ipa); + guest_lock_component(vm); + ret = kvm_pgtable_stage2_relax_perms(&vm->pgt, ipa, prot, 0); guest_unlock_component(vm); - host_unlock_component(); return ret; } -int __pkvm_host_test_clear_young_guest(u64 gfn, bool mkold, struct pkvm_hyp_vm *vm) +int __pkvm_host_wrprotect_guest(u64 gfn, struct pkvm_hyp_vm *vm) { u64 ipa = hyp_pfn_to_phys(gfn); - u64 phys; int ret; - host_lock_component(); + if (pkvm_hyp_vm_is_protected(vm)) + return -EPERM; + + assert_host_shared_guest(vm, ipa); guest_lock_component(vm); + ret = kvm_pgtable_stage2_wrprotect(&vm->pgt, ipa, PAGE_SIZE); + guest_unlock_component(vm); - ret = __check_host_shared_guest(vm, &phys, ipa); - if (!ret) - ret = kvm_pgtable_stage2_test_clear_young(&vm->pgt, ipa, PAGE_SIZE, mkold); + return ret; +} + +int __pkvm_host_test_clear_young_guest(u64 gfn, bool mkold, struct pkvm_hyp_vm *vm) +{ + u64 ipa = hyp_pfn_to_phys(gfn); + int ret; + + if (pkvm_hyp_vm_is_protected(vm)) + return -EPERM; + assert_host_shared_guest(vm, ipa); + guest_lock_component(vm); + ret = kvm_pgtable_stage2_test_clear_young(&vm->pgt, ipa, PAGE_SIZE, mkold); guest_unlock_component(vm); - host_unlock_component(); return ret; } @@ -1063,18 +1073,14 @@ int __pkvm_host_mkyoung_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu) { struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu); u64 ipa = hyp_pfn_to_phys(gfn); - u64 phys; - int ret; - - host_lock_component(); - guest_lock_component(vm); - ret = __check_host_shared_guest(vm, &phys, ipa); - if (!ret) - kvm_pgtable_stage2_mkyoung(&vm->pgt, ipa, 0); + if (pkvm_hyp_vm_is_protected(vm)) + return -EPERM; + assert_host_shared_guest(vm, ipa); + guest_lock_component(vm); + kvm_pgtable_stage2_mkyoung(&vm->pgt, ipa, 0); guest_unlock_component(vm); - host_unlock_component(); - return ret; + return 0; } diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index 6c846d033d24..7d2ba6ef0261 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -39,6 +39,9 @@ static void __activate_cptr_traps(struct kvm_vcpu *vcpu) { u64 val = CPTR_EL2_TAM; /* Same bit irrespective of E2H */ + if (!guest_owns_fp_regs()) + __activate_traps_fpsimd32(vcpu); + if (has_hvhe()) { val |= CPACR_EL1_TTA; @@ -47,6 +50,8 @@ static void __activate_cptr_traps(struct kvm_vcpu *vcpu) if (vcpu_has_sve(vcpu)) val |= CPACR_EL1_ZEN; } + + write_sysreg(val, cpacr_el1); } else { val |= CPTR_EL2_TTA | CPTR_NVHE_EL2_RES1; @@ -61,12 +66,32 @@ static void __activate_cptr_traps(struct kvm_vcpu *vcpu) if (!guest_owns_fp_regs()) val |= CPTR_EL2_TFP; + + write_sysreg(val, cptr_el2); } +} - if (!guest_owns_fp_regs()) - __activate_traps_fpsimd32(vcpu); +static void __deactivate_cptr_traps(struct kvm_vcpu *vcpu) +{ + if (has_hvhe()) { + u64 val = CPACR_EL1_FPEN; + + if (cpus_have_final_cap(ARM64_SVE)) + val |= CPACR_EL1_ZEN; + if (cpus_have_final_cap(ARM64_SME)) + val |= CPACR_EL1_SMEN; - kvm_write_cptr_el2(val); + write_sysreg(val, cpacr_el1); + } else { + u64 val = CPTR_NVHE_EL2_RES1; + + if (!cpus_have_final_cap(ARM64_SVE)) + val |= CPTR_EL2_TZ; + if (!cpus_have_final_cap(ARM64_SME)) + val |= CPTR_EL2_TSM; + + write_sysreg(val, cptr_el2); + } } static void __activate_traps(struct kvm_vcpu *vcpu) @@ -119,7 +144,7 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu) write_sysreg(this_cpu_ptr(&kvm_init_params)->hcr_el2, hcr_el2); - kvm_reset_cptr_el2(vcpu); + __deactivate_cptr_traps(vcpu); write_sysreg(__kvm_hyp_host_vector, vbar_el2); } @@ -192,34 +217,6 @@ static bool kvm_handle_pvm_sys64(struct kvm_vcpu *vcpu, u64 *exit_code) kvm_handle_pvm_sysreg(vcpu, exit_code)); } -static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu) -{ - /* - * Non-protected kvm relies on the host restoring its sve state. - * Protected kvm restores the host's sve state as not to reveal that - * fpsimd was used by a guest nor leak upper sve bits. - */ - if (unlikely(is_protected_kvm_enabled() && system_supports_sve())) { - __hyp_sve_save_host(); - - /* Re-enable SVE traps if not supported for the guest vcpu. */ - if (!vcpu_has_sve(vcpu)) - cpacr_clear_set(CPACR_EL1_ZEN, 0); - - } else { - __fpsimd_save_state(*host_data_ptr(fpsimd_state)); - } - - if (kvm_has_fpmr(kern_hyp_va(vcpu->kvm))) { - u64 val = read_sysreg_s(SYS_FPMR); - - if (unlikely(is_protected_kvm_enabled())) - *host_data_ptr(fpmr) = val; - else - **host_data_ptr(fpmr_ptr) = val; - } -} - static const exit_handler_fn hyp_exit_handlers[] = { [0 ... ESR_ELx_EC_MAX] = NULL, [ESR_ELx_EC_CP15_32] = kvm_hyp_handle_cp15_32, @@ -251,19 +248,21 @@ static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu) return hyp_exit_handlers; } -/* - * Some guests (e.g., protected VMs) are not be allowed to run in AArch32. - * The ARMv8 architecture does not give the hypervisor a mechanism to prevent a - * guest from dropping to AArch32 EL0 if implemented by the CPU. If the - * hypervisor spots a guest in such a state ensure it is handled, and don't - * trust the host to spot or fix it. The check below is based on the one in - * kvm_arch_vcpu_ioctl_run(). - * - * Returns false if the guest ran in AArch32 when it shouldn't have, and - * thus should exit to the host, or true if a the guest run loop can continue. - */ -static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code) +static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) { + const exit_handler_fn *handlers = kvm_get_exit_handler_array(vcpu); + + synchronize_vcpu_pstate(vcpu, exit_code); + + /* + * Some guests (e.g., protected VMs) are not be allowed to run in + * AArch32. The ARMv8 architecture does not give the hypervisor a + * mechanism to prevent a guest from dropping to AArch32 EL0 if + * implemented by the CPU. If the hypervisor spots a guest in such a + * state ensure it is handled, and don't trust the host to spot or fix + * it. The check below is based on the one in + * kvm_arch_vcpu_ioctl_run(). + */ if (unlikely(vcpu_is_protected(vcpu) && vcpu_mode_is_32bit(vcpu))) { /* * As we have caught the guest red-handed, decide that it isn't @@ -276,6 +275,8 @@ static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code) *exit_code &= BIT(ARM_EXIT_WITH_SERROR_BIT); *exit_code |= ARM_EXCEPTION_IL; } + + return __fixup_guest_exit(vcpu, exit_code, handlers); } /* Switch to the guest for legacy non-VHE systems */ diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index b5b9dbaf1fdd..647737d6e8d0 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -136,6 +136,16 @@ write: write_sysreg(val, cpacr_el1); } +static void __deactivate_cptr_traps(struct kvm_vcpu *vcpu) +{ + u64 val = CPACR_EL1_FPEN | CPACR_EL1_ZEN_EL1EN; + + if (cpus_have_final_cap(ARM64_SME)) + val |= CPACR_EL1_SMEN_EL1EN; + + write_sysreg(val, cpacr_el1); +} + static void __activate_traps(struct kvm_vcpu *vcpu) { u64 val; @@ -207,7 +217,7 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu) */ asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT)); - kvm_reset_cptr_el2(vcpu); + __deactivate_cptr_traps(vcpu); if (!arm64_kernel_unmapped_at_el0()) host_vectors = __this_cpu_read(this_cpu_vector); @@ -413,14 +423,6 @@ static bool kvm_hyp_handle_eret(struct kvm_vcpu *vcpu, u64 *exit_code) return true; } -static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu) -{ - __fpsimd_save_state(*host_data_ptr(fpsimd_state)); - - if (kvm_has_fpmr(vcpu->kvm)) - **host_data_ptr(fpmr_ptr) = read_sysreg_s(SYS_FPMR); -} - static bool kvm_hyp_handle_tlbi_el2(struct kvm_vcpu *vcpu, u64 *exit_code) { int ret = -EINVAL; @@ -538,13 +540,10 @@ static const exit_handler_fn hyp_exit_handlers[] = { [ESR_ELx_EC_MOPS] = kvm_hyp_handle_mops, }; -static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu) +static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) { - return hyp_exit_handlers; -} + synchronize_vcpu_pstate(vcpu, exit_code); -static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code) -{ /* * If we were in HYP context on entry, adjust the PSTATE view * so that the usual helpers work correctly. @@ -564,6 +563,8 @@ static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code) *vcpu_cpsr(vcpu) &= ~(PSR_MODE_MASK | PSR_MODE32_BIT); *vcpu_cpsr(vcpu) |= mode; } + + return __fixup_guest_exit(vcpu, exit_code, hyp_exit_handlers); } /* Switch to the guest for VHE systems running in EL2 */ @@ -578,6 +579,8 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) sysreg_save_host_state_vhe(host_ctxt); + fpsimd_lazy_switch_to_guest(vcpu); + /* * Note that ARM erratum 1165522 requires us to configure both stage 1 * and stage 2 translation for the guest context before we clear @@ -602,6 +605,8 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) __deactivate_traps(vcpu); + fpsimd_lazy_switch_to_host(vcpu); + sysreg_restore_host_state_vhe(host_ctxt); if (guest_owns_fp_regs()) diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index bc7e22ab5d81..775461cf2d2d 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -34,9 +34,9 @@ * * CPU Interface: * - * - kvm_vgic_vcpu_init(): initialization of static data that - * doesn't depend on any sizing information or emulation type. No - * allocation is allowed there. + * - kvm_vgic_vcpu_init(): initialization of static data that doesn't depend + * on any sizing information. Private interrupts are allocated if not + * already allocated at vgic-creation time. */ /* EARLY INIT */ @@ -58,6 +58,8 @@ void kvm_vgic_early_init(struct kvm *kvm) /* CREATION */ +static int vgic_allocate_private_irqs_locked(struct kvm_vcpu *vcpu, u32 type); + /** * kvm_vgic_create: triggered by the instantiation of the VGIC device by * user space, either through the legacy KVM_CREATE_IRQCHIP ioctl (v2 only) @@ -112,6 +114,22 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) goto out_unlock; } + kvm_for_each_vcpu(i, vcpu, kvm) { + ret = vgic_allocate_private_irqs_locked(vcpu, type); + if (ret) + break; + } + + if (ret) { + kvm_for_each_vcpu(i, vcpu, kvm) { + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + kfree(vgic_cpu->private_irqs); + vgic_cpu->private_irqs = NULL; + } + + goto out_unlock; + } + kvm->arch.vgic.in_kernel = true; kvm->arch.vgic.vgic_model = type; @@ -180,7 +198,7 @@ static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis) return 0; } -static int vgic_allocate_private_irqs_locked(struct kvm_vcpu *vcpu) +static int vgic_allocate_private_irqs_locked(struct kvm_vcpu *vcpu, u32 type) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; int i; @@ -218,17 +236,28 @@ static int vgic_allocate_private_irqs_locked(struct kvm_vcpu *vcpu) /* PPIs */ irq->config = VGIC_CONFIG_LEVEL; } + + switch (type) { + case KVM_DEV_TYPE_ARM_VGIC_V3: + irq->group = 1; + irq->mpidr = kvm_vcpu_get_mpidr_aff(vcpu); + break; + case KVM_DEV_TYPE_ARM_VGIC_V2: + irq->group = 0; + irq->targets = BIT(vcpu->vcpu_id); + break; + } } return 0; } -static int vgic_allocate_private_irqs(struct kvm_vcpu *vcpu) +static int vgic_allocate_private_irqs(struct kvm_vcpu *vcpu, u32 type) { int ret; mutex_lock(&vcpu->kvm->arch.config_lock); - ret = vgic_allocate_private_irqs_locked(vcpu); + ret = vgic_allocate_private_irqs_locked(vcpu, type); mutex_unlock(&vcpu->kvm->arch.config_lock); return ret; @@ -258,7 +287,7 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu) if (!irqchip_in_kernel(vcpu->kvm)) return 0; - ret = vgic_allocate_private_irqs(vcpu); + ret = vgic_allocate_private_irqs(vcpu, dist->vgic_model); if (ret) return ret; @@ -295,7 +324,7 @@ int vgic_init(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; struct kvm_vcpu *vcpu; - int ret = 0, i; + int ret = 0; unsigned long idx; lockdep_assert_held(&kvm->arch.config_lock); @@ -315,35 +344,6 @@ int vgic_init(struct kvm *kvm) if (ret) goto out; - /* Initialize groups on CPUs created before the VGIC type was known */ - kvm_for_each_vcpu(idx, vcpu, kvm) { - ret = vgic_allocate_private_irqs_locked(vcpu); - if (ret) - goto out; - - for (i = 0; i < VGIC_NR_PRIVATE_IRQS; i++) { - struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, i); - - switch (dist->vgic_model) { - case KVM_DEV_TYPE_ARM_VGIC_V3: - irq->group = 1; - irq->mpidr = kvm_vcpu_get_mpidr_aff(vcpu); - break; - case KVM_DEV_TYPE_ARM_VGIC_V2: - irq->group = 0; - irq->targets = 1U << idx; - break; - default: - ret = -EINVAL; - } - - vgic_put_irq(kvm, irq); - - if (ret) - goto out; - } - } - /* * If we have GICv4.1 enabled, unconditionally request enable the * v4 support so that we get HW-accelerated vSGIs. Otherwise, only diff --git a/arch/arm64/mm/trans_pgd.c b/arch/arm64/mm/trans_pgd.c index 19c67ed1a21f..18543b603c77 100644 --- a/arch/arm64/mm/trans_pgd.c +++ b/arch/arm64/mm/trans_pgd.c @@ -162,6 +162,13 @@ static int copy_p4d(struct trans_pgd_info *info, pgd_t *dst_pgdp, unsigned long next; unsigned long addr = start; + if (pgd_none(READ_ONCE(*dst_pgdp))) { + dst_p4dp = trans_alloc(info); + if (!dst_p4dp) + return -ENOMEM; + pgd_populate(NULL, dst_pgdp, dst_p4dp); + } + dst_p4dp = p4d_offset(dst_pgdp, start); src_p4dp = p4d_offset(src_pgdp, start); do { diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h index 4a2b40ce39e0..85fa9962266a 100644 --- a/arch/mips/include/asm/ptrace.h +++ b/arch/mips/include/asm/ptrace.h @@ -27,8 +27,8 @@ */ struct pt_regs { #ifdef CONFIG_32BIT - /* Pad bytes for argument save space on the stack. */ - unsigned long pad0[8]; + /* Saved syscall stack arguments; entries 0-3 unused. */ + unsigned long args[8]; #endif /* Saved main processor registers. */ diff --git a/arch/mips/include/asm/syscall.h b/arch/mips/include/asm/syscall.h index ebdf4d910af2..056aa1b713e2 100644 --- a/arch/mips/include/asm/syscall.h +++ b/arch/mips/include/asm/syscall.h @@ -57,37 +57,21 @@ static inline void mips_syscall_update_nr(struct task_struct *task, static inline void mips_get_syscall_arg(unsigned long *arg, struct task_struct *task, struct pt_regs *regs, unsigned int n) { - unsigned long usp __maybe_unused = regs->regs[29]; - +#ifdef CONFIG_32BIT switch (n) { case 0: case 1: case 2: case 3: *arg = regs->regs[4 + n]; - - return; - -#ifdef CONFIG_32BIT - case 4: case 5: case 6: case 7: - get_user(*arg, (int *)usp + n); return; -#endif - -#ifdef CONFIG_64BIT case 4: case 5: case 6: case 7: -#ifdef CONFIG_MIPS32_O32 - if (test_tsk_thread_flag(task, TIF_32BIT_REGS)) - get_user(*arg, (int *)usp + n); - else -#endif - *arg = regs->regs[4 + n]; - + *arg = regs->args[n]; return; -#endif - - default: - BUG(); } - - unreachable(); +#else + *arg = regs->regs[4 + n]; + if ((IS_ENABLED(CONFIG_MIPS32_O32) && + test_tsk_thread_flag(task, TIF_32BIT_REGS))) + *arg = (unsigned int)*arg; +#endif } static inline long syscall_get_error(struct task_struct *task, diff --git a/arch/mips/kernel/asm-offsets.c b/arch/mips/kernel/asm-offsets.c index cb1045ebab06..b910ec54a3a1 100644 --- a/arch/mips/kernel/asm-offsets.c +++ b/arch/mips/kernel/asm-offsets.c @@ -27,6 +27,12 @@ void output_ptreg_defines(void); void output_ptreg_defines(void) { COMMENT("MIPS pt_regs offsets."); +#ifdef CONFIG_32BIT + OFFSET(PT_ARG4, pt_regs, args[4]); + OFFSET(PT_ARG5, pt_regs, args[5]); + OFFSET(PT_ARG6, pt_regs, args[6]); + OFFSET(PT_ARG7, pt_regs, args[7]); +#endif OFFSET(PT_R0, pt_regs, regs[0]); OFFSET(PT_R1, pt_regs, regs[1]); OFFSET(PT_R2, pt_regs, regs[2]); diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S index 2c604717e630..4947a4f39e37 100644 --- a/arch/mips/kernel/scall32-o32.S +++ b/arch/mips/kernel/scall32-o32.S @@ -64,10 +64,10 @@ load_a6: user_lw(t7, 24(t0)) # argument #7 from usp load_a7: user_lw(t8, 28(t0)) # argument #8 from usp loads_done: - sw t5, 16(sp) # argument #5 to ksp - sw t6, 20(sp) # argument #6 to ksp - sw t7, 24(sp) # argument #7 to ksp - sw t8, 28(sp) # argument #8 to ksp + sw t5, PT_ARG4(sp) # argument #5 to ksp + sw t6, PT_ARG5(sp) # argument #6 to ksp + sw t7, PT_ARG6(sp) # argument #7 to ksp + sw t8, PT_ARG7(sp) # argument #8 to ksp .set pop .section __ex_table,"a" diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h index c3efacab4b94..aa90a048f319 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-4k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h @@ -77,9 +77,17 @@ /* * With 4K page size the real_pte machinery is all nops. */ -#define __real_pte(e, p, o) ((real_pte_t){(e)}) +static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep, int offset) +{ + return (real_pte_t){pte}; +} + #define __rpte_to_pte(r) ((r).pte) -#define __rpte_to_hidx(r,index) (pte_val(__rpte_to_pte(r)) >> H_PAGE_F_GIX_SHIFT) + +static inline unsigned long __rpte_to_hidx(real_pte_t rpte, unsigned long index) +{ + return pte_val(__rpte_to_pte(rpte)) >> H_PAGE_F_GIX_SHIFT; +} #define pte_iterate_hashed_subpages(rpte, psize, va, index, shift) \ do { \ diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c index af97fbb3c257..f84e0337cc02 100644 --- a/arch/powerpc/lib/code-patching.c +++ b/arch/powerpc/lib/code-patching.c @@ -108,7 +108,7 @@ static int text_area_cpu_up(unsigned int cpu) unsigned long addr; int err; - area = get_vm_area(PAGE_SIZE, VM_ALLOC); + area = get_vm_area(PAGE_SIZE, 0); if (!area) { WARN_ONCE(1, "Failed to create text area for cpu %d\n", cpu); @@ -493,7 +493,9 @@ static int __do_patch_instructions_mm(u32 *addr, u32 *code, size_t len, bool rep orig_mm = start_using_temp_mm(patching_mm); + kasan_disable_current(); err = __patch_instructions(patch_addr, code, len, repeat_instr); + kasan_enable_current(); /* context synchronisation performed by __patch_instructions */ stop_using_temp_mm(patching_mm, orig_mm); diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index d6beec5292a0..44f01a4bc810 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -740,7 +740,6 @@ CONFIG_IMA=y CONFIG_IMA_DEFAULT_HASH_SHA256=y CONFIG_IMA_WRITE_POLICY=y CONFIG_IMA_APPRAISE=y -CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor" CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_CRYPTO_USER=m # CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 8cfbfb10bba8..8bcd37edd3c9 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -725,7 +725,6 @@ CONFIG_IMA=y CONFIG_IMA_DEFAULT_HASH_SHA256=y CONFIG_IMA_WRITE_POLICY=y CONFIG_IMA_APPRAISE=y -CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor" CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_CRYPTO_FIPS=y CONFIG_CRYPTO_USER=m diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index bcbaa069de96..853b2326a171 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -62,7 +62,6 @@ CONFIG_ZFCP=y # CONFIG_INOTIFY_USER is not set # CONFIG_MISC_FILESYSTEMS is not set # CONFIG_NETWORK_FILESYSTEMS is not set -CONFIG_LSM="yama,loadpin,safesetid,integrity" # CONFIG_ZLIB_DFLTCC is not set CONFIG_XZ_DEC_MICROLZMA=y CONFIG_PRINTK_TIME=y diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h index d5125296ade2..a5ca0a947691 100644 --- a/arch/s390/include/asm/bitops.h +++ b/arch/s390/include/asm/bitops.h @@ -53,7 +53,11 @@ static __always_inline bool arch_test_bit(unsigned long nr, const volatile unsig unsigned long mask; int cc; - if (__builtin_constant_p(nr)) { + /* + * With CONFIG_PROFILE_ALL_BRANCHES enabled gcc fails to + * handle __builtin_constant_p() in some cases. + */ + if (!IS_ENABLED(CONFIG_PROFILE_ALL_BRANCHES) && __builtin_constant_p(nr)) { addr = (const volatile unsigned char *)ptr; addr += (nr ^ (BITS_PER_LONG - BITS_PER_BYTE)) / BITS_PER_BYTE; mask = 1UL << (nr & (BITS_PER_BYTE - 1)); diff --git a/arch/s390/pci/pci_bus.c b/arch/s390/pci/pci_bus.c index 857afbc4828f..39a481ec4a40 100644 --- a/arch/s390/pci/pci_bus.c +++ b/arch/s390/pci/pci_bus.c @@ -331,6 +331,17 @@ error: return rc; } +static bool zpci_bus_is_isolated_vf(struct zpci_bus *zbus, struct zpci_dev *zdev) +{ + struct pci_dev *pdev; + + pdev = zpci_iov_find_parent_pf(zbus, zdev); + if (!pdev) + return true; + pci_dev_put(pdev); + return false; +} + int zpci_bus_device_register(struct zpci_dev *zdev, struct pci_ops *ops) { bool topo_is_tid = zdev->tid_avail; @@ -345,6 +356,15 @@ int zpci_bus_device_register(struct zpci_dev *zdev, struct pci_ops *ops) topo = topo_is_tid ? zdev->tid : zdev->pchid; zbus = zpci_bus_get(topo, topo_is_tid); + /* + * An isolated VF gets its own domain/bus even if there exists + * a matching domain/bus already + */ + if (zbus && zpci_bus_is_isolated_vf(zbus, zdev)) { + zpci_bus_put(zbus); + zbus = NULL; + } + if (!zbus) { zbus = zpci_bus_alloc(topo, topo_is_tid); if (!zbus) diff --git a/arch/s390/pci/pci_iov.c b/arch/s390/pci/pci_iov.c index ead062bf2b41..191e56a623f6 100644 --- a/arch/s390/pci/pci_iov.c +++ b/arch/s390/pci/pci_iov.c @@ -60,18 +60,35 @@ static int zpci_iov_link_virtfn(struct pci_dev *pdev, struct pci_dev *virtfn, in return 0; } -int zpci_iov_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *virtfn, int vfn) +/** + * zpci_iov_find_parent_pf - Find the parent PF, if any, of the given function + * @zbus: The bus that the PCI function is on, or would be added on + * @zdev: The PCI function + * + * Finds the parent PF, if it exists and is configured, of the given PCI function + * and increments its refcount. Th PF is searched for on the provided bus so the + * caller has to ensure that this is the correct bus to search. This function may + * be used before adding the PCI function to a zbus. + * + * Return: Pointer to the struct pci_dev of the parent PF or NULL if it not + * found. If the function is not a VF or has no RequesterID information, + * NULL is returned as well. + */ +struct pci_dev *zpci_iov_find_parent_pf(struct zpci_bus *zbus, struct zpci_dev *zdev) { - int i, cand_devfn; - struct zpci_dev *zdev; + int i, vfid, devfn, cand_devfn; struct pci_dev *pdev; - int vfid = vfn - 1; /* Linux' vfid's start at 0 vfn at 1*/ - int rc = 0; if (!zbus->multifunction) - return 0; - - /* If the parent PF for the given VF is also configured in the + return NULL; + /* Non-VFs and VFs without RID available don't have a parent */ + if (!zdev->vfn || !zdev->rid_available) + return NULL; + /* Linux vfid starts at 0 vfn at 1 */ + vfid = zdev->vfn - 1; + devfn = zdev->rid & ZPCI_RID_MASK_DEVFN; + /* + * If the parent PF for the given VF is also configured in the * instance, it must be on the same zbus. * We can then identify the parent PF by checking what * devfn the VF would have if it belonged to that PF using the PF's @@ -85,15 +102,26 @@ int zpci_iov_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *virtfn, int vfn if (!pdev) continue; cand_devfn = pci_iov_virtfn_devfn(pdev, vfid); - if (cand_devfn == virtfn->devfn) { - rc = zpci_iov_link_virtfn(pdev, virtfn, vfid); - /* balance pci_get_slot() */ - pci_dev_put(pdev); - break; - } + if (cand_devfn == devfn) + return pdev; /* balance pci_get_slot() */ pci_dev_put(pdev); } } + return NULL; +} + +int zpci_iov_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *virtfn, int vfn) +{ + struct zpci_dev *zdev = to_zpci(virtfn); + struct pci_dev *pdev_pf; + int rc = 0; + + pdev_pf = zpci_iov_find_parent_pf(zbus, zdev); + if (pdev_pf) { + /* Linux' vfids start at 0 while zdev->vfn starts at 1 */ + rc = zpci_iov_link_virtfn(pdev_pf, virtfn, zdev->vfn - 1); + pci_dev_put(pdev_pf); + } return rc; } diff --git a/arch/s390/pci/pci_iov.h b/arch/s390/pci/pci_iov.h index e3fa4e77fc86..d2c2793eb0f3 100644 --- a/arch/s390/pci/pci_iov.h +++ b/arch/s390/pci/pci_iov.h @@ -19,6 +19,8 @@ void zpci_iov_map_resources(struct pci_dev *pdev); int zpci_iov_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *virtfn, int vfn); +struct pci_dev *zpci_iov_find_parent_pf(struct zpci_bus *zbus, struct zpci_dev *zdev); + #else /* CONFIG_PCI_IOV */ static inline void zpci_iov_remove_virtfn(struct pci_dev *pdev, int vfn) {} @@ -28,5 +30,10 @@ static inline int zpci_iov_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *v { return 0; } + +static inline struct pci_dev *zpci_iov_find_parent_pf(struct zpci_bus *zbus, struct zpci_dev *zdev) +{ + return NULL; +} #endif /* CONFIG_PCI_IOV */ #endif /* __S390_PCI_IOV_h */ diff --git a/arch/um/drivers/virt-pci.c b/arch/um/drivers/virt-pci.c index 744e7f31e8ef..dd5580f975cc 100644 --- a/arch/um/drivers/virt-pci.c +++ b/arch/um/drivers/virt-pci.c @@ -25,8 +25,10 @@ #define MAX_IRQ_MSG_SIZE (sizeof(struct virtio_pcidev_msg) + sizeof(u32)) #define NUM_IRQ_MSGS 10 -#define HANDLE_NO_FREE(ptr) ((void *)((unsigned long)(ptr) | 1)) -#define HANDLE_IS_NO_FREE(ptr) ((unsigned long)(ptr) & 1) +struct um_pci_message_buffer { + struct virtio_pcidev_msg hdr; + u8 data[8]; +}; struct um_pci_device { struct virtio_device *vdev; @@ -36,6 +38,11 @@ struct um_pci_device { struct virtqueue *cmd_vq, *irq_vq; +#define UM_PCI_WRITE_BUFS 20 + struct um_pci_message_buffer bufs[UM_PCI_WRITE_BUFS + 1]; + void *extra_ptrs[UM_PCI_WRITE_BUFS + 1]; + DECLARE_BITMAP(used_bufs, UM_PCI_WRITE_BUFS); + #define UM_PCI_STAT_WAITING 0 unsigned long status; @@ -61,12 +68,40 @@ static unsigned long um_pci_msi_used[BITS_TO_LONGS(MAX_MSI_VECTORS)]; static unsigned int um_pci_max_delay_us = 40000; module_param_named(max_delay_us, um_pci_max_delay_us, uint, 0644); -struct um_pci_message_buffer { - struct virtio_pcidev_msg hdr; - u8 data[8]; -}; +static int um_pci_get_buf(struct um_pci_device *dev, bool *posted) +{ + int i; + + for (i = 0; i < UM_PCI_WRITE_BUFS; i++) { + if (!test_and_set_bit(i, dev->used_bufs)) + return i; + } -static struct um_pci_message_buffer __percpu *um_pci_msg_bufs; + *posted = false; + return UM_PCI_WRITE_BUFS; +} + +static void um_pci_free_buf(struct um_pci_device *dev, void *buf) +{ + int i; + + if (buf == &dev->bufs[UM_PCI_WRITE_BUFS]) { + kfree(dev->extra_ptrs[UM_PCI_WRITE_BUFS]); + dev->extra_ptrs[UM_PCI_WRITE_BUFS] = NULL; + return; + } + + for (i = 0; i < UM_PCI_WRITE_BUFS; i++) { + if (buf == &dev->bufs[i]) { + kfree(dev->extra_ptrs[i]); + dev->extra_ptrs[i] = NULL; + WARN_ON(!test_and_clear_bit(i, dev->used_bufs)); + return; + } + } + + WARN_ON(1); +} static int um_pci_send_cmd(struct um_pci_device *dev, struct virtio_pcidev_msg *cmd, @@ -82,7 +117,9 @@ static int um_pci_send_cmd(struct um_pci_device *dev, }; struct um_pci_message_buffer *buf; int delay_count = 0; + bool bounce_out; int ret, len; + int buf_idx; bool posted; if (WARN_ON(cmd_size < sizeof(*cmd) || cmd_size > sizeof(*buf))) @@ -101,26 +138,28 @@ static int um_pci_send_cmd(struct um_pci_device *dev, break; } - buf = get_cpu_var(um_pci_msg_bufs); - if (buf) - memcpy(buf, cmd, cmd_size); + bounce_out = !posted && cmd_size <= sizeof(*cmd) && + out && out_size <= sizeof(buf->data); - if (posted) { - u8 *ncmd = kmalloc(cmd_size + extra_size, GFP_ATOMIC); - - if (ncmd) { - memcpy(ncmd, cmd, cmd_size); - if (extra) - memcpy(ncmd + cmd_size, extra, extra_size); - cmd = (void *)ncmd; - cmd_size += extra_size; - extra = NULL; - extra_size = 0; - } else { - /* try without allocating memory */ - posted = false; - cmd = (void *)buf; + buf_idx = um_pci_get_buf(dev, &posted); + buf = &dev->bufs[buf_idx]; + memcpy(buf, cmd, cmd_size); + + if (posted && extra && extra_size > sizeof(buf) - cmd_size) { + dev->extra_ptrs[buf_idx] = kmemdup(extra, extra_size, + GFP_ATOMIC); + + if (!dev->extra_ptrs[buf_idx]) { + um_pci_free_buf(dev, buf); + return -ENOMEM; } + extra = dev->extra_ptrs[buf_idx]; + } else if (extra && extra_size <= sizeof(buf) - cmd_size) { + memcpy((u8 *)buf + cmd_size, extra, extra_size); + cmd_size += extra_size; + extra_size = 0; + extra = NULL; + cmd = (void *)buf; } else { cmd = (void *)buf; } @@ -128,39 +167,40 @@ static int um_pci_send_cmd(struct um_pci_device *dev, sg_init_one(&out_sg, cmd, cmd_size); if (extra) sg_init_one(&extra_sg, extra, extra_size); - if (out) + /* allow stack for small buffers */ + if (bounce_out) + sg_init_one(&in_sg, buf->data, out_size); + else if (out) sg_init_one(&in_sg, out, out_size); /* add to internal virtio queue */ ret = virtqueue_add_sgs(dev->cmd_vq, sgs_list, extra ? 2 : 1, out ? 1 : 0, - posted ? cmd : HANDLE_NO_FREE(cmd), - GFP_ATOMIC); + cmd, GFP_ATOMIC); if (ret) { - if (posted) - kfree(cmd); - goto out; + um_pci_free_buf(dev, buf); + return ret; } if (posted) { virtqueue_kick(dev->cmd_vq); - ret = 0; - goto out; + return 0; } /* kick and poll for getting a response on the queue */ set_bit(UM_PCI_STAT_WAITING, &dev->status); virtqueue_kick(dev->cmd_vq); + ret = 0; while (1) { void *completed = virtqueue_get_buf(dev->cmd_vq, &len); - if (completed == HANDLE_NO_FREE(cmd)) + if (completed == buf) break; - if (completed && !HANDLE_IS_NO_FREE(completed)) - kfree(completed); + if (completed) + um_pci_free_buf(dev, completed); if (WARN_ONCE(virtqueue_is_broken(dev->cmd_vq) || ++delay_count > um_pci_max_delay_us, @@ -172,8 +212,11 @@ static int um_pci_send_cmd(struct um_pci_device *dev, } clear_bit(UM_PCI_STAT_WAITING, &dev->status); -out: - put_cpu_var(um_pci_msg_bufs); + if (bounce_out) + memcpy(out, buf->data, out_size); + + um_pci_free_buf(dev, buf); + return ret; } @@ -187,20 +230,13 @@ static unsigned long um_pci_cfgspace_read(void *priv, unsigned int offset, .size = size, .addr = offset, }; - /* buf->data is maximum size - we may only use parts of it */ - struct um_pci_message_buffer *buf; - u8 *data; - unsigned long ret = ULONG_MAX; - size_t bytes = sizeof(buf->data); + /* max 8, we might not use it all */ + u8 data[8]; if (!dev) return ULONG_MAX; - buf = get_cpu_var(um_pci_msg_bufs); - data = buf->data; - - if (buf) - memset(data, 0xff, bytes); + memset(data, 0xff, sizeof(data)); switch (size) { case 1: @@ -212,34 +248,26 @@ static unsigned long um_pci_cfgspace_read(void *priv, unsigned int offset, break; default: WARN(1, "invalid config space read size %d\n", size); - goto out; + return ULONG_MAX; } - if (um_pci_send_cmd(dev, &hdr, sizeof(hdr), NULL, 0, data, bytes)) - goto out; + if (um_pci_send_cmd(dev, &hdr, sizeof(hdr), NULL, 0, data, size)) + return ULONG_MAX; switch (size) { case 1: - ret = data[0]; - break; + return data[0]; case 2: - ret = le16_to_cpup((void *)data); - break; + return le16_to_cpup((void *)data); case 4: - ret = le32_to_cpup((void *)data); - break; + return le32_to_cpup((void *)data); #ifdef CONFIG_64BIT case 8: - ret = le64_to_cpup((void *)data); - break; + return le64_to_cpup((void *)data); #endif default: - break; + return ULONG_MAX; } - -out: - put_cpu_var(um_pci_msg_bufs); - return ret; } static void um_pci_cfgspace_write(void *priv, unsigned int offset, int size, @@ -312,13 +340,8 @@ static void um_pci_bar_copy_from(void *priv, void *buffer, static unsigned long um_pci_bar_read(void *priv, unsigned int offset, int size) { - /* buf->data is maximum size - we may only use parts of it */ - struct um_pci_message_buffer *buf; - u8 *data; - unsigned long ret = ULONG_MAX; - - buf = get_cpu_var(um_pci_msg_bufs); - data = buf->data; + /* 8 is maximum size - we may only use parts of it */ + u8 data[8]; switch (size) { case 1: @@ -330,33 +353,25 @@ static unsigned long um_pci_bar_read(void *priv, unsigned int offset, break; default: WARN(1, "invalid config space read size %d\n", size); - goto out; + return ULONG_MAX; } um_pci_bar_copy_from(priv, data, offset, size); switch (size) { case 1: - ret = data[0]; - break; + return data[0]; case 2: - ret = le16_to_cpup((void *)data); - break; + return le16_to_cpup((void *)data); case 4: - ret = le32_to_cpup((void *)data); - break; + return le32_to_cpup((void *)data); #ifdef CONFIG_64BIT case 8: - ret = le64_to_cpup((void *)data); - break; + return le64_to_cpup((void *)data); #endif default: - break; + return ULONG_MAX; } - -out: - put_cpu_var(um_pci_msg_bufs); - return ret; } static void um_pci_bar_copy_to(void *priv, unsigned int offset, @@ -523,11 +538,8 @@ static void um_pci_cmd_vq_cb(struct virtqueue *vq) if (test_bit(UM_PCI_STAT_WAITING, &dev->status)) return; - while ((cmd = virtqueue_get_buf(vq, &len))) { - if (WARN_ON(HANDLE_IS_NO_FREE(cmd))) - continue; - kfree(cmd); - } + while ((cmd = virtqueue_get_buf(vq, &len))) + um_pci_free_buf(dev, cmd); } static void um_pci_irq_vq_cb(struct virtqueue *vq) @@ -1006,10 +1018,6 @@ static int __init um_pci_init(void) "No virtio device ID configured for PCI - no PCI support\n")) return 0; - um_pci_msg_bufs = alloc_percpu(struct um_pci_message_buffer); - if (!um_pci_msg_bufs) - return -ENOMEM; - bridge = pci_alloc_host_bridge(0); if (!bridge) { err = -ENOMEM; @@ -1070,7 +1078,6 @@ free: pci_free_resource_list(&bridge->windows); pci_free_host_bridge(bridge); } - free_percpu(um_pci_msg_bufs); return err; } module_init(um_pci_init); @@ -1082,6 +1089,5 @@ static void __exit um_pci_exit(void) irq_domain_remove(um_pci_inner_domain); pci_free_resource_list(&bridge->windows); pci_free_host_bridge(bridge); - free_percpu(um_pci_msg_bufs); } module_exit(um_pci_exit); diff --git a/arch/um/drivers/virtio_uml.c b/arch/um/drivers/virtio_uml.c index 65df43fa9be5..ad8d78fb1d9a 100644 --- a/arch/um/drivers/virtio_uml.c +++ b/arch/um/drivers/virtio_uml.c @@ -52,7 +52,7 @@ struct virtio_uml_device { struct platform_device *pdev; struct virtio_uml_platform_data *pdata; - spinlock_t sock_lock; + raw_spinlock_t sock_lock; int sock, req_fd, irq; u64 features; u64 protocol_features; @@ -246,7 +246,7 @@ static int vhost_user_send(struct virtio_uml_device *vu_dev, if (request_ack) msg->header.flags |= VHOST_USER_FLAG_NEED_REPLY; - spin_lock_irqsave(&vu_dev->sock_lock, flags); + raw_spin_lock_irqsave(&vu_dev->sock_lock, flags); rc = full_sendmsg_fds(vu_dev->sock, msg, size, fds, num_fds); if (rc < 0) goto out; @@ -266,7 +266,7 @@ static int vhost_user_send(struct virtio_uml_device *vu_dev, } out: - spin_unlock_irqrestore(&vu_dev->sock_lock, flags); + raw_spin_unlock_irqrestore(&vu_dev->sock_lock, flags); return rc; } @@ -1239,7 +1239,7 @@ static int virtio_uml_probe(struct platform_device *pdev) goto error_free; vu_dev->sock = rc; - spin_lock_init(&vu_dev->sock_lock); + raw_spin_lock_init(&vu_dev->sock_lock); rc = vhost_user_init(vu_dev); if (rc) diff --git a/arch/um/kernel/irq.c b/arch/um/kernel/irq.c index 338450741aac..a4991746f5ea 100644 --- a/arch/um/kernel/irq.c +++ b/arch/um/kernel/irq.c @@ -52,7 +52,7 @@ struct irq_entry { bool sigio_workaround; }; -static DEFINE_SPINLOCK(irq_lock); +static DEFINE_RAW_SPINLOCK(irq_lock); static LIST_HEAD(active_fds); static DECLARE_BITMAP(irqs_allocated, UM_LAST_SIGNAL_IRQ); static bool irqs_suspended; @@ -257,7 +257,7 @@ static struct irq_entry *get_irq_entry_by_fd(int fd) return NULL; } -static void free_irq_entry(struct irq_entry *to_free, bool remove) +static void remove_irq_entry(struct irq_entry *to_free, bool remove) { if (!to_free) return; @@ -265,7 +265,6 @@ static void free_irq_entry(struct irq_entry *to_free, bool remove) if (remove) os_del_epoll_fd(to_free->fd); list_del(&to_free->list); - kfree(to_free); } static bool update_irq_entry(struct irq_entry *entry) @@ -286,17 +285,19 @@ static bool update_irq_entry(struct irq_entry *entry) return false; } -static void update_or_free_irq_entry(struct irq_entry *entry) +static struct irq_entry *update_or_remove_irq_entry(struct irq_entry *entry) { - if (!update_irq_entry(entry)) - free_irq_entry(entry, false); + if (update_irq_entry(entry)) + return NULL; + remove_irq_entry(entry, false); + return entry; } static int activate_fd(int irq, int fd, enum um_irq_type type, void *dev_id, void (*timetravel_handler)(int, int, void *, struct time_travel_event *)) { - struct irq_entry *irq_entry; + struct irq_entry *irq_entry, *to_free = NULL; int err, events = os_event_mask(type); unsigned long flags; @@ -304,9 +305,10 @@ static int activate_fd(int irq, int fd, enum um_irq_type type, void *dev_id, if (err < 0) goto out; - spin_lock_irqsave(&irq_lock, flags); + raw_spin_lock_irqsave(&irq_lock, flags); irq_entry = get_irq_entry_by_fd(fd); if (irq_entry) { +already: /* cannot register the same FD twice with the same type */ if (WARN_ON(irq_entry->reg[type].events)) { err = -EALREADY; @@ -316,11 +318,22 @@ static int activate_fd(int irq, int fd, enum um_irq_type type, void *dev_id, /* temporarily disable to avoid IRQ-side locking */ os_del_epoll_fd(fd); } else { - irq_entry = kzalloc(sizeof(*irq_entry), GFP_ATOMIC); - if (!irq_entry) { - err = -ENOMEM; - goto out_unlock; + struct irq_entry *new; + + /* don't restore interrupts */ + raw_spin_unlock(&irq_lock); + new = kzalloc(sizeof(*irq_entry), GFP_ATOMIC); + if (!new) { + local_irq_restore(flags); + return -ENOMEM; } + raw_spin_lock(&irq_lock); + irq_entry = get_irq_entry_by_fd(fd); + if (irq_entry) { + to_free = new; + goto already; + } + irq_entry = new; irq_entry->fd = fd; list_add_tail(&irq_entry->list, &active_fds); maybe_sigio_broken(fd); @@ -339,12 +352,11 @@ static int activate_fd(int irq, int fd, enum um_irq_type type, void *dev_id, #endif WARN_ON(!update_irq_entry(irq_entry)); - spin_unlock_irqrestore(&irq_lock, flags); - - return 0; + err = 0; out_unlock: - spin_unlock_irqrestore(&irq_lock, flags); + raw_spin_unlock_irqrestore(&irq_lock, flags); out: + kfree(to_free); return err; } @@ -358,19 +370,20 @@ void free_irq_by_fd(int fd) struct irq_entry *to_free; unsigned long flags; - spin_lock_irqsave(&irq_lock, flags); + raw_spin_lock_irqsave(&irq_lock, flags); to_free = get_irq_entry_by_fd(fd); - free_irq_entry(to_free, true); - spin_unlock_irqrestore(&irq_lock, flags); + remove_irq_entry(to_free, true); + raw_spin_unlock_irqrestore(&irq_lock, flags); + kfree(to_free); } EXPORT_SYMBOL(free_irq_by_fd); static void free_irq_by_irq_and_dev(unsigned int irq, void *dev) { - struct irq_entry *entry; + struct irq_entry *entry, *to_free = NULL; unsigned long flags; - spin_lock_irqsave(&irq_lock, flags); + raw_spin_lock_irqsave(&irq_lock, flags); list_for_each_entry(entry, &active_fds, list) { enum um_irq_type i; @@ -386,12 +399,13 @@ static void free_irq_by_irq_and_dev(unsigned int irq, void *dev) os_del_epoll_fd(entry->fd); reg->events = 0; - update_or_free_irq_entry(entry); + to_free = update_or_remove_irq_entry(entry); goto out; } } out: - spin_unlock_irqrestore(&irq_lock, flags); + raw_spin_unlock_irqrestore(&irq_lock, flags); + kfree(to_free); } void deactivate_fd(int fd, int irqnum) @@ -402,7 +416,7 @@ void deactivate_fd(int fd, int irqnum) os_del_epoll_fd(fd); - spin_lock_irqsave(&irq_lock, flags); + raw_spin_lock_irqsave(&irq_lock, flags); entry = get_irq_entry_by_fd(fd); if (!entry) goto out; @@ -414,9 +428,10 @@ void deactivate_fd(int fd, int irqnum) entry->reg[i].events = 0; } - update_or_free_irq_entry(entry); + entry = update_or_remove_irq_entry(entry); out: - spin_unlock_irqrestore(&irq_lock, flags); + raw_spin_unlock_irqrestore(&irq_lock, flags); + kfree(entry); ignore_sigio_fd(fd); } @@ -546,7 +561,7 @@ void um_irqs_suspend(void) irqs_suspended = true; - spin_lock_irqsave(&irq_lock, flags); + raw_spin_lock_irqsave(&irq_lock, flags); list_for_each_entry(entry, &active_fds, list) { enum um_irq_type t; bool clear = true; @@ -579,7 +594,7 @@ void um_irqs_suspend(void) !__ignore_sigio_fd(entry->fd); } } - spin_unlock_irqrestore(&irq_lock, flags); + raw_spin_unlock_irqrestore(&irq_lock, flags); } void um_irqs_resume(void) @@ -588,7 +603,7 @@ void um_irqs_resume(void) unsigned long flags; - spin_lock_irqsave(&irq_lock, flags); + raw_spin_lock_irqsave(&irq_lock, flags); list_for_each_entry(entry, &active_fds, list) { if (entry->suspended) { int err = os_set_fd_async(entry->fd); @@ -602,7 +617,7 @@ void um_irqs_resume(void) } } } - spin_unlock_irqrestore(&irq_lock, flags); + raw_spin_unlock_irqrestore(&irq_lock, flags); irqs_suspended = false; send_sigio_to_self(); @@ -613,7 +628,7 @@ static int normal_irq_set_wake(struct irq_data *d, unsigned int on) struct irq_entry *entry; unsigned long flags; - spin_lock_irqsave(&irq_lock, flags); + raw_spin_lock_irqsave(&irq_lock, flags); list_for_each_entry(entry, &active_fds, list) { enum um_irq_type t; @@ -628,7 +643,7 @@ static int normal_irq_set_wake(struct irq_data *d, unsigned int on) } } unlock: - spin_unlock_irqrestore(&irq_lock, flags); + raw_spin_unlock_irqrestore(&irq_lock, flags); return 0; } #else diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index e5a2d4d897e0..0cd6fad3d908 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -191,7 +191,15 @@ void initial_thread_cb(void (*proc)(void *), void *arg) int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { - memcpy(dst, src, arch_task_struct_size); + /* init_task is not dynamically sized (missing FPU state) */ + if (unlikely(src == &init_task)) { + memcpy(dst, src, sizeof(init_task)); + memset((void *)dst + sizeof(init_task), 0, + arch_task_struct_size - sizeof(init_task)); + } else { + memcpy(dst, src, arch_task_struct_size); + } + return 0; } diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c index f683cfc9e51a..e2f8f156402f 100644 --- a/arch/um/os-Linux/skas/process.c +++ b/arch/um/os-Linux/skas/process.c @@ -181,6 +181,10 @@ extern char __syscall_stub_start[]; static int stub_exe_fd; +#ifndef CLOSE_RANGE_CLOEXEC +#define CLOSE_RANGE_CLOEXEC (1U << 2) +#endif + static int userspace_tramp(void *stack) { char *const argv[] = { "uml-userspace", NULL }; @@ -202,8 +206,12 @@ static int userspace_tramp(void *stack) init_data.stub_data_fd = phys_mapping(uml_to_phys(stack), &offset); init_data.stub_data_offset = MMAP_OFFSET(offset); - /* Set CLOEXEC on all FDs and then unset on all memory related FDs */ - close_range(0, ~0U, CLOSE_RANGE_CLOEXEC); + /* + * Avoid leaking unneeded FDs to the stub by setting CLOEXEC on all FDs + * and then unsetting it on all memory related FDs. + * This is not strictly necessary from a safety perspective. + */ + syscall(__NR_close_range, 0, ~0U, CLOSE_RANGE_CLOEXEC); fcntl(init_data.stub_data_fd, F_SETFD, 0); for (iomem = iomem_regions; iomem; iomem = iomem->next) @@ -224,7 +232,9 @@ static int userspace_tramp(void *stack) if (ret != sizeof(init_data)) exit(4); - execveat(stub_exe_fd, "", argv, NULL, AT_EMPTY_PATH); + /* Raw execveat for compatibility with older libc versions */ + syscall(__NR_execveat, stub_exe_fd, (unsigned long)"", + (unsigned long)argv, NULL, AT_EMPTY_PATH); exit(5); } diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 7601196d1d18..e86333eee266 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -4905,20 +4905,22 @@ static inline bool intel_pmu_broken_perf_cap(void) static void update_pmu_cap(struct x86_hybrid_pmu *pmu) { - unsigned int sub_bitmaps, eax, ebx, ecx, edx; + unsigned int cntr, fixed_cntr, ecx, edx; + union cpuid35_eax eax; + union cpuid35_ebx ebx; - cpuid(ARCH_PERFMON_EXT_LEAF, &sub_bitmaps, &ebx, &ecx, &edx); + cpuid(ARCH_PERFMON_EXT_LEAF, &eax.full, &ebx.full, &ecx, &edx); - if (ebx & ARCH_PERFMON_EXT_UMASK2) + if (ebx.split.umask2) pmu->config_mask |= ARCH_PERFMON_EVENTSEL_UMASK2; - if (ebx & ARCH_PERFMON_EXT_EQ) + if (ebx.split.eq) pmu->config_mask |= ARCH_PERFMON_EVENTSEL_EQ; - if (sub_bitmaps & ARCH_PERFMON_NUM_COUNTER_LEAF_BIT) { + if (eax.split.cntr_subleaf) { cpuid_count(ARCH_PERFMON_EXT_LEAF, ARCH_PERFMON_NUM_COUNTER_LEAF, - &eax, &ebx, &ecx, &edx); - pmu->cntr_mask64 = eax; - pmu->fixed_cntr_mask64 = ebx; + &cntr, &fixed_cntr, &ecx, &edx); + pmu->cntr_mask64 = cntr; + pmu->fixed_cntr_mask64 = fixed_cntr; } if (!intel_pmu_broken_perf_cap()) { @@ -4941,11 +4943,6 @@ static void intel_pmu_check_hybrid_pmus(struct x86_hybrid_pmu *pmu) else pmu->intel_ctrl &= ~(1ULL << GLOBAL_CTRL_EN_PERF_METRICS); - if (pmu->intel_cap.pebs_output_pt_available) - pmu->pmu.capabilities |= PERF_PMU_CAP_AUX_OUTPUT; - else - pmu->pmu.capabilities &= ~PERF_PMU_CAP_AUX_OUTPUT; - intel_pmu_check_event_constraints(pmu->event_constraints, pmu->cntr_mask64, pmu->fixed_cntr_mask64, @@ -5023,9 +5020,6 @@ static bool init_hybrid_pmu(int cpu) pr_info("%s PMU driver: ", pmu->name); - if (pmu->intel_cap.pebs_output_pt_available) - pr_cont("PEBS-via-PT "); - pr_cont("\n"); x86_pmu_show_pmu_cap(&pmu->pmu); @@ -5048,8 +5042,11 @@ static void intel_pmu_cpu_starting(int cpu) init_debug_store_on_cpu(cpu); /* - * Deal with CPUs that don't clear their LBRs on power-up. + * Deal with CPUs that don't clear their LBRs on power-up, and that may + * even boot with LBRs enabled. */ + if (!static_cpu_has(X86_FEATURE_ARCH_LBR) && x86_pmu.lbr_nr) + msr_clear_bit(MSR_IA32_DEBUGCTLMSR, DEBUGCTLMSR_LBR_BIT); intel_pmu_lbr_reset(); cpuc->lbr_sel = NULL; @@ -6370,11 +6367,9 @@ static __always_inline int intel_pmu_init_hybrid(enum hybrid_pmu_type pmus) pmu->intel_cap.capabilities = x86_pmu.intel_cap.capabilities; if (pmu->pmu_type & hybrid_small_tiny) { pmu->intel_cap.perf_metrics = 0; - pmu->intel_cap.pebs_output_pt_available = 1; pmu->mid_ack = true; } else if (pmu->pmu_type & hybrid_big) { pmu->intel_cap.perf_metrics = 1; - pmu->intel_cap.pebs_output_pt_available = 0; pmu->late_ack = true; } } diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index ba74e1198328..c2e2eae7309c 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -2578,7 +2578,15 @@ void __init intel_ds_init(void) } pr_cont("PEBS fmt4%c%s, ", pebs_type, pebs_qual); - if (!is_hybrid() && x86_pmu.intel_cap.pebs_output_pt_available) { + /* + * The PEBS-via-PT is not supported on hybrid platforms, + * because not all CPUs of a hybrid machine support it. + * The global x86_pmu.intel_cap, which only contains the + * common capabilities, is used to check the availability + * of the feature. The per-PMU pebs_output_pt_available + * in a hybrid machine should be ignored. + */ + if (x86_pmu.intel_cap.pebs_output_pt_available) { pr_cont("PEBS-via-PT, "); x86_get_pmu(smp_processor_id())->capabilities |= PERF_PMU_CAP_AUX_OUTPUT; } diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c index d3bb3865c1b1..4952faf03e82 100644 --- a/arch/x86/events/rapl.c +++ b/arch/x86/events/rapl.c @@ -370,6 +370,10 @@ static int rapl_pmu_event_init(struct perf_event *event) unsigned int rapl_pmu_idx; struct rapl_pmus *rapl_pmus; + /* only look at RAPL events */ + if (event->attr.type != event->pmu->type) + return -ENOENT; + /* unsupported modes and filters */ if (event->attr.sample_period) /* no sampling */ return -EINVAL; @@ -387,10 +391,6 @@ static int rapl_pmu_event_init(struct perf_event *event) rapl_pmus_scope = rapl_pmus->pmu.scope; if (rapl_pmus_scope == PERF_PMU_SCOPE_PKG || rapl_pmus_scope == PERF_PMU_SCOPE_DIE) { - /* only look at RAPL package events */ - if (event->attr.type != rapl_pmus_pkg->pmu.type) - return -ENOENT; - cfg = array_index_nospec((long)cfg, NR_RAPL_PKG_DOMAINS + 1); if (!cfg || cfg >= NR_RAPL_PKG_DOMAINS + 1) return -EINVAL; @@ -398,10 +398,6 @@ static int rapl_pmu_event_init(struct perf_event *event) bit = cfg - 1; event->hw.event_base = rapl_model->rapl_pkg_msrs[bit].msr; } else if (rapl_pmus_scope == PERF_PMU_SCOPE_CORE) { - /* only look at RAPL core events */ - if (event->attr.type != rapl_pmus_core->pmu.type) - return -ENOENT; - cfg = array_index_nospec((long)cfg, NR_RAPL_CORE_DOMAINS + 1); if (!cfg || cfg >= NR_RAPL_PKG_DOMAINS + 1) return -EINVAL; diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index c35550581da0..823c0434bbad 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -48,6 +48,7 @@ KVM_X86_OP(set_idt) KVM_X86_OP(get_gdt) KVM_X86_OP(set_gdt) KVM_X86_OP(sync_dirty_debug_regs) +KVM_X86_OP(set_dr6) KVM_X86_OP(set_dr7) KVM_X86_OP(cache_reg) KVM_X86_OP(get_rflags) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index b15cde0a9b5c..0b7af5902ff7 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1696,6 +1696,7 @@ struct kvm_x86_ops { void (*get_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void (*set_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void (*sync_dirty_debug_regs)(struct kvm_vcpu *vcpu); + void (*set_dr6)(struct kvm_vcpu *vcpu, unsigned long value); void (*set_dr7)(struct kvm_vcpu *vcpu, unsigned long value); void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg); unsigned long (*get_rflags)(struct kvm_vcpu *vcpu); diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 9a71880eec07..72765b2fe0d8 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -395,7 +395,8 @@ #define MSR_IA32_PASID_VALID BIT_ULL(31) /* DEBUGCTLMSR bits (others vary by model): */ -#define DEBUGCTLMSR_LBR (1UL << 0) /* last branch recording */ +#define DEBUGCTLMSR_LBR_BIT 0 /* last branch recording */ +#define DEBUGCTLMSR_LBR (1UL << DEBUGCTLMSR_LBR_BIT) #define DEBUGCTLMSR_BTF_SHIFT 1 #define DEBUGCTLMSR_BTF (1UL << 1) /* single-step on branches */ #define DEBUGCTLMSR_BUS_LOCK_DETECT (1UL << 2) diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 1ac79f361645..0ba8d20f2d1d 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -188,11 +188,33 @@ union cpuid10_edx { * detection/enumeration details: */ #define ARCH_PERFMON_EXT_LEAF 0x00000023 -#define ARCH_PERFMON_EXT_UMASK2 0x1 -#define ARCH_PERFMON_EXT_EQ 0x2 -#define ARCH_PERFMON_NUM_COUNTER_LEAF_BIT 0x1 #define ARCH_PERFMON_NUM_COUNTER_LEAF 0x1 +union cpuid35_eax { + struct { + unsigned int leaf0:1; + /* Counters Sub-Leaf */ + unsigned int cntr_subleaf:1; + /* Auto Counter Reload Sub-Leaf */ + unsigned int acr_subleaf:1; + /* Events Sub-Leaf */ + unsigned int events_subleaf:1; + unsigned int reserved:28; + } split; + unsigned int full; +}; + +union cpuid35_ebx { + struct { + /* UnitMask2 Supported */ + unsigned int umask2:1; + /* EQ-bit Supported */ + unsigned int eq:1; + unsigned int reserved:30; + } split; + unsigned int full; +}; + /* * Intel Architectural LBR CPUID detection/enumeration details: */ diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h index 5d9685f92e5c..1581246491b5 100644 --- a/arch/x86/include/asm/sev.h +++ b/arch/x86/include/asm/sev.h @@ -531,6 +531,7 @@ static inline void __init snp_secure_tsc_init(void) { } #ifdef CONFIG_KVM_AMD_SEV bool snp_probe_rmptable_info(void); +int snp_rmptable_init(void); int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level); void snp_dump_hva_rmpentry(unsigned long address); int psmash(u64 pfn); @@ -541,6 +542,7 @@ void kdump_sev_callback(void); void snp_fixup_e820_tables(void); #else static inline bool snp_probe_rmptable_info(void) { return false; } +static inline int snp_rmptable_init(void) { return -ENOSYS; } static inline int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level) { return -ENODEV; } static inline void snp_dump_hva_rmpentry(unsigned long address) {} static inline int psmash(u64 pfn) { return -ENODEV; } diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 6a6dd5a84f22..6ebeb6cea6c0 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -2226,6 +2226,9 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) u32 vector; bool all_cpus; + if (!lapic_in_kernel(vcpu)) + return HV_STATUS_INVALID_HYPERCALL_INPUT; + if (hc->code == HVCALL_SEND_IPI) { if (!hc->fast) { if (unlikely(kvm_read_guest(kvm, hc->ingpa, &send_ipi, @@ -2852,7 +2855,8 @@ int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, ent->eax |= HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED; ent->eax |= HV_X64_APIC_ACCESS_RECOMMENDED; ent->eax |= HV_X64_RELAXED_TIMING_RECOMMENDED; - ent->eax |= HV_X64_CLUSTER_IPI_RECOMMENDED; + if (!vcpu || lapic_in_kernel(vcpu)) + ent->eax |= HV_X64_CLUSTER_IPI_RECOMMENDED; ent->eax |= HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED; if (evmcs_ver) ent->eax |= HV_X64_ENLIGHTENED_VMCS_RECOMMENDED; diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 74c20dbb92da..d4ac4a1f8b81 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -5540,7 +5540,7 @@ void kvm_init_shadow_npt_mmu(struct kvm_vcpu *vcpu, unsigned long cr0, union kvm_mmu_page_role root_role; /* NPT requires CR0.PG=1. */ - WARN_ON_ONCE(cpu_role.base.direct); + WARN_ON_ONCE(cpu_role.base.direct || !cpu_role.base.guest_mode); root_role = cpu_role.base; root_role.level = kvm_mmu_get_tdp_level(vcpu); diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index d77b094d9a4d..04c375bf1ac2 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -646,6 +646,11 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm, u32 pause_count12; u32 pause_thresh12; + nested_svm_transition_tlb_flush(vcpu); + + /* Enter Guest-Mode */ + enter_guest_mode(vcpu); + /* * Filled at exit: exit_code, exit_code_hi, exit_info_1, exit_info_2, * exit_int_info, exit_int_info_err, next_rip, insn_len, insn_bytes. @@ -762,11 +767,6 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm, } } - nested_svm_transition_tlb_flush(vcpu); - - /* Enter Guest-Mode */ - enter_guest_mode(vcpu); - /* * Merge guest and host intercepts - must be called with vcpu in * guest-mode to take effect. diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index a2a794c32050..0dbb25442ec1 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2972,6 +2972,16 @@ void __init sev_hardware_setup(void) WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_FLUSHBYASID))) goto out; + /* + * The kernel's initcall infrastructure lacks the ability to express + * dependencies between initcalls, whereas the modules infrastructure + * automatically handles dependencies via symbol loading. Ensure the + * PSP SEV driver is initialized before proceeding if KVM is built-in, + * as the dependency isn't handled by the initcall infrastructure. + */ + if (IS_BUILTIN(CONFIG_KVM_AMD) && sev_module_init()) + goto out; + /* Retrieve SEV CPUID information */ cpuid(0x8000001f, &eax, &ebx, &ecx, &edx); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 7640a84e554a..a713c803a3a3 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1991,11 +1991,11 @@ static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *sd) svm->asid = sd->next_asid++; } -static void svm_set_dr6(struct vcpu_svm *svm, unsigned long value) +static void svm_set_dr6(struct kvm_vcpu *vcpu, unsigned long value) { - struct vmcb *vmcb = svm->vmcb; + struct vmcb *vmcb = to_svm(vcpu)->vmcb; - if (svm->vcpu.arch.guest_state_protected) + if (vcpu->arch.guest_state_protected) return; if (unlikely(value != vmcb->save.dr6)) { @@ -4247,10 +4247,8 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu, * Run with all-zero DR6 unless needed, so that we can get the exact cause * of a #DB. */ - if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) - svm_set_dr6(svm, vcpu->arch.dr6); - else - svm_set_dr6(svm, DR6_ACTIVE_LOW); + if (likely(!(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT))) + svm_set_dr6(vcpu, DR6_ACTIVE_LOW); clgi(); kvm_load_guest_xsave_state(vcpu); @@ -5043,6 +5041,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .set_idt = svm_set_idt, .get_gdt = svm_get_gdt, .set_gdt = svm_set_gdt, + .set_dr6 = svm_set_dr6, .set_dr7 = svm_set_dr7, .sync_dirty_debug_regs = svm_sync_dirty_debug_regs, .cache_reg = svm_cache_reg, diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c index 2427f918e763..43ee9ed11291 100644 --- a/arch/x86/kvm/vmx/main.c +++ b/arch/x86/kvm/vmx/main.c @@ -61,6 +61,7 @@ struct kvm_x86_ops vt_x86_ops __initdata = { .set_idt = vmx_set_idt, .get_gdt = vmx_get_gdt, .set_gdt = vmx_set_gdt, + .set_dr6 = vmx_set_dr6, .set_dr7 = vmx_set_dr7, .sync_dirty_debug_regs = vmx_sync_dirty_debug_regs, .cache_reg = vmx_cache_reg, diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index f72835e85b6d..6c56d5235f0f 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -5648,6 +5648,12 @@ void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu) set_debugreg(DR6_RESERVED, 6); } +void vmx_set_dr6(struct kvm_vcpu *vcpu, unsigned long val) +{ + lockdep_assert_irqs_disabled(); + set_debugreg(vcpu->arch.dr6, 6); +} + void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val) { vmcs_writel(GUEST_DR7, val); @@ -7417,10 +7423,6 @@ fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit) vmx->loaded_vmcs->host_state.cr4 = cr4; } - /* When KVM_DEBUGREG_WONT_EXIT, dr6 is accessible in guest. */ - if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) - set_debugreg(vcpu->arch.dr6, 6); - /* When single-stepping over STI and MOV SS, we must clear the * corresponding interruptibility bits in the guest state. Otherwise * vmentry fails as it then expects bit 14 (BS) in pending debug diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h index ce3295a67c04..430773a5ef8e 100644 --- a/arch/x86/kvm/vmx/x86_ops.h +++ b/arch/x86/kvm/vmx/x86_ops.h @@ -73,6 +73,7 @@ void vmx_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void vmx_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void vmx_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void vmx_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt); +void vmx_set_dr6(struct kvm_vcpu *vcpu, unsigned long val); void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val); void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu); void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 8e77e61d4fbd..02159c967d29 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -10961,6 +10961,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) set_debugreg(vcpu->arch.eff_db[1], 1); set_debugreg(vcpu->arch.eff_db[2], 2); set_debugreg(vcpu->arch.eff_db[3], 3); + /* When KVM_DEBUGREG_WONT_EXIT, dr6 is accessible in guest. */ + if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) + kvm_x86_call(set_dr6)(vcpu, vcpu->arch.dr6); } else if (unlikely(hw_breakpoint_active())) { set_debugreg(0, 7); } diff --git a/arch/x86/um/os-Linux/registers.c b/arch/x86/um/os-Linux/registers.c index 76eaeb93928c..eb1cdadc8a61 100644 --- a/arch/x86/um/os-Linux/registers.c +++ b/arch/x86/um/os-Linux/registers.c @@ -18,6 +18,7 @@ #include <registers.h> #include <sys/mman.h> +static unsigned long ptrace_regset; unsigned long host_fp_size; int get_fp_registers(int pid, unsigned long *regs) @@ -27,7 +28,7 @@ int get_fp_registers(int pid, unsigned long *regs) .iov_len = host_fp_size, }; - if (ptrace(PTRACE_GETREGSET, pid, NT_X86_XSTATE, &iov) < 0) + if (ptrace(PTRACE_GETREGSET, pid, ptrace_regset, &iov) < 0) return -errno; return 0; } @@ -39,7 +40,7 @@ int put_fp_registers(int pid, unsigned long *regs) .iov_len = host_fp_size, }; - if (ptrace(PTRACE_SETREGSET, pid, NT_X86_XSTATE, &iov) < 0) + if (ptrace(PTRACE_SETREGSET, pid, ptrace_regset, &iov) < 0) return -errno; return 0; } @@ -58,9 +59,23 @@ int arch_init_registers(int pid) return -ENOMEM; /* GDB has x86_xsave_length, which uses x86_cpuid_count */ - ret = ptrace(PTRACE_GETREGSET, pid, NT_X86_XSTATE, &iov); + ptrace_regset = NT_X86_XSTATE; + ret = ptrace(PTRACE_GETREGSET, pid, ptrace_regset, &iov); if (ret) ret = -errno; + + if (ret == -ENODEV) { +#ifdef CONFIG_X86_32 + ptrace_regset = NT_PRXFPREG; +#else + ptrace_regset = NT_PRFPREG; +#endif + iov.iov_len = 2 * 1024 * 1024; + ret = ptrace(PTRACE_GETREGSET, pid, ptrace_regset, &iov); + if (ret) + ret = -errno; + } + munmap(iov.iov_base, 2 * 1024 * 1024); host_fp_size = iov.iov_len; diff --git a/arch/x86/um/signal.c b/arch/x86/um/signal.c index 75087e85b6fd..2934e170b0fe 100644 --- a/arch/x86/um/signal.c +++ b/arch/x86/um/signal.c @@ -187,7 +187,12 @@ static int copy_sc_to_user(struct sigcontext __user *to, * Put magic/size values for userspace. We do not bother to verify them * later on, however, userspace needs them should it try to read the * XSTATE data. And ptrace does not fill in these parts. + * + * Skip this if we do not have an XSTATE frame. */ + if (host_fp_size <= sizeof(to_fp64->fpstate)) + return 0; + BUILD_BUG_ON(sizeof(int) != FP_XSTATE_MAGIC2_SIZE); #ifdef CONFIG_X86_32 __put_user(offsetof(struct _fpstate_32, _fxsr_env) + @@ -367,11 +372,13 @@ int setup_signal_stack_si(unsigned long stack_top, struct ksignal *ksig, int err = 0, sig = ksig->sig; unsigned long fp_to; - frame = (struct rt_sigframe __user *) - round_down(stack_top - sizeof(struct rt_sigframe), 16); + frame = (void __user *)stack_top - sizeof(struct rt_sigframe); /* Add required space for math frame */ - frame = (struct rt_sigframe __user *)((unsigned long)frame - math_size); + frame = (void __user *)((unsigned long)frame - math_size); + + /* ABI requires 16 byte boundary alignment */ + frame = (void __user *)round_down((unsigned long)frame, 16); /* Subtract 128 for a red zone and 8 for proper alignment */ frame = (struct rt_sigframe __user *) ((unsigned long) frame - 128 - 8); diff --git a/arch/x86/virt/svm/sev.c b/arch/x86/virt/svm/sev.c index 1dcc027ec77e..42e74a5a7d78 100644 --- a/arch/x86/virt/svm/sev.c +++ b/arch/x86/virt/svm/sev.c @@ -505,19 +505,19 @@ static bool __init setup_rmptable(void) * described in the SNP_INIT_EX firmware command description in the SNP * firmware ABI spec. */ -static int __init snp_rmptable_init(void) +int __init snp_rmptable_init(void) { unsigned int i; u64 val; - if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) - return 0; + if (WARN_ON_ONCE(!cc_platform_has(CC_ATTR_HOST_SEV_SNP))) + return -ENOSYS; - if (!amd_iommu_snp_en) - goto nosnp; + if (WARN_ON_ONCE(!amd_iommu_snp_en)) + return -ENOSYS; if (!setup_rmptable()) - goto nosnp; + return -ENOSYS; /* * Check if SEV-SNP is already enabled, this can happen in case of @@ -530,7 +530,7 @@ static int __init snp_rmptable_init(void) /* Zero out the RMP bookkeeping area */ if (!clear_rmptable_bookkeeping()) { free_rmp_segment_table(); - goto nosnp; + return -ENOSYS; } /* Zero out the RMP entries */ @@ -562,17 +562,8 @@ skip_enable: crash_kexec_post_notifiers = true; return 0; - -nosnp: - cc_platform_clear(CC_ATTR_HOST_SEV_SNP); - return -ENOSYS; } -/* - * This must be called after the IOMMU has been initialized. - */ -device_initcall(snp_rmptable_init); - static void set_rmp_segment_info(unsigned int segment_shift) { rmp_segment_shift = segment_shift; diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 2c70cd35e72c..d078de2c952b 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -111,6 +111,51 @@ static pud_t level3_user_vsyscall[PTRS_PER_PUD] __page_aligned_bss; */ static DEFINE_SPINLOCK(xen_reservation_lock); +/* Protected by xen_reservation_lock. */ +#define MIN_CONTIG_ORDER 9 /* 2MB */ +static unsigned int discontig_frames_order = MIN_CONTIG_ORDER; +static unsigned long discontig_frames_early[1UL << MIN_CONTIG_ORDER] __initdata; +static unsigned long *discontig_frames __refdata = discontig_frames_early; +static bool discontig_frames_dyn; + +static int alloc_discontig_frames(unsigned int order) +{ + unsigned long *new_array, *old_array; + unsigned int old_order; + unsigned long flags; + + BUG_ON(order < MIN_CONTIG_ORDER); + BUILD_BUG_ON(sizeof(discontig_frames_early) != PAGE_SIZE); + + new_array = (unsigned long *)__get_free_pages(GFP_KERNEL, + order - MIN_CONTIG_ORDER); + if (!new_array) + return -ENOMEM; + + spin_lock_irqsave(&xen_reservation_lock, flags); + + old_order = discontig_frames_order; + + if (order > discontig_frames_order || !discontig_frames_dyn) { + if (!discontig_frames_dyn) + old_array = NULL; + else + old_array = discontig_frames; + + discontig_frames = new_array; + discontig_frames_order = order; + discontig_frames_dyn = true; + } else { + old_array = new_array; + } + + spin_unlock_irqrestore(&xen_reservation_lock, flags); + + free_pages((unsigned long)old_array, old_order - MIN_CONTIG_ORDER); + + return 0; +} + /* * Note about cr3 (pagetable base) values: * @@ -814,6 +859,9 @@ static void __init xen_after_bootmem(void) SetPagePinned(virt_to_page(level3_user_vsyscall)); #endif xen_pgd_walk(&init_mm, xen_mark_pinned, FIXADDR_TOP); + + if (alloc_discontig_frames(MIN_CONTIG_ORDER)) + BUG(); } static void xen_unpin_page(struct mm_struct *mm, struct page *page, @@ -2203,10 +2251,6 @@ void __init xen_init_mmu_ops(void) memset(dummy_mapping, 0xff, PAGE_SIZE); } -/* Protected by xen_reservation_lock. */ -#define MAX_CONTIG_ORDER 9 /* 2MB */ -static unsigned long discontig_frames[1<<MAX_CONTIG_ORDER]; - #define VOID_PTE (mfn_pte(0, __pgprot(0))) static void xen_zap_pfn_range(unsigned long vaddr, unsigned int order, unsigned long *in_frames, @@ -2323,18 +2367,25 @@ int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order, unsigned int address_bits, dma_addr_t *dma_handle) { - unsigned long *in_frames = discontig_frames, out_frame; + unsigned long *in_frames, out_frame; unsigned long flags; int success; unsigned long vstart = (unsigned long)phys_to_virt(pstart); - if (unlikely(order > MAX_CONTIG_ORDER)) - return -ENOMEM; + if (unlikely(order > discontig_frames_order)) { + if (!discontig_frames_dyn) + return -ENOMEM; + + if (alloc_discontig_frames(order)) + return -ENOMEM; + } memset((void *) vstart, 0, PAGE_SIZE << order); spin_lock_irqsave(&xen_reservation_lock, flags); + in_frames = discontig_frames; + /* 1. Zap current PTEs, remembering MFNs. */ xen_zap_pfn_range(vstart, order, in_frames, NULL); @@ -2358,12 +2409,12 @@ int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order, void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order) { - unsigned long *out_frames = discontig_frames, in_frame; + unsigned long *out_frames, in_frame; unsigned long flags; int success; unsigned long vstart; - if (unlikely(order > MAX_CONTIG_ORDER)) + if (unlikely(order > discontig_frames_order)) return; vstart = (unsigned long)phys_to_virt(pstart); @@ -2371,6 +2422,8 @@ void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order) spin_lock_irqsave(&xen_reservation_lock, flags); + out_frames = discontig_frames; + /* 1. Find start MFN of contiguous extent. */ in_frame = virt_to_mfn((void *)vstart); diff --git a/block/partitions/mac.c b/block/partitions/mac.c index c80183156d68..b02530d98629 100644 --- a/block/partitions/mac.c +++ b/block/partitions/mac.c @@ -53,13 +53,25 @@ int mac_partition(struct parsed_partitions *state) } secsize = be16_to_cpu(md->block_size); put_dev_sector(sect); + + /* + * If the "block size" is not a power of 2, things get weird - we might + * end up with a partition straddling a sector boundary, so we wouldn't + * be able to read a partition entry with read_part_sector(). + * Real block sizes are probably (?) powers of two, so just require + * that. + */ + if (!is_power_of_2(secsize)) + return -1; datasize = round_down(secsize, 512); data = read_part_sector(state, datasize / 512, §); if (!data) return -1; partoffset = secsize % 512; - if (partoffset + sizeof(*part) > datasize) + if (partoffset + sizeof(*part) > datasize) { + put_dev_sector(sect); return -1; + } part = (struct mac_partition *) (data + partoffset); if (be16_to_cpu(part->signature) != MAC_PARTITION_MAGIC) { put_dev_sector(sect); @@ -112,8 +124,8 @@ int mac_partition(struct parsed_partitions *state) int i, l; goodness++; - l = strlen(part->name); - if (strcmp(part->name, "/") == 0) + l = strnlen(part->name, sizeof(part->name)); + if (strncmp(part->name, "/", sizeof(part->name)) == 0) goodness++; for (i = 0; i <= l - 4; ++i) { if (strncasecmp(part->name + i, "root", diff --git a/drivers/acpi/arm64/gtdt.c b/drivers/acpi/arm64/gtdt.c index 3561553eff8b..70f8290b659d 100644 --- a/drivers/acpi/arm64/gtdt.c +++ b/drivers/acpi/arm64/gtdt.c @@ -163,7 +163,7 @@ int __init acpi_gtdt_init(struct acpi_table_header *table, { void *platform_timer; struct acpi_table_gtdt *gtdt; - int cnt = 0; + u32 cnt = 0; gtdt = container_of(table, struct acpi_table_gtdt, header); acpi_gtdt_desc.gtdt = gtdt; @@ -188,13 +188,17 @@ int __init acpi_gtdt_init(struct acpi_table_header *table, cnt++; if (cnt != gtdt->platform_timer_count) { + cnt = min(cnt, gtdt->platform_timer_count); + pr_err(FW_BUG "limiting Platform Timer count to %d\n", cnt); + } + + if (!cnt) { acpi_gtdt_desc.platform_timer = NULL; - pr_err(FW_BUG "invalid timer data.\n"); - return -EINVAL; + return 0; } if (platform_timer_count) - *platform_timer_count = gtdt->platform_timer_count; + *platform_timer_count = cnt; return 0; } diff --git a/drivers/base/Makefile b/drivers/base/Makefile index 7fb21768ca36..8074a10183dc 100644 --- a/drivers/base/Makefile +++ b/drivers/base/Makefile @@ -6,7 +6,7 @@ obj-y := component.o core.o bus.o dd.o syscore.o \ cpu.o firmware.o init.o map.o devres.o \ attribute_container.o transport_class.o \ topology.o container.o property.o cacheinfo.o \ - swnode.o + swnode.o faux.o obj-$(CONFIG_AUXILIARY_BUS) += auxiliary.o obj-$(CONFIG_DEVTMPFS) += devtmpfs.o obj-y += power/ diff --git a/drivers/base/base.h b/drivers/base/base.h index 8cf04a557bdb..0042e4774b0c 100644 --- a/drivers/base/base.h +++ b/drivers/base/base.h @@ -137,6 +137,7 @@ int hypervisor_init(void); static inline int hypervisor_init(void) { return 0; } #endif int platform_bus_init(void); +int faux_bus_init(void); void cpu_dev_init(void); void container_dev_init(void); #ifdef CONFIG_AUXILIARY_BUS diff --git a/drivers/base/faux.c b/drivers/base/faux.c new file mode 100644 index 000000000000..531e9d789ee0 --- /dev/null +++ b/drivers/base/faux.c @@ -0,0 +1,232 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2025 Greg Kroah-Hartman <gregkh@linuxfoundation.org> + * Copyright (c) 2025 The Linux Foundation + * + * A "simple" faux bus that allows devices to be created and added + * automatically to it. This is to be used whenever you need to create a + * device that is not associated with any "real" system resources, and do + * not want to have to deal with a bus/driver binding logic. It is + * intended to be very simple, with only a create and a destroy function + * available. + */ +#include <linux/err.h> +#include <linux/init.h> +#include <linux/slab.h> +#include <linux/string.h> +#include <linux/container_of.h> +#include <linux/device/faux.h> +#include "base.h" + +/* + * Internal wrapper structure so we can hold a pointer to the + * faux_device_ops for this device. + */ +struct faux_object { + struct faux_device faux_dev; + const struct faux_device_ops *faux_ops; +}; +#define to_faux_object(dev) container_of_const(dev, struct faux_object, faux_dev.dev) + +static struct device faux_bus_root = { + .init_name = "faux", +}; + +static int faux_match(struct device *dev, const struct device_driver *drv) +{ + /* Match always succeeds, we only have one driver */ + return 1; +} + +static int faux_probe(struct device *dev) +{ + struct faux_object *faux_obj = to_faux_object(dev); + struct faux_device *faux_dev = &faux_obj->faux_dev; + const struct faux_device_ops *faux_ops = faux_obj->faux_ops; + int ret = 0; + + if (faux_ops && faux_ops->probe) + ret = faux_ops->probe(faux_dev); + + return ret; +} + +static void faux_remove(struct device *dev) +{ + struct faux_object *faux_obj = to_faux_object(dev); + struct faux_device *faux_dev = &faux_obj->faux_dev; + const struct faux_device_ops *faux_ops = faux_obj->faux_ops; + + if (faux_ops && faux_ops->remove) + faux_ops->remove(faux_dev); +} + +static const struct bus_type faux_bus_type = { + .name = "faux", + .match = faux_match, + .probe = faux_probe, + .remove = faux_remove, +}; + +static struct device_driver faux_driver = { + .name = "faux_driver", + .bus = &faux_bus_type, + .probe_type = PROBE_FORCE_SYNCHRONOUS, +}; + +static void faux_device_release(struct device *dev) +{ + struct faux_object *faux_obj = to_faux_object(dev); + + kfree(faux_obj); +} + +/** + * faux_device_create_with_groups - Create and register with the driver + * core a faux device and populate the device with an initial + * set of sysfs attributes. + * @name: The name of the device we are adding, must be unique for + * all faux devices. + * @parent: Pointer to a potential parent struct device. If set to + * NULL, the device will be created in the "root" of the faux + * device tree in sysfs. + * @faux_ops: struct faux_device_ops that the new device will call back + * into, can be NULL. + * @groups: The set of sysfs attributes that will be created for this + * device when it is registered with the driver core. + * + * Create a new faux device and register it in the driver core properly. + * If present, callbacks in @faux_ops will be called with the device that + * for the caller to do something with at the proper time given the + * device's lifecycle. + * + * Note, when this function is called, the functions specified in struct + * faux_ops can be called before the function returns, so be prepared for + * everything to be properly initialized before that point in time. + * + * Return: + * * NULL if an error happened with creating the device + * * pointer to a valid struct faux_device that is registered with sysfs + */ +struct faux_device *faux_device_create_with_groups(const char *name, + struct device *parent, + const struct faux_device_ops *faux_ops, + const struct attribute_group **groups) +{ + struct faux_object *faux_obj; + struct faux_device *faux_dev; + struct device *dev; + int ret; + + faux_obj = kzalloc(sizeof(*faux_obj), GFP_KERNEL); + if (!faux_obj) + return NULL; + + /* Save off the callbacks so we can use them in the future */ + faux_obj->faux_ops = faux_ops; + + /* Initialize the device portion and register it with the driver core */ + faux_dev = &faux_obj->faux_dev; + dev = &faux_dev->dev; + + device_initialize(dev); + dev->release = faux_device_release; + if (parent) + dev->parent = parent; + else + dev->parent = &faux_bus_root; + dev->bus = &faux_bus_type; + dev->groups = groups; + dev_set_name(dev, "%s", name); + + ret = device_add(dev); + if (ret) { + pr_err("%s: device_add for faux device '%s' failed with %d\n", + __func__, name, ret); + put_device(dev); + return NULL; + } + + return faux_dev; +} +EXPORT_SYMBOL_GPL(faux_device_create_with_groups); + +/** + * faux_device_create - create and register with the driver core a faux device + * @name: The name of the device we are adding, must be unique for all + * faux devices. + * @parent: Pointer to a potential parent struct device. If set to + * NULL, the device will be created in the "root" of the faux + * device tree in sysfs. + * @faux_ops: struct faux_device_ops that the new device will call back + * into, can be NULL. + * + * Create a new faux device and register it in the driver core properly. + * If present, callbacks in @faux_ops will be called with the device that + * for the caller to do something with at the proper time given the + * device's lifecycle. + * + * Note, when this function is called, the functions specified in struct + * faux_ops can be called before the function returns, so be prepared for + * everything to be properly initialized before that point in time. + * + * Return: + * * NULL if an error happened with creating the device + * * pointer to a valid struct faux_device that is registered with sysfs + */ +struct faux_device *faux_device_create(const char *name, + struct device *parent, + const struct faux_device_ops *faux_ops) +{ + return faux_device_create_with_groups(name, parent, faux_ops, NULL); +} +EXPORT_SYMBOL_GPL(faux_device_create); + +/** + * faux_device_destroy - destroy a faux device + * @faux_dev: faux device to destroy + * + * Unregisters and cleans up a device that was created with a call to + * faux_device_create() + */ +void faux_device_destroy(struct faux_device *faux_dev) +{ + struct device *dev = &faux_dev->dev; + + if (!faux_dev) + return; + + device_del(dev); + + /* The final put_device() will clean up the memory we allocated for this device. */ + put_device(dev); +} +EXPORT_SYMBOL_GPL(faux_device_destroy); + +int __init faux_bus_init(void) +{ + int ret; + + ret = device_register(&faux_bus_root); + if (ret) { + put_device(&faux_bus_root); + return ret; + } + + ret = bus_register(&faux_bus_type); + if (ret) + goto error_bus; + + ret = driver_register(&faux_driver); + if (ret) + goto error_driver; + + return ret; + +error_driver: + bus_unregister(&faux_bus_type); + +error_bus: + device_unregister(&faux_bus_root); + return ret; +} diff --git a/drivers/base/init.c b/drivers/base/init.c index c4954835128c..9d2b06d65dfc 100644 --- a/drivers/base/init.c +++ b/drivers/base/init.c @@ -32,6 +32,7 @@ void __init driver_init(void) /* These are also core pieces, but must come after the * core core pieces. */ + faux_bus_init(); of_core_init(); platform_bus_init(); auxiliary_bus_init(); diff --git a/drivers/base/regmap/regmap-irq.c b/drivers/base/regmap/regmap-irq.c index 0bcd81389a29..978613407ea3 100644 --- a/drivers/base/regmap/regmap-irq.c +++ b/drivers/base/regmap/regmap-irq.c @@ -906,6 +906,7 @@ err_alloc: kfree(d->wake_buf); kfree(d->mask_buf_def); kfree(d->mask_buf); + kfree(d->main_status_buf); kfree(d->status_buf); kfree(d->status_reg_buf); if (d->config_buf) { @@ -981,6 +982,7 @@ void regmap_del_irq_chip(int irq, struct regmap_irq_chip_data *d) kfree(d->wake_buf); kfree(d->mask_buf_def); kfree(d->mask_buf); + kfree(d->main_status_buf); kfree(d->status_reg_buf); kfree(d->status_buf); if (d->config_buf) { diff --git a/drivers/crypto/ccp/sp-dev.c b/drivers/crypto/ccp/sp-dev.c index 7eb3e4668286..3467f6db4f50 100644 --- a/drivers/crypto/ccp/sp-dev.c +++ b/drivers/crypto/ccp/sp-dev.c @@ -19,6 +19,7 @@ #include <linux/types.h> #include <linux/ccp.h> +#include "sev-dev.h" #include "ccp-dev.h" #include "sp-dev.h" @@ -253,8 +254,12 @@ unlock: static int __init sp_mod_init(void) { #ifdef CONFIG_X86 + static bool initialized; int ret; + if (initialized) + return 0; + ret = sp_pci_init(); if (ret) return ret; @@ -263,6 +268,8 @@ static int __init sp_mod_init(void) psp_pci_init(); #endif + initialized = true; + return 0; #endif @@ -279,6 +286,13 @@ static int __init sp_mod_init(void) return -ENODEV; } +#if IS_BUILTIN(CONFIG_KVM_AMD) && IS_ENABLED(CONFIG_KVM_AMD_SEV) +int __init sev_module_init(void) +{ + return sp_mod_init(); +} +#endif + static void __exit sp_mod_exit(void) { #ifdef CONFIG_X86 diff --git a/drivers/dma/tegra210-adma.c b/drivers/dma/tegra210-adma.c index 6896da8ac7ef..5c6a5b358987 100644 --- a/drivers/dma/tegra210-adma.c +++ b/drivers/dma/tegra210-adma.c @@ -887,7 +887,7 @@ static int tegra_adma_probe(struct platform_device *pdev) const struct tegra_adma_chip_data *cdata; struct tegra_adma *tdma; struct resource *res_page, *res_base; - int ret, i, page_no; + int ret, i; cdata = of_device_get_match_data(&pdev->dev); if (!cdata) { @@ -914,9 +914,20 @@ static int tegra_adma_probe(struct platform_device *pdev) res_base = platform_get_resource_byname(pdev, IORESOURCE_MEM, "global"); if (res_base) { - page_no = (res_page->start - res_base->start) / cdata->ch_base_offset; - if (page_no <= 0) + resource_size_t page_offset, page_no; + unsigned int ch_base_offset; + + if (res_page->start < res_base->start) + return -EINVAL; + page_offset = res_page->start - res_base->start; + ch_base_offset = cdata->ch_base_offset; + if (!ch_base_offset) return -EINVAL; + + page_no = div_u64(page_offset, ch_base_offset); + if (!page_no || page_no > INT_MAX) + return -EINVAL; + tdma->ch_page_no = page_no - 1; tdma->base_addr = devm_ioremap_resource(&pdev->dev, res_base); if (IS_ERR(tdma->base_addr)) diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 8296bf985d1d..7309394b8fc9 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -934,13 +934,15 @@ char * __init efi_md_typeattr_format(char *buf, size_t size, EFI_MEMORY_WB | EFI_MEMORY_UCE | EFI_MEMORY_RO | EFI_MEMORY_WP | EFI_MEMORY_RP | EFI_MEMORY_XP | EFI_MEMORY_NV | EFI_MEMORY_SP | EFI_MEMORY_CPU_CRYPTO | - EFI_MEMORY_RUNTIME | EFI_MEMORY_MORE_RELIABLE)) + EFI_MEMORY_MORE_RELIABLE | EFI_MEMORY_HOT_PLUGGABLE | + EFI_MEMORY_RUNTIME)) snprintf(pos, size, "|attr=0x%016llx]", (unsigned long long)attr); else snprintf(pos, size, - "|%3s|%2s|%2s|%2s|%2s|%2s|%2s|%2s|%2s|%3s|%2s|%2s|%2s|%2s]", + "|%3s|%2s|%2s|%2s|%2s|%2s|%2s|%2s|%2s|%2s|%3s|%2s|%2s|%2s|%2s]", attr & EFI_MEMORY_RUNTIME ? "RUN" : "", + attr & EFI_MEMORY_HOT_PLUGGABLE ? "HP" : "", attr & EFI_MEMORY_MORE_RELIABLE ? "MR" : "", attr & EFI_MEMORY_CPU_CRYPTO ? "CC" : "", attr & EFI_MEMORY_SP ? "SP" : "", diff --git a/drivers/firmware/efi/libstub/randomalloc.c b/drivers/firmware/efi/libstub/randomalloc.c index e5872e38d9a4..5a732018be36 100644 --- a/drivers/firmware/efi/libstub/randomalloc.c +++ b/drivers/firmware/efi/libstub/randomalloc.c @@ -25,6 +25,9 @@ static unsigned long get_entry_num_slots(efi_memory_desc_t *md, if (md->type != EFI_CONVENTIONAL_MEMORY) return 0; + if (md->attribute & EFI_MEMORY_HOT_PLUGGABLE) + return 0; + if (efi_soft_reserve_enabled() && (md->attribute & EFI_MEMORY_SP)) return 0; diff --git a/drivers/firmware/efi/libstub/relocate.c b/drivers/firmware/efi/libstub/relocate.c index 99b45d1cd624..d4264bfb6dc1 100644 --- a/drivers/firmware/efi/libstub/relocate.c +++ b/drivers/firmware/efi/libstub/relocate.c @@ -53,6 +53,9 @@ efi_status_t efi_low_alloc_above(unsigned long size, unsigned long align, if (desc->type != EFI_CONVENTIONAL_MEMORY) continue; + if (desc->attribute & EFI_MEMORY_HOT_PLUGGABLE) + continue; + if (efi_soft_reserve_enabled() && (desc->attribute & EFI_MEMORY_SP)) continue; diff --git a/drivers/gpio/gpio-bcm-kona.c b/drivers/gpio/gpio-bcm-kona.c index 5321ef98f442..64908f1a5e7f 100644 --- a/drivers/gpio/gpio-bcm-kona.c +++ b/drivers/gpio/gpio-bcm-kona.c @@ -69,6 +69,22 @@ struct bcm_kona_gpio { struct bcm_kona_gpio_bank { int id; int irq; + /* + * Used to keep track of lock/unlock operations for each GPIO in the + * bank. + * + * All GPIOs are locked by default (see bcm_kona_gpio_reset), and the + * unlock count for all GPIOs is 0 by default. Each unlock increments + * the counter, and each lock decrements the counter. + * + * The lock function only locks the GPIO once its unlock counter is + * down to 0. This is necessary because the GPIO is unlocked in two + * places in this driver: once for requested GPIOs, and once for + * requested IRQs. Since it is possible for a GPIO to be requested + * as both a GPIO and an IRQ, we need to ensure that we don't lock it + * too early. + */ + u8 gpio_unlock_count[GPIO_PER_BANK]; /* Used in the interrupt handler */ struct bcm_kona_gpio *kona_gpio; }; @@ -86,14 +102,24 @@ static void bcm_kona_gpio_lock_gpio(struct bcm_kona_gpio *kona_gpio, u32 val; unsigned long flags; int bank_id = GPIO_BANK(gpio); + int bit = GPIO_BIT(gpio); + struct bcm_kona_gpio_bank *bank = &kona_gpio->banks[bank_id]; - raw_spin_lock_irqsave(&kona_gpio->lock, flags); + if (bank->gpio_unlock_count[bit] == 0) { + dev_err(kona_gpio->gpio_chip.parent, + "Unbalanced locks for GPIO %u\n", gpio); + return; + } - val = readl(kona_gpio->reg_base + GPIO_PWD_STATUS(bank_id)); - val |= BIT(gpio); - bcm_kona_gpio_write_lock_regs(kona_gpio->reg_base, bank_id, val); + if (--bank->gpio_unlock_count[bit] == 0) { + raw_spin_lock_irqsave(&kona_gpio->lock, flags); - raw_spin_unlock_irqrestore(&kona_gpio->lock, flags); + val = readl(kona_gpio->reg_base + GPIO_PWD_STATUS(bank_id)); + val |= BIT(bit); + bcm_kona_gpio_write_lock_regs(kona_gpio->reg_base, bank_id, val); + + raw_spin_unlock_irqrestore(&kona_gpio->lock, flags); + } } static void bcm_kona_gpio_unlock_gpio(struct bcm_kona_gpio *kona_gpio, @@ -102,14 +128,20 @@ static void bcm_kona_gpio_unlock_gpio(struct bcm_kona_gpio *kona_gpio, u32 val; unsigned long flags; int bank_id = GPIO_BANK(gpio); + int bit = GPIO_BIT(gpio); + struct bcm_kona_gpio_bank *bank = &kona_gpio->banks[bank_id]; - raw_spin_lock_irqsave(&kona_gpio->lock, flags); + if (bank->gpio_unlock_count[bit] == 0) { + raw_spin_lock_irqsave(&kona_gpio->lock, flags); - val = readl(kona_gpio->reg_base + GPIO_PWD_STATUS(bank_id)); - val &= ~BIT(gpio); - bcm_kona_gpio_write_lock_regs(kona_gpio->reg_base, bank_id, val); + val = readl(kona_gpio->reg_base + GPIO_PWD_STATUS(bank_id)); + val &= ~BIT(bit); + bcm_kona_gpio_write_lock_regs(kona_gpio->reg_base, bank_id, val); - raw_spin_unlock_irqrestore(&kona_gpio->lock, flags); + raw_spin_unlock_irqrestore(&kona_gpio->lock, flags); + } + + ++bank->gpio_unlock_count[bit]; } static int bcm_kona_gpio_get_dir(struct gpio_chip *chip, unsigned gpio) @@ -360,6 +392,7 @@ static void bcm_kona_gpio_irq_mask(struct irq_data *d) kona_gpio = irq_data_get_irq_chip_data(d); reg_base = kona_gpio->reg_base; + raw_spin_lock_irqsave(&kona_gpio->lock, flags); val = readl(reg_base + GPIO_INT_MASK(bank_id)); @@ -382,6 +415,7 @@ static void bcm_kona_gpio_irq_unmask(struct irq_data *d) kona_gpio = irq_data_get_irq_chip_data(d); reg_base = kona_gpio->reg_base; + raw_spin_lock_irqsave(&kona_gpio->lock, flags); val = readl(reg_base + GPIO_INT_MSKCLR(bank_id)); @@ -477,15 +511,26 @@ static void bcm_kona_gpio_irq_handler(struct irq_desc *desc) static int bcm_kona_gpio_irq_reqres(struct irq_data *d) { struct bcm_kona_gpio *kona_gpio = irq_data_get_irq_chip_data(d); + unsigned int gpio = d->hwirq; - return gpiochip_reqres_irq(&kona_gpio->gpio_chip, d->hwirq); + /* + * We need to unlock the GPIO before any other operations are performed + * on the relevant GPIO configuration registers + */ + bcm_kona_gpio_unlock_gpio(kona_gpio, gpio); + + return gpiochip_reqres_irq(&kona_gpio->gpio_chip, gpio); } static void bcm_kona_gpio_irq_relres(struct irq_data *d) { struct bcm_kona_gpio *kona_gpio = irq_data_get_irq_chip_data(d); + unsigned int gpio = d->hwirq; + + /* Once we no longer use it, lock the GPIO again */ + bcm_kona_gpio_lock_gpio(kona_gpio, gpio); - gpiochip_relres_irq(&kona_gpio->gpio_chip, d->hwirq); + gpiochip_relres_irq(&kona_gpio->gpio_chip, gpio); } static struct irq_chip bcm_gpio_irq_chip = { @@ -614,7 +659,7 @@ static int bcm_kona_gpio_probe(struct platform_device *pdev) bank->irq = platform_get_irq(pdev, i); bank->kona_gpio = kona_gpio; if (bank->irq < 0) { - dev_err(dev, "Couldn't get IRQ for bank %d", i); + dev_err(dev, "Couldn't get IRQ for bank %d\n", i); ret = -ENOENT; goto err_irq_domain; } diff --git a/drivers/gpio/gpio-stmpe.c b/drivers/gpio/gpio-stmpe.c index 75a3633ceddb..222279a9d82b 100644 --- a/drivers/gpio/gpio-stmpe.c +++ b/drivers/gpio/gpio-stmpe.c @@ -191,7 +191,7 @@ static void stmpe_gpio_irq_sync_unlock(struct irq_data *d) [REG_IE][CSB] = STMPE_IDX_IEGPIOR_CSB, [REG_IE][MSB] = STMPE_IDX_IEGPIOR_MSB, }; - int i, j; + int ret, i, j; /* * STMPE1600: to be able to get IRQ from pins, @@ -199,8 +199,16 @@ static void stmpe_gpio_irq_sync_unlock(struct irq_data *d) * GPSR or GPCR registers */ if (stmpe->partnum == STMPE1600) { - stmpe_reg_read(stmpe, stmpe->regs[STMPE_IDX_GPMR_LSB]); - stmpe_reg_read(stmpe, stmpe->regs[STMPE_IDX_GPMR_CSB]); + ret = stmpe_reg_read(stmpe, stmpe->regs[STMPE_IDX_GPMR_LSB]); + if (ret < 0) { + dev_err(stmpe->dev, "Failed to read GPMR_LSB: %d\n", ret); + goto err; + } + ret = stmpe_reg_read(stmpe, stmpe->regs[STMPE_IDX_GPMR_CSB]); + if (ret < 0) { + dev_err(stmpe->dev, "Failed to read GPMR_CSB: %d\n", ret); + goto err; + } } for (i = 0; i < CACHE_NR_REGS; i++) { @@ -222,6 +230,7 @@ static void stmpe_gpio_irq_sync_unlock(struct irq_data *d) } } +err: mutex_unlock(&stmpe_gpio->irq_lock); } diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c index 1f9fe50bba00..f7746c57ba76 100644 --- a/drivers/gpio/gpiolib-acpi.c +++ b/drivers/gpio/gpiolib-acpi.c @@ -1689,6 +1689,20 @@ static const struct dmi_system_id gpiolib_acpi_quirks[] __initconst = { .ignore_wake = "PNP0C50:00@8", }, }, + { + /* + * Spurious wakeups from GPIO 11 + * Found in BIOS 1.04 + * https://gitlab.freedesktop.org/drm/amd/-/issues/3954 + */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_FAMILY, "Acer Nitro V 14"), + }, + .driver_data = &(struct acpi_gpiolib_dmi_quirk) { + .ignore_interrupt = "AMDI0030:00@11", + }, + }, {} /* Terminating entry */ }; diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 679ed764cb14..ca2f58a2cd45 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -904,13 +904,13 @@ int gpiochip_get_ngpios(struct gpio_chip *gc, struct device *dev) } if (gc->ngpio == 0) { - chip_err(gc, "tried to insert a GPIO chip with zero lines\n"); + dev_err(dev, "tried to insert a GPIO chip with zero lines\n"); return -EINVAL; } if (gc->ngpio > FASTPATH_NGPIO) - chip_warn(gc, "line cnt %u is greater than fast path cnt %u\n", - gc->ngpio, FASTPATH_NGPIO); + dev_warn(dev, "line cnt %u is greater than fast path cnt %u\n", + gc->ngpio, FASTPATH_NGPIO); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index dce9323fb410..95a05b03f799 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -120,9 +120,10 @@ * - 3.58.0 - Add GFX12 DCC support * - 3.59.0 - Cleared VRAM * - 3.60.0 - Add AMDGPU_TILING_GFX12_DCC_WRITE_COMPRESS_DISABLE (Vulkan requirement) + * - 3.61.0 - Contains fix for RV/PCO compute queues */ #define KMS_DRIVER_MAJOR 3 -#define KMS_DRIVER_MINOR 60 +#define KMS_DRIVER_MINOR 61 #define KMS_DRIVER_PATCHLEVEL 0 /* diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index babe94ade247..e5fc80ed06ea 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -3815,9 +3815,10 @@ int psp_init_cap_microcode(struct psp_context *psp, const char *chip_name) if (err == -ENODEV) { dev_warn(adev->dev, "cap microcode does not exist, skip\n"); err = 0; - goto out; + } else { + dev_err(adev->dev, "fail to initialize cap microcode\n"); } - dev_err(adev->dev, "fail to initialize cap microcode\n"); + goto out; } info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CAP]; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index fa572b40989e..0dce4421418c 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -7437,6 +7437,38 @@ static void gfx_v9_0_ring_emit_cleaner_shader(struct amdgpu_ring *ring) amdgpu_ring_write(ring, 0); /* RESERVED field, programmed to zero */ } +static void gfx_v9_0_ring_begin_use_compute(struct amdgpu_ring *ring) +{ + struct amdgpu_device *adev = ring->adev; + struct amdgpu_ip_block *gfx_block = + amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_GFX); + + amdgpu_gfx_enforce_isolation_ring_begin_use(ring); + + /* Raven and PCO APUs seem to have stability issues + * with compute and gfxoff and gfx pg. Disable gfx pg during + * submission and allow again afterwards. + */ + if (gfx_block && amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 1, 0)) + gfx_v9_0_set_powergating_state(gfx_block, AMD_PG_STATE_UNGATE); +} + +static void gfx_v9_0_ring_end_use_compute(struct amdgpu_ring *ring) +{ + struct amdgpu_device *adev = ring->adev; + struct amdgpu_ip_block *gfx_block = + amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_GFX); + + /* Raven and PCO APUs seem to have stability issues + * with compute and gfxoff and gfx pg. Disable gfx pg during + * submission and allow again afterwards. + */ + if (gfx_block && amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 1, 0)) + gfx_v9_0_set_powergating_state(gfx_block, AMD_PG_STATE_GATE); + + amdgpu_gfx_enforce_isolation_ring_end_use(ring); +} + static const struct amd_ip_funcs gfx_v9_0_ip_funcs = { .name = "gfx_v9_0", .early_init = gfx_v9_0_early_init, @@ -7613,8 +7645,8 @@ static const struct amdgpu_ring_funcs gfx_v9_0_ring_funcs_compute = { .emit_wave_limit = gfx_v9_0_emit_wave_limit, .reset = gfx_v9_0_reset_kcq, .emit_cleaner_shader = gfx_v9_0_ring_emit_cleaner_shader, - .begin_use = amdgpu_gfx_enforce_isolation_ring_begin_use, - .end_use = amdgpu_gfx_enforce_isolation_ring_end_use, + .begin_use = gfx_v9_0_ring_begin_use_compute, + .end_use = gfx_v9_0_ring_end_use_compute, }; static const struct amdgpu_ring_funcs gfx_v9_0_ring_funcs_kiq = { diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h index 984f0e705078..651660958e5b 100644 --- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h +++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h @@ -4121,7 +4121,8 @@ static const uint32_t cwsr_trap_gfx12_hex[] = { 0x0000ffff, 0x8bfe7e7e, 0x8bea6a6a, 0xb97af804, 0xbe804ec2, 0xbf94fffe, - 0xbe804a6c, 0xbfb10000, + 0xbe804a6c, 0xbe804ec2, + 0xbf94fffe, 0xbfb10000, 0xbf9f0000, 0xbf9f0000, 0xbf9f0000, 0xbf9f0000, 0xbf9f0000, 0x00000000, diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx12.asm b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx12.asm index 1740e98c6719..7b9d36e5fa43 100644 --- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx12.asm +++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx12.asm @@ -1049,6 +1049,10 @@ L_SKIP_BARRIER_RESTORE: s_rfe_b64 s_restore_pc_lo //Return to the main shader program and resume execution L_END_PGM: + // Make sure that no wave of the workgroup can exit the trap handler + // before the workgroup barrier state is saved. + s_barrier_signal -2 + s_barrier_wait -2 s_endpgm_saved end diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c index bcddd989c7f3..bd36a75309e1 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c @@ -300,7 +300,7 @@ static int init_user_queue(struct process_queue_manager *pqm, return 0; free_gang_ctx_bo: - amdgpu_amdkfd_free_gtt_mem(dev->adev, (*q)->gang_ctx_bo); + amdgpu_amdkfd_free_gtt_mem(dev->adev, &(*q)->gang_ctx_bo); cleanup: uninit_queue(*q); *q = NULL; diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c index 6a9e26905edf..7a22aef6e59c 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c @@ -78,7 +78,7 @@ int amdgpu_dpm_set_powergating_by_smu(struct amdgpu_device *adev, int ret = 0; const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs; enum ip_power_state pwr_state = gate ? POWER_STATE_OFF : POWER_STATE_ON; - bool is_vcn = (block_type == AMD_IP_BLOCK_TYPE_UVD || block_type == AMD_IP_BLOCK_TYPE_VCN); + bool is_vcn = block_type == AMD_IP_BLOCK_TYPE_VCN; if (atomic_read(&adev->pm.pwr_state[block_type]) == pwr_state && (!is_vcn || adev->vcn.num_vcn_inst == 1)) { diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index 8ca793c222ff..ed9dac00ebfb 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -612,7 +612,8 @@ static int smu_sys_set_pp_table(void *handle, return -EIO; } - if (!smu_table->hardcode_pptable) { + if (!smu_table->hardcode_pptable || smu_table->power_play_table_size < size) { + kfree(smu_table->hardcode_pptable); smu_table->hardcode_pptable = kzalloc(size, GFP_KERNEL); if (!smu_table->hardcode_pptable) return -ENOMEM; diff --git a/drivers/gpu/drm/display/drm_dp_helper.c b/drivers/gpu/drm/display/drm_dp_helper.c index da3c8521a7fa..61c7c2c588c6 100644 --- a/drivers/gpu/drm/display/drm_dp_helper.c +++ b/drivers/gpu/drm/display/drm_dp_helper.c @@ -2544,7 +2544,7 @@ u8 drm_dp_dsc_sink_bpp_incr(const u8 dsc_dpcd[DP_DSC_RECEIVER_CAP_SIZE]) { u8 bpp_increment_dpcd = dsc_dpcd[DP_DSC_BITS_PER_PIXEL_INC - DP_DSC_SUPPORT]; - switch (bpp_increment_dpcd) { + switch (bpp_increment_dpcd & DP_DSC_BITS_PER_PIXEL_MASK) { case DP_DSC_BITS_PER_PIXEL_1_16: return 16; case DP_DSC_BITS_PER_PIXEL_1_8: diff --git a/drivers/gpu/drm/hisilicon/hibmc/Kconfig b/drivers/gpu/drm/hisilicon/hibmc/Kconfig index 93b8d32e3be1..98d77d74999d 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/Kconfig +++ b/drivers/gpu/drm/hisilicon/hibmc/Kconfig @@ -4,6 +4,8 @@ config DRM_HISI_HIBMC depends on DRM && PCI depends on MMU select DRM_CLIENT_SELECTION + select DRM_DISPLAY_HELPER + select DRM_DISPLAY_DP_HELPER select DRM_KMS_HELPER select DRM_VRAM_HELPER select DRM_TTM diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c index 5c397a2df70e..5d27e1c733c5 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c @@ -168,7 +168,7 @@ static int igt_ppgtt_alloc(void *arg) return PTR_ERR(ppgtt); if (!ppgtt->vm.allocate_va_range) - goto err_ppgtt_cleanup; + goto ppgtt_vm_put; /* * While we only allocate the page tables here and so we could @@ -236,7 +236,7 @@ err_ppgtt_cleanup: goto retry; } i915_gem_ww_ctx_fini(&ww); - +ppgtt_vm_put: i915_vm_put(&ppgtt->vm); return err; } diff --git a/drivers/gpu/drm/panthor/panthor_drv.c b/drivers/gpu/drm/panthor/panthor_drv.c index d5dcd3d1b33a..08136e790ca0 100644 --- a/drivers/gpu/drm/panthor/panthor_drv.c +++ b/drivers/gpu/drm/panthor/panthor_drv.c @@ -802,6 +802,7 @@ static void panthor_query_group_priorities_info(struct drm_file *file, { int prio; + memset(arg, 0, sizeof(*arg)); for (prio = PANTHOR_GROUP_PRIORITY_REALTIME; prio >= 0; prio--) { if (!group_priority_permit(file, prio)) arg->allowed_mask |= BIT(prio); diff --git a/drivers/gpu/drm/tests/drm_hdmi_state_helper_test.c b/drivers/gpu/drm/tests/drm_hdmi_state_helper_test.c index b976a5e9aef5..23ecc00accb2 100644 --- a/drivers/gpu/drm/tests/drm_hdmi_state_helper_test.c +++ b/drivers/gpu/drm/tests/drm_hdmi_state_helper_test.c @@ -70,10 +70,17 @@ static int light_up_connector(struct kunit *test, state = drm_kunit_helper_atomic_state_alloc(test, drm, ctx); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, state); +retry: conn_state = drm_atomic_get_connector_state(state, connector); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, conn_state); ret = drm_atomic_set_crtc_for_connector(conn_state, crtc); + if (ret == -EDEADLK) { + drm_atomic_state_clear(state); + ret = drm_modeset_backoff(ctx); + if (!ret) + goto retry; + } KUNIT_EXPECT_EQ(test, ret, 0); crtc_state = drm_atomic_get_crtc_state(state, crtc); @@ -282,15 +289,16 @@ static void drm_test_check_broadcast_rgb_crtc_mode_changed(struct kunit *test) 8); KUNIT_ASSERT_NOT_NULL(test, priv); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); - + drm = &priv->drm; + crtc = priv->crtc; conn = &priv->connector; + preferred = find_preferred_mode(conn); KUNIT_ASSERT_NOT_NULL(test, preferred); - drm = &priv->drm; - crtc = priv->crtc; + ctx = drm_kunit_helper_acquire_ctx_alloc(test); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); KUNIT_ASSERT_EQ(test, ret, 0); @@ -345,15 +353,16 @@ static void drm_test_check_broadcast_rgb_crtc_mode_not_changed(struct kunit *tes 8); KUNIT_ASSERT_NOT_NULL(test, priv); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); - + drm = &priv->drm; + crtc = priv->crtc; conn = &priv->connector; + preferred = find_preferred_mode(conn); KUNIT_ASSERT_NOT_NULL(test, preferred); - drm = &priv->drm; - crtc = priv->crtc; + ctx = drm_kunit_helper_acquire_ctx_alloc(test); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); KUNIT_ASSERT_EQ(test, ret, 0); @@ -408,18 +417,18 @@ static void drm_test_check_broadcast_rgb_auto_cea_mode(struct kunit *test) 8); KUNIT_ASSERT_NOT_NULL(test, priv); + drm = &priv->drm; + crtc = priv->crtc; conn = &priv->connector; KUNIT_ASSERT_TRUE(test, conn->display_info.is_hdmi); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); - preferred = find_preferred_mode(conn); KUNIT_ASSERT_NOT_NULL(test, preferred); KUNIT_ASSERT_NE(test, drm_match_cea_mode(preferred), 1); - drm = &priv->drm; - crtc = priv->crtc; + ctx = drm_kunit_helper_acquire_ctx_alloc(test); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); KUNIT_ASSERT_EQ(test, ret, 0); @@ -474,7 +483,6 @@ static void drm_test_check_broadcast_rgb_auto_cea_mode_vic_1(struct kunit *test) mode = drm_kunit_display_mode_from_cea_vic(test, drm, 1); KUNIT_ASSERT_NOT_NULL(test, mode); - drm = &priv->drm; crtc = priv->crtc; ret = light_up_connector(test, drm, crtc, conn, mode, ctx); KUNIT_ASSERT_EQ(test, ret, 0); @@ -520,18 +528,18 @@ static void drm_test_check_broadcast_rgb_full_cea_mode(struct kunit *test) 8); KUNIT_ASSERT_NOT_NULL(test, priv); + drm = &priv->drm; + crtc = priv->crtc; conn = &priv->connector; KUNIT_ASSERT_TRUE(test, conn->display_info.is_hdmi); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); - preferred = find_preferred_mode(conn); KUNIT_ASSERT_NOT_NULL(test, preferred); KUNIT_ASSERT_NE(test, drm_match_cea_mode(preferred), 1); - drm = &priv->drm; - crtc = priv->crtc; + ctx = drm_kunit_helper_acquire_ctx_alloc(test); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); KUNIT_ASSERT_EQ(test, ret, 0); @@ -588,7 +596,6 @@ static void drm_test_check_broadcast_rgb_full_cea_mode_vic_1(struct kunit *test) mode = drm_kunit_display_mode_from_cea_vic(test, drm, 1); KUNIT_ASSERT_NOT_NULL(test, mode); - drm = &priv->drm; crtc = priv->crtc; ret = light_up_connector(test, drm, crtc, conn, mode, ctx); KUNIT_ASSERT_EQ(test, ret, 0); @@ -636,18 +643,18 @@ static void drm_test_check_broadcast_rgb_limited_cea_mode(struct kunit *test) 8); KUNIT_ASSERT_NOT_NULL(test, priv); + drm = &priv->drm; + crtc = priv->crtc; conn = &priv->connector; KUNIT_ASSERT_TRUE(test, conn->display_info.is_hdmi); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); - preferred = find_preferred_mode(conn); KUNIT_ASSERT_NOT_NULL(test, preferred); KUNIT_ASSERT_NE(test, drm_match_cea_mode(preferred), 1); - drm = &priv->drm; - crtc = priv->crtc; + ctx = drm_kunit_helper_acquire_ctx_alloc(test); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); KUNIT_ASSERT_EQ(test, ret, 0); @@ -704,7 +711,6 @@ static void drm_test_check_broadcast_rgb_limited_cea_mode_vic_1(struct kunit *te mode = drm_kunit_display_mode_from_cea_vic(test, drm, 1); KUNIT_ASSERT_NOT_NULL(test, mode); - drm = &priv->drm; crtc = priv->crtc; ret = light_up_connector(test, drm, crtc, conn, mode, ctx); KUNIT_ASSERT_EQ(test, ret, 0); @@ -754,20 +760,20 @@ static void drm_test_check_output_bpc_crtc_mode_changed(struct kunit *test) 10); KUNIT_ASSERT_NOT_NULL(test, priv); + drm = &priv->drm; + crtc = priv->crtc; conn = &priv->connector; ret = set_connector_edid(test, conn, test_edid_hdmi_1080p_rgb_yuv_dc_max_200mhz, ARRAY_SIZE(test_edid_hdmi_1080p_rgb_yuv_dc_max_200mhz)); KUNIT_ASSERT_GT(test, ret, 0); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); - preferred = find_preferred_mode(conn); KUNIT_ASSERT_NOT_NULL(test, preferred); - drm = &priv->drm; - crtc = priv->crtc; + ctx = drm_kunit_helper_acquire_ctx_alloc(test); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); KUNIT_ASSERT_EQ(test, ret, 0); @@ -828,20 +834,20 @@ static void drm_test_check_output_bpc_crtc_mode_not_changed(struct kunit *test) 10); KUNIT_ASSERT_NOT_NULL(test, priv); + drm = &priv->drm; + crtc = priv->crtc; conn = &priv->connector; ret = set_connector_edid(test, conn, test_edid_hdmi_1080p_rgb_yuv_dc_max_200mhz, ARRAY_SIZE(test_edid_hdmi_1080p_rgb_yuv_dc_max_200mhz)); KUNIT_ASSERT_GT(test, ret, 0); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); - preferred = find_preferred_mode(conn); KUNIT_ASSERT_NOT_NULL(test, preferred); - drm = &priv->drm; - crtc = priv->crtc; + ctx = drm_kunit_helper_acquire_ctx_alloc(test); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); KUNIT_ASSERT_EQ(test, ret, 0); @@ -899,6 +905,8 @@ static void drm_test_check_output_bpc_dvi(struct kunit *test) 12); KUNIT_ASSERT_NOT_NULL(test, priv); + drm = &priv->drm; + crtc = priv->crtc; conn = &priv->connector; ret = set_connector_edid(test, conn, test_edid_dvi_1080p, @@ -908,14 +916,12 @@ static void drm_test_check_output_bpc_dvi(struct kunit *test) info = &conn->display_info; KUNIT_ASSERT_FALSE(test, info->is_hdmi); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); - preferred = find_preferred_mode(conn); KUNIT_ASSERT_NOT_NULL(test, preferred); - drm = &priv->drm; - crtc = priv->crtc; + ctx = drm_kunit_helper_acquire_ctx_alloc(test); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); KUNIT_ASSERT_EQ(test, ret, 0); @@ -946,21 +952,21 @@ static void drm_test_check_tmds_char_rate_rgb_8bpc(struct kunit *test) 8); KUNIT_ASSERT_NOT_NULL(test, priv); + drm = &priv->drm; + crtc = priv->crtc; conn = &priv->connector; ret = set_connector_edid(test, conn, test_edid_hdmi_1080p_rgb_max_200mhz, ARRAY_SIZE(test_edid_hdmi_1080p_rgb_max_200mhz)); KUNIT_ASSERT_GT(test, ret, 0); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); - preferred = find_preferred_mode(conn); KUNIT_ASSERT_NOT_NULL(test, preferred); KUNIT_ASSERT_FALSE(test, preferred->flags & DRM_MODE_FLAG_DBLCLK); - drm = &priv->drm; - crtc = priv->crtc; + ctx = drm_kunit_helper_acquire_ctx_alloc(test); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); KUNIT_ASSERT_EQ(test, ret, 0); @@ -993,21 +999,21 @@ static void drm_test_check_tmds_char_rate_rgb_10bpc(struct kunit *test) 10); KUNIT_ASSERT_NOT_NULL(test, priv); + drm = &priv->drm; + crtc = priv->crtc; conn = &priv->connector; ret = set_connector_edid(test, conn, test_edid_hdmi_1080p_rgb_yuv_dc_max_340mhz, ARRAY_SIZE(test_edid_hdmi_1080p_rgb_yuv_dc_max_340mhz)); KUNIT_ASSERT_GT(test, ret, 0); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); - preferred = find_preferred_mode(conn); KUNIT_ASSERT_NOT_NULL(test, preferred); KUNIT_ASSERT_FALSE(test, preferred->flags & DRM_MODE_FLAG_DBLCLK); - drm = &priv->drm; - crtc = priv->crtc; + ctx = drm_kunit_helper_acquire_ctx_alloc(test); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); KUNIT_ASSERT_EQ(test, ret, 0); @@ -1040,21 +1046,21 @@ static void drm_test_check_tmds_char_rate_rgb_12bpc(struct kunit *test) 12); KUNIT_ASSERT_NOT_NULL(test, priv); + drm = &priv->drm; + crtc = priv->crtc; conn = &priv->connector; ret = set_connector_edid(test, conn, test_edid_hdmi_1080p_rgb_yuv_dc_max_340mhz, ARRAY_SIZE(test_edid_hdmi_1080p_rgb_yuv_dc_max_340mhz)); KUNIT_ASSERT_GT(test, ret, 0); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); - preferred = find_preferred_mode(conn); KUNIT_ASSERT_NOT_NULL(test, preferred); KUNIT_ASSERT_FALSE(test, preferred->flags & DRM_MODE_FLAG_DBLCLK); - drm = &priv->drm; - crtc = priv->crtc; + ctx = drm_kunit_helper_acquire_ctx_alloc(test); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); KUNIT_ASSERT_EQ(test, ret, 0); @@ -1091,15 +1097,16 @@ static void drm_test_check_hdmi_funcs_reject_rate(struct kunit *test) 8); KUNIT_ASSERT_NOT_NULL(test, priv); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); - + drm = &priv->drm; + crtc = priv->crtc; conn = &priv->connector; + preferred = find_preferred_mode(conn); KUNIT_ASSERT_NOT_NULL(test, preferred); - drm = &priv->drm; - crtc = priv->crtc; + ctx = drm_kunit_helper_acquire_ctx_alloc(test); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); KUNIT_ASSERT_EQ(test, ret, 0); @@ -1147,6 +1154,8 @@ static void drm_test_check_max_tmds_rate_bpc_fallback(struct kunit *test) 12); KUNIT_ASSERT_NOT_NULL(test, priv); + drm = &priv->drm; + crtc = priv->crtc; conn = &priv->connector; ret = set_connector_edid(test, conn, test_edid_hdmi_1080p_rgb_yuv_dc_max_200mhz, @@ -1157,9 +1166,6 @@ static void drm_test_check_max_tmds_rate_bpc_fallback(struct kunit *test) KUNIT_ASSERT_TRUE(test, info->is_hdmi); KUNIT_ASSERT_GT(test, info->max_tmds_clock, 0); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); - preferred = find_preferred_mode(conn); KUNIT_ASSERT_NOT_NULL(test, preferred); KUNIT_ASSERT_FALSE(test, preferred->flags & DRM_MODE_FLAG_DBLCLK); @@ -1170,8 +1176,9 @@ static void drm_test_check_max_tmds_rate_bpc_fallback(struct kunit *test) rate = drm_hdmi_compute_mode_clock(preferred, 10, HDMI_COLORSPACE_RGB); KUNIT_ASSERT_LT(test, rate, info->max_tmds_clock * 1000); - drm = &priv->drm; - crtc = priv->crtc; + ctx = drm_kunit_helper_acquire_ctx_alloc(test); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); KUNIT_EXPECT_EQ(test, ret, 0); @@ -1216,6 +1223,8 @@ static void drm_test_check_max_tmds_rate_format_fallback(struct kunit *test) 12); KUNIT_ASSERT_NOT_NULL(test, priv); + drm = &priv->drm; + crtc = priv->crtc; conn = &priv->connector; ret = set_connector_edid(test, conn, test_edid_hdmi_1080p_rgb_yuv_dc_max_200mhz, @@ -1226,9 +1235,6 @@ static void drm_test_check_max_tmds_rate_format_fallback(struct kunit *test) KUNIT_ASSERT_TRUE(test, info->is_hdmi); KUNIT_ASSERT_GT(test, info->max_tmds_clock, 0); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); - preferred = find_preferred_mode(conn); KUNIT_ASSERT_NOT_NULL(test, preferred); KUNIT_ASSERT_FALSE(test, preferred->flags & DRM_MODE_FLAG_DBLCLK); @@ -1242,8 +1248,9 @@ static void drm_test_check_max_tmds_rate_format_fallback(struct kunit *test) rate = drm_hdmi_compute_mode_clock(preferred, 12, HDMI_COLORSPACE_YUV422); KUNIT_ASSERT_LT(test, rate, info->max_tmds_clock * 1000); - drm = &priv->drm; - crtc = priv->crtc; + ctx = drm_kunit_helper_acquire_ctx_alloc(test); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); KUNIT_EXPECT_EQ(test, ret, 0); @@ -1290,9 +1297,6 @@ static void drm_test_check_output_bpc_format_vic_1(struct kunit *test) KUNIT_ASSERT_TRUE(test, info->is_hdmi); KUNIT_ASSERT_GT(test, info->max_tmds_clock, 0); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); - mode = drm_kunit_display_mode_from_cea_vic(test, drm, 1); KUNIT_ASSERT_NOT_NULL(test, mode); @@ -1306,7 +1310,9 @@ static void drm_test_check_output_bpc_format_vic_1(struct kunit *test) rate = mode->clock * 1500; KUNIT_ASSERT_LT(test, rate, info->max_tmds_clock * 1000); - drm = &priv->drm; + ctx = drm_kunit_helper_acquire_ctx_alloc(test); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + crtc = priv->crtc; ret = light_up_connector(test, drm, crtc, conn, mode, ctx); KUNIT_EXPECT_EQ(test, ret, 0); @@ -1340,6 +1346,8 @@ static void drm_test_check_output_bpc_format_driver_rgb_only(struct kunit *test) 12); KUNIT_ASSERT_NOT_NULL(test, priv); + drm = &priv->drm; + crtc = priv->crtc; conn = &priv->connector; ret = set_connector_edid(test, conn, test_edid_hdmi_1080p_rgb_yuv_dc_max_200mhz, @@ -1350,9 +1358,6 @@ static void drm_test_check_output_bpc_format_driver_rgb_only(struct kunit *test) KUNIT_ASSERT_TRUE(test, info->is_hdmi); KUNIT_ASSERT_GT(test, info->max_tmds_clock, 0); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); - preferred = find_preferred_mode(conn); KUNIT_ASSERT_NOT_NULL(test, preferred); @@ -1371,8 +1376,9 @@ static void drm_test_check_output_bpc_format_driver_rgb_only(struct kunit *test) rate = drm_hdmi_compute_mode_clock(preferred, 12, HDMI_COLORSPACE_YUV422); KUNIT_ASSERT_LT(test, rate, info->max_tmds_clock * 1000); - drm = &priv->drm; - crtc = priv->crtc; + ctx = drm_kunit_helper_acquire_ctx_alloc(test); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); KUNIT_EXPECT_EQ(test, ret, 0); @@ -1407,6 +1413,8 @@ static void drm_test_check_output_bpc_format_display_rgb_only(struct kunit *test 12); KUNIT_ASSERT_NOT_NULL(test, priv); + drm = &priv->drm; + crtc = priv->crtc; conn = &priv->connector; ret = set_connector_edid(test, conn, test_edid_hdmi_1080p_rgb_max_200mhz, @@ -1417,9 +1425,6 @@ static void drm_test_check_output_bpc_format_display_rgb_only(struct kunit *test KUNIT_ASSERT_TRUE(test, info->is_hdmi); KUNIT_ASSERT_GT(test, info->max_tmds_clock, 0); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); - preferred = find_preferred_mode(conn); KUNIT_ASSERT_NOT_NULL(test, preferred); @@ -1438,8 +1443,9 @@ static void drm_test_check_output_bpc_format_display_rgb_only(struct kunit *test rate = drm_hdmi_compute_mode_clock(preferred, 12, HDMI_COLORSPACE_YUV422); KUNIT_ASSERT_LT(test, rate, info->max_tmds_clock * 1000); - drm = &priv->drm; - crtc = priv->crtc; + ctx = drm_kunit_helper_acquire_ctx_alloc(test); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); KUNIT_EXPECT_EQ(test, ret, 0); @@ -1473,6 +1479,8 @@ static void drm_test_check_output_bpc_format_driver_8bpc_only(struct kunit *test 8); KUNIT_ASSERT_NOT_NULL(test, priv); + drm = &priv->drm; + crtc = priv->crtc; conn = &priv->connector; ret = set_connector_edid(test, conn, test_edid_hdmi_1080p_rgb_yuv_dc_max_340mhz, @@ -1483,9 +1491,6 @@ static void drm_test_check_output_bpc_format_driver_8bpc_only(struct kunit *test KUNIT_ASSERT_TRUE(test, info->is_hdmi); KUNIT_ASSERT_GT(test, info->max_tmds_clock, 0); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); - preferred = find_preferred_mode(conn); KUNIT_ASSERT_NOT_NULL(test, preferred); @@ -1496,8 +1501,9 @@ static void drm_test_check_output_bpc_format_driver_8bpc_only(struct kunit *test rate = drm_hdmi_compute_mode_clock(preferred, 12, HDMI_COLORSPACE_RGB); KUNIT_ASSERT_LT(test, rate, info->max_tmds_clock * 1000); - drm = &priv->drm; - crtc = priv->crtc; + ctx = drm_kunit_helper_acquire_ctx_alloc(test); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); KUNIT_EXPECT_EQ(test, ret, 0); @@ -1533,6 +1539,8 @@ static void drm_test_check_output_bpc_format_display_8bpc_only(struct kunit *tes 12); KUNIT_ASSERT_NOT_NULL(test, priv); + drm = &priv->drm; + crtc = priv->crtc; conn = &priv->connector; ret = set_connector_edid(test, conn, test_edid_hdmi_1080p_rgb_max_340mhz, @@ -1543,9 +1551,6 @@ static void drm_test_check_output_bpc_format_display_8bpc_only(struct kunit *tes KUNIT_ASSERT_TRUE(test, info->is_hdmi); KUNIT_ASSERT_GT(test, info->max_tmds_clock, 0); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); - preferred = find_preferred_mode(conn); KUNIT_ASSERT_NOT_NULL(test, preferred); @@ -1556,8 +1561,9 @@ static void drm_test_check_output_bpc_format_display_8bpc_only(struct kunit *tes rate = drm_hdmi_compute_mode_clock(preferred, 12, HDMI_COLORSPACE_RGB); KUNIT_ASSERT_LT(test, rate, info->max_tmds_clock * 1000); - drm = &priv->drm; - crtc = priv->crtc; + ctx = drm_kunit_helper_acquire_ctx_alloc(test); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); KUNIT_EXPECT_EQ(test, ret, 0); diff --git a/drivers/gpu/drm/xe/xe_drm_client.c b/drivers/gpu/drm/xe/xe_drm_client.c index 63f30b6df70b..2d4874d2b922 100644 --- a/drivers/gpu/drm/xe/xe_drm_client.c +++ b/drivers/gpu/drm/xe/xe_drm_client.c @@ -135,8 +135,8 @@ void xe_drm_client_add_bo(struct xe_drm_client *client, XE_WARN_ON(bo->client); XE_WARN_ON(!list_empty(&bo->client_link)); - spin_lock(&client->bos_lock); bo->client = xe_drm_client_get(client); + spin_lock(&client->bos_lock); list_add_tail(&bo->client_link, &client->bos_list); spin_unlock(&client->bos_lock); } diff --git a/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c b/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c index 423856cc18d4..d414421f8c13 100644 --- a/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c +++ b/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c @@ -57,12 +57,35 @@ bool xe_ttm_stolen_cpu_access_needs_ggtt(struct xe_device *xe) return GRAPHICS_VERx100(xe) < 1270 && !IS_DGFX(xe); } +static u32 get_wopcm_size(struct xe_device *xe) +{ + u32 wopcm_size; + u64 val; + + val = xe_mmio_read64_2x32(xe_root_tile_mmio(xe), STOLEN_RESERVED); + val = REG_FIELD_GET64(WOPCM_SIZE_MASK, val); + + switch (val) { + case 0x5 ... 0x6: + val--; + fallthrough; + case 0x0 ... 0x3: + wopcm_size = (1U << val) * SZ_1M; + break; + default: + WARN(1, "Missing case wopcm_size=%llx\n", val); + wopcm_size = 0; + } + + return wopcm_size; +} + static s64 detect_bar2_dgfx(struct xe_device *xe, struct xe_ttm_stolen_mgr *mgr) { struct xe_tile *tile = xe_device_get_root_tile(xe); struct xe_mmio *mmio = xe_root_tile_mmio(xe); struct pci_dev *pdev = to_pci_dev(xe->drm.dev); - u64 stolen_size; + u64 stolen_size, wopcm_size; u64 tile_offset; u64 tile_size; @@ -74,7 +97,13 @@ static s64 detect_bar2_dgfx(struct xe_device *xe, struct xe_ttm_stolen_mgr *mgr) if (drm_WARN_ON(&xe->drm, tile_size < mgr->stolen_base)) return 0; + /* Carve out the top of DSM as it contains the reserved WOPCM region */ + wopcm_size = get_wopcm_size(xe); + if (drm_WARN_ON(&xe->drm, !wopcm_size)) + return 0; + stolen_size = tile_size - mgr->stolen_base; + stolen_size -= wopcm_size; /* Verify usage fits in the actual resource available */ if (mgr->stolen_base + stolen_size <= pci_resource_len(pdev, LMEM_BAR)) @@ -89,29 +118,6 @@ static s64 detect_bar2_dgfx(struct xe_device *xe, struct xe_ttm_stolen_mgr *mgr) return ALIGN_DOWN(stolen_size, SZ_1M); } -static u32 get_wopcm_size(struct xe_device *xe) -{ - u32 wopcm_size; - u64 val; - - val = xe_mmio_read64_2x32(xe_root_tile_mmio(xe), STOLEN_RESERVED); - val = REG_FIELD_GET64(WOPCM_SIZE_MASK, val); - - switch (val) { - case 0x5 ... 0x6: - val--; - fallthrough; - case 0x0 ... 0x3: - wopcm_size = (1U << val) * SZ_1M; - break; - default: - WARN(1, "Missing case wopcm_size=%llx\n", val); - wopcm_size = 0; - } - - return wopcm_size; -} - static u32 detect_bar2_integrated(struct xe_device *xe, struct xe_ttm_stolen_mgr *mgr) { struct pci_dev *pdev = to_pci_dev(xe->drm.dev); diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c index 7b1d091f3c09..46cae925b095 100644 --- a/drivers/gpu/host1x/dev.c +++ b/drivers/gpu/host1x/dev.c @@ -619,6 +619,8 @@ static int host1x_probe(struct platform_device *pdev) goto free_contexts; } + mutex_init(&host->intr_mutex); + pm_runtime_enable(&pdev->dev); err = devm_tegra_core_dev_init_opp_table_common(&pdev->dev); diff --git a/drivers/gpu/host1x/intr.c b/drivers/gpu/host1x/intr.c index b3285dd10180..f77a678949e9 100644 --- a/drivers/gpu/host1x/intr.c +++ b/drivers/gpu/host1x/intr.c @@ -104,8 +104,6 @@ int host1x_intr_init(struct host1x *host) unsigned int id; int i, err; - mutex_init(&host->intr_mutex); - for (id = 0; id < host1x_syncpt_nb_pts(host); ++id) { struct host1x_syncpt *syncpt = &host->syncpt[id]; diff --git a/drivers/infiniband/ulp/ipoib/ipoib_netlink.c b/drivers/infiniband/ulp/ipoib/ipoib_netlink.c index 9ad8d9856275..53db7c8191e3 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_netlink.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_netlink.c @@ -97,10 +97,13 @@ out_err: return ret; } -static int ipoib_new_child_link(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +static int ipoib_new_child_link(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { + struct net *link_net = rtnl_newlink_link_net(params); + struct nlattr **data = params->data; + struct nlattr **tb = params->tb; struct net_device *pdev; struct ipoib_dev_priv *ppriv; u16 child_pkey; @@ -109,7 +112,7 @@ static int ipoib_new_child_link(struct net *src_net, struct net_device *dev, if (!tb[IFLA_LINK]) return -EINVAL; - pdev = __dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK])); + pdev = __dev_get_by_index(link_net, nla_get_u32(tb[IFLA_LINK])); if (!pdev || pdev->type != ARPHRD_INFINIBAND) return -ENODEV; diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h index 0bbda60d3cdc..23caea22f8dc 100644 --- a/drivers/iommu/amd/amd_iommu_types.h +++ b/drivers/iommu/amd/amd_iommu_types.h @@ -175,6 +175,7 @@ #define CONTROL_GAM_EN 25 #define CONTROL_GALOG_EN 28 #define CONTROL_GAINT_EN 29 +#define CONTROL_EPH_EN 45 #define CONTROL_XT_EN 50 #define CONTROL_INTCAPXT_EN 51 #define CONTROL_IRTCACHEDIS 59 diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index c5cd92edada0..cb536d372b12 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -2653,6 +2653,10 @@ static void iommu_init_flags(struct amd_iommu *iommu) /* Set IOTLB invalidation timeout to 1s */ iommu_set_inv_tlb_timeout(iommu, CTRL_INV_TO_1S); + + /* Enable Enhanced Peripheral Page Request Handling */ + if (check_feature(FEATURE_EPHSUP)) + iommu_feature_enable(iommu, CONTROL_EPH_EN); } static void iommu_apply_resume_quirks(struct amd_iommu *iommu) @@ -3194,7 +3198,7 @@ out: return true; } -static void iommu_snp_enable(void) +static __init void iommu_snp_enable(void) { #ifdef CONFIG_KVM_AMD_SEV if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) @@ -3219,6 +3223,14 @@ static void iommu_snp_enable(void) goto disable_snp; } + /* + * Enable host SNP support once SNP support is checked on IOMMU. + */ + if (snp_rmptable_init()) { + pr_warn("SNP: RMP initialization failed, SNP cannot be supported.\n"); + goto disable_snp; + } + pr_info("IOMMU SNP support enabled.\n"); return; @@ -3318,6 +3330,19 @@ static int __init iommu_go_to_state(enum iommu_init_state state) ret = state_next(); } + /* + * SNP platform initilazation requires IOMMUs to be fully configured. + * If the SNP support on IOMMUs has NOT been checked, simply mark SNP + * as unsupported. If the SNP support on IOMMUs has been checked and + * host SNP support enabled but RMP enforcement has not been enabled + * in IOMMUs, then the system is in a half-baked state, but can limp + * along as all memory should be Hypervisor-Owned in the RMP. WARN, + * but leave SNP as "supported" to avoid confusing the kernel. + */ + if (ret && cc_platform_has(CC_ATTR_HOST_SEV_SNP) && + !WARN_ON_ONCE(amd_iommu_snp_en)) + cc_platform_clear(CC_ATTR_HOST_SEV_SNP); + return ret; } @@ -3426,18 +3451,23 @@ void __init amd_iommu_detect(void) int ret; if (no_iommu || (iommu_detected && !gart_iommu_aperture)) - return; + goto disable_snp; if (!amd_iommu_sme_check()) - return; + goto disable_snp; ret = iommu_go_to_state(IOMMU_IVRS_DETECTED); if (ret) - return; + goto disable_snp; amd_iommu_detected = true; iommu_detected = 1; x86_init.iommu.iommu_init = amd_iommu_init; + return; + +disable_snp: + if (cc_platform_has(CC_ATTR_HOST_SEV_SNP)) + cc_platform_clear(CC_ATTR_HOST_SEV_SNP); } /**************************************************************************** diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c index c666ecab955d..69e23e017d9e 100644 --- a/drivers/iommu/exynos-iommu.c +++ b/drivers/iommu/exynos-iommu.c @@ -249,7 +249,7 @@ struct exynos_iommu_domain { struct list_head clients; /* list of sysmmu_drvdata.domain_node */ sysmmu_pte_t *pgtable; /* lv1 page table, 16KB */ short *lv2entcnt; /* free lv2 entry counter for each section */ - spinlock_t lock; /* lock for modyfying list of clients */ + spinlock_t lock; /* lock for modifying list of clients */ spinlock_t pgtablelock; /* lock for modifying page table @ pgtable */ struct iommu_domain domain; /* generic domain data structure */ }; @@ -292,7 +292,7 @@ struct sysmmu_drvdata { struct clk *aclk; /* SYSMMU's aclk clock */ struct clk *pclk; /* SYSMMU's pclk clock */ struct clk *clk_master; /* master's device clock */ - spinlock_t lock; /* lock for modyfying state */ + spinlock_t lock; /* lock for modifying state */ bool active; /* current status */ struct exynos_iommu_domain *domain; /* domain we belong to */ struct list_head domain_node; /* node for domain clients list */ @@ -746,7 +746,7 @@ static int exynos_sysmmu_probe(struct platform_device *pdev) ret = devm_request_irq(dev, irq, exynos_sysmmu_irq, 0, dev_name(dev), data); if (ret) { - dev_err(dev, "Unabled to register handler of irq %d\n", irq); + dev_err(dev, "Unable to register handler of irq %d\n", irq); return ret; } diff --git a/drivers/iommu/intel/prq.c b/drivers/iommu/intel/prq.c index c2d792db52c3..064194399b38 100644 --- a/drivers/iommu/intel/prq.c +++ b/drivers/iommu/intel/prq.c @@ -87,7 +87,9 @@ prq_retry: struct page_req_dsc *req; req = &iommu->prq[head / sizeof(*req)]; - if (!req->pasid_present || req->pasid != pasid) { + if (req->rid != sid || + (req->pasid_present && pasid != req->pasid) || + (!req->pasid_present && pasid != IOMMU_NO_PASID)) { head = (head + sizeof(*req)) & PRQ_RING_MASK; continue; } diff --git a/drivers/iommu/io-pgfault.c b/drivers/iommu/io-pgfault.c index 4674e618797c..8b5926c1452e 100644 --- a/drivers/iommu/io-pgfault.c +++ b/drivers/iommu/io-pgfault.c @@ -478,6 +478,7 @@ void iopf_queue_remove_device(struct iopf_queue *queue, struct device *dev) ops->page_response(dev, iopf, &resp); list_del_init(&group->pending_node); + iopf_free_group(group); } mutex_unlock(&fault_param->lock); diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 870c3cdbd0f6..60aed01e54f2 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -1756,7 +1756,7 @@ static int iommu_get_def_domain_type(struct iommu_group *group, group->id); /* - * Try to recover, drivers are allowed to force IDENITY or DMA, IDENTITY + * Try to recover, drivers are allowed to force IDENTITY or DMA, IDENTITY * takes precedence. */ if (type == IOMMU_DOMAIN_IDENTITY) diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c index 4b6e91372526..345ea91629e0 100644 --- a/drivers/mmc/host/mtk-sd.c +++ b/drivers/mmc/host/mtk-sd.c @@ -273,6 +273,7 @@ #define MSDC_PAD_TUNE_CMD2_SEL BIT(21) /* RW */ #define PAD_DS_TUNE_DLY_SEL BIT(0) /* RW */ +#define PAD_DS_TUNE_DLY2_SEL BIT(1) /* RW */ #define PAD_DS_TUNE_DLY1 GENMASK(6, 2) /* RW */ #define PAD_DS_TUNE_DLY2 GENMASK(11, 7) /* RW */ #define PAD_DS_TUNE_DLY3 GENMASK(16, 12) /* RW */ @@ -318,6 +319,7 @@ /* EMMC50_PAD_DS_TUNE mask */ #define PAD_DS_DLY_SEL BIT(16) /* RW */ +#define PAD_DS_DLY2_SEL BIT(15) /* RW */ #define PAD_DS_DLY1 GENMASK(14, 10) /* RW */ #define PAD_DS_DLY3 GENMASK(4, 0) /* RW */ @@ -2504,13 +2506,23 @@ tune_done: static int msdc_prepare_hs400_tuning(struct mmc_host *mmc, struct mmc_ios *ios) { struct msdc_host *host = mmc_priv(mmc); + host->hs400_mode = true; - if (host->top_base) - writel(host->hs400_ds_delay, - host->top_base + EMMC50_PAD_DS_TUNE); - else - writel(host->hs400_ds_delay, host->base + PAD_DS_TUNE); + if (host->top_base) { + if (host->hs400_ds_dly3) + sdr_set_field(host->top_base + EMMC50_PAD_DS_TUNE, + PAD_DS_DLY3, host->hs400_ds_dly3); + if (host->hs400_ds_delay) + writel(host->hs400_ds_delay, + host->top_base + EMMC50_PAD_DS_TUNE); + } else { + if (host->hs400_ds_dly3) + sdr_set_field(host->base + PAD_DS_TUNE, + PAD_DS_TUNE_DLY3, host->hs400_ds_dly3); + if (host->hs400_ds_delay) + writel(host->hs400_ds_delay, host->base + PAD_DS_TUNE); + } /* hs400 mode must set it to 0 */ sdr_clr_bits(host->base + MSDC_PATCH_BIT2, MSDC_PATCH_BIT2_CFGCRCSTS); /* to improve read performance, set outstanding to 2 */ @@ -2530,14 +2542,11 @@ static int msdc_execute_hs400_tuning(struct mmc_host *mmc, struct mmc_card *card if (host->top_base) { sdr_set_bits(host->top_base + EMMC50_PAD_DS_TUNE, PAD_DS_DLY_SEL); - if (host->hs400_ds_dly3) - sdr_set_field(host->top_base + EMMC50_PAD_DS_TUNE, - PAD_DS_DLY3, host->hs400_ds_dly3); + sdr_clr_bits(host->top_base + EMMC50_PAD_DS_TUNE, + PAD_DS_DLY2_SEL); } else { sdr_set_bits(host->base + PAD_DS_TUNE, PAD_DS_TUNE_DLY_SEL); - if (host->hs400_ds_dly3) - sdr_set_field(host->base + PAD_DS_TUNE, - PAD_DS_TUNE_DLY3, host->hs400_ds_dly3); + sdr_clr_bits(host->base + PAD_DS_TUNE, PAD_DS_TUNE_DLY2_SEL); } host->hs400_tuning = true; diff --git a/drivers/mmc/host/sdhci_am654.c b/drivers/mmc/host/sdhci_am654.c index b73f673db92b..f75c31815ab0 100644 --- a/drivers/mmc/host/sdhci_am654.c +++ b/drivers/mmc/host/sdhci_am654.c @@ -155,7 +155,6 @@ struct sdhci_am654_data { u32 tuning_loop; #define SDHCI_AM654_QUIRK_FORCE_CDTEST BIT(0) -#define SDHCI_AM654_QUIRK_SUPPRESS_V1P8_ENA BIT(1) }; struct window { @@ -357,29 +356,6 @@ static void sdhci_j721e_4bit_set_clock(struct sdhci_host *host, sdhci_set_clock(host, clock); } -static int sdhci_am654_start_signal_voltage_switch(struct mmc_host *mmc, struct mmc_ios *ios) -{ - struct sdhci_host *host = mmc_priv(mmc); - struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); - struct sdhci_am654_data *sdhci_am654 = sdhci_pltfm_priv(pltfm_host); - int ret; - - if ((sdhci_am654->quirks & SDHCI_AM654_QUIRK_SUPPRESS_V1P8_ENA) && - ios->signal_voltage == MMC_SIGNAL_VOLTAGE_180) { - if (!IS_ERR(mmc->supply.vqmmc)) { - ret = mmc_regulator_set_vqmmc(mmc, ios); - if (ret < 0) { - pr_err("%s: Switching to 1.8V signalling voltage failed,\n", - mmc_hostname(mmc)); - return -EIO; - } - } - return 0; - } - - return sdhci_start_signal_voltage_switch(mmc, ios); -} - static u8 sdhci_am654_write_power_on(struct sdhci_host *host, u8 val, int reg) { writeb(val, host->ioaddr + reg); @@ -868,11 +844,6 @@ static int sdhci_am654_get_of_property(struct platform_device *pdev, if (device_property_read_bool(dev, "ti,fails-without-test-cd")) sdhci_am654->quirks |= SDHCI_AM654_QUIRK_FORCE_CDTEST; - /* Suppress v1p8 ena for eMMC and SD with vqmmc supply */ - if (!!of_parse_phandle(dev->of_node, "vmmc-supply", 0) == - !!of_parse_phandle(dev->of_node, "vqmmc-supply", 0)) - sdhci_am654->quirks |= SDHCI_AM654_QUIRK_SUPPRESS_V1P8_ENA; - sdhci_get_of_property(pdev); return 0; @@ -969,7 +940,6 @@ static int sdhci_am654_probe(struct platform_device *pdev) goto err_pltfm_free; } - host->mmc_host_ops.start_signal_voltage_switch = sdhci_am654_start_signal_voltage_switch; host->mmc_host_ops.execute_tuning = sdhci_am654_execute_tuning; pm_runtime_get_noresume(dev); diff --git a/drivers/net/amt.c b/drivers/net/amt.c index 98c6205ed19f..53899b70fae1 100644 --- a/drivers/net/amt.c +++ b/drivers/net/amt.c @@ -3161,14 +3161,17 @@ static int amt_validate(struct nlattr *tb[], struct nlattr *data[], return 0; } -static int amt_newlink(struct net *net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +static int amt_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { + struct net *link_net = rtnl_newlink_link_net(params); struct amt_dev *amt = netdev_priv(dev); + struct nlattr **data = params->data; + struct nlattr **tb = params->tb; int err = -EINVAL; - amt->net = net; + amt->net = link_net; amt->mode = nla_get_u32(data[IFLA_AMT_MODE]); if (data[IFLA_AMT_MAX_TUNNELS] && @@ -3183,7 +3186,7 @@ static int amt_newlink(struct net *net, struct net_device *dev, amt->hash_buckets = AMT_HSIZE; amt->nr_tunnels = 0; get_random_bytes(&amt->hash_seed, sizeof(amt->hash_seed)); - amt->stream_dev = dev_get_by_index(net, + amt->stream_dev = dev_get_by_index(link_net, nla_get_u32(data[IFLA_AMT_LINK])); if (!amt->stream_dev) { NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_AMT_LINK], diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c index 70814303aab8..d1473c5f8eef 100644 --- a/drivers/net/bareudp.c +++ b/drivers/net/bareudp.c @@ -698,10 +698,13 @@ static void bareudp_dellink(struct net_device *dev, struct list_head *head) unregister_netdevice_queue(dev, head); } -static int bareudp_newlink(struct net *net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +static int bareudp_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { + struct net *link_net = rtnl_newlink_link_net(params); + struct nlattr **data = params->data; + struct nlattr **tb = params->tb; struct bareudp_conf conf; int err; @@ -709,7 +712,7 @@ static int bareudp_newlink(struct net *net, struct net_device *dev, if (err) return err; - err = bareudp_configure(net, dev, &conf, extack); + err = bareudp_configure(link_net, dev, &conf, extack); if (err) return err; diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c index 2a6a424806aa..ac5e402c34bc 100644 --- a/drivers/net/bonding/bond_netlink.c +++ b/drivers/net/bonding/bond_netlink.c @@ -564,10 +564,12 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[], return 0; } -static int bond_newlink(struct net *src_net, struct net_device *bond_dev, - struct nlattr *tb[], struct nlattr *data[], +static int bond_newlink(struct net_device *bond_dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { + struct nlattr **data = params->data; + struct nlattr **tb = params->tb; int err; err = bond_changelink(bond_dev, tb, data, extack); diff --git a/drivers/net/can/c_can/c_can_platform.c b/drivers/net/can/c_can/c_can_platform.c index 399844809bbe..19c86b94a40e 100644 --- a/drivers/net/can/c_can/c_can_platform.c +++ b/drivers/net/can/c_can/c_can_platform.c @@ -269,30 +269,22 @@ static int c_can_plat_probe(struct platform_device *pdev) /* get the appropriate clk */ clk = devm_clk_get(&pdev->dev, NULL); - if (IS_ERR(clk)) { - ret = PTR_ERR(clk); - goto exit; - } + if (IS_ERR(clk)) + return PTR_ERR(clk); /* get the platform data */ irq = platform_get_irq(pdev, 0); - if (irq < 0) { - ret = irq; - goto exit; - } + if (irq < 0) + return irq; addr = devm_platform_get_and_ioremap_resource(pdev, 0, &mem); - if (IS_ERR(addr)) { - ret = PTR_ERR(addr); - goto exit; - } + if (IS_ERR(addr)) + return PTR_ERR(addr); /* allocate the c_can device */ dev = alloc_c_can_dev(drvdata->msg_obj_num); - if (!dev) { - ret = -ENOMEM; - goto exit; - } + if (!dev) + return -ENOMEM; priv = netdev_priv(dev); switch (drvdata->id) { @@ -324,33 +316,22 @@ static int c_can_plat_probe(struct platform_device *pdev) /* Check if we need custom RAMINIT via syscon. Mostly for TI * platforms. Only supported with DT boot. */ - if (np && of_property_read_bool(np, "syscon-raminit")) { + if (np && of_property_present(np, "syscon-raminit")) { + unsigned int args[2]; u32 id; struct c_can_raminit *raminit = &priv->raminit_sys; ret = -EINVAL; - raminit->syscon = syscon_regmap_lookup_by_phandle(np, - "syscon-raminit"); + raminit->syscon = syscon_regmap_lookup_by_phandle_args(np, + "syscon-raminit", + 2, args); if (IS_ERR(raminit->syscon)) { - /* can fail with -EPROBE_DEFER */ ret = PTR_ERR(raminit->syscon); - free_c_can_dev(dev); - return ret; - } - - if (of_property_read_u32_index(np, "syscon-raminit", 1, - &raminit->reg)) { - dev_err(&pdev->dev, - "couldn't get the RAMINIT reg. offset!\n"); goto exit_free_device; } - if (of_property_read_u32_index(np, "syscon-raminit", 2, - &id)) { - dev_err(&pdev->dev, - "couldn't get the CAN instance ID\n"); - goto exit_free_device; - } + raminit->reg = args[0]; + id = args[1]; if (id >= drvdata->raminit_num) { dev_err(&pdev->dev, @@ -396,8 +377,6 @@ exit_pm_runtime: pm_runtime_disable(priv->device); exit_free_device: free_c_can_dev(dev); -exit: - dev_err(&pdev->dev, "probe failed\n"); return ret; } diff --git a/drivers/net/can/dev/netlink.c b/drivers/net/can/dev/netlink.c index 01aacdcda260..f1db9b7ffd4d 100644 --- a/drivers/net/can/dev/netlink.c +++ b/drivers/net/can/dev/netlink.c @@ -624,8 +624,8 @@ nla_put_failure: return -EMSGSIZE; } -static int can_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +static int can_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { return -EOPNOTSUPP; diff --git a/drivers/net/can/flexcan/flexcan-core.c b/drivers/net/can/flexcan/flexcan-core.c index ac1a860986df..b347a1c93536 100644 --- a/drivers/net/can/flexcan/flexcan-core.c +++ b/drivers/net/can/flexcan/flexcan-core.c @@ -386,6 +386,16 @@ static const struct flexcan_devtype_data fsl_lx2160a_r1_devtype_data = { FLEXCAN_QUIRK_SUPPORT_RX_MAILBOX_RTR, }; +static const struct flexcan_devtype_data nxp_s32g2_devtype_data = { + .quirks = FLEXCAN_QUIRK_DISABLE_RXFG | FLEXCAN_QUIRK_ENABLE_EACEN_RRS | + FLEXCAN_QUIRK_DISABLE_MECR | FLEXCAN_QUIRK_BROKEN_PERR_STATE | + FLEXCAN_QUIRK_USE_RX_MAILBOX | FLEXCAN_QUIRK_SUPPORT_FD | + FLEXCAN_QUIRK_SUPPORT_ECC | FLEXCAN_QUIRK_NR_IRQ_3 | + FLEXCAN_QUIRK_SUPPORT_RX_MAILBOX | + FLEXCAN_QUIRK_SUPPORT_RX_MAILBOX_RTR | + FLEXCAN_QUIRK_SECONDARY_MB_IRQ, +}; + static const struct can_bittiming_const flexcan_bittiming_const = { .name = DRV_NAME, .tseg1_min = 4, @@ -1762,14 +1772,25 @@ static int flexcan_open(struct net_device *dev) goto out_free_irq_boff; } + if (priv->devtype_data.quirks & FLEXCAN_QUIRK_SECONDARY_MB_IRQ) { + err = request_irq(priv->irq_secondary_mb, + flexcan_irq, IRQF_SHARED, dev->name, dev); + if (err) + goto out_free_irq_err; + } + flexcan_chip_interrupts_enable(dev); netif_start_queue(dev); return 0; + out_free_irq_err: + if (priv->devtype_data.quirks & FLEXCAN_QUIRK_NR_IRQ_3) + free_irq(priv->irq_err, dev); out_free_irq_boff: - free_irq(priv->irq_boff, dev); + if (priv->devtype_data.quirks & FLEXCAN_QUIRK_NR_IRQ_3) + free_irq(priv->irq_boff, dev); out_free_irq: free_irq(dev->irq, dev); out_can_rx_offload_disable: @@ -1794,6 +1815,9 @@ static int flexcan_close(struct net_device *dev) netif_stop_queue(dev); flexcan_chip_interrupts_disable(dev); + if (priv->devtype_data.quirks & FLEXCAN_QUIRK_SECONDARY_MB_IRQ) + free_irq(priv->irq_secondary_mb, dev); + if (priv->devtype_data.quirks & FLEXCAN_QUIRK_NR_IRQ_3) { free_irq(priv->irq_err, dev); free_irq(priv->irq_boff, dev); @@ -2041,6 +2065,7 @@ static const struct of_device_id flexcan_of_match[] = { { .compatible = "fsl,vf610-flexcan", .data = &fsl_vf610_devtype_data, }, { .compatible = "fsl,ls1021ar2-flexcan", .data = &fsl_ls1021a_r2_devtype_data, }, { .compatible = "fsl,lx2160ar1-flexcan", .data = &fsl_lx2160a_r1_devtype_data, }, + { .compatible = "nxp,s32g2-flexcan", .data = &nxp_s32g2_devtype_data, }, { /* sentinel */ }, }; MODULE_DEVICE_TABLE(of, flexcan_of_match); @@ -2187,6 +2212,14 @@ static int flexcan_probe(struct platform_device *pdev) } } + if (priv->devtype_data.quirks & FLEXCAN_QUIRK_SECONDARY_MB_IRQ) { + priv->irq_secondary_mb = platform_get_irq_byname(pdev, "mb-1"); + if (priv->irq_secondary_mb < 0) { + err = priv->irq_secondary_mb; + goto failed_platform_get_irq; + } + } + if (priv->devtype_data.quirks & FLEXCAN_QUIRK_SUPPORT_FD) { priv->can.ctrlmode_supported |= CAN_CTRLMODE_FD | CAN_CTRLMODE_FD_NON_ISO; diff --git a/drivers/net/can/flexcan/flexcan.h b/drivers/net/can/flexcan/flexcan.h index 4933d8c7439e..2cf886618c96 100644 --- a/drivers/net/can/flexcan/flexcan.h +++ b/drivers/net/can/flexcan/flexcan.h @@ -70,6 +70,10 @@ #define FLEXCAN_QUIRK_SUPPORT_RX_FIFO BIT(16) /* Setup stop mode with ATF SCMI protocol to support wakeup */ #define FLEXCAN_QUIRK_SETUP_STOP_MODE_SCMI BIT(17) +/* Device has two separate interrupt lines for two mailbox ranges, which + * both need to have an interrupt handler registered. + */ +#define FLEXCAN_QUIRK_SECONDARY_MB_IRQ BIT(18) struct flexcan_devtype_data { u32 quirks; /* quirks needed for different IP cores */ @@ -107,6 +111,7 @@ struct flexcan_priv { int irq_boff; int irq_err; + int irq_secondary_mb; /* IPC handle when setup stop mode by System Controller firmware(scfw) */ struct imx_sc_ipc *sc_ipc_handle; diff --git a/drivers/net/can/rockchip/rockchip_canfd-core.c b/drivers/net/can/rockchip/rockchip_canfd-core.c index d9a937ba126c..46201c126703 100644 --- a/drivers/net/can/rockchip/rockchip_canfd-core.c +++ b/drivers/net/can/rockchip/rockchip_canfd-core.c @@ -236,11 +236,6 @@ static void rkcanfd_chip_fifo_setup(struct rkcanfd_priv *priv) { u32 reg; - /* TXE FIFO */ - reg = rkcanfd_read(priv, RKCANFD_REG_RX_FIFO_CTRL); - reg |= RKCANFD_REG_RX_FIFO_CTRL_RX_FIFO_ENABLE; - rkcanfd_write(priv, RKCANFD_REG_RX_FIFO_CTRL, reg); - /* RX FIFO */ reg = rkcanfd_read(priv, RKCANFD_REG_RX_FIFO_CTRL); reg |= RKCANFD_REG_RX_FIFO_CTRL_RX_FIFO_ENABLE; diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c index b6f4de375df7..3ccac6781b98 100644 --- a/drivers/net/can/usb/gs_usb.c +++ b/drivers/net/can/usb/gs_usb.c @@ -43,6 +43,9 @@ #define USB_XYLANTA_SAINT3_VENDOR_ID 0x16d0 #define USB_XYLANTA_SAINT3_PRODUCT_ID 0x0f30 +#define USB_CANNECTIVITY_VENDOR_ID 0x1209 +#define USB_CANNECTIVITY_PRODUCT_ID 0xca01 + /* Timestamp 32 bit timer runs at 1 MHz (1 µs tick). Worker accounts * for timer overflow (will be after ~71 minutes) */ @@ -1546,6 +1549,8 @@ static const struct usb_device_id gs_usb_table[] = { USB_ABE_CANDEBUGGER_FD_PRODUCT_ID, 0) }, { USB_DEVICE_INTERFACE_NUMBER(USB_XYLANTA_SAINT3_VENDOR_ID, USB_XYLANTA_SAINT3_PRODUCT_ID, 0) }, + { USB_DEVICE_INTERFACE_NUMBER(USB_CANNECTIVITY_VENDOR_ID, + USB_CANNECTIVITY_PRODUCT_ID, 0) }, {} /* Terminating entry */ }; diff --git a/drivers/net/can/vxcan.c b/drivers/net/can/vxcan.c index ca8811941085..99a78a757167 100644 --- a/drivers/net/can/vxcan.c +++ b/drivers/net/can/vxcan.c @@ -172,10 +172,13 @@ static void vxcan_setup(struct net_device *dev) /* forward declaration for rtnl_create_link() */ static struct rtnl_link_ops vxcan_link_ops; -static int vxcan_newlink(struct net *peer_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +static int vxcan_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { + struct net *peer_net = rtnl_newlink_peer_net(params); + struct nlattr **data = params->data; + struct nlattr **tb = params->tb; struct vxcan_priv *priv; struct net_device *peer; diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index 79dc77835681..61d164ffb3ae 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -2410,6 +2410,19 @@ static const struct b53_chip_data b53_switch_chips[] = { .jumbo_size_reg = B53_JUMBO_MAX_SIZE, }, { + .chip_id = BCM53101_DEVICE_ID, + .dev_name = "BCM53101", + .vlans = 4096, + .enabled_ports = 0x11f, + .arl_bins = 4, + .arl_buckets = 512, + .vta_regs = B53_VTA_REGS, + .imp_port = 8, + .duplex_reg = B53_DUPLEX_STAT_GE, + .jumbo_pm_reg = B53_JUMBO_PORT_MASK, + .jumbo_size_reg = B53_JUMBO_MAX_SIZE, + }, + { .chip_id = BCM53115_DEVICE_ID, .dev_name = "BCM53115", .vlans = 4096, @@ -2789,6 +2802,7 @@ int b53_switch_detect(struct b53_device *dev) return ret; switch (id32) { + case BCM53101_DEVICE_ID: case BCM53115_DEVICE_ID: case BCM53125_DEVICE_ID: case BCM53128_DEVICE_ID: diff --git a/drivers/net/dsa/b53/b53_mdio.c b/drivers/net/dsa/b53/b53_mdio.c index 31d070bf161a..43a3b37b731b 100644 --- a/drivers/net/dsa/b53/b53_mdio.c +++ b/drivers/net/dsa/b53/b53_mdio.c @@ -374,6 +374,7 @@ static void b53_mdio_shutdown(struct mdio_device *mdiodev) static const struct of_device_id b53_of_match[] = { { .compatible = "brcm,bcm5325" }, + { .compatible = "brcm,bcm53101" }, { .compatible = "brcm,bcm53115" }, { .compatible = "brcm,bcm53125" }, { .compatible = "brcm,bcm53128" }, diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h index 9e9b5bc0c5d6..0166c37a13a7 100644 --- a/drivers/net/dsa/b53/b53_priv.h +++ b/drivers/net/dsa/b53/b53_priv.h @@ -66,6 +66,7 @@ enum { BCM5395_DEVICE_ID = 0x95, BCM5397_DEVICE_ID = 0x97, BCM5398_DEVICE_ID = 0x98, + BCM53101_DEVICE_ID = 0x53101, BCM53115_DEVICE_ID = 0x53115, BCM53125_DEVICE_ID = 0x53125, BCM53128_DEVICE_ID = 0x53128, @@ -188,6 +189,7 @@ static inline int is531x5(struct b53_device *dev) { return dev->chip_id == BCM53115_DEVICE_ID || dev->chip_id == BCM53125_DEVICE_ID || + dev->chip_id == BCM53101_DEVICE_ID || dev->chip_id == BCM53128_DEVICE_ID || dev->chip_id == BCM53134_DEVICE_ID; } diff --git a/drivers/net/dsa/b53/b53_serdes.c b/drivers/net/dsa/b53/b53_serdes.c index 4730982b6840..7460122f6abc 100644 --- a/drivers/net/dsa/b53/b53_serdes.c +++ b/drivers/net/dsa/b53/b53_serdes.c @@ -239,7 +239,6 @@ int b53_serdes_init(struct b53_device *dev, int port) pcs->dev = dev; pcs->lane = lane; pcs->pcs.ops = &b53_pcs_ops; - pcs->pcs.neg_mode = true; return 0; } diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 9fd44e55d519..8422262febaf 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -3104,7 +3104,6 @@ mt753x_setup(struct dsa_switch *ds) /* Initialise the PCS devices */ for (i = 0; i < priv->ds->num_ports; i++) { priv->pcs[i].pcs.ops = priv->info->pcs_ops; - priv->pcs[i].pcs.neg_mode = true; priv->pcs[i].priv = priv; priv->pcs[i].port = i; } diff --git a/drivers/net/dsa/mv88e6xxx/pcs-6185.c b/drivers/net/dsa/mv88e6xxx/pcs-6185.c index 75ed1fa500a5..af7e06d265f7 100644 --- a/drivers/net/dsa/mv88e6xxx/pcs-6185.c +++ b/drivers/net/dsa/mv88e6xxx/pcs-6185.c @@ -138,7 +138,6 @@ static int mv88e6185_pcs_init(struct mv88e6xxx_chip *chip, int port) mpcs->chip = chip; mpcs->port = port; mpcs->phylink_pcs.ops = &mv88e6185_phylink_pcs_ops; - mpcs->phylink_pcs.neg_mode = true; irq = mv88e6xxx_serdes_irq_mapping(chip, port); if (irq) { diff --git a/drivers/net/dsa/mv88e6xxx/pcs-6352.c b/drivers/net/dsa/mv88e6xxx/pcs-6352.c index 143fe21d1834..36993400837e 100644 --- a/drivers/net/dsa/mv88e6xxx/pcs-6352.c +++ b/drivers/net/dsa/mv88e6xxx/pcs-6352.c @@ -275,7 +275,6 @@ static struct marvell_c22_pcs *marvell_c22_pcs_alloc(struct device *dev, mpcs->mdio.bus = bus; mpcs->mdio.addr = addr; mpcs->phylink_pcs.ops = &marvell_c22_pcs_ops; - mpcs->phylink_pcs.neg_mode = true; return mpcs; } diff --git a/drivers/net/dsa/mv88e6xxx/pcs-639x.c b/drivers/net/dsa/mv88e6xxx/pcs-639x.c index 59f63d6beec8..5db17c0b77f5 100644 --- a/drivers/net/dsa/mv88e6xxx/pcs-639x.c +++ b/drivers/net/dsa/mv88e6xxx/pcs-639x.c @@ -565,9 +565,7 @@ static int mv88e6390_pcs_init(struct mv88e6xxx_chip *chip, int port) return -ENOMEM; mpcs->sgmii_pcs.ops = &mv88e639x_sgmii_pcs_ops; - mpcs->sgmii_pcs.neg_mode = true; mpcs->xg_pcs.ops = &mv88e6390_xg_pcs_ops; - mpcs->xg_pcs.neg_mode = true; if (chip->info->prod_num == MV88E6XXX_PORT_SWITCH_ID_PROD_6190X || chip->info->prod_num == MV88E6XXX_PORT_SWITCH_ID_PROD_6390X) @@ -945,9 +943,7 @@ static int mv88e6393x_pcs_init(struct mv88e6xxx_chip *chip, int port) return -ENOMEM; mpcs->sgmii_pcs.ops = &mv88e6393x_sgmii_pcs_ops; - mpcs->sgmii_pcs.neg_mode = true; mpcs->xg_pcs.ops = &mv88e6393x_xg_pcs_ops; - mpcs->xg_pcs.neg_mode = true; mpcs->supports_5g = true; err = mv88e6393x_erratum_4_6(mpcs); diff --git a/drivers/net/dsa/qca/qca8k-8xxx.c b/drivers/net/dsa/qca/qca8k-8xxx.c index e8cb4da15dbe..a36b8b07030e 100644 --- a/drivers/net/dsa/qca/qca8k-8xxx.c +++ b/drivers/net/dsa/qca/qca8k-8xxx.c @@ -1634,7 +1634,6 @@ static void qca8k_setup_pcs(struct qca8k_priv *priv, struct qca8k_pcs *qpcs, int port) { qpcs->pcs.ops = &qca8k_pcs_ops; - qpcs->pcs.neg_mode = true; /* We don't have interrupts for link changes, so we need to poll */ qpcs->pcs.poll = true; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 7b8b5b39c7bb..15c57a06ecaf 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -55,6 +55,8 @@ #include <net/page_pool/helpers.h> #include <linux/align.h> #include <net/netdev_queues.h> +#include <net/netdev_rx_queue.h> +#include <linux/pci-tph.h> #include "bnxt_hsi.h" #include "bnxt.h" @@ -76,6 +78,7 @@ #define BNXT_DEF_MSG_ENABLE (NETIF_MSG_DRV | NETIF_MSG_HW | \ NETIF_MSG_TX_ERR) +MODULE_IMPORT_NS("NETDEV_INTERNAL"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Broadcom NetXtreme network driver"); @@ -3314,74 +3317,81 @@ poll_done: return work_done; } -static void bnxt_free_tx_skbs(struct bnxt *bp) +static void bnxt_free_one_tx_ring_skbs(struct bnxt *bp, + struct bnxt_tx_ring_info *txr, int idx) { int i, max_idx; struct pci_dev *pdev = bp->pdev; - if (!bp->tx_ring) - return; - max_idx = bp->tx_nr_pages * TX_DESC_CNT; - for (i = 0; i < bp->tx_nr_rings; i++) { - struct bnxt_tx_ring_info *txr = &bp->tx_ring[i]; - int j; - if (!txr->tx_buf_ring) + for (i = 0; i < max_idx;) { + struct bnxt_sw_tx_bd *tx_buf = &txr->tx_buf_ring[i]; + struct sk_buff *skb; + int j, last; + + if (idx < bp->tx_nr_rings_xdp && + tx_buf->action == XDP_REDIRECT) { + dma_unmap_single(&pdev->dev, + dma_unmap_addr(tx_buf, mapping), + dma_unmap_len(tx_buf, len), + DMA_TO_DEVICE); + xdp_return_frame(tx_buf->xdpf); + tx_buf->action = 0; + tx_buf->xdpf = NULL; + i++; continue; + } - for (j = 0; j < max_idx;) { - struct bnxt_sw_tx_bd *tx_buf = &txr->tx_buf_ring[j]; - struct sk_buff *skb; - int k, last; - - if (i < bp->tx_nr_rings_xdp && - tx_buf->action == XDP_REDIRECT) { - dma_unmap_single(&pdev->dev, - dma_unmap_addr(tx_buf, mapping), - dma_unmap_len(tx_buf, len), - DMA_TO_DEVICE); - xdp_return_frame(tx_buf->xdpf); - tx_buf->action = 0; - tx_buf->xdpf = NULL; - j++; - continue; - } + skb = tx_buf->skb; + if (!skb) { + i++; + continue; + } - skb = tx_buf->skb; - if (!skb) { - j++; - continue; - } + tx_buf->skb = NULL; - tx_buf->skb = NULL; + if (tx_buf->is_push) { + dev_kfree_skb(skb); + i += 2; + continue; + } - if (tx_buf->is_push) { - dev_kfree_skb(skb); - j += 2; - continue; - } + dma_unmap_single(&pdev->dev, + dma_unmap_addr(tx_buf, mapping), + skb_headlen(skb), + DMA_TO_DEVICE); - dma_unmap_single(&pdev->dev, - dma_unmap_addr(tx_buf, mapping), - skb_headlen(skb), - DMA_TO_DEVICE); + last = tx_buf->nr_frags; + i += 2; + for (j = 0; j < last; j++, i++) { + int ring_idx = i & bp->tx_ring_mask; + skb_frag_t *frag = &skb_shinfo(skb)->frags[j]; - last = tx_buf->nr_frags; - j += 2; - for (k = 0; k < last; k++, j++) { - int ring_idx = j & bp->tx_ring_mask; - skb_frag_t *frag = &skb_shinfo(skb)->frags[k]; - - tx_buf = &txr->tx_buf_ring[ring_idx]; - dma_unmap_page( - &pdev->dev, - dma_unmap_addr(tx_buf, mapping), - skb_frag_size(frag), DMA_TO_DEVICE); - } - dev_kfree_skb(skb); + tx_buf = &txr->tx_buf_ring[ring_idx]; + dma_unmap_page(&pdev->dev, + dma_unmap_addr(tx_buf, mapping), + skb_frag_size(frag), DMA_TO_DEVICE); } - netdev_tx_reset_queue(netdev_get_tx_queue(bp->dev, i)); + dev_kfree_skb(skb); + } + netdev_tx_reset_queue(netdev_get_tx_queue(bp->dev, idx)); +} + +static void bnxt_free_tx_skbs(struct bnxt *bp) +{ + int i; + + if (!bp->tx_ring) + return; + + for (i = 0; i < bp->tx_nr_rings; i++) { + struct bnxt_tx_ring_info *txr = &bp->tx_ring[i]; + + if (!txr->tx_buf_ring) + continue; + + bnxt_free_one_tx_ring_skbs(bp, txr, i); } } @@ -5565,6 +5575,8 @@ int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp, unsigned long *bmap, int bmap_size, if (bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY) flags |= FUNC_DRV_RGTR_REQ_FLAGS_ERROR_RECOVERY_SUPPORT | FUNC_DRV_RGTR_REQ_FLAGS_MASTER_SUPPORT; + if (bp->fw_cap & BNXT_FW_CAP_NPAR_1_2) + flags |= FUNC_DRV_RGTR_REQ_FLAGS_NPAR_1_2_SUPPORT; req->flags = cpu_to_le32(flags); req->ver_maj_8b = DRV_VER_MAJ; req->ver_min_8b = DRV_VER_MIN; @@ -6935,6 +6947,30 @@ static void bnxt_hwrm_ring_grp_free(struct bnxt *bp) hwrm_req_drop(bp, req); } +static void bnxt_set_rx_ring_params_p5(struct bnxt *bp, u32 ring_type, + struct hwrm_ring_alloc_input *req, + struct bnxt_ring_struct *ring) +{ + struct bnxt_ring_grp_info *grp_info = &bp->grp_info[ring->grp_idx]; + u32 enables = RING_ALLOC_REQ_ENABLES_RX_BUF_SIZE_VALID | + RING_ALLOC_REQ_ENABLES_NQ_RING_ID_VALID; + + if (ring_type == HWRM_RING_ALLOC_AGG) { + req->ring_type = RING_ALLOC_REQ_RING_TYPE_RX_AGG; + req->rx_ring_id = cpu_to_le16(grp_info->rx_fw_ring_id); + req->rx_buf_size = cpu_to_le16(BNXT_RX_PAGE_SIZE); + enables |= RING_ALLOC_REQ_ENABLES_RX_RING_ID_VALID; + } else { + req->rx_buf_size = cpu_to_le16(bp->rx_buf_use_size); + if (NET_IP_ALIGN == 2) + req->flags = + cpu_to_le16(RING_ALLOC_REQ_FLAGS_RX_SOP_PAD); + } + req->stat_ctx_id = cpu_to_le32(grp_info->fw_stats_ctx); + req->nq_ring_id = cpu_to_le16(grp_info->cp_fw_ring_id); + req->enables |= cpu_to_le32(enables); +} + static int hwrm_ring_alloc_send_msg(struct bnxt *bp, struct bnxt_ring_struct *ring, u32 ring_type, u32 map_index) @@ -6986,37 +7022,13 @@ static int hwrm_ring_alloc_send_msg(struct bnxt *bp, break; } case HWRM_RING_ALLOC_RX: - req->ring_type = RING_ALLOC_REQ_RING_TYPE_RX; - req->length = cpu_to_le32(bp->rx_ring_mask + 1); - if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) { - u16 flags = 0; - - /* Association of rx ring with stats context */ - grp_info = &bp->grp_info[ring->grp_idx]; - req->rx_buf_size = cpu_to_le16(bp->rx_buf_use_size); - req->stat_ctx_id = cpu_to_le32(grp_info->fw_stats_ctx); - req->enables |= cpu_to_le32( - RING_ALLOC_REQ_ENABLES_RX_BUF_SIZE_VALID); - if (NET_IP_ALIGN == 2) - flags = RING_ALLOC_REQ_FLAGS_RX_SOP_PAD; - req->flags = cpu_to_le16(flags); - } - break; case HWRM_RING_ALLOC_AGG: - if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) { - req->ring_type = RING_ALLOC_REQ_RING_TYPE_RX_AGG; - /* Association of agg ring with rx ring */ - grp_info = &bp->grp_info[ring->grp_idx]; - req->rx_ring_id = cpu_to_le16(grp_info->rx_fw_ring_id); - req->rx_buf_size = cpu_to_le16(BNXT_RX_PAGE_SIZE); - req->stat_ctx_id = cpu_to_le32(grp_info->fw_stats_ctx); - req->enables |= cpu_to_le32( - RING_ALLOC_REQ_ENABLES_RX_RING_ID_VALID | - RING_ALLOC_REQ_ENABLES_RX_BUF_SIZE_VALID); - } else { - req->ring_type = RING_ALLOC_REQ_RING_TYPE_RX; - } - req->length = cpu_to_le32(bp->rx_agg_ring_mask + 1); + req->ring_type = RING_ALLOC_REQ_RING_TYPE_RX; + req->length = (ring_type == HWRM_RING_ALLOC_RX) ? + cpu_to_le32(bp->rx_ring_mask + 1) : + cpu_to_le32(bp->rx_agg_ring_mask + 1); + if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) + bnxt_set_rx_ring_params_p5(bp, ring_type, req, ring); break; case HWRM_RING_ALLOC_CMPL: req->ring_type = RING_ALLOC_REQ_RING_TYPE_L2_CMPL; @@ -7197,6 +7209,39 @@ static int bnxt_hwrm_rx_agg_ring_alloc(struct bnxt *bp, return 0; } +static int bnxt_hwrm_cp_ring_alloc_p5(struct bnxt *bp, + struct bnxt_cp_ring_info *cpr) +{ + const u32 type = HWRM_RING_ALLOC_CMPL; + struct bnxt_napi *bnapi = cpr->bnapi; + struct bnxt_ring_struct *ring; + u32 map_idx = bnapi->index; + int rc; + + ring = &cpr->cp_ring_struct; + ring->handle = BNXT_SET_NQ_HDL(cpr); + rc = hwrm_ring_alloc_send_msg(bp, ring, type, map_idx); + if (rc) + return rc; + bnxt_set_db(bp, &cpr->cp_db, type, map_idx, ring->fw_ring_id); + bnxt_db_cq(bp, &cpr->cp_db, cpr->cp_raw_cons); + return 0; +} + +static int bnxt_hwrm_tx_ring_alloc(struct bnxt *bp, + struct bnxt_tx_ring_info *txr, u32 tx_idx) +{ + struct bnxt_ring_struct *ring = &txr->tx_ring_struct; + const u32 type = HWRM_RING_ALLOC_TX; + int rc; + + rc = hwrm_ring_alloc_send_msg(bp, ring, type, tx_idx); + if (rc) + return rc; + bnxt_set_db(bp, &txr->tx_db, type, tx_idx, ring->fw_ring_id); + return 0; +} + static int bnxt_hwrm_ring_alloc(struct bnxt *bp) { bool agg_rings = !!(bp->flags & BNXT_FLAG_AGG_RINGS); @@ -7233,33 +7278,17 @@ static int bnxt_hwrm_ring_alloc(struct bnxt *bp) } } - type = HWRM_RING_ALLOC_TX; for (i = 0; i < bp->tx_nr_rings; i++) { struct bnxt_tx_ring_info *txr = &bp->tx_ring[i]; - struct bnxt_ring_struct *ring; - u32 map_idx; if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) { - struct bnxt_cp_ring_info *cpr2 = txr->tx_cpr; - struct bnxt_napi *bnapi = txr->bnapi; - u32 type2 = HWRM_RING_ALLOC_CMPL; - - ring = &cpr2->cp_ring_struct; - ring->handle = BNXT_SET_NQ_HDL(cpr2); - map_idx = bnapi->index; - rc = hwrm_ring_alloc_send_msg(bp, ring, type2, map_idx); + rc = bnxt_hwrm_cp_ring_alloc_p5(bp, txr->tx_cpr); if (rc) goto err_out; - bnxt_set_db(bp, &cpr2->cp_db, type2, map_idx, - ring->fw_ring_id); - bnxt_db_cq(bp, &cpr2->cp_db, cpr2->cp_raw_cons); } - ring = &txr->tx_ring_struct; - map_idx = i; - rc = hwrm_ring_alloc_send_msg(bp, ring, type, map_idx); + rc = bnxt_hwrm_tx_ring_alloc(bp, txr, i); if (rc) goto err_out; - bnxt_set_db(bp, &txr->tx_db, type, map_idx, ring->fw_ring_id); } for (i = 0; i < bp->rx_nr_rings; i++) { @@ -7272,20 +7301,9 @@ static int bnxt_hwrm_ring_alloc(struct bnxt *bp) if (!agg_rings) bnxt_db_write(bp, &rxr->rx_db, rxr->rx_prod); if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) { - struct bnxt_cp_ring_info *cpr2 = rxr->rx_cpr; - struct bnxt_napi *bnapi = rxr->bnapi; - u32 type2 = HWRM_RING_ALLOC_CMPL; - struct bnxt_ring_struct *ring; - u32 map_idx = bnapi->index; - - ring = &cpr2->cp_ring_struct; - ring->handle = BNXT_SET_NQ_HDL(cpr2); - rc = hwrm_ring_alloc_send_msg(bp, ring, type2, map_idx); + rc = bnxt_hwrm_cp_ring_alloc_p5(bp, rxr->rx_cpr); if (rc) goto err_out; - bnxt_set_db(bp, &cpr2->cp_db, type2, map_idx, - ring->fw_ring_id); - bnxt_db_cq(bp, &cpr2->cp_db, cpr2->cp_raw_cons); } } @@ -7353,6 +7371,23 @@ exit: return 0; } +static void bnxt_hwrm_tx_ring_free(struct bnxt *bp, + struct bnxt_tx_ring_info *txr, + bool close_path) +{ + struct bnxt_ring_struct *ring = &txr->tx_ring_struct; + u32 cmpl_ring_id; + + if (ring->fw_ring_id == INVALID_HW_RING_ID) + return; + + cmpl_ring_id = close_path ? bnxt_cp_ring_for_tx(bp, txr) : + INVALID_HW_RING_ID; + hwrm_ring_free_send_msg(bp, ring, RING_FREE_REQ_RING_TYPE_TX, + cmpl_ring_id); + ring->fw_ring_id = INVALID_HW_RING_ID; +} + static void bnxt_hwrm_rx_ring_free(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, bool close_path) @@ -7397,6 +7432,33 @@ static void bnxt_hwrm_rx_agg_ring_free(struct bnxt *bp, bp->grp_info[grp_idx].agg_fw_ring_id = INVALID_HW_RING_ID; } +static void bnxt_hwrm_cp_ring_free(struct bnxt *bp, + struct bnxt_cp_ring_info *cpr) +{ + struct bnxt_ring_struct *ring; + + ring = &cpr->cp_ring_struct; + if (ring->fw_ring_id == INVALID_HW_RING_ID) + return; + + hwrm_ring_free_send_msg(bp, ring, RING_FREE_REQ_RING_TYPE_L2_CMPL, + INVALID_HW_RING_ID); + ring->fw_ring_id = INVALID_HW_RING_ID; +} + +static void bnxt_clear_one_cp_ring(struct bnxt *bp, struct bnxt_cp_ring_info *cpr) +{ + struct bnxt_ring_struct *ring = &cpr->cp_ring_struct; + int i, size = ring->ring_mem.page_size; + + cpr->cp_raw_cons = 0; + cpr->toggle = 0; + + for (i = 0; i < bp->cp_nr_pages; i++) + if (cpr->cp_desc_ring[i]) + memset(cpr->cp_desc_ring[i], 0, size); +} + static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path) { u32 type; @@ -7405,20 +7467,8 @@ static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path) if (!bp->bnapi) return; - for (i = 0; i < bp->tx_nr_rings; i++) { - struct bnxt_tx_ring_info *txr = &bp->tx_ring[i]; - struct bnxt_ring_struct *ring = &txr->tx_ring_struct; - - if (ring->fw_ring_id != INVALID_HW_RING_ID) { - u32 cmpl_ring_id = bnxt_cp_ring_for_tx(bp, txr); - - hwrm_ring_free_send_msg(bp, ring, - RING_FREE_REQ_RING_TYPE_TX, - close_path ? cmpl_ring_id : - INVALID_HW_RING_ID); - ring->fw_ring_id = INVALID_HW_RING_ID; - } - } + for (i = 0; i < bp->tx_nr_rings; i++) + bnxt_hwrm_tx_ring_free(bp, &bp->tx_ring[i], close_path); bnxt_cancel_dim(bp); for (i = 0; i < bp->rx_nr_rings; i++) { @@ -7442,17 +7492,9 @@ static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path) struct bnxt_ring_struct *ring; int j; - for (j = 0; j < cpr->cp_ring_count && cpr->cp_ring_arr; j++) { - struct bnxt_cp_ring_info *cpr2 = &cpr->cp_ring_arr[j]; + for (j = 0; j < cpr->cp_ring_count && cpr->cp_ring_arr; j++) + bnxt_hwrm_cp_ring_free(bp, &cpr->cp_ring_arr[j]); - ring = &cpr2->cp_ring_struct; - if (ring->fw_ring_id == INVALID_HW_RING_ID) - continue; - hwrm_ring_free_send_msg(bp, ring, - RING_FREE_REQ_RING_TYPE_L2_CMPL, - INVALID_HW_RING_ID); - ring->fw_ring_id = INVALID_HW_RING_ID; - } ring = &cpr->cp_ring_struct; if (ring->fw_ring_id != INVALID_HW_RING_ID) { hwrm_ring_free_send_msg(bp, ring, type, @@ -8365,6 +8407,7 @@ static int bnxt_hwrm_func_qcfg(struct bnxt *bp) switch (resp->port_partition_type) { case FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_0: + case FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_2: case FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_5: case FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR2_0: bp->port_partition_type = resp->port_partition_type; @@ -9529,6 +9572,8 @@ static int __bnxt_hwrm_func_qcaps(struct bnxt *bp) bp->fw_cap |= BNXT_FW_CAP_HOT_RESET_IF; if (BNXT_PF(bp) && (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_FW_LIVEPATCH_SUPPORTED)) bp->fw_cap |= BNXT_FW_CAP_LIVEPATCH; + if (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_NPAR_1_2_SUPPORTED) + bp->fw_cap |= BNXT_FW_CAP_NPAR_1_2; if (BNXT_PF(bp) && (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_DFLT_VLAN_TPID_PCP_SUPPORTED)) bp->fw_cap |= BNXT_FW_CAP_DFLT_VLAN_TPID_PCP; if (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_BS_V2_SUPPORTED) @@ -11237,6 +11282,155 @@ int bnxt_reserve_rings(struct bnxt *bp, bool irq_re_init) return 0; } +static void bnxt_tx_queue_stop(struct bnxt *bp, int idx) +{ + struct bnxt_tx_ring_info *txr; + struct netdev_queue *txq; + struct bnxt_napi *bnapi; + int i; + + bnapi = bp->bnapi[idx]; + bnxt_for_each_napi_tx(i, bnapi, txr) { + WRITE_ONCE(txr->dev_state, BNXT_DEV_STATE_CLOSING); + synchronize_net(); + + if (!(bnapi->flags & BNXT_NAPI_FLAG_XDP)) { + txq = netdev_get_tx_queue(bp->dev, txr->txq_index); + if (txq) { + __netif_tx_lock_bh(txq); + netif_tx_stop_queue(txq); + __netif_tx_unlock_bh(txq); + } + } + + if (!bp->tph_mode) + continue; + + bnxt_hwrm_tx_ring_free(bp, txr, true); + bnxt_hwrm_cp_ring_free(bp, txr->tx_cpr); + bnxt_free_one_tx_ring_skbs(bp, txr, txr->txq_index); + bnxt_clear_one_cp_ring(bp, txr->tx_cpr); + } +} + +static int bnxt_tx_queue_start(struct bnxt *bp, int idx) +{ + struct bnxt_tx_ring_info *txr; + struct netdev_queue *txq; + struct bnxt_napi *bnapi; + int rc, i; + + bnapi = bp->bnapi[idx]; + /* All rings have been reserved and previously allocated. + * Reallocating with the same parameters should never fail. + */ + bnxt_for_each_napi_tx(i, bnapi, txr) { + if (!bp->tph_mode) + goto start_tx; + + rc = bnxt_hwrm_cp_ring_alloc_p5(bp, txr->tx_cpr); + if (rc) + return rc; + + rc = bnxt_hwrm_tx_ring_alloc(bp, txr, false); + if (rc) + return rc; + + txr->tx_prod = 0; + txr->tx_cons = 0; + txr->tx_hw_cons = 0; +start_tx: + WRITE_ONCE(txr->dev_state, 0); + synchronize_net(); + + if (bnapi->flags & BNXT_NAPI_FLAG_XDP) + continue; + + txq = netdev_get_tx_queue(bp->dev, txr->txq_index); + if (txq) + netif_tx_start_queue(txq); + } + + return 0; +} + +static void bnxt_irq_affinity_notify(struct irq_affinity_notify *notify, + const cpumask_t *mask) +{ + struct bnxt_irq *irq; + u16 tag; + int err; + + irq = container_of(notify, struct bnxt_irq, affinity_notify); + + if (!irq->bp->tph_mode) + return; + + cpumask_copy(irq->cpu_mask, mask); + + if (irq->ring_nr >= irq->bp->rx_nr_rings) + return; + + if (pcie_tph_get_cpu_st(irq->bp->pdev, TPH_MEM_TYPE_VM, + cpumask_first(irq->cpu_mask), &tag)) + return; + + if (pcie_tph_set_st_entry(irq->bp->pdev, irq->msix_nr, tag)) + return; + + rtnl_lock(); + if (netif_running(irq->bp->dev)) { + err = netdev_rx_queue_restart(irq->bp->dev, irq->ring_nr); + if (err) + netdev_err(irq->bp->dev, + "RX queue restart failed: err=%d\n", err); + } + rtnl_unlock(); +} + +static void bnxt_irq_affinity_release(struct kref *ref) +{ + struct irq_affinity_notify *notify = + container_of(ref, struct irq_affinity_notify, kref); + struct bnxt_irq *irq; + + irq = container_of(notify, struct bnxt_irq, affinity_notify); + + if (!irq->bp->tph_mode) + return; + + if (pcie_tph_set_st_entry(irq->bp->pdev, irq->msix_nr, 0)) { + netdev_err(irq->bp->dev, + "Setting ST=0 for MSIX entry %d failed\n", + irq->msix_nr); + return; + } +} + +static void bnxt_release_irq_notifier(struct bnxt_irq *irq) +{ + irq_set_affinity_notifier(irq->vector, NULL); +} + +static void bnxt_register_irq_notifier(struct bnxt *bp, struct bnxt_irq *irq) +{ + struct irq_affinity_notify *notify; + + irq->bp = bp; + + /* Nothing to do if TPH is not enabled */ + if (!bp->tph_mode) + return; + + /* Register IRQ affinity notifier */ + notify = &irq->affinity_notify; + notify->irq = irq->vector; + notify->notify = bnxt_irq_affinity_notify; + notify->release = bnxt_irq_affinity_release; + + irq_set_affinity_notifier(irq->vector, notify); +} + static void bnxt_free_irq(struct bnxt *bp) { struct bnxt_irq *irq; @@ -11259,11 +11453,18 @@ static void bnxt_free_irq(struct bnxt *bp) free_cpumask_var(irq->cpu_mask); irq->have_cpumask = 0; } + + bnxt_release_irq_notifier(irq); + free_irq(irq->vector, bp->bnapi[i]); } irq->requested = 0; } + + /* Disable TPH support */ + pcie_disable_tph(bp->pdev); + bp->tph_mode = 0; } static int bnxt_request_irq(struct bnxt *bp) @@ -11283,6 +11484,12 @@ static int bnxt_request_irq(struct bnxt *bp) #ifdef CONFIG_RFS_ACCEL rmap = bp->dev->rx_cpu_rmap; #endif + + /* Enable TPH support as part of IRQ request */ + rc = pcie_enable_tph(bp->pdev, PCI_TPH_ST_IV_MODE); + if (!rc) + bp->tph_mode = PCI_TPH_ST_IV_MODE; + for (i = 0, j = 0; i < bp->cp_nr_rings; i++) { int map_idx = bnxt_cp_num_to_irq_num(bp, i); struct bnxt_irq *irq = &bp->irq_tbl[map_idx]; @@ -11306,8 +11513,11 @@ static int bnxt_request_irq(struct bnxt *bp) if (zalloc_cpumask_var(&irq->cpu_mask, GFP_KERNEL)) { int numa_node = dev_to_node(&bp->pdev->dev); + u16 tag; irq->have_cpumask = 1; + irq->msix_nr = map_idx; + irq->ring_nr = i; cpumask_set_cpu(cpumask_local_spread(i, numa_node), irq->cpu_mask); rc = irq_update_affinity_hint(irq->vector, irq->cpu_mask); @@ -11317,6 +11527,16 @@ static int bnxt_request_irq(struct bnxt *bp) irq->vector); break; } + + bnxt_register_irq_notifier(bp, irq); + + /* Init ST table entry */ + if (pcie_tph_get_cpu_st(irq->bp->pdev, TPH_MEM_TYPE_VM, + cpumask_first(irq->cpu_mask), + &tag)) + continue; + + pcie_tph_set_st_entry(irq->bp->pdev, irq->msix_nr, tag); } } return rc; @@ -15601,6 +15821,7 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx) struct bnxt_rx_ring_info *rxr, *clone; struct bnxt_cp_ring_info *cpr; struct bnxt_vnic_info *vnic; + struct bnxt_napi *bnapi; int i, rc; rxr = &bp->rx_ring[idx]; @@ -15618,19 +15839,38 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx) bnxt_copy_rx_ring(bp, rxr, clone); + bnapi = rxr->bnapi; + cpr = &bnapi->cp_ring; + + /* All rings have been reserved and previously allocated. + * Reallocating with the same parameters should never fail. + */ rc = bnxt_hwrm_rx_ring_alloc(bp, rxr); if (rc) - return rc; + goto err_reset; + + if (bp->tph_mode) { + rc = bnxt_hwrm_cp_ring_alloc_p5(bp, rxr->rx_cpr); + if (rc) + goto err_reset; + } + rc = bnxt_hwrm_rx_agg_ring_alloc(bp, rxr); if (rc) - goto err_free_hwrm_rx_ring; + goto err_reset; bnxt_db_write(bp, &rxr->rx_db, rxr->rx_prod); if (bp->flags & BNXT_FLAG_AGG_RINGS) bnxt_db_write(bp, &rxr->rx_agg_db, rxr->rx_agg_prod); - cpr = &rxr->bnapi->cp_ring; - cpr->sw_stats->rx.rx_resets++; + if (bp->flags & BNXT_FLAG_SHARED_RINGS) { + rc = bnxt_tx_queue_start(bp, idx); + if (rc) + goto err_reset; + } + + napi_enable(&bnapi->napi); + bnxt_db_nq_arm(bp, &cpr->cp_db, cpr->cp_raw_cons); for (i = 0; i <= BNXT_VNIC_NTUPLE; i++) { vnic = &bp->vnic_info[i]; @@ -15648,8 +15888,12 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx) return 0; -err_free_hwrm_rx_ring: - bnxt_hwrm_rx_ring_free(bp, rxr, false); +err_reset: + netdev_err(bp->dev, "Unexpected HWRM error during queue start rc: %d\n", + rc); + napi_enable(&bnapi->napi); + bnxt_db_nq_arm(bp, &cpr->cp_db, cpr->cp_raw_cons); + bnxt_reset_task(bp, true); return rc; } @@ -15657,7 +15901,9 @@ static int bnxt_queue_stop(struct net_device *dev, void *qmem, int idx) { struct bnxt *bp = netdev_priv(dev); struct bnxt_rx_ring_info *rxr; + struct bnxt_cp_ring_info *cpr; struct bnxt_vnic_info *vnic; + struct bnxt_napi *bnapi; int i; for (i = 0; i <= BNXT_VNIC_NTUPLE; i++) { @@ -15669,14 +15915,30 @@ static int bnxt_queue_stop(struct net_device *dev, void *qmem, int idx) /* Make sure NAPI sees that the VNIC is disabled */ synchronize_net(); rxr = &bp->rx_ring[idx]; - cancel_work_sync(&rxr->bnapi->cp_ring.dim.work); + bnapi = rxr->bnapi; + cpr = &bnapi->cp_ring; + cancel_work_sync(&cpr->dim.work); bnxt_hwrm_rx_ring_free(bp, rxr, false); bnxt_hwrm_rx_agg_ring_free(bp, rxr, false); - rxr->rx_next_cons = 0; page_pool_disable_direct_recycling(rxr->page_pool); if (bnxt_separate_head_pool()) page_pool_disable_direct_recycling(rxr->head_pool); + if (bp->flags & BNXT_FLAG_SHARED_RINGS) + bnxt_tx_queue_stop(bp, idx); + + /* Disable NAPI now after freeing the rings because HWRM_RING_FREE + * completion is handled in NAPI to guarantee no more DMA on that ring + * after seeing the completion. + */ + napi_disable(&bnapi->napi); + + if (bp->tph_mode) { + bnxt_hwrm_cp_ring_free(bp, rxr->rx_cpr); + bnxt_clear_one_cp_ring(bp, rxr->rx_cpr); + } + bnxt_db_nq(bp, &cpr->cp_db, cpr->cp_raw_cons); + memcpy(qmem, rxr, sizeof(*rxr)); bnxt_init_rx_ring_struct(bp, qmem); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 2373f423a523..e85b5ce94f58 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -1234,6 +1234,11 @@ struct bnxt_irq { u8 have_cpumask:1; char name[IFNAMSIZ + BNXT_IRQ_NAME_EXTRA]; cpumask_var_t cpu_mask; + + struct bnxt *bp; + int msix_nr; + int ring_nr; + struct irq_affinity_notify affinity_notify; }; #define HWRM_RING_ALLOC_TX 0x1 @@ -2410,6 +2415,8 @@ struct bnxt { u8 max_q; u8 num_tc; + u8 tph_mode; + unsigned int current_interval; #define BNXT_TIMER_INTERVAL HZ @@ -2492,6 +2499,7 @@ struct bnxt { #define BNXT_FW_CAP_CFA_RFS_RING_TBL_IDX_V3 BIT_ULL(39) #define BNXT_FW_CAP_VNIC_RE_FLUSH BIT_ULL(40) #define BNXT_FW_CAP_SW_MAX_RESOURCE_LIMITS BIT_ULL(41) + #define BNXT_FW_CAP_NPAR_1_2 BIT_ULL(42) u32 fw_dbg_cap; diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h index 5740c98d8c9f..f69b2b7c8802 100644 --- a/drivers/net/ethernet/cadence/macb.h +++ b/drivers/net/ethernet/cadence/macb.h @@ -951,75 +951,73 @@ struct macb_tx_skb { * device stats by a periodic timer. */ struct macb_stats { - u32 rx_pause_frames; - u32 tx_ok; - u32 tx_single_cols; - u32 tx_multiple_cols; - u32 rx_ok; - u32 rx_fcs_errors; - u32 rx_align_errors; - u32 tx_deferred; - u32 tx_late_cols; - u32 tx_excessive_cols; - u32 tx_underruns; - u32 tx_carrier_errors; - u32 rx_resource_errors; - u32 rx_overruns; - u32 rx_symbol_errors; - u32 rx_oversize_pkts; - u32 rx_jabbers; - u32 rx_undersize_pkts; - u32 sqe_test_errors; - u32 rx_length_mismatch; - u32 tx_pause_frames; + u64 rx_pause_frames; + u64 tx_ok; + u64 tx_single_cols; + u64 tx_multiple_cols; + u64 rx_ok; + u64 rx_fcs_errors; + u64 rx_align_errors; + u64 tx_deferred; + u64 tx_late_cols; + u64 tx_excessive_cols; + u64 tx_underruns; + u64 tx_carrier_errors; + u64 rx_resource_errors; + u64 rx_overruns; + u64 rx_symbol_errors; + u64 rx_oversize_pkts; + u64 rx_jabbers; + u64 rx_undersize_pkts; + u64 sqe_test_errors; + u64 rx_length_mismatch; + u64 tx_pause_frames; }; struct gem_stats { - u32 tx_octets_31_0; - u32 tx_octets_47_32; - u32 tx_frames; - u32 tx_broadcast_frames; - u32 tx_multicast_frames; - u32 tx_pause_frames; - u32 tx_64_byte_frames; - u32 tx_65_127_byte_frames; - u32 tx_128_255_byte_frames; - u32 tx_256_511_byte_frames; - u32 tx_512_1023_byte_frames; - u32 tx_1024_1518_byte_frames; - u32 tx_greater_than_1518_byte_frames; - u32 tx_underrun; - u32 tx_single_collision_frames; - u32 tx_multiple_collision_frames; - u32 tx_excessive_collisions; - u32 tx_late_collisions; - u32 tx_deferred_frames; - u32 tx_carrier_sense_errors; - u32 rx_octets_31_0; - u32 rx_octets_47_32; - u32 rx_frames; - u32 rx_broadcast_frames; - u32 rx_multicast_frames; - u32 rx_pause_frames; - u32 rx_64_byte_frames; - u32 rx_65_127_byte_frames; - u32 rx_128_255_byte_frames; - u32 rx_256_511_byte_frames; - u32 rx_512_1023_byte_frames; - u32 rx_1024_1518_byte_frames; - u32 rx_greater_than_1518_byte_frames; - u32 rx_undersized_frames; - u32 rx_oversize_frames; - u32 rx_jabbers; - u32 rx_frame_check_sequence_errors; - u32 rx_length_field_frame_errors; - u32 rx_symbol_errors; - u32 rx_alignment_errors; - u32 rx_resource_errors; - u32 rx_overruns; - u32 rx_ip_header_checksum_errors; - u32 rx_tcp_checksum_errors; - u32 rx_udp_checksum_errors; + u64 tx_octets; + u64 tx_frames; + u64 tx_broadcast_frames; + u64 tx_multicast_frames; + u64 tx_pause_frames; + u64 tx_64_byte_frames; + u64 tx_65_127_byte_frames; + u64 tx_128_255_byte_frames; + u64 tx_256_511_byte_frames; + u64 tx_512_1023_byte_frames; + u64 tx_1024_1518_byte_frames; + u64 tx_greater_than_1518_byte_frames; + u64 tx_underrun; + u64 tx_single_collision_frames; + u64 tx_multiple_collision_frames; + u64 tx_excessive_collisions; + u64 tx_late_collisions; + u64 tx_deferred_frames; + u64 tx_carrier_sense_errors; + u64 rx_octets; + u64 rx_frames; + u64 rx_broadcast_frames; + u64 rx_multicast_frames; + u64 rx_pause_frames; + u64 rx_64_byte_frames; + u64 rx_65_127_byte_frames; + u64 rx_128_255_byte_frames; + u64 rx_256_511_byte_frames; + u64 rx_512_1023_byte_frames; + u64 rx_1024_1518_byte_frames; + u64 rx_greater_than_1518_byte_frames; + u64 rx_undersized_frames; + u64 rx_oversize_frames; + u64 rx_jabbers; + u64 rx_frame_check_sequence_errors; + u64 rx_length_field_frame_errors; + u64 rx_symbol_errors; + u64 rx_alignment_errors; + u64 rx_resource_errors; + u64 rx_overruns; + u64 rx_ip_header_checksum_errors; + u64 rx_tcp_checksum_errors; + u64 rx_udp_checksum_errors; }; /* Describes the name and offset of an individual statistic register, as diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 48496209fb16..2112a9701e05 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -853,9 +853,7 @@ static int macb_mii_probe(struct net_device *dev) struct macb *bp = netdev_priv(dev); bp->phylink_sgmii_pcs.ops = &macb_phylink_pcs_ops; - bp->phylink_sgmii_pcs.neg_mode = true; bp->phylink_usx_pcs.ops = &macb_phylink_usx_pcs_ops; - bp->phylink_usx_pcs.neg_mode = true; bp->phylink_config.dev = &dev->dev; bp->phylink_config.type = PHYLINK_NETDEV; @@ -990,8 +988,8 @@ err_out: static void macb_update_stats(struct macb *bp) { - u32 *p = &bp->hw_stats.macb.rx_pause_frames; - u32 *end = &bp->hw_stats.macb.tx_pause_frames + 1; + u64 *p = &bp->hw_stats.macb.rx_pause_frames; + u64 *end = &bp->hw_stats.macb.tx_pause_frames + 1; int offset = MACB_PFR; WARN_ON((unsigned long)(end - p - 1) != (MACB_TPF - MACB_PFR) / 4); @@ -3071,7 +3069,7 @@ static void gem_update_stats(struct macb *bp) unsigned int i, q, idx; unsigned long *stat; - u32 *p = &bp->hw_stats.gem.tx_octets_31_0; + u64 *p = &bp->hw_stats.gem.tx_octets; for (i = 0; i < GEM_STATS_LEN; ++i, ++p) { u32 offset = gem_statistics[i].offset; @@ -3084,7 +3082,7 @@ static void gem_update_stats(struct macb *bp) /* Add GEM_OCTTXH, GEM_OCTRXH */ val = bp->macb_reg_readl(bp, offset + 4); bp->ethtool_stats[i] += ((u64)val) << 32; - *(++p) += val; + *(p++) += ((u64)val) << 32; } } @@ -3094,15 +3092,12 @@ static void gem_update_stats(struct macb *bp) bp->ethtool_stats[idx++] = *stat; } -static struct net_device_stats *gem_get_stats(struct macb *bp) +static void gem_get_stats(struct macb *bp, struct rtnl_link_stats64 *nstat) { struct gem_stats *hwstat = &bp->hw_stats.gem; - struct net_device_stats *nstat = &bp->dev->stats; - if (!netif_running(bp->dev)) - return nstat; - - gem_update_stats(bp); + if (netif_running(bp->dev)) + gem_update_stats(bp); nstat->rx_errors = (hwstat->rx_frame_check_sequence_errors + hwstat->rx_alignment_errors + @@ -3131,8 +3126,6 @@ static struct net_device_stats *gem_get_stats(struct macb *bp) nstat->tx_aborted_errors = hwstat->tx_excessive_collisions; nstat->tx_carrier_errors = hwstat->tx_carrier_sense_errors; nstat->tx_fifo_errors = hwstat->tx_underrun; - - return nstat; } static void gem_get_ethtool_stats(struct net_device *dev, @@ -3183,14 +3176,17 @@ static void gem_get_ethtool_strings(struct net_device *dev, u32 sset, u8 *p) } } -static struct net_device_stats *macb_get_stats(struct net_device *dev) +static void macb_get_stats(struct net_device *dev, + struct rtnl_link_stats64 *nstat) { struct macb *bp = netdev_priv(dev); - struct net_device_stats *nstat = &bp->dev->stats; struct macb_stats *hwstat = &bp->hw_stats.macb; - if (macb_is_gem(bp)) - return gem_get_stats(bp); + netdev_stats_to_stats64(nstat, &bp->dev->stats); + if (macb_is_gem(bp)) { + gem_get_stats(bp, nstat); + return; + } /* read stats from hardware */ macb_update_stats(bp); @@ -3226,8 +3222,154 @@ static struct net_device_stats *macb_get_stats(struct net_device *dev) nstat->tx_carrier_errors = hwstat->tx_carrier_errors; nstat->tx_fifo_errors = hwstat->tx_underruns; /* Don't know about heartbeat or window errors... */ +} + +static void macb_get_pause_stats(struct net_device *dev, + struct ethtool_pause_stats *pause_stats) +{ + struct macb *bp = netdev_priv(dev); + struct macb_stats *hwstat = &bp->hw_stats.macb; + + macb_update_stats(bp); + pause_stats->tx_pause_frames = hwstat->tx_pause_frames; + pause_stats->rx_pause_frames = hwstat->rx_pause_frames; +} + +static void gem_get_pause_stats(struct net_device *dev, + struct ethtool_pause_stats *pause_stats) +{ + struct macb *bp = netdev_priv(dev); + struct gem_stats *hwstat = &bp->hw_stats.gem; + + gem_update_stats(bp); + pause_stats->tx_pause_frames = hwstat->tx_pause_frames; + pause_stats->rx_pause_frames = hwstat->rx_pause_frames; +} + +static void macb_get_eth_mac_stats(struct net_device *dev, + struct ethtool_eth_mac_stats *mac_stats) +{ + struct macb *bp = netdev_priv(dev); + struct macb_stats *hwstat = &bp->hw_stats.macb; + + macb_update_stats(bp); + mac_stats->FramesTransmittedOK = hwstat->tx_ok; + mac_stats->SingleCollisionFrames = hwstat->tx_single_cols; + mac_stats->MultipleCollisionFrames = hwstat->tx_multiple_cols; + mac_stats->FramesReceivedOK = hwstat->rx_ok; + mac_stats->FrameCheckSequenceErrors = hwstat->rx_fcs_errors; + mac_stats->AlignmentErrors = hwstat->rx_align_errors; + mac_stats->FramesWithDeferredXmissions = hwstat->tx_deferred; + mac_stats->LateCollisions = hwstat->tx_late_cols; + mac_stats->FramesAbortedDueToXSColls = hwstat->tx_excessive_cols; + mac_stats->FramesLostDueToIntMACXmitError = hwstat->tx_underruns; + mac_stats->CarrierSenseErrors = hwstat->tx_carrier_errors; + mac_stats->FramesLostDueToIntMACRcvError = hwstat->rx_overruns; + mac_stats->InRangeLengthErrors = hwstat->rx_length_mismatch; + mac_stats->FrameTooLongErrors = hwstat->rx_oversize_pkts; +} + +static void gem_get_eth_mac_stats(struct net_device *dev, + struct ethtool_eth_mac_stats *mac_stats) +{ + struct macb *bp = netdev_priv(dev); + struct gem_stats *hwstat = &bp->hw_stats.gem; + + gem_update_stats(bp); + mac_stats->FramesTransmittedOK = hwstat->tx_frames; + mac_stats->SingleCollisionFrames = hwstat->tx_single_collision_frames; + mac_stats->MultipleCollisionFrames = + hwstat->tx_multiple_collision_frames; + mac_stats->FramesReceivedOK = hwstat->rx_frames; + mac_stats->FrameCheckSequenceErrors = + hwstat->rx_frame_check_sequence_errors; + mac_stats->AlignmentErrors = hwstat->rx_alignment_errors; + mac_stats->OctetsTransmittedOK = hwstat->tx_octets; + mac_stats->FramesWithDeferredXmissions = hwstat->tx_deferred_frames; + mac_stats->LateCollisions = hwstat->tx_late_collisions; + mac_stats->FramesAbortedDueToXSColls = hwstat->tx_excessive_collisions; + mac_stats->FramesLostDueToIntMACXmitError = hwstat->tx_underrun; + mac_stats->CarrierSenseErrors = hwstat->tx_carrier_sense_errors; + mac_stats->OctetsReceivedOK = hwstat->rx_octets; + mac_stats->MulticastFramesXmittedOK = hwstat->tx_multicast_frames; + mac_stats->BroadcastFramesXmittedOK = hwstat->tx_broadcast_frames; + mac_stats->MulticastFramesReceivedOK = hwstat->rx_multicast_frames; + mac_stats->BroadcastFramesReceivedOK = hwstat->rx_broadcast_frames; + mac_stats->InRangeLengthErrors = hwstat->rx_length_field_frame_errors; + mac_stats->FrameTooLongErrors = hwstat->rx_oversize_frames; +} + +/* TODO: Report SQE test errors when added to phy_stats */ +static void macb_get_eth_phy_stats(struct net_device *dev, + struct ethtool_eth_phy_stats *phy_stats) +{ + struct macb *bp = netdev_priv(dev); + struct macb_stats *hwstat = &bp->hw_stats.macb; - return nstat; + macb_update_stats(bp); + phy_stats->SymbolErrorDuringCarrier = hwstat->rx_symbol_errors; +} + +static void gem_get_eth_phy_stats(struct net_device *dev, + struct ethtool_eth_phy_stats *phy_stats) +{ + struct macb *bp = netdev_priv(dev); + struct gem_stats *hwstat = &bp->hw_stats.gem; + + gem_update_stats(bp); + phy_stats->SymbolErrorDuringCarrier = hwstat->rx_symbol_errors; +} + +static void macb_get_rmon_stats(struct net_device *dev, + struct ethtool_rmon_stats *rmon_stats, + const struct ethtool_rmon_hist_range **ranges) +{ + struct macb *bp = netdev_priv(dev); + struct macb_stats *hwstat = &bp->hw_stats.macb; + + macb_update_stats(bp); + rmon_stats->undersize_pkts = hwstat->rx_undersize_pkts; + rmon_stats->oversize_pkts = hwstat->rx_oversize_pkts; + rmon_stats->jabbers = hwstat->rx_jabbers; +} + +static const struct ethtool_rmon_hist_range gem_rmon_ranges[] = { + { 64, 64 }, + { 65, 127 }, + { 128, 255 }, + { 256, 511 }, + { 512, 1023 }, + { 1024, 1518 }, + { 1519, 16384 }, + { }, +}; + +static void gem_get_rmon_stats(struct net_device *dev, + struct ethtool_rmon_stats *rmon_stats, + const struct ethtool_rmon_hist_range **ranges) +{ + struct macb *bp = netdev_priv(dev); + struct gem_stats *hwstat = &bp->hw_stats.gem; + + gem_update_stats(bp); + rmon_stats->undersize_pkts = hwstat->rx_undersized_frames; + rmon_stats->oversize_pkts = hwstat->rx_oversize_frames; + rmon_stats->jabbers = hwstat->rx_jabbers; + rmon_stats->hist[0] = hwstat->rx_64_byte_frames; + rmon_stats->hist[1] = hwstat->rx_65_127_byte_frames; + rmon_stats->hist[2] = hwstat->rx_128_255_byte_frames; + rmon_stats->hist[3] = hwstat->rx_256_511_byte_frames; + rmon_stats->hist[4] = hwstat->rx_512_1023_byte_frames; + rmon_stats->hist[5] = hwstat->rx_1024_1518_byte_frames; + rmon_stats->hist[6] = hwstat->rx_greater_than_1518_byte_frames; + rmon_stats->hist_tx[0] = hwstat->tx_64_byte_frames; + rmon_stats->hist_tx[1] = hwstat->tx_65_127_byte_frames; + rmon_stats->hist_tx[2] = hwstat->tx_128_255_byte_frames; + rmon_stats->hist_tx[3] = hwstat->tx_256_511_byte_frames; + rmon_stats->hist_tx[4] = hwstat->tx_512_1023_byte_frames; + rmon_stats->hist_tx[5] = hwstat->tx_1024_1518_byte_frames; + rmon_stats->hist_tx[6] = hwstat->tx_greater_than_1518_byte_frames; + *ranges = gem_rmon_ranges; } static int macb_get_regs_len(struct net_device *netdev) @@ -3756,6 +3898,10 @@ static const struct ethtool_ops macb_ethtool_ops = { .get_regs = macb_get_regs, .get_link = ethtool_op_get_link, .get_ts_info = ethtool_op_get_ts_info, + .get_pause_stats = macb_get_pause_stats, + .get_eth_mac_stats = macb_get_eth_mac_stats, + .get_eth_phy_stats = macb_get_eth_phy_stats, + .get_rmon_stats = macb_get_rmon_stats, .get_wol = macb_get_wol, .set_wol = macb_set_wol, .get_link_ksettings = macb_get_link_ksettings, @@ -3774,6 +3920,10 @@ static const struct ethtool_ops gem_ethtool_ops = { .get_ethtool_stats = gem_get_ethtool_stats, .get_strings = gem_get_ethtool_strings, .get_sset_count = gem_get_sset_count, + .get_pause_stats = gem_get_pause_stats, + .get_eth_mac_stats = gem_get_eth_mac_stats, + .get_eth_phy_stats = gem_get_eth_phy_stats, + .get_rmon_stats = gem_get_rmon_stats, .get_link_ksettings = macb_get_link_ksettings, .set_link_ksettings = macb_set_link_ksettings, .get_ringparam = macb_get_ringparam, @@ -3910,7 +4060,7 @@ static const struct net_device_ops macb_netdev_ops = { .ndo_stop = macb_close, .ndo_start_xmit = macb_start_xmit, .ndo_set_rx_mode = macb_set_rx_mode, - .ndo_get_stats = macb_get_stats, + .ndo_get_stats64 = macb_get_stats, .ndo_eth_ioctl = macb_ioctl, .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = macb_change_mtu, @@ -4571,7 +4721,7 @@ static const struct net_device_ops at91ether_netdev_ops = { .ndo_open = at91ether_open, .ndo_stop = at91ether_close, .ndo_start_xmit = at91ether_start_xmit, - .ndo_get_stats = macb_get_stats, + .ndo_get_stats64 = macb_get_stats, .ndo_set_rx_mode = macb_set_rx_mode, .ndo_set_mac_address = eth_mac_addr, .ndo_eth_ioctl = macb_ioctl, diff --git a/drivers/net/ethernet/freescale/fman/fman_dtsec.c b/drivers/net/ethernet/freescale/fman/fman_dtsec.c index b3e2a596ad2c..51402dff72c5 100644 --- a/drivers/net/ethernet/freescale/fman/fman_dtsec.c +++ b/drivers/net/ethernet/freescale/fman/fman_dtsec.c @@ -1446,7 +1446,6 @@ int dtsec_initialization(struct mac_device *mac_dev, goto _return_fm_mac_free; } dtsec->pcs.ops = &dtsec_pcs_ops; - dtsec->pcs.neg_mode = true; dtsec->pcs.poll = true; supported = mac_dev->phylink_config.supported_interfaces; diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c index 88510f822759..affd5a6c44e7 100644 --- a/drivers/net/ethernet/freescale/ucc_geth.c +++ b/drivers/net/ethernet/freescale/ucc_geth.c @@ -3408,7 +3408,7 @@ static int ucc_geth_parse_clock(struct device_node *np, const char *which, return 0; } -struct phylink_mac_ops ugeth_mac_ops = { +static const struct phylink_mac_ops ugeth_mac_ops = { .mac_link_up = ugeth_mac_link_up, .mac_link_down = ugeth_mac_link_down, .mac_config = ugeth_mac_config, diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h index 8167cc5fb0df..216d6e157bef 100644 --- a/drivers/net/ethernet/google/gve/gve.h +++ b/drivers/net/ethernet/google/gve/gve.h @@ -68,6 +68,9 @@ #define GVE_FLOW_RULE_IDS_CACHE_SIZE \ (GVE_ADMINQ_BUFFER_SIZE / sizeof(((struct gve_adminq_queried_flow_rule *)0)->location)) +#define GVE_RSS_KEY_SIZE 40 +#define GVE_RSS_INDIR_SIZE 128 + #define GVE_XDP_ACTIONS 5 #define GVE_GQ_TX_MIN_PKT_DESC_BYTES 182 @@ -672,6 +675,7 @@ struct gve_rx_alloc_rings_cfg { u16 packet_buffer_size; bool raw_addressing; bool enable_header_split; + bool reset_rss; /* Allocated resources are returned here */ struct gve_rx_ring *rx; @@ -722,6 +726,11 @@ struct gve_flow_rules_cache { u32 rule_ids_cache_num; }; +struct gve_rss_config { + u8 *hash_key; + u32 *hash_lut; +}; + struct gve_priv { struct net_device *dev; struct gve_tx_ring *tx; /* array of tx_cfg.num_queues */ @@ -842,6 +851,8 @@ struct gve_priv { u16 rss_key_size; u16 rss_lut_size; + bool cache_rss_config; + struct gve_rss_config rss_config; }; enum gve_service_task_flags_bit { @@ -1116,6 +1127,16 @@ static inline u32 gve_xdp_tx_start_queue_id(struct gve_priv *priv) return gve_xdp_tx_queue_id(priv, 0); } +static inline bool gve_supports_xdp_xmit(struct gve_priv *priv) +{ + switch (priv->queue_format) { + case GVE_GQI_QPL_FORMAT: + return true; + default: + return false; + } +} + /* gqi napi handler defined in gve_main.c */ int gve_napi_poll(struct napi_struct *napi, int budget); @@ -1210,13 +1231,16 @@ int gve_adjust_config(struct gve_priv *priv, struct gve_rx_alloc_rings_cfg *rx_alloc_cfg); int gve_adjust_queues(struct gve_priv *priv, struct gve_queue_config new_rx_config, - struct gve_queue_config new_tx_config); + struct gve_queue_config new_tx_config, + bool reset_rss); /* flow steering rule */ int gve_get_flow_rule_entry(struct gve_priv *priv, struct ethtool_rxnfc *cmd); int gve_get_flow_rule_ids(struct gve_priv *priv, struct ethtool_rxnfc *cmd, u32 *rule_locs); int gve_add_flow_rule(struct gve_priv *priv, struct ethtool_rxnfc *cmd); int gve_del_flow_rule(struct gve_priv *priv, struct ethtool_rxnfc *cmd); int gve_flow_rules_reset(struct gve_priv *priv); +/* RSS config */ +int gve_init_rss_config(struct gve_priv *priv, u16 num_queues); /* report stats handling */ void gve_handle_report_stats(struct gve_priv *priv); /* exported by ethtool.c */ diff --git a/drivers/net/ethernet/google/gve/gve_adminq.c b/drivers/net/ethernet/google/gve/gve_adminq.c index aa7d723011d0..be7a423e5ab9 100644 --- a/drivers/net/ethernet/google/gve/gve_adminq.c +++ b/drivers/net/ethernet/google/gve/gve_adminq.c @@ -885,6 +885,15 @@ static void gve_set_default_desc_cnt(struct gve_priv *priv, priv->min_rx_desc_cnt = priv->rx_desc_cnt; } +static void gve_set_default_rss_sizes(struct gve_priv *priv) +{ + if (!gve_is_gqi(priv)) { + priv->rss_key_size = GVE_RSS_KEY_SIZE; + priv->rss_lut_size = GVE_RSS_INDIR_SIZE; + priv->cache_rss_config = true; + } +} + static void gve_enable_supported_features(struct gve_priv *priv, u32 supported_features_mask, const struct gve_device_option_jumbo_frames @@ -968,6 +977,10 @@ static void gve_enable_supported_features(struct gve_priv *priv, be16_to_cpu(dev_op_rss_config->hash_key_size); priv->rss_lut_size = be16_to_cpu(dev_op_rss_config->hash_lut_size); + priv->cache_rss_config = false; + dev_dbg(&priv->pdev->dev, + "RSS device option enabled with key size of %u, lut size of %u.\n", + priv->rss_key_size, priv->rss_lut_size); } } @@ -1052,6 +1065,8 @@ int gve_adminq_describe_device(struct gve_priv *priv) /* set default descriptor counts */ gve_set_default_desc_cnt(priv, descriptor); + gve_set_default_rss_sizes(priv); + /* DQO supports LRO. */ if (!gve_is_gqi(priv)) priv->dev->hw_features |= NETIF_F_LRO; @@ -1276,8 +1291,9 @@ int gve_adminq_reset_flow_rules(struct gve_priv *priv) int gve_adminq_configure_rss(struct gve_priv *priv, struct ethtool_rxfh_param *rxfh) { + const u32 *hash_lut_to_config = NULL; + const u8 *hash_key_to_config = NULL; dma_addr_t lut_bus = 0, key_bus = 0; - u16 key_size = 0, lut_size = 0; union gve_adminq_command cmd; __be32 *lut = NULL; u8 hash_alg = 0; @@ -1287,7 +1303,7 @@ int gve_adminq_configure_rss(struct gve_priv *priv, struct ethtool_rxfh_param *r switch (rxfh->hfunc) { case ETH_RSS_HASH_NO_CHANGE: - break; + fallthrough; case ETH_RSS_HASH_TOP: hash_alg = ETH_RSS_HASH_TOP; break; @@ -1296,27 +1312,46 @@ int gve_adminq_configure_rss(struct gve_priv *priv, struct ethtool_rxfh_param *r } if (rxfh->indir) { - lut_size = priv->rss_lut_size; + if (rxfh->indir_size != priv->rss_lut_size) + return -EINVAL; + + hash_lut_to_config = rxfh->indir; + } else if (priv->cache_rss_config) { + hash_lut_to_config = priv->rss_config.hash_lut; + } + + if (hash_lut_to_config) { lut = dma_alloc_coherent(&priv->pdev->dev, - lut_size * sizeof(*lut), + priv->rss_lut_size * sizeof(*lut), &lut_bus, GFP_KERNEL); if (!lut) return -ENOMEM; for (i = 0; i < priv->rss_lut_size; i++) - lut[i] = cpu_to_be32(rxfh->indir[i]); + lut[i] = cpu_to_be32(hash_lut_to_config[i]); } if (rxfh->key) { - key_size = priv->rss_key_size; + if (rxfh->key_size != priv->rss_key_size) { + err = -EINVAL; + goto out; + } + + hash_key_to_config = rxfh->key; + } else if (priv->cache_rss_config) { + hash_key_to_config = priv->rss_config.hash_key; + } + + if (hash_key_to_config) { key = dma_alloc_coherent(&priv->pdev->dev, - key_size, &key_bus, GFP_KERNEL); + priv->rss_key_size, + &key_bus, GFP_KERNEL); if (!key) { err = -ENOMEM; goto out; } - memcpy(key, rxfh->key, key_size); + memcpy(key, hash_key_to_config, priv->rss_key_size); } /* Zero-valued fields in the cmd.configure_rss instruct the device to @@ -1330,8 +1365,10 @@ int gve_adminq_configure_rss(struct gve_priv *priv, struct ethtool_rxfh_param *r BIT(GVE_RSS_HASH_TCPV6) | BIT(GVE_RSS_HASH_UDPV6)), .hash_alg = hash_alg, - .hash_key_size = cpu_to_be16(key_size), - .hash_lut_size = cpu_to_be16(lut_size), + .hash_key_size = + cpu_to_be16((key_bus) ? priv->rss_key_size : 0), + .hash_lut_size = + cpu_to_be16((lut_bus) ? priv->rss_lut_size : 0), .hash_key_addr = cpu_to_be64(key_bus), .hash_lut_addr = cpu_to_be64(lut_bus), }; @@ -1341,11 +1378,11 @@ int gve_adminq_configure_rss(struct gve_priv *priv, struct ethtool_rxfh_param *r out: if (lut) dma_free_coherent(&priv->pdev->dev, - lut_size * sizeof(*lut), + priv->rss_lut_size * sizeof(*lut), lut, lut_bus); if (key) dma_free_coherent(&priv->pdev->dev, - key_size, key, key_bus); + priv->rss_key_size, key, key_bus); return err; } @@ -1449,12 +1486,15 @@ static int gve_adminq_process_rss_query(struct gve_priv *priv, rxfh->hfunc = descriptor->hash_alg; rss_info_addr = (void *)(descriptor + 1); - if (rxfh->key) + if (rxfh->key) { + rxfh->key_size = priv->rss_key_size; memcpy(rxfh->key, rss_info_addr, priv->rss_key_size); + } rss_info_addr += priv->rss_key_size; lut = (__be32 *)rss_info_addr; if (rxfh->indir) { + rxfh->indir_size = priv->rss_lut_size; for (i = 0; i < priv->rss_lut_size; i++) rxfh->indir[i] = be32_to_cpu(lut[i]); } diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c index bdfc6e77b2af..a572f1e05934 100644 --- a/drivers/net/ethernet/google/gve/gve_ethtool.c +++ b/drivers/net/ethernet/google/gve/gve_ethtool.c @@ -482,6 +482,7 @@ static int gve_set_channels(struct net_device *netdev, struct ethtool_channels old_settings; int new_tx = cmd->tx_count; int new_rx = cmd->rx_count; + bool reset_rss = false; gve_get_channels(netdev, &old_settings); @@ -498,16 +499,14 @@ static int gve_set_channels(struct net_device *netdev, return -EINVAL; } - if (!netif_running(netdev)) { - priv->tx_cfg.num_queues = new_tx; - priv->rx_cfg.num_queues = new_rx; - return 0; - } + if (new_rx != priv->rx_cfg.num_queues && + priv->cache_rss_config && !netif_is_rxfh_configured(netdev)) + reset_rss = true; new_tx_cfg.num_queues = new_tx; new_rx_cfg.num_queues = new_rx; - return gve_adjust_queues(priv, new_rx_cfg, new_tx_cfg); + return gve_adjust_queues(priv, new_rx_cfg, new_tx_cfg, reset_rss); } static void gve_get_ringparam(struct net_device *netdev, @@ -855,6 +854,25 @@ static u32 gve_get_rxfh_indir_size(struct net_device *netdev) return priv->rss_lut_size; } +static void gve_get_rss_config_cache(struct gve_priv *priv, + struct ethtool_rxfh_param *rxfh) +{ + struct gve_rss_config *rss_config = &priv->rss_config; + + rxfh->hfunc = ETH_RSS_HASH_TOP; + + if (rxfh->key) { + rxfh->key_size = priv->rss_key_size; + memcpy(rxfh->key, rss_config->hash_key, priv->rss_key_size); + } + + if (rxfh->indir) { + rxfh->indir_size = priv->rss_lut_size; + memcpy(rxfh->indir, rss_config->hash_lut, + priv->rss_lut_size * sizeof(*rxfh->indir)); + } +} + static int gve_get_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh) { struct gve_priv *priv = netdev_priv(netdev); @@ -862,18 +880,46 @@ static int gve_get_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rx if (!priv->rss_key_size || !priv->rss_lut_size) return -EOPNOTSUPP; + if (priv->cache_rss_config) { + gve_get_rss_config_cache(priv, rxfh); + return 0; + } + return gve_adminq_query_rss_config(priv, rxfh); } +static void gve_set_rss_config_cache(struct gve_priv *priv, + struct ethtool_rxfh_param *rxfh) +{ + struct gve_rss_config *rss_config = &priv->rss_config; + + if (rxfh->key) + memcpy(rss_config->hash_key, rxfh->key, priv->rss_key_size); + + if (rxfh->indir) + memcpy(rss_config->hash_lut, rxfh->indir, + priv->rss_lut_size * sizeof(*rxfh->indir)); +} + static int gve_set_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh, struct netlink_ext_ack *extack) { struct gve_priv *priv = netdev_priv(netdev); + int err; if (!priv->rss_key_size || !priv->rss_lut_size) return -EOPNOTSUPP; - return gve_adminq_configure_rss(priv, rxfh); + err = gve_adminq_configure_rss(priv, rxfh); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Fail to configure RSS config"); + return err; + } + + if (priv->cache_rss_config) + gve_set_rss_config_cache(priv, rxfh); + + return 0; } const struct ethtool_ops gve_ethtool_ops = { diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 533e659b15b3..029be8342b7b 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -184,6 +184,43 @@ static void gve_free_flow_rule_caches(struct gve_priv *priv) flow_rules_cache->rules_cache = NULL; } +static int gve_alloc_rss_config_cache(struct gve_priv *priv) +{ + struct gve_rss_config *rss_config = &priv->rss_config; + + if (!priv->cache_rss_config) + return 0; + + rss_config->hash_key = kcalloc(priv->rss_key_size, + sizeof(rss_config->hash_key[0]), + GFP_KERNEL); + if (!rss_config->hash_key) + return -ENOMEM; + + rss_config->hash_lut = kcalloc(priv->rss_lut_size, + sizeof(rss_config->hash_lut[0]), + GFP_KERNEL); + if (!rss_config->hash_lut) + goto free_rss_key_cache; + + return 0; + +free_rss_key_cache: + kfree(rss_config->hash_key); + rss_config->hash_key = NULL; + return -ENOMEM; +} + +static void gve_free_rss_config_cache(struct gve_priv *priv) +{ + struct gve_rss_config *rss_config = &priv->rss_config; + + kfree(rss_config->hash_key); + kfree(rss_config->hash_lut); + + memset(rss_config, 0, sizeof(*rss_config)); +} + static int gve_alloc_counter_array(struct gve_priv *priv) { priv->counter_array = @@ -575,9 +612,12 @@ static int gve_setup_device_resources(struct gve_priv *priv) err = gve_alloc_flow_rule_caches(priv); if (err) return err; - err = gve_alloc_counter_array(priv); + err = gve_alloc_rss_config_cache(priv); if (err) goto abort_with_flow_rule_caches; + err = gve_alloc_counter_array(priv); + if (err) + goto abort_with_rss_config_cache; err = gve_alloc_notify_blocks(priv); if (err) goto abort_with_counter; @@ -611,6 +651,12 @@ static int gve_setup_device_resources(struct gve_priv *priv) } } + err = gve_init_rss_config(priv, priv->rx_cfg.num_queues); + if (err) { + dev_err(&priv->pdev->dev, "Failed to init RSS config"); + goto abort_with_ptype_lut; + } + err = gve_adminq_report_stats(priv, priv->stats_report_len, priv->stats_report_bus, GVE_STATS_REPORT_TIMER_PERIOD); @@ -629,6 +675,8 @@ abort_with_ntfy_blocks: gve_free_notify_blocks(priv); abort_with_counter: gve_free_counter_array(priv); +abort_with_rss_config_cache: + gve_free_rss_config_cache(priv); abort_with_flow_rule_caches: gve_free_flow_rule_caches(priv); @@ -669,6 +717,7 @@ static void gve_teardown_device_resources(struct gve_priv *priv) priv->ptype_lut_dqo = NULL; gve_free_flow_rule_caches(priv); + gve_free_rss_config_cache(priv); gve_free_counter_array(priv); gve_free_notify_blocks(priv); gve_free_stats_report(priv); @@ -1390,6 +1439,12 @@ static int gve_queues_start(struct gve_priv *priv, if (err) goto stop_and_free_rings; + if (rx_alloc_cfg->reset_rss) { + err = gve_init_rss_config(priv, priv->rx_cfg.num_queues); + if (err) + goto reset; + } + err = gve_register_qpls(priv); if (err) goto reset; @@ -1786,6 +1841,26 @@ static int gve_xdp(struct net_device *dev, struct netdev_bpf *xdp) } } +int gve_init_rss_config(struct gve_priv *priv, u16 num_queues) +{ + struct gve_rss_config *rss_config = &priv->rss_config; + struct ethtool_rxfh_param rxfh = {0}; + u16 i; + + if (!priv->cache_rss_config) + return 0; + + for (i = 0; i < priv->rss_lut_size; i++) + rss_config->hash_lut[i] = + ethtool_rxfh_indir_default(i, num_queues); + + netdev_rss_key_fill(rss_config->hash_key, priv->rss_key_size); + + rxfh.hfunc = ETH_RSS_HASH_TOP; + + return gve_adminq_configure_rss(priv, &rxfh); +} + int gve_flow_rules_reset(struct gve_priv *priv) { if (!priv->max_flow_rules) @@ -1834,7 +1909,8 @@ int gve_adjust_config(struct gve_priv *priv, int gve_adjust_queues(struct gve_priv *priv, struct gve_queue_config new_rx_config, - struct gve_queue_config new_tx_config) + struct gve_queue_config new_tx_config, + bool reset_rss) { struct gve_tx_alloc_rings_cfg tx_alloc_cfg = {0}; struct gve_rx_alloc_rings_cfg rx_alloc_cfg = {0}; @@ -1847,6 +1923,7 @@ int gve_adjust_queues(struct gve_priv *priv, tx_alloc_cfg.qcfg = &new_tx_config; rx_alloc_cfg.qcfg_tx = &new_tx_config; rx_alloc_cfg.qcfg = &new_rx_config; + rx_alloc_cfg.reset_rss = reset_rss; tx_alloc_cfg.num_rings = new_tx_config.num_queues; /* Add dedicated XDP TX queues if enabled. */ @@ -1858,6 +1935,11 @@ int gve_adjust_queues(struct gve_priv *priv, return err; } /* Set the config for the next up. */ + if (reset_rss) { + err = gve_init_rss_config(priv, new_rx_config.num_queues); + if (err) + return err; + } priv->tx_cfg = new_tx_config; priv->rx_cfg = new_rx_config; @@ -1903,6 +1985,8 @@ static void gve_turndown(struct gve_priv *priv) /* Stop tx queues */ netif_tx_disable(priv->dev); + xdp_features_clear_redirect_target(priv->dev); + gve_clear_napi_enabled(priv); gve_clear_report_stats(priv); @@ -1972,6 +2056,9 @@ static void gve_turnup(struct gve_priv *priv) napi_schedule(&block->napi); } + if (priv->num_xdp_queues && gve_supports_xdp_xmit(priv)) + xdp_features_set_redirect_target(priv->dev, false); + gve_set_napi_enabled(priv); } @@ -2246,7 +2333,6 @@ static void gve_set_netdev_xdp_features(struct gve_priv *priv) if (priv->queue_format == GVE_GQI_QPL_FORMAT) { xdp_features = NETDEV_XDP_ACT_BASIC; xdp_features |= NETDEV_XDP_ACT_REDIRECT; - xdp_features |= NETDEV_XDP_ACT_NDO_XMIT; xdp_features |= NETDEV_XDP_ACT_XSK_ZEROCOPY; } else { xdp_features = 0; diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index e95ae0d39948..0676fc547b6f 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2408,6 +2408,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) dma_addr_t data_dma_addr; struct netdev_queue *txq; unsigned long lpar_rc; + unsigned int skblen; union sub_crq tx_crq; unsigned int offset; bool use_scrq_send_direct = false; @@ -2522,6 +2523,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) tx_buff->skb = skb; tx_buff->index = bufidx; tx_buff->pool_index = queue_num; + skblen = skb->len; memset(&tx_crq, 0, sizeof(tx_crq)); tx_crq.v1.first = IBMVNIC_CRQ_CMD; @@ -2614,7 +2616,7 @@ early_exit: netif_stop_subqueue(netdev, queue_num); } - tx_bytes += skb->len; + tx_bytes += skblen; txq_trans_cond_update(txq); ret = NETDEV_TX_OK; goto out; diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig index 26b9938bc38d..1640d2f27833 100644 --- a/drivers/net/ethernet/intel/Kconfig +++ b/drivers/net/ethernet/intel/Kconfig @@ -264,6 +264,7 @@ config I40EVF tristate "Intel(R) Ethernet Adaptive Virtual Function support" select IAVF depends on PCI_MSI + depends on PTP_1588_CLOCK_OPTIONAL help This driver supports virtual functions for Intel XL710, X710, X722, XXV710, and all devices advertising support for diff --git a/drivers/net/ethernet/intel/iavf/Makefile b/drivers/net/ethernet/intel/iavf/Makefile index 356ac9faa5bf..e13720a728ff 100644 --- a/drivers/net/ethernet/intel/iavf/Makefile +++ b/drivers/net/ethernet/intel/iavf/Makefile @@ -13,3 +13,5 @@ obj-$(CONFIG_IAVF) += iavf.o iavf-y := iavf_main.o iavf_ethtool.o iavf_virtchnl.o iavf_fdir.o \ iavf_adv_rss.o iavf_txrx.o iavf_common.o iavf_adminq.o + +iavf-$(CONFIG_PTP_1588_CLOCK) += iavf_ptp.o diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index 532a0a595fe8..9de3e0ba3731 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -41,6 +41,7 @@ #include "iavf_txrx.h" #include "iavf_fdir.h" #include "iavf_adv_rss.h" +#include "iavf_types.h" #include <linux/bitmap.h> #define DEFAULT_DEBUG_LEVEL_SHIFT 3 @@ -82,7 +83,7 @@ struct iavf_vsi { #define MAXIMUM_ETHERNET_VLAN_SIZE (VLAN_ETH_FRAME_LEN + ETH_FCS_LEN) -#define IAVF_RX_DESC(R, i) (&(((union iavf_32byte_rx_desc *)((R)->desc))[i])) +#define IAVF_RX_DESC(R, i) (&(((struct iavf_rx_desc *)((R)->desc))[i])) #define IAVF_TX_DESC(R, i) (&(((struct iavf_tx_desc *)((R)->desc))[i])) #define IAVF_TX_CTXTDESC(R, i) \ (&(((struct iavf_tx_context_desc *)((R)->desc))[i])) @@ -271,6 +272,7 @@ struct iavf_adapter { /* Lock to protect accesses to MAC and VLAN lists */ spinlock_t mac_vlan_list_lock; char misc_vector_name[IFNAMSIZ + 9]; + u8 rxdid; int num_active_queues; int num_req_queues; @@ -343,6 +345,17 @@ struct iavf_adapter { #define IAVF_FLAG_AQ_CONFIGURE_QUEUES_BW BIT_ULL(39) #define IAVF_FLAG_AQ_CFG_QUEUES_QUANTA_SIZE BIT_ULL(40) #define IAVF_FLAG_AQ_GET_QOS_CAPS BIT_ULL(41) +#define IAVF_FLAG_AQ_GET_SUPPORTED_RXDIDS BIT_ULL(42) +#define IAVF_FLAG_AQ_GET_PTP_CAPS BIT_ULL(43) +#define IAVF_FLAG_AQ_SEND_PTP_CMD BIT_ULL(44) + + /* AQ messages that must be sent after IAVF_FLAG_AQ_GET_CONFIG, in + * order to negotiated extended capabilities. + */ +#define IAVF_FLAG_AQ_EXTENDED_CAPS \ + (IAVF_FLAG_AQ_GET_OFFLOAD_VLAN_V2_CAPS | \ + IAVF_FLAG_AQ_GET_SUPPORTED_RXDIDS | \ + IAVF_FLAG_AQ_GET_PTP_CAPS) /* flags for processing extended capability messages during * __IAVF_INIT_EXTENDED_CAPS. Each capability exchange requires @@ -354,10 +367,18 @@ struct iavf_adapter { u64 extended_caps; #define IAVF_EXTENDED_CAP_SEND_VLAN_V2 BIT_ULL(0) #define IAVF_EXTENDED_CAP_RECV_VLAN_V2 BIT_ULL(1) +#define IAVF_EXTENDED_CAP_SEND_RXDID BIT_ULL(2) +#define IAVF_EXTENDED_CAP_RECV_RXDID BIT_ULL(3) +#define IAVF_EXTENDED_CAP_SEND_PTP BIT_ULL(4) +#define IAVF_EXTENDED_CAP_RECV_PTP BIT_ULL(5) #define IAVF_EXTENDED_CAPS \ (IAVF_EXTENDED_CAP_SEND_VLAN_V2 | \ - IAVF_EXTENDED_CAP_RECV_VLAN_V2) + IAVF_EXTENDED_CAP_RECV_VLAN_V2 | \ + IAVF_EXTENDED_CAP_SEND_RXDID | \ + IAVF_EXTENDED_CAP_RECV_RXDID | \ + IAVF_EXTENDED_CAP_SEND_PTP | \ + IAVF_EXTENDED_CAP_RECV_PTP) /* Lock to prevent possible clobbering of * current_netdev_promisc_flags @@ -417,12 +438,18 @@ struct iavf_adapter { VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF) #define QOS_ALLOWED(_a) ((_a)->vf_res->vf_cap_flags & \ VIRTCHNL_VF_OFFLOAD_QOS) +#define IAVF_RXDID_ALLOWED(a) \ + ((a)->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC) +#define IAVF_PTP_ALLOWED(a) \ + ((a)->vf_res->vf_cap_flags & VIRTCHNL_VF_CAP_PTP) struct virtchnl_vf_resource *vf_res; /* incl. all VSIs */ struct virtchnl_vsi_resource *vsi_res; /* our LAN VSI */ struct virtchnl_version_info pf_version; #define PF_IS_V11(_a) (((_a)->pf_version.major == 1) && \ ((_a)->pf_version.minor == 1)) struct virtchnl_vlan_caps vlan_v2_caps; + u64 supp_rxdids; + struct iavf_ptp ptp; u16 msg_enable; struct iavf_eth_stats current_stats; struct virtchnl_qos_cap_list *qos_caps; @@ -555,6 +582,10 @@ int iavf_send_vf_config_msg(struct iavf_adapter *adapter); int iavf_get_vf_config(struct iavf_adapter *adapter); int iavf_get_vf_vlan_v2_caps(struct iavf_adapter *adapter); int iavf_send_vf_offload_vlan_v2_msg(struct iavf_adapter *adapter); +int iavf_send_vf_supported_rxdids_msg(struct iavf_adapter *adapter); +int iavf_get_vf_supported_rxdids(struct iavf_adapter *adapter); +int iavf_send_vf_ptp_caps_msg(struct iavf_adapter *adapter); +int iavf_get_vf_ptp_caps(struct iavf_adapter *adapter); void iavf_set_queue_vlan_tag_loc(struct iavf_adapter *adapter); u16 iavf_get_num_vlans_added(struct iavf_adapter *adapter); void iavf_irq_enable(struct iavf_adapter *adapter, bool flush); diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 852e5b62f0a5..4c29739780bd 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -4,6 +4,7 @@ #include <linux/net/intel/libie/rx.h> #include "iavf.h" +#include "iavf_ptp.h" #include "iavf_prototype.h" /* All iavf tracepoints are defined by the include below, which must * be included exactly once across the whole kernel with @@ -710,6 +711,47 @@ static void iavf_configure_tx(struct iavf_adapter *adapter) } /** + * iavf_select_rx_desc_format - Select Rx descriptor format + * @adapter: adapter private structure + * + * Select what Rx descriptor format based on availability and enabled + * features. + * + * Return: the desired RXDID to select for a given Rx queue, as defined by + * enum virtchnl_rxdid_format. + */ +static u8 iavf_select_rx_desc_format(const struct iavf_adapter *adapter) +{ + u64 rxdids = adapter->supp_rxdids; + + /* If we did not negotiate VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC, we must + * stick with the default value of the legacy 32 byte format. + */ + if (!IAVF_RXDID_ALLOWED(adapter)) + return VIRTCHNL_RXDID_1_32B_BASE; + + /* Rx timestamping requires the use of flexible NIC descriptors */ + if (iavf_ptp_cap_supported(adapter, VIRTCHNL_1588_PTP_CAP_RX_TSTAMP)) { + if (rxdids & BIT(VIRTCHNL_RXDID_2_FLEX_SQ_NIC)) + return VIRTCHNL_RXDID_2_FLEX_SQ_NIC; + + pci_warn(adapter->pdev, + "Unable to negotiate flexible descriptor format\n"); + } + + /* Warn if the PF does not list support for the default legacy + * descriptor format. This shouldn't happen, as this is the format + * used if VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC is not supported. It is + * likely caused by a bug in the PF implementation failing to indicate + * support for the format. + */ + if (!(rxdids & VIRTCHNL_RXDID_1_32B_BASE_M)) + netdev_warn(adapter->netdev, "PF does not list support for default Rx descriptor format\n"); + + return VIRTCHNL_RXDID_1_32B_BASE; +} + +/** * iavf_configure_rx - Configure Receive Unit after Reset * @adapter: board private structure * @@ -719,8 +761,12 @@ static void iavf_configure_rx(struct iavf_adapter *adapter) { struct iavf_hw *hw = &adapter->hw; - for (u32 i = 0; i < adapter->num_active_queues; i++) + adapter->rxdid = iavf_select_rx_desc_format(adapter); + + for (u32 i = 0; i < adapter->num_active_queues; i++) { adapter->rx_rings[i].tail = hw->hw_addr + IAVF_QRX_TAIL1(i); + adapter->rx_rings[i].rxdid = adapter->rxdid; + } } /** @@ -2071,6 +2117,10 @@ static int iavf_process_aq_command(struct iavf_adapter *adapter) return iavf_send_vf_config_msg(adapter); if (adapter->aq_required & IAVF_FLAG_AQ_GET_OFFLOAD_VLAN_V2_CAPS) return iavf_send_vf_offload_vlan_v2_msg(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_GET_SUPPORTED_RXDIDS) + return iavf_send_vf_supported_rxdids_msg(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_GET_PTP_CAPS) + return iavf_send_vf_ptp_caps_msg(adapter); if (adapter->aq_required & IAVF_FLAG_AQ_DISABLE_QUEUES) { iavf_disable_queues(adapter); return 0; @@ -2235,7 +2285,10 @@ static int iavf_process_aq_command(struct iavf_adapter *adapter) iavf_enable_vlan_insertion_v2(adapter, ETH_P_8021AD); return 0; } - + if (adapter->aq_required & IAVF_FLAG_AQ_SEND_PTP_CMD) { + iavf_virtchnl_send_ptp_cmd(adapter); + return IAVF_SUCCESS; + } if (adapter->aq_required & IAVF_FLAG_AQ_REQUEST_STATS) { iavf_request_stats(adapter); return 0; @@ -2600,6 +2653,112 @@ err: } /** + * iavf_init_send_supported_rxdids - part of querying for supported RXDID + * formats + * @adapter: board private structure + * + * Function processes send of the request for supported RXDIDs to the PF. + * Must clear IAVF_EXTENDED_CAP_RECV_RXDID if the message is not sent, e.g. + * due to the PF not negotiating VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC. + */ +static void iavf_init_send_supported_rxdids(struct iavf_adapter *adapter) +{ + int ret; + + ret = iavf_send_vf_supported_rxdids_msg(adapter); + if (ret == -EOPNOTSUPP) { + /* PF does not support VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC. In this + * case, we did not send the capability exchange message and + * do not expect a response. + */ + adapter->extended_caps &= ~IAVF_EXTENDED_CAP_RECV_RXDID; + } + + /* We sent the message, so move on to the next step */ + adapter->extended_caps &= ~IAVF_EXTENDED_CAP_SEND_RXDID; +} + +/** + * iavf_init_recv_supported_rxdids - part of querying for supported RXDID + * formats + * @adapter: board private structure + * + * Function processes receipt of the supported RXDIDs message from the PF. + **/ +static void iavf_init_recv_supported_rxdids(struct iavf_adapter *adapter) +{ + int ret; + + memset(&adapter->supp_rxdids, 0, sizeof(adapter->supp_rxdids)); + + ret = iavf_get_vf_supported_rxdids(adapter); + if (ret) + goto err; + + /* We've processed the PF response to the + * VIRTCHNL_OP_GET_SUPPORTED_RXDIDS message we sent previously. + */ + adapter->extended_caps &= ~IAVF_EXTENDED_CAP_RECV_RXDID; + return; + +err: + /* We didn't receive a reply. Make sure we try sending again when + * __IAVF_INIT_FAILED attempts to recover. + */ + adapter->extended_caps |= IAVF_EXTENDED_CAP_SEND_RXDID; + iavf_change_state(adapter, __IAVF_INIT_FAILED); +} + +/** + * iavf_init_send_ptp_caps - part of querying for extended PTP capabilities + * @adapter: board private structure + * + * Function processes send of the request for 1588 PTP capabilities to the PF. + * Must clear IAVF_EXTENDED_CAP_SEND_PTP if the message is not sent, e.g. + * due to the PF not negotiating VIRTCHNL_VF_PTP_CAP + */ +static void iavf_init_send_ptp_caps(struct iavf_adapter *adapter) +{ + if (iavf_send_vf_ptp_caps_msg(adapter) == -EOPNOTSUPP) { + /* PF does not support VIRTCHNL_VF_PTP_CAP. In this case, we + * did not send the capability exchange message and do not + * expect a response. + */ + adapter->extended_caps &= ~IAVF_EXTENDED_CAP_RECV_PTP; + } + + /* We sent the message, so move on to the next step */ + adapter->extended_caps &= ~IAVF_EXTENDED_CAP_SEND_PTP; +} + +/** + * iavf_init_recv_ptp_caps - part of querying for supported PTP capabilities + * @adapter: board private structure + * + * Function processes receipt of the PTP capabilities supported on this VF. + **/ +static void iavf_init_recv_ptp_caps(struct iavf_adapter *adapter) +{ + memset(&adapter->ptp.hw_caps, 0, sizeof(adapter->ptp.hw_caps)); + + if (iavf_get_vf_ptp_caps(adapter)) + goto err; + + /* We've processed the PF response to the VIRTCHNL_OP_1588_PTP_GET_CAPS + * message we sent previously. + */ + adapter->extended_caps &= ~IAVF_EXTENDED_CAP_RECV_PTP; + return; + +err: + /* We didn't receive a reply. Make sure we try sending again when + * __IAVF_INIT_FAILED attempts to recover. + */ + adapter->extended_caps |= IAVF_EXTENDED_CAP_SEND_PTP; + iavf_change_state(adapter, __IAVF_INIT_FAILED); +} + +/** * iavf_init_process_extended_caps - Part of driver startup * @adapter: board private structure * @@ -2623,6 +2782,24 @@ static void iavf_init_process_extended_caps(struct iavf_adapter *adapter) return; } + /* Process capability exchange for RXDID formats */ + if (adapter->extended_caps & IAVF_EXTENDED_CAP_SEND_RXDID) { + iavf_init_send_supported_rxdids(adapter); + return; + } else if (adapter->extended_caps & IAVF_EXTENDED_CAP_RECV_RXDID) { + iavf_init_recv_supported_rxdids(adapter); + return; + } + + /* Process capability exchange for PTP features */ + if (adapter->extended_caps & IAVF_EXTENDED_CAP_SEND_PTP) { + iavf_init_send_ptp_caps(adapter); + return; + } else if (adapter->extended_caps & IAVF_EXTENDED_CAP_RECV_PTP) { + iavf_init_recv_ptp_caps(adapter); + return; + } + /* When we reach here, no further extended capabilities exchanges are * necessary, so we finally transition into __IAVF_INIT_CONFIG_ADAPTER */ @@ -2714,6 +2891,9 @@ static void iavf_init_config_adapter(struct iavf_adapter *adapter) if (QOS_ALLOWED(adapter)) adapter->aq_required |= IAVF_FLAG_AQ_GET_QOS_CAPS; + /* Setup initial PTP configuration */ + iavf_ptp_init(adapter); + iavf_schedule_finish_config(adapter); return; @@ -3139,15 +3319,18 @@ continue_reset: } adapter->aq_required |= IAVF_FLAG_AQ_GET_CONFIG; - /* always set since VIRTCHNL_OP_GET_VF_RESOURCES has not been - * sent/received yet, so VLAN_V2_ALLOWED() cannot is not reliable here, - * however the VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS won't be sent until - * VIRTCHNL_OP_GET_VF_RESOURCES and VIRTCHNL_VF_OFFLOAD_VLAN_V2 have - * been successfully sent and negotiated - */ - adapter->aq_required |= IAVF_FLAG_AQ_GET_OFFLOAD_VLAN_V2_CAPS; adapter->aq_required |= IAVF_FLAG_AQ_MAP_VECTORS; + /* Certain capabilities require an extended negotiation process using + * extra messages that must be processed after getting the VF + * configuration. The related checks such as VLAN_V2_ALLOWED() are not + * reliable here, since the configuration has not yet been negotiated. + * + * Always set these flags, since them related VIRTCHNL messages won't + * be sent until after VIRTCHNL_OP_GET_VF_RESOURCES. + */ + adapter->aq_required |= IAVF_FLAG_AQ_EXTENDED_CAPS; + spin_lock_bh(&adapter->mac_vlan_list_lock); /* Delete filter for the current MAC address, it could have @@ -4996,6 +5179,25 @@ static netdev_features_t iavf_fix_features(struct net_device *netdev, return iavf_fix_strip_features(adapter, features); } +static int iavf_hwstamp_get(struct net_device *netdev, + struct kernel_hwtstamp_config *config) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + + *config = adapter->ptp.hwtstamp_config; + + return 0; +} + +static int iavf_hwstamp_set(struct net_device *netdev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + + return iavf_ptp_set_ts_config(adapter, config, extack); +} + static int iavf_verify_shaper(struct net_shaper_binding *binding, const struct net_shaper *shaper, @@ -5104,6 +5306,8 @@ static const struct net_device_ops iavf_netdev_ops = { .ndo_set_features = iavf_set_features, .ndo_setup_tc = iavf_setup_tc, .net_shaper_ops = &iavf_shaper_ops, + .ndo_hwtstamp_get = iavf_hwstamp_get, + .ndo_hwtstamp_set = iavf_hwstamp_set, }; /** @@ -5358,6 +5562,10 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* Setup the wait queue for indicating virtchannel events */ init_waitqueue_head(&adapter->vc_waitqueue); + INIT_LIST_HEAD(&adapter->ptp.aq_cmds); + init_waitqueue_head(&adapter->ptp.phc_time_waitqueue); + mutex_init(&adapter->ptp.aq_cmd_lock); + queue_delayed_work(adapter->wq, &adapter->watchdog_task, msecs_to_jiffies(5 * (pdev->devfn & 0x07))); /* Initialization goes on in the work. Do not add more of it below. */ @@ -5514,6 +5722,8 @@ static void iavf_remove(struct pci_dev *pdev) msleep(50); } + iavf_ptp_release(adapter); + iavf_misc_irq_disable(adapter); /* Shut down all the garbage mashers on the detention level */ cancel_work_sync(&adapter->reset_task); diff --git a/drivers/net/ethernet/intel/iavf/iavf_ptp.c b/drivers/net/ethernet/intel/iavf/iavf_ptp.c new file mode 100644 index 000000000000..b4d5eda2e84f --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_ptp.c @@ -0,0 +1,485 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2024 Intel Corporation. */ + +#include "iavf.h" +#include "iavf_ptp.h" + +#define iavf_clock_to_adapter(info) \ + container_of_const(info, struct iavf_adapter, ptp.info) + +/** + * iavf_ptp_disable_rx_tstamp - Disable timestamping in Rx rings + * @adapter: private adapter structure + * + * Disable timestamp reporting for all Rx rings. + */ +static void iavf_ptp_disable_rx_tstamp(struct iavf_adapter *adapter) +{ + for (u32 i = 0; i < adapter->num_active_queues; i++) + adapter->rx_rings[i].flags &= ~IAVF_TXRX_FLAGS_HW_TSTAMP; +} + +/** + * iavf_ptp_enable_rx_tstamp - Enable timestamping in Rx rings + * @adapter: private adapter structure + * + * Enable timestamp reporting for all Rx rings. + */ +static void iavf_ptp_enable_rx_tstamp(struct iavf_adapter *adapter) +{ + for (u32 i = 0; i < adapter->num_active_queues; i++) + adapter->rx_rings[i].flags |= IAVF_TXRX_FLAGS_HW_TSTAMP; +} + +/** + * iavf_ptp_set_timestamp_mode - Set device timestamping mode + * @adapter: private adapter structure + * @config: pointer to kernel_hwtstamp_config + * + * Set the timestamping mode requested from the userspace. + * + * Note: this function always translates Rx timestamp requests for any packet + * category into HWTSTAMP_FILTER_ALL. + * + * Return: 0 on success, negative error code otherwise. + */ +static int iavf_ptp_set_timestamp_mode(struct iavf_adapter *adapter, + struct kernel_hwtstamp_config *config) +{ + /* Reserved for future extensions. */ + if (config->flags) + return -EINVAL; + + switch (config->tx_type) { + case HWTSTAMP_TX_OFF: + break; + case HWTSTAMP_TX_ON: + return -EOPNOTSUPP; + default: + return -ERANGE; + } + + if (config->rx_filter == HWTSTAMP_FILTER_NONE) { + iavf_ptp_disable_rx_tstamp(adapter); + return 0; + } else if (config->rx_filter > HWTSTAMP_FILTER_NTP_ALL) { + return -ERANGE; + } else if (!(iavf_ptp_cap_supported(adapter, + VIRTCHNL_1588_PTP_CAP_RX_TSTAMP))) { + return -EOPNOTSUPP; + } + + config->rx_filter = HWTSTAMP_FILTER_ALL; + iavf_ptp_enable_rx_tstamp(adapter); + + return 0; +} + +/** + * iavf_ptp_set_ts_config - Set timestamping configuration + * @adapter: private adapter structure + * @config: pointer to kernel_hwtstamp_config structure + * @extack: pointer to netlink_ext_ack structure + * + * Program the requested timestamping configuration to the device. + * + * Return: 0 on success, negative error code otherwise. + */ +int iavf_ptp_set_ts_config(struct iavf_adapter *adapter, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) +{ + int err; + + err = iavf_ptp_set_timestamp_mode(adapter, config); + if (err) + return err; + + /* Save successful settings for future reference */ + adapter->ptp.hwtstamp_config = *config; + + return 0; +} + +/** + * iavf_ptp_cap_supported - Check if a PTP capability is supported + * @adapter: private adapter structure + * @cap: the capability bitmask to check + * + * Return: true if every capability set in cap is also set in the enabled + * capabilities reported by the PF, false otherwise. + */ +bool iavf_ptp_cap_supported(const struct iavf_adapter *adapter, u32 cap) +{ + if (!IAVF_PTP_ALLOWED(adapter)) + return false; + + /* Only return true if every bit in cap is set in hw_caps.caps */ + return (adapter->ptp.hw_caps.caps & cap) == cap; +} + +/** + * iavf_allocate_ptp_cmd - Allocate a PTP command message structure + * @v_opcode: the virtchnl opcode + * @msglen: length in bytes of the associated virtchnl structure + * + * Allocates a PTP command message and pre-fills it with the provided message + * length and opcode. + * + * Return: allocated PTP command. + */ +static struct iavf_ptp_aq_cmd *iavf_allocate_ptp_cmd(enum virtchnl_ops v_opcode, + u16 msglen) +{ + struct iavf_ptp_aq_cmd *cmd; + + cmd = kzalloc(struct_size(cmd, msg, msglen), GFP_KERNEL); + if (!cmd) + return NULL; + + cmd->v_opcode = v_opcode; + cmd->msglen = msglen; + + return cmd; +} + +/** + * iavf_queue_ptp_cmd - Queue PTP command for sending over virtchnl + * @adapter: private adapter structure + * @cmd: the command structure to send + * + * Queue the given command structure into the PTP virtchnl command queue tos + * end to the PF. + */ +static void iavf_queue_ptp_cmd(struct iavf_adapter *adapter, + struct iavf_ptp_aq_cmd *cmd) +{ + mutex_lock(&adapter->ptp.aq_cmd_lock); + list_add_tail(&cmd->list, &adapter->ptp.aq_cmds); + mutex_unlock(&adapter->ptp.aq_cmd_lock); + + adapter->aq_required |= IAVF_FLAG_AQ_SEND_PTP_CMD; + mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0); +} + +/** + * iavf_send_phc_read - Send request to read PHC time + * @adapter: private adapter structure + * + * Send a request to obtain the PTP hardware clock time. This allocates the + * VIRTCHNL_OP_1588_PTP_GET_TIME message and queues it up to send to + * indirectly read the PHC time. + * + * This function does not wait for the reply from the PF. + * + * Return: 0 if success, error code otherwise. + */ +static int iavf_send_phc_read(struct iavf_adapter *adapter) +{ + struct iavf_ptp_aq_cmd *cmd; + + if (!adapter->ptp.clock) + return -EOPNOTSUPP; + + cmd = iavf_allocate_ptp_cmd(VIRTCHNL_OP_1588_PTP_GET_TIME, + sizeof(struct virtchnl_phc_time)); + if (!cmd) + return -ENOMEM; + + iavf_queue_ptp_cmd(adapter, cmd); + + return 0; +} + +/** + * iavf_read_phc_indirect - Indirectly read the PHC time via virtchnl + * @adapter: private adapter structure + * @ts: storage for the timestamp value + * @sts: system timestamp values before and after the read + * + * Used when the device does not have direct register access to the PHC time. + * Indirectly reads the time via the VIRTCHNL_OP_1588_PTP_GET_TIME, and waits + * for the reply from the PF. + * + * Based on some simple measurements using ftrace and phc2sys, this clock + * access method has about a ~110 usec latency even when the system is not + * under load. In order to achieve acceptable results when using phc2sys with + * the indirect clock access method, it is recommended to use more + * conservative proportional and integration constants with the P/I servo. + * + * Return: 0 if success, error code otherwise. + */ +static int iavf_read_phc_indirect(struct iavf_adapter *adapter, + struct timespec64 *ts, + struct ptp_system_timestamp *sts) +{ + long ret; + int err; + + adapter->ptp.phc_time_ready = false; + + ptp_read_system_prets(sts); + + err = iavf_send_phc_read(adapter); + if (err) + return err; + + ret = wait_event_interruptible_timeout(adapter->ptp.phc_time_waitqueue, + adapter->ptp.phc_time_ready, + HZ); + + ptp_read_system_postts(sts); + + if (ret < 0) + return ret; + else if (!ret) + return -EBUSY; + + *ts = ns_to_timespec64(adapter->ptp.cached_phc_time); + + return 0; +} + +static int iavf_ptp_gettimex64(struct ptp_clock_info *info, + struct timespec64 *ts, + struct ptp_system_timestamp *sts) +{ + struct iavf_adapter *adapter = iavf_clock_to_adapter(info); + + if (!adapter->ptp.clock) + return -EOPNOTSUPP; + + return iavf_read_phc_indirect(adapter, ts, sts); +} + +/** + * iavf_ptp_cache_phc_time - Cache PHC time for performing timestamp extension + * @adapter: private adapter structure + * + * Periodically cache the PHC time in order to allow for timestamp extension. + * This is required because the Tx and Rx timestamps only contain 32bits of + * nanoseconds. Timestamp extension allows calculating the corrected 64bit + * timestamp. This algorithm relies on the cached time being within ~1 second + * of the timestamp. + */ +static void iavf_ptp_cache_phc_time(struct iavf_adapter *adapter) +{ + if (!time_is_before_jiffies(adapter->ptp.cached_phc_updated + HZ)) + return; + + /* The response from virtchnl will store the time into + * cached_phc_time. + */ + iavf_send_phc_read(adapter); +} + +/** + * iavf_ptp_do_aux_work - Perform periodic work required for PTP support + * @info: PTP clock info structure + * + * Handler to take care of periodic work required for PTP operation. This + * includes the following tasks: + * + * 1) updating cached_phc_time + * + * cached_phc_time is used by the Tx and Rx timestamp flows in order to + * perform timestamp extension, by carefully comparing the timestamp + * 32bit nanosecond timestamps and determining the corrected 64bit + * timestamp value to report to userspace. This algorithm only works if + * the cached_phc_time is within ~1 second of the Tx or Rx timestamp + * event. This task periodically reads the PHC time and stores it, to + * ensure that timestamp extension operates correctly. + * + * Returns: time in jiffies until the periodic task should be re-scheduled. + */ +static long iavf_ptp_do_aux_work(struct ptp_clock_info *info) +{ + struct iavf_adapter *adapter = iavf_clock_to_adapter(info); + + iavf_ptp_cache_phc_time(adapter); + + /* Check work about twice a second */ + return msecs_to_jiffies(500); +} + +/** + * iavf_ptp_register_clock - Register a new PTP for userspace + * @adapter: private adapter structure + * + * Allocate and register a new PTP clock device if necessary. + * + * Return: 0 if success, error otherwise. + */ +static int iavf_ptp_register_clock(struct iavf_adapter *adapter) +{ + struct ptp_clock_info *ptp_info = &adapter->ptp.info; + struct device *dev = &adapter->pdev->dev; + struct ptp_clock *clock; + + snprintf(ptp_info->name, sizeof(ptp_info->name), "%s-%s-clk", + KBUILD_MODNAME, dev_name(dev)); + ptp_info->owner = THIS_MODULE; + ptp_info->gettimex64 = iavf_ptp_gettimex64; + ptp_info->do_aux_work = iavf_ptp_do_aux_work; + + clock = ptp_clock_register(ptp_info, dev); + if (IS_ERR(clock)) + return PTR_ERR(clock); + + adapter->ptp.clock = clock; + + dev_dbg(&adapter->pdev->dev, "PTP clock %s registered\n", + adapter->ptp.info.name); + + return 0; +} + +/** + * iavf_ptp_init - Initialize PTP support if capability was negotiated + * @adapter: private adapter structure + * + * Initialize PTP functionality, based on the capabilities that the PF has + * enabled for this VF. + */ +void iavf_ptp_init(struct iavf_adapter *adapter) +{ + int err; + + if (!iavf_ptp_cap_supported(adapter, VIRTCHNL_1588_PTP_CAP_READ_PHC)) { + pci_notice(adapter->pdev, + "Device does not have PTP clock support\n"); + return; + } + + err = iavf_ptp_register_clock(adapter); + if (err) { + pci_err(adapter->pdev, + "Failed to register PTP clock device (%p)\n", + ERR_PTR(err)); + return; + } + + for (int i = 0; i < adapter->num_active_queues; i++) { + struct iavf_ring *rx_ring = &adapter->rx_rings[i]; + + rx_ring->ptp = &adapter->ptp; + } + + ptp_schedule_worker(adapter->ptp.clock, 0); +} + +/** + * iavf_ptp_release - Disable PTP support + * @adapter: private adapter structure + * + * Release all PTP resources that were previously initialized. + */ +void iavf_ptp_release(struct iavf_adapter *adapter) +{ + struct iavf_ptp_aq_cmd *cmd, *tmp; + + if (!adapter->ptp.clock) + return; + + pci_dbg(adapter->pdev, "removing PTP clock %s\n", + adapter->ptp.info.name); + ptp_clock_unregister(adapter->ptp.clock); + adapter->ptp.clock = NULL; + + /* Cancel any remaining uncompleted PTP clock commands */ + mutex_lock(&adapter->ptp.aq_cmd_lock); + list_for_each_entry_safe(cmd, tmp, &adapter->ptp.aq_cmds, list) { + list_del(&cmd->list); + kfree(cmd); + } + adapter->aq_required &= ~IAVF_FLAG_AQ_SEND_PTP_CMD; + mutex_unlock(&adapter->ptp.aq_cmd_lock); + + adapter->ptp.hwtstamp_config.rx_filter = HWTSTAMP_FILTER_NONE; + iavf_ptp_disable_rx_tstamp(adapter); +} + +/** + * iavf_ptp_process_caps - Handle change in PTP capabilities + * @adapter: private adapter structure + * + * Handle any state changes necessary due to change in PTP capabilities, such + * as after a device reset or change in configuration from the PF. + */ +void iavf_ptp_process_caps(struct iavf_adapter *adapter) +{ + bool phc = iavf_ptp_cap_supported(adapter, VIRTCHNL_1588_PTP_CAP_READ_PHC); + + /* Check if the device gained or lost necessary access to support the + * PTP hardware clock. If so, driver must respond appropriately by + * creating or destroying the PTP clock device. + */ + if (adapter->ptp.clock && !phc) + iavf_ptp_release(adapter); + else if (!adapter->ptp.clock && phc) + iavf_ptp_init(adapter); + + /* Check if the device lost access to Rx timestamp incoming packets */ + if (!iavf_ptp_cap_supported(adapter, VIRTCHNL_1588_PTP_CAP_RX_TSTAMP)) { + adapter->ptp.hwtstamp_config.rx_filter = HWTSTAMP_FILTER_NONE; + iavf_ptp_disable_rx_tstamp(adapter); + } +} + +/** + * iavf_ptp_extend_32b_timestamp - Convert a 32b nanoseconds timestamp to 64b + * nanoseconds + * @cached_phc_time: recently cached copy of PHC time + * @in_tstamp: Ingress/egress 32b nanoseconds timestamp value + * + * Hardware captures timestamps which contain only 32 bits of nominal + * nanoseconds, as opposed to the 64bit timestamps that the stack expects. + * + * Extend the 32bit nanosecond timestamp using the following algorithm and + * assumptions: + * + * 1) have a recently cached copy of the PHC time + * 2) assume that the in_tstamp was captured 2^31 nanoseconds (~2.1 + * seconds) before or after the PHC time was captured. + * 3) calculate the delta between the cached time and the timestamp + * 4) if the delta is smaller than 2^31 nanoseconds, then the timestamp was + * captured after the PHC time. In this case, the full timestamp is just + * the cached PHC time plus the delta. + * 5) otherwise, if the delta is larger than 2^31 nanoseconds, then the + * timestamp was captured *before* the PHC time, i.e. because the PHC + * cache was updated after the timestamp was captured by hardware. In this + * case, the full timestamp is the cached time minus the inverse delta. + * + * This algorithm works even if the PHC time was updated after a Tx timestamp + * was requested, but before the Tx timestamp event was reported from + * hardware. + * + * This calculation primarily relies on keeping the cached PHC time up to + * date. If the timestamp was captured more than 2^31 nanoseconds after the + * PHC time, it is possible that the lower 32bits of PHC time have + * overflowed more than once, and we might generate an incorrect timestamp. + * + * This is prevented by (a) periodically updating the cached PHC time once + * a second, and (b) discarding any Tx timestamp packet if it has waited for + * a timestamp for more than one second. + * + * Return: extended timestamp (to 64b). + */ +u64 iavf_ptp_extend_32b_timestamp(u64 cached_phc_time, u32 in_tstamp) +{ + u32 low = lower_32_bits(cached_phc_time); + u32 delta = in_tstamp - low; + u64 ns; + + /* Do not assume that the in_tstamp is always more recent than the + * cached PHC time. If the delta is large, it indicates that the + * in_tstamp was taken in the past, and should be converted + * forward. + */ + if (delta > S32_MAX) + ns = cached_phc_time - (low - in_tstamp); + else + ns = cached_phc_time + delta; + + return ns; +} diff --git a/drivers/net/ethernet/intel/iavf/iavf_ptp.h b/drivers/net/ethernet/intel/iavf/iavf_ptp.h new file mode 100644 index 000000000000..783b8f287cd9 --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_ptp.h @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2024 Intel Corporation. */ + +#ifndef _IAVF_PTP_H_ +#define _IAVF_PTP_H_ + +#include "iavf_types.h" + +/* bit indicating whether a 40bit timestamp is valid */ +#define IAVF_PTP_40B_TSTAMP_VALID BIT(24) + +#if IS_ENABLED(CONFIG_PTP_1588_CLOCK) +void iavf_ptp_init(struct iavf_adapter *adapter); +void iavf_ptp_release(struct iavf_adapter *adapter); +void iavf_ptp_process_caps(struct iavf_adapter *adapter); +bool iavf_ptp_cap_supported(const struct iavf_adapter *adapter, u32 cap); +void iavf_virtchnl_send_ptp_cmd(struct iavf_adapter *adapter); +int iavf_ptp_set_ts_config(struct iavf_adapter *adapter, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack); +u64 iavf_ptp_extend_32b_timestamp(u64 cached_phc_time, u32 in_tstamp); +#else /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */ +static inline void iavf_ptp_init(struct iavf_adapter *adapter) { } +static inline void iavf_ptp_release(struct iavf_adapter *adapter) { } +static inline void iavf_ptp_process_caps(struct iavf_adapter *adapter) { } +static inline bool iavf_ptp_cap_supported(const struct iavf_adapter *adapter, + u32 cap) +{ + return false; +} + +static inline void iavf_virtchnl_send_ptp_cmd(struct iavf_adapter *adapter) { } +static inline int iavf_ptp_set_ts_config(struct iavf_adapter *adapter, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) +{ + return -1; +} + +static inline u64 iavf_ptp_extend_32b_timestamp(u64 cached_phc_time, + u32 in_tstamp) +{ + return 0; +} + +#endif /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */ +#endif /* _IAVF_PTP_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_trace.h b/drivers/net/ethernet/intel/iavf/iavf_trace.h index 62212011c807..c5e4d1823886 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_trace.h +++ b/drivers/net/ethernet/intel/iavf/iavf_trace.h @@ -112,7 +112,7 @@ DECLARE_EVENT_CLASS( iavf_rx_template, TP_PROTO(struct iavf_ring *ring, - union iavf_32byte_rx_desc *desc, + struct iavf_rx_desc *desc, struct sk_buff *skb), TP_ARGS(ring, desc, skb), @@ -140,7 +140,7 @@ DECLARE_EVENT_CLASS( DEFINE_EVENT( iavf_rx_template, iavf_clean_rx_irq, TP_PROTO(struct iavf_ring *ring, - union iavf_32byte_rx_desc *desc, + struct iavf_rx_desc *desc, struct sk_buff *skb), TP_ARGS(ring, desc, skb)); @@ -148,7 +148,7 @@ DEFINE_EVENT( DEFINE_EVENT( iavf_rx_template, iavf_clean_rx_irq_rx, TP_PROTO(struct iavf_ring *ring, - union iavf_32byte_rx_desc *desc, + struct iavf_rx_desc *desc, struct sk_buff *skb), TP_ARGS(ring, desc, skb)); diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c index 26b424fd6718..422312b8b54a 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c +++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c @@ -8,6 +8,26 @@ #include "iavf.h" #include "iavf_trace.h" #include "iavf_prototype.h" +#include "iavf_ptp.h" + +/** + * iavf_is_descriptor_done - tests DD bit in Rx descriptor + * @qw1: quad word 1 from descriptor to get Descriptor Done field from + * @flex: is the descriptor flex or legacy + * + * This function tests the descriptor done bit in specified descriptor. Because + * there are two types of descriptors (legacy and flex) the parameter rx_ring + * is used to distinguish. + * + * Return: true or false based on the state of DD bit in Rx descriptor. + */ +static bool iavf_is_descriptor_done(u64 qw1, bool flex) +{ + if (flex) + return FIELD_GET(IAVF_RXD_FLEX_DD_M, qw1); + else + return FIELD_GET(IAVF_RXD_LEGACY_DD_M, qw1); +} static __le64 build_ctob(u32 td_cmd, u32 td_offset, unsigned int size, u32 td_tag) @@ -766,7 +786,7 @@ int iavf_setup_rx_descriptors(struct iavf_ring *rx_ring) u64_stats_init(&rx_ring->syncp); /* Round up to nearest 4K */ - rx_ring->size = rx_ring->count * sizeof(union iavf_32byte_rx_desc); + rx_ring->size = rx_ring->count * sizeof(struct iavf_rx_desc); rx_ring->size = ALIGN(rx_ring->size, 4096); rx_ring->desc = dma_alloc_coherent(fq.pp->p.dev, rx_ring->size, &rx_ring->dma, GFP_KERNEL); @@ -845,7 +865,7 @@ bool iavf_alloc_rx_buffers(struct iavf_ring *rx_ring, u16 cleaned_count) .count = rx_ring->count, }; u16 ntu = rx_ring->next_to_use; - union iavf_rx_desc *rx_desc; + struct iavf_rx_desc *rx_desc; /* do nothing if no valid netdev defined */ if (!rx_ring->netdev || !cleaned_count) @@ -863,7 +883,7 @@ bool iavf_alloc_rx_buffers(struct iavf_ring *rx_ring, u16 cleaned_count) /* Refresh the desc even if buffer_addrs didn't change * because each write-back erases this info. */ - rx_desc->read.pkt_addr = cpu_to_le64(addr); + rx_desc->qw0 = cpu_to_le64(addr); rx_desc++; ntu++; @@ -873,7 +893,7 @@ bool iavf_alloc_rx_buffers(struct iavf_ring *rx_ring, u16 cleaned_count) } /* clear the status bits for the next_to_use descriptor */ - rx_desc->wb.qword1.status_error_len = 0; + rx_desc->qw1 = 0; cleaned_count--; } while (cleaned_count); @@ -896,60 +916,43 @@ no_buffers: } /** - * iavf_rx_checksum - Indicate in skb if hw indicated a good cksum + * iavf_rx_csum - Indicate in skb if hw indicated a good checksum * @vsi: the VSI we care about * @skb: skb currently being received and modified - * @rx_desc: the receive descriptor + * @decoded_pt: decoded ptype information + * @csum_bits: decoded Rx descriptor information **/ -static void iavf_rx_checksum(struct iavf_vsi *vsi, - struct sk_buff *skb, - union iavf_rx_desc *rx_desc) +static void iavf_rx_csum(const struct iavf_vsi *vsi, struct sk_buff *skb, + struct libeth_rx_pt decoded_pt, + struct libeth_rx_csum csum_bits) { - struct libeth_rx_pt decoded; - u32 rx_error, rx_status; bool ipv4, ipv6; - u8 ptype; - u64 qword; skb->ip_summed = CHECKSUM_NONE; - qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); - ptype = FIELD_GET(IAVF_RXD_QW1_PTYPE_MASK, qword); - - decoded = libie_rx_pt_parse(ptype); - if (!libeth_rx_pt_has_checksum(vsi->netdev, decoded)) - return; - - rx_error = FIELD_GET(IAVF_RXD_QW1_ERROR_MASK, qword); - rx_status = FIELD_GET(IAVF_RXD_QW1_STATUS_MASK, qword); - /* did the hardware decode the packet and checksum? */ - if (!(rx_status & BIT(IAVF_RX_DESC_STATUS_L3L4P_SHIFT))) + if (unlikely(!csum_bits.l3l4p)) return; - ipv4 = libeth_rx_pt_get_ip_ver(decoded) == LIBETH_RX_PT_OUTER_IPV4; - ipv6 = libeth_rx_pt_get_ip_ver(decoded) == LIBETH_RX_PT_OUTER_IPV6; + ipv4 = libeth_rx_pt_get_ip_ver(decoded_pt) == LIBETH_RX_PT_OUTER_IPV4; + ipv6 = libeth_rx_pt_get_ip_ver(decoded_pt) == LIBETH_RX_PT_OUTER_IPV6; - if (ipv4 && - (rx_error & (BIT(IAVF_RX_DESC_ERROR_IPE_SHIFT) | - BIT(IAVF_RX_DESC_ERROR_EIPE_SHIFT)))) + if (unlikely(ipv4 && (csum_bits.ipe || csum_bits.eipe))) goto checksum_fail; /* likely incorrect csum if alternate IP extension headers found */ - if (ipv6 && - rx_status & BIT(IAVF_RX_DESC_STATUS_IPV6EXADD_SHIFT)) - /* don't increment checksum err here, non-fatal err */ + if (unlikely(ipv6 && csum_bits.ipv6exadd)) return; /* there was some L4 error, count error and punt packet to the stack */ - if (rx_error & BIT(IAVF_RX_DESC_ERROR_L4E_SHIFT)) + if (unlikely(csum_bits.l4e)) goto checksum_fail; /* handle packets that were not able to be checksummed due * to arrival speed, in this case the stack can compute * the csum. */ - if (rx_error & BIT(IAVF_RX_DESC_ERROR_PPRS_SHIFT)) + if (unlikely(csum_bits.pprs)) return; skb->ip_summed = CHECKSUM_UNNECESSARY; @@ -960,52 +963,196 @@ checksum_fail: } /** - * iavf_rx_hash - set the hash value in the skb + * iavf_legacy_rx_csum - Indicate in skb if hw indicated a good checksum + * @vsi: the VSI we care about + * @qw1: quad word 1 + * @decoded_pt: decoded packet type + * + * This function only operates on the VIRTCHNL_RXDID_1_32B_BASE legacy 32byte + * descriptor writeback format. + * + * Return: decoded checksum bits. + **/ +static struct libeth_rx_csum +iavf_legacy_rx_csum(const struct iavf_vsi *vsi, u64 qw1, + const struct libeth_rx_pt decoded_pt) +{ + struct libeth_rx_csum csum_bits = {}; + + if (!libeth_rx_pt_has_checksum(vsi->netdev, decoded_pt)) + return csum_bits; + + csum_bits.ipe = FIELD_GET(IAVF_RXD_LEGACY_IPE_M, qw1); + csum_bits.eipe = FIELD_GET(IAVF_RXD_LEGACY_EIPE_M, qw1); + csum_bits.l4e = FIELD_GET(IAVF_RXD_LEGACY_L4E_M, qw1); + csum_bits.pprs = FIELD_GET(IAVF_RXD_LEGACY_PPRS_M, qw1); + csum_bits.l3l4p = FIELD_GET(IAVF_RXD_LEGACY_L3L4P_M, qw1); + csum_bits.ipv6exadd = FIELD_GET(IAVF_RXD_LEGACY_IPV6EXADD_M, qw1); + + return csum_bits; +} + +/** + * iavf_flex_rx_csum - Indicate in skb if hw indicated a good checksum + * @vsi: the VSI we care about + * @qw1: quad word 1 + * @decoded_pt: decoded packet type + * + * This function only operates on the VIRTCHNL_RXDID_2_FLEX_SQ_NIC flexible + * descriptor writeback format. + * + * Return: decoded checksum bits. + **/ +static struct libeth_rx_csum +iavf_flex_rx_csum(const struct iavf_vsi *vsi, u64 qw1, + const struct libeth_rx_pt decoded_pt) +{ + struct libeth_rx_csum csum_bits = {}; + + if (!libeth_rx_pt_has_checksum(vsi->netdev, decoded_pt)) + return csum_bits; + + csum_bits.ipe = FIELD_GET(IAVF_RXD_FLEX_XSUM_IPE_M, qw1); + csum_bits.eipe = FIELD_GET(IAVF_RXD_FLEX_XSUM_EIPE_M, qw1); + csum_bits.l4e = FIELD_GET(IAVF_RXD_FLEX_XSUM_L4E_M, qw1); + csum_bits.eudpe = FIELD_GET(IAVF_RXD_FLEX_XSUM_EUDPE_M, qw1); + csum_bits.l3l4p = FIELD_GET(IAVF_RXD_FLEX_L3L4P_M, qw1); + csum_bits.ipv6exadd = FIELD_GET(IAVF_RXD_FLEX_IPV6EXADD_M, qw1); + csum_bits.nat = FIELD_GET(IAVF_RXD_FLEX_NAT_M, qw1); + + return csum_bits; +} + +/** + * iavf_legacy_rx_hash - set the hash value in the skb + * @ring: descriptor ring + * @qw0: quad word 0 + * @qw1: quad word 1 + * @skb: skb currently being received and modified + * @decoded_pt: decoded packet type + * + * This function only operates on the VIRTCHNL_RXDID_1_32B_BASE legacy 32byte + * descriptor writeback format. + **/ +static void iavf_legacy_rx_hash(const struct iavf_ring *ring, __le64 qw0, + __le64 qw1, struct sk_buff *skb, + const struct libeth_rx_pt decoded_pt) +{ + const __le64 rss_mask = cpu_to_le64(IAVF_RXD_LEGACY_FLTSTAT_M); + u32 hash; + + if (!libeth_rx_pt_has_hash(ring->netdev, decoded_pt)) + return; + + if ((qw1 & rss_mask) == rss_mask) { + hash = le64_get_bits(qw0, IAVF_RXD_LEGACY_RSS_M); + libeth_rx_pt_set_hash(skb, hash, decoded_pt); + } +} + +/** + * iavf_flex_rx_hash - set the hash value in the skb * @ring: descriptor ring - * @rx_desc: specific descriptor + * @qw1: quad word 1 * @skb: skb currently being received and modified - * @rx_ptype: Rx packet type + * @decoded_pt: decoded packet type + * + * This function only operates on the VIRTCHNL_RXDID_2_FLEX_SQ_NIC flexible + * descriptor writeback format. **/ -static void iavf_rx_hash(struct iavf_ring *ring, - union iavf_rx_desc *rx_desc, - struct sk_buff *skb, - u8 rx_ptype) +static void iavf_flex_rx_hash(const struct iavf_ring *ring, __le64 qw1, + struct sk_buff *skb, + const struct libeth_rx_pt decoded_pt) { - struct libeth_rx_pt decoded; + bool rss_valid; u32 hash; - const __le64 rss_mask = - cpu_to_le64((u64)IAVF_RX_DESC_FLTSTAT_RSS_HASH << - IAVF_RX_DESC_STATUS_FLTSTAT_SHIFT); - decoded = libie_rx_pt_parse(rx_ptype); - if (!libeth_rx_pt_has_hash(ring->netdev, decoded)) + if (!libeth_rx_pt_has_hash(ring->netdev, decoded_pt)) return; - if ((rx_desc->wb.qword1.status_error_len & rss_mask) == rss_mask) { - hash = le32_to_cpu(rx_desc->wb.qword0.hi_dword.rss); - libeth_rx_pt_set_hash(skb, hash, decoded); + rss_valid = le64_get_bits(qw1, IAVF_RXD_FLEX_RSS_VALID_M); + if (rss_valid) { + hash = le64_get_bits(qw1, IAVF_RXD_FLEX_RSS_HASH_M); + libeth_rx_pt_set_hash(skb, hash, decoded_pt); } } /** + * iavf_flex_rx_tstamp - Capture Rx timestamp from the descriptor + * @rx_ring: descriptor ring + * @qw2: quad word 2 of descriptor + * @qw3: quad word 3 of descriptor + * @skb: skb currently being received + * + * Read the Rx timestamp value from the descriptor and pass it to the stack. + * + * This function only operates on the VIRTCHNL_RXDID_2_FLEX_SQ_NIC flexible + * descriptor writeback format. + */ +static void iavf_flex_rx_tstamp(const struct iavf_ring *rx_ring, __le64 qw2, + __le64 qw3, struct sk_buff *skb) +{ + u32 tstamp; + u64 ns; + + /* Skip processing if timestamps aren't enabled */ + if (!(rx_ring->flags & IAVF_TXRX_FLAGS_HW_TSTAMP)) + return; + + /* Check if this Rx descriptor has a valid timestamp */ + if (!le64_get_bits(qw2, IAVF_PTP_40B_TSTAMP_VALID)) + return; + + /* the ts_low field only contains the valid bit and sub-nanosecond + * precision, so we don't need to extract it. + */ + tstamp = le64_get_bits(qw3, IAVF_RXD_FLEX_QW3_TSTAMP_HIGH_M); + + ns = iavf_ptp_extend_32b_timestamp(rx_ring->ptp->cached_phc_time, + tstamp); + + *skb_hwtstamps(skb) = (struct skb_shared_hwtstamps) { + .hwtstamp = ns_to_ktime(ns), + }; +} + +/** * iavf_process_skb_fields - Populate skb header fields from Rx descriptor * @rx_ring: rx descriptor ring packet is being transacted on * @rx_desc: pointer to the EOP Rx descriptor * @skb: pointer to current skb being populated - * @rx_ptype: the packet type decoded by hardware + * @ptype: the packet type decoded by hardware + * @flex: is the descriptor flex or legacy * * This function checks the ring, descriptor, and packet information in * order to populate the hash, checksum, VLAN, protocol, and * other fields within the skb. **/ -static void -iavf_process_skb_fields(struct iavf_ring *rx_ring, - union iavf_rx_desc *rx_desc, struct sk_buff *skb, - u8 rx_ptype) +static void iavf_process_skb_fields(const struct iavf_ring *rx_ring, + const struct iavf_rx_desc *rx_desc, + struct sk_buff *skb, u32 ptype, + bool flex) { - iavf_rx_hash(rx_ring, rx_desc, skb, rx_ptype); - - iavf_rx_checksum(rx_ring->vsi, skb, rx_desc); + struct libeth_rx_csum csum_bits; + struct libeth_rx_pt decoded_pt; + __le64 qw0 = rx_desc->qw0; + __le64 qw1 = rx_desc->qw1; + __le64 qw2 = rx_desc->qw2; + __le64 qw3 = rx_desc->qw3; + + decoded_pt = libie_rx_pt_parse(ptype); + + if (flex) { + iavf_flex_rx_hash(rx_ring, qw1, skb, decoded_pt); + iavf_flex_rx_tstamp(rx_ring, qw2, qw3, skb); + csum_bits = iavf_flex_rx_csum(rx_ring->vsi, le64_to_cpu(qw1), + decoded_pt); + } else { + iavf_legacy_rx_hash(rx_ring, qw0, qw1, skb, decoded_pt); + csum_bits = iavf_legacy_rx_csum(rx_ring->vsi, le64_to_cpu(qw1), + decoded_pt); + } + iavf_rx_csum(rx_ring->vsi, skb, decoded_pt, csum_bits); skb_record_rx_queue(skb, rx_ring->queue_index); @@ -1092,8 +1239,7 @@ static struct sk_buff *iavf_build_skb(const struct libeth_fqe *rx_buffer, /** * iavf_is_non_eop - process handling of non-EOP buffers * @rx_ring: Rx ring being processed - * @rx_desc: Rx descriptor for current buffer - * @skb: Current socket buffer containing buffer in progress + * @fields: Rx descriptor extracted fields * * This function updates next to clean. If the buffer is an EOP buffer * this function exits returning false, otherwise it will place the @@ -1101,8 +1247,7 @@ static struct sk_buff *iavf_build_skb(const struct libeth_fqe *rx_buffer, * that this is in fact a non-EOP buffer. **/ static bool iavf_is_non_eop(struct iavf_ring *rx_ring, - union iavf_rx_desc *rx_desc, - struct sk_buff *skb) + struct libeth_rqe_info fields) { u32 ntc = rx_ring->next_to_clean + 1; @@ -1113,8 +1258,7 @@ static bool iavf_is_non_eop(struct iavf_ring *rx_ring, prefetch(IAVF_RX_DESC(rx_ring, ntc)); /* if we are the last buffer then there is nothing else to do */ -#define IAVF_RXD_EOF BIT(IAVF_RX_DESC_STATUS_EOF_SHIFT) - if (likely(iavf_test_staterr(rx_desc, IAVF_RXD_EOF))) + if (likely(fields.eop)) return false; rx_ring->rx_stats.non_eop_descs++; @@ -1123,6 +1267,109 @@ static bool iavf_is_non_eop(struct iavf_ring *rx_ring, } /** + * iavf_extract_legacy_rx_fields - Extract fields from the Rx descriptor + * @rx_ring: rx descriptor ring + * @rx_desc: the descriptor to process + * + * Decode the Rx descriptor and extract relevant information including the + * size, VLAN tag, Rx packet type, end of packet field and RXE field value. + * + * This function only operates on the VIRTCHNL_RXDID_1_32B_BASE legacy 32byte + * descriptor writeback format. + * + * Return: fields extracted from the Rx descriptor. + */ +static struct libeth_rqe_info +iavf_extract_legacy_rx_fields(const struct iavf_ring *rx_ring, + const struct iavf_rx_desc *rx_desc) +{ + u64 qw0 = le64_to_cpu(rx_desc->qw0); + u64 qw1 = le64_to_cpu(rx_desc->qw1); + u64 qw2 = le64_to_cpu(rx_desc->qw2); + struct libeth_rqe_info fields; + bool l2tag1p, l2tag2p; + + fields.eop = FIELD_GET(IAVF_RXD_LEGACY_EOP_M, qw1); + fields.len = FIELD_GET(IAVF_RXD_LEGACY_LENGTH_M, qw1); + + if (!fields.eop) + return fields; + + fields.rxe = FIELD_GET(IAVF_RXD_LEGACY_RXE_M, qw1); + fields.ptype = FIELD_GET(IAVF_RXD_LEGACY_PTYPE_M, qw1); + fields.vlan = 0; + + if (rx_ring->flags & IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1) { + l2tag1p = FIELD_GET(IAVF_RXD_LEGACY_L2TAG1P_M, qw1); + if (l2tag1p) + fields.vlan = FIELD_GET(IAVF_RXD_LEGACY_L2TAG1_M, qw0); + } else if (rx_ring->flags & IAVF_RXR_FLAGS_VLAN_TAG_LOC_L2TAG2_2) { + l2tag2p = FIELD_GET(IAVF_RXD_LEGACY_L2TAG2P_M, qw2); + if (l2tag2p) + fields.vlan = FIELD_GET(IAVF_RXD_LEGACY_L2TAG2_M, qw2); + } + + return fields; +} + +/** + * iavf_extract_flex_rx_fields - Extract fields from the Rx descriptor + * @rx_ring: rx descriptor ring + * @rx_desc: the descriptor to process + * + * Decode the Rx descriptor and extract relevant information including the + * size, VLAN tag, Rx packet type, end of packet field and RXE field value. + * + * This function only operates on the VIRTCHNL_RXDID_2_FLEX_SQ_NIC flexible + * descriptor writeback format. + * + * Return: fields extracted from the Rx descriptor. + */ +static struct libeth_rqe_info +iavf_extract_flex_rx_fields(const struct iavf_ring *rx_ring, + const struct iavf_rx_desc *rx_desc) +{ + struct libeth_rqe_info fields = {}; + u64 qw0 = le64_to_cpu(rx_desc->qw0); + u64 qw1 = le64_to_cpu(rx_desc->qw1); + u64 qw2 = le64_to_cpu(rx_desc->qw2); + bool l2tag1p, l2tag2p; + + fields.eop = FIELD_GET(IAVF_RXD_FLEX_EOP_M, qw1); + fields.len = FIELD_GET(IAVF_RXD_FLEX_PKT_LEN_M, qw0); + + if (!fields.eop) + return fields; + + fields.rxe = FIELD_GET(IAVF_RXD_FLEX_RXE_M, qw1); + fields.ptype = FIELD_GET(IAVF_RXD_FLEX_PTYPE_M, qw0); + fields.vlan = 0; + + if (rx_ring->flags & IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1) { + l2tag1p = FIELD_GET(IAVF_RXD_FLEX_L2TAG1P_M, qw1); + if (l2tag1p) + fields.vlan = FIELD_GET(IAVF_RXD_FLEX_L2TAG1_M, qw1); + } else if (rx_ring->flags & IAVF_RXR_FLAGS_VLAN_TAG_LOC_L2TAG2_2) { + l2tag2p = FIELD_GET(IAVF_RXD_FLEX_L2TAG2P_M, qw2); + if (l2tag2p) + fields.vlan = FIELD_GET(IAVF_RXD_FLEX_L2TAG2_2_M, qw2); + } + + return fields; +} + +static struct libeth_rqe_info +iavf_extract_rx_fields(const struct iavf_ring *rx_ring, + const struct iavf_rx_desc *rx_desc, + bool flex) +{ + if (flex) + return iavf_extract_flex_rx_fields(rx_ring, rx_desc); + else + return iavf_extract_legacy_rx_fields(rx_ring, rx_desc); +} + +/** * iavf_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf * @rx_ring: rx descriptor ring to transact packets on * @budget: Total limit on number of packets to process @@ -1136,18 +1383,17 @@ static bool iavf_is_non_eop(struct iavf_ring *rx_ring, **/ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget) { + bool flex = rx_ring->rxdid == VIRTCHNL_RXDID_2_FLEX_SQ_NIC; unsigned int total_rx_bytes = 0, total_rx_packets = 0; struct sk_buff *skb = rx_ring->skb; u16 cleaned_count = IAVF_DESC_UNUSED(rx_ring); bool failure = false; while (likely(total_rx_packets < (unsigned int)budget)) { + struct libeth_rqe_info fields; struct libeth_fqe *rx_buffer; - union iavf_rx_desc *rx_desc; - unsigned int size; - u16 vlan_tag = 0; - u8 rx_ptype; - u64 qword; + struct iavf_rx_desc *rx_desc; + u64 qw1; /* return some buffers to hardware, one at a time is too slow */ if (cleaned_count >= IAVF_RX_BUFFER_WRITE) { @@ -1158,35 +1404,32 @@ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget) rx_desc = IAVF_RX_DESC(rx_ring, rx_ring->next_to_clean); - /* status_error_len will always be zero for unused descriptors - * because it's cleared in cleanup, and overlaps with hdr_addr - * which is always zero because packet split isn't used, if the - * hardware wrote DD then the length will be non-zero - */ - qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); - /* This memory barrier is needed to keep us from reading * any other fields out of the rx_desc until we have * verified the descriptor has been written back. */ dma_rmb(); -#define IAVF_RXD_DD BIT(IAVF_RX_DESC_STATUS_DD_SHIFT) - if (!iavf_test_staterr(rx_desc, IAVF_RXD_DD)) + + qw1 = le64_to_cpu(rx_desc->qw1); + /* If DD field (descriptor done) is unset then other fields are + * not valid + */ + if (!iavf_is_descriptor_done(qw1, flex)) break; - size = FIELD_GET(IAVF_RXD_QW1_LENGTH_PBUF_MASK, qword); + fields = iavf_extract_rx_fields(rx_ring, rx_desc, flex); iavf_trace(clean_rx_irq, rx_ring, rx_desc, skb); rx_buffer = &rx_ring->rx_fqes[rx_ring->next_to_clean]; - if (!libeth_rx_sync_for_cpu(rx_buffer, size)) + if (!libeth_rx_sync_for_cpu(rx_buffer, fields.len)) goto skip_data; /* retrieve a buffer from the ring */ if (skb) - iavf_add_rx_frag(skb, rx_buffer, size); + iavf_add_rx_frag(skb, rx_buffer, fields.len); else - skb = iavf_build_skb(rx_buffer, size); + skb = iavf_build_skb(rx_buffer, fields.len); /* exit if we failed to retrieve a buffer */ if (!skb) { @@ -1197,15 +1440,14 @@ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget) skip_data: cleaned_count++; - if (iavf_is_non_eop(rx_ring, rx_desc, skb) || unlikely(!skb)) + if (iavf_is_non_eop(rx_ring, fields) || unlikely(!skb)) continue; - /* ERR_MASK will only have valid bits if EOP set, and - * what we are doing here is actually checking - * IAVF_RX_DESC_ERROR_RXE_SHIFT, since it is the zeroth bit in - * the error field + /* RXE field in descriptor is an indication of the MAC errors + * (like CRC, alignment, oversize etc). If it is set then iavf + * should finish. */ - if (unlikely(iavf_test_staterr(rx_desc, BIT(IAVF_RXD_QW1_ERROR_SHIFT)))) { + if (unlikely(fields.rxe)) { dev_kfree_skb_any(skb); skb = NULL; continue; @@ -1219,22 +1461,11 @@ skip_data: /* probably a little skewed due to removing CRC */ total_rx_bytes += skb->len; - qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); - rx_ptype = FIELD_GET(IAVF_RXD_QW1_PTYPE_MASK, qword); - /* populate checksum, VLAN, and protocol */ - iavf_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype); - - if (qword & BIT(IAVF_RX_DESC_STATUS_L2TAG1P_SHIFT) && - rx_ring->flags & IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1) - vlan_tag = le16_to_cpu(rx_desc->wb.qword0.lo_dword.l2tag1); - if (rx_desc->wb.qword2.ext_status & - cpu_to_le16(BIT(IAVF_RX_DESC_EXT_STATUS_L2TAG2P_SHIFT)) && - rx_ring->flags & IAVF_RXR_FLAGS_VLAN_TAG_LOC_L2TAG2_2) - vlan_tag = le16_to_cpu(rx_desc->wb.qword2.l2tag2_2); + iavf_process_skb_fields(rx_ring, rx_desc, skb, fields.ptype, flex); iavf_trace(clean_rx_irq_rx, rx_ring, rx_desc, skb); - iavf_receive_skb(rx_ring, skb, vlan_tag); + iavf_receive_skb(rx_ring, skb, fields.vlan); skb = NULL; /* update budget accounting */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.h b/drivers/net/ethernet/intel/iavf/iavf_txrx.h index f97c702c0802..79ad554f2d53 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_txrx.h +++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.h @@ -80,25 +80,6 @@ enum iavf_dyn_idx_t { BIT_ULL(IAVF_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | \ BIT_ULL(IAVF_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP)) -#define iavf_rx_desc iavf_32byte_rx_desc - -/** - * iavf_test_staterr - tests bits in Rx descriptor status and error fields - * @rx_desc: pointer to receive descriptor (in le64 format) - * @stat_err_bits: value to mask - * - * This function does some fast chicanery in order to return the - * value of the mask which is really only used for boolean tests. - * The status_error_len doesn't need to be shifted because it begins - * at offset zero. - */ -static inline bool iavf_test_staterr(union iavf_rx_desc *rx_desc, - const u64 stat_err_bits) -{ - return !!(rx_desc->wb.qword1.status_error_len & - cpu_to_le64(stat_err_bits)); -} - /* How many Rx Buffers do we bundle into one write to the hardware ? */ #define IAVF_RX_INCREMENT(r, i) \ do { \ @@ -262,6 +243,8 @@ struct iavf_ring { u16 next_to_use; u16 next_to_clean; + u16 rxdid; /* Rx descriptor format */ + u16 flags; #define IAVF_TXR_FLAGS_WB_ON_ITR BIT(0) #define IAVF_TXR_FLAGS_ARM_WB BIT(1) @@ -269,6 +252,7 @@ struct iavf_ring { #define IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1 BIT(3) #define IAVF_TXR_FLAGS_VLAN_TAG_LOC_L2TAG2 BIT(4) #define IAVF_RXR_FLAGS_VLAN_TAG_LOC_L2TAG2_2 BIT(5) +#define IAVF_TXRX_FLAGS_HW_TSTAMP BIT(6) /* stats structs */ struct iavf_queue_stats stats; @@ -295,6 +279,8 @@ struct iavf_ring { * for this ring. */ + struct iavf_ptp *ptp; + u32 rx_buf_len; struct net_shaper q_shaper; bool q_shaper_update; diff --git a/drivers/net/ethernet/intel/iavf/iavf_type.h b/drivers/net/ethernet/intel/iavf/iavf_type.h index f6b09e57abce..f9e1319620f4 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_type.h +++ b/drivers/net/ethernet/intel/iavf/iavf_type.h @@ -178,110 +178,116 @@ struct iavf_hw { char err_str[16]; }; -/* RX Descriptors */ -union iavf_16byte_rx_desc { - struct { - __le64 pkt_addr; /* Packet buffer address */ - __le64 hdr_addr; /* Header buffer address */ - } read; - struct { - struct { - struct { - union { - __le16 mirroring_status; - __le16 fcoe_ctx_id; - } mirr_fcoe; - __le16 l2tag1; - } lo_dword; - union { - __le32 rss; /* RSS Hash */ - __le32 fd_id; /* Flow director filter id */ - __le32 fcoe_param; /* FCoE DDP Context id */ - } hi_dword; - } qword0; - struct { - /* ext status/error/pktype/length */ - __le64 status_error_len; - } qword1; - } wb; /* writeback */ -}; - -union iavf_32byte_rx_desc { - struct { - __le64 pkt_addr; /* Packet buffer address */ - __le64 hdr_addr; /* Header buffer address */ - /* bit 0 of hdr_buffer_addr is DD bit */ - __le64 rsvd1; - __le64 rsvd2; - } read; - struct { - struct { - struct { - union { - __le16 mirroring_status; - __le16 fcoe_ctx_id; - } mirr_fcoe; - __le16 l2tag1; - } lo_dword; - union { - __le32 rss; /* RSS Hash */ - __le32 fcoe_param; /* FCoE DDP Context id */ - /* Flow director filter id in case of - * Programming status desc WB - */ - __le32 fd_id; - } hi_dword; - } qword0; - struct { - /* status/error/pktype/length */ - __le64 status_error_len; - } qword1; - struct { - __le16 ext_status; /* extended status */ - __le16 rsvd; - __le16 l2tag2_1; - __le16 l2tag2_2; - } qword2; - struct { - union { - __le32 flex_bytes_lo; - __le32 pe_status; - } lo_dword; - union { - __le32 flex_bytes_hi; - __le32 fd_id; - } hi_dword; - } qword3; - } wb; /* writeback */ -}; - -enum iavf_rx_desc_status_bits { - /* Note: These are predefined bit offsets */ - IAVF_RX_DESC_STATUS_DD_SHIFT = 0, - IAVF_RX_DESC_STATUS_EOF_SHIFT = 1, - IAVF_RX_DESC_STATUS_L2TAG1P_SHIFT = 2, - IAVF_RX_DESC_STATUS_L3L4P_SHIFT = 3, - IAVF_RX_DESC_STATUS_CRCP_SHIFT = 4, - IAVF_RX_DESC_STATUS_TSYNINDX_SHIFT = 5, /* 2 BITS */ - IAVF_RX_DESC_STATUS_TSYNVALID_SHIFT = 7, - /* Note: Bit 8 is reserved in X710 and XL710 */ - IAVF_RX_DESC_STATUS_EXT_UDP_0_SHIFT = 8, - IAVF_RX_DESC_STATUS_UMBCAST_SHIFT = 9, /* 2 BITS */ - IAVF_RX_DESC_STATUS_FLM_SHIFT = 11, - IAVF_RX_DESC_STATUS_FLTSTAT_SHIFT = 12, /* 2 BITS */ - IAVF_RX_DESC_STATUS_LPBK_SHIFT = 14, - IAVF_RX_DESC_STATUS_IPV6EXADD_SHIFT = 15, - IAVF_RX_DESC_STATUS_RESERVED_SHIFT = 16, /* 2 BITS */ - /* Note: For non-tunnel packets INT_UDP_0 is the right status for - * UDP header - */ - IAVF_RX_DESC_STATUS_INT_UDP_0_SHIFT = 18, - IAVF_RX_DESC_STATUS_LAST /* this entry must be last!!! */ -}; - -#define IAVF_RXD_QW1_STATUS_SHIFT 0 -#define IAVF_RXD_QW1_STATUS_MASK ((BIT(IAVF_RX_DESC_STATUS_LAST) - 1) \ - << IAVF_RXD_QW1_STATUS_SHIFT) +/** + * struct iavf_rx_desc - Receive descriptor (both legacy and flexible) + * @qw0: quad word 0 fields: + * Legacy: Descriptor Type; Mirror ID; L2TAG1P (S-TAG); Filter Status + * Flex: Descriptor Type; Mirror ID; UMBCAST; Packet Type; Flexible Flags + * Section 0; Packet Length; Header Length; Split Header Flag; + * Flexible Flags section 1 / Extended Status + * @qw1: quad word 1 fields: + * Legacy: Status Field; Error Field; Packet Type; Packet Length (packet, + * header, Split Header Flag) + * Flex: Status / Error 0 Field; L2TAG1P (S-TAG); Flexible Metadata + * Container #0; Flexible Metadata Container #1 + * @qw2: quad word 2 fields: + * Legacy: Extended Status; 1st L2TAG2P (C-TAG); 2nd L2TAG2P (C-TAG) + * Flex: Status / Error 1 Field; Flexible Flags section 2; Timestamp Low; + * 1st L2TAG2 (C-TAG); 2nd L2TAG2 (C-TAG) + * @qw3: quad word 3 fields: + * Legacy: FD Filter ID / Flexible Bytes + * Flex: Flexible Metadata Container #2; Flexible Metadata Container #3; + * Flexible Metadata Container #4 / Timestamp High 0; Flexible + * Metadata Container #5 / Timestamp High 1; + */ +struct iavf_rx_desc { + aligned_le64 qw0; +/* The hash signature (RSS) */ +#define IAVF_RXD_LEGACY_RSS_M GENMASK_ULL(63, 32) +/* Stripped C-TAG VLAN from the receive packet */ +#define IAVF_RXD_LEGACY_L2TAG1_M GENMASK_ULL(33, 16) +/* Packet type */ +#define IAVF_RXD_FLEX_PTYPE_M GENMASK_ULL(25, 16) +/* Packet length */ +#define IAVF_RXD_FLEX_PKT_LEN_M GENMASK_ULL(45, 32) + + aligned_le64 qw1; +/* Descriptor done indication flag. */ +#define IAVF_RXD_LEGACY_DD_M BIT(0) +/* End of packet. Set to 1 if this descriptor is the last one of the packet */ +#define IAVF_RXD_LEGACY_EOP_M BIT(1) +/* L2 TAG 1 presence indication */ +#define IAVF_RXD_LEGACY_L2TAG1P_M BIT(2) +/* Detectable L3 and L4 integrity check is processed by the HW */ +#define IAVF_RXD_LEGACY_L3L4P_M BIT(3) +/* Set when an IPv6 packet contains a Destination Options Header or a Routing + * Header. + */ +#define IAVF_RXD_LEGACY_IPV6EXADD_M BIT(15) +/* Receive MAC Errors: CRC; Alignment; Oversize; Undersizes; Length error */ +#define IAVF_RXD_LEGACY_RXE_M BIT(19) +/* Checksum reports: + * - IPE: IP checksum error + * - L4E: L4 integrity error + * - EIPE: External IP header (tunneled packets) + */ +#define IAVF_RXD_LEGACY_IPE_M BIT(22) +#define IAVF_RXD_LEGACY_L4E_M BIT(23) +#define IAVF_RXD_LEGACY_EIPE_M BIT(24) +/* Set for packets that skip checksum calculation in pre-parser */ +#define IAVF_RXD_LEGACY_PPRS_M BIT(26) +/* Indicates the content in the Filter Status field */ +#define IAVF_RXD_LEGACY_FLTSTAT_M GENMASK_ULL(13, 12) +/* Packet type */ +#define IAVF_RXD_LEGACY_PTYPE_M GENMASK_ULL(37, 30) +/* Packet length */ +#define IAVF_RXD_LEGACY_LENGTH_M GENMASK_ULL(51, 38) +/* Descriptor done indication flag */ +#define IAVF_RXD_FLEX_DD_M BIT(0) +/* End of packet. Set to 1 if this descriptor is the last one of the packet */ +#define IAVF_RXD_FLEX_EOP_M BIT(1) +/* Detectable L3 and L4 integrity check is processed by the HW */ +#define IAVF_RXD_FLEX_L3L4P_M BIT(3) +/* Checksum reports: + * - IPE: IP checksum error + * - L4E: L4 integrity error + * - EIPE: External IP header (tunneled packets) + * - EUDPE: External UDP checksum error (tunneled packets) + */ +#define IAVF_RXD_FLEX_XSUM_IPE_M BIT(4) +#define IAVF_RXD_FLEX_XSUM_L4E_M BIT(5) +#define IAVF_RXD_FLEX_XSUM_EIPE_M BIT(6) +#define IAVF_RXD_FLEX_XSUM_EUDPE_M BIT(7) +/* Set when an IPv6 packet contains a Destination Options Header or a Routing + * Header. + */ +#define IAVF_RXD_FLEX_IPV6EXADD_M BIT(9) +/* Receive MAC Errors: CRC; Alignment; Oversize; Undersizes; Length error */ +#define IAVF_RXD_FLEX_RXE_M BIT(10) +/* Indicates that the RSS/HASH result is valid */ +#define IAVF_RXD_FLEX_RSS_VALID_M BIT(12) +/* L2 TAG 1 presence indication */ +#define IAVF_RXD_FLEX_L2TAG1P_M BIT(13) +/* Stripped L2 Tag from the receive packet */ +#define IAVF_RXD_FLEX_L2TAG1_M GENMASK_ULL(31, 16) +/* The hash signature (RSS) */ +#define IAVF_RXD_FLEX_RSS_HASH_M GENMASK_ULL(63, 32) + + aligned_le64 qw2; +/* L2 Tag 2 Presence */ +#define IAVF_RXD_LEGACY_L2TAG2P_M BIT(0) +/* Stripped S-TAG VLAN from the receive packet */ +#define IAVF_RXD_LEGACY_L2TAG2_M GENMASK_ULL(63, 32) +/* Stripped S-TAG VLAN from the receive packet */ +#define IAVF_RXD_FLEX_L2TAG2_2_M GENMASK_ULL(63, 48) +/* The packet is a UDP tunneled packet */ +#define IAVF_RXD_FLEX_NAT_M BIT(4) +/* L2 Tag 2 Presence */ +#define IAVF_RXD_FLEX_L2TAG2P_M BIT(11) + aligned_le64 qw3; +#define IAVF_RXD_FLEX_QW3_TSTAMP_HIGH_M GENMASK_ULL(63, 32) +} __aligned(4 * sizeof(__le64)); +static_assert(sizeof(struct iavf_rx_desc) == 32); #define IAVF_RXD_QW1_STATUS_TSYNINDX_SHIFT IAVF_RX_DESC_STATUS_TSYNINDX_SHIFT #define IAVF_RXD_QW1_STATUS_TSYNINDX_MASK (0x3UL << \ @@ -298,22 +304,6 @@ enum iavf_rx_desc_fltstat_values { IAVF_RX_DESC_FLTSTAT_RSS_HASH = 3, }; -#define IAVF_RXD_QW1_ERROR_SHIFT 19 -#define IAVF_RXD_QW1_ERROR_MASK (0xFFUL << IAVF_RXD_QW1_ERROR_SHIFT) - -enum iavf_rx_desc_error_bits { - /* Note: These are predefined bit offsets */ - IAVF_RX_DESC_ERROR_RXE_SHIFT = 0, - IAVF_RX_DESC_ERROR_RECIPE_SHIFT = 1, - IAVF_RX_DESC_ERROR_HBO_SHIFT = 2, - IAVF_RX_DESC_ERROR_L3L4E_SHIFT = 3, /* 3 BITS */ - IAVF_RX_DESC_ERROR_IPE_SHIFT = 3, - IAVF_RX_DESC_ERROR_L4E_SHIFT = 4, - IAVF_RX_DESC_ERROR_EIPE_SHIFT = 5, - IAVF_RX_DESC_ERROR_OVERSIZE_SHIFT = 6, - IAVF_RX_DESC_ERROR_PPRS_SHIFT = 7 -}; - enum iavf_rx_desc_error_l3l4e_fcoe_masks { IAVF_RX_DESC_ERROR_L3L4E_NONE = 0, IAVF_RX_DESC_ERROR_L3L4E_PROT = 1, @@ -322,13 +312,6 @@ enum iavf_rx_desc_error_l3l4e_fcoe_masks { IAVF_RX_DESC_ERROR_L3L4E_DMAC_WARN = 4 }; -#define IAVF_RXD_QW1_PTYPE_SHIFT 30 -#define IAVF_RXD_QW1_PTYPE_MASK (0xFFULL << IAVF_RXD_QW1_PTYPE_SHIFT) - -#define IAVF_RXD_QW1_LENGTH_PBUF_SHIFT 38 -#define IAVF_RXD_QW1_LENGTH_PBUF_MASK (0x3FFFULL << \ - IAVF_RXD_QW1_LENGTH_PBUF_SHIFT) - #define IAVF_RXD_QW1_LENGTH_HBUF_SHIFT 52 #define IAVF_RXD_QW1_LENGTH_HBUF_MASK (0x7FFULL << \ IAVF_RXD_QW1_LENGTH_HBUF_SHIFT) @@ -347,6 +330,8 @@ enum iavf_rx_desc_ext_status_bits { IAVF_RX_DESC_EXT_STATUS_PELONGB_SHIFT = 11, }; +#define IAVF_RX_DESC_EXT_STATUS_L2TAG2P_M BIT(IAVF_RX_DESC_EXT_STATUS_L2TAG2P_SHIFT) + enum iavf_rx_desc_pe_status_bits { /* Note: These are predefined bit offsets */ IAVF_RX_DESC_PE_STATUS_QPID_SHIFT = 0, /* 18 BITS */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_types.h b/drivers/net/ethernet/intel/iavf/iavf_types.h new file mode 100644 index 000000000000..a095855122bf --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_types.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2024 Intel Corporation. */ + +#ifndef _IAVF_TYPES_H_ +#define _IAVF_TYPES_H_ + +#include "iavf_types.h" + +#include <linux/avf/virtchnl.h> +#include <linux/ptp_clock_kernel.h> + +/* structure used to queue PTP commands for processing */ +struct iavf_ptp_aq_cmd { + struct list_head list; + enum virtchnl_ops v_opcode:16; + u16 msglen; + u8 msg[] __counted_by(msglen); +}; + +struct iavf_ptp { + wait_queue_head_t phc_time_waitqueue; + struct virtchnl_ptp_caps hw_caps; + struct ptp_clock_info info; + struct ptp_clock *clock; + struct list_head aq_cmds; + u64 cached_phc_time; + unsigned long cached_phc_updated; + /* Lock protecting access to the AQ command list */ + struct mutex aq_cmd_lock; + struct kernel_hwtstamp_config hwtstamp_config; + bool phc_time_ready:1; +}; + +#endif /* _IAVF_TYPES_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 15d388b431c5..a6f0e5990be2 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -4,6 +4,7 @@ #include <linux/net/intel/libie/rx.h> #include "iavf.h" +#include "iavf_ptp.h" #include "iavf_prototype.h" /** @@ -144,9 +145,11 @@ int iavf_send_vf_config_msg(struct iavf_adapter *adapter) VIRTCHNL_VF_OFFLOAD_ENCAP | VIRTCHNL_VF_OFFLOAD_TC_U32 | VIRTCHNL_VF_OFFLOAD_VLAN_V2 | + VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC | VIRTCHNL_VF_OFFLOAD_CRC | VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM | VIRTCHNL_VF_OFFLOAD_REQ_QUEUES | + VIRTCHNL_VF_CAP_PTP | VIRTCHNL_VF_OFFLOAD_ADQ | VIRTCHNL_VF_OFFLOAD_USO | VIRTCHNL_VF_OFFLOAD_FDIR_PF | @@ -177,6 +180,54 @@ int iavf_send_vf_offload_vlan_v2_msg(struct iavf_adapter *adapter) NULL, 0); } +int iavf_send_vf_supported_rxdids_msg(struct iavf_adapter *adapter) +{ + adapter->aq_required &= ~IAVF_FLAG_AQ_GET_SUPPORTED_RXDIDS; + + if (!IAVF_RXDID_ALLOWED(adapter)) + return -EOPNOTSUPP; + + adapter->current_op = VIRTCHNL_OP_GET_SUPPORTED_RXDIDS; + + return iavf_send_pf_msg(adapter, VIRTCHNL_OP_GET_SUPPORTED_RXDIDS, + NULL, 0); +} + +/** + * iavf_send_vf_ptp_caps_msg - Send request for PTP capabilities + * @adapter: private adapter structure + * + * Send the VIRTCHNL_OP_1588_PTP_GET_CAPS command to the PF to request the PTP + * capabilities available to this device. This includes the following + * potential access: + * + * * READ_PHC - access to read the PTP hardware clock time + * * RX_TSTAMP - access to request Rx timestamps on all received packets + * + * The PF will reply with the same opcode a filled out copy of the + * virtchnl_ptp_caps structure which defines the specifics of which features + * are accessible to this device. + * + * Return: 0 if success, error code otherwise. + */ +int iavf_send_vf_ptp_caps_msg(struct iavf_adapter *adapter) +{ + struct virtchnl_ptp_caps hw_caps = { + .caps = VIRTCHNL_1588_PTP_CAP_READ_PHC | + VIRTCHNL_1588_PTP_CAP_RX_TSTAMP + }; + + adapter->aq_required &= ~IAVF_FLAG_AQ_GET_PTP_CAPS; + + if (!IAVF_PTP_ALLOWED(adapter)) + return -EOPNOTSUPP; + + adapter->current_op = VIRTCHNL_OP_1588_PTP_GET_CAPS; + + return iavf_send_pf_msg(adapter, VIRTCHNL_OP_1588_PTP_GET_CAPS, + (u8 *)&hw_caps, sizeof(hw_caps)); +} + /** * iavf_validate_num_queues * @adapter: adapter structure @@ -263,6 +314,40 @@ int iavf_get_vf_vlan_v2_caps(struct iavf_adapter *adapter) return err; } +int iavf_get_vf_supported_rxdids(struct iavf_adapter *adapter) +{ + struct iavf_arq_event_info event; + u64 rxdids; + int err; + + event.msg_buf = (u8 *)&rxdids; + event.buf_len = sizeof(rxdids); + + err = iavf_poll_virtchnl_msg(&adapter->hw, &event, + VIRTCHNL_OP_GET_SUPPORTED_RXDIDS); + if (!err) + adapter->supp_rxdids = rxdids; + + return err; +} + +int iavf_get_vf_ptp_caps(struct iavf_adapter *adapter) +{ + struct virtchnl_ptp_caps caps = {}; + struct iavf_arq_event_info event; + int err; + + event.msg_buf = (u8 *)∩︀ + event.buf_len = sizeof(caps); + + err = iavf_poll_virtchnl_msg(&adapter->hw, &event, + VIRTCHNL_OP_1588_PTP_GET_CAPS); + if (!err) + adapter->ptp.hw_caps = caps; + + return err; +} + /** * iavf_configure_queues * @adapter: adapter structure @@ -275,6 +360,7 @@ void iavf_configure_queues(struct iavf_adapter *adapter) int pairs = adapter->num_active_queues; struct virtchnl_queue_pair_info *vqpi; u32 i, max_frame; + u8 rx_flags = 0; size_t len; max_frame = LIBIE_MAX_RX_FRM_LEN(adapter->rx_rings->pp->p.offset); @@ -292,6 +378,9 @@ void iavf_configure_queues(struct iavf_adapter *adapter) if (!vqci) return; + if (iavf_ptp_cap_supported(adapter, VIRTCHNL_1588_PTP_CAP_RX_TSTAMP)) + rx_flags |= VIRTCHNL_PTP_RX_TSTAMP; + vqci->vsi_id = adapter->vsi_res->vsi_id; vqci->num_queue_pairs = pairs; vqpi = vqci->qpair; @@ -309,9 +398,12 @@ void iavf_configure_queues(struct iavf_adapter *adapter) vqpi->rxq.dma_ring_addr = adapter->rx_rings[i].dma; vqpi->rxq.max_pkt_size = max_frame; vqpi->rxq.databuffer_size = adapter->rx_rings[i].rx_buf_len; + if (IAVF_RXDID_ALLOWED(adapter)) + vqpi->rxq.rxdid = adapter->rxdid; if (CRC_OFFLOAD_ALLOWED(adapter)) vqpi->rxq.crc_disable = !!(adapter->netdev->features & NETIF_F_RXFCS); + vqpi->rxq.flags = rx_flags; vqpi++; } @@ -1402,6 +1494,67 @@ void iavf_disable_vlan_insertion_v2(struct iavf_adapter *adapter, u16 tpid) VIRTCHNL_OP_DISABLE_VLAN_INSERTION_V2); } +#if IS_ENABLED(CONFIG_PTP_1588_CLOCK) +/** + * iavf_virtchnl_send_ptp_cmd - Send one queued PTP command + * @adapter: adapter private structure + * + * De-queue one PTP command request and send the command message to the PF. + * Clear IAVF_FLAG_AQ_SEND_PTP_CMD if no more messages are left to send. + */ +void iavf_virtchnl_send_ptp_cmd(struct iavf_adapter *adapter) +{ + struct iavf_ptp_aq_cmd *cmd; + int err; + + if (!adapter->ptp.clock) { + /* This shouldn't be possible to hit, since no messages should + * be queued if PTP is not initialized. + */ + pci_err(adapter->pdev, "PTP is not initialized\n"); + adapter->aq_required &= ~IAVF_FLAG_AQ_SEND_PTP_CMD; + return; + } + + mutex_lock(&adapter->ptp.aq_cmd_lock); + cmd = list_first_entry_or_null(&adapter->ptp.aq_cmds, + struct iavf_ptp_aq_cmd, list); + if (!cmd) { + /* no further PTP messages to send */ + adapter->aq_required &= ~IAVF_FLAG_AQ_SEND_PTP_CMD; + goto out_unlock; + } + + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + pci_err(adapter->pdev, + "Cannot send PTP command %d, command %d pending\n", + cmd->v_opcode, adapter->current_op); + goto out_unlock; + } + + err = iavf_send_pf_msg(adapter, cmd->v_opcode, cmd->msg, cmd->msglen); + if (!err) { + /* Command was sent without errors, so we can remove it from + * the list and discard it. + */ + list_del(&cmd->list); + kfree(cmd); + } else { + /* We failed to send the command, try again next cycle */ + pci_err(adapter->pdev, "Failed to send PTP command %d\n", + cmd->v_opcode); + } + + if (list_empty(&adapter->ptp.aq_cmds)) + /* no further PTP messages to send */ + adapter->aq_required &= ~IAVF_FLAG_AQ_SEND_PTP_CMD; + +out_unlock: + mutex_unlock(&adapter->ptp.aq_cmd_lock); +} +#endif /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */ + /** * iavf_print_link_message - print link up or down * @adapter: adapter structure @@ -2098,6 +2251,37 @@ static void iavf_activate_fdir_filters(struct iavf_adapter *adapter) } /** + * iavf_virtchnl_ptp_get_time - Respond to VIRTCHNL_OP_1588_PTP_GET_TIME + * @adapter: private adapter structure + * @data: the message from the PF + * @len: length of the message from the PF + * + * Handle the VIRTCHNL_OP_1588_PTP_GET_TIME message from the PF. This message + * is sent by the PF in response to the same op as a request from the VF. + * Extract the 64bit nanoseconds time from the message and store it in + * cached_phc_time. Then, notify any thread that is waiting for the update via + * the wait queue. + */ +static void iavf_virtchnl_ptp_get_time(struct iavf_adapter *adapter, + void *data, u16 len) +{ + struct virtchnl_phc_time *msg = data; + + if (len != sizeof(*msg)) { + dev_err_once(&adapter->pdev->dev, + "Invalid VIRTCHNL_OP_1588_PTP_GET_TIME from PF. Got size %u, expected %zu\n", + len, sizeof(*msg)); + return; + } + + adapter->ptp.cached_phc_time = msg->time; + adapter->ptp.cached_phc_updated = jiffies; + adapter->ptp.phc_time_ready = true; + + wake_up(&adapter->ptp.phc_time_waitqueue); +} + +/** * iavf_virtchnl_completion * @adapter: adapter structure * @v_opcode: opcode sent by PF @@ -2509,6 +2693,25 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, aq_required; } break; + case VIRTCHNL_OP_GET_SUPPORTED_RXDIDS: + if (msglen != sizeof(u64)) + return; + + adapter->supp_rxdids = *(u64 *)msg; + + break; + case VIRTCHNL_OP_1588_PTP_GET_CAPS: + if (msglen != sizeof(adapter->ptp.hw_caps)) + return; + + adapter->ptp.hw_caps = *(struct virtchnl_ptp_caps *)msg; + + /* process any state change needed due to new capabilities */ + iavf_ptp_process_caps(adapter); + break; + case VIRTCHNL_OP_1588_PTP_GET_TIME: + iavf_virtchnl_ptp_get_time(adapter, msg, msglen); + break; case VIRTCHNL_OP_ENABLE_QUEUES: /* enable transmits */ iavf_irq_enable(adapter, true); diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index 0e862f20427a..b3234a55a253 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -473,9 +473,6 @@ static int ice_setup_rx_ctx(struct ice_rx_ring *ring) */ if (vsi->type != ICE_VSI_VF) ice_write_qrxflxp_cntxt(hw, pf_q, rxdid, 0x3, true); - else - ice_write_qrxflxp_cntxt(hw, pf_q, ICE_RXDID_LEGACY_1, 0x3, - false); /* Absolute queue number out of 2K needs to be passed */ err = ice_write_rxq_ctx(hw, &rlan_ctx, pf_q); diff --git a/drivers/net/ethernet/intel/ice/ice_irq.c b/drivers/net/ethernet/intel/ice/ice_irq.c index cbae3d81f0f1..30801fd375f0 100644 --- a/drivers/net/ethernet/intel/ice/ice_irq.c +++ b/drivers/net/ethernet/intel/ice/ice_irq.c @@ -149,8 +149,8 @@ int ice_init_interrupt_scheme(struct ice_pf *pf) vectors = pci_alloc_irq_vectors(pf->pdev, pf->msix.min, vectors, PCI_IRQ_MSIX); - if (vectors < pf->msix.min) - return -ENOMEM; + if (vectors < 0) + return vectors; ice_init_irq_tracker(pf, pf->msix.max, vectors); diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 978f308d3b1b..7f5b229cab05 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -1775,9 +1775,8 @@ void ice_update_eth_stats(struct ice_vsi *vsi) * @prio: priority for the RXDID for this queue * @ena_ts: true to enable timestamp and false to disable timestamp */ -void -ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio, - bool ena_ts) +void ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio, + bool ena_ts) { int regval = rd32(hw, QRXFLXP_CNTXT(pf_q)); diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index b65114ff487b..1bb0033347c7 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -298,8 +298,8 @@ void ice_ptp_restore_timestamp_mode(struct ice_pf *pf) * @sts: Optional parameter for holding a pair of system timestamps from * the system clock. Will be ignored if NULL is given. */ -static u64 -ice_ptp_read_src_clk_reg(struct ice_pf *pf, struct ptp_system_timestamp *sts) +u64 ice_ptp_read_src_clk_reg(struct ice_pf *pf, + struct ptp_system_timestamp *sts) { struct ice_hw *hw = &pf->hw; u32 hi, lo, lo2; diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.h b/drivers/net/ethernet/intel/ice/ice_ptp.h index 783139de7f74..3b769a0cad00 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp.h @@ -304,6 +304,8 @@ void ice_ptp_req_tx_single_tstamp(struct ice_ptp_tx *tx, u8 idx); void ice_ptp_complete_tx_single_tstamp(struct ice_ptp_tx *tx); enum ice_tx_tstamp_work ice_ptp_process_ts(struct ice_pf *pf); irqreturn_t ice_ptp_ts_irq(struct ice_pf *pf); +u64 ice_ptp_read_src_clk_reg(struct ice_pf *pf, + struct ptp_system_timestamp *sts); u64 ice_ptp_get_rx_hwts(const union ice_32b_rx_flex_desc *rx_desc, const struct ice_pkt_ctx *pkt_ctx); @@ -347,6 +349,12 @@ static inline irqreturn_t ice_ptp_ts_irq(struct ice_pf *pf) return IRQ_HANDLED; } +static inline u64 ice_ptp_read_src_clk_reg(struct ice_pf *pf, + struct ptp_system_timestamp *sts) +{ + return 0; +} + static inline u64 ice_ptp_get_rx_hwts(const union ice_32b_rx_flex_desc *rx_desc, const struct ice_pkt_ctx *pkt_ctx) diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.h b/drivers/net/ethernet/intel/ice/ice_vf_lib.h index 4261fe1c2bcd..799b2c1f1184 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.h @@ -124,6 +124,9 @@ struct ice_vf { u8 spoofchk:1; u8 link_forced:1; u8 link_up:1; /* only valid if VF link is forced */ + + u32 ptp_caps; + unsigned int min_tx_rate; /* Minimum Tx bandwidth limit in Mbps */ unsigned int max_tx_rate; /* Maximum Tx bandwidth limit in Mbps */ DECLARE_BITMAP(vf_states, ICE_VF_STATES_NBITS); /* VF runtime states */ diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index ff4ad788d96a..674767781fe4 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -498,6 +498,9 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_QOS) vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_QOS; + if (vf->driver_caps & VIRTCHNL_VF_CAP_PTP) + vfres->vf_cap_flags |= VIRTCHNL_VF_CAP_PTP; + vfres->num_vsis = 1; /* Tx and Rx queue are equal for VF */ vfres->num_queue_pairs = vsi->num_txq; @@ -1975,6 +1978,7 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) struct ice_vsi *vsi; u8 act_prt, pri_prt; int i = -1, q_idx; + bool ena_ts; lag = pf->lag; mutex_lock(&pf->lag_mutex); @@ -2104,9 +2108,14 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) rxdid = ICE_RXDID_LEGACY_1; } + ena_ts = ((vf->driver_caps & + VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC) && + (vf->driver_caps & VIRTCHNL_VF_CAP_PTP) && + (qpi->rxq.flags & VIRTCHNL_PTP_RX_TSTAMP)); + ice_write_qrxflxp_cntxt(&vsi->back->hw, - vsi->rxq_map[q_idx], - rxdid, 0x03, false); + vsi->rxq_map[q_idx], rxdid, + ICE_RXDID_PRIO, ena_ts); } } @@ -3031,8 +3040,8 @@ err: static int ice_vc_query_rxdid(struct ice_vf *vf) { enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; - struct virtchnl_supported_rxdids rxdid = {}; struct ice_pf *pf = vf->pf; + u64 rxdid; if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; @@ -3044,7 +3053,7 @@ static int ice_vc_query_rxdid(struct ice_vf *vf) goto err; } - rxdid.supported_rxdids = pf->supported_rxdids; + rxdid = pf->supported_rxdids; err: return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_GET_SUPPORTED_RXDIDS, @@ -4092,6 +4101,59 @@ out: v_ret, NULL, 0); } +static int ice_vc_get_ptp_cap(struct ice_vf *vf, + const struct virtchnl_ptp_caps *msg) +{ + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_ERR_PARAM; + u32 caps = VIRTCHNL_1588_PTP_CAP_RX_TSTAMP | + VIRTCHNL_1588_PTP_CAP_READ_PHC; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) + goto err; + + v_ret = VIRTCHNL_STATUS_SUCCESS; + + if (msg->caps & caps) + vf->ptp_caps = caps; + +err: + /* send the response back to the VF */ + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_1588_PTP_GET_CAPS, v_ret, + (u8 *)&vf->ptp_caps, + sizeof(struct virtchnl_ptp_caps)); +} + +static int ice_vc_get_phc_time(struct ice_vf *vf) +{ + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_ERR_PARAM; + struct virtchnl_phc_time *phc_time = NULL; + struct ice_pf *pf = vf->pf; + u32 len = 0; + int ret; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) + goto err; + + v_ret = VIRTCHNL_STATUS_SUCCESS; + + phc_time = kzalloc(sizeof(*phc_time), GFP_KERNEL); + if (!phc_time) { + v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY; + goto err; + } + + len = sizeof(*phc_time); + + phc_time->time = ice_ptp_read_src_clk_reg(pf, NULL); + +err: + /* send the response back to the VF */ + ret = ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_1588_PTP_GET_TIME, v_ret, + (u8 *)phc_time, len); + kfree(phc_time); + return ret; +} + static const struct ice_virtchnl_ops ice_virtchnl_dflt_ops = { .get_ver_msg = ice_vc_get_ver_msg, .get_vf_res_msg = ice_vc_get_vf_res_msg, @@ -4128,6 +4190,8 @@ static const struct ice_virtchnl_ops ice_virtchnl_dflt_ops = { .get_qos_caps = ice_vc_get_qos_caps, .cfg_q_bw = ice_vc_cfg_q_bw, .cfg_q_quanta = ice_vc_cfg_q_quanta, + .get_ptp_cap = ice_vc_get_ptp_cap, + .get_phc_time = ice_vc_get_phc_time, /* If you add a new op here please make sure to add it to * ice_virtchnl_repr_ops as well. */ @@ -4264,6 +4328,8 @@ static const struct ice_virtchnl_ops ice_virtchnl_repr_ops = { .get_qos_caps = ice_vc_get_qos_caps, .cfg_q_bw = ice_vc_cfg_q_bw, .cfg_q_quanta = ice_vc_cfg_q_quanta, + .get_ptp_cap = ice_vc_get_ptp_cap, + .get_phc_time = ice_vc_get_phc_time, }; /** @@ -4501,6 +4567,12 @@ error_handler: case VIRTCHNL_OP_CONFIG_QUANTA: err = ops->cfg_q_quanta(vf, msg); break; + case VIRTCHNL_OP_1588_PTP_GET_CAPS: + err = ops->get_ptp_cap(vf, (const void *)msg); + break; + case VIRTCHNL_OP_1588_PTP_GET_TIME: + err = ops->get_phc_time(vf); + break; case VIRTCHNL_OP_UNKNOWN: default: dev_err(dev, "Unsupported opcode %d from VF %d\n", v_opcode, diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.h b/drivers/net/ethernet/intel/ice/ice_virtchnl.h index 0c629aef9baf..222990f229d5 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.h +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.h @@ -26,6 +26,9 @@ #define ICE_MAX_MACADDR_PER_VF 18 #define ICE_FLEX_DESC_RXDID_MAX_NUM 64 +/* Priority to be compared against previous priority from the pipe */ +#define ICE_RXDID_PRIO 0x03 + /* VFs only get a single VSI. For ice hardware, the VF does not need to know * its VSI index. However, the virtchnl interface requires a VSI number, * mainly due to legacy hardware. @@ -72,6 +75,9 @@ struct ice_virtchnl_ops { int (*cfg_q_tc_map)(struct ice_vf *vf, u8 *msg); int (*cfg_q_bw)(struct ice_vf *vf, u8 *msg); int (*cfg_q_quanta)(struct ice_vf *vf, u8 *msg); + int (*get_ptp_cap)(struct ice_vf *vf, + const struct virtchnl_ptp_caps *msg); + int (*get_phc_time)(struct ice_vf *vf); }; #ifdef CONFIG_PCI_IOV diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c index c105a82ee136..a3d1579a619a 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c @@ -84,6 +84,12 @@ static const u32 fdir_pf_allowlist_opcodes[] = { VIRTCHNL_OP_ADD_FDIR_FILTER, VIRTCHNL_OP_DEL_FDIR_FILTER, }; +/* VIRTCHNL_VF_CAP_PTP */ +static const u32 ptp_allowlist_opcodes[] = { + VIRTCHNL_OP_1588_PTP_GET_CAPS, + VIRTCHNL_OP_1588_PTP_GET_TIME, +}; + static const u32 tc_allowlist_opcodes[] = { VIRTCHNL_OP_GET_QOS_CAPS, VIRTCHNL_OP_CONFIG_QUEUE_BW, VIRTCHNL_OP_CONFIG_QUANTA, @@ -110,6 +116,7 @@ static const struct allowlist_opcode_info allowlist_opcodes[] = { ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_FDIR_PF, fdir_pf_allowlist_opcodes), ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_VLAN_V2, vlan_v2_allowlist_opcodes), ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_QOS, tc_allowlist_opcodes), + ALLOW_ITEM(VIRTCHNL_VF_CAP_PTP, ptp_allowlist_opcodes), }; /** diff --git a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c index dfd7cf1d9aa0..eae1b6f474e6 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c @@ -595,7 +595,7 @@ static bool idpf_rx_singleq_is_non_eop(const union virtchnl2_rx_desc *rx_desc) */ static void idpf_rx_singleq_csum(struct idpf_rx_queue *rxq, struct sk_buff *skb, - struct idpf_rx_csum_decoded csum_bits, + struct libeth_rx_csum csum_bits, struct libeth_rx_pt decoded) { bool ipv4, ipv6; @@ -661,10 +661,10 @@ checksum_fail: * * Return: parsed checksum status. **/ -static struct idpf_rx_csum_decoded +static struct libeth_rx_csum idpf_rx_singleq_base_csum(const union virtchnl2_rx_desc *rx_desc) { - struct idpf_rx_csum_decoded csum_bits = { }; + struct libeth_rx_csum csum_bits = { }; u32 rx_error, rx_status; u64 qword; @@ -696,10 +696,10 @@ idpf_rx_singleq_base_csum(const union virtchnl2_rx_desc *rx_desc) * * Return: parsed checksum status. **/ -static struct idpf_rx_csum_decoded +static struct libeth_rx_csum idpf_rx_singleq_flex_csum(const union virtchnl2_rx_desc *rx_desc) { - struct idpf_rx_csum_decoded csum_bits = { }; + struct libeth_rx_csum csum_bits = { }; u16 rx_status0, rx_status1; rx_status0 = le16_to_cpu(rx_desc->flex_nic_wb.status_error0); @@ -798,7 +798,7 @@ idpf_rx_singleq_process_skb_fields(struct idpf_rx_queue *rx_q, u16 ptype) { struct libeth_rx_pt decoded = rx_q->rx_ptype_lkup[ptype]; - struct idpf_rx_csum_decoded csum_bits; + struct libeth_rx_csum csum_bits; /* modifies the skb - consumes the enet header */ skb->protocol = eth_type_trans(skb, rx_q->netdev); @@ -891,6 +891,7 @@ bool idpf_rx_singleq_buf_hw_alloc_all(struct idpf_rx_queue *rx_q, * idpf_rx_singleq_extract_base_fields - Extract fields from the Rx descriptor * @rx_desc: the descriptor to process * @fields: storage for extracted values + * @ptype: pointer that will store packet type * * Decode the Rx descriptor and extract relevant information including the * size and Rx packet type. @@ -900,20 +901,21 @@ bool idpf_rx_singleq_buf_hw_alloc_all(struct idpf_rx_queue *rx_q, */ static void idpf_rx_singleq_extract_base_fields(const union virtchnl2_rx_desc *rx_desc, - struct idpf_rx_extracted *fields) + struct libeth_rqe_info *fields, u32 *ptype) { u64 qword; qword = le64_to_cpu(rx_desc->base_wb.qword1.status_error_ptype_len); - fields->size = FIELD_GET(VIRTCHNL2_RX_BASE_DESC_QW1_LEN_PBUF_M, qword); - fields->rx_ptype = FIELD_GET(VIRTCHNL2_RX_BASE_DESC_QW1_PTYPE_M, qword); + fields->len = FIELD_GET(VIRTCHNL2_RX_BASE_DESC_QW1_LEN_PBUF_M, qword); + *ptype = FIELD_GET(VIRTCHNL2_RX_BASE_DESC_QW1_PTYPE_M, qword); } /** * idpf_rx_singleq_extract_flex_fields - Extract fields from the Rx descriptor * @rx_desc: the descriptor to process * @fields: storage for extracted values + * @ptype: pointer that will store packet type * * Decode the Rx descriptor and extract relevant information including the * size and Rx packet type. @@ -923,12 +925,12 @@ idpf_rx_singleq_extract_base_fields(const union virtchnl2_rx_desc *rx_desc, */ static void idpf_rx_singleq_extract_flex_fields(const union virtchnl2_rx_desc *rx_desc, - struct idpf_rx_extracted *fields) + struct libeth_rqe_info *fields, u32 *ptype) { - fields->size = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_PKT_LEN_M, - le16_to_cpu(rx_desc->flex_nic_wb.pkt_len)); - fields->rx_ptype = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_PTYPE_M, - le16_to_cpu(rx_desc->flex_nic_wb.ptype_flex_flags0)); + fields->len = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_PKT_LEN_M, + le16_to_cpu(rx_desc->flex_nic_wb.pkt_len)); + *ptype = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_PTYPE_M, + le16_to_cpu(rx_desc->flex_nic_wb.ptype_flex_flags0)); } /** @@ -936,17 +938,18 @@ idpf_rx_singleq_extract_flex_fields(const union virtchnl2_rx_desc *rx_desc, * @rx_q: Rx descriptor queue * @rx_desc: the descriptor to process * @fields: storage for extracted values + * @ptype: pointer that will store packet type * */ static void idpf_rx_singleq_extract_fields(const struct idpf_rx_queue *rx_q, const union virtchnl2_rx_desc *rx_desc, - struct idpf_rx_extracted *fields) + struct libeth_rqe_info *fields, u32 *ptype) { if (rx_q->rxdids == VIRTCHNL2_RXDID_1_32B_BASE_M) - idpf_rx_singleq_extract_base_fields(rx_desc, fields); + idpf_rx_singleq_extract_base_fields(rx_desc, fields, ptype); else - idpf_rx_singleq_extract_flex_fields(rx_desc, fields); + idpf_rx_singleq_extract_flex_fields(rx_desc, fields, ptype); } /** @@ -966,9 +969,10 @@ static int idpf_rx_singleq_clean(struct idpf_rx_queue *rx_q, int budget) /* Process Rx packets bounded by budget */ while (likely(total_rx_pkts < (unsigned int)budget)) { - struct idpf_rx_extracted fields = { }; + struct libeth_rqe_info fields = { }; union virtchnl2_rx_desc *rx_desc; struct idpf_rx_buf *rx_buf; + u32 ptype; /* get the Rx desc from Rx queue based on 'next_to_clean' */ rx_desc = &rx_q->rx[ntc]; @@ -989,16 +993,16 @@ static int idpf_rx_singleq_clean(struct idpf_rx_queue *rx_q, int budget) */ dma_rmb(); - idpf_rx_singleq_extract_fields(rx_q, rx_desc, &fields); + idpf_rx_singleq_extract_fields(rx_q, rx_desc, &fields, &ptype); rx_buf = &rx_q->rx_buf[ntc]; - if (!libeth_rx_sync_for_cpu(rx_buf, fields.size)) + if (!libeth_rx_sync_for_cpu(rx_buf, fields.len)) goto skip_data; if (skb) - idpf_rx_add_frag(rx_buf, skb, fields.size); + idpf_rx_add_frag(rx_buf, skb, fields.len); else - skb = idpf_rx_build_skb(rx_buf, fields.size); + skb = idpf_rx_build_skb(rx_buf, fields.len); /* exit if we failed to retrieve a buffer */ if (!skb) @@ -1033,8 +1037,7 @@ skip_data: total_rx_bytes += skb->len; /* protocol */ - idpf_rx_singleq_process_skb_fields(rx_q, skb, - rx_desc, fields.rx_ptype); + idpf_rx_singleq_process_skb_fields(rx_q, skb, rx_desc, ptype); /* send completed skb up the stack */ napi_gro_receive(rx_q->pp->p.napi, skb); diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c index 9be6a6b59c4e..2747dc69999a 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c @@ -2895,7 +2895,7 @@ idpf_rx_hash(const struct idpf_rx_queue *rxq, struct sk_buff *skb, * skb->protocol must be set before this function is called */ static void idpf_rx_csum(struct idpf_rx_queue *rxq, struct sk_buff *skb, - struct idpf_rx_csum_decoded csum_bits, + struct libeth_rx_csum csum_bits, struct libeth_rx_pt decoded) { bool ipv4, ipv6; @@ -2923,7 +2923,7 @@ static void idpf_rx_csum(struct idpf_rx_queue *rxq, struct sk_buff *skb, if (unlikely(csum_bits.l4e)) goto checksum_fail; - if (csum_bits.raw_csum_inv || + if (!csum_bits.raw_csum_valid || decoded.inner_prot == LIBETH_RX_PT_INNER_SCTP) { skb->ip_summed = CHECKSUM_UNNECESSARY; return; @@ -2946,10 +2946,10 @@ checksum_fail: * * Return: parsed checksum status. **/ -static struct idpf_rx_csum_decoded +static struct libeth_rx_csum idpf_rx_splitq_extract_csum_bits(const struct virtchnl2_rx_flex_desc_adv_nic_3 *rx_desc) { - struct idpf_rx_csum_decoded csum = { }; + struct libeth_rx_csum csum = { }; u8 qword0, qword1; qword0 = rx_desc->status_err0_qw0; @@ -2965,9 +2965,9 @@ idpf_rx_splitq_extract_csum_bits(const struct virtchnl2_rx_flex_desc_adv_nic_3 * qword1); csum.ipv6exadd = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS0_IPV6EXADD_M, qword0); - csum.raw_csum_inv = - le16_get_bits(rx_desc->ptype_err_fflags0, - VIRTCHNL2_RX_FLEX_DESC_ADV_RAW_CSUM_INV_M); + csum.raw_csum_valid = + !le16_get_bits(rx_desc->ptype_err_fflags0, + VIRTCHNL2_RX_FLEX_DESC_ADV_RAW_CSUM_INV_M); csum.raw_csum = le16_to_cpu(rx_desc->misc.raw_cs); return csum; @@ -3058,7 +3058,7 @@ static int idpf_rx_process_skb_fields(struct idpf_rx_queue *rxq, struct sk_buff *skb, const struct virtchnl2_rx_flex_desc_adv_nic_3 *rx_desc) { - struct idpf_rx_csum_decoded csum_bits; + struct libeth_rx_csum csum_bits; struct libeth_rx_pt decoded; u16 rx_ptype; diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_txrx.h index 0f71a6f5557b..cd9a20c9cc7f 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.h +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.h @@ -213,25 +213,6 @@ enum idpf_tx_ctx_desc_eipt_offload { IDPF_TX_CTX_EXT_IP_IPV4 = 0x3 }; -/* Checksum offload bits decoded from the receive descriptor. */ -struct idpf_rx_csum_decoded { - u32 l3l4p : 1; - u32 ipe : 1; - u32 eipe : 1; - u32 eudpe : 1; - u32 ipv6exadd : 1; - u32 l4e : 1; - u32 pprs : 1; - u32 nat : 1; - u32 raw_csum_inv : 1; - u32 raw_csum : 16; -}; - -struct idpf_rx_extracted { - unsigned int size; - u16 rx_ptype; -}; - #define IDPF_TX_COMPLQ_CLEAN_BUDGET 256 #define IDPF_TX_MIN_PKT_LEN 17 #define IDPF_TX_DESCS_FOR_SKB_DATA_PTR 1 diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 4fe121b9f94b..44b18c573909 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -5557,7 +5557,6 @@ static int mvneta_probe(struct platform_device *pdev) clk_prepare_enable(pp->clk_bus); pp->phylink_pcs.ops = &mvneta_phylink_pcs_ops; - pp->phylink_pcs.neg_mode = true; pp->phylink_config.dev = &dev->dev; pp->phylink_config.type = PHYLINK_NETDEV; diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index dd76c1b7ed3a..f166dc4e6503 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -7024,9 +7024,7 @@ static int mvpp2_port_probe(struct platform_device *pdev, dev->dev_port = port->id; port->pcs_gmac.ops = &mvpp2_phylink_gmac_pcs_ops; - port->pcs_gmac.neg_mode = true; port->pcs_xlg.ops = &mvpp2_phylink_xlg_pcs_ops; - port->pcs_xlg.neg_mode = true; if (!mvpp2_use_acpi_compat_mode(port_fwnode)) { port->phylink_config.dev = &dev->dev; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile index cb6513ab35e7..69e0778f9ac1 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile +++ b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile @@ -9,7 +9,7 @@ obj-$(CONFIG_RVU_ESWITCH) += rvu_rep.o rvu_nicpf-y := otx2_pf.o otx2_common.o otx2_txrx.o otx2_ethtool.o \ otx2_flows.o otx2_tc.o cn10k.o otx2_dmac_flt.o \ - otx2_devlink.o qos_sq.o qos.o + otx2_devlink.o qos_sq.o qos.o otx2_xsk.o rvu_nicvf-y := otx2_vf.o rvu_rep-y := rep.o diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c index a15cc86635d6..c3b6e0f60a79 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c @@ -112,9 +112,12 @@ int cn10k_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq) struct otx2_nic *pfvf = dev; int cnt = cq->pool_ptrs; u64 ptrs[NPA_MAX_BURST]; + struct otx2_pool *pool; dma_addr_t bufptr; int num_ptrs = 1; + pool = &pfvf->qset.pool[cq->cq_idx]; + /* Refill pool with new buffers */ while (cq->pool_ptrs) { if (otx2_alloc_buffer(pfvf, cq, &bufptr)) { @@ -124,7 +127,9 @@ int cn10k_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq) break; } cq->pool_ptrs--; - ptrs[num_ptrs] = (u64)bufptr + OTX2_HEAD_ROOM; + ptrs[num_ptrs] = pool->xsk_pool ? + (u64)bufptr : (u64)bufptr + OTX2_HEAD_ROOM; + num_ptrs++; if (num_ptrs == NPA_MAX_BURST || cq->pool_ptrs == 0) { __cn10k_aura_freeptr(pfvf, cq->cq_idx, ptrs, diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c index 2b49bfec7869..84cd029a85aa 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c @@ -17,6 +17,7 @@ #include "otx2_common.h" #include "otx2_struct.h" #include "cn10k.h" +#include "otx2_xsk.h" static bool otx2_is_pfc_enabled(struct otx2_nic *pfvf) { @@ -330,6 +331,10 @@ int otx2_set_rss_table(struct otx2_nic *pfvf, int ctx_id) rss_ctx = rss->rss_ctx[ctx_id]; /* Get memory to put this msg */ for (idx = 0; idx < rss->rss_size; idx++) { + /* Ignore the queue if AF_XDP zero copy is enabled */ + if (test_bit(rss_ctx->ind_tbl[idx], pfvf->af_xdp_zc_qidx)) + continue; + aq = otx2_mbox_alloc_msg_nix_aq_enq(mbox); if (!aq) { /* The shared memory buffer can be full. @@ -549,10 +554,13 @@ static int otx2_alloc_pool_buf(struct otx2_nic *pfvf, struct otx2_pool *pool, } static int __otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool, - dma_addr_t *dma) + dma_addr_t *dma, int qidx, int idx) { u8 *buf; + if (pool->xsk_pool) + return otx2_xsk_pool_alloc_buf(pfvf, pool, dma, idx); + if (pool->page_pool) return otx2_alloc_pool_buf(pfvf, pool, dma); @@ -571,12 +579,12 @@ static int __otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool, } int otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool, - dma_addr_t *dma) + dma_addr_t *dma, int qidx, int idx) { int ret; local_bh_disable(); - ret = __otx2_alloc_rbuf(pfvf, pool, dma); + ret = __otx2_alloc_rbuf(pfvf, pool, dma, qidx, idx); local_bh_enable(); return ret; } @@ -584,7 +592,8 @@ int otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool, int otx2_alloc_buffer(struct otx2_nic *pfvf, struct otx2_cq_queue *cq, dma_addr_t *dma) { - if (unlikely(__otx2_alloc_rbuf(pfvf, cq->rbpool, dma))) + if (unlikely(__otx2_alloc_rbuf(pfvf, cq->rbpool, dma, + cq->cq_idx, cq->pool_ptrs - 1))) return -ENOMEM; return 0; } @@ -884,7 +893,7 @@ void otx2_sqb_flush(struct otx2_nic *pfvf) #define RQ_PASS_LVL_AURA (255 - ((95 * 256) / 100)) /* RED when 95% is full */ #define RQ_DROP_LVL_AURA (255 - ((99 * 256) / 100)) /* Drop when 99% is full */ -static int otx2_rq_init(struct otx2_nic *pfvf, u16 qidx, u16 lpb_aura) +int otx2_rq_init(struct otx2_nic *pfvf, u16 qidx, u16 lpb_aura) { struct otx2_qset *qset = &pfvf->qset; struct nix_aq_enq_req *aq; @@ -1028,6 +1037,10 @@ int otx2_sq_init(struct otx2_nic *pfvf, u16 qidx, u16 sqb_aura) sq->stats.bytes = 0; sq->stats.pkts = 0; + /* Attach XSK_BUFF_POOL to XDP queue */ + if (qidx > pfvf->hw.xdp_queues) + otx2_attach_xsk_buff(pfvf, sq, (qidx - pfvf->hw.xdp_queues)); + chan_offset = qidx % pfvf->hw.tx_chan_cnt; err = pfvf->hw_ops->sq_aq_init(pfvf, qidx, chan_offset, sqb_aura); @@ -1041,12 +1054,13 @@ int otx2_sq_init(struct otx2_nic *pfvf, u16 qidx, u16 sqb_aura) } -static int otx2_cq_init(struct otx2_nic *pfvf, u16 qidx) +int otx2_cq_init(struct otx2_nic *pfvf, u16 qidx) { struct otx2_qset *qset = &pfvf->qset; int err, pool_id, non_xdp_queues; struct nix_aq_enq_req *aq; struct otx2_cq_queue *cq; + struct otx2_pool *pool; cq = &qset->cq[qidx]; cq->cq_idx = qidx; @@ -1055,8 +1069,20 @@ static int otx2_cq_init(struct otx2_nic *pfvf, u16 qidx) cq->cq_type = CQ_RX; cq->cint_idx = qidx; cq->cqe_cnt = qset->rqe_cnt; - if (pfvf->xdp_prog) + if (pfvf->xdp_prog) { xdp_rxq_info_reg(&cq->xdp_rxq, pfvf->netdev, qidx, 0); + pool = &qset->pool[qidx]; + if (pool->xsk_pool) { + xdp_rxq_info_reg_mem_model(&cq->xdp_rxq, + MEM_TYPE_XSK_BUFF_POOL, + NULL); + xsk_pool_set_rxq_info(pool->xsk_pool, &cq->xdp_rxq); + } else if (pool->page_pool) { + xdp_rxq_info_reg_mem_model(&cq->xdp_rxq, + MEM_TYPE_PAGE_POOL, + pool->page_pool); + } + } } else if (qidx < non_xdp_queues) { cq->cq_type = CQ_TX; cq->cint_idx = qidx - pfvf->hw.rx_queues; @@ -1275,9 +1301,10 @@ void otx2_free_bufs(struct otx2_nic *pfvf, struct otx2_pool *pool, pa = otx2_iova_to_phys(pfvf->iommu_domain, iova); page = virt_to_head_page(phys_to_virt(pa)); - if (pool->page_pool) { page_pool_put_full_page(pool->page_pool, page, true); + } else if (pool->xsk_pool) { + /* Note: No way of identifying xdp_buff */ } else { dma_unmap_page_attrs(pfvf->dev, iova, size, DMA_FROM_DEVICE, @@ -1292,6 +1319,7 @@ void otx2_free_aura_ptr(struct otx2_nic *pfvf, int type) int pool_id, pool_start = 0, pool_end = 0, size = 0; struct otx2_pool *pool; u64 iova; + int idx; if (type == AURA_NIX_SQ) { pool_start = otx2_get_pool_idx(pfvf, type, 0); @@ -1306,16 +1334,21 @@ void otx2_free_aura_ptr(struct otx2_nic *pfvf, int type) /* Free SQB and RQB pointers from the aura pool */ for (pool_id = pool_start; pool_id < pool_end; pool_id++) { - iova = otx2_aura_allocptr(pfvf, pool_id); pool = &pfvf->qset.pool[pool_id]; + iova = otx2_aura_allocptr(pfvf, pool_id); while (iova) { if (type == AURA_NIX_RQ) iova -= OTX2_HEAD_ROOM; - otx2_free_bufs(pfvf, pool, iova, size); - iova = otx2_aura_allocptr(pfvf, pool_id); } + + for (idx = 0 ; idx < pool->xdp_cnt; idx++) { + if (!pool->xdp[idx]) + continue; + + xsk_buff_free(pool->xdp[idx]); + } } } @@ -1332,7 +1365,8 @@ void otx2_aura_pool_free(struct otx2_nic *pfvf) qmem_free(pfvf->dev, pool->stack); qmem_free(pfvf->dev, pool->fc_addr); page_pool_destroy(pool->page_pool); - pool->page_pool = NULL; + devm_kfree(pfvf->dev, pool->xdp); + pool->xsk_pool = NULL; } devm_kfree(pfvf->dev, pfvf->qset.pool); pfvf->qset.pool = NULL; @@ -1419,6 +1453,7 @@ int otx2_pool_init(struct otx2_nic *pfvf, u16 pool_id, int stack_pages, int numptrs, int buf_size, int type) { struct page_pool_params pp_params = { 0 }; + struct xsk_buff_pool *xsk_pool; struct npa_aq_enq_req *aq; struct otx2_pool *pool; int err; @@ -1462,21 +1497,35 @@ int otx2_pool_init(struct otx2_nic *pfvf, u16 pool_id, aq->ctype = NPA_AQ_CTYPE_POOL; aq->op = NPA_AQ_INSTOP_INIT; - if (type != AURA_NIX_RQ) { - pool->page_pool = NULL; + if (type != AURA_NIX_RQ) + return 0; + + if (!test_bit(pool_id, pfvf->af_xdp_zc_qidx)) { + pp_params.order = get_order(buf_size); + pp_params.flags = PP_FLAG_DMA_MAP; + pp_params.pool_size = min(OTX2_PAGE_POOL_SZ, numptrs); + pp_params.nid = NUMA_NO_NODE; + pp_params.dev = pfvf->dev; + pp_params.dma_dir = DMA_FROM_DEVICE; + pool->page_pool = page_pool_create(&pp_params); + if (IS_ERR(pool->page_pool)) { + netdev_err(pfvf->netdev, "Creation of page pool failed\n"); + return PTR_ERR(pool->page_pool); + } return 0; } - pp_params.order = get_order(buf_size); - pp_params.flags = PP_FLAG_DMA_MAP; - pp_params.pool_size = min(OTX2_PAGE_POOL_SZ, numptrs); - pp_params.nid = NUMA_NO_NODE; - pp_params.dev = pfvf->dev; - pp_params.dma_dir = DMA_FROM_DEVICE; - pool->page_pool = page_pool_create(&pp_params); - if (IS_ERR(pool->page_pool)) { - netdev_err(pfvf->netdev, "Creation of page pool failed\n"); - return PTR_ERR(pool->page_pool); + /* Set XSK pool to support AF_XDP zero-copy */ + xsk_pool = xsk_get_pool_from_qid(pfvf->netdev, pool_id); + if (xsk_pool) { + pool->xsk_pool = xsk_pool; + pool->xdp_cnt = numptrs; + pool->xdp = devm_kcalloc(pfvf->dev, + numptrs, sizeof(struct xdp_buff *), GFP_KERNEL); + if (IS_ERR(pool->xdp)) { + netdev_err(pfvf->netdev, "Creation of xsk pool failed\n"); + return PTR_ERR(pool->xdp); + } } return 0; @@ -1537,9 +1586,18 @@ int otx2_sq_aura_pool_init(struct otx2_nic *pfvf) } for (ptr = 0; ptr < num_sqbs; ptr++) { - err = otx2_alloc_rbuf(pfvf, pool, &bufptr); - if (err) + err = otx2_alloc_rbuf(pfvf, pool, &bufptr, pool_id, ptr); + if (err) { + if (pool->xsk_pool) { + ptr--; + while (ptr >= 0) { + xsk_buff_free(pool->xdp[ptr]); + ptr--; + } + } goto err_mem; + } + pfvf->hw_ops->aura_freeptr(pfvf, pool_id, bufptr); sq->sqb_ptrs[sq->sqb_count++] = (u64)bufptr; } @@ -1589,11 +1647,19 @@ int otx2_rq_aura_pool_init(struct otx2_nic *pfvf) /* Allocate pointers and free them to aura/pool */ for (pool_id = 0; pool_id < hw->rqpool_cnt; pool_id++) { pool = &pfvf->qset.pool[pool_id]; + for (ptr = 0; ptr < num_ptrs; ptr++) { - err = otx2_alloc_rbuf(pfvf, pool, &bufptr); - if (err) + err = otx2_alloc_rbuf(pfvf, pool, &bufptr, pool_id, ptr); + if (err) { + if (pool->xsk_pool) { + while (ptr) + xsk_buff_free(pool->xdp[--ptr]); + } return -ENOMEM; + } + pfvf->hw_ops->aura_freeptr(pfvf, pool_id, + pool->xsk_pool ? bufptr : bufptr + OTX2_HEAD_ROOM); } } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h index 65814e3dc93f..1e88422825be 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h @@ -21,6 +21,7 @@ #include <linux/time64.h> #include <linux/dim.h> #include <uapi/linux/if_macsec.h> +#include <net/page_pool/helpers.h> #include <mbox.h> #include <npc.h> @@ -128,6 +129,12 @@ enum otx2_errcodes_re { ERRCODE_IL4_CSUM = 0x22, }; +enum otx2_xdp_action { + OTX2_XDP_TX = BIT(0), + OTX2_XDP_REDIRECT = BIT(1), + OTX2_AF_XDP_FRAME = BIT(2), +}; + struct otx2_dev_stats { u64 rx_bytes; u64 rx_frames; @@ -531,6 +538,8 @@ struct otx2_nic { /* Inline ipsec */ struct cn10k_ipsec ipsec; + /* af_xdp zero-copy */ + unsigned long *af_xdp_zc_qidx; }; static inline bool is_otx2_lbkvf(struct pci_dev *pdev) @@ -1002,7 +1011,7 @@ void otx2_txschq_free_one(struct otx2_nic *pfvf, u16 lvl, u16 schq); void otx2_free_pending_sqe(struct otx2_nic *pfvf); void otx2_sqb_flush(struct otx2_nic *pfvf); int otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool, - dma_addr_t *dma); + dma_addr_t *dma, int qidx, int idx); int otx2_rxtx_enable(struct otx2_nic *pfvf, bool enable); void otx2_ctx_disable(struct mbox *mbox, int type, bool npa); int otx2_nix_config_bp(struct otx2_nic *pfvf, bool enable); @@ -1032,6 +1041,8 @@ void otx2_pfaf_mbox_destroy(struct otx2_nic *pf); void otx2_disable_mbox_intr(struct otx2_nic *pf); void otx2_disable_napi(struct otx2_nic *pf); irqreturn_t otx2_cq_intr_handler(int irq, void *cq_irq); +int otx2_rq_init(struct otx2_nic *pfvf, u16 qidx, u16 lpb_aura); +int otx2_cq_init(struct otx2_nic *pfvf, u16 qidx); /* RSS configuration APIs*/ int otx2_rss_init(struct otx2_nic *pfvf); @@ -1094,7 +1105,8 @@ int otx2_del_macfilter(struct net_device *netdev, const u8 *mac); int otx2_add_macfilter(struct net_device *netdev, const u8 *mac); int otx2_enable_rxvlan(struct otx2_nic *pf, bool enable); int otx2_install_rxvlan_offload_flow(struct otx2_nic *pfvf); -bool otx2_xdp_sq_append_pkt(struct otx2_nic *pfvf, u64 iova, int len, u16 qidx); +bool otx2_xdp_sq_append_pkt(struct otx2_nic *pfvf, struct xdp_frame *xdpf, + u64 iova, int len, u16 qidx, u16 flags); u16 otx2_get_max_mtu(struct otx2_nic *pfvf); int otx2_handle_ntuple_tc_features(struct net_device *netdev, netdev_features_t features); @@ -1175,4 +1187,5 @@ static inline int mcam_entry_cmp(const void *a, const void *b) dma_addr_t otx2_dma_map_skb_frag(struct otx2_nic *pfvf, struct sk_buff *skb, int seg, int *len); void otx2_dma_unmap_skb_frags(struct otx2_nic *pfvf, struct sg_list *sg); +int otx2_read_free_sqe(struct otx2_nic *pfvf, u16 qidx); #endif /* OTX2_COMMON_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c index 2d53dc77ef1e..010385b29988 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c @@ -910,8 +910,12 @@ static int otx2_get_rxfh(struct net_device *dev, return -ENOENT; if (indir) { - for (idx = 0; idx < rss->rss_size; idx++) + for (idx = 0; idx < rss->rss_size; idx++) { + /* Ignore if the rx queue is AF_XDP zero copy enabled */ + if (test_bit(rss_ctx->ind_tbl[idx], pfvf->af_xdp_zc_qidx)) + continue; indir[idx] = rss_ctx->ind_tbl[idx]; + } } if (rxfh->key) memcpy(rxfh->key, rss->key, sizeof(rss->key)); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index e1dde93e8af8..cfed9ec5b157 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -27,6 +27,7 @@ #include "qos.h" #include <rvu_trace.h> #include "cn10k_ipsec.h" +#include "otx2_xsk.h" #define DRV_NAME "rvu_nicpf" #define DRV_STRING "Marvell RVU NIC Physical Function Driver" @@ -1662,9 +1663,7 @@ void otx2_free_hw_resources(struct otx2_nic *pf) struct nix_lf_free_req *free_req; struct mbox *mbox = &pf->mbox; struct otx2_cq_queue *cq; - struct otx2_pool *pool; struct msg_req *req; - int pool_id; int qidx; /* Ensure all SQE are processed */ @@ -1705,13 +1704,6 @@ void otx2_free_hw_resources(struct otx2_nic *pf) /* Free RQ buffer pointers*/ otx2_free_aura_ptr(pf, AURA_NIX_RQ); - for (qidx = 0; qidx < pf->hw.rx_queues; qidx++) { - pool_id = otx2_get_pool_idx(pf, AURA_NIX_RQ, qidx); - pool = &pf->qset.pool[pool_id]; - page_pool_destroy(pool->page_pool); - pool->page_pool = NULL; - } - otx2_free_cq_res(pf); /* Free all ingress bandwidth profiles allocated */ @@ -2691,7 +2683,6 @@ static int otx2_get_vf_config(struct net_device *netdev, int vf, static int otx2_xdp_xmit_tx(struct otx2_nic *pf, struct xdp_frame *xdpf, int qidx) { - struct page *page; u64 dma_addr; int err = 0; @@ -2701,11 +2692,11 @@ static int otx2_xdp_xmit_tx(struct otx2_nic *pf, struct xdp_frame *xdpf, if (dma_mapping_error(pf->dev, dma_addr)) return -ENOMEM; - err = otx2_xdp_sq_append_pkt(pf, dma_addr, xdpf->len, qidx); + err = otx2_xdp_sq_append_pkt(pf, xdpf, dma_addr, xdpf->len, + qidx, OTX2_XDP_REDIRECT); if (!err) { otx2_dma_unmap_page(pf, dma_addr, xdpf->len, DMA_TO_DEVICE); - page = virt_to_page(xdpf->data); - put_page(page); + xdp_return_frame(xdpf); return -ENOMEM; } return 0; @@ -2789,6 +2780,8 @@ static int otx2_xdp(struct net_device *netdev, struct netdev_bpf *xdp) switch (xdp->command) { case XDP_SETUP_PROG: return otx2_xdp_setup(pf, xdp->prog); + case XDP_SETUP_XSK_POOL: + return otx2_xsk_pool_setup(pf, xdp->xsk.pool, xdp->xsk.queue_id); default: return -EINVAL; } @@ -2866,6 +2859,7 @@ static const struct net_device_ops otx2_netdev_ops = { .ndo_set_vf_vlan = otx2_set_vf_vlan, .ndo_get_vf_config = otx2_get_vf_config, .ndo_bpf = otx2_xdp, + .ndo_xsk_wakeup = otx2_xsk_wakeup, .ndo_xdp_xmit = otx2_xdp_xmit, .ndo_setup_tc = otx2_setup_tc, .ndo_set_vf_trust = otx2_ndo_set_vf_trust, @@ -3204,16 +3198,28 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id) /* Enable link notifications */ otx2_cgx_config_linkevents(pf, true); + pf->af_xdp_zc_qidx = bitmap_zalloc(qcount, GFP_KERNEL); + if (!pf->af_xdp_zc_qidx) { + err = -ENOMEM; + goto err_sriov_cleannup; + } + #ifdef CONFIG_DCB err = otx2_dcbnl_set_ops(netdev); if (err) - goto err_pf_sriov_init; + goto err_free_zc_bmap; #endif otx2_qos_init(pf, qos_txqs); return 0; +#ifdef CONFIG_DCB +err_free_zc_bmap: + bitmap_free(pf->af_xdp_zc_qidx); +#endif +err_sriov_cleannup: + otx2_sriov_vfcfg_cleanup(pf); err_pf_sriov_init: otx2_shutdown_tc(pf); err_mcam_flow_del: diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c index 224cef938927..6bc5ce5a9f61 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c @@ -12,6 +12,7 @@ #include <linux/bpf_trace.h> #include <net/ip6_checksum.h> #include <net/xfrm.h> +#include <net/xdp.h> #include "otx2_reg.h" #include "otx2_common.h" @@ -19,6 +20,7 @@ #include "otx2_txrx.h" #include "otx2_ptp.h" #include "cn10k.h" +#include "otx2_xsk.h" #define CQE_ADDR(CQ, idx) ((CQ)->cqe_base + ((CQ)->cqe_size * (idx))) #define PTP_PORT 0x13F @@ -29,6 +31,12 @@ DEFINE_STATIC_KEY_FALSE(cn10k_ipsec_sa_enabled); +static int otx2_get_free_sqe(struct otx2_snd_queue *sq) +{ + return (sq->cons_head - sq->head - 1 + sq->sqe_cnt) + & (sq->sqe_cnt - 1); +} + static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf, struct bpf_prog *prog, struct nix_cqe_rx_s *cqe, @@ -96,20 +104,22 @@ static unsigned int frag_num(unsigned int i) static void otx2_xdp_snd_pkt_handler(struct otx2_nic *pfvf, struct otx2_snd_queue *sq, - struct nix_cqe_tx_s *cqe) + struct nix_cqe_tx_s *cqe, + int *xsk_frames) { struct nix_send_comp_s *snd_comp = &cqe->comp; struct sg_list *sg; - struct page *page; - u64 pa; sg = &sq->sg[snd_comp->sqe_id]; + if (sg->flags & OTX2_AF_XDP_FRAME) { + (*xsk_frames)++; + return; + } - pa = otx2_iova_to_phys(pfvf->iommu_domain, sg->dma_addr[0]); - otx2_dma_unmap_page(pfvf, sg->dma_addr[0], - sg->size[0], DMA_TO_DEVICE); - page = virt_to_page(phys_to_virt(pa)); - put_page(page); + if (sg->flags & OTX2_XDP_REDIRECT) + otx2_dma_unmap_page(pfvf, sg->dma_addr[0], sg->size[0], DMA_TO_DEVICE); + xdp_return_frame((struct xdp_frame *)sg->skb); + sg->skb = (u64)NULL; } static void otx2_snd_pkt_handler(struct otx2_nic *pfvf, @@ -431,6 +441,18 @@ int otx2_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq) return cnt - cq->pool_ptrs; } +static void otx2_zc_submit_pkts(struct otx2_nic *pfvf, struct xsk_buff_pool *xsk_pool, + int *xsk_frames, int qidx, int budget) +{ + if (*xsk_frames) + xsk_tx_completed(xsk_pool, *xsk_frames); + + if (xsk_uses_need_wakeup(xsk_pool)) + xsk_set_tx_need_wakeup(xsk_pool); + + otx2_zc_napi_handler(pfvf, xsk_pool, qidx, budget); +} + static int otx2_tx_napi_handler(struct otx2_nic *pfvf, struct otx2_cq_queue *cq, int budget) { @@ -439,16 +461,22 @@ static int otx2_tx_napi_handler(struct otx2_nic *pfvf, struct nix_cqe_tx_s *cqe; struct net_device *ndev; int processed_cqe = 0; + int xsk_frames = 0; + + qidx = cq->cq_idx - pfvf->hw.rx_queues; + sq = &pfvf->qset.sq[qidx]; if (cq->pend_cqe >= budget) goto process_cqe; - if (otx2_nix_cq_op_status(pfvf, cq) || !cq->pend_cqe) + if (otx2_nix_cq_op_status(pfvf, cq) || !cq->pend_cqe) { + if (sq->xsk_pool) + otx2_zc_submit_pkts(pfvf, sq->xsk_pool, &xsk_frames, + qidx, budget); return 0; + } process_cqe: - qidx = cq->cq_idx - pfvf->hw.rx_queues; - sq = &pfvf->qset.sq[qidx]; while (likely(processed_cqe < budget) && cq->pend_cqe) { cqe = (struct nix_cqe_tx_s *)otx2_get_next_cqe(cq); @@ -458,10 +486,8 @@ process_cqe: break; } - qidx = cq->cq_idx - pfvf->hw.rx_queues; - if (cq->cq_type == CQ_XDP) - otx2_xdp_snd_pkt_handler(pfvf, sq, cqe); + otx2_xdp_snd_pkt_handler(pfvf, sq, cqe, &xsk_frames); else otx2_snd_pkt_handler(pfvf, cq, &pfvf->qset.sq[qidx], cqe, budget, &tx_pkts, &tx_bytes); @@ -502,6 +528,10 @@ process_cqe: netif_carrier_ok(ndev)) netif_tx_wake_queue(txq); } + + if (sq->xsk_pool) + otx2_zc_submit_pkts(pfvf, sq->xsk_pool, &xsk_frames, qidx, budget); + return 0; } @@ -527,9 +557,10 @@ static void otx2_adjust_adaptive_coalese(struct otx2_nic *pfvf, struct otx2_cq_p int otx2_napi_handler(struct napi_struct *napi, int budget) { struct otx2_cq_queue *rx_cq = NULL; + struct otx2_cq_queue *cq = NULL; + struct otx2_pool *pool = NULL; struct otx2_cq_poll *cq_poll; int workdone = 0, cq_idx, i; - struct otx2_cq_queue *cq; struct otx2_qset *qset; struct otx2_nic *pfvf; int filled_cnt = -1; @@ -554,6 +585,7 @@ int otx2_napi_handler(struct napi_struct *napi, int budget) if (rx_cq && rx_cq->pool_ptrs) filled_cnt = pfvf->hw_ops->refill_pool_ptrs(pfvf, rx_cq); + /* Clear the IRQ */ otx2_write64(pfvf, NIX_LF_CINTX_INT(cq_poll->cint_idx), BIT_ULL(0)); @@ -566,20 +598,31 @@ int otx2_napi_handler(struct napi_struct *napi, int budget) if (pfvf->flags & OTX2_FLAG_ADPTV_INT_COAL_ENABLED) otx2_adjust_adaptive_coalese(pfvf, cq_poll); + if (likely(cq)) + pool = &pfvf->qset.pool[cq->cq_idx]; + if (unlikely(!filled_cnt)) { struct refill_work *work; struct delayed_work *dwork; - work = &pfvf->refill_wrk[cq->cq_idx]; - dwork = &work->pool_refill_work; - /* Schedule a task if no other task is running */ - if (!cq->refill_task_sched) { - work->napi = napi; - cq->refill_task_sched = true; - schedule_delayed_work(dwork, - msecs_to_jiffies(100)); + if (likely(cq)) { + work = &pfvf->refill_wrk[cq->cq_idx]; + dwork = &work->pool_refill_work; + /* Schedule a task if no other task is running */ + if (!cq->refill_task_sched) { + work->napi = napi; + cq->refill_task_sched = true; + schedule_delayed_work(dwork, + msecs_to_jiffies(100)); + } + /* Call wake-up for not able to fill buffers */ + if (pool->xsk_pool) + xsk_set_rx_need_wakeup(pool->xsk_pool); } } else { + /* Clear wake-up, since buffers are filled successfully */ + if (pool && pool->xsk_pool) + xsk_clear_rx_need_wakeup(pool->xsk_pool); /* Re-enable interrupts */ otx2_write64(pfvf, NIX_LF_CINTX_ENA_W1S(cq_poll->cint_idx), @@ -1147,7 +1190,7 @@ bool otx2_sq_append_skb(void *dev, struct netdev_queue *txq, /* Check if there is enough room between producer * and consumer index. */ - free_desc = (sq->cons_head - sq->head - 1 + sq->sqe_cnt) & (sq->sqe_cnt - 1); + free_desc = otx2_get_free_sqe(sq); if (free_desc < sq->sqe_thresh) return false; @@ -1230,15 +1273,19 @@ void otx2_cleanup_rx_cqes(struct otx2_nic *pfvf, struct otx2_cq_queue *cq, int q u16 pool_id; u64 iova; - if (pfvf->xdp_prog) + pool_id = otx2_get_pool_idx(pfvf, AURA_NIX_RQ, qidx); + pool = &pfvf->qset.pool[pool_id]; + + if (pfvf->xdp_prog) { + if (pool->page_pool) + xdp_rxq_info_unreg_mem_model(&cq->xdp_rxq); + xdp_rxq_info_unreg(&cq->xdp_rxq); + } if (otx2_nix_cq_op_status(pfvf, cq) || !cq->pend_cqe) return; - pool_id = otx2_get_pool_idx(pfvf, AURA_NIX_RQ, qidx); - pool = &pfvf->qset.pool[pool_id]; - while (cq->pend_cqe) { cqe = (struct nix_cqe_rx_s *)otx2_get_next_cqe(cq); processed_cqe++; @@ -1359,8 +1406,9 @@ void otx2_free_pending_sqe(struct otx2_nic *pfvf) } } -static void otx2_xdp_sqe_add_sg(struct otx2_snd_queue *sq, u64 dma_addr, - int len, int *offset) +static void otx2_xdp_sqe_add_sg(struct otx2_snd_queue *sq, + struct xdp_frame *xdpf, + u64 dma_addr, int len, int *offset, u16 flags) { struct nix_sqe_sg_s *sg = NULL; u64 *iova = NULL; @@ -1377,16 +1425,34 @@ static void otx2_xdp_sqe_add_sg(struct otx2_snd_queue *sq, u64 dma_addr, sq->sg[sq->head].dma_addr[0] = dma_addr; sq->sg[sq->head].size[0] = len; sq->sg[sq->head].num_segs = 1; + sq->sg[sq->head].flags = flags; + sq->sg[sq->head].skb = (u64)xdpf; } -bool otx2_xdp_sq_append_pkt(struct otx2_nic *pfvf, u64 iova, int len, u16 qidx) +int otx2_read_free_sqe(struct otx2_nic *pfvf, u16 qidx) +{ + struct otx2_snd_queue *sq; + int free_sqe; + + sq = &pfvf->qset.sq[qidx]; + free_sqe = otx2_get_free_sqe(sq); + if (free_sqe < sq->sqe_thresh) { + netdev_warn(pfvf->netdev, "No free sqe for Send queue%d\n", qidx); + return 0; + } + + return free_sqe - sq->sqe_thresh; +} + +bool otx2_xdp_sq_append_pkt(struct otx2_nic *pfvf, struct xdp_frame *xdpf, + u64 iova, int len, u16 qidx, u16 flags) { struct nix_sqe_hdr_s *sqe_hdr; struct otx2_snd_queue *sq; int offset, free_sqe; sq = &pfvf->qset.sq[qidx]; - free_sqe = (sq->num_sqbs - *sq->aura_fc_addr) * sq->sqe_per_sqb; + free_sqe = otx2_get_free_sqe(sq); if (free_sqe < sq->sqe_thresh) return false; @@ -1405,7 +1471,7 @@ bool otx2_xdp_sq_append_pkt(struct otx2_nic *pfvf, u64 iova, int len, u16 qidx) offset = sizeof(*sqe_hdr); - otx2_xdp_sqe_add_sg(sq, iova, len, &offset); + otx2_xdp_sqe_add_sg(sq, xdpf, iova, len, &offset, flags); sqe_hdr->sizem1 = (offset / 16) - 1; pfvf->hw_ops->sqe_flush(pfvf, sq, offset, qidx); @@ -1418,14 +1484,28 @@ static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf, struct otx2_cq_queue *cq, bool *need_xdp_flush) { + struct xdp_buff xdp, *xsk_buff = NULL; unsigned char *hard_start; + struct otx2_pool *pool; + struct xdp_frame *xdpf; int qidx = cq->cq_idx; - struct xdp_buff xdp; struct page *page; u64 iova, pa; u32 act; int err; + pool = &pfvf->qset.pool[qidx]; + + if (pool->xsk_pool) { + xsk_buff = pool->xdp[--cq->rbpool->xdp_top]; + if (!xsk_buff) + return false; + + xsk_buff->data_end = xsk_buff->data + cqe->sg.seg_size; + act = bpf_prog_run_xdp(prog, xsk_buff); + goto handle_xdp_verdict; + } + iova = cqe->sg.seg_addr - OTX2_HEAD_ROOM; pa = otx2_iova_to_phys(pfvf->iommu_domain, iova); page = virt_to_page(phys_to_virt(pa)); @@ -1438,37 +1518,59 @@ static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf, act = bpf_prog_run_xdp(prog, &xdp); +handle_xdp_verdict: switch (act) { case XDP_PASS: break; case XDP_TX: qidx += pfvf->hw.tx_queues; cq->pool_ptrs++; - return otx2_xdp_sq_append_pkt(pfvf, iova, - cqe->sg.seg_size, qidx); + xdpf = xdp_convert_buff_to_frame(&xdp); + return otx2_xdp_sq_append_pkt(pfvf, xdpf, + cqe->sg.seg_addr, + cqe->sg.seg_size, + qidx, OTX2_XDP_TX); case XDP_REDIRECT: cq->pool_ptrs++; - err = xdp_do_redirect(pfvf->netdev, &xdp, prog); + if (xsk_buff) { + err = xdp_do_redirect(pfvf->netdev, xsk_buff, prog); + if (!err) { + *need_xdp_flush = true; + return true; + } + return false; + } - otx2_dma_unmap_page(pfvf, iova, pfvf->rbsize, - DMA_FROM_DEVICE); + err = xdp_do_redirect(pfvf->netdev, &xdp, prog); if (!err) { *need_xdp_flush = true; return true; } - put_page(page); + + otx2_dma_unmap_page(pfvf, iova, pfvf->rbsize, + DMA_FROM_DEVICE); + xdpf = xdp_convert_buff_to_frame(&xdp); + xdp_return_frame(xdpf); break; default: bpf_warn_invalid_xdp_action(pfvf->netdev, prog, act); break; case XDP_ABORTED: + if (xsk_buff) + xsk_buff_free(xsk_buff); trace_xdp_exception(pfvf->netdev, prog, act); break; case XDP_DROP: - otx2_dma_unmap_page(pfvf, iova, pfvf->rbsize, - DMA_FROM_DEVICE); - put_page(page); cq->pool_ptrs++; + if (xsk_buff) { + xsk_buff_free(xsk_buff); + } else if (page->pp) { + page_pool_recycle_direct(pool->page_pool, page); + } else { + otx2_dma_unmap_page(pfvf, iova, pfvf->rbsize, + DMA_FROM_DEVICE); + put_page(page); + } return true; } return false; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h index d23810963fdb..acf259d72008 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h @@ -12,6 +12,7 @@ #include <linux/iommu.h> #include <linux/if_vlan.h> #include <net/xdp.h> +#include <net/xdp_sock_drv.h> #define LBK_CHAN_BASE 0x000 #define SDP_CHAN_BASE 0x700 @@ -76,6 +77,7 @@ struct otx2_rcv_queue { struct sg_list { u16 num_segs; + u16 flags; u64 skb; u64 size[OTX2_MAX_FRAGS_IN_SQE]; u64 dma_addr[OTX2_MAX_FRAGS_IN_SQE]; @@ -104,6 +106,8 @@ struct otx2_snd_queue { /* SQE ring and CPT response queue for Inline IPSEC */ struct qmem *sqe_ring; struct qmem *cpt_resp; + /* Buffer pool for af_xdp zero-copy */ + struct xsk_buff_pool *xsk_pool; } ____cacheline_aligned_in_smp; enum cq_type { @@ -127,7 +131,11 @@ struct otx2_pool { struct qmem *stack; struct qmem *fc_addr; struct page_pool *page_pool; + struct xsk_buff_pool *xsk_pool; + struct xdp_buff **xdp; + u16 xdp_cnt; u16 rbsize; + u16 xdp_top; }; struct otx2_cq_queue { @@ -144,6 +152,7 @@ struct otx2_cq_queue { void *cqe_base; struct qmem *cqe; struct otx2_pool *rbpool; + bool xsk_zc_en; struct xdp_rxq_info xdp_rxq; } ____cacheline_aligned_in_smp; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c index e926c6ce96cf..7ef3ba477d49 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c @@ -722,15 +722,27 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (err) goto err_shutdown_tc; + vf->af_xdp_zc_qidx = bitmap_zalloc(qcount, GFP_KERNEL); + if (!vf->af_xdp_zc_qidx) { + err = -ENOMEM; + goto err_unreg_devlink; + } + #ifdef CONFIG_DCB err = otx2_dcbnl_set_ops(netdev); if (err) - goto err_shutdown_tc; + goto err_free_zc_bmap; #endif otx2_qos_init(vf, qos_txqs); return 0; +#ifdef CONFIG_DCB +err_free_zc_bmap: + bitmap_free(vf->af_xdp_zc_qidx); +#endif +err_unreg_devlink: + otx2_unregister_dl(vf); err_shutdown_tc: otx2_shutdown_tc(vf); err_unreg_netdev: diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_xsk.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_xsk.c new file mode 100644 index 000000000000..ce10caea8511 --- /dev/null +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_xsk.c @@ -0,0 +1,225 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Marvell RVU Ethernet driver + * + * Copyright (C) 2024 Marvell. + * + */ + +#include <linux/bpf_trace.h> +#include <linux/stringify.h> +#include <net/xdp_sock_drv.h> +#include <net/xdp.h> + +#include "otx2_common.h" +#include "otx2_xsk.h" + +int otx2_xsk_pool_alloc_buf(struct otx2_nic *pfvf, struct otx2_pool *pool, + dma_addr_t *dma, int idx) +{ + struct xdp_buff *xdp; + int delta; + + xdp = xsk_buff_alloc(pool->xsk_pool); + if (!xdp) + return -ENOMEM; + + pool->xdp[pool->xdp_top++] = xdp; + *dma = OTX2_DATA_ALIGN(xsk_buff_xdp_get_dma(xdp)); + /* Adjust xdp->data for unaligned addresses */ + delta = *dma - xsk_buff_xdp_get_dma(xdp); + xdp->data += delta; + + return 0; +} + +static int otx2_xsk_ctx_disable(struct otx2_nic *pfvf, u16 qidx, int aura_id) +{ + struct nix_cn10k_aq_enq_req *cn10k_rq_aq; + struct npa_aq_enq_req *aura_aq; + struct npa_aq_enq_req *pool_aq; + struct nix_aq_enq_req *rq_aq; + + if (test_bit(CN10K_LMTST, &pfvf->hw.cap_flag)) { + cn10k_rq_aq = otx2_mbox_alloc_msg_nix_cn10k_aq_enq(&pfvf->mbox); + if (!cn10k_rq_aq) + return -ENOMEM; + cn10k_rq_aq->qidx = qidx; + cn10k_rq_aq->rq.ena = 0; + cn10k_rq_aq->rq_mask.ena = 1; + cn10k_rq_aq->ctype = NIX_AQ_CTYPE_RQ; + cn10k_rq_aq->op = NIX_AQ_INSTOP_WRITE; + } else { + rq_aq = otx2_mbox_alloc_msg_nix_aq_enq(&pfvf->mbox); + if (!rq_aq) + return -ENOMEM; + rq_aq->qidx = qidx; + rq_aq->sq.ena = 0; + rq_aq->sq_mask.ena = 1; + rq_aq->ctype = NIX_AQ_CTYPE_RQ; + rq_aq->op = NIX_AQ_INSTOP_WRITE; + } + + aura_aq = otx2_mbox_alloc_msg_npa_aq_enq(&pfvf->mbox); + if (!aura_aq) + goto fail; + + aura_aq->aura_id = aura_id; + aura_aq->aura.ena = 0; + aura_aq->aura_mask.ena = 1; + aura_aq->ctype = NPA_AQ_CTYPE_AURA; + aura_aq->op = NPA_AQ_INSTOP_WRITE; + + pool_aq = otx2_mbox_alloc_msg_npa_aq_enq(&pfvf->mbox); + if (!pool_aq) + goto fail; + + pool_aq->aura_id = aura_id; + pool_aq->pool.ena = 0; + pool_aq->pool_mask.ena = 1; + + pool_aq->ctype = NPA_AQ_CTYPE_POOL; + pool_aq->op = NPA_AQ_INSTOP_WRITE; + + return otx2_sync_mbox_msg(&pfvf->mbox); + +fail: + otx2_mbox_reset(&pfvf->mbox.mbox, 0); + return -ENOMEM; +} + +static void otx2_clean_up_rq(struct otx2_nic *pfvf, int qidx) +{ + struct otx2_qset *qset = &pfvf->qset; + struct otx2_cq_queue *cq; + struct otx2_pool *pool; + u64 iova; + + /* If the DOWN flag is set SQs are already freed */ + if (pfvf->flags & OTX2_FLAG_INTF_DOWN) + return; + + cq = &qset->cq[qidx]; + if (cq) + otx2_cleanup_rx_cqes(pfvf, cq, qidx); + + pool = &pfvf->qset.pool[qidx]; + iova = otx2_aura_allocptr(pfvf, qidx); + while (iova) { + iova -= OTX2_HEAD_ROOM; + otx2_free_bufs(pfvf, pool, iova, pfvf->rbsize); + iova = otx2_aura_allocptr(pfvf, qidx); + } + + mutex_lock(&pfvf->mbox.lock); + otx2_xsk_ctx_disable(pfvf, qidx, qidx); + mutex_unlock(&pfvf->mbox.lock); +} + +int otx2_xsk_pool_enable(struct otx2_nic *pf, struct xsk_buff_pool *pool, u16 qidx) +{ + u16 rx_queues = pf->hw.rx_queues; + u16 tx_queues = pf->hw.tx_queues; + int err; + + if (qidx >= rx_queues || qidx >= tx_queues) + return -EINVAL; + + err = xsk_pool_dma_map(pool, pf->dev, DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING); + if (err) + return err; + + set_bit(qidx, pf->af_xdp_zc_qidx); + otx2_clean_up_rq(pf, qidx); + /* Reconfigure RSS table as 'qidx' cannot be part of RSS now */ + otx2_set_rss_table(pf, DEFAULT_RSS_CONTEXT_GROUP); + /* Kick start the NAPI context so that receiving will start */ + return otx2_xsk_wakeup(pf->netdev, qidx, XDP_WAKEUP_RX); +} + +int otx2_xsk_pool_disable(struct otx2_nic *pf, u16 qidx) +{ + struct net_device *netdev = pf->netdev; + struct xsk_buff_pool *pool; + struct otx2_snd_queue *sq; + + pool = xsk_get_pool_from_qid(netdev, qidx); + if (!pool) + return -EINVAL; + + sq = &pf->qset.sq[qidx + pf->hw.tx_queues]; + sq->xsk_pool = NULL; + otx2_clean_up_rq(pf, qidx); + clear_bit(qidx, pf->af_xdp_zc_qidx); + xsk_pool_dma_unmap(pool, DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING); + /* Reconfigure RSS table as 'qidx' now need to be part of RSS now */ + otx2_set_rss_table(pf, DEFAULT_RSS_CONTEXT_GROUP); + + return 0; +} + +int otx2_xsk_pool_setup(struct otx2_nic *pf, struct xsk_buff_pool *pool, u16 qidx) +{ + if (pool) + return otx2_xsk_pool_enable(pf, pool, qidx); + + return otx2_xsk_pool_disable(pf, qidx); +} + +int otx2_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags) +{ + struct otx2_nic *pf = netdev_priv(dev); + struct otx2_cq_poll *cq_poll = NULL; + struct otx2_qset *qset = &pf->qset; + + if (pf->flags & OTX2_FLAG_INTF_DOWN) + return -ENETDOWN; + + if (queue_id >= pf->hw.rx_queues || queue_id >= pf->hw.tx_queues) + return -EINVAL; + + cq_poll = &qset->napi[queue_id]; + if (!cq_poll) + return -EINVAL; + + /* Trigger interrupt */ + if (!napi_if_scheduled_mark_missed(&cq_poll->napi)) { + otx2_write64(pf, NIX_LF_CINTX_ENA_W1S(cq_poll->cint_idx), BIT_ULL(0)); + otx2_write64(pf, NIX_LF_CINTX_INT_W1S(cq_poll->cint_idx), BIT_ULL(0)); + } + + return 0; +} + +void otx2_attach_xsk_buff(struct otx2_nic *pfvf, struct otx2_snd_queue *sq, int qidx) +{ + if (test_bit(qidx, pfvf->af_xdp_zc_qidx)) + sq->xsk_pool = xsk_get_pool_from_qid(pfvf->netdev, qidx); +} + +void otx2_zc_napi_handler(struct otx2_nic *pfvf, struct xsk_buff_pool *pool, + int queue, int budget) +{ + struct xdp_desc *xdp_desc = pool->tx_descs; + int err, i, work_done = 0, batch; + + budget = min(budget, otx2_read_free_sqe(pfvf, queue)); + batch = xsk_tx_peek_release_desc_batch(pool, budget); + if (!batch) + return; + + for (i = 0; i < batch; i++) { + dma_addr_t dma_addr; + + dma_addr = xsk_buff_raw_get_dma(pool, xdp_desc[i].addr); + err = otx2_xdp_sq_append_pkt(pfvf, NULL, dma_addr, xdp_desc[i].len, + queue, OTX2_AF_XDP_FRAME); + if (!err) { + netdev_err(pfvf->netdev, "AF_XDP: Unable to transfer packet err%d\n", err); + break; + } + work_done++; + } + + if (work_done) + xsk_tx_release(pool); +} diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_xsk.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_xsk.h new file mode 100644 index 000000000000..8047fafee8fe --- /dev/null +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_xsk.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Marvell RVU PF/VF Netdev Devlink + * + * Copyright (C) 2024 Marvell. + * + */ + +#ifndef OTX2_XSK_H +#define OTX2_XSK_H + +struct otx2_nic; +struct xsk_buff_pool; + +int otx2_xsk_pool_setup(struct otx2_nic *pf, struct xsk_buff_pool *pool, u16 qid); +int otx2_xsk_pool_enable(struct otx2_nic *pf, struct xsk_buff_pool *pool, u16 qid); +int otx2_xsk_pool_disable(struct otx2_nic *pf, u16 qid); +int otx2_xsk_pool_alloc_buf(struct otx2_nic *pfvf, struct otx2_pool *pool, + dma_addr_t *dma, int idx); +int otx2_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags); +void otx2_zc_napi_handler(struct otx2_nic *pfvf, struct xsk_buff_pool *pool, + int queue, int budget); +void otx2_attach_xsk_buff(struct otx2_nic *pfvf, struct otx2_snd_queue *sq, int qidx); + +#endif /* OTX2_XSK_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/qos_sq.c b/drivers/net/ethernet/marvell/octeontx2/nic/qos_sq.c index 9d887bfc3108..c5dbae0e513b 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/qos_sq.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/qos_sq.c @@ -82,7 +82,7 @@ static int otx2_qos_sq_aura_pool_init(struct otx2_nic *pfvf, int qidx) } for (ptr = 0; ptr < num_sqbs; ptr++) { - err = otx2_alloc_rbuf(pfvf, pool, &bufptr); + err = otx2_alloc_rbuf(pfvf, pool, &bufptr, pool_id, ptr); if (err) goto sqb_free; pfvf->hw_ops->aura_freeptr(pfvf, pool_id, bufptr); diff --git a/drivers/net/ethernet/marvell/prestera/prestera_main.c b/drivers/net/ethernet/marvell/prestera/prestera_main.c index 440a4c42b405..8cdecf61253c 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_main.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_main.c @@ -396,7 +396,6 @@ static int prestera_port_sfp_bind(struct prestera_port *port) continue; port->phylink_pcs.ops = &prestera_pcs_ops; - port->phylink_pcs.neg_mode = true; port->phy_config.dev = &port->dev->dev; port->phy_config.type = PHYLINK_NETDEV; diff --git a/drivers/net/ethernet/mediatek/airoha_eth.c b/drivers/net/ethernet/mediatek/airoha_eth.c index 09f448f29124..aa5f220ddbcf 100644 --- a/drivers/net/ethernet/mediatek/airoha_eth.c +++ b/drivers/net/ethernet/mediatek/airoha_eth.c @@ -2556,11 +2556,10 @@ static u16 airoha_dev_select_queue(struct net_device *dev, struct sk_buff *skb, static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, struct net_device *dev) { - struct skb_shared_info *sinfo = skb_shinfo(skb); struct airoha_gdm_port *port = netdev_priv(dev); + u32 nr_frags = 1 + skb_shinfo(skb)->nr_frags; u32 msg0, msg1, len = skb_headlen(skb); struct airoha_qdma *qdma = port->qdma; - u32 nr_frags = 1 + sinfo->nr_frags; struct netdev_queue *txq; struct airoha_queue *q; void *data = skb->data; @@ -2583,8 +2582,9 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, if (skb_cow_head(skb, 0)) goto error; - if (sinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)) { - __be16 csum = cpu_to_be16(sinfo->gso_size); + if (skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | + SKB_GSO_TCPV6)) { + __be16 csum = cpu_to_be16(skb_shinfo(skb)->gso_size); tcp_hdr(skb)->check = (__force __sum16)csum; msg0 |= FIELD_PREP(QDMA_ETH_TXMSG_TSO_MASK, 1); @@ -2613,7 +2613,7 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, for (i = 0; i < nr_frags; i++) { struct airoha_qdma_desc *desc = &q->desc[index]; struct airoha_queue_entry *e = &q->entry[index]; - skb_frag_t *frag = &sinfo->frags[i]; + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; dma_addr_t addr; u32 val; diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 0ad965ced5ef..922330b3f4d7 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -815,12 +815,60 @@ static void mtk_mac_link_up(struct phylink_config *config, mtk_w32(mac->hw, mcr, MTK_MAC_MCR(mac->id)); } +static void mtk_mac_disable_tx_lpi(struct phylink_config *config) +{ + struct mtk_mac *mac = container_of(config, struct mtk_mac, + phylink_config); + struct mtk_eth *eth = mac->hw; + + mtk_m32(eth, MAC_MCR_EEE100M | MAC_MCR_EEE1G, 0, MTK_MAC_MCR(mac->id)); +} + +static int mtk_mac_enable_tx_lpi(struct phylink_config *config, u32 timer, + bool tx_clk_stop) +{ + struct mtk_mac *mac = container_of(config, struct mtk_mac, + phylink_config); + struct mtk_eth *eth = mac->hw; + u32 val; + + /* Tx idle timer in ms */ + timer = DIV_ROUND_UP(timer, 1000); + + /* If the timer is zero, then set LPI_MODE, which allows the + * system to enter LPI mode immediately rather than waiting for + * the LPI threshold. + */ + if (!timer) + val = MAC_EEE_LPI_MODE; + else if (FIELD_FIT(MAC_EEE_LPI_TXIDLE_THD, timer)) + val = FIELD_PREP(MAC_EEE_LPI_TXIDLE_THD, timer); + else + val = MAC_EEE_LPI_TXIDLE_THD; + + if (tx_clk_stop) + val |= MAC_EEE_CKG_TXIDLE; + + /* PHY Wake-up time, this field does not have a reset value, so use the + * reset value from MT7531 (36us for 100M and 17us for 1000M). + */ + val |= FIELD_PREP(MAC_EEE_WAKEUP_TIME_1000, 17) | + FIELD_PREP(MAC_EEE_WAKEUP_TIME_100, 36); + + mtk_w32(eth, val, MTK_MAC_EEECR(mac->id)); + mtk_m32(eth, 0, MAC_MCR_EEE100M | MAC_MCR_EEE1G, MTK_MAC_MCR(mac->id)); + + return 0; +} + static const struct phylink_mac_ops mtk_phylink_ops = { .mac_select_pcs = mtk_mac_select_pcs, .mac_config = mtk_mac_config, .mac_finish = mtk_mac_finish, .mac_link_down = mtk_mac_link_down, .mac_link_up = mtk_mac_link_up, + .mac_disable_tx_lpi = mtk_mac_disable_tx_lpi, + .mac_enable_tx_lpi = mtk_mac_enable_tx_lpi, }; static int mtk_mdio_init(struct mtk_eth *eth) @@ -4469,6 +4517,20 @@ static int mtk_set_pauseparam(struct net_device *dev, struct ethtool_pauseparam return phylink_ethtool_set_pauseparam(mac->phylink, pause); } +static int mtk_get_eee(struct net_device *dev, struct ethtool_keee *eee) +{ + struct mtk_mac *mac = netdev_priv(dev); + + return phylink_ethtool_get_eee(mac->phylink, eee); +} + +static int mtk_set_eee(struct net_device *dev, struct ethtool_keee *eee) +{ + struct mtk_mac *mac = netdev_priv(dev); + + return phylink_ethtool_set_eee(mac->phylink, eee); +} + static u16 mtk_select_queue(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev) { @@ -4501,6 +4563,8 @@ static const struct ethtool_ops mtk_ethtool_ops = { .set_pauseparam = mtk_set_pauseparam, .get_rxnfc = mtk_get_rxnfc, .set_rxnfc = mtk_set_rxnfc, + .get_eee = mtk_get_eee, + .set_eee = mtk_set_eee, }; static const struct net_device_ops mtk_netdev_ops = { @@ -4610,6 +4674,9 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np) mac->phylink_config.type = PHYLINK_NETDEV; mac->phylink_config.mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | MAC_10 | MAC_100 | MAC_1000 | MAC_2500FD; + mac->phylink_config.lpi_capabilities = MAC_100FD | MAC_1000FD | + MAC_2500FD; + mac->phylink_config.lpi_timer_default = 1000; /* MT7623 gmac0 is now missing its speed-specific PLL configuration * in its .mac_config method (since state->speed is not valid there. diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h index 0d5225f1d3ee..90a377ab4359 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h @@ -453,6 +453,8 @@ #define MAC_MCR_RX_FIFO_CLR_DIS BIT(12) #define MAC_MCR_BACKOFF_EN BIT(9) #define MAC_MCR_BACKPR_EN BIT(8) +#define MAC_MCR_EEE1G BIT(7) +#define MAC_MCR_EEE100M BIT(6) #define MAC_MCR_FORCE_RX_FC BIT(5) #define MAC_MCR_FORCE_TX_FC BIT(4) #define MAC_MCR_SPEED_1000 BIT(3) @@ -461,6 +463,15 @@ #define MAC_MCR_FORCE_LINK BIT(0) #define MAC_MCR_FORCE_LINK_DOWN (MAC_MCR_FORCE_MODE) +/* Mac EEE control registers */ +#define MTK_MAC_EEECR(x) (0x10104 + (x * 0x100)) +#define MAC_EEE_WAKEUP_TIME_1000 GENMASK(31, 24) +#define MAC_EEE_WAKEUP_TIME_100 GENMASK(23, 16) +#define MAC_EEE_LPI_TXIDLE_THD GENMASK(15, 8) +#define MAC_EEE_CKG_TXIDLE BIT(3) +#define MAC_EEE_CKG_RXLPI BIT(2) +#define MAC_EEE_LPI_MODE BIT(0) + /* Mac status registers */ #define MTK_MAC_MSR(x) (0x10108 + (x * 0x100)) #define MAC_MSR_EEE1G BIT(7) diff --git a/drivers/net/ethernet/mellanox/mlx4/alloc.c b/drivers/net/ethernet/mellanox/mlx4/alloc.c index 598df63518c5..07b061a97a6e 100644 --- a/drivers/net/ethernet/mellanox/mlx4/alloc.c +++ b/drivers/net/ethernet/mellanox/mlx4/alloc.c @@ -660,9 +660,9 @@ static struct mlx4_db_pgdir *mlx4_alloc_db_pgdir(struct device *dma_device) } static int mlx4_alloc_db_from_pgdir(struct mlx4_db_pgdir *pgdir, - struct mlx4_db *db, int order) + struct mlx4_db *db, unsigned int order) { - int o; + unsigned int o; int i; for (o = order; o <= 1; ++o) { @@ -690,7 +690,7 @@ found: return 0; } -int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, int order) +int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, unsigned int order) { struct mlx4_priv *priv = mlx4_priv(dev); struct mlx4_db_pgdir *pgdir; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 15c57e9517e9..b33285d755b9 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -48,60 +48,43 @@ #if IS_ENABLED(CONFIG_IPV6) #include <net/ip6_checksum.h> #endif +#include <net/page_pool/helpers.h> #include "mlx4_en.h" -static int mlx4_alloc_page(struct mlx4_en_priv *priv, - struct mlx4_en_rx_alloc *frag, - gfp_t gfp) -{ - struct page *page; - dma_addr_t dma; - - page = alloc_page(gfp); - if (unlikely(!page)) - return -ENOMEM; - dma = dma_map_page(priv->ddev, page, 0, PAGE_SIZE, priv->dma_dir); - if (unlikely(dma_mapping_error(priv->ddev, dma))) { - __free_page(page); - return -ENOMEM; - } - frag->page = page; - frag->dma = dma; - frag->page_offset = priv->rx_headroom; - return 0; -} - static int mlx4_en_alloc_frags(struct mlx4_en_priv *priv, struct mlx4_en_rx_ring *ring, struct mlx4_en_rx_desc *rx_desc, struct mlx4_en_rx_alloc *frags, gfp_t gfp) { + dma_addr_t dma; int i; for (i = 0; i < priv->num_frags; i++, frags++) { if (!frags->page) { - if (mlx4_alloc_page(priv, frags, gfp)) { + frags->page = page_pool_alloc_pages(ring->pp, gfp); + if (!frags->page) { ring->alloc_fail++; return -ENOMEM; } + page_pool_fragment_page(frags->page, 1); + frags->page_offset = priv->rx_headroom; + ring->rx_alloc_pages++; } - rx_desc->data[i].addr = cpu_to_be64(frags->dma + - frags->page_offset); + dma = page_pool_get_dma_addr(frags->page); + rx_desc->data[i].addr = cpu_to_be64(dma + frags->page_offset); } return 0; } static void mlx4_en_free_frag(const struct mlx4_en_priv *priv, + struct mlx4_en_rx_ring *ring, struct mlx4_en_rx_alloc *frag) { - if (frag->page) { - dma_unmap_page(priv->ddev, frag->dma, - PAGE_SIZE, priv->dma_dir); - __free_page(frag->page); - } + if (frag->page) + page_pool_put_full_page(ring->pp, frag->page, false); /* We need to clear all fields, otherwise a change of priv->log_rx_info * could lead to see garbage later in frag->page. */ @@ -141,18 +124,6 @@ static int mlx4_en_prepare_rx_desc(struct mlx4_en_priv *priv, (index << ring->log_stride); struct mlx4_en_rx_alloc *frags = ring->rx_info + (index << priv->log_rx_info); - if (likely(ring->page_cache.index > 0)) { - /* XDP uses a single page per frame */ - if (!frags->page) { - ring->page_cache.index--; - frags->page = ring->page_cache.buf[ring->page_cache.index].page; - frags->dma = ring->page_cache.buf[ring->page_cache.index].dma; - } - frags->page_offset = XDP_PACKET_HEADROOM; - rx_desc->data[0].addr = cpu_to_be64(frags->dma + - XDP_PACKET_HEADROOM); - return 0; - } return mlx4_en_alloc_frags(priv, ring, rx_desc, frags, gfp); } @@ -178,7 +149,7 @@ static void mlx4_en_free_rx_desc(const struct mlx4_en_priv *priv, frags = ring->rx_info + (index << priv->log_rx_info); for (nr = 0; nr < priv->num_frags; nr++) { en_dbg(DRV, priv, "Freeing fragment:%d\n", nr); - mlx4_en_free_frag(priv, frags + nr); + mlx4_en_free_frag(priv, ring, frags + nr); } } @@ -268,6 +239,7 @@ int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv, u32 size, u16 stride, int node, int queue_index) { struct mlx4_en_dev *mdev = priv->mdev; + struct page_pool_params pp = {}; struct mlx4_en_rx_ring *ring; int err = -ENOMEM; int tmp; @@ -286,9 +258,26 @@ int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv, ring->log_stride = ffs(ring->stride) - 1; ring->buf_size = ring->size * ring->stride + TXBB_SIZE; - if (xdp_rxq_info_reg(&ring->xdp_rxq, priv->dev, queue_index, 0) < 0) + pp.flags = PP_FLAG_DMA_MAP; + pp.pool_size = size * DIV_ROUND_UP(priv->rx_skb_size, PAGE_SIZE); + pp.nid = node; + pp.napi = &priv->rx_cq[queue_index]->napi; + pp.netdev = priv->dev; + pp.dev = &mdev->dev->persist->pdev->dev; + pp.dma_dir = priv->dma_dir; + + ring->pp = page_pool_create(&pp); + if (!ring->pp) goto err_ring; + if (xdp_rxq_info_reg(&ring->xdp_rxq, priv->dev, queue_index, 0) < 0) + goto err_pp; + + err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, MEM_TYPE_PAGE_POOL, + ring->pp); + if (err) + goto err_xdp_info; + tmp = size * roundup_pow_of_two(MLX4_EN_MAX_RX_FRAGS * sizeof(struct mlx4_en_rx_alloc)); ring->rx_info = kvzalloc_node(tmp, GFP_KERNEL, node); @@ -319,6 +308,8 @@ err_info: ring->rx_info = NULL; err_xdp_info: xdp_rxq_info_unreg(&ring->xdp_rxq); +err_pp: + page_pool_destroy(ring->pp); err_ring: kfree(ring); *pring = NULL; @@ -409,26 +400,6 @@ void mlx4_en_recover_from_oom(struct mlx4_en_priv *priv) } } -/* When the rx ring is running in page-per-packet mode, a released frame can go - * directly into a small cache, to avoid unmapping or touching the page - * allocator. In bpf prog performance scenarios, buffers are either forwarded - * or dropped, never converted to skbs, so every page can come directly from - * this cache when it is sized to be a multiple of the napi budget. - */ -bool mlx4_en_rx_recycle(struct mlx4_en_rx_ring *ring, - struct mlx4_en_rx_alloc *frame) -{ - struct mlx4_en_page_cache *cache = &ring->page_cache; - - if (cache->index >= MLX4_EN_CACHE_SIZE) - return false; - - cache->buf[cache->index].page = frame->page; - cache->buf[cache->index].dma = frame->dma; - cache->index++; - return true; -} - void mlx4_en_destroy_rx_ring(struct mlx4_en_priv *priv, struct mlx4_en_rx_ring **pring, u32 size, u16 stride) @@ -445,6 +416,7 @@ void mlx4_en_destroy_rx_ring(struct mlx4_en_priv *priv, xdp_rxq_info_unreg(&ring->xdp_rxq); mlx4_free_hwq_res(mdev->dev, &ring->wqres, size * stride + TXBB_SIZE); kvfree(ring->rx_info); + page_pool_destroy(ring->pp); ring->rx_info = NULL; kfree(ring); *pring = NULL; @@ -453,14 +425,6 @@ void mlx4_en_destroy_rx_ring(struct mlx4_en_priv *priv, void mlx4_en_deactivate_rx_ring(struct mlx4_en_priv *priv, struct mlx4_en_rx_ring *ring) { - int i; - - for (i = 0; i < ring->page_cache.index; i++) { - dma_unmap_page(priv->ddev, ring->page_cache.buf[i].dma, - PAGE_SIZE, priv->dma_dir); - put_page(ring->page_cache.buf[i].page); - } - ring->page_cache.index = 0; mlx4_en_free_rx_buf(priv, ring); if (ring->stride <= TXBB_SIZE) ring->buf -= TXBB_SIZE; @@ -487,7 +451,7 @@ static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv, if (unlikely(!page)) goto fail; - dma = frags->dma; + dma = page_pool_get_dma_addr(page); dma_sync_single_range_for_cpu(priv->ddev, dma, frags->page_offset, frag_size, priv->dma_dir); @@ -498,6 +462,7 @@ static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv, if (frag_info->frag_stride == PAGE_SIZE / 2) { frags->page_offset ^= PAGE_SIZE / 2; release = page_count(page) != 1 || + atomic_long_read(&page->pp_ref_count) != 1 || page_is_pfmemalloc(page) || page_to_nid(page) != numa_mem_id(); } else if (!priv->rx_headroom) { @@ -511,10 +476,9 @@ static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv, release = frags->page_offset + frag_info->frag_size > PAGE_SIZE; } if (release) { - dma_unmap_page(priv->ddev, dma, PAGE_SIZE, priv->dma_dir); frags->page = NULL; } else { - page_ref_inc(page); + page_pool_ref_page(page); } nr++; @@ -784,7 +748,8 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud /* Get pointer to first fragment since we haven't * skb yet and cast it to ethhdr struct */ - dma = frags[0].dma + frags[0].page_offset; + dma = page_pool_get_dma_addr(frags[0].page); + dma += frags[0].page_offset; dma_sync_single_for_cpu(priv->ddev, dma, sizeof(*ethh), DMA_FROM_DEVICE); @@ -823,7 +788,8 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud void *orig_data; u32 act; - dma = frags[0].dma + frags[0].page_offset; + dma = page_pool_get_dma_addr(frags[0].page); + dma += frags[0].page_offset; dma_sync_single_for_cpu(priv->ddev, dma, priv->frag_info[0].frag_size, DMA_FROM_DEVICE); @@ -886,6 +852,7 @@ xdp_drop_no_cnt: skb = napi_get_frags(&cq->napi); if (unlikely(!skb)) goto next; + skb_mark_for_recycle(skb); if (unlikely(ring->hwtstamp_rx_filter == HWTSTAMP_FILTER_ALL)) { u64 timestamp = mlx4_en_get_cqe_ts(cqe); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 1ddb11cb25f9..87f35bcbeff8 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -44,6 +44,7 @@ #include <linux/ipv6.h> #include <linux/indirect_call_wrapper.h> #include <net/ipv6.h> +#include <net/page_pool/helpers.h> #include "mlx4_en.h" @@ -350,16 +351,10 @@ u32 mlx4_en_recycle_tx_desc(struct mlx4_en_priv *priv, int napi_mode) { struct mlx4_en_tx_info *tx_info = &ring->tx_info[index]; - struct mlx4_en_rx_alloc frame = { - .page = tx_info->page, - .dma = tx_info->map0_dma, - }; - - if (!napi_mode || !mlx4_en_rx_recycle(ring->recycle_ring, &frame)) { - dma_unmap_page(priv->ddev, tx_info->map0_dma, - PAGE_SIZE, priv->dma_dir); - put_page(tx_info->page); - } + struct page_pool *pool = ring->recycle_ring->pp; + + /* Note that napi_mode = 0 means ndo_close() path, not budget = 0 */ + page_pool_put_full_page(pool, tx_info->page, !!napi_mode); return tx_info->nr_txbb; } @@ -450,6 +445,8 @@ int mlx4_en_process_tx_cq(struct net_device *dev, if (unlikely(!priv->port_up)) return 0; + if (unlikely(!napi_budget) && cq->type == TX_XDP) + return 0; netdev_txq_bql_complete_prefetchw(ring->tx_queue); @@ -1194,7 +1191,7 @@ netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring, tx_desc = ring->buf + (index << LOG_TXBB_SIZE); data = &tx_desc->data; - dma = frame->dma; + dma = page_pool_get_dma_addr(frame->page); tx_info->page = frame->page; frame->page = NULL; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 28b70dcc652e..ad0d91a75184 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -247,20 +247,11 @@ struct mlx4_en_tx_desc { struct mlx4_en_rx_alloc { struct page *page; - dma_addr_t dma; u32 page_offset; }; #define MLX4_EN_CACHE_SIZE (2 * NAPI_POLL_WEIGHT) -struct mlx4_en_page_cache { - u32 index; - struct { - struct page *page; - dma_addr_t dma; - } buf[MLX4_EN_CACHE_SIZE]; -}; - enum { MLX4_EN_TX_RING_STATE_RECOVERING, }; @@ -335,14 +326,14 @@ struct mlx4_en_rx_ring { u16 stride; u16 log_stride; u16 cqn; /* index of port CQ associated with this ring */ + u8 fcs_del; u32 prod; u32 cons; u32 buf_size; - u8 fcs_del; + struct page_pool *pp; void *buf; void *rx_info; struct bpf_prog __rcu *xdp_prog; - struct mlx4_en_page_cache page_cache; unsigned long bytes; unsigned long packets; unsigned long csum_ok; @@ -707,8 +698,6 @@ netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring, struct mlx4_en_priv *priv, unsigned int length, int tx_ind, bool *doorbell_pending); void mlx4_en_xmit_doorbell(struct mlx4_en_tx_ring *ring); -bool mlx4_en_rx_recycle(struct mlx4_en_rx_ring *ring, - struct mlx4_en_rx_alloc *frame); int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv, struct mlx4_en_tx_ring **pring, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig index ea6070180c96..bf4015a12b41 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig +++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig @@ -80,8 +80,8 @@ config MLX5_BRIDGE default y help mlx5 ConnectX offloads support for Ethernet Bridging (BRIDGE). - Enable adding representors of mlx5 uplink and VF ports to Bridge and - offloading rules for traffic between such ports. Supports VLANs (trunk and + Enable offloading FDB rules from a bridge device containing + representors of mlx5 uplink and VF ports. Supports VLANs (trunk and access modes). config MLX5_CLS_ACT diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index f9113cb13a0c..1bf2212a0bb6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -260,12 +260,10 @@ void mlx5e_build_ptys2ethtool_map(void) ETHTOOL_LINK_MODE_800000baseVR4_Full_BIT); } -static void mlx5e_ethtool_get_speed_arr(struct mlx5_core_dev *mdev, +static void mlx5e_ethtool_get_speed_arr(bool ext, struct ptys2ethtool_config **arr, u32 *size) { - bool ext = mlx5_ptys_ext_supported(mdev); - *arr = ext ? ptys2ext_ethtool_table : ptys2legacy_ethtool_table; *size = ext ? ARRAY_SIZE(ptys2ext_ethtool_table) : ARRAY_SIZE(ptys2legacy_ethtool_table); @@ -912,37 +910,19 @@ int mlx5e_set_per_queue_coalesce(struct net_device *dev, u32 queue, return mlx5e_ethtool_set_per_queue_coalesce(priv, queue, coal); } -static void ptys2ethtool_supported_link(struct mlx5_core_dev *mdev, - unsigned long *supported_modes, - u32 eth_proto_cap) -{ - unsigned long proto_cap = eth_proto_cap; - struct ptys2ethtool_config *table; - u32 max_size; - int proto; - - mlx5e_ethtool_get_speed_arr(mdev, &table, &max_size); - for_each_set_bit(proto, &proto_cap, max_size) - bitmap_or(supported_modes, supported_modes, - table[proto].supported, - __ETHTOOL_LINK_MODE_MASK_NBITS); -} - -static void ptys2ethtool_adver_link(unsigned long *advertising_modes, - u32 eth_proto_cap, bool ext) +static void ptys2ethtool_process_link(u32 eth_eproto, bool ext, bool advertised, + unsigned long *modes) { - unsigned long proto_cap = eth_proto_cap; + unsigned long eproto = eth_eproto; struct ptys2ethtool_config *table; u32 max_size; int proto; - table = ext ? ptys2ext_ethtool_table : ptys2legacy_ethtool_table; - max_size = ext ? ARRAY_SIZE(ptys2ext_ethtool_table) : - ARRAY_SIZE(ptys2legacy_ethtool_table); - - for_each_set_bit(proto, &proto_cap, max_size) - bitmap_or(advertising_modes, advertising_modes, - table[proto].advertised, + mlx5e_ethtool_get_speed_arr(ext, &table, &max_size); + for_each_set_bit(proto, &eproto, max_size) + bitmap_or(modes, modes, + advertised ? + table[proto].advertised : table[proto].supported, __ETHTOOL_LINK_MODE_MASK_NBITS); } @@ -1128,18 +1108,19 @@ static void get_supported(struct mlx5_core_dev *mdev, u32 eth_proto_cap, struct ethtool_link_ksettings *link_ksettings) { unsigned long *supported = link_ksettings->link_modes.supported; - ptys2ethtool_supported_link(mdev, supported, eth_proto_cap); + bool ext = mlx5_ptys_ext_supported(mdev); + + ptys2ethtool_process_link(eth_proto_cap, ext, false, supported); ethtool_link_ksettings_add_link_mode(link_ksettings, supported, Pause); } -static void get_advertising(u32 eth_proto_cap, u8 tx_pause, u8 rx_pause, +static void get_advertising(u32 eth_proto_admin, u8 tx_pause, u8 rx_pause, struct ethtool_link_ksettings *link_ksettings, bool ext) { unsigned long *advertising = link_ksettings->link_modes.advertising; - ptys2ethtool_adver_link(advertising, eth_proto_cap, ext); - + ptys2ethtool_process_link(eth_proto_admin, ext, true, advertising); if (rx_pause) ethtool_link_ksettings_add_link_mode(link_ksettings, advertising, Pause); if (tx_pause ^ rx_pause) @@ -1195,7 +1176,7 @@ static void get_lp_advertising(struct mlx5_core_dev *mdev, u32 eth_proto_lp, unsigned long *lp_advertising = link_ksettings->link_modes.lp_advertising; bool ext = mlx5_ptys_ext_supported(mdev); - ptys2ethtool_adver_link(lp_advertising, eth_proto_lp, ext); + ptys2ethtool_process_link(eth_proto_lp, ext, true, lp_advertising); } static int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv, @@ -1363,13 +1344,6 @@ static bool ext_link_mode_requested(const unsigned long *adver) return bitmap_intersects(modes, adver, __ETHTOOL_LINK_MODE_MASK_NBITS); } -static bool ext_requested(u8 autoneg, const unsigned long *adver, bool ext_supported) -{ - bool ext_link_mode = ext_link_mode_requested(adver); - - return autoneg == AUTONEG_ENABLE ? ext_link_mode : ext_supported; -} - static int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv, const struct ethtool_link_ksettings *link_ksettings) { @@ -1379,6 +1353,7 @@ static int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv, bool an_changes = false; u8 an_disable_admin; bool ext_supported; + bool ext_requested; u8 an_disable_cap; bool an_disable; u32 link_modes; @@ -1395,10 +1370,11 @@ static int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv, speed = link_ksettings->base.speed; ext_supported = mlx5_ptys_ext_supported(mdev); - ext = ext_requested(autoneg, adver, ext_supported); - if (!ext_supported && ext) + ext_requested = ext_link_mode_requested(adver); + if (!ext_supported && ext_requested) return -EOPNOTSUPP; + ext = autoneg == AUTONEG_ENABLE ? ext_requested : ext_supported; ethtool2ptys_adver_func = ext ? mlx5e_ethtool2ptys_ext_adver_link : mlx5e_ethtool2ptys_adver_link; err = mlx5_port_query_eth_proto(mdev, 1, ext, &eproto); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c index d91ea53eb394..01c5f5990f9a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/events.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c @@ -6,6 +6,7 @@ #include "mlx5_core.h" #include "lib/eq.h" #include "lib/events.h" +#include "hwmon.h" struct mlx5_event_nb { struct mlx5_nb nb; @@ -153,21 +154,50 @@ static int any_notifier(struct notifier_block *nb, return NOTIFY_OK; } +#if IS_ENABLED(CONFIG_HWMON) +static void print_sensor_names_in_bit_set(struct mlx5_core_dev *dev, struct mlx5_hwmon *hwmon, + u64 bit_set, int bit_set_offset) +{ + unsigned long *bit_set_ptr = (unsigned long *)&bit_set; + int num_bits = sizeof(bit_set) * BITS_PER_BYTE; + int i; + + for_each_set_bit(i, bit_set_ptr, num_bits) { + const char *sensor_name = hwmon_get_sensor_name(hwmon, i + bit_set_offset); + + mlx5_core_warn(dev, "Sensor name[%d]: %s\n", i + bit_set_offset, sensor_name); + } +} +#endif /* CONFIG_HWMON */ + /* type == MLX5_EVENT_TYPE_TEMP_WARN_EVENT */ static int temp_warn(struct notifier_block *nb, unsigned long type, void *data) { struct mlx5_event_nb *event_nb = mlx5_nb_cof(nb, struct mlx5_event_nb, nb); struct mlx5_events *events = event_nb->ctx; + struct mlx5_core_dev *dev = events->dev; struct mlx5_eqe *eqe = data; u64 value_lsb; u64 value_msb; value_lsb = be64_to_cpu(eqe->data.temp_warning.sensor_warning_lsb); + /* bit 1-63 are not supported for NICs, + * hence read only bit 0 (asic) from lsb. + */ + value_lsb &= 0x1; value_msb = be64_to_cpu(eqe->data.temp_warning.sensor_warning_msb); - mlx5_core_warn(events->dev, - "High temperature on sensors with bit set %llx %llx", - value_msb, value_lsb); + if (net_ratelimit()) { + mlx5_core_warn(dev, "High temperature on sensors with bit set %#llx %#llx.\n", + value_msb, value_lsb); +#if IS_ENABLED(CONFIG_HWMON) + if (dev->hwmon) { + print_sensor_names_in_bit_set(dev, dev->hwmon, value_lsb, 0); + print_sensor_names_in_bit_set(dev, dev->hwmon, value_msb, + sizeof(value_lsb) * BITS_PER_BYTE); + } +#endif + } return NOTIFY_OK; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/hwmon.c b/drivers/net/ethernet/mellanox/mlx5/core/hwmon.c index 353f81dccd1c..4ba2636d7fb6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/hwmon.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/hwmon.c @@ -416,3 +416,8 @@ void mlx5_hwmon_dev_unregister(struct mlx5_core_dev *mdev) mlx5_hwmon_free(hwmon); mdev->hwmon = NULL; } + +const char *hwmon_get_sensor_name(struct mlx5_hwmon *hwmon, int channel) +{ + return hwmon->temp_channel_desc[channel].sensor_name; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/hwmon.h b/drivers/net/ethernet/mellanox/mlx5/core/hwmon.h index 999654a9b9da..f38271c22c10 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/hwmon.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/hwmon.h @@ -10,6 +10,7 @@ int mlx5_hwmon_dev_register(struct mlx5_core_dev *mdev); void mlx5_hwmon_dev_unregister(struct mlx5_core_dev *mdev); +const char *hwmon_get_sensor_name(struct mlx5_hwmon *hwmon, int channel); #else static inline int mlx5_hwmon_dev_register(struct mlx5_core_dev *mdev) diff --git a/drivers/net/ethernet/meta/fbnic/fbnic.h b/drivers/net/ethernet/meta/fbnic/fbnic.h index 37f81db1fc30..4ca7b99ef131 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic.h @@ -186,6 +186,9 @@ void fbnic_dbg_exit(void); void fbnic_csr_get_regs(struct fbnic_dev *fbd, u32 *data, u32 *regs_version); int fbnic_csr_regs_len(struct fbnic_dev *fbd); +void fbnic_config_txrx_usecs(struct fbnic_napi_vector *nv, u32 arm); +void fbnic_config_rx_frames(struct fbnic_napi_vector *nv); + enum fbnic_boards { fbnic_board_asic }; diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c b/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c index fb7139a1da46..c1477aad98a0 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c @@ -136,6 +136,61 @@ static void fbnic_clone_free(struct fbnic_net *clone) kfree(clone); } +static int fbnic_get_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) +{ + struct fbnic_net *fbn = netdev_priv(netdev); + + ec->tx_coalesce_usecs = fbn->tx_usecs; + ec->rx_coalesce_usecs = fbn->rx_usecs; + ec->rx_max_coalesced_frames = fbn->rx_max_frames; + + return 0; +} + +static int fbnic_set_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) +{ + struct fbnic_net *fbn = netdev_priv(netdev); + + /* Verify against hardware limits */ + if (ec->rx_coalesce_usecs > FIELD_MAX(FBNIC_INTR_CQ_REARM_RCQ_TIMEOUT)) { + NL_SET_ERR_MSG_MOD(extack, "rx_usecs is above device max"); + return -EINVAL; + } + if (ec->tx_coalesce_usecs > FIELD_MAX(FBNIC_INTR_CQ_REARM_TCQ_TIMEOUT)) { + NL_SET_ERR_MSG_MOD(extack, "tx_usecs is above device max"); + return -EINVAL; + } + if (ec->rx_max_coalesced_frames > + FIELD_MAX(FBNIC_QUEUE_RIM_THRESHOLD_RCD_MASK) / + FBNIC_MIN_RXD_PER_FRAME) { + NL_SET_ERR_MSG_MOD(extack, "rx_frames is above device max"); + return -EINVAL; + } + + fbn->tx_usecs = ec->tx_coalesce_usecs; + fbn->rx_usecs = ec->rx_coalesce_usecs; + fbn->rx_max_frames = ec->rx_max_coalesced_frames; + + if (netif_running(netdev)) { + int i; + + for (i = 0; i < fbn->num_napi; i++) { + struct fbnic_napi_vector *nv = fbn->napi[i]; + + fbnic_config_txrx_usecs(nv, 0); + fbnic_config_rx_frames(nv); + } + } + + return 0; +} + static void fbnic_get_strings(struct net_device *dev, u32 sset, u8 *data) { int i; @@ -1287,10 +1342,15 @@ fbnic_get_eth_mac_stats(struct net_device *netdev, } static const struct ethtool_ops fbnic_ethtool_ops = { + .supported_coalesce_params = + ETHTOOL_COALESCE_USECS | + ETHTOOL_COALESCE_RX_MAX_FRAMES, .rxfh_max_num_contexts = FBNIC_RPC_RSS_TBL_COUNT, .get_drvinfo = fbnic_get_drvinfo, .get_regs_len = fbnic_get_regs_len, .get_regs = fbnic_get_regs, + .get_coalesce = fbnic_get_coalesce, + .set_coalesce = fbnic_set_coalesce, .get_strings = fbnic_get_strings, .get_ethtool_stats = fbnic_get_ethtool_stats, .get_sset_count = fbnic_get_sset_count, diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c index b12672d1607e..cf8feb90b617 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c @@ -517,7 +517,7 @@ static void fbnic_get_queue_stats_tx(struct net_device *dev, int idx, struct fbnic_net *fbn = netdev_priv(dev); struct fbnic_ring *txr = fbn->tx[idx]; struct fbnic_queue_stats *stats; - u64 stop, wake, csum; + u64 stop, wake, csum, lso; unsigned int start; u64 bytes, packets; @@ -530,13 +530,15 @@ static void fbnic_get_queue_stats_tx(struct net_device *dev, int idx, bytes = stats->bytes; packets = stats->packets; csum = stats->twq.csum_partial; + lso = stats->twq.lso; stop = stats->twq.stop; wake = stats->twq.wake; } while (u64_stats_fetch_retry(&stats->syncp, start)); tx->bytes = bytes; tx->packets = packets; - tx->needs_csum = csum; + tx->needs_csum = csum + lso; + tx->hw_gso_wire_packets = lso; tx->stop = stop; tx->wake = wake; } @@ -549,7 +551,8 @@ static void fbnic_get_base_stats(struct net_device *dev, tx->bytes = fbn->tx_stats.bytes; tx->packets = fbn->tx_stats.packets; - tx->needs_csum = fbn->tx_stats.twq.csum_partial; + tx->needs_csum = fbn->tx_stats.twq.csum_partial + fbn->tx_stats.twq.lso; + tx->hw_gso_wire_packets = fbn->tx_stats.twq.lso; tx->stop = fbn->tx_stats.twq.stop; tx->wake = fbn->tx_stats.twq.wake; @@ -638,6 +641,10 @@ struct net_device *fbnic_netdev_alloc(struct fbnic_dev *fbd) fbn->ppq_size = FBNIC_PPQ_SIZE_DEFAULT; fbn->rcq_size = FBNIC_RCQ_SIZE_DEFAULT; + fbn->tx_usecs = FBNIC_TX_USECS_DEFAULT; + fbn->rx_usecs = FBNIC_RX_USECS_DEFAULT; + fbn->rx_max_frames = FBNIC_RX_FRAMES_DEFAULT; + default_queues = netif_get_num_default_rss_queues(); if (default_queues > fbd->max_num_queues) default_queues = fbd->max_num_queues; @@ -650,11 +657,25 @@ struct net_device *fbnic_netdev_alloc(struct fbnic_dev *fbd) netdev->priv_flags |= IFF_UNICAST_FLT; + netdev->gso_partial_features = + NETIF_F_GSO_GRE | + NETIF_F_GSO_GRE_CSUM | + NETIF_F_GSO_IPXIP4 | + NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_UDP_TUNNEL_CSUM; + netdev->features |= + netdev->gso_partial_features | + FBNIC_TUN_GSO_FEATURES | NETIF_F_RXHASH | NETIF_F_SG | NETIF_F_HW_CSUM | - NETIF_F_RXCSUM; + NETIF_F_RXCSUM | + NETIF_F_TSO | + NETIF_F_TSO_ECN | + NETIF_F_TSO6 | + NETIF_F_GSO_PARTIAL | + NETIF_F_GSO_UDP_L4; netdev->hw_features |= netdev->features; netdev->vlan_features |= netdev->features; diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h index a392ac1cc4f2..561837e80ec8 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h @@ -12,6 +12,10 @@ #include "fbnic_txrx.h" #define FBNIC_MAX_NAPI_VECTORS 128u +#define FBNIC_MIN_RXD_PER_FRAME 2 + +/* Natively supported tunnel GSO features (not thru GSO_PARTIAL) */ +#define FBNIC_TUN_GSO_FEATURES NETIF_F_GSO_IPXIP6 struct fbnic_net { struct fbnic_ring *tx[FBNIC_MAX_TXQS]; @@ -27,6 +31,11 @@ struct fbnic_net { u32 ppq_size; u32 rcq_size; + u16 rx_usecs; + u16 tx_usecs; + + u32 rx_max_frames; + u16 num_napi; struct phylink *phylink; diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_phylink.c b/drivers/net/ethernet/meta/fbnic/fbnic_phylink.c index bb11fc83367d..860b02b22c15 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_phylink.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_phylink.c @@ -133,7 +133,6 @@ int fbnic_phylink_init(struct net_device *netdev) struct fbnic_net *fbn = netdev_priv(netdev); struct phylink *phylink; - fbn->phylink_pcs.neg_mode = true; fbn->phylink_pcs.ops = &fbnic_phylink_pcs_ops; fbn->phylink_config.dev = &netdev->dev; diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c index 24d2b528b66c..aba4c65974ee 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c @@ -6,6 +6,7 @@ #include <linux/pci.h> #include <net/netdev_queues.h> #include <net/page_pool/helpers.h> +#include <net/tcp.h> #include "fbnic.h" #include "fbnic_csr.h" @@ -18,6 +19,7 @@ enum { struct fbnic_xmit_cb { u32 bytecount; + u16 gso_segs; u8 desc_count; u8 flags; int hw_head; @@ -179,8 +181,72 @@ static bool fbnic_tx_tstamp(struct sk_buff *skb) } static bool +fbnic_tx_lso(struct fbnic_ring *ring, struct sk_buff *skb, + struct skb_shared_info *shinfo, __le64 *meta, + unsigned int *l2len, unsigned int *i3len) +{ + unsigned int l3_type, l4_type, l4len, hdrlen; + unsigned char *l4hdr; + __be16 payload_len; + + if (unlikely(skb_cow_head(skb, 0))) + return true; + + if (shinfo->gso_type & SKB_GSO_PARTIAL) { + l3_type = FBNIC_TWD_L3_TYPE_OTHER; + } else if (!skb->encapsulation) { + if (ip_hdr(skb)->version == 4) + l3_type = FBNIC_TWD_L3_TYPE_IPV4; + else + l3_type = FBNIC_TWD_L3_TYPE_IPV6; + } else { + unsigned int o3len; + + o3len = skb_inner_network_header(skb) - skb_network_header(skb); + *i3len -= o3len; + *meta |= cpu_to_le64(FIELD_PREP(FBNIC_TWD_L3_OHLEN_MASK, + o3len / 2)); + l3_type = FBNIC_TWD_L3_TYPE_V6V6; + } + + l4hdr = skb_checksum_start(skb); + payload_len = cpu_to_be16(skb->len - (l4hdr - skb->data)); + + if (shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)) { + struct tcphdr *tcph = (struct tcphdr *)l4hdr; + + l4_type = FBNIC_TWD_L4_TYPE_TCP; + l4len = __tcp_hdrlen((struct tcphdr *)l4hdr); + csum_replace_by_diff(&tcph->check, (__force __wsum)payload_len); + } else { + struct udphdr *udph = (struct udphdr *)l4hdr; + + l4_type = FBNIC_TWD_L4_TYPE_UDP; + l4len = sizeof(struct udphdr); + csum_replace_by_diff(&udph->check, (__force __wsum)payload_len); + } + + hdrlen = (l4hdr - skb->data) + l4len; + *meta |= cpu_to_le64(FIELD_PREP(FBNIC_TWD_L3_TYPE_MASK, l3_type) | + FIELD_PREP(FBNIC_TWD_L4_TYPE_MASK, l4_type) | + FIELD_PREP(FBNIC_TWD_L4_HLEN_MASK, l4len / 4) | + FIELD_PREP(FBNIC_TWD_MSS_MASK, shinfo->gso_size) | + FBNIC_TWD_FLAG_REQ_LSO); + + FBNIC_XMIT_CB(skb)->bytecount += (shinfo->gso_segs - 1) * hdrlen; + FBNIC_XMIT_CB(skb)->gso_segs = shinfo->gso_segs; + + u64_stats_update_begin(&ring->stats.syncp); + ring->stats.twq.lso += shinfo->gso_segs; + u64_stats_update_end(&ring->stats.syncp); + + return false; +} + +static bool fbnic_tx_offloads(struct fbnic_ring *ring, struct sk_buff *skb, __le64 *meta) { + struct skb_shared_info *shinfo = skb_shinfo(skb); unsigned int l2len, i3len; if (fbnic_tx_tstamp(skb)) @@ -195,10 +261,15 @@ fbnic_tx_offloads(struct fbnic_ring *ring, struct sk_buff *skb, __le64 *meta) *meta |= cpu_to_le64(FIELD_PREP(FBNIC_TWD_CSUM_OFFSET_MASK, skb->csum_offset / 2)); - *meta |= cpu_to_le64(FBNIC_TWD_FLAG_REQ_CSO); - u64_stats_update_begin(&ring->stats.syncp); - ring->stats.twq.csum_partial++; - u64_stats_update_end(&ring->stats.syncp); + if (shinfo->gso_size) { + if (fbnic_tx_lso(ring, skb, shinfo, meta, &l2len, &i3len)) + return true; + } else { + *meta |= cpu_to_le64(FBNIC_TWD_FLAG_REQ_CSO); + u64_stats_update_begin(&ring->stats.syncp); + ring->stats.twq.csum_partial++; + u64_stats_update_end(&ring->stats.syncp); + } *meta |= cpu_to_le64(FIELD_PREP(FBNIC_TWD_L2_HLEN_MASK, l2len / 2) | FIELD_PREP(FBNIC_TWD_L3_IHLEN_MASK, i3len / 2)); @@ -341,7 +412,9 @@ fbnic_xmit_frame_ring(struct sk_buff *skb, struct fbnic_ring *ring) /* Write all members within DWORD to condense this into 2 4B writes */ FBNIC_XMIT_CB(skb)->bytecount = skb->len; + FBNIC_XMIT_CB(skb)->gso_segs = 1; FBNIC_XMIT_CB(skb)->desc_count = 0; + FBNIC_XMIT_CB(skb)->flags = 0; if (fbnic_tx_offloads(ring, skb, meta)) goto err_free; @@ -368,6 +441,59 @@ netdev_tx_t fbnic_xmit_frame(struct sk_buff *skb, struct net_device *dev) return fbnic_xmit_frame_ring(skb, fbn->tx[q_map]); } +static netdev_features_t +fbnic_features_check_encap_gso(struct sk_buff *skb, struct net_device *dev, + netdev_features_t features, unsigned int l3len) +{ + netdev_features_t skb_gso_features; + struct ipv6hdr *ip6_hdr; + unsigned char l4_hdr; + unsigned int start; + __be16 frag_off; + + /* Require MANGLEID for GSO_PARTIAL of IPv4. + * In theory we could support TSO with single, innermost v4 header + * by pretending everything before it is L2, but that needs to be + * parsed case by case.. so leaving it for when the need arises. + */ + if (!(features & NETIF_F_TSO_MANGLEID)) + features &= ~NETIF_F_TSO; + + skb_gso_features = skb_shinfo(skb)->gso_type; + skb_gso_features <<= NETIF_F_GSO_SHIFT; + + /* We'd only clear the native GSO features, so don't bother validating + * if the match can only be on those supported thru GSO_PARTIAL. + */ + if (!(skb_gso_features & FBNIC_TUN_GSO_FEATURES)) + return features; + + /* We can only do IPv6-in-IPv6, not v4-in-v6. It'd be nice + * to fall back to partial for this, or any failure below. + * This is just an optimization, UDPv4 will be caught later on. + */ + if (skb_gso_features & NETIF_F_TSO) + return features & ~FBNIC_TUN_GSO_FEATURES; + + /* Inner headers multiple of 2 */ + if ((skb_inner_network_header(skb) - skb_network_header(skb)) % 2) + return features & ~FBNIC_TUN_GSO_FEATURES; + + /* Encapsulated GSO packet, make 100% sure it's IPv6-in-IPv6. */ + ip6_hdr = ipv6_hdr(skb); + if (ip6_hdr->version != 6) + return features & ~FBNIC_TUN_GSO_FEATURES; + + l4_hdr = ip6_hdr->nexthdr; + start = (unsigned char *)ip6_hdr - skb->data + sizeof(struct ipv6hdr); + start = ipv6_skip_exthdr(skb, start, &l4_hdr, &frag_off); + if (frag_off || l4_hdr != IPPROTO_IPV6 || + skb->data + start != skb_inner_network_header(skb)) + return features & ~FBNIC_TUN_GSO_FEATURES; + + return features; +} + netdev_features_t fbnic_features_check(struct sk_buff *skb, struct net_device *dev, netdev_features_t features) @@ -388,9 +514,12 @@ fbnic_features_check(struct sk_buff *skb, struct net_device *dev, !FIELD_FIT(FBNIC_TWD_L2_HLEN_MASK, l2len / 2) || !FIELD_FIT(FBNIC_TWD_L3_IHLEN_MASK, l3len / 2) || !FIELD_FIT(FBNIC_TWD_CSUM_OFFSET_MASK, skb->csum_offset / 2)) - return features & ~NETIF_F_CSUM_MASK; + return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); - return features; + if (likely(!skb->encapsulation) || !skb_is_gso(skb)) + return features; + + return fbnic_features_check_encap_gso(skb, dev, features, l3len); } static void fbnic_clean_twq0(struct fbnic_napi_vector *nv, int napi_budget, @@ -441,7 +570,7 @@ static void fbnic_clean_twq0(struct fbnic_napi_vector *nv, int napi_budget, } total_bytes += FBNIC_XMIT_CB(skb)->bytecount; - total_packets += 1; + total_packets += FBNIC_XMIT_CB(skb)->gso_segs; napi_consume_skb(skb, napi_budget); } @@ -1105,12 +1234,13 @@ void fbnic_aggregate_ring_tx_counters(struct fbnic_net *fbn, fbn->tx_stats.packets += stats->packets; fbn->tx_stats.dropped += stats->dropped; fbn->tx_stats.twq.csum_partial += stats->twq.csum_partial; + fbn->tx_stats.twq.lso += stats->twq.lso; fbn->tx_stats.twq.ts_lost += stats->twq.ts_lost; fbn->tx_stats.twq.ts_packets += stats->twq.ts_packets; fbn->tx_stats.twq.stop += stats->twq.stop; fbn->tx_stats.twq.wake += stats->twq.wake; /* Remember to add new stats here */ - BUILD_BUG_ON(sizeof(fbn->tx_stats.twq) / 8 != 5); + BUILD_BUG_ON(sizeof(fbn->tx_stats.twq) / 8 != 6); } static void fbnic_remove_tx_ring(struct fbnic_net *fbn, @@ -2054,9 +2184,51 @@ static void fbnic_config_drop_mode_rcq(struct fbnic_napi_vector *nv, fbnic_ring_wr32(rcq, FBNIC_QUEUE_RDE_CTL0, rcq_ctl); } +static void fbnic_config_rim_threshold(struct fbnic_ring *rcq, u16 nv_idx, u32 rx_desc) +{ + u32 threshold; + + /* Set the threhsold to half the ring size if rx_frames + * is not configured + */ + threshold = rx_desc ? : rcq->size_mask / 2; + + fbnic_ring_wr32(rcq, FBNIC_QUEUE_RIM_CTL, nv_idx); + fbnic_ring_wr32(rcq, FBNIC_QUEUE_RIM_THRESHOLD, threshold); +} + +void fbnic_config_txrx_usecs(struct fbnic_napi_vector *nv, u32 arm) +{ + struct fbnic_net *fbn = netdev_priv(nv->napi.dev); + struct fbnic_dev *fbd = nv->fbd; + u32 val = arm; + + val |= FIELD_PREP(FBNIC_INTR_CQ_REARM_RCQ_TIMEOUT, fbn->rx_usecs) | + FBNIC_INTR_CQ_REARM_RCQ_TIMEOUT_UPD_EN; + val |= FIELD_PREP(FBNIC_INTR_CQ_REARM_TCQ_TIMEOUT, fbn->tx_usecs) | + FBNIC_INTR_CQ_REARM_TCQ_TIMEOUT_UPD_EN; + + fbnic_wr32(fbd, FBNIC_INTR_CQ_REARM(nv->v_idx), val); +} + +void fbnic_config_rx_frames(struct fbnic_napi_vector *nv) +{ + struct fbnic_net *fbn = netdev_priv(nv->napi.dev); + int i; + + for (i = nv->txt_count; i < nv->rxt_count + nv->txt_count; i++) { + struct fbnic_q_triad *qt = &nv->qt[i]; + + fbnic_config_rim_threshold(&qt->cmpl, nv->v_idx, + fbn->rx_max_frames * + FBNIC_MIN_RXD_PER_FRAME); + } +} + static void fbnic_enable_rcq(struct fbnic_napi_vector *nv, struct fbnic_ring *rcq) { + struct fbnic_net *fbn = netdev_priv(nv->napi.dev); u32 log_size = fls(rcq->size_mask); u32 rcq_ctl; @@ -2084,8 +2256,8 @@ static void fbnic_enable_rcq(struct fbnic_napi_vector *nv, fbnic_ring_wr32(rcq, FBNIC_QUEUE_RCQ_SIZE, log_size & 0xf); /* Store interrupt information for the completion queue */ - fbnic_ring_wr32(rcq, FBNIC_QUEUE_RIM_CTL, nv->v_idx); - fbnic_ring_wr32(rcq, FBNIC_QUEUE_RIM_THRESHOLD, rcq->size_mask / 2); + fbnic_config_rim_threshold(rcq, nv->v_idx, fbn->rx_max_frames * + FBNIC_MIN_RXD_PER_FRAME); fbnic_ring_wr32(rcq, FBNIC_QUEUE_RIM_MASK, 0); /* Enable queue */ @@ -2124,12 +2296,7 @@ void fbnic_enable(struct fbnic_net *fbn) static void fbnic_nv_irq_enable(struct fbnic_napi_vector *nv) { - struct fbnic_dev *fbd = nv->fbd; - u32 val; - - val = FBNIC_INTR_CQ_REARM_INTR_UNMASK; - - fbnic_wr32(fbd, FBNIC_INTR_CQ_REARM(nv->v_idx), val); + fbnic_config_txrx_usecs(nv, FBNIC_INTR_CQ_REARM_INTR_UNMASK); } void fbnic_napi_enable(struct fbnic_net *fbn) diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h index b53a7d28ecd3..54368dc22328 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h @@ -31,6 +31,9 @@ struct fbnic_net; #define FBNIC_HPQ_SIZE_DEFAULT 256 #define FBNIC_PPQ_SIZE_DEFAULT 256 #define FBNIC_RCQ_SIZE_DEFAULT 1024 +#define FBNIC_TX_USECS_DEFAULT 35 +#define FBNIC_RX_USECS_DEFAULT 30 +#define FBNIC_RX_FRAMES_DEFAULT 0 #define FBNIC_RX_TROOM \ SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) @@ -59,6 +62,7 @@ struct fbnic_queue_stats { union { struct { u64 csum_partial; + u64 lso; u64 ts_packets; u64 ts_lost; u64 stop; diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c index 3234a960fcc3..0af143ec0f86 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c @@ -828,7 +828,6 @@ static int lan966x_probe_port(struct lan966x *lan966x, u32 p, port->phylink_config.type = PHYLINK_NETDEV; port->phylink_pcs.poll = true; port->phylink_pcs.ops = &lan966x_phylink_pcs_ops; - port->phylink_pcs.neg_mode = true; port->phylink_config.mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | MAC_10 | MAC_100 | MAC_1000FD | MAC_2500FD; diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c index 6a0e5b83ecd0..74ad1d73b465 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c @@ -338,7 +338,6 @@ static int sparx5_create_port(struct sparx5 *sparx5, spx5_port->custom_etype = 0x8880; /* Vitesse */ spx5_port->phylink_pcs.poll = true; spx5_port->phylink_pcs.ops = &sparx5_phylink_pcs_ops; - spx5_port->phylink_pcs.neg_mode = true; spx5_port->is_mrouter = false; INIT_LIST_HEAD(&spx5_port->tc_templates); sparx5->ports[config->portno] = spx5_port; diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index be95336ce089..c15a5ef4674e 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -666,8 +666,11 @@ int mana_gd_create_hwc_queue(struct gdma_dev *gd, gmi = &queue->mem_info; err = mana_gd_alloc_memory(gc, spec->queue_size, gmi); - if (err) + if (err) { + dev_err(gc->dev, "GDMA queue type: %d, size: %u, gdma memory allocation err: %d\n", + spec->type, spec->queue_size, err); goto free_q; + } queue->head = 0; queue->tail = 0; @@ -688,6 +691,8 @@ int mana_gd_create_hwc_queue(struct gdma_dev *gd, *queue_ptr = queue; return 0; out: + dev_err(gc->dev, "Failed to create queue type %d of size %u, err: %d\n", + spec->type, spec->queue_size, err); mana_gd_free_memory(gmi); free_q: kfree(queue); @@ -770,7 +775,13 @@ static int mana_gd_create_dma_region(struct gdma_dev *gd, } gmi->dma_region_handle = resp.dma_region_handle; + dev_dbg(gc->dev, "Created DMA region handle 0x%llx\n", + gmi->dma_region_handle); out: + if (err) + dev_dbg(gc->dev, + "Failed to create DMA region of length: %u, page_type: %d, status: 0x%x, err: %d\n", + length, req->gdma_page_type, resp.hdr.status, err); kfree(req); return err; } @@ -793,8 +804,11 @@ int mana_gd_create_mana_eq(struct gdma_dev *gd, gmi = &queue->mem_info; err = mana_gd_alloc_memory(gc, spec->queue_size, gmi); - if (err) + if (err) { + dev_err(gc->dev, "GDMA queue type: %d, size: %u, gdma memory allocation err: %d\n", + spec->type, spec->queue_size, err); goto free_q; + } err = mana_gd_create_dma_region(gd, gmi); if (err) @@ -815,6 +829,8 @@ int mana_gd_create_mana_eq(struct gdma_dev *gd, *queue_ptr = queue; return 0; out: + dev_err(gc->dev, "Failed to create queue type %d of size: %u, err: %d\n", + spec->type, spec->queue_size, err); mana_gd_free_memory(gmi); free_q: kfree(queue); @@ -841,8 +857,11 @@ int mana_gd_create_mana_wq_cq(struct gdma_dev *gd, gmi = &queue->mem_info; err = mana_gd_alloc_memory(gc, spec->queue_size, gmi); - if (err) + if (err) { + dev_err(gc->dev, "GDMA queue type: %d, size: %u, memory allocation err: %d\n", + spec->type, spec->queue_size, err); goto free_q; + } err = mana_gd_create_dma_region(gd, gmi); if (err) @@ -862,6 +881,8 @@ int mana_gd_create_mana_wq_cq(struct gdma_dev *gd, *queue_ptr = queue; return 0; out: + dev_err(gc->dev, "Failed to create queue type %d of size: %u, err: %d\n", + spec->type, spec->queue_size, err); mana_gd_free_memory(gmi); free_q: kfree(queue); @@ -1157,8 +1178,11 @@ int mana_gd_post_and_ring(struct gdma_queue *queue, int err; err = mana_gd_post_work_request(queue, wqe_req, wqe_info); - if (err) + if (err) { + dev_err(gc->dev, "Failed to post work req from queue type %d of size %u (err=%d)\n", + queue->type, queue->queue_size, err); return err; + } mana_gd_wq_ring_doorbell(gc, queue); @@ -1435,8 +1459,10 @@ static int mana_gd_setup(struct pci_dev *pdev) mana_smc_init(&gc->shm_channel, gc->dev, gc->shm_base); err = mana_gd_setup_irqs(pdev); - if (err) + if (err) { + dev_err(gc->dev, "Failed to setup IRQs: %d\n", err); return err; + } err = mana_hwc_create_channel(gc); if (err) @@ -1454,12 +1480,14 @@ static int mana_gd_setup(struct pci_dev *pdev) if (err) goto destroy_hwc; + dev_dbg(&pdev->dev, "mana gdma setup successful\n"); return 0; destroy_hwc: mana_hwc_destroy_channel(gc); remove_irq: mana_gd_remove_irqs(pdev); + dev_err(&pdev->dev, "%s failed (error %d)\n", __func__, err); return err; } @@ -1470,6 +1498,7 @@ static void mana_gd_cleanup(struct pci_dev *pdev) mana_hwc_destroy_channel(gc); mana_gd_remove_irqs(pdev); + dev_dbg(&pdev->dev, "mana gdma cleanup successful\n"); } static bool mana_is_pf(unsigned short dev_id) @@ -1488,8 +1517,10 @@ static int mana_gd_probe(struct pci_dev *pdev, const struct pci_device_id *ent) BUILD_BUG_ON(2 * MAX_PORTS_IN_MANA_DEV * GDMA_EQE_SIZE > EQ_SIZE); err = pci_enable_device(pdev); - if (err) + if (err) { + dev_err(&pdev->dev, "Failed to enable pci device (err=%d)\n", err); return -ENXIO; + } pci_set_master(pdev); @@ -1498,9 +1529,10 @@ static int mana_gd_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto disable_dev; err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); - if (err) + if (err) { + dev_err(&pdev->dev, "DMA set mask failed: %d\n", err); goto release_region; - + } dma_set_max_seg_size(&pdev->dev, UINT_MAX); err = -ENOMEM; @@ -1575,6 +1607,8 @@ static void mana_gd_remove(struct pci_dev *pdev) pci_release_regions(pdev); pci_disable_device(pdev); + + dev_dbg(&pdev->dev, "mana gdma remove successful\n"); } /* The 'state' parameter is not used. */ diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c index a00f915c5188..1ba49602089b 100644 --- a/drivers/net/ethernet/microsoft/mana/hw_channel.c +++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c @@ -440,7 +440,8 @@ static int mana_hwc_alloc_dma_buf(struct hw_channel_context *hwc, u16 q_depth, gmi = &dma_buf->mem_info; err = mana_gd_alloc_memory(gc, buf_size, gmi); if (err) { - dev_err(hwc->dev, "Failed to allocate DMA buffer: %d\n", err); + dev_err(hwc->dev, "Failed to allocate DMA buffer size: %u, err %d\n", + buf_size, err); goto out; } @@ -529,6 +530,9 @@ static int mana_hwc_create_wq(struct hw_channel_context *hwc, out: if (err) mana_hwc_destroy_wq(hwc, hwc_wq); + + dev_err(hwc->dev, "Failed to create HWC queue size= %u type= %d err= %d\n", + queue_size, q_type, err); return err; } diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index aa1e47233fe5..0411a1897f57 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -52,10 +52,12 @@ static int mana_open(struct net_device *ndev) { struct mana_port_context *apc = netdev_priv(ndev); int err; - err = mana_alloc_queues(ndev); - if (err) + + if (err) { + netdev_err(ndev, "%s failed to allocate queues: %d\n", __func__, err); return err; + } apc->port_is_up = true; @@ -64,7 +66,7 @@ static int mana_open(struct net_device *ndev) netif_carrier_on(ndev); netif_tx_wake_all_queues(ndev); - + netdev_dbg(ndev, "%s successful\n", __func__); return 0; } @@ -176,6 +178,9 @@ static int mana_map_skb(struct sk_buff *skb, struct mana_port_context *apc, return 0; frag_err: + if (net_ratelimit()) + netdev_err(apc->ndev, "Failed to map skb of size %u to DMA\n", + skb->len); for (i = sg_i - 1; i >= hsg; i--) dma_unmap_page(dev, ash->dma_handle[i], ash->size[i], DMA_TO_DEVICE); @@ -256,6 +261,9 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev) if (skb_cow_head(skb, MANA_HEADROOM)) goto tx_drop_count; + if (unlikely(ipv6_hopopt_jumbo_remove(skb))) + goto tx_drop_count; + txq = &apc->tx_qp[txq_idx].txq; gdma_sq = txq->gdma_sq; cq = &apc->tx_qp[txq_idx].tx_cq; @@ -687,6 +695,7 @@ int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu, int num_qu return 0; error: + netdev_err(mpc->ndev, "Failed to pre-allocate RX buffers for %d queues\n", num_queues); mana_pre_dealloc_rxbufs(mpc); return -ENOMEM; } @@ -1304,8 +1313,10 @@ static int mana_create_eq(struct mana_context *ac) for (i = 0; i < gc->max_num_queues; i++) { spec.eq.msix_index = (i + 1) % gc->num_msix_usable; err = mana_gd_create_mana_eq(gd, &spec, &ac->eqs[i].eq); - if (err) + if (err) { + dev_err(gc->dev, "Failed to create EQ %d : %d\n", i, err); goto out; + } mana_create_eq_debugfs(ac, i); } @@ -2080,6 +2091,8 @@ static int mana_create_txq(struct mana_port_context *apc, return 0; out: + netdev_err(net, "Failed to create %d TX queues, %d\n", + apc->num_queues, err); mana_destroy_txq(apc); return err; } @@ -2415,6 +2428,7 @@ static int mana_add_rx_queues(struct mana_port_context *apc, rxq = mana_create_rxq(apc, i, &ac->eqs[i], ndev); if (!rxq) { err = -ENOMEM; + netdev_err(ndev, "Failed to create rxq %d : %d\n", i, err); goto out; } @@ -2661,12 +2675,18 @@ int mana_alloc_queues(struct net_device *ndev) int err; err = mana_create_vport(apc, ndev); - if (err) + if (err) { + netdev_err(ndev, "Failed to create vPort %u : %d\n", apc->port_idx, err); return err; + } err = netif_set_real_num_tx_queues(ndev, apc->num_queues); - if (err) + if (err) { + netdev_err(ndev, + "netif_set_real_num_tx_queues () failed for ndev with num_queues %u : %d\n", + apc->num_queues, err); goto destroy_vport; + } err = mana_add_rx_queues(apc, ndev); if (err) @@ -2675,14 +2695,20 @@ int mana_alloc_queues(struct net_device *ndev) apc->rss_state = apc->num_queues > 1 ? TRI_STATE_TRUE : TRI_STATE_FALSE; err = netif_set_real_num_rx_queues(ndev, apc->num_queues); - if (err) + if (err) { + netdev_err(ndev, + "netif_set_real_num_rx_queues () failed for ndev with num_queues %u : %d\n", + apc->num_queues, err); goto destroy_vport; + } mana_rss_table_init(apc); err = mana_config_rss(apc, TRI_STATE_TRUE, true, true); - if (err) + if (err) { + netdev_err(ndev, "Failed to configure RSS table: %d\n", err); goto destroy_vport; + } if (gd->gdma_context->is_pf) { err = mana_pf_register_filter(apc); @@ -2823,8 +2849,10 @@ int mana_detach(struct net_device *ndev, bool from_close) if (apc->port_st_save) { err = mana_dealloc_queues(ndev); - if (err) + if (err) { + netdev_err(ndev, "%s failed to deallocate queues: %d\n", __func__, err); return err; + } } if (!from_close) { @@ -2873,6 +2901,8 @@ static int mana_probe_port(struct mana_context *ac, int port_idx, ndev->dev_port = port_idx; SET_NETDEV_DEV(ndev, gc->dev); + netif_set_tso_max_size(ndev, GSO_MAX_SIZE); + netif_carrier_off(ndev); netdev_rss_key_fill(apc->hashkey, MANA_HASH_KEY_SIZE); @@ -2968,6 +2998,8 @@ static int add_adev(struct gdma_dev *gd) goto add_fail; gd->adev = adev; + dev_dbg(gd->gdma_context->dev, + "Auxiliary device added successfully\n"); return 0; add_fail: @@ -3009,8 +3041,10 @@ int mana_probe(struct gdma_dev *gd, bool resuming) } err = mana_create_eq(ac); - if (err) + if (err) { + dev_err(dev, "Failed to create EQs: %d\n", err); goto out; + } err = mana_query_device_cfg(ac, MANA_MAJOR_VERSION, MANA_MINOR_VERSION, MANA_MICRO_VERSION, &num_ports); @@ -3066,8 +3100,14 @@ int mana_probe(struct gdma_dev *gd, bool resuming) err = add_adev(gd); out: - if (err) + if (err) { mana_remove(gd, false); + } else { + dev_dbg(dev, "gd=%p, id=%u, num_ports=%d, type=%u, instance=%u\n", + gd, gd->dev_id.as_uint32, ac->num_ports, + gd->dev_id.type, gd->dev_id.instance); + dev_dbg(dev, "%s succeeded\n", __func__); + } return err; } @@ -3129,6 +3169,7 @@ out: gd->driver_data = NULL; gd->gdma_context = NULL; kfree(ac); + dev_dbg(dev, "%s succeeded\n", __func__); } struct net_device *mana_get_primary_netdev_rcu(struct mana_context *ac, u32 port_index) diff --git a/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c b/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c index 2ec62c8d86e1..59486fe2ad18 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c @@ -20,6 +20,8 @@ nfp_bpf_cmsg_alloc(struct nfp_app_bpf *bpf, unsigned int size) struct sk_buff *skb; skb = nfp_app_ctrl_msg_alloc(bpf->app, size, GFP_KERNEL); + if (!skb) + return NULL; skb_put(skb, size); return skb; diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c index f3bea196a8f9..ba8763cac9d9 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c @@ -117,11 +117,14 @@ static void rmnet_unregister_bridge(struct rmnet_port *port) rmnet_unregister_real_device(bridge_dev); } -static int rmnet_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +static int rmnet_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { + struct net *link_net = rtnl_newlink_link_net(params); u32 data_format = RMNET_FLAGS_INGRESS_DEAGGREGATION; + struct nlattr **data = params->data; + struct nlattr **tb = params->tb; struct net_device *real_dev; int mode = RMNET_EPMODE_VND; struct rmnet_endpoint *ep; @@ -134,7 +137,7 @@ static int rmnet_newlink(struct net *src_net, struct net_device *dev, return -EINVAL; } - real_dev = __dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK])); + real_dev = __dev_get_by_index(link_net, nla_get_u32(tb[IFLA_LINK])); if (!real_dev) { NL_SET_ERR_MSG_MOD(extack, "link does not exist"); return -ENODEV; diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 9fe53322d7bb..fa339bd8c775 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -5200,6 +5200,33 @@ static int r8169_mdio_write_reg(struct mii_bus *mii_bus, int phyaddr, return 0; } +static int r8169_mdio_read_reg_c45(struct mii_bus *mii_bus, int addr, + int devnum, int regnum) +{ + struct rtl8169_private *tp = mii_bus->priv; + + if (addr > 0) + return -ENODEV; + + if (devnum == MDIO_MMD_VEND2 && regnum > MDIO_STAT2) + return r8168_phy_ocp_read(tp, regnum); + + return 0; +} + +static int r8169_mdio_write_reg_c45(struct mii_bus *mii_bus, int addr, + int devnum, int regnum, u16 val) +{ + struct rtl8169_private *tp = mii_bus->priv; + + if (addr > 0 || devnum != MDIO_MMD_VEND2 || regnum <= MDIO_STAT2) + return -ENODEV; + + r8168_phy_ocp_write(tp, regnum, val); + + return 0; +} + static int r8169_mdio_register(struct rtl8169_private *tp) { struct pci_dev *pdev = tp->pci_dev; @@ -5230,6 +5257,11 @@ static int r8169_mdio_register(struct rtl8169_private *tp) new_bus->read = r8169_mdio_read_reg; new_bus->write = r8169_mdio_write_reg; + if (tp->mac_version >= RTL_GIGA_MAC_VER_40) { + new_bus->read_c45 = r8169_mdio_read_reg_c45; + new_bus->write_c45 = r8169_mdio_write_reg_c45; + } + ret = devm_mdiobus_register(&pdev->dev, new_bus); if (ret) return ret; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c index bd4eb187f8c6..392574bdd4a4 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c @@ -29,10 +29,8 @@ struct tegra_eqos { void __iomem *regs; struct reset_control *rst; - struct clk *clk_master; struct clk *clk_slave; struct clk *clk_tx; - struct clk *clk_rx; struct gpio_desc *reset; }; @@ -123,49 +121,14 @@ static int dwc_qos_probe(struct platform_device *pdev, struct plat_stmmacenet_data *plat_dat, struct stmmac_resources *stmmac_res) { - int err; - - plat_dat->stmmac_clk = devm_clk_get(&pdev->dev, "apb_pclk"); - if (IS_ERR(plat_dat->stmmac_clk)) { - dev_err(&pdev->dev, "apb_pclk clock not found.\n"); - return PTR_ERR(plat_dat->stmmac_clk); - } - - err = clk_prepare_enable(plat_dat->stmmac_clk); - if (err < 0) { - dev_err(&pdev->dev, "failed to enable apb_pclk clock: %d\n", - err); - return err; - } - - plat_dat->pclk = devm_clk_get(&pdev->dev, "phy_ref_clk"); - if (IS_ERR(plat_dat->pclk)) { - dev_err(&pdev->dev, "phy_ref_clk clock not found.\n"); - err = PTR_ERR(plat_dat->pclk); - goto disable; - } - - err = clk_prepare_enable(plat_dat->pclk); - if (err < 0) { - dev_err(&pdev->dev, "failed to enable phy_ref clock: %d\n", - err); - goto disable; + for (int i = 0; i < plat_dat->num_clks; i++) { + if (strcmp(plat_dat->clks[i].id, "apb_pclk") == 0) + plat_dat->stmmac_clk = plat_dat->clks[i].clk; + else if (strcmp(plat_dat->clks[i].id, "phy_ref_clk") == 0) + plat_dat->pclk = plat_dat->clks[i].clk; } return 0; - -disable: - clk_disable_unprepare(plat_dat->stmmac_clk); - return err; -} - -static void dwc_qos_remove(struct platform_device *pdev) -{ - struct net_device *ndev = platform_get_drvdata(pdev); - struct stmmac_priv *priv = netdev_priv(ndev); - - clk_disable_unprepare(priv->plat->pclk); - clk_disable_unprepare(priv->plat->stmmac_clk); } #define SDMEMCOMPPADCTRL 0x8800 @@ -178,7 +141,7 @@ static void dwc_qos_remove(struct platform_device *pdev) #define AUTO_CAL_STATUS 0x880c #define AUTO_CAL_STATUS_ACTIVE BIT(31) -static void tegra_eqos_fix_speed(void *priv, unsigned int speed, unsigned int mode) +static void tegra_eqos_fix_speed(void *priv, int speed, unsigned int mode) { struct tegra_eqos *eqos = priv; bool needs_calibration = false; @@ -197,7 +160,7 @@ static void tegra_eqos_fix_speed(void *priv, unsigned int speed, unsigned int mo break; default: - dev_err(eqos->dev, "invalid speed %u\n", speed); + dev_err(eqos->dev, "invalid speed %d\n", speed); break; } @@ -278,52 +241,19 @@ static int tegra_eqos_probe(struct platform_device *pdev, if (!is_of_node(dev->fwnode)) goto bypass_clk_reset_gpio; - eqos->clk_master = devm_clk_get(&pdev->dev, "master_bus"); - if (IS_ERR(eqos->clk_master)) { - err = PTR_ERR(eqos->clk_master); - goto error; - } - - err = clk_prepare_enable(eqos->clk_master); - if (err < 0) - goto error; - - eqos->clk_slave = devm_clk_get(&pdev->dev, "slave_bus"); - if (IS_ERR(eqos->clk_slave)) { - err = PTR_ERR(eqos->clk_slave); - goto disable_master; - } - - data->stmmac_clk = eqos->clk_slave; - - err = clk_prepare_enable(eqos->clk_slave); - if (err < 0) - goto disable_master; - - eqos->clk_rx = devm_clk_get(&pdev->dev, "rx"); - if (IS_ERR(eqos->clk_rx)) { - err = PTR_ERR(eqos->clk_rx); - goto disable_slave; - } - - err = clk_prepare_enable(eqos->clk_rx); - if (err < 0) - goto disable_slave; - - eqos->clk_tx = devm_clk_get(&pdev->dev, "tx"); - if (IS_ERR(eqos->clk_tx)) { - err = PTR_ERR(eqos->clk_tx); - goto disable_rx; + for (int i = 0; i < data->num_clks; i++) { + if (strcmp(data->clks[i].id, "slave_bus") == 0) { + eqos->clk_slave = data->clks[i].clk; + data->stmmac_clk = eqos->clk_slave; + } else if (strcmp(data->clks[i].id, "tx") == 0) { + eqos->clk_tx = data->clks[i].clk; + } } - err = clk_prepare_enable(eqos->clk_tx); - if (err < 0) - goto disable_rx; - eqos->reset = devm_gpiod_get(&pdev->dev, "phy-reset", GPIOD_OUT_HIGH); if (IS_ERR(eqos->reset)) { err = PTR_ERR(eqos->reset); - goto disable_tx; + return err; } usleep_range(2000, 4000); @@ -365,15 +295,7 @@ reset: reset_control_assert(eqos->rst); reset_phy: gpiod_set_value(eqos->reset, 1); -disable_tx: - clk_disable_unprepare(eqos->clk_tx); -disable_rx: - clk_disable_unprepare(eqos->clk_rx); -disable_slave: - clk_disable_unprepare(eqos->clk_slave); -disable_master: - clk_disable_unprepare(eqos->clk_master); -error: + return err; } @@ -383,10 +305,6 @@ static void tegra_eqos_remove(struct platform_device *pdev) reset_control_assert(eqos->rst); gpiod_set_value(eqos->reset, 1); - clk_disable_unprepare(eqos->clk_tx); - clk_disable_unprepare(eqos->clk_rx); - clk_disable_unprepare(eqos->clk_slave); - clk_disable_unprepare(eqos->clk_master); } struct dwc_eth_dwmac_data { @@ -398,7 +316,6 @@ struct dwc_eth_dwmac_data { static const struct dwc_eth_dwmac_data dwc_qos_data = { .probe = dwc_qos_probe, - .remove = dwc_qos_remove, }; static const struct dwc_eth_dwmac_data tegra_eqos_data = { @@ -434,9 +351,19 @@ static int dwc_eth_dwmac_probe(struct platform_device *pdev) if (IS_ERR(plat_dat)) return PTR_ERR(plat_dat); + ret = devm_clk_bulk_get_all(&pdev->dev, &plat_dat->clks); + if (ret < 0) + return dev_err_probe(&pdev->dev, ret, "Failed to retrieve all required clocks\n"); + plat_dat->num_clks = ret; + + ret = clk_bulk_prepare_enable(plat_dat->num_clks, plat_dat->clks); + if (ret) + return dev_err_probe(&pdev->dev, ret, "Failed to enable clocks\n"); + ret = data->probe(pdev, plat_dat, &stmmac_res); if (ret < 0) { dev_err_probe(&pdev->dev, ret, "failed to probe subdriver\n"); + clk_bulk_disable_unprepare(plat_dat->num_clks, plat_dat->clks); return ret; } @@ -451,7 +378,8 @@ static int dwc_eth_dwmac_probe(struct platform_device *pdev) return ret; remove: - data->remove(pdev); + if (data->remove) + data->remove(pdev); return ret; } @@ -459,10 +387,15 @@ remove: static void dwc_eth_dwmac_remove(struct platform_device *pdev) { const struct dwc_eth_dwmac_data *data = device_get_match_data(&pdev->dev); + struct plat_stmmacenet_data *plat_data = dev_get_platdata(&pdev->dev); stmmac_dvr_remove(&pdev->dev); - data->remove(pdev); + if (data->remove) + data->remove(pdev); + + if (plat_data) + clk_bulk_disable_unprepare(plat_data->num_clks, plat_data->clks); } static const struct of_device_id dwc_eth_dwmac_match[] = { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c index 20d3a202bb8d..610204b51e3f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c @@ -51,7 +51,7 @@ struct imx_dwmac_ops { int (*fix_soc_reset)(void *priv, void __iomem *ioaddr); int (*set_intf_mode)(struct plat_stmmacenet_data *plat_dat); - void (*fix_mac_speed)(void *priv, unsigned int speed, unsigned int mode); + void (*fix_mac_speed)(void *priv, int speed, unsigned int mode); }; struct imx_priv_data { @@ -192,7 +192,7 @@ static void imx_dwmac_exit(struct platform_device *pdev, void *priv) /* nothing to do now */ } -static void imx_dwmac_fix_speed(void *priv, unsigned int speed, unsigned int mode) +static void imx_dwmac_fix_speed(void *priv, int speed, unsigned int mode) { struct plat_stmmacenet_data *plat_dat; struct imx_priv_data *dwmac = priv; @@ -208,7 +208,7 @@ static void imx_dwmac_fix_speed(void *priv, unsigned int speed, unsigned int mod rate = rgmii_clock(speed); if (rate < 0) { - dev_err(dwmac->dev, "invalid speed %u\n", speed); + dev_err(dwmac->dev, "invalid speed %d\n", speed); return; } @@ -217,7 +217,7 @@ static void imx_dwmac_fix_speed(void *priv, unsigned int speed, unsigned int mod dev_err(dwmac->dev, "failed to set tx rate %lu\n", rate); } -static void imx93_dwmac_fix_speed(void *priv, unsigned int speed, unsigned int mode) +static void imx93_dwmac_fix_speed(void *priv, int speed, unsigned int mode) { struct imx_priv_data *dwmac = priv; unsigned int iface; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c index ddee6154d40b..0591756a2100 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c @@ -22,13 +22,13 @@ struct intel_dwmac { }; struct intel_dwmac_data { - void (*fix_mac_speed)(void *priv, unsigned int speed, unsigned int mode); + void (*fix_mac_speed)(void *priv, int speed, unsigned int mode); unsigned long ptp_ref_clk_rate; unsigned long tx_clk_rate; bool tx_clk_en; }; -static void kmb_eth_fix_mac_speed(void *priv, unsigned int speed, unsigned int mode) +static void kmb_eth_fix_mac_speed(void *priv, int speed, unsigned int mode) { struct intel_dwmac *dwmac = priv; long rate; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c index 61227dcf56dc..7f4b9c1cc32b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c @@ -112,7 +112,7 @@ struct ipq806x_gmac { phy_interface_t phy_mode; }; -static int get_clk_div_sgmii(struct ipq806x_gmac *gmac, unsigned int speed) +static int get_clk_div_sgmii(struct ipq806x_gmac *gmac, int speed) { struct device *dev = &gmac->pdev->dev; int div; @@ -138,7 +138,7 @@ static int get_clk_div_sgmii(struct ipq806x_gmac *gmac, unsigned int speed) return div; } -static int get_clk_div_rgmii(struct ipq806x_gmac *gmac, unsigned int speed) +static int get_clk_div_rgmii(struct ipq806x_gmac *gmac, int speed) { struct device *dev = &gmac->pdev->dev; int div; @@ -164,7 +164,7 @@ static int get_clk_div_rgmii(struct ipq806x_gmac *gmac, unsigned int speed) return div; } -static int ipq806x_gmac_set_speed(struct ipq806x_gmac *gmac, unsigned int speed) +static int ipq806x_gmac_set_speed(struct ipq806x_gmac *gmac, int speed) { uint32_t clk_bits, val; int div; @@ -260,7 +260,7 @@ static int ipq806x_gmac_of_parse(struct ipq806x_gmac *gmac) return PTR_ERR_OR_ZERO(gmac->qsgmii_csr); } -static void ipq806x_gmac_fix_mac_speed(void *priv, unsigned int speed, unsigned int mode) +static void ipq806x_gmac_fix_mac_speed(void *priv, int speed, unsigned int mode) { struct ipq806x_gmac *gmac = priv; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c index 79acdf38c525..60a4e3330ccd 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c @@ -149,8 +149,7 @@ static struct stmmac_pci_info loongson_gmac_pci_info = { .setup = loongson_gmac_data, }; -static void loongson_gnet_fix_speed(void *priv, unsigned int speed, - unsigned int mode) +static void loongson_gnet_fix_speed(void *priv, int speed, unsigned int mode) { struct loongson_data *ld = (struct loongson_data *)priv; struct net_device *ndev = dev_get_drvdata(ld->dev); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c index 5469fa1b429e..b115b7873cef 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c @@ -22,7 +22,7 @@ struct meson_dwmac { void __iomem *reg; }; -static void meson6_dwmac_fix_mac_speed(void *priv, unsigned int speed, unsigned int mode) +static void meson6_dwmac_fix_mac_speed(void *priv, int speed, unsigned int mode) { struct meson_dwmac *dwmac = priv; unsigned int val; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c index 2a5b38723635..192f270197c8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c @@ -111,7 +111,7 @@ struct qcom_ethqos { unsigned int link_clk_rate; struct clk *link_clk; struct phy *serdes_phy; - unsigned int speed; + int speed; int serdes_speed; phy_interface_t phy_mode; @@ -175,7 +175,7 @@ static void rgmii_dump(void *priv) #define RGMII_ID_MODE_10_LOW_SVS_CLK_FREQ (5 * 1000 * 1000UL) static void -ethqos_update_link_clk(struct qcom_ethqos *ethqos, unsigned int speed) +ethqos_update_link_clk(struct qcom_ethqos *ethqos, int speed) { if (!phy_interface_mode_is_rgmii(ethqos->phy_mode)) return; @@ -699,7 +699,7 @@ static int ethqos_configure(struct qcom_ethqos *ethqos) return ethqos->configure_func(ethqos); } -static void ethqos_fix_mac_speed(void *priv, unsigned int speed, unsigned int mode) +static void ethqos_fix_mac_speed(void *priv, int speed, unsigned int mode) { struct qcom_ethqos *ethqos = priv; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c index a4dc89e23a68..83d104a274c5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c @@ -1920,7 +1920,7 @@ static void rk_gmac_powerdown(struct rk_priv_data *gmac) gmac_clk_enable(gmac, false); } -static void rk_fix_speed(void *priv, unsigned int speed, unsigned int mode) +static void rk_fix_speed(void *priv, int speed, unsigned int mode) { struct rk_priv_data *bsp_priv = priv; struct device *dev = &bsp_priv->pdev->dev; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-s32.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-s32.c index 9cc0e5817416..6a498833b8ed 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-s32.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-s32.c @@ -100,7 +100,7 @@ static void s32_gmac_exit(struct platform_device *pdev, void *priv) clk_disable_unprepare(gmac->rx_clk); } -static void s32_fix_mac_speed(void *priv, unsigned int speed, unsigned int mode) +static void s32_fix_mac_speed(void *priv, int speed, unsigned int mode) { struct s32_priv_data *gmac = priv; long tx_clk_rate; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c index 16020b72dec8..6b78ae730466 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c @@ -61,7 +61,7 @@ struct socfpga_dwmac { struct mdio_device *pcs_mdiodev; }; -static void socfpga_dwmac_fix_mac_speed(void *priv, unsigned int speed, unsigned int mode) +static void socfpga_dwmac_fix_mac_speed(void *priv, int speed, unsigned int mode) { struct socfpga_dwmac *dwmac = (struct socfpga_dwmac *)priv; void __iomem *splitter_base = dwmac->splitter_base; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c index 0a0a363d3730..282c846dad0b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c @@ -31,7 +31,7 @@ struct starfive_dwmac { const struct starfive_dwmac_data *data; }; -static void starfive_dwmac_fix_mac_speed(void *priv, unsigned int speed, unsigned int mode) +static void starfive_dwmac_fix_mac_speed(void *priv, int speed, unsigned int mode) { struct starfive_dwmac *dwmac = priv; long rate; @@ -39,7 +39,7 @@ static void starfive_dwmac_fix_mac_speed(void *priv, unsigned int speed, unsigne rate = rgmii_clock(speed); if (rate < 0) { - dev_err(dwmac->dev, "invalid speed %u\n", speed); + dev_err(dwmac->dev, "invalid speed %d\n", speed); return; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c index f25461c292fe..13b9c2a51fce 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c @@ -99,12 +99,12 @@ struct sti_dwmac { int clk_sel_reg; /* GMAC ext clk selection register */ struct regmap *regmap; bool gmac_en; - u32 speed; - void (*fix_retime_src)(void *priv, unsigned int speed, unsigned int mode); + int speed; + void (*fix_retime_src)(void *priv, int speed, unsigned int mode); }; struct sti_dwmac_of_data { - void (*fix_retime_src)(void *priv, unsigned int speed, unsigned int mode); + void (*fix_retime_src)(void *priv, int speed, unsigned int mode); }; static u32 phy_intf_sels[] = { @@ -132,7 +132,7 @@ static u32 stih4xx_tx_retime_val[] = { | STIH4XX_ETH_SEL_INTERNAL_NOTEXT_PHYCLK, }; -static void stih4xx_fix_retime_src(void *priv, u32 spd, unsigned int mode) +static void stih4xx_fix_retime_src(void *priv, int spd, unsigned int mode) { struct sti_dwmac *dwmac = priv; u32 src = dwmac->tx_retime_src; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c index 9ae318436c4a..1b1ce2888b2e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c @@ -72,7 +72,7 @@ static void sun7i_gmac_exit(struct platform_device *pdev, void *priv) regulator_disable(gmac->regulator); } -static void sun7i_fix_speed(void *priv, unsigned int speed, unsigned int mode) +static void sun7i_fix_speed(void *priv, int speed, unsigned int mode) { struct sunxi_priv_data *gmac = priv; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c index dce84ed184e9..ddb1d8aba321 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c @@ -104,7 +104,7 @@ static int thead_dwmac_set_txclk_dir(struct plat_stmmacenet_data *plat) return 0; } -static void thead_dwmac_fix_speed(void *priv, unsigned int speed, unsigned int mode) +static void thead_dwmac_fix_speed(void *priv, int speed, unsigned int mode) { struct plat_stmmacenet_data *plat; struct thead_dwmac *dwmac = priv; @@ -142,7 +142,7 @@ static void thead_dwmac_fix_speed(void *priv, unsigned int speed, unsigned int m div = rate * 10 / GMAC_MII_RATE; break; default: - dev_err(dwmac->dev, "invalid speed %u\n", speed); + dev_err(dwmac->dev, "invalid speed %d\n", speed); return; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c index eccf7f537467..33cf99797df5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c @@ -54,7 +54,7 @@ struct visconti_eth { spinlock_t lock; /* lock to protect register update */ }; -static void visconti_eth_fix_mac_speed(void *priv, unsigned int speed, unsigned int mode) +static void visconti_eth_fix_mac_speed(void *priv, int speed, unsigned int mode) { struct visconti_eth *dwmac = priv; struct net_device *netdev = dev_get_drvdata(dwmac->dev); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c index 7900bf3effa7..a8b901cdf5cb 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c @@ -16,6 +16,7 @@ #include <linux/slab.h> #include <linux/ethtool.h> #include <linux/io.h> +#include <linux/string_choices.h> #include "stmmac.h" #include "stmmac_pcs.h" #include "stmmac_ptp.h" @@ -625,7 +626,7 @@ int dwmac1000_ptp_enable(struct ptp_clock_info *ptp, } netdev_dbg(priv->dev, "Auxiliary Snapshot %s.\n", - on ? "enabled" : "disabled"); + str_enabled_disabled(on)); writel(tcr_val, ptpaddr + PTP_TCR); /* wait for auxts fifo clear to finish */ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index 925d8b97a42b..b403029b1aaa 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -284,8 +284,7 @@ struct stmmac_priv { struct stmmac_channel channel[STMMAC_CH_MAX]; int speed; - unsigned int flow_ctrl; - unsigned int pause; + unsigned int pause_time; struct mii_bus *mii; struct phylink_config phylink_config; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 61ff545b74e3..edf4b1d651a6 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -88,13 +88,13 @@ MODULE_PARM_DESC(phyaddr, "Physical device address"); #define STMMAC_XDP_TX BIT(1) #define STMMAC_XDP_REDIRECT BIT(2) -static int flow_ctrl = FLOW_AUTO; +static int flow_ctrl = 0xdead; module_param(flow_ctrl, int, 0644); -MODULE_PARM_DESC(flow_ctrl, "Flow control ability [on/off]"); +MODULE_PARM_DESC(flow_ctrl, "Flow control ability [on/off] (obsolete)"); static int pause = PAUSE_TIME; module_param(pause, int, 0644); -MODULE_PARM_DESC(pause, "Flow Control Pause Time"); +MODULE_PARM_DESC(pause, "Flow Control Pause Time (units of 512 bit times)"); #define TC_DEFAULT 64 static int tc = TC_DEFAULT; @@ -188,12 +188,11 @@ static void stmmac_verify_args(void) watchdog = TX_TIMEO; if (unlikely((buf_sz < DEFAULT_BUFSIZE) || (buf_sz > BUF_SIZE_16KiB))) buf_sz = DEFAULT_BUFSIZE; - if (unlikely(flow_ctrl > 1)) - flow_ctrl = FLOW_AUTO; - else if (likely(flow_ctrl < 0)) - flow_ctrl = FLOW_OFF; if (unlikely((pause < 0) || (pause > 0xffff))) pause = PAUSE_TIME; + + if (flow_ctrl != 0xdead) + pr_warn("stmmac: module parameter 'flow_ctrl' is obsolete - please remove from your module configuration\n"); } static void __stmmac_disable_all_queues(struct stmmac_priv *priv) @@ -858,14 +857,16 @@ static void stmmac_release_ptp(struct stmmac_priv *priv) * stmmac_mac_flow_ctrl - Configure flow control in all queues * @priv: driver private structure * @duplex: duplex passed to the next function + * @flow_ctrl: desired flow control modes * Description: It is used for configuring the flow control in all queues */ -static void stmmac_mac_flow_ctrl(struct stmmac_priv *priv, u32 duplex) +static void stmmac_mac_flow_ctrl(struct stmmac_priv *priv, u32 duplex, + unsigned int flow_ctrl) { u32 tx_cnt = priv->plat->tx_queues_to_use; - stmmac_flow_ctrl(priv, priv->hw, duplex, priv->flow_ctrl, - priv->pause, tx_cnt); + stmmac_flow_ctrl(priv, priv->hw, duplex, flow_ctrl, priv->pause_time, + tx_cnt); } static unsigned long stmmac_mac_get_caps(struct phylink_config *config, @@ -925,6 +926,7 @@ static void stmmac_mac_link_up(struct phylink_config *config, bool tx_pause, bool rx_pause) { struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev)); + unsigned int flow_ctrl; u32 old_ctrl, ctrl; if ((priv->plat->flags & STMMAC_FLAG_SERDES_UP_AFTER_PHY_LINKUP) && @@ -1005,15 +1007,15 @@ static void stmmac_mac_link_up(struct phylink_config *config, /* Flow Control operation */ if (rx_pause && tx_pause) - priv->flow_ctrl = FLOW_AUTO; + flow_ctrl = FLOW_AUTO; else if (rx_pause && !tx_pause) - priv->flow_ctrl = FLOW_RX; + flow_ctrl = FLOW_RX; else if (!rx_pause && tx_pause) - priv->flow_ctrl = FLOW_TX; + flow_ctrl = FLOW_TX; else - priv->flow_ctrl = FLOW_OFF; + flow_ctrl = FLOW_OFF; - stmmac_mac_flow_ctrl(priv, duplex); + stmmac_mac_flow_ctrl(priv, duplex, flow_ctrl); if (ctrl != old_ctrl) writel(ctrl, priv->ioaddr + MAC_CTRL_REG); @@ -1046,10 +1048,6 @@ static void stmmac_mac_disable_tx_lpi(struct phylink_config *config) priv->tx_path_in_lpi_mode = false; 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); - mutex_unlock(&priv->lock); } @@ -1068,9 +1066,6 @@ static int stmmac_mac_enable_tx_lpi(struct phylink_config *config, u32 timer, stmmac_set_eee_timer(priv, priv->hw, STMMAC_DEFAULT_LIT_LS, STMMAC_DEFAULT_TWT_LS); - if (priv->hw->xpcs) - xpcs_config_eee(priv->hw->xpcs, priv->plat->mult_fact_100ns, - true); /* Try to cnfigure the hardware timer. */ ret = stmmac_set_lpi_mode(priv, priv->hw, STMMAC_LPI_TIMER, @@ -7424,7 +7419,7 @@ int stmmac_dvr_probe(struct device *device, return -ENOMEM; stmmac_set_ethtool_ops(ndev); - priv->pause = pause; + priv->pause_time = pause; priv->plat = plat_dat; priv->ioaddr = res->addr; priv->dev->base_addr = (unsigned long)res->addr; @@ -7620,9 +7615,6 @@ int stmmac_dvr_probe(struct device *device, "%s: warning: maxmtu having invalid value (%d)\n", __func__, priv->plat->maxmtu); - if (flow_ctrl) - priv->flow_ctrl = FLOW_AUTO; /* RX/TX pause on */ - ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE; /* Setup channels NAPI */ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c index 0c7d81ddd440..7c0a4046bbe3 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c @@ -524,6 +524,8 @@ int stmmac_pcs_setup(struct net_device *ndev) if (ret) return dev_err_probe(priv->device, ret, "No xPCS found\n"); + xpcs_config_eee_mult_fact(xpcs, priv->plat->mult_fact_100ns); + priv->hw->xpcs = xpcs; return 0; diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 2806238629f8..3e671be95d6f 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -164,6 +164,7 @@ #define AM65_CPSW_CPPI_TX_PKT_TYPE 0x7 /* XDP */ +#define AM65_CPSW_XDP_TX BIT(2) #define AM65_CPSW_XDP_CONSUMED BIT(1) #define AM65_CPSW_XDP_REDIRECT BIT(0) #define AM65_CPSW_XDP_PASS 0 @@ -829,19 +830,19 @@ static void am65_cpsw_nuss_tx_cleanup(void *data, dma_addr_t desc_dma) { struct am65_cpsw_tx_chn *tx_chn = data; enum am65_cpsw_tx_buf_type buf_type; + struct am65_cpsw_tx_swdata *swdata; struct cppi5_host_desc_t *desc_tx; struct xdp_frame *xdpf; struct sk_buff *skb; - void **swdata; desc_tx = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool, desc_dma); swdata = cppi5_hdesc_get_swdata(desc_tx); buf_type = am65_cpsw_nuss_buf_type(tx_chn, desc_dma); if (buf_type == AM65_CPSW_TX_BUF_TYPE_SKB) { - skb = *(swdata); + skb = swdata->skb; dev_kfree_skb_any(skb); } else { - xdpf = *(swdata); + xdpf = swdata->xdpf; xdp_return_frame(xdpf); } @@ -1098,10 +1099,10 @@ static int am65_cpsw_xdp_tx_frame(struct net_device *ndev, struct am65_cpsw_common *common = am65_ndev_to_common(ndev); struct am65_cpsw_port *port = am65_ndev_to_port(ndev); struct cppi5_host_desc_t *host_desc; + struct am65_cpsw_tx_swdata *swdata; struct netdev_queue *netif_txq; dma_addr_t dma_desc, dma_buf; u32 pkt_len = xdpf->len; - void **swdata; int ret; host_desc = k3_cppi_desc_pool_alloc(tx_chn->desc_pool); @@ -1131,7 +1132,8 @@ static int am65_cpsw_xdp_tx_frame(struct net_device *ndev, cppi5_hdesc_attach_buf(host_desc, dma_buf, pkt_len, dma_buf, pkt_len); swdata = cppi5_hdesc_get_swdata(host_desc); - *(swdata) = xdpf; + swdata->ndev = ndev; + swdata->xdpf = xdpf; /* Report BQL before sending the packet */ netif_txq = netdev_get_tx_queue(ndev, tx_chn->id); @@ -1167,17 +1169,16 @@ pool_free: static int am65_cpsw_run_xdp(struct am65_cpsw_rx_flow *flow, struct am65_cpsw_port *port, - struct xdp_buff *xdp, - int cpu, int *len) + struct xdp_buff *xdp, int *len) { struct am65_cpsw_common *common = flow->common; struct net_device *ndev = port->ndev; int ret = AM65_CPSW_XDP_CONSUMED; struct am65_cpsw_tx_chn *tx_chn; struct netdev_queue *netif_txq; + int cpu = smp_processor_id(); struct xdp_frame *xdpf; struct bpf_prog *prog; - struct page *page; int pkt_len; u32 act; int err; @@ -1193,8 +1194,7 @@ static int am65_cpsw_run_xdp(struct am65_cpsw_rx_flow *flow, switch (act) { case XDP_PASS: - ret = AM65_CPSW_XDP_PASS; - goto out; + return AM65_CPSW_XDP_PASS; case XDP_TX: tx_chn = &common->tx_chns[cpu % AM65_CPSW_MAX_QUEUES]; netif_txq = netdev_get_tx_queue(ndev, tx_chn->id); @@ -1213,15 +1213,13 @@ static int am65_cpsw_run_xdp(struct am65_cpsw_rx_flow *flow, goto drop; dev_sw_netstats_rx_add(ndev, pkt_len); - ret = AM65_CPSW_XDP_CONSUMED; - goto out; + return AM65_CPSW_XDP_TX; case XDP_REDIRECT: if (unlikely(xdp_do_redirect(ndev, xdp, prog))) goto drop; dev_sw_netstats_rx_add(ndev, pkt_len); - ret = AM65_CPSW_XDP_REDIRECT; - goto out; + return AM65_CPSW_XDP_REDIRECT; default: bpf_warn_invalid_xdp_action(ndev, prog, act); fallthrough; @@ -1233,10 +1231,6 @@ drop: ndev->stats.rx_dropped++; } - page = virt_to_head_page(xdp->data); - am65_cpsw_put_page(flow, page, true); - -out: return ret; } @@ -1274,7 +1268,7 @@ static void am65_cpsw_nuss_rx_csum(struct sk_buff *skb, u32 csum_info) } static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_rx_flow *flow, - int cpu, int *xdp_state) + int *xdp_state) { struct am65_cpsw_rx_chn *rx_chn = &flow->common->rx_chns; u32 buf_dma_len, pkt_len, port_id = 0, csum_info; @@ -1334,8 +1328,13 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_rx_flow *flow, xdp_init_buff(&xdp, PAGE_SIZE, &port->xdp_rxq[flow->id]); xdp_prepare_buff(&xdp, page_addr, AM65_CPSW_HEADROOM, pkt_len, false); - *xdp_state = am65_cpsw_run_xdp(flow, port, &xdp, - cpu, &pkt_len); + *xdp_state = am65_cpsw_run_xdp(flow, port, &xdp, &pkt_len); + if (*xdp_state == AM65_CPSW_XDP_CONSUMED) { + page = virt_to_head_page(xdp.data); + am65_cpsw_put_page(flow, page, true); + goto allocate; + } + if (*xdp_state != AM65_CPSW_XDP_PASS) goto allocate; @@ -1401,7 +1400,6 @@ static int am65_cpsw_nuss_rx_poll(struct napi_struct *napi_rx, int budget) { struct am65_cpsw_rx_flow *flow = am65_cpsw_napi_to_rx_flow(napi_rx); struct am65_cpsw_common *common = flow->common; - int cpu = smp_processor_id(); int xdp_state_or = 0; int cur_budget, ret; int xdp_state; @@ -1410,7 +1408,7 @@ static int am65_cpsw_nuss_rx_poll(struct napi_struct *napi_rx, int budget) /* process only this flow */ cur_budget = budget; while (cur_budget--) { - ret = am65_cpsw_nuss_rx_packets(flow, cpu, &xdp_state); + ret = am65_cpsw_nuss_rx_packets(flow, &xdp_state); xdp_state_or |= xdp_state; if (ret) break; @@ -1438,52 +1436,6 @@ static int am65_cpsw_nuss_rx_poll(struct napi_struct *napi_rx, int budget) return num_rx; } -static struct sk_buff * -am65_cpsw_nuss_tx_compl_packet_skb(struct am65_cpsw_tx_chn *tx_chn, - dma_addr_t desc_dma) -{ - struct cppi5_host_desc_t *desc_tx; - struct sk_buff *skb; - void **swdata; - - desc_tx = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool, - desc_dma); - swdata = cppi5_hdesc_get_swdata(desc_tx); - skb = *(swdata); - am65_cpsw_nuss_xmit_free(tx_chn, desc_tx); - - am65_cpts_tx_timestamp(tx_chn->common->cpts, skb); - - dev_sw_netstats_tx_add(skb->dev, 1, skb->len); - - return skb; -} - -static struct xdp_frame * -am65_cpsw_nuss_tx_compl_packet_xdp(struct am65_cpsw_common *common, - struct am65_cpsw_tx_chn *tx_chn, - dma_addr_t desc_dma, - struct net_device **ndev) -{ - struct cppi5_host_desc_t *desc_tx; - struct am65_cpsw_port *port; - struct xdp_frame *xdpf; - u32 port_id = 0; - void **swdata; - - desc_tx = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool, desc_dma); - cppi5_desc_get_tags_ids(&desc_tx->hdr, NULL, &port_id); - swdata = cppi5_hdesc_get_swdata(desc_tx); - xdpf = *(swdata); - am65_cpsw_nuss_xmit_free(tx_chn, desc_tx); - - port = am65_common_get_port(common, port_id); - dev_sw_netstats_tx_add(port->ndev, 1, xdpf->len); - *ndev = port->ndev; - - return xdpf; -} - static void am65_cpsw_nuss_tx_wake(struct am65_cpsw_tx_chn *tx_chn, struct net_device *ndev, struct netdev_queue *netif_txq) { @@ -1504,13 +1456,17 @@ static void am65_cpsw_nuss_tx_wake(struct am65_cpsw_tx_chn *tx_chn, struct net_d static int am65_cpsw_nuss_tx_compl_packets(struct am65_cpsw_common *common, int chn, unsigned int budget, bool *tdown) { + bool single_port = AM65_CPSW_IS_CPSW2G(common); enum am65_cpsw_tx_buf_type buf_type; + struct am65_cpsw_tx_swdata *swdata; + struct cppi5_host_desc_t *desc_tx; struct device *dev = common->dev; struct am65_cpsw_tx_chn *tx_chn; struct netdev_queue *netif_txq; unsigned int total_bytes = 0; struct net_device *ndev; struct xdp_frame *xdpf; + unsigned int pkt_len; struct sk_buff *skb; dma_addr_t desc_dma; int res, num_tx = 0; @@ -1518,9 +1474,12 @@ static int am65_cpsw_nuss_tx_compl_packets(struct am65_cpsw_common *common, tx_chn = &common->tx_chns[chn]; while (true) { - spin_lock(&tx_chn->lock); + if (!single_port) + spin_lock(&tx_chn->lock); res = k3_udma_glue_pop_tx_chn(tx_chn->tx_chn, &desc_dma); - spin_unlock(&tx_chn->lock); + if (!single_port) + spin_unlock(&tx_chn->lock); + if (res == -ENODATA) break; @@ -1531,27 +1490,43 @@ static int am65_cpsw_nuss_tx_compl_packets(struct am65_cpsw_common *common, break; } + desc_tx = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool, + desc_dma); + swdata = cppi5_hdesc_get_swdata(desc_tx); + ndev = swdata->ndev; buf_type = am65_cpsw_nuss_buf_type(tx_chn, desc_dma); if (buf_type == AM65_CPSW_TX_BUF_TYPE_SKB) { - skb = am65_cpsw_nuss_tx_compl_packet_skb(tx_chn, desc_dma); - ndev = skb->dev; - total_bytes = skb->len; + skb = swdata->skb; + am65_cpts_tx_timestamp(tx_chn->common->cpts, skb); + pkt_len = skb->len; napi_consume_skb(skb, budget); } else { - xdpf = am65_cpsw_nuss_tx_compl_packet_xdp(common, tx_chn, - desc_dma, &ndev); - total_bytes = xdpf->len; + xdpf = swdata->xdpf; + pkt_len = xdpf->len; if (buf_type == AM65_CPSW_TX_BUF_TYPE_XDP_TX) xdp_return_frame_rx_napi(xdpf); else xdp_return_frame(xdpf); } + + total_bytes += pkt_len; num_tx++; + am65_cpsw_nuss_xmit_free(tx_chn, desc_tx); + dev_sw_netstats_tx_add(ndev, 1, pkt_len); + if (!single_port) { + /* as packets from multi ports can be interleaved + * on the same channel, we have to figure out the + * port/queue at every packet and report it/wake queue. + */ + netif_txq = netdev_get_tx_queue(ndev, chn); + netdev_tx_completed_queue(netif_txq, 1, pkt_len); + am65_cpsw_nuss_tx_wake(tx_chn, ndev, netif_txq); + } + } + if (single_port) { netif_txq = netdev_get_tx_queue(ndev, chn); - netdev_tx_completed_queue(netif_txq, num_tx, total_bytes); - am65_cpsw_nuss_tx_wake(tx_chn, ndev, netif_txq); } @@ -1560,66 +1535,6 @@ static int am65_cpsw_nuss_tx_compl_packets(struct am65_cpsw_common *common, return num_tx; } -static int am65_cpsw_nuss_tx_compl_packets_2g(struct am65_cpsw_common *common, - int chn, unsigned int budget, bool *tdown) -{ - enum am65_cpsw_tx_buf_type buf_type; - struct device *dev = common->dev; - struct am65_cpsw_tx_chn *tx_chn; - struct netdev_queue *netif_txq; - unsigned int total_bytes = 0; - struct net_device *ndev; - struct xdp_frame *xdpf; - struct sk_buff *skb; - dma_addr_t desc_dma; - int res, num_tx = 0; - - tx_chn = &common->tx_chns[chn]; - - while (true) { - res = k3_udma_glue_pop_tx_chn(tx_chn->tx_chn, &desc_dma); - if (res == -ENODATA) - break; - - if (cppi5_desc_is_tdcm(desc_dma)) { - if (atomic_dec_and_test(&common->tdown_cnt)) - complete(&common->tdown_complete); - *tdown = true; - break; - } - - buf_type = am65_cpsw_nuss_buf_type(tx_chn, desc_dma); - if (buf_type == AM65_CPSW_TX_BUF_TYPE_SKB) { - skb = am65_cpsw_nuss_tx_compl_packet_skb(tx_chn, desc_dma); - ndev = skb->dev; - total_bytes += skb->len; - napi_consume_skb(skb, budget); - } else { - xdpf = am65_cpsw_nuss_tx_compl_packet_xdp(common, tx_chn, - desc_dma, &ndev); - total_bytes += xdpf->len; - if (buf_type == AM65_CPSW_TX_BUF_TYPE_XDP_TX) - xdp_return_frame_rx_napi(xdpf); - else - xdp_return_frame(xdpf); - } - num_tx++; - } - - if (!num_tx) - return 0; - - netif_txq = netdev_get_tx_queue(ndev, chn); - - netdev_tx_completed_queue(netif_txq, num_tx, total_bytes); - - am65_cpsw_nuss_tx_wake(tx_chn, ndev, netif_txq); - - dev_dbg(dev, "%s:%u pkt:%d\n", __func__, chn, num_tx); - - return num_tx; -} - static enum hrtimer_restart am65_cpsw_nuss_tx_timer_callback(struct hrtimer *timer) { struct am65_cpsw_tx_chn *tx_chns = @@ -1635,13 +1550,8 @@ static int am65_cpsw_nuss_tx_poll(struct napi_struct *napi_tx, int budget) bool tdown = false; int num_tx; - if (AM65_CPSW_IS_CPSW2G(tx_chn->common)) - num_tx = am65_cpsw_nuss_tx_compl_packets_2g(tx_chn->common, tx_chn->id, - budget, &tdown); - else - num_tx = am65_cpsw_nuss_tx_compl_packets(tx_chn->common, - tx_chn->id, budget, &tdown); - + num_tx = am65_cpsw_nuss_tx_compl_packets(tx_chn->common, + tx_chn->id, budget, &tdown); if (num_tx >= budget) return budget; @@ -1685,12 +1595,12 @@ static netdev_tx_t am65_cpsw_nuss_ndo_slave_xmit(struct sk_buff *skb, struct am65_cpsw_common *common = am65_ndev_to_common(ndev); struct cppi5_host_desc_t *first_desc, *next_desc, *cur_desc; struct am65_cpsw_port *port = am65_ndev_to_port(ndev); + struct am65_cpsw_tx_swdata *swdata; struct device *dev = common->dev; struct am65_cpsw_tx_chn *tx_chn; struct netdev_queue *netif_txq; dma_addr_t desc_dma, buf_dma; int ret, q_idx, i; - void **swdata; u32 *psdata; u32 pkt_len; @@ -1736,7 +1646,8 @@ static netdev_tx_t am65_cpsw_nuss_ndo_slave_xmit(struct sk_buff *skb, k3_udma_glue_tx_dma_to_cppi5_addr(tx_chn->tx_chn, &buf_dma); cppi5_hdesc_attach_buf(first_desc, buf_dma, pkt_len, buf_dma, pkt_len); swdata = cppi5_hdesc_get_swdata(first_desc); - *(swdata) = skb; + swdata->ndev = ndev; + swdata->skb = skb; psdata = cppi5_hdesc_get_psdata(first_desc); /* HW csum offload if enabled */ @@ -3578,6 +3489,10 @@ static int am65_cpsw_nuss_probe(struct platform_device *pdev) __be64 id_temp; int ret, i; + BUILD_BUG_ON_MSG(sizeof(struct am65_cpsw_tx_swdata) > AM65_CPSW_NAV_SW_DATA_SIZE, + "TX SW_DATA size exceeds AM65_CPSW_NAV_SW_DATA_SIZE"); + BUILD_BUG_ON_MSG(sizeof(struct am65_cpsw_swdata) > AM65_CPSW_NAV_SW_DATA_SIZE, + "SW_DATA size exceeds AM65_CPSW_NAV_SW_DATA_SIZE"); common = devm_kzalloc(dev, sizeof(struct am65_cpsw_common), GFP_KERNEL); if (!common) return -ENOMEM; diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.h b/drivers/net/ethernet/ti/am65-cpsw-nuss.h index e7832a5cf3cc..917c37e4e89b 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.h +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.h @@ -104,6 +104,14 @@ struct am65_cpsw_rx_flow { char name[32]; }; +struct am65_cpsw_tx_swdata { + struct net_device *ndev; + union { + struct sk_buff *skb; + struct xdp_frame *xdpf; + }; +}; + struct am65_cpsw_swdata { u32 flow_id; struct page *page; diff --git a/drivers/net/ethernet/wangxun/Kconfig b/drivers/net/ethernet/wangxun/Kconfig index e46ccebcfd22..6b60173fe1f5 100644 --- a/drivers/net/ethernet/wangxun/Kconfig +++ b/drivers/net/ethernet/wangxun/Kconfig @@ -18,6 +18,7 @@ if NET_VENDOR_WANGXUN config LIBWX tristate + depends on PTP_1588_CLOCK_OPTIONAL select PAGE_POOL help Common library for Wangxun(R) Ethernet drivers. diff --git a/drivers/net/ethernet/wangxun/libwx/Makefile b/drivers/net/ethernet/wangxun/libwx/Makefile index 42ccd6e4052e..e9f0f1f2309b 100644 --- a/drivers/net/ethernet/wangxun/libwx/Makefile +++ b/drivers/net/ethernet/wangxun/libwx/Makefile @@ -4,4 +4,4 @@ obj-$(CONFIG_LIBWX) += libwx.o -libwx-objs := wx_hw.o wx_lib.o wx_ethtool.o +libwx-objs := wx_hw.o wx_lib.o wx_ethtool.o wx_ptp.o diff --git a/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c b/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c index abe5921dde02..28f982fbc64c 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c @@ -41,6 +41,9 @@ static const struct wx_stats wx_gstrings_stats[] = { WX_STAT("rx_csum_offload_good_count", hw_csum_rx_good), WX_STAT("rx_csum_offload_errors", hw_csum_rx_error), WX_STAT("alloc_rx_buff_failed", alloc_rx_buff_failed), + WX_STAT("tx_hwtstamp_timeouts", tx_hwtstamp_timeouts), + WX_STAT("tx_hwtstamp_skipped", tx_hwtstamp_skipped), + WX_STAT("rx_hwtstamp_cleared", rx_hwtstamp_cleared), }; static const struct wx_stats wx_gstrings_fdir_stats[] = { @@ -452,3 +455,53 @@ void wx_set_msglevel(struct net_device *netdev, u32 data) wx->msg_enable = data; } EXPORT_SYMBOL(wx_set_msglevel); + +int wx_get_ts_info(struct net_device *dev, + struct kernel_ethtool_ts_info *info) +{ + struct wx *wx = netdev_priv(dev); + + info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) | + BIT(HWTSTAMP_FILTER_PTP_V1_L4_SYNC) | + BIT(HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ) | + BIT(HWTSTAMP_FILTER_PTP_V2_L2_EVENT) | + BIT(HWTSTAMP_FILTER_PTP_V2_L4_EVENT) | + BIT(HWTSTAMP_FILTER_PTP_V2_SYNC) | + BIT(HWTSTAMP_FILTER_PTP_V2_L2_SYNC) | + BIT(HWTSTAMP_FILTER_PTP_V2_L4_SYNC) | + BIT(HWTSTAMP_FILTER_PTP_V2_DELAY_REQ) | + BIT(HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ) | + BIT(HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ) | + BIT(HWTSTAMP_FILTER_PTP_V2_EVENT); + + info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_TX_HARDWARE | + SOF_TIMESTAMPING_RX_HARDWARE | + SOF_TIMESTAMPING_RAW_HARDWARE; + + if (wx->ptp_clock) + info->phc_index = ptp_clock_index(wx->ptp_clock); + else + info->phc_index = -1; + + info->tx_types = BIT(HWTSTAMP_TX_OFF) | + BIT(HWTSTAMP_TX_ON); + + return 0; +} +EXPORT_SYMBOL(wx_get_ts_info); + +void wx_get_ptp_stats(struct net_device *dev, + struct ethtool_ts_stats *ts_stats) +{ + struct wx *wx = netdev_priv(dev); + + if (wx->ptp_clock) { + ts_stats->pkts = wx->tx_hwtstamp_pkts; + ts_stats->lost = wx->tx_hwtstamp_timeouts + + wx->tx_hwtstamp_skipped + + wx->rx_hwtstamp_cleared; + ts_stats->err = wx->tx_hwtstamp_errors; + } +} +EXPORT_SYMBOL(wx_get_ptp_stats); diff --git a/drivers/net/ethernet/wangxun/libwx/wx_ethtool.h b/drivers/net/ethernet/wangxun/libwx/wx_ethtool.h index 600c3b597d1a..9e002e699eca 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_ethtool.h +++ b/drivers/net/ethernet/wangxun/libwx/wx_ethtool.h @@ -40,4 +40,8 @@ int wx_set_channels(struct net_device *dev, struct ethtool_channels *ch); u32 wx_get_msglevel(struct net_device *netdev); void wx_set_msglevel(struct net_device *netdev, u32 data); +int wx_get_ts_info(struct net_device *dev, + struct kernel_ethtool_ts_info *info); +void wx_get_ptp_stats(struct net_device *dev, + struct ethtool_ts_stats *ts_stats); #endif /* _WX_ETHTOOL_H_ */ diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.c b/drivers/net/ethernet/wangxun/libwx/wx_hw.c index deaf670c160e..907d13ade404 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_hw.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.c @@ -393,6 +393,25 @@ rel_out: } EXPORT_SYMBOL(wx_host_interface_command); +int wx_set_pps(struct wx *wx, bool enable, u64 nsec, u64 cycles) +{ + struct wx_hic_set_pps pps_cmd; + + pps_cmd.hdr.cmd = FW_PPS_SET_CMD; + pps_cmd.hdr.buf_len = FW_PPS_SET_LEN; + pps_cmd.hdr.cmd_or_resp.cmd_resv = FW_CEM_CMD_RESERVED; + pps_cmd.lan_id = wx->bus.func; + pps_cmd.enable = (u8)enable; + pps_cmd.nsec = nsec; + pps_cmd.cycles = cycles; + pps_cmd.hdr.checksum = FW_DEFAULT_CHECKSUM; + + return wx_host_interface_command(wx, (u32 *)&pps_cmd, + sizeof(pps_cmd), + WX_HI_COMMAND_TIMEOUT, + false); +} + /** * wx_read_ee_hostif_data - Read EEPROM word using a host interface cmd * assuming that the semaphore is already obtained. diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.h b/drivers/net/ethernet/wangxun/libwx/wx_hw.h index 11fb33349482..b883342bb576 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_hw.h +++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.h @@ -18,6 +18,7 @@ void wx_control_hw(struct wx *wx, bool drv); int wx_mng_present(struct wx *wx); int wx_host_interface_command(struct wx *wx, u32 *buffer, u32 length, u32 timeout, bool return_data); +int wx_set_pps(struct wx *wx, bool enable, u64 nsec, u64 cycles); int wx_read_ee_hostif(struct wx *wx, u16 offset, u16 *data); int wx_read_ee_hostif_buffer(struct wx *wx, u16 offset, u16 words, u16 *data); diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_lib.c index 2b3d6586f44a..42f90802870b 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_lib.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.c @@ -13,6 +13,7 @@ #include "wx_type.h" #include "wx_lib.h" +#include "wx_ptp.h" #include "wx_hw.h" /* Lookup table mapping the HW PTYPE to the bit field for decoding */ @@ -597,8 +598,17 @@ static void wx_process_skb_fields(struct wx_ring *rx_ring, union wx_rx_desc *rx_desc, struct sk_buff *skb) { + struct wx *wx = netdev_priv(rx_ring->netdev); + wx_rx_hash(rx_ring, rx_desc, skb); wx_rx_checksum(rx_ring, rx_desc, skb); + + if (unlikely(test_bit(WX_FLAG_RX_HWTSTAMP_ENABLED, wx->flags)) && + unlikely(wx_test_staterr(rx_desc, WX_RXD_STAT_TS))) { + wx_ptp_rx_hwtstamp(rx_ring->q_vector->wx, skb); + rx_ring->last_rx_timestamp = jiffies; + } + wx_rx_vlan(rx_ring, rx_desc, skb); skb_record_rx_queue(skb, rx_ring->queue_index); skb->protocol = eth_type_trans(skb, rx_ring->netdev); @@ -705,6 +715,7 @@ static bool wx_clean_tx_irq(struct wx_q_vector *q_vector, { unsigned int budget = q_vector->wx->tx_work_limit; unsigned int total_bytes = 0, total_packets = 0; + struct wx *wx = netdev_priv(tx_ring->netdev); unsigned int i = tx_ring->next_to_clean; struct wx_tx_buffer *tx_buffer; union wx_tx_desc *tx_desc; @@ -737,6 +748,11 @@ static bool wx_clean_tx_irq(struct wx_q_vector *q_vector, total_bytes += tx_buffer->bytecount; total_packets += tx_buffer->gso_segs; + /* schedule check for Tx timestamp */ + if (unlikely(test_bit(WX_STATE_PTP_TX_IN_PROGRESS, wx->state)) && + skb_shinfo(tx_buffer->skb)->tx_flags & SKBTX_IN_PROGRESS) + ptp_schedule_worker(wx->ptp_clock, 0); + /* free the skb */ napi_consume_skb(tx_buffer->skb, napi_budget); @@ -932,9 +948,9 @@ static void wx_tx_olinfo_status(union wx_tx_desc *tx_desc, tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status); } -static void wx_tx_map(struct wx_ring *tx_ring, - struct wx_tx_buffer *first, - const u8 hdr_len) +static int wx_tx_map(struct wx_ring *tx_ring, + struct wx_tx_buffer *first, + const u8 hdr_len) { struct sk_buff *skb = first->skb; struct wx_tx_buffer *tx_buffer; @@ -1013,6 +1029,8 @@ static void wx_tx_map(struct wx_ring *tx_ring, netdev_tx_sent_queue(wx_txring_txq(tx_ring), first->bytecount); + /* set the timestamp */ + first->time_stamp = jiffies; skb_tx_timestamp(skb); /* Force memory writes to complete before letting h/w know there @@ -1038,7 +1056,7 @@ static void wx_tx_map(struct wx_ring *tx_ring, if (netif_xmit_stopped(wx_txring_txq(tx_ring)) || !netdev_xmit_more()) writel(i, tx_ring->tail); - return; + return 0; dma_error: dev_err(tx_ring->dev, "TX DMA map failed\n"); @@ -1062,6 +1080,8 @@ dma_error: first->skb = NULL; tx_ring->next_to_use = i; + + return -ENOMEM; } static void wx_tx_ctxtdesc(struct wx_ring *tx_ring, u32 vlan_macip_lens, @@ -1486,6 +1506,20 @@ static netdev_tx_t wx_xmit_frame_ring(struct sk_buff *skb, tx_flags |= WX_TX_FLAGS_HW_VLAN; } + if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && + wx->ptp_clock) { + if (wx->tstamp_config.tx_type == HWTSTAMP_TX_ON && + !test_and_set_bit_lock(WX_STATE_PTP_TX_IN_PROGRESS, + wx->state)) { + skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; + tx_flags |= WX_TX_FLAGS_TSTAMP; + wx->ptp_tx_skb = skb_get(skb); + wx->ptp_tx_start = jiffies; + } else { + wx->tx_hwtstamp_skipped++; + } + } + /* record initial flags and protocol */ first->tx_flags = tx_flags; first->protocol = vlan_get_protocol(skb); @@ -1501,12 +1535,20 @@ static netdev_tx_t wx_xmit_frame_ring(struct sk_buff *skb, if (test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags) && tx_ring->atr_sample_rate) wx->atr(tx_ring, first, ptype); - wx_tx_map(tx_ring, first, hdr_len); + if (wx_tx_map(tx_ring, first, hdr_len)) + goto cleanup_tx_tstamp; return NETDEV_TX_OK; out_drop: dev_kfree_skb_any(first->skb); first->skb = NULL; +cleanup_tx_tstamp: + if (unlikely(tx_flags & WX_TX_FLAGS_TSTAMP)) { + dev_kfree_skb_any(wx->ptp_tx_skb); + wx->ptp_tx_skb = NULL; + wx->tx_hwtstamp_errors++; + clear_bit_unlock(WX_STATE_PTP_TX_IN_PROGRESS, wx->state); + } return NETDEV_TX_OK; } diff --git a/drivers/net/ethernet/wangxun/libwx/wx_ptp.c b/drivers/net/ethernet/wangxun/libwx/wx_ptp.c new file mode 100644 index 000000000000..07c015ba338f --- /dev/null +++ b/drivers/net/ethernet/wangxun/libwx/wx_ptp.c @@ -0,0 +1,883 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2015 - 2025 Beijing WangXun Technology Co., Ltd. */ +/* Copyright (c) 1999 - 2025 Intel Corporation. */ + +#include <linux/ptp_classify.h> +#include <linux/clocksource.h> +#include <linux/pci.h> + +#include "wx_type.h" +#include "wx_ptp.h" +#include "wx_hw.h" + +#define WX_INCVAL_10GB 0xCCCCCC +#define WX_INCVAL_1GB 0x800000 +#define WX_INCVAL_100 0xA00000 +#define WX_INCVAL_10 0xC7F380 +#define WX_INCVAL_EM 0x2000000 + +#define WX_INCVAL_SHIFT_10GB 20 +#define WX_INCVAL_SHIFT_1GB 18 +#define WX_INCVAL_SHIFT_100 15 +#define WX_INCVAL_SHIFT_10 12 +#define WX_INCVAL_SHIFT_EM 22 + +#define WX_OVERFLOW_PERIOD (HZ * 30) +#define WX_PTP_TX_TIMEOUT (HZ) + +#define WX_1588_PPS_WIDTH_EM 120 + +#define WX_NS_PER_SEC 1000000000ULL + +static u64 wx_ptp_timecounter_cyc2time(struct wx *wx, u64 timestamp) +{ + unsigned int seq; + u64 ns; + + do { + seq = read_seqbegin(&wx->hw_tc_lock); + ns = timecounter_cyc2time(&wx->hw_tc, timestamp); + } while (read_seqretry(&wx->hw_tc_lock, seq)); + + return ns; +} + +static u64 wx_ptp_readtime(struct wx *wx, struct ptp_system_timestamp *sts) +{ + u32 timeh1, timeh2, timel; + + timeh1 = rd32ptp(wx, WX_TSC_1588_SYSTIMH); + ptp_read_system_prets(sts); + timel = rd32ptp(wx, WX_TSC_1588_SYSTIML); + ptp_read_system_postts(sts); + timeh2 = rd32ptp(wx, WX_TSC_1588_SYSTIMH); + + if (timeh1 != timeh2) { + ptp_read_system_prets(sts); + timel = rd32ptp(wx, WX_TSC_1588_SYSTIML); + ptp_read_system_prets(sts); + } + return (u64)timel | (u64)timeh2 << 32; +} + +static int wx_ptp_adjfine(struct ptp_clock_info *ptp, long ppb) +{ + struct wx *wx = container_of(ptp, struct wx, ptp_caps); + u64 incval, mask; + + smp_mb(); /* Force any pending update before accessing. */ + incval = READ_ONCE(wx->base_incval); + incval = adjust_by_scaled_ppm(incval, ppb); + + mask = (wx->mac.type == wx_mac_em) ? 0x7FFFFFF : 0xFFFFFF; + incval &= mask; + if (wx->mac.type != wx_mac_em) + incval |= 2 << 24; + + wr32ptp(wx, WX_TSC_1588_INC, incval); + + return 0; +} + +static int wx_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) +{ + struct wx *wx = container_of(ptp, struct wx, ptp_caps); + unsigned long flags; + + write_seqlock_irqsave(&wx->hw_tc_lock, flags); + timecounter_adjtime(&wx->hw_tc, delta); + write_sequnlock_irqrestore(&wx->hw_tc_lock, flags); + + if (wx->ptp_setup_sdp) + wx->ptp_setup_sdp(wx); + + return 0; +} + +static int wx_ptp_gettimex64(struct ptp_clock_info *ptp, + struct timespec64 *ts, + struct ptp_system_timestamp *sts) +{ + struct wx *wx = container_of(ptp, struct wx, ptp_caps); + u64 ns, stamp; + + stamp = wx_ptp_readtime(wx, sts); + ns = wx_ptp_timecounter_cyc2time(wx, stamp); + *ts = ns_to_timespec64(ns); + + return 0; +} + +static int wx_ptp_settime64(struct ptp_clock_info *ptp, + const struct timespec64 *ts) +{ + struct wx *wx = container_of(ptp, struct wx, ptp_caps); + unsigned long flags; + u64 ns; + + ns = timespec64_to_ns(ts); + /* reset the timecounter */ + write_seqlock_irqsave(&wx->hw_tc_lock, flags); + timecounter_init(&wx->hw_tc, &wx->hw_cc, ns); + write_sequnlock_irqrestore(&wx->hw_tc_lock, flags); + + if (wx->ptp_setup_sdp) + wx->ptp_setup_sdp(wx); + + return 0; +} + +/** + * wx_ptp_clear_tx_timestamp - utility function to clear Tx timestamp state + * @wx: the private board structure + * + * This function should be called whenever the state related to a Tx timestamp + * needs to be cleared. This helps ensure that all related bits are reset for + * the next Tx timestamp event. + */ +static void wx_ptp_clear_tx_timestamp(struct wx *wx) +{ + rd32ptp(wx, WX_TSC_1588_STMPH); + if (wx->ptp_tx_skb) { + dev_kfree_skb_any(wx->ptp_tx_skb); + wx->ptp_tx_skb = NULL; + } + clear_bit_unlock(WX_STATE_PTP_TX_IN_PROGRESS, wx->state); +} + +/** + * wx_ptp_convert_to_hwtstamp - convert register value to hw timestamp + * @wx: private board structure + * @hwtstamp: stack timestamp structure + * @timestamp: unsigned 64bit system time value + * + * We need to convert the adapter's RX/TXSTMP registers into a hwtstamp value + * which can be used by the stack's ptp functions. + * + * The lock is used to protect consistency of the cyclecounter and the SYSTIME + * registers. However, it does not need to protect against the Rx or Tx + * timestamp registers, as there can't be a new timestamp until the old one is + * unlatched by reading. + * + * In addition to the timestamp in hardware, some controllers need a software + * overflow cyclecounter, and this function takes this into account as well. + **/ +static void wx_ptp_convert_to_hwtstamp(struct wx *wx, + struct skb_shared_hwtstamps *hwtstamp, + u64 timestamp) +{ + u64 ns; + + ns = wx_ptp_timecounter_cyc2time(wx, timestamp); + hwtstamp->hwtstamp = ns_to_ktime(ns); +} + +/** + * wx_ptp_tx_hwtstamp - utility function which checks for TX time stamp + * @wx: the private board struct + * + * if the timestamp is valid, we convert it into the timecounter ns + * value, then store that result into the shhwtstamps structure which + * is passed up the network stack + */ +static void wx_ptp_tx_hwtstamp(struct wx *wx) +{ + struct skb_shared_hwtstamps shhwtstamps; + struct sk_buff *skb = wx->ptp_tx_skb; + u64 regval = 0; + + regval |= (u64)rd32ptp(wx, WX_TSC_1588_STMPL); + regval |= (u64)rd32ptp(wx, WX_TSC_1588_STMPH) << 32; + + wx_ptp_convert_to_hwtstamp(wx, &shhwtstamps, regval); + + wx->ptp_tx_skb = NULL; + clear_bit_unlock(WX_STATE_PTP_TX_IN_PROGRESS, wx->state); + skb_tstamp_tx(skb, &shhwtstamps); + dev_kfree_skb_any(skb); + wx->tx_hwtstamp_pkts++; +} + +static int wx_ptp_tx_hwtstamp_work(struct wx *wx) +{ + u32 tsynctxctl; + + /* we have to have a valid skb to poll for a timestamp */ + if (!wx->ptp_tx_skb) { + wx_ptp_clear_tx_timestamp(wx); + return 0; + } + + /* stop polling once we have a valid timestamp */ + tsynctxctl = rd32ptp(wx, WX_TSC_1588_CTL); + if (tsynctxctl & WX_TSC_1588_CTL_VALID) { + wx_ptp_tx_hwtstamp(wx); + return 0; + } + + return -1; +} + +/** + * wx_ptp_overflow_check - watchdog task to detect SYSTIME overflow + * @wx: pointer to wx struct + * + * this watchdog task periodically reads the timecounter + * in order to prevent missing when the system time registers wrap + * around. This needs to be run approximately twice a minute for the fastest + * overflowing hardware. We run it for all hardware since it shouldn't have a + * large impact. + */ +static void wx_ptp_overflow_check(struct wx *wx) +{ + bool timeout = time_is_before_jiffies(wx->last_overflow_check + + WX_OVERFLOW_PERIOD); + unsigned long flags; + + if (timeout) { + /* Update the timecounter */ + write_seqlock_irqsave(&wx->hw_tc_lock, flags); + timecounter_read(&wx->hw_tc); + write_sequnlock_irqrestore(&wx->hw_tc_lock, flags); + + wx->last_overflow_check = jiffies; + } +} + +/** + * wx_ptp_rx_hang - detect error case when Rx timestamp registers latched + * @wx: pointer to wx struct + * + * this watchdog task is scheduled to detect error case where hardware has + * dropped an Rx packet that was timestamped when the ring is full. The + * particular error is rare but leaves the device in a state unable to + * timestamp any future packets. + */ +static void wx_ptp_rx_hang(struct wx *wx) +{ + struct wx_ring *rx_ring; + unsigned long rx_event; + u32 tsyncrxctl; + int n; + + tsyncrxctl = rd32(wx, WX_PSR_1588_CTL); + + /* if we don't have a valid timestamp in the registers, just update the + * timeout counter and exit + */ + if (!(tsyncrxctl & WX_PSR_1588_CTL_VALID)) { + wx->last_rx_ptp_check = jiffies; + return; + } + + /* determine the most recent watchdog or rx_timestamp event */ + rx_event = wx->last_rx_ptp_check; + for (n = 0; n < wx->num_rx_queues; n++) { + rx_ring = wx->rx_ring[n]; + if (time_after(rx_ring->last_rx_timestamp, rx_event)) + rx_event = rx_ring->last_rx_timestamp; + } + + /* only need to read the high RXSTMP register to clear the lock */ + if (time_is_before_jiffies(rx_event + 5 * HZ)) { + rd32(wx, WX_PSR_1588_STMPH); + wx->last_rx_ptp_check = jiffies; + + wx->rx_hwtstamp_cleared++; + dev_warn(&wx->pdev->dev, "clearing RX Timestamp hang"); + } +} + +/** + * wx_ptp_tx_hang - detect error case where Tx timestamp never finishes + * @wx: private network wx structure + */ +static void wx_ptp_tx_hang(struct wx *wx) +{ + bool timeout = time_is_before_jiffies(wx->ptp_tx_start + + WX_PTP_TX_TIMEOUT); + + if (!wx->ptp_tx_skb) + return; + + if (!test_bit(WX_STATE_PTP_TX_IN_PROGRESS, wx->state)) + return; + + /* If we haven't received a timestamp within the timeout, it is + * reasonable to assume that it will never occur, so we can unlock the + * timestamp bit when this occurs. + */ + if (timeout) { + wx_ptp_clear_tx_timestamp(wx); + wx->tx_hwtstamp_timeouts++; + dev_warn(&wx->pdev->dev, "clearing Tx timestamp hang\n"); + } +} + +static long wx_ptp_do_aux_work(struct ptp_clock_info *ptp) +{ + struct wx *wx = container_of(ptp, struct wx, ptp_caps); + int ts_done; + + ts_done = wx_ptp_tx_hwtstamp_work(wx); + + wx_ptp_overflow_check(wx); + if (unlikely(test_bit(WX_FLAG_RX_HWTSTAMP_IN_REGISTER, + wx->flags))) + wx_ptp_rx_hang(wx); + wx_ptp_tx_hang(wx); + + return ts_done ? 1 : HZ; +} + +static u64 wx_ptp_trigger_calc(struct wx *wx) +{ + struct cyclecounter *cc = &wx->hw_cc; + unsigned long flags; + u64 ns = 0; + u32 rem; + + /* Read the current clock time, and save the cycle counter value */ + write_seqlock_irqsave(&wx->hw_tc_lock, flags); + ns = timecounter_read(&wx->hw_tc); + wx->pps_edge_start = wx->hw_tc.cycle_last; + write_sequnlock_irqrestore(&wx->hw_tc_lock, flags); + wx->pps_edge_end = wx->pps_edge_start; + + /* Figure out how far past the next second we are */ + div_u64_rem(ns, WX_NS_PER_SEC, &rem); + + /* Figure out how many nanoseconds to add to round the clock edge up + * to the next full second + */ + rem = (WX_NS_PER_SEC - rem); + + /* Adjust the clock edge to align with the next full second. */ + wx->pps_edge_start += div_u64(((u64)rem << cc->shift), cc->mult); + wx->pps_edge_end += div_u64(((u64)(rem + wx->pps_width) << + cc->shift), cc->mult); + + return (ns + rem); +} + +static int wx_ptp_setup_sdp(struct wx *wx) +{ + struct cyclecounter *cc = &wx->hw_cc; + u32 tsauxc; + u64 nsec; + + if (wx->pps_width >= WX_NS_PER_SEC) { + wx_err(wx, "PTP pps width cannot be longer than 1s!\n"); + return -EINVAL; + } + + /* disable the pin first */ + wr32ptp(wx, WX_TSC_1588_AUX_CTL, 0); + WX_WRITE_FLUSH(wx); + + if (!test_bit(WX_FLAG_PTP_PPS_ENABLED, wx->flags)) { + if (wx->pps_enabled) { + wx->pps_enabled = false; + wx_set_pps(wx, false, 0, 0); + } + return 0; + } + + wx->pps_enabled = true; + nsec = wx_ptp_trigger_calc(wx); + wx_set_pps(wx, wx->pps_enabled, nsec, wx->pps_edge_start); + + tsauxc = WX_TSC_1588_AUX_CTL_PLSG | WX_TSC_1588_AUX_CTL_EN_TT0 | + WX_TSC_1588_AUX_CTL_EN_TT1 | WX_TSC_1588_AUX_CTL_EN_TS0; + wr32ptp(wx, WX_TSC_1588_TRGT_L(0), (u32)wx->pps_edge_start); + wr32ptp(wx, WX_TSC_1588_TRGT_H(0), (u32)(wx->pps_edge_start >> 32)); + wr32ptp(wx, WX_TSC_1588_TRGT_L(1), (u32)wx->pps_edge_end); + wr32ptp(wx, WX_TSC_1588_TRGT_H(1), (u32)(wx->pps_edge_end >> 32)); + wr32ptp(wx, WX_TSC_1588_SDP(0), + WX_TSC_1588_SDP_FUN_SEL_TT0 | WX_TSC_1588_SDP_OUT_LEVEL_H); + wr32ptp(wx, WX_TSC_1588_SDP(1), WX_TSC_1588_SDP_FUN_SEL_TS0); + wr32ptp(wx, WX_TSC_1588_AUX_CTL, tsauxc); + wr32ptp(wx, WX_TSC_1588_INT_EN, WX_TSC_1588_INT_EN_TT1); + WX_WRITE_FLUSH(wx); + + /* Adjust the clock edge to align with the next full second. */ + wx->sec_to_cc = div_u64(((u64)WX_NS_PER_SEC << cc->shift), cc->mult); + + return 0; +} + +static int wx_ptp_feature_enable(struct ptp_clock_info *ptp, + struct ptp_clock_request *rq, int on) +{ + struct wx *wx = container_of(ptp, struct wx, ptp_caps); + + /** + * When PPS is enabled, unmask the interrupt for the ClockOut + * feature, so that the interrupt handler can send the PPS + * event when the clock SDP triggers. Clear mask when PPS is + * disabled + */ + if (rq->type != PTP_CLK_REQ_PEROUT || !wx->ptp_setup_sdp) + return -EOPNOTSUPP; + + /* Reject requests with unsupported flags */ + if (rq->perout.flags & ~(PTP_PEROUT_DUTY_CYCLE | + PTP_PEROUT_PHASE)) + return -EOPNOTSUPP; + + if (rq->perout.phase.sec || rq->perout.phase.nsec) { + wx_err(wx, "Absolute start time not supported.\n"); + return -EINVAL; + } + + if (rq->perout.period.sec != 1 || rq->perout.period.nsec) { + wx_err(wx, "Only 1pps is supported.\n"); + return -EINVAL; + } + + if (rq->perout.flags & PTP_PEROUT_DUTY_CYCLE) { + struct timespec64 ts_on; + + ts_on.tv_sec = rq->perout.on.sec; + ts_on.tv_nsec = rq->perout.on.nsec; + wx->pps_width = timespec64_to_ns(&ts_on); + } else { + wx->pps_width = 120000000; + } + + if (on) + set_bit(WX_FLAG_PTP_PPS_ENABLED, wx->flags); + else + clear_bit(WX_FLAG_PTP_PPS_ENABLED, wx->flags); + + return wx->ptp_setup_sdp(wx); +} + +void wx_ptp_check_pps_event(struct wx *wx) +{ + u32 tsauxc, int_status; + + /* this check is necessary in case the interrupt was enabled via some + * alternative means (ex. debug_fs). Better to check here than + * everywhere that calls this function. + */ + if (!wx->ptp_clock) + return; + + int_status = rd32ptp(wx, WX_TSC_1588_INT_ST); + if (int_status & WX_TSC_1588_INT_ST_TT1) { + /* disable the pin first */ + wr32ptp(wx, WX_TSC_1588_AUX_CTL, 0); + WX_WRITE_FLUSH(wx); + + wx_ptp_trigger_calc(wx); + + tsauxc = WX_TSC_1588_AUX_CTL_PLSG | WX_TSC_1588_AUX_CTL_EN_TT0 | + WX_TSC_1588_AUX_CTL_EN_TT1 | WX_TSC_1588_AUX_CTL_EN_TS0; + wr32ptp(wx, WX_TSC_1588_TRGT_L(0), (u32)wx->pps_edge_start); + wr32ptp(wx, WX_TSC_1588_TRGT_H(0), (u32)(wx->pps_edge_start >> 32)); + wr32ptp(wx, WX_TSC_1588_TRGT_L(1), (u32)wx->pps_edge_end); + wr32ptp(wx, WX_TSC_1588_TRGT_H(1), (u32)(wx->pps_edge_end >> 32)); + wr32ptp(wx, WX_TSC_1588_AUX_CTL, tsauxc); + WX_WRITE_FLUSH(wx); + } +} +EXPORT_SYMBOL(wx_ptp_check_pps_event); + +static long wx_ptp_create_clock(struct wx *wx) +{ + struct net_device *netdev = wx->netdev; + long err; + + /* do nothing if we already have a clock device */ + if (!IS_ERR_OR_NULL(wx->ptp_clock)) + return 0; + + snprintf(wx->ptp_caps.name, sizeof(wx->ptp_caps.name), + "%s", netdev->name); + wx->ptp_caps.owner = THIS_MODULE; + wx->ptp_caps.n_alarm = 0; + wx->ptp_caps.n_ext_ts = 0; + wx->ptp_caps.pps = 0; + wx->ptp_caps.adjfine = wx_ptp_adjfine; + wx->ptp_caps.adjtime = wx_ptp_adjtime; + wx->ptp_caps.gettimex64 = wx_ptp_gettimex64; + wx->ptp_caps.settime64 = wx_ptp_settime64; + wx->ptp_caps.do_aux_work = wx_ptp_do_aux_work; + if (wx->mac.type == wx_mac_em) { + wx->ptp_caps.max_adj = 500000000; + wx->ptp_caps.n_per_out = 1; + wx->ptp_setup_sdp = wx_ptp_setup_sdp; + wx->ptp_caps.enable = wx_ptp_feature_enable; + } else { + wx->ptp_caps.max_adj = 250000000; + wx->ptp_caps.n_per_out = 0; + wx->ptp_setup_sdp = NULL; + } + + wx->ptp_clock = ptp_clock_register(&wx->ptp_caps, &wx->pdev->dev); + if (IS_ERR(wx->ptp_clock)) { + err = PTR_ERR(wx->ptp_clock); + wx->ptp_clock = NULL; + wx_err(wx, "ptp clock register failed\n"); + return err; + } else if (wx->ptp_clock) { + dev_info(&wx->pdev->dev, "registered PHC device on %s\n", + netdev->name); + } + + /* Set the default timestamp mode to disabled here. We do this in + * create_clock instead of initialization, because we don't want to + * override the previous settings during a suspend/resume cycle. + */ + wx->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE; + wx->tstamp_config.tx_type = HWTSTAMP_TX_OFF; + + return 0; +} + +static int wx_ptp_set_timestamp_mode(struct wx *wx, + struct kernel_hwtstamp_config *config) +{ + u32 tsync_tx_ctl = WX_TSC_1588_CTL_ENABLED; + u32 tsync_rx_ctl = WX_PSR_1588_CTL_ENABLED; + DECLARE_BITMAP(flags, WX_PF_FLAGS_NBITS); + u32 tsync_rx_mtrl = PTP_EV_PORT << 16; + bool is_l2 = false; + u32 regval; + + memcpy(flags, wx->flags, sizeof(wx->flags)); + + switch (config->tx_type) { + case HWTSTAMP_TX_OFF: + tsync_tx_ctl = 0; + break; + case HWTSTAMP_TX_ON: + break; + default: + return -ERANGE; + } + + switch (config->rx_filter) { + case HWTSTAMP_FILTER_NONE: + tsync_rx_ctl = 0; + tsync_rx_mtrl = 0; + clear_bit(WX_FLAG_RX_HWTSTAMP_ENABLED, flags); + clear_bit(WX_FLAG_RX_HWTSTAMP_IN_REGISTER, flags); + break; + case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: + tsync_rx_ctl |= WX_PSR_1588_CTL_TYPE_L4_V1; + tsync_rx_mtrl |= WX_PSR_1588_MSG_V1_SYNC; + set_bit(WX_FLAG_RX_HWTSTAMP_ENABLED, flags); + set_bit(WX_FLAG_RX_HWTSTAMP_IN_REGISTER, flags); + break; + case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: + tsync_rx_ctl |= WX_PSR_1588_CTL_TYPE_L4_V1; + tsync_rx_mtrl |= WX_PSR_1588_MSG_V1_DELAY_REQ; + set_bit(WX_FLAG_RX_HWTSTAMP_ENABLED, flags); + set_bit(WX_FLAG_RX_HWTSTAMP_IN_REGISTER, flags); + break; + case HWTSTAMP_FILTER_PTP_V2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: + tsync_rx_ctl |= WX_PSR_1588_CTL_TYPE_EVENT_V2; + is_l2 = true; + config->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; + set_bit(WX_FLAG_RX_HWTSTAMP_ENABLED, flags); + set_bit(WX_FLAG_RX_HWTSTAMP_IN_REGISTER, flags); + break; + default: + /* register PSR_1588_MSG must be set in order to do V1 packets, + * therefore it is not possible to time stamp both V1 Sync and + * Delay_Req messages unless hardware supports timestamping all + * packets => return error + */ + config->rx_filter = HWTSTAMP_FILTER_NONE; + return -ERANGE; + } + + /* define ethertype filter for timestamping L2 packets */ + if (is_l2) + wr32(wx, WX_PSR_ETYPE_SWC(WX_PSR_ETYPE_SWC_FILTER_1588), + (WX_PSR_ETYPE_SWC_FILTER_EN | /* enable filter */ + WX_PSR_ETYPE_SWC_1588 | /* enable timestamping */ + ETH_P_1588)); /* 1588 eth protocol type */ + else + wr32(wx, WX_PSR_ETYPE_SWC(WX_PSR_ETYPE_SWC_FILTER_1588), 0); + + /* enable/disable TX */ + regval = rd32ptp(wx, WX_TSC_1588_CTL); + regval &= ~WX_TSC_1588_CTL_ENABLED; + regval |= tsync_tx_ctl; + wr32ptp(wx, WX_TSC_1588_CTL, regval); + + /* enable/disable RX */ + regval = rd32(wx, WX_PSR_1588_CTL); + regval &= ~(WX_PSR_1588_CTL_ENABLED | WX_PSR_1588_CTL_TYPE_MASK); + regval |= tsync_rx_ctl; + wr32(wx, WX_PSR_1588_CTL, regval); + + /* define which PTP packets are time stamped */ + wr32(wx, WX_PSR_1588_MSG, tsync_rx_mtrl); + + WX_WRITE_FLUSH(wx); + + /* configure adapter flags only when HW is actually configured */ + memcpy(wx->flags, flags, sizeof(wx->flags)); + + /* clear TX/RX timestamp state, just to be sure */ + wx_ptp_clear_tx_timestamp(wx); + rd32(wx, WX_PSR_1588_STMPH); + + return 0; +} + +static u64 wx_ptp_read(const struct cyclecounter *hw_cc) +{ + struct wx *wx = container_of(hw_cc, struct wx, hw_cc); + + return wx_ptp_readtime(wx, NULL); +} + +static void wx_ptp_link_speed_adjust(struct wx *wx, u32 *shift, u32 *incval) +{ + if (wx->mac.type == wx_mac_em) { + *shift = WX_INCVAL_SHIFT_EM; + *incval = WX_INCVAL_EM; + return; + } + + switch (wx->speed) { + case SPEED_10: + *shift = WX_INCVAL_SHIFT_10; + *incval = WX_INCVAL_10; + break; + case SPEED_100: + *shift = WX_INCVAL_SHIFT_100; + *incval = WX_INCVAL_100; + break; + case SPEED_1000: + *shift = WX_INCVAL_SHIFT_1GB; + *incval = WX_INCVAL_1GB; + break; + case SPEED_10000: + default: + *shift = WX_INCVAL_SHIFT_10GB; + *incval = WX_INCVAL_10GB; + break; + } +} + +/** + * wx_ptp_reset_cyclecounter - create the cycle counter from hw + * @wx: pointer to the wx structure + * + * This function should be called to set the proper values for the TSC_1588_INC + * register and tell the cyclecounter structure what the tick rate of SYSTIME + * is. It does not directly modify SYSTIME registers or the timecounter + * structure. It should be called whenever a new TSC_1588_INC value is + * necessary, such as during initialization or when the link speed changes. + */ +void wx_ptp_reset_cyclecounter(struct wx *wx) +{ + u32 incval = 0, mask = 0; + struct cyclecounter cc; + unsigned long flags; + + /* For some of the boards below this mask is technically incorrect. + * The timestamp mask overflows at approximately 61bits. However the + * particular hardware does not overflow on an even bitmask value. + * Instead, it overflows due to conversion of upper 32bits billions of + * cycles. Timecounters are not really intended for this purpose so + * they do not properly function if the overflow point isn't 2^N-1. + * However, the actual SYSTIME values in question take ~138 years to + * overflow. In practice this means they won't actually overflow. A + * proper fix to this problem would require modification of the + * timecounter delta calculations. + */ + cc.mask = CLOCKSOURCE_MASK(64); + cc.mult = 1; + cc.shift = 0; + + cc.read = wx_ptp_read; + wx_ptp_link_speed_adjust(wx, &cc.shift, &incval); + + /* update the base incval used to calculate frequency adjustment */ + WRITE_ONCE(wx->base_incval, incval); + + mask = (wx->mac.type == wx_mac_em) ? 0x7FFFFFF : 0xFFFFFF; + incval &= mask; + if (wx->mac.type != wx_mac_em) + incval |= 2 << 24; + wr32ptp(wx, WX_TSC_1588_INC, incval); + + smp_mb(); /* Force the above update. */ + + /* need lock to prevent incorrect read while modifying cyclecounter */ + write_seqlock_irqsave(&wx->hw_tc_lock, flags); + memcpy(&wx->hw_cc, &cc, sizeof(wx->hw_cc)); + write_sequnlock_irqrestore(&wx->hw_tc_lock, flags); +} +EXPORT_SYMBOL(wx_ptp_reset_cyclecounter); + +void wx_ptp_reset(struct wx *wx) +{ + unsigned long flags; + + /* reset the hardware timestamping mode */ + wx_ptp_set_timestamp_mode(wx, &wx->tstamp_config); + wx_ptp_reset_cyclecounter(wx); + + wr32ptp(wx, WX_TSC_1588_SYSTIML, 0); + wr32ptp(wx, WX_TSC_1588_SYSTIMH, 0); + WX_WRITE_FLUSH(wx); + + write_seqlock_irqsave(&wx->hw_tc_lock, flags); + timecounter_init(&wx->hw_tc, &wx->hw_cc, + ktime_to_ns(ktime_get_real())); + write_sequnlock_irqrestore(&wx->hw_tc_lock, flags); + + wx->last_overflow_check = jiffies; + ptp_schedule_worker(wx->ptp_clock, HZ); + + /* Now that the shift has been calculated and the systime + * registers reset, (re-)enable the Clock out feature + */ + if (wx->ptp_setup_sdp) + wx->ptp_setup_sdp(wx); +} +EXPORT_SYMBOL(wx_ptp_reset); + +void wx_ptp_init(struct wx *wx) +{ + /* Initialize the seqlock_t first, since the user might call the clock + * functions any time after we've initialized the ptp clock device. + */ + seqlock_init(&wx->hw_tc_lock); + + /* obtain a ptp clock device, or re-use an existing device */ + if (wx_ptp_create_clock(wx)) + return; + + wx->tx_hwtstamp_pkts = 0; + wx->tx_hwtstamp_timeouts = 0; + wx->tx_hwtstamp_skipped = 0; + wx->tx_hwtstamp_errors = 0; + wx->rx_hwtstamp_cleared = 0; + /* reset the ptp related hardware bits */ + wx_ptp_reset(wx); + + /* enter the WX_STATE_PTP_RUNNING state */ + set_bit(WX_STATE_PTP_RUNNING, wx->state); +} +EXPORT_SYMBOL(wx_ptp_init); + +/** + * wx_ptp_suspend - stop ptp work items + * @wx: pointer to wx struct + * + * This function suspends ptp activity, and prevents more work from being + * generated, but does not destroy the clock device. + */ +void wx_ptp_suspend(struct wx *wx) +{ + /* leave the WX_STATE_PTP_RUNNING STATE */ + if (!test_and_clear_bit(WX_STATE_PTP_RUNNING, wx->state)) + return; + + clear_bit(WX_FLAG_PTP_PPS_ENABLED, wx->flags); + if (wx->ptp_setup_sdp) + wx->ptp_setup_sdp(wx); + + wx_ptp_clear_tx_timestamp(wx); +} +EXPORT_SYMBOL(wx_ptp_suspend); + +/** + * wx_ptp_stop - destroy the ptp_clock device + * @wx: pointer to wx struct + * + * Completely destroy the ptp_clock device, and disable all PTP related + * features. Intended to be run when the device is being closed. + */ +void wx_ptp_stop(struct wx *wx) +{ + /* first, suspend ptp activity */ + wx_ptp_suspend(wx); + + /* now destroy the ptp clock device */ + if (wx->ptp_clock) { + ptp_clock_unregister(wx->ptp_clock); + wx->ptp_clock = NULL; + dev_info(&wx->pdev->dev, "removed PHC on %s\n", wx->netdev->name); + } +} +EXPORT_SYMBOL(wx_ptp_stop); + +/** + * wx_ptp_rx_hwtstamp - utility function which checks for RX time stamp + * @wx: pointer to wx struct + * @skb: particular skb to send timestamp with + * + * if the timestamp is valid, we convert it into the timecounter ns + * value, then store that result into the shhwtstamps structure which + * is passed up the network stack + */ +void wx_ptp_rx_hwtstamp(struct wx *wx, struct sk_buff *skb) +{ + u64 regval = 0; + u32 tsyncrxctl; + + /* Read the tsyncrxctl register afterwards in order to prevent taking an + * I/O hit on every packet. + */ + tsyncrxctl = rd32(wx, WX_PSR_1588_CTL); + if (!(tsyncrxctl & WX_PSR_1588_CTL_VALID)) + return; + + regval |= (u64)rd32(wx, WX_PSR_1588_STMPL); + regval |= (u64)rd32(wx, WX_PSR_1588_STMPH) << 32; + + wx_ptp_convert_to_hwtstamp(wx, skb_hwtstamps(skb), regval); +} + +int wx_hwtstamp_get(struct net_device *dev, + struct kernel_hwtstamp_config *cfg) +{ + struct wx *wx = netdev_priv(dev); + + if (!netif_running(dev)) + return -EINVAL; + + *cfg = wx->tstamp_config; + + return 0; +} +EXPORT_SYMBOL(wx_hwtstamp_get); + +int wx_hwtstamp_set(struct net_device *dev, + struct kernel_hwtstamp_config *cfg, + struct netlink_ext_ack *extack) +{ + struct wx *wx = netdev_priv(dev); + int err; + + if (!netif_running(dev)) + return -EINVAL; + + err = wx_ptp_set_timestamp_mode(wx, cfg); + if (err) + return err; + + /* save these settings for future reference */ + memcpy(&wx->tstamp_config, cfg, sizeof(wx->tstamp_config)); + + return 0; +} +EXPORT_SYMBOL(wx_hwtstamp_set); diff --git a/drivers/net/ethernet/wangxun/libwx/wx_ptp.h b/drivers/net/ethernet/wangxun/libwx/wx_ptp.h new file mode 100644 index 000000000000..50db90a6e3ee --- /dev/null +++ b/drivers/net/ethernet/wangxun/libwx/wx_ptp.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2019 - 2025 Beijing WangXun Technology Co., Ltd. */ + +#ifndef _WX_PTP_H_ +#define _WX_PTP_H_ + +void wx_ptp_check_pps_event(struct wx *wx); +void wx_ptp_reset_cyclecounter(struct wx *wx); +void wx_ptp_reset(struct wx *wx); +void wx_ptp_init(struct wx *wx); +void wx_ptp_suspend(struct wx *wx); +void wx_ptp_stop(struct wx *wx); +void wx_ptp_rx_hwtstamp(struct wx *wx, struct sk_buff *skb); +int wx_hwtstamp_get(struct net_device *dev, + struct kernel_hwtstamp_config *cfg); +int wx_hwtstamp_set(struct net_device *dev, + struct kernel_hwtstamp_config *cfg, + struct netlink_ext_ack *extack); + +#endif /* _WX_PTP_H_ */ diff --git a/drivers/net/ethernet/wangxun/libwx/wx_type.h b/drivers/net/ethernet/wangxun/libwx/wx_type.h index b54bffda027b..db446e690dc7 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_type.h +++ b/drivers/net/ethernet/wangxun/libwx/wx_type.h @@ -4,6 +4,8 @@ #ifndef _WX_TYPE_H_ #define _WX_TYPE_H_ +#include <linux/ptp_clock_kernel.h> +#include <linux/timecounter.h> #include <linux/bitfield.h> #include <linux/netdevice.h> #include <linux/if_vlan.h> @@ -180,6 +182,23 @@ #define WX_PSR_VLAN_CTL 0x15088 #define WX_PSR_VLAN_CTL_CFIEN BIT(29) /* bit 29 */ #define WX_PSR_VLAN_CTL_VFE BIT(30) /* bit 30 */ +/* EType Queue Filter */ +#define WX_PSR_ETYPE_SWC(_i) (0x15128 + ((_i) * 4)) +#define WX_PSR_ETYPE_SWC_FILTER_1588 3 +#define WX_PSR_ETYPE_SWC_FILTER_EN BIT(31) +#define WX_PSR_ETYPE_SWC_1588 BIT(30) +/* 1588 */ +#define WX_PSR_1588_MSG 0x15120 +#define WX_PSR_1588_MSG_V1_SYNC FIELD_PREP(GENMASK(7, 0), 0) +#define WX_PSR_1588_MSG_V1_DELAY_REQ FIELD_PREP(GENMASK(7, 0), 1) +#define WX_PSR_1588_STMPL 0x151E8 +#define WX_PSR_1588_STMPH 0x151A4 +#define WX_PSR_1588_CTL 0x15188 +#define WX_PSR_1588_CTL_ENABLED BIT(4) +#define WX_PSR_1588_CTL_TYPE_MASK GENMASK(3, 1) +#define WX_PSR_1588_CTL_TYPE_L4_V1 FIELD_PREP(GENMASK(3, 1), 1) +#define WX_PSR_1588_CTL_TYPE_EVENT_V2 FIELD_PREP(GENMASK(3, 1), 5) +#define WX_PSR_1588_CTL_VALID BIT(0) /* mcasst/ucast overflow tbl */ #define WX_PSR_MC_TBL(_i) (0x15200 + ((_i) * 4)) #define WX_PSR_UC_TBL(_i) (0x15400 + ((_i) * 4)) @@ -253,6 +272,32 @@ #define WX_TSC_ST_SECTX_RDY BIT(0) #define WX_TSC_BUF_AE 0x1D00C #define WX_TSC_BUF_AE_THR GENMASK(9, 0) +/* 1588 */ +#define WX_TSC_1588_CTL 0x11F00 +#define WX_TSC_1588_CTL_ENABLED BIT(4) +#define WX_TSC_1588_CTL_VALID BIT(0) +#define WX_TSC_1588_STMPL 0x11F04 +#define WX_TSC_1588_STMPH 0x11F08 +#define WX_TSC_1588_SYSTIML 0x11F0C +#define WX_TSC_1588_SYSTIMH 0x11F10 +#define WX_TSC_1588_INC 0x11F14 +#define WX_TSC_1588_INT_ST 0x11F20 +#define WX_TSC_1588_INT_ST_TT1 BIT(5) +#define WX_TSC_1588_INT_EN 0x11F24 +#define WX_TSC_1588_INT_EN_TT1 BIT(5) +#define WX_TSC_1588_AUX_CTL 0x11F28 +#define WX_TSC_1588_AUX_CTL_EN_TS0 BIT(8) +#define WX_TSC_1588_AUX_CTL_EN_TT1 BIT(2) +#define WX_TSC_1588_AUX_CTL_PLSG BIT(1) +#define WX_TSC_1588_AUX_CTL_EN_TT0 BIT(0) +#define WX_TSC_1588_TRGT_L(i) (0x11F2C + ((i) * 8)) /* [0,1] */ +#define WX_TSC_1588_TRGT_H(i) (0x11F30 + ((i) * 8)) /* [0,1] */ +#define WX_TSC_1588_SDP(i) (0x11F5C + ((i) * 4)) /* [0,3] */ +#define WX_TSC_1588_SDP_OUT_LEVEL_H FIELD_PREP(BIT(4), 0) +#define WX_TSC_1588_SDP_OUT_LEVEL_L FIELD_PREP(BIT(4), 1) +#define WX_TSC_1588_SDP_FUN_SEL_MASK GENMASK(2, 0) +#define WX_TSC_1588_SDP_FUN_SEL_TT0 FIELD_PREP(WX_TSC_1588_SDP_FUN_SEL_MASK, 1) +#define WX_TSC_1588_SDP_FUN_SEL_TS0 FIELD_PREP(WX_TSC_1588_SDP_FUN_SEL_MASK, 5) /************************************** MNG ********************************/ #define WX_MNG_SWFW_SYNC 0x1E008 @@ -382,6 +427,8 @@ enum WX_MSCA_CMD_value { #define FW_CEM_CMD_RESERVED 0X0 #define FW_CEM_MAX_RETRIES 3 #define FW_CEM_RESP_STATUS_SUCCESS 0x1 +#define FW_PPS_SET_CMD 0xF6 +#define FW_PPS_SET_LEN 0x14 #define WX_SW_REGION_PTR 0x1C @@ -460,6 +507,7 @@ enum WX_MSCA_CMD_value { #define WX_RXD_STAT_L4CS BIT(7) /* L4 xsum calculated */ #define WX_RXD_STAT_IPCS BIT(8) /* IP xsum calculated */ #define WX_RXD_STAT_OUTERIPCS BIT(10) /* Cloud IP xsum calculated*/ +#define WX_RXD_STAT_TS BIT(14) /* IEEE1588 Time Stamp */ #define WX_RXD_ERR_OUTERIPER BIT(26) /* CRC IP Header error */ #define WX_RXD_ERR_RXE BIT(29) /* Any MAC Error */ @@ -701,6 +749,15 @@ struct wx_hic_reset { u16 reset_type; }; +struct wx_hic_set_pps { + struct wx_hic_hdr hdr; + u8 lan_id; + u8 enable; + u16 pad2; + u64 nsec; + u64 cycles; +}; + /* Bus parameters */ struct wx_bus_info { u8 func; @@ -863,6 +920,7 @@ struct wx_tx_context_desc { */ struct wx_tx_buffer { union wx_tx_desc *next_to_watch; + unsigned long time_stamp; struct sk_buff *skb; unsigned int bytecount; unsigned short gso_segs; @@ -924,6 +982,7 @@ struct wx_ring { unsigned int size; /* length in bytes */ u16 count; /* amount of descriptors */ + unsigned long last_rx_timestamp; u8 queue_index; /* needed for multiqueue queue management */ u8 reg_idx; /* holds the special value that gets @@ -1026,6 +1085,8 @@ struct wx_hw_stats { enum wx_state { WX_STATE_RESETTING, + WX_STATE_PTP_RUNNING, + WX_STATE_PTP_TX_IN_PROGRESS, WX_STATE_NBITS, /* must be last */ }; @@ -1033,6 +1094,9 @@ enum wx_pf_flags { WX_FLAG_FDIR_CAPABLE, WX_FLAG_FDIR_HASH, WX_FLAG_FDIR_PERFECT, + WX_FLAG_RX_HWTSTAMP_ENABLED, + WX_FLAG_RX_HWTSTAMP_IN_REGISTER, + WX_FLAG_PTP_PPS_ENABLED, WX_PF_FLAGS_NBITS /* must be last */ }; @@ -1133,6 +1197,29 @@ struct wx { void (*atr)(struct wx_ring *ring, struct wx_tx_buffer *first, u8 ptype); void (*configure_fdir)(struct wx *wx); void (*do_reset)(struct net_device *netdev); + int (*ptp_setup_sdp)(struct wx *wx); + + bool pps_enabled; + u64 pps_width; + u64 pps_edge_start; + u64 pps_edge_end; + u64 sec_to_cc; + u32 base_incval; + u32 tx_hwtstamp_pkts; + u32 tx_hwtstamp_timeouts; + u32 tx_hwtstamp_skipped; + u32 tx_hwtstamp_errors; + u32 rx_hwtstamp_cleared; + unsigned long last_overflow_check; + unsigned long last_rx_ptp_check; + unsigned long ptp_tx_start; + seqlock_t hw_tc_lock; /* seqlock for ptp */ + struct cyclecounter hw_cc; + struct timecounter hw_tc; + struct ptp_clock *ptp_clock; + struct ptp_clock_info ptp_caps; + struct kernel_hwtstamp_config tstamp_config; + struct sk_buff *ptp_tx_skb; }; #define WX_INTR_ALL (~0ULL) @@ -1177,6 +1264,24 @@ rd64(struct wx *wx, u32 reg) return (lsb | msb << 32); } +static inline u32 +rd32ptp(struct wx *wx, u32 reg) +{ + if (wx->mac.type == wx_mac_em) + return rd32(wx, reg); + + return rd32(wx, reg + 0xB500); +} + +static inline void +wr32ptp(struct wx *wx, u32 reg, u32 value) +{ + if (wx->mac.type == wx_mac_em) + return wr32(wx, reg, value); + + return wr32(wx, reg + 0xB500, value); +} + /* On some domestic CPU platforms, sometimes IO is not synchronized with * flushing memory, here use readl() to flush PCI read and write. */ diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_ethtool.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_ethtool.c index e868f7ef4920..7e2d9ec38a30 100644 --- a/drivers/net/ethernet/wangxun/ngbe/ngbe_ethtool.c +++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_ethtool.c @@ -138,6 +138,8 @@ static const struct ethtool_ops ngbe_ethtool_ops = { .set_channels = ngbe_set_channels, .get_msglevel = wx_get_msglevel, .set_msglevel = wx_set_msglevel, + .get_ts_info = wx_get_ts_info, + .get_ts_stats = wx_get_ptp_stats, }; void ngbe_set_ethtool_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c index 53aeae2f884b..a6159214ec0a 100644 --- a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c +++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c @@ -14,6 +14,7 @@ #include "../libwx/wx_type.h" #include "../libwx/wx_hw.h" #include "../libwx/wx_lib.h" +#include "../libwx/wx_ptp.h" #include "ngbe_type.h" #include "ngbe_mdio.h" #include "ngbe_hw.h" @@ -167,7 +168,7 @@ static irqreturn_t ngbe_intr(int __always_unused irq, void *data) struct wx_q_vector *q_vector; struct wx *wx = data; struct pci_dev *pdev; - u32 eicr; + u32 eicr, eicr_misc; q_vector = wx->q_vector[0]; pdev = wx->pdev; @@ -185,6 +186,10 @@ static irqreturn_t ngbe_intr(int __always_unused irq, void *data) if (!(pdev->msi_enabled)) wr32(wx, WX_PX_INTA, 1); + eicr_misc = wx_misc_isb(wx, WX_ISB_MISC); + if (unlikely(eicr_misc & NGBE_PX_MISC_IC_TIMESYNC)) + wx_ptp_check_pps_event(wx); + wx->isb_mem[WX_ISB_MISC] = 0; /* would disable interrupts here but it is auto disabled */ napi_schedule_irqoff(&q_vector->napi); @@ -198,6 +203,12 @@ static irqreturn_t ngbe_intr(int __always_unused irq, void *data) static irqreturn_t ngbe_msix_other(int __always_unused irq, void *data) { struct wx *wx = data; + u32 eicr; + + eicr = wx_misc_isb(wx, WX_ISB_MISC); + + if (unlikely(eicr & NGBE_PX_MISC_IC_TIMESYNC)) + wx_ptp_check_pps_event(wx); /* re-enable the original interrupt state, no lsc, no queues */ if (netif_running(wx->netdev)) @@ -317,6 +328,8 @@ void ngbe_down(struct wx *wx) { phylink_stop(wx->phylink); ngbe_disable_device(wx); + if (test_bit(WX_STATE_PTP_RUNNING, wx->state)) + wx_ptp_reset(wx); wx_clean_all_tx_rings(wx); wx_clean_all_rx_rings(wx); } @@ -379,6 +392,8 @@ static int ngbe_open(struct net_device *netdev) if (err) goto err_dis_phy; + wx_ptp_init(wx); + ngbe_up(wx); return 0; @@ -407,6 +422,7 @@ static int ngbe_close(struct net_device *netdev) { struct wx *wx = netdev_priv(netdev); + wx_ptp_stop(wx); ngbe_down(wx); wx_free_irq(wx); wx_free_isb_resources(wx); @@ -507,6 +523,8 @@ static const struct net_device_ops ngbe_netdev_ops = { .ndo_get_stats64 = wx_get_stats64, .ndo_vlan_rx_add_vid = wx_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = wx_vlan_rx_kill_vid, + .ndo_hwtstamp_set = wx_hwtstamp_set, + .ndo_hwtstamp_get = wx_hwtstamp_get, }; /** diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c index a5e9b779c44d..ea1d7e9a91f3 100644 --- a/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c +++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c @@ -7,6 +7,7 @@ #include <linux/phy.h> #include "../libwx/wx_type.h" +#include "../libwx/wx_ptp.h" #include "../libwx/wx_hw.h" #include "ngbe_type.h" #include "ngbe_mdio.h" @@ -64,6 +65,11 @@ static void ngbe_mac_config(struct phylink_config *config, unsigned int mode, static void ngbe_mac_link_down(struct phylink_config *config, unsigned int mode, phy_interface_t interface) { + struct wx *wx = phylink_to_wx(config); + + wx->speed = SPEED_UNKNOWN; + if (test_bit(WX_STATE_PTP_RUNNING, wx->state)) + wx_ptp_reset_cyclecounter(wx); } static void ngbe_mac_link_up(struct phylink_config *config, @@ -103,6 +109,11 @@ static void ngbe_mac_link_up(struct phylink_config *config, wr32(wx, WX_MAC_PKT_FLT, WX_MAC_PKT_FLT_PR); reg = rd32(wx, WX_MAC_WDG_TIMEOUT); wr32(wx, WX_MAC_WDG_TIMEOUT, reg); + + wx->speed = speed; + wx->last_rx_ptp_check = jiffies; + if (test_bit(WX_STATE_PTP_RUNNING, wx->state)) + wx_ptp_reset_cyclecounter(wx); } static const struct phylink_mac_ops ngbe_mac_ops = { diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h b/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h index f48ed7fc1805..992adbb98c7d 100644 --- a/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h +++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h @@ -70,15 +70,20 @@ /* Extended Interrupt Enable Set */ #define NGBE_PX_MISC_IEN_DEV_RST BIT(10) +#define NGBE_PX_MISC_IEN_TIMESYNC BIT(11) #define NGBE_PX_MISC_IEN_ETH_LK BIT(18) #define NGBE_PX_MISC_IEN_INT_ERR BIT(20) #define NGBE_PX_MISC_IEN_GPIO BIT(26) #define NGBE_PX_MISC_IEN_MASK ( \ NGBE_PX_MISC_IEN_DEV_RST | \ + NGBE_PX_MISC_IEN_TIMESYNC | \ NGBE_PX_MISC_IEN_ETH_LK | \ NGBE_PX_MISC_IEN_INT_ERR | \ NGBE_PX_MISC_IEN_GPIO) +/* Extended Interrupt Cause Read */ +#define NGBE_PX_MISC_IC_TIMESYNC BIT(11) /* time sync */ + #define NGBE_INTR_ALL 0x1FF #define NGBE_INTR_MISC BIT(0) diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.c index d98314b26c19..78999d484f18 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.c @@ -529,6 +529,8 @@ static const struct ethtool_ops txgbe_ethtool_ops = { .set_rxnfc = txgbe_set_rxnfc, .get_msglevel = wx_get_msglevel, .set_msglevel = wx_set_msglevel, + .get_ts_info = wx_get_ts_info, + .get_ts_stats = wx_get_ptp_stats, }; void txgbe_set_ethtool_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c index f77450268036..734450af9a43 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c @@ -13,6 +13,7 @@ #include "../libwx/wx_type.h" #include "../libwx/wx_lib.h" +#include "../libwx/wx_ptp.h" #include "../libwx/wx_hw.h" #include "txgbe_type.h" #include "txgbe_hw.h" @@ -116,6 +117,9 @@ static void txgbe_reset(struct wx *wx) memcpy(old_addr, &wx->mac_table[0].addr, netdev->addr_len); wx_flush_sw_mac_table(wx); wx_mac_set_default_filter(wx, old_addr); + + if (test_bit(WX_STATE_PTP_RUNNING, wx->state)) + wx_ptp_reset(wx); } static void txgbe_disable_device(struct wx *wx) @@ -176,6 +180,7 @@ void txgbe_down(struct wx *wx) void txgbe_up(struct wx *wx) { wx_configure(wx); + wx_ptp_init(wx); txgbe_up_complete(wx); } @@ -321,6 +326,8 @@ static int txgbe_open(struct net_device *netdev) if (err) goto err_free_irq; + wx_ptp_init(wx); + txgbe_up_complete(wx); return 0; @@ -344,6 +351,7 @@ err_reset: */ static void txgbe_close_suspend(struct wx *wx) { + wx_ptp_suspend(wx); txgbe_disable_device(wx); wx_free_resources(wx); } @@ -363,6 +371,7 @@ static int txgbe_close(struct net_device *netdev) { struct wx *wx = netdev_priv(netdev); + wx_ptp_stop(wx); txgbe_down(wx); wx_free_irq(wx); wx_free_resources(wx); @@ -479,6 +488,8 @@ static const struct net_device_ops txgbe_netdev_ops = { .ndo_get_stats64 = wx_get_stats64, .ndo_vlan_rx_add_vid = wx_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = wx_vlan_rx_kill_vid, + .ndo_hwtstamp_set = wx_hwtstamp_set, + .ndo_hwtstamp_get = wx_hwtstamp_get, }; /** diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c index 1ae68f94dd49..7e17d727c2ba 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c @@ -15,6 +15,7 @@ #include "../libwx/wx_type.h" #include "../libwx/wx_lib.h" +#include "../libwx/wx_ptp.h" #include "../libwx/wx_hw.h" #include "txgbe_type.h" #include "txgbe_phy.h" @@ -179,6 +180,10 @@ static void txgbe_mac_link_down(struct phylink_config *config, struct wx *wx = phylink_to_wx(config); wr32m(wx, WX_MAC_TX_CFG, WX_MAC_TX_CFG_TE, 0); + + wx->speed = SPEED_UNKNOWN; + if (test_bit(WX_STATE_PTP_RUNNING, wx->state)) + wx_ptp_reset_cyclecounter(wx); } static void txgbe_mac_link_up(struct phylink_config *config, @@ -215,6 +220,11 @@ static void txgbe_mac_link_up(struct phylink_config *config, wr32(wx, WX_MAC_PKT_FLT, WX_MAC_PKT_FLT_PR); wdg = rd32(wx, WX_MAC_WDG_TIMEOUT); wr32(wx, WX_MAC_WDG_TIMEOUT, wdg); + + wx->speed = speed; + wx->last_rx_ptp_check = jiffies; + if (test_bit(WX_STATE_PTP_RUNNING, wx->state)) + wx_ptp_reset_cyclecounter(wx); } static int txgbe_mac_prepare(struct phylink_config *config, unsigned int mode, diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 0673b2694e4c..054abf283ab3 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -1002,6 +1002,7 @@ static int axienet_tx_poll(struct napi_struct *napi, int budget) &size, budget); if (packets) { + netdev_completed_queue(ndev, packets, size); u64_stats_update_begin(&lp->tx_stat_sync); u64_stats_add(&lp->tx_packets, packets); u64_stats_add(&lp->tx_bytes, size); @@ -1125,6 +1126,7 @@ axienet_start_xmit(struct sk_buff *skb, struct net_device *ndev) if (++new_tail_ptr >= lp->tx_bd_num) new_tail_ptr = 0; WRITE_ONCE(lp->tx_bd_tail, new_tail_ptr); + netdev_sent_queue(ndev, skb->len); /* Start the transfer */ axienet_dma_out_addr(lp, XAXIDMA_TX_TDESC_OFFSET, tail_p); @@ -1751,6 +1753,7 @@ static int axienet_stop(struct net_device *ndev) dma_release_channel(lp->tx_chan); } + netdev_reset_queue(ndev); axienet_iow(lp, XAE_IE_OFFSET, 0); if (lp->eth_irq > 0) @@ -2676,6 +2679,7 @@ static void axienet_dma_err_handler(struct work_struct *work) ~(XAE_OPTION_TXEN | XAE_OPTION_RXEN)); axienet_dma_stop(lp); + netdev_reset_queue(ndev); for (i = 0; i < lp->tx_bd_num; i++) { cur_p = &lp->tx_bd_v[i]; @@ -3073,12 +3077,12 @@ static int axienet_probe(struct platform_device *pdev) } of_node_put(np); lp->pcs.ops = &axienet_pcs_ops; - lp->pcs.neg_mode = true; lp->pcs.poll = true; } lp->phylink_config.dev = &ndev->dev; lp->phylink_config.type = PHYLINK_NETDEV; + lp->phylink_config.mac_managed_pm = true; lp->phylink_config.mac_capabilities = MAC_SYM_PAUSE | MAC_ASYM_PAUSE | MAC_10FD | MAC_100FD | MAC_1000FD; diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 642155cb8315..fc62b25e0362 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -1614,10 +1614,13 @@ static void geneve_link_config(struct net_device *dev, geneve_change_mtu(dev, ldev_mtu - info->options_len); } -static int geneve_newlink(struct net *net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +static int geneve_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { + struct net *link_net = rtnl_newlink_link_net(params); + struct nlattr **data = params->data; + struct nlattr **tb = params->tb; struct geneve_config cfg = { .df = GENEVE_DF_UNSET, .use_udp6_rx_checksums = false, @@ -1631,7 +1634,7 @@ static int geneve_newlink(struct net *net, struct net_device *dev, if (err) return err; - err = geneve_configure(net, dev, extack, &cfg); + err = geneve_configure(link_net, dev, extack, &cfg); if (err) return err; @@ -1902,21 +1905,9 @@ static void geneve_destroy_tunnels(struct net *net, struct list_head *head) { struct geneve_net *gn = net_generic(net, geneve_net_id); struct geneve_dev *geneve, *next; - struct net_device *dev, *aux; - /* gather any geneve devices that were moved into this ns */ - for_each_netdev_safe(net, dev, aux) - if (dev->rtnl_link_ops == &geneve_link_ops) - unregister_netdevice_queue(dev, head); - - /* now gather any other geneve devices that were created in this ns */ - list_for_each_entry_safe(geneve, next, &gn->geneve_list, next) { - /* If geneve->dev is in the same netns, it was already added - * to the list by the previous loop. - */ - if (!net_eq(dev_net(geneve->dev), net)) - unregister_netdevice_queue(geneve->dev, head); - } + list_for_each_entry_safe(geneve, next, &gn->geneve_list, next) + geneve_dellink(geneve->dev, head); } static void __net_exit geneve_exit_batch_rtnl(struct list_head *net_list, diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index d64740bf44ed..ef793607890d 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -1462,10 +1462,12 @@ static int gtp_create_sockets(struct gtp_dev *gtp, const struct nlattr *nla, #define GTP_TH_MAXLEN (sizeof(struct udphdr) + sizeof(struct gtp0_header)) #define GTP_IPV6_MAXLEN (sizeof(struct ipv6hdr) + GTP_TH_MAXLEN) -static int gtp_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +static int gtp_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { + struct net *link_net = rtnl_newlink_link_net(params); + struct nlattr **data = params->data; unsigned int role = GTP_ROLE_GGSN; struct gtp_dev *gtp; struct gtp_net *gn; @@ -1496,7 +1498,7 @@ static int gtp_newlink(struct net *src_net, struct net_device *dev, gtp->restart_count = nla_get_u8_default(data[IFLA_GTP_RESTART_COUNT], 0); - gtp->net = src_net; + gtp->net = link_net; err = gtp_hashtable_new(gtp, hashsize); if (err < 0) @@ -1526,7 +1528,7 @@ static int gtp_newlink(struct net *src_net, struct net_device *dev, goto out_encap; } - gn = net_generic(src_net, gtp_net_id); + gn = net_generic(link_net, gtp_net_id); list_add(>p->list, &gn->gtp_dev_list); dev->priv_destructor = gtp_destructor; @@ -2481,11 +2483,6 @@ 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, *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_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 234db693cefa..70f7cb383228 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -1166,6 +1166,8 @@ struct netvsc_device { u32 max_chn; u32 num_chn; + u32 netvsc_gso_max_size; + atomic_t open_chn; struct work_struct subchan_work; wait_queue_head_t subchan_open; diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index d6c4abfc3a28..9c6501bf27bd 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -2461,6 +2461,21 @@ static int netvsc_vf_changed(struct net_device *vf_netdev, unsigned long event) } else { netdev_info(ndev, "Data path switched %s VF: %s\n", vf_is_up ? "to" : "from", vf_netdev->name); + + /* In Azure, when accelerated networking in enabled, other NICs + * like MANA, MLX, are configured as a bonded nic with + * Netvsc(failover) NIC. For bonded NICs, the min of the max + * pkt aggregate size of the members is propagated in the stack. + * In order to allow these NICs (MANA/MLX) to use up to + * GSO_MAX_SIZE gso packet size, we need to allow Netvsc NIC to + * also support this in the guest. + * This value is only increased for netvsc NIC when datapath is + * switched over to the VF + */ + if (vf_is_up) + netif_set_tso_max_size(ndev, vf_netdev->tso_max_size); + else + netif_set_tso_max_size(ndev, netvsc_dev->netvsc_gso_max_size); } return NOTIFY_OK; diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index c0ceeef4fcd8..82747dfacd70 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -1356,9 +1356,10 @@ static int rndis_netdev_set_hwcaps(struct rndis_device *rndis_device, struct net_device_context *net_device_ctx = netdev_priv(net); struct ndis_offload hwcaps; struct ndis_offload_params offloads; - unsigned int gso_max_size = GSO_LEGACY_MAX_SIZE; int ret; + nvdev->netvsc_gso_max_size = GSO_LEGACY_MAX_SIZE; + /* Find HW offload capabilities */ ret = rndis_query_hwcaps(rndis_device, nvdev, &hwcaps); if (ret != 0) @@ -1390,8 +1391,8 @@ static int rndis_netdev_set_hwcaps(struct rndis_device *rndis_device, offloads.lso_v2_ipv4 = NDIS_OFFLOAD_PARAMETERS_LSOV2_ENABLED; net->hw_features |= NETIF_F_TSO; - if (hwcaps.lsov2.ip4_maxsz < gso_max_size) - gso_max_size = hwcaps.lsov2.ip4_maxsz; + if (hwcaps.lsov2.ip4_maxsz < nvdev->netvsc_gso_max_size) + nvdev->netvsc_gso_max_size = hwcaps.lsov2.ip4_maxsz; } if (hwcaps.csum.ip4_txcsum & NDIS_TXCSUM_CAP_UDP4) { @@ -1411,8 +1412,8 @@ static int rndis_netdev_set_hwcaps(struct rndis_device *rndis_device, offloads.lso_v2_ipv6 = NDIS_OFFLOAD_PARAMETERS_LSOV2_ENABLED; net->hw_features |= NETIF_F_TSO6; - if (hwcaps.lsov2.ip6_maxsz < gso_max_size) - gso_max_size = hwcaps.lsov2.ip6_maxsz; + if (hwcaps.lsov2.ip6_maxsz < nvdev->netvsc_gso_max_size) + nvdev->netvsc_gso_max_size = hwcaps.lsov2.ip6_maxsz; } if (hwcaps.csum.ip6_txcsum & NDIS_TXCSUM_CAP_UDP6) { @@ -1438,7 +1439,7 @@ static int rndis_netdev_set_hwcaps(struct rndis_device *rndis_device, */ net->features &= ~NETVSC_SUPPORTED_HW_FEATURES | net->hw_features; - netif_set_tso_max_size(net, gso_max_size); + netif_set_tso_max_size(net, nvdev->netvsc_gso_max_size); ret = rndis_filter_set_offload_params(net, nvdev, &offloads); diff --git a/drivers/net/ipvlan/ipvlan.h b/drivers/net/ipvlan/ipvlan.h index 025e0c19ec25..50de3ee204db 100644 --- a/drivers/net/ipvlan/ipvlan.h +++ b/drivers/net/ipvlan/ipvlan.h @@ -166,8 +166,7 @@ struct ipvl_addr *ipvlan_addr_lookup(struct ipvl_port *port, void *lyr3h, void *ipvlan_get_L3_hdr(struct ipvl_port *port, struct sk_buff *skb, int *type); void ipvlan_count_rx(const struct ipvl_dev *ipvlan, unsigned int len, bool success, bool mcast); -int ipvlan_link_new(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +int ipvlan_link_new(struct net_device *dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack); void ipvlan_link_delete(struct net_device *dev, struct list_head *head); void ipvlan_link_setup(struct net_device *dev); diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index da3a97a65507..b56144ca2fde 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -532,11 +532,13 @@ err: return ret; } -int ipvlan_link_new(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +int ipvlan_link_new(struct net_device *dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { + struct net *link_net = rtnl_newlink_link_net(params); struct ipvl_dev *ipvlan = netdev_priv(dev); + struct nlattr **data = params->data; + struct nlattr **tb = params->tb; struct ipvl_port *port; struct net_device *phy_dev; int err; @@ -545,7 +547,7 @@ int ipvlan_link_new(struct net *src_net, struct net_device *dev, if (!tb[IFLA_LINK]) return -EINVAL; - phy_dev = __dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK])); + phy_dev = __dev_get_by_index(link_net, nla_get_u32(tb[IFLA_LINK])); if (!phy_dev) return -ENODEV; diff --git a/drivers/net/ipvlan/ipvtap.c b/drivers/net/ipvlan/ipvtap.c index 1afc4c47be73..edd13916831a 100644 --- a/drivers/net/ipvlan/ipvtap.c +++ b/drivers/net/ipvlan/ipvtap.c @@ -73,8 +73,8 @@ static void ipvtap_update_features(struct tap_dev *tap, netdev_update_features(vlan->dev); } -static int ipvtap_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +static int ipvtap_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct ipvtap_dev *vlantap = netdev_priv(dev); @@ -97,7 +97,7 @@ static int ipvtap_newlink(struct net *src_net, struct net_device *dev, /* Don't put anything that may fail after macvlan_common_newlink * because we can't undo what it does. */ - err = ipvlan_link_new(src_net, dev, tb, data, extack); + err = ipvlan_link_new(dev, params, extack); if (err) { netdev_rx_handler_unregister(dev); return err; diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 1bc1e5993f56..4de5d63fd577 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -4141,11 +4141,14 @@ static int macsec_add_dev(struct net_device *dev, sci_t sci, u8 icv_len) static struct lock_class_key macsec_netdev_addr_lock_key; -static int macsec_newlink(struct net *net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +static int macsec_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { + struct net *link_net = rtnl_newlink_link_net(params); struct macsec_dev *macsec = macsec_priv(dev); + struct nlattr **data = params->data; + struct nlattr **tb = params->tb; rx_handler_func_t *rx_handler; u8 icv_len = MACSEC_DEFAULT_ICV_LEN; struct net_device *real_dev; @@ -4154,7 +4157,7 @@ static int macsec_newlink(struct net *net, struct net_device *dev, if (!tb[IFLA_LINK]) return -EINVAL; - real_dev = __dev_get_by_index(net, nla_get_u32(tb[IFLA_LINK])); + real_dev = __dev_get_by_index(link_net, nla_get_u32(tb[IFLA_LINK])); if (!real_dev) return -ENODEV; if (real_dev->type != ARPHRD_ETHER) diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index fed4fe2a4748..4e9d54be887c 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -1440,21 +1440,24 @@ static int macvlan_changelink_sources(struct macvlan_dev *vlan, u32 mode, return 0; } -int macvlan_common_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +int macvlan_common_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { + struct net *link_net = rtnl_newlink_link_net(params); struct macvlan_dev *vlan = netdev_priv(dev); - struct macvlan_port *port; + struct nlattr **data = params->data; + struct nlattr **tb = params->tb; struct net_device *lowerdev; - int err; - int macmode; + struct macvlan_port *port; bool create = false; + int macmode; + int err; if (!tb[IFLA_LINK]) return -EINVAL; - lowerdev = __dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK])); + lowerdev = __dev_get_by_index(link_net, nla_get_u32(tb[IFLA_LINK])); if (lowerdev == NULL) return -ENODEV; @@ -1565,11 +1568,11 @@ destroy_macvlan_port: } EXPORT_SYMBOL_GPL(macvlan_common_newlink); -static int macvlan_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +static int macvlan_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { - return macvlan_common_newlink(src_net, dev, tb, data, extack); + return macvlan_common_newlink(dev, params, extack); } void macvlan_dellink(struct net_device *dev, struct list_head *head) diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index 29a5929d48e5..b391a0f740a3 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -77,8 +77,8 @@ static void macvtap_update_features(struct tap_dev *tap, netdev_update_features(vlan->dev); } -static int macvtap_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +static int macvtap_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct macvtap_dev *vlantap = netdev_priv(dev); @@ -105,7 +105,7 @@ static int macvtap_newlink(struct net *src_net, struct net_device *dev, /* Don't put anything that may fail after macvlan_common_newlink * because we can't undo what it does. */ - err = macvlan_common_newlink(src_net, dev, tb, data, extack); + err = macvlan_common_newlink(dev, params, extack); if (err) { netdev_rx_handler_unregister(dev); return err; diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c index 9b394ddc5206..a41dc79e9c2e 100644 --- a/drivers/net/netdevsim/netdev.c +++ b/drivers/net/netdevsim/netdev.c @@ -87,7 +87,8 @@ static netdev_tx_t nsim_start_xmit(struct sk_buff *skb, struct net_device *dev) if (unlikely(nsim_forward_skb(peer_dev, skb, rq) == NET_RX_DROP)) goto out_drop_cnt; - napi_schedule(&rq->napi); + if (!hrtimer_active(&rq->napi_timer)) + hrtimer_start(&rq->napi_timer, us_to_ktime(5), HRTIMER_MODE_REL); rcu_read_unlock(); u64_stats_update_begin(&ns->syncp); @@ -426,6 +427,22 @@ err_pp_destroy: return err; } +static enum hrtimer_restart nsim_napi_schedule(struct hrtimer *timer) +{ + struct nsim_rq *rq; + + rq = container_of(timer, struct nsim_rq, napi_timer); + napi_schedule(&rq->napi); + + return HRTIMER_NORESTART; +} + +static void nsim_rq_timer_init(struct nsim_rq *rq) +{ + hrtimer_init(&rq->napi_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + rq->napi_timer.function = nsim_napi_schedule; +} + static void nsim_enable_napi(struct netdevsim *ns) { struct net_device *dev = ns->netdev; @@ -615,11 +632,13 @@ static struct nsim_rq *nsim_queue_alloc(void) return NULL; skb_queue_head_init(&rq->skb_queue); + nsim_rq_timer_init(rq); return rq; } static void nsim_queue_free(struct nsim_rq *rq) { + hrtimer_cancel(&rq->napi_timer); skb_queue_purge_reason(&rq->skb_queue, SKB_DROP_REASON_QUEUE_PURGE); kfree(rq); } diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h index 96d54c08043d..e757f85ed861 100644 --- a/drivers/net/netdevsim/netdevsim.h +++ b/drivers/net/netdevsim/netdevsim.h @@ -97,6 +97,7 @@ struct nsim_rq { struct napi_struct napi; struct sk_buff_head skb_queue; struct page_pool *page_pool; + struct hrtimer napi_timer; }; struct netdevsim { diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c index 1e1b00756be7..751347392570 100644 --- a/drivers/net/netkit.c +++ b/drivers/net/netkit.c @@ -327,17 +327,20 @@ static int netkit_validate(struct nlattr *tb[], struct nlattr *data[], static struct rtnl_link_ops netkit_link_ops; -static int netkit_new_link(struct net *peer_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +static int netkit_new_link(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { - struct nlattr *peer_tb[IFLA_MAX + 1], **tbp = tb, *attr; - enum netkit_action policy_prim = NETKIT_PASS; - enum netkit_action policy_peer = NETKIT_PASS; + struct net *peer_net = rtnl_newlink_peer_net(params); enum netkit_scrub scrub_prim = NETKIT_SCRUB_DEFAULT; enum netkit_scrub scrub_peer = NETKIT_SCRUB_DEFAULT; + struct nlattr *peer_tb[IFLA_MAX + 1], **tbp, *attr; + enum netkit_action policy_prim = NETKIT_PASS; + enum netkit_action policy_peer = NETKIT_PASS; + struct nlattr **data = params->data; enum netkit_mode mode = NETKIT_L3; unsigned char ifname_assign_type; + struct nlattr **tb = params->tb; u16 headroom = 0, tailroom = 0; struct ifinfomsg *ifmp = NULL; struct net_device *peer; @@ -345,6 +348,7 @@ static int netkit_new_link(struct net *peer_net, struct net_device *dev, struct netkit *nk; int err; + tbp = tb; if (data) { if (data[IFLA_NETKIT_MODE]) mode = nla_get_u32(data[IFLA_NETKIT_MODE]); diff --git a/drivers/net/pcs/pcs-lynx.c b/drivers/net/pcs/pcs-lynx.c index e46f588cae7d..23b40e9eacbb 100644 --- a/drivers/net/pcs/pcs-lynx.c +++ b/drivers/net/pcs/pcs-lynx.c @@ -355,7 +355,6 @@ static struct phylink_pcs *lynx_pcs_create(struct mdio_device *mdio) mdio_device_get(mdio); lynx->mdio = mdio; lynx->pcs.ops = &lynx_pcs_phylink_ops; - lynx->pcs.neg_mode = true; lynx->pcs.poll = true; for (i = 0; i < ARRAY_SIZE(lynx_interfaces); i++) diff --git a/drivers/net/pcs/pcs-mtk-lynxi.c b/drivers/net/pcs/pcs-mtk-lynxi.c index 7d6261dee534..149ddf51d785 100644 --- a/drivers/net/pcs/pcs-mtk-lynxi.c +++ b/drivers/net/pcs/pcs-mtk-lynxi.c @@ -305,7 +305,6 @@ struct phylink_pcs *mtk_pcs_lynxi_create(struct device *dev, mpcs->regmap = regmap; mpcs->flags = flags; mpcs->pcs.ops = &mtk_pcs_lynxi_ops; - mpcs->pcs.neg_mode = true; mpcs->pcs.poll = true; mpcs->interface = PHY_INTERFACE_MODE_NA; diff --git a/drivers/net/pcs/pcs-rzn1-miic.c b/drivers/net/pcs/pcs-rzn1-miic.c index a808ac7375f5..d79bb9b06cd2 100644 --- a/drivers/net/pcs/pcs-rzn1-miic.c +++ b/drivers/net/pcs/pcs-rzn1-miic.c @@ -349,7 +349,6 @@ struct phylink_pcs *miic_create(struct device *dev, struct device_node *np) miic_port->miic = miic; miic_port->port = port - 1; miic_port->pcs.ops = &miic_phylink_ops; - miic_port->pcs.neg_mode = true; phy_interface_set_rgmii(miic_port->pcs.supported_interfaces); __set_bit(PHY_INTERFACE_MODE_RMII, miic_port->pcs.supported_interfaces); diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c index 1faa37f0e7b9..e32dec4b812e 100644 --- a/drivers/net/pcs/pcs-xpcs.c +++ b/drivers/net/pcs/pcs-xpcs.c @@ -602,36 +602,6 @@ static void xpcs_get_interfaces(struct dw_xpcs *xpcs, unsigned long *interfaces) __set_bit(compat->interface, interfaces); } -int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns, int enable) -{ - u16 mask, val; - int ret; - - mask = DW_VR_MII_EEE_LTX_EN | DW_VR_MII_EEE_LRX_EN | - DW_VR_MII_EEE_TX_QUIET_EN | DW_VR_MII_EEE_RX_QUIET_EN | - DW_VR_MII_EEE_TX_EN_CTRL | DW_VR_MII_EEE_RX_EN_CTRL | - DW_VR_MII_EEE_MULT_FACT_100NS; - - if (enable) - val = DW_VR_MII_EEE_LTX_EN | DW_VR_MII_EEE_LRX_EN | - DW_VR_MII_EEE_TX_QUIET_EN | DW_VR_MII_EEE_RX_QUIET_EN | - DW_VR_MII_EEE_TX_EN_CTRL | DW_VR_MII_EEE_RX_EN_CTRL | - FIELD_PREP(DW_VR_MII_EEE_MULT_FACT_100NS, - mult_fact_100ns); - else - val = 0; - - ret = xpcs_modify(xpcs, MDIO_MMD_VEND2, DW_VR_MII_EEE_MCTRL0, mask, - val); - if (ret < 0) - return ret; - - return xpcs_modify(xpcs, MDIO_MMD_VEND2, DW_VR_MII_EEE_MCTRL1, - DW_VR_MII_EEE_TRN_LPI, - enable ? DW_VR_MII_EEE_TRN_LPI : 0); -} -EXPORT_SYMBOL_GPL(xpcs_config_eee); - static void xpcs_pre_config(struct phylink_pcs *pcs, phy_interface_t interface) { struct dw_xpcs *xpcs = phylink_pcs_to_xpcs(pcs); @@ -1193,6 +1163,63 @@ static void xpcs_an_restart(struct phylink_pcs *pcs) BMCR_ANRESTART); } +static int xpcs_config_eee(struct dw_xpcs *xpcs, bool enable) +{ + u16 mask, val; + int ret; + + mask = DW_VR_MII_EEE_LTX_EN | DW_VR_MII_EEE_LRX_EN | + DW_VR_MII_EEE_TX_QUIET_EN | DW_VR_MII_EEE_RX_QUIET_EN | + DW_VR_MII_EEE_TX_EN_CTRL | DW_VR_MII_EEE_RX_EN_CTRL | + DW_VR_MII_EEE_MULT_FACT_100NS; + + if (enable) + val = DW_VR_MII_EEE_LTX_EN | DW_VR_MII_EEE_LRX_EN | + DW_VR_MII_EEE_TX_QUIET_EN | DW_VR_MII_EEE_RX_QUIET_EN | + DW_VR_MII_EEE_TX_EN_CTRL | DW_VR_MII_EEE_RX_EN_CTRL | + FIELD_PREP(DW_VR_MII_EEE_MULT_FACT_100NS, + xpcs->eee_mult_fact); + else + val = 0; + + ret = xpcs_modify(xpcs, MDIO_MMD_VEND2, DW_VR_MII_EEE_MCTRL0, mask, + val); + if (ret < 0) + return ret; + + return xpcs_modify(xpcs, MDIO_MMD_VEND2, DW_VR_MII_EEE_MCTRL1, + DW_VR_MII_EEE_TRN_LPI, + enable ? DW_VR_MII_EEE_TRN_LPI : 0); +} + +static void xpcs_disable_eee(struct phylink_pcs *pcs) +{ + struct dw_xpcs *xpcs = phylink_pcs_to_xpcs(pcs); + + xpcs_config_eee(xpcs, false); +} + +static void xpcs_enable_eee(struct phylink_pcs *pcs) +{ + struct dw_xpcs *xpcs = phylink_pcs_to_xpcs(pcs); + + xpcs_config_eee(xpcs, true); +} + +/** + * xpcs_config_eee_mult_fact() - set the EEE clock multiplying factor + * @xpcs: pointer to a &struct dw_xpcs instance + * @mult_fact: the multiplying factor + * + * Configure the EEE clock multiplying factor. This value should be such that + * clk_eee_time_period * (mult_fact + 1) is within the range 80 to 120ns. + */ +void xpcs_config_eee_mult_fact(struct dw_xpcs *xpcs, u8 mult_fact) +{ + xpcs->eee_mult_fact = mult_fact; +} +EXPORT_SYMBOL_GPL(xpcs_config_eee_mult_fact); + static int xpcs_read_ids(struct dw_xpcs *xpcs) { int ret; @@ -1341,6 +1368,8 @@ static const struct phylink_pcs_ops xpcs_phylink_ops = { .pcs_get_state = xpcs_get_state, .pcs_an_restart = xpcs_an_restart, .pcs_link_up = xpcs_link_up, + .pcs_disable_eee = xpcs_disable_eee, + .pcs_enable_eee = xpcs_enable_eee, }; static int xpcs_identify(struct dw_xpcs *xpcs) @@ -1374,7 +1403,6 @@ static struct dw_xpcs *xpcs_create_data(struct mdio_device *mdiodev) mdio_device_get(mdiodev); xpcs->mdiodev = mdiodev; xpcs->pcs.ops = &xpcs_phylink_ops; - xpcs->pcs.neg_mode = true; xpcs->pcs.poll = true; return xpcs; diff --git a/drivers/net/pcs/pcs-xpcs.h b/drivers/net/pcs/pcs-xpcs.h index adc5a0b3c883..929fa238445e 100644 --- a/drivers/net/pcs/pcs-xpcs.h +++ b/drivers/net/pcs/pcs-xpcs.h @@ -55,23 +55,11 @@ /* Clause 37 Defines */ /* VR MII MMD registers offsets */ #define DW_VR_MII_DIG_CTRL1 0x8000 -#define DW_VR_MII_AN_CTRL 0x8001 -#define DW_VR_MII_AN_INTR_STS 0x8002 -/* EEE Mode Control Register */ -#define DW_VR_MII_EEE_MCTRL0 0x8006 -#define DW_VR_MII_EEE_MCTRL1 0x800b -#define DW_VR_MII_DIG_CTRL2 0x80e1 - -/* VR_MII_DIG_CTRL1 */ #define DW_VR_MII_DIG_CTRL1_MAC_AUTO_SW BIT(9) #define DW_VR_MII_DIG_CTRL1_2G5_EN BIT(2) #define DW_VR_MII_DIG_CTRL1_PHY_MODE_CTRL BIT(0) -/* VR_MII_DIG_CTRL2 */ -#define DW_VR_MII_DIG_CTRL2_TX_POL_INV BIT(4) -#define DW_VR_MII_DIG_CTRL2_RX_POL_INV BIT(0) - -/* VR_MII_AN_CTRL */ +#define DW_VR_MII_AN_CTRL 0x8001 #define DW_VR_MII_AN_CTRL_8BIT BIT(8) #define DW_VR_MII_TX_CONFIG_MASK BIT(3) #define DW_VR_MII_TX_CONFIG_PHY_SIDE_SGMII 0x1 @@ -81,7 +69,7 @@ #define DW_VR_MII_PCS_MODE_C37_SGMII 0x2 #define DW_VR_MII_AN_INTR_EN BIT(0) -/* VR_MII_AN_INTR_STS */ +#define DW_VR_MII_AN_INTR_STS 0x8002 #define DW_VR_MII_AN_STS_C37_ANCMPLT_INTR BIT(0) #define DW_VR_MII_AN_STS_C37_ANSGM_FD BIT(1) #define DW_VR_MII_AN_STS_C37_ANSGM_SP GENMASK(3, 2) @@ -90,19 +78,22 @@ #define DW_VR_MII_C37_ANSGM_SP_1000 0x2 #define DW_VR_MII_C37_ANSGM_SP_LNKSTS BIT(4) -/* VR MII EEE Control 0 defines */ +#define DW_VR_MII_EEE_MCTRL0 0x8006 #define DW_VR_MII_EEE_LTX_EN BIT(0) /* LPI Tx Enable */ #define DW_VR_MII_EEE_LRX_EN BIT(1) /* LPI Rx Enable */ #define DW_VR_MII_EEE_TX_QUIET_EN BIT(2) /* Tx Quiet Enable */ #define DW_VR_MII_EEE_RX_QUIET_EN BIT(3) /* Rx Quiet Enable */ #define DW_VR_MII_EEE_TX_EN_CTRL BIT(4) /* Tx Control Enable */ #define DW_VR_MII_EEE_RX_EN_CTRL BIT(7) /* Rx Control Enable */ - #define DW_VR_MII_EEE_MULT_FACT_100NS GENMASK(11, 8) -/* VR MII EEE Control 1 defines */ +#define DW_VR_MII_EEE_MCTRL1 0x800b #define DW_VR_MII_EEE_TRN_LPI BIT(0) /* Transparent Mode Enable */ +#define DW_VR_MII_DIG_CTRL2 0x80e1 +#define DW_VR_MII_DIG_CTRL2_TX_POL_INV BIT(4) +#define DW_VR_MII_DIG_CTRL2_RX_POL_INV BIT(0) + #define DW_XPCS_INFO_DECLARE(_name, _pcs, _pma) \ static const struct dw_xpcs_info _name = { .pcs = _pcs, .pma = _pma } @@ -122,6 +113,7 @@ struct dw_xpcs { struct phylink_pcs pcs; phy_interface_t interface; bool need_reset; + u8 eee_mult_fact; }; int xpcs_read(struct dw_xpcs *xpcs, int dev, u32 reg); diff --git a/drivers/net/pfcp.c b/drivers/net/pfcp.c index 68d0d9e92a22..f873a92d2445 100644 --- a/drivers/net/pfcp.c +++ b/drivers/net/pfcp.c @@ -184,15 +184,16 @@ static int pfcp_add_sock(struct pfcp_dev *pfcp) return PTR_ERR_OR_ZERO(pfcp->sock); } -static int pfcp_newlink(struct net *net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +static int pfcp_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { + struct net *link_net = rtnl_newlink_link_net(params); struct pfcp_dev *pfcp = netdev_priv(dev); struct pfcp_net *pn; int err; - pfcp->net = net; + pfcp->net = link_net; err = pfcp_add_sock(pfcp); if (err) { @@ -206,7 +207,7 @@ static int pfcp_newlink(struct net *net, struct net_device *dev, goto exit_del_pfcp_sock; } - pn = net_generic(net, pfcp_net_id); + pn = net_generic(link_net, pfcp_net_id); list_add(&pfcp->list, &pn->pfcp_dev_list); netdev_dbg(dev, "registered new PFCP interface\n"); diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c index 6599feca1967..3662f3905d5a 100644 --- a/drivers/net/phy/dp83822.c +++ b/drivers/net/phy/dp83822.c @@ -31,6 +31,7 @@ #define MII_DP83822_RCSR 0x17 #define MII_DP83822_RESET_CTRL 0x1f #define MII_DP83822_MLEDCR 0x25 +#define MII_DP83822_LDCTRL 0x403 #define MII_DP83822_LEDCFG1 0x460 #define MII_DP83822_IOCTRL1 0x462 #define MII_DP83822_IOCTRL2 0x463 @@ -123,6 +124,9 @@ #define DP83822_IOCTRL1_GPIO1_CTRL GENMASK(2, 0) #define DP83822_IOCTRL1_GPIO1_CTRL_LED_1 BIT(0) +/* LDCTRL bits */ +#define DP83822_100BASE_TX_LINE_DRIVER_SWING GENMASK(7, 4) + /* IOCTRL2 bits */ #define DP83822_IOCTRL2_GPIO2_CLK_SRC GENMASK(6, 4) #define DP83822_IOCTRL2_GPIO2_CTRL GENMASK(2, 0) @@ -197,6 +201,7 @@ struct dp83822_private { bool set_gpio2_clk_out; u32 gpio2_clk_out; bool led_pin_enable[DP83822_MAX_LED_PINS]; + int tx_amplitude_100base_tx_index; }; static int dp83822_config_wol(struct phy_device *phydev, @@ -522,6 +527,12 @@ static int dp83822_config_init(struct phy_device *phydev) FIELD_PREP(DP83822_IOCTRL2_GPIO2_CLK_SRC, dp83822->gpio2_clk_out)); + if (dp83822->tx_amplitude_100base_tx_index >= 0) + phy_modify_mmd(phydev, MDIO_MMD_VEND2, MII_DP83822_LDCTRL, + DP83822_100BASE_TX_LINE_DRIVER_SWING, + FIELD_PREP(DP83822_100BASE_TX_LINE_DRIVER_SWING, + dp83822->tx_amplitude_100base_tx_index)); + err = dp83822_config_init_leds(phydev); if (err) return err; @@ -720,6 +731,11 @@ static int dp83822_phy_reset(struct phy_device *phydev) } #ifdef CONFIG_OF_MDIO +static const u32 tx_amplitude_100base_tx_gain[] = { + 80, 82, 83, 85, 87, 88, 90, 92, + 93, 95, 97, 98, 100, 102, 103, 105, +}; + static int dp83822_of_init_leds(struct phy_device *phydev) { struct device_node *node = phydev->mdio.dev.of_node; @@ -780,6 +796,8 @@ static int dp83822_of_init(struct phy_device *phydev) struct dp83822_private *dp83822 = phydev->priv; struct device *dev = &phydev->mdio.dev; const char *of_val; + int i, ret; + u32 val; /* Signal detection for the PHY is only enabled if the FX_EN and the * SD_EN pins are strapped. Signal detection can only enabled if FX_EN @@ -815,6 +833,26 @@ static int dp83822_of_init(struct phy_device *phydev) dp83822->set_gpio2_clk_out = true; } + dp83822->tx_amplitude_100base_tx_index = -1; + ret = phy_get_tx_amplitude_gain(phydev, dev, + ETHTOOL_LINK_MODE_100baseT_Full_BIT, + &val); + if (!ret) { + for (i = 0; i < ARRAY_SIZE(tx_amplitude_100base_tx_gain); i++) { + if (tx_amplitude_100base_tx_gain[i] == val) { + dp83822->tx_amplitude_100base_tx_index = i; + break; + } + } + + if (dp83822->tx_amplitude_100base_tx_index < 0) { + phydev_err(phydev, + "Invalid value for tx-amplitude-100base-tx-percent property (%u)\n", + val); + return -EINVAL; + } + } + return dp83822_of_init_leds(phydev); } diff --git a/drivers/net/phy/marvell-88q2xxx.c b/drivers/net/phy/marvell-88q2xxx.c index bad5e7b2357d..15c0f8adc2f5 100644 --- a/drivers/net/phy/marvell-88q2xxx.c +++ b/drivers/net/phy/marvell-88q2xxx.c @@ -7,34 +7,34 @@ * Copyright (C) 2024 Liebherr-Electronics and Drives GmbH */ #include <linux/ethtool_netlink.h> +#include <linux/hwmon.h> #include <linux/marvell_phy.h> #include <linux/of.h> #include <linux/phy.h> -#include <linux/hwmon.h> -#define PHY_ID_88Q2220_REVB0 (MARVELL_PHY_ID_88Q2220 | 0x1) -#define PHY_ID_88Q2220_REVB1 (MARVELL_PHY_ID_88Q2220 | 0x2) -#define PHY_ID_88Q2220_REVB2 (MARVELL_PHY_ID_88Q2220 | 0x3) +#define PHY_ID_88Q2220_REVB0 (MARVELL_PHY_ID_88Q2220 | 0x1) +#define PHY_ID_88Q2220_REVB1 (MARVELL_PHY_ID_88Q2220 | 0x2) +#define PHY_ID_88Q2220_REVB2 (MARVELL_PHY_ID_88Q2220 | 0x3) -#define MDIO_MMD_AN_MV_STAT 32769 -#define MDIO_MMD_AN_MV_STAT_ANEG 0x0100 -#define MDIO_MMD_AN_MV_STAT_LOCAL_RX 0x1000 -#define MDIO_MMD_AN_MV_STAT_REMOTE_RX 0x2000 -#define MDIO_MMD_AN_MV_STAT_LOCAL_MASTER 0x4000 -#define MDIO_MMD_AN_MV_STAT_MS_CONF_FAULT 0x8000 +#define MDIO_MMD_AN_MV_STAT 32769 +#define MDIO_MMD_AN_MV_STAT_ANEG 0x0100 +#define MDIO_MMD_AN_MV_STAT_LOCAL_RX 0x1000 +#define MDIO_MMD_AN_MV_STAT_REMOTE_RX 0x2000 +#define MDIO_MMD_AN_MV_STAT_LOCAL_MASTER 0x4000 +#define MDIO_MMD_AN_MV_STAT_MS_CONF_FAULT 0x8000 -#define MDIO_MMD_AN_MV_STAT2 32794 -#define MDIO_MMD_AN_MV_STAT2_AN_RESOLVED 0x0800 -#define MDIO_MMD_AN_MV_STAT2_100BT1 0x2000 -#define MDIO_MMD_AN_MV_STAT2_1000BT1 0x4000 +#define MDIO_MMD_AN_MV_STAT2 32794 +#define MDIO_MMD_AN_MV_STAT2_AN_RESOLVED 0x0800 +#define MDIO_MMD_AN_MV_STAT2_100BT1 0x2000 +#define MDIO_MMD_AN_MV_STAT2_1000BT1 0x4000 -#define MDIO_MMD_PCS_MV_RESET_CTRL 32768 -#define MDIO_MMD_PCS_MV_RESET_CTRL_TX_DISABLE 0x8 +#define MDIO_MMD_PCS_MV_RESET_CTRL 32768 +#define MDIO_MMD_PCS_MV_RESET_CTRL_TX_DISABLE 0x8 -#define MDIO_MMD_PCS_MV_INT_EN 32784 -#define MDIO_MMD_PCS_MV_INT_EN_LINK_UP 0x0040 -#define MDIO_MMD_PCS_MV_INT_EN_LINK_DOWN 0x0080 -#define MDIO_MMD_PCS_MV_INT_EN_100BT1 0x1000 +#define MDIO_MMD_PCS_MV_INT_EN 32784 +#define MDIO_MMD_PCS_MV_INT_EN_LINK_UP 0x0040 +#define MDIO_MMD_PCS_MV_INT_EN_LINK_DOWN 0x0080 +#define MDIO_MMD_PCS_MV_INT_EN_100BT1 0x1000 #define MDIO_MMD_PCS_MV_GPIO_INT_STAT 32785 #define MDIO_MMD_PCS_MV_GPIO_INT_STAT_LINK_UP 0x0040 @@ -80,11 +80,11 @@ #define MDIO_MMD_PCS_MV_100BT1_STAT1_REMOTE_RX 0x2000 #define MDIO_MMD_PCS_MV_100BT1_STAT1_LOCAL_MASTER 0x4000 -#define MDIO_MMD_PCS_MV_100BT1_STAT2 33033 -#define MDIO_MMD_PCS_MV_100BT1_STAT2_JABBER 0x0001 -#define MDIO_MMD_PCS_MV_100BT1_STAT2_POL 0x0002 -#define MDIO_MMD_PCS_MV_100BT1_STAT2_LINK 0x0004 -#define MDIO_MMD_PCS_MV_100BT1_STAT2_ANGE 0x0008 +#define MDIO_MMD_PCS_MV_100BT1_STAT2 33033 +#define MDIO_MMD_PCS_MV_100BT1_STAT2_JABBER 0x0001 +#define MDIO_MMD_PCS_MV_100BT1_STAT2_POL 0x0002 +#define MDIO_MMD_PCS_MV_100BT1_STAT2_LINK 0x0004 +#define MDIO_MMD_PCS_MV_100BT1_STAT2_ANGE 0x0008 #define MDIO_MMD_PCS_MV_100BT1_INT_EN 33042 #define MDIO_MMD_PCS_MV_100BT1_INT_EN_LINKEVENT 0x0400 @@ -92,7 +92,7 @@ #define MDIO_MMD_PCS_MV_COPPER_INT_STAT 33043 #define MDIO_MMD_PCS_MV_COPPER_INT_STAT_LINKEVENT 0x0400 -#define MDIO_MMD_PCS_MV_RX_STAT 33328 +#define MDIO_MMD_PCS_MV_RX_STAT 33328 #define MDIO_MMD_PCS_MV_TDR_RESET 65226 #define MDIO_MMD_PCS_MV_TDR_RESET_TDR_RST 0x1000 @@ -115,8 +115,8 @@ #define MDIO_MMD_PCS_MV_TDR_OFF_CUTOFF 65246 -#define MV88Q2XXX_LED_INDEX_TX_ENABLE 0 -#define MV88Q2XXX_LED_INDEX_GPIO 1 +#define MV88Q2XXX_LED_INDEX_TX_ENABLE 0 +#define MV88Q2XXX_LED_INDEX_GPIO 1 struct mv88q2xxx_priv { bool enable_temp; @@ -513,6 +513,15 @@ static int mv88q2xxx_config_init(struct phy_device *phydev) return ret; } + /* Enable temperature sense */ + if (priv->enable_temp) { + ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, + MDIO_MMD_PCS_MV_TEMP_SENSOR2, + MDIO_MMD_PCS_MV_TEMP_SENSOR2_DIS_MASK, 0); + if (ret < 0) + return ret; + } + return 0; } @@ -825,13 +834,24 @@ static int mv88q2xxx_leds_probe(struct phy_device *phydev) static int mv88q2xxx_probe(struct phy_device *phydev) { struct mv88q2xxx_priv *priv; - int ret; priv = devm_kzalloc(&phydev->mdio.dev, sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; phydev->priv = priv; + + return 0; +} + +static int mv88q222x_probe(struct phy_device *phydev) +{ + int ret; + + ret = mv88q2xxx_probe(phydev); + if (ret) + return ret; + ret = mv88q2xxx_leds_probe(phydev); if (ret) return ret; @@ -903,18 +923,6 @@ static int mv88q222x_revb1_revb2_config_init(struct phy_device *phydev) static int mv88q222x_config_init(struct phy_device *phydev) { - struct mv88q2xxx_priv *priv = phydev->priv; - int ret; - - /* Enable temperature sense */ - if (priv->enable_temp) { - ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, - MDIO_MMD_PCS_MV_TEMP_SENSOR2, - MDIO_MMD_PCS_MV_TEMP_SENSOR2_DIS_MASK, 0); - if (ret < 0) - return ret; - } - if (phydev->c45_ids.device_ids[MDIO_MMD_PMAPMD] == PHY_ID_88Q2220_REVB0) return mv88q222x_revb0_config_init(phydev); else @@ -1101,6 +1109,7 @@ static struct phy_driver mv88q2xxx_driver[] = { .phy_id = MARVELL_PHY_ID_88Q2110, .phy_id_mask = MARVELL_PHY_ID_MASK, .name = "mv88q2110", + .probe = mv88q2xxx_probe, .get_features = mv88q2xxx_get_features, .config_aneg = mv88q2xxx_config_aneg, .config_init = mv88q2110_config_init, @@ -1115,7 +1124,7 @@ static struct phy_driver mv88q2xxx_driver[] = { .phy_id_mask = MARVELL_PHY_ID_MASK, .name = "mv88q2220", .flags = PHY_POLL_CABLE_TEST, - .probe = mv88q2xxx_probe, + .probe = mv88q222x_probe, .get_features = mv88q2xxx_get_features, .config_aneg = mv88q2xxx_config_aneg, .aneg_done = genphy_c45_aneg_done, diff --git a/drivers/net/phy/mediatek/mtk-ge-soc.c b/drivers/net/phy/mediatek/mtk-ge-soc.c index bdf99b327029..9de6fbb45564 100644 --- a/drivers/net/phy/mediatek/mtk-ge-soc.c +++ b/drivers/net/phy/mediatek/mtk-ge-soc.c @@ -24,7 +24,107 @@ #define MTK_PHY_SMI_DET_ON_THRESH_MASK GENMASK(13, 8) #define MTK_PHY_PAGE_EXTENDED_2A30 0x2a30 -#define MTK_PHY_PAGE_EXTENDED_52B5 0x52b5 + +/* Registers on Token Ring debug nodes */ +/* ch_addr = 0x0, node_addr = 0x7, data_addr = 0x15 */ +/* NormMseLoThresh */ +#define NORMAL_MSE_LO_THRESH_MASK GENMASK(15, 8) + +/* ch_addr = 0x0, node_addr = 0xf, data_addr = 0x3c */ +/* RemAckCntLimitCtrl */ +#define REMOTE_ACK_COUNT_LIMIT_CTRL_MASK GENMASK(2, 1) + +/* ch_addr = 0x1, node_addr = 0xd, data_addr = 0x20 */ +/* VcoSlicerThreshBitsHigh */ +#define VCO_SLICER_THRESH_HIGH_MASK GENMASK(23, 0) + +/* ch_addr = 0x1, node_addr = 0xf, data_addr = 0x0 */ +/* DfeTailEnableVgaThresh1000 */ +#define DFE_TAIL_EANBLE_VGA_TRHESH_1000 GENMASK(5, 1) + +/* ch_addr = 0x1, node_addr = 0xf, data_addr = 0x1 */ +/* MrvlTrFix100Kp */ +#define MRVL_TR_FIX_100KP_MASK GENMASK(22, 20) +/* MrvlTrFix100Kf */ +#define MRVL_TR_FIX_100KF_MASK GENMASK(19, 17) +/* MrvlTrFix1000Kp */ +#define MRVL_TR_FIX_1000KP_MASK GENMASK(16, 14) +/* MrvlTrFix1000Kf */ +#define MRVL_TR_FIX_1000KF_MASK GENMASK(13, 11) + +/* ch_addr = 0x1, node_addr = 0xf, data_addr = 0x12 */ +/* VgaDecRate */ +#define VGA_DECIMATION_RATE_MASK GENMASK(8, 5) + +/* ch_addr = 0x1, node_addr = 0xf, data_addr = 0x17 */ +/* SlvDSPreadyTime */ +#define SLAVE_DSP_READY_TIME_MASK GENMASK(22, 15) +/* MasDSPreadyTime */ +#define MASTER_DSP_READY_TIME_MASK GENMASK(14, 7) + +/* ch_addr = 0x1, node_addr = 0xf, data_addr = 0x18 */ +/* EnabRandUpdTrig */ +#define ENABLE_RANDOM_UPDOWN_COUNTER_TRIGGER BIT(8) + +/* ch_addr = 0x1, node_addr = 0xf, data_addr = 0x20 */ +/* ResetSyncOffset */ +#define RESET_SYNC_OFFSET_MASK GENMASK(11, 8) + +/* ch_addr = 0x2, node_addr = 0xd, data_addr = 0x0 */ +/* FfeUpdGainForceVal */ +#define FFE_UPDATE_GAIN_FORCE_VAL_MASK GENMASK(9, 7) +/* FfeUpdGainForce */ +#define FFE_UPDATE_GAIN_FORCE BIT(6) + +/* ch_addr = 0x2, node_addr = 0xd, data_addr = 0x3 */ +/* TrFreeze */ +#define TR_FREEZE_MASK GENMASK(11, 0) + +/* ch_addr = 0x2, node_addr = 0xd, data_addr = 0x6 */ +/* SS: Steady-state, KP: Proportional Gain */ +/* SSTrKp100 */ +#define SS_TR_KP100_MASK GENMASK(21, 19) +/* SSTrKf100 */ +#define SS_TR_KF100_MASK GENMASK(18, 16) +/* SSTrKp1000Mas */ +#define SS_TR_KP1000_MASTER_MASK GENMASK(15, 13) +/* SSTrKf1000Mas */ +#define SS_TR_KF1000_MASTER_MASK GENMASK(12, 10) +/* SSTrKp1000Slv */ +#define SS_TR_KP1000_SLAVE_MASK GENMASK(9, 7) +/* SSTrKf1000Slv */ +#define SS_TR_KF1000_SLAVE_MASK GENMASK(6, 4) + +/* ch_addr = 0x2, node_addr = 0xd, data_addr = 0x8 */ +/* clear this bit if wanna select from AFE */ +/* Regsigdet_sel_1000 */ +#define EEE1000_SELECT_SIGNAL_DETECTION_FROM_DFE BIT(4) + +/* ch_addr = 0x2, node_addr = 0xd, data_addr = 0xd */ +/* RegEEE_st2TrKf1000 */ +#define EEE1000_STAGE2_TR_KF_MASK GENMASK(13, 11) + +/* ch_addr = 0x2, node_addr = 0xd, data_addr = 0xf */ +/* RegEEE_slv_waketr_timer_tar */ +#define SLAVE_WAKETR_TIMER_MASK GENMASK(20, 11) +/* RegEEE_slv_remtx_timer_tar */ +#define SLAVE_REMTX_TIMER_MASK GENMASK(10, 1) + +/* ch_addr = 0x2, node_addr = 0xd, data_addr = 0x10 */ +/* RegEEE_slv_wake_int_timer_tar */ +#define SLAVE_WAKEINT_TIMER_MASK GENMASK(10, 1) + +/* ch_addr = 0x2, node_addr = 0xd, data_addr = 0x14 */ +/* RegEEE_trfreeze_timer2 */ +#define TR_FREEZE_TIMER2_MASK GENMASK(9, 0) + +/* ch_addr = 0x2, node_addr = 0xd, data_addr = 0x1c */ +/* RegEEE100Stg1_tar */ +#define EEE100_LPSYNC_STAGE1_UPDATE_TIMER_MASK GENMASK(8, 0) + +/* ch_addr = 0x2, node_addr = 0xd, data_addr = 0x25 */ +/* REGEEE_wake_slv_tr_wait_dfesigdet_en */ +#define WAKE_SLAVE_TR_WAIT_DFE_DETECTION_EN BIT(11) #define ANALOG_INTERNAL_OPERATION_MAX_US 20 #define TXRESERVE_MIN 0 @@ -701,40 +801,36 @@ restore: static void mt798x_phy_common_finetune(struct phy_device *phydev) { phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_52B5); - /* SlvDSPreadyTime = 24, MasDSPreadyTime = 24 */ - __phy_write(phydev, 0x11, 0xc71); - __phy_write(phydev, 0x12, 0xc); - __phy_write(phydev, 0x10, 0x8fae); - - /* EnabRandUpdTrig = 1 */ - __phy_write(phydev, 0x11, 0x2f00); - __phy_write(phydev, 0x12, 0xe); - __phy_write(phydev, 0x10, 0x8fb0); - - /* NormMseLoThresh = 85 */ - __phy_write(phydev, 0x11, 0x55a0); - __phy_write(phydev, 0x12, 0x0); - __phy_write(phydev, 0x10, 0x83aa); - - /* FfeUpdGainForce = 1(Enable), FfeUpdGainForceVal = 4 */ - __phy_write(phydev, 0x11, 0x240); - __phy_write(phydev, 0x12, 0x0); - __phy_write(phydev, 0x10, 0x9680); - - /* TrFreeze = 0 (mt7988 default) */ - __phy_write(phydev, 0x11, 0x0); - __phy_write(phydev, 0x12, 0x0); - __phy_write(phydev, 0x10, 0x9686); - - /* SSTrKp100 = 5 */ - /* SSTrKf100 = 6 */ - /* SSTrKp1000Mas = 5 */ - /* SSTrKf1000Mas = 6 */ - /* SSTrKp1000Slv = 5 */ - /* SSTrKf1000Slv = 6 */ - __phy_write(phydev, 0x11, 0xbaef); - __phy_write(phydev, 0x12, 0x2e); - __phy_write(phydev, 0x10, 0x968c); + __mtk_tr_modify(phydev, 0x1, 0xf, 0x17, + SLAVE_DSP_READY_TIME_MASK | MASTER_DSP_READY_TIME_MASK, + FIELD_PREP(SLAVE_DSP_READY_TIME_MASK, 0x18) | + FIELD_PREP(MASTER_DSP_READY_TIME_MASK, 0x18)); + + __mtk_tr_set_bits(phydev, 0x1, 0xf, 0x18, + ENABLE_RANDOM_UPDOWN_COUNTER_TRIGGER); + + __mtk_tr_modify(phydev, 0x0, 0x7, 0x15, + NORMAL_MSE_LO_THRESH_MASK, + FIELD_PREP(NORMAL_MSE_LO_THRESH_MASK, 0x55)); + + __mtk_tr_modify(phydev, 0x2, 0xd, 0x0, + FFE_UPDATE_GAIN_FORCE_VAL_MASK, + FIELD_PREP(FFE_UPDATE_GAIN_FORCE_VAL_MASK, 0x4) | + FFE_UPDATE_GAIN_FORCE); + + __mtk_tr_clr_bits(phydev, 0x2, 0xd, 0x3, TR_FREEZE_MASK); + + __mtk_tr_modify(phydev, 0x2, 0xd, 0x6, + SS_TR_KP100_MASK | SS_TR_KF100_MASK | + SS_TR_KP1000_MASTER_MASK | SS_TR_KF1000_MASTER_MASK | + SS_TR_KP1000_SLAVE_MASK | SS_TR_KF1000_SLAVE_MASK, + FIELD_PREP(SS_TR_KP100_MASK, 0x5) | + FIELD_PREP(SS_TR_KF100_MASK, 0x6) | + FIELD_PREP(SS_TR_KP1000_MASTER_MASK, 0x5) | + FIELD_PREP(SS_TR_KF1000_MASTER_MASK, 0x6) | + FIELD_PREP(SS_TR_KP1000_SLAVE_MASK, 0x5) | + FIELD_PREP(SS_TR_KF1000_SLAVE_MASK, 0x6)); + phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0); } @@ -757,27 +853,29 @@ static void mt7981_phy_finetune(struct phy_device *phydev) } phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_52B5); - /* ResetSyncOffset = 6 */ - __phy_write(phydev, 0x11, 0x600); - __phy_write(phydev, 0x12, 0x0); - __phy_write(phydev, 0x10, 0x8fc0); + __mtk_tr_modify(phydev, 0x1, 0xf, 0x20, + RESET_SYNC_OFFSET_MASK, + FIELD_PREP(RESET_SYNC_OFFSET_MASK, 0x6)); - /* VgaDecRate = 1 */ - __phy_write(phydev, 0x11, 0x4c2a); - __phy_write(phydev, 0x12, 0x3e); - __phy_write(phydev, 0x10, 0x8fa4); + __mtk_tr_modify(phydev, 0x1, 0xf, 0x12, + VGA_DECIMATION_RATE_MASK, + FIELD_PREP(VGA_DECIMATION_RATE_MASK, 0x1)); /* MrvlTrFix100Kp = 3, MrvlTrFix100Kf = 2, * MrvlTrFix1000Kp = 3, MrvlTrFix1000Kf = 2 */ - __phy_write(phydev, 0x11, 0xd10a); - __phy_write(phydev, 0x12, 0x34); - __phy_write(phydev, 0x10, 0x8f82); + __mtk_tr_modify(phydev, 0x1, 0xf, 0x1, + MRVL_TR_FIX_100KP_MASK | MRVL_TR_FIX_100KF_MASK | + MRVL_TR_FIX_1000KP_MASK | MRVL_TR_FIX_1000KF_MASK, + FIELD_PREP(MRVL_TR_FIX_100KP_MASK, 0x3) | + FIELD_PREP(MRVL_TR_FIX_100KF_MASK, 0x2) | + FIELD_PREP(MRVL_TR_FIX_1000KP_MASK, 0x3) | + FIELD_PREP(MRVL_TR_FIX_1000KF_MASK, 0x2)); /* VcoSlicerThreshBitsHigh */ - __phy_write(phydev, 0x11, 0x5555); - __phy_write(phydev, 0x12, 0x55); - __phy_write(phydev, 0x10, 0x8ec0); + __mtk_tr_modify(phydev, 0x1, 0xd, 0x20, + VCO_SLICER_THRESH_HIGH_MASK, + FIELD_PREP(VCO_SLICER_THRESH_HIGH_MASK, 0x555555)); phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0); /* TR_OPEN_LOOP_EN = 1, lpf_x_average = 9 */ @@ -829,25 +927,23 @@ static void mt7988_phy_finetune(struct phy_device *phydev) phy_write_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_TX_FILTER, 0x5); phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_52B5); - /* ResetSyncOffset = 5 */ - __phy_write(phydev, 0x11, 0x500); - __phy_write(phydev, 0x12, 0x0); - __phy_write(phydev, 0x10, 0x8fc0); + __mtk_tr_modify(phydev, 0x1, 0xf, 0x20, + RESET_SYNC_OFFSET_MASK, + FIELD_PREP(RESET_SYNC_OFFSET_MASK, 0x5)); /* VgaDecRate is 1 at default on mt7988 */ - /* MrvlTrFix100Kp = 6, MrvlTrFix100Kf = 7, - * MrvlTrFix1000Kp = 6, MrvlTrFix1000Kf = 7 - */ - __phy_write(phydev, 0x11, 0xb90a); - __phy_write(phydev, 0x12, 0x6f); - __phy_write(phydev, 0x10, 0x8f82); - - /* RemAckCntLimitCtrl = 1 */ - __phy_write(phydev, 0x11, 0xfbba); - __phy_write(phydev, 0x12, 0xc3); - __phy_write(phydev, 0x10, 0x87f8); - + __mtk_tr_modify(phydev, 0x1, 0xf, 0x1, + MRVL_TR_FIX_100KP_MASK | MRVL_TR_FIX_100KF_MASK | + MRVL_TR_FIX_1000KP_MASK | MRVL_TR_FIX_1000KF_MASK, + FIELD_PREP(MRVL_TR_FIX_100KP_MASK, 0x6) | + FIELD_PREP(MRVL_TR_FIX_100KF_MASK, 0x7) | + FIELD_PREP(MRVL_TR_FIX_1000KP_MASK, 0x6) | + FIELD_PREP(MRVL_TR_FIX_1000KF_MASK, 0x7)); + + __mtk_tr_modify(phydev, 0x0, 0xf, 0x3c, + REMOTE_ACK_COUNT_LIMIT_CTRL_MASK, + FIELD_PREP(REMOTE_ACK_COUNT_LIMIT_CTRL_MASK, 0x1)); phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0); /* TR_OPEN_LOOP_EN = 1, lpf_x_average = 10 */ @@ -923,45 +1019,37 @@ static void mt798x_phy_eee(struct phy_device *phydev) MTK_PHY_TR_READY_SKIP_AFE_WAKEUP); phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_52B5); - /* Regsigdet_sel_1000 = 0 */ - __phy_write(phydev, 0x11, 0xb); - __phy_write(phydev, 0x12, 0x0); - __phy_write(phydev, 0x10, 0x9690); - - /* REG_EEE_st2TrKf1000 = 2 */ - __phy_write(phydev, 0x11, 0x114f); - __phy_write(phydev, 0x12, 0x2); - __phy_write(phydev, 0x10, 0x969a); - - /* RegEEE_slv_wake_tr_timer_tar = 6, RegEEE_slv_remtx_timer_tar = 20 */ - __phy_write(phydev, 0x11, 0x3028); - __phy_write(phydev, 0x12, 0x0); - __phy_write(phydev, 0x10, 0x969e); - - /* RegEEE_slv_wake_int_timer_tar = 8 */ - __phy_write(phydev, 0x11, 0x5010); - __phy_write(phydev, 0x12, 0x0); - __phy_write(phydev, 0x10, 0x96a0); - - /* RegEEE_trfreeze_timer2 = 586 */ - __phy_write(phydev, 0x11, 0x24a); - __phy_write(phydev, 0x12, 0x0); - __phy_write(phydev, 0x10, 0x96a8); - - /* RegEEE100Stg1_tar = 16 */ - __phy_write(phydev, 0x11, 0x3210); - __phy_write(phydev, 0x12, 0x0); - __phy_write(phydev, 0x10, 0x96b8); - - /* REGEEE_wake_slv_tr_wait_dfesigdet_en = 0 */ - __phy_write(phydev, 0x11, 0x1463); - __phy_write(phydev, 0x12, 0x0); - __phy_write(phydev, 0x10, 0x96ca); - - /* DfeTailEnableVgaThresh1000 = 27 */ - __phy_write(phydev, 0x11, 0x36); - __phy_write(phydev, 0x12, 0x0); - __phy_write(phydev, 0x10, 0x8f80); + __mtk_tr_clr_bits(phydev, 0x2, 0xd, 0x8, + EEE1000_SELECT_SIGNAL_DETECTION_FROM_DFE); + + __mtk_tr_modify(phydev, 0x2, 0xd, 0xd, + EEE1000_STAGE2_TR_KF_MASK, + FIELD_PREP(EEE1000_STAGE2_TR_KF_MASK, 0x2)); + + __mtk_tr_modify(phydev, 0x2, 0xd, 0xf, + SLAVE_WAKETR_TIMER_MASK | SLAVE_REMTX_TIMER_MASK, + FIELD_PREP(SLAVE_WAKETR_TIMER_MASK, 0x6) | + FIELD_PREP(SLAVE_REMTX_TIMER_MASK, 0x14)); + + __mtk_tr_modify(phydev, 0x2, 0xd, 0x10, + SLAVE_WAKEINT_TIMER_MASK, + FIELD_PREP(SLAVE_WAKEINT_TIMER_MASK, 0x8)); + + __mtk_tr_modify(phydev, 0x2, 0xd, 0x14, + TR_FREEZE_TIMER2_MASK, + FIELD_PREP(TR_FREEZE_TIMER2_MASK, 0x24a)); + + __mtk_tr_modify(phydev, 0x2, 0xd, 0x1c, + EEE100_LPSYNC_STAGE1_UPDATE_TIMER_MASK, + FIELD_PREP(EEE100_LPSYNC_STAGE1_UPDATE_TIMER_MASK, + 0x10)); + + __mtk_tr_clr_bits(phydev, 0x2, 0xd, 0x25, + WAKE_SLAVE_TR_WAIT_DFE_DETECTION_EN); + + __mtk_tr_modify(phydev, 0x1, 0xf, 0x0, + DFE_TAIL_EANBLE_VGA_TRHESH_1000, + FIELD_PREP(DFE_TAIL_EANBLE_VGA_TRHESH_1000, 0x1b)); phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0); phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_3); diff --git a/drivers/net/phy/mediatek/mtk-ge.c b/drivers/net/phy/mediatek/mtk-ge.c index b517ca8573e7..73d9b72f9d9e 100644 --- a/drivers/net/phy/mediatek/mtk-ge.c +++ b/drivers/net/phy/mediatek/mtk-ge.c @@ -8,31 +8,58 @@ #define MTK_GPHY_ID_MT7530 0x03a29412 #define MTK_GPHY_ID_MT7531 0x03a29441 -#define MTK_EXT_PAGE_ACCESS 0x1f -#define MTK_PHY_PAGE_STANDARD 0x0000 -#define MTK_PHY_PAGE_EXTENDED 0x0001 -#define MTK_PHY_PAGE_EXTENDED_2 0x0002 -#define MTK_PHY_PAGE_EXTENDED_3 0x0003 -#define MTK_PHY_PAGE_EXTENDED_2A30 0x2a30 -#define MTK_PHY_PAGE_EXTENDED_52B5 0x52b5 +#define MTK_PHY_PAGE_EXTENDED_2 0x0002 +#define MTK_PHY_PAGE_EXTENDED_3 0x0003 +#define MTK_PHY_RG_LPI_PCS_DSP_CTRL_REG11 0x11 + +#define MTK_PHY_PAGE_EXTENDED_2A30 0x2a30 + +/* Registers on Token Ring debug nodes */ +/* ch_addr = 0x1, node_addr = 0xf, data_addr = 0x17 */ +#define SLAVE_DSP_READY_TIME_MASK GENMASK(22, 15) + +/* Registers on MDIO_MMD_VEND1 */ +#define MTK_PHY_GBE_MODE_TX_DELAY_SEL 0x13 +#define MTK_PHY_TEST_MODE_TX_DELAY_SEL 0x14 +#define MTK_TX_DELAY_PAIR_B_MASK GENMASK(10, 8) +#define MTK_TX_DELAY_PAIR_D_MASK GENMASK(2, 0) + +#define MTK_PHY_MCC_CTRL_AND_TX_POWER_CTRL 0xa6 +#define MTK_MCC_NEARECHO_OFFSET_MASK GENMASK(15, 8) + +#define MTK_PHY_RXADC_CTRL_RG7 0xc6 +#define MTK_PHY_DA_AD_BUF_BIAS_LP_MASK GENMASK(9, 8) + +#define MTK_PHY_RG_LPI_PCS_DSP_CTRL_REG123 0x123 +#define MTK_PHY_LPI_NORM_MSE_LO_THRESH100_MASK GENMASK(15, 8) +#define MTK_PHY_LPI_NORM_MSE_HI_THRESH100_MASK GENMASK(7, 0) static void mtk_gephy_config_init(struct phy_device *phydev) { /* Enable HW auto downshift */ - phy_modify_paged(phydev, MTK_PHY_PAGE_EXTENDED, 0x14, 0, BIT(4)); + phy_modify_paged(phydev, MTK_PHY_PAGE_EXTENDED_1, + MTK_PHY_AUX_CTRL_AND_STATUS, + 0, MTK_PHY_ENABLE_DOWNSHIFT); /* Increase SlvDPSready time */ - phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_52B5); - __phy_write(phydev, 0x10, 0xafae); - __phy_write(phydev, 0x12, 0x2f); - __phy_write(phydev, 0x10, 0x8fae); - phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0); + mtk_tr_modify(phydev, 0x1, 0xf, 0x17, SLAVE_DSP_READY_TIME_MASK, + FIELD_PREP(SLAVE_DSP_READY_TIME_MASK, 0x5e)); /* Adjust 100_mse_threshold */ - phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x123, 0xffff); - - /* Disable mcc */ - phy_write_mmd(phydev, MDIO_MMD_VEND1, 0xa6, 0x300); + phy_modify_mmd(phydev, MDIO_MMD_VEND1, + MTK_PHY_RG_LPI_PCS_DSP_CTRL_REG123, + MTK_PHY_LPI_NORM_MSE_LO_THRESH100_MASK | + MTK_PHY_LPI_NORM_MSE_HI_THRESH100_MASK, + FIELD_PREP(MTK_PHY_LPI_NORM_MSE_LO_THRESH100_MASK, + 0xff) | + FIELD_PREP(MTK_PHY_LPI_NORM_MSE_HI_THRESH100_MASK, + 0xff)); + + /* If echo time is narrower than 0x3, it will be regarded as noise */ + phy_modify_mmd(phydev, MDIO_MMD_VEND1, + MTK_PHY_MCC_CTRL_AND_TX_POWER_CTRL, + MTK_MCC_NEARECHO_OFFSET_MASK, + FIELD_PREP(MTK_MCC_NEARECHO_OFFSET_MASK, 0x3)); } static int mt7530_phy_config_init(struct phy_device *phydev) @@ -40,7 +67,8 @@ static int mt7530_phy_config_init(struct phy_device *phydev) mtk_gephy_config_init(phydev); /* Increase post_update_timer */ - phy_write_paged(phydev, MTK_PHY_PAGE_EXTENDED_3, 0x11, 0x4b); + phy_write_paged(phydev, MTK_PHY_PAGE_EXTENDED_3, + MTK_PHY_RG_LPI_PCS_DSP_CTRL_REG11, 0x4b); return 0; } @@ -51,11 +79,19 @@ static int mt7531_phy_config_init(struct phy_device *phydev) /* PHY link down power saving enable */ phy_set_bits(phydev, 0x17, BIT(4)); - phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, 0xc6, 0x300); + phy_modify_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RXADC_CTRL_RG7, + MTK_PHY_DA_AD_BUF_BIAS_LP_MASK, + FIELD_PREP(MTK_PHY_DA_AD_BUF_BIAS_LP_MASK, 0x3)); /* Set TX Pair delay selection */ - phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x13, 0x404); - phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x14, 0x404); + phy_modify_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_GBE_MODE_TX_DELAY_SEL, + MTK_TX_DELAY_PAIR_B_MASK | MTK_TX_DELAY_PAIR_D_MASK, + FIELD_PREP(MTK_TX_DELAY_PAIR_B_MASK, 0x4) | + FIELD_PREP(MTK_TX_DELAY_PAIR_D_MASK, 0x4)); + phy_modify_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_TEST_MODE_TX_DELAY_SEL, + MTK_TX_DELAY_PAIR_B_MASK | MTK_TX_DELAY_PAIR_D_MASK, + FIELD_PREP(MTK_TX_DELAY_PAIR_B_MASK, 0x4) | + FIELD_PREP(MTK_TX_DELAY_PAIR_D_MASK, 0x4)); return 0; } diff --git a/drivers/net/phy/mediatek/mtk-phy-lib.c b/drivers/net/phy/mediatek/mtk-phy-lib.c index 98a09d670e9c..dfd0f4e439a2 100644 --- a/drivers/net/phy/mediatek/mtk-phy-lib.c +++ b/drivers/net/phy/mediatek/mtk-phy-lib.c @@ -6,6 +6,83 @@ #include "mtk.h" +/* Difference between functions with mtk_tr* and __mtk_tr* prefixes is + * mtk_tr* functions: wrapped by page switching operations + * __mtk_tr* functions: no page switching operations + */ + +static void __mtk_tr_access(struct phy_device *phydev, bool read, u8 ch_addr, + u8 node_addr, u8 data_addr) +{ + u16 tr_cmd = BIT(15); /* bit 14 & 0 are reserved */ + + if (read) + tr_cmd |= BIT(13); + + tr_cmd |= (((ch_addr & 0x3) << 11) | + ((node_addr & 0xf) << 7) | + ((data_addr & 0x3f) << 1)); + dev_dbg(&phydev->mdio.dev, "tr_cmd: 0x%x\n", tr_cmd); + __phy_write(phydev, 0x10, tr_cmd); +} + +static void __mtk_tr_read(struct phy_device *phydev, u8 ch_addr, u8 node_addr, + u8 data_addr, u16 *tr_high, u16 *tr_low) +{ + __mtk_tr_access(phydev, true, ch_addr, node_addr, data_addr); + *tr_low = __phy_read(phydev, 0x11); + *tr_high = __phy_read(phydev, 0x12); + dev_dbg(&phydev->mdio.dev, "tr_high read: 0x%x, tr_low read: 0x%x\n", + *tr_high, *tr_low); +} + +static void __mtk_tr_write(struct phy_device *phydev, u8 ch_addr, u8 node_addr, + u8 data_addr, u32 tr_data) +{ + __phy_write(phydev, 0x11, tr_data & 0xffff); + __phy_write(phydev, 0x12, tr_data >> 16); + dev_dbg(&phydev->mdio.dev, "tr_high write: 0x%x, tr_low write: 0x%x\n", + tr_data >> 16, tr_data & 0xffff); + __mtk_tr_access(phydev, false, ch_addr, node_addr, data_addr); +} + +void __mtk_tr_modify(struct phy_device *phydev, u8 ch_addr, u8 node_addr, + u8 data_addr, u32 mask, u32 set) +{ + u32 tr_data; + u16 tr_high; + u16 tr_low; + + __mtk_tr_read(phydev, ch_addr, node_addr, data_addr, &tr_high, &tr_low); + tr_data = (tr_high << 16) | tr_low; + tr_data = (tr_data & ~mask) | set; + __mtk_tr_write(phydev, ch_addr, node_addr, data_addr, tr_data); +} +EXPORT_SYMBOL_GPL(__mtk_tr_modify); + +void mtk_tr_modify(struct phy_device *phydev, u8 ch_addr, u8 node_addr, + u8 data_addr, u32 mask, u32 set) +{ + phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_52B5); + __mtk_tr_modify(phydev, ch_addr, node_addr, data_addr, mask, set); + phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0); +} +EXPORT_SYMBOL_GPL(mtk_tr_modify); + +void __mtk_tr_set_bits(struct phy_device *phydev, u8 ch_addr, u8 node_addr, + u8 data_addr, u32 set) +{ + __mtk_tr_modify(phydev, ch_addr, node_addr, data_addr, 0, set); +} +EXPORT_SYMBOL_GPL(__mtk_tr_set_bits); + +void __mtk_tr_clr_bits(struct phy_device *phydev, u8 ch_addr, u8 node_addr, + u8 data_addr, u32 clr) +{ + __mtk_tr_modify(phydev, ch_addr, node_addr, data_addr, clr, 0); +} +EXPORT_SYMBOL_GPL(__mtk_tr_clr_bits); + int mtk_phy_read_page(struct phy_device *phydev) { return __phy_read(phydev, MTK_EXT_PAGE_ACCESS); diff --git a/drivers/net/phy/mediatek/mtk.h b/drivers/net/phy/mediatek/mtk.h index 63d9fe179b8f..320f76ffa81f 100644 --- a/drivers/net/phy/mediatek/mtk.h +++ b/drivers/net/phy/mediatek/mtk.h @@ -8,7 +8,13 @@ #ifndef _MTK_EPHY_H_ #define _MTK_EPHY_H_ +#define MTK_PHY_AUX_CTRL_AND_STATUS 0x14 +#define MTK_PHY_ENABLE_DOWNSHIFT BIT(4) + #define MTK_EXT_PAGE_ACCESS 0x1f +#define MTK_PHY_PAGE_EXTENDED_1 0x0001 +#define MTK_PHY_PAGE_STANDARD 0x0000 +#define MTK_PHY_PAGE_EXTENDED_52B5 0x52b5 /* Registers on MDIO_MMD_VEND2 */ #define MTK_PHY_LED0_ON_CTRL 0x24 @@ -66,6 +72,15 @@ struct mtk_socphy_priv { unsigned long led_state; }; +void __mtk_tr_modify(struct phy_device *phydev, u8 ch_addr, u8 node_addr, + u8 data_addr, u32 mask, u32 set); +void mtk_tr_modify(struct phy_device *phydev, u8 ch_addr, u8 node_addr, + u8 data_addr, u32 mask, u32 set); +void __mtk_tr_set_bits(struct phy_device *phydev, u8 ch_addr, u8 node_addr, + u8 data_addr, u32 set); +void __mtk_tr_clr_bits(struct phy_device *phydev, u8 ch_addr, u8 node_addr, + u8 data_addr, u32 clr); + int mtk_phy_read_page(struct phy_device *phydev); int mtk_phy_write_page(struct phy_device *phydev, int page); diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c index 468d246113a4..37c9a344bf4a 100644 --- a/drivers/net/phy/phy-c45.c +++ b/drivers/net/phy/phy-c45.c @@ -683,13 +683,10 @@ EXPORT_SYMBOL_GPL(genphy_c45_read_mdix); static int genphy_c45_write_eee_adv(struct phy_device *phydev, unsigned long *adv) { - __ETHTOOL_DECLARE_LINK_MODE_MASK(tmp); int val, changed = 0; - linkmode_andnot(tmp, adv, phydev->eee_disabled_modes); - if (linkmode_intersects(phydev->supported_eee, PHY_EEE_CAP1_FEATURES)) { - val = linkmode_to_mii_eee_cap1_t(tmp); + val = linkmode_to_mii_eee_cap1_t(adv); /* IEEE 802.3-2018 45.2.7.13 EEE advertisement 1 * (Register 7.60) @@ -707,7 +704,7 @@ static int genphy_c45_write_eee_adv(struct phy_device *phydev, } if (linkmode_intersects(phydev->supported_eee, PHY_EEE_CAP2_FEATURES)) { - val = linkmode_to_mii_eee_cap2_t(tmp); + val = linkmode_to_mii_eee_cap2_t(adv); /* IEEE 802.3-2022 45.2.7.16 EEE advertisement 2 * (Register 7.62) @@ -1467,42 +1464,29 @@ EXPORT_SYMBOL_GPL(genphy_c45_plca_get_status); /** * genphy_c45_eee_is_active - get EEE status * @phydev: target phy_device struct - * @adv: variable to store advertised linkmodes * @lp: variable to store LP advertised linkmodes * - * Description: this function will read local and link partner PHY - * advertisements. Compare them return current EEE state. + * Description: this function will read link partner PHY advertisement + * and compare it to local advertisement to return current EEE state. */ -int genphy_c45_eee_is_active(struct phy_device *phydev, unsigned long *adv, - unsigned long *lp) +int genphy_c45_eee_is_active(struct phy_device *phydev, unsigned long *lp) { - __ETHTOOL_DECLARE_LINK_MODE_MASK(tmp_adv) = {}; __ETHTOOL_DECLARE_LINK_MODE_MASK(tmp_lp) = {}; __ETHTOOL_DECLARE_LINK_MODE_MASK(common); - bool eee_active; int ret; - ret = genphy_c45_read_eee_adv(phydev, tmp_adv); - if (ret) - return ret; - ret = genphy_c45_read_eee_lpa(phydev, tmp_lp); if (ret) return ret; - linkmode_and(common, tmp_adv, tmp_lp); - if (!linkmode_empty(tmp_adv) && !linkmode_empty(common)) - eee_active = phy_check_valid(phydev->speed, phydev->duplex, - common); - else - eee_active = false; - - if (adv) - linkmode_copy(adv, tmp_adv); if (lp) linkmode_copy(lp, tmp_lp); - return eee_active; + linkmode_and(common, phydev->advertising_eee, tmp_lp); + if (linkmode_empty(common)) + return 0; + + return phy_check_valid(phydev->speed, phydev->duplex, common); } EXPORT_SYMBOL(genphy_c45_eee_is_active); @@ -1519,14 +1503,14 @@ int genphy_c45_ethtool_get_eee(struct phy_device *phydev, { int ret; - ret = genphy_c45_eee_is_active(phydev, data->advertised, - data->lp_advertised); + ret = genphy_c45_eee_is_active(phydev, data->lp_advertised); if (ret < 0) return ret; data->eee_active = phydev->eee_active; - linkmode_copy(data->supported, phydev->supported_eee); - + linkmode_andnot(data->supported, phydev->supported_eee, + phydev->eee_disabled_modes); + linkmode_copy(data->advertised, phydev->advertising_eee); return 0; } EXPORT_SYMBOL(genphy_c45_ethtool_get_eee); @@ -1559,7 +1543,9 @@ int genphy_c45_ethtool_set_eee(struct phy_device *phydev, phydev_warn(phydev, "At least some EEE link modes are not supported.\n"); return -EINVAL; } - linkmode_copy(phydev->advertising_eee, adv); + + linkmode_andnot(phydev->advertising_eee, adv, + phydev->eee_disabled_modes); } else if (linkmode_empty(phydev->advertising_eee)) { phy_advertise_eee_all(phydev); } diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 347ad1b64497..831b36839627 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -302,7 +302,7 @@ void phy_ethtool_ksettings_get(struct phy_device *phydev, cmd->base.port = PORT_BNC; else cmd->base.port = phydev->port; - cmd->base.transceiver = phy_is_internal(phydev) ? + cmd->base.transceiver = phydev->is_internal ? XCVR_INTERNAL : XCVR_EXTERNAL; cmd->base.phy_address = phydev->mdio.addr; cmd->base.autoneg = phydev->autoneg; @@ -520,12 +520,12 @@ int __phy_hwtstamp_set(struct phy_device *phydev, * @phydev: the phy_device struct * @jiffies: Run the state machine after these jiffies */ -void phy_queue_state_machine(struct phy_device *phydev, unsigned long jiffies) +static void phy_queue_state_machine(struct phy_device *phydev, + unsigned long jiffies) { mod_delayed_work(system_power_efficient_wq, &phydev->state_queue, jiffies); } -EXPORT_SYMBOL(phy_queue_state_machine); /** * phy_trigger_machine - Trigger the state machine to run now @@ -1031,7 +1031,7 @@ static int phy_check_link_status(struct phy_device *phydev) if (phydev->link && phydev->state != PHY_RUNNING) { phy_check_downshift(phydev); phydev->state = PHY_RUNNING; - err = genphy_c45_eee_is_active(phydev, NULL, NULL); + err = genphy_c45_eee_is_active(phydev, NULL); phydev->eee_active = err > 0; phydev->enable_tx_lpi = phydev->eee_cfg.tx_lpi_enabled && phydev->eee_active; @@ -1780,7 +1780,7 @@ int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable) if (!phydev->drv) return -EIO; - ret = genphy_c45_eee_is_active(phydev, NULL, NULL); + ret = genphy_c45_eee_is_active(phydev, NULL); if (ret < 0) return ret; if (!ret) diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 9b06ba92f2ed..7c4e1ad1864c 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -45,6 +45,17 @@ MODULE_DESCRIPTION("PHY library"); MODULE_AUTHOR("Andy Fleming"); MODULE_LICENSE("GPL"); +#define PHY_ANY_ID "MATCH ANY PHY" +#define PHY_ANY_UID 0xffffffff + +struct phy_fixup { + struct list_head list; + char bus_id[MII_BUS_ID_SIZE + 3]; + u32 phy_uid; + u32 phy_uid_mask; + int (*run)(struct phy_device *phydev); +}; + __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_features) __ro_after_init; EXPORT_SYMBOL_GPL(phy_basic_features); @@ -80,37 +91,28 @@ static const int phy_all_ports_features_array[7] = { ETHTOOL_LINK_MODE_Backplane_BIT, }; -const int phy_10_100_features_array[4] = { +static const int phy_10_100_features_array[4] = { ETHTOOL_LINK_MODE_10baseT_Half_BIT, ETHTOOL_LINK_MODE_10baseT_Full_BIT, ETHTOOL_LINK_MODE_100baseT_Half_BIT, ETHTOOL_LINK_MODE_100baseT_Full_BIT, }; -EXPORT_SYMBOL_GPL(phy_10_100_features_array); -const int phy_basic_t1_features_array[3] = { +static const int phy_basic_t1_features_array[3] = { ETHTOOL_LINK_MODE_TP_BIT, ETHTOOL_LINK_MODE_10baseT1L_Full_BIT, ETHTOOL_LINK_MODE_100baseT1_Full_BIT, }; -EXPORT_SYMBOL_GPL(phy_basic_t1_features_array); -const int phy_basic_t1s_p2mp_features_array[2] = { +static const int phy_basic_t1s_p2mp_features_array[2] = { ETHTOOL_LINK_MODE_TP_BIT, ETHTOOL_LINK_MODE_10baseT1S_P2MP_Half_BIT, }; -EXPORT_SYMBOL_GPL(phy_basic_t1s_p2mp_features_array); -const int phy_gbit_features_array[2] = { +static const int phy_gbit_features_array[2] = { ETHTOOL_LINK_MODE_1000baseT_Half_BIT, ETHTOOL_LINK_MODE_1000baseT_Full_BIT, }; -EXPORT_SYMBOL_GPL(phy_gbit_features_array); - -const int phy_10gbit_features_array[1] = { - ETHTOOL_LINK_MODE_10000baseT_Full_BIT, -}; -EXPORT_SYMBOL_GPL(phy_10gbit_features_array); static const int phy_eee_cap1_features_array[] = { ETHTOOL_LINK_MODE_100baseT_Full_BIT, @@ -185,9 +187,8 @@ static void features_init(void) linkmode_set_bit_array(phy_gbit_features_array, ARRAY_SIZE(phy_gbit_features_array), phy_10gbit_features); - linkmode_set_bit_array(phy_10gbit_features_array, - ARRAY_SIZE(phy_10gbit_features_array), - phy_10gbit_features); + linkmode_set_bit(ETHTOOL_LINK_MODE_10000baseT_Full_BIT, + phy_10gbit_features); linkmode_set_bit_array(phy_eee_cap1_features_array, ARRAY_SIZE(phy_eee_cap1_features_array), @@ -378,8 +379,8 @@ static SIMPLE_DEV_PM_OPS(mdio_bus_phy_pm_ops, mdio_bus_phy_suspend, * comparison * @run: The actual code to be run when a matching PHY is found */ -int phy_register_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask, - int (*run)(struct phy_device *)) +static int phy_register_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask, + int (*run)(struct phy_device *)) { struct phy_fixup *fixup = kzalloc(sizeof(*fixup), GFP_KERNEL); @@ -397,7 +398,6 @@ int phy_register_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask, return 0; } -EXPORT_SYMBOL(phy_register_fixup); /* Registers a fixup to be run on any PHY with the UID in phy_uid */ int phy_register_fixup_for_uid(u32 phy_uid, u32 phy_uid_mask, @@ -544,7 +544,7 @@ phy_interface_show(struct device *dev, struct device_attribute *attr, char *buf) struct phy_device *phydev = to_phy_device(dev); const char *mode = NULL; - if (phy_is_internal(phydev)) + if (phydev->is_internal) mode = "internal"; else mode = phy_modes(phydev->interface); @@ -3096,19 +3096,12 @@ void phy_get_pause(struct phy_device *phydev, bool *tx_pause, bool *rx_pause) EXPORT_SYMBOL(phy_get_pause); #if IS_ENABLED(CONFIG_OF_MDIO) -static int phy_get_int_delay_property(struct device *dev, const char *name) +static int phy_get_u32_property(struct device *dev, const char *name, u32 *val) { - s32 int_delay; - int ret; - - ret = device_property_read_u32(dev, name, &int_delay); - if (ret) - return ret; - - return int_delay; + return device_property_read_u32(dev, name, val); } #else -static int phy_get_int_delay_property(struct device *dev, const char *name) +static int phy_get_u32_property(struct device *dev, const char *name, u32 *val) { return -EINVAL; } @@ -3133,12 +3126,12 @@ static int phy_get_int_delay_property(struct device *dev, const char *name) s32 phy_get_internal_delay(struct phy_device *phydev, struct device *dev, const int *delay_values, int size, bool is_rx) { - s32 delay; - int i; + int i, ret; + u32 delay; if (is_rx) { - delay = phy_get_int_delay_property(dev, "rx-internal-delay-ps"); - if (delay < 0 && size == 0) { + ret = phy_get_u32_property(dev, "rx-internal-delay-ps", &delay); + if (ret < 0 && size == 0) { if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID || phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID) return 1; @@ -3147,8 +3140,8 @@ s32 phy_get_internal_delay(struct phy_device *phydev, struct device *dev, } } else { - delay = phy_get_int_delay_property(dev, "tx-internal-delay-ps"); - if (delay < 0 && size == 0) { + ret = phy_get_u32_property(dev, "tx-internal-delay-ps", &delay); + if (ret < 0 && size == 0) { if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID || phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID) return 1; @@ -3157,8 +3150,8 @@ s32 phy_get_internal_delay(struct phy_device *phydev, struct device *dev, } } - if (delay < 0) - return delay; + if (ret < 0) + return ret; if (size == 0) return delay; @@ -3193,6 +3186,30 @@ s32 phy_get_internal_delay(struct phy_device *phydev, struct device *dev, } EXPORT_SYMBOL(phy_get_internal_delay); +/** + * phy_get_tx_amplitude_gain - stores tx amplitude gain in @val + * @phydev: phy_device struct + * @dev: pointer to the devices device struct + * @linkmode: linkmode for which the tx amplitude gain should be retrieved + * @val: tx amplitude gain + * + * Returns: 0 on success, < 0 on failure + */ +int phy_get_tx_amplitude_gain(struct phy_device *phydev, struct device *dev, + enum ethtool_link_mode_bit_indices linkmode, + u32 *val) +{ + switch (linkmode) { + case ETHTOOL_LINK_MODE_100baseT_Full_BIT: + return phy_get_u32_property(dev, + "tx-amplitude-100base-tx-percent", + val); + default: + return -EINVAL; + } +} +EXPORT_SYMBOL_GPL(phy_get_tx_amplitude_gain); + static int phy_led_set_brightness(struct led_classdev *led_cdev, enum led_brightness value) { @@ -3563,22 +3580,21 @@ static int phy_probe(struct device *dev) if (err) goto out; - /* There is no "enabled" flag. If PHY is advertising, assume it is - * kind of enabled. - */ - phydev->eee_cfg.eee_enabled = !linkmode_empty(phydev->advertising_eee); + /* Get the EEE modes we want to prohibit. */ + of_set_phy_eee_broken(phydev); /* Some PHYs may advertise, by default, not support EEE modes. So, - * we need to clean them. + * we need to clean them. In addition remove all disabled EEE modes. */ - if (phydev->eee_cfg.eee_enabled) - linkmode_and(phydev->advertising_eee, phydev->supported_eee, - phydev->advertising_eee); + linkmode_and(phydev->advertising_eee, phydev->supported_eee, + phydev->advertising_eee); + linkmode_andnot(phydev->advertising_eee, phydev->advertising_eee, + phydev->eee_disabled_modes); - /* Get the EEE modes we want to prohibit. We will ask - * the PHY stop advertising these mode later on + /* There is no "enabled" flag. If PHY is advertising, assume it is + * kind of enabled. */ - of_set_phy_eee_broken(phydev); + phydev->eee_cfg.eee_enabled = !linkmode_empty(phydev->advertising_eee); /* Get master/slave strap overrides */ of_set_phy_timing_role(phydev); diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 74693307dfbf..a3b186ab3854 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -1073,6 +1073,18 @@ static void phylink_pcs_link_up(struct phylink_pcs *pcs, unsigned int neg_mode, pcs->ops->pcs_link_up(pcs, neg_mode, interface, speed, duplex); } +static void phylink_pcs_disable_eee(struct phylink_pcs *pcs) +{ + if (pcs && pcs->ops->pcs_disable_eee) + pcs->ops->pcs_disable_eee(pcs); +} + +static void phylink_pcs_enable_eee(struct phylink_pcs *pcs) +{ + if (pcs && pcs->ops->pcs_enable_eee) + pcs->ops->pcs_enable_eee(pcs); +} + /* Query inband for a specific interface mode, asking the MAC for the * PCS which will be used to handle the interface mode. */ @@ -1353,7 +1365,6 @@ static void phylink_major_config(struct phylink *pl, bool restart, struct phylink_pcs *pcs = NULL; bool pcs_changed = false; unsigned int rate_kbd; - unsigned int neg_mode; int err; phylink_dbg(pl, "major config, requested %s/%s\n", @@ -1416,11 +1427,7 @@ static void phylink_major_config(struct phylink *pl, bool restart, if (pl->pcs_state == PCS_STATE_STARTING || pcs_changed) phylink_pcs_enable(pl->pcs); - neg_mode = pl->act_link_an_mode; - if (pl->pcs && pl->pcs->neg_mode) - neg_mode = pl->pcs_neg_mode; - - err = phylink_pcs_config(pl->pcs, neg_mode, state, + err = phylink_pcs_config(pl->pcs, pl->pcs_neg_mode, state, !!(pl->link_config.pause & MLO_PAUSE_AN)); if (err < 0) phylink_err(pl, "pcs_config failed: %pe\n", @@ -1463,7 +1470,6 @@ static void phylink_major_config(struct phylink *pl, bool restart, */ static int phylink_change_inband_advert(struct phylink *pl) { - unsigned int neg_mode; int ret; if (test_bit(PHYLINK_DISABLE_STOPPED, &pl->phylink_disable_state)) @@ -1479,15 +1485,11 @@ static int phylink_change_inband_advert(struct phylink *pl) phylink_pcs_neg_mode(pl, pl->pcs, pl->link_config.interface, pl->link_config.advertising); - neg_mode = pl->act_link_an_mode; - if (pl->pcs->neg_mode) - neg_mode = pl->pcs_neg_mode; - /* Modern PCS-based method; update the advert at the PCS, and * restart negotiation if the pcs_config() helper indicates that * the programmed advertisement has changed. */ - ret = phylink_pcs_config(pl->pcs, neg_mode, &pl->link_config, + ret = phylink_pcs_config(pl->pcs, pl->pcs_neg_mode, &pl->link_config, !!(pl->link_config.pause & MLO_PAUSE_AN)); if (ret < 0) return ret; @@ -1511,13 +1513,7 @@ static void phylink_mac_pcs_get_state(struct phylink *pl, 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); - + autoneg = pl->pcs_neg_mode == PHYLINK_PCS_NEG_INBAND_ENABLED; if (autoneg) { state->speed = SPEED_UNKNOWN; state->duplex = DUPLEX_UNKNOWN; @@ -1528,6 +1524,7 @@ static void phylink_mac_pcs_get_state(struct phylink *pl, state->pause = pl->link_config.pause; } + pcs = pl->pcs; if (pcs) pcs->ops->pcs_get_state(pcs, pl->pcs_neg_mode, state); else @@ -1601,6 +1598,8 @@ static void phylink_deactivate_lpi(struct phylink *pl) phylink_dbg(pl, "disabling LPI\n"); pl->mac_ops->mac_disable_tx_lpi(pl->config); + + phylink_pcs_disable_eee(pl->pcs); } } @@ -1617,20 +1616,24 @@ static void phylink_activate_lpi(struct phylink *pl) phylink_dbg(pl, "LPI timer %uus, tx clock stop %u\n", pl->mac_tx_lpi_timer, pl->mac_tx_clk_stop); + phylink_pcs_enable_eee(pl->pcs); + 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 + if (err) { + phylink_pcs_disable_eee(pl->pcs); phylink_err(pl, "%ps() failed: %pe\n", pl->mac_ops->mac_enable_tx_lpi, ERR_PTR(err)); + return; + } + + pl->mac_enable_tx_lpi = true; } static void phylink_link_up(struct phylink *pl, struct phylink_link_state link_state) { struct net_device *ndev = pl->netdev; - unsigned int neg_mode; int speed, duplex; bool rx_pause; @@ -1661,11 +1664,7 @@ static void phylink_link_up(struct phylink *pl, pl->cur_interface = link_state.interface; - neg_mode = pl->act_link_an_mode; - if (pl->pcs && pl->pcs->neg_mode) - neg_mode = pl->pcs_neg_mode; - - phylink_pcs_link_up(pl->pcs, neg_mode, pl->cur_interface, speed, + phylink_pcs_link_up(pl->pcs, pl->pcs_neg_mode, pl->cur_interface, speed, duplex); pl->mac_ops->mac_link_up(pl->config, pl->phydev, pl->act_link_an_mode, diff --git a/drivers/net/phy/qt2025.rs b/drivers/net/phy/qt2025.rs index 1ab065798175..7e754d5d7154 100644 --- a/drivers/net/phy/qt2025.rs +++ b/drivers/net/phy/qt2025.rs @@ -41,7 +41,7 @@ impl Driver for PhyQT2025 { fn probe(dev: &mut phy::Device) -> Result<()> { // Check the hardware revision code. - // Only 0x3b works with this driver and firmware. + // Only 0xb3 works with this driver and firmware. let hw_rev = dev.read(C45::new(Mmd::PMAPMD, 0xd001))?; if (hw_rev >> 8) != 0xb3 { return Err(code::ENODEV); diff --git a/drivers/net/phy/realtek/realtek_main.c b/drivers/net/phy/realtek/realtek_main.c index 210fefac44d4..7a0b19d66aca 100644 --- a/drivers/net/phy/realtek/realtek_main.c +++ b/drivers/net/phy/realtek/realtek_main.c @@ -79,9 +79,7 @@ /* RTL822X_VND2_XXXXX registers are only accessible when phydev->is_c45 * is set, they cannot be accessed by C45-over-C22. */ -#define RTL822X_VND2_GBCR 0xa412 - -#define RTL822X_VND2_GANLPAR 0xa414 +#define RTL822X_VND2_C22_REG(reg) (0xa400 + 2 * (reg)) #define RTL8366RB_POWER_SAVE 0x15 #define RTL8366RB_POWER_SAVE_ON BIT(12) @@ -96,6 +94,16 @@ #define RTL_VND2_PHYSR_MASTER BIT(11) #define RTL_VND2_PHYSR_SPEED_MASK (RTL_VND2_PHYSR_SPEEDL | RTL_VND2_PHYSR_SPEEDH) +#define RTL_MDIO_PCS_EEE_ABLE 0xa5c4 +#define RTL_MDIO_AN_EEE_ADV 0xa5d0 +#define RTL_MDIO_AN_EEE_LPABLE 0xa5d2 +#define RTL_MDIO_AN_10GBT_CTRL 0xa5d4 +#define RTL_MDIO_AN_10GBT_STAT 0xa5d6 +#define RTL_MDIO_PMA_SPEED 0xa616 +#define RTL_MDIO_AN_EEE_LPABLE2 0xa6d0 +#define RTL_MDIO_AN_EEE_ADV2 0xa6d4 +#define RTL_MDIO_PCS_EEE_ABLE2 0xa6ec + #define RTL_GENERIC_PHYID 0x001cc800 #define RTL_8211FVD_PHYID 0x001cc878 #define RTL_8221B 0x001cc840 @@ -735,29 +743,31 @@ static int rtlgen_read_status(struct phy_device *phydev) return 0; } +static int rtlgen_read_vend2(struct phy_device *phydev, int regnum) +{ + return __mdiobus_c45_read(phydev->mdio.bus, 0, MDIO_MMD_VEND2, regnum); +} + +static int rtlgen_write_vend2(struct phy_device *phydev, int regnum, u16 val) +{ + return __mdiobus_c45_write(phydev->mdio.bus, 0, MDIO_MMD_VEND2, regnum, + val); +} + static int rtlgen_read_mmd(struct phy_device *phydev, int devnum, u16 regnum) { int ret; - 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); - } else if (devnum == MDIO_MMD_AN && regnum == MDIO_AN_EEE_ADV) { - rtl821x_write_page(phydev, 0xa5d); - ret = __phy_read(phydev, 0x10); - rtl821x_write_page(phydev, 0); - } else if (devnum == MDIO_MMD_AN && regnum == MDIO_AN_EEE_LPABLE) { - rtl821x_write_page(phydev, 0xa5d); - ret = __phy_read(phydev, 0x11); - rtl821x_write_page(phydev, 0); - } else { + if (devnum == MDIO_MMD_VEND2) + ret = rtlgen_read_vend2(phydev, regnum); + else if (devnum == MDIO_MMD_PCS && regnum == MDIO_PCS_EEE_ABLE) + ret = rtlgen_read_vend2(phydev, RTL_MDIO_PCS_EEE_ABLE); + else if (devnum == MDIO_MMD_AN && regnum == MDIO_AN_EEE_ADV) + ret = rtlgen_read_vend2(phydev, RTL_MDIO_AN_EEE_ADV); + else if (devnum == MDIO_MMD_AN && regnum == MDIO_AN_EEE_LPABLE) + ret = rtlgen_read_vend2(phydev, RTL_MDIO_AN_EEE_LPABLE); + else ret = -EOPNOTSUPP; - } return ret; } @@ -767,17 +777,12 @@ static int rtlgen_write_mmd(struct phy_device *phydev, int devnum, u16 regnum, { int ret; - 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); - } else { + if (devnum == MDIO_MMD_VEND2) + ret = rtlgen_write_vend2(phydev, regnum, val); + else if (devnum == MDIO_MMD_AN && regnum == MDIO_AN_EEE_ADV) + ret = rtlgen_write_vend2(phydev, regnum, RTL_MDIO_AN_EEE_ADV); + else ret = -EOPNOTSUPP; - } return ret; } @@ -789,19 +794,12 @@ static int rtl822x_read_mmd(struct phy_device *phydev, int devnum, u16 regnum) if (ret != -EOPNOTSUPP) return ret; - if (devnum == MDIO_MMD_PCS && regnum == MDIO_PCS_EEE_ABLE2) { - rtl821x_write_page(phydev, 0xa6e); - ret = __phy_read(phydev, 0x16); - rtl821x_write_page(phydev, 0); - } else if (devnum == MDIO_MMD_AN && regnum == MDIO_AN_EEE_ADV2) { - rtl821x_write_page(phydev, 0xa6d); - ret = __phy_read(phydev, 0x12); - rtl821x_write_page(phydev, 0); - } else if (devnum == MDIO_MMD_AN && regnum == MDIO_AN_EEE_LPABLE2) { - rtl821x_write_page(phydev, 0xa6d); - ret = __phy_read(phydev, 0x10); - rtl821x_write_page(phydev, 0); - } + if (devnum == MDIO_MMD_PCS && regnum == MDIO_PCS_EEE_ABLE2) + ret = rtlgen_read_vend2(phydev, RTL_MDIO_PCS_EEE_ABLE2); + else if (devnum == MDIO_MMD_AN && regnum == MDIO_AN_EEE_ADV2) + ret = rtlgen_read_vend2(phydev, RTL_MDIO_AN_EEE_ADV2); + else if (devnum == MDIO_MMD_AN && regnum == MDIO_AN_EEE_LPABLE2) + ret = rtlgen_read_vend2(phydev, RTL_MDIO_AN_EEE_LPABLE2); return ret; } @@ -814,11 +812,8 @@ static int rtl822x_write_mmd(struct phy_device *phydev, int devnum, u16 regnum, if (ret != -EOPNOTSUPP) return ret; - if (devnum == MDIO_MMD_AN && regnum == MDIO_AN_EEE_ADV2) { - rtl821x_write_page(phydev, 0xa6d); - ret = __phy_write(phydev, 0x12, val); - rtl821x_write_page(phydev, 0); - } + if (devnum == MDIO_MMD_AN && regnum == MDIO_AN_EEE_ADV2) + ret = rtlgen_write_vend2(phydev, RTL_MDIO_AN_EEE_ADV2, val); return ret; } @@ -914,7 +909,7 @@ static int rtl822x_get_features(struct phy_device *phydev) { int val; - val = phy_read_paged(phydev, 0xa61, 0x13); + val = phy_read_mmd(phydev, MDIO_MMD_VEND2, RTL_MDIO_PMA_SPEED); if (val < 0) return val; @@ -935,10 +930,10 @@ static int rtl822x_config_aneg(struct phy_device *phydev) if (phydev->autoneg == AUTONEG_ENABLE) { u16 adv = linkmode_adv_to_mii_10gbt_adv_t(phydev->advertising); - ret = phy_modify_paged_changed(phydev, 0xa5d, 0x12, - MDIO_AN_10GBT_CTRL_ADV2_5G | - MDIO_AN_10GBT_CTRL_ADV5G, - adv); + ret = phy_modify_mmd_changed(phydev, MDIO_MMD_VEND2, + RTL_MDIO_AN_10GBT_CTRL, + MDIO_AN_10GBT_CTRL_ADV2_5G | + MDIO_AN_10GBT_CTRL_ADV5G, adv); if (ret < 0) return ret; } @@ -982,7 +977,7 @@ static int rtl822x_read_status(struct phy_device *phydev) !phydev->autoneg_complete) return 0; - lpadv = phy_read_paged(phydev, 0xa5d, 0x13); + lpadv = phy_read_mmd(phydev, MDIO_MMD_VEND2, RTL_MDIO_AN_10GBT_STAT); if (lpadv < 0) return lpadv; @@ -1029,7 +1024,8 @@ static int rtl822x_c45_config_aneg(struct phy_device *phydev) val = linkmode_adv_to_mii_ctrl1000_t(phydev->advertising); /* Vendor register as C45 has no standardized support for 1000BaseT */ - ret = phy_modify_mmd_changed(phydev, MDIO_MMD_VEND2, RTL822X_VND2_GBCR, + ret = phy_modify_mmd_changed(phydev, MDIO_MMD_VEND2, + RTL822X_VND2_C22_REG(MII_CTRL1000), ADVERTISE_1000FULL, val); if (ret < 0) return ret; @@ -1046,7 +1042,7 @@ static int rtl822x_c45_read_status(struct phy_device *phydev) /* Vendor register as C45 has no standardized support for 1000BaseT */ if (phydev->autoneg == AUTONEG_ENABLE && genphy_c45_aneg_done(phydev)) { val = phy_read_mmd(phydev, MDIO_MMD_VEND2, - RTL822X_VND2_GANLPAR); + RTL822X_VND2_C22_REG(MII_STAT1000)); if (val < 0) return val; } else { diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index 7dbcbf0a4ee2..9369f5297769 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -515,6 +515,8 @@ static const struct sfp_quirk sfp_quirks[] = { SFP_QUIRK_F("OEM", "SFP-10G-T", sfp_fixup_rollball_cc), SFP_QUIRK_M("OEM", "SFP-2.5G-T", sfp_quirk_oem_2_5g), + SFP_QUIRK_M("OEM", "SFP-2.5G-BX10-D", sfp_quirk_2500basex), + SFP_QUIRK_M("OEM", "SFP-2.5G-BX10-U", sfp_quirk_2500basex), SFP_QUIRK_F("OEM", "RTSFP-10", sfp_fixup_rollball_cc), SFP_QUIRK_F("OEM", "RTSFP-10G", sfp_fixup_rollball_cc), SFP_QUIRK_F("Turris", "RTSFP-2.5G", sfp_fixup_rollball), diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 4583e15ad03a..6220866258fc 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -1303,10 +1303,13 @@ static int ppp_nl_validate(struct nlattr *tb[], struct nlattr *data[], return 0; } -static int ppp_nl_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +static int ppp_nl_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { + struct net *link_net = rtnl_newlink_link_net(params); + struct nlattr **data = params->data; + struct nlattr **tb = params->tb; struct ppp_config conf = { .unit = -1, .ifname_is_set = true, @@ -1343,7 +1346,7 @@ static int ppp_nl_newlink(struct net *src_net, struct net_device *dev, if (!tb[IFLA_IFNAME] || !nla_len(tb[IFLA_IFNAME]) || !*(char *)nla_data(tb[IFLA_IFNAME])) conf.ifname_is_set = false; - err = ppp_dev_configure(src_net, dev, &conf); + err = ppp_dev_configure(link_net, dev, &conf); out_unlock: mutex_unlock(&ppp_mutex); diff --git a/drivers/net/pse-pd/pd692x0.c b/drivers/net/pse-pd/pd692x0.c index fc9e23927b3b..7d60a714ca53 100644 --- a/drivers/net/pse-pd/pd692x0.c +++ b/drivers/net/pse-pd/pd692x0.c @@ -1047,7 +1047,7 @@ static int pd692x0_pi_get_pw_limit(struct pse_controller_dev *pcdev, if (ret < 0) return ret; - return pd692x0_pi_get_pw_from_table(buf.data[2], buf.data[3]); + return pd692x0_pi_get_pw_from_table(buf.data[0], buf.data[1]); } static int pd692x0_pi_set_pw_limit(struct pse_controller_dev *pcdev, diff --git a/drivers/net/team/team_core.c b/drivers/net/team/team_core.c index f4019815f473..78edb8186b6d 100644 --- a/drivers/net/team/team_core.c +++ b/drivers/net/team/team_core.c @@ -2218,10 +2218,12 @@ static void team_setup(struct net_device *dev) dev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; } -static int team_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +static int team_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { + struct nlattr **tb = params->tb; + if (tb[IFLA_ADDRESS] == NULL) eth_hw_addr_random(dev); diff --git a/drivers/net/tun_vnet.h b/drivers/net/tun_vnet.h index fd7411c4447f..58b9ac7a5fc4 100644 --- a/drivers/net/tun_vnet.h +++ b/drivers/net/tun_vnet.h @@ -143,7 +143,8 @@ static inline int tun_vnet_hdr_put(int sz, struct iov_iter *iter, if (unlikely(copy_to_iter(hdr, sizeof(*hdr), iter) != sizeof(*hdr))) return -EFAULT; - iov_iter_advance(iter, sz - sizeof(*hdr)); + if (iov_iter_zero(sz - sizeof(*hdr), iter) != sz - sizeof(*hdr)) + return -EFAULT; return 0; } diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 01251868a9c2..ba3ae2d8092f 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -1765,10 +1765,13 @@ static int veth_init_queues(struct net_device *dev, struct nlattr *tb[]) return 0; } -static int veth_newlink(struct net *peer_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +static int veth_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { + struct net *peer_net = rtnl_newlink_peer_net(params); + struct nlattr **data = params->data; + struct nlattr **tb = params->tb; int err; struct net_device *peer; struct veth_priv *priv; diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 5f21ce1013c4..849c3ced2690 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -1675,11 +1675,12 @@ static void vrf_dellink(struct net_device *dev, struct list_head *head) unregister_netdevice_queue(dev, head); } -static int vrf_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +static int vrf_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct net_vrf *vrf = netdev_priv(dev); + struct nlattr **data = params->data; struct netns_vrf *nn_vrf; bool *add_fib_rules; struct net *net; diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index ac5bc78edfd7..227d7f5a302a 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -3936,7 +3936,7 @@ static void vxlan_config_apply(struct net_device *dev, } static int vxlan_dev_configure(struct net *src_net, struct net_device *dev, - struct vxlan_config *conf, bool changelink, + struct vxlan_config *conf, struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = netdev_priv(dev); @@ -3947,7 +3947,7 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev, if (ret) return ret; - vxlan_config_apply(dev, conf, lowerdev, src_net, changelink); + vxlan_config_apply(dev, conf, lowerdev, src_net, false); return 0; } @@ -3965,7 +3965,7 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev, int err; dst = &vxlan->default_dst; - err = vxlan_dev_configure(net, dev, conf, false, extack); + err = vxlan_dev_configure(net, dev, conf, extack); if (err) return err; @@ -4400,10 +4400,13 @@ static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[], return 0; } -static int vxlan_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +static int vxlan_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { + struct net *link_net = rtnl_newlink_link_net(params); + struct nlattr **data = params->data; + struct nlattr **tb = params->tb; struct vxlan_config conf; int err; @@ -4411,7 +4414,7 @@ static int vxlan_newlink(struct net *src_net, struct net_device *dev, if (err) return err; - return __vxlan_dev_create(src_net, dev, &conf, extack); + return __vxlan_dev_create(link_net, dev, &conf, extack); } static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[], @@ -4419,6 +4422,7 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[], struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = netdev_priv(dev); + bool rem_ip_changed, change_igmp; struct net_device *lowerdev; struct vxlan_config conf; struct vxlan_rdst *dst; @@ -4442,8 +4446,13 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[], if (err) return err; + rem_ip_changed = !vxlan_addr_equal(&conf.remote_ip, &dst->remote_ip); + change_igmp = vxlan->dev->flags & IFF_UP && + (rem_ip_changed || + dst->remote_ifindex != conf.remote_ifindex); + /* handle default dst entry */ - if (!vxlan_addr_equal(&conf.remote_ip, &dst->remote_ip)) { + if (rem_ip_changed) { u32 hash_index = fdb_head_index(vxlan, all_zeros_mac, conf.vni); spin_lock_bh(&vxlan->hash_lock[hash_index]); @@ -4487,6 +4496,9 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[], } } + if (change_igmp && vxlan_addr_multicast(&dst->remote_ip)) + err = vxlan_multicast_leave(vxlan); + if (conf.age_interval != vxlan->cfg.age_interval) mod_timer(&vxlan->age_timer, jiffies); @@ -4494,7 +4506,12 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[], if (lowerdev && lowerdev != dst->remote_dev) dst->remote_dev = lowerdev; vxlan_config_apply(dev, &conf, lowerdev, vxlan->net, true); - return 0; + + if (!err && change_igmp && + vxlan_addr_multicast(&dst->remote_ip)) + err = vxlan_multicast_join(vxlan); + + return err; } static void vxlan_dellink(struct net_device *dev, struct list_head *head) diff --git a/drivers/net/wireguard/device.c b/drivers/net/wireguard/device.c index 6cf173a008e7..c496d35b266d 100644 --- a/drivers/net/wireguard/device.c +++ b/drivers/net/wireguard/device.c @@ -307,14 +307,15 @@ static void wg_setup(struct net_device *dev) wg->dev = dev; } -static int wg_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +static int wg_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { + struct net *link_net = rtnl_newlink_link_net(params); struct wg_device *wg = netdev_priv(dev); int ret = -ENOMEM; - rcu_assign_pointer(wg->creating_net, src_net); + rcu_assign_pointer(wg->creating_net, link_net); init_rwsem(&wg->static_identity.lock); mutex_init(&wg->socket_update_lock); mutex_init(&wg->device_update_lock); diff --git a/drivers/net/wireless/virtual/virt_wifi.c b/drivers/net/wireless/virtual/virt_wifi.c index 4ee374080466..f9d11a023313 100644 --- a/drivers/net/wireless/virtual/virt_wifi.c +++ b/drivers/net/wireless/virtual/virt_wifi.c @@ -519,11 +519,13 @@ static rx_handler_result_t virt_wifi_rx_handler(struct sk_buff **pskb) } /* Called with rtnl lock held. */ -static int virt_wifi_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +static int virt_wifi_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct virt_wifi_netdev_priv *priv = netdev_priv(dev); + struct net *link_net = rtnl_newlink_link_net(params); + struct nlattr **tb = params->tb; int err; if (!tb[IFLA_LINK]) @@ -532,7 +534,7 @@ static int virt_wifi_newlink(struct net *src_net, struct net_device *dev, netif_carrier_off(dev); priv->upperdev = dev; - priv->lowerdev = __dev_get_by_index(src_net, + priv->lowerdev = __dev_get_by_index(link_net, nla_get_u32(tb[IFLA_LINK])); if (!priv->lowerdev) diff --git a/drivers/net/wwan/mhi_wwan_mbim.c b/drivers/net/wwan/mhi_wwan_mbim.c index d5a9360323d2..8755c5e6a65b 100644 --- a/drivers/net/wwan/mhi_wwan_mbim.c +++ b/drivers/net/wwan/mhi_wwan_mbim.c @@ -220,7 +220,7 @@ static int mbim_rx_verify_nth16(struct mhi_mbim_context *mbim, struct sk_buff *s if (mbim->rx_seq + 1 != le16_to_cpu(nth16->wSequence) && (mbim->rx_seq || le16_to_cpu(nth16->wSequence)) && !(mbim->rx_seq == 0xffff && !le16_to_cpu(nth16->wSequence))) { - net_err_ratelimited("sequence number glitch prev=%d curr=%d\n", + net_dbg_ratelimited("sequence number glitch prev=%d curr=%d\n", mbim->rx_seq, le16_to_cpu(nth16->wSequence)); } mbim->rx_seq = le16_to_cpu(nth16->wSequence); diff --git a/drivers/net/wwan/wwan_core.c b/drivers/net/wwan/wwan_core.c index a51e2755991a..63a47d420bc5 100644 --- a/drivers/net/wwan/wwan_core.c +++ b/drivers/net/wwan/wwan_core.c @@ -967,15 +967,18 @@ out: return dev; } -static int wwan_rtnl_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +static int wwan_rtnl_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct wwan_device *wwandev = wwan_dev_get_by_parent(dev->dev.parent); - u32 link_id = nla_get_u32(data[IFLA_WWAN_LINK_ID]); struct wwan_netdev_priv *priv = netdev_priv(dev); + struct nlattr **data = params->data; + u32 link_id; int ret; + link_id = nla_get_u32(data[IFLA_WWAN_LINK_ID]); + if (IS_ERR(wwandev)) return PTR_ERR(wwandev); @@ -1061,6 +1064,11 @@ static void wwan_create_default_link(struct wwan_device *wwandev, { struct nlattr *tb[IFLA_MAX + 1], *linkinfo[IFLA_INFO_MAX + 1]; struct nlattr *data[IFLA_WWAN_MAX + 1]; + struct rtnl_newlink_params params = { + .src_net = &init_net, + .tb = tb, + .data = data, + }; struct net_device *dev; struct nlmsghdr *nlh; struct sk_buff *msg; @@ -1105,7 +1113,7 @@ static void wwan_create_default_link(struct wwan_device *wwandev, if (WARN_ON(IS_ERR(dev))) goto unlock; - if (WARN_ON(wwan_rtnl_newlink(&init_net, dev, tb, data, NULL))) { + if (WARN_ON(wwan_rtnl_newlink(dev, ¶ms, NULL))) { free_netdev(dev); goto unlock; } diff --git a/drivers/of/address.c b/drivers/of/address.c index 125833e5ce52..d177a2b9edaf 100644 --- a/drivers/of/address.c +++ b/drivers/of/address.c @@ -16,6 +16,8 @@ #include <linux/string.h> #include <linux/dma-direct.h> /* for bus_dma_region */ +#include <kunit/visibility.h> + /* Uncomment me to enable of_dump_addr() debugging output */ // #define DEBUG @@ -183,7 +185,7 @@ static u64 of_bus_pci_map(__be32 *addr, const __be32 *range, int na, int ns, #endif /* CONFIG_PCI */ -static int __of_address_resource_bounds(struct resource *r, u64 start, u64 size) +VISIBLE_IF_KUNIT int __of_address_resource_bounds(struct resource *r, u64 start, u64 size) { if (overflows_type(start, r->start)) return -EOVERFLOW; @@ -197,6 +199,7 @@ static int __of_address_resource_bounds(struct resource *r, u64 start, u64 size) return 0; } +EXPORT_SYMBOL_IF_KUNIT(__of_address_resource_bounds); /* * of_pci_range_to_resource - Create a resource from an of_pci_range diff --git a/drivers/of/of_private.h b/drivers/of/of_private.h index f3e1193c8ded..1bdc7ceef3c5 100644 --- a/drivers/of/of_private.h +++ b/drivers/of/of_private.h @@ -208,4 +208,8 @@ static void __maybe_unused of_dump_addr(const char *s, const __be32 *addr, int n static void __maybe_unused of_dump_addr(const char *s, const __be32 *addr, int na) { } #endif +#if IS_ENABLED(CONFIG_KUNIT) +int __of_address_resource_bounds(struct resource *r, u64 start, u64 size); +#endif + #endif /* _LINUX_OF_PRIVATE_H */ diff --git a/drivers/of/of_test.c b/drivers/of/of_test.c index b0557ded838f..8bba5a72c9c7 100644 --- a/drivers/of/of_test.c +++ b/drivers/of/of_test.c @@ -2,6 +2,7 @@ /* * KUnit tests for OF APIs */ +#include <linux/ioport.h> #include <linux/module.h> #include <linux/of.h> @@ -54,8 +55,124 @@ static struct kunit_suite of_dtb_suite = { .init = of_dtb_test_init, }; +struct of_address_resource_bounds_case { + u64 start; + u64 size; + int ret; + + u64 res_start; + u64 res_end; +}; + +static void of_address_resource_bounds_case_desc(const struct of_address_resource_bounds_case *p, + char *name) +{ + snprintf(name, KUNIT_PARAM_DESC_SIZE, "start=0x%016llx,size=0x%016llx", p->start, p->size); +} + +static const struct of_address_resource_bounds_case of_address_resource_bounds_cases[] = { + { + .start = 0, + .size = 0, + .ret = 0, + .res_start = 0, + .res_end = -1, + }, + { + .start = 0, + .size = 0x1000, + .ret = 0, + .res_start = 0, + .res_end = 0xfff, + }, + { + .start = 0x1000, + .size = 0, + .ret = 0, + .res_start = 0x1000, + .res_end = 0xfff, + }, + { + .start = 0x1000, + .size = 0x1000, + .ret = 0, + .res_start = 0x1000, + .res_end = 0x1fff, + }, + { + .start = 1, + .size = RESOURCE_SIZE_MAX, + .ret = 0, + .res_start = 1, + .res_end = RESOURCE_SIZE_MAX, + }, + { + .start = RESOURCE_SIZE_MAX, + .size = 1, + .ret = 0, + .res_start = RESOURCE_SIZE_MAX, + .res_end = RESOURCE_SIZE_MAX, + }, + { + .start = 2, + .size = RESOURCE_SIZE_MAX, + .ret = -EOVERFLOW, + }, + { + .start = RESOURCE_SIZE_MAX, + .size = 2, + .ret = -EOVERFLOW, + }, + { + .start = ULL(0x100000000), + .size = 1, + .ret = sizeof(resource_size_t) > sizeof(u32) ? 0 : -EOVERFLOW, + .res_start = ULL(0x100000000), + .res_end = ULL(0x100000000), + }, + { + .start = 0x1000, + .size = 0xffffffff, + .ret = sizeof(resource_size_t) > sizeof(u32) ? 0 : -EOVERFLOW, + .res_start = 0x1000, + .res_end = ULL(0x100000ffe), + }, +}; + +KUNIT_ARRAY_PARAM(of_address_resource_bounds, + of_address_resource_bounds_cases, of_address_resource_bounds_case_desc); + +static void of_address_resource_bounds(struct kunit *test) +{ + const struct of_address_resource_bounds_case *param = test->param_value; + struct resource r; /* Intentionally uninitialized */ + int ret; + + if (!IS_ENABLED(CONFIG_OF_ADDRESS)) + kunit_skip(test, "CONFIG_OF_ADDRESS not enabled\n"); + + ret = __of_address_resource_bounds(&r, param->start, param->size); + KUNIT_EXPECT_EQ(test, param->ret, ret); + if (ret == 0) { + KUNIT_EXPECT_EQ(test, (resource_size_t)param->res_start, r.start); + KUNIT_EXPECT_EQ(test, (resource_size_t)param->res_end, r.end); + KUNIT_EXPECT_EQ(test, param->size, resource_size(&r)); + } +} + +static struct kunit_case of_address_test_cases[] = { + KUNIT_CASE_PARAM(of_address_resource_bounds, of_address_resource_bounds_gen_params), + {} +}; + +static struct kunit_suite of_address_suite = { + .name = "of_address", + .test_cases = of_address_test_cases, +}; + kunit_test_suites( - &of_dtb_suite, + &of_dtb_suite, &of_address_suite, ); MODULE_DESCRIPTION("KUnit tests for OF APIs"); +MODULE_IMPORT_NS("EXPORTED_FOR_KUNIT_TESTING"); MODULE_LICENSE("GPL"); diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index b6536ed599c3..246744d8d268 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -339,13 +339,14 @@ out: return (res->flags & IORESOURCE_MEM_64) ? 1 : 0; } -static void pci_read_bases(struct pci_dev *dev, unsigned int howmany, int rom) +static __always_inline void pci_read_bases(struct pci_dev *dev, + unsigned int howmany, int rom) { u32 rombar, stdbars[PCI_STD_NUM_BARS]; unsigned int pos, reg; u16 orig_cmd; - BUILD_BUG_ON(howmany > PCI_STD_NUM_BARS); + BUILD_BUG_ON(statically_true(howmany > PCI_STD_NUM_BARS)); if (dev->non_compliant_bars) return; diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index b84ff7bade82..82b21e34c545 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -5522,7 +5522,7 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x443, quirk_intel_qat_vf_cap); * AMD Matisse USB 3.0 Host Controller 0x149c * Intel 82579LM Gigabit Ethernet Controller 0x1502 * Intel 82579V Gigabit Ethernet Controller 0x1503 - * + * Mediatek MT7922 802.11ax PCI Express Wireless Network Adapter */ static void quirk_no_flr(struct pci_dev *dev) { @@ -5534,6 +5534,7 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x149c, quirk_no_flr); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x7901, quirk_no_flr); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x1502, quirk_no_flr); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x1503, quirk_no_flr); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_MEDIATEK, 0x0616, quirk_no_flr); /* FLR may cause the SolidRun SNET DPU (rev 0x1) to hang */ static void quirk_no_flr_snet(struct pci_dev *dev) diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 89578b91c468..4ddf0efead68 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -5774,43 +5774,36 @@ regulator_register(struct device *dev, goto clean; } - if (config->init_data) { - /* - * Providing of_match means the framework is expected to parse - * DT to get the init_data. This would conflict with provided - * init_data, if set. Warn if it happens. - */ - if (regulator_desc->of_match) - dev_warn(dev, "Using provided init data - OF match ignored\n"); + /* + * DT may override the config->init_data provided if the platform + * needs to do so. If so, config->init_data is completely ignored. + */ + init_data = regulator_of_get_init_data(dev, regulator_desc, config, + &rdev->dev.of_node); + /* + * Sometimes not all resources are probed already so we need to take + * that into account. This happens most the time if the ena_gpiod comes + * from a gpio extender or something else. + */ + if (PTR_ERR(init_data) == -EPROBE_DEFER) { + ret = -EPROBE_DEFER; + goto clean; + } + + /* + * We need to keep track of any GPIO descriptor coming from the + * device tree until we have handled it over to the core. If the + * config that was passed in to this function DOES NOT contain + * a descriptor, and the config after this call DOES contain + * a descriptor, we definitely got one from parsing the device + * tree. + */ + if (!cfg->ena_gpiod && config->ena_gpiod) + dangling_of_gpiod = true; + if (!init_data) { init_data = config->init_data; rdev->dev.of_node = of_node_get(config->of_node); - - } else { - init_data = regulator_of_get_init_data(dev, regulator_desc, - config, - &rdev->dev.of_node); - - /* - * Sometimes not all resources are probed already so we need to - * take that into account. This happens most the time if the - * ena_gpiod comes from a gpio extender or something else. - */ - if (PTR_ERR(init_data) == -EPROBE_DEFER) { - ret = -EPROBE_DEFER; - goto clean; - } - - /* - * We need to keep track of any GPIO descriptor coming from the - * device tree until we have handled it over to the core. If the - * config that was passed in to this function DOES NOT contain a - * descriptor, and the config after this call DOES contain a - * descriptor, we definitely got one from parsing the device - * tree. - */ - if (!cfg->ena_gpiod && config->ena_gpiod) - dangling_of_gpiod = true; } ww_mutex_init(&rdev->mutex, ®ulator_ww_class); diff --git a/drivers/s390/cio/chp.c b/drivers/s390/cio/chp.c index 4a0b3f19bd8e..4f01b1929240 100644 --- a/drivers/s390/cio/chp.c +++ b/drivers/s390/cio/chp.c @@ -695,7 +695,8 @@ static int info_update(void) if (time_after(jiffies, chp_info_expires)) { /* Data is too old, update. */ rc = sclp_chp_read_info(&chp_info); - chp_info_expires = jiffies + CHP_INFO_UPDATE_INTERVAL ; + if (!rc) + chp_info_expires = jiffies + CHP_INFO_UPDATE_INTERVAL; } mutex_unlock(&info_lock); diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c index e36e3ea165d3..2f34761e6413 100644 --- a/drivers/s390/net/ism_drv.c +++ b/drivers/s390/net/ism_drv.c @@ -588,6 +588,15 @@ out: return ret; } +static void ism_dev_release(struct device *dev) +{ + struct ism_dev *ism; + + ism = container_of(dev, struct ism_dev, dev); + + kfree(ism); +} + static int ism_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct ism_dev *ism; @@ -601,6 +610,7 @@ static int ism_probe(struct pci_dev *pdev, const struct pci_device_id *id) dev_set_drvdata(&pdev->dev, ism); ism->pdev = pdev; ism->dev.parent = &pdev->dev; + ism->dev.release = ism_dev_release; device_initialize(&ism->dev); dev_set_name(&ism->dev, dev_name(&pdev->dev)); ret = device_add(&ism->dev); @@ -637,7 +647,7 @@ err: device_del(&ism->dev); err_dev: dev_set_drvdata(&pdev->dev, NULL); - kfree(ism); + put_device(&ism->dev); return ret; } @@ -682,7 +692,7 @@ static void ism_remove(struct pci_dev *pdev) pci_disable_device(pdev); device_del(&ism->dev); dev_set_drvdata(&pdev->dev, NULL); - kfree(ism); + put_device(&ism->dev); } static struct pci_driver ism_driver = { diff --git a/drivers/spi/atmel-quadspi.c b/drivers/spi/atmel-quadspi.c index abdc49d9d940..d8c9be64d006 100644 --- a/drivers/spi/atmel-quadspi.c +++ b/drivers/spi/atmel-quadspi.c @@ -235,8 +235,8 @@ /** * struct atmel_qspi_pcal - Pad Calibration Clock Division * @pclk_rate: peripheral clock rate. - * @pclkdiv: calibration clock division. The clock applied to the calibration - * cell is divided by pclkdiv + 1. + * @pclk_div: calibration clock division. The clock applied to the calibration + * cell is divided by pclk_div + 1. */ struct atmel_qspi_pcal { u32 pclk_rate; diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c index 5f9cac41baff..06711a62fa3d 100644 --- a/drivers/spi/spi-pxa2xx.c +++ b/drivers/spi/spi-pxa2xx.c @@ -399,7 +399,7 @@ static void lpss_ssp_cs_control(struct spi_device *spi, bool enable) lpss_ssp_select_cs(spi, config); mask = LPSS_CS_CONTROL_CS_HIGH; - __lpss_ssp_update_priv(drv_data, config->reg_cs_ctrl, mask, enable ? mask : 0); + __lpss_ssp_update_priv(drv_data, config->reg_cs_ctrl, mask, enable ? 0 : mask); if (config->cs_clk_stays_gated) { /* * Changing CS alone when dynamic clock gating is on won't diff --git a/drivers/spi/spi-sn-f-ospi.c b/drivers/spi/spi-sn-f-ospi.c index 6ad4b729897e..c4969f66a0ba 100644 --- a/drivers/spi/spi-sn-f-ospi.c +++ b/drivers/spi/spi-sn-f-ospi.c @@ -116,6 +116,9 @@ struct f_ospi { static u32 f_ospi_get_dummy_cycle(const struct spi_mem_op *op) { + if (!op->dummy.nbytes) + return 0; + return (op->dummy.nbytes * 8) / op->dummy.buswidth; } diff --git a/drivers/thermal/cpufreq_cooling.c b/drivers/thermal/cpufreq_cooling.c index 280071be30b1..6b7ab1814c12 100644 --- a/drivers/thermal/cpufreq_cooling.c +++ b/drivers/thermal/cpufreq_cooling.c @@ -57,8 +57,6 @@ struct time_in_idle { * @max_level: maximum cooling level. One less than total number of valid * cpufreq frequencies. * @em: Reference on the Energy Model of the device - * @cdev: thermal_cooling_device pointer to keep track of the - * registered cooling device. * @policy: cpufreq policy. * @cooling_ops: cpufreq callbacks to thermal cooling device ops * @idle_time: idle time stats diff --git a/drivers/tty/serial/8250/8250.h b/drivers/tty/serial/8250/8250.h index 11e05aa014e5..b861585ca02a 100644 --- a/drivers/tty/serial/8250/8250.h +++ b/drivers/tty/serial/8250/8250.h @@ -374,6 +374,7 @@ static inline int is_omap1510_8250(struct uart_8250_port *pt) #ifdef CONFIG_SERIAL_8250_DMA extern int serial8250_tx_dma(struct uart_8250_port *); +extern void serial8250_tx_dma_flush(struct uart_8250_port *); extern int serial8250_rx_dma(struct uart_8250_port *); extern void serial8250_rx_dma_flush(struct uart_8250_port *); extern int serial8250_request_dma(struct uart_8250_port *); @@ -406,6 +407,7 @@ static inline int serial8250_tx_dma(struct uart_8250_port *p) { return -1; } +static inline void serial8250_tx_dma_flush(struct uart_8250_port *p) { } static inline int serial8250_rx_dma(struct uart_8250_port *p) { return -1; diff --git a/drivers/tty/serial/8250/8250_dma.c b/drivers/tty/serial/8250/8250_dma.c index d215c494ee24..f245a84f4a50 100644 --- a/drivers/tty/serial/8250/8250_dma.c +++ b/drivers/tty/serial/8250/8250_dma.c @@ -149,6 +149,22 @@ err: return ret; } +void serial8250_tx_dma_flush(struct uart_8250_port *p) +{ + struct uart_8250_dma *dma = p->dma; + + if (!dma->tx_running) + return; + + /* + * kfifo_reset() has been called by the serial core, avoid + * advancing and underflowing in __dma_tx_complete(). + */ + dma->tx_size = 0; + + dmaengine_terminate_async(dma->rxchan); +} + int serial8250_rx_dma(struct uart_8250_port *p) { struct uart_8250_dma *dma = p->dma; diff --git a/drivers/tty/serial/8250/8250_of.c b/drivers/tty/serial/8250/8250_of.c index 64aed7efc569..11c860ea80f6 100644 --- a/drivers/tty/serial/8250/8250_of.c +++ b/drivers/tty/serial/8250/8250_of.c @@ -110,7 +110,6 @@ static int of_platform_serial_setup(struct platform_device *ofdev, spin_lock_init(&port->lock); if (resource_type(&resource) == IORESOURCE_IO) { - port->iotype = UPIO_PORT; port->iobase = resource.start; } else { port->mapbase = resource.start; diff --git a/drivers/tty/serial/8250/8250_platform.c b/drivers/tty/serial/8250/8250_platform.c index 8bdc1879d952..c0343bfb8064 100644 --- a/drivers/tty/serial/8250/8250_platform.c +++ b/drivers/tty/serial/8250/8250_platform.c @@ -112,7 +112,6 @@ static int serial8250_probe_acpi(struct platform_device *pdev) struct device *dev = &pdev->dev; struct uart_8250_port uart = { }; struct resource *regs; - unsigned char iotype; int ret, line; regs = platform_get_mem_or_io(pdev, 0); @@ -122,13 +121,11 @@ static int serial8250_probe_acpi(struct platform_device *pdev) switch (resource_type(regs)) { case IORESOURCE_IO: uart.port.iobase = regs->start; - iotype = UPIO_PORT; break; case IORESOURCE_MEM: uart.port.mapbase = regs->start; uart.port.mapsize = resource_size(regs); uart.port.flags = UPF_IOREMAP; - iotype = UPIO_MEM; break; default: return -EINVAL; @@ -147,12 +144,6 @@ static int serial8250_probe_acpi(struct platform_device *pdev) if (ret) return ret; - /* - * The previous call may not set iotype correctly when reg-io-width - * property is absent and it doesn't support IO port resource. - */ - uart.port.iotype = iotype; - line = serial8250_register_8250_port(&uart); if (line < 0) return line; diff --git a/drivers/tty/serial/8250/8250_pnp.c b/drivers/tty/serial/8250/8250_pnp.c index 7c06ae79d8e2..7a837fdf9df1 100644 --- a/drivers/tty/serial/8250/8250_pnp.c +++ b/drivers/tty/serial/8250/8250_pnp.c @@ -436,7 +436,6 @@ serial_pnp_probe(struct pnp_dev *dev, const struct pnp_device_id *dev_id) { struct uart_8250_port uart, *port; int ret, flags = dev_id->driver_data; - unsigned char iotype; long line; if (flags & UNKNOWN_DEV) { @@ -448,14 +447,11 @@ serial_pnp_probe(struct pnp_dev *dev, const struct pnp_device_id *dev_id) memset(&uart, 0, sizeof(uart)); if ((flags & CIR_PORT) && pnp_port_valid(dev, 2)) { uart.port.iobase = pnp_port_start(dev, 2); - iotype = UPIO_PORT; } else if (pnp_port_valid(dev, 0)) { uart.port.iobase = pnp_port_start(dev, 0); - iotype = UPIO_PORT; } else if (pnp_mem_valid(dev, 0)) { uart.port.mapbase = pnp_mem_start(dev, 0); uart.port.mapsize = pnp_mem_len(dev, 0); - iotype = UPIO_MEM; uart.port.flags = UPF_IOREMAP; } else return -ENODEV; @@ -471,12 +467,6 @@ serial_pnp_probe(struct pnp_dev *dev, const struct pnp_device_id *dev_id) if (ret) return ret; - /* - * The previous call may not set iotype correctly when reg-io-width - * property is absent and it doesn't support IO port resource. - */ - uart.port.iotype = iotype; - if (flags & CIR_PORT) { uart.port.flags |= UPF_FIXED_PORT | UPF_FIXED_TYPE; uart.port.type = PORT_8250_CIR; diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index d7976a21cca9..442967a6cd52 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -2555,6 +2555,14 @@ static void serial8250_shutdown(struct uart_port *port) serial8250_do_shutdown(port); } +static void serial8250_flush_buffer(struct uart_port *port) +{ + struct uart_8250_port *up = up_to_u8250p(port); + + if (up->dma) + serial8250_tx_dma_flush(up); +} + static unsigned int serial8250_do_get_divisor(struct uart_port *port, unsigned int baud, unsigned int *frac) @@ -3244,6 +3252,7 @@ static const struct uart_ops serial8250_pops = { .break_ctl = serial8250_break_ctl, .startup = serial8250_startup, .shutdown = serial8250_shutdown, + .flush_buffer = serial8250_flush_buffer, .set_termios = serial8250_set_termios, .set_ldisc = serial8250_set_ldisc, .pm = serial8250_pm, diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c index 7b51cdc274fd..560f45ed19ae 100644 --- a/drivers/tty/serial/sc16is7xx.c +++ b/drivers/tty/serial/sc16is7xx.c @@ -1561,7 +1561,7 @@ int sc16is7xx_probe(struct device *dev, const struct sc16is7xx_devtype *devtype, /* Always ask for fixed clock rate from a property. */ device_property_read_u32(dev, "clock-frequency", &uartclk); - s->polling = !!irq; + s->polling = (irq <= 0); if (s->polling) dev_dbg(dev, "No interrupt pin definition, falling back to polling mode\n"); diff --git a/drivers/tty/serial/serial_port.c b/drivers/tty/serial/serial_port.c index d35f1d24156c..2fc48cd63f6c 100644 --- a/drivers/tty/serial/serial_port.c +++ b/drivers/tty/serial/serial_port.c @@ -173,6 +173,7 @@ EXPORT_SYMBOL(uart_remove_one_port); * The caller is responsible to initialize the following fields of the @port * ->dev (must be valid) * ->flags + * ->iobase * ->mapbase * ->mapsize * ->regshift (if @use_defaults is false) @@ -214,7 +215,7 @@ static int __uart_read_properties(struct uart_port *port, bool use_defaults) /* Read the registers I/O access type (default: MMIO 8-bit) */ ret = device_property_read_u32(dev, "reg-io-width", &value); if (ret) { - port->iotype = UPIO_MEM; + port->iotype = port->iobase ? UPIO_PORT : UPIO_MEM; } else { switch (value) { case 1: @@ -227,15 +228,16 @@ static int __uart_read_properties(struct uart_port *port, bool use_defaults) port->iotype = device_is_big_endian(dev) ? UPIO_MEM32BE : UPIO_MEM32; break; default: - if (!use_defaults) { - dev_err(dev, "Unsupported reg-io-width (%u)\n", value); - return -EINVAL; - } port->iotype = UPIO_UNKNOWN; break; } } + if (!use_defaults && port->iotype == UPIO_UNKNOWN) { + dev_err(dev, "Unsupported reg-io-width (%u)\n", value); + return -EINVAL; + } + /* Read the address mapping base offset (default: no offset) */ ret = device_property_read_u32(dev, "reg-offset", &value); if (ret) diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 6b37d1c47fce..c2ecfa3c8349 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -371,7 +371,7 @@ static void acm_process_notification(struct acm *acm, unsigned char *buf) static void acm_ctrl_irq(struct urb *urb) { struct acm *acm = urb->context; - struct usb_cdc_notification *dr = urb->transfer_buffer; + struct usb_cdc_notification *dr; unsigned int current_size = urb->actual_length; unsigned int expected_size, copy_size, alloc_size; int retval; @@ -398,14 +398,25 @@ static void acm_ctrl_irq(struct urb *urb) usb_mark_last_busy(acm->dev); - if (acm->nb_index) + if (acm->nb_index == 0) { + /* + * The first chunk of a message must contain at least the + * notification header with the length field, otherwise we + * can't get an expected_size. + */ + if (current_size < sizeof(struct usb_cdc_notification)) { + dev_dbg(&acm->control->dev, "urb too short\n"); + goto exit; + } + dr = urb->transfer_buffer; + } else { dr = (struct usb_cdc_notification *)acm->notification_buffer; - + } /* size = notification-header + (optional) data */ expected_size = sizeof(struct usb_cdc_notification) + le16_to_cpu(dr->wLength); - if (current_size < expected_size) { + if (acm->nb_index != 0 || current_size < expected_size) { /* notification is transmitted fragmented, reassemble */ if (acm->nb_size < expected_size) { u8 *new_buffer; @@ -1727,13 +1738,16 @@ static const struct usb_device_id acm_ids[] = { { USB_DEVICE(0x0870, 0x0001), /* Metricom GS Modem */ .driver_info = NO_UNION_NORMAL, /* has no union descriptor */ }, - { USB_DEVICE(0x045b, 0x023c), /* Renesas USB Download mode */ + { USB_DEVICE(0x045b, 0x023c), /* Renesas R-Car H3 USB Download mode */ + .driver_info = DISABLE_ECHO, /* Don't echo banner */ + }, + { USB_DEVICE(0x045b, 0x0247), /* Renesas R-Car D3 USB Download mode */ .driver_info = DISABLE_ECHO, /* Don't echo banner */ }, - { USB_DEVICE(0x045b, 0x0248), /* Renesas USB Download mode */ + { USB_DEVICE(0x045b, 0x0248), /* Renesas R-Car M3-N USB Download mode */ .driver_info = DISABLE_ECHO, /* Don't echo banner */ }, - { USB_DEVICE(0x045b, 0x024D), /* Renesas USB Download mode */ + { USB_DEVICE(0x045b, 0x024D), /* Renesas R-Car E3 USB Download mode */ .driver_info = DISABLE_ECHO, /* Don't echo banner */ }, { USB_DEVICE(0x0e8d, 0x0003), /* FIREFLY, MediaTek Inc; andrey.arapov@gmail.com */ diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index c3f839637cb5..a76bb50b6202 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -1849,6 +1849,17 @@ static int hub_probe(struct usb_interface *intf, const struct usb_device_id *id) hdev = interface_to_usbdev(intf); /* + * The USB 2.0 spec prohibits hubs from having more than one + * configuration or interface, and we rely on this prohibition. + * Refuse to accept a device that violates it. + */ + if (hdev->descriptor.bNumConfigurations > 1 || + hdev->actconfig->desc.bNumInterfaces > 1) { + dev_err(&intf->dev, "Invalid hub with more than one config or interface\n"); + return -EINVAL; + } + + /* * Set default autosuspend delay as 0 to speedup bus suspend, * based on the below considerations: * @@ -4698,7 +4709,6 @@ void usb_ep0_reinit(struct usb_device *udev) EXPORT_SYMBOL_GPL(usb_ep0_reinit); #define usb_sndaddr0pipe() (PIPE_CONTROL << 30) -#define usb_rcvaddr0pipe() ((PIPE_CONTROL << 30) | USB_DIR_IN) static int hub_set_address(struct usb_device *udev, int devnum) { @@ -4804,7 +4814,7 @@ static int get_bMaxPacketSize0(struct usb_device *udev, for (i = 0; i < GET_MAXPACKET0_TRIES; ++i) { /* Start with invalid values in case the transfer fails */ buf->bDescriptorType = buf->bMaxPacketSize0 = 0; - rc = usb_control_msg(udev, usb_rcvaddr0pipe(), + rc = usb_control_msg(udev, usb_rcvctrlpipe(udev, 0), USB_REQ_GET_DESCRIPTOR, USB_DIR_IN, USB_DT_DEVICE << 8, 0, buf, size, diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index 67732c791c93..dfcfc142bd5e 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -435,6 +435,9 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x0c45, 0x7056), .driver_info = USB_QUIRK_IGNORE_REMOTE_WAKEUP }, + /* Sony Xperia XZ1 Compact (lilac) smartphone in fastboot mode */ + { USB_DEVICE(0x0fce, 0x0dde), .driver_info = USB_QUIRK_NO_LPM }, + /* Action Semiconductor flash disk */ { USB_DEVICE(0x10d6, 0x2200), .driver_info = USB_QUIRK_STRING_FETCH_255 }, @@ -525,6 +528,9 @@ static const struct usb_device_id usb_quirk_list[] = { /* Blackmagic Design UltraStudio SDI */ { USB_DEVICE(0x1edb, 0xbd4f), .driver_info = USB_QUIRK_NO_LPM }, + /* Teclast disk */ + { USB_DEVICE(0x1f75, 0x0917), .driver_info = USB_QUIRK_NO_LPM }, + /* Hauppauge HVR-950q */ { USB_DEVICE(0x2040, 0x7200), .driver_info = USB_QUIRK_CONFIG_INTF_STRINGS }, diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c index e7bf9cc635be..bd4c788f03bc 100644 --- a/drivers/usb/dwc2/gadget.c +++ b/drivers/usb/dwc2/gadget.c @@ -4615,6 +4615,7 @@ static int dwc2_hsotg_udc_stop(struct usb_gadget *gadget) spin_lock_irqsave(&hsotg->lock, flags); hsotg->driver = NULL; + hsotg->gadget.dev.of_node = NULL; hsotg->gadget.speed = USB_SPEED_UNKNOWN; hsotg->enabled = 0; diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index ac7c730f81ac..c955039bb4f6 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -717,6 +717,7 @@ struct dwc3_event_buffer { /** * struct dwc3_ep - device side endpoint representation * @endpoint: usb endpoint + * @nostream_work: work for handling bulk NoStream * @cancelled_list: list of cancelled requests for this endpoint * @pending_list: list of pending requests for this endpoint * @started_list: list of started requests on this endpoint diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index d27af65eb08a..ddd6b2ce5710 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -2629,10 +2629,38 @@ static int dwc3_gadget_run_stop(struct dwc3 *dwc, int is_on) { u32 reg; u32 timeout = 2000; + u32 saved_config = 0; if (pm_runtime_suspended(dwc->dev)) return 0; + /* + * When operating in USB 2.0 speeds (HS/FS), ensure that + * GUSB2PHYCFG.ENBLSLPM and GUSB2PHYCFG.SUSPHY are cleared before starting + * or stopping the controller. This resolves timeout issues that occur + * during frequent role switches between host and device modes. + * + * Save and clear these settings, then restore them after completing the + * controller start or stop sequence. + * + * This solution was discovered through experimentation as it is not + * mentioned in the dwc3 programming guide. It has been tested on an + * Exynos platforms. + */ + reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0)); + if (reg & DWC3_GUSB2PHYCFG_SUSPHY) { + saved_config |= DWC3_GUSB2PHYCFG_SUSPHY; + reg &= ~DWC3_GUSB2PHYCFG_SUSPHY; + } + + if (reg & DWC3_GUSB2PHYCFG_ENBLSLPM) { + saved_config |= DWC3_GUSB2PHYCFG_ENBLSLPM; + reg &= ~DWC3_GUSB2PHYCFG_ENBLSLPM; + } + + if (saved_config) + dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(0), reg); + reg = dwc3_readl(dwc->regs, DWC3_DCTL); if (is_on) { if (DWC3_VER_IS_WITHIN(DWC3, ANY, 187A)) { @@ -2660,6 +2688,12 @@ static int dwc3_gadget_run_stop(struct dwc3 *dwc, int is_on) reg &= DWC3_DSTS_DEVCTRLHLT; } while (--timeout && !(!is_on ^ !reg)); + if (saved_config) { + reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0)); + reg |= saved_config; + dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(0), reg); + } + if (!timeout) return -ETIMEDOUT; diff --git a/drivers/usb/gadget/function/f_midi.c b/drivers/usb/gadget/function/f_midi.c index 837fcdfa3840..da82598fcef8 100644 --- a/drivers/usb/gadget/function/f_midi.c +++ b/drivers/usb/gadget/function/f_midi.c @@ -283,7 +283,7 @@ f_midi_complete(struct usb_ep *ep, struct usb_request *req) /* Our transmit completed. See if there's more to go. * f_midi_transmit eats req, don't queue it again. */ req->length = 0; - f_midi_transmit(midi); + queue_work(system_highpri_wq, &midi->work); return; } break; @@ -907,6 +907,15 @@ static int f_midi_bind(struct usb_configuration *c, struct usb_function *f) status = -ENODEV; + /* + * Reset wMaxPacketSize with maximum packet size of FS bulk transfer before + * endpoint claim. This ensures that the wMaxPacketSize does not exceed the + * limit during bind retries where configured dwc3 TX/RX FIFO's maxpacket + * size of 512 bytes for IN/OUT endpoints in support HS speed only. + */ + bulk_in_desc.wMaxPacketSize = cpu_to_le16(64); + bulk_out_desc.wMaxPacketSize = cpu_to_le16(64); + /* allocate instance-specific endpoints */ midi->in_ep = usb_ep_autoconfig(cdev->gadget, &bulk_in_desc); if (!midi->in_ep) @@ -1000,11 +1009,11 @@ static int f_midi_bind(struct usb_configuration *c, struct usb_function *f) } /* configure the endpoint descriptors ... */ - ms_out_desc.bLength = USB_DT_MS_ENDPOINT_SIZE(midi->in_ports); - ms_out_desc.bNumEmbMIDIJack = midi->in_ports; + ms_out_desc.bLength = USB_DT_MS_ENDPOINT_SIZE(midi->out_ports); + ms_out_desc.bNumEmbMIDIJack = midi->out_ports; - ms_in_desc.bLength = USB_DT_MS_ENDPOINT_SIZE(midi->out_ports); - ms_in_desc.bNumEmbMIDIJack = midi->out_ports; + ms_in_desc.bLength = USB_DT_MS_ENDPOINT_SIZE(midi->in_ports); + ms_in_desc.bNumEmbMIDIJack = midi->in_ports; /* ... and add them to the list */ endpoint_descriptor_index = i; diff --git a/drivers/usb/gadget/function/uvc_video.c b/drivers/usb/gadget/function/uvc_video.c index 79e223713d8b..fb77b0b21790 100644 --- a/drivers/usb/gadget/function/uvc_video.c +++ b/drivers/usb/gadget/function/uvc_video.c @@ -818,7 +818,7 @@ int uvcg_video_init(struct uvc_video *video, struct uvc_device *uvc) return -EINVAL; /* Allocate a kthread for asynchronous hw submit handler. */ - video->kworker = kthread_create_worker(0, "UVCG"); + video->kworker = kthread_run_worker(0, "UVCG"); if (IS_ERR(video->kworker)) { uvcg_err(&video->uvc->func, "failed to create UVCG kworker\n"); return PTR_ERR(video->kworker); diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c index a6f46364be65..4b3d5075621a 100644 --- a/drivers/usb/gadget/udc/core.c +++ b/drivers/usb/gadget/udc/core.c @@ -1543,8 +1543,8 @@ void usb_del_gadget(struct usb_gadget *gadget) kobject_uevent(&udc->dev.kobj, KOBJ_REMOVE); sysfs_remove_link(&udc->dev.kobj, "gadget"); - flush_work(&gadget->work); device_del(&gadget->dev); + flush_work(&gadget->work); ida_free(&gadget_id_numbers, gadget->id_number); cancel_work_sync(&udc->vbus_work); device_unregister(&udc->dev); diff --git a/drivers/usb/gadget/udc/renesas_usb3.c b/drivers/usb/gadget/udc/renesas_usb3.c index fce5c41d9f29..89b304cf6d03 100644 --- a/drivers/usb/gadget/udc/renesas_usb3.c +++ b/drivers/usb/gadget/udc/renesas_usb3.c @@ -310,7 +310,7 @@ struct renesas_usb3_request { struct list_head queue; }; -#define USB3_EP_NAME_SIZE 8 +#define USB3_EP_NAME_SIZE 16 struct renesas_usb3_ep { struct usb_ep ep; struct renesas_usb3 *usb3; diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c index 1f9c1b1435d8..0404489c2f6a 100644 --- a/drivers/usb/host/pci-quirks.c +++ b/drivers/usb/host/pci-quirks.c @@ -958,6 +958,15 @@ static void quirk_usb_disable_ehci(struct pci_dev *pdev) * booting from USB disk or using a usb keyboard */ hcc_params = readl(base + EHCI_HCC_PARAMS); + + /* LS7A EHCI controller doesn't have extended capabilities, the + * EECP (EHCI Extended Capabilities Pointer) field of HCCPARAMS + * register should be 0x0 but it reads as 0xa0. So clear it to + * avoid error messages on boot. + */ + if (pdev->vendor == PCI_VENDOR_ID_LOONGSON && pdev->device == 0x7a14) + hcc_params &= ~(0xffL << 8); + offset = (hcc_params >> 8) & 0xff; while (offset && --count) { pci_read_config_dword(pdev, offset, &cap); diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 2d1e205c14c6..ad0ff356f6fa 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -653,8 +653,8 @@ put_runtime_pm: } EXPORT_SYMBOL_NS_GPL(xhci_pci_common_probe, "xhci"); -static const struct pci_device_id pci_ids_reject[] = { - /* handled by xhci-pci-renesas */ +/* handled by xhci-pci-renesas if enabled */ +static const struct pci_device_id pci_ids_renesas[] = { { PCI_DEVICE(PCI_VENDOR_ID_RENESAS, 0x0014) }, { PCI_DEVICE(PCI_VENDOR_ID_RENESAS, 0x0015) }, { /* end: all zeroes */ } @@ -662,7 +662,8 @@ static const struct pci_device_id pci_ids_reject[] = { static int xhci_pci_probe(struct pci_dev *dev, const struct pci_device_id *id) { - if (pci_match_id(pci_ids_reject, dev)) + if (IS_ENABLED(CONFIG_USB_XHCI_PCI_RENESAS) && + pci_match_id(pci_ids_renesas, dev)) return -ENODEV; return xhci_pci_common_probe(dev, id); diff --git a/drivers/usb/phy/phy-generic.c b/drivers/usb/phy/phy-generic.c index 6c3ececf9137..8423be59ec0f 100644 --- a/drivers/usb/phy/phy-generic.c +++ b/drivers/usb/phy/phy-generic.c @@ -212,7 +212,7 @@ int usb_phy_gen_create_phy(struct device *dev, struct usb_phy_generic *nop) if (of_property_read_u32(node, "clock-frequency", &clk_rate)) clk_rate = 0; - needs_clk = of_property_read_bool(node, "clocks"); + needs_clk = of_property_present(node, "clocks"); } nop->gpiod_reset = devm_gpiod_get_optional(dev, "reset", GPIOD_ASIS); diff --git a/drivers/usb/roles/class.c b/drivers/usb/roles/class.c index c58a12c147f4..30482d4cf826 100644 --- a/drivers/usb/roles/class.c +++ b/drivers/usb/roles/class.c @@ -387,8 +387,11 @@ usb_role_switch_register(struct device *parent, dev_set_name(&sw->dev, "%s-role-switch", desc->name ? desc->name : dev_name(parent)); + sw->registered = true; + ret = device_register(&sw->dev); if (ret) { + sw->registered = false; put_device(&sw->dev); return ERR_PTR(ret); } @@ -399,8 +402,6 @@ usb_role_switch_register(struct device *parent, dev_warn(&sw->dev, "failed to add component\n"); } - sw->registered = true; - /* TODO: Symlinks for the host port and the device controller. */ return sw; diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 1e2ae0c6c41c..58bd54e8c483 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -619,15 +619,6 @@ static void option_instat_callback(struct urb *urb); /* Luat Air72*U series based on UNISOC UIS8910 uses UNISOC's vendor ID */ #define LUAT_PRODUCT_AIR720U 0x4e00 -/* MeiG Smart Technology products */ -#define MEIGSMART_VENDOR_ID 0x2dee -/* 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 -/* MeiG Smart SLM770A based on ASR1803 */ -#define MEIGSMART_PRODUCT_SLM770A 0x4d57 - /* Device flags */ /* Highest interface number which can be used with NCTRL() and RSVD() */ @@ -1367,15 +1358,15 @@ static const struct usb_device_id option_ids[] = { .driver_info = NCTRL(2) | RSVD(3) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1063, 0xff), /* Telit LN920 (ECM) */ .driver_info = NCTRL(0) | RSVD(1) }, - { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1070, 0xff), /* Telit FN990 (rmnet) */ + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1070, 0xff), /* Telit FN990A (rmnet) */ .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) }, - { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1071, 0xff), /* Telit FN990 (MBIM) */ + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1071, 0xff), /* Telit FN990A (MBIM) */ .driver_info = NCTRL(0) | RSVD(1) }, - { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1072, 0xff), /* Telit FN990 (RNDIS) */ + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1072, 0xff), /* Telit FN990A (RNDIS) */ .driver_info = NCTRL(2) | RSVD(3) }, - { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1073, 0xff), /* Telit FN990 (ECM) */ + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1073, 0xff), /* Telit FN990A (ECM) */ .driver_info = NCTRL(0) | RSVD(1) }, - { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1075, 0xff), /* Telit FN990 (PCIe) */ + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1075, 0xff), /* Telit FN990A (PCIe) */ .driver_info = RSVD(0) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1080, 0xff), /* Telit FE990 (rmnet) */ .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) }, @@ -1403,6 +1394,22 @@ static const struct usb_device_id option_ids[] = { .driver_info = RSVD(0) | NCTRL(3) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10c8, 0xff), /* Telit FE910C04 (rmnet) */ .driver_info = RSVD(0) | NCTRL(2) | RSVD(3) | RSVD(4) }, + { USB_DEVICE_INTERFACE_PROTOCOL(TELIT_VENDOR_ID, 0x10d0, 0x60) }, /* Telit FN990B (rmnet) */ + { USB_DEVICE_INTERFACE_PROTOCOL(TELIT_VENDOR_ID, 0x10d0, 0x40) }, + { USB_DEVICE_INTERFACE_PROTOCOL(TELIT_VENDOR_ID, 0x10d0, 0x30), + .driver_info = NCTRL(5) }, + { USB_DEVICE_INTERFACE_PROTOCOL(TELIT_VENDOR_ID, 0x10d1, 0x60) }, /* Telit FN990B (MBIM) */ + { USB_DEVICE_INTERFACE_PROTOCOL(TELIT_VENDOR_ID, 0x10d1, 0x40) }, + { USB_DEVICE_INTERFACE_PROTOCOL(TELIT_VENDOR_ID, 0x10d1, 0x30), + .driver_info = NCTRL(6) }, + { USB_DEVICE_INTERFACE_PROTOCOL(TELIT_VENDOR_ID, 0x10d2, 0x60) }, /* Telit FN990B (RNDIS) */ + { USB_DEVICE_INTERFACE_PROTOCOL(TELIT_VENDOR_ID, 0x10d2, 0x40) }, + { USB_DEVICE_INTERFACE_PROTOCOL(TELIT_VENDOR_ID, 0x10d2, 0x30), + .driver_info = NCTRL(6) }, + { USB_DEVICE_INTERFACE_PROTOCOL(TELIT_VENDOR_ID, 0x10d3, 0x60) }, /* Telit FN990B (ECM) */ + { USB_DEVICE_INTERFACE_PROTOCOL(TELIT_VENDOR_ID, 0x10d3, 0x40) }, + { USB_DEVICE_INTERFACE_PROTOCOL(TELIT_VENDOR_ID, 0x10d3, 0x30), + .driver_info = NCTRL(6) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910), .driver_info = NCTRL(0) | RSVD(1) | RSVD(3) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910_DUAL_MODEM), @@ -2347,6 +2354,14 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0a05, 0xff) }, /* Fibocom FM650-CN (NCM mode) */ { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0a06, 0xff) }, /* Fibocom FM650-CN (RNDIS mode) */ { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0a07, 0xff) }, /* Fibocom FM650-CN (MBIM mode) */ + { USB_DEVICE_AND_INTERFACE_INFO(0x2dee, 0x4d41, 0xff, 0, 0) }, /* MeiG Smart SLM320 */ + { USB_DEVICE_AND_INTERFACE_INFO(0x2dee, 0x4d57, 0xff, 0, 0) }, /* MeiG Smart SLM770A */ + { USB_DEVICE_AND_INTERFACE_INFO(0x2dee, 0x4d22, 0xff, 0, 0) }, /* MeiG Smart SRM815 */ + { USB_DEVICE_AND_INTERFACE_INFO(0x2dee, 0x4d22, 0xff, 0x10, 0x02) }, /* MeiG Smart SLM828 */ + { USB_DEVICE_AND_INTERFACE_INFO(0x2dee, 0x4d22, 0xff, 0x10, 0x03) }, /* MeiG Smart SLM828 */ + { USB_DEVICE_AND_INTERFACE_INFO(0x2dee, 0x4d22, 0xff, 0xff, 0x30) }, /* MeiG Smart SRM815 and SRM825L */ + { USB_DEVICE_AND_INTERFACE_INFO(0x2dee, 0x4d22, 0xff, 0xff, 0x40) }, /* MeiG Smart SRM825L */ + { USB_DEVICE_AND_INTERFACE_INFO(0x2dee, 0x4d22, 0xff, 0xff, 0x60) }, /* MeiG Smart SRM825L */ { USB_DEVICE_INTERFACE_CLASS(0x2df3, 0x9d03, 0xff) }, /* LongSung M5710 */ { USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1404, 0xff) }, /* GosunCn GM500 RNDIS */ { USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1405, 0xff) }, /* GosunCn GM500 MBIM */ @@ -2403,12 +2418,6 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, TOZED_PRODUCT_LT70C, 0xff, 0, 0) }, { 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) }, { USB_DEVICE_INTERFACE_CLASS(0x1bbb, 0x0530, 0xff), /* TCL IK512 MBIM */ .driver_info = NCTRL(1) }, { USB_DEVICE_INTERFACE_CLASS(0x1bbb, 0x0640, 0xff), /* TCL IK512 ECM */ diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 47be450d2be3..6bf1a22c785a 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -5591,8 +5591,7 @@ static void run_state_machine(struct tcpm_port *port) tcpm_set_auto_vbus_discharge_threshold(port, TYPEC_PWR_MODE_USB, port->pps_data.active, 0); tcpm_set_charge(port, false); - tcpm_set_state(port, hard_reset_state(port), - port->timings.ps_src_off_time); + tcpm_set_state(port, ERROR_RECOVERY, port->timings.ps_src_off_time); break; case PR_SWAP_SNK_SRC_SOURCE_ON: tcpm_enable_auto_vbus_discharge(port, true); diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index a337edcf8faf..1f65795cf5d7 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -74,19 +74,21 @@ static inline phys_addr_t xen_dma_to_phys(struct device *dev, return xen_bus_to_phys(dev, dma_to_phys(dev, dma_addr)); } +static inline bool range_requires_alignment(phys_addr_t p, size_t size) +{ + phys_addr_t algn = 1ULL << (get_order(size) + PAGE_SHIFT); + phys_addr_t bus_addr = pfn_to_bfn(XEN_PFN_DOWN(p)) << XEN_PAGE_SHIFT; + + return IS_ALIGNED(p, algn) && !IS_ALIGNED(bus_addr, algn); +} + static inline int range_straddles_page_boundary(phys_addr_t p, size_t size) { unsigned long next_bfn, xen_pfn = XEN_PFN_DOWN(p); unsigned int i, nr_pages = XEN_PFN_UP(xen_offset_in_page(p) + size); - phys_addr_t algn = 1ULL << (get_order(size) + PAGE_SHIFT); next_bfn = pfn_to_bfn(xen_pfn); - /* If buffer is physically aligned, ensure DMA alignment. */ - if (IS_ALIGNED(p, algn) && - !IS_ALIGNED((phys_addr_t)next_bfn << XEN_PAGE_SHIFT, algn)) - return 1; - for (i = 1; i < nr_pages; i++) if (pfn_to_bfn(++xen_pfn) != ++next_bfn) return 1; @@ -111,7 +113,7 @@ static struct io_tlb_pool *xen_swiotlb_find_pool(struct device *dev, } #ifdef CONFIG_X86 -int xen_swiotlb_fixup(void *buf, unsigned long nslabs) +int __init xen_swiotlb_fixup(void *buf, unsigned long nslabs) { int rc; unsigned int order = get_order(IO_TLB_SEGSIZE << IO_TLB_SHIFT); @@ -156,7 +158,8 @@ xen_swiotlb_alloc_coherent(struct device *dev, size_t size, *dma_handle = xen_phys_to_dma(dev, phys); if (*dma_handle + size - 1 > dma_mask || - range_straddles_page_boundary(phys, size)) { + range_straddles_page_boundary(phys, size) || + range_requires_alignment(phys, size)) { if (xen_create_contiguous_region(phys, order, fls64(dma_mask), dma_handle) != 0) goto out_free_pages; @@ -182,7 +185,8 @@ xen_swiotlb_free_coherent(struct device *dev, size_t size, void *vaddr, size = ALIGN(size, XEN_PAGE_SIZE); if (WARN_ON_ONCE(dma_handle + size - 1 > dev->coherent_dma_mask) || - WARN_ON_ONCE(range_straddles_page_boundary(phys, size))) + WARN_ON_ONCE(range_straddles_page_boundary(phys, size) || + range_requires_alignment(phys, size))) return; if (TestClearPageXenRemapped(virt_to_page(vaddr))) diff --git a/fs/bcachefs/btree_update_interior.c b/fs/bcachefs/btree_update_interior.c index f4aeadbe53c1..e4e7c804625e 100644 --- a/fs/bcachefs/btree_update_interior.c +++ b/fs/bcachefs/btree_update_interior.c @@ -681,9 +681,11 @@ static void btree_update_nodes_written(struct btree_update *as) b = as->old_nodes[i]; + bch2_trans_begin(trans); btree_node_lock_nopath_nofail(trans, &b->c, SIX_LOCK_read); seq = b->data ? b->data->keys.seq : 0; six_unlock_read(&b->c.lock); + bch2_trans_unlock_long(trans); if (seq == as->old_nodes_seq[i]) wait_on_bit_io(&b->flags, BTREE_NODE_write_in_flight_inner, diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c index 53a421ff136d..9bf316e7b845 100644 --- a/fs/bcachefs/fsck.c +++ b/fs/bcachefs/fsck.c @@ -823,6 +823,7 @@ struct inode_walker_entry { struct bch_inode_unpacked inode; u32 snapshot; u64 count; + u64 i_size; }; struct inode_walker { @@ -910,8 +911,9 @@ found: if (k.k->p.snapshot != i->snapshot && !is_whiteout) { struct inode_walker_entry new = *i; - new.snapshot = k.k->p.snapshot; - new.count = 0; + new.snapshot = k.k->p.snapshot; + new.count = 0; + new.i_size = 0; struct printbuf buf = PRINTBUF; bch2_bkey_val_to_text(&buf, c, k); @@ -1116,37 +1118,6 @@ err: return ret; } -static int check_directory_size(struct btree_trans *trans, - struct bch_inode_unpacked *inode_u, - struct bkey_s_c inode_k, bool *write_inode) -{ - struct btree_iter iter; - struct bkey_s_c k; - u64 new_size = 0; - int ret; - - for_each_btree_key_max_norestart(trans, iter, BTREE_ID_dirents, - SPOS(inode_k.k->p.offset, 0, inode_k.k->p.snapshot), - POS(inode_k.k->p.offset, U64_MAX), - 0, k, ret) { - if (k.k->type != KEY_TYPE_dirent) - continue; - - struct bkey_s_c_dirent dirent = bkey_s_c_to_dirent(k); - struct qstr name = bch2_dirent_get_name(dirent); - - new_size += dirent_occupied_size(&name); - } - bch2_trans_iter_exit(trans, &iter); - - if (!ret && inode_u->bi_size != new_size) { - inode_u->bi_size = new_size; - *write_inode = true; - } - - return ret; -} - static int check_inode(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k, @@ -1335,16 +1306,6 @@ static int check_inode(struct btree_trans *trans, u.bi_journal_seq = journal_cur_seq(&c->journal); do_update = true; } - - if (S_ISDIR(u.bi_mode)) { - ret = check_directory_size(trans, &u, k, &do_update); - - fsck_err_on(ret, - trans, directory_size_mismatch, - "directory inode %llu:%u with the mismatch directory size", - u.bi_inum, k.k->p.snapshot); - ret = 0; - } do_update: if (do_update) { ret = __bch2_fsck_write_inode(trans, &u); @@ -2017,10 +1978,31 @@ fsck_err: return ret; } -static int check_subdir_count(struct btree_trans *trans, struct inode_walker *w) +static int check_dir_i_size_notnested(struct btree_trans *trans, struct inode_walker *w) +{ + struct bch_fs *c = trans->c; + int ret = 0; + + darray_for_each(w->inodes, i) + if (fsck_err_on(i->inode.bi_size != i->i_size, + trans, inode_dir_wrong_nlink, + "directory %llu:%u with wrong i_size: got %llu, should be %llu", + w->last_pos.inode, i->snapshot, i->inode.bi_size, i->i_size)) { + i->inode.bi_size = i->i_size; + ret = bch2_fsck_write_inode(trans, &i->inode); + if (ret) + break; + } +fsck_err: + bch_err_fn(c, ret); + return ret; +} + +static int check_subdir_dirents_count(struct btree_trans *trans, struct inode_walker *w) { u32 restart_count = trans->restart_count; return check_subdir_count_notnested(trans, w) ?: + check_dir_i_size_notnested(trans, w) ?: trans_was_restarted(trans, restart_count); } @@ -2367,7 +2349,7 @@ static int check_dirent(struct btree_trans *trans, struct btree_iter *iter, goto out; if (dir->last_pos.inode != k.k->p.inode && dir->have_inodes) { - ret = check_subdir_count(trans, dir); + ret = check_subdir_dirents_count(trans, dir); if (ret) goto err; } @@ -2457,9 +2439,11 @@ static int check_dirent(struct btree_trans *trans, struct btree_iter *iter, if (ret) goto err; - if (d.v->d_type == DT_DIR) - for_each_visible_inode(c, s, dir, d.k->p.snapshot, i) + for_each_visible_inode(c, s, dir, d.k->p.snapshot, i) { + if (d.v->d_type == DT_DIR) i->count++; + i->i_size += bkey_bytes(d.k); + } out: err: fsck_err: diff --git a/fs/bcachefs/reflink.c b/fs/bcachefs/reflink.c index 376fd0a6e868..441e648f28b5 100644 --- a/fs/bcachefs/reflink.c +++ b/fs/bcachefs/reflink.c @@ -172,7 +172,7 @@ static int bch2_indirect_extent_missing_error(struct btree_trans *trans, bool should_commit) { if (REFLINK_P_ERROR(p.v)) - return -BCH_ERR_missing_indirect_extent; + return 0; struct bch_fs *c = trans->c; u64 live_start = REFLINK_P_IDX(p.v); @@ -259,8 +259,6 @@ struct bkey_s_c bch2_lookup_indirect_extent(struct btree_trans *trans, return k; if (unlikely(!bkey_extent_is_reflink_data(k.k))) { - bch2_trans_iter_exit(trans, iter); - unsigned size = min((u64) k.k->size, REFLINK_P_IDX(p.v) + p.k->size + le32_to_cpu(p.v->back_pad) - reflink_offset); @@ -268,14 +266,16 @@ struct bkey_s_c bch2_lookup_indirect_extent(struct btree_trans *trans, int ret = bch2_indirect_extent_missing_error(trans, p, reflink_offset, k.k->p.offset, should_commit); - if (ret) + if (ret) { + bch2_trans_iter_exit(trans, iter); return bkey_s_c_err(ret); + } } else if (unlikely(REFLINK_P_ERROR(p.v))) { - bch2_trans_iter_exit(trans, iter); - int ret = bch2_indirect_extent_not_missing(trans, p, should_commit); - if (ret) + if (ret) { + bch2_trans_iter_exit(trans, iter); return bkey_s_c_err(ret); + } } *offset_into_extent = reflink_offset - bkey_start_offset(k.k); @@ -300,7 +300,7 @@ static int trans_trigger_reflink_p_segment(struct btree_trans *trans, if (ret) return ret; - if (bkey_deleted(k.k)) { + if (!bkey_refcount_c(k)) { if (!(flags & BTREE_TRIGGER_overwrite)) ret = -BCH_ERR_missing_indirect_extent; goto next; @@ -381,8 +381,6 @@ static s64 gc_trigger_reflink_p_segment(struct btree_trans *trans, not_found: if (flags & BTREE_TRIGGER_check_repair) { ret = bch2_indirect_extent_missing_error(trans, p, *idx, next_idx, false); - if (ret == -BCH_ERR_missing_indirect_extent) - ret = 0; if (ret) goto err; } diff --git a/fs/bcachefs/sb-downgrade.c b/fs/bcachefs/sb-downgrade.c index 14f6b6a5fb38..35e07bc8fbd3 100644 --- a/fs/bcachefs/sb-downgrade.c +++ b/fs/bcachefs/sb-downgrade.c @@ -92,7 +92,7 @@ BCH_FSCK_ERR_accounting_key_replicas_nr_devs_0, \ BCH_FSCK_ERR_accounting_key_junk_at_end) \ x(directory_size, \ - BIT_ULL(BCH_RECOVERY_PASS_check_inodes), \ + BIT_ULL(BCH_RECOVERY_PASS_check_dirents), \ BCH_FSCK_ERR_directory_size_mismatch) \ #define DOWNGRADE_TABLE() \ diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 7c0980db77b3..2fecf66661e9 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -447,7 +447,7 @@ static bool ep_busy_loop(struct eventpoll *ep, int nonblock) if (!budget) budget = BUSY_POLL_BUDGET; - if (napi_id >= MIN_NAPI_ID && ep_busy_loop_on(ep)) { + if (napi_id_valid(napi_id) && ep_busy_loop_on(ep)) { napi_busy_loop(napi_id, nonblock ? NULL : ep_busy_loop_end, ep, prefer_busy_poll, budget); if (ep_events_available(ep)) @@ -492,7 +492,7 @@ static inline void ep_set_busy_poll_napi_id(struct epitem *epi) * or * Nothing to do if we already have this ID */ - if (napi_id < MIN_NAPI_ID || napi_id == ep->napi_id) + if (!napi_id_valid(napi_id) || napi_id == ep->napi_id) return; /* record NAPI ID for use in next busy poll */ @@ -546,7 +546,7 @@ static void ep_suspend_napi_irqs(struct eventpoll *ep) { unsigned int napi_id = READ_ONCE(ep->napi_id); - if (napi_id >= MIN_NAPI_ID && READ_ONCE(ep->prefer_busy_poll)) + if (napi_id_valid(napi_id) && READ_ONCE(ep->prefer_busy_poll)) napi_suspend_irqs(napi_id); } @@ -554,7 +554,7 @@ static void ep_resume_napi_irqs(struct eventpoll *ep) { unsigned int napi_id = READ_ONCE(ep->napi_id); - if (napi_id >= MIN_NAPI_ID && READ_ONCE(ep->prefer_busy_poll)) + if (napi_id_valid(napi_id) && READ_ONCE(ep->prefer_busy_poll)) napi_resume_irqs(napi_id); } diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index f761d44b3436..0d1b6d35ff3b 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -155,8 +155,9 @@ static void netfs_read_cache_to_pagecache(struct netfs_io_request *rreq, netfs_cache_read_terminated, subreq); } -static void netfs_issue_read(struct netfs_io_request *rreq, - struct netfs_io_subrequest *subreq) +static void netfs_queue_read(struct netfs_io_request *rreq, + struct netfs_io_subrequest *subreq, + bool last_subreq) { struct netfs_io_stream *stream = &rreq->io_streams[0]; @@ -177,8 +178,17 @@ static void netfs_issue_read(struct netfs_io_request *rreq, } } + if (last_subreq) { + smp_wmb(); /* Write lists before ALL_QUEUED. */ + set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags); + } + spin_unlock(&rreq->lock); +} +static void netfs_issue_read(struct netfs_io_request *rreq, + struct netfs_io_subrequest *subreq) +{ switch (subreq->source) { case NETFS_DOWNLOAD_FROM_SERVER: rreq->netfs_ops->issue_read(subreq); @@ -293,11 +303,8 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq) } size -= slice; start += slice; - if (size <= 0) { - smp_wmb(); /* Write lists before ALL_QUEUED. */ - set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags); - } + netfs_queue_read(rreq, subreq, size <= 0); netfs_issue_read(rreq, subreq); cond_resched(); } while (size > 0); diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h index eb76f98c894b..1c4f953c3d68 100644 --- a/fs/netfs/internal.h +++ b/fs/netfs/internal.h @@ -135,6 +135,8 @@ extern atomic_t netfs_n_rh_write_begin; extern atomic_t netfs_n_rh_write_done; extern atomic_t netfs_n_rh_write_failed; extern atomic_t netfs_n_rh_write_zskip; +extern atomic_t netfs_n_rh_retry_read_req; +extern atomic_t netfs_n_rh_retry_read_subreq; extern atomic_t netfs_n_wh_buffered_write; extern atomic_t netfs_n_wh_writethrough; extern atomic_t netfs_n_wh_dio_write; @@ -147,6 +149,8 @@ extern atomic_t netfs_n_wh_upload_failed; extern atomic_t netfs_n_wh_write; extern atomic_t netfs_n_wh_write_done; extern atomic_t netfs_n_wh_write_failed; +extern atomic_t netfs_n_wh_retry_write_req; +extern atomic_t netfs_n_wh_retry_write_subreq; extern atomic_t netfs_n_wb_lock_skip; extern atomic_t netfs_n_wb_lock_wait; extern atomic_t netfs_n_folioq; diff --git a/fs/netfs/read_collect.c b/fs/netfs/read_collect.c index f65affa5a9e4..636cc5a98ef5 100644 --- a/fs/netfs/read_collect.c +++ b/fs/netfs/read_collect.c @@ -470,7 +470,8 @@ void netfs_read_collection_worker(struct work_struct *work) */ void netfs_wake_read_collector(struct netfs_io_request *rreq) { - if (test_bit(NETFS_RREQ_OFFLOAD_COLLECTION, &rreq->flags)) { + if (test_bit(NETFS_RREQ_OFFLOAD_COLLECTION, &rreq->flags) && + !test_bit(NETFS_RREQ_RETRYING, &rreq->flags)) { if (!work_pending(&rreq->work)) { netfs_get_request(rreq, netfs_rreq_trace_get_work); if (!queue_work(system_unbound_wq, &rreq->work)) @@ -586,7 +587,8 @@ void netfs_read_subreq_terminated(struct netfs_io_subrequest *subreq) smp_mb__after_atomic(); /* Clear IN_PROGRESS before task state */ /* If we are at the head of the queue, wake up the collector. */ - if (list_is_first(&subreq->rreq_link, &stream->subrequests)) + if (list_is_first(&subreq->rreq_link, &stream->subrequests) || + test_bit(NETFS_RREQ_RETRYING, &rreq->flags)) netfs_wake_read_collector(rreq); netfs_put_subrequest(subreq, true, netfs_sreq_trace_put_terminated); diff --git a/fs/netfs/read_retry.c b/fs/netfs/read_retry.c index 2290af0d51ac..0f294b26e08c 100644 --- a/fs/netfs/read_retry.c +++ b/fs/netfs/read_retry.c @@ -14,7 +14,7 @@ static void netfs_reissue_read(struct netfs_io_request *rreq, { __clear_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); __set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags); - netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); + netfs_stat(&netfs_n_rh_retry_read_subreq); subreq->rreq->netfs_ops->issue_read(subreq); } @@ -48,6 +48,7 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) __clear_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); subreq->retry_count++; netfs_reset_iter(subreq); + netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); netfs_reissue_read(rreq, subreq); } } @@ -75,7 +76,7 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) struct iov_iter source; unsigned long long start, len; size_t part; - bool boundary = false; + bool boundary = false, subreq_superfluous = false; /* Go through the subreqs and find the next span of contiguous * buffer that we then rejig (cifs, for example, needs the @@ -116,8 +117,10 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) /* Work through the sublist. */ subreq = from; list_for_each_entry_from(subreq, &stream->subrequests, rreq_link) { - if (!len) + if (!len) { + subreq_superfluous = true; break; + } subreq->source = NETFS_DOWNLOAD_FROM_SERVER; subreq->start = start - subreq->transferred; subreq->len = len + subreq->transferred; @@ -154,19 +157,21 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); netfs_reissue_read(rreq, subreq); - if (subreq == to) + if (subreq == to) { + subreq_superfluous = false; break; + } } /* If we managed to use fewer subreqs, we can discard the * excess; if we used the same number, then we're done. */ if (!len) { - if (subreq == to) + if (!subreq_superfluous) continue; list_for_each_entry_safe_from(subreq, tmp, &stream->subrequests, rreq_link) { - trace_netfs_sreq(subreq, netfs_sreq_trace_discard); + trace_netfs_sreq(subreq, netfs_sreq_trace_superfluous); list_del(&subreq->rreq_link); netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_done); if (subreq == to) @@ -187,14 +192,12 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) subreq->source = NETFS_DOWNLOAD_FROM_SERVER; subreq->start = start; subreq->len = len; - subreq->debug_index = atomic_inc_return(&rreq->subreq_counter); subreq->stream_nr = stream->stream_nr; subreq->retry_count = 1; trace_netfs_sreq_ref(rreq->debug_id, subreq->debug_index, refcount_read(&subreq->ref), netfs_sreq_trace_new); - netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); list_add(&subreq->rreq_link, &to->rreq_link); to = list_next_entry(to, rreq_link); @@ -256,14 +259,34 @@ void netfs_retry_reads(struct netfs_io_request *rreq) { struct netfs_io_subrequest *subreq; struct netfs_io_stream *stream = &rreq->io_streams[0]; + DEFINE_WAIT(myself); + + netfs_stat(&netfs_n_rh_retry_read_req); + + set_bit(NETFS_RREQ_RETRYING, &rreq->flags); /* Wait for all outstanding I/O to quiesce before performing retries as * we may need to renegotiate the I/O sizes. */ list_for_each_entry(subreq, &stream->subrequests, rreq_link) { - wait_on_bit(&subreq->flags, NETFS_SREQ_IN_PROGRESS, - TASK_UNINTERRUPTIBLE); + if (!test_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags)) + continue; + + trace_netfs_rreq(rreq, netfs_rreq_trace_wait_queue); + for (;;) { + prepare_to_wait(&rreq->waitq, &myself, TASK_UNINTERRUPTIBLE); + + if (!test_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags)) + break; + + trace_netfs_sreq(subreq, netfs_sreq_trace_wait_for); + schedule(); + trace_netfs_rreq(rreq, netfs_rreq_trace_woke_queue); + } + + finish_wait(&rreq->waitq, &myself); } + clear_bit(NETFS_RREQ_RETRYING, &rreq->flags); trace_netfs_rreq(rreq, netfs_rreq_trace_resubmit); netfs_retry_read_subrequests(rreq); diff --git a/fs/netfs/stats.c b/fs/netfs/stats.c index f1af344266cc..ab6b916addc4 100644 --- a/fs/netfs/stats.c +++ b/fs/netfs/stats.c @@ -29,6 +29,8 @@ atomic_t netfs_n_rh_write_begin; atomic_t netfs_n_rh_write_done; atomic_t netfs_n_rh_write_failed; atomic_t netfs_n_rh_write_zskip; +atomic_t netfs_n_rh_retry_read_req; +atomic_t netfs_n_rh_retry_read_subreq; atomic_t netfs_n_wh_buffered_write; atomic_t netfs_n_wh_writethrough; atomic_t netfs_n_wh_dio_write; @@ -41,6 +43,8 @@ atomic_t netfs_n_wh_upload_failed; atomic_t netfs_n_wh_write; atomic_t netfs_n_wh_write_done; atomic_t netfs_n_wh_write_failed; +atomic_t netfs_n_wh_retry_write_req; +atomic_t netfs_n_wh_retry_write_subreq; atomic_t netfs_n_wb_lock_skip; atomic_t netfs_n_wb_lock_wait; atomic_t netfs_n_folioq; @@ -81,6 +85,11 @@ int netfs_stats_show(struct seq_file *m, void *v) atomic_read(&netfs_n_wh_write), atomic_read(&netfs_n_wh_write_done), atomic_read(&netfs_n_wh_write_failed)); + seq_printf(m, "Retries: rq=%u rs=%u wq=%u ws=%u\n", + atomic_read(&netfs_n_rh_retry_read_req), + atomic_read(&netfs_n_rh_retry_read_subreq), + atomic_read(&netfs_n_wh_retry_write_req), + atomic_read(&netfs_n_wh_retry_write_subreq)); seq_printf(m, "Objs : rr=%u sr=%u foq=%u wsc=%u\n", atomic_read(&netfs_n_rh_rreq), atomic_read(&netfs_n_rh_sreq), diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c index 69727411683e..77279fc5b5a7 100644 --- a/fs/netfs/write_issue.c +++ b/fs/netfs/write_issue.c @@ -253,6 +253,7 @@ void netfs_reissue_write(struct netfs_io_stream *stream, subreq->retry_count++; __clear_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); __set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags); + netfs_stat(&netfs_n_wh_retry_write_subreq); netfs_do_issue_write(stream, subreq); } diff --git a/fs/netfs/write_retry.c b/fs/netfs/write_retry.c index c841a851dd73..545d33079a77 100644 --- a/fs/netfs/write_retry.c +++ b/fs/netfs/write_retry.c @@ -203,6 +203,8 @@ void netfs_retry_writes(struct netfs_io_request *wreq) struct netfs_io_stream *stream; int s; + netfs_stat(&netfs_n_wh_retry_write_req); + /* Wait for all outstanding I/O to quiesce before performing retries as * we may need to renegotiate the I/O sizes. */ diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index a00120a3c099..10d01eb09c43 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -1524,7 +1524,7 @@ int vmcore_add_device_dump(struct vmcoredd_data *data) pr_warn_once("Unexpected adding of device dump\n"); if (vmcore_open) { ret = -EBUSY; - goto out_err; + goto unlock; } list_add_tail(&dump->list, &vmcoredd_list); @@ -1532,6 +1532,9 @@ int vmcore_add_device_dump(struct vmcoredd_data *data) mutex_unlock(&vmcore_mutex); return 0; +unlock: + mutex_unlock(&vmcore_mutex); + out_err: vfree(buf); vfree(dump); diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index ac1f890a0d54..cddeb2adbf4a 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -253,6 +253,7 @@ struct cifs_cred { struct cifs_open_info_data { bool adjust_tz; bool reparse_point; + bool contains_posix_file_info; struct { /* ioctl response buffer */ struct { @@ -1508,7 +1509,6 @@ struct cifs_io_parms { struct cifs_io_request { struct netfs_io_request rreq; struct cifsFileInfo *cfile; - struct TCP_Server_Info *server; pid_t pid; }; @@ -2325,8 +2325,8 @@ struct smb2_compound_vars { struct kvec io_iov[SMB2_IOCTL_IOV_SIZE]; struct kvec si_iov[SMB2_SET_INFO_IOV_SIZE]; struct kvec close_iov; - struct smb2_file_rename_info rename_info; - struct smb2_file_link_info link_info; + struct smb2_file_rename_info_hdr rename_info; + struct smb2_file_link_info_hdr link_info; struct kvec ea_iov; }; diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index 79de2f2f9c41..8582cf61242c 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -147,7 +147,7 @@ static int cifs_prepare_read(struct netfs_io_subrequest *subreq) struct netfs_io_request *rreq = subreq->rreq; struct cifs_io_subrequest *rdata = container_of(subreq, struct cifs_io_subrequest, subreq); struct cifs_io_request *req = container_of(subreq->rreq, struct cifs_io_request, rreq); - struct TCP_Server_Info *server = req->server; + struct TCP_Server_Info *server; struct cifs_sb_info *cifs_sb = CIFS_SB(rreq->inode->i_sb); size_t size; int rc = 0; @@ -156,6 +156,8 @@ static int cifs_prepare_read(struct netfs_io_subrequest *subreq) rdata->xid = get_xid(); rdata->have_xid = true; } + + server = cifs_pick_channel(tlink_tcon(req->cfile->tlink)->ses); rdata->server = server; if (cifs_sb->ctx->rsize == 0) @@ -198,7 +200,7 @@ static void cifs_issue_read(struct netfs_io_subrequest *subreq) struct netfs_io_request *rreq = subreq->rreq; struct cifs_io_subrequest *rdata = container_of(subreq, struct cifs_io_subrequest, subreq); struct cifs_io_request *req = container_of(subreq->rreq, struct cifs_io_request, rreq); - struct TCP_Server_Info *server = req->server; + struct TCP_Server_Info *server = rdata->server; int rc = 0; cifs_dbg(FYI, "%s: op=%08x[%x] mapping=%p len=%zu/%zu\n", @@ -266,7 +268,6 @@ static int cifs_init_request(struct netfs_io_request *rreq, struct file *file) open_file = file->private_data; rreq->netfs_priv = file->private_data; req->cfile = cifsFileInfo_get(open_file); - req->server = cifs_pick_channel(tlink_tcon(req->cfile->tlink)->ses); if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD) req->pid = req->cfile->pid; } else if (rreq->origin != NETFS_WRITEBACK) { diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index 9cc31cf6ebd0..616149c7f0a5 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -1215,6 +1215,19 @@ static int reparse_info_to_fattr(struct cifs_open_info_data *data, rc = server->ops->parse_reparse_point(cifs_sb, full_path, iov, data); + /* + * If the reparse point was not handled but it is the + * name surrogate which points to directory, then treat + * is as a new mount point. Name surrogate reparse point + * represents another named entity in the system. + */ + if (rc == -EOPNOTSUPP && + IS_REPARSE_TAG_NAME_SURROGATE(data->reparse.tag) && + (le32_to_cpu(data->fi.Attributes) & ATTR_DIRECTORY)) { + rc = 0; + cifs_create_junction_fattr(fattr, sb); + goto out; + } } if (data->reparse.tag == IO_REPARSE_TAG_SYMLINK && !rc) { @@ -1408,7 +1421,7 @@ int cifs_get_inode_info(struct inode **inode, struct cifs_fattr fattr = {}; int rc; - if (is_inode_cache_good(*inode)) { + if (!data && is_inode_cache_good(*inode)) { cifs_dbg(FYI, "No need to revalidate cached inode sizes\n"); return 0; } @@ -1507,7 +1520,7 @@ int smb311_posix_get_inode_info(struct inode **inode, struct cifs_fattr fattr = {}; int rc; - if (is_inode_cache_good(*inode)) { + if (!data && is_inode_cache_good(*inode)) { cifs_dbg(FYI, "No need to revalidate cached inode sizes\n"); return 0; } diff --git a/fs/smb/client/reparse.c b/fs/smb/client/reparse.c index 0a5a52a8a7dd..2b9e9885dc42 100644 --- a/fs/smb/client/reparse.c +++ b/fs/smb/client/reparse.c @@ -1088,13 +1088,12 @@ int parse_reparse_point(struct reparse_data_buffer *buf, le32_to_cpu(buf->ReparseTag)); return -EIO; } - break; + return 0; default: cifs_tcon_dbg(VFS | ONCE, "unhandled reparse tag: 0x%08x\n", le32_to_cpu(buf->ReparseTag)); - break; + return -EOPNOTSUPP; } - return 0; } int smb2_parse_reparse_point(struct cifs_sb_info *cifs_sb, diff --git a/fs/smb/client/reparse.h b/fs/smb/client/reparse.h index 5a753fec7e2c..c0be5ab45a78 100644 --- a/fs/smb/client/reparse.h +++ b/fs/smb/client/reparse.h @@ -99,14 +99,30 @@ static inline bool reparse_inode_match(struct inode *inode, static inline bool cifs_open_data_reparse(struct cifs_open_info_data *data) { - struct smb2_file_all_info *fi = &data->fi; - u32 attrs = le32_to_cpu(fi->Attributes); + u32 attrs; bool ret; - ret = data->reparse_point || (attrs & ATTR_REPARSE); - if (ret) - attrs |= ATTR_REPARSE; - fi->Attributes = cpu_to_le32(attrs); + if (data->contains_posix_file_info) { + struct smb311_posix_qinfo *fi = &data->posix_fi; + + attrs = le32_to_cpu(fi->DosAttributes); + if (data->reparse_point) { + attrs |= ATTR_REPARSE; + fi->DosAttributes = cpu_to_le32(attrs); + } + + } else { + struct smb2_file_all_info *fi = &data->fi; + + attrs = le32_to_cpu(fi->Attributes); + if (data->reparse_point) { + attrs |= ATTR_REPARSE; + fi->Attributes = cpu_to_le32(attrs); + } + } + + ret = attrs & ATTR_REPARSE; + return ret; } diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c index 5dfb30b0a852..826b57a5a2a8 100644 --- a/fs/smb/client/smb2inode.c +++ b/fs/smb/client/smb2inode.c @@ -650,6 +650,7 @@ finished: switch (cmds[i]) { case SMB2_OP_QUERY_INFO: idata = in_iov[i].iov_base; + idata->contains_posix_file_info = false; if (rc == 0 && cfile && cfile->symlink_target) { idata->symlink_target = kstrdup(cfile->symlink_target, GFP_KERNEL); if (!idata->symlink_target) @@ -673,6 +674,7 @@ finished: break; case SMB2_OP_POSIX_QUERY_INFO: idata = in_iov[i].iov_base; + idata->contains_posix_file_info = true; if (rc == 0 && cfile && cfile->symlink_target) { idata->symlink_target = kstrdup(cfile->symlink_target, GFP_KERNEL); if (!idata->symlink_target) @@ -770,6 +772,7 @@ finished: idata = in_iov[i].iov_base; idata->reparse.io.iov = *iov; idata->reparse.io.buftype = resp_buftype[i + 1]; + idata->contains_posix_file_info = false; /* BB VERIFY */ rbuf = reparse_buf_ptr(iov); if (IS_ERR(rbuf)) { rc = PTR_ERR(rbuf); @@ -791,6 +794,7 @@ finished: case SMB2_OP_QUERY_WSL_EA: if (!rc) { idata = in_iov[i].iov_base; + idata->contains_posix_file_info = false; qi_rsp = rsp_iov[i + 1].iov_base; data[0] = (u8 *)qi_rsp + le16_to_cpu(qi_rsp->OutputBufferOffset); size[0] = le32_to_cpu(qi_rsp->OutputBufferLength); diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index ec36bed54b0b..23e0c8be7fb5 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -1001,6 +1001,7 @@ static int smb2_query_file_info(const unsigned int xid, struct cifs_tcon *tcon, if (!data->symlink_target) return -ENOMEM; } + data->contains_posix_file_info = false; return SMB2_query_info(xid, tcon, fid->persistent_fid, fid->volatile_fid, &data->fi); } @@ -5146,7 +5147,7 @@ int __cifs_sfu_make_node(unsigned int xid, struct inode *inode, FILE_CREATE, CREATE_NOT_DIR | CREATE_OPTION_SPECIAL, ACL_NO_MODE); oparms.fid = &fid; - + idata.contains_posix_file_info = false; rc = server->ops->open(xid, &oparms, &oplock, &idata); if (rc) goto out; diff --git a/fs/smb/common/smb2pdu.h b/fs/smb/common/smb2pdu.h index 3336df2ea5d4..c7a0efda4403 100644 --- a/fs/smb/common/smb2pdu.h +++ b/fs/smb/common/smb2pdu.h @@ -1707,23 +1707,33 @@ struct smb2_file_internal_info { } __packed; /* level 6 Query */ struct smb2_file_rename_info { /* encoding of request for level 10 */ - __u8 ReplaceIfExists; /* 1 = replace existing target with new */ - /* 0 = fail if target already exists */ - __u8 Reserved[7]; - __u64 RootDirectory; /* MBZ for network operations (why says spec?) */ - __le32 FileNameLength; + /* New members MUST be added within the struct_group() macro below. */ + __struct_group(smb2_file_rename_info_hdr, __hdr, __packed, + __u8 ReplaceIfExists; /* 1 = replace existing target with new */ + /* 0 = fail if target already exists */ + __u8 Reserved[7]; + __u64 RootDirectory; /* MBZ for network operations (why says spec?) */ + __le32 FileNameLength; + ); char FileName[]; /* New name to be assigned */ /* padding - overall struct size must be >= 24 so filename + pad >= 6 */ } __packed; /* level 10 Set */ +static_assert(offsetof(struct smb2_file_rename_info, FileName) == sizeof(struct smb2_file_rename_info_hdr), + "struct member likely outside of __struct_group()"); struct smb2_file_link_info { /* encoding of request for level 11 */ - __u8 ReplaceIfExists; /* 1 = replace existing link with new */ - /* 0 = fail if link already exists */ - __u8 Reserved[7]; - __u64 RootDirectory; /* MBZ for network operations (why says spec?) */ - __le32 FileNameLength; + /* New members MUST be added within the struct_group() macro below. */ + __struct_group(smb2_file_link_info_hdr, __hdr, __packed, + __u8 ReplaceIfExists; /* 1 = replace existing link with new */ + /* 0 = fail if link already exists */ + __u8 Reserved[7]; + __u64 RootDirectory; /* MBZ for network operations (why says spec?) */ + __le32 FileNameLength; + ); char FileName[]; /* Name to be assigned to new link */ } __packed; /* level 11 Set */ +static_assert(offsetof(struct smb2_file_link_info, FileName) == sizeof(struct smb2_file_link_info_hdr), + "struct member likely outside of __struct_group()"); /* * This level 18, although with struct with same name is different from cifs diff --git a/fs/smb/common/smbfsctl.h b/fs/smb/common/smbfsctl.h index 4b379e84c46b..3253a18ecb5c 100644 --- a/fs/smb/common/smbfsctl.h +++ b/fs/smb/common/smbfsctl.h @@ -159,6 +159,9 @@ #define IO_REPARSE_TAG_LX_CHR 0x80000025 #define IO_REPARSE_TAG_LX_BLK 0x80000026 +/* If Name Surrogate Bit is set, the file or directory represents another named entity in the system. */ +#define IS_REPARSE_TAG_NAME_SURROGATE(tag) (!!((tag) & 0x20000000)) + /* fsctl flags */ /* If Flags is set to this value, the request is an FSCTL not ioctl request */ #define SMB2_0_IOCTL_IS_FSCTL 0x00000001 diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h index bdcd40f0ec74..19877d99f255 100644 --- a/fs/xfs/scrub/common.h +++ b/fs/xfs/scrub/common.h @@ -224,7 +224,6 @@ static inline bool xchk_skip_xref(struct xfs_scrub_metadata *sm) bool xchk_dir_looks_zapped(struct xfs_inode *dp); bool xchk_pptr_looks_zapped(struct xfs_inode *ip); -#ifdef CONFIG_XFS_ONLINE_REPAIR /* Decide if a repair is required. */ static inline bool xchk_needs_repair(const struct xfs_scrub_metadata *sm) { @@ -244,10 +243,6 @@ static inline bool xchk_could_repair(const struct xfs_scrub *sc) return (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR) && !(sc->flags & XREP_ALREADY_FIXED); } -#else -# define xchk_needs_repair(sc) (false) -# define xchk_could_repair(sc) (false) -#endif /* CONFIG_XFS_ONLINE_REPAIR */ int xchk_metadata_inode_forks(struct xfs_scrub *sc); diff --git a/fs/xfs/scrub/inode_repair.c b/fs/xfs/scrub/inode_repair.c index 2f641b6d663e..13ff1c933cb8 100644 --- a/fs/xfs/scrub/inode_repair.c +++ b/fs/xfs/scrub/inode_repair.c @@ -1055,9 +1055,17 @@ xrep_dinode_check_dfork( return true; break; case S_IFREG: - if (fmt == XFS_DINODE_FMT_LOCAL) + switch (fmt) { + case XFS_DINODE_FMT_LOCAL: return true; - fallthrough; + case XFS_DINODE_FMT_EXTENTS: + case XFS_DINODE_FMT_BTREE: + case XFS_DINODE_FMT_META_BTREE: + break; + default: + return true; + } + break; case S_IFLNK: case S_IFDIR: switch (fmt) { diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h index 823c00d1a502..af0a3a9e5ed9 100644 --- a/fs/xfs/scrub/repair.h +++ b/fs/xfs/scrub/repair.h @@ -191,7 +191,16 @@ int xrep_reset_metafile_resv(struct xfs_scrub *sc); #else #define xrep_ino_dqattach(sc) (0) -#define xrep_will_attempt(sc) (false) + +/* + * When online repair is not built into the kernel, we still want to attempt + * the repair so that the stub xrep_attempt below will return EOPNOTSUPP. + */ +static inline bool xrep_will_attempt(const struct xfs_scrub *sc) +{ + return (sc->sm->sm_flags & XFS_SCRUB_IFLAG_FORCE_REBUILD) || + xchk_needs_repair(sc->sm); +} static inline int xrep_attempt( diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c index 7567dd5cad14..6fa9e3e5bab7 100644 --- a/fs/xfs/scrub/scrub.c +++ b/fs/xfs/scrub/scrub.c @@ -149,6 +149,18 @@ xchk_probe( if (xchk_should_terminate(sc, &error)) return error; + /* + * If the caller is probing to see if repair works but repair isn't + * built into the kernel, return EOPNOTSUPP because that's the signal + * that userspace expects. If online repair is built in, set the + * CORRUPT flag (without any of the usual tracing/logging) to force us + * into xrep_probe. + */ + if (xchk_could_repair(sc)) { + if (!IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR)) + return -EOPNOTSUPP; + sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT; + } return 0; } diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 67877c36ed11..6d9965b546cb 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -19,6 +19,7 @@ #include "xfs_reflink.h" #include "xfs_errortag.h" #include "xfs_error.h" +#include "xfs_icache.h" struct xfs_writepage_ctx { struct iomap_writepage_ctx ctx; @@ -528,12 +529,44 @@ xfs_vm_readahead( } static int -xfs_iomap_swapfile_activate( +xfs_vm_swap_activate( struct swap_info_struct *sis, struct file *swap_file, sector_t *span) { - sis->bdev = xfs_inode_buftarg(XFS_I(file_inode(swap_file)))->bt_bdev; + struct xfs_inode *ip = XFS_I(file_inode(swap_file)); + + /* + * Swap file activation can race against concurrent shared extent + * removal in files that have been cloned. If this happens, + * iomap_swapfile_iter() can fail because it encountered a shared + * extent even though an operation is in progress to remove those + * shared extents. + * + * This race becomes problematic when we defer extent removal + * operations beyond the end of a syscall (i.e. use async background + * processing algorithms). Users think the extents are no longer + * shared, but iomap_swapfile_iter() still sees them as shared + * because the refcountbt entries for the extents being removed have + * not yet been updated. Hence the swapon call fails unexpectedly. + * + * The race condition is currently most obvious from the unlink() + * operation as extent removal is deferred until after the last + * reference to the inode goes away. We then process the extent + * removal asynchronously, hence triggers the "syscall completed but + * work not done" condition mentioned above. To close this race + * window, we need to flush any pending inodegc operations to ensure + * they have updated the refcountbt records before we try to map the + * swapfile. + */ + xfs_inodegc_flush(ip->i_mount); + + /* + * Direct the swap code to the correct block device when this file + * sits on the RT device. + */ + sis->bdev = xfs_inode_buftarg(ip)->bt_bdev; + return iomap_swapfile_activate(sis, swap_file, span, &xfs_read_iomap_ops); } @@ -549,11 +582,11 @@ const struct address_space_operations xfs_address_space_operations = { .migrate_folio = filemap_migrate_folio, .is_partially_uptodate = iomap_is_partially_uptodate, .error_remove_folio = generic_error_remove_folio, - .swap_activate = xfs_iomap_swapfile_activate, + .swap_activate = xfs_vm_swap_activate, }; const struct address_space_operations xfs_dax_aops = { .writepages = xfs_dax_writepages, .dirty_folio = noop_dirty_folio, - .swap_activate = xfs_iomap_swapfile_activate, + .swap_activate = xfs_vm_swap_activate, }; diff --git a/fs/xfs/xfs_qm_bhv.c b/fs/xfs/xfs_qm_bhv.c index 37f1230e7584..245d754f382a 100644 --- a/fs/xfs/xfs_qm_bhv.c +++ b/fs/xfs/xfs_qm_bhv.c @@ -78,6 +78,28 @@ xfs_qm_statvfs( } } +STATIC int +xfs_qm_validate_state_change( + struct xfs_mount *mp, + uint uqd, + uint gqd, + uint pqd) +{ + int state; + + /* Is quota state changing? */ + state = ((uqd && !XFS_IS_UQUOTA_ON(mp)) || + (!uqd && XFS_IS_UQUOTA_ON(mp)) || + (gqd && !XFS_IS_GQUOTA_ON(mp)) || + (!gqd && XFS_IS_GQUOTA_ON(mp)) || + (pqd && !XFS_IS_PQUOTA_ON(mp)) || + (!pqd && XFS_IS_PQUOTA_ON(mp))); + + return state && + (xfs_dev_is_read_only(mp, "changing quota state") || + xfs_has_norecovery(mp)); +} + int xfs_qm_newmount( xfs_mount_t *mp, @@ -97,24 +119,25 @@ xfs_qm_newmount( } /* - * If the device itself is read-only, we can't allow - * the user to change the state of quota on the mount - - * this would generate a transaction on the ro device, - * which would lead to an I/O error and shutdown + * If the device itself is read-only and/or in norecovery + * mode, we can't allow the user to change the state of + * quota on the mount - this would generate a transaction + * on the ro device, which would lead to an I/O error and + * shutdown. */ - if (((uquotaondisk && !XFS_IS_UQUOTA_ON(mp)) || - (!uquotaondisk && XFS_IS_UQUOTA_ON(mp)) || - (gquotaondisk && !XFS_IS_GQUOTA_ON(mp)) || - (!gquotaondisk && XFS_IS_GQUOTA_ON(mp)) || - (pquotaondisk && !XFS_IS_PQUOTA_ON(mp)) || - (!pquotaondisk && XFS_IS_PQUOTA_ON(mp))) && - xfs_dev_is_read_only(mp, "changing quota state")) { - xfs_warn(mp, "please mount with%s%s%s%s.", - (!quotaondisk ? "out quota" : ""), - (uquotaondisk ? " usrquota" : ""), - (gquotaondisk ? " grpquota" : ""), - (pquotaondisk ? " prjquota" : "")); + if (xfs_qm_validate_state_change(mp, uquotaondisk, + gquotaondisk, pquotaondisk)) { + + if (xfs_has_metadir(mp)) + xfs_warn(mp, + "metadir enabled, please mount without any quota mount options"); + else + xfs_warn(mp, "please mount with%s%s%s%s.", + (!quotaondisk ? "out quota" : ""), + (uquotaondisk ? " usrquota" : ""), + (gquotaondisk ? " grpquota" : ""), + (pquotaondisk ? " prjquota" : "")); return -EPERM; } diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index d92d7a07ea89..0055066fb1d9 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1661,8 +1661,12 @@ xfs_fs_fill_super( #endif } - /* Filesystem claims it needs repair, so refuse the mount. */ - if (xfs_has_needsrepair(mp)) { + /* + * Filesystem claims it needs repair, so refuse the mount unless + * norecovery is also specified, in which case the filesystem can + * be mounted with no risk of further damage. + */ + if (xfs_has_needsrepair(mp) && !xfs_has_norecovery(mp)) { xfs_warn(mp, "Filesystem needs repair. Please run xfs_repair."); error = -EFSCORRUPTED; goto out_free_sb; diff --git a/include/drm/display/drm_dp.h b/include/drm/display/drm_dp.h index a6f8b098c56f..3bd9f482f0c3 100644 --- a/include/drm/display/drm_dp.h +++ b/include/drm/display/drm_dp.h @@ -359,6 +359,7 @@ # define DP_DSC_BITS_PER_PIXEL_1_4 0x2 # define DP_DSC_BITS_PER_PIXEL_1_2 0x3 # define DP_DSC_BITS_PER_PIXEL_1_1 0x4 +# define DP_DSC_BITS_PER_PIXEL_MASK 0x7 #define DP_PSR_SUPPORT 0x070 /* XXX 1.2? */ # define DP_PSR_IS_SUPPORTED 1 diff --git a/include/dt-bindings/clock/qcom,qcs8300-camcc.h b/include/dt-bindings/clock/qcom,qcs8300-camcc.h new file mode 100644 index 000000000000..fc535c847859 --- /dev/null +++ b/include/dt-bindings/clock/qcom,qcs8300-camcc.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (c) 2024, Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#ifndef _DT_BINDINGS_CLK_QCOM_QCS8300_CAM_CC_H +#define _DT_BINDINGS_CLK_QCOM_QCS8300_CAM_CC_H + +#include "qcom,sa8775p-camcc.h" + +/* QCS8300 introduces below new clocks compared to SA8775P */ + +/* CAM_CC clocks */ +#define CAM_CC_TITAN_TOP_ACCU_SHIFT_CLK 86 + +#endif diff --git a/include/dt-bindings/clock/qcom,qcs8300-gpucc.h b/include/dt-bindings/clock/qcom,qcs8300-gpucc.h new file mode 100644 index 000000000000..afa187467b4c --- /dev/null +++ b/include/dt-bindings/clock/qcom,qcs8300-gpucc.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (c) 2024, Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#ifndef _DT_BINDINGS_CLK_QCOM_GPUCC_QCS8300_H +#define _DT_BINDINGS_CLK_QCOM_GPUCC_QCS8300_H + +#include "qcom,sa8775p-gpucc.h" + +/* QCS8300 introduces below new clocks compared to SA8775P */ + +/* GPU_CC clocks */ +#define GPU_CC_CX_ACCU_SHIFT_CLK 23 +#define GPU_CC_GX_ACCU_SHIFT_CLK 24 + +#endif diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index 13a11f3c09b8..4811b9a14604 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -154,7 +154,10 @@ enum virtchnl_ops { VIRTCHNL_OP_DISABLE_VLAN_STRIPPING_V2 = 55, VIRTCHNL_OP_ENABLE_VLAN_INSERTION_V2 = 56, VIRTCHNL_OP_DISABLE_VLAN_INSERTION_V2 = 57, - /* opcode 57 - 65 are reserved */ + /* opcode 58 and 59 are reserved */ + VIRTCHNL_OP_1588_PTP_GET_CAPS = 60, + VIRTCHNL_OP_1588_PTP_GET_TIME = 61, + /* opcode 62 - 65 are reserved */ VIRTCHNL_OP_GET_QOS_CAPS = 66, /* opcode 68 through 111 are reserved */ VIRTCHNL_OP_CONFIG_QUEUE_BW = 112, @@ -270,6 +273,7 @@ VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vsi_resource); #define VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF BIT(27) #define VIRTCHNL_VF_OFFLOAD_FDIR_PF BIT(28) #define VIRTCHNL_VF_OFFLOAD_QOS BIT(29) +#define VIRTCHNL_VF_CAP_PTP BIT(31) #define VF_BASE_MODE_OFFLOADS (VIRTCHNL_VF_OFFLOAD_L2 | \ VIRTCHNL_VF_OFFLOAD_VLAN | \ @@ -309,6 +313,60 @@ struct virtchnl_txq_info { VIRTCHNL_CHECK_STRUCT_LEN(24, virtchnl_txq_info); +/* RX descriptor IDs (range from 0 to 63) */ +enum virtchnl_rx_desc_ids { + VIRTCHNL_RXDID_0_16B_BASE = 0, + VIRTCHNL_RXDID_1_32B_BASE = 1, + VIRTCHNL_RXDID_2_FLEX_SQ_NIC = 2, + VIRTCHNL_RXDID_3_FLEX_SQ_SW = 3, + VIRTCHNL_RXDID_4_FLEX_SQ_NIC_VEB = 4, + VIRTCHNL_RXDID_5_FLEX_SQ_NIC_ACL = 5, + VIRTCHNL_RXDID_6_FLEX_SQ_NIC_2 = 6, + VIRTCHNL_RXDID_7_HW_RSVD = 7, + /* 8 through 15 are reserved */ + VIRTCHNL_RXDID_16_COMMS_GENERIC = 16, + VIRTCHNL_RXDID_17_COMMS_AUX_VLAN = 17, + VIRTCHNL_RXDID_18_COMMS_AUX_IPV4 = 18, + VIRTCHNL_RXDID_19_COMMS_AUX_IPV6 = 19, + VIRTCHNL_RXDID_20_COMMS_AUX_FLOW = 20, + VIRTCHNL_RXDID_21_COMMS_AUX_TCP = 21, + /* 22 through 63 are reserved */ +}; + +#define VIRTCHNL_RXDID_BIT(x) BIT_ULL(VIRTCHNL_RXDID_##x) + +/* RX descriptor ID bitmasks */ +enum virtchnl_rx_desc_id_bitmasks { + VIRTCHNL_RXDID_0_16B_BASE_M = VIRTCHNL_RXDID_BIT(0_16B_BASE), + VIRTCHNL_RXDID_1_32B_BASE_M = VIRTCHNL_RXDID_BIT(1_32B_BASE), + VIRTCHNL_RXDID_2_FLEX_SQ_NIC_M = VIRTCHNL_RXDID_BIT(2_FLEX_SQ_NIC), + VIRTCHNL_RXDID_3_FLEX_SQ_SW_M = VIRTCHNL_RXDID_BIT(3_FLEX_SQ_SW), + VIRTCHNL_RXDID_4_FLEX_SQ_NIC_VEB_M = VIRTCHNL_RXDID_BIT(4_FLEX_SQ_NIC_VEB), + VIRTCHNL_RXDID_5_FLEX_SQ_NIC_ACL_M = VIRTCHNL_RXDID_BIT(5_FLEX_SQ_NIC_ACL), + VIRTCHNL_RXDID_6_FLEX_SQ_NIC_2_M = VIRTCHNL_RXDID_BIT(6_FLEX_SQ_NIC_2), + VIRTCHNL_RXDID_7_HW_RSVD_M = VIRTCHNL_RXDID_BIT(7_HW_RSVD), + /* 8 through 15 are reserved */ + VIRTCHNL_RXDID_16_COMMS_GENERIC_M = VIRTCHNL_RXDID_BIT(16_COMMS_GENERIC), + VIRTCHNL_RXDID_17_COMMS_AUX_VLAN_M = VIRTCHNL_RXDID_BIT(17_COMMS_AUX_VLAN), + VIRTCHNL_RXDID_18_COMMS_AUX_IPV4_M = VIRTCHNL_RXDID_BIT(18_COMMS_AUX_IPV4), + VIRTCHNL_RXDID_19_COMMS_AUX_IPV6_M = VIRTCHNL_RXDID_BIT(19_COMMS_AUX_IPV6), + VIRTCHNL_RXDID_20_COMMS_AUX_FLOW_M = VIRTCHNL_RXDID_BIT(20_COMMS_AUX_FLOW), + VIRTCHNL_RXDID_21_COMMS_AUX_TCP_M = VIRTCHNL_RXDID_BIT(21_COMMS_AUX_TCP), + /* 22 through 63 are reserved */ +}; + +/* virtchnl_rxq_info_flags - definition of bits in the flags field of the + * virtchnl_rxq_info structure. + * + * @VIRTCHNL_PTP_RX_TSTAMP: request to enable Rx timestamping + * + * Other flag bits are currently reserved and they may be extended in the + * future. + */ +enum virtchnl_rxq_info_flags { + VIRTCHNL_PTP_RX_TSTAMP = BIT(0), +}; + /* VIRTCHNL_OP_CONFIG_RX_QUEUE * VF sends this message to set up parameters for one RX queue. * External data buffer contains one instance of virtchnl_rxq_info. @@ -331,8 +389,14 @@ struct virtchnl_rxq_info { u32 databuffer_size; u32 max_pkt_size; u8 crc_disable; - u8 rxdid; - u8 pad1[2]; + /* see enum virtchnl_rx_desc_ids; + * only used when VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC is supported. Note + * that when the offload is not supported, the descriptor format aligns + * with VIRTCHNL_RXDID_1_32B_BASE. + */ + enum virtchnl_rx_desc_ids rxdid:8; + enum virtchnl_rxq_info_flags flags:8; /* see virtchnl_rxq_info_flags */ + u8 pad1; u64 dma_ring_addr; /* see enum virtchnl_rx_hsplit; deprecated with AVF 1.0 */ @@ -1032,10 +1096,6 @@ struct virtchnl_filter { VIRTCHNL_CHECK_STRUCT_LEN(272, virtchnl_filter); -struct virtchnl_supported_rxdids { - u64 supported_rxdids; -}; - /* VIRTCHNL_OP_EVENT * PF sends this message to inform the VF driver of events that may affect it. * No direct response is expected from the VF, though it may generate other @@ -1425,6 +1485,61 @@ struct virtchnl_fdir_del { VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_fdir_del); +#define VIRTCHNL_1588_PTP_CAP_RX_TSTAMP BIT(1) +#define VIRTCHNL_1588_PTP_CAP_READ_PHC BIT(2) + +/** + * struct virtchnl_ptp_caps - Defines the PTP caps available to the VF. + * @caps: On send, VF sets what capabilities it requests. On reply, PF + * indicates what has been enabled for this VF. The PF shall not set + * bits which were not requested by the VF. + * @rsvd: Reserved bits for future extension. + * + * Structure that defines the PTP capabilities available to the VF. The VF + * sends VIRTCHNL_OP_1588_PTP_GET_CAPS, and must fill in the ptp_caps field + * indicating what capabilities it is requesting. The PF will respond with the + * same message with the virtchnl_ptp_caps structure indicating what is + * enabled for the VF. + * + * VIRTCHNL_1588_PTP_CAP_RX_TSTAMP indicates that the VF receive queues have + * receive timestamps enabled in the flexible descriptors. Note that this + * requires a VF to also negotiate to enable advanced flexible descriptors in + * the receive path instead of the default legacy descriptor format. + * + * VIRTCHNL_1588_PTP_CAP_READ_PHC indicates that the VF may read the PHC time + * via the VIRTCHNL_OP_1588_PTP_GET_TIME command. + * + * Note that in the future, additional capability flags may be added which + * indicate additional extended support. All fields marked as reserved by this + * header will be set to zero. VF implementations should verify this to ensure + * that future extensions do not break compatibility. + */ +struct virtchnl_ptp_caps { + u32 caps; + u8 rsvd[44]; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(48, virtchnl_ptp_caps); + +/** + * struct virtchnl_phc_time - Contains the 64bits of PHC clock time in ns. + * @time: PHC time in nanoseconds + * @rsvd: Reserved for future extension + * + * Structure received with VIRTCHNL_OP_1588_PTP_GET_TIME. Contains the 64bits + * of PHC clock time in nanoseconds. + * + * VIRTCHNL_OP_1588_PTP_GET_TIME may be sent to request the current time of + * the PHC. This op is available in case direct access via the PHC registers + * is not available. + */ +struct virtchnl_phc_time { + u64 time; + u8 rsvd[8]; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_phc_time); + struct virtchnl_shaper_bw { /* Unit is Kbps */ u32 committed; @@ -1757,6 +1872,12 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode, } } break; + case VIRTCHNL_OP_1588_PTP_GET_CAPS: + valid_len = sizeof(struct virtchnl_ptp_caps); + break; + case VIRTCHNL_OP_1588_PTP_GET_TIME: + valid_len = sizeof(struct virtchnl_phc_time); + break; /* These are always errors coming from the VF. */ case VIRTCHNL_OP_EVENT: case VIRTCHNL_OP_UNKNOWN: diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 9ebb53f031cd..fa2a76cc2f73 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -861,12 +861,22 @@ static inline bool blk_mq_add_to_batch(struct request *req, void (*complete)(struct io_comp_batch *)) { /* - * blk_mq_end_request_batch() can't end request allocated from - * sched tags + * Check various conditions that exclude batch processing: + * 1) No batch container + * 2) Has scheduler data attached + * 3) Not a passthrough request and end_io set + * 4) Not a passthrough request and an ioerror */ - if (!iob || (req->rq_flags & RQF_SCHED_TAGS) || ioerror || - (req->end_io && !blk_rq_is_passthrough(req))) + if (!iob) return false; + if (req->rq_flags & RQF_SCHED_TAGS) + return false; + if (!blk_rq_is_passthrough(req)) { + if (req->end_io) + return false; + if (ioerror < 0) + return false; + } if (!iob->complete) iob->complete = complete; diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 1b20d2d8ef7c..17960a1e858d 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -71,9 +71,6 @@ enum { /* Cgroup is frozen. */ CGRP_FROZEN, - - /* Control group has to be killed. */ - CGRP_KILL, }; /* cgroup_root->flags */ @@ -461,6 +458,9 @@ struct cgroup { int nr_threaded_children; /* # of live threaded child cgroups */ + /* sequence number for cgroup.kill, serialized by css_set_lock. */ + unsigned int kill_seq; + struct kernfs_node *kn; /* cgroup kernfs entry */ struct cgroup_file procs_file; /* handle for "cgroup.procs" */ struct cgroup_file events_file; /* handle for "cgroup.events" */ diff --git a/include/linux/device/faux.h b/include/linux/device/faux.h new file mode 100644 index 000000000000..9f43c0e46aa4 --- /dev/null +++ b/include/linux/device/faux.h @@ -0,0 +1,69 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2025 Greg Kroah-Hartman <gregkh@linuxfoundation.org> + * Copyright (c) 2025 The Linux Foundation + * + * A "simple" faux bus that allows devices to be created and added + * automatically to it. This is to be used whenever you need to create a + * device that is not associated with any "real" system resources, and do + * not want to have to deal with a bus/driver binding logic. It is + * intended to be very simple, with only a create and a destroy function + * available. + */ +#ifndef _FAUX_DEVICE_H_ +#define _FAUX_DEVICE_H_ + +#include <linux/container_of.h> +#include <linux/device.h> + +/** + * struct faux_device - a "faux" device + * @dev: internal struct device of the object + * + * A simple faux device that can be created/destroyed. To be used when a + * driver only needs to have a device to "hang" something off. This can be + * used for downloading firmware or other basic tasks. Use this instead of + * a struct platform_device if the device has no resources assigned to + * it at all. + */ +struct faux_device { + struct device dev; +}; +#define to_faux_device(x) container_of_const((x), struct faux_device, dev) + +/** + * struct faux_device_ops - a set of callbacks for a struct faux_device + * @probe: called when a faux device is probed by the driver core + * before the device is fully bound to the internal faux bus + * code. If probe succeeds, return 0, otherwise return a + * negative error number to stop the probe sequence from + * succeeding. + * @remove: called when a faux device is removed from the system + * + * Both @probe and @remove are optional, if not needed, set to NULL. + */ +struct faux_device_ops { + int (*probe)(struct faux_device *faux_dev); + void (*remove)(struct faux_device *faux_dev); +}; + +struct faux_device *faux_device_create(const char *name, + struct device *parent, + const struct faux_device_ops *faux_ops); +struct faux_device *faux_device_create_with_groups(const char *name, + struct device *parent, + const struct faux_device_ops *faux_ops, + const struct attribute_group **groups); +void faux_device_destroy(struct faux_device *faux_dev); + +static inline void *faux_device_get_drvdata(const struct faux_device *faux_dev) +{ + return dev_get_drvdata(&faux_dev->dev); +} + +static inline void faux_device_set_drvdata(struct faux_device *faux_dev, void *data) +{ + dev_set_drvdata(&faux_dev->dev, data); +} + +#endif /* _FAUX_DEVICE_H_ */ diff --git a/include/linux/efi.h b/include/linux/efi.h index 053c57e61869..7d63d1d75f22 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -114,21 +114,22 @@ typedef struct { #define EFI_MAX_MEMORY_TYPE 16 /* Attribute values: */ -#define EFI_MEMORY_UC ((u64)0x0000000000000001ULL) /* uncached */ -#define EFI_MEMORY_WC ((u64)0x0000000000000002ULL) /* write-coalescing */ -#define EFI_MEMORY_WT ((u64)0x0000000000000004ULL) /* write-through */ -#define EFI_MEMORY_WB ((u64)0x0000000000000008ULL) /* write-back */ -#define EFI_MEMORY_UCE ((u64)0x0000000000000010ULL) /* uncached, exported */ -#define EFI_MEMORY_WP ((u64)0x0000000000001000ULL) /* write-protect */ -#define EFI_MEMORY_RP ((u64)0x0000000000002000ULL) /* read-protect */ -#define EFI_MEMORY_XP ((u64)0x0000000000004000ULL) /* execute-protect */ -#define EFI_MEMORY_NV ((u64)0x0000000000008000ULL) /* non-volatile */ -#define EFI_MEMORY_MORE_RELIABLE \ - ((u64)0x0000000000010000ULL) /* higher reliability */ -#define EFI_MEMORY_RO ((u64)0x0000000000020000ULL) /* read-only */ -#define EFI_MEMORY_SP ((u64)0x0000000000040000ULL) /* soft reserved */ -#define EFI_MEMORY_CPU_CRYPTO ((u64)0x0000000000080000ULL) /* supports encryption */ -#define EFI_MEMORY_RUNTIME ((u64)0x8000000000000000ULL) /* range requires runtime mapping */ +#define EFI_MEMORY_UC BIT_ULL(0) /* uncached */ +#define EFI_MEMORY_WC BIT_ULL(1) /* write-coalescing */ +#define EFI_MEMORY_WT BIT_ULL(2) /* write-through */ +#define EFI_MEMORY_WB BIT_ULL(3) /* write-back */ +#define EFI_MEMORY_UCE BIT_ULL(4) /* uncached, exported */ +#define EFI_MEMORY_WP BIT_ULL(12) /* write-protect */ +#define EFI_MEMORY_RP BIT_ULL(13) /* read-protect */ +#define EFI_MEMORY_XP BIT_ULL(14) /* execute-protect */ +#define EFI_MEMORY_NV BIT_ULL(15) /* non-volatile */ +#define EFI_MEMORY_MORE_RELIABLE BIT_ULL(16) /* higher reliability */ +#define EFI_MEMORY_RO BIT_ULL(17) /* read-only */ +#define EFI_MEMORY_SP BIT_ULL(18) /* soft reserved */ +#define EFI_MEMORY_CPU_CRYPTO BIT_ULL(19) /* supports encryption */ +#define EFI_MEMORY_HOT_PLUGGABLE BIT_ULL(20) /* supports unplugging at runtime */ +#define EFI_MEMORY_RUNTIME BIT_ULL(63) /* range requires runtime mapping */ + #define EFI_MEMORY_DESCRIPTOR_VERSION 1 #define EFI_PAGE_SHIFT 12 diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index 523025106a64..0f7281e3e448 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -59,8 +59,10 @@ static inline void macvlan_count_rx(const struct macvlan_dev *vlan, extern void macvlan_common_setup(struct net_device *dev); -extern int macvlan_common_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +struct rtnl_newlink_params; + +extern int macvlan_common_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack); extern void macvlan_dellink(struct net_device *dev, struct list_head *head); diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 87edb7a8173b..f016263e1fcf 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -1135,7 +1135,7 @@ int mlx4_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt, int mlx4_buf_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt, struct mlx4_buf *buf); -int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, int order); +int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, unsigned int order); void mlx4_db_free(struct mlx4_dev *dev, struct mlx4_db *db); int mlx4_alloc_hwq_res(struct mlx4_dev *dev, struct mlx4_hwq_resources *wqres, diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index fccc03cd2164..9a387d456592 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3276,6 +3276,8 @@ static inline struct net_device *first_net_device_rcu(struct net *net) } int netdev_boot_setup_check(struct net_device *dev); +struct net_device *dev_getbyhwaddr(struct net *net, unsigned short type, + const char *hwaddr); struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type, const char *hwaddr); struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type); @@ -4116,7 +4118,6 @@ void netif_receive_skb_list(struct list_head *head); gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb); void napi_gro_flush(struct napi_struct *napi, bool flush_old); struct sk_buff *napi_get_frags(struct napi_struct *napi); -void napi_get_frags_check(struct napi_struct *napi); gro_result_t napi_gro_frags(struct napi_struct *napi); static inline void napi_free_frags(struct napi_struct *napi) diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 071d05d81d38..c86a11cfc4a3 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -278,7 +278,7 @@ struct netfs_io_request { #define NETFS_RREQ_PAUSE 11 /* Pause subrequest generation */ #define NETFS_RREQ_USE_IO_ITER 12 /* Use ->io_iter rather than ->i_pages */ #define NETFS_RREQ_ALL_QUEUED 13 /* All subreqs are now queued */ -#define NETFS_RREQ_NEED_RETRY 14 /* Need to try retrying */ +#define NETFS_RREQ_RETRYING 14 /* Set if we're in the retry path */ #define NETFS_RREQ_USE_PGPRIV2 31 /* [DEPRECATED] Use PG_private_2 to mark * write to cache on read */ const struct netfs_request_ops *netfs_ops; diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index de5deb1a0118..1a2594a38199 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -3134,6 +3134,7 @@ #define PCI_DEVICE_ID_INTEL_HDA_LNL_P 0xa828 #define PCI_DEVICE_ID_INTEL_S21152BB 0xb152 #define PCI_DEVICE_ID_INTEL_HDA_BMG 0xe2f7 +#define PCI_DEVICE_ID_INTEL_HDA_PTL_H 0xe328 #define PCI_DEVICE_ID_INTEL_HDA_PTL 0xe428 #define PCI_DEVICE_ID_INTEL_HDA_CML_R 0xf0c8 #define PCI_DEVICE_ID_INTEL_HDA_RKL_S 0xf1c8 diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index 733f4ddd2ef1..e40f554ff717 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -50,8 +50,7 @@ struct dw_xpcs; struct phylink_pcs *xpcs_to_phylink_pcs(struct dw_xpcs *xpcs); int xpcs_get_an_mode(struct dw_xpcs *xpcs, phy_interface_t interface); -int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns, - int enable); +void xpcs_config_eee_mult_fact(struct dw_xpcs *xpcs, u8 mult_fact); struct dw_xpcs *xpcs_create_mdiodev(struct mii_bus *bus, int addr); struct dw_xpcs *xpcs_create_fwnode(struct fwnode_handle *fwnode); void xpcs_destroy(struct dw_xpcs *xpcs); diff --git a/include/linux/phy.h b/include/linux/phy.h index 64982eba71d1..13be48d3b8b3 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -37,10 +37,7 @@ 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; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_fibre_features) __ro_after_init; -extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_all_ports_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_features) __ro_after_init; -extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_fec_features) __ro_after_init; -extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_full_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_eee_cap1_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_eee_cap2_features) __ro_after_init; @@ -54,11 +51,6 @@ extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_eee_cap2_features) __ro_after_init; #define PHY_EEE_CAP2_FEATURES ((unsigned long *)&phy_eee_cap2_features) extern const int phy_basic_ports_array[3]; -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]; -extern const int phy_gbit_features_array[2]; -extern const int phy_10gbit_features_array[1]; /* * Set phydev->irq to PHY_POLL if interrupts are not supported, @@ -1287,9 +1279,6 @@ struct phy_driver { #define to_phy_driver(d) container_of_const(to_mdio_common_driver(d), \ struct phy_driver, mdiodrv) -#define PHY_ANY_ID "MATCH ANY PHY" -#define PHY_ANY_UID 0xffffffff - #define PHY_ID_MATCH_EXACT(id) .phy_id = (id), .phy_id_mask = GENMASK(31, 0) #define PHY_ID_MATCH_MODEL(id) .phy_id = (id), .phy_id_mask = GENMASK(31, 4) #define PHY_ID_MATCH_VENDOR(id) .phy_id = (id), .phy_id_mask = GENMASK(31, 10) @@ -1322,15 +1311,6 @@ static inline bool phydev_id_compare(struct phy_device *phydev, u32 id) return phy_id_compare(id, phydev->phy_id, phydev->drv->phy_id_mask); } -/* A Structure for boards to register fixups with the PHY Lib */ -struct phy_fixup { - struct list_head list; - char bus_id[MII_BUS_ID_SIZE + 3]; - u32 phy_uid; - u32 phy_uid_mask; - int (*run)(struct phy_device *phydev); -}; - const char *phy_speed_to_str(int speed); const char *phy_duplex_to_str(unsigned int duplex); const char *phy_rate_matching_to_str(int rate_matching); @@ -1357,22 +1337,25 @@ void of_set_phy_timing_role(struct phy_device *phydev); int phy_speed_down_core(struct phy_device *phydev); /** - * phy_disable_eee_mode - Don't advertise an EEE mode. + * phy_is_started - Convenience function to check whether PHY is started * @phydev: The phy_device struct - * @link_mode: The EEE mode to be disabled */ -static inline void phy_disable_eee_mode(struct phy_device *phydev, u32 link_mode) +static inline bool phy_is_started(struct phy_device *phydev) { - linkmode_set_bit(link_mode, phydev->eee_disabled_modes); + return phydev->state >= PHY_UP; } /** - * phy_is_started - Convenience function to check whether PHY is started + * phy_disable_eee_mode - Don't advertise an EEE mode. * @phydev: The phy_device struct + * @link_mode: The EEE mode to be disabled */ -static inline bool phy_is_started(struct phy_device *phydev) +static inline void phy_disable_eee_mode(struct phy_device *phydev, u32 link_mode) { - return phydev->state >= PHY_UP; + WARN_ON(phy_is_started(phydev)); + + linkmode_set_bit(link_mode, phydev->eee_disabled_modes); + linkmode_clear_bit(link_mode, phydev->advertising_eee); } void phy_resolve_aneg_pause(struct phy_device *phydev); @@ -1757,15 +1740,6 @@ static inline bool phy_is_default_hwtstamp(struct phy_device *phydev) } /** - * phy_is_internal - Convenience function for testing if a PHY is internal - * @phydev: the phy_device struct - */ -static inline bool phy_is_internal(struct phy_device *phydev) -{ - return phydev->is_internal; -} - -/** * phy_on_sfp - Convenience function for testing if a PHY is on an SFP module * @phydev: the phy_device struct */ @@ -2055,8 +2029,7 @@ int genphy_c45_plca_set_cfg(struct phy_device *phydev, const struct phy_plca_cfg *plca_cfg); int genphy_c45_plca_get_status(struct phy_device *phydev, struct phy_plca_status *plca_st); -int genphy_c45_eee_is_active(struct phy_device *phydev, unsigned long *adv, - unsigned long *lp); +int genphy_c45_eee_is_active(struct phy_device *phydev, unsigned long *lp); int genphy_c45_ethtool_get_eee(struct phy_device *phydev, struct ethtool_keee *data); int genphy_c45_ethtool_set_eee(struct phy_device *phydev, @@ -2088,7 +2061,6 @@ int phy_drivers_register(struct phy_driver *new_driver, int n, struct module *owner); void phy_error(struct phy_device *phydev); void phy_state_machine(struct work_struct *work); -void phy_queue_state_machine(struct phy_device *phydev, unsigned long jiffies); void phy_trigger_machine(struct phy_device *phydev); void phy_mac_interrupt(struct phy_device *phydev); void phy_start_machine(struct phy_device *phydev); @@ -2124,11 +2096,13 @@ void phy_get_pause(struct phy_device *phydev, bool *tx_pause, bool *rx_pause); s32 phy_get_internal_delay(struct phy_device *phydev, struct device *dev, const int *delay_values, int size, bool is_rx); +int phy_get_tx_amplitude_gain(struct phy_device *phydev, struct device *dev, + enum ethtool_link_mode_bit_indices linkmode, + u32 *val); + void phy_resolve_pause(unsigned long *local_adv, unsigned long *partner_adv, bool *tx_pause, bool *rx_pause); -int phy_register_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask, - int (*run)(struct phy_device *)); int phy_register_fixup_for_id(const char *bus_id, int (*run)(struct phy_device *)); int phy_register_fixup_for_uid(u32 phy_uid, u32 phy_uid_mask, diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 0de78673172d..08df65f6867a 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -442,7 +442,6 @@ struct phylink_pcs_ops; * are supported by this PCS. * @ops: a pointer to the &struct phylink_pcs_ops structure * @phylink: pointer to &struct phylink_config - * @neg_mode: provide PCS neg mode via "mode" argument * @poll: poll the PCS for link changes * @rxc_always_on: The MAC driver requires the reference clock * to always be on. Standalone PCS drivers which @@ -459,7 +458,6 @@ struct phylink_pcs { DECLARE_PHY_INTERFACE_MASK(supported_interfaces); const struct phylink_pcs_ops *ops; struct phylink *phylink; - bool neg_mode; bool poll; bool rxc_always_on; }; @@ -477,6 +475,10 @@ struct phylink_pcs { * @pcs_an_restart: restart 802.3z BaseX autonegotiation. * @pcs_link_up: program the PCS for the resolved link configuration * (where necessary). + * @pcs_disable_eee: optional notification to PCS that EEE has been disabled + * at the MAC. + * @pcs_enable_eee: optional notification to PCS that EEE will be enabled at + * the MAC. * @pcs_pre_init: configure PCS components necessary for MAC hardware * initialization e.g. RX clock for stmmac. */ @@ -500,6 +502,8 @@ struct phylink_pcs_ops { void (*pcs_an_restart)(struct phylink_pcs *pcs); void (*pcs_link_up)(struct phylink_pcs *pcs, unsigned int neg_mode, phy_interface_t interface, int speed, int duplex); + void (*pcs_disable_eee)(struct phylink_pcs *pcs); + void (*pcs_enable_eee)(struct phylink_pcs *pcs); int (*pcs_pre_init)(struct phylink_pcs *pcs); }; @@ -626,6 +630,22 @@ void pcs_link_up(struct phylink_pcs *pcs, unsigned int neg_mode, phy_interface_t interface, int speed, int duplex); /** + * pcs_disable_eee() - Disable EEE at the PCS + * @pcs: a pointer to a &struct phylink_pcs + * + * Optional method informing the PCS that EEE has been disabled at the MAC. + */ +void pcs_disable_eee(struct phylink_pcs *pcs); + +/** + * pcs_enable_eee() - Enable EEE at the PCS + * @pcs: a pointer to a &struct phylink_pcs + * + * Optional method informing the PCS that EEE is about to be enabled at the MAC. + */ +void pcs_enable_eee(struct phylink_pcs *pcs); + +/** * pcs_pre_init() - Configure PCS components necessary for MAC initialization * @pcs: a pointer to a &struct phylink_pcs. * diff --git a/include/linux/psp-sev.h b/include/linux/psp-sev.h index 903ddfea8585..f3cad182d4ef 100644 --- a/include/linux/psp-sev.h +++ b/include/linux/psp-sev.h @@ -815,6 +815,15 @@ struct sev_data_snp_commit { #ifdef CONFIG_CRYPTO_DEV_SP_PSP /** + * sev_module_init - perform PSP SEV module initialization + * + * Returns: + * 0 if the PSP module is successfully initialized + * negative value if the PSP module initialization fails + */ +int sev_module_init(void); + +/** * sev_platform_init - perform SEV INIT command * * @args: struct sev_platform_init_args to pass in arguments diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 0f2aeb37bbb0..ca1db4b92c32 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -43,6 +43,7 @@ struct kernel_clone_args { void *fn_arg; struct cgroup *cgrp; struct css_set *cset; + unsigned int kill_seq; }; /* diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index c9878a612e53..6d2aa77ea963 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -231,7 +231,7 @@ struct plat_stmmacenet_data { u8 tx_sched_algorithm; struct stmmac_rxq_cfg rx_queues_cfg[MTL_MAX_RX_QUEUES]; struct stmmac_txq_cfg tx_queues_cfg[MTL_MAX_TX_QUEUES]; - void (*fix_mac_speed)(void *priv, unsigned int speed, unsigned int mode); + void (*fix_mac_speed)(void *priv, int speed, unsigned int mode); int (*fix_soc_reset)(void *priv, void __iomem *ioaddr); int (*serdes_powerup)(struct net_device *ndev, void *priv); void (*serdes_powerdown)(struct net_device *ndev, void *priv); @@ -254,6 +254,8 @@ struct plat_stmmacenet_data { struct clk *clk_ptp_ref; unsigned long clk_ptp_rate; unsigned long clk_ref_rate; + struct clk_bulk_data *clks; + int num_clks; unsigned int mult_fact_100ns; s32 ptp_max_adj; u32 cdc_error_adj; diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h index 741fa7754700..cab6146a510a 100644 --- a/include/net/busy_poll.h +++ b/include/net/busy_poll.h @@ -119,7 +119,7 @@ static inline void sk_busy_loop(struct sock *sk, int nonblock) #ifdef CONFIG_NET_RX_BUSY_POLL unsigned int napi_id = READ_ONCE(sk->sk_napi_id); - if (napi_id >= MIN_NAPI_ID) + if (napi_id_valid(napi_id)) napi_busy_loop(napi_id, nonblock ? NULL : sk_busy_loop_end, sk, READ_ONCE(sk->sk_prefer_busy_poll), READ_ONCE(sk->sk_busy_poll_budget) ?: BUSY_POLL_BUDGET); @@ -134,7 +134,7 @@ static inline void skb_mark_napi_id(struct sk_buff *skb, /* If the skb was already marked with a valid NAPI ID, avoid overwriting * it. */ - if (skb->napi_id < MIN_NAPI_ID) + if (!napi_id_valid(skb->napi_id)) skb->napi_id = napi->napi_id; #endif } diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h index 84c15402931c..4160731dcb6e 100644 --- a/include/net/dst_metadata.h +++ b/include/net/dst_metadata.h @@ -163,11 +163,8 @@ static inline struct metadata_dst *tun_dst_unclone(struct sk_buff *skb) if (!new_md) return ERR_PTR(-ENOMEM); - unsafe_memcpy(&new_md->u.tun_info, &md_dst->u.tun_info, - sizeof(struct ip_tunnel_info) + md_size, - /* metadata_dst_alloc() reserves room (md_size bytes) for - * options right after the ip_tunnel_info struct. - */); + memcpy(&new_md->u.tun_info, &md_dst->u.tun_info, + sizeof(struct ip_tunnel_info) + md_size); #ifdef CONFIG_DST_CACHE /* Unclone the dst cache if there is one */ if (new_md->u.tun_info.dst_cache.cache) { diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index 710caacad9da..5927910ec06e 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -43,6 +43,8 @@ struct fib_rule { struct fib_kuid_range uid_range; struct fib_rule_port_range sport_range; struct fib_rule_port_range dport_range; + u16 sport_mask; + u16 dport_mask; struct rcu_head rcu; }; @@ -146,6 +148,17 @@ static inline bool fib_rule_port_inrange(const struct fib_rule_port_range *a, ntohs(port) <= a->end; } +static inline bool fib_rule_port_match(const struct fib_rule_port_range *range, + u16 port_mask, __be16 port) +{ + if ((range->start ^ ntohs(port)) & port_mask) + return false; + if (!port_mask && fib_rule_port_range_set(range) && + !fib_rule_port_inrange(range, port)) + return false; + return true; +} + static inline bool fib_rule_port_range_valid(const struct fib_rule_port_range *a) { return a->start != 0 && a->end != 0 && a->end < 0xffff && @@ -159,6 +172,12 @@ static inline bool fib_rule_port_range_compare(struct fib_rule_port_range *a, a->end == b->end; } +static inline bool +fib_rule_port_is_range(const struct fib_rule_port_range *range) +{ + return range->start != range->end; +} + static inline bool fib_rule_requires_fldissect(struct fib_rule *rule) { return rule->iifindex != LOOPBACK_IFINDEX && (rule->ip_proto || diff --git a/include/net/gro.h b/include/net/gro.h index b9b58c1f8d19..7b548f91754b 100644 --- a/include/net/gro.h +++ b/include/net/gro.h @@ -11,6 +11,9 @@ #include <net/udp.h> #include <net/hotdata.h> +/* This should be increased if a protocol with a bigger head is added. */ +#define GRO_MAX_HEAD (MAX_HEADER + 128) + struct napi_gro_cb { union { struct { diff --git a/include/net/ip.h b/include/net/ip.h index ba7b43447775..ce5e59957dd5 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -92,11 +92,12 @@ static inline void ipcm_init(struct ipcm_cookie *ipcm) static inline void ipcm_init_sk(struct ipcm_cookie *ipcm, const struct inet_sock *inet) { - ipcm_init(ipcm); + *ipcm = (struct ipcm_cookie) { + .tos = READ_ONCE(inet->tos), + }; + + sockcm_init(&ipcm->sockc, &inet->sk); - ipcm->sockc.mark = READ_ONCE(inet->sk.sk_mark); - ipcm->sockc.priority = READ_ONCE(inet->sk.sk_priority); - ipcm->sockc.tsflags = READ_ONCE(inet->sk.sk_tsflags); ipcm->oif = READ_ONCE(inet->sk.sk_bound_dev_if); ipcm->addr = inet->inet_saddr; ipcm->protocol = inet->inet_num; @@ -257,13 +258,6 @@ static inline u8 ip_sendmsg_scope(const struct inet_sock *inet, return RT_SCOPE_UNIVERSE; } -static inline __u8 get_rttos(struct ipcm_cookie* ipc, struct inet_sock *inet) -{ - u8 dsfield = ipc->tos != -1 ? ipc->tos : READ_ONCE(inet->tos); - - return dsfield & INET_DSCP_MASK; -} - /* datagram.c */ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len); int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len); @@ -673,6 +667,14 @@ static inline void ip_ipgre_mc_map(__be32 naddr, const unsigned char *broadcast, memcpy(buf, &naddr, sizeof(naddr)); } +#if IS_MODULE(CONFIG_IPV6) +#define EXPORT_IPV6_MOD(X) EXPORT_SYMBOL(X) +#define EXPORT_IPV6_MOD_GPL(X) EXPORT_SYMBOL_GPL(X) +#else +#define EXPORT_IPV6_MOD(X) +#define EXPORT_IPV6_MOD_GPL(X) +#endif + #if IS_ENABLED(CONFIG_IPV6) #include <linux/ipv6.h> #endif diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 1aa31bdb2b31..a36a335cef9f 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -95,8 +95,8 @@ struct ip_tunnel_encap { #define ip_tunnel_info_opts(info) \ _Generic(info, \ - const struct ip_tunnel_info * : ((const void *)((info) + 1)),\ - struct ip_tunnel_info * : ((void *)((info) + 1))\ + const struct ip_tunnel_info * : ((const void *)(info)->options),\ + struct ip_tunnel_info * : ((void *)(info)->options)\ ) struct ip_tunnel_info { @@ -107,6 +107,7 @@ struct ip_tunnel_info { #endif u8 options_len; u8 mode; + u8 options[] __aligned_largest __counted_by(options_len); }; /* 6rd prefix/relay information */ @@ -406,8 +407,9 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, bool log_ecn_error); int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[], struct ip_tunnel_parm_kern *p, __u32 fwmark); -int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[], - struct ip_tunnel_parm_kern *p, __u32 fwmark); +int ip_tunnel_newlink(struct net *net, struct net_device *dev, + struct nlattr *tb[], struct ip_tunnel_parm_kern *p, + __u32 fwmark); void ip_tunnel_setup(struct net_device *dev, unsigned int net_id); bool ip_tunnel_netlink_encap_parms(struct nlattr *data[], @@ -650,7 +652,7 @@ static inline void iptunnel_xmit_stats(struct net_device *dev, int pkt_len) static inline void ip_tunnel_info_opts_get(void *to, const struct ip_tunnel_info *info) { - memcpy(to, info + 1, info->options_len); + memcpy(to, ip_tunnel_info_opts(info), info->options_len); } static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info, diff --git a/include/net/ipv6.h b/include/net/ipv6.h index f5c43ad1565e..9614006f483c 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -363,15 +363,6 @@ struct ipcm6_cookie { struct ipv6_txoptions *opt; }; -static inline void ipcm6_init(struct ipcm6_cookie *ipc6) -{ - *ipc6 = (struct ipcm6_cookie) { - .hlimit = -1, - .tclass = -1, - .dontfrag = -1, - }; -} - static inline void ipcm6_init_sk(struct ipcm6_cookie *ipc6, const struct sock *sk) { @@ -380,6 +371,8 @@ static inline void ipcm6_init_sk(struct ipcm6_cookie *ipc6, .tclass = inet6_sk(sk)->tclass, .dontfrag = inet6_test_bit(DONTFRAG, sk), }; + + sockcm_init(&ipc6->sockc, sk); } static inline struct ipv6_txoptions *txopt_get(const struct ipv6_pinfo *np) diff --git a/include/net/libeth/rx.h b/include/net/libeth/rx.h index 43574bd6612f..ab05024be518 100644 --- a/include/net/libeth/rx.h +++ b/include/net/libeth/rx.h @@ -198,6 +198,53 @@ struct libeth_rx_pt { enum xdp_rss_hash_type hash_type:16; }; +/** + * struct libeth_rx_csum - checksum offload bits decoded from the Rx descriptor + * @l3l4p: detectable L3 and L4 integrity check is processed by the hardware + * @ipe: IP checksum error + * @eipe: external (outermost) IP header (only for tunels) + * @eudpe: external (outermost) UDP checksum error (only for tunels) + * @ipv6exadd: IPv6 header with extension headers + * @l4e: L4 integrity error + * @pprs: set for packets that skip checksum calculation in the HW pre parser + * @nat: the packet is a UDP tunneled packet + * @raw_csum_valid: set if raw checksum is valid + * @pad: padding to naturally align raw_csum field + * @raw_csum: raw checksum + */ +struct libeth_rx_csum { + u32 l3l4p:1; + u32 ipe:1; + u32 eipe:1; + u32 eudpe:1; + u32 ipv6exadd:1; + u32 l4e:1; + u32 pprs:1; + u32 nat:1; + + u32 raw_csum_valid:1; + u32 pad:7; + u32 raw_csum:16; +}; + +/** + * struct libeth_rqe_info - receive queue element info + * @len: packet length + * @ptype: packet type based on types programmed into the device + * @eop: whether it's the last fragment of the packet + * @rxe: MAC errors: CRC, Alignment, Oversize, Undersizes, Length error + * @vlan: C-VLAN or S-VLAN tag depending on the VLAN offload configuration + */ +struct libeth_rqe_info { + u32 len; + + u32 ptype:14; + u32 eop:1; + u32 rxe:1; + + u32 vlan:16; +}; + void libeth_rx_pt_gen_hash_type(struct libeth_rx_pt *pt); /** diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 7ba1402ca779..f467a66abc6b 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -297,6 +297,7 @@ static inline int check_net(const struct net *net) } void net_drop_ns(void *); +void net_passive_dec(struct net *net); #else @@ -326,8 +327,18 @@ static inline int check_net(const struct net *net) } #define net_drop_ns NULL + +static inline void net_passive_dec(struct net *net) +{ + refcount_dec(&net->passive); +} #endif +static inline void net_passive_inc(struct net *net) +{ + refcount_inc(&net->passive); +} + /* Returns true if the netns initialization is completed successfully */ static inline bool net_initialized(const struct net *net) { diff --git a/include/net/netlink.h b/include/net/netlink.h index e015ffbed819..29e0db940382 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -118,6 +118,7 @@ * nla_nest_start(skb, type) start a nested attribute * nla_nest_end(skb, nla) finalize a nested attribute * nla_nest_cancel(skb, nla) cancel nested attribute construction + * nla_put_empty_nest(skb, type) create an empty nest * * Attribute Length Calculations: * nla_attr_size(payload) length of attribute w/o padding @@ -2241,6 +2242,20 @@ static inline void nla_nest_cancel(struct sk_buff *skb, struct nlattr *start) } /** + * nla_put_empty_nest - Create an empty nest + * @skb: socket buffer the message is stored in + * @attrtype: attribute type of the container + * + * This function is a helper for creating empty nests. + * + * Returns: 0 when successful or -EMSGSIZE on failure. + */ +static inline int nla_put_empty_nest(struct sk_buff *skb, int attrtype) +{ + return nla_nest_start(skb, attrtype) ? 0 : -EMSGSIZE; +} + +/** * __nla_validate_nested - Validate a stream of nested attributes * @start: container attribute * @maxtype: maximum attribute type to be expected diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index bc0069a8b6ea..ec65a8cebb99 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -70,6 +70,40 @@ static inline int rtnl_msg_family(const struct nlmsghdr *nlh) } /** + * struct rtnl_newlink_params - parameters of rtnl_link_ops::newlink() + * + * @src_net: Source netns of rtnetlink socket + * @link_net: Link netns by IFLA_LINK_NETNSID, NULL if not specified + * @peer_net: Peer netns + * @tb: IFLA_* attributes + * @data: IFLA_INFO_DATA attributes + */ +struct rtnl_newlink_params { + struct net *src_net; + struct net *link_net; + struct net *peer_net; + struct nlattr **tb; + struct nlattr **data; +}; + +/* Get effective link netns from newlink params. Generally, this is link_net + * and falls back to src_net. But for compatibility, a driver may * choose to + * use dev_net(dev) instead. + */ +static inline struct net *rtnl_newlink_link_net(struct rtnl_newlink_params *p) +{ + return p->link_net ? : p->src_net; +} + +/* Get peer netns from newlink params. Fallback to link netns if peer netns is + * not specified explicitly. + */ +static inline struct net *rtnl_newlink_peer_net(struct rtnl_newlink_params *p) +{ + return p->peer_net ? : rtnl_newlink_link_net(p); +} + +/** * struct rtnl_link_ops - rtnetlink link operations * * @list: Used internally, protected by link_ops_mutex and SRCU @@ -125,10 +159,8 @@ struct rtnl_link_ops { struct nlattr *data[], struct netlink_ext_ack *extack); - int (*newlink)(struct net *src_net, - struct net_device *dev, - struct nlattr *tb[], - struct nlattr *data[], + int (*newlink)(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack); int (*changelink)(struct net_device *dev, struct nlattr *tb[], diff --git a/include/net/sock.h b/include/net/sock.h index 2f6b55c59c16..efc031163c33 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1288,10 +1288,6 @@ struct proto { unsigned int inuse_idx; #endif -#if IS_ENABLED(CONFIG_MPTCP) - int (*forward_alloc_get)(const struct sock *sk); -#endif - bool (*stream_memory_free)(const struct sock *sk, int wake); bool (*sock_is_readable)(struct sock *sk); /* Memory pressure */ @@ -1352,15 +1348,6 @@ int sock_load_diag_module(int family, int protocol); INDIRECT_CALLABLE_DECLARE(bool tcp_stream_memory_free(const struct sock *sk, int wake)); -static inline int sk_forward_alloc_get(const struct sock *sk) -{ -#if IS_ENABLED(CONFIG_MPTCP) - if (sk->sk_prot->forward_alloc_get) - return sk->sk_prot->forward_alloc_get(sk); -#endif - return READ_ONCE(sk->sk_forward_alloc); -} - static inline bool __sk_stream_memory_free(const struct sock *sk, int wake) { if (READ_ONCE(sk->sk_wmem_queued) >= READ_ONCE(sk->sk_sndbuf)) @@ -1832,6 +1819,7 @@ static inline void sockcm_init(struct sockcm_cookie *sockc, const struct sock *sk) { *sockc = (struct sockcm_cookie) { + .mark = READ_ONCE(sk->sk_mark), .tsflags = READ_ONCE(sk->sk_tsflags), .priority = READ_ONCE(sk->sk_priority), }; diff --git a/include/net/tcp.h b/include/net/tcp.h index ae6c95b01012..9745c7f18170 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -41,6 +41,7 @@ #include <net/inet_ecn.h> #include <net/dst.h> #include <net/mptcp.h> +#include <net/xfrm.h> #include <linux/seq_file.h> #include <linux/memcontrol.h> @@ -685,6 +686,19 @@ void tcp_fin(struct sock *sk); void tcp_check_space(struct sock *sk); void tcp_sack_compress_send_ack(struct sock *sk); +static inline void tcp_cleanup_skb(struct sk_buff *skb) +{ + skb_dst_drop(skb); + secpath_reset(skb); +} + +static inline void tcp_add_receive_queue(struct sock *sk, struct sk_buff *skb) +{ + DEBUG_NET_WARN_ON_ONCE(skb_dst(skb)); + DEBUG_NET_WARN_ON_ONCE(secpath_exists(skb)); + __skb_queue_tail(&sk->sk_receive_queue, skb); +} + /* tcp_timer.c */ void tcp_init_xmit_timers(struct sock *); static inline void tcp_clear_xmit_timers(struct sock *sk) diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index 6e699cadcb29..f880835f7695 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -99,7 +99,7 @@ EM(netfs_sreq_trace_limited, "LIMIT") \ EM(netfs_sreq_trace_need_clear, "N-CLR") \ EM(netfs_sreq_trace_partial_read, "PARTR") \ - EM(netfs_sreq_trace_need_retry, "NRTRY") \ + EM(netfs_sreq_trace_need_retry, "ND-RT") \ EM(netfs_sreq_trace_prepare, "PREP ") \ EM(netfs_sreq_trace_prep_failed, "PRPFL") \ EM(netfs_sreq_trace_progress, "PRGRS") \ @@ -108,7 +108,9 @@ EM(netfs_sreq_trace_short, "SHORT") \ EM(netfs_sreq_trace_split, "SPLIT") \ EM(netfs_sreq_trace_submit, "SUBMT") \ + EM(netfs_sreq_trace_superfluous, "SPRFL") \ EM(netfs_sreq_trace_terminated, "TERM ") \ + EM(netfs_sreq_trace_wait_for, "_WAIT") \ EM(netfs_sreq_trace_write, "WRITE") \ EM(netfs_sreq_trace_write_skip, "SKIP ") \ E_(netfs_sreq_trace_write_term, "WTERM") diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h index a27c4b619dff..1a40c41ff8c3 100644 --- a/include/trace/events/tcp.h +++ b/include/trace/events/tcp.h @@ -259,6 +259,12 @@ TRACE_EVENT(tcp_retransmit_synack, __entry->saddr_v6, __entry->daddr_v6) ); +DECLARE_TRACE(tcp_cwnd_reduction_tp, + TP_PROTO(const struct sock *sk, int newly_acked_sacked, + int newly_lost, int flag), + TP_ARGS(sk, newly_acked_sacked, newly_lost, flag) +); + #include <trace/events/net_probe_common.h> TRACE_EVENT(tcp_probe, diff --git a/include/uapi/linux/can.h b/include/uapi/linux/can.h index e78cbd85ce7c..42abf0679fb4 100644 --- a/include/uapi/linux/can.h +++ b/include/uapi/linux/can.h @@ -182,7 +182,7 @@ struct canfd_frame { /* * defined bits for canxl_frame.flags * - * The canxl_frame.flags element contains two bits CANXL_XLF and CANXL_SEC + * The canxl_frame.flags element contains three bits CANXL_[XLF|SEC|RRS] * and shares the relative position of the struct can[fd]_frame.len element. * The CANXL_XLF bit ALWAYS needs to be set to indicate a valid CAN XL frame. * As a side effect setting this bit intentionally breaks the length checks @@ -192,6 +192,7 @@ struct canfd_frame { */ #define CANXL_XLF 0x80 /* mandatory CAN XL frame flag (must always be set!) */ #define CANXL_SEC 0x01 /* Simple Extended Content (security/segmentation) */ +#define CANXL_RRS 0x02 /* Remote Request Substitution */ /* the 8-bit VCID is optionally placed in the canxl_frame.prio element */ #define CANXL_VCID_OFFSET 16 /* bit offset of VCID in prio element */ diff --git a/include/uapi/linux/fib_rules.h b/include/uapi/linux/fib_rules.h index 00e9890ca3c0..95ec01b15c65 100644 --- a/include/uapi/linux/fib_rules.h +++ b/include/uapi/linux/fib_rules.h @@ -70,6 +70,8 @@ enum { FRA_DSCP, /* dscp */ FRA_FLOWLABEL, /* flowlabel */ FRA_FLOWLABEL_MASK, /* flowlabel mask */ + FRA_SPORT_MASK, /* sport mask */ + FRA_DPORT_MASK, /* dport mask */ __FRA_MAX }; diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index b97ff8bbb0c6..7600bf62dbdf 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -140,12 +140,18 @@ enum { }; enum { + __NETDEV_A_XSK_INFO_MAX, + NETDEV_A_XSK_INFO_MAX = (__NETDEV_A_XSK_INFO_MAX - 1) +}; + +enum { NETDEV_A_QUEUE_ID = 1, NETDEV_A_QUEUE_IFINDEX, NETDEV_A_QUEUE_TYPE, NETDEV_A_QUEUE_NAPI_ID, NETDEV_A_QUEUE_DMABUF, NETDEV_A_QUEUE_IO_URING, + NETDEV_A_QUEUE_XSK, __NETDEV_A_QUEUE_MAX, NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1) diff --git a/include/uapi/linux/taskstats.h b/include/uapi/linux/taskstats.h index 934e20ef7f79..95762232e018 100644 --- a/include/uapi/linux/taskstats.h +++ b/include/uapi/linux/taskstats.h @@ -34,7 +34,7 @@ */ -#define TASKSTATS_VERSION 14 +#define TASKSTATS_VERSION 15 #define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN * in linux/sched.h */ diff --git a/include/uapi/linux/thermal.h b/include/uapi/linux/thermal.h index 349718c271eb..46a2633d33aa 100644 --- a/include/uapi/linux/thermal.h +++ b/include/uapi/linux/thermal.h @@ -30,7 +30,6 @@ enum thermal_genl_attr { THERMAL_GENL_ATTR_TZ, THERMAL_GENL_ATTR_TZ_ID, THERMAL_GENL_ATTR_TZ_TEMP, - THERMAL_GENL_ATTR_TZ_PREV_TEMP, THERMAL_GENL_ATTR_TZ_TRIP, THERMAL_GENL_ATTR_TZ_TRIP_ID, THERMAL_GENL_ATTR_TZ_TRIP_TYPE, @@ -54,6 +53,7 @@ enum thermal_genl_attr { THERMAL_GENL_ATTR_THRESHOLD, THERMAL_GENL_ATTR_THRESHOLD_TEMP, THERMAL_GENL_ATTR_THRESHOLD_DIRECTION, + THERMAL_GENL_ATTR_TZ_PREV_TEMP, __THERMAL_GENL_ATTR_MAX, }; #define THERMAL_GENL_ATTR_MAX (__THERMAL_GENL_ATTR_MAX - 1) diff --git a/include/uapi/linux/virtio_snd.h b/include/uapi/linux/virtio_snd.h index 5f4100c2cf04..a4cfb9f6561a 100644 --- a/include/uapi/linux/virtio_snd.h +++ b/include/uapi/linux/virtio_snd.h @@ -25,7 +25,7 @@ struct virtio_snd_config { __le32 streams; /* # of available channel maps */ __le32 chmaps; - /* # of available control elements */ + /* # of available control elements (if VIRTIO_SND_F_CTLS) */ __le32 controls; }; diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c index 04bf493eecae..8e72de7712ac 100644 --- a/io_uring/kbuf.c +++ b/io_uring/kbuf.c @@ -415,6 +415,13 @@ void io_destroy_buffers(struct io_ring_ctx *ctx) } } +static void io_destroy_bl(struct io_ring_ctx *ctx, struct io_buffer_list *bl) +{ + scoped_guard(mutex, &ctx->mmap_lock) + WARN_ON_ONCE(xa_erase(&ctx->io_bl_xa, bl->bgid) != bl); + io_put_bl(ctx, bl); +} + int io_remove_buffers_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_provide_buf *p = io_kiocb_to_cmd(req, struct io_provide_buf); @@ -636,12 +643,13 @@ int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg) /* if mapped buffer ring OR classic exists, don't allow */ if (bl->flags & IOBL_BUF_RING || !list_empty(&bl->buf_list)) return -EEXIST; - } else { - free_bl = bl = kzalloc(sizeof(*bl), GFP_KERNEL); - if (!bl) - return -ENOMEM; + io_destroy_bl(ctx, bl); } + free_bl = bl = kzalloc(sizeof(*bl), GFP_KERNEL); + if (!bl) + return -ENOMEM; + mmap_offset = (unsigned long)reg.bgid << IORING_OFF_PBUF_SHIFT; ring_size = flex_array_size(br, bufs, reg.ring_entries); diff --git a/io_uring/napi.c b/io_uring/napi.c index b1ade3fda30f..4a10de03e426 100644 --- a/io_uring/napi.c +++ b/io_uring/napi.c @@ -44,7 +44,7 @@ int __io_napi_add_id(struct io_ring_ctx *ctx, unsigned int napi_id) struct io_napi_entry *e; /* Non-NAPI IDs can be rejected. */ - if (napi_id < MIN_NAPI_ID) + if (!napi_id_valid(napi_id)) return -EINVAL; hash_list = &ctx->napi_ht[hash_min(napi_id, HASH_BITS(ctx->napi_ht))]; @@ -87,7 +87,7 @@ static int __io_napi_del_id(struct io_ring_ctx *ctx, unsigned int napi_id) struct io_napi_entry *e; /* Non-NAPI IDs can be rejected. */ - if (napi_id < MIN_NAPI_ID) + if (!napi_id_valid(napi_id)) return -EINVAL; hash_list = &ctx->napi_ht[hash_min(napi_id, HASH_BITS(ctx->napi_ht))]; diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c index 1f6a82128b47..e6701b7aa147 100644 --- a/io_uring/uring_cmd.c +++ b/io_uring/uring_cmd.c @@ -54,9 +54,6 @@ bool io_uring_try_cancel_uring_cmd(struct io_ring_ctx *ctx, continue; if (cmd->flags & IORING_URING_CMD_CANCELABLE) { - /* ->sqe isn't available if no async data */ - if (!req_has_async_data(req)) - cmd->sqe = NULL; file->f_op->uring_cmd(cmd, IO_URING_F_CANCEL | IO_URING_F_COMPLETE_DEFER); ret = true; @@ -179,12 +176,13 @@ static int io_uring_cmd_prep_setup(struct io_kiocb *req, return -ENOMEM; cache->op_data = NULL; - if (!(req->flags & REQ_F_FORCE_ASYNC)) { - /* defer memcpy until we need it */ - ioucmd->sqe = sqe; - return 0; - } - + /* + * Unconditionally cache the SQE for now - this is only needed for + * requests that go async, but prep handlers must ensure that any + * sqe data is stable beyond prep. Since uring_cmd is special in + * that it doesn't read in per-op data, play it safe and ensure that + * any SQE data is stable beyond prep. This can later get relaxed. + */ memcpy(cache->sqes, sqe, uring_sqe_size(req->ctx)); ioucmd->sqe = cache->sqes; return 0; @@ -249,16 +247,8 @@ int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags) } ret = file->f_op->uring_cmd(ioucmd, issue_flags); - if (ret == -EAGAIN) { - struct io_uring_cmd_data *cache = req->async_data; - - if (ioucmd->sqe != (void *) cache) - memcpy(cache->sqes, ioucmd->sqe, uring_sqe_size(req->ctx)); - return -EAGAIN; - } else if (ret == -EIOCBQUEUED) { - return -EIOCBQUEUED; - } - + if (ret == -EAGAIN || ret == -EIOCBQUEUED) + return ret; if (ret < 0) req_set_fail(req); io_req_uring_cleanup(req, issue_flags); diff --git a/io_uring/waitid.c b/io_uring/waitid.c index 853e97a7b0ec..15a7daf3ff4f 100644 --- a/io_uring/waitid.c +++ b/io_uring/waitid.c @@ -118,7 +118,6 @@ static int io_waitid_finish(struct io_kiocb *req, int ret) static void io_waitid_complete(struct io_kiocb *req, int ret) { struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid); - struct io_tw_state ts = {}; /* anyone completing better be holding a reference */ WARN_ON_ONCE(!(atomic_read(&iw->refs) & IO_WAITID_REF_MASK)); @@ -131,7 +130,6 @@ static void io_waitid_complete(struct io_kiocb *req, int ret) if (ret < 0) req_set_fail(req); io_req_set_res(req, ret, 0); - io_req_task_complete(req, &ts); } static bool __io_waitid_cancel(struct io_ring_ctx *ctx, struct io_kiocb *req) @@ -153,6 +151,7 @@ static bool __io_waitid_cancel(struct io_ring_ctx *ctx, struct io_kiocb *req) list_del_init(&iwa->wo.child_wait.entry); spin_unlock_irq(&iw->head->lock); io_waitid_complete(req, -ECANCELED); + io_req_queue_tw_complete(req, -ECANCELED); return true; } @@ -258,6 +257,7 @@ static void io_waitid_cb(struct io_kiocb *req, struct io_tw_state *ts) } io_waitid_complete(req, ret); + io_req_task_complete(req, ts); } static int io_waitid_wait(struct wait_queue_entry *wait, unsigned mode, @@ -285,10 +285,16 @@ static int io_waitid_wait(struct wait_queue_entry *wait, unsigned mode, int io_waitid_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid); + struct io_waitid_async *iwa; if (sqe->addr || sqe->buf_index || sqe->addr3 || sqe->waitid_flags) return -EINVAL; + iwa = io_uring_alloc_async_data(NULL, req); + if (!unlikely(iwa)) + return -ENOMEM; + iwa->req = req; + iw->which = READ_ONCE(sqe->len); iw->upid = READ_ONCE(sqe->fd); iw->options = READ_ONCE(sqe->file_index); @@ -299,16 +305,10 @@ int io_waitid_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) int io_waitid(struct io_kiocb *req, unsigned int issue_flags) { struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid); + struct io_waitid_async *iwa = req->async_data; struct io_ring_ctx *ctx = req->ctx; - struct io_waitid_async *iwa; int ret; - iwa = io_uring_alloc_async_data(NULL, req); - if (!iwa) - return -ENOMEM; - - iwa->req = req; - ret = kernel_waitid_prepare(&iwa->wo, iw->which, iw->upid, &iw->info, iw->options, NULL); if (ret) diff --git a/kernel/acct.c b/kernel/acct.c index 31222e8cd534..6520baa13669 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -103,48 +103,50 @@ struct bsd_acct_struct { atomic_long_t count; struct rcu_head rcu; struct mutex lock; - int active; + bool active; + bool check_space; unsigned long needcheck; struct file *file; struct pid_namespace *ns; struct work_struct work; struct completion done; + acct_t ac; }; -static void do_acct_process(struct bsd_acct_struct *acct); +static void fill_ac(struct bsd_acct_struct *acct); +static void acct_write_process(struct bsd_acct_struct *acct); /* * Check the amount of free space and suspend/resume accordingly. */ -static int check_free_space(struct bsd_acct_struct *acct) +static bool check_free_space(struct bsd_acct_struct *acct) { struct kstatfs sbuf; - if (time_is_after_jiffies(acct->needcheck)) - goto out; + if (!acct->check_space) + return acct->active; /* May block */ if (vfs_statfs(&acct->file->f_path, &sbuf)) - goto out; + return acct->active; if (acct->active) { u64 suspend = sbuf.f_blocks * SUSPEND; do_div(suspend, 100); if (sbuf.f_bavail <= suspend) { - acct->active = 0; + acct->active = false; pr_info("Process accounting paused\n"); } } else { u64 resume = sbuf.f_blocks * RESUME; do_div(resume, 100); if (sbuf.f_bavail >= resume) { - acct->active = 1; + acct->active = true; pr_info("Process accounting resumed\n"); } } acct->needcheck = jiffies + ACCT_TIMEOUT*HZ; -out: return acct->active; } @@ -189,7 +191,11 @@ static void acct_pin_kill(struct fs_pin *pin) { struct bsd_acct_struct *acct = to_acct(pin); mutex_lock(&acct->lock); - do_acct_process(acct); + /* + * Fill the accounting struct with the exiting task's info + * before punting to the workqueue. + */ + fill_ac(acct); schedule_work(&acct->work); wait_for_completion(&acct->done); cmpxchg(&acct->ns->bacct, pin, NULL); @@ -202,6 +208,9 @@ static void close_work(struct work_struct *work) { struct bsd_acct_struct *acct = container_of(work, struct bsd_acct_struct, work); struct file *file = acct->file; + + /* We were fired by acct_pin_kill() which holds acct->lock. */ + acct_write_process(acct); if (file->f_op->flush) file->f_op->flush(file, NULL); __fput_sync(file); @@ -234,6 +243,20 @@ static int acct_on(struct filename *pathname) return -EACCES; } + /* Exclude kernel kernel internal filesystems. */ + if (file_inode(file)->i_sb->s_flags & (SB_NOUSER | SB_KERNMOUNT)) { + kfree(acct); + filp_close(file, NULL); + return -EINVAL; + } + + /* Exclude procfs and sysfs. */ + if (file_inode(file)->i_sb->s_iflags & SB_I_USERNS_VISIBLE) { + kfree(acct); + filp_close(file, NULL); + return -EINVAL; + } + if (!(file->f_mode & FMODE_CAN_WRITE)) { kfree(acct); filp_close(file, NULL); @@ -430,13 +453,27 @@ static u32 encode_float(u64 value) * do_exit() or when switching to a different output file. */ -static void fill_ac(acct_t *ac) +static void fill_ac(struct bsd_acct_struct *acct) { struct pacct_struct *pacct = ¤t->signal->pacct; + struct file *file = acct->file; + acct_t *ac = &acct->ac; u64 elapsed, run_time; time64_t btime; struct tty_struct *tty; + lockdep_assert_held(&acct->lock); + + if (time_is_after_jiffies(acct->needcheck)) { + acct->check_space = false; + + /* Don't fill in @ac if nothing will be written. */ + if (!acct->active) + return; + } else { + acct->check_space = true; + } + /* * Fill the accounting struct with the needed info as recorded * by the different kernel functions. @@ -484,64 +521,61 @@ static void fill_ac(acct_t *ac) ac->ac_majflt = encode_comp_t(pacct->ac_majflt); ac->ac_exitcode = pacct->ac_exitcode; spin_unlock_irq(¤t->sighand->siglock); -} -/* - * do_acct_process does all actual work. Caller holds the reference to file. - */ -static void do_acct_process(struct bsd_acct_struct *acct) -{ - acct_t ac; - unsigned long flim; - const struct cred *orig_cred; - struct file *file = acct->file; - /* - * Accounting records are not subject to resource limits. - */ - flim = rlimit(RLIMIT_FSIZE); - current->signal->rlim[RLIMIT_FSIZE].rlim_cur = RLIM_INFINITY; - /* Perform file operations on behalf of whoever enabled accounting */ - orig_cred = override_creds(file->f_cred); - - /* - * First check to see if there is enough free_space to continue - * the process accounting system. - */ - if (!check_free_space(acct)) - goto out; - - fill_ac(&ac); /* we really need to bite the bullet and change layout */ - ac.ac_uid = from_kuid_munged(file->f_cred->user_ns, orig_cred->uid); - ac.ac_gid = from_kgid_munged(file->f_cred->user_ns, orig_cred->gid); + ac->ac_uid = from_kuid_munged(file->f_cred->user_ns, current_uid()); + ac->ac_gid = from_kgid_munged(file->f_cred->user_ns, current_gid()); #if ACCT_VERSION == 1 || ACCT_VERSION == 2 /* backward-compatible 16 bit fields */ - ac.ac_uid16 = ac.ac_uid; - ac.ac_gid16 = ac.ac_gid; + ac->ac_uid16 = ac->ac_uid; + ac->ac_gid16 = ac->ac_gid; #elif ACCT_VERSION == 3 { struct pid_namespace *ns = acct->ns; - ac.ac_pid = task_tgid_nr_ns(current, ns); + ac->ac_pid = task_tgid_nr_ns(current, ns); rcu_read_lock(); - ac.ac_ppid = task_tgid_nr_ns(rcu_dereference(current->real_parent), - ns); + ac->ac_ppid = task_tgid_nr_ns(rcu_dereference(current->real_parent), ns); rcu_read_unlock(); } #endif +} + +static void acct_write_process(struct bsd_acct_struct *acct) +{ + struct file *file = acct->file; + const struct cred *cred; + acct_t *ac = &acct->ac; + + /* Perform file operations on behalf of whoever enabled accounting */ + cred = override_creds(file->f_cred); + /* - * Get freeze protection. If the fs is frozen, just skip the write - * as we could deadlock the system otherwise. + * First check to see if there is enough free_space to continue + * the process accounting system. Then get freeze protection. If + * the fs is frozen, just skip the write as we could deadlock + * the system otherwise. */ - if (file_start_write_trylock(file)) { + if (check_free_space(acct) && file_start_write_trylock(file)) { /* it's been opened O_APPEND, so position is irrelevant */ loff_t pos = 0; - __kernel_write(file, &ac, sizeof(acct_t), &pos); + __kernel_write(file, ac, sizeof(acct_t), &pos); file_end_write(file); } -out: + + revert_creds(cred); +} + +static void do_acct_process(struct bsd_acct_struct *acct) +{ + unsigned long flim; + + /* Accounting records are not subject to resource limits. */ + flim = rlimit(RLIMIT_FSIZE); + current->signal->rlim[RLIMIT_FSIZE].rlim_cur = RLIM_INFINITY; + fill_ac(acct); + acct_write_process(acct); current->signal->rlim[RLIMIT_FSIZE].rlim_cur = flim; - revert_creds(orig_cred); } /** diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index d9061bd55436..afc665b7b1fe 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -4013,7 +4013,7 @@ static void __cgroup_kill(struct cgroup *cgrp) lockdep_assert_held(&cgroup_mutex); spin_lock_irq(&css_set_lock); - set_bit(CGRP_KILL, &cgrp->flags); + cgrp->kill_seq++; spin_unlock_irq(&css_set_lock); css_task_iter_start(&cgrp->self, CSS_TASK_ITER_PROCS | CSS_TASK_ITER_THREADED, &it); @@ -4029,10 +4029,6 @@ static void __cgroup_kill(struct cgroup *cgrp) send_sig(SIGKILL, task, 0); } css_task_iter_end(&it); - - spin_lock_irq(&css_set_lock); - clear_bit(CGRP_KILL, &cgrp->flags); - spin_unlock_irq(&css_set_lock); } static void cgroup_kill(struct cgroup *cgrp) @@ -6488,6 +6484,10 @@ static int cgroup_css_set_fork(struct kernel_clone_args *kargs) spin_lock_irq(&css_set_lock); cset = task_css_set(current); get_css_set(cset); + if (kargs->cgrp) + kargs->kill_seq = kargs->cgrp->kill_seq; + else + kargs->kill_seq = cset->dfl_cgrp->kill_seq; spin_unlock_irq(&css_set_lock); if (!(kargs->flags & CLONE_INTO_CGROUP)) { @@ -6668,6 +6668,7 @@ void cgroup_post_fork(struct task_struct *child, struct kernel_clone_args *kargs) __releases(&cgroup_threadgroup_rwsem) __releases(&cgroup_mutex) { + unsigned int cgrp_kill_seq = 0; unsigned long cgrp_flags = 0; bool kill = false; struct cgroup_subsys *ss; @@ -6681,10 +6682,13 @@ void cgroup_post_fork(struct task_struct *child, /* init tasks are special, only link regular threads */ if (likely(child->pid)) { - if (kargs->cgrp) + if (kargs->cgrp) { cgrp_flags = kargs->cgrp->flags; - else + cgrp_kill_seq = kargs->cgrp->kill_seq; + } else { cgrp_flags = cset->dfl_cgrp->flags; + cgrp_kill_seq = cset->dfl_cgrp->kill_seq; + } WARN_ON_ONCE(!list_empty(&child->cg_list)); cset->nr_tasks++; @@ -6719,7 +6723,7 @@ void cgroup_post_fork(struct task_struct *child, * child down right after we finished preparing it for * userspace. */ - kill = test_bit(CGRP_KILL, &cgrp_flags); + kill = kargs->kill_seq != cgrp_kill_seq; } spin_unlock_irq(&css_set_lock); diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c index 5877974ece92..aac91466279f 100644 --- a/kernel/cgroup/rstat.c +++ b/kernel/cgroup/rstat.c @@ -590,7 +590,6 @@ static void root_cgroup_cputime(struct cgroup_base_stat *bstat) cputime->sum_exec_runtime += user; cputime->sum_exec_runtime += sys; - cputime->sum_exec_runtime += cpustat[CPUTIME_STEAL]; #ifdef CONFIG_SCHED_CORE bstat->forceidle_sum += cpustat[CPUTIME_FORCEIDLE]; diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig index 5432418c0fea..875f25ed6f71 100644 --- a/kernel/irq/Kconfig +++ b/kernel/irq/Kconfig @@ -31,10 +31,6 @@ config GENERIC_IRQ_EFFECTIVE_AFF_MASK config GENERIC_PENDING_IRQ bool -# Deduce delayed migration from top-level interrupt chip flags -config GENERIC_PENDING_IRQ_CHIPFLAGS - bool - # Support for generic irq migrating off cpu before the cpu is offline. config GENERIC_IRQ_MIGRATION bool diff --git a/kernel/sched/autogroup.c b/kernel/sched/autogroup.c index 83d46b9b8ec8..2b331822c7e7 100644 --- a/kernel/sched/autogroup.c +++ b/kernel/sched/autogroup.c @@ -150,7 +150,7 @@ void sched_autogroup_exit_task(struct task_struct *p) * see this thread after that: we can no longer use signal->autogroup. * See the PF_EXITING check in task_wants_autogroup(). */ - sched_move_task(p); + sched_move_task(p, true); } static void @@ -182,7 +182,7 @@ autogroup_move_group(struct task_struct *p, struct autogroup *ag) * sched_autogroup_exit_task(). */ for_each_thread(p, t) - sched_move_task(t); + sched_move_task(t, true); unlock_task_sighand(p, &flags); autogroup_kref_put(prev); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 165c90ba64ea..9aecd914ac69 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1063,9 +1063,10 @@ void wake_up_q(struct wake_q_head *head) struct task_struct *task; task = container_of(node, struct task_struct, wake_q); - /* Task can safely be re-inserted now: */ node = node->next; - task->wake_q.next = NULL; + /* pairs with cmpxchg_relaxed() in __wake_q_add() */ + WRITE_ONCE(task->wake_q.next, NULL); + /* Task can safely be re-inserted now. */ /* * wake_up_process() executes a full barrier, which pairs with @@ -9050,7 +9051,7 @@ static void sched_change_group(struct task_struct *tsk, struct task_group *group * now. This function just updates tsk->se.cfs_rq and tsk->se.parent to reflect * its new group. */ -void sched_move_task(struct task_struct *tsk) +void sched_move_task(struct task_struct *tsk, bool for_autogroup) { int queued, running, queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK; @@ -9079,7 +9080,8 @@ void sched_move_task(struct task_struct *tsk) put_prev_task(rq, tsk); sched_change_group(tsk, group); - scx_move_task(tsk); + if (!for_autogroup) + scx_cgroup_move_task(tsk); if (queued) enqueue_task(rq, tsk, queue_flags); @@ -9180,7 +9182,7 @@ static void cpu_cgroup_attach(struct cgroup_taskset *tset) struct cgroup_subsys_state *css; cgroup_taskset_for_each(task, css, tset) - sched_move_task(task); + sched_move_task(task, false); scx_cgroup_finish_attach(); } diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 8857c0709bdd..5a81d9a1e31f 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -123,6 +123,19 @@ enum scx_ops_flags { SCX_OPS_SWITCH_PARTIAL = 1LLU << 3, /* + * A migration disabled task can only execute on its current CPU. By + * default, such tasks are automatically put on the CPU's local DSQ with + * the default slice on enqueue. If this ops flag is set, they also go + * through ops.enqueue(). + * + * A migration disabled task never invokes ops.select_cpu() as it can + * only select the current CPU. Also, p->cpus_ptr will only contain its + * current CPU while p->nr_cpus_allowed keeps tracking p->user_cpus_ptr + * and thus may disagree with cpumask_weight(p->cpus_ptr). + */ + SCX_OPS_ENQ_MIGRATION_DISABLED = 1LLU << 4, + + /* * CPU cgroup support flags */ SCX_OPS_HAS_CGROUP_WEIGHT = 1LLU << 16, /* cpu.weight */ @@ -130,6 +143,7 @@ enum scx_ops_flags { SCX_OPS_ALL_FLAGS = SCX_OPS_KEEP_BUILTIN_IDLE | SCX_OPS_ENQ_LAST | SCX_OPS_ENQ_EXITING | + SCX_OPS_ENQ_MIGRATION_DISABLED | SCX_OPS_SWITCH_PARTIAL | SCX_OPS_HAS_CGROUP_WEIGHT, }; @@ -416,7 +430,7 @@ struct sched_ext_ops { /** * @update_idle: Update the idle state of a CPU - * @cpu: CPU to udpate the idle state for + * @cpu: CPU to update the idle state for * @idle: whether entering or exiting the idle state * * This operation is called when @rq's CPU goes or leaves the idle @@ -882,6 +896,7 @@ static bool scx_warned_zero_slice; static DEFINE_STATIC_KEY_FALSE(scx_ops_enq_last); static DEFINE_STATIC_KEY_FALSE(scx_ops_enq_exiting); +static DEFINE_STATIC_KEY_FALSE(scx_ops_enq_migration_disabled); static DEFINE_STATIC_KEY_FALSE(scx_ops_cpu_preempt); static DEFINE_STATIC_KEY_FALSE(scx_builtin_idle_enabled); @@ -1214,7 +1229,7 @@ static bool scx_kf_allowed_if_unlocked(void) /** * nldsq_next_task - Iterate to the next task in a non-local DSQ - * @dsq: user dsq being interated + * @dsq: user dsq being iterated * @cur: current position, %NULL to start iteration * @rev: walk backwards * @@ -2014,6 +2029,11 @@ static void do_enqueue_task(struct rq *rq, struct task_struct *p, u64 enq_flags, unlikely(p->flags & PF_EXITING)) goto local; + /* see %SCX_OPS_ENQ_MIGRATION_DISABLED */ + if (!static_branch_unlikely(&scx_ops_enq_migration_disabled) && + is_migration_disabled(p)) + goto local; + if (!SCX_HAS_OP(enqueue)) goto global; @@ -2078,7 +2098,7 @@ static void set_task_runnable(struct rq *rq, struct task_struct *p) /* * list_add_tail() must be used. scx_ops_bypass() depends on tasks being - * appened to the runnable_list. + * appended to the runnable_list. */ list_add_tail(&p->scx.runnable_node, &rq->scx.runnable_list); } @@ -2313,12 +2333,35 @@ static void move_remote_task_to_local_dsq(struct task_struct *p, u64 enq_flags, * * - The BPF scheduler is bypassed while the rq is offline and we can always say * no to the BPF scheduler initiated migrations while offline. + * + * The caller must ensure that @p and @rq are on different CPUs. */ static bool task_can_run_on_remote_rq(struct task_struct *p, struct rq *rq, bool trigger_error) { int cpu = cpu_of(rq); + SCHED_WARN_ON(task_cpu(p) == cpu); + + /* + * If @p has migration disabled, @p->cpus_ptr is updated to contain only + * the pinned CPU in migrate_disable_switch() while @p is being switched + * out. However, put_prev_task_scx() is called before @p->cpus_ptr is + * updated and thus another CPU may see @p on a DSQ inbetween leading to + * @p passing the below task_allowed_on_cpu() check while migration is + * disabled. + * + * Test the migration disabled state first as the race window is narrow + * and the BPF scheduler failing to check migration disabled state can + * easily be masked if task_allowed_on_cpu() is done first. + */ + if (unlikely(is_migration_disabled(p))) { + if (trigger_error) + scx_ops_error("SCX_DSQ_LOCAL[_ON] cannot move migration disabled %s[%d] from CPU %d to %d", + p->comm, p->pid, task_cpu(p), cpu); + return false; + } + /* * We don't require the BPF scheduler to avoid dispatching to offline * CPUs mostly for convenience but also because CPUs can go offline @@ -2327,14 +2370,11 @@ static bool task_can_run_on_remote_rq(struct task_struct *p, struct rq *rq, */ if (!task_allowed_on_cpu(p, cpu)) { if (trigger_error) - scx_ops_error("SCX_DSQ_LOCAL[_ON] verdict target cpu %d not allowed for %s[%d]", - cpu_of(rq), p->comm, p->pid); + scx_ops_error("SCX_DSQ_LOCAL[_ON] target CPU %d not allowed for %s[%d]", + cpu, p->comm, p->pid); return false; } - if (unlikely(is_migration_disabled(p))) - return false; - if (!scx_rq_online(rq)) return false; @@ -2437,7 +2477,8 @@ static struct rq *move_task_between_dsqs(struct task_struct *p, u64 enq_flags, if (dst_dsq->id == SCX_DSQ_LOCAL) { dst_rq = container_of(dst_dsq, struct rq, scx.local_dsq); - if (!task_can_run_on_remote_rq(p, dst_rq, true)) { + if (src_rq != dst_rq && + unlikely(!task_can_run_on_remote_rq(p, dst_rq, true))) { dst_dsq = find_global_dsq(p); dst_rq = src_rq; } @@ -2480,7 +2521,7 @@ static struct rq *move_task_between_dsqs(struct task_struct *p, u64 enq_flags, /* * A poorly behaving BPF scheduler can live-lock the system by e.g. incessantly * banging on the same DSQ on a large NUMA system to the point where switching - * to the bypass mode can take a long time. Inject artifical delays while the + * to the bypass mode can take a long time. Inject artificial delays while the * bypass mode is switching to guarantee timely completion. */ static void scx_ops_breather(struct rq *rq) @@ -2575,6 +2616,9 @@ static void dispatch_to_local_dsq(struct rq *rq, struct scx_dispatch_q *dst_dsq, { struct rq *src_rq = task_rq(p); struct rq *dst_rq = container_of(dst_dsq, struct rq, scx.local_dsq); +#ifdef CONFIG_SMP + struct rq *locked_rq = rq; +#endif /* * We're synchronized against dequeue through DISPATCHING. As @p can't @@ -2588,7 +2632,8 @@ static void dispatch_to_local_dsq(struct rq *rq, struct scx_dispatch_q *dst_dsq, } #ifdef CONFIG_SMP - if (unlikely(!task_can_run_on_remote_rq(p, dst_rq, true))) { + if (src_rq != dst_rq && + unlikely(!task_can_run_on_remote_rq(p, dst_rq, true))) { dispatch_enqueue(find_global_dsq(p), p, enq_flags | SCX_ENQ_CLEAR_OPSS); return; @@ -2611,8 +2656,9 @@ static void dispatch_to_local_dsq(struct rq *rq, struct scx_dispatch_q *dst_dsq, atomic_long_set_release(&p->scx.ops_state, SCX_OPSS_NONE); /* switch to @src_rq lock */ - if (rq != src_rq) { - raw_spin_rq_unlock(rq); + if (locked_rq != src_rq) { + raw_spin_rq_unlock(locked_rq); + locked_rq = src_rq; raw_spin_rq_lock(src_rq); } @@ -2630,6 +2676,8 @@ static void dispatch_to_local_dsq(struct rq *rq, struct scx_dispatch_q *dst_dsq, } else { move_remote_task_to_local_dsq(p, enq_flags, src_rq, dst_rq); + /* task has been moved to dst_rq, which is now locked */ + locked_rq = dst_rq; } /* if the destination CPU is idle, wake it up */ @@ -2638,8 +2686,8 @@ static void dispatch_to_local_dsq(struct rq *rq, struct scx_dispatch_q *dst_dsq, } /* switch back to @rq lock */ - if (rq != dst_rq) { - raw_spin_rq_unlock(dst_rq); + if (locked_rq != rq) { + raw_spin_rq_unlock(locked_rq); raw_spin_rq_lock(rq); } #else /* CONFIG_SMP */ @@ -3144,7 +3192,7 @@ static struct task_struct *pick_task_scx(struct rq *rq) * * Unless overridden by ops.core_sched_before(), @p->scx.core_sched_at is used * to implement the default task ordering. The older the timestamp, the higher - * prority the task - the global FIFO ordering matching the default scheduling + * priority the task - the global FIFO ordering matching the default scheduling * behavior. * * When ops.core_sched_before() is enabled, @p->scx.core_sched_at is used to @@ -3851,7 +3899,7 @@ static void task_tick_scx(struct rq *rq, struct task_struct *curr, int queued) curr->scx.slice = 0; touch_core_sched(rq, curr); } else if (SCX_HAS_OP(tick)) { - SCX_CALL_OP(SCX_KF_REST, tick, curr); + SCX_CALL_OP_TASK(SCX_KF_REST, tick, curr); } if (!curr->scx.slice) @@ -3998,7 +4046,7 @@ static void scx_ops_disable_task(struct task_struct *p) WARN_ON_ONCE(scx_get_task_state(p) != SCX_TASK_ENABLED); if (SCX_HAS_OP(disable)) - SCX_CALL_OP(SCX_KF_REST, disable, p); + SCX_CALL_OP_TASK(SCX_KF_REST, disable, p); scx_set_task_state(p, SCX_TASK_READY); } @@ -4027,7 +4075,7 @@ static void scx_ops_exit_task(struct task_struct *p) } if (SCX_HAS_OP(exit_task)) - SCX_CALL_OP(SCX_KF_REST, exit_task, p, &args); + SCX_CALL_OP_TASK(SCX_KF_REST, exit_task, p, &args); scx_set_task_state(p, SCX_TASK_NONE); } @@ -4323,25 +4371,12 @@ err: return ops_sanitize_err("cgroup_prep_move", ret); } -void scx_move_task(struct task_struct *p) +void scx_cgroup_move_task(struct task_struct *p) { if (!scx_cgroup_enabled) return; /* - * We're called from sched_move_task() which handles both cgroup and - * autogroup moves. Ignore the latter. - * - * Also ignore exiting tasks, because in the exit path tasks transition - * from the autogroup to the root group, so task_group_is_autogroup() - * alone isn't able to catch exiting autogroup tasks. This is safe for - * cgroup_move(), because cgroup migrations never happen for PF_EXITING - * tasks. - */ - if (task_group_is_autogroup(task_group(p)) || (p->flags & PF_EXITING)) - return; - - /* * @p must have ops.cgroup_prep_move() called on it and thus * cgrp_moving_from set. */ @@ -4590,7 +4625,7 @@ static int scx_cgroup_init(void) cgroup_warned_missing_idle = false; /* - * scx_tg_on/offline() are excluded thorugh scx_cgroup_rwsem. If we walk + * scx_tg_on/offline() are excluded through scx_cgroup_rwsem. If we walk * cgroups and init, all online cgroups are initialized. */ rcu_read_lock(); @@ -5059,6 +5094,7 @@ static void scx_ops_disable_workfn(struct kthread_work *work) static_branch_disable(&scx_has_op[i]); static_branch_disable(&scx_ops_enq_last); static_branch_disable(&scx_ops_enq_exiting); + static_branch_disable(&scx_ops_enq_migration_disabled); static_branch_disable(&scx_ops_cpu_preempt); static_branch_disable(&scx_builtin_idle_enabled); synchronize_rcu(); @@ -5277,9 +5313,10 @@ static void scx_dump_task(struct seq_buf *s, struct scx_dump_ctx *dctx, scx_get_task_state(p), p->scx.flags & ~SCX_TASK_STATE_MASK, p->scx.dsq_flags, ops_state & SCX_OPSS_STATE_MASK, ops_state >> SCX_OPSS_QSEQ_SHIFT); - dump_line(s, " sticky/holding_cpu=%d/%d dsq_id=%s dsq_vtime=%llu slice=%llu", - p->scx.sticky_cpu, p->scx.holding_cpu, dsq_id_buf, - p->scx.dsq_vtime, p->scx.slice); + dump_line(s, " sticky/holding_cpu=%d/%d dsq_id=%s", + p->scx.sticky_cpu, p->scx.holding_cpu, dsq_id_buf); + dump_line(s, " dsq_vtime=%llu slice=%llu weight=%u", + p->scx.dsq_vtime, p->scx.slice, p->scx.weight); dump_line(s, " cpus=%*pb", cpumask_pr_args(p->cpus_ptr)); if (SCX_HAS_OP(dump_task)) { @@ -5667,6 +5704,8 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link) if (ops->flags & SCX_OPS_ENQ_EXITING) static_branch_enable(&scx_ops_enq_exiting); + if (ops->flags & SCX_OPS_ENQ_MIGRATION_DISABLED) + static_branch_enable(&scx_ops_enq_migration_disabled); if (scx_ops.cpu_acquire || scx_ops.cpu_release) static_branch_enable(&scx_ops_cpu_preempt); diff --git a/kernel/sched/ext.h b/kernel/sched/ext.h index 4d022d17ac7d..1079b56b0f7a 100644 --- a/kernel/sched/ext.h +++ b/kernel/sched/ext.h @@ -73,7 +73,7 @@ static inline void scx_update_idle(struct rq *rq, bool idle, bool do_notify) {} int scx_tg_online(struct task_group *tg); void scx_tg_offline(struct task_group *tg); int scx_cgroup_can_attach(struct cgroup_taskset *tset); -void scx_move_task(struct task_struct *p); +void scx_cgroup_move_task(struct task_struct *p); void scx_cgroup_finish_attach(void); void scx_cgroup_cancel_attach(struct cgroup_taskset *tset); void scx_group_set_weight(struct task_group *tg, unsigned long cgrp_weight); @@ -82,7 +82,7 @@ void scx_group_set_idle(struct task_group *tg, bool idle); static inline int scx_tg_online(struct task_group *tg) { return 0; } static inline void scx_tg_offline(struct task_group *tg) {} static inline int scx_cgroup_can_attach(struct cgroup_taskset *tset) { return 0; } -static inline void scx_move_task(struct task_struct *p) {} +static inline void scx_cgroup_move_task(struct task_struct *p) {} static inline void scx_cgroup_finish_attach(void) {} static inline void scx_cgroup_cancel_attach(struct cgroup_taskset *tset) {} static inline void scx_group_set_weight(struct task_group *tg, unsigned long cgrp_weight) {} diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 38e0e323dda2..b93c8c3dc05a 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -572,7 +572,7 @@ extern void sched_online_group(struct task_group *tg, extern void sched_destroy_group(struct task_group *tg); extern void sched_release_group(struct task_group *tg); -extern void sched_move_task(struct task_struct *tsk); +extern void sched_move_task(struct task_struct *tsk, bool for_autogroup); #ifdef CONFIG_FAIR_GROUP_SCHED extern int sched_group_set_shares(struct task_group *tg, unsigned long shares); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index b8e0ae15ca5b..bb6089c2951e 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1672,7 +1672,8 @@ static void *rb_range_buffer(struct ring_buffer_per_cpu *cpu_buffer, int idx) * must be the same. */ static bool rb_meta_valid(struct ring_buffer_meta *meta, int cpu, - struct trace_buffer *buffer, int nr_pages) + struct trace_buffer *buffer, int nr_pages, + unsigned long *subbuf_mask) { int subbuf_size = PAGE_SIZE; struct buffer_data_page *subbuf; @@ -1680,6 +1681,9 @@ static bool rb_meta_valid(struct ring_buffer_meta *meta, int cpu, unsigned long buffers_end; int i; + if (!subbuf_mask) + return false; + /* Check the meta magic and meta struct size */ if (meta->magic != RING_BUFFER_META_MAGIC || meta->struct_size != sizeof(*meta)) { @@ -1712,6 +1716,8 @@ static bool rb_meta_valid(struct ring_buffer_meta *meta, int cpu, subbuf = rb_subbufs_from_meta(meta); + bitmap_clear(subbuf_mask, 0, meta->nr_subbufs); + /* Is the meta buffers and the subbufs themselves have correct data? */ for (i = 0; i < meta->nr_subbufs; i++) { if (meta->buffers[i] < 0 || @@ -1725,6 +1731,12 @@ static bool rb_meta_valid(struct ring_buffer_meta *meta, int cpu, return false; } + if (test_bit(meta->buffers[i], subbuf_mask)) { + pr_info("Ring buffer boot meta [%d] array has duplicates\n", cpu); + return false; + } + + set_bit(meta->buffers[i], subbuf_mask); subbuf = (void *)subbuf + subbuf_size; } @@ -1838,6 +1850,11 @@ static void rb_meta_validate_events(struct ring_buffer_per_cpu *cpu_buffer) cpu_buffer->cpu); goto invalid; } + + /* If the buffer has content, update pages_touched */ + if (ret) + local_inc(&cpu_buffer->pages_touched); + entries += ret; entry_bytes += local_read(&head_page->page->commit); local_set(&cpu_buffer->head_page->entries, ret); @@ -1889,17 +1906,22 @@ static void rb_meta_init_text_addr(struct ring_buffer_meta *meta) static void rb_range_meta_init(struct trace_buffer *buffer, int nr_pages) { struct ring_buffer_meta *meta; + unsigned long *subbuf_mask; unsigned long delta; void *subbuf; int cpu; int i; + /* Create a mask to test the subbuf array */ + subbuf_mask = bitmap_alloc(nr_pages + 1, GFP_KERNEL); + /* If subbuf_mask fails to allocate, then rb_meta_valid() will return false */ + for (cpu = 0; cpu < nr_cpu_ids; cpu++) { void *next_meta; meta = rb_range_meta(buffer, nr_pages, cpu); - if (rb_meta_valid(meta, cpu, buffer, nr_pages)) { + if (rb_meta_valid(meta, cpu, buffer, nr_pages, subbuf_mask)) { /* Make the mappings match the current address */ subbuf = rb_subbufs_from_meta(meta); delta = (unsigned long)subbuf - meta->first_buffer; @@ -1943,6 +1965,7 @@ static void rb_range_meta_init(struct trace_buffer *buffer, int nr_pages) subbuf += meta->subbuf_size; } } + bitmap_free(subbuf_mask); } static void *rbm_start(struct seq_file *m, loff_t *pos) @@ -7126,6 +7149,7 @@ int ring_buffer_map(struct trace_buffer *buffer, int cpu, kfree(cpu_buffer->subbuf_ids); cpu_buffer->subbuf_ids = NULL; rb_free_meta_page(cpu_buffer); + atomic_dec(&cpu_buffer->resize_disabled); } unlock: diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 1496a5ac33ae..0e6d517e74e0 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -5977,8 +5977,6 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr, ssize_t tracing_resize_ring_buffer(struct trace_array *tr, unsigned long size, int cpu_id) { - int ret; - guard(mutex)(&trace_types_lock); if (cpu_id != RING_BUFFER_ALL_CPUS) { @@ -5987,11 +5985,7 @@ ssize_t tracing_resize_ring_buffer(struct trace_array *tr, return -EINVAL; } - ret = __tracing_resize_ring_buffer(tr, size, cpu_id); - if (ret < 0) - ret = -ENOMEM; - - return ret; + return __tracing_resize_ring_buffer(tr, size, cpu_id); } static void update_last_data(struct trace_array *tr) @@ -8285,6 +8279,10 @@ static int tracing_buffers_mmap(struct file *filp, struct vm_area_struct *vma) struct trace_iterator *iter = &info->iter; int ret = 0; + /* Currently the boot mapped buffer is not supported for mmap */ + if (iter->tr->flags & TRACE_ARRAY_FL_BOOT) + return -ENODEV; + ret = get_snapshot_map(iter->tr); if (ret) return ret; diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 3c2c45313c88..97152f2250fe 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -3517,12 +3517,6 @@ repeat: } /* - * Put the reference grabbed by send_mayday(). @pool won't - * go away while we're still attached to it. - */ - put_pwq(pwq); - - /* * Leave this pool. Notify regular workers; otherwise, we end up * with 0 concurrency and stalling the execution. */ @@ -3532,6 +3526,12 @@ repeat: worker_detach_from_pool(rescuer); + /* + * Put the reference grabbed by send_mayday(). @pool might + * go away any time after it. + */ + put_pwq_unlocked(pwq); + raw_spin_lock_irq(&wq_mayday_lock); } diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 9ec806f989f2..65f550cb5081 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -1428,6 +1428,8 @@ static ssize_t __import_iovec_ubuf(int type, const struct iovec __user *uvec, struct iovec *iov = *iovp; ssize_t ret; + *iovp = NULL; + if (compat) ret = copy_compat_iovec_from_user(iov, uvec, 1); else @@ -1438,7 +1440,6 @@ static ssize_t __import_iovec_ubuf(int type, const struct iovec __user *uvec, ret = import_ubuf(type, iov->iov_base, iov->iov_len, i); if (unlikely(ret)) return ret; - *iovp = NULL; return i->count; } diff --git a/lib/test_xarray.c b/lib/test_xarray.c index 6932a26f4927..0e865bab4a10 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -1418,7 +1418,7 @@ static noinline void check_pause(struct xarray *xa) { XA_STATE(xas, xa, 0); void *entry; - unsigned int order; + int order; unsigned long index = 1; unsigned int count = 0; @@ -1450,7 +1450,7 @@ static noinline void check_pause(struct xarray *xa) xa_destroy(xa); index = 0; - for (order = XA_CHUNK_SHIFT; order > 0; order--) { + for (order = order_limit - 1; order >= 0; order--) { XA_BUG_ON(xa, xa_store_order(xa, index, order, xa_mk_index(index), GFP_KERNEL)); index += 1UL << order; @@ -1462,24 +1462,25 @@ static noinline void check_pause(struct xarray *xa) rcu_read_lock(); xas_for_each(&xas, entry, ULONG_MAX) { XA_BUG_ON(xa, entry != xa_mk_index(index)); - index += 1UL << (XA_CHUNK_SHIFT - count); + index += 1UL << (order_limit - count - 1); count++; } rcu_read_unlock(); - XA_BUG_ON(xa, count != XA_CHUNK_SHIFT); + XA_BUG_ON(xa, count != order_limit); index = 0; count = 0; - xas_set(&xas, XA_CHUNK_SIZE / 2 + 1); + /* test unaligned index */ + xas_set(&xas, 1 % (1UL << (order_limit - 1))); rcu_read_lock(); xas_for_each(&xas, entry, ULONG_MAX) { XA_BUG_ON(xa, entry != xa_mk_index(index)); - index += 1UL << (XA_CHUNK_SHIFT - count); + index += 1UL << (order_limit - count - 1); count++; xas_pause(&xas); } rcu_read_unlock(); - XA_BUG_ON(xa, count != XA_CHUNK_SHIFT); + XA_BUG_ON(xa, count != order_limit); xa_destroy(xa); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 65068671e460..163190e89ea1 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3145,7 +3145,7 @@ int __alloc_bootmem_huge_page(struct hstate *h, int nid) /* do node specific alloc */ if (nid != NUMA_NO_NODE) { - m = memblock_alloc_try_nid_raw(huge_page_size(h), huge_page_size(h), + m = memblock_alloc_exact_nid_raw(huge_page_size(h), huge_page_size(h), 0, MEMBLOCK_ALLOC_ACCESSIBLE, nid); if (!m) return 0; diff --git a/mm/kasan/report.c b/mm/kasan/report.c index 3fe77a360f1c..8357e1a33699 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -370,6 +370,36 @@ static inline bool init_task_stack_addr(const void *addr) sizeof(init_thread_union.stack)); } +/* + * This function is invoked with report_lock (a raw_spinlock) held. A + * PREEMPT_RT kernel cannot call find_vm_area() as it will acquire a sleeping + * rt_spinlock. + * + * For !RT kernel, the PROVE_RAW_LOCK_NESTING config option will print a + * lockdep warning for this raw_spinlock -> spinlock dependency. This config + * option is enabled by default to ensure better test coverage to expose this + * kind of RT kernel problem. This lockdep splat, however, can be suppressed + * by using DEFINE_WAIT_OVERRIDE_MAP() if it serves a useful purpose and the + * invalid PREEMPT_RT case has been taken care of. + */ +static inline struct vm_struct *kasan_find_vm_area(void *addr) +{ + static DEFINE_WAIT_OVERRIDE_MAP(vmalloc_map, LD_WAIT_SLEEP); + struct vm_struct *va; + + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + return NULL; + + /* + * Suppress lockdep warning and fetch vmalloc area of the + * offending address. + */ + lock_map_acquire_try(&vmalloc_map); + va = find_vm_area(addr); + lock_map_release(&vmalloc_map); + return va; +} + static void print_address_description(void *addr, u8 tag, struct kasan_report_info *info) { @@ -399,7 +429,7 @@ static void print_address_description(void *addr, u8 tag, } if (is_vmalloc_addr(addr)) { - struct vm_struct *va = find_vm_area(addr); + struct vm_struct *va = kasan_find_vm_area(addr); if (va) { pr_err("The buggy address belongs to the virtual mapping at\n" @@ -409,6 +439,8 @@ static void print_address_description(void *addr, u8 tag, pr_err("\n"); page = vmalloc_to_page(addr); + } else { + pr_err("The buggy address %px belongs to a vmalloc virtual mapping\n", addr); } } diff --git a/mm/madvise.c b/mm/madvise.c index 49f3a75046f6..08b207f8e61e 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -933,7 +933,16 @@ static long madvise_dontneed_free(struct vm_area_struct *vma, */ end = vma->vm_end; } - VM_WARN_ON(start >= end); + /* + * If the memory region between start and end was + * originally backed by 4kB pages and then remapped to + * be backed by hugepages while mmap_lock was dropped, + * the adjustment for hugetlb vma above may have rounded + * end down to the start address. + */ + if (start == end) + return 0; + VM_WARN_ON(start > end); } if (behavior == MADV_DONTNEED || behavior == MADV_DONTNEED_LOCKED) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 46f8b372d212..4de6acb9b8ec 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4166,6 +4166,7 @@ static ssize_t memory_max_write(struct kernfs_open_file *of, memcg_memory_event(memcg, MEMCG_OOM); if (!mem_cgroup_out_of_memory(memcg, GFP_KERNEL, 0)) break; + cond_resched(); } memcg_wb_domain_size_changed(memcg); diff --git a/mm/memory.c b/mm/memory.c index 539c0f7c6d54..b4d3d4893267 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1719,7 +1719,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, pmd_t pmdval; unsigned long start = addr; bool can_reclaim_pt = reclaim_pt_is_enabled(start, end, details); - bool direct_reclaim = false; + bool direct_reclaim = true; int nr; retry: @@ -1734,8 +1734,10 @@ retry: do { bool any_skipped = false; - if (need_resched()) + if (need_resched()) { + direct_reclaim = false; break; + } nr = do_zap_pte_range(tlb, vma, pte, addr, end, details, rss, &force_flush, &force_break, &any_skipped); @@ -1743,11 +1745,20 @@ retry: can_reclaim_pt = false; if (unlikely(force_break)) { addr += nr * PAGE_SIZE; + direct_reclaim = false; break; } } while (pte += nr, addr += PAGE_SIZE * nr, addr != end); - if (can_reclaim_pt && addr == end) + /* + * Fast path: try to hold the pmd lock and unmap the PTE page. + * + * If the pte lock was released midway (retry case), or if the attempt + * to hold the pmd lock failed, then we need to recheck all pte entries + * to ensure they are still none, thereby preventing the pte entries + * from being repopulated by another thread. + */ + if (can_reclaim_pt && direct_reclaim && addr == end) direct_reclaim = try_get_and_clear_pmd(mm, pmd, &pmdval); add_mm_rss_vec(mm, rss); diff --git a/mm/migrate_device.c b/mm/migrate_device.c index 9cf26592ac93..5bd888223cc8 100644 --- a/mm/migrate_device.c +++ b/mm/migrate_device.c @@ -840,20 +840,15 @@ void migrate_device_finalize(unsigned long *src_pfns, dst = src; } + if (!folio_is_zone_device(dst)) + folio_add_lru(dst); remove_migration_ptes(src, dst, 0); folio_unlock(src); - - if (folio_is_zone_device(src)) - folio_put(src); - else - folio_putback_lru(src); + folio_put(src); if (dst != src) { folio_unlock(dst); - if (folio_is_zone_device(dst)) - folio_put(dst); - else - folio_putback_lru(dst); + folio_put(dst); } } } diff --git a/mm/zswap.c b/mm/zswap.c index 6504174fbc6a..ac9d299e7d0c 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -1445,9 +1445,9 @@ resched: * main API **********************************/ -static ssize_t zswap_store_page(struct page *page, - struct obj_cgroup *objcg, - struct zswap_pool *pool) +static bool zswap_store_page(struct page *page, + struct obj_cgroup *objcg, + struct zswap_pool *pool) { swp_entry_t page_swpentry = page_swap_entry(page); struct zswap_entry *entry, *old; @@ -1456,7 +1456,7 @@ static ssize_t zswap_store_page(struct page *page, entry = zswap_entry_cache_alloc(GFP_KERNEL, page_to_nid(page)); if (!entry) { zswap_reject_kmemcache_fail++; - return -EINVAL; + return false; } if (!zswap_compress(page, entry, pool)) @@ -1483,13 +1483,17 @@ static ssize_t zswap_store_page(struct page *page, /* * The entry is successfully compressed and stored in the tree, there is - * no further possibility of failure. Grab refs to the pool and objcg. - * These refs will be dropped by zswap_entry_free() when the entry is - * removed from the tree. + * no further possibility of failure. Grab refs to the pool and objcg, + * charge zswap memory, and increment zswap_stored_pages. + * The opposite actions will be performed by zswap_entry_free() + * when the entry is removed from the tree. */ zswap_pool_get(pool); - if (objcg) + if (objcg) { obj_cgroup_get(objcg); + obj_cgroup_charge_zswap(objcg, entry->length); + } + atomic_long_inc(&zswap_stored_pages); /* * We finish initializing the entry while it's already in xarray. @@ -1510,13 +1514,13 @@ static ssize_t zswap_store_page(struct page *page, zswap_lru_add(&zswap_list_lru, entry); } - return entry->length; + return true; store_failed: zpool_free(pool->zpool, entry->handle); compress_failed: zswap_entry_cache_free(entry); - return -EINVAL; + return false; } bool zswap_store(struct folio *folio) @@ -1526,7 +1530,6 @@ bool zswap_store(struct folio *folio) struct obj_cgroup *objcg = NULL; struct mem_cgroup *memcg = NULL; struct zswap_pool *pool; - size_t compressed_bytes = 0; bool ret = false; long index; @@ -1564,20 +1567,14 @@ bool zswap_store(struct folio *folio) for (index = 0; index < nr_pages; ++index) { struct page *page = folio_page(folio, index); - ssize_t bytes; - bytes = zswap_store_page(page, objcg, pool); - if (bytes < 0) + if (!zswap_store_page(page, objcg, pool)) goto put_pool; - compressed_bytes += bytes; } - if (objcg) { - obj_cgroup_charge_zswap(objcg, compressed_bytes); + if (objcg) count_objcg_events(objcg, ZSWPOUT, nr_pages); - } - atomic_long_add(nr_pages, &zswap_stored_pages); count_vm_events(ZSWPOUT, nr_pages); ret = true; diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c index 134419667d59..a000b1ef0520 100644 --- a/net/8021q/vlan_netlink.c +++ b/net/8021q/vlan_netlink.c @@ -135,11 +135,14 @@ static int vlan_changelink(struct net_device *dev, struct nlattr *tb[], return 0; } -static int vlan_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +static int vlan_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { + struct net *link_net = rtnl_newlink_link_net(params); struct vlan_dev_priv *vlan = vlan_dev_priv(dev); + struct nlattr **data = params->data; + struct nlattr **tb = params->tb; struct net_device *real_dev; unsigned int max_mtu; __be16 proto; @@ -155,7 +158,7 @@ static int vlan_newlink(struct net *src_net, struct net_device *dev, return -EINVAL; } - real_dev = __dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK])); + real_dev = __dev_get_by_index(link_net, nla_get_u32(tb[IFLA_LINK])); if (!real_dev) { NL_SET_ERR_MSG_MOD(extack, "link does not exist"); return -ENODEV; diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 822d788a5f86..d893c8013261 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -1077,19 +1077,18 @@ static int batadv_softif_validate(struct nlattr *tb[], struct nlattr *data[], /** * batadv_softif_newlink() - pre-initialize and register new batadv link - * @src_net: the applicable net namespace * @dev: network device to register - * @tb: IFLA_INFO_DATA netlink attributes - * @data: enum batadv_ifla_attrs attributes + * @params: rtnl newlink parameters * @extack: extended ACK report struct * * Return: 0 if successful or error otherwise. */ -static int batadv_softif_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +static int batadv_softif_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct batadv_priv *bat_priv = netdev_priv(dev); + struct nlattr **data = params->data; const char *algo_name; int err; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 3e0f47203f2a..6e337937d0d7 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -1553,11 +1553,13 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], return 0; } -static int br_dev_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +static int br_dev_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct net_bridge *br = netdev_priv(dev); + struct nlattr **data = params->data; + struct nlattr **tb = params->tb; int err; err = register_netdevice(dev); diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c index 94ad09e36df2..fa6a3c2634a8 100644 --- a/net/caif/chnl_net.c +++ b/net/caif/chnl_net.c @@ -438,10 +438,11 @@ static void caif_netlink_parms(struct nlattr *data[], } } -static int ipcaif_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +static int ipcaif_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { + struct nlattr **data = params->data; int ret; struct chnl_net *caifdev; ASSERT_RTNL(); diff --git a/net/can/raw.c b/net/can/raw.c index 46e8ed9d64da..9b1d5f036f57 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -963,7 +963,7 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) skb->dev = dev; skb->priority = sockc.priority; - skb->mark = READ_ONCE(sk->sk_mark); + skb->mark = sockc.mark; skb->tstamp = sockc.transmit_time; skb_setup_tx_timestamp(skb, &sockc); diff --git a/net/core/dev.c b/net/core/dev.c index 436f2bdfb2d5..8c7ee7ada6a3 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1008,7 +1008,7 @@ struct net_device *dev_get_by_napi_id(unsigned int napi_id) WARN_ON_ONCE(!rcu_read_lock_held()); - if (napi_id < MIN_NAPI_ID) + if (!napi_id_valid(napi_id)) return NULL; napi = napi_by_id(napi_id); @@ -1122,6 +1122,12 @@ out: return ret; } +static bool dev_addr_cmp(struct net_device *dev, unsigned short type, + const char *ha) +{ + return dev->type == type && !memcmp(dev->dev_addr, ha, dev->addr_len); +} + /** * dev_getbyhwaddr_rcu - find a device by its hardware address * @net: the applicable net namespace @@ -1130,7 +1136,7 @@ out: * * Search for an interface by MAC address. Returns NULL if the device * is not found or a pointer to the device. - * The caller must hold RCU or RTNL. + * The caller must hold RCU. * The returned device has not had its ref count increased * and the caller must therefore be careful about locking * @@ -1142,14 +1148,39 @@ struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type, struct net_device *dev; for_each_netdev_rcu(net, dev) - if (dev->type == type && - !memcmp(dev->dev_addr, ha, dev->addr_len)) + if (dev_addr_cmp(dev, type, ha)) return dev; return NULL; } EXPORT_SYMBOL(dev_getbyhwaddr_rcu); +/** + * dev_getbyhwaddr() - find a device by its hardware address + * @net: the applicable net namespace + * @type: media type of device + * @ha: hardware address + * + * Similar to dev_getbyhwaddr_rcu(), but the owner needs to hold + * rtnl_lock. + * + * Context: rtnl_lock() must be held. + * Return: pointer to the net_device, or NULL if not found + */ +struct net_device *dev_getbyhwaddr(struct net *net, unsigned short type, + const char *ha) +{ + struct net_device *dev; + + ASSERT_RTNL(); + for_each_netdev(net, dev) + if (dev_addr_cmp(dev, type, ha)) + return dev; + + return NULL; +} +EXPORT_SYMBOL(dev_getbyhwaddr); + struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type) { struct net_device *dev, *ret = NULL; @@ -2071,6 +2102,42 @@ static void __move_netdevice_notifier_net(struct net *src_net, __register_netdevice_notifier_net(dst_net, nb, true); } +static void rtnl_net_dev_lock(struct net_device *dev) +{ + bool again; + + do { + struct net *net; + + again = false; + + /* netns might be being dismantled. */ + rcu_read_lock(); + net = dev_net_rcu(dev); + net_passive_inc(net); + rcu_read_unlock(); + + rtnl_net_lock(net); + +#ifdef CONFIG_NET_NS + /* dev might have been moved to another netns. */ + if (!net_eq(net, rcu_access_pointer(dev->nd_net.net))) { + rtnl_net_unlock(net); + net_passive_dec(net); + again = true; + } +#endif + } while (again); +} + +static void rtnl_net_dev_unlock(struct net_device *dev) +{ + struct net *net = dev_net(dev); + + rtnl_net_unlock(net); + net_passive_dec(net); +} + int register_netdevice_notifier_dev_net(struct net_device *dev, struct notifier_block *nb, struct netdev_net_notifier *nn) @@ -2078,6 +2145,11 @@ int register_netdevice_notifier_dev_net(struct net_device *dev, struct net *net = dev_net(dev); int err; + /* rtnl_net_lock() assumes dev is not yet published by + * register_netdevice(). + */ + DEBUG_NET_WARN_ON_ONCE(!list_empty(&dev->dev_list)); + rtnl_net_lock(net); err = __register_netdevice_notifier_net(net, nb, false); if (!err) { @@ -2094,13 +2166,12 @@ int unregister_netdevice_notifier_dev_net(struct net_device *dev, struct notifier_block *nb, struct netdev_net_notifier *nn) { - struct net *net = dev_net(dev); int err; - rtnl_net_lock(net); + rtnl_net_dev_lock(dev); list_del(&nn->list); - err = __unregister_netdevice_notifier_net(net, nb); - rtnl_net_unlock(net); + err = __unregister_netdevice_notifier_net(dev_net(dev), nb); + rtnl_net_dev_unlock(dev); return err; } @@ -6741,7 +6812,7 @@ static void napi_hash_add(struct napi_struct *napi) /* 0..NR_CPUS range is reserved for sender_cpu use */ do { - if (unlikely(++napi_gen_id < MIN_NAPI_ID)) + if (unlikely(!napi_id_valid(++napi_gen_id))) napi_gen_id = MIN_NAPI_ID; } while (napi_by_id(napi_gen_id)); @@ -6912,7 +6983,7 @@ netif_napi_dev_list_add(struct net_device *dev, struct napi_struct *napi) higher = &dev->napi_list; list_for_each_entry(pos, &dev->napi_list, dev_list) { - if (pos->napi_id >= MIN_NAPI_ID) + if (napi_id_valid(pos->napi_id)) pos_id = pos->napi_id; else if (pos->config) pos_id = pos->config->napi_id; @@ -6926,6 +6997,23 @@ netif_napi_dev_list_add(struct net_device *dev, struct napi_struct *napi) list_add_rcu(&napi->dev_list, higher); /* adds after higher */ } +/* Double check that napi_get_frags() allocates skbs with + * skb->head being backed by slab, not a page fragment. + * This is to make sure bug fixed in 3226b158e67c + * ("net: avoid 32 x truesize under-estimation for tiny skbs") + * does not accidentally come back. + */ +static void napi_get_frags_check(struct napi_struct *napi) +{ + struct sk_buff *skb; + + local_bh_disable(); + skb = napi_get_frags(napi); + WARN_ON_ONCE(skb && skb->head_frag); + napi_free_frags(napi); + local_bh_enable(); +} + void netif_napi_add_weight_locked(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), @@ -9183,7 +9271,7 @@ int __dev_change_flags(struct net_device *dev, unsigned int flags, if ((flags ^ dev->gflags) & IFF_PROMISC) { int inc = (flags & IFF_PROMISC) ? 1 : -1; - unsigned int old_flags = dev->flags; + old_flags = dev->flags; dev->gflags ^= IFF_PROMISC; @@ -11902,11 +11990,9 @@ EXPORT_SYMBOL(unregister_netdevice_many); */ void unregister_netdev(struct net_device *dev) { - struct net *net = dev_net(dev); - - rtnl_net_lock(net); + rtnl_net_dev_lock(dev); unregister_netdevice(dev); - rtnl_net_unlock(net); + rtnl_net_dev_unlock(dev); } EXPORT_SYMBOL(unregister_netdev); diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 6efd4cccc9dd..212f0a048cab 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -1734,30 +1734,30 @@ static int __init init_net_drop_monitor(void) return -ENOSPC; } - rc = genl_register_family(&net_drop_monitor_family); - if (rc) { - pr_err("Could not create drop monitor netlink family\n"); - return rc; + for_each_possible_cpu(cpu) { + net_dm_cpu_data_init(cpu); + net_dm_hw_cpu_data_init(cpu); } - WARN_ON(net_drop_monitor_family.mcgrp_offset != NET_DM_GRP_ALERT); rc = register_netdevice_notifier(&dropmon_net_notifier); if (rc < 0) { pr_crit("Failed to register netdevice notifier\n"); + return rc; + } + + rc = genl_register_family(&net_drop_monitor_family); + if (rc) { + pr_err("Could not create drop monitor netlink family\n"); goto out_unreg; } + WARN_ON(net_drop_monitor_family.mcgrp_offset != NET_DM_GRP_ALERT); rc = 0; - for_each_possible_cpu(cpu) { - net_dm_cpu_data_init(cpu); - net_dm_hw_cpu_data_init(cpu); - } - goto out; out_unreg: - genl_unregister_family(&net_drop_monitor_family); + WARN_ON(unregister_netdevice_notifier(&dropmon_net_notifier)); out: return rc; } @@ -1766,19 +1766,18 @@ static void exit_net_drop_monitor(void) { int cpu; - BUG_ON(unregister_netdevice_notifier(&dropmon_net_notifier)); - /* * Because of the module_get/put we do in the trace state change path * we are guaranteed not to have any current users when we get here */ + BUG_ON(genl_unregister_family(&net_drop_monitor_family)); + + BUG_ON(unregister_netdevice_notifier(&dropmon_net_notifier)); for_each_possible_cpu(cpu) { net_dm_hw_cpu_data_fini(cpu); net_dm_cpu_data_fini(cpu); } - - BUG_ON(genl_unregister_family(&net_drop_monitor_family)); } module_init(init_net_drop_monitor); diff --git a/net/core/dst.c b/net/core/dst.c index 9552a90d4772..c99b95cf9cbb 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -286,7 +286,8 @@ struct metadata_dst *metadata_dst_alloc(u8 optslen, enum metadata_type type, { struct metadata_dst *md_dst; - md_dst = kmalloc(sizeof(*md_dst) + optslen, flags); + md_dst = kmalloc(struct_size(md_dst, u.tun_info.options, optslen), + flags); if (!md_dst) return NULL; @@ -314,7 +315,8 @@ metadata_dst_alloc_percpu(u8 optslen, enum metadata_type type, gfp_t flags) int cpu; struct metadata_dst __percpu *md_dst; - md_dst = __alloc_percpu_gfp(sizeof(struct metadata_dst) + optslen, + md_dst = __alloc_percpu_gfp(struct_size(md_dst, u.tun_info.options, + optslen), __alignof__(struct metadata_dst), flags); if (!md_dst) return NULL; diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 424b4cd4e9e5..5ddd34cbe7f6 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -481,11 +481,17 @@ static struct fib_rule *rule_find(struct fib_rules_ops *ops, &rule->sport_range)) continue; + if (rule->sport_mask && r->sport_mask != rule->sport_mask) + continue; + if (fib_rule_port_range_set(&rule->dport_range) && !fib_rule_port_range_compare(&r->dport_range, &rule->dport_range)) continue; + if (rule->dport_mask && r->dport_mask != rule->dport_mask) + continue; + if (!ops->compare(r, frh, tb)) continue; return r; @@ -515,6 +521,33 @@ static int fib_nl2rule_l3mdev(struct nlattr *nla, struct fib_rule *nlrule, } #endif +static int fib_nl2rule_port_mask(const struct nlattr *mask_attr, + const struct fib_rule_port_range *range, + u16 *port_mask, + struct netlink_ext_ack *extack) +{ + if (!fib_rule_port_range_valid(range)) { + NL_SET_ERR_MSG_ATTR(extack, mask_attr, + "Cannot specify port mask without port value"); + return -EINVAL; + } + + if (fib_rule_port_is_range(range)) { + NL_SET_ERR_MSG_ATTR(extack, mask_attr, + "Cannot specify port mask for port range"); + return -EINVAL; + } + + if (range->start & ~nla_get_u16(mask_attr)) { + NL_SET_ERR_MSG_ATTR(extack, mask_attr, "Invalid port mask"); + return -EINVAL; + } + + *port_mask = nla_get_u16(mask_attr); + + return 0; +} + static int fib_nl2rule(struct net *net, struct nlmsghdr *nlh, struct netlink_ext_ack *extack, struct fib_rules_ops *ops, @@ -644,6 +677,16 @@ static int fib_nl2rule(struct net *net, struct nlmsghdr *nlh, NL_SET_ERR_MSG(extack, "Invalid sport range"); goto errout_free; } + if (!fib_rule_port_is_range(&nlrule->sport_range)) + nlrule->sport_mask = U16_MAX; + } + + if (tb[FRA_SPORT_MASK]) { + err = fib_nl2rule_port_mask(tb[FRA_SPORT_MASK], + &nlrule->sport_range, + &nlrule->sport_mask, extack); + if (err) + goto errout_free; } if (tb[FRA_DPORT_RANGE]) { @@ -653,6 +696,16 @@ static int fib_nl2rule(struct net *net, struct nlmsghdr *nlh, NL_SET_ERR_MSG(extack, "Invalid dport range"); goto errout_free; } + if (!fib_rule_port_is_range(&nlrule->dport_range)) + nlrule->dport_mask = U16_MAX; + } + + if (tb[FRA_DPORT_MASK]) { + err = fib_nl2rule_port_mask(tb[FRA_DPORT_MASK], + &nlrule->dport_range, + &nlrule->dport_mask, extack); + if (err) + goto errout_free; } *rule = nlrule; @@ -751,10 +804,16 @@ static int rule_exists(struct fib_rules_ops *ops, struct fib_rule_hdr *frh, &rule->sport_range)) continue; + if (r->sport_mask != rule->sport_mask) + continue; + if (!fib_rule_port_range_compare(&r->dport_range, &rule->dport_range)) continue; + if (r->dport_mask != rule->dport_mask) + continue; + if (!ops->compare(r, frh, tb)) continue; return 1; @@ -784,6 +843,8 @@ static const struct nla_policy fib_rule_policy[FRA_MAX + 1] = { [FRA_DSCP] = NLA_POLICY_MAX(NLA_U8, INET_DSCP_MASK >> 2), [FRA_FLOWLABEL] = { .type = NLA_BE32 }, [FRA_FLOWLABEL_MASK] = { .type = NLA_BE32 }, + [FRA_SPORT_MASK] = { .type = NLA_U16 }, + [FRA_DPORT_MASK] = { .type = NLA_U16 }, }; int fib_newrule(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh, @@ -1049,7 +1110,9 @@ static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops, + nla_total_size(1) /* FRA_PROTOCOL */ + nla_total_size(1) /* FRA_IP_PROTO */ + nla_total_size(sizeof(struct fib_rule_port_range)) /* FRA_SPORT_RANGE */ - + nla_total_size(sizeof(struct fib_rule_port_range)); /* FRA_DPORT_RANGE */ + + nla_total_size(sizeof(struct fib_rule_port_range)) /* FRA_DPORT_RANGE */ + + nla_total_size(2) /* FRA_SPORT_MASK */ + + nla_total_size(2); /* FRA_DPORT_MASK */ if (ops->nlmsg_payload) payload += ops->nlmsg_payload(rule); @@ -1117,8 +1180,12 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, nla_put_uid_range(skb, &rule->uid_range)) || (fib_rule_port_range_set(&rule->sport_range) && nla_put_port_range(skb, FRA_SPORT_RANGE, &rule->sport_range)) || + (rule->sport_mask && nla_put_u16(skb, FRA_SPORT_MASK, + rule->sport_mask)) || (fib_rule_port_range_set(&rule->dport_range) && nla_put_port_range(skb, FRA_DPORT_RANGE, &rule->dport_range)) || + (rule->dport_mask && nla_put_u16(skb, FRA_DPORT_MASK, + rule->dport_mask)) || (rule->ip_proto && nla_put_u8(skb, FRA_IP_PROTO, rule->ip_proto))) goto nla_put_failure; diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 5db41bf2ed93..9cd8de6bebb5 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -853,23 +853,30 @@ __skb_flow_dissect_ports(const struct sk_buff *skb, void *target_container, const void *data, int nhoff, u8 ip_proto, int hlen) { - enum flow_dissector_key_id dissector_ports = FLOW_DISSECTOR_KEY_MAX; - struct flow_dissector_key_ports *key_ports; + struct flow_dissector_key_ports_range *key_ports_range = NULL; + struct flow_dissector_key_ports *key_ports = NULL; + __be32 ports; if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS)) - dissector_ports = FLOW_DISSECTOR_KEY_PORTS; - else if (dissector_uses_key(flow_dissector, - FLOW_DISSECTOR_KEY_PORTS_RANGE)) - dissector_ports = FLOW_DISSECTOR_KEY_PORTS_RANGE; + key_ports = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_PORTS, + target_container); - if (dissector_ports == FLOW_DISSECTOR_KEY_MAX) + if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS_RANGE)) + key_ports_range = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_PORTS_RANGE, + target_container); + + if (!key_ports && !key_ports_range) return; - key_ports = skb_flow_dissector_target(flow_dissector, - dissector_ports, - target_container); - key_ports->ports = __skb_flow_get_ports(skb, nhoff, ip_proto, - data, hlen); + ports = __skb_flow_get_ports(skb, nhoff, ip_proto, data, hlen); + + if (key_ports) + key_ports->ports = ports; + + if (key_ports_range) + key_ports_range->tp.ports = ports; } static void @@ -924,6 +931,7 @@ static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys, struct flow_dissector *flow_dissector, void *target_container) { + struct flow_dissector_key_ports_range *key_ports_range = NULL; struct flow_dissector_key_ports *key_ports = NULL; struct flow_dissector_key_control *key_control; struct flow_dissector_key_basic *key_basic; @@ -968,20 +976,21 @@ static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys, key_control->addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; } - if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS)) + if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS)) { key_ports = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_PORTS, target_container); - else if (dissector_uses_key(flow_dissector, - FLOW_DISSECTOR_KEY_PORTS_RANGE)) - key_ports = skb_flow_dissector_target(flow_dissector, - FLOW_DISSECTOR_KEY_PORTS_RANGE, - target_container); - - if (key_ports) { key_ports->src = flow_keys->sport; key_ports->dst = flow_keys->dport; } + if (dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_PORTS_RANGE)) { + key_ports_range = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_PORTS_RANGE, + target_container); + key_ports_range->tp.src = flow_keys->sport; + key_ports_range->tp.dst = flow_keys->dport; + } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_FLOW_LABEL)) { diff --git a/net/core/gro.c b/net/core/gro.c index d1f44084e978..78b320b63174 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -7,9 +7,6 @@ #define MAX_GRO_SKBS 8 -/* This should be increased if a protocol with a bigger head is added. */ -#define GRO_MAX_HEAD (MAX_HEADER + 128) - static DEFINE_SPINLOCK(offload_lock); /** diff --git a/net/core/neighbour.c b/net/core/neighbour.c index d8dd686b5287..344c9cd168ec 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -518,7 +518,7 @@ static struct neigh_hash_table *neigh_hash_alloc(unsigned int shift) if (!ret) return NULL; - hash_heads = kvzalloc(size, GFP_ATOMIC); + hash_heads = kzalloc(size, GFP_ATOMIC); if (!hash_heads) { kfree(ret); return NULL; @@ -536,7 +536,7 @@ static void neigh_hash_free_rcu(struct rcu_head *head) struct neigh_hash_table, rcu); - kvfree(nht->hash_heads); + kfree(nht->hash_heads); kfree(nht); } diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index cb39a12b2f82..4303f2a49262 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -464,7 +464,7 @@ static void net_complete_free(void) } -static void net_free(struct net *net) +void net_passive_dec(struct net *net) { if (refcount_dec_and_test(&net->passive)) { kfree(rcu_access_pointer(net->gen)); @@ -482,7 +482,7 @@ void net_drop_ns(void *p) struct net *net = (struct net *)p; if (net) - net_free(net); + net_passive_dec(net); } struct net *copy_net_ns(unsigned long flags, @@ -523,7 +523,7 @@ put_userns: key_remove_domain(net->key_domain); #endif put_user_ns(user_ns); - net_free(net); + net_passive_dec(net); dec_ucounts: dec_net_namespaces(ucounts); return ERR_PTR(rv); @@ -672,7 +672,7 @@ static void cleanup_net(struct work_struct *work) key_remove_domain(net->key_domain); #endif put_user_ns(net->user_ns); - net_free(net); + net_passive_dec(net); } cleanup_net_task = NULL; } diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index 55bb58d623ac..2b774183d31c 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -269,7 +269,7 @@ netdev_nl_napi_dump_one(struct net_device *netdev, struct sk_buff *rsp, prev_id = UINT_MAX; list_for_each_entry(napi, &netdev->napi_list, dev_list) { - if (napi->napi_id < MIN_NAPI_ID) + if (!napi_id_valid(napi->napi_id)) continue; /* Dump continuation below depends on the list being sorted */ @@ -402,11 +402,23 @@ netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev, if (params->mp_ops && params->mp_ops->nl_fill(params->mp_priv, rsp, rxq)) goto nla_put_failure; +#ifdef CONFIG_XDP_SOCKETS + if (rxq->pool) + if (nla_put_empty_nest(rsp, NETDEV_A_QUEUE_XSK)) + goto nla_put_failure; +#endif + break; case NETDEV_QUEUE_TYPE_TX: txq = netdev_get_tx_queue(netdev, q_idx); if (nla_put_napi_id(rsp, txq->napi)) goto nla_put_failure; +#ifdef CONFIG_XDP_SOCKETS + if (txq->pool) + if (nla_put_empty_nest(rsp, NETDEV_A_QUEUE_XSK)) + goto nla_put_failure; +#endif + break; } genlmsg_end(rsp, hdr); diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 1c6fec08bc43..acef1fcd8ddc 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -1112,7 +1112,13 @@ static void page_pool_release_retry(struct work_struct *wq) int inflight; inflight = page_pool_release(pool); - if (!inflight) + /* In rare cases, a driver bug may cause inflight to go negative. + * Don't reschedule release if inflight is 0 or negative. + * - If 0, the page_pool has been destroyed + * - if negative, we will never recover + * in both cases no reschedule is necessary. + */ + if (inflight <= 0) return; /* Periodic warning for page pools the user can't see */ diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c index 9d8a3d8597fa..c82a95beceff 100644 --- a/net/core/page_pool_user.c +++ b/net/core/page_pool_user.c @@ -233,7 +233,7 @@ page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool, goto err_cancel; napi_id = pool->p.napi ? READ_ONCE(pool->p.napi->napi_id) : 0; - if (napi_id >= MIN_NAPI_ID && + if (napi_id_valid(napi_id) && nla_put_uint(rsp, NETDEV_A_PAGE_POOL_NAPI_ID, napi_id)) goto err_cancel; diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 82b6a2c3c141..55064713223e 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -517,21 +517,23 @@ static ssize_t pgctrl_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { char data[128]; + size_t max; struct pktgen_net *pn = net_generic(current->nsproxy->net_ns, pg_net_id); if (!capable(CAP_NET_ADMIN)) return -EPERM; - if (count == 0) + if (count < 1) return -EINVAL; - if (count > sizeof(data)) - count = sizeof(data); - - if (copy_from_user(data, buf, count)) + max = min(count, sizeof(data) - 1); + if (copy_from_user(data, buf, max)) return -EFAULT; - data[count - 1] = 0; /* Strip trailing '\n' and terminate string */ + if (data[max - 1] == '\n') + data[max - 1] = 0; /* strip trailing '\n', terminate string */ + else + data[max] = 0; /* terminate string */ if (!strcmp(data, "stop")) pktgen_stop_all_threads(pn); @@ -753,14 +755,15 @@ static int hex32_arg(const char __user *user_buffer, unsigned long maxlen, for (; i < maxlen; i++) { int value; char c; - *num <<= 4; if (get_user(c, &user_buffer[i])) return -EFAULT; value = hex_to_bin(c); - if (value >= 0) + if (value >= 0) { + *num <<= 4; *num |= value; - else + } else { break; + } } return i; } @@ -823,6 +826,7 @@ static int strn_len(const char __user * user_buffer, unsigned int maxlen) case '\r': case '\t': case ' ': + case '=': goto done_str; default: break; @@ -1113,7 +1117,7 @@ static ssize_t pktgen_if_write(struct file *file, i += len; if (!value) - return len; + return -EINVAL; pkt_dev->delay = pkt_dev->min_pkt_size*8*NSEC_PER_USEC/value; if (debug) pr_info("Delay set at: %llu ns\n", pkt_dev->delay); @@ -1128,7 +1132,7 @@ static ssize_t pktgen_if_write(struct file *file, i += len; if (!value) - return len; + return -EINVAL; pkt_dev->delay = NSEC_PER_SEC/value; if (debug) pr_info("Delay set at: %llu ns\n", pkt_dev->delay); @@ -1198,7 +1202,7 @@ static ssize_t pktgen_if_write(struct file *file, if ((value > 0) && ((pkt_dev->xmit_mode == M_NETIF_RECEIVE) || !(pkt_dev->odev->priv_flags & IFF_TX_SKB_SHARING))) - return -ENOTSUPP; + return -EOPNOTSUPP; if (value > 0 && (pkt_dev->n_imix_entries > 0 || !(pkt_dev->flags & F_SHARED))) return -EINVAL; @@ -1258,7 +1262,7 @@ static ssize_t pktgen_if_write(struct file *file, ((pkt_dev->xmit_mode == M_QUEUE_XMIT) || ((pkt_dev->xmit_mode == M_START_XMIT) && (!(pkt_dev->odev->priv_flags & IFF_TX_SKB_SHARING))))) - return -ENOTSUPP; + return -EOPNOTSUPP; if (value > 1 && !(pkt_dev->flags & F_SHARED)) return -EINVAL; @@ -1303,7 +1307,7 @@ static ssize_t pktgen_if_write(struct file *file, } else if (strcmp(f, "netif_receive") == 0) { /* clone_skb set earlier, not supported in this mode */ if (pkt_dev->clone_skb > 0) - return -ENOTSUPP; + return -EOPNOTSUPP; pkt_dev->xmit_mode = M_NETIF_RECEIVE; @@ -1896,8 +1900,8 @@ static ssize_t pktgen_thread_write(struct file *file, i = len; /* Read variable name */ - - len = strn_len(&user_buffer[i], sizeof(name) - 1); + max = min(sizeof(name) - 1, count - i); + len = strn_len(&user_buffer[i], max); if (len < 0) return len; @@ -1927,7 +1931,8 @@ static ssize_t pktgen_thread_write(struct file *file, if (!strcmp(name, "add_device")) { char f[32]; memset(f, 0, 32); - len = strn_len(&user_buffer[i], sizeof(f) - 1); + max = min(sizeof(f) - 1, count - i); + len = strn_len(&user_buffer[i], max); if (len < 0) { ret = len; goto out; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index abe1a461ea67..b52e610e157e 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3767,7 +3767,13 @@ static int rtnl_newlink_create(struct sk_buff *skb, struct ifinfomsg *ifm, struct netlink_ext_ack *extack) { unsigned char name_assign_type = NET_NAME_USER; - struct net *net = sock_net(skb->sk); + struct rtnl_newlink_params params = { + .src_net = sock_net(skb->sk), + .link_net = link_net, + .peer_net = peer_net, + .tb = tb, + .data = data, + }; u32 portid = NETLINK_CB(skb).portid; struct net_device *dev; char ifname[IFNAMSIZ]; @@ -3783,8 +3789,8 @@ static int rtnl_newlink_create(struct sk_buff *skb, struct ifinfomsg *ifm, name_assign_type = NET_NAME_ENUM; } - dev = rtnl_create_link(link_net ? : tgt_net, ifname, - name_assign_type, ops, tb, extack); + dev = rtnl_create_link(tgt_net, ifname, name_assign_type, ops, tb, + extack); if (IS_ERR(dev)) { err = PTR_ERR(dev); goto out; @@ -3792,13 +3798,8 @@ static int rtnl_newlink_create(struct sk_buff *skb, struct ifinfomsg *ifm, dev->ifindex = ifm->ifi_index; - if (link_net) - net = link_net; - if (peer_net) - net = peer_net; - if (ops->newlink) - err = ops->newlink(net, dev, tb, data, extack); + err = ops->newlink(dev, ¶ms, extack); else err = register_netdevice(dev); if (err < 0) { @@ -3809,11 +3810,6 @@ static int rtnl_newlink_create(struct sk_buff *skb, struct ifinfomsg *ifm, err = rtnl_configure_link(dev, ifm, portid, nlh); if (err < 0) goto out_unregister; - if (link_net) { - err = dev_change_net_namespace(dev, tgt_net, ifname); - if (err < 0) - goto out_unregister; - } if (tb[IFLA_MASTER]) { err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]), extack); if (err) @@ -3867,20 +3863,26 @@ static int __rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh, { struct nlattr ** const tb = tbs->tb; struct net *net = sock_net(skb->sk); + struct net *device_net; struct net_device *dev; struct ifinfomsg *ifm; bool link_specified; + /* When creating, lookup for existing device in target net namespace */ + device_net = (nlh->nlmsg_flags & NLM_F_CREATE) && + (nlh->nlmsg_flags & NLM_F_EXCL) ? + tgt_net : net; + ifm = nlmsg_data(nlh); if (ifm->ifi_index > 0) { link_specified = true; - dev = __dev_get_by_index(net, ifm->ifi_index); + dev = __dev_get_by_index(device_net, ifm->ifi_index); } else if (ifm->ifi_index < 0) { NL_SET_ERR_MSG(extack, "ifindex can't be negative"); return -EINVAL; } else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME]) { link_specified = true; - dev = rtnl_dev_get(net, tb); + dev = rtnl_dev_get(device_net, tb); } else { link_specified = false; dev = NULL; diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c index b0ff6153be62..568779d5a0ef 100644 --- a/net/core/secure_seq.c +++ b/net/core/secure_seq.c @@ -71,7 +71,7 @@ u32 secure_tcpv6_ts_off(const struct net *net, return siphash(&combined, offsetofend(typeof(combined), daddr), &ts_secret); } -EXPORT_SYMBOL(secure_tcpv6_ts_off); +EXPORT_IPV6_MOD(secure_tcpv6_ts_off); u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr, __be16 sport, __be16 dport) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index dd33c12f00ca..5b241c9e6f38 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -69,6 +69,7 @@ #include <net/dst.h> #include <net/sock.h> #include <net/checksum.h> +#include <net/gro.h> #include <net/gso.h> #include <net/hotdata.h> #include <net/ip6_checksum.h> @@ -95,7 +96,9 @@ static struct kmem_cache *skbuff_ext_cache __ro_after_init; #endif -#define SKB_SMALL_HEAD_SIZE SKB_HEAD_ALIGN(MAX_TCP_HEADER) +#define GRO_MAX_HEAD_PAD (GRO_MAX_HEAD + NET_SKB_PAD + NET_IP_ALIGN) +#define SKB_SMALL_HEAD_SIZE SKB_HEAD_ALIGN(max(MAX_TCP_HEADER, \ + GRO_MAX_HEAD_PAD)) /* We want SKB_SMALL_HEAD_CACHE_SIZE to not be a power of two. * This should ensure that SKB_SMALL_HEAD_HEADROOM is a unique @@ -220,67 +223,9 @@ static void skb_under_panic(struct sk_buff *skb, unsigned int sz, void *addr) #define NAPI_SKB_CACHE_BULK 16 #define NAPI_SKB_CACHE_HALF (NAPI_SKB_CACHE_SIZE / 2) -#if PAGE_SIZE == SZ_4K - -#define NAPI_HAS_SMALL_PAGE_FRAG 1 -#define NAPI_SMALL_PAGE_PFMEMALLOC(nc) ((nc).pfmemalloc) - -/* specialized page frag allocator using a single order 0 page - * and slicing it into 1K sized fragment. Constrained to systems - * with a very limited amount of 1K fragments fitting a single - * page - to avoid excessive truesize underestimation - */ - -struct page_frag_1k { - void *va; - u16 offset; - bool pfmemalloc; -}; - -static void *page_frag_alloc_1k(struct page_frag_1k *nc, gfp_t gfp) -{ - struct page *page; - int offset; - - offset = nc->offset - SZ_1K; - if (likely(offset >= 0)) - goto use_frag; - - page = alloc_pages_node(NUMA_NO_NODE, gfp, 0); - if (!page) - return NULL; - - nc->va = page_address(page); - nc->pfmemalloc = page_is_pfmemalloc(page); - offset = PAGE_SIZE - SZ_1K; - page_ref_add(page, offset / SZ_1K); - -use_frag: - nc->offset = offset; - return nc->va + offset; -} -#else - -/* the small page is actually unused in this build; add dummy helpers - * to please the compiler and avoid later preprocessor's conditionals - */ -#define NAPI_HAS_SMALL_PAGE_FRAG 0 -#define NAPI_SMALL_PAGE_PFMEMALLOC(nc) false - -struct page_frag_1k { -}; - -static void *page_frag_alloc_1k(struct page_frag_1k *nc, gfp_t gfp_mask) -{ - return NULL; -} - -#endif - struct napi_alloc_cache { local_lock_t bh_lock; struct page_frag_cache page; - struct page_frag_1k page_small; unsigned int skb_count; void *skb_cache[NAPI_SKB_CACHE_SIZE]; }; @@ -290,23 +235,6 @@ static DEFINE_PER_CPU(struct napi_alloc_cache, napi_alloc_cache) = { .bh_lock = INIT_LOCAL_LOCK(bh_lock), }; -/* Double check that napi_get_frags() allocates skbs with - * skb->head being backed by slab, not a page fragment. - * This is to make sure bug fixed in 3226b158e67c - * ("net: avoid 32 x truesize under-estimation for tiny skbs") - * does not accidentally come back. - */ -void napi_get_frags_check(struct napi_struct *napi) -{ - struct sk_buff *skb; - - local_bh_disable(); - skb = napi_get_frags(napi); - WARN_ON_ONCE(!NAPI_HAS_SMALL_PAGE_FRAG && skb && skb->head_frag); - napi_free_frags(napi); - local_bh_enable(); -} - void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask) { struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); @@ -736,7 +664,7 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len, /* If requested length is either too small or too big, * we use kmalloc() for skb->head allocation. */ - if (len <= SKB_WITH_OVERHEAD(1024) || + if (len <= SKB_WITH_OVERHEAD(SKB_SMALL_HEAD_CACHE_SIZE) || len > SKB_WITH_OVERHEAD(PAGE_SIZE) || (gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) { skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX, NUMA_NO_NODE); @@ -813,10 +741,8 @@ struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int len) /* If requested length is either too small or too big, * we use kmalloc() for skb->head allocation. - * When the small frag allocator is available, prefer it over kmalloc - * for small fragments */ - if ((!NAPI_HAS_SMALL_PAGE_FRAG && len <= SKB_WITH_OVERHEAD(1024)) || + if (len <= SKB_WITH_OVERHEAD(SKB_SMALL_HEAD_CACHE_SIZE) || len > SKB_WITH_OVERHEAD(PAGE_SIZE) || (gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) { skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX | SKB_ALLOC_NAPI, @@ -826,32 +752,16 @@ struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int len) goto skb_success; } + len = SKB_HEAD_ALIGN(len); + if (sk_memalloc_socks()) gfp_mask |= __GFP_MEMALLOC; local_lock_nested_bh(&napi_alloc_cache.bh_lock); nc = this_cpu_ptr(&napi_alloc_cache); - if (NAPI_HAS_SMALL_PAGE_FRAG && len <= SKB_WITH_OVERHEAD(1024)) { - /* we are artificially inflating the allocation size, but - * that is not as bad as it may look like, as: - * - 'len' less than GRO_MAX_HEAD makes little sense - * - On most systems, larger 'len' values lead to fragment - * size above 512 bytes - * - kmalloc would use the kmalloc-1k slab for such values - * - Builds with smaller GRO_MAX_HEAD will very likely do - * little networking, as that implies no WiFi and no - * tunnels support, and 32 bits arches. - */ - len = SZ_1K; - data = page_frag_alloc_1k(&nc->page_small, gfp_mask); - pfmemalloc = NAPI_SMALL_PAGE_PFMEMALLOC(nc->page_small); - } else { - len = SKB_HEAD_ALIGN(len); - - data = page_frag_alloc(&nc->page, len, gfp_mask); - pfmemalloc = page_frag_cache_is_pfmemalloc(&nc->page); - } + data = page_frag_alloc(&nc->page, len, gfp_mask); + pfmemalloc = page_frag_cache_is_pfmemalloc(&nc->page); local_unlock_nested_bh(&napi_alloc_cache.bh_lock); if (unlikely(!data)) diff --git a/net/core/sock.c b/net/core/sock.c index ba653c6a1229..5ac445f8244b 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2056,7 +2056,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname, v.val = READ_ONCE(sk->sk_napi_id); /* aggregate non-NAPI IDs down to 0 */ - if (v.val < MIN_NAPI_ID) + if (!napi_id_valid(v.val)) v.val = 0; break; @@ -3896,7 +3896,7 @@ void sk_get_meminfo(const struct sock *sk, u32 *mem) mem[SK_MEMINFO_RCVBUF] = READ_ONCE(sk->sk_rcvbuf); mem[SK_MEMINFO_WMEM_ALLOC] = sk_wmem_alloc_get(sk); mem[SK_MEMINFO_SNDBUF] = READ_ONCE(sk->sk_sndbuf); - mem[SK_MEMINFO_FWD_ALLOC] = sk_forward_alloc_get(sk); + mem[SK_MEMINFO_FWD_ALLOC] = READ_ONCE(sk->sk_forward_alloc); mem[SK_MEMINFO_WMEM_QUEUED] = READ_ONCE(sk->sk_wmem_queued); mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc); mem[SK_MEMINFO_BACKLOG] = READ_ONCE(sk->sk_backlog.len); diff --git a/net/core/sock_map.c b/net/core/sock_map.c index f1b9b3958792..2f1be9baad05 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -541,6 +541,9 @@ static bool sock_map_sk_state_allowed(const struct sock *sk) return (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_LISTEN); if (sk_is_stream_unix(sk)) return (1 << sk->sk_state) & TCPF_ESTABLISHED; + if (sk_is_vsock(sk) && + (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET)) + return (1 << sk->sk_state) & TCPF_ESTABLISHED; return true; } diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index be515ba821e2..bfa529a54aca 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -426,9 +426,6 @@ struct sock *dccp_v4_request_recv_sock(const struct sock *sk, newinet = inet_sk(newsk); ireq = inet_rsk(req); - sk_daddr_set(newsk, ireq->ir_rmt_addr); - sk_rcv_saddr_set(newsk, ireq->ir_loc_addr); - newinet->inet_saddr = ireq->ir_loc_addr; RCU_INIT_POINTER(newinet->inet_opt, rcu_dereference(ireq->ireq_opt)); newinet->mc_index = inet_iif(skb); newinet->mc_ttl = ip_hdr(skb)->ttl; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index d6649246188d..39ae9d89d7d4 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -365,6 +365,9 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) ireq = inet_rsk(req); ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr; ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr; + ireq->ir_rmt_addr = LOOPBACK4_IPV6; + ireq->ir_loc_addr = LOOPBACK4_IPV6; + ireq->ireq_family = AF_INET6; ireq->ir_mark = inet_request_mark(sk, skb); @@ -504,10 +507,7 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk, memcpy(newnp, np, sizeof(struct ipv6_pinfo)); - newsk->sk_v6_daddr = ireq->ir_v6_rmt_addr; newnp->saddr = ireq->ir_v6_loc_addr; - newsk->sk_v6_rcv_saddr = ireq->ir_v6_loc_addr; - newsk->sk_bound_dev_if = ireq->ir_iif; /* Now IPv6 options... @@ -546,9 +546,6 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk, dccp_sync_mss(newsk, dst_mtu(dst)); - newinet->inet_daddr = newinet->inet_saddr = LOOPBACK4_IPV6; - newinet->inet_rcv_saddr = LOOPBACK4_IPV6; - if (__inet_inherit_port(sk, newsk) < 0) { inet_csk_prepare_forced_close(newsk); dccp_done(newsk); diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 98b7dcea207a..271c7cef9ef3 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -992,8 +992,10 @@ static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev, if (rc) return rc; - /* Nonzero ring with RSS only makes sense if NIC adds them together */ if (cmd == ETHTOOL_SRXCLSRLINS && info.fs.flow_type & FLOW_RSS) { + /* Nonzero ring with RSS only makes sense + * if NIC adds them together + */ if (!ops->cap_rss_rxnfc_adds && ethtool_get_flow_spec_ring(info.fs.ring_cookie)) return -EINVAL; diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c index b68f2f71d0e1..b120470246cc 100644 --- a/net/hsr/hsr_netlink.c +++ b/net/hsr/hsr_netlink.c @@ -29,10 +29,12 @@ static const struct nla_policy hsr_policy[IFLA_HSR_MAX + 1] = { /* Here, it seems a netdevice has already been allocated for us, and the * hsr_dev_setup routine has been executed. Nice! */ -static int hsr_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +static int hsr_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { + struct net *link_net = rtnl_newlink_link_net(params); + struct nlattr **data = params->data; enum hsr_version proto_version; unsigned char multicast_spec; u8 proto = HSR_PROTOCOL_HSR; @@ -46,7 +48,7 @@ static int hsr_newlink(struct net *src_net, struct net_device *dev, NL_SET_ERR_MSG_MOD(extack, "Slave1 device not specified"); return -EINVAL; } - link[0] = __dev_get_by_index(src_net, + link[0] = __dev_get_by_index(link_net, nla_get_u32(data[IFLA_HSR_SLAVE1])); if (!link[0]) { NL_SET_ERR_MSG_MOD(extack, "Slave1 does not exist"); @@ -56,7 +58,7 @@ static int hsr_newlink(struct net *src_net, struct net_device *dev, NL_SET_ERR_MSG_MOD(extack, "Slave2 device not specified"); return -EINVAL; } - link[1] = __dev_get_by_index(src_net, + link[1] = __dev_get_by_index(link_net, nla_get_u32(data[IFLA_HSR_SLAVE2])); if (!link[1]) { NL_SET_ERR_MSG_MOD(extack, "Slave2 does not exist"); @@ -69,7 +71,7 @@ static int hsr_newlink(struct net *src_net, struct net_device *dev, } if (data[IFLA_HSR_INTERLINK]) - interlink = __dev_get_by_index(src_net, + interlink = __dev_get_by_index(link_net, nla_get_u32(data[IFLA_HSR_INTERLINK])); if (interlink && interlink == link[0]) { diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c index 175efd860f7b..ee318d46817d 100644 --- a/net/ieee802154/6lowpan/core.c +++ b/net/ieee802154/6lowpan/core.c @@ -129,10 +129,11 @@ static int lowpan_validate(struct nlattr *tb[], struct nlattr *data[], return 0; } -static int lowpan_newlink(struct net *src_net, struct net_device *ldev, - struct nlattr *tb[], struct nlattr *data[], +static int lowpan_newlink(struct net_device *ldev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { + struct nlattr **tb = params->tb; struct net_device *wdev; int ret; @@ -142,6 +143,8 @@ static int lowpan_newlink(struct net *src_net, struct net_device *ldev, if (!tb[IFLA_LINK]) return -EINVAL; + if (params->link_net && !net_eq(params->link_net, dev_net(ldev))) + return -EINVAL; /* find and hold wpan device */ wdev = dev_get_by_index(dev_net(ldev), nla_get_u32(tb[IFLA_LINK])); if (!wdev) diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 21f46ee7b6e9..5df1f1325259 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -153,7 +153,7 @@ void inet_sock_destruct(struct sock *sk) WARN_ON_ONCE(atomic_read(&sk->sk_rmem_alloc)); WARN_ON_ONCE(refcount_read(&sk->sk_wmem_alloc)); WARN_ON_ONCE(sk->sk_wmem_queued); - WARN_ON_ONCE(sk_forward_alloc_get(sk)); + WARN_ON_ONCE(sk->sk_forward_alloc); kfree(rcu_dereference_protected(inet->inet_opt, 1)); dst_release(rcu_dereference_protected(sk->sk_dst_cache, 1)); diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 2c8f98cfe26c..a648fff71ea7 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1077,7 +1077,7 @@ static int arp_req_set_public(struct net *net, struct arpreq *r, __be32 mask = ((struct sockaddr_in *)&r->arp_netmask)->sin_addr.s_addr; if (!dev && (r->arp_flags & ATF_COM)) { - dev = dev_getbyhwaddr_rcu(net, r->arp_ha.sa_family, + dev = dev_getbyhwaddr(net, r->arp_ha.sa_family, r->arp_ha.sa_data); if (!dev) return -ENODEV; diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 041c46787d94..6b3d6a957822 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -201,12 +201,12 @@ INDIRECT_CALLABLE_SCOPE int fib4_rule_match(struct fib_rule *rule, if (rule->ip_proto && (rule->ip_proto != fl4->flowi4_proto)) return 0; - if (fib_rule_port_range_set(&rule->sport_range) && - !fib_rule_port_inrange(&rule->sport_range, fl4->fl4_sport)) + if (!fib_rule_port_match(&rule->sport_range, rule->sport_mask, + fl4->fl4_sport)) return 0; - if (fib_rule_port_range_set(&rule->dport_range) && - !fib_rule_port_inrange(&rule->dport_range, fl4->fl4_dport)) + if (!fib_rule_port_match(&rule->dport_range, rule->dport_mask, + fl4->fl4_dport)) return 0; return 1; diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 5482edb5aade..799775ba97d4 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -405,7 +405,6 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) struct ipcm_cookie ipc; struct flowi4 fl4; struct sock *sk; - struct inet_sock *inet; __be32 daddr, saddr; u32 mark = IP4_REPLY_MARK(net, skb->mark); int type = icmp_param->data.icmph.type; @@ -424,12 +423,11 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) sk = icmp_xmit_lock(net); if (!sk) goto out_bh_enable; - inet = inet_sk(sk); icmp_param->data.icmph.checksum = 0; ipcm_init(&ipc); - inet->tos = ip_hdr(skb)->tos; + ipc.tos = ip_hdr(skb)->tos; ipc.sockc.mark = mark; daddr = ipc.addr = ip_hdr(skb)->saddr; saddr = fib_compute_spec_dst(skb); @@ -737,8 +735,8 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, icmp_param.data.icmph.checksum = 0; icmp_param.skb = skb_in; icmp_param.offset = skb_network_offset(skb_in); - inet_sk(sk)->tos = tos; ipcm_init(&ipc); + ipc.tos = tos; ipc.addr = iph->saddr; ipc.opt = &icmp_param.replyopts.opt; ipc.sockc.mark = mark; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 2b7775b90a09..bf9ce0c19657 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -1237,39 +1237,59 @@ struct sock *inet_csk_clone_lock(const struct sock *sk, const gfp_t priority) { struct sock *newsk = sk_clone_lock(sk, priority); + struct inet_connection_sock *newicsk; + struct inet_request_sock *ireq; + struct inet_sock *newinet; - if (newsk) { - struct inet_connection_sock *newicsk = inet_csk(newsk); + if (!newsk) + return NULL; - inet_sk_set_state(newsk, TCP_SYN_RECV); - newicsk->icsk_bind_hash = NULL; - newicsk->icsk_bind2_hash = NULL; + newicsk = inet_csk(newsk); + newinet = inet_sk(newsk); + ireq = inet_rsk(req); - inet_sk(newsk)->inet_dport = inet_rsk(req)->ir_rmt_port; - inet_sk(newsk)->inet_num = inet_rsk(req)->ir_num; - inet_sk(newsk)->inet_sport = htons(inet_rsk(req)->ir_num); + newicsk->icsk_bind_hash = NULL; + newicsk->icsk_bind2_hash = NULL; - /* listeners have SOCK_RCU_FREE, not the children */ - sock_reset_flag(newsk, SOCK_RCU_FREE); + newinet->inet_dport = ireq->ir_rmt_port; + newinet->inet_num = ireq->ir_num; + newinet->inet_sport = htons(ireq->ir_num); - inet_sk(newsk)->mc_list = NULL; + newsk->sk_bound_dev_if = ireq->ir_iif; - newsk->sk_mark = inet_rsk(req)->ir_mark; - atomic64_set(&newsk->sk_cookie, - atomic64_read(&inet_rsk(req)->ir_cookie)); + newsk->sk_daddr = ireq->ir_rmt_addr; + newsk->sk_rcv_saddr = ireq->ir_loc_addr; + newinet->inet_saddr = ireq->ir_loc_addr; - newicsk->icsk_retransmits = 0; - newicsk->icsk_backoff = 0; - newicsk->icsk_probes_out = 0; - newicsk->icsk_probes_tstamp = 0; +#if IS_ENABLED(CONFIG_IPV6) + newsk->sk_v6_daddr = ireq->ir_v6_rmt_addr; + newsk->sk_v6_rcv_saddr = ireq->ir_v6_loc_addr; +#endif - /* Deinitialize accept_queue to trap illegal accesses. */ - memset(&newicsk->icsk_accept_queue, 0, sizeof(newicsk->icsk_accept_queue)); + /* listeners have SOCK_RCU_FREE, not the children */ + sock_reset_flag(newsk, SOCK_RCU_FREE); - inet_clone_ulp(req, newsk, priority); + inet_sk(newsk)->mc_list = NULL; + + newsk->sk_mark = inet_rsk(req)->ir_mark; + atomic64_set(&newsk->sk_cookie, + atomic64_read(&inet_rsk(req)->ir_cookie)); + + newicsk->icsk_retransmits = 0; + newicsk->icsk_backoff = 0; + newicsk->icsk_probes_out = 0; + newicsk->icsk_probes_tstamp = 0; + + /* Deinitialize accept_queue to trap illegal accesses. */ + memset(&newicsk->icsk_accept_queue, 0, + sizeof(newicsk->icsk_accept_queue)); + + inet_sk_set_state(newsk, TCP_SYN_RECV); + + inet_clone_ulp(req, newsk, priority); + + security_inet_csk_clone(newsk, req); - security_inet_csk_clone(newsk, req); - } return newsk; } EXPORT_SYMBOL_GPL(inet_csk_clone_lock); diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 321acc8abf17..efe2a085cf68 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -282,7 +282,7 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, struct inet_diag_meminfo minfo = { .idiag_rmem = sk_rmem_alloc_get(sk), .idiag_wmem = READ_ONCE(sk->sk_wmem_queued), - .idiag_fmem = sk_forward_alloc_get(sk), + .idiag_fmem = READ_ONCE(sk->sk_forward_alloc), .idiag_tmem = sk_wmem_alloc_get(sk), }; diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index b8b23a77ceb4..7b1e0a2d6906 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -60,7 +60,7 @@ void inet_peer_base_init(struct inet_peer_base *bp) seqlock_init(&bp->lock); bp->total = 0; } -EXPORT_SYMBOL_GPL(inet_peer_base_init); +EXPORT_IPV6_MOD_GPL(inet_peer_base_init); #define PEER_MAX_GC 32 @@ -218,7 +218,7 @@ struct inet_peer *inet_getpeer(struct inet_peer_base *base, return p; } -EXPORT_SYMBOL_GPL(inet_getpeer); +EXPORT_IPV6_MOD_GPL(inet_getpeer); void inet_putpeer(struct inet_peer *p) { @@ -269,7 +269,7 @@ bool inet_peer_xrlim_allow(struct inet_peer *peer, int timeout) WRITE_ONCE(peer->rate_tokens, token); return rc; } -EXPORT_SYMBOL(inet_peer_xrlim_allow); +EXPORT_IPV6_MOD(inet_peer_xrlim_allow); void inetpeer_invalidate_tree(struct inet_peer_base *base) { @@ -286,4 +286,4 @@ void inetpeer_invalidate_tree(struct inet_peer_base *base) base->total = 0; } -EXPORT_SYMBOL(inetpeer_invalidate_tree); +EXPORT_IPV6_MOD(inetpeer_invalidate_tree); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index c9f11a046c26..26d15f907551 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1396,10 +1396,12 @@ ipgre_newlink_encap_setup(struct net_device *dev, struct nlattr *data[]) return 0; } -static int ipgre_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +static int ipgre_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { + struct nlattr **data = params->data; + struct nlattr **tb = params->tb; struct ip_tunnel_parm_kern p; __u32 fwmark = 0; int err; @@ -1411,13 +1413,16 @@ static int ipgre_newlink(struct net *src_net, struct net_device *dev, err = ipgre_netlink_parms(dev, data, tb, &p, &fwmark); if (err < 0) return err; - return ip_tunnel_newlink(dev, tb, &p, fwmark); + return ip_tunnel_newlink(params->link_net ? : dev_net(dev), dev, tb, &p, + fwmark); } -static int erspan_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +static int erspan_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { + struct nlattr **data = params->data; + struct nlattr **tb = params->tb; struct ip_tunnel_parm_kern p; __u32 fwmark = 0; int err; @@ -1429,7 +1434,8 @@ static int erspan_newlink(struct net *src_net, struct net_device *dev, err = erspan_netlink_parms(dev, data, tb, &p, &fwmark); if (err) return err; - return ip_tunnel_newlink(dev, tb, &p, fwmark); + return ip_tunnel_newlink(params->link_net ? : dev_net(dev), dev, tb, &p, + fwmark); } static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[], @@ -1697,6 +1703,7 @@ static struct rtnl_link_ops erspan_link_ops __read_mostly = { struct net_device *gretap_fb_dev_create(struct net *net, const char *name, u8 name_assign_type) { + struct rtnl_newlink_params params = { .src_net = net }; struct nlattr *tb[IFLA_MAX + 1]; struct net_device *dev; LIST_HEAD(list_kill); @@ -1704,6 +1711,7 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name, int err; memset(&tb, 0, sizeof(tb)); + params.tb = tb; dev = rtnl_create_link(net, name, name_assign_type, &ipgre_tap_ops, tb, NULL); @@ -1714,7 +1722,7 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name, t = netdev_priv(dev); t->collect_md = true; - err = ipgre_newlink(net, dev, tb, NULL, NULL); + err = ipgre_newlink(dev, ¶ms, NULL); if (err < 0) { free_netdev(dev); return ERR_PTR(err); diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 09b73acf037a..011f2a5aab3b 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -1213,11 +1213,11 @@ void ip_tunnel_delete_nets(struct list_head *net_list, unsigned int id, } EXPORT_SYMBOL_GPL(ip_tunnel_delete_nets); -int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[], - struct ip_tunnel_parm_kern *p, __u32 fwmark) +int ip_tunnel_newlink(struct net *net, struct net_device *dev, + struct nlattr *tb[], struct ip_tunnel_parm_kern *p, + __u32 fwmark) { struct ip_tunnel *nt; - struct net *net = dev_net(dev); struct ip_tunnel_net *itn; int mtu; int err; @@ -1326,7 +1326,6 @@ int ip_tunnel_init(struct net_device *dev) } tunnel->dev = dev; - tunnel->net = dev_net(dev); strscpy(tunnel->parms.name, dev->name); iph->version = 4; iph->ihl = 5; diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index f0b4419cef34..159b4473290e 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -575,15 +575,18 @@ static void vti_netlink_parms(struct nlattr *data[], *fwmark = nla_get_u32(data[IFLA_VTI_FWMARK]); } -static int vti_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +static int vti_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { + struct nlattr **data = params->data; struct ip_tunnel_parm_kern parms; + struct nlattr **tb = params->tb; __u32 fwmark = 0; vti_netlink_parms(data, &parms, &fwmark); - return ip_tunnel_newlink(dev, tb, &parms, fwmark); + return ip_tunnel_newlink(params->link_net ? : dev_net(dev), dev, tb, + &parms, fwmark); } static int vti_changelink(struct net_device *dev, struct nlattr *tb[], diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index dc0db5895e0e..bab0bf90c908 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -436,11 +436,13 @@ static void ipip_netlink_parms(struct nlattr *data[], *fwmark = nla_get_u32(data[IFLA_IPTUN_FWMARK]); } -static int ipip_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +static int ipip_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); + struct nlattr **data = params->data; + struct nlattr **tb = params->tb; struct ip_tunnel_encap ipencap; struct ip_tunnel_parm_kern p; __u32 fwmark = 0; @@ -453,7 +455,8 @@ static int ipip_newlink(struct net *src_net, struct net_device *dev, } ipip_netlink_parms(data, &p, &t->collect_md, &fwmark); - return ip_tunnel_newlink(dev, tb, &p, fwmark); + return ip_tunnel_newlink(params->link_net ? : dev_net(dev), dev, tb, &p, + fwmark); } static int ipip_changelink(struct net_device *dev, struct nlattr *tb[], diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 619ddc087957..85d09f2ecadc 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -705,7 +705,7 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) struct ip_options_data opt_copy; int free = 0; __be32 saddr, daddr, faddr; - u8 tos, scope; + u8 scope; int err; pr_debug("ping_v4_sendmsg(sk=%p,sk->num=%u)\n", inet, inet->inet_num); @@ -768,7 +768,6 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) } faddr = ipc.opt->opt.faddr; } - tos = get_rttos(&ipc, inet); scope = ip_sendmsg_scope(inet, &ipc, msg); if (ipv4_is_multicast(daddr)) { @@ -779,7 +778,8 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) } else if (!ipc.oif) ipc.oif = READ_ONCE(inet->uc_index); - flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos, scope, + flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, + ipc.tos & INET_DSCP_MASK, scope, sk->sk_protocol, inet_sk_flowi_flags(sk), faddr, saddr, 0, 0, sk->sk_uid); diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 4304a68d1db0..6aace4d55733 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -486,7 +486,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) struct ipcm_cookie ipc; struct rtable *rt = NULL; struct flowi4 fl4; - u8 tos, scope; + u8 scope; int free = 0; __be32 daddr; __be32 saddr; @@ -581,7 +581,6 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) daddr = ipc.opt->opt.faddr; } } - tos = get_rttos(&ipc, inet); scope = ip_sendmsg_scope(inet, &ipc, msg); uc_index = READ_ONCE(inet->uc_index); @@ -606,7 +605,8 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) } } - flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos, scope, + flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, + ipc.tos & INET_DSCP_MASK, scope, hdrincl ? ipc.protocol : sk->sk_protocol, inet_sk_flowi_flags(sk) | (hdrincl ? FLOWI_FLAG_KNOWN_NH : 0), diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 1948d15f1f28..26816b876dd8 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -222,7 +222,7 @@ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb, return NULL; } -EXPORT_SYMBOL(tcp_get_cookie_sock); +EXPORT_IPV6_MOD(tcp_get_cookie_sock); /* * when syncookies are in effect and tcp timestamps are enabled we stored @@ -259,7 +259,7 @@ bool cookie_timestamp_decode(const struct net *net, return READ_ONCE(net->ipv4.sysctl_tcp_window_scaling) != 0; } -EXPORT_SYMBOL(cookie_timestamp_decode); +EXPORT_IPV6_MOD(cookie_timestamp_decode); static int cookie_tcp_reqsk_init(struct sock *sk, struct sk_buff *skb, struct request_sock *req) @@ -310,7 +310,7 @@ struct request_sock *cookie_bpf_check(struct sock *sk, struct sk_buff *skb) return req; } -EXPORT_SYMBOL_GPL(cookie_bpf_check); +EXPORT_IPV6_MOD_GPL(cookie_bpf_check); #endif struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, @@ -351,7 +351,7 @@ struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, return req; } -EXPORT_SYMBOL_GPL(cookie_tcp_reqsk_alloc); +EXPORT_IPV6_MOD_GPL(cookie_tcp_reqsk_alloc); static struct request_sock *cookie_tcp_check(struct net *net, struct sock *sk, struct sk_buff *skb) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 298d1da05bee..08d73f17e816 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -300,10 +300,10 @@ DEFINE_PER_CPU(u32, tcp_tw_isn); EXPORT_PER_CPU_SYMBOL_GPL(tcp_tw_isn); long sysctl_tcp_mem[3] __read_mostly; -EXPORT_SYMBOL(sysctl_tcp_mem); +EXPORT_IPV6_MOD(sysctl_tcp_mem); atomic_long_t tcp_memory_allocated ____cacheline_aligned_in_smp; /* Current allocated memory. */ -EXPORT_SYMBOL(tcp_memory_allocated); +EXPORT_IPV6_MOD(tcp_memory_allocated); DEFINE_PER_CPU(int, tcp_memory_per_cpu_fw_alloc); EXPORT_PER_CPU_SYMBOL_GPL(tcp_memory_per_cpu_fw_alloc); @@ -316,7 +316,7 @@ EXPORT_SYMBOL(tcp_have_smc); * Current number of TCP sockets. */ struct percpu_counter tcp_sockets_allocated ____cacheline_aligned_in_smp; -EXPORT_SYMBOL(tcp_sockets_allocated); +EXPORT_IPV6_MOD(tcp_sockets_allocated); /* * TCP splice context @@ -349,7 +349,7 @@ void tcp_enter_memory_pressure(struct sock *sk) if (!cmpxchg(&tcp_memory_pressure, 0, val)) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMEMORYPRESSURES); } -EXPORT_SYMBOL_GPL(tcp_enter_memory_pressure); +EXPORT_IPV6_MOD_GPL(tcp_enter_memory_pressure); void tcp_leave_memory_pressure(struct sock *sk) { @@ -362,7 +362,7 @@ void tcp_leave_memory_pressure(struct sock *sk) NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPMEMORYPRESSURESCHRONO, jiffies_to_msecs(jiffies - val)); } -EXPORT_SYMBOL_GPL(tcp_leave_memory_pressure); +EXPORT_IPV6_MOD_GPL(tcp_leave_memory_pressure); /* Convert seconds to retransmits based on initial and max timeout */ static u8 secs_to_retrans(int seconds, int timeout, int rto_max) @@ -479,7 +479,7 @@ void tcp_init_sock(struct sock *sk) sk_sockets_allocated_inc(sk); xa_init_flags(&sk->sk_user_frags, XA_FLAGS_ALLOC1); } -EXPORT_SYMBOL(tcp_init_sock); +EXPORT_IPV6_MOD(tcp_init_sock); static void tcp_tx_timestamp(struct sock *sk, struct sockcm_cookie *sockc) { @@ -668,7 +668,7 @@ int tcp_ioctl(struct sock *sk, int cmd, int *karg) *karg = answ; return 0; } -EXPORT_SYMBOL(tcp_ioctl); +EXPORT_IPV6_MOD(tcp_ioctl); void tcp_mark_push(struct tcp_sock *tp, struct sk_buff *skb) { @@ -884,7 +884,7 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos, return ret; } -EXPORT_SYMBOL(tcp_splice_read); +EXPORT_IPV6_MOD(tcp_splice_read); struct sk_buff *tcp_stream_alloc_skb(struct sock *sk, gfp_t gfp, bool force_schedule) @@ -1131,7 +1131,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) /* 'common' sending to sendq */ } - sockcm_init(&sockc, sk); + sockc = (struct sockcm_cookie) { .tsflags = READ_ONCE(sk->sk_tsflags)}; if (msg->msg_controllen) { err = sock_cmsg_send(sk, msg, &sockc); if (unlikely(err)) { @@ -1384,7 +1384,7 @@ void tcp_splice_eof(struct socket *sock) tcp_push(sk, 0, mss_now, tp->nonagle, size_goal); release_sock(sk); } -EXPORT_SYMBOL_GPL(tcp_splice_eof); +EXPORT_IPV6_MOD_GPL(tcp_splice_eof); /* * Handle reading urgent data. BSD has very simple semantics for @@ -1675,7 +1675,7 @@ int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) } return copied; } -EXPORT_SYMBOL(tcp_read_skb); +EXPORT_IPV6_MOD(tcp_read_skb); void tcp_read_done(struct sock *sk, size_t len) { @@ -1720,7 +1720,7 @@ int tcp_peek_len(struct socket *sock) { return tcp_inq(sock->sk); } -EXPORT_SYMBOL(tcp_peek_len); +EXPORT_IPV6_MOD(tcp_peek_len); /* Make sure sk_rcvbuf is big enough to satisfy SO_RCVLOWAT hint */ int tcp_set_rcvlowat(struct sock *sk, int val) @@ -1747,7 +1747,7 @@ int tcp_set_rcvlowat(struct sock *sk, int val) } return 0; } -EXPORT_SYMBOL(tcp_set_rcvlowat); +EXPORT_IPV6_MOD(tcp_set_rcvlowat); void tcp_update_recv_tstamps(struct sk_buff *skb, struct scm_timestamping_internal *tss) @@ -1780,7 +1780,7 @@ int tcp_mmap(struct file *file, struct socket *sock, vma->vm_ops = &tcp_vm_ops; return 0; } -EXPORT_SYMBOL(tcp_mmap); +EXPORT_IPV6_MOD(tcp_mmap); static skb_frag_t *skb_advance_to_frag(struct sk_buff *skb, u32 offset_skb, u32 *offset_frag) @@ -2877,7 +2877,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, } return ret; } -EXPORT_SYMBOL(tcp_recvmsg); +EXPORT_IPV6_MOD(tcp_recvmsg); void tcp_set_state(struct sock *sk, int state) { @@ -3007,7 +3007,7 @@ void tcp_shutdown(struct sock *sk, int how) tcp_send_fin(sk); } } -EXPORT_SYMBOL(tcp_shutdown); +EXPORT_IPV6_MOD(tcp_shutdown); int tcp_orphan_count_sum(void) { @@ -3506,7 +3506,7 @@ static int tcp_repair_options_est(struct sock *sk, sockptr_t optbuf, } DEFINE_STATIC_KEY_FALSE(tcp_tx_delay_enabled); -EXPORT_SYMBOL(tcp_tx_delay_enabled); +EXPORT_IPV6_MOD(tcp_tx_delay_enabled); static void tcp_enable_tx_delay(void) { @@ -4049,7 +4049,7 @@ int tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, optval, optlen); return do_tcp_setsockopt(sk, level, optname, optval, optlen); } -EXPORT_SYMBOL(tcp_setsockopt); +EXPORT_IPV6_MOD(tcp_setsockopt); static void tcp_get_info_chrono_stats(const struct tcp_sock *tp, struct tcp_info *info) @@ -4680,7 +4680,7 @@ bool tcp_bpf_bypass_getsockopt(int level, int optname) return false; } -EXPORT_SYMBOL(tcp_bpf_bypass_getsockopt); +EXPORT_IPV6_MOD(tcp_bpf_bypass_getsockopt); int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) @@ -4694,11 +4694,11 @@ int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, return do_tcp_getsockopt(sk, level, optname, USER_SOCKPTR(optval), USER_SOCKPTR(optlen)); } -EXPORT_SYMBOL(tcp_getsockopt); +EXPORT_IPV6_MOD(tcp_getsockopt); #ifdef CONFIG_TCP_MD5SIG int tcp_md5_sigpool_id = -1; -EXPORT_SYMBOL_GPL(tcp_md5_sigpool_id); +EXPORT_IPV6_MOD_GPL(tcp_md5_sigpool_id); int tcp_md5_alloc_sigpool(void) { @@ -4744,7 +4744,7 @@ int tcp_md5_hash_key(struct tcp_sigpool *hp, */ return data_race(crypto_ahash_update(hp->req)); } -EXPORT_SYMBOL(tcp_md5_hash_key); +EXPORT_IPV6_MOD(tcp_md5_hash_key); /* Called with rcu_read_lock() */ static enum skb_drop_reason @@ -4864,7 +4864,7 @@ tcp_inbound_hash(struct sock *sk, const struct request_sock *req, return tcp_inbound_md5_hash(sk, skb, saddr, daddr, family, l3index, md5_location); } -EXPORT_SYMBOL_GPL(tcp_inbound_hash); +EXPORT_IPV6_MOD_GPL(tcp_inbound_hash); void tcp_done(struct sock *sk) { diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index e4c95238df58..1a6b1bc54245 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -178,7 +178,7 @@ void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb) if (!skb) return; - skb_dst_drop(skb); + tcp_cleanup_skb(skb); /* segs_in has been initialized to 1 in tcp_create_openreq_child(). * Hence, reset segs_in to 0 before calling tcp_segs_in() * to avoid double counting. Also, tcp_segs_in() expects @@ -195,7 +195,7 @@ void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb) TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_SYN; tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq; - __skb_queue_tail(&sk->sk_receive_queue, skb); + tcp_add_receive_queue(sk, skb); tp->syn_data_acked = 1; /* u64_stats_update_begin(&tp->syncp) not needed here, @@ -468,7 +468,7 @@ bool tcp_fastopen_defer_connect(struct sock *sk, int *err) } return false; } -EXPORT_SYMBOL(tcp_fastopen_defer_connect); +EXPORT_IPV6_MOD(tcp_fastopen_defer_connect); /* * The following code block is to deal with middle box issues with TFO: diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 4a9e70e23ef8..217a8747a79b 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -245,9 +245,15 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb) do_div(val, skb->truesize); tcp_sk(sk)->scaling_ratio = val ? val : 1; - if (old_ratio != tcp_sk(sk)->scaling_ratio) - WRITE_ONCE(tcp_sk(sk)->window_clamp, - tcp_win_from_space(sk, sk->sk_rcvbuf)); + if (old_ratio != tcp_sk(sk)->scaling_ratio) { + struct tcp_sock *tp = tcp_sk(sk); + + val = tcp_win_from_space(sk, sk->sk_rcvbuf); + tcp_set_window_clamp(sk, val); + + if (tp->window_clamp < tp->rcvq_space.space) + tp->rcvq_space.space = tp->window_clamp; + } } icsk->icsk_ack.rcv_mss = min_t(unsigned int, len, tcp_sk(sk)->advmss); @@ -632,7 +638,7 @@ void tcp_initialize_rcv_mss(struct sock *sk) inet_csk(sk)->icsk_ack.rcv_mss = hint; } -EXPORT_SYMBOL(tcp_initialize_rcv_mss); +EXPORT_IPV6_MOD(tcp_initialize_rcv_mss); /* Receiver "autotuning" code. * @@ -2711,6 +2717,8 @@ void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, int newly_lost, if (newly_acked_sacked <= 0 || WARN_ON_ONCE(!tp->prior_cwnd)) return; + trace_tcp_cwnd_reduction_tp(sk, newly_acked_sacked, newly_lost, flag); + tp->prr_delivered += newly_acked_sacked; if (delta < 0) { u64 dividend = (u64)tp->snd_ssthresh * tp->prr_delivered + @@ -2893,7 +2901,7 @@ void tcp_simple_retransmit(struct sock *sk) */ tcp_non_congestion_loss_retransmit(sk); } -EXPORT_SYMBOL(tcp_simple_retransmit); +EXPORT_IPV6_MOD(tcp_simple_retransmit); void tcp_enter_recovery(struct sock *sk, bool ece_ack) { @@ -4523,7 +4531,7 @@ void tcp_done_with_error(struct sock *sk, int err) if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); } -EXPORT_SYMBOL(tcp_done_with_error); +EXPORT_IPV6_MOD(tcp_done_with_error); /* When we get a reset we do this. */ void tcp_reset(struct sock *sk, struct sk_buff *skb) @@ -4969,7 +4977,7 @@ static void tcp_ofo_queue(struct sock *sk) tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq); fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN; if (!eaten) - __skb_queue_tail(&sk->sk_receive_queue, skb); + tcp_add_receive_queue(sk, skb); else kfree_skb_partial(skb, fragstolen); @@ -5161,7 +5169,7 @@ static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, skb, fragstolen)) ? 1 : 0; tcp_rcv_nxt_update(tcp_sk(sk), TCP_SKB_CB(skb)->end_seq); if (!eaten) { - __skb_queue_tail(&sk->sk_receive_queue, skb); + tcp_add_receive_queue(sk, skb); skb_set_owner_r(skb, sk); } return eaten; @@ -5244,7 +5252,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) __kfree_skb(skb); return; } - skb_dst_drop(skb); + tcp_cleanup_skb(skb); __skb_pull(skb, tcp_hdr(skb)->doff * 4); reason = SKB_DROP_REASON_NOT_SPECIFIED; @@ -6225,7 +6233,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHPHITS); /* Bulk data transfer: receiver */ - skb_dst_drop(skb); + tcp_cleanup_skb(skb); __skb_pull(skb, tcp_header_len); eaten = tcp_queue_rcv(sk, skb, &fragstolen); @@ -6293,7 +6301,7 @@ csum_error: discard: tcp_drop_reason(sk, skb, reason); } -EXPORT_SYMBOL(tcp_rcv_established); +EXPORT_IPV6_MOD(tcp_rcv_established); void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb) { @@ -7006,7 +7014,7 @@ consume: __kfree_skb(skb); return 0; } -EXPORT_SYMBOL(tcp_rcv_state_process); +EXPORT_IPV6_MOD(tcp_rcv_state_process); static inline void pr_drop_req(struct request_sock *req, __u16 port, int family) { @@ -7188,7 +7196,7 @@ u16 tcp_get_syncookie_mss(struct request_sock_ops *rsk_ops, return mss; } -EXPORT_SYMBOL_GPL(tcp_get_syncookie_mss); +EXPORT_IPV6_MOD_GPL(tcp_get_syncookie_mss); int tcp_conn_request(struct request_sock_ops *rsk_ops, const struct tcp_request_sock_ops *af_ops, @@ -7369,4 +7377,4 @@ drop: tcp_listendrop(sk); return 0; } -EXPORT_SYMBOL(tcp_conn_request); +EXPORT_IPV6_MOD(tcp_conn_request); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index d1fd2128ac6c..7900855237d9 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -92,7 +92,6 @@ static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, #endif struct inet_hashinfo tcp_hashinfo; -EXPORT_SYMBOL(tcp_hashinfo); static DEFINE_PER_CPU(struct sock_bh_locked, ipv4_tcp_sk) = { .bh_lock = INIT_LOCAL_LOCK(bh_lock), @@ -199,7 +198,7 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) return 0; } -EXPORT_SYMBOL_GPL(tcp_twsk_unique); +EXPORT_IPV6_MOD_GPL(tcp_twsk_unique); static int tcp_v4_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) @@ -359,7 +358,7 @@ failure: inet->inet_dport = 0; return err; } -EXPORT_SYMBOL(tcp_v4_connect); +EXPORT_IPV6_MOD(tcp_v4_connect); /* * This routine reacts to ICMP_FRAG_NEEDED mtu indications as defined in RFC1191. @@ -400,7 +399,7 @@ void tcp_v4_mtu_reduced(struct sock *sk) tcp_simple_retransmit(sk); } /* else let the usual retransmit timer handle it */ } -EXPORT_SYMBOL(tcp_v4_mtu_reduced); +EXPORT_IPV6_MOD(tcp_v4_mtu_reduced); static void do_redirect(struct sk_buff *skb, struct sock *sk) { @@ -434,7 +433,7 @@ void tcp_req_err(struct sock *sk, u32 seq, bool abort) } reqsk_put(req); } -EXPORT_SYMBOL(tcp_req_err); +EXPORT_IPV6_MOD(tcp_req_err); /* TCP-LD (RFC 6069) logic */ void tcp_ld_RTO_revert(struct sock *sk, u32 seq) @@ -473,7 +472,7 @@ void tcp_ld_RTO_revert(struct sock *sk, u32 seq) tcp_retransmit_timer(sk); } } -EXPORT_SYMBOL(tcp_ld_RTO_revert); +EXPORT_IPV6_MOD(tcp_ld_RTO_revert); /* * This routine is called by the ICMP module when it gets some @@ -675,7 +674,7 @@ void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb) __tcp_v4_send_check(skb, inet->inet_saddr, inet->inet_daddr); } -EXPORT_SYMBOL(tcp_v4_send_check); +EXPORT_IPV6_MOD(tcp_v4_send_check); #define REPLY_OPTIONS_LEN (MAX_TCP_OPTION_SPACE / sizeof(__be32)) @@ -1230,7 +1229,7 @@ static void tcp_v4_reqsk_destructor(struct request_sock *req) */ DEFINE_STATIC_KEY_DEFERRED_FALSE(tcp_md5_needed, HZ); -EXPORT_SYMBOL(tcp_md5_needed); +EXPORT_IPV6_MOD(tcp_md5_needed); static bool better_md5_match(struct tcp_md5sig_key *old, struct tcp_md5sig_key *new) { @@ -1289,7 +1288,7 @@ struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, int l3index, } return best_match; } -EXPORT_SYMBOL(__tcp_md5_do_lookup); +EXPORT_IPV6_MOD(__tcp_md5_do_lookup); static struct tcp_md5sig_key *tcp_md5_do_lookup_exact(const struct sock *sk, const union tcp_md5_addr *addr, @@ -1336,7 +1335,7 @@ struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk, addr = (const union tcp_md5_addr *)&addr_sk->sk_daddr; return tcp_md5_do_lookup(sk, l3index, addr, AF_INET); } -EXPORT_SYMBOL(tcp_v4_md5_lookup); +EXPORT_IPV6_MOD(tcp_v4_md5_lookup); static int tcp_md5sig_info_add(struct sock *sk, gfp_t gfp) { @@ -1432,7 +1431,7 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, return __tcp_md5_do_add(sk, addr, family, prefixlen, l3index, flags, newkey, newkeylen, GFP_KERNEL); } -EXPORT_SYMBOL(tcp_md5_do_add); +EXPORT_IPV6_MOD(tcp_md5_do_add); int tcp_md5_key_copy(struct sock *sk, const union tcp_md5_addr *addr, int family, u8 prefixlen, int l3index, @@ -1464,7 +1463,7 @@ int tcp_md5_key_copy(struct sock *sk, const union tcp_md5_addr *addr, key->flags, key->key, key->keylen, sk_gfp_mask(sk, GFP_ATOMIC)); } -EXPORT_SYMBOL(tcp_md5_key_copy); +EXPORT_IPV6_MOD(tcp_md5_key_copy); int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family, u8 prefixlen, int l3index, u8 flags) @@ -1479,7 +1478,7 @@ int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family, kfree_rcu(key, rcu); return 0; } -EXPORT_SYMBOL(tcp_md5_do_del); +EXPORT_IPV6_MOD(tcp_md5_do_del); void tcp_clear_md5_list(struct sock *sk) { @@ -1658,7 +1657,7 @@ clear_hash_nostart: memset(md5_hash, 0, 16); return 1; } -EXPORT_SYMBOL(tcp_v4_md5_hash_skb); +EXPORT_IPV6_MOD(tcp_v4_md5_hash_skb); #endif @@ -1731,7 +1730,7 @@ drop: tcp_listendrop(sk); return 0; } -EXPORT_SYMBOL(tcp_v4_conn_request); +EXPORT_IPV6_MOD(tcp_v4_conn_request); /* @@ -1769,10 +1768,6 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, newtp = tcp_sk(newsk); newinet = inet_sk(newsk); ireq = inet_rsk(req); - sk_daddr_set(newsk, ireq->ir_rmt_addr); - sk_rcv_saddr_set(newsk, ireq->ir_loc_addr); - newsk->sk_bound_dev_if = ireq->ir_iif; - newinet->inet_saddr = ireq->ir_loc_addr; inet_opt = rcu_dereference(ireq->ireq_opt); RCU_INIT_POINTER(newinet->inet_opt, inet_opt); newinet->mc_index = inet_iif(skb); @@ -1855,7 +1850,7 @@ put_and_exit: tcp_done(newsk); goto exit; } -EXPORT_SYMBOL(tcp_v4_syn_recv_sock); +EXPORT_IPV6_MOD(tcp_v4_syn_recv_sock); static struct sock *tcp_v4_cookie_check(struct sock *sk, struct sk_buff *skb) { @@ -2026,7 +2021,7 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, */ skb_condense(skb); - skb_dst_drop(skb); + tcp_cleanup_skb(skb); if (unlikely(tcp_checksum_complete(skb))) { bh_unlock_sock(sk); @@ -2134,7 +2129,7 @@ no_coalesce: } return false; } -EXPORT_SYMBOL(tcp_add_backlog); +EXPORT_IPV6_MOD(tcp_add_backlog); int tcp_filter(struct sock *sk, struct sk_buff *skb) { @@ -2142,7 +2137,7 @@ int tcp_filter(struct sock *sk, struct sk_buff *skb) return sk_filter_trim_cap(sk, skb, th->doff * 4); } -EXPORT_SYMBOL(tcp_filter); +EXPORT_IPV6_MOD(tcp_filter); static void tcp_v4_restore_cb(struct sk_buff *skb) { @@ -2451,7 +2446,7 @@ void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) sk->sk_rx_dst_ifindex = skb->skb_iif; } } -EXPORT_SYMBOL(inet_sk_rx_dst_set); +EXPORT_IPV6_MOD(inet_sk_rx_dst_set); const struct inet_connection_sock_af_ops ipv4_specific = { .queue_xmit = ip_queue_xmit, @@ -2467,7 +2462,7 @@ const struct inet_connection_sock_af_ops ipv4_specific = { .sockaddr_len = sizeof(struct sockaddr_in), .mtu_reduced = tcp_v4_mtu_reduced, }; -EXPORT_SYMBOL(ipv4_specific); +EXPORT_IPV6_MOD(ipv4_specific); #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) static const struct tcp_sock_af_ops tcp_sock_ipv4_specific = { @@ -2577,7 +2572,7 @@ void tcp_v4_destroy_sock(struct sock *sk) sk_sockets_allocated_dec(sk); } -EXPORT_SYMBOL(tcp_v4_destroy_sock); +EXPORT_IPV6_MOD(tcp_v4_destroy_sock); #ifdef CONFIG_PROC_FS /* Proc filesystem TCP sock list dumping. */ @@ -2813,7 +2808,7 @@ out: st->last_pos = *pos; return rc; } -EXPORT_SYMBOL(tcp_seq_start); +EXPORT_IPV6_MOD(tcp_seq_start); void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos) { @@ -2844,7 +2839,7 @@ out: st->last_pos = *pos; return rc; } -EXPORT_SYMBOL(tcp_seq_next); +EXPORT_IPV6_MOD(tcp_seq_next); void tcp_seq_stop(struct seq_file *seq, void *v) { @@ -2862,7 +2857,7 @@ void tcp_seq_stop(struct seq_file *seq, void *v) break; } } -EXPORT_SYMBOL(tcp_seq_stop); +EXPORT_IPV6_MOD(tcp_seq_stop); static void get_openreq4(const struct request_sock *req, struct seq_file *f, int i) diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 0deb2ac85acf..1eccc518b957 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -264,7 +264,7 @@ kill: inet_twsk_put(tw); return TCP_TW_SUCCESS; } -EXPORT_SYMBOL(tcp_timewait_state_process); +EXPORT_IPV6_MOD(tcp_timewait_state_process); static void tcp_time_wait_init(struct sock *sk, struct tcp_timewait_sock *tcptw) { @@ -398,7 +398,7 @@ void tcp_twsk_destructor(struct sock *sk) #endif tcp_ao_destroy_sock(sk, true); } -EXPORT_SYMBOL_GPL(tcp_twsk_destructor); +EXPORT_IPV6_MOD_GPL(tcp_twsk_destructor); void tcp_twsk_purge(struct list_head *net_exit_list) { @@ -457,7 +457,6 @@ void tcp_openreq_init_rwin(struct request_sock *req, rcv_wnd); ireq->rcv_wscale = rcv_wscale; } -EXPORT_SYMBOL(tcp_openreq_init_rwin); static void tcp_ecn_openreq_child(struct tcp_sock *tp, const struct request_sock *req) @@ -492,7 +491,7 @@ void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst) tcp_set_ca_state(sk, TCP_CA_Open); } -EXPORT_SYMBOL_GPL(tcp_ca_openreq_child); +EXPORT_IPV6_MOD_GPL(tcp_ca_openreq_child); static void smc_check_reset_syn_req(const struct tcp_sock *oldtp, struct request_sock *req, @@ -909,7 +908,7 @@ embryonic_reset: } return NULL; } -EXPORT_SYMBOL(tcp_check_req); +EXPORT_IPV6_MOD(tcp_check_req); /* * Queue segment on the new socket if the new socket is active, @@ -951,4 +950,4 @@ enum skb_drop_reason tcp_child_process(struct sock *parent, struct sock *child, sock_put(child); return reason; } -EXPORT_SYMBOL(tcp_child_process); +EXPORT_IPV6_MOD(tcp_child_process); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index a796cf451e55..9a3cf51eab78 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -250,7 +250,7 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss, WRITE_ONCE(*__window_clamp, min_t(__u32, U16_MAX << (*rcv_wscale), window_clamp)); } -EXPORT_SYMBOL(tcp_select_initial_window); +EXPORT_IPV6_MOD(tcp_select_initial_window); /* Chose a new window to advertise, update state in tcp_sock for the * socket, and return result with RFC1323 scaling applied. The return @@ -1173,7 +1173,7 @@ void tcp_release_cb(struct sock *sk) if ((flags & TCPF_ACK_DEFERRED) && inet_csk_ack_scheduled(sk)) tcp_send_ack(sk); } -EXPORT_SYMBOL(tcp_release_cb); +EXPORT_IPV6_MOD(tcp_release_cb); void __init tcp_tasklet_init(void) { @@ -1785,7 +1785,7 @@ int tcp_mtu_to_mss(struct sock *sk, int pmtu) return __tcp_mtu_to_mss(sk, pmtu) - (tcp_sk(sk)->tcp_header_len - sizeof(struct tcphdr)); } -EXPORT_SYMBOL(tcp_mtu_to_mss); +EXPORT_IPV6_MOD(tcp_mtu_to_mss); /* Inverse of above */ int tcp_mss_to_mtu(struct sock *sk, int mss) @@ -1858,7 +1858,7 @@ unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu) return mss_now; } -EXPORT_SYMBOL(tcp_sync_mss); +EXPORT_IPV6_MOD(tcp_sync_mss); /* Compute the current effective MSS, taking SACKs and IP options, * and even PMTU discovery events into account. @@ -3853,7 +3853,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, return skb; } -EXPORT_SYMBOL(tcp_make_synack); +EXPORT_IPV6_MOD(tcp_make_synack); static void tcp_ca_dst_init(struct sock *sk, const struct dst_entry *dst) { @@ -4430,4 +4430,4 @@ int tcp_rtx_synack(const struct sock *sk, struct request_sock *req) } return res; } -EXPORT_SYMBOL(tcp_rtx_synack); +EXPORT_IPV6_MOD(tcp_rtx_synack); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index c0e601e4f39c..728bce01ccd3 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -750,7 +750,7 @@ void tcp_syn_ack_timeout(const struct request_sock *req) __NET_INC_STATS(net, LINUX_MIB_TCPTIMEOUTS); } -EXPORT_SYMBOL(tcp_syn_ack_timeout); +EXPORT_IPV6_MOD(tcp_syn_ack_timeout); void tcp_reset_keepalive_timer(struct sock *sk, unsigned long len) { @@ -772,7 +772,7 @@ void tcp_set_keepalive(struct sock *sk, int val) else if (!val) tcp_delete_keepalive_timer(sk); } -EXPORT_SYMBOL_GPL(tcp_set_keepalive); +EXPORT_IPV6_MOD_GPL(tcp_set_keepalive); static void tcp_keepalive_timer(struct timer_list *t) { diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index a9bb9ce5438e..17c7736d8349 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -121,13 +121,12 @@ #endif struct udp_table udp_table __read_mostly; -EXPORT_SYMBOL(udp_table); long sysctl_udp_mem[3] __read_mostly; -EXPORT_SYMBOL(sysctl_udp_mem); +EXPORT_IPV6_MOD(sysctl_udp_mem); atomic_long_t udp_memory_allocated ____cacheline_aligned_in_smp; -EXPORT_SYMBOL(udp_memory_allocated); +EXPORT_IPV6_MOD(udp_memory_allocated); DEFINE_PER_CPU(int, udp_memory_per_cpu_fw_alloc); EXPORT_PER_CPU_SYMBOL_GPL(udp_memory_per_cpu_fw_alloc); @@ -352,7 +351,7 @@ fail_unlock: fail: return error; } -EXPORT_SYMBOL(udp_lib_get_port); +EXPORT_IPV6_MOD(udp_lib_get_port); int udp_v4_get_port(struct sock *sk, unsigned short snum) { @@ -418,7 +417,7 @@ u32 udp_ehashfn(const struct net *net, const __be32 laddr, const __u16 lport, return __inet_ehashfn(laddr, lport, faddr, fport, udp_ehash_secret + net_hash_mix(net)); } -EXPORT_SYMBOL(udp_ehashfn); +EXPORT_IPV6_MOD(udp_ehashfn); /** * udp4_lib_lookup1() - Simplified lookup using primary hash (destination port) @@ -653,7 +652,7 @@ void udp_lib_hash4(struct sock *sk, u16 hash) spin_unlock_bh(&hslot->lock); } -EXPORT_SYMBOL(udp_lib_hash4); +EXPORT_IPV6_MOD(udp_lib_hash4); /* call with sock lock */ void udp4_hash4(struct sock *sk) @@ -669,7 +668,7 @@ void udp4_hash4(struct sock *sk) udp_lib_hash4(sk, hash); } -EXPORT_SYMBOL(udp4_hash4); +EXPORT_IPV6_MOD(udp4_hash4); #endif /* CONFIG_BASE_SMALL */ /* UDP is nearly always wildcards out the wazoo, it makes no sense to try @@ -809,11 +808,11 @@ static inline bool __udp_is_mcast_sock(struct net *net, const struct sock *sk, } DEFINE_STATIC_KEY_FALSE(udp_encap_needed_key); -EXPORT_SYMBOL(udp_encap_needed_key); +EXPORT_IPV6_MOD(udp_encap_needed_key); #if IS_ENABLED(CONFIG_IPV6) DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key); -EXPORT_SYMBOL(udpv6_encap_needed_key); +EXPORT_IPV6_MOD(udpv6_encap_needed_key); #endif void udp_encap_enable(void) @@ -1041,7 +1040,7 @@ void udp_flush_pending_frames(struct sock *sk) ip_flush_pending_frames(sk); } } -EXPORT_SYMBOL(udp_flush_pending_frames); +EXPORT_IPV6_MOD(udp_flush_pending_frames); /** * udp4_hwcsum - handle outgoing HW checksumming @@ -1229,7 +1228,7 @@ out: WRITE_ONCE(up->pending, 0); return err; } -EXPORT_SYMBOL(udp_push_pending_frames); +EXPORT_IPV6_MOD(udp_push_pending_frames); static int __udp_cmsg_send(struct cmsghdr *cmsg, u16 *gso_size) { @@ -1266,7 +1265,7 @@ int udp_cmsg_send(struct sock *sk, struct msghdr *msg, u16 *gso_size) return need_ip; } -EXPORT_SYMBOL_GPL(udp_cmsg_send); +EXPORT_IPV6_MOD_GPL(udp_cmsg_send); int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { @@ -1281,7 +1280,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) int free = 0; int connected = 0; __be32 daddr, faddr, saddr; - u8 tos, scope; + u8 scope; __be16 dport; int err, is_udplite = IS_UDPLITE(sk); int corkreq = udp_test_bit(CORK, sk) || msg->msg_flags & MSG_MORE; @@ -1405,7 +1404,6 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) faddr = ipc.opt->opt.faddr; connected = 0; } - tos = get_rttos(&ipc, inet); scope = ip_sendmsg_scope(inet, &ipc, msg); if (scope == RT_SCOPE_LINK) connected = 0; @@ -1442,7 +1440,8 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) fl4 = &fl4_stack; - flowi4_init_output(fl4, ipc.oif, ipc.sockc.mark, tos, scope, + flowi4_init_output(fl4, ipc.oif, ipc.sockc.mark, + ipc.tos & INET_DSCP_MASK, scope, sk->sk_protocol, flow_flags, faddr, saddr, dport, inet->inet_sport, sk->sk_uid); @@ -1561,7 +1560,7 @@ void udp_splice_eof(struct socket *sock) udp_push_pending_frames(sk); release_sock(sk); } -EXPORT_SYMBOL_GPL(udp_splice_eof); +EXPORT_IPV6_MOD_GPL(udp_splice_eof); #define UDP_SKB_IS_STATELESS 0x80000000 @@ -1678,7 +1677,7 @@ void udp_skb_destructor(struct sock *sk, struct sk_buff *skb) prefetch(&skb->data); udp_rmem_release(sk, udp_skb_truesize(skb), 1, false); } -EXPORT_SYMBOL(udp_skb_destructor); +EXPORT_IPV6_MOD(udp_skb_destructor); /* as above, but the caller held the rx queue lock, too */ static void udp_skb_dtor_locked(struct sock *sk, struct sk_buff *skb) @@ -1785,7 +1784,7 @@ drop: busylock_release(busy); return err; } -EXPORT_SYMBOL_GPL(__udp_enqueue_schedule_skb); +EXPORT_IPV6_MOD_GPL(__udp_enqueue_schedule_skb); void udp_destruct_common(struct sock *sk) { @@ -1801,7 +1800,7 @@ void udp_destruct_common(struct sock *sk) } udp_rmem_release(sk, total, 0, true); } -EXPORT_SYMBOL_GPL(udp_destruct_common); +EXPORT_IPV6_MOD_GPL(udp_destruct_common); static void udp_destruct_sock(struct sock *sk) { @@ -1832,7 +1831,7 @@ void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len) skb_release_head_state(skb); __consume_stateless_skb(skb); } -EXPORT_SYMBOL_GPL(skb_consume_udp); +EXPORT_IPV6_MOD_GPL(skb_consume_udp); static struct sk_buff *__first_packet_length(struct sock *sk, struct sk_buff_head *rcvq, @@ -1914,7 +1913,7 @@ int udp_ioctl(struct sock *sk, int cmd, int *karg) return 0; } -EXPORT_SYMBOL(udp_ioctl); +EXPORT_IPV6_MOD(udp_ioctl); struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags, int *off, int *err) @@ -2010,7 +2009,7 @@ try_again: WARN_ON_ONCE(!skb_set_owner_sk_safe(skb, sk)); return recv_actor(sk, skb); } -EXPORT_SYMBOL(udp_read_skb); +EXPORT_IPV6_MOD(udp_read_skb); /* * This should be easy, if there is something there we @@ -2137,7 +2136,7 @@ int udp_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) return BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr, &addr_len); } -EXPORT_SYMBOL(udp_pre_connect); +EXPORT_IPV6_MOD(udp_pre_connect); static int udp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { @@ -2186,7 +2185,7 @@ int udp_disconnect(struct sock *sk, int flags) release_sock(sk); return 0; } -EXPORT_SYMBOL(udp_disconnect); +EXPORT_IPV6_MOD(udp_disconnect); void udp_lib_unhash(struct sock *sk) { @@ -2216,7 +2215,7 @@ void udp_lib_unhash(struct sock *sk) spin_unlock_bh(&hslot->lock); } } -EXPORT_SYMBOL(udp_lib_unhash); +EXPORT_IPV6_MOD(udp_lib_unhash); /* * inet_rcv_saddr was changed, we must rehash secondary hash @@ -2280,7 +2279,7 @@ void udp_lib_rehash(struct sock *sk, u16 newhash, u16 newhash4) } } } -EXPORT_SYMBOL(udp_lib_rehash); +EXPORT_IPV6_MOD(udp_lib_rehash); void udp_v4_rehash(struct sock *sk) { @@ -2485,7 +2484,7 @@ bool udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst) } return false; } -EXPORT_SYMBOL(udp_sk_rx_dst_set); +EXPORT_IPV6_MOD(udp_sk_rx_dst_set); /* * Multicasts and broadcasts go to each listener. @@ -3041,7 +3040,7 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, return err; } -EXPORT_SYMBOL(udp_lib_setsockopt); +EXPORT_IPV6_MOD(udp_lib_setsockopt); int udp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) @@ -3112,7 +3111,7 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname, return -EFAULT; return 0; } -EXPORT_SYMBOL(udp_lib_getsockopt); +EXPORT_IPV6_MOD(udp_lib_getsockopt); int udp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) @@ -3154,7 +3153,7 @@ __poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait) return mask; } -EXPORT_SYMBOL(udp_poll); +EXPORT_IPV6_MOD(udp_poll); int udp_abort(struct sock *sk, int err) { @@ -3177,7 +3176,7 @@ out: return 0; } -EXPORT_SYMBOL_GPL(udp_abort); +EXPORT_IPV6_MOD_GPL(udp_abort); struct proto udp_prot = { .name = "UDP", @@ -3311,7 +3310,7 @@ void *udp_seq_start(struct seq_file *seq, loff_t *pos) return *pos ? udp_get_idx(seq, *pos-1) : SEQ_START_TOKEN; } -EXPORT_SYMBOL(udp_seq_start); +EXPORT_IPV6_MOD(udp_seq_start); void *udp_seq_next(struct seq_file *seq, void *v, loff_t *pos) { @@ -3325,7 +3324,7 @@ void *udp_seq_next(struct seq_file *seq, void *v, loff_t *pos) ++*pos; return sk; } -EXPORT_SYMBOL(udp_seq_next); +EXPORT_IPV6_MOD(udp_seq_next); void udp_seq_stop(struct seq_file *seq, void *v) { @@ -3337,7 +3336,7 @@ void udp_seq_stop(struct seq_file *seq, void *v) if (state->bucket <= udptable->mask) spin_unlock_bh(&udptable->hash[state->bucket].lock); } -EXPORT_SYMBOL(udp_seq_stop); +EXPORT_IPV6_MOD(udp_seq_stop); /* ------------------------------------------------------------------------ */ static void udp4_format_sock(struct sock *sp, struct seq_file *f, @@ -3616,7 +3615,7 @@ const struct seq_operations udp_seq_ops = { .stop = udp_seq_stop, .show = udp4_seq_show, }; -EXPORT_SYMBOL(udp_seq_ops); +EXPORT_IPV6_MOD(udp_seq_ops); static struct udp_seq_afinfo udp4_seq_afinfo = { .family = AF_INET, diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 40af8fd6efa7..0144d01417d9 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -340,12 +340,12 @@ INDIRECT_CALLABLE_SCOPE int fib6_rule_match(struct fib_rule *rule, if (rule->ip_proto && (rule->ip_proto != fl6->flowi6_proto)) return 0; - if (fib_rule_port_range_set(&rule->sport_range) && - !fib_rule_port_inrange(&rule->sport_range, fl6->fl6_sport)) + if (!fib_rule_port_match(&rule->sport_range, rule->sport_mask, + fl6->fl6_sport)) return 0; - if (fib_rule_port_range_set(&rule->dport_range) && - !fib_rule_port_inrange(&rule->dport_range, fl6->fl6_dport)) + if (!fib_rule_port_match(&rule->dport_range, rule->dport_mask, + fl6->fl6_dport)) return 0; return 1; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 235808cfec70..d31a4ce3b19f 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1498,7 +1498,6 @@ static int ip6gre_tunnel_init_common(struct net_device *dev) tunnel = netdev_priv(dev); tunnel->dev = dev; - tunnel->net = dev_net(dev); strcpy(tunnel->parms.name, dev->name); ret = dst_cache_init(&tunnel->dst_cache, GFP_KERNEL); @@ -1882,7 +1881,6 @@ static int ip6erspan_tap_init(struct net_device *dev) tunnel = netdev_priv(dev); tunnel->dev = dev; - tunnel->net = dev_net(dev); strcpy(tunnel->parms.name, dev->name); ret = dst_cache_init(&tunnel->dst_cache, GFP_KERNEL); @@ -1971,7 +1969,7 @@ static bool ip6gre_netlink_encap_parms(struct nlattr *data[], return ret; } -static int ip6gre_newlink_common(struct net *src_net, struct net_device *dev, +static int ip6gre_newlink_common(struct net *link_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { @@ -1992,7 +1990,7 @@ static int ip6gre_newlink_common(struct net *src_net, struct net_device *dev, eth_hw_addr_random(dev); nt->dev = dev; - nt->net = dev_net(dev); + nt->net = link_net; err = register_netdevice(dev); if (err) @@ -2005,12 +2003,14 @@ out: return err; } -static int ip6gre_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +static int ip6gre_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { + struct net *net = params->link_net ? : dev_net(dev); struct ip6_tnl *nt = netdev_priv(dev); - struct net *net = dev_net(dev); + struct nlattr **data = params->data; + struct nlattr **tb = params->tb; struct ip6gre_net *ign; int err; @@ -2025,7 +2025,7 @@ static int ip6gre_newlink(struct net *src_net, struct net_device *dev, return -EEXIST; } - err = ip6gre_newlink_common(src_net, dev, tb, data, extack); + err = ip6gre_newlink_common(net, dev, tb, data, extack); if (!err) { ip6gre_tnl_link_config(nt, !tb[IFLA_MTU]); ip6gre_tunnel_link_md(ign, nt); @@ -2241,12 +2241,14 @@ static void ip6erspan_tap_setup(struct net_device *dev) netif_keep_dst(dev); } -static int ip6erspan_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +static int ip6erspan_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { + struct net *net = params->link_net ? : dev_net(dev); struct ip6_tnl *nt = netdev_priv(dev); - struct net *net = dev_net(dev); + struct nlattr **data = params->data; + struct nlattr **tb = params->tb; struct ip6gre_net *ign; int err; @@ -2262,7 +2264,7 @@ static int ip6erspan_newlink(struct net *src_net, struct net_device *dev, return -EEXIST; } - err = ip6gre_newlink_common(src_net, dev, tb, data, extack); + err = ip6gre_newlink_common(net, dev, tb, data, extack); if (!err) { ip6erspan_tnl_link_config(nt, !tb[IFLA_MTU]); ip6erspan_tunnel_link_md(ign, nt); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 48fd53b98972..89d206731af0 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -253,8 +253,7 @@ static void ip6_dev_free(struct net_device *dev) static int ip6_tnl_create2(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); - struct net *net = dev_net(dev); - struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); + struct ip6_tnl_net *ip6n = net_generic(t->net, ip6_tnl_net_id); int err; dev->rtnl_link_ops = &ip6_link_ops; @@ -1878,7 +1877,6 @@ ip6_tnl_dev_init_gen(struct net_device *dev) int t_hlen; t->dev = dev; - t->net = dev_net(dev); ret = dst_cache_init(&t->dst_cache, GFP_KERNEL); if (ret) @@ -1940,6 +1938,7 @@ static int __net_init ip6_fb_tnl_dev_init(struct net_device *dev) struct net *net = dev_net(dev); struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); + t->net = net; t->parms.proto = IPPROTO_IPV6; rcu_assign_pointer(ip6n->tnls_wc[0], t); @@ -2002,17 +2001,22 @@ static void ip6_tnl_netlink_parms(struct nlattr *data[], parms->fwmark = nla_get_u32(data[IFLA_IPTUN_FWMARK]); } -static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +static int ip6_tnl_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { - struct net *net = dev_net(dev); - struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); + struct nlattr **data = params->data; + struct nlattr **tb = params->tb; struct ip_tunnel_encap ipencap; + struct ip6_tnl_net *ip6n; struct ip6_tnl *nt, *t; + struct net *net; int err; + net = params->link_net ? : dev_net(dev); + ip6n = net_generic(net, ip6_tnl_net_id); nt = netdev_priv(dev); + nt->net = net; if (ip_tunnel_netlink_encap_parms(data, &ipencap)) { err = ip6_tnl_encap_setup(nt, &ipencap); diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 590737c27537..83c055996fbb 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -177,8 +177,7 @@ vti6_tnl_unlink(struct vti6_net *ip6n, struct ip6_tnl *t) static int vti6_tnl_create2(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); - struct net *net = dev_net(dev); - struct vti6_net *ip6n = net_generic(net, vti6_net_id); + struct vti6_net *ip6n = net_generic(t->net, vti6_net_id); int err; dev->rtnl_link_ops = &vti6_link_ops; @@ -925,7 +924,6 @@ static inline int vti6_dev_init_gen(struct net_device *dev) struct ip6_tnl *t = netdev_priv(dev); t->dev = dev; - t->net = dev_net(dev); netdev_hold(dev, &t->dev_tracker, GFP_KERNEL); netdev_lockdep_set_classes(dev); return 0; @@ -958,6 +956,7 @@ static int __net_init vti6_fb_tnl_dev_init(struct net_device *dev) struct net *net = dev_net(dev); struct vti6_net *ip6n = net_generic(net, vti6_net_id); + t->net = net; t->parms.proto = IPPROTO_IPV6; rcu_assign_pointer(ip6n->tnls_wc[0], t); @@ -997,17 +996,20 @@ static void vti6_netlink_parms(struct nlattr *data[], parms->fwmark = nla_get_u32(data[IFLA_VTI_FWMARK]); } -static int vti6_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +static int vti6_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { - struct net *net = dev_net(dev); + struct nlattr **data = params->data; struct ip6_tnl *nt; + struct net *net; + net = params->link_net ? : dev_net(dev); nt = netdev_priv(dev); vti6_netlink_parms(data, &nt->parms); nt->parms.proto = IPPROTO_IPV6; + nt->net = net; if (vti6_locate(net, &nt->parms, 0)) return -EEXIST; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 8699d1a188dc..ecb5c4b8518f 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1680,7 +1680,7 @@ static void ndisc_fill_redirect_hdr_option(struct sk_buff *skb, void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) { struct net_device *dev = skb->dev; - struct net *net = dev_net(dev); + struct net *net = dev_net_rcu(dev); struct sock *sk = net->ipv6.ndisc_sk; int optlen = 0; struct inet_peer *peer; @@ -1695,8 +1695,8 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) ops_data_buf[NDISC_OPS_REDIRECT_DATA_SPACE], *ops_data = NULL; bool ret; - if (netif_is_l3_master(skb->dev)) { - dev = dev_get_by_index_rcu(dev_net(skb->dev), IPCB(skb)->iif); + if (netif_is_l3_master(dev)) { + dev = dev_get_by_index_rcu(net, IPCB(skb)->iif); if (!dev) return; } @@ -1734,10 +1734,8 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) goto release; } - rcu_read_lock(); peer = inet_getpeer_v6(net->ipv6.peers, &ipv6_hdr(skb)->saddr); ret = inet_peer_xrlim_allow(peer, 1*HZ); - rcu_read_unlock(); if (!ret) goto release; diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index 46b8adf6e7f8..84d90dd8b3f0 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -119,9 +119,6 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) return -EINVAL; ipcm6_init_sk(&ipc6, sk); - ipc6.sockc.priority = READ_ONCE(sk->sk_priority); - ipc6.sockc.tsflags = READ_ONCE(sk->sk_tsflags); - ipc6.sockc.mark = READ_ONCE(sk->sk_mark); fl6.flowi6_oif = oif; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index a45aba090aa4..fda640ebd53f 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -769,19 +769,16 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) hdrincl = inet_test_bit(HDRINCL, sk); + ipcm6_init_sk(&ipc6, sk); + /* * Get and verify the address. */ memset(&fl6, 0, sizeof(fl6)); - fl6.flowi6_mark = READ_ONCE(sk->sk_mark); + fl6.flowi6_mark = ipc6.sockc.mark; fl6.flowi6_uid = sk->sk_uid; - ipcm6_init(&ipc6); - ipc6.sockc.tsflags = READ_ONCE(sk->sk_tsflags); - ipc6.sockc.mark = fl6.flowi6_mark; - ipc6.sockc.priority = READ_ONCE(sk->sk_priority); - if (sin6) { if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; @@ -891,9 +888,6 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (hdrincl) fl6.flowi6_flags |= FLOWI_FLAG_KNOWN_NH; - if (ipc6.tclass < 0) - ipc6.tclass = np->tclass; - fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); @@ -904,9 +898,6 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (ipc6.hlimit < 0) ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); - if (ipc6.dontfrag < 0) - ipc6.dontfrag = inet6_test_bit(DONTFRAG, sk); - if (msg->msg_flags&MSG_CONFIRM) goto do_confirm; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 39bd8951bfca..f7b59bc957d3 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -201,8 +201,7 @@ static void ipip6_tunnel_clone_6rd(struct net_device *dev, struct sit_net *sitn) static int ipip6_tunnel_create(struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); - struct net *net = dev_net(dev); - struct sit_net *sitn = net_generic(net, sit_net_id); + struct sit_net *sitn = net_generic(t->net, sit_net_id); int err; __dev_addr_set(dev, &t->parms.iph.saddr, 4); @@ -269,6 +268,7 @@ static struct ip_tunnel *ipip6_tunnel_locate(struct net *net, nt = netdev_priv(dev); + nt->net = net; nt->parms = *parms; if (ipip6_tunnel_create(dev) < 0) goto failed_free; @@ -1449,7 +1449,6 @@ static int ipip6_tunnel_init(struct net_device *dev) int err; tunnel->dev = dev; - tunnel->net = dev_net(dev); strcpy(tunnel->parms.name, dev->name); ipip6_tunnel_bind_dev(dev); @@ -1550,19 +1549,23 @@ static bool ipip6_netlink_6rd_parms(struct nlattr *data[], } #endif -static int ipip6_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], +static int ipip6_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { - struct net *net = dev_net(dev); + struct nlattr **data = params->data; + struct nlattr **tb = params->tb; struct ip_tunnel *nt; struct ip_tunnel_encap ipencap; #ifdef CONFIG_IPV6_SIT_6RD struct ip_tunnel_6rd ip6rd; #endif + struct net *net; int err; + net = params->link_net ? : dev_net(dev); nt = netdev_priv(dev); + nt->net = net; if (ip_tunnel_netlink_encap_parms(data, &ipencap)) { err = ip_tunnel_encap_setup(nt, &ipencap); @@ -1858,6 +1861,9 @@ static int __net_init sit_init_net(struct net *net) */ sitn->fb_tunnel_dev->netns_local = true; + t = netdev_priv(sitn->fb_tunnel_dev); + t->net = net; + err = register_netdev(sitn->fb_tunnel_dev); if (err) goto err_reg_dev; @@ -1865,8 +1871,6 @@ static int __net_init sit_init_net(struct net *net) ipip6_tunnel_clone_6rd(sitn->fb_tunnel_dev, sitn); ipip6_fb_tunnel_init(sitn->fb_tunnel_dev); - t = netdev_priv(sitn->fb_tunnel_dev); - strcpy(t->parms.name, sitn->fb_tunnel_dev->name); return 0; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 2debdf085a3b..a80608260298 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -798,6 +798,8 @@ static void tcp_v6_init_req(struct request_sock *req, ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr; ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr; + ireq->ir_rmt_addr = LOOPBACK4_IPV6; + ireq->ir_loc_addr = LOOPBACK4_IPV6; /* So that link locals have meaning */ if ((!sk_listener->sk_bound_dev_if || l3_slave) && @@ -1451,10 +1453,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * ip6_dst_store(newsk, dst, NULL, NULL); - newsk->sk_v6_daddr = ireq->ir_v6_rmt_addr; newnp->saddr = ireq->ir_v6_loc_addr; - newsk->sk_v6_rcv_saddr = ireq->ir_v6_loc_addr; - newsk->sk_bound_dev_if = ireq->ir_iif; /* Now IPv6 options... @@ -1507,9 +1506,6 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * tcp_initialize_rcv_mss(newsk); - newinet->inet_daddr = newinet->inet_saddr = LOOPBACK4_IPV6; - newinet->inet_rcv_saddr = LOOPBACK4_IPV6; - #ifdef CONFIG_TCP_MD5SIG l3index = l3mdev_master_ifindex_by_index(sock_net(sk), ireq->ir_iif); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index c6ea438b5c75..3a0d6c5a8286 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1494,11 +1494,8 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) int is_udplite = IS_UDPLITE(sk); int (*getfrag)(void *, char *, int, int, int, struct sk_buff *); - ipcm6_init(&ipc6); + ipcm6_init_sk(&ipc6, sk); ipc6.gso_size = READ_ONCE(up->gso_size); - ipc6.sockc.tsflags = READ_ONCE(sk->sk_tsflags); - ipc6.sockc.mark = READ_ONCE(sk->sk_mark); - ipc6.sockc.priority = READ_ONCE(sk->sk_priority); /* destination address check */ if (sin6) { @@ -1704,9 +1701,6 @@ do_udp_sendmsg: security_sk_classify_flow(sk, flowi6_to_flowi_common(fl6)); - if (ipc6.tclass < 0) - ipc6.tclass = np->tclass; - fl6->flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6->flowlabel); dst = ip6_sk_dst_lookup_flow(sk, fl6, final_p, connected); @@ -1752,8 +1746,6 @@ back_from_confirm: WRITE_ONCE(up->pending, AF_INET6); do_append_data: - if (ipc6.dontfrag < 0) - ipc6.dontfrag = inet6_test_bit(DONTFRAG, sk); up->len += ulen; err = ip6_append_data(sk, getfrag, msg, ulen, sizeof(struct udphdr), &ipc6, fl6, dst_rt6_info(dst), diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index f4c1da070826..b98d13584c81 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -547,7 +547,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) fl6.flowi6_mark = READ_ONCE(sk->sk_mark); fl6.flowi6_uid = sk->sk_uid; - ipcm6_init(&ipc6); + ipcm6_init_sk(&ipc6, sk); if (lsa) { if (addr_len < SIN6_LEN_RFC2133) @@ -634,9 +634,6 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6)); - if (ipc6.tclass < 0) - ipc6.tclass = np->tclass; - fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); @@ -648,9 +645,6 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (ipc6.hlimit < 0) ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); - if (ipc6.dontfrag < 0) - ipc6.dontfrag = inet6_test_bit(DONTFRAG, sk); - if (msg->msg_flags & MSG_CONFIRM) goto do_confirm; diff --git a/net/mptcp/fastopen.c b/net/mptcp/fastopen.c index a29ff901df75..b9e451197902 100644 --- a/net/mptcp/fastopen.c +++ b/net/mptcp/fastopen.c @@ -40,17 +40,17 @@ void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subf tp->copied_seq += skb->len; subflow->ssn_offset += skb->len; - /* initialize a dummy sequence number, we will update it at MPC - * completion, if needed - */ + /* Only the sequence delta is relevant */ MPTCP_SKB_CB(skb)->map_seq = -skb->len; MPTCP_SKB_CB(skb)->end_seq = 0; MPTCP_SKB_CB(skb)->offset = 0; MPTCP_SKB_CB(skb)->has_rxtstamp = TCP_SKB_CB(skb)->has_rxtstamp; + MPTCP_SKB_CB(skb)->cant_coalesce = 1; mptcp_data_lock(sk); + DEBUG_NET_WARN_ON_ONCE(sock_owned_by_user_nocheck(sk)); - mptcp_set_owner_r(skb, sk); + skb_set_owner_r(skb, sk); __skb_queue_tail(&sk->sk_receive_queue, skb); mptcp_sk(sk)->bytes_received += skb->len; @@ -58,22 +58,3 @@ void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subf mptcp_data_unlock(sk); } - -void __mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow, - const struct mptcp_options_received *mp_opt) -{ - struct sock *sk = (struct sock *)msk; - struct sk_buff *skb; - - skb = skb_peek_tail(&sk->sk_receive_queue); - if (skb) { - WARN_ON_ONCE(MPTCP_SKB_CB(skb)->end_seq); - pr_debug("msk %p moving seq %llx -> %llx end_seq %llx -> %llx\n", sk, - MPTCP_SKB_CB(skb)->map_seq, MPTCP_SKB_CB(skb)->map_seq + msk->ack_seq, - MPTCP_SKB_CB(skb)->end_seq, MPTCP_SKB_CB(skb)->end_seq + msk->ack_seq); - MPTCP_SKB_CB(skb)->map_seq += msk->ack_seq; - MPTCP_SKB_CB(skb)->end_seq += msk->ack_seq; - } - - pr_debug("msk=%p ack_seq=%llx\n", msk, msk->ack_seq); -} diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 6bd819047470..6b61b7dee33b 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -118,24 +118,14 @@ static void mptcp_drop(struct sock *sk, struct sk_buff *skb) __kfree_skb(skb); } -static void mptcp_rmem_fwd_alloc_add(struct sock *sk, int size) -{ - WRITE_ONCE(mptcp_sk(sk)->rmem_fwd_alloc, - mptcp_sk(sk)->rmem_fwd_alloc + size); -} - -static void mptcp_rmem_charge(struct sock *sk, int size) -{ - mptcp_rmem_fwd_alloc_add(sk, -size); -} - static bool mptcp_try_coalesce(struct sock *sk, struct sk_buff *to, struct sk_buff *from) { bool fragstolen; int delta; - if (MPTCP_SKB_CB(from)->offset || + if (unlikely(MPTCP_SKB_CB(to)->cant_coalesce) || + MPTCP_SKB_CB(from)->offset || ((to->len + from->len) > (sk->sk_rcvbuf >> 3)) || !skb_try_coalesce(to, from, &fragstolen, &delta)) return false; @@ -150,7 +140,7 @@ static bool mptcp_try_coalesce(struct sock *sk, struct sk_buff *to, * negative one */ atomic_add(delta, &sk->sk_rmem_alloc); - mptcp_rmem_charge(sk, delta); + sk_mem_charge(sk, delta); kfree_skb_partial(from, fragstolen); return true; @@ -165,44 +155,6 @@ static bool mptcp_ooo_try_coalesce(struct mptcp_sock *msk, struct sk_buff *to, return mptcp_try_coalesce((struct sock *)msk, to, from); } -static void __mptcp_rmem_reclaim(struct sock *sk, int amount) -{ - amount >>= PAGE_SHIFT; - mptcp_rmem_charge(sk, amount << PAGE_SHIFT); - __sk_mem_reduce_allocated(sk, amount); -} - -static void mptcp_rmem_uncharge(struct sock *sk, int size) -{ - struct mptcp_sock *msk = mptcp_sk(sk); - int reclaimable; - - mptcp_rmem_fwd_alloc_add(sk, size); - reclaimable = msk->rmem_fwd_alloc - sk_unused_reserved_mem(sk); - - /* see sk_mem_uncharge() for the rationale behind the following schema */ - if (unlikely(reclaimable >= PAGE_SIZE)) - __mptcp_rmem_reclaim(sk, reclaimable); -} - -static void mptcp_rfree(struct sk_buff *skb) -{ - unsigned int len = skb->truesize; - struct sock *sk = skb->sk; - - atomic_sub(len, &sk->sk_rmem_alloc); - mptcp_rmem_uncharge(sk, len); -} - -void mptcp_set_owner_r(struct sk_buff *skb, struct sock *sk) -{ - skb_orphan(skb); - skb->sk = sk; - skb->destructor = mptcp_rfree; - atomic_add(skb->truesize, &sk->sk_rmem_alloc); - mptcp_rmem_charge(sk, skb->truesize); -} - /* "inspired" by tcp_data_queue_ofo(), main differences: * - use mptcp seqs * - don't cope with sacks @@ -315,25 +267,7 @@ merge_right: end: skb_condense(skb); - mptcp_set_owner_r(skb, sk); -} - -static bool mptcp_rmem_schedule(struct sock *sk, struct sock *ssk, int size) -{ - struct mptcp_sock *msk = mptcp_sk(sk); - int amt, amount; - - if (size <= msk->rmem_fwd_alloc) - return true; - - size -= msk->rmem_fwd_alloc; - amt = sk_mem_pages(size); - amount = amt << PAGE_SHIFT; - if (!__sk_mem_raise_allocated(sk, size, amt, SK_MEM_RECV)) - return false; - - mptcp_rmem_fwd_alloc_add(sk, amount); - return true; + skb_set_owner_r(skb, sk); } static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk, @@ -351,7 +285,7 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk, skb_orphan(skb); /* try to fetch required memory from subflow */ - if (!mptcp_rmem_schedule(sk, ssk, skb->truesize)) { + if (!sk_rmem_schedule(sk, skb, skb->truesize)) { MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED); goto drop; } @@ -366,6 +300,7 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk, MPTCP_SKB_CB(skb)->end_seq = MPTCP_SKB_CB(skb)->map_seq + copy_len; MPTCP_SKB_CB(skb)->offset = offset; MPTCP_SKB_CB(skb)->has_rxtstamp = has_rxtstamp; + MPTCP_SKB_CB(skb)->cant_coalesce = 0; if (MPTCP_SKB_CB(skb)->map_seq == msk->ack_seq) { /* in sequence */ @@ -375,7 +310,7 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk, if (tail && mptcp_try_coalesce(sk, tail, skb)) return true; - mptcp_set_owner_r(skb, sk); + skb_set_owner_r(skb, sk); __skb_queue_tail(&sk->sk_receive_queue, skb); return true; } else if (after64(MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq)) { @@ -561,7 +496,7 @@ static void mptcp_cleanup_rbuf(struct mptcp_sock *msk, int copied) bool cleanup, rx_empty; cleanup = (space > 0) && (space >= (old_space << 1)) && copied; - rx_empty = !__mptcp_rmem(sk) && copied; + rx_empty = !sk_rmem_alloc_get(sk) && copied; mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); @@ -634,27 +569,13 @@ static void mptcp_dss_corruption(struct mptcp_sock *msk, struct sock *ssk) } static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, - struct sock *ssk, - unsigned int *bytes) + struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct sock *sk = (struct sock *)msk; - unsigned int moved = 0; bool more_data_avail; struct tcp_sock *tp; - bool done = false; - int sk_rbuf; - - sk_rbuf = READ_ONCE(sk->sk_rcvbuf); - - if (!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) { - int ssk_rbuf = READ_ONCE(ssk->sk_rcvbuf); - - if (unlikely(ssk_rbuf > sk_rbuf)) { - WRITE_ONCE(sk->sk_rcvbuf, ssk_rbuf); - sk_rbuf = ssk_rbuf; - } - } + bool ret = false; pr_debug("msk=%p ssk=%p\n", msk, ssk); tp = tcp_sk(ssk); @@ -664,20 +585,16 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, struct sk_buff *skb; bool fin; + if (sk_rmem_alloc_get(sk) > sk->sk_rcvbuf) + break; + /* try to move as much data as available */ map_remaining = subflow->map_data_len - mptcp_subflow_get_map_offset(subflow); skb = skb_peek(&ssk->sk_receive_queue); - if (!skb) { - /* With racing move_skbs_to_msk() and __mptcp_move_skbs(), - * a different CPU can have already processed the pending - * data, stop here or we can enter an infinite loop - */ - if (!moved) - done = true; + if (unlikely(!skb)) break; - } if (__mptcp_check_fallback(msk)) { /* Under fallback skbs have no MPTCP extension and TCP could @@ -690,19 +607,13 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, offset = seq - TCP_SKB_CB(skb)->seq; fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN; - if (fin) { - done = true; + if (fin) seq++; - } if (offset < skb->len) { size_t len = skb->len - offset; - if (tp->urg_data) - done = true; - - if (__mptcp_move_skb(msk, ssk, skb, offset, len)) - moved += len; + ret = __mptcp_move_skb(msk, ssk, skb, offset, len) || ret; seq += len; if (unlikely(map_remaining < len)) { @@ -716,22 +627,16 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, } sk_eat_skb(ssk, skb); - done = true; } WRITE_ONCE(tp->copied_seq, seq); more_data_avail = mptcp_subflow_data_available(ssk); - if (atomic_read(&sk->sk_rmem_alloc) > sk_rbuf) { - done = true; - break; - } } while (more_data_avail); - if (moved > 0) + if (ret) msk->last_data_recv = tcp_jiffies32; - *bytes += moved; - return done; + return ret; } static bool __mptcp_ofo_queue(struct mptcp_sock *msk) @@ -825,9 +730,9 @@ void __mptcp_error_report(struct sock *sk) static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk) { struct sock *sk = (struct sock *)msk; - unsigned int moved = 0; + bool moved; - __mptcp_move_skbs_from_subflow(msk, ssk, &moved); + moved = __mptcp_move_skbs_from_subflow(msk, ssk); __mptcp_ofo_queue(msk); if (unlikely(ssk->sk_err)) { if (!sock_owned_by_user(sk)) @@ -843,14 +748,29 @@ static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk) */ if (mptcp_pending_data_fin(sk, NULL)) mptcp_schedule_work(sk); - return moved > 0; + return moved; +} + +static void __mptcp_rcvbuf_update(struct sock *sk, struct sock *ssk) +{ + if (unlikely(ssk->sk_rcvbuf > sk->sk_rcvbuf)) + WRITE_ONCE(sk->sk_rcvbuf, ssk->sk_rcvbuf); +} + +static void __mptcp_data_ready(struct sock *sk, struct sock *ssk) +{ + struct mptcp_sock *msk = mptcp_sk(sk); + + __mptcp_rcvbuf_update(sk, ssk); + + /* Wake-up the reader only for in-sequence data */ + if (move_skbs_to_msk(msk, ssk) && mptcp_epollin_ready(sk)) + sk->sk_data_ready(sk); } void mptcp_data_ready(struct sock *sk, struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); - struct mptcp_sock *msk = mptcp_sk(sk); - int sk_rbuf, ssk_rbuf; /* The peer can send data while we are shutting down this * subflow at msk destruction time, but we must avoid enqueuing @@ -859,19 +779,11 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk) if (unlikely(subflow->disposable)) return; - ssk_rbuf = READ_ONCE(ssk->sk_rcvbuf); - sk_rbuf = READ_ONCE(sk->sk_rcvbuf); - if (unlikely(ssk_rbuf > sk_rbuf)) - sk_rbuf = ssk_rbuf; - - /* over limit? can't append more skbs to msk, Also, no need to wake-up*/ - if (__mptcp_rmem(sk) > sk_rbuf) - return; - - /* Wake-up the reader only for in-sequence data */ mptcp_data_lock(sk); - if (move_skbs_to_msk(msk, ssk) && mptcp_epollin_ready(sk)) - sk->sk_data_ready(sk); + if (!sock_owned_by_user(sk)) + __mptcp_data_ready(sk, ssk); + else + __set_bit(MPTCP_DEQUEUE, &mptcp_sk(sk)->cb_flags); mptcp_data_unlock(sk); } @@ -950,20 +862,6 @@ bool mptcp_schedule_work(struct sock *sk) return false; } -static struct sock *mptcp_subflow_recv_lookup(const struct mptcp_sock *msk) -{ - struct mptcp_subflow_context *subflow; - - msk_owned_by_me(msk); - - mptcp_for_each_subflow(msk, subflow) { - if (READ_ONCE(subflow->data_avail)) - return mptcp_subflow_tcp_sock(subflow); - } - - return NULL; -} - static bool mptcp_skb_can_collapse_to(u64 write_seq, const struct sk_buff *skb, const struct mptcp_ext *mpext) @@ -1944,16 +1842,17 @@ do_error: static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied); -static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk, +static int __mptcp_recvmsg_mskq(struct sock *sk, struct msghdr *msg, size_t len, int flags, struct scm_timestamping_internal *tss, int *cmsg_flags) { + struct mptcp_sock *msk = mptcp_sk(sk); struct sk_buff *skb, *tmp; int copied = 0; - skb_queue_walk_safe(&msk->receive_queue, skb, tmp) { + skb_queue_walk_safe(&sk->sk_receive_queue, skb, tmp) { u32 offset = MPTCP_SKB_CB(skb)->offset; u32 data_len = skb->len - offset; u32 count = min_t(size_t, len - copied, data_len); @@ -1985,10 +1884,11 @@ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk, } if (!(flags & MSG_PEEK)) { - /* we will bulk release the skb memory later */ + /* avoid the indirect call, we know the destructor is sock_wfree */ skb->destructor = NULL; - WRITE_ONCE(msk->rmem_released, msk->rmem_released + skb->truesize); - __skb_unlink(skb, &msk->receive_queue); + atomic_sub(skb->truesize, &sk->sk_rmem_alloc); + sk_mem_uncharge(sk, skb->truesize); + __skb_unlink(skb, &sk->sk_receive_queue); __kfree_skb(skb); msk->bytes_consumed += count; } @@ -2101,66 +2001,65 @@ new_measure: msk->rcvq_space.time = mstamp; } -static void __mptcp_update_rmem(struct sock *sk) +static struct mptcp_subflow_context * +__mptcp_first_ready_from(struct mptcp_sock *msk, + struct mptcp_subflow_context *subflow) { - struct mptcp_sock *msk = mptcp_sk(sk); + struct mptcp_subflow_context *start_subflow = subflow; - if (!msk->rmem_released) - return; - - atomic_sub(msk->rmem_released, &sk->sk_rmem_alloc); - mptcp_rmem_uncharge(sk, msk->rmem_released); - WRITE_ONCE(msk->rmem_released, 0); + while (!READ_ONCE(subflow->data_avail)) { + subflow = mptcp_next_subflow(msk, subflow); + if (subflow == start_subflow) + return NULL; + } + return subflow; } -static void __mptcp_splice_receive_queue(struct sock *sk) +static bool __mptcp_move_skbs(struct sock *sk) { + struct mptcp_subflow_context *subflow; struct mptcp_sock *msk = mptcp_sk(sk); + bool ret = false; - skb_queue_splice_tail_init(&sk->sk_receive_queue, &msk->receive_queue); -} + if (list_empty(&msk->conn_list)) + return false; -static bool __mptcp_move_skbs(struct mptcp_sock *msk) -{ - struct sock *sk = (struct sock *)msk; - unsigned int moved = 0; - bool ret, done; + /* verify we can move any data from the subflow, eventually updating */ + if (!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) + mptcp_for_each_subflow(msk, subflow) + __mptcp_rcvbuf_update(sk, subflow->tcp_sock); - do { - struct sock *ssk = mptcp_subflow_recv_lookup(msk); + subflow = list_first_entry(&msk->conn_list, + struct mptcp_subflow_context, node); + for (;;) { + struct sock *ssk; bool slowpath; - /* we can have data pending in the subflows only if the msk - * receive buffer was full at subflow_data_ready() time, - * that is an unlikely slow path. + /* + * As an optimization avoid traversing the subflows list + * and ev. acquiring the subflow socket lock before baling out */ - if (likely(!ssk)) + if (sk_rmem_alloc_get(sk) > sk->sk_rcvbuf) break; - slowpath = lock_sock_fast(ssk); - mptcp_data_lock(sk); - __mptcp_update_rmem(sk); - done = __mptcp_move_skbs_from_subflow(msk, ssk, &moved); - mptcp_data_unlock(sk); + subflow = __mptcp_first_ready_from(msk, subflow); + if (!subflow) + break; + ssk = mptcp_subflow_tcp_sock(subflow); + slowpath = lock_sock_fast(ssk); + ret = __mptcp_move_skbs_from_subflow(msk, ssk) || ret; if (unlikely(ssk->sk_err)) __mptcp_error_report(sk); unlock_sock_fast(ssk, slowpath); - } while (!done); - /* acquire the data lock only if some input data is pending */ - ret = moved > 0; - if (!RB_EMPTY_ROOT(&msk->out_of_order_queue) || - !skb_queue_empty_lockless(&sk->sk_receive_queue)) { - mptcp_data_lock(sk); - __mptcp_update_rmem(sk); - ret |= __mptcp_ofo_queue(msk); - __mptcp_splice_receive_queue(sk); - mptcp_data_unlock(sk); + subflow = mptcp_next_subflow(msk, subflow); } + + __mptcp_ofo_queue(msk); if (ret) mptcp_check_data_fin((struct sock *)msk); - return !skb_queue_empty(&msk->receive_queue); + return ret; } static unsigned int mptcp_inq_hint(const struct sock *sk) @@ -2168,7 +2067,7 @@ static unsigned int mptcp_inq_hint(const struct sock *sk) const struct mptcp_sock *msk = mptcp_sk(sk); const struct sk_buff *skb; - skb = skb_peek(&msk->receive_queue); + skb = skb_peek(&sk->sk_receive_queue); if (skb) { u64 hint_val = READ_ONCE(msk->ack_seq) - MPTCP_SKB_CB(skb)->map_seq; @@ -2214,7 +2113,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, while (copied < len) { int err, bytes_read; - bytes_read = __mptcp_recvmsg_mskq(msk, msg, len - copied, flags, &tss, &cmsg_flags); + bytes_read = __mptcp_recvmsg_mskq(sk, msg, len - copied, flags, &tss, &cmsg_flags); if (unlikely(bytes_read < 0)) { if (!copied) copied = bytes_read; @@ -2223,7 +2122,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, copied += bytes_read; - if (skb_queue_empty(&msk->receive_queue) && __mptcp_move_skbs(msk)) + if (skb_queue_empty(&sk->sk_receive_queue) && __mptcp_move_skbs(sk)) continue; /* only the MPTCP socket status is relevant here. The exit @@ -2249,7 +2148,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, /* race breaker: the shutdown could be after the * previous receive queue check */ - if (__mptcp_move_skbs(msk)) + if (__mptcp_move_skbs(sk)) continue; break; } @@ -2293,9 +2192,8 @@ out_err: } } - pr_debug("msk=%p rx queue empty=%d:%d copied=%d\n", - msk, skb_queue_empty_lockless(&sk->sk_receive_queue), - skb_queue_empty(&msk->receive_queue), copied); + pr_debug("msk=%p rx queue empty=%d copied=%d\n", + msk, skb_queue_empty(&sk->sk_receive_queue), copied); release_sock(sk); return copied; @@ -2822,11 +2720,8 @@ static void __mptcp_init_sock(struct sock *sk) INIT_LIST_HEAD(&msk->join_list); INIT_LIST_HEAD(&msk->rtx_queue); INIT_WORK(&msk->work, mptcp_worker); - __skb_queue_head_init(&msk->receive_queue); msk->out_of_order_queue = RB_ROOT; msk->first_pending = NULL; - WRITE_ONCE(msk->rmem_fwd_alloc, 0); - WRITE_ONCE(msk->rmem_released, 0); msk->timer_ival = TCP_RTO_MIN; msk->scaling_ratio = TCP_DEFAULT_SCALING_RATIO; @@ -3052,8 +2947,6 @@ static void __mptcp_destroy_sock(struct sock *sk) sk->sk_prot->destroy(sk); - WARN_ON_ONCE(READ_ONCE(msk->rmem_fwd_alloc)); - WARN_ON_ONCE(msk->rmem_released); sk_stream_kill_queues(sk); xfrm_sk_free_policy(sk); @@ -3405,18 +3298,12 @@ void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags) mptcp_for_each_subflow_safe(msk, subflow, tmp) __mptcp_close_ssk(sk, mptcp_subflow_tcp_sock(subflow), subflow, flags); - /* move to sk_receive_queue, sk_stream_kill_queues will purge it */ - mptcp_data_lock(sk); - skb_queue_splice_tail_init(&msk->receive_queue, &sk->sk_receive_queue); __skb_queue_purge(&sk->sk_receive_queue); skb_rbtree_purge(&msk->out_of_order_queue); - mptcp_data_unlock(sk); /* move all the rx fwd alloc into the sk_mem_reclaim_final in * inet_sock_destruct() will dispose it */ - sk_forward_alloc_add(sk, msk->rmem_fwd_alloc); - WRITE_ONCE(msk->rmem_fwd_alloc, 0); mptcp_token_destroy(msk); mptcp_pm_free_anno_list(msk); mptcp_free_local_addr_list(msk); @@ -3453,7 +3340,8 @@ void __mptcp_check_push(struct sock *sk, struct sock *ssk) #define MPTCP_FLAGS_PROCESS_CTX_NEED (BIT(MPTCP_PUSH_PENDING) | \ BIT(MPTCP_RETRANSMIT) | \ - BIT(MPTCP_FLUSH_JOIN_LIST)) + BIT(MPTCP_FLUSH_JOIN_LIST) | \ + BIT(MPTCP_DEQUEUE)) /* processes deferred events and flush wmem */ static void mptcp_release_cb(struct sock *sk) @@ -3487,6 +3375,11 @@ static void mptcp_release_cb(struct sock *sk) __mptcp_push_pending(sk, 0); if (flags & BIT(MPTCP_RETRANSMIT)) __mptcp_retrans(sk); + if ((flags & BIT(MPTCP_DEQUEUE)) && __mptcp_move_skbs(sk)) { + /* notify ack seq update */ + mptcp_cleanup_rbuf(msk, 0); + sk->sk_data_ready(sk); + } cond_resched(); spin_lock_bh(&sk->sk_lock.slock); @@ -3506,8 +3399,6 @@ static void mptcp_release_cb(struct sock *sk) if (__test_and_clear_bit(MPTCP_SYNC_SNDBUF, &msk->cb_flags)) __mptcp_sync_sndbuf(sk); } - - __mptcp_update_rmem(sk); } /* MP_JOIN client subflow must wait for 4th ack before sending any data: @@ -3678,12 +3569,6 @@ static void mptcp_shutdown(struct sock *sk, int how) __mptcp_wr_shutdown(sk); } -static int mptcp_forward_alloc_get(const struct sock *sk) -{ - return READ_ONCE(sk->sk_forward_alloc) + - READ_ONCE(mptcp_sk(sk)->rmem_fwd_alloc); -} - static int mptcp_ioctl_outq(const struct mptcp_sock *msk, u64 v) { const struct sock *sk = (void *)msk; @@ -3724,7 +3609,8 @@ static int mptcp_ioctl(struct sock *sk, int cmd, int *karg) return -EINVAL; lock_sock(sk); - __mptcp_move_skbs(msk); + if (__mptcp_move_skbs(sk)) + mptcp_cleanup_rbuf(msk, 0); *karg = mptcp_inq_hint(sk); release_sock(sk); break; @@ -3841,7 +3727,6 @@ static struct proto mptcp_prot = { .hash = mptcp_hash, .unhash = mptcp_unhash, .get_port = mptcp_get_port, - .forward_alloc_get = mptcp_forward_alloc_get, .stream_memory_free = mptcp_stream_memory_free, .sockets_allocated = &mptcp_sockets_allocated, diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 37226cdd9e37..ca65f8bff632 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -124,12 +124,14 @@ #define MPTCP_FLUSH_JOIN_LIST 5 #define MPTCP_SYNC_STATE 6 #define MPTCP_SYNC_SNDBUF 7 +#define MPTCP_DEQUEUE 8 struct mptcp_skb_cb { u64 map_seq; u64 end_seq; u32 offset; - u8 has_rxtstamp:1; + u8 has_rxtstamp; + u8 cant_coalesce; }; #define MPTCP_SKB_CB(__skb) ((struct mptcp_skb_cb *)&((__skb)->cb[0])) @@ -279,7 +281,6 @@ struct mptcp_sock { u64 rcv_data_fin_seq; u64 bytes_retrans; u64 bytes_consumed; - int rmem_fwd_alloc; int snd_burst; int old_wspace; u64 recovery_snd_nxt; /* in recovery mode accept up to this seq; @@ -294,7 +295,6 @@ struct mptcp_sock { u32 last_ack_recv; unsigned long timer_ival; u32 token; - int rmem_released; unsigned long flags; unsigned long cb_flags; bool recovery; /* closing subflow write queue reinjected */ @@ -324,7 +324,6 @@ struct mptcp_sock { struct work_struct work; struct sk_buff *ooo_last_skb; struct rb_root out_of_order_queue; - struct sk_buff_head receive_queue; struct list_head conn_list; struct list_head rtx_queue; struct mptcp_data_frag *first_pending; @@ -355,6 +354,8 @@ struct mptcp_sock { list_for_each_entry(__subflow, &((__msk)->conn_list), node) #define mptcp_for_each_subflow_safe(__msk, __subflow, __tmp) \ list_for_each_entry_safe(__subflow, __tmp, &((__msk)->conn_list), node) +#define mptcp_next_subflow(__msk, __subflow) \ + list_next_entry_circular(__subflow, &((__msk)->conn_list), node) extern struct genl_family mptcp_genl_family; @@ -381,14 +382,6 @@ static inline void msk_owned_by_me(const struct mptcp_sock *msk) #define mptcp_sk(ptr) container_of_const(ptr, struct mptcp_sock, sk.icsk_inet.sk) #endif -/* the msk socket don't use the backlog, also account for the bulk - * free memory - */ -static inline int __mptcp_rmem(const struct sock *sk) -{ - return atomic_read(&sk->sk_rmem_alloc) - READ_ONCE(mptcp_sk(sk)->rmem_released); -} - static inline int mptcp_win_from_space(const struct sock *sk, int space) { return __tcp_win_from_space(mptcp_sk(sk)->scaling_ratio, space); @@ -401,7 +394,8 @@ static inline int mptcp_space_from_win(const struct sock *sk, int win) static inline int __mptcp_space(const struct sock *sk) { - return mptcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf) - __mptcp_rmem(sk)); + return mptcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf) - + sk_rmem_alloc_get(sk)); } static inline struct mptcp_data_frag *mptcp_send_head(const struct sock *sk) @@ -1059,8 +1053,6 @@ void mptcp_event_pm_listener(const struct sock *ssk, enum mptcp_event_type event); bool mptcp_userspace_pm_active(const struct mptcp_sock *msk); -void __mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow, - const struct mptcp_options_received *mp_opt); void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subflow, struct request_sock *req); int mptcp_nl_fill_addr(struct sk_buff *skb, diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index fd021cf8286e..d2caffa56bdd 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -802,9 +802,6 @@ void __mptcp_subflow_fully_established(struct mptcp_sock *msk, subflow_set_remote_key(msk, subflow, mp_opt); WRITE_ONCE(subflow->fully_established, true); WRITE_ONCE(msk->fully_established, true); - - if (subflow->is_mptfo) - __mptcp_fastopen_gen_msk_ackseq(msk, subflow, mp_opt); } static struct sock *subflow_syn_recv_sock(const struct sock *sk, @@ -1271,7 +1268,12 @@ out: subflow->map_valid = 0; } -/* sched mptcp worker to remove the subflow if no more data is pending */ +static bool subflow_is_done(const struct sock *sk) +{ + return sk->sk_shutdown & RCV_SHUTDOWN || sk->sk_state == TCP_CLOSE; +} + +/* sched mptcp worker for subflow cleanup if no more data is pending */ static void subflow_sched_work_if_closed(struct mptcp_sock *msk, struct sock *ssk) { struct sock *sk = (struct sock *)msk; @@ -1281,8 +1283,18 @@ static void subflow_sched_work_if_closed(struct mptcp_sock *msk, struct sock *ss inet_sk_state_load(sk) != TCP_ESTABLISHED))) return; - if (skb_queue_empty(&ssk->sk_receive_queue) && - !test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) + if (!skb_queue_empty(&ssk->sk_receive_queue)) + return; + + if (!test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) + mptcp_schedule_work(sk); + + /* when the fallback subflow closes the rx side, trigger a 'dummy' + * ingress data fin, so that the msk state will follow along + */ + if (__mptcp_check_fallback(msk) && subflow_is_done(ssk) && + msk->first == ssk && + mptcp_update_rcv_data_fin(msk, READ_ONCE(msk->ack_seq), true)) mptcp_schedule_work(sk); } @@ -1842,11 +1854,6 @@ static void __subflow_state_change(struct sock *sk) rcu_read_unlock(); } -static bool subflow_is_done(const struct sock *sk) -{ - return sk->sk_shutdown & RCV_SHUTDOWN || sk->sk_state == TCP_CLOSE; -} - static void subflow_state_change(struct sock *sk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); @@ -1873,13 +1880,6 @@ static void subflow_state_change(struct sock *sk) subflow_error_report(sk); subflow_sched_work_if_closed(mptcp_sk(parent), sk); - - /* when the fallback subflow closes the rx side, trigger a 'dummy' - * ingress data fin, so that the msk state will follow along - */ - if (__mptcp_check_fallback(msk) && subflow_is_done(sk) && msk->first == sk && - mptcp_update_rcv_data_fin(msk, READ_ONCE(msk->ack_seq), true)) - mptcp_schedule_work(parent); } void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_ssk) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 85311226183a..f8f13058a46e 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -771,6 +771,7 @@ static int netlink_release(struct socket *sock) nlk->cb.done(&nlk->cb); module_put(nlk->cb.module); kfree_skb(nlk->cb.skb); + WRITE_ONCE(nlk->cb_running, false); } module_put(nlk->module); diff --git a/net/nfc/hci/llc.c b/net/nfc/hci/llc.c index ba91284f4086..e6cf4eb06b46 100644 --- a/net/nfc/hci/llc.c +++ b/net/nfc/hci/llc.c @@ -78,17 +78,6 @@ static struct nfc_llc_engine *nfc_llc_name_to_engine(const char *name) return NULL; } -void nfc_llc_unregister(const char *name) -{ - struct nfc_llc_engine *llc_engine; - - llc_engine = nfc_llc_name_to_engine(name); - if (llc_engine == NULL) - return; - - nfc_llc_del_engine(llc_engine); -} - struct nfc_llc *nfc_llc_allocate(const char *name, struct nfc_hci_dev *hdev, xmit_to_drv_t xmit_to_drv, rcv_to_hci_t rcv_to_hci, int tx_headroom, diff --git a/net/nfc/hci/llc.h b/net/nfc/hci/llc.h index d66271d211a5..09914608ec43 100644 --- a/net/nfc/hci/llc.h +++ b/net/nfc/hci/llc.h @@ -40,7 +40,6 @@ struct nfc_llc { void *nfc_llc_get_data(struct nfc_llc *llc); int nfc_llc_register(const char *name, const struct nfc_llc_ops *ops); -void nfc_llc_unregister(const char *name); int nfc_llc_nop_register(void); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index c131e5ceea37..3e9ddf72cd03 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2102,8 +2102,8 @@ retry: skb->protocol = proto; skb->dev = dev; - skb->priority = READ_ONCE(sk->sk_priority); - skb->mark = READ_ONCE(sk->sk_mark); + skb->priority = sockc.priority; + skb->mark = sockc.mark; skb_set_delivery_type_by_clockid(skb, sockc.transmit_time, sk->sk_clockid); skb_setup_tx_timestamp(skb, &sockc); @@ -2634,8 +2634,8 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, skb->protocol = proto; skb->dev = dev; - skb->priority = READ_ONCE(po->sk.sk_priority); - skb->mark = READ_ONCE(po->sk.sk_mark); + skb->priority = sockc->priority; + skb->mark = sockc->mark; skb_set_delivery_type_by_clockid(skb, sockc->transmit_time, po->sk.sk_clockid); skb_setup_tx_timestamp(skb, sockc); skb_zcopy_set_nouarg(skb, ph.raw); @@ -3039,7 +3039,6 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) goto out_unlock; sockcm_init(&sockc, sk); - sockc.mark = READ_ONCE(sk->sk_mark); if (msg->msg_controllen) { err = sock_cmsg_send(sk, msg, &sockc); if (unlikely(err)) diff --git a/net/rds/stats.c b/net/rds/stats.c index 9e87da43c004..cb2e3d2cdf73 100644 --- a/net/rds/stats.c +++ b/net/rds/stats.c @@ -89,8 +89,7 @@ void rds_stats_info_copy(struct rds_info_iterator *iter, for (i = 0; i < nr; i++) { BUG_ON(strlen(names[i]) >= sizeof(ctr.name)); - strncpy(ctr.name, names[i], sizeof(ctr.name) - 1); - ctr.name[sizeof(ctr.name) - 1] = '\0'; + strscpy_pad(ctr.name, names[i]); ctr.value = values[i]; rds_info_copy(iter, &ctr, sizeof(ctr)); diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index af7c99845948..ae5dea7c48a8 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -571,8 +571,8 @@ static void tunnel_key_release(struct tc_action *a) static int tunnel_key_geneve_opts_dump(struct sk_buff *skb, const struct ip_tunnel_info *info) { + const u8 *src = ip_tunnel_info_opts(info); int len = info->options_len; - u8 *src = (u8 *)(info + 1); struct nlattr *start; start = nla_nest_start_noflag(skb, TCA_TUNNEL_KEY_ENC_OPTS_GENEVE); @@ -580,7 +580,7 @@ static int tunnel_key_geneve_opts_dump(struct sk_buff *skb, return -EMSGSIZE; while (len > 0) { - struct geneve_opt *opt = (struct geneve_opt *)src; + const struct geneve_opt *opt = (const struct geneve_opt *)src; if (nla_put_be16(skb, TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS, opt->opt_class) || @@ -603,7 +603,7 @@ static int tunnel_key_geneve_opts_dump(struct sk_buff *skb, static int tunnel_key_vxlan_opts_dump(struct sk_buff *skb, const struct ip_tunnel_info *info) { - struct vxlan_metadata *md = (struct vxlan_metadata *)(info + 1); + const struct vxlan_metadata *md = ip_tunnel_info_opts(info); struct nlattr *start; start = nla_nest_start_noflag(skb, TCA_TUNNEL_KEY_ENC_OPTS_VXLAN); @@ -622,7 +622,7 @@ static int tunnel_key_vxlan_opts_dump(struct sk_buff *skb, static int tunnel_key_erspan_opts_dump(struct sk_buff *skb, const struct ip_tunnel_info *info) { - struct erspan_metadata *md = (struct erspan_metadata *)(info + 1); + const struct erspan_metadata *md = ip_tunnel_info_opts(info); struct nlattr *start; start = nla_nest_start_noflag(skb, TCA_TUNNEL_KEY_ENC_OPTS_ERSPAN); diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 8e47e5355be6..4f648af8cfaa 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -97,7 +97,7 @@ tcf_exts_miss_cookie_base_alloc(struct tcf_exts *exts, struct tcf_proto *tp, err = xa_alloc_cyclic(&tcf_exts_miss_cookies_xa, &n->miss_cookie_base, n, xa_limit_32b, &next, GFP_KERNEL); - if (err) + if (err < 0) goto err_xa_alloc; exts->miss_cookie_node = n; diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c index 8996c73c9779..3f2e707a11d1 100644 --- a/net/sched/em_meta.c +++ b/net/sched/em_meta.c @@ -460,7 +460,7 @@ META_COLLECTOR(int_sk_fwd_alloc) *err = -1; return; } - dst->value = sk_forward_alloc_get(sk); + dst->value = READ_ONCE(sk->sk_forward_alloc); } META_COLLECTOR(int_sk_sndbuf) diff --git a/net/sctp/stream.c b/net/sctp/stream.c index c241cc552e8d..bfcff6d6a438 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -735,7 +735,7 @@ struct sctp_chunk *sctp_process_strreset_tsnreq( * value SHOULD be the smallest TSN not acknowledged by the * receiver of the request plus 2^31. */ - init_tsn = sctp_tsnmap_get_ctsn(&asoc->peer.tsn_map) + (1 << 31); + init_tsn = sctp_tsnmap_get_ctsn(&asoc->peer.tsn_map) + (1U << 31); sctp_tsnmap_init(&asoc->peer.tsn_map, SCTP_TSN_MAP_INITIAL, init_tsn, GFP_ATOMIC); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 34945de1fb1f..319153850be1 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1508,7 +1508,6 @@ out: } static long unix_wait_for_peer(struct sock *other, long timeo) - __releases(&unix_sk(other)->lock) { struct unix_sock *u = unix_sk(other); int sched; diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 53a081d49d28..7e3db87ae433 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1189,6 +1189,9 @@ static int vsock_read_skb(struct sock *sk, skb_read_actor_t read_actor) { struct vsock_sock *vsk = vsock_sk(sk); + if (WARN_ON_ONCE(!vsk->transport)) + return -ENODEV; + return vsk->transport->read_skb(vsk, read_actor); } diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index b58c3818f284..f0e48e6911fc 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -670,6 +670,13 @@ static int virtio_vsock_vqs_init(struct virtio_vsock *vsock) }; int ret; + mutex_lock(&vsock->rx_lock); + vsock->rx_buf_nr = 0; + vsock->rx_buf_max_nr = 0; + mutex_unlock(&vsock->rx_lock); + + atomic_set(&vsock->queued_replies, 0); + ret = virtio_find_vqs(vdev, VSOCK_VQ_MAX, vsock->vqs, vqs_info, NULL); if (ret < 0) return ret; @@ -779,9 +786,6 @@ static int virtio_vsock_probe(struct virtio_device *vdev) vsock->vdev = vdev; - vsock->rx_buf_nr = 0; - vsock->rx_buf_max_nr = 0; - atomic_set(&vsock->queued_replies, 0); mutex_init(&vsock->tx_lock); mutex_init(&vsock->rx_lock); diff --git a/net/vmw_vsock/vsock_bpf.c b/net/vmw_vsock/vsock_bpf.c index f201d9eca1df..07b96d56f3a5 100644 --- a/net/vmw_vsock/vsock_bpf.c +++ b/net/vmw_vsock/vsock_bpf.c @@ -87,7 +87,7 @@ static int vsock_bpf_recvmsg(struct sock *sk, struct msghdr *msg, lock_sock(sk); vsk = vsock_sk(sk); - if (!vsk->transport) { + if (WARN_ON_ONCE(!vsk->transport)) { copied = -ENODEV; goto out; } diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 41093ea63700..84bf9f1d4bf2 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -878,7 +878,7 @@ static bool xsk_no_wakeup(struct sock *sk) #ifdef CONFIG_NET_RX_BUSY_POLL /* Prefer busy-polling, skip the wakeup. */ return READ_ONCE(sk->sk_prefer_busy_poll) && READ_ONCE(sk->sk_ll_usec) && - READ_ONCE(sk->sk_napi_id) >= MIN_NAPI_ID; + napi_id_valid(READ_ONCE(sk->sk_napi_id)); #else return false; #endif diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c index c397eb99d867..622445f041d3 100644 --- a/net/xfrm/xfrm_interface_core.c +++ b/net/xfrm/xfrm_interface_core.c @@ -242,10 +242,9 @@ static void xfrmi_dev_free(struct net_device *dev) gro_cells_destroy(&xi->gro_cells); } -static int xfrmi_create(struct net_device *dev) +static int xfrmi_create(struct net *net, struct net_device *dev) { struct xfrm_if *xi = netdev_priv(dev); - struct net *net = dev_net(dev); struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id); int err; @@ -814,15 +813,17 @@ static void xfrmi_netlink_parms(struct nlattr *data[], parms->collect_md = true; } -static int xfrmi_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], - struct netlink_ext_ack *extack) +static int xfrmi_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, + struct netlink_ext_ack *extack) { - struct net *net = dev_net(dev); + struct nlattr **data = params->data; struct xfrm_if_parms p = {}; struct xfrm_if *xi; + struct net *net; int err; + net = params->link_net ? : dev_net(dev); xfrmi_netlink_parms(data, &p); if (p.collect_md) { struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id); @@ -851,7 +852,7 @@ static int xfrmi_newlink(struct net *src_net, struct net_device *dev, xi->net = net; xi->dev = dev; - err = xfrmi_create(dev); + err = xfrmi_create(net, dev); return err; } diff --git a/rust/bindings/bindings_helper.h b/rust/bindings/bindings_helper.h index 55354e4dec14..f46cf3bb7069 100644 --- a/rust/bindings/bindings_helper.h +++ b/rust/bindings/bindings_helper.h @@ -11,6 +11,7 @@ #include <linux/blk_types.h> #include <linux/blkdev.h> #include <linux/cred.h> +#include <linux/device/faux.h> #include <linux/errname.h> #include <linux/ethtool.h> #include <linux/file.h> diff --git a/rust/kernel/faux.rs b/rust/kernel/faux.rs new file mode 100644 index 000000000000..5acc0c02d451 --- /dev/null +++ b/rust/kernel/faux.rs @@ -0,0 +1,67 @@ +// SPDX-License-Identifier: GPL-2.0-only + +//! Abstractions for the faux bus. +//! +//! This module provides bindings for working with faux devices in kernel modules. +//! +//! C header: [`include/linux/device/faux.h`] + +use crate::{bindings, device, error::code::*, prelude::*}; +use core::ptr::{addr_of_mut, null, null_mut, NonNull}; + +/// The registration of a faux device. +/// +/// This type represents the registration of a [`struct faux_device`]. When an instance of this type +/// is dropped, its respective faux device will be unregistered from the system. +/// +/// # Invariants +/// +/// `self.0` always holds a valid pointer to an initialized and registered [`struct faux_device`]. +/// +/// [`struct faux_device`]: srctree/include/linux/device/faux.h +#[repr(transparent)] +pub struct Registration(NonNull<bindings::faux_device>); + +impl Registration { + /// Create and register a new faux device with the given name. + pub fn new(name: &CStr) -> Result<Self> { + // SAFETY: + // - `name` is copied by this function into its own storage + // - `faux_ops` is safe to leave NULL according to the C API + let dev = unsafe { bindings::faux_device_create(name.as_char_ptr(), null_mut(), null()) }; + + // The above function will return either a valid device, or NULL on failure + // INVARIANT: The device will remain registered until faux_device_destroy() is called, which + // happens in our Drop implementation. + Ok(Self(NonNull::new(dev).ok_or(ENODEV)?)) + } + + fn as_raw(&self) -> *mut bindings::faux_device { + self.0.as_ptr() + } +} + +impl AsRef<device::Device> for Registration { + fn as_ref(&self) -> &device::Device { + // SAFETY: The underlying `device` in `faux_device` is guaranteed by the C API to be + // a valid initialized `device`. + unsafe { device::Device::as_ref(addr_of_mut!((*self.as_raw()).dev)) } + } +} + +impl Drop for Registration { + fn drop(&mut self) { + // SAFETY: `self.0` is a valid registered faux_device via our type invariants. + unsafe { bindings::faux_device_destroy(self.as_raw()) } + } +} + +// SAFETY: The faux device API is thread-safe as guaranteed by the device core, as long as +// faux_device_destroy() is guaranteed to only be called once - which is guaranteed by our type not +// having Copy/Clone. +unsafe impl Send for Registration {} + +// SAFETY: The faux device API is thread-safe as guaranteed by the device core, as long as +// faux_device_destroy() is guaranteed to only be called once - which is guaranteed by our type not +// having Copy/Clone. +unsafe impl Sync for Registration {} diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs index 496ed32b0911..398242f92a96 100644 --- a/rust/kernel/lib.rs +++ b/rust/kernel/lib.rs @@ -46,6 +46,7 @@ pub mod device_id; pub mod devres; pub mod driver; pub mod error; +pub mod faux; #[cfg(CONFIG_RUST_FW_LOADER_ABSTRACTIONS)] pub mod firmware; pub mod fs; diff --git a/rust/kernel/rbtree.rs b/rust/kernel/rbtree.rs index ee2731dad72d..0d1e75810664 100644 --- a/rust/kernel/rbtree.rs +++ b/rust/kernel/rbtree.rs @@ -1149,7 +1149,7 @@ pub struct VacantEntry<'a, K, V> { /// # Invariants /// - `parent` may be null if the new node becomes the root. /// - `child_field_of_parent` is a valid pointer to the left-child or right-child of `parent`. If `parent` is -/// null, it is a pointer to the root of the [`RBTree`]. +/// null, it is a pointer to the root of the [`RBTree`]. struct RawVacantEntry<'a, K, V> { rbtree: *mut RBTree<K, V>, /// The node that will become the parent of the new node if we insert one. diff --git a/samples/rust/Kconfig b/samples/rust/Kconfig index 918dbead2c0b..3b6eae84b297 100644 --- a/samples/rust/Kconfig +++ b/samples/rust/Kconfig @@ -61,6 +61,16 @@ config SAMPLE_RUST_DRIVER_PLATFORM If unsure, say N. +config SAMPLE_RUST_DRIVER_FAUX + tristate "Faux Driver" + help + This option builds the Rust Faux driver sample. + + To compile this as a module, choose M here: + the module will be called rust_driver_faux. + + If unsure, say N. + config SAMPLE_RUST_HOSTPROGS bool "Host programs" help diff --git a/samples/rust/Makefile b/samples/rust/Makefile index 5a8ab0df0567..0dbc6d90f1ef 100644 --- a/samples/rust/Makefile +++ b/samples/rust/Makefile @@ -6,6 +6,7 @@ obj-$(CONFIG_SAMPLE_RUST_MISC_DEVICE) += rust_misc_device.o obj-$(CONFIG_SAMPLE_RUST_PRINT) += rust_print.o obj-$(CONFIG_SAMPLE_RUST_DRIVER_PCI) += rust_driver_pci.o obj-$(CONFIG_SAMPLE_RUST_DRIVER_PLATFORM) += rust_driver_platform.o +obj-$(CONFIG_SAMPLE_RUST_DRIVER_FAUX) += rust_driver_faux.o rust_print-y := rust_print_main.o rust_print_events.o diff --git a/samples/rust/rust_driver_faux.rs b/samples/rust/rust_driver_faux.rs new file mode 100644 index 000000000000..048c6cb98b29 --- /dev/null +++ b/samples/rust/rust_driver_faux.rs @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: GPL-2.0-only + +//! Rust faux device sample. + +use kernel::{c_str, faux, prelude::*, Module}; + +module! { + type: SampleModule, + name: "rust_faux_driver", + author: "Lyude Paul", + description: "Rust faux device sample", + license: "GPL", +} + +struct SampleModule { + _reg: faux::Registration, +} + +impl Module for SampleModule { + fn init(_module: &'static ThisModule) -> Result<Self> { + pr_info!("Initialising Rust Faux Device Sample\n"); + + let reg = faux::Registration::new(c_str!("rust-faux-sample-device"))?; + + dev_info!(reg.as_ref(), "Hello from faux device!\n"); + + Ok(Self { _reg: reg }) + } +} diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 36b28987a2f0..c35d22607978 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -190,8 +190,8 @@ static struct module *new_module(const char *name, size_t namelen) /* * Set mod->is_gpl_compatible to true by default. If MODULE_LICENSE() - * is missing, do not check the use for EXPORT_SYMBOL_GPL() becasue - * modpost will exit wiht error anyway. + * is missing, do not check the use for EXPORT_SYMBOL_GPL() because + * modpost will exit with an error anyway. */ mod->is_gpl_compatible = true; diff --git a/scripts/package/install-extmod-build b/scripts/package/install-extmod-build index b724626ea0ca..2966473b4660 100755 --- a/scripts/package/install-extmod-build +++ b/scripts/package/install-extmod-build @@ -62,8 +62,8 @@ if [ "${CC}" != "${HOSTCC}" ]; then # # Clear VPATH and srcroot because the source files reside in the output # directory. - # shellcheck disable=SC2016 # $(MAKE), $(CC), and $(build) will be expanded by Make - "${MAKE}" run-command KBUILD_RUN_COMMAND='+$(MAKE) HOSTCC="$(CC)" VPATH= srcroot=. $(build)='"${destdir}"/scripts + # shellcheck disable=SC2016 # $(MAKE) and $(build) will be expanded by Make + "${MAKE}" run-command KBUILD_RUN_COMMAND='+$(MAKE) HOSTCC='"${CC}"' VPATH= srcroot=. $(build)='"${destdir}"/scripts rm -f "${destdir}/scripts/Kbuild" fi diff --git a/sound/core/hrtimer.c b/sound/core/hrtimer.c index 147c1fea4708..e9c60dce59fb 100644 --- a/sound/core/hrtimer.c +++ b/sound/core/hrtimer.c @@ -66,9 +66,8 @@ static int snd_hrtimer_open(struct snd_timer *t) stime = kzalloc(sizeof(*stime), GFP_KERNEL); if (!stime) return -ENOMEM; - hrtimer_init(&stime->hrt, CLOCK_MONOTONIC, HRTIMER_MODE_REL); stime->timer = t; - stime->hrt.function = snd_hrtimer_callback; + hrtimer_setup(&stime->hrt, snd_hrtimer_callback, CLOCK_MONOTONIC, HRTIMER_MODE_REL); t->private_data = stime; return 0; } diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c index 073b56dc2225..cb66ec42a3f8 100644 --- a/sound/core/seq/seq_clientmgr.c +++ b/sound/core/seq/seq_clientmgr.c @@ -678,12 +678,18 @@ static int snd_seq_deliver_single_event(struct snd_seq_client *client, dest_port->time_real); #if IS_ENABLED(CONFIG_SND_SEQ_UMP) - if (!(dest->filter & SNDRV_SEQ_FILTER_NO_CONVERT)) { - if (snd_seq_ev_is_ump(event)) { + if (snd_seq_ev_is_ump(event)) { + if (!(dest->filter & SNDRV_SEQ_FILTER_NO_CONVERT)) { result = snd_seq_deliver_from_ump(client, dest, dest_port, event, atomic, hop); goto __skip; - } else if (snd_seq_client_is_ump(dest)) { + } else if (dest->type == USER_CLIENT && + !snd_seq_client_is_ump(dest)) { + result = 0; // drop the event + goto __skip; + } + } else if (snd_seq_client_is_ump(dest)) { + if (!(dest->filter & SNDRV_SEQ_FILTER_NO_CONVERT)) { result = snd_seq_deliver_to_ump(client, dest, dest_port, event, atomic, hop); goto __skip; diff --git a/sound/drivers/dummy.c b/sound/drivers/dummy.c index 8f5df9b3aaaa..c1a3efb633c5 100644 --- a/sound/drivers/dummy.c +++ b/sound/drivers/dummy.c @@ -457,8 +457,7 @@ static int dummy_hrtimer_create(struct snd_pcm_substream *substream) if (!dpcm) return -ENOMEM; substream->runtime->private_data = dpcm; - hrtimer_init(&dpcm->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); - dpcm->timer.function = dummy_hrtimer_callback; + hrtimer_setup(&dpcm->timer, dummy_hrtimer_callback, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); dpcm->substream = substream; atomic_set(&dpcm->running, 0); return 0; diff --git a/sound/drivers/pcsp/pcsp.c b/sound/drivers/pcsp/pcsp.c index 78c9b1c7590f..e8482c2290c3 100644 --- a/sound/drivers/pcsp/pcsp.c +++ b/sound/drivers/pcsp/pcsp.c @@ -103,8 +103,7 @@ static int snd_card_pcsp_probe(int devnum, struct device *dev) if (devnum != 0) return -EINVAL; - hrtimer_init(&pcsp_chip.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); - pcsp_chip.timer.function = pcsp_do_timer; + hrtimer_setup(&pcsp_chip.timer, pcsp_do_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); err = snd_devm_card_new(dev, index, id, THIS_MODULE, 0, &card); if (err < 0) diff --git a/sound/hda/intel-dsp-config.c b/sound/hda/intel-dsp-config.c index f564ec7af194..ce3ae2cba660 100644 --- a/sound/hda/intel-dsp-config.c +++ b/sound/hda/intel-dsp-config.c @@ -539,6 +539,11 @@ static const struct config_entry config_table[] = { .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, .device = PCI_DEVICE_ID_INTEL_HDA_PTL, }, + { + .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, + .device = PCI_DEVICE_ID_INTEL_HDA_PTL_H, + }, + #endif }; diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c index 14763c0f31ad..46a220404999 100644 --- a/sound/pci/hda/hda_codec.c +++ b/sound/pci/hda/hda_codec.c @@ -2470,7 +2470,9 @@ int snd_hda_create_dig_out_ctls(struct hda_codec *codec, break; id = kctl->id; id.index = spdif_index; - snd_ctl_rename_id(codec->card, &kctl->id, &id); + err = snd_ctl_rename_id(codec->card, &kctl->id, &id); + if (err < 0) + return err; } bus->primary_dig_out_type = HDA_PCM_TYPE_HDMI; } diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 7d7f9aac50a9..67540e037309 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2496,6 +2496,8 @@ static const struct pci_device_id azx_ids[] = { { PCI_DEVICE_DATA(INTEL, HDA_ARL, AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE) }, /* Panther Lake */ { PCI_DEVICE_DATA(INTEL, HDA_PTL, AZX_DRIVER_SKL | AZX_DCAPS_INTEL_LNL) }, + /* Panther Lake-H */ + { PCI_DEVICE_DATA(INTEL, HDA_PTL_H, AZX_DRIVER_SKL | AZX_DCAPS_INTEL_LNL) }, /* Apollolake (Broxton-P) */ { PCI_DEVICE_DATA(INTEL, HDA_APL, AZX_DRIVER_SKL | AZX_DCAPS_INTEL_BROXTON) }, /* Gemini-Lake */ diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index 4985e72b9094..34874039ad45 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -1090,6 +1090,7 @@ static const struct hda_quirk cxt5066_fixups[] = { SND_PCI_QUIRK(0x103c, 0x814f, "HP ZBook 15u G3", CXT_FIXUP_MUTE_LED_GPIO), SND_PCI_QUIRK(0x103c, 0x8174, "HP Spectre x360", CXT_FIXUP_HP_SPECTRE), SND_PCI_QUIRK(0x103c, 0x822e, "HP ProBook 440 G4", CXT_FIXUP_MUTE_LED_GPIO), + SND_PCI_QUIRK(0x103c, 0x8231, "HP ProBook 450 G4", CXT_FIXUP_MUTE_LED_GPIO), SND_PCI_QUIRK(0x103c, 0x828c, "HP EliteBook 840 G4", CXT_FIXUP_HP_DOCK), SND_PCI_QUIRK(0x103c, 0x8299, "HP 800 G3 SFF", CXT_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x829a, "HP 800 G3 DM", CXT_FIXUP_HP_MIC_NO_PRESENCE), diff --git a/sound/pci/hda/patch_cs8409-tables.c b/sound/pci/hda/patch_cs8409-tables.c index 759f48038273..09240138e087 100644 --- a/sound/pci/hda/patch_cs8409-tables.c +++ b/sound/pci/hda/patch_cs8409-tables.c @@ -121,7 +121,7 @@ static const struct cs8409_i2c_param cs42l42_init_reg_seq[] = { { CS42L42_MIXER_CHA_VOL, 0x3F }, { CS42L42_MIXER_CHB_VOL, 0x3F }, { CS42L42_MIXER_ADC_VOL, 0x3f }, - { CS42L42_HP_CTL, 0x03 }, + { CS42L42_HP_CTL, 0x0D }, { CS42L42_MIC_DET_CTL1, 0xB6 }, { CS42L42_TIPSENSE_CTL, 0xC2 }, { CS42L42_HS_CLAMP_DISABLE, 0x01 }, @@ -131,7 +131,7 @@ static const struct cs8409_i2c_param cs42l42_init_reg_seq[] = { { CS42L42_RSENSE_CTL3, 0x00 }, { CS42L42_TSENSE_CTL, 0x80 }, { CS42L42_HS_BIAS_CTL, 0xC0 }, - { CS42L42_PWR_CTL1, 0x02 }, + { CS42L42_PWR_CTL1, 0x02, 10000 }, { CS42L42_ADC_OVFL_INT_MASK, 0xff }, { CS42L42_MIXER_INT_MASK, 0xff }, { CS42L42_SRC_INT_MASK, 0xff }, @@ -315,7 +315,7 @@ static const struct cs8409_i2c_param dolphin_c0_init_reg_seq[] = { { CS42L42_ASP_TX_SZ_EN, 0x01 }, { CS42L42_PWR_CTL1, 0x0A }, { CS42L42_PWR_CTL2, 0x84 }, - { CS42L42_HP_CTL, 0x03 }, + { CS42L42_HP_CTL, 0x0D }, { CS42L42_MIXER_CHA_VOL, 0x3F }, { CS42L42_MIXER_CHB_VOL, 0x3F }, { CS42L42_MIXER_ADC_VOL, 0x3f }, @@ -328,7 +328,7 @@ static const struct cs8409_i2c_param dolphin_c0_init_reg_seq[] = { { CS42L42_RSENSE_CTL3, 0x00 }, { CS42L42_TSENSE_CTL, 0x80 }, { CS42L42_HS_BIAS_CTL, 0xC0 }, - { CS42L42_PWR_CTL1, 0x02 }, + { CS42L42_PWR_CTL1, 0x02, 10000 }, { CS42L42_ADC_OVFL_INT_MASK, 0xff }, { CS42L42_MIXER_INT_MASK, 0xff }, { CS42L42_SRC_INT_MASK, 0xff }, @@ -371,7 +371,7 @@ static const struct cs8409_i2c_param dolphin_c1_init_reg_seq[] = { { CS42L42_ASP_TX_SZ_EN, 0x00 }, { CS42L42_PWR_CTL1, 0x0E }, { CS42L42_PWR_CTL2, 0x84 }, - { CS42L42_HP_CTL, 0x01 }, + { CS42L42_HP_CTL, 0x0D }, { CS42L42_MIXER_CHA_VOL, 0x3F }, { CS42L42_MIXER_CHB_VOL, 0x3F }, { CS42L42_MIXER_ADC_VOL, 0x3f }, @@ -384,7 +384,7 @@ static const struct cs8409_i2c_param dolphin_c1_init_reg_seq[] = { { CS42L42_RSENSE_CTL3, 0x00 }, { CS42L42_TSENSE_CTL, 0x80 }, { CS42L42_HS_BIAS_CTL, 0xC0 }, - { CS42L42_PWR_CTL1, 0x06 }, + { CS42L42_PWR_CTL1, 0x06, 10000 }, { CS42L42_ADC_OVFL_INT_MASK, 0xff }, { CS42L42_MIXER_INT_MASK, 0xff }, { CS42L42_SRC_INT_MASK, 0xff }, diff --git a/sound/pci/hda/patch_cs8409.c b/sound/pci/hda/patch_cs8409.c index 614327218634..e50006757a2c 100644 --- a/sound/pci/hda/patch_cs8409.c +++ b/sound/pci/hda/patch_cs8409.c @@ -346,6 +346,11 @@ static int cs8409_i2c_bulk_write(struct sub_codec *scodec, const struct cs8409_i if (cs8409_i2c_wait_complete(codec) < 0) goto error; + /* Certain use cases may require a delay + * after a write operation before proceeding. + */ + if (seq[i].delay) + fsleep(seq[i].delay); } mutex_unlock(&spec->i2c_mux); @@ -876,7 +881,7 @@ static void cs42l42_resume(struct sub_codec *cs42l42) { CS42L42_DET_INT_STATUS2, 0x00 }, { CS42L42_TSRS_PLUG_STATUS, 0x00 }, }; - int fsv_old, fsv_new; + unsigned int fsv; /* Bring CS42L42 out of Reset */ spec->gpio_data = snd_hda_codec_read(codec, CS8409_PIN_AFG, 0, AC_VERB_GET_GPIO_DATA, 0); @@ -888,18 +893,19 @@ static void cs42l42_resume(struct sub_codec *cs42l42) /* Initialize CS42L42 companion codec */ cs8409_i2c_bulk_write(cs42l42, cs42l42->init_seq, cs42l42->init_seq_num); - msleep(CS42L42_INIT_TIMEOUT_MS); /* Clear interrupts, by reading interrupt status registers */ cs8409_i2c_bulk_read(cs42l42, irq_regs, ARRAY_SIZE(irq_regs)); - fsv_old = cs8409_i2c_read(cs42l42, CS42L42_HP_CTL); - if (cs42l42->full_scale_vol == CS42L42_FULL_SCALE_VOL_0DB) - fsv_new = fsv_old & ~CS42L42_FULL_SCALE_VOL_MASK; - else - fsv_new = fsv_old & CS42L42_FULL_SCALE_VOL_MASK; - if (fsv_new != fsv_old) - cs8409_i2c_write(cs42l42, CS42L42_HP_CTL, fsv_new); + fsv = cs8409_i2c_read(cs42l42, CS42L42_HP_CTL); + if (cs42l42->full_scale_vol) { + // Set the full scale volume bit + fsv |= CS42L42_FULL_SCALE_VOL_MASK; + cs8409_i2c_write(cs42l42, CS42L42_HP_CTL, fsv); + } + // Unmute analog channels A and B + fsv = (fsv & ~CS42L42_ANA_MUTE_AB); + cs8409_i2c_write(cs42l42, CS42L42_HP_CTL, fsv); /* we have to explicitly allow unsol event handling even during the * resume phase so that the jack event is processed properly @@ -920,7 +926,7 @@ static void cs42l42_suspend(struct sub_codec *cs42l42) { CS42L42_MIXER_CHA_VOL, 0x3F }, { CS42L42_MIXER_ADC_VOL, 0x3F }, { CS42L42_MIXER_CHB_VOL, 0x3F }, - { CS42L42_HP_CTL, 0x0F }, + { CS42L42_HP_CTL, 0x0D }, { CS42L42_ASP_RX_DAI0_EN, 0x00 }, { CS42L42_ASP_CLK_CFG, 0x00 }, { CS42L42_PWR_CTL1, 0xFE }, diff --git a/sound/pci/hda/patch_cs8409.h b/sound/pci/hda/patch_cs8409.h index 5e48115caf09..e4bd2e12110b 100644 --- a/sound/pci/hda/patch_cs8409.h +++ b/sound/pci/hda/patch_cs8409.h @@ -229,10 +229,10 @@ enum cs8409_coefficient_index_registers { #define CS42L42_I2C_SLEEP_US (2000) #define CS42L42_PDN_TIMEOUT_US (250000) #define CS42L42_PDN_SLEEP_US (2000) -#define CS42L42_INIT_TIMEOUT_MS (45) +#define CS42L42_ANA_MUTE_AB (0x0C) #define CS42L42_FULL_SCALE_VOL_MASK (2) -#define CS42L42_FULL_SCALE_VOL_0DB (1) -#define CS42L42_FULL_SCALE_VOL_MINUS6DB (0) +#define CS42L42_FULL_SCALE_VOL_0DB (0) +#define CS42L42_FULL_SCALE_VOL_MINUS6DB (1) /* Dell BULLSEYE / WARLOCK / CYBORG Specific Definitions */ @@ -290,6 +290,7 @@ enum { struct cs8409_i2c_param { unsigned int addr; unsigned int value; + unsigned int delay; }; struct cs8409_cir_param { diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 8192be394d0d..224616fbec4f 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -3788,6 +3788,7 @@ static void alc225_init(struct hda_codec *codec) AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_UNMUTE); msleep(75); + alc_update_coef_idx(codec, 0x4a, 3 << 10, 0); alc_update_coefex_idx(codec, 0x57, 0x04, 0x0007, 0x4); /* Hight power */ } } @@ -11045,6 +11046,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { 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(0x2014, 0x800a, "Positivo ARN50", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), 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/pci/hda/tas2781_hda_spi.c b/sound/pci/hda/tas2781_hda_spi.c index a42fa990e7b9..04db80af53c0 100644 --- a/sound/pci/hda/tas2781_hda_spi.c +++ b/sound/pci/hda/tas2781_hda_spi.c @@ -912,7 +912,7 @@ static void tasdev_fw_ready(const struct firmware *fmw, void *context) struct tasdevice_priv *tas_priv = context; struct tas2781_hda *tas_hda = dev_get_drvdata(tas_priv->dev); struct hda_codec *codec = tas_priv->codec; - int i, j, ret; + int i, j, ret, val; pm_runtime_get_sync(tas_priv->dev); guard(mutex)(&tas_priv->codec_lock); @@ -981,13 +981,16 @@ static void tasdev_fw_ready(const struct firmware *fmw, void *context) /* Perform AMP reset before firmware download. */ tas_priv->rcabin.profile_cfg_id = TAS2781_PRE_POST_RESET_CFG; - tasdevice_spi_tuning_switch(tas_priv, 0); tas2781_spi_reset(tas_priv); tas_priv->rcabin.profile_cfg_id = 0; - tasdevice_spi_tuning_switch(tas_priv, 1); tas_priv->fw_state = TASDEVICE_DSP_FW_ALL_OK; - ret = tasdevice_spi_prmg_load(tas_priv, 0); + ret = tasdevice_spi_dev_read(tas_priv, TAS2781_REG_CLK_CONFIG, &val); + if (ret < 0) + goto out; + + if (val == TAS2781_REG_CLK_CONFIG_RESET) + ret = tasdevice_spi_prmg_load(tas_priv, 0); if (ret < 0) { dev_err(tas_priv->dev, "FW download failed = %d\n", ret); goto out; @@ -1001,7 +1004,6 @@ static void tasdev_fw_ready(const struct firmware *fmw, void *context) * If calibrated data occurs error, dsp will still works with default * calibrated data inside algo. */ - tas_priv->save_calibration(tas_priv); out: if (fmw) @@ -1160,7 +1162,8 @@ static int tas2781_runtime_suspend(struct device *dev) guard(mutex)(&tas_hda->priv->codec_lock); - tasdevice_spi_tuning_switch(tas_hda->priv, 1); + if (tas_hda->priv->playback_started) + tasdevice_spi_tuning_switch(tas_hda->priv, 1); tas_hda->priv->cur_book = -1; tas_hda->priv->cur_conf = -1; @@ -1174,7 +1177,8 @@ static int tas2781_runtime_resume(struct device *dev) guard(mutex)(&tas_hda->priv->codec_lock); - tasdevice_spi_tuning_switch(tas_hda->priv, 0); + if (tas_hda->priv->playback_started) + tasdevice_spi_tuning_switch(tas_hda->priv, 0); return 0; } @@ -1189,12 +1193,9 @@ static int tas2781_system_suspend(struct device *dev) return ret; /* Shutdown chip before system suspend */ - tasdevice_spi_tuning_switch(tas_hda->priv, 1); - tas2781_spi_reset(tas_hda->priv); - /* - * Reset GPIO may be shared, so cannot reset here. - * However beyond this point, amps may be powered down. - */ + if (tas_hda->priv->playback_started) + tasdevice_spi_tuning_switch(tas_hda->priv, 1); + return 0; } diff --git a/sound/pci/hda/tas2781_spi_fwlib.c b/sound/pci/hda/tas2781_spi_fwlib.c index 0e2acbc3c900..131d9a77d140 100644 --- a/sound/pci/hda/tas2781_spi_fwlib.c +++ b/sound/pci/hda/tas2781_spi_fwlib.c @@ -2,7 +2,7 @@ // // TAS2781 HDA SPI driver // -// Copyright 2024 Texas Instruments, Inc. +// Copyright 2024-2025 Texas Instruments, Inc. // // Author: Baojun Xu <baojun.xu@ti.com> @@ -771,19 +771,19 @@ static int tasdevice_process_block(void *context, unsigned char *data, switch (subblk_typ) { case TASDEVICE_CMD_SING_W: subblk_offset = tasdevice_single_byte_wr(tas_priv, - dev_idx & 0x4f, data, sublocksize); + dev_idx & 0x3f, data, sublocksize); break; case TASDEVICE_CMD_BURST: subblk_offset = tasdevice_burst_wr(tas_priv, - dev_idx & 0x4f, data, sublocksize); + dev_idx & 0x3f, data, sublocksize); break; case TASDEVICE_CMD_DELAY: subblk_offset = tasdevice_delay(tas_priv, - dev_idx & 0x4f, data, sublocksize); + dev_idx & 0x3f, data, sublocksize); break; case TASDEVICE_CMD_FIELD_W: subblk_offset = tasdevice_field_wr(tas_priv, - dev_idx & 0x4f, data, sublocksize); + dev_idx & 0x3f, data, sublocksize); break; default: subblk_offset = 2; diff --git a/sound/sh/sh_dac_audio.c b/sound/sh/sh_dac_audio.c index 3f5422145c5e..84a4b17a0cc2 100644 --- a/sound/sh/sh_dac_audio.c +++ b/sound/sh/sh_dac_audio.c @@ -312,8 +312,7 @@ static int snd_sh_dac_create(struct snd_card *card, chip->card = card; - hrtimer_init(&chip->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); - chip->hrtimer.function = sh_dac_audio_timer; + hrtimer_setup(&chip->hrtimer, sh_dac_audio_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); dac_audio_reset(chip); chip->rate = 8000; diff --git a/sound/soc/codecs/arizona.c b/sound/soc/codecs/arizona.c index 402b9a2ff024..68cdb1027d0c 100644 --- a/sound/soc/codecs/arizona.c +++ b/sound/soc/codecs/arizona.c @@ -967,7 +967,7 @@ int arizona_out_ev(struct snd_soc_dapm_widget *w, case ARIZONA_OUT3L_ENA_SHIFT: case ARIZONA_OUT3R_ENA_SHIFT: priv->out_up_pending++; - priv->out_up_delay += 17; + priv->out_up_delay += 17000; break; case ARIZONA_OUT4L_ENA_SHIFT: case ARIZONA_OUT4R_ENA_SHIFT: @@ -977,7 +977,7 @@ int arizona_out_ev(struct snd_soc_dapm_widget *w, case WM8997: break; default: - priv->out_up_delay += 10; + priv->out_up_delay += 10000; break; } break; @@ -999,7 +999,7 @@ int arizona_out_ev(struct snd_soc_dapm_widget *w, if (!priv->out_up_pending && priv->out_up_delay) { dev_dbg(component->dev, "Power up delay: %d\n", priv->out_up_delay); - msleep(priv->out_up_delay); + fsleep(priv->out_up_delay); priv->out_up_delay = 0; } break; @@ -1017,7 +1017,7 @@ int arizona_out_ev(struct snd_soc_dapm_widget *w, case ARIZONA_OUT3L_ENA_SHIFT: case ARIZONA_OUT3R_ENA_SHIFT: priv->out_down_pending++; - priv->out_down_delay++; + priv->out_down_delay += 1000; break; case ARIZONA_OUT4L_ENA_SHIFT: case ARIZONA_OUT4R_ENA_SHIFT: @@ -1028,10 +1028,10 @@ int arizona_out_ev(struct snd_soc_dapm_widget *w, break; case WM8998: case WM1814: - priv->out_down_delay += 5; + priv->out_down_delay += 5000; break; default: - priv->out_down_delay++; + priv->out_down_delay += 1000; break; } break; @@ -1053,7 +1053,7 @@ int arizona_out_ev(struct snd_soc_dapm_widget *w, if (!priv->out_down_pending && priv->out_down_delay) { dev_dbg(component->dev, "Power down delay: %d\n", priv->out_down_delay); - msleep(priv->out_down_delay); + fsleep(priv->out_down_delay); priv->out_down_delay = 0; } break; diff --git a/sound/soc/codecs/cs35l41.c b/sound/soc/codecs/cs35l41.c index 07a5cab35fe1..ff4134bee858 100644 --- a/sound/soc/codecs/cs35l41.c +++ b/sound/soc/codecs/cs35l41.c @@ -1148,21 +1148,31 @@ err_dsp: return ret; } +#ifdef CONFIG_ACPI static int cs35l41_acpi_get_name(struct cs35l41_private *cs35l41) { - acpi_handle handle = ACPI_HANDLE(cs35l41->dev); + struct acpi_device *adev = ACPI_COMPANION(cs35l41->dev); + acpi_handle handle = acpi_device_handle(adev); + const char *hid; const char *sub; - /* If there is no ACPI_HANDLE, there is no ACPI for this system, return 0 */ - if (!handle) + /* If there is no acpi_device, there is no ACPI for this system, return 0 */ + if (!adev) return 0; sub = acpi_get_subsystem_id(handle); if (IS_ERR(sub)) { - /* If bad ACPI, return 0 and fallback to legacy firmware path, otherwise fail */ - if (PTR_ERR(sub) == -ENODATA) - return 0; - else + /* If no _SUB, fallback to _HID, otherwise fail */ + if (PTR_ERR(sub) == -ENODATA) { + hid = acpi_device_hid(adev); + /* If dummy hid, return 0 and fallback to legacy firmware path */ + if (!strcmp(hid, "device")) + return 0; + sub = kstrdup(hid, GFP_KERNEL); + if (!sub) + sub = ERR_PTR(-ENOMEM); + + } else return PTR_ERR(sub); } @@ -1171,6 +1181,12 @@ static int cs35l41_acpi_get_name(struct cs35l41_private *cs35l41) return 0; } +#else +static int cs35l41_acpi_get_name(struct cs35l41_private *cs35l41) +{ + return 0; +} +#endif /* CONFIG_ACPI */ int cs35l41_probe(struct cs35l41_private *cs35l41, const struct cs35l41_hw_cfg *hw_cfg) { diff --git a/sound/soc/codecs/madera.c b/sound/soc/codecs/madera.c index a840a2eb92b9..af109761f359 100644 --- a/sound/soc/codecs/madera.c +++ b/sound/soc/codecs/madera.c @@ -2323,10 +2323,10 @@ int madera_out_ev(struct snd_soc_dapm_widget *w, case CS42L92: case CS47L92: case CS47L93: - out_up_delay = 6; + out_up_delay = 6000; break; default: - out_up_delay = 17; + out_up_delay = 17000; break; } @@ -2357,7 +2357,7 @@ int madera_out_ev(struct snd_soc_dapm_widget *w, case MADERA_OUT3R_ENA_SHIFT: priv->out_up_pending--; if (!priv->out_up_pending) { - msleep(priv->out_up_delay); + fsleep(priv->out_up_delay); priv->out_up_delay = 0; } break; @@ -2376,7 +2376,7 @@ int madera_out_ev(struct snd_soc_dapm_widget *w, case MADERA_OUT3L_ENA_SHIFT: case MADERA_OUT3R_ENA_SHIFT: priv->out_down_pending++; - priv->out_down_delay++; + priv->out_down_delay += 1000; break; default: break; @@ -2393,7 +2393,7 @@ int madera_out_ev(struct snd_soc_dapm_widget *w, case MADERA_OUT3R_ENA_SHIFT: priv->out_down_pending--; if (!priv->out_down_pending) { - msleep(priv->out_down_delay); + fsleep(priv->out_down_delay); priv->out_down_delay = 0; } break; diff --git a/sound/soc/codecs/tas2781-i2c.c b/sound/soc/codecs/tas2781-i2c.c index a730ab6ad4e3..90c5b2e74d12 100644 --- a/sound/soc/codecs/tas2781-i2c.c +++ b/sound/soc/codecs/tas2781-i2c.c @@ -2,7 +2,7 @@ // // ALSA SoC Texas Instruments TAS2563/TAS2781 Audio Smart Amplifier // -// Copyright (C) 2022 - 2024 Texas Instruments Incorporated +// Copyright (C) 2022 - 2025 Texas Instruments Incorporated // https://www.ti.com // // The TAS2563/TAS2781 driver implements a flexible and configurable @@ -1260,8 +1260,6 @@ static int tasdevice_create_cali_ctrls(struct tasdevice_priv *priv) (cali_data->cali_dat_sz_per_dev + 1) + 1 + 15 + 1; priv->cali_data.total_sz = priv->ndev * (cali_data->cali_dat_sz_per_dev + 1); - priv->cali_data.data = devm_kzalloc(priv->dev, - ext_cali_data->max, GFP_KERNEL); cali_ctrls[i].name = cali_name; cali_ctrls[i].iface = SNDRV_CTL_ELEM_IFACE_MIXER; cali_ctrls[i].info = snd_soc_bytes_info_ext; diff --git a/sound/soc/codecs/wm5110.c b/sound/soc/codecs/wm5110.c index 502196253d42..64eee0d2347d 100644 --- a/sound/soc/codecs/wm5110.c +++ b/sound/soc/codecs/wm5110.c @@ -302,7 +302,7 @@ static int wm5110_hp_pre_enable(struct snd_soc_dapm_widget *w) } else { wseq = wm5110_no_dre_left_enable; nregs = ARRAY_SIZE(wm5110_no_dre_left_enable); - priv->out_up_delay += 10; + priv->out_up_delay += 10000; } break; case ARIZONA_OUT1R_ENA_SHIFT: @@ -312,7 +312,7 @@ static int wm5110_hp_pre_enable(struct snd_soc_dapm_widget *w) } else { wseq = wm5110_no_dre_right_enable; nregs = ARRAY_SIZE(wm5110_no_dre_right_enable); - priv->out_up_delay += 10; + priv->out_up_delay += 10000; } break; default: @@ -338,7 +338,7 @@ static int wm5110_hp_pre_disable(struct snd_soc_dapm_widget *w) snd_soc_component_update_bits(component, ARIZONA_SPARE_TRIGGERS, ARIZONA_WS_TRG1, 0); - priv->out_down_delay += 27; + priv->out_down_delay += 27000; } break; case ARIZONA_OUT1R_ENA_SHIFT: @@ -350,7 +350,7 @@ static int wm5110_hp_pre_disable(struct snd_soc_dapm_widget *w) snd_soc_component_update_bits(component, ARIZONA_SPARE_TRIGGERS, ARIZONA_WS_TRG2, 0); - priv->out_down_delay += 27; + priv->out_down_delay += 27000; } break; default: diff --git a/sound/soc/fsl/fsl_micfil.c b/sound/soc/fsl/fsl_micfil.c index 1075598a6647..fa4136683392 100644 --- a/sound/soc/fsl/fsl_micfil.c +++ b/sound/soc/fsl/fsl_micfil.c @@ -183,6 +183,8 @@ static int micfil_set_quality(struct fsl_micfil *micfil) case QUALITY_VLOW2: qsel = MICFIL_QSEL_VLOW2_QUALITY; break; + default: + return -EINVAL; } return regmap_update_bits(micfil->regmap, REG_MICFIL_CTRL2, diff --git a/sound/soc/fsl/imx-audmix.c b/sound/soc/fsl/imx-audmix.c index 231400661c90..50ecc5f51100 100644 --- a/sound/soc/fsl/imx-audmix.c +++ b/sound/soc/fsl/imx-audmix.c @@ -23,7 +23,6 @@ struct imx_audmix { struct snd_soc_card card; struct platform_device *audmix_pdev; struct platform_device *out_pdev; - struct clk *cpu_mclk; int num_dai; struct snd_soc_dai_link *dai; int num_dai_conf; @@ -32,34 +31,11 @@ struct imx_audmix { struct snd_soc_dapm_route *dapm_routes; }; -static const u32 imx_audmix_rates[] = { - 8000, 12000, 16000, 24000, 32000, 48000, 64000, 96000, -}; - -static const struct snd_pcm_hw_constraint_list imx_audmix_rate_constraints = { - .count = ARRAY_SIZE(imx_audmix_rates), - .list = imx_audmix_rates, -}; - static int imx_audmix_fe_startup(struct snd_pcm_substream *substream) { - struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream); - struct imx_audmix *priv = snd_soc_card_get_drvdata(rtd->card); struct snd_pcm_runtime *runtime = substream->runtime; - struct device *dev = rtd->card->dev; - unsigned long clk_rate = clk_get_rate(priv->cpu_mclk); int ret; - if (clk_rate % 24576000 == 0) { - ret = snd_pcm_hw_constraint_list(runtime, 0, - SNDRV_PCM_HW_PARAM_RATE, - &imx_audmix_rate_constraints); - if (ret < 0) - return ret; - } else { - dev_warn(dev, "mclk may be not supported %lu\n", clk_rate); - } - ret = snd_pcm_hw_constraint_minmax(runtime, SNDRV_PCM_HW_PARAM_CHANNELS, 1, 8); if (ret < 0) @@ -323,13 +299,6 @@ static int imx_audmix_probe(struct platform_device *pdev) } put_device(&cpu_pdev->dev); - priv->cpu_mclk = devm_clk_get(&cpu_pdev->dev, "mclk1"); - if (IS_ERR(priv->cpu_mclk)) { - ret = PTR_ERR(priv->cpu_mclk); - dev_err(&cpu_pdev->dev, "failed to get DAI mclk1: %d\n", ret); - return ret; - } - priv->audmix_pdev = audmix_pdev; priv->out_pdev = cpu_pdev; diff --git a/sound/soc/generic/simple-card-utils.c b/sound/soc/generic/simple-card-utils.c index dd414634b4ac..c2445c5ccd84 100644 --- a/sound/soc/generic/simple-card-utils.c +++ b/sound/soc/generic/simple-card-utils.c @@ -1092,6 +1092,7 @@ int graph_util_parse_dai(struct device *dev, struct device_node *ep, args.np = ep; dai = snd_soc_get_dai_via_args(&args); if (dai) { + dlc->of_node = node; dlc->dai_name = snd_soc_dai_name_get(dai); dlc->dai_args = snd_soc_copy_dai_args(dev, &args); if (!dlc->dai_args) diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c index b0d35fda7b17..203b07d4d833 100644 --- a/sound/soc/intel/boards/sof_sdw.c +++ b/sound/soc/intel/boards/sof_sdw.c @@ -13,6 +13,7 @@ #include <linux/soundwire/sdw.h> #include <linux/soundwire/sdw_type.h> #include <linux/soundwire/sdw_intel.h> +#include <sound/core.h> #include <sound/soc-acpi.h> #include "sof_sdw_common.h" #include "../../codecs/rt711.h" @@ -748,9 +749,36 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = { }, .driver_data = (void *)(SOC_SDW_PCH_DMIC), }, + { + .callback = sof_sdw_quirk_cb, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Google"), + DMI_MATCH(DMI_PRODUCT_NAME, "Fatcat"), + }, + .driver_data = (void *)(SOC_SDW_PCH_DMIC | + SOF_BT_OFFLOAD_SSP(2) | + SOF_SSP_BT_OFFLOAD_PRESENT), + }, + {} +}; + +static const struct snd_pci_quirk sof_sdw_ssid_quirk_table[] = { + SND_PCI_QUIRK(0x1043, 0x1e13, "ASUS Zenbook S14", SOC_SDW_CODEC_MIC), {} }; +static void sof_sdw_check_ssid_quirk(const struct snd_soc_acpi_mach *mach) +{ + const struct snd_pci_quirk *quirk_entry; + + quirk_entry = snd_pci_quirk_lookup_id(mach->mach_params.subsystem_vendor, + mach->mach_params.subsystem_device, + sof_sdw_ssid_quirk_table); + + if (quirk_entry) + sof_sdw_quirk = quirk_entry->value; +} + static struct snd_soc_dai_link_component platform_component[] = { { /* name might be overridden during probe */ @@ -1278,6 +1306,13 @@ static int mc_probe(struct platform_device *pdev) snd_soc_card_set_drvdata(card, ctx); + if (mach->mach_params.subsystem_id_set) { + snd_soc_card_set_pci_ssid(card, + mach->mach_params.subsystem_vendor, + mach->mach_params.subsystem_device); + sof_sdw_check_ssid_quirk(mach); + } + dmi_check_system(sof_sdw_quirk_table); if (quirk_override != -1) { @@ -1293,12 +1328,6 @@ static int mc_probe(struct platform_device *pdev) for (i = 0; i < ctx->codec_info_list_count; i++) codec_info_list[i].amp_num = 0; - if (mach->mach_params.subsystem_id_set) { - snd_soc_card_set_pci_ssid(card, - mach->mach_params.subsystem_vendor, - mach->mach_params.subsystem_device); - } - ret = sof_card_dai_links_create(card); if (ret < 0) return ret; diff --git a/sound/soc/intel/common/soc-acpi-intel-mtl-match.c b/sound/soc/intel/common/soc-acpi-intel-mtl-match.c index 770e2194a283..9e611e3667ad 100644 --- a/sound/soc/intel/common/soc-acpi-intel-mtl-match.c +++ b/sound/soc/intel/common/soc-acpi-intel-mtl-match.c @@ -330,7 +330,7 @@ static const struct snd_soc_acpi_adr_device rt1316_3_single_adr[] = { static const struct snd_soc_acpi_adr_device rt1318_1_single_adr[] = { { - .adr = 0x000130025D131801, + .adr = 0x000130025D131801ull, .num_endpoints = 1, .endpoints = &single_endpoint, .name_prefix = "rt1318-1" diff --git a/sound/soc/intel/common/soc-acpi-intel-ptl-match.c b/sound/soc/intel/common/soc-acpi-intel-ptl-match.c index 9eb4a43e3e7a..dd7993b76dee 100644 --- a/sound/soc/intel/common/soc-acpi-intel-ptl-match.c +++ b/sound/soc/intel/common/soc-acpi-intel-ptl-match.c @@ -251,7 +251,7 @@ static const struct snd_soc_acpi_link_adr ptl_rvp[] = { {} }; -static const struct snd_soc_acpi_link_adr lnl_sdw_rt713_vb_l2_rt1320_l13[] = { +static const struct snd_soc_acpi_link_adr ptl_sdw_rt713_vb_l2_rt1320_l13[] = { { .mask = BIT(2), .num_adr = ARRAY_SIZE(rt713_vb_2_adr), @@ -270,7 +270,7 @@ static const struct snd_soc_acpi_link_adr lnl_sdw_rt713_vb_l2_rt1320_l13[] = { {} }; -static const struct snd_soc_acpi_link_adr lnl_sdw_rt712_vb_l2_rt1320_l1[] = { +static const struct snd_soc_acpi_link_adr ptl_sdw_rt712_vb_l2_rt1320_l1[] = { { .mask = BIT(2), .num_adr = ARRAY_SIZE(rt712_vb_2_group1_adr), @@ -337,17 +337,17 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_ptl_sdw_machines[] = { }, { .link_mask = BIT(1) | BIT(2), - .links = lnl_sdw_rt712_vb_l2_rt1320_l1, + .links = ptl_sdw_rt712_vb_l2_rt1320_l1, .drv_name = "sof_sdw", .machine_check = snd_soc_acpi_intel_sdca_is_device_rt712_vb, - .sof_tplg_filename = "sof-lnl-rt712-l2-rt1320-l1.tplg" + .sof_tplg_filename = "sof-ptl-rt712-l2-rt1320-l1.tplg" }, { .link_mask = BIT(1) | BIT(2) | BIT(3), - .links = lnl_sdw_rt713_vb_l2_rt1320_l13, + .links = ptl_sdw_rt713_vb_l2_rt1320_l13, .drv_name = "sof_sdw", .machine_check = snd_soc_acpi_intel_sdca_is_device_rt712_vb, - .sof_tplg_filename = "sof-lnl-rt713-l2-rt1320-l13.tplg" + .sof_tplg_filename = "sof-ptl-rt713-l2-rt1320-l13.tplg" }, {}, }; diff --git a/sound/soc/intel/common/soc-acpi-intel-tgl-match.c b/sound/soc/intel/common/soc-acpi-intel-tgl-match.c index 6f8c06413665..b77aafb0bfb6 100644 --- a/sound/soc/intel/common/soc-acpi-intel-tgl-match.c +++ b/sound/soc/intel/common/soc-acpi-intel-tgl-match.c @@ -658,25 +658,25 @@ static const struct snd_soc_acpi_endpoint cs35l56_7_fb_endpoints[] = { static const struct snd_soc_acpi_adr_device cs35l56_sdw_eight_1_4_fb_adr[] = { { - .adr = 0x00003301fa355601, + .adr = 0x00003301fa355601ull, .num_endpoints = ARRAY_SIZE(cs35l56_l_fb_endpoints), .endpoints = cs35l56_l_fb_endpoints, .name_prefix = "AMP1" }, { - .adr = 0x00003201fa355601, + .adr = 0x00003201fa355601ull, .num_endpoints = ARRAY_SIZE(cs35l56_2_fb_endpoints), .endpoints = cs35l56_2_fb_endpoints, .name_prefix = "AMP2" }, { - .adr = 0x00003101fa355601, + .adr = 0x00003101fa355601ull, .num_endpoints = ARRAY_SIZE(cs35l56_4_fb_endpoints), .endpoints = cs35l56_4_fb_endpoints, .name_prefix = "AMP3" }, { - .adr = 0x00003001fa355601, + .adr = 0x00003001fa355601ull, .num_endpoints = ARRAY_SIZE(cs35l56_6_fb_endpoints), .endpoints = cs35l56_6_fb_endpoints, .name_prefix = "AMP4" @@ -685,25 +685,25 @@ static const struct snd_soc_acpi_adr_device cs35l56_sdw_eight_1_4_fb_adr[] = { static const struct snd_soc_acpi_adr_device cs35l56_sdw_eight_5_8_fb_adr[] = { { - .adr = 0x00013701fa355601, + .adr = 0x00013701fa355601ull, .num_endpoints = ARRAY_SIZE(cs35l56_r_fb_endpoints), .endpoints = cs35l56_r_fb_endpoints, .name_prefix = "AMP8" }, { - .adr = 0x00013601fa355601, + .adr = 0x00013601fa355601ull, .num_endpoints = ARRAY_SIZE(cs35l56_3_fb_endpoints), .endpoints = cs35l56_3_fb_endpoints, .name_prefix = "AMP7" }, { - .adr = 0x00013501fa355601, + .adr = 0x00013501fa355601ull, .num_endpoints = ARRAY_SIZE(cs35l56_5_fb_endpoints), .endpoints = cs35l56_5_fb_endpoints, .name_prefix = "AMP6" }, { - .adr = 0x00013401fa355601, + .adr = 0x00013401fa355601ull, .num_endpoints = ARRAY_SIZE(cs35l56_7_fb_endpoints), .endpoints = cs35l56_7_fb_endpoints, .name_prefix = "AMP5" diff --git a/sound/soc/renesas/rcar/core.c b/sound/soc/renesas/rcar/core.c index d3709fd0409e..f3f0c3f0bb9f 100644 --- a/sound/soc/renesas/rcar/core.c +++ b/sound/soc/renesas/rcar/core.c @@ -1770,20 +1770,6 @@ int rsnd_kctrl_accept_anytime(struct rsnd_dai_stream *io) return 1; } -int rsnd_kctrl_accept_runtime(struct rsnd_dai_stream *io) -{ - struct snd_pcm_runtime *runtime = rsnd_io_to_runtime(io); - struct rsnd_priv *priv = rsnd_io_to_priv(io); - struct device *dev = rsnd_priv_to_dev(priv); - - if (!runtime) { - dev_warn(dev, "Can't update kctrl when idle\n"); - return 0; - } - - return 1; -} - struct rsnd_kctrl_cfg *rsnd_kctrl_init_m(struct rsnd_kctrl_cfg_m *cfg) { cfg->cfg.val = cfg->val; diff --git a/sound/soc/renesas/rcar/rsnd.h b/sound/soc/renesas/rcar/rsnd.h index a5f54b65313c..04c70690f7a2 100644 --- a/sound/soc/renesas/rcar/rsnd.h +++ b/sound/soc/renesas/rcar/rsnd.h @@ -742,7 +742,6 @@ struct rsnd_kctrl_cfg_s { #define rsnd_kctrl_vals(x) ((x).val) /* = (x).cfg.val[0] */ int rsnd_kctrl_accept_anytime(struct rsnd_dai_stream *io); -int rsnd_kctrl_accept_runtime(struct rsnd_dai_stream *io); struct rsnd_kctrl_cfg *rsnd_kctrl_init_m(struct rsnd_kctrl_cfg_m *cfg); struct rsnd_kctrl_cfg *rsnd_kctrl_init_s(struct rsnd_kctrl_cfg_s *cfg); int rsnd_kctrl_new(struct rsnd_mod *mod, diff --git a/sound/soc/renesas/rcar/src.c b/sound/soc/renesas/rcar/src.c index e7f86db0d94c..7d73b183bda6 100644 --- a/sound/soc/renesas/rcar/src.c +++ b/sound/soc/renesas/rcar/src.c @@ -35,6 +35,7 @@ struct rsnd_src { struct rsnd_mod *dma; struct rsnd_kctrl_cfg_s sen; /* sync convert enable */ struct rsnd_kctrl_cfg_s sync; /* sync convert */ + u32 current_sync_rate; int irq; }; @@ -100,7 +101,7 @@ static u32 rsnd_src_convert_rate(struct rsnd_dai_stream *io, if (!rsnd_src_sync_is_enabled(mod)) return rsnd_io_converted_rate(io); - convert_rate = src->sync.val; + convert_rate = src->current_sync_rate; if (!convert_rate) convert_rate = rsnd_io_converted_rate(io); @@ -201,13 +202,73 @@ static const u32 chan222222[] = { static void rsnd_src_set_convert_rate(struct rsnd_dai_stream *io, struct rsnd_mod *mod) { + struct snd_pcm_runtime *runtime = rsnd_io_to_runtime(io); struct rsnd_priv *priv = rsnd_mod_to_priv(mod); - struct device *dev = rsnd_priv_to_dev(priv); + struct rsnd_src *src = rsnd_mod_to_src(mod); + u32 fin, fout, new_rate; + int inc, cnt, rate; + u64 base, val; + + if (!runtime) + return; + + if (!rsnd_src_sync_is_enabled(mod)) + return; + + fin = rsnd_src_get_in_rate(priv, io); + fout = rsnd_src_get_out_rate(priv, io); + + new_rate = src->sync.val; + + if (!new_rate) + new_rate = fout; + + /* Do nothing if no diff */ + if (new_rate == src->current_sync_rate) + return; + + /* + * SRCm_IFSVR::INTIFS can change within 1% + * see + * SRCm_IFSVR::INTIFS Note + */ + inc = fout / 100; + cnt = abs(new_rate - fout) / inc; + if (fout > new_rate) + inc *= -1; + + /* + * After start running SRC, we can update only SRC_IFSVR + * for Synchronous Mode + */ + base = (u64)0x0400000 * fin; + rate = fout; + for (int i = 0; i < cnt; i++) { + val = base; + rate += inc; + do_div(val, rate); + + rsnd_mod_write(mod, SRC_IFSVR, val); + } + val = base; + do_div(val, new_rate); + + rsnd_mod_write(mod, SRC_IFSVR, val); + + /* update current_sync_rate */ + src->current_sync_rate = new_rate; +} + +static void rsnd_src_init_convert_rate(struct rsnd_dai_stream *io, + struct rsnd_mod *mod) +{ struct snd_pcm_runtime *runtime = rsnd_io_to_runtime(io); + struct rsnd_priv *priv = rsnd_mod_to_priv(mod); + struct device *dev = rsnd_priv_to_dev(priv); int is_play = rsnd_io_is_play(io); int use_src = 0; u32 fin, fout; - u32 ifscr, fsrate, adinr; + u32 ifscr, adinr; u32 cr, route; u32 i_busif, o_busif, tmp; const u32 *bsdsr_table; @@ -245,26 +306,15 @@ static void rsnd_src_set_convert_rate(struct rsnd_dai_stream *io, adinr = rsnd_get_adinr_bit(mod, io) | chan; /* - * SRC_IFSCR / SRC_IFSVR - */ - ifscr = 0; - fsrate = 0; - if (use_src) { - u64 n; - - ifscr = 1; - n = (u64)0x0400000 * fin; - do_div(n, fout); - fsrate = n; - } - - /* + * SRC_IFSCR * SRC_SRCCR / SRC_ROUTE_MODE0 */ + ifscr = 0; cr = 0x00011110; route = 0x0; if (use_src) { route = 0x1; + ifscr = 0x1; if (rsnd_src_sync_is_enabled(mod)) { cr |= 0x1; @@ -335,7 +385,6 @@ static void rsnd_src_set_convert_rate(struct rsnd_dai_stream *io, rsnd_mod_write(mod, SRC_SRCIR, 1); /* initialize */ rsnd_mod_write(mod, SRC_ADINR, adinr); rsnd_mod_write(mod, SRC_IFSCR, ifscr); - rsnd_mod_write(mod, SRC_IFSVR, fsrate); rsnd_mod_write(mod, SRC_SRCCR, cr); rsnd_mod_write(mod, SRC_BSDSR, bsdsr_table[idx]); rsnd_mod_write(mod, SRC_BSISR, bsisr_table[idx]); @@ -348,6 +397,9 @@ static void rsnd_src_set_convert_rate(struct rsnd_dai_stream *io, rsnd_adg_set_src_timesel_gen2(mod, io, fin, fout); + /* update SRC_IFSVR */ + rsnd_src_set_convert_rate(io, mod); + return; convert_rate_err: @@ -467,7 +519,8 @@ static int rsnd_src_init(struct rsnd_mod *mod, int ret; /* reset sync convert_rate */ - src->sync.val = 0; + src->sync.val = + src->current_sync_rate = 0; ret = rsnd_mod_power_on(mod); if (ret < 0) @@ -475,7 +528,7 @@ static int rsnd_src_init(struct rsnd_mod *mod, rsnd_src_activation(mod); - rsnd_src_set_convert_rate(io, mod); + rsnd_src_init_convert_rate(io, mod); rsnd_src_status_clear(mod); @@ -493,7 +546,8 @@ static int rsnd_src_quit(struct rsnd_mod *mod, rsnd_mod_power_off(mod); /* reset sync convert_rate */ - src->sync.val = 0; + src->sync.val = + src->current_sync_rate = 0; return 0; } @@ -531,6 +585,22 @@ static irqreturn_t rsnd_src_interrupt(int irq, void *data) return IRQ_HANDLED; } +static int rsnd_src_kctrl_accept_runtime(struct rsnd_dai_stream *io) +{ + struct snd_pcm_runtime *runtime = rsnd_io_to_runtime(io); + + if (!runtime) { + struct rsnd_priv *priv = rsnd_io_to_priv(io); + struct device *dev = rsnd_priv_to_dev(priv); + + dev_warn(dev, "\"SRC Out Rate\" can use during running\n"); + + return 0; + } + + return 1; +} + static int rsnd_src_probe_(struct rsnd_mod *mod, struct rsnd_dai_stream *io, struct rsnd_priv *priv) @@ -585,7 +655,7 @@ static int rsnd_src_pcm_new(struct rsnd_mod *mod, "SRC Out Rate Switch" : "SRC In Rate Switch", rsnd_kctrl_accept_anytime, - rsnd_src_set_convert_rate, + rsnd_src_init_convert_rate, &src->sen, 1); if (ret < 0) return ret; @@ -594,7 +664,7 @@ static int rsnd_src_pcm_new(struct rsnd_mod *mod, rsnd_io_is_play(io) ? "SRC Out Rate" : "SRC In Rate", - rsnd_kctrl_accept_runtime, + rsnd_src_kctrl_accept_runtime, rsnd_src_set_convert_rate, &src->sync, 192000); diff --git a/sound/soc/renesas/rcar/ssi.c b/sound/soc/renesas/rcar/ssi.c index b3d4e8ae07ef..0c6424a1fcac 100644 --- a/sound/soc/renesas/rcar/ssi.c +++ b/sound/soc/renesas/rcar/ssi.c @@ -336,7 +336,8 @@ static int rsnd_ssi_master_clk_start(struct rsnd_mod *mod, return 0; rate_err: - dev_err(dev, "unsupported clock rate\n"); + dev_err(dev, "unsupported clock rate (%d)\n", rate); + return ret; } diff --git a/sound/soc/rockchip/rockchip_i2s_tdm.c b/sound/soc/rockchip/rockchip_i2s_tdm.c index 7f5fcaecee4b..78ab88843f86 100644 --- a/sound/soc/rockchip/rockchip_i2s_tdm.c +++ b/sound/soc/rockchip/rockchip_i2s_tdm.c @@ -451,11 +451,11 @@ static int rockchip_i2s_tdm_set_fmt(struct snd_soc_dai *cpu_dai, break; case SND_SOC_DAIFMT_DSP_A: val = I2S_TXCR_TFS_TDM_PCM; - tdm_val = TDM_SHIFT_CTRL(0); + tdm_val = TDM_SHIFT_CTRL(2); break; case SND_SOC_DAIFMT_DSP_B: val = I2S_TXCR_TFS_TDM_PCM; - tdm_val = TDM_SHIFT_CTRL(2); + tdm_val = TDM_SHIFT_CTRL(4); break; default: ret = -EINVAL; diff --git a/sound/soc/sof/amd/acp-ipc.c b/sound/soc/sof/amd/acp-ipc.c index 5f371d9263f3..22d4b807e1bb 100644 --- a/sound/soc/sof/amd/acp-ipc.c +++ b/sound/soc/sof/amd/acp-ipc.c @@ -165,8 +165,9 @@ irqreturn_t acp_sof_ipc_irq_thread(int irq, void *context) int dsp_msg, dsp_ack; unsigned int status; - if (sdev->first_boot && sdev->fw_state != SOF_FW_BOOT_COMPLETE) { + if (unlikely(sdev->first_boot && sdev->fw_state != SOF_FW_BOOT_COMPLETE)) { acp_mailbox_read(sdev, sdev->dsp_box.offset, &status, sizeof(status)); + if ((status & SOF_IPC_PANIC_MAGIC_MASK) == SOF_IPC_PANIC_MAGIC) { snd_sof_dsp_panic(sdev, sdev->dsp_box.offset + sizeof(status), true); @@ -188,13 +189,21 @@ irqreturn_t acp_sof_ipc_irq_thread(int irq, void *context) dsp_ack = snd_sof_dsp_read(sdev, ACP_DSP_BAR, ACP_SCRATCH_REG_0 + dsp_ack_write); if (dsp_ack) { - spin_lock_irq(&sdev->ipc_lock); - /* handle immediate reply from DSP core */ - acp_dsp_ipc_get_reply(sdev); - snd_sof_ipc_reply(sdev, 0); - /* set the done bit */ - acp_dsp_ipc_dsp_done(sdev); - spin_unlock_irq(&sdev->ipc_lock); + if (likely(sdev->fw_state == SOF_FW_BOOT_COMPLETE)) { + spin_lock_irq(&sdev->ipc_lock); + + /* handle immediate reply from DSP core */ + acp_dsp_ipc_get_reply(sdev); + snd_sof_ipc_reply(sdev, 0); + /* set the done bit */ + acp_dsp_ipc_dsp_done(sdev); + + spin_unlock_irq(&sdev->ipc_lock); + } else { + dev_dbg_ratelimited(sdev->dev, "IPC reply before FW_BOOT_COMPLETE: %#x\n", + dsp_ack); + } + ipc_irq = true; } diff --git a/sound/soc/sof/amd/acp.c b/sound/soc/sof/amd/acp.c index 33648ff8b833..9e13c96528be 100644 --- a/sound/soc/sof/amd/acp.c +++ b/sound/soc/sof/amd/acp.c @@ -27,6 +27,7 @@ MODULE_PARM_DESC(enable_fw_debug, "Enable Firmware debug"); static struct acp_quirk_entry quirk_valve_galileo = { .signed_fw_image = true, .skip_iram_dram_size_mod = true, + .post_fw_run_delay = true, }; const struct dmi_system_id acp_sof_quirk_table[] = { diff --git a/sound/soc/sof/amd/acp.h b/sound/soc/sof/amd/acp.h index 800594440f73..2a19d82d6200 100644 --- a/sound/soc/sof/amd/acp.h +++ b/sound/soc/sof/amd/acp.h @@ -220,6 +220,7 @@ struct sof_amd_acp_desc { struct acp_quirk_entry { bool signed_fw_image; bool skip_iram_dram_size_mod; + bool post_fw_run_delay; }; /* Common device data struct for ACP devices */ diff --git a/sound/soc/sof/amd/pci-vangogh.c b/sound/soc/sof/amd/pci-vangogh.c index 53f64d6bc91b..28f2d4050a67 100644 --- a/sound/soc/sof/amd/pci-vangogh.c +++ b/sound/soc/sof/amd/pci-vangogh.c @@ -13,11 +13,9 @@ #include <linux/module.h> #include <linux/pci.h> -#include <linux/platform_device.h> #include <sound/sof.h> #include <sound/soc-acpi.h> -#include "../ops.h" #include "../sof-pci-dev.h" #include "../../amd/mach-config.h" #include "acp.h" diff --git a/sound/soc/sof/amd/vangogh.c b/sound/soc/sof/amd/vangogh.c index 8e2672106ac6..6ed5f9aaa414 100644 --- a/sound/soc/sof/amd/vangogh.c +++ b/sound/soc/sof/amd/vangogh.c @@ -11,13 +11,10 @@ * Hardware interface for Audio DSP on Vangogh platform */ -#include <linux/platform_device.h> +#include <linux/delay.h> #include <linux/module.h> -#include "../ops.h" -#include "../sof-audio.h" #include "acp.h" -#include "acp-dsp-offset.h" #define I2S_HS_INSTANCE 0 #define I2S_BT_INSTANCE 1 @@ -136,6 +133,20 @@ static struct snd_soc_dai_driver vangogh_sof_dai[] = { }, }; +static int sof_vangogh_post_fw_run_delay(struct snd_sof_dev *sdev) +{ + /* + * Resuming from suspend in some cases my cause the DSP firmware + * to enter an unrecoverable faulty state. Delaying a bit any host + * to DSP transmission right after firmware boot completion seems + * to resolve the issue. + */ + if (!sdev->first_boot) + usleep_range(100, 150); + + return 0; +} + /* Vangogh ops */ struct snd_sof_dsp_ops sof_vangogh_ops; EXPORT_SYMBOL_NS(sof_vangogh_ops, "SND_SOC_SOF_AMD_COMMON"); @@ -157,6 +168,9 @@ int sof_vangogh_ops_init(struct snd_sof_dev *sdev) if (quirks->signed_fw_image) sof_vangogh_ops.load_firmware = acp_sof_load_signed_firmware; + + if (quirks->post_fw_run_delay) + sof_vangogh_ops.post_fw_run = sof_vangogh_post_fw_run_delay; } return 0; diff --git a/sound/soc/sof/intel/hda-codec.c b/sound/soc/sof/intel/hda-codec.c index 568f3dfe822f..2f9925830d1d 100644 --- a/sound/soc/sof/intel/hda-codec.c +++ b/sound/soc/sof/intel/hda-codec.c @@ -454,6 +454,7 @@ int hda_codec_i915_exit(struct snd_sof_dev *sdev) } EXPORT_SYMBOL_NS_GPL(hda_codec_i915_exit, "SND_SOC_SOF_HDA_AUDIO_CODEC_I915"); +MODULE_SOFTDEP("pre: snd-hda-codec-hdmi"); #endif MODULE_LICENSE("Dual BSD/GPL"); diff --git a/sound/soc/sof/intel/pci-ptl.c b/sound/soc/sof/intel/pci-ptl.c index 0aacdfac9fb4..c4fb6a2441b7 100644 --- a/sound/soc/sof/intel/pci-ptl.c +++ b/sound/soc/sof/intel/pci-ptl.c @@ -50,6 +50,7 @@ static const struct sof_dev_desc ptl_desc = { /* PCI IDs */ static const struct pci_device_id sof_pci_ids[] = { { PCI_DEVICE_DATA(INTEL, HDA_PTL, &ptl_desc) }, /* PTL */ + { PCI_DEVICE_DATA(INTEL, HDA_PTL_H, &ptl_desc) }, /* PTL-H */ { 0, } }; MODULE_DEVICE_TABLE(pci, sof_pci_ids); diff --git a/sound/soc/sof/ipc4-topology.c b/sound/soc/sof/ipc4-topology.c index c04c62478827..6d5cda813e48 100644 --- a/sound/soc/sof/ipc4-topology.c +++ b/sound/soc/sof/ipc4-topology.c @@ -765,10 +765,16 @@ static int sof_ipc4_widget_setup_comp_dai(struct snd_sof_widget *swidget) } list_for_each_entry(w, &sdev->widget_list, list) { - if (w->widget->sname && + struct snd_sof_dai *alh_dai; + + if (!WIDGET_IS_DAI(w->id) || !w->widget->sname || strcmp(w->widget->sname, swidget->widget->sname)) continue; + alh_dai = w->private; + if (alh_dai->type != SOF_DAI_INTEL_ALH) + continue; + blob->alh_cfg.device_count++; } @@ -2061,11 +2067,13 @@ sof_ipc4_prepare_copier_module(struct snd_sof_widget *swidget, list_for_each_entry(w, &sdev->widget_list, list) { u32 node_type; - if (w->widget->sname && + if (!WIDGET_IS_DAI(w->id) || !w->widget->sname || strcmp(w->widget->sname, swidget->widget->sname)) continue; dai = w->private; + if (dai->type != SOF_DAI_INTEL_ALH) + continue; alh_copier = (struct sof_ipc4_copier *)dai->private; alh_data = &alh_copier->data; node_type = SOF_IPC4_GET_NODE_TYPE(alh_data->gtw_cfg.node_id); diff --git a/sound/soc/sof/pcm.c b/sound/soc/sof/pcm.c index 35a7462d8b69..c5c6353f18ce 100644 --- a/sound/soc/sof/pcm.c +++ b/sound/soc/sof/pcm.c @@ -511,6 +511,8 @@ static int sof_pcm_close(struct snd_soc_component *component, */ } + spcm->stream[substream->stream].substream = NULL; + return 0; } diff --git a/sound/soc/sof/stream-ipc.c b/sound/soc/sof/stream-ipc.c index 794c7bbccbaf..8262443ac89a 100644 --- a/sound/soc/sof/stream-ipc.c +++ b/sound/soc/sof/stream-ipc.c @@ -43,7 +43,7 @@ int sof_ipc_msg_data(struct snd_sof_dev *sdev, return -ESTRPIPE; posn_offset = stream->posn_offset; - } else { + } else if (sps->cstream) { struct sof_compr_stream *sstream = sps->cstream->runtime->private_data; @@ -51,6 +51,10 @@ int sof_ipc_msg_data(struct snd_sof_dev *sdev, return -ESTRPIPE; posn_offset = sstream->posn_offset; + + } else { + dev_err(sdev->dev, "%s: No stream opened\n", __func__); + return -EINVAL; } snd_sof_dsp_mailbox_read(sdev, posn_offset, p, sz); diff --git a/tools/accounting/getdelays.c b/tools/accounting/getdelays.c index 100ad3dc091a..3feac0482fe9 100644 --- a/tools/accounting/getdelays.c +++ b/tools/accounting/getdelays.c @@ -196,22 +196,22 @@ static int get_family_id(int sd) static void print_delayacct(struct taskstats *t) { - printf("\n\nCPU %15s%15s%15s%15s%15s%15s\n" - " %15llu%15llu%15llu%15llu%15.3fms%13.6fms\n" - "IO %15s%15s%15s%15s\n" - " %15llu%15llu%15.3fms%13.6fms\n" - "SWAP %15s%15s%15s%15s\n" - " %15llu%15llu%15.3fms%13.6fms\n" - "RECLAIM %12s%15s%15s%15s\n" - " %15llu%15llu%15.3fms%13.6fms\n" - "THRASHING%12s%15s%15s%15s\n" - " %15llu%15llu%15.3fms%13.6fms\n" - "COMPACT %12s%15s%15s%15s\n" - " %15llu%15llu%15.3fms%13.6fms\n" - "WPCOPY %12s%15s%15s%15s\n" - " %15llu%15llu%15.3fms%13.6fms\n" - "IRQ %15s%15s%15s%15s\n" - " %15llu%15llu%15.3fms%13.6fms\n", + printf("\n\nCPU %15s%15s%15s%15s%15s%15s%15s\n" + " %15llu%15llu%15llu%15llu%15.3fms%13.6fms%13.6fms\n" + "IO %15s%15s%15s%15s%15s\n" + " %15llu%15llu%15.3fms%13.6fms%13.6fms\n" + "SWAP %15s%15s%15s%15s%15s\n" + " %15llu%15llu%15.3fms%13.6fms%13.6fms\n" + "RECLAIM %12s%15s%15s%15s%15s\n" + " %15llu%15llu%15.3fms%13.6fms%13.6fms\n" + "THRASHING%12s%15s%15s%15s%15s\n" + " %15llu%15llu%15.3fms%13.6fms%13.6fms\n" + "COMPACT %12s%15s%15s%15s%15s\n" + " %15llu%15llu%15.3fms%13.6fms%13.6fms\n" + "WPCOPY %12s%15s%15s%15s%15s\n" + " %15llu%15llu%15.3fms%13.6fms%13.6fms\n" + "IRQ %15s%15s%15s%15s%15s\n" + " %15llu%15llu%15.3fms%13.6fms%13.6fms\n", "count", "real total", "virtual total", "delay total", "delay average", "delay max", "delay min", (unsigned long long)t->cpu_count, diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index b97ff8bbb0c6..7600bf62dbdf 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -140,12 +140,18 @@ enum { }; enum { + __NETDEV_A_XSK_INFO_MAX, + NETDEV_A_XSK_INFO_MAX = (__NETDEV_A_XSK_INFO_MAX - 1) +}; + +enum { NETDEV_A_QUEUE_ID = 1, NETDEV_A_QUEUE_IFINDEX, NETDEV_A_QUEUE_TYPE, NETDEV_A_QUEUE_NAPI_ID, NETDEV_A_QUEUE_DMABUF, NETDEV_A_QUEUE_IO_URING, + NETDEV_A_QUEUE_XSK, __NETDEV_A_QUEUE_MAX, NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1) diff --git a/tools/mm/page-types.c b/tools/mm/page-types.c index bcac7ebfb51f..d7e5e8902af8 100644 --- a/tools/mm/page-types.c +++ b/tools/mm/page-types.c @@ -24,8 +24,8 @@ #include <signal.h> #include <inttypes.h> #include <sys/types.h> -#include <sys/errno.h> -#include <sys/fcntl.h> +#include <errno.h> +#include <fcntl.h> #include <sys/mount.h> #include <sys/statfs.h> #include <sys/mman.h> diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 753dbc4f8198..be18a0489303 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -227,6 +227,7 @@ static bool is_rust_noreturn(const struct symbol *func) str_ends_with(func->name, "_4core9panicking18panic_bounds_check") || str_ends_with(func->name, "_4core9panicking19assert_failed_inner") || str_ends_with(func->name, "_4core9panicking36panic_misaligned_pointer_dereference") || + strstr(func->name, "_4core9panicking13assert_failed") || strstr(func->name, "_4core9panicking11panic_const24panic_const_") || (strstr(func->name, "_4core5slice5index24slice_") && str_ends_with(func->name, "_fail")); @@ -1975,6 +1976,14 @@ static int add_jump_table(struct objtool_file *file, struct instruction *insn, reloc_addend(reloc) == pfunc->offset) break; + /* + * Clang sometimes leaves dangling unused jump table entries + * which point to the end of the function. Ignore them. + */ + if (reloc->sym->sec == pfunc->sec && + reloc_addend(reloc) == pfunc->offset + pfunc->len) + goto next; + dest_insn = find_insn(file, reloc->sym->sec, reloc_addend(reloc)); if (!dest_insn) break; @@ -1992,6 +2001,7 @@ static int add_jump_table(struct objtool_file *file, struct instruction *insn, alt->insn = dest_insn; alt->next = insn->alts; insn->alts = alt; +next: prev_offset = reloc_offset(reloc); } @@ -2264,7 +2274,7 @@ static int read_annotate(struct objtool_file *file, if (sec->sh.sh_entsize != 8) { static bool warned = false; - if (!warned) { + if (!warned && opts.verbose) { WARN("%s: dodgy linker, sh_entsize != 8", sec->name); warned = true; } diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h index f3e15e9efa76..7849405614b1 100644 --- a/tools/sched_ext/include/scx/common.bpf.h +++ b/tools/sched_ext/include/scx/common.bpf.h @@ -270,8 +270,16 @@ void bpf_obj_drop_impl(void *kptr, void *meta) __ksym; #define bpf_obj_new(type) ((type *)bpf_obj_new_impl(bpf_core_type_id_local(type), NULL)) #define bpf_obj_drop(kptr) bpf_obj_drop_impl(kptr, NULL) -void bpf_list_push_front(struct bpf_list_head *head, struct bpf_list_node *node) __ksym; -void bpf_list_push_back(struct bpf_list_head *head, struct bpf_list_node *node) __ksym; +int bpf_list_push_front_impl(struct bpf_list_head *head, + struct bpf_list_node *node, + void *meta, __u64 off) __ksym; +#define bpf_list_push_front(head, node) bpf_list_push_front_impl(head, node, NULL, 0) + +int bpf_list_push_back_impl(struct bpf_list_head *head, + struct bpf_list_node *node, + void *meta, __u64 off) __ksym; +#define bpf_list_push_back(head, node) bpf_list_push_back_impl(head, node, NULL, 0) + struct bpf_list_node *bpf_list_pop_front(struct bpf_list_head *head) __ksym; struct bpf_list_node *bpf_list_pop_back(struct bpf_list_head *head) __ksym; struct bpf_rb_node *bpf_rbtree_remove(struct bpf_rb_root *root, @@ -404,6 +412,17 @@ static __always_inline const struct cpumask *cast_mask(struct bpf_cpumask *mask) return (const struct cpumask *)mask; } +/* + * Return true if task @p cannot migrate to a different CPU, false + * otherwise. + */ +static inline bool is_migration_disabled(const struct task_struct *p) +{ + if (bpf_core_field_exists(p->migration_disabled)) + return p->migration_disabled; + return false; +} + /* rcu */ void bpf_rcu_read_lock(void) __ksym; void bpf_rcu_read_unlock(void) __ksym; @@ -421,7 +440,7 @@ void bpf_rcu_read_unlock(void) __ksym; */ static inline s64 time_delta(u64 after, u64 before) { - return (s64)(after - before) > 0 ? : 0; + return (s64)(after - before) > 0 ? (s64)(after - before) : 0; } /** diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector_classification.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector_classification.c index 3729fbfd3084..80b153d3ddec 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector_classification.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector_classification.c @@ -542,8 +542,12 @@ static void detach_program(struct bpf_flow *skel, int prog_fd) static int set_port_drop(int pf, bool multi_port) { + char dst_port[16]; + + snprintf(dst_port, sizeof(dst_port), "%d", CFG_PORT_INNER); + SYS(fail, "tc qdisc add dev lo ingress"); - SYS(fail_delete_qdisc, "tc filter add %s %s %s %s %s %s %s %s %s %s", + SYS(fail_delete_qdisc, "tc filter add %s %s %s %s %s %s %s %s %s %s %s %s", "dev lo", "parent FFFF:", "protocol", pf == PF_INET6 ? "ipv6" : "ip", @@ -551,6 +555,7 @@ static int set_port_drop(int pf, bool multi_port) "flower", "ip_proto udp", "src_port", multi_port ? "8-10" : "9", + "dst_port", dst_port, "action drop"); return 0; diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index 884ad87783d5..05eb37935c3e 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -111,31 +111,35 @@ out: static void test_sockmap_vsock_delete_on_close(void) { - int err, c, p, map; - const int zero = 0; - - err = create_pair(AF_VSOCK, SOCK_STREAM, &c, &p); - if (!ASSERT_OK(err, "create_pair(AF_VSOCK)")) - return; + int map, c, p, err, zero = 0; map = bpf_map_create(BPF_MAP_TYPE_SOCKMAP, NULL, sizeof(int), sizeof(int), 1, NULL); - if (!ASSERT_GE(map, 0, "bpf_map_create")) { - close(c); - goto out; - } + if (!ASSERT_OK_FD(map, "bpf_map_create")) + return; - err = bpf_map_update_elem(map, &zero, &c, BPF_NOEXIST); - close(c); - if (!ASSERT_OK(err, "bpf_map_update")) - goto out; + err = create_pair(AF_VSOCK, SOCK_STREAM, &c, &p); + if (!ASSERT_OK(err, "create_pair")) + goto close_map; - err = bpf_map_update_elem(map, &zero, &p, BPF_NOEXIST); + if (xbpf_map_update_elem(map, &zero, &c, BPF_NOEXIST)) + goto close_socks; + + xclose(c); + xclose(p); + + err = create_pair(AF_VSOCK, SOCK_STREAM, &c, &p); + if (!ASSERT_OK(err, "create_pair")) + goto close_map; + + err = bpf_map_update_elem(map, &zero, &c, BPF_NOEXIST); ASSERT_OK(err, "after close(), bpf_map_update"); -out: - close(p); - close(map); +close_socks: + xclose(c); + xclose(p); +close_map: + xclose(map); } static void test_skmsg_helpers(enum bpf_map_type map_type) @@ -1061,6 +1065,34 @@ destroy: test_sockmap_pass_prog__destroy(skel); } +static void test_sockmap_vsock_unconnected(void) +{ + struct sockaddr_storage addr; + int map, s, zero = 0; + socklen_t alen; + + map = bpf_map_create(BPF_MAP_TYPE_SOCKMAP, NULL, sizeof(int), + sizeof(int), 1, NULL); + if (!ASSERT_OK_FD(map, "bpf_map_create")) + return; + + s = xsocket(AF_VSOCK, SOCK_STREAM, 0); + if (s < 0) + goto close_map; + + /* Fail connect(), but trigger transport assignment. */ + init_addr_loopback(AF_VSOCK, &addr, &alen); + if (!ASSERT_ERR(connect(s, sockaddr(&addr), alen), "connect")) + goto close_sock; + + ASSERT_ERR(bpf_map_update_elem(map, &zero, &s, BPF_ANY), "map_update"); + +close_sock: + xclose(s); +close_map: + xclose(map); +} + void test_sockmap_basic(void) { if (test__start_subtest("sockmap create_update_free")) @@ -1127,4 +1159,6 @@ void test_sockmap_basic(void) test_skmsg_helpers_with_link(BPF_MAP_TYPE_SOCKHASH); if (test__start_subtest("sockmap skb_verdict vsock poll")) test_sockmap_skb_verdict_vsock_poll(); + if (test__start_subtest("sockmap vsock unconnected")) + test_sockmap_vsock_unconnected(); } diff --git a/tools/testing/selftests/cgroup/test_cpuset_v1_hp.sh b/tools/testing/selftests/cgroup/test_cpuset_v1_hp.sh index 3f45512fb512..7406c24be1ac 100755 --- a/tools/testing/selftests/cgroup/test_cpuset_v1_hp.sh +++ b/tools/testing/selftests/cgroup/test_cpuset_v1_hp.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # SPDX-License-Identifier: GPL-2.0 # # Test the special cpuset v1 hotplug case where a cpuset become empty of diff --git a/tools/testing/selftests/drivers/net/.gitignore b/tools/testing/selftests/drivers/net/.gitignore new file mode 100644 index 000000000000..ec746f374e85 --- /dev/null +++ b/tools/testing/selftests/drivers/net/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +xdp_helper diff --git a/tools/testing/selftests/drivers/net/Makefile b/tools/testing/selftests/drivers/net/Makefile index 28b6d47f812d..0c95bd944d56 100644 --- a/tools/testing/selftests/drivers/net/Makefile +++ b/tools/testing/selftests/drivers/net/Makefile @@ -1,10 +1,13 @@ # SPDX-License-Identifier: GPL-2.0 +CFLAGS += $(KHDR_INCLUDES) TEST_INCLUDES := $(wildcard lib/py/*.py) \ $(wildcard lib/sh/*.sh) \ ../../net/net_helper.sh \ ../../net/lib.sh \ +TEST_GEN_FILES := xdp_helper + TEST_PROGS := \ netcons_basic.sh \ netcons_fragmented_msg.sh \ diff --git a/tools/testing/selftests/drivers/net/config b/tools/testing/selftests/drivers/net/config index a2d8af60876d..f27172ddee0a 100644 --- a/tools/testing/selftests/drivers/net/config +++ b/tools/testing/selftests/drivers/net/config @@ -4,3 +4,4 @@ CONFIG_CONFIGFS_FS=y CONFIG_NETCONSOLE=m CONFIG_NETCONSOLE_DYNAMIC=y CONFIG_NETCONSOLE_EXTENDED_LOG=y +CONFIG_XDP_SOCKETS=y diff --git a/tools/testing/selftests/drivers/net/hw/Makefile b/tools/testing/selftests/drivers/net/hw/Makefile index 21ba64ce1e34..ae783e18be83 100644 --- a/tools/testing/selftests/drivers/net/hw/Makefile +++ b/tools/testing/selftests/drivers/net/hw/Makefile @@ -15,6 +15,7 @@ TEST_PROGS = \ nic_performance.py \ pp_alloc_fail.py \ rss_ctx.py \ + tso.py \ # TEST_FILES := \ diff --git a/tools/testing/selftests/drivers/net/hw/csum.py b/tools/testing/selftests/drivers/net/hw/csum.py index cd477f3440ca..701aca1361e0 100755 --- a/tools/testing/selftests/drivers/net/hw/csum.py +++ b/tools/testing/selftests/drivers/net/hw/csum.py @@ -9,15 +9,12 @@ from lib.py import ksft_run, ksft_exit, KsftSkipEx from lib.py import EthtoolFamily, NetDrvEpEnv from lib.py import bkg, cmd, wait_port_listen -def test_receive(cfg, ipv4=False, extra_args=None): +def test_receive(cfg, ipver="6", extra_args=None): """Test local nic checksum receive. Remote host sends crafted packets.""" if not cfg.have_rx_csum: raise KsftSkipEx(f"Test requires rx checksum offload on {cfg.ifname}") - if ipv4: - ip_args = f"-4 -S {cfg.remote_v4} -D {cfg.v4}" - else: - ip_args = f"-6 -S {cfg.remote_v6} -D {cfg.v6}" + ip_args = f"-{ipver} -S {cfg.remote_addr_v[ipver]} -D {cfg.addr_v[ipver]}" rx_cmd = f"{cfg.bin_local} -i {cfg.ifname} -n 100 {ip_args} -r 1 -R {extra_args}" tx_cmd = f"{cfg.bin_remote} -i {cfg.ifname} -n 100 {ip_args} -r 1 -T {extra_args}" @@ -27,17 +24,14 @@ def test_receive(cfg, ipv4=False, extra_args=None): cmd(tx_cmd, host=cfg.remote) -def test_transmit(cfg, ipv4=False, extra_args=None): +def test_transmit(cfg, ipver="6", extra_args=None): """Test local nic checksum transmit. Remote host verifies packets.""" if (not cfg.have_tx_csum_generic and - not (cfg.have_tx_csum_ipv4 and ipv4) and - not (cfg.have_tx_csum_ipv6 and not ipv4)): + not (cfg.have_tx_csum_ipv4 and ipver == "4") and + not (cfg.have_tx_csum_ipv6 and ipver == "6")): raise KsftSkipEx(f"Test requires tx checksum offload on {cfg.ifname}") - if ipv4: - ip_args = f"-4 -S {cfg.v4} -D {cfg.remote_v4}" - else: - ip_args = f"-6 -S {cfg.v6} -D {cfg.remote_v6}" + ip_args = f"-{ipver} -S {cfg.addr_v[ipver]} -D {cfg.remote_addr_v[ipver]}" # Cannot randomize input when calculating zero checksum if extra_args != "-U -Z": @@ -51,26 +45,20 @@ def test_transmit(cfg, ipv4=False, extra_args=None): cmd(tx_cmd) -def test_builder(name, cfg, ipv4=False, tx=False, extra_args=""): +def test_builder(name, cfg, ipver="6", tx=False, extra_args=""): """Construct specific tests from the common template. Most tests follow the same basic pattern, differing only in Direction of the test and optional flags passed to csum.""" def f(cfg): - if ipv4: - cfg.require_v4() - else: - cfg.require_v6() + cfg.require_ipver(ipver) if tx: - test_transmit(cfg, ipv4, extra_args) + test_transmit(cfg, ipver, extra_args) else: - test_receive(cfg, ipv4, extra_args) + test_receive(cfg, ipver, extra_args) - if ipv4: - f.__name__ = "ipv4_" + name - else: - f.__name__ = "ipv6_" + name + f.__name__ = f"ipv{ipver}_" + name return f @@ -104,15 +92,15 @@ def main() -> None: cfg.bin_remote = cfg.remote.deploy(cfg.bin_local) cases = [] - for ipv4 in [True, False]: - cases.append(test_builder("rx_tcp", cfg, ipv4, False, "-t")) - cases.append(test_builder("rx_tcp_invalid", cfg, ipv4, False, "-t -E")) + for ipver in ["4", "6"]: + cases.append(test_builder("rx_tcp", cfg, ipver, False, "-t")) + cases.append(test_builder("rx_tcp_invalid", cfg, ipver, False, "-t -E")) - cases.append(test_builder("rx_udp", cfg, ipv4, False, "")) - cases.append(test_builder("rx_udp_invalid", cfg, ipv4, False, "-E")) + cases.append(test_builder("rx_udp", cfg, ipver, False, "")) + cases.append(test_builder("rx_udp_invalid", cfg, ipver, False, "-E")) - cases.append(test_builder("tx_udp_csum_offload", cfg, ipv4, True, "-U")) - cases.append(test_builder("tx_udp_zero_checksum", cfg, ipv4, True, "-U -Z")) + cases.append(test_builder("tx_udp_csum_offload", cfg, ipver, True, "-U")) + cases.append(test_builder("tx_udp_zero_checksum", cfg, ipver, True, "-U -Z")) ksft_run(cases=cases, args=(cfg, )) ksft_exit() diff --git a/tools/testing/selftests/drivers/net/hw/devmem.py b/tools/testing/selftests/drivers/net/hw/devmem.py index 1223f0f5c10c..3947e9157115 100755 --- a/tools/testing/selftests/drivers/net/hw/devmem.py +++ b/tools/testing/selftests/drivers/net/hw/devmem.py @@ -21,15 +21,15 @@ def require_devmem(cfg): @ksft_disruptive def check_rx(cfg) -> None: - cfg.require_v6() + cfg.require_ipver("6") require_devmem(cfg) port = rand_port() - listen_cmd = f"./ncdevmem -l -f {cfg.ifname} -s {cfg.v6} -p {port}" + listen_cmd = f"./ncdevmem -l -f {cfg.ifname} -s {cfg.addr_v['6']} -p {port}" with bkg(listen_cmd) as socat: wait_port_listen(port) - cmd(f"echo -e \"hello\\nworld\"| socat -u - TCP6:[{cfg.v6}]:{port}", host=cfg.remote, shell=True) + cmd(f"echo -e \"hello\\nworld\"| socat -u - TCP6:[{cfg.addr_v['6']}]:{port}", host=cfg.remote, shell=True) ksft_eq(socat.stdout.strip(), "hello\nworld") diff --git a/tools/testing/selftests/drivers/net/hw/tso.py b/tools/testing/selftests/drivers/net/hw/tso.py new file mode 100755 index 000000000000..e1ecb92f79d9 --- /dev/null +++ b/tools/testing/selftests/drivers/net/hw/tso.py @@ -0,0 +1,241 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +"""Run the tools/testing/selftests/net/csum testsuite.""" + +import fcntl +import socket +import struct +import termios +import time + +from lib.py import ksft_pr, ksft_run, ksft_exit, KsftSkipEx, KsftXfailEx +from lib.py import ksft_eq, ksft_ge, ksft_lt +from lib.py import EthtoolFamily, NetdevFamily, NetDrvEpEnv +from lib.py import bkg, cmd, defer, ethtool, ip, rand_port, wait_port_listen + + +def sock_wait_drain(sock, max_wait=1000): + """Wait for all pending write data on the socket to get ACKed.""" + for _ in range(max_wait): + one = b'\0' * 4 + outq = fcntl.ioctl(sock.fileno(), termios.TIOCOUTQ, one) + outq = struct.unpack("I", outq)[0] + if outq == 0: + break + time.sleep(0.01) + ksft_eq(outq, 0) + + +def tcp_sock_get_retrans(sock): + """Get the number of retransmissions for the TCP socket.""" + info = sock.getsockopt(socket.SOL_TCP, socket.TCP_INFO, 512) + return struct.unpack("I", info[100:104])[0] + + +def run_one_stream(cfg, ipver, remote_v4, remote_v6, should_lso): + cfg.require_cmd("socat", remote=True) + + port = rand_port() + listen_cmd = f"socat -{ipver} -t 2 -u TCP-LISTEN:{port},reuseport /dev/null,ignoreeof" + + with bkg(listen_cmd, host=cfg.remote) as nc: + wait_port_listen(port, host=cfg.remote) + + if ipver == "4": + sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM) + sock.connect((remote_v4, port)) + else: + sock = socket.socket(socket.AF_INET6, socket.SOCK_STREAM) + sock.connect((remote_v6, port)) + + # Small send to make sure the connection is working. + sock.send("ping".encode()) + sock_wait_drain(sock) + + # Send 4MB of data, record the LSO packet count. + qstat_old = cfg.netnl.qstats_get({"ifindex": cfg.ifindex}, dump=True)[0] + buf = b"0" * 1024 * 1024 * 4 + sock.send(buf) + sock_wait_drain(sock) + qstat_new = cfg.netnl.qstats_get({"ifindex": cfg.ifindex}, dump=True)[0] + + # No math behind the 10 here, but try to catch cases where + # TCP falls back to non-LSO. + ksft_lt(tcp_sock_get_retrans(sock), 10) + sock.close() + + # Check that at least 90% of the data was sent as LSO packets. + # System noise may cause false negatives. Also header overheads + # will add up to 5% of extra packes... The check is best effort. + total_lso_wire = len(buf) * 0.90 // cfg.dev["mtu"] + total_lso_super = len(buf) * 0.90 // cfg.dev["tso_max_size"] + if should_lso: + if cfg.have_stat_super_count: + ksft_ge(qstat_new['tx-hw-gso-packets'] - + qstat_old['tx-hw-gso-packets'], + total_lso_super, + comment="Number of LSO super-packets with LSO enabled") + if cfg.have_stat_wire_count: + ksft_ge(qstat_new['tx-hw-gso-wire-packets'] - + qstat_old['tx-hw-gso-wire-packets'], + total_lso_wire, + comment="Number of LSO wire-packets with LSO enabled") + else: + if cfg.have_stat_super_count: + ksft_lt(qstat_new['tx-hw-gso-packets'] - + qstat_old['tx-hw-gso-packets'], + 15, comment="Number of LSO super-packets with LSO disabled") + if cfg.have_stat_wire_count: + ksft_lt(qstat_new['tx-hw-gso-wire-packets'] - + qstat_old['tx-hw-gso-wire-packets'], + 500, comment="Number of LSO wire-packets with LSO disabled") + + +def build_tunnel(cfg, outer_ipver, tun_info): + local_v4 = NetDrvEpEnv.nsim_v4_pfx + "1" + local_v6 = NetDrvEpEnv.nsim_v6_pfx + "1" + remote_v4 = NetDrvEpEnv.nsim_v4_pfx + "2" + remote_v6 = NetDrvEpEnv.nsim_v6_pfx + "2" + + local_addr = cfg.addr_v[outer_ipver] + remote_addr = cfg.remote_addr_v[outer_ipver] + + tun_type = tun_info[0] + tun_arg = tun_info[2] + ip(f"link add {tun_type}-ksft type {tun_type} {tun_arg} local {local_addr} remote {remote_addr} dev {cfg.ifname}") + defer(ip, f"link del {tun_type}-ksft") + ip(f"link set dev {tun_type}-ksft up") + ip(f"addr add {local_v4}/24 dev {tun_type}-ksft") + ip(f"addr add {local_v6}/64 dev {tun_type}-ksft") + + ip(f"link add {tun_type}-ksft type {tun_type} {tun_arg} local {remote_addr} remote {local_addr} dev {cfg.remote_ifname}", + host=cfg.remote) + defer(ip, f"link del {tun_type}-ksft", host=cfg.remote) + ip(f"link set dev {tun_type}-ksft up", host=cfg.remote) + ip(f"addr add {remote_v4}/24 dev {tun_type}-ksft", host=cfg.remote) + ip(f"addr add {remote_v6}/64 dev {tun_type}-ksft", host=cfg.remote) + + return remote_v4, remote_v6 + + +def test_builder(name, cfg, outer_ipver, feature, tun=None, inner_ipver=None): + """Construct specific tests from the common template.""" + def f(cfg): + cfg.require_ipver(outer_ipver) + + if not cfg.have_stat_super_count and \ + not cfg.have_stat_wire_count: + raise KsftSkipEx(f"Device does not support LSO queue stats") + + ipver = outer_ipver + if tun: + remote_v4, remote_v6 = build_tunnel(cfg, ipver, tun) + ipver = inner_ipver + else: + remote_v4 = cfg.remote_addr_v["4"] + remote_v6 = cfg.remote_addr_v["6"] + + tun_partial = tun and tun[1] + # Tunnel which can silently fall back to gso-partial + has_gso_partial = tun and 'tx-gso-partial' in cfg.features + + # For TSO4 via partial we need mangleid + if ipver == "4" and feature in cfg.partial_features: + ksft_pr("Testing with mangleid enabled") + if 'tx-tcp-mangleid-segmentation' not in cfg.features: + ethtool(f"-K {cfg.ifname} tx-tcp-mangleid-segmentation on") + defer(ethtool, f"-K {cfg.ifname} tx-tcp-mangleid-segmentation off") + + # First test without the feature enabled. + ethtool(f"-K {cfg.ifname} {feature} off") + if has_gso_partial: + ethtool(f"-K {cfg.ifname} tx-gso-partial off") + run_one_stream(cfg, ipver, remote_v4, remote_v6, should_lso=False) + + # Now test with the feature enabled. + # For compatible tunnels only - just GSO partial, not specific feature. + if has_gso_partial: + ethtool(f"-K {cfg.ifname} tx-gso-partial on") + run_one_stream(cfg, ipver, remote_v4, remote_v6, + should_lso=tun_partial) + + # Full feature enabled. + if feature in cfg.features: + ethtool(f"-K {cfg.ifname} {feature} on") + run_one_stream(cfg, ipver, remote_v4, remote_v6, should_lso=True) + else: + raise KsftXfailEx(f"Device does not support {feature}") + + f.__name__ = name + ((outer_ipver + "_") if tun else "") + "ipv" + inner_ipver + return f + + +def query_nic_features(cfg) -> None: + """Query and cache the NIC features.""" + cfg.have_stat_super_count = False + cfg.have_stat_wire_count = False + + cfg.features = set() + features = cfg.ethnl.features_get({"header": {"dev-index": cfg.ifindex}}) + for f in features["active"]["bits"]["bit"]: + cfg.features.add(f["name"]) + + # Check which features are supported via GSO partial + cfg.partial_features = set() + if 'tx-gso-partial' in cfg.features: + ethtool(f"-K {cfg.ifname} tx-gso-partial off") + + no_partial = set() + features = cfg.ethnl.features_get({"header": {"dev-index": cfg.ifindex}}) + for f in features["active"]["bits"]["bit"]: + no_partial.add(f["name"]) + cfg.partial_features = cfg.features - no_partial + ethtool(f"-K {cfg.ifname} tx-gso-partial on") + + stats = cfg.netnl.qstats_get({"ifindex": cfg.ifindex}, dump=True) + if stats: + if 'tx-hw-gso-packets' in stats[0]: + ksft_pr("Detected qstat for LSO super-packets") + cfg.have_stat_super_count = True + if 'tx-hw-gso-wire-packets' in stats[0]: + ksft_pr("Detected qstat for LSO wire-packets") + cfg.have_stat_wire_count = True + + +def main() -> None: + with NetDrvEpEnv(__file__, nsim_test=False) as cfg: + cfg.ethnl = EthtoolFamily() + cfg.netnl = NetdevFamily() + + query_nic_features(cfg) + + test_info = ( + # name, v4/v6 ethtool_feature tun:(type, partial, args) + ("", "4", "tx-tcp-segmentation", None), + ("", "6", "tx-tcp6-segmentation", None), + ("vxlan", "", "tx-udp_tnl-segmentation", ("vxlan", True, "id 100 dstport 4789 noudpcsum")), + ("vxlan_csum", "", "tx-udp_tnl-csum-segmentation", ("vxlan", False, "id 100 dstport 4789 udpcsum")), + ("gre", "4", "tx-gre-segmentation", ("ipgre", False, "")), + ("gre", "6", "tx-gre-segmentation", ("ip6gre", False, "")), + ) + + cases = [] + for outer_ipver in ["4", "6"]: + for info in test_info: + # Skip if test which only works for a specific IP version + if info[1] and outer_ipver != info[1]: + continue + + cases.append(test_builder(info[0], cfg, outer_ipver, info[2], + tun=info[3], inner_ipver="4")) + if info[3]: + cases.append(test_builder(info[0], cfg, outer_ipver, info[2], + tun=info[3], inner_ipver="6")) + + ksft_run(cases=cases, args=(cfg, )) + ksft_exit() + + +if __name__ == "__main__": + main() diff --git a/tools/testing/selftests/drivers/net/lib/py/env.py b/tools/testing/selftests/drivers/net/lib/py/env.py index 886b4904613c..96b33b5ef9dd 100644 --- a/tools/testing/selftests/drivers/net/lib/py/env.py +++ b/tools/testing/selftests/drivers/net/lib/py/env.py @@ -64,7 +64,7 @@ class NetDrvEnv(NetDrvEnvBase): self._ns = None if 'NETIF' in self.env: - self.dev = ip("link show dev " + self.env['NETIF'], json=True)[0] + self.dev = ip("-d link show dev " + self.env['NETIF'], json=True)[0] else: self._ns = NetdevSimDev(**kwargs) self.dev = self._ns.nsims[0].dev @@ -113,17 +113,20 @@ class NetDrvEpEnv(NetDrvEnvBase): self._ns = None self._ns_peer = None + self.addr_v = { "4": None, "6": None } + self.remote_addr_v = { "4": None, "6": None } + if "NETIF" in self.env: if nsim_test is True: raise KsftXfailEx("Test only works on netdevsim") self._check_env() - self.dev = ip("link show dev " + self.env['NETIF'], json=True)[0] + self.dev = ip("-d link show dev " + self.env['NETIF'], json=True)[0] - self.v4 = self.env.get("LOCAL_V4") - self.v6 = self.env.get("LOCAL_V6") - self.remote_v4 = self.env.get("REMOTE_V4") - self.remote_v6 = self.env.get("REMOTE_V6") + self.addr_v["4"] = self.env.get("LOCAL_V4") + self.addr_v["6"] = self.env.get("LOCAL_V6") + self.remote_addr_v["4"] = self.env.get("REMOTE_V4") + self.remote_addr_v["6"] = self.env.get("REMOTE_V6") kind = self.env["REMOTE_TYPE"] args = self.env["REMOTE_ARGS"] else: @@ -134,26 +137,29 @@ class NetDrvEpEnv(NetDrvEnvBase): self.dev = self._ns.nsims[0].dev - self.v4 = self.nsim_v4_pfx + "1" - self.v6 = self.nsim_v6_pfx + "1" - self.remote_v4 = self.nsim_v4_pfx + "2" - self.remote_v6 = self.nsim_v6_pfx + "2" + self.addr_v["4"] = self.nsim_v4_pfx + "1" + self.addr_v["6"] = self.nsim_v6_pfx + "1" + self.remote_addr_v["4"] = self.nsim_v4_pfx + "2" + self.remote_addr_v["6"] = self.nsim_v6_pfx + "2" kind = "netns" args = self._netns.name self.remote = Remote(kind, args, src_path) - self.addr = self.v6 if self.v6 else self.v4 - self.remote_addr = self.remote_v6 if self.remote_v6 else self.remote_v4 + self.addr_ipver = "6" if self.addr_v["6"] else "4" + self.addr = self.addr_v[self.addr_ipver] + self.remote_addr = self.remote_addr_v[self.addr_ipver] - self.addr_ipver = "6" if self.v6 else "4" # Bracketed addresses, some commands need IPv6 to be inside [] - self.baddr = f"[{self.v6}]" if self.v6 else self.v4 - self.remote_baddr = f"[{self.remote_v6}]" if self.remote_v6 else self.remote_v4 + self.baddr = f"[{self.addr_v['6']}]" if self.addr_v["6"] else self.addr_v["4"] + self.remote_baddr = f"[{self.remote_addr_v['6']}]" if self.remote_addr_v["6"] else self.remote_addr_v["4"] self.ifname = self.dev['ifname'] self.ifindex = self.dev['ifindex'] + # resolve remote interface name + self.remote_ifname = self.resolve_remote_ifc() + self._required_cmd = {} def create_local(self): @@ -200,6 +206,18 @@ class NetDrvEpEnv(NetDrvEnvBase): raise Exception("Invalid environment, missing configuration:", missing, "Please see tools/testing/selftests/drivers/net/README.rst") + def resolve_remote_ifc(self): + v4 = v6 = None + if self.remote_addr_v["4"]: + v4 = ip("addr show to " + self.remote_addr_v["4"], json=True, host=self.remote) + if self.remote_addr_v["6"]: + v6 = ip("addr show to " + self.remote_addr_v["6"], json=True, host=self.remote) + if v4 and v6 and v4[0]["ifname"] != v6[0]["ifname"]: + raise Exception("Can't resolve remote interface name, v4 and v6 don't match") + if (v4 and len(v4) > 1) or (v6 and len(v6) > 1): + raise Exception("Can't resolve remote interface name, multiple interfaces match") + return v6[0]["ifname"] if v6 else v4[0]["ifname"] + def __enter__(self): return self @@ -223,13 +241,9 @@ class NetDrvEpEnv(NetDrvEnvBase): del self.remote self.remote = None - def require_v4(self): - if not self.v4 or not self.remote_v4: - raise KsftSkipEx("Test requires IPv4 connectivity") - - def require_v6(self): - if not self.v6 or not self.remote_v6: - raise KsftSkipEx("Test requires IPv6 connectivity") + def require_ipver(self, ipver): + if not self.addr_v[ipver] or not self.remote_addr_v[ipver]: + raise KsftSkipEx(f"Test requires IPv{ipver} connectivity") def _require_cmd(self, comm, key, host=None): cached = self._required_cmd.get(comm, {}) diff --git a/tools/testing/selftests/drivers/net/ping.py b/tools/testing/selftests/drivers/net/ping.py index eb83e7b48797..17dc11e9b6dd 100755 --- a/tools/testing/selftests/drivers/net/ping.py +++ b/tools/testing/selftests/drivers/net/ping.py @@ -8,17 +8,17 @@ from lib.py import bkg, cmd, wait_port_listen, rand_port def test_v4(cfg) -> None: - cfg.require_v4() + cfg.require_ipver("4") - cmd(f"ping -c 1 -W0.5 {cfg.remote_v4}") - cmd(f"ping -c 1 -W0.5 {cfg.v4}", host=cfg.remote) + cmd("ping -c 1 -W0.5 " + cfg.remote_addr_v["4"]) + cmd("ping -c 1 -W0.5 " + cfg.addr_v["4"], host=cfg.remote) def test_v6(cfg) -> None: - cfg.require_v6() + cfg.require_ipver("6") - cmd(f"ping -c 1 -W0.5 {cfg.remote_v6}") - cmd(f"ping -c 1 -W0.5 {cfg.v6}", host=cfg.remote) + cmd("ping -c 1 -W0.5 " + cfg.remote_addr_v["6"]) + cmd("ping -c 1 -W0.5 " + cfg.addr_v["6"], host=cfg.remote) def test_tcp(cfg) -> None: diff --git a/tools/testing/selftests/drivers/net/queues.py b/tools/testing/selftests/drivers/net/queues.py index 38303da957ee..9040baf7b726 100755 --- a/tools/testing/selftests/drivers/net/queues.py +++ b/tools/testing/selftests/drivers/net/queues.py @@ -2,13 +2,15 @@ # SPDX-License-Identifier: GPL-2.0 from lib.py import ksft_disruptive, ksft_exit, ksft_run -from lib.py import ksft_eq, ksft_raises, KsftSkipEx +from lib.py import ksft_eq, ksft_not_in, ksft_raises, KsftSkipEx, KsftFailEx from lib.py import EthtoolFamily, NetdevFamily, NlError from lib.py import NetDrvEnv -from lib.py import cmd, defer, ip +from lib.py import bkg, cmd, defer, ip import errno import glob - +import os +import socket +import struct def sys_get_queues(ifname, qtype='rx') -> int: folders = glob.glob(f'/sys/class/net/{ifname}/queues/{qtype}-*') @@ -22,6 +24,40 @@ def nl_get_queues(cfg, nl, qtype='rx'): return None +def check_xsk(cfg, nl, xdp_queue_id=0) -> None: + # Probe for support + xdp = cmd(cfg.rpath("xdp_helper") + ' - -', fail=False) + if xdp.ret == 255: + raise KsftSkipEx('AF_XDP unsupported') + elif xdp.ret > 0: + raise KsftFailEx('unable to create AF_XDP socket') + + with bkg(f'{cfg.rpath("xdp_helper")} {cfg.ifindex} {xdp_queue_id}', + ksft_wait=3): + + rx = tx = False + + queues = nl.queue_get({'ifindex': cfg.ifindex}, dump=True) + if not queues: + raise KsftSkipEx("Netlink reports no queues") + + for q in queues: + if q['id'] == 0: + if q['type'] == 'rx': + rx = True + if q['type'] == 'tx': + tx = True + + ksft_eq(q.get('xsk', None), {}, + comment="xsk attr on queue we configured") + else: + ksft_not_in('xsk', q, + comment="xsk attr on queue we didn't configure") + + ksft_eq(rx, True) + ksft_eq(tx, True) + + def get_queues(cfg, nl) -> None: snl = NetdevFamily(recv_size=4096) @@ -81,7 +117,8 @@ def check_down(cfg, nl) -> None: def main() -> None: with NetDrvEnv(__file__, queue_count=100) as cfg: - ksft_run([get_queues, addremove_queues, check_down], args=(cfg, NetdevFamily())) + ksft_run([get_queues, addremove_queues, check_down, check_xsk], + args=(cfg, NetdevFamily())) ksft_exit() diff --git a/tools/testing/selftests/drivers/net/xdp_helper.c b/tools/testing/selftests/drivers/net/xdp_helper.c new file mode 100644 index 000000000000..aeed25914104 --- /dev/null +++ b/tools/testing/selftests/drivers/net/xdp_helper.c @@ -0,0 +1,151 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <errno.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <sys/mman.h> +#include <sys/socket.h> +#include <linux/if_xdp.h> +#include <linux/if_link.h> +#include <net/if.h> +#include <inttypes.h> + +#define UMEM_SZ (1U << 16) +#define NUM_DESC (UMEM_SZ / 2048) + +/* Move this to a common header when reused! */ +static void ksft_ready(void) +{ + const char msg[7] = "ready\n"; + char *env_str; + int fd; + + env_str = getenv("KSFT_READY_FD"); + if (env_str) { + fd = atoi(env_str); + if (!fd) { + fprintf(stderr, "invalid KSFT_READY_FD = '%s'\n", + env_str); + return; + } + } else { + fd = STDOUT_FILENO; + } + + write(fd, msg, sizeof(msg)); + if (fd != STDOUT_FILENO) + close(fd); +} + +static void ksft_wait(void) +{ + char *env_str; + char byte; + int fd; + + env_str = getenv("KSFT_WAIT_FD"); + if (env_str) { + fd = atoi(env_str); + if (!fd) { + fprintf(stderr, "invalid KSFT_WAIT_FD = '%s'\n", + env_str); + return; + } + } else { + /* Not running in KSFT env, wait for input from STDIN instead */ + fd = STDIN_FILENO; + } + + read(fd, &byte, sizeof(byte)); + if (fd != STDIN_FILENO) + close(fd); +} + +/* this is a simple helper program that creates an XDP socket and does the + * minimum necessary to get bind() to succeed. + * + * this test program is not intended to actually process packets, but could be + * extended in the future if that is actually needed. + * + * it is used by queues.py to ensure the xsk netlinux attribute is set + * correctly. + */ +int main(int argc, char **argv) +{ + struct xdp_umem_reg umem_reg = { 0 }; + struct sockaddr_xdp sxdp = { 0 }; + int num_desc = NUM_DESC; + void *umem_area; + int ifindex; + int sock_fd; + int queue; + + if (argc != 3) { + fprintf(stderr, "Usage: %s ifindex queue_id\n", argv[0]); + return 1; + } + + sock_fd = socket(AF_XDP, SOCK_RAW, 0); + if (sock_fd < 0) { + perror("socket creation failed"); + /* if the kernel doesn't support AF_XDP, let the test program + * know with -1. All other error paths return 1. + */ + if (errno == EAFNOSUPPORT) + return -1; + return 1; + } + + /* "Probing mode", just checking if AF_XDP sockets are supported */ + if (!strcmp(argv[1], "-") && !strcmp(argv[2], "-")) { + printf("AF_XDP support detected\n"); + close(sock_fd); + return 0; + } + + ifindex = atoi(argv[1]); + queue = atoi(argv[2]); + + umem_area = mmap(NULL, UMEM_SZ, PROT_READ | PROT_WRITE, MAP_PRIVATE | + MAP_ANONYMOUS, -1, 0); + if (umem_area == MAP_FAILED) { + perror("mmap failed"); + return 1; + } + + umem_reg.addr = (uintptr_t)umem_area; + umem_reg.len = UMEM_SZ; + umem_reg.chunk_size = 2048; + umem_reg.headroom = 0; + + setsockopt(sock_fd, SOL_XDP, XDP_UMEM_REG, &umem_reg, + sizeof(umem_reg)); + setsockopt(sock_fd, SOL_XDP, XDP_UMEM_FILL_RING, &num_desc, + sizeof(num_desc)); + setsockopt(sock_fd, SOL_XDP, XDP_UMEM_COMPLETION_RING, &num_desc, + sizeof(num_desc)); + setsockopt(sock_fd, SOL_XDP, XDP_RX_RING, &num_desc, sizeof(num_desc)); + + sxdp.sxdp_family = AF_XDP; + sxdp.sxdp_ifindex = ifindex; + sxdp.sxdp_queue_id = queue; + sxdp.sxdp_flags = 0; + + if (bind(sock_fd, (struct sockaddr *)&sxdp, sizeof(sxdp)) != 0) { + munmap(umem_area, UMEM_SZ); + perror("bind failed"); + close(sock_fd); + return 1; + } + + ksft_ready(); + ksft_wait(); + + /* parent program will write a byte to stdin when its ready for this + * helper to exit + */ + + close(sock_fd); + return 0; +} diff --git a/tools/testing/selftests/kvm/x86/hyperv_cpuid.c b/tools/testing/selftests/kvm/x86/hyperv_cpuid.c index 4f5881d4ef66..4e920705681a 100644 --- a/tools/testing/selftests/kvm/x86/hyperv_cpuid.c +++ b/tools/testing/selftests/kvm/x86/hyperv_cpuid.c @@ -41,13 +41,19 @@ static bool smt_possible(void) return res; } -static void test_hv_cpuid(const struct kvm_cpuid2 *hv_cpuid_entries, - bool evmcs_expected) +static void test_hv_cpuid(struct kvm_vcpu *vcpu, bool evmcs_expected) { + const bool has_irqchip = !vcpu || vcpu->vm->has_irqchip; + const struct kvm_cpuid2 *hv_cpuid_entries; int i; int nent_expected = 10; u32 test_val; + if (vcpu) + hv_cpuid_entries = vcpu_get_supported_hv_cpuid(vcpu); + else + hv_cpuid_entries = kvm_get_supported_hv_cpuid(); + TEST_ASSERT(hv_cpuid_entries->nent == nent_expected, "KVM_GET_SUPPORTED_HV_CPUID should return %d entries" " (returned %d)", @@ -80,12 +86,19 @@ static void test_hv_cpuid(const struct kvm_cpuid2 *hv_cpuid_entries, entry->eax, evmcs_expected ); break; + case 0x40000003: + TEST_ASSERT(has_irqchip || !(entry->edx & BIT(19)), + "\"Direct\" Synthetic Timers should require in-kernel APIC"); + break; case 0x40000004: test_val = entry->eax & (1UL << 18); TEST_ASSERT(!!test_val == !smt_possible(), "NoNonArchitecturalCoreSharing bit" " doesn't reflect SMT setting"); + + TEST_ASSERT(has_irqchip || !(entry->eax & BIT(10)), + "Cluster IPI (i.e. SEND_IPI) should require in-kernel APIC"); break; case 0x4000000A: TEST_ASSERT(entry->eax & (1UL << 19), @@ -109,9 +122,16 @@ static void test_hv_cpuid(const struct kvm_cpuid2 *hv_cpuid_entries, * entry->edx); */ } + + /* + * Note, the CPUID array returned by the system-scoped helper is a one- + * time allocation, i.e. must not be freed. + */ + if (vcpu) + free((void *)hv_cpuid_entries); } -void test_hv_cpuid_e2big(struct kvm_vm *vm, struct kvm_vcpu *vcpu) +static void test_hv_cpuid_e2big(struct kvm_vm *vm, struct kvm_vcpu *vcpu) { static struct kvm_cpuid2 cpuid = {.nent = 0}; int ret; @@ -129,19 +149,20 @@ void test_hv_cpuid_e2big(struct kvm_vm *vm, struct kvm_vcpu *vcpu) int main(int argc, char *argv[]) { struct kvm_vm *vm; - const struct kvm_cpuid2 *hv_cpuid_entries; struct kvm_vcpu *vcpu; TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_CPUID)); - vm = vm_create_with_one_vcpu(&vcpu, guest_code); + /* Test the vCPU ioctl without an in-kernel local APIC. */ + vm = vm_create_barebones(); + vcpu = __vm_vcpu_add(vm, 0); + test_hv_cpuid(vcpu, false); + kvm_vm_free(vm); /* Test vCPU ioctl version */ + vm = vm_create_with_one_vcpu(&vcpu, guest_code); test_hv_cpuid_e2big(vm, vcpu); - - hv_cpuid_entries = vcpu_get_supported_hv_cpuid(vcpu); - test_hv_cpuid(hv_cpuid_entries, false); - free((void *)hv_cpuid_entries); + test_hv_cpuid(vcpu, false); if (!kvm_cpu_has(X86_FEATURE_VMX) || !kvm_has_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)) { @@ -149,9 +170,7 @@ int main(int argc, char *argv[]) goto do_sys; } vcpu_enable_evmcs(vcpu); - hv_cpuid_entries = vcpu_get_supported_hv_cpuid(vcpu); - test_hv_cpuid(hv_cpuid_entries, true); - free((void *)hv_cpuid_entries); + test_hv_cpuid(vcpu, true); do_sys: /* Test system ioctl version */ @@ -161,9 +180,7 @@ do_sys: } test_hv_cpuid_e2big(vm, NULL); - - hv_cpuid_entries = kvm_get_supported_hv_cpuid(); - test_hv_cpuid(hv_cpuid_entries, kvm_cpu_has(X86_FEATURE_VMX)); + test_hv_cpuid(NULL, kvm_cpu_has(X86_FEATURE_VMX)); out: kvm_vm_free(vm); diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index 333c468c2699..da7e26668103 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -220,7 +220,7 @@ run_test() { if test_selected ${CATEGORY}; then # On memory constrainted systems some tests can fail to allocate hugepages. # perform some cleanup before the test for a higher success rate. - if [ ${CATEGORY} == "thp" ] | [ ${CATEGORY} == "hugetlb" ]; then + if [ ${CATEGORY} == "thp" -o ${CATEGORY} == "hugetlb" ]; then echo 3 > /proc/sys/vm/drop_caches sleep 2 echo 1 > /proc/sys/vm/compact_memory diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 28a715a8ef2b..80dcae53ef55 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -42,6 +42,7 @@ socket so_incoming_cpu so_netns_cookie so_txtime +so_rcv_listener stress_reuseport_listen tap tcp_fastopen_backup_key diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index b6271714504d..aeb96c085614 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -33,8 +33,10 @@ TEST_PROGS += gro.sh TEST_PROGS += gre_gso.sh TEST_PROGS += cmsg_so_mark.sh TEST_PROGS += cmsg_so_priority.sh +TEST_PROGS += test_so_rcv.sh TEST_PROGS += cmsg_time.sh cmsg_ipv6.sh TEST_PROGS += netns-name.sh +TEST_PROGS += link_netns.py TEST_PROGS += nl_netdev.py TEST_PROGS += rtnetlink.py TEST_PROGS += srv6_end_dt46_l3vpn_test.sh @@ -76,6 +78,7 @@ TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls tun tap epoll_busy_ TEST_GEN_FILES += toeplitz TEST_GEN_FILES += cmsg_sender TEST_GEN_FILES += stress_reuseport_listen +TEST_GEN_FILES += so_rcv_listener TEST_PROGS += test_vxlan_vnifiltering.sh TEST_GEN_FILES += io_uring_zerocopy_tx TEST_PROGS += io_uring_zerocopy_tx.sh diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index 5b9baf708950..ab55270669ec 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -107,3 +107,8 @@ CONFIG_XFRM_INTERFACE=m CONFIG_XFRM_USER=m CONFIG_IP_NF_MATCH_RPFILTER=m CONFIG_IP6_NF_MATCH_RPFILTER=m +CONFIG_IPVLAN=m +CONFIG_CAN=m +CONFIG_CAN_DEV=m +CONFIG_CAN_VXCAN=m +CONFIG_NETKIT=y diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh index 899dbad0104b..4fcc38907e48 100755 --- a/tools/testing/selftests/net/fcnal-test.sh +++ b/tools/testing/selftests/net/fcnal-test.sh @@ -3667,7 +3667,7 @@ ipv6_addr_bind_novrf() # when it really should not a=${NSA_LO_IP6} log_start - show_hint "Tecnically should fail since address is not on device but kernel allows" + show_hint "Technically should fail since address is not on device but kernel allows" run_cmd nettest -6 -s -l ${a} -I ${NSA_DEV} -t1 -b log_test_addr ${a} $? 0 "TCP socket bind to out of scope local address" } @@ -3724,7 +3724,7 @@ ipv6_addr_bind_vrf() # passes when it really should not a=${VRF_IP6} log_start - show_hint "Tecnically should fail since address is not on device but kernel allows" + show_hint "Technically should fail since address is not on device but kernel allows" run_cmd nettest -6 -s -l ${a} -I ${NSA_DEV} -t1 -b log_test_addr ${a} $? 0 "TCP socket bind to VRF address with device bind" diff --git a/tools/testing/selftests/net/fdb_flush.sh b/tools/testing/selftests/net/fdb_flush.sh index d5e3abb8658c..9931a1e36e3d 100755 --- a/tools/testing/selftests/net/fdb_flush.sh +++ b/tools/testing/selftests/net/fdb_flush.sh @@ -583,7 +583,7 @@ vxlan_test_flush_by_remote_attributes() $IP link del dev vx10 $IP link add name vx10 type vxlan dstport "$VXPORT" external - # For multicat FDB entries, the VXLAN driver stores a linked list of + # For multicast FDB entries, the VXLAN driver stores a linked list of # remotes for a given key. Verify that only the expected remotes are # flushed. multicast_fdb_entries_add diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index 77c83d9508d3..bea1282e0281 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -741,7 +741,7 @@ ipv6_fcnal() run_cmd "$IP nexthop add id 52 via 2001:db8:92::3" log_test $? 2 "Create nexthop - gw only" - # gw is not reachable throught given dev + # gw is not reachable through given dev run_cmd "$IP nexthop add id 53 via 2001:db8:3::3 dev veth1" log_test $? 2 "Create nexthop - invalid gw+dev combination" diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh index 847936363a12..06c51d7ceb4a 100755 --- a/tools/testing/selftests/net/fib_rule_tests.sh +++ b/tools/testing/selftests/net/fib_rule_tests.sh @@ -256,6 +256,24 @@ fib_rule6_test() fib_rule6_test_match_n_redirect "$match" "$match" \ "$getnomatch" "sport and dport redirect to table" \ "sport and dport no redirect to table" + + match="sport 100-200 dport 300-400" + getmatch="sport 100 dport 400" + getnomatch="sport 100 dport 401" + fib_rule6_test_match_n_redirect "$match" "$getmatch" \ + "$getnomatch" \ + "sport and dport range redirect to table" \ + "sport and dport range no redirect to table" + fi + + ip rule help 2>&1 | grep sport | grep -q MASK + if [ $? -eq 0 ]; then + match="sport 0x0f00/0xff00 dport 0x000f/0x00ff" + getmatch="sport 0x0f11 dport 0x220f" + getnomatch="sport 0x1f11 dport 0x221f" + fib_rule6_test_match_n_redirect "$match" "$getmatch" \ + "$getnomatch" "sport and dport masked redirect to table" \ + "sport and dport masked no redirect to table" fi fib_check_iproute_support "ipproto" "ipproto" @@ -525,6 +543,24 @@ fib_rule4_test() fib_rule4_test_match_n_redirect "$match" "$match" \ "$getnomatch" "sport and dport redirect to table" \ "sport and dport no redirect to table" + + match="sport 100-200 dport 300-400" + getmatch="sport 100 dport 400" + getnomatch="sport 100 dport 401" + fib_rule4_test_match_n_redirect "$match" "$getmatch" \ + "$getnomatch" \ + "sport and dport range redirect to table" \ + "sport and dport range no redirect to table" + fi + + ip rule help 2>&1 | grep sport | grep -q MASK + if [ $? -eq 0 ]; then + match="sport 0x0f00/0xff00 dport 0x000f/0x00ff" + getmatch="sport 0x0f11 dport 0x220f" + getnomatch="sport 0x1f11 dport 0x221f" + fib_rule4_test_match_n_redirect "$match" "$getmatch" \ + "$getnomatch" "sport and dport masked redirect to table" \ + "sport and dport masked no redirect to table" fi fib_check_iproute_support "ipproto" "ipproto" diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 8de80acf249e..508f3c700d71 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -291,16 +291,6 @@ if [[ "$CHECK_TC" = "yes" ]]; then check_tc_version fi -require_command() -{ - local cmd=$1; shift - - if [[ ! -x "$(command -v "$cmd")" ]]; then - echo "SKIP: $cmd not installed" - exit $ksft_skip - fi -} - # IPv6 support was added in v3.0 check_mtools_version() { diff --git a/tools/testing/selftests/net/forwarding/tc_flower_port_range.sh b/tools/testing/selftests/net/forwarding/tc_flower_port_range.sh index 3885a2a91f7d..baed5e380dae 100755 --- a/tools/testing/selftests/net/forwarding/tc_flower_port_range.sh +++ b/tools/testing/selftests/net/forwarding/tc_flower_port_range.sh @@ -20,6 +20,7 @@ ALL_TESTS=" test_port_range_ipv4_tcp test_port_range_ipv6_udp test_port_range_ipv6_tcp + test_port_range_ipv4_udp_drop " NUM_NETIFS=4 @@ -194,6 +195,51 @@ test_port_range_ipv6_tcp() __test_port_range $proto $ip_proto $sip $dip $mode "$name" } +test_port_range_ipv4_udp_drop() +{ + local proto=ipv4 + local ip_proto=udp + local sip=192.0.2.1 + local dip=192.0.2.2 + local mode="-4" + local name="IPv4 UDP Drop" + local dmac=$(mac_get $h2) + local smac=$(mac_get $h1) + local sport_min=2000 + local sport_max=3000 + local sport_mid=$((sport_min + (sport_max - sport_min) / 2)) + local dport=5000 + + RET=0 + + tc filter add dev $swp1 ingress protocol $proto handle 101 pref 1 \ + flower src_ip $sip dst_ip $dip ip_proto $ip_proto \ + src_port $sport_min-$sport_max \ + dst_port $dport \ + action drop + + # Test ports outside range - should pass + $MZ $mode $h1 -c 1 -q -p 100 -a $smac -b $dmac -A $sip -B $dip \ + -t $ip_proto "sp=$((sport_min - 1)),dp=$dport" + $MZ $mode $h1 -c 1 -q -p 100 -a $smac -b $dmac -A $sip -B $dip \ + -t $ip_proto "sp=$((sport_max + 1)),dp=$dport" + + # Test ports inside range - should be dropped + $MZ $mode $h1 -c 1 -q -p 100 -a $smac -b $dmac -A $sip -B $dip \ + -t $ip_proto "sp=$sport_min,dp=$dport" + $MZ $mode $h1 -c 1 -q -p 100 -a $smac -b $dmac -A $sip -B $dip \ + -t $ip_proto "sp=$sport_mid,dp=$dport" + $MZ $mode $h1 -c 1 -q -p 100 -a $smac -b $dmac -A $sip -B $dip \ + -t $ip_proto "sp=$sport_max,dp=$dport" + + tc_check_packets "dev $swp1 ingress" 101 3 + check_err $? "Filter did not drop the expected number of packets" + + tc filter del dev $swp1 ingress protocol $proto pref 1 handle 101 flower + + log_test "Port range matching - $name" +} + setup_prepare() { h1=${NETIFS[p1]} diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index 0bd9a038a1f0..975be4fdbcdb 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -450,6 +450,25 @@ kill_process() { kill $pid && wait $pid; } 2>/dev/null } +check_command() +{ + local cmd=$1; shift + + if [[ ! -x "$(command -v "$cmd")" ]]; then + log_test_skip "$cmd not installed" + return $EXIT_STATUS + fi +} + +require_command() +{ + local cmd=$1; shift + + if ! check_command "$cmd"; then + exit $EXIT_STATUS + fi +} + ip_link_add() { local name=$1; shift diff --git a/tools/testing/selftests/net/lib/py/__init__.py b/tools/testing/selftests/net/lib/py/__init__.py index 729457859316..8697bd27dc30 100644 --- a/tools/testing/selftests/net/lib/py/__init__.py +++ b/tools/testing/selftests/net/lib/py/__init__.py @@ -2,7 +2,7 @@ from .consts import KSRC from .ksft import * -from .netns import NetNS +from .netns import NetNS, NetNSEnter from .nsim import * from .utils import * from .ynl import NlError, YnlFamily, EthtoolFamily, NetdevFamily, RtnlFamily, RtnlAddrFamily diff --git a/tools/testing/selftests/net/lib/py/ksft.py b/tools/testing/selftests/net/lib/py/ksft.py index 3efe005436cd..fd23349fa8ca 100644 --- a/tools/testing/selftests/net/lib/py/ksft.py +++ b/tools/testing/selftests/net/lib/py/ksft.py @@ -71,6 +71,11 @@ def ksft_in(a, b, comment=""): _fail("Check failed", a, "not in", b, comment) +def ksft_not_in(a, b, comment=""): + if a in b: + _fail("Check failed", a, "in", b, comment) + + def ksft_is(a, b, comment=""): if a is not b: _fail("Check failed", a, "is not", b, comment) diff --git a/tools/testing/selftests/net/lib/py/netns.py b/tools/testing/selftests/net/lib/py/netns.py index ecff85f9074f..8e9317044eef 100644 --- a/tools/testing/selftests/net/lib/py/netns.py +++ b/tools/testing/selftests/net/lib/py/netns.py @@ -1,9 +1,12 @@ # SPDX-License-Identifier: GPL-2.0 from .utils import ip +import ctypes import random import string +libc = ctypes.cdll.LoadLibrary('libc.so.6') + class NetNS: def __init__(self, name=None): @@ -29,3 +32,18 @@ class NetNS: def __repr__(self): return f"NetNS({self.name})" + + +class NetNSEnter: + def __init__(self, ns_name): + self.ns_path = f"/run/netns/{ns_name}" + + def __enter__(self): + self.saved = open("/proc/thread-self/ns/net") + with open(self.ns_path) as ns_file: + libc.setns(ns_file.fileno(), 0) + return self + + def __exit__(self, exc_type, exc_value, traceback): + libc.setns(self.saved.fileno(), 0) + self.saved.close() diff --git a/tools/testing/selftests/net/lib/py/utils.py b/tools/testing/selftests/net/lib/py/utils.py index 9e3bcddcf3e8..d879700ef2b9 100644 --- a/tools/testing/selftests/net/lib/py/utils.py +++ b/tools/testing/selftests/net/lib/py/utils.py @@ -2,8 +2,10 @@ import errno import json as _json +import os import random import re +import select import socket import subprocess import time @@ -15,21 +17,56 @@ class CmdExitFailure(Exception): self.cmd = cmd_obj +def fd_read_timeout(fd, timeout): + rlist, _, _ = select.select([fd], [], [], timeout) + if rlist: + return os.read(fd, 1024) + else: + raise TimeoutError("Timeout waiting for fd read") + + class cmd: - def __init__(self, comm, shell=True, fail=True, ns=None, background=False, host=None, timeout=5): + """ + Execute a command on local or remote host. + + Use bkg() instead to run a command in the background. + """ + def __init__(self, comm, shell=True, fail=True, ns=None, background=False, + host=None, timeout=5, ksft_wait=None): if ns: comm = f'ip netns exec {ns} ' + comm self.stdout = None self.stderr = None self.ret = None + self.ksft_term_fd = None self.comm = comm if host: self.proc = host.cmd(comm) else: + # ksft_wait lets us wait for the background process to fully start, + # we pass an FD to the child process, and wait for it to write back. + # Similarly term_fd tells child it's time to exit. + pass_fds = () + env = os.environ.copy() + if ksft_wait is not None: + rfd, ready_fd = os.pipe() + wait_fd, self.ksft_term_fd = os.pipe() + pass_fds = (ready_fd, wait_fd, ) + env["KSFT_READY_FD"] = str(ready_fd) + env["KSFT_WAIT_FD"] = str(wait_fd) + self.proc = subprocess.Popen(comm, shell=shell, stdout=subprocess.PIPE, - stderr=subprocess.PIPE) + stderr=subprocess.PIPE, pass_fds=pass_fds, + env=env) + if ksft_wait is not None: + os.close(ready_fd) + os.close(wait_fd) + msg = fd_read_timeout(rfd, ksft_wait) + os.close(rfd) + if not msg: + raise Exception("Did not receive ready message") if not background: self.process(terminate=False, fail=fail, timeout=timeout) @@ -37,6 +74,8 @@ class cmd: if fail is None: fail = not terminate + if self.ksft_term_fd: + os.write(self.ksft_term_fd, b"1") if terminate: self.proc.terminate() stdout, stderr = self.proc.communicate(timeout) @@ -54,13 +93,36 @@ class cmd: class bkg(cmd): + """ + Run a command in the background. + + Examples usage: + + Run a command on remote host, and wait for it to finish. + This is usually paired with wait_port_listen() to make sure + the command has initialized: + + with bkg("socat ...", exit_wait=True, host=cfg.remote) as nc: + ... + + Run a command and expect it to let us know that it's ready + by writing to a special file descriptor passed via KSFT_READY_FD. + Command will be terminated when we exit the context manager: + + with bkg("my_binary", ksft_wait=5): + """ def __init__(self, comm, shell=True, fail=None, ns=None, host=None, - exit_wait=False): + exit_wait=False, ksft_wait=None): super().__init__(comm, background=True, - shell=shell, fail=fail, ns=ns, host=host) - self.terminate = not exit_wait + shell=shell, fail=fail, ns=ns, host=host, + ksft_wait=ksft_wait) + self.terminate = not exit_wait and not ksft_wait self.check_fail = fail + if shell and self.terminate: + print("# Warning: combining shell and terminate is risky!") + print("# SIGTERM may not reach the child on zsh/ksh!") + def __enter__(self): return self diff --git a/tools/testing/selftests/net/link_netns.py b/tools/testing/selftests/net/link_netns.py new file mode 100755 index 000000000000..aab043c59d69 --- /dev/null +++ b/tools/testing/selftests/net/link_netns.py @@ -0,0 +1,141 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +import time + +from lib.py import ksft_run, ksft_exit, ksft_true +from lib.py import ip +from lib.py import NetNS, NetNSEnter +from lib.py import RtnlFamily + + +LINK_NETNSID = 100 + + +def test_event() -> None: + with NetNS() as ns1, NetNS() as ns2: + with NetNSEnter(str(ns2)): + rtnl = RtnlFamily() + + rtnl.ntf_subscribe("rtnlgrp-link") + + ip(f"netns set {ns2} {LINK_NETNSID}", ns=str(ns1)) + ip(f"link add netns {ns1} link-netnsid {LINK_NETNSID} dummy1 type dummy") + ip(f"link add netns {ns1} dummy2 type dummy", ns=str(ns2)) + + ip("link del dummy1", ns=str(ns1)) + ip("link del dummy2", ns=str(ns1)) + + time.sleep(1) + rtnl.check_ntf() + ksft_true(rtnl.async_msg_queue.empty(), + "Received unexpected link notification") + + +def validate_link_netns(netns, ifname, link_netnsid) -> bool: + link_info = ip(f"-d link show dev {ifname}", ns=netns, json=True) + if not link_info: + return False + return link_info[0].get("link_netnsid") == link_netnsid + + +def test_link_net() -> None: + configs = [ + # type, common args, type args, fallback to dev_net + ("ipvlan", "link dummy1", "", False), + ("macsec", "link dummy1", "", False), + ("macvlan", "link dummy1", "", False), + ("macvtap", "link dummy1", "", False), + ("vlan", "link dummy1", "id 100", False), + ("gre", "", "local 192.0.2.1", True), + ("vti", "", "local 192.0.2.1", True), + ("ipip", "", "local 192.0.2.1", True), + ("ip6gre", "", "local 2001:db8::1", True), + ("ip6tnl", "", "local 2001:db8::1", True), + ("vti6", "", "local 2001:db8::1", True), + ("sit", "", "local 192.0.2.1", True), + ("xfrm", "", "if_id 1", True), + ] + + with NetNS() as ns1, NetNS() as ns2, NetNS() as ns3: + net1, net2, net3 = str(ns1), str(ns2), str(ns3) + + # prepare link netnsid and a dummy link needed by certain drivers + ip(f"netns set {net3} {LINK_NETNSID}", ns=str(net2)) + ip("link add dummy1 type dummy", ns=net3) + + cases = [ + # source, "netns", "link-netns", expected link-netns + (net3, None, None, None, None), + (net3, net2, None, None, LINK_NETNSID), + (net2, None, net3, LINK_NETNSID, LINK_NETNSID), + (net1, net2, net3, LINK_NETNSID, LINK_NETNSID), + ] + + for src_net, netns, link_netns, exp1, exp2 in cases: + tgt_net = netns or src_net + for typ, cargs, targs, fb_dev_net in configs: + cmd = "link add" + if netns: + cmd += f" netns {netns}" + if link_netns: + cmd += f" link-netns {link_netns}" + cmd += f" {cargs} foo type {typ} {targs}" + ip(cmd, ns=src_net) + if fb_dev_net: + ksft_true(validate_link_netns(tgt_net, "foo", exp1), + f"{typ} link_netns validation failed") + else: + ksft_true(validate_link_netns(tgt_net, "foo", exp2), + f"{typ} link_netns validation failed") + ip(f"link del foo", ns=tgt_net) + + +def test_peer_net() -> None: + types = [ + "vxcan", + "netkit", + "veth", + ] + + with NetNS() as ns1, NetNS() as ns2, NetNS() as ns3, NetNS() as ns4: + net1, net2, net3, net4 = str(ns1), str(ns2), str(ns3), str(ns4) + + ip(f"netns set {net3} {LINK_NETNSID}", ns=str(net2)) + + cases = [ + # source, "netns", "link-netns", "peer netns", expected + (net1, None, None, None, None), + (net1, net2, None, None, None), + (net2, None, net3, None, LINK_NETNSID), + (net1, net2, net3, None, None), + (net2, None, None, net3, LINK_NETNSID), + (net1, net2, None, net3, LINK_NETNSID), + (net2, None, net2, net3, LINK_NETNSID), + (net1, net2, net4, net3, LINK_NETNSID), + ] + + for src_net, netns, link_netns, peer_netns, exp in cases: + tgt_net = netns or src_net + for typ in types: + cmd = "link add" + if netns: + cmd += f" netns {netns}" + if link_netns: + cmd += f" link-netns {link_netns}" + cmd += f" foo type {typ}" + if peer_netns: + cmd += f" peer netns {peer_netns}" + ip(cmd, ns=src_net) + ksft_true(validate_link_netns(tgt_net, "foo", exp), + f"{typ} peer_netns validation failed") + ip(f"link del foo", ns=tgt_net) + + +def main() -> None: + ksft_run([test_event, test_link_net, test_peer_net]) + ksft_exit() + + +if __name__ == "__main__": + main() diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh index 9c2a415976cb..2329c2f8519b 100755 --- a/tools/testing/selftests/net/mptcp/simult_flows.sh +++ b/tools/testing/selftests/net/mptcp/simult_flows.sh @@ -28,7 +28,7 @@ size=0 usage() { echo "Usage: $0 [ -b ] [ -c ] [ -d ] [ -i]" - echo -e "\t-b: bail out after first error, otherwise runs al testcases" + echo -e "\t-b: bail out after first error, otherwise runs all testcases" echo -e "\t-c: capture packets for each test using tcpdump (default: no capture)" echo -e "\t-d: debug this script" echo -e "\t-i: use 'ip mptcp' instead of 'pm_nl_ctl'" diff --git a/tools/testing/selftests/net/netns-name.sh b/tools/testing/selftests/net/netns-name.sh index 6974474c26f3..0be1905d1f2f 100755 --- a/tools/testing/selftests/net/netns-name.sh +++ b/tools/testing/selftests/net/netns-name.sh @@ -78,6 +78,16 @@ ip -netns $NS link show dev $ALT_NAME 2> /dev/null && fail "Can still find alt-name after move" ip -netns $test_ns link del $DEV || fail +# +# Test no conflict of the same name/ifindex in different netns +# +ip -netns $NS link add name $DEV index 100 type dummy || fail +ip -netns $NS link add netns $test_ns name $DEV index 100 type dummy || + fail "Can create in netns without moving" +ip -netns $test_ns link show dev $DEV >> /dev/null || fail "Device not found" +ip -netns $NS link del $DEV || fail +ip -netns $test_ns link del $DEV || fail + echo -ne "$(basename $0) \t\t\t\t" if [ $RET_CODE -eq 0 ]; then echo "[ OK ]" diff --git a/tools/testing/selftests/net/psock_tpacket.c b/tools/testing/selftests/net/psock_tpacket.c index 404a2ce759ab..221270cee3ea 100644 --- a/tools/testing/selftests/net/psock_tpacket.c +++ b/tools/testing/selftests/net/psock_tpacket.c @@ -12,7 +12,7 @@ * * Datapath: * Open a pair of packet sockets and send resp. receive an a priori known - * packet pattern accross the sockets and check if it was received resp. + * packet pattern across the sockets and check if it was received resp. * sent correctly. Fanout in combination with RX_RING is currently not * tested here. * diff --git a/tools/testing/selftests/net/reuseaddr_ports_exhausted.c b/tools/testing/selftests/net/reuseaddr_ports_exhausted.c index 066efd30e294..7b9bf8a7bbe1 100644 --- a/tools/testing/selftests/net/reuseaddr_ports_exhausted.c +++ b/tools/testing/selftests/net/reuseaddr_ports_exhausted.c @@ -112,7 +112,7 @@ TEST(reuseaddr_ports_exhausted_reusable_same_euid) ASSERT_NE(-1, fd[0]) TH_LOG("failed to bind."); if (opts->reuseport[0] && opts->reuseport[1]) { - EXPECT_EQ(-1, fd[1]) TH_LOG("should fail to bind because both sockets succeed to be listened."); + EXPECT_EQ(-1, fd[1]) TH_LOG("should fail to bind because both sockets successfully listened."); } else { EXPECT_NE(-1, fd[1]) TH_LOG("should succeed to bind to connect to different destinations."); } diff --git a/tools/testing/selftests/net/so_rcv_listener.c b/tools/testing/selftests/net/so_rcv_listener.c new file mode 100644 index 000000000000..bc5841192aa6 --- /dev/null +++ b/tools/testing/selftests/net/so_rcv_listener.c @@ -0,0 +1,168 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <errno.h> +#include <netdb.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <linux/types.h> +#include <sys/socket.h> +#include <netinet/in.h> +#include <arpa/inet.h> + +#ifndef SO_RCVPRIORITY +#define SO_RCVPRIORITY 82 +#endif + +struct options { + __u32 val; + int name; + int rcvname; + const char *host; + const char *service; +} opt; + +static void __attribute__((noreturn)) usage(const char *bin) +{ + printf("Usage: %s [opts] <dst host> <dst port / service>\n", bin); + printf("Options:\n" + "\t\t-M val Test SO_RCVMARK\n" + "\t\t-P val Test SO_RCVPRIORITY\n" + ""); + exit(EXIT_FAILURE); +} + +static void parse_args(int argc, char *argv[]) +{ + int o; + + while ((o = getopt(argc, argv, "M:P:")) != -1) { + switch (o) { + case 'M': + opt.val = atoi(optarg); + opt.name = SO_MARK; + opt.rcvname = SO_RCVMARK; + break; + case 'P': + opt.val = atoi(optarg); + opt.name = SO_PRIORITY; + opt.rcvname = SO_RCVPRIORITY; + break; + default: + usage(argv[0]); + break; + } + } + + if (optind != argc - 2) + usage(argv[0]); + + opt.host = argv[optind]; + opt.service = argv[optind + 1]; +} + +int main(int argc, char *argv[]) +{ + int err = 0; + int recv_fd = -1; + int ret_value = 0; + __u32 recv_val; + struct cmsghdr *cmsg; + char cbuf[CMSG_SPACE(sizeof(__u32))]; + char recv_buf[CMSG_SPACE(sizeof(__u32))]; + struct iovec iov[1]; + struct msghdr msg; + struct sockaddr_in recv_addr4; + struct sockaddr_in6 recv_addr6; + + parse_args(argc, argv); + + int family = strchr(opt.host, ':') ? AF_INET6 : AF_INET; + + recv_fd = socket(family, SOCK_DGRAM, IPPROTO_UDP); + if (recv_fd < 0) { + perror("Can't open recv socket"); + ret_value = -errno; + goto cleanup; + } + + err = setsockopt(recv_fd, SOL_SOCKET, opt.rcvname, &opt.val, sizeof(opt.val)); + if (err < 0) { + perror("Recv setsockopt error"); + ret_value = -errno; + goto cleanup; + } + + if (family == AF_INET) { + memset(&recv_addr4, 0, sizeof(recv_addr4)); + recv_addr4.sin_family = family; + recv_addr4.sin_port = htons(atoi(opt.service)); + + if (inet_pton(family, opt.host, &recv_addr4.sin_addr) <= 0) { + perror("Invalid IPV4 address"); + ret_value = -errno; + goto cleanup; + } + + err = bind(recv_fd, (struct sockaddr *)&recv_addr4, sizeof(recv_addr4)); + } else { + memset(&recv_addr6, 0, sizeof(recv_addr6)); + recv_addr6.sin6_family = family; + recv_addr6.sin6_port = htons(atoi(opt.service)); + + if (inet_pton(family, opt.host, &recv_addr6.sin6_addr) <= 0) { + perror("Invalid IPV6 address"); + ret_value = -errno; + goto cleanup; + } + + err = bind(recv_fd, (struct sockaddr *)&recv_addr6, sizeof(recv_addr6)); + } + + if (err < 0) { + perror("Recv bind error"); + ret_value = -errno; + goto cleanup; + } + + iov[0].iov_base = recv_buf; + iov[0].iov_len = sizeof(recv_buf); + + memset(&msg, 0, sizeof(msg)); + msg.msg_iov = iov; + msg.msg_iovlen = 1; + msg.msg_control = cbuf; + msg.msg_controllen = sizeof(cbuf); + + err = recvmsg(recv_fd, &msg, 0); + if (err < 0) { + perror("Message receive error"); + ret_value = -errno; + goto cleanup; + } + + for (cmsg = CMSG_FIRSTHDR(&msg); cmsg != NULL; cmsg = CMSG_NXTHDR(&msg, cmsg)) { + if (cmsg->cmsg_level == SOL_SOCKET && cmsg->cmsg_type == opt.name) { + recv_val = *(__u32 *)CMSG_DATA(cmsg); + printf("Received value: %u\n", recv_val); + + if (recv_val != opt.val) { + fprintf(stderr, "Error: expected value: %u, got: %u\n", + opt.val, recv_val); + ret_value = -EINVAL; + } + goto cleanup; + } + } + + fprintf(stderr, "Error: No matching cmsg received\n"); + ret_value = -ENOMSG; + +cleanup: + if (recv_fd >= 0) + close(recv_fd); + + return ret_value; +} diff --git a/tools/testing/selftests/net/test_so_rcv.sh b/tools/testing/selftests/net/test_so_rcv.sh new file mode 100755 index 000000000000..d8aa4362879d --- /dev/null +++ b/tools/testing/selftests/net/test_so_rcv.sh @@ -0,0 +1,73 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source lib.sh + +HOSTS=("127.0.0.1" "::1") +PORT=1234 +TOTAL_TESTS=0 +FAILED_TESTS=0 + +declare -A TESTS=( + ["SO_RCVPRIORITY"]="-P 2" + ["SO_RCVMARK"]="-M 3" +) + +check_result() { + ((TOTAL_TESTS++)) + if [ "$1" -ne 0 ]; then + ((FAILED_TESTS++)) + fi +} + +cleanup() +{ + cleanup_ns $NS +} + +trap cleanup EXIT + +setup_ns NS + +for HOST in "${HOSTS[@]}"; do + PROTOCOL="IPv4" + if [[ "$HOST" == "::1" ]]; then + PROTOCOL="IPv6" + fi + for test_name in "${!TESTS[@]}"; do + echo "Running $test_name test, $PROTOCOL" + arg=${TESTS[$test_name]} + + ip netns exec $NS ./so_rcv_listener $arg $HOST $PORT & + LISTENER_PID=$! + + sleep 0.5 + + if ! ip netns exec $NS ./cmsg_sender $arg $HOST $PORT; then + echo "Sender failed for $test_name, $PROTOCOL" + kill "$LISTENER_PID" 2>/dev/null + wait "$LISTENER_PID" + check_result 1 + continue + fi + + wait "$LISTENER_PID" + LISTENER_EXIT_CODE=$? + + if [ "$LISTENER_EXIT_CODE" -eq 0 ]; then + echo "Rcv test OK for $test_name, $PROTOCOL" + check_result 0 + else + echo "Rcv test FAILED for $test_name, $PROTOCOL" + check_result 1 + fi + done +done + +if [ "$FAILED_TESTS" -ne 0 ]; then + echo "FAIL - $FAILED_TESTS/$TOTAL_TESTS tests failed" + exit ${KSFT_FAIL} +else + echo "OK - All $TOTAL_TESTS tests passed" + exit ${KSFT_PASS} +fi diff --git a/tools/testing/selftests/net/test_vxlan_fdb_changelink.sh b/tools/testing/selftests/net/test_vxlan_fdb_changelink.sh index 2d442cdab11e..062f957950af 100755 --- a/tools/testing/selftests/net/test_vxlan_fdb_changelink.sh +++ b/tools/testing/selftests/net/test_vxlan_fdb_changelink.sh @@ -1,29 +1,114 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 -# Check FDB default-remote handling across "ip link set". +ALL_TESTS=" + test_set_remote + test_change_mc_remote +" +source lib.sh check_remotes() { local what=$1; shift local N=$(bridge fdb sh dev vx | grep 00:00:00:00:00:00 | wc -l) - echo -ne "expected two remotes after $what\t" - if [[ $N != 2 ]]; then - echo "[FAIL]" - EXIT_STATUS=1 + ((N == 2)) + check_err $? "expected 2 remotes after $what, got $N" +} + +# Check FDB default-remote handling across "ip link set". +test_set_remote() +{ + RET=0 + + ip_link_add vx up type vxlan id 2000 dstport 4789 + bridge fdb ap dev vx 00:00:00:00:00:00 dst 192.0.2.20 self permanent + bridge fdb ap dev vx 00:00:00:00:00:00 dst 192.0.2.30 self permanent + check_remotes "fdb append" + + ip link set dev vx type vxlan remote 192.0.2.30 + check_remotes "link set" + + log_test 'FDB default-remote handling across "ip link set"' +} + +fmt_remote() +{ + local addr=$1; shift + + if [[ $addr == 224.* ]]; then + echo "group $addr" else - echo "[ OK ]" + echo "remote $addr" fi } -ip link add name vx up type vxlan id 2000 dstport 4789 -bridge fdb ap dev vx 00:00:00:00:00:00 dst 192.0.2.20 self permanent -bridge fdb ap dev vx 00:00:00:00:00:00 dst 192.0.2.30 self permanent -check_remotes "fdb append" +change_remote() +{ + local remote=$1; shift + + ip link set dev vx type vxlan $(fmt_remote $remote) dev v1 +} + +check_membership() +{ + local check_vec=("$@") + + local memberships + memberships=$( + netstat -n --groups | + sed -n '/^v1\b/p' | + grep -o '[^ ]*$' + ) + check_err $? "Couldn't obtain group memberships" + + local item + for item in "${check_vec[@]}"; do + eval "local $item" + echo "$memberships" | grep -q "\b$group\b" + check_err_fail $fail $? "$group is_ex reported in IGMP query response" + done +} + +test_change_mc_remote() +{ + check_command netstat || return + + ip_link_add v1 up type veth peer name v2 + ip_link_set_up v2 + + RET=0 + + ip_link_add vx up type vxlan dstport 4789 \ + local 192.0.2.1 $(fmt_remote 224.1.1.1) dev v1 vni 1000 + + check_membership "group=224.1.1.1 fail=0" \ + "group=224.1.1.2 fail=1" \ + "group=224.1.1.3 fail=1" + + log_test "MC group report after VXLAN creation" + + RET=0 + + change_remote 224.1.1.2 + check_membership "group=224.1.1.1 fail=1" \ + "group=224.1.1.2 fail=0" \ + "group=224.1.1.3 fail=1" + + log_test "MC group report after changing VXLAN remote MC->MC" + + RET=0 + + change_remote 192.0.2.2 + check_membership "group=224.1.1.1 fail=1" \ + "group=224.1.1.2 fail=1" \ + "group=224.1.1.3 fail=1" + + log_test "MC group report after changing VXLAN remote MC->UC" +} + +trap defer_scopes_cleanup EXIT -ip link set dev vx type vxlan remote 192.0.2.30 -check_remotes "link set" +tests_run -ip link del dev vx exit $EXIT_STATUS diff --git a/tools/testing/selftests/sched_ext/create_dsq.c b/tools/testing/selftests/sched_ext/create_dsq.c index fa946d9146d4..d67431f57ac6 100644 --- a/tools/testing/selftests/sched_ext/create_dsq.c +++ b/tools/testing/selftests/sched_ext/create_dsq.c @@ -14,11 +14,11 @@ static enum scx_test_status setup(void **ctx) { struct create_dsq *skel; - skel = create_dsq__open_and_load(); - if (!skel) { - SCX_ERR("Failed to open and load skel"); - return SCX_TEST_FAIL; - } + skel = create_dsq__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(create_dsq__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.c b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.c index e65d22f23f3b..b6d13496b24e 100644 --- a/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.c +++ b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.c @@ -15,8 +15,11 @@ static enum scx_test_status setup(void **ctx) { struct ddsp_bogus_dsq_fail *skel; - skel = ddsp_bogus_dsq_fail__open_and_load(); - SCX_FAIL_IF(!skel, "Failed to open and load skel"); + skel = ddsp_bogus_dsq_fail__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(ddsp_bogus_dsq_fail__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.c b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.c index abafee587cd6..af9ce4ee8baa 100644 --- a/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.c +++ b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.c @@ -14,8 +14,11 @@ static enum scx_test_status setup(void **ctx) { struct ddsp_vtimelocal_fail *skel; - skel = ddsp_vtimelocal_fail__open_and_load(); - SCX_FAIL_IF(!skel, "Failed to open and load skel"); + skel = ddsp_vtimelocal_fail__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(ddsp_vtimelocal_fail__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c index fbda6bf54671..c02b2aa6fc64 100644 --- a/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c +++ b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c @@ -43,7 +43,7 @@ void BPF_STRUCT_OPS(dsp_local_on_dispatch, s32 cpu, struct task_struct *prev) if (!p) return; - if (p->nr_cpus_allowed == nr_cpus) + if (p->nr_cpus_allowed == nr_cpus && !is_migration_disabled(p)) target = bpf_get_prandom_u32() % nr_cpus; else target = scx_bpf_task_cpu(p); diff --git a/tools/testing/selftests/sched_ext/dsp_local_on.c b/tools/testing/selftests/sched_ext/dsp_local_on.c index 0ff27e57fe43..e1f2ce4abfe6 100644 --- a/tools/testing/selftests/sched_ext/dsp_local_on.c +++ b/tools/testing/selftests/sched_ext/dsp_local_on.c @@ -15,6 +15,7 @@ static enum scx_test_status setup(void **ctx) skel = dsp_local_on__open(); SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); skel->rodata->nr_cpus = libbpf_num_possible_cpus(); SCX_FAIL_IF(dsp_local_on__load(skel), "Failed to load skel"); diff --git a/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.c b/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.c index 73e679953e27..d3387ae03679 100644 --- a/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.c +++ b/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.c @@ -15,11 +15,11 @@ static enum scx_test_status setup(void **ctx) { struct enq_last_no_enq_fails *skel; - skel = enq_last_no_enq_fails__open_and_load(); - if (!skel) { - SCX_ERR("Failed to open and load skel"); - return SCX_TEST_FAIL; - } + skel = enq_last_no_enq_fails__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(enq_last_no_enq_fails__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/enq_select_cpu_fails.c b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.c index dd1350e5f002..a80e3a3b3698 100644 --- a/tools/testing/selftests/sched_ext/enq_select_cpu_fails.c +++ b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.c @@ -15,11 +15,11 @@ static enum scx_test_status setup(void **ctx) { struct enq_select_cpu_fails *skel; - skel = enq_select_cpu_fails__open_and_load(); - if (!skel) { - SCX_ERR("Failed to open and load skel"); - return SCX_TEST_FAIL; - } + skel = enq_select_cpu_fails__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(enq_select_cpu_fails__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/exit.c b/tools/testing/selftests/sched_ext/exit.c index 31bcd06e21cd..9451782689de 100644 --- a/tools/testing/selftests/sched_ext/exit.c +++ b/tools/testing/selftests/sched_ext/exit.c @@ -23,6 +23,7 @@ static enum scx_test_status run(void *ctx) char buf[16]; skel = exit__open(); + SCX_ENUM_INIT(skel); skel->rodata->exit_point = tc; exit__load(skel); link = bpf_map__attach_struct_ops(skel->maps.exit_ops); diff --git a/tools/testing/selftests/sched_ext/hotplug.c b/tools/testing/selftests/sched_ext/hotplug.c index 87bf220b1bce..1c9ceb661c43 100644 --- a/tools/testing/selftests/sched_ext/hotplug.c +++ b/tools/testing/selftests/sched_ext/hotplug.c @@ -49,8 +49,10 @@ static enum scx_test_status test_hotplug(bool onlining, bool cbs_defined) SCX_ASSERT(is_cpu_online()); - skel = hotplug__open_and_load(); - SCX_ASSERT(skel); + skel = hotplug__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(hotplug__load(skel), "Failed to load skel"); /* Testing the offline -> online path, so go offline before starting */ if (onlining) diff --git a/tools/testing/selftests/sched_ext/init_enable_count.c b/tools/testing/selftests/sched_ext/init_enable_count.c index 97d45f1e5597..eddf9e0e26e7 100644 --- a/tools/testing/selftests/sched_ext/init_enable_count.c +++ b/tools/testing/selftests/sched_ext/init_enable_count.c @@ -15,22 +15,6 @@ #define SCHED_EXT 7 -static struct init_enable_count * -open_load_prog(bool global) -{ - struct init_enable_count *skel; - - skel = init_enable_count__open(); - SCX_BUG_ON(!skel, "Failed to open skel"); - - if (!global) - skel->struct_ops.init_enable_count_ops->flags |= SCX_OPS_SWITCH_PARTIAL; - - SCX_BUG_ON(init_enable_count__load(skel), "Failed to load skel"); - - return skel; -} - static enum scx_test_status run_test(bool global) { struct init_enable_count *skel; @@ -40,7 +24,14 @@ static enum scx_test_status run_test(bool global) struct sched_param param = {}; pid_t pids[num_pre_forks]; - skel = open_load_prog(global); + skel = init_enable_count__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + + if (!global) + skel->struct_ops.init_enable_count_ops->flags |= SCX_OPS_SWITCH_PARTIAL; + + SCX_FAIL_IF(init_enable_count__load(skel), "Failed to load skel"); /* * Fork a bunch of children before we attach the scheduler so that we @@ -159,7 +150,7 @@ static enum scx_test_status run(void *ctx) struct scx_test init_enable_count = { .name = "init_enable_count", - .description = "Verify we do the correct amount of counting of init, " + .description = "Verify we correctly count the occurrences of init, " "enable, etc callbacks.", .run = run, }; diff --git a/tools/testing/selftests/sched_ext/maximal.c b/tools/testing/selftests/sched_ext/maximal.c index f38fc973c380..c6be50a9941d 100644 --- a/tools/testing/selftests/sched_ext/maximal.c +++ b/tools/testing/selftests/sched_ext/maximal.c @@ -14,8 +14,11 @@ static enum scx_test_status setup(void **ctx) { struct maximal *skel; - skel = maximal__open_and_load(); - SCX_FAIL_IF(!skel, "Failed to open and load skel"); + skel = maximal__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(maximal__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/maybe_null.c b/tools/testing/selftests/sched_ext/maybe_null.c index 31cfafb0cf65..aacf0c58ca4f 100644 --- a/tools/testing/selftests/sched_ext/maybe_null.c +++ b/tools/testing/selftests/sched_ext/maybe_null.c @@ -43,7 +43,7 @@ static enum scx_test_status run(void *ctx) struct scx_test maybe_null = { .name = "maybe_null", - .description = "Verify if PTR_MAYBE_NULL work for .dispatch", + .description = "Verify if PTR_MAYBE_NULL works for .dispatch", .run = run, }; REGISTER_SCX_TEST(&maybe_null) diff --git a/tools/testing/selftests/sched_ext/minimal.c b/tools/testing/selftests/sched_ext/minimal.c index 6c5db8ebbf8a..89f7261757ff 100644 --- a/tools/testing/selftests/sched_ext/minimal.c +++ b/tools/testing/selftests/sched_ext/minimal.c @@ -15,11 +15,11 @@ static enum scx_test_status setup(void **ctx) { struct minimal *skel; - skel = minimal__open_and_load(); - if (!skel) { - SCX_ERR("Failed to open and load skel"); - return SCX_TEST_FAIL; - } + skel = minimal__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(minimal__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/prog_run.c b/tools/testing/selftests/sched_ext/prog_run.c index 3cd57ef8daaa..05974820ca69 100644 --- a/tools/testing/selftests/sched_ext/prog_run.c +++ b/tools/testing/selftests/sched_ext/prog_run.c @@ -15,11 +15,11 @@ static enum scx_test_status setup(void **ctx) { struct prog_run *skel; - skel = prog_run__open_and_load(); - if (!skel) { - SCX_ERR("Failed to open and load skel"); - return SCX_TEST_FAIL; - } + skel = prog_run__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(prog_run__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/reload_loop.c b/tools/testing/selftests/sched_ext/reload_loop.c index 5cfba2d6e056..308211d80436 100644 --- a/tools/testing/selftests/sched_ext/reload_loop.c +++ b/tools/testing/selftests/sched_ext/reload_loop.c @@ -18,11 +18,10 @@ bool force_exit = false; static enum scx_test_status setup(void **ctx) { - skel = maximal__open_and_load(); - if (!skel) { - SCX_ERR("Failed to open and load skel"); - return SCX_TEST_FAIL; - } + skel = maximal__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(maximal__load(skel), "Failed to load skel"); return SCX_TEST_PASS; } diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl.c b/tools/testing/selftests/sched_ext/select_cpu_dfl.c index a53a40c2d2f0..5b6e045e1109 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dfl.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dfl.c @@ -17,8 +17,11 @@ static enum scx_test_status setup(void **ctx) { struct select_cpu_dfl *skel; - skel = select_cpu_dfl__open_and_load(); - SCX_FAIL_IF(!skel, "Failed to open and load skel"); + skel = select_cpu_dfl__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(select_cpu_dfl__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.c b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.c index 1d85bf4bf3a3..9b5d232efb7f 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.c @@ -17,8 +17,11 @@ static enum scx_test_status setup(void **ctx) { struct select_cpu_dfl_nodispatch *skel; - skel = select_cpu_dfl_nodispatch__open_and_load(); - SCX_FAIL_IF(!skel, "Failed to open and load skel"); + skel = select_cpu_dfl_nodispatch__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(select_cpu_dfl_nodispatch__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch.c index 0309ca8785b3..80283dbc41b7 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dispatch.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch.c @@ -17,8 +17,11 @@ static enum scx_test_status setup(void **ctx) { struct select_cpu_dispatch *skel; - skel = select_cpu_dispatch__open_and_load(); - SCX_FAIL_IF(!skel, "Failed to open and load skel"); + skel = select_cpu_dispatch__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(select_cpu_dispatch__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.c index 47eb6ed7627d..5e72ebbc90a5 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.c @@ -15,8 +15,11 @@ static enum scx_test_status setup(void **ctx) { struct select_cpu_dispatch_bad_dsq *skel; - skel = select_cpu_dispatch_bad_dsq__open_and_load(); - SCX_FAIL_IF(!skel, "Failed to open and load skel"); + skel = select_cpu_dispatch_bad_dsq__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(select_cpu_dispatch_bad_dsq__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.c index 48ff028a3c46..aa85949478bc 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.c @@ -15,8 +15,11 @@ static enum scx_test_status setup(void **ctx) { struct select_cpu_dispatch_dbl_dsp *skel; - skel = select_cpu_dispatch_dbl_dsp__open_and_load(); - SCX_FAIL_IF(!skel, "Failed to open and load skel"); + skel = select_cpu_dispatch_dbl_dsp__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(select_cpu_dispatch_dbl_dsp__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/select_cpu_vtime.c b/tools/testing/selftests/sched_ext/select_cpu_vtime.c index b4629c2364f5..1e9b5c9bfff1 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_vtime.c +++ b/tools/testing/selftests/sched_ext/select_cpu_vtime.c @@ -15,8 +15,11 @@ static enum scx_test_status setup(void **ctx) { struct select_cpu_vtime *skel; - skel = select_cpu_vtime__open_and_load(); - SCX_FAIL_IF(!skel, "Failed to open and load skel"); + skel = select_cpu_vtime__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(select_cpu_vtime__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; |