diff options
679 files changed, 14983 insertions, 5888 deletions
@@ -918,6 +918,11 @@ S: Ottawa, Ontario S: K1N 6Z9 S: CANADA +N: Vivien Didelot +E: vivien.didelot@gmail.com +D: DSA framework and MV88E6XXX driver +S: Montreal, Quebec, Canada + N: Jeff Dike E: jdike@karaya.com W: http://user-mode-linux.sourceforge.net diff --git a/Documentation/arm64/booting.rst b/Documentation/arm64/booting.rst index 8aefa1001ae5..8c324ad638de 100644 --- a/Documentation/arm64/booting.rst +++ b/Documentation/arm64/booting.rst @@ -340,6 +340,14 @@ Before jumping into the kernel, the following conditions must be met: - SMCR_EL2.LEN must be initialised to the same value for all CPUs the kernel will execute on. + - HWFGRTR_EL2.nTPIDR2_EL0 (bit 55) must be initialised to 0b01. + + - HWFGWTR_EL2.nTPIDR2_EL0 (bit 55) must be initialised to 0b01. + + - HWFGRTR_EL2.nSMPRI_EL1 (bit 54) must be initialised to 0b01. + + - HWFGWTR_EL2.nSMPRI_EL1 (bit 54) must be initialised to 0b01. + For CPUs with the Scalable Matrix Extension FA64 feature (FEAT_SME_FA64) - If EL3 is present: diff --git a/Documentation/arm64/cpu-feature-registers.rst b/Documentation/arm64/cpu-feature-registers.rst index 04ba83e1965f..c7adc7897df6 100644 --- a/Documentation/arm64/cpu-feature-registers.rst +++ b/Documentation/arm64/cpu-feature-registers.rst @@ -92,7 +92,7 @@ operation if the source belongs to the supported system register space. The infrastructure emulates only the following system register space:: - Op0=3, Op1=0, CRn=0, CRm=0,4,5,6,7 + Op0=3, Op1=0, CRn=0, CRm=0,2,3,4,5,6,7 (See Table C5-6 'System instruction encodings for non-Debug System register accesses' in ARMv8 ARM DDI 0487A.h, for the list of @@ -293,6 +293,42 @@ infrastructure: | WFXT | [3-0] | y | +------------------------------+---------+---------+ + 10) MVFR0_EL1 - AArch32 Media and VFP Feature Register 0 + + +------------------------------+---------+---------+ + | Name | bits | visible | + +------------------------------+---------+---------+ + | FPDP | [11-8] | y | + +------------------------------+---------+---------+ + + 11) MVFR1_EL1 - AArch32 Media and VFP Feature Register 1 + + +------------------------------+---------+---------+ + | Name | bits | visible | + +------------------------------+---------+---------+ + | SIMDFMAC | [31-28] | y | + +------------------------------+---------+---------+ + | SIMDSP | [19-16] | y | + +------------------------------+---------+---------+ + | SIMDInt | [15-12] | y | + +------------------------------+---------+---------+ + | SIMDLS | [11-8] | y | + +------------------------------+---------+---------+ + + 12) ID_ISAR5_EL1 - AArch32 Instruction Set Attribute Register 5 + + +------------------------------+---------+---------+ + | Name | bits | visible | + +------------------------------+---------+---------+ + | CRC32 | [19-16] | y | + +------------------------------+---------+---------+ + | SHA2 | [15-12] | y | + +------------------------------+---------+---------+ + | SHA1 | [11-8] | y | + +------------------------------+---------+---------+ + | AES | [7-4] | y | + +------------------------------+---------+---------+ + Appendix I: Example ------------------- diff --git a/Documentation/devicetree/bindings/arm/mediatek/mediatek,mt7622-wed.yaml b/Documentation/devicetree/bindings/arm/mediatek/mediatek,mt7622-wed.yaml index 84fb0a146b6e..5c223cb063d4 100644 --- a/Documentation/devicetree/bindings/arm/mediatek/mediatek,mt7622-wed.yaml +++ b/Documentation/devicetree/bindings/arm/mediatek/mediatek,mt7622-wed.yaml @@ -29,6 +29,38 @@ properties: interrupts: maxItems: 1 + memory-region: + items: + - description: firmware EMI region + - description: firmware ILM region + - description: firmware DLM region + - description: firmware CPU DATA region + - description: firmware BOOT region + + memory-region-names: + items: + - const: wo-emi + - const: wo-ilm + - const: wo-dlm + - const: wo-data + - const: wo-boot + + mediatek,wo-ccif: + $ref: /schemas/types.yaml#/definitions/phandle + description: mediatek wed-wo controller interface. + +allOf: + - if: + properties: + compatible: + contains: + const: mediatek,mt7622-wed + then: + properties: + memory-region-names: false + memory-region: false + mediatek,wo-ccif: false + required: - compatible - reg @@ -49,3 +81,23 @@ examples: interrupts = <GIC_SPI 214 IRQ_TYPE_LEVEL_LOW>; }; }; + + - | + #include <dt-bindings/interrupt-controller/arm-gic.h> + #include <dt-bindings/interrupt-controller/irq.h> + soc { + #address-cells = <2>; + #size-cells = <2>; + + wed@15010000 { + compatible = "mediatek,mt7986-wed", "syscon"; + reg = <0 0x15010000 0 0x1000>; + interrupts = <GIC_SPI 205 IRQ_TYPE_LEVEL_HIGH>; + + memory-region = <&wo_emi>, <&wo_ilm>, <&wo_dlm>, + <&wo_data>, <&wo_boot>; + memory-region-names = "wo-emi", "wo-ilm", "wo-dlm", + "wo-data", "wo-boot"; + mediatek,wo-ccif = <&wo_ccif0>; + }; + }; diff --git a/Documentation/devicetree/bindings/hwlock/qcom-hwspinlock.yaml b/Documentation/devicetree/bindings/hwlock/qcom-hwspinlock.yaml index 1c7149f7d171..ee2726149cf3 100644 --- a/Documentation/devicetree/bindings/hwlock/qcom-hwspinlock.yaml +++ b/Documentation/devicetree/bindings/hwlock/qcom-hwspinlock.yaml @@ -15,9 +15,22 @@ description: properties: compatible: - enum: - - qcom,sfpb-mutex - - qcom,tcsr-mutex + oneOf: + - enum: + - qcom,sfpb-mutex + - qcom,tcsr-mutex + - items: + - enum: + - qcom,apq8084-tcsr-mutex + - qcom,ipq6018-tcsr-mutex + - qcom,msm8226-tcsr-mutex + - qcom,msm8994-tcsr-mutex + - const: qcom,tcsr-mutex + - items: + - enum: + - qcom,msm8974-tcsr-mutex + - const: qcom,tcsr-mutex + - const: syscon reg: maxItems: 1 @@ -34,9 +47,9 @@ additionalProperties: false examples: - | - tcsr_mutex: hwlock@1f40000 { - compatible = "qcom,tcsr-mutex"; - reg = <0x01f40000 0x40000>; - #hwlock-cells = <1>; - }; + hwlock@1f40000 { + compatible = "qcom,tcsr-mutex"; + reg = <0x01f40000 0x40000>; + #hwlock-cells = <1>; + }; ... diff --git a/Documentation/devicetree/bindings/net/asix,ax88178.yaml b/Documentation/devicetree/bindings/net/asix,ax88178.yaml index 1af52358de4c..a81dbc4792f6 100644 --- a/Documentation/devicetree/bindings/net/asix,ax88178.yaml +++ b/Documentation/devicetree/bindings/net/asix,ax88178.yaml @@ -27,7 +27,9 @@ properties: - usbb95,772b # ASIX AX88772B - usbb95,7e2b # ASIX AX88772B - reg: true + reg: + maxItems: 1 + local-mac-address: true mac-address: true diff --git a/Documentation/devicetree/bindings/net/dsa/dsa-port.yaml b/Documentation/devicetree/bindings/net/dsa/dsa-port.yaml index 10ad7e71097b..9abb8eba5fad 100644 --- a/Documentation/devicetree/bindings/net/dsa/dsa-port.yaml +++ b/Documentation/devicetree/bindings/net/dsa/dsa-port.yaml @@ -19,7 +19,8 @@ allOf: properties: reg: - description: Port number + items: + - description: Port number label: description: diff --git a/Documentation/devicetree/bindings/net/engleder,tsnep.yaml b/Documentation/devicetree/bindings/net/engleder,tsnep.yaml index 5bd964a46a9d..a6921e805e37 100644 --- a/Documentation/devicetree/bindings/net/engleder,tsnep.yaml +++ b/Documentation/devicetree/bindings/net/engleder,tsnep.yaml @@ -47,7 +47,7 @@ properties: nvmem-cells: true - nvmem-cells-names: true + nvmem-cell-names: true phy-connection-type: enum: diff --git a/Documentation/devicetree/bindings/net/microchip,lan95xx.yaml b/Documentation/devicetree/bindings/net/microchip,lan95xx.yaml index cf91fecd8909..3715c5f8f0e0 100644 --- a/Documentation/devicetree/bindings/net/microchip,lan95xx.yaml +++ b/Documentation/devicetree/bindings/net/microchip,lan95xx.yaml @@ -39,7 +39,9 @@ properties: - usb424,9e08 # SMSC LAN89530 USB Ethernet Device - usb424,ec00 # SMSC9512/9514 USB Hub & Ethernet Device - reg: true + reg: + maxItems: 1 + local-mac-address: true mac-address: true diff --git a/Documentation/devicetree/bindings/power/fsl,imx-gpcv2.yaml b/Documentation/devicetree/bindings/power/fsl,imx-gpcv2.yaml index 58022ae7d5dd..dfdb8dfb6b65 100644 --- a/Documentation/devicetree/bindings/power/fsl,imx-gpcv2.yaml +++ b/Documentation/devicetree/bindings/power/fsl,imx-gpcv2.yaml @@ -81,6 +81,9 @@ properties: power-supply: true + power-domains: + maxItems: 1 + resets: description: | A number of phandles to resets that need to be asserted during diff --git a/Documentation/devicetree/bindings/soc/mediatek/mediatek,mt7986-wo-ccif.yaml b/Documentation/devicetree/bindings/soc/mediatek/mediatek,mt7986-wo-ccif.yaml new file mode 100644 index 000000000000..8e6ba2ec8a43 --- /dev/null +++ b/Documentation/devicetree/bindings/soc/mediatek/mediatek,mt7986-wo-ccif.yaml @@ -0,0 +1,51 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/soc/mediatek/mediatek,mt7986-wo-ccif.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: MediaTek Wireless Ethernet Dispatch (WED) WO controller interface for MT7986 + +maintainers: + - Lorenzo Bianconi <lorenzo@kernel.org> + - Felix Fietkau <nbd@nbd.name> + +description: + The MediaTek wo-ccif provides a configuration interface for WED WO + controller used to perfrom offload rx packet processing (e.g. 802.11 + aggregation packet reordering or rx header translation) on MT7986 soc. + +properties: + compatible: + items: + - enum: + - mediatek,mt7986-wo-ccif + - const: syscon + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + +required: + - compatible + - reg + - interrupts + +additionalProperties: false + +examples: + - | + #include <dt-bindings/interrupt-controller/arm-gic.h> + #include <dt-bindings/interrupt-controller/irq.h> + soc { + #address-cells = <2>; + #size-cells = <2>; + + syscon@151a5000 { + compatible = "mediatek,mt7986-wo-ccif", "syscon"; + reg = <0 0x151a5000 0 0x1000>; + interrupts = <GIC_SPI 205 IRQ_TYPE_LEVEL_HIGH>; + }; + }; diff --git a/Documentation/driver-api/driver-model/devres.rst b/Documentation/driver-api/driver-model/devres.rst index 687adb58048e..56082265e8e5 100644 --- a/Documentation/driver-api/driver-model/devres.rst +++ b/Documentation/driver-api/driver-model/devres.rst @@ -279,6 +279,7 @@ GPIO devm_gpio_request_one() I2C + devm_i2c_add_adapter() devm_i2c_new_dummy_device() IIO diff --git a/Documentation/kbuild/reproducible-builds.rst b/Documentation/kbuild/reproducible-builds.rst index 071f0151a7a4..f2dcc39044e6 100644 --- a/Documentation/kbuild/reproducible-builds.rst +++ b/Documentation/kbuild/reproducible-builds.rst @@ -119,6 +119,16 @@ To avoid this, you can make the vDSO different for different kernel versions by including an arbitrary string of "salt" in it. This is specified by the Kconfig symbol ``CONFIG_BUILD_SALT``. +Git +--- + +Uncommitted changes or different commit ids in git can also lead +to different compilation results. For example, after executing +``git reset HEAD^``, even if the code is the same, the +``include/config/kernel.release`` generated during compilation +will be different, which will eventually lead to binary differences. +See ``scripts/setlocalversion`` for details. + .. _KBUILD_BUILD_TIMESTAMP: kbuild.html#kbuild-build-timestamp .. _KBUILD_BUILD_USER and KBUILD_BUILD_HOST: kbuild.html#kbuild-build-user-kbuild-build-host .. _KCFLAGS: kbuild.html#kcflags diff --git a/Documentation/networking/device_drivers/ethernet/marvell/octeon_ep.rst b/Documentation/networking/device_drivers/ethernet/marvell/octeon_ep.rst index bc562c49011b..cad96c8d1f97 100644 --- a/Documentation/networking/device_drivers/ethernet/marvell/octeon_ep.rst +++ b/Documentation/networking/device_drivers/ethernet/marvell/octeon_ep.rst @@ -23,6 +23,7 @@ Supported Devices ================= Currently, this driver support following devices: * Network controller: Cavium, Inc. Device b200 + * Network controller: Cavium, Inc. Device b400 Interface Control ================= diff --git a/Documentation/networking/devlink/devlink-trap.rst b/Documentation/networking/devlink/devlink-trap.rst index 90d1381b88de..2c14dfe69b3a 100644 --- a/Documentation/networking/devlink/devlink-trap.rst +++ b/Documentation/networking/devlink/devlink-trap.rst @@ -485,6 +485,16 @@ be added to the following table: - Traps incoming packets that the device decided to drop because the destination MAC is not configured in the MAC table and the interface is not in promiscuous mode + * - ``eapol`` + - ``control`` + - Traps "Extensible Authentication Protocol over LAN" (EAPOL) packets + specified in IEEE 802.1X + * - ``locked_port`` + - ``drop`` + - Traps packets that the device decided to drop because they failed the + locked bridge port check. That is, packets that were received via a + locked port and whose {SMAC, VID} does not correspond to an FDB entry + pointing to the port Driver-specific Packet Traps ============================ @@ -589,6 +599,9 @@ narrow. The description of these groups must be added to the following table: * - ``parser_error_drops`` - Contains packet traps for packets that were marked by the device during parsing as erroneous + * - ``eapol`` + - Contains packet traps for "Extensible Authentication Protocol over LAN" + (EAPOL) packets specified in IEEE 802.1X Packet Trap Policers ==================== diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index d578b8bcd8a4..bede24ef44fd 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -491,6 +491,7 @@ Kernel response contents: ``ETHTOOL_A_LINKSTATE_SQI_MAX`` u32 Max support SQI value ``ETHTOOL_A_LINKSTATE_EXT_STATE`` u8 link extended state ``ETHTOOL_A_LINKSTATE_EXT_SUBSTATE`` u8 link extended substate + ``ETHTOOL_A_LINKSTATE_EXT_DOWN_CNT`` u32 count of link down events ==================================== ====== ============================ For most NIC drivers, the value of ``ETHTOOL_A_LINKSTATE_LINK`` returns diff --git a/MAINTAINERS b/MAINTAINERS index 95fc5e1b4548..14ee1c72d01a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3985,7 +3985,7 @@ M: RafaÅ‚ MiÅ‚ecki <rafal@milecki.pl> R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained -T: git git://github.com/broadcom/stblinux.git +T: git https://github.com/broadcom/stblinux.git F: Documentation/devicetree/bindings/arm/bcm/brcm,bcmbca.yaml F: arch/arm64/boot/dts/broadcom/bcmbca/* N: bcmbca @@ -4010,7 +4010,7 @@ R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com> L: linux-rpi-kernel@lists.infradead.org (moderated for non-subscribers) L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained -T: git git://github.com/broadcom/stblinux.git +T: git https://github.com/broadcom/stblinux.git F: Documentation/devicetree/bindings/pci/brcm,stb-pcie.yaml F: drivers/pci/controller/pcie-brcmstb.c F: drivers/staging/vc04_services @@ -4024,7 +4024,7 @@ M: Ray Jui <rjui@broadcom.com> M: Scott Branden <sbranden@broadcom.com> R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com> S: Maintained -T: git git://github.com/broadcom/mach-bcm +T: git https://github.com/broadcom/mach-bcm F: arch/arm/mach-bcm/ N: bcm281* N: bcm113* @@ -4089,7 +4089,7 @@ M: Florian Fainelli <f.fainelli@gmail.com> R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained -T: git git://github.com/broadcom/stblinux.git +T: git https://github.com/broadcom/stblinux.git F: Documentation/devicetree/bindings/pci/brcm,stb-pcie.yaml F: arch/arm/boot/dts/bcm7*.dts* F: arch/arm/include/asm/hardware/cache-b15-rac.h @@ -4122,7 +4122,7 @@ M: Florian Fainelli <f.fainelli@gmail.com> R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com> L: linux-mips@vger.kernel.org S: Maintained -T: git git://github.com/broadcom/stblinux.git +T: git https://github.com/broadcom/stblinux.git F: arch/mips/bmips/* F: arch/mips/boot/dts/brcm/bcm*.dts* F: arch/mips/include/asm/mach-bmips/* @@ -4263,7 +4263,7 @@ M: Scott Branden <sbranden@broadcom.com> R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained -T: git git://github.com/broadcom/stblinux.git +T: git https://github.com/broadcom/stblinux.git F: arch/arm64/boot/dts/broadcom/northstar2/* F: arch/arm64/boot/dts/broadcom/stingray/* F: drivers/clk/bcm/clk-ns* @@ -4333,7 +4333,7 @@ M: Florian Fainelli <f.fainelli@gmail.com> R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com> L: linux-pm@vger.kernel.org S: Maintained -T: git git://github.com/broadcom/stblinux.git +T: git https://github.com/broadcom/stblinux.git F: drivers/soc/bcm/bcm63xx/bcm-pmb.c F: include/dt-bindings/soc/bcm-pmb.h @@ -8604,8 +8604,8 @@ F: include/asm-generic/ F: include/uapi/asm-generic/ GENERIC PHY FRAMEWORK -M: Kishon Vijay Abraham I <kishon@ti.com> M: Vinod Koul <vkoul@kernel.org> +M: Kishon Vijay Abraham I <kishon@kernel.org> L: linux-phy@lists.infradead.org S: Supported Q: https://patchwork.kernel.org/project/linux-phy/list/ @@ -9219,7 +9219,7 @@ W: https://www.hisilicon.com F: drivers/i2c/busses/i2c-hisi.c HISILICON LPC BUS DRIVER -M: john.garry@huawei.com +M: Jay Fang <f.fangjian@huawei.com> S: Maintained W: http://www.hisilicon.com F: Documentation/devicetree/bindings/arm/hisilicon/low-pin-count.yaml @@ -9438,8 +9438,9 @@ F: Documentation/devicetree/bindings/iio/humidity/st,hts221.yaml F: drivers/iio/humidity/hts221* HUAWEI ETHERNET DRIVER +M: Cai Huoqing <cai.huoqing@linux.dev> L: netdev@vger.kernel.org -S: Orphan +S: Maintained F: Documentation/networking/device_drivers/ethernet/huawei/hinic.rst F: drivers/net/ethernet/huawei/hinic/ @@ -9543,6 +9544,7 @@ F: include/asm-generic/hyperv-tlfs.h F: include/asm-generic/mshyperv.h F: include/clocksource/hyperv_timer.h F: include/linux/hyperv.h +F: include/net/mana F: include/uapi/linux/hyperv.h F: net/vmw_vsock/hyperv_transport.c F: tools/hv/ @@ -12228,7 +12230,6 @@ F: arch/mips/boot/dts/img/pistachio* MARVELL 88E6XXX ETHERNET SWITCH FABRIC DRIVER M: Andrew Lunn <andrew@lunn.ch> -M: Vivien Didelot <vivien.didelot@gmail.com> L: netdev@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/net/dsa/marvell.txt @@ -12925,6 +12926,7 @@ M: Felix Fietkau <nbd@nbd.name> M: John Crispin <john@phrozen.org> M: Sean Wang <sean.wang@mediatek.com> M: Mark Lee <Mark-MC.Lee@mediatek.com> +M: Lorenzo Bianconi <lorenzo@kernel.org> L: netdev@vger.kernel.org S: Maintained F: drivers/net/ethernet/mediatek/ @@ -14327,7 +14329,6 @@ F: drivers/net/wireless/ NETWORKING [DSA] M: Andrew Lunn <andrew@lunn.ch> -M: Vivien Didelot <vivien.didelot@gmail.com> M: Florian Fainelli <f.fainelli@gmail.com> M: Vladimir Oltean <olteanv@gmail.com> S: Maintained @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 1 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc4 NAME = Hurr durr I'ma ninja sloth # *DOCUMENTATION* @@ -1218,7 +1218,7 @@ quiet_cmd_ar_vmlinux.a = AR $@ cmd_ar_vmlinux.a = \ rm -f $@; \ $(AR) cDPrST $@ $(KBUILD_VMLINUX_OBJS); \ - $(AR) mPiT $$($(AR) t $@ | head -n1) $@ $$($(AR) t $@ | grep -F --file=$(srctree)/scripts/head-object-list.txt) + $(AR) mPiT $$($(AR) t $@ | sed -n 1p) $@ $$($(AR) t $@ | grep -F -f $(srctree)/scripts/head-object-list.txt) targets += vmlinux.a vmlinux.a: $(KBUILD_VMLINUX_OBJS) scripts/head-object-list.txt autoksyms_recursive FORCE diff --git a/arch/arm/boot/dts/imx6q-yapp4-crux.dts b/arch/arm/boot/dts/imx6q-yapp4-crux.dts index 15f4824a5142..bddf3822ebf7 100644 --- a/arch/arm/boot/dts/imx6q-yapp4-crux.dts +++ b/arch/arm/boot/dts/imx6q-yapp4-crux.dts @@ -33,6 +33,10 @@ status = "okay"; }; +®_pu { + regulator-always-on; +}; + ®_usb_h1_vbus { status = "okay"; }; diff --git a/arch/arm/boot/dts/imx6qdl-gw5910.dtsi b/arch/arm/boot/dts/imx6qdl-gw5910.dtsi index 68e5ab2e27e2..6bb4855d13ce 100644 --- a/arch/arm/boot/dts/imx6qdl-gw5910.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw5910.dtsi @@ -29,7 +29,7 @@ user-pb { label = "user_pb"; - gpios = <&gsc_gpio 0 GPIO_ACTIVE_LOW>; + gpios = <&gsc_gpio 2 GPIO_ACTIVE_LOW>; linux,code = <BTN_0>; }; diff --git a/arch/arm/boot/dts/imx6qdl-gw5913.dtsi b/arch/arm/boot/dts/imx6qdl-gw5913.dtsi index 8e23cec7149e..696427b487f0 100644 --- a/arch/arm/boot/dts/imx6qdl-gw5913.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw5913.dtsi @@ -26,7 +26,7 @@ user-pb { label = "user_pb"; - gpios = <&gsc_gpio 0 GPIO_ACTIVE_LOW>; + gpios = <&gsc_gpio 2 GPIO_ACTIVE_LOW>; linux,code = <BTN_0>; }; diff --git a/arch/arm/boot/dts/imx6qp-yapp4-crux-plus.dts b/arch/arm/boot/dts/imx6qp-yapp4-crux-plus.dts index cea165f2161a..afaf4a6759d4 100644 --- a/arch/arm/boot/dts/imx6qp-yapp4-crux-plus.dts +++ b/arch/arm/boot/dts/imx6qp-yapp4-crux-plus.dts @@ -33,6 +33,10 @@ status = "okay"; }; +®_pu { + regulator-always-on; +}; + ®_usb_h1_vbus { status = "okay"; }; diff --git a/arch/arm/boot/dts/ste-href.dtsi b/arch/arm/boot/dts/ste-href.dtsi index fbaa0ce46427..8f1bb78fc1e4 100644 --- a/arch/arm/boot/dts/ste-href.dtsi +++ b/arch/arm/boot/dts/ste-href.dtsi @@ -24,6 +24,14 @@ polling-delay = <0>; polling-delay-passive = <0>; thermal-sensors = <&bat_therm>; + + trips { + battery-crit-hi { + temperature = <70000>; + hysteresis = <2000>; + type = "critical"; + }; + }; }; }; diff --git a/arch/arm/boot/dts/ste-snowball.dts b/arch/arm/boot/dts/ste-snowball.dts index 1c9094f24893..e2f0cdacba7d 100644 --- a/arch/arm/boot/dts/ste-snowball.dts +++ b/arch/arm/boot/dts/ste-snowball.dts @@ -28,6 +28,14 @@ polling-delay = <0>; polling-delay-passive = <0>; thermal-sensors = <&bat_therm>; + + trips { + battery-crit-hi { + temperature = <70000>; + hysteresis = <2000>; + type = "critical"; + }; + }; }; }; diff --git a/arch/arm/boot/dts/ste-ux500-samsung-codina-tmo.dts b/arch/arm/boot/dts/ste-ux500-samsung-codina-tmo.dts index d6940e0afa86..27a3ab7e25e1 100644 --- a/arch/arm/boot/dts/ste-ux500-samsung-codina-tmo.dts +++ b/arch/arm/boot/dts/ste-ux500-samsung-codina-tmo.dts @@ -44,6 +44,14 @@ polling-delay = <0>; polling-delay-passive = <0>; thermal-sensors = <&bat_therm>; + + trips { + battery-crit-hi { + temperature = <70000>; + hysteresis = <2000>; + type = "critical"; + }; + }; }; }; diff --git a/arch/arm/boot/dts/ste-ux500-samsung-codina.dts b/arch/arm/boot/dts/ste-ux500-samsung-codina.dts index 5f41256d7f4b..b88f0c07873d 100644 --- a/arch/arm/boot/dts/ste-ux500-samsung-codina.dts +++ b/arch/arm/boot/dts/ste-ux500-samsung-codina.dts @@ -57,6 +57,14 @@ polling-delay = <0>; polling-delay-passive = <0>; thermal-sensors = <&bat_therm>; + + trips { + battery-crit-hi { + temperature = <70000>; + hysteresis = <2000>; + type = "critical"; + }; + }; }; }; diff --git a/arch/arm/boot/dts/ste-ux500-samsung-gavini.dts b/arch/arm/boot/dts/ste-ux500-samsung-gavini.dts index 806da3fc33cd..7231bc745200 100644 --- a/arch/arm/boot/dts/ste-ux500-samsung-gavini.dts +++ b/arch/arm/boot/dts/ste-ux500-samsung-gavini.dts @@ -30,6 +30,14 @@ polling-delay = <0>; polling-delay-passive = <0>; thermal-sensors = <&bat_therm>; + + trips { + battery-crit-hi { + temperature = <70000>; + hysteresis = <2000>; + type = "critical"; + }; + }; }; }; diff --git a/arch/arm/boot/dts/ste-ux500-samsung-golden.dts b/arch/arm/boot/dts/ste-ux500-samsung-golden.dts index b0dce91aff4b..9604695edf53 100644 --- a/arch/arm/boot/dts/ste-ux500-samsung-golden.dts +++ b/arch/arm/boot/dts/ste-ux500-samsung-golden.dts @@ -35,6 +35,14 @@ polling-delay = <0>; polling-delay-passive = <0>; thermal-sensors = <&bat_therm>; + + trips { + battery-crit-hi { + temperature = <70000>; + hysteresis = <2000>; + type = "critical"; + }; + }; }; }; diff --git a/arch/arm/boot/dts/ste-ux500-samsung-janice.dts b/arch/arm/boot/dts/ste-ux500-samsung-janice.dts index ed5c79c3d04b..69387e8754a9 100644 --- a/arch/arm/boot/dts/ste-ux500-samsung-janice.dts +++ b/arch/arm/boot/dts/ste-ux500-samsung-janice.dts @@ -30,6 +30,14 @@ polling-delay = <0>; polling-delay-passive = <0>; thermal-sensors = <&bat_therm>; + + trips { + battery-crit-hi { + temperature = <70000>; + hysteresis = <2000>; + type = "critical"; + }; + }; }; }; diff --git a/arch/arm/boot/dts/ste-ux500-samsung-kyle.dts b/arch/arm/boot/dts/ste-ux500-samsung-kyle.dts index c57676faf181..167846df3104 100644 --- a/arch/arm/boot/dts/ste-ux500-samsung-kyle.dts +++ b/arch/arm/boot/dts/ste-ux500-samsung-kyle.dts @@ -34,6 +34,14 @@ polling-delay = <0>; polling-delay-passive = <0>; thermal-sensors = <&bat_therm>; + + trips { + battery-crit-hi { + temperature = <70000>; + hysteresis = <2000>; + type = "critical"; + }; + }; }; }; diff --git a/arch/arm/boot/dts/ste-ux500-samsung-skomer.dts b/arch/arm/boot/dts/ste-ux500-samsung-skomer.dts index 81b341a5ae45..93e5f5ed888d 100644 --- a/arch/arm/boot/dts/ste-ux500-samsung-skomer.dts +++ b/arch/arm/boot/dts/ste-ux500-samsung-skomer.dts @@ -30,6 +30,14 @@ polling-delay = <0>; polling-delay-passive = <0>; thermal-sensors = <&bat_therm>; + + trips { + battery-crit-hi { + temperature = <70000>; + hysteresis = <2000>; + type = "critical"; + }; + }; }; }; diff --git a/arch/arm64/boot/dts/arm/juno-base.dtsi b/arch/arm64/boot/dts/arm/juno-base.dtsi index 2f27619d8abd..8b4d280b1e7e 100644 --- a/arch/arm64/boot/dts/arm/juno-base.dtsi +++ b/arch/arm64/boot/dts/arm/juno-base.dtsi @@ -751,12 +751,26 @@ polling-delay = <1000>; polling-delay-passive = <100>; thermal-sensors = <&scpi_sensors0 0>; + trips { + pmic_crit0: trip0 { + temperature = <90000>; + hysteresis = <2000>; + type = "critical"; + }; + }; }; soc { polling-delay = <1000>; polling-delay-passive = <100>; thermal-sensors = <&scpi_sensors0 3>; + trips { + soc_crit0: trip0 { + temperature = <80000>; + hysteresis = <2000>; + type = "critical"; + }; + }; }; big_cluster_thermal_zone: big-cluster { diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi index 421d879013d7..260d045dbd9a 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi @@ -779,6 +779,9 @@ little-endian; #address-cells = <1>; #size-cells = <0>; + clock-frequency = <2500000>; + clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL + QORIQ_CLK_PLL_DIV(1)>; status = "disabled"; }; @@ -788,6 +791,9 @@ little-endian; #address-cells = <1>; #size-cells = <0>; + clock-frequency = <2500000>; + clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL + QORIQ_CLK_PLL_DIV(1)>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi index f1b9cc8714dc..348d9e3a9125 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi @@ -532,6 +532,9 @@ little-endian; #address-cells = <1>; #size-cells = <0>; + clock-frequency = <2500000>; + clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL + QORIQ_CLK_PLL_DIV(2)>; status = "disabled"; }; @@ -541,6 +544,9 @@ little-endian; #address-cells = <1>; #size-cells = <0>; + clock-frequency = <2500000>; + clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL + QORIQ_CLK_PLL_DIV(2)>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi index 6680fb2a6dc9..8c76d86cb756 100644 --- a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi @@ -1385,6 +1385,9 @@ #address-cells = <1>; #size-cells = <0>; little-endian; + clock-frequency = <2500000>; + clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL + QORIQ_CLK_PLL_DIV(2)>; status = "disabled"; }; @@ -1395,6 +1398,9 @@ little-endian; #address-cells = <1>; #size-cells = <0>; + clock-frequency = <2500000>; + clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL + QORIQ_CLK_PLL_DIV(2)>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi b/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi index 82a1c4488378..10370d1a6c6d 100644 --- a/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi @@ -38,9 +38,9 @@ conn_subsys: bus@5b000000 { interrupts = <GIC_SPI 232 IRQ_TYPE_LEVEL_HIGH>; reg = <0x5b010000 0x10000>; clocks = <&sdhc0_lpcg IMX_LPCG_CLK_4>, - <&sdhc0_lpcg IMX_LPCG_CLK_5>, - <&sdhc0_lpcg IMX_LPCG_CLK_0>; - clock-names = "ipg", "per", "ahb"; + <&sdhc0_lpcg IMX_LPCG_CLK_0>, + <&sdhc0_lpcg IMX_LPCG_CLK_5>; + clock-names = "ipg", "ahb", "per"; power-domains = <&pd IMX_SC_R_SDHC_0>; status = "disabled"; }; @@ -49,9 +49,9 @@ conn_subsys: bus@5b000000 { interrupts = <GIC_SPI 233 IRQ_TYPE_LEVEL_HIGH>; reg = <0x5b020000 0x10000>; clocks = <&sdhc1_lpcg IMX_LPCG_CLK_4>, - <&sdhc1_lpcg IMX_LPCG_CLK_5>, - <&sdhc1_lpcg IMX_LPCG_CLK_0>; - clock-names = "ipg", "per", "ahb"; + <&sdhc1_lpcg IMX_LPCG_CLK_0>, + <&sdhc1_lpcg IMX_LPCG_CLK_5>; + clock-names = "ipg", "ahb", "per"; power-domains = <&pd IMX_SC_R_SDHC_1>; fsl,tuning-start-tap = <20>; fsl,tuning-step = <2>; @@ -62,9 +62,9 @@ conn_subsys: bus@5b000000 { interrupts = <GIC_SPI 234 IRQ_TYPE_LEVEL_HIGH>; reg = <0x5b030000 0x10000>; clocks = <&sdhc2_lpcg IMX_LPCG_CLK_4>, - <&sdhc2_lpcg IMX_LPCG_CLK_5>, - <&sdhc2_lpcg IMX_LPCG_CLK_0>; - clock-names = "ipg", "per", "ahb"; + <&sdhc2_lpcg IMX_LPCG_CLK_0>, + <&sdhc2_lpcg IMX_LPCG_CLK_5>; + clock-names = "ipg", "ahb", "per"; power-domains = <&pd IMX_SC_R_SDHC_2>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-mx8menlo.dts b/arch/arm64/boot/dts/freescale/imx8mm-mx8menlo.dts index 32f6f2f50c10..43e89859c044 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-mx8menlo.dts +++ b/arch/arm64/boot/dts/freescale/imx8mm-mx8menlo.dts @@ -250,21 +250,21 @@ /* SODIMM 96 */ MX8MM_IOMUXC_SAI1_RXD2_GPIO4_IO4 0x1c4 /* CPLD_D[7] */ - MX8MM_IOMUXC_SAI1_RXD3_GPIO4_IO5 0x1c4 + MX8MM_IOMUXC_SAI1_RXD3_GPIO4_IO5 0x184 /* CPLD_D[6] */ - MX8MM_IOMUXC_SAI1_RXFS_GPIO4_IO0 0x1c4 + MX8MM_IOMUXC_SAI1_RXFS_GPIO4_IO0 0x184 /* CPLD_D[5] */ - MX8MM_IOMUXC_SAI1_TXC_GPIO4_IO11 0x1c4 + MX8MM_IOMUXC_SAI1_TXC_GPIO4_IO11 0x184 /* CPLD_D[4] */ - MX8MM_IOMUXC_SAI1_TXD0_GPIO4_IO12 0x1c4 + MX8MM_IOMUXC_SAI1_TXD0_GPIO4_IO12 0x184 /* CPLD_D[3] */ - MX8MM_IOMUXC_SAI1_TXD1_GPIO4_IO13 0x1c4 + MX8MM_IOMUXC_SAI1_TXD1_GPIO4_IO13 0x184 /* CPLD_D[2] */ - MX8MM_IOMUXC_SAI1_TXD2_GPIO4_IO14 0x1c4 + MX8MM_IOMUXC_SAI1_TXD2_GPIO4_IO14 0x184 /* CPLD_D[1] */ - MX8MM_IOMUXC_SAI1_TXD3_GPIO4_IO15 0x1c4 + MX8MM_IOMUXC_SAI1_TXD3_GPIO4_IO15 0x184 /* CPLD_D[0] */ - MX8MM_IOMUXC_SAI1_TXD4_GPIO4_IO16 0x1c4 + MX8MM_IOMUXC_SAI1_TXD4_GPIO4_IO16 0x184 /* KBD_intK */ MX8MM_IOMUXC_SAI2_MCLK_GPIO4_IO27 0x1c4 /* DISP_reset */ diff --git a/arch/arm64/boot/dts/freescale/imx8mm.dtsi b/arch/arm64/boot/dts/freescale/imx8mm.dtsi index afb90f59c83c..dabd94dc30c4 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm.dtsi @@ -276,6 +276,7 @@ assigned-clocks = <&clk IMX8MM_CLK_USB_PHY_REF>; assigned-clock-parents = <&clk IMX8MM_SYS_PLL1_100M>; clock-names = "main_clk"; + power-domains = <&pgc_otg1>; }; usbphynop2: usbphynop2 { @@ -285,6 +286,7 @@ assigned-clocks = <&clk IMX8MM_CLK_USB_PHY_REF>; assigned-clock-parents = <&clk IMX8MM_SYS_PLL1_100M>; clock-names = "main_clk"; + power-domains = <&pgc_otg2>; }; soc: soc@0 { @@ -674,13 +676,11 @@ pgc_otg1: power-domain@2 { #power-domain-cells = <0>; reg = <IMX8MM_POWER_DOMAIN_OTG1>; - power-domains = <&pgc_hsiomix>; }; pgc_otg2: power-domain@3 { #power-domain-cells = <0>; reg = <IMX8MM_POWER_DOMAIN_OTG2>; - power-domains = <&pgc_hsiomix>; }; pgc_gpumix: power-domain@4 { @@ -1186,7 +1186,7 @@ assigned-clock-parents = <&clk IMX8MM_SYS_PLL2_500M>; phys = <&usbphynop1>; fsl,usbmisc = <&usbmisc1 0>; - power-domains = <&pgc_otg1>; + power-domains = <&pgc_hsiomix>; status = "disabled"; }; @@ -1206,7 +1206,7 @@ assigned-clock-parents = <&clk IMX8MM_SYS_PLL2_500M>; phys = <&usbphynop2>; fsl,usbmisc = <&usbmisc2 0>; - power-domains = <&pgc_otg2>; + power-domains = <&pgc_hsiomix>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mn.dtsi b/arch/arm64/boot/dts/freescale/imx8mn.dtsi index cb2836bfbd95..ad0b99adf691 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn.dtsi @@ -662,7 +662,6 @@ pgc_otg1: power-domain@1 { #power-domain-cells = <0>; reg = <IMX8MN_POWER_DOMAIN_OTG1>; - power-domains = <&pgc_hsiomix>; }; pgc_gpumix: power-domain@2 { @@ -1076,7 +1075,7 @@ assigned-clock-parents = <&clk IMX8MN_SYS_PLL2_500M>; phys = <&usbphynop1>; fsl,usbmisc = <&usbmisc1 0>; - power-domains = <&pgc_otg1>; + power-domains = <&pgc_hsiomix>; status = "disabled"; }; @@ -1175,5 +1174,6 @@ assigned-clocks = <&clk IMX8MN_CLK_USB_PHY_REF>; assigned-clock-parents = <&clk IMX8MN_SYS_PLL1_100M>; clock-names = "main_clk"; + power-domains = <&pgc_otg1>; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-verdin.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-verdin.dtsi index 7b712d1888ea..5dcd1de586b5 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-verdin.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-verdin.dtsi @@ -354,16 +354,6 @@ "SODIMM_82", "SODIMM_70", "SODIMM_72"; - - ctrl-sleep-moci-hog { - gpio-hog; - /* Verdin CTRL_SLEEP_MOCI# (SODIMM 256) */ - gpios = <29 GPIO_ACTIVE_HIGH>; - line-name = "CTRL_SLEEP_MOCI#"; - output-high; - pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_ctrl_sleep_moci>; - }; }; &gpio3 { @@ -432,6 +422,16 @@ "SODIMM_256", "SODIMM_48", "SODIMM_44"; + + ctrl-sleep-moci-hog { + gpio-hog; + /* Verdin CTRL_SLEEP_MOCI# (SODIMM 256) */ + gpios = <29 GPIO_ACTIVE_HIGH>; + line-name = "CTRL_SLEEP_MOCI#"; + output-high; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_ctrl_sleep_moci>; + }; }; /* On-module I2C */ diff --git a/arch/arm64/boot/dts/freescale/imx93.dtsi b/arch/arm64/boot/dts/freescale/imx93.dtsi index 3a5713bb4880..0247866fc86b 100644 --- a/arch/arm64/boot/dts/freescale/imx93.dtsi +++ b/arch/arm64/boot/dts/freescale/imx93.dtsi @@ -451,7 +451,7 @@ clocks = <&clk IMX93_CLK_GPIO2_GATE>, <&clk IMX93_CLK_GPIO2_GATE>; clock-names = "gpio", "port"; - gpio-ranges = <&iomuxc 0 32 32>; + gpio-ranges = <&iomuxc 0 4 30>; }; gpio3: gpio@43820080 { @@ -465,7 +465,8 @@ clocks = <&clk IMX93_CLK_GPIO3_GATE>, <&clk IMX93_CLK_GPIO3_GATE>; clock-names = "gpio", "port"; - gpio-ranges = <&iomuxc 0 64 32>; + gpio-ranges = <&iomuxc 0 84 8>, <&iomuxc 8 66 18>, + <&iomuxc 26 34 2>, <&iomuxc 28 0 4>; }; gpio4: gpio@43830080 { @@ -479,7 +480,7 @@ clocks = <&clk IMX93_CLK_GPIO4_GATE>, <&clk IMX93_CLK_GPIO4_GATE>; clock-names = "gpio", "port"; - gpio-ranges = <&iomuxc 0 96 32>; + gpio-ranges = <&iomuxc 0 38 28>, <&iomuxc 28 36 2>; }; gpio1: gpio@47400080 { @@ -493,7 +494,7 @@ clocks = <&clk IMX93_CLK_GPIO1_GATE>, <&clk IMX93_CLK_GPIO1_GATE>; clock-names = "gpio", "port"; - gpio-ranges = <&iomuxc 0 0 32>; + gpio-ranges = <&iomuxc 0 92 16>; }; s4muap: mailbox@47520000 { @@ -501,7 +502,7 @@ reg = <0x47520000 0x10000>; interrupts = <GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>; - interrupt-names = "txirq", "rxirq"; + interrupt-names = "tx", "rx"; #mbox-cells = <2>; }; diff --git a/arch/arm64/boot/dts/mediatek/mt7986a.dtsi b/arch/arm64/boot/dts/mediatek/mt7986a.dtsi index 72e0d9722e07..07dee1c0d281 100644 --- a/arch/arm64/boot/dts/mediatek/mt7986a.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt7986a.dtsi @@ -76,6 +76,47 @@ no-map; reg = <0 0x4fc00000 0 0x00100000>; }; + + wo_emi0: wo-emi@4fd00000 { + reg = <0 0x4fd00000 0 0x40000>; + no-map; + }; + + wo_emi1: wo-emi@4fd40000 { + reg = <0 0x4fd40000 0 0x40000>; + no-map; + }; + + wo_ilm0: wo-ilm@151e0000 { + reg = <0 0x151e0000 0 0x8000>; + no-map; + }; + + wo_ilm1: wo-ilm@151f0000 { + reg = <0 0x151f0000 0 0x8000>; + no-map; + }; + + wo_data: wo-data@4fd80000 { + reg = <0 0x4fd80000 0 0x240000>; + no-map; + }; + + wo_dlm0: wo-dlm@151e8000 { + reg = <0 0x151e8000 0 0x2000>; + no-map; + }; + + wo_dlm1: wo-dlm@151f8000 { + reg = <0 0x151f8000 0 0x2000>; + no-map; + }; + + wo_boot: wo-boot@15194000 { + reg = <0 0x15194000 0 0x1000>; + no-map; + }; + }; timer { @@ -240,6 +281,11 @@ reg = <0 0x15010000 0 0x1000>; interrupt-parent = <&gic>; interrupts = <GIC_SPI 205 IRQ_TYPE_LEVEL_HIGH>; + memory-region = <&wo_emi0>, <&wo_ilm0>, <&wo_dlm0>, + <&wo_data>, <&wo_boot>; + memory-region-names = "wo-emi", "wo-ilm", "wo-dlm", + "wo-data", "wo-boot"; + mediatek,wo-ccif = <&wo_ccif0>; }; wed1: wed@15011000 { @@ -248,6 +294,25 @@ reg = <0 0x15011000 0 0x1000>; interrupt-parent = <&gic>; interrupts = <GIC_SPI 206 IRQ_TYPE_LEVEL_HIGH>; + memory-region = <&wo_emi1>, <&wo_ilm1>, <&wo_dlm1>, + <&wo_data>, <&wo_boot>; + memory-region-names = "wo-emi", "wo-ilm", "wo-dlm", + "wo-data", "wo-boot"; + mediatek,wo-ccif = <&wo_ccif1>; + }; + + wo_ccif0: syscon@151a5000 { + compatible = "mediatek,mt7986-wo-ccif", "syscon"; + reg = <0 0x151a5000 0 0x1000>; + interrupt-parent = <&gic>; + interrupts = <GIC_SPI 211 IRQ_TYPE_LEVEL_HIGH>; + }; + + wo_ccif1: syscon@151ad000 { + compatible = "mediatek,mt7986-wo-ccif", "syscon"; + reg = <0 0x151ad000 0 0x1000>; + interrupt-parent = <&gic>; + interrupts = <GIC_SPI 212 IRQ_TYPE_LEVEL_HIGH>; }; eth: ethernet@15100000 { diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h index 439e2bc5d5d8..d6cf535d8352 100644 --- a/arch/arm64/include/asm/efi.h +++ b/arch/arm64/include/asm/efi.h @@ -14,8 +14,16 @@ #ifdef CONFIG_EFI extern void efi_init(void); + +bool efi_runtime_fixup_exception(struct pt_regs *regs, const char *msg); #else #define efi_init() + +static inline +bool efi_runtime_fixup_exception(struct pt_regs *regs, const char *msg) +{ + return false; +} #endif int efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md); diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 6062454a9067..b3f37e2209ad 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -428,6 +428,30 @@ static const struct arm64_ftr_bits ftr_id_aa64dfr0[] = { ARM64_FTR_END, }; +static const struct arm64_ftr_bits ftr_mvfr0[] = { + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPROUND_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPSHVEC_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPSQRT_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPDIVIDE_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPTRAP_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPDP_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPSP_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_SIMD_SHIFT, 4, 0), + ARM64_FTR_END, +}; + +static const struct arm64_ftr_bits ftr_mvfr1[] = { + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_SIMDFMAC_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_FPHP_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_SIMDHP_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_SIMDSP_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_SIMDINT_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_SIMDLS_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_FPDNAN_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_FPFTZ_SHIFT, 4, 0), + ARM64_FTR_END, +}; + static const struct arm64_ftr_bits ftr_mvfr2[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR2_FPMISC_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR2_SIMDMISC_SHIFT, 4, 0), @@ -458,10 +482,10 @@ static const struct arm64_ftr_bits ftr_id_isar0[] = { static const struct arm64_ftr_bits ftr_id_isar5[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_RDM_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_CRC32_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_SHA2_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_SHA1_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_AES_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_CRC32_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_SHA2_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_SHA1_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_AES_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_SEVL_SHIFT, 4, 0), ARM64_FTR_END, }; @@ -574,7 +598,7 @@ static const struct arm64_ftr_bits ftr_smcr[] = { * Common ftr bits for a 32bit register with all hidden, strict * attributes, with 4bit feature fields and a default safe value of * 0. Covers the following 32bit registers: - * id_isar[1-4], id_mmfr[1-3], id_pfr1, mvfr[0-1] + * id_isar[1-3], id_mmfr[1-3] */ static const struct arm64_ftr_bits ftr_generic_32bits[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 28, 4, 0), @@ -645,8 +669,8 @@ static const struct __ftr_reg_entry { ARM64_FTR_REG(SYS_ID_ISAR6_EL1, ftr_id_isar6), /* Op1 = 0, CRn = 0, CRm = 3 */ - ARM64_FTR_REG(SYS_MVFR0_EL1, ftr_generic_32bits), - ARM64_FTR_REG(SYS_MVFR1_EL1, ftr_generic_32bits), + ARM64_FTR_REG(SYS_MVFR0_EL1, ftr_mvfr0), + ARM64_FTR_REG(SYS_MVFR1_EL1, ftr_mvfr1), ARM64_FTR_REG(SYS_MVFR2_EL1, ftr_mvfr2), ARM64_FTR_REG(SYS_ID_PFR2_EL1, ftr_id_pfr2), ARM64_FTR_REG(SYS_ID_DFR1_EL1, ftr_id_dfr1), @@ -3339,7 +3363,7 @@ static void __maybe_unused cpu_enable_cnp(struct arm64_cpu_capabilities const *c /* * We emulate only the following system register space. - * Op0 = 0x3, CRn = 0x0, Op1 = 0x0, CRm = [0, 4 - 7] + * Op0 = 0x3, CRn = 0x0, Op1 = 0x0, CRm = [0, 2 - 7] * See Table C5-6 System instruction encodings for System register accesses, * ARMv8 ARM(ARM DDI 0487A.f) for more details. */ @@ -3349,7 +3373,7 @@ static inline bool __attribute_const__ is_emulated(u32 id) sys_reg_CRn(id) == 0x0 && sys_reg_Op1(id) == 0x0 && (sys_reg_CRm(id) == 0 || - ((sys_reg_CRm(id) >= 4) && (sys_reg_CRm(id) <= 7)))); + ((sys_reg_CRm(id) >= 2) && (sys_reg_CRm(id) <= 7)))); } /* diff --git a/arch/arm64/kernel/efi-rt-wrapper.S b/arch/arm64/kernel/efi-rt-wrapper.S index 75691a2641c1..67babd5f04c2 100644 --- a/arch/arm64/kernel/efi-rt-wrapper.S +++ b/arch/arm64/kernel/efi-rt-wrapper.S @@ -6,7 +6,7 @@ #include <linux/linkage.h> SYM_FUNC_START(__efi_rt_asm_wrapper) - stp x29, x30, [sp, #-32]! + stp x29, x30, [sp, #-112]! mov x29, sp /* @@ -17,6 +17,20 @@ SYM_FUNC_START(__efi_rt_asm_wrapper) stp x1, x18, [sp, #16] /* + * Preserve all callee saved registers and record the stack pointer + * value in a per-CPU variable so we can recover from synchronous + * exceptions occurring while running the firmware routines. + */ + stp x19, x20, [sp, #32] + stp x21, x22, [sp, #48] + stp x23, x24, [sp, #64] + stp x25, x26, [sp, #80] + stp x27, x28, [sp, #96] + + adr_this_cpu x8, __efi_rt_asm_recover_sp, x9 + str x29, [x8] + + /* * We are lucky enough that no EFI runtime services take more than * 5 arguments, so all are passed in registers rather than via the * stack. @@ -31,7 +45,7 @@ SYM_FUNC_START(__efi_rt_asm_wrapper) ldp x1, x2, [sp, #16] cmp x2, x18 - ldp x29, x30, [sp], #32 + ldp x29, x30, [sp], #112 b.ne 0f ret 0: @@ -45,3 +59,18 @@ SYM_FUNC_START(__efi_rt_asm_wrapper) mov x18, x2 b efi_handle_corrupted_x18 // tail call SYM_FUNC_END(__efi_rt_asm_wrapper) + +SYM_FUNC_START(__efi_rt_asm_recover) + ldr_this_cpu x8, __efi_rt_asm_recover_sp, x9 + mov sp, x8 + + ldp x0, x18, [sp, #16] + ldp x19, x20, [sp, #32] + ldp x21, x22, [sp, #48] + ldp x23, x24, [sp, #64] + ldp x25, x26, [sp, #80] + ldp x27, x28, [sp, #96] + ldp x29, x30, [sp], #112 + + b efi_handle_runtime_exception +SYM_FUNC_END(__efi_rt_asm_recover) diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index e1be6c429810..8d36e66a6e64 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -9,6 +9,7 @@ #include <linux/efi.h> #include <linux/init.h> +#include <linux/percpu.h> #include <asm/efi.h> @@ -128,3 +129,28 @@ asmlinkage efi_status_t efi_handle_corrupted_x18(efi_status_t s, const char *f) pr_err_ratelimited(FW_BUG "register x18 corrupted by EFI %s\n", f); return s; } + +asmlinkage DEFINE_PER_CPU(u64, __efi_rt_asm_recover_sp); + +asmlinkage efi_status_t __efi_rt_asm_recover(void); + +asmlinkage efi_status_t efi_handle_runtime_exception(const char *f) +{ + pr_err(FW_BUG "Synchronous exception occurred in EFI runtime service %s()\n", f); + clear_bit(EFI_RUNTIME_SERVICES, &efi.flags); + return EFI_ABORTED; +} + +bool efi_runtime_fixup_exception(struct pt_regs *regs, const char *msg) +{ + /* Check whether the exception occurred while running the firmware */ + if (current_work() != &efi_rts_work.work || regs->pc >= TASK_SIZE_64) + return false; + + pr_err(FW_BUG "Unable to handle %s in EFI runtime service\n", msg); + add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK); + dump_stack(); + + regs->pc = (u64)__efi_rt_asm_recover; + return true; +} diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c index 9173fad279af..27369fa1c032 100644 --- a/arch/arm64/kernel/entry-common.c +++ b/arch/arm64/kernel/entry-common.c @@ -329,7 +329,8 @@ static void cortex_a76_erratum_1463225_svc_handler(void) __this_cpu_write(__in_cortex_a76_erratum_1463225_wa, 0); } -static bool cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs) +static __always_inline bool +cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs) { if (!__this_cpu_read(__in_cortex_a76_erratum_1463225_wa)) return false; diff --git a/arch/arm64/kvm/hyp/exception.c b/arch/arm64/kvm/hyp/exception.c index b7557b25ed56..791d3de76771 100644 --- a/arch/arm64/kvm/hyp/exception.c +++ b/arch/arm64/kvm/hyp/exception.c @@ -13,6 +13,7 @@ #include <hyp/adjust_pc.h> #include <linux/kvm_host.h> #include <asm/kvm_emulate.h> +#include <asm/kvm_mmu.h> #if !defined (__KVM_NVHE_HYPERVISOR__) && !defined (__KVM_VHE_HYPERVISOR__) #error Hypervisor code only! @@ -115,7 +116,7 @@ static void enter_exception64(struct kvm_vcpu *vcpu, unsigned long target_mode, new |= (old & PSR_C_BIT); new |= (old & PSR_V_BIT); - if (kvm_has_mte(vcpu->kvm)) + if (kvm_has_mte(kern_hyp_va(vcpu->kvm))) new |= PSR_TCO_BIT; new |= (old & PSR_DIT_BIT); diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 6cbbb6c02f66..3330d1b76bdd 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -87,6 +87,17 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu) vcpu->arch.mdcr_el2_host = read_sysreg(mdcr_el2); write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2); + + if (cpus_have_final_cap(ARM64_SME)) { + sysreg_clear_set_s(SYS_HFGRTR_EL2, + HFGxTR_EL2_nSMPRI_EL1_MASK | + HFGxTR_EL2_nTPIDR2_EL0_MASK, + 0); + sysreg_clear_set_s(SYS_HFGWTR_EL2, + HFGxTR_EL2_nSMPRI_EL1_MASK | + HFGxTR_EL2_nTPIDR2_EL0_MASK, + 0); + } } static inline void __deactivate_traps_common(struct kvm_vcpu *vcpu) @@ -96,6 +107,15 @@ static inline void __deactivate_traps_common(struct kvm_vcpu *vcpu) write_sysreg(0, hstr_el2); if (kvm_arm_support_pmu_v3()) write_sysreg(0, pmuserenr_el0); + + if (cpus_have_final_cap(ARM64_SME)) { + sysreg_clear_set_s(SYS_HFGRTR_EL2, 0, + HFGxTR_EL2_nSMPRI_EL1_MASK | + HFGxTR_EL2_nTPIDR2_EL0_MASK); + sysreg_clear_set_s(SYS_HFGWTR_EL2, 0, + HFGxTR_EL2_nSMPRI_EL1_MASK | + HFGxTR_EL2_nTPIDR2_EL0_MASK); + } } static inline void ___activate_traps(struct kvm_vcpu *vcpu) diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index 1e78acf9662e..07f9dc9848ef 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -516,7 +516,7 @@ static enum pkvm_page_state hyp_get_page_state(kvm_pte_t pte) if (!kvm_pte_valid(pte)) return PKVM_NOPAGE; - return pkvm_getstate(kvm_pgtable_stage2_pte_prot(pte)); + return pkvm_getstate(kvm_pgtable_hyp_pte_prot(pte)); } static int __hyp_check_page_state_range(u64 addr, u64 size, diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index 8e9d49a964be..c2cb46ca4fb6 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -55,18 +55,6 @@ static void __activate_traps(struct kvm_vcpu *vcpu) write_sysreg(val, cptr_el2); write_sysreg(__this_cpu_read(kvm_hyp_vector), vbar_el2); - if (cpus_have_final_cap(ARM64_SME)) { - val = read_sysreg_s(SYS_HFGRTR_EL2); - val &= ~(HFGxTR_EL2_nTPIDR2_EL0_MASK | - HFGxTR_EL2_nSMPRI_EL1_MASK); - write_sysreg_s(val, SYS_HFGRTR_EL2); - - val = read_sysreg_s(SYS_HFGWTR_EL2); - val &= ~(HFGxTR_EL2_nTPIDR2_EL0_MASK | - HFGxTR_EL2_nSMPRI_EL1_MASK); - write_sysreg_s(val, SYS_HFGWTR_EL2); - } - if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) { struct kvm_cpu_context *ctxt = &vcpu->arch.ctxt; @@ -110,20 +98,6 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu) write_sysreg(this_cpu_ptr(&kvm_init_params)->hcr_el2, hcr_el2); - if (cpus_have_final_cap(ARM64_SME)) { - u64 val; - - val = read_sysreg_s(SYS_HFGRTR_EL2); - val |= HFGxTR_EL2_nTPIDR2_EL0_MASK | - HFGxTR_EL2_nSMPRI_EL1_MASK; - write_sysreg_s(val, SYS_HFGRTR_EL2); - - val = read_sysreg_s(SYS_HFGWTR_EL2); - val |= HFGxTR_EL2_nTPIDR2_EL0_MASK | - HFGxTR_EL2_nSMPRI_EL1_MASK; - write_sysreg_s(val, SYS_HFGWTR_EL2); - } - cptr = CPTR_EL2_DEFAULT; if (vcpu_has_sve(vcpu) && (vcpu->arch.fp_state == FP_STATE_GUEST_OWNED)) cptr |= CPTR_EL2_TZ; diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 7acb87eaa092..1a97391fedd2 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -63,10 +63,6 @@ static void __activate_traps(struct kvm_vcpu *vcpu) __activate_traps_fpsimd32(vcpu); } - if (cpus_have_final_cap(ARM64_SME)) - write_sysreg(read_sysreg(sctlr_el2) & ~SCTLR_ELx_ENTP2, - sctlr_el2); - write_sysreg(val, cpacr_el1); write_sysreg(__this_cpu_read(kvm_hyp_vector), vbar_el1); @@ -88,10 +84,6 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu) */ asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT)); - if (cpus_have_final_cap(ARM64_SME)) - write_sysreg(read_sysreg(sctlr_el2) | SCTLR_ELx_ENTP2, - sctlr_el2); - write_sysreg(CPACR_EL1_DEFAULT, cpacr_el1); if (!arm64_kernel_unmapped_at_el0()) diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 5b391490e045..3e9cf9826417 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -30,6 +30,7 @@ #include <asm/bug.h> #include <asm/cmpxchg.h> #include <asm/cpufeature.h> +#include <asm/efi.h> #include <asm/exception.h> #include <asm/daifflags.h> #include <asm/debug-monitors.h> @@ -391,6 +392,9 @@ static void __do_kernel_fault(unsigned long addr, unsigned long esr, msg = "paging request"; } + if (efi_runtime_fixup_exception(regs, msg)) + return; + die_kernel_fault(msg, addr, esr, regs); } diff --git a/arch/sparc/net/bpf_jit_comp_32.c b/arch/sparc/net/bpf_jit_comp_32.c index b1dbf2fa8c0a..a74e5004c6c8 100644 --- a/arch/sparc/net/bpf_jit_comp_32.c +++ b/arch/sparc/net/bpf_jit_comp_32.c @@ -555,11 +555,11 @@ void bpf_jit_compile(struct bpf_prog *fp) emit_skb_load16(vlan_tci, r_A); break; case BPF_ANC | SKF_AD_VLAN_TAG_PRESENT: - __emit_skb_load8(__pkt_vlan_present_offset, r_A); - if (PKT_VLAN_PRESENT_BIT) - emit_alu_K(SRL, PKT_VLAN_PRESENT_BIT); - if (PKT_VLAN_PRESENT_BIT < 7) - emit_andi(r_A, 1, r_A); + emit_skb_load32(vlan_all, r_A); + emit_cmpi(r_A, 0); + emit_branch_off(BE, 12); + emit_nop(); + emit_loadimm(1, r_A); break; case BPF_LD | BPF_W | BPF_LEN: emit_skb_load32(len, r_A); diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c index 928dcf7a20d9..b8998cf0508a 100644 --- a/arch/x86/coco/tdx/tdx.c +++ b/arch/x86/coco/tdx/tdx.c @@ -34,6 +34,8 @@ #define VE_GET_PORT_NUM(e) ((e) >> 16) #define VE_IS_IO_STRING(e) ((e) & BIT(4)) +#define ATTR_SEPT_VE_DISABLE BIT(28) + /* * Wrapper for standard use of __tdx_hypercall with no output aside from * return code. @@ -98,10 +100,11 @@ static inline void tdx_module_call(u64 fn, u64 rcx, u64 rdx, u64 r8, u64 r9, panic("TDCALL %lld failed (Buggy TDX module!)\n", fn); } -static u64 get_cc_mask(void) +static void tdx_parse_tdinfo(u64 *cc_mask) { struct tdx_module_output out; unsigned int gpa_width; + u64 td_attr; /* * TDINFO TDX module call is used to get the TD execution environment @@ -109,19 +112,27 @@ static u64 get_cc_mask(void) * information, etc. More details about the ABI can be found in TDX * Guest-Host-Communication Interface (GHCI), section 2.4.2 TDCALL * [TDG.VP.INFO]. + */ + tdx_module_call(TDX_GET_INFO, 0, 0, 0, 0, &out); + + /* + * The highest bit of a guest physical address is the "sharing" bit. + * Set it for shared pages and clear it for private pages. * * The GPA width that comes out of this call is critical. TDX guests * can not meaningfully run without it. */ - tdx_module_call(TDX_GET_INFO, 0, 0, 0, 0, &out); - gpa_width = out.rcx & GENMASK(5, 0); + *cc_mask = BIT_ULL(gpa_width - 1); /* - * The highest bit of a guest physical address is the "sharing" bit. - * Set it for shared pages and clear it for private pages. + * The kernel can not handle #VE's when accessing normal kernel + * memory. Ensure that no #VE will be delivered for accesses to + * TD-private memory. Only VMM-shared memory (MMIO) will #VE. */ - return BIT_ULL(gpa_width - 1); + td_attr = out.rdx; + if (!(td_attr & ATTR_SEPT_VE_DISABLE)) + panic("TD misconfiguration: SEPT_VE_DISABLE attibute must be set.\n"); } /* @@ -758,7 +769,7 @@ void __init tdx_early_init(void) setup_force_cpu_cap(X86_FEATURE_TDX_GUEST); cc_set_vendor(CC_VENDOR_INTEL); - cc_mask = get_cc_mask(); + tdx_parse_tdinfo(&cc_mask); cc_set_mask(cc_mask); /* diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index a646a5f9a235..1b92bf05fd65 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -4911,6 +4911,7 @@ static const struct x86_cpu_desc isolation_ucodes[] = { INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 5, 0x00000000), INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 6, 0x00000000), INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 7, 0x00000000), + INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 11, 0x00000000), INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_L, 3, 0x0000007c), INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE, 3, 0x0000007c), INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE, 9, 0x0000004e), diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 7839507b3844..446d2833efa7 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -982,8 +982,13 @@ struct event_constraint intel_icl_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL), /* SLOTS */ INTEL_PLD_CONSTRAINT(0x1cd, 0xff), /* MEM_TRANS_RETIRED.LOAD_LATENCY */ - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x1d0, 0xf), /* MEM_INST_RETIRED.LOAD */ - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x2d0, 0xf), /* MEM_INST_RETIRED.STORE */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_INST_RETIRED.LOCK_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x41d0, 0xf), /* MEM_INST_RETIRED.SPLIT_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x42d0, 0xf), /* MEM_INST_RETIRED.SPLIT_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x81d0, 0xf), /* MEM_INST_RETIRED.ALL_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x82d0, 0xf), /* MEM_INST_RETIRED.ALL_STORES */ INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(0xd1, 0xd4, 0xf), /* MEM_LOAD_*_RETIRED.* */ @@ -1004,8 +1009,13 @@ struct event_constraint intel_spr_pebs_event_constraints[] = { INTEL_FLAGS_EVENT_CONSTRAINT(0xc0, 0xfe), INTEL_PLD_CONSTRAINT(0x1cd, 0xfe), INTEL_PSD_CONSTRAINT(0x2cd, 0x1), - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x1d0, 0xf), - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x2d0, 0xf), + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_INST_RETIRED.LOCK_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x41d0, 0xf), /* MEM_INST_RETIRED.SPLIT_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x42d0, 0xf), /* MEM_INST_RETIRED.SPLIT_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x81d0, 0xf), /* MEM_INST_RETIRED.ALL_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x82d0, 0xf), /* MEM_INST_RETIRED.ALL_STORES */ INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(0xd1, 0xd4, 0xf), diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c index fea544e5842a..a829492bca4c 100644 --- a/arch/x86/events/rapl.c +++ b/arch/x86/events/rapl.c @@ -619,12 +619,8 @@ static int rapl_check_hw_unit(struct rapl_model *rm) case RAPL_UNIT_QUIRK_INTEL_HSW: rapl_hw_unit[PERF_RAPL_RAM] = 16; break; - /* - * SPR shares the same DRAM domain energy unit as HSW, plus it - * also has a fixed energy unit for Psys domain. - */ + /* SPR uses a fixed energy unit for Psys domain. */ case RAPL_UNIT_QUIRK_INTEL_SPR: - rapl_hw_unit[PERF_RAPL_RAM] = 16; rapl_hw_unit[PERF_RAPL_PSYS] = 0; break; default: diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 5d75fe229342..347707d459c6 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -107,6 +107,11 @@ #define INTEL_FAM6_SAPPHIRERAPIDS_X 0x8F /* Golden Cove */ +#define INTEL_FAM6_EMERALDRAPIDS_X 0xCF + +#define INTEL_FAM6_GRANITERAPIDS_X 0xAD +#define INTEL_FAM6_GRANITERAPIDS_D 0xAE + #define INTEL_FAM6_ALDERLAKE 0x97 /* Golden Cove / Gracemont */ #define INTEL_FAM6_ALDERLAKE_L 0x9A /* Golden Cove / Gracemont */ #define INTEL_FAM6_ALDERLAKE_N 0xBE @@ -118,7 +123,7 @@ #define INTEL_FAM6_METEORLAKE 0xAC #define INTEL_FAM6_METEORLAKE_L 0xAA -/* "Small Core" Processors (Atom) */ +/* "Small Core" Processors (Atom/E-Core) */ #define INTEL_FAM6_ATOM_BONNELL 0x1C /* Diamondville, Pineview */ #define INTEL_FAM6_ATOM_BONNELL_MID 0x26 /* Silverthorne, Lincroft */ @@ -145,6 +150,10 @@ #define INTEL_FAM6_ATOM_TREMONT 0x96 /* Elkhart Lake */ #define INTEL_FAM6_ATOM_TREMONT_L 0x9C /* Jasper Lake */ +#define INTEL_FAM6_SIERRAFOREST_X 0xAF + +#define INTEL_FAM6_GRANDRIDGE 0xB6 + /* Xeon Phi */ #define INTEL_FAM6_XEON_PHI_KNL 0x57 /* Knights Landing */ diff --git a/arch/x86/include/asm/syscall_wrapper.h b/arch/x86/include/asm/syscall_wrapper.h index 59358d1bf880..fd2669b1cb2d 100644 --- a/arch/x86/include/asm/syscall_wrapper.h +++ b/arch/x86/include/asm/syscall_wrapper.h @@ -6,7 +6,7 @@ #ifndef _ASM_X86_SYSCALL_WRAPPER_H #define _ASM_X86_SYSCALL_WRAPPER_H -struct pt_regs; +#include <asm/ptrace.h> extern long __x64_sys_ni_syscall(const struct pt_regs *regs); extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 0810e93cbedc..62bc7a01cecc 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -1338,7 +1338,7 @@ int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid, if (sanity_check_entries(entries, cpuid->nent, type)) return -EINVAL; - array.entries = kvcalloc(sizeof(struct kvm_cpuid_entry2), cpuid->nent, GFP_KERNEL); + array.entries = kvcalloc(cpuid->nent, sizeof(struct kvm_cpuid_entry2), GFP_KERNEL); if (!array.entries) return -ENOMEM; diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index 87c4e46daf37..07254314f3dd 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -24,8 +24,6 @@ extern int __read_mostly pt_mode; #define PMU_CAP_FW_WRITES (1ULL << 13) #define PMU_CAP_LBR_FMT 0x3f -#define DEBUGCTLMSR_LBR_MASK (DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI) - struct nested_vmx_msrs { /* * We only store the "true" versions of the VMX capability MSRs. We @@ -400,6 +398,7 @@ static inline bool vmx_pebs_supported(void) static inline u64 vmx_get_perf_capabilities(void) { u64 perf_cap = PMU_CAP_FW_WRITES; + struct x86_pmu_lbr lbr; u64 host_perf_cap = 0; if (!enable_pmu) @@ -408,7 +407,8 @@ static inline u64 vmx_get_perf_capabilities(void) if (boot_cpu_has(X86_FEATURE_PDCM)) rdmsrl(MSR_IA32_PERF_CAPABILITIES, host_perf_cap); - perf_cap |= host_perf_cap & PMU_CAP_LBR_FMT; + if (x86_perf_get_lbr(&lbr) >= 0 && lbr.nr) + perf_cap |= host_perf_cap & PMU_CAP_LBR_FMT; if (vmx_pebs_supported()) { perf_cap |= host_perf_cap & PERF_CAP_PEBS_MASK; @@ -419,19 +419,6 @@ static inline u64 vmx_get_perf_capabilities(void) return perf_cap; } -static inline u64 vmx_supported_debugctl(void) -{ - u64 debugctl = 0; - - if (boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT)) - debugctl |= DEBUGCTLMSR_BUS_LOCK_DETECT; - - if (vmx_get_perf_capabilities() & PMU_CAP_LBR_FMT) - debugctl |= DEBUGCTLMSR_LBR_MASK; - - return debugctl; -} - static inline bool cpu_has_notify_vmexit(void) { return vmcs_config.cpu_based_2nd_exec_ctrl & diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 65f092e4a81b..63247c57c72c 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -2021,15 +2021,17 @@ static u64 nested_vmx_truncate_sysenter_addr(struct kvm_vcpu *vcpu, return (unsigned long)data; } -static u64 vcpu_supported_debugctl(struct kvm_vcpu *vcpu) +static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated) { - u64 debugctl = vmx_supported_debugctl(); + u64 debugctl = 0; - if (!intel_pmu_lbr_is_enabled(vcpu)) - debugctl &= ~DEBUGCTLMSR_LBR_MASK; + if (boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT) && + (host_initiated || guest_cpuid_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT))) + debugctl |= DEBUGCTLMSR_BUS_LOCK_DETECT; - if (!guest_cpuid_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT)) - debugctl &= ~DEBUGCTLMSR_BUS_LOCK_DETECT; + if ((vmx_get_perf_capabilities() & PMU_CAP_LBR_FMT) && + (host_initiated || intel_pmu_lbr_is_enabled(vcpu))) + debugctl |= DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI; return debugctl; } @@ -2103,7 +2105,9 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) vmcs_writel(GUEST_SYSENTER_ESP, data); break; case MSR_IA32_DEBUGCTLMSR: { - u64 invalid = data & ~vcpu_supported_debugctl(vcpu); + u64 invalid; + + invalid = data & ~vmx_get_supported_debugctl(vcpu, msr_info->host_initiated); if (invalid & (DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR)) { if (report_ignored_msrs) vcpu_unimpl(vcpu, "%s: BTF|LBR in IA32_DEBUGCTLMSR 0x%llx, nop\n", diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 521b433f978c..5f5eb577d583 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -10404,7 +10404,10 @@ void __kvm_set_or_clear_apicv_inhibit(struct kvm *kvm, kvm->arch.apicv_inhibit_reasons = new; if (new) { unsigned long gfn = gpa_to_gfn(APIC_DEFAULT_PHYS_BASE); + int idx = srcu_read_lock(&kvm->srcu); + kvm_zap_gfn_range(kvm, gfn, gfn+1); + srcu_read_unlock(&kvm->srcu, idx); } } else { kvm->arch.apicv_inhibit_reasons = new; diff --git a/arch/x86/xen/pmu.c b/arch/x86/xen/pmu.c index 68aff1382872..246d67dab510 100644 --- a/arch/x86/xen/pmu.c +++ b/arch/x86/xen/pmu.c @@ -302,7 +302,7 @@ static bool xen_amd_pmu_emulate(unsigned int msr, u64 *val, bool is_read) static bool pmu_msr_chk_emulated(unsigned int msr, uint64_t *val, bool is_read, bool *emul) { - int type, index; + int type, index = 0; if (is_amd_pmu_msr(msr)) *emul = xen_amd_pmu_emulate(msr, val, is_read); diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index cfa99e8f054b..4f4309500559 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -910,17 +910,9 @@ static int register_callback(unsigned type, const void *func) void xen_enable_sysenter(void) { - int ret; - unsigned sysenter_feature; - - sysenter_feature = X86_FEATURE_SYSENTER32; - - if (!boot_cpu_has(sysenter_feature)) - return; - - ret = register_callback(CALLBACKTYPE_sysenter, xen_entry_SYSENTER_compat); - if(ret != 0) - setup_clear_cpu_cap(sysenter_feature); + if (cpu_feature_enabled(X86_FEATURE_SYSENTER32) && + register_callback(CALLBACKTYPE_sysenter, xen_entry_SYSENTER_compat)) + setup_clear_cpu_cap(X86_FEATURE_SYSENTER32); } void xen_enable_syscall(void) @@ -934,12 +926,9 @@ void xen_enable_syscall(void) mechanism for syscalls. */ } - if (boot_cpu_has(X86_FEATURE_SYSCALL32)) { - ret = register_callback(CALLBACKTYPE_syscall32, - xen_entry_SYSCALL_compat); - if (ret != 0) - setup_clear_cpu_cap(X86_FEATURE_SYSCALL32); - } + if (cpu_feature_enabled(X86_FEATURE_SYSCALL32) && + register_callback(CALLBACKTYPE_syscall32, xen_entry_SYSCALL_compat)) + setup_clear_cpu_cap(X86_FEATURE_SYSCALL32); } static void __init xen_pvmmu_arch_setup(void) diff --git a/block/blk-mq.c b/block/blk-mq.c index 75c8296b6feb..6a789cda68a5 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1262,6 +1262,7 @@ static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq) (!blk_queue_nomerges(rq->q) && blk_rq_bytes(last) >= BLK_PLUG_FLUSH_SIZE)) { blk_mq_flush_plug_list(plug, false); + last = NULL; trace_block_plug(rq->q); } @@ -4193,9 +4194,7 @@ int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, return 0; err_hctxs: - xa_destroy(&q->hctx_table); - q->nr_hw_queues = 0; - blk_mq_sysfs_deinit(q); + blk_mq_release(q); err_poll: blk_stat_free_callback(q->poll_cb); q->poll_cb = NULL; diff --git a/block/genhd.c b/block/genhd.c index fee90eb98b4a..0f9769db2de8 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -527,6 +527,7 @@ out_unregister_bdi: bdi_unregister(disk->bdi); out_unregister_queue: blk_unregister_queue(disk); + rq_qos_exit(disk->queue); out_put_slave_dir: kobject_put(disk->slave_dir); out_put_holder_dir: diff --git a/drivers/acpi/numa/srat.c b/drivers/acpi/numa/srat.c index 3b818ab186be..1f4fc5f8a819 100644 --- a/drivers/acpi/numa/srat.c +++ b/drivers/acpi/numa/srat.c @@ -327,6 +327,7 @@ static int __init acpi_parse_cfmws(union acpi_subtable_headers *header, pr_warn("ACPI NUMA: Failed to add memblk for CFMWS node %d [mem %#llx-%#llx]\n", node, start, end); } + node_set(node, numa_nodes_parsed); /* Set the next available fake_pxm value */ (*fake_pxm)++; diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index 9cd8797d12bb..b2a616287638 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -646,6 +646,20 @@ static const struct dmi_system_id video_detect_dmi_table[] = { }, /* + * Models which have nvidia-ec-wmi support, but should not use it. + * Note this indicates a likely firmware bug on these models and should + * be revisited if/when Linux gets support for dynamic mux mode. + */ + { + .callback = video_detect_force_native, + /* Dell G15 5515 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Dell G15 5515"), + }, + }, + + /* * Desktops which falsely report a backlight and which our heuristics * for this do not catch. */ @@ -670,7 +684,7 @@ static const struct dmi_system_id video_detect_dmi_table[] = { static bool google_cros_ec_present(void) { - return acpi_dev_found("GOOG0004"); + return acpi_dev_found("GOOG0004") || acpi_dev_found("GOOG000C"); } /* @@ -718,6 +732,10 @@ static enum acpi_backlight_type __acpi_video_get_backlight_type(bool native) if (apple_gmux_present()) return acpi_backlight_apple_gmux; + /* Chromebooks should always prefer native backlight control. */ + if (google_cros_ec_present() && native_available) + return acpi_backlight_native; + /* On systems with ACPI video use either native or ACPI video. */ if (video_caps & ACPI_VIDEO_BACKLIGHT) { /* @@ -735,13 +753,6 @@ static enum acpi_backlight_type __acpi_video_get_backlight_type(bool native) return acpi_backlight_video; } - /* - * Chromebooks that don't have backlight handle in ACPI table - * are supposed to use native backlight if it's available. - */ - if (google_cros_ec_present() && native_available) - return acpi_backlight_native; - /* No ACPI video (old hw), use vendor specific fw methods. */ return acpi_backlight_vendor; } @@ -754,6 +765,18 @@ EXPORT_SYMBOL(acpi_video_get_backlight_type); bool acpi_video_backlight_use_native(void) { - return __acpi_video_get_backlight_type(true) == acpi_backlight_native; + /* + * Call __acpi_video_get_backlight_type() to let it know that + * a native backlight is available. + */ + __acpi_video_get_backlight_type(true); + + /* + * For now just always return true. There is a whole bunch of laptop + * models where (video_caps & ACPI_VIDEO_BACKLIGHT) is false causing + * __acpi_video_get_backlight_type() to return vendor, while these + * models only have a native backlight control. + */ + return true; } EXPORT_SYMBOL(acpi_video_backlight_use_native); diff --git a/drivers/acpi/x86/utils.c b/drivers/acpi/x86/utils.c index f8a2cbdc0ce2..d7d3f1669d4c 100644 --- a/drivers/acpi/x86/utils.c +++ b/drivers/acpi/x86/utils.c @@ -219,6 +219,12 @@ static const struct dmi_system_id force_storage_d3_dmi[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 14 7425 2-in-1"), } }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 16 5625"), + } + }, {} }; diff --git a/drivers/ata/pata_legacy.c b/drivers/ata/pata_legacy.c index 0a8bf09a5c19..03c580625c2c 100644 --- a/drivers/ata/pata_legacy.c +++ b/drivers/ata/pata_legacy.c @@ -315,9 +315,10 @@ static void pdc20230_set_piomode(struct ata_port *ap, struct ata_device *adev) outb(inb(0x1F4) & 0x07, 0x1F4); rt = inb(0x1F3); - rt &= 0x07 << (3 * adev->devno); + rt &= ~(0x07 << (3 * !adev->devno)); if (pio) - rt |= (1 + 3 * pio) << (3 * adev->devno); + rt |= (1 + 3 * pio) << (3 * !adev->devno); + outb(rt, 0x1F3); udelay(100); outb(inb(0x1F2) | 0x01, 0x1F2); diff --git a/drivers/ata/pata_palmld.c b/drivers/ata/pata_palmld.c index 400e65190904..51caa2a427dd 100644 --- a/drivers/ata/pata_palmld.c +++ b/drivers/ata/pata_palmld.c @@ -63,8 +63,8 @@ static int palmld_pata_probe(struct platform_device *pdev) /* remap drive's physical memory address */ mem = devm_platform_ioremap_resource(pdev, 0); - if (!mem) - return -ENOMEM; + if (IS_ERR(mem)) + return PTR_ERR(mem); /* request and activate power and reset GPIOs */ lda->power = devm_gpiod_get(dev, "power", GPIOD_OUT_HIGH); diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig index db1b4b202646..a41145d52de9 100644 --- a/drivers/block/Kconfig +++ b/drivers/block/Kconfig @@ -408,6 +408,12 @@ config BLK_DEV_UBLK definition isn't finalized yet, and might change according to future requirement, so mark is as experimental now. + Say Y if you want to get better performance because task_work_add() + can be used in IO path for replacing io_uring cmd, which will become + shared between IO tasks and ubq daemon, meantime task_work_add() can + can handle batch more effectively, but task_work_add() isn't exported + for module, so ublk has to be built to kernel. + source "drivers/block/rnbd/Kconfig" endif # BLK_DEV diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 5afce6ffaadf..f96cb01e9604 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -57,11 +57,14 @@ #define UBLK_PARAM_TYPE_ALL (UBLK_PARAM_TYPE_BASIC | UBLK_PARAM_TYPE_DISCARD) struct ublk_rq_data { - struct callback_head work; + union { + struct callback_head work; + struct llist_node node; + }; }; struct ublk_uring_cmd_pdu { - struct request *req; + struct ublk_queue *ubq; }; /* @@ -119,6 +122,8 @@ struct ublk_queue { struct task_struct *ubq_daemon; char *io_cmd_buf; + struct llist_head io_cmds; + unsigned long io_addr; /* mapped vm address */ unsigned int max_io_sz; bool force_abort; @@ -764,8 +769,12 @@ static inline void __ublk_rq_task_work(struct request *req) static void ublk_rq_task_work_cb(struct io_uring_cmd *cmd) { struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd); + struct ublk_queue *ubq = pdu->ubq; + struct llist_node *io_cmds = llist_del_all(&ubq->io_cmds); + struct ublk_rq_data *data; - __ublk_rq_task_work(pdu->req); + llist_for_each_entry(data, io_cmds, node) + __ublk_rq_task_work(blk_mq_rq_from_pdu(data)); } static void ublk_rq_task_work_fn(struct callback_head *work) @@ -777,6 +786,54 @@ static void ublk_rq_task_work_fn(struct callback_head *work) __ublk_rq_task_work(req); } +static void ublk_submit_cmd(struct ublk_queue *ubq, const struct request *rq) +{ + struct ublk_io *io = &ubq->ios[rq->tag]; + + /* + * If the check pass, we know that this is a re-issued request aborted + * previously in monitor_work because the ubq_daemon(cmd's task) is + * PF_EXITING. We cannot call io_uring_cmd_complete_in_task() anymore + * because this ioucmd's io_uring context may be freed now if no inflight + * ioucmd exists. Otherwise we may cause null-deref in ctx->fallback_work. + * + * Note: monitor_work sets UBLK_IO_FLAG_ABORTED and ends this request(releasing + * the tag). Then the request is re-started(allocating the tag) and we are here. + * Since releasing/allocating a tag implies smp_mb(), finding UBLK_IO_FLAG_ABORTED + * guarantees that here is a re-issued request aborted previously. + */ + if (unlikely(io->flags & UBLK_IO_FLAG_ABORTED)) { + struct llist_node *io_cmds = llist_del_all(&ubq->io_cmds); + struct ublk_rq_data *data; + + llist_for_each_entry(data, io_cmds, node) + __ublk_abort_rq(ubq, blk_mq_rq_from_pdu(data)); + } else { + struct io_uring_cmd *cmd = io->cmd; + struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd); + + pdu->ubq = ubq; + io_uring_cmd_complete_in_task(cmd, ublk_rq_task_work_cb); + } +} + +static void ublk_queue_cmd(struct ublk_queue *ubq, struct request *rq, + bool last) +{ + struct ublk_rq_data *data = blk_mq_rq_to_pdu(rq); + + if (ublk_can_use_task_work(ubq)) { + enum task_work_notify_mode notify_mode = last ? + TWA_SIGNAL_NO_IPI : TWA_NONE; + + if (task_work_add(ubq->ubq_daemon, &data->work, notify_mode)) + __ublk_abort_rq(ubq, rq); + } else { + if (llist_add(&data->node, &ubq->io_cmds)) + ublk_submit_cmd(ubq, rq); + } +} + static blk_status_t ublk_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { @@ -788,6 +845,7 @@ static blk_status_t ublk_queue_rq(struct blk_mq_hw_ctx *hctx, res = ublk_setup_iod(ubq, rq); if (unlikely(res != BLK_STS_OK)) return BLK_STS_IOERR; + /* With recovery feature enabled, force_abort is set in * ublk_stop_dev() before calling del_gendisk(). We have to * abort all requeued and new rqs here to let del_gendisk() @@ -803,41 +861,11 @@ static blk_status_t ublk_queue_rq(struct blk_mq_hw_ctx *hctx, blk_mq_start_request(bd->rq); if (unlikely(ubq_daemon_is_dying(ubq))) { - fail: __ublk_abort_rq(ubq, rq); return BLK_STS_OK; } - if (ublk_can_use_task_work(ubq)) { - struct ublk_rq_data *data = blk_mq_rq_to_pdu(rq); - enum task_work_notify_mode notify_mode = bd->last ? - TWA_SIGNAL_NO_IPI : TWA_NONE; - - if (task_work_add(ubq->ubq_daemon, &data->work, notify_mode)) - goto fail; - } else { - struct ublk_io *io = &ubq->ios[rq->tag]; - struct io_uring_cmd *cmd = io->cmd; - struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd); - - /* - * If the check pass, we know that this is a re-issued request aborted - * previously in monitor_work because the ubq_daemon(cmd's task) is - * PF_EXITING. We cannot call io_uring_cmd_complete_in_task() anymore - * because this ioucmd's io_uring context may be freed now if no inflight - * ioucmd exists. Otherwise we may cause null-deref in ctx->fallback_work. - * - * Note: monitor_work sets UBLK_IO_FLAG_ABORTED and ends this request(releasing - * the tag). Then the request is re-started(allocating the tag) and we are here. - * Since releasing/allocating a tag implies smp_mb(), finding UBLK_IO_FLAG_ABORTED - * guarantees that here is a re-issued request aborted previously. - */ - if ((io->flags & UBLK_IO_FLAG_ABORTED)) - goto fail; - - pdu->req = rq; - io_uring_cmd_complete_in_task(cmd, ublk_rq_task_work_cb); - } + ublk_queue_cmd(ubq, rq, bd->last); return BLK_STS_OK; } @@ -1164,22 +1192,12 @@ static void ublk_mark_io_ready(struct ublk_device *ub, struct ublk_queue *ubq) } static void ublk_handle_need_get_data(struct ublk_device *ub, int q_id, - int tag, struct io_uring_cmd *cmd) + int tag) { struct ublk_queue *ubq = ublk_get_queue(ub, q_id); struct request *req = blk_mq_tag_to_rq(ub->tag_set.tags[q_id], tag); - if (ublk_can_use_task_work(ubq)) { - struct ublk_rq_data *data = blk_mq_rq_to_pdu(req); - - /* should not fail since we call it just in ubq->ubq_daemon */ - task_work_add(ubq->ubq_daemon, &data->work, TWA_SIGNAL_NO_IPI); - } else { - struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd); - - pdu->req = req; - io_uring_cmd_complete_in_task(cmd, ublk_rq_task_work_cb); - } + ublk_queue_cmd(ubq, req, true); } static int ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) @@ -1267,7 +1285,7 @@ static int ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) io->addr = ub_cmd->addr; io->cmd = cmd; io->flags |= UBLK_IO_FLAG_ACTIVE; - ublk_handle_need_get_data(ub, ub_cmd->q_id, ub_cmd->tag, cmd); + ublk_handle_need_get_data(ub, ub_cmd->q_id, ub_cmd->tag); break; default: goto out; @@ -1658,6 +1676,9 @@ static int ublk_ctrl_add_dev(struct io_uring_cmd *cmd) */ ub->dev_info.flags &= UBLK_F_ALL; + if (!IS_BUILTIN(CONFIG_BLK_DEV_UBLK)) + ub->dev_info.flags |= UBLK_F_URING_CMD_COMP_IN_TASK; + /* We are not ready to support zero copy */ ub->dev_info.flags &= ~UBLK_F_SUPPORT_ZERO_COPY; diff --git a/drivers/clk/clk-renesas-pcie.c b/drivers/clk/clk-renesas-pcie.c index 4f5df1fc74b4..e6247141d0c0 100644 --- a/drivers/clk/clk-renesas-pcie.c +++ b/drivers/clk/clk-renesas-pcie.c @@ -90,13 +90,66 @@ static const struct regmap_access_table rs9_writeable_table = { .n_yes_ranges = ARRAY_SIZE(rs9_writeable_ranges), }; +static int rs9_regmap_i2c_write(void *context, + unsigned int reg, unsigned int val) +{ + struct i2c_client *i2c = context; + const u8 data[3] = { reg, 1, val }; + const int count = ARRAY_SIZE(data); + int ret; + + ret = i2c_master_send(i2c, data, count); + if (ret == count) + return 0; + else if (ret < 0) + return ret; + else + return -EIO; +} + +static int rs9_regmap_i2c_read(void *context, + unsigned int reg, unsigned int *val) +{ + struct i2c_client *i2c = context; + struct i2c_msg xfer[2]; + u8 txdata = reg; + u8 rxdata[2]; + int ret; + + xfer[0].addr = i2c->addr; + xfer[0].flags = 0; + xfer[0].len = 1; + xfer[0].buf = (void *)&txdata; + + xfer[1].addr = i2c->addr; + xfer[1].flags = I2C_M_RD; + xfer[1].len = 2; + xfer[1].buf = (void *)rxdata; + + ret = i2c_transfer(i2c->adapter, xfer, 2); + if (ret < 0) + return ret; + if (ret != 2) + return -EIO; + + /* + * Byte 0 is transfer length, which is always 1 due + * to BCP register programming to 1 in rs9_probe(), + * ignore it and use data from Byte 1. + */ + *val = rxdata[1]; + return 0; +} + static const struct regmap_config rs9_regmap_config = { .reg_bits = 8, .val_bits = 8, - .cache_type = REGCACHE_FLAT, - .max_register = 0x8, + .cache_type = REGCACHE_NONE, + .max_register = RS9_REG_BCP, .rd_table = &rs9_readable_table, .wr_table = &rs9_writeable_table, + .reg_write = rs9_regmap_i2c_write, + .reg_read = rs9_regmap_i2c_read, }; static int rs9_get_output_config(struct rs9_driver_data *rs9, int idx) @@ -242,11 +295,17 @@ static int rs9_probe(struct i2c_client *client) return ret; } - rs9->regmap = devm_regmap_init_i2c(client, &rs9_regmap_config); + rs9->regmap = devm_regmap_init(&client->dev, NULL, + client, &rs9_regmap_config); if (IS_ERR(rs9->regmap)) return dev_err_probe(&client->dev, PTR_ERR(rs9->regmap), "Failed to allocate register map\n"); + /* Always read back 1 Byte via I2C */ + ret = regmap_write(rs9->regmap, RS9_REG_BCP, 1); + if (ret < 0) + return ret; + /* Register clock */ for (i = 0; i < rs9->chip_info->num_clks; i++) { snprintf(name, 5, "DIF%d", i); diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index c3c3f8c07258..57b83665e5c3 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -1459,10 +1459,14 @@ static void clk_core_init_rate_req(struct clk_core * const core, { struct clk_core *parent; - if (WARN_ON(!core || !req)) + if (WARN_ON(!req)) return; memset(req, 0, sizeof(*req)); + req->max_rate = ULONG_MAX; + + if (!core) + return; req->rate = rate; clk_core_get_boundaries(core, &req->min_rate, &req->max_rate); diff --git a/drivers/clk/mediatek/clk-mt8195-topckgen.c b/drivers/clk/mediatek/clk-mt8195-topckgen.c index 8cbab5ca2e58..1e016329c1d2 100644 --- a/drivers/clk/mediatek/clk-mt8195-topckgen.c +++ b/drivers/clk/mediatek/clk-mt8195-topckgen.c @@ -1270,8 +1270,10 @@ static int clk_mt8195_topck_probe(struct platform_device *pdev) hw = devm_clk_hw_register_mux(&pdev->dev, "mfg_ck_fast_ref", mfg_fast_parents, ARRAY_SIZE(mfg_fast_parents), CLK_SET_RATE_PARENT, (base + 0x250), 8, 1, 0, &mt8195_clk_lock); - if (IS_ERR(hw)) + if (IS_ERR(hw)) { + r = PTR_ERR(hw); goto unregister_muxes; + } top_clk_data->hws[CLK_TOP_MFG_CK_FAST_REF] = hw; r = clk_mt8195_reg_mfg_mux_notifier(&pdev->dev, diff --git a/drivers/clk/qcom/gcc-sc7280.c b/drivers/clk/qcom/gcc-sc7280.c index 8afb7575e712..46d41ebce2b0 100644 --- a/drivers/clk/qcom/gcc-sc7280.c +++ b/drivers/clk/qcom/gcc-sc7280.c @@ -3467,6 +3467,7 @@ static int gcc_sc7280_probe(struct platform_device *pdev) regmap_update_bits(regmap, 0x28004, BIT(0), BIT(0)); regmap_update_bits(regmap, 0x28014, BIT(0), BIT(0)); regmap_update_bits(regmap, 0x71004, BIT(0), BIT(0)); + regmap_update_bits(regmap, 0x7100C, BIT(13), BIT(13)); ret = qcom_cc_register_rcg_dfs(regmap, gcc_dfs_clocks, ARRAY_SIZE(gcc_dfs_clocks)); diff --git a/drivers/clk/qcom/gpucc-sc7280.c b/drivers/clk/qcom/gpucc-sc7280.c index 9a832f2bcf49..1490cd45a654 100644 --- a/drivers/clk/qcom/gpucc-sc7280.c +++ b/drivers/clk/qcom/gpucc-sc7280.c @@ -463,6 +463,7 @@ static int gpu_cc_sc7280_probe(struct platform_device *pdev) */ regmap_update_bits(regmap, 0x1170, BIT(0), BIT(0)); regmap_update_bits(regmap, 0x1098, BIT(0), BIT(0)); + regmap_update_bits(regmap, 0x1098, BIT(13), BIT(13)); return qcom_cc_really_probe(pdev, &gpu_cc_sc7280_desc, regmap); } diff --git a/drivers/clk/renesas/r8a779g0-cpg-mssr.c b/drivers/clk/renesas/r8a779g0-cpg-mssr.c index 9641122133b5..d5b325e3c539 100644 --- a/drivers/clk/renesas/r8a779g0-cpg-mssr.c +++ b/drivers/clk/renesas/r8a779g0-cpg-mssr.c @@ -47,6 +47,7 @@ enum clk_ids { CLK_S0_VIO, CLK_S0_VC, CLK_S0_HSC, + CLK_SASYNCPER, CLK_SV_VIP, CLK_SV_IR, CLK_SDSRC, @@ -84,6 +85,7 @@ static const struct cpg_core_clk r8a779g0_core_clks[] __initconst = { DEF_FIXED(".s0_vio", CLK_S0_VIO, CLK_PLL1_DIV2, 2, 1), DEF_FIXED(".s0_vc", CLK_S0_VC, CLK_PLL1_DIV2, 2, 1), DEF_FIXED(".s0_hsc", CLK_S0_HSC, CLK_PLL1_DIV2, 2, 1), + DEF_FIXED(".sasyncper", CLK_SASYNCPER, CLK_PLL5_DIV4, 3, 1), DEF_FIXED(".sv_vip", CLK_SV_VIP, CLK_PLL1, 5, 1), DEF_FIXED(".sv_ir", CLK_SV_IR, CLK_PLL1, 5, 1), DEF_BASE(".sdsrc", CLK_SDSRC, CLK_TYPE_GEN4_SDSRC, CLK_PLL5), @@ -128,6 +130,9 @@ static const struct cpg_core_clk r8a779g0_core_clks[] __initconst = { DEF_FIXED("s0d4_hsc", R8A779G0_CLK_S0D4_HSC, CLK_S0_HSC, 4, 1), DEF_FIXED("cl16m_hsc", R8A779G0_CLK_CL16M_HSC, CLK_S0_HSC, 48, 1), DEF_FIXED("s0d2_cc", R8A779G0_CLK_S0D2_CC, CLK_S0, 2, 1), + DEF_FIXED("sasyncperd1",R8A779G0_CLK_SASYNCPERD1, CLK_SASYNCPER,1, 1), + DEF_FIXED("sasyncperd2",R8A779G0_CLK_SASYNCPERD2, CLK_SASYNCPER,2, 1), + DEF_FIXED("sasyncperd4",R8A779G0_CLK_SASYNCPERD4, CLK_SASYNCPER,4, 1), DEF_FIXED("svd1_ir", R8A779G0_CLK_SVD1_IR, CLK_SV_IR, 1, 1), DEF_FIXED("svd2_ir", R8A779G0_CLK_SVD2_IR, CLK_SV_IR, 2, 1), DEF_FIXED("svd1_vip", R8A779G0_CLK_SVD1_VIP, CLK_SV_VIP, 1, 1), @@ -153,10 +158,10 @@ static const struct mssr_mod_clk r8a779g0_mod_clks[] __initconst = { DEF_MOD("avb0", 211, R8A779G0_CLK_S0D4_HSC), DEF_MOD("avb1", 212, R8A779G0_CLK_S0D4_HSC), DEF_MOD("avb2", 213, R8A779G0_CLK_S0D4_HSC), - DEF_MOD("hscif0", 514, R8A779G0_CLK_S0D3_PER), - DEF_MOD("hscif1", 515, R8A779G0_CLK_S0D3_PER), - DEF_MOD("hscif2", 516, R8A779G0_CLK_S0D3_PER), - DEF_MOD("hscif3", 517, R8A779G0_CLK_S0D3_PER), + DEF_MOD("hscif0", 514, R8A779G0_CLK_SASYNCPERD1), + DEF_MOD("hscif1", 515, R8A779G0_CLK_SASYNCPERD1), + DEF_MOD("hscif2", 516, R8A779G0_CLK_SASYNCPERD1), + DEF_MOD("hscif3", 517, R8A779G0_CLK_SASYNCPERD1), DEF_MOD("i2c0", 518, R8A779G0_CLK_S0D6_PER), DEF_MOD("i2c1", 519, R8A779G0_CLK_S0D6_PER), DEF_MOD("i2c2", 520, R8A779G0_CLK_S0D6_PER), diff --git a/drivers/clk/sifive/Kconfig b/drivers/clk/sifive/Kconfig index 9132c3c4aa86..b7fde0aadfcb 100644 --- a/drivers/clk/sifive/Kconfig +++ b/drivers/clk/sifive/Kconfig @@ -2,7 +2,8 @@ menuconfig CLK_SIFIVE bool "SiFive SoC driver support" - depends on RISCV || COMPILE_TEST + depends on SOC_SIFIVE || COMPILE_TEST + default SOC_SIFIVE help SoC drivers for SiFive Linux-capable SoCs. @@ -10,6 +11,7 @@ if CLK_SIFIVE config CLK_SIFIVE_PRCI bool "PRCI driver for SiFive SoCs" + default SOC_SIFIVE select RESET_CONTROLLER select RESET_SIMPLE select CLK_ANALOGBITS_WRPLL_CLN28HPC diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index 16176b9278b4..0c90f13870a4 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -174,7 +174,7 @@ int cxl_mbox_send_cmd(struct cxl_dev_state *cxlds, u16 opcode, void *in, }; int rc; - if (out_size > cxlds->payload_size) + if (in_size > cxlds->payload_size || out_size > cxlds->payload_size) return -E2BIG; rc = cxlds->mbox_send(cxlds, &mbox_cmd); diff --git a/drivers/cxl/core/pmem.c b/drivers/cxl/core/pmem.c index 1d12a8206444..36aa5070d902 100644 --- a/drivers/cxl/core/pmem.c +++ b/drivers/cxl/core/pmem.c @@ -188,6 +188,7 @@ static void cxl_nvdimm_release(struct device *dev) { struct cxl_nvdimm *cxl_nvd = to_cxl_nvdimm(dev); + xa_destroy(&cxl_nvd->pmem_regions); kfree(cxl_nvd); } @@ -230,6 +231,7 @@ static struct cxl_nvdimm *cxl_nvdimm_alloc(struct cxl_memdev *cxlmd) dev = &cxl_nvd->dev; cxl_nvd->cxlmd = cxlmd; + xa_init(&cxl_nvd->pmem_regions); device_initialize(dev); lockdep_set_class(&dev->mutex, &cxl_nvdimm_key); device_set_pm_not_required(dev); diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c index bffde862de0b..e7556864ea80 100644 --- a/drivers/cxl/core/port.c +++ b/drivers/cxl/core/port.c @@ -811,6 +811,7 @@ static struct cxl_dport *find_dport(struct cxl_port *port, int id) static int add_dport(struct cxl_port *port, struct cxl_dport *new) { struct cxl_dport *dup; + int rc; device_lock_assert(&port->dev); dup = find_dport(port, new->port_id); @@ -821,8 +822,14 @@ static int add_dport(struct cxl_port *port, struct cxl_dport *new) dev_name(dup->dport)); return -EBUSY; } - return xa_insert(&port->dports, (unsigned long)new->dport, new, - GFP_KERNEL); + + rc = xa_insert(&port->dports, (unsigned long)new->dport, new, + GFP_KERNEL); + if (rc) + return rc; + + port->nr_dports++; + return 0; } /* diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c index 401148016978..f9ae5ad284ff 100644 --- a/drivers/cxl/core/region.c +++ b/drivers/cxl/core/region.c @@ -174,7 +174,8 @@ static int cxl_region_decode_commit(struct cxl_region *cxlr) iter = to_cxl_port(iter->dev.parent)) { cxl_rr = cxl_rr_load(iter, cxlr); cxld = cxl_rr->decoder; - rc = cxld->commit(cxld); + if (cxld->commit) + rc = cxld->commit(cxld); if (rc) break; } @@ -657,6 +658,9 @@ static struct cxl_region_ref *alloc_region_ref(struct cxl_port *port, xa_for_each(&port->regions, index, iter) { struct cxl_region_params *ip = &iter->region->params; + if (!ip->res) + continue; + if (ip->res->start > p->res->start) { dev_dbg(&cxlr->dev, "%s: HPA order violation %s:%pr vs %pr\n", @@ -686,18 +690,27 @@ static struct cxl_region_ref *alloc_region_ref(struct cxl_port *port, return cxl_rr; } -static void free_region_ref(struct cxl_region_ref *cxl_rr) +static void cxl_rr_free_decoder(struct cxl_region_ref *cxl_rr) { - struct cxl_port *port = cxl_rr->port; struct cxl_region *cxlr = cxl_rr->region; struct cxl_decoder *cxld = cxl_rr->decoder; + if (!cxld) + return; + dev_WARN_ONCE(&cxlr->dev, cxld->region != cxlr, "region mismatch\n"); if (cxld->region == cxlr) { cxld->region = NULL; put_device(&cxlr->dev); } +} +static void free_region_ref(struct cxl_region_ref *cxl_rr) +{ + struct cxl_port *port = cxl_rr->port; + struct cxl_region *cxlr = cxl_rr->region; + + cxl_rr_free_decoder(cxl_rr); xa_erase(&port->regions, (unsigned long)cxlr); xa_destroy(&cxl_rr->endpoints); kfree(cxl_rr); @@ -728,6 +741,33 @@ static int cxl_rr_ep_add(struct cxl_region_ref *cxl_rr, return 0; } +static int cxl_rr_alloc_decoder(struct cxl_port *port, struct cxl_region *cxlr, + struct cxl_endpoint_decoder *cxled, + struct cxl_region_ref *cxl_rr) +{ + struct cxl_decoder *cxld; + + if (port == cxled_to_port(cxled)) + cxld = &cxled->cxld; + else + cxld = cxl_region_find_decoder(port, cxlr); + if (!cxld) { + dev_dbg(&cxlr->dev, "%s: no decoder available\n", + dev_name(&port->dev)); + return -EBUSY; + } + + if (cxld->region) { + dev_dbg(&cxlr->dev, "%s: %s already attached to %s\n", + dev_name(&port->dev), dev_name(&cxld->dev), + dev_name(&cxld->region->dev)); + return -EBUSY; + } + + cxl_rr->decoder = cxld; + return 0; +} + /** * cxl_port_attach_region() - track a region's interest in a port by endpoint * @port: port to add a new region reference 'struct cxl_region_ref' @@ -794,12 +834,6 @@ static int cxl_port_attach_region(struct cxl_port *port, cxl_rr->nr_targets++; nr_targets_inc = true; } - - /* - * The decoder for @cxlr was allocated when the region was first - * attached to @port. - */ - cxld = cxl_rr->decoder; } else { cxl_rr = alloc_region_ref(port, cxlr); if (IS_ERR(cxl_rr)) { @@ -810,26 +844,11 @@ static int cxl_port_attach_region(struct cxl_port *port, } nr_targets_inc = true; - if (port == cxled_to_port(cxled)) - cxld = &cxled->cxld; - else - cxld = cxl_region_find_decoder(port, cxlr); - if (!cxld) { - dev_dbg(&cxlr->dev, "%s: no decoder available\n", - dev_name(&port->dev)); - goto out_erase; - } - - if (cxld->region) { - dev_dbg(&cxlr->dev, "%s: %s already attached to %s\n", - dev_name(&port->dev), dev_name(&cxld->dev), - dev_name(&cxld->region->dev)); - rc = -EBUSY; + rc = cxl_rr_alloc_decoder(port, cxlr, cxled, cxl_rr); + if (rc) goto out_erase; - } - - cxl_rr->decoder = cxld; } + cxld = cxl_rr->decoder; rc = cxl_rr_ep_add(cxl_rr, cxled); if (rc) { @@ -971,7 +990,14 @@ static int cxl_port_setup_targets(struct cxl_port *port, if (cxl_rr->nr_targets_set) { int i, distance; - distance = p->nr_targets / cxl_rr->nr_targets; + /* + * Passthrough ports impose no distance requirements between + * peers + */ + if (port->nr_dports == 1) + distance = 0; + else + distance = p->nr_targets / cxl_rr->nr_targets; for (i = 0; i < cxl_rr->nr_targets_set; i++) if (ep->dport == cxlsd->target[i]) { rc = check_last_peer(cxled, ep, cxl_rr, @@ -1508,9 +1534,24 @@ static const struct attribute_group *region_groups[] = { static void cxl_region_release(struct device *dev) { + struct cxl_root_decoder *cxlrd = to_cxl_root_decoder(dev->parent); struct cxl_region *cxlr = to_cxl_region(dev); + int id = atomic_read(&cxlrd->region_id); + + /* + * Try to reuse the recently idled id rather than the cached + * next id to prevent the region id space from increasing + * unnecessarily. + */ + if (cxlr->id < id) + if (atomic_try_cmpxchg(&cxlrd->region_id, &id, cxlr->id)) { + memregion_free(id); + goto out; + } memregion_free(cxlr->id); +out: + put_device(dev->parent); kfree(cxlr); } @@ -1538,8 +1579,19 @@ static struct cxl_region *to_cxl_region(struct device *dev) static void unregister_region(void *dev) { struct cxl_region *cxlr = to_cxl_region(dev); + struct cxl_region_params *p = &cxlr->params; + int i; device_del(dev); + + /* + * Now that region sysfs is shutdown, the parameter block is now + * read-only, so no need to hold the region rwsem to access the + * region parameters. + */ + for (i = 0; i < p->interleave_ways; i++) + detach_target(cxlr, i); + cxl_region_iomem_release(cxlr); put_device(dev); } @@ -1561,6 +1613,11 @@ static struct cxl_region *cxl_region_alloc(struct cxl_root_decoder *cxlrd, int i device_initialize(dev); lockdep_set_class(&dev->mutex, &cxl_region_key); dev->parent = &cxlrd->cxlsd.cxld.dev; + /* + * Keep root decoder pinned through cxl_region_release to fixup + * region id allocations + */ + get_device(dev->parent); device_set_pm_not_required(dev); dev->bus = &cxl_bus_type; dev->type = &cxl_region_type; diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h index f680450f0b16..ac75554b5d76 100644 --- a/drivers/cxl/cxl.h +++ b/drivers/cxl/cxl.h @@ -423,7 +423,7 @@ struct cxl_nvdimm { struct device dev; struct cxl_memdev *cxlmd; struct cxl_nvdimm_bridge *bridge; - struct cxl_pmem_region *region; + struct xarray pmem_regions; }; struct cxl_pmem_region_mapping { @@ -457,6 +457,7 @@ struct cxl_pmem_region { * @regions: cxl_region_ref instances, regions mapped by this port * @parent_dport: dport that points to this port in the parent * @decoder_ida: allocator for decoder ids + * @nr_dports: number of entries in @dports * @hdm_end: track last allocated HDM decoder instance for allocation ordering * @commit_end: cursor to track highest committed decoder for commit ordering * @component_reg_phys: component register capability base address (optional) @@ -475,6 +476,7 @@ struct cxl_port { struct xarray regions; struct cxl_dport *parent_dport; struct ida decoder_ida; + int nr_dports; int hdm_end; int commit_end; resource_size_t component_reg_phys; diff --git a/drivers/cxl/pmem.c b/drivers/cxl/pmem.c index 7dc0a2fa1a6b..4c627d67281a 100644 --- a/drivers/cxl/pmem.c +++ b/drivers/cxl/pmem.c @@ -30,17 +30,20 @@ static void unregister_nvdimm(void *nvdimm) struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm); struct cxl_nvdimm_bridge *cxl_nvb = cxl_nvd->bridge; struct cxl_pmem_region *cxlr_pmem; + unsigned long index; device_lock(&cxl_nvb->dev); - cxlr_pmem = cxl_nvd->region; dev_set_drvdata(&cxl_nvd->dev, NULL); - cxl_nvd->region = NULL; - device_unlock(&cxl_nvb->dev); + xa_for_each(&cxl_nvd->pmem_regions, index, cxlr_pmem) { + get_device(&cxlr_pmem->dev); + device_unlock(&cxl_nvb->dev); - if (cxlr_pmem) { device_release_driver(&cxlr_pmem->dev); put_device(&cxlr_pmem->dev); + + device_lock(&cxl_nvb->dev); } + device_unlock(&cxl_nvb->dev); nvdimm_delete(nvdimm); cxl_nvd->bridge = NULL; @@ -107,7 +110,7 @@ static int cxl_pmem_get_config_size(struct cxl_dev_state *cxlds, *cmd = (struct nd_cmd_get_config_size) { .config_size = cxlds->lsa_size, - .max_xfer = cxlds->payload_size, + .max_xfer = cxlds->payload_size - sizeof(struct cxl_mbox_set_lsa), }; return 0; @@ -148,7 +151,7 @@ static int cxl_pmem_set_config_data(struct cxl_dev_state *cxlds, return -EINVAL; /* 4-byte status follows the input data in the payload */ - if (struct_size(cmd, in_buf, cmd->in_length) + 4 > buf_len) + if (size_add(struct_size(cmd, in_buf, cmd->in_length), 4) > buf_len) return -EINVAL; set_lsa = @@ -366,25 +369,49 @@ static int match_cxl_nvdimm(struct device *dev, void *data) static void unregister_nvdimm_region(void *nd_region) { - struct cxl_nvdimm_bridge *cxl_nvb; - struct cxl_pmem_region *cxlr_pmem; + nvdimm_region_delete(nd_region); +} + +static int cxl_nvdimm_add_region(struct cxl_nvdimm *cxl_nvd, + struct cxl_pmem_region *cxlr_pmem) +{ + int rc; + + rc = xa_insert(&cxl_nvd->pmem_regions, (unsigned long)cxlr_pmem, + cxlr_pmem, GFP_KERNEL); + if (rc) + return rc; + + get_device(&cxlr_pmem->dev); + return 0; +} + +static void cxl_nvdimm_del_region(struct cxl_nvdimm *cxl_nvd, + struct cxl_pmem_region *cxlr_pmem) +{ + /* + * It is possible this is called without a corresponding + * cxl_nvdimm_add_region for @cxlr_pmem + */ + cxlr_pmem = xa_erase(&cxl_nvd->pmem_regions, (unsigned long)cxlr_pmem); + if (cxlr_pmem) + put_device(&cxlr_pmem->dev); +} + +static void release_mappings(void *data) +{ int i; + struct cxl_pmem_region *cxlr_pmem = data; + struct cxl_nvdimm_bridge *cxl_nvb = cxlr_pmem->bridge; - cxlr_pmem = nd_region_provider_data(nd_region); - cxl_nvb = cxlr_pmem->bridge; device_lock(&cxl_nvb->dev); for (i = 0; i < cxlr_pmem->nr_mappings; i++) { struct cxl_pmem_region_mapping *m = &cxlr_pmem->mapping[i]; struct cxl_nvdimm *cxl_nvd = m->cxl_nvd; - if (cxl_nvd->region) { - put_device(&cxlr_pmem->dev); - cxl_nvd->region = NULL; - } + cxl_nvdimm_del_region(cxl_nvd, cxlr_pmem); } device_unlock(&cxl_nvb->dev); - - nvdimm_region_delete(nd_region); } static void cxlr_pmem_remove_resource(void *res) @@ -422,7 +449,7 @@ static int cxl_pmem_region_probe(struct device *dev) if (!cxl_nvb->nvdimm_bus) { dev_dbg(dev, "nvdimm bus not found\n"); rc = -ENXIO; - goto err; + goto out_nvb; } memset(&mappings, 0, sizeof(mappings)); @@ -431,7 +458,7 @@ static int cxl_pmem_region_probe(struct device *dev) res = devm_kzalloc(dev, sizeof(*res), GFP_KERNEL); if (!res) { rc = -ENOMEM; - goto err; + goto out_nvb; } res->name = "Persistent Memory"; @@ -442,11 +469,11 @@ static int cxl_pmem_region_probe(struct device *dev) rc = insert_resource(&iomem_resource, res); if (rc) - goto err; + goto out_nvb; rc = devm_add_action_or_reset(dev, cxlr_pmem_remove_resource, res); if (rc) - goto err; + goto out_nvb; ndr_desc.res = res; ndr_desc.provider_data = cxlr_pmem; @@ -462,7 +489,7 @@ static int cxl_pmem_region_probe(struct device *dev) nd_set = devm_kzalloc(dev, sizeof(*nd_set), GFP_KERNEL); if (!nd_set) { rc = -ENOMEM; - goto err; + goto out_nvb; } ndr_desc.memregion = cxlr->id; @@ -472,9 +499,13 @@ static int cxl_pmem_region_probe(struct device *dev) info = kmalloc_array(cxlr_pmem->nr_mappings, sizeof(*info), GFP_KERNEL); if (!info) { rc = -ENOMEM; - goto err; + goto out_nvb; } + rc = devm_add_action_or_reset(dev, release_mappings, cxlr_pmem); + if (rc) + goto out_nvd; + for (i = 0; i < cxlr_pmem->nr_mappings; i++) { struct cxl_pmem_region_mapping *m = &cxlr_pmem->mapping[i]; struct cxl_memdev *cxlmd = m->cxlmd; @@ -486,7 +517,7 @@ static int cxl_pmem_region_probe(struct device *dev) dev_dbg(dev, "[%d]: %s: no cxl_nvdimm found\n", i, dev_name(&cxlmd->dev)); rc = -ENODEV; - goto err; + goto out_nvd; } /* safe to drop ref now with bridge lock held */ @@ -498,10 +529,17 @@ static int cxl_pmem_region_probe(struct device *dev) dev_dbg(dev, "[%d]: %s: no nvdimm found\n", i, dev_name(&cxlmd->dev)); rc = -ENODEV; - goto err; + goto out_nvd; } - cxl_nvd->region = cxlr_pmem; - get_device(&cxlr_pmem->dev); + + /* + * Pin the region per nvdimm device as those may be released + * out-of-order with respect to the region, and a single nvdimm + * maybe associated with multiple regions + */ + rc = cxl_nvdimm_add_region(cxl_nvd, cxlr_pmem); + if (rc) + goto out_nvd; m->cxl_nvd = cxl_nvd; mappings[i] = (struct nd_mapping_desc) { .nvdimm = nvdimm, @@ -527,27 +565,18 @@ static int cxl_pmem_region_probe(struct device *dev) nvdimm_pmem_region_create(cxl_nvb->nvdimm_bus, &ndr_desc); if (!cxlr_pmem->nd_region) { rc = -ENOMEM; - goto err; + goto out_nvd; } rc = devm_add_action_or_reset(dev, unregister_nvdimm_region, cxlr_pmem->nd_region); -out: +out_nvd: kfree(info); +out_nvb: device_unlock(&cxl_nvb->dev); put_device(&cxl_nvb->dev); return rc; - -err: - dev_dbg(dev, "failed to create nvdimm region\n"); - for (i--; i >= 0; i--) { - nvdimm = mappings[i].nvdimm; - cxl_nvd = nvdimm_provider_data(nvdimm); - put_device(&cxl_nvd->region->dev); - cxl_nvd->region = NULL; - } - goto out; } static struct cxl_driver cxl_pmem_region_driver = { diff --git a/drivers/firmware/arm_scmi/bus.c b/drivers/firmware/arm_scmi/bus.c index d4e23101448a..35bb70724d44 100644 --- a/drivers/firmware/arm_scmi/bus.c +++ b/drivers/firmware/arm_scmi/bus.c @@ -216,9 +216,20 @@ void scmi_device_destroy(struct scmi_device *scmi_dev) device_unregister(&scmi_dev->dev); } +void scmi_device_link_add(struct device *consumer, struct device *supplier) +{ + struct device_link *link; + + link = device_link_add(consumer, supplier, DL_FLAG_AUTOREMOVE_CONSUMER); + + WARN_ON(!link); +} + void scmi_set_handle(struct scmi_device *scmi_dev) { scmi_dev->handle = scmi_handle_get(&scmi_dev->dev); + if (scmi_dev->handle) + scmi_device_link_add(&scmi_dev->dev, scmi_dev->handle->dev); } int scmi_protocol_register(const struct scmi_protocol *proto) diff --git a/drivers/firmware/arm_scmi/common.h b/drivers/firmware/arm_scmi/common.h index 61aba7447c32..a1c0154c31c6 100644 --- a/drivers/firmware/arm_scmi/common.h +++ b/drivers/firmware/arm_scmi/common.h @@ -97,6 +97,7 @@ static inline void unpack_scmi_header(u32 msg_hdr, struct scmi_msg_hdr *hdr) struct scmi_revision_info * scmi_revision_area_get(const struct scmi_protocol_handle *ph); int scmi_handle_put(const struct scmi_handle *handle); +void scmi_device_link_add(struct device *consumer, struct device *supplier); struct scmi_handle *scmi_handle_get(struct device *dev); void scmi_set_handle(struct scmi_device *scmi_dev); void scmi_setup_protocol_implemented(const struct scmi_protocol_handle *ph, @@ -117,6 +118,7 @@ void scmi_protocol_release(const struct scmi_handle *handle, u8 protocol_id); * * @dev: Reference to device in the SCMI hierarchy corresponding to this * channel + * @rx_timeout_ms: The configured RX timeout in milliseconds. * @handle: Pointer to SCMI entity handle * @no_completion_irq: Flag to indicate that this channel has no completion * interrupt mechanism for synchronous commands. @@ -126,6 +128,7 @@ void scmi_protocol_release(const struct scmi_handle *handle, u8 protocol_id); */ struct scmi_chan_info { struct device *dev; + unsigned int rx_timeout_ms; struct scmi_handle *handle; bool no_completion_irq; void *transport_info; @@ -232,7 +235,7 @@ void scmi_free_channel(struct scmi_chan_info *cinfo, struct idr *idr, int id); struct scmi_shared_mem; void shmem_tx_prepare(struct scmi_shared_mem __iomem *shmem, - struct scmi_xfer *xfer); + struct scmi_xfer *xfer, struct scmi_chan_info *cinfo); u32 shmem_read_header(struct scmi_shared_mem __iomem *shmem); void shmem_fetch_response(struct scmi_shared_mem __iomem *shmem, struct scmi_xfer *xfer); diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c index 609ebedee9cb..f818d00bb2c6 100644 --- a/drivers/firmware/arm_scmi/driver.c +++ b/drivers/firmware/arm_scmi/driver.c @@ -2013,6 +2013,7 @@ static int scmi_chan_setup(struct scmi_info *info, struct device *dev, return -ENOMEM; cinfo->dev = dev; + cinfo->rx_timeout_ms = info->desc->max_rx_timeout_ms; ret = info->desc->ops->chan_setup(cinfo, info->dev, tx); if (ret) @@ -2044,8 +2045,12 @@ scmi_txrx_setup(struct scmi_info *info, struct device *dev, int prot_id) { int ret = scmi_chan_setup(info, dev, prot_id, true); - if (!ret) /* Rx is optional, hence no error check */ - scmi_chan_setup(info, dev, prot_id, false); + if (!ret) { + /* Rx is optional, report only memory errors */ + ret = scmi_chan_setup(info, dev, prot_id, false); + if (ret && ret != -ENOMEM) + ret = 0; + } return ret; } @@ -2273,10 +2278,16 @@ int scmi_protocol_device_request(const struct scmi_device_id *id_table) sdev = scmi_get_protocol_device(child, info, id_table->protocol_id, id_table->name); - /* Set handle if not already set: device existed */ - if (sdev && !sdev->handle) - sdev->handle = - scmi_handle_get_from_info_unlocked(info); + if (sdev) { + /* Set handle if not already set: device existed */ + if (!sdev->handle) + sdev->handle = + scmi_handle_get_from_info_unlocked(info); + /* Relink consumer and suppliers */ + if (sdev->handle) + scmi_device_link_add(&sdev->dev, + sdev->handle->dev); + } } else { dev_err(info->dev, "Failed. SCMI protocol %d not active.\n", @@ -2475,20 +2486,17 @@ void scmi_free_channel(struct scmi_chan_info *cinfo, struct idr *idr, int id) static int scmi_remove(struct platform_device *pdev) { - int ret = 0, id; + int ret, id; struct scmi_info *info = platform_get_drvdata(pdev); struct device_node *child; mutex_lock(&scmi_list_mutex); if (info->users) - ret = -EBUSY; - else - list_del(&info->node); + dev_warn(&pdev->dev, + "Still active SCMI users will be forcibly unbound.\n"); + list_del(&info->node); mutex_unlock(&scmi_list_mutex); - if (ret) - return ret; - scmi_notification_exit(&info->handle); mutex_lock(&info->protocols_mtx); @@ -2500,7 +2508,11 @@ static int scmi_remove(struct platform_device *pdev) idr_destroy(&info->active_protocols); /* Safe to free channels since no more users */ - return scmi_cleanup_txrx_channels(info); + ret = scmi_cleanup_txrx_channels(info); + if (ret) + dev_warn(&pdev->dev, "Failed to cleanup SCMI channels.\n"); + + return 0; } static ssize_t protocol_version_show(struct device *dev, @@ -2571,6 +2583,7 @@ MODULE_DEVICE_TABLE(of, scmi_of_match); static struct platform_driver scmi_driver = { .driver = { .name = "arm-scmi", + .suppress_bind_attrs = true, .of_match_table = scmi_of_match, .dev_groups = versions_groups, }, diff --git a/drivers/firmware/arm_scmi/mailbox.c b/drivers/firmware/arm_scmi/mailbox.c index 08ff4d110beb..1e40cb035044 100644 --- a/drivers/firmware/arm_scmi/mailbox.c +++ b/drivers/firmware/arm_scmi/mailbox.c @@ -36,7 +36,7 @@ static void tx_prepare(struct mbox_client *cl, void *m) { struct scmi_mailbox *smbox = client_to_scmi_mailbox(cl); - shmem_tx_prepare(smbox->shmem, m); + shmem_tx_prepare(smbox->shmem, m, smbox->cinfo); } static void rx_callback(struct mbox_client *cl, void *m) diff --git a/drivers/firmware/arm_scmi/optee.c b/drivers/firmware/arm_scmi/optee.c index f42dad997ac9..2a7aeab40e54 100644 --- a/drivers/firmware/arm_scmi/optee.c +++ b/drivers/firmware/arm_scmi/optee.c @@ -498,7 +498,7 @@ static int scmi_optee_send_message(struct scmi_chan_info *cinfo, msg_tx_prepare(channel->req.msg, xfer); ret = invoke_process_msg_channel(channel, msg_command_size(xfer)); } else { - shmem_tx_prepare(channel->req.shmem, xfer); + shmem_tx_prepare(channel->req.shmem, xfer, cinfo); ret = invoke_process_smt_channel(channel); } diff --git a/drivers/firmware/arm_scmi/shmem.c b/drivers/firmware/arm_scmi/shmem.c index 0e3eaea5d852..1dfe534b8518 100644 --- a/drivers/firmware/arm_scmi/shmem.c +++ b/drivers/firmware/arm_scmi/shmem.c @@ -5,10 +5,13 @@ * Copyright (C) 2019 ARM Ltd. */ +#include <linux/ktime.h> #include <linux/io.h> #include <linux/processor.h> #include <linux/types.h> +#include <asm-generic/bug.h> + #include "common.h" /* @@ -30,16 +33,36 @@ struct scmi_shared_mem { }; void shmem_tx_prepare(struct scmi_shared_mem __iomem *shmem, - struct scmi_xfer *xfer) + struct scmi_xfer *xfer, struct scmi_chan_info *cinfo) { + ktime_t stop; + /* * Ideally channel must be free by now unless OS timeout last * request and platform continued to process the same, wait * until it releases the shared memory, otherwise we may endup - * overwriting its response with new message payload or vice-versa + * overwriting its response with new message payload or vice-versa. + * Giving up anyway after twice the expected channel timeout so as + * not to bail-out on intermittent issues where the platform is + * occasionally a bit slower to answer. + * + * Note that after a timeout is detected we bail-out and carry on but + * the transport functionality is probably permanently compromised: + * this is just to ease debugging and avoid complete hangs on boot + * due to a misbehaving SCMI firmware. */ - spin_until_cond(ioread32(&shmem->channel_status) & - SCMI_SHMEM_CHAN_STAT_CHANNEL_FREE); + stop = ktime_add_ms(ktime_get(), 2 * cinfo->rx_timeout_ms); + spin_until_cond((ioread32(&shmem->channel_status) & + SCMI_SHMEM_CHAN_STAT_CHANNEL_FREE) || + ktime_after(ktime_get(), stop)); + if (!(ioread32(&shmem->channel_status) & + SCMI_SHMEM_CHAN_STAT_CHANNEL_FREE)) { + WARN_ON_ONCE(1); + dev_err(cinfo->dev, + "Timeout waiting for a free TX channel !\n"); + return; + } + /* Mark channel busy + clear error */ iowrite32(0x0, &shmem->channel_status); iowrite32(xfer->hdr.poll_completion ? 0 : SCMI_SHMEM_FLAG_INTR_ENABLED, diff --git a/drivers/firmware/arm_scmi/smc.c b/drivers/firmware/arm_scmi/smc.c index 745acfdd0b3d..87a7b13cf868 100644 --- a/drivers/firmware/arm_scmi/smc.c +++ b/drivers/firmware/arm_scmi/smc.c @@ -188,7 +188,7 @@ static int smc_send_message(struct scmi_chan_info *cinfo, */ smc_channel_lock_acquire(scmi_info, xfer); - shmem_tx_prepare(scmi_info->shmem, xfer); + shmem_tx_prepare(scmi_info->shmem, xfer, cinfo); arm_smccc_1_1_invoke(scmi_info->func_id, 0, 0, 0, 0, 0, 0, 0, &res); diff --git a/drivers/firmware/arm_scmi/virtio.c b/drivers/firmware/arm_scmi/virtio.c index 14709dbc96a1..33c9b81a55cd 100644 --- a/drivers/firmware/arm_scmi/virtio.c +++ b/drivers/firmware/arm_scmi/virtio.c @@ -148,7 +148,6 @@ static void scmi_vio_channel_cleanup_sync(struct scmi_vio_channel *vioch) { unsigned long flags; DECLARE_COMPLETION_ONSTACK(vioch_shutdown_done); - void *deferred_wq = NULL; /* * Prepare to wait for the last release if not already released @@ -162,16 +161,11 @@ static void scmi_vio_channel_cleanup_sync(struct scmi_vio_channel *vioch) vioch->shutdown_done = &vioch_shutdown_done; virtio_break_device(vioch->vqueue->vdev); - if (!vioch->is_rx && vioch->deferred_tx_wq) { - deferred_wq = vioch->deferred_tx_wq; + if (!vioch->is_rx && vioch->deferred_tx_wq) /* Cannot be kicked anymore after this...*/ vioch->deferred_tx_wq = NULL; - } spin_unlock_irqrestore(&vioch->lock, flags); - if (deferred_wq) - destroy_workqueue(deferred_wq); - scmi_vio_channel_release(vioch); /* Let any possibly concurrent RX path release the channel */ @@ -416,6 +410,11 @@ static bool virtio_chan_available(struct device *dev, int idx) return vioch && !vioch->cinfo; } +static void scmi_destroy_tx_workqueue(void *deferred_tx_wq) +{ + destroy_workqueue(deferred_tx_wq); +} + static int virtio_chan_setup(struct scmi_chan_info *cinfo, struct device *dev, bool tx) { @@ -430,6 +429,8 @@ static int virtio_chan_setup(struct scmi_chan_info *cinfo, struct device *dev, /* Setup a deferred worker for polling. */ if (tx && !vioch->deferred_tx_wq) { + int ret; + vioch->deferred_tx_wq = alloc_workqueue(dev_name(&scmi_vdev->dev), WQ_UNBOUND | WQ_FREEZABLE | WQ_SYSFS, @@ -437,6 +438,11 @@ static int virtio_chan_setup(struct scmi_chan_info *cinfo, struct device *dev, if (!vioch->deferred_tx_wq) return -ENOMEM; + ret = devm_add_action_or_reset(dev, scmi_destroy_tx_workqueue, + vioch->deferred_tx_wq); + if (ret) + return ret; + INIT_WORK(&vioch->deferred_tx_work, scmi_vio_deferred_tx_worker); } @@ -444,12 +450,12 @@ static int virtio_chan_setup(struct scmi_chan_info *cinfo, struct device *dev, for (i = 0; i < vioch->max_msg; i++) { struct scmi_vio_msg *msg; - msg = devm_kzalloc(cinfo->dev, sizeof(*msg), GFP_KERNEL); + msg = devm_kzalloc(dev, sizeof(*msg), GFP_KERNEL); if (!msg) return -ENOMEM; if (tx) { - msg->request = devm_kzalloc(cinfo->dev, + msg->request = devm_kzalloc(dev, VIRTIO_SCMI_MAX_PDU_SIZE, GFP_KERNEL); if (!msg->request) @@ -458,7 +464,7 @@ static int virtio_chan_setup(struct scmi_chan_info *cinfo, struct device *dev, refcount_set(&msg->users, 1); } - msg->input = devm_kzalloc(cinfo->dev, VIRTIO_SCMI_MAX_PDU_SIZE, + msg->input = devm_kzalloc(dev, VIRTIO_SCMI_MAX_PDU_SIZE, GFP_KERNEL); if (!msg->input) return -ENOMEM; diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 3ecdc43a3f2b..a46df5d1d094 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -611,7 +611,7 @@ int __init efi_config_parse_tables(const efi_config_table_t *config_tables, seed = early_memremap(efi_rng_seed, sizeof(*seed)); if (seed != NULL) { - size = READ_ONCE(seed->size); + size = min(seed->size, EFI_RANDOM_SEED_SIZE); early_memunmap(seed, sizeof(*seed)); } else { pr_err("Could not map UEFI random seed!\n"); diff --git a/drivers/firmware/efi/libstub/random.c b/drivers/firmware/efi/libstub/random.c index 24aa37535372..33ab56769595 100644 --- a/drivers/firmware/efi/libstub/random.c +++ b/drivers/firmware/efi/libstub/random.c @@ -75,7 +75,12 @@ efi_status_t efi_random_get_seed(void) if (status != EFI_SUCCESS) return status; - status = efi_bs_call(allocate_pool, EFI_RUNTIME_SERVICES_DATA, + /* + * Use EFI_ACPI_RECLAIM_MEMORY here so that it is guaranteed that the + * allocation will survive a kexec reboot (although we refresh the seed + * beforehand) + */ + status = efi_bs_call(allocate_pool, EFI_ACPI_RECLAIM_MEMORY, sizeof(*seed) + EFI_RANDOM_SEED_SIZE, (void **)&seed); if (status != EFI_SUCCESS) diff --git a/drivers/firmware/efi/tpm.c b/drivers/firmware/efi/tpm.c index 8f665678e9e3..e8d69bd548f3 100644 --- a/drivers/firmware/efi/tpm.c +++ b/drivers/firmware/efi/tpm.c @@ -97,7 +97,7 @@ int __init efi_tpm_eventlog_init(void) goto out_calc; } - memblock_reserve((unsigned long)final_tbl, + memblock_reserve(efi.tpm_final_log, tbl_size + sizeof(*final_tbl)); efi_tpm_final_log_size = tbl_size; diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c index 433b61587139..0ba9f18312f5 100644 --- a/drivers/firmware/efi/vars.c +++ b/drivers/firmware/efi/vars.c @@ -21,29 +21,22 @@ static struct efivars *__efivars; static DEFINE_SEMAPHORE(efivars_lock); -static efi_status_t check_var_size(u32 attributes, unsigned long size) -{ - const struct efivar_operations *fops; - - fops = __efivars->ops; - - if (!fops->query_variable_store) - return (size <= SZ_64K) ? EFI_SUCCESS : EFI_OUT_OF_RESOURCES; - - return fops->query_variable_store(attributes, size, false); -} - -static -efi_status_t check_var_size_nonblocking(u32 attributes, unsigned long size) +static efi_status_t check_var_size(bool nonblocking, u32 attributes, + unsigned long size) { const struct efivar_operations *fops; + efi_status_t status; fops = __efivars->ops; if (!fops->query_variable_store) + status = EFI_UNSUPPORTED; + else + status = fops->query_variable_store(attributes, size, + nonblocking); + if (status == EFI_UNSUPPORTED) return (size <= SZ_64K) ? EFI_SUCCESS : EFI_OUT_OF_RESOURCES; - - return fops->query_variable_store(attributes, size, true); + return status; } /** @@ -196,26 +189,6 @@ efi_status_t efivar_get_next_variable(unsigned long *name_size, EXPORT_SYMBOL_NS_GPL(efivar_get_next_variable, EFIVAR); /* - * efivar_set_variable_blocking() - local helper function for set_variable - * - * Must be called with efivars_lock held. - */ -static efi_status_t -efivar_set_variable_blocking(efi_char16_t *name, efi_guid_t *vendor, - u32 attr, unsigned long data_size, void *data) -{ - efi_status_t status; - - if (data_size > 0) { - status = check_var_size(attr, data_size + - ucs2_strsize(name, 1024)); - if (status != EFI_SUCCESS) - return status; - } - return __efivars->ops->set_variable(name, vendor, attr, data_size, data); -} - -/* * efivar_set_variable_locked() - set a variable identified by name/vendor * * Must be called with efivars_lock held. If @nonblocking is set, it will use @@ -228,23 +201,21 @@ efi_status_t efivar_set_variable_locked(efi_char16_t *name, efi_guid_t *vendor, efi_set_variable_t *setvar; efi_status_t status; - if (!nonblocking) - return efivar_set_variable_blocking(name, vendor, attr, - data_size, data); + if (data_size > 0) { + status = check_var_size(nonblocking, attr, + data_size + ucs2_strsize(name, 1024)); + if (status != EFI_SUCCESS) + return status; + } /* * If no _nonblocking variant exists, the ordinary one * is assumed to be non-blocking. */ - setvar = __efivars->ops->set_variable_nonblocking ?: - __efivars->ops->set_variable; + setvar = __efivars->ops->set_variable_nonblocking; + if (!setvar || !nonblocking) + setvar = __efivars->ops->set_variable; - if (data_size > 0) { - status = check_var_size_nonblocking(attr, data_size + - ucs2_strsize(name, 1024)); - if (status != EFI_SUCCESS) - return status; - } return setvar(name, vendor, attr, data_size, data); } EXPORT_SYMBOL_NS_GPL(efivar_set_variable_locked, EFIVAR); @@ -264,7 +235,8 @@ efi_status_t efivar_set_variable(efi_char16_t *name, efi_guid_t *vendor, if (efivar_lock()) return EFI_ABORTED; - status = efivar_set_variable_blocking(name, vendor, attr, data_size, data); + status = efivar_set_variable_locked(name, vendor, attr, data_size, + data, false); efivar_unlock(); return status; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c index 0561812aa0a4..5d9a34601a1a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c @@ -706,6 +706,13 @@ err: void amdgpu_amdkfd_set_compute_idle(struct amdgpu_device *adev, bool idle) { + /* Temporary workaround to fix issues observed in some + * compute applications when GFXOFF is enabled on GFX11. + */ + if (IP_VERSION_MAJ(adev->ip_versions[GC_HWIP][0]) == 11) { + pr_debug("GFXOFF is %s\n", idle ? "enabled" : "disabled"); + amdgpu_gfx_off_ctrl(adev, idle); + } amdgpu_dpm_switch_power_profile(adev, PP_SMC_POWER_PROFILE_COMPUTE, !idle); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index ddaecb2610c9..64510898eedd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -4060,15 +4060,18 @@ void amdgpu_device_fini_sw(struct amdgpu_device *adev) * at suspend time. * */ -static void amdgpu_device_evict_resources(struct amdgpu_device *adev) +static int amdgpu_device_evict_resources(struct amdgpu_device *adev) { + int ret; + /* No need to evict vram on APUs for suspend to ram or s2idle */ if ((adev->in_s3 || adev->in_s0ix) && (adev->flags & AMD_IS_APU)) - return; + return 0; - if (amdgpu_ttm_evict_resources(adev, TTM_PL_VRAM)) + ret = amdgpu_ttm_evict_resources(adev, TTM_PL_VRAM); + if (ret) DRM_WARN("evicting device resources failed\n"); - + return ret; } /* @@ -4118,7 +4121,9 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon) if (!adev->in_s0ix) amdgpu_amdkfd_suspend(adev, adev->in_runpm); - amdgpu_device_evict_resources(adev); + r = amdgpu_device_evict_resources(adev); + if (r) + return r; amdgpu_fence_driver_hw_fini(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 3c9fecdd6b2f..bf2d50c8c92a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -2201,7 +2201,8 @@ amdgpu_pci_remove(struct pci_dev *pdev) pm_runtime_forbid(dev->dev); } - if (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 2)) { + if (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 2) && + !amdgpu_sriov_vf(adev)) { bool need_to_reset_gpu = false; if (adev->gmc.xgmi.num_physical_nodes > 1) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index bf1ff8f0e712..4e42dcb1950f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -337,12 +337,14 @@ static int amdgpu_firmware_info(struct drm_amdgpu_info_firmware *fw_info, fw_info->feature = adev->psp.cap_feature_version; break; case AMDGPU_INFO_FW_MES_KIQ: - fw_info->ver = adev->mes.ucode_fw_version[0]; - fw_info->feature = 0; + fw_info->ver = adev->mes.kiq_version & AMDGPU_MES_VERSION_MASK; + fw_info->feature = (adev->mes.kiq_version & AMDGPU_MES_FEAT_VERSION_MASK) + >> AMDGPU_MES_FEAT_VERSION_SHIFT; break; case AMDGPU_INFO_FW_MES: - fw_info->ver = adev->mes.ucode_fw_version[1]; - fw_info->feature = 0; + fw_info->ver = adev->mes.sched_version & AMDGPU_MES_VERSION_MASK; + fw_info->feature = (adev->mes.sched_version & AMDGPU_MES_FEAT_VERSION_MASK) + >> AMDGPU_MES_FEAT_VERSION_SHIFT; break; case AMDGPU_INFO_FW_IMU: fw_info->ver = adev->gfx.imu_fw_version; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c index f4b5301ea2a0..500a1dc4fe02 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c @@ -500,6 +500,8 @@ static int amdgpu_vkms_sw_init(void *handle) adev_to_drm(adev)->mode_config.fb_base = adev->gmc.aper_base; + adev_to_drm(adev)->mode_config.fb_modifiers_not_supported = true; + r = amdgpu_display_modeset_create_props(adev); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h index c7118843db05..0c4c5499bb5c 100644 --- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h +++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h @@ -2495,442 +2495,444 @@ static const uint32_t cwsr_trap_gfx10_hex[] = { 0xbf9f0000, 0x00000000, }; static const uint32_t cwsr_trap_gfx11_hex[] = { - 0xbfa00001, 0xbfa0021e, + 0xbfa00001, 0xbfa00221, 0xb0804006, 0xb8f8f802, 0x9178ff78, 0x00020006, - 0xb8fbf803, 0xbf0d9f6d, - 0xbfa20006, 0x8b6eff78, - 0x00002000, 0xbfa10009, - 0x8b6eff6d, 0x00ff0000, - 0xbfa2001e, 0x8b6eff7b, - 0x00000400, 0xbfa20041, - 0xbf830010, 0xb8fbf803, - 0xbfa0fffa, 0x8b6eff7b, - 0x00000900, 0xbfa20015, - 0x8b6eff7b, 0x000071ff, - 0xbfa10008, 0x8b6fff7b, - 0x00007080, 0xbfa10001, - 0xbeee1287, 0xb8eff801, - 0x846e8c6e, 0x8b6e6f6e, - 0xbfa2000a, 0x8b6eff6d, - 0x00ff0000, 0xbfa20007, - 0xb8eef801, 0x8b6eff6e, - 0x00000800, 0xbfa20003, + 0xb8fbf803, 0xbf0d9e6d, + 0xbfa10001, 0xbfbd0000, + 0xbf0d9f6d, 0xbfa20006, + 0x8b6eff78, 0x00002000, + 0xbfa10009, 0x8b6eff6d, + 0x00ff0000, 0xbfa2001e, 0x8b6eff7b, 0x00000400, - 0xbfa20026, 0xbefa4d82, - 0xbf89fc07, 0x84fa887a, - 0xf4005bbd, 0xf8000010, - 0xbf89fc07, 0x846e976e, - 0x9177ff77, 0x00800000, - 0x8c776e77, 0xf4045bbd, - 0xf8000000, 0xbf89fc07, - 0xf4045ebd, 0xf8000008, - 0xbf89fc07, 0x8bee6e6e, - 0xbfa10001, 0xbe80486e, - 0x8b6eff6d, 0x01ff0000, - 0xbfa20005, 0x8c78ff78, - 0x00002000, 0x80ec886c, - 0x82ed806d, 0xbfa00005, - 0x8b6eff6d, 0x01000000, - 0xbfa20002, 0x806c846c, - 0x826d806d, 0x8b6dff6d, - 0x0000ffff, 0x8bfe7e7e, - 0x8bea6a6a, 0xb978f802, - 0xbe804a6c, 0x8b6dff6d, - 0x0000ffff, 0xbefa0080, - 0xb97a0283, 0xbeee007e, - 0xbeef007f, 0xbefe0180, - 0xbefe4d84, 0xbf89fc07, - 0x8b7aff7f, 0x04000000, - 0x847a857a, 0x8c6d7a6d, - 0xbefa007e, 0x8b7bff7f, - 0x0000ffff, 0xbefe00c1, - 0xbeff00c1, 0xdca6c000, - 0x007a0000, 0x7e000280, - 0xbefe007a, 0xbeff007b, - 0xb8fb02dc, 0x847b997b, - 0xb8fa3b05, 0x807a817a, - 0xbf0d997b, 0xbfa20002, - 0x847a897a, 0xbfa00001, - 0x847a8a7a, 0xb8fb1e06, - 0x847b8a7b, 0x807a7b7a, + 0xbfa20041, 0xbf830010, + 0xb8fbf803, 0xbfa0fffa, + 0x8b6eff7b, 0x00000900, + 0xbfa20015, 0x8b6eff7b, + 0x000071ff, 0xbfa10008, + 0x8b6fff7b, 0x00007080, + 0xbfa10001, 0xbeee1287, + 0xb8eff801, 0x846e8c6e, + 0x8b6e6f6e, 0xbfa2000a, + 0x8b6eff6d, 0x00ff0000, + 0xbfa20007, 0xb8eef801, + 0x8b6eff6e, 0x00000800, + 0xbfa20003, 0x8b6eff7b, + 0x00000400, 0xbfa20026, + 0xbefa4d82, 0xbf89fc07, + 0x84fa887a, 0xf4005bbd, + 0xf8000010, 0xbf89fc07, + 0x846e976e, 0x9177ff77, + 0x00800000, 0x8c776e77, + 0xf4045bbd, 0xf8000000, + 0xbf89fc07, 0xf4045ebd, + 0xf8000008, 0xbf89fc07, + 0x8bee6e6e, 0xbfa10001, + 0xbe80486e, 0x8b6eff6d, + 0x01ff0000, 0xbfa20005, + 0x8c78ff78, 0x00002000, + 0x80ec886c, 0x82ed806d, + 0xbfa00005, 0x8b6eff6d, + 0x01000000, 0xbfa20002, + 0x806c846c, 0x826d806d, + 0x8b6dff6d, 0x0000ffff, + 0x8bfe7e7e, 0x8bea6a6a, + 0xb978f802, 0xbe804a6c, + 0x8b6dff6d, 0x0000ffff, + 0xbefa0080, 0xb97a0283, + 0xbeee007e, 0xbeef007f, + 0xbefe0180, 0xbefe4d84, + 0xbf89fc07, 0x8b7aff7f, + 0x04000000, 0x847a857a, + 0x8c6d7a6d, 0xbefa007e, 0x8b7bff7f, 0x0000ffff, - 0x807aff7a, 0x00000200, - 0x807a7e7a, 0x827b807b, - 0xd7610000, 0x00010870, - 0xd7610000, 0x00010a71, - 0xd7610000, 0x00010c72, - 0xd7610000, 0x00010e73, - 0xd7610000, 0x00011074, - 0xd7610000, 0x00011275, - 0xd7610000, 0x00011476, - 0xd7610000, 0x00011677, - 0xd7610000, 0x00011a79, - 0xd7610000, 0x00011c7e, - 0xd7610000, 0x00011e7f, - 0xbefe00ff, 0x00003fff, - 0xbeff0080, 0xdca6c040, - 0x007a0000, 0xd760007a, - 0x00011d00, 0xd760007b, - 0x00011f00, 0xbefe007a, - 0xbeff007b, 0xbef4007e, - 0x8b75ff7f, 0x0000ffff, - 0x8c75ff75, 0x00040000, - 0xbef60080, 0xbef700ff, - 0x10807fac, 0xbef1007d, - 0xbef00080, 0xb8f302dc, - 0x84739973, 0xbefe00c1, - 0x857d9973, 0x8b7d817d, - 0xbf06817d, 0xbfa20002, - 0xbeff0080, 0xbfa00002, - 0xbeff00c1, 0xbfa00009, + 0xbefe00c1, 0xbeff00c1, + 0xdca6c000, 0x007a0000, + 0x7e000280, 0xbefe007a, + 0xbeff007b, 0xb8fb02dc, + 0x847b997b, 0xb8fa3b05, + 0x807a817a, 0xbf0d997b, + 0xbfa20002, 0x847a897a, + 0xbfa00001, 0x847a8a7a, + 0xb8fb1e06, 0x847b8a7b, + 0x807a7b7a, 0x8b7bff7f, + 0x0000ffff, 0x807aff7a, + 0x00000200, 0x807a7e7a, + 0x827b807b, 0xd7610000, + 0x00010870, 0xd7610000, + 0x00010a71, 0xd7610000, + 0x00010c72, 0xd7610000, + 0x00010e73, 0xd7610000, + 0x00011074, 0xd7610000, + 0x00011275, 0xd7610000, + 0x00011476, 0xd7610000, + 0x00011677, 0xd7610000, + 0x00011a79, 0xd7610000, + 0x00011c7e, 0xd7610000, + 0x00011e7f, 0xbefe00ff, + 0x00003fff, 0xbeff0080, + 0xdca6c040, 0x007a0000, + 0xd760007a, 0x00011d00, + 0xd760007b, 0x00011f00, + 0xbefe007a, 0xbeff007b, + 0xbef4007e, 0x8b75ff7f, + 0x0000ffff, 0x8c75ff75, + 0x00040000, 0xbef60080, + 0xbef700ff, 0x10807fac, + 0xbef1007d, 0xbef00080, + 0xb8f302dc, 0x84739973, + 0xbefe00c1, 0x857d9973, + 0x8b7d817d, 0xbf06817d, + 0xbfa20002, 0xbeff0080, + 0xbfa00002, 0xbeff00c1, + 0xbfa00009, 0xbef600ff, + 0x01000000, 0xe0685080, + 0x701d0100, 0xe0685100, + 0x701d0200, 0xe0685180, + 0x701d0300, 0xbfa00008, 0xbef600ff, 0x01000000, - 0xe0685080, 0x701d0100, - 0xe0685100, 0x701d0200, - 0xe0685180, 0x701d0300, - 0xbfa00008, 0xbef600ff, - 0x01000000, 0xe0685100, - 0x701d0100, 0xe0685200, - 0x701d0200, 0xe0685300, - 0x701d0300, 0xb8f03b05, - 0x80708170, 0xbf0d9973, - 0xbfa20002, 0x84708970, - 0xbfa00001, 0x84708a70, - 0xb8fa1e06, 0x847a8a7a, - 0x80707a70, 0x8070ff70, - 0x00000200, 0xbef600ff, - 0x01000000, 0x7e000280, - 0x7e020280, 0x7e040280, - 0xbefd0080, 0xd7610002, - 0x0000fa71, 0x807d817d, - 0xd7610002, 0x0000fa6c, - 0x807d817d, 0x917aff6d, - 0x80000000, 0xd7610002, - 0x0000fa7a, 0x807d817d, - 0xd7610002, 0x0000fa6e, - 0x807d817d, 0xd7610002, - 0x0000fa6f, 0x807d817d, - 0xd7610002, 0x0000fa78, - 0x807d817d, 0xb8faf803, - 0xd7610002, 0x0000fa7a, - 0x807d817d, 0xd7610002, - 0x0000fa7b, 0x807d817d, - 0xb8f1f801, 0xd7610002, - 0x0000fa71, 0x807d817d, - 0xb8f1f814, 0xd7610002, - 0x0000fa71, 0x807d817d, - 0xb8f1f815, 0xd7610002, - 0x0000fa71, 0x807d817d, - 0xbefe00ff, 0x0000ffff, - 0xbeff0080, 0xe0685000, - 0x701d0200, 0xbefe00c1, + 0xe0685100, 0x701d0100, + 0xe0685200, 0x701d0200, + 0xe0685300, 0x701d0300, 0xb8f03b05, 0x80708170, 0xbf0d9973, 0xbfa20002, 0x84708970, 0xbfa00001, 0x84708a70, 0xb8fa1e06, 0x847a8a7a, 0x80707a70, + 0x8070ff70, 0x00000200, 0xbef600ff, 0x01000000, - 0xbef90080, 0xbefd0080, - 0xbf800000, 0xbe804100, - 0xbe824102, 0xbe844104, - 0xbe864106, 0xbe884108, - 0xbe8a410a, 0xbe8c410c, - 0xbe8e410e, 0xd7610002, - 0x0000f200, 0x80798179, - 0xd7610002, 0x0000f201, + 0x7e000280, 0x7e020280, + 0x7e040280, 0xbefd0080, + 0xd7610002, 0x0000fa71, + 0x807d817d, 0xd7610002, + 0x0000fa6c, 0x807d817d, + 0x917aff6d, 0x80000000, + 0xd7610002, 0x0000fa7a, + 0x807d817d, 0xd7610002, + 0x0000fa6e, 0x807d817d, + 0xd7610002, 0x0000fa6f, + 0x807d817d, 0xd7610002, + 0x0000fa78, 0x807d817d, + 0xb8faf803, 0xd7610002, + 0x0000fa7a, 0x807d817d, + 0xd7610002, 0x0000fa7b, + 0x807d817d, 0xb8f1f801, + 0xd7610002, 0x0000fa71, + 0x807d817d, 0xb8f1f814, + 0xd7610002, 0x0000fa71, + 0x807d817d, 0xb8f1f815, + 0xd7610002, 0x0000fa71, + 0x807d817d, 0xbefe00ff, + 0x0000ffff, 0xbeff0080, + 0xe0685000, 0x701d0200, + 0xbefe00c1, 0xb8f03b05, + 0x80708170, 0xbf0d9973, + 0xbfa20002, 0x84708970, + 0xbfa00001, 0x84708a70, + 0xb8fa1e06, 0x847a8a7a, + 0x80707a70, 0xbef600ff, + 0x01000000, 0xbef90080, + 0xbefd0080, 0xbf800000, + 0xbe804100, 0xbe824102, + 0xbe844104, 0xbe864106, + 0xbe884108, 0xbe8a410a, + 0xbe8c410c, 0xbe8e410e, + 0xd7610002, 0x0000f200, 0x80798179, 0xd7610002, - 0x0000f202, 0x80798179, - 0xd7610002, 0x0000f203, + 0x0000f201, 0x80798179, + 0xd7610002, 0x0000f202, 0x80798179, 0xd7610002, - 0x0000f204, 0x80798179, - 0xd7610002, 0x0000f205, + 0x0000f203, 0x80798179, + 0xd7610002, 0x0000f204, 0x80798179, 0xd7610002, - 0x0000f206, 0x80798179, - 0xd7610002, 0x0000f207, + 0x0000f205, 0x80798179, + 0xd7610002, 0x0000f206, 0x80798179, 0xd7610002, - 0x0000f208, 0x80798179, - 0xd7610002, 0x0000f209, + 0x0000f207, 0x80798179, + 0xd7610002, 0x0000f208, 0x80798179, 0xd7610002, - 0x0000f20a, 0x80798179, - 0xd7610002, 0x0000f20b, + 0x0000f209, 0x80798179, + 0xd7610002, 0x0000f20a, 0x80798179, 0xd7610002, - 0x0000f20c, 0x80798179, - 0xd7610002, 0x0000f20d, + 0x0000f20b, 0x80798179, + 0xd7610002, 0x0000f20c, 0x80798179, 0xd7610002, - 0x0000f20e, 0x80798179, - 0xd7610002, 0x0000f20f, - 0x80798179, 0xbf06a079, - 0xbfa10006, 0xe0685000, - 0x701d0200, 0x8070ff70, - 0x00000080, 0xbef90080, - 0x7e040280, 0x807d907d, - 0xbf0aff7d, 0x00000060, - 0xbfa2ffbc, 0xbe804100, - 0xbe824102, 0xbe844104, - 0xbe864106, 0xbe884108, - 0xbe8a410a, 0xd7610002, - 0x0000f200, 0x80798179, - 0xd7610002, 0x0000f201, + 0x0000f20d, 0x80798179, + 0xd7610002, 0x0000f20e, 0x80798179, 0xd7610002, - 0x0000f202, 0x80798179, - 0xd7610002, 0x0000f203, + 0x0000f20f, 0x80798179, + 0xbf06a079, 0xbfa10006, + 0xe0685000, 0x701d0200, + 0x8070ff70, 0x00000080, + 0xbef90080, 0x7e040280, + 0x807d907d, 0xbf0aff7d, + 0x00000060, 0xbfa2ffbc, + 0xbe804100, 0xbe824102, + 0xbe844104, 0xbe864106, + 0xbe884108, 0xbe8a410a, + 0xd7610002, 0x0000f200, 0x80798179, 0xd7610002, - 0x0000f204, 0x80798179, - 0xd7610002, 0x0000f205, + 0x0000f201, 0x80798179, + 0xd7610002, 0x0000f202, 0x80798179, 0xd7610002, - 0x0000f206, 0x80798179, - 0xd7610002, 0x0000f207, + 0x0000f203, 0x80798179, + 0xd7610002, 0x0000f204, 0x80798179, 0xd7610002, - 0x0000f208, 0x80798179, - 0xd7610002, 0x0000f209, + 0x0000f205, 0x80798179, + 0xd7610002, 0x0000f206, 0x80798179, 0xd7610002, - 0x0000f20a, 0x80798179, - 0xd7610002, 0x0000f20b, - 0x80798179, 0xe0685000, - 0x701d0200, 0xbefe00c1, - 0x857d9973, 0x8b7d817d, - 0xbf06817d, 0xbfa20002, - 0xbeff0080, 0xbfa00001, - 0xbeff00c1, 0xb8fb4306, - 0x8b7bc17b, 0xbfa10044, - 0xbfbd0000, 0x8b7aff6d, - 0x80000000, 0xbfa10040, - 0x847b867b, 0x847b827b, - 0xbef6007b, 0xb8f03b05, - 0x80708170, 0xbf0d9973, - 0xbfa20002, 0x84708970, - 0xbfa00001, 0x84708a70, - 0xb8fa1e06, 0x847a8a7a, - 0x80707a70, 0x8070ff70, - 0x00000200, 0x8070ff70, - 0x00000080, 0xbef600ff, - 0x01000000, 0xd71f0000, - 0x000100c1, 0xd7200000, - 0x000200c1, 0x16000084, - 0x857d9973, 0x8b7d817d, - 0xbf06817d, 0xbefd0080, - 0xbfa20012, 0xbe8300ff, - 0x00000080, 0xbf800000, - 0xbf800000, 0xbf800000, - 0xd8d80000, 0x01000000, - 0xbf890000, 0xe0685000, - 0x701d0100, 0x807d037d, - 0x80700370, 0xd5250000, - 0x0001ff00, 0x00000080, - 0xbf0a7b7d, 0xbfa2fff4, - 0xbfa00011, 0xbe8300ff, - 0x00000100, 0xbf800000, - 0xbf800000, 0xbf800000, - 0xd8d80000, 0x01000000, - 0xbf890000, 0xe0685000, - 0x701d0100, 0x807d037d, - 0x80700370, 0xd5250000, - 0x0001ff00, 0x00000100, - 0xbf0a7b7d, 0xbfa2fff4, + 0x0000f207, 0x80798179, + 0xd7610002, 0x0000f208, + 0x80798179, 0xd7610002, + 0x0000f209, 0x80798179, + 0xd7610002, 0x0000f20a, + 0x80798179, 0xd7610002, + 0x0000f20b, 0x80798179, + 0xe0685000, 0x701d0200, 0xbefe00c1, 0x857d9973, 0x8b7d817d, 0xbf06817d, - 0xbfa20004, 0xbef000ff, - 0x00000200, 0xbeff0080, - 0xbfa00003, 0xbef000ff, - 0x00000400, 0xbeff00c1, - 0xb8fb3b05, 0x807b817b, - 0x847b827b, 0x857d9973, + 0xbfa20002, 0xbeff0080, + 0xbfa00001, 0xbeff00c1, + 0xb8fb4306, 0x8b7bc17b, + 0xbfa10044, 0xbfbd0000, + 0x8b7aff6d, 0x80000000, + 0xbfa10040, 0x847b867b, + 0x847b827b, 0xbef6007b, + 0xb8f03b05, 0x80708170, + 0xbf0d9973, 0xbfa20002, + 0x84708970, 0xbfa00001, + 0x84708a70, 0xb8fa1e06, + 0x847a8a7a, 0x80707a70, + 0x8070ff70, 0x00000200, + 0x8070ff70, 0x00000080, + 0xbef600ff, 0x01000000, + 0xd71f0000, 0x000100c1, + 0xd7200000, 0x000200c1, + 0x16000084, 0x857d9973, 0x8b7d817d, 0xbf06817d, - 0xbfa20017, 0xbef600ff, - 0x01000000, 0xbefd0084, - 0xbf0a7b7d, 0xbfa10037, - 0x7e008700, 0x7e028701, - 0x7e048702, 0x7e068703, - 0xe0685000, 0x701d0000, - 0xe0685080, 0x701d0100, - 0xe0685100, 0x701d0200, - 0xe0685180, 0x701d0300, - 0x807d847d, 0x8070ff70, - 0x00000200, 0xbf0a7b7d, - 0xbfa2ffef, 0xbfa00025, + 0xbefd0080, 0xbfa20012, + 0xbe8300ff, 0x00000080, + 0xbf800000, 0xbf800000, + 0xbf800000, 0xd8d80000, + 0x01000000, 0xbf890000, + 0xe0685000, 0x701d0100, + 0x807d037d, 0x80700370, + 0xd5250000, 0x0001ff00, + 0x00000080, 0xbf0a7b7d, + 0xbfa2fff4, 0xbfa00011, + 0xbe8300ff, 0x00000100, + 0xbf800000, 0xbf800000, + 0xbf800000, 0xd8d80000, + 0x01000000, 0xbf890000, + 0xe0685000, 0x701d0100, + 0x807d037d, 0x80700370, + 0xd5250000, 0x0001ff00, + 0x00000100, 0xbf0a7b7d, + 0xbfa2fff4, 0xbefe00c1, + 0x857d9973, 0x8b7d817d, + 0xbf06817d, 0xbfa20004, + 0xbef000ff, 0x00000200, + 0xbeff0080, 0xbfa00003, + 0xbef000ff, 0x00000400, + 0xbeff00c1, 0xb8fb3b05, + 0x807b817b, 0x847b827b, + 0x857d9973, 0x8b7d817d, + 0xbf06817d, 0xbfa20017, 0xbef600ff, 0x01000000, 0xbefd0084, 0xbf0a7b7d, - 0xbfa10011, 0x7e008700, + 0xbfa10037, 0x7e008700, 0x7e028701, 0x7e048702, 0x7e068703, 0xe0685000, - 0x701d0000, 0xe0685100, - 0x701d0100, 0xe0685200, - 0x701d0200, 0xe0685300, + 0x701d0000, 0xe0685080, + 0x701d0100, 0xe0685100, + 0x701d0200, 0xe0685180, 0x701d0300, 0x807d847d, - 0x8070ff70, 0x00000400, + 0x8070ff70, 0x00000200, 0xbf0a7b7d, 0xbfa2ffef, - 0xb8fb1e06, 0x8b7bc17b, - 0xbfa1000c, 0x847b837b, - 0x807b7d7b, 0xbefe00c1, - 0xbeff0080, 0x7e008700, + 0xbfa00025, 0xbef600ff, + 0x01000000, 0xbefd0084, + 0xbf0a7b7d, 0xbfa10011, + 0x7e008700, 0x7e028701, + 0x7e048702, 0x7e068703, 0xe0685000, 0x701d0000, - 0x807d817d, 0x8070ff70, - 0x00000080, 0xbf0a7b7d, - 0xbfa2fff8, 0xbfa00146, - 0xbef4007e, 0x8b75ff7f, - 0x0000ffff, 0x8c75ff75, - 0x00040000, 0xbef60080, - 0xbef700ff, 0x10807fac, - 0xb8f202dc, 0x84729972, - 0x8b6eff7f, 0x04000000, - 0xbfa1003a, 0xbefe00c1, - 0x857d9972, 0x8b7d817d, - 0xbf06817d, 0xbfa20002, - 0xbeff0080, 0xbfa00001, - 0xbeff00c1, 0xb8ef4306, - 0x8b6fc16f, 0xbfa1002f, - 0x846f866f, 0x846f826f, - 0xbef6006f, 0xb8f83b05, - 0x80788178, 0xbf0d9972, - 0xbfa20002, 0x84788978, - 0xbfa00001, 0x84788a78, - 0xb8ee1e06, 0x846e8a6e, - 0x80786e78, 0x8078ff78, - 0x00000200, 0x8078ff78, - 0x00000080, 0xbef600ff, - 0x01000000, 0x857d9972, - 0x8b7d817d, 0xbf06817d, - 0xbefd0080, 0xbfa2000c, - 0xe0500000, 0x781d0000, - 0xbf8903f7, 0xdac00000, - 0x00000000, 0x807dff7d, - 0x00000080, 0x8078ff78, - 0x00000080, 0xbf0a6f7d, - 0xbfa2fff5, 0xbfa0000b, - 0xe0500000, 0x781d0000, - 0xbf8903f7, 0xdac00000, - 0x00000000, 0x807dff7d, - 0x00000100, 0x8078ff78, - 0x00000100, 0xbf0a6f7d, - 0xbfa2fff5, 0xbef80080, + 0xe0685100, 0x701d0100, + 0xe0685200, 0x701d0200, + 0xe0685300, 0x701d0300, + 0x807d847d, 0x8070ff70, + 0x00000400, 0xbf0a7b7d, + 0xbfa2ffef, 0xb8fb1e06, + 0x8b7bc17b, 0xbfa1000c, + 0x847b837b, 0x807b7d7b, + 0xbefe00c1, 0xbeff0080, + 0x7e008700, 0xe0685000, + 0x701d0000, 0x807d817d, + 0x8070ff70, 0x00000080, + 0xbf0a7b7d, 0xbfa2fff8, + 0xbfa00146, 0xbef4007e, + 0x8b75ff7f, 0x0000ffff, + 0x8c75ff75, 0x00040000, + 0xbef60080, 0xbef700ff, + 0x10807fac, 0xb8f202dc, + 0x84729972, 0x8b6eff7f, + 0x04000000, 0xbfa1003a, 0xbefe00c1, 0x857d9972, 0x8b7d817d, 0xbf06817d, 0xbfa20002, 0xbeff0080, 0xbfa00001, 0xbeff00c1, - 0xb8ef3b05, 0x806f816f, - 0x846f826f, 0x857d9972, - 0x8b7d817d, 0xbf06817d, - 0xbfa20024, 0xbef600ff, - 0x01000000, 0xbeee0078, + 0xb8ef4306, 0x8b6fc16f, + 0xbfa1002f, 0x846f866f, + 0x846f826f, 0xbef6006f, + 0xb8f83b05, 0x80788178, + 0xbf0d9972, 0xbfa20002, + 0x84788978, 0xbfa00001, + 0x84788a78, 0xb8ee1e06, + 0x846e8a6e, 0x80786e78, 0x8078ff78, 0x00000200, - 0xbefd0084, 0xbf0a6f7d, - 0xbfa10050, 0xe0505000, - 0x781d0000, 0xe0505080, - 0x781d0100, 0xe0505100, - 0x781d0200, 0xe0505180, - 0x781d0300, 0xbf8903f7, - 0x7e008500, 0x7e028501, - 0x7e048502, 0x7e068503, - 0x807d847d, 0x8078ff78, - 0x00000200, 0xbf0a6f7d, - 0xbfa2ffee, 0xe0505000, - 0x6e1d0000, 0xe0505080, - 0x6e1d0100, 0xe0505100, - 0x6e1d0200, 0xe0505180, - 0x6e1d0300, 0xbf8903f7, - 0xbfa00034, 0xbef600ff, - 0x01000000, 0xbeee0078, - 0x8078ff78, 0x00000400, - 0xbefd0084, 0xbf0a6f7d, - 0xbfa10012, 0xe0505000, - 0x781d0000, 0xe0505100, - 0x781d0100, 0xe0505200, - 0x781d0200, 0xe0505300, - 0x781d0300, 0xbf8903f7, - 0x7e008500, 0x7e028501, - 0x7e048502, 0x7e068503, - 0x807d847d, 0x8078ff78, - 0x00000400, 0xbf0a6f7d, - 0xbfa2ffee, 0xb8ef1e06, - 0x8b6fc16f, 0xbfa1000e, - 0x846f836f, 0x806f7d6f, - 0xbefe00c1, 0xbeff0080, + 0x8078ff78, 0x00000080, + 0xbef600ff, 0x01000000, + 0x857d9972, 0x8b7d817d, + 0xbf06817d, 0xbefd0080, + 0xbfa2000c, 0xe0500000, + 0x781d0000, 0xbf8903f7, + 0xdac00000, 0x00000000, + 0x807dff7d, 0x00000080, + 0x8078ff78, 0x00000080, + 0xbf0a6f7d, 0xbfa2fff5, + 0xbfa0000b, 0xe0500000, + 0x781d0000, 0xbf8903f7, + 0xdac00000, 0x00000000, + 0x807dff7d, 0x00000100, + 0x8078ff78, 0x00000100, + 0xbf0a6f7d, 0xbfa2fff5, + 0xbef80080, 0xbefe00c1, + 0x857d9972, 0x8b7d817d, + 0xbf06817d, 0xbfa20002, + 0xbeff0080, 0xbfa00001, + 0xbeff00c1, 0xb8ef3b05, + 0x806f816f, 0x846f826f, + 0x857d9972, 0x8b7d817d, + 0xbf06817d, 0xbfa20024, + 0xbef600ff, 0x01000000, + 0xbeee0078, 0x8078ff78, + 0x00000200, 0xbefd0084, + 0xbf0a6f7d, 0xbfa10050, 0xe0505000, 0x781d0000, + 0xe0505080, 0x781d0100, + 0xe0505100, 0x781d0200, + 0xe0505180, 0x781d0300, 0xbf8903f7, 0x7e008500, - 0x807d817d, 0x8078ff78, - 0x00000080, 0xbf0a6f7d, - 0xbfa2fff7, 0xbeff00c1, + 0x7e028501, 0x7e048502, + 0x7e068503, 0x807d847d, + 0x8078ff78, 0x00000200, + 0xbf0a6f7d, 0xbfa2ffee, 0xe0505000, 0x6e1d0000, - 0xe0505100, 0x6e1d0100, - 0xe0505200, 0x6e1d0200, - 0xe0505300, 0x6e1d0300, - 0xbf8903f7, 0xb8f83b05, - 0x80788178, 0xbf0d9972, - 0xbfa20002, 0x84788978, - 0xbfa00001, 0x84788a78, - 0xb8ee1e06, 0x846e8a6e, - 0x80786e78, 0x8078ff78, - 0x00000200, 0x80f8ff78, - 0x00000050, 0xbef600ff, - 0x01000000, 0xbefd00ff, - 0x0000006c, 0x80f89078, - 0xf428403a, 0xf0000000, - 0xbf89fc07, 0x80fd847d, - 0xbf800000, 0xbe804300, - 0xbe824302, 0x80f8a078, - 0xf42c403a, 0xf0000000, - 0xbf89fc07, 0x80fd887d, - 0xbf800000, 0xbe804300, - 0xbe824302, 0xbe844304, - 0xbe864306, 0x80f8c078, - 0xf430403a, 0xf0000000, - 0xbf89fc07, 0x80fd907d, - 0xbf800000, 0xbe804300, - 0xbe824302, 0xbe844304, - 0xbe864306, 0xbe884308, - 0xbe8a430a, 0xbe8c430c, - 0xbe8e430e, 0xbf06807d, - 0xbfa1fff0, 0xb980f801, - 0x00000000, 0xbfbd0000, + 0xe0505080, 0x6e1d0100, + 0xe0505100, 0x6e1d0200, + 0xe0505180, 0x6e1d0300, + 0xbf8903f7, 0xbfa00034, + 0xbef600ff, 0x01000000, + 0xbeee0078, 0x8078ff78, + 0x00000400, 0xbefd0084, + 0xbf0a6f7d, 0xbfa10012, + 0xe0505000, 0x781d0000, + 0xe0505100, 0x781d0100, + 0xe0505200, 0x781d0200, + 0xe0505300, 0x781d0300, + 0xbf8903f7, 0x7e008500, + 0x7e028501, 0x7e048502, + 0x7e068503, 0x807d847d, + 0x8078ff78, 0x00000400, + 0xbf0a6f7d, 0xbfa2ffee, + 0xb8ef1e06, 0x8b6fc16f, + 0xbfa1000e, 0x846f836f, + 0x806f7d6f, 0xbefe00c1, + 0xbeff0080, 0xe0505000, + 0x781d0000, 0xbf8903f7, + 0x7e008500, 0x807d817d, + 0x8078ff78, 0x00000080, + 0xbf0a6f7d, 0xbfa2fff7, + 0xbeff00c1, 0xe0505000, + 0x6e1d0000, 0xe0505100, + 0x6e1d0100, 0xe0505200, + 0x6e1d0200, 0xe0505300, + 0x6e1d0300, 0xbf8903f7, 0xb8f83b05, 0x80788178, 0xbf0d9972, 0xbfa20002, 0x84788978, 0xbfa00001, 0x84788a78, 0xb8ee1e06, 0x846e8a6e, 0x80786e78, 0x8078ff78, 0x00000200, + 0x80f8ff78, 0x00000050, 0xbef600ff, 0x01000000, - 0xf4205bfa, 0xf0000000, - 0x80788478, 0xf4205b3a, + 0xbefd00ff, 0x0000006c, + 0x80f89078, 0xf428403a, + 0xf0000000, 0xbf89fc07, + 0x80fd847d, 0xbf800000, + 0xbe804300, 0xbe824302, + 0x80f8a078, 0xf42c403a, + 0xf0000000, 0xbf89fc07, + 0x80fd887d, 0xbf800000, + 0xbe804300, 0xbe824302, + 0xbe844304, 0xbe864306, + 0x80f8c078, 0xf430403a, + 0xf0000000, 0xbf89fc07, + 0x80fd907d, 0xbf800000, + 0xbe804300, 0xbe824302, + 0xbe844304, 0xbe864306, + 0xbe884308, 0xbe8a430a, + 0xbe8c430c, 0xbe8e430e, + 0xbf06807d, 0xbfa1fff0, + 0xb980f801, 0x00000000, + 0xbfbd0000, 0xb8f83b05, + 0x80788178, 0xbf0d9972, + 0xbfa20002, 0x84788978, + 0xbfa00001, 0x84788a78, + 0xb8ee1e06, 0x846e8a6e, + 0x80786e78, 0x8078ff78, + 0x00000200, 0xbef600ff, + 0x01000000, 0xf4205bfa, 0xf0000000, 0x80788478, - 0xf4205b7a, 0xf0000000, - 0x80788478, 0xf4205c3a, + 0xf4205b3a, 0xf0000000, + 0x80788478, 0xf4205b7a, 0xf0000000, 0x80788478, - 0xf4205c7a, 0xf0000000, - 0x80788478, 0xf4205eba, + 0xf4205c3a, 0xf0000000, + 0x80788478, 0xf4205c7a, 0xf0000000, 0x80788478, - 0xf4205efa, 0xf0000000, - 0x80788478, 0xf4205e7a, + 0xf4205eba, 0xf0000000, + 0x80788478, 0xf4205efa, 0xf0000000, 0x80788478, - 0xf4205cfa, 0xf0000000, - 0x80788478, 0xf4205bba, + 0xf4205e7a, 0xf0000000, + 0x80788478, 0xf4205cfa, 0xf0000000, 0x80788478, - 0xbf89fc07, 0xb96ef814, 0xf4205bba, 0xf0000000, 0x80788478, 0xbf89fc07, - 0xb96ef815, 0xbefd006f, - 0xbefe0070, 0xbeff0071, - 0x8b6f7bff, 0x000003ff, - 0xb96f4803, 0x8b6f7bff, - 0xfffff800, 0x856f8b6f, - 0xb96fa2c3, 0xb973f801, - 0xb8ee3b05, 0x806e816e, - 0xbf0d9972, 0xbfa20002, - 0x846e896e, 0xbfa00001, - 0x846e8a6e, 0xb8ef1e06, - 0x846f8a6f, 0x806e6f6e, - 0x806eff6e, 0x00000200, - 0x806e746e, 0x826f8075, - 0x8b6fff6f, 0x0000ffff, - 0xf4085c37, 0xf8000050, - 0xf4085d37, 0xf8000060, - 0xf4005e77, 0xf8000074, - 0xbf89fc07, 0x8b6dff6d, - 0x0000ffff, 0x8bfe7e7e, - 0x8bea6a6a, 0xb8eef802, - 0xbf0d866e, 0xbfa20002, - 0xb97af802, 0xbe80486c, - 0xb97af802, 0xbe804a6c, - 0xbfb00000, 0xbf9f0000, + 0xb96ef814, 0xf4205bba, + 0xf0000000, 0x80788478, + 0xbf89fc07, 0xb96ef815, + 0xbefd006f, 0xbefe0070, + 0xbeff0071, 0x8b6f7bff, + 0x000003ff, 0xb96f4803, + 0x8b6f7bff, 0xfffff800, + 0x856f8b6f, 0xb96fa2c3, + 0xb973f801, 0xb8ee3b05, + 0x806e816e, 0xbf0d9972, + 0xbfa20002, 0x846e896e, + 0xbfa00001, 0x846e8a6e, + 0xb8ef1e06, 0x846f8a6f, + 0x806e6f6e, 0x806eff6e, + 0x00000200, 0x806e746e, + 0x826f8075, 0x8b6fff6f, + 0x0000ffff, 0xf4085c37, + 0xf8000050, 0xf4085d37, + 0xf8000060, 0xf4005e77, + 0xf8000074, 0xbf89fc07, + 0x8b6dff6d, 0x0000ffff, + 0x8bfe7e7e, 0x8bea6a6a, + 0xb8eef802, 0xbf0d866e, + 0xbfa20002, 0xb97af802, + 0xbe80486c, 0xb97af802, + 0xbe804a6c, 0xbfb00000, 0xbf9f0000, 0xbf9f0000, 0xbf9f0000, 0xbf9f0000, + 0xbf9f0000, 0x00000000, }; diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm index 0f81670f6f9c..8b92c33c2a7c 100644 --- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm +++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm @@ -186,6 +186,12 @@ L_SKIP_RESTORE: s_getreg_b32 s_save_trapsts, hwreg(HW_REG_TRAPSTS) #if SW_SA_TRAP + // If ttmp1[30] is set then issue s_barrier to unblock dependent waves. + s_bitcmp1_b32 s_save_pc_hi, 30 + s_cbranch_scc0 L_TRAP_NO_BARRIER + s_barrier + +L_TRAP_NO_BARRIER: // If ttmp1[31] is set then trap may occur early. // Spin wait until SAVECTX exception is raised. s_bitcmp1_b32 s_save_pc_hi, 31 diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c index 2797029bd500..22b077ac9a19 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c @@ -973,12 +973,10 @@ out_unlock_prange: out_unlock_svms: mutex_unlock(&p->svms.lock); out_unref_process: + pr_debug("CPU fault svms 0x%p address 0x%lx done\n", &p->svms, addr); kfd_unref_process(p); out_mmput: mmput(mm); - - pr_debug("CPU fault svms 0x%p address 0x%lx done\n", &p->svms, addr); - return r ? VM_FAULT_SIGBUS : 0; } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index c053cb79cd06..589bee9acf16 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1549,6 +1549,9 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) adev->dm.dc->debug.visual_confirm = amdgpu_dc_visual_confirm; + /* TODO: Remove after DP2 receiver gets proper support of Cable ID feature */ + adev->dm.dc->debug.ignore_cable_id = true; + r = dm_dmub_hw_init(adev); if (r) { DRM_ERROR("DMUB interface failed to initialize: status=%d\n", r); diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c index 1c612ccf1944..6f77d8e538ab 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c @@ -157,6 +157,7 @@ void dcn32_init_clocks(struct clk_mgr *clk_mgr_base) struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base); unsigned int num_levels; struct clk_limit_num_entries *num_entries_per_clk = &clk_mgr_base->bw_params->clk_table.num_entries_per_clk; + unsigned int i; memset(&(clk_mgr_base->clks), 0, sizeof(struct dc_clocks)); clk_mgr_base->clks.p_state_change_support = true; @@ -205,18 +206,17 @@ void dcn32_init_clocks(struct clk_mgr *clk_mgr_base) clk_mgr->dpm_present = true; if (clk_mgr_base->ctx->dc->debug.min_disp_clk_khz) { - unsigned int i; - for (i = 0; i < num_levels; i++) if (clk_mgr_base->bw_params->clk_table.entries[i].dispclk_mhz < khz_to_mhz_ceil(clk_mgr_base->ctx->dc->debug.min_disp_clk_khz)) clk_mgr_base->bw_params->clk_table.entries[i].dispclk_mhz = khz_to_mhz_ceil(clk_mgr_base->ctx->dc->debug.min_disp_clk_khz); } + for (i = 0; i < num_levels; i++) + if (clk_mgr_base->bw_params->clk_table.entries[i].dispclk_mhz > 1950) + clk_mgr_base->bw_params->clk_table.entries[i].dispclk_mhz = 1950; if (clk_mgr_base->ctx->dc->debug.min_dpp_clk_khz) { - unsigned int i; - for (i = 0; i < num_levels; i++) if (clk_mgr_base->bw_params->clk_table.entries[i].dppclk_mhz < khz_to_mhz_ceil(clk_mgr_base->ctx->dc->debug.min_dpp_clk_khz)) @@ -669,6 +669,9 @@ static void dcn32_get_memclk_states_from_smu(struct clk_mgr *clk_mgr_base) &clk_mgr_base->bw_params->clk_table.entries[0].memclk_mhz, &num_entries_per_clk->num_memclk_levels); + /* memclk must have at least one level */ + num_entries_per_clk->num_memclk_levels = num_entries_per_clk->num_memclk_levels ? num_entries_per_clk->num_memclk_levels : 1; + dcn32_init_single_clock(clk_mgr, PPCLK_FCLK, &clk_mgr_base->bw_params->clk_table.entries[0].fclk_mhz, &num_entries_per_clk->num_fclk_levels); diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index bfc5474c0f4c..737b221ca689 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -852,6 +852,7 @@ struct dc_debug_options { bool enable_double_buffered_dsc_pg_support; bool enable_dp_dig_pixel_rate_div_policy; enum lttpr_mode lttpr_mode_override; + unsigned int dsc_delay_factor_wa_x1000; }; struct gpu_info_soc_bounding_box_v1_0; diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c index 4996d2810edb..938dba5249d4 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c @@ -623,6 +623,10 @@ void hubp2_cursor_set_attributes( hubp->att.size.bits.width = attr->width; hubp->att.size.bits.height = attr->height; hubp->att.cur_ctl.bits.mode = attr->color_format; + + hubp->cur_rect.w = attr->width; + hubp->cur_rect.h = attr->height; + hubp->att.cur_ctl.bits.pitch = hw_pitch; hubp->att.cur_ctl.bits.line_per_chunk = lpc; hubp->att.cur_ctl.bits.cur_2x_magnify = attr->attribute_flags.bits.ENABLE_MAGNIFICATION; diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c index d0ad72caead2..9066c511a052 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c @@ -847,7 +847,7 @@ static const struct resource_caps res_cap_dcn314 = { .num_ddc = 5, .num_vmid = 16, .num_mpc_3dlut = 2, - .num_dsc = 3, + .num_dsc = 4, }; static const struct dc_plane_cap plane_cap = { diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c index d680f1c5b69f..45db40c41882 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c @@ -1228,6 +1228,7 @@ int dcn20_populate_dml_pipes_from_context( pipes[pipe_cnt].pipe.src.dcc = false; pipes[pipe_cnt].pipe.src.dcc_rate = 1; pipes[pipe_cnt].pipe.dest.synchronized_vblank_all_planes = synchronized_vblank; + pipes[pipe_cnt].pipe.dest.synchronize_timings = synchronized_vblank; pipes[pipe_cnt].pipe.dest.hblank_start = timing->h_total - timing->h_front_porch; pipes[pipe_cnt].pipe.dest.hblank_end = pipes[pipe_cnt].pipe.dest.hblank_start - timing->h_addressable diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c index 819de0f11012..f37c9a6b3b7e 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c @@ -2359,9 +2359,11 @@ void dcn32_update_bw_bounding_box_fpu(struct dc *dc, struct clk_bw_params *bw_pa if (dc->ctx->dc_bios->vram_info.dram_channel_width_bytes) dcn3_2_soc.dram_channel_width_bytes = dc->ctx->dc_bios->vram_info.dram_channel_width_bytes; - } + /* DML DSC delay factor workaround */ + dcn3_2_ip.dsc_delay_factor_wa = dc->debug.dsc_delay_factor_wa_x1000 / 1000.0; + /* Override dispclk_dppclk_vco_speed_mhz from Clk Mgr */ dcn3_2_soc.dispclk_dppclk_vco_speed_mhz = dc->clk_mgr->dentist_vco_freq_khz / 1000.0; dc->dml.soc.dispclk_dppclk_vco_speed_mhz = dc->clk_mgr->dentist_vco_freq_khz / 1000.0; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c index 5b91660a6496..3d184679f129 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c @@ -364,10 +364,11 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman for (k = 0; k < mode_lib->vba.NumberOfActiveSurfaces; ++k) { v->DSCDelay[k] = dml32_DSCDelayRequirement(mode_lib->vba.DSCEnabled[k], mode_lib->vba.ODMCombineEnabled[k], mode_lib->vba.DSCInputBitPerComponent[k], - mode_lib->vba.OutputBpp[k], mode_lib->vba.HActive[k], mode_lib->vba.HTotal[k], + mode_lib->vba.OutputBppPerState[mode_lib->vba.VoltageLevel][k], + mode_lib->vba.HActive[k], mode_lib->vba.HTotal[k], mode_lib->vba.NumberOfDSCSlices[k], mode_lib->vba.OutputFormat[k], mode_lib->vba.Output[k], mode_lib->vba.PixelClock[k], - mode_lib->vba.PixelClockBackEnd[k]); + mode_lib->vba.PixelClockBackEnd[k], mode_lib->vba.ip.dsc_delay_factor_wa); } for (k = 0; k < mode_lib->vba.NumberOfActiveSurfaces; ++k) @@ -1627,7 +1628,7 @@ static void mode_support_configuration(struct vba_vars_st *v, && !mode_lib->vba.MSOOrODMSplitWithNonDPLink && !mode_lib->vba.NotEnoughLanesForMSO && mode_lib->vba.LinkCapacitySupport[i] == true && !mode_lib->vba.P2IWith420 - && !mode_lib->vba.DSCOnlyIfNecessaryWithBPP + //&& !mode_lib->vba.DSCOnlyIfNecessaryWithBPP && !mode_lib->vba.DSC422NativeNotSupported && !mode_lib->vba.MPCCombineMethodIncompatible && mode_lib->vba.ODMCombine2To1SupportCheckOK[i] == true @@ -2475,7 +2476,8 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l mode_lib->vba.OutputBppPerState[i][k], mode_lib->vba.HActive[k], mode_lib->vba.HTotal[k], mode_lib->vba.NumberOfDSCSlices[k], mode_lib->vba.OutputFormat[k], mode_lib->vba.Output[k], - mode_lib->vba.PixelClock[k], mode_lib->vba.PixelClockBackEnd[k]); + mode_lib->vba.PixelClock[k], mode_lib->vba.PixelClockBackEnd[k], + mode_lib->vba.ip.dsc_delay_factor_wa); } for (k = 0; k <= mode_lib->vba.NumberOfActiveSurfaces - 1; k++) { diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c index ad66e241f9ae..968924c491c1 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c @@ -1726,7 +1726,8 @@ unsigned int dml32_DSCDelayRequirement(bool DSCEnabled, enum output_format_class OutputFormat, enum output_encoder_class Output, double PixelClock, - double PixelClockBackEnd) + double PixelClockBackEnd, + double dsc_delay_factor_wa) { unsigned int DSCDelayRequirement_val; @@ -1746,7 +1747,7 @@ unsigned int dml32_DSCDelayRequirement(bool DSCEnabled, } DSCDelayRequirement_val = DSCDelayRequirement_val + (HTotal - HActive) * - dml_ceil(DSCDelayRequirement_val / HActive, 1); + dml_ceil((double)DSCDelayRequirement_val / HActive, 1); DSCDelayRequirement_val = DSCDelayRequirement_val * PixelClock / PixelClockBackEnd; @@ -1764,7 +1765,7 @@ unsigned int dml32_DSCDelayRequirement(bool DSCEnabled, dml_print("DML::%s: DSCDelayRequirement_val = %d\n", __func__, DSCDelayRequirement_val); #endif - return DSCDelayRequirement_val; + return dml_ceil(DSCDelayRequirement_val * dsc_delay_factor_wa, 1); } void dml32_CalculateSurfaceSizeInMall( diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h index 55cead0d4237..2c3827546ac7 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h @@ -327,7 +327,8 @@ unsigned int dml32_DSCDelayRequirement(bool DSCEnabled, enum output_format_class OutputFormat, enum output_encoder_class Output, double PixelClock, - double PixelClockBackEnd); + double PixelClockBackEnd, + double dsc_delay_factor_wa); void dml32_CalculateSurfaceSizeInMall( unsigned int NumberOfActiveSurfaces, diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_rq_dlg_calc_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_rq_dlg_calc_32.c index a1276f6b9581..395ae8761980 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_rq_dlg_calc_32.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_rq_dlg_calc_32.c @@ -291,8 +291,8 @@ void dml32_rq_dlg_get_dlg_reg(struct display_mode_lib *mode_lib, dml_print("DML_DLG: %s: vready_after_vcount0 = %d\n", __func__, dlg_regs->vready_after_vcount0); - dst_x_after_scaler = get_dst_x_after_scaler(mode_lib, e2e_pipe_param, num_pipes, pipe_idx); - dst_y_after_scaler = get_dst_y_after_scaler(mode_lib, e2e_pipe_param, num_pipes, pipe_idx); + dst_x_after_scaler = dml_ceil(get_dst_x_after_scaler(mode_lib, e2e_pipe_param, num_pipes, pipe_idx), 1); + dst_y_after_scaler = dml_ceil(get_dst_y_after_scaler(mode_lib, e2e_pipe_param, num_pipes, pipe_idx), 1); // do some adjustment on the dst_after scaler to account for odm combine mode dml_print("DML_DLG: %s: input dst_x_after_scaler = %d\n", __func__, dst_x_after_scaler); diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c index dd90f241e906..ec0486efab14 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c @@ -29,6 +29,7 @@ #include "dcn321_fpu.h" #include "dcn32/dcn32_resource.h" #include "dcn321/dcn321_resource.h" +#include "dml/dcn32/display_mode_vba_util_32.h" #define DCN3_2_DEFAULT_DET_SIZE 256 @@ -119,15 +120,15 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_21_soc = { }, }, .num_states = 1, - .sr_exit_time_us = 12.36, - .sr_enter_plus_exit_time_us = 16.72, + .sr_exit_time_us = 19.95, + .sr_enter_plus_exit_time_us = 24.36, .sr_exit_z8_time_us = 285.0, .sr_enter_plus_exit_z8_time_us = 320, .writeback_latency_us = 12.0, .round_trip_ping_latency_dcfclk_cycles = 263, - .urgent_latency_pixel_data_only_us = 4.0, - .urgent_latency_pixel_mixed_with_vm_data_us = 4.0, - .urgent_latency_vm_data_only_us = 4.0, + .urgent_latency_pixel_data_only_us = 9.35, + .urgent_latency_pixel_mixed_with_vm_data_us = 9.35, + .urgent_latency_vm_data_only_us = 9.35, .fclk_change_latency_us = 20, .usr_retraining_latency_us = 2, .smn_latency_us = 2, @@ -538,9 +539,11 @@ void dcn321_update_bw_bounding_box_fpu(struct dc *dc, struct clk_bw_params *bw_p if (dc->ctx->dc_bios->vram_info.dram_channel_width_bytes) dcn3_21_soc.dram_channel_width_bytes = dc->ctx->dc_bios->vram_info.dram_channel_width_bytes; - } + /* DML DSC delay factor workaround */ + dcn3_21_ip.dsc_delay_factor_wa = dc->debug.dsc_delay_factor_wa_x1000 / 1000.0; + /* Override dispclk_dppclk_vco_speed_mhz from Clk Mgr */ dcn3_21_soc.dispclk_dppclk_vco_speed_mhz = dc->clk_mgr->dentist_vco_freq_khz / 1000.0; dc->dml.soc.dispclk_dppclk_vco_speed_mhz = dc->clk_mgr->dentist_vco_freq_khz / 1000.0; diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h index f33a8879b05a..d7be01ac0751 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h +++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h @@ -364,6 +364,9 @@ struct _vcs_dpi_ip_params_st { unsigned int max_num_dp2p0_outputs; unsigned int max_num_dp2p0_streams; unsigned int VBlankNomDefaultUS; + + /* DM workarounds */ + double dsc_delay_factor_wa; // TODO: Remove after implementing root cause fix }; struct _vcs_dpi_display_xfc_params_st { diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c index 03924aed8d5c..8e6585dab20e 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c +++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c @@ -625,7 +625,7 @@ static void fetch_pipe_params(struct display_mode_lib *mode_lib) mode_lib->vba.skip_dio_check[mode_lib->vba.NumberOfActivePlanes] = dout->is_virtual; - if (!dout->dsc_enable) + if (dout->dsc_enable) mode_lib->vba.ForcedOutputLinkBPP[mode_lib->vba.NumberOfActivePlanes] = dout->output_bpp; else mode_lib->vba.ForcedOutputLinkBPP[mode_lib->vba.NumberOfActivePlanes] = 0.0; diff --git a/drivers/gpu/drm/drm_format_helper.c b/drivers/gpu/drm/drm_format_helper.c index e2f76621453c..3ee59bae9d2f 100644 --- a/drivers/gpu/drm/drm_format_helper.c +++ b/drivers/gpu/drm/drm_format_helper.c @@ -807,6 +807,38 @@ static bool is_listed_fourcc(const uint32_t *fourccs, size_t nfourccs, uint32_t return false; } +static const uint32_t conv_from_xrgb8888[] = { + DRM_FORMAT_XRGB8888, + DRM_FORMAT_ARGB8888, + DRM_FORMAT_XRGB2101010, + DRM_FORMAT_ARGB2101010, + DRM_FORMAT_RGB565, + DRM_FORMAT_RGB888, +}; + +static const uint32_t conv_from_rgb565_888[] = { + DRM_FORMAT_XRGB8888, + DRM_FORMAT_ARGB8888, +}; + +static bool is_conversion_supported(uint32_t from, uint32_t to) +{ + switch (from) { + case DRM_FORMAT_XRGB8888: + case DRM_FORMAT_ARGB8888: + return is_listed_fourcc(conv_from_xrgb8888, ARRAY_SIZE(conv_from_xrgb8888), to); + case DRM_FORMAT_RGB565: + case DRM_FORMAT_RGB888: + return is_listed_fourcc(conv_from_rgb565_888, ARRAY_SIZE(conv_from_rgb565_888), to); + case DRM_FORMAT_XRGB2101010: + return to == DRM_FORMAT_ARGB2101010; + case DRM_FORMAT_ARGB2101010: + return to == DRM_FORMAT_XRGB2101010; + default: + return false; + } +} + /** * drm_fb_build_fourcc_list - Filters a list of supported color formats against * the device's native formats @@ -827,7 +859,9 @@ static bool is_listed_fourcc(const uint32_t *fourccs, size_t nfourccs, uint32_t * be handed over to drm_universal_plane_init() et al. Native formats * will go before emulated formats. Other heuristics might be applied * to optimize the order. Formats near the beginning of the list are - * usually preferred over formats near the end of the list. + * usually preferred over formats near the end of the list. Formats + * without conversion helpers will be skipped. New drivers should only + * pass in XRGB8888 and avoid exposing additional emulated formats. * * Returns: * The number of color-formats 4CC codes returned in @fourccs_out. @@ -839,7 +873,7 @@ size_t drm_fb_build_fourcc_list(struct drm_device *dev, { u32 *fourccs = fourccs_out; const u32 *fourccs_end = fourccs_out + nfourccs_out; - bool found_native = false; + uint32_t native_format = 0; size_t i; /* @@ -858,27 +892,19 @@ size_t drm_fb_build_fourcc_list(struct drm_device *dev, drm_dbg_kms(dev, "adding native format %p4cc\n", &fourcc); - if (!found_native) - found_native = is_listed_fourcc(driver_fourccs, driver_nfourccs, fourcc); + /* + * There should only be one native format with the current API. + * This API needs to be refactored to correctly support arbitrary + * sets of native formats, since it needs to report which native + * format to use for each emulated format. + */ + if (!native_format) + native_format = fourcc; *fourccs = fourcc; ++fourccs; } /* - * The plane's atomic_update helper converts the framebuffer's color format - * to a native format when copying to device memory. - * - * If there is not a single format supported by both, device and - * driver, the native formats are likely not supported by the conversion - * helpers. Therefore *only* support the native formats and add a - * conversion helper ASAP. - */ - if (!found_native) { - drm_warn(dev, "Format conversion helpers required to add extra formats.\n"); - goto out; - } - - /* * The extra formats, emulated by the driver, go second. */ @@ -890,6 +916,9 @@ size_t drm_fb_build_fourcc_list(struct drm_device *dev, } else if (fourccs == fourccs_end) { drm_warn(dev, "Ignoring emulated format %p4cc\n", &fourcc); continue; /* end of available output buffer */ + } else if (!is_conversion_supported(fourcc, native_format)) { + drm_dbg_kms(dev, "Unsupported emulated format %p4cc\n", &fourcc); + continue; /* format is not supported for conversion */ } drm_dbg_kms(dev, "adding emulated format %p4cc\n", &fourcc); @@ -898,7 +927,6 @@ size_t drm_fb_build_fourcc_list(struct drm_device *dev, ++fourccs; } -out: return fourccs - fourccs_out; } EXPORT_SYMBOL(drm_fb_build_fourcc_list); diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index a26edcdadc21..cea00aaca04b 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -282,6 +282,7 @@ i915-y += \ display/intel_ddi.o \ display/intel_ddi_buf_trans.o \ display/intel_display_trace.o \ + display/intel_dkl_phy.o \ display/intel_dp.o \ display/intel_dp_aux.o \ display/intel_dp_aux_backlight.o \ diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c index da8472cdc135..69ecf2a3d6c6 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.c +++ b/drivers/gpu/drm/i915/display/intel_ddi.c @@ -43,6 +43,7 @@ #include "intel_de.h" #include "intel_display_power.h" #include "intel_display_types.h" +#include "intel_dkl_phy.h" #include "intel_dp.h" #include "intel_dp_link_training.h" #include "intel_dp_mst.h" @@ -1262,33 +1263,30 @@ static void tgl_dkl_phy_set_signal_levels(struct intel_encoder *encoder, for (ln = 0; ln < 2; ln++) { int level; - intel_de_write(dev_priv, HIP_INDEX_REG(tc_port), - HIP_INDEX_VAL(tc_port, ln)); - - intel_de_write(dev_priv, DKL_TX_PMD_LANE_SUS(tc_port), 0); + intel_dkl_phy_write(dev_priv, DKL_TX_PMD_LANE_SUS(tc_port), ln, 0); level = intel_ddi_level(encoder, crtc_state, 2*ln+0); - intel_de_rmw(dev_priv, DKL_TX_DPCNTL0(tc_port), - DKL_TX_PRESHOOT_COEFF_MASK | - DKL_TX_DE_EMPAHSIS_COEFF_MASK | - DKL_TX_VSWING_CONTROL_MASK, - DKL_TX_PRESHOOT_COEFF(trans->entries[level].dkl.preshoot) | - DKL_TX_DE_EMPHASIS_COEFF(trans->entries[level].dkl.de_emphasis) | - DKL_TX_VSWING_CONTROL(trans->entries[level].dkl.vswing)); + intel_dkl_phy_rmw(dev_priv, DKL_TX_DPCNTL0(tc_port), ln, + DKL_TX_PRESHOOT_COEFF_MASK | + DKL_TX_DE_EMPAHSIS_COEFF_MASK | + DKL_TX_VSWING_CONTROL_MASK, + DKL_TX_PRESHOOT_COEFF(trans->entries[level].dkl.preshoot) | + DKL_TX_DE_EMPHASIS_COEFF(trans->entries[level].dkl.de_emphasis) | + DKL_TX_VSWING_CONTROL(trans->entries[level].dkl.vswing)); level = intel_ddi_level(encoder, crtc_state, 2*ln+1); - intel_de_rmw(dev_priv, DKL_TX_DPCNTL1(tc_port), - DKL_TX_PRESHOOT_COEFF_MASK | - DKL_TX_DE_EMPAHSIS_COEFF_MASK | - DKL_TX_VSWING_CONTROL_MASK, - DKL_TX_PRESHOOT_COEFF(trans->entries[level].dkl.preshoot) | - DKL_TX_DE_EMPHASIS_COEFF(trans->entries[level].dkl.de_emphasis) | - DKL_TX_VSWING_CONTROL(trans->entries[level].dkl.vswing)); + intel_dkl_phy_rmw(dev_priv, DKL_TX_DPCNTL1(tc_port), ln, + DKL_TX_PRESHOOT_COEFF_MASK | + DKL_TX_DE_EMPAHSIS_COEFF_MASK | + DKL_TX_VSWING_CONTROL_MASK, + DKL_TX_PRESHOOT_COEFF(trans->entries[level].dkl.preshoot) | + DKL_TX_DE_EMPHASIS_COEFF(trans->entries[level].dkl.de_emphasis) | + DKL_TX_VSWING_CONTROL(trans->entries[level].dkl.vswing)); - intel_de_rmw(dev_priv, DKL_TX_DPCNTL2(tc_port), - DKL_TX_DP20BITMODE, 0); + intel_dkl_phy_rmw(dev_priv, DKL_TX_DPCNTL2(tc_port), ln, + DKL_TX_DP20BITMODE, 0); if (IS_ALDERLAKE_P(dev_priv)) { u32 val; @@ -1306,10 +1304,10 @@ static void tgl_dkl_phy_set_signal_levels(struct intel_encoder *encoder, val |= DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX2(0); } - intel_de_rmw(dev_priv, DKL_TX_DPCNTL2(tc_port), - DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX1_MASK | - DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX2_MASK, - val); + intel_dkl_phy_rmw(dev_priv, DKL_TX_DPCNTL2(tc_port), ln, + DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX1_MASK | + DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX2_MASK, + val); } } } @@ -2019,12 +2017,8 @@ icl_program_mg_dp_mode(struct intel_digital_port *dig_port, return; if (DISPLAY_VER(dev_priv) >= 12) { - intel_de_write(dev_priv, HIP_INDEX_REG(tc_port), - HIP_INDEX_VAL(tc_port, 0x0)); - ln0 = intel_de_read(dev_priv, DKL_DP_MODE(tc_port)); - intel_de_write(dev_priv, HIP_INDEX_REG(tc_port), - HIP_INDEX_VAL(tc_port, 0x1)); - ln1 = intel_de_read(dev_priv, DKL_DP_MODE(tc_port)); + ln0 = intel_dkl_phy_read(dev_priv, DKL_DP_MODE(tc_port), 0); + ln1 = intel_dkl_phy_read(dev_priv, DKL_DP_MODE(tc_port), 1); } else { ln0 = intel_de_read(dev_priv, MG_DP_MODE(0, tc_port)); ln1 = intel_de_read(dev_priv, MG_DP_MODE(1, tc_port)); @@ -2085,12 +2079,8 @@ icl_program_mg_dp_mode(struct intel_digital_port *dig_port, } if (DISPLAY_VER(dev_priv) >= 12) { - intel_de_write(dev_priv, HIP_INDEX_REG(tc_port), - HIP_INDEX_VAL(tc_port, 0x0)); - intel_de_write(dev_priv, DKL_DP_MODE(tc_port), ln0); - intel_de_write(dev_priv, HIP_INDEX_REG(tc_port), - HIP_INDEX_VAL(tc_port, 0x1)); - intel_de_write(dev_priv, DKL_DP_MODE(tc_port), ln1); + intel_dkl_phy_write(dev_priv, DKL_DP_MODE(tc_port), 0, ln0); + intel_dkl_phy_write(dev_priv, DKL_DP_MODE(tc_port), 1, ln1); } else { intel_de_write(dev_priv, MG_DP_MODE(0, tc_port), ln0); intel_de_write(dev_priv, MG_DP_MODE(1, tc_port), ln1); @@ -3094,10 +3084,8 @@ static void adlp_tbt_to_dp_alt_switch_wa(struct intel_encoder *encoder) enum tc_port tc_port = intel_port_to_tc(i915, encoder->port); int ln; - for (ln = 0; ln < 2; ln++) { - intel_de_write(i915, HIP_INDEX_REG(tc_port), HIP_INDEX_VAL(tc_port, ln)); - intel_de_rmw(i915, DKL_PCS_DW5(tc_port), DKL_PCS_DW5_CORE_SOFTRESET, 0); - } + for (ln = 0; ln < 2; ln++) + intel_dkl_phy_rmw(i915, DKL_PCS_DW5(tc_port), ln, DKL_PCS_DW5_CORE_SOFTRESET, 0); } static void intel_ddi_prepare_link_retrain(struct intel_dp *intel_dp, diff --git a/drivers/gpu/drm/i915/display/intel_display_core.h b/drivers/gpu/drm/i915/display/intel_display_core.h index 96cf994b0ad1..9b51148e8ba5 100644 --- a/drivers/gpu/drm/i915/display/intel_display_core.h +++ b/drivers/gpu/drm/i915/display/intel_display_core.h @@ -316,6 +316,14 @@ struct intel_display { } dbuf; struct { + /* + * dkl.phy_lock protects against concurrent access of the + * Dekel TypeC PHYs. + */ + spinlock_t phy_lock; + } dkl; + + struct { /* VLV/CHV/BXT/GLK DSI MMIO register base address */ u32 mmio_base; } dsi; diff --git a/drivers/gpu/drm/i915/display/intel_display_power_well.c b/drivers/gpu/drm/i915/display/intel_display_power_well.c index df7ee4969ef1..1d18eee56253 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power_well.c +++ b/drivers/gpu/drm/i915/display/intel_display_power_well.c @@ -12,6 +12,7 @@ #include "intel_de.h" #include "intel_display_power_well.h" #include "intel_display_types.h" +#include "intel_dkl_phy.h" #include "intel_dmc.h" #include "intel_dpio_phy.h" #include "intel_dpll.h" @@ -529,11 +530,9 @@ icl_tc_phy_aux_power_well_enable(struct drm_i915_private *dev_priv, enum tc_port tc_port; tc_port = TGL_AUX_PW_TO_TC_PORT(i915_power_well_instance(power_well)->hsw.idx); - intel_de_write(dev_priv, HIP_INDEX_REG(tc_port), - HIP_INDEX_VAL(tc_port, 0x2)); - if (intel_de_wait_for_set(dev_priv, DKL_CMN_UC_DW_27(tc_port), - DKL_CMN_UC_DW27_UC_HEALTH, 1)) + if (wait_for(intel_dkl_phy_read(dev_priv, DKL_CMN_UC_DW_27(tc_port), 2) & + DKL_CMN_UC_DW27_UC_HEALTH, 1)) drm_warn(&dev_priv->drm, "Timeout waiting TC uC health\n"); } diff --git a/drivers/gpu/drm/i915/display/intel_dkl_phy.c b/drivers/gpu/drm/i915/display/intel_dkl_phy.c new file mode 100644 index 000000000000..710b030c7ed5 --- /dev/null +++ b/drivers/gpu/drm/i915/display/intel_dkl_phy.c @@ -0,0 +1,109 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2022 Intel Corporation + */ + +#include "i915_drv.h" +#include "i915_reg.h" + +#include "intel_de.h" +#include "intel_display.h" +#include "intel_dkl_phy.h" + +static void +dkl_phy_set_hip_idx(struct drm_i915_private *i915, i915_reg_t reg, int idx) +{ + enum tc_port tc_port = DKL_REG_TC_PORT(reg); + + drm_WARN_ON(&i915->drm, tc_port < TC_PORT_1 || tc_port >= I915_MAX_TC_PORTS); + + intel_de_write(i915, + HIP_INDEX_REG(tc_port), + HIP_INDEX_VAL(tc_port, idx)); +} + +/** + * intel_dkl_phy_read - read a Dekel PHY register + * @i915: i915 device instance + * @reg: Dekel PHY register + * @ln: lane instance of @reg + * + * Read the @reg Dekel PHY register. + * + * Returns the read value. + */ +u32 +intel_dkl_phy_read(struct drm_i915_private *i915, i915_reg_t reg, int ln) +{ + u32 val; + + spin_lock(&i915->display.dkl.phy_lock); + + dkl_phy_set_hip_idx(i915, reg, ln); + val = intel_de_read(i915, reg); + + spin_unlock(&i915->display.dkl.phy_lock); + + return val; +} + +/** + * intel_dkl_phy_write - write a Dekel PHY register + * @i915: i915 device instance + * @reg: Dekel PHY register + * @ln: lane instance of @reg + * @val: value to write + * + * Write @val to the @reg Dekel PHY register. + */ +void +intel_dkl_phy_write(struct drm_i915_private *i915, i915_reg_t reg, int ln, u32 val) +{ + spin_lock(&i915->display.dkl.phy_lock); + + dkl_phy_set_hip_idx(i915, reg, ln); + intel_de_write(i915, reg, val); + + spin_unlock(&i915->display.dkl.phy_lock); +} + +/** + * intel_dkl_phy_rmw - read-modify-write a Dekel PHY register + * @i915: i915 device instance + * @reg: Dekel PHY register + * @ln: lane instance of @reg + * @clear: mask to clear + * @set: mask to set + * + * Read the @reg Dekel PHY register, clearing then setting the @clear/@set bits in it, and writing + * this value back to the register if the value differs from the read one. + */ +void +intel_dkl_phy_rmw(struct drm_i915_private *i915, i915_reg_t reg, int ln, u32 clear, u32 set) +{ + spin_lock(&i915->display.dkl.phy_lock); + + dkl_phy_set_hip_idx(i915, reg, ln); + intel_de_rmw(i915, reg, clear, set); + + spin_unlock(&i915->display.dkl.phy_lock); +} + +/** + * intel_dkl_phy_posting_read - do a posting read from a Dekel PHY register + * @i915: i915 device instance + * @reg: Dekel PHY register + * @ln: lane instance of @reg + * + * Read the @reg Dekel PHY register without returning the read value. + */ +void +intel_dkl_phy_posting_read(struct drm_i915_private *i915, i915_reg_t reg, int ln) +{ + spin_lock(&i915->display.dkl.phy_lock); + + dkl_phy_set_hip_idx(i915, reg, ln); + intel_de_posting_read(i915, reg); + + spin_unlock(&i915->display.dkl.phy_lock); +} diff --git a/drivers/gpu/drm/i915/display/intel_dkl_phy.h b/drivers/gpu/drm/i915/display/intel_dkl_phy.h new file mode 100644 index 000000000000..260ad121a0b1 --- /dev/null +++ b/drivers/gpu/drm/i915/display/intel_dkl_phy.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2022 Intel Corporation + */ + +#ifndef __INTEL_DKL_PHY_H__ +#define __INTEL_DKL_PHY_H__ + +#include <linux/types.h> + +#include "i915_reg_defs.h" + +struct drm_i915_private; + +u32 +intel_dkl_phy_read(struct drm_i915_private *i915, i915_reg_t reg, int ln); +void +intel_dkl_phy_write(struct drm_i915_private *i915, i915_reg_t reg, int ln, u32 val); +void +intel_dkl_phy_rmw(struct drm_i915_private *i915, i915_reg_t reg, int ln, u32 clear, u32 set); +void +intel_dkl_phy_posting_read(struct drm_i915_private *i915, i915_reg_t reg, int ln); + +#endif /* __INTEL_DKL_PHY_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index 47419d162f30..2b5bc95a8b0d 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -5276,7 +5276,7 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp, encoder->devdata, IS_ERR(edid) ? NULL : edid); intel_panel_add_edid_fixed_modes(intel_connector, - intel_connector->panel.vbt.drrs_type != DRRS_TYPE_NONE, + intel_connector->panel.vbt.drrs_type != DRRS_TYPE_NONE || intel_vrr_is_capable(intel_connector)); /* MSO requires information from the EDID */ diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c index e5fb66a5dd02..64dd603dc69a 100644 --- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c +++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c @@ -25,6 +25,7 @@ #include "intel_de.h" #include "intel_display_types.h" +#include "intel_dkl_phy.h" #include "intel_dpio_phy.h" #include "intel_dpll.h" #include "intel_dpll_mgr.h" @@ -3508,15 +3509,12 @@ static bool dkl_pll_get_hw_state(struct drm_i915_private *dev_priv, * All registers read here have the same HIP_INDEX_REG even though * they are on different building blocks */ - intel_de_write(dev_priv, HIP_INDEX_REG(tc_port), - HIP_INDEX_VAL(tc_port, 0x2)); - - hw_state->mg_refclkin_ctl = intel_de_read(dev_priv, - DKL_REFCLKIN_CTL(tc_port)); + hw_state->mg_refclkin_ctl = intel_dkl_phy_read(dev_priv, + DKL_REFCLKIN_CTL(tc_port), 2); hw_state->mg_refclkin_ctl &= MG_REFCLKIN_CTL_OD_2_MUX_MASK; hw_state->mg_clktop2_hsclkctl = - intel_de_read(dev_priv, DKL_CLKTOP2_HSCLKCTL(tc_port)); + intel_dkl_phy_read(dev_priv, DKL_CLKTOP2_HSCLKCTL(tc_port), 2); hw_state->mg_clktop2_hsclkctl &= MG_CLKTOP2_HSCLKCTL_TLINEDRV_CLKSEL_MASK | MG_CLKTOP2_HSCLKCTL_CORE_INPUTSEL_MASK | @@ -3524,32 +3522,32 @@ static bool dkl_pll_get_hw_state(struct drm_i915_private *dev_priv, MG_CLKTOP2_HSCLKCTL_DSDIV_RATIO_MASK; hw_state->mg_clktop2_coreclkctl1 = - intel_de_read(dev_priv, DKL_CLKTOP2_CORECLKCTL1(tc_port)); + intel_dkl_phy_read(dev_priv, DKL_CLKTOP2_CORECLKCTL1(tc_port), 2); hw_state->mg_clktop2_coreclkctl1 &= MG_CLKTOP2_CORECLKCTL1_A_DIVRATIO_MASK; - hw_state->mg_pll_div0 = intel_de_read(dev_priv, DKL_PLL_DIV0(tc_port)); + hw_state->mg_pll_div0 = intel_dkl_phy_read(dev_priv, DKL_PLL_DIV0(tc_port), 2); val = DKL_PLL_DIV0_MASK; if (dev_priv->display.vbt.override_afc_startup) val |= DKL_PLL_DIV0_AFC_STARTUP_MASK; hw_state->mg_pll_div0 &= val; - hw_state->mg_pll_div1 = intel_de_read(dev_priv, DKL_PLL_DIV1(tc_port)); + hw_state->mg_pll_div1 = intel_dkl_phy_read(dev_priv, DKL_PLL_DIV1(tc_port), 2); hw_state->mg_pll_div1 &= (DKL_PLL_DIV1_IREF_TRIM_MASK | DKL_PLL_DIV1_TDC_TARGET_CNT_MASK); - hw_state->mg_pll_ssc = intel_de_read(dev_priv, DKL_PLL_SSC(tc_port)); + hw_state->mg_pll_ssc = intel_dkl_phy_read(dev_priv, DKL_PLL_SSC(tc_port), 2); hw_state->mg_pll_ssc &= (DKL_PLL_SSC_IREF_NDIV_RATIO_MASK | DKL_PLL_SSC_STEP_LEN_MASK | DKL_PLL_SSC_STEP_NUM_MASK | DKL_PLL_SSC_EN); - hw_state->mg_pll_bias = intel_de_read(dev_priv, DKL_PLL_BIAS(tc_port)); + hw_state->mg_pll_bias = intel_dkl_phy_read(dev_priv, DKL_PLL_BIAS(tc_port), 2); hw_state->mg_pll_bias &= (DKL_PLL_BIAS_FRAC_EN_H | DKL_PLL_BIAS_FBDIV_FRAC_MASK); hw_state->mg_pll_tdc_coldst_bias = - intel_de_read(dev_priv, DKL_PLL_TDC_COLDST_BIAS(tc_port)); + intel_dkl_phy_read(dev_priv, DKL_PLL_TDC_COLDST_BIAS(tc_port), 2); hw_state->mg_pll_tdc_coldst_bias &= (DKL_PLL_TDC_SSC_STEP_SIZE_MASK | DKL_PLL_TDC_FEED_FWD_GAIN_MASK); @@ -3737,61 +3735,58 @@ static void dkl_pll_write(struct drm_i915_private *dev_priv, * All registers programmed here have the same HIP_INDEX_REG even * though on different building block */ - intel_de_write(dev_priv, HIP_INDEX_REG(tc_port), - HIP_INDEX_VAL(tc_port, 0x2)); - /* All the registers are RMW */ - val = intel_de_read(dev_priv, DKL_REFCLKIN_CTL(tc_port)); + val = intel_dkl_phy_read(dev_priv, DKL_REFCLKIN_CTL(tc_port), 2); val &= ~MG_REFCLKIN_CTL_OD_2_MUX_MASK; val |= hw_state->mg_refclkin_ctl; - intel_de_write(dev_priv, DKL_REFCLKIN_CTL(tc_port), val); + intel_dkl_phy_write(dev_priv, DKL_REFCLKIN_CTL(tc_port), 2, val); - val = intel_de_read(dev_priv, DKL_CLKTOP2_CORECLKCTL1(tc_port)); + val = intel_dkl_phy_read(dev_priv, DKL_CLKTOP2_CORECLKCTL1(tc_port), 2); val &= ~MG_CLKTOP2_CORECLKCTL1_A_DIVRATIO_MASK; val |= hw_state->mg_clktop2_coreclkctl1; - intel_de_write(dev_priv, DKL_CLKTOP2_CORECLKCTL1(tc_port), val); + intel_dkl_phy_write(dev_priv, DKL_CLKTOP2_CORECLKCTL1(tc_port), 2, val); - val = intel_de_read(dev_priv, DKL_CLKTOP2_HSCLKCTL(tc_port)); + val = intel_dkl_phy_read(dev_priv, DKL_CLKTOP2_HSCLKCTL(tc_port), 2); val &= ~(MG_CLKTOP2_HSCLKCTL_TLINEDRV_CLKSEL_MASK | MG_CLKTOP2_HSCLKCTL_CORE_INPUTSEL_MASK | MG_CLKTOP2_HSCLKCTL_HSDIV_RATIO_MASK | MG_CLKTOP2_HSCLKCTL_DSDIV_RATIO_MASK); val |= hw_state->mg_clktop2_hsclkctl; - intel_de_write(dev_priv, DKL_CLKTOP2_HSCLKCTL(tc_port), val); + intel_dkl_phy_write(dev_priv, DKL_CLKTOP2_HSCLKCTL(tc_port), 2, val); val = DKL_PLL_DIV0_MASK; if (dev_priv->display.vbt.override_afc_startup) val |= DKL_PLL_DIV0_AFC_STARTUP_MASK; - intel_de_rmw(dev_priv, DKL_PLL_DIV0(tc_port), val, - hw_state->mg_pll_div0); + intel_dkl_phy_rmw(dev_priv, DKL_PLL_DIV0(tc_port), 2, val, + hw_state->mg_pll_div0); - val = intel_de_read(dev_priv, DKL_PLL_DIV1(tc_port)); + val = intel_dkl_phy_read(dev_priv, DKL_PLL_DIV1(tc_port), 2); val &= ~(DKL_PLL_DIV1_IREF_TRIM_MASK | DKL_PLL_DIV1_TDC_TARGET_CNT_MASK); val |= hw_state->mg_pll_div1; - intel_de_write(dev_priv, DKL_PLL_DIV1(tc_port), val); + intel_dkl_phy_write(dev_priv, DKL_PLL_DIV1(tc_port), 2, val); - val = intel_de_read(dev_priv, DKL_PLL_SSC(tc_port)); + val = intel_dkl_phy_read(dev_priv, DKL_PLL_SSC(tc_port), 2); val &= ~(DKL_PLL_SSC_IREF_NDIV_RATIO_MASK | DKL_PLL_SSC_STEP_LEN_MASK | DKL_PLL_SSC_STEP_NUM_MASK | DKL_PLL_SSC_EN); val |= hw_state->mg_pll_ssc; - intel_de_write(dev_priv, DKL_PLL_SSC(tc_port), val); + intel_dkl_phy_write(dev_priv, DKL_PLL_SSC(tc_port), 2, val); - val = intel_de_read(dev_priv, DKL_PLL_BIAS(tc_port)); + val = intel_dkl_phy_read(dev_priv, DKL_PLL_BIAS(tc_port), 2); val &= ~(DKL_PLL_BIAS_FRAC_EN_H | DKL_PLL_BIAS_FBDIV_FRAC_MASK); val |= hw_state->mg_pll_bias; - intel_de_write(dev_priv, DKL_PLL_BIAS(tc_port), val); + intel_dkl_phy_write(dev_priv, DKL_PLL_BIAS(tc_port), 2, val); - val = intel_de_read(dev_priv, DKL_PLL_TDC_COLDST_BIAS(tc_port)); + val = intel_dkl_phy_read(dev_priv, DKL_PLL_TDC_COLDST_BIAS(tc_port), 2); val &= ~(DKL_PLL_TDC_SSC_STEP_SIZE_MASK | DKL_PLL_TDC_FEED_FWD_GAIN_MASK); val |= hw_state->mg_pll_tdc_coldst_bias; - intel_de_write(dev_priv, DKL_PLL_TDC_COLDST_BIAS(tc_port), val); + intel_dkl_phy_write(dev_priv, DKL_PLL_TDC_COLDST_BIAS(tc_port), 2, val); - intel_de_posting_read(dev_priv, DKL_PLL_TDC_COLDST_BIAS(tc_port)); + intel_dkl_phy_posting_read(dev_priv, DKL_PLL_TDC_COLDST_BIAS(tc_port), 2); } static void icl_pll_power_enable(struct drm_i915_private *dev_priv, diff --git a/drivers/gpu/drm/i915/display/intel_lvds.c b/drivers/gpu/drm/i915/display/intel_lvds.c index 9aa38e8141b5..e5352239b2a2 100644 --- a/drivers/gpu/drm/i915/display/intel_lvds.c +++ b/drivers/gpu/drm/i915/display/intel_lvds.c @@ -972,8 +972,7 @@ void intel_lvds_init(struct drm_i915_private *dev_priv) /* Try EDID first */ intel_panel_add_edid_fixed_modes(intel_connector, - intel_connector->panel.vbt.drrs_type != DRRS_TYPE_NONE, - false); + intel_connector->panel.vbt.drrs_type != DRRS_TYPE_NONE); /* Failed to get EDID, what about VBT? */ if (!intel_panel_preferred_fixed_mode(intel_connector)) diff --git a/drivers/gpu/drm/i915/display/intel_panel.c b/drivers/gpu/drm/i915/display/intel_panel.c index a3a3f9fe4342..41cec9dc4223 100644 --- a/drivers/gpu/drm/i915/display/intel_panel.c +++ b/drivers/gpu/drm/i915/display/intel_panel.c @@ -254,10 +254,10 @@ static void intel_panel_destroy_probed_modes(struct intel_connector *connector) } void intel_panel_add_edid_fixed_modes(struct intel_connector *connector, - bool has_drrs, bool has_vrr) + bool use_alt_fixed_modes) { intel_panel_add_edid_preferred_mode(connector); - if (intel_panel_preferred_fixed_mode(connector) && (has_drrs || has_vrr)) + if (intel_panel_preferred_fixed_mode(connector) && use_alt_fixed_modes) intel_panel_add_edid_alt_fixed_modes(connector); intel_panel_destroy_probed_modes(connector); } diff --git a/drivers/gpu/drm/i915/display/intel_panel.h b/drivers/gpu/drm/i915/display/intel_panel.h index eff3ffd3d082..5c5b5b7f95b6 100644 --- a/drivers/gpu/drm/i915/display/intel_panel.h +++ b/drivers/gpu/drm/i915/display/intel_panel.h @@ -44,7 +44,7 @@ int intel_panel_fitting(struct intel_crtc_state *crtc_state, int intel_panel_compute_config(struct intel_connector *connector, struct drm_display_mode *adjusted_mode); void intel_panel_add_edid_fixed_modes(struct intel_connector *connector, - bool has_drrs, bool has_vrr); + bool use_alt_fixed_modes); void intel_panel_add_vbt_lfp_fixed_mode(struct intel_connector *connector); void intel_panel_add_vbt_sdvo_fixed_mode(struct intel_connector *connector); void intel_panel_add_encoder_fixed_mode(struct intel_connector *connector, diff --git a/drivers/gpu/drm/i915/display/intel_sdvo.c b/drivers/gpu/drm/i915/display/intel_sdvo.c index f5b744bef18f..774c1dc31a52 100644 --- a/drivers/gpu/drm/i915/display/intel_sdvo.c +++ b/drivers/gpu/drm/i915/display/intel_sdvo.c @@ -2747,13 +2747,10 @@ intel_sdvo_dvi_init(struct intel_sdvo *intel_sdvo, int device) if (!intel_sdvo_connector) return false; - if (device == 0) { - intel_sdvo->controlled_output |= SDVO_OUTPUT_TMDS0; + if (device == 0) intel_sdvo_connector->output_flag = SDVO_OUTPUT_TMDS0; - } else if (device == 1) { - intel_sdvo->controlled_output |= SDVO_OUTPUT_TMDS1; + else if (device == 1) intel_sdvo_connector->output_flag = SDVO_OUTPUT_TMDS1; - } intel_connector = &intel_sdvo_connector->base; connector = &intel_connector->base; @@ -2808,7 +2805,6 @@ intel_sdvo_tv_init(struct intel_sdvo *intel_sdvo, int type) encoder->encoder_type = DRM_MODE_ENCODER_TVDAC; connector->connector_type = DRM_MODE_CONNECTOR_SVIDEO; - intel_sdvo->controlled_output |= type; intel_sdvo_connector->output_flag = type; if (intel_sdvo_connector_init(intel_sdvo_connector, intel_sdvo) < 0) { @@ -2849,13 +2845,10 @@ intel_sdvo_analog_init(struct intel_sdvo *intel_sdvo, int device) encoder->encoder_type = DRM_MODE_ENCODER_DAC; connector->connector_type = DRM_MODE_CONNECTOR_VGA; - if (device == 0) { - intel_sdvo->controlled_output |= SDVO_OUTPUT_RGB0; + if (device == 0) intel_sdvo_connector->output_flag = SDVO_OUTPUT_RGB0; - } else if (device == 1) { - intel_sdvo->controlled_output |= SDVO_OUTPUT_RGB1; + else if (device == 1) intel_sdvo_connector->output_flag = SDVO_OUTPUT_RGB1; - } if (intel_sdvo_connector_init(intel_sdvo_connector, intel_sdvo) < 0) { kfree(intel_sdvo_connector); @@ -2885,13 +2878,10 @@ intel_sdvo_lvds_init(struct intel_sdvo *intel_sdvo, int device) encoder->encoder_type = DRM_MODE_ENCODER_LVDS; connector->connector_type = DRM_MODE_CONNECTOR_LVDS; - if (device == 0) { - intel_sdvo->controlled_output |= SDVO_OUTPUT_LVDS0; + if (device == 0) intel_sdvo_connector->output_flag = SDVO_OUTPUT_LVDS0; - } else if (device == 1) { - intel_sdvo->controlled_output |= SDVO_OUTPUT_LVDS1; + else if (device == 1) intel_sdvo_connector->output_flag = SDVO_OUTPUT_LVDS1; - } if (intel_sdvo_connector_init(intel_sdvo_connector, intel_sdvo) < 0) { kfree(intel_sdvo_connector); @@ -2910,8 +2900,12 @@ intel_sdvo_lvds_init(struct intel_sdvo *intel_sdvo, int device) intel_panel_add_vbt_sdvo_fixed_mode(intel_connector); if (!intel_panel_preferred_fixed_mode(intel_connector)) { + mutex_lock(&i915->drm.mode_config.mutex); + intel_ddc_get_modes(connector, &intel_sdvo->ddc); - intel_panel_add_edid_fixed_modes(intel_connector, false, false); + intel_panel_add_edid_fixed_modes(intel_connector, false); + + mutex_unlock(&i915->drm.mode_config.mutex); } intel_panel_init(intel_connector); @@ -2926,16 +2920,39 @@ err: return false; } +static u16 intel_sdvo_filter_output_flags(u16 flags) +{ + flags &= SDVO_OUTPUT_MASK; + + /* SDVO requires XXX1 function may not exist unless it has XXX0 function.*/ + if (!(flags & SDVO_OUTPUT_TMDS0)) + flags &= ~SDVO_OUTPUT_TMDS1; + + if (!(flags & SDVO_OUTPUT_RGB0)) + flags &= ~SDVO_OUTPUT_RGB1; + + if (!(flags & SDVO_OUTPUT_LVDS0)) + flags &= ~SDVO_OUTPUT_LVDS1; + + return flags; +} + static bool intel_sdvo_output_setup(struct intel_sdvo *intel_sdvo, u16 flags) { - /* SDVO requires XXX1 function may not exist unless it has XXX0 function.*/ + struct drm_i915_private *i915 = to_i915(intel_sdvo->base.base.dev); + + flags = intel_sdvo_filter_output_flags(flags); + + intel_sdvo->controlled_output = flags; + + intel_sdvo_select_ddc_bus(i915, intel_sdvo); if (flags & SDVO_OUTPUT_TMDS0) if (!intel_sdvo_dvi_init(intel_sdvo, 0)) return false; - if ((flags & SDVO_TMDS_MASK) == SDVO_TMDS_MASK) + if (flags & SDVO_OUTPUT_TMDS1) if (!intel_sdvo_dvi_init(intel_sdvo, 1)) return false; @@ -2956,7 +2973,7 @@ intel_sdvo_output_setup(struct intel_sdvo *intel_sdvo, u16 flags) if (!intel_sdvo_analog_init(intel_sdvo, 0)) return false; - if ((flags & SDVO_RGB_MASK) == SDVO_RGB_MASK) + if (flags & SDVO_OUTPUT_RGB1) if (!intel_sdvo_analog_init(intel_sdvo, 1)) return false; @@ -2964,14 +2981,13 @@ intel_sdvo_output_setup(struct intel_sdvo *intel_sdvo, u16 flags) if (!intel_sdvo_lvds_init(intel_sdvo, 0)) return false; - if ((flags & SDVO_LVDS_MASK) == SDVO_LVDS_MASK) + if (flags & SDVO_OUTPUT_LVDS1) if (!intel_sdvo_lvds_init(intel_sdvo, 1)) return false; - if ((flags & SDVO_OUTPUT_MASK) == 0) { + if (flags == 0) { unsigned char bytes[2]; - intel_sdvo->controlled_output = 0; memcpy(bytes, &intel_sdvo->caps.output_flags, 2); DRM_DEBUG_KMS("%s: Unknown SDVO output type (0x%02x%02x)\n", SDVO_NAME(intel_sdvo), @@ -3383,8 +3399,6 @@ bool intel_sdvo_init(struct drm_i915_private *dev_priv, */ intel_sdvo->base.cloneable = 0; - intel_sdvo_select_ddc_bus(dev_priv, intel_sdvo); - /* Set the input timing to the screen. Assume always input 0. */ if (!intel_sdvo_set_target_input(intel_sdvo)) goto err_output; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_internal.c b/drivers/gpu/drm/i915/gem/i915_gem_internal.c index c698f95af15f..629acb403a2c 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_internal.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_internal.c @@ -6,7 +6,6 @@ #include <linux/scatterlist.h> #include <linux/slab.h> -#include <linux/swiotlb.h> #include "i915_drv.h" #include "i915_gem.h" @@ -38,22 +37,12 @@ static int i915_gem_object_get_pages_internal(struct drm_i915_gem_object *obj) struct scatterlist *sg; unsigned int sg_page_sizes; unsigned int npages; - int max_order; + int max_order = MAX_ORDER; + unsigned int max_segment; gfp_t gfp; - max_order = MAX_ORDER; -#ifdef CONFIG_SWIOTLB - if (is_swiotlb_active(obj->base.dev->dev)) { - unsigned int max_segment; - - max_segment = swiotlb_max_segment(); - if (max_segment) { - max_segment = max_t(unsigned int, max_segment, - PAGE_SIZE) >> PAGE_SHIFT; - max_order = min(max_order, ilog2(max_segment)); - } - } -#endif + max_segment = i915_sg_segment_size(i915->drm.dev) >> PAGE_SHIFT; + max_order = min(max_order, get_order(max_segment)); gfp = GFP_KERNEL | __GFP_HIGHMEM | __GFP_RECLAIMABLE; if (IS_I965GM(i915) || IS_I965G(i915)) { diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c index f42ca1179f37..11125c32dd35 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c @@ -194,7 +194,7 @@ static int shmem_get_pages(struct drm_i915_gem_object *obj) struct intel_memory_region *mem = obj->mm.region; struct address_space *mapping = obj->base.filp->f_mapping; const unsigned long page_count = obj->base.size / PAGE_SIZE; - unsigned int max_segment = i915_sg_segment_size(); + unsigned int max_segment = i915_sg_segment_size(i915->drm.dev); struct sg_table *st; struct sgt_iter sgt_iter; struct page *page; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c index 4f861782c3e8..a4aa9500fa17 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c @@ -189,7 +189,7 @@ static int i915_ttm_tt_shmem_populate(struct ttm_device *bdev, struct drm_i915_private *i915 = container_of(bdev, typeof(*i915), bdev); struct intel_memory_region *mr = i915->mm.regions[INTEL_MEMORY_SYSTEM]; struct i915_ttm_tt *i915_tt = container_of(ttm, typeof(*i915_tt), ttm); - const unsigned int max_segment = i915_sg_segment_size(); + const unsigned int max_segment = i915_sg_segment_size(i915->drm.dev); const size_t size = (size_t)ttm->num_pages << PAGE_SHIFT; struct file *filp = i915_tt->filp; struct sgt_iter sgt_iter; @@ -538,7 +538,7 @@ static struct i915_refct_sgt *i915_ttm_tt_get_st(struct ttm_tt *ttm) ret = sg_alloc_table_from_pages_segment(st, ttm->pages, ttm->num_pages, 0, (unsigned long)ttm->num_pages << PAGE_SHIFT, - i915_sg_segment_size(), GFP_KERNEL); + i915_sg_segment_size(i915_tt->dev), GFP_KERNEL); if (ret) { st->sgl = NULL; return ERR_PTR(ret); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c index d4398948f016..f34e01a7fefb 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c @@ -129,7 +129,7 @@ static void i915_gem_object_userptr_drop_ref(struct drm_i915_gem_object *obj) static int i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj) { const unsigned long num_pages = obj->base.size >> PAGE_SHIFT; - unsigned int max_segment = i915_sg_segment_size(); + unsigned int max_segment = i915_sg_segment_size(obj->base.dev->dev); struct sg_table *st; unsigned int sg_page_sizes; struct page **pvec; diff --git a/drivers/gpu/drm/i915/i915_driver.c b/drivers/gpu/drm/i915/i915_driver.c index c459eb362c47..f2a15d8155f4 100644 --- a/drivers/gpu/drm/i915/i915_driver.c +++ b/drivers/gpu/drm/i915/i915_driver.c @@ -353,6 +353,7 @@ static int i915_driver_early_probe(struct drm_i915_private *dev_priv) mutex_init(&dev_priv->display.wm.wm_mutex); mutex_init(&dev_priv->display.pps.mutex); mutex_init(&dev_priv->display.hdcp.comp_mutex); + spin_lock_init(&dev_priv->display.dkl.phy_lock); i915_memcpy_init_early(dev_priv); intel_runtime_pm_init_early(&dev_priv->runtime_pm); diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 0b287a59dc2f..da35bb2db26b 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -7420,6 +7420,9 @@ enum skl_power_gate { #define _DKL_PHY5_BASE 0x16C000 #define _DKL_PHY6_BASE 0x16D000 +#define DKL_REG_TC_PORT(__reg) \ + (TC_PORT_1 + ((__reg).reg - _DKL_PHY1_BASE) / (_DKL_PHY2_BASE - _DKL_PHY1_BASE)) + /* DEKEL PHY MMIO Address = Phy base + (internal address & ~index_mask) */ #define _DKL_PCS_DW5 0x14 #define DKL_PCS_DW5(tc_port) _MMIO(_PORT(tc_port, _DKL_PHY1_BASE, \ diff --git a/drivers/gpu/drm/i915/i915_scatterlist.h b/drivers/gpu/drm/i915/i915_scatterlist.h index 9ddb3e743a3e..b0a1db44f895 100644 --- a/drivers/gpu/drm/i915/i915_scatterlist.h +++ b/drivers/gpu/drm/i915/i915_scatterlist.h @@ -9,7 +9,8 @@ #include <linux/pfn.h> #include <linux/scatterlist.h> -#include <linux/swiotlb.h> +#include <linux/dma-mapping.h> +#include <xen/xen.h> #include "i915_gem.h" @@ -127,19 +128,26 @@ static inline unsigned int i915_sg_dma_sizes(struct scatterlist *sg) return page_sizes; } -static inline unsigned int i915_sg_segment_size(void) +static inline unsigned int i915_sg_segment_size(struct device *dev) { - unsigned int size = swiotlb_max_segment(); - - if (size == 0) - size = UINT_MAX; - - size = rounddown(size, PAGE_SIZE); - /* swiotlb_max_segment_size can return 1 byte when it means one page. */ - if (size < PAGE_SIZE) - size = PAGE_SIZE; - - return size; + size_t max = min_t(size_t, UINT_MAX, dma_max_mapping_size(dev)); + + /* + * For Xen PV guests pages aren't contiguous in DMA (machine) address + * space. The DMA API takes care of that both in dma_alloc_* (by + * calling into the hypervisor to make the pages contiguous) and in + * dma_map_* (by bounce buffering). But i915 abuses ignores the + * coherency aspects of the DMA API and thus can't cope with bounce + * buffering actually happening, so add a hack here to force small + * allocations and mappings when running in PV mode on Xen. + * + * Note this will still break if bounce buffering is required for other + * reasons, like confidential computing hypervisors or PCIe root ports + * with addressing limitations. + */ + if (xen_pv_domain()) + max = PAGE_SIZE; + return round_down(max, PAGE_SIZE); } bool i915_sg_trim(struct sg_table *orig_st); diff --git a/drivers/gpu/drm/imx/Kconfig b/drivers/gpu/drm/imx/Kconfig index 975de4ff7313..fd5b2471fdf0 100644 --- a/drivers/gpu/drm/imx/Kconfig +++ b/drivers/gpu/drm/imx/Kconfig @@ -4,7 +4,6 @@ config DRM_IMX select DRM_KMS_HELPER select VIDEOMODE_HELPERS select DRM_GEM_DMA_HELPER - select DRM_KMS_HELPER depends on DRM && (ARCH_MXC || ARCH_MULTIPLATFORM || COMPILE_TEST) depends on IMX_IPUV3_CORE help diff --git a/drivers/gpu/drm/imx/imx-tve.c b/drivers/gpu/drm/imx/imx-tve.c index 6b34fac3f73a..ab4d1c878fda 100644 --- a/drivers/gpu/drm/imx/imx-tve.c +++ b/drivers/gpu/drm/imx/imx-tve.c @@ -218,8 +218,9 @@ static int imx_tve_connector_get_modes(struct drm_connector *connector) return ret; } -static int imx_tve_connector_mode_valid(struct drm_connector *connector, - struct drm_display_mode *mode) +static enum drm_mode_status +imx_tve_connector_mode_valid(struct drm_connector *connector, + struct drm_display_mode *mode) { struct imx_tve *tve = con_to_tve(connector); unsigned long rate; diff --git a/drivers/gpu/drm/rockchip/dw-mipi-dsi-rockchip.c b/drivers/gpu/drm/rockchip/dw-mipi-dsi-rockchip.c index bf6948125b84..f4df9820b295 100644 --- a/drivers/gpu/drm/rockchip/dw-mipi-dsi-rockchip.c +++ b/drivers/gpu/drm/rockchip/dw-mipi-dsi-rockchip.c @@ -752,7 +752,7 @@ static void dw_mipi_dsi_rockchip_config(struct dw_mipi_dsi_rockchip *dsi) static void dw_mipi_dsi_rockchip_set_lcdsel(struct dw_mipi_dsi_rockchip *dsi, int mux) { - if (dsi->cdata->lcdsel_grf_reg < 0) + if (dsi->cdata->lcdsel_grf_reg) regmap_write(dsi->grf_regmap, dsi->cdata->lcdsel_grf_reg, mux ? dsi->cdata->lcdsel_lit : dsi->cdata->lcdsel_big); } @@ -1051,23 +1051,31 @@ static int dw_mipi_dsi_rockchip_host_attach(void *priv_data, if (ret) { DRM_DEV_ERROR(dsi->dev, "Failed to register component: %d\n", ret); - return ret; + goto out; } second = dw_mipi_dsi_rockchip_find_second(dsi); - if (IS_ERR(second)) - return PTR_ERR(second); + if (IS_ERR(second)) { + ret = PTR_ERR(second); + goto out; + } if (second) { ret = component_add(second, &dw_mipi_dsi_rockchip_ops); if (ret) { DRM_DEV_ERROR(second, "Failed to register component: %d\n", ret); - return ret; + goto out; } } return 0; + +out: + mutex_lock(&dsi->usage_mutex); + dsi->usage_mode = DW_DSI_USAGE_IDLE; + mutex_unlock(&dsi->usage_mutex); + return ret; } static int dw_mipi_dsi_rockchip_host_detach(void *priv_data, @@ -1635,7 +1643,6 @@ static const struct rockchip_dw_dsi_chip_data rk3399_chip_data[] = { static const struct rockchip_dw_dsi_chip_data rk3568_chip_data[] = { { .reg = 0xfe060000, - .lcdsel_grf_reg = -1, .lanecfg1_grf_reg = RK3568_GRF_VO_CON2, .lanecfg1 = HIWORD_UPDATE(0, RK3568_DSI0_SKEWCALHS | RK3568_DSI0_FORCETXSTOPMODE | @@ -1645,7 +1652,6 @@ static const struct rockchip_dw_dsi_chip_data rk3568_chip_data[] = { }, { .reg = 0xfe070000, - .lcdsel_grf_reg = -1, .lanecfg1_grf_reg = RK3568_GRF_VO_CON3, .lanecfg1 = HIWORD_UPDATE(0, RK3568_DSI1_SKEWCALHS | RK3568_DSI1_FORCETXSTOPMODE | @@ -1681,5 +1687,11 @@ struct platform_driver dw_mipi_dsi_rockchip_driver = { .of_match_table = dw_mipi_dsi_rockchip_dt_ids, .pm = &dw_mipi_dsi_rockchip_pm_ops, .name = "dw-mipi-dsi-rockchip", + /* + * For dual-DSI display, one DSI pokes at the other DSI's + * drvdata in dw_mipi_dsi_rockchip_find_second(). This is not + * safe for asynchronous probe. + */ + .probe_type = PROBE_FORCE_SYNCHRONOUS, }, }; diff --git a/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c b/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c index c14f88893868..2f4b8f64cbad 100644 --- a/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c +++ b/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c @@ -565,7 +565,8 @@ static int dw_hdmi_rockchip_bind(struct device *dev, struct device *master, ret = rockchip_hdmi_parse_dt(hdmi); if (ret) { - DRM_DEV_ERROR(hdmi->dev, "Unable to parse OF data\n"); + if (ret != -EPROBE_DEFER) + DRM_DEV_ERROR(hdmi->dev, "Unable to parse OF data\n"); return ret; } diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c index 614e97aaac80..da8a69953706 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c @@ -364,9 +364,12 @@ rockchip_gem_create_with_handle(struct drm_file *file_priv, { struct rockchip_gem_object *rk_obj; struct drm_gem_object *obj; + bool is_framebuffer; int ret; - rk_obj = rockchip_gem_create_object(drm, size, false); + is_framebuffer = drm->fb_helper && file_priv == drm->fb_helper->client.file; + + rk_obj = rockchip_gem_create_object(drm, size, is_framebuffer); if (IS_ERR(rk_obj)) return ERR_CAST(rk_obj); diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c index aac20be5ac08..105a548d0abe 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c @@ -877,10 +877,14 @@ static void vop2_crtc_atomic_disable(struct drm_crtc *crtc, { struct vop2_video_port *vp = to_vop2_video_port(crtc); struct vop2 *vop2 = vp->vop2; + struct drm_crtc_state *old_crtc_state; int ret; vop2_lock(vop2); + old_crtc_state = drm_atomic_get_old_crtc_state(state, crtc); + drm_atomic_helper_disable_planes_on_crtc(old_crtc_state, false); + drm_crtc_vblank_off(crtc); /* @@ -996,13 +1000,15 @@ static int vop2_plane_atomic_check(struct drm_plane *plane, static void vop2_plane_atomic_disable(struct drm_plane *plane, struct drm_atomic_state *state) { - struct drm_plane_state *old_pstate = drm_atomic_get_old_plane_state(state, plane); + struct drm_plane_state *old_pstate = NULL; struct vop2_win *win = to_vop2_win(plane); struct vop2 *vop2 = win->vop2; drm_dbg(vop2->drm, "%s disable\n", win->data->name); - if (!old_pstate->crtc) + if (state) + old_pstate = drm_atomic_get_old_plane_state(state, plane); + if (old_pstate && !old_pstate->crtc) return; vop2_win_disable(win); diff --git a/drivers/hwmon/pmbus/pmbus.h b/drivers/hwmon/pmbus/pmbus.h index 7daaf0caf4d3..10fb17879f8e 100644 --- a/drivers/hwmon/pmbus/pmbus.h +++ b/drivers/hwmon/pmbus/pmbus.h @@ -467,7 +467,6 @@ extern const struct regulator_ops pmbus_regulator_ops; #define PMBUS_REGULATOR_STEP(_name, _id, _voltages, _step) \ [_id] = { \ .name = (_name # _id), \ - .supply_name = "vin", \ .id = (_id), \ .of_match = of_match_ptr(_name # _id), \ .regulators_node = of_match_ptr("regulators"), \ diff --git a/drivers/hwmon/scmi-hwmon.c b/drivers/hwmon/scmi-hwmon.c index b1329a58ce40..e192f0c67146 100644 --- a/drivers/hwmon/scmi-hwmon.c +++ b/drivers/hwmon/scmi-hwmon.c @@ -20,6 +20,11 @@ struct scmi_sensors { const struct scmi_sensor_info **info[hwmon_max]; }; +struct scmi_thermal_sensor { + const struct scmi_protocol_handle *ph; + const struct scmi_sensor_info *info; +}; + static inline u64 __pow10(u8 x) { u64 r = 1; @@ -64,16 +69,14 @@ static int scmi_hwmon_scale(const struct scmi_sensor_info *sensor, u64 *value) return 0; } -static int scmi_hwmon_read(struct device *dev, enum hwmon_sensor_types type, - u32 attr, int channel, long *val) +static int scmi_hwmon_read_scaled_value(const struct scmi_protocol_handle *ph, + const struct scmi_sensor_info *sensor, + long *val) { int ret; u64 value; - const struct scmi_sensor_info *sensor; - struct scmi_sensors *scmi_sensors = dev_get_drvdata(dev); - sensor = *(scmi_sensors->info[type] + channel); - ret = sensor_ops->reading_get(scmi_sensors->ph, sensor->id, &value); + ret = sensor_ops->reading_get(ph, sensor->id, &value); if (ret) return ret; @@ -84,6 +87,17 @@ static int scmi_hwmon_read(struct device *dev, enum hwmon_sensor_types type, return ret; } +static int scmi_hwmon_read(struct device *dev, enum hwmon_sensor_types type, + u32 attr, int channel, long *val) +{ + const struct scmi_sensor_info *sensor; + struct scmi_sensors *scmi_sensors = dev_get_drvdata(dev); + + sensor = *(scmi_sensors->info[type] + channel); + + return scmi_hwmon_read_scaled_value(scmi_sensors->ph, sensor, val); +} + static int scmi_hwmon_read_string(struct device *dev, enum hwmon_sensor_types type, u32 attr, int channel, const char **str) @@ -122,6 +136,25 @@ static struct hwmon_chip_info scmi_chip_info = { .info = NULL, }; +static int scmi_hwmon_thermal_get_temp(struct thermal_zone_device *tz, + int *temp) +{ + int ret; + long value; + struct scmi_thermal_sensor *th_sensor = tz->devdata; + + ret = scmi_hwmon_read_scaled_value(th_sensor->ph, th_sensor->info, + &value); + if (!ret) + *temp = value; + + return ret; +} + +static const struct thermal_zone_device_ops scmi_hwmon_thermal_ops = { + .get_temp = scmi_hwmon_thermal_get_temp, +}; + static int scmi_hwmon_add_chan_info(struct hwmon_channel_info *scmi_hwmon_chan, struct device *dev, int num, enum hwmon_sensor_types type, u32 config) @@ -149,7 +182,6 @@ static enum hwmon_sensor_types scmi_types[] = { }; static u32 hwmon_attributes[hwmon_max] = { - [hwmon_chip] = HWMON_C_REGISTER_TZ, [hwmon_temp] = HWMON_T_INPUT | HWMON_T_LABEL, [hwmon_in] = HWMON_I_INPUT | HWMON_I_LABEL, [hwmon_curr] = HWMON_C_INPUT | HWMON_C_LABEL, @@ -157,6 +189,43 @@ static u32 hwmon_attributes[hwmon_max] = { [hwmon_energy] = HWMON_E_INPUT | HWMON_E_LABEL, }; +static int scmi_thermal_sensor_register(struct device *dev, + const struct scmi_protocol_handle *ph, + const struct scmi_sensor_info *sensor) +{ + struct scmi_thermal_sensor *th_sensor; + struct thermal_zone_device *tzd; + + th_sensor = devm_kzalloc(dev, sizeof(*th_sensor), GFP_KERNEL); + if (!th_sensor) + return -ENOMEM; + + th_sensor->ph = ph; + th_sensor->info = sensor; + + /* + * Try to register a temperature sensor with the Thermal Framework: + * skip sensors not defined as part of any thermal zone (-ENODEV) but + * report any other errors related to misconfigured zones/sensors. + */ + tzd = devm_thermal_of_zone_register(dev, th_sensor->info->id, th_sensor, + &scmi_hwmon_thermal_ops); + if (IS_ERR(tzd)) { + devm_kfree(dev, th_sensor); + + if (PTR_ERR(tzd) != -ENODEV) + return PTR_ERR(tzd); + + dev_dbg(dev, "Sensor '%s' not attached to any thermal zone.\n", + sensor->name); + } else { + dev_dbg(dev, "Sensor '%s' attached to thermal zone ID:%d\n", + sensor->name, tzd->id); + } + + return 0; +} + static int scmi_hwmon_probe(struct scmi_device *sdev) { int i, idx; @@ -164,7 +233,7 @@ static int scmi_hwmon_probe(struct scmi_device *sdev) enum hwmon_sensor_types type; struct scmi_sensors *scmi_sensors; const struct scmi_sensor_info *sensor; - int nr_count[hwmon_max] = {0}, nr_types = 0; + int nr_count[hwmon_max] = {0}, nr_types = 0, nr_count_temp = 0; const struct hwmon_chip_info *chip_info; struct device *hwdev, *dev = &sdev->dev; struct hwmon_channel_info *scmi_hwmon_chan; @@ -208,10 +277,8 @@ static int scmi_hwmon_probe(struct scmi_device *sdev) } } - if (nr_count[hwmon_temp]) { - nr_count[hwmon_chip]++; - nr_types++; - } + if (nr_count[hwmon_temp]) + nr_count_temp = nr_count[hwmon_temp]; scmi_hwmon_chan = devm_kcalloc(dev, nr_types, sizeof(*scmi_hwmon_chan), GFP_KERNEL); @@ -262,8 +329,31 @@ static int scmi_hwmon_probe(struct scmi_device *sdev) hwdev = devm_hwmon_device_register_with_info(dev, "scmi_sensors", scmi_sensors, chip_info, NULL); + if (IS_ERR(hwdev)) + return PTR_ERR(hwdev); - return PTR_ERR_OR_ZERO(hwdev); + for (i = 0; i < nr_count_temp; i++) { + int ret; + + sensor = *(scmi_sensors->info[hwmon_temp] + i); + if (!sensor) + continue; + + /* + * Warn on any misconfiguration related to thermal zones but + * bail out of probing only on memory errors. + */ + ret = scmi_thermal_sensor_register(dev, ph, sensor); + if (ret) { + if (ret == -ENOMEM) + return ret; + dev_warn(dev, + "Thermal zone misconfigured for %s. err=%d\n", + sensor->name, ret); + } + } + + return 0; } static const struct scmi_device_id scmi_id_table[] = { diff --git a/drivers/hwspinlock/qcom_hwspinlock.c b/drivers/hwspinlock/qcom_hwspinlock.c index 80ea45b3a815..9cf186362ae2 100644 --- a/drivers/hwspinlock/qcom_hwspinlock.c +++ b/drivers/hwspinlock/qcom_hwspinlock.c @@ -22,6 +22,7 @@ struct qcom_hwspinlock_of_data { u32 offset; u32 stride; + const struct regmap_config *regmap_config; }; static int qcom_hwspinlock_trylock(struct hwspinlock *lock) @@ -73,15 +74,42 @@ static const struct qcom_hwspinlock_of_data of_sfpb_mutex = { .stride = 0x4, }; -/* All modern platform has offset 0 and stride of 4k */ +static const struct regmap_config tcsr_msm8226_mutex_config = { + .reg_bits = 32, + .reg_stride = 4, + .val_bits = 32, + .max_register = 0x1000, + .fast_io = true, +}; + +static const struct qcom_hwspinlock_of_data of_msm8226_tcsr_mutex = { + .offset = 0, + .stride = 0x80, + .regmap_config = &tcsr_msm8226_mutex_config, +}; + +static const struct regmap_config tcsr_mutex_config = { + .reg_bits = 32, + .reg_stride = 4, + .val_bits = 32, + .max_register = 0x20000, + .fast_io = true, +}; + static const struct qcom_hwspinlock_of_data of_tcsr_mutex = { .offset = 0, .stride = 0x1000, + .regmap_config = &tcsr_mutex_config, }; static const struct of_device_id qcom_hwspinlock_of_match[] = { { .compatible = "qcom,sfpb-mutex", .data = &of_sfpb_mutex }, { .compatible = "qcom,tcsr-mutex", .data = &of_tcsr_mutex }, + { .compatible = "qcom,apq8084-tcsr-mutex", .data = &of_msm8226_tcsr_mutex }, + { .compatible = "qcom,ipq6018-tcsr-mutex", .data = &of_msm8226_tcsr_mutex }, + { .compatible = "qcom,msm8226-tcsr-mutex", .data = &of_msm8226_tcsr_mutex }, + { .compatible = "qcom,msm8974-tcsr-mutex", .data = &of_msm8226_tcsr_mutex }, + { .compatible = "qcom,msm8994-tcsr-mutex", .data = &of_msm8226_tcsr_mutex }, { } }; MODULE_DEVICE_TABLE(of, qcom_hwspinlock_of_match); @@ -117,14 +145,6 @@ static struct regmap *qcom_hwspinlock_probe_syscon(struct platform_device *pdev, return regmap; } -static const struct regmap_config tcsr_mutex_config = { - .reg_bits = 32, - .reg_stride = 4, - .val_bits = 32, - .max_register = 0x40000, - .fast_io = true, -}; - static struct regmap *qcom_hwspinlock_probe_mmio(struct platform_device *pdev, u32 *offset, u32 *stride) { @@ -133,6 +153,8 @@ static struct regmap *qcom_hwspinlock_probe_mmio(struct platform_device *pdev, void __iomem *base; data = of_device_get_match_data(dev); + if (!data->regmap_config) + return ERR_PTR(-EINVAL); *offset = data->offset; *stride = data->stride; @@ -141,7 +163,7 @@ static struct regmap *qcom_hwspinlock_probe_mmio(struct platform_device *pdev, if (IS_ERR(base)) return ERR_CAST(base); - return devm_regmap_init_mmio(dev, base, &tcsr_mutex_config); + return devm_regmap_init_mmio(dev, base, data->regmap_config); } static int qcom_hwspinlock_probe(struct platform_device *pdev) diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index e06509edc5f3..1fda1eaa6d6a 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -1243,6 +1243,7 @@ static const struct { */ { "Latitude 5480", 0x29 }, { "Vostro V131", 0x1d }, + { "Vostro 5568", 0x29 }, }; static void register_dell_lis3lv02d_i2c_device(struct i801_priv *priv) diff --git a/drivers/i2c/busses/i2c-piix4.c b/drivers/i2c/busses/i2c-piix4.c index 39cb1b7bb865..809fbd014cd6 100644 --- a/drivers/i2c/busses/i2c-piix4.c +++ b/drivers/i2c/busses/i2c-piix4.c @@ -1080,6 +1080,7 @@ static int piix4_probe(struct pci_dev *dev, const struct pci_device_id *id) "", &piix4_main_adapters[0]); if (retval < 0) return retval; + piix4_adapter_count = 1; } /* Check for auxiliary SMBus on some AMD chipsets */ diff --git a/drivers/i2c/busses/i2c-tegra.c b/drivers/i2c/busses/i2c-tegra.c index 954022c04cc4..3869c258a529 100644 --- a/drivers/i2c/busses/i2c-tegra.c +++ b/drivers/i2c/busses/i2c-tegra.c @@ -284,6 +284,7 @@ struct tegra_i2c_dev { struct dma_chan *tx_dma_chan; struct dma_chan *rx_dma_chan; unsigned int dma_buf_size; + struct device *dma_dev; dma_addr_t dma_phys; void *dma_buf; @@ -420,7 +421,7 @@ static int tegra_i2c_dma_submit(struct tegra_i2c_dev *i2c_dev, size_t len) static void tegra_i2c_release_dma(struct tegra_i2c_dev *i2c_dev) { if (i2c_dev->dma_buf) { - dma_free_coherent(i2c_dev->dev, i2c_dev->dma_buf_size, + dma_free_coherent(i2c_dev->dma_dev, i2c_dev->dma_buf_size, i2c_dev->dma_buf, i2c_dev->dma_phys); i2c_dev->dma_buf = NULL; } @@ -472,10 +473,13 @@ static int tegra_i2c_init_dma(struct tegra_i2c_dev *i2c_dev) i2c_dev->tx_dma_chan = chan; + WARN_ON(i2c_dev->tx_dma_chan->device != i2c_dev->rx_dma_chan->device); + i2c_dev->dma_dev = chan->device->dev; + i2c_dev->dma_buf_size = i2c_dev->hw->quirks->max_write_len + I2C_PACKET_HEADER_SIZE; - dma_buf = dma_alloc_coherent(i2c_dev->dev, i2c_dev->dma_buf_size, + dma_buf = dma_alloc_coherent(i2c_dev->dma_dev, i2c_dev->dma_buf_size, &dma_phys, GFP_KERNEL | __GFP_NOWARN); if (!dma_buf) { dev_err(i2c_dev->dev, "failed to allocate DMA buffer\n"); @@ -1272,7 +1276,7 @@ static int tegra_i2c_xfer_msg(struct tegra_i2c_dev *i2c_dev, if (i2c_dev->dma_mode) { if (i2c_dev->msg_read) { - dma_sync_single_for_device(i2c_dev->dev, + dma_sync_single_for_device(i2c_dev->dma_dev, i2c_dev->dma_phys, xfer_size, DMA_FROM_DEVICE); @@ -1280,7 +1284,7 @@ static int tegra_i2c_xfer_msg(struct tegra_i2c_dev *i2c_dev, if (err) return err; } else { - dma_sync_single_for_cpu(i2c_dev->dev, + dma_sync_single_for_cpu(i2c_dev->dma_dev, i2c_dev->dma_phys, xfer_size, DMA_TO_DEVICE); } @@ -1293,7 +1297,7 @@ static int tegra_i2c_xfer_msg(struct tegra_i2c_dev *i2c_dev, memcpy(i2c_dev->dma_buf + I2C_PACKET_HEADER_SIZE, msg->buf, msg->len); - dma_sync_single_for_device(i2c_dev->dev, + dma_sync_single_for_device(i2c_dev->dma_dev, i2c_dev->dma_phys, xfer_size, DMA_TO_DEVICE); @@ -1344,7 +1348,7 @@ static int tegra_i2c_xfer_msg(struct tegra_i2c_dev *i2c_dev, } if (i2c_dev->msg_read && i2c_dev->msg_err == I2C_ERR_NONE) { - dma_sync_single_for_cpu(i2c_dev->dev, + dma_sync_single_for_cpu(i2c_dev->dma_dev, i2c_dev->dma_phys, xfer_size, DMA_FROM_DEVICE); diff --git a/drivers/net/can/at91_can.c b/drivers/net/can/at91_can.c index 3a2d109a3792..199cb200f2bd 100644 --- a/drivers/net/can/at91_can.c +++ b/drivers/net/can/at91_can.c @@ -452,7 +452,7 @@ static netdev_tx_t at91_start_xmit(struct sk_buff *skb, struct net_device *dev) unsigned int mb, prio; u32 reg_mid, reg_mcr; - if (can_dropped_invalid_skb(dev, skb)) + if (can_dev_dropped_skb(dev, skb)) return NETDEV_TX_OK; mb = get_tx_next_mb(priv); diff --git a/drivers/net/can/c_can/c_can_main.c b/drivers/net/can/c_can/c_can_main.c index d6605dbb7737..c63f7fc1e691 100644 --- a/drivers/net/can/c_can/c_can_main.c +++ b/drivers/net/can/c_can/c_can_main.c @@ -457,7 +457,7 @@ static netdev_tx_t c_can_start_xmit(struct sk_buff *skb, struct c_can_tx_ring *tx_ring = &priv->tx; u32 idx, obj, cmd = IF_COMM_TX; - if (can_dropped_invalid_skb(dev, skb)) + if (can_dev_dropped_skb(dev, skb)) return NETDEV_TX_OK; if (c_can_tx_busy(priv, tx_ring)) diff --git a/drivers/net/can/can327.c b/drivers/net/can/can327.c index 0aa1af31d0fe..094197780776 100644 --- a/drivers/net/can/can327.c +++ b/drivers/net/can/can327.c @@ -813,7 +813,7 @@ static netdev_tx_t can327_netdev_start_xmit(struct sk_buff *skb, struct can327 *elm = netdev_priv(dev); struct can_frame *frame = (struct can_frame *)skb->data; - if (can_dropped_invalid_skb(dev, skb)) + if (can_dev_dropped_skb(dev, skb)) return NETDEV_TX_OK; /* We shouldn't get here after a hardware fault: diff --git a/drivers/net/can/cc770/cc770.c b/drivers/net/can/cc770/cc770.c index 0b9dfc76e769..30909f3aab57 100644 --- a/drivers/net/can/cc770/cc770.c +++ b/drivers/net/can/cc770/cc770.c @@ -429,7 +429,7 @@ static netdev_tx_t cc770_start_xmit(struct sk_buff *skb, struct net_device *dev) struct cc770_priv *priv = netdev_priv(dev); unsigned int mo = obj2msgobj(CC770_OBJ_TX); - if (can_dropped_invalid_skb(dev, skb)) + if (can_dev_dropped_skb(dev, skb)) return NETDEV_TX_OK; netif_stop_queue(dev); diff --git a/drivers/net/can/ctucanfd/ctucanfd_base.c b/drivers/net/can/ctucanfd/ctucanfd_base.c index b8da15ea6ad9..64c349fd4600 100644 --- a/drivers/net/can/ctucanfd/ctucanfd_base.c +++ b/drivers/net/can/ctucanfd/ctucanfd_base.c @@ -600,7 +600,7 @@ static netdev_tx_t ctucan_start_xmit(struct sk_buff *skb, struct net_device *nde bool ok; unsigned long flags; - if (can_dropped_invalid_skb(ndev, skb)) + if (can_dev_dropped_skb(ndev, skb)) return NETDEV_TX_OK; if (unlikely(!CTU_CAN_FD_TXTNF(priv))) { diff --git a/drivers/net/can/dev/skb.c b/drivers/net/can/dev/skb.c index 791a51e2f5d6..241ec636e91f 100644 --- a/drivers/net/can/dev/skb.c +++ b/drivers/net/can/dev/skb.c @@ -5,7 +5,6 @@ */ #include <linux/can/dev.h> -#include <linux/can/netlink.h> #include <linux/module.h> #define MOD_DESC "CAN device driver interface" @@ -337,8 +336,6 @@ static bool can_skb_headroom_valid(struct net_device *dev, struct sk_buff *skb) /* Drop a given socketbuffer if it does not contain a valid CAN frame. */ bool can_dropped_invalid_skb(struct net_device *dev, struct sk_buff *skb) { - struct can_priv *priv = netdev_priv(dev); - switch (ntohs(skb->protocol)) { case ETH_P_CAN: if (!can_is_can_skb(skb)) @@ -359,13 +356,8 @@ bool can_dropped_invalid_skb(struct net_device *dev, struct sk_buff *skb) goto inval_skb; } - if (!can_skb_headroom_valid(dev, skb)) { + if (!can_skb_headroom_valid(dev, skb)) goto inval_skb; - } else if (priv->ctrlmode & CAN_CTRLMODE_LISTENONLY) { - netdev_info_once(dev, - "interface in listen only mode, dropping skb\n"); - goto inval_skb; - } return false; diff --git a/drivers/net/can/flexcan/flexcan-core.c b/drivers/net/can/flexcan/flexcan-core.c index 5ee38e586fd8..9bdadd716f4e 100644 --- a/drivers/net/can/flexcan/flexcan-core.c +++ b/drivers/net/can/flexcan/flexcan-core.c @@ -742,7 +742,7 @@ static netdev_tx_t flexcan_start_xmit(struct sk_buff *skb, struct net_device *de u32 ctrl = FLEXCAN_MB_CODE_TX_DATA | ((can_fd_len2dlc(cfd->len)) << 16); int i; - if (can_dropped_invalid_skb(dev, skb)) + if (can_dev_dropped_skb(dev, skb)) return NETDEV_TX_OK; netif_stop_queue(dev); diff --git a/drivers/net/can/grcan.c b/drivers/net/can/grcan.c index 6c37aab93eb3..4bedcc3eea0d 100644 --- a/drivers/net/can/grcan.c +++ b/drivers/net/can/grcan.c @@ -1345,7 +1345,7 @@ static netdev_tx_t grcan_start_xmit(struct sk_buff *skb, unsigned long flags; u32 oneshotmode = priv->can.ctrlmode & CAN_CTRLMODE_ONE_SHOT; - if (can_dropped_invalid_skb(dev, skb)) + if (can_dev_dropped_skb(dev, skb)) return NETDEV_TX_OK; /* Trying to transmit in silent mode will generate error interrupts, but diff --git a/drivers/net/can/ifi_canfd/ifi_canfd.c b/drivers/net/can/ifi_canfd/ifi_canfd.c index 8d42b7e6661f..07eaf724a572 100644 --- a/drivers/net/can/ifi_canfd/ifi_canfd.c +++ b/drivers/net/can/ifi_canfd/ifi_canfd.c @@ -860,7 +860,7 @@ static netdev_tx_t ifi_canfd_start_xmit(struct sk_buff *skb, u32 txst, txid, txdlc; int i; - if (can_dropped_invalid_skb(ndev, skb)) + if (can_dev_dropped_skb(ndev, skb)) return NETDEV_TX_OK; /* Check if the TX buffer is full */ diff --git a/drivers/net/can/janz-ican3.c b/drivers/net/can/janz-ican3.c index 71a2caae0757..0732a5092141 100644 --- a/drivers/net/can/janz-ican3.c +++ b/drivers/net/can/janz-ican3.c @@ -1693,7 +1693,7 @@ static netdev_tx_t ican3_xmit(struct sk_buff *skb, struct net_device *ndev) void __iomem *desc_addr; unsigned long flags; - if (can_dropped_invalid_skb(ndev, skb)) + if (can_dev_dropped_skb(ndev, skb)) return NETDEV_TX_OK; spin_lock_irqsave(&mod->lock, flags); diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c index 4e9680c8eb34..bcad11709bc9 100644 --- a/drivers/net/can/kvaser_pciefd.c +++ b/drivers/net/can/kvaser_pciefd.c @@ -772,7 +772,7 @@ static netdev_tx_t kvaser_pciefd_start_xmit(struct sk_buff *skb, int nwords; u8 count; - if (can_dropped_invalid_skb(netdev, skb)) + if (can_dev_dropped_skb(netdev, skb)) return NETDEV_TX_OK; nwords = kvaser_pciefd_prepare_tx_packet(&packet, can, skb); diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index 59deb185fd6b..944529590ffe 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -1731,7 +1731,7 @@ static netdev_tx_t m_can_start_xmit(struct sk_buff *skb, { struct m_can_classdev *cdev = netdev_priv(dev); - if (can_dropped_invalid_skb(dev, skb)) + if (can_dev_dropped_skb(dev, skb)) return NETDEV_TX_OK; if (cdev->is_peripheral) { diff --git a/drivers/net/can/mscan/mscan.c b/drivers/net/can/mscan/mscan.c index 2119fbb287ef..a6829cdc0e81 100644 --- a/drivers/net/can/mscan/mscan.c +++ b/drivers/net/can/mscan/mscan.c @@ -191,7 +191,7 @@ static netdev_tx_t mscan_start_xmit(struct sk_buff *skb, struct net_device *dev) int i, rtr, buf_id; u32 can_id; - if (can_dropped_invalid_skb(dev, skb)) + if (can_dev_dropped_skb(dev, skb)) return NETDEV_TX_OK; out_8(®s->cantier, 0); diff --git a/drivers/net/can/peak_canfd/peak_canfd.c b/drivers/net/can/peak_canfd/peak_canfd.c index f8420cc1d907..31c9c127e24b 100644 --- a/drivers/net/can/peak_canfd/peak_canfd.c +++ b/drivers/net/can/peak_canfd/peak_canfd.c @@ -651,7 +651,7 @@ static netdev_tx_t peak_canfd_start_xmit(struct sk_buff *skb, int room_left; u8 len; - if (can_dropped_invalid_skb(ndev, skb)) + if (can_dev_dropped_skb(ndev, skb)) return NETDEV_TX_OK; msg_size = ALIGN(sizeof(*msg) + cf->len, 4); diff --git a/drivers/net/can/rcar/rcar_can.c b/drivers/net/can/rcar/rcar_can.c index 6ee968c59ac9..cc43c9c5e38c 100644 --- a/drivers/net/can/rcar/rcar_can.c +++ b/drivers/net/can/rcar/rcar_can.c @@ -590,7 +590,7 @@ static netdev_tx_t rcar_can_start_xmit(struct sk_buff *skb, struct can_frame *cf = (struct can_frame *)skb->data; u32 data, i; - if (can_dropped_invalid_skb(ndev, skb)) + if (can_dev_dropped_skb(ndev, skb)) return NETDEV_TX_OK; if (cf->can_id & CAN_EFF_FLAG) /* Extended frame format */ diff --git a/drivers/net/can/rcar/rcar_canfd.c b/drivers/net/can/rcar/rcar_canfd.c index a0dd6044830b..0a59eab35da7 100644 --- a/drivers/net/can/rcar/rcar_canfd.c +++ b/drivers/net/can/rcar/rcar_canfd.c @@ -81,8 +81,7 @@ enum rcanfd_chip_id { /* RSCFDnCFDGERFL / RSCFDnGERFL */ #define RCANFD_GERFL_EEF0_7 GENMASK(23, 16) -#define RCANFD_GERFL_EEF1 BIT(17) -#define RCANFD_GERFL_EEF0 BIT(16) +#define RCANFD_GERFL_EEF(ch) BIT(16 + (ch)) #define RCANFD_GERFL_CMPOF BIT(3) /* CAN FD only */ #define RCANFD_GERFL_THLES BIT(2) #define RCANFD_GERFL_MES BIT(1) @@ -90,7 +89,7 @@ enum rcanfd_chip_id { #define RCANFD_GERFL_ERR(gpriv, x) \ ((x) & (reg_v3u(gpriv, RCANFD_GERFL_EEF0_7, \ - RCANFD_GERFL_EEF0 | RCANFD_GERFL_EEF1) | \ + RCANFD_GERFL_EEF(0) | RCANFD_GERFL_EEF(1)) | \ RCANFD_GERFL_MES | \ ((gpriv)->fdmode ? RCANFD_GERFL_CMPOF : 0))) @@ -936,12 +935,8 @@ static void rcar_canfd_global_error(struct net_device *ndev) u32 ridx = ch + RCANFD_RFFIFO_IDX; gerfl = rcar_canfd_read(priv->base, RCANFD_GERFL); - if ((gerfl & RCANFD_GERFL_EEF0) && (ch == 0)) { - netdev_dbg(ndev, "Ch0: ECC Error flag\n"); - stats->tx_dropped++; - } - if ((gerfl & RCANFD_GERFL_EEF1) && (ch == 1)) { - netdev_dbg(ndev, "Ch1: ECC Error flag\n"); + if (gerfl & RCANFD_GERFL_EEF(ch)) { + netdev_dbg(ndev, "Ch%u: ECC Error flag\n", ch); stats->tx_dropped++; } if (gerfl & RCANFD_GERFL_MES) { @@ -1481,7 +1476,7 @@ static netdev_tx_t rcar_canfd_start_xmit(struct sk_buff *skb, unsigned long flags; u32 ch = priv->channel; - if (can_dropped_invalid_skb(ndev, skb)) + if (can_dev_dropped_skb(ndev, skb)) return NETDEV_TX_OK; if (cf->can_id & CAN_EFF_FLAG) { diff --git a/drivers/net/can/sja1000/sja1000.c b/drivers/net/can/sja1000/sja1000.c index 1bb1129b0450..aac5956e4a53 100644 --- a/drivers/net/can/sja1000/sja1000.c +++ b/drivers/net/can/sja1000/sja1000.c @@ -291,7 +291,7 @@ static netdev_tx_t sja1000_start_xmit(struct sk_buff *skb, u8 cmd_reg_val = 0x00; int i; - if (can_dropped_invalid_skb(dev, skb)) + if (can_dev_dropped_skb(dev, skb)) return NETDEV_TX_OK; netif_stop_queue(dev); diff --git a/drivers/net/can/slcan/slcan-core.c b/drivers/net/can/slcan/slcan-core.c index 8d13fdf8c28a..fbb34139daa1 100644 --- a/drivers/net/can/slcan/slcan-core.c +++ b/drivers/net/can/slcan/slcan-core.c @@ -594,7 +594,7 @@ static netdev_tx_t slcan_netdev_xmit(struct sk_buff *skb, { struct slcan *sl = netdev_priv(dev); - if (can_dropped_invalid_skb(dev, skb)) + if (can_dev_dropped_skb(dev, skb)) return NETDEV_TX_OK; spin_lock(&sl->lock); diff --git a/drivers/net/can/softing/softing_main.c b/drivers/net/can/softing/softing_main.c index a5ef57f415f7..c72f505d29fe 100644 --- a/drivers/net/can/softing/softing_main.c +++ b/drivers/net/can/softing/softing_main.c @@ -60,7 +60,7 @@ static netdev_tx_t softing_netdev_start_xmit(struct sk_buff *skb, struct can_frame *cf = (struct can_frame *)skb->data; uint8_t buf[DPRAM_TX_SIZE]; - if (can_dropped_invalid_skb(dev, skb)) + if (can_dev_dropped_skb(dev, skb)) return NETDEV_TX_OK; spin_lock(&card->spin); diff --git a/drivers/net/can/spi/hi311x.c b/drivers/net/can/spi/hi311x.c index b87dc420428d..e1b8533a602e 100644 --- a/drivers/net/can/spi/hi311x.c +++ b/drivers/net/can/spi/hi311x.c @@ -373,7 +373,7 @@ static netdev_tx_t hi3110_hard_start_xmit(struct sk_buff *skb, return NETDEV_TX_BUSY; } - if (can_dropped_invalid_skb(net, skb)) + if (can_dev_dropped_skb(net, skb)) return NETDEV_TX_OK; netif_stop_queue(net); diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c index 24883a65ca66..79c4bab5f724 100644 --- a/drivers/net/can/spi/mcp251x.c +++ b/drivers/net/can/spi/mcp251x.c @@ -789,7 +789,7 @@ static netdev_tx_t mcp251x_hard_start_xmit(struct sk_buff *skb, return NETDEV_TX_BUSY; } - if (can_dropped_invalid_skb(net, skb)) + if (can_dev_dropped_skb(net, skb)) return NETDEV_TX_OK; netif_stop_queue(net); diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-tx.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-tx.c index ffb6c36b7d9b..160528d3cc26 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-tx.c +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-tx.c @@ -172,7 +172,7 @@ netdev_tx_t mcp251xfd_start_xmit(struct sk_buff *skb, u8 tx_head; int err; - if (can_dropped_invalid_skb(ndev, skb)) + if (can_dev_dropped_skb(ndev, skb)) return NETDEV_TX_OK; if (mcp251xfd_tx_busy(priv, tx_ring)) diff --git a/drivers/net/can/sun4i_can.c b/drivers/net/can/sun4i_can.c index 525309da1320..2b78f9197681 100644 --- a/drivers/net/can/sun4i_can.c +++ b/drivers/net/can/sun4i_can.c @@ -429,7 +429,7 @@ static netdev_tx_t sun4ican_start_xmit(struct sk_buff *skb, struct net_device *d canid_t id; int i; - if (can_dropped_invalid_skb(dev, skb)) + if (can_dev_dropped_skb(dev, skb)) return NETDEV_TX_OK; netif_stop_queue(dev); diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c index b218fb3c6b76..27700f72eac2 100644 --- a/drivers/net/can/ti_hecc.c +++ b/drivers/net/can/ti_hecc.c @@ -470,7 +470,7 @@ static netdev_tx_t ti_hecc_xmit(struct sk_buff *skb, struct net_device *ndev) u32 mbxno, mbx_mask, data; unsigned long flags; - if (can_dropped_invalid_skb(ndev, skb)) + if (can_dev_dropped_skb(ndev, skb)) return NETDEV_TX_OK; mbxno = get_tx_head_mb(priv); diff --git a/drivers/net/can/usb/ems_usb.c b/drivers/net/can/usb/ems_usb.c index d31191686a54..050c0b49938a 100644 --- a/drivers/net/can/usb/ems_usb.c +++ b/drivers/net/can/usb/ems_usb.c @@ -747,7 +747,7 @@ static netdev_tx_t ems_usb_start_xmit(struct sk_buff *skb, struct net_device *ne size_t size = CPC_HEADER_SIZE + CPC_MSG_HEADER_LEN + sizeof(struct cpc_can_msg); - if (can_dropped_invalid_skb(netdev, skb)) + if (can_dev_dropped_skb(netdev, skb)) return NETDEV_TX_OK; /* create a URB, and a buffer for it, and copy the data to the URB */ diff --git a/drivers/net/can/usb/esd_usb.c b/drivers/net/can/usb/esd_usb.c index 1bcfad11b1e4..81b88e9e5bdc 100644 --- a/drivers/net/can/usb/esd_usb.c +++ b/drivers/net/can/usb/esd_usb.c @@ -725,7 +725,7 @@ static netdev_tx_t esd_usb_start_xmit(struct sk_buff *skb, int ret = NETDEV_TX_OK; size_t size = sizeof(struct esd_usb_msg); - if (can_dropped_invalid_skb(netdev, skb)) + if (can_dev_dropped_skb(netdev, skb)) return NETDEV_TX_OK; /* create a URB, and a buffer for it, and copy the data to the URB */ diff --git a/drivers/net/can/usb/etas_es58x/es58x_core.c b/drivers/net/can/usb/etas_es58x/es58x_core.c index 51294b717040..25f863b4f5f0 100644 --- a/drivers/net/can/usb/etas_es58x/es58x_core.c +++ b/drivers/net/can/usb/etas_es58x/es58x_core.c @@ -1913,7 +1913,7 @@ static netdev_tx_t es58x_start_xmit(struct sk_buff *skb, unsigned int frame_len; int ret; - if (can_dropped_invalid_skb(netdev, skb)) { + if (can_dev_dropped_skb(netdev, skb)) { if (priv->tx_urb) goto xmit_commit; return NETDEV_TX_OK; diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c index ccb1a29835a2..838744d2ce34 100644 --- a/drivers/net/can/usb/gs_usb.c +++ b/drivers/net/can/usb/gs_usb.c @@ -728,7 +728,7 @@ static netdev_tx_t gs_can_start_xmit(struct sk_buff *skb, unsigned int idx; struct gs_tx_context *txc; - if (can_dropped_invalid_skb(netdev, skb)) + if (can_dev_dropped_skb(netdev, skb)) return NETDEV_TX_OK; /* find an empty context to keep track of transmission */ diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c index 989e75351062..3a2bfaad1406 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c @@ -653,7 +653,7 @@ static netdev_tx_t kvaser_usb_start_xmit(struct sk_buff *skb, unsigned int i; unsigned long flags; - if (can_dropped_invalid_skb(netdev, skb)) + if (can_dev_dropped_skb(netdev, skb)) return NETDEV_TX_OK; urb = usb_alloc_urb(0, GFP_ATOMIC); diff --git a/drivers/net/can/usb/mcba_usb.c b/drivers/net/can/usb/mcba_usb.c index 69346c63021f..218b098b261d 100644 --- a/drivers/net/can/usb/mcba_usb.c +++ b/drivers/net/can/usb/mcba_usb.c @@ -311,7 +311,7 @@ static netdev_tx_t mcba_usb_start_xmit(struct sk_buff *skb, .cmd_id = MBCA_CMD_TRANSMIT_MESSAGE_EV }; - if (can_dropped_invalid_skb(netdev, skb)) + if (can_dev_dropped_skb(netdev, skb)) return NETDEV_TX_OK; ctx = mcba_usb_get_free_ctx(priv, cf); diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c index 225697d70a9a..1d996d3320fe 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c @@ -351,7 +351,7 @@ static netdev_tx_t peak_usb_ndo_start_xmit(struct sk_buff *skb, int i, err; size_t size = dev->adapter->tx_buffer_size; - if (can_dropped_invalid_skb(netdev, skb)) + if (can_dev_dropped_skb(netdev, skb)) return NETDEV_TX_OK; for (i = 0; i < PCAN_USB_MAX_TX_URBS; i++) diff --git a/drivers/net/can/usb/ucan.c b/drivers/net/can/usb/ucan.c index a1734f1c0148..ffa38f533c35 100644 --- a/drivers/net/can/usb/ucan.c +++ b/drivers/net/can/usb/ucan.c @@ -1121,7 +1121,7 @@ static netdev_tx_t ucan_start_xmit(struct sk_buff *skb, struct can_frame *cf = (struct can_frame *)skb->data; /* check skb */ - if (can_dropped_invalid_skb(netdev, skb)) + if (can_dev_dropped_skb(netdev, skb)) return NETDEV_TX_OK; /* allocate a context and slow down tx path, if fifo state is low */ diff --git a/drivers/net/can/usb/usb_8dev.c b/drivers/net/can/usb/usb_8dev.c index 64c00abe91cf..8a5596ce4e46 100644 --- a/drivers/net/can/usb/usb_8dev.c +++ b/drivers/net/can/usb/usb_8dev.c @@ -602,7 +602,7 @@ static netdev_tx_t usb_8dev_start_xmit(struct sk_buff *skb, int i, err; size_t size = sizeof(struct usb_8dev_tx_msg); - if (can_dropped_invalid_skb(netdev, skb)) + if (can_dev_dropped_skb(netdev, skb)) return NETDEV_TX_OK; /* create a URB, and a buffer for it, and copy the data to the URB */ diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c index 5d3172795ad0..43c812ea1de0 100644 --- a/drivers/net/can/xilinx_can.c +++ b/drivers/net/can/xilinx_can.c @@ -743,7 +743,7 @@ static netdev_tx_t xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev) struct xcan_priv *priv = netdev_priv(ndev); int ret; - if (can_dropped_invalid_skb(ndev, skb)) + if (can_dev_dropped_skb(ndev, skb)) return NETDEV_TX_OK; if (priv->devtype.flags & XCAN_FLAG_TX_MAILBOXES) diff --git a/drivers/net/dsa/microchip/ksz8863_smi.c b/drivers/net/dsa/microchip/ksz8863_smi.c index ddb40838181e..2f4623f3bd85 100644 --- a/drivers/net/dsa/microchip/ksz8863_smi.c +++ b/drivers/net/dsa/microchip/ksz8863_smi.c @@ -152,11 +152,10 @@ static int ksz8863_smi_probe(struct mdio_device *mdiodev) ®map_smi[i], dev, &rc); if (IS_ERR(dev->regmap[i])) { - ret = PTR_ERR(dev->regmap[i]); - dev_err(&mdiodev->dev, - "Failed to initialize regmap%i: %d\n", - ksz8863_regmap_config[i].val_bits, ret); - return ret; + return dev_err_probe(&mdiodev->dev, + PTR_ERR(dev->regmap[i]), + "Failed to initialize regmap%i\n", + ksz8863_regmap_config[i].val_bits); } } diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c index a6a0321a8931..0d6b40968657 100644 --- a/drivers/net/dsa/microchip/ksz9477.c +++ b/drivers/net/dsa/microchip/ksz9477.c @@ -195,7 +195,8 @@ int ksz9477_reset_switch(struct ksz_device *dev) /* KSZ9893 compatible chips do not support refclk configuration */ if (dev->chip_id == KSZ9893_CHIP_ID || - dev->chip_id == KSZ8563_CHIP_ID) + dev->chip_id == KSZ8563_CHIP_ID || + dev->chip_id == KSZ9563_CHIP_ID) return 0; data8 = SW_ENABLE_REFCLKO; diff --git a/drivers/net/dsa/microchip/ksz9477_i2c.c b/drivers/net/dsa/microchip/ksz9477_i2c.c index 3763930dc6fc..db4aec0a51dc 100644 --- a/drivers/net/dsa/microchip/ksz9477_i2c.c +++ b/drivers/net/dsa/microchip/ksz9477_i2c.c @@ -30,17 +30,17 @@ static int ksz9477_i2c_probe(struct i2c_client *i2c, rc.lock_arg = &dev->regmap_mutex; dev->regmap[i] = devm_regmap_init_i2c(i2c, &rc); if (IS_ERR(dev->regmap[i])) { - ret = PTR_ERR(dev->regmap[i]); - dev_err(&i2c->dev, - "Failed to initialize regmap%i: %d\n", - ksz9477_regmap_config[i].val_bits, ret); - return ret; + return dev_err_probe(&i2c->dev, PTR_ERR(dev->regmap[i]), + "Failed to initialize regmap%i\n", + ksz9477_regmap_config[i].val_bits); } } if (i2c->dev.platform_data) dev->pdata = i2c->dev.platform_data; + dev->irq = i2c->irq; + ret = ksz_switch_register(dev); /* Main DSA driver may not be started yet. */ @@ -101,7 +101,7 @@ static const struct of_device_id ksz9477_dt_ids[] = { }, { .compatible = "microchip,ksz9563", - .data = &ksz_switch_chips[KSZ9893] + .data = &ksz_switch_chips[KSZ9563] }, { .compatible = "microchip,ksz8563", diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index d612181b3226..8c8db315317d 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -1039,6 +1039,7 @@ const struct ksz_chip_data ksz_switch_chips[] = { .num_statics = 16, .cpu_ports = 0x07, /* can be configured as cpu port */ .port_cnt = 3, /* total port count */ + .port_nirqs = 3, .ops = &ksz9477_dev_ops, .mib_names = ksz9477_mib_names, .mib_cnt = ARRAY_SIZE(ksz9477_mib_names), @@ -1282,6 +1283,31 @@ const struct ksz_chip_data ksz_switch_chips[] = { .gbit_capable = {true, true, true}, }, + [KSZ9563] = { + .chip_id = KSZ9563_CHIP_ID, + .dev_name = "KSZ9563", + .num_vlans = 4096, + .num_alus = 4096, + .num_statics = 16, + .cpu_ports = 0x07, /* can be configured as cpu port */ + .port_cnt = 3, /* total port count */ + .port_nirqs = 3, + .ops = &ksz9477_dev_ops, + .mib_names = ksz9477_mib_names, + .mib_cnt = ARRAY_SIZE(ksz9477_mib_names), + .reg_mib_cnt = MIB_COUNTER_NUM, + .regs = ksz9477_regs, + .masks = ksz9477_masks, + .shifts = ksz9477_shifts, + .xmii_ctrl0 = ksz9477_xmii_ctrl0, + .xmii_ctrl1 = ksz8795_xmii_ctrl1, /* Same as ksz8795 */ + .supports_mii = {false, false, true}, + .supports_rmii = {false, false, true}, + .supports_rgmii = {false, false, true}, + .internal_phy = {true, true, false}, + .gbit_capable = {true, true, true}, + }, + [KSZ9567] = { .chip_id = KSZ9567_CHIP_ID, .dev_name = "KSZ9567", @@ -2389,7 +2415,8 @@ static enum dsa_tag_protocol ksz_get_tag_protocol(struct dsa_switch *ds, if (dev->chip_id == KSZ8830_CHIP_ID || dev->chip_id == KSZ8563_CHIP_ID || - dev->chip_id == KSZ9893_CHIP_ID) + dev->chip_id == KSZ9893_CHIP_ID || + dev->chip_id == KSZ9563_CHIP_ID) proto = DSA_TAG_PROTO_KSZ9893; if (dev->chip_id == KSZ9477_CHIP_ID || @@ -2509,7 +2536,8 @@ static void ksz_set_xmii(struct ksz_device *dev, int port, data8 |= bitval[P_RGMII_SEL]; /* On KSZ9893, disable RGMII in-band status support */ if (dev->chip_id == KSZ9893_CHIP_ID || - dev->chip_id == KSZ8563_CHIP_ID) + dev->chip_id == KSZ8563_CHIP_ID || + dev->chip_id == KSZ9563_CHIP_ID) data8 &= ~P_MII_MAC_MODE; break; default: @@ -2782,6 +2810,8 @@ static int ksz_switch_detect(struct ksz_device *dev) if (id4 == SKU_ID_KSZ8563) dev->chip_id = KSZ8563_CHIP_ID; + else if (id4 == SKU_ID_KSZ9563) + dev->chip_id = KSZ9563_CHIP_ID; else dev->chip_id = KSZ9893_CHIP_ID; diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h index 9cfa179575ce..c6726cbd5465 100644 --- a/drivers/net/dsa/microchip/ksz_common.h +++ b/drivers/net/dsa/microchip/ksz_common.h @@ -154,6 +154,7 @@ enum ksz_model { KSZ9896, KSZ9897, KSZ9893, + KSZ9563, KSZ9567, LAN9370, LAN9371, @@ -172,6 +173,7 @@ enum ksz_chip_id { KSZ9896_CHIP_ID = 0x00989600, KSZ9897_CHIP_ID = 0x00989700, KSZ9893_CHIP_ID = 0x00989300, + KSZ9563_CHIP_ID = 0x00956300, KSZ9567_CHIP_ID = 0x00956700, LAN9370_CHIP_ID = 0x00937000, LAN9371_CHIP_ID = 0x00937100, @@ -551,6 +553,7 @@ static inline int is_lan937x(struct ksz_device *dev) /* KSZ9893, KSZ9563, KSZ8563 specific register */ #define REG_CHIP_ID4 0x0f #define SKU_ID_KSZ8563 0x3c +#define SKU_ID_KSZ9563 0x1c /* Driver set switch broadcast storm protection at 10% rate. */ #define BROADCAST_STORM_PROT_RATE 10 diff --git a/drivers/net/dsa/microchip/ksz_spi.c b/drivers/net/dsa/microchip/ksz_spi.c index 1b6ab891b986..96c52e8fb51b 100644 --- a/drivers/net/dsa/microchip/ksz_spi.c +++ b/drivers/net/dsa/microchip/ksz_spi.c @@ -71,11 +71,9 @@ static int ksz_spi_probe(struct spi_device *spi) dev->regmap[i] = devm_regmap_init_spi(spi, &rc); if (IS_ERR(dev->regmap[i])) { - ret = PTR_ERR(dev->regmap[i]); - dev_err(&spi->dev, - "Failed to initialize regmap%i: %d\n", - regmap_config[i].val_bits, ret); - return ret; + return dev_err_probe(&spi->dev, PTR_ERR(dev->regmap[i]), + "Failed to initialize regmap%i\n", + regmap_config[i].val_bits); } } @@ -163,7 +161,7 @@ static const struct of_device_id ksz_dt_ids[] = { }, { .compatible = "microchip,ksz9563", - .data = &ksz_switch_chips[KSZ9893] + .data = &ksz_switch_chips[KSZ9563] }, { .compatible = "microchip,ksz8563", diff --git a/drivers/net/dsa/microchip/lan937x_main.c b/drivers/net/dsa/microchip/lan937x_main.c index 7e4f307a0387..06d3d0308cba 100644 --- a/drivers/net/dsa/microchip/lan937x_main.c +++ b/drivers/net/dsa/microchip/lan937x_main.c @@ -242,7 +242,11 @@ int lan937x_change_mtu(struct ksz_device *dev, int port, int new_mtu) } /* Write the frame size in PORT_MAX_FR_SIZE register */ - ksz_pwrite16(dev, port, PORT_MAX_FR_SIZE, new_mtu); + ret = ksz_pwrite16(dev, port, PORT_MAX_FR_SIZE, new_mtu); + if (ret) { + dev_err(ds->dev, "failed to update mtu for port %d\n", port); + return ret; + } return 0; } diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c index 7633b227b2ca..28b5cae60eb5 100644 --- a/drivers/net/ethernet/altera/altera_tse_main.c +++ b/drivers/net/ethernet/altera/altera_tse_main.c @@ -1095,7 +1095,6 @@ static struct phylink_pcs *alt_tse_select_pcs(struct phylink_config *config, } static const struct phylink_mac_ops alt_tse_phylink_ops = { - .validate = phylink_generic_validate, .mac_an_restart = alt_tse_mac_an_restart, .mac_config = alt_tse_mac_config, .mac_link_down = alt_tse_mac_link_down, diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c index d6cfea65a714..390671640388 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c @@ -1004,8 +1004,10 @@ static int xgene_enet_open(struct net_device *ndev) xgene_enet_napi_enable(pdata); ret = xgene_enet_register_irq(ndev); - if (ret) + if (ret) { + xgene_enet_napi_disable(pdata); return ret; + } if (ndev->phydev) { phy_start(ndev->phydev); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_macsec.c b/drivers/net/ethernet/aquantia/atlantic/aq_macsec.c index a0180811305d..7eb5851eb95d 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_macsec.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_macsec.c @@ -570,6 +570,7 @@ static int aq_update_txsa(struct aq_nic_s *nic, const unsigned int sc_idx, ret = aq_mss_set_egress_sakey_record(hw, &key_rec, sa_idx); + memzero_explicit(&key_rec, sizeof(key_rec)); return ret; } @@ -899,6 +900,7 @@ static int aq_update_rxsa(struct aq_nic_s *nic, const unsigned int sc_idx, ret = aq_mss_set_ingress_sakey_record(hw, &sa_key_record, sa_idx); + memzero_explicit(&sa_key_record, sizeof(sa_key_record)); return ret; } diff --git a/drivers/net/ethernet/aquantia/atlantic/macsec/macsec_api.c b/drivers/net/ethernet/aquantia/atlantic/macsec/macsec_api.c index 36c7cf05630a..431924959520 100644 --- a/drivers/net/ethernet/aquantia/atlantic/macsec/macsec_api.c +++ b/drivers/net/ethernet/aquantia/atlantic/macsec/macsec_api.c @@ -757,6 +757,7 @@ set_ingress_sakey_record(struct aq_hw_s *hw, u16 table_index) { u16 packed_record[18]; + int ret; if (table_index >= NUMROWS_INGRESSSAKEYRECORD) return -EINVAL; @@ -789,9 +790,12 @@ set_ingress_sakey_record(struct aq_hw_s *hw, packed_record[16] = rec->key_len & 0x3; - return set_raw_ingress_record(hw, packed_record, 18, 2, - ROWOFFSET_INGRESSSAKEYRECORD + - table_index); + ret = set_raw_ingress_record(hw, packed_record, 18, 2, + ROWOFFSET_INGRESSSAKEYRECORD + + table_index); + + memzero_explicit(packed_record, sizeof(packed_record)); + return ret; } int aq_mss_set_ingress_sakey_record(struct aq_hw_s *hw, @@ -1739,14 +1743,14 @@ static int set_egress_sakey_record(struct aq_hw_s *hw, ret = set_raw_egress_record(hw, packed_record, 8, 2, ROWOFFSET_EGRESSSAKEYRECORD + table_index); if (unlikely(ret)) - return ret; + goto clear_key; ret = set_raw_egress_record(hw, packed_record + 8, 8, 2, ROWOFFSET_EGRESSSAKEYRECORD + table_index - 32); - if (unlikely(ret)) - return ret; - return 0; +clear_key: + memzero_explicit(packed_record, sizeof(packed_record)); + return ret; } int aq_mss_set_egress_sakey_record(struct aq_hw_s *hw, diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c index cc932b3cf873..a5de1bd8538c 100644 --- a/drivers/net/ethernet/atheros/ag71xx.c +++ b/drivers/net/ethernet/atheros/ag71xx.c @@ -1086,7 +1086,6 @@ static void ag71xx_mac_link_up(struct phylink_config *config, } static const struct phylink_mac_ops ag71xx_phylink_mac_ops = { - .validate = phylink_generic_validate, .mac_config = ag71xx_mac_config, .mac_link_down = ag71xx_mac_link_down, .mac_link_up = ag71xx_mac_link_up, diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig index f4e1ca68d831..55dfdb34e37b 100644 --- a/drivers/net/ethernet/broadcom/Kconfig +++ b/drivers/net/ethernet/broadcom/Kconfig @@ -77,7 +77,7 @@ config BCMGENET select BCM7XXX_PHY select MDIO_BCM_UNIMAC select DIMLIB - select BROADCOM_PHY if ARCH_BCM2835 + select BROADCOM_PHY if (ARCH_BCM2835 && PTP_1588_CLOCK_OPTIONAL) help This driver supports the built-in Ethernet MACs found in the Broadcom BCM7xxx Set Top Box family chipset. diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 51b1690fd045..5d1e4fe335aa 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -13671,19 +13671,20 @@ static int bnx2x_send_update_drift_ramrod(struct bnx2x *bp, int drift_dir, return bnx2x_func_state_change(bp, &func_params); } -static int bnx2x_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb) +static int bnx2x_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) { struct bnx2x *bp = container_of(ptp, struct bnx2x, ptp_clock_info); int rc; int drift_dir = 1; int val, period, period1, period2, dif, dif1, dif2; int best_dif = BNX2X_MAX_PHC_DRIFT, best_period = 0, best_val = 0; + s32 ppb = scaled_ppm_to_ppb(scaled_ppm); - DP(BNX2X_MSG_PTP, "PTP adjfreq called, ppb = %d\n", ppb); + DP(BNX2X_MSG_PTP, "PTP adjfine called, ppb = %d\n", ppb); if (!netif_running(bp->dev)) { DP(BNX2X_MSG_PTP, - "PTP adjfreq called while the interface is down\n"); + "PTP adjfine called while the interface is down\n"); return -ENETDOWN; } @@ -13818,7 +13819,7 @@ void bnx2x_register_phc(struct bnx2x *bp) bp->ptp_clock_info.n_ext_ts = 0; bp->ptp_clock_info.n_per_out = 0; bp->ptp_clock_info.pps = 0; - bp->ptp_clock_info.adjfreq = bnx2x_ptp_adjfreq; + bp->ptp_clock_info.adjfine = bnx2x_ptp_adjfine; bp->ptp_clock_info.adjtime = bnx2x_ptp_adjtime; bp->ptp_clock_info.gettime64 = bnx2x_ptp_gettime; bp->ptp_clock_info.settime64 = bnx2x_ptp_settime; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 04cf7684f1b0..743504a27b71 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -5250,7 +5250,7 @@ int bnxt_get_nr_rss_ctxs(struct bnxt *bp, int rx_rings) return 1; } -static void __bnxt_fill_hw_rss_tbl(struct bnxt *bp, struct bnxt_vnic_info *vnic) +static void bnxt_fill_hw_rss_tbl(struct bnxt *bp, struct bnxt_vnic_info *vnic) { bool no_rss = !(vnic->flags & BNXT_VNIC_RSS_FLAG); u16 i, j; @@ -5263,8 +5263,8 @@ static void __bnxt_fill_hw_rss_tbl(struct bnxt *bp, struct bnxt_vnic_info *vnic) } } -static void __bnxt_fill_hw_rss_tbl_p5(struct bnxt *bp, - struct bnxt_vnic_info *vnic) +static void bnxt_fill_hw_rss_tbl_p5(struct bnxt *bp, + struct bnxt_vnic_info *vnic) { __le16 *ring_tbl = vnic->rss_table; struct bnxt_rx_ring_info *rxr; @@ -5285,12 +5285,27 @@ static void __bnxt_fill_hw_rss_tbl_p5(struct bnxt *bp, } } -static void bnxt_fill_hw_rss_tbl(struct bnxt *bp, struct bnxt_vnic_info *vnic) +static void +__bnxt_hwrm_vnic_set_rss(struct bnxt *bp, struct hwrm_vnic_rss_cfg_input *req, + struct bnxt_vnic_info *vnic) { if (bp->flags & BNXT_FLAG_CHIP_P5) - __bnxt_fill_hw_rss_tbl_p5(bp, vnic); + bnxt_fill_hw_rss_tbl_p5(bp, vnic); else - __bnxt_fill_hw_rss_tbl(bp, vnic); + bnxt_fill_hw_rss_tbl(bp, vnic); + + if (bp->rss_hash_delta) { + req->hash_type = cpu_to_le32(bp->rss_hash_delta); + if (bp->rss_hash_cfg & bp->rss_hash_delta) + req->flags |= VNIC_RSS_CFG_REQ_FLAGS_HASH_TYPE_INCLUDE; + else + req->flags |= VNIC_RSS_CFG_REQ_FLAGS_HASH_TYPE_EXCLUDE; + } else { + req->hash_type = cpu_to_le32(bp->rss_hash_cfg); + } + req->hash_mode_flags = VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_DEFAULT; + req->ring_grp_tbl_addr = cpu_to_le64(vnic->rss_table_dma_addr); + req->hash_key_tbl_addr = cpu_to_le64(vnic->rss_hash_key_dma_addr); } static int bnxt_hwrm_vnic_set_rss(struct bnxt *bp, u16 vnic_id, bool set_rss) @@ -5307,14 +5322,8 @@ static int bnxt_hwrm_vnic_set_rss(struct bnxt *bp, u16 vnic_id, bool set_rss) if (rc) return rc; - if (set_rss) { - bnxt_fill_hw_rss_tbl(bp, vnic); - req->hash_type = cpu_to_le32(bp->rss_hash_cfg); - req->hash_mode_flags = VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_DEFAULT; - req->ring_grp_tbl_addr = cpu_to_le64(vnic->rss_table_dma_addr); - req->hash_key_tbl_addr = - cpu_to_le64(vnic->rss_hash_key_dma_addr); - } + if (set_rss) + __bnxt_hwrm_vnic_set_rss(bp, req, vnic); req->rss_ctx_idx = cpu_to_le16(vnic->fw_rss_cos_lb_ctx[0]); return hwrm_req_send(bp, req); } @@ -5335,10 +5344,7 @@ static int bnxt_hwrm_vnic_set_rss_p5(struct bnxt *bp, u16 vnic_id, bool set_rss) if (!set_rss) return hwrm_req_send(bp, req); - bnxt_fill_hw_rss_tbl(bp, vnic); - req->hash_type = cpu_to_le32(bp->rss_hash_cfg); - req->hash_mode_flags = VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_DEFAULT; - req->hash_key_tbl_addr = cpu_to_le64(vnic->rss_hash_key_dma_addr); + __bnxt_hwrm_vnic_set_rss(bp, req, vnic); ring_tbl_map = vnic->rss_table_dma_addr; nr_ctxs = bnxt_get_nr_rss_ctxs(bp, bp->rx_nr_rings); @@ -5357,6 +5363,25 @@ exit: return rc; } +static void bnxt_hwrm_update_rss_hash_cfg(struct bnxt *bp) +{ + struct bnxt_vnic_info *vnic = &bp->vnic_info[0]; + struct hwrm_vnic_rss_qcfg_output *resp; + struct hwrm_vnic_rss_qcfg_input *req; + + if (hwrm_req_init(bp, req, HWRM_VNIC_RSS_QCFG)) + return; + + /* all contexts configured to same hash_type, zero always exists */ + req->rss_ctx_idx = cpu_to_le16(vnic->fw_rss_cos_lb_ctx[0]); + resp = hwrm_req_hold(bp, req); + if (!hwrm_req_send(bp, req)) { + bp->rss_hash_cfg = le32_to_cpu(resp->hash_type) ?: bp->rss_hash_cfg; + bp->rss_hash_delta = 0; + } + hwrm_req_drop(bp, req); +} + static int bnxt_hwrm_vnic_set_hds(struct bnxt *bp, u16 vnic_id) { struct bnxt_vnic_info *vnic = &bp->vnic_info[vnic_id]; @@ -5614,6 +5639,8 @@ static int bnxt_hwrm_vnic_qcaps(struct bnxt *bp) (BNXT_CHIP_P5_THOR(bp) && !(bp->fw_cap & BNXT_FW_CAP_EXT_HW_STATS_SUPPORTED))) bp->fw_cap |= BNXT_FW_CAP_VLAN_RX_STRIP; + if (flags & VNIC_QCAPS_RESP_FLAGS_RSS_HASH_TYPE_DELTA_CAP) + bp->fw_cap |= BNXT_FW_CAP_RSS_HASH_TYPE_DELTA; bp->max_tpa_v2 = le16_to_cpu(resp->max_aggs_supported); if (bp->max_tpa_v2) { if (BNXT_CHIP_P5_THOR(bp)) @@ -6958,8 +6985,11 @@ static int bnxt_hwrm_func_qcfg(struct bnxt *bp) if (flags & FUNC_QCFG_RESP_FLAGS_FW_DCBX_AGENT_ENABLED) bp->fw_cap |= BNXT_FW_CAP_DCBX_AGENT; } - if (BNXT_PF(bp) && (flags & FUNC_QCFG_RESP_FLAGS_MULTI_HOST)) + if (BNXT_PF(bp) && (flags & FUNC_QCFG_RESP_FLAGS_MULTI_HOST)) { bp->flags |= BNXT_FLAG_MULTI_HOST; + if (bp->fw_cap & BNXT_FW_CAP_PTP_RTC) + bp->fw_cap &= ~BNXT_FW_CAP_PTP_RTC; + } if (flags & FUNC_QCFG_RESP_FLAGS_RING_MONITOR_ENABLED) bp->fw_cap |= BNXT_FW_CAP_RING_MONITOR; @@ -8808,6 +8838,8 @@ static int bnxt_init_chip(struct bnxt *bp, bool irq_re_init) rc = bnxt_setup_vnic(bp, 0); if (rc) goto err_out; + if (bp->fw_cap & BNXT_FW_CAP_RSS_HASH_TYPE_DELTA) + bnxt_hwrm_update_rss_hash_cfg(bp); if (bp->flags & BNXT_FLAG_RFS) { rc = bnxt_alloc_rfs_vnics(bp); @@ -9983,17 +10015,12 @@ static int bnxt_try_recover_fw(struct bnxt *bp) return -ENODEV; } -int bnxt_cancel_reservations(struct bnxt *bp, bool fw_reset) +static void bnxt_clear_reservations(struct bnxt *bp, bool fw_reset) { struct bnxt_hw_resc *hw_resc = &bp->hw_resc; - int rc; if (!BNXT_NEW_RM(bp)) - return 0; /* no resource reservations required */ - - rc = bnxt_hwrm_func_resc_qcaps(bp, true); - if (rc) - netdev_err(bp->dev, "resc_qcaps failed\n"); + return; /* no resource reservations required */ hw_resc->resv_cp_rings = 0; hw_resc->resv_stat_ctxs = 0; @@ -10006,6 +10033,20 @@ int bnxt_cancel_reservations(struct bnxt *bp, bool fw_reset) bp->tx_nr_rings = 0; bp->rx_nr_rings = 0; } +} + +int bnxt_cancel_reservations(struct bnxt *bp, bool fw_reset) +{ + int rc; + + if (!BNXT_NEW_RM(bp)) + return 0; /* no resource reservations required */ + + rc = bnxt_hwrm_func_resc_qcaps(bp, true); + if (rc) + netdev_err(bp->dev, "resc_qcaps failed\n"); + + bnxt_clear_reservations(bp, fw_reset); return rc; } @@ -12243,6 +12284,8 @@ static void bnxt_set_dflt_rss_hash_type(struct bnxt *bp) VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV4 | VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6 | VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV6; + if (bp->fw_cap & BNXT_FW_CAP_RSS_HASH_TYPE_DELTA) + bp->rss_hash_delta = bp->rss_hash_cfg; if (BNXT_CHIP_P4_PLUS(bp) && bp->hwrm_spec_code >= 0x10501) { bp->flags |= BNXT_FLAG_UDP_RSS_CAP; bp->rss_hash_cfg |= VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV4 | @@ -12894,8 +12937,8 @@ static int bnxt_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb, rcu_read_lock(); hlist_for_each_entry_rcu(fltr, head, hash) { if (bnxt_fltr_match(fltr, new_fltr)) { + rc = fltr->sw_id; rcu_read_unlock(); - rc = 0; goto err_free; } } @@ -13073,13 +13116,6 @@ int bnxt_get_port_parent_id(struct net_device *dev, return 0; } -static struct devlink_port *bnxt_get_devlink_port(struct net_device *dev) -{ - struct bnxt *bp = netdev_priv(dev); - - return &bp->dl_port; -} - static const struct net_device_ops bnxt_netdev_ops = { .ndo_open = bnxt_open, .ndo_start_xmit = bnxt_start_xmit, @@ -13111,7 +13147,6 @@ static const struct net_device_ops bnxt_netdev_ops = { .ndo_xdp_xmit = bnxt_xdp_xmit, .ndo_bridge_getlink = bnxt_bridge_getlink, .ndo_bridge_setlink = bnxt_bridge_setlink, - .ndo_get_devlink_port = bnxt_get_devlink_port, }; static void bnxt_remove_one(struct pci_dev *pdev) @@ -13122,9 +13157,6 @@ static void bnxt_remove_one(struct pci_dev *pdev) if (BNXT_PF(bp)) bnxt_sriov_disable(bp); - if (BNXT_PF(bp)) - devlink_port_type_clear(&bp->dl_port); - bnxt_ptp_clear(bp); pci_disable_pcie_error_reporting(pdev); unregister_netdev(dev); @@ -13537,6 +13569,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) return -ENOMEM; bp = netdev_priv(dev); + SET_NETDEV_DEVLINK_PORT(dev, &bp->dl_port); bp->board_idx = ent->driver_data; bp->msg_enable = BNXT_DEF_MSG_ENABLE; bnxt_set_max_func_irqs(bp, max_irqs); @@ -13712,8 +13745,6 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (rc) goto init_err_cleanup; - if (BNXT_PF(bp)) - devlink_port_type_eth_set(&bp->dl_port, bp->dev); bnxt_dl_fw_reporters_create(bp); bnxt_print_device_info(bp); @@ -13913,7 +13944,9 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev) pci_ers_result_t result = PCI_ERS_RESULT_DISCONNECT; struct net_device *netdev = pci_get_drvdata(pdev); struct bnxt *bp = netdev_priv(netdev); - int err = 0, off; + int retry = 0; + int err = 0; + int off; netdev_info(bp->dev, "PCI Slot Reset\n"); @@ -13941,11 +13974,36 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev) pci_restore_state(pdev); pci_save_state(pdev); + bnxt_inv_fw_health_reg(bp); + bnxt_try_map_fw_health_reg(bp); + + /* In some PCIe AER scenarios, firmware may take up to + * 10 seconds to become ready in the worst case. + */ + do { + err = bnxt_try_recover_fw(bp); + if (!err) + break; + retry++; + } while (retry < BNXT_FW_SLOT_RESET_RETRY); + + if (err) { + dev_err(&pdev->dev, "Firmware not ready\n"); + goto reset_exit; + } + err = bnxt_hwrm_func_reset(bp); if (!err) result = PCI_ERS_RESULT_RECOVERED; + + bnxt_ulp_irq_stop(bp); + bnxt_clear_int_mode(bp); + err = bnxt_init_int_mode(bp); + bnxt_ulp_irq_restart(bp, err); } +reset_exit: + bnxt_clear_reservations(bp, true); rtnl_unlock(); return result; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 91a1ba0a914d..41c6dd0ae447 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -1621,6 +1621,7 @@ struct bnxt_fw_health { #define BNXT_FW_RETRY 5 #define BNXT_FW_IF_RETRY 10 +#define BNXT_FW_SLOT_RESET_RETRY 4 enum board_idx { BCM57301, @@ -1900,6 +1901,7 @@ struct bnxt { u16 *rss_indir_tbl; u16 rss_indir_tbl_entries; u32 rss_hash_cfg; + u32 rss_hash_delta; u16 max_mtu; u8 max_tc; @@ -1965,6 +1967,7 @@ struct bnxt { #define BNXT_FW_CAP_CFA_RFS_RING_TBL_IDX_V2 0x00010000 #define BNXT_FW_CAP_PCIE_STATS_SUPPORTED 0x00020000 #define BNXT_FW_CAP_EXT_STATS_SUPPORTED 0x00040000 + #define BNXT_FW_CAP_RSS_HASH_TYPE_DELTA 0x00080000 #define BNXT_FW_CAP_ERR_RECOVER_RELOAD 0x00100000 #define BNXT_FW_CAP_HOT_RESET 0x00200000 #define BNXT_FW_CAP_PTP_RTC 0x00400000 diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index cc89e5eabcb9..c2f663770a7f 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -162,7 +162,7 @@ static int bnxt_set_coalesce(struct net_device *dev, } reset_coalesce: - if (netif_running(dev)) { + if (test_bit(BNXT_STATE_OPEN, &bp->state)) { if (update_stats) { rc = bnxt_close_nic(bp, true, false); if (!rc) @@ -1234,6 +1234,8 @@ static int bnxt_srxfh(struct bnxt *bp, struct ethtool_rxnfc *cmd) if (bp->rss_hash_cfg == rss_hash_cfg) return 0; + if (bp->fw_cap & BNXT_FW_CAP_RSS_HASH_TYPE_DELTA) + bp->rss_hash_delta = bp->rss_hash_cfg ^ rss_hash_cfg; bp->rss_hash_cfg = rss_hash_cfg; if (netif_running(bp->dev)) { bnxt_close_nic(bp, false, false); @@ -4112,6 +4114,20 @@ static void bnxt_get_rmon_stats(struct net_device *dev, *ranges = bnxt_rmon_ranges; } +static void bnxt_get_link_ext_stats(struct net_device *dev, + struct ethtool_link_ext_stats *stats) +{ + struct bnxt *bp = netdev_priv(dev); + u64 *rx; + + if (BNXT_VF(bp) || !(bp->flags & BNXT_FLAG_PORT_STATS_EXT)) + return; + + rx = bp->rx_port_stats_ext.sw_stats; + stats->link_down_events = + *(rx + BNXT_RX_STATS_EXT_OFFSET(link_down_events)); +} + void bnxt_ethtool_free(struct bnxt *bp) { kfree(bp->test_info); @@ -4161,6 +4177,7 @@ const struct ethtool_ops bnxt_ethtool_ops = { .get_eeprom = bnxt_get_eeprom, .set_eeprom = bnxt_set_eeprom, .get_link = bnxt_get_link, + .get_link_ext_stats = bnxt_get_link_ext_stats, .get_eee = bnxt_get_eee, .set_eee = bnxt_set_eee, .get_module_info = bnxt_get_module_info, diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h index 184dd8d11cd3..2686a714a59f 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h @@ -6768,6 +6768,53 @@ struct hwrm_vnic_rss_cfg_cmd_err { u8 unused_0[7]; }; +/* hwrm_vnic_rss_qcfg_input (size:192b/24B) */ +struct hwrm_vnic_rss_qcfg_input { + __le16 req_type; + __le16 cmpl_ring; + __le16 seq_id; + __le16 target_id; + __le64 resp_addr; + __le16 rss_ctx_idx; + __le16 vnic_id; + u8 unused_0[4]; +}; + +/* hwrm_vnic_rss_qcfg_output (size:512b/64B) */ +struct hwrm_vnic_rss_qcfg_output { + __le16 error_code; + __le16 req_type; + __le16 seq_id; + __le16 resp_len; + __le32 hash_type; + #define VNIC_RSS_QCFG_RESP_HASH_TYPE_IPV4 0x1UL + #define VNIC_RSS_QCFG_RESP_HASH_TYPE_TCP_IPV4 0x2UL + #define VNIC_RSS_QCFG_RESP_HASH_TYPE_UDP_IPV4 0x4UL + #define VNIC_RSS_QCFG_RESP_HASH_TYPE_IPV6 0x8UL + #define VNIC_RSS_QCFG_RESP_HASH_TYPE_TCP_IPV6 0x10UL + #define VNIC_RSS_QCFG_RESP_HASH_TYPE_UDP_IPV6 0x20UL + #define VNIC_RSS_QCFG_RESP_HASH_TYPE_IPV6_FLOW_LABEL 0x40UL + #define VNIC_RSS_QCFG_RESP_HASH_TYPE_AH_SPI_IPV4 0x80UL + #define VNIC_RSS_QCFG_RESP_HASH_TYPE_ESP_SPI_IPV4 0x100UL + #define VNIC_RSS_QCFG_RESP_HASH_TYPE_AH_SPI_IPV6 0x200UL + #define VNIC_RSS_QCFG_RESP_HASH_TYPE_ESP_SPI_IPV6 0x400UL + u8 unused_0[4]; + __le32 hash_key[10]; + u8 hash_mode_flags; + #define VNIC_RSS_QCFG_RESP_HASH_MODE_FLAGS_DEFAULT 0x1UL + #define VNIC_RSS_QCFG_RESP_HASH_MODE_FLAGS_INNERMOST_4 0x2UL + #define VNIC_RSS_QCFG_RESP_HASH_MODE_FLAGS_INNERMOST_2 0x4UL + #define VNIC_RSS_QCFG_RESP_HASH_MODE_FLAGS_OUTERMOST_4 0x8UL + #define VNIC_RSS_QCFG_RESP_HASH_MODE_FLAGS_OUTERMOST_2 0x10UL + u8 ring_select_mode; + #define VNIC_RSS_QCFG_RESP_RING_SELECT_MODE_TOEPLITZ 0x0UL + #define VNIC_RSS_QCFG_RESP_RING_SELECT_MODE_XOR 0x1UL + #define VNIC_RSS_QCFG_RESP_RING_SELECT_MODE_TOEPLITZ_CHECKSUM 0x2UL + #define VNIC_RSS_QCFG_RESP_RING_SELECT_MODE_LAST VNIC_RSS_QCFG_RESP_RING_SELECT_MODE_TOEPLITZ_CHECKSUM + u8 unused_1[5]; + u8 valid; +}; + /* hwrm_vnic_plcmodes_cfg_input (size:320b/40B) */ struct hwrm_vnic_plcmodes_cfg_input { __le16 req_type; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c index b01d42928a53..132442f16fe6 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c @@ -476,7 +476,8 @@ static int __hwrm_send(struct bnxt *bp, struct bnxt_hwrm_ctx *ctx) memset(ctx->resp, 0, PAGE_SIZE); req_type = le16_to_cpu(ctx->req->req_type); - if (BNXT_NO_FW_ACCESS(bp) && req_type != HWRM_FUNC_RESET) { + if (BNXT_NO_FW_ACCESS(bp) && + (req_type != HWRM_FUNC_RESET && req_type != HWRM_VER_GET)) { netdev_dbg(bp->dev, "hwrm req_type 0x%x skipped, FW channel down\n", req_type); goto exit; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c index 2132ce63193c..4ec8bba18cdd 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c @@ -14,6 +14,7 @@ #include <linux/net_tstamp.h> #include <linux/timekeeping.h> #include <linux/ptp_classify.h> +#include <linux/clocksource.h> #include "bnxt_hsi.h" #include "bnxt.h" #include "bnxt_hwrm.h" @@ -204,24 +205,33 @@ static int bnxt_ptp_adjtime(struct ptp_clock_info *ptp_info, s64 delta) return 0; } -static int bnxt_ptp_adjfreq(struct ptp_clock_info *ptp_info, s32 ppb) +static int bnxt_ptp_adjfine(struct ptp_clock_info *ptp_info, long scaled_ppm) { struct bnxt_ptp_cfg *ptp = container_of(ptp_info, struct bnxt_ptp_cfg, ptp_info); struct hwrm_port_mac_cfg_input *req; struct bnxt *bp = ptp->bp; - int rc; + int rc = 0; - rc = hwrm_req_init(bp, req, HWRM_PORT_MAC_CFG); - if (rc) - return rc; + if (!(ptp->bp->fw_cap & BNXT_FW_CAP_PTP_RTC)) { + spin_lock_bh(&ptp->ptp_lock); + timecounter_read(&ptp->tc); + ptp->cc.mult = adjust_by_scaled_ppm(ptp->cmult, scaled_ppm); + spin_unlock_bh(&ptp->ptp_lock); + } else { + s32 ppb = scaled_ppm_to_ppb(scaled_ppm); - req->ptp_freq_adj_ppb = cpu_to_le32(ppb); - req->enables = cpu_to_le32(PORT_MAC_CFG_REQ_ENABLES_PTP_FREQ_ADJ_PPB); - rc = hwrm_req_send(ptp->bp, req); - if (rc) - netdev_err(ptp->bp->dev, - "ptp adjfreq failed. rc = %d\n", rc); + rc = hwrm_req_init(bp, req, HWRM_PORT_MAC_CFG); + if (rc) + return rc; + + req->ptp_freq_adj_ppb = cpu_to_le32(ppb); + req->enables = cpu_to_le32(PORT_MAC_CFG_REQ_ENABLES_PTP_FREQ_ADJ_PPB); + rc = hwrm_req_send(ptp->bp, req); + if (rc) + netdev_err(ptp->bp->dev, + "ptp adjfine failed. rc = %d\n", rc); + } return rc; } @@ -749,7 +759,7 @@ static const struct ptp_clock_info bnxt_ptp_caps = { .n_per_out = 0, .n_pins = 0, .pps = 0, - .adjfreq = bnxt_ptp_adjfreq, + .adjfine = bnxt_ptp_adjfine, .adjtime = bnxt_ptp_adjtime, .do_aux_work = bnxt_ptp_ts_aux_work, .gettimex64 = bnxt_ptp_gettimex, @@ -846,8 +856,9 @@ static void bnxt_ptp_timecounter_init(struct bnxt *bp, bool init_tc) memset(&ptp->cc, 0, sizeof(ptp->cc)); ptp->cc.read = bnxt_cc_read; ptp->cc.mask = CYCLECOUNTER_MASK(48); - ptp->cc.shift = 0; - ptp->cc.mult = 1; + ptp->cc.shift = BNXT_CYCLES_SHIFT; + ptp->cc.mult = clocksource_khz2mult(BNXT_DEVCLK_FREQ, ptp->cc.shift); + ptp->cmult = ptp->cc.mult; ptp->next_overflow_check = jiffies + BNXT_PHC_OVERFLOW_PERIOD; } if (init_tc) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h index 4ce0a14c1e23..34162e07a119 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h @@ -17,6 +17,8 @@ #define BNXT_PTP_GRC_WIN_BASE 0x6000 #define BNXT_MAX_PHC_DRIFT 31000000 +#define BNXT_CYCLES_SHIFT 23 +#define BNXT_DEVCLK_FREQ 1000000 #define BNXT_LO_TIMER_MASK 0x0000ffffffffUL #define BNXT_HI_TIMER_MASK 0xffff00000000UL @@ -88,8 +90,9 @@ struct bnxt_ptp_cfg { u64 old_time; unsigned long next_period; unsigned long next_overflow_check; - /* 48-bit PHC overflows in 78 hours. Check overflow every 19 hours. */ - #define BNXT_PHC_OVERFLOW_PERIOD (19 * 3600 * HZ) + u32 cmult; + /* a 23b shift cyclecounter will overflow in ~36 mins. Check overflow every 18 mins. */ + #define BNXT_PHC_OVERFLOW_PERIOD (18 * 60 * HZ) u16 tx_seqid; u16 tx_hdr_off; diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 4179a12fc881..59debdc344a5 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -6179,34 +6179,26 @@ static int tg3_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info) return 0; } -static int tg3_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb) +static int tg3_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) { struct tg3 *tp = container_of(ptp, struct tg3, ptp_info); - bool neg_adj = false; - u32 correction = 0; - - if (ppb < 0) { - neg_adj = true; - ppb = -ppb; - } + u64 correction; + bool neg_adj; /* Frequency adjustment is performed using hardware with a 24 bit * accumulator and a programmable correction value. On each clk, the * correction value gets added to the accumulator and when it * overflows, the time counter is incremented/decremented. - * - * So conversion from ppb to correction value is - * ppb * (1 << 24) / 1000000000 */ - correction = div_u64((u64)ppb * (1 << 24), 1000000000ULL) & - TG3_EAV_REF_CLK_CORRECT_MASK; + neg_adj = diff_by_scaled_ppm(1 << 24, scaled_ppm, &correction); tg3_full_lock(tp, 0); if (correction) tw32(TG3_EAV_REF_CLK_CORRECT_CTL, TG3_EAV_REF_CLK_CORRECT_EN | - (neg_adj ? TG3_EAV_REF_CLK_CORRECT_NEG : 0) | correction); + (neg_adj ? TG3_EAV_REF_CLK_CORRECT_NEG : 0) | + ((u32)correction & TG3_EAV_REF_CLK_CORRECT_MASK)); else tw32(TG3_EAV_REF_CLK_CORRECT_CTL, 0); @@ -6330,7 +6322,7 @@ static const struct ptp_clock_info tg3_ptp_caps = { .n_per_out = 1, .n_pins = 0, .pps = 0, - .adjfreq = tg3_ptp_adjfreq, + .adjfine = tg3_ptp_adjfine, .adjtime = tg3_ptp_adjtime, .gettimex64 = tg3_ptp_gettimex, .settime64 = tg3_ptp_settime, diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 4f63f1ba3161..95667b979fab 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -742,7 +742,6 @@ static struct phylink_pcs *macb_mac_select_pcs(struct phylink_config *config, } static const struct phylink_mac_ops macb_phylink_ops = { - .validate = phylink_generic_validate, .mac_select_pcs = macb_mac_select_pcs, .mac_config = macb_mac_config, .mac_link_down = macb_mac_link_down, @@ -2947,6 +2946,18 @@ static int macb_change_mtu(struct net_device *dev, int new_mtu) return 0; } +static int macb_set_mac_addr(struct net_device *dev, void *addr) +{ + int err; + + err = eth_mac_addr(dev, addr); + if (err < 0) + return err; + + macb_set_hwaddr(netdev_priv(dev)); + return 0; +} + static void gem_update_stats(struct macb *bp) { struct macb_queue *queue; @@ -3786,7 +3797,7 @@ static const struct net_device_ops macb_netdev_ops = { .ndo_eth_ioctl = macb_ioctl, .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = macb_change_mtu, - .ndo_set_mac_address = eth_mac_addr, + .ndo_set_mac_address = macb_set_mac_addr, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = macb_poll_controller, #endif @@ -4049,6 +4060,8 @@ static int macb_init(struct platform_device *pdev) dev->ethtool_ops = &macb_ethtool_ops; } + dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; + /* Set features */ dev->hw_features = NETIF_F_SG; diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index d312bd594935..cc88e743d963 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -1512,14 +1512,17 @@ static void free_netsgbuf_with_resp(void *buf) } /** - * liquidio_ptp_adjfreq - Adjust ptp frequency + * liquidio_ptp_adjfine - Adjust ptp frequency * @ptp: PTP clock info - * @ppb: how much to adjust by, in parts-per-billion + * @scaled_ppm: how much to adjust by, in scaled parts-per-million + * + * Scaled parts per million is ppm with a 16-bit binary fractional field. */ -static int liquidio_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb) +static int liquidio_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) { struct lio *lio = container_of(ptp, struct lio, ptp_info); struct octeon_device *oct = (struct octeon_device *)lio->oct_dev; + s32 ppb = scaled_ppm_to_ppb(scaled_ppm); u64 comp, delta; unsigned long flags; bool neg_adj = false; @@ -1643,7 +1646,7 @@ static void oct_ptp_open(struct net_device *netdev) lio->ptp_info.n_ext_ts = 0; lio->ptp_info.n_per_out = 0; lio->ptp_info.pps = 0; - lio->ptp_info.adjfreq = liquidio_ptp_adjfreq; + lio->ptp_info.adjfine = liquidio_ptp_adjfine; lio->ptp_info.adjtime = liquidio_ptp_adjtime; lio->ptp_info.gettime64 = liquidio_ptp_gettime; lio->ptp_info.settime64 = liquidio_ptp_settime; diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c index a52e6b6e2876..9b84c8d8d309 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c +++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c @@ -1301,6 +1301,7 @@ static int cxgb_up(struct adapter *adap) if (ret < 0) { CH_ERR(adap, "failed to bind qsets, err %d\n", ret); t3_intr_disable(adap); + quiesce_rx(adap); free_irq_resources(adap); err = ret; goto out; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c index 5bf117d2179f..cbd06d9b95d4 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c @@ -194,17 +194,20 @@ int cxgb4_ptp_redirect_rx_packet(struct adapter *adapter, struct port_info *pi) } /** - * cxgb4_ptp_adjfreq - Adjust frequency of PHC cycle counter + * cxgb4_ptp_adjfine - Adjust frequency of PHC cycle counter * @ptp: ptp clock structure - * @ppb: Desired frequency change in parts per billion + * @scaled_ppm: Desired frequency in scaled parts per billion * - * Adjust the frequency of the PHC cycle counter by the indicated ppb from + * Adjust the frequency of the PHC cycle counter by the indicated amount from * the base frequency. + * + * Scaled parts per million is ppm with a 16-bit binary fractional field. */ -static int cxgb4_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb) +static int cxgb4_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) { struct adapter *adapter = (struct adapter *)container_of(ptp, struct adapter, ptp_clock_info); + s32 ppb = scaled_ppm_to_ppb(scaled_ppm); struct fw_ptp_cmd c; int err; @@ -404,7 +407,7 @@ static const struct ptp_clock_info cxgb4_ptp_clock_info = { .n_ext_ts = 0, .n_per_out = 0, .pps = 0, - .adjfreq = cxgb4_ptp_adjfreq, + .adjfine = cxgb4_ptp_adjfine, .adjtime = cxgb4_ptp_adjtime, .gettime64 = cxgb4_ptp_gettime, .settime64 = cxgb4_ptp_settime, diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c index 54db79f4dcfe..63b2bd084130 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c @@ -858,7 +858,7 @@ static int cxgb4vf_open(struct net_device *dev) */ err = t4vf_update_port_info(pi); if (err < 0) - return err; + goto err_unwind; /* * Note that this interface is up and start everything up ... diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-devlink.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-devlink.c index 7fefe1574b6a..5c6dd3029e2f 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-devlink.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-devlink.c @@ -226,25 +226,16 @@ int dpaa2_eth_dl_port_add(struct dpaa2_eth_priv *priv) { struct devlink_port *devlink_port = &priv->devlink_port; struct devlink_port_attrs attrs = {}; - int err; attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; devlink_port_attrs_set(devlink_port, &attrs); - - err = devlink_port_register(priv->devlink, devlink_port, 0); - if (err) - return err; - - devlink_port_type_eth_set(devlink_port, priv->net_dev); - - return 0; + return devlink_port_register(priv->devlink, devlink_port, 0); } void dpaa2_eth_dl_port_del(struct dpaa2_eth_priv *priv) { struct devlink_port *devlink_port = &priv->devlink_port; - devlink_port_type_clear(devlink_port); devlink_port_unregister(devlink_port); } diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index 892a1403c469..273f1d77c012 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -4791,6 +4791,7 @@ static int dpaa2_eth_probe(struct fsl_mc_device *dpni_dev) priv = netdev_priv(net_dev); priv->net_dev = net_dev; + SET_NETDEV_DEVLINK_PORT(net_dev, &priv->devlink_port); priv->iommu_domain = iommu_get_domain_for_dev(dev); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c index 2bbab28f763d..51c9da8e1be2 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c @@ -236,7 +236,6 @@ static void dpaa2_mac_link_down(struct phylink_config *config, } static const struct phylink_mac_ops dpaa2_mac_phylink_ops = { - .validate = phylink_generic_validate, .mac_select_pcs = dpaa2_mac_select_pcs, .mac_config = dpaa2_mac_config, .mac_link_up = dpaa2_mac_link_up, diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c index bdf94335ee99..9f6c4f5c0a6c 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c @@ -1111,7 +1111,6 @@ static void enetc_pl_mac_link_down(struct phylink_config *config, } static const struct phylink_mac_ops enetc_mac_phylink_ops = { - .validate = phylink_generic_validate, .mac_select_pcs = enetc_pl_mac_select_pcs, .mac_config = enetc_pl_mac_config, .mac_link_up = enetc_pl_mac_link_up, diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index f7a5584efe22..616eea712ca8 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1581,8 +1581,20 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id) bool need_swap = fep->quirks & FEC_QUIRK_SWAP_FRAME; struct bpf_prog *xdp_prog = READ_ONCE(fep->xdp_prog); u32 ret, xdp_result = FEC_ENET_XDP_PASS; + u32 data_start = FEC_ENET_XDP_HEADROOM; struct xdp_buff xdp; struct page *page; + u32 sub_len = 4; + +#if !defined(CONFIG_M5272) + /*If it has the FEC_QUIRK_HAS_RACC quirk property, the bit of + * FEC_RACC_SHIFT16 is set by default in the probe function. + */ + if (fep->quirks & FEC_QUIRK_HAS_RACC) { + data_start += 2; + sub_len += 2; + } +#endif #ifdef CONFIG_M532x flush_cache_all(); @@ -1645,9 +1657,9 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id) if (xdp_prog) { xdp_buff_clear_frags_flag(&xdp); + /* subtract 16bit shift and FCS */ xdp_prepare_buff(&xdp, page_address(page), - FEC_ENET_XDP_HEADROOM, pkt_len, false); - + data_start, pkt_len - sub_len, false); ret = fec_enet_run_xdp(fep, xdp_prog, &xdp, rxq, index); xdp_result |= ret; if (ret != FEC_ENET_XDP_PASS) @@ -1659,18 +1671,15 @@ fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id) * bridging applications. */ skb = build_skb(page_address(page), PAGE_SIZE); - skb_reserve(skb, FEC_ENET_XDP_HEADROOM); - skb_put(skb, pkt_len - 4); + skb_reserve(skb, data_start); + skb_put(skb, pkt_len - sub_len); skb_mark_for_recycle(skb); - data = skb->data; - if (need_swap) + if (unlikely(need_swap)) { + data = page_address(page) + FEC_ENET_XDP_HEADROOM; swap_buffer(data, pkt_len); - -#if !defined(CONFIG_M5272) - if (fep->quirks & FEC_QUIRK_HAS_RACC) - data = skb_pull_inline(skb, 2); -#endif + } + data = skb->data; /* Extract the enhanced buffer descriptor */ ebdp = NULL; @@ -3604,6 +3613,13 @@ static int fec_enet_bpf(struct net_device *dev, struct netdev_bpf *bpf) switch (bpf->command) { case XDP_SETUP_PROG: + /* No need to support the SoCs that require to + * do the frame swap because the performance wouldn't be + * better than the skb mode. + */ + if (fep->quirks & FEC_QUIRK_SWAP_FRAME) + return -EOPNOTSUPP; + if (is_run) { napi_disable(&fep->napi); netif_tx_disable(dev); @@ -3631,17 +3647,12 @@ static int fec_enet_bpf(struct net_device *dev, struct netdev_bpf *bpf) } static int -fec_enet_xdp_get_tx_queue(struct fec_enet_private *fep, int cpu) +fec_enet_xdp_get_tx_queue(struct fec_enet_private *fep, int index) { - int index = cpu; - if (unlikely(index < 0)) - index = 0; - - while (index >= fep->num_tx_queues) - index -= fep->num_tx_queues; + return 0; - return index; + return (index % fep->num_tx_queues); } static int fec_enet_txq_xmit_frame(struct fec_enet_private *fep, diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c index 67aa694a62ec..ab86bb8562ef 100644 --- a/drivers/net/ethernet/freescale/fec_ptp.c +++ b/drivers/net/ethernet/freescale/fec_ptp.c @@ -338,18 +338,21 @@ void fec_ptp_start_cyclecounter(struct net_device *ndev) } /** - * fec_ptp_adjfreq - adjust ptp cycle frequency + * fec_ptp_adjfine - adjust ptp cycle frequency * @ptp: the ptp clock structure - * @ppb: parts per billion adjustment from base + * @scaled_ppm: scaled parts per million adjustment from base * * Adjust the frequency of the ptp cycle counter by the - * indicated ppb from the base frequency. + * indicated amount from the base frequency. + * + * Scaled parts per million is ppm with a 16-bit binary fractional field. * * Because ENET hardware frequency adjust is complex, * using software method to do that. */ -static int fec_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb) +static int fec_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) { + s32 ppb = scaled_ppm_to_ppb(scaled_ppm); unsigned long flags; int neg_adj = 0; u32 i, tmp; @@ -742,7 +745,7 @@ void fec_ptp_init(struct platform_device *pdev, int irq_idx) fep->ptp_caps.n_per_out = 1; fep->ptp_caps.n_pins = 0; fep->ptp_caps.pps = 1; - fep->ptp_caps.adjfreq = fec_ptp_adjfreq; + fep->ptp_caps.adjfine = fec_ptp_adjfine; fep->ptp_caps.adjtime = fec_ptp_adjtime; fep->ptp_caps.gettime64 = fec_ptp_gettime; fep->ptp_caps.settime64 = fec_ptp_settime; diff --git a/drivers/net/ethernet/freescale/fman/fman_dtsec.c b/drivers/net/ethernet/freescale/fman/fman_dtsec.c index 3c87820ca202..d00bae15a901 100644 --- a/drivers/net/ethernet/freescale/fman/fman_dtsec.c +++ b/drivers/net/ethernet/freescale/fman/fman_dtsec.c @@ -986,7 +986,6 @@ static void dtsec_link_down(struct phylink_config *config, unsigned int mode, } static const struct phylink_mac_ops dtsec_mac_ops = { - .validate = phylink_generic_validate, .mac_select_pcs = dtsec_select_pcs, .mac_config = dtsec_mac_config, .mac_link_up = dtsec_link_up, diff --git a/drivers/net/ethernet/freescale/fman/fman_tgec.c b/drivers/net/ethernet/freescale/fman/fman_tgec.c index c265b7f19a4d..c2261d26db5b 100644 --- a/drivers/net/ethernet/freescale/fman/fman_tgec.c +++ b/drivers/net/ethernet/freescale/fman/fman_tgec.c @@ -469,7 +469,6 @@ static void tgec_link_down(struct phylink_config *config, unsigned int mode, } static const struct phylink_mac_ops tgec_mac_ops = { - .validate = phylink_generic_validate, .mac_config = tgec_mac_config, .mac_link_up = tgec_link_up, .mac_link_down = tgec_link_down, diff --git a/drivers/net/ethernet/freescale/fman/mac.c b/drivers/net/ethernet/freescale/fman/mac.c index c6496a498726..43665806c590 100644 --- a/drivers/net/ethernet/freescale/fman/mac.c +++ b/drivers/net/ethernet/freescale/fman/mac.c @@ -331,12 +331,21 @@ _return_of_node_put: return err; } +static int mac_remove(struct platform_device *pdev) +{ + struct mac_device *mac_dev = platform_get_drvdata(pdev); + + platform_device_unregister(mac_dev->priv->eth_dev); + return 0; +} + static struct platform_driver mac_driver = { .driver = { .name = KBUILD_MODNAME, .of_match_table = mac_match, }, .probe = mac_probe, + .remove = mac_remove, }; builtin_platform_driver(mac_driver); diff --git a/drivers/net/ethernet/fungible/funeth/funeth_main.c b/drivers/net/ethernet/fungible/funeth/funeth_main.c index 095f51c4d9d9..b4cce30e526a 100644 --- a/drivers/net/ethernet/fungible/funeth/funeth_main.c +++ b/drivers/net/ethernet/fungible/funeth/funeth_main.c @@ -1178,13 +1178,6 @@ static int fun_xdp(struct net_device *dev, struct netdev_bpf *xdp) } } -static struct devlink_port *fun_get_devlink_port(struct net_device *netdev) -{ - struct funeth_priv *fp = netdev_priv(netdev); - - return &fp->dl_port; -} - static int fun_init_vports(struct fun_ethdev *ed, unsigned int n) { if (ed->num_vports) @@ -1350,7 +1343,6 @@ static const struct net_device_ops fun_netdev_ops = { .ndo_set_vf_vlan = fun_set_vf_vlan, .ndo_set_vf_rate = fun_set_vf_rate, .ndo_get_vf_config = fun_get_vf_config, - .ndo_get_devlink_port = fun_get_devlink_port, }; #define GSO_ENCAP_FLAGS (NETIF_F_GSO_GRE | NETIF_F_GSO_IPXIP4 | \ @@ -1760,6 +1752,7 @@ static int fun_create_netdev(struct fun_ethdev *ed, unsigned int portid) goto free_rss; SET_NETDEV_DEV(netdev, fdev->dev); + SET_NETDEV_DEVLINK_PORT(netdev, &fp->dl_port); netdev->netdev_ops = &fun_netdev_ops; netdev->hw_features = NETIF_F_SG | NETIF_F_RXHASH | NETIF_F_RXCSUM; @@ -1800,9 +1793,6 @@ static int fun_create_netdev(struct fun_ethdev *ed, unsigned int portid) rc = register_netdev(netdev); if (rc) goto unreg_devlink; - - devlink_port_type_eth_set(&fp->dl_port, netdev); - return 0; unreg_devlink: @@ -1827,7 +1817,6 @@ static void fun_destroy_netdev(struct net_device *netdev) struct funeth_priv *fp; fp = netdev_priv(netdev); - devlink_port_type_clear(&fp->dl_port); unregister_netdev(netdev); devlink_port_unregister(&fp->dl_port); fun_ktls_cleanup(fp); diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c index e2f4494c65fb..1f55137722b0 100644 --- a/drivers/net/ethernet/google/gve/gve_rx.c +++ b/drivers/net/ethernet/google/gve/gve_rx.c @@ -150,8 +150,10 @@ static int gve_prefill_rx_pages(struct gve_rx_ring *rx) for (j = 0; j < rx->qpl_copy_pool_mask + 1; j++) { struct page *page = alloc_page(GFP_KERNEL); - if (!page) + if (!page) { + err = -ENOMEM; goto alloc_err_qpl; + } rx->qpl_copy_pool[j].page = page; rx->qpl_copy_pool[j].page_offset = 0; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 6962a9d69cf8..987271da6e9b 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -12984,14 +12984,16 @@ static void hclge_clean_vport_config(struct hnae3_ae_dev *ae_dev, int num_vfs) static int hclge_get_dscp_prio(struct hnae3_handle *h, u8 dscp, u8 *tc_mode, u8 *priority) { + struct hclge_vport *vport = hclge_get_vport(h); + if (dscp >= HNAE3_MAX_DSCP) return -EINVAL; if (tc_mode) - *tc_mode = h->kinfo.tc_map_mode; + *tc_mode = vport->nic.kinfo.tc_map_mode; if (priority) - *priority = h->kinfo.dscp_prio[dscp] == HNAE3_PRIO_ID_INVALID ? 0 : - h->kinfo.dscp_prio[dscp]; + *priority = vport->nic.kinfo.dscp_prio[dscp] == HNAE3_PRIO_ID_INVALID ? 0 : + vport->nic.kinfo.dscp_prio[dscp]; return 0; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c index a40b1583f114..80a2a0073d97 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c @@ -22,28 +22,16 @@ static int hclge_ptp_get_cycle(struct hclge_dev *hdev) return 0; } -static int hclge_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb) +static int hclge_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) { struct hclge_dev *hdev = hclge_ptp_get_hdev(ptp); struct hclge_ptp_cycle *cycle = &hdev->ptp->cycle; - u64 adj_val, adj_base, diff; + u64 adj_val, adj_base; unsigned long flags; - bool is_neg = false; u32 quo, numerator; - if (ppb < 0) { - ppb = -ppb; - is_neg = true; - } - adj_base = (u64)cycle->quo * (u64)cycle->den + (u64)cycle->numer; - adj_val = adj_base * ppb; - diff = div_u64(adj_val, 1000000000ULL); - - if (is_neg) - adj_val = adj_base - diff; - else - adj_val = adj_base + diff; + adj_val = adjust_by_scaled_ppm(adj_base, scaled_ppm); /* This clock cycle is defined by three part: quotient, numerator * and denominator. For example, 2.5ns, the quotient is 2, @@ -446,7 +434,7 @@ static int hclge_ptp_create_clock(struct hclge_dev *hdev) ptp->info.max_adj = HCLGE_PTP_CYCLE_ADJ_MAX; ptp->info.n_ext_ts = 0; ptp->info.pps = 0; - ptp->info.adjfreq = hclge_ptp_adjfreq; + ptp->info.adjfine = hclge_ptp_adjfine; ptp->info.adjtime = hclge_ptp_adjtime; ptp->info.gettimex64 = hclge_ptp_gettimex; ptp->info.settime64 = hclge_ptp_settime; @@ -504,7 +492,7 @@ int hclge_ptp_init(struct hclge_dev *hdev) goto out; set_bit(HCLGE_PTP_FLAG_EN, &hdev->ptp->flags); - ret = hclge_ptp_adjfreq(&hdev->ptp->info, 0); + ret = hclge_ptp_adjfine(&hdev->ptp->info, 0); if (ret) { dev_err(&hdev->pdev->dev, "failed to init freq, ret = %d\n", ret); diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h index d2d89b0a5ef0..6b5797e69781 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h @@ -46,104 +46,170 @@ enum hinic_port_cmd { HINIC_PORT_CMD_VF_REGISTER = 0x0, HINIC_PORT_CMD_VF_UNREGISTER = 0x1, - HINIC_PORT_CMD_CHANGE_MTU = 2, + HINIC_PORT_CMD_CHANGE_MTU = 0x2, - HINIC_PORT_CMD_ADD_VLAN = 3, - HINIC_PORT_CMD_DEL_VLAN = 4, + HINIC_PORT_CMD_ADD_VLAN = 0x3, + HINIC_PORT_CMD_DEL_VLAN = 0x4, - HINIC_PORT_CMD_SET_PFC = 5, + HINIC_PORT_CMD_SET_ETS = 0x7, + HINIC_PORT_CMD_GET_ETS = 0x8, - HINIC_PORT_CMD_SET_MAC = 9, - HINIC_PORT_CMD_GET_MAC = 10, - HINIC_PORT_CMD_DEL_MAC = 11, + HINIC_PORT_CMD_SET_PFC = 0x5, - HINIC_PORT_CMD_SET_RX_MODE = 12, + HINIC_PORT_CMD_SET_MAC = 0x9, + HINIC_PORT_CMD_GET_MAC = 0xA, + HINIC_PORT_CMD_DEL_MAC = 0xB, - HINIC_PORT_CMD_GET_PAUSE_INFO = 20, - HINIC_PORT_CMD_SET_PAUSE_INFO = 21, + HINIC_PORT_CMD_SET_RX_MODE = 0xC, - HINIC_PORT_CMD_GET_LINK_STATE = 24, + HINIC_PORT_CMD_SET_ANTI_ATTACK_RATE = 0xD, - HINIC_PORT_CMD_SET_LRO = 25, + HINIC_PORT_CMD_GET_PAUSE_INFO = 0x14, + HINIC_PORT_CMD_SET_PAUSE_INFO = 0x15, - HINIC_PORT_CMD_SET_RX_CSUM = 26, + HINIC_PORT_CMD_GET_LINK_STATE = 0x18, - HINIC_PORT_CMD_SET_RX_VLAN_OFFLOAD = 27, + HINIC_PORT_CMD_SET_LRO = 0x19, - HINIC_PORT_CMD_GET_PORT_STATISTICS = 28, + HINIC_PORT_CMD_SET_RX_CSUM = 0x1A, - HINIC_PORT_CMD_CLEAR_PORT_STATISTICS = 29, + HINIC_PORT_CMD_SET_RX_VLAN_OFFLOAD = 0x1B, - HINIC_PORT_CMD_GET_VPORT_STAT = 30, + HINIC_PORT_CMD_GET_PORT_STATISTICS = 0x1C, - HINIC_PORT_CMD_CLEAN_VPORT_STAT = 31, + HINIC_PORT_CMD_CLEAR_PORT_STATISTICS = 0x1D, - HINIC_PORT_CMD_GET_RSS_TEMPLATE_INDIR_TBL = 37, + HINIC_PORT_CMD_GET_VPORT_STAT = 0x1E, - HINIC_PORT_CMD_SET_PORT_STATE = 41, + HINIC_PORT_CMD_CLEAN_VPORT_STAT = 0x1F, - HINIC_PORT_CMD_SET_RSS_TEMPLATE_TBL = 43, + HINIC_PORT_CMD_GET_RSS_TEMPLATE_INDIR_TBL = 0x25, - HINIC_PORT_CMD_GET_RSS_TEMPLATE_TBL = 44, + HINIC_PORT_CMD_SET_PORT_STATE = 0x29, + HINIC_PORT_CMD_GET_PORT_STATE = 0x30, - HINIC_PORT_CMD_SET_RSS_HASH_ENGINE = 45, + HINIC_PORT_CMD_SET_RSS_TEMPLATE_TBL = 0x2B, - HINIC_PORT_CMD_GET_RSS_HASH_ENGINE = 46, + HINIC_PORT_CMD_GET_RSS_TEMPLATE_TBL = 0x2C, - HINIC_PORT_CMD_GET_RSS_CTX_TBL = 47, + HINIC_PORT_CMD_SET_RSS_HASH_ENGINE = 0x2D, - HINIC_PORT_CMD_SET_RSS_CTX_TBL = 48, + HINIC_PORT_CMD_GET_RSS_HASH_ENGINE = 0x2E, - HINIC_PORT_CMD_RSS_TEMP_MGR = 49, + HINIC_PORT_CMD_GET_RSS_CTX_TBL = 0x2F, - HINIC_PORT_CMD_RD_LINE_TBL = 57, + HINIC_PORT_CMD_SET_RSS_CTX_TBL = 0x30, - HINIC_PORT_CMD_RSS_CFG = 66, + HINIC_PORT_CMD_RSS_TEMP_MGR = 0x31, - HINIC_PORT_CMD_FWCTXT_INIT = 69, + HINIC_PORT_CMD_RD_LINE_TBL = 0x39, - HINIC_PORT_CMD_GET_LOOPBACK_MODE = 72, - HINIC_PORT_CMD_SET_LOOPBACK_MODE, + HINIC_PORT_CMD_RSS_CFG = 0x42, - HINIC_PORT_CMD_ENABLE_SPOOFCHK = 78, + HINIC_PORT_CMD_GET_PHY_TYPE = 0x44, - HINIC_PORT_CMD_GET_MGMT_VERSION = 88, + HINIC_PORT_CMD_FWCTXT_INIT = 0x45, - HINIC_PORT_CMD_SET_FUNC_STATE = 93, + HINIC_PORT_CMD_GET_LOOPBACK_MODE = 0x48, + HINIC_PORT_CMD_SET_LOOPBACK_MODE = 0x49, - HINIC_PORT_CMD_GET_GLOBAL_QPN = 102, + HINIC_PORT_CMD_GET_JUMBO_FRAME_SIZE = 0x4A, + HINIC_PORT_CMD_SET_JUMBO_FRAME_SIZE = 0x4B, - HINIC_PORT_CMD_SET_VF_RATE = 105, + HINIC_PORT_CMD_ENABLE_SPOOFCHK = 0x4E, - HINIC_PORT_CMD_SET_VF_VLAN = 106, + HINIC_PORT_CMD_GET_MGMT_VERSION = 0x58, - HINIC_PORT_CMD_CLR_VF_VLAN, + HINIC_PORT_CMD_GET_PORT_TYPE = 0x5B, - HINIC_PORT_CMD_SET_TSO = 112, + HINIC_PORT_CMD_SET_FUNC_STATE = 0x5D, - HINIC_PORT_CMD_UPDATE_FW = 114, + HINIC_PORT_CMD_GET_PORT_ID_BY_FUNC_ID = 0x5E, - HINIC_PORT_CMD_SET_RQ_IQ_MAP = 115, + HINIC_PORT_CMD_GET_DMA_CS = 0x64, + HINIC_PORT_CMD_SET_DMA_CS = 0x65, - HINIC_PORT_CMD_LINK_STATUS_REPORT = 160, + HINIC_PORT_CMD_GET_GLOBAL_QPN = 0x66, - HINIC_PORT_CMD_UPDATE_MAC = 164, + HINIC_PORT_CMD_SET_VF_RATE = 0x69, - HINIC_PORT_CMD_GET_CAP = 170, + HINIC_PORT_CMD_SET_VF_VLAN = 0x6A, - HINIC_PORT_CMD_GET_LINK_MODE = 217, + HINIC_PORT_CMD_CLR_VF_VLAN = 0x6B, - HINIC_PORT_CMD_SET_SPEED = 218, + HINIC_PORT_CMD_SET_TSO = 0x70, - HINIC_PORT_CMD_SET_AUTONEG = 219, + HINIC_PORT_CMD_UPDATE_FW = 0x72, - HINIC_PORT_CMD_GET_STD_SFP_INFO = 240, + HINIC_PORT_CMD_SET_RQ_IQ_MAP = 0x73, - HINIC_PORT_CMD_SET_LRO_TIMER = 244, + HINIC_PORT_CMD_SET_PFC_THD = 0x75, - HINIC_PORT_CMD_SET_VF_MAX_MIN_RATE = 249, + HINIC_PORT_CMD_LINK_STATUS_REPORT = 0xA0, - HINIC_PORT_CMD_GET_SFP_ABS = 251, + HINIC_PORT_CMD_SET_LOSSLESS_ETH = 0xA3, + + HINIC_PORT_CMD_UPDATE_MAC = 0xA4, + + HINIC_PORT_CMD_GET_CAP = 0xAA, + + HINIC_PORT_CMD_UP_TC_ADD_FLOW = 0xAF, + HINIC_PORT_CMD_UP_TC_DEL_FLOW = 0xB0, + HINIC_PORT_CMD_UP_TC_GET_FLOW = 0xB1, + + HINIC_PORT_CMD_UP_TC_FLUSH_TCAM = 0xB2, + + HINIC_PORT_CMD_UP_TC_CTRL_TCAM_BLOCK = 0xB3, + + HINIC_PORT_CMD_UP_TC_ENABLE = 0xB4, + + HINIC_PORT_CMD_UP_TC_GET_TCAM_BLOCK = 0xB5, + + HINIC_PORT_CMD_SET_IPSU_MAC = 0xCB, + HINIC_PORT_CMD_GET_IPSU_MAC = 0xCC, + + HINIC_PORT_CMD_SET_XSFP_STATUS = 0xD4, + + HINIC_PORT_CMD_GET_LINK_MODE = 0xD9, + + HINIC_PORT_CMD_SET_SPEED = 0xDA, + + HINIC_PORT_CMD_SET_AUTONEG = 0xDB, + + HINIC_PORT_CMD_CLEAR_QP_RES = 0xDD, + + HINIC_PORT_CMD_SET_SUPER_CQE = 0xDE, + + HINIC_PORT_CMD_SET_VF_COS = 0xDF, + HINIC_PORT_CMD_GET_VF_COS = 0xE1, + + HINIC_PORT_CMD_CABLE_PLUG_EVENT = 0xE5, + + HINIC_PORT_CMD_LINK_ERR_EVENT = 0xE6, + + HINIC_PORT_CMD_SET_COS_UP_MAP = 0xE8, + + HINIC_PORT_CMD_RESET_LINK_CFG = 0xEB, + + HINIC_PORT_CMD_GET_STD_SFP_INFO = 0xF0, + + HINIC_PORT_CMD_FORCE_PKT_DROP = 0xF3, + + HINIC_PORT_CMD_SET_LRO_TIMER = 0xF4, + + HINIC_PORT_CMD_SET_VHD_CFG = 0xF7, + + HINIC_PORT_CMD_SET_LINK_FOLLOW = 0xF8, + + HINIC_PORT_CMD_SET_VF_MAX_MIN_RATE = 0xF9, + + HINIC_PORT_CMD_GET_SFP_ABS = 0xFB, + + HINIC_PORT_CMD_Q_FILTER = 0xFC, + + HINIC_PORT_CMD_TCAM_FILTER = 0xFE, + + HINIC_PORT_CMD_SET_VLAN_FILTER = 0xFF, }; /* cmd of mgmt CPU message for HILINK module */ diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c index 9d4d795e1081..977c41473ab7 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_main.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c @@ -1092,6 +1092,16 @@ static int set_features(struct hinic_dev *nic_dev, } } + if (changed & NETIF_F_HW_VLAN_CTAG_FILTER) { + ret = hinic_set_vlan_fliter(nic_dev, + !!(features & + NETIF_F_HW_VLAN_CTAG_FILTER)); + if (ret) { + err = ret; + failed_features |= NETIF_F_HW_VLAN_CTAG_FILTER; + } + } + if (err) { nic_dev->netdev->features = features ^ failed_features; return -EIO; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_port.c b/drivers/net/ethernet/huawei/hinic/hinic_port.c index 0a39c3dffa9a..9406237c461e 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_port.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_port.c @@ -447,6 +447,39 @@ int hinic_set_rx_vlan_offload(struct hinic_dev *nic_dev, u8 en) return 0; } +int hinic_set_vlan_fliter(struct hinic_dev *nic_dev, u32 en) +{ + struct hinic_hwdev *hwdev = nic_dev->hwdev; + struct hinic_hwif *hwif = hwdev->hwif; + struct pci_dev *pdev = hwif->pdev; + struct hinic_vlan_filter vlan_filter; + u16 out_size = sizeof(vlan_filter); + int err; + + if (!hwdev) + return -EINVAL; + + vlan_filter.func_idx = HINIC_HWIF_FUNC_IDX(hwif); + vlan_filter.enable = en; + + err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_SET_VLAN_FILTER, + &vlan_filter, sizeof(vlan_filter), + &vlan_filter, &out_size); + if (vlan_filter.status == HINIC_MGMT_CMD_UNSUPPORTED) { + err = HINIC_MGMT_CMD_UNSUPPORTED; + } else if ((err == HINIC_MBOX_VF_CMD_ERROR) && + HINIC_IS_VF(hwif)) { + err = HINIC_MGMT_CMD_UNSUPPORTED; + } else if (err || !out_size || vlan_filter.status) { + dev_err(&pdev->dev, + "Failed to set vlan fliter, err: %d, status: 0x%x, out size: 0x%x\n", + err, vlan_filter.status, out_size); + err = -EINVAL; + } + + return err; +} + int hinic_set_max_qnum(struct hinic_dev *nic_dev, u8 num_rqs) { struct hinic_hwdev *hwdev = nic_dev->hwdev; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_port.h b/drivers/net/ethernet/huawei/hinic/hinic_port.h index c9ae3d4dc547..c8694ac7c702 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_port.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_port.h @@ -351,6 +351,16 @@ struct hinic_vlan_cfg { u8 rsvd1[5]; }; +struct hinic_vlan_filter { + u8 status; + u8 version; + u8 rsvd0[6]; + + u16 func_idx; + u8 rsvd1[2]; + u32 enable; +}; + struct hinic_rss_template_mgmt { u8 status; u8 version; @@ -831,6 +841,8 @@ int hinic_get_vport_stats(struct hinic_dev *nic_dev, int hinic_set_rx_vlan_offload(struct hinic_dev *nic_dev, u8 en); +int hinic_set_vlan_fliter(struct hinic_dev *nic_dev, u32 en); + int hinic_get_mgmt_version(struct hinic_dev *nic_dev, u8 *mgmt_ver); int hinic_set_link_settings(struct hinic_hwdev *hwdev, diff --git a/drivers/net/ethernet/huawei/hinic/hinic_sriov.c b/drivers/net/ethernet/huawei/hinic/hinic_sriov.c index f7e05b41385b..ee357088d021 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_sriov.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_sriov.c @@ -489,6 +489,24 @@ static struct vf_cmd_check_handle nic_cmd_support_vf[] = { {HINIC_PORT_CMD_UPDATE_MAC, hinic_mbox_check_func_id_8B}, {HINIC_PORT_CMD_GET_CAP, hinic_mbox_check_func_id_8B}, {HINIC_PORT_CMD_GET_LINK_MODE, hinic_mbox_check_func_id_8B}, + {HINIC_PORT_CMD_GET_VF_COS, NULL}, + {HINIC_PORT_CMD_SET_VHD_CFG, hinic_mbox_check_func_id_8B}, + {HINIC_PORT_CMD_SET_VLAN_FILTER, hinic_mbox_check_func_id_8B}, + {HINIC_PORT_CMD_Q_FILTER, hinic_mbox_check_func_id_8B}, + {HINIC_PORT_CMD_TCAM_FILTER, NULL}, + {HINIC_PORT_CMD_UP_TC_ADD_FLOW, NULL}, + {HINIC_PORT_CMD_UP_TC_DEL_FLOW, NULL}, + {HINIC_PORT_CMD_UP_TC_FLUSH_TCAM, hinic_mbox_check_func_id_8B}, + {HINIC_PORT_CMD_UP_TC_CTRL_TCAM_BLOCK, hinic_mbox_check_func_id_8B}, + {HINIC_PORT_CMD_UP_TC_ENABLE, hinic_mbox_check_func_id_8B}, + {HINIC_PORT_CMD_CABLE_PLUG_EVENT, NULL}, + {HINIC_PORT_CMD_LINK_ERR_EVENT, NULL}, + {HINIC_PORT_CMD_SET_PORT_STATE, hinic_mbox_check_func_id_8B}, + {HINIC_PORT_CMD_SET_ETS, NULL}, + {HINIC_PORT_CMD_SET_ANTI_ATTACK_RATE, NULL}, + {HINIC_PORT_CMD_RESET_LINK_CFG, hinic_mbox_check_func_id_8B}, + {HINIC_PORT_CMD_SET_LINK_FOLLOW, NULL}, + {HINIC_PORT_CMD_CLEAR_QP_RES, NULL}, }; #define CHECK_IPSU_15BIT 0X8000 diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index 7d79006250ae..113fcb3e353e 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -1749,7 +1749,8 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id) kobject_uevent(kobj, KOBJ_ADD); } - rc = netif_set_real_num_tx_queues(netdev, ibmveth_real_max_tx_queues()); + rc = netif_set_real_num_tx_queues(netdev, min(num_online_cpus(), + IBMVETH_DEFAULT_QUEUES)); if (rc) { netdev_dbg(netdev, "failed to set number of tx queues rc=%d\n", rc); diff --git a/drivers/net/ethernet/ibm/ibmveth.h b/drivers/net/ethernet/ibm/ibmveth.h index 4f8357187292..8468e2c59d7a 100644 --- a/drivers/net/ethernet/ibm/ibmveth.h +++ b/drivers/net/ethernet/ibm/ibmveth.h @@ -100,6 +100,7 @@ static inline long h_illan_attributes(unsigned long unit_address, #define IBMVETH_MAX_BUF_SIZE (1024 * 128) #define IBMVETH_MAX_TX_BUF_SIZE (1024 * 64) #define IBMVETH_MAX_QUEUES 16U +#define IBMVETH_DEFAULT_QUEUES 8U static int pool_size[] = { 512, 1024 * 2, 1024 * 16, 1024 * 32, 1024 * 64 }; static int pool_count[] = { 256, 512, 256, 256, 256 }; diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index 61e60e4de600..da6e303ad99b 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -4229,8 +4229,6 @@ process_skb: */ p = buffer_info->rxbuf.page; if (length <= copybreak) { - u8 *vaddr; - if (likely(!(netdev->features & NETIF_F_RXFCS))) length -= 4; skb = e1000_alloc_rx_skb(adapter, @@ -4238,10 +4236,9 @@ process_skb: if (!skb) break; - vaddr = kmap_atomic(p); - memcpy(skb_tail_pointer(skb), vaddr, - length); - kunmap_atomic(vaddr); + memcpy(skb_tail_pointer(skb), + page_address(p), length); + /* re-use the page, so don't erase * buffer_info->rxbuf.page */ diff --git a/drivers/net/ethernet/intel/e1000e/Makefile b/drivers/net/ethernet/intel/e1000e/Makefile index 44e58b6e7660..0baa15503c38 100644 --- a/drivers/net/ethernet/intel/e1000e/Makefile +++ b/drivers/net/ethernet/intel/e1000e/Makefile @@ -5,6 +5,9 @@ # Makefile for the Intel(R) PRO/1000 ethernet driver # +ccflags-y += -I$(src) +subdir-ccflags-y += -I$(src) + obj-$(CONFIG_E1000E) += e1000e.o e1000e-objs := 82571.o ich8lan.o 80003es2lan.o \ diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h index e8a9a9610ac6..a187582d2299 100644 --- a/drivers/net/ethernet/intel/e1000e/e1000.h +++ b/drivers/net/ethernet/intel/e1000e/e1000.h @@ -116,7 +116,8 @@ enum e1000_boards { board_pch_spt, board_pch_cnp, board_pch_tgp, - board_pch_adp + board_pch_adp, + board_pch_mtp }; struct e1000_ps_page { @@ -504,6 +505,7 @@ extern const struct e1000_info e1000_pch_spt_info; extern const struct e1000_info e1000_pch_cnp_info; extern const struct e1000_info e1000_pch_tgp_info; extern const struct e1000_info e1000_pch_adp_info; +extern const struct e1000_info e1000_pch_mtp_info; extern const struct e1000_info e1000_es2_info; void e1000e_ptp_init(struct e1000_adapter *adapter); diff --git a/drivers/net/ethernet/intel/e1000e/e1000e_trace.h b/drivers/net/ethernet/intel/e1000e/e1000e_trace.h new file mode 100644 index 000000000000..19d3cf4d924e --- /dev/null +++ b/drivers/net/ethernet/intel/e1000e/e1000e_trace.h @@ -0,0 +1,42 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2022, Intel Corporation. */ +/* Modeled on trace-events-sample.h */ +/* The trace subsystem name for e1000e will be "e1000e_trace". + * + * This file is named e1000e_trace.h. + * + * Since this include file's name is different from the trace + * subsystem name, we'll have to define TRACE_INCLUDE_FILE at the end + * of this file. + */ + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM e1000e_trace + +#if !defined(_TRACE_E1000E_TRACE_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_E1000E_TRACE_H + +#include <linux/tracepoint.h> + +TRACE_EVENT(e1000e_trace_mac_register, + TP_PROTO(uint32_t reg), + TP_ARGS(reg), + TP_STRUCT__entry(__field(uint32_t, reg)), + TP_fast_assign(__entry->reg = reg;), + TP_printk("event: TraceHub e1000e mac register: 0x%08x", + __entry->reg) +); + +#endif +/* This must be outside ifdef _E1000E_TRACE_H */ +/* This trace include file is not located in the .../include/trace + * with the kernel tracepoint definitions, because we're a loadable + * module. + */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE e1000e_trace + +#include <trace/define_trace.h> diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c index 51a5afe9df2f..59e82d131d88 100644 --- a/drivers/net/ethernet/intel/e1000e/ethtool.c +++ b/drivers/net/ethernet/intel/e1000e/ethtool.c @@ -908,6 +908,7 @@ static int e1000_reg_test(struct e1000_adapter *adapter, u64 *data) case e1000_pch_adp: case e1000_pch_mtp: case e1000_pch_lnp: + case e1000_pch_ptp: mask |= BIT(18); break; default: @@ -1575,6 +1576,7 @@ static void e1000_loopback_cleanup(struct e1000_adapter *adapter) case e1000_pch_adp: case e1000_pch_mtp: case e1000_pch_lnp: + case e1000_pch_ptp: fext_nvm11 = er32(FEXTNVM11); fext_nvm11 &= ~E1000_FEXTNVM11_DISABLE_MULR_FIX; ew32(FEXTNVM11, fext_nvm11); diff --git a/drivers/net/ethernet/intel/e1000e/hw.h b/drivers/net/ethernet/intel/e1000e/hw.h index bcf680e83811..29f9fae35f42 100644 --- a/drivers/net/ethernet/intel/e1000e/hw.h +++ b/drivers/net/ethernet/intel/e1000e/hw.h @@ -114,6 +114,14 @@ struct e1000_hw; #define E1000_DEV_ID_PCH_LNP_I219_V20 0x550F #define E1000_DEV_ID_PCH_LNP_I219_LM21 0x5510 #define E1000_DEV_ID_PCH_LNP_I219_V21 0x5511 +#define E1000_DEV_ID_PCH_ARL_I219_LM24 0x57A0 +#define E1000_DEV_ID_PCH_ARL_I219_V24 0x57A1 +#define E1000_DEV_ID_PCH_PTP_I219_LM25 0x57B3 +#define E1000_DEV_ID_PCH_PTP_I219_V25 0x57B4 +#define E1000_DEV_ID_PCH_PTP_I219_LM26 0x57B5 +#define E1000_DEV_ID_PCH_PTP_I219_V26 0x57B6 +#define E1000_DEV_ID_PCH_PTP_I219_LM27 0x57B7 +#define E1000_DEV_ID_PCH_PTP_I219_V27 0x57B8 #define E1000_REVISION_4 4 @@ -141,6 +149,7 @@ enum e1000_mac_type { e1000_pch_adp, e1000_pch_mtp, e1000_pch_lnp, + e1000_pch_ptp, }; enum e1000_media_type { diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index 9466f65a6da7..0c7fd10312c8 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -322,6 +322,7 @@ static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw) case e1000_pch_adp: case e1000_pch_mtp: case e1000_pch_lnp: + case e1000_pch_ptp: if (e1000_phy_is_accessible_pchlan(hw)) break; @@ -468,6 +469,7 @@ static s32 e1000_init_phy_params_pchlan(struct e1000_hw *hw) case e1000_pch_adp: case e1000_pch_mtp: case e1000_pch_lnp: + case e1000_pch_ptp: /* In case the PHY needs to be in mdio slow mode, * set slow mode and try to get the PHY id again. */ @@ -714,6 +716,7 @@ static s32 e1000_init_mac_params_ich8lan(struct e1000_hw *hw) case e1000_pch_adp: case e1000_pch_mtp: case e1000_pch_lnp: + case e1000_pch_ptp: case e1000_pchlan: /* check management mode */ mac->ops.check_mng_mode = e1000_check_mng_mode_pchlan; @@ -1681,6 +1684,7 @@ static s32 e1000_get_variants_ich8lan(struct e1000_adapter *adapter) case e1000_pch_adp: case e1000_pch_mtp: case e1000_pch_lnp: + case e1000_pch_ptp: rc = e1000_init_phy_params_pchlan(hw); break; default: @@ -2137,6 +2141,7 @@ static s32 e1000_sw_lcd_config_ich8lan(struct e1000_hw *hw) case e1000_pch_adp: case e1000_pch_mtp: case e1000_pch_lnp: + case e1000_pch_ptp: sw_cfg_mask = E1000_FEXTNVM_SW_CONFIG_ICH8M; break; default: @@ -3182,6 +3187,7 @@ static s32 e1000_valid_nvm_bank_detect_ich8lan(struct e1000_hw *hw, u32 *bank) case e1000_pch_adp: case e1000_pch_mtp: case e1000_pch_lnp: + case e1000_pch_ptp: bank1_offset = nvm->flash_bank_size; act_offset = E1000_ICH_NVM_SIG_WORD; @@ -4122,6 +4128,7 @@ static s32 e1000_validate_nvm_checksum_ich8lan(struct e1000_hw *hw) case e1000_pch_adp: case e1000_pch_mtp: case e1000_pch_lnp: + case e1000_pch_ptp: word = NVM_COMPAT; valid_csum_mask = NVM_COMPAT_VALID_CSUM; break; @@ -6041,3 +6048,23 @@ const struct e1000_info e1000_pch_adp_info = { .phy_ops = &ich8_phy_ops, .nvm_ops = &spt_nvm_ops, }; + +const struct e1000_info e1000_pch_mtp_info = { + .mac = e1000_pch_mtp, + .flags = FLAG_IS_ICH + | FLAG_HAS_WOL + | FLAG_HAS_HW_TIMESTAMP + | FLAG_HAS_CTRLEXT_ON_LOAD + | FLAG_HAS_AMT + | FLAG_HAS_FLASH + | FLAG_HAS_JUMBO_FRAMES + | FLAG_APME_IN_WUC, + .flags2 = FLAG2_HAS_PHY_STATS + | FLAG2_HAS_EEE, + .pba = 26, + .max_hw_frame_size = 9022, + .get_variants = e1000_get_variants_ich8lan, + .mac_ops = &ich8_mac_ops, + .phy_ops = &ich8_phy_ops, + .nvm_ops = &spt_nvm_ops, +}; diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 49e926959ad3..36bc4fd91ef4 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -28,6 +28,8 @@ #include <linux/suspend.h> #include "e1000.h" +#define CREATE_TRACE_POINTS +#include "e1000e_trace.h" char e1000e_driver_name[] = "e1000e"; @@ -53,6 +55,7 @@ static const struct e1000_info *e1000_info_tbl[] = { [board_pch_cnp] = &e1000_pch_cnp_info, [board_pch_tgp] = &e1000_pch_tgp_info, [board_pch_adp] = &e1000_pch_adp_info, + [board_pch_mtp] = &e1000_pch_mtp_info, }; struct e1000_reg_info { @@ -1388,26 +1391,18 @@ static bool e1000_clean_rx_irq_ps(struct e1000_ring *rx_ring, int *work_done, /* page alloc/put takes too long and effects small * packet throughput, so unsplit small packets and - * save the alloc/put only valid in softirq (napi) - * context to call kmap_* + * save the alloc/put */ if (l1 && (l1 <= copybreak) && ((length + l1) <= adapter->rx_ps_bsize0)) { - u8 *vaddr; - ps_page = &buffer_info->ps_pages[0]; - /* there is no documentation about how to call - * kmap_atomic, so we can't hold the mapping - * very long - */ dma_sync_single_for_cpu(&pdev->dev, ps_page->dma, PAGE_SIZE, DMA_FROM_DEVICE); - vaddr = kmap_atomic(ps_page->page); - memcpy(skb_tail_pointer(skb), vaddr, l1); - kunmap_atomic(vaddr); + memcpy(skb_tail_pointer(skb), + page_address(ps_page->page), l1); dma_sync_single_for_device(&pdev->dev, ps_page->dma, PAGE_SIZE, @@ -1607,11 +1602,9 @@ static bool e1000_clean_jumbo_rx_irq(struct e1000_ring *rx_ring, int *work_done, */ if (length <= copybreak && skb_tailroom(skb) >= length) { - u8 *vaddr; - vaddr = kmap_atomic(buffer_info->page); - memcpy(skb_tail_pointer(skb), vaddr, + memcpy(skb_tail_pointer(skb), + page_address(buffer_info->page), length); - kunmap_atomic(vaddr); /* re-use the page, so don't erase * buffer_info->page */ @@ -3552,6 +3545,7 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca) case e1000_pch_adp: case e1000_pch_mtp: case e1000_pch_lnp: + case e1000_pch_ptp: if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI) { /* Stable 24MHz frequency */ incperiod = INCPERIOD_24MHZ; @@ -4067,6 +4061,7 @@ void e1000e_reset(struct e1000_adapter *adapter) case e1000_pch_adp: case e1000_pch_mtp: case e1000_pch_lnp: + case e1000_pch_ptp: fc->refresh_time = 0xFFFF; fc->pause_time = 0xFFFF; @@ -6348,6 +6343,7 @@ static void e1000e_s0ix_entry_flow(struct e1000_adapter *adapter) mac_data = er32(H2ME); mac_data |= E1000_H2ME_START_DPG; mac_data &= ~E1000_H2ME_EXIT_DPG; + trace_e1000e_trace_mac_register(mac_data); ew32(H2ME, mac_data); } else { /* Request driver configure the device to S0ix */ @@ -6502,6 +6498,7 @@ static void e1000e_s0ix_exit_flow(struct e1000_adapter *adapter) mac_data = er32(H2ME); mac_data &= ~E1000_H2ME_START_DPG; mac_data |= E1000_H2ME_EXIT_DPG; + trace_e1000e_trace_mac_register(mac_data); ew32(H2ME, mac_data); /* Poll up to 2.5 seconds for ME to unconfigure DPG. @@ -7905,14 +7902,22 @@ static const struct pci_device_id e1000_pci_tbl[] = { { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_V17), board_pch_adp }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_LM22), board_pch_adp }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_V22), board_pch_adp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_LM18), board_pch_adp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_V18), board_pch_adp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_LM19), board_pch_adp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_V19), board_pch_adp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_LM20), board_pch_adp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_V20), board_pch_adp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_LM21), board_pch_adp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_V21), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_LM18), board_pch_mtp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_V18), board_pch_mtp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_LM19), board_pch_mtp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_V19), board_pch_mtp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_LM20), board_pch_mtp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_V20), board_pch_mtp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_LM21), board_pch_mtp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_V21), board_pch_mtp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ARL_I219_LM24), board_pch_mtp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ARL_I219_V24), board_pch_mtp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_LM25), board_pch_mtp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_V25), board_pch_mtp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_LM26), board_pch_mtp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_V26), board_pch_mtp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_LM27), board_pch_mtp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_V27), board_pch_mtp }, { 0, 0, 0, 0, 0, 0, 0 } /* terminate list */ }; diff --git a/drivers/net/ethernet/intel/e1000e/ptp.c b/drivers/net/ethernet/intel/e1000e/ptp.c index 6e5a1720e6cd..def4566a916f 100644 --- a/drivers/net/ethernet/intel/e1000e/ptp.c +++ b/drivers/net/ethernet/intel/e1000e/ptp.c @@ -287,6 +287,7 @@ void e1000e_ptp_init(struct e1000_adapter *adapter) case e1000_pch_adp: case e1000_pch_mtp: case e1000_pch_lnp: + case e1000_pch_ptp: if ((hw->mac.type < e1000_pch_lpt) || (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI)) { adapter->ptp_clock_info.max_adj = 24000000 - 1; diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 9a60d6b207f7..60e351665c70 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -992,6 +992,7 @@ struct i40e_q_vector { struct rcu_head rcu; /* to avoid race with update stats on free */ char name[I40E_INT_NAME_STR_LEN]; bool arm_wb_state; + int irq_num; /* IRQ assigned to this q_vector */ } ____cacheline_internodealigned_in_smp; /* lan device */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index cc269f9db99f..616d27ec3226 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -1287,8 +1287,10 @@ static int i40e_set_link_ksettings(struct net_device *netdev, * trying to set something that we do not support. */ if (memcmp(©_ks.base, &safe_ks.base, - sizeof(struct ethtool_link_settings))) + sizeof(struct ethtool_link_settings))) { + netdev_err(netdev, "Only speed and autoneg are supported.\n"); return -EOPNOTSUPP; + } while (test_and_set_bit(__I40E_CONFIG_BUSY, pf->state)) { timeout--; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 1a1fab94205d..4880b740fa6e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -4123,6 +4123,7 @@ static int i40e_vsi_request_irq_msix(struct i40e_vsi *vsi, char *basename) } /* register for affinity change notifications */ + q_vector->irq_num = irq_num; q_vector->affinity_notify.notify = i40e_irq_affinity_notify; q_vector->affinity_notify.release = i40e_irq_affinity_release; irq_set_affinity_notifier(irq_num, &q_vector->affinity_notify); diff --git a/drivers/net/ethernet/intel/i40e/i40e_trace.h b/drivers/net/ethernet/intel/i40e/i40e_trace.h index b5b12299931f..79d587ad5409 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_trace.h +++ b/drivers/net/ethernet/intel/i40e/i40e_trace.h @@ -55,6 +55,55 @@ * being built from shared code. */ +#define NO_DEV "(i40e no_device)" + +TRACE_EVENT(i40e_napi_poll, + + TP_PROTO(struct napi_struct *napi, struct i40e_q_vector *q, int budget, + int budget_per_ring, unsigned int rx_cleaned, unsigned int tx_cleaned, + bool rx_clean_complete, bool tx_clean_complete), + + TP_ARGS(napi, q, budget, budget_per_ring, rx_cleaned, tx_cleaned, + rx_clean_complete, tx_clean_complete), + + TP_STRUCT__entry( + __field(int, budget) + __field(int, budget_per_ring) + __field(unsigned int, rx_cleaned) + __field(unsigned int, tx_cleaned) + __field(int, rx_clean_complete) + __field(int, tx_clean_complete) + __field(int, irq_num) + __field(int, curr_cpu) + __string(qname, q->name) + __string(dev_name, napi->dev ? napi->dev->name : NO_DEV) + __bitmask(irq_affinity, nr_cpumask_bits) + ), + + TP_fast_assign( + __entry->budget = budget; + __entry->budget_per_ring = budget_per_ring; + __entry->rx_cleaned = rx_cleaned; + __entry->tx_cleaned = tx_cleaned; + __entry->rx_clean_complete = rx_clean_complete; + __entry->tx_clean_complete = tx_clean_complete; + __entry->irq_num = q->irq_num; + __entry->curr_cpu = get_cpu(); + __assign_str(qname, q->name); + __assign_str(dev_name, napi->dev ? napi->dev->name : NO_DEV); + __assign_bitmask(irq_affinity, cpumask_bits(&q->affinity_mask), + nr_cpumask_bits); + ), + + TP_printk("i40e_napi_poll on dev %s q %s irq %d irq_mask %s curr_cpu %d " + "budget %d bpr %d rx_cleaned %u tx_cleaned %u " + "rx_clean_complete %d tx_clean_complete %d", + __get_str(dev_name), __get_str(qname), __entry->irq_num, + __get_bitmask(irq_affinity), __entry->curr_cpu, __entry->budget, + __entry->budget_per_ring, __entry->rx_cleaned, __entry->tx_cleaned, + __entry->rx_clean_complete, __entry->tx_clean_complete) +); + /* Events related to a vsi & ring */ DECLARE_EVENT_CLASS( i40e_tx_template, diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index b97c95f89fa0..924f972b91fa 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -923,11 +923,13 @@ void i40e_detect_recover_hung(struct i40e_vsi *vsi) * @vsi: the VSI we care about * @tx_ring: Tx ring to clean * @napi_budget: Used to determine if we are in netpoll + * @tx_cleaned: Out parameter set to the number of TXes cleaned * * Returns true if there's any budget left (e.g. the clean is finished) **/ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, - struct i40e_ring *tx_ring, int napi_budget) + struct i40e_ring *tx_ring, int napi_budget, + unsigned int *tx_cleaned) { int i = tx_ring->next_to_clean; struct i40e_tx_buffer *tx_buf; @@ -1048,6 +1050,7 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, } } + *tx_cleaned = total_packets; return !!budget; } @@ -2422,6 +2425,7 @@ static void i40e_inc_ntc(struct i40e_ring *rx_ring) * i40e_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 + * @rx_cleaned: Out parameter of the number of packets processed * * This function provides a "bounce buffer" approach to Rx interrupt * processing. The advantage to this is that on systems that have @@ -2430,7 +2434,8 @@ static void i40e_inc_ntc(struct i40e_ring *rx_ring) * * Returns amount of work completed **/ -static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) +static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget, + unsigned int *rx_cleaned) { unsigned int total_rx_bytes = 0, total_rx_packets = 0, frame_sz = 0; u16 cleaned_count = I40E_DESC_UNUSED(rx_ring); @@ -2567,6 +2572,8 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) i40e_update_rx_stats(rx_ring, total_rx_bytes, total_rx_packets); + *rx_cleaned = total_rx_packets; + /* guarantee a trip back through this routine if there was a failure */ return failure ? budget : (int)total_rx_packets; } @@ -2689,6 +2696,10 @@ int i40e_napi_poll(struct napi_struct *napi, int budget) container_of(napi, struct i40e_q_vector, napi); struct i40e_vsi *vsi = q_vector->vsi; struct i40e_ring *ring; + bool tx_clean_complete = true; + bool rx_clean_complete = true; + unsigned int tx_cleaned = 0; + unsigned int rx_cleaned = 0; bool clean_complete = true; bool arm_wb = false; int budget_per_ring; @@ -2705,10 +2716,10 @@ int i40e_napi_poll(struct napi_struct *napi, int budget) i40e_for_each_ring(ring, q_vector->tx) { bool wd = ring->xsk_pool ? i40e_clean_xdp_tx_irq(vsi, ring) : - i40e_clean_tx_irq(vsi, ring, budget); + i40e_clean_tx_irq(vsi, ring, budget, &tx_cleaned); if (!wd) { - clean_complete = false; + clean_complete = tx_clean_complete = false; continue; } arm_wb |= ring->arm_wb; @@ -2733,14 +2744,18 @@ int i40e_napi_poll(struct napi_struct *napi, int budget) i40e_for_each_ring(ring, q_vector->rx) { int cleaned = ring->xsk_pool ? i40e_clean_rx_irq_zc(ring, budget_per_ring) : - i40e_clean_rx_irq(ring, budget_per_ring); + i40e_clean_rx_irq(ring, budget_per_ring, &rx_cleaned); work_done += cleaned; /* if we clean as many as budgeted, we must not be done */ if (cleaned >= budget_per_ring) - clean_complete = false; + clean_complete = rx_clean_complete = false; } + if (!i40e_enabled_xdp_vsi(vsi)) + trace_i40e_napi_poll(napi, q_vector, budget, budget_per_ring, rx_cleaned, + tx_cleaned, rx_clean_complete, tx_clean_complete); + /* If work not completed, return budget and polling will return */ if (!clean_complete) { int cpu_id = smp_processor_id(); diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 3fc572341781..258bdf8906dd 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -4820,7 +4820,7 @@ static void iavf_shutdown(struct pci_dev *pdev) iavf_close(netdev); if (iavf_lock_timeout(&adapter->crit_lock, 5000)) - dev_warn(&adapter->pdev->dev, "failed to acquire crit_lock in %s\n", __FUNCTION__); + dev_warn(&adapter->pdev->dev, "%s: failed to acquire crit_lock\n", __func__); /* Prevent the watchdog from running. */ iavf_change_state(adapter, __IAVF_REMOVE); adapter->aq_required = 0; @@ -5083,7 +5083,7 @@ static void iavf_remove(struct pci_dev *pdev) } mutex_lock(&adapter->crit_lock); - dev_info(&adapter->pdev->dev, "Remove device\n"); + dev_info(&adapter->pdev->dev, "Removing device\n"); iavf_change_state(adapter, __IAVF_REMOVE); iavf_request_reset(adapter); diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 5a9e6563923e..24a701fd140e 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -2438,6 +2438,8 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, list_for_each_entry(f, &adapter->vlan_filter_list, list) { if (f->is_new_vlan) { f->is_new_vlan = false; + if (!f->vlan.vid) + continue; if (f->vlan.tpid == ETH_P_8021Q) set_bit(f->vlan.vid, adapter->vsi.active_cvlans); diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index 9e36f01dfa4f..e864634d66bc 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -958,7 +958,7 @@ ice_vsi_stop_tx_ring(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, * associated to the queue to schedule NAPI handler */ q_vector = ring->q_vector; - if (q_vector) + if (q_vector && !(vsi->vf && ice_is_vf_disabled(vsi->vf))) ice_trigger_sw_intr(hw, q_vector); status = ice_dis_vsi_txq(vsi->port_info, txq_meta->vsi_idx, diff --git a/drivers/net/ethernet/intel/ice/ice_devlink.c b/drivers/net/ethernet/intel/ice/ice_devlink.c index e6ec20079ced..455489e9457d 100644 --- a/drivers/net/ethernet/intel/ice/ice_devlink.c +++ b/drivers/net/ethernet/intel/ice/ice_devlink.c @@ -1033,12 +1033,7 @@ int ice_devlink_create_pf_port(struct ice_pf *pf) */ void ice_devlink_destroy_pf_port(struct ice_pf *pf) { - struct devlink_port *devlink_port; - - devlink_port = &pf->devlink_port; - - devlink_port_type_clear(devlink_port); - devlink_port_unregister(devlink_port); + devlink_port_unregister(&pf->devlink_port); } /** @@ -1094,12 +1089,7 @@ int ice_devlink_create_vf_port(struct ice_vf *vf) */ void ice_devlink_destroy_vf_port(struct ice_vf *vf) { - struct devlink_port *devlink_port; - - devlink_port = &vf->devlink_port; - - devlink_port_type_clear(devlink_port); - devlink_port_unregister(devlink_port); + devlink_port_unregister(&vf->devlink_port); } #define ICE_DEVLINK_READ_BLK_SIZE (1024 * 1024) diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 938ba8c215cb..7276badfa19e 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -2240,6 +2240,31 @@ int ice_vsi_stop_xdp_tx_rings(struct ice_vsi *vsi) } /** + * ice_vsi_is_rx_queue_active + * @vsi: the VSI being configured + * + * Return true if at least one queue is active. + */ +bool ice_vsi_is_rx_queue_active(struct ice_vsi *vsi) +{ + struct ice_pf *pf = vsi->back; + struct ice_hw *hw = &pf->hw; + int i; + + ice_for_each_rxq(vsi, i) { + u32 rx_reg; + int pf_q; + + pf_q = vsi->rxq_map[i]; + rx_reg = rd32(hw, QRX_CTRL(pf_q)); + if (rx_reg & QRX_CTRL_QENA_STAT_M) + return true; + } + + return false; +} + +/** * ice_vsi_is_vlan_pruning_ena - check if VLAN pruning is enabled or not * @vsi: VSI to check whether or not VLAN pruning is enabled. * diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h index ec4bf0c89857..dcdf69a693e9 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_lib.h @@ -129,4 +129,5 @@ u16 ice_vsi_num_non_zero_vlans(struct ice_vsi *vsi); bool ice_is_feature_supported(struct ice_pf *pf, enum ice_feature f); void ice_clear_feature_support(struct ice_pf *pf, enum ice_feature f); void ice_init_feature_support(struct ice_pf *pf); +bool ice_vsi_is_rx_queue_active(struct ice_vsi *vsi); #endif /* !_ICE_LIB_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 1f27dc20b4f1..a9fc89aebebe 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -299,20 +299,6 @@ static int ice_clear_promisc(struct ice_vsi *vsi, u8 promisc_m) } /** - * ice_get_devlink_port - Get devlink port from netdev - * @netdev: the netdevice structure - */ -static struct devlink_port *ice_get_devlink_port(struct net_device *netdev) -{ - struct ice_pf *pf = ice_netdev_to_pf(netdev); - - if (!ice_is_switchdev_running(pf)) - return NULL; - - return &pf->devlink_port; -} - -/** * ice_vsi_sync_fltr - Update the VSI filter list to the HW * @vsi: ptr to the VSI * @@ -4603,6 +4589,7 @@ static int ice_register_netdev(struct ice_pf *pf) if (err) goto err_devlink_create; + SET_NETDEV_DEVLINK_PORT(vsi->netdev, &pf->devlink_port); err = register_netdev(vsi->netdev); if (err) goto err_register_netdev; @@ -4611,8 +4598,6 @@ static int ice_register_netdev(struct ice_pf *pf) netif_carrier_off(vsi->netdev); netif_tx_stop_all_queues(vsi->netdev); - devlink_port_type_eth_set(&pf->devlink_port, vsi->netdev); - return 0; err_register_netdev: ice_devlink_destroy_pf_port(pf); @@ -9108,5 +9093,4 @@ static const struct net_device_ops ice_netdev_ops = { .ndo_bpf = ice_xdp, .ndo_xdp_xmit = ice_xdp_xmit, .ndo_xsk_wakeup = ice_xsk_wakeup, - .ndo_get_devlink_port = ice_get_devlink_port, }; diff --git a/drivers/net/ethernet/intel/ice/ice_repr.c b/drivers/net/ethernet/intel/ice/ice_repr.c index bd31748aae1b..0483eb14c288 100644 --- a/drivers/net/ethernet/intel/ice/ice_repr.c +++ b/drivers/net/ethernet/intel/ice/ice_repr.c @@ -134,14 +134,6 @@ static int ice_repr_stop(struct net_device *netdev) return 0; } -static struct devlink_port * -ice_repr_get_devlink_port(struct net_device *netdev) -{ - struct ice_repr *repr = ice_netdev_to_repr(netdev); - - return &repr->vf->devlink_port; -} - /** * ice_repr_sp_stats64 - get slow path stats for port representor * @dev: network interface device structure @@ -250,7 +242,6 @@ static const struct net_device_ops ice_repr_netdev_ops = { .ndo_open = ice_repr_open, .ndo_stop = ice_repr_stop, .ndo_start_xmit = ice_eswitch_port_start_xmit, - .ndo_get_devlink_port = ice_repr_get_devlink_port, .ndo_setup_tc = ice_repr_setup_tc, .ndo_has_offload_stats = ice_repr_ndo_has_offload_stats, .ndo_get_offload_stats = ice_repr_ndo_get_offload_stats, @@ -339,12 +330,11 @@ static int ice_repr_add(struct ice_vf *vf) repr->netdev->max_mtu = ICE_MAX_MTU; SET_NETDEV_DEV(repr->netdev, ice_pf_to_dev(vf->pf)); + SET_NETDEV_DEVLINK_PORT(repr->netdev, &vf->devlink_port); err = ice_repr_reg_netdev(repr->netdev); if (err) goto err_netdev; - devlink_port_type_eth_set(&vf->devlink_port, repr->netdev); - ice_virtchnl_set_repr_ops(vf); return 0; diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c index 0abeed092de1..1c51778db951 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c @@ -576,7 +576,10 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags) return -EINVAL; } ice_vsi_stop_lan_tx_rings(vsi, ICE_NO_RESET, vf->vf_id); - ice_vsi_stop_all_rx_rings(vsi); + + if (ice_vsi_is_rx_queue_active(vsi)) + ice_vsi_stop_all_rx_rings(vsi); + dev_dbg(dev, "VF is already disabled, there is no need for resetting it, telling VM, all is fine %d\n", vf->vf_id); return 0; diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index d6c1c2e66f26..97290fc0fddd 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -1195,15 +1195,19 @@ static int igb_alloc_q_vector(struct igb_adapter *adapter, return -ENOMEM; ring_count = txr_count + rxr_count; - size = struct_size(q_vector, ring, ring_count); + size = kmalloc_size_roundup(struct_size(q_vector, ring, ring_count)); /* allocate q_vector and rings */ q_vector = adapter->q_vector[v_idx]; if (!q_vector) { q_vector = kzalloc(size, GFP_KERNEL); } else if (size > ksize(q_vector)) { - kfree_rcu(q_vector, rcu); - q_vector = kzalloc(size, GFP_KERNEL); + struct igb_q_vector *new_q_vector; + + new_q_vector = kzalloc(size, GFP_KERNEL); + if (new_q_vector) + kfree_rcu(q_vector, rcu); + q_vector = new_q_vector; } else { memset(q_vector, 0, size); } diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h index 4f9d7f013a95..f7311aeb293b 100644 --- a/drivers/net/ethernet/intel/igc/igc_defines.h +++ b/drivers/net/ethernet/intel/igc/igc_defines.h @@ -400,6 +400,15 @@ #define IGC_DTXMXPKTSZ_TSN 0x19 /* 1600 bytes of max TX DMA packet size */ #define IGC_DTXMXPKTSZ_DEFAULT 0x98 /* 9728-byte Jumbo frames */ +/* Transmit Scheduling Latency */ +/* Latency between transmission scheduling (LaunchTime) and the time + * the packet is transmitted to the network in nanosecond. + */ +#define IGC_TXOFFSET_SPEED_10 0x000034BC +#define IGC_TXOFFSET_SPEED_100 0x00000578 +#define IGC_TXOFFSET_SPEED_1000 0x0000012C +#define IGC_TXOFFSET_SPEED_2500 0x00000578 + /* Time Sync Interrupt Causes */ #define IGC_TSICR_SYS_WRAP BIT(0) /* SYSTIM Wrap around. */ #define IGC_TSICR_TXTS BIT(1) /* Transmit Timestamp. */ diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 5d307b6e660b..1586e1e435c6 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -5381,6 +5381,13 @@ static void igc_watchdog_task(struct work_struct *work) break; } + /* Once the launch time has been set on the wire, there + * is a delay before the link speed can be determined + * based on link-up activity. Write into the register + * as soon as we know the correct link speed. + */ + igc_tsn_adjust_txtime_offset(adapter); + if (adapter->link_speed != SPEED_1000) goto no_wait; diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h index c0d8214148d1..01c86d36856d 100644 --- a/drivers/net/ethernet/intel/igc/igc_regs.h +++ b/drivers/net/ethernet/intel/igc/igc_regs.h @@ -224,6 +224,7 @@ /* Transmit Scheduling Registers */ #define IGC_TQAVCTRL 0x3570 #define IGC_TXQCTL(_n) (0x3344 + 0x4 * (_n)) +#define IGC_GTXOFFSET 0x3310 #define IGC_BASET_L 0x3314 #define IGC_BASET_H 0x3318 #define IGC_QBVCYCLET 0x331C diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.c b/drivers/net/ethernet/intel/igc/igc_tsn.c index 0fce22de2ab8..f975ed807da1 100644 --- a/drivers/net/ethernet/intel/igc/igc_tsn.c +++ b/drivers/net/ethernet/intel/igc/igc_tsn.c @@ -48,6 +48,35 @@ static unsigned int igc_tsn_new_flags(struct igc_adapter *adapter) return new_flags; } +void igc_tsn_adjust_txtime_offset(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + u16 txoffset; + + if (!is_any_launchtime(adapter)) + return; + + switch (adapter->link_speed) { + case SPEED_10: + txoffset = IGC_TXOFFSET_SPEED_10; + break; + case SPEED_100: + txoffset = IGC_TXOFFSET_SPEED_100; + break; + case SPEED_1000: + txoffset = IGC_TXOFFSET_SPEED_1000; + break; + case SPEED_2500: + txoffset = IGC_TXOFFSET_SPEED_2500; + break; + default: + txoffset = 0; + break; + } + + wr32(IGC_GTXOFFSET, txoffset); +} + /* Returns the TSN specific registers to their default values after * the adapter is reset. */ @@ -57,6 +86,7 @@ static int igc_tsn_disable_offload(struct igc_adapter *adapter) u32 tqavctrl; int i; + wr32(IGC_GTXOFFSET, 0); wr32(IGC_TXPBS, I225_TXPBSIZE_DEFAULT); wr32(IGC_DTXMXPKTSZ, IGC_DTXMXPKTSZ_DEFAULT); diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.h b/drivers/net/ethernet/intel/igc/igc_tsn.h index 1512307f5a52..b53e6af560b7 100644 --- a/drivers/net/ethernet/intel/igc/igc_tsn.h +++ b/drivers/net/ethernet/intel/igc/igc_tsn.h @@ -6,5 +6,6 @@ int igc_tsn_offload_apply(struct igc_adapter *adapter); int igc_tsn_reset(struct igc_adapter *adapter); +void igc_tsn_adjust_txtime_offset(struct igc_adapter *adapter); #endif /* _IGC_BASE_H */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index 5369a97ff5ec..bc68b8f2176d 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -39,7 +39,10 @@ /* TX/RX descriptor defines */ #define IXGBE_DEFAULT_TXD 512 #define IXGBE_DEFAULT_TX_WORK 256 -#define IXGBE_MAX_TXD 4096 +#define IXGBE_MAX_TXD_82598 4096 +#define IXGBE_MAX_TXD_82599 8192 +#define IXGBE_MAX_TXD_X540 8192 +#define IXGBE_MAX_TXD_X550 32768 #define IXGBE_MIN_TXD 64 #if (PAGE_SIZE < 8192) @@ -47,7 +50,10 @@ #else #define IXGBE_DEFAULT_RXD 128 #endif -#define IXGBE_MAX_RXD 4096 +#define IXGBE_MAX_RXD_82598 4096 +#define IXGBE_MAX_RXD_82599 8192 +#define IXGBE_MAX_RXD_X540 8192 +#define IXGBE_MAX_RXD_X550 32768 #define IXGBE_MIN_RXD 64 /* flow control */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index eda7188e8df4..6cfc9dc16537 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -1117,6 +1117,42 @@ static void ixgbe_get_drvinfo(struct net_device *netdev, drvinfo->n_priv_flags = IXGBE_PRIV_FLAGS_STR_LEN; } +static u32 ixgbe_get_max_rxd(struct ixgbe_adapter *adapter) +{ + switch (adapter->hw.mac.type) { + case ixgbe_mac_82598EB: + return IXGBE_MAX_RXD_82598; + case ixgbe_mac_82599EB: + return IXGBE_MAX_RXD_82599; + case ixgbe_mac_X540: + return IXGBE_MAX_RXD_X540; + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + return IXGBE_MAX_RXD_X550; + default: + return IXGBE_MAX_RXD_82598; + } +} + +static u32 ixgbe_get_max_txd(struct ixgbe_adapter *adapter) +{ + switch (adapter->hw.mac.type) { + case ixgbe_mac_82598EB: + return IXGBE_MAX_TXD_82598; + case ixgbe_mac_82599EB: + return IXGBE_MAX_TXD_82599; + case ixgbe_mac_X540: + return IXGBE_MAX_TXD_X540; + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + return IXGBE_MAX_TXD_X550; + default: + return IXGBE_MAX_TXD_82598; + } +} + static void ixgbe_get_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring, struct kernel_ethtool_ringparam *kernel_ring, @@ -1126,8 +1162,8 @@ static void ixgbe_get_ringparam(struct net_device *netdev, struct ixgbe_ring *tx_ring = adapter->tx_ring[0]; struct ixgbe_ring *rx_ring = adapter->rx_ring[0]; - ring->rx_max_pending = IXGBE_MAX_RXD; - ring->tx_max_pending = IXGBE_MAX_TXD; + ring->rx_max_pending = ixgbe_get_max_rxd(adapter); + ring->tx_max_pending = ixgbe_get_max_txd(adapter); ring->rx_pending = rx_ring->count; ring->tx_pending = tx_ring->count; } @@ -1146,11 +1182,11 @@ static int ixgbe_set_ringparam(struct net_device *netdev, return -EINVAL; new_tx_count = clamp_t(u32, ring->tx_pending, - IXGBE_MIN_TXD, IXGBE_MAX_TXD); + IXGBE_MIN_TXD, ixgbe_get_max_txd(adapter)); new_tx_count = ALIGN(new_tx_count, IXGBE_REQ_TX_DESCRIPTOR_MULTIPLE); new_rx_count = clamp_t(u32, ring->rx_pending, - IXGBE_MIN_RXD, IXGBE_MAX_RXD); + IXGBE_MIN_RXD, ixgbe_get_max_rxd(adapter)); new_rx_count = ALIGN(new_rx_count, IXGBE_REQ_RX_DESCRIPTOR_MULTIPLE); if ((new_tx_count == adapter->tx_ring_count) && @@ -1960,18 +1996,13 @@ static bool ixgbe_check_lbtest_frame(struct ixgbe_rx_buffer *rx_buffer, unsigned int frame_size) { unsigned char *data; - bool match = true; frame_size >>= 1; data = page_address(rx_buffer->page) + rx_buffer->page_offset; - if (data[3] != 0xFF || - data[frame_size + 10] != 0xBE || - data[frame_size + 12] != 0xAF) - match = false; - - return match; + return data[3] == 0xFF && data[frame_size + 10] == 0xBE && + data[frame_size + 12] == 0xAF; } static u16 ixgbe_clean_test_rings(struct ixgbe_ring *rx_ring, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c index fd3f77a9e28d..0310af851086 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c @@ -1302,7 +1302,7 @@ static void ixgbe_ptp_init_systime(struct ixgbe_adapter *adapter) default: /* Other devices aren't supported */ return; - }; + } IXGBE_WRITE_FLUSH(hw); } diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index be733677bdc8..0aaf70c063da 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -2044,12 +2044,16 @@ static int ixgbevf_vlan_rx_add_vid(struct net_device *netdev, spin_unlock_bh(&adapter->mbx_lock); - /* translate error return types so error makes sense */ - if (err == IXGBE_ERR_MBX) - return -EIO; + if (err) { + netdev_err(netdev, "VF could not set VLAN %d\n", vid); + + /* translate error return types so error makes sense */ + if (err == IXGBE_ERR_MBX) + return -EIO; - if (err == IXGBE_ERR_INVALID_ARGUMENT) - return -EACCES; + if (err == IXGBE_ERR_INVALID_ARGUMENT) + return -EACCES; + } set_bit(vid, adapter->active_vlans); @@ -2070,6 +2074,9 @@ static int ixgbevf_vlan_rx_kill_vid(struct net_device *netdev, spin_unlock_bh(&adapter->mbx_lock); + if (err) + netdev_err(netdev, "Could not remove VLAN %d\n", vid); + clear_bit(vid, adapter->active_vlans); return err; diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index 707993b445d1..3b129a1c3381 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -108,6 +108,7 @@ static char mv643xx_eth_driver_version[] = "1.4"; #define TXQ_COMMAND 0x0048 #define TXQ_FIX_PRIO_CONF 0x004c #define PORT_SERIAL_CONTROL1 0x004c +#define RGMII_EN 0x00000008 #define CLK125_BYPASS_EN 0x00000010 #define TX_BW_RATE 0x0050 #define TX_BW_MTU 0x0058 @@ -2481,6 +2482,7 @@ out_free: for (i = 0; i < mp->rxq_count; i++) rxq_deinit(mp->rxq + i); out: + napi_disable(&mp->napi); free_irq(dev->irq, dev); return err; @@ -2761,6 +2763,8 @@ static int mv643xx_eth_shared_of_add_port(struct platform_device *pdev, mv643xx_eth_property(pnp, "rx-sram-addr", ppd.rx_sram_addr); mv643xx_eth_property(pnp, "rx-sram-size", ppd.rx_sram_size); + of_get_phy_mode(pnp, &ppd.interface); + ppd.phy_node = of_parse_phandle(pnp, "phy-handle", 0); if (!ppd.phy_node) { ppd.phy_addr = MV643XX_ETH_PHY_NONE; @@ -3092,6 +3096,7 @@ static int mv643xx_eth_probe(struct platform_device *pdev) struct mv643xx_eth_private *mp; struct net_device *dev; struct phy_device *phydev = NULL; + u32 psc1r; int err, irq; pd = dev_get_platdata(&pdev->dev); @@ -3119,14 +3124,45 @@ static int mv643xx_eth_probe(struct platform_device *pdev) mp->dev = dev; - /* Kirkwood resets some registers on gated clocks. Especially - * CLK125_BYPASS_EN must be cleared but is not available on - * all other SoCs/System Controllers using this driver. - */ if (of_device_is_compatible(pdev->dev.of_node, - "marvell,kirkwood-eth-port")) - wrlp(mp, PORT_SERIAL_CONTROL1, - rdlp(mp, PORT_SERIAL_CONTROL1) & ~CLK125_BYPASS_EN); + "marvell,kirkwood-eth-port")) { + psc1r = rdlp(mp, PORT_SERIAL_CONTROL1); + + /* Kirkwood resets some registers on gated clocks. Especially + * CLK125_BYPASS_EN must be cleared but is not available on + * all other SoCs/System Controllers using this driver. + */ + psc1r &= ~CLK125_BYPASS_EN; + + /* On Kirkwood with two Ethernet controllers, if both of them + * have RGMII_EN disabled, the first controller will be in GMII + * mode and the second one is effectively disabled, instead of + * two MII interfaces. + * + * To enable GMII in the first controller, the second one must + * also be configured (and may be enabled) with RGMII_EN + * disabled too, even though it cannot be used at all. + */ + switch (pd->interface) { + /* Use internal to denote second controller being disabled */ + case PHY_INTERFACE_MODE_INTERNAL: + case PHY_INTERFACE_MODE_MII: + case PHY_INTERFACE_MODE_GMII: + psc1r &= ~RGMII_EN; + break; + case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_RXID: + case PHY_INTERFACE_MODE_RGMII_TXID: + psc1r |= RGMII_EN; + break; + default: + /* Unknown; don't touch */ + break; + } + + wrlp(mp, PORT_SERIAL_CONTROL1, psc1r); + } /* * Start with a default rate, and if there is a clock, allow diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 05ff3c58087e..c2cb98d24f5c 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -4228,7 +4228,6 @@ static void mvneta_mac_link_up(struct phylink_config *config, } static const struct phylink_mac_ops mvneta_phylink_ops = { - .validate = phylink_generic_validate, .mac_select_pcs = mvneta_mac_select_pcs, .mac_prepare = mvneta_mac_prepare, .mac_config = mvneta_mac_config, diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 116e53172072..d98f7e9a480e 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -6603,7 +6603,6 @@ static void mvpp2_mac_link_down(struct phylink_config *config, } static const struct phylink_mac_ops mvpp2_phylink_ops = { - .validate = phylink_generic_validate, .mac_select_pcs = mvpp2_select_pcs, .mac_prepare = mvpp2_mac_prepare, .mac_config = mvpp2_mac_config, diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c index 9089adcb75f9..1cbfa800a8af 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c @@ -23,6 +23,7 @@ struct workqueue_struct *octep_wq; /* Supported Devices */ static const struct pci_device_id octep_pci_id_tbl[] = { {PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, OCTEP_PCI_DEVICE_ID_CN93_PF)}, + {PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, OCTEP_PCI_DEVICE_ID_CNF95N_PF)}, {0, }, }; MODULE_DEVICE_TABLE(pci, octep_pci_id_tbl); @@ -907,6 +908,18 @@ static void octep_ctrl_mbox_task(struct work_struct *work) } } +static const char *octep_devid_to_str(struct octep_device *oct) +{ + switch (oct->chip_id) { + case OCTEP_PCI_DEVICE_ID_CN93_PF: + return "CN93XX"; + case OCTEP_PCI_DEVICE_ID_CNF95N_PF: + return "CNF95N"; + default: + return "Unsupported"; + } +} + /** * octep_device_setup() - Setup Octeon Device. * @@ -939,9 +952,10 @@ int octep_device_setup(struct octep_device *oct) switch (oct->chip_id) { case OCTEP_PCI_DEVICE_ID_CN93_PF: - dev_info(&pdev->dev, - "Setting up OCTEON CN93XX PF PASS%d.%d\n", - OCTEP_MAJOR_REV(oct), OCTEP_MINOR_REV(oct)); + case OCTEP_PCI_DEVICE_ID_CNF95N_PF: + dev_info(&pdev->dev, "Setting up OCTEON %s PF PASS%d.%d\n", + octep_devid_to_str(oct), OCTEP_MAJOR_REV(oct), + OCTEP_MINOR_REV(oct)); octep_device_setup_cn93_pf(oct); break; default: diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.h b/drivers/net/ethernet/marvell/octeon_ep/octep_main.h index 025626a61383..123ffc13754d 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.h +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.h @@ -21,6 +21,8 @@ #define OCTEP_PCI_DEVICE_ID_CN93_PF 0xB200 #define OCTEP_PCI_DEVICE_ID_CN93_VF 0xB203 +#define OCTEP_PCI_DEVICE_ID_CNF95N_PF 0xB400 //95N PF + #define OCTEP_MAX_QUEUES 63 #define OCTEP_MAX_IQ OCTEP_MAX_QUEUES #define OCTEP_MAX_OQ OCTEP_MAX_QUEUES diff --git a/drivers/net/ethernet/marvell/octeontx2/Kconfig b/drivers/net/ethernet/marvell/octeontx2/Kconfig index e1036b0eb6b1..6b4f640163f7 100644 --- a/drivers/net/ethernet/marvell/octeontx2/Kconfig +++ b/drivers/net/ethernet/marvell/octeontx2/Kconfig @@ -32,10 +32,12 @@ config OCTEONTX2_PF tristate "Marvell OcteonTX2 NIC Physical Function driver" select OCTEONTX2_MBOX select NET_DEVLINK + depends on MACSEC || !MACSEC depends on (64BIT && COMPILE_TEST) || ARM64 select DIMLIB depends on PCI depends on PTP_1588_CLOCK_OPTIONAL + depends on MACSEC || !MACSEC help This driver supports Marvell's OcteonTX2 NIC physical function. diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c index 9ac9e6615ae7..9e10e7471b88 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c @@ -898,6 +898,7 @@ static int otx2_sq_init(struct otx2_nic *pfvf, u16 qidx, u16 sqb_aura) } sq->head = 0; + sq->cons_head = 0; sq->sqe_per_sqb = (pfvf->hw.sqb_size / sq->sqe_size) - 1; sq->num_sqbs = (qset->sqe_cnt + sq->sqe_per_sqb) / sq->sqe_per_sqb; /* Set SQE threshold to 10% of total SQEs */ diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index 892ca88e0cf4..c1ea60bc2630 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -15,6 +15,7 @@ #include <net/ip.h> #include <linux/bpf.h> #include <linux/bpf_trace.h> +#include <linux/bitfield.h> #include "otx2_reg.h" #include "otx2_common.h" @@ -1171,6 +1172,59 @@ int otx2_set_real_num_queues(struct net_device *netdev, } EXPORT_SYMBOL(otx2_set_real_num_queues); +static char *nix_sqoperr_e_str[NIX_SQOPERR_MAX] = { + "NIX_SQOPERR_OOR", + "NIX_SQOPERR_CTX_FAULT", + "NIX_SQOPERR_CTX_POISON", + "NIX_SQOPERR_DISABLED", + "NIX_SQOPERR_SIZE_ERR", + "NIX_SQOPERR_OFLOW", + "NIX_SQOPERR_SQB_NULL", + "NIX_SQOPERR_SQB_FAULT", + "NIX_SQOPERR_SQE_SZ_ZERO", +}; + +static char *nix_mnqerr_e_str[NIX_MNQERR_MAX] = { + "NIX_MNQERR_SQ_CTX_FAULT", + "NIX_MNQERR_SQ_CTX_POISON", + "NIX_MNQERR_SQB_FAULT", + "NIX_MNQERR_SQB_POISON", + "NIX_MNQERR_TOTAL_ERR", + "NIX_MNQERR_LSO_ERR", + "NIX_MNQERR_CQ_QUERY_ERR", + "NIX_MNQERR_MAX_SQE_SIZE_ERR", + "NIX_MNQERR_MAXLEN_ERR", + "NIX_MNQERR_SQE_SIZEM1_ZERO", +}; + +static char *nix_snd_status_e_str[NIX_SND_STATUS_MAX] = { + "NIX_SND_STATUS_GOOD", + "NIX_SND_STATUS_SQ_CTX_FAULT", + "NIX_SND_STATUS_SQ_CTX_POISON", + "NIX_SND_STATUS_SQB_FAULT", + "NIX_SND_STATUS_SQB_POISON", + "NIX_SND_STATUS_HDR_ERR", + "NIX_SND_STATUS_EXT_ERR", + "NIX_SND_STATUS_JUMP_FAULT", + "NIX_SND_STATUS_JUMP_POISON", + "NIX_SND_STATUS_CRC_ERR", + "NIX_SND_STATUS_IMM_ERR", + "NIX_SND_STATUS_SG_ERR", + "NIX_SND_STATUS_MEM_ERR", + "NIX_SND_STATUS_INVALID_SUBDC", + "NIX_SND_STATUS_SUBDC_ORDER_ERR", + "NIX_SND_STATUS_DATA_FAULT", + "NIX_SND_STATUS_DATA_POISON", + "NIX_SND_STATUS_NPC_DROP_ACTION", + "NIX_SND_STATUS_LOCK_VIOL", + "NIX_SND_STATUS_NPC_UCAST_CHAN_ERR", + "NIX_SND_STATUS_NPC_MCAST_CHAN_ERR", + "NIX_SND_STATUS_NPC_MCAST_ABORT", + "NIX_SND_STATUS_NPC_VTAG_PTR_ERR", + "NIX_SND_STATUS_NPC_VTAG_SIZE_ERR", + "NIX_SND_STATUS_SEND_STATS_ERR", +}; + static irqreturn_t otx2_q_intr_handler(int irq, void *data) { struct otx2_nic *pf = data; @@ -1204,46 +1258,67 @@ static irqreturn_t otx2_q_intr_handler(int irq, void *data) /* SQ */ for (qidx = 0; qidx < pf->hw.tot_tx_queues; qidx++) { + u64 sq_op_err_dbg, mnq_err_dbg, snd_err_dbg; + u8 sq_op_err_code, mnq_err_code, snd_err_code; + + /* Below debug registers captures first errors corresponding to + * those registers. We don't have to check against SQ qid as + * these are fatal errors. + */ + ptr = otx2_get_regaddr(pf, NIX_LF_SQ_OP_INT); val = otx2_atomic64_add((qidx << 44), ptr); otx2_write64(pf, NIX_LF_SQ_OP_INT, (qidx << 44) | (val & NIX_SQINT_BITS)); - if (!(val & (NIX_SQINT_BITS | BIT_ULL(42)))) - continue; - if (val & BIT_ULL(42)) { netdev_err(pf->netdev, "SQ%lld: error reading NIX_LF_SQ_OP_INT, NIX_LF_ERR_INT 0x%llx\n", qidx, otx2_read64(pf, NIX_LF_ERR_INT)); - } else { - if (val & BIT_ULL(NIX_SQINT_LMT_ERR)) { - netdev_err(pf->netdev, "SQ%lld: LMT store error NIX_LF_SQ_OP_ERR_DBG:0x%llx", - qidx, - otx2_read64(pf, - NIX_LF_SQ_OP_ERR_DBG)); - otx2_write64(pf, NIX_LF_SQ_OP_ERR_DBG, - BIT_ULL(44)); - } - if (val & BIT_ULL(NIX_SQINT_MNQ_ERR)) { - netdev_err(pf->netdev, "SQ%lld: Meta-descriptor enqueue error NIX_LF_MNQ_ERR_DGB:0x%llx\n", - qidx, - otx2_read64(pf, NIX_LF_MNQ_ERR_DBG)); - otx2_write64(pf, NIX_LF_MNQ_ERR_DBG, - BIT_ULL(44)); - } - if (val & BIT_ULL(NIX_SQINT_SEND_ERR)) { - netdev_err(pf->netdev, "SQ%lld: Send error, NIX_LF_SEND_ERR_DBG 0x%llx", - qidx, - otx2_read64(pf, - NIX_LF_SEND_ERR_DBG)); - otx2_write64(pf, NIX_LF_SEND_ERR_DBG, - BIT_ULL(44)); - } - if (val & BIT_ULL(NIX_SQINT_SQB_ALLOC_FAIL)) - netdev_err(pf->netdev, "SQ%lld: SQB allocation failed", - qidx); + goto done; } + sq_op_err_dbg = otx2_read64(pf, NIX_LF_SQ_OP_ERR_DBG); + if (!(sq_op_err_dbg & BIT(44))) + goto chk_mnq_err_dbg; + + sq_op_err_code = FIELD_GET(GENMASK(7, 0), sq_op_err_dbg); + netdev_err(pf->netdev, "SQ%lld: NIX_LF_SQ_OP_ERR_DBG(%llx) err=%s\n", + qidx, sq_op_err_dbg, nix_sqoperr_e_str[sq_op_err_code]); + + otx2_write64(pf, NIX_LF_SQ_OP_ERR_DBG, BIT_ULL(44)); + + if (sq_op_err_code == NIX_SQOPERR_SQB_NULL) + goto chk_mnq_err_dbg; + + /* Err is not NIX_SQOPERR_SQB_NULL, call aq function to read SQ structure. + * TODO: But we are in irq context. How to call mbox functions which does sleep + */ + +chk_mnq_err_dbg: + mnq_err_dbg = otx2_read64(pf, NIX_LF_MNQ_ERR_DBG); + if (!(mnq_err_dbg & BIT(44))) + goto chk_snd_err_dbg; + + mnq_err_code = FIELD_GET(GENMASK(7, 0), mnq_err_dbg); + netdev_err(pf->netdev, "SQ%lld: NIX_LF_MNQ_ERR_DBG(%llx) err=%s\n", + qidx, mnq_err_dbg, nix_mnqerr_e_str[mnq_err_code]); + otx2_write64(pf, NIX_LF_MNQ_ERR_DBG, BIT_ULL(44)); + +chk_snd_err_dbg: + snd_err_dbg = otx2_read64(pf, NIX_LF_SEND_ERR_DBG); + if (snd_err_dbg & BIT(44)) { + snd_err_code = FIELD_GET(GENMASK(7, 0), snd_err_dbg); + netdev_err(pf->netdev, "SQ%lld: NIX_LF_SND_ERR_DBG:0x%llx err=%s\n", + qidx, snd_err_dbg, nix_snd_status_e_str[snd_err_code]); + otx2_write64(pf, NIX_LF_SEND_ERR_DBG, BIT_ULL(44)); + } + +done: + /* Print values and reset */ + if (val & BIT_ULL(NIX_SQINT_SQB_ALLOC_FAIL)) + netdev_err(pf->netdev, "SQ%lld: SQB allocation failed", + qidx); + schedule_work(&pf->reset_task); } @@ -1898,7 +1973,7 @@ static u16 otx2_select_queue(struct net_device *netdev, struct sk_buff *skb, #endif #ifdef CONFIG_DCB - if (!skb->vlan_present) + if (!skb_vlan_tag_present(skb)) goto pick_tx; vlan_prio = skb->vlan_tci >> 13; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_struct.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_struct.h index aa205a0d158f..fa37b9f312ca 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_struct.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_struct.h @@ -281,4 +281,61 @@ enum nix_sqint_e { BIT_ULL(NIX_SQINT_SEND_ERR) | \ BIT_ULL(NIX_SQINT_SQB_ALLOC_FAIL)) +enum nix_sqoperr_e { + NIX_SQOPERR_OOR = 0, + NIX_SQOPERR_CTX_FAULT = 1, + NIX_SQOPERR_CTX_POISON = 2, + NIX_SQOPERR_DISABLED = 3, + NIX_SQOPERR_SIZE_ERR = 4, + NIX_SQOPERR_OFLOW = 5, + NIX_SQOPERR_SQB_NULL = 6, + NIX_SQOPERR_SQB_FAULT = 7, + NIX_SQOPERR_SQE_SZ_ZERO = 8, + NIX_SQOPERR_MAX, +}; + +enum nix_mnqerr_e { + NIX_MNQERR_SQ_CTX_FAULT = 0, + NIX_MNQERR_SQ_CTX_POISON = 1, + NIX_MNQERR_SQB_FAULT = 2, + NIX_MNQERR_SQB_POISON = 3, + NIX_MNQERR_TOTAL_ERR = 4, + NIX_MNQERR_LSO_ERR = 5, + NIX_MNQERR_CQ_QUERY_ERR = 6, + NIX_MNQERR_MAX_SQE_SIZE_ERR = 7, + NIX_MNQERR_MAXLEN_ERR = 8, + NIX_MNQERR_SQE_SIZEM1_ZERO = 9, + NIX_MNQERR_MAX, +}; + +enum nix_snd_status_e { + NIX_SND_STATUS_GOOD = 0x0, + NIX_SND_STATUS_SQ_CTX_FAULT = 0x1, + NIX_SND_STATUS_SQ_CTX_POISON = 0x2, + NIX_SND_STATUS_SQB_FAULT = 0x3, + NIX_SND_STATUS_SQB_POISON = 0x4, + NIX_SND_STATUS_HDR_ERR = 0x5, + NIX_SND_STATUS_EXT_ERR = 0x6, + NIX_SND_STATUS_JUMP_FAULT = 0x7, + NIX_SND_STATUS_JUMP_POISON = 0x8, + NIX_SND_STATUS_CRC_ERR = 0x9, + NIX_SND_STATUS_IMM_ERR = 0x10, + NIX_SND_STATUS_SG_ERR = 0x11, + NIX_SND_STATUS_MEM_ERR = 0x12, + NIX_SND_STATUS_INVALID_SUBDC = 0x13, + NIX_SND_STATUS_SUBDC_ORDER_ERR = 0x14, + NIX_SND_STATUS_DATA_FAULT = 0x15, + NIX_SND_STATUS_DATA_POISON = 0x16, + NIX_SND_STATUS_NPC_DROP_ACTION = 0x17, + NIX_SND_STATUS_LOCK_VIOL = 0x18, + NIX_SND_STATUS_NPC_UCAST_CHAN_ERR = 0x19, + NIX_SND_STATUS_NPC_MCAST_CHAN_ERR = 0x20, + NIX_SND_STATUS_NPC_MCAST_ABORT = 0x21, + NIX_SND_STATUS_NPC_VTAG_PTR_ERR = 0x22, + NIX_SND_STATUS_NPC_VTAG_SIZE_ERR = 0x23, + NIX_SND_STATUS_SEND_MEM_FAULT = 0x24, + NIX_SND_STATUS_SEND_STATS_ERR = 0x25, + NIX_SND_STATUS_MAX, +}; + #endif /* OTX2_STRUCT_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c index 5ec11d71bf60..ef10aef3cda0 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c @@ -441,6 +441,7 @@ static int otx2_tx_napi_handler(struct otx2_nic *pfvf, struct otx2_cq_queue *cq, int budget) { int tx_pkts = 0, tx_bytes = 0, qidx; + struct otx2_snd_queue *sq; struct nix_cqe_tx_s *cqe; int processed_cqe = 0; @@ -451,6 +452,9 @@ static int otx2_tx_napi_handler(struct otx2_nic *pfvf, 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); if (unlikely(!cqe)) { @@ -458,18 +462,20 @@ process_cqe: return 0; break; } + if (cq->cq_type == CQ_XDP) { - qidx = cq->cq_idx - pfvf->hw.rx_queues; - otx2_xdp_snd_pkt_handler(pfvf, &pfvf->qset.sq[qidx], - cqe); + otx2_xdp_snd_pkt_handler(pfvf, sq, cqe); } else { - otx2_snd_pkt_handler(pfvf, cq, - &pfvf->qset.sq[cq->cint_idx], - cqe, budget, &tx_pkts, &tx_bytes); + otx2_snd_pkt_handler(pfvf, cq, sq, cqe, budget, + &tx_pkts, &tx_bytes); } + cqe->hdr.cqe_type = NIX_XQE_TYPE_INVALID; processed_cqe++; cq->pend_cqe--; + + sq->cons_head++; + sq->cons_head &= (sq->sqe_cnt - 1); } /* Free CQEs to HW */ @@ -1072,17 +1078,17 @@ bool otx2_sq_append_skb(struct net_device *netdev, struct otx2_snd_queue *sq, { struct netdev_queue *txq = netdev_get_tx_queue(netdev, qidx); struct otx2_nic *pfvf = netdev_priv(netdev); - int offset, num_segs, free_sqe; + int offset, num_segs, free_desc; struct nix_sqe_hdr_s *sqe_hdr; - /* Check if there is room for new SQE. - * 'Num of SQBs freed to SQ's pool - SQ's Aura count' - * will give free SQE count. + /* Check if there is enough room between producer + * and consumer index. */ - free_sqe = (sq->num_sqbs - *sq->aura_fc_addr) * sq->sqe_per_sqb; + free_desc = (sq->cons_head - sq->head - 1 + sq->sqe_cnt) & (sq->sqe_cnt - 1); + if (free_desc < sq->sqe_thresh) + return false; - if (free_sqe < sq->sqe_thresh || - free_sqe < otx2_get_sqe_count(pfvf, skb)) + if (free_desc < otx2_get_sqe_count(pfvf, skb)) return false; num_segs = skb_shinfo(skb)->nr_frags + 1; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h index fbe62bbfb789..93cac2c2664c 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h @@ -79,6 +79,7 @@ struct sg_list { struct otx2_snd_queue { u8 aura_id; u16 head; + u16 cons_head; u16 sqe_size; u32 sqe_cnt; u16 num_sqbs; diff --git a/drivers/net/ethernet/marvell/prestera/prestera_devlink.c b/drivers/net/ethernet/marvell/prestera/prestera_devlink.c index 06279cd6da67..84ad05c9f12d 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_devlink.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_devlink.c @@ -445,23 +445,6 @@ void prestera_devlink_port_unregister(struct prestera_port *port) devlink_port_unregister(&port->dl_port); } -void prestera_devlink_port_set(struct prestera_port *port) -{ - devlink_port_type_eth_set(&port->dl_port, port->dev); -} - -void prestera_devlink_port_clear(struct prestera_port *port) -{ - devlink_port_type_clear(&port->dl_port); -} - -struct devlink_port *prestera_devlink_get_port(struct net_device *dev) -{ - struct prestera_port *port = netdev_priv(dev); - - return &port->dl_port; -} - int prestera_devlink_traps_register(struct prestera_switch *sw) { const u32 groups_count = ARRAY_SIZE(prestera_trap_groups_arr); diff --git a/drivers/net/ethernet/marvell/prestera/prestera_devlink.h b/drivers/net/ethernet/marvell/prestera/prestera_devlink.h index b322295bad3a..bf84ad6fd87e 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_devlink.h +++ b/drivers/net/ethernet/marvell/prestera/prestera_devlink.h @@ -15,11 +15,6 @@ void prestera_devlink_unregister(struct prestera_switch *sw); int prestera_devlink_port_register(struct prestera_port *port); void prestera_devlink_port_unregister(struct prestera_port *port); -void prestera_devlink_port_set(struct prestera_port *port); -void prestera_devlink_port_clear(struct prestera_port *port); - -struct devlink_port *prestera_devlink_get_port(struct net_device *dev); - void prestera_devlink_trap_report(struct prestera_port *port, struct sk_buff *skb, u8 cpu_code); int prestera_devlink_traps_register(struct prestera_switch *sw); diff --git a/drivers/net/ethernet/marvell/prestera/prestera_main.c b/drivers/net/ethernet/marvell/prestera/prestera_main.c index 24f9d6024745..f8deaee84398 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_main.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_main.c @@ -360,7 +360,6 @@ static void prestera_pcs_an_restart(struct phylink_pcs *pcs) } static const struct phylink_mac_ops prestera_mac_ops = { - .validate = phylink_generic_validate, .mac_select_pcs = prestera_mac_select_pcs, .mac_config = prestera_mac_config, .mac_link_down = prestera_mac_link_down, @@ -569,7 +568,6 @@ static const struct net_device_ops prestera_netdev_ops = { .ndo_change_mtu = prestera_port_change_mtu, .ndo_get_stats64 = prestera_port_get_stats64, .ndo_set_mac_address = prestera_port_set_mac_address, - .ndo_get_devlink_port = prestera_devlink_get_port, }; int prestera_port_autoneg_set(struct prestera_port *port, u64 link_modes) @@ -644,6 +642,7 @@ static int prestera_port_create(struct prestera_switch *sw, u32 id) dev->netdev_ops = &prestera_netdev_ops; dev->ethtool_ops = &prestera_ethtool_ops; SET_NETDEV_DEV(dev, sw->dev->dev); + SET_NETDEV_DEVLINK_PORT(dev, &port->dl_port); if (port->caps.transceiver != PRESTERA_PORT_TCVR_SFP) netif_carrier_off(dev); @@ -737,8 +736,6 @@ static int prestera_port_create(struct prestera_switch *sw, u32 id) if (err) goto err_register_netdev; - prestera_devlink_port_set(port); - err = prestera_port_sfp_bind(port); if (err) goto err_sfp_bind; @@ -761,7 +758,6 @@ static void prestera_port_destroy(struct prestera_port *port) struct net_device *dev = port->dev; cancel_delayed_work_sync(&port->cached_hw_stats.caching_dw); - prestera_devlink_port_clear(port); unregister_netdev(dev); prestera_port_list_del(port); prestera_devlink_port_unregister(port); diff --git a/drivers/net/ethernet/marvell/prestera/prestera_pci.c b/drivers/net/ethernet/marvell/prestera/prestera_pci.c index 59470d99f522..f328d957b2db 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_pci.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_pci.c @@ -15,12 +15,13 @@ #define PRESTERA_MSG_MAX_SIZE 1500 #define PRESTERA_SUPP_FW_MAJ_VER 4 -#define PRESTERA_SUPP_FW_MIN_VER 0 +#define PRESTERA_SUPP_FW_MIN_VER 1 #define PRESTERA_PREV_FW_MAJ_VER 4 #define PRESTERA_PREV_FW_MIN_VER 0 #define PRESTERA_FW_PATH_FMT "mrvl/prestera/mvsw_prestera_fw-v%u.%u.img" +#define PRESTERA_FW_ARM64_PATH_FMT "mrvl/prestera/mvsw_prestera_fw_arm64-v%u.%u.img" #define PRESTERA_FW_HDR_MAGIC 0x351D9D06 #define PRESTERA_FW_DL_TIMEOUT_MS 50000 @@ -184,6 +185,15 @@ struct prestera_fw_regs { #define PRESTERA_FW_CMD_DEFAULT_WAIT_MS 30000 #define PRESTERA_FW_READY_WAIT_MS 20000 +#define PRESTERA_DEV_ID_AC3X_98DX_55 0xC804 +#define PRESTERA_DEV_ID_AC3X_98DX_65 0xC80C +#define PRESTERA_DEV_ID_ALDRIN2 0xCC1E +#define PRESTERA_DEV_ID_98DX7312M 0x981F +#define PRESTERA_DEV_ID_98DX3500 0x9820 +#define PRESTERA_DEV_ID_98DX3501 0x9826 +#define PRESTERA_DEV_ID_98DX3510 0x9821 +#define PRESTERA_DEV_ID_98DX3520 0x9822 + struct prestera_fw_evtq { u8 __iomem *addr; size_t len; @@ -201,6 +211,7 @@ struct prestera_fw { const struct firmware *bin; struct workqueue_struct *wq; struct prestera_device dev; + struct pci_dev *pci_dev; u8 __iomem *ldr_regs; u8 __iomem *ldr_ring_buf; u32 ldr_buf_len; @@ -689,6 +700,20 @@ static int prestera_fw_hdr_parse(struct prestera_fw *fw) return prestera_fw_rev_check(fw); } +static const char *prestera_fw_path_fmt_get(struct prestera_fw *fw) +{ + switch (fw->pci_dev->device) { + case PRESTERA_DEV_ID_98DX3500: + case PRESTERA_DEV_ID_98DX3501: + case PRESTERA_DEV_ID_98DX3510: + case PRESTERA_DEV_ID_98DX3520: + return PRESTERA_FW_ARM64_PATH_FMT; + + default: + return PRESTERA_FW_PATH_FMT; + } +} + static int prestera_fw_get(struct prestera_fw *fw) { int ver_maj = PRESTERA_SUPP_FW_MAJ_VER; @@ -697,7 +722,7 @@ static int prestera_fw_get(struct prestera_fw *fw) int err; pick_fw_ver: - snprintf(fw_path, sizeof(fw_path), PRESTERA_FW_PATH_FMT, + snprintf(fw_path, sizeof(fw_path), prestera_fw_path_fmt_get(fw), ver_maj, ver_min); err = request_firmware_direct(&fw->bin, fw_path, fw->dev.dev); @@ -774,22 +799,56 @@ out_release: return err; } +static bool prestera_pci_pp_use_bar2(struct pci_dev *pdev) +{ + switch (pdev->device) { + case PRESTERA_DEV_ID_98DX7312M: + case PRESTERA_DEV_ID_98DX3500: + case PRESTERA_DEV_ID_98DX3501: + case PRESTERA_DEV_ID_98DX3510: + case PRESTERA_DEV_ID_98DX3520: + return true; + + default: + return false; + } +} + +static u32 prestera_pci_pp_bar2_offs(struct pci_dev *pdev) +{ + if (pci_resource_len(pdev, 2) == 0x1000000) + return 0x0; + else + return (pci_resource_len(pdev, 2) / 2); +} + +static u32 prestera_pci_fw_bar2_offs(struct pci_dev *pdev) +{ + if (pci_resource_len(pdev, 2) == 0x1000000) + return 0x400000; + else + return 0x0; +} + static int prestera_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { const char *driver_name = dev_driver_string(&pdev->dev); + u8 __iomem *mem_addr, *pp_addr = NULL; struct prestera_fw *fw; int err; err = pcim_enable_device(pdev); - if (err) - return err; + if (err) { + dev_err(&pdev->dev, "pci_enable_device failed\n"); + goto err_pci_enable_device; + } - err = pcim_iomap_regions(pdev, BIT(PRESTERA_PCI_BAR_FW) | - BIT(PRESTERA_PCI_BAR_PP), - pci_name(pdev)); - if (err) - return err; + err = pci_request_regions(pdev, driver_name); + if (err) { + dev_err(&pdev->dev, "pci_request_regions failed\n"); + goto err_pci_request_regions; + } err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(30)); if (err) { @@ -797,6 +856,26 @@ static int prestera_pci_probe(struct pci_dev *pdev, goto err_dma_mask; } + mem_addr = pcim_iomap(pdev, 2, 0); + if (!mem_addr) { + dev_err(&pdev->dev, "pci mem ioremap failed\n"); + err = -EIO; + goto err_mem_ioremap; + } + + /* AC5X devices use second half of BAR2 */ + if (prestera_pci_pp_use_bar2(pdev)) { + pp_addr = mem_addr + prestera_pci_pp_bar2_offs(pdev); + mem_addr = mem_addr + prestera_pci_fw_bar2_offs(pdev); + } else { + pp_addr = pcim_iomap(pdev, 4, 0); + if (!pp_addr) { + dev_err(&pdev->dev, "pp regs ioremap failed\n"); + err = -EIO; + goto err_pp_ioremap; + } + } + pci_set_master(pdev); fw = devm_kzalloc(&pdev->dev, sizeof(*fw), GFP_KERNEL); @@ -805,8 +884,9 @@ static int prestera_pci_probe(struct pci_dev *pdev, goto err_pci_dev_alloc; } - fw->dev.ctl_regs = pcim_iomap_table(pdev)[PRESTERA_PCI_BAR_FW]; - fw->dev.pp_regs = pcim_iomap_table(pdev)[PRESTERA_PCI_BAR_PP]; + fw->pci_dev = pdev; + fw->dev.ctl_regs = mem_addr; + fw->dev.pp_regs = pp_addr; fw->dev.dev = &pdev->dev; pci_set_drvdata(pdev, fw); @@ -854,7 +934,12 @@ err_wq_alloc: prestera_fw_uninit(fw); err_prestera_fw_init: err_pci_dev_alloc: +err_pp_ioremap: +err_mem_ioremap: err_dma_mask: + pci_release_regions(pdev); +err_pci_request_regions: +err_pci_enable_device: return err; } @@ -867,12 +952,18 @@ static void prestera_pci_remove(struct pci_dev *pdev) pci_free_irq_vectors(pdev); destroy_workqueue(fw->wq); prestera_fw_uninit(fw); + pci_release_regions(pdev); } static const struct pci_device_id prestera_pci_devices[] = { - { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0xC804) }, - { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0xC80C) }, - { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0xCC1E) }, + { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, PRESTERA_DEV_ID_AC3X_98DX_55) }, + { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, PRESTERA_DEV_ID_AC3X_98DX_65) }, + { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, PRESTERA_DEV_ID_ALDRIN2) }, + { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, PRESTERA_DEV_ID_98DX7312M) }, + { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, PRESTERA_DEV_ID_98DX3500) }, + { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, PRESTERA_DEV_ID_98DX3501) }, + { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, PRESTERA_DEV_ID_98DX3510) }, + { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, PRESTERA_DEV_ID_98DX3520) }, { } }; MODULE_DEVICE_TABLE(pci, prestera_pci_devices); diff --git a/drivers/net/ethernet/marvell/prestera/prestera_rxtx.c b/drivers/net/ethernet/marvell/prestera/prestera_rxtx.c index 42ee963e9f75..9277a8fd1339 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_rxtx.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_rxtx.c @@ -776,6 +776,7 @@ tx_done: int prestera_rxtx_switch_init(struct prestera_switch *sw) { struct prestera_rxtx *rxtx; + int err; rxtx = kzalloc(sizeof(*rxtx), GFP_KERNEL); if (!rxtx) @@ -783,7 +784,11 @@ int prestera_rxtx_switch_init(struct prestera_switch *sw) sw->rxtx = rxtx; - return prestera_sdma_switch_init(sw); + err = prestera_sdma_switch_init(sw); + if (err) + kfree(rxtx); + + return err; } void prestera_rxtx_switch_fini(struct prestera_switch *sw) diff --git a/drivers/net/ethernet/mediatek/Makefile b/drivers/net/ethernet/mediatek/Makefile index 45ba0970504a..8e0c61c33ff8 100644 --- a/drivers/net/ethernet/mediatek/Makefile +++ b/drivers/net/ethernet/mediatek/Makefile @@ -5,7 +5,7 @@ obj-$(CONFIG_NET_MEDIATEK_SOC) += mtk_eth.o mtk_eth-y := mtk_eth_soc.o mtk_sgmii.o mtk_eth_path.o mtk_ppe.o mtk_ppe_debugfs.o mtk_ppe_offload.o -mtk_eth-$(CONFIG_NET_MEDIATEK_SOC_WED) += mtk_wed.o +mtk_eth-$(CONFIG_NET_MEDIATEK_SOC_WED) += mtk_wed.o mtk_wed_mcu.o mtk_wed_wo.o ifdef CONFIG_DEBUG_FS mtk_eth-$(CONFIG_NET_MEDIATEK_SOC_WED) += mtk_wed_debugfs.o endif diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 789268b15106..1cf76fd7afbc 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -653,7 +653,6 @@ static void mtk_mac_link_up(struct phylink_config *config, } static const struct phylink_mac_ops mtk_phylink_ops = { - .validate = phylink_generic_validate, .mac_select_pcs = mtk_mac_select_pcs, .mac_pcs_get_state = mtk_mac_pcs_get_state, .mac_config = mtk_mac_config, diff --git a/drivers/net/ethernet/mediatek/mtk_star_emac.c b/drivers/net/ethernet/mediatek/mtk_star_emac.c index 7e890f81148e..7050351250b7 100644 --- a/drivers/net/ethernet/mediatek/mtk_star_emac.c +++ b/drivers/net/ethernet/mediatek/mtk_star_emac.c @@ -1026,6 +1026,8 @@ static int mtk_star_enable(struct net_device *ndev) return 0; err_free_irq: + napi_disable(&priv->rx_napi); + napi_disable(&priv->tx_napi); free_irq(ndev->irq, ndev); err_free_skbs: mtk_star_free_rx_skbs(priv); diff --git a/drivers/net/ethernet/mediatek/mtk_wed.c b/drivers/net/ethernet/mediatek/mtk_wed.c index 65e01bf4b4d2..7d8842378c2b 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed.c +++ b/drivers/net/ethernet/mediatek/mtk_wed.c @@ -9,6 +9,7 @@ #include <linux/skbuff.h> #include <linux/of_platform.h> #include <linux/of_address.h> +#include <linux/of_reserved_mem.h> #include <linux/mfd/syscon.h> #include <linux/debugfs.h> #include <linux/soc/mediatek/mtk_wed.h> @@ -16,12 +17,14 @@ #include "mtk_wed_regs.h" #include "mtk_wed.h" #include "mtk_ppe.h" +#include "mtk_wed_wo.h" #define MTK_PCIE_BASE(n) (0x1a143000 + (n) * 0x2000) #define MTK_WED_PKT_SIZE 1900 #define MTK_WED_BUF_SIZE 2048 #define MTK_WED_BUF_PER_PAGE (PAGE_SIZE / 2048) +#define MTK_WED_RX_RING_SIZE 1536 #define MTK_WED_TX_RING_SIZE 2048 #define MTK_WED_WDMA_RING_SIZE 1024 @@ -30,6 +33,10 @@ #define MTK_WED_PER_GROUP_PKT 128 #define MTK_WED_FBUF_SIZE 128 +#define MTK_WED_MIOD_CNT 16 +#define MTK_WED_FB_CMD_CNT 1024 +#define MTK_WED_RRO_QUE_CNT 8192 +#define MTK_WED_MIOD_ENTRY_CNT 128 static struct mtk_wed_hw *hw_list[2]; static DEFINE_MUTEX(hw_lock); @@ -64,12 +71,76 @@ wdma_set(struct mtk_wed_device *dev, u32 reg, u32 mask) wdma_m32(dev, reg, 0, mask); } +static void +wdma_clr(struct mtk_wed_device *dev, u32 reg, u32 mask) +{ + wdma_m32(dev, reg, mask, 0); +} + +static u32 +wifi_r32(struct mtk_wed_device *dev, u32 reg) +{ + return readl(dev->wlan.base + reg); +} + +static void +wifi_w32(struct mtk_wed_device *dev, u32 reg, u32 val) +{ + writel(val, dev->wlan.base + reg); +} + static u32 mtk_wed_read_reset(struct mtk_wed_device *dev) { return wed_r32(dev, MTK_WED_RESET); } +static u32 +mtk_wdma_read_reset(struct mtk_wed_device *dev) +{ + return wdma_r32(dev, MTK_WDMA_GLO_CFG); +} + +static void +mtk_wdma_rx_reset(struct mtk_wed_device *dev) +{ + u32 status, mask = MTK_WDMA_GLO_CFG_RX_DMA_BUSY; + int i; + + wdma_clr(dev, MTK_WDMA_GLO_CFG, MTK_WDMA_GLO_CFG_RX_DMA_EN); + if (readx_poll_timeout(mtk_wdma_read_reset, dev, status, + !(status & mask), 0, 1000)) + dev_err(dev->hw->dev, "rx reset failed\n"); + + for (i = 0; i < ARRAY_SIZE(dev->rx_wdma); i++) { + if (dev->rx_wdma[i].desc) + continue; + + wdma_w32(dev, + MTK_WDMA_RING_RX(i) + MTK_WED_RING_OFS_CPU_IDX, 0); + } +} + +static void +mtk_wdma_tx_reset(struct mtk_wed_device *dev) +{ + u32 status, mask = MTK_WDMA_GLO_CFG_TX_DMA_BUSY; + int i; + + wdma_clr(dev, MTK_WDMA_GLO_CFG, MTK_WDMA_GLO_CFG_TX_DMA_EN); + if (readx_poll_timeout(mtk_wdma_read_reset, dev, status, + !(status & mask), 0, 1000)) + dev_err(dev->hw->dev, "tx reset failed\n"); + + for (i = 0; i < ARRAY_SIZE(dev->tx_wdma); i++) { + if (dev->tx_wdma[i].desc) + continue; + + wdma_w32(dev, + MTK_WDMA_RING_TX(i) + MTK_WED_RING_OFS_CPU_IDX, 0); + } +} + static void mtk_wed_reset(struct mtk_wed_device *dev, u32 mask) { @@ -81,6 +152,54 @@ mtk_wed_reset(struct mtk_wed_device *dev, u32 mask) WARN_ON_ONCE(1); } +static u32 +mtk_wed_wo_read_status(struct mtk_wed_device *dev) +{ + return wed_r32(dev, MTK_WED_SCR0 + 4 * MTK_WED_DUMMY_CR_WO_STATUS); +} + +static void +mtk_wed_wo_reset(struct mtk_wed_device *dev) +{ + struct mtk_wed_wo *wo = dev->hw->wed_wo; + u8 state = MTK_WED_WO_STATE_DISABLE; + void __iomem *reg; + u32 val; + + mtk_wdma_tx_reset(dev); + mtk_wed_reset(dev, MTK_WED_RESET_WED); + + mtk_wed_mcu_send_msg(wo, MTK_WED_MODULE_ID_WO, + MTK_WED_WO_CMD_CHANGE_STATE, &state, + sizeof(state), false); + + if (readx_poll_timeout(mtk_wed_wo_read_status, dev, val, + val == MTK_WED_WOIF_DISABLE_DONE, + 100, MTK_WOCPU_TIMEOUT)) + dev_err(dev->hw->dev, "failed to disable wed-wo\n"); + + reg = ioremap(MTK_WED_WO_CPU_MCUSYS_RESET_ADDR, 4); + + val = readl(reg); + switch (dev->hw->index) { + case 0: + val |= MTK_WED_WO_CPU_WO0_MCUSYS_RESET_MASK; + writel(val, reg); + val &= ~MTK_WED_WO_CPU_WO0_MCUSYS_RESET_MASK; + writel(val, reg); + break; + case 1: + val |= MTK_WED_WO_CPU_WO1_MCUSYS_RESET_MASK; + writel(val, reg); + val &= ~MTK_WED_WO_CPU_WO1_MCUSYS_RESET_MASK; + writel(val, reg); + break; + default: + break; + } + iounmap(reg); +} + static struct mtk_wed_hw * mtk_wed_assign(struct mtk_wed_device *dev) { @@ -115,7 +234,7 @@ out: } static int -mtk_wed_buffer_alloc(struct mtk_wed_device *dev) +mtk_wed_tx_buffer_alloc(struct mtk_wed_device *dev) { struct mtk_wdma_desc *desc; dma_addr_t desc_phys; @@ -132,16 +251,16 @@ mtk_wed_buffer_alloc(struct mtk_wed_device *dev) if (!page_list) return -ENOMEM; - dev->buf_ring.size = ring_size; - dev->buf_ring.pages = page_list; + dev->tx_buf_ring.size = ring_size; + dev->tx_buf_ring.pages = page_list; desc = dma_alloc_coherent(dev->hw->dev, ring_size * sizeof(*desc), &desc_phys, GFP_KERNEL); if (!desc) return -ENOMEM; - dev->buf_ring.desc = desc; - dev->buf_ring.desc_phys = desc_phys; + dev->tx_buf_ring.desc = desc; + dev->tx_buf_ring.desc_phys = desc_phys; for (i = 0, page_idx = 0; i < ring_size; i += MTK_WED_BUF_PER_PAGE) { dma_addr_t page_phys, buf_phys; @@ -202,10 +321,10 @@ mtk_wed_buffer_alloc(struct mtk_wed_device *dev) } static void -mtk_wed_free_buffer(struct mtk_wed_device *dev) +mtk_wed_free_tx_buffer(struct mtk_wed_device *dev) { - struct mtk_wdma_desc *desc = dev->buf_ring.desc; - void **page_list = dev->buf_ring.pages; + struct mtk_wdma_desc *desc = dev->tx_buf_ring.desc; + void **page_list = dev->tx_buf_ring.pages; int page_idx; int i; @@ -215,7 +334,8 @@ mtk_wed_free_buffer(struct mtk_wed_device *dev) if (!desc) goto free_pagelist; - for (i = 0, page_idx = 0; i < dev->buf_ring.size; i += MTK_WED_BUF_PER_PAGE) { + for (i = 0, page_idx = 0; i < dev->tx_buf_ring.size; + i += MTK_WED_BUF_PER_PAGE) { void *page = page_list[page_idx++]; dma_addr_t buf_addr; @@ -228,13 +348,59 @@ mtk_wed_free_buffer(struct mtk_wed_device *dev) __free_page(page); } - dma_free_coherent(dev->hw->dev, dev->buf_ring.size * sizeof(*desc), - desc, dev->buf_ring.desc_phys); + dma_free_coherent(dev->hw->dev, dev->tx_buf_ring.size * sizeof(*desc), + desc, dev->tx_buf_ring.desc_phys); free_pagelist: kfree(page_list); } +static int +mtk_wed_rx_buffer_alloc(struct mtk_wed_device *dev) +{ + struct mtk_rxbm_desc *desc; + dma_addr_t desc_phys; + + dev->rx_buf_ring.size = dev->wlan.rx_nbuf; + desc = dma_alloc_coherent(dev->hw->dev, + dev->wlan.rx_nbuf * sizeof(*desc), + &desc_phys, GFP_KERNEL); + if (!desc) + return -ENOMEM; + + dev->rx_buf_ring.desc = desc; + dev->rx_buf_ring.desc_phys = desc_phys; + dev->wlan.init_rx_buf(dev, dev->wlan.rx_npkt); + + return 0; +} + +static void +mtk_wed_free_rx_buffer(struct mtk_wed_device *dev) +{ + struct mtk_rxbm_desc *desc = dev->rx_buf_ring.desc; + + if (!desc) + return; + + dev->wlan.release_rx_buf(dev); + dma_free_coherent(dev->hw->dev, dev->rx_buf_ring.size * sizeof(*desc), + desc, dev->rx_buf_ring.desc_phys); +} + +static void +mtk_wed_rx_buffer_hw_init(struct mtk_wed_device *dev) +{ + wed_w32(dev, MTK_WED_RX_BM_RX_DMAD, + FIELD_PREP(MTK_WED_RX_BM_RX_DMAD_SDL0, dev->wlan.rx_size)); + wed_w32(dev, MTK_WED_RX_BM_BASE, dev->rx_buf_ring.desc_phys); + wed_w32(dev, MTK_WED_RX_BM_INIT_PTR, MTK_WED_RX_BM_INIT_SW_TAIL | + FIELD_PREP(MTK_WED_RX_BM_SW_TAIL, dev->wlan.rx_npkt)); + wed_w32(dev, MTK_WED_RX_BM_DYN_ALLOC_TH, + FIELD_PREP(MTK_WED_RX_BM_DYN_ALLOC_TH_H, 0xffff)); + wed_set(dev, MTK_WED_CTRL, MTK_WED_CTRL_WED_RX_BM_EN); +} + static void mtk_wed_free_ring(struct mtk_wed_device *dev, struct mtk_wed_ring *ring) { @@ -246,14 +412,21 @@ mtk_wed_free_ring(struct mtk_wed_device *dev, struct mtk_wed_ring *ring) } static void +mtk_wed_free_rx_rings(struct mtk_wed_device *dev) +{ + mtk_wed_free_rx_buffer(dev); + mtk_wed_free_ring(dev, &dev->rro.ring); +} + +static void mtk_wed_free_tx_rings(struct mtk_wed_device *dev) { int i; for (i = 0; i < ARRAY_SIZE(dev->tx_ring); i++) mtk_wed_free_ring(dev, &dev->tx_ring[i]); - for (i = 0; i < ARRAY_SIZE(dev->tx_wdma); i++) - mtk_wed_free_ring(dev, &dev->tx_wdma[i]); + for (i = 0; i < ARRAY_SIZE(dev->rx_wdma); i++) + mtk_wed_free_ring(dev, &dev->rx_wdma[i]); } static void @@ -290,6 +463,38 @@ mtk_wed_set_512_support(struct mtk_wed_device *dev, bool enable) } } +#define MTK_WFMDA_RX_DMA_EN BIT(2) +static void +mtk_wed_check_wfdma_rx_fill(struct mtk_wed_device *dev, int idx) +{ + u32 val; + int i; + + if (!(dev->rx_ring[idx].flags & MTK_WED_RING_CONFIGURED)) + return; /* queue is not configured by mt76 */ + + for (i = 0; i < 3; i++) { + u32 cur_idx; + + cur_idx = wed_r32(dev, + MTK_WED_WPDMA_RING_RX_DATA(idx) + + MTK_WED_RING_OFS_CPU_IDX); + if (cur_idx == MTK_WED_RX_RING_SIZE - 1) + break; + + usleep_range(100000, 200000); + } + + if (i == 3) { + dev_err(dev->hw->dev, "rx dma enable failed\n"); + return; + } + + val = wifi_r32(dev, dev->wlan.wpdma_rx_glo - dev->wlan.phy_base) | + MTK_WFMDA_RX_DMA_EN; + wifi_w32(dev, dev->wlan.wpdma_rx_glo - dev->wlan.phy_base, val); +} + static void mtk_wed_dma_disable(struct mtk_wed_device *dev) { @@ -303,20 +508,25 @@ mtk_wed_dma_disable(struct mtk_wed_device *dev) MTK_WED_GLO_CFG_TX_DMA_EN | MTK_WED_GLO_CFG_RX_DMA_EN); - wdma_m32(dev, MTK_WDMA_GLO_CFG, + wdma_clr(dev, MTK_WDMA_GLO_CFG, MTK_WDMA_GLO_CFG_TX_DMA_EN | MTK_WDMA_GLO_CFG_RX_INFO1_PRERES | - MTK_WDMA_GLO_CFG_RX_INFO2_PRERES, 0); + MTK_WDMA_GLO_CFG_RX_INFO2_PRERES); if (dev->hw->version == 1) { regmap_write(dev->hw->mirror, dev->hw->index * 4, 0); - wdma_m32(dev, MTK_WDMA_GLO_CFG, - MTK_WDMA_GLO_CFG_RX_INFO3_PRERES, 0); + wdma_clr(dev, MTK_WDMA_GLO_CFG, + MTK_WDMA_GLO_CFG_RX_INFO3_PRERES); } else { wed_clr(dev, MTK_WED_WPDMA_GLO_CFG, MTK_WED_WPDMA_GLO_CFG_RX_DRV_R0_PKT_PROC | MTK_WED_WPDMA_GLO_CFG_RX_DRV_R0_CRX_SYNC); + wed_clr(dev, MTK_WED_WPDMA_RX_D_GLO_CFG, + MTK_WED_WPDMA_RX_D_RX_DRV_EN); + wed_clr(dev, MTK_WED_WDMA_GLO_CFG, + MTK_WED_WDMA_GLO_CFG_TX_DDONE_CHK); + mtk_wed_set_512_support(dev, false); } } @@ -337,6 +547,13 @@ mtk_wed_stop(struct mtk_wed_device *dev) wdma_w32(dev, MTK_WDMA_INT_MASK, 0); wdma_w32(dev, MTK_WDMA_INT_GRP2, 0); wed_w32(dev, MTK_WED_WPDMA_INT_MASK, 0); + + if (dev->hw->version == 1) + return; + + wed_w32(dev, MTK_WED_EXT_INT_MASK1, 0); + wed_w32(dev, MTK_WED_EXT_INT_MASK2, 0); + wed_clr(dev, MTK_WED_CTRL, MTK_WED_CTRL_WED_RX_BM_EN); } static void @@ -352,10 +569,22 @@ mtk_wed_detach(struct mtk_wed_device *dev) wdma_w32(dev, MTK_WDMA_RESET_IDX, 0); mtk_wed_reset(dev, MTK_WED_RESET_WED); + if (mtk_wed_get_rx_capa(dev)) { + wdma_clr(dev, MTK_WDMA_GLO_CFG, MTK_WDMA_GLO_CFG_TX_DMA_EN); + wdma_w32(dev, MTK_WDMA_RESET_IDX, MTK_WDMA_RESET_IDX_TX); + wdma_w32(dev, MTK_WDMA_RESET_IDX, 0); + } - mtk_wed_free_buffer(dev); + mtk_wed_free_tx_buffer(dev); mtk_wed_free_tx_rings(dev); + if (mtk_wed_get_rx_capa(dev)) { + mtk_wed_wo_reset(dev); + mtk_wed_free_rx_rings(dev); + mtk_wed_wo_deinit(hw); + mtk_wdma_rx_reset(dev); + } + if (dev->wlan.bus_type == MTK_WED_BUS_PCIE) { struct device_node *wlan_node; @@ -431,10 +660,12 @@ mtk_wed_set_wpdma(struct mtk_wed_device *dev) } else { mtk_wed_bus_init(dev); - wed_w32(dev, MTK_WED_WPDMA_CFG_BASE, dev->wlan.wpdma_int); - wed_w32(dev, MTK_WED_WPDMA_CFG_INT_MASK, dev->wlan.wpdma_mask); - wed_w32(dev, MTK_WED_WPDMA_CFG_TX, dev->wlan.wpdma_tx); - wed_w32(dev, MTK_WED_WPDMA_CFG_TX_FREE, dev->wlan.wpdma_txfree); + wed_w32(dev, MTK_WED_WPDMA_CFG_BASE, dev->wlan.wpdma_int); + wed_w32(dev, MTK_WED_WPDMA_CFG_INT_MASK, dev->wlan.wpdma_mask); + wed_w32(dev, MTK_WED_WPDMA_CFG_TX, dev->wlan.wpdma_tx); + wed_w32(dev, MTK_WED_WPDMA_CFG_TX_FREE, dev->wlan.wpdma_txfree); + wed_w32(dev, MTK_WED_WPDMA_RX_GLO_CFG, dev->wlan.wpdma_rx_glo); + wed_w32(dev, MTK_WED_WPDMA_RX_RING, dev->wlan.wpdma_rx); } } @@ -484,6 +715,132 @@ mtk_wed_hw_init_early(struct mtk_wed_device *dev) } } +static int +mtk_wed_rro_ring_alloc(struct mtk_wed_device *dev, struct mtk_wed_ring *ring, + int size) +{ + ring->desc = dma_alloc_coherent(dev->hw->dev, + size * sizeof(*ring->desc), + &ring->desc_phys, GFP_KERNEL); + if (!ring->desc) + return -ENOMEM; + + ring->desc_size = sizeof(*ring->desc); + ring->size = size; + memset(ring->desc, 0, size); + + return 0; +} + +#define MTK_WED_MIOD_COUNT (MTK_WED_MIOD_ENTRY_CNT * MTK_WED_MIOD_CNT) +static int +mtk_wed_rro_alloc(struct mtk_wed_device *dev) +{ + struct reserved_mem *rmem; + struct device_node *np; + int index; + + index = of_property_match_string(dev->hw->node, "memory-region-names", + "wo-dlm"); + if (index < 0) + return index; + + np = of_parse_phandle(dev->hw->node, "memory-region", index); + if (!np) + return -ENODEV; + + rmem = of_reserved_mem_lookup(np); + of_node_put(np); + + if (!rmem) + return -ENODEV; + + dev->rro.miod_phys = rmem->base; + dev->rro.fdbk_phys = MTK_WED_MIOD_COUNT + dev->rro.miod_phys; + + return mtk_wed_rro_ring_alloc(dev, &dev->rro.ring, + MTK_WED_RRO_QUE_CNT); +} + +static int +mtk_wed_rro_cfg(struct mtk_wed_device *dev) +{ + struct mtk_wed_wo *wo = dev->hw->wed_wo; + struct { + struct { + __le32 base; + __le32 cnt; + __le32 unit; + } ring[2]; + __le32 wed; + u8 version; + } req = { + .ring[0] = { + .base = cpu_to_le32(MTK_WED_WOCPU_VIEW_MIOD_BASE), + .cnt = cpu_to_le32(MTK_WED_MIOD_CNT), + .unit = cpu_to_le32(MTK_WED_MIOD_ENTRY_CNT), + }, + .ring[1] = { + .base = cpu_to_le32(MTK_WED_WOCPU_VIEW_MIOD_BASE + + MTK_WED_MIOD_COUNT), + .cnt = cpu_to_le32(MTK_WED_FB_CMD_CNT), + .unit = cpu_to_le32(4), + }, + }; + + return mtk_wed_mcu_send_msg(wo, MTK_WED_MODULE_ID_WO, + MTK_WED_WO_CMD_WED_CFG, + &req, sizeof(req), true); +} + +static void +mtk_wed_rro_hw_init(struct mtk_wed_device *dev) +{ + wed_w32(dev, MTK_WED_RROQM_MIOD_CFG, + FIELD_PREP(MTK_WED_RROQM_MIOD_MID_DW, 0x70 >> 2) | + FIELD_PREP(MTK_WED_RROQM_MIOD_MOD_DW, 0x10 >> 2) | + FIELD_PREP(MTK_WED_RROQM_MIOD_ENTRY_DW, + MTK_WED_MIOD_ENTRY_CNT >> 2)); + + wed_w32(dev, MTK_WED_RROQM_MIOD_CTRL0, dev->rro.miod_phys); + wed_w32(dev, MTK_WED_RROQM_MIOD_CTRL1, + FIELD_PREP(MTK_WED_RROQM_MIOD_CNT, MTK_WED_MIOD_CNT)); + wed_w32(dev, MTK_WED_RROQM_FDBK_CTRL0, dev->rro.fdbk_phys); + wed_w32(dev, MTK_WED_RROQM_FDBK_CTRL1, + FIELD_PREP(MTK_WED_RROQM_FDBK_CNT, MTK_WED_FB_CMD_CNT)); + wed_w32(dev, MTK_WED_RROQM_FDBK_CTRL2, 0); + wed_w32(dev, MTK_WED_RROQ_BASE_L, dev->rro.ring.desc_phys); + + wed_set(dev, MTK_WED_RROQM_RST_IDX, + MTK_WED_RROQM_RST_IDX_MIOD | + MTK_WED_RROQM_RST_IDX_FDBK); + + wed_w32(dev, MTK_WED_RROQM_RST_IDX, 0); + wed_w32(dev, MTK_WED_RROQM_MIOD_CTRL2, MTK_WED_MIOD_CNT - 1); + wed_set(dev, MTK_WED_CTRL, MTK_WED_CTRL_RX_RRO_QM_EN); +} + +static void +mtk_wed_route_qm_hw_init(struct mtk_wed_device *dev) +{ + wed_w32(dev, MTK_WED_RESET, MTK_WED_RESET_RX_ROUTE_QM); + + for (;;) { + usleep_range(100, 200); + if (!(wed_r32(dev, MTK_WED_RESET) & MTK_WED_RESET_RX_ROUTE_QM)) + break; + } + + /* configure RX_ROUTE_QM */ + wed_clr(dev, MTK_WED_RTQM_GLO_CFG, MTK_WED_RTQM_Q_RST); + wed_clr(dev, MTK_WED_RTQM_GLO_CFG, MTK_WED_RTQM_TXDMAD_FPORT); + wed_set(dev, MTK_WED_RTQM_GLO_CFG, + FIELD_PREP(MTK_WED_RTQM_TXDMAD_FPORT, 0x3 + dev->hw->index)); + wed_clr(dev, MTK_WED_RTQM_GLO_CFG, MTK_WED_RTQM_Q_RST); + /* enable RX_ROUTE_QM */ + wed_set(dev, MTK_WED_CTRL, MTK_WED_CTRL_RX_ROUTE_QM_EN); +} + static void mtk_wed_hw_init(struct mtk_wed_device *dev) { @@ -495,11 +852,11 @@ mtk_wed_hw_init(struct mtk_wed_device *dev) wed_w32(dev, MTK_WED_TX_BM_CTRL, MTK_WED_TX_BM_CTRL_PAUSE | FIELD_PREP(MTK_WED_TX_BM_CTRL_VLD_GRP_NUM, - dev->buf_ring.size / 128) | + dev->tx_buf_ring.size / 128) | FIELD_PREP(MTK_WED_TX_BM_CTRL_RSV_GRP_NUM, MTK_WED_TX_RING_SIZE / 256)); - wed_w32(dev, MTK_WED_TX_BM_BASE, dev->buf_ring.desc_phys); + wed_w32(dev, MTK_WED_TX_BM_BASE, dev->tx_buf_ring.desc_phys); wed_w32(dev, MTK_WED_TX_BM_BUF_LEN, MTK_WED_PKT_SIZE); @@ -526,9 +883,9 @@ mtk_wed_hw_init(struct mtk_wed_device *dev) wed_w32(dev, MTK_WED_TX_TKID_CTRL, MTK_WED_TX_TKID_CTRL_PAUSE | FIELD_PREP(MTK_WED_TX_TKID_CTRL_VLD_GRP_NUM, - dev->buf_ring.size / 128) | + dev->tx_buf_ring.size / 128) | FIELD_PREP(MTK_WED_TX_TKID_CTRL_RSV_GRP_NUM, - dev->buf_ring.size / 128)); + dev->tx_buf_ring.size / 128)); wed_w32(dev, MTK_WED_TX_TKID_DYN_THR, FIELD_PREP(MTK_WED_TX_TKID_DYN_THR_LO, 0) | MTK_WED_TX_TKID_DYN_THR_HI); @@ -536,18 +893,28 @@ mtk_wed_hw_init(struct mtk_wed_device *dev) mtk_wed_reset(dev, MTK_WED_RESET_TX_BM); - if (dev->hw->version == 1) + if (dev->hw->version == 1) { wed_set(dev, MTK_WED_CTRL, MTK_WED_CTRL_WED_TX_BM_EN | MTK_WED_CTRL_WED_TX_FREE_AGENT_EN); - else + } else { wed_clr(dev, MTK_WED_TX_TKID_CTRL, MTK_WED_TX_TKID_CTRL_PAUSE); + /* rx hw init */ + wed_w32(dev, MTK_WED_WPDMA_RX_D_RST_IDX, + MTK_WED_WPDMA_RX_D_RST_CRX_IDX | + MTK_WED_WPDMA_RX_D_RST_DRV_IDX); + wed_w32(dev, MTK_WED_WPDMA_RX_D_RST_IDX, 0); + + mtk_wed_rx_buffer_hw_init(dev); + mtk_wed_rro_hw_init(dev); + mtk_wed_route_qm_hw_init(dev); + } wed_clr(dev, MTK_WED_TX_BM_CTRL, MTK_WED_TX_BM_CTRL_PAUSE); } static void -mtk_wed_ring_reset(struct mtk_wed_ring *ring, int size) +mtk_wed_ring_reset(struct mtk_wed_ring *ring, int size, bool tx) { void *head = (void *)ring->desc; int i; @@ -557,7 +924,10 @@ mtk_wed_ring_reset(struct mtk_wed_ring *ring, int size) desc = (struct mtk_wdma_desc *)(head + i * ring->desc_size); desc->buf0 = 0; - desc->ctrl = cpu_to_le32(MTK_WDMA_DESC_CTRL_DMA_DONE); + if (tx) + desc->ctrl = cpu_to_le32(MTK_WDMA_DESC_CTRL_DMA_DONE); + else + desc->ctrl = cpu_to_le32(MTK_WFDMA_DESC_CTRL_TO_HOST); desc->buf1 = 0; desc->info = 0; } @@ -613,7 +983,8 @@ mtk_wed_reset_dma(struct mtk_wed_device *dev) if (!dev->tx_ring[i].desc) continue; - mtk_wed_ring_reset(&dev->tx_ring[i], MTK_WED_TX_RING_SIZE); + mtk_wed_ring_reset(&dev->tx_ring[i], MTK_WED_TX_RING_SIZE, + true); } if (mtk_wed_poll_busy(dev)) @@ -631,6 +1002,9 @@ mtk_wed_reset_dma(struct mtk_wed_device *dev) wdma_w32(dev, MTK_WDMA_RESET_IDX, MTK_WDMA_RESET_IDX_RX); wdma_w32(dev, MTK_WDMA_RESET_IDX, 0); + if (mtk_wed_get_rx_capa(dev)) + mtk_wdma_rx_reset(dev); + if (busy) { mtk_wed_reset(dev, MTK_WED_RESET_WDMA_INT_AGENT); mtk_wed_reset(dev, MTK_WED_RESET_WDMA_RX_DRV); @@ -665,12 +1039,11 @@ mtk_wed_reset_dma(struct mtk_wed_device *dev) MTK_WED_WPDMA_RESET_IDX_RX); wed_w32(dev, MTK_WED_WPDMA_RESET_IDX, 0); } - } static int mtk_wed_ring_alloc(struct mtk_wed_device *dev, struct mtk_wed_ring *ring, - int size, u32 desc_size) + int size, u32 desc_size, bool tx) { ring->desc = dma_alloc_coherent(dev->hw->dev, size * desc_size, &ring->desc_phys, GFP_KERNEL); @@ -679,18 +1052,23 @@ mtk_wed_ring_alloc(struct mtk_wed_device *dev, struct mtk_wed_ring *ring, ring->desc_size = desc_size; ring->size = size; - mtk_wed_ring_reset(ring, size); + mtk_wed_ring_reset(ring, size, tx); return 0; } static int -mtk_wed_wdma_ring_setup(struct mtk_wed_device *dev, int idx, int size) +mtk_wed_wdma_rx_ring_setup(struct mtk_wed_device *dev, int idx, int size) { u32 desc_size = sizeof(struct mtk_wdma_desc) * dev->hw->version; - struct mtk_wed_ring *wdma = &dev->tx_wdma[idx]; + struct mtk_wed_ring *wdma; + + if (idx >= ARRAY_SIZE(dev->rx_wdma)) + return -EINVAL; - if (mtk_wed_ring_alloc(dev, wdma, MTK_WED_WDMA_RING_SIZE, desc_size)) + wdma = &dev->rx_wdma[idx]; + if (mtk_wed_ring_alloc(dev, wdma, MTK_WED_WDMA_RING_SIZE, desc_size, + true)) return -ENOMEM; wdma_w32(dev, MTK_WDMA_RING_RX(idx) + MTK_WED_RING_OFS_BASE, @@ -707,6 +1085,60 @@ mtk_wed_wdma_ring_setup(struct mtk_wed_device *dev, int idx, int size) return 0; } +static int +mtk_wed_wdma_tx_ring_setup(struct mtk_wed_device *dev, int idx, int size) +{ + u32 desc_size = sizeof(struct mtk_wdma_desc) * dev->hw->version; + struct mtk_wed_ring *wdma; + + if (idx >= ARRAY_SIZE(dev->tx_wdma)) + return -EINVAL; + + wdma = &dev->tx_wdma[idx]; + if (mtk_wed_ring_alloc(dev, wdma, MTK_WED_WDMA_RING_SIZE, desc_size, + true)) + return -ENOMEM; + + wdma_w32(dev, MTK_WDMA_RING_TX(idx) + MTK_WED_RING_OFS_BASE, + wdma->desc_phys); + wdma_w32(dev, MTK_WDMA_RING_TX(idx) + MTK_WED_RING_OFS_COUNT, + size); + wdma_w32(dev, MTK_WDMA_RING_TX(idx) + MTK_WED_RING_OFS_CPU_IDX, 0); + wdma_w32(dev, MTK_WDMA_RING_TX(idx) + MTK_WED_RING_OFS_DMA_IDX, 0); + + if (!idx) { + wed_w32(dev, MTK_WED_WDMA_RING_TX + MTK_WED_RING_OFS_BASE, + wdma->desc_phys); + wed_w32(dev, MTK_WED_WDMA_RING_TX + MTK_WED_RING_OFS_COUNT, + size); + wed_w32(dev, MTK_WED_WDMA_RING_TX + MTK_WED_RING_OFS_CPU_IDX, + 0); + wed_w32(dev, MTK_WED_WDMA_RING_TX + MTK_WED_RING_OFS_DMA_IDX, + 0); + } + + return 0; +} + +static void +mtk_wed_ppe_check(struct mtk_wed_device *dev, struct sk_buff *skb, + u32 reason, u32 hash) +{ + struct mtk_eth *eth = dev->hw->eth; + struct ethhdr *eh; + + if (!skb) + return; + + if (reason != MTK_PPE_CPU_REASON_HIT_UNBIND_RATE_REACHED) + return; + + skb_set_mac_header(skb, 0); + eh = eth_hdr(skb); + skb->protocol = eh->h_proto; + mtk_ppe_check_skb(eth->ppe[dev->hw->index], skb, hash); +} + static void mtk_wed_configure_irq(struct mtk_wed_device *dev, u32 irq_mask) { @@ -729,6 +1161,8 @@ mtk_wed_configure_irq(struct mtk_wed_device *dev, u32 irq_mask) wed_clr(dev, MTK_WED_WDMA_INT_CTRL, wdma_mask); } else { + wdma_mask |= FIELD_PREP(MTK_WDMA_INT_MASK_TX_DONE, + GENMASK(1, 0)); /* initail tx interrupt trigger */ wed_w32(dev, MTK_WED_WPDMA_INT_CTRL_TX, MTK_WED_WPDMA_INT_CTRL_TX0_DONE_EN | @@ -747,6 +1181,16 @@ mtk_wed_configure_irq(struct mtk_wed_device *dev, u32 irq_mask) FIELD_PREP(MTK_WED_WPDMA_INT_CTRL_TX_FREE_DONE_TRIG, dev->wlan.txfree_tbit)); + wed_w32(dev, MTK_WED_WPDMA_INT_CTRL_RX, + MTK_WED_WPDMA_INT_CTRL_RX0_EN | + MTK_WED_WPDMA_INT_CTRL_RX0_CLR | + MTK_WED_WPDMA_INT_CTRL_RX1_EN | + MTK_WED_WPDMA_INT_CTRL_RX1_CLR | + FIELD_PREP(MTK_WED_WPDMA_INT_CTRL_RX0_DONE_TRIG, + dev->wlan.rx_tbit[0]) | + FIELD_PREP(MTK_WED_WPDMA_INT_CTRL_RX1_DONE_TRIG, + dev->wlan.rx_tbit[1])); + wed_w32(dev, MTK_WED_WDMA_INT_CLR, wdma_mask); wed_set(dev, MTK_WED_WDMA_INT_CTRL, FIELD_PREP(MTK_WED_WDMA_INT_CTRL_POLL_SRC_SEL, @@ -784,9 +1228,15 @@ mtk_wed_dma_enable(struct mtk_wed_device *dev) wdma_set(dev, MTK_WDMA_GLO_CFG, MTK_WDMA_GLO_CFG_RX_INFO3_PRERES); } else { + int i; + wed_set(dev, MTK_WED_WPDMA_CTRL, MTK_WED_WPDMA_CTRL_SDL1_FIXED); + wed_set(dev, MTK_WED_WDMA_GLO_CFG, + MTK_WED_WDMA_GLO_CFG_TX_DRV_EN | + MTK_WED_WDMA_GLO_CFG_TX_DDONE_CHK); + wed_set(dev, MTK_WED_WPDMA_GLO_CFG, MTK_WED_WPDMA_GLO_CFG_RX_DRV_R0_PKT_PROC | MTK_WED_WPDMA_GLO_CFG_RX_DRV_R0_CRX_SYNC); @@ -794,6 +1244,15 @@ mtk_wed_dma_enable(struct mtk_wed_device *dev) wed_clr(dev, MTK_WED_WPDMA_GLO_CFG, MTK_WED_WPDMA_GLO_CFG_TX_TKID_KEEP | MTK_WED_WPDMA_GLO_CFG_TX_DMAD_DW3_PREV); + + wed_set(dev, MTK_WED_WPDMA_RX_D_GLO_CFG, + MTK_WED_WPDMA_RX_D_RX_DRV_EN | + FIELD_PREP(MTK_WED_WPDMA_RX_D_RXD_READ_LEN, 0x18) | + FIELD_PREP(MTK_WED_WPDMA_RX_D_INIT_PHASE_RXEN_SEL, + 0x2)); + + for (i = 0; i < MTK_WED_RX_QUEUES; i++) + mtk_wed_check_wfdma_rx_fill(dev, i); } } @@ -802,9 +1261,9 @@ mtk_wed_start(struct mtk_wed_device *dev, u32 irq_mask) { int i; - for (i = 0; i < ARRAY_SIZE(dev->tx_wdma); i++) - if (!dev->tx_wdma[i].desc) - mtk_wed_wdma_ring_setup(dev, i, 16); + for (i = 0; i < ARRAY_SIZE(dev->rx_wdma); i++) + if (!dev->rx_wdma[i].desc) + mtk_wed_wdma_rx_ring_setup(dev, i, 16); mtk_wed_hw_init(dev); mtk_wed_configure_irq(dev, irq_mask); @@ -819,7 +1278,19 @@ mtk_wed_start(struct mtk_wed_device *dev, u32 irq_mask) val |= BIT(0) | (BIT(1) * !!dev->hw->index); regmap_write(dev->hw->mirror, dev->hw->index * 4, val); } else { - mtk_wed_set_512_support(dev, true); + /* driver set mid ready and only once */ + wed_w32(dev, MTK_WED_EXT_INT_MASK1, + MTK_WED_EXT_INT_STATUS_WPDMA_MID_RDY); + wed_w32(dev, MTK_WED_EXT_INT_MASK2, + MTK_WED_EXT_INT_STATUS_WPDMA_MID_RDY); + + wed_r32(dev, MTK_WED_EXT_INT_MASK1); + wed_r32(dev, MTK_WED_EXT_INT_MASK2); + + if (mtk_wed_rro_cfg(dev)) + return; + + mtk_wed_set_512_support(dev, dev->wlan.wcid_512); } mtk_wed_dma_enable(dev); @@ -853,7 +1324,7 @@ mtk_wed_attach(struct mtk_wed_device *dev) if (!hw) { module_put(THIS_MODULE); ret = -ENODEV; - goto out; + goto unlock; } device = dev->wlan.bus_type == MTK_WED_BUS_PCIE @@ -866,23 +1337,36 @@ mtk_wed_attach(struct mtk_wed_device *dev) dev->dev = hw->dev; dev->irq = hw->irq; dev->wdma_idx = hw->index; + dev->version = hw->version; if (hw->eth->dma_dev == hw->eth->dev && of_dma_is_coherent(hw->eth->dev->of_node)) mtk_eth_set_dma_device(hw->eth, hw->dev); - ret = mtk_wed_buffer_alloc(dev); - if (ret) { - mtk_wed_detach(dev); + ret = mtk_wed_tx_buffer_alloc(dev); + if (ret) goto out; + + if (mtk_wed_get_rx_capa(dev)) { + ret = mtk_wed_rx_buffer_alloc(dev); + if (ret) + goto out; + + ret = mtk_wed_rro_alloc(dev); + if (ret) + goto out; } mtk_wed_hw_init_early(dev); - if (hw->hifsys) + if (hw->version == 1) regmap_update_bits(hw->hifsys, HIFSYS_DMA_AG_MAP, BIT(hw->index), 0); - + else + ret = mtk_wed_wo_init(hw); out: + if (ret) + mtk_wed_detach(dev); +unlock: mutex_unlock(&hw_lock); return ret; @@ -905,13 +1389,14 @@ mtk_wed_tx_ring_setup(struct mtk_wed_device *dev, int idx, void __iomem *regs) * WDMA RX. */ - BUG_ON(idx >= ARRAY_SIZE(dev->tx_ring)); + if (WARN_ON(idx >= ARRAY_SIZE(dev->tx_ring))) + return -EINVAL; if (mtk_wed_ring_alloc(dev, ring, MTK_WED_TX_RING_SIZE, - sizeof(*ring->desc))) + sizeof(*ring->desc), true)) return -ENOMEM; - if (mtk_wed_wdma_ring_setup(dev, idx, MTK_WED_WDMA_RING_SIZE)) + if (mtk_wed_wdma_rx_ring_setup(dev, idx, MTK_WED_WDMA_RING_SIZE)) return -ENOMEM; ring->reg_base = MTK_WED_RING_TX(idx); @@ -955,6 +1440,37 @@ mtk_wed_txfree_ring_setup(struct mtk_wed_device *dev, void __iomem *regs) return 0; } +static int +mtk_wed_rx_ring_setup(struct mtk_wed_device *dev, int idx, void __iomem *regs) +{ + struct mtk_wed_ring *ring = &dev->rx_ring[idx]; + + if (WARN_ON(idx >= ARRAY_SIZE(dev->rx_ring))) + return -EINVAL; + + if (mtk_wed_ring_alloc(dev, ring, MTK_WED_RX_RING_SIZE, + sizeof(*ring->desc), false)) + return -ENOMEM; + + if (mtk_wed_wdma_tx_ring_setup(dev, idx, MTK_WED_WDMA_RING_SIZE)) + return -ENOMEM; + + ring->reg_base = MTK_WED_RING_RX_DATA(idx); + ring->wpdma = regs; + ring->flags |= MTK_WED_RING_CONFIGURED; + + /* WPDMA -> WED */ + wpdma_rx_w32(dev, idx, MTK_WED_RING_OFS_BASE, ring->desc_phys); + wpdma_rx_w32(dev, idx, MTK_WED_RING_OFS_COUNT, MTK_WED_RX_RING_SIZE); + + wed_w32(dev, MTK_WED_WPDMA_RING_RX_DATA(idx) + MTK_WED_RING_OFS_BASE, + ring->desc_phys); + wed_w32(dev, MTK_WED_WPDMA_RING_RX_DATA(idx) + MTK_WED_RING_OFS_COUNT, + MTK_WED_RX_RING_SIZE); + + return 0; +} + static u32 mtk_wed_irq_get(struct mtk_wed_device *dev, u32 mask) { @@ -1051,7 +1567,9 @@ void mtk_wed_add_hw(struct device_node *np, struct mtk_eth *eth, static const struct mtk_wed_ops wed_ops = { .attach = mtk_wed_attach, .tx_ring_setup = mtk_wed_tx_ring_setup, + .rx_ring_setup = mtk_wed_rx_ring_setup, .txfree_ring_setup = mtk_wed_txfree_ring_setup, + .msg_update = mtk_wed_mcu_msg_update, .start = mtk_wed_start, .stop = mtk_wed_stop, .reset_dma = mtk_wed_reset_dma, @@ -1060,6 +1578,7 @@ void mtk_wed_add_hw(struct device_node *np, struct mtk_eth *eth, .irq_get = mtk_wed_irq_get, .irq_set_mask = mtk_wed_irq_set_mask, .detach = mtk_wed_detach, + .ppe_check = mtk_wed_ppe_check, }; struct device_node *eth_np = eth->dev->of_node; struct platform_device *pdev; diff --git a/drivers/net/ethernet/mediatek/mtk_wed.h b/drivers/net/ethernet/mediatek/mtk_wed.h index ae420ca01a48..e012b8a82133 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed.h +++ b/drivers/net/ethernet/mediatek/mtk_wed.h @@ -10,6 +10,7 @@ #include <linux/netdevice.h> struct mtk_eth; +struct mtk_wed_wo; struct mtk_wed_hw { struct device_node *node; @@ -22,6 +23,7 @@ struct mtk_wed_hw { struct regmap *mirror; struct dentry *debugfs_dir; struct mtk_wed_device *wed_dev; + struct mtk_wed_wo *wed_wo; u32 debugfs_reg; u32 num_flows; u8 version; @@ -85,6 +87,24 @@ wpdma_tx_w32(struct mtk_wed_device *dev, int ring, u32 reg, u32 val) } static inline u32 +wpdma_rx_r32(struct mtk_wed_device *dev, int ring, u32 reg) +{ + if (!dev->rx_ring[ring].wpdma) + return 0; + + return readl(dev->rx_ring[ring].wpdma + reg); +} + +static inline void +wpdma_rx_w32(struct mtk_wed_device *dev, int ring, u32 reg, u32 val) +{ + if (!dev->rx_ring[ring].wpdma) + return; + + writel(val, dev->rx_ring[ring].wpdma + reg); +} + +static inline u32 wpdma_txfree_r32(struct mtk_wed_device *dev, u32 reg) { if (!dev->txfree_ring.wpdma) @@ -126,6 +146,7 @@ static inline int mtk_wed_flow_add(int index) static inline void mtk_wed_flow_remove(int index) { } + #endif #ifdef CONFIG_DEBUG_FS diff --git a/drivers/net/ethernet/mediatek/mtk_wed_debugfs.c b/drivers/net/ethernet/mediatek/mtk_wed_debugfs.c index f420f187e837..56f663439721 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed_debugfs.c +++ b/drivers/net/ethernet/mediatek/mtk_wed_debugfs.c @@ -2,6 +2,7 @@ /* Copyright (C) 2021 Felix Fietkau <nbd@nbd.name> */ #include <linux/seq_file.h> +#include <linux/soc/mediatek/mtk_wed.h> #include "mtk_wed.h" #include "mtk_wed_regs.h" @@ -18,6 +19,8 @@ enum { DUMP_TYPE_WDMA, DUMP_TYPE_WPDMA_TX, DUMP_TYPE_WPDMA_TXFREE, + DUMP_TYPE_WPDMA_RX, + DUMP_TYPE_WED_RRO, }; #define DUMP_STR(_str) { _str, 0, DUMP_TYPE_STRING } @@ -36,6 +39,9 @@ enum { #define DUMP_WPDMA_TX_RING(_n) DUMP_RING("WPDMA_TX" #_n, 0, DUMP_TYPE_WPDMA_TX, _n) #define DUMP_WPDMA_TXFREE_RING DUMP_RING("WPDMA_RX1", 0, DUMP_TYPE_WPDMA_TXFREE) +#define DUMP_WPDMA_RX_RING(_n) DUMP_RING("WPDMA_RX" #_n, 0, DUMP_TYPE_WPDMA_RX, _n) +#define DUMP_WED_RRO_RING(_base)DUMP_RING("WED_RRO_MIOD", MTK_##_base, DUMP_TYPE_WED_RRO) +#define DUMP_WED_RRO_FDBK(_base)DUMP_RING("WED_RRO_FDBK", MTK_##_base, DUMP_TYPE_WED_RRO) static void print_reg_val(struct seq_file *s, const char *name, u32 val) @@ -57,6 +63,7 @@ dump_wed_regs(struct seq_file *s, struct mtk_wed_device *dev, cur > regs ? "\n" : "", cur->name); continue; + case DUMP_TYPE_WED_RRO: case DUMP_TYPE_WED: val = wed_r32(dev, cur->offset); break; @@ -69,6 +76,9 @@ dump_wed_regs(struct seq_file *s, struct mtk_wed_device *dev, case DUMP_TYPE_WPDMA_TXFREE: val = wpdma_txfree_r32(dev, cur->offset); break; + case DUMP_TYPE_WPDMA_RX: + val = wpdma_rx_r32(dev, cur->base, cur->offset); + break; } print_reg_val(s, cur->name, val); } @@ -132,6 +142,80 @@ wed_txinfo_show(struct seq_file *s, void *data) } DEFINE_SHOW_ATTRIBUTE(wed_txinfo); +static int +wed_rxinfo_show(struct seq_file *s, void *data) +{ + static const struct reg_dump regs[] = { + DUMP_STR("WPDMA RX"), + DUMP_WPDMA_RX_RING(0), + DUMP_WPDMA_RX_RING(1), + + DUMP_STR("WPDMA RX"), + DUMP_WED(WED_WPDMA_RX_D_MIB(0)), + DUMP_WED_RING(WED_WPDMA_RING_RX_DATA(0)), + DUMP_WED(WED_WPDMA_RX_D_PROCESSED_MIB(0)), + DUMP_WED(WED_WPDMA_RX_D_MIB(1)), + DUMP_WED_RING(WED_WPDMA_RING_RX_DATA(1)), + DUMP_WED(WED_WPDMA_RX_D_PROCESSED_MIB(1)), + DUMP_WED(WED_WPDMA_RX_D_COHERENT_MIB), + + DUMP_STR("WED RX"), + DUMP_WED_RING(WED_RING_RX_DATA(0)), + DUMP_WED_RING(WED_RING_RX_DATA(1)), + + DUMP_STR("WED RRO"), + DUMP_WED_RRO_RING(WED_RROQM_MIOD_CTRL0), + DUMP_WED(WED_RROQM_MID_MIB), + DUMP_WED(WED_RROQM_MOD_MIB), + DUMP_WED(WED_RROQM_MOD_COHERENT_MIB), + DUMP_WED_RRO_FDBK(WED_RROQM_FDBK_CTRL0), + DUMP_WED(WED_RROQM_FDBK_IND_MIB), + DUMP_WED(WED_RROQM_FDBK_ENQ_MIB), + DUMP_WED(WED_RROQM_FDBK_ANC_MIB), + DUMP_WED(WED_RROQM_FDBK_ANC2H_MIB), + + DUMP_STR("WED Route QM"), + DUMP_WED(WED_RTQM_R2H_MIB(0)), + DUMP_WED(WED_RTQM_R2Q_MIB(0)), + DUMP_WED(WED_RTQM_Q2H_MIB(0)), + DUMP_WED(WED_RTQM_R2H_MIB(1)), + DUMP_WED(WED_RTQM_R2Q_MIB(1)), + DUMP_WED(WED_RTQM_Q2H_MIB(1)), + DUMP_WED(WED_RTQM_Q2N_MIB), + DUMP_WED(WED_RTQM_Q2B_MIB), + DUMP_WED(WED_RTQM_PFDBK_MIB), + + DUMP_STR("WED WDMA TX"), + DUMP_WED(WED_WDMA_TX_MIB), + DUMP_WED_RING(WED_WDMA_RING_TX), + + DUMP_STR("WDMA TX"), + DUMP_WDMA(WDMA_GLO_CFG), + DUMP_WDMA_RING(WDMA_RING_TX(0)), + DUMP_WDMA_RING(WDMA_RING_TX(1)), + + DUMP_STR("WED RX BM"), + DUMP_WED(WED_RX_BM_BASE), + DUMP_WED(WED_RX_BM_RX_DMAD), + DUMP_WED(WED_RX_BM_PTR), + DUMP_WED(WED_RX_BM_TKID_MIB), + DUMP_WED(WED_RX_BM_BLEN), + DUMP_WED(WED_RX_BM_STS), + DUMP_WED(WED_RX_BM_INTF2), + DUMP_WED(WED_RX_BM_INTF), + DUMP_WED(WED_RX_BM_ERR_STS), + }; + struct mtk_wed_hw *hw = s->private; + struct mtk_wed_device *dev = hw->wed_dev; + + if (!dev) + return 0; + + dump_wed_regs(s, dev, regs, ARRAY_SIZE(regs)); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(wed_rxinfo); static int mtk_wed_reg_set(void *data, u64 val) @@ -175,4 +259,7 @@ void mtk_wed_hw_add_debugfs(struct mtk_wed_hw *hw) debugfs_create_u32("regidx", 0600, dir, &hw->debugfs_reg); debugfs_create_file_unsafe("regval", 0600, dir, hw, &fops_regval); debugfs_create_file_unsafe("txinfo", 0400, dir, hw, &wed_txinfo_fops); + if (hw->version != 1) + debugfs_create_file_unsafe("rxinfo", 0400, dir, hw, + &wed_rxinfo_fops); } diff --git a/drivers/net/ethernet/mediatek/mtk_wed_mcu.c b/drivers/net/ethernet/mediatek/mtk_wed_mcu.c new file mode 100644 index 000000000000..f9539e6233c9 --- /dev/null +++ b/drivers/net/ethernet/mediatek/mtk_wed_mcu.c @@ -0,0 +1,387 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (C) 2022 MediaTek Inc. + * + * Author: Lorenzo Bianconi <lorenzo@kernel.org> + * Sujuan Chen <sujuan.chen@mediatek.com> + */ + +#include <linux/firmware.h> +#include <linux/of_address.h> +#include <linux/of_reserved_mem.h> +#include <linux/mfd/syscon.h> +#include <linux/soc/mediatek/mtk_wed.h> +#include <asm/unaligned.h> + +#include "mtk_wed_regs.h" +#include "mtk_wed_wo.h" +#include "mtk_wed.h" + +static u32 wo_r32(struct mtk_wed_wo *wo, u32 reg) +{ + return readl(wo->boot.addr + reg); +} + +static void wo_w32(struct mtk_wed_wo *wo, u32 reg, u32 val) +{ + writel(val, wo->boot.addr + reg); +} + +static struct sk_buff * +mtk_wed_mcu_msg_alloc(const void *data, int data_len) +{ + int length = sizeof(struct mtk_wed_mcu_hdr) + data_len; + struct sk_buff *skb; + + skb = alloc_skb(length, GFP_KERNEL); + if (!skb) + return NULL; + + memset(skb->head, 0, length); + skb_reserve(skb, sizeof(struct mtk_wed_mcu_hdr)); + if (data && data_len) + skb_put_data(skb, data, data_len); + + return skb; +} + +static struct sk_buff * +mtk_wed_mcu_get_response(struct mtk_wed_wo *wo, unsigned long expires) +{ + if (!time_is_after_jiffies(expires)) + return NULL; + + wait_event_timeout(wo->mcu.wait, !skb_queue_empty(&wo->mcu.res_q), + expires - jiffies); + return skb_dequeue(&wo->mcu.res_q); +} + +void mtk_wed_mcu_rx_event(struct mtk_wed_wo *wo, struct sk_buff *skb) +{ + skb_queue_tail(&wo->mcu.res_q, skb); + wake_up(&wo->mcu.wait); +} + +static void +mtk_wed_update_rx_stats(struct mtk_wed_device *wed, struct sk_buff *skb) +{ + u32 count = get_unaligned_le32(skb->data); + struct mtk_wed_wo_rx_stats *stats; + int i; + + if (count * sizeof(*stats) > skb->len - sizeof(u32)) + return; + + stats = (struct mtk_wed_wo_rx_stats *)(skb->data + sizeof(u32)); + for (i = 0 ; i < count ; i++) + wed->wlan.update_wo_rx_stats(wed, &stats[i]); +} + +void mtk_wed_mcu_rx_unsolicited_event(struct mtk_wed_wo *wo, + struct sk_buff *skb) +{ + struct mtk_wed_mcu_hdr *hdr = (struct mtk_wed_mcu_hdr *)skb->data; + + skb_pull(skb, sizeof(*hdr)); + + switch (hdr->cmd) { + case MTK_WED_WO_EVT_LOG_DUMP: + dev_notice(wo->hw->dev, "%s\n", skb->data); + break; + case MTK_WED_WO_EVT_PROFILING: { + struct mtk_wed_wo_log_info *info = (void *)skb->data; + u32 count = skb->len / sizeof(*info); + int i; + + for (i = 0 ; i < count ; i++) + dev_notice(wo->hw->dev, + "SN:%u latency: total=%u, rro:%u, mod:%u\n", + le32_to_cpu(info[i].sn), + le32_to_cpu(info[i].total), + le32_to_cpu(info[i].rro), + le32_to_cpu(info[i].mod)); + break; + } + case MTK_WED_WO_EVT_RXCNT_INFO: + mtk_wed_update_rx_stats(wo->hw->wed_dev, skb); + break; + default: + break; + } + + dev_kfree_skb(skb); +} + +static int +mtk_wed_mcu_skb_send_msg(struct mtk_wed_wo *wo, struct sk_buff *skb, + int id, int cmd, u16 *wait_seq, bool wait_resp) +{ + struct mtk_wed_mcu_hdr *hdr; + + /* TODO: make it dynamic based on cmd */ + wo->mcu.timeout = 20 * HZ; + + hdr = (struct mtk_wed_mcu_hdr *)skb_push(skb, sizeof(*hdr)); + hdr->cmd = cmd; + hdr->length = cpu_to_le16(skb->len); + + if (wait_resp && wait_seq) { + u16 seq = ++wo->mcu.seq; + + if (!seq) + seq = ++wo->mcu.seq; + *wait_seq = seq; + + hdr->flag |= cpu_to_le16(MTK_WED_WARP_CMD_FLAG_NEED_RSP); + hdr->seq = cpu_to_le16(seq); + } + if (id == MTK_WED_MODULE_ID_WO) + hdr->flag |= cpu_to_le16(MTK_WED_WARP_CMD_FLAG_FROM_TO_WO); + + return mtk_wed_wo_queue_tx_skb(wo, &wo->q_tx, skb); +} + +static int +mtk_wed_mcu_parse_response(struct mtk_wed_wo *wo, struct sk_buff *skb, + int cmd, int seq) +{ + struct mtk_wed_mcu_hdr *hdr; + + if (!skb) { + dev_err(wo->hw->dev, "Message %08x (seq %d) timeout\n", + cmd, seq); + return -ETIMEDOUT; + } + + hdr = (struct mtk_wed_mcu_hdr *)skb->data; + if (le16_to_cpu(hdr->seq) != seq) + return -EAGAIN; + + skb_pull(skb, sizeof(*hdr)); + switch (cmd) { + case MTK_WED_WO_CMD_RXCNT_INFO: + mtk_wed_update_rx_stats(wo->hw->wed_dev, skb); + break; + default: + break; + } + + return 0; +} + +int mtk_wed_mcu_send_msg(struct mtk_wed_wo *wo, int id, int cmd, + const void *data, int len, bool wait_resp) +{ + unsigned long expires; + struct sk_buff *skb; + u16 seq; + int ret; + + skb = mtk_wed_mcu_msg_alloc(data, len); + if (!skb) + return -ENOMEM; + + mutex_lock(&wo->mcu.mutex); + + ret = mtk_wed_mcu_skb_send_msg(wo, skb, id, cmd, &seq, wait_resp); + if (ret || !wait_resp) + goto unlock; + + expires = jiffies + wo->mcu.timeout; + do { + skb = mtk_wed_mcu_get_response(wo, expires); + ret = mtk_wed_mcu_parse_response(wo, skb, cmd, seq); + dev_kfree_skb(skb); + } while (ret == -EAGAIN); + +unlock: + mutex_unlock(&wo->mcu.mutex); + + return ret; +} + +int mtk_wed_mcu_msg_update(struct mtk_wed_device *dev, int id, void *data, + int len) +{ + struct mtk_wed_wo *wo = dev->hw->wed_wo; + + if (dev->hw->version == 1) + return 0; + + return mtk_wed_mcu_send_msg(wo, MTK_WED_MODULE_ID_WO, id, data, len, + true); +} + +static int +mtk_wed_get_memory_region(struct mtk_wed_wo *wo, + struct mtk_wed_wo_memory_region *region) +{ + struct reserved_mem *rmem; + struct device_node *np; + int index; + + index = of_property_match_string(wo->hw->node, "memory-region-names", + region->name); + if (index < 0) + return index; + + np = of_parse_phandle(wo->hw->node, "memory-region", index); + if (!np) + return -ENODEV; + + rmem = of_reserved_mem_lookup(np); + of_node_put(np); + + if (!rmem) + return -ENODEV; + + region->phy_addr = rmem->base; + region->size = rmem->size; + region->addr = devm_ioremap(wo->hw->dev, region->phy_addr, region->size); + + return !region->addr ? -EINVAL : 0; +} + +static int +mtk_wed_mcu_run_firmware(struct mtk_wed_wo *wo, const struct firmware *fw, + struct mtk_wed_wo_memory_region *region) +{ + const u8 *first_region_ptr, *region_ptr, *trailer_ptr, *ptr = fw->data; + const struct mtk_wed_fw_trailer *trailer; + const struct mtk_wed_fw_region *fw_region; + + trailer_ptr = fw->data + fw->size - sizeof(*trailer); + trailer = (const struct mtk_wed_fw_trailer *)trailer_ptr; + region_ptr = trailer_ptr - trailer->num_region * sizeof(*fw_region); + first_region_ptr = region_ptr; + + while (region_ptr < trailer_ptr) { + u32 length; + + fw_region = (const struct mtk_wed_fw_region *)region_ptr; + length = le32_to_cpu(fw_region->len); + + if (region->phy_addr != le32_to_cpu(fw_region->addr)) + goto next; + + if (region->size < length) + goto next; + + if (first_region_ptr < ptr + length) + goto next; + + if (region->shared && region->consumed) + return 0; + + if (!region->shared || !region->consumed) { + memcpy_toio(region->addr, ptr, length); + region->consumed = true; + return 0; + } +next: + region_ptr += sizeof(*fw_region); + ptr += length; + } + + return -EINVAL; +} + +static int +mtk_wed_mcu_load_firmware(struct mtk_wed_wo *wo) +{ + static struct mtk_wed_wo_memory_region mem_region[] = { + [MTK_WED_WO_REGION_EMI] = { + .name = "wo-emi", + }, + [MTK_WED_WO_REGION_ILM] = { + .name = "wo-ilm", + }, + [MTK_WED_WO_REGION_DATA] = { + .name = "wo-data", + .shared = true, + }, + }; + const struct mtk_wed_fw_trailer *trailer; + const struct firmware *fw; + const char *fw_name; + u32 val, boot_cr; + int ret, i; + + /* load firmware region metadata */ + for (i = 0; i < ARRAY_SIZE(mem_region); i++) { + ret = mtk_wed_get_memory_region(wo, &mem_region[i]); + if (ret) + return ret; + } + + wo->boot.name = "wo-boot"; + ret = mtk_wed_get_memory_region(wo, &wo->boot); + if (ret) + return ret; + + /* set dummy cr */ + wed_w32(wo->hw->wed_dev, MTK_WED_SCR0 + 4 * MTK_WED_DUMMY_CR_FWDL, + wo->hw->index + 1); + + /* load firmware */ + fw_name = wo->hw->index ? MT7986_FIRMWARE_WO1 : MT7986_FIRMWARE_WO0; + ret = request_firmware(&fw, fw_name, wo->hw->dev); + if (ret) + return ret; + + trailer = (void *)(fw->data + fw->size - + sizeof(struct mtk_wed_fw_trailer)); + dev_info(wo->hw->dev, + "MTK WED WO Firmware Version: %.10s, Build Time: %.15s\n", + trailer->fw_ver, trailer->build_date); + dev_info(wo->hw->dev, "MTK WED WO Chip ID %02x Region %d\n", + trailer->chip_id, trailer->num_region); + + for (i = 0; i < ARRAY_SIZE(mem_region); i++) { + ret = mtk_wed_mcu_run_firmware(wo, fw, &mem_region[i]); + if (ret) + goto out; + } + + /* set the start address */ + boot_cr = wo->hw->index ? MTK_WO_MCU_CFG_LS_WA_BOOT_ADDR_ADDR + : MTK_WO_MCU_CFG_LS_WM_BOOT_ADDR_ADDR; + wo_w32(wo, boot_cr, mem_region[MTK_WED_WO_REGION_EMI].phy_addr >> 16); + /* wo firmware reset */ + wo_w32(wo, MTK_WO_MCU_CFG_LS_WF_MCCR_CLR_ADDR, 0xc00); + + val = wo_r32(wo, MTK_WO_MCU_CFG_LS_WF_MCU_CFG_WM_WA_ADDR); + val |= wo->hw->index ? MTK_WO_MCU_CFG_LS_WF_WM_WA_WA_CPU_RSTB_MASK + : MTK_WO_MCU_CFG_LS_WF_WM_WA_WM_CPU_RSTB_MASK; + wo_w32(wo, MTK_WO_MCU_CFG_LS_WF_MCU_CFG_WM_WA_ADDR, val); +out: + release_firmware(fw); + + return ret; +} + +static u32 +mtk_wed_mcu_read_fw_dl(struct mtk_wed_wo *wo) +{ + return wed_r32(wo->hw->wed_dev, + MTK_WED_SCR0 + 4 * MTK_WED_DUMMY_CR_FWDL); +} + +int mtk_wed_mcu_init(struct mtk_wed_wo *wo) +{ + u32 val; + int ret; + + skb_queue_head_init(&wo->mcu.res_q); + init_waitqueue_head(&wo->mcu.wait); + mutex_init(&wo->mcu.mutex); + + ret = mtk_wed_mcu_load_firmware(wo); + if (ret) + return ret; + + return readx_poll_timeout(mtk_wed_mcu_read_fw_dl, wo, val, !val, + 100, MTK_FW_DL_TIMEOUT); +} + +MODULE_FIRMWARE(MT7986_FIRMWARE_WO0); +MODULE_FIRMWARE(MT7986_FIRMWARE_WO1); diff --git a/drivers/net/ethernet/mediatek/mtk_wed_regs.h b/drivers/net/ethernet/mediatek/mtk_wed_regs.h index e270fb336143..9e39dace95eb 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed_regs.h +++ b/drivers/net/ethernet/mediatek/mtk_wed_regs.h @@ -4,6 +4,7 @@ #ifndef __MTK_WED_REGS_H #define __MTK_WED_REGS_H +#define MTK_WFDMA_DESC_CTRL_TO_HOST BIT(8) #define MTK_WDMA_DESC_CTRL_LEN1 GENMASK(14, 0) #define MTK_WDMA_DESC_CTRL_LEN1_V2 GENMASK(13, 0) #define MTK_WDMA_DESC_CTRL_LAST_SEG1 BIT(15) @@ -28,6 +29,8 @@ struct mtk_wdma_desc { #define MTK_WED_RESET_WED_TX_DMA BIT(12) #define MTK_WED_RESET_WDMA_RX_DRV BIT(17) #define MTK_WED_RESET_WDMA_INT_AGENT BIT(19) +#define MTK_WED_RESET_RX_RRO_QM BIT(20) +#define MTK_WED_RESET_RX_ROUTE_QM BIT(21) #define MTK_WED_RESET_WED BIT(31) #define MTK_WED_CTRL 0x00c @@ -39,8 +42,12 @@ struct mtk_wdma_desc { #define MTK_WED_CTRL_WED_TX_BM_BUSY BIT(9) #define MTK_WED_CTRL_WED_TX_FREE_AGENT_EN BIT(10) #define MTK_WED_CTRL_WED_TX_FREE_AGENT_BUSY BIT(11) -#define MTK_WED_CTRL_RESERVE_EN BIT(12) -#define MTK_WED_CTRL_RESERVE_BUSY BIT(13) +#define MTK_WED_CTRL_WED_RX_BM_EN BIT(12) +#define MTK_WED_CTRL_WED_RX_BM_BUSY BIT(13) +#define MTK_WED_CTRL_RX_RRO_QM_EN BIT(14) +#define MTK_WED_CTRL_RX_RRO_QM_BUSY BIT(15) +#define MTK_WED_CTRL_RX_ROUTE_QM_EN BIT(16) +#define MTK_WED_CTRL_RX_ROUTE_QM_BUSY BIT(17) #define MTK_WED_CTRL_FINAL_DIDX_READ BIT(24) #define MTK_WED_CTRL_ETH_DMAD_FMT BIT(25) #define MTK_WED_CTRL_MIB_READ_CLEAR BIT(28) @@ -62,6 +69,9 @@ struct mtk_wdma_desc { #define MTK_WED_EXT_INT_STATUS_TX_DMA_R_RESP_ERR BIT(22) #define MTK_WED_EXT_INT_STATUS_TX_DMA_W_RESP_ERR BIT(23) #define MTK_WED_EXT_INT_STATUS_RX_DRV_DMA_RECYCLE BIT(24) +#define MTK_WED_EXT_INT_STATUS_RX_DRV_GET_BM_DMAD_SKIP BIT(25) +#define MTK_WED_EXT_INT_STATUS_WPDMA_RX_D_DRV_ERR BIT(26) +#define MTK_WED_EXT_INT_STATUS_WPDMA_MID_RDY BIT(27) #define MTK_WED_EXT_INT_STATUS_ERROR_MASK (MTK_WED_EXT_INT_STATUS_TF_LEN_ERR | \ MTK_WED_EXT_INT_STATUS_TKID_WO_PYLD | \ MTK_WED_EXT_INT_STATUS_TKID_TITO_INVALID | \ @@ -71,6 +81,8 @@ struct mtk_wdma_desc { MTK_WED_EXT_INT_STATUS_TX_DMA_R_RESP_ERR) #define MTK_WED_EXT_INT_MASK 0x028 +#define MTK_WED_EXT_INT_MASK1 0x02c +#define MTK_WED_EXT_INT_MASK2 0x030 #define MTK_WED_STATUS 0x060 #define MTK_WED_STATUS_TX GENMASK(15, 8) @@ -151,7 +163,9 @@ struct mtk_wdma_desc { #define MTK_WED_RING_TX(_n) (0x300 + (_n) * 0x10) #define MTK_WED_RING_RX(_n) (0x400 + (_n) * 0x10) +#define MTK_WED_RING_RX_DATA(_n) (0x420 + (_n) * 0x10) +#define MTK_WED_SCR0 0x3c0 #define MTK_WED_WPDMA_INT_TRIGGER 0x504 #define MTK_WED_WPDMA_INT_TRIGGER_RX_DONE BIT(1) #define MTK_WED_WPDMA_INT_TRIGGER_TX_DONE GENMASK(5, 4) @@ -212,6 +226,12 @@ struct mtk_wdma_desc { #define MTK_WED_WPDMA_INT_CTRL_TX1_DONE_TRIG GENMASK(14, 10) #define MTK_WED_WPDMA_INT_CTRL_RX 0x534 +#define MTK_WED_WPDMA_INT_CTRL_RX0_EN BIT(0) +#define MTK_WED_WPDMA_INT_CTRL_RX0_CLR BIT(1) +#define MTK_WED_WPDMA_INT_CTRL_RX0_DONE_TRIG GENMASK(6, 2) +#define MTK_WED_WPDMA_INT_CTRL_RX1_EN BIT(8) +#define MTK_WED_WPDMA_INT_CTRL_RX1_CLR BIT(9) +#define MTK_WED_WPDMA_INT_CTRL_RX1_DONE_TRIG GENMASK(14, 10) #define MTK_WED_WPDMA_INT_CTRL_TX_FREE 0x538 #define MTK_WED_WPDMA_INT_CTRL_TX_FREE_DONE_EN BIT(0) @@ -241,11 +261,34 @@ struct mtk_wdma_desc { #define MTK_WED_WPDMA_RING_TX(_n) (0x600 + (_n) * 0x10) #define MTK_WED_WPDMA_RING_RX(_n) (0x700 + (_n) * 0x10) +#define MTK_WED_WPDMA_RING_RX_DATA(_n) (0x730 + (_n) * 0x10) + +#define MTK_WED_WPDMA_RX_D_GLO_CFG 0x75c +#define MTK_WED_WPDMA_RX_D_RX_DRV_EN BIT(0) +#define MTK_WED_WPDMA_RX_D_INIT_PHASE_RXEN_SEL GENMASK(11, 7) +#define MTK_WED_WPDMA_RX_D_RXD_READ_LEN GENMASK(31, 24) + +#define MTK_WED_WPDMA_RX_D_RST_IDX 0x760 +#define MTK_WED_WPDMA_RX_D_RST_CRX_IDX GENMASK(17, 16) +#define MTK_WED_WPDMA_RX_D_RST_DRV_IDX GENMASK(25, 24) + +#define MTK_WED_WPDMA_RX_GLO_CFG 0x76c +#define MTK_WED_WPDMA_RX_RING 0x770 + +#define MTK_WED_WPDMA_RX_D_MIB(_n) (0x774 + (_n) * 4) +#define MTK_WED_WPDMA_RX_D_PROCESSED_MIB(_n) (0x784 + (_n) * 4) +#define MTK_WED_WPDMA_RX_D_COHERENT_MIB 0x78c + +#define MTK_WED_WDMA_RING_TX 0x800 + +#define MTK_WED_WDMA_TX_MIB 0x810 + #define MTK_WED_WDMA_RING_RX(_n) (0x900 + (_n) * 0x10) #define MTK_WED_WDMA_RX_THRES(_n) (0x940 + (_n) * 0x4) #define MTK_WED_WDMA_GLO_CFG 0xa04 #define MTK_WED_WDMA_GLO_CFG_TX_DRV_EN BIT(0) +#define MTK_WED_WDMA_GLO_CFG_TX_DDONE_CHK BIT(1) #define MTK_WED_WDMA_GLO_CFG_RX_DRV_EN BIT(2) #define MTK_WED_WDMA_GLO_CFG_RX_DRV_BUSY BIT(3) #define MTK_WED_WDMA_GLO_CFG_BT_SIZE GENMASK(5, 4) @@ -290,6 +333,20 @@ struct mtk_wdma_desc { #define MTK_WED_WDMA_RX_RECYCLE_MIB(_n) (0xae8 + (_n) * 4) #define MTK_WED_WDMA_RX_PROCESSED_MIB(_n) (0xaf0 + (_n) * 4) +#define MTK_WED_RX_BM_RX_DMAD 0xd80 +#define MTK_WED_RX_BM_RX_DMAD_SDL0 GENMASK(13, 0) + +#define MTK_WED_RX_BM_BASE 0xd84 +#define MTK_WED_RX_BM_INIT_PTR 0xd88 +#define MTK_WED_RX_BM_SW_TAIL GENMASK(15, 0) +#define MTK_WED_RX_BM_INIT_SW_TAIL BIT(16) + +#define MTK_WED_RX_PTR 0xd8c + +#define MTK_WED_RX_BM_DYN_ALLOC_TH 0xdb4 +#define MTK_WED_RX_BM_DYN_ALLOC_TH_H GENMASK(31, 16) +#define MTK_WED_RX_BM_DYN_ALLOC_TH_L GENMASK(15, 0) + #define MTK_WED_RING_OFS_BASE 0x00 #define MTK_WED_RING_OFS_COUNT 0x04 #define MTK_WED_RING_OFS_CPU_IDX 0x08 @@ -300,7 +357,9 @@ struct mtk_wdma_desc { #define MTK_WDMA_GLO_CFG 0x204 #define MTK_WDMA_GLO_CFG_TX_DMA_EN BIT(0) +#define MTK_WDMA_GLO_CFG_TX_DMA_BUSY BIT(1) #define MTK_WDMA_GLO_CFG_RX_DMA_EN BIT(2) +#define MTK_WDMA_GLO_CFG_RX_DMA_BUSY BIT(3) #define MTK_WDMA_GLO_CFG_RX_INFO3_PRERES BIT(26) #define MTK_WDMA_GLO_CFG_RX_INFO2_PRERES BIT(27) #define MTK_WDMA_GLO_CFG_RX_INFO1_PRERES BIT(28) @@ -329,4 +388,70 @@ struct mtk_wdma_desc { /* DMA channel mapping */ #define HIFSYS_DMA_AG_MAP 0x008 +#define MTK_WED_RTQM_GLO_CFG 0xb00 +#define MTK_WED_RTQM_BUSY BIT(1) +#define MTK_WED_RTQM_Q_RST BIT(2) +#define MTK_WED_RTQM_Q_DBG_BYPASS BIT(5) +#define MTK_WED_RTQM_TXDMAD_FPORT GENMASK(23, 20) + +#define MTK_WED_RTQM_R2H_MIB(_n) (0xb70 + (_n) * 0x4) +#define MTK_WED_RTQM_R2Q_MIB(_n) (0xb78 + (_n) * 0x4) +#define MTK_WED_RTQM_Q2N_MIB 0xb80 +#define MTK_WED_RTQM_Q2H_MIB(_n) (0xb84 + (_n) * 0x4) + +#define MTK_WED_RTQM_Q2B_MIB 0xb8c +#define MTK_WED_RTQM_PFDBK_MIB 0xb90 + +#define MTK_WED_RROQM_GLO_CFG 0xc04 +#define MTK_WED_RROQM_RST_IDX 0xc08 +#define MTK_WED_RROQM_RST_IDX_MIOD BIT(0) +#define MTK_WED_RROQM_RST_IDX_FDBK BIT(4) + +#define MTK_WED_RROQM_MIOD_CTRL0 0xc40 +#define MTK_WED_RROQM_MIOD_CTRL1 0xc44 +#define MTK_WED_RROQM_MIOD_CNT GENMASK(11, 0) + +#define MTK_WED_RROQM_MIOD_CTRL2 0xc48 +#define MTK_WED_RROQM_MIOD_CTRL3 0xc4c + +#define MTK_WED_RROQM_FDBK_CTRL0 0xc50 +#define MTK_WED_RROQM_FDBK_CTRL1 0xc54 +#define MTK_WED_RROQM_FDBK_CNT GENMASK(11, 0) + +#define MTK_WED_RROQM_FDBK_CTRL2 0xc58 + +#define MTK_WED_RROQ_BASE_L 0xc80 +#define MTK_WED_RROQ_BASE_H 0xc84 + +#define MTK_WED_RROQM_MIOD_CFG 0xc8c +#define MTK_WED_RROQM_MIOD_MID_DW GENMASK(5, 0) +#define MTK_WED_RROQM_MIOD_MOD_DW GENMASK(13, 8) +#define MTK_WED_RROQM_MIOD_ENTRY_DW GENMASK(22, 16) + +#define MTK_WED_RROQM_MID_MIB 0xcc0 +#define MTK_WED_RROQM_MOD_MIB 0xcc4 +#define MTK_WED_RROQM_MOD_COHERENT_MIB 0xcc8 +#define MTK_WED_RROQM_FDBK_MIB 0xcd0 +#define MTK_WED_RROQM_FDBK_COHERENT_MIB 0xcd4 +#define MTK_WED_RROQM_FDBK_IND_MIB 0xce0 +#define MTK_WED_RROQM_FDBK_ENQ_MIB 0xce4 +#define MTK_WED_RROQM_FDBK_ANC_MIB 0xce8 +#define MTK_WED_RROQM_FDBK_ANC2H_MIB 0xcec + +#define MTK_WED_RX_BM_RX_DMAD 0xd80 +#define MTK_WED_RX_BM_BASE 0xd84 +#define MTK_WED_RX_BM_INIT_PTR 0xd88 +#define MTK_WED_RX_BM_PTR 0xd8c +#define MTK_WED_RX_BM_PTR_HEAD GENMASK(32, 16) +#define MTK_WED_RX_BM_PTR_TAIL GENMASK(15, 0) + +#define MTK_WED_RX_BM_BLEN 0xd90 +#define MTK_WED_RX_BM_STS 0xd94 +#define MTK_WED_RX_BM_INTF2 0xd98 +#define MTK_WED_RX_BM_INTF 0xd9c +#define MTK_WED_RX_BM_ERR_STS 0xda8 + +#define MTK_WED_WOCPU_VIEW_MIOD_BASE 0x8000 +#define MTK_WED_PCIE_INT_MASK 0x0 + #endif diff --git a/drivers/net/ethernet/mediatek/mtk_wed_wo.c b/drivers/net/ethernet/mediatek/mtk_wed_wo.c new file mode 100644 index 000000000000..4754b6db009e --- /dev/null +++ b/drivers/net/ethernet/mediatek/mtk_wed_wo.c @@ -0,0 +1,508 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (C) 2022 MediaTek Inc. + * + * Author: Lorenzo Bianconi <lorenzo@kernel.org> + * Sujuan Chen <sujuan.chen@mediatek.com> + */ + +#include <linux/kernel.h> +#include <linux/dma-mapping.h> +#include <linux/of_platform.h> +#include <linux/interrupt.h> +#include <linux/of_address.h> +#include <linux/mfd/syscon.h> +#include <linux/of_irq.h> +#include <linux/bitfield.h> + +#include "mtk_wed.h" +#include "mtk_wed_regs.h" +#include "mtk_wed_wo.h" + +static u32 +mtk_wed_mmio_r32(struct mtk_wed_wo *wo, u32 reg) +{ + u32 val; + + if (regmap_read(wo->mmio.regs, reg, &val)) + val = ~0; + + return val; +} + +static void +mtk_wed_mmio_w32(struct mtk_wed_wo *wo, u32 reg, u32 val) +{ + regmap_write(wo->mmio.regs, reg, val); +} + +static u32 +mtk_wed_wo_get_isr(struct mtk_wed_wo *wo) +{ + u32 val = mtk_wed_mmio_r32(wo, MTK_WED_WO_CCIF_RCHNUM); + + return val & MTK_WED_WO_CCIF_RCHNUM_MASK; +} + +static void +mtk_wed_wo_set_isr(struct mtk_wed_wo *wo, u32 mask) +{ + mtk_wed_mmio_w32(wo, MTK_WED_WO_CCIF_IRQ0_MASK, mask); +} + +static void +mtk_wed_wo_set_ack(struct mtk_wed_wo *wo, u32 mask) +{ + mtk_wed_mmio_w32(wo, MTK_WED_WO_CCIF_ACK, mask); +} + +static void +mtk_wed_wo_set_isr_mask(struct mtk_wed_wo *wo, u32 mask, u32 val, bool set) +{ + unsigned long flags; + + spin_lock_irqsave(&wo->mmio.lock, flags); + wo->mmio.irq_mask &= ~mask; + wo->mmio.irq_mask |= val; + if (set) + mtk_wed_wo_set_isr(wo, wo->mmio.irq_mask); + spin_unlock_irqrestore(&wo->mmio.lock, flags); +} + +static void +mtk_wed_wo_irq_enable(struct mtk_wed_wo *wo, u32 mask) +{ + mtk_wed_wo_set_isr_mask(wo, 0, mask, false); + tasklet_schedule(&wo->mmio.irq_tasklet); +} + +static void +mtk_wed_wo_irq_disable(struct mtk_wed_wo *wo, u32 mask) +{ + mtk_wed_wo_set_isr_mask(wo, mask, 0, true); +} + +static void +mtk_wed_wo_kickout(struct mtk_wed_wo *wo) +{ + mtk_wed_mmio_w32(wo, MTK_WED_WO_CCIF_BUSY, 1 << MTK_WED_WO_TXCH_NUM); + mtk_wed_mmio_w32(wo, MTK_WED_WO_CCIF_TCHNUM, MTK_WED_WO_TXCH_NUM); +} + +static void +mtk_wed_wo_queue_kick(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q, + u32 val) +{ + wmb(); + mtk_wed_mmio_w32(wo, q->regs.cpu_idx, val); +} + +static void * +mtk_wed_wo_dequeue(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q, u32 *len, + bool flush) +{ + int buf_len = SKB_WITH_OVERHEAD(q->buf_size); + int index = (q->tail + 1) % q->n_desc; + struct mtk_wed_wo_queue_entry *entry; + struct mtk_wed_wo_queue_desc *desc; + void *buf; + + if (!q->queued) + return NULL; + + if (flush) + q->desc[index].ctrl |= cpu_to_le32(MTK_WED_WO_CTL_DMA_DONE); + else if (!(q->desc[index].ctrl & cpu_to_le32(MTK_WED_WO_CTL_DMA_DONE))) + return NULL; + + q->tail = index; + q->queued--; + + desc = &q->desc[index]; + entry = &q->entry[index]; + buf = entry->buf; + if (len) + *len = FIELD_GET(MTK_WED_WO_CTL_SD_LEN0, + le32_to_cpu(READ_ONCE(desc->ctrl))); + if (buf) + dma_unmap_single(wo->hw->dev, entry->addr, buf_len, + DMA_FROM_DEVICE); + entry->buf = NULL; + + return buf; +} + +static int +mtk_wed_wo_queue_refill(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q, + gfp_t gfp, bool rx) +{ + enum dma_data_direction dir = rx ? DMA_FROM_DEVICE : DMA_TO_DEVICE; + int n_buf = 0; + + spin_lock_bh(&q->lock); + while (q->queued < q->n_desc) { + void *buf = page_frag_alloc(&q->cache, q->buf_size, gfp); + struct mtk_wed_wo_queue_entry *entry; + dma_addr_t addr; + + if (!buf) + break; + + addr = dma_map_single(wo->hw->dev, buf, q->buf_size, dir); + if (unlikely(dma_mapping_error(wo->hw->dev, addr))) { + skb_free_frag(buf); + break; + } + + q->head = (q->head + 1) % q->n_desc; + entry = &q->entry[q->head]; + entry->addr = addr; + entry->len = q->buf_size; + q->entry[q->head].buf = buf; + + if (rx) { + struct mtk_wed_wo_queue_desc *desc = &q->desc[q->head]; + u32 ctrl = MTK_WED_WO_CTL_LAST_SEC0 | + FIELD_PREP(MTK_WED_WO_CTL_SD_LEN0, + entry->len); + + WRITE_ONCE(desc->buf0, cpu_to_le32(addr)); + WRITE_ONCE(desc->ctrl, cpu_to_le32(ctrl)); + } + q->queued++; + n_buf++; + } + spin_unlock_bh(&q->lock); + + return n_buf; +} + +static void +mtk_wed_wo_rx_complete(struct mtk_wed_wo *wo) +{ + mtk_wed_wo_set_ack(wo, MTK_WED_WO_RXCH_INT_MASK); + mtk_wed_wo_irq_enable(wo, MTK_WED_WO_RXCH_INT_MASK); +} + +static void +mtk_wed_wo_rx_run_queue(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q) +{ + for (;;) { + struct mtk_wed_mcu_hdr *hdr; + struct sk_buff *skb; + void *data; + u32 len; + + data = mtk_wed_wo_dequeue(wo, q, &len, false); + if (!data) + break; + + skb = build_skb(data, q->buf_size); + if (!skb) { + skb_free_frag(data); + continue; + } + + __skb_put(skb, len); + if (mtk_wed_mcu_check_msg(wo, skb)) { + dev_kfree_skb(skb); + continue; + } + + hdr = (struct mtk_wed_mcu_hdr *)skb->data; + if (hdr->flag & cpu_to_le16(MTK_WED_WARP_CMD_FLAG_RSP)) + mtk_wed_mcu_rx_event(wo, skb); + else + mtk_wed_mcu_rx_unsolicited_event(wo, skb); + } + + if (mtk_wed_wo_queue_refill(wo, q, GFP_ATOMIC, true)) { + u32 index = (q->head - 1) % q->n_desc; + + mtk_wed_wo_queue_kick(wo, q, index); + } +} + +static irqreturn_t +mtk_wed_wo_irq_handler(int irq, void *data) +{ + struct mtk_wed_wo *wo = data; + + mtk_wed_wo_set_isr(wo, 0); + tasklet_schedule(&wo->mmio.irq_tasklet); + + return IRQ_HANDLED; +} + +static void mtk_wed_wo_irq_tasklet(struct tasklet_struct *t) +{ + struct mtk_wed_wo *wo = from_tasklet(wo, t, mmio.irq_tasklet); + u32 intr, mask; + + /* disable interrupts */ + mtk_wed_wo_set_isr(wo, 0); + + intr = mtk_wed_wo_get_isr(wo); + intr &= wo->mmio.irq_mask; + mask = intr & (MTK_WED_WO_RXCH_INT_MASK | MTK_WED_WO_EXCEPTION_INT_MASK); + mtk_wed_wo_irq_disable(wo, mask); + + if (intr & MTK_WED_WO_RXCH_INT_MASK) { + mtk_wed_wo_rx_run_queue(wo, &wo->q_rx); + mtk_wed_wo_rx_complete(wo); + } +} + +/* mtk wed wo hw queues */ + +static int +mtk_wed_wo_queue_alloc(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q, + int n_desc, int buf_size, int index, + struct mtk_wed_wo_queue_regs *regs) +{ + spin_lock_init(&q->lock); + q->regs = *regs; + q->n_desc = n_desc; + q->buf_size = buf_size; + + q->desc = dmam_alloc_coherent(wo->hw->dev, n_desc * sizeof(*q->desc), + &q->desc_dma, GFP_KERNEL); + if (!q->desc) + return -ENOMEM; + + q->entry = devm_kzalloc(wo->hw->dev, n_desc * sizeof(*q->entry), + GFP_KERNEL); + if (!q->entry) + return -ENOMEM; + + return 0; +} + +static void +mtk_wed_wo_queue_free(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q) +{ + mtk_wed_mmio_w32(wo, q->regs.cpu_idx, 0); + dma_free_coherent(wo->hw->dev, q->n_desc * sizeof(*q->desc), q->desc, + q->desc_dma); +} + +static void +mtk_wed_wo_queue_tx_clean(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q) +{ + struct page *page; + int i; + + spin_lock_bh(&q->lock); + for (i = 0; i < q->n_desc; i++) { + struct mtk_wed_wo_queue_entry *entry = &q->entry[i]; + + dma_unmap_single(wo->hw->dev, entry->addr, entry->len, + DMA_TO_DEVICE); + skb_free_frag(entry->buf); + entry->buf = NULL; + } + spin_unlock_bh(&q->lock); + + if (!q->cache.va) + return; + + page = virt_to_page(q->cache.va); + __page_frag_cache_drain(page, q->cache.pagecnt_bias); + memset(&q->cache, 0, sizeof(q->cache)); +} + +static void +mtk_wed_wo_queue_rx_clean(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q) +{ + struct page *page; + + spin_lock_bh(&q->lock); + for (;;) { + void *buf = mtk_wed_wo_dequeue(wo, q, NULL, true); + + if (!buf) + break; + + skb_free_frag(buf); + } + spin_unlock_bh(&q->lock); + + if (!q->cache.va) + return; + + page = virt_to_page(q->cache.va); + __page_frag_cache_drain(page, q->cache.pagecnt_bias); + memset(&q->cache, 0, sizeof(q->cache)); +} + +static void +mtk_wed_wo_queue_reset(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q) +{ + mtk_wed_mmio_w32(wo, q->regs.cpu_idx, 0); + mtk_wed_mmio_w32(wo, q->regs.desc_base, q->desc_dma); + mtk_wed_mmio_w32(wo, q->regs.ring_size, q->n_desc); +} + +int mtk_wed_wo_queue_tx_skb(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q, + struct sk_buff *skb) +{ + struct mtk_wed_wo_queue_entry *entry; + struct mtk_wed_wo_queue_desc *desc; + int ret = 0, index; + u32 ctrl; + + spin_lock_bh(&q->lock); + + q->tail = mtk_wed_mmio_r32(wo, q->regs.dma_idx); + index = (q->head + 1) % q->n_desc; + if (q->tail == index) { + ret = -ENOMEM; + goto out; + } + + entry = &q->entry[index]; + if (skb->len > entry->len) { + ret = -ENOMEM; + goto out; + } + + desc = &q->desc[index]; + q->head = index; + + dma_sync_single_for_cpu(wo->hw->dev, entry->addr, skb->len, + DMA_TO_DEVICE); + memcpy(entry->buf, skb->data, skb->len); + dma_sync_single_for_device(wo->hw->dev, entry->addr, skb->len, + DMA_TO_DEVICE); + + ctrl = FIELD_PREP(MTK_WED_WO_CTL_SD_LEN0, skb->len) | + MTK_WED_WO_CTL_LAST_SEC0 | MTK_WED_WO_CTL_DMA_DONE; + WRITE_ONCE(desc->buf0, cpu_to_le32(entry->addr)); + WRITE_ONCE(desc->ctrl, cpu_to_le32(ctrl)); + + mtk_wed_wo_queue_kick(wo, q, q->head); + mtk_wed_wo_kickout(wo); +out: + spin_unlock_bh(&q->lock); + + dev_kfree_skb(skb); + + return ret; +} + +static int +mtk_wed_wo_exception_init(struct mtk_wed_wo *wo) +{ + return 0; +} + +static int +mtk_wed_wo_hardware_init(struct mtk_wed_wo *wo) +{ + struct mtk_wed_wo_queue_regs regs; + struct device_node *np; + int ret; + + np = of_parse_phandle(wo->hw->node, "mediatek,wo-ccif", 0); + if (!np) + return -ENODEV; + + wo->mmio.regs = syscon_regmap_lookup_by_phandle(np, NULL); + if (IS_ERR_OR_NULL(wo->mmio.regs)) + return PTR_ERR(wo->mmio.regs); + + wo->mmio.irq = irq_of_parse_and_map(np, 0); + wo->mmio.irq_mask = MTK_WED_WO_ALL_INT_MASK; + spin_lock_init(&wo->mmio.lock); + tasklet_setup(&wo->mmio.irq_tasklet, mtk_wed_wo_irq_tasklet); + + ret = devm_request_irq(wo->hw->dev, wo->mmio.irq, + mtk_wed_wo_irq_handler, IRQF_TRIGGER_HIGH, + KBUILD_MODNAME, wo); + if (ret) + goto error; + + regs.desc_base = MTK_WED_WO_CCIF_DUMMY1; + regs.ring_size = MTK_WED_WO_CCIF_DUMMY2; + regs.dma_idx = MTK_WED_WO_CCIF_SHADOW4; + regs.cpu_idx = MTK_WED_WO_CCIF_DUMMY3; + + ret = mtk_wed_wo_queue_alloc(wo, &wo->q_tx, MTK_WED_WO_RING_SIZE, + MTK_WED_WO_CMD_LEN, MTK_WED_WO_TXCH_NUM, + ®s); + if (ret) + goto error; + + mtk_wed_wo_queue_refill(wo, &wo->q_tx, GFP_KERNEL, false); + mtk_wed_wo_queue_reset(wo, &wo->q_tx); + + regs.desc_base = MTK_WED_WO_CCIF_DUMMY5; + regs.ring_size = MTK_WED_WO_CCIF_DUMMY6; + regs.dma_idx = MTK_WED_WO_CCIF_SHADOW8; + regs.cpu_idx = MTK_WED_WO_CCIF_DUMMY7; + + ret = mtk_wed_wo_queue_alloc(wo, &wo->q_rx, MTK_WED_WO_RING_SIZE, + MTK_WED_WO_CMD_LEN, MTK_WED_WO_RXCH_NUM, + ®s); + if (ret) + goto error; + + mtk_wed_wo_queue_refill(wo, &wo->q_rx, GFP_KERNEL, true); + mtk_wed_wo_queue_reset(wo, &wo->q_rx); + + /* rx queue irqmask */ + mtk_wed_wo_set_isr(wo, wo->mmio.irq_mask); + + return 0; + +error: + devm_free_irq(wo->hw->dev, wo->mmio.irq, wo); + + return ret; +} + +static void +mtk_wed_wo_hw_deinit(struct mtk_wed_wo *wo) +{ + /* disable interrupts */ + mtk_wed_wo_set_isr(wo, 0); + + tasklet_disable(&wo->mmio.irq_tasklet); + + disable_irq(wo->mmio.irq); + devm_free_irq(wo->hw->dev, wo->mmio.irq, wo); + + mtk_wed_wo_queue_tx_clean(wo, &wo->q_tx); + mtk_wed_wo_queue_rx_clean(wo, &wo->q_rx); + mtk_wed_wo_queue_free(wo, &wo->q_tx); + mtk_wed_wo_queue_free(wo, &wo->q_rx); +} + +int mtk_wed_wo_init(struct mtk_wed_hw *hw) +{ + struct mtk_wed_wo *wo; + int ret; + + wo = devm_kzalloc(hw->dev, sizeof(*wo), GFP_KERNEL); + if (!wo) + return -ENOMEM; + + hw->wed_wo = wo; + wo->hw = hw; + + ret = mtk_wed_wo_hardware_init(wo); + if (ret) + return ret; + + ret = mtk_wed_mcu_init(wo); + if (ret) + return ret; + + return mtk_wed_wo_exception_init(wo); +} + +void mtk_wed_wo_deinit(struct mtk_wed_hw *hw) +{ + struct mtk_wed_wo *wo = hw->wed_wo; + + mtk_wed_wo_hw_deinit(wo); +} diff --git a/drivers/net/ethernet/mediatek/mtk_wed_wo.h b/drivers/net/ethernet/mediatek/mtk_wed_wo.h new file mode 100644 index 000000000000..c8fb85795864 --- /dev/null +++ b/drivers/net/ethernet/mediatek/mtk_wed_wo.h @@ -0,0 +1,282 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (C) 2022 Lorenzo Bianconi <lorenzo@kernel.org> */ + +#ifndef __MTK_WED_WO_H +#define __MTK_WED_WO_H + +#include <linux/skbuff.h> +#include <linux/netdevice.h> + +struct mtk_wed_hw; + +struct mtk_wed_mcu_hdr { + /* DW0 */ + u8 version; + u8 cmd; + __le16 length; + + /* DW1 */ + __le16 seq; + __le16 flag; + + /* DW2 */ + __le32 status; + + /* DW3 */ + u8 rsv[20]; +}; + +struct mtk_wed_wo_log_info { + __le32 sn; + __le32 total; + __le32 rro; + __le32 mod; +}; + +enum mtk_wed_wo_event { + MTK_WED_WO_EVT_LOG_DUMP = 0x1, + MTK_WED_WO_EVT_PROFILING = 0x2, + MTK_WED_WO_EVT_RXCNT_INFO = 0x3, +}; + +#define MTK_WED_MODULE_ID_WO 1 +#define MTK_FW_DL_TIMEOUT 4000000 /* us */ +#define MTK_WOCPU_TIMEOUT 2000000 /* us */ + +enum { + MTK_WED_WARP_CMD_FLAG_RSP = BIT(0), + MTK_WED_WARP_CMD_FLAG_NEED_RSP = BIT(1), + MTK_WED_WARP_CMD_FLAG_FROM_TO_WO = BIT(2), +}; + +#define MTK_WED_WO_CPU_MCUSYS_RESET_ADDR 0x15194050 +#define MTK_WED_WO_CPU_WO0_MCUSYS_RESET_MASK 0x20 +#define MTK_WED_WO_CPU_WO1_MCUSYS_RESET_MASK 0x1 + +enum { + MTK_WED_WO_REGION_EMI, + MTK_WED_WO_REGION_ILM, + MTK_WED_WO_REGION_DATA, + MTK_WED_WO_REGION_BOOT, + __MTK_WED_WO_REGION_MAX, +}; + +enum mtk_wed_wo_state { + MTK_WED_WO_STATE_UNDEFINED, + MTK_WED_WO_STATE_INIT, + MTK_WED_WO_STATE_ENABLE, + MTK_WED_WO_STATE_DISABLE, + MTK_WED_WO_STATE_HALT, + MTK_WED_WO_STATE_GATING, + MTK_WED_WO_STATE_SER_RESET, + MTK_WED_WO_STATE_WF_RESET, +}; + +enum mtk_wed_wo_done_state { + MTK_WED_WOIF_UNDEFINED, + MTK_WED_WOIF_DISABLE_DONE, + MTK_WED_WOIF_TRIGGER_ENABLE, + MTK_WED_WOIF_ENABLE_DONE, + MTK_WED_WOIF_TRIGGER_GATING, + MTK_WED_WOIF_GATING_DONE, + MTK_WED_WOIF_TRIGGER_HALT, + MTK_WED_WOIF_HALT_DONE, +}; + +enum mtk_wed_dummy_cr_idx { + MTK_WED_DUMMY_CR_FWDL, + MTK_WED_DUMMY_CR_WO_STATUS, +}; + +#define MT7986_FIRMWARE_WO0 "mediatek/mt7986_wo_0.bin" +#define MT7986_FIRMWARE_WO1 "mediatek/mt7986_wo_1.bin" + +#define MTK_WO_MCU_CFG_LS_BASE 0 +#define MTK_WO_MCU_CFG_LS_HW_VER_ADDR (MTK_WO_MCU_CFG_LS_BASE + 0x000) +#define MTK_WO_MCU_CFG_LS_FW_VER_ADDR (MTK_WO_MCU_CFG_LS_BASE + 0x004) +#define MTK_WO_MCU_CFG_LS_CFG_DBG1_ADDR (MTK_WO_MCU_CFG_LS_BASE + 0x00c) +#define MTK_WO_MCU_CFG_LS_CFG_DBG2_ADDR (MTK_WO_MCU_CFG_LS_BASE + 0x010) +#define MTK_WO_MCU_CFG_LS_WF_MCCR_ADDR (MTK_WO_MCU_CFG_LS_BASE + 0x014) +#define MTK_WO_MCU_CFG_LS_WF_MCCR_SET_ADDR (MTK_WO_MCU_CFG_LS_BASE + 0x018) +#define MTK_WO_MCU_CFG_LS_WF_MCCR_CLR_ADDR (MTK_WO_MCU_CFG_LS_BASE + 0x01c) +#define MTK_WO_MCU_CFG_LS_WF_MCU_CFG_WM_WA_ADDR (MTK_WO_MCU_CFG_LS_BASE + 0x050) +#define MTK_WO_MCU_CFG_LS_WM_BOOT_ADDR_ADDR (MTK_WO_MCU_CFG_LS_BASE + 0x060) +#define MTK_WO_MCU_CFG_LS_WA_BOOT_ADDR_ADDR (MTK_WO_MCU_CFG_LS_BASE + 0x064) + +#define MTK_WO_MCU_CFG_LS_WF_WM_WA_WM_CPU_RSTB_MASK BIT(5) +#define MTK_WO_MCU_CFG_LS_WF_WM_WA_WA_CPU_RSTB_MASK BIT(0) + +#define MTK_WED_WO_RING_SIZE 256 +#define MTK_WED_WO_CMD_LEN 1504 + +#define MTK_WED_WO_TXCH_NUM 0 +#define MTK_WED_WO_RXCH_NUM 1 +#define MTK_WED_WO_RXCH_WO_EXCEPTION 7 + +#define MTK_WED_WO_TXCH_INT_MASK BIT(0) +#define MTK_WED_WO_RXCH_INT_MASK BIT(1) +#define MTK_WED_WO_EXCEPTION_INT_MASK BIT(7) +#define MTK_WED_WO_ALL_INT_MASK (MTK_WED_WO_RXCH_INT_MASK | \ + MTK_WED_WO_EXCEPTION_INT_MASK) + +#define MTK_WED_WO_CCIF_BUSY 0x004 +#define MTK_WED_WO_CCIF_START 0x008 +#define MTK_WED_WO_CCIF_TCHNUM 0x00c +#define MTK_WED_WO_CCIF_RCHNUM 0x010 +#define MTK_WED_WO_CCIF_RCHNUM_MASK GENMASK(7, 0) + +#define MTK_WED_WO_CCIF_ACK 0x014 +#define MTK_WED_WO_CCIF_IRQ0_MASK 0x018 +#define MTK_WED_WO_CCIF_IRQ1_MASK 0x01c +#define MTK_WED_WO_CCIF_DUMMY1 0x020 +#define MTK_WED_WO_CCIF_DUMMY2 0x024 +#define MTK_WED_WO_CCIF_DUMMY3 0x028 +#define MTK_WED_WO_CCIF_DUMMY4 0x02c +#define MTK_WED_WO_CCIF_SHADOW1 0x030 +#define MTK_WED_WO_CCIF_SHADOW2 0x034 +#define MTK_WED_WO_CCIF_SHADOW3 0x038 +#define MTK_WED_WO_CCIF_SHADOW4 0x03c +#define MTK_WED_WO_CCIF_DUMMY5 0x050 +#define MTK_WED_WO_CCIF_DUMMY6 0x054 +#define MTK_WED_WO_CCIF_DUMMY7 0x058 +#define MTK_WED_WO_CCIF_DUMMY8 0x05c +#define MTK_WED_WO_CCIF_SHADOW5 0x060 +#define MTK_WED_WO_CCIF_SHADOW6 0x064 +#define MTK_WED_WO_CCIF_SHADOW7 0x068 +#define MTK_WED_WO_CCIF_SHADOW8 0x06c + +#define MTK_WED_WO_CTL_SD_LEN1 GENMASK(13, 0) +#define MTK_WED_WO_CTL_LAST_SEC1 BIT(14) +#define MTK_WED_WO_CTL_BURST BIT(15) +#define MTK_WED_WO_CTL_SD_LEN0_SHIFT 16 +#define MTK_WED_WO_CTL_SD_LEN0 GENMASK(29, 16) +#define MTK_WED_WO_CTL_LAST_SEC0 BIT(30) +#define MTK_WED_WO_CTL_DMA_DONE BIT(31) +#define MTK_WED_WO_INFO_WINFO GENMASK(15, 0) + +struct mtk_wed_wo_memory_region { + const char *name; + void __iomem *addr; + phys_addr_t phy_addr; + u32 size; + bool shared:1; + bool consumed:1; +}; + +struct mtk_wed_fw_region { + __le32 decomp_crc; + __le32 decomp_len; + __le32 decomp_blk_sz; + u8 rsv0[4]; + __le32 addr; + __le32 len; + u8 feature_set; + u8 rsv1[15]; +} __packed; + +struct mtk_wed_fw_trailer { + u8 chip_id; + u8 eco_code; + u8 num_region; + u8 format_ver; + u8 format_flag; + u8 rsv[2]; + char fw_ver[10]; + char build_date[15]; + u32 crc; +}; + +struct mtk_wed_wo_queue_regs { + u32 desc_base; + u32 ring_size; + u32 cpu_idx; + u32 dma_idx; +}; + +struct mtk_wed_wo_queue_desc { + __le32 buf0; + __le32 ctrl; + __le32 buf1; + __le32 info; + __le32 reserved[4]; +} __packed __aligned(32); + +struct mtk_wed_wo_queue_entry { + dma_addr_t addr; + void *buf; + u32 len; +}; + +struct mtk_wed_wo_queue { + struct mtk_wed_wo_queue_regs regs; + + struct page_frag_cache cache; + spinlock_t lock; + + struct mtk_wed_wo_queue_desc *desc; + dma_addr_t desc_dma; + + struct mtk_wed_wo_queue_entry *entry; + + u16 head; + u16 tail; + int n_desc; + int queued; + int buf_size; + +}; + +struct mtk_wed_wo { + struct mtk_wed_hw *hw; + struct mtk_wed_wo_memory_region boot; + + struct mtk_wed_wo_queue q_tx; + struct mtk_wed_wo_queue q_rx; + + struct { + struct mutex mutex; + int timeout; + u16 seq; + + struct sk_buff_head res_q; + wait_queue_head_t wait; + } mcu; + + struct { + struct regmap *regs; + + spinlock_t lock; + struct tasklet_struct irq_tasklet; + int irq; + u32 irq_mask; + } mmio; +}; + +static inline int +mtk_wed_mcu_check_msg(struct mtk_wed_wo *wo, struct sk_buff *skb) +{ + struct mtk_wed_mcu_hdr *hdr = (struct mtk_wed_mcu_hdr *)skb->data; + + if (hdr->version) + return -EINVAL; + + if (skb->len < sizeof(*hdr) || skb->len != le16_to_cpu(hdr->length)) + return -EINVAL; + + return 0; +} + +void mtk_wed_mcu_rx_event(struct mtk_wed_wo *wo, struct sk_buff *skb); +void mtk_wed_mcu_rx_unsolicited_event(struct mtk_wed_wo *wo, + struct sk_buff *skb); +int mtk_wed_mcu_send_msg(struct mtk_wed_wo *wo, int id, int cmd, + const void *data, int len, bool wait_resp); +int mtk_wed_mcu_msg_update(struct mtk_wed_device *dev, int id, void *data, + int len); +int mtk_wed_mcu_init(struct mtk_wed_wo *wo); +int mtk_wed_wo_init(struct mtk_wed_hw *hw); +void mtk_wed_wo_deinit(struct mtk_wed_hw *hw); +int mtk_wed_wo_queue_tx_skb(struct mtk_wed_wo *dev, struct mtk_wed_wo_queue *q, + struct sk_buff *skb); + +#endif /* __MTK_WED_WO_H */ diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index ca4b93a01034..8800d3f1f55c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -2337,11 +2337,8 @@ void mlx4_en_destroy_netdev(struct net_device *dev) en_dbg(DRV, priv, "Destroying netdev on port:%d\n", priv->port); /* Unregister device - this will close the port if it was up */ - if (priv->registered) { - devlink_port_type_clear(mlx4_get_devlink_port(mdev->dev, - priv->port)); + if (priv->registered) unregister_netdev(dev); - } if (priv->allocated) mlx4_free_hwq_res(mdev->dev, &priv->res, MLX4_EN_PAGE_SIZE); @@ -3474,6 +3471,8 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, mdev->profile.prof[priv->port].tx_ppp, mdev->profile.prof[priv->port].tx_pause); + SET_NETDEV_DEVLINK_PORT(dev, + mlx4_get_devlink_port(mdev->dev, priv->port)); err = register_netdev(dev); if (err) { en_err(priv, "Netdev registration failed for port %d\n", port); @@ -3481,8 +3480,6 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, } priv->registered = 1; - devlink_port_type_eth_set(mlx4_get_devlink_port(mdev->dev, priv->port), - dev); return 0; diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index d3fc86cd3c1d..3ae246391549 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -3043,7 +3043,7 @@ static int mlx4_init_port_info(struct mlx4_dev *dev, int port) */ if (!IS_ENABLED(CONFIG_MLX4_EN) && dev->caps.port_type[port] == MLX4_PORT_TYPE_ETH) - devlink_port_type_eth_set(&info->devlink_port, NULL); + devlink_port_type_eth_set(&info->devlink_port); else if (!IS_ENABLED(CONFIG_MLX4_INFINIBAND) && dev->caps.port_type[port] == MLX4_PORT_TYPE_IB) devlink_port_type_ib_set(&info->devlink_port, NULL); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 46ba4c2faad2..2e0d59ca62b5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -1770,12 +1770,17 @@ void mlx5_cmd_flush(struct mlx5_core_dev *dev) struct mlx5_cmd *cmd = &dev->cmd; int i; - for (i = 0; i < cmd->max_reg_cmds; i++) - while (down_trylock(&cmd->sem)) + for (i = 0; i < cmd->max_reg_cmds; i++) { + while (down_trylock(&cmd->sem)) { mlx5_cmd_trigger_completions(dev); + cond_resched(); + } + } - while (down_trylock(&cmd->pages_sem)) + while (down_trylock(&cmd->pages_sem)) { mlx5_cmd_trigger_completions(dev); + cond_resched(); + } /* Unlock cmdif */ up(&cmd->pages_sem); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c index b69f9d10ccbd..83adaabf59f5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c @@ -51,13 +51,6 @@ int mlx5e_devlink_port_register(struct mlx5e_priv *priv) return ret; } -void mlx5e_devlink_port_type_eth_set(struct mlx5e_priv *priv) -{ - struct devlink_port *dl_port = mlx5e_devlink_get_dl_port(priv); - - devlink_port_type_eth_set(dl_port, priv->netdev); -} - void mlx5e_devlink_port_unregister(struct mlx5e_priv *priv) { struct devlink_port *dl_port = mlx5e_devlink_get_dl_port(priv); @@ -69,13 +62,3 @@ void mlx5e_devlink_port_unregister(struct mlx5e_priv *priv) if (!(priv->mdev->priv.flags & MLX5_PRIV_FLAGS_MLX5E_LOCKED_FLOW)) devl_unlock(devlink); } - -struct devlink_port *mlx5e_get_devlink_port(struct net_device *dev) -{ - struct mlx5e_priv *priv = netdev_priv(dev); - - if (!netif_device_present(dev)) - return NULL; - - return mlx5e_devlink_get_dl_port(priv); -} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.h b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.h index 10b50feb9883..4f238d4fff55 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.h @@ -9,8 +9,6 @@ int mlx5e_devlink_port_register(struct mlx5e_priv *priv); void mlx5e_devlink_port_unregister(struct mlx5e_priv *priv); -void mlx5e_devlink_port_type_eth_set(struct mlx5e_priv *priv); -struct devlink_port *mlx5e_get_devlink_port(struct net_device *dev); static inline struct devlink_port * mlx5e_devlink_get_dl_port(struct mlx5e_priv *priv) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c index 39ef2a2561a3..8099a21e674c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c @@ -164,6 +164,36 @@ static int mlx5_esw_bridge_port_changeupper(struct notifier_block *nb, void *ptr return err; } +static int +mlx5_esw_bridge_changeupper_validate_netdev(void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct netdev_notifier_changeupper_info *info = ptr; + struct net_device *upper = info->upper_dev; + struct net_device *lower; + struct list_head *iter; + + if (!netif_is_bridge_master(upper) || !netif_is_lag_master(dev)) + return 0; + + netdev_for_each_lower_dev(dev, lower, iter) { + struct mlx5_core_dev *mdev; + struct mlx5e_priv *priv; + + if (!mlx5e_eswitch_rep(lower)) + continue; + + priv = netdev_priv(lower); + mdev = priv->mdev; + if (!mlx5_lag_is_active(mdev)) + return -EAGAIN; + if (!mlx5_lag_is_shared_fdb(mdev)) + return -EOPNOTSUPP; + } + + return 0; +} + static int mlx5_esw_bridge_switchdev_port_event(struct notifier_block *nb, unsigned long event, void *ptr) { @@ -171,6 +201,7 @@ static int mlx5_esw_bridge_switchdev_port_event(struct notifier_block *nb, switch (event) { case NETDEV_PRECHANGEUPPER: + err = mlx5_esw_bridge_changeupper_validate_netdev(ptr); break; case NETDEV_CHANGEUPPER: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c index 305fde62a78d..3337241cfd84 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c @@ -6,70 +6,42 @@ #include "en/tc_priv.h" #include "mlx5_core.h" -/* Must be aligned with enum flow_action_id. */ static struct mlx5e_tc_act *tc_acts_fdb[NUM_FLOW_ACTIONS] = { - &mlx5e_tc_act_accept, - &mlx5e_tc_act_drop, - &mlx5e_tc_act_trap, - &mlx5e_tc_act_goto, - &mlx5e_tc_act_mirred, - &mlx5e_tc_act_mirred, - &mlx5e_tc_act_redirect_ingress, - NULL, /* FLOW_ACTION_MIRRED_INGRESS, */ - &mlx5e_tc_act_vlan, - &mlx5e_tc_act_vlan, - &mlx5e_tc_act_vlan_mangle, - &mlx5e_tc_act_tun_encap, - &mlx5e_tc_act_tun_decap, - &mlx5e_tc_act_pedit, - &mlx5e_tc_act_pedit, - &mlx5e_tc_act_csum, - NULL, /* FLOW_ACTION_MARK, */ - &mlx5e_tc_act_ptype, - NULL, /* FLOW_ACTION_PRIORITY, */ - NULL, /* FLOW_ACTION_WAKE, */ - NULL, /* FLOW_ACTION_QUEUE, */ - &mlx5e_tc_act_sample, - &mlx5e_tc_act_police, - &mlx5e_tc_act_ct, - NULL, /* FLOW_ACTION_CT_METADATA, */ - &mlx5e_tc_act_mpls_push, - &mlx5e_tc_act_mpls_pop, - NULL, /* FLOW_ACTION_MPLS_MANGLE, */ - NULL, /* FLOW_ACTION_GATE, */ - NULL, /* FLOW_ACTION_PPPOE_PUSH, */ - NULL, /* FLOW_ACTION_JUMP, */ - NULL, /* FLOW_ACTION_PIPE, */ - &mlx5e_tc_act_vlan, - &mlx5e_tc_act_vlan, + [FLOW_ACTION_ACCEPT] = &mlx5e_tc_act_accept, + [FLOW_ACTION_DROP] = &mlx5e_tc_act_drop, + [FLOW_ACTION_TRAP] = &mlx5e_tc_act_trap, + [FLOW_ACTION_GOTO] = &mlx5e_tc_act_goto, + [FLOW_ACTION_REDIRECT] = &mlx5e_tc_act_mirred, + [FLOW_ACTION_MIRRED] = &mlx5e_tc_act_mirred, + [FLOW_ACTION_REDIRECT_INGRESS] = &mlx5e_tc_act_redirect_ingress, + [FLOW_ACTION_VLAN_PUSH] = &mlx5e_tc_act_vlan, + [FLOW_ACTION_VLAN_POP] = &mlx5e_tc_act_vlan, + [FLOW_ACTION_VLAN_MANGLE] = &mlx5e_tc_act_vlan_mangle, + [FLOW_ACTION_TUNNEL_ENCAP] = &mlx5e_tc_act_tun_encap, + [FLOW_ACTION_TUNNEL_DECAP] = &mlx5e_tc_act_tun_decap, + [FLOW_ACTION_MANGLE] = &mlx5e_tc_act_pedit, + [FLOW_ACTION_ADD] = &mlx5e_tc_act_pedit, + [FLOW_ACTION_CSUM] = &mlx5e_tc_act_csum, + [FLOW_ACTION_PTYPE] = &mlx5e_tc_act_ptype, + [FLOW_ACTION_SAMPLE] = &mlx5e_tc_act_sample, + [FLOW_ACTION_POLICE] = &mlx5e_tc_act_police, + [FLOW_ACTION_CT] = &mlx5e_tc_act_ct, + [FLOW_ACTION_MPLS_PUSH] = &mlx5e_tc_act_mpls_push, + [FLOW_ACTION_MPLS_POP] = &mlx5e_tc_act_mpls_pop, + [FLOW_ACTION_VLAN_PUSH_ETH] = &mlx5e_tc_act_vlan, + [FLOW_ACTION_VLAN_POP_ETH] = &mlx5e_tc_act_vlan, }; -/* Must be aligned with enum flow_action_id. */ static struct mlx5e_tc_act *tc_acts_nic[NUM_FLOW_ACTIONS] = { - &mlx5e_tc_act_accept, - &mlx5e_tc_act_drop, - NULL, /* FLOW_ACTION_TRAP, */ - &mlx5e_tc_act_goto, - &mlx5e_tc_act_mirred_nic, - NULL, /* FLOW_ACTION_MIRRED, */ - NULL, /* FLOW_ACTION_REDIRECT_INGRESS, */ - NULL, /* FLOW_ACTION_MIRRED_INGRESS, */ - NULL, /* FLOW_ACTION_VLAN_PUSH, */ - NULL, /* FLOW_ACTION_VLAN_POP, */ - NULL, /* FLOW_ACTION_VLAN_MANGLE, */ - NULL, /* FLOW_ACTION_TUNNEL_ENCAP, */ - NULL, /* FLOW_ACTION_TUNNEL_DECAP, */ - &mlx5e_tc_act_pedit, - &mlx5e_tc_act_pedit, - &mlx5e_tc_act_csum, - &mlx5e_tc_act_mark, - NULL, /* FLOW_ACTION_PTYPE, */ - NULL, /* FLOW_ACTION_PRIORITY, */ - NULL, /* FLOW_ACTION_WAKE, */ - NULL, /* FLOW_ACTION_QUEUE, */ - NULL, /* FLOW_ACTION_SAMPLE, */ - NULL, /* FLOW_ACTION_POLICE, */ - &mlx5e_tc_act_ct, + [FLOW_ACTION_ACCEPT] = &mlx5e_tc_act_accept, + [FLOW_ACTION_DROP] = &mlx5e_tc_act_drop, + [FLOW_ACTION_GOTO] = &mlx5e_tc_act_goto, + [FLOW_ACTION_REDIRECT] = &mlx5e_tc_act_mirred_nic, + [FLOW_ACTION_MANGLE] = &mlx5e_tc_act_pedit, + [FLOW_ACTION_ADD] = &mlx5e_tc_act_pedit, + [FLOW_ACTION_CSUM] = &mlx5e_tc_act_csum, + [FLOW_ACTION_MARK] = &mlx5e_tc_act_mark, + [FLOW_ACTION_CT] = &mlx5e_tc_act_ct, }; /** diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h index cb164b62f543..853f312cd757 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h @@ -11,6 +11,27 @@ #define INL_HDR_START_SZ (sizeof(((struct mlx5_wqe_eth_seg *)NULL)->inline_hdr.start)) +/* IPSEC inline data includes: + * 1. ESP trailer: up to 255 bytes of padding, 1 byte for pad length, 1 byte for + * next header. + * 2. ESP authentication data: 16 bytes for ICV. + */ +#define MLX5E_MAX_TX_IPSEC_DS DIV_ROUND_UP(sizeof(struct mlx5_wqe_inline_seg) + \ + 255 + 1 + 1 + 16, MLX5_SEND_WQE_DS) + +/* 366 should be big enough to cover all L2, L3 and L4 headers with possible + * encapsulations. + */ +#define MLX5E_MAX_TX_INLINE_DS DIV_ROUND_UP(366 - INL_HDR_START_SZ + VLAN_HLEN, \ + MLX5_SEND_WQE_DS) + +/* Sync the calculation with mlx5e_sq_calc_wqe_attr. */ +#define MLX5E_MAX_TX_WQEBBS DIV_ROUND_UP(MLX5E_TX_WQE_EMPTY_DS_COUNT + \ + MLX5E_MAX_TX_INLINE_DS + \ + MLX5E_MAX_TX_IPSEC_DS + \ + MAX_SKB_FRAGS + 1, \ + MLX5_SEND_WQEBB_NUM_DS) + #define MLX5E_RX_ERR_CQE(cqe) (get_cqe_opcode(cqe) != MLX5_CQE_RESP_SEND) static inline @@ -424,6 +445,8 @@ mlx5e_set_eseg_swp(struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg, static inline u16 mlx5e_stop_room_for_wqe(struct mlx5_core_dev *mdev, u16 wqe_size) { + WARN_ON_ONCE(PAGE_SIZE / MLX5_SEND_WQE_BB < mlx5e_get_max_sq_wqebbs(mdev)); + /* A WQE must not cross the page boundary, hence two conditions: * 1. Its size must not exceed the page size. * 2. If the WQE size is X, and the space remaining in a page is less @@ -436,7 +459,6 @@ static inline u16 mlx5e_stop_room_for_wqe(struct mlx5_core_dev *mdev, u16 wqe_si "wqe_size %u is greater than max SQ WQEBBs %u", wqe_size, mlx5e_get_max_sq_wqebbs(mdev)); - return MLX5E_STOP_ROOM(wqe_size); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index 4685c652c97e..20507ef2f956 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -117,7 +117,7 @@ mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq, xdpi.page.rq = rq; dma_addr = page_pool_get_dma_addr(page) + (xdpf->data - (void *)xdpf); - dma_sync_single_for_device(sq->pdev, dma_addr, xdptxd.len, DMA_TO_DEVICE); + dma_sync_single_for_device(sq->pdev, dma_addr, xdptxd.len, DMA_BIDIRECTIONAL); if (unlikely(xdp_frame_has_frags(xdpf))) { sinfo = xdp_get_shared_info_from_frame(xdpf); @@ -131,7 +131,7 @@ mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq, skb_frag_off(frag); len = skb_frag_size(frag); dma_sync_single_for_device(sq->pdev, addr, len, - DMA_TO_DEVICE); + DMA_BIDIRECTIONAL); } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 364f04309149..1669c7d7f285 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -4897,7 +4897,6 @@ const struct net_device_ops mlx5e_netdev_ops = { .ndo_has_offload_stats = mlx5e_has_offload_stats, .ndo_get_offload_stats = mlx5e_get_offload_stats, #endif - .ndo_get_devlink_port = mlx5e_get_devlink_port, }; static u32 mlx5e_choose_lro_timeout(struct mlx5_core_dev *mdev, u32 wanted_timeout) @@ -5694,6 +5693,13 @@ int mlx5e_attach_netdev(struct mlx5e_priv *priv) mlx5e_fs_set_state_destroy(priv->fs, !test_bit(MLX5E_STATE_DESTROYING, &priv->state)); + /* Validate the max_wqe_size_sq capability. */ + if (WARN_ON_ONCE(mlx5e_get_max_sq_wqebbs(priv->mdev) < MLX5E_MAX_TX_WQEBBS)) { + mlx5_core_warn(priv->mdev, "MLX5E: Max SQ WQEBBs firmware capability: %u, needed %lu\n", + mlx5e_get_max_sq_wqebbs(priv->mdev), MLX5E_MAX_TX_WQEBBS); + return -EIO; + } + /* max number of channels may have changed */ max_nch = mlx5e_calc_max_nch(priv->mdev, priv->netdev, profile); if (priv->channels.params.num_channels > max_nch) { @@ -5932,14 +5938,13 @@ static int mlx5e_probe(struct auxiliary_device *adev, goto err_profile_cleanup; } + SET_NETDEV_DEVLINK_PORT(netdev, mlx5e_devlink_get_dl_port(priv)); err = register_netdev(netdev); if (err) { mlx5_core_err(mdev, "register_netdev failed, %d\n", err); goto err_resume; } - mlx5e_devlink_port_type_eth_set(priv); - mlx5e_dcbnl_init_app(priv); mlx5_uplink_netdev_set(mdev, netdev); return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 794cd8dfe9c9..1b53e8852c86 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -607,15 +607,6 @@ static int mlx5e_rep_change_mtu(struct net_device *netdev, int new_mtu) return mlx5e_change_mtu(netdev, new_mtu, NULL); } -static struct devlink_port *mlx5e_rep_get_devlink_port(struct net_device *netdev) -{ - struct mlx5e_priv *priv = netdev_priv(netdev); - struct mlx5e_rep_priv *rpriv = priv->ppriv; - struct mlx5_core_dev *dev = priv->mdev; - - return mlx5_esw_offloads_devlink_port(dev->priv.eswitch, rpriv->rep->vport); -} - static int mlx5e_rep_change_carrier(struct net_device *dev, bool new_carrier) { struct mlx5e_priv *priv = netdev_priv(dev); @@ -644,7 +635,6 @@ static const struct net_device_ops mlx5e_netdev_ops_rep = { .ndo_stop = mlx5e_rep_close, .ndo_start_xmit = mlx5e_xmit, .ndo_setup_tc = mlx5e_rep_setup_tc, - .ndo_get_devlink_port = mlx5e_rep_get_devlink_port, .ndo_get_stats64 = mlx5e_rep_get_stats, .ndo_has_offload_stats = mlx5e_rep_has_offload_stats, .ndo_get_offload_stats = mlx5e_rep_get_offload_stats, @@ -1253,37 +1243,20 @@ mlx5e_vport_uplink_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep * { struct mlx5e_priv *priv = netdev_priv(mlx5_uplink_netdev_get(dev)); struct mlx5e_rep_priv *rpriv = mlx5e_rep_to_rep_priv(rep); - struct devlink_port *dl_port; - int err; rpriv->netdev = priv->netdev; - - err = mlx5e_netdev_change_profile(priv, &mlx5e_uplink_rep_profile, - rpriv); - if (err) - return err; - - dl_port = mlx5_esw_offloads_devlink_port(dev->priv.eswitch, rpriv->rep->vport); - if (dl_port) - devlink_port_type_eth_set(dl_port, rpriv->netdev); - - return 0; + return mlx5e_netdev_change_profile(priv, &mlx5e_uplink_rep_profile, + rpriv); } static void mlx5e_vport_uplink_rep_unload(struct mlx5e_rep_priv *rpriv) { struct net_device *netdev = rpriv->netdev; - struct devlink_port *dl_port; - struct mlx5_core_dev *dev; struct mlx5e_priv *priv; priv = netdev_priv(netdev); - dev = priv->mdev; - dl_port = mlx5_esw_offloads_devlink_port(dev->priv.eswitch, rpriv->rep->vport); - if (dl_port) - devlink_port_type_clear(dl_port); mlx5e_netdev_attach_nic_profile(priv); } @@ -1326,6 +1299,11 @@ mlx5e_vport_vf_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) goto err_cleanup_profile; } + dl_port = mlx5_esw_offloads_devlink_port(dev->priv.eswitch, + rpriv->rep->vport); + if (dl_port) + SET_NETDEV_DEVLINK_PORT(netdev, dl_port); + err = register_netdev(netdev); if (err) { netdev_warn(netdev, @@ -1334,9 +1312,6 @@ mlx5e_vport_vf_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) goto err_detach_netdev; } - dl_port = mlx5_esw_offloads_devlink_port(dev->priv.eswitch, rpriv->rep->vport); - if (dl_port) - devlink_port_type_eth_set(dl_port, netdev); return 0; err_detach_netdev: @@ -1382,8 +1357,6 @@ mlx5e_vport_rep_unload(struct mlx5_eswitch_rep *rep) struct mlx5e_rep_priv *rpriv = mlx5e_rep_to_rep_priv(rep); struct net_device *netdev = rpriv->netdev; struct mlx5e_priv *priv = netdev_priv(netdev); - struct mlx5_core_dev *dev = priv->mdev; - struct devlink_port *dl_port; void *ppriv = priv->ppriv; if (rep->vport == MLX5_VPORT_UPLINK) { @@ -1391,9 +1364,6 @@ mlx5e_vport_rep_unload(struct mlx5_eswitch_rep *rep) goto free_ppriv; } - dl_port = mlx5_esw_offloads_devlink_port(dev->priv.eswitch, rpriv->rep->vport); - if (dl_port) - devlink_port_type_clear(dl_port); unregister_netdev(netdev); mlx5e_detach_netdev(priv); priv->profile->cleanup(priv); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 58084650151f..a61a43fc8d5c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -266,7 +266,7 @@ static inline bool mlx5e_rx_cache_get(struct mlx5e_rq *rq, union mlx5e_alloc_uni addr = page_pool_get_dma_addr(au->page); /* Non-XSK always uses PAGE_SIZE. */ - dma_sync_single_for_device(rq->pdev, addr, PAGE_SIZE, DMA_FROM_DEVICE); + dma_sync_single_for_device(rq->pdev, addr, PAGE_SIZE, rq->buff.map_dir); return true; } @@ -282,8 +282,7 @@ static inline int mlx5e_page_alloc_pool(struct mlx5e_rq *rq, union mlx5e_alloc_u return -ENOMEM; /* Non-XSK always uses PAGE_SIZE. */ - addr = dma_map_page_attrs(rq->pdev, au->page, 0, PAGE_SIZE, - rq->buff.map_dir, DMA_ATTR_SKIP_CPU_SYNC); + addr = dma_map_page(rq->pdev, au->page, 0, PAGE_SIZE, rq->buff.map_dir); if (unlikely(dma_mapping_error(rq->pdev, addr))) { page_pool_recycle_direct(rq->page_pool, au->page); au->page = NULL; @@ -427,14 +426,15 @@ mlx5e_add_skb_frag(struct mlx5e_rq *rq, struct sk_buff *skb, { dma_addr_t addr = page_pool_get_dma_addr(au->page); - dma_sync_single_for_cpu(rq->pdev, addr + frag_offset, len, DMA_FROM_DEVICE); + dma_sync_single_for_cpu(rq->pdev, addr + frag_offset, len, + rq->buff.map_dir); page_ref_inc(au->page); skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, au->page, frag_offset, len, truesize); } static inline void -mlx5e_copy_skb_header(struct device *pdev, struct sk_buff *skb, +mlx5e_copy_skb_header(struct mlx5e_rq *rq, struct sk_buff *skb, struct page *page, dma_addr_t addr, int offset_from, int dma_offset, u32 headlen) { @@ -442,7 +442,8 @@ mlx5e_copy_skb_header(struct device *pdev, struct sk_buff *skb, /* Aligning len to sizeof(long) optimizes memcpy performance */ unsigned int len = ALIGN(headlen, sizeof(long)); - dma_sync_single_for_cpu(pdev, addr + dma_offset, len, DMA_FROM_DEVICE); + dma_sync_single_for_cpu(rq->pdev, addr + dma_offset, len, + rq->buff.map_dir); skb_copy_to_linear_data(skb, from, len); } @@ -1538,7 +1539,7 @@ mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi, addr = page_pool_get_dma_addr(au->page); dma_sync_single_range_for_cpu(rq->pdev, addr, wi->offset, - frag_size, DMA_FROM_DEVICE); + frag_size, rq->buff.map_dir); net_prefetch(data); prog = rcu_dereference(rq->xdp_prog); @@ -1587,7 +1588,7 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi addr = page_pool_get_dma_addr(au->page); dma_sync_single_range_for_cpu(rq->pdev, addr, wi->offset, - rq->buff.frame0_sz, DMA_FROM_DEVICE); + rq->buff.frame0_sz, rq->buff.map_dir); net_prefetchw(va); /* xdp_frame data area */ net_prefetch(va + rx_headroom); @@ -1608,7 +1609,7 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi addr = page_pool_get_dma_addr(au->page); dma_sync_single_for_cpu(rq->pdev, addr + wi->offset, - frag_consumed_bytes, DMA_FROM_DEVICE); + frag_consumed_bytes, rq->buff.map_dir); if (!xdp_buff_has_frags(&xdp)) { /* Init on the first fragment to avoid cold cache access @@ -1905,7 +1906,7 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w mlx5e_fill_skb_data(skb, rq, au, byte_cnt, frag_offset); /* copy header */ addr = page_pool_get_dma_addr(head_au->page); - mlx5e_copy_skb_header(rq->pdev, skb, head_au->page, addr, + mlx5e_copy_skb_header(rq, skb, head_au->page, addr, head_offset, head_offset, headlen); /* skb linear part was allocated with headlen and aligned to long */ skb->tail += headlen; @@ -1939,7 +1940,7 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, addr = page_pool_get_dma_addr(au->page); dma_sync_single_range_for_cpu(rq->pdev, addr, head_offset, - frag_size, DMA_FROM_DEVICE); + frag_size, rq->buff.map_dir); net_prefetch(data); prog = rcu_dereference(rq->xdp_prog); @@ -1987,7 +1988,7 @@ mlx5e_skb_from_cqe_shampo(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, if (likely(frag_size <= BIT(MLX5E_SHAMPO_LOG_MAX_HEADER_ENTRY_SIZE))) { /* build SKB around header */ - dma_sync_single_range_for_cpu(rq->pdev, head->addr, 0, frag_size, DMA_FROM_DEVICE); + dma_sync_single_range_for_cpu(rq->pdev, head->addr, 0, frag_size, rq->buff.map_dir); prefetchw(hdr); prefetch(data); skb = mlx5e_build_linear_skb(rq, hdr, frag_size, rx_headroom, head_size, 0); @@ -2009,7 +2010,7 @@ mlx5e_skb_from_cqe_shampo(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, } prefetchw(skb->data); - mlx5e_copy_skb_header(rq->pdev, skb, head->page, head->addr, + mlx5e_copy_skb_header(rq, skb, head->page, head->addr, head_offset + rx_headroom, rx_headroom, head_size); /* skb linear part was allocated with headlen and aligned to long */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index dd6fea9e9a5b..5a6aa61ec82a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -3633,10 +3633,14 @@ mlx5e_clone_flow_attr_for_post_act(struct mlx5_flow_attr *attr, attr2->action = 0; attr2->flags = 0; attr2->parse_attr = parse_attr; - attr2->esw_attr->out_count = 0; - attr2->esw_attr->split_count = 0; attr2->dest_chain = 0; attr2->dest_ft = NULL; + + if (ns_type == MLX5_FLOW_NAMESPACE_FDB) { + attr2->esw_attr->out_count = 0; + attr2->esw_attr->split_count = 0; + } + return attr2; } @@ -4758,12 +4762,6 @@ int mlx5e_policer_validate(const struct flow_action *action, return -EOPNOTSUPP; } - if (act->police.rate_pkt_ps) { - NL_SET_ERR_MSG_MOD(extack, - "QoS offload not support packets per second"); - return -EOPNOTSUPP; - } - return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 6adca01fbdc9..f7897ddb29c5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -305,6 +305,8 @@ static void mlx5e_sq_calc_wqe_attr(struct sk_buff *skb, const struct mlx5e_tx_at u16 ds_cnt_inl = 0; u16 ds_cnt_ids = 0; + /* Sync the calculation with MLX5E_MAX_TX_WQEBBS. */ + if (attr->insz) ds_cnt_ids = DIV_ROUND_UP(sizeof(struct mlx5_wqe_inline_seg) + attr->insz, MLX5_SEND_WQE_DS); @@ -317,6 +319,9 @@ static void mlx5e_sq_calc_wqe_attr(struct sk_buff *skb, const struct mlx5e_tx_at inl += VLAN_HLEN; ds_cnt_inl = DIV_ROUND_UP(inl, MLX5_SEND_WQE_DS); + if (WARN_ON_ONCE(ds_cnt_inl > MLX5E_MAX_TX_INLINE_DS)) + netdev_warn(skb->dev, "ds_cnt_inl = %u > max %u\n", ds_cnt_inl, + (u16)MLX5E_MAX_TX_INLINE_DS); ds_cnt += ds_cnt_inl; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index c59107fa9e6d..2169486c4bfb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1387,12 +1387,14 @@ void mlx5_eswitch_disable_locked(struct mlx5_eswitch *esw) esw->mode == MLX5_ESWITCH_LEGACY ? "LEGACY" : "OFFLOADS", esw->esw_funcs.num_vfs, esw->enabled_vports); - esw->fdb_table.flags &= ~MLX5_ESW_FDB_CREATED; - if (esw->mode == MLX5_ESWITCH_OFFLOADS) - esw_offloads_disable(esw); - else if (esw->mode == MLX5_ESWITCH_LEGACY) - esw_legacy_disable(esw); - mlx5_esw_acls_ns_cleanup(esw); + if (esw->fdb_table.flags & MLX5_ESW_FDB_CREATED) { + esw->fdb_table.flags &= ~MLX5_ESW_FDB_CREATED; + if (esw->mode == MLX5_ESWITCH_OFFLOADS) + esw_offloads_disable(esw); + else if (esw->mode == MLX5_ESWITCH_LEGACY) + esw_legacy_disable(esw); + mlx5_esw_acls_ns_cleanup(esw); + } if (esw->mode == MLX5_ESWITCH_OFFLOADS) devl_rate_nodes_destroy(devlink); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 4e50df3139c6..728ca9f2bb9d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -2310,7 +2310,7 @@ out_free: static int esw_offloads_start(struct mlx5_eswitch *esw, struct netlink_ext_ack *extack) { - int err, err1; + int err; esw->mode = MLX5_ESWITCH_OFFLOADS; err = mlx5_eswitch_enable_locked(esw, esw->dev->priv.sriov.num_vfs); @@ -2318,11 +2318,6 @@ static int esw_offloads_start(struct mlx5_eswitch *esw, NL_SET_ERR_MSG_MOD(extack, "Failed setting eswitch to offloads"); esw->mode = MLX5_ESWITCH_LEGACY; - err1 = mlx5_eswitch_enable_locked(esw, MLX5_ESWITCH_IGNORE_NUM_VFS); - if (err1) { - NL_SET_ERR_MSG_MOD(extack, - "Failed setting eswitch back to legacy"); - } mlx5_rescan_drivers(esw->dev); } if (esw->offloads.inline_mode == MLX5_INLINE_MODE_NONE) { @@ -3389,19 +3384,12 @@ err_metadata: static int esw_offloads_stop(struct mlx5_eswitch *esw, struct netlink_ext_ack *extack) { - int err, err1; + int err; esw->mode = MLX5_ESWITCH_LEGACY; err = mlx5_eswitch_enable_locked(esw, MLX5_ESWITCH_IGNORE_NUM_VFS); - if (err) { + if (err) NL_SET_ERR_MSG_MOD(extack, "Failed setting eswitch to legacy"); - esw->mode = MLX5_ESWITCH_OFFLOADS; - err1 = mlx5_eswitch_enable_locked(esw, MLX5_ESWITCH_IGNORE_NUM_VFS); - if (err1) { - NL_SET_ERR_MSG_MOD(extack, - "Failed setting eswitch back to offloads"); - } - } return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c index ee568bf34ae2..108a3503f413 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c @@ -30,9 +30,9 @@ mlx5_eswitch_termtbl_hash(struct mlx5_flow_act *flow_act, sizeof(dest->vport.num), hash); hash = jhash((const void *)&dest->vport.vhca_id, sizeof(dest->vport.num), hash); - if (dest->vport.pkt_reformat) - hash = jhash(dest->vport.pkt_reformat, - sizeof(*dest->vport.pkt_reformat), + if (flow_act->pkt_reformat) + hash = jhash(flow_act->pkt_reformat, + sizeof(*flow_act->pkt_reformat), hash); return hash; } @@ -53,9 +53,11 @@ mlx5_eswitch_termtbl_cmp(struct mlx5_flow_act *flow_act1, if (ret) return ret; - return dest1->vport.pkt_reformat && dest2->vport.pkt_reformat ? - memcmp(dest1->vport.pkt_reformat, dest2->vport.pkt_reformat, - sizeof(*dest1->vport.pkt_reformat)) : 0; + if (flow_act1->pkt_reformat && flow_act2->pkt_reformat) + return memcmp(flow_act1->pkt_reformat, flow_act2->pkt_reformat, + sizeof(*flow_act1->pkt_reformat)); + + return !(flow_act1->pkt_reformat == flow_act2->pkt_reformat); } static int diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c index 07c583996c29..9d908a0ccfef 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c @@ -152,7 +152,8 @@ static void mlx5_fw_reset_complete_reload(struct mlx5_core_dev *dev) mlx5_unload_one(dev); if (mlx5_health_wait_pci_up(dev)) mlx5_core_err(dev, "reset reload flow aborted, PCI reads still not working\n"); - mlx5_load_one(dev, false); + else + mlx5_load_one(dev, false); devlink_remote_reload_actions_performed(priv_to_devlink(dev), 0, BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT) | BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE)); diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index e2a985ec2c76..a83f6bc30072 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -3172,29 +3172,17 @@ void mlxsw_core_cpu_port_fini(struct mlxsw_core *mlxsw_core) } EXPORT_SYMBOL(mlxsw_core_cpu_port_fini); -void mlxsw_core_port_eth_set(struct mlxsw_core *mlxsw_core, u16 local_port, - void *port_driver_priv, struct net_device *dev) +void mlxsw_core_port_netdev_link(struct mlxsw_core *mlxsw_core, u16 local_port, + void *port_driver_priv, struct net_device *dev) { struct mlxsw_core_port *mlxsw_core_port = &mlxsw_core->ports[local_port]; struct devlink_port *devlink_port = &mlxsw_core_port->devlink_port; mlxsw_core_port->port_driver_priv = port_driver_priv; - devlink_port_type_eth_set(devlink_port, dev); + SET_NETDEV_DEVLINK_PORT(dev, devlink_port); } -EXPORT_SYMBOL(mlxsw_core_port_eth_set); - -void mlxsw_core_port_clear(struct mlxsw_core *mlxsw_core, u16 local_port, - void *port_driver_priv) -{ - struct mlxsw_core_port *mlxsw_core_port = - &mlxsw_core->ports[local_port]; - struct devlink_port *devlink_port = &mlxsw_core_port->devlink_port; - - mlxsw_core_port->port_driver_priv = port_driver_priv; - devlink_port_type_clear(devlink_port); -} -EXPORT_SYMBOL(mlxsw_core_port_clear); +EXPORT_SYMBOL(mlxsw_core_port_netdev_link); struct devlink_port * mlxsw_core_port_devlink_port_get(struct mlxsw_core *mlxsw_core, diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h index ca0c3d2bee6b..e0a6fcbbcb19 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core.h @@ -264,10 +264,9 @@ int mlxsw_core_cpu_port_init(struct mlxsw_core *mlxsw_core, const unsigned char *switch_id, unsigned char switch_id_len); void mlxsw_core_cpu_port_fini(struct mlxsw_core *mlxsw_core); -void mlxsw_core_port_eth_set(struct mlxsw_core *mlxsw_core, u16 local_port, - void *port_driver_priv, struct net_device *dev); -void mlxsw_core_port_clear(struct mlxsw_core *mlxsw_core, u16 local_port, - void *port_driver_priv); +void mlxsw_core_port_netdev_link(struct mlxsw_core *mlxsw_core, u16 local_port, + void *port_driver_priv, + struct net_device *dev); struct devlink_port * mlxsw_core_port_devlink_port_get(struct mlxsw_core *mlxsw_core, u16 local_port); diff --git a/drivers/net/ethernet/mellanox/mlxsw/minimal.c b/drivers/net/ethernet/mellanox/mlxsw/minimal.c index 55b3c42bb007..6b56eadd736e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/minimal.c +++ b/drivers/net/ethernet/mellanox/mlxsw/minimal.c @@ -81,20 +81,9 @@ static int mlxsw_m_port_stop(struct net_device *dev) return 0; } -static struct devlink_port * -mlxsw_m_port_get_devlink_port(struct net_device *dev) -{ - struct mlxsw_m_port *mlxsw_m_port = netdev_priv(dev); - struct mlxsw_m *mlxsw_m = mlxsw_m_port->mlxsw_m; - - return mlxsw_core_port_devlink_port_get(mlxsw_m->core, - mlxsw_m_port->local_port); -} - static const struct net_device_ops mlxsw_m_port_netdev_ops = { .ndo_open = mlxsw_m_port_open, .ndo_stop = mlxsw_m_port_stop, - .ndo_get_devlink_port = mlxsw_m_port_get_devlink_port, }; static void mlxsw_m_module_get_drvinfo(struct net_device *dev, @@ -265,6 +254,8 @@ mlxsw_m_port_create(struct mlxsw_m *mlxsw_m, u16 local_port, u8 slot_index, SET_NETDEV_DEV(dev, mlxsw_m->bus_info->dev); dev_net_set(dev, mlxsw_core_net(mlxsw_m->core)); mlxsw_m_port = netdev_priv(dev); + mlxsw_core_port_netdev_link(mlxsw_m->core, local_port, + mlxsw_m_port, dev); mlxsw_m_port->dev = dev; mlxsw_m_port->mlxsw_m = mlxsw_m; mlxsw_m_port->local_port = local_port; @@ -298,9 +289,6 @@ mlxsw_m_port_create(struct mlxsw_m *mlxsw_m, u16 local_port, u8 slot_index, goto err_register_netdev; } - mlxsw_core_port_eth_set(mlxsw_m->core, mlxsw_m_port->local_port, - mlxsw_m_port, dev); - return 0; err_register_netdev: @@ -316,7 +304,6 @@ static void mlxsw_m_port_remove(struct mlxsw_m *mlxsw_m, u16 local_port) { struct mlxsw_m_port *mlxsw_m_port = mlxsw_m->ports[local_port]; - mlxsw_core_port_clear(mlxsw_m->core, local_port, mlxsw_m); unregister_netdev(mlxsw_m_port->dev); /* This calls ndo_stop */ mlxsw_m->ports[local_port] = NULL; free_netdev(mlxsw_m_port->dev); diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index b74f30ec629a..f2d6f8654e04 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -2046,6 +2046,39 @@ static inline void mlxsw_reg_spvmlr_pack(char *payload, u16 local_port, } } +/* SPFSR - Switch Port FDB Security Register + * ----------------------------------------- + * Configures the security mode per port. + */ +#define MLXSW_REG_SPFSR_ID 0x2023 +#define MLXSW_REG_SPFSR_LEN 0x08 + +MLXSW_REG_DEFINE(spfsr, MLXSW_REG_SPFSR_ID, MLXSW_REG_SPFSR_LEN); + +/* reg_spfsr_local_port + * Local port. + * Access: Index + * + * Note: not supported for CPU port. + */ +MLXSW_ITEM32_LP(reg, spfsr, 0x00, 16, 0x00, 12); + +/* reg_spfsr_security + * Security checks. + * 0: disabled (default) + * 1: enabled + * Access: RW + */ +MLXSW_ITEM32(reg, spfsr, security, 0x04, 31, 1); + +static inline void mlxsw_reg_spfsr_pack(char *payload, u16 local_port, + bool security) +{ + MLXSW_REG_ZERO(spfsr, payload); + mlxsw_reg_spfsr_local_port_set(payload, local_port); + mlxsw_reg_spfsr_security_set(payload, security); +} + /* SPVC - Switch Port VLAN Classification Register * ----------------------------------------------- * Configures the port to identify packets as untagged / single tagged / @@ -6316,6 +6349,7 @@ enum mlxsw_reg_htgt_trap_group { MLXSW_REG_HTGT_TRAP_GROUP_SP_TUNNEL_DISCARDS, MLXSW_REG_HTGT_TRAP_GROUP_SP_ACL_DISCARDS, MLXSW_REG_HTGT_TRAP_GROUP_SP_BUFFER_DISCARDS, + MLXSW_REG_HTGT_TRAP_GROUP_SP_EAPOL, __MLXSW_REG_HTGT_TRAP_GROUP_MAX, MLXSW_REG_HTGT_TRAP_GROUP_MAX = __MLXSW_REG_HTGT_TRAP_GROUP_MAX - 1 @@ -12761,6 +12795,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = { MLXSW_REG(svpe), MLXSW_REG(sfmr), MLXSW_REG(spvmlr), + MLXSW_REG(spfsr), MLXSW_REG(spvc), MLXSW_REG(spevet), MLXSW_REG(smpe), diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 6ed496f6cbfb..f5b2d965d476 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -466,6 +466,24 @@ int mlxsw_sp_port_vid_learning_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid, return err; } +int mlxsw_sp_port_security_set(struct mlxsw_sp_port *mlxsw_sp_port, bool enable) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + char spfsr_pl[MLXSW_REG_SPFSR_LEN]; + int err; + + if (mlxsw_sp_port->security == enable) + return 0; + + mlxsw_reg_spfsr_pack(spfsr_pl, mlxsw_sp_port->local_port, enable); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(spfsr), spfsr_pl); + if (err) + return err; + + mlxsw_sp_port->security = enable; + return 0; +} + int mlxsw_sp_ethtype_to_sver_type(u16 ethtype, u8 *p_sver_type) { switch (ethtype) { @@ -1259,16 +1277,6 @@ static int mlxsw_sp_set_features(struct net_device *dev, return 0; } -static struct devlink_port * -mlxsw_sp_port_get_devlink_port(struct net_device *dev) -{ - struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); - struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; - - return mlxsw_core_port_devlink_port_get(mlxsw_sp->core, - mlxsw_sp_port->local_port); -} - static int mlxsw_sp_port_hwtstamp_set(struct mlxsw_sp_port *mlxsw_sp_port, struct ifreq *ifr) { @@ -1342,7 +1350,6 @@ static const struct net_device_ops mlxsw_sp_port_netdev_ops = { .ndo_vlan_rx_add_vid = mlxsw_sp_port_add_vid, .ndo_vlan_rx_kill_vid = mlxsw_sp_port_kill_vid, .ndo_set_features = mlxsw_sp_set_features, - .ndo_get_devlink_port = mlxsw_sp_port_get_devlink_port, .ndo_eth_ioctl = mlxsw_sp_port_ioctl, }; @@ -1651,6 +1658,8 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u16 local_port, SET_NETDEV_DEV(dev, mlxsw_sp->bus_info->dev); dev_net_set(dev, mlxsw_sp_net(mlxsw_sp)); mlxsw_sp_port = netdev_priv(dev); + mlxsw_core_port_netdev_link(mlxsw_sp->core, local_port, + mlxsw_sp_port, dev); mlxsw_sp_port->dev = dev; mlxsw_sp_port->mlxsw_sp = mlxsw_sp; mlxsw_sp_port->local_port = local_port; @@ -1839,8 +1848,6 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u16 local_port, goto err_register_netdev; } - mlxsw_core_port_eth_set(mlxsw_sp->core, mlxsw_sp_port->local_port, - mlxsw_sp_port, dev); mlxsw_core_schedule_dw(&mlxsw_sp_port->periodic_hw_stats.update_dw, 0); return 0; @@ -1897,7 +1904,6 @@ static void mlxsw_sp_port_remove(struct mlxsw_sp *mlxsw_sp, u16 local_port) cancel_delayed_work_sync(&mlxsw_sp_port->periodic_hw_stats.update_dw); cancel_delayed_work_sync(&mlxsw_sp_port->ptp.shaper_dw); - mlxsw_core_port_clear(mlxsw_sp->core, local_port, mlxsw_sp); unregister_netdev(mlxsw_sp_port->dev); /* This calls ndo_stop */ mlxsw_sp_port_ptp_clear(mlxsw_sp_port); mlxsw_sp_port_vlan_classification_set(mlxsw_sp_port, true, true); @@ -4754,6 +4760,10 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev, NL_SET_ERR_MSG_MOD(extack, "VLAN uppers are only supported with 802.1q VLAN protocol"); return -EOPNOTSUPP; } + if (is_vlan_dev(upper_dev) && mlxsw_sp_port->security) { + NL_SET_ERR_MSG_MOD(extack, "VLAN uppers are not supported on a locked port"); + return -EOPNOTSUPP; + } break; case NETDEV_CHANGEUPPER: upper_dev = info->upper_dev; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index c8ff2a6d7e90..bbc73324451d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -321,7 +321,8 @@ struct mlxsw_sp_port { struct mlxsw_sp *mlxsw_sp; u16 local_port; u8 lagged:1, - split:1; + split:1, + security:1; u16 pvid; u16 lag_id; struct { @@ -687,6 +688,8 @@ int mlxsw_sp_port_vid_stp_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid, int mlxsw_sp_port_vp_mode_set(struct mlxsw_sp_port *mlxsw_sp_port, bool enable); int mlxsw_sp_port_vid_learning_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid, bool learn_enable); +int mlxsw_sp_port_security_set(struct mlxsw_sp_port *mlxsw_sp_port, + bool enable); int mlxsw_sp_ethtype_to_sver_type(u16 ethtype, u8 *p_sver_type); int mlxsw_sp_port_egress_ethtype_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 ethtype); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 4efccd942fb8..accea95cae5d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -782,10 +782,25 @@ err_port_bridge_vlan_learning_set: static int mlxsw_sp_port_attr_br_pre_flags_set(struct mlxsw_sp_port *mlxsw_sp_port, - struct switchdev_brport_flags flags) + const struct net_device *orig_dev, + struct switchdev_brport_flags flags, + struct netlink_ext_ack *extack) { - if (flags.mask & ~(BR_LEARNING | BR_FLOOD | BR_MCAST_FLOOD)) + if (flags.mask & ~(BR_LEARNING | BR_FLOOD | BR_MCAST_FLOOD | + BR_PORT_LOCKED | BR_PORT_MAB)) { + NL_SET_ERR_MSG_MOD(extack, "Unsupported bridge port flag"); return -EINVAL; + } + + if ((flags.mask & BR_PORT_LOCKED) && is_vlan_dev(orig_dev)) { + NL_SET_ERR_MSG_MOD(extack, "Locked flag cannot be set on a VLAN upper"); + return -EINVAL; + } + + if ((flags.mask & BR_PORT_LOCKED) && vlan_uses_dev(orig_dev)) { + NL_SET_ERR_MSG_MOD(extack, "Locked flag cannot be set on a bridge port that has VLAN uppers"); + return -EINVAL; + } return 0; } @@ -819,6 +834,13 @@ static int mlxsw_sp_port_attr_br_flags_set(struct mlxsw_sp_port *mlxsw_sp_port, return err; } + if (flags.mask & BR_PORT_LOCKED) { + err = mlxsw_sp_port_security_set(mlxsw_sp_port, + flags.val & BR_PORT_LOCKED); + if (err) + return err; + } + if (bridge_port->bridge_device->multicast_enabled) goto out; @@ -1186,7 +1208,9 @@ static int mlxsw_sp_port_attr_set(struct net_device *dev, const void *ctx, break; case SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS: err = mlxsw_sp_port_attr_br_pre_flags_set(mlxsw_sp_port, - attr->u.brport_flags); + attr->orig_dev, + attr->u.brport_flags, + extack); break; case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS: err = mlxsw_sp_port_attr_br_flags_set(mlxsw_sp_port, @@ -2783,6 +2807,7 @@ void mlxsw_sp_port_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_port, bridge_device->ops->port_leave(bridge_device, bridge_port, mlxsw_sp_port); + mlxsw_sp_port_security_set(mlxsw_sp_port, false); mlxsw_sp_bridge_port_put(mlxsw_sp->bridge, bridge_port); } @@ -2888,13 +2913,14 @@ static void mlxsw_sp_fdb_nve_call_notifiers(struct net_device *dev, static void mlxsw_sp_fdb_call_notifiers(enum switchdev_notifier_type type, const char *mac, u16 vid, - struct net_device *dev, bool offloaded) + struct net_device *dev, bool offloaded, bool locked) { struct switchdev_notifier_fdb_info info = {}; info.addr = mac; info.vid = vid; info.offloaded = offloaded; + info.locked = locked; call_switchdev_notifiers(type, dev, &info.info, NULL); } @@ -2941,6 +2967,12 @@ static void mlxsw_sp_fdb_notify_mac_process(struct mlxsw_sp *mlxsw_sp, vid = bridge_device->vlan_enabled ? mlxsw_sp_port_vlan->vid : 0; evid = mlxsw_sp_port_vlan->vid; + if (adding && mlxsw_sp_port->security) { + mlxsw_sp_fdb_call_notifiers(SWITCHDEV_FDB_ADD_TO_BRIDGE, mac, + vid, bridge_port->dev, false, true); + return; + } + do_fdb_op: err = mlxsw_sp_port_fdb_uc_op(mlxsw_sp, local_port, mac, fid, evid, adding, true); @@ -2952,7 +2984,8 @@ do_fdb_op: if (!do_notification) return; type = adding ? SWITCHDEV_FDB_ADD_TO_BRIDGE : SWITCHDEV_FDB_DEL_TO_BRIDGE; - mlxsw_sp_fdb_call_notifiers(type, mac, vid, bridge_port->dev, adding); + mlxsw_sp_fdb_call_notifiers(type, mac, vid, bridge_port->dev, adding, + false); return; @@ -3004,6 +3037,12 @@ static void mlxsw_sp_fdb_notify_mac_lag_process(struct mlxsw_sp *mlxsw_sp, vid = bridge_device->vlan_enabled ? mlxsw_sp_port_vlan->vid : 0; lag_vid = mlxsw_sp_port_vlan->vid; + if (adding && mlxsw_sp_port->security) { + mlxsw_sp_fdb_call_notifiers(SWITCHDEV_FDB_ADD_TO_BRIDGE, mac, + vid, bridge_port->dev, false, true); + return; + } + do_fdb_op: err = mlxsw_sp_port_fdb_uc_lag_op(mlxsw_sp, lag_id, mac, fid, lag_vid, adding, true); @@ -3015,7 +3054,8 @@ do_fdb_op: if (!do_notification) return; type = adding ? SWITCHDEV_FDB_ADD_TO_BRIDGE : SWITCHDEV_FDB_DEL_TO_BRIDGE; - mlxsw_sp_fdb_call_notifiers(type, mac, vid, bridge_port->dev, adding); + mlxsw_sp_fdb_call_notifiers(type, mac, vid, bridge_port->dev, adding, + false); return; @@ -3122,7 +3162,7 @@ static void mlxsw_sp_fdb_notify_mac_uc_tunnel_process(struct mlxsw_sp *mlxsw_sp, type = adding ? SWITCHDEV_FDB_ADD_TO_BRIDGE : SWITCHDEV_FDB_DEL_TO_BRIDGE; - mlxsw_sp_fdb_call_notifiers(type, mac, vid, nve_dev, adding); + mlxsw_sp_fdb_call_notifiers(type, mac, vid, nve_dev, adding, false); mlxsw_sp_fid_put(fid); @@ -3264,7 +3304,7 @@ mlxsw_sp_switchdev_bridge_vxlan_fdb_event(struct mlxsw_sp *mlxsw_sp, &vxlan_fdb_info.info, NULL); mlxsw_sp_fdb_call_notifiers(SWITCHDEV_FDB_OFFLOADED, vxlan_fdb_info.eth_addr, - fdb_info->vid, dev, true); + fdb_info->vid, dev, true, false); break; case SWITCHDEV_FDB_DEL_TO_DEVICE: err = mlxsw_sp_port_fdb_tunnel_uc_op(mlxsw_sp, @@ -3359,7 +3399,7 @@ static void mlxsw_sp_switchdev_bridge_fdb_event_work(struct work_struct *work) break; mlxsw_sp_fdb_call_notifiers(SWITCHDEV_FDB_OFFLOADED, fdb_info->addr, - fdb_info->vid, dev, true); + fdb_info->vid, dev, true, false); break; case SWITCHDEV_FDB_DEL_TO_DEVICE: fdb_info = &switchdev_work->fdb_info; @@ -3443,7 +3483,8 @@ mlxsw_sp_switchdev_vxlan_fdb_add(struct mlxsw_sp *mlxsw_sp, call_switchdev_notifiers(SWITCHDEV_VXLAN_FDB_OFFLOADED, dev, &vxlan_fdb_info->info, NULL); mlxsw_sp_fdb_call_notifiers(SWITCHDEV_FDB_OFFLOADED, - vxlan_fdb_info->eth_addr, vid, dev, true); + vxlan_fdb_info->eth_addr, vid, dev, true, + false); mlxsw_sp_fid_put(fid); @@ -3493,7 +3534,8 @@ mlxsw_sp_switchdev_vxlan_fdb_del(struct mlxsw_sp *mlxsw_sp, false, false); vid = bridge_device->ops->fid_vid(bridge_device, fid); mlxsw_sp_fdb_call_notifiers(SWITCHDEV_FDB_OFFLOADED, - vxlan_fdb_info->eth_addr, vid, dev, false); + vxlan_fdb_info->eth_addr, vid, dev, false, + false); mlxsw_sp_fid_put(fid); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c index f4bfdb6dab9c..899c954e0e5f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c @@ -510,6 +510,9 @@ mlxsw_sp_trap_policer_items_arr[] = { { .policer = MLXSW_SP_TRAP_POLICER(20, 10240, 4096), }, + { + .policer = MLXSW_SP_TRAP_POLICER(21, 128, 128), + }, }; static const struct mlxsw_sp_trap_group_item mlxsw_sp_trap_group_items_arr[] = { @@ -628,6 +631,11 @@ static const struct mlxsw_sp_trap_group_item mlxsw_sp_trap_group_items_arr[] = { .hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_FLOW_LOGGING, .priority = 4, }, + { + .group = DEVLINK_TRAP_GROUP_GENERIC(EAPOL, 21), + .hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_EAPOL, + .priority = 5, + }, }; static const struct mlxsw_sp_trap_item mlxsw_sp_trap_items_arr[] = { @@ -1160,6 +1168,23 @@ static const struct mlxsw_sp_trap_item mlxsw_sp_trap_items_arr[] = { MLXSW_SP_RXL_DISCARD(ROUTER3, L3_DISCARDS), }, }, + { + .trap = MLXSW_SP_TRAP_CONTROL(EAPOL, EAPOL, TRAP), + .listeners_arr = { + MLXSW_SP_RXL_NO_MARK(EAPOL, EAPOL, TRAP_TO_CPU, true), + }, + }, + { + .trap = MLXSW_SP_TRAP_DROP(LOCKED_PORT, L2_DROPS), + .listeners_arr = { + MLXSW_RXL_DIS(mlxsw_sp_rx_drop_listener, FDB_MISS, + TRAP_EXCEPTION_TO_CPU, false, + SP_L2_DISCARDS, DISCARD, SP_L2_DISCARDS), + MLXSW_RXL_DIS(mlxsw_sp_rx_drop_listener, FDB_MISMATCH, + TRAP_EXCEPTION_TO_CPU, false, + SP_L2_DISCARDS, DISCARD, SP_L2_DISCARDS), + }, + }, }; static struct mlxsw_sp_trap_policer_item * diff --git a/drivers/net/ethernet/mellanox/mlxsw/trap.h b/drivers/net/ethernet/mellanox/mlxsw/trap.h index 8da169663bda..83477c8e6971 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/trap.h +++ b/drivers/net/ethernet/mellanox/mlxsw/trap.h @@ -25,6 +25,8 @@ enum { MLXSW_TRAP_ID_IGMP_V2_LEAVE = 0x33, MLXSW_TRAP_ID_IGMP_V3_REPORT = 0x34, MLXSW_TRAP_ID_PKT_SAMPLE = 0x38, + MLXSW_TRAP_ID_FDB_MISS = 0x3A, + MLXSW_TRAP_ID_FDB_MISMATCH = 0x3B, MLXSW_TRAP_ID_FID_MISS = 0x3D, MLXSW_TRAP_ID_DECAP_ECN0 = 0x40, MLXSW_TRAP_ID_MTUERROR = 0x52, diff --git a/drivers/net/ethernet/microchip/lan743x_ethtool.c b/drivers/net/ethernet/microchip/lan743x_ethtool.c index 88f9484cc2a7..2db5949b4c7e 100644 --- a/drivers/net/ethernet/microchip/lan743x_ethtool.c +++ b/drivers/net/ethernet/microchip/lan743x_ethtool.c @@ -1190,14 +1190,12 @@ static int lan743x_ethtool_set_wol(struct net_device *netdev, } #endif /* CONFIG_PM */ -static void lan743x_common_regs(struct net_device *dev, - struct ethtool_regs *regs, void *p) - +static void lan743x_common_regs(struct net_device *dev, void *p) { struct lan743x_adapter *adapter = netdev_priv(dev); u32 *rb = p; - memset(p, 0, (MAX_LAN743X_ETH_REGS * sizeof(u32))); + memset(p, 0, (MAX_LAN743X_ETH_COMMON_REGS * sizeof(u32))); rb[ETH_PRIV_FLAGS] = adapter->flags; rb[ETH_ID_REV] = lan743x_csr_read(adapter, ID_REV); @@ -1220,17 +1218,120 @@ static void lan743x_common_regs(struct net_device *dev, rb[ETH_WK_SRC] = lan743x_csr_read(adapter, MAC_WK_SRC); } +static void lan743x_sgmii_regs(struct net_device *dev, void *p) +{ + struct lan743x_adapter *adp = netdev_priv(dev); + u32 *rb = p; + u16 idx; + int val; + struct { + u8 id; + u8 dev; + u16 addr; + } regs[] = { + { ETH_SR_VSMMD_DEV_ID1, MDIO_MMD_VEND1, 0x0002}, + { ETH_SR_VSMMD_DEV_ID2, MDIO_MMD_VEND1, 0x0003}, + { ETH_SR_VSMMD_PCS_ID1, MDIO_MMD_VEND1, 0x0004}, + { ETH_SR_VSMMD_PCS_ID2, MDIO_MMD_VEND1, 0x0005}, + { ETH_SR_VSMMD_STS, MDIO_MMD_VEND1, 0x0008}, + { ETH_SR_VSMMD_CTRL, MDIO_MMD_VEND1, 0x0009}, + { ETH_SR_MII_CTRL, MDIO_MMD_VEND2, 0x0000}, + { ETH_SR_MII_STS, MDIO_MMD_VEND2, 0x0001}, + { ETH_SR_MII_DEV_ID1, MDIO_MMD_VEND2, 0x0002}, + { ETH_SR_MII_DEV_ID2, MDIO_MMD_VEND2, 0x0003}, + { ETH_SR_MII_AN_ADV, MDIO_MMD_VEND2, 0x0004}, + { ETH_SR_MII_LP_BABL, MDIO_MMD_VEND2, 0x0005}, + { ETH_SR_MII_EXPN, MDIO_MMD_VEND2, 0x0006}, + { ETH_SR_MII_EXT_STS, MDIO_MMD_VEND2, 0x000F}, + { ETH_SR_MII_TIME_SYNC_ABL, MDIO_MMD_VEND2, 0x0708}, + { ETH_SR_MII_TIME_SYNC_TX_MAX_DLY_LWR, MDIO_MMD_VEND2, 0x0709}, + { ETH_SR_MII_TIME_SYNC_TX_MAX_DLY_UPR, MDIO_MMD_VEND2, 0x070A}, + { ETH_SR_MII_TIME_SYNC_TX_MIN_DLY_LWR, MDIO_MMD_VEND2, 0x070B}, + { ETH_SR_MII_TIME_SYNC_TX_MIN_DLY_UPR, MDIO_MMD_VEND2, 0x070C}, + { ETH_SR_MII_TIME_SYNC_RX_MAX_DLY_LWR, MDIO_MMD_VEND2, 0x070D}, + { ETH_SR_MII_TIME_SYNC_RX_MAX_DLY_UPR, MDIO_MMD_VEND2, 0x070E}, + { ETH_SR_MII_TIME_SYNC_RX_MIN_DLY_LWR, MDIO_MMD_VEND2, 0x070F}, + { ETH_SR_MII_TIME_SYNC_RX_MIN_DLY_UPR, MDIO_MMD_VEND2, 0x0710}, + { ETH_VR_MII_DIG_CTRL1, MDIO_MMD_VEND2, 0x8000}, + { ETH_VR_MII_AN_CTRL, MDIO_MMD_VEND2, 0x8001}, + { ETH_VR_MII_AN_INTR_STS, MDIO_MMD_VEND2, 0x8002}, + { ETH_VR_MII_TC, MDIO_MMD_VEND2, 0x8003}, + { ETH_VR_MII_DBG_CTRL, MDIO_MMD_VEND2, 0x8005}, + { ETH_VR_MII_EEE_MCTRL0, MDIO_MMD_VEND2, 0x8006}, + { ETH_VR_MII_EEE_TXTIMER, MDIO_MMD_VEND2, 0x8008}, + { ETH_VR_MII_EEE_RXTIMER, MDIO_MMD_VEND2, 0x8009}, + { ETH_VR_MII_LINK_TIMER_CTRL, MDIO_MMD_VEND2, 0x800A}, + { ETH_VR_MII_EEE_MCTRL1, MDIO_MMD_VEND2, 0x800B}, + { ETH_VR_MII_DIG_STS, MDIO_MMD_VEND2, 0x8010}, + { ETH_VR_MII_ICG_ERRCNT1, MDIO_MMD_VEND2, 0x8011}, + { ETH_VR_MII_GPIO, MDIO_MMD_VEND2, 0x8015}, + { ETH_VR_MII_EEE_LPI_STATUS, MDIO_MMD_VEND2, 0x8016}, + { ETH_VR_MII_EEE_WKERR, MDIO_MMD_VEND2, 0x8017}, + { ETH_VR_MII_MISC_STS, MDIO_MMD_VEND2, 0x8018}, + { ETH_VR_MII_RX_LSTS, MDIO_MMD_VEND2, 0x8020}, + { ETH_VR_MII_GEN2_GEN4_TX_BSTCTRL0, MDIO_MMD_VEND2, 0x8038}, + { ETH_VR_MII_GEN2_GEN4_TX_LVLCTRL0, MDIO_MMD_VEND2, 0x803A}, + { ETH_VR_MII_GEN2_GEN4_TXGENCTRL0, MDIO_MMD_VEND2, 0x803C}, + { ETH_VR_MII_GEN2_GEN4_TXGENCTRL1, MDIO_MMD_VEND2, 0x803D}, + { ETH_VR_MII_GEN4_TXGENCTRL2, MDIO_MMD_VEND2, 0x803E}, + { ETH_VR_MII_GEN2_GEN4_TX_STS, MDIO_MMD_VEND2, 0x8048}, + { ETH_VR_MII_GEN2_GEN4_RXGENCTRL0, MDIO_MMD_VEND2, 0x8058}, + { ETH_VR_MII_GEN2_GEN4_RXGENCTRL1, MDIO_MMD_VEND2, 0x8059}, + { ETH_VR_MII_GEN4_RXEQ_CTRL, MDIO_MMD_VEND2, 0x805B}, + { ETH_VR_MII_GEN4_RXLOS_CTRL0, MDIO_MMD_VEND2, 0x805D}, + { ETH_VR_MII_GEN2_GEN4_MPLL_CTRL0, MDIO_MMD_VEND2, 0x8078}, + { ETH_VR_MII_GEN2_GEN4_MPLL_CTRL1, MDIO_MMD_VEND2, 0x8079}, + { ETH_VR_MII_GEN2_GEN4_MPLL_STS, MDIO_MMD_VEND2, 0x8088}, + { ETH_VR_MII_GEN2_GEN4_LVL_CTRL, MDIO_MMD_VEND2, 0x8090}, + { ETH_VR_MII_GEN4_MISC_CTRL2, MDIO_MMD_VEND2, 0x8093}, + { ETH_VR_MII_GEN2_GEN4_MISC_CTRL0, MDIO_MMD_VEND2, 0x8099}, + { ETH_VR_MII_GEN2_GEN4_MISC_CTRL1, MDIO_MMD_VEND2, 0x809A}, + { ETH_VR_MII_SNPS_CR_CTRL, MDIO_MMD_VEND2, 0x80A0}, + { ETH_VR_MII_SNPS_CR_ADDR, MDIO_MMD_VEND2, 0x80A1}, + { ETH_VR_MII_SNPS_CR_DATA, MDIO_MMD_VEND2, 0x80A2}, + { ETH_VR_MII_DIG_CTRL2, MDIO_MMD_VEND2, 0x80E1}, + { ETH_VR_MII_DIG_ERRCNT, MDIO_MMD_VEND2, 0x80E2}, + }; + + for (idx = 0; idx < ARRAY_SIZE(regs); idx++) { + val = lan743x_sgmii_read(adp, regs[idx].dev, regs[idx].addr); + if (val < 0) + rb[regs[idx].id] = 0xFFFF; + else + rb[regs[idx].id] = val; + } +} + static int lan743x_get_regs_len(struct net_device *dev) { - return MAX_LAN743X_ETH_REGS * sizeof(u32); + struct lan743x_adapter *adapter = netdev_priv(dev); + u32 num_regs = MAX_LAN743X_ETH_COMMON_REGS; + + if (adapter->is_sgmii_en) + num_regs += MAX_LAN743X_ETH_SGMII_REGS; + + return num_regs * sizeof(u32); } static void lan743x_get_regs(struct net_device *dev, struct ethtool_regs *regs, void *p) { + struct lan743x_adapter *adapter = netdev_priv(dev); + int regs_len; + + regs_len = lan743x_get_regs_len(dev); + memset(p, 0, regs_len); + regs->version = LAN743X_ETH_REG_VERSION; + regs->len = regs_len; + + lan743x_common_regs(dev, p); + p = (u32 *)p + MAX_LAN743X_ETH_COMMON_REGS; - lan743x_common_regs(dev, regs, p); + if (adapter->is_sgmii_en) { + lan743x_sgmii_regs(dev, p); + p = (u32 *)p + MAX_LAN743X_ETH_SGMII_REGS; + } } static void lan743x_get_pauseparam(struct net_device *dev, diff --git a/drivers/net/ethernet/microchip/lan743x_ethtool.h b/drivers/net/ethernet/microchip/lan743x_ethtool.h index 7f5996a52488..267d5035b8ad 100644 --- a/drivers/net/ethernet/microchip/lan743x_ethtool.h +++ b/drivers/net/ethernet/microchip/lan743x_ethtool.h @@ -29,7 +29,76 @@ enum { ETH_WK_SRC, /* Add new registers above */ - MAX_LAN743X_ETH_REGS + MAX_LAN743X_ETH_COMMON_REGS +}; + +enum { + /* SGMII Register */ + ETH_SR_VSMMD_DEV_ID1, + ETH_SR_VSMMD_DEV_ID2, + ETH_SR_VSMMD_PCS_ID1, + ETH_SR_VSMMD_PCS_ID2, + ETH_SR_VSMMD_STS, + ETH_SR_VSMMD_CTRL, + ETH_SR_MII_CTRL, + ETH_SR_MII_STS, + ETH_SR_MII_DEV_ID1, + ETH_SR_MII_DEV_ID2, + ETH_SR_MII_AN_ADV, + ETH_SR_MII_LP_BABL, + ETH_SR_MII_EXPN, + ETH_SR_MII_EXT_STS, + ETH_SR_MII_TIME_SYNC_ABL, + ETH_SR_MII_TIME_SYNC_TX_MAX_DLY_LWR, + ETH_SR_MII_TIME_SYNC_TX_MAX_DLY_UPR, + ETH_SR_MII_TIME_SYNC_TX_MIN_DLY_LWR, + ETH_SR_MII_TIME_SYNC_TX_MIN_DLY_UPR, + ETH_SR_MII_TIME_SYNC_RX_MAX_DLY_LWR, + ETH_SR_MII_TIME_SYNC_RX_MAX_DLY_UPR, + ETH_SR_MII_TIME_SYNC_RX_MIN_DLY_LWR, + ETH_SR_MII_TIME_SYNC_RX_MIN_DLY_UPR, + ETH_VR_MII_DIG_CTRL1, + ETH_VR_MII_AN_CTRL, + ETH_VR_MII_AN_INTR_STS, + ETH_VR_MII_TC, + ETH_VR_MII_DBG_CTRL, + ETH_VR_MII_EEE_MCTRL0, + ETH_VR_MII_EEE_TXTIMER, + ETH_VR_MII_EEE_RXTIMER, + ETH_VR_MII_LINK_TIMER_CTRL, + ETH_VR_MII_EEE_MCTRL1, + ETH_VR_MII_DIG_STS, + ETH_VR_MII_ICG_ERRCNT1, + ETH_VR_MII_GPIO, + ETH_VR_MII_EEE_LPI_STATUS, + ETH_VR_MII_EEE_WKERR, + ETH_VR_MII_MISC_STS, + ETH_VR_MII_RX_LSTS, + ETH_VR_MII_GEN2_GEN4_TX_BSTCTRL0, + ETH_VR_MII_GEN2_GEN4_TX_LVLCTRL0, + ETH_VR_MII_GEN2_GEN4_TXGENCTRL0, + ETH_VR_MII_GEN2_GEN4_TXGENCTRL1, + ETH_VR_MII_GEN4_TXGENCTRL2, + ETH_VR_MII_GEN2_GEN4_TX_STS, + ETH_VR_MII_GEN2_GEN4_RXGENCTRL0, + ETH_VR_MII_GEN2_GEN4_RXGENCTRL1, + ETH_VR_MII_GEN4_RXEQ_CTRL, + ETH_VR_MII_GEN4_RXLOS_CTRL0, + ETH_VR_MII_GEN2_GEN4_MPLL_CTRL0, + ETH_VR_MII_GEN2_GEN4_MPLL_CTRL1, + ETH_VR_MII_GEN2_GEN4_MPLL_STS, + ETH_VR_MII_GEN2_GEN4_LVL_CTRL, + ETH_VR_MII_GEN4_MISC_CTRL2, + ETH_VR_MII_GEN2_GEN4_MISC_CTRL0, + ETH_VR_MII_GEN2_GEN4_MISC_CTRL1, + ETH_VR_MII_SNPS_CR_CTRL, + ETH_VR_MII_SNPS_CR_ADDR, + ETH_VR_MII_SNPS_CR_DATA, + ETH_VR_MII_DIG_CTRL2, + ETH_VR_MII_DIG_ERRCNT, + + /* Add new registers above */ + MAX_LAN743X_ETH_SGMII_REGS }; extern const struct ethtool_ops lan743x_ethtool_ops; diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index c0f8ba601c01..534840f9a7ca 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -939,7 +939,7 @@ static int lan743x_sgmii_wait_till_not_busy(struct lan743x_adapter *adapter) return ret; } -static int lan743x_sgmii_read(struct lan743x_adapter *adapter, u8 mmd, u16 addr) +int lan743x_sgmii_read(struct lan743x_adapter *adapter, u8 mmd, u16 addr) { u32 mmd_access; int ret; diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h index bc5eea4c7b40..8438c3dbcf36 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.h +++ b/drivers/net/ethernet/microchip/lan743x_main.h @@ -1161,5 +1161,6 @@ int lan743x_hs_syslock_acquire(struct lan743x_adapter *adapter, u16 timeout); void lan743x_hs_syslock_release(struct lan743x_adapter *adapter); void lan743x_mac_flow_ctrl_set_enables(struct lan743x_adapter *adapter, bool tx_enable, bool rx_enable); +int lan743x_sgmii_read(struct lan743x_adapter *adapter, u8 mmd, u16 addr); #endif /* _LAN743X_H */ diff --git a/drivers/net/ethernet/microchip/lan966x/Kconfig b/drivers/net/ethernet/microchip/lan966x/Kconfig index 49e1464a4313..b7ae5ce7d3f7 100644 --- a/drivers/net/ethernet/microchip/lan966x/Kconfig +++ b/drivers/net/ethernet/microchip/lan966x/Kconfig @@ -7,5 +7,6 @@ config LAN966X_SWITCH depends on BRIDGE || BRIDGE=n select PHYLINK select PACKING + select PAGE_POOL help This driver supports the Lan966x network switch device. diff --git a/drivers/net/ethernet/microchip/lan966x/Makefile b/drivers/net/ethernet/microchip/lan966x/Makefile index 962f7c5f9e7d..251a7d561d63 100644 --- a/drivers/net/ethernet/microchip/lan966x/Makefile +++ b/drivers/net/ethernet/microchip/lan966x/Makefile @@ -11,4 +11,5 @@ lan966x-switch-objs := lan966x_main.o lan966x_phylink.o lan966x_port.o \ lan966x_ptp.o lan966x_fdma.o lan966x_lag.o \ lan966x_tc.o lan966x_mqprio.o lan966x_taprio.o \ lan966x_tbf.o lan966x_cbs.o lan966x_ets.o \ - lan966x_tc_matchall.o lan966x_police.o lan966x_mirror.o + lan966x_tc_matchall.o lan966x_police.o lan966x_mirror.o \ + lan966x_xdp.o diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c index e6948939ccc2..5fbbd479cfb0 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c @@ -10,50 +10,39 @@ static int lan966x_fdma_channel_active(struct lan966x *lan966x) static struct page *lan966x_fdma_rx_alloc_page(struct lan966x_rx *rx, struct lan966x_db *db) { - struct lan966x *lan966x = rx->lan966x; - dma_addr_t dma_addr; struct page *page; - page = dev_alloc_pages(rx->page_order); + page = page_pool_dev_alloc_pages(rx->page_pool); if (unlikely(!page)) return NULL; - dma_addr = dma_map_page(lan966x->dev, page, 0, - PAGE_SIZE << rx->page_order, - DMA_FROM_DEVICE); - if (unlikely(dma_mapping_error(lan966x->dev, dma_addr))) - goto free_page; - - db->dataptr = dma_addr; + db->dataptr = page_pool_get_dma_addr(page); return page; - -free_page: - __free_pages(page, rx->page_order); - return NULL; } static void lan966x_fdma_rx_free_pages(struct lan966x_rx *rx) { - struct lan966x *lan966x = rx->lan966x; - struct lan966x_rx_dcb *dcb; - struct lan966x_db *db; int i, j; for (i = 0; i < FDMA_DCB_MAX; ++i) { - dcb = &rx->dcbs[i]; - - for (j = 0; j < FDMA_RX_DCB_MAX_DBS; ++j) { - db = &dcb->db[j]; - dma_unmap_single(lan966x->dev, - (dma_addr_t)db->dataptr, - PAGE_SIZE << rx->page_order, - DMA_FROM_DEVICE); - __free_pages(rx->page[i][j], rx->page_order); - } + for (j = 0; j < FDMA_RX_DCB_MAX_DBS; ++j) + page_pool_put_full_page(rx->page_pool, + rx->page[i][j], false); } } +static void lan966x_fdma_rx_free_page(struct lan966x_rx *rx) +{ + struct page *page; + + page = rx->page[rx->dcb_index][rx->db_index]; + if (unlikely(!page)) + return; + + page_pool_recycle_direct(rx->page_pool, page); +} + static void lan966x_fdma_rx_add_dcb(struct lan966x_rx *rx, struct lan966x_rx_dcb *dcb, u64 nextptr) @@ -73,6 +62,25 @@ static void lan966x_fdma_rx_add_dcb(struct lan966x_rx *rx, rx->last_entry = dcb; } +static int lan966x_fdma_rx_alloc_page_pool(struct lan966x_rx *rx) +{ + struct lan966x *lan966x = rx->lan966x; + struct page_pool_params pp_params = { + .order = rx->page_order, + .flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV, + .pool_size = FDMA_DCB_MAX, + .nid = NUMA_NO_NODE, + .dev = lan966x->dev, + .dma_dir = DMA_FROM_DEVICE, + .offset = 0, + .max_len = rx->max_mtu - + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)), + }; + + rx->page_pool = page_pool_create(&pp_params); + return PTR_ERR_OR_ZERO(rx->page_pool); +} + static int lan966x_fdma_rx_alloc(struct lan966x_rx *rx) { struct lan966x *lan966x = rx->lan966x; @@ -82,6 +90,9 @@ static int lan966x_fdma_rx_alloc(struct lan966x_rx *rx) int i, j; int size; + if (lan966x_fdma_rx_alloc_page_pool(rx)) + return PTR_ERR(rx->page_pool); + /* calculate how many pages are needed to allocate the dcbs */ size = sizeof(struct lan966x_rx_dcb) * FDMA_DCB_MAX; size = ALIGN(size, PAGE_SIZE); @@ -116,6 +127,12 @@ static int lan966x_fdma_rx_alloc(struct lan966x_rx *rx) return 0; } +static void lan966x_fdma_rx_advance_dcb(struct lan966x_rx *rx) +{ + rx->dcb_index++; + rx->dcb_index &= FDMA_DCB_MAX - 1; +} + static void lan966x_fdma_rx_free(struct lan966x_rx *rx) { struct lan966x *lan966x = rx->lan966x; @@ -403,40 +420,58 @@ static bool lan966x_fdma_rx_more_frames(struct lan966x_rx *rx) return true; } -static struct sk_buff *lan966x_fdma_rx_get_frame(struct lan966x_rx *rx) +static int lan966x_fdma_rx_check_frame(struct lan966x_rx *rx, u64 *src_port) { struct lan966x *lan966x = rx->lan966x; - u64 src_port, timestamp; + struct lan966x_port *port; struct lan966x_db *db; - struct sk_buff *skb; struct page *page; - /* Get the received frame and unmap it */ db = &rx->dcbs[rx->dcb_index].db[rx->db_index]; page = rx->page[rx->dcb_index][rx->db_index]; + if (unlikely(!page)) + return FDMA_ERROR; dma_sync_single_for_cpu(lan966x->dev, (dma_addr_t)db->dataptr, FDMA_DCB_STATUS_BLOCKL(db->status), DMA_FROM_DEVICE); + lan966x_ifh_get_src_port(page_address(page), src_port); + if (WARN_ON(*src_port >= lan966x->num_phys_ports)) + return FDMA_ERROR; + + port = lan966x->ports[*src_port]; + if (!lan966x_xdp_port_present(port)) + return FDMA_PASS; + + return lan966x_xdp_run(port, page, FDMA_DCB_STATUS_BLOCKL(db->status)); +} + +static struct sk_buff *lan966x_fdma_rx_get_frame(struct lan966x_rx *rx, + u64 src_port) +{ + struct lan966x *lan966x = rx->lan966x; + struct lan966x_db *db; + struct sk_buff *skb; + struct page *page; + u64 timestamp; + + /* Get the received frame and unmap it */ + db = &rx->dcbs[rx->dcb_index].db[rx->db_index]; + page = rx->page[rx->dcb_index][rx->db_index]; + skb = build_skb(page_address(page), PAGE_SIZE << rx->page_order); if (unlikely(!skb)) - goto unmap_page; + goto free_page; + + skb_mark_for_recycle(skb); skb_put(skb, FDMA_DCB_STATUS_BLOCKL(db->status)); - lan966x_ifh_get_src_port(skb->data, &src_port); lan966x_ifh_get_timestamp(skb->data, ×tamp); - if (WARN_ON(src_port >= lan966x->num_phys_ports)) - goto free_skb; - - dma_unmap_single_attrs(lan966x->dev, (dma_addr_t)db->dataptr, - PAGE_SIZE << rx->page_order, DMA_FROM_DEVICE, - DMA_ATTR_SKIP_CPU_SYNC); - skb->dev = lan966x->ports[src_port]->dev; - skb_pull(skb, IFH_LEN * sizeof(u32)); + skb_pull(skb, IFH_LEN_BYTES); if (likely(!(skb->dev->features & NETIF_F_RXFCS))) skb_trim(skb, skb->len - ETH_FCS_LEN); @@ -457,13 +492,8 @@ static struct sk_buff *lan966x_fdma_rx_get_frame(struct lan966x_rx *rx) return skb; -free_skb: - kfree_skb(skb); -unmap_page: - dma_unmap_single_attrs(lan966x->dev, (dma_addr_t)db->dataptr, - PAGE_SIZE << rx->page_order, DMA_FROM_DEVICE, - DMA_ATTR_SKIP_CPU_SYNC); - __free_pages(page, rx->page_order); +free_page: + page_pool_recycle_direct(rx->page_pool, page); return NULL; } @@ -478,6 +508,7 @@ static int lan966x_fdma_napi_poll(struct napi_struct *napi, int weight) struct sk_buff *skb; struct page *page; int counter = 0; + u64 src_port; u64 nextptr; lan966x_fdma_tx_clear_buf(lan966x, weight); @@ -487,19 +518,30 @@ static int lan966x_fdma_napi_poll(struct napi_struct *napi, int weight) if (!lan966x_fdma_rx_more_frames(rx)) break; - skb = lan966x_fdma_rx_get_frame(rx); + counter++; - rx->page[rx->dcb_index][rx->db_index] = NULL; - rx->dcb_index++; - rx->dcb_index &= FDMA_DCB_MAX - 1; + switch (lan966x_fdma_rx_check_frame(rx, &src_port)) { + case FDMA_PASS: + break; + case FDMA_ERROR: + lan966x_fdma_rx_free_page(rx); + lan966x_fdma_rx_advance_dcb(rx); + goto allocate_new; + case FDMA_DROP: + lan966x_fdma_rx_free_page(rx); + lan966x_fdma_rx_advance_dcb(rx); + continue; + } + skb = lan966x_fdma_rx_get_frame(rx, src_port); + lan966x_fdma_rx_advance_dcb(rx); if (!skb) - break; + goto allocate_new; napi_gro_receive(&lan966x->napi, skb); - counter++; } +allocate_new: /* Allocate new pages and map them */ while (dcb_reload != rx->dcb_index) { db = &rx->dcbs[dcb_reload].db[rx->db_index]; @@ -592,7 +634,7 @@ int lan966x_fdma_xmit(struct sk_buff *skb, __be32 *ifh, struct net_device *dev) } /* skb processing */ - needed_headroom = max_t(int, IFH_LEN * sizeof(u32) - skb_headroom(skb), 0); + needed_headroom = max_t(int, IFH_LEN_BYTES - skb_headroom(skb), 0); needed_tailroom = max_t(int, ETH_FCS_LEN - skb_tailroom(skb), 0); if (needed_headroom || needed_tailroom || skb_header_cloned(skb)) { err = pskb_expand_head(skb, needed_headroom, needed_tailroom, @@ -605,8 +647,8 @@ int lan966x_fdma_xmit(struct sk_buff *skb, __be32 *ifh, struct net_device *dev) } skb_tx_timestamp(skb); - skb_push(skb, IFH_LEN * sizeof(u32)); - memcpy(skb->data, ifh, IFH_LEN * sizeof(u32)); + skb_push(skb, IFH_LEN_BYTES); + memcpy(skb->data, ifh, IFH_LEN_BYTES); skb_put(skb, 4); dma_addr = dma_map_single(lan966x->dev, skb->data, skb->len, @@ -696,6 +738,7 @@ static int lan966x_qsys_sw_status(struct lan966x *lan966x) static int lan966x_fdma_reload(struct lan966x *lan966x, int new_mtu) { + struct page_pool *page_pool; dma_addr_t rx_dma; void *rx_dcbs; u32 size; @@ -704,6 +747,7 @@ static int lan966x_fdma_reload(struct lan966x *lan966x, int new_mtu) /* Store these for later to free them */ rx_dma = lan966x->rx.dma; rx_dcbs = lan966x->rx.dcbs; + page_pool = lan966x->rx.page_pool; napi_synchronize(&lan966x->napi); napi_disable(&lan966x->napi); @@ -712,6 +756,7 @@ static int lan966x_fdma_reload(struct lan966x *lan966x, int new_mtu) lan966x_fdma_rx_disable(&lan966x->rx); lan966x_fdma_rx_free_pages(&lan966x->rx); lan966x->rx.page_order = round_up(new_mtu, PAGE_SIZE) / PAGE_SIZE - 1; + lan966x->rx.max_mtu = new_mtu; err = lan966x_fdma_rx_alloc(&lan966x->rx); if (err) goto restore; @@ -721,11 +766,14 @@ static int lan966x_fdma_reload(struct lan966x *lan966x, int new_mtu) size = ALIGN(size, PAGE_SIZE); dma_free_coherent(lan966x->dev, size, rx_dcbs, rx_dma); + page_pool_destroy(page_pool); + lan966x_fdma_wakeup_netdev(lan966x); napi_enable(&lan966x->napi); return err; restore: + lan966x->rx.page_pool = page_pool; lan966x->rx.dma = rx_dma; lan966x->rx.dcbs = rx_dcbs; lan966x_fdma_rx_start(&lan966x->rx); @@ -733,19 +781,22 @@ restore: return err; } +static int lan966x_fdma_get_max_frame(struct lan966x *lan966x) +{ + return lan966x_fdma_get_max_mtu(lan966x) + + IFH_LEN_BYTES + + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) + + VLAN_HLEN * 2; +} + int lan966x_fdma_change_mtu(struct lan966x *lan966x) { int max_mtu; int err; u32 val; - max_mtu = lan966x_fdma_get_max_mtu(lan966x); - max_mtu += IFH_LEN * sizeof(u32); - max_mtu += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - max_mtu += VLAN_HLEN * 2; - - if (round_up(max_mtu, PAGE_SIZE) / PAGE_SIZE - 1 == - lan966x->rx.page_order) + max_mtu = lan966x_fdma_get_max_frame(lan966x); + if (max_mtu == lan966x->rx.max_mtu) return 0; /* Disable the CPU port */ @@ -800,6 +851,7 @@ int lan966x_fdma_init(struct lan966x *lan966x) lan966x->rx.lan966x = lan966x; lan966x->rx.channel_id = FDMA_XTR_CHANNEL; + lan966x->rx.max_mtu = lan966x_fdma_get_max_frame(lan966x); lan966x->tx.lan966x = lan966x; lan966x->tx.channel_id = FDMA_INJ_CHANNEL; lan966x->tx.last_in_use = -1; @@ -832,5 +884,6 @@ void lan966x_fdma_deinit(struct lan966x *lan966x) lan966x_fdma_rx_free_pages(&lan966x->rx); lan966x_fdma_rx_free(&lan966x->rx); + page_pool_destroy(lan966x->rx.page_pool); lan966x_fdma_tx_free(&lan966x->tx); } diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_ifh.h b/drivers/net/ethernet/microchip/lan966x/lan966x_ifh.h index ca3314789d18..f3b1e0d31826 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_ifh.h +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_ifh.h @@ -8,6 +8,7 @@ */ #define IFH_LEN 7 +#define IFH_LEN_BYTES (IFH_LEN * sizeof(u32)) /* Timestamp for frame */ #define IFH_POS_TIMESTAMP 192 diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c index 20ee5b28f70a..42be5d0f1f01 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c @@ -468,6 +468,7 @@ static const struct net_device_ops lan966x_port_netdev_ops = { .ndo_get_port_parent_id = lan966x_port_get_parent_id, .ndo_eth_ioctl = lan966x_port_ioctl, .ndo_setup_tc = lan966x_tc_setup, + .ndo_bpf = lan966x_xdp, }; bool lan966x_netdevice_check(const struct net_device *dev) @@ -694,6 +695,7 @@ static void lan966x_cleanup_ports(struct lan966x *lan966x) if (port->dev) unregister_netdev(port->dev); + lan966x_xdp_port_deinit(port); if (lan966x->fdma && lan966x->fdma_ndev == port->dev) lan966x_fdma_netdev_deinit(lan966x, port->dev); @@ -760,7 +762,7 @@ static int lan966x_probe_port(struct lan966x *lan966x, u32 p, NETIF_F_HW_VLAN_STAG_TX | NETIF_F_HW_TC; dev->hw_features |= NETIF_F_HW_TC; - dev->needed_headroom = IFH_LEN * sizeof(u32); + dev->needed_headroom = IFH_LEN_BYTES; eth_hw_addr_gen(dev, lan966x->base_mac, p + 1); @@ -1136,6 +1138,9 @@ static int lan966x_probe(struct platform_device *pdev) lan966x->ports[p]->serdes = serdes; lan966x_port_init(lan966x->ports[p]); + err = lan966x_xdp_port_init(lan966x->ports[p]); + if (err) + goto cleanup_ports; } lan966x_mdb_init(lan966x); diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h index 4ec33999e4df..bc93051aa079 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h @@ -9,6 +9,7 @@ #include <linux/phy.h> #include <linux/phylink.h> #include <linux/ptp_clock_kernel.h> +#include <net/page_pool.h> #include <net/pkt_cls.h> #include <net/pkt_sched.h> #include <net/switchdev.h> @@ -100,6 +101,17 @@ enum macaccess_entry_type { ENTRYTYPE_MACV6, }; +/* FDMA return action codes for checking if the frame is valid + * FDMA_PASS, frame is valid and can be used + * FDMA_ERROR, something went wrong, stop getting more frames + * FDMA_DROP, frame is dropped, but continue to get more frames + */ +enum lan966x_fdma_action { + FDMA_PASS = 0, + FDMA_ERROR, + FDMA_DROP, +}; + struct lan966x_port; struct lan966x_db { @@ -150,7 +162,14 @@ struct lan966x_rx { */ u8 page_order; + /* Represents the max size frame that it can receive to the CPU. This + * includes the IFH + VLAN tags + frame + skb_shared_info + */ + u32 max_mtu; + u8 channel_id; + + struct page_pool *page_pool; }; struct lan966x_tx_dcb_buf { @@ -320,6 +339,9 @@ struct lan966x_port { enum netdev_lag_hash hash_type; struct lan966x_port_tc tc; + + struct bpf_prog *xdp_prog; + struct xdp_rxq_info xdp_rxq; }; extern const struct phylink_mac_ops lan966x_phylink_mac_ops; @@ -527,6 +549,17 @@ void lan966x_mirror_port_stats(struct lan966x_port *port, struct flow_stats *stats, bool ingress); +int lan966x_xdp_port_init(struct lan966x_port *port); +void lan966x_xdp_port_deinit(struct lan966x_port *port); +int lan966x_xdp(struct net_device *dev, struct netdev_bpf *xdp); +int lan966x_xdp_run(struct lan966x_port *port, + struct page *page, + u32 data_len); +static inline bool lan966x_xdp_port_present(struct lan966x_port *port) +{ + return !!port->xdp_prog; +} + static inline void __iomem *lan_addr(void __iomem *base[], int id, int tinst, int tcnt, int gbase, int ginst, diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_phylink.c b/drivers/net/ethernet/microchip/lan966x/lan966x_phylink.c index e4ac59480514..c5f9803e6e63 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_phylink.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_phylink.c @@ -5,7 +5,6 @@ #include <linux/device.h> #include <linux/netdevice.h> #include <linux/phy/phy.h> -#include <linux/sfp.h> #include "lan966x_main.h" @@ -125,7 +124,6 @@ static void lan966x_pcs_aneg_restart(struct phylink_pcs *pcs) } const struct phylink_mac_ops lan966x_phylink_mac_ops = { - .validate = phylink_generic_validate, .mac_select_pcs = lan966x_phylink_mac_select, .mac_config = lan966x_phylink_mac_config, .mac_prepare = lan966x_phylink_mac_prepare, diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_xdp.c b/drivers/net/ethernet/microchip/lan966x/lan966x_xdp.c new file mode 100644 index 000000000000..e77d9f2aad2b --- /dev/null +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_xdp.c @@ -0,0 +1,76 @@ +// SPDX-License-Identifier: GPL-2.0+ + +#include <linux/bpf.h> +#include <linux/bpf_trace.h> +#include <linux/filter.h> + +#include "lan966x_main.h" + +static int lan966x_xdp_setup(struct net_device *dev, struct netdev_bpf *xdp) +{ + struct lan966x_port *port = netdev_priv(dev); + struct lan966x *lan966x = port->lan966x; + struct bpf_prog *old_prog; + + if (!lan966x->fdma) { + NL_SET_ERR_MSG_MOD(xdp->extack, + "Allow to set xdp only when using fdma"); + return -EOPNOTSUPP; + } + + old_prog = xchg(&port->xdp_prog, xdp->prog); + if (old_prog) + bpf_prog_put(old_prog); + + return 0; +} + +int lan966x_xdp(struct net_device *dev, struct netdev_bpf *xdp) +{ + switch (xdp->command) { + case XDP_SETUP_PROG: + return lan966x_xdp_setup(dev, xdp); + default: + return -EINVAL; + } +} + +int lan966x_xdp_run(struct lan966x_port *port, struct page *page, u32 data_len) +{ + struct bpf_prog *xdp_prog = port->xdp_prog; + struct lan966x *lan966x = port->lan966x; + struct xdp_buff xdp; + u32 act; + + xdp_init_buff(&xdp, PAGE_SIZE << lan966x->rx.page_order, + &port->xdp_rxq); + xdp_prepare_buff(&xdp, page_address(page), IFH_LEN_BYTES, + data_len - IFH_LEN_BYTES, false); + act = bpf_prog_run_xdp(xdp_prog, &xdp); + switch (act) { + case XDP_PASS: + return FDMA_PASS; + default: + bpf_warn_invalid_xdp_action(port->dev, xdp_prog, act); + fallthrough; + case XDP_ABORTED: + trace_xdp_exception(port->dev, xdp_prog, act); + fallthrough; + case XDP_DROP: + return FDMA_DROP; + } +} + +int lan966x_xdp_port_init(struct lan966x_port *port) +{ + struct lan966x *lan966x = port->lan966x; + + return xdp_rxq_info_reg(&port->xdp_rxq, port->dev, 0, + lan966x->napi.napi_id); +} + +void lan966x_xdp_port_deinit(struct lan966x_port *port) +{ + if (xdp_rxq_info_is_reg(&port->xdp_rxq)) + xdp_rxq_info_unreg(&port->xdp_rxq); +} diff --git a/drivers/net/ethernet/microchip/sparx5/Makefile b/drivers/net/ethernet/microchip/sparx5/Makefile index 38adf917bc09..cff07b8841bd 100644 --- a/drivers/net/ethernet/microchip/sparx5/Makefile +++ b/drivers/net/ethernet/microchip/sparx5/Makefile @@ -9,7 +9,7 @@ sparx5-switch-y := sparx5_main.o sparx5_packet.o \ sparx5_netdev.o sparx5_phylink.o sparx5_port.o sparx5_mactable.o sparx5_vlan.o \ sparx5_switchdev.o sparx5_calendar.o sparx5_ethtool.o sparx5_fdma.o \ sparx5_ptp.o sparx5_pgid.o sparx5_tc.o sparx5_qos.o \ - sparx5_vcap_impl.o sparx5_vcap_ag_api.o sparx5_tc_flower.o + sparx5_vcap_impl.o sparx5_vcap_ag_api.o sparx5_tc_flower.o sparx5_tc_matchall.o sparx5-switch-$(CONFIG_SPARX5_DCB) += sparx5_dcb.o diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_phylink.c b/drivers/net/ethernet/microchip/sparx5/sparx5_phylink.c index 830da0e5ff27..bb97d27a1da4 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_phylink.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_phylink.c @@ -138,7 +138,6 @@ const struct phylink_pcs_ops sparx5_phylink_pcs_ops = { }; const struct phylink_mac_ops sparx5_phylink_mac_ops = { - .validate = phylink_generic_validate, .mac_select_pcs = sparx5_phylink_mac_select_pcs, .mac_config = sparx5_phylink_mac_config, .mac_link_down = sparx5_phylink_mac_link_down, diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_tc.c b/drivers/net/ethernet/microchip/sparx5/sparx5_tc.c index 9432251b8322..edd4c53dcce2 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_tc.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_tc.c @@ -19,9 +19,14 @@ static int sparx5_tc_block_cb(enum tc_setup_type type, { struct net_device *ndev = cb_priv; - if (type == TC_SETUP_CLSFLOWER) + switch (type) { + case TC_SETUP_CLSMATCHALL: + return sparx5_tc_matchall(ndev, type_data, ingress); + case TC_SETUP_CLSFLOWER: return sparx5_tc_flower(ndev, type_data, ingress); - return -EOPNOTSUPP; + default: + return -EOPNOTSUPP; + } } static int sparx5_tc_block_cb_ingress(enum tc_setup_type type, diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_tc.h b/drivers/net/ethernet/microchip/sparx5/sparx5_tc.h index 2b07a93fc9b7..adab88e6b21f 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_tc.h +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_tc.h @@ -8,6 +8,7 @@ #define __SPARX5_TC_H__ #include <net/flow_offload.h> +#include <net/pkt_cls.h> #include <linux/netdevice.h> /* Controls how PORT_MASK is applied */ @@ -23,6 +24,10 @@ enum SPX5_PORT_MASK_MODE { int sparx5_port_setup_tc(struct net_device *ndev, enum tc_setup_type type, void *type_data); +int sparx5_tc_matchall(struct net_device *ndev, + struct tc_cls_matchall_offload *tmo, + bool ingress); + int sparx5_tc_flower(struct net_device *ndev, struct flow_cls_offload *fco, bool ingress); diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c b/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c index 626558a5c850..7b364f6b4546 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c @@ -16,9 +16,32 @@ struct sparx5_tc_flower_parse_usage { struct flow_cls_offload *fco; struct flow_rule *frule; struct vcap_rule *vrule; + u16 l3_proto; + u8 l4_proto; unsigned int used_keys; }; +/* These protocols have dedicated keysets in IS2 and a TC dissector + * ETH_P_ARP does not have a TC dissector + */ +static u16 sparx5_tc_known_etypes[] = { + ETH_P_ALL, + ETH_P_IP, + ETH_P_IPV6, +}; + +static bool sparx5_tc_is_known_etype(u16 etype) +{ + int idx; + + /* For now this only knows about IS2 traffic classification */ + for (idx = 0; idx < ARRAY_SIZE(sparx5_tc_known_etypes); ++idx) + if (sparx5_tc_known_etypes[idx] == etype) + return true; + + return false; +} + static int sparx5_tc_flower_handler_ethaddr_usage(struct sparx5_tc_flower_parse_usage *st) { enum vcap_key_field smac_key = VCAP_KF_L2_SMAC; @@ -54,18 +77,379 @@ out: return err; } +static int +sparx5_tc_flower_handler_ipv4_usage(struct sparx5_tc_flower_parse_usage *st) +{ + int err = 0; + + if (st->l3_proto == ETH_P_IP) { + struct flow_match_ipv4_addrs mt; + + flow_rule_match_ipv4_addrs(st->frule, &mt); + if (mt.mask->src) { + err = vcap_rule_add_key_u32(st->vrule, + VCAP_KF_L3_IP4_SIP, + be32_to_cpu(mt.key->src), + be32_to_cpu(mt.mask->src)); + if (err) + goto out; + } + if (mt.mask->dst) { + err = vcap_rule_add_key_u32(st->vrule, + VCAP_KF_L3_IP4_DIP, + be32_to_cpu(mt.key->dst), + be32_to_cpu(mt.mask->dst)); + if (err) + goto out; + } + } + + st->used_keys |= BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS); + + return err; + +out: + NL_SET_ERR_MSG_MOD(st->fco->common.extack, "ipv4_addr parse error"); + return err; +} + +static int +sparx5_tc_flower_handler_ipv6_usage(struct sparx5_tc_flower_parse_usage *st) +{ + int err = 0; + + if (st->l3_proto == ETH_P_IPV6) { + struct flow_match_ipv6_addrs mt; + struct vcap_u128_key sip; + struct vcap_u128_key dip; + + flow_rule_match_ipv6_addrs(st->frule, &mt); + /* Check if address masks are non-zero */ + if (!ipv6_addr_any(&mt.mask->src)) { + vcap_netbytes_copy(sip.value, mt.key->src.s6_addr, 16); + vcap_netbytes_copy(sip.mask, mt.mask->src.s6_addr, 16); + err = vcap_rule_add_key_u128(st->vrule, + VCAP_KF_L3_IP6_SIP, &sip); + if (err) + goto out; + } + if (!ipv6_addr_any(&mt.mask->dst)) { + vcap_netbytes_copy(dip.value, mt.key->dst.s6_addr, 16); + vcap_netbytes_copy(dip.mask, mt.mask->dst.s6_addr, 16); + err = vcap_rule_add_key_u128(st->vrule, + VCAP_KF_L3_IP6_DIP, &dip); + if (err) + goto out; + } + } + st->used_keys |= BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS); + return err; +out: + NL_SET_ERR_MSG_MOD(st->fco->common.extack, "ipv6_addr parse error"); + return err; +} + +static int +sparx5_tc_flower_handler_control_usage(struct sparx5_tc_flower_parse_usage *st) +{ + struct flow_match_control mt; + u32 value, mask; + int err = 0; + + flow_rule_match_control(st->frule, &mt); + + if (mt.mask->flags) { + if (mt.mask->flags & FLOW_DIS_FIRST_FRAG) { + if (mt.key->flags & FLOW_DIS_FIRST_FRAG) { + value = 1; /* initial fragment */ + mask = 0x3; + } else { + if (mt.mask->flags & FLOW_DIS_IS_FRAGMENT) { + value = 3; /* follow up fragment */ + mask = 0x3; + } else { + value = 0; /* no fragment */ + mask = 0x3; + } + } + } else { + if (mt.mask->flags & FLOW_DIS_IS_FRAGMENT) { + value = 3; /* follow up fragment */ + mask = 0x3; + } else { + value = 0; /* no fragment */ + mask = 0x3; + } + } + + err = vcap_rule_add_key_u32(st->vrule, + VCAP_KF_L3_FRAGMENT_TYPE, + value, mask); + if (err) + goto out; + } + + st->used_keys |= BIT(FLOW_DISSECTOR_KEY_CONTROL); + + return err; + +out: + NL_SET_ERR_MSG_MOD(st->fco->common.extack, "ip_frag parse error"); + return err; +} + +static int +sparx5_tc_flower_handler_portnum_usage(struct sparx5_tc_flower_parse_usage *st) +{ + struct flow_match_ports mt; + u16 value, mask; + int err = 0; + + flow_rule_match_ports(st->frule, &mt); + + if (mt.mask->src) { + value = be16_to_cpu(mt.key->src); + mask = be16_to_cpu(mt.mask->src); + err = vcap_rule_add_key_u32(st->vrule, VCAP_KF_L4_SPORT, value, + mask); + if (err) + goto out; + } + + if (mt.mask->dst) { + value = be16_to_cpu(mt.key->dst); + mask = be16_to_cpu(mt.mask->dst); + err = vcap_rule_add_key_u32(st->vrule, VCAP_KF_L4_DPORT, value, + mask); + if (err) + goto out; + } + + st->used_keys |= BIT(FLOW_DISSECTOR_KEY_PORTS); + + return err; + +out: + NL_SET_ERR_MSG_MOD(st->fco->common.extack, "port parse error"); + return err; +} + +static int +sparx5_tc_flower_handler_basic_usage(struct sparx5_tc_flower_parse_usage *st) +{ + struct flow_match_basic mt; + int err = 0; + + flow_rule_match_basic(st->frule, &mt); + + if (mt.mask->n_proto) { + st->l3_proto = be16_to_cpu(mt.key->n_proto); + if (!sparx5_tc_is_known_etype(st->l3_proto)) { + err = vcap_rule_add_key_u32(st->vrule, VCAP_KF_ETYPE, + st->l3_proto, ~0); + if (err) + goto out; + } else if (st->l3_proto == ETH_P_IP) { + err = vcap_rule_add_key_bit(st->vrule, VCAP_KF_IP4_IS, + VCAP_BIT_1); + if (err) + goto out; + } else if (st->l3_proto == ETH_P_IPV6) { + err = vcap_rule_add_key_bit(st->vrule, VCAP_KF_IP4_IS, + VCAP_BIT_0); + if (err) + goto out; + } + } + + if (mt.mask->ip_proto) { + st->l4_proto = mt.key->ip_proto; + if (st->l4_proto == IPPROTO_TCP) { + err = vcap_rule_add_key_bit(st->vrule, + VCAP_KF_TCP_IS, + VCAP_BIT_1); + if (err) + goto out; + } else if (st->l4_proto == IPPROTO_UDP) { + err = vcap_rule_add_key_bit(st->vrule, + VCAP_KF_TCP_IS, + VCAP_BIT_0); + if (err) + goto out; + } else { + err = vcap_rule_add_key_u32(st->vrule, + VCAP_KF_L3_IP_PROTO, + st->l4_proto, ~0); + if (err) + goto out; + } + } + + st->used_keys |= BIT(FLOW_DISSECTOR_KEY_BASIC); + + return err; + +out: + NL_SET_ERR_MSG_MOD(st->fco->common.extack, "ip_proto parse error"); + return err; +} + +static int +sparx5_tc_flower_handler_vlan_usage(struct sparx5_tc_flower_parse_usage *st) +{ + enum vcap_key_field vid_key = VCAP_KF_8021Q_VID_CLS; + enum vcap_key_field pcp_key = VCAP_KF_8021Q_PCP_CLS; + struct flow_match_vlan mt; + int err; + + flow_rule_match_vlan(st->frule, &mt); + + if (mt.mask->vlan_id) { + err = vcap_rule_add_key_u32(st->vrule, vid_key, + mt.key->vlan_id, + mt.mask->vlan_id); + if (err) + goto out; + } + + if (mt.mask->vlan_priority) { + err = vcap_rule_add_key_u32(st->vrule, pcp_key, + mt.key->vlan_priority, + mt.mask->vlan_priority); + if (err) + goto out; + } + + st->used_keys |= BIT(FLOW_DISSECTOR_KEY_VLAN); + + return err; +out: + NL_SET_ERR_MSG_MOD(st->fco->common.extack, "vlan parse error"); + return err; +} + +static int +sparx5_tc_flower_handler_tcp_usage(struct sparx5_tc_flower_parse_usage *st) +{ + struct flow_match_tcp mt; + u16 tcp_flags_mask; + u16 tcp_flags_key; + enum vcap_bit val; + int err = 0; + + flow_rule_match_tcp(st->frule, &mt); + tcp_flags_key = be16_to_cpu(mt.key->flags); + tcp_flags_mask = be16_to_cpu(mt.mask->flags); + + if (tcp_flags_mask & TCPHDR_FIN) { + val = VCAP_BIT_0; + if (tcp_flags_key & TCPHDR_FIN) + val = VCAP_BIT_1; + err = vcap_rule_add_key_bit(st->vrule, VCAP_KF_L4_FIN, val); + if (err) + goto out; + } + + if (tcp_flags_mask & TCPHDR_SYN) { + val = VCAP_BIT_0; + if (tcp_flags_key & TCPHDR_SYN) + val = VCAP_BIT_1; + err = vcap_rule_add_key_bit(st->vrule, VCAP_KF_L4_SYN, val); + if (err) + goto out; + } + + if (tcp_flags_mask & TCPHDR_RST) { + val = VCAP_BIT_0; + if (tcp_flags_key & TCPHDR_RST) + val = VCAP_BIT_1; + err = vcap_rule_add_key_bit(st->vrule, VCAP_KF_L4_RST, val); + if (err) + goto out; + } + + if (tcp_flags_mask & TCPHDR_PSH) { + val = VCAP_BIT_0; + if (tcp_flags_key & TCPHDR_PSH) + val = VCAP_BIT_1; + err = vcap_rule_add_key_bit(st->vrule, VCAP_KF_L4_PSH, val); + if (err) + goto out; + } + + if (tcp_flags_mask & TCPHDR_ACK) { + val = VCAP_BIT_0; + if (tcp_flags_key & TCPHDR_ACK) + val = VCAP_BIT_1; + err = vcap_rule_add_key_bit(st->vrule, VCAP_KF_L4_ACK, val); + if (err) + goto out; + } + + if (tcp_flags_mask & TCPHDR_URG) { + val = VCAP_BIT_0; + if (tcp_flags_key & TCPHDR_URG) + val = VCAP_BIT_1; + err = vcap_rule_add_key_bit(st->vrule, VCAP_KF_L4_URG, val); + if (err) + goto out; + } + + st->used_keys |= BIT(FLOW_DISSECTOR_KEY_TCP); + + return err; + +out: + NL_SET_ERR_MSG_MOD(st->fco->common.extack, "tcp_flags parse error"); + return err; +} + +static int +sparx5_tc_flower_handler_ip_usage(struct sparx5_tc_flower_parse_usage *st) +{ + struct flow_match_ip mt; + int err = 0; + + flow_rule_match_ip(st->frule, &mt); + + if (mt.mask->tos) { + err = vcap_rule_add_key_u32(st->vrule, VCAP_KF_L3_TOS, + mt.key->tos, + mt.mask->tos); + if (err) + goto out; + } + + st->used_keys |= BIT(FLOW_DISSECTOR_KEY_IP); + + return err; + +out: + NL_SET_ERR_MSG_MOD(st->fco->common.extack, "ip_tos parse error"); + return err; +} + static int (*sparx5_tc_flower_usage_handlers[])(struct sparx5_tc_flower_parse_usage *st) = { - /* More dissector handlers will be added here later */ [FLOW_DISSECTOR_KEY_ETH_ADDRS] = sparx5_tc_flower_handler_ethaddr_usage, + [FLOW_DISSECTOR_KEY_IPV4_ADDRS] = sparx5_tc_flower_handler_ipv4_usage, + [FLOW_DISSECTOR_KEY_IPV6_ADDRS] = sparx5_tc_flower_handler_ipv6_usage, + [FLOW_DISSECTOR_KEY_CONTROL] = sparx5_tc_flower_handler_control_usage, + [FLOW_DISSECTOR_KEY_PORTS] = sparx5_tc_flower_handler_portnum_usage, + [FLOW_DISSECTOR_KEY_BASIC] = sparx5_tc_flower_handler_basic_usage, + [FLOW_DISSECTOR_KEY_VLAN] = sparx5_tc_flower_handler_vlan_usage, + [FLOW_DISSECTOR_KEY_TCP] = sparx5_tc_flower_handler_tcp_usage, + [FLOW_DISSECTOR_KEY_IP] = sparx5_tc_flower_handler_ip_usage, }; static int sparx5_tc_use_dissectors(struct flow_cls_offload *fco, struct vcap_admin *admin, - struct vcap_rule *vrule) + struct vcap_rule *vrule, + u16 *l3_proto) { struct sparx5_tc_flower_parse_usage state = { .fco = fco, .vrule = vrule, + .l3_proto = ETH_P_ALL, }; int idx, err = 0; @@ -79,9 +463,72 @@ static int sparx5_tc_use_dissectors(struct flow_cls_offload *fco, if (err) return err; } + + if (state.frule->match.dissector->used_keys ^ state.used_keys) { + NL_SET_ERR_MSG_MOD(fco->common.extack, + "Unsupported match item"); + return -ENOENT; + } + + if (l3_proto) + *l3_proto = state.l3_proto; return err; } +static int sparx5_tc_flower_action_check(struct vcap_control *vctrl, + struct flow_cls_offload *fco, + struct vcap_admin *admin) +{ + struct flow_rule *rule = flow_cls_offload_flow_rule(fco); + struct flow_action_entry *actent, *last_actent = NULL; + struct flow_action *act = &rule->action; + u64 action_mask = 0; + int idx; + + if (!flow_action_has_entries(act)) { + NL_SET_ERR_MSG_MOD(fco->common.extack, "No actions"); + return -EINVAL; + } + + if (!flow_action_basic_hw_stats_check(act, fco->common.extack)) + return -EOPNOTSUPP; + + flow_action_for_each(idx, actent, act) { + if (action_mask & BIT(actent->id)) { + NL_SET_ERR_MSG_MOD(fco->common.extack, + "More actions of the same type"); + return -EINVAL; + } + action_mask |= BIT(actent->id); + last_actent = actent; /* Save last action for later check */ + } + + /* Check that last action is a goto */ + if (last_actent->id != FLOW_ACTION_GOTO) { + NL_SET_ERR_MSG_MOD(fco->common.extack, + "Last action must be 'goto'"); + return -EINVAL; + } + + /* Check if the goto chain is in the next lookup */ + if (!vcap_is_next_lookup(vctrl, fco->common.chain_index, + last_actent->chain_index)) { + NL_SET_ERR_MSG_MOD(fco->common.extack, + "Invalid goto chain"); + return -EINVAL; + } + + /* Catch unsupported combinations of actions */ + if (action_mask & BIT(FLOW_ACTION_TRAP) && + action_mask & BIT(FLOW_ACTION_ACCEPT)) { + NL_SET_ERR_MSG_MOD(fco->common.extack, + "Cannot combine pass and trap action"); + return -EOPNOTSUPP; + } + + return 0; +} + static int sparx5_tc_flower_replace(struct net_device *ndev, struct flow_cls_offload *fco, struct vcap_admin *admin) @@ -91,25 +538,23 @@ static int sparx5_tc_flower_replace(struct net_device *ndev, struct vcap_control *vctrl; struct flow_rule *frule; struct vcap_rule *vrule; + u16 l3_proto; int err, idx; - frule = flow_cls_offload_flow_rule(fco); - if (!flow_action_has_entries(&frule->action)) { - NL_SET_ERR_MSG_MOD(fco->common.extack, "No actions"); - return -EINVAL; - } + vctrl = port->sparx5->vcap_ctrl; - if (!flow_action_basic_hw_stats_check(&frule->action, fco->common.extack)) - return -EOPNOTSUPP; + err = sparx5_tc_flower_action_check(vctrl, fco, admin); + if (err) + return err; - vctrl = port->sparx5->vcap_ctrl; vrule = vcap_alloc_rule(vctrl, ndev, fco->common.chain_index, VCAP_USER_TC, fco->common.prio, 0); if (IS_ERR(vrule)) return PTR_ERR(vrule); vrule->cookie = fco->cookie; - sparx5_tc_use_dissectors(fco, admin, vrule); + sparx5_tc_use_dissectors(fco, admin, vrule, &l3_proto); + frule = flow_cls_offload_flow_rule(fco); flow_action_for_each(idx, act, &frule->action) { switch (act->id) { case FLOW_ACTION_TRAP: @@ -139,6 +584,9 @@ static int sparx5_tc_flower_replace(struct net_device *ndev, if (err) goto out; break; + case FLOW_ACTION_GOTO: + /* Links between VCAPs will be added later */ + break; default: NL_SET_ERR_MSG_MOD(fco->common.extack, "Unsupported TC action"); @@ -146,14 +594,8 @@ static int sparx5_tc_flower_replace(struct net_device *ndev, goto out; } } - /* For now the keyset is hardcoded */ - err = vcap_set_rule_set_keyset(vrule, VCAP_KFS_MAC_ETYPE); - if (err) { - NL_SET_ERR_MSG_MOD(fco->common.extack, - "No matching port keyset for filter protocol and keys"); - goto out; - } - err = vcap_val_rule(vrule, ETH_P_ALL); + /* provide the l3 protocol to guide the keyset selection */ + err = vcap_val_rule(vrule, l3_proto); if (err) { vcap_set_tc_exterr(fco, vrule); goto out; diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_tc_matchall.c b/drivers/net/ethernet/microchip/sparx5/sparx5_tc_matchall.c new file mode 100644 index 000000000000..30dd61e5d150 --- /dev/null +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_tc_matchall.c @@ -0,0 +1,97 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Microchip VCAP API + * + * Copyright (c) 2022 Microchip Technology Inc. and its subsidiaries. + */ + +#include "sparx5_tc.h" +#include "vcap_api.h" +#include "vcap_api_client.h" +#include "sparx5_main_regs.h" +#include "sparx5_main.h" +#include "sparx5_vcap_impl.h" + +static int sparx5_tc_matchall_replace(struct net_device *ndev, + struct tc_cls_matchall_offload *tmo, + bool ingress) +{ + struct sparx5_port *port = netdev_priv(ndev); + struct flow_action_entry *action; + struct sparx5 *sparx5; + int err; + + if (!flow_offload_has_one_action(&tmo->rule->action)) { + NL_SET_ERR_MSG_MOD(tmo->common.extack, + "Only one action per filter is supported"); + return -EOPNOTSUPP; + } + action = &tmo->rule->action.entries[0]; + + sparx5 = port->sparx5; + switch (action->id) { + case FLOW_ACTION_GOTO: + err = vcap_enable_lookups(sparx5->vcap_ctrl, ndev, + action->chain_index, tmo->cookie, + true); + if (err == -EFAULT) { + NL_SET_ERR_MSG_MOD(tmo->common.extack, + "Unsupported goto chain"); + return -EOPNOTSUPP; + } + if (err == -EADDRINUSE) { + NL_SET_ERR_MSG_MOD(tmo->common.extack, + "VCAP already enabled"); + return -EOPNOTSUPP; + } + if (err) { + NL_SET_ERR_MSG_MOD(tmo->common.extack, + "Could not enable VCAP lookups"); + return err; + } + break; + default: + NL_SET_ERR_MSG_MOD(tmo->common.extack, "Unsupported action"); + return -EOPNOTSUPP; + } + return 0; +} + +static int sparx5_tc_matchall_destroy(struct net_device *ndev, + struct tc_cls_matchall_offload *tmo, + bool ingress) +{ + struct sparx5_port *port = netdev_priv(ndev); + struct sparx5 *sparx5; + int err; + + sparx5 = port->sparx5; + if (!tmo->rule && tmo->cookie) { + err = vcap_enable_lookups(sparx5->vcap_ctrl, ndev, 0, + tmo->cookie, false); + if (err) + return err; + return 0; + } + NL_SET_ERR_MSG_MOD(tmo->common.extack, "Unsupported action"); + return -EOPNOTSUPP; +} + +int sparx5_tc_matchall(struct net_device *ndev, + struct tc_cls_matchall_offload *tmo, + bool ingress) +{ + if (!tc_cls_can_offload_and_chain0(ndev, &tmo->common)) { + NL_SET_ERR_MSG_MOD(tmo->common.extack, + "Only chain zero is supported"); + return -EOPNOTSUPP; + } + + switch (tmo->command) { + case TC_CLSMATCHALL_REPLACE: + return sparx5_tc_matchall_replace(ndev, tmo, ingress); + case TC_CLSMATCHALL_DESTROY: + return sparx5_tc_matchall_destroy(ndev, tmo, ingress); + default: + return -EOPNOTSUPP; + } +} diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_impl.c b/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_impl.c index 50153264179e..10bc56cd0045 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_impl.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_vcap_impl.c @@ -21,6 +21,14 @@ #define STREAMSIZE (64 * 4) /* bytes in the VCAP cache area */ #define SPARX5_IS2_LOOKUPS 4 +#define VCAP_IS2_KEYSEL(_ena, _noneth, _v4_mc, _v4_uc, _v6_mc, _v6_uc, _arp) \ + (ANA_ACL_VCAP_S2_KEY_SEL_KEY_SEL_ENA_SET(_ena) | \ + ANA_ACL_VCAP_S2_KEY_SEL_NON_ETH_KEY_SEL_SET(_noneth) | \ + ANA_ACL_VCAP_S2_KEY_SEL_IP4_MC_KEY_SEL_SET(_v4_mc) | \ + ANA_ACL_VCAP_S2_KEY_SEL_IP4_UC_KEY_SEL_SET(_v4_uc) | \ + ANA_ACL_VCAP_S2_KEY_SEL_IP6_MC_KEY_SEL_SET(_v6_mc) | \ + ANA_ACL_VCAP_S2_KEY_SEL_IP6_UC_KEY_SEL_SET(_v6_uc) | \ + ANA_ACL_VCAP_S2_KEY_SEL_ARP_KEY_SEL_SET(_arp)) /* IS2 port keyset selection control */ @@ -152,7 +160,7 @@ static const char *sparx5_vcap_keyset_name(struct net_device *ndev, { struct sparx5_port *port = netdev_priv(ndev); - return port->sparx5->vcap_ctrl->stats->keyfield_set_names[keyset]; + return vcap_keyset_name(port->sparx5->vcap_ctrl, keyset); } /* Check if this is the first lookup of IS2 */ @@ -196,6 +204,127 @@ static void sparx5_vcap_add_wide_port_mask(struct vcap_rule *rule, vcap_rule_add_key_u72(rule, VCAP_KF_IF_IGR_PORT_MASK, &port_mask); } +/* Convert chain id to vcap lookup id */ +static int sparx5_vcap_cid_to_lookup(int cid) +{ + int lookup = 0; + + /* For now only handle IS2 */ + if (cid >= SPARX5_VCAP_CID_IS2_L1 && cid < SPARX5_VCAP_CID_IS2_L2) + lookup = 1; + else if (cid >= SPARX5_VCAP_CID_IS2_L2 && cid < SPARX5_VCAP_CID_IS2_L3) + lookup = 2; + else if (cid >= SPARX5_VCAP_CID_IS2_L3 && cid < SPARX5_VCAP_CID_IS2_MAX) + lookup = 3; + + return lookup; +} + +/* Return the list of keysets for the vcap port configuration */ +static int sparx5_vcap_is2_get_port_keysets(struct net_device *ndev, + int lookup, + struct vcap_keyset_list *keysetlist, + u16 l3_proto) +{ + struct sparx5_port *port = netdev_priv(ndev); + struct sparx5 *sparx5 = port->sparx5; + int portno = port->portno; + u32 value; + + /* Check if the port keyset selection is enabled */ + value = spx5_rd(sparx5, ANA_ACL_VCAP_S2_KEY_SEL(portno, lookup)); + if (!ANA_ACL_VCAP_S2_KEY_SEL_KEY_SEL_ENA_GET(value)) + return -ENOENT; + + /* Collect all keysets for the port in a list */ + if (l3_proto == ETH_P_ALL || l3_proto == ETH_P_ARP) { + switch (ANA_ACL_VCAP_S2_KEY_SEL_ARP_KEY_SEL_GET(value)) { + case VCAP_IS2_PS_ARP_MAC_ETYPE: + vcap_keyset_list_add(keysetlist, VCAP_KFS_MAC_ETYPE); + break; + case VCAP_IS2_PS_ARP_ARP: + vcap_keyset_list_add(keysetlist, VCAP_KFS_ARP); + break; + } + } + + if (l3_proto == ETH_P_ALL || l3_proto == ETH_P_IP) { + switch (ANA_ACL_VCAP_S2_KEY_SEL_IP4_UC_KEY_SEL_GET(value)) { + case VCAP_IS2_PS_IPV4_UC_MAC_ETYPE: + vcap_keyset_list_add(keysetlist, VCAP_KFS_MAC_ETYPE); + break; + case VCAP_IS2_PS_IPV4_UC_IP4_TCP_UDP_OTHER: + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP4_TCP_UDP); + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP4_OTHER); + break; + case VCAP_IS2_PS_IPV4_UC_IP_7TUPLE: + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP_7TUPLE); + break; + } + + switch (ANA_ACL_VCAP_S2_KEY_SEL_IP4_MC_KEY_SEL_GET(value)) { + case VCAP_IS2_PS_IPV4_MC_MAC_ETYPE: + vcap_keyset_list_add(keysetlist, VCAP_KFS_MAC_ETYPE); + break; + case VCAP_IS2_PS_IPV4_MC_IP4_TCP_UDP_OTHER: + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP4_TCP_UDP); + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP4_OTHER); + break; + case VCAP_IS2_PS_IPV4_MC_IP_7TUPLE: + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP_7TUPLE); + break; + } + } + + if (l3_proto == ETH_P_ALL || l3_proto == ETH_P_IPV6) { + switch (ANA_ACL_VCAP_S2_KEY_SEL_IP6_UC_KEY_SEL_GET(value)) { + case VCAP_IS2_PS_IPV6_UC_MAC_ETYPE: + vcap_keyset_list_add(keysetlist, VCAP_KFS_MAC_ETYPE); + break; + case VCAP_IS2_PS_IPV6_UC_IP_7TUPLE: + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP_7TUPLE); + break; + case VCAP_IS2_PS_IPV6_UC_IP6_STD: + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP6_STD); + break; + case VCAP_IS2_PS_IPV6_UC_IP4_TCP_UDP_OTHER: + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP4_TCP_UDP); + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP4_OTHER); + break; + } + + switch (ANA_ACL_VCAP_S2_KEY_SEL_IP6_MC_KEY_SEL_GET(value)) { + case VCAP_IS2_PS_IPV6_MC_MAC_ETYPE: + vcap_keyset_list_add(keysetlist, VCAP_KFS_MAC_ETYPE); + break; + case VCAP_IS2_PS_IPV6_MC_IP_7TUPLE: + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP_7TUPLE); + break; + case VCAP_IS2_PS_IPV6_MC_IP6_STD: + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP6_STD); + break; + case VCAP_IS2_PS_IPV6_MC_IP4_TCP_UDP_OTHER: + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP4_TCP_UDP); + vcap_keyset_list_add(keysetlist, VCAP_KFS_IP4_OTHER); + break; + case VCAP_IS2_PS_IPV6_MC_IP6_VID: + /* Not used */ + break; + } + } + + if (l3_proto != ETH_P_ARP && l3_proto != ETH_P_IP && + l3_proto != ETH_P_IPV6) { + switch (ANA_ACL_VCAP_S2_KEY_SEL_NON_ETH_KEY_SEL_GET(value)) { + case VCAP_IS2_PS_NONETH_MAC_ETYPE: + /* IS2 non-classified frames generate MAC_ETYPE */ + vcap_keyset_list_add(keysetlist, VCAP_KFS_MAC_ETYPE); + break; + } + } + return 0; +} + /* API callback used for validating a field keyset (check the port keysets) */ static enum vcap_keyfield_set sparx5_vcap_validate_keyset(struct net_device *ndev, @@ -204,10 +333,30 @@ sparx5_vcap_validate_keyset(struct net_device *ndev, struct vcap_keyset_list *kslist, u16 l3_proto) { + struct vcap_keyset_list keysetlist = {}; + enum vcap_keyfield_set keysets[10] = {}; + int idx, jdx, lookup; + if (!kslist || kslist->cnt == 0) return VCAP_KFS_NO_VALUE; - /* for now just return whatever the API suggests */ - return kslist->keysets[0]; + + /* Get a list of currently configured keysets in the lookups */ + lookup = sparx5_vcap_cid_to_lookup(rule->vcap_chain_id); + keysetlist.max = ARRAY_SIZE(keysets); + keysetlist.keysets = keysets; + sparx5_vcap_is2_get_port_keysets(ndev, lookup, &keysetlist, l3_proto); + + /* Check if there is a match and return the match */ + for (idx = 0; idx < kslist->cnt; ++idx) + for (jdx = 0; jdx < keysetlist.cnt; ++jdx) + if (kslist->keysets[idx] == keysets[jdx]) + return kslist->keysets[idx]; + + pr_err("%s:%d: %s not supported in port key selection\n", + __func__, __LINE__, + sparx5_vcap_keyset_name(ndev, kslist->keysets[0])); + + return -ENOENT; } /* API callback used for adding default fields to a rule */ @@ -340,6 +489,28 @@ static int sparx5_port_info(struct net_device *ndev, enum vcap_type vtype, return 0; } +/* Enable all lookups in the VCAP instance */ +static int sparx5_vcap_enable(struct net_device *ndev, + struct vcap_admin *admin, + bool enable) +{ + struct sparx5_port *port = netdev_priv(ndev); + struct sparx5 *sparx5; + int portno; + + sparx5 = port->sparx5; + portno = port->portno; + + /* For now we only consider IS2 */ + if (enable) + spx5_wr(ANA_ACL_VCAP_S2_CFG_SEC_ENA_SET(0xf), sparx5, + ANA_ACL_VCAP_S2_CFG(portno)); + else + spx5_wr(ANA_ACL_VCAP_S2_CFG_SEC_ENA_SET(0), sparx5, + ANA_ACL_VCAP_S2_CFG(portno)); + return 0; +} + /* API callback operations: only IS2 is supported for now */ static struct vcap_operations sparx5_vcap_ops = { .validate_keyset = sparx5_vcap_validate_keyset, @@ -351,6 +522,7 @@ static struct vcap_operations sparx5_vcap_ops = { .update = sparx5_vcap_update, .move = sparx5_vcap_move, .port_info = sparx5_port_info, + .enable = sparx5_vcap_enable, }; /* Enable lookups per port and set the keyset generation: only IS2 for now */ @@ -360,21 +532,15 @@ static void sparx5_vcap_port_key_selection(struct sparx5 *sparx5, int portno, lookup; u32 keysel; - /* enable all 4 lookups on all ports */ - for (portno = 0; portno < SPX5_PORTS; ++portno) - spx5_wr(ANA_ACL_VCAP_S2_CFG_SEC_ENA_SET(0xf), sparx5, - ANA_ACL_VCAP_S2_CFG(portno)); - /* all traffic types generate the MAC_ETYPE keyset for now in all * lookups on all ports */ - keysel = ANA_ACL_VCAP_S2_KEY_SEL_KEY_SEL_ENA_SET(true) | - ANA_ACL_VCAP_S2_KEY_SEL_NON_ETH_KEY_SEL_SET(VCAP_IS2_PS_NONETH_MAC_ETYPE) | - ANA_ACL_VCAP_S2_KEY_SEL_IP4_MC_KEY_SEL_SET(VCAP_IS2_PS_IPV4_MC_MAC_ETYPE) | - ANA_ACL_VCAP_S2_KEY_SEL_IP4_UC_KEY_SEL_SET(VCAP_IS2_PS_IPV4_UC_MAC_ETYPE) | - ANA_ACL_VCAP_S2_KEY_SEL_IP6_MC_KEY_SEL_SET(VCAP_IS2_PS_IPV6_MC_MAC_ETYPE) | - ANA_ACL_VCAP_S2_KEY_SEL_IP6_UC_KEY_SEL_SET(VCAP_IS2_PS_IPV6_UC_MAC_ETYPE) | - ANA_ACL_VCAP_S2_KEY_SEL_ARP_KEY_SEL_SET(VCAP_IS2_PS_ARP_MAC_ETYPE); + keysel = VCAP_IS2_KEYSEL(true, VCAP_IS2_PS_NONETH_MAC_ETYPE, + VCAP_IS2_PS_IPV4_MC_IP4_TCP_UDP_OTHER, + VCAP_IS2_PS_IPV4_UC_IP4_TCP_UDP_OTHER, + VCAP_IS2_PS_IPV6_MC_IP_7TUPLE, + VCAP_IS2_PS_IPV6_UC_IP_7TUPLE, + VCAP_IS2_PS_ARP_MAC_ETYPE); for (lookup = 0; lookup < admin->lookups; ++lookup) { for (portno = 0; portno < SPX5_PORTS; ++portno) { spx5_wr(keysel, sparx5, @@ -418,6 +584,7 @@ sparx5_vcap_admin_alloc(struct sparx5 *sparx5, struct vcap_control *ctrl, return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&admin->list); INIT_LIST_HEAD(&admin->rules); + INIT_LIST_HEAD(&admin->enabled); admin->vtype = cfg->vtype; admin->vinst = cfg->vinst; admin->lookups = cfg->lookups; diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api.c b/drivers/net/ethernet/microchip/vcap/vcap_api.c index d255bc7deae7..b6ab6bae28c0 100644 --- a/drivers/net/ethernet/microchip/vcap/vcap_api.c +++ b/drivers/net/ethernet/microchip/vcap/vcap_api.c @@ -44,6 +44,13 @@ struct vcap_stream_iter { const struct vcap_typegroup *tg; /* current typegroup */ }; +/* Stores the filter cookie that enabled the port */ +struct vcap_enabled_port { + struct list_head list; /* for insertion in enabled ports list */ + struct net_device *ndev; /* the enabled port */ + unsigned long cookie; /* filter that enabled the port */ +}; + static void vcap_iter_set(struct vcap_stream_iter *itr, int sw_width, const struct vcap_typegroup *tg, u32 offset) { @@ -516,7 +523,7 @@ static int vcap_api_check(struct vcap_control *ctrl) !ctrl->ops->add_default_fields || !ctrl->ops->cache_erase || !ctrl->ops->cache_write || !ctrl->ops->cache_read || !ctrl->ops->init || !ctrl->ops->update || !ctrl->ops->move || - !ctrl->ops->port_info) { + !ctrl->ops->port_info || !ctrl->ops->enable) { pr_err("%s:%d: client operations are missing\n", __func__, __LINE__); return -ENOENT; @@ -644,6 +651,23 @@ static int vcap_write_rule(struct vcap_rule_internal *ri) return 0; } +/* Convert a chain id to a VCAP lookup index */ +int vcap_chain_id_to_lookup(struct vcap_admin *admin, int cur_cid) +{ + int lookup_first = admin->vinst * admin->lookups_per_instance; + int lookup_last = lookup_first + admin->lookups_per_instance; + int cid_next = admin->first_cid + VCAP_CID_LOOKUP_SIZE; + int cid = admin->first_cid; + int lookup; + + for (lookup = lookup_first; lookup < lookup_last; ++lookup, + cid += VCAP_CID_LOOKUP_SIZE, cid_next += VCAP_CID_LOOKUP_SIZE) + if (cur_cid >= cid && cur_cid < cid_next) + return lookup; + return 0; +} +EXPORT_SYMBOL_GPL(vcap_chain_id_to_lookup); + /* Lookup a vcap instance using chain id */ struct vcap_admin *vcap_find_admin(struct vcap_control *vctrl, int cid) { @@ -660,6 +684,42 @@ struct vcap_admin *vcap_find_admin(struct vcap_control *vctrl, int cid) } EXPORT_SYMBOL_GPL(vcap_find_admin); +/* Is the next chain id in the following lookup, possible in another VCAP */ +bool vcap_is_next_lookup(struct vcap_control *vctrl, int cur_cid, int next_cid) +{ + struct vcap_admin *admin, *next_admin; + int lookup, next_lookup; + + /* The offset must be at least one lookup */ + if (next_cid < cur_cid + VCAP_CID_LOOKUP_SIZE) + return false; + + if (vcap_api_check(vctrl)) + return false; + + admin = vcap_find_admin(vctrl, cur_cid); + if (!admin) + return false; + + /* If no VCAP contains the next chain, the next chain must be beyond + * the last chain in the current VCAP + */ + next_admin = vcap_find_admin(vctrl, next_cid); + if (!next_admin) + return next_cid > admin->last_cid; + + lookup = vcap_chain_id_to_lookup(admin, cur_cid); + next_lookup = vcap_chain_id_to_lookup(next_admin, next_cid); + + /* Next lookup must be the following lookup */ + if (admin == next_admin || admin->vtype == next_admin->vtype) + return next_lookup == lookup + 1; + + /* Must be the first lookup in the next VCAP instance */ + return next_lookup == 0; +} +EXPORT_SYMBOL_GPL(vcap_is_next_lookup); + /* Check if there is room for a new rule */ static int vcap_rule_space(struct vcap_admin *admin, int size) { @@ -704,15 +764,122 @@ static int vcap_add_type_keyfield(struct vcap_rule *rule) return 0; } +/* Add a keyset to a keyset list */ +bool vcap_keyset_list_add(struct vcap_keyset_list *keysetlist, + enum vcap_keyfield_set keyset) +{ + int idx; + + if (keysetlist->cnt < keysetlist->max) { + /* Avoid duplicates */ + for (idx = 0; idx < keysetlist->cnt; ++idx) + if (keysetlist->keysets[idx] == keyset) + return keysetlist->cnt < keysetlist->max; + keysetlist->keysets[keysetlist->cnt++] = keyset; + } + return keysetlist->cnt < keysetlist->max; +} +EXPORT_SYMBOL_GPL(vcap_keyset_list_add); + +/* map keyset id to a string with the keyset name */ +const char *vcap_keyset_name(struct vcap_control *vctrl, + enum vcap_keyfield_set keyset) +{ + return vctrl->stats->keyfield_set_names[keyset]; +} +EXPORT_SYMBOL_GPL(vcap_keyset_name); + +/* map key field id to a string with the key name */ +const char *vcap_keyfield_name(struct vcap_control *vctrl, + enum vcap_key_field key) +{ + return vctrl->stats->keyfield_names[key]; +} +EXPORT_SYMBOL_GPL(vcap_keyfield_name); + +/* map action field id to a string with the action name */ +static const char *vcap_actionfield_name(struct vcap_control *vctrl, + enum vcap_action_field action) +{ + return vctrl->stats->actionfield_names[action]; +} + +/* Return the keyfield that matches a key in a keyset */ +static const struct vcap_field * +vcap_find_keyset_keyfield(struct vcap_control *vctrl, + enum vcap_type vtype, + enum vcap_keyfield_set keyset, + enum vcap_key_field key) +{ + const struct vcap_field *fields; + int idx, count; + + fields = vcap_keyfields(vctrl, vtype, keyset); + if (!fields) + return NULL; + + /* Iterate the keyfields of the keyset */ + count = vcap_keyfield_count(vctrl, vtype, keyset); + for (idx = 0; idx < count; ++idx) { + if (fields[idx].width == 0) + continue; + + if (key == idx) + return &fields[idx]; + } + + return NULL; +} + +/* Match a list of keys against the keysets available in a vcap type */ +static bool vcap_rule_find_keysets(struct vcap_rule_internal *ri, + struct vcap_keyset_list *matches) +{ + const struct vcap_client_keyfield *ckf; + int keyset, found, keycount, map_size; + const struct vcap_field **map; + enum vcap_type vtype; + + vtype = ri->admin->vtype; + map = ri->vctrl->vcaps[vtype].keyfield_set_map; + map_size = ri->vctrl->vcaps[vtype].keyfield_set_size; + + /* Get a count of the keyfields we want to match */ + keycount = 0; + list_for_each_entry(ckf, &ri->data.keyfields, ctrl.list) + ++keycount; + + matches->cnt = 0; + /* Iterate the keysets of the VCAP */ + for (keyset = 0; keyset < map_size; ++keyset) { + if (!map[keyset]) + continue; + + /* Iterate the keys in the rule */ + found = 0; + list_for_each_entry(ckf, &ri->data.keyfields, ctrl.list) + if (vcap_find_keyset_keyfield(ri->vctrl, vtype, + keyset, ckf->ctrl.key)) + ++found; + + /* Save the keyset if all keyfields were found */ + if (found == keycount) + if (!vcap_keyset_list_add(matches, keyset)) + /* bail out when the quota is filled */ + break; + } + + return matches->cnt > 0; +} + /* Validate a rule with respect to available port keys */ int vcap_val_rule(struct vcap_rule *rule, u16 l3_proto) { struct vcap_rule_internal *ri = to_intrule(rule); + struct vcap_keyset_list matches = {}; enum vcap_keyfield_set keysets[10]; - struct vcap_keyset_list kslist; int ret; - /* This validation will be much expanded later */ ret = vcap_api_check(ri->vctrl); if (ret) return ret; @@ -724,24 +891,41 @@ int vcap_val_rule(struct vcap_rule *rule, u16 l3_proto) ri->data.exterr = VCAP_ERR_NO_NETDEV; return -EINVAL; } + + matches.keysets = keysets; + matches.max = ARRAY_SIZE(keysets); if (ri->data.keyset == VCAP_KFS_NO_VALUE) { - ri->data.exterr = VCAP_ERR_NO_KEYSET_MATCH; - return -EINVAL; + /* Iterate over rule keyfields and select keysets that fits */ + if (!vcap_rule_find_keysets(ri, &matches)) { + ri->data.exterr = VCAP_ERR_NO_KEYSET_MATCH; + return -EINVAL; + } + } else { + /* prepare for keyset validation */ + keysets[0] = ri->data.keyset; + matches.cnt = 1; } - /* prepare for keyset validation */ - keysets[0] = ri->data.keyset; - kslist.keysets = keysets; - kslist.cnt = 1; + /* Pick a keyset that is supported in the port lookups */ - ret = ri->vctrl->ops->validate_keyset(ri->ndev, ri->admin, rule, &kslist, - l3_proto); + ret = ri->vctrl->ops->validate_keyset(ri->ndev, ri->admin, rule, + &matches, l3_proto); if (ret < 0) { pr_err("%s:%d: keyset validation failed: %d\n", __func__, __LINE__, ret); ri->data.exterr = VCAP_ERR_NO_PORT_KEYSET_MATCH; return ret; } + /* use the keyset that is supported in the port lookups */ + ret = vcap_set_rule_set_keyset(rule, ret); + if (ret < 0) { + pr_err("%s:%d: keyset was not updated: %d\n", + __func__, __LINE__, ret); + return ret; + } if (ri->data.actionset == VCAP_AFS_NO_VALUE) { + /* Later also actionsets will be matched against actions in + * the rule, and the type will be set accordingly + */ ri->data.exterr = VCAP_ERR_NO_ACTIONSET_MATCH; return -EINVAL; } @@ -951,6 +1135,7 @@ EXPORT_SYMBOL_GPL(vcap_del_rule); /* Delete all rules in the VCAP instance */ int vcap_del_rules(struct vcap_control *vctrl, struct vcap_admin *admin) { + struct vcap_enabled_port *eport, *next_eport; struct vcap_rule_internal *ri, *next_ri; int ret = vcap_api_check(vctrl); @@ -962,6 +1147,13 @@ int vcap_del_rules(struct vcap_control *vctrl, struct vcap_admin *admin) kfree(ri); } admin->last_used_addr = admin->last_valid_addr; + + /* Remove list of enabled ports */ + list_for_each_entry_safe(eport, next_eport, &admin->enabled, list) { + list_del(&eport->list); + kfree(eport); + } + return 0; } EXPORT_SYMBOL_GPL(vcap_del_rules); @@ -992,14 +1184,60 @@ static void vcap_copy_from_client_keyfield(struct vcap_rule *rule, memcpy(&field->data, data, sizeof(field->data)); } +/* Check if the keyfield is already in the rule */ +static bool vcap_keyfield_unique(struct vcap_rule *rule, + enum vcap_key_field key) +{ + struct vcap_rule_internal *ri = to_intrule(rule); + const struct vcap_client_keyfield *ckf; + + list_for_each_entry(ckf, &ri->data.keyfields, ctrl.list) + if (ckf->ctrl.key == key) + return false; + return true; +} + +/* Check if the keyfield is in the keyset */ +static bool vcap_keyfield_match_keyset(struct vcap_rule *rule, + enum vcap_key_field key) +{ + struct vcap_rule_internal *ri = to_intrule(rule); + enum vcap_keyfield_set keyset = rule->keyset; + enum vcap_type vt = ri->admin->vtype; + const struct vcap_field *fields; + + /* the field is accepted if the rule has no keyset yet */ + if (keyset == VCAP_KFS_NO_VALUE) + return true; + fields = vcap_keyfields(ri->vctrl, vt, keyset); + if (!fields) + return false; + /* if there is a width there is a way */ + return fields[key].width > 0; +} + static int vcap_rule_add_key(struct vcap_rule *rule, enum vcap_key_field key, enum vcap_field_type ftype, struct vcap_client_keyfield_data *data) { + struct vcap_rule_internal *ri = to_intrule(rule); struct vcap_client_keyfield *field; - /* More validation will be added here later */ + if (!vcap_keyfield_unique(rule, key)) { + pr_warn("%s:%d: keyfield %s is already in the rule\n", + __func__, __LINE__, + vcap_keyfield_name(ri->vctrl, key)); + return -EINVAL; + } + + if (!vcap_keyfield_match_keyset(rule, key)) { + pr_err("%s:%d: keyfield %s does not belong in the rule keyset\n", + __func__, __LINE__, + vcap_keyfield_name(ri->vctrl, key)); + return -EINVAL; + } + field = kzalloc(sizeof(*field), GFP_KERNEL); if (!field) return -ENOMEM; @@ -1073,6 +1311,17 @@ int vcap_rule_add_key_u72(struct vcap_rule *rule, enum vcap_key_field key, } EXPORT_SYMBOL_GPL(vcap_rule_add_key_u72); +/* Add a 128 bit key with value and mask to the rule */ +int vcap_rule_add_key_u128(struct vcap_rule *rule, enum vcap_key_field key, + struct vcap_u128_key *fieldval) +{ + struct vcap_client_keyfield_data data; + + memcpy(&data.u128, fieldval, sizeof(data.u128)); + return vcap_rule_add_key(rule, key, VCAP_FIELD_U128, &data); +} +EXPORT_SYMBOL_GPL(vcap_rule_add_key_u128); + static void vcap_copy_from_client_actionfield(struct vcap_rule *rule, struct vcap_client_actionfield *field, struct vcap_client_actionfield_data *data) @@ -1081,14 +1330,60 @@ static void vcap_copy_from_client_actionfield(struct vcap_rule *rule, memcpy(&field->data, data, sizeof(field->data)); } +/* Check if the actionfield is already in the rule */ +static bool vcap_actionfield_unique(struct vcap_rule *rule, + enum vcap_action_field act) +{ + struct vcap_rule_internal *ri = to_intrule(rule); + const struct vcap_client_actionfield *caf; + + list_for_each_entry(caf, &ri->data.actionfields, ctrl.list) + if (caf->ctrl.action == act) + return false; + return true; +} + +/* Check if the actionfield is in the actionset */ +static bool vcap_actionfield_match_actionset(struct vcap_rule *rule, + enum vcap_action_field action) +{ + enum vcap_actionfield_set actionset = rule->actionset; + struct vcap_rule_internal *ri = to_intrule(rule); + enum vcap_type vt = ri->admin->vtype; + const struct vcap_field *fields; + + /* the field is accepted if the rule has no actionset yet */ + if (actionset == VCAP_AFS_NO_VALUE) + return true; + fields = vcap_actionfields(ri->vctrl, vt, actionset); + if (!fields) + return false; + /* if there is a width there is a way */ + return fields[action].width > 0; +} + static int vcap_rule_add_action(struct vcap_rule *rule, enum vcap_action_field action, enum vcap_field_type ftype, struct vcap_client_actionfield_data *data) { + struct vcap_rule_internal *ri = to_intrule(rule); struct vcap_client_actionfield *field; - /* More validation will be added here later */ + if (!vcap_actionfield_unique(rule, action)) { + pr_warn("%s:%d: actionfield %s is already in the rule\n", + __func__, __LINE__, + vcap_actionfield_name(ri->vctrl, action)); + return -EINVAL; + } + + if (!vcap_actionfield_match_actionset(rule, action)) { + pr_err("%s:%d: actionfield %s does not belong in the rule actionset\n", + __func__, __LINE__, + vcap_actionfield_name(ri->vctrl, action)); + return -EINVAL; + } + field = kzalloc(sizeof(*field), GFP_KERNEL); if (!field) return -ENOMEM; @@ -1179,6 +1474,109 @@ void vcap_set_tc_exterr(struct flow_cls_offload *fco, struct vcap_rule *vrule) } EXPORT_SYMBOL_GPL(vcap_set_tc_exterr); +/* Check if this port is already enabled for this VCAP instance */ +static bool vcap_is_enabled(struct vcap_admin *admin, struct net_device *ndev, + unsigned long cookie) +{ + struct vcap_enabled_port *eport; + + list_for_each_entry(eport, &admin->enabled, list) + if (eport->cookie == cookie || eport->ndev == ndev) + return true; + + return false; +} + +/* Enable this port for this VCAP instance */ +static int vcap_enable(struct vcap_admin *admin, struct net_device *ndev, + unsigned long cookie) +{ + struct vcap_enabled_port *eport; + + eport = kzalloc(sizeof(*eport), GFP_KERNEL); + if (!eport) + return -ENOMEM; + + eport->ndev = ndev; + eport->cookie = cookie; + list_add_tail(&eport->list, &admin->enabled); + + return 0; +} + +/* Disable this port for this VCAP instance */ +static int vcap_disable(struct vcap_admin *admin, struct net_device *ndev, + unsigned long cookie) +{ + struct vcap_enabled_port *eport; + + list_for_each_entry(eport, &admin->enabled, list) { + if (eport->cookie == cookie && eport->ndev == ndev) { + list_del(&eport->list); + kfree(eport); + return 0; + } + } + + return -ENOENT; +} + +/* Find the VCAP instance that enabled the port using a specific filter */ +static struct vcap_admin *vcap_find_admin_by_cookie(struct vcap_control *vctrl, + unsigned long cookie) +{ + struct vcap_enabled_port *eport; + struct vcap_admin *admin; + + list_for_each_entry(admin, &vctrl->list, list) + list_for_each_entry(eport, &admin->enabled, list) + if (eport->cookie == cookie) + return admin; + + return NULL; +} + +/* Enable/Disable the VCAP instance lookups. Chain id 0 means disable */ +int vcap_enable_lookups(struct vcap_control *vctrl, struct net_device *ndev, + int chain_id, unsigned long cookie, bool enable) +{ + struct vcap_admin *admin; + int err; + + err = vcap_api_check(vctrl); + if (err) + return err; + + if (!ndev) + return -ENODEV; + + if (chain_id) + admin = vcap_find_admin(vctrl, chain_id); + else + admin = vcap_find_admin_by_cookie(vctrl, cookie); + if (!admin) + return -ENOENT; + + /* first instance and first chain */ + if (admin->vinst || chain_id > admin->first_cid) + return -EFAULT; + + err = vctrl->ops->enable(ndev, admin, enable); + if (err) + return err; + + if (chain_id) { + if (vcap_is_enabled(admin, ndev, cookie)) + return -EADDRINUSE; + vcap_enable(admin, ndev, cookie); + } else { + vcap_disable(admin, ndev, cookie); + } + + return 0; +} +EXPORT_SYMBOL_GPL(vcap_enable_lookups); + #ifdef CONFIG_VCAP_KUNIT_TEST #include "vcap_api_kunit.c" #endif diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api.h b/drivers/net/ethernet/microchip/vcap/vcap_api.h index eb2eae75c7e8..bfb8ad535074 100644 --- a/drivers/net/ethernet/microchip/vcap/vcap_api.h +++ b/drivers/net/ethernet/microchip/vcap/vcap_api.h @@ -166,6 +166,7 @@ enum vcap_rule_error { struct vcap_admin { struct list_head list; /* for insertion in vcap_control */ struct list_head rules; /* list of rules */ + struct list_head enabled; /* list of enabled ports */ enum vcap_type vtype; /* type of vcap */ int vinst; /* instance number within the same type */ int first_cid; /* first chain id in this vcap */ @@ -255,6 +256,11 @@ struct vcap_operations { int (*pf)(void *out, int arg, const char *fmt, ...), void *out, int arg); + /* enable/disable the lookups in a vcap instance */ + int (*enable) + (struct net_device *ndev, + struct vcap_admin *admin, + bool enable); }; /* VCAP API Client control interface */ diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api_client.h b/drivers/net/ethernet/microchip/vcap/vcap_api_client.h index 5df6808679ff..0ea5ec96adc8 100644 --- a/drivers/net/ethernet/microchip/vcap/vcap_api_client.h +++ b/drivers/net/ethernet/microchip/vcap/vcap_api_client.h @@ -143,6 +143,10 @@ enum vcap_bit { VCAP_BIT_1 }; +/* Enable/Disable the VCAP instance lookups. Chain id 0 means disable */ +int vcap_enable_lookups(struct vcap_control *vctrl, struct net_device *ndev, + int chain_id, unsigned long cookie, bool enable); + /* VCAP rule operations */ /* Allocate a rule and fill in the basic information */ struct vcap_rule *vcap_alloc_rule(struct vcap_control *vctrl, @@ -176,12 +180,16 @@ int vcap_rule_add_key_u48(struct vcap_rule *rule, enum vcap_key_field key, struct vcap_u48_key *fieldval); int vcap_rule_add_key_u72(struct vcap_rule *rule, enum vcap_key_field key, struct vcap_u72_key *fieldval); +int vcap_rule_add_key_u128(struct vcap_rule *rule, enum vcap_key_field key, + struct vcap_u128_key *fieldval); int vcap_rule_add_action_bit(struct vcap_rule *rule, enum vcap_action_field action, enum vcap_bit val); int vcap_rule_add_action_u32(struct vcap_rule *rule, enum vcap_action_field action, u32 value); /* VCAP lookup operations */ +/* Convert a chain id to a VCAP lookup index */ +int vcap_chain_id_to_lookup(struct vcap_admin *admin, int cur_cid); /* Lookup a vcap instance using chain id */ struct vcap_admin *vcap_find_admin(struct vcap_control *vctrl, int cid); /* Find information on a key field in a rule */ @@ -189,6 +197,8 @@ const struct vcap_field *vcap_lookup_keyfield(struct vcap_rule *rule, enum vcap_key_field key); /* Find a rule id with a provided cookie */ int vcap_lookup_rule_by_cookie(struct vcap_control *vctrl, u64 cookie); +/* Is the next chain id in the following lookup, possible in another VCAP */ +bool vcap_is_next_lookup(struct vcap_control *vctrl, int cur_cid, int next_cid); /* Copy to host byte order */ void vcap_netbytes_copy(u8 *dst, u8 *src, int count); @@ -199,4 +209,15 @@ void vcap_set_tc_exterr(struct flow_cls_offload *fco, struct vcap_rule *vrule); /* Cleanup a VCAP instance */ int vcap_del_rules(struct vcap_control *vctrl, struct vcap_admin *admin); +/* Add a keyset to a keyset list */ +bool vcap_keyset_list_add(struct vcap_keyset_list *keysetlist, + enum vcap_keyfield_set keyset); + +/* map keyset id to a string with the keyset name */ +const char *vcap_keyset_name(struct vcap_control *vctrl, + enum vcap_keyfield_set keyset); +/* map key field id to a string with the key name */ +const char *vcap_keyfield_name(struct vcap_control *vctrl, + enum vcap_key_field key); + #endif /* __VCAP_API_CLIENT__ */ diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c b/drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c index d142ed660338..b0ec51b37683 100644 --- a/drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c +++ b/drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c @@ -22,6 +22,7 @@ static u32 test_init_start; static u32 test_init_count; static u32 test_hw_counter_id; static struct vcap_cache_data test_hw_cache; +static struct net_device test_netdev = {}; /* Callback used by the VCAP API */ static enum vcap_keyfield_set test_val_keyset(struct net_device *ndev, @@ -204,6 +205,13 @@ static int vcap_test_port_info(struct net_device *ndev, enum vcap_type vtype, return 0; } +static int vcap_test_enable(struct net_device *ndev, + struct vcap_admin *admin, + bool enable) +{ + return 0; +} + static struct vcap_operations test_callbacks = { .validate_keyset = test_val_keyset, .add_default_fields = test_add_def_fields, @@ -214,6 +222,7 @@ static struct vcap_operations test_callbacks = { .update = test_cache_update, .move = test_cache_move, .port_info = vcap_test_port_info, + .enable = vcap_test_enable, }; static struct vcap_control test_vctrl = { @@ -904,6 +913,586 @@ static void vcap_api_encode_rule_actionset_test(struct kunit *test) KUNIT_EXPECT_EQ(test, (u32)0x00000000, actwords[11]); } +static void vcap_api_rule_add_keyvalue_test(struct kunit *test) +{ + struct vcap_admin admin = { + .vtype = VCAP_TYPE_IS2, + }; + struct vcap_rule_internal ri = { + .admin = &admin, + .data = { + .keyset = VCAP_KFS_NO_VALUE, + }, + .vctrl = &test_vctrl, + }; + struct vcap_rule *rule = (struct vcap_rule *)&ri; + struct vcap_client_keyfield *kf; + int ret; + struct vcap_u128_key dip = { + .value = {0x17, 0x26, 0x35, 0x44, 0x63, 0x62, 0x71}, + .mask = {0xf1, 0xf2, 0xf3, 0xf4, 0x4f, 0x3f, 0x2f, 0x1f}, + }; + int idx; + + INIT_LIST_HEAD(&rule->keyfields); + ret = vcap_rule_add_key_bit(rule, VCAP_KF_LOOKUP_FIRST_IS, VCAP_BIT_0); + KUNIT_EXPECT_EQ(test, 0, ret); + ret = list_empty(&rule->keyfields); + KUNIT_EXPECT_EQ(test, false, ret); + kf = list_first_entry(&rule->keyfields, struct vcap_client_keyfield, + ctrl.list); + KUNIT_EXPECT_EQ(test, VCAP_KF_LOOKUP_FIRST_IS, kf->ctrl.key); + KUNIT_EXPECT_EQ(test, VCAP_FIELD_BIT, kf->ctrl.type); + KUNIT_EXPECT_EQ(test, 0x0, kf->data.u1.value); + KUNIT_EXPECT_EQ(test, 0x1, kf->data.u1.mask); + + INIT_LIST_HEAD(&rule->keyfields); + ret = vcap_rule_add_key_bit(rule, VCAP_KF_LOOKUP_FIRST_IS, VCAP_BIT_1); + KUNIT_EXPECT_EQ(test, 0, ret); + ret = list_empty(&rule->keyfields); + KUNIT_EXPECT_EQ(test, false, ret); + kf = list_first_entry(&rule->keyfields, struct vcap_client_keyfield, + ctrl.list); + KUNIT_EXPECT_EQ(test, VCAP_KF_LOOKUP_FIRST_IS, kf->ctrl.key); + KUNIT_EXPECT_EQ(test, VCAP_FIELD_BIT, kf->ctrl.type); + KUNIT_EXPECT_EQ(test, 0x1, kf->data.u1.value); + KUNIT_EXPECT_EQ(test, 0x1, kf->data.u1.mask); + + INIT_LIST_HEAD(&rule->keyfields); + ret = vcap_rule_add_key_bit(rule, VCAP_KF_LOOKUP_FIRST_IS, + VCAP_BIT_ANY); + KUNIT_EXPECT_EQ(test, 0, ret); + ret = list_empty(&rule->keyfields); + KUNIT_EXPECT_EQ(test, false, ret); + kf = list_first_entry(&rule->keyfields, struct vcap_client_keyfield, + ctrl.list); + KUNIT_EXPECT_EQ(test, VCAP_KF_LOOKUP_FIRST_IS, kf->ctrl.key); + KUNIT_EXPECT_EQ(test, VCAP_FIELD_BIT, kf->ctrl.type); + KUNIT_EXPECT_EQ(test, 0x0, kf->data.u1.value); + KUNIT_EXPECT_EQ(test, 0x0, kf->data.u1.mask); + + INIT_LIST_HEAD(&rule->keyfields); + ret = vcap_rule_add_key_u32(rule, VCAP_KF_TYPE, 0x98765432, 0xff00ffab); + KUNIT_EXPECT_EQ(test, 0, ret); + ret = list_empty(&rule->keyfields); + KUNIT_EXPECT_EQ(test, false, ret); + kf = list_first_entry(&rule->keyfields, struct vcap_client_keyfield, + ctrl.list); + KUNIT_EXPECT_EQ(test, VCAP_KF_TYPE, kf->ctrl.key); + KUNIT_EXPECT_EQ(test, VCAP_FIELD_U32, kf->ctrl.type); + KUNIT_EXPECT_EQ(test, 0x98765432, kf->data.u32.value); + KUNIT_EXPECT_EQ(test, 0xff00ffab, kf->data.u32.mask); + + INIT_LIST_HEAD(&rule->keyfields); + ret = vcap_rule_add_key_u128(rule, VCAP_KF_L3_IP6_SIP, &dip); + KUNIT_EXPECT_EQ(test, 0, ret); + ret = list_empty(&rule->keyfields); + KUNIT_EXPECT_EQ(test, false, ret); + kf = list_first_entry(&rule->keyfields, struct vcap_client_keyfield, + ctrl.list); + KUNIT_EXPECT_EQ(test, VCAP_KF_L3_IP6_SIP, kf->ctrl.key); + KUNIT_EXPECT_EQ(test, VCAP_FIELD_U128, kf->ctrl.type); + for (idx = 0; idx < ARRAY_SIZE(dip.value); ++idx) + KUNIT_EXPECT_EQ(test, dip.value[idx], kf->data.u128.value[idx]); + for (idx = 0; idx < ARRAY_SIZE(dip.mask); ++idx) + KUNIT_EXPECT_EQ(test, dip.mask[idx], kf->data.u128.mask[idx]); +} + +static void vcap_api_rule_add_actionvalue_test(struct kunit *test) +{ + struct vcap_admin admin = { + .vtype = VCAP_TYPE_IS2, + }; + struct vcap_rule_internal ri = { + .admin = &admin, + .data = { + .actionset = VCAP_AFS_NO_VALUE, + }, + }; + struct vcap_rule *rule = (struct vcap_rule *)&ri; + struct vcap_client_actionfield *af; + int ret; + + INIT_LIST_HEAD(&rule->actionfields); + ret = vcap_rule_add_action_bit(rule, VCAP_AF_POLICE_ENA, VCAP_BIT_0); + KUNIT_EXPECT_EQ(test, 0, ret); + ret = list_empty(&rule->actionfields); + KUNIT_EXPECT_EQ(test, false, ret); + af = list_first_entry(&rule->actionfields, + struct vcap_client_actionfield, ctrl.list); + KUNIT_EXPECT_EQ(test, VCAP_AF_POLICE_ENA, af->ctrl.action); + KUNIT_EXPECT_EQ(test, VCAP_FIELD_BIT, af->ctrl.type); + KUNIT_EXPECT_EQ(test, 0x0, af->data.u1.value); + + INIT_LIST_HEAD(&rule->actionfields); + ret = vcap_rule_add_action_bit(rule, VCAP_AF_POLICE_ENA, VCAP_BIT_1); + KUNIT_EXPECT_EQ(test, 0, ret); + ret = list_empty(&rule->actionfields); + KUNIT_EXPECT_EQ(test, false, ret); + af = list_first_entry(&rule->actionfields, + struct vcap_client_actionfield, ctrl.list); + KUNIT_EXPECT_EQ(test, VCAP_AF_POLICE_ENA, af->ctrl.action); + KUNIT_EXPECT_EQ(test, VCAP_FIELD_BIT, af->ctrl.type); + KUNIT_EXPECT_EQ(test, 0x1, af->data.u1.value); + + INIT_LIST_HEAD(&rule->actionfields); + ret = vcap_rule_add_action_bit(rule, VCAP_AF_POLICE_ENA, VCAP_BIT_ANY); + KUNIT_EXPECT_EQ(test, 0, ret); + ret = list_empty(&rule->actionfields); + KUNIT_EXPECT_EQ(test, false, ret); + af = list_first_entry(&rule->actionfields, + struct vcap_client_actionfield, ctrl.list); + KUNIT_EXPECT_EQ(test, VCAP_AF_POLICE_ENA, af->ctrl.action); + KUNIT_EXPECT_EQ(test, VCAP_FIELD_BIT, af->ctrl.type); + KUNIT_EXPECT_EQ(test, 0x0, af->data.u1.value); + + INIT_LIST_HEAD(&rule->actionfields); + ret = vcap_rule_add_action_u32(rule, VCAP_AF_TYPE, 0x98765432); + KUNIT_EXPECT_EQ(test, 0, ret); + ret = list_empty(&rule->actionfields); + KUNIT_EXPECT_EQ(test, false, ret); + af = list_first_entry(&rule->actionfields, + struct vcap_client_actionfield, ctrl.list); + KUNIT_EXPECT_EQ(test, VCAP_AF_TYPE, af->ctrl.action); + KUNIT_EXPECT_EQ(test, VCAP_FIELD_U32, af->ctrl.type); + KUNIT_EXPECT_EQ(test, 0x98765432, af->data.u32.value); + + INIT_LIST_HEAD(&rule->actionfields); + ret = vcap_rule_add_action_u32(rule, VCAP_AF_MASK_MODE, 0xaabbccdd); + KUNIT_EXPECT_EQ(test, 0, ret); + ret = list_empty(&rule->actionfields); + KUNIT_EXPECT_EQ(test, false, ret); + af = list_first_entry(&rule->actionfields, + struct vcap_client_actionfield, ctrl.list); + KUNIT_EXPECT_EQ(test, VCAP_AF_MASK_MODE, af->ctrl.action); + KUNIT_EXPECT_EQ(test, VCAP_FIELD_U32, af->ctrl.type); + KUNIT_EXPECT_EQ(test, 0xaabbccdd, af->data.u32.value); +} + +static void vcap_api_rule_find_keyset_basic_test(struct kunit *test) +{ + struct vcap_keyset_list matches = {}; + struct vcap_admin admin = { + .vtype = VCAP_TYPE_IS2, + }; + struct vcap_rule_internal ri = { + .admin = &admin, + .vctrl = &test_vctrl, + }; + struct vcap_client_keyfield ckf[] = { + { + .ctrl.key = VCAP_KF_TYPE, + }, { + .ctrl.key = VCAP_KF_LOOKUP_FIRST_IS, + }, { + .ctrl.key = VCAP_KF_IF_IGR_PORT_MASK_L3, + }, { + .ctrl.key = VCAP_KF_IF_IGR_PORT_MASK_RNG, + }, { + .ctrl.key = VCAP_KF_IF_IGR_PORT_MASK, + }, { + .ctrl.key = VCAP_KF_L2_DMAC, + }, { + .ctrl.key = VCAP_KF_ETYPE_LEN_IS, + }, { + .ctrl.key = VCAP_KF_ETYPE, + }, + }; + int idx; + bool ret; + enum vcap_keyfield_set keysets[10] = {}; + + matches.keysets = keysets; + matches.max = ARRAY_SIZE(keysets); + + INIT_LIST_HEAD(&ri.data.keyfields); + for (idx = 0; idx < ARRAY_SIZE(ckf); idx++) + list_add_tail(&ckf[idx].ctrl.list, &ri.data.keyfields); + + ret = vcap_rule_find_keysets(&ri, &matches); + + KUNIT_EXPECT_EQ(test, true, ret); + KUNIT_EXPECT_EQ(test, 1, matches.cnt); + KUNIT_EXPECT_EQ(test, VCAP_KFS_MAC_ETYPE, matches.keysets[0]); +} + +static void vcap_api_rule_find_keyset_failed_test(struct kunit *test) +{ + struct vcap_keyset_list matches = {}; + struct vcap_admin admin = { + .vtype = VCAP_TYPE_IS2, + }; + struct vcap_rule_internal ri = { + .admin = &admin, + .vctrl = &test_vctrl, + }; + struct vcap_client_keyfield ckf[] = { + { + .ctrl.key = VCAP_KF_TYPE, + }, { + .ctrl.key = VCAP_KF_LOOKUP_FIRST_IS, + }, { + .ctrl.key = VCAP_KF_ARP_OPCODE, + }, { + .ctrl.key = VCAP_KF_L3_IP4_SIP, + }, { + .ctrl.key = VCAP_KF_L3_IP4_DIP, + }, { + .ctrl.key = VCAP_KF_8021Q_PCP_CLS, + }, { + .ctrl.key = VCAP_KF_ETYPE_LEN_IS, /* Not with ARP */ + }, { + .ctrl.key = VCAP_KF_ETYPE, /* Not with ARP */ + }, + }; + int idx; + bool ret; + enum vcap_keyfield_set keysets[10] = {}; + + matches.keysets = keysets; + matches.max = ARRAY_SIZE(keysets); + + INIT_LIST_HEAD(&ri.data.keyfields); + for (idx = 0; idx < ARRAY_SIZE(ckf); idx++) + list_add_tail(&ckf[idx].ctrl.list, &ri.data.keyfields); + + ret = vcap_rule_find_keysets(&ri, &matches); + + KUNIT_EXPECT_EQ(test, false, ret); + KUNIT_EXPECT_EQ(test, 0, matches.cnt); + KUNIT_EXPECT_EQ(test, VCAP_KFS_NO_VALUE, matches.keysets[0]); +} + +static void vcap_api_rule_find_keyset_many_test(struct kunit *test) +{ + struct vcap_keyset_list matches = {}; + struct vcap_admin admin = { + .vtype = VCAP_TYPE_IS2, + }; + struct vcap_rule_internal ri = { + .admin = &admin, + .vctrl = &test_vctrl, + }; + struct vcap_client_keyfield ckf[] = { + { + .ctrl.key = VCAP_KF_TYPE, + }, { + .ctrl.key = VCAP_KF_LOOKUP_FIRST_IS, + }, { + .ctrl.key = VCAP_KF_8021Q_DEI_CLS, + }, { + .ctrl.key = VCAP_KF_8021Q_PCP_CLS, + }, { + .ctrl.key = VCAP_KF_8021Q_VID_CLS, + }, { + .ctrl.key = VCAP_KF_ISDX_CLS, + }, { + .ctrl.key = VCAP_KF_L2_MC_IS, + }, { + .ctrl.key = VCAP_KF_L2_BC_IS, + }, + }; + int idx; + bool ret; + enum vcap_keyfield_set keysets[10] = {}; + + matches.keysets = keysets; + matches.max = ARRAY_SIZE(keysets); + + INIT_LIST_HEAD(&ri.data.keyfields); + for (idx = 0; idx < ARRAY_SIZE(ckf); idx++) + list_add_tail(&ckf[idx].ctrl.list, &ri.data.keyfields); + + ret = vcap_rule_find_keysets(&ri, &matches); + + KUNIT_EXPECT_EQ(test, true, ret); + KUNIT_EXPECT_EQ(test, 6, matches.cnt); + KUNIT_EXPECT_EQ(test, VCAP_KFS_ARP, matches.keysets[0]); + KUNIT_EXPECT_EQ(test, VCAP_KFS_IP4_OTHER, matches.keysets[1]); + KUNIT_EXPECT_EQ(test, VCAP_KFS_IP4_TCP_UDP, matches.keysets[2]); + KUNIT_EXPECT_EQ(test, VCAP_KFS_IP6_STD, matches.keysets[3]); + KUNIT_EXPECT_EQ(test, VCAP_KFS_IP_7TUPLE, matches.keysets[4]); + KUNIT_EXPECT_EQ(test, VCAP_KFS_MAC_ETYPE, matches.keysets[5]); +} + +static void vcap_api_encode_rule_test(struct kunit *test) +{ + /* Data used by VCAP Library callback */ + static u32 keydata[32] = {}; + static u32 mskdata[32] = {}; + static u32 actdata[32] = {}; + + struct vcap_admin is2_admin = { + .vtype = VCAP_TYPE_IS2, + .first_cid = 10000, + .last_cid = 19999, + .lookups = 4, + .last_valid_addr = 3071, + .first_valid_addr = 0, + .last_used_addr = 800, + .cache = { + .keystream = keydata, + .maskstream = mskdata, + .actionstream = actdata, + }, + }; + struct vcap_rule *rule = 0; + struct vcap_rule_internal *ri = 0; + int vcap_chain_id = 10005; + enum vcap_user user = VCAP_USER_VCAP_UTIL; + u16 priority = 10; + int id = 100; + int ret; + struct vcap_u48_key smac = { + .value = { 0x88, 0x75, 0x32, 0x34, 0x9e, 0xb1 }, + .mask = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff } + }; + struct vcap_u48_key dmac = { + .value = { 0x06, 0x05, 0x04, 0x03, 0x02, 0x01 }, + .mask = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff } + }; + u32 port_mask_rng_value = 0x05; + u32 port_mask_rng_mask = 0x0f; + u32 igr_port_mask_value = 0xffabcd01; + u32 igr_port_mask_mask = ~0; + /* counter is not written yet, so it is not in expwriteaddr */ + u32 expwriteaddr[] = {792, 793, 794, 795, 796, 797, 0}; + int idx; + + vcap_test_api_init(&is2_admin); + + /* Allocate the rule */ + rule = vcap_alloc_rule(&test_vctrl, &test_netdev, vcap_chain_id, user, + priority, id); + KUNIT_EXPECT_PTR_NE(test, NULL, rule); + ri = (struct vcap_rule_internal *)rule; + + /* Add rule keys */ + ret = vcap_rule_add_key_u48(rule, VCAP_KF_L2_DMAC, &dmac); + KUNIT_EXPECT_EQ(test, 0, ret); + ret = vcap_rule_add_key_u48(rule, VCAP_KF_L2_SMAC, &smac); + KUNIT_EXPECT_EQ(test, 0, ret); + ret = vcap_rule_add_key_bit(rule, VCAP_KF_ETYPE_LEN_IS, VCAP_BIT_1); + KUNIT_EXPECT_EQ(test, 0, ret); + /* Cannot add the same field twice */ + ret = vcap_rule_add_key_bit(rule, VCAP_KF_ETYPE_LEN_IS, VCAP_BIT_1); + KUNIT_EXPECT_EQ(test, -EINVAL, ret); + ret = vcap_rule_add_key_bit(rule, VCAP_KF_IF_IGR_PORT_MASK_L3, + VCAP_BIT_ANY); + KUNIT_EXPECT_EQ(test, 0, ret); + ret = vcap_rule_add_key_u32(rule, VCAP_KF_IF_IGR_PORT_MASK_RNG, + port_mask_rng_value, port_mask_rng_mask); + KUNIT_EXPECT_EQ(test, 0, ret); + ret = vcap_rule_add_key_u32(rule, VCAP_KF_IF_IGR_PORT_MASK, + igr_port_mask_value, igr_port_mask_mask); + KUNIT_EXPECT_EQ(test, 0, ret); + + /* Add rule actions */ + ret = vcap_rule_add_action_bit(rule, VCAP_AF_POLICE_ENA, VCAP_BIT_1); + KUNIT_EXPECT_EQ(test, 0, ret); + ret = vcap_rule_add_action_u32(rule, VCAP_AF_CNT_ID, id); + KUNIT_EXPECT_EQ(test, 0, ret); + ret = vcap_rule_add_action_u32(rule, VCAP_AF_MATCH_ID, 1); + KUNIT_EXPECT_EQ(test, 0, ret); + ret = vcap_rule_add_action_u32(rule, VCAP_AF_MATCH_ID_MASK, 1); + KUNIT_EXPECT_EQ(test, 0, ret); + + /* For now the actionset is hardcoded */ + ret = vcap_set_rule_set_actionset(rule, VCAP_AFS_BASE_TYPE); + KUNIT_EXPECT_EQ(test, 0, ret); + + /* Validation with validate keyset callback */ + ret = vcap_val_rule(rule, ETH_P_ALL); + KUNIT_EXPECT_EQ(test, 0, ret); + KUNIT_EXPECT_EQ(test, VCAP_KFS_MAC_ETYPE, rule->keyset); + KUNIT_EXPECT_EQ(test, VCAP_AFS_BASE_TYPE, rule->actionset); + KUNIT_EXPECT_EQ(test, 6, ri->size); + KUNIT_EXPECT_EQ(test, 2, ri->keyset_sw_regs); + KUNIT_EXPECT_EQ(test, 4, ri->actionset_sw_regs); + + /* Add rule with write callback */ + ret = vcap_add_rule(rule); + KUNIT_EXPECT_EQ(test, 0, ret); + KUNIT_EXPECT_EQ(test, 792, is2_admin.last_used_addr); + for (idx = 0; idx < ARRAY_SIZE(expwriteaddr); ++idx) + KUNIT_EXPECT_EQ(test, expwriteaddr[idx], test_updateaddr[idx]); + + /* Check that the rule has been added */ + ret = list_empty(&is2_admin.rules); + KUNIT_EXPECT_EQ(test, false, ret); + KUNIT_EXPECT_EQ(test, 0, ret); + vcap_free_rule(rule); + + /* Check that the rule has been freed: tricky to access since this + * memory should not be accessible anymore + */ + KUNIT_EXPECT_PTR_NE(test, NULL, rule); + ret = list_empty(&rule->keyfields); + KUNIT_EXPECT_EQ(test, true, ret); + ret = list_empty(&rule->actionfields); + KUNIT_EXPECT_EQ(test, true, ret); +} + +static void vcap_api_next_lookup_basic_test(struct kunit *test) +{ + struct vcap_admin admin1 = { + .vtype = VCAP_TYPE_IS2, + .vinst = 0, + .first_cid = 8000000, + .last_cid = 8199999, + .lookups = 4, + .lookups_per_instance = 2, + }; + struct vcap_admin admin2 = { + .vtype = VCAP_TYPE_IS2, + .vinst = 1, + .first_cid = 8200000, + .last_cid = 8399999, + .lookups = 4, + .lookups_per_instance = 2, + }; + bool ret; + + vcap_test_api_init(&admin1); + list_add_tail(&admin2.list, &test_vctrl.list); + + ret = vcap_is_next_lookup(&test_vctrl, 8000000, 1001000); + KUNIT_EXPECT_EQ(test, false, ret); + ret = vcap_is_next_lookup(&test_vctrl, 8000000, 8001000); + KUNIT_EXPECT_EQ(test, false, ret); + ret = vcap_is_next_lookup(&test_vctrl, 8000000, 8101000); + KUNIT_EXPECT_EQ(test, true, ret); + + ret = vcap_is_next_lookup(&test_vctrl, 8100000, 8101000); + KUNIT_EXPECT_EQ(test, false, ret); + ret = vcap_is_next_lookup(&test_vctrl, 8100000, 8201000); + KUNIT_EXPECT_EQ(test, true, ret); + + ret = vcap_is_next_lookup(&test_vctrl, 8200000, 8201000); + KUNIT_EXPECT_EQ(test, false, ret); + ret = vcap_is_next_lookup(&test_vctrl, 8200000, 8301000); + KUNIT_EXPECT_EQ(test, true, ret); + + ret = vcap_is_next_lookup(&test_vctrl, 8300000, 8301000); + KUNIT_EXPECT_EQ(test, false, ret); + ret = vcap_is_next_lookup(&test_vctrl, 8300000, 8401000); + KUNIT_EXPECT_EQ(test, true, ret); +} + +static void vcap_api_next_lookup_advanced_test(struct kunit *test) +{ + struct vcap_admin admin1 = { + .vtype = VCAP_TYPE_IS0, + .vinst = 0, + .first_cid = 1000000, + .last_cid = 1199999, + .lookups = 6, + .lookups_per_instance = 2, + }; + struct vcap_admin admin2 = { + .vtype = VCAP_TYPE_IS0, + .vinst = 1, + .first_cid = 1200000, + .last_cid = 1399999, + .lookups = 6, + .lookups_per_instance = 2, + }; + struct vcap_admin admin3 = { + .vtype = VCAP_TYPE_IS0, + .vinst = 2, + .first_cid = 1400000, + .last_cid = 1599999, + .lookups = 6, + .lookups_per_instance = 2, + }; + struct vcap_admin admin4 = { + .vtype = VCAP_TYPE_IS2, + .vinst = 0, + .first_cid = 8000000, + .last_cid = 8199999, + .lookups = 4, + .lookups_per_instance = 2, + }; + struct vcap_admin admin5 = { + .vtype = VCAP_TYPE_IS2, + .vinst = 1, + .first_cid = 8200000, + .last_cid = 8399999, + .lookups = 4, + .lookups_per_instance = 2, + }; + bool ret; + + vcap_test_api_init(&admin1); + list_add_tail(&admin2.list, &test_vctrl.list); + list_add_tail(&admin3.list, &test_vctrl.list); + list_add_tail(&admin4.list, &test_vctrl.list); + list_add_tail(&admin5.list, &test_vctrl.list); + + ret = vcap_is_next_lookup(&test_vctrl, 1000000, 1001000); + KUNIT_EXPECT_EQ(test, false, ret); + ret = vcap_is_next_lookup(&test_vctrl, 1000000, 1101000); + KUNIT_EXPECT_EQ(test, true, ret); + + ret = vcap_is_next_lookup(&test_vctrl, 1100000, 1201000); + KUNIT_EXPECT_EQ(test, true, ret); + ret = vcap_is_next_lookup(&test_vctrl, 1100000, 1301000); + KUNIT_EXPECT_EQ(test, false, ret); + ret = vcap_is_next_lookup(&test_vctrl, 1100000, 8101000); + KUNIT_EXPECT_EQ(test, false, ret); + ret = vcap_is_next_lookup(&test_vctrl, 1300000, 1401000); + KUNIT_EXPECT_EQ(test, true, ret); + ret = vcap_is_next_lookup(&test_vctrl, 1400000, 1501000); + KUNIT_EXPECT_EQ(test, true, ret); + ret = vcap_is_next_lookup(&test_vctrl, 1500000, 8001000); + KUNIT_EXPECT_EQ(test, true, ret); + + ret = vcap_is_next_lookup(&test_vctrl, 8000000, 8001000); + KUNIT_EXPECT_EQ(test, false, ret); + ret = vcap_is_next_lookup(&test_vctrl, 8000000, 8101000); + KUNIT_EXPECT_EQ(test, true, ret); + + ret = vcap_is_next_lookup(&test_vctrl, 8300000, 8301000); + KUNIT_EXPECT_EQ(test, false, ret); + ret = vcap_is_next_lookup(&test_vctrl, 8300000, 8401000); + KUNIT_EXPECT_EQ(test, true, ret); +} + +static struct kunit_case vcap_api_support_test_cases[] = { + KUNIT_CASE(vcap_api_next_lookup_basic_test), + KUNIT_CASE(vcap_api_next_lookup_advanced_test), + {} +}; + +static struct kunit_suite vcap_api_support_test_suite = { + .name = "VCAP_API_Support_Testsuite", + .test_cases = vcap_api_support_test_cases, +}; + +static struct kunit_case vcap_api_full_rule_test_cases[] = { + KUNIT_CASE(vcap_api_rule_find_keyset_basic_test), + KUNIT_CASE(vcap_api_rule_find_keyset_failed_test), + KUNIT_CASE(vcap_api_rule_find_keyset_many_test), + KUNIT_CASE(vcap_api_encode_rule_test), + {} +}; + +static struct kunit_suite vcap_api_full_rule_test_suite = { + .name = "VCAP_API_Full_Rule_Testsuite", + .test_cases = vcap_api_full_rule_test_cases, +}; + +static struct kunit_case vcap_api_rule_value_test_cases[] = { + KUNIT_CASE(vcap_api_rule_add_keyvalue_test), + KUNIT_CASE(vcap_api_rule_add_actionvalue_test), + {} +}; + +static struct kunit_suite vcap_api_rule_value_test_suite = { + .name = "VCAP_API_Rule_Value_Testsuite", + .test_cases = vcap_api_rule_value_test_cases, +}; + static struct kunit_case vcap_api_encoding_test_cases[] = { KUNIT_CASE(vcap_api_set_bit_1_test), KUNIT_CASE(vcap_api_set_bit_0_test), @@ -930,4 +1519,7 @@ static struct kunit_suite vcap_api_encoding_test_suite = { .test_cases = vcap_api_encoding_test_cases, }; +kunit_test_suite(vcap_api_support_test_suite); +kunit_test_suite(vcap_api_full_rule_test_suite); +kunit_test_suite(vcap_api_rule_value_test_suite); kunit_test_suite(vcap_api_encoding_test_suite); diff --git a/drivers/net/ethernet/microsoft/Kconfig b/drivers/net/ethernet/microsoft/Kconfig index fe4e7a7d9c0b..090e6b983243 100644 --- a/drivers/net/ethernet/microsoft/Kconfig +++ b/drivers/net/ethernet/microsoft/Kconfig @@ -19,6 +19,7 @@ config MICROSOFT_MANA tristate "Microsoft Azure Network Adapter (MANA) support" depends on PCI_MSI && X86_64 depends on PCI_HYPERV + select AUXILIARY_BUS help This driver supports Microsoft Azure Network Adapter (MANA). So far, the driver is only supported on X86_64. diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index 726ac94d96ae..690b69cae4e3 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -6,7 +6,7 @@ #include <linux/utsname.h> #include <linux/version.h> -#include "mana.h" +#include <net/mana/mana.h> static u32 mana_gd_r32(struct gdma_context *g, u64 offset) { @@ -44,6 +44,9 @@ static void mana_gd_init_vf_regs(struct pci_dev *pdev) gc->db_page_base = gc->bar0_va + mana_gd_r64(gc, GDMA_REG_DB_PAGE_OFFSET); + gc->phys_db_page_base = gc->bar0_pa + + mana_gd_r64(gc, GDMA_REG_DB_PAGE_OFFSET); + gc->shm_base = gc->bar0_va + mana_gd_r64(gc, GDMA_REG_SHM_OFFSET); } @@ -149,6 +152,7 @@ int mana_gd_send_request(struct gdma_context *gc, u32 req_len, const void *req, return mana_hwc_send_request(hwc, req_len, req, resp_len, resp); } +EXPORT_SYMBOL_NS(mana_gd_send_request, NET_MANA); int mana_gd_alloc_memory(struct gdma_context *gc, unsigned int length, struct gdma_mem_info *gmi) @@ -194,7 +198,7 @@ static int mana_gd_create_hw_eq(struct gdma_context *gc, req.type = queue->type; req.pdid = queue->gdma_dev->pdid; req.doolbell_id = queue->gdma_dev->doorbell; - req.gdma_region = queue->mem_info.gdma_region; + req.gdma_region = queue->mem_info.dma_region_handle; req.queue_size = queue->queue_size; req.log2_throttle_limit = queue->eq.log2_throttle_limit; req.eq_pci_msix_index = queue->eq.msix_index; @@ -208,7 +212,7 @@ static int mana_gd_create_hw_eq(struct gdma_context *gc, queue->id = resp.queue_index; queue->eq.disable_needed = true; - queue->mem_info.gdma_region = GDMA_INVALID_DMA_REGION; + queue->mem_info.dma_region_handle = GDMA_INVALID_DMA_REGION; return 0; } @@ -667,24 +671,30 @@ free_q: return err; } -static void mana_gd_destroy_dma_region(struct gdma_context *gc, u64 gdma_region) +int mana_gd_destroy_dma_region(struct gdma_context *gc, + gdma_obj_handle_t dma_region_handle) { struct gdma_destroy_dma_region_req req = {}; struct gdma_general_resp resp = {}; int err; - if (gdma_region == GDMA_INVALID_DMA_REGION) - return; + if (dma_region_handle == GDMA_INVALID_DMA_REGION) + return 0; mana_gd_init_req_hdr(&req.hdr, GDMA_DESTROY_DMA_REGION, sizeof(req), sizeof(resp)); - req.gdma_region = gdma_region; + req.dma_region_handle = dma_region_handle; err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp), &resp); - if (err || resp.hdr.status) + if (err || resp.hdr.status) { dev_err(gc->dev, "Failed to destroy DMA region: %d, 0x%x\n", err, resp.hdr.status); + return -EPROTO; + } + + return 0; } +EXPORT_SYMBOL_NS(mana_gd_destroy_dma_region, NET_MANA); static int mana_gd_create_dma_region(struct gdma_dev *gd, struct gdma_mem_info *gmi) @@ -729,14 +739,15 @@ static int mana_gd_create_dma_region(struct gdma_dev *gd, if (err) goto out; - if (resp.hdr.status || resp.gdma_region == GDMA_INVALID_DMA_REGION) { + if (resp.hdr.status || + resp.dma_region_handle == GDMA_INVALID_DMA_REGION) { dev_err(gc->dev, "Failed to create DMA region: 0x%x\n", resp.hdr.status); err = -EPROTO; goto out; } - gmi->gdma_region = resp.gdma_region; + gmi->dma_region_handle = resp.dma_region_handle; out: kfree(req); return err; @@ -859,7 +870,7 @@ void mana_gd_destroy_queue(struct gdma_context *gc, struct gdma_queue *queue) return; } - mana_gd_destroy_dma_region(gc, gmi->gdma_region); + mana_gd_destroy_dma_region(gc, gmi->dma_region_handle); mana_gd_free_memory(gmi); kfree(queue); } @@ -1393,6 +1404,12 @@ static int mana_gd_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) goto release_region; + err = dma_set_max_seg_size(&pdev->dev, UINT_MAX); + if (err) { + dev_err(&pdev->dev, "Failed to set dma device segment size\n"); + goto release_region; + } + err = -ENOMEM; gc = vzalloc(sizeof(*gc)); if (!gc) @@ -1400,6 +1417,7 @@ static int mana_gd_probe(struct pci_dev *pdev, const struct pci_device_id *ent) mutex_init(&gc->eq_test_event_mutex); pci_set_drvdata(pdev, gc); + gc->bar0_pa = pci_resource_start(pdev, 0); bar0_va = pci_iomap(pdev, bar, 0); if (!bar0_va) diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c index 543a5d5c304f..9d1507eba5b9 100644 --- a/drivers/net/ethernet/microsoft/mana/hw_channel.c +++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c @@ -1,8 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* Copyright (c) 2021, Microsoft Corporation. */ -#include "gdma.h" -#include "hw_channel.h" +#include <net/mana/gdma.h> +#include <net/mana/hw_channel.h> static int mana_hwc_get_msg_index(struct hw_channel_context *hwc, u16 *msg_id) { @@ -836,7 +836,7 @@ int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len, goto out; } - if (ctx->status_code) { + if (ctx->status_code && ctx->status_code != GDMA_STATUS_MORE_ENTRIES) { dev_err(hwc->dev, "HWC: Failed hw_channel req: 0x%x\n", ctx->status_code); err = -EPROTO; diff --git a/drivers/net/ethernet/microsoft/mana/mana_bpf.c b/drivers/net/ethernet/microsoft/mana/mana_bpf.c index 421fd39ff3a8..3caea631229c 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_bpf.c +++ b/drivers/net/ethernet/microsoft/mana/mana_bpf.c @@ -8,7 +8,7 @@ #include <linux/bpf_trace.h> #include <net/xdp.h> -#include "mana.h" +#include <net/mana/mana.h> void mana_xdp_tx(struct sk_buff *skb, struct net_device *ndev) { diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 318dbbb48279..ad1277ac7f0d 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -12,7 +12,20 @@ #include <net/checksum.h> #include <net/ip6_checksum.h> -#include "mana.h" +#include <net/mana/mana.h> +#include <net/mana/mana_auxiliary.h> + +static DEFINE_IDA(mana_adev_ida); + +static int mana_adev_idx_alloc(void) +{ + return ida_alloc(&mana_adev_ida, GFP_KERNEL); +} + +static void mana_adev_idx_free(int idx) +{ + ida_free(&mana_adev_ida, idx); +} /* Microsoft Azure Network Adapter (MANA) functions */ @@ -128,7 +141,7 @@ frag_err: return -ENOMEM; } -int mana_start_xmit(struct sk_buff *skb, struct net_device *ndev) +netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev) { enum mana_tx_pkt_format pkt_fmt = MANA_SHORT_PKT_FMT; struct mana_port_context *apc = netdev_priv(ndev); @@ -176,7 +189,7 @@ int mana_start_xmit(struct sk_buff *skb, struct net_device *ndev) pkg.wqe_req.client_data_unit = 0; pkg.wqe_req.num_sge = 1 + skb_shinfo(skb)->nr_frags; - WARN_ON_ONCE(pkg.wqe_req.num_sge > 30); + WARN_ON_ONCE(pkg.wqe_req.num_sge > MAX_TX_WQE_SGL_ENTRIES); if (pkg.wqe_req.num_sge <= ARRAY_SIZE(pkg.sgl_array)) { pkg.wqe_req.sgl = pkg.sgl_array; @@ -633,13 +646,48 @@ static int mana_query_vport_cfg(struct mana_port_context *apc, u32 vport_index, return 0; } -static int mana_cfg_vport(struct mana_port_context *apc, u32 protection_dom_id, - u32 doorbell_pg_id) +void mana_uncfg_vport(struct mana_port_context *apc) +{ + mutex_lock(&apc->vport_mutex); + apc->vport_use_count--; + WARN_ON(apc->vport_use_count < 0); + mutex_unlock(&apc->vport_mutex); +} +EXPORT_SYMBOL_NS(mana_uncfg_vport, NET_MANA); + +int mana_cfg_vport(struct mana_port_context *apc, u32 protection_dom_id, + u32 doorbell_pg_id) { struct mana_config_vport_resp resp = {}; struct mana_config_vport_req req = {}; int err; + /* This function is used to program the Ethernet port in the hardware + * table. It can be called from the Ethernet driver or the RDMA driver. + * + * For Ethernet usage, the hardware supports only one active user on a + * physical port. The driver checks on the port usage before programming + * the hardware when creating the RAW QP (RDMA driver) or exposing the + * device to kernel NET layer (Ethernet driver). + * + * Because the RDMA driver doesn't know in advance which QP type the + * user will create, it exposes the device with all its ports. The user + * may not be able to create RAW QP on a port if this port is already + * in used by the Ethernet driver from the kernel. + * + * This physical port limitation only applies to the RAW QP. For RC QP, + * the hardware doesn't have this limitation. The user can create RC + * QPs on a physical port up to the hardware limits independent of the + * Ethernet usage on the same port. + */ + mutex_lock(&apc->vport_mutex); + if (apc->vport_use_count > 0) { + mutex_unlock(&apc->vport_mutex); + return -EBUSY; + } + apc->vport_use_count++; + mutex_unlock(&apc->vport_mutex); + mana_gd_init_req_hdr(&req.hdr, MANA_CONFIG_VPORT_TX, sizeof(req), sizeof(resp)); req.vport = apc->port_handle; @@ -666,9 +714,16 @@ static int mana_cfg_vport(struct mana_port_context *apc, u32 protection_dom_id, apc->tx_shortform_allowed = resp.short_form_allowed; apc->tx_vp_offset = resp.tx_vport_offset; + + netdev_info(apc->ndev, "Configured vPort %llu PD %u DB %u\n", + apc->port_handle, protection_dom_id, doorbell_pg_id); out: + if (err) + mana_uncfg_vport(apc); + return err; } +EXPORT_SYMBOL_NS(mana_cfg_vport, NET_MANA); static int mana_cfg_vport_steering(struct mana_port_context *apc, enum TRI_STATE rx, @@ -729,16 +784,19 @@ static int mana_cfg_vport_steering(struct mana_port_context *apc, resp.hdr.status); err = -EPROTO; } + + netdev_info(ndev, "Configured steering vPort %llu entries %u\n", + apc->port_handle, num_entries); out: kfree(req); return err; } -static int mana_create_wq_obj(struct mana_port_context *apc, - mana_handle_t vport, - u32 wq_type, struct mana_obj_spec *wq_spec, - struct mana_obj_spec *cq_spec, - mana_handle_t *wq_obj) +int mana_create_wq_obj(struct mana_port_context *apc, + mana_handle_t vport, + u32 wq_type, struct mana_obj_spec *wq_spec, + struct mana_obj_spec *cq_spec, + mana_handle_t *wq_obj) { struct mana_create_wqobj_resp resp = {}; struct mana_create_wqobj_req req = {}; @@ -787,9 +845,10 @@ static int mana_create_wq_obj(struct mana_port_context *apc, out: return err; } +EXPORT_SYMBOL_NS(mana_create_wq_obj, NET_MANA); -static void mana_destroy_wq_obj(struct mana_port_context *apc, u32 wq_type, - mana_handle_t wq_obj) +void mana_destroy_wq_obj(struct mana_port_context *apc, u32 wq_type, + mana_handle_t wq_obj) { struct mana_destroy_wqobj_resp resp = {}; struct mana_destroy_wqobj_req req = {}; @@ -814,6 +873,7 @@ static void mana_destroy_wq_obj(struct mana_port_context *apc, u32 wq_type, netdev_err(ndev, "Failed to destroy WQ object: %d, 0x%x\n", err, resp.hdr.status); } +EXPORT_SYMBOL_NS(mana_destroy_wq_obj, NET_MANA); static void mana_destroy_eq(struct mana_context *ac) { @@ -1463,10 +1523,10 @@ static int mana_create_txq(struct mana_port_context *apc, memset(&wq_spec, 0, sizeof(wq_spec)); memset(&cq_spec, 0, sizeof(cq_spec)); - wq_spec.gdma_region = txq->gdma_sq->mem_info.gdma_region; + wq_spec.gdma_region = txq->gdma_sq->mem_info.dma_region_handle; wq_spec.queue_size = txq->gdma_sq->queue_size; - cq_spec.gdma_region = cq->gdma_cq->mem_info.gdma_region; + cq_spec.gdma_region = cq->gdma_cq->mem_info.dma_region_handle; cq_spec.queue_size = cq->gdma_cq->queue_size; cq_spec.modr_ctx_id = 0; cq_spec.attached_eq = cq->gdma_cq->cq.parent->id; @@ -1481,8 +1541,10 @@ static int mana_create_txq(struct mana_port_context *apc, txq->gdma_sq->id = wq_spec.queue_index; cq->gdma_cq->id = cq_spec.queue_index; - txq->gdma_sq->mem_info.gdma_region = GDMA_INVALID_DMA_REGION; - cq->gdma_cq->mem_info.gdma_region = GDMA_INVALID_DMA_REGION; + txq->gdma_sq->mem_info.dma_region_handle = + GDMA_INVALID_DMA_REGION; + cq->gdma_cq->mem_info.dma_region_handle = + GDMA_INVALID_DMA_REGION; txq->gdma_txq_id = txq->gdma_sq->id; @@ -1693,10 +1755,10 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc, memset(&wq_spec, 0, sizeof(wq_spec)); memset(&cq_spec, 0, sizeof(cq_spec)); - wq_spec.gdma_region = rxq->gdma_rq->mem_info.gdma_region; + wq_spec.gdma_region = rxq->gdma_rq->mem_info.dma_region_handle; wq_spec.queue_size = rxq->gdma_rq->queue_size; - cq_spec.gdma_region = cq->gdma_cq->mem_info.gdma_region; + cq_spec.gdma_region = cq->gdma_cq->mem_info.dma_region_handle; cq_spec.queue_size = cq->gdma_cq->queue_size; cq_spec.modr_ctx_id = 0; cq_spec.attached_eq = cq->gdma_cq->cq.parent->id; @@ -1709,8 +1771,8 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc, rxq->gdma_rq->id = wq_spec.queue_index; cq->gdma_cq->id = cq_spec.queue_index; - rxq->gdma_rq->mem_info.gdma_region = GDMA_INVALID_DMA_REGION; - cq->gdma_cq->mem_info.gdma_region = GDMA_INVALID_DMA_REGION; + rxq->gdma_rq->mem_info.dma_region_handle = GDMA_INVALID_DMA_REGION; + cq->gdma_cq->mem_info.dma_region_handle = GDMA_INVALID_DMA_REGION; rxq->gdma_id = rxq->gdma_rq->id; cq->gdma_id = cq->gdma_cq->id; @@ -1791,6 +1853,7 @@ static void mana_destroy_vport(struct mana_port_context *apc) } mana_destroy_txq(apc); + mana_uncfg_vport(apc); if (gd->gdma_context->is_pf) mana_pf_deregister_hw_vport(apc); @@ -2063,12 +2126,16 @@ static int mana_probe_port(struct mana_context *ac, int port_idx, apc->pf_filter_handle = INVALID_MANA_HANDLE; apc->port_idx = port_idx; + mutex_init(&apc->vport_mutex); + apc->vport_use_count = 0; + ndev->netdev_ops = &mana_devops; ndev->ethtool_ops = &mana_ethtool_ops; ndev->mtu = ETH_DATA_LEN; ndev->max_mtu = ndev->mtu; ndev->min_mtu = ndev->mtu; ndev->needed_headroom = MANA_HEADROOM; + ndev->dev_port = port_idx; SET_NETDEV_DEV(ndev, gc->dev); netif_carrier_off(ndev); @@ -2106,6 +2173,69 @@ free_net: return err; } +static void adev_release(struct device *dev) +{ + struct mana_adev *madev = container_of(dev, struct mana_adev, adev.dev); + + kfree(madev); +} + +static void remove_adev(struct gdma_dev *gd) +{ + struct auxiliary_device *adev = gd->adev; + int id = adev->id; + + auxiliary_device_delete(adev); + auxiliary_device_uninit(adev); + + mana_adev_idx_free(id); + gd->adev = NULL; +} + +static int add_adev(struct gdma_dev *gd) +{ + struct auxiliary_device *adev; + struct mana_adev *madev; + int ret; + + madev = kzalloc(sizeof(*madev), GFP_KERNEL); + if (!madev) + return -ENOMEM; + + adev = &madev->adev; + ret = mana_adev_idx_alloc(); + if (ret < 0) + goto idx_fail; + adev->id = ret; + + adev->name = "rdma"; + adev->dev.parent = gd->gdma_context->dev; + adev->dev.release = adev_release; + madev->mdev = gd; + + ret = auxiliary_device_init(adev); + if (ret) + goto init_fail; + + ret = auxiliary_device_add(adev); + if (ret) + goto add_fail; + + gd->adev = adev; + return 0; + +add_fail: + auxiliary_device_uninit(adev); + +init_fail: + mana_adev_idx_free(adev->id); + +idx_fail: + kfree(madev); + + return ret; +} + int mana_probe(struct gdma_dev *gd, bool resuming) { struct gdma_context *gc = gd->gdma_context; @@ -2173,6 +2303,8 @@ int mana_probe(struct gdma_dev *gd, bool resuming) break; } } + + err = add_adev(gd); out: if (err) mana_remove(gd, false); @@ -2189,6 +2321,10 @@ void mana_remove(struct gdma_dev *gd, bool suspending) int err; int i; + /* adev currently doesn't support suspending, always remove it */ + if (gd->adev) + remove_adev(gd); + for (i = 0; i < ac->num_ports; i++) { ndev = ac->ports[i]; if (!ndev) { @@ -2221,7 +2357,6 @@ void mana_remove(struct gdma_dev *gd, bool suspending) } mana_destroy_eq(ac); - out: mana_gd_deregister_device(gd); diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c index 96d55c91c969..5b776a33a817 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c +++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c @@ -5,7 +5,7 @@ #include <linux/etherdevice.h> #include <linux/ethtool.h> -#include "mana.h" +#include <net/mana/mana.h> static const struct { char name[ETH_GSTRING_LEN]; diff --git a/drivers/net/ethernet/microsoft/mana/shm_channel.c b/drivers/net/ethernet/microsoft/mana/shm_channel.c index da255da62176..5553af9c8085 100644 --- a/drivers/net/ethernet/microsoft/mana/shm_channel.c +++ b/drivers/net/ethernet/microsoft/mana/shm_channel.c @@ -6,7 +6,7 @@ #include <linux/io.h> #include <linux/mm.h> -#include "shm_channel.h" +#include <net/mana/shm_channel.h> #define PAGE_FRAME_L48_WIDTH_BYTES 6 #define PAGE_FRAME_L48_WIDTH_BITS (PAGE_FRAME_L48_WIDTH_BYTES * 8) diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c index 50858cc10fef..ca4bde861397 100644 --- a/drivers/net/ethernet/mscc/ocelot_net.c +++ b/drivers/net/ethernet/mscc/ocelot_net.c @@ -194,15 +194,6 @@ void ocelot_port_devlink_teardown(struct ocelot *ocelot, int port) devlink_port_unregister(dlp); } -static struct devlink_port *ocelot_get_devlink_port(struct net_device *dev) -{ - struct ocelot_port_private *priv = netdev_priv(dev); - struct ocelot *ocelot = priv->port.ocelot; - int port = priv->port.index; - - return &ocelot->devlink_ports[port]; -} - int ocelot_setup_tc_cls_flower(struct ocelot_port_private *priv, struct flow_cls_offload *f, bool ingress) @@ -925,7 +916,6 @@ static const struct net_device_ops ocelot_port_netdev_ops = { .ndo_set_features = ocelot_set_features, .ndo_setup_tc = ocelot_setup_tc, .ndo_eth_ioctl = ocelot_ioctl, - .ndo_get_devlink_port = ocelot_get_devlink_port, }; struct net_device *ocelot_port_to_netdev(struct ocelot *ocelot, int port) @@ -1737,7 +1727,6 @@ static void vsc7514_phylink_mac_link_up(struct phylink_config *config, } static const struct phylink_mac_ops ocelot_phylink_ops = { - .validate = phylink_generic_validate, .mac_config = vsc7514_phylink_mac_config, .mac_link_down = vsc7514_phylink_mac_link_down, .mac_link_up = vsc7514_phylink_mac_link_up, @@ -1873,6 +1862,7 @@ int ocelot_probe_port(struct ocelot *ocelot, int port, struct regmap *target, if (ocelot->fdma) ocelot_fdma_netdev_init(ocelot, dev); + SET_NETDEV_DEVLINK_PORT(dev, &ocelot->devlink_ports[port]); err = register_netdev(dev); if (err) { dev_err(ocelot->dev, "register_netdev failed\n"); diff --git a/drivers/net/ethernet/mscc/ocelot_vsc7514.c b/drivers/net/ethernet/mscc/ocelot_vsc7514.c index 6f22aea08a64..93431d2ff4f1 100644 --- a/drivers/net/ethernet/mscc/ocelot_vsc7514.c +++ b/drivers/net/ethernet/mscc/ocelot_vsc7514.c @@ -377,9 +377,6 @@ static int mscc_ocelot_init_ports(struct platform_device *pdev, return -ENOMEM; for_each_available_child_of_node(ports, portnp) { - struct ocelot_port_private *priv; - struct ocelot_port *ocelot_port; - struct devlink_port *dlp; struct regmap *target; struct resource *res; char res_name[8]; @@ -420,12 +417,6 @@ static int mscc_ocelot_init_ports(struct platform_device *pdev, } devlink_ports_registered |= BIT(port); - - ocelot_port = ocelot->ports[port]; - priv = container_of(ocelot_port, struct ocelot_port_private, - port); - dlp = &ocelot->devlink_ports[port]; - devlink_port_type_eth_set(dlp, priv->dev); } /* Initialize unused devlink ports at the end */ diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c index dcf8212119f9..1d3c4474b7cb 100644 --- a/drivers/net/ethernet/neterion/s2io.c +++ b/drivers/net/ethernet/neterion/s2io.c @@ -7128,9 +7128,8 @@ static int s2io_card_up(struct s2io_nic *sp) if (ret) { DBG_PRINT(ERR_DBG, "%s: Out of memory in Open\n", dev->name); - s2io_reset(sp); - free_rx_buffers(sp); - return -ENOMEM; + ret = -ENOMEM; + goto err_fill_buff; } DBG_PRINT(INFO_DBG, "Buf in ring:%d is %d:\n", i, ring->rx_bufs_left); @@ -7168,18 +7167,16 @@ static int s2io_card_up(struct s2io_nic *sp) /* Enable Rx Traffic and interrupts on the NIC */ if (start_nic(sp)) { DBG_PRINT(ERR_DBG, "%s: Starting NIC failed\n", dev->name); - s2io_reset(sp); - free_rx_buffers(sp); - return -ENODEV; + ret = -ENODEV; + goto err_out; } /* Add interrupt service routine */ if (s2io_add_isr(sp) != 0) { if (sp->config.intr_type == MSI_X) s2io_rem_isr(sp); - s2io_reset(sp); - free_rx_buffers(sp); - return -ENODEV; + ret = -ENODEV; + goto err_out; } timer_setup(&sp->alarm_timer, s2io_alarm_handle, 0); @@ -7199,6 +7196,20 @@ static int s2io_card_up(struct s2io_nic *sp) } return 0; + +err_out: + if (config->napi) { + if (config->intr_type == MSI_X) { + for (i = 0; i < sp->config.rx_ring_num; i++) + napi_disable(&sp->mac_control.rings[i].napi); + } else { + napi_disable(&sp->napi); + } + } +err_fill_buff: + s2io_reset(sp); + free_rx_buffers(sp); + return ret; } /** diff --git a/drivers/net/ethernet/netronome/nfp/nfp_app.h b/drivers/net/ethernet/netronome/nfp/nfp_app.h index dd56207df246..90707346a4ef 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_app.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_app.h @@ -445,6 +445,4 @@ int nfp_app_nic_vnic_alloc(struct nfp_app *app, struct nfp_net *nn, int nfp_app_nic_vnic_init_phy_port(struct nfp_pf *pf, struct nfp_app *app, struct nfp_net *nn, unsigned int id); -struct devlink_port *nfp_devlink_get_devlink_port(struct net_device *netdev); - #endif diff --git a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c index 405786c00334..8bfd48d50ef0 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c @@ -334,6 +334,8 @@ int nfp_devlink_port_register(struct nfp_app *app, struct nfp_port *port) int serial_len; int ret; + SET_NETDEV_DEVLINK_PORT(port->netdev, &port->dl_port); + rtnl_lock(); ret = nfp_devlink_fill_eth_port(port, ð_port); rtnl_unlock(); @@ -360,24 +362,3 @@ void nfp_devlink_port_unregister(struct nfp_port *port) { devl_port_unregister(&port->dl_port); } - -void nfp_devlink_port_type_eth_set(struct nfp_port *port) -{ - devlink_port_type_eth_set(&port->dl_port, port->netdev); -} - -void nfp_devlink_port_type_clear(struct nfp_port *port) -{ - devlink_port_type_clear(&port->dl_port); -} - -struct devlink_port *nfp_devlink_get_devlink_port(struct net_device *netdev) -{ - struct nfp_port *port; - - port = nfp_port_from_netdev(netdev); - if (!port) - return NULL; - - return &port->dl_port; -} diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index a5ca5c4a7896..184ffae2ac94 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -735,8 +735,9 @@ static unsigned int nfp_net_calc_fl_bufsz_xsk(struct nfp_net_dp *dp) */ static void nfp_net_vecs_init(struct nfp_net *nn) { + int numa_node = dev_to_node(&nn->pdev->dev); struct nfp_net_r_vector *r_vec; - int r; + unsigned int r; nn->lsc_handler = nfp_net_irq_lsc; nn->exn_handler = nfp_net_irq_exn; @@ -762,7 +763,7 @@ static void nfp_net_vecs_init(struct nfp_net *nn) tasklet_disable(&r_vec->tasklet); } - cpumask_set_cpu(r, &r_vec->affinity_mask); + cpumask_set_cpu(cpumask_local_spread(r, numa_node), &r_vec->affinity_mask); } } @@ -2013,7 +2014,6 @@ const struct net_device_ops nfp_nfd3_netdev_ops = { .ndo_get_phys_port_name = nfp_net_get_phys_port_name, .ndo_bpf = nfp_net_xdp, .ndo_xsk_wakeup = nfp_net_xsk_wakeup, - .ndo_get_devlink_port = nfp_devlink_get_devlink_port, .ndo_bridge_getlink = nfp_net_bridge_getlink, .ndo_bridge_setlink = nfp_net_bridge_setlink, }; @@ -2044,7 +2044,6 @@ const struct net_device_ops nfp_nfdk_netdev_ops = { .ndo_features_check = nfp_net_features_check, .ndo_get_phys_port_name = nfp_net_get_phys_port_name, .ndo_bpf = nfp_net_xdp, - .ndo_get_devlink_port = nfp_devlink_get_devlink_port, .ndo_bridge_getlink = nfp_net_bridge_getlink, .ndo_bridge_setlink = nfp_net_bridge_setlink, }; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c index 3bae92dc899e..7abf0c576868 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c @@ -156,22 +156,17 @@ nfp_net_pf_init_vnic(struct nfp_pf *pf, struct nfp_net *nn, unsigned int id) nfp_net_debugfs_vnic_add(nn, pf->ddir); - if (nn->port) - nfp_devlink_port_type_eth_set(nn->port); - nfp_net_info(nn); if (nfp_net_is_data_vnic(nn)) { err = nfp_app_vnic_init(pf->app, nn); if (err) - goto err_devlink_port_type_clean; + goto err_debugfs_vnic_clean; } return 0; -err_devlink_port_type_clean: - if (nn->port) - nfp_devlink_port_type_clear(nn->port); +err_debugfs_vnic_clean: nfp_net_debugfs_dir_clean(&nn->debugfs_dir); nfp_net_clean(nn); err_devlink_port_clean: @@ -220,8 +215,6 @@ static void nfp_net_pf_clean_vnic(struct nfp_pf *pf, struct nfp_net *nn) { if (nfp_net_is_data_vnic(nn)) nfp_app_vnic_clean(pf->app, nn); - if (nn->port) - nfp_devlink_port_type_clear(nn->port); nfp_net_debugfs_dir_clean(&nn->debugfs_dir); nfp_net_clean(nn); if (nn->port) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c index a6b6ca1fd55e..3af1229a3f08 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c @@ -275,7 +275,6 @@ const struct net_device_ops nfp_repr_netdev_ops = { .ndo_set_features = nfp_port_set_features, .ndo_set_mac_address = eth_mac_addr, .ndo_get_port_parent_id = nfp_port_get_port_parent_id, - .ndo_get_devlink_port = nfp_devlink_get_devlink_port, }; void diff --git a/drivers/net/ethernet/netronome/nfp/nfp_port.h b/drivers/net/ethernet/netronome/nfp/nfp_port.h index 6793cdf9ff11..f8cd157ca1d7 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_port.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_port.h @@ -129,8 +129,6 @@ int nfp_net_refresh_port_table_sync(struct nfp_pf *pf); int nfp_devlink_port_register(struct nfp_app *app, struct nfp_port *port); void nfp_devlink_port_unregister(struct nfp_port *port); -void nfp_devlink_port_type_eth_set(struct nfp_port *port); -void nfp_devlink_port_type_clear(struct nfp_port *port); /* Mac stats (0x0000 - 0x0200) * all counters are 64bit. diff --git a/drivers/net/ethernet/ni/nixge.c b/drivers/net/ethernet/ni/nixge.c index 3db4a2431741..19d043b593cc 100644 --- a/drivers/net/ethernet/ni/nixge.c +++ b/drivers/net/ethernet/ni/nixge.c @@ -900,6 +900,7 @@ static int nixge_open(struct net_device *ndev) err_rx_irq: free_irq(priv->tx_irq, ndev); err_tx_irq: + napi_disable(&priv->napi); phy_stop(phy); phy_disconnect(phy); tasklet_kill(&priv->dma_err_tasklet); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_devlink.c b/drivers/net/ethernet/pensando/ionic/ionic_devlink.c index 4297ed9024c0..567f778433e2 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_devlink.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_devlink.c @@ -90,7 +90,7 @@ int ionic_devlink_register(struct ionic *ionic) return err; } - devlink_port_type_eth_set(&ionic->dl_port, ionic->lif->netdev); + SET_NETDEV_DEVLINK_PORT(ionic->lif->netdev, &ionic->dl_port); devlink_register(dl); return 0; } diff --git a/drivers/net/ethernet/qlogic/qede/qede_ptp.c b/drivers/net/ethernet/qlogic/qede/qede_ptp.c index c9c8225f04d6..747cc5e2bb78 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ptp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_ptp.c @@ -28,16 +28,19 @@ struct qede_ptp { }; /** - * qede_ptp_adjfreq() - Adjust the frequency of the PTP cycle counter. + * qede_ptp_adjfine() - Adjust the frequency of the PTP cycle counter. * * @info: The PTP clock info structure. - * @ppb: Parts per billion adjustment from base. + * @scaled_ppm: Scaled parts per million adjustment from base. + * + * Scaled parts per million is ppm with a 16-bit binary fractional field. * * Return: Zero on success, negative errno otherwise. */ -static int qede_ptp_adjfreq(struct ptp_clock_info *info, s32 ppb) +static int qede_ptp_adjfine(struct ptp_clock_info *info, long scaled_ppm) { struct qede_ptp *ptp = container_of(info, struct qede_ptp, clock_info); + s32 ppb = scaled_ppm_to_ppb(scaled_ppm); struct qede_dev *edev = ptp->edev; int rc; @@ -47,7 +50,7 @@ static int qede_ptp_adjfreq(struct ptp_clock_info *info, s32 ppb) rc = ptp->ops->adjfreq(edev->cdev, ppb); spin_unlock_bh(&ptp->lock); } else { - DP_ERR(edev, "PTP adjfreq called while interface is down\n"); + DP_ERR(edev, "PTP adjfine called while interface is down\n"); rc = -EFAULT; } __qede_unlock(edev); @@ -462,7 +465,7 @@ int qede_ptp_enable(struct qede_dev *edev) ptp->clock_info.n_ext_ts = 0; ptp->clock_info.n_per_out = 0; ptp->clock_info.pps = 0; - ptp->clock_info.adjfreq = qede_ptp_adjfreq; + ptp->clock_info.adjfine = qede_ptp_adjfine; ptp->clock_info.adjtime = qede_ptp_adjtime; ptp->clock_info.gettime64 = qede_ptp_gettime; ptp->clock_info.settime64 = qede_ptp_settime; diff --git a/drivers/net/ethernet/renesas/rswitch.c b/drivers/net/ethernet/renesas/rswitch.c index 20df2020d3e5..f3d27aef1286 100644 --- a/drivers/net/ethernet/renesas/rswitch.c +++ b/drivers/net/ethernet/renesas/rswitch.c @@ -219,9 +219,9 @@ static void rswitch_ack_data_irq(struct rswitch_private *priv, int index) iowrite32(BIT(index % 32), priv->addr + offs); } -static u32 rswitch_next_queue_index(struct rswitch_gwca_queue *gq, bool cur, u32 num) +static int rswitch_next_queue_index(struct rswitch_gwca_queue *gq, bool cur, int num) { - u32 index = cur ? gq->cur : gq->dirty; + int index = cur ? gq->cur : gq->dirty; if (index + num >= gq->ring_size) index = (index + num) % gq->ring_size; @@ -231,7 +231,7 @@ static u32 rswitch_next_queue_index(struct rswitch_gwca_queue *gq, bool cur, u32 return index; } -static u32 rswitch_get_num_cur_queues(struct rswitch_gwca_queue *gq) +static int rswitch_get_num_cur_queues(struct rswitch_gwca_queue *gq) { if (gq->cur >= gq->dirty) return gq->cur - gq->dirty; @@ -250,9 +250,9 @@ static bool rswitch_is_queue_rxed(struct rswitch_gwca_queue *gq) } static int rswitch_gwca_queue_alloc_skb(struct rswitch_gwca_queue *gq, - u32 start_index, u32 num) + int start_index, int num) { - u32 i, index; + int i, index; for (i = 0; i < num; i++) { index = (i + start_index) % gq->ring_size; @@ -410,12 +410,12 @@ err: static int rswitch_gwca_queue_ts_fill(struct net_device *ndev, struct rswitch_gwca_queue *gq, - u32 start_index, u32 num) + int start_index, int num) { struct rswitch_device *rdev = netdev_priv(ndev); struct rswitch_ext_ts_desc *desc; dma_addr_t dma_addr; - u32 i, index; + int i, index; for (i = 0; i < num; i++) { index = (i + start_index) % gq->ring_size; @@ -736,7 +736,8 @@ static int rswitch_tx_free(struct net_device *ndev, bool free_txed_only) int free_num = 0; int size; - for (; gq->cur - gq->dirty > 0; gq->dirty = rswitch_next_queue_index(gq, false, 1)) { + for (; rswitch_get_num_cur_queues(gq) > 0; + gq->dirty = rswitch_next_queue_index(gq, false, 1)) { desc = &gq->ring[gq->dirty]; if (free_txed_only && (desc->desc.die_dt & DT_MASK) != DT_FEMPTY) break; @@ -1190,7 +1191,6 @@ static void rswitch_mac_link_up(struct phylink_config *config, } static const struct phylink_mac_ops rswitch_phylink_ops = { - .validate = phylink_generic_validate, .mac_config = rswitch_mac_config, .mac_link_down = rswitch_mac_link_down, .mac_link_up = rswitch_mac_link_up, @@ -1390,7 +1390,7 @@ static int rswitch_stop(struct net_device *ndev) return 0; }; -static int rswitch_start_xmit(struct sk_buff *skb, struct net_device *ndev) +static netdev_tx_t rswitch_start_xmit(struct sk_buff *skb, struct net_device *ndev) { struct rswitch_device *rdev = netdev_priv(ndev); struct rswitch_gwca_queue *gq = rdev->tx_queue; diff --git a/drivers/net/ethernet/renesas/rswitch.h b/drivers/net/ethernet/renesas/rswitch.h index 778177ec8d4f..edbdd1b98d3d 100644 --- a/drivers/net/ethernet/renesas/rswitch.h +++ b/drivers/net/ethernet/renesas/rswitch.h @@ -908,9 +908,9 @@ struct rswitch_gwca_queue { struct rswitch_ext_ts_desc *ts_ring; }; dma_addr_t ring_dma; - u32 ring_size; - u32 cur; - u32 dirty; + int ring_size; + int cur; + int dirty; struct sk_buff **skbs; struct net_device *ndev; /* queue to ndev for irq */ diff --git a/drivers/net/ethernet/sfc/mae.c b/drivers/net/ethernet/sfc/mae.c index 6f472ea0638a..1e605e2a08c5 100644 --- a/drivers/net/ethernet/sfc/mae.c +++ b/drivers/net/ethernet/sfc/mae.c @@ -250,6 +250,32 @@ static int efx_mae_match_check_cap_typ(u8 support, enum mask_type typ) } } +/* Validate field mask against hardware capabilities. Captures caller's 'rc' */ +#define CHECK(_mcdi, _field) ({ \ + enum mask_type typ = classify_mask((const u8 *)&mask->_field, \ + sizeof(mask->_field)); \ + \ + rc = efx_mae_match_check_cap_typ(supported_fields[MAE_FIELD_ ## _mcdi],\ + typ); \ + if (rc) \ + NL_SET_ERR_MSG_FMT_MOD(extack, \ + "No support for %s mask in field %s", \ + mask_type_name(typ), #_field); \ + rc; \ +}) +/* Booleans need special handling */ +#define CHECK_BIT(_mcdi, _field) ({ \ + enum mask_type typ = mask->_field ? MASK_ONES : MASK_ZEROES; \ + \ + rc = efx_mae_match_check_cap_typ(supported_fields[MAE_FIELD_ ## _mcdi],\ + typ); \ + if (rc) \ + NL_SET_ERR_MSG_FMT_MOD(extack, \ + "No support for %s mask in field %s", \ + mask_type_name(typ), #_field); \ + rc; \ +}) + int efx_mae_match_check_caps(struct efx_nic *efx, const struct efx_tc_match_fields *mask, struct netlink_ext_ack *extack) @@ -269,8 +295,33 @@ int efx_mae_match_check_caps(struct efx_nic *efx, mask_type_name(ingress_port_mask_type)); return rc; } + if (CHECK(ETHER_TYPE, eth_proto) || + CHECK(VLAN0_TCI, vlan_tci[0]) || + CHECK(VLAN0_PROTO, vlan_proto[0]) || + CHECK(VLAN1_TCI, vlan_tci[1]) || + CHECK(VLAN1_PROTO, vlan_proto[1]) || + CHECK(ETH_SADDR, eth_saddr) || + CHECK(ETH_DADDR, eth_daddr) || + CHECK(IP_PROTO, ip_proto) || + CHECK(IP_TOS, ip_tos) || + CHECK(IP_TTL, ip_ttl) || + CHECK(SRC_IP4, src_ip) || + CHECK(DST_IP4, dst_ip) || +#ifdef CONFIG_IPV6 + CHECK(SRC_IP6, src_ip6) || + CHECK(DST_IP6, dst_ip6) || +#endif + CHECK(L4_SPORT, l4_sport) || + CHECK(L4_DPORT, l4_dport) || + CHECK(TCP_FLAGS, tcp_flags) || + CHECK_BIT(IS_IP_FRAG, ip_frag) || + CHECK_BIT(IP_FIRST_FRAG, ip_firstfrag) || + CHECK(RECIRC_ID, recirc_id)) + return rc; return 0; } +#undef CHECK_BIT +#undef CHECK static bool efx_mae_asl_id(u32 id) { @@ -439,10 +490,90 @@ static int efx_mae_populate_match_criteria(MCDI_DECLARE_STRUCT_PTR(match_crit), } MCDI_STRUCT_SET_DWORD(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_INGRESS_MPORT_SELECTOR_MASK, match->mask.ingress_port); + EFX_POPULATE_DWORD_2(*_MCDI_STRUCT_DWORD(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_FLAGS), + MAE_FIELD_MASK_VALUE_PAIRS_V2_IS_IP_FRAG, + match->value.ip_frag, + MAE_FIELD_MASK_VALUE_PAIRS_V2_IP_FIRST_FRAG, + match->value.ip_firstfrag); + EFX_POPULATE_DWORD_2(*_MCDI_STRUCT_DWORD(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_FLAGS_MASK), + MAE_FIELD_MASK_VALUE_PAIRS_V2_IS_IP_FRAG, + match->mask.ip_frag, + MAE_FIELD_MASK_VALUE_PAIRS_V2_IP_FIRST_FRAG, + match->mask.ip_firstfrag); MCDI_STRUCT_SET_BYTE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_RECIRC_ID, match->value.recirc_id); MCDI_STRUCT_SET_BYTE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_RECIRC_ID_MASK, match->mask.recirc_id); + MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_ETHER_TYPE_BE, + match->value.eth_proto); + MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_ETHER_TYPE_BE_MASK, + match->mask.eth_proto); + MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_VLAN0_TCI_BE, + match->value.vlan_tci[0]); + MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_VLAN0_TCI_BE_MASK, + match->mask.vlan_tci[0]); + MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_VLAN0_PROTO_BE, + match->value.vlan_proto[0]); + MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_VLAN0_PROTO_BE_MASK, + match->mask.vlan_proto[0]); + MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_VLAN1_TCI_BE, + match->value.vlan_tci[1]); + MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_VLAN1_TCI_BE_MASK, + match->mask.vlan_tci[1]); + MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_VLAN1_PROTO_BE, + match->value.vlan_proto[1]); + MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_VLAN1_PROTO_BE_MASK, + match->mask.vlan_proto[1]); + memcpy(MCDI_STRUCT_PTR(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_ETH_SADDR_BE), + match->value.eth_saddr, ETH_ALEN); + memcpy(MCDI_STRUCT_PTR(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_ETH_SADDR_BE_MASK), + match->mask.eth_saddr, ETH_ALEN); + memcpy(MCDI_STRUCT_PTR(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_ETH_DADDR_BE), + match->value.eth_daddr, ETH_ALEN); + memcpy(MCDI_STRUCT_PTR(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_ETH_DADDR_BE_MASK), + match->mask.eth_daddr, ETH_ALEN); + MCDI_STRUCT_SET_BYTE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_IP_PROTO, + match->value.ip_proto); + MCDI_STRUCT_SET_BYTE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_IP_PROTO_MASK, + match->mask.ip_proto); + MCDI_STRUCT_SET_BYTE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_IP_TOS, + match->value.ip_tos); + MCDI_STRUCT_SET_BYTE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_IP_TOS_MASK, + match->mask.ip_tos); + MCDI_STRUCT_SET_BYTE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_IP_TTL, + match->value.ip_ttl); + MCDI_STRUCT_SET_BYTE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_IP_TTL_MASK, + match->mask.ip_ttl); + MCDI_STRUCT_SET_DWORD_BE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_SRC_IP4_BE, + match->value.src_ip); + MCDI_STRUCT_SET_DWORD_BE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_SRC_IP4_BE_MASK, + match->mask.src_ip); + MCDI_STRUCT_SET_DWORD_BE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_DST_IP4_BE, + match->value.dst_ip); + MCDI_STRUCT_SET_DWORD_BE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_DST_IP4_BE_MASK, + match->mask.dst_ip); +#ifdef CONFIG_IPV6 + memcpy(MCDI_STRUCT_PTR(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_SRC_IP6_BE), + &match->value.src_ip6, sizeof(struct in6_addr)); + memcpy(MCDI_STRUCT_PTR(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_SRC_IP6_BE_MASK), + &match->mask.src_ip6, sizeof(struct in6_addr)); + memcpy(MCDI_STRUCT_PTR(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_DST_IP6_BE), + &match->value.dst_ip6, sizeof(struct in6_addr)); + memcpy(MCDI_STRUCT_PTR(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_DST_IP6_BE_MASK), + &match->mask.dst_ip6, sizeof(struct in6_addr)); +#endif + MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_L4_SPORT_BE, + match->value.l4_sport); + MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_L4_SPORT_BE_MASK, + match->mask.l4_sport); + MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_L4_DPORT_BE, + match->value.l4_dport); + MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_L4_DPORT_BE_MASK, + match->mask.l4_dport); + MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_TCP_FLAGS_BE, + match->value.tcp_flags); + MCDI_STRUCT_SET_WORD_BE(match_crit, MAE_FIELD_MASK_VALUE_PAIRS_V2_TCP_FLAGS_BE_MASK, + match->mask.tcp_flags); return 0; } diff --git a/drivers/net/ethernet/sfc/mcdi.h b/drivers/net/ethernet/sfc/mcdi.h index 1f18e9dc62e8..fbeb58104936 100644 --- a/drivers/net/ethernet/sfc/mcdi.h +++ b/drivers/net/ethernet/sfc/mcdi.h @@ -224,12 +224,24 @@ void efx_mcdi_sensor_event(struct efx_nic *efx, efx_qword_t *ev); #define MCDI_WORD(_buf, _field) \ ((u16)BUILD_BUG_ON_ZERO(MC_CMD_ ## _field ## _LEN != 2) + \ le16_to_cpu(*(__force const __le16 *)MCDI_PTR(_buf, _field))) +/* Write a 16-bit field defined in the protocol as being big-endian. */ +#define MCDI_STRUCT_SET_WORD_BE(_buf, _field, _value) do { \ + BUILD_BUG_ON(_field ## _LEN != 2); \ + BUILD_BUG_ON(_field ## _OFST & 1); \ + *(__force __be16 *)MCDI_STRUCT_PTR(_buf, _field) = (_value); \ + } while (0) #define MCDI_SET_DWORD(_buf, _field, _value) \ EFX_POPULATE_DWORD_1(*_MCDI_DWORD(_buf, _field), EFX_DWORD_0, _value) #define MCDI_STRUCT_SET_DWORD(_buf, _field, _value) \ EFX_POPULATE_DWORD_1(*_MCDI_STRUCT_DWORD(_buf, _field), EFX_DWORD_0, _value) #define MCDI_DWORD(_buf, _field) \ EFX_DWORD_FIELD(*_MCDI_DWORD(_buf, _field), EFX_DWORD_0) +/* Write a 32-bit field defined in the protocol as being big-endian. */ +#define MCDI_STRUCT_SET_DWORD_BE(_buf, _field, _value) do { \ + BUILD_BUG_ON(_field ## _LEN != 4); \ + BUILD_BUG_ON(_field ## _OFST & 3); \ + *(__force __be32 *)MCDI_STRUCT_PTR(_buf, _field) = (_value); \ + } while (0) #define MCDI_POPULATE_DWORD_1(_buf, _field, _name1, _value1) \ EFX_POPULATE_DWORD_1(*_MCDI_DWORD(_buf, _field), \ MC_CMD_ ## _name1, _value1) diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c index eaef4a15008a..9f07e1ba7780 100644 --- a/drivers/net/ethernet/sfc/ptp.c +++ b/drivers/net/ethernet/sfc/ptp.c @@ -351,7 +351,7 @@ struct efx_ptp_data { void (*xmit_skb)(struct efx_nic *efx, struct sk_buff *skb); }; -static int efx_phc_adjfreq(struct ptp_clock_info *ptp, s32 delta); +static int efx_phc_adjfine(struct ptp_clock_info *ptp, long scaled_ppm); static int efx_phc_adjtime(struct ptp_clock_info *ptp, s64 delta); static int efx_phc_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts); static int efx_phc_settime(struct ptp_clock_info *ptp, @@ -1508,7 +1508,7 @@ static const struct ptp_clock_info efx_phc_clock_info = { .n_per_out = 0, .n_pins = 0, .pps = 1, - .adjfreq = efx_phc_adjfreq, + .adjfine = efx_phc_adjfine, .adjtime = efx_phc_adjtime, .gettime64 = efx_phc_gettime, .settime64 = efx_phc_settime, @@ -2137,11 +2137,12 @@ void __efx_rx_skb_attach_timestamp(struct efx_channel *channel, ptp->ts_corrections.general_rx); } -static int efx_phc_adjfreq(struct ptp_clock_info *ptp, s32 delta) +static int efx_phc_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) { struct efx_ptp_data *ptp_data = container_of(ptp, struct efx_ptp_data, phc_clock_info); + s32 delta = scaled_ppm_to_ppb(scaled_ppm); struct efx_nic *efx = ptp_data->efx; MCDI_DECLARE_BUF(inadj, MC_CMD_PTP_IN_ADJUST_LEN); s64 adjustment_ns; diff --git a/drivers/net/ethernet/sfc/siena/ptp.c b/drivers/net/ethernet/sfc/siena/ptp.c index 7c46752e6eae..38e666561bcd 100644 --- a/drivers/net/ethernet/sfc/siena/ptp.c +++ b/drivers/net/ethernet/sfc/siena/ptp.c @@ -347,7 +347,7 @@ struct efx_ptp_data { void (*xmit_skb)(struct efx_nic *efx, struct sk_buff *skb); }; -static int efx_phc_adjfreq(struct ptp_clock_info *ptp, s32 delta); +static int efx_phc_adjfine(struct ptp_clock_info *ptp, long scaled_ppm); static int efx_phc_adjtime(struct ptp_clock_info *ptp, s64 delta); static int efx_phc_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts); static int efx_phc_settime(struct ptp_clock_info *ptp, @@ -1429,7 +1429,7 @@ static const struct ptp_clock_info efx_phc_clock_info = { .n_per_out = 0, .n_pins = 0, .pps = 1, - .adjfreq = efx_phc_adjfreq, + .adjfine = efx_phc_adjfine, .adjtime = efx_phc_adjtime, .gettime64 = efx_phc_gettime, .settime64 = efx_phc_settime, @@ -2044,11 +2044,12 @@ void __efx_siena_rx_skb_attach_timestamp(struct efx_channel *channel, ptp->ts_corrections.general_rx); } -static int efx_phc_adjfreq(struct ptp_clock_info *ptp, s32 delta) +static int efx_phc_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) { struct efx_ptp_data *ptp_data = container_of(ptp, struct efx_ptp_data, phc_clock_info); + s32 delta = scaled_ppm_to_ppb(scaled_ppm); struct efx_nic *efx = ptp_data->efx; MCDI_DECLARE_BUF(inadj, MC_CMD_PTP_IN_ADJUST_LEN); s64 adjustment_ns; diff --git a/drivers/net/ethernet/sfc/tc.c b/drivers/net/ethernet/sfc/tc.c index b21a961eabb1..17e1a3447554 100644 --- a/drivers/net/ethernet/sfc/tc.c +++ b/drivers/net/ethernet/sfc/tc.c @@ -124,19 +124,59 @@ static void efx_tc_flow_free(void *ptr, void *arg) kfree(rule); } +/* Boilerplate for the simple 'copy a field' cases */ +#define _MAP_KEY_AND_MASK(_name, _type, _tcget, _tcfield, _field) \ +if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_##_name)) { \ + struct flow_match_##_type fm; \ + \ + flow_rule_match_##_tcget(rule, &fm); \ + match->value._field = fm.key->_tcfield; \ + match->mask._field = fm.mask->_tcfield; \ +} +#define MAP_KEY_AND_MASK(_name, _type, _tcfield, _field) \ + _MAP_KEY_AND_MASK(_name, _type, _type, _tcfield, _field) +#define MAP_ENC_KEY_AND_MASK(_name, _type, _tcget, _tcfield, _field) \ + _MAP_KEY_AND_MASK(ENC_##_name, _type, _tcget, _tcfield, _field) + static int efx_tc_flower_parse_match(struct efx_nic *efx, struct flow_rule *rule, struct efx_tc_match *match, struct netlink_ext_ack *extack) { struct flow_dissector *dissector = rule->match.dissector; + unsigned char ipv = 0; + /* Owing to internal TC infelicities, the IPV6_ADDRS key might be set + * even on IPv4 filters; so rather than relying on dissector->used_keys + * we check the addr_type in the CONTROL key. If we don't find it (or + * it's masked, which should never happen), we treat both IPV4_ADDRS + * and IPV6_ADDRS as absent. + */ if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) { struct flow_match_control fm; flow_rule_match_control(rule, &fm); + if (IS_ALL_ONES(fm.mask->addr_type)) + switch (fm.key->addr_type) { + case FLOW_DISSECTOR_KEY_IPV4_ADDRS: + ipv = 4; + break; + case FLOW_DISSECTOR_KEY_IPV6_ADDRS: + ipv = 6; + break; + default: + break; + } - if (fm.mask->flags) { + if (fm.mask->flags & FLOW_DIS_IS_FRAGMENT) { + match->value.ip_frag = fm.key->flags & FLOW_DIS_IS_FRAGMENT; + match->mask.ip_frag = true; + } + if (fm.mask->flags & FLOW_DIS_FIRST_FRAG) { + match->value.ip_firstfrag = fm.key->flags & FLOW_DIS_FIRST_FRAG; + match->mask.ip_firstfrag = true; + } + if (fm.mask->flags & ~(FLOW_DIS_IS_FRAGMENT | FLOW_DIS_FIRST_FRAG)) { NL_SET_ERR_MSG_FMT_MOD(extack, "Unsupported match on control.flags %#x", fm.mask->flags); return -EOPNOTSUPP; @@ -144,26 +184,101 @@ static int efx_tc_flower_parse_match(struct efx_nic *efx, } if (dissector->used_keys & ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | - BIT(FLOW_DISSECTOR_KEY_BASIC))) { + BIT(FLOW_DISSECTOR_KEY_BASIC) | + BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_VLAN) | + BIT(FLOW_DISSECTOR_KEY_CVLAN) | + BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_PORTS) | + BIT(FLOW_DISSECTOR_KEY_TCP) | + BIT(FLOW_DISSECTOR_KEY_IP))) { NL_SET_ERR_MSG_FMT_MOD(extack, "Unsupported flower keys %#x", dissector->used_keys); return -EOPNOTSUPP; } - if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) { - struct flow_match_basic fm; + MAP_KEY_AND_MASK(BASIC, basic, n_proto, eth_proto); + /* Make sure we're IP if any L3/L4 keys used. */ + if (!IS_ALL_ONES(match->mask.eth_proto) || + !(match->value.eth_proto == htons(ETH_P_IP) || + match->value.eth_proto == htons(ETH_P_IPV6))) + if (dissector->used_keys & + (BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_PORTS) | + BIT(FLOW_DISSECTOR_KEY_IP) | + BIT(FLOW_DISSECTOR_KEY_TCP))) { + NL_SET_ERR_MSG_FMT_MOD(extack, "L3/L4 flower keys %#x require protocol ipv[46]", + dissector->used_keys); + return -EINVAL; + } - flow_rule_match_basic(rule, &fm); - if (fm.mask->n_proto) { - NL_SET_ERR_MSG_MOD(extack, "Unsupported eth_proto match"); - return -EOPNOTSUPP; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) { + struct flow_match_vlan fm; + + flow_rule_match_vlan(rule, &fm); + if (fm.mask->vlan_id || fm.mask->vlan_priority || fm.mask->vlan_tpid) { + match->value.vlan_proto[0] = fm.key->vlan_tpid; + match->mask.vlan_proto[0] = fm.mask->vlan_tpid; + match->value.vlan_tci[0] = cpu_to_be16(fm.key->vlan_priority << 13 | + fm.key->vlan_id); + match->mask.vlan_tci[0] = cpu_to_be16(fm.mask->vlan_priority << 13 | + fm.mask->vlan_id); } - if (fm.mask->ip_proto) { - NL_SET_ERR_MSG_MOD(extack, "Unsupported ip_proto match"); - return -EOPNOTSUPP; + } + + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CVLAN)) { + struct flow_match_vlan fm; + + flow_rule_match_cvlan(rule, &fm); + if (fm.mask->vlan_id || fm.mask->vlan_priority || fm.mask->vlan_tpid) { + match->value.vlan_proto[1] = fm.key->vlan_tpid; + match->mask.vlan_proto[1] = fm.mask->vlan_tpid; + match->value.vlan_tci[1] = cpu_to_be16(fm.key->vlan_priority << 13 | + fm.key->vlan_id); + match->mask.vlan_tci[1] = cpu_to_be16(fm.mask->vlan_priority << 13 | + fm.mask->vlan_id); } } + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { + struct flow_match_eth_addrs fm; + + flow_rule_match_eth_addrs(rule, &fm); + ether_addr_copy(match->value.eth_saddr, fm.key->src); + ether_addr_copy(match->value.eth_daddr, fm.key->dst); + ether_addr_copy(match->mask.eth_saddr, fm.mask->src); + ether_addr_copy(match->mask.eth_daddr, fm.mask->dst); + } + + MAP_KEY_AND_MASK(BASIC, basic, ip_proto, ip_proto); + /* Make sure we're TCP/UDP if any L4 keys used. */ + if ((match->value.ip_proto != IPPROTO_UDP && + match->value.ip_proto != IPPROTO_TCP) || !IS_ALL_ONES(match->mask.ip_proto)) + if (dissector->used_keys & + (BIT(FLOW_DISSECTOR_KEY_PORTS) | + BIT(FLOW_DISSECTOR_KEY_TCP))) { + NL_SET_ERR_MSG_FMT_MOD(extack, "L4 flower keys %#x require ipproto udp or tcp", + dissector->used_keys); + return -EINVAL; + } + MAP_KEY_AND_MASK(IP, ip, tos, ip_tos); + MAP_KEY_AND_MASK(IP, ip, ttl, ip_ttl); + if (ipv == 4) { + MAP_KEY_AND_MASK(IPV4_ADDRS, ipv4_addrs, src, src_ip); + MAP_KEY_AND_MASK(IPV4_ADDRS, ipv4_addrs, dst, dst_ip); + } +#ifdef CONFIG_IPV6 + else if (ipv == 6) { + MAP_KEY_AND_MASK(IPV6_ADDRS, ipv6_addrs, src, src_ip6); + MAP_KEY_AND_MASK(IPV6_ADDRS, ipv6_addrs, dst, dst_ip6); + } +#endif + MAP_KEY_AND_MASK(PORTS, ports, src, l4_sport); + MAP_KEY_AND_MASK(PORTS, ports, dst, l4_dport); + MAP_KEY_AND_MASK(TCP, tcp, flags, tcp_flags); + return 0; } diff --git a/drivers/net/ethernet/sfc/tc.h b/drivers/net/ethernet/sfc/tc.h index 4373c3243e3c..4240c375a8e6 100644 --- a/drivers/net/ethernet/sfc/tc.h +++ b/drivers/net/ethernet/sfc/tc.h @@ -15,6 +15,8 @@ #include <linux/rhashtable.h> #include "net_driver.h" +#define IS_ALL_ONES(v) (!(typeof (v))~(v)) + struct efx_tc_action_set { u16 deliver:1; u32 dest_mport; @@ -26,6 +28,20 @@ struct efx_tc_match_fields { /* L1 */ u32 ingress_port; u8 recirc_id; + /* L2 (inner when encap) */ + __be16 eth_proto; + __be16 vlan_tci[2], vlan_proto[2]; + u8 eth_saddr[ETH_ALEN], eth_daddr[ETH_ALEN]; + /* L3 (when IP) */ + u8 ip_proto, ip_tos, ip_ttl; + __be32 src_ip, dst_ip; +#ifdef CONFIG_IPV6 + struct in6_addr src_ip6, dst_ip6; +#endif + bool ip_frag, ip_firstfrag; + /* L4 */ + __be16 l4_sport, l4_dport; /* Ports (UDP, TCP) */ + __be16 tcp_flags; }; struct efx_tc_match { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c index 0a2afc1a3124..7deb1f817dac 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c @@ -629,7 +629,6 @@ static int ehl_common_data(struct pci_dev *pdev, { plat->rx_queues_to_use = 8; plat->tx_queues_to_use = 8; - plat->clk_ptp_rate = 200000000; plat->use_phy_wol = 1; plat->safety_feat_cfg->tsoee = 1; @@ -654,6 +653,8 @@ static int ehl_sgmii_data(struct pci_dev *pdev, plat->serdes_powerup = intel_serdes_powerup; plat->serdes_powerdown = intel_serdes_powerdown; + plat->clk_ptp_rate = 204800000; + return ehl_common_data(pdev, plat); } @@ -667,6 +668,8 @@ static int ehl_rgmii_data(struct pci_dev *pdev, plat->bus_id = 1; plat->phy_interface = PHY_INTERFACE_MODE_RGMII; + plat->clk_ptp_rate = 204800000; + return ehl_common_data(pdev, plat); } @@ -683,6 +686,8 @@ static int ehl_pse0_common_data(struct pci_dev *pdev, plat->bus_id = 2; plat->addr64 = 32; + plat->clk_ptp_rate = 200000000; + intel_mgbe_pse_crossts_adj(intel_priv, EHL_PSE_ART_MHZ); return ehl_common_data(pdev, plat); @@ -722,6 +727,8 @@ static int ehl_pse1_common_data(struct pci_dev *pdev, plat->bus_id = 3; plat->addr64 = 32; + plat->clk_ptp_rate = 200000000; + intel_mgbe_pse_crossts_adj(intel_priv, EHL_PSE_ART_MHZ); return ehl_common_data(pdev, plat); @@ -757,7 +764,7 @@ static int tgl_common_data(struct pci_dev *pdev, { plat->rx_queues_to_use = 6; plat->tx_queues_to_use = 4; - plat->clk_ptp_rate = 200000000; + plat->clk_ptp_rate = 204800000; plat->speed_mode_2500 = intel_speed_mode_2500; plat->safety_feat_cfg->tsoee = 1; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c index 79fa7870563b..a25c187d3185 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c @@ -75,20 +75,24 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id plat->mdio_bus_data = devm_kzalloc(&pdev->dev, sizeof(*plat->mdio_bus_data), GFP_KERNEL); - if (!plat->mdio_bus_data) - return -ENOMEM; + if (!plat->mdio_bus_data) { + ret = -ENOMEM; + goto err_put_node; + } plat->mdio_bus_data->needs_reset = true; } plat->dma_cfg = devm_kzalloc(&pdev->dev, sizeof(*plat->dma_cfg), GFP_KERNEL); - if (!plat->dma_cfg) - return -ENOMEM; + if (!plat->dma_cfg) { + ret = -ENOMEM; + goto err_put_node; + } /* Enable pci device */ ret = pci_enable_device(pdev); if (ret) { dev_err(&pdev->dev, "%s: ERROR: failed to enable device\n", __func__); - return ret; + goto err_put_node; } /* Get the base address of device */ @@ -97,7 +101,7 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id continue; ret = pcim_iomap_regions(pdev, BIT(0), pci_name(pdev)); if (ret) - return ret; + goto err_disable_device; break; } @@ -108,7 +112,8 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id phy_mode = device_get_phy_mode(&pdev->dev); if (phy_mode < 0) { dev_err(&pdev->dev, "phy_mode not found\n"); - return phy_mode; + ret = phy_mode; + goto err_disable_device; } plat->phy_interface = phy_mode; @@ -125,6 +130,7 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id if (res.irq < 0) { dev_err(&pdev->dev, "IRQ macirq not found\n"); ret = -ENODEV; + goto err_disable_msi; } res.wol_irq = of_irq_get_byname(np, "eth_wake_irq"); @@ -137,15 +143,31 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id if (res.lpi_irq < 0) { dev_err(&pdev->dev, "IRQ eth_lpi not found\n"); ret = -ENODEV; + goto err_disable_msi; } - return stmmac_dvr_probe(&pdev->dev, plat, &res); + ret = stmmac_dvr_probe(&pdev->dev, plat, &res); + if (ret) + goto err_disable_msi; + + return ret; + +err_disable_msi: + pci_disable_msi(pdev); +err_disable_device: + pci_disable_device(pdev); +err_put_node: + of_node_put(plat->mdio_node); + return ret; } static void loongson_dwmac_remove(struct pci_dev *pdev) { + struct net_device *ndev = dev_get_drvdata(&pdev->dev); + struct stmmac_priv *priv = netdev_priv(ndev); int i; + of_node_put(priv->plat->mdio_node); stmmac_dvr_remove(&pdev->dev); for (i = 0; i < PCI_STD_NUM_BARS; i++) { @@ -155,6 +177,7 @@ static void loongson_dwmac_remove(struct pci_dev *pdev) break; } + pci_disable_msi(pdev); pci_disable_device(pdev); } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c index c7a6588d9398..e8b507f88fbc 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c @@ -272,11 +272,9 @@ static int meson8b_devm_clk_prepare_enable(struct meson8b_dwmac *dwmac, if (ret) return ret; - devm_add_action_or_reset(dwmac->dev, - (void(*)(void *))clk_disable_unprepare, - dwmac->rgmii_tx_clk); - - return 0; + return devm_add_action_or_reset(dwmac->dev, + (void(*)(void *))clk_disable_unprepare, + clk); } static int meson8b_init_rgmii_delays(struct meson8b_dwmac *dwmac) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 8273e6a175c8..2fea8785aaf4 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1080,7 +1080,6 @@ static void stmmac_mac_link_up(struct phylink_config *config, } static const struct phylink_mac_ops stmmac_phylink_mac_ops = { - .validate = phylink_generic_validate, .mac_select_pcs = stmmac_mac_select_pcs, .mac_config = stmmac_mac_config, .mac_link_down = stmmac_mac_link_down, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c index 4d11980dcd64..fc06ddeac0d5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c @@ -15,29 +15,20 @@ * stmmac_adjust_freq * * @ptp: pointer to ptp_clock_info structure - * @ppb: desired period change in parts ber billion + * @scaled_ppm: desired period change in scaled parts per million * * Description: this function will adjust the frequency of hardware clock. + * + * Scaled parts per million is ppm with a 16-bit binary fractional field. */ -static int stmmac_adjust_freq(struct ptp_clock_info *ptp, s32 ppb) +static int stmmac_adjust_freq(struct ptp_clock_info *ptp, long scaled_ppm) { struct stmmac_priv *priv = container_of(ptp, struct stmmac_priv, ptp_clock_ops); unsigned long flags; - u32 diff, addend; - int neg_adj = 0; - u64 adj; - - if (ppb < 0) { - neg_adj = 1; - ppb = -ppb; - } + u32 addend; - addend = priv->default_addend; - adj = addend; - adj *= ppb; - diff = div_u64(adj, 1000000000ULL); - addend = neg_adj ? (addend - diff) : (addend + diff); + addend = adjust_by_scaled_ppm(priv->default_addend, scaled_ppm); write_lock_irqsave(&priv->ptp_lock, flags); stmmac_config_addend(priv, priv->ptpaddr, addend); @@ -269,7 +260,7 @@ static struct ptp_clock_info stmmac_ptp_clock_ops = { .n_per_out = 0, /* will be overwritten in stmmac_ptp_register */ .n_pins = 0, .pps = 0, - .adjfreq = stmmac_adjust_freq, + .adjfine = stmmac_adjust_freq, .adjtime = stmmac_adjust_time, .gettime64 = stmmac_get_time, .settime64 = stmmac_set_time, diff --git a/drivers/net/ethernet/sunplus/spl2sw_driver.c b/drivers/net/ethernet/sunplus/spl2sw_driver.c index 9be585237277..c499a14314f1 100644 --- a/drivers/net/ethernet/sunplus/spl2sw_driver.c +++ b/drivers/net/ethernet/sunplus/spl2sw_driver.c @@ -287,7 +287,6 @@ static u32 spl2sw_init_netdev(struct platform_device *pdev, u8 *mac_addr, if (ret) { dev_err(&pdev->dev, "Failed to register net device \"%s\"!\n", ndev->name); - free_netdev(ndev); *r_ndev = NULL; return ret; } diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 8800c8a010ff..6b0458df613a 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -24,6 +24,7 @@ #include <linux/platform_device.h> #include <linux/pm_runtime.h> #include <linux/regmap.h> +#include <linux/rtnetlink.h> #include <linux/mfd/syscon.h> #include <linux/sys_soc.h> #include <linux/dma/ti-cppi5.h> @@ -132,6 +133,11 @@ NETIF_MSG_IFUP | NETIF_MSG_PROBE | NETIF_MSG_IFDOWN | \ NETIF_MSG_RX_ERR | NETIF_MSG_TX_ERR) +static int am65_cpsw_nuss_init_tx_chns(struct am65_cpsw_common *common); +static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common); +static void am65_cpsw_nuss_free_tx_chns(struct am65_cpsw_common *common); +static void am65_cpsw_nuss_free_rx_chns(struct am65_cpsw_common *common); + static void am65_cpsw_port_set_sl_mac(struct am65_cpsw_port *slave, const u8 *dev_addr) { @@ -373,6 +379,20 @@ static int am65_cpsw_nuss_common_open(struct am65_cpsw_common *common) if (common->usage_count) return 0; + /* init tx/rx channels */ + ret = am65_cpsw_nuss_init_tx_chns(common); + if (ret) { + dev_err(common->dev, "init_tx_chns failed\n"); + return ret; + } + + ret = am65_cpsw_nuss_init_rx_chns(common); + if (ret) { + dev_err(common->dev, "init_rx_chns failed\n"); + am65_cpsw_nuss_free_tx_chns(common); + return ret; + } + /* Control register */ writel(AM65_CPSW_CTL_P0_ENABLE | AM65_CPSW_CTL_P0_TX_CRC_REMOVE | AM65_CPSW_CTL_VLAN_AWARE | AM65_CPSW_CTL_P0_RX_PAD, @@ -401,6 +421,7 @@ static int am65_cpsw_nuss_common_open(struct am65_cpsw_common *common) /* disable priority elevation */ writel(0, common->cpsw_base + AM65_CPSW_REG_PTYPE); + cpsw_ale_control_set(common->ale, 0, ALE_CLEAR, 1); cpsw_ale_start(common->ale); /* limit to one RX flow only */ @@ -432,7 +453,8 @@ static int am65_cpsw_nuss_common_open(struct am65_cpsw_common *common) GFP_KERNEL); if (!skb) { dev_err(common->dev, "cannot allocate skb\n"); - return -ENOMEM; + ret = -ENOMEM; + goto err; } ret = am65_cpsw_nuss_rx_push(common, skb); @@ -441,7 +463,7 @@ static int am65_cpsw_nuss_common_open(struct am65_cpsw_common *common) "cannot submit skb to channel rx, error %d\n", ret); kfree_skb(skb); - return ret; + goto err; } kmemleak_not_leak(skb); } @@ -450,7 +472,7 @@ static int am65_cpsw_nuss_common_open(struct am65_cpsw_common *common) for (i = 0; i < common->tx_ch_num; i++) { ret = k3_udma_glue_enable_tx_chn(common->tx_chns[i].tx_chn); if (ret) - return ret; + goto err; napi_enable(&common->tx_chns[i].napi_tx); } @@ -462,6 +484,12 @@ static int am65_cpsw_nuss_common_open(struct am65_cpsw_common *common) dev_dbg(common->dev, "cpsw_nuss started\n"); return 0; + +err: + am65_cpsw_nuss_free_tx_chns(common); + am65_cpsw_nuss_free_rx_chns(common); + + return ret; } static void am65_cpsw_nuss_tx_cleanup(void *data, dma_addr_t desc_dma); @@ -515,6 +543,9 @@ static int am65_cpsw_nuss_common_stop(struct am65_cpsw_common *common) writel(0, common->cpsw_base + AM65_CPSW_REG_CTL); writel(0, common->cpsw_base + AM65_CPSW_REG_STAT_PORT_EN); + am65_cpsw_nuss_free_tx_chns(common); + am65_cpsw_nuss_free_rx_chns(common); + dev_dbg(common->dev, "cpsw_nuss stopped\n"); return 0; } @@ -555,11 +586,29 @@ static int am65_cpsw_nuss_ndo_slave_open(struct net_device *ndev) struct am65_cpsw_common *common = am65_ndev_to_common(ndev); struct am65_cpsw_port *port = am65_ndev_to_port(ndev); int ret, i; + u32 reg; + int tmo; ret = pm_runtime_resume_and_get(common->dev); if (ret < 0) return ret; + /* Idle MAC port */ + cpsw_sl_ctl_set(port->slave.mac_sl, CPSW_SL_CTL_CMD_IDLE); + + tmo = cpsw_sl_wait_for_idle(port->slave.mac_sl, 100); + dev_info(common->dev, "down msc_sl %08x tmo %d\n", + cpsw_sl_reg_read(port->slave.mac_sl, CPSW_SL_MACSTATUS), tmo); + + cpsw_sl_ctl_reset(port->slave.mac_sl); + + /* soft reset MAC */ + cpsw_sl_reg_write(port->slave.mac_sl, CPSW_SL_SOFT_RESET, 1); + mdelay(1); + reg = cpsw_sl_reg_read(port->slave.mac_sl, CPSW_SL_SOFT_RESET); + if (reg) + dev_info(common->dev, "mac reset not yet done\n"); + /* Notify the stack of the actual queue counts. */ ret = netif_set_real_num_tx_queues(ndev, common->tx_ch_num); if (ret) { @@ -1380,13 +1429,6 @@ static void am65_cpsw_nuss_ndo_get_stats(struct net_device *dev, stats->tx_dropped = dev->stats.tx_dropped; } -static struct devlink_port *am65_cpsw_ndo_get_devlink_port(struct net_device *ndev) -{ - struct am65_cpsw_port *port = am65_ndev_to_port(ndev); - - return &port->devlink_port; -} - static const struct net_device_ops am65_cpsw_nuss_netdev_ops = { .ndo_open = am65_cpsw_nuss_ndo_slave_open, .ndo_stop = am65_cpsw_nuss_ndo_slave_stop, @@ -1400,7 +1442,6 @@ static const struct net_device_ops am65_cpsw_nuss_netdev_ops = { .ndo_vlan_rx_kill_vid = am65_cpsw_nuss_ndo_slave_kill_vid, .ndo_eth_ioctl = am65_cpsw_nuss_ndo_slave_ioctl, .ndo_setup_tc = am65_cpsw_qos_ndo_setup_tc, - .ndo_get_devlink_port = am65_cpsw_ndo_get_devlink_port, }; static void am65_cpsw_nuss_mac_config(struct phylink_config *config, unsigned int mode, @@ -1479,7 +1520,6 @@ static void am65_cpsw_nuss_mac_link_up(struct phylink_config *config, struct phy } static const struct phylink_mac_ops am65_cpsw_phylink_mac_ops = { - .validate = phylink_generic_validate, .mac_config = am65_cpsw_nuss_mac_config, .mac_link_down = am65_cpsw_nuss_mac_link_down, .mac_link_up = am65_cpsw_nuss_mac_link_up, @@ -1499,9 +1539,9 @@ static void am65_cpsw_nuss_slave_disable_unused(struct am65_cpsw_port *port) cpsw_sl_ctl_reset(port->slave.mac_sl); } -static void am65_cpsw_nuss_free_tx_chns(void *data) +static void am65_cpsw_nuss_free_tx_chns(struct am65_cpsw_common *common) { - struct am65_cpsw_common *common = data; + struct device *dev = common->dev; int i; for (i = 0; i < common->tx_ch_num; i++) { @@ -1513,7 +1553,11 @@ static void am65_cpsw_nuss_free_tx_chns(void *data) if (!IS_ERR_OR_NULL(tx_chn->tx_chn)) k3_udma_glue_release_tx_chn(tx_chn->tx_chn); - memset(tx_chn, 0, sizeof(*tx_chn)); + /* Don't clear tx_chn memory as we need to preserve + * data between suspend/resume + */ + if (!(tx_chn->irq < 0)) + devm_free_irq(dev, tx_chn->irq, tx_chn); } } @@ -1522,12 +1566,10 @@ void am65_cpsw_nuss_remove_tx_chns(struct am65_cpsw_common *common) struct device *dev = common->dev; int i; - devm_remove_action(dev, am65_cpsw_nuss_free_tx_chns, common); - for (i = 0; i < common->tx_ch_num; i++) { struct am65_cpsw_tx_chn *tx_chn = &common->tx_chns[i]; - if (tx_chn->irq) + if (!(tx_chn->irq < 0)) devm_free_irq(dev, tx_chn->irq, tx_chn); netif_napi_del(&tx_chn->napi_tx); @@ -1597,7 +1639,7 @@ static int am65_cpsw_nuss_init_tx_chns(struct am65_cpsw_common *common) } tx_chn->irq = k3_udma_glue_tx_get_irq(tx_chn->tx_chn); - if (tx_chn->irq <= 0) { + if (tx_chn->irq < 0) { dev_err(dev, "Failed to get tx dma irq %d\n", tx_chn->irq); goto err; @@ -1606,25 +1648,36 @@ static int am65_cpsw_nuss_init_tx_chns(struct am65_cpsw_common *common) snprintf(tx_chn->tx_chn_name, sizeof(tx_chn->tx_chn_name), "%s-tx%d", dev_name(dev), tx_chn->id); + + ret = devm_request_irq(dev, tx_chn->irq, + am65_cpsw_nuss_tx_irq, + IRQF_TRIGGER_HIGH, + tx_chn->tx_chn_name, tx_chn); + if (ret) { + dev_err(dev, "failure requesting tx%u irq %u, %d\n", + tx_chn->id, tx_chn->irq, ret); + tx_chn->irq = -EINVAL; + goto err; + } } + return 0; + err: - i = devm_add_action(dev, am65_cpsw_nuss_free_tx_chns, common); - if (i) { - dev_err(dev, "Failed to add free_tx_chns action %d\n", i); - return i; - } + am65_cpsw_nuss_free_tx_chns(common); return ret; } -static void am65_cpsw_nuss_free_rx_chns(void *data) +static void am65_cpsw_nuss_free_rx_chns(struct am65_cpsw_common *common) { - struct am65_cpsw_common *common = data; struct am65_cpsw_rx_chn *rx_chn; rx_chn = &common->rx_chns; + if (!(rx_chn->irq < 0)) + devm_free_irq(common->dev, rx_chn->irq, common); + if (!IS_ERR_OR_NULL(rx_chn->desc_pool)) k3_cppi_desc_pool_destroy(rx_chn->desc_pool); @@ -1647,7 +1700,7 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common) rx_cfg.swdata_size = AM65_CPSW_NAV_SW_DATA_SIZE; rx_cfg.flow_id_num = AM65_CPSW_MAX_RX_FLOWS; - rx_cfg.flow_id_base = common->rx_flow_id_base; + rx_cfg.flow_id_base = -1; /* init all flows */ rx_chn->dev = dev; @@ -1719,13 +1772,21 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common) } } -err: - i = devm_add_action(dev, am65_cpsw_nuss_free_rx_chns, common); - if (i) { - dev_err(dev, "Failed to add free_rx_chns action %d\n", i); - return i; + ret = devm_request_irq(dev, rx_chn->irq, + am65_cpsw_nuss_rx_irq, + IRQF_TRIGGER_HIGH, dev_name(dev), common); + if (ret) { + dev_err(dev, "failure requesting rx irq %u, %d\n", + rx_chn->irq, ret); + rx_chn->irq = -EINVAL; + goto err; } + return 0; + +err: + am65_cpsw_nuss_free_rx_chns(common); + return ret; } @@ -1990,6 +2051,7 @@ am65_cpsw_nuss_init_port_ndev(struct am65_cpsw_common *common, u32 port_idx) port->slave.phylink_config.dev = &port->ndev->dev; port->slave.phylink_config.type = PHYLINK_NETDEV; port->slave.phylink_config.mac_capabilities = MAC_SYM_PAUSE | MAC_10 | MAC_100 | MAC_1000FD; + port->slave.phylink_config.mac_managed_pm = true; /* MAC does PM */ if (phy_interface_mode_is_rgmii(port->slave.phy_if)) { phy_interface_set_rgmii(port->slave.phylink_config.supported_interfaces); @@ -2051,28 +2113,16 @@ static int am65_cpsw_nuss_init_ndevs(struct am65_cpsw_common *common) static int am65_cpsw_nuss_ndev_add_tx_napi(struct am65_cpsw_common *common) { - struct device *dev = common->dev; - int i, ret = 0; + int i; for (i = 0; i < common->tx_ch_num; i++) { struct am65_cpsw_tx_chn *tx_chn = &common->tx_chns[i]; netif_napi_add_tx(common->dma_ndev, &tx_chn->napi_tx, am65_cpsw_nuss_tx_poll); - - ret = devm_request_irq(dev, tx_chn->irq, - am65_cpsw_nuss_tx_irq, - IRQF_TRIGGER_HIGH, - tx_chn->tx_chn_name, tx_chn); - if (ret) { - dev_err(dev, "failure requesting tx%u irq %u, %d\n", - tx_chn->id, tx_chn->irq, ret); - goto err; - } } -err: - return ret; + return 0; } static void am65_cpsw_nuss_cleanup_ndev(struct am65_cpsw_common *common) @@ -2534,7 +2584,6 @@ static void am65_cpsw_unregister_devlink(struct am65_cpsw_common *common) static int am65_cpsw_nuss_register_ndevs(struct am65_cpsw_common *common) { struct device *dev = common->dev; - struct devlink_port *dl_port; struct am65_cpsw_port *port; int ret = 0, i; @@ -2542,15 +2591,6 @@ static int am65_cpsw_nuss_register_ndevs(struct am65_cpsw_common *common) if (ret) return ret; - ret = devm_request_irq(dev, common->rx_chns.irq, - am65_cpsw_nuss_rx_irq, - IRQF_TRIGGER_HIGH, dev_name(dev), common); - if (ret) { - dev_err(dev, "failure requesting rx irq %u, %d\n", - common->rx_chns.irq, ret); - return ret; - } - ret = am65_cpsw_nuss_register_devlink(common); if (ret) return ret; @@ -2561,15 +2601,14 @@ static int am65_cpsw_nuss_register_ndevs(struct am65_cpsw_common *common) if (!port->ndev) continue; + SET_NETDEV_DEVLINK_PORT(port->ndev, &port->devlink_port); + ret = register_netdev(port->ndev); if (ret) { dev_err(dev, "error registering slave net device%i %d\n", i, ret); goto err_cleanup_ndev; } - - dl_port = &port->devlink_port; - devlink_port_type_eth_set(dl_port, port->ndev); } ret = am65_cpsw_register_notifiers(common); @@ -2675,6 +2714,7 @@ static int am65_cpsw_nuss_probe(struct platform_device *pdev) struct clk *clk; u64 id_temp; int ret, i; + int ale_entries; common = devm_kzalloc(dev, sizeof(struct am65_cpsw_common), GFP_KERNEL); if (!common) @@ -2705,7 +2745,6 @@ static int am65_cpsw_nuss_probe(struct platform_device *pdev) if (common->port_num < 1 || common->port_num > AM65_CPSW_MAX_PORTS) return -ENOENT; - common->rx_flow_id_base = -1; init_completion(&common->tdown_complete); common->tx_ch_num = 1; common->pf_p0_rx_ptype_rrobin = false; @@ -2747,14 +2786,6 @@ static int am65_cpsw_nuss_probe(struct platform_device *pdev) am65_cpsw_nuss_get_ver(common); - /* init tx channels */ - ret = am65_cpsw_nuss_init_tx_chns(common); - if (ret) - goto err_of_clear; - ret = am65_cpsw_nuss_init_rx_chns(common); - if (ret) - goto err_of_clear; - ret = am65_cpsw_nuss_init_host_p(common); if (ret) goto err_of_clear; @@ -2778,6 +2809,10 @@ static int am65_cpsw_nuss_probe(struct platform_device *pdev) goto err_of_clear; } + ale_entries = common->ale->params.ale_entries; + common->ale_context = devm_kzalloc(dev, + ale_entries * ALE_ENTRY_WORDS * sizeof(u32), + GFP_KERNEL); ret = am65_cpsw_init_cpts(common); if (ret) goto err_of_clear; @@ -2823,7 +2858,6 @@ static int am65_cpsw_nuss_remove(struct platform_device *pdev) if (ret < 0) return ret; - am65_cpsw_nuss_phylink_cleanup(common); am65_cpsw_unregister_devlink(common); am65_cpsw_unregister_notifiers(common); @@ -2831,6 +2865,7 @@ static int am65_cpsw_nuss_remove(struct platform_device *pdev) * dma_deconfigure(dev) before devres_release_all(dev) */ am65_cpsw_nuss_cleanup_ndev(common); + am65_cpsw_nuss_phylink_cleanup(common); of_platform_device_destroy(common->mdio_dev, NULL); @@ -2839,10 +2874,89 @@ static int am65_cpsw_nuss_remove(struct platform_device *pdev) return 0; } +#ifdef CONFIG_PM_SLEEP +static int am65_cpsw_nuss_suspend(struct device *dev) +{ + struct am65_cpsw_common *common = dev_get_drvdata(dev); + struct am65_cpsw_port *port; + struct net_device *ndev; + int i, ret; + struct am65_cpsw_host *host_p = am65_common_get_host(common); + + cpsw_ale_dump(common->ale, common->ale_context); + host_p->vid_context = readl(host_p->port_base + AM65_CPSW_PORT_VLAN_REG_OFFSET); + for (i = 0; i < common->port_num; i++) { + port = &common->ports[i]; + ndev = port->ndev; + + if (!ndev) + continue; + + port->vid_context = readl(port->port_base + AM65_CPSW_PORT_VLAN_REG_OFFSET); + netif_device_detach(ndev); + if (netif_running(ndev)) { + rtnl_lock(); + ret = am65_cpsw_nuss_ndo_slave_stop(ndev); + rtnl_unlock(); + if (ret < 0) { + netdev_err(ndev, "failed to stop: %d", ret); + return ret; + } + } + } + + am65_cpts_suspend(common->cpts); + + return 0; +} + +static int am65_cpsw_nuss_resume(struct device *dev) +{ + struct am65_cpsw_common *common = dev_get_drvdata(dev); + struct am65_cpsw_port *port; + struct net_device *ndev; + int i, ret; + struct am65_cpsw_host *host_p = am65_common_get_host(common); + + am65_cpts_resume(common->cpts); + + for (i = 0; i < common->port_num; i++) { + port = &common->ports[i]; + ndev = port->ndev; + + if (!ndev) + continue; + + if (netif_running(ndev)) { + rtnl_lock(); + ret = am65_cpsw_nuss_ndo_slave_open(ndev); + rtnl_unlock(); + if (ret < 0) { + netdev_err(ndev, "failed to start: %d", ret); + return ret; + } + } + + netif_device_attach(ndev); + writel(port->vid_context, port->port_base + AM65_CPSW_PORT_VLAN_REG_OFFSET); + } + + writel(host_p->vid_context, host_p->port_base + AM65_CPSW_PORT_VLAN_REG_OFFSET); + cpsw_ale_restore(common->ale, common->ale_context); + + return 0; +} +#endif /* CONFIG_PM_SLEEP */ + +static const struct dev_pm_ops am65_cpsw_nuss_dev_pm_ops = { + SET_SYSTEM_SLEEP_PM_OPS(am65_cpsw_nuss_suspend, am65_cpsw_nuss_resume) +}; + static struct platform_driver am65_cpsw_nuss_driver = { .driver = { .name = AM65_CPSW_DRV_NAME, .of_match_table = am65_cpsw_nuss_of_mtable, + .pm = &am65_cpsw_nuss_dev_pm_ops, }, .probe = am65_cpsw_nuss_probe, .remove = am65_cpsw_nuss_remove, diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.h b/drivers/net/ethernet/ti/am65-cpsw-nuss.h index 2c9850fdfcb6..4b75620f8d28 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.h +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.h @@ -55,12 +55,16 @@ struct am65_cpsw_port { bool rx_ts_enabled; struct am65_cpsw_qos qos; struct devlink_port devlink_port; + /* Only for suspend resume context */ + u32 vid_context; }; struct am65_cpsw_host { struct am65_cpsw_common *common; void __iomem *port_base; void __iomem *stat_base; + /* Only for suspend resume context */ + u32 vid_context; }; struct am65_cpsw_tx_chn { @@ -145,6 +149,8 @@ struct am65_cpsw_common { struct net_device *hw_bridge_dev; struct notifier_block am65_cpsw_netdevice_nb; unsigned char switch_id[MAX_PHYS_ITEM_ID_LEN]; + /* only for suspend/resume context restore */ + u32 *ale_context; }; struct am65_cpsw_ndev_stats { diff --git a/drivers/net/ethernet/ti/am65-cpts.c b/drivers/net/ethernet/ti/am65-cpts.c index e2f0fb286143..9535396b28cd 100644 --- a/drivers/net/ethernet/ti/am65-cpts.c +++ b/drivers/net/ethernet/ti/am65-cpts.c @@ -176,6 +176,16 @@ struct am65_cpts { u32 genf_enable; u32 hw_ts_enable; struct sk_buff_head txq; + /* context save/restore */ + u64 sr_cpts_ns; + u64 sr_ktime_ns; + u32 sr_control; + u32 sr_int_enable; + u32 sr_rftclk_sel; + u32 sr_ts_ppm_hi; + u32 sr_ts_ppm_low; + struct am65_genf_regs sr_genf[AM65_CPTS_GENF_MAX_NUM]; + struct am65_genf_regs sr_estf[AM65_CPTS_ESTF_MAX_NUM]; }; struct am65_cpts_skb_cb_data { @@ -381,9 +391,10 @@ static irqreturn_t am65_cpts_interrupt(int irq, void *dev_id) } /* PTP clock operations */ -static int am65_cpts_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb) +static int am65_cpts_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) { struct am65_cpts *cpts = container_of(ptp, struct am65_cpts, ptp_info); + s32 ppb = scaled_ppm_to_ppb(scaled_ppm); int neg_adj = 0; u64 adj_period; u32 val; @@ -615,7 +626,7 @@ static long am65_cpts_ts_work(struct ptp_clock_info *ptp); static struct ptp_clock_info am65_ptp_info = { .owner = THIS_MODULE, .name = "CTPS timer", - .adjfreq = am65_cpts_ptp_adjfreq, + .adjfine = am65_cpts_ptp_adjfine, .adjtime = am65_cpts_ptp_adjtime, .gettimex64 = am65_cpts_ptp_gettimex, .settime64 = am65_cpts_ptp_settime, @@ -1029,6 +1040,72 @@ refclk_disable: } EXPORT_SYMBOL_GPL(am65_cpts_create); +void am65_cpts_suspend(struct am65_cpts *cpts) +{ + /* save state and disable CPTS */ + cpts->sr_control = am65_cpts_read32(cpts, control); + cpts->sr_int_enable = am65_cpts_read32(cpts, int_enable); + cpts->sr_rftclk_sel = am65_cpts_read32(cpts, rftclk_sel); + cpts->sr_ts_ppm_hi = am65_cpts_read32(cpts, ts_ppm_hi); + cpts->sr_ts_ppm_low = am65_cpts_read32(cpts, ts_ppm_low); + cpts->sr_cpts_ns = am65_cpts_gettime(cpts, NULL); + cpts->sr_ktime_ns = ktime_to_ns(ktime_get_real()); + am65_cpts_disable(cpts); + clk_disable(cpts->refclk); + + /* Save GENF state */ + memcpy_fromio(&cpts->sr_genf, &cpts->reg->genf, sizeof(cpts->sr_genf)); + + /* Save ESTF state */ + memcpy_fromio(&cpts->sr_estf, &cpts->reg->estf, sizeof(cpts->sr_estf)); +} +EXPORT_SYMBOL_GPL(am65_cpts_suspend); + +void am65_cpts_resume(struct am65_cpts *cpts) +{ + int i; + s64 ktime_ns; + + /* restore state and enable CPTS */ + clk_enable(cpts->refclk); + am65_cpts_write32(cpts, cpts->sr_rftclk_sel, rftclk_sel); + am65_cpts_set_add_val(cpts); + am65_cpts_write32(cpts, cpts->sr_control, control); + am65_cpts_write32(cpts, cpts->sr_int_enable, int_enable); + + /* Restore time to saved CPTS time + time in suspend/resume */ + ktime_ns = ktime_to_ns(ktime_get_real()); + ktime_ns -= cpts->sr_ktime_ns; + am65_cpts_settime(cpts, cpts->sr_cpts_ns + ktime_ns); + + /* Restore compensation (PPM) */ + am65_cpts_write32(cpts, cpts->sr_ts_ppm_hi, ts_ppm_hi); + am65_cpts_write32(cpts, cpts->sr_ts_ppm_low, ts_ppm_low); + + /* Restore GENF state */ + for (i = 0; i < AM65_CPTS_GENF_MAX_NUM; i++) { + am65_cpts_write32(cpts, 0, genf[i].length); /* TRM sequence */ + am65_cpts_write32(cpts, cpts->sr_genf[i].comp_hi, genf[i].comp_hi); + am65_cpts_write32(cpts, cpts->sr_genf[i].comp_lo, genf[i].comp_lo); + am65_cpts_write32(cpts, cpts->sr_genf[i].length, genf[i].length); + am65_cpts_write32(cpts, cpts->sr_genf[i].control, genf[i].control); + am65_cpts_write32(cpts, cpts->sr_genf[i].ppm_hi, genf[i].ppm_hi); + am65_cpts_write32(cpts, cpts->sr_genf[i].ppm_low, genf[i].ppm_low); + } + + /* Restore ESTTF state */ + for (i = 0; i < AM65_CPTS_ESTF_MAX_NUM; i++) { + am65_cpts_write32(cpts, 0, estf[i].length); /* TRM sequence */ + am65_cpts_write32(cpts, cpts->sr_estf[i].comp_hi, estf[i].comp_hi); + am65_cpts_write32(cpts, cpts->sr_estf[i].comp_lo, estf[i].comp_lo); + am65_cpts_write32(cpts, cpts->sr_estf[i].length, estf[i].length); + am65_cpts_write32(cpts, cpts->sr_estf[i].control, estf[i].control); + am65_cpts_write32(cpts, cpts->sr_estf[i].ppm_hi, estf[i].ppm_hi); + am65_cpts_write32(cpts, cpts->sr_estf[i].ppm_low, estf[i].ppm_low); + } +} +EXPORT_SYMBOL_GPL(am65_cpts_resume); + static int am65_cpts_probe(struct platform_device *pdev) { struct device_node *node = pdev->dev.of_node; diff --git a/drivers/net/ethernet/ti/am65-cpts.h b/drivers/net/ethernet/ti/am65-cpts.h index cf9fbc28fd03..bd08f4b2edd2 100644 --- a/drivers/net/ethernet/ti/am65-cpts.h +++ b/drivers/net/ethernet/ti/am65-cpts.h @@ -28,6 +28,8 @@ u64 am65_cpts_ns_gettime(struct am65_cpts *cpts); int am65_cpts_estf_enable(struct am65_cpts *cpts, int idx, struct am65_cpts_estf_cfg *cfg); void am65_cpts_estf_disable(struct am65_cpts *cpts, int idx); +void am65_cpts_suspend(struct am65_cpts *cpts); +void am65_cpts_resume(struct am65_cpts *cpts); #else static inline struct am65_cpts *am65_cpts_create(struct device *dev, void __iomem *regs, @@ -69,6 +71,14 @@ static inline int am65_cpts_estf_enable(struct am65_cpts *cpts, int idx, static inline void am65_cpts_estf_disable(struct am65_cpts *cpts, int idx) { } + +static inline void am65_cpts_suspend(struct am65_cpts *cpts) +{ +} + +static inline void am65_cpts_resume(struct am65_cpts *cpts) +{ +} #endif #endif /* K3_CPTS_H_ */ diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 709ca6dd6ecb..13c9c2d6b79b 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -854,6 +854,8 @@ static int cpsw_ndo_open(struct net_device *ndev) err_cleanup: if (!cpsw->usage_count) { + napi_disable(&cpsw->napi_rx); + napi_disable(&cpsw->napi_tx); cpdma_ctlr_stop(cpsw->dma); cpsw_destroy_xdp_rxqs(cpsw); } diff --git a/drivers/net/ethernet/ti/cpsw_ale.c b/drivers/net/ethernet/ti/cpsw_ale.c index 231370e9a801..0c5e783e574c 100644 --- a/drivers/net/ethernet/ti/cpsw_ale.c +++ b/drivers/net/ethernet/ti/cpsw_ale.c @@ -1452,6 +1452,16 @@ void cpsw_ale_dump(struct cpsw_ale *ale, u32 *data) } } +void cpsw_ale_restore(struct cpsw_ale *ale, u32 *data) +{ + int i; + + for (i = 0; i < ale->params.ale_entries; i++) { + cpsw_ale_write(ale, i, data); + data += ALE_ENTRY_WORDS; + } +} + u32 cpsw_ale_get_num_entries(struct cpsw_ale *ale) { return ale ? ale->params.ale_entries : 0; diff --git a/drivers/net/ethernet/ti/cpsw_ale.h b/drivers/net/ethernet/ti/cpsw_ale.h index aba4572cfa3b..6779ee111d57 100644 --- a/drivers/net/ethernet/ti/cpsw_ale.h +++ b/drivers/net/ethernet/ti/cpsw_ale.h @@ -127,6 +127,7 @@ int cpsw_ale_control_get(struct cpsw_ale *ale, int port, int control); int cpsw_ale_control_set(struct cpsw_ale *ale, int port, int control, int value); void cpsw_ale_dump(struct cpsw_ale *ale, u32 *data); +void cpsw_ale_restore(struct cpsw_ale *ale, u32 *data); u32 cpsw_ale_get_num_entries(struct cpsw_ale *ale); static inline int cpsw_ale_get_vlan_p0_untag(struct cpsw_ale *ale, u16 vid) diff --git a/drivers/net/ethernet/ti/cpts.c b/drivers/net/ethernet/ti/cpts.c index 92ca739fac01..bcccf43d368b 100644 --- a/drivers/net/ethernet/ti/cpts.c +++ b/drivers/net/ethernet/ti/cpts.c @@ -213,25 +213,13 @@ static void cpts_update_cur_time(struct cpts *cpts, int match, /* PTP clock operations */ -static int cpts_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb) +static int cpts_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) { struct cpts *cpts = container_of(ptp, struct cpts, info); - int neg_adj = 0; - u32 diff, mult; - u64 adj; - - if (ppb < 0) { - neg_adj = 1; - ppb = -ppb; - } - mult = cpts->cc_mult; - adj = mult; - adj *= ppb; - diff = div_u64(adj, 1000000000ULL); mutex_lock(&cpts->ptp_clk_mutex); - cpts->mult_new = neg_adj ? mult - diff : mult + diff; + cpts->mult_new = adjust_by_scaled_ppm(cpts->cc_mult, scaled_ppm); cpts_update_cur_time(cpts, CPTS_EV_PUSH, NULL); @@ -435,7 +423,7 @@ static const struct ptp_clock_info cpts_info = { .n_ext_ts = 0, .n_pins = 0, .pps = 0, - .adjfreq = cpts_ptp_adjfreq, + .adjfine = cpts_ptp_adjfine, .adjtime = cpts_ptp_adjtime, .gettimex64 = cpts_ptp_gettimeex, .settime64 = cpts_ptp_settime, @@ -794,7 +782,7 @@ struct cpts *cpts_create(struct device *dev, void __iomem *regs, cpts_calc_mult_shift(cpts); /* save cc.mult original value as it can be modified - * by cpts_ptp_adjfreq(). + * by cpts_ptp_adjfine(). */ cpts->cc_mult = cpts->cc.mult; diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c index 8b776f9cdb3f..1bb596a9d8a2 100644 --- a/drivers/net/ethernet/ti/netcp_core.c +++ b/drivers/net/ethernet/ti/netcp_core.c @@ -1261,7 +1261,7 @@ out: } /* Submit the packet */ -static int netcp_ndo_start_xmit(struct sk_buff *skb, struct net_device *ndev) +static netdev_tx_t netcp_ndo_start_xmit(struct sk_buff *skb, struct net_device *ndev) { struct netcp_intf *netcp = netdev_priv(ndev); struct netcp_stats *tx_stats = &netcp->stats; diff --git a/drivers/net/ethernet/tundra/tsi108_eth.c b/drivers/net/ethernet/tundra/tsi108_eth.c index 2cd2afc3fff0..d09d352e1c0a 100644 --- a/drivers/net/ethernet/tundra/tsi108_eth.c +++ b/drivers/net/ethernet/tundra/tsi108_eth.c @@ -1290,12 +1290,15 @@ static int tsi108_open(struct net_device *dev) data->rxring = dma_alloc_coherent(&data->pdev->dev, rxring_size, &data->rxdma, GFP_KERNEL); - if (!data->rxring) + if (!data->rxring) { + free_irq(data->irq_num, dev); return -ENOMEM; + } data->txring = dma_alloc_coherent(&data->pdev->dev, txring_size, &data->txdma, GFP_KERNEL); if (!data->txring) { + free_irq(data->irq_num, dev); dma_free_coherent(&data->pdev->dev, rxring_size, data->rxring, data->rxdma); return -ENOMEM; diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c index 0b1032195859..167f7ff73192 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c @@ -183,6 +183,7 @@ static int txgbe_calc_eeprom_checksum(struct txgbe_hw *hw, u16 *checksum) eeprom_ptrs); if (status != 0) { wx_err(wxhw, "Failed to read EEPROM image\n"); + kvfree(eeprom_ptrs); return status; } local_buffer = eeprom_ptrs; @@ -196,13 +197,14 @@ static int txgbe_calc_eeprom_checksum(struct txgbe_hw *hw, u16 *checksum) if (i != wxhw->eeprom.sw_region_offset + TXGBE_EEPROM_CHECKSUM) *checksum += local_buffer[i]; - *checksum = TXGBE_EEPROM_SUM - *checksum; - if (*checksum < 0) - return -EINVAL; - if (eeprom_ptrs) kvfree(eeprom_ptrs); + if (*checksum > TXGBE_EEPROM_SUM) + return -EINVAL; + + *checksum = TXGBE_EEPROM_SUM - *checksum; + return 0; } diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 441e1058104f..3e310b55bce2 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -1736,7 +1736,6 @@ static void axienet_mac_link_up(struct phylink_config *config, } static const struct phylink_mac_ops axienet_phylink_ops = { - .validate = phylink_generic_validate, .mac_select_pcs = axienet_mac_select_pcs, .mac_config = axienet_mac_config, .mac_link_down = axienet_mac_link_down, @@ -2217,12 +2216,48 @@ static void axienet_shutdown(struct platform_device *pdev) rtnl_unlock(); } +static int axienet_suspend(struct device *dev) +{ + struct net_device *ndev = dev_get_drvdata(dev); + + if (!netif_running(ndev)) + return 0; + + netif_device_detach(ndev); + + rtnl_lock(); + axienet_stop(ndev); + rtnl_unlock(); + + return 0; +} + +static int axienet_resume(struct device *dev) +{ + struct net_device *ndev = dev_get_drvdata(dev); + + if (!netif_running(ndev)) + return 0; + + rtnl_lock(); + axienet_open(ndev); + rtnl_unlock(); + + netif_device_attach(ndev); + + return 0; +} + +static DEFINE_SIMPLE_DEV_PM_OPS(axienet_pm_ops, + axienet_suspend, axienet_resume); + static struct platform_driver axienet_driver = { .probe = axienet_probe, .remove = axienet_remove, .shutdown = axienet_shutdown, .driver = { .name = "xilinx_axienet", + .pm = &axienet_pm_ops, .of_match_table = axienet_of_match, }, }; diff --git a/drivers/net/ethernet/xscale/ptp_ixp46x.c b/drivers/net/ethernet/xscale/ptp_ixp46x.c index 9abbdb71e629..94203eb46e6b 100644 --- a/drivers/net/ethernet/xscale/ptp_ixp46x.c +++ b/drivers/net/ethernet/xscale/ptp_ixp46x.c @@ -120,24 +120,13 @@ static irqreturn_t isr(int irq, void *priv) * PTP clock operations */ -static int ptp_ixp_adjfreq(struct ptp_clock_info *ptp, s32 ppb) +static int ptp_ixp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) { - u64 adj; - u32 diff, addend; - int neg_adj = 0; + u32 addend; struct ixp_clock *ixp_clock = container_of(ptp, struct ixp_clock, caps); struct ixp46x_ts_regs *regs = ixp_clock->regs; - if (ppb < 0) { - neg_adj = 1; - ppb = -ppb; - } - addend = DEFAULT_ADDEND; - adj = addend; - adj *= ppb; - diff = div_u64(adj, 1000000000ULL); - - addend = neg_adj ? addend - diff : addend + diff; + addend = adjust_by_scaled_ppm(DEFAULT_ADDEND, scaled_ppm); __raw_writel(addend, ®s->addend); @@ -230,7 +219,7 @@ static const struct ptp_clock_info ptp_ixp_caps = { .n_ext_ts = N_EXT_TS, .n_pins = 0, .pps = 0, - .adjfreq = ptp_ixp_adjfreq, + .adjfine = ptp_ixp_adjfine, .adjtime = ptp_ixp_adjtime, .gettime64 = ptp_ixp_gettime, .settime64 = ptp_ixp_settime, diff --git a/drivers/net/hamradio/baycom_epp.c b/drivers/net/hamradio/baycom_epp.c index 791b4a53d69f..bd3b0c2655a2 100644 --- a/drivers/net/hamradio/baycom_epp.c +++ b/drivers/net/hamradio/baycom_epp.c @@ -758,7 +758,7 @@ static void epp_bh(struct work_struct *work) * ===================== network driver interface ========================= */ -static int baycom_send_packet(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t baycom_send_packet(struct sk_buff *skb, struct net_device *dev) { struct baycom_state *bc = netdev_priv(dev); diff --git a/drivers/net/hamradio/bpqether.c b/drivers/net/hamradio/bpqether.c index 30af0081e2be..83a16d10eedb 100644 --- a/drivers/net/hamradio/bpqether.c +++ b/drivers/net/hamradio/bpqether.c @@ -533,7 +533,7 @@ static int bpq_device_event(struct notifier_block *this, if (!net_eq(dev_net(dev), &init_net)) return NOTIFY_DONE; - if (!dev_is_ethdev(dev)) + if (!dev_is_ethdev(dev) && !bpq_get_ax25_dev(dev)) return NOTIFY_DONE; switch (event) { diff --git a/drivers/net/ipa/ipa.h b/drivers/net/ipa/ipa.h index a44595575d06..5372db58b5bd 100644 --- a/drivers/net/ipa/ipa.h +++ b/drivers/net/ipa/ipa.h @@ -61,12 +61,13 @@ struct ipa_interrupt; * @zero_addr: DMA address of preallocated zero-filled memory * @zero_virt: Virtual address of preallocated zero-filled memory * @zero_size: Size (bytes) of preallocated zero-filled memory - * @endpoint_count: Number of endpoints represented by bit masks below - * @defined: Bit mask indicating endpoints defined in config data - * @available: Bit mask indicating endpoints hardware supports - * @filter_map: Bit mask indicating endpoints that support filtering - * @set_up: Bit mask indicating endpoints set up - * @enabled: Bit mask indicating endpoints enabled + * @endpoint_count: Number of defined bits in most bitmaps below + * @available_count: Number of defined bits in the available bitmap + * @defined: Bitmap of endpoints defined in config data + * @available: Bitmap of endpoints supported by hardware + * @filtered: Bitmap of endpoints that support filtering + * @set_up: Bitmap of endpoints that are set up for use + * @enabled: Bitmap of currently enabled endpoints * @modem_tx_count: Number of defined modem TX endoints * @endpoint: Array of endpoint information * @channel_map: Mapping of GSI channel to IPA endpoint @@ -117,13 +118,14 @@ struct ipa { void *zero_virt; size_t zero_size; - /* Bit masks indicating endpoint state */ + /* Bitmaps indicating endpoint state */ u32 endpoint_count; - u32 defined; /* Defined in configuration data */ - u32 available; /* Supported by hardware */ - u32 filter_map; - u32 set_up; - u32 enabled; + u32 available_count; + unsigned long *defined; /* Defined in configuration data */ + unsigned long *available; /* Supported by hardware */ + u64 filtered; /* Support filtering (AP and modem) */ + unsigned long *set_up; + unsigned long *enabled; u32 modem_tx_count; struct ipa_endpoint endpoint[IPA_ENDPOINT_MAX]; diff --git a/drivers/net/ipa/ipa_endpoint.c b/drivers/net/ipa/ipa_endpoint.c index 2a6184ea8f5c..136932464261 100644 --- a/drivers/net/ipa/ipa_endpoint.c +++ b/drivers/net/ipa/ipa_endpoint.c @@ -350,29 +350,32 @@ ipa_endpoint_program_delay(struct ipa_endpoint *endpoint, bool enable) static bool ipa_endpoint_aggr_active(struct ipa_endpoint *endpoint) { - u32 mask = BIT(endpoint->endpoint_id); + u32 endpoint_id = endpoint->endpoint_id; struct ipa *ipa = endpoint->ipa; + u32 unit = endpoint_id / 32; const struct ipa_reg *reg; u32 val; - WARN_ON(!(mask & ipa->available)); + WARN_ON(!test_bit(endpoint_id, ipa->available)); reg = ipa_reg(ipa, STATE_AGGR_ACTIVE); - val = ioread32(ipa->reg_virt + ipa_reg_offset(reg)); + val = ioread32(ipa->reg_virt + ipa_reg_n_offset(reg, unit)); - return !!(val & mask); + return !!(val & BIT(endpoint_id % 32)); } static void ipa_endpoint_force_close(struct ipa_endpoint *endpoint) { - u32 mask = BIT(endpoint->endpoint_id); + u32 endpoint_id = endpoint->endpoint_id; + u32 mask = BIT(endpoint_id % 32); struct ipa *ipa = endpoint->ipa; + u32 unit = endpoint_id / 32; const struct ipa_reg *reg; - WARN_ON(!(mask & ipa->available)); + WARN_ON(!test_bit(endpoint_id, ipa->available)); reg = ipa_reg(ipa, AGGR_FORCE_CLOSE); - iowrite32(mask, ipa->reg_virt + ipa_reg_offset(reg)); + iowrite32(mask, ipa->reg_virt + ipa_reg_n_offset(reg, unit)); } /** @@ -453,8 +456,8 @@ void ipa_endpoint_modem_pause_all(struct ipa *ipa, bool enable) /* Reset all modem endpoints to use the default exception endpoint */ int ipa_endpoint_modem_exception_reset_all(struct ipa *ipa) { - u32 defined = ipa->defined; struct gsi_trans *trans; + u32 endpoint_id; u32 count; /* We need one command per modem TX endpoint, plus the commands @@ -468,14 +471,11 @@ int ipa_endpoint_modem_exception_reset_all(struct ipa *ipa) return -EBUSY; } - while (defined) { - u32 endpoint_id = __ffs(defined); + for_each_set_bit(endpoint_id, ipa->defined, ipa->endpoint_count) { struct ipa_endpoint *endpoint; const struct ipa_reg *reg; u32 offset; - defined ^= BIT(endpoint_id); - /* We only reset modem TX endpoints */ endpoint = &ipa->endpoint[endpoint_id]; if (!(endpoint->ee_id == GSI_EE_MODEM && endpoint->toward_ipa)) @@ -1666,6 +1666,7 @@ static void ipa_endpoint_program(struct ipa_endpoint *endpoint) int ipa_endpoint_enable_one(struct ipa_endpoint *endpoint) { + u32 endpoint_id = endpoint->endpoint_id; struct ipa *ipa = endpoint->ipa; struct gsi *gsi = &ipa->gsi; int ret; @@ -1675,37 +1676,35 @@ int ipa_endpoint_enable_one(struct ipa_endpoint *endpoint) dev_err(&ipa->pdev->dev, "error %d starting %cX channel %u for endpoint %u\n", ret, endpoint->toward_ipa ? 'T' : 'R', - endpoint->channel_id, endpoint->endpoint_id); + endpoint->channel_id, endpoint_id); return ret; } if (!endpoint->toward_ipa) { - ipa_interrupt_suspend_enable(ipa->interrupt, - endpoint->endpoint_id); + ipa_interrupt_suspend_enable(ipa->interrupt, endpoint_id); ipa_endpoint_replenish_enable(endpoint); } - ipa->enabled |= BIT(endpoint->endpoint_id); + __set_bit(endpoint_id, ipa->enabled); return 0; } void ipa_endpoint_disable_one(struct ipa_endpoint *endpoint) { - u32 mask = BIT(endpoint->endpoint_id); + u32 endpoint_id = endpoint->endpoint_id; struct ipa *ipa = endpoint->ipa; struct gsi *gsi = &ipa->gsi; int ret; - if (!(ipa->enabled & mask)) + if (!test_bit(endpoint_id, ipa->enabled)) return; - ipa->enabled ^= mask; + __clear_bit(endpoint_id, endpoint->ipa->enabled); if (!endpoint->toward_ipa) { ipa_endpoint_replenish_disable(endpoint); - ipa_interrupt_suspend_disable(ipa->interrupt, - endpoint->endpoint_id); + ipa_interrupt_suspend_disable(ipa->interrupt, endpoint_id); } /* Note that if stop fails, the channel's state is not well-defined */ @@ -1713,7 +1712,7 @@ void ipa_endpoint_disable_one(struct ipa_endpoint *endpoint) if (ret) dev_err(&ipa->pdev->dev, "error %d attempting to stop endpoint %u\n", ret, - endpoint->endpoint_id); + endpoint_id); } void ipa_endpoint_suspend_one(struct ipa_endpoint *endpoint) @@ -1722,7 +1721,7 @@ void ipa_endpoint_suspend_one(struct ipa_endpoint *endpoint) struct gsi *gsi = &endpoint->ipa->gsi; int ret; - if (!(endpoint->ipa->enabled & BIT(endpoint->endpoint_id))) + if (!test_bit(endpoint->endpoint_id, endpoint->ipa->enabled)) return; if (!endpoint->toward_ipa) { @@ -1742,7 +1741,7 @@ void ipa_endpoint_resume_one(struct ipa_endpoint *endpoint) struct gsi *gsi = &endpoint->ipa->gsi; int ret; - if (!(endpoint->ipa->enabled & BIT(endpoint->endpoint_id))) + if (!test_bit(endpoint->endpoint_id, endpoint->ipa->enabled)) return; if (!endpoint->toward_ipa) @@ -1802,12 +1801,12 @@ static void ipa_endpoint_setup_one(struct ipa_endpoint *endpoint) ipa_endpoint_program(endpoint); - endpoint->ipa->set_up |= BIT(endpoint->endpoint_id); + __set_bit(endpoint->endpoint_id, endpoint->ipa->set_up); } static void ipa_endpoint_teardown_one(struct ipa_endpoint *endpoint) { - endpoint->ipa->set_up &= ~BIT(endpoint->endpoint_id); + __clear_bit(endpoint->endpoint_id, endpoint->ipa->set_up); if (!endpoint->toward_ipa) cancel_delayed_work_sync(&endpoint->replenish_work); @@ -1817,40 +1816,35 @@ static void ipa_endpoint_teardown_one(struct ipa_endpoint *endpoint) void ipa_endpoint_setup(struct ipa *ipa) { - u32 defined = ipa->defined; - - ipa->set_up = 0; - while (defined) { - u32 endpoint_id = __ffs(defined); - - defined ^= BIT(endpoint_id); + u32 endpoint_id; + for_each_set_bit(endpoint_id, ipa->defined, ipa->endpoint_count) ipa_endpoint_setup_one(&ipa->endpoint[endpoint_id]); - } } void ipa_endpoint_teardown(struct ipa *ipa) { - u32 set_up = ipa->set_up; - - while (set_up) { - u32 endpoint_id = __fls(set_up); - - set_up ^= BIT(endpoint_id); + u32 endpoint_id; + for_each_set_bit(endpoint_id, ipa->set_up, ipa->endpoint_count) ipa_endpoint_teardown_one(&ipa->endpoint[endpoint_id]); - } - ipa->set_up = 0; +} + +void ipa_endpoint_deconfig(struct ipa *ipa) +{ + ipa->available_count = 0; + bitmap_free(ipa->available); + ipa->available = NULL; } int ipa_endpoint_config(struct ipa *ipa) { struct device *dev = &ipa->pdev->dev; const struct ipa_reg *reg; + u32 endpoint_id; u32 tx_count; u32 rx_count; u32 rx_base; - u32 defined; u32 limit; u32 val; @@ -1865,7 +1859,13 @@ int ipa_endpoint_config(struct ipa *ipa) * assume the configuration is valid. */ if (ipa->version < IPA_VERSION_3_5) { - ipa->available = ~0; + ipa->available = bitmap_zalloc(IPA_ENDPOINT_MAX, GFP_KERNEL); + if (!ipa->available) + return -ENOMEM; + ipa->available_count = IPA_ENDPOINT_MAX; + + bitmap_set(ipa->available, 0, IPA_ENDPOINT_MAX); + return 0; } @@ -1887,26 +1887,29 @@ int ipa_endpoint_config(struct ipa *ipa) return -EINVAL; } + /* Allocate and initialize the available endpoint bitmap */ + ipa->available = bitmap_zalloc(limit, GFP_KERNEL); + if (!ipa->available) + return -ENOMEM; + ipa->available_count = limit; + /* Mark all supported RX and TX endpoints as available */ - ipa->available = GENMASK(limit - 1, rx_base) | GENMASK(tx_count - 1, 0); + bitmap_set(ipa->available, 0, tx_count); + bitmap_set(ipa->available, rx_base, rx_count); - defined = ipa->defined; - while (defined) { - u32 endpoint_id = __ffs(defined); + for_each_set_bit(endpoint_id, ipa->defined, ipa->endpoint_count) { struct ipa_endpoint *endpoint; - defined ^= BIT(endpoint_id); - if (endpoint_id >= limit) { dev_err(dev, "invalid endpoint id, %u > %u\n", endpoint_id, limit - 1); - return -EINVAL; + goto err_free_bitmap; } - if (!(BIT(endpoint_id) & ipa->available)) { + if (!test_bit(endpoint_id, ipa->available)) { dev_err(dev, "unavailable endpoint id %u\n", endpoint_id); - return -EINVAL; + goto err_free_bitmap; } /* Make sure it's pointing in the right direction */ @@ -1919,15 +1922,15 @@ int ipa_endpoint_config(struct ipa *ipa) } dev_err(dev, "endpoint id %u wrong direction\n", endpoint_id); - return -EINVAL; + goto err_free_bitmap; } return 0; -} -void ipa_endpoint_deconfig(struct ipa *ipa) -{ - ipa->available = 0; /* Nothing more to do */ +err_free_bitmap: + ipa_endpoint_deconfig(ipa); + + return -EINVAL; } static void ipa_endpoint_init_one(struct ipa *ipa, enum ipa_endpoint_name name, @@ -1948,48 +1951,64 @@ static void ipa_endpoint_init_one(struct ipa *ipa, enum ipa_endpoint_name name, endpoint->toward_ipa = data->toward_ipa; endpoint->config = data->endpoint.config; - ipa->defined |= BIT(endpoint->endpoint_id); + __set_bit(endpoint->endpoint_id, ipa->defined); } static void ipa_endpoint_exit_one(struct ipa_endpoint *endpoint) { - endpoint->ipa->defined &= ~BIT(endpoint->endpoint_id); + __clear_bit(endpoint->endpoint_id, endpoint->ipa->defined); memset(endpoint, 0, sizeof(*endpoint)); } void ipa_endpoint_exit(struct ipa *ipa) { - u32 defined = ipa->defined; - - while (defined) { - u32 endpoint_id = __fls(defined); + u32 endpoint_id; - defined ^= BIT(endpoint_id); + ipa->filtered = 0; + for_each_set_bit(endpoint_id, ipa->defined, ipa->endpoint_count) ipa_endpoint_exit_one(&ipa->endpoint[endpoint_id]); - } + + bitmap_free(ipa->enabled); + ipa->enabled = NULL; + bitmap_free(ipa->set_up); + ipa->set_up = NULL; + bitmap_free(ipa->defined); + ipa->defined = NULL; + memset(ipa->name_map, 0, sizeof(ipa->name_map)); memset(ipa->channel_map, 0, sizeof(ipa->channel_map)); } /* Returns a bitmask of endpoints that support filtering, or 0 on error */ -u32 ipa_endpoint_init(struct ipa *ipa, u32 count, +int ipa_endpoint_init(struct ipa *ipa, u32 count, const struct ipa_gsi_endpoint_data *data) { enum ipa_endpoint_name name; - u32 filter_map; + u32 filtered; BUILD_BUG_ON(!IPA_REPLENISH_BATCH); /* Number of endpoints is one more than the maximum ID */ ipa->endpoint_count = ipa_endpoint_max(ipa, count, data) + 1; if (!ipa->endpoint_count) - return 0; /* Error */ + return -EINVAL; + + /* Initialize endpoint state bitmaps */ + ipa->defined = bitmap_zalloc(ipa->endpoint_count, GFP_KERNEL); + if (!ipa->defined) + return -ENOMEM; + + ipa->set_up = bitmap_zalloc(ipa->endpoint_count, GFP_KERNEL); + if (!ipa->set_up) + goto err_free_defined; - ipa->defined = 0; + ipa->enabled = bitmap_zalloc(ipa->endpoint_count, GFP_KERNEL); + if (!ipa->enabled) + goto err_free_set_up; - filter_map = 0; + filtered = 0; for (name = 0; name < count; name++, data++) { if (ipa_gsi_endpoint_data_empty(data)) continue; /* Skip over empty slots */ @@ -1997,18 +2016,28 @@ u32 ipa_endpoint_init(struct ipa *ipa, u32 count, ipa_endpoint_init_one(ipa, name, data); if (data->endpoint.filter_support) - filter_map |= BIT(data->endpoint_id); + filtered |= BIT(data->endpoint_id); if (data->ee_id == GSI_EE_MODEM && data->toward_ipa) ipa->modem_tx_count++; } - if (!ipa_filter_map_valid(ipa, filter_map)) - goto err_endpoint_exit; + /* Make sure the set of filtered endpoints is valid */ + if (!ipa_filtered_valid(ipa, filtered)) { + ipa_endpoint_exit(ipa); - return filter_map; /* Non-zero bitmask */ + return -EINVAL; + } + + ipa->filtered = filtered; -err_endpoint_exit: - ipa_endpoint_exit(ipa); + return 0; - return 0; /* Error */ +err_free_set_up: + bitmap_free(ipa->set_up); + ipa->set_up = NULL; +err_free_defined: + bitmap_free(ipa->defined); + ipa->defined = NULL; + + return -ENOMEM; } diff --git a/drivers/net/ipa/ipa_endpoint.h b/drivers/net/ipa/ipa_endpoint.h index d8dfa24f5214..4a5c3bc549df 100644 --- a/drivers/net/ipa/ipa_endpoint.h +++ b/drivers/net/ipa/ipa_endpoint.h @@ -195,7 +195,7 @@ void ipa_endpoint_deconfig(struct ipa *ipa); void ipa_endpoint_default_route_set(struct ipa *ipa, u32 endpoint_id); void ipa_endpoint_default_route_clear(struct ipa *ipa); -u32 ipa_endpoint_init(struct ipa *ipa, u32 count, +int ipa_endpoint_init(struct ipa *ipa, u32 count, const struct ipa_gsi_endpoint_data *data); void ipa_endpoint_exit(struct ipa *ipa); diff --git a/drivers/net/ipa/ipa_interrupt.c b/drivers/net/ipa/ipa_interrupt.c index c269432f9c2e..a49f66efacb8 100644 --- a/drivers/net/ipa/ipa_interrupt.c +++ b/drivers/net/ipa/ipa_interrupt.c @@ -132,24 +132,28 @@ static void ipa_interrupt_suspend_control(struct ipa_interrupt *interrupt, u32 endpoint_id, bool enable) { struct ipa *ipa = interrupt->ipa; - u32 mask = BIT(endpoint_id); + u32 unit = endpoint_id / 32; const struct ipa_reg *reg; u32 offset; + u32 mask; u32 val; - WARN_ON(!(mask & ipa->available)); + WARN_ON(!test_bit(endpoint_id, ipa->available)); /* IPA version 3.0 does not support TX_SUSPEND interrupt control */ if (ipa->version == IPA_VERSION_3_0) return; reg = ipa_reg(ipa, IRQ_SUSPEND_EN); - offset = ipa_reg_offset(reg); + offset = ipa_reg_n_offset(reg, unit); val = ioread32(ipa->reg_virt + offset); + + mask = BIT(endpoint_id); if (enable) val |= mask; else val &= ~mask; + iowrite32(val, ipa->reg_virt + offset); } @@ -171,18 +175,24 @@ ipa_interrupt_suspend_disable(struct ipa_interrupt *interrupt, u32 endpoint_id) void ipa_interrupt_suspend_clear_all(struct ipa_interrupt *interrupt) { struct ipa *ipa = interrupt->ipa; - const struct ipa_reg *reg; - u32 val; + u32 unit_count; + u32 unit; - reg = ipa_reg(ipa, IRQ_SUSPEND_INFO); - val = ioread32(ipa->reg_virt + ipa_reg_offset(reg)); + unit_count = roundup(ipa->endpoint_count, 32); + for (unit = 0; unit < unit_count; unit++) { + const struct ipa_reg *reg; + u32 val; - /* SUSPEND interrupt status isn't cleared on IPA version 3.0 */ - if (ipa->version == IPA_VERSION_3_0) - return; + reg = ipa_reg(ipa, IRQ_SUSPEND_INFO); + val = ioread32(ipa->reg_virt + ipa_reg_n_offset(reg, unit)); - reg = ipa_reg(ipa, IRQ_SUSPEND_CLR); - iowrite32(val, ipa->reg_virt + ipa_reg_offset(reg)); + /* SUSPEND interrupt status isn't cleared on IPA version 3.0 */ + if (ipa->version == IPA_VERSION_3_0) + continue; + + reg = ipa_reg(ipa, IRQ_SUSPEND_CLR); + iowrite32(val, ipa->reg_virt + ipa_reg_n_offset(reg, unit)); + } } /* Simulate arrival of an IPA TX_SUSPEND interrupt */ diff --git a/drivers/net/ipa/ipa_main.c b/drivers/net/ipa/ipa_main.c index 8f6a6890697e..ebb6c9b311eb 100644 --- a/drivers/net/ipa/ipa_main.c +++ b/drivers/net/ipa/ipa_main.c @@ -788,12 +788,9 @@ static int ipa_probe(struct platform_device *pdev) goto err_mem_exit; /* Result is a non-zero mask of endpoints that support filtering */ - ipa->filter_map = ipa_endpoint_init(ipa, data->endpoint_count, - data->endpoint_data); - if (!ipa->filter_map) { - ret = -EINVAL; + ret = ipa_endpoint_init(ipa, data->endpoint_count, data->endpoint_data); + if (ret) goto err_gsi_exit; - } ret = ipa_table_init(ipa); if (ret) diff --git a/drivers/net/ipa/ipa_table.c b/drivers/net/ipa/ipa_table.c index cf3a3de239dc..cc9349a1d4df 100644 --- a/drivers/net/ipa/ipa_table.c +++ b/drivers/net/ipa/ipa_table.c @@ -161,20 +161,20 @@ ipa_table_mem(struct ipa *ipa, bool filter, bool hashed, bool ipv6) return ipa_mem_find(ipa, mem_id); } -bool ipa_filter_map_valid(struct ipa *ipa, u32 filter_map) +bool ipa_filtered_valid(struct ipa *ipa, u64 filtered) { struct device *dev = &ipa->pdev->dev; u32 count; - if (!filter_map) { + if (!filtered) { dev_err(dev, "at least one filtering endpoint is required\n"); return false; } - count = hweight32(filter_map); + count = hweight64(filtered); if (count > ipa->filter_count) { - dev_err(dev, "too many filtering endpoints (%u, max %u)\n", + dev_err(dev, "too many filtering endpoints (%u > %u)\n", count, ipa->filter_count); return false; @@ -200,16 +200,17 @@ static dma_addr_t ipa_table_addr(struct ipa *ipa, bool filter_mask, u16 count) } static void ipa_table_reset_add(struct gsi_trans *trans, bool filter, - u16 first, u16 count, enum ipa_mem_id mem_id) + bool hashed, bool ipv6, u16 first, u16 count) { struct ipa *ipa = container_of(trans->gsi, struct ipa, gsi); - const struct ipa_mem *mem = ipa_mem_find(ipa, mem_id); + const struct ipa_mem *mem; dma_addr_t addr; u32 offset; u16 size; - /* Nothing to do if the table memory region is empty */ - if (!mem->size) + /* Nothing to do if the memory region is doesn't exist or is empty */ + mem = ipa_table_mem(ipa, filter, hashed, ipv6); + if (!mem || !mem->size) return; if (filter) @@ -227,14 +228,13 @@ static void ipa_table_reset_add(struct gsi_trans *trans, bool filter, * for the IPv4 and IPv6 non-hashed and hashed filter tables. */ static int -ipa_filter_reset_table(struct ipa *ipa, enum ipa_mem_id mem_id, bool modem) +ipa_filter_reset_table(struct ipa *ipa, bool hashed, bool ipv6, bool modem) { - u32 ep_mask = ipa->filter_map; - u32 count = hweight32(ep_mask); + u64 ep_mask = ipa->filtered; struct gsi_trans *trans; enum gsi_ee_id ee_id; - trans = ipa_cmd_trans_alloc(ipa, count); + trans = ipa_cmd_trans_alloc(ipa, hweight64(ep_mask)); if (!trans) { dev_err(&ipa->pdev->dev, "no transaction for %s filter reset\n", @@ -253,7 +253,7 @@ ipa_filter_reset_table(struct ipa *ipa, enum ipa_mem_id mem_id, bool modem) if (endpoint->ee_id != ee_id) continue; - ipa_table_reset_add(trans, true, endpoint_id, 1, mem_id); + ipa_table_reset_add(trans, true, hashed, ipv6, endpoint_id, 1); } gsi_trans_commit_wait(trans); @@ -269,18 +269,18 @@ static int ipa_filter_reset(struct ipa *ipa, bool modem) { int ret; - ret = ipa_filter_reset_table(ipa, IPA_MEM_V4_FILTER, modem); + ret = ipa_filter_reset_table(ipa, false, false, modem); if (ret) return ret; - ret = ipa_filter_reset_table(ipa, IPA_MEM_V4_FILTER_HASHED, modem); + ret = ipa_filter_reset_table(ipa, true, false, modem); if (ret) return ret; - ret = ipa_filter_reset_table(ipa, IPA_MEM_V6_FILTER, modem); + ret = ipa_filter_reset_table(ipa, false, true, modem); if (ret) return ret; - ret = ipa_filter_reset_table(ipa, IPA_MEM_V6_FILTER_HASHED, modem); + ret = ipa_filter_reset_table(ipa, true, true, modem); return ret; } @@ -312,13 +312,11 @@ static int ipa_route_reset(struct ipa *ipa, bool modem) count = ipa->route_count - modem_route_count; } - ipa_table_reset_add(trans, false, first, count, IPA_MEM_V4_ROUTE); - ipa_table_reset_add(trans, false, first, count, - IPA_MEM_V4_ROUTE_HASHED); + ipa_table_reset_add(trans, false, false, false, first, count); + ipa_table_reset_add(trans, false, true, false, first, count); - ipa_table_reset_add(trans, false, first, count, IPA_MEM_V6_ROUTE); - ipa_table_reset_add(trans, false, first, count, - IPA_MEM_V6_ROUTE_HASHED); + ipa_table_reset_add(trans, false, false, true, first, count); + ipa_table_reset_add(trans, false, true, true, first, count); gsi_trans_commit_wait(trans); @@ -376,14 +374,12 @@ int ipa_table_hash_flush(struct ipa *ipa) return 0; } -static void ipa_table_init_add(struct gsi_trans *trans, bool filter, - enum ipa_cmd_opcode opcode, - enum ipa_mem_id mem_id, - enum ipa_mem_id hash_mem_id) +static void ipa_table_init_add(struct gsi_trans *trans, bool filter, bool ipv6) { struct ipa *ipa = container_of(trans->gsi, struct ipa, gsi); - const struct ipa_mem *hash_mem = ipa_mem_find(ipa, hash_mem_id); - const struct ipa_mem *mem = ipa_mem_find(ipa, mem_id); + const struct ipa_mem *hash_mem; + enum ipa_cmd_opcode opcode; + const struct ipa_mem *mem; dma_addr_t hash_addr; dma_addr_t addr; u32 zero_offset; @@ -393,6 +389,14 @@ static void ipa_table_init_add(struct gsi_trans *trans, bool filter, u16 count; u16 size; + opcode = filter ? ipv6 ? IPA_CMD_IP_V6_FILTER_INIT + : IPA_CMD_IP_V4_FILTER_INIT + : ipv6 ? IPA_CMD_IP_V6_ROUTING_INIT + : IPA_CMD_IP_V4_ROUTING_INIT; + + mem = ipa_table_mem(ipa, filter, false, ipv6); + hash_mem = ipa_table_mem(ipa, filter, true, ipv6); + /* Compute the number of table entries to initialize */ if (filter) { /* The number of filtering endpoints determines number of @@ -400,14 +404,14 @@ static void ipa_table_init_add(struct gsi_trans *trans, bool filter, * to hold the bitmap itself. The size of the hashed filter * table is either the same as the non-hashed one, or zero. */ - count = 1 + hweight32(ipa->filter_map); - hash_count = hash_mem->size ? count : 0; + count = 1 + hweight64(ipa->filtered); + hash_count = hash_mem && hash_mem->size ? count : 0; } else { /* The size of a route table region determines the number * of entries it has. */ count = mem->size / sizeof(__le64); - hash_count = hash_mem->size / sizeof(__le64); + hash_count = hash_mem && hash_mem->size / sizeof(__le64); } size = count * sizeof(__le64); hash_size = hash_count * sizeof(__le64); @@ -458,17 +462,10 @@ int ipa_table_setup(struct ipa *ipa) return -EBUSY; } - ipa_table_init_add(trans, false, IPA_CMD_IP_V4_ROUTING_INIT, - IPA_MEM_V4_ROUTE, IPA_MEM_V4_ROUTE_HASHED); - - ipa_table_init_add(trans, false, IPA_CMD_IP_V6_ROUTING_INIT, - IPA_MEM_V6_ROUTE, IPA_MEM_V6_ROUTE_HASHED); - - ipa_table_init_add(trans, true, IPA_CMD_IP_V4_FILTER_INIT, - IPA_MEM_V4_FILTER, IPA_MEM_V4_FILTER_HASHED); - - ipa_table_init_add(trans, true, IPA_CMD_IP_V6_FILTER_INIT, - IPA_MEM_V6_FILTER, IPA_MEM_V6_FILTER_HASHED); + ipa_table_init_add(trans, false, false); + ipa_table_init_add(trans, false, true); + ipa_table_init_add(trans, true, false); + ipa_table_init_add(trans, true, true); gsi_trans_commit_wait(trans); @@ -505,7 +502,7 @@ static void ipa_filter_tuple_zero(struct ipa_endpoint *endpoint) static void ipa_filter_config(struct ipa *ipa, bool modem) { enum gsi_ee_id ee_id = modem ? GSI_EE_MODEM : GSI_EE_AP; - u32 ep_mask = ipa->filter_map; + u64 ep_mask = ipa->filtered; if (!ipa_table_hash_support(ipa)) return; @@ -617,7 +614,7 @@ bool ipa_table_mem_valid(struct ipa *ipa, bool filter) /* Filter tables must able to hold the endpoint bitmap plus * an entry for each endpoint that supports filtering */ - if (count < 1 + hweight32(ipa->filter_map)) + if (count < 1 + hweight64(ipa->filtered)) return false; } else { /* Routing tables must be able to hold all modem entries, @@ -722,9 +719,9 @@ int ipa_table_init(struct ipa *ipa) * that option, so there's no shifting required. */ if (ipa->version < IPA_VERSION_5_0) - *virt++ = cpu_to_le64((u64)ipa->filter_map << 1); + *virt++ = cpu_to_le64(ipa->filtered << 1); else - *virt++ = cpu_to_le64((u64)ipa->filter_map); + *virt++ = cpu_to_le64(ipa->filtered); /* All the rest contain the DMA address of the zero rule */ le_addr = cpu_to_le64(addr); diff --git a/drivers/net/ipa/ipa_table.h b/drivers/net/ipa/ipa_table.h index 8a4dcd7df4c0..7cc951904bb4 100644 --- a/drivers/net/ipa/ipa_table.h +++ b/drivers/net/ipa/ipa_table.h @@ -11,13 +11,13 @@ struct ipa; /** - * ipa_filter_map_valid() - Validate a filter table endpoint bitmap + * ipa_filtered_valid() - Validate a filter table endpoint bitmap * @ipa: IPA pointer - * @filter_mask: Filter table endpoint bitmap to check + * @filtered: Filter table endpoint bitmap to check * * Return: true if all regions are valid, false otherwise */ -bool ipa_filter_map_valid(struct ipa *ipa, u32 filter_mask); +bool ipa_filtered_valid(struct ipa *ipa, u64 filtered); /** * ipa_table_hash_support() - Return true if hashed tables are supported diff --git a/drivers/net/ipa/reg/ipa_reg-v3.1.c b/drivers/net/ipa/reg/ipa_reg-v3.1.c index 0d002c3c38a2..677ece3bce9e 100644 --- a/drivers/net/ipa/reg/ipa_reg-v3.1.c +++ b/drivers/net/ipa/reg/ipa_reg-v3.1.c @@ -103,7 +103,7 @@ static const u32 ipa_reg_filt_rout_hash_flush_fmask[] = { IPA_REG_FIELDS(FILT_ROUT_HASH_FLUSH, filt_rout_hash_flush, 0x0000090); /* Valid bits defined by ipa->available */ -IPA_REG(STATE_AGGR_ACTIVE, state_aggr_active, 0x0000010c); +IPA_REG_STRIDE(STATE_AGGR_ACTIVE, state_aggr_active, 0x0000010c, 0x0004); IPA_REG(IPA_BCR, ipa_bcr, 0x000001d0); @@ -116,7 +116,7 @@ static const u32 ipa_reg_local_pkt_proc_cntxt_fmask[] = { IPA_REG_FIELDS(LOCAL_PKT_PROC_CNTXT, local_pkt_proc_cntxt, 0x000001e8); /* Valid bits defined by ipa->available */ -IPA_REG(AGGR_FORCE_CLOSE, aggr_force_close, 0x000001ec); +IPA_REG_STRIDE(AGGR_FORCE_CLOSE, aggr_force_close, 0x000001ec, 0x0004); static const u32 ipa_reg_counter_cfg_fmask[] = { [EOT_COAL_GRANULARITY] = GENMASK(3, 0), @@ -386,13 +386,16 @@ static const u32 ipa_reg_ipa_irq_uc_fmask[] = { IPA_REG_FIELDS(IPA_IRQ_UC, ipa_irq_uc, 0x0000301c + 0x1000 * GSI_EE_AP); /* Valid bits defined by ipa->available */ -IPA_REG(IRQ_SUSPEND_INFO, irq_suspend_info, 0x00003030 + 0x1000 * GSI_EE_AP); +IPA_REG_STRIDE(IRQ_SUSPEND_INFO, irq_suspend_info, + 0x00003030 + 0x1000 * GSI_EE_AP, 0x0004); /* Valid bits defined by ipa->available */ -IPA_REG(IRQ_SUSPEND_EN, irq_suspend_en, 0x00003034 + 0x1000 * GSI_EE_AP); +IPA_REG_STRIDE(IRQ_SUSPEND_EN, irq_suspend_en, + 0x00003034 + 0x1000 * GSI_EE_AP, 0x0004); /* Valid bits defined by ipa->available */ -IPA_REG(IRQ_SUSPEND_CLR, irq_suspend_clr, 0x00003038 + 0x1000 * GSI_EE_AP); +IPA_REG_STRIDE(IRQ_SUSPEND_CLR, irq_suspend_clr, + 0x00003038 + 0x1000 * GSI_EE_AP, 0x0004); static const struct ipa_reg *ipa_reg_array[] = { [COMP_CFG] = &ipa_reg_comp_cfg, diff --git a/drivers/net/ipa/reg/ipa_reg-v3.5.1.c b/drivers/net/ipa/reg/ipa_reg-v3.5.1.c index 6e2f939b18f1..b9c6a50de243 100644 --- a/drivers/net/ipa/reg/ipa_reg-v3.5.1.c +++ b/drivers/net/ipa/reg/ipa_reg-v3.5.1.c @@ -108,7 +108,7 @@ static const u32 ipa_reg_filt_rout_hash_flush_fmask[] = { IPA_REG_FIELDS(FILT_ROUT_HASH_FLUSH, filt_rout_hash_flush, 0x0000090); /* Valid bits defined by ipa->available */ -IPA_REG(STATE_AGGR_ACTIVE, state_aggr_active, 0x0000010c); +IPA_REG_STRIDE(STATE_AGGR_ACTIVE, state_aggr_active, 0x0000010c, 0x0004); IPA_REG(IPA_BCR, ipa_bcr, 0x000001d0); @@ -121,7 +121,7 @@ static const u32 ipa_reg_local_pkt_proc_cntxt_fmask[] = { IPA_REG_FIELDS(LOCAL_PKT_PROC_CNTXT, local_pkt_proc_cntxt, 0x000001e8); /* Valid bits defined by ipa->available */ -IPA_REG(AGGR_FORCE_CLOSE, aggr_force_close, 0x000001ec); +IPA_REG_STRIDE(AGGR_FORCE_CLOSE, aggr_force_close, 0x000001ec, 0x0004); static const u32 ipa_reg_counter_cfg_fmask[] = { /* Bits 0-3 reserved */ @@ -397,13 +397,16 @@ static const u32 ipa_reg_ipa_irq_uc_fmask[] = { IPA_REG_FIELDS(IPA_IRQ_UC, ipa_irq_uc, 0x0000301c + 0x1000 * GSI_EE_AP); /* Valid bits defined by ipa->available */ -IPA_REG(IRQ_SUSPEND_INFO, irq_suspend_info, 0x00003030 + 0x1000 * GSI_EE_AP); +IPA_REG_STRIDE(IRQ_SUSPEND_INFO, irq_suspend_info, + 0x00003030 + 0x1000 * GSI_EE_AP, 0x0004); /* Valid bits defined by ipa->available */ -IPA_REG(IRQ_SUSPEND_EN, irq_suspend_en, 0x00003034 + 0x1000 * GSI_EE_AP); +IPA_REG_STRIDE(IRQ_SUSPEND_EN, irq_suspend_en, + 0x00003034 + 0x1000 * GSI_EE_AP, 0x0004); /* Valid bits defined by ipa->available */ -IPA_REG(IRQ_SUSPEND_CLR, irq_suspend_clr, 0x00003038 + 0x1000 * GSI_EE_AP); +IPA_REG_STRIDE(IRQ_SUSPEND_CLR, irq_suspend_clr, + 0x00003038 + 0x1000 * GSI_EE_AP, 0x0004); static const struct ipa_reg *ipa_reg_array[] = { [COMP_CFG] = &ipa_reg_comp_cfg, diff --git a/drivers/net/ipa/reg/ipa_reg-v4.11.c b/drivers/net/ipa/reg/ipa_reg-v4.11.c index 8fd36569bb9f..9a315130530d 100644 --- a/drivers/net/ipa/reg/ipa_reg-v4.11.c +++ b/drivers/net/ipa/reg/ipa_reg-v4.11.c @@ -140,7 +140,7 @@ static const u32 ipa_reg_filt_rout_hash_flush_fmask[] = { IPA_REG_FIELDS(FILT_ROUT_HASH_FLUSH, filt_rout_hash_flush, 0x000014c); /* Valid bits defined by ipa->available */ -IPA_REG(STATE_AGGR_ACTIVE, state_aggr_active, 0x000000b4); +IPA_REG_STRIDE(STATE_AGGR_ACTIVE, state_aggr_active, 0x000000b4, 0x0004); static const u32 ipa_reg_local_pkt_proc_cntxt_fmask[] = { [IPA_BASE_ADDR] = GENMASK(17, 0), @@ -151,7 +151,7 @@ static const u32 ipa_reg_local_pkt_proc_cntxt_fmask[] = { IPA_REG_FIELDS(LOCAL_PKT_PROC_CNTXT, local_pkt_proc_cntxt, 0x000001e8); /* Valid bits defined by ipa->available */ -IPA_REG(AGGR_FORCE_CLOSE, aggr_force_close, 0x000001ec); +IPA_REG_STRIDE(AGGR_FORCE_CLOSE, aggr_force_close, 0x000001ec, 0x0004); static const u32 ipa_reg_ipa_tx_cfg_fmask[] = { /* Bits 0-1 reserved */ @@ -453,13 +453,16 @@ static const u32 ipa_reg_ipa_irq_uc_fmask[] = { IPA_REG_FIELDS(IPA_IRQ_UC, ipa_irq_uc, 0x0000401c + 0x1000 * GSI_EE_AP); /* Valid bits defined by ipa->available */ -IPA_REG(IRQ_SUSPEND_INFO, irq_suspend_info, 0x00004030 + 0x1000 * GSI_EE_AP); +IPA_REG_STRIDE(IRQ_SUSPEND_INFO, irq_suspend_info, + 0x00004030 + 0x1000 * GSI_EE_AP, 0x0004); /* Valid bits defined by ipa->available */ -IPA_REG(IRQ_SUSPEND_EN, irq_suspend_en, 0x00004034 + 0x1000 * GSI_EE_AP); +IPA_REG_STRIDE(IRQ_SUSPEND_EN, irq_suspend_en, + 0x00004034 + 0x1000 * GSI_EE_AP, 0x0004); /* Valid bits defined by ipa->available */ -IPA_REG(IRQ_SUSPEND_CLR, irq_suspend_clr, 0x00004038 + 0x1000 * GSI_EE_AP); +IPA_REG_STRIDE(IRQ_SUSPEND_CLR, irq_suspend_clr, + 0x00004038 + 0x1000 * GSI_EE_AP, 0x0004); static const struct ipa_reg *ipa_reg_array[] = { [COMP_CFG] = &ipa_reg_comp_cfg, diff --git a/drivers/net/ipa/reg/ipa_reg-v4.2.c b/drivers/net/ipa/reg/ipa_reg-v4.2.c index f8e78e1907c8..7a95149f8ec7 100644 --- a/drivers/net/ipa/reg/ipa_reg-v4.2.c +++ b/drivers/net/ipa/reg/ipa_reg-v4.2.c @@ -132,7 +132,7 @@ static const u32 ipa_reg_filt_rout_hash_flush_fmask[] = { IPA_REG_FIELDS(FILT_ROUT_HASH_FLUSH, filt_rout_hash_flush, 0x000014c); /* Valid bits defined by ipa->available */ -IPA_REG(STATE_AGGR_ACTIVE, state_aggr_active, 0x000000b4); +IPA_REG_STRIDE(STATE_AGGR_ACTIVE, state_aggr_active, 0x000000b4, 0x0004); IPA_REG(IPA_BCR, ipa_bcr, 0x000001d0); @@ -145,7 +145,7 @@ static const u32 ipa_reg_local_pkt_proc_cntxt_fmask[] = { IPA_REG_FIELDS(LOCAL_PKT_PROC_CNTXT, local_pkt_proc_cntxt, 0x000001e8); /* Valid bits defined by ipa->available */ -IPA_REG(AGGR_FORCE_CLOSE, aggr_force_close, 0x000001ec); +IPA_REG_STRIDE(AGGR_FORCE_CLOSE, aggr_force_close, 0x000001ec, 0x0004); static const u32 ipa_reg_counter_cfg_fmask[] = { /* Bits 0-3 reserved */ @@ -399,13 +399,16 @@ static const u32 ipa_reg_ipa_irq_uc_fmask[] = { IPA_REG_FIELDS(IPA_IRQ_UC, ipa_irq_uc, 0x0000301c + 0x1000 * GSI_EE_AP); /* Valid bits defined by ipa->available */ -IPA_REG(IRQ_SUSPEND_INFO, irq_suspend_info, 0x00003030 + 0x1000 * GSI_EE_AP); +IPA_REG_STRIDE(IRQ_SUSPEND_INFO, irq_suspend_info, + 0x00003030 + 0x1000 * GSI_EE_AP, 0x0004); /* Valid bits defined by ipa->available */ -IPA_REG(IRQ_SUSPEND_EN, irq_suspend_en, 0x00003034 + 0x1000 * GSI_EE_AP); +IPA_REG_STRIDE(IRQ_SUSPEND_EN, irq_suspend_en, + 0x00003034 + 0x1000 * GSI_EE_AP, 0x0004); /* Valid bits defined by ipa->available */ -IPA_REG(IRQ_SUSPEND_CLR, irq_suspend_clr, 0x00003038 + 0x1000 * GSI_EE_AP); +IPA_REG_STRIDE(IRQ_SUSPEND_CLR, irq_suspend_clr, + 0x00003038 + 0x1000 * GSI_EE_AP, 0x0004); static const struct ipa_reg *ipa_reg_array[] = { [COMP_CFG] = &ipa_reg_comp_cfg, diff --git a/drivers/net/ipa/reg/ipa_reg-v4.5.c b/drivers/net/ipa/reg/ipa_reg-v4.5.c index d32b805abb11..587eb8d4e00f 100644 --- a/drivers/net/ipa/reg/ipa_reg-v4.5.c +++ b/drivers/net/ipa/reg/ipa_reg-v4.5.c @@ -134,7 +134,7 @@ static const u32 ipa_reg_filt_rout_hash_flush_fmask[] = { IPA_REG_FIELDS(FILT_ROUT_HASH_FLUSH, filt_rout_hash_flush, 0x000014c); /* Valid bits defined by ipa->available */ -IPA_REG(STATE_AGGR_ACTIVE, state_aggr_active, 0x000000b4); +IPA_REG_STRIDE(STATE_AGGR_ACTIVE, state_aggr_active, 0x000000b4, 0x0004); static const u32 ipa_reg_local_pkt_proc_cntxt_fmask[] = { [IPA_BASE_ADDR] = GENMASK(17, 0), @@ -145,7 +145,7 @@ static const u32 ipa_reg_local_pkt_proc_cntxt_fmask[] = { IPA_REG_FIELDS(LOCAL_PKT_PROC_CNTXT, local_pkt_proc_cntxt, 0x000001e8); /* Valid bits defined by ipa->available */ -IPA_REG(AGGR_FORCE_CLOSE, aggr_force_close, 0x000001ec); +IPA_REG_STRIDE(AGGR_FORCE_CLOSE, aggr_force_close, 0x000001ec, 0x0004); static const u32 ipa_reg_ipa_tx_cfg_fmask[] = { /* Bits 0-1 reserved */ @@ -472,13 +472,16 @@ static const u32 ipa_reg_ipa_irq_uc_fmask[] = { IPA_REG_FIELDS(IPA_IRQ_UC, ipa_irq_uc, 0x0000301c + 0x1000 * GSI_EE_AP); /* Valid bits defined by ipa->available */ -IPA_REG(IRQ_SUSPEND_INFO, irq_suspend_info, 0x00003030 + 0x1000 * GSI_EE_AP); +IPA_REG_STRIDE(IRQ_SUSPEND_INFO, irq_suspend_info, + 0x00003030 + 0x1000 * GSI_EE_AP, 0x0004); /* Valid bits defined by ipa->available */ -IPA_REG(IRQ_SUSPEND_EN, irq_suspend_en, 0x00003034 + 0x1000 * GSI_EE_AP); +IPA_REG_STRIDE(IRQ_SUSPEND_EN, irq_suspend_en, + 0x00003034 + 0x1000 * GSI_EE_AP, 0x0004); /* Valid bits defined by ipa->available */ -IPA_REG(IRQ_SUSPEND_CLR, irq_suspend_clr, 0x00003038 + 0x1000 * GSI_EE_AP); +IPA_REG_STRIDE(IRQ_SUSPEND_CLR, irq_suspend_clr, + 0x00003038 + 0x1000 * GSI_EE_AP, 0x0004); static const struct ipa_reg *ipa_reg_array[] = { [COMP_CFG] = &ipa_reg_comp_cfg, diff --git a/drivers/net/ipa/reg/ipa_reg-v4.9.c b/drivers/net/ipa/reg/ipa_reg-v4.9.c index eabbc5451937..1f67a03fe599 100644 --- a/drivers/net/ipa/reg/ipa_reg-v4.9.c +++ b/drivers/net/ipa/reg/ipa_reg-v4.9.c @@ -139,7 +139,7 @@ static const u32 ipa_reg_filt_rout_hash_flush_fmask[] = { IPA_REG_FIELDS(FILT_ROUT_HASH_FLUSH, filt_rout_hash_flush, 0x000014c); /* Valid bits defined by ipa->available */ -IPA_REG(STATE_AGGR_ACTIVE, state_aggr_active, 0x000000b4); +IPA_REG_STRIDE(STATE_AGGR_ACTIVE, state_aggr_active, 0x000000b4, 0x0004); static const u32 ipa_reg_local_pkt_proc_cntxt_fmask[] = { [IPA_BASE_ADDR] = GENMASK(17, 0), @@ -150,7 +150,7 @@ static const u32 ipa_reg_local_pkt_proc_cntxt_fmask[] = { IPA_REG_FIELDS(LOCAL_PKT_PROC_CNTXT, local_pkt_proc_cntxt, 0x000001e8); /* Valid bits defined by ipa->available */ -IPA_REG(AGGR_FORCE_CLOSE, aggr_force_close, 0x000001ec); +IPA_REG_STRIDE(AGGR_FORCE_CLOSE, aggr_force_close, 0x000001ec, 0x0004); static const u32 ipa_reg_ipa_tx_cfg_fmask[] = { /* Bits 0-1 reserved */ @@ -450,13 +450,16 @@ static const u32 ipa_reg_ipa_irq_uc_fmask[] = { IPA_REG_FIELDS(IPA_IRQ_UC, ipa_irq_uc, 0x0000401c + 0x1000 * GSI_EE_AP); /* Valid bits defined by ipa->available */ -IPA_REG(IRQ_SUSPEND_INFO, irq_suspend_info, 0x00004030 + 0x1000 * GSI_EE_AP); +IPA_REG_STRIDE(IRQ_SUSPEND_INFO, irq_suspend_info, + 0x00004030 + 0x1000 * GSI_EE_AP, 0x0004); /* Valid bits defined by ipa->available */ -IPA_REG(IRQ_SUSPEND_EN, irq_suspend_en, 0x00004034 + 0x1000 * GSI_EE_AP); +IPA_REG_STRIDE(IRQ_SUSPEND_EN, irq_suspend_en, + 0x00004034 + 0x1000 * GSI_EE_AP, 0x0004); /* Valid bits defined by ipa->available */ -IPA_REG(IRQ_SUSPEND_CLR, irq_suspend_clr, 0x00004038 + 0x1000 * GSI_EE_AP); +IPA_REG_STRIDE(IRQ_SUSPEND_CLR, irq_suspend_clr, + 0x00004038 + 0x1000 * GSI_EE_AP, 0x0004); static const struct ipa_reg *ipa_reg_array[] = { [COMP_CFG] = &ipa_reg_comp_cfg, diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index ad38fadd0d89..a7b46219bab7 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -1413,7 +1413,8 @@ static struct macsec_rx_sc *del_rx_sc(struct macsec_secy *secy, sci_t sci) return NULL; } -static struct macsec_rx_sc *create_rx_sc(struct net_device *dev, sci_t sci) +static struct macsec_rx_sc *create_rx_sc(struct net_device *dev, sci_t sci, + bool active) { struct macsec_rx_sc *rx_sc; struct macsec_dev *macsec; @@ -1437,7 +1438,7 @@ static struct macsec_rx_sc *create_rx_sc(struct net_device *dev, sci_t sci) } rx_sc->sci = sci; - rx_sc->active = true; + rx_sc->active = active; refcount_set(&rx_sc->refcnt, 1); secy = &macsec_priv(dev)->secy; @@ -1838,6 +1839,7 @@ static int macsec_add_rxsa(struct sk_buff *skb, struct genl_info *info) secy->key_len); err = macsec_offload(ops->mdo_add_rxsa, &ctx); + memzero_explicit(ctx.sa.key, secy->key_len); if (err) goto cleanup; } @@ -1876,7 +1878,7 @@ static int macsec_add_rxsc(struct sk_buff *skb, struct genl_info *info) struct macsec_rx_sc *rx_sc; struct nlattr *tb_rxsc[MACSEC_RXSC_ATTR_MAX + 1]; struct macsec_secy *secy; - bool was_active; + bool active = true; int ret; if (!attrs[MACSEC_ATTR_IFINDEX]) @@ -1898,16 +1900,15 @@ static int macsec_add_rxsc(struct sk_buff *skb, struct genl_info *info) secy = &macsec_priv(dev)->secy; sci = nla_get_sci(tb_rxsc[MACSEC_RXSC_ATTR_SCI]); - rx_sc = create_rx_sc(dev, sci); + if (tb_rxsc[MACSEC_RXSC_ATTR_ACTIVE]) + active = nla_get_u8(tb_rxsc[MACSEC_RXSC_ATTR_ACTIVE]); + + rx_sc = create_rx_sc(dev, sci, active); if (IS_ERR(rx_sc)) { rtnl_unlock(); return PTR_ERR(rx_sc); } - was_active = rx_sc->active; - if (tb_rxsc[MACSEC_RXSC_ATTR_ACTIVE]) - rx_sc->active = !!nla_get_u8(tb_rxsc[MACSEC_RXSC_ATTR_ACTIVE]); - if (macsec_is_offloaded(netdev_priv(dev))) { const struct macsec_ops *ops; struct macsec_context ctx; @@ -1931,7 +1932,8 @@ static int macsec_add_rxsc(struct sk_buff *skb, struct genl_info *info) return 0; cleanup: - rx_sc->active = was_active; + del_rx_sc(secy, sci); + free_rx_sc(rx_sc); rtnl_unlock(); return ret; } @@ -2080,6 +2082,7 @@ static int macsec_add_txsa(struct sk_buff *skb, struct genl_info *info) secy->key_len); err = macsec_offload(ops->mdo_add_txsa, &ctx); + memzero_explicit(ctx.sa.key, secy->key_len); if (err) goto cleanup; } @@ -2570,7 +2573,7 @@ static bool macsec_is_configured(struct macsec_dev *macsec) struct macsec_tx_sc *tx_sc = &secy->tx_sc; int i; - if (secy->n_rx_sc > 0) + if (secy->rx_sc) return true; for (i = 0; i < MACSEC_NUM_AN; i++) @@ -2654,11 +2657,6 @@ static int macsec_upd_offload(struct sk_buff *skb, struct genl_info *info) if (ret) goto rollback; - /* Force features update, since they are different for SW MACSec and - * HW offloading cases. - */ - netdev_update_features(dev); - rtnl_unlock(); return 0; @@ -3432,16 +3430,9 @@ static netdev_tx_t macsec_start_xmit(struct sk_buff *skb, return ret; } -#define SW_MACSEC_FEATURES \ +#define MACSEC_FEATURES \ (NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST) -/* If h/w offloading is enabled, use real device features save for - * VLAN_FEATURES - they require additional ops - * HW_MACSEC - no reason to report it - */ -#define REAL_DEV_FEATURES(dev) \ - ((dev)->features & ~(NETIF_F_VLAN_FEATURES | NETIF_F_HW_MACSEC)) - static int macsec_dev_init(struct net_device *dev) { struct macsec_dev *macsec = macsec_priv(dev); @@ -3458,12 +3449,8 @@ static int macsec_dev_init(struct net_device *dev) return err; } - if (macsec_is_offloaded(macsec)) { - dev->features = REAL_DEV_FEATURES(real_dev); - } else { - dev->features = real_dev->features & SW_MACSEC_FEATURES; - dev->features |= NETIF_F_LLTX | NETIF_F_GSO_SOFTWARE; - } + dev->features = real_dev->features & MACSEC_FEATURES; + dev->features |= NETIF_F_LLTX | NETIF_F_GSO_SOFTWARE; dev->needed_headroom = real_dev->needed_headroom + MACSEC_NEEDED_HEADROOM; @@ -3495,10 +3482,7 @@ static netdev_features_t macsec_fix_features(struct net_device *dev, struct macsec_dev *macsec = macsec_priv(dev); struct net_device *real_dev = macsec->real_dev; - if (macsec_is_offloaded(macsec)) - return REAL_DEV_FEATURES(real_dev); - - features &= (real_dev->features & SW_MACSEC_FEATURES) | + features &= (real_dev->features & MACSEC_FEATURES) | NETIF_F_GSO_SOFTWARE | NETIF_F_SOFT_FEATURES; features |= NETIF_F_LLTX; diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index c58fea63be7d..28f9f917ff54 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -1533,8 +1533,10 @@ destroy_macvlan_port: /* the macvlan port may be freed by macvlan_uninit when fail to register. * so we destroy the macvlan port only when it's valid. */ - if (create && macvlan_port_get_rtnl(lowerdev)) + if (create && macvlan_port_get_rtnl(lowerdev)) { + macvlan_flush_sources(port, vlan); macvlan_port_destroy(port->dev); + } return err; } EXPORT_SYMBOL_GPL(macvlan_common_newlink); diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index a7880c7ce94c..387c05953a8b 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -1406,7 +1406,6 @@ static int __nsim_dev_port_add(struct nsim_dev *nsim_dev, enum nsim_dev_port_typ goto err_nsim_destroy; } - devlink_port_type_eth_set(devlink_port, nsim_dev_port->ns->netdev); list_add(&nsim_dev_port->list, &nsim_dev->port_list); return 0; @@ -1429,7 +1428,6 @@ static void __nsim_dev_port_del(struct nsim_dev_port *nsim_dev_port) list_del(&nsim_dev_port->list); if (nsim_dev_port_is_vf(nsim_dev_port)) devl_rate_leaf_destroy(&nsim_dev_port->devlink_port); - devlink_port_type_clear(devlink_port); nsim_destroy(nsim_dev_port->ns); nsim_dev_port_debugfs_exit(nsim_dev_port); devl_port_unregister(devlink_port); diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c index e470e3398abc..6db6a75ff9b9 100644 --- a/drivers/net/netdevsim/netdev.c +++ b/drivers/net/netdevsim/netdev.c @@ -238,13 +238,6 @@ nsim_set_features(struct net_device *dev, netdev_features_t features) return 0; } -static struct devlink_port *nsim_get_devlink_port(struct net_device *dev) -{ - struct netdevsim *ns = netdev_priv(dev); - - return &ns->nsim_dev_port->devlink_port; -} - static const struct net_device_ops nsim_netdev_ops = { .ndo_start_xmit = nsim_start_xmit, .ndo_set_rx_mode = nsim_set_rx_mode, @@ -263,7 +256,6 @@ static const struct net_device_ops nsim_netdev_ops = { .ndo_setup_tc = nsim_setup_tc, .ndo_set_features = nsim_set_features, .ndo_bpf = nsim_bpf, - .ndo_get_devlink_port = nsim_get_devlink_port, }; static const struct net_device_ops nsim_vf_netdev_ops = { @@ -275,7 +267,6 @@ static const struct net_device_ops nsim_vf_netdev_ops = { .ndo_get_stats64 = nsim_get_stats64, .ndo_setup_tc = nsim_setup_tc, .ndo_set_features = nsim_set_features, - .ndo_get_devlink_port = nsim_get_devlink_port, }; static void nsim_setup(struct net_device *dev) @@ -360,6 +351,7 @@ nsim_create(struct nsim_dev *nsim_dev, struct nsim_dev_port *nsim_dev_port) ns->nsim_dev_port = nsim_dev_port; ns->nsim_bus_dev = nsim_dev->nsim_bus_dev; SET_NETDEV_DEV(dev, &ns->nsim_bus_dev->dev); + SET_NETDEV_DEVLINK_PORT(dev, &nsim_dev_port->devlink_port); nsim_ethtool_init(ns); if (nsim_dev_port_is_pf(nsim_dev_port)) err = nsim_init_netdevsim(ns); diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c index 70f88eae2a9e..f6a038a1d51e 100644 --- a/drivers/net/pcs/pcs-xpcs.c +++ b/drivers/net/pcs/pcs-xpcs.c @@ -188,18 +188,12 @@ static bool __xpcs_linkmode_supported(const struct xpcs_compat *compat, int xpcs_read(struct dw_xpcs *xpcs, int dev, u32 reg) { - struct mii_bus *bus = xpcs->mdiodev->bus; - int addr = xpcs->mdiodev->addr; - - return mdiobus_c45_read(bus, addr, dev, reg); + return mdiodev_c45_read(xpcs->mdiodev, dev, reg); } int xpcs_write(struct dw_xpcs *xpcs, int dev, u32 reg, u16 val) { - struct mii_bus *bus = xpcs->mdiodev->bus; - int addr = xpcs->mdiodev->addr; - - return mdiobus_c45_write(bus, addr, dev, reg, val); + return mdiodev_c45_write(xpcs->mdiodev, dev, reg, val); } static int xpcs_modify_changed(struct dw_xpcs *xpcs, int dev, u32 reg, diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c index 417527f8bbf5..29e95b34781f 100644 --- a/drivers/net/phy/dp83867.c +++ b/drivers/net/phy/dp83867.c @@ -933,6 +933,12 @@ static void dp83867_link_change_notify(struct phy_device *phydev) } } +static int dp83867_loopback(struct phy_device *phydev, bool enable) +{ + return phy_modify(phydev, MII_BMCR, BMCR_LOOPBACK, + enable ? BMCR_LOOPBACK : 0); +} + static struct phy_driver dp83867_driver[] = { { .phy_id = DP83867_PHY_ID, @@ -959,6 +965,7 @@ static struct phy_driver dp83867_driver[] = { .resume = genphy_resume, .link_change_notify = dp83867_link_change_notify, + .set_loopback = dp83867_loopback, }, }; module_phy_driver(dp83867_driver); diff --git a/drivers/net/phy/motorcomm.c b/drivers/net/phy/motorcomm.c index c7593f224177..bd1ab5d0631f 100644 --- a/drivers/net/phy/motorcomm.c +++ b/drivers/net/phy/motorcomm.c @@ -1119,19 +1119,19 @@ static int yt8521_config_init(struct phy_device *phydev) switch (phydev->interface) { case PHY_INTERFACE_MODE_RGMII: - val = YT8521_RC1R_GE_TX_DELAY_DIS | YT8521_RC1R_GE_TX_DELAY_DIS; + val = YT8521_RC1R_GE_TX_DELAY_DIS | YT8521_RC1R_FE_TX_DELAY_DIS; val |= YT8521_RC1R_RX_DELAY_DIS; break; case PHY_INTERFACE_MODE_RGMII_RXID: - val = YT8521_RC1R_GE_TX_DELAY_DIS | YT8521_RC1R_GE_TX_DELAY_DIS; + val = YT8521_RC1R_GE_TX_DELAY_DIS | YT8521_RC1R_FE_TX_DELAY_DIS; val |= YT8521_RC1R_RX_DELAY_EN; break; case PHY_INTERFACE_MODE_RGMII_TXID: - val = YT8521_RC1R_GE_TX_DELAY_EN | YT8521_RC1R_GE_TX_DELAY_EN; + val = YT8521_RC1R_GE_TX_DELAY_EN | YT8521_RC1R_FE_TX_DELAY_EN; val |= YT8521_RC1R_RX_DELAY_DIS; break; case PHY_INTERFACE_MODE_RGMII_ID: - val = YT8521_RC1R_GE_TX_DELAY_EN | YT8521_RC1R_GE_TX_DELAY_EN; + val = YT8521_RC1R_GE_TX_DELAY_EN | YT8521_RC1R_FE_TX_DELAY_EN; val |= YT8521_RC1R_RX_DELAY_EN; break; case PHY_INTERFACE_MODE_SGMII: diff --git a/drivers/net/phy/mscc/mscc_macsec.c b/drivers/net/phy/mscc/mscc_macsec.c index ee5b17edca39..f81b077618f4 100644 --- a/drivers/net/phy/mscc/mscc_macsec.c +++ b/drivers/net/phy/mscc/mscc_macsec.c @@ -632,6 +632,7 @@ static void vsc8584_macsec_free_flow(struct vsc8531_private *priv, list_del(&flow->list); clear_bit(flow->index, bitmap); + memzero_explicit(flow->key, sizeof(flow->key)); kfree(flow); } diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index e741d8aebffe..e5b6cb1a77f9 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -67,6 +67,7 @@ static void phy_link_down(struct phy_device *phydev) { phydev->phy_link_change(phydev, false); phy_led_trigger_change_speed(phydev); + WRITE_ONCE(phydev->link_down_events, phydev->link_down_events + 1); } static const char *phy_pause_str(struct phy_device *phydev) diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 88f60e98b760..25feab1802ee 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -649,7 +649,10 @@ static int phylink_validate_mac_and_pcs(struct phylink *pl, } /* Then validate the link parameters with the MAC */ - pl->mac_ops->validate(pl->config, supported, state); + if (pl->mac_ops->validate) + pl->mac_ops->validate(pl->config, supported, state); + else + phylink_generic_validate(pl->config, supported, state); return phylink_is_empty_linkmode(supported) ? -EINVAL : 0; } diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 0718e39117a8..addef005ba37 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1967,17 +1967,25 @@ drop: skb_headlen(skb)); if (unlikely(headlen > skb_headlen(skb))) { + WARN_ON_ONCE(1); + err = -ENOMEM; dev_core_stats_rx_dropped_inc(tun->dev); +napi_busy: napi_free_frags(&tfile->napi); rcu_read_unlock(); mutex_unlock(&tfile->napi_mutex); - WARN_ON(1); - return -ENOMEM; + return err; } - local_bh_disable(); - napi_gro_frags(&tfile->napi); - local_bh_enable(); + if (likely(napi_schedule_prep(&tfile->napi))) { + local_bh_disable(); + napi_gro_frags(&tfile->napi); + napi_complete(&tfile->napi); + local_bh_enable(); + } else { + err = -EBUSY; + goto napi_busy; + } mutex_unlock(&tfile->napi_mutex); } else if (tfile->napi_enabled) { struct sk_buff_head *queue = &tfile->sk.sk_write_queue; diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c index 02941d97d034..0fe3773c5bca 100644 --- a/drivers/net/usb/asix_devices.c +++ b/drivers/net/usb/asix_devices.c @@ -773,7 +773,6 @@ static void ax88772_mac_link_up(struct phylink_config *config, } static const struct phylink_mac_ops ax88772_phylink_mac_ops = { - .validate = phylink_generic_validate, .mac_config = ax88772_mac_config, .mac_link_down = ax88772_mac_link_down, .mac_link_up = ax88772_mac_link_up, diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index 8d5cbda33f66..6b5f24f28dd1 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -43,6 +43,7 @@ #include <linux/ctype.h> #include <linux/etherdevice.h> #include <linux/ethtool.h> +#include <linux/kstrtox.h> #include <linux/workqueue.h> #include <linux/mii.h> #include <linux/crc32.h> @@ -318,7 +319,7 @@ static ssize_t ndp_to_end_store(struct device *d, struct device_attribute *attr struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0]; bool enable; - if (strtobool(buf, &enable)) + if (kstrtobool(buf, &enable)) return -EINVAL; /* no change? */ diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 26c34a7c21bd..30d733c81ed8 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -13,6 +13,7 @@ #include <linux/ethtool.h> #include <linux/etherdevice.h> #include <linux/if_arp.h> +#include <linux/kstrtox.h> #include <linux/mii.h> #include <linux/rtnetlink.h> #include <linux/usb.h> @@ -343,7 +344,7 @@ static ssize_t raw_ip_store(struct device *d, struct device_attribute *attr, co bool enable; int ret; - if (strtobool(buf, &enable)) + if (kstrtobool(buf, &enable)) return -EINVAL; /* no change? */ @@ -492,7 +493,7 @@ static ssize_t pass_through_store(struct device *d, struct qmi_wwan_state *info; bool enable; - if (strtobool(buf, &enable)) + if (kstrtobool(buf, &enable)) return -EINVAL; info = (void *)&dev->data; diff --git a/drivers/net/wan/lapbether.c b/drivers/net/wan/lapbether.c index 960f1393595c..d62a904d2e42 100644 --- a/drivers/net/wan/lapbether.c +++ b/drivers/net/wan/lapbether.c @@ -325,6 +325,7 @@ static int lapbeth_open(struct net_device *dev) err = lapb_register(dev, &lapbeth_callbacks); if (err != LAPB_OK) { + napi_disable(&lapbeth->napi); pr_err("lapb_register error: %d\n", err); return -ENODEV; } @@ -446,7 +447,7 @@ static int lapbeth_device_event(struct notifier_block *this, if (dev_net(dev) != &init_net) return NOTIFY_DONE; - if (!dev_is_ethdev(dev)) + if (!dev_is_ethdev(dev) && !lapbeth_get_x25_dev(dev)) return NOTIFY_DONE; switch (event) { diff --git a/drivers/net/wireless/ath/ath11k/qmi.h b/drivers/net/wireless/ath/ath11k/qmi.h index 2ec56a34fa81..0909d53cefeb 100644 --- a/drivers/net/wireless/ath/ath11k/qmi.h +++ b/drivers/net/wireless/ath/ath11k/qmi.h @@ -27,7 +27,7 @@ #define ATH11K_QMI_WLANFW_MAX_NUM_MEM_SEG_V01 52 #define ATH11K_QMI_CALDB_SIZE 0x480000 #define ATH11K_QMI_BDF_EXT_STR_LENGTH 0x20 -#define ATH11K_QMI_FW_MEM_REQ_SEGMENT_CNT 3 +#define ATH11K_QMI_FW_MEM_REQ_SEGMENT_CNT 5 #define QMI_WLFW_REQUEST_MEM_IND_V01 0x0035 #define QMI_WLFW_FW_MEM_READY_IND_V01 0x0037 diff --git a/drivers/net/wireless/ath/ath11k/reg.c b/drivers/net/wireless/ath/ath11k/reg.c index 7ee3ff69dfc8..6fae4e61ede7 100644 --- a/drivers/net/wireless/ath/ath11k/reg.c +++ b/drivers/net/wireless/ath/ath11k/reg.c @@ -287,11 +287,7 @@ int ath11k_regd_update(struct ath11k *ar) goto err; } - rtnl_lock(); - wiphy_lock(ar->hw->wiphy); - ret = regulatory_set_wiphy_regd_sync(ar->hw->wiphy, regd_copy); - wiphy_unlock(ar->hw->wiphy); - rtnl_unlock(); + ret = regulatory_set_wiphy_regd(ar->hw->wiphy, regd_copy); kfree(regd_copy); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c index bc3f4e4edcdf..dac7eb77799b 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c @@ -228,6 +228,10 @@ static void brcmf_fweh_event_worker(struct work_struct *work) brcmf_fweh_event_name(event->code), event->code, event->emsg.ifidx, event->emsg.bsscfgidx, event->emsg.addr); + if (event->emsg.bsscfgidx >= BRCMF_MAX_IFS) { + bphy_err(drvr, "invalid bsscfg index: %u\n", event->emsg.bsscfgidx); + goto event_free; + } /* convert event message */ emsg_be = &event->emsg; diff --git a/drivers/net/wireless/cisco/airo.c b/drivers/net/wireless/cisco/airo.c index 10daef81c355..fb2c35bd73bb 100644 --- a/drivers/net/wireless/cisco/airo.c +++ b/drivers/net/wireless/cisco/airo.c @@ -5232,7 +5232,7 @@ static int get_wep_tx_idx(struct airo_info *ai) return -1; } -static int set_wep_key(struct airo_info *ai, u16 index, const char *key, +static int set_wep_key(struct airo_info *ai, u16 index, const u8 *key, u16 keylen, int perm, int lock) { static const unsigned char macaddr[ETH_ALEN] = { 0x01, 0, 0, 0, 0, 0 }; @@ -5283,7 +5283,7 @@ static void proc_wepkey_on_close(struct inode *inode, struct file *file) struct net_device *dev = pde_data(inode); struct airo_info *ai = dev->ml_priv; int i, rc; - char key[16]; + u8 key[16]; u16 index = 0; int j = 0; @@ -5311,12 +5311,22 @@ static void proc_wepkey_on_close(struct inode *inode, struct file *file) } for (i = 0; i < 16*3 && data->wbuffer[i+j]; i++) { + int val; + + if (i % 3 == 2) + continue; + + val = hex_to_bin(data->wbuffer[i+j]); + if (val < 0) { + airo_print_err(ai->dev->name, "WebKey passed invalid key hex"); + return; + } switch(i%3) { case 0: - key[i/3] = hex_to_bin(data->wbuffer[i+j])<<4; + key[i/3] = (u8)val << 4; break; case 1: - key[i/3] |= hex_to_bin(data->wbuffer[i+j]); + key[i/3] |= (u8)val; break; } } diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 1927fc8111ff..c57c8903b7c0 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -910,6 +910,7 @@ static void hwsim_send_nullfunc(struct mac80211_hwsim_data *data, u8 *mac, struct hwsim_vif_priv *vp = (void *)vif->drv_priv; struct sk_buff *skb; struct ieee80211_hdr *hdr; + struct ieee80211_tx_info *cb; if (!vp->assoc) return; @@ -931,6 +932,10 @@ static void hwsim_send_nullfunc(struct mac80211_hwsim_data *data, u8 *mac, memcpy(hdr->addr2, mac, ETH_ALEN); memcpy(hdr->addr3, vp->bssid, ETH_ALEN); + cb = IEEE80211_SKB_CB(skb); + cb->control.rates[0].count = 1; + cb->control.rates[1].idx = -1; + rcu_read_lock(); mac80211_hwsim_tx_frame(data->hw, skb, rcu_dereference(vif->bss_conf.chanctx_conf)->def.chan); diff --git a/drivers/net/wireless/ralink/rt2x00/rt2400pci.c b/drivers/net/wireless/ralink/rt2x00/rt2400pci.c index bb5685826c18..13dd672b825e 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2400pci.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2400pci.c @@ -1023,9 +1023,9 @@ static int rt2400pci_set_state(struct rt2x00_dev *rt2x00dev, { u32 reg, reg2; unsigned int i; - char put_to_sleep; - char bbp_state; - char rf_state; + bool put_to_sleep; + u8 bbp_state; + u8 rf_state; put_to_sleep = (state != STATE_AWAKE); @@ -1561,7 +1561,7 @@ static int rt2400pci_probe_hw_mode(struct rt2x00_dev *rt2x00dev) { struct hw_mode_spec *spec = &rt2x00dev->spec; struct channel_info *info; - char *tx_power; + u8 *tx_power; unsigned int i; /* diff --git a/drivers/net/wireless/ralink/rt2x00/rt2400pci.h b/drivers/net/wireless/ralink/rt2x00/rt2400pci.h index b8187b6de143..979d5fd8babf 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2400pci.h +++ b/drivers/net/wireless/ralink/rt2x00/rt2400pci.h @@ -939,7 +939,7 @@ #define DEFAULT_TXPOWER 39 #define __CLAMP_TX(__txpower) \ - clamp_t(char, (__txpower), MIN_TXPOWER, MAX_TXPOWER) + clamp_t(u8, (__txpower), MIN_TXPOWER, MAX_TXPOWER) #define TXPOWER_FROM_DEV(__txpower) \ ((__CLAMP_TX(__txpower) - MAX_TXPOWER) + MIN_TXPOWER) diff --git a/drivers/net/wireless/ralink/rt2x00/rt2500pci.c b/drivers/net/wireless/ralink/rt2x00/rt2500pci.c index 43d2c1931d2b..ecddda4c471e 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2500pci.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2500pci.c @@ -1176,9 +1176,9 @@ static int rt2500pci_set_state(struct rt2x00_dev *rt2x00dev, { u32 reg, reg2; unsigned int i; - char put_to_sleep; - char bbp_state; - char rf_state; + bool put_to_sleep; + u8 bbp_state; + u8 rf_state; put_to_sleep = (state != STATE_AWAKE); @@ -1856,7 +1856,7 @@ static int rt2500pci_probe_hw_mode(struct rt2x00_dev *rt2x00dev) { struct hw_mode_spec *spec = &rt2x00dev->spec; struct channel_info *info; - char *tx_power; + u8 *tx_power; unsigned int i; /* diff --git a/drivers/net/wireless/ralink/rt2x00/rt2500pci.h b/drivers/net/wireless/ralink/rt2x00/rt2500pci.h index 7e64aee2a172..ba362675c52c 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2500pci.h +++ b/drivers/net/wireless/ralink/rt2x00/rt2500pci.h @@ -1219,6 +1219,6 @@ (((u8)(__txpower)) > MAX_TXPOWER) ? DEFAULT_TXPOWER : (__txpower) #define TXPOWER_TO_DEV(__txpower) \ - clamp_t(char, __txpower, MIN_TXPOWER, MAX_TXPOWER) + clamp_t(u8, __txpower, MIN_TXPOWER, MAX_TXPOWER) #endif /* RT2500PCI_H */ diff --git a/drivers/net/wireless/ralink/rt2x00/rt2500usb.c b/drivers/net/wireless/ralink/rt2x00/rt2500usb.c index a2696e24ae2b..13fdcff0ad66 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2500usb.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2500usb.c @@ -984,9 +984,9 @@ static int rt2500usb_set_state(struct rt2x00_dev *rt2x00dev, u16 reg; u16 reg2; unsigned int i; - char put_to_sleep; - char bbp_state; - char rf_state; + bool put_to_sleep; + u8 bbp_state; + u8 rf_state; put_to_sleep = (state != STATE_AWAKE); @@ -1663,7 +1663,7 @@ static int rt2500usb_probe_hw_mode(struct rt2x00_dev *rt2x00dev) { struct hw_mode_spec *spec = &rt2x00dev->spec; struct channel_info *info; - char *tx_power; + u8 *tx_power; unsigned int i; /* diff --git a/drivers/net/wireless/ralink/rt2x00/rt2500usb.h b/drivers/net/wireless/ralink/rt2x00/rt2500usb.h index 0c070288a140..746f0e950b76 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2500usb.h +++ b/drivers/net/wireless/ralink/rt2x00/rt2500usb.h @@ -839,6 +839,6 @@ (((u8)(__txpower)) > MAX_TXPOWER) ? DEFAULT_TXPOWER : (__txpower) #define TXPOWER_TO_DEV(__txpower) \ - clamp_t(char, __txpower, MIN_TXPOWER, MAX_TXPOWER) + clamp_t(u8, __txpower, MIN_TXPOWER, MAX_TXPOWER) #endif /* RT2500USB_H */ diff --git a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c index cbbb1a4849cf..12b700c7b9c3 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c @@ -3372,10 +3372,10 @@ static void rt2800_config_channel_rf53xx(struct rt2x00_dev *rt2x00dev, if (rt2x00_has_cap_bt_coexist(rt2x00dev)) { if (rt2x00_rt_rev_gte(rt2x00dev, RT5390, REV_RT5390F)) { /* r55/r59 value array of channel 1~14 */ - static const char r55_bt_rev[] = {0x83, 0x83, + static const u8 r55_bt_rev[] = {0x83, 0x83, 0x83, 0x73, 0x73, 0x63, 0x53, 0x53, 0x53, 0x43, 0x43, 0x43, 0x43, 0x43}; - static const char r59_bt_rev[] = {0x0e, 0x0e, + static const u8 r59_bt_rev[] = {0x0e, 0x0e, 0x0e, 0x0e, 0x0e, 0x0b, 0x0a, 0x09, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07}; @@ -3384,7 +3384,7 @@ static void rt2800_config_channel_rf53xx(struct rt2x00_dev *rt2x00dev, rt2800_rfcsr_write(rt2x00dev, 59, r59_bt_rev[idx]); } else { - static const char r59_bt[] = {0x8b, 0x8b, 0x8b, + static const u8 r59_bt[] = {0x8b, 0x8b, 0x8b, 0x8b, 0x8b, 0x8b, 0x8b, 0x8a, 0x89, 0x88, 0x88, 0x86, 0x85, 0x84}; @@ -3392,10 +3392,10 @@ static void rt2800_config_channel_rf53xx(struct rt2x00_dev *rt2x00dev, } } else { if (rt2x00_rt_rev_gte(rt2x00dev, RT5390, REV_RT5390F)) { - static const char r55_nonbt_rev[] = {0x23, 0x23, + static const u8 r55_nonbt_rev[] = {0x23, 0x23, 0x23, 0x23, 0x13, 0x13, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03}; - static const char r59_nonbt_rev[] = {0x07, 0x07, + static const u8 r59_nonbt_rev[] = {0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x06, 0x05, 0x04, 0x04}; @@ -3406,14 +3406,14 @@ static void rt2800_config_channel_rf53xx(struct rt2x00_dev *rt2x00dev, } else if (rt2x00_rt(rt2x00dev, RT5390) || rt2x00_rt(rt2x00dev, RT5392) || rt2x00_rt(rt2x00dev, RT6352)) { - static const char r59_non_bt[] = {0x8f, 0x8f, + static const u8 r59_non_bt[] = {0x8f, 0x8f, 0x8f, 0x8f, 0x8f, 0x8f, 0x8f, 0x8d, 0x8a, 0x88, 0x88, 0x87, 0x87, 0x86}; rt2800_rfcsr_write(rt2x00dev, 59, r59_non_bt[idx]); } else if (rt2x00_rt(rt2x00dev, RT5350)) { - static const char r59_non_bt[] = {0x0b, 0x0b, + static const u8 r59_non_bt[] = {0x0b, 0x0b, 0x0b, 0x0b, 0x0b, 0x0b, 0x0b, 0x0a, 0x0a, 0x09, 0x08, 0x07, 0x07, 0x06}; @@ -4035,23 +4035,23 @@ static void rt2800_iq_calibrate(struct rt2x00_dev *rt2x00dev, int channel) rt2800_bbp_write(rt2x00dev, 159, cal != 0xff ? cal : 0); } -static char rt2800_txpower_to_dev(struct rt2x00_dev *rt2x00dev, +static s8 rt2800_txpower_to_dev(struct rt2x00_dev *rt2x00dev, unsigned int channel, - char txpower) + s8 txpower) { if (rt2x00_rt(rt2x00dev, RT3593) || rt2x00_rt(rt2x00dev, RT3883)) txpower = rt2x00_get_field8(txpower, EEPROM_TXPOWER_ALC); if (channel <= 14) - return clamp_t(char, txpower, MIN_G_TXPOWER, MAX_G_TXPOWER); + return clamp_t(s8, txpower, MIN_G_TXPOWER, MAX_G_TXPOWER); if (rt2x00_rt(rt2x00dev, RT3593) || rt2x00_rt(rt2x00dev, RT3883)) - return clamp_t(char, txpower, MIN_A_TXPOWER_3593, + return clamp_t(s8, txpower, MIN_A_TXPOWER_3593, MAX_A_TXPOWER_3593); else - return clamp_t(char, txpower, MIN_A_TXPOWER, MAX_A_TXPOWER); + return clamp_t(s8, txpower, MIN_A_TXPOWER, MAX_A_TXPOWER); } static void rt3883_bbp_adjust(struct rt2x00_dev *rt2x00dev, @@ -8530,7 +8530,7 @@ static void rt2800_r_calibration(struct rt2x00_dev *rt2x00dev) u8 bytevalue = 0; int rcalcode; u8 r_cal_code = 0; - char d1 = 0, d2 = 0; + s8 d1 = 0, d2 = 0; u8 rfvalue; u32 MAC_RF_BYPASS0, MAC_RF_CONTROL0, MAC_PWR_PIN_CFG; u32 maccfg; @@ -8591,7 +8591,7 @@ static void rt2800_r_calibration(struct rt2x00_dev *rt2x00dev) if (bytevalue > 128) d1 = bytevalue - 256; else - d1 = (char)bytevalue; + d1 = (s8)bytevalue; rt2800_bbp_write(rt2x00dev, 22, 0x0); rt2800_rfcsr_write_bank(rt2x00dev, 0, 35, 0x01); @@ -8601,7 +8601,7 @@ static void rt2800_r_calibration(struct rt2x00_dev *rt2x00dev) if (bytevalue > 128) d2 = bytevalue - 256; else - d2 = (char)bytevalue; + d2 = (s8)bytevalue; rt2800_bbp_write(rt2x00dev, 22, 0x0); rcalcode = rt2800_calcrcalibrationcode(rt2x00dev, d1, d2); @@ -8703,7 +8703,7 @@ static void rt2800_rxdcoc_calibration(struct rt2x00_dev *rt2x00dev) static u32 rt2800_do_sqrt_accumulation(u32 si) { u32 root, root_pre, bit; - char i; + s8 i; bit = 1 << 15; root = 0; @@ -9330,11 +9330,11 @@ static void rt2800_loft_search(struct rt2x00_dev *rt2x00dev, u8 ch_idx, u8 alc_idx, u8 dc_result[][RF_ALC_NUM][2]) { u32 p0 = 0, p1 = 0, pf = 0; - char idx0 = 0, idx1 = 0; + s8 idx0 = 0, idx1 = 0; u8 idxf[] = {0x00, 0x00}; u8 ibit = 0x20; u8 iorq; - char bidx; + s8 bidx; rt2800_bbp_write(rt2x00dev, 158, 0xb0); rt2800_bbp_write(rt2x00dev, 159, 0x80); @@ -9384,17 +9384,17 @@ static void rt2800_loft_search(struct rt2x00_dev *rt2x00dev, u8 ch_idx, static void rt2800_iq_search(struct rt2x00_dev *rt2x00dev, u8 ch_idx, u8 *ges, u8 *pes) { u32 p0 = 0, p1 = 0, pf = 0; - char perr = 0, gerr = 0, iq_err = 0; - char pef = 0, gef = 0; - char psta, pend; - char gsta, gend; + s8 perr = 0, gerr = 0, iq_err = 0; + s8 pef = 0, gef = 0; + s8 psta, pend; + s8 gsta, gend; u8 ibit = 0x20; u8 first_search = 0x00, touch_neg_max = 0x00; - char idx0 = 0, idx1 = 0; + s8 idx0 = 0, idx1 = 0; u8 gop; u8 bbp = 0; - char bidx; + s8 bidx; for (bidx = 5; bidx >= 1; bidx--) { for (gop = 0; gop < 2; gop++) { @@ -10043,11 +10043,11 @@ static int rt2800_rf_lp_config(struct rt2x00_dev *rt2x00dev, bool btxcal) return 0; } -static char rt2800_lp_tx_filter_bw_cal(struct rt2x00_dev *rt2x00dev) +static s8 rt2800_lp_tx_filter_bw_cal(struct rt2x00_dev *rt2x00dev) { unsigned int cnt; u8 bbp_val; - char cal_val; + s8 cal_val; rt2800_bbp_dcoc_write(rt2x00dev, 0, 0x82); @@ -10079,7 +10079,7 @@ static void rt2800_bw_filter_calibration(struct rt2x00_dev *rt2x00dev, u8 rx_filter_target_20m = 0x27, rx_filter_target_40m = 0x31; int loop = 0, is_ht40, cnt; u8 bbp_val, rf_val; - char cal_r32_init, cal_r32_val, cal_diff; + s8 cal_r32_init, cal_r32_val, cal_diff; u8 saverfb5r00, saverfb5r01, saverfb5r03, saverfb5r04, saverfb5r05; u8 saverfb5r06, saverfb5r07; u8 saverfb5r08, saverfb5r17, saverfb5r18, saverfb5r19, saverfb5r20; @@ -11550,9 +11550,9 @@ static int rt2800_probe_hw_mode(struct rt2x00_dev *rt2x00dev) { struct hw_mode_spec *spec = &rt2x00dev->spec; struct channel_info *info; - char *default_power1; - char *default_power2; - char *default_power3; + s8 *default_power1; + s8 *default_power2; + s8 *default_power3; unsigned int i, tx_chains, rx_chains; u32 reg; diff --git a/drivers/net/wireless/ralink/rt2x00/rt2800lib.h b/drivers/net/wireless/ralink/rt2x00/rt2800lib.h index 3cbef77b4bd3..194de676df8f 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2800lib.h +++ b/drivers/net/wireless/ralink/rt2x00/rt2800lib.h @@ -32,10 +32,10 @@ struct rf_reg_pair { struct rt2800_drv_data { u8 calibration_bw20; u8 calibration_bw40; - char rx_calibration_bw20; - char rx_calibration_bw40; - char tx_calibration_bw20; - char tx_calibration_bw40; + s8 rx_calibration_bw20; + s8 rx_calibration_bw40; + s8 tx_calibration_bw20; + s8 tx_calibration_bw40; u8 bbp25; u8 bbp26; u8 txmixer_gain_24g; diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00usb.c b/drivers/net/wireless/ralink/rt2x00/rt2x00usb.c index 0827bc860bf8..8fd22c69855f 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2x00usb.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2x00usb.c @@ -117,12 +117,12 @@ int rt2x00usb_vendor_request_buff(struct rt2x00_dev *rt2x00dev, const u16 buffer_length) { int status = 0; - unsigned char *tb; + u8 *tb; u16 off, len, bsize; mutex_lock(&rt2x00dev->csr_mutex); - tb = (char *)buffer; + tb = (u8 *)buffer; off = offset; len = buffer_length; while (len && !status) { @@ -215,7 +215,7 @@ void rt2x00usb_register_read_async(struct rt2x00_dev *rt2x00dev, rd->cr.wLength = cpu_to_le16(sizeof(u32)); usb_fill_control_urb(urb, usb_dev, usb_rcvctrlpipe(usb_dev, 0), - (unsigned char *)(&rd->cr), &rd->reg, sizeof(rd->reg), + (u8 *)(&rd->cr), &rd->reg, sizeof(rd->reg), rt2x00usb_register_read_async_cb, rd); usb_anchor_urb(urb, rt2x00dev->anchor); if (usb_submit_urb(urb, GFP_ATOMIC) < 0) { diff --git a/drivers/net/wireless/ralink/rt2x00/rt61pci.c b/drivers/net/wireless/ralink/rt2x00/rt61pci.c index b1679a8e4610..483723bf514b 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt61pci.c +++ b/drivers/net/wireless/ralink/rt2x00/rt61pci.c @@ -1709,7 +1709,7 @@ static int rt61pci_set_state(struct rt2x00_dev *rt2x00dev, enum dev_state state) { u32 reg, reg2; unsigned int i; - char put_to_sleep; + bool put_to_sleep; put_to_sleep = (state != STATE_AWAKE); @@ -2656,7 +2656,7 @@ static int rt61pci_probe_hw_mode(struct rt2x00_dev *rt2x00dev) { struct hw_mode_spec *spec = &rt2x00dev->spec; struct channel_info *info; - char *tx_power; + u8 *tx_power; unsigned int i; /* diff --git a/drivers/net/wireless/ralink/rt2x00/rt61pci.h b/drivers/net/wireless/ralink/rt2x00/rt61pci.h index 5f208ad509bd..d72d0ffd1127 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt61pci.h +++ b/drivers/net/wireless/ralink/rt2x00/rt61pci.h @@ -1484,6 +1484,6 @@ struct hw_pairwise_ta_entry { (((u8)(__txpower)) > MAX_TXPOWER) ? DEFAULT_TXPOWER : (__txpower) #define TXPOWER_TO_DEV(__txpower) \ - clamp_t(char, __txpower, MIN_TXPOWER, MAX_TXPOWER) + clamp_t(u8, __txpower, MIN_TXPOWER, MAX_TXPOWER) #endif /* RT61PCI_H */ diff --git a/drivers/net/wireless/ralink/rt2x00/rt73usb.c b/drivers/net/wireless/ralink/rt2x00/rt73usb.c index e2f4f40cb7ee..dfa9d5213898 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt73usb.c +++ b/drivers/net/wireless/ralink/rt2x00/rt73usb.c @@ -1378,7 +1378,7 @@ static int rt73usb_set_state(struct rt2x00_dev *rt2x00dev, enum dev_state state) { u32 reg, reg2; unsigned int i; - char put_to_sleep; + bool put_to_sleep; put_to_sleep = (state != STATE_AWAKE); @@ -2090,7 +2090,7 @@ static int rt73usb_probe_hw_mode(struct rt2x00_dev *rt2x00dev) { struct hw_mode_spec *spec = &rt2x00dev->spec; struct channel_info *info; - char *tx_power; + u8 *tx_power; unsigned int i; /* diff --git a/drivers/net/wireless/ralink/rt2x00/rt73usb.h b/drivers/net/wireless/ralink/rt2x00/rt73usb.h index 1b56d285c34b..bb0a68516c08 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt73usb.h +++ b/drivers/net/wireless/ralink/rt2x00/rt73usb.h @@ -1063,6 +1063,6 @@ struct hw_pairwise_ta_entry { (((u8)(__txpower)) > MAX_TXPOWER) ? DEFAULT_TXPOWER : (__txpower) #define TXPOWER_TO_DEV(__txpower) \ - clamp_t(char, __txpower, MIN_TXPOWER, MAX_TXPOWER) + clamp_t(u8, __txpower, MIN_TXPOWER, MAX_TXPOWER) #endif /* RT73USB_H */ diff --git a/drivers/net/wwan/Kconfig b/drivers/net/wwan/Kconfig index 32149029c891..410b0245114e 100644 --- a/drivers/net/wwan/Kconfig +++ b/drivers/net/wwan/Kconfig @@ -94,7 +94,7 @@ config RPMSG_WWAN_CTRL config IOSM tristate "IOSM Driver for Intel M.2 WWAN Device" - depends on INTEL_IOMMU + depends on PCI select NET_DEVLINK select RELAY if WWAN_DEBUGFS help diff --git a/drivers/net/wwan/iosm/iosm_ipc_coredump.c b/drivers/net/wwan/iosm/iosm_ipc_coredump.c index 9acd87724c9d..26ca30476f40 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_coredump.c +++ b/drivers/net/wwan/iosm/iosm_ipc_coredump.c @@ -2,6 +2,7 @@ /* * Copyright (C) 2020-2021 Intel Corporation. */ +#include <linux/vmalloc.h> #include "iosm_ipc_coredump.h" diff --git a/drivers/net/wwan/iosm/iosm_ipc_devlink.c b/drivers/net/wwan/iosm/iosm_ipc_devlink.c index 17da85a8f337..2fe724d623c0 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_devlink.c +++ b/drivers/net/wwan/iosm/iosm_ipc_devlink.c @@ -2,6 +2,7 @@ /* * Copyright (C) 2020-2021 Intel Corporation. */ +#include <linux/vmalloc.h> #include "iosm_ipc_chnl_cfg.h" #include "iosm_ipc_coredump.h" diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c index b7f9237dedf7..66b90cc4c346 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c +++ b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c @@ -91,6 +91,14 @@ void ipc_imem_wwan_channel_init(struct iosm_imem *ipc_imem, } ipc_chnl_cfg_get(&chnl_cfg, ipc_imem->nr_of_channels); + + if (ipc_imem->mmio->mux_protocol == MUX_AGGREGATION && + ipc_imem->nr_of_channels == IPC_MEM_IP_CHL_ID_0) { + chnl_cfg.ul_nr_of_entries = IPC_MEM_MAX_TDS_MUX_AGGR_UL; + chnl_cfg.dl_nr_of_entries = IPC_MEM_MAX_TDS_MUX_AGGR_DL; + chnl_cfg.dl_buf_size = IPC_MEM_MAX_ADB_BUF_SIZE; + } + ipc_imem_channel_init(ipc_imem, IPC_CTYPE_WWAN, chnl_cfg, IRQ_MOD_OFF); diff --git a/drivers/net/wwan/iosm/iosm_ipc_mux.h b/drivers/net/wwan/iosm/iosm_ipc_mux.h index cd9d74cc097f..9968bb885c1f 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_mux.h +++ b/drivers/net/wwan/iosm/iosm_ipc_mux.h @@ -10,6 +10,7 @@ #define IPC_MEM_MAX_UL_DG_ENTRIES 100 #define IPC_MEM_MAX_TDS_MUX_AGGR_UL 60 +#define IPC_MEM_MAX_TDS_MUX_AGGR_DL 60 #define IPC_MEM_MAX_ADB_BUF_SIZE (16 * 1024) #define IPC_MEM_MAX_UL_ADB_BUF_SIZE IPC_MEM_MAX_ADB_BUF_SIZE diff --git a/drivers/net/wwan/iosm/iosm_ipc_pcie.c b/drivers/net/wwan/iosm/iosm_ipc_pcie.c index 31f57b986df2..d3d34d1c4704 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_pcie.c +++ b/drivers/net/wwan/iosm/iosm_ipc_pcie.c @@ -232,6 +232,7 @@ static void ipc_pcie_config_init(struct iosm_pcie *ipc_pcie) */ static enum ipc_pcie_sleep_state ipc_pcie_read_bios_cfg(struct device *dev) { + enum ipc_pcie_sleep_state sleep_state = IPC_PCIE_D0L12; union acpi_object *object; acpi_handle handle_acpi; @@ -242,18 +243,23 @@ static enum ipc_pcie_sleep_state ipc_pcie_read_bios_cfg(struct device *dev) } object = acpi_evaluate_dsm(handle_acpi, &wwan_acpi_guid, 0, 3, NULL); + if (!object) + goto default_ret; + + if (object->integer.value == 3) + sleep_state = IPC_PCIE_D3L2; - if (object && object->integer.value == 3) - return IPC_PCIE_D3L2; + kfree(object); default_ret: - return IPC_PCIE_D0L12; + return sleep_state; } static int ipc_pcie_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) { struct iosm_pcie *ipc_pcie = kzalloc(sizeof(*ipc_pcie), GFP_KERNEL); + int ret; pr_debug("Probing device 0x%X from the vendor 0x%X", pci_id->device, pci_id->vendor); @@ -286,6 +292,12 @@ static int ipc_pcie_probe(struct pci_dev *pci, goto pci_enable_fail; } + ret = dma_set_mask(ipc_pcie->dev, DMA_BIT_MASK(64)); + if (ret) { + dev_err(ipc_pcie->dev, "Could not set PCI DMA mask: %d", ret); + return ret; + } + ipc_pcie_config_aspm(ipc_pcie); dev_dbg(ipc_pcie->dev, "PCIe device enabled."); diff --git a/drivers/net/wwan/iosm/iosm_ipc_wwan.c b/drivers/net/wwan/iosm/iosm_ipc_wwan.c index 2f1f8b5d5b59..4c9022a93e01 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_wwan.c +++ b/drivers/net/wwan/iosm/iosm_ipc_wwan.c @@ -40,13 +40,11 @@ struct iosm_netdev_priv { * @ipc_imem: Pointer to imem data-struct * @sub_netlist: List of active netdevs * @dev: Pointer device structure - * @if_mutex: Mutex used for add and remove interface id */ struct iosm_wwan { struct iosm_imem *ipc_imem; struct iosm_netdev_priv __rcu *sub_netlist[IP_MUX_SESSION_END + 1]; struct device *dev; - struct mutex if_mutex; /* Mutex used for add and remove interface id */ }; /* Bring-up the wwan net link */ @@ -55,14 +53,11 @@ static int ipc_wwan_link_open(struct net_device *netdev) struct iosm_netdev_priv *priv = wwan_netdev_drvpriv(netdev); struct iosm_wwan *ipc_wwan = priv->ipc_wwan; int if_id = priv->if_id; - int ret; if (if_id < IP_MUX_SESSION_START || if_id >= ARRAY_SIZE(ipc_wwan->sub_netlist)) return -EINVAL; - mutex_lock(&ipc_wwan->if_mutex); - /* get channel id */ priv->ch_id = ipc_imem_sys_wwan_open(ipc_wwan->ipc_imem, if_id); @@ -70,8 +65,7 @@ static int ipc_wwan_link_open(struct net_device *netdev) dev_err(ipc_wwan->dev, "cannot connect wwan0 & id %d to the IPC mem layer", if_id); - ret = -ENODEV; - goto out; + return -ENODEV; } /* enable tx path, DL data may follow */ @@ -80,10 +74,7 @@ static int ipc_wwan_link_open(struct net_device *netdev) dev_dbg(ipc_wwan->dev, "Channel id %d allocated to if_id %d", priv->ch_id, priv->if_id); - ret = 0; -out: - mutex_unlock(&ipc_wwan->if_mutex); - return ret; + return 0; } /* Bring-down the wwan net link */ @@ -93,11 +84,9 @@ static int ipc_wwan_link_stop(struct net_device *netdev) netif_stop_queue(netdev); - mutex_lock(&priv->ipc_wwan->if_mutex); ipc_imem_sys_wwan_close(priv->ipc_wwan->ipc_imem, priv->if_id, priv->ch_id); priv->ch_id = -1; - mutex_unlock(&priv->ipc_wwan->if_mutex); return 0; } @@ -168,6 +157,7 @@ static void ipc_wwan_setup(struct net_device *iosm_dev) iosm_dev->max_mtu = ETH_MAX_MTU; iosm_dev->flags = IFF_POINTOPOINT | IFF_NOARP; + iosm_dev->needs_free_netdev = true; iosm_dev->netdev_ops = &ipc_inm_ops; } @@ -189,26 +179,17 @@ static int ipc_wwan_newlink(void *ctxt, struct net_device *dev, priv->netdev = dev; priv->ipc_wwan = ipc_wwan; - mutex_lock(&ipc_wwan->if_mutex); - if (rcu_access_pointer(ipc_wwan->sub_netlist[if_id])) { - err = -EBUSY; - goto out_unlock; - } + if (rcu_access_pointer(ipc_wwan->sub_netlist[if_id])) + return -EBUSY; err = register_netdevice(dev); if (err) - goto out_unlock; + return err; rcu_assign_pointer(ipc_wwan->sub_netlist[if_id], priv); - mutex_unlock(&ipc_wwan->if_mutex); - netif_device_attach(dev); return 0; - -out_unlock: - mutex_unlock(&ipc_wwan->if_mutex); - return err; } static void ipc_wwan_dellink(void *ctxt, struct net_device *dev, @@ -222,17 +203,12 @@ static void ipc_wwan_dellink(void *ctxt, struct net_device *dev, if_id >= ARRAY_SIZE(ipc_wwan->sub_netlist))) return; - mutex_lock(&ipc_wwan->if_mutex); - if (WARN_ON(rcu_access_pointer(ipc_wwan->sub_netlist[if_id]) != priv)) - goto unlock; + return; RCU_INIT_POINTER(ipc_wwan->sub_netlist[if_id], NULL); /* unregistering includes synchronize_net() */ unregister_netdevice_queue(dev, head); - -unlock: - mutex_unlock(&ipc_wwan->if_mutex); } static const struct wwan_ops iosm_wwan_ops = { @@ -323,12 +299,9 @@ struct iosm_wwan *ipc_wwan_init(struct iosm_imem *ipc_imem, struct device *dev) ipc_wwan->dev = dev; ipc_wwan->ipc_imem = ipc_imem; - mutex_init(&ipc_wwan->if_mutex); - /* WWAN core will create a netdev for the default IP MUX channel */ if (wwan_register_ops(ipc_wwan->dev, &iosm_wwan_ops, ipc_wwan, IP_MUX_SESSION_DEFAULT)) { - mutex_destroy(&ipc_wwan->if_mutex); kfree(ipc_wwan); return NULL; } @@ -341,7 +314,5 @@ void ipc_wwan_deinit(struct iosm_wwan *ipc_wwan) /* This call will remove all child netdev(s) */ wwan_unregister_ops(ipc_wwan->dev); - mutex_destroy(&ipc_wwan->if_mutex); - kfree(ipc_wwan); } diff --git a/drivers/net/wwan/mhi_wwan_mbim.c b/drivers/net/wwan/mhi_wwan_mbim.c index 22b5939a42bb..3f72ae943b29 100644 --- a/drivers/net/wwan/mhi_wwan_mbim.c +++ b/drivers/net/wwan/mhi_wwan_mbim.c @@ -582,6 +582,7 @@ static void mhi_mbim_setup(struct net_device *ndev) ndev->min_mtu = ETH_MIN_MTU; ndev->max_mtu = MHI_MAX_BUF_SZ - ndev->needed_headroom; ndev->tx_queue_len = 1000; + ndev->needs_free_netdev = true; } static const struct wwan_ops mhi_mbim_wwan_ops = { diff --git a/drivers/net/wwan/t7xx/t7xx_hif_dpmaif.h b/drivers/net/wwan/t7xx/t7xx_hif_dpmaif.h index 1225ca0ed51e..0ce4505e813d 100644 --- a/drivers/net/wwan/t7xx/t7xx_hif_dpmaif.h +++ b/drivers/net/wwan/t7xx/t7xx_hif_dpmaif.h @@ -20,6 +20,7 @@ #include <linux/bitmap.h> #include <linux/mm_types.h> +#include <linux/netdevice.h> #include <linux/sched.h> #include <linux/skbuff.h> #include <linux/spinlock.h> @@ -109,20 +110,14 @@ struct dpmaif_rx_queue { struct dpmaif_bat_request *bat_req; struct dpmaif_bat_request *bat_frag; - wait_queue_head_t rx_wq; - struct task_struct *rx_thread; - struct sk_buff_head skb_list; - unsigned int skb_list_max_len; - - struct workqueue_struct *worker; - struct work_struct dpmaif_rxq_work; - atomic_t rx_processing; struct dpmaif_ctrl *dpmaif_ctrl; unsigned int expect_pit_seq; unsigned int pit_remain_release_cnt; struct dpmaif_cur_rx_skb_info rx_data_info; + struct napi_struct napi; + bool sleep_lock_pending; }; struct dpmaif_tx_queue { @@ -168,7 +163,8 @@ enum dpmaif_txq_state { struct dpmaif_callbacks { void (*state_notify)(struct t7xx_pci_dev *t7xx_dev, enum dpmaif_txq_state state, int txq_number); - void (*recv_skb)(struct t7xx_pci_dev *t7xx_dev, struct sk_buff *skb); + void (*recv_skb)(struct t7xx_ccmni_ctrl *ccmni_ctlb, struct sk_buff *skb, + struct napi_struct *napi); }; struct dpmaif_ctrl { diff --git a/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_rx.c b/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_rx.c index 91a0eb19e0d8..aa2174a10437 100644 --- a/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_rx.c +++ b/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_rx.c @@ -45,6 +45,7 @@ #include "t7xx_dpmaif.h" #include "t7xx_hif_dpmaif.h" #include "t7xx_hif_dpmaif_rx.h" +#include "t7xx_netdev.h" #include "t7xx_pci.h" #define DPMAIF_BAT_COUNT 8192 @@ -76,43 +77,6 @@ static unsigned int t7xx_normal_pit_bid(const struct dpmaif_pit *pit_info) return value; } -static int t7xx_dpmaif_net_rx_push_thread(void *arg) -{ - struct dpmaif_rx_queue *q = arg; - struct dpmaif_ctrl *hif_ctrl; - struct dpmaif_callbacks *cb; - - hif_ctrl = q->dpmaif_ctrl; - cb = hif_ctrl->callbacks; - - while (!kthread_should_stop()) { - struct sk_buff *skb; - unsigned long flags; - - if (skb_queue_empty(&q->skb_list)) { - if (wait_event_interruptible(q->rx_wq, - !skb_queue_empty(&q->skb_list) || - kthread_should_stop())) - continue; - - if (kthread_should_stop()) - break; - } - - spin_lock_irqsave(&q->skb_list.lock, flags); - skb = __skb_dequeue(&q->skb_list); - spin_unlock_irqrestore(&q->skb_list.lock, flags); - - if (!skb) - continue; - - cb->recv_skb(hif_ctrl->t7xx_dev, skb); - cond_resched(); - } - - return 0; -} - static int t7xx_dpmaif_update_bat_wr_idx(struct dpmaif_ctrl *dpmaif_ctrl, const unsigned int q_num, const unsigned int bat_cnt) { @@ -726,21 +690,10 @@ static int t7xx_dpmaifq_rx_notify_hw(struct dpmaif_rx_queue *rxq) return ret; } -static void t7xx_dpmaif_rx_skb_enqueue(struct dpmaif_rx_queue *rxq, struct sk_buff *skb) -{ - unsigned long flags; - - spin_lock_irqsave(&rxq->skb_list.lock, flags); - if (rxq->skb_list.qlen < rxq->skb_list_max_len) - __skb_queue_tail(&rxq->skb_list, skb); - else - dev_kfree_skb_any(skb); - spin_unlock_irqrestore(&rxq->skb_list.lock, flags); -} - static void t7xx_dpmaif_rx_skb(struct dpmaif_rx_queue *rxq, struct dpmaif_cur_rx_skb_info *skb_info) { + struct dpmaif_ctrl *dpmaif_ctrl = rxq->dpmaif_ctrl; struct sk_buff *skb = skb_info->cur_skb; struct t7xx_skb_cb *skb_cb; u8 netif_id; @@ -758,11 +711,11 @@ static void t7xx_dpmaif_rx_skb(struct dpmaif_rx_queue *rxq, skb_cb = T7XX_SKB_CB(skb); skb_cb->netif_idx = netif_id; skb_cb->rx_pkt_type = skb_info->pkt_type; - t7xx_dpmaif_rx_skb_enqueue(rxq, skb); + dpmaif_ctrl->callbacks->recv_skb(dpmaif_ctrl->t7xx_dev->ccmni_ctlb, skb, &rxq->napi); } static int t7xx_dpmaif_rx_start(struct dpmaif_rx_queue *rxq, const unsigned int pit_cnt, - const unsigned long timeout) + const unsigned int budget, int *once_more) { unsigned int cur_pit, pit_len, rx_cnt, recv_skb_cnt = 0; struct device *dev = rxq->dpmaif_ctrl->dev; @@ -777,13 +730,14 @@ static int t7xx_dpmaif_rx_start(struct dpmaif_rx_queue *rxq, const unsigned int struct dpmaif_pit *pkt_info; u32 val; - if (!skb_info->msg_pit_received && time_after_eq(jiffies, timeout)) + if (!skb_info->msg_pit_received && recv_skb_cnt >= budget) break; pkt_info = (struct dpmaif_pit *)rxq->pit_base + cur_pit; if (t7xx_dpmaif_check_pit_seq(rxq, pkt_info)) { dev_err_ratelimited(dev, "RXQ%u checks PIT SEQ fail\n", rxq->index); - return -EAGAIN; + *once_more = 1; + return recv_skb_cnt; } val = FIELD_GET(PD_PIT_PACKET_TYPE, le32_to_cpu(pkt_info->header)); @@ -817,12 +771,7 @@ static int t7xx_dpmaif_rx_start(struct dpmaif_rx_queue *rxq, const unsigned int } memset(skb_info, 0, sizeof(*skb_info)); - recv_skb_cnt++; - if (!(recv_skb_cnt & DPMAIF_RX_PUSH_THRESHOLD_MASK)) { - wake_up_all(&rxq->rx_wq); - recv_skb_cnt = 0; - } } } @@ -837,16 +786,13 @@ static int t7xx_dpmaif_rx_start(struct dpmaif_rx_queue *rxq, const unsigned int } } - if (recv_skb_cnt) - wake_up_all(&rxq->rx_wq); - if (!ret) ret = t7xx_dpmaifq_rx_notify_hw(rxq); if (ret) return ret; - return rx_cnt; + return recv_skb_cnt; } static unsigned int t7xx_dpmaifq_poll_pit(struct dpmaif_rx_queue *rxq) @@ -863,53 +809,30 @@ static unsigned int t7xx_dpmaifq_poll_pit(struct dpmaif_rx_queue *rxq) return pit_cnt; } -static int t7xx_dpmaif_rx_data_collect(struct dpmaif_ctrl *dpmaif_ctrl, - const unsigned int q_num, const unsigned int budget) +static int t7xx_dpmaif_napi_rx_data_collect(struct dpmaif_ctrl *dpmaif_ctrl, + const unsigned int q_num, + const unsigned int budget, int *once_more) { struct dpmaif_rx_queue *rxq = &dpmaif_ctrl->rxq[q_num]; - unsigned long time_limit; unsigned int cnt; + int ret = 0; - time_limit = jiffies + msecs_to_jiffies(DPMAIF_WQ_TIME_LIMIT_MS); - - while ((cnt = t7xx_dpmaifq_poll_pit(rxq))) { - unsigned int rd_cnt; - int real_cnt; - - rd_cnt = min(cnt, budget); - - real_cnt = t7xx_dpmaif_rx_start(rxq, rd_cnt, time_limit); - if (real_cnt < 0) - return real_cnt; - - if (real_cnt < cnt) - return -EAGAIN; - } - - return 0; -} + cnt = t7xx_dpmaifq_poll_pit(rxq); + if (!cnt) + return ret; -static void t7xx_dpmaif_do_rx(struct dpmaif_ctrl *dpmaif_ctrl, struct dpmaif_rx_queue *rxq) -{ - struct dpmaif_hw_info *hw_info = &dpmaif_ctrl->hw_info; - int ret; + ret = t7xx_dpmaif_rx_start(rxq, cnt, budget, once_more); + if (ret < 0) + dev_err(dpmaif_ctrl->dev, "dlq%u rx ERR:%d\n", rxq->index, ret); - ret = t7xx_dpmaif_rx_data_collect(dpmaif_ctrl, rxq->index, rxq->budget); - if (ret < 0) { - /* Try one more time */ - queue_work(rxq->worker, &rxq->dpmaif_rxq_work); - t7xx_dpmaif_clr_ip_busy_sts(hw_info); - } else { - t7xx_dpmaif_clr_ip_busy_sts(hw_info); - t7xx_dpmaif_dlq_unmask_rx_done(hw_info, rxq->index); - } + return ret; } -static void t7xx_dpmaif_rxq_work(struct work_struct *work) +int t7xx_dpmaif_napi_rx_poll(struct napi_struct *napi, const int budget) { - struct dpmaif_rx_queue *rxq = container_of(work, struct dpmaif_rx_queue, dpmaif_rxq_work); - struct dpmaif_ctrl *dpmaif_ctrl = rxq->dpmaif_ctrl; - int ret; + struct dpmaif_rx_queue *rxq = container_of(napi, struct dpmaif_rx_queue, napi); + struct t7xx_pci_dev *t7xx_dev = rxq->dpmaif_ctrl->t7xx_dev; + int ret, once_more = 0, work_done = 0; atomic_set(&rxq->rx_processing, 1); /* Ensure rx_processing is changed to 1 before actually begin RX flow */ @@ -917,22 +840,52 @@ static void t7xx_dpmaif_rxq_work(struct work_struct *work) if (!rxq->que_started) { atomic_set(&rxq->rx_processing, 0); - dev_err(dpmaif_ctrl->dev, "Work RXQ: %d has not been started\n", rxq->index); - return; + dev_err(rxq->dpmaif_ctrl->dev, "Work RXQ: %d has not been started\n", rxq->index); + return work_done; } - ret = pm_runtime_resume_and_get(dpmaif_ctrl->dev); - if (ret < 0 && ret != -EACCES) - return; + if (!rxq->sleep_lock_pending) { + pm_runtime_get_noresume(rxq->dpmaif_ctrl->dev); + t7xx_pci_disable_sleep(t7xx_dev); + } - t7xx_pci_disable_sleep(dpmaif_ctrl->t7xx_dev); - if (t7xx_pci_sleep_disable_complete(dpmaif_ctrl->t7xx_dev)) - t7xx_dpmaif_do_rx(dpmaif_ctrl, rxq); + ret = try_wait_for_completion(&t7xx_dev->sleep_lock_acquire); + if (!ret) { + napi_complete_done(napi, work_done); + rxq->sleep_lock_pending = true; + napi_reschedule(napi); + return work_done; + } - t7xx_pci_enable_sleep(dpmaif_ctrl->t7xx_dev); - pm_runtime_mark_last_busy(dpmaif_ctrl->dev); - pm_runtime_put_autosuspend(dpmaif_ctrl->dev); + rxq->sleep_lock_pending = false; + while (work_done < budget) { + int each_budget = budget - work_done; + int rx_cnt = t7xx_dpmaif_napi_rx_data_collect(rxq->dpmaif_ctrl, rxq->index, + each_budget, &once_more); + if (rx_cnt > 0) + work_done += rx_cnt; + else + break; + } + + if (once_more) { + napi_gro_flush(napi, false); + work_done = budget; + t7xx_dpmaif_clr_ip_busy_sts(&rxq->dpmaif_ctrl->hw_info); + } else if (work_done < budget) { + napi_complete_done(napi, work_done); + t7xx_dpmaif_clr_ip_busy_sts(&rxq->dpmaif_ctrl->hw_info); + t7xx_dpmaif_dlq_unmask_rx_done(&rxq->dpmaif_ctrl->hw_info, rxq->index); + } else { + t7xx_dpmaif_clr_ip_busy_sts(&rxq->dpmaif_ctrl->hw_info); + } + + t7xx_pci_enable_sleep(rxq->dpmaif_ctrl->t7xx_dev); + pm_runtime_mark_last_busy(rxq->dpmaif_ctrl->dev); + pm_runtime_put_noidle(rxq->dpmaif_ctrl->dev); atomic_set(&rxq->rx_processing, 0); + + return work_done; } void t7xx_dpmaif_irq_rx_done(struct dpmaif_ctrl *dpmaif_ctrl, const unsigned int que_mask) @@ -947,7 +900,7 @@ void t7xx_dpmaif_irq_rx_done(struct dpmaif_ctrl *dpmaif_ctrl, const unsigned int } rxq = &dpmaif_ctrl->rxq[qno]; - queue_work(rxq->worker, &rxq->dpmaif_rxq_work); + napi_schedule(&rxq->napi); } static void t7xx_dpmaif_base_free(const struct dpmaif_ctrl *dpmaif_ctrl, @@ -1082,50 +1035,14 @@ int t7xx_dpmaif_rxq_init(struct dpmaif_rx_queue *queue) int ret; ret = t7xx_dpmaif_rx_alloc(queue); - if (ret < 0) { + if (ret < 0) dev_err(queue->dpmaif_ctrl->dev, "Failed to allocate RX buffers: %d\n", ret); - return ret; - } - - INIT_WORK(&queue->dpmaif_rxq_work, t7xx_dpmaif_rxq_work); - - queue->worker = alloc_workqueue("dpmaif_rx%d_worker", - WQ_UNBOUND | WQ_MEM_RECLAIM | WQ_HIGHPRI, 1, queue->index); - if (!queue->worker) { - ret = -ENOMEM; - goto err_free_rx_buffer; - } - - init_waitqueue_head(&queue->rx_wq); - skb_queue_head_init(&queue->skb_list); - queue->skb_list_max_len = queue->bat_req->pkt_buf_sz; - queue->rx_thread = kthread_run(t7xx_dpmaif_net_rx_push_thread, - queue, "dpmaif_rx%d_push", queue->index); - - ret = PTR_ERR_OR_ZERO(queue->rx_thread); - if (ret) - goto err_free_workqueue; - - return 0; - -err_free_workqueue: - destroy_workqueue(queue->worker); - -err_free_rx_buffer: - t7xx_dpmaif_rx_buf_free(queue); return ret; } void t7xx_dpmaif_rxq_free(struct dpmaif_rx_queue *queue) { - if (queue->worker) - destroy_workqueue(queue->worker); - - if (queue->rx_thread) - kthread_stop(queue->rx_thread); - - skb_queue_purge(&queue->skb_list); t7xx_dpmaif_rx_buf_free(queue); } @@ -1188,8 +1105,6 @@ void t7xx_dpmaif_rx_stop(struct dpmaif_ctrl *dpmaif_ctrl) struct dpmaif_rx_queue *rxq = &dpmaif_ctrl->rxq[i]; int timeout, value; - flush_work(&rxq->dpmaif_rxq_work); - timeout = readx_poll_timeout_atomic(atomic_read, &rxq->rx_processing, value, !value, 0, DPMAIF_CHECK_INIT_TIMEOUT_US); if (timeout) @@ -1205,7 +1120,6 @@ static void t7xx_dpmaif_stop_rxq(struct dpmaif_rx_queue *rxq) { int cnt, j = 0; - flush_work(&rxq->dpmaif_rxq_work); rxq->que_started = false; do { diff --git a/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_rx.h b/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_rx.h index 182f62dfe398..f4e1b69ad426 100644 --- a/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_rx.h +++ b/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_rx.h @@ -112,5 +112,6 @@ int t7xx_dpmaif_bat_alloc(const struct dpmaif_ctrl *dpmaif_ctrl, struct dpmaif_b const enum bat_type buf_type); void t7xx_dpmaif_bat_free(const struct dpmaif_ctrl *dpmaif_ctrl, struct dpmaif_bat_request *bat_req); +int t7xx_dpmaif_napi_rx_poll(struct napi_struct *napi, const int budget); #endif /* __T7XX_HIF_DPMA_RX_H__ */ diff --git a/drivers/net/wwan/t7xx/t7xx_netdev.c b/drivers/net/wwan/t7xx/t7xx_netdev.c index f71d3bc3b237..494a28e386a3 100644 --- a/drivers/net/wwan/t7xx/t7xx_netdev.c +++ b/drivers/net/wwan/t7xx/t7xx_netdev.c @@ -22,6 +22,7 @@ #include <linux/gfp.h> #include <linux/if_arp.h> #include <linux/if_ether.h> +#include <linux/ip.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/netdev_features.h> @@ -29,6 +30,7 @@ #include <linux/skbuff.h> #include <linux/types.h> #include <linux/wwan.h> +#include <net/ipv6.h> #include <net/pkt_sched.h> #include "t7xx_hif_dpmaif_rx.h" @@ -39,13 +41,47 @@ #include "t7xx_state_monitor.h" #define IP_MUX_SESSION_DEFAULT 0 +#define SBD_PACKET_TYPE_MASK GENMASK(7, 4) + +static void t7xx_ccmni_enable_napi(struct t7xx_ccmni_ctrl *ctlb) +{ + int i; + + if (ctlb->is_napi_en) + return; + + for (i = 0; i < RXQ_NUM; i++) { + napi_enable(ctlb->napi[i]); + napi_schedule(ctlb->napi[i]); + } + ctlb->is_napi_en = true; +} + +static void t7xx_ccmni_disable_napi(struct t7xx_ccmni_ctrl *ctlb) +{ + int i; + + if (!ctlb->is_napi_en) + return; + + for (i = 0; i < RXQ_NUM; i++) { + napi_synchronize(ctlb->napi[i]); + napi_disable(ctlb->napi[i]); + } + + ctlb->is_napi_en = false; +} static int t7xx_ccmni_open(struct net_device *dev) { struct t7xx_ccmni *ccmni = wwan_netdev_drvpriv(dev); + struct t7xx_ccmni_ctrl *ccmni_ctl = ccmni->ctlb; netif_carrier_on(dev); netif_tx_start_all_queues(dev); + if (!atomic_fetch_inc(&ccmni_ctl->napi_usr_refcnt)) + t7xx_ccmni_enable_napi(ccmni_ctl); + atomic_inc(&ccmni->usage); return 0; } @@ -53,8 +89,12 @@ static int t7xx_ccmni_open(struct net_device *dev) static int t7xx_ccmni_close(struct net_device *dev) { struct t7xx_ccmni *ccmni = wwan_netdev_drvpriv(dev); + struct t7xx_ccmni_ctrl *ccmni_ctl = ccmni->ctlb; atomic_dec(&ccmni->usage); + if (atomic_dec_and_test(&ccmni_ctl->napi_usr_refcnt)) + t7xx_ccmni_disable_napi(ccmni_ctl); + netif_carrier_off(dev); netif_tx_disable(dev); return 0; @@ -127,6 +167,9 @@ static void t7xx_ccmni_start(struct t7xx_ccmni_ctrl *ctlb) netif_carrier_on(ccmni->dev); } } + + if (atomic_read(&ctlb->napi_usr_refcnt)) + t7xx_ccmni_enable_napi(ctlb); } static void t7xx_ccmni_pre_stop(struct t7xx_ccmni_ctrl *ctlb) @@ -149,6 +192,9 @@ static void t7xx_ccmni_post_stop(struct t7xx_ccmni_ctrl *ctlb) struct t7xx_ccmni *ccmni; int i; + if (atomic_read(&ctlb->napi_usr_refcnt)) + t7xx_ccmni_disable_napi(ctlb); + for (i = 0; i < ctlb->nic_dev_num; i++) { ccmni = ctlb->ccmni_inst[i]; if (!ccmni) @@ -161,7 +207,7 @@ static void t7xx_ccmni_post_stop(struct t7xx_ccmni_ctrl *ctlb) static void t7xx_ccmni_wwan_setup(struct net_device *dev) { - dev->hard_header_len += sizeof(struct ccci_header); + dev->needed_headroom += sizeof(struct ccci_header); dev->mtu = ETH_DATA_LEN; dev->max_mtu = CCMNI_MTU_MAX; @@ -183,6 +229,9 @@ static void t7xx_ccmni_wwan_setup(struct net_device *dev) dev->features |= NETIF_F_RXCSUM; dev->hw_features |= NETIF_F_RXCSUM; + dev->features |= NETIF_F_GRO; + dev->hw_features |= NETIF_F_GRO; + dev->needs_free_netdev = true; dev->type = ARPHRD_NONE; @@ -190,6 +239,34 @@ static void t7xx_ccmni_wwan_setup(struct net_device *dev) dev->netdev_ops = &ccmni_netdev_ops; } +static void t7xx_init_netdev_napi(struct t7xx_ccmni_ctrl *ctlb) +{ + int i; + + /* one HW, but shared with multiple net devices, + * so add a dummy device for NAPI. + */ + init_dummy_netdev(&ctlb->dummy_dev); + atomic_set(&ctlb->napi_usr_refcnt, 0); + ctlb->is_napi_en = false; + + for (i = 0; i < RXQ_NUM; i++) { + ctlb->napi[i] = &ctlb->hif_ctrl->rxq[i].napi; + netif_napi_add_weight(&ctlb->dummy_dev, ctlb->napi[i], t7xx_dpmaif_napi_rx_poll, + NIC_NAPI_POLL_BUDGET); + } +} + +static void t7xx_uninit_netdev_napi(struct t7xx_ccmni_ctrl *ctlb) +{ + int i; + + for (i = 0; i < RXQ_NUM; i++) { + netif_napi_del(ctlb->napi[i]); + ctlb->napi[i] = NULL; + } +} + static int t7xx_ccmni_wwan_newlink(void *ctxt, struct net_device *dev, u32 if_id, struct netlink_ext_ack *extack) { @@ -311,7 +388,8 @@ static void init_md_status_notifier(struct t7xx_pci_dev *t7xx_dev) t7xx_fsm_notifier_register(t7xx_dev->md, md_status_notifier); } -static void t7xx_ccmni_recv_skb(struct t7xx_pci_dev *t7xx_dev, struct sk_buff *skb) +static void t7xx_ccmni_recv_skb(struct t7xx_ccmni_ctrl *ccmni_ctlb, struct sk_buff *skb, + struct napi_struct *napi) { struct t7xx_skb_cb *skb_cb; struct net_device *net_dev; @@ -321,23 +399,22 @@ static void t7xx_ccmni_recv_skb(struct t7xx_pci_dev *t7xx_dev, struct sk_buff *s skb_cb = T7XX_SKB_CB(skb); netif_id = skb_cb->netif_idx; - ccmni = t7xx_dev->ccmni_ctlb->ccmni_inst[netif_id]; + ccmni = ccmni_ctlb->ccmni_inst[netif_id]; if (!ccmni) { dev_kfree_skb(skb); return; } net_dev = ccmni->dev; - skb->dev = net_dev; - pkt_type = skb_cb->rx_pkt_type; + skb->dev = net_dev; if (pkt_type == PKT_TYPE_IP6) skb->protocol = htons(ETH_P_IPV6); else skb->protocol = htons(ETH_P_IP); skb_len = skb->len; - netif_rx(skb); + napi_gro_receive(napi, skb); net_dev->stats.rx_packets++; net_dev->stats.rx_bytes += skb_len; } @@ -404,6 +481,7 @@ int t7xx_ccmni_init(struct t7xx_pci_dev *t7xx_dev) if (!ctlb->hif_ctrl) return -ENOMEM; + t7xx_init_netdev_napi(ctlb); init_md_status_notifier(t7xx_dev); return 0; } @@ -419,5 +497,6 @@ void t7xx_ccmni_exit(struct t7xx_pci_dev *t7xx_dev) ctlb->wwan_is_registered = false; } + t7xx_uninit_netdev_napi(ctlb); t7xx_dpmaif_hif_exit(ctlb->hif_ctrl); } diff --git a/drivers/net/wwan/t7xx/t7xx_netdev.h b/drivers/net/wwan/t7xx/t7xx_netdev.h index f5ad49ca12a7..f5ed6f99a145 100644 --- a/drivers/net/wwan/t7xx/t7xx_netdev.h +++ b/drivers/net/wwan/t7xx/t7xx_netdev.h @@ -30,6 +30,7 @@ #define CCMNI_NETDEV_WDT_TO (1 * HZ) #define CCMNI_MTU_MAX 3000 +#define NIC_NAPI_POLL_BUDGET 128 struct t7xx_ccmni { u8 index; @@ -47,6 +48,10 @@ struct t7xx_ccmni_ctrl { unsigned int md_sta; struct t7xx_fsm_notifier md_status_notify; bool wwan_is_registered; + struct net_device dummy_dev; + struct napi_struct *napi[RXQ_NUM]; + atomic_t napi_usr_refcnt; + bool is_napi_en; }; int t7xx_ccmni_init(struct t7xx_pci_dev *t7xx_dev); diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c index 9807c4d935cd..ba9d761ec49a 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c @@ -2240,7 +2240,7 @@ static void qmp_combo_enable_autonomous_mode(struct qmp_phy *qphy) static void qmp_combo_disable_autonomous_mode(struct qmp_phy *qphy) { const struct qmp_phy_cfg *cfg = qphy->cfg; - void __iomem *pcs_usb = qphy->pcs_usb ?: qphy->pcs_usb; + void __iomem *pcs_usb = qphy->pcs_usb ?: qphy->pcs; void __iomem *pcs_misc = qphy->pcs_misc; /* Disable i/o clamp_n on resume for normal mode */ diff --git a/drivers/phy/ralink/phy-mt7621-pci.c b/drivers/phy/ralink/phy-mt7621-pci.c index 5e6530f545b5..85888ab2d307 100644 --- a/drivers/phy/ralink/phy-mt7621-pci.c +++ b/drivers/phy/ralink/phy-mt7621-pci.c @@ -280,7 +280,8 @@ static struct phy *mt7621_pcie_phy_of_xlate(struct device *dev, } static const struct soc_device_attribute mt7621_pci_quirks_match[] = { - { .soc_id = "mt7621", .revision = "E2" } + { .soc_id = "mt7621", .revision = "E2" }, + { /* sentinel */ } }; static const struct regmap_config mt7621_pci_phy_regmap_config = { diff --git a/drivers/phy/st/phy-stm32-usbphyc.c b/drivers/phy/st/phy-stm32-usbphyc.c index a98c911cc37a..5bb9647b078f 100644 --- a/drivers/phy/st/phy-stm32-usbphyc.c +++ b/drivers/phy/st/phy-stm32-usbphyc.c @@ -710,6 +710,8 @@ static int stm32_usbphyc_probe(struct platform_device *pdev) ret = of_property_read_u32(child, "reg", &index); if (ret || index > usbphyc->nphys) { dev_err(&phy->dev, "invalid reg property: %d\n", ret); + if (!ret) + ret = -EINVAL; goto put_child; } diff --git a/drivers/phy/sunplus/phy-sunplus-usb2.c b/drivers/phy/sunplus/phy-sunplus-usb2.c index b932087c55b2..e827b79f6d49 100644 --- a/drivers/phy/sunplus/phy-sunplus-usb2.c +++ b/drivers/phy/sunplus/phy-sunplus-usb2.c @@ -256,8 +256,8 @@ static int sp_usb_phy_probe(struct platform_device *pdev) usbphy->moon4_res_mem = platform_get_resource_byname(pdev, IORESOURCE_MEM, "moon4"); usbphy->moon4_regs = devm_ioremap(&pdev->dev, usbphy->moon4_res_mem->start, resource_size(usbphy->moon4_res_mem)); - if (IS_ERR(usbphy->moon4_regs)) - return PTR_ERR(usbphy->moon4_regs); + if (!usbphy->moon4_regs) + return -ENOMEM; usbphy->phy_clk = devm_clk_get(&pdev->dev, NULL); if (IS_ERR(usbphy->phy_clk)) diff --git a/drivers/phy/tegra/xusb.c b/drivers/phy/tegra/xusb.c index 95091876c422..dce45fbbd699 100644 --- a/drivers/phy/tegra/xusb.c +++ b/drivers/phy/tegra/xusb.c @@ -1461,8 +1461,14 @@ EXPORT_SYMBOL_GPL(tegra_phy_xusb_utmi_port_reset); void tegra_phy_xusb_utmi_pad_power_on(struct phy *phy) { - struct tegra_xusb_lane *lane = phy_get_drvdata(phy); - struct tegra_xusb_padctl *padctl = lane->pad->padctl; + struct tegra_xusb_lane *lane; + struct tegra_xusb_padctl *padctl; + + if (!phy) + return; + + lane = phy_get_drvdata(phy); + padctl = lane->pad->padctl; if (padctl->soc->ops->utmi_pad_power_on) padctl->soc->ops->utmi_pad_power_on(phy); @@ -1471,8 +1477,14 @@ EXPORT_SYMBOL_GPL(tegra_phy_xusb_utmi_pad_power_on); void tegra_phy_xusb_utmi_pad_power_down(struct phy *phy) { - struct tegra_xusb_lane *lane = phy_get_drvdata(phy); - struct tegra_xusb_padctl *padctl = lane->pad->padctl; + struct tegra_xusb_lane *lane; + struct tegra_xusb_padctl *padctl; + + if (!phy) + return; + + lane = phy_get_drvdata(phy); + padctl = lane->pad->padctl; if (padctl->soc->ops->utmi_pad_power_down) padctl->soc->ops->utmi_pad_power_down(phy); diff --git a/drivers/platform/x86/hp-wmi.c b/drivers/platform/x86/hp-wmi.c index 627a6d0eaf83..12449038bed1 100644 --- a/drivers/platform/x86/hp-wmi.c +++ b/drivers/platform/x86/hp-wmi.c @@ -1300,8 +1300,16 @@ static int __init hp_wmi_bios_setup(struct platform_device *device) wwan_rfkill = NULL; rfkill2_count = 0; - if (hp_wmi_rfkill_setup(device)) - hp_wmi_rfkill2_setup(device); + /* + * In pre-2009 BIOS, command 1Bh return 0x4 to indicate that + * BIOS no longer controls the power for the wireless + * devices. All features supported by this command will no + * longer be supported. + */ + if (!hp_wmi_bios_2009_later()) { + if (hp_wmi_rfkill_setup(device)) + hp_wmi_rfkill2_setup(device); + } err = hp_wmi_hwmon_init(); diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c index abd0c81d62c4..33b3dfdd1b08 100644 --- a/drivers/platform/x86/ideapad-laptop.c +++ b/drivers/platform/x86/ideapad-laptop.c @@ -1533,6 +1533,24 @@ static const struct dmi_system_id hw_rfkill_list[] = { {} }; +static const struct dmi_system_id no_touchpad_switch_list[] = { + { + .ident = "Lenovo Yoga 3 Pro 1370", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo YOGA 3"), + }, + }, + { + .ident = "ZhaoYang K4e-IML", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ZhaoYang K4e-IML"), + }, + }, + {} +}; + static void ideapad_check_features(struct ideapad_private *priv) { acpi_handle handle = priv->adev->handle; @@ -1541,7 +1559,12 @@ static void ideapad_check_features(struct ideapad_private *priv) priv->features.hw_rfkill_switch = dmi_check_system(hw_rfkill_list); /* Most ideapads with ELAN0634 touchpad don't use EC touchpad switch */ - priv->features.touchpad_ctrl_via_ec = !acpi_dev_present("ELAN0634", NULL, -1); + if (acpi_dev_present("ELAN0634", NULL, -1)) + priv->features.touchpad_ctrl_via_ec = 0; + else if (dmi_check_system(no_touchpad_switch_list)) + priv->features.touchpad_ctrl_via_ec = 0; + else + priv->features.touchpad_ctrl_via_ec = 1; if (!read_ec_data(handle, VPCCMD_R_FAN, &val)) priv->features.fan_mode = true; diff --git a/drivers/platform/x86/intel/hid.c b/drivers/platform/x86/intel/hid.c index 79cff1fc675c..b6313ecd190c 100644 --- a/drivers/platform/x86/intel/hid.c +++ b/drivers/platform/x86/intel/hid.c @@ -27,6 +27,9 @@ static const struct acpi_device_id intel_hid_ids[] = { {"INTC1051", 0}, {"INTC1054", 0}, {"INTC1070", 0}, + {"INTC1076", 0}, + {"INTC1077", 0}, + {"INTC1078", 0}, {"", 0}, }; MODULE_DEVICE_TABLE(acpi, intel_hid_ids); diff --git a/drivers/platform/x86/intel/pmt/class.c b/drivers/platform/x86/intel/pmt/class.c index 53d7fd2943b4..46598dcb634a 100644 --- a/drivers/platform/x86/intel/pmt/class.c +++ b/drivers/platform/x86/intel/pmt/class.c @@ -9,6 +9,7 @@ */ #include <linux/kernel.h> +#include <linux/io-64-nonatomic-lo-hi.h> #include <linux/module.h> #include <linux/mm.h> #include <linux/pci.h> @@ -19,6 +20,7 @@ #define PMT_XA_START 0 #define PMT_XA_MAX INT_MAX #define PMT_XA_LIMIT XA_LIMIT(PMT_XA_START, PMT_XA_MAX) +#define GUID_SPR_PUNIT 0x9956f43f bool intel_pmt_is_early_client_hw(struct device *dev) { @@ -33,6 +35,29 @@ bool intel_pmt_is_early_client_hw(struct device *dev) } EXPORT_SYMBOL_GPL(intel_pmt_is_early_client_hw); +static inline int +pmt_memcpy64_fromio(void *to, const u64 __iomem *from, size_t count) +{ + int i, remain; + u64 *buf = to; + + if (!IS_ALIGNED((unsigned long)from, 8)) + return -EFAULT; + + for (i = 0; i < count/8; i++) + buf[i] = readq(&from[i]); + + /* Copy any remaining bytes */ + remain = count % 8; + if (remain) { + u64 tmp = readq(&from[i]); + + memcpy(&buf[i], &tmp, remain); + } + + return count; +} + /* * sysfs */ @@ -54,7 +79,11 @@ intel_pmt_read(struct file *filp, struct kobject *kobj, if (count > entry->size - off) count = entry->size - off; - memcpy_fromio(buf, entry->base + off, count); + if (entry->guid == GUID_SPR_PUNIT) + /* PUNIT on SPR only supports aligned 64-bit read */ + count = pmt_memcpy64_fromio(buf, entry->base + off, count); + else + memcpy_fromio(buf, entry->base + off, count); return count; } diff --git a/drivers/platform/x86/p2sb.c b/drivers/platform/x86/p2sb.c index 384d0962ae93..1cf2471d54dd 100644 --- a/drivers/platform/x86/p2sb.c +++ b/drivers/platform/x86/p2sb.c @@ -19,26 +19,23 @@ #define P2SBC 0xe0 #define P2SBC_HIDE BIT(8) +#define P2SB_DEVFN_DEFAULT PCI_DEVFN(31, 1) + static const struct x86_cpu_id p2sb_cpu_ids[] = { X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT, PCI_DEVFN(13, 0)), - X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_D, PCI_DEVFN(31, 1)), - X86_MATCH_INTEL_FAM6_MODEL(ATOM_SILVERMONT_D, PCI_DEVFN(31, 1)), - X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE, PCI_DEVFN(31, 1)), - X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE_L, PCI_DEVFN(31, 1)), - X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE, PCI_DEVFN(31, 1)), - X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_L, PCI_DEVFN(31, 1)), {} }; static int p2sb_get_devfn(unsigned int *devfn) { + unsigned int fn = P2SB_DEVFN_DEFAULT; const struct x86_cpu_id *id; id = x86_match_cpu(p2sb_cpu_ids); - if (!id) - return -ENODEV; + if (id) + fn = (unsigned int)id->driver_data; - *devfn = (unsigned int)id->driver_data; + *devfn = fn; return 0; } diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c index bc97bfa8e8a6..baae3120efd0 100644 --- a/drivers/platform/x86/touchscreen_dmi.c +++ b/drivers/platform/x86/touchscreen_dmi.c @@ -770,6 +770,22 @@ static const struct ts_dmi_data predia_basic_data = { .properties = predia_basic_props, }; +static const struct property_entry rca_cambio_w101_v2_props[] = { + PROPERTY_ENTRY_U32("touchscreen-min-x", 4), + PROPERTY_ENTRY_U32("touchscreen-min-y", 20), + PROPERTY_ENTRY_U32("touchscreen-size-x", 1644), + PROPERTY_ENTRY_U32("touchscreen-size-y", 874), + PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), + PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-rca-cambio-w101-v2.fw"), + PROPERTY_ENTRY_U32("silead,max-fingers", 10), + { } +}; + +static const struct ts_dmi_data rca_cambio_w101_v2_data = { + .acpi_name = "MSSL1680:00", + .properties = rca_cambio_w101_v2_props, +}; + static const struct property_entry rwc_nanote_p8_props[] = { PROPERTY_ENTRY_U32("touchscreen-min-y", 46), PROPERTY_ENTRY_U32("touchscreen-size-x", 1728), @@ -1410,6 +1426,15 @@ const struct dmi_system_id touchscreen_dmi_table[] = { }, }, { + /* RCA Cambio W101 v2 */ + /* https://github.com/onitake/gsl-firmware/discussions/193 */ + .driver_data = (void *)&rca_cambio_w101_v2_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "RCA"), + DMI_MATCH(DMI_PRODUCT_NAME, "W101SA23T1"), + }, + }, + { /* RWC NANOTE P8 */ .driver_data = (void *)&rwc_nanote_p8_data, .matches = { diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c index 51cae72bb6db..62d4d29e7c05 100644 --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -131,10 +131,7 @@ static int ptp_clock_adjtime(struct posix_clock *pc, struct __kernel_timex *tx) long ppb = scaled_ppm_to_ppb(tx->freq); if (ppb > ops->max_adj || ppb < -ops->max_adj) return -ERANGE; - if (ops->adjfine) - err = ops->adjfine(ops, tx->freq); - else - err = ops->adjfreq(ops, ppb); + err = ops->adjfine(ops, tx->freq); ptp->dialed_frequency = tx->freq; } else if (tx->modes & ADJ_OFFSET) { if (ops->adjphase) { diff --git a/drivers/ptp/ptp_dte.c b/drivers/ptp/ptp_dte.c index 8641fd060491..7cc5a00e625b 100644 --- a/drivers/ptp/ptp_dte.c +++ b/drivers/ptp/ptp_dte.c @@ -134,8 +134,9 @@ static s64 dte_read_nco_with_ovf(struct ptp_dte *ptp_dte) return ns; } -static int ptp_dte_adjfreq(struct ptp_clock_info *ptp, s32 ppb) +static int ptp_dte_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) { + s32 ppb = scaled_ppm_to_ppb(scaled_ppm); u32 nco_incr; unsigned long flags; struct ptp_dte *ptp_dte = container_of(ptp, struct ptp_dte, caps); @@ -219,7 +220,7 @@ static const struct ptp_clock_info ptp_dte_caps = { .n_ext_ts = 0, .n_pins = 0, .pps = 0, - .adjfreq = ptp_dte_adjfreq, + .adjfine = ptp_dte_adjfine, .adjtime = ptp_dte_adjtime, .gettime64 = ptp_dte_gettime, .settime64 = ptp_dte_settime, diff --git a/drivers/ptp/ptp_pch.c b/drivers/ptp/ptp_pch.c index 7d4da9e605ef..33355d5eb033 100644 --- a/drivers/ptp/ptp_pch.c +++ b/drivers/ptp/ptp_pch.c @@ -336,24 +336,13 @@ static irqreturn_t isr(int irq, void *priv) * PTP clock operations */ -static int ptp_pch_adjfreq(struct ptp_clock_info *ptp, s32 ppb) +static int ptp_pch_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) { - u64 adj; - u32 diff, addend; - int neg_adj = 0; + u32 addend; struct pch_dev *pch_dev = container_of(ptp, struct pch_dev, caps); struct pch_ts_regs __iomem *regs = pch_dev->regs; - if (ppb < 0) { - neg_adj = 1; - ppb = -ppb; - } - addend = DEFAULT_ADDEND; - adj = addend; - adj *= ppb; - diff = div_u64(adj, 1000000000ULL); - - addend = neg_adj ? addend - diff : addend + diff; + addend = adjust_by_scaled_ppm(DEFAULT_ADDEND, scaled_ppm); iowrite32(addend, ®s->addend); @@ -440,7 +429,7 @@ static const struct ptp_clock_info ptp_pch_caps = { .n_ext_ts = N_EXT_TS, .n_pins = 0, .pps = 0, - .adjfreq = ptp_pch_adjfreq, + .adjfine = ptp_pch_adjfine, .adjtime = ptp_pch_adjtime, .gettime64 = ptp_pch_gettime, .settime64 = ptp_pch_settime, diff --git a/drivers/s390/net/ctcm_main.c b/drivers/s390/net/ctcm_main.c index 37b551bd43bf..bdfab9ea0046 100644 --- a/drivers/s390/net/ctcm_main.c +++ b/drivers/s390/net/ctcm_main.c @@ -825,16 +825,9 @@ done: /* * Start transmission of a packet. * Called from generic network device layer. - * - * skb Pointer to buffer containing the packet. - * dev Pointer to interface struct. - * - * returns 0 if packet consumed, !0 if packet rejected. - * Note: If we return !0, then the packet is free'd by - * the generic network layer. */ /* first merge version - leaving both functions separated */ -static int ctcm_tx(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t ctcm_tx(struct sk_buff *skb, struct net_device *dev) { struct ctcm_priv *priv = dev->ml_priv; @@ -877,7 +870,7 @@ static int ctcm_tx(struct sk_buff *skb, struct net_device *dev) } /* unmerged MPC variant of ctcm_tx */ -static int ctcmpc_tx(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t ctcmpc_tx(struct sk_buff *skb, struct net_device *dev) { int len = 0; struct ctcm_priv *priv = dev->ml_priv; diff --git a/drivers/s390/net/lcs.c b/drivers/s390/net/lcs.c index 84c8981317b4..38f312664ce7 100644 --- a/drivers/s390/net/lcs.c +++ b/drivers/s390/net/lcs.c @@ -1519,9 +1519,8 @@ lcs_txbuffer_cb(struct lcs_channel *channel, struct lcs_buffer *buffer) /* * Packet transmit function called by network stack */ -static int -__lcs_start_xmit(struct lcs_card *card, struct sk_buff *skb, - struct net_device *dev) +static netdev_tx_t __lcs_start_xmit(struct lcs_card *card, struct sk_buff *skb, + struct net_device *dev) { struct lcs_header *header; int rc = NETDEV_TX_OK; @@ -1582,8 +1581,7 @@ out: return rc; } -static int -lcs_start_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t lcs_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct lcs_card *card; int rc; diff --git a/drivers/s390/net/netiucv.c b/drivers/s390/net/netiucv.c index 65aa0a96c21d..66076cada8ae 100644 --- a/drivers/s390/net/netiucv.c +++ b/drivers/s390/net/netiucv.c @@ -1248,15 +1248,8 @@ static int netiucv_close(struct net_device *dev) /* * Start transmission of a packet. * Called from generic network device layer. - * - * @param skb Pointer to buffer containing the packet. - * @param dev Pointer to interface struct. - * - * @return 0 if packet consumed, !0 if packet rejected. - * Note: If we return !0, then the packet is free'd by - * the generic network layer. */ -static int netiucv_tx(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t netiucv_tx(struct sk_buff *skb, struct net_device *dev) { struct netiucv_priv *privptr = netdev_priv(dev); int rc; diff --git a/drivers/soc/imx/imx93-pd.c b/drivers/soc/imx/imx93-pd.c index 1f3d7039c1de..4d235c8c4924 100644 --- a/drivers/soc/imx/imx93-pd.c +++ b/drivers/soc/imx/imx93-pd.c @@ -135,11 +135,24 @@ static int imx93_pd_probe(struct platform_device *pdev) ret = pm_genpd_init(&domain->genpd, NULL, domain->init_off); if (ret) - return ret; + goto err_clk_unprepare; platform_set_drvdata(pdev, domain); - return of_genpd_add_provider_simple(np, &domain->genpd); + ret = of_genpd_add_provider_simple(np, &domain->genpd); + if (ret) + goto err_genpd_remove; + + return 0; + +err_genpd_remove: + pm_genpd_remove(&domain->genpd); + +err_clk_unprepare: + if (!domain->init_off) + clk_bulk_disable_unprepare(domain->num_clks, domain->clks); + + return ret; } static const struct of_device_id imx93_pd_ids[] = { diff --git a/drivers/soundwire/intel.c b/drivers/soundwire/intel.c index 244209358784..8c76541d553f 100644 --- a/drivers/soundwire/intel.c +++ b/drivers/soundwire/intel.c @@ -1513,6 +1513,7 @@ static int intel_link_probe(struct auxiliary_device *auxdev, bus->link_id = auxdev->id; bus->dev_num_ida_min = INTEL_DEV_NUM_IDA_MIN; + bus->clk_stop_timeout = 1; sdw_cdns_probe(cdns); diff --git a/drivers/soundwire/qcom.c b/drivers/soundwire/qcom.c index b33d5db494a5..cee2b2223141 100644 --- a/drivers/soundwire/qcom.c +++ b/drivers/soundwire/qcom.c @@ -344,6 +344,9 @@ static int qcom_swrm_cmd_fifo_wr_cmd(struct qcom_swrm_ctrl *swrm, u8 cmd_data, if (swrm_wait_for_wr_fifo_avail(swrm)) return SDW_CMD_FAIL_OTHER; + if (cmd_id == SWR_BROADCAST_CMD_ID) + reinit_completion(&swrm->broadcast); + /* Its assumed that write is okay as we do not get any status back */ swrm->reg_write(swrm, SWRM_CMD_FIFO_WR_CMD, val); @@ -377,6 +380,12 @@ static int qcom_swrm_cmd_fifo_rd_cmd(struct qcom_swrm_ctrl *swrm, val = swrm_get_packed_reg_val(&swrm->rcmd_id, len, dev_addr, reg_addr); + /* + * Check for outstanding cmd wrt. write fifo depth to avoid + * overflow as read will also increase write fifo cnt. + */ + swrm_wait_for_wr_fifo_avail(swrm); + /* wait for FIFO RD to complete to avoid overflow */ usleep_range(100, 105); swrm->reg_write(swrm, SWRM_CMD_FIFO_RD_CMD, val); diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 4ec18ceb2f21..18374a6d05bd 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -289,8 +289,10 @@ static void prelim_release(struct preftree *preftree) struct prelim_ref *ref, *next_ref; rbtree_postorder_for_each_entry_safe(ref, next_ref, - &preftree->root.rb_root, rbnode) + &preftree->root.rb_root, rbnode) { + free_inode_elem_list(ref->inode_list); free_pref(ref); + } preftree->root = RB_ROOT_CACHED; preftree->count = 0; @@ -648,6 +650,18 @@ unode_aux_to_inode_list(struct ulist_node *node) return (struct extent_inode_elem *)(uintptr_t)node->aux; } +static void free_leaf_list(struct ulist *ulist) +{ + struct ulist_node *node; + struct ulist_iterator uiter; + + ULIST_ITER_INIT(&uiter); + while ((node = ulist_next(ulist, &uiter))) + free_inode_elem_list(unode_aux_to_inode_list(node)); + + ulist_free(ulist); +} + /* * We maintain three separate rbtrees: one for direct refs, one for * indirect refs which have a key, and one for indirect refs which do not @@ -762,7 +776,11 @@ static int resolve_indirect_refs(struct btrfs_fs_info *fs_info, cond_resched(); } out: - ulist_free(parents); + /* + * We may have inode lists attached to refs in the parents ulist, so we + * must free them before freeing the ulist and its refs. + */ + free_leaf_list(parents); return ret; } @@ -1368,6 +1386,12 @@ again: if (ret < 0) goto out; ref->inode_list = eie; + /* + * We transferred the list ownership to the ref, + * so set to NULL to avoid a double free in case + * an error happens after this. + */ + eie = NULL; } ret = ulist_add_merge_ptr(refs, ref->parent, ref->inode_list, @@ -1393,6 +1417,14 @@ again: eie->next = ref->inode_list; } eie = NULL; + /* + * We have transferred the inode list ownership from + * this ref to the ref we added to the 'refs' ulist. + * So set this ref's inode list to NULL to avoid + * use-after-free when our caller uses it or double + * frees in case an error happens before we return. + */ + ref->inode_list = NULL; } cond_resched(); } @@ -1409,24 +1441,6 @@ out: return ret; } -static void free_leaf_list(struct ulist *blocks) -{ - struct ulist_node *node = NULL; - struct extent_inode_elem *eie; - struct ulist_iterator uiter; - - ULIST_ITER_INIT(&uiter); - while ((node = ulist_next(blocks, &uiter))) { - if (!node->aux) - continue; - eie = unode_aux_to_inode_list(node); - free_inode_elem_list(eie); - node->aux = 0; - } - - ulist_free(blocks); -} - /* * Finds all leafs with a reference to the specified combination of bytenr and * offset. key_list_head will point to a list of corresponding keys (caller must diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index b39b339fbf96..a9543f01184c 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -114,6 +114,22 @@ noinline void btrfs_release_path(struct btrfs_path *p) } /* + * We want the transaction abort to print stack trace only for errors where the + * cause could be a bug, eg. due to ENOSPC, and not for common errors that are + * caused by external factors. + */ +bool __cold abort_should_print_stack(int errno) +{ + switch (errno) { + case -EIO: + case -EROFS: + case -ENOMEM: + return false; + } + return true; +} + +/* * safely gets a reference on the root node of a tree. A lock * is not taken, so a concurrent writer may put a different node * at the root of the tree. See btrfs_lock_root_node for the diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 727595eee973..9e6d48ff4597 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3462,7 +3462,10 @@ ssize_t btrfs_encoded_read(struct kiocb *iocb, struct iov_iter *iter, ssize_t btrfs_do_encoded_write(struct kiocb *iocb, struct iov_iter *from, const struct btrfs_ioctl_encoded_io_args *encoded); -ssize_t btrfs_dio_rw(struct kiocb *iocb, struct iov_iter *iter, size_t done_before); +ssize_t btrfs_dio_read(struct kiocb *iocb, struct iov_iter *iter, + size_t done_before); +struct iomap_dio *btrfs_dio_write(struct kiocb *iocb, struct iov_iter *iter, + size_t done_before); extern const struct dentry_operations btrfs_dentry_operations; @@ -3793,9 +3796,11 @@ void __btrfs_abort_transaction(struct btrfs_trans_handle *trans, const char *function, unsigned int line, int errno, bool first_hit); +bool __cold abort_should_print_stack(int errno); + /* * Call btrfs_abort_transaction as early as possible when an error condition is - * detected, that way the exact line number is reported. + * detected, that way the exact stack trace is reported for some errors. */ #define btrfs_abort_transaction(trans, errno) \ do { \ @@ -3804,10 +3809,11 @@ do { \ if (!test_and_set_bit(BTRFS_FS_STATE_TRANS_ABORTED, \ &((trans)->fs_info->fs_state))) { \ first = true; \ - if ((errno) != -EIO && (errno) != -EROFS) { \ - WARN(1, KERN_DEBUG \ + if (WARN(abort_should_print_stack(errno), \ + KERN_DEBUG \ "BTRFS: Transaction aborted (error %d)\n", \ - (errno)); \ + (errno))) { \ + /* Stack trace printed. */ \ } else { \ btrfs_debug((trans)->fs_info, \ "Transaction aborted (error %d)", \ diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 4b28263c3d32..d99bf7c64611 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2551,7 +2551,9 @@ static int btrfs_read_roots(struct btrfs_fs_info *fs_info) fs_info->dev_root = root; } /* Initialize fs_info for all devices in any case */ - btrfs_init_devices_late(fs_info); + ret = btrfs_init_devices_late(fs_info); + if (ret) + goto out; /* * This tree can share blocks with some other fs tree during relocation diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 176b432035ae..d01631d47806 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1598,14 +1598,19 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb, write_bytes); else btrfs_check_nocow_unlock(BTRFS_I(inode)); + + if (nowait && ret == -ENOSPC) + ret = -EAGAIN; break; } release_bytes = reserve_bytes; again: ret = balance_dirty_pages_ratelimited_flags(inode->i_mapping, bdp_flags); - if (ret) + if (ret) { + btrfs_delalloc_release_extents(BTRFS_I(inode), reserve_bytes); break; + } /* * This is going to setup the pages array with the number of @@ -1765,6 +1770,7 @@ static ssize_t btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from) loff_t endbyte; ssize_t err; unsigned int ilock_flags = 0; + struct iomap_dio *dio; if (iocb->ki_flags & IOCB_NOWAIT) ilock_flags |= BTRFS_ILOCK_TRY; @@ -1825,11 +1831,22 @@ relock: * So here we disable page faults in the iov_iter and then retry if we * got -EFAULT, faulting in the pages before the retry. */ -again: from->nofault = true; - err = btrfs_dio_rw(iocb, from, written); + dio = btrfs_dio_write(iocb, from, written); from->nofault = false; + /* + * iomap_dio_complete() will call btrfs_sync_file() if we have a dsync + * iocb, and that needs to lock the inode. So unlock it before calling + * iomap_dio_complete() to avoid a deadlock. + */ + btrfs_inode_unlock(inode, ilock_flags); + + if (IS_ERR_OR_NULL(dio)) + err = PTR_ERR_OR_ZERO(dio); + else + err = iomap_dio_complete(dio); + /* No increment (+=) because iomap returns a cumulative value. */ if (err > 0) written = err; @@ -1855,12 +1872,10 @@ again: } else { fault_in_iov_iter_readable(from, left); prev_left = left; - goto again; + goto relock; } } - btrfs_inode_unlock(inode, ilock_flags); - /* * If 'err' is -ENOTBLK or we have not written all data, then it means * we must fallback to buffered IO. @@ -4035,7 +4050,7 @@ again: */ pagefault_disable(); to->nofault = true; - ret = btrfs_dio_rw(iocb, to, read); + ret = btrfs_dio_read(iocb, to, read); to->nofault = false; pagefault_enable(); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index b0807c59e321..0e516aefbf51 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -7980,7 +7980,7 @@ static void btrfs_submit_direct(const struct iomap_iter *iter, */ status = BLK_STS_RESOURCE; dip->csums = kcalloc(nr_sectors, fs_info->csum_size, GFP_NOFS); - if (!dip) + if (!dip->csums) goto out_err; status = btrfs_lookup_bio_sums(inode, dio_bio, dip->csums); @@ -8078,13 +8078,21 @@ static const struct iomap_dio_ops btrfs_dio_ops = { .bio_set = &btrfs_dio_bioset, }; -ssize_t btrfs_dio_rw(struct kiocb *iocb, struct iov_iter *iter, size_t done_before) +ssize_t btrfs_dio_read(struct kiocb *iocb, struct iov_iter *iter, size_t done_before) { struct btrfs_dio_data data; return iomap_dio_rw(iocb, iter, &btrfs_dio_iomap_ops, &btrfs_dio_ops, - IOMAP_DIO_PARTIAL | IOMAP_DIO_NOSYNC, - &data, done_before); + IOMAP_DIO_PARTIAL, &data, done_before); +} + +struct iomap_dio *btrfs_dio_write(struct kiocb *iocb, struct iov_iter *iter, + size_t done_before) +{ + struct btrfs_dio_data data; + + return __iomap_dio_rw(iocb, iter, &btrfs_dio_iomap_ops, &btrfs_dio_ops, + IOMAP_DIO_PARTIAL, &data, done_before); } static int btrfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index f260c53829e5..196c4c6ed1ed 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -2672,17 +2672,11 @@ static int scrub_extent(struct scrub_ctx *sctx, struct map_lookup *map, u8 csum[BTRFS_CSUM_SIZE]; u32 blocksize; - /* - * Block size determines how many scrub_block will be allocated. Here - * we use BTRFS_STRIPE_LEN (64KiB) as default limit, so we won't - * allocate too many scrub_block, while still won't cause too large - * bios for large extents. - */ if (flags & BTRFS_EXTENT_FLAG_DATA) { if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) blocksize = map->stripe_len; else - blocksize = BTRFS_STRIPE_LEN; + blocksize = sctx->fs_info->sectorsize; spin_lock(&sctx->stat_lock); sctx->stat.data_extents_scrubbed++; sctx->stat.data_bytes_scrubbed += len; @@ -3917,7 +3911,6 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, if (sctx->is_dev_replace && btrfs_is_zoned(fs_info)) { if (!test_bit(BLOCK_GROUP_FLAG_TO_COPY, &cache->runtime_flags)) { - spin_unlock(&cache->lock); btrfs_put_block_group(cache); goto skip; } diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c index 9c478fa256f6..d43cb5242fec 100644 --- a/fs/btrfs/tests/btrfs-tests.c +++ b/fs/btrfs/tests/btrfs-tests.c @@ -200,7 +200,7 @@ void btrfs_free_dummy_fs_info(struct btrfs_fs_info *fs_info) void btrfs_free_dummy_root(struct btrfs_root *root) { - if (!root) + if (IS_ERR_OR_NULL(root)) return; /* Will be freed by btrfs_free_fs_roots */ if (WARN_ON(test_bit(BTRFS_ROOT_IN_RADIX, &root->state))) diff --git a/fs/btrfs/tests/qgroup-tests.c b/fs/btrfs/tests/qgroup-tests.c index eee1e4459541..63676ea19f29 100644 --- a/fs/btrfs/tests/qgroup-tests.c +++ b/fs/btrfs/tests/qgroup-tests.c @@ -225,20 +225,20 @@ static int test_no_shared_qgroup(struct btrfs_root *root, */ ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots, false); if (ret) { - ulist_free(old_roots); test_err("couldn't find old roots: %d", ret); return ret; } ret = insert_normal_tree_ref(root, nodesize, nodesize, 0, BTRFS_FS_TREE_OBJECTID); - if (ret) + if (ret) { + ulist_free(old_roots); return ret; + } ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots, false); if (ret) { ulist_free(old_roots); - ulist_free(new_roots); test_err("couldn't find old roots: %d", ret); return ret; } @@ -250,29 +250,31 @@ static int test_no_shared_qgroup(struct btrfs_root *root, return ret; } + /* btrfs_qgroup_account_extent() always frees the ulists passed to it. */ + old_roots = NULL; + new_roots = NULL; + if (btrfs_verify_qgroup_counts(fs_info, BTRFS_FS_TREE_OBJECTID, nodesize, nodesize)) { test_err("qgroup counts didn't match expected values"); return -EINVAL; } - old_roots = NULL; - new_roots = NULL; ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots, false); if (ret) { - ulist_free(old_roots); test_err("couldn't find old roots: %d", ret); return ret; } ret = remove_extent_item(root, nodesize, nodesize); - if (ret) + if (ret) { + ulist_free(old_roots); return -EINVAL; + } ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots, false); if (ret) { ulist_free(old_roots); - ulist_free(new_roots); test_err("couldn't find old roots: %d", ret); return ret; } @@ -322,20 +324,20 @@ static int test_multiple_refs(struct btrfs_root *root, ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots, false); if (ret) { - ulist_free(old_roots); test_err("couldn't find old roots: %d", ret); return ret; } ret = insert_normal_tree_ref(root, nodesize, nodesize, 0, BTRFS_FS_TREE_OBJECTID); - if (ret) + if (ret) { + ulist_free(old_roots); return ret; + } ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots, false); if (ret) { ulist_free(old_roots); - ulist_free(new_roots); test_err("couldn't find old roots: %d", ret); return ret; } @@ -355,20 +357,20 @@ static int test_multiple_refs(struct btrfs_root *root, ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots, false); if (ret) { - ulist_free(old_roots); test_err("couldn't find old roots: %d", ret); return ret; } ret = add_tree_ref(root, nodesize, nodesize, 0, BTRFS_FIRST_FREE_OBJECTID); - if (ret) + if (ret) { + ulist_free(old_roots); return ret; + } ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots, false); if (ret) { ulist_free(old_roots); - ulist_free(new_roots); test_err("couldn't find old roots: %d", ret); return ret; } @@ -394,20 +396,20 @@ static int test_multiple_refs(struct btrfs_root *root, ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots, false); if (ret) { - ulist_free(old_roots); test_err("couldn't find old roots: %d", ret); return ret; } ret = remove_extent_ref(root, nodesize, nodesize, 0, BTRFS_FIRST_FREE_OBJECTID); - if (ret) + if (ret) { + ulist_free(old_roots); return ret; + } ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots, false); if (ret) { ulist_free(old_roots); - ulist_free(new_roots); test_err("couldn't find old roots: %d", ret); return ret; } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index a8d4bc6a1937..635f45f1a2ef 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1011,6 +1011,18 @@ static struct btrfs_fs_devices *clone_fs_devices(struct btrfs_fs_devices *orig) rcu_assign_pointer(device->name, name); } + if (orig_dev->zone_info) { + struct btrfs_zoned_device_info *zone_info; + + zone_info = btrfs_clone_dev_zone_info(orig_dev); + if (!zone_info) { + btrfs_free_device(device); + ret = -ENOMEM; + goto error; + } + device->zone_info = zone_info; + } + list_add(&device->dev_list, &fs_devices->devices); device->fs_devices = fs_devices; fs_devices->num_devices++; @@ -6918,18 +6930,18 @@ static bool dev_args_match_fs_devices(const struct btrfs_dev_lookup_args *args, static bool dev_args_match_device(const struct btrfs_dev_lookup_args *args, const struct btrfs_device *device) { - ASSERT((args->devid != (u64)-1) || args->missing); + if (args->missing) { + if (test_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state) && + !device->bdev) + return true; + return false; + } - if ((args->devid != (u64)-1) && device->devid != args->devid) + if (device->devid != args->devid) return false; if (args->uuid && memcmp(device->uuid, args->uuid, BTRFS_UUID_SIZE) != 0) return false; - if (!args->missing) - return true; - if (test_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state) && - !device->bdev) - return true; - return false; + return true; } /* @@ -7744,10 +7756,11 @@ error: return ret; } -void btrfs_init_devices_late(struct btrfs_fs_info *fs_info) +int btrfs_init_devices_late(struct btrfs_fs_info *fs_info) { struct btrfs_fs_devices *fs_devices = fs_info->fs_devices, *seed_devs; struct btrfs_device *device; + int ret = 0; fs_devices->fs_info = fs_info; @@ -7756,12 +7769,18 @@ void btrfs_init_devices_late(struct btrfs_fs_info *fs_info) device->fs_info = fs_info; list_for_each_entry(seed_devs, &fs_devices->seed_list, seed_list) { - list_for_each_entry(device, &seed_devs->devices, dev_list) + list_for_each_entry(device, &seed_devs->devices, dev_list) { device->fs_info = fs_info; + ret = btrfs_get_dev_zone_info(device, false); + if (ret) + break; + } seed_devs->fs_info = fs_info; } mutex_unlock(&fs_devices->device_list_mutex); + + return ret; } static u64 btrfs_dev_stats_value(const struct extent_buffer *eb, diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index f8b668dc8bf8..099def5613b8 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -671,7 +671,7 @@ int find_free_dev_extent(struct btrfs_device *device, u64 num_bytes, void btrfs_dev_stat_inc_and_print(struct btrfs_device *dev, int index); int btrfs_get_dev_stats(struct btrfs_fs_info *fs_info, struct btrfs_ioctl_get_dev_stats *stats); -void btrfs_init_devices_late(struct btrfs_fs_info *fs_info); +int btrfs_init_devices_late(struct btrfs_fs_info *fs_info); int btrfs_init_dev_stats(struct btrfs_fs_info *fs_info); int btrfs_run_dev_stats(struct btrfs_trans_handle *trans); void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_device *srcdev); diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index e2d073b08a7d..1912abf6d020 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -639,6 +639,46 @@ void btrfs_destroy_dev_zone_info(struct btrfs_device *device) device->zone_info = NULL; } +struct btrfs_zoned_device_info *btrfs_clone_dev_zone_info(struct btrfs_device *orig_dev) +{ + struct btrfs_zoned_device_info *zone_info; + + zone_info = kmemdup(orig_dev->zone_info, sizeof(*zone_info), GFP_KERNEL); + if (!zone_info) + return NULL; + + zone_info->seq_zones = bitmap_zalloc(zone_info->nr_zones, GFP_KERNEL); + if (!zone_info->seq_zones) + goto out; + + bitmap_copy(zone_info->seq_zones, orig_dev->zone_info->seq_zones, + zone_info->nr_zones); + + zone_info->empty_zones = bitmap_zalloc(zone_info->nr_zones, GFP_KERNEL); + if (!zone_info->empty_zones) + goto out; + + bitmap_copy(zone_info->empty_zones, orig_dev->zone_info->empty_zones, + zone_info->nr_zones); + + zone_info->active_zones = bitmap_zalloc(zone_info->nr_zones, GFP_KERNEL); + if (!zone_info->active_zones) + goto out; + + bitmap_copy(zone_info->active_zones, orig_dev->zone_info->active_zones, + zone_info->nr_zones); + zone_info->zone_cache = NULL; + + return zone_info; + +out: + bitmap_free(zone_info->seq_zones); + bitmap_free(zone_info->empty_zones); + bitmap_free(zone_info->active_zones); + kfree(zone_info); + return NULL; +} + int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos, struct blk_zone *zone) { diff --git a/fs/btrfs/zoned.h b/fs/btrfs/zoned.h index e17462db3a84..8bd16d40b7c6 100644 --- a/fs/btrfs/zoned.h +++ b/fs/btrfs/zoned.h @@ -36,6 +36,7 @@ int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos, int btrfs_get_dev_zone_info_all_devices(struct btrfs_fs_info *fs_info); int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache); void btrfs_destroy_dev_zone_info(struct btrfs_device *device); +struct btrfs_zoned_device_info *btrfs_clone_dev_zone_info(struct btrfs_device *orig_dev); int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info); int btrfs_check_mountopts_zoned(struct btrfs_fs_info *info); int btrfs_sb_log_location_bdev(struct block_device *bdev, int mirror, int rw, @@ -103,6 +104,16 @@ static inline int btrfs_get_dev_zone_info(struct btrfs_device *device, static inline void btrfs_destroy_dev_zone_info(struct btrfs_device *device) { } +/* + * In case the kernel is compiled without CONFIG_BLK_DEV_ZONED we'll never call + * into btrfs_clone_dev_zone_info() so it's safe to return NULL here. + */ +static inline struct btrfs_zoned_device_info *btrfs_clone_dev_zone_info( + struct btrfs_device *orig_dev) +{ + return NULL; +} + static inline int btrfs_check_zoned_mode(const struct btrfs_fs_info *fs_info) { if (!btrfs_is_zoned(fs_info)) diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index d0b9fec111aa..fe220686bba4 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -1143,8 +1143,32 @@ const struct inode_operations cifs_file_inode_ops = { .fiemap = cifs_fiemap, }; +const char *cifs_get_link(struct dentry *dentry, struct inode *inode, + struct delayed_call *done) +{ + char *target_path; + + target_path = kmalloc(PATH_MAX, GFP_KERNEL); + if (!target_path) + return ERR_PTR(-ENOMEM); + + spin_lock(&inode->i_lock); + if (likely(CIFS_I(inode)->symlink_target)) { + strscpy(target_path, CIFS_I(inode)->symlink_target, PATH_MAX); + } else { + kfree(target_path); + target_path = ERR_PTR(-EOPNOTSUPP); + } + spin_unlock(&inode->i_lock); + + if (!IS_ERR(target_path)) + set_delayed_call(done, kfree_link, target_path); + + return target_path; +} + const struct inode_operations cifs_symlink_inode_ops = { - .get_link = simple_get_link, + .get_link = cifs_get_link, .permission = cifs_permission, .listxattr = cifs_listxattr, }; diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 9bde08d44617..4e2ca3c6e5c0 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -215,11 +215,6 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr) kfree(cifs_i->symlink_target); cifs_i->symlink_target = fattr->cf_symlink_target; fattr->cf_symlink_target = NULL; - - if (unlikely(!cifs_i->symlink_target)) - inode->i_link = ERR_PTR(-EOPNOTSUPP); - else - inode->i_link = cifs_i->symlink_target; } spin_unlock(&inode->i_lock); diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index da51ffd02928..3e68d8208cf5 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -400,6 +400,7 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv) { struct smb_hdr *buf = (struct smb_hdr *)buffer; struct smb_com_lock_req *pSMB = (struct smb_com_lock_req *)buf; + struct TCP_Server_Info *pserver; struct cifs_ses *ses; struct cifs_tcon *tcon; struct cifsInodeInfo *pCifsInode; @@ -464,9 +465,12 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv) if (!(pSMB->LockType & LOCKING_ANDX_OPLOCK_RELEASE)) return false; + /* If server is a channel, select the primary channel */ + pserver = CIFS_SERVER_IS_CHAN(srv) ? srv->primary_server : srv; + /* look up tcon based on tid & uid */ spin_lock(&cifs_tcp_ses_lock); - list_for_each_entry(ses, &srv->smb_ses_list, smb_ses_list) { + list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { if (tcon->tid != buf->Tid) continue; diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index a38720477966..572293c18e16 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -135,6 +135,7 @@ static __u32 get_neg_ctxt_len(struct smb2_hdr *hdr, __u32 len, int smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *server) { + struct TCP_Server_Info *pserver; struct smb2_hdr *shdr = (struct smb2_hdr *)buf; struct smb2_pdu *pdu = (struct smb2_pdu *)shdr; int hdr_size = sizeof(struct smb2_hdr); @@ -143,6 +144,9 @@ smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *server) __u32 calc_len; /* calculated length */ __u64 mid; + /* If server is a channel, select the primary channel */ + pserver = CIFS_SERVER_IS_CHAN(server) ? server->primary_server : server; + /* * Add function to do table lookup of StructureSize by command * ie Validate the wct via smb2_struct_sizes table above @@ -155,7 +159,7 @@ smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *server) /* decrypt frame now that it is completely read in */ spin_lock(&cifs_tcp_ses_lock); - list_for_each_entry(iter, &server->smb_ses_list, smb_ses_list) { + list_for_each_entry(iter, &pserver->smb_ses_list, smb_ses_list) { if (iter->Suid == le64_to_cpu(thdr->SessionId)) { ses = iter; break; @@ -608,51 +612,52 @@ smb2_tcon_find_pending_open_lease(struct cifs_tcon *tcon, } static bool -smb2_is_valid_lease_break(char *buffer) +smb2_is_valid_lease_break(char *buffer, struct TCP_Server_Info *server) { struct smb2_lease_break *rsp = (struct smb2_lease_break *)buffer; - struct TCP_Server_Info *server; + struct TCP_Server_Info *pserver; struct cifs_ses *ses; struct cifs_tcon *tcon; struct cifs_pending_open *open; cifs_dbg(FYI, "Checking for lease break\n"); + /* If server is a channel, select the primary channel */ + pserver = CIFS_SERVER_IS_CHAN(server) ? server->primary_server : server; + /* look up tcon based on tid & uid */ spin_lock(&cifs_tcp_ses_lock); - list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) { - list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { - list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { - spin_lock(&tcon->open_file_lock); - cifs_stats_inc( - &tcon->stats.cifs_stats.num_oplock_brks); - if (smb2_tcon_has_lease(tcon, rsp)) { - spin_unlock(&tcon->open_file_lock); - spin_unlock(&cifs_tcp_ses_lock); - return true; - } - open = smb2_tcon_find_pending_open_lease(tcon, - rsp); - if (open) { - __u8 lease_key[SMB2_LEASE_KEY_SIZE]; - struct tcon_link *tlink; - - tlink = cifs_get_tlink(open->tlink); - memcpy(lease_key, open->lease_key, - SMB2_LEASE_KEY_SIZE); - spin_unlock(&tcon->open_file_lock); - spin_unlock(&cifs_tcp_ses_lock); - smb2_queue_pending_open_break(tlink, - lease_key, - rsp->NewLeaseState); - return true; - } + list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { + list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { + spin_lock(&tcon->open_file_lock); + cifs_stats_inc( + &tcon->stats.cifs_stats.num_oplock_brks); + if (smb2_tcon_has_lease(tcon, rsp)) { spin_unlock(&tcon->open_file_lock); + spin_unlock(&cifs_tcp_ses_lock); + return true; + } + open = smb2_tcon_find_pending_open_lease(tcon, + rsp); + if (open) { + __u8 lease_key[SMB2_LEASE_KEY_SIZE]; + struct tcon_link *tlink; + + tlink = cifs_get_tlink(open->tlink); + memcpy(lease_key, open->lease_key, + SMB2_LEASE_KEY_SIZE); + spin_unlock(&tcon->open_file_lock); + spin_unlock(&cifs_tcp_ses_lock); + smb2_queue_pending_open_break(tlink, + lease_key, + rsp->NewLeaseState); + return true; + } + spin_unlock(&tcon->open_file_lock); - if (cached_dir_lease_break(tcon, rsp->LeaseKey)) { - spin_unlock(&cifs_tcp_ses_lock); - return true; - } + if (cached_dir_lease_break(tcon, rsp->LeaseKey)) { + spin_unlock(&cifs_tcp_ses_lock); + return true; } } } @@ -671,6 +676,7 @@ bool smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server) { struct smb2_oplock_break *rsp = (struct smb2_oplock_break *)buffer; + struct TCP_Server_Info *pserver; struct cifs_ses *ses; struct cifs_tcon *tcon; struct cifsInodeInfo *cinode; @@ -684,16 +690,19 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server) if (rsp->StructureSize != smb2_rsp_struct_sizes[SMB2_OPLOCK_BREAK_HE]) { if (le16_to_cpu(rsp->StructureSize) == 44) - return smb2_is_valid_lease_break(buffer); + return smb2_is_valid_lease_break(buffer, server); else return false; } cifs_dbg(FYI, "oplock level 0x%x\n", rsp->OplockLevel); + /* If server is a channel, select the primary channel */ + pserver = CIFS_SERVER_IS_CHAN(server) ? server->primary_server : server; + /* look up tcon based on tid & uid */ spin_lock(&cifs_tcp_ses_lock); - list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { + list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { spin_lock(&tcon->open_file_lock); diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 4f53fa012936..880cd494afea 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -2302,14 +2302,18 @@ static void smb2_is_network_name_deleted(char *buf, struct TCP_Server_Info *server) { struct smb2_hdr *shdr = (struct smb2_hdr *)buf; + struct TCP_Server_Info *pserver; struct cifs_ses *ses; struct cifs_tcon *tcon; if (shdr->Status != STATUS_NETWORK_NAME_DELETED) return; + /* If server is a channel, select the primary channel */ + pserver = CIFS_SERVER_IS_CHAN(server) ? server->primary_server : server; + spin_lock(&cifs_tcp_ses_lock); - list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { + list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { if (tcon->tid == le32_to_cpu(shdr->Id.SyncId.TreeId)) { spin_lock(&tcon->tc_lock); @@ -4264,21 +4268,23 @@ init_sg(int num_rqst, struct smb_rqst *rqst, u8 *sign) static int smb2_get_enc_key(struct TCP_Server_Info *server, __u64 ses_id, int enc, u8 *key) { + struct TCP_Server_Info *pserver; struct cifs_ses *ses; u8 *ses_enc_key; + /* If server is a channel, select the primary channel */ + pserver = CIFS_SERVER_IS_CHAN(server) ? server->primary_server : server; + spin_lock(&cifs_tcp_ses_lock); - list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) { - list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { - if (ses->Suid == ses_id) { - spin_lock(&ses->ses_lock); - ses_enc_key = enc ? ses->smb3encryptionkey : - ses->smb3decryptionkey; - memcpy(key, ses_enc_key, SMB3_ENC_DEC_KEY_SIZE); - spin_unlock(&ses->ses_lock); - spin_unlock(&cifs_tcp_ses_lock); - return 0; - } + list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { + if (ses->Suid == ses_id) { + spin_lock(&ses->ses_lock); + ses_enc_key = enc ? ses->smb3encryptionkey : + ses->smb3decryptionkey; + memcpy(key, ses_enc_key, SMB3_ENC_DEC_KEY_SIZE); + spin_unlock(&ses->ses_lock); + spin_unlock(&cifs_tcp_ses_lock); + return 0; } } spin_unlock(&cifs_tcp_ses_lock); diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c index 8e3f26e6f6b9..381babc1212c 100644 --- a/fs/cifs/smb2transport.c +++ b/fs/cifs/smb2transport.c @@ -77,18 +77,19 @@ static int smb2_get_sign_key(__u64 ses_id, struct TCP_Server_Info *server, u8 *key) { struct cifs_chan *chan; + struct TCP_Server_Info *pserver; struct cifs_ses *ses = NULL; - struct TCP_Server_Info *it = NULL; int i; int rc = 0; spin_lock(&cifs_tcp_ses_lock); - list_for_each_entry(it, &cifs_tcp_ses_list, tcp_ses_list) { - list_for_each_entry(ses, &it->smb_ses_list, smb_ses_list) { - if (ses->Suid == ses_id) - goto found; - } + /* If server is a channel, select the primary channel */ + pserver = CIFS_SERVER_IS_CHAN(server) ? server->primary_server : server; + + list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { + if (ses->Suid == ses_id) + goto found; } cifs_server_dbg(VFS, "%s: Could not find session 0x%llx\n", __func__, ses_id); @@ -136,9 +137,13 @@ out: static struct cifs_ses * smb2_find_smb_ses_unlocked(struct TCP_Server_Info *server, __u64 ses_id) { + struct TCP_Server_Info *pserver; struct cifs_ses *ses; - list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { + /* If server is a channel, select the primary channel */ + pserver = CIFS_SERVER_IS_CHAN(server) ? server->primary_server : server; + + list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { if (ses->Suid != ses_id) continue; ++ses->ses_count; diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c index ef05bfa87798..0f6d0a80467d 100644 --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -1521,6 +1521,7 @@ static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl, struct ext4_iloc iloc; int inode_len, ino, ret, tag = tl->fc_tag; struct ext4_extent_header *eh; + size_t off_gen = offsetof(struct ext4_inode, i_generation); memcpy(&fc_inode, val, sizeof(fc_inode)); @@ -1548,8 +1549,8 @@ static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl, raw_inode = ext4_raw_inode(&iloc); memcpy(raw_inode, raw_fc_inode, offsetof(struct ext4_inode, i_block)); - memcpy(&raw_inode->i_generation, &raw_fc_inode->i_generation, - inode_len - offsetof(struct ext4_inode, i_generation)); + memcpy((u8 *)raw_inode + off_gen, (u8 *)raw_fc_inode + off_gen, + inode_len - off_gen); if (le32_to_cpu(raw_inode->i_flags) & EXT4_EXTENTS_FL) { eh = (struct ext4_extent_header *)(&raw_inode->i_block[0]); if (eh->eh_magic != EXT4_EXT_MAGIC) { diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index ded535535b27..95dfea28bf4e 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -145,9 +145,8 @@ static int ext4_update_backup_sb(struct super_block *sb, if (ext4_has_metadata_csum(sb) && es->s_checksum != ext4_superblock_csum(sb, es)) { ext4_msg(sb, KERN_ERR, "Invalid checksum for backup " - "superblock %llu\n", sb_block); + "superblock %llu", sb_block); unlock_buffer(bh); - err = -EFSBADCRC; goto out_bh; } func(es, arg); diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index 0a220ec9862d..a19a9661646e 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -424,7 +424,8 @@ int ext4_ext_migrate(struct inode *inode) * already is extent-based, error out. */ if (!ext4_has_feature_extents(inode->i_sb) || - (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) + ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) || + ext4_has_inline_data(inode)) return -EINVAL; if (S_ISLNK(inode->i_mode) && inode->i_blocks == 0) diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index d5daaf41e1fc..c08c0aba1883 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2259,8 +2259,16 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname, memset(de, 0, len); /* wipe old data */ de = (struct ext4_dir_entry_2 *) data2; top = data2 + len; - while ((char *)(de2 = ext4_next_entry(de, blocksize)) < top) + while ((char *)(de2 = ext4_next_entry(de, blocksize)) < top) { + if (ext4_check_dir_entry(dir, NULL, de, bh2, data2, len, + (data2 + (blocksize - csum_size) - + (char *) de))) { + brelse(bh2); + brelse(bh); + return -EFSCORRUPTED; + } de = de2; + } de->rec_len = ext4_rec_len_to_disk(data2 + (blocksize - csum_size) - (char *) de, blocksize); diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 6dfe9ccae0c5..46b87ffeb304 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -1158,6 +1158,7 @@ static void update_backups(struct super_block *sb, sector_t blk_off, char *data, while (group < sbi->s_groups_count) { struct buffer_head *bh; ext4_fsblk_t backup_block; + struct ext4_super_block *es; /* Out of journal space, and can't get more - abort - so sad */ err = ext4_resize_ensure_credits_batch(handle, 1); @@ -1186,6 +1187,10 @@ static void update_backups(struct super_block *sb, sector_t blk_off, char *data, memcpy(bh->b_data, data, size); if (rest) memset(bh->b_data + size, 0, rest); + es = (struct ext4_super_block *) bh->b_data; + es->s_block_group_nr = cpu_to_le16(group); + if (ext4_has_metadata_csum(sb)) + es->s_checksum = ext4_superblock_csum(sb, es); set_buffer_uptodate(bh); unlock_buffer(bh); err = ext4_handle_dirty_metadata(handle, NULL, bh); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 7950904fbf04..7cdd2138c897 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -4881,7 +4881,7 @@ out: flush_work(&sbi->s_error_work); jbd2_journal_destroy(sbi->s_journal); sbi->s_journal = NULL; - return err; + return -EINVAL; } static int ext4_journal_data_mode_check(struct super_block *sb) diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 1a3afd469e3a..71bfb663aac5 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -3001,6 +3001,10 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset, goto out; } + err = file_modified(file); + if (err) + goto out; + if (!(mode & FALLOC_FL_KEEP_SIZE)) set_bit(FUSE_I_SIZE_UNSTABLE, &fi->state); diff --git a/fs/fuse/readdir.c b/fs/fuse/readdir.c index b4e565711045..e8deaacf1832 100644 --- a/fs/fuse/readdir.c +++ b/fs/fuse/readdir.c @@ -77,8 +77,10 @@ static void fuse_add_dirent_to_cache(struct file *file, goto unlock; addr = kmap_local_page(page); - if (!offset) + if (!offset) { clear_page(addr); + SetPageUptodate(page); + } memcpy(addr + offset, dirent, reclen); kunmap_local(addr); fi->rdc.size = (index << PAGE_SHIFT) + offset + reclen; @@ -516,6 +518,12 @@ retry_locked: page = find_get_page_flags(file->f_mapping, index, FGP_ACCESSED | FGP_LOCK); + /* Page gone missing, then re-added to cache, but not initialized? */ + if (page && !PageUptodate(page)) { + unlock_page(page); + put_page(page); + page = NULL; + } spin_lock(&fi->rdc.lock); if (!page) { /* diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 07c81ab3fd4d..98ac37e34e3d 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -1630,17 +1630,20 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, NULL_VM_UFFD_CTX, anon_vma_name(vma)); if (prev) { vma = prev; + mas_pause(&mas); goto next; } if (vma->vm_start < start) { ret = split_vma(mm, vma, start, 1); if (ret) break; + mas_pause(&mas); } if (vma->vm_end > end) { ret = split_vma(mm, vma, end, 0); if (ret) break; + mas_pause(&mas); } next: /* diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h index 517a138faa66..191b22b9a35b 100644 --- a/fs/xfs/libxfs/xfs_ag.h +++ b/fs/xfs/libxfs/xfs_ag.h @@ -133,6 +133,21 @@ xfs_verify_agbno(struct xfs_perag *pag, xfs_agblock_t agbno) return true; } +static inline bool +xfs_verify_agbext( + struct xfs_perag *pag, + xfs_agblock_t agbno, + xfs_agblock_t len) +{ + if (agbno + len <= agbno) + return false; + + if (!xfs_verify_agbno(pag, agbno)) + return false; + + return xfs_verify_agbno(pag, agbno + len - 1); +} + /* * Verify that an AG inode number pointer neither points outside the AG * nor points at static metadata. diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index 6261599bb389..de79f5d07f65 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -263,11 +263,7 @@ xfs_alloc_get_rec( goto out_bad_rec; /* check for valid extent range, including overflow */ - if (!xfs_verify_agbno(pag, *bno)) - goto out_bad_rec; - if (*bno > *bno + *len) - goto out_bad_rec; - if (!xfs_verify_agbno(pag, *bno + *len - 1)) + if (!xfs_verify_agbext(pag, *bno, *len)) goto out_bad_rec; return 0; diff --git a/fs/xfs/libxfs/xfs_dir2_leaf.c b/fs/xfs/libxfs/xfs_dir2_leaf.c index d9b66306a9a7..cb9e950a911d 100644 --- a/fs/xfs/libxfs/xfs_dir2_leaf.c +++ b/fs/xfs/libxfs/xfs_dir2_leaf.c @@ -146,6 +146,8 @@ xfs_dir3_leaf_check_int( xfs_dir2_leaf_tail_t *ltp; int stale; int i; + bool isleaf1 = (hdr->magic == XFS_DIR2_LEAF1_MAGIC || + hdr->magic == XFS_DIR3_LEAF1_MAGIC); ltp = xfs_dir2_leaf_tail_p(geo, leaf); @@ -158,8 +160,7 @@ xfs_dir3_leaf_check_int( return __this_address; /* Leaves and bests don't overlap in leaf format. */ - if ((hdr->magic == XFS_DIR2_LEAF1_MAGIC || - hdr->magic == XFS_DIR3_LEAF1_MAGIC) && + if (isleaf1 && (char *)&hdr->ents[hdr->count] > (char *)xfs_dir2_leaf_bests_p(ltp)) return __this_address; @@ -175,6 +176,10 @@ xfs_dir3_leaf_check_int( } if (hdr->ents[i].address == cpu_to_be32(XFS_DIR2_NULL_DATAPTR)) stale++; + if (isleaf1 && xfs_dir2_dataptr_to_db(geo, + be32_to_cpu(hdr->ents[i].address)) >= + be32_to_cpu(ltp->bestcount)) + return __this_address; } if (hdr->stale != stale) return __this_address; diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h index b55bdfa9c8a8..371dc07233e0 100644 --- a/fs/xfs/libxfs/xfs_format.h +++ b/fs/xfs/libxfs/xfs_format.h @@ -1564,20 +1564,6 @@ struct xfs_rmap_rec { #define RMAPBT_UNUSED_OFFSET_BITLEN 7 #define RMAPBT_OFFSET_BITLEN 54 -#define XFS_RMAP_ATTR_FORK (1 << 0) -#define XFS_RMAP_BMBT_BLOCK (1 << 1) -#define XFS_RMAP_UNWRITTEN (1 << 2) -#define XFS_RMAP_KEY_FLAGS (XFS_RMAP_ATTR_FORK | \ - XFS_RMAP_BMBT_BLOCK) -#define XFS_RMAP_REC_FLAGS (XFS_RMAP_UNWRITTEN) -struct xfs_rmap_irec { - xfs_agblock_t rm_startblock; /* extent start block */ - xfs_extlen_t rm_blockcount; /* extent length */ - uint64_t rm_owner; /* extent owner */ - uint64_t rm_offset; /* offset within the owner */ - unsigned int rm_flags; /* state flags */ -}; - /* * Key structure * @@ -1626,7 +1612,7 @@ unsigned int xfs_refc_block(struct xfs_mount *mp); * on the startblock. This speeds up mount time deletion of stale * staging extents because they're all at the right side of the tree. */ -#define XFS_REFC_COW_START ((xfs_agblock_t)(1U << 31)) +#define XFS_REFC_COWFLAG (1U << 31) #define REFCNTBT_COWFLAG_BITLEN 1 #define REFCNTBT_AGBLOCK_BITLEN 31 @@ -1640,12 +1626,6 @@ struct xfs_refcount_key { __be32 rc_startblock; /* starting block number */ }; -struct xfs_refcount_irec { - xfs_agblock_t rc_startblock; /* starting block number */ - xfs_extlen_t rc_blockcount; /* count of free blocks */ - xfs_nlink_t rc_refcount; /* number of inodes linked here */ -}; - #define MAXREFCOUNT ((xfs_nlink_t)~0U) #define MAXREFCEXTLEN ((xfs_extlen_t)~0U) diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h index b351b9dc6561..f13e0809dc63 100644 --- a/fs/xfs/libxfs/xfs_log_format.h +++ b/fs/xfs/libxfs/xfs_log_format.h @@ -613,25 +613,49 @@ typedef struct xfs_efi_log_format { uint16_t efi_size; /* size of this item */ uint32_t efi_nextents; /* # extents to free */ uint64_t efi_id; /* efi identifier */ - xfs_extent_t efi_extents[1]; /* array of extents to free */ + xfs_extent_t efi_extents[]; /* array of extents to free */ } xfs_efi_log_format_t; +static inline size_t +xfs_efi_log_format_sizeof( + unsigned int nr) +{ + return sizeof(struct xfs_efi_log_format) + + nr * sizeof(struct xfs_extent); +} + typedef struct xfs_efi_log_format_32 { uint16_t efi_type; /* efi log item type */ uint16_t efi_size; /* size of this item */ uint32_t efi_nextents; /* # extents to free */ uint64_t efi_id; /* efi identifier */ - xfs_extent_32_t efi_extents[1]; /* array of extents to free */ + xfs_extent_32_t efi_extents[]; /* array of extents to free */ } __attribute__((packed)) xfs_efi_log_format_32_t; +static inline size_t +xfs_efi_log_format32_sizeof( + unsigned int nr) +{ + return sizeof(struct xfs_efi_log_format_32) + + nr * sizeof(struct xfs_extent_32); +} + typedef struct xfs_efi_log_format_64 { uint16_t efi_type; /* efi log item type */ uint16_t efi_size; /* size of this item */ uint32_t efi_nextents; /* # extents to free */ uint64_t efi_id; /* efi identifier */ - xfs_extent_64_t efi_extents[1]; /* array of extents to free */ + xfs_extent_64_t efi_extents[]; /* array of extents to free */ } xfs_efi_log_format_64_t; +static inline size_t +xfs_efi_log_format64_sizeof( + unsigned int nr) +{ + return sizeof(struct xfs_efi_log_format_64) + + nr * sizeof(struct xfs_extent_64); +} + /* * This is the structure used to lay out an efd log item in the * log. The efd_extents array is a variable size array whose @@ -642,25 +666,49 @@ typedef struct xfs_efd_log_format { uint16_t efd_size; /* size of this item */ uint32_t efd_nextents; /* # of extents freed */ uint64_t efd_efi_id; /* id of corresponding efi */ - xfs_extent_t efd_extents[1]; /* array of extents freed */ + xfs_extent_t efd_extents[]; /* array of extents freed */ } xfs_efd_log_format_t; +static inline size_t +xfs_efd_log_format_sizeof( + unsigned int nr) +{ + return sizeof(struct xfs_efd_log_format) + + nr * sizeof(struct xfs_extent); +} + typedef struct xfs_efd_log_format_32 { uint16_t efd_type; /* efd log item type */ uint16_t efd_size; /* size of this item */ uint32_t efd_nextents; /* # of extents freed */ uint64_t efd_efi_id; /* id of corresponding efi */ - xfs_extent_32_t efd_extents[1]; /* array of extents freed */ + xfs_extent_32_t efd_extents[]; /* array of extents freed */ } __attribute__((packed)) xfs_efd_log_format_32_t; +static inline size_t +xfs_efd_log_format32_sizeof( + unsigned int nr) +{ + return sizeof(struct xfs_efd_log_format_32) + + nr * sizeof(struct xfs_extent_32); +} + typedef struct xfs_efd_log_format_64 { uint16_t efd_type; /* efd log item type */ uint16_t efd_size; /* size of this item */ uint32_t efd_nextents; /* # of extents freed */ uint64_t efd_efi_id; /* id of corresponding efi */ - xfs_extent_64_t efd_extents[1]; /* array of extents freed */ + xfs_extent_64_t efd_extents[]; /* array of extents freed */ } xfs_efd_log_format_64_t; +static inline size_t +xfs_efd_log_format64_sizeof( + unsigned int nr) +{ + return sizeof(struct xfs_efd_log_format_64) + + nr * sizeof(struct xfs_extent_64); +} + /* * RUI/RUD (reverse mapping) log format definitions */ diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c index 64b910caafaa..3f34bafe18dd 100644 --- a/fs/xfs/libxfs/xfs_refcount.c +++ b/fs/xfs/libxfs/xfs_refcount.c @@ -46,13 +46,16 @@ STATIC int __xfs_refcount_cow_free(struct xfs_btree_cur *rcur, int xfs_refcount_lookup_le( struct xfs_btree_cur *cur, + enum xfs_refc_domain domain, xfs_agblock_t bno, int *stat) { - trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_ag.pag->pag_agno, bno, + trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_ag.pag->pag_agno, + xfs_refcount_encode_startblock(bno, domain), XFS_LOOKUP_LE); cur->bc_rec.rc.rc_startblock = bno; cur->bc_rec.rc.rc_blockcount = 0; + cur->bc_rec.rc.rc_domain = domain; return xfs_btree_lookup(cur, XFS_LOOKUP_LE, stat); } @@ -63,13 +66,16 @@ xfs_refcount_lookup_le( int xfs_refcount_lookup_ge( struct xfs_btree_cur *cur, + enum xfs_refc_domain domain, xfs_agblock_t bno, int *stat) { - trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_ag.pag->pag_agno, bno, + trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_ag.pag->pag_agno, + xfs_refcount_encode_startblock(bno, domain), XFS_LOOKUP_GE); cur->bc_rec.rc.rc_startblock = bno; cur->bc_rec.rc.rc_blockcount = 0; + cur->bc_rec.rc.rc_domain = domain; return xfs_btree_lookup(cur, XFS_LOOKUP_GE, stat); } @@ -80,13 +86,16 @@ xfs_refcount_lookup_ge( int xfs_refcount_lookup_eq( struct xfs_btree_cur *cur, + enum xfs_refc_domain domain, xfs_agblock_t bno, int *stat) { - trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_ag.pag->pag_agno, bno, + trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_ag.pag->pag_agno, + xfs_refcount_encode_startblock(bno, domain), XFS_LOOKUP_LE); cur->bc_rec.rc.rc_startblock = bno; cur->bc_rec.rc.rc_blockcount = 0; + cur->bc_rec.rc.rc_domain = domain; return xfs_btree_lookup(cur, XFS_LOOKUP_EQ, stat); } @@ -96,7 +105,17 @@ xfs_refcount_btrec_to_irec( const union xfs_btree_rec *rec, struct xfs_refcount_irec *irec) { - irec->rc_startblock = be32_to_cpu(rec->refc.rc_startblock); + uint32_t start; + + start = be32_to_cpu(rec->refc.rc_startblock); + if (start & XFS_REFC_COWFLAG) { + start &= ~XFS_REFC_COWFLAG; + irec->rc_domain = XFS_REFC_DOMAIN_COW; + } else { + irec->rc_domain = XFS_REFC_DOMAIN_SHARED; + } + + irec->rc_startblock = start; irec->rc_blockcount = be32_to_cpu(rec->refc.rc_blockcount); irec->rc_refcount = be32_to_cpu(rec->refc.rc_refcount); } @@ -114,7 +133,6 @@ xfs_refcount_get_rec( struct xfs_perag *pag = cur->bc_ag.pag; union xfs_btree_rec *rec; int error; - xfs_agblock_t realstart; error = xfs_btree_get_rec(cur, &rec, stat); if (error || !*stat) @@ -124,22 +142,11 @@ xfs_refcount_get_rec( if (irec->rc_blockcount == 0 || irec->rc_blockcount > MAXREFCEXTLEN) goto out_bad_rec; - /* handle special COW-staging state */ - realstart = irec->rc_startblock; - if (realstart & XFS_REFC_COW_START) { - if (irec->rc_refcount != 1) - goto out_bad_rec; - realstart &= ~XFS_REFC_COW_START; - } else if (irec->rc_refcount < 2) { + if (!xfs_refcount_check_domain(irec)) goto out_bad_rec; - } /* check for valid extent range, including overflow */ - if (!xfs_verify_agbno(pag, realstart)) - goto out_bad_rec; - if (realstart > realstart + irec->rc_blockcount) - goto out_bad_rec; - if (!xfs_verify_agbno(pag, realstart + irec->rc_blockcount - 1)) + if (!xfs_verify_agbext(pag, irec->rc_startblock, irec->rc_blockcount)) goto out_bad_rec; if (irec->rc_refcount == 0 || irec->rc_refcount > MAXREFCOUNT) @@ -169,12 +176,17 @@ xfs_refcount_update( struct xfs_refcount_irec *irec) { union xfs_btree_rec rec; + uint32_t start; int error; trace_xfs_refcount_update(cur->bc_mp, cur->bc_ag.pag->pag_agno, irec); - rec.refc.rc_startblock = cpu_to_be32(irec->rc_startblock); + + start = xfs_refcount_encode_startblock(irec->rc_startblock, + irec->rc_domain); + rec.refc.rc_startblock = cpu_to_be32(start); rec.refc.rc_blockcount = cpu_to_be32(irec->rc_blockcount); rec.refc.rc_refcount = cpu_to_be32(irec->rc_refcount); + error = xfs_btree_update(cur, &rec); if (error) trace_xfs_refcount_update_error(cur->bc_mp, @@ -196,9 +208,12 @@ xfs_refcount_insert( int error; trace_xfs_refcount_insert(cur->bc_mp, cur->bc_ag.pag->pag_agno, irec); + cur->bc_rec.rc.rc_startblock = irec->rc_startblock; cur->bc_rec.rc.rc_blockcount = irec->rc_blockcount; cur->bc_rec.rc.rc_refcount = irec->rc_refcount; + cur->bc_rec.rc.rc_domain = irec->rc_domain; + error = xfs_btree_insert(cur, i); if (error) goto out_error; @@ -244,7 +259,8 @@ xfs_refcount_delete( } if (error) goto out_error; - error = xfs_refcount_lookup_ge(cur, irec.rc_startblock, &found_rec); + error = xfs_refcount_lookup_ge(cur, irec.rc_domain, irec.rc_startblock, + &found_rec); out_error: if (error) trace_xfs_refcount_delete_error(cur->bc_mp, @@ -343,6 +359,7 @@ xfs_refc_next( STATIC int xfs_refcount_split_extent( struct xfs_btree_cur *cur, + enum xfs_refc_domain domain, xfs_agblock_t agbno, bool *shape_changed) { @@ -351,7 +368,7 @@ xfs_refcount_split_extent( int error; *shape_changed = false; - error = xfs_refcount_lookup_le(cur, agbno, &found_rec); + error = xfs_refcount_lookup_le(cur, domain, agbno, &found_rec); if (error) goto out_error; if (!found_rec) @@ -364,6 +381,8 @@ xfs_refcount_split_extent( error = -EFSCORRUPTED; goto out_error; } + if (rcext.rc_domain != domain) + return 0; if (rcext.rc_startblock == agbno || xfs_refc_next(&rcext) <= agbno) return 0; @@ -415,6 +434,9 @@ xfs_refcount_merge_center_extents( trace_xfs_refcount_merge_center_extents(cur->bc_mp, cur->bc_ag.pag->pag_agno, left, center, right); + ASSERT(left->rc_domain == center->rc_domain); + ASSERT(right->rc_domain == center->rc_domain); + /* * Make sure the center and right extents are not in the btree. * If the center extent was synthesized, the first delete call @@ -423,8 +445,8 @@ xfs_refcount_merge_center_extents( * call removes the center and the second one removes the right * extent. */ - error = xfs_refcount_lookup_ge(cur, center->rc_startblock, - &found_rec); + error = xfs_refcount_lookup_ge(cur, center->rc_domain, + center->rc_startblock, &found_rec); if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { @@ -451,8 +473,8 @@ xfs_refcount_merge_center_extents( } /* Enlarge the left extent. */ - error = xfs_refcount_lookup_le(cur, left->rc_startblock, - &found_rec); + error = xfs_refcount_lookup_le(cur, left->rc_domain, + left->rc_startblock, &found_rec); if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { @@ -491,10 +513,12 @@ xfs_refcount_merge_left_extent( trace_xfs_refcount_merge_left_extent(cur->bc_mp, cur->bc_ag.pag->pag_agno, left, cleft); + ASSERT(left->rc_domain == cleft->rc_domain); + /* If the extent at agbno (cleft) wasn't synthesized, remove it. */ if (cleft->rc_refcount > 1) { - error = xfs_refcount_lookup_le(cur, cleft->rc_startblock, - &found_rec); + error = xfs_refcount_lookup_le(cur, cleft->rc_domain, + cleft->rc_startblock, &found_rec); if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { @@ -512,8 +536,8 @@ xfs_refcount_merge_left_extent( } /* Enlarge the left extent. */ - error = xfs_refcount_lookup_le(cur, left->rc_startblock, - &found_rec); + error = xfs_refcount_lookup_le(cur, left->rc_domain, + left->rc_startblock, &found_rec); if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { @@ -552,13 +576,15 @@ xfs_refcount_merge_right_extent( trace_xfs_refcount_merge_right_extent(cur->bc_mp, cur->bc_ag.pag->pag_agno, cright, right); + ASSERT(right->rc_domain == cright->rc_domain); + /* * If the extent ending at agbno+aglen (cright) wasn't synthesized, * remove it. */ if (cright->rc_refcount > 1) { - error = xfs_refcount_lookup_le(cur, cright->rc_startblock, - &found_rec); + error = xfs_refcount_lookup_le(cur, cright->rc_domain, + cright->rc_startblock, &found_rec); if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { @@ -576,8 +602,8 @@ xfs_refcount_merge_right_extent( } /* Enlarge the right extent. */ - error = xfs_refcount_lookup_le(cur, right->rc_startblock, - &found_rec); + error = xfs_refcount_lookup_le(cur, right->rc_domain, + right->rc_startblock, &found_rec); if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { @@ -600,8 +626,6 @@ out_error: return error; } -#define XFS_FIND_RCEXT_SHARED 1 -#define XFS_FIND_RCEXT_COW 2 /* * Find the left extent and the one after it (cleft). This function assumes * that we've already split any extent crossing agbno. @@ -611,16 +635,16 @@ xfs_refcount_find_left_extents( struct xfs_btree_cur *cur, struct xfs_refcount_irec *left, struct xfs_refcount_irec *cleft, + enum xfs_refc_domain domain, xfs_agblock_t agbno, - xfs_extlen_t aglen, - int flags) + xfs_extlen_t aglen) { struct xfs_refcount_irec tmp; int error; int found_rec; left->rc_startblock = cleft->rc_startblock = NULLAGBLOCK; - error = xfs_refcount_lookup_le(cur, agbno - 1, &found_rec); + error = xfs_refcount_lookup_le(cur, domain, agbno - 1, &found_rec); if (error) goto out_error; if (!found_rec) @@ -634,11 +658,9 @@ xfs_refcount_find_left_extents( goto out_error; } - if (xfs_refc_next(&tmp) != agbno) - return 0; - if ((flags & XFS_FIND_RCEXT_SHARED) && tmp.rc_refcount < 2) + if (tmp.rc_domain != domain) return 0; - if ((flags & XFS_FIND_RCEXT_COW) && tmp.rc_refcount > 1) + if (xfs_refc_next(&tmp) != agbno) return 0; /* We have a left extent; retrieve (or invent) the next right one */ *left = tmp; @@ -655,6 +677,9 @@ xfs_refcount_find_left_extents( goto out_error; } + if (tmp.rc_domain != domain) + goto not_found; + /* if tmp starts at the end of our range, just use that */ if (tmp.rc_startblock == agbno) *cleft = tmp; @@ -671,8 +696,10 @@ xfs_refcount_find_left_extents( cleft->rc_blockcount = min(aglen, tmp.rc_startblock - agbno); cleft->rc_refcount = 1; + cleft->rc_domain = domain; } } else { +not_found: /* * No extents, so pretend that there's one covering the whole * range. @@ -680,6 +707,7 @@ xfs_refcount_find_left_extents( cleft->rc_startblock = agbno; cleft->rc_blockcount = aglen; cleft->rc_refcount = 1; + cleft->rc_domain = domain; } trace_xfs_refcount_find_left_extent(cur->bc_mp, cur->bc_ag.pag->pag_agno, left, cleft, agbno); @@ -700,16 +728,16 @@ xfs_refcount_find_right_extents( struct xfs_btree_cur *cur, struct xfs_refcount_irec *right, struct xfs_refcount_irec *cright, + enum xfs_refc_domain domain, xfs_agblock_t agbno, - xfs_extlen_t aglen, - int flags) + xfs_extlen_t aglen) { struct xfs_refcount_irec tmp; int error; int found_rec; right->rc_startblock = cright->rc_startblock = NULLAGBLOCK; - error = xfs_refcount_lookup_ge(cur, agbno + aglen, &found_rec); + error = xfs_refcount_lookup_ge(cur, domain, agbno + aglen, &found_rec); if (error) goto out_error; if (!found_rec) @@ -723,11 +751,9 @@ xfs_refcount_find_right_extents( goto out_error; } - if (tmp.rc_startblock != agbno + aglen) - return 0; - if ((flags & XFS_FIND_RCEXT_SHARED) && tmp.rc_refcount < 2) + if (tmp.rc_domain != domain) return 0; - if ((flags & XFS_FIND_RCEXT_COW) && tmp.rc_refcount > 1) + if (tmp.rc_startblock != agbno + aglen) return 0; /* We have a right extent; retrieve (or invent) the next left one */ *right = tmp; @@ -744,6 +770,9 @@ xfs_refcount_find_right_extents( goto out_error; } + if (tmp.rc_domain != domain) + goto not_found; + /* if tmp ends at the end of our range, just use that */ if (xfs_refc_next(&tmp) == agbno + aglen) *cright = tmp; @@ -760,8 +789,10 @@ xfs_refcount_find_right_extents( cright->rc_blockcount = right->rc_startblock - cright->rc_startblock; cright->rc_refcount = 1; + cright->rc_domain = domain; } } else { +not_found: /* * No extents, so pretend that there's one covering the whole * range. @@ -769,6 +800,7 @@ xfs_refcount_find_right_extents( cright->rc_startblock = agbno; cright->rc_blockcount = aglen; cright->rc_refcount = 1; + cright->rc_domain = domain; } trace_xfs_refcount_find_right_extent(cur->bc_mp, cur->bc_ag.pag->pag_agno, cright, right, agbno + aglen); @@ -794,10 +826,10 @@ xfs_refc_valid( STATIC int xfs_refcount_merge_extents( struct xfs_btree_cur *cur, + enum xfs_refc_domain domain, xfs_agblock_t *agbno, xfs_extlen_t *aglen, enum xfs_refc_adjust_op adjust, - int flags, bool *shape_changed) { struct xfs_refcount_irec left = {0}, cleft = {0}; @@ -812,12 +844,12 @@ xfs_refcount_merge_extents( * just below (agbno + aglen) [cright], and just above (agbno + aglen) * [right]. */ - error = xfs_refcount_find_left_extents(cur, &left, &cleft, *agbno, - *aglen, flags); + error = xfs_refcount_find_left_extents(cur, &left, &cleft, domain, + *agbno, *aglen); if (error) return error; - error = xfs_refcount_find_right_extents(cur, &right, &cright, *agbno, - *aglen, flags); + error = xfs_refcount_find_right_extents(cur, &right, &cright, domain, + *agbno, *aglen); if (error) return error; @@ -870,7 +902,7 @@ xfs_refcount_merge_extents( aglen); } - return error; + return 0; } /* @@ -933,7 +965,8 @@ xfs_refcount_adjust_extents( if (*aglen == 0) return 0; - error = xfs_refcount_lookup_ge(cur, *agbno, &found_rec); + error = xfs_refcount_lookup_ge(cur, XFS_REFC_DOMAIN_SHARED, *agbno, + &found_rec); if (error) goto out_error; @@ -941,10 +974,11 @@ xfs_refcount_adjust_extents( error = xfs_refcount_get_rec(cur, &ext, &found_rec); if (error) goto out_error; - if (!found_rec) { + if (!found_rec || ext.rc_domain != XFS_REFC_DOMAIN_SHARED) { ext.rc_startblock = cur->bc_mp->m_sb.sb_agblocks; ext.rc_blockcount = 0; ext.rc_refcount = 0; + ext.rc_domain = XFS_REFC_DOMAIN_SHARED; } /* @@ -957,6 +991,8 @@ xfs_refcount_adjust_extents( tmp.rc_blockcount = min(*aglen, ext.rc_startblock - *agbno); tmp.rc_refcount = 1 + adj; + tmp.rc_domain = XFS_REFC_DOMAIN_SHARED; + trace_xfs_refcount_modify_extent(cur->bc_mp, cur->bc_ag.pag->pag_agno, &tmp); @@ -986,15 +1022,30 @@ xfs_refcount_adjust_extents( (*agbno) += tmp.rc_blockcount; (*aglen) -= tmp.rc_blockcount; - error = xfs_refcount_lookup_ge(cur, *agbno, + /* Stop if there's nothing left to modify */ + if (*aglen == 0 || !xfs_refcount_still_have_space(cur)) + break; + + /* Move the cursor to the start of ext. */ + error = xfs_refcount_lookup_ge(cur, + XFS_REFC_DOMAIN_SHARED, *agbno, &found_rec); if (error) goto out_error; } - /* Stop if there's nothing left to modify */ - if (*aglen == 0 || !xfs_refcount_still_have_space(cur)) - break; + /* + * A previous step trimmed agbno/aglen such that the end of the + * range would not be in the middle of the record. If this is + * no longer the case, something is seriously wrong with the + * btree. Make sure we never feed the synthesized record into + * the processing loop below. + */ + if (XFS_IS_CORRUPT(cur->bc_mp, ext.rc_blockcount == 0) || + XFS_IS_CORRUPT(cur->bc_mp, ext.rc_blockcount > *aglen)) { + error = -EFSCORRUPTED; + goto out_error; + } /* * Adjust the reference count and either update the tree @@ -1070,13 +1121,15 @@ xfs_refcount_adjust( /* * Ensure that no rcextents cross the boundary of the adjustment range. */ - error = xfs_refcount_split_extent(cur, agbno, &shape_changed); + error = xfs_refcount_split_extent(cur, XFS_REFC_DOMAIN_SHARED, + agbno, &shape_changed); if (error) goto out_error; if (shape_changed) shape_changes++; - error = xfs_refcount_split_extent(cur, agbno + aglen, &shape_changed); + error = xfs_refcount_split_extent(cur, XFS_REFC_DOMAIN_SHARED, + agbno + aglen, &shape_changed); if (error) goto out_error; if (shape_changed) @@ -1085,8 +1138,8 @@ xfs_refcount_adjust( /* * Try to merge with the left or right extents of the range. */ - error = xfs_refcount_merge_extents(cur, new_agbno, new_aglen, adj, - XFS_FIND_RCEXT_SHARED, &shape_changed); + error = xfs_refcount_merge_extents(cur, XFS_REFC_DOMAIN_SHARED, + new_agbno, new_aglen, adj, &shape_changed); if (error) goto out_error; if (shape_changed) @@ -1125,6 +1178,32 @@ xfs_refcount_finish_one_cleanup( } /* + * Set up a continuation a deferred refcount operation by updating the intent. + * Checks to make sure we're not going to run off the end of the AG. + */ +static inline int +xfs_refcount_continue_op( + struct xfs_btree_cur *cur, + xfs_fsblock_t startblock, + xfs_agblock_t new_agbno, + xfs_extlen_t new_len, + xfs_fsblock_t *new_fsbno) +{ + struct xfs_mount *mp = cur->bc_mp; + struct xfs_perag *pag = cur->bc_ag.pag; + + if (XFS_IS_CORRUPT(mp, !xfs_verify_agbext(pag, new_agbno, new_len))) + return -EFSCORRUPTED; + + *new_fsbno = XFS_AGB_TO_FSB(mp, pag->pag_agno, new_agbno); + + ASSERT(xfs_verify_fsbext(mp, *new_fsbno, new_len)); + ASSERT(pag->pag_agno == XFS_FSB_TO_AGNO(mp, *new_fsbno)); + + return 0; +} + +/* * Process one of the deferred refcount operations. We pass back the * btree cursor to maintain our lock on the btree between calls. * This saves time and eliminates a buffer deadlock between the @@ -1191,12 +1270,20 @@ xfs_refcount_finish_one( case XFS_REFCOUNT_INCREASE: error = xfs_refcount_adjust(rcur, bno, blockcount, &new_agbno, new_len, XFS_REFCOUNT_ADJUST_INCREASE); - *new_fsb = XFS_AGB_TO_FSB(mp, pag->pag_agno, new_agbno); + if (error) + goto out_drop; + if (*new_len > 0) + error = xfs_refcount_continue_op(rcur, startblock, + new_agbno, *new_len, new_fsb); break; case XFS_REFCOUNT_DECREASE: error = xfs_refcount_adjust(rcur, bno, blockcount, &new_agbno, new_len, XFS_REFCOUNT_ADJUST_DECREASE); - *new_fsb = XFS_AGB_TO_FSB(mp, pag->pag_agno, new_agbno); + if (error) + goto out_drop; + if (*new_len > 0) + error = xfs_refcount_continue_op(rcur, startblock, + new_agbno, *new_len, new_fsb); break; case XFS_REFCOUNT_ALLOC_COW: *new_fsb = startblock + blockcount; @@ -1307,7 +1394,8 @@ xfs_refcount_find_shared( *flen = 0; /* Try to find a refcount extent that crosses the start */ - error = xfs_refcount_lookup_le(cur, agbno, &have); + error = xfs_refcount_lookup_le(cur, XFS_REFC_DOMAIN_SHARED, agbno, + &have); if (error) goto out_error; if (!have) { @@ -1325,6 +1413,8 @@ xfs_refcount_find_shared( error = -EFSCORRUPTED; goto out_error; } + if (tmp.rc_domain != XFS_REFC_DOMAIN_SHARED) + goto done; /* If the extent ends before the start, look at the next one */ if (tmp.rc_startblock + tmp.rc_blockcount <= agbno) { @@ -1340,6 +1430,8 @@ xfs_refcount_find_shared( error = -EFSCORRUPTED; goto out_error; } + if (tmp.rc_domain != XFS_REFC_DOMAIN_SHARED) + goto done; } /* If the extent starts after the range we want, bail out */ @@ -1371,7 +1463,8 @@ xfs_refcount_find_shared( error = -EFSCORRUPTED; goto out_error; } - if (tmp.rc_startblock >= agbno + aglen || + if (tmp.rc_domain != XFS_REFC_DOMAIN_SHARED || + tmp.rc_startblock >= agbno + aglen || tmp.rc_startblock != *fbno + *flen) break; *flen = min(*flen + tmp.rc_blockcount, agbno + aglen - *fbno); @@ -1455,17 +1548,23 @@ xfs_refcount_adjust_cow_extents( return 0; /* Find any overlapping refcount records */ - error = xfs_refcount_lookup_ge(cur, agbno, &found_rec); + error = xfs_refcount_lookup_ge(cur, XFS_REFC_DOMAIN_COW, agbno, + &found_rec); if (error) goto out_error; error = xfs_refcount_get_rec(cur, &ext, &found_rec); if (error) goto out_error; + if (XFS_IS_CORRUPT(cur->bc_mp, found_rec && + ext.rc_domain != XFS_REFC_DOMAIN_COW)) { + error = -EFSCORRUPTED; + goto out_error; + } if (!found_rec) { - ext.rc_startblock = cur->bc_mp->m_sb.sb_agblocks + - XFS_REFC_COW_START; + ext.rc_startblock = cur->bc_mp->m_sb.sb_agblocks; ext.rc_blockcount = 0; ext.rc_refcount = 0; + ext.rc_domain = XFS_REFC_DOMAIN_COW; } switch (adj) { @@ -1480,6 +1579,8 @@ xfs_refcount_adjust_cow_extents( tmp.rc_startblock = agbno; tmp.rc_blockcount = aglen; tmp.rc_refcount = 1; + tmp.rc_domain = XFS_REFC_DOMAIN_COW; + trace_xfs_refcount_modify_extent(cur->bc_mp, cur->bc_ag.pag->pag_agno, &tmp); @@ -1542,24 +1643,24 @@ xfs_refcount_adjust_cow( bool shape_changed; int error; - agbno += XFS_REFC_COW_START; - /* * Ensure that no rcextents cross the boundary of the adjustment range. */ - error = xfs_refcount_split_extent(cur, agbno, &shape_changed); + error = xfs_refcount_split_extent(cur, XFS_REFC_DOMAIN_COW, + agbno, &shape_changed); if (error) goto out_error; - error = xfs_refcount_split_extent(cur, agbno + aglen, &shape_changed); + error = xfs_refcount_split_extent(cur, XFS_REFC_DOMAIN_COW, + agbno + aglen, &shape_changed); if (error) goto out_error; /* * Try to merge with the left or right extents of the range. */ - error = xfs_refcount_merge_extents(cur, &agbno, &aglen, adj, - XFS_FIND_RCEXT_COW, &shape_changed); + error = xfs_refcount_merge_extents(cur, XFS_REFC_DOMAIN_COW, &agbno, + &aglen, adj, &shape_changed); if (error) goto out_error; @@ -1666,10 +1767,18 @@ xfs_refcount_recover_extent( be32_to_cpu(rec->refc.rc_refcount) != 1)) return -EFSCORRUPTED; - rr = kmem_alloc(sizeof(struct xfs_refcount_recovery), 0); + rr = kmalloc(sizeof(struct xfs_refcount_recovery), + GFP_KERNEL | __GFP_NOFAIL); + INIT_LIST_HEAD(&rr->rr_list); xfs_refcount_btrec_to_irec(rec, &rr->rr_rrec); - list_add_tail(&rr->rr_list, debris); + if (XFS_IS_CORRUPT(cur->bc_mp, + rr->rr_rrec.rc_domain != XFS_REFC_DOMAIN_COW)) { + kfree(rr); + return -EFSCORRUPTED; + } + + list_add_tail(&rr->rr_list, debris); return 0; } @@ -1687,10 +1796,11 @@ xfs_refcount_recover_cow_leftovers( union xfs_btree_irec low; union xfs_btree_irec high; xfs_fsblock_t fsb; - xfs_agblock_t agbno; int error; - if (mp->m_sb.sb_agblocks >= XFS_REFC_COW_START) + /* reflink filesystems mustn't have AGs larger than 2^31-1 blocks */ + BUILD_BUG_ON(XFS_MAX_CRC_AG_BLOCKS >= XFS_REFC_COWFLAG); + if (mp->m_sb.sb_agblocks > XFS_MAX_CRC_AG_BLOCKS) return -EOPNOTSUPP; INIT_LIST_HEAD(&debris); @@ -1717,7 +1827,7 @@ xfs_refcount_recover_cow_leftovers( /* Find all the leftover CoW staging extents. */ memset(&low, 0, sizeof(low)); memset(&high, 0, sizeof(high)); - low.rc.rc_startblock = XFS_REFC_COW_START; + low.rc.rc_domain = high.rc.rc_domain = XFS_REFC_DOMAIN_COW; high.rc.rc_startblock = -1U; error = xfs_btree_query_range(cur, &low, &high, xfs_refcount_recover_extent, &debris); @@ -1738,8 +1848,8 @@ xfs_refcount_recover_cow_leftovers( &rr->rr_rrec); /* Free the orphan record */ - agbno = rr->rr_rrec.rc_startblock - XFS_REFC_COW_START; - fsb = XFS_AGB_TO_FSB(mp, pag->pag_agno, agbno); + fsb = XFS_AGB_TO_FSB(mp, pag->pag_agno, + rr->rr_rrec.rc_startblock); xfs_refcount_free_cow_extent(tp, fsb, rr->rr_rrec.rc_blockcount); @@ -1751,7 +1861,7 @@ xfs_refcount_recover_cow_leftovers( goto out_free; list_del(&rr->rr_list); - kmem_free(rr); + kfree(rr); } return error; @@ -1761,7 +1871,7 @@ out_free: /* Free the leftover list */ list_for_each_entry_safe(rr, n, &debris, rr_list) { list_del(&rr->rr_list); - kmem_free(rr); + kfree(rr); } return error; } @@ -1770,6 +1880,7 @@ out_free: int xfs_refcount_has_record( struct xfs_btree_cur *cur, + enum xfs_refc_domain domain, xfs_agblock_t bno, xfs_extlen_t len, bool *exists) @@ -1781,6 +1892,7 @@ xfs_refcount_has_record( low.rc.rc_startblock = bno; memset(&high, 0xFF, sizeof(high)); high.rc.rc_startblock = bno + len - 1; + low.rc.rc_domain = high.rc.rc_domain = domain; return xfs_btree_has_record(cur, &low, &high, exists); } diff --git a/fs/xfs/libxfs/xfs_refcount.h b/fs/xfs/libxfs/xfs_refcount.h index e8b322de7f3d..452f30556f5a 100644 --- a/fs/xfs/libxfs/xfs_refcount.h +++ b/fs/xfs/libxfs/xfs_refcount.h @@ -14,14 +14,33 @@ struct xfs_bmbt_irec; struct xfs_refcount_irec; extern int xfs_refcount_lookup_le(struct xfs_btree_cur *cur, - xfs_agblock_t bno, int *stat); + enum xfs_refc_domain domain, xfs_agblock_t bno, int *stat); extern int xfs_refcount_lookup_ge(struct xfs_btree_cur *cur, - xfs_agblock_t bno, int *stat); + enum xfs_refc_domain domain, xfs_agblock_t bno, int *stat); extern int xfs_refcount_lookup_eq(struct xfs_btree_cur *cur, - xfs_agblock_t bno, int *stat); + enum xfs_refc_domain domain, xfs_agblock_t bno, int *stat); extern int xfs_refcount_get_rec(struct xfs_btree_cur *cur, struct xfs_refcount_irec *irec, int *stat); +static inline uint32_t +xfs_refcount_encode_startblock( + xfs_agblock_t startblock, + enum xfs_refc_domain domain) +{ + uint32_t start; + + /* + * low level btree operations need to handle the generic btree range + * query functions (which set rc_domain == -1U), so we check that the + * domain is /not/ shared. + */ + start = startblock & ~XFS_REFC_COWFLAG; + if (domain != XFS_REFC_DOMAIN_SHARED) + start |= XFS_REFC_COWFLAG; + + return start; +} + enum xfs_refcount_intent_type { XFS_REFCOUNT_INCREASE = 1, XFS_REFCOUNT_DECREASE, @@ -36,6 +55,18 @@ struct xfs_refcount_intent { xfs_fsblock_t ri_startblock; }; +/* Check that the refcount is appropriate for the record domain. */ +static inline bool +xfs_refcount_check_domain( + const struct xfs_refcount_irec *irec) +{ + if (irec->rc_domain == XFS_REFC_DOMAIN_COW && irec->rc_refcount != 1) + return false; + if (irec->rc_domain == XFS_REFC_DOMAIN_SHARED && irec->rc_refcount < 2) + return false; + return true; +} + void xfs_refcount_increase_extent(struct xfs_trans *tp, struct xfs_bmbt_irec *irec); void xfs_refcount_decrease_extent(struct xfs_trans *tp, @@ -79,7 +110,8 @@ extern int xfs_refcount_recover_cow_leftovers(struct xfs_mount *mp, #define XFS_REFCOUNT_ITEM_OVERHEAD 32 extern int xfs_refcount_has_record(struct xfs_btree_cur *cur, - xfs_agblock_t bno, xfs_extlen_t len, bool *exists); + enum xfs_refc_domain domain, xfs_agblock_t bno, + xfs_extlen_t len, bool *exists); union xfs_btree_rec; extern void xfs_refcount_btrec_to_irec(const union xfs_btree_rec *rec, struct xfs_refcount_irec *irec); diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c index 316c1ec0c3c2..e1f789866683 100644 --- a/fs/xfs/libxfs/xfs_refcount_btree.c +++ b/fs/xfs/libxfs/xfs_refcount_btree.c @@ -13,6 +13,7 @@ #include "xfs_btree.h" #include "xfs_btree_staging.h" #include "xfs_refcount_btree.h" +#include "xfs_refcount.h" #include "xfs_alloc.h" #include "xfs_error.h" #include "xfs_trace.h" @@ -160,7 +161,12 @@ xfs_refcountbt_init_rec_from_cur( struct xfs_btree_cur *cur, union xfs_btree_rec *rec) { - rec->refc.rc_startblock = cpu_to_be32(cur->bc_rec.rc.rc_startblock); + const struct xfs_refcount_irec *irec = &cur->bc_rec.rc; + uint32_t start; + + start = xfs_refcount_encode_startblock(irec->rc_startblock, + irec->rc_domain); + rec->refc.rc_startblock = cpu_to_be32(start); rec->refc.rc_blockcount = cpu_to_be32(cur->bc_rec.rc.rc_blockcount); rec->refc.rc_refcount = cpu_to_be32(cur->bc_rec.rc.rc_refcount); } @@ -182,10 +188,13 @@ xfs_refcountbt_key_diff( struct xfs_btree_cur *cur, const union xfs_btree_key *key) { - struct xfs_refcount_irec *rec = &cur->bc_rec.rc; const struct xfs_refcount_key *kp = &key->refc; + const struct xfs_refcount_irec *irec = &cur->bc_rec.rc; + uint32_t start; - return (int64_t)be32_to_cpu(kp->rc_startblock) - rec->rc_startblock; + start = xfs_refcount_encode_startblock(irec->rc_startblock, + irec->rc_domain); + return (int64_t)be32_to_cpu(kp->rc_startblock) - start; } STATIC int64_t diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c index 094dfc897ebc..b56aca1e7c66 100644 --- a/fs/xfs/libxfs/xfs_rmap.c +++ b/fs/xfs/libxfs/xfs_rmap.c @@ -235,13 +235,8 @@ xfs_rmap_get_rec( goto out_bad_rec; } else { /* check for valid extent range, including overflow */ - if (!xfs_verify_agbno(pag, irec->rm_startblock)) - goto out_bad_rec; - if (irec->rm_startblock > - irec->rm_startblock + irec->rm_blockcount) - goto out_bad_rec; - if (!xfs_verify_agbno(pag, - irec->rm_startblock + irec->rm_blockcount - 1)) + if (!xfs_verify_agbext(pag, irec->rm_startblock, + irec->rm_blockcount)) goto out_bad_rec; } diff --git a/fs/xfs/libxfs/xfs_trans_resv.c b/fs/xfs/libxfs/xfs_trans_resv.c index 2c4ad6e4bb14..5b2f27cbdb80 100644 --- a/fs/xfs/libxfs/xfs_trans_resv.c +++ b/fs/xfs/libxfs/xfs_trans_resv.c @@ -422,7 +422,7 @@ xfs_calc_itruncate_reservation_minlogsize( /* * In renaming a files we can modify: - * the four inodes involved: 4 * inode size + * the five inodes involved: 5 * inode size * the two directory btrees: 2 * (max depth + v2) * dir block size * the two directory bmap btrees: 2 * max depth * block size * And the bmap_finish transaction can free dir and bmap blocks (two sets @@ -437,7 +437,7 @@ xfs_calc_rename_reservation( struct xfs_mount *mp) { return XFS_DQUOT_LOGRES(mp) + - max((xfs_calc_inode_res(mp, 4) + + max((xfs_calc_inode_res(mp, 5) + xfs_calc_buf_res(2 * XFS_DIROP_LOG_COUNT(mp), XFS_FSB_TO_B(mp, 1))), (xfs_calc_buf_res(7, mp->m_sb.sb_sectsize) + diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h index a6b7d98cf68f..5ebdda7e1078 100644 --- a/fs/xfs/libxfs/xfs_types.h +++ b/fs/xfs/libxfs/xfs_types.h @@ -166,6 +166,36 @@ typedef struct xfs_bmbt_irec xfs_exntst_t br_state; /* extent state */ } xfs_bmbt_irec_t; +enum xfs_refc_domain { + XFS_REFC_DOMAIN_SHARED = 0, + XFS_REFC_DOMAIN_COW, +}; + +#define XFS_REFC_DOMAIN_STRINGS \ + { XFS_REFC_DOMAIN_SHARED, "shared" }, \ + { XFS_REFC_DOMAIN_COW, "cow" } + +struct xfs_refcount_irec { + xfs_agblock_t rc_startblock; /* starting block number */ + xfs_extlen_t rc_blockcount; /* count of free blocks */ + xfs_nlink_t rc_refcount; /* number of inodes linked here */ + enum xfs_refc_domain rc_domain; /* shared or cow staging extent? */ +}; + +#define XFS_RMAP_ATTR_FORK (1 << 0) +#define XFS_RMAP_BMBT_BLOCK (1 << 1) +#define XFS_RMAP_UNWRITTEN (1 << 2) +#define XFS_RMAP_KEY_FLAGS (XFS_RMAP_ATTR_FORK | \ + XFS_RMAP_BMBT_BLOCK) +#define XFS_RMAP_REC_FLAGS (XFS_RMAP_UNWRITTEN) +struct xfs_rmap_irec { + xfs_agblock_t rm_startblock; /* extent start block */ + xfs_extlen_t rm_blockcount; /* extent length */ + uint64_t rm_owner; /* extent owner */ + uint64_t rm_offset; /* offset within the owner */ + unsigned int rm_flags; /* state flags */ +}; + /* per-AG block reservation types */ enum xfs_ag_resv_type { XFS_AG_RESV_NONE = 0, diff --git a/fs/xfs/scrub/alloc.c b/fs/xfs/scrub/alloc.c index ab427b4d7fe0..3b38f4e2a537 100644 --- a/fs/xfs/scrub/alloc.c +++ b/fs/xfs/scrub/alloc.c @@ -100,9 +100,7 @@ xchk_allocbt_rec( bno = be32_to_cpu(rec->alloc.ar_startblock); len = be32_to_cpu(rec->alloc.ar_blockcount); - if (bno + len <= bno || - !xfs_verify_agbno(pag, bno) || - !xfs_verify_agbno(pag, bno + len - 1)) + if (!xfs_verify_agbext(pag, bno, len)) xchk_btree_set_corrupt(bs->sc, bs->cur, 0); xchk_allocbt_xref(bs->sc, bno, len); diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c index e1026e07bf94..e312be7cd375 100644 --- a/fs/xfs/scrub/ialloc.c +++ b/fs/xfs/scrub/ialloc.c @@ -108,9 +108,8 @@ xchk_iallocbt_chunk( xfs_agblock_t bno; bno = XFS_AGINO_TO_AGBNO(mp, agino); - if (bno + len <= bno || - !xfs_verify_agbno(pag, bno) || - !xfs_verify_agbno(pag, bno + len - 1)) + + if (!xfs_verify_agbext(pag, bno, len)) xchk_btree_set_corrupt(bs->sc, bs->cur, 0); xchk_iallocbt_chunk_xref(bs->sc, irec, agino, bno, len); diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c index c68b767dc08f..a26ee0f24ef2 100644 --- a/fs/xfs/scrub/refcount.c +++ b/fs/xfs/scrub/refcount.c @@ -269,15 +269,13 @@ done: STATIC void xchk_refcountbt_xref_rmap( struct xfs_scrub *sc, - xfs_agblock_t bno, - xfs_extlen_t len, - xfs_nlink_t refcount) + const struct xfs_refcount_irec *irec) { struct xchk_refcnt_check refchk = { - .sc = sc, - .bno = bno, - .len = len, - .refcount = refcount, + .sc = sc, + .bno = irec->rc_startblock, + .len = irec->rc_blockcount, + .refcount = irec->rc_refcount, .seen = 0, }; struct xfs_rmap_irec low; @@ -291,9 +289,9 @@ xchk_refcountbt_xref_rmap( /* Cross-reference with the rmapbt to confirm the refcount. */ memset(&low, 0, sizeof(low)); - low.rm_startblock = bno; + low.rm_startblock = irec->rc_startblock; memset(&high, 0xFF, sizeof(high)); - high.rm_startblock = bno + len - 1; + high.rm_startblock = irec->rc_startblock + irec->rc_blockcount - 1; INIT_LIST_HEAD(&refchk.fragments); error = xfs_rmap_query_range(sc->sa.rmap_cur, &low, &high, @@ -302,7 +300,7 @@ xchk_refcountbt_xref_rmap( goto out_free; xchk_refcountbt_process_rmap_fragments(&refchk); - if (refcount != refchk.seen) + if (irec->rc_refcount != refchk.seen) xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0); out_free: @@ -315,17 +313,16 @@ out_free: /* Cross-reference with the other btrees. */ STATIC void xchk_refcountbt_xref( - struct xfs_scrub *sc, - xfs_agblock_t agbno, - xfs_extlen_t len, - xfs_nlink_t refcount) + struct xfs_scrub *sc, + const struct xfs_refcount_irec *irec) { if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) return; - xchk_xref_is_used_space(sc, agbno, len); - xchk_xref_is_not_inode_chunk(sc, agbno, len); - xchk_refcountbt_xref_rmap(sc, agbno, len, refcount); + xchk_xref_is_used_space(sc, irec->rc_startblock, irec->rc_blockcount); + xchk_xref_is_not_inode_chunk(sc, irec->rc_startblock, + irec->rc_blockcount); + xchk_refcountbt_xref_rmap(sc, irec); } /* Scrub a refcountbt record. */ @@ -334,35 +331,27 @@ xchk_refcountbt_rec( struct xchk_btree *bs, const union xfs_btree_rec *rec) { + struct xfs_refcount_irec irec; xfs_agblock_t *cow_blocks = bs->private; struct xfs_perag *pag = bs->cur->bc_ag.pag; - xfs_agblock_t bno; - xfs_extlen_t len; - xfs_nlink_t refcount; - bool has_cowflag; - bno = be32_to_cpu(rec->refc.rc_startblock); - len = be32_to_cpu(rec->refc.rc_blockcount); - refcount = be32_to_cpu(rec->refc.rc_refcount); + xfs_refcount_btrec_to_irec(rec, &irec); - /* Only CoW records can have refcount == 1. */ - has_cowflag = (bno & XFS_REFC_COW_START); - if ((refcount == 1 && !has_cowflag) || (refcount != 1 && has_cowflag)) + /* Check the domain and refcount are not incompatible. */ + if (!xfs_refcount_check_domain(&irec)) xchk_btree_set_corrupt(bs->sc, bs->cur, 0); - if (has_cowflag) - (*cow_blocks) += len; + + if (irec.rc_domain == XFS_REFC_DOMAIN_COW) + (*cow_blocks) += irec.rc_blockcount; /* Check the extent. */ - bno &= ~XFS_REFC_COW_START; - if (bno + len <= bno || - !xfs_verify_agbno(pag, bno) || - !xfs_verify_agbno(pag, bno + len - 1)) + if (!xfs_verify_agbext(pag, irec.rc_startblock, irec.rc_blockcount)) xchk_btree_set_corrupt(bs->sc, bs->cur, 0); - if (refcount == 0) + if (irec.rc_refcount == 0) xchk_btree_set_corrupt(bs->sc, bs->cur, 0); - xchk_refcountbt_xref(bs->sc, bno, len, refcount); + xchk_refcountbt_xref(bs->sc, &irec); return 0; } @@ -426,7 +415,6 @@ xchk_xref_is_cow_staging( xfs_extlen_t len) { struct xfs_refcount_irec rc; - bool has_cowflag; int has_refcount; int error; @@ -434,8 +422,8 @@ xchk_xref_is_cow_staging( return; /* Find the CoW staging extent. */ - error = xfs_refcount_lookup_le(sc->sa.refc_cur, - agbno + XFS_REFC_COW_START, &has_refcount); + error = xfs_refcount_lookup_le(sc->sa.refc_cur, XFS_REFC_DOMAIN_COW, + agbno, &has_refcount); if (!xchk_should_check_xref(sc, &error, &sc->sa.refc_cur)) return; if (!has_refcount) { @@ -451,9 +439,8 @@ xchk_xref_is_cow_staging( return; } - /* CoW flag must be set, refcount must be 1. */ - has_cowflag = (rc.rc_startblock & XFS_REFC_COW_START); - if (!has_cowflag || rc.rc_refcount != 1) + /* CoW lookup returned a shared extent record? */ + if (rc.rc_domain != XFS_REFC_DOMAIN_COW) xchk_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0); /* Must be at least as long as what was passed in */ @@ -477,7 +464,8 @@ xchk_xref_is_not_shared( if (!sc->sa.refc_cur || xchk_skip_xref(sc->sm)) return; - error = xfs_refcount_has_record(sc->sa.refc_cur, agbno, len, &shared); + error = xfs_refcount_has_record(sc->sa.refc_cur, XFS_REFC_DOMAIN_SHARED, + agbno, len, &shared); if (!xchk_should_check_xref(sc, &error, &sc->sa.refc_cur)) return; if (shared) diff --git a/fs/xfs/xfs_attr_item.c b/fs/xfs/xfs_attr_item.c index cf5ce607dc05..2788a6f2edcd 100644 --- a/fs/xfs/xfs_attr_item.c +++ b/fs/xfs/xfs_attr_item.c @@ -245,28 +245,6 @@ xfs_attri_init( return attrip; } -/* - * Copy an attr format buffer from the given buf, and into the destination attr - * format structure. - */ -STATIC int -xfs_attri_copy_format( - struct xfs_log_iovec *buf, - struct xfs_attri_log_format *dst_attr_fmt) -{ - struct xfs_attri_log_format *src_attr_fmt = buf->i_addr; - size_t len; - - len = sizeof(struct xfs_attri_log_format); - if (buf->i_len != len) { - XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL); - return -EFSCORRUPTED; - } - - memcpy((char *)dst_attr_fmt, (char *)src_attr_fmt, len); - return 0; -} - static inline struct xfs_attrd_log_item *ATTRD_ITEM(struct xfs_log_item *lip) { return container_of(lip, struct xfs_attrd_log_item, attrd_item); @@ -731,24 +709,50 @@ xlog_recover_attri_commit_pass2( struct xfs_attri_log_nameval *nv; const void *attr_value = NULL; const void *attr_name; - int error; + size_t len; attri_formatp = item->ri_buf[0].i_addr; attr_name = item->ri_buf[1].i_addr; /* Validate xfs_attri_log_format before the large memory allocation */ + len = sizeof(struct xfs_attri_log_format); + if (item->ri_buf[0].i_len != len) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); + return -EFSCORRUPTED; + } + if (!xfs_attri_validate(mp, attri_formatp)) { - XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp); + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); + return -EFSCORRUPTED; + } + + /* Validate the attr name */ + if (item->ri_buf[1].i_len != + xlog_calc_iovec_len(attri_formatp->alfi_name_len)) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); return -EFSCORRUPTED; } if (!xfs_attr_namecheck(attr_name, attri_formatp->alfi_name_len)) { - XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp); + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + item->ri_buf[1].i_addr, item->ri_buf[1].i_len); return -EFSCORRUPTED; } - if (attri_formatp->alfi_value_len) + /* Validate the attr value, if present */ + if (attri_formatp->alfi_value_len != 0) { + if (item->ri_buf[2].i_len != xlog_calc_iovec_len(attri_formatp->alfi_value_len)) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + item->ri_buf[0].i_addr, + item->ri_buf[0].i_len); + return -EFSCORRUPTED; + } + attr_value = item->ri_buf[2].i_addr; + } /* * Memory alloc failure will cause replay to abort. We attach the @@ -760,9 +764,7 @@ xlog_recover_attri_commit_pass2( attri_formatp->alfi_value_len); attrip = xfs_attri_init(mp, nv); - error = xfs_attri_copy_format(&item->ri_buf[0], &attrip->attri_format); - if (error) - goto out; + memcpy(&attrip->attri_format, attri_formatp, len); /* * The ATTRI has two references. One for the ATTRD and one for ATTRI to @@ -774,10 +776,6 @@ xlog_recover_attri_commit_pass2( xfs_attri_release(attrip); xfs_attri_log_nameval_put(nv); return 0; -out: - xfs_attri_item_free(attrip); - xfs_attri_log_nameval_put(nv); - return error; } /* @@ -842,7 +840,8 @@ xlog_recover_attrd_commit_pass2( attrd_formatp = item->ri_buf[0].i_addr; if (item->ri_buf[0].i_len != sizeof(struct xfs_attrd_log_format)) { - XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL); + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); return -EFSCORRUPTED; } diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c index 51f66e982484..41323da523d1 100644 --- a/fs/xfs/xfs_bmap_item.c +++ b/fs/xfs/xfs_bmap_item.c @@ -608,28 +608,18 @@ static const struct xfs_item_ops xfs_bui_item_ops = { .iop_relog = xfs_bui_item_relog, }; -/* - * Copy an BUI format buffer from the given buf, and into the destination - * BUI format structure. The BUI/BUD items were designed not to need any - * special alignment handling. - */ -static int +static inline void xfs_bui_copy_format( - struct xfs_log_iovec *buf, - struct xfs_bui_log_format *dst_bui_fmt) + struct xfs_bui_log_format *dst, + const struct xfs_bui_log_format *src) { - struct xfs_bui_log_format *src_bui_fmt; - uint len; + unsigned int i; - src_bui_fmt = buf->i_addr; - len = xfs_bui_log_format_sizeof(src_bui_fmt->bui_nextents); + memcpy(dst, src, offsetof(struct xfs_bui_log_format, bui_extents)); - if (buf->i_len == len) { - memcpy(dst_bui_fmt, src_bui_fmt, len); - return 0; - } - XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL); - return -EFSCORRUPTED; + for (i = 0; i < src->bui_nextents; i++) + memcpy(&dst->bui_extents[i], &src->bui_extents[i], + sizeof(struct xfs_map_extent)); } /* @@ -646,23 +636,34 @@ xlog_recover_bui_commit_pass2( struct xlog_recover_item *item, xfs_lsn_t lsn) { - int error; struct xfs_mount *mp = log->l_mp; struct xfs_bui_log_item *buip; struct xfs_bui_log_format *bui_formatp; + size_t len; bui_formatp = item->ri_buf[0].i_addr; + if (item->ri_buf[0].i_len < xfs_bui_log_format_sizeof(0)) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); + return -EFSCORRUPTED; + } + if (bui_formatp->bui_nextents != XFS_BUI_MAX_FAST_EXTENTS) { - XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, log->l_mp); + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); return -EFSCORRUPTED; } - buip = xfs_bui_init(mp); - error = xfs_bui_copy_format(&item->ri_buf[0], &buip->bui_format); - if (error) { - xfs_bui_item_free(buip); - return error; + + len = xfs_bui_log_format_sizeof(bui_formatp->bui_nextents); + if (item->ri_buf[0].i_len != len) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); + return -EFSCORRUPTED; } + + buip = xfs_bui_init(mp); + xfs_bui_copy_format(&buip->bui_format, bui_formatp); atomic_set(&buip->bui_next_extent, bui_formatp->bui_nextents); /* * Insert the intent into the AIL directly and drop one reference so @@ -696,7 +697,8 @@ xlog_recover_bud_commit_pass2( bud_formatp = item->ri_buf[0].i_addr; if (item->ri_buf[0].i_len != sizeof(struct xfs_bud_log_format)) { - XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, log->l_mp); + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); return -EFSCORRUPTED; } diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c index 7db588ed0be5..c6b2aabd6f18 100644 --- a/fs/xfs/xfs_error.c +++ b/fs/xfs/xfs_error.c @@ -234,13 +234,18 @@ int xfs_errortag_init( struct xfs_mount *mp) { + int ret; + mp->m_errortag = kmem_zalloc(sizeof(unsigned int) * XFS_ERRTAG_MAX, KM_MAYFAIL); if (!mp->m_errortag) return -ENOMEM; - return xfs_sysfs_init(&mp->m_errortag_kobj, &xfs_errortag_ktype, - &mp->m_kobj, "errortag"); + ret = xfs_sysfs_init(&mp->m_errortag_kobj, &xfs_errortag_ktype, + &mp->m_kobj, "errortag"); + if (ret) + kmem_free(mp->m_errortag); + return ret; } void diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c index 27ccfcd82f04..d5130d1fcfae 100644 --- a/fs/xfs/xfs_extfree_item.c +++ b/fs/xfs/xfs_extfree_item.c @@ -66,27 +66,16 @@ xfs_efi_release( xfs_efi_item_free(efip); } -/* - * This returns the number of iovecs needed to log the given efi item. - * We only need 1 iovec for an efi item. It just logs the efi_log_format - * structure. - */ -static inline int -xfs_efi_item_sizeof( - struct xfs_efi_log_item *efip) -{ - return sizeof(struct xfs_efi_log_format) + - (efip->efi_format.efi_nextents - 1) * sizeof(xfs_extent_t); -} - STATIC void xfs_efi_item_size( struct xfs_log_item *lip, int *nvecs, int *nbytes) { + struct xfs_efi_log_item *efip = EFI_ITEM(lip); + *nvecs += 1; - *nbytes += xfs_efi_item_sizeof(EFI_ITEM(lip)); + *nbytes += xfs_efi_log_format_sizeof(efip->efi_format.efi_nextents); } /* @@ -112,7 +101,7 @@ xfs_efi_item_format( xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_EFI_FORMAT, &efip->efi_format, - xfs_efi_item_sizeof(efip)); + xfs_efi_log_format_sizeof(efip->efi_format.efi_nextents)); } @@ -155,13 +144,11 @@ xfs_efi_init( { struct xfs_efi_log_item *efip; - uint size; ASSERT(nextents > 0); if (nextents > XFS_EFI_MAX_FAST_EXTENTS) { - size = (uint)(sizeof(struct xfs_efi_log_item) + - ((nextents - 1) * sizeof(xfs_extent_t))); - efip = kmem_zalloc(size, 0); + efip = kzalloc(xfs_efi_log_item_sizeof(nextents), + GFP_KERNEL | __GFP_NOFAIL); } else { efip = kmem_cache_zalloc(xfs_efi_cache, GFP_KERNEL | __GFP_NOFAIL); @@ -188,15 +175,17 @@ xfs_efi_copy_format(xfs_log_iovec_t *buf, xfs_efi_log_format_t *dst_efi_fmt) { xfs_efi_log_format_t *src_efi_fmt = buf->i_addr; uint i; - uint len = sizeof(xfs_efi_log_format_t) + - (src_efi_fmt->efi_nextents - 1) * sizeof(xfs_extent_t); - uint len32 = sizeof(xfs_efi_log_format_32_t) + - (src_efi_fmt->efi_nextents - 1) * sizeof(xfs_extent_32_t); - uint len64 = sizeof(xfs_efi_log_format_64_t) + - (src_efi_fmt->efi_nextents - 1) * sizeof(xfs_extent_64_t); + uint len = xfs_efi_log_format_sizeof(src_efi_fmt->efi_nextents); + uint len32 = xfs_efi_log_format32_sizeof(src_efi_fmt->efi_nextents); + uint len64 = xfs_efi_log_format64_sizeof(src_efi_fmt->efi_nextents); if (buf->i_len == len) { - memcpy((char *)dst_efi_fmt, (char*)src_efi_fmt, len); + memcpy(dst_efi_fmt, src_efi_fmt, + offsetof(struct xfs_efi_log_format, efi_extents)); + for (i = 0; i < src_efi_fmt->efi_nextents; i++) + memcpy(&dst_efi_fmt->efi_extents[i], + &src_efi_fmt->efi_extents[i], + sizeof(struct xfs_extent)); return 0; } else if (buf->i_len == len32) { xfs_efi_log_format_32_t *src_efi_fmt_32 = buf->i_addr; @@ -227,7 +216,8 @@ xfs_efi_copy_format(xfs_log_iovec_t *buf, xfs_efi_log_format_t *dst_efi_fmt) } return 0; } - XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL); + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, NULL, buf->i_addr, + buf->i_len); return -EFSCORRUPTED; } @@ -246,27 +236,16 @@ xfs_efd_item_free(struct xfs_efd_log_item *efdp) kmem_cache_free(xfs_efd_cache, efdp); } -/* - * This returns the number of iovecs needed to log the given efd item. - * We only need 1 iovec for an efd item. It just logs the efd_log_format - * structure. - */ -static inline int -xfs_efd_item_sizeof( - struct xfs_efd_log_item *efdp) -{ - return sizeof(xfs_efd_log_format_t) + - (efdp->efd_format.efd_nextents - 1) * sizeof(xfs_extent_t); -} - STATIC void xfs_efd_item_size( struct xfs_log_item *lip, int *nvecs, int *nbytes) { + struct xfs_efd_log_item *efdp = EFD_ITEM(lip); + *nvecs += 1; - *nbytes += xfs_efd_item_sizeof(EFD_ITEM(lip)); + *nbytes += xfs_efd_log_format_sizeof(efdp->efd_format.efd_nextents); } /* @@ -291,7 +270,7 @@ xfs_efd_item_format( xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_EFD_FORMAT, &efdp->efd_format, - xfs_efd_item_sizeof(efdp)); + xfs_efd_log_format_sizeof(efdp->efd_format.efd_nextents)); } /* @@ -340,9 +319,8 @@ xfs_trans_get_efd( ASSERT(nextents > 0); if (nextents > XFS_EFD_MAX_FAST_EXTENTS) { - efdp = kmem_zalloc(sizeof(struct xfs_efd_log_item) + - (nextents - 1) * sizeof(struct xfs_extent), - 0); + efdp = kzalloc(xfs_efd_log_item_sizeof(nextents), + GFP_KERNEL | __GFP_NOFAIL); } else { efdp = kmem_cache_zalloc(xfs_efd_cache, GFP_KERNEL | __GFP_NOFAIL); @@ -733,6 +711,12 @@ xlog_recover_efi_commit_pass2( efi_formatp = item->ri_buf[0].i_addr; + if (item->ri_buf[0].i_len < xfs_efi_log_format_sizeof(0)) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); + return -EFSCORRUPTED; + } + efip = xfs_efi_init(mp, efi_formatp->efi_nextents); error = xfs_efi_copy_format(&item->ri_buf[0], &efip->efi_format); if (error) { @@ -769,12 +753,24 @@ xlog_recover_efd_commit_pass2( xfs_lsn_t lsn) { struct xfs_efd_log_format *efd_formatp; + int buflen = item->ri_buf[0].i_len; efd_formatp = item->ri_buf[0].i_addr; - ASSERT((item->ri_buf[0].i_len == (sizeof(xfs_efd_log_format_32_t) + - ((efd_formatp->efd_nextents - 1) * sizeof(xfs_extent_32_t)))) || - (item->ri_buf[0].i_len == (sizeof(xfs_efd_log_format_64_t) + - ((efd_formatp->efd_nextents - 1) * sizeof(xfs_extent_64_t))))); + + if (buflen < sizeof(struct xfs_efd_log_format)) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp, + efd_formatp, buflen); + return -EFSCORRUPTED; + } + + if (item->ri_buf[0].i_len != xfs_efd_log_format32_sizeof( + efd_formatp->efd_nextents) && + item->ri_buf[0].i_len != xfs_efd_log_format64_sizeof( + efd_formatp->efd_nextents)) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp, + efd_formatp, buflen); + return -EFSCORRUPTED; + } xlog_recover_release_intent(log, XFS_LI_EFI, efd_formatp->efd_efi_id); return 0; diff --git a/fs/xfs/xfs_extfree_item.h b/fs/xfs/xfs_extfree_item.h index 186d0f2137f1..da6a5afa607c 100644 --- a/fs/xfs/xfs_extfree_item.h +++ b/fs/xfs/xfs_extfree_item.h @@ -52,6 +52,14 @@ struct xfs_efi_log_item { xfs_efi_log_format_t efi_format; }; +static inline size_t +xfs_efi_log_item_sizeof( + unsigned int nr) +{ + return offsetof(struct xfs_efi_log_item, efi_format) + + xfs_efi_log_format_sizeof(nr); +} + /* * This is the "extent free done" log item. It is used to log * the fact that some extents earlier mentioned in an efi item @@ -64,6 +72,14 @@ struct xfs_efd_log_item { xfs_efd_log_format_t efd_format; }; +static inline size_t +xfs_efd_log_item_sizeof( + unsigned int nr) +{ + return offsetof(struct xfs_efd_log_item, efd_format) + + xfs_efd_log_format_sizeof(nr); +} + /* * Max number of extents in fast allocation path. */ diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index c6c80265c0b2..e462d39c840e 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -1261,7 +1261,7 @@ xfs_file_llseek( } #ifdef CONFIG_FS_DAX -static int +static inline vm_fault_t xfs_dax_fault( struct vm_fault *vmf, enum page_entry_size pe_size, @@ -1274,14 +1274,15 @@ xfs_dax_fault( &xfs_read_iomap_ops); } #else -static int +static inline vm_fault_t xfs_dax_fault( struct vm_fault *vmf, enum page_entry_size pe_size, bool write_fault, pfn_t *pfn) { - return 0; + ASSERT(0); + return VM_FAULT_SIGBUS; } #endif diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index c000b74dd203..aa303be11576 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -2818,7 +2818,7 @@ retry: * Lock all the participating inodes. Depending upon whether * the target_name exists in the target directory, and * whether the target directory is the same as the source - * directory, we can lock from 2 to 4 inodes. + * directory, we can lock from 2 to 5 inodes. */ xfs_lock_inodes(inodes, num_inodes, XFS_ILOCK_EXCL); diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 17e923b9c5fa..322eb2ee6c55 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -2552,6 +2552,8 @@ xlog_recover_process_intents( for (lip = xfs_trans_ail_cursor_first(ailp, &cur, 0); lip != NULL; lip = xfs_trans_ail_cursor_next(ailp, &cur)) { + const struct xfs_item_ops *ops; + if (!xlog_item_is_intent(lip)) break; @@ -2567,13 +2569,17 @@ xlog_recover_process_intents( * deferred ops, you /must/ attach them to the capture list in * the recover routine or else those subsequent intents will be * replayed in the wrong order! + * + * The recovery function can free the log item, so we must not + * access lip after it returns. */ spin_unlock(&ailp->ail_lock); - error = lip->li_ops->iop_recover(lip, &capture_list); + ops = lip->li_ops; + error = ops->iop_recover(lip, &capture_list); spin_lock(&ailp->ail_lock); if (error) { trace_xlog_intent_recovery_failed(log->l_mp, error, - lip->li_ops->iop_recover); + ops->iop_recover); break; } } diff --git a/fs/xfs/xfs_ondisk.h b/fs/xfs/xfs_ondisk.h index 758702b9495f..9737b5a9f405 100644 --- a/fs/xfs/xfs_ondisk.h +++ b/fs/xfs/xfs_ondisk.h @@ -118,10 +118,10 @@ xfs_check_ondisk_structs(void) /* log structures */ XFS_CHECK_STRUCT_SIZE(struct xfs_buf_log_format, 88); XFS_CHECK_STRUCT_SIZE(struct xfs_dq_logformat, 24); - XFS_CHECK_STRUCT_SIZE(struct xfs_efd_log_format_32, 28); - XFS_CHECK_STRUCT_SIZE(struct xfs_efd_log_format_64, 32); - XFS_CHECK_STRUCT_SIZE(struct xfs_efi_log_format_32, 28); - XFS_CHECK_STRUCT_SIZE(struct xfs_efi_log_format_64, 32); + XFS_CHECK_STRUCT_SIZE(struct xfs_efd_log_format_32, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_efd_log_format_64, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_efi_log_format_32, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_efi_log_format_64, 16); XFS_CHECK_STRUCT_SIZE(struct xfs_extent_32, 12); XFS_CHECK_STRUCT_SIZE(struct xfs_extent_64, 16); XFS_CHECK_STRUCT_SIZE(struct xfs_log_dinode, 176); @@ -134,6 +134,21 @@ xfs_check_ondisk_structs(void) XFS_CHECK_STRUCT_SIZE(struct xfs_trans_header, 16); XFS_CHECK_STRUCT_SIZE(struct xfs_attri_log_format, 40); XFS_CHECK_STRUCT_SIZE(struct xfs_attrd_log_format, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_bui_log_format, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_bud_log_format, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_cui_log_format, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_cud_log_format, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_rui_log_format, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_rud_log_format, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_map_extent, 32); + XFS_CHECK_STRUCT_SIZE(struct xfs_phys_extent, 16); + + XFS_CHECK_OFFSET(struct xfs_bui_log_format, bui_extents, 16); + XFS_CHECK_OFFSET(struct xfs_cui_log_format, cui_extents, 16); + XFS_CHECK_OFFSET(struct xfs_rui_log_format, rui_extents, 16); + XFS_CHECK_OFFSET(struct xfs_efi_log_format, efi_extents, 16); + XFS_CHECK_OFFSET(struct xfs_efi_log_format_32, efi_extents, 16); + XFS_CHECK_OFFSET(struct xfs_efi_log_format_64, efi_extents, 16); /* * The v5 superblock format extended several v4 header structures with diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c index 7e97bf19793d..858e3e9eb4a8 100644 --- a/fs/xfs/xfs_refcount_item.c +++ b/fs/xfs/xfs_refcount_item.c @@ -523,7 +523,9 @@ xfs_cui_item_recover( type = refc_type; break; default: - XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp); + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + &cuip->cui_format, + sizeof(cuip->cui_format)); error = -EFSCORRUPTED; goto abort_error; } @@ -536,7 +538,8 @@ xfs_cui_item_recover( &new_fsb, &new_len, &rcur); if (error == -EFSCORRUPTED) XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, - refc, sizeof(*refc)); + &cuip->cui_format, + sizeof(cuip->cui_format)); if (error) goto abort_error; @@ -622,28 +625,18 @@ static const struct xfs_item_ops xfs_cui_item_ops = { .iop_relog = xfs_cui_item_relog, }; -/* - * Copy an CUI format buffer from the given buf, and into the destination - * CUI format structure. The CUI/CUD items were designed not to need any - * special alignment handling. - */ -static int +static inline void xfs_cui_copy_format( - struct xfs_log_iovec *buf, - struct xfs_cui_log_format *dst_cui_fmt) + struct xfs_cui_log_format *dst, + const struct xfs_cui_log_format *src) { - struct xfs_cui_log_format *src_cui_fmt; - uint len; + unsigned int i; - src_cui_fmt = buf->i_addr; - len = xfs_cui_log_format_sizeof(src_cui_fmt->cui_nextents); + memcpy(dst, src, offsetof(struct xfs_cui_log_format, cui_extents)); - if (buf->i_len == len) { - memcpy(dst_cui_fmt, src_cui_fmt, len); - return 0; - } - XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL); - return -EFSCORRUPTED; + for (i = 0; i < src->cui_nextents; i++) + memcpy(&dst->cui_extents[i], &src->cui_extents[i], + sizeof(struct xfs_phys_extent)); } /* @@ -660,19 +653,28 @@ xlog_recover_cui_commit_pass2( struct xlog_recover_item *item, xfs_lsn_t lsn) { - int error; struct xfs_mount *mp = log->l_mp; struct xfs_cui_log_item *cuip; struct xfs_cui_log_format *cui_formatp; + size_t len; cui_formatp = item->ri_buf[0].i_addr; - cuip = xfs_cui_init(mp, cui_formatp->cui_nextents); - error = xfs_cui_copy_format(&item->ri_buf[0], &cuip->cui_format); - if (error) { - xfs_cui_item_free(cuip); - return error; + if (item->ri_buf[0].i_len < xfs_cui_log_format_sizeof(0)) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); + return -EFSCORRUPTED; } + + len = xfs_cui_log_format_sizeof(cui_formatp->cui_nextents); + if (item->ri_buf[0].i_len != len) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); + return -EFSCORRUPTED; + } + + cuip = xfs_cui_init(mp, cui_formatp->cui_nextents); + xfs_cui_copy_format(&cuip->cui_format, cui_formatp); atomic_set(&cuip->cui_next_extent, cui_formatp->cui_nextents); /* * Insert the intent into the AIL directly and drop one reference so @@ -706,7 +708,8 @@ xlog_recover_cud_commit_pass2( cud_formatp = item->ri_buf[0].i_addr; if (item->ri_buf[0].i_len != sizeof(struct xfs_cud_log_format)) { - XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, log->l_mp); + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); return -EFSCORRUPTED; } diff --git a/fs/xfs/xfs_rmap_item.c b/fs/xfs/xfs_rmap_item.c index fef92e02f3bb..534504ede1a3 100644 --- a/fs/xfs/xfs_rmap_item.c +++ b/fs/xfs/xfs_rmap_item.c @@ -155,31 +155,6 @@ xfs_rui_init( return ruip; } -/* - * Copy an RUI format buffer from the given buf, and into the destination - * RUI format structure. The RUI/RUD items were designed not to need any - * special alignment handling. - */ -STATIC int -xfs_rui_copy_format( - struct xfs_log_iovec *buf, - struct xfs_rui_log_format *dst_rui_fmt) -{ - struct xfs_rui_log_format *src_rui_fmt; - uint len; - - src_rui_fmt = buf->i_addr; - len = xfs_rui_log_format_sizeof(src_rui_fmt->rui_nextents); - - if (buf->i_len != len) { - XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL); - return -EFSCORRUPTED; - } - - memcpy(dst_rui_fmt, src_rui_fmt, len); - return 0; -} - static inline struct xfs_rud_log_item *RUD_ITEM(struct xfs_log_item *lip) { return container_of(lip, struct xfs_rud_log_item, rud_item); @@ -582,7 +557,9 @@ xfs_rui_item_recover( type = XFS_RMAP_FREE; break; default: - XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL); + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + &ruip->rui_format, + sizeof(ruip->rui_format)); error = -EFSCORRUPTED; goto abort_error; } @@ -652,6 +629,20 @@ static const struct xfs_item_ops xfs_rui_item_ops = { .iop_relog = xfs_rui_item_relog, }; +static inline void +xfs_rui_copy_format( + struct xfs_rui_log_format *dst, + const struct xfs_rui_log_format *src) +{ + unsigned int i; + + memcpy(dst, src, offsetof(struct xfs_rui_log_format, rui_extents)); + + for (i = 0; i < src->rui_nextents; i++) + memcpy(&dst->rui_extents[i], &src->rui_extents[i], + sizeof(struct xfs_map_extent)); +} + /* * This routine is called to create an in-core extent rmap update * item from the rui format structure which was logged on disk. @@ -666,19 +657,28 @@ xlog_recover_rui_commit_pass2( struct xlog_recover_item *item, xfs_lsn_t lsn) { - int error; struct xfs_mount *mp = log->l_mp; struct xfs_rui_log_item *ruip; struct xfs_rui_log_format *rui_formatp; + size_t len; rui_formatp = item->ri_buf[0].i_addr; - ruip = xfs_rui_init(mp, rui_formatp->rui_nextents); - error = xfs_rui_copy_format(&item->ri_buf[0], &ruip->rui_format); - if (error) { - xfs_rui_item_free(ruip); - return error; + if (item->ri_buf[0].i_len < xfs_rui_log_format_sizeof(0)) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); + return -EFSCORRUPTED; + } + + len = xfs_rui_log_format_sizeof(rui_formatp->rui_nextents); + if (item->ri_buf[0].i_len != len) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); + return -EFSCORRUPTED; } + + ruip = xfs_rui_init(mp, rui_formatp->rui_nextents); + xfs_rui_copy_format(&ruip->rui_format, rui_formatp); atomic_set(&ruip->rui_next_extent, rui_formatp->rui_nextents); /* * Insert the intent into the AIL directly and drop one reference so @@ -711,7 +711,11 @@ xlog_recover_rud_commit_pass2( struct xfs_rud_log_format *rud_formatp; rud_formatp = item->ri_buf[0].i_addr; - ASSERT(item->ri_buf[0].i_len == sizeof(struct xfs_rud_log_format)); + if (item->ri_buf[0].i_len != sizeof(struct xfs_rud_log_format)) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp, + rud_formatp, item->ri_buf[0].i_len); + return -EFSCORRUPTED; + } xlog_recover_release_intent(log, XFS_LI_RUI, rud_formatp->rud_rui_id); return 0; diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index f029c6702dda..ee4b429a2f2c 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -2028,18 +2028,14 @@ xfs_init_caches(void) goto out_destroy_trans_cache; xfs_efd_cache = kmem_cache_create("xfs_efd_item", - (sizeof(struct xfs_efd_log_item) + - (XFS_EFD_MAX_FAST_EXTENTS - 1) * - sizeof(struct xfs_extent)), - 0, 0, NULL); + xfs_efd_log_item_sizeof(XFS_EFD_MAX_FAST_EXTENTS), + 0, 0, NULL); if (!xfs_efd_cache) goto out_destroy_buf_item_cache; xfs_efi_cache = kmem_cache_create("xfs_efi_item", - (sizeof(struct xfs_efi_log_item) + - (XFS_EFI_MAX_FAST_EXTENTS - 1) * - sizeof(struct xfs_extent)), - 0, 0, NULL); + xfs_efi_log_item_sizeof(XFS_EFI_MAX_FAST_EXTENTS), + 0, 0, NULL); if (!xfs_efi_cache) goto out_destroy_efd_cache; diff --git a/fs/xfs/xfs_sysfs.h b/fs/xfs/xfs_sysfs.h index 43585850f154..513095e353a5 100644 --- a/fs/xfs/xfs_sysfs.h +++ b/fs/xfs/xfs_sysfs.h @@ -33,10 +33,15 @@ xfs_sysfs_init( const char *name) { struct kobject *parent; + int err; parent = parent_kobj ? &parent_kobj->kobject : NULL; init_completion(&kobj->complete); - return kobject_init_and_add(&kobj->kobject, ktype, parent, "%s", name); + err = kobject_init_and_add(&kobj->kobject, ktype, parent, "%s", name); + if (err) + kobject_put(&kobj->kobject); + + return err; } static inline void diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index cb7c81ba7fa3..372d871bccc5 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -799,6 +799,9 @@ TRACE_DEFINE_ENUM(PE_SIZE_PTE); TRACE_DEFINE_ENUM(PE_SIZE_PMD); TRACE_DEFINE_ENUM(PE_SIZE_PUD); +TRACE_DEFINE_ENUM(XFS_REFC_DOMAIN_SHARED); +TRACE_DEFINE_ENUM(XFS_REFC_DOMAIN_COW); + TRACE_EVENT(xfs_filemap_fault, TP_PROTO(struct xfs_inode *ip, enum page_entry_size pe_size, bool write_fault), @@ -2925,6 +2928,7 @@ DECLARE_EVENT_CLASS(xfs_refcount_extent_class, TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_agnumber_t, agno) + __field(enum xfs_refc_domain, domain) __field(xfs_agblock_t, startblock) __field(xfs_extlen_t, blockcount) __field(xfs_nlink_t, refcount) @@ -2932,13 +2936,15 @@ DECLARE_EVENT_CLASS(xfs_refcount_extent_class, TP_fast_assign( __entry->dev = mp->m_super->s_dev; __entry->agno = agno; + __entry->domain = irec->rc_domain; __entry->startblock = irec->rc_startblock; __entry->blockcount = irec->rc_blockcount; __entry->refcount = irec->rc_refcount; ), - TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x refcount %u", + TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->agno, + __print_symbolic(__entry->domain, XFS_REFC_DOMAIN_STRINGS), __entry->startblock, __entry->blockcount, __entry->refcount) @@ -2958,6 +2964,7 @@ DECLARE_EVENT_CLASS(xfs_refcount_extent_at_class, TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_agnumber_t, agno) + __field(enum xfs_refc_domain, domain) __field(xfs_agblock_t, startblock) __field(xfs_extlen_t, blockcount) __field(xfs_nlink_t, refcount) @@ -2966,14 +2973,16 @@ DECLARE_EVENT_CLASS(xfs_refcount_extent_at_class, TP_fast_assign( __entry->dev = mp->m_super->s_dev; __entry->agno = agno; + __entry->domain = irec->rc_domain; __entry->startblock = irec->rc_startblock; __entry->blockcount = irec->rc_blockcount; __entry->refcount = irec->rc_refcount; __entry->agbno = agbno; ), - TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x refcount %u @ agbno 0x%x", + TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u @ agbno 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->agno, + __print_symbolic(__entry->domain, XFS_REFC_DOMAIN_STRINGS), __entry->startblock, __entry->blockcount, __entry->refcount, @@ -2994,9 +3003,11 @@ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_class, TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_agnumber_t, agno) + __field(enum xfs_refc_domain, i1_domain) __field(xfs_agblock_t, i1_startblock) __field(xfs_extlen_t, i1_blockcount) __field(xfs_nlink_t, i1_refcount) + __field(enum xfs_refc_domain, i2_domain) __field(xfs_agblock_t, i2_startblock) __field(xfs_extlen_t, i2_blockcount) __field(xfs_nlink_t, i2_refcount) @@ -3004,20 +3015,24 @@ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_class, TP_fast_assign( __entry->dev = mp->m_super->s_dev; __entry->agno = agno; + __entry->i1_domain = i1->rc_domain; __entry->i1_startblock = i1->rc_startblock; __entry->i1_blockcount = i1->rc_blockcount; __entry->i1_refcount = i1->rc_refcount; + __entry->i2_domain = i2->rc_domain; __entry->i2_startblock = i2->rc_startblock; __entry->i2_blockcount = i2->rc_blockcount; __entry->i2_refcount = i2->rc_refcount; ), - TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x refcount %u -- " - "agbno 0x%x fsbcount 0x%x refcount %u", + TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u -- " + "dom %s agbno 0x%x fsbcount 0x%x refcount %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->agno, + __print_symbolic(__entry->i1_domain, XFS_REFC_DOMAIN_STRINGS), __entry->i1_startblock, __entry->i1_blockcount, __entry->i1_refcount, + __print_symbolic(__entry->i2_domain, XFS_REFC_DOMAIN_STRINGS), __entry->i2_startblock, __entry->i2_blockcount, __entry->i2_refcount) @@ -3038,9 +3053,11 @@ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_at_class, TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_agnumber_t, agno) + __field(enum xfs_refc_domain, i1_domain) __field(xfs_agblock_t, i1_startblock) __field(xfs_extlen_t, i1_blockcount) __field(xfs_nlink_t, i1_refcount) + __field(enum xfs_refc_domain, i2_domain) __field(xfs_agblock_t, i2_startblock) __field(xfs_extlen_t, i2_blockcount) __field(xfs_nlink_t, i2_refcount) @@ -3049,21 +3066,25 @@ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_at_class, TP_fast_assign( __entry->dev = mp->m_super->s_dev; __entry->agno = agno; + __entry->i1_domain = i1->rc_domain; __entry->i1_startblock = i1->rc_startblock; __entry->i1_blockcount = i1->rc_blockcount; __entry->i1_refcount = i1->rc_refcount; + __entry->i2_domain = i2->rc_domain; __entry->i2_startblock = i2->rc_startblock; __entry->i2_blockcount = i2->rc_blockcount; __entry->i2_refcount = i2->rc_refcount; __entry->agbno = agbno; ), - TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x refcount %u -- " - "agbno 0x%x fsbcount 0x%x refcount %u @ agbno 0x%x", + TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u -- " + "dom %s agbno 0x%x fsbcount 0x%x refcount %u @ agbno 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->agno, + __print_symbolic(__entry->i1_domain, XFS_REFC_DOMAIN_STRINGS), __entry->i1_startblock, __entry->i1_blockcount, __entry->i1_refcount, + __print_symbolic(__entry->i2_domain, XFS_REFC_DOMAIN_STRINGS), __entry->i2_startblock, __entry->i2_blockcount, __entry->i2_refcount, @@ -3086,12 +3107,15 @@ DECLARE_EVENT_CLASS(xfs_refcount_triple_extent_class, TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_agnumber_t, agno) + __field(enum xfs_refc_domain, i1_domain) __field(xfs_agblock_t, i1_startblock) __field(xfs_extlen_t, i1_blockcount) __field(xfs_nlink_t, i1_refcount) + __field(enum xfs_refc_domain, i2_domain) __field(xfs_agblock_t, i2_startblock) __field(xfs_extlen_t, i2_blockcount) __field(xfs_nlink_t, i2_refcount) + __field(enum xfs_refc_domain, i3_domain) __field(xfs_agblock_t, i3_startblock) __field(xfs_extlen_t, i3_blockcount) __field(xfs_nlink_t, i3_refcount) @@ -3099,27 +3123,33 @@ DECLARE_EVENT_CLASS(xfs_refcount_triple_extent_class, TP_fast_assign( __entry->dev = mp->m_super->s_dev; __entry->agno = agno; + __entry->i1_domain = i1->rc_domain; __entry->i1_startblock = i1->rc_startblock; __entry->i1_blockcount = i1->rc_blockcount; __entry->i1_refcount = i1->rc_refcount; + __entry->i2_domain = i2->rc_domain; __entry->i2_startblock = i2->rc_startblock; __entry->i2_blockcount = i2->rc_blockcount; __entry->i2_refcount = i2->rc_refcount; + __entry->i3_domain = i3->rc_domain; __entry->i3_startblock = i3->rc_startblock; __entry->i3_blockcount = i3->rc_blockcount; __entry->i3_refcount = i3->rc_refcount; ), - TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x refcount %u -- " - "agbno 0x%x fsbcount 0x%x refcount %u -- " - "agbno 0x%x fsbcount 0x%x refcount %u", + TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u -- " + "dom %s agbno 0x%x fsbcount 0x%x refcount %u -- " + "dom %s agbno 0x%x fsbcount 0x%x refcount %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->agno, + __print_symbolic(__entry->i1_domain, XFS_REFC_DOMAIN_STRINGS), __entry->i1_startblock, __entry->i1_blockcount, __entry->i1_refcount, + __print_symbolic(__entry->i2_domain, XFS_REFC_DOMAIN_STRINGS), __entry->i2_startblock, __entry->i2_blockcount, __entry->i2_refcount, + __print_symbolic(__entry->i3_domain, XFS_REFC_DOMAIN_STRINGS), __entry->i3_startblock, __entry->i3_blockcount, __entry->i3_refcount) diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c index 16fbf2a1144c..f51df7d94ef7 100644 --- a/fs/xfs/xfs_trans_ail.c +++ b/fs/xfs/xfs_trans_ail.c @@ -730,11 +730,10 @@ void xfs_ail_push_all_sync( struct xfs_ail *ailp) { - struct xfs_log_item *lip; DEFINE_WAIT(wait); spin_lock(&ailp->ail_lock); - while ((lip = xfs_ail_max(ailp)) != NULL) { + while (xfs_ail_max(ailp) != NULL) { prepare_to_wait(&ailp->ail_empty, &wait, TASK_UNINTERRUPTIBLE); wake_up_process(ailp->ail_task); spin_unlock(&ailp->ail_lock); diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 58f5431a5559..982ba245eb41 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -152,6 +152,22 @@ static inline bool can_is_canxl_dev_mtu(unsigned int mtu) return (mtu >= CANXL_MIN_MTU && mtu <= CANXL_MAX_MTU); } +/* drop skb if it does not contain a valid CAN frame for sending */ +static inline bool can_dev_dropped_skb(struct net_device *dev, struct sk_buff *skb) +{ + struct can_priv *priv = netdev_priv(dev); + + if (priv->ctrlmode & CAN_CTRLMODE_LISTENONLY) { + netdev_info_once(dev, + "interface in listen only mode, dropping skb\n"); + kfree_skb(skb); + dev->stats.tx_dropped++; + return true; + } + + return can_dropped_invalid_skb(dev, skb); +} + void can_setup(struct net_device *dev); struct net_device *alloc_candev_mqs(int sizeof_priv, unsigned int echo_skb_max, diff --git a/include/linux/efi.h b/include/linux/efi.h index 80f3c1c7827d..929d559ad41d 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1222,7 +1222,7 @@ efi_status_t efi_random_get_seed(void); arch_efi_call_virt_teardown(); \ }) -#define EFI_RANDOM_SEED_SIZE 64U +#define EFI_RANDOM_SEED_SIZE 32U // BLAKE2S_HASH_SIZE struct linux_efi_random_seed { u32 size; diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 99dc7bfbcd3c..5c51c7fda32a 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -125,6 +125,20 @@ struct ethtool_link_ext_state_info { }; }; +struct ethtool_link_ext_stats { + /* Custom Linux statistic for PHY level link down events. + * In a simpler world it should be equal to netdev->carrier_down_count + * unfortunately netdev also counts local reconfigurations which don't + * actually take the physical link down, not to mention NC-SI which, + * if present, keeps the link up regardless of host state. + * This statistic counts when PHY _actually_ went down, or lost link. + * + * Note that we need u64 for ethtool_stats_init() and comparisons + * to ETHTOOL_STAT_NOT_SET, but only u32 is exposed to the user. + */ + u64 link_down_events; +}; + /** * ethtool_rxfh_indir_default - get default value for RX flow hash indirection * @index: Index in RX flow hash indirection table @@ -481,6 +495,7 @@ struct ethtool_module_power_mode_params { * do not attach ext_substate attribute to netlink message). If link_ext_state * and link_ext_substate are unknown, return -ENODATA. If not implemented, * link_ext_state and link_ext_substate will not be sent to userspace. + * @get_link_ext_stats: Read extra link-related counters. * @get_eeprom_len: Read range of EEPROM addresses for validation of * @get_eeprom and @set_eeprom requests. * Returns 0 if device does not support EEPROM access. @@ -652,6 +667,8 @@ struct ethtool_ops { u32 (*get_link)(struct net_device *); int (*get_link_ext_state)(struct net_device *, struct ethtool_link_ext_state_info *); + void (*get_link_ext_stats)(struct net_device *dev, + struct ethtool_link_ext_stats *stats); int (*get_eeprom_len)(struct net_device *); int (*get_eeprom)(struct net_device *, struct ethtool_eeprom *, u8 *); diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index 18a31b125f9d..1067a8450826 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -454,13 +454,18 @@ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size, #define __fortify_memcpy_chk(p, q, size, p_size, q_size, \ p_size_field, q_size_field, op) ({ \ - size_t __fortify_size = (size_t)(size); \ - WARN_ONCE(fortify_memcpy_chk(__fortify_size, p_size, q_size, \ - p_size_field, q_size_field, #op), \ + const size_t __fortify_size = (size_t)(size); \ + const size_t __p_size = (p_size); \ + const size_t __q_size = (q_size); \ + const size_t __p_size_field = (p_size_field); \ + const size_t __q_size_field = (q_size_field); \ + WARN_ONCE(fortify_memcpy_chk(__fortify_size, __p_size, \ + __q_size, __p_size_field, \ + __q_size_field, #op), \ #op ": detected field-spanning write (size %zu) of single %s (size %zu)\n", \ __fortify_size, \ "field \"" #p "\" at " __FILE__ ":" __stringify(__LINE__), \ - p_size_field); \ + __p_size_field); \ __underlying_##op(p, q, __fortify_size); \ }) diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index d62ef428e3aa..1668ac4d7adc 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -59,6 +59,7 @@ struct br_ip_list { #define BR_MRP_LOST_IN_CONT BIT(19) #define BR_TX_FWD_OFFLOAD BIT(20) #define BR_PORT_LOCKED BIT(21) +#define BR_PORT_MAB BIT(22) #define BR_DEFAULT_AGEING_TIME (300 * HZ) diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index e00c4ee81ff7..6864b89ef868 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -76,7 +76,7 @@ static inline bool is_vlan_dev(const struct net_device *dev) return dev->priv_flags & IFF_802_1Q_VLAN; } -#define skb_vlan_tag_present(__skb) ((__skb)->vlan_present) +#define skb_vlan_tag_present(__skb) (!!(__skb)->vlan_all) #define skb_vlan_tag_get(__skb) ((__skb)->vlan_tci) #define skb_vlan_tag_get_id(__skb) ((__skb)->vlan_tci & VLAN_VID_MASK) #define skb_vlan_tag_get_cfi(__skb) (!!((__skb)->vlan_tci & VLAN_CFI_MASK)) @@ -471,7 +471,7 @@ static inline struct sk_buff *vlan_insert_tag_set_proto(struct sk_buff *skb, */ static inline void __vlan_hwaccel_clear_tag(struct sk_buff *skb) { - skb->vlan_present = 0; + skb->vlan_all = 0; } /** @@ -483,9 +483,7 @@ static inline void __vlan_hwaccel_clear_tag(struct sk_buff *skb) */ static inline void __vlan_hwaccel_copy_tag(struct sk_buff *dst, const struct sk_buff *src) { - dst->vlan_present = src->vlan_present; - dst->vlan_proto = src->vlan_proto; - dst->vlan_tci = src->vlan_tci; + dst->vlan_all = src->vlan_all; } /* @@ -519,7 +517,6 @@ static inline void __vlan_hwaccel_put_tag(struct sk_buff *skb, { skb->vlan_proto = vlan_proto; skb->vlan_tci = vlan_tci; - skb->vlan_present = 1; } /** diff --git a/include/linux/mdio.h b/include/linux/mdio.h index 00177567cfef..f7fbbf3069e7 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -488,6 +488,19 @@ static inline int mdiobus_c45_write(struct mii_bus *bus, int prtad, int devad, return mdiobus_write(bus, prtad, mdiobus_c45_addr(devad, regnum), val); } +static inline int mdiodev_c45_read(struct mdio_device *mdiodev, int devad, + u16 regnum) +{ + return mdiobus_c45_read(mdiodev->bus, mdiodev->addr, devad, regnum); +} + +static inline int mdiodev_c45_write(struct mdio_device *mdiodev, u32 devad, + u16 regnum, u16 val) +{ + return mdiobus_c45_write(mdiodev->bus, mdiodev->addr, devad, regnum, + val); +} + int mdiobus_register_device(struct mdio_device *mdiodev); int mdiobus_unregister_device(struct mdio_device *mdiodev); bool mdiobus_is_registered_device(struct mii_bus *bus, int addr); diff --git a/include/linux/mv643xx_eth.h b/include/linux/mv643xx_eth.h index 3682ae75c7aa..145169be2ed8 100644 --- a/include/linux/mv643xx_eth.h +++ b/include/linux/mv643xx_eth.h @@ -8,6 +8,7 @@ #include <linux/mbus.h> #include <linux/if_ether.h> +#include <linux/phy.h> #define MV643XX_ETH_SHARED_NAME "mv643xx_eth" #define MV643XX_ETH_NAME "mv643xx_eth_port" @@ -59,6 +60,7 @@ struct mv643xx_eth_platform_data { */ int speed; int duplex; + phy_interface_t interface; /* * How many RX/TX queues to use. diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 4b5052db978f..02a2318da7c7 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1366,10 +1366,6 @@ struct netdev_net_notifier { * queue id bound to an AF_XDP socket. The flags field specifies if * only RX, only Tx, or both should be woken up using the flags * XDP_WAKEUP_RX and XDP_WAKEUP_TX. - * struct devlink_port *(*ndo_get_devlink_port)(struct net_device *dev); - * Get devlink port instance associated with a given netdev. - * Called with a reference on the netdevice and devlink locks only, - * rtnl_lock is not held. * int (*ndo_tunnel_ctl)(struct net_device *dev, struct ip_tunnel_parm *p, * int cmd); * Add, change, delete or get information on an IPv4 tunnel. @@ -1600,7 +1596,6 @@ struct net_device_ops { struct xdp_buff *xdp); int (*ndo_xsk_wakeup)(struct net_device *dev, u32 queue_id, u32 flags); - struct devlink_port * (*ndo_get_devlink_port)(struct net_device *dev); int (*ndo_tunnel_ctl)(struct net_device *dev, struct ip_tunnel_parm *p, int cmd); struct net_device * (*ndo_get_peer_dev)(struct net_device *dev); @@ -1655,7 +1650,6 @@ struct net_device_ops { * @IFF_FAILOVER: device is a failover master device * @IFF_FAILOVER_SLAVE: device is lower dev of a failover master device * @IFF_L3MDEV_RX_HANDLER: only invoke the rx handler of L3 master device - * @IFF_LIVE_RENAME_OK: rename is allowed while device is up and running * @IFF_TX_SKB_NO_LINEAR: device/driver is capable of xmitting frames with * skb_headlen(skb) == 0 (data starts from frag0) * @IFF_CHANGE_PROTO_DOWN: device supports setting carrier via IFLA_PROTO_DOWN @@ -1691,7 +1685,7 @@ enum netdev_priv_flags { IFF_FAILOVER = 1<<27, IFF_FAILOVER_SLAVE = 1<<28, IFF_L3MDEV_RX_HANDLER = 1<<29, - IFF_LIVE_RENAME_OK = 1<<30, + /* was IFF_LIVE_RENAME_OK */ IFF_TX_SKB_NO_LINEAR = BIT_ULL(31), IFF_CHANGE_PROTO_DOWN = BIT_ULL(32), }; @@ -1726,7 +1720,6 @@ enum netdev_priv_flags { #define IFF_FAILOVER IFF_FAILOVER #define IFF_FAILOVER_SLAVE IFF_FAILOVER_SLAVE #define IFF_L3MDEV_RX_HANDLER IFF_L3MDEV_RX_HANDLER -#define IFF_LIVE_RENAME_OK IFF_LIVE_RENAME_OK #define IFF_TX_SKB_NO_LINEAR IFF_TX_SKB_NO_LINEAR /* Specifies the type of the struct net_device::ml_priv pointer */ @@ -1999,6 +1992,11 @@ enum netdev_ml_priv_type { * registered * @offload_xstats_l3: L3 HW stats for this netdevice. * + * @devlink_port: Pointer to related devlink port structure. + * Assigned by a driver before netdev registration using + * SET_NETDEV_DEVLINK_PORT macro. This pointer is static + * during the time netdevice is registered. + * * FIXME: cleanup struct net_device such that network protocol info * moves out. */ @@ -2349,9 +2347,22 @@ struct net_device { netdevice_tracker watchdog_dev_tracker; netdevice_tracker dev_registered_tracker; struct rtnl_hw_stats64 *offload_xstats_l3; + + struct devlink_port *devlink_port; }; #define to_net_dev(d) container_of(d, struct net_device, dev) +/* + * Driver should use this to assign devlink port instance to a netdevice + * before it registers the netdevice. Therefore devlink_port is static + * during the netdev lifetime after it is registered. + */ +#define SET_NETDEV_DEVLINK_PORT(dev, port) \ +({ \ + WARN_ON((dev)->reg_state != NETREG_UNINITIALIZED); \ + ((dev)->devlink_port = (port)); \ +}) + static inline bool netif_elide_gro(const struct net_device *dev) { if (!(dev->features & NETIF_F_GRO) || dev->xdp_prog) @@ -2785,6 +2796,7 @@ enum netdev_cmd { NETDEV_PRE_TYPE_CHANGE, NETDEV_POST_TYPE_CHANGE, NETDEV_POST_INIT, + NETDEV_PRE_UNINIT, NETDEV_RELEASE, NETDEV_NOTIFY_PEERS, NETDEV_JOIN, @@ -2814,6 +2826,8 @@ int unregister_netdevice_notifier(struct notifier_block *nb); int register_netdevice_notifier_net(struct net *net, struct notifier_block *nb); int unregister_netdevice_notifier_net(struct net *net, struct notifier_block *nb); +void move_netdevice_notifier_net(struct net *src_net, struct net *dst_net, + struct notifier_block *nb); int register_netdevice_notifier_dev_net(struct net_device *dev, struct notifier_block *nb, struct netdev_net_notifier *nn); diff --git a/include/linux/phy.h b/include/linux/phy.h index ddf66198f751..9a3752c0c444 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -600,6 +600,7 @@ struct macsec_ops; * @psec: Pointer to Power Sourcing Equipment control struct * @lock: Mutex for serialization access to PHY * @state_queue: Work queue for state machine + * @link_down_events: Number of times link was lost * @shared: Pointer to private data shared by phys in one package * @priv: Pointer to driver private data * @@ -723,6 +724,8 @@ struct phy_device { int pma_extable; + unsigned int link_down_events; + void (*phy_link_change)(struct phy_device *phydev, bool up); void (*adjust_link)(struct net_device *dev); diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 1df3e5e316e8..c492c26202b5 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -207,6 +207,11 @@ struct phylink_mac_ops { * * If the @state->interface mode is not supported, then the @supported * mask must be cleared. + * + * This member is optional; if not set, the generic validator will be + * used making use of @config->mac_capabilities and + * @config->supported_interfaces to determine which link modes are + * supported. */ void validate(struct phylink_config *config, unsigned long *supported, struct phylink_link_state *state); diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 81d6e4ec2294..0260f5ea98fe 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -208,8 +208,10 @@ static inline void proc_remove(struct proc_dir_entry *de) {} static inline int remove_proc_subtree(const char *name, struct proc_dir_entry *parent) { return 0; } #define proc_create_net_data(name, mode, parent, ops, state_size, data) ({NULL;}) +#define proc_create_net_data_write(name, mode, parent, ops, write, state_size, data) ({NULL;}) #define proc_create_net(name, mode, parent, state_size, ops) ({NULL;}) #define proc_create_net_single(name, mode, parent, show, data) ({NULL;}) +#define proc_create_net_single_write(name, mode, parent, show, write, data) ({NULL;}) static inline struct pid *tgid_pidfd_to_pid(const struct file *file) { diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index f4781c5766d6..fdffa6a98d79 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -77,12 +77,6 @@ struct ptp_system_timestamp { * nominal frequency in parts per million, but with a * 16 bit binary fractional field. * - * @adjfreq: Adjusts the frequency of the hardware clock. - * This method is deprecated. New drivers should implement - * the @adjfine method instead. - * parameter delta: Desired frequency offset from nominal frequency - * in parts per billion - * * @adjphase: Adjusts the phase offset of the hardware clock. * parameter delta: Desired change in nanoseconds. * @@ -174,7 +168,6 @@ struct ptp_clock_info { int pps; struct ptp_pin_desc *pin_config; int (*adjfine)(struct ptp_clock_info *ptp, long scaled_ppm); - int (*adjfreq)(struct ptp_clock_info *ptp, s32 delta); int (*adjphase)(struct ptp_clock_info *ptp, s32 phase); int (*adjtime)(struct ptp_clock_info *ptp, s64 delta); int (*gettime64)(struct ptp_clock_info *ptp, struct timespec64 *ts); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 59c9fd55699d..4e464a27adaf 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -818,7 +818,7 @@ typedef unsigned char *sk_buff_data_t; * @mark: Generic packet mark * @reserved_tailroom: (aka @mark) number of bytes of free space available * at the tail of an sk_buff - * @vlan_present: VLAN tag is present + * @vlan_all: vlan fields (proto & tci) * @vlan_proto: vlan encapsulation protocol * @vlan_tci: vlan tag control information * @inner_protocol: Protocol (encapsulation) @@ -951,7 +951,7 @@ struct sk_buff { /* private: */ __u8 __pkt_vlan_present_offset[0]; /* public: */ - __u8 vlan_present:1; /* See PKT_VLAN_PRESENT_BIT */ + __u8 remcsum_offload:1; __u8 csum_complete_sw:1; __u8 csum_level:2; __u8 dst_pending_confirm:1; @@ -966,7 +966,6 @@ struct sk_buff { __u8 ipvs_property:1; __u8 inner_protocol_type:1; - __u8 remcsum_offload:1; #ifdef CONFIG_NET_SWITCHDEV __u8 offload_fwd_mark:1; __u8 offload_l3_fwd_mark:1; @@ -999,8 +998,13 @@ struct sk_buff { __u32 priority; int skb_iif; __u32 hash; - __be16 vlan_proto; - __u16 vlan_tci; + union { + u32 vlan_all; + struct { + __be16 vlan_proto; + __u16 vlan_tci; + }; + }; #if defined(CONFIG_NET_RX_BUSY_POLL) || defined(CONFIG_XPS) union { unsigned int napi_id; @@ -1059,15 +1063,13 @@ struct sk_buff { #endif #define PKT_TYPE_OFFSET offsetof(struct sk_buff, __pkt_type_offset) -/* if you move pkt_vlan_present, tc_at_ingress, or mono_delivery_time +/* if you move tc_at_ingress or mono_delivery_time * around, you also must adapt these constants. */ #ifdef __BIG_ENDIAN_BITFIELD -#define PKT_VLAN_PRESENT_BIT 7 #define TC_AT_INGRESS_MASK (1 << 0) #define SKB_MONO_DELIVERY_TIME_MASK (1 << 2) #else -#define PKT_VLAN_PRESENT_BIT 0 #define TC_AT_INGRESS_MASK (1 << 7) #define SKB_MONO_DELIVERY_TIME_MASK (1 << 5) #endif diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 48f4b645193b..70d6cb94e580 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -376,7 +376,7 @@ static inline void sk_psock_report_error(struct sk_psock *psock, int err) } struct sk_psock *sk_psock_init(struct sock *sk, int node); -void sk_psock_stop(struct sk_psock *psock, bool wait); +void sk_psock_stop(struct sk_psock *psock); #if IS_ENABLED(CONFIG_BPF_STREAM_PARSER) int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock); diff --git a/include/linux/slab.h b/include/linux/slab.h index 90877fcde70b..45efc6c553b8 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -470,35 +470,12 @@ void *__kmalloc_node(size_t size, gfp_t flags, int node) __assume_kmalloc_alignm void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t flags, int node) __assume_slab_alignment __malloc; -#ifdef CONFIG_TRACING void *kmalloc_trace(struct kmem_cache *s, gfp_t flags, size_t size) __assume_kmalloc_alignment __alloc_size(3); void *kmalloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, int node, size_t size) __assume_kmalloc_alignment __alloc_size(4); -#else /* CONFIG_TRACING */ -/* Save a function call when CONFIG_TRACING=n */ -static __always_inline __alloc_size(3) -void *kmalloc_trace(struct kmem_cache *s, gfp_t flags, size_t size) -{ - void *ret = kmem_cache_alloc(s, flags); - - ret = kasan_kmalloc(s, ret, size, flags); - return ret; -} - -static __always_inline __alloc_size(4) -void *kmalloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, - int node, size_t size) -{ - void *ret = kmem_cache_alloc_node(s, gfpflags, node); - - ret = kasan_kmalloc(s, ret, size, gfpflags); - return ret; -} -#endif /* CONFIG_TRACING */ - void *kmalloc_large(size_t size, gfp_t flags) __assume_page_alignment __alloc_size(1); diff --git a/include/linux/soc/mediatek/mtk_wed.h b/include/linux/soc/mediatek/mtk_wed.h index 4450c8b7a1cb..8294978f4bca 100644 --- a/include/linux/soc/mediatek/mtk_wed.h +++ b/include/linux/soc/mediatek/mtk_wed.h @@ -5,27 +5,76 @@ #include <linux/rcupdate.h> #include <linux/regmap.h> #include <linux/pci.h> +#include <linux/skbuff.h> #define MTK_WED_TX_QUEUES 2 +#define MTK_WED_RX_QUEUES 2 + +#define WED_WO_STA_REC 0x6 struct mtk_wed_hw; struct mtk_wdma_desc; +enum mtk_wed_wo_cmd { + MTK_WED_WO_CMD_WED_CFG, + MTK_WED_WO_CMD_WED_RX_STAT, + MTK_WED_WO_CMD_RRO_SER, + MTK_WED_WO_CMD_DBG_INFO, + MTK_WED_WO_CMD_DEV_INFO, + MTK_WED_WO_CMD_BSS_INFO, + MTK_WED_WO_CMD_STA_REC, + MTK_WED_WO_CMD_DEV_INFO_DUMP, + MTK_WED_WO_CMD_BSS_INFO_DUMP, + MTK_WED_WO_CMD_STA_REC_DUMP, + MTK_WED_WO_CMD_BA_INFO_DUMP, + MTK_WED_WO_CMD_FBCMD_Q_DUMP, + MTK_WED_WO_CMD_FW_LOG_CTRL, + MTK_WED_WO_CMD_LOG_FLUSH, + MTK_WED_WO_CMD_CHANGE_STATE, + MTK_WED_WO_CMD_CPU_STATS_ENABLE, + MTK_WED_WO_CMD_CPU_STATS_DUMP, + MTK_WED_WO_CMD_EXCEPTION_INIT, + MTK_WED_WO_CMD_PROF_CTRL, + MTK_WED_WO_CMD_STA_BA_DUMP, + MTK_WED_WO_CMD_BA_CTRL_DUMP, + MTK_WED_WO_CMD_RXCNT_CTRL, + MTK_WED_WO_CMD_RXCNT_INFO, + MTK_WED_WO_CMD_SET_CAP, + MTK_WED_WO_CMD_CCIF_RING_DUMP, + MTK_WED_WO_CMD_WED_END +}; + +struct mtk_rxbm_desc { + __le32 buf0; + __le32 token; +} __packed __aligned(4); + enum mtk_wed_bus_tye { MTK_WED_BUS_PCIE, MTK_WED_BUS_AXI, }; +#define MTK_WED_RING_CONFIGURED BIT(0) struct mtk_wed_ring { struct mtk_wdma_desc *desc; dma_addr_t desc_phys; u32 desc_size; int size; + u32 flags; u32 reg_base; void __iomem *wpdma; }; +struct mtk_wed_wo_rx_stats { + __le16 wlan_idx; + __le16 tid; + __le32 rx_pkt_cnt; + __le32 rx_byte_cnt; + __le32 rx_err_cnt; + __le32 rx_drop_cnt; +}; + struct mtk_wed_device { #ifdef CONFIG_NET_MEDIATEK_SOC_WED const struct mtk_wed_ops *ops; @@ -34,17 +83,33 @@ struct mtk_wed_device { bool init_done, running; int wdma_idx; int irq; + u8 version; struct mtk_wed_ring tx_ring[MTK_WED_TX_QUEUES]; + struct mtk_wed_ring rx_ring[MTK_WED_RX_QUEUES]; struct mtk_wed_ring txfree_ring; struct mtk_wed_ring tx_wdma[MTK_WED_TX_QUEUES]; + struct mtk_wed_ring rx_wdma[MTK_WED_RX_QUEUES]; struct { int size; void **pages; struct mtk_wdma_desc *desc; dma_addr_t desc_phys; - } buf_ring; + } tx_buf_ring; + + struct { + int size; + struct page_frag_cache rx_page; + struct mtk_rxbm_desc *desc; + dma_addr_t desc_phys; + } rx_buf_ring; + + struct { + struct mtk_wed_ring ring; + dma_addr_t miod_phys; + dma_addr_t fdbk_phys; + } rro; /* filled by driver: */ struct { @@ -53,22 +118,36 @@ struct mtk_wed_device { struct pci_dev *pci_dev; }; enum mtk_wed_bus_tye bus_type; + void __iomem *base; + u32 phy_base; u32 wpdma_phys; u32 wpdma_int; u32 wpdma_mask; u32 wpdma_tx; u32 wpdma_txfree; + u32 wpdma_rx_glo; + u32 wpdma_rx; + + bool wcid_512; u16 token_start; unsigned int nbuf; + unsigned int rx_nbuf; + unsigned int rx_npkt; + unsigned int rx_size; u8 tx_tbit[MTK_WED_TX_QUEUES]; + u8 rx_tbit[MTK_WED_RX_QUEUES]; u8 txfree_tbit; u32 (*init_buf)(void *ptr, dma_addr_t phys, int token_id); int (*offload_enable)(struct mtk_wed_device *wed); void (*offload_disable)(struct mtk_wed_device *wed); + u32 (*init_rx_buf)(struct mtk_wed_device *wed, int size); + void (*release_rx_buf)(struct mtk_wed_device *wed); + void (*update_wo_rx_stats)(struct mtk_wed_device *wed, + struct mtk_wed_wo_rx_stats *stats); } wlan; #endif }; @@ -77,9 +156,15 @@ struct mtk_wed_ops { int (*attach)(struct mtk_wed_device *dev); int (*tx_ring_setup)(struct mtk_wed_device *dev, int ring, void __iomem *regs); + int (*rx_ring_setup)(struct mtk_wed_device *dev, int ring, + void __iomem *regs); int (*txfree_ring_setup)(struct mtk_wed_device *dev, void __iomem *regs); + int (*msg_update)(struct mtk_wed_device *dev, int cmd_id, + void *data, int len); void (*detach)(struct mtk_wed_device *dev); + void (*ppe_check)(struct mtk_wed_device *dev, struct sk_buff *skb, + u32 reason, u32 hash); void (*stop)(struct mtk_wed_device *dev); void (*start)(struct mtk_wed_device *dev, u32 irq_mask); @@ -114,6 +199,16 @@ mtk_wed_device_attach(struct mtk_wed_device *dev) return ret; } +static inline bool +mtk_wed_get_rx_capa(struct mtk_wed_device *dev) +{ +#ifdef CONFIG_NET_MEDIATEK_SOC_WED + return dev->version != 1; +#else + return false; +#endif +} + #ifdef CONFIG_NET_MEDIATEK_SOC_WED #define mtk_wed_device_active(_dev) !!(_dev)->ops #define mtk_wed_device_detach(_dev) (_dev)->ops->detach(_dev) @@ -130,6 +225,12 @@ mtk_wed_device_attach(struct mtk_wed_device *dev) (_dev)->ops->irq_get(_dev, _mask) #define mtk_wed_device_irq_set_mask(_dev, _mask) \ (_dev)->ops->irq_set_mask(_dev, _mask) +#define mtk_wed_device_rx_ring_setup(_dev, _ring, _regs) \ + (_dev)->ops->rx_ring_setup(_dev, _ring, _regs) +#define mtk_wed_device_ppe_check(_dev, _skb, _reason, _hash) \ + (_dev)->ops->ppe_check(_dev, _skb, _reason, _hash) +#define mtk_wed_device_update_msg(_dev, _id, _msg, _len) \ + (_dev)->ops->msg_update(_dev, _id, _msg, _len) #else static inline bool mtk_wed_device_active(struct mtk_wed_device *dev) { @@ -143,6 +244,9 @@ static inline bool mtk_wed_device_active(struct mtk_wed_device *dev) #define mtk_wed_device_reg_write(_dev, _reg, _val) do {} while (0) #define mtk_wed_device_irq_get(_dev, _mask) 0 #define mtk_wed_device_irq_set_mask(_dev, _mask) do {} while (0) +#define mtk_wed_device_rx_ring_setup(_dev, _ring, _regs) -ENODEV +#define mtk_wed_device_ppe_check(_dev, _skb, _reason, _hash) do {} while (0) +#define mtk_wed_device_update_msg(_dev, _id, _msg, _len) -ENODEV #endif #endif diff --git a/include/linux/udp.h b/include/linux/udp.h index 5cdba00a904a..dea57aa37df6 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -70,7 +70,8 @@ struct udp_sock { * For encapsulation sockets. */ int (*encap_rcv)(struct sock *sk, struct sk_buff *skb); - void (*encap_err_rcv)(struct sock *sk, struct sk_buff *skb, unsigned int udp_offset); + void (*encap_err_rcv)(struct sock *sk, struct sk_buff *skb, int err, + __be16 port, u32 info, u8 *payload); int (*encap_err_lookup)(struct sock *sk, struct sk_buff *skb); void (*encap_destroy)(struct sock *sk); diff --git a/include/net/devlink.h b/include/net/devlink.h index ba6b8b094943..611a23a3deb2 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -121,12 +121,21 @@ struct devlink_port { struct list_head region_list; struct devlink *devlink; unsigned int index; - spinlock_t type_lock; /* Protects type and type_dev - * pointer consistency. + spinlock_t type_lock; /* Protects type and type_eth/ib + * structures consistency. */ enum devlink_port_type type; enum devlink_port_type desired_type; - void *type_dev; + union { + struct { + struct net_device *netdev; + int ifindex; + char ifname[IFNAMSIZ]; + } type_eth; + struct { + struct ib_device *ibdev; + } type_ib; + }; struct devlink_port_attrs attrs; u8 attrs_set:1, switch_port:1, @@ -885,6 +894,8 @@ enum devlink_trap_generic_id { DEVLINK_TRAP_GENERIC_ID_ESP_PARSING, DEVLINK_TRAP_GENERIC_ID_BLACKHOLE_NEXTHOP, DEVLINK_TRAP_GENERIC_ID_DMAC_FILTER, + DEVLINK_TRAP_GENERIC_ID_EAPOL, + DEVLINK_TRAP_GENERIC_ID_LOCKED_PORT, /* Add new generic trap IDs above */ __DEVLINK_TRAP_GENERIC_ID_MAX, @@ -921,6 +932,7 @@ enum devlink_trap_group_generic_id { DEVLINK_TRAP_GROUP_GENERIC_ID_ACL_SAMPLE, DEVLINK_TRAP_GROUP_GENERIC_ID_ACL_TRAP, DEVLINK_TRAP_GROUP_GENERIC_ID_PARSER_ERROR_DROPS, + DEVLINK_TRAP_GROUP_GENERIC_ID_EAPOL, /* Add new generic trap group IDs above */ __DEVLINK_TRAP_GROUP_GENERIC_ID_MAX, @@ -1112,6 +1124,10 @@ enum devlink_trap_group_generic_id { "blackhole_nexthop" #define DEVLINK_TRAP_GENERIC_NAME_DMAC_FILTER \ "dmac_filter" +#define DEVLINK_TRAP_GENERIC_NAME_EAPOL \ + "eapol" +#define DEVLINK_TRAP_GENERIC_NAME_LOCKED_PORT \ + "locked_port" #define DEVLINK_TRAP_GROUP_GENERIC_NAME_L2_DROPS \ "l2_drops" @@ -1165,6 +1181,8 @@ enum devlink_trap_group_generic_id { "acl_trap" #define DEVLINK_TRAP_GROUP_GENERIC_NAME_PARSER_ERROR_DROPS \ "parser_error_drops" +#define DEVLINK_TRAP_GROUP_GENERIC_NAME_EAPOL \ + "eapol" #define DEVLINK_TRAP_GENERIC(_type, _init_action, _id, _group_id, \ _metadata_cap) \ @@ -1575,8 +1593,7 @@ int devlink_port_register(struct devlink *devlink, unsigned int port_index); void devl_port_unregister(struct devlink_port *devlink_port); void devlink_port_unregister(struct devlink_port *devlink_port); -void devlink_port_type_eth_set(struct devlink_port *devlink_port, - struct net_device *netdev); +void devlink_port_type_eth_set(struct devlink_port *devlink_port); void devlink_port_type_ib_set(struct devlink_port *devlink_port, struct ib_device *ibdev); void devlink_port_type_clear(struct devlink_port *devlink_port); @@ -1865,6 +1882,9 @@ int devlink_compat_phys_port_name_get(struct net_device *dev, int devlink_compat_switch_id_get(struct net_device *dev, struct netdev_phys_item_id *ppid); +int devlink_nl_port_handle_fill(struct sk_buff *msg, struct devlink_port *devlink_port); +size_t devlink_nl_port_handle_size(struct devlink_port *devlink_port); + #else static inline struct devlink *devlink_try_get(struct devlink *devlink) @@ -1901,6 +1921,17 @@ devlink_compat_switch_id_get(struct net_device *dev, return -EOPNOTSUPP; } +static inline int +devlink_nl_port_handle_fill(struct sk_buff *msg, struct devlink_port *devlink_port) +{ + return 0; +} + +static inline size_t devlink_nl_port_handle_size(struct devlink_port *devlink_port) +{ + return 0; +} + #endif #endif /* _NET_DEVLINK_H_ */ diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 9f97f73615b6..d21210709f84 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -18,12 +18,11 @@ struct genl_multicast_group { u8 flags; }; -struct genl_ops; +struct genl_split_ops; struct genl_info; /** * struct genl_family - generic netlink family - * @id: protocol family identifier (private) * @hdrsize: length of user specific header in bytes * @name: name of family * @version: protocol version @@ -43,12 +42,13 @@ struct genl_info; * @resv_start_op: first operation for which reserved fields of the header * can be validated and policies are required (see below); * new families should leave this field at zero - * @mcgrp_offset: starting number of multicast group IDs in this family - * (private) * @ops: the operations supported by this family * @n_ops: number of operations supported by this family * @small_ops: the small-struct operations supported by this family * @n_small_ops: number of small-struct operations supported by this family + * @split_ops: the split do/dump form of operation definition + * @n_split_ops: number of entries in @split_ops, not that with split do/dump + * ops the number of entries is not the same as number of commands * * Attribute policies (the combination of @policy and @maxattr fields) * can be attached at the family level or at the operation level. @@ -58,29 +58,35 @@ struct genl_info; * if policy is not provided core will reject all TLV attributes. */ struct genl_family { - int id; /* private */ unsigned int hdrsize; char name[GENL_NAMSIZ]; unsigned int version; unsigned int maxattr; - unsigned int mcgrp_offset; /* private */ u8 netnsok:1; u8 parallel_ops:1; u8 n_ops; u8 n_small_ops; + u8 n_split_ops; u8 n_mcgrps; u8 resv_start_op; const struct nla_policy *policy; - int (*pre_doit)(const struct genl_ops *ops, + int (*pre_doit)(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info); - void (*post_doit)(const struct genl_ops *ops, + void (*post_doit)(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info); const struct genl_ops * ops; const struct genl_small_ops *small_ops; + const struct genl_split_ops *split_ops; const struct genl_multicast_group *mcgrps; struct module *module; + +/* private: internal use only */ + /* protocol family identifier */ + int id; + /* starting number of multicast group IDs in this family */ + unsigned int mcgrp_offset; }; /** @@ -182,6 +188,58 @@ struct genl_ops { }; /** + * struct genl_split_ops - generic netlink operations (do/dump split version) + * @cmd: command identifier + * @internal_flags: flags used by the family + * @flags: GENL_* flags (%GENL_ADMIN_PERM or %GENL_UNS_ADMIN_PERM) + * @validate: validation flags from enum genl_validate_flags + * @policy: netlink policy (takes precedence over family policy) + * @maxattr: maximum number of attributes supported + * + * Do callbacks: + * @pre_doit: called before an operation's @doit callback, it may + * do additional, common, filtering and return an error + * @doit: standard command callback + * @post_doit: called after an operation's @doit callback, it may + * undo operations done by pre_doit, for example release locks + * + * Dump callbacks: + * @start: start callback for dumps + * @dumpit: callback for dumpers + * @done: completion callback for dumps + * + * Do callbacks can be used if %GENL_CMD_CAP_DO is set in @flags. + * Dump callbacks can be used if %GENL_CMD_CAP_DUMP is set in @flags. + * Exactly one of those flags must be set. + */ +struct genl_split_ops { + union { + struct { + int (*pre_doit)(const struct genl_split_ops *ops, + struct sk_buff *skb, + struct genl_info *info); + int (*doit)(struct sk_buff *skb, + struct genl_info *info); + void (*post_doit)(const struct genl_split_ops *ops, + struct sk_buff *skb, + struct genl_info *info); + }; + struct { + int (*start)(struct netlink_callback *cb); + int (*dumpit)(struct sk_buff *skb, + struct netlink_callback *cb); + int (*done)(struct netlink_callback *cb); + }; + }; + const struct nla_policy *policy; + unsigned int maxattr; + u8 cmd; + u8 internal_flags; + u8 flags; + u8 validate; +}; + +/** * struct genl_dumpit_info - info that is available during dumpit op call * @family: generic netlink family - for internal genl code usage * @op: generic netlink ops - for internal genl code usage @@ -189,7 +247,7 @@ struct genl_ops { */ struct genl_dumpit_info { const struct genl_family *family; - struct genl_ops op; + struct genl_split_ops op; struct nlattr **attrs; }; diff --git a/drivers/net/ethernet/microsoft/mana/gdma.h b/include/net/mana/gdma.h index db340f36ef29..28d0687bf7da 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma.h +++ b/include/net/mana/gdma.h @@ -9,6 +9,8 @@ #include "shm_channel.h" +#define GDMA_STATUS_MORE_ENTRIES 0x00000105 + /* Structures labeled with "HW DATA" are exchanged with the hardware. All of * them are naturally aligned and hence don't need __packed. */ @@ -22,11 +24,19 @@ enum gdma_request_type { GDMA_GENERATE_TEST_EQE = 10, GDMA_CREATE_QUEUE = 12, GDMA_DISABLE_QUEUE = 13, + GDMA_ALLOCATE_RESOURCE_RANGE = 22, + GDMA_DESTROY_RESOURCE_RANGE = 24, GDMA_CREATE_DMA_REGION = 25, GDMA_DMA_REGION_ADD_PAGES = 26, GDMA_DESTROY_DMA_REGION = 27, + GDMA_CREATE_PD = 29, + GDMA_DESTROY_PD = 30, + GDMA_CREATE_MR = 31, + GDMA_DESTROY_MR = 32, }; +#define GDMA_RESOURCE_DOORBELL_PAGE 27 + enum gdma_queue_type { GDMA_INVALID_QUEUE, GDMA_SQ, @@ -55,6 +65,8 @@ enum { GDMA_DEVICE_MANA = 2, }; +typedef u64 gdma_obj_handle_t; + struct gdma_resource { /* Protect the bitmap */ spinlock_t lock; @@ -188,7 +200,7 @@ struct gdma_mem_info { u64 length; /* Allocated by the PF driver */ - u64 gdma_region; + gdma_obj_handle_t dma_region_handle; }; #define REGISTER_ATB_MST_MKEY_LOWER_SIZE 8 @@ -204,6 +216,8 @@ struct gdma_dev { /* GDMA driver specific pointer */ void *driver_data; + + struct auxiliary_device *adev; }; #define MINIMUM_SUPPORTED_PAGE_SIZE PAGE_SIZE @@ -349,9 +363,11 @@ struct gdma_context { u32 test_event_eq_id; bool is_pf; + phys_addr_t bar0_pa; void __iomem *bar0_va; void __iomem *shm_base; void __iomem *db_page_base; + phys_addr_t phys_db_page_base; u32 db_page_size; int numa_node; @@ -424,6 +440,13 @@ struct gdma_wqe { #define MAX_TX_WQE_SIZE 512 #define MAX_RX_WQE_SIZE 256 +#define MAX_TX_WQE_SGL_ENTRIES ((GDMA_MAX_SQE_SIZE - \ + sizeof(struct gdma_sge) - INLINE_OOB_SMALL_SIZE) / \ + sizeof(struct gdma_sge)) + +#define MAX_RX_WQE_SGL_ENTRIES ((GDMA_MAX_RQE_SIZE - \ + sizeof(struct gdma_sge)) / sizeof(struct gdma_sge)) + struct gdma_cqe { u32 cqe_data[GDMA_COMP_DATA_SIZE / 4]; @@ -575,6 +598,26 @@ struct gdma_register_device_resp { u32 db_id; }; /* HW DATA */ +struct gdma_allocate_resource_range_req { + struct gdma_req_hdr hdr; + u32 resource_type; + u32 num_resources; + u32 alignment; + u32 allocated_resources; +}; + +struct gdma_allocate_resource_range_resp { + struct gdma_resp_hdr hdr; + u32 allocated_resources; +}; + +struct gdma_destroy_resource_range_req { + struct gdma_req_hdr hdr; + u32 resource_type; + u32 num_resources; + u32 allocated_resources; +}; + /* GDMA_CREATE_QUEUE */ struct gdma_create_queue_req { struct gdma_req_hdr hdr; @@ -582,7 +625,7 @@ struct gdma_create_queue_req { u32 reserved1; u32 pdid; u32 doolbell_id; - u64 gdma_region; + gdma_obj_handle_t gdma_region; u32 reserved2; u32 queue_size; u32 log2_throttle_limit; @@ -609,6 +652,28 @@ struct gdma_disable_queue_req { u32 alloc_res_id_on_creation; }; /* HW DATA */ +enum atb_page_size { + ATB_PAGE_SIZE_4K, + ATB_PAGE_SIZE_8K, + ATB_PAGE_SIZE_16K, + ATB_PAGE_SIZE_32K, + ATB_PAGE_SIZE_64K, + ATB_PAGE_SIZE_128K, + ATB_PAGE_SIZE_256K, + ATB_PAGE_SIZE_512K, + ATB_PAGE_SIZE_1M, + ATB_PAGE_SIZE_2M, + ATB_PAGE_SIZE_MAX, +}; + +enum gdma_mr_access_flags { + GDMA_ACCESS_FLAG_LOCAL_READ = BIT_ULL(0), + GDMA_ACCESS_FLAG_LOCAL_WRITE = BIT_ULL(1), + GDMA_ACCESS_FLAG_REMOTE_READ = BIT_ULL(2), + GDMA_ACCESS_FLAG_REMOTE_WRITE = BIT_ULL(3), + GDMA_ACCESS_FLAG_REMOTE_ATOMIC = BIT_ULL(4), +}; + /* GDMA_CREATE_DMA_REGION */ struct gdma_create_dma_region_req { struct gdma_req_hdr hdr; @@ -635,14 +700,14 @@ struct gdma_create_dma_region_req { struct gdma_create_dma_region_resp { struct gdma_resp_hdr hdr; - u64 gdma_region; + gdma_obj_handle_t dma_region_handle; }; /* HW DATA */ /* GDMA_DMA_REGION_ADD_PAGES */ struct gdma_dma_region_add_pages_req { struct gdma_req_hdr hdr; - u64 gdma_region; + gdma_obj_handle_t dma_region_handle; u32 page_addr_list_len; u32 reserved3; @@ -654,9 +719,88 @@ struct gdma_dma_region_add_pages_req { struct gdma_destroy_dma_region_req { struct gdma_req_hdr hdr; - u64 gdma_region; + gdma_obj_handle_t dma_region_handle; }; /* HW DATA */ +enum gdma_pd_flags { + GDMA_PD_FLAG_INVALID = 0, +}; + +struct gdma_create_pd_req { + struct gdma_req_hdr hdr; + enum gdma_pd_flags flags; + u32 reserved; +};/* HW DATA */ + +struct gdma_create_pd_resp { + struct gdma_resp_hdr hdr; + gdma_obj_handle_t pd_handle; + u32 pd_id; + u32 reserved; +};/* HW DATA */ + +struct gdma_destroy_pd_req { + struct gdma_req_hdr hdr; + gdma_obj_handle_t pd_handle; +};/* HW DATA */ + +struct gdma_destory_pd_resp { + struct gdma_resp_hdr hdr; +};/* HW DATA */ + +enum gdma_mr_type { + /* Guest Virtual Address - MRs of this type allow access + * to memory mapped by PTEs associated with this MR using a virtual + * address that is set up in the MST + */ + GDMA_MR_TYPE_GVA = 2, +}; + +struct gdma_create_mr_params { + gdma_obj_handle_t pd_handle; + enum gdma_mr_type mr_type; + union { + struct { + gdma_obj_handle_t dma_region_handle; + u64 virtual_address; + enum gdma_mr_access_flags access_flags; + } gva; + }; +}; + +struct gdma_create_mr_request { + struct gdma_req_hdr hdr; + gdma_obj_handle_t pd_handle; + enum gdma_mr_type mr_type; + u32 reserved_1; + + union { + struct { + gdma_obj_handle_t dma_region_handle; + u64 virtual_address; + enum gdma_mr_access_flags access_flags; + } gva; + + }; + u32 reserved_2; +};/* HW DATA */ + +struct gdma_create_mr_response { + struct gdma_resp_hdr hdr; + gdma_obj_handle_t mr_handle; + u32 lkey; + u32 rkey; +};/* HW DATA */ + +struct gdma_destroy_mr_request { + struct gdma_req_hdr hdr; + gdma_obj_handle_t mr_handle; +};/* HW DATA */ + +struct gdma_destroy_mr_response { + struct gdma_resp_hdr hdr; +};/* HW DATA */ + int mana_gd_verify_vf_version(struct pci_dev *pdev); int mana_gd_register_device(struct gdma_dev *gd); @@ -683,4 +827,8 @@ void mana_gd_free_memory(struct gdma_mem_info *gmi); int mana_gd_send_request(struct gdma_context *gc, u32 req_len, const void *req, u32 resp_len, void *resp); + +int mana_gd_destroy_dma_region(struct gdma_context *gc, + gdma_obj_handle_t dma_region_handle); + #endif /* _GDMA_H */ diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.h b/include/net/mana/hw_channel.h index 6a757a6e2732..6a757a6e2732 100644 --- a/drivers/net/ethernet/microsoft/mana/hw_channel.h +++ b/include/net/mana/hw_channel.h diff --git a/drivers/net/ethernet/microsoft/mana/mana.h b/include/net/mana/mana.h index d58be64374c8..575ea36ce606 100644 --- a/drivers/net/ethernet/microsoft/mana/mana.h +++ b/include/net/mana/mana.h @@ -265,8 +265,6 @@ struct mana_cq { int budget; }; -#define GDMA_MAX_RQE_SGES 15 - struct mana_recv_buf_oob { /* A valid GDMA work request representing the data buffer. */ struct gdma_wqe_request wqe_req; @@ -276,7 +274,7 @@ struct mana_recv_buf_oob { /* SGL of the buffer going to be sent has part of the work request. */ u32 num_sge; - struct gdma_sge sgl[GDMA_MAX_RQE_SGES]; + struct gdma_sge sgl[MAX_RX_WQE_SGL_ENTRIES]; /* Required to store the result of mana_gd_post_work_request. * gdma_posted_wqe_info.wqe_size_in_bu is required for progressing the @@ -380,6 +378,10 @@ struct mana_port_context { mana_handle_t port_handle; mana_handle_t pf_filter_handle; + /* Mutex for sharing access to vport_use_count */ + struct mutex vport_mutex; + int vport_use_count; + u16 port_idx; bool port_is_up; @@ -388,7 +390,7 @@ struct mana_port_context { struct mana_ethtool_stats eth_stats; }; -int mana_start_xmit(struct sk_buff *skb, struct net_device *ndev); +netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev); int mana_config_rss(struct mana_port_context *ac, enum TRI_STATE rx, bool update_hash, bool update_tab); @@ -631,4 +633,16 @@ struct mana_tx_package { struct gdma_posted_wqe_info wqe_info; }; +int mana_create_wq_obj(struct mana_port_context *apc, + mana_handle_t vport, + u32 wq_type, struct mana_obj_spec *wq_spec, + struct mana_obj_spec *cq_spec, + mana_handle_t *wq_obj); + +void mana_destroy_wq_obj(struct mana_port_context *apc, u32 wq_type, + mana_handle_t wq_obj); + +int mana_cfg_vport(struct mana_port_context *apc, u32 protection_dom_id, + u32 doorbell_pg_id); +void mana_uncfg_vport(struct mana_port_context *apc); #endif /* _MANA_H */ diff --git a/include/net/mana/mana_auxiliary.h b/include/net/mana/mana_auxiliary.h new file mode 100644 index 000000000000..373d59756846 --- /dev/null +++ b/include/net/mana/mana_auxiliary.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (c) 2022, Microsoft Corporation. */ + +#include "mana.h" +#include <linux/auxiliary_bus.h> + +struct mana_adev { + struct auxiliary_device adev; + struct gdma_dev *mdev; +}; diff --git a/drivers/net/ethernet/microsoft/mana/shm_channel.h b/include/net/mana/shm_channel.h index 5199b41497ff..5199b41497ff 100644 --- a/drivers/net/ethernet/microsoft/mana/shm_channel.h +++ b/include/net/mana/shm_channel.h diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h index 9939c366f720..f30b1694b690 100644 --- a/include/net/netfilter/nf_conntrack_helper.h +++ b/include/net/netfilter/nf_conntrack_helper.h @@ -115,6 +115,11 @@ struct nf_conn_help *nf_ct_helper_ext_add(struct nf_conn *ct, gfp_t gfp); int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl, gfp_t flags); +int nf_ct_helper(struct sk_buff *skb, struct nf_conn *ct, + enum ip_conntrack_info ctinfo, u16 proto); +int nf_ct_add_helper(struct nf_conn *ct, const char *name, u8 family, + u8 proto, bool nat, struct nf_conntrack_helper **hp); + void nf_ct_helper_destroy(struct nf_conn *ct); static inline struct nf_conn_help *nfct_help(const struct nf_conn *ct) diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 7dcdc97c0bc3..ca0312b78294 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -248,6 +248,7 @@ struct switchdev_notifier_fdb_info { u16 vid; u8 added_by_user:1, is_local:1, + locked:1, offloaded:1; }; diff --git a/include/net/tc_act/tc_ct.h b/include/net/tc_act/tc_ct.h index 8250d6f0a462..b24ea2d9400b 100644 --- a/include/net/tc_act/tc_ct.h +++ b/include/net/tc_act/tc_ct.h @@ -10,6 +10,7 @@ #include <net/netfilter/nf_conntrack_labels.h> struct tcf_ct_params { + struct nf_conntrack_helper *helper; struct nf_conn *tmpl; u16 zone; diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index 72394f441dad..0ca9b7a11baf 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -68,8 +68,8 @@ typedef int (*udp_tunnel_encap_rcv_t)(struct sock *sk, struct sk_buff *skb); typedef int (*udp_tunnel_encap_err_lookup_t)(struct sock *sk, struct sk_buff *skb); typedef void (*udp_tunnel_encap_err_rcv_t)(struct sock *sk, - struct sk_buff *skb, - unsigned int udp_offset); + struct sk_buff *skb, int err, + __be16 port, u32 info, u8 *payload); typedef void (*udp_tunnel_encap_destroy_t)(struct sock *sk); typedef struct sk_buff *(*udp_tunnel_gro_receive_t)(struct sock *sk, struct list_head *head, diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index d20bf4aa0204..b9886d1df825 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -17,7 +17,9 @@ * Declare tracing information enums and their string mappings for display. */ #define rxrpc_skb_traces \ + EM(rxrpc_skb_ack, "ACK") \ EM(rxrpc_skb_cleaned, "CLN") \ + EM(rxrpc_skb_cloned_jumbo, "CLJ") \ EM(rxrpc_skb_freed, "FRE") \ EM(rxrpc_skb_got, "GOT") \ EM(rxrpc_skb_lost, "*L*") \ @@ -34,7 +36,8 @@ EM(rxrpc_local_new, "NEW") \ EM(rxrpc_local_processing, "PRO") \ EM(rxrpc_local_put, "PUT") \ - E_(rxrpc_local_queued, "QUE") + EM(rxrpc_local_queued, "QUE") \ + E_(rxrpc_local_tx_ack, "TAK") #define rxrpc_peer_traces \ EM(rxrpc_peer_got, "GOT") \ @@ -73,6 +76,7 @@ EM(rxrpc_call_got, "GOT") \ EM(rxrpc_call_got_kernel, "Gke") \ EM(rxrpc_call_got_timer, "GTM") \ + EM(rxrpc_call_got_tx, "Gtx") \ EM(rxrpc_call_got_userid, "Gus") \ EM(rxrpc_call_new_client, "NWc") \ EM(rxrpc_call_new_service, "NWs") \ @@ -81,20 +85,22 @@ EM(rxrpc_call_put_noqueue, "PnQ") \ EM(rxrpc_call_put_notimer, "PnT") \ EM(rxrpc_call_put_timer, "PTM") \ + EM(rxrpc_call_put_tx, "Ptx") \ EM(rxrpc_call_put_userid, "Pus") \ EM(rxrpc_call_queued, "QUE") \ EM(rxrpc_call_queued_ref, "QUR") \ EM(rxrpc_call_release, "RLS") \ E_(rxrpc_call_seen, "SEE") -#define rxrpc_transmit_traces \ - EM(rxrpc_transmit_await_reply, "AWR") \ - EM(rxrpc_transmit_end, "END") \ - EM(rxrpc_transmit_queue, "QUE") \ - EM(rxrpc_transmit_queue_last, "QLS") \ - EM(rxrpc_transmit_rotate, "ROT") \ - EM(rxrpc_transmit_rotate_last, "RLS") \ - E_(rxrpc_transmit_wait, "WAI") +#define rxrpc_txqueue_traces \ + EM(rxrpc_txqueue_await_reply, "AWR") \ + EM(rxrpc_txqueue_dequeue, "DEQ") \ + EM(rxrpc_txqueue_end, "END") \ + EM(rxrpc_txqueue_queue, "QUE") \ + EM(rxrpc_txqueue_queue_last, "QLS") \ + EM(rxrpc_txqueue_rotate, "ROT") \ + EM(rxrpc_txqueue_rotate_last, "RLS") \ + E_(rxrpc_txqueue_wait, "WAI") #define rxrpc_receive_traces \ EM(rxrpc_receive_end, "END") \ @@ -102,7 +108,12 @@ EM(rxrpc_receive_incoming, "INC") \ EM(rxrpc_receive_queue, "QUE") \ EM(rxrpc_receive_queue_last, "QLS") \ - E_(rxrpc_receive_rotate, "ROT") + EM(rxrpc_receive_queue_oos, "QUO") \ + EM(rxrpc_receive_queue_oos_last, "QOL") \ + EM(rxrpc_receive_oos, "OOS") \ + EM(rxrpc_receive_oos_last, "OSL") \ + EM(rxrpc_receive_rotate, "ROT") \ + E_(rxrpc_receive_rotate_last, "RLS") #define rxrpc_recvmsg_traces \ EM(rxrpc_recvmsg_cont, "CONT") \ @@ -133,7 +144,6 @@ #define rxrpc_timer_traces \ EM(rxrpc_timer_begin, "Begin ") \ - EM(rxrpc_timer_expired, "*EXPR*") \ EM(rxrpc_timer_exp_ack, "ExpAck") \ EM(rxrpc_timer_exp_hard, "ExpHrd") \ EM(rxrpc_timer_exp_idle, "ExpIdl") \ @@ -158,6 +168,7 @@ #define rxrpc_propose_ack_traces \ EM(rxrpc_propose_ack_client_tx_end, "ClTxEnd") \ EM(rxrpc_propose_ack_input_data, "DataIn ") \ + EM(rxrpc_propose_ack_input_data_hole, "DataInH") \ EM(rxrpc_propose_ack_ping_for_check_life, "ChkLife") \ EM(rxrpc_propose_ack_ping_for_keepalive, "KeepAlv") \ EM(rxrpc_propose_ack_ping_for_lost_ack, "LostAck") \ @@ -170,11 +181,6 @@ EM(rxrpc_propose_ack_rotate_rx, "RxAck ") \ E_(rxrpc_propose_ack_terminal_ack, "ClTerm ") -#define rxrpc_propose_ack_outcomes \ - EM(rxrpc_propose_ack_subsume, " Subsume") \ - EM(rxrpc_propose_ack_update, " Update") \ - E_(rxrpc_propose_ack_use, " New") - #define rxrpc_congest_modes \ EM(RXRPC_CALL_CONGEST_AVOIDANCE, "CongAvoid") \ EM(RXRPC_CALL_FAST_RETRANSMIT, "FastReTx ") \ @@ -187,6 +193,7 @@ EM(rxrpc_cong_new_low_nack, " NewLowN") \ EM(rxrpc_cong_no_change, " -") \ EM(rxrpc_cong_progress, " Progres") \ + EM(rxrpc_cong_idle_reset, " IdleRes") \ EM(rxrpc_cong_retransmit_again, " ReTxAgn") \ EM(rxrpc_cong_rtt_window_end, " RttWinE") \ E_(rxrpc_cong_saw_nack, " SawNack") @@ -242,6 +249,33 @@ EM(rxrpc_tx_point_version_keepalive, "VerKeepalive") \ E_(rxrpc_tx_point_version_reply, "VerReply") +#define rxrpc_req_ack_traces \ + EM(rxrpc_reqack_ack_lost, "ACK-LOST ") \ + EM(rxrpc_reqack_already_on, "ALREADY-ON") \ + EM(rxrpc_reqack_more_rtt, "MORE-RTT ") \ + EM(rxrpc_reqack_no_srv_last, "NO-SRVLAST") \ + EM(rxrpc_reqack_old_rtt, "OLD-RTT ") \ + EM(rxrpc_reqack_retrans, "RETRANS ") \ + EM(rxrpc_reqack_slow_start, "SLOW-START") \ + E_(rxrpc_reqack_small_txwin, "SMALL-TXWN") +/* ---- Must update size of stat_why_req_ack[] if more are added! */ + +#define rxrpc_txbuf_traces \ + EM(rxrpc_txbuf_alloc_ack, "ALLOC ACK ") \ + EM(rxrpc_txbuf_alloc_data, "ALLOC DATA ") \ + EM(rxrpc_txbuf_free, "FREE ") \ + EM(rxrpc_txbuf_get_buffer, "GET BUFFER ") \ + EM(rxrpc_txbuf_get_trans, "GET TRANS ") \ + EM(rxrpc_txbuf_get_retrans, "GET RETRANS") \ + EM(rxrpc_txbuf_put_ack_tx, "PUT ACK TX ") \ + EM(rxrpc_txbuf_put_cleaned, "PUT CLEANED") \ + EM(rxrpc_txbuf_put_nomem, "PUT NOMEM ") \ + EM(rxrpc_txbuf_put_rotated, "PUT ROTATED") \ + EM(rxrpc_txbuf_put_send_aborted, "PUT SEND-X ") \ + EM(rxrpc_txbuf_put_trans, "PUT TRANS ") \ + EM(rxrpc_txbuf_see_send_more, "SEE SEND+ ") \ + E_(rxrpc_txbuf_see_unacked, "SEE UNACKED") + /* * Generate enums for tracing information. */ @@ -263,12 +297,14 @@ enum rxrpc_propose_ack_outcome { rxrpc_propose_ack_outcomes } __mode(byte); enum rxrpc_propose_ack_trace { rxrpc_propose_ack_traces } __mode(byte); enum rxrpc_receive_trace { rxrpc_receive_traces } __mode(byte); enum rxrpc_recvmsg_trace { rxrpc_recvmsg_traces } __mode(byte); +enum rxrpc_req_ack_trace { rxrpc_req_ack_traces } __mode(byte); enum rxrpc_rtt_rx_trace { rxrpc_rtt_rx_traces } __mode(byte); enum rxrpc_rtt_tx_trace { rxrpc_rtt_tx_traces } __mode(byte); enum rxrpc_skb_trace { rxrpc_skb_traces } __mode(byte); enum rxrpc_timer_trace { rxrpc_timer_traces } __mode(byte); -enum rxrpc_transmit_trace { rxrpc_transmit_traces } __mode(byte); enum rxrpc_tx_point { rxrpc_tx_points } __mode(byte); +enum rxrpc_txbuf_trace { rxrpc_txbuf_traces } __mode(byte); +enum rxrpc_txqueue_trace { rxrpc_txqueue_traces } __mode(byte); #endif /* end __RXRPC_DECLARE_TRACE_ENUMS_ONCE_ONLY */ @@ -286,16 +322,17 @@ rxrpc_congest_changes; rxrpc_congest_modes; rxrpc_conn_traces; rxrpc_local_traces; -rxrpc_propose_ack_outcomes; rxrpc_propose_ack_traces; rxrpc_receive_traces; rxrpc_recvmsg_traces; +rxrpc_req_ack_traces; rxrpc_rtt_rx_traces; rxrpc_rtt_tx_traces; rxrpc_skb_traces; rxrpc_timer_traces; -rxrpc_transmit_traces; rxrpc_tx_points; +rxrpc_txbuf_traces; +rxrpc_txqueue_traces; /* * Now redefine the EM() and E_() macros to map the enums to the strings that @@ -449,14 +486,13 @@ TRACE_EVENT(rxrpc_call, TRACE_EVENT(rxrpc_skb, TP_PROTO(struct sk_buff *skb, enum rxrpc_skb_trace op, - int usage, int mod_count, u8 flags, const void *where), + int usage, int mod_count, const void *where), - TP_ARGS(skb, op, usage, mod_count, flags, where), + TP_ARGS(skb, op, usage, mod_count, where), TP_STRUCT__entry( __field(struct sk_buff *, skb ) __field(enum rxrpc_skb_trace, op ) - __field(u8, flags ) __field(int, usage ) __field(int, mod_count ) __field(const void *, where ) @@ -464,16 +500,14 @@ TRACE_EVENT(rxrpc_skb, TP_fast_assign( __entry->skb = skb; - __entry->flags = flags; __entry->op = op; __entry->usage = usage; __entry->mod_count = mod_count; __entry->where = where; ), - TP_printk("s=%p %cx %s u=%d m=%d p=%pSR", + TP_printk("s=%p Rx %s u=%d m=%d p=%pSR", __entry->skb, - __entry->flags & RXRPC_SKB_TX_BUFFER ? 'T' : 'R', __print_symbolic(__entry->op, rxrpc_skb_traces), __entry->usage, __entry->mod_count, @@ -578,15 +612,16 @@ TRACE_EVENT(rxrpc_call_complete, __entry->abort_code) ); -TRACE_EVENT(rxrpc_transmit, - TP_PROTO(struct rxrpc_call *call, enum rxrpc_transmit_trace why), +TRACE_EVENT(rxrpc_txqueue, + TP_PROTO(struct rxrpc_call *call, enum rxrpc_txqueue_trace why), TP_ARGS(call, why), TP_STRUCT__entry( __field(unsigned int, call ) - __field(enum rxrpc_transmit_trace, why ) - __field(rxrpc_seq_t, tx_hard_ack ) + __field(enum rxrpc_txqueue_trace, why ) + __field(rxrpc_seq_t, acks_hard_ack ) + __field(rxrpc_seq_t, tx_bottom ) __field(rxrpc_seq_t, tx_top ) __field(int, tx_winsize ) ), @@ -594,31 +629,33 @@ TRACE_EVENT(rxrpc_transmit, TP_fast_assign( __entry->call = call->debug_id; __entry->why = why; - __entry->tx_hard_ack = call->tx_hard_ack; + __entry->acks_hard_ack = call->acks_hard_ack; + __entry->tx_bottom = call->tx_bottom; __entry->tx_top = call->tx_top; __entry->tx_winsize = call->tx_winsize; ), - TP_printk("c=%08x %s f=%08x n=%u/%u", + TP_printk("c=%08x %s f=%08x h=%08x n=%u/%u/%u", __entry->call, - __print_symbolic(__entry->why, rxrpc_transmit_traces), - __entry->tx_hard_ack + 1, - __entry->tx_top - __entry->tx_hard_ack, + __print_symbolic(__entry->why, rxrpc_txqueue_traces), + __entry->tx_bottom, + __entry->acks_hard_ack, + __entry->tx_top - __entry->tx_bottom, + __entry->tx_top - __entry->acks_hard_ack, __entry->tx_winsize) ); TRACE_EVENT(rxrpc_rx_data, TP_PROTO(unsigned int call, rxrpc_seq_t seq, - rxrpc_serial_t serial, u8 flags, u8 anno), + rxrpc_serial_t serial, u8 flags), - TP_ARGS(call, seq, serial, flags, anno), + TP_ARGS(call, seq, serial, flags), TP_STRUCT__entry( __field(unsigned int, call ) __field(rxrpc_seq_t, seq ) __field(rxrpc_serial_t, serial ) __field(u8, flags ) - __field(u8, anno ) ), TP_fast_assign( @@ -626,15 +663,13 @@ TRACE_EVENT(rxrpc_rx_data, __entry->seq = seq; __entry->serial = serial; __entry->flags = flags; - __entry->anno = anno; ), - TP_printk("c=%08x DATA %08x q=%08x fl=%02x a=%02x", + TP_printk("c=%08x DATA %08x q=%08x fl=%02x", __entry->call, __entry->serial, __entry->seq, - __entry->flags, - __entry->anno) + __entry->flags) ); TRACE_EVENT(rxrpc_rx_ack, @@ -841,8 +876,7 @@ TRACE_EVENT(rxrpc_receive, __field(enum rxrpc_receive_trace, why ) __field(rxrpc_serial_t, serial ) __field(rxrpc_seq_t, seq ) - __field(rxrpc_seq_t, hard_ack ) - __field(rxrpc_seq_t, top ) + __field(u64, window ) ), TP_fast_assign( @@ -850,8 +884,7 @@ TRACE_EVENT(rxrpc_receive, __entry->why = why; __entry->serial = serial; __entry->seq = seq; - __entry->hard_ack = call->rx_hard_ack; - __entry->top = call->rx_top; + __entry->window = atomic64_read(&call->ackr_window); ), TP_printk("c=%08x %s r=%08x q=%08x w=%08x-%08x", @@ -859,12 +892,36 @@ TRACE_EVENT(rxrpc_receive, __print_symbolic(__entry->why, rxrpc_receive_traces), __entry->serial, __entry->seq, - __entry->hard_ack, - __entry->top) + lower_32_bits(__entry->window), + upper_32_bits(__entry->window)) ); TRACE_EVENT(rxrpc_recvmsg, TP_PROTO(struct rxrpc_call *call, enum rxrpc_recvmsg_trace why, + int ret), + + TP_ARGS(call, why, ret), + + TP_STRUCT__entry( + __field(unsigned int, call ) + __field(enum rxrpc_recvmsg_trace, why ) + __field(int, ret ) + ), + + TP_fast_assign( + __entry->call = call ? call->debug_id : 0; + __entry->why = why; + __entry->ret = ret; + ), + + TP_printk("c=%08x %s ret=%d", + __entry->call, + __print_symbolic(__entry->why, rxrpc_recvmsg_traces), + __entry->ret) + ); + +TRACE_EVENT(rxrpc_recvdata, + TP_PROTO(struct rxrpc_call *call, enum rxrpc_recvmsg_trace why, rxrpc_seq_t seq, unsigned int offset, unsigned int len, int ret), @@ -986,7 +1043,7 @@ TRACE_EVENT(rxrpc_timer, __entry->call = call->debug_id; __entry->why = why; __entry->now = now; - __entry->ack_at = call->ack_at; + __entry->ack_at = call->delay_ack_at; __entry->ack_lost_at = call->ack_lost_at; __entry->resend_at = call->resend_at; __entry->expect_rx_by = call->expect_rx_by; @@ -1007,6 +1064,47 @@ TRACE_EVENT(rxrpc_timer, __entry->timer - __entry->now) ); +TRACE_EVENT(rxrpc_timer_expired, + TP_PROTO(struct rxrpc_call *call, unsigned long now), + + TP_ARGS(call, now), + + TP_STRUCT__entry( + __field(unsigned int, call ) + __field(long, now ) + __field(long, ack_at ) + __field(long, ack_lost_at ) + __field(long, resend_at ) + __field(long, ping_at ) + __field(long, expect_rx_by ) + __field(long, expect_req_by ) + __field(long, expect_term_by ) + __field(long, timer ) + ), + + TP_fast_assign( + __entry->call = call->debug_id; + __entry->now = now; + __entry->ack_at = call->delay_ack_at; + __entry->ack_lost_at = call->ack_lost_at; + __entry->resend_at = call->resend_at; + __entry->expect_rx_by = call->expect_rx_by; + __entry->expect_req_by = call->expect_req_by; + __entry->expect_term_by = call->expect_term_by; + __entry->timer = call->timer.expires; + ), + + TP_printk("c=%08x EXPIRED a=%ld la=%ld r=%ld xr=%ld xq=%ld xt=%ld t=%ld", + __entry->call, + __entry->ack_at - __entry->now, + __entry->ack_lost_at - __entry->now, + __entry->resend_at - __entry->now, + __entry->expect_rx_by - __entry->now, + __entry->expect_req_by - __entry->now, + __entry->expect_term_by - __entry->now, + __entry->timer - __entry->now) + ); + TRACE_EVENT(rxrpc_rx_lose, TP_PROTO(struct rxrpc_skb_priv *sp), @@ -1031,20 +1129,15 @@ TRACE_EVENT(rxrpc_rx_lose, TRACE_EVENT(rxrpc_propose_ack, TP_PROTO(struct rxrpc_call *call, enum rxrpc_propose_ack_trace why, - u8 ack_reason, rxrpc_serial_t serial, bool immediate, - bool background, enum rxrpc_propose_ack_outcome outcome), + u8 ack_reason, rxrpc_serial_t serial), - TP_ARGS(call, why, ack_reason, serial, immediate, background, - outcome), + TP_ARGS(call, why, ack_reason, serial), TP_STRUCT__entry( __field(unsigned int, call ) __field(enum rxrpc_propose_ack_trace, why ) __field(rxrpc_serial_t, serial ) __field(u8, ack_reason ) - __field(bool, immediate ) - __field(bool, background ) - __field(enum rxrpc_propose_ack_outcome, outcome ) ), TP_fast_assign( @@ -1052,45 +1145,91 @@ TRACE_EVENT(rxrpc_propose_ack, __entry->why = why; __entry->serial = serial; __entry->ack_reason = ack_reason; - __entry->immediate = immediate; - __entry->background = background; - __entry->outcome = outcome; ), - TP_printk("c=%08x %s %s r=%08x i=%u b=%u%s", + TP_printk("c=%08x %s %s r=%08x", __entry->call, __print_symbolic(__entry->why, rxrpc_propose_ack_traces), __print_symbolic(__entry->ack_reason, rxrpc_ack_names), - __entry->serial, - __entry->immediate, - __entry->background, - __print_symbolic(__entry->outcome, rxrpc_propose_ack_outcomes)) + __entry->serial) + ); + +TRACE_EVENT(rxrpc_send_ack, + TP_PROTO(struct rxrpc_call *call, enum rxrpc_propose_ack_trace why, + u8 ack_reason, rxrpc_serial_t serial), + + TP_ARGS(call, why, ack_reason, serial), + + TP_STRUCT__entry( + __field(unsigned int, call ) + __field(enum rxrpc_propose_ack_trace, why ) + __field(rxrpc_serial_t, serial ) + __field(u8, ack_reason ) + ), + + TP_fast_assign( + __entry->call = call->debug_id; + __entry->why = why; + __entry->serial = serial; + __entry->ack_reason = ack_reason; + ), + + TP_printk("c=%08x %s %s r=%08x", + __entry->call, + __print_symbolic(__entry->why, rxrpc_propose_ack_traces), + __print_symbolic(__entry->ack_reason, rxrpc_ack_names), + __entry->serial) + ); + +TRACE_EVENT(rxrpc_drop_ack, + TP_PROTO(struct rxrpc_call *call, enum rxrpc_propose_ack_trace why, + u8 ack_reason, rxrpc_serial_t serial, bool nobuf), + + TP_ARGS(call, why, ack_reason, serial, nobuf), + + TP_STRUCT__entry( + __field(unsigned int, call ) + __field(enum rxrpc_propose_ack_trace, why ) + __field(rxrpc_serial_t, serial ) + __field(u8, ack_reason ) + __field(bool, nobuf ) + ), + + TP_fast_assign( + __entry->call = call->debug_id; + __entry->why = why; + __entry->serial = serial; + __entry->ack_reason = ack_reason; + __entry->nobuf = nobuf; + ), + + TP_printk("c=%08x %s %s r=%08x nbf=%u", + __entry->call, + __print_symbolic(__entry->why, rxrpc_propose_ack_traces), + __print_symbolic(__entry->ack_reason, rxrpc_ack_names), + __entry->serial, __entry->nobuf) ); TRACE_EVENT(rxrpc_retransmit, - TP_PROTO(struct rxrpc_call *call, rxrpc_seq_t seq, u8 annotation, - s64 expiry), + TP_PROTO(struct rxrpc_call *call, rxrpc_seq_t seq, s64 expiry), - TP_ARGS(call, seq, annotation, expiry), + TP_ARGS(call, seq, expiry), TP_STRUCT__entry( __field(unsigned int, call ) __field(rxrpc_seq_t, seq ) - __field(u8, annotation ) __field(s64, expiry ) ), TP_fast_assign( __entry->call = call->debug_id; __entry->seq = seq; - __entry->annotation = annotation; __entry->expiry = expiry; ), - TP_printk("c=%08x q=%x a=%02x xp=%lld", + TP_printk("c=%08x q=%x xp=%lld", __entry->call, __entry->seq, - __entry->annotation, __entry->expiry) ); @@ -1113,14 +1252,14 @@ TRACE_EVENT(rxrpc_congest, TP_fast_assign( __entry->call = call->debug_id; __entry->change = change; - __entry->hard_ack = call->tx_hard_ack; + __entry->hard_ack = call->acks_hard_ack; __entry->top = call->tx_top; __entry->lowest_nak = call->acks_lowest_nak; __entry->ack_serial = ack_serial; memcpy(&__entry->sum, summary, sizeof(__entry->sum)); ), - TP_printk("c=%08x r=%08x %s q=%08x %s cw=%u ss=%u nr=%u,%u nw=%u,%u r=%u b=%u u=%u d=%u l=%x%s%s%s", + TP_printk("c=%08x r=%08x %s q=%08x %s cw=%u ss=%u nA=%u,%u+%u r=%u b=%u u=%u d=%u l=%x%s%s%s", __entry->call, __entry->ack_serial, __print_symbolic(__entry->sum.ack_reason, rxrpc_ack_names), @@ -1128,8 +1267,8 @@ TRACE_EVENT(rxrpc_congest, __print_symbolic(__entry->sum.mode, rxrpc_congest_modes), __entry->sum.cwnd, __entry->sum.ssthresh, - __entry->sum.nr_acks, __entry->sum.nr_nacks, - __entry->sum.nr_new_acks, __entry->sum.nr_new_nacks, + __entry->sum.nr_acks, __entry->sum.saw_nacks, + __entry->sum.nr_new_acks, __entry->sum.nr_rot_new_acks, __entry->top - __entry->hard_ack, __entry->sum.cumulative_acks, @@ -1230,26 +1369,23 @@ TRACE_EVENT(rxrpc_connect_call, ); TRACE_EVENT(rxrpc_resend, - TP_PROTO(struct rxrpc_call *call, int ix), + TP_PROTO(struct rxrpc_call *call), - TP_ARGS(call, ix), + TP_ARGS(call), TP_STRUCT__entry( __field(unsigned int, call ) - __field(int, ix ) - __array(u8, anno, 64 ) + __field(rxrpc_seq_t, seq ) ), TP_fast_assign( __entry->call = call->debug_id; - __entry->ix = ix; - memcpy(__entry->anno, call->rxtx_annotations, 64); + __entry->seq = call->acks_hard_ack; ), - TP_printk("c=%08x ix=%u a=%64phN", + TP_printk("c=%08x q=%x", __entry->call, - __entry->ix, - __entry->anno) + __entry->seq) ); TRACE_EVENT(rxrpc_rx_icmp, @@ -1329,8 +1465,8 @@ TRACE_EVENT(rxrpc_call_reset, __entry->call_id = call->call_id; __entry->call_serial = call->rx_serial; __entry->conn_serial = call->conn->hi_serial; - __entry->tx_seq = call->tx_hard_ack; - __entry->rx_seq = call->rx_hard_ack; + __entry->tx_seq = call->acks_hard_ack; + __entry->rx_seq = call->rx_highest_seq; ), TP_printk("c=%08x %08x:%08x r=%08x/%08x tx=%08x rx=%08x", @@ -1395,6 +1531,61 @@ TRACE_EVENT(rxrpc_rx_discard_ack, __entry->call_ackr_prev) ); +TRACE_EVENT(rxrpc_req_ack, + TP_PROTO(unsigned int call_debug_id, rxrpc_seq_t seq, + enum rxrpc_req_ack_trace why), + + TP_ARGS(call_debug_id, seq, why), + + TP_STRUCT__entry( + __field(unsigned int, call_debug_id ) + __field(rxrpc_seq_t, seq ) + __field(enum rxrpc_req_ack_trace, why ) + ), + + TP_fast_assign( + __entry->call_debug_id = call_debug_id; + __entry->seq = seq; + __entry->why = why; + ), + + TP_printk("c=%08x q=%08x REQ-%s", + __entry->call_debug_id, + __entry->seq, + __print_symbolic(__entry->why, rxrpc_req_ack_traces)) + ); + +TRACE_EVENT(rxrpc_txbuf, + TP_PROTO(unsigned int debug_id, + unsigned int call_debug_id, rxrpc_seq_t seq, + int ref, enum rxrpc_txbuf_trace what), + + TP_ARGS(debug_id, call_debug_id, seq, ref, what), + + TP_STRUCT__entry( + __field(unsigned int, debug_id ) + __field(unsigned int, call_debug_id ) + __field(rxrpc_seq_t, seq ) + __field(int, ref ) + __field(enum rxrpc_txbuf_trace, what ) + ), + + TP_fast_assign( + __entry->debug_id = debug_id; + __entry->call_debug_id = call_debug_id; + __entry->seq = seq; + __entry->ref = ref; + __entry->what = what; + ), + + TP_printk("B=%08x c=%08x q=%08x %s r=%d", + __entry->debug_id, + __entry->call_debug_id, + __entry->seq, + __print_symbolic(__entry->what, rxrpc_txbuf_traces), + __entry->ref) + ); + #undef EM #undef E_ #endif /* _TRACE_RXRPC_H */ diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index 7c1dc818b1d5..d676ed2b246e 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -187,7 +187,7 @@ #define AUDIT_MAX_KEY_LEN 256 #define AUDIT_BITMASK_SIZE 64 #define AUDIT_WORD(nr) ((__u32)((nr)/32)) -#define AUDIT_BIT(nr) (1 << ((nr) - AUDIT_WORD(nr)*32)) +#define AUDIT_BIT(nr) (1U << ((nr) - AUDIT_WORD(nr)*32)) #define AUDIT_SYSCALL_CLASSES 16 #define AUDIT_CLASS_DIR_WRITE 0 diff --git a/include/uapi/linux/capability.h b/include/uapi/linux/capability.h index 463d1ba2232a..3d61a0ae055d 100644 --- a/include/uapi/linux/capability.h +++ b/include/uapi/linux/capability.h @@ -426,7 +426,7 @@ struct vfs_ns_cap_data { */ #define CAP_TO_INDEX(x) ((x) >> 5) /* 1 << 5 == bits in __u32 */ -#define CAP_TO_MASK(x) (1 << ((x) & 31)) /* mask for indexed __u32 */ +#define CAP_TO_MASK(x) (1U << ((x) & 31)) /* mask for indexed __u32 */ #endif /* _UAPI_LINUX_CAPABILITY_H */ diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index bb57084ac524..aaf7c6963d61 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -262,6 +262,7 @@ enum { ETHTOOL_A_LINKSTATE_SQI_MAX, /* u32 */ ETHTOOL_A_LINKSTATE_EXT_STATE, /* u8 */ ETHTOOL_A_LINKSTATE_EXT_SUBSTATE, /* u8 */ + ETHTOOL_A_LINKSTATE_EXT_DOWN_CNT, /* u32 */ /* add new constants above here */ __ETHTOOL_A_LINKSTATE_CNT, diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 5e7a1041df3a..1021a7e47a86 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -372,6 +372,8 @@ enum { IFLA_TSO_MAX_SEGS, IFLA_ALLMULTI, /* Allmulti count: > 0 means acts ALLMULTI */ + IFLA_DEVLINK_PORT, + __IFLA_MAX }; @@ -561,6 +563,7 @@ enum { IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT, IFLA_BRPORT_MCAST_EHT_HOSTS_CNT, IFLA_BRPORT_LOCKED, + IFLA_BRPORT_MAB, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h index f243ce665f74..07a4cb149305 100644 --- a/include/uapi/linux/in.h +++ b/include/uapi/linux/in.h @@ -20,6 +20,7 @@ #define _UAPI_LINUX_IN_H #include <linux/types.h> +#include <linux/stddef.h> #include <linux/libc-compat.h> #include <linux/socket.h> diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h index a998bf761635..5e67a7eaf4a7 100644 --- a/include/uapi/linux/neighbour.h +++ b/include/uapi/linux/neighbour.h @@ -52,7 +52,8 @@ enum { #define NTF_STICKY (1 << 6) #define NTF_ROUTER (1 << 7) /* Extended flags under NDA_FLAGS_EXT: */ -#define NTF_EXT_MANAGED (1 << 0) +#define NTF_EXT_MANAGED (1 << 0) +#define NTF_EXT_LOCKED (1 << 1) /* * Neighbor Cache Entry States. @@ -86,6 +87,11 @@ enum { * NTF_EXT_MANAGED flagged neigbor entries are managed by the kernel on behalf * of a user space control plane, and automatically refreshed so that (if * possible) they remain in NUD_REACHABLE state. + * + * NTF_EXT_LOCKED flagged bridge FDB entries are entries generated by the + * bridge in response to a host trying to communicate via a locked bridge port + * with MAB enabled. Their purpose is to notify user space that a host requires + * authentication. */ struct nda_cacheinfo { diff --git a/include/uapi/linux/tc_act/tc_ct.h b/include/uapi/linux/tc_act/tc_ct.h index 5fb1d7ac1027..6c5200f0ed38 100644 --- a/include/uapi/linux/tc_act/tc_ct.h +++ b/include/uapi/linux/tc_act/tc_ct.h @@ -22,6 +22,9 @@ enum { TCA_CT_NAT_PORT_MIN, /* be16 */ TCA_CT_NAT_PORT_MAX, /* be16 */ TCA_CT_PAD, + TCA_CT_HELPER_NAME, /* string */ + TCA_CT_HELPER_FAMILY, /* u8 */ + TCA_CT_HELPER_PROTO, /* u8 */ __TCA_CT_MAX }; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index d3b75aa0c54d..07c0259dfc1a 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1029,12 +1029,17 @@ out: */ static void *realloc_array(void *arr, size_t old_n, size_t new_n, size_t size) { + void *new_arr; + if (!new_n || old_n == new_n) goto out; - arr = krealloc_array(arr, new_n, size, GFP_KERNEL); - if (!arr) + new_arr = krealloc_array(arr, new_n, size, GFP_KERNEL); + if (!new_arr) { + kfree(arr); return NULL; + } + arr = new_arr; if (new_n > old_n) memset(arr + old_n * size, 0, (new_n - old_n) * size); @@ -6734,8 +6739,12 @@ static int release_reference(struct bpf_verifier_env *env, return err; bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({ - if (reg->ref_obj_id == ref_obj_id) - __mark_reg_unknown(env, reg); + if (reg->ref_obj_id == ref_obj_id) { + if (!env->allow_ptr_leaks) + __mark_reg_not_init(env, reg); + else + __mark_reg_unknown(env, reg); + } })); return 0; diff --git a/kernel/events/hw_breakpoint_test.c b/kernel/events/hw_breakpoint_test.c index 5ced822df788..c57610f52bb4 100644 --- a/kernel/events/hw_breakpoint_test.c +++ b/kernel/events/hw_breakpoint_test.c @@ -295,11 +295,11 @@ static int test_init(struct kunit *test) { /* Most test cases want 2 distinct CPUs. */ if (num_online_cpus() < 2) - return -EINVAL; + kunit_skip(test, "not enough cpus"); /* Want the system to not use breakpoints elsewhere. */ if (hw_breakpoint_is_used()) - return -EBUSY; + kunit_skip(test, "hw breakpoint already in use"); return 0; } diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 3220b0a2fb4a..cd9f5a66a690 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -2429,8 +2429,11 @@ int enable_kprobe(struct kprobe *kp) if (!kprobes_all_disarmed && kprobe_disabled(p)) { p->flags &= ~KPROBE_FLAG_DISABLED; ret = arm_kprobe(p); - if (ret) + if (ret) { p->flags |= KPROBE_FLAG_DISABLED; + if (p != kp) + kp->flags |= KPROBE_FLAG_DISABLED; + } } out: mutex_unlock(&kprobe_mutex); diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index aac63ca9c3d1..e8143e368074 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -141,6 +141,8 @@ static int fprobe_init_rethook(struct fprobe *fp, int num) return -E2BIG; fp->rethook = rethook_alloc((void *)fp, fprobe_exit_handler); + if (!fp->rethook) + return -ENOMEM; for (i = 0; i < size; i++) { struct fprobe_rethook_node *node; @@ -301,7 +303,8 @@ int unregister_fprobe(struct fprobe *fp) { int ret; - if (!fp || fp->ops.func != fprobe_handler) + if (!fp || (fp->ops.saved_func != fprobe_handler && + fp->ops.saved_func != fprobe_kprobe_handler)) return -EINVAL; /* diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 72de9009a6a0..705b990d264d 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -3028,18 +3028,8 @@ int ftrace_shutdown(struct ftrace_ops *ops, int command) command |= FTRACE_UPDATE_TRACE_FUNC; } - if (!command || !ftrace_enabled) { - /* - * If these are dynamic or per_cpu ops, they still - * need their data freed. Since, function tracing is - * not currently active, we can just free them - * without synchronizing all CPUs. - */ - if (ops->flags & FTRACE_OPS_FL_DYNAMIC) - goto free_ops; - - return 0; - } + if (!command || !ftrace_enabled) + goto out; /* * If the ops uses a trampoline, then it needs to be @@ -3076,6 +3066,7 @@ int ftrace_shutdown(struct ftrace_ops *ops, int command) removed_ops = NULL; ops->flags &= ~FTRACE_OPS_FL_REMOVING; +out: /* * Dynamic ops may be freed, we must make sure that all * callers are done before leaving this function. @@ -3103,7 +3094,6 @@ int ftrace_shutdown(struct ftrace_ops *ops, int command) if (IS_ENABLED(CONFIG_PREEMPTION)) synchronize_rcu_tasks(); - free_ops: ftrace_trampoline_free(ops); } diff --git a/kernel/trace/kprobe_event_gen_test.c b/kernel/trace/kprobe_event_gen_test.c index 80e04a1e1977..d81f7c51025c 100644 --- a/kernel/trace/kprobe_event_gen_test.c +++ b/kernel/trace/kprobe_event_gen_test.c @@ -100,20 +100,20 @@ static int __init test_gen_kprobe_cmd(void) KPROBE_GEN_TEST_FUNC, KPROBE_GEN_TEST_ARG0, KPROBE_GEN_TEST_ARG1); if (ret) - goto free; + goto out; /* Use kprobe_event_add_fields to add the rest of the fields */ ret = kprobe_event_add_fields(&cmd, KPROBE_GEN_TEST_ARG2, KPROBE_GEN_TEST_ARG3); if (ret) - goto free; + goto out; /* * This actually creates the event. */ ret = kprobe_event_gen_cmd_end(&cmd); if (ret) - goto free; + goto out; /* * Now get the gen_kprobe_test event file. We need to prevent @@ -136,13 +136,11 @@ static int __init test_gen_kprobe_cmd(void) goto delete; } out: + kfree(buf); return ret; delete: /* We got an error after creating the event, delete it */ ret = kprobe_event_delete("gen_kprobe_test"); - free: - kfree(buf); - goto out; } @@ -170,14 +168,14 @@ static int __init test_gen_kretprobe_cmd(void) KPROBE_GEN_TEST_FUNC, "$retval"); if (ret) - goto free; + goto out; /* * This actually creates the event. */ ret = kretprobe_event_gen_cmd_end(&cmd); if (ret) - goto free; + goto out; /* * Now get the gen_kretprobe_test event file. We need to @@ -201,13 +199,11 @@ static int __init test_gen_kretprobe_cmd(void) goto delete; } out: + kfree(buf); return ret; delete: /* We got an error after creating the event, delete it */ ret = kprobe_event_delete("gen_kretprobe_test"); - free: - kfree(buf); - goto out; } diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 199759c73519..9712083832f4 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -937,6 +937,9 @@ void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu) struct ring_buffer_per_cpu *cpu_buffer; struct rb_irq_work *rbwork; + if (!buffer) + return; + if (cpu == RING_BUFFER_ALL_CPUS) { /* Wake up individual ones too. One level recursion */ @@ -945,7 +948,15 @@ void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu) rbwork = &buffer->irq_work; } else { + if (WARN_ON_ONCE(!buffer->buffers)) + return; + if (WARN_ON_ONCE(cpu >= nr_cpu_ids)) + return; + cpu_buffer = buffer->buffers[cpu]; + /* The CPU buffer may not have been initialized yet */ + if (!cpu_buffer) + return; rbwork = &cpu_buffer->irq_work; } diff --git a/lib/net_utils.c b/lib/net_utils.c index af525353395d..c17201df3d08 100644 --- a/lib/net_utils.c +++ b/lib/net_utils.c @@ -6,10 +6,11 @@ bool mac_pton(const char *s, u8 *mac) { + size_t maxlen = 3 * ETH_ALEN - 1; int i; /* XX:XX:XX:XX:XX:XX */ - if (strlen(s) < 3 * ETH_ALEN - 1) + if (strnlen(s, maxlen) < maxlen) return false; /* Don't dirty result unless string is valid MAC. */ diff --git a/lib/nlattr.c b/lib/nlattr.c index b67a53e29b8f..9055e8b4d144 100644 --- a/lib/nlattr.c +++ b/lib/nlattr.c @@ -646,7 +646,7 @@ EXPORT_SYMBOL(__nla_validate); /** * nla_policy_len - Determine the max. length of a policy - * @policy: policy to use + * @p: policy to use * @n: number of policies * * Determines the max. length of the policy. It is currently used diff --git a/lib/test_bpf.c b/lib/test_bpf.c index 5820704165a6..ade9ac672adb 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -14346,7 +14346,6 @@ static struct sk_buff *populate_skb(char *buf, int size) skb->hash = SKB_HASH; skb->queue_mapping = SKB_QUEUE_MAP; skb->vlan_tci = SKB_VLAN_TCI; - skb->vlan_present = SKB_VLAN_PRESENT; skb->vlan_proto = htons(ETH_P_IP); dev_net_set(&dev, &init_net); skb->dev = &dev; diff --git a/mm/slab_common.c b/mm/slab_common.c index 33b1886b06eb..0042fb2730d1 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -941,7 +941,7 @@ void *__do_kmalloc_node(size_t size, gfp_t flags, int node, unsigned long caller if (unlikely(size > KMALLOC_MAX_CACHE_SIZE)) { ret = __kmalloc_large_node(size, flags, node); - trace_kmalloc(_RET_IP_, ret, size, + trace_kmalloc(caller, ret, size, PAGE_SIZE << get_order(size), flags, node); return ret; } @@ -953,7 +953,7 @@ void *__do_kmalloc_node(size_t size, gfp_t flags, int node, unsigned long caller ret = __kmem_cache_alloc_node(s, flags, node, size, caller); ret = kasan_kmalloc(s, ret, size, flags); - trace_kmalloc(_RET_IP_, ret, size, s->size, flags, node); + trace_kmalloc(caller, ret, size, s->size, flags, node); return ret; } @@ -1010,7 +1010,7 @@ EXPORT_SYMBOL(kfree); /** * __ksize -- Report full size of underlying allocation - * @objp: pointer to the object + * @object: pointer to the object * * This should only be used internally to query the true size of allocations. * It is not meant to be a way to discover the usable size of an allocation @@ -1018,7 +1018,7 @@ EXPORT_SYMBOL(kfree); * the originally requested allocation size may trigger KASAN, UBSAN_BOUNDS, * and/or FORTIFY_SOURCE. * - * Return: size of the actual memory used by @objp in bytes + * Return: size of the actual memory used by @object in bytes */ size_t __ksize(const void *object) { @@ -1040,7 +1040,6 @@ size_t __ksize(const void *object) return slab_ksize(folio_slab(folio)->slab_cache); } -#ifdef CONFIG_TRACING void *kmalloc_trace(struct kmem_cache *s, gfp_t gfpflags, size_t size) { void *ret = __kmem_cache_alloc_node(s, gfpflags, NUMA_NO_NODE, @@ -1064,7 +1063,6 @@ void *kmalloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, return ret; } EXPORT_SYMBOL(kmalloc_node_trace); -#endif /* !CONFIG_TRACING */ #endif /* !CONFIG_SLOB */ gfp_t kmalloc_fix_flags(gfp_t flags) @@ -1411,20 +1409,6 @@ void kfree_sensitive(const void *p) } EXPORT_SYMBOL(kfree_sensitive); -/** - * ksize - get the actual amount of memory allocated for a given object - * @objp: Pointer to the object - * - * kmalloc may internally round up allocations and return more memory - * than requested. ksize() can be used to determine the actual amount of - * memory allocated. The caller may use this additional memory, even though - * a smaller amount of memory was initially specified with the kmalloc call. - * The caller must guarantee that objp points to a valid object previously - * allocated with either kmalloc() or kmem_cache_alloc(). The object - * must not be freed during the duration of the call. - * - * Return: size of the actual memory used by @objp in bytes - */ size_t ksize(const void *objp) { size_t size; diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c index a5e4a4e976cf..ad5714f737be 100644 --- a/net/batman-adv/netlink.c +++ b/net/batman-adv/netlink.c @@ -1267,7 +1267,8 @@ batadv_get_vlan_from_info(struct batadv_priv *bat_priv, struct net *net, * * Return: 0 on success or negative error number in case of failure */ -static int batadv_pre_doit(const struct genl_ops *ops, struct sk_buff *skb, +static int batadv_pre_doit(const struct genl_split_ops *ops, + struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); @@ -1332,7 +1333,8 @@ err_put_softif: * @skb: Netlink message with request data * @info: receiver information */ -static void batadv_post_doit(const struct genl_ops *ops, struct sk_buff *skb, +static void batadv_post_doit(const struct genl_split_ops *ops, + struct sk_buff *skb, struct genl_info *info) { struct batadv_hard_iface *hard_iface; diff --git a/net/bridge/br.c b/net/bridge/br.c index 96e91d69a9a8..4f5098d33a46 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -166,13 +166,14 @@ static int br_switchdev_event(struct notifier_block *unused, case SWITCHDEV_FDB_ADD_TO_BRIDGE: fdb_info = ptr; err = br_fdb_external_learn_add(br, p, fdb_info->addr, - fdb_info->vid, false); + fdb_info->vid, + fdb_info->locked, false); if (err) { err = notifier_from_errno(err); break; } br_fdb_offloaded_set(br, p, fdb_info->addr, - fdb_info->vid, true); + fdb_info->vid, fdb_info->offloaded); break; case SWITCHDEV_FDB_DEL_TO_BRIDGE: fdb_info = ptr; diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index e7f4fccb6adb..e69a872bfc1d 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -105,6 +105,7 @@ static int fdb_fill_info(struct sk_buff *skb, const struct net_bridge *br, struct nda_cacheinfo ci; struct nlmsghdr *nlh; struct ndmsg *ndm; + u32 ext_flags = 0; nlh = nlmsg_put(skb, portid, seq, type, sizeof(*ndm), flags); if (nlh == NULL) @@ -125,11 +126,16 @@ static int fdb_fill_info(struct sk_buff *skb, const struct net_bridge *br, ndm->ndm_flags |= NTF_EXT_LEARNED; if (test_bit(BR_FDB_STICKY, &fdb->flags)) ndm->ndm_flags |= NTF_STICKY; + if (test_bit(BR_FDB_LOCKED, &fdb->flags)) + ext_flags |= NTF_EXT_LOCKED; if (nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->key.addr)) goto nla_put_failure; if (nla_put_u32(skb, NDA_MASTER, br->dev->ifindex)) goto nla_put_failure; + if (nla_put_u32(skb, NDA_FLAGS_EXT, ext_flags)) + goto nla_put_failure; + ci.ndm_used = jiffies_to_clock_t(now - fdb->used); ci.ndm_confirmed = 0; ci.ndm_updated = jiffies_to_clock_t(now - fdb->updated); @@ -171,6 +177,7 @@ static inline size_t fdb_nlmsg_size(void) return NLMSG_ALIGN(sizeof(struct ndmsg)) + nla_total_size(ETH_ALEN) /* NDA_LLADDR */ + nla_total_size(sizeof(u32)) /* NDA_MASTER */ + + nla_total_size(sizeof(u32)) /* NDA_FLAGS_EXT */ + nla_total_size(sizeof(u16)) /* NDA_VLAN */ + nla_total_size(sizeof(struct nda_cacheinfo)) + nla_total_size(0) /* NDA_FDB_EXT_ATTRS */ @@ -879,6 +886,11 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, &fdb->flags))) clear_bit(BR_FDB_ADDED_BY_EXT_LEARN, &fdb->flags); + /* Clear locked flag when roaming to an + * unlocked port. + */ + if (unlikely(test_bit(BR_FDB_LOCKED, &fdb->flags))) + clear_bit(BR_FDB_LOCKED, &fdb->flags); } if (unlikely(test_bit(BR_FDB_ADDED_BY_USER, &flags))) @@ -1082,6 +1094,9 @@ static int fdb_add_entry(struct net_bridge *br, struct net_bridge_port *source, modified = true; } + if (test_and_clear_bit(BR_FDB_LOCKED, &fdb->flags)) + modified = true; + if (fdb_handle_notify(fdb, notify)) modified = true; @@ -1124,7 +1139,7 @@ static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge *br, "FDB entry towards bridge must be permanent"); return -EINVAL; } - err = br_fdb_external_learn_add(br, p, addr, vid, true); + err = br_fdb_external_learn_add(br, p, addr, vid, false, true); } else { spin_lock_bh(&br->hash_lock); err = fdb_add_entry(br, p, addr, ndm, nlh_flags, vid, nfea_tb); @@ -1150,6 +1165,7 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_bridge_port *p = NULL; struct net_bridge_vlan *v; struct net_bridge *br = NULL; + u32 ext_flags = 0; int err = 0; trace_br_fdb_add(ndm, dev, addr, vid, nlh_flags); @@ -1178,6 +1194,14 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], vg = nbp_vlan_group(p); } + if (tb[NDA_FLAGS_EXT]) + ext_flags = nla_get_u32(tb[NDA_FLAGS_EXT]); + + if (ext_flags & NTF_EXT_LOCKED) { + NL_SET_ERR_MSG_MOD(extack, "Cannot add FDB entry with \"locked\" flag set"); + return -EINVAL; + } + if (tb[NDA_FDB_EXT_ATTRS]) { attr = tb[NDA_FDB_EXT_ATTRS]; err = nla_parse_nested(nfea_tb, NFEA_MAX, attr, @@ -1353,7 +1377,7 @@ void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p) } int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, - const unsigned char *addr, u16 vid, + const unsigned char *addr, u16 vid, bool locked, bool swdev_notify) { struct net_bridge_fdb_entry *fdb; @@ -1362,6 +1386,9 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, trace_br_fdb_external_learn_add(br, p, addr, vid); + if (locked && (!p || !(p->flags & BR_PORT_MAB))) + return -EINVAL; + spin_lock_bh(&br->hash_lock); fdb = br_fdb_find(br, addr, vid); @@ -1374,6 +1401,9 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, if (!p) flags |= BIT(BR_FDB_LOCAL); + if (locked) + flags |= BIT(BR_FDB_LOCKED); + fdb = fdb_create(br, p, addr, vid, flags); if (!fdb) { err = -ENOMEM; @@ -1381,6 +1411,13 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, } fdb_notify(br, fdb, RTM_NEWNEIGH, swdev_notify); } else { + if (locked && + (!test_bit(BR_FDB_LOCKED, &fdb->flags) || + READ_ONCE(fdb->dst) != p)) { + err = -EINVAL; + goto err_unlock; + } + fdb->updated = jiffies; if (READ_ONCE(fdb->dst) != p) { @@ -1397,6 +1434,11 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, modified = true; } + if (locked != test_bit(BR_FDB_LOCKED, &fdb->flags)) { + change_bit(BR_FDB_LOCKED, &fdb->flags); + modified = true; + } + if (swdev_notify) set_bit(BR_FDB_ADDED_BY_USER, &fdb->flags); diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 68b3e850bcb9..d04d2205ad4e 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -109,9 +109,26 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb struct net_bridge_fdb_entry *fdb_src = br_fdb_find_rcu(br, eth_hdr(skb)->h_source, vid); - if (!fdb_src || READ_ONCE(fdb_src->dst) != p || - test_bit(BR_FDB_LOCAL, &fdb_src->flags)) + if (!fdb_src) { + /* FDB miss. Create locked FDB entry if MAB is enabled + * and drop the packet. + */ + if (p->flags & BR_PORT_MAB) + br_fdb_update(br, p, eth_hdr(skb)->h_source, + vid, BIT(BR_FDB_LOCKED)); goto drop; + } else if (READ_ONCE(fdb_src->dst) != p || + test_bit(BR_FDB_LOCAL, &fdb_src->flags)) { + /* FDB mismatch. Drop the packet without roaming. */ + goto drop; + } else if test_bit(BR_FDB_LOCKED, &fdb_src->flags) { + /* FDB match, but entry is locked. Refresh it and drop + * the packet. + */ + br_fdb_update(br, p, eth_hdr(skb)->h_source, vid, + BIT(BR_FDB_LOCKED)); + goto drop; + } } nbp_switchdev_frame_mark(p, skb); diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index d087fd4c784a..4316cc82ae17 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -188,6 +188,7 @@ static inline size_t br_port_info_size(void) + nla_total_size(1) /* IFLA_BRPORT_NEIGH_SUPPRESS */ + nla_total_size(1) /* IFLA_BRPORT_ISOLATED */ + nla_total_size(1) /* IFLA_BRPORT_LOCKED */ + + nla_total_size(1) /* IFLA_BRPORT_MAB */ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_ROOT_ID */ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_BRIDGE_ID */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_DESIGNATED_PORT */ @@ -274,7 +275,8 @@ static int br_port_fill_attrs(struct sk_buff *skb, nla_put_u8(skb, IFLA_BRPORT_MRP_IN_OPEN, !!(p->flags & BR_MRP_LOST_IN_CONT)) || nla_put_u8(skb, IFLA_BRPORT_ISOLATED, !!(p->flags & BR_ISOLATED)) || - nla_put_u8(skb, IFLA_BRPORT_LOCKED, !!(p->flags & BR_PORT_LOCKED))) + nla_put_u8(skb, IFLA_BRPORT_LOCKED, !!(p->flags & BR_PORT_LOCKED)) || + nla_put_u8(skb, IFLA_BRPORT_MAB, !!(p->flags & BR_PORT_MAB))) return -EMSGSIZE; timerval = br_timer_value(&p->message_age_timer); @@ -876,6 +878,7 @@ static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = { [IFLA_BRPORT_NEIGH_SUPPRESS] = { .type = NLA_U8 }, [IFLA_BRPORT_ISOLATED] = { .type = NLA_U8 }, [IFLA_BRPORT_LOCKED] = { .type = NLA_U8 }, + [IFLA_BRPORT_MAB] = { .type = NLA_U8 }, [IFLA_BRPORT_BACKUP_PORT] = { .type = NLA_U32 }, [IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT] = { .type = NLA_U32 }, }; @@ -943,6 +946,22 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[], br_set_port_flag(p, tb, IFLA_BRPORT_NEIGH_SUPPRESS, BR_NEIGH_SUPPRESS); br_set_port_flag(p, tb, IFLA_BRPORT_ISOLATED, BR_ISOLATED); br_set_port_flag(p, tb, IFLA_BRPORT_LOCKED, BR_PORT_LOCKED); + br_set_port_flag(p, tb, IFLA_BRPORT_MAB, BR_PORT_MAB); + + if ((p->flags & BR_PORT_MAB) && + (!(p->flags & BR_PORT_LOCKED) || !(p->flags & BR_LEARNING))) { + NL_SET_ERR_MSG(extack, "Bridge port must be locked and have learning enabled when MAB is enabled"); + p->flags = old_flags; + return -EINVAL; + } else if (!(p->flags & BR_PORT_MAB) && (old_flags & BR_PORT_MAB)) { + struct net_bridge_fdb_flush_desc desc = { + .flags = BIT(BR_FDB_LOCKED), + .flags_mask = BIT(BR_FDB_LOCKED), + .port_ifindex = p->dev->ifindex, + }; + + br_fdb_flush(p->br, &desc); + } changed_mask = old_flags ^ p->flags; diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 06e5f6faa431..4c4fda930068 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -251,7 +251,8 @@ enum { BR_FDB_ADDED_BY_EXT_LEARN, BR_FDB_OFFLOADED, BR_FDB_NOTIFY, - BR_FDB_NOTIFY_INACTIVE + BR_FDB_NOTIFY_INACTIVE, + BR_FDB_LOCKED, }; struct net_bridge_fdb_key { @@ -810,7 +811,7 @@ int br_fdb_sync_static(struct net_bridge *br, struct net_bridge_port *p); void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p); int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, const unsigned char *addr, u16 vid, - bool swdev_notify); + bool locked, bool swdev_notify); int br_fdb_external_learn_del(struct net_bridge *br, struct net_bridge_port *p, const unsigned char *addr, u16 vid, bool swdev_notify); diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index 8f3d76c751dd..7eb6fd5bb917 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -71,7 +71,7 @@ bool nbp_switchdev_allowed_egress(const struct net_bridge_port *p, } /* Flags that can be offloaded to hardware */ -#define BR_PORT_FLAGS_HW_OFFLOAD (BR_LEARNING | BR_FLOOD | \ +#define BR_PORT_FLAGS_HW_OFFLOAD (BR_LEARNING | BR_FLOOD | BR_PORT_MAB | \ BR_MCAST_FLOOD | BR_BCAST_FLOOD | BR_PORT_LOCKED | \ BR_HAIRPIN_MODE | BR_ISOLATED | BR_MULTICAST_TO_UNICAST) @@ -136,6 +136,7 @@ static void br_switchdev_fdb_populate(struct net_bridge *br, item->added_by_user = test_bit(BR_FDB_ADDED_BY_USER, &fdb->flags); item->offloaded = test_bit(BR_FDB_OFFLOADED, &fdb->flags); item->is_local = test_bit(BR_FDB_LOCAL, &fdb->flags); + item->locked = false; item->info.dev = (!p || item->is_local) ? br->dev : p->dev; item->info.ctx = ctx; } @@ -146,6 +147,9 @@ br_switchdev_fdb_notify(struct net_bridge *br, { struct switchdev_notifier_fdb_info item; + if (test_bit(BR_FDB_LOCKED, &fdb->flags)) + return; + br_switchdev_fdb_populate(br, &item, fdb, NULL); switch (type) { diff --git a/net/can/af_can.c b/net/can/af_can.c index 9503ab10f9b8..27dcdcc0b808 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -450,7 +450,7 @@ int can_rx_register(struct net *net, struct net_device *dev, canid_t can_id, /* insert new receiver (dev,canid,mask) -> (func,data) */ - if (dev && dev->type != ARPHRD_CAN) + if (dev && (dev->type != ARPHRD_CAN || !can_get_ml_priv(dev))) return -ENODEV; if (dev && !net_eq(net, dev_net(dev))) @@ -902,6 +902,7 @@ out_pernet: static __exit void can_exit(void) { /* protocol unregister */ + dev_remove_pack(&canxl_packet); dev_remove_pack(&canfd_packet); dev_remove_pack(&can_packet); sock_unregister(PF_CAN); diff --git a/net/can/isotp.c b/net/can/isotp.c index a9d1357f8489..608f8c24ae46 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -111,6 +111,9 @@ MODULE_ALIAS("can-proto-6"); #define ISOTP_FC_WT 1 /* wait */ #define ISOTP_FC_OVFLW 2 /* overflow */ +#define ISOTP_FC_TIMEOUT 1 /* 1 sec */ +#define ISOTP_ECHO_TIMEOUT 2 /* 2 secs */ + enum { ISOTP_IDLE = 0, ISOTP_WAIT_FIRST_FC, @@ -258,7 +261,8 @@ static int isotp_send_fc(struct sock *sk, int ae, u8 flowstatus) so->lastrxcf_tstamp = ktime_set(0, 0); /* start rx timeout watchdog */ - hrtimer_start(&so->rxtimer, ktime_set(1, 0), HRTIMER_MODE_REL_SOFT); + hrtimer_start(&so->rxtimer, ktime_set(ISOTP_FC_TIMEOUT, 0), + HRTIMER_MODE_REL_SOFT); return 0; } @@ -344,6 +348,8 @@ static int check_pad(struct isotp_sock *so, struct canfd_frame *cf, return 0; } +static void isotp_send_cframe(struct isotp_sock *so); + static int isotp_rcv_fc(struct isotp_sock *so, struct canfd_frame *cf, int ae) { struct sock *sk = &so->sk; @@ -398,14 +404,15 @@ static int isotp_rcv_fc(struct isotp_sock *so, struct canfd_frame *cf, int ae) case ISOTP_FC_CTS: so->tx.bs = 0; so->tx.state = ISOTP_SENDING; - /* start cyclic timer for sending CF frame */ - hrtimer_start(&so->txtimer, so->tx_gap, + /* send CF frame and enable echo timeout handling */ + hrtimer_start(&so->txtimer, ktime_set(ISOTP_ECHO_TIMEOUT, 0), HRTIMER_MODE_REL_SOFT); + isotp_send_cframe(so); break; case ISOTP_FC_WT: /* start timer to wait for next FC frame */ - hrtimer_start(&so->txtimer, ktime_set(1, 0), + hrtimer_start(&so->txtimer, ktime_set(ISOTP_FC_TIMEOUT, 0), HRTIMER_MODE_REL_SOFT); break; @@ -600,7 +607,7 @@ static int isotp_rcv_cf(struct sock *sk, struct canfd_frame *cf, int ae, /* perform blocksize handling, if enabled */ if (!so->rxfc.bs || ++so->rx.bs < so->rxfc.bs) { /* start rx timeout watchdog */ - hrtimer_start(&so->rxtimer, ktime_set(1, 0), + hrtimer_start(&so->rxtimer, ktime_set(ISOTP_FC_TIMEOUT, 0), HRTIMER_MODE_REL_SOFT); return 0; } @@ -829,7 +836,7 @@ static void isotp_rcv_echo(struct sk_buff *skb, void *data) struct isotp_sock *so = isotp_sk(sk); struct canfd_frame *cf = (struct canfd_frame *)skb->data; - /* only handle my own local echo skb's */ + /* only handle my own local echo CF/SF skb's (no FF!) */ if (skb->sk != sk || so->cfecho != *(u32 *)cf->data) return; @@ -849,13 +856,16 @@ static void isotp_rcv_echo(struct sk_buff *skb, void *data) if (so->txfc.bs && so->tx.bs >= so->txfc.bs) { /* stop and wait for FC with timeout */ so->tx.state = ISOTP_WAIT_FC; - hrtimer_start(&so->txtimer, ktime_set(1, 0), + hrtimer_start(&so->txtimer, ktime_set(ISOTP_FC_TIMEOUT, 0), HRTIMER_MODE_REL_SOFT); return; } /* no gap between data frames needed => use burst mode */ if (!so->tx_gap) { + /* enable echo timeout handling */ + hrtimer_start(&so->txtimer, ktime_set(ISOTP_ECHO_TIMEOUT, 0), + HRTIMER_MODE_REL_SOFT); isotp_send_cframe(so); return; } @@ -879,7 +889,7 @@ static enum hrtimer_restart isotp_tx_timer_handler(struct hrtimer *hrtimer) /* start timeout for unlikely lost echo skb */ hrtimer_set_expires(&so->txtimer, ktime_add(ktime_get(), - ktime_set(2, 0))); + ktime_set(ISOTP_ECHO_TIMEOUT, 0))); restart = HRTIMER_RESTART; /* push out the next consecutive frame */ @@ -907,7 +917,8 @@ static enum hrtimer_restart isotp_tx_timer_handler(struct hrtimer *hrtimer) break; default: - WARN_ON_ONCE(1); + WARN_ONCE(1, "can-isotp: tx timer state %08X cfecho %08X\n", + so->tx.state, so->cfecho); } return restart; @@ -923,7 +934,7 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) struct canfd_frame *cf; int ae = (so->opt.flags & CAN_ISOTP_EXTEND_ADDR) ? 1 : 0; int wait_tx_done = (so->opt.flags & CAN_ISOTP_WAIT_TX_DONE) ? 1 : 0; - s64 hrtimer_sec = 0; + s64 hrtimer_sec = ISOTP_ECHO_TIMEOUT; int off; int err; @@ -942,6 +953,8 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) err = wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE); if (err) goto err_out; + + so->tx.state = ISOTP_SENDING; } if (!size || size > MAX_MSG_LENGTH) { @@ -986,6 +999,10 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) cf = (struct canfd_frame *)skb->data; skb_put_zero(skb, so->ll.mtu); + /* cfecho should have been zero'ed by init / former isotp_rcv_echo() */ + if (so->cfecho) + pr_notice_once("can-isotp: uninit cfecho %08X\n", so->cfecho); + /* check for single frame transmission depending on TX_DL */ if (size <= so->tx.ll_dl - SF_PCI_SZ4 - ae - off) { /* The message size generally fits into a SingleFrame - good. @@ -1011,11 +1028,8 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) else cf->data[ae] |= size; - so->tx.state = ISOTP_IDLE; - wake_up_interruptible(&so->wait); - - /* don't enable wait queue for a single frame transmission */ - wait_tx_done = 0; + /* set CF echo tag for isotp_rcv_echo() (SF-mode) */ + so->cfecho = *(u32 *)cf->data; } else { /* send first frame */ @@ -1031,31 +1045,23 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) /* disable wait for FCs due to activated block size */ so->txfc.bs = 0; - /* cfecho should have been zero'ed by init */ - if (so->cfecho) - pr_notice_once("can-isotp: no fc cfecho %08X\n", - so->cfecho); - - /* set consecutive frame echo tag */ + /* set CF echo tag for isotp_rcv_echo() (CF-mode) */ so->cfecho = *(u32 *)cf->data; - - /* switch directly to ISOTP_SENDING state */ - so->tx.state = ISOTP_SENDING; - - /* start timeout for unlikely lost echo skb */ - hrtimer_sec = 2; } else { /* standard flow control check */ so->tx.state = ISOTP_WAIT_FIRST_FC; /* start timeout for FC */ - hrtimer_sec = 1; - } + hrtimer_sec = ISOTP_FC_TIMEOUT; - hrtimer_start(&so->txtimer, ktime_set(hrtimer_sec, 0), - HRTIMER_MODE_REL_SOFT); + /* no CF echo tag for isotp_rcv_echo() (FF-mode) */ + so->cfecho = 0; + } } + hrtimer_start(&so->txtimer, ktime_set(hrtimer_sec, 0), + HRTIMER_MODE_REL_SOFT); + /* send the first or only CAN frame */ cf->flags = so->ll.tx_flags; @@ -1068,8 +1074,7 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) __func__, ERR_PTR(err)); /* no transmission -> no timeout monitoring */ - if (hrtimer_sec) - hrtimer_cancel(&so->txtimer); + hrtimer_cancel(&so->txtimer); /* reset consecutive frame echo tag */ so->cfecho = 0; diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c index 144c86b0e3ff..821d4ff303b3 100644 --- a/net/can/j1939/main.c +++ b/net/can/j1939/main.c @@ -336,6 +336,9 @@ int j1939_send_one(struct j1939_priv *priv, struct sk_buff *skb) /* re-claim the CAN_HDR from the SKB */ cf = skb_push(skb, J1939_CAN_HDR); + /* initialize header structure */ + memset(cf, 0, J1939_CAN_HDR); + /* make it a full can frame again */ skb_put(skb, J1939_CAN_FTR + (8 - dlc)); diff --git a/net/core/dev.c b/net/core/dev.c index 2e4f1c97b59e..117e830cabb0 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1163,22 +1163,6 @@ int dev_change_name(struct net_device *dev, const char *newname) net = dev_net(dev); - /* Some auto-enslaved devices e.g. failover slaves are - * special, as userspace might rename the device after - * the interface had been brought up and running since - * the point kernel initiated auto-enslavement. Allow - * live name change even when these slave devices are - * up and running. - * - * Typically, users of these auto-enslaving devices - * don't actually care about slave name change, as - * they are supposed to operate on master interface - * directly. - */ - if (dev->flags & IFF_UP && - likely(!(dev->priv_flags & IFF_LIVE_RENAME_OK))) - return -EBUSY; - down_write(&devnet_rename_sem); if (strncmp(newname, dev->name, IFNAMSIZ) == 0) { @@ -1195,7 +1179,8 @@ int dev_change_name(struct net_device *dev, const char *newname) } if (oldname[0] && !strchr(oldname, '%')) - netdev_info(dev, "renamed from %s\n", oldname); + netdev_info(dev, "renamed from %s%s\n", oldname, + dev->flags & IFF_UP ? " (while UP)" : ""); old_assign_type = dev->name_assign_type; dev->name_assign_type = NET_NAME_RENAMED; @@ -1621,10 +1606,10 @@ const char *netdev_cmd_to_name(enum netdev_cmd cmd) N(UP) N(DOWN) N(REBOOT) N(CHANGE) N(REGISTER) N(UNREGISTER) N(CHANGEMTU) N(CHANGEADDR) N(GOING_DOWN) N(CHANGENAME) N(FEAT_CHANGE) N(BONDING_FAILOVER) N(PRE_UP) N(PRE_TYPE_CHANGE) N(POST_TYPE_CHANGE) - N(POST_INIT) N(RELEASE) N(NOTIFY_PEERS) N(JOIN) N(CHANGEUPPER) - N(RESEND_IGMP) N(PRECHANGEMTU) N(CHANGEINFODATA) N(BONDING_INFO) - N(PRECHANGEUPPER) N(CHANGELOWERSTATE) N(UDP_TUNNEL_PUSH_INFO) - N(UDP_TUNNEL_DROP_INFO) N(CHANGE_TX_QUEUE_LEN) + N(POST_INIT) N(PRE_UNINIT) N(RELEASE) N(NOTIFY_PEERS) N(JOIN) + N(CHANGEUPPER) N(RESEND_IGMP) N(PRECHANGEMTU) N(CHANGEINFODATA) + N(BONDING_INFO) N(PRECHANGEUPPER) N(CHANGELOWERSTATE) + N(UDP_TUNNEL_PUSH_INFO) N(UDP_TUNNEL_DROP_INFO) N(CHANGE_TX_QUEUE_LEN) N(CVLAN_FILTER_PUSH_INFO) N(CVLAN_FILTER_DROP_INFO) N(SVLAN_FILTER_PUSH_INFO) N(SVLAN_FILTER_DROP_INFO) N(PRE_CHANGEADDR) N(OFFLOAD_XSTATS_ENABLE) N(OFFLOAD_XSTATS_DISABLE) @@ -1876,6 +1861,22 @@ int unregister_netdevice_notifier_net(struct net *net, } EXPORT_SYMBOL(unregister_netdevice_notifier_net); +static void __move_netdevice_notifier_net(struct net *src_net, + struct net *dst_net, + struct notifier_block *nb) +{ + __unregister_netdevice_notifier_net(src_net, nb); + __register_netdevice_notifier_net(dst_net, nb, true); +} + +void move_netdevice_notifier_net(struct net *src_net, struct net *dst_net, + struct notifier_block *nb) +{ + rtnl_lock(); + __move_netdevice_notifier_net(src_net, dst_net, nb); + rtnl_unlock(); +} + int register_netdevice_notifier_dev_net(struct net_device *dev, struct notifier_block *nb, struct netdev_net_notifier *nn) @@ -1912,10 +1913,8 @@ static void move_netdevice_notifiers_dev_net(struct net_device *dev, { struct netdev_net_notifier *nn; - list_for_each_entry(nn, &dev->net_notifier_list, list) { - __unregister_netdevice_notifier_net(dev_net(dev), nn->nb); - __register_netdevice_notifier_net(net, nn->nb, true); - } + list_for_each_entry(nn, &dev->net_notifier_list, list) + __move_netdevice_notifier_net(dev_net(dev), net, nn->nb); } /** @@ -10060,7 +10059,7 @@ int register_netdevice(struct net_device *dev) dev->reg_state = ret ? NETREG_UNREGISTERED : NETREG_REGISTERED; write_unlock(&dev_base_lock); if (ret) - goto err_uninit; + goto err_uninit_notify; __netdev_update_features(dev); @@ -10107,6 +10106,8 @@ int register_netdevice(struct net_device *dev) out: return ret; +err_uninit_notify: + call_netdevice_notifiers(NETDEV_PRE_UNINIT, dev); err_uninit: if (dev->netdev_ops->ndo_uninit) dev->netdev_ops->ndo_uninit(dev); @@ -10856,6 +10857,8 @@ void unregister_netdevice_many_notify(struct list_head *head, netdev_name_node_alt_flush(dev); netdev_name_node_free(dev->name_node); + call_netdevice_notifiers(NETDEV_PRE_UNINIT, dev); + if (dev->netdev_ops->ndo_uninit) dev->netdev_ops->ndo_uninit(dev); diff --git a/net/core/devlink.c b/net/core/devlink.c index 0a16ad45520e..7f789bbcbbd7 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -71,6 +71,7 @@ struct devlink { refcount_t refcount; struct completion comp; struct rcu_head rcu; + struct notifier_block netdevice_nb; char priv[] __aligned(NETDEV_ALIGN); }; @@ -769,7 +770,7 @@ devlink_region_snapshot_get_by_id(struct devlink_region *region, u32 id) #define DEVLINK_NL_FLAG_NEED_RATE_NODE BIT(3) #define DEVLINK_NL_FLAG_NEED_LINECARD BIT(4) -static int devlink_nl_pre_doit(const struct genl_ops *ops, +static int devlink_nl_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info) { struct devlink_linecard *linecard; @@ -827,7 +828,7 @@ unlock: return err; } -static void devlink_nl_post_doit(const struct genl_ops *ops, +static void devlink_nl_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info) { struct devlink_linecard *linecard; @@ -879,6 +880,24 @@ nla_put_failure: return -EMSGSIZE; } +int devlink_nl_port_handle_fill(struct sk_buff *msg, struct devlink_port *devlink_port) +{ + if (devlink_nl_put_handle(msg, devlink_port->devlink)) + return -EMSGSIZE; + if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index)) + return -EMSGSIZE; + return 0; +} + +size_t devlink_nl_port_handle_size(struct devlink_port *devlink_port) +{ + struct devlink *devlink = devlink_port->devlink; + + return nla_total_size(strlen(devlink->dev->bus->name) + 1) /* DEVLINK_ATTR_BUS_NAME */ + + nla_total_size(strlen(dev_name(devlink->dev)) + 1) /* DEVLINK_ATTR_DEV_NAME */ + + nla_total_size(4); /* DEVLINK_ATTR_PORT_INDEX */ +} + struct devlink_reload_combination { enum devlink_reload_action action; enum devlink_reload_limit limit; @@ -1292,8 +1311,6 @@ static int devlink_nl_port_fill(struct sk_buff *msg, if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index)) goto nla_put_failure; - /* Hold rtnl lock while accessing port's netdev attributes. */ - rtnl_lock(); spin_lock_bh(&devlink_port->type_lock); if (nla_put_u16(msg, DEVLINK_ATTR_PORT_TYPE, devlink_port->type)) goto nla_put_failure_type_locked; @@ -1302,18 +1319,15 @@ static int devlink_nl_port_fill(struct sk_buff *msg, devlink_port->desired_type)) goto nla_put_failure_type_locked; if (devlink_port->type == DEVLINK_PORT_TYPE_ETH) { - struct net *net = devlink_net(devlink_port->devlink); - struct net_device *netdev = devlink_port->type_dev; - - if (netdev && net_eq(net, dev_net(netdev)) && + if (devlink_port->type_eth.netdev && (nla_put_u32(msg, DEVLINK_ATTR_PORT_NETDEV_IFINDEX, - netdev->ifindex) || + devlink_port->type_eth.ifindex) || nla_put_string(msg, DEVLINK_ATTR_PORT_NETDEV_NAME, - netdev->name))) + devlink_port->type_eth.ifname))) goto nla_put_failure_type_locked; } if (devlink_port->type == DEVLINK_PORT_TYPE_IB) { - struct ib_device *ibdev = devlink_port->type_dev; + struct ib_device *ibdev = devlink_port->type_ib.ibdev; if (ibdev && nla_put_string(msg, DEVLINK_ATTR_PORT_IBDEV_NAME, @@ -1321,7 +1335,6 @@ static int devlink_nl_port_fill(struct sk_buff *msg, goto nla_put_failure_type_locked; } spin_unlock_bh(&devlink_port->type_lock); - rtnl_unlock(); if (devlink_nl_port_attrs_put(msg, devlink_port)) goto nla_put_failure; if (devlink_nl_port_function_attrs_put(msg, devlink_port, extack)) @@ -1336,7 +1349,6 @@ static int devlink_nl_port_fill(struct sk_buff *msg, nla_put_failure_type_locked: spin_unlock_bh(&devlink_port->type_lock); - rtnl_unlock(); nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; @@ -4490,8 +4502,11 @@ static int devlink_reload(struct devlink *devlink, struct net *dest_net, if (err) return err; - if (dest_net && !net_eq(dest_net, curr_net)) + if (dest_net && !net_eq(dest_net, curr_net)) { + move_netdevice_notifier_net(curr_net, dest_net, + &devlink->netdevice_nb); write_pnet(&devlink->_net, dest_net); + } err = devlink->ops->reload_up(devlink, action, limit, actions_performed, extack); devlink_reload_failed_set(devlink, !!err); @@ -9602,6 +9617,9 @@ void devlink_set_features(struct devlink *devlink, u64 features) } EXPORT_SYMBOL_GPL(devlink_set_features); +static int devlink_netdevice_event(struct notifier_block *nb, + unsigned long event, void *ptr); + /** * devlink_alloc_ns - Allocate new devlink instance resources * in specific namespace @@ -9632,10 +9650,13 @@ struct devlink *devlink_alloc_ns(const struct devlink_ops *ops, ret = xa_alloc_cyclic(&devlinks, &devlink->index, devlink, xa_limit_31b, &last_id, GFP_KERNEL); - if (ret < 0) { - kfree(devlink); - return NULL; - } + if (ret < 0) + goto err_xa_alloc; + + devlink->netdevice_nb.notifier_call = devlink_netdevice_event; + ret = register_netdevice_notifier_net(net, &devlink->netdevice_nb); + if (ret) + goto err_register_netdevice_notifier; devlink->dev = dev; devlink->ops = ops; @@ -9662,6 +9683,12 @@ struct devlink *devlink_alloc_ns(const struct devlink_ops *ops, init_completion(&devlink->comp); return devlink; + +err_register_netdevice_notifier: + xa_erase(&devlinks, devlink->index); +err_xa_alloc: + kfree(devlink); + return NULL; } EXPORT_SYMBOL_GPL(devlink_alloc_ns); @@ -9815,6 +9842,10 @@ void devlink_free(struct devlink *devlink) WARN_ON(!list_empty(&devlink->port_list)); xa_destroy(&devlink->snapshot_ids); + + unregister_netdevice_notifier_net(devlink_net(devlink), + &devlink->netdevice_nb); + xa_erase(&devlinks, devlink->index); kfree(devlink); @@ -9967,6 +9998,7 @@ EXPORT_SYMBOL_GPL(devlink_port_register); void devl_port_unregister(struct devlink_port *devlink_port) { lockdep_assert_held(&devlink_port->devlink->lock); + WARN_ON(devlink_port->type != DEVLINK_PORT_TYPE_NOTSET); devlink_port_type_warn_cancel(devlink_port); devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_DEL); @@ -9994,20 +10026,6 @@ void devlink_port_unregister(struct devlink_port *devlink_port) } EXPORT_SYMBOL_GPL(devlink_port_unregister); -static void __devlink_port_type_set(struct devlink_port *devlink_port, - enum devlink_port_type type, - void *type_dev) -{ - ASSERT_DEVLINK_PORT_REGISTERED(devlink_port); - - devlink_port_type_warn_cancel(devlink_port); - spin_lock_bh(&devlink_port->type_lock); - devlink_port->type = type; - devlink_port->type_dev = type_dev; - spin_unlock_bh(&devlink_port->type_lock); - devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); -} - static void devlink_port_type_netdev_checks(struct devlink_port *devlink_port, struct net_device *netdev) { @@ -10045,23 +10063,58 @@ static void devlink_port_type_netdev_checks(struct devlink_port *devlink_port, } } +static void __devlink_port_type_set(struct devlink_port *devlink_port, + enum devlink_port_type type, + void *type_dev) +{ + struct net_device *netdev = type_dev; + + ASSERT_DEVLINK_PORT_REGISTERED(devlink_port); + + if (type == DEVLINK_PORT_TYPE_NOTSET) { + devlink_port_type_warn_schedule(devlink_port); + } else { + devlink_port_type_warn_cancel(devlink_port); + if (type == DEVLINK_PORT_TYPE_ETH && netdev) + devlink_port_type_netdev_checks(devlink_port, netdev); + } + + spin_lock_bh(&devlink_port->type_lock); + devlink_port->type = type; + switch (type) { + case DEVLINK_PORT_TYPE_ETH: + devlink_port->type_eth.netdev = netdev; + if (netdev) { + ASSERT_RTNL(); + devlink_port->type_eth.ifindex = netdev->ifindex; + BUILD_BUG_ON(sizeof(devlink_port->type_eth.ifname) != + sizeof(netdev->name)); + strcpy(devlink_port->type_eth.ifname, netdev->name); + } + break; + case DEVLINK_PORT_TYPE_IB: + devlink_port->type_ib.ibdev = type_dev; + break; + default: + break; + } + spin_unlock_bh(&devlink_port->type_lock); + devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); +} + /** * devlink_port_type_eth_set - Set port type to Ethernet * * @devlink_port: devlink port - * @netdev: related netdevice + * + * If driver is calling this, most likely it is doing something wrong. */ -void devlink_port_type_eth_set(struct devlink_port *devlink_port, - struct net_device *netdev) +void devlink_port_type_eth_set(struct devlink_port *devlink_port) { - if (netdev) - devlink_port_type_netdev_checks(devlink_port, netdev); - else - dev_warn(devlink_port->devlink->dev, - "devlink port type for port %d set to Ethernet without a software interface reference, device type not supported by the kernel?\n", - devlink_port->index); - - __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_ETH, netdev); + dev_warn(devlink_port->devlink->dev, + "devlink port type for port %d set to Ethernet without a software interface reference, device type not supported by the kernel?\n", + devlink_port->index); + __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_ETH, NULL); } EXPORT_SYMBOL_GPL(devlink_port_type_eth_set); @@ -10082,14 +10135,71 @@ EXPORT_SYMBOL_GPL(devlink_port_type_ib_set); * devlink_port_type_clear - Clear port type * * @devlink_port: devlink port + * + * If driver is calling this for clearing Ethernet type, most likely + * it is doing something wrong. */ void devlink_port_type_clear(struct devlink_port *devlink_port) { + if (devlink_port->type == DEVLINK_PORT_TYPE_ETH) + dev_warn(devlink_port->devlink->dev, + "devlink port type for port %d cleared without a software interface reference, device type not supported by the kernel?\n", + devlink_port->index); __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_NOTSET, NULL); - devlink_port_type_warn_schedule(devlink_port); } EXPORT_SYMBOL_GPL(devlink_port_type_clear); +static int devlink_netdevice_event(struct notifier_block *nb, + unsigned long event, void *ptr) +{ + struct net_device *netdev = netdev_notifier_info_to_dev(ptr); + struct devlink_port *devlink_port = netdev->devlink_port; + struct devlink *devlink; + + devlink = container_of(nb, struct devlink, netdevice_nb); + + if (!devlink_port || devlink_port->devlink != devlink) + return NOTIFY_OK; + + switch (event) { + case NETDEV_POST_INIT: + /* Set the type but not netdev pointer. It is going to be set + * later on by NETDEV_REGISTER event. Happens once during + * netdevice register + */ + __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_ETH, + NULL); + break; + case NETDEV_REGISTER: + case NETDEV_CHANGENAME: + /* Set the netdev on top of previously set type. Note this + * event happens also during net namespace change so here + * we take into account netdev pointer appearing in this + * namespace. + */ + __devlink_port_type_set(devlink_port, devlink_port->type, + netdev); + break; + case NETDEV_UNREGISTER: + /* Clear netdev pointer, but not the type. This event happens + * also during net namespace change so we need to clear + * pointer to netdev that is going to another net namespace. + */ + __devlink_port_type_set(devlink_port, devlink_port->type, + NULL); + break; + case NETDEV_PRE_UNINIT: + /* Clear the type and the netdev pointer. Happens one during + * netdevice unregister. + */ + __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_NOTSET, + NULL); + break; + } + + return NOTIFY_OK; +} + static int __devlink_port_attrs_set(struct devlink_port *devlink_port, enum devlink_port_flavour flavour) { @@ -11624,6 +11734,8 @@ static const struct devlink_trap devlink_trap_generic[] = { DEVLINK_TRAP(ESP_PARSING, DROP), DEVLINK_TRAP(BLACKHOLE_NEXTHOP, DROP), DEVLINK_TRAP(DMAC_FILTER, DROP), + DEVLINK_TRAP(EAPOL, CONTROL), + DEVLINK_TRAP(LOCKED_PORT, DROP), }; #define DEVLINK_TRAP_GROUP(_id) \ @@ -11659,6 +11771,7 @@ static const struct devlink_trap_group devlink_trap_group_generic[] = { DEVLINK_TRAP_GROUP(ACL_SAMPLE), DEVLINK_TRAP_GROUP(ACL_TRAP), DEVLINK_TRAP_GROUP(PARSER_ERROR_DROPS), + DEVLINK_TRAP_GROUP(EAPOL), }; static int devlink_trap_generic_verify(const struct devlink_trap *trap) @@ -12016,7 +12129,7 @@ devlink_trap_report_metadata_set(struct devlink_trap_metadata *metadata, spin_lock(&in_devlink_port->type_lock); if (in_devlink_port->type == DEVLINK_PORT_TYPE_ETH) - metadata->input_dev = in_devlink_port->type_dev; + metadata->input_dev = in_devlink_port->type_eth.netdev; spin_unlock(&in_devlink_port->type_lock); } @@ -12416,14 +12529,6 @@ free_msg: nlmsg_free(msg); } -static struct devlink_port *netdev_to_devlink_port(struct net_device *dev) -{ - if (!dev->netdev_ops->ndo_get_devlink_port) - return NULL; - - return dev->netdev_ops->ndo_get_devlink_port(dev); -} - void devlink_compat_running_version(struct devlink *devlink, char *buf, size_t len) { @@ -12469,7 +12574,7 @@ int devlink_compat_phys_port_name_get(struct net_device *dev, */ ASSERT_RTNL(); - devlink_port = netdev_to_devlink_port(dev); + devlink_port = dev->devlink_port; if (!devlink_port) return -EOPNOTSUPP; @@ -12485,7 +12590,7 @@ int devlink_compat_switch_id_get(struct net_device *dev, * devlink_port instance cannot disappear in the middle. No need to take * any devlink lock as only permanent values are accessed. */ - devlink_port = netdev_to_devlink_port(dev); + devlink_port = dev->devlink_port; if (!devlink_port || !devlink_port->switch_port) return -EOPNOTSUPP; diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 11aa6e8a3098..5a782d1d8fd3 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -1620,7 +1620,7 @@ static const struct genl_small_ops dropmon_ops[] = { }, }; -static int net_dm_nl_pre_doit(const struct genl_ops *ops, +static int net_dm_nl_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info) { mutex_lock(&net_dm_mutex); @@ -1628,7 +1628,7 @@ static int net_dm_nl_pre_doit(const struct genl_ops *ops, return 0; } -static void net_dm_nl_post_doit(const struct genl_ops *ops, +static void net_dm_nl_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info) { mutex_unlock(&net_dm_mutex); diff --git a/net/core/failover.c b/net/core/failover.c index 864d2d83eff4..655411c4ca51 100644 --- a/net/core/failover.c +++ b/net/core/failover.c @@ -80,14 +80,14 @@ static int failover_slave_register(struct net_device *slave_dev) goto err_upper_link; } - slave_dev->priv_flags |= (IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK); + slave_dev->priv_flags |= IFF_FAILOVER_SLAVE; if (fops && fops->slave_register && !fops->slave_register(slave_dev, failover_dev)) return NOTIFY_OK; netdev_upper_dev_unlink(slave_dev, failover_dev); - slave_dev->priv_flags &= ~(IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK); + slave_dev->priv_flags &= ~IFF_FAILOVER_SLAVE; err_upper_link: netdev_rx_handler_unregister(slave_dev); done: @@ -121,7 +121,7 @@ int failover_slave_unregister(struct net_device *slave_dev) netdev_rx_handler_unregister(slave_dev); netdev_upper_dev_unlink(slave_dev, failover_dev); - slave_dev->priv_flags &= ~(IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK); + slave_dev->priv_flags &= ~IFF_FAILOVER_SLAVE; if (fops && fops->slave_unregister && !fops->slave_unregister(slave_dev, failover_dev)) diff --git a/net/core/filter.c b/net/core/filter.c index cd667cdbdb26..6dd2baf5eeb2 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -325,11 +325,11 @@ static u32 convert_skb_access(int skb_field, int dst_reg, int src_reg, offsetof(struct sk_buff, vlan_tci)); break; case SKF_AD_VLAN_TAG_PRESENT: - *insn++ = BPF_LDX_MEM(BPF_B, dst_reg, src_reg, PKT_VLAN_PRESENT_OFFSET); - if (PKT_VLAN_PRESENT_BIT) - *insn++ = BPF_ALU32_IMM(BPF_RSH, dst_reg, PKT_VLAN_PRESENT_BIT); - if (PKT_VLAN_PRESENT_BIT < 7) - *insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg, 1); + BUILD_BUG_ON(sizeof_field(struct sk_buff, vlan_all) != 4); + *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, + offsetof(struct sk_buff, vlan_all)); + *insn++ = BPF_JMP_IMM(BPF_JEQ, dst_reg, 0, 1); + *insn++ = BPF_ALU32_IMM(BPF_MOV, dst_reg, 1); break; } @@ -9298,13 +9298,11 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct __sk_buff, vlan_present): - *target_size = 1; - *insn++ = BPF_LDX_MEM(BPF_B, si->dst_reg, si->src_reg, - PKT_VLAN_PRESENT_OFFSET); - if (PKT_VLAN_PRESENT_BIT) - *insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, PKT_VLAN_PRESENT_BIT); - if (PKT_VLAN_PRESENT_BIT < 7) - *insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, 1); + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, + bpf_target_off(struct sk_buff, + vlan_all, 4, target_size)); + *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); + *insn++ = BPF_ALU32_IMM(BPF_MOV, si->dst_reg, 1); break; case offsetof(struct __sk_buff, vlan_tci): diff --git a/net/core/gro.c b/net/core/gro.c index bc9451743307..fd8c6a7e8d3e 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -370,9 +370,7 @@ static void gro_list_prepare(const struct list_head *head, } diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev; - diffs |= skb_vlan_tag_present(p) ^ skb_vlan_tag_present(skb); - if (skb_vlan_tag_present(p)) - diffs |= skb_vlan_tag_get(p) ^ skb_vlan_tag_get(skb); + diffs |= p->vlan_all ^ skb->vlan_all; diffs |= skb_metadata_differs(p, skb); if (maclen == ETH_HLEN) diffs |= compare_ether_header(skb_mac_header(p), @@ -489,45 +487,45 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff rcu_read_lock(); list_for_each_entry_rcu(ptype, head, list) { - if (ptype->type != type || !ptype->callbacks.gro_receive) - continue; - - skb_set_network_header(skb, skb_gro_offset(skb)); - skb_reset_mac_len(skb); - BUILD_BUG_ON(sizeof_field(struct napi_gro_cb, zeroed) != sizeof(u32)); - BUILD_BUG_ON(!IS_ALIGNED(offsetof(struct napi_gro_cb, zeroed), - sizeof(u32))); /* Avoid slow unaligned acc */ - *(u32 *)&NAPI_GRO_CB(skb)->zeroed = 0; - NAPI_GRO_CB(skb)->flush = skb_has_frag_list(skb); - NAPI_GRO_CB(skb)->is_atomic = 1; - NAPI_GRO_CB(skb)->count = 1; - if (unlikely(skb_is_gso(skb))) { - NAPI_GRO_CB(skb)->count = skb_shinfo(skb)->gso_segs; - /* Only support TCP at the moment. */ - if (!skb_is_gso_tcp(skb)) - NAPI_GRO_CB(skb)->flush = 1; - } - - /* Setup for GRO checksum validation */ - switch (skb->ip_summed) { - case CHECKSUM_COMPLETE: - NAPI_GRO_CB(skb)->csum = skb->csum; - NAPI_GRO_CB(skb)->csum_valid = 1; - break; - case CHECKSUM_UNNECESSARY: - NAPI_GRO_CB(skb)->csum_cnt = skb->csum_level + 1; - break; - } + if (ptype->type == type && ptype->callbacks.gro_receive) + goto found_ptype; + } + rcu_read_unlock(); + goto normal; + +found_ptype: + skb_set_network_header(skb, skb_gro_offset(skb)); + skb_reset_mac_len(skb); + BUILD_BUG_ON(sizeof_field(struct napi_gro_cb, zeroed) != sizeof(u32)); + BUILD_BUG_ON(!IS_ALIGNED(offsetof(struct napi_gro_cb, zeroed), + sizeof(u32))); /* Avoid slow unaligned acc */ + *(u32 *)&NAPI_GRO_CB(skb)->zeroed = 0; + NAPI_GRO_CB(skb)->flush = skb_has_frag_list(skb); + NAPI_GRO_CB(skb)->is_atomic = 1; + NAPI_GRO_CB(skb)->count = 1; + if (unlikely(skb_is_gso(skb))) { + NAPI_GRO_CB(skb)->count = skb_shinfo(skb)->gso_segs; + /* Only support TCP at the moment. */ + if (!skb_is_gso_tcp(skb)) + NAPI_GRO_CB(skb)->flush = 1; + } - pp = INDIRECT_CALL_INET(ptype->callbacks.gro_receive, - ipv6_gro_receive, inet_gro_receive, - &gro_list->list, skb); + /* Setup for GRO checksum validation */ + switch (skb->ip_summed) { + case CHECKSUM_COMPLETE: + NAPI_GRO_CB(skb)->csum = skb->csum; + NAPI_GRO_CB(skb)->csum_valid = 1; + break; + case CHECKSUM_UNNECESSARY: + NAPI_GRO_CB(skb)->csum_cnt = skb->csum_level + 1; break; } - rcu_read_unlock(); - if (&ptype->list == head) - goto normal; + pp = INDIRECT_CALL_INET(ptype->callbacks.gro_receive, + ipv6_gro_receive, inet_gro_receive, + &gro_list->list, skb); + + rcu_read_unlock(); if (PTR_ERR(pp) == -EINPROGRESS) { ret = GRO_CONSUMED; diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 8409d41405df..679b84cc8794 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -532,7 +532,7 @@ static ssize_t phys_port_name_show(struct device *dev, * returning early without hitting the trylock/restart below. */ if (!netdev->netdev_ops->ndo_get_phys_port_name && - !netdev->netdev_ops->ndo_get_devlink_port) + !netdev->devlink_port) return -EOPNOTSUPP; if (!rtnl_trylock()) @@ -562,7 +562,7 @@ static ssize_t phys_switch_id_show(struct device *dev, * because recurse is false when calling dev_get_port_parent_id. */ if (!netdev->netdev_ops->ndo_get_port_parent_id && - !netdev->netdev_ops->ndo_get_devlink_port) + !netdev->devlink_port) return -EOPNOTSUPP; if (!rtnl_trylock()) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index d2f27548fc0b..64289bc98887 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -53,6 +53,7 @@ #include <net/fib_rules.h> #include <net/rtnetlink.h> #include <net/net_namespace.h> +#include <net/devlink.h> #include "dev.h" @@ -1038,6 +1039,16 @@ static size_t rtnl_proto_down_size(const struct net_device *dev) return size; } +static size_t rtnl_devlink_port_size(const struct net_device *dev) +{ + size_t size = nla_total_size(0); /* nest IFLA_DEVLINK_PORT */ + + if (dev->devlink_port) + size += devlink_nl_port_handle_size(dev->devlink_port); + + return size; +} + static noinline size_t if_nlmsg_size(const struct net_device *dev, u32 ext_filter_mask) { @@ -1091,6 +1102,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(4) /* IFLA_MAX_MTU */ + rtnl_prop_list_size(dev) + nla_total_size(MAX_ADDR_LEN) /* IFLA_PERM_ADDRESS */ + + rtnl_devlink_port_size(dev) + 0; } @@ -1728,6 +1740,30 @@ nla_put_failure: return -EMSGSIZE; } +static int rtnl_fill_devlink_port(struct sk_buff *skb, + const struct net_device *dev) +{ + struct nlattr *devlink_port_nest; + int ret; + + devlink_port_nest = nla_nest_start(skb, IFLA_DEVLINK_PORT); + if (!devlink_port_nest) + return -EMSGSIZE; + + if (dev->devlink_port) { + ret = devlink_nl_port_handle_fill(skb, dev->devlink_port); + if (ret < 0) + goto nest_cancel; + } + + nla_nest_end(skb, devlink_port_nest); + return 0; + +nest_cancel: + nla_nest_cancel(skb, devlink_port_nest); + return ret; +} + static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, struct net *src_net, int type, u32 pid, u32 seq, u32 change, @@ -1865,6 +1901,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, dev->dev.parent->bus->name)) goto nla_put_failure; + if (rtnl_fill_devlink_port(skb, dev)) + goto nla_put_failure; + nlmsg_end(skb, nlh); return 0; @@ -4051,6 +4090,11 @@ int ndo_dflt_fdb_add(struct ndmsg *ndm, return err; } + if (tb[NDA_FLAGS_EXT]) { + netdev_info(dev, "invalid flags given to default FDB implementation\n"); + return err; + } + if (vid) { netdev_info(dev, "vlans aren't supported yet for dev_uc|mc_add()\n"); return err; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 42a35b59fb1e..90d085290d49 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4147,23 +4147,25 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb, int i = 0; int pos; - if (list_skb && !list_skb->head_frag && skb_headlen(list_skb) && - (skb_shinfo(head_skb)->gso_type & SKB_GSO_DODGY)) { - /* gso_size is untrusted, and we have a frag_list with a linear - * non head_frag head. - * - * (we assume checking the first list_skb member suffices; - * i.e if either of the list_skb members have non head_frag - * head, then the first one has too). - * - * If head_skb's headlen does not fit requested gso_size, it - * means that the frag_list members do NOT terminate on exact - * gso_size boundaries. Hence we cannot perform skb_frag_t page - * sharing. Therefore we must fallback to copying the frag_list - * skbs; we do so by disabling SG. - */ - if (mss != GSO_BY_FRAGS && mss != skb_headlen(head_skb)) - features &= ~NETIF_F_SG; + if ((skb_shinfo(head_skb)->gso_type & SKB_GSO_DODGY) && + mss != GSO_BY_FRAGS && mss != skb_headlen(head_skb)) { + struct sk_buff *check_skb; + + for (check_skb = list_skb; check_skb; check_skb = check_skb->next) { + if (skb_headlen(check_skb) && !check_skb->head_frag) { + /* gso_size is untrusted, and we have a frag_list with + * a linear non head_frag item. + * + * If head_skb's headlen does not fit requested gso_size, + * it means that the frag_list members do NOT terminate + * on exact gso_size boundaries. Hence we cannot perform + * skb_frag_t page sharing. Therefore we must fallback to + * copying the frag_list skbs; we do so by disabling SG. + */ + features &= ~NETIF_F_SG; + break; + } + } } __skb_push(head_skb, doffset); @@ -6435,6 +6437,7 @@ void skb_condense(struct sk_buff *skb) */ skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); } +EXPORT_SYMBOL(skb_condense); #ifdef CONFIG_SKB_EXTENSIONS static void *skb_ext_get_ptr(struct skb_ext *ext, enum skb_ext_id id) diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 1efdc47a999b..e6b9ced3eda8 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -803,16 +803,13 @@ static void sk_psock_link_destroy(struct sk_psock *psock) } } -void sk_psock_stop(struct sk_psock *psock, bool wait) +void sk_psock_stop(struct sk_psock *psock) { spin_lock_bh(&psock->ingress_lock); sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED); sk_psock_cork_free(psock); __sk_psock_zap_ingress(psock); spin_unlock_bh(&psock->ingress_lock); - - if (wait) - cancel_work_sync(&psock->work); } static void sk_psock_done_strp(struct sk_psock *psock); @@ -850,7 +847,7 @@ void sk_psock_drop(struct sock *sk, struct sk_psock *psock) sk_psock_stop_verdict(sk, psock); write_unlock_bh(&sk->sk_callback_lock); - sk_psock_stop(psock, false); + sk_psock_stop(psock); INIT_RCU_WORK(&psock->rwork, sk_psock_destroy); queue_rcu_work(system_wq, &psock->rwork); diff --git a/net/core/sock_map.c b/net/core/sock_map.c index a660baedd9e7..81beb16ab1eb 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -1596,7 +1596,7 @@ void sock_map_destroy(struct sock *sk) saved_destroy = psock->saved_destroy; sock_map_remove_links(sk, psock); rcu_read_unlock(); - sk_psock_stop(psock, false); + sk_psock_stop(psock); sk_psock_put(sk, psock); saved_destroy(sk); } @@ -1619,9 +1619,10 @@ void sock_map_close(struct sock *sk, long timeout) saved_close = psock->saved_close; sock_map_remove_links(sk, psock); rcu_read_unlock(); - sk_psock_stop(psock, true); - sk_psock_put(sk, psock); + sk_psock_stop(psock); release_sock(sk); + cancel_work_sync(&psock->work); + sk_psock_put(sk, psock); saved_close(sk, timeout); } EXPORT_SYMBOL_GPL(sock_map_close); diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index e504a18fc125..b80dbd02e154 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -529,7 +529,6 @@ static void dsa_port_devlink_teardown(struct dsa_port *dp) static int dsa_port_setup(struct dsa_port *dp) { - struct devlink_port *dlp = &dp->devlink_port; bool dsa_port_link_registered = false; struct dsa_switch *ds = dp->ds; bool dsa_port_enabled = false; @@ -585,10 +584,6 @@ static int dsa_port_setup(struct dsa_port *dp) case DSA_PORT_TYPE_USER: of_get_mac_address(dp->dn, dp->mac); err = dsa_slave_create(dp); - if (err) - break; - - devlink_port_type_eth_set(dlp, dp->slave); break; } @@ -608,13 +603,9 @@ static int dsa_port_setup(struct dsa_port *dp) static void dsa_port_teardown(struct dsa_port *dp) { - struct devlink_port *dlp = &dp->devlink_port; - if (!dp->setup) return; - devlink_port_type_clear(dlp); - switch (dp->type) { case DSA_PORT_TYPE_UNUSED: break; diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 83e419afa89e..4176482cd03f 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -2165,13 +2165,6 @@ static const struct dcbnl_rtnl_ops __maybe_unused dsa_slave_dcbnl_ops = { .ieee_delapp = dsa_slave_dcbnl_ieee_delapp, }; -static struct devlink_port *dsa_slave_get_devlink_port(struct net_device *dev) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - - return &dp->devlink_port; -} - static void dsa_slave_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *s) { @@ -2219,7 +2212,6 @@ static const struct net_device_ops dsa_slave_netdev_ops = { .ndo_get_stats64 = dsa_slave_get_stats64, .ndo_vlan_rx_add_vid = dsa_slave_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = dsa_slave_vlan_rx_kill_vid, - .ndo_get_devlink_port = dsa_slave_get_devlink_port, .ndo_change_mtu = dsa_slave_change_mtu, .ndo_fill_forward_path = dsa_slave_fill_forward_path, }; @@ -2406,6 +2398,7 @@ int dsa_slave_create(struct dsa_port *port) SET_NETDEV_DEVTYPE(slave_dev, &dsa_type); SET_NETDEV_DEV(slave_dev, port->ds->dev); + SET_NETDEV_DEVLINK_PORT(slave_dev, &port->devlink_port); slave_dev->dev.of_node = port->dn; slave_dev->vlan_features = master->vlan_features; diff --git a/net/ethtool/channels.c b/net/ethtool/channels.c index 403158862011..c7e37130647e 100644 --- a/net/ethtool/channels.c +++ b/net/ethtool/channels.c @@ -116,9 +116,10 @@ int ethnl_set_channels(struct sk_buff *skb, struct genl_info *info) struct ethtool_channels channels = {}; struct ethnl_req_info req_info = {}; struct nlattr **tb = info->attrs; - u32 err_attr, max_rx_in_use = 0; + u32 err_attr, max_rxfh_in_use; const struct ethtool_ops *ops; struct net_device *dev; + u64 max_rxnfc_in_use; int ret; ret = ethnl_parse_header_dev_get(&req_info, @@ -189,15 +190,23 @@ int ethnl_set_channels(struct sk_buff *skb, struct genl_info *info) } /* ensure the new Rx count fits within the configured Rx flow - * indirection table settings + * indirection table/rxnfc settings */ - if (netif_is_rxfh_configured(dev) && - !ethtool_get_max_rxfh_channel(dev, &max_rx_in_use) && - (channels.combined_count + channels.rx_count) <= max_rx_in_use) { + if (ethtool_get_max_rxnfc_channel(dev, &max_rxnfc_in_use)) + max_rxnfc_in_use = 0; + if (!netif_is_rxfh_configured(dev) || + ethtool_get_max_rxfh_channel(dev, &max_rxfh_in_use)) + max_rxfh_in_use = 0; + if (channels.combined_count + channels.rx_count <= max_rxfh_in_use) { ret = -EINVAL; GENL_SET_ERR_MSG(info, "requested channel counts are too low for existing indirection table settings"); goto out_ops; } + if (channels.combined_count + channels.rx_count <= max_rxnfc_in_use) { + ret = -EINVAL; + GENL_SET_ERR_MSG(info, "requested channel counts are too low for existing ntuple filter settings"); + goto out_ops; + } /* Disabling channels, query zero-copy AF_XDP sockets */ from_channel = channels.combined_count + diff --git a/net/ethtool/common.c b/net/ethtool/common.c index ee3e02da0013..21cfe8557205 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -512,6 +512,72 @@ int __ethtool_get_link(struct net_device *dev) return netif_running(dev) && dev->ethtool_ops->get_link(dev); } +static int ethtool_get_rxnfc_rule_count(struct net_device *dev) +{ + const struct ethtool_ops *ops = dev->ethtool_ops; + struct ethtool_rxnfc info = { + .cmd = ETHTOOL_GRXCLSRLCNT, + }; + int err; + + err = ops->get_rxnfc(dev, &info, NULL); + if (err) + return err; + + return info.rule_cnt; +} + +int ethtool_get_max_rxnfc_channel(struct net_device *dev, u64 *max) +{ + const struct ethtool_ops *ops = dev->ethtool_ops; + struct ethtool_rxnfc *info; + int err, i, rule_cnt; + u64 max_ring = 0; + + if (!ops->get_rxnfc) + return -EOPNOTSUPP; + + rule_cnt = ethtool_get_rxnfc_rule_count(dev); + if (rule_cnt <= 0) + return -EINVAL; + + info = kvzalloc(struct_size(info, rule_locs, rule_cnt), GFP_KERNEL); + if (!info) + return -ENOMEM; + + info->cmd = ETHTOOL_GRXCLSRLALL; + info->rule_cnt = rule_cnt; + err = ops->get_rxnfc(dev, info, info->rule_locs); + if (err) + goto err_free_info; + + for (i = 0; i < rule_cnt; i++) { + struct ethtool_rxnfc rule_info = { + .cmd = ETHTOOL_GRXCLSRULE, + .fs.location = info->rule_locs[i], + }; + + err = ops->get_rxnfc(dev, &rule_info, NULL); + if (err) + goto err_free_info; + + if (rule_info.fs.ring_cookie != RX_CLS_FLOW_DISC && + rule_info.fs.ring_cookie != RX_CLS_FLOW_WAKE && + !(rule_info.flow_type & FLOW_RSS) && + !ethtool_get_flow_spec_ring_vf(rule_info.fs.ring_cookie)) + max_ring = + max_t(u64, max_ring, rule_info.fs.ring_cookie); + } + + kvfree(info); + *max = max_ring; + return 0; + +err_free_info: + kvfree(info); + return err; +} + int ethtool_get_max_rxfh_channel(struct net_device *dev, u32 *max) { u32 dev_size, current_max = 0; diff --git a/net/ethtool/common.h b/net/ethtool/common.h index c1779657e074..b1b9db810eca 100644 --- a/net/ethtool/common.h +++ b/net/ethtool/common.h @@ -43,6 +43,7 @@ bool convert_legacy_settings_to_link_ksettings( struct ethtool_link_ksettings *link_ksettings, const struct ethtool_cmd *legacy_settings); int ethtool_get_max_rxfh_channel(struct net_device *dev, u32 *max); +int ethtool_get_max_rxnfc_channel(struct net_device *dev, u64 *max); int __ethtool_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info); extern const struct ethtool_phy_ops *ethtool_phy_ops; diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 57e7238a4136..99272a67525c 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -44,16 +44,9 @@ struct ethtool_devlink_compat { static struct devlink *netdev_to_devlink_get(struct net_device *dev) { - struct devlink_port *devlink_port; - - if (!dev->netdev_ops->ndo_get_devlink_port) - return NULL; - - devlink_port = dev->netdev_ops->ndo_get_devlink_port(dev); - if (!devlink_port) + if (!dev->devlink_port) return NULL; - - return devlink_try_get(devlink_port->devlink); + return devlink_try_get(dev->devlink_port->devlink); } /* @@ -713,15 +706,22 @@ static int ethtool_get_drvinfo(struct net_device *dev, struct ethtool_devlink_compat *rsp) { const struct ethtool_ops *ops = dev->ethtool_ops; + struct device *parent = dev->dev.parent; rsp->info.cmd = ETHTOOL_GDRVINFO; strscpy(rsp->info.version, UTS_RELEASE, sizeof(rsp->info.version)); if (ops->get_drvinfo) { ops->get_drvinfo(dev, &rsp->info); - } else if (dev->dev.parent && dev->dev.parent->driver) { - strscpy(rsp->info.bus_info, dev_name(dev->dev.parent), + if (!rsp->info.bus_info[0] && parent) + strscpy(rsp->info.bus_info, dev_name(parent), + sizeof(rsp->info.bus_info)); + if (!rsp->info.driver[0] && parent && parent->driver) + strscpy(rsp->info.driver, parent->driver->name, + sizeof(rsp->info.driver)); + } else if (parent && parent->driver) { + strscpy(rsp->info.bus_info, dev_name(parent), sizeof(rsp->info.bus_info)); - strscpy(rsp->info.driver, dev->dev.parent->driver->name, + strscpy(rsp->info.driver, parent->driver->name, sizeof(rsp->info.driver)); } else if (dev->rtnl_link_ops) { strscpy(rsp->info.driver, dev->rtnl_link_ops->kind, @@ -1796,7 +1796,8 @@ static noinline_for_stack int ethtool_set_channels(struct net_device *dev, { struct ethtool_channels channels, curr = { .cmd = ETHTOOL_GCHANNELS }; u16 from_channel, to_channel; - u32 max_rx_in_use = 0; + u64 max_rxnfc_in_use; + u32 max_rxfh_in_use; unsigned int i; int ret; @@ -1827,11 +1828,15 @@ static noinline_for_stack int ethtool_set_channels(struct net_device *dev, return -EINVAL; /* ensure the new Rx count fits within the configured Rx flow - * indirection table settings */ - if (netif_is_rxfh_configured(dev) && - !ethtool_get_max_rxfh_channel(dev, &max_rx_in_use) && - (channels.combined_count + channels.rx_count) <= max_rx_in_use) - return -EINVAL; + * indirection table/rxnfc settings */ + if (ethtool_get_max_rxnfc_channel(dev, &max_rxnfc_in_use)) + max_rxnfc_in_use = 0; + if (!netif_is_rxfh_configured(dev) || + ethtool_get_max_rxfh_channel(dev, &max_rxfh_in_use)) + max_rxfh_in_use = 0; + if (channels.combined_count + channels.rx_count <= + max_t(u64, max_rxnfc_in_use, max_rxfh_in_use)) + return -EINVAL; /* Disabling channels, query zero-copy AF_XDP sockets */ from_channel = channels.combined_count + diff --git a/net/ethtool/linkstate.c b/net/ethtool/linkstate.c index fb676f349455..2158c17a0b32 100644 --- a/net/ethtool/linkstate.c +++ b/net/ethtool/linkstate.c @@ -13,6 +13,7 @@ struct linkstate_reply_data { int link; int sqi; int sqi_max; + struct ethtool_link_ext_stats link_stats; bool link_ext_state_provided; struct ethtool_link_ext_state_info ethtool_link_ext_state_info; }; @@ -22,7 +23,7 @@ struct linkstate_reply_data { const struct nla_policy ethnl_linkstate_get_policy[] = { [ETHTOOL_A_LINKSTATE_HEADER] = - NLA_POLICY_NESTED(ethnl_header_policy), + NLA_POLICY_NESTED(ethnl_header_policy_stats), }; static int linkstate_get_sqi(struct net_device *dev) @@ -107,6 +108,19 @@ static int linkstate_prepare_data(const struct ethnl_req_info *req_base, goto out; } + ethtool_stats_init((u64 *)&data->link_stats, + sizeof(data->link_stats) / 8); + + if (req_base->flags & ETHTOOL_FLAG_STATS) { + if (dev->phydev) + data->link_stats.link_down_events = + READ_ONCE(dev->phydev->link_down_events); + + if (dev->ethtool_ops->get_link_ext_stats) + dev->ethtool_ops->get_link_ext_stats(dev, + &data->link_stats); + } + ret = 0; out: ethnl_ops_complete(dev); @@ -134,6 +148,9 @@ static int linkstate_reply_size(const struct ethnl_req_info *req_base, if (data->ethtool_link_ext_state_info.__link_ext_substate) len += nla_total_size(sizeof(u8)); /* LINKSTATE_EXT_SUBSTATE */ + if (data->link_stats.link_down_events != ETHTOOL_STAT_NOT_SET) + len += nla_total_size(sizeof(u32)); + return len; } @@ -166,6 +183,11 @@ static int linkstate_fill_reply(struct sk_buff *skb, return -EMSGSIZE; } + if (data->link_stats.link_down_events != ETHTOOL_STAT_NOT_SET) + if (nla_put_u32(skb, ETHTOOL_A_LINKSTATE_EXT_DOWN_CNT, + data->link_stats.link_down_events)) + return -EMSGSIZE; + return 0; } diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c index 38c4f3cb010e..b33d1b5eda87 100644 --- a/net/ieee802154/nl802154.c +++ b/net/ieee802154/nl802154.c @@ -2157,7 +2157,8 @@ static int nl802154_del_llsec_seclevel(struct sk_buff *skb, #define NL802154_FLAG_CHECK_NETDEV_UP 0x08 #define NL802154_FLAG_NEED_WPAN_DEV 0x10 -static int nl802154_pre_doit(const struct genl_ops *ops, struct sk_buff *skb, +static int nl802154_pre_doit(const struct genl_split_ops *ops, + struct sk_buff *skb, struct genl_info *info) { struct cfg802154_registered_device *rdev; @@ -2219,7 +2220,8 @@ static int nl802154_pre_doit(const struct genl_ops *ops, struct sk_buff *skb, return 0; } -static void nl802154_post_doit(const struct genl_ops *ops, struct sk_buff *skb, +static void nl802154_post_doit(const struct genl_split_ops *ops, + struct sk_buff *skb, struct genl_info *info) { if (info->user_ptr[1]) { diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 5f16807d3235..9f92ae35bb01 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -433,6 +433,7 @@ void ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err, } kfree_skb(skb); } +EXPORT_SYMBOL_GPL(ip_icmp_error); void ip_local_error(struct sock *sk, int err, __be32 daddr, __be16 port, u32 info) { diff --git a/net/ipv4/metrics.c b/net/ipv4/metrics.c index 25ea6ac44db9..7fcfdfd8f9de 100644 --- a/net/ipv4/metrics.c +++ b/net/ipv4/metrics.c @@ -14,9 +14,6 @@ static int ip_metrics_convert(struct net *net, struct nlattr *fc_mx, struct nlattr *nla; int remaining; - if (!fc_mx) - return 0; - nla_for_each_attr(nla, fc_mx, fc_mx_len, remaining) { int type = nla_type(nla); u32 val; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index de8f0cd7cb32..4a69c5fcfedc 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3648,7 +3648,7 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, case TCP_REPAIR_OPTIONS: if (!tp->repair) err = -EINVAL; - else if (sk->sk_state == TCP_ESTABLISHED) + else if (sk->sk_state == TCP_ESTABLISHED && !tp->bytes_sent) err = tcp_repair_options_est(sk, optval, optlen); else err = -EPERM; diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index c501c329b1db..cf9c3e8f7ccb 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -278,7 +278,7 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock, { bool cork = false, enospc = sk_msg_full(msg); struct sock *sk_redir; - u32 tosend, delta = 0; + u32 tosend, origsize, sent, delta = 0; u32 eval = __SK_NONE; int ret; @@ -333,10 +333,12 @@ more_data: cork = true; psock->cork = NULL; } - sk_msg_return(sk, msg, msg->sg.size); + sk_msg_return(sk, msg, tosend); release_sock(sk); + origsize = msg->sg.size; ret = tcp_bpf_sendmsg_redir(sk_redir, msg, tosend, flags); + sent = origsize - msg->sg.size; if (eval == __SK_REDIRECT) sock_put(sk_redir); @@ -375,7 +377,7 @@ more_data: msg->sg.data[msg->sg.start].page_link && msg->sg.data[msg->sg.start].length) { if (eval == __SK_REDIRECT) - sk_mem_charge(sk, msg->sg.size); + sk_mem_charge(sk, tosend - sent); goto more_data; } } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 89accc3c8bb3..b859d6c8298e 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -784,7 +784,8 @@ int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) if (tunnel) { /* ...not for tunnels though: we don't have a sending socket */ if (udp_sk(sk)->encap_err_rcv) - udp_sk(sk)->encap_err_rcv(sk, skb, iph->ihl << 2); + udp_sk(sk)->encap_err_rcv(sk, skb, err, uh->dest, info, + (u8 *)(uh+1)); goto out; } if (!inet->recverr) { diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index 8a22486cf270..17ac45aa7194 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -437,6 +437,7 @@ static void ip6addrlbl_putmsg(struct nlmsghdr *nlh, { struct ifaddrlblmsg *ifal = nlmsg_data(nlh); ifal->ifal_family = AF_INET6; + ifal->__ifal_reserved = 0; ifal->ifal_prefixlen = prefixlen; ifal->ifal_flags = 0; ifal->ifal_index = ifindex; diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index df7e032ce87d..7c7155b48f17 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -334,6 +334,7 @@ void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, if (sock_queue_err_skb(sk, skb)) kfree_skb(skb); } +EXPORT_SYMBOL_GPL(ipv6_icmp_error); void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info) { diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 10f45658dbf6..e2de3d906c82 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -632,7 +632,8 @@ int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, /* Tunnels don't have an application socket: don't pass errors back */ if (tunnel) { if (udp_sk(sk)->encap_err_rcv) - udp_sk(sk)->encap_err_rcv(sk, skb, offset); + udp_sk(sk)->encap_err_rcv(sk, skb, err, uh->dest, + ntohl(info), (u8 *)(uh+1)); goto out; } @@ -1639,6 +1640,7 @@ do_confirm: err = 0; goto out; } +EXPORT_SYMBOL(udpv6_sendmsg); void udpv6_destroy_sock(struct sock *sk) { diff --git a/net/mac80211/main.c b/net/mac80211/main.c index b7279d88cddb..846528850612 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -1446,8 +1446,10 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) ieee80211_led_exit(local); destroy_workqueue(local->workqueue); fail_workqueue: - if (local->wiphy_ciphers_allocated) + if (local->wiphy_ciphers_allocated) { kfree(local->hw.wiphy->cipher_suites); + local->wiphy_ciphers_allocated = false; + } kfree(local->int_scan_req); return result; } @@ -1515,8 +1517,10 @@ void ieee80211_free_hw(struct ieee80211_hw *hw) mutex_destroy(&local->iflist_mtx); mutex_destroy(&local->mtx); - if (local->wiphy_ciphers_allocated) + if (local->wiphy_ciphers_allocated) { kfree(local->hw.wiphy->cipher_suites); + local->wiphy_ciphers_allocated = false; + } idr_for_each(&local->ack_status_frames, ieee80211_free_ack_frame, NULL); diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index acc1c299f1ae..69d5e1ec6ede 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -710,7 +710,7 @@ int mesh_path_send_to_gates(struct mesh_path *mpath) void mesh_path_discard_frame(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) { - kfree_skb(skb); + ieee80211_free_txskb(&sdata->local->hw, skb); sdata->u.mesh.mshstats.dropped_frames_no_route++; } diff --git a/net/mac80211/s1g.c b/net/mac80211/s1g.c index 8ca7d45d6daa..c1f964e9991c 100644 --- a/net/mac80211/s1g.c +++ b/net/mac80211/s1g.c @@ -112,6 +112,9 @@ ieee80211_s1g_rx_twt_setup(struct ieee80211_sub_if_data *sdata, goto out; } + /* TWT Information not supported yet */ + twt->control |= IEEE80211_TWT_CONTROL_RX_DISABLED; + drv_add_twt_setup(sdata->local, sdata, &sta->sta, twt); out: ieee80211_s1g_send_twt_setup(sdata, mgmt->sa, sdata->vif.addr, twt); diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index bb2e54610101..165ac0711d71 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -4406,6 +4406,11 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, if (likely(!is_multicast_ether_addr(eth->h_dest))) goto normal; + if (unlikely(!ieee80211_sdata_running(sdata))) { + kfree_skb(skb); + return NETDEV_TX_OK; + } + if (unlikely(ieee80211_multicast_to_unicast(skb, dev))) { struct sk_buff_head queue; diff --git a/net/mctp/af_mctp.c b/net/mctp/af_mctp.c index b6b5e496fa40..fc9e728b6333 100644 --- a/net/mctp/af_mctp.c +++ b/net/mctp/af_mctp.c @@ -665,12 +665,14 @@ static __init int mctp_init(void) rc = mctp_neigh_init(); if (rc) - goto err_unreg_proto; + goto err_unreg_routes; mctp_device_init(); return 0; +err_unreg_routes: + mctp_routes_exit(); err_unreg_proto: proto_unregister(&mctp_proto); err_unreg_sock: diff --git a/net/mctp/route.c b/net/mctp/route.c index 2155f15a074c..f9a80b82dc51 100644 --- a/net/mctp/route.c +++ b/net/mctp/route.c @@ -1400,7 +1400,7 @@ int __init mctp_routes_init(void) return register_pernet_subsys(&mctp_net_ops); } -void __exit mctp_routes_exit(void) +void mctp_routes_exit(void) { unregister_pernet_subsys(&mctp_net_ops); rtnl_unregister(PF_MCTP, RTM_DELROUTE); diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index ff737a76052e..48ea6d0264b5 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -26,7 +26,9 @@ #include <net/netfilter/nf_conntrack_extend.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_l4proto.h> +#include <net/netfilter/nf_conntrack_seqadj.h> #include <net/netfilter/nf_log.h> +#include <net/ip.h> static DEFINE_MUTEX(nf_ct_helper_mutex); struct hlist_head *nf_ct_helper_hash __read_mostly; @@ -240,6 +242,104 @@ int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl, } EXPORT_SYMBOL_GPL(__nf_ct_try_assign_helper); +/* 'skb' should already be pulled to nh_ofs. */ +int nf_ct_helper(struct sk_buff *skb, struct nf_conn *ct, + enum ip_conntrack_info ctinfo, u16 proto) +{ + const struct nf_conntrack_helper *helper; + const struct nf_conn_help *help; + unsigned int protoff; + int err; + + if (ctinfo == IP_CT_RELATED_REPLY) + return NF_ACCEPT; + + help = nfct_help(ct); + if (!help) + return NF_ACCEPT; + + helper = rcu_dereference(help->helper); + if (!helper) + return NF_ACCEPT; + + if (helper->tuple.src.l3num != NFPROTO_UNSPEC && + helper->tuple.src.l3num != proto) + return NF_ACCEPT; + + switch (proto) { + case NFPROTO_IPV4: + protoff = ip_hdrlen(skb); + proto = ip_hdr(skb)->protocol; + break; + case NFPROTO_IPV6: { + u8 nexthdr = ipv6_hdr(skb)->nexthdr; + __be16 frag_off; + int ofs; + + ofs = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, + &frag_off); + if (ofs < 0 || (frag_off & htons(~0x7)) != 0) { + pr_debug("proto header not found\n"); + return NF_ACCEPT; + } + protoff = ofs; + proto = nexthdr; + break; + } + default: + WARN_ONCE(1, "helper invoked on non-IP family!"); + return NF_DROP; + } + + if (helper->tuple.dst.protonum != proto) + return NF_ACCEPT; + + err = helper->help(skb, protoff, ct, ctinfo); + if (err != NF_ACCEPT) + return err; + + /* Adjust seqs after helper. This is needed due to some helpers (e.g., + * FTP with NAT) adusting the TCP payload size when mangling IP + * addresses and/or port numbers in the text-based control connection. + */ + if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) && + !nf_ct_seq_adjust(skb, ct, ctinfo, protoff)) + return NF_DROP; + return NF_ACCEPT; +} +EXPORT_SYMBOL_GPL(nf_ct_helper); + +int nf_ct_add_helper(struct nf_conn *ct, const char *name, u8 family, + u8 proto, bool nat, struct nf_conntrack_helper **hp) +{ + struct nf_conntrack_helper *helper; + struct nf_conn_help *help; + int ret = 0; + + helper = nf_conntrack_helper_try_module_get(name, family, proto); + if (!helper) + return -EINVAL; + + help = nf_ct_helper_ext_add(ct, GFP_KERNEL); + if (!help) { + nf_conntrack_helper_put(helper); + return -ENOMEM; + } +#if IS_ENABLED(CONFIG_NF_NAT) + if (nat) { + ret = nf_nat_helper_try_module_get(name, family, proto); + if (ret) { + nf_conntrack_helper_put(helper); + return ret; + } + } +#endif + rcu_assign_pointer(help->helper, helper); + *hp = helper; + return ret; +} +EXPORT_SYMBOL_GPL(nf_ct_add_helper); + /* appropriate ct lock protecting must be taken by caller */ static int unhelp(struct nf_conn *ct, void *me) { diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index ce1efa888c12..38e1256b6d18 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -10127,7 +10127,8 @@ static void __net_exit nf_tables_exit_net(struct net *net) struct nftables_pernet *nft_net = nft_pernet(net); mutex_lock(&nft_net->commit_mutex); - if (!list_empty(&nft_net->commit_list)) + if (!list_empty(&nft_net->commit_list) || + !list_empty(&nft_net->module_list)) __nf_tables_abort(net, NFNL_ABORT_NONE); __nft_release_tables(net); mutex_unlock(&nft_net->commit_mutex); diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 9c44518cb70f..6d18fb346868 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -294,6 +294,7 @@ replay: nfnl_lock(subsys_id); if (nfnl_dereference_protected(subsys_id) != ss || nfnetlink_find_client(type, ss) != nc) { + nfnl_unlock(subsys_id); err = -EAGAIN; break; } diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index b10d5e50b99d..9ebdf3262015 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2500,7 +2500,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, skb = nlmsg_new(payload + tlvlen, GFP_KERNEL); if (!skb) - goto err_bad_put; + goto err_skb; rep = nlmsg_put(skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, NLMSG_ERROR, sizeof(*errmsg), flags); @@ -2528,6 +2528,8 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, return; err_bad_put: + nlmsg_free(skb); +err_skb: NETLINK_CB(in_skb).sk->sk_err = ENOBUFS; sk_error_report(NETLINK_CB(in_skb).sk); } diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 3e16527beb91..600993c80050 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -101,6 +101,17 @@ genl_op_fill_in_reject_policy(const struct genl_family *family, op->maxattr = 1; } +static void +genl_op_fill_in_reject_policy_split(const struct genl_family *family, + struct genl_split_ops *op) +{ + if (op->policy) + return; + + op->policy = genl_policy_reject_all; + op->maxattr = 1; +} + static const struct genl_family *genl_family_find_byid(unsigned int id) { return idr_find(&genl_fam_idr, id); @@ -118,10 +129,15 @@ static const struct genl_family *genl_family_find_byname(char *name) return NULL; } -static int genl_get_cmd_cnt(const struct genl_family *family) -{ - return family->n_ops + family->n_small_ops; -} +struct genl_op_iter { + const struct genl_family *family; + struct genl_split_ops doit; + struct genl_split_ops dumpit; + int cmd_idx; + int entry_idx; + u32 cmd; + u8 flags; +}; static void genl_op_from_full(const struct genl_family *family, unsigned int i, struct genl_ops *op) @@ -181,24 +197,187 @@ static int genl_get_cmd_small(u32 cmd, const struct genl_family *family, return -ENOENT; } -static int genl_get_cmd(u32 cmd, const struct genl_family *family, - struct genl_ops *op) +static void genl_op_from_split(struct genl_op_iter *iter) { - if (!genl_get_cmd_full(cmd, family, op)) - return 0; - return genl_get_cmd_small(cmd, family, op); + const struct genl_family *family = iter->family; + int i, cnt = 0; + + i = iter->entry_idx - family->n_ops - family->n_small_ops; + + if (family->split_ops[i + cnt].flags & GENL_CMD_CAP_DO) { + iter->doit = family->split_ops[i + cnt]; + genl_op_fill_in_reject_policy_split(family, &iter->doit); + cnt++; + } else { + memset(&iter->doit, 0, sizeof(iter->doit)); + } + + if (i + cnt < family->n_split_ops && + family->split_ops[i + cnt].flags & GENL_CMD_CAP_DUMP) { + iter->dumpit = family->split_ops[i + cnt]; + genl_op_fill_in_reject_policy_split(family, &iter->dumpit); + cnt++; + } else { + memset(&iter->dumpit, 0, sizeof(iter->dumpit)); + } + + WARN_ON(!cnt); + iter->entry_idx += cnt; } -static void genl_get_cmd_by_index(unsigned int i, - const struct genl_family *family, - struct genl_ops *op) +static int +genl_get_cmd_split(u32 cmd, u8 flag, const struct genl_family *family, + struct genl_split_ops *op) { - if (i < family->n_ops) - genl_op_from_full(family, i, op); - else if (i < family->n_ops + family->n_small_ops) - genl_op_from_small(family, i - family->n_ops, op); - else - WARN_ON_ONCE(1); + int i; + + for (i = 0; i < family->n_split_ops; i++) + if (family->split_ops[i].cmd == cmd && + family->split_ops[i].flags & flag) { + *op = family->split_ops[i]; + return 0; + } + + return -ENOENT; +} + +static int +genl_cmd_full_to_split(struct genl_split_ops *op, + const struct genl_family *family, + const struct genl_ops *full, u8 flags) +{ + if ((flags & GENL_CMD_CAP_DO && !full->doit) || + (flags & GENL_CMD_CAP_DUMP && !full->dumpit)) { + memset(op, 0, sizeof(*op)); + return -ENOENT; + } + + if (flags & GENL_CMD_CAP_DUMP) { + op->start = full->start; + op->dumpit = full->dumpit; + op->done = full->done; + } else { + op->pre_doit = family->pre_doit; + op->doit = full->doit; + op->post_doit = family->post_doit; + } + + if (flags & GENL_CMD_CAP_DUMP && + full->validate & GENL_DONT_VALIDATE_DUMP) { + op->policy = NULL; + op->maxattr = 0; + } else { + op->policy = full->policy; + op->maxattr = full->maxattr; + } + + op->cmd = full->cmd; + op->internal_flags = full->internal_flags; + op->flags = full->flags; + op->validate = full->validate; + + /* Make sure flags include the GENL_CMD_CAP_DO / GENL_CMD_CAP_DUMP */ + op->flags |= flags; + + return 0; +} + +/* Must make sure that op is initialized to 0 on failure */ +static int +genl_get_cmd(u32 cmd, u8 flags, const struct genl_family *family, + struct genl_split_ops *op) +{ + struct genl_ops full; + int err; + + err = genl_get_cmd_full(cmd, family, &full); + if (err == -ENOENT) + err = genl_get_cmd_small(cmd, family, &full); + /* Found one of legacy forms */ + if (err == 0) + return genl_cmd_full_to_split(op, family, &full, flags); + + err = genl_get_cmd_split(cmd, flags, family, op); + if (err) + memset(op, 0, sizeof(*op)); + return err; +} + +/* For policy dumping only, get ops of both do and dump. + * Fail if both are missing, genl_get_cmd() will zero-init in case of failure. + */ +static int +genl_get_cmd_both(u32 cmd, const struct genl_family *family, + struct genl_split_ops *doit, struct genl_split_ops *dumpit) +{ + int err1, err2; + + err1 = genl_get_cmd(cmd, GENL_CMD_CAP_DO, family, doit); + err2 = genl_get_cmd(cmd, GENL_CMD_CAP_DUMP, family, dumpit); + + return err1 && err2 ? -ENOENT : 0; +} + +static bool +genl_op_iter_init(const struct genl_family *family, struct genl_op_iter *iter) +{ + iter->family = family; + iter->cmd_idx = 0; + iter->entry_idx = 0; + + iter->flags = 0; + + return iter->family->n_ops + + iter->family->n_small_ops + + iter->family->n_split_ops; +} + +static bool genl_op_iter_next(struct genl_op_iter *iter) +{ + const struct genl_family *family = iter->family; + bool legacy_op = true; + struct genl_ops op; + + if (iter->entry_idx < family->n_ops) { + genl_op_from_full(family, iter->entry_idx, &op); + } else if (iter->entry_idx < family->n_ops + family->n_small_ops) { + genl_op_from_small(family, iter->entry_idx - family->n_ops, + &op); + } else if (iter->entry_idx < + family->n_ops + family->n_small_ops + family->n_split_ops) { + legacy_op = false; + /* updates entry_idx */ + genl_op_from_split(iter); + } else { + return false; + } + + iter->cmd_idx++; + + if (legacy_op) { + iter->entry_idx++; + + genl_cmd_full_to_split(&iter->doit, family, + &op, GENL_CMD_CAP_DO); + genl_cmd_full_to_split(&iter->dumpit, family, + &op, GENL_CMD_CAP_DUMP); + } + + iter->cmd = iter->doit.cmd | iter->dumpit.cmd; + iter->flags = iter->doit.flags | iter->dumpit.flags; + + return true; +} + +static void +genl_op_iter_copy(struct genl_op_iter *dst, struct genl_op_iter *src) +{ + *dst = *src; +} + +static unsigned int genl_op_iter_idx(struct genl_op_iter *iter) +{ + return iter->cmd_idx; } static int genl_allocate_reserve_groups(int n_groups, int *first_id) @@ -366,31 +545,72 @@ static void genl_unregister_mc_groups(const struct genl_family *family) } } +static bool genl_split_op_check(const struct genl_split_ops *op) +{ + if (WARN_ON(hweight8(op->flags & (GENL_CMD_CAP_DO | + GENL_CMD_CAP_DUMP)) != 1)) + return true; + return false; +} + static int genl_validate_ops(const struct genl_family *family) { - int i, j; + struct genl_op_iter i, j; + unsigned int s; if (WARN_ON(family->n_ops && !family->ops) || - WARN_ON(family->n_small_ops && !family->small_ops)) + WARN_ON(family->n_small_ops && !family->small_ops) || + WARN_ON(family->n_split_ops && !family->split_ops)) return -EINVAL; - for (i = 0; i < genl_get_cmd_cnt(family); i++) { - struct genl_ops op; - - genl_get_cmd_by_index(i, family, &op); - if (op.dumpit == NULL && op.doit == NULL) + for (genl_op_iter_init(family, &i); genl_op_iter_next(&i); ) { + if (!(i.flags & (GENL_CMD_CAP_DO | GENL_CMD_CAP_DUMP))) return -EINVAL; - if (WARN_ON(op.cmd >= family->resv_start_op && op.validate)) + + if (WARN_ON(i.cmd >= family->resv_start_op && + (i.doit.validate || i.dumpit.validate))) return -EINVAL; - for (j = i + 1; j < genl_get_cmd_cnt(family); j++) { - struct genl_ops op2; - genl_get_cmd_by_index(j, family, &op2); - if (op.cmd == op2.cmd) + genl_op_iter_copy(&j, &i); + while (genl_op_iter_next(&j)) { + if (i.cmd == j.cmd) return -EINVAL; } } + if (family->n_split_ops) { + if (genl_split_op_check(&family->split_ops[0])) + return -EINVAL; + } + + for (s = 1; s < family->n_split_ops; s++) { + const struct genl_split_ops *a, *b; + + a = &family->split_ops[s - 1]; + b = &family->split_ops[s]; + + if (genl_split_op_check(b)) + return -EINVAL; + + /* Check sort order */ + if (a->cmd < b->cmd) + continue; + + if (a->internal_flags != b->internal_flags || + ((a->flags ^ b->flags) & ~(GENL_CMD_CAP_DO | + GENL_CMD_CAP_DUMP))) { + WARN_ON(1); + return -EINVAL; + } + + if ((a->flags & GENL_CMD_CAP_DO) && + (b->flags & GENL_CMD_CAP_DUMP)) + continue; + + WARN_ON(1); + return -EINVAL; + } + return 0; } @@ -544,7 +764,7 @@ static struct nlattr ** genl_family_rcv_msg_attrs_parse(const struct genl_family *family, struct nlmsghdr *nlh, struct netlink_ext_ack *extack, - const struct genl_ops *ops, + const struct genl_split_ops *ops, int hdrlen, enum genl_validate_flags no_strict_flag) { @@ -580,22 +800,21 @@ struct genl_start_context { const struct genl_family *family; struct nlmsghdr *nlh; struct netlink_ext_ack *extack; - const struct genl_ops *ops; + const struct genl_split_ops *ops; int hdrlen; }; static int genl_start(struct netlink_callback *cb) { struct genl_start_context *ctx = cb->data; - const struct genl_ops *ops = ctx->ops; + const struct genl_split_ops *ops; struct genl_dumpit_info *info; struct nlattr **attrs = NULL; int rc = 0; - if (ops->validate & GENL_DONT_VALIDATE_DUMP) - goto no_attrs; - - if (ctx->nlh->nlmsg_len < nlmsg_msg_size(ctx->hdrlen)) + ops = ctx->ops; + if (!(ops->validate & GENL_DONT_VALIDATE_DUMP) && + ctx->nlh->nlmsg_len < nlmsg_msg_size(ctx->hdrlen)) return -EINVAL; attrs = genl_family_rcv_msg_attrs_parse(ctx->family, ctx->nlh, ctx->extack, @@ -604,7 +823,6 @@ static int genl_start(struct netlink_callback *cb) if (IS_ERR(attrs)) return PTR_ERR(attrs); -no_attrs: info = genl_dumpit_info_alloc(); if (!info) { genl_family_rcv_msg_attrs_free(attrs); @@ -633,7 +851,7 @@ no_attrs: static int genl_lock_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { - const struct genl_ops *ops = &genl_dumpit_info(cb)->op; + const struct genl_split_ops *ops = &genl_dumpit_info(cb)->op; int rc; genl_lock(); @@ -645,7 +863,7 @@ static int genl_lock_dumpit(struct sk_buff *skb, struct netlink_callback *cb) static int genl_lock_done(struct netlink_callback *cb) { const struct genl_dumpit_info *info = genl_dumpit_info(cb); - const struct genl_ops *ops = &info->op; + const struct genl_split_ops *ops = &info->op; int rc = 0; if (ops->done) { @@ -661,7 +879,7 @@ static int genl_lock_done(struct netlink_callback *cb) static int genl_parallel_done(struct netlink_callback *cb) { const struct genl_dumpit_info *info = genl_dumpit_info(cb); - const struct genl_ops *ops = &info->op; + const struct genl_split_ops *ops = &info->op; int rc = 0; if (ops->done) @@ -675,15 +893,12 @@ static int genl_family_rcv_msg_dumpit(const struct genl_family *family, struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack, - const struct genl_ops *ops, + const struct genl_split_ops *ops, int hdrlen, struct net *net) { struct genl_start_context ctx; int err; - if (!ops->dumpit) - return -EOPNOTSUPP; - ctx.family = family; ctx.nlh = nlh; ctx.extack = extack; @@ -721,16 +936,13 @@ static int genl_family_rcv_msg_doit(const struct genl_family *family, struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack, - const struct genl_ops *ops, + const struct genl_split_ops *ops, int hdrlen, struct net *net) { struct nlattr **attrbuf; struct genl_info info; int err; - if (!ops->doit) - return -EOPNOTSUPP; - attrbuf = genl_family_rcv_msg_attrs_parse(family, nlh, extack, ops, hdrlen, GENL_DONT_VALIDATE_STRICT); @@ -747,16 +959,16 @@ static int genl_family_rcv_msg_doit(const struct genl_family *family, genl_info_net_set(&info, net); memset(&info.user_ptr, 0, sizeof(info.user_ptr)); - if (family->pre_doit) { - err = family->pre_doit(ops, skb, &info); + if (ops->pre_doit) { + err = ops->pre_doit(ops, skb, &info); if (err) goto out; } err = ops->doit(skb, &info); - if (family->post_doit) - family->post_doit(ops, skb, &info); + if (ops->post_doit) + ops->post_doit(ops, skb, &info); out: genl_family_rcv_msg_attrs_free(attrbuf); @@ -801,8 +1013,9 @@ static int genl_family_rcv_msg(const struct genl_family *family, { struct net *net = sock_net(skb->sk); struct genlmsghdr *hdr = nlmsg_data(nlh); - struct genl_ops op; + struct genl_split_ops op; int hdrlen; + u8 flags; /* this family doesn't exist in this netns */ if (!family->netnsok && !net_eq(net, &init_net)) @@ -815,7 +1028,9 @@ static int genl_family_rcv_msg(const struct genl_family *family, if (genl_header_check(family, nlh, hdr, extack)) return -EINVAL; - if (genl_get_cmd(hdr->cmd, family, &op)) + flags = (nlh->nlmsg_flags & NLM_F_DUMP) == NLM_F_DUMP ? + GENL_CMD_CAP_DUMP : GENL_CMD_CAP_DO; + if (genl_get_cmd(hdr->cmd, flags, family, &op)) return -EOPNOTSUPP; if ((op.flags & GENL_ADMIN_PERM) && @@ -826,7 +1041,7 @@ static int genl_family_rcv_msg(const struct genl_family *family, !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) return -EPERM; - if ((nlh->nlmsg_flags & NLM_F_DUMP) == NLM_F_DUMP) + if (flags & GENL_CMD_CAP_DUMP) return genl_family_rcv_msg_dumpit(family, skb, nlh, extack, &op, hdrlen, net); else @@ -871,6 +1086,7 @@ static struct genl_family genl_ctrl; static int ctrl_fill_info(const struct genl_family *family, u32 portid, u32 seq, u32 flags, struct sk_buff *skb, u8 cmd) { + struct genl_op_iter i; void *hdr; hdr = genlmsg_put(skb, portid, seq, &genl_ctrl, flags, cmd); @@ -884,33 +1100,26 @@ static int ctrl_fill_info(const struct genl_family *family, u32 portid, u32 seq, nla_put_u32(skb, CTRL_ATTR_MAXATTR, family->maxattr)) goto nla_put_failure; - if (genl_get_cmd_cnt(family)) { + if (genl_op_iter_init(family, &i)) { struct nlattr *nla_ops; - int i; nla_ops = nla_nest_start_noflag(skb, CTRL_ATTR_OPS); if (nla_ops == NULL) goto nla_put_failure; - for (i = 0; i < genl_get_cmd_cnt(family); i++) { + while (genl_op_iter_next(&i)) { struct nlattr *nest; - struct genl_ops op; u32 op_flags; - genl_get_cmd_by_index(i, family, &op); - op_flags = op.flags; - if (op.dumpit) - op_flags |= GENL_CMD_CAP_DUMP; - if (op.doit) - op_flags |= GENL_CMD_CAP_DO; - if (op.policy) + op_flags = i.flags; + if (i.doit.policy || i.dumpit.policy) op_flags |= GENL_CMD_CAP_HASPOL; - nest = nla_nest_start_noflag(skb, i + 1); + nest = nla_nest_start_noflag(skb, genl_op_iter_idx(&i)); if (nest == NULL) goto nla_put_failure; - if (nla_put_u32(skb, CTRL_ATTR_OP_ID, op.cmd) || + if (nla_put_u32(skb, CTRL_ATTR_OP_ID, i.cmd) || nla_put_u32(skb, CTRL_ATTR_OP_FLAGS, op_flags)) goto nla_put_failure; @@ -1163,10 +1372,10 @@ static int genl_ctrl_event(int event, const struct genl_family *family, struct ctrl_dump_policy_ctx { struct netlink_policy_dump_state *state; const struct genl_family *rt; - unsigned int opidx; + struct genl_op_iter *op_iter; u32 op; u16 fam_id; - u8 policies:1, + u8 dump_map:1, single_op:1; }; @@ -1183,8 +1392,8 @@ static int ctrl_dumppolicy_start(struct netlink_callback *cb) struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx; struct nlattr **tb = info->attrs; const struct genl_family *rt; - struct genl_ops op; - int err, i; + struct genl_op_iter i; + int err; BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx)); @@ -1208,40 +1417,73 @@ static int ctrl_dumppolicy_start(struct netlink_callback *cb) ctx->rt = rt; if (tb[CTRL_ATTR_OP]) { + struct genl_split_ops doit, dump; + ctx->single_op = true; ctx->op = nla_get_u32(tb[CTRL_ATTR_OP]); - err = genl_get_cmd(ctx->op, rt, &op); + err = genl_get_cmd_both(ctx->op, rt, &doit, &dump); if (err) { NL_SET_BAD_ATTR(cb->extack, tb[CTRL_ATTR_OP]); return err; } - if (!op.policy) + if (doit.policy) { + err = netlink_policy_dump_add_policy(&ctx->state, + doit.policy, + doit.maxattr); + if (err) + goto err_free_state; + } + if (dump.policy) { + err = netlink_policy_dump_add_policy(&ctx->state, + dump.policy, + dump.maxattr); + if (err) + goto err_free_state; + } + + if (!ctx->state) return -ENODATA; - return netlink_policy_dump_add_policy(&ctx->state, op.policy, - op.maxattr); + ctx->dump_map = 1; + return 0; } - for (i = 0; i < genl_get_cmd_cnt(rt); i++) { - genl_get_cmd_by_index(i, rt, &op); + ctx->op_iter = kmalloc(sizeof(*ctx->op_iter), GFP_KERNEL); + if (!ctx->op_iter) + return -ENOMEM; - if (op.policy) { + genl_op_iter_init(rt, ctx->op_iter); + ctx->dump_map = genl_op_iter_next(ctx->op_iter); + + for (genl_op_iter_init(rt, &i); genl_op_iter_next(&i); ) { + if (i.doit.policy) { err = netlink_policy_dump_add_policy(&ctx->state, - op.policy, - op.maxattr); + i.doit.policy, + i.doit.maxattr); + if (err) + goto err_free_state; + } + if (i.dumpit.policy) { + err = netlink_policy_dump_add_policy(&ctx->state, + i.dumpit.policy, + i.dumpit.maxattr); if (err) goto err_free_state; } } - if (!ctx->state) - return -ENODATA; + if (!ctx->state) { + err = -ENODATA; + goto err_free_op_iter; + } return 0; err_free_state: netlink_policy_dump_free(ctx->state); +err_free_op_iter: + kfree(ctx->op_iter); return err; } @@ -1265,7 +1507,8 @@ static void *ctrl_dumppolicy_prep(struct sk_buff *skb, static int ctrl_dumppolicy_put_op(struct sk_buff *skb, struct netlink_callback *cb, - struct genl_ops *op) + struct genl_split_ops *doit, + struct genl_split_ops *dumpit) { struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx; struct nlattr *nest_pol, *nest_op; @@ -1273,10 +1516,7 @@ static int ctrl_dumppolicy_put_op(struct sk_buff *skb, int idx; /* skip if we have nothing to show */ - if (!op->policy) - return 0; - if (!op->doit && - (!op->dumpit || op->validate & GENL_DONT_VALIDATE_DUMP)) + if (!doit->policy && !dumpit->policy) return 0; hdr = ctrl_dumppolicy_prep(skb, cb); @@ -1287,21 +1527,26 @@ static int ctrl_dumppolicy_put_op(struct sk_buff *skb, if (!nest_pol) goto err; - nest_op = nla_nest_start(skb, op->cmd); + nest_op = nla_nest_start(skb, doit->cmd); if (!nest_op) goto err; - /* for now both do/dump are always the same */ - idx = netlink_policy_dump_get_policy_idx(ctx->state, - op->policy, - op->maxattr); + if (doit->policy) { + idx = netlink_policy_dump_get_policy_idx(ctx->state, + doit->policy, + doit->maxattr); - if (op->doit && nla_put_u32(skb, CTRL_ATTR_POLICY_DO, idx)) - goto err; + if (nla_put_u32(skb, CTRL_ATTR_POLICY_DO, idx)) + goto err; + } + if (dumpit->policy) { + idx = netlink_policy_dump_get_policy_idx(ctx->state, + dumpit->policy, + dumpit->maxattr); - if (op->dumpit && !(op->validate & GENL_DONT_VALIDATE_DUMP) && - nla_put_u32(skb, CTRL_ATTR_POLICY_DUMP, idx)) - goto err; + if (nla_put_u32(skb, CTRL_ATTR_POLICY_DUMP, idx)) + goto err; + } nla_nest_end(skb, nest_op); nla_nest_end(skb, nest_pol); @@ -1318,31 +1563,29 @@ static int ctrl_dumppolicy(struct sk_buff *skb, struct netlink_callback *cb) struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx; void *hdr; - if (!ctx->policies) { - while (ctx->opidx < genl_get_cmd_cnt(ctx->rt)) { - struct genl_ops op; + if (ctx->dump_map) { + if (ctx->single_op) { + struct genl_split_ops doit, dumpit; - if (ctx->single_op) { - int err; + if (WARN_ON(genl_get_cmd_both(ctx->op, ctx->rt, + &doit, &dumpit))) + return -ENOENT; - err = genl_get_cmd(ctx->op, ctx->rt, &op); - if (WARN_ON(err)) - return skb->len; + if (ctrl_dumppolicy_put_op(skb, cb, &doit, &dumpit)) + return skb->len; - /* break out of the loop after this one */ - ctx->opidx = genl_get_cmd_cnt(ctx->rt); - } else { - genl_get_cmd_by_index(ctx->opidx, ctx->rt, &op); - } + /* done with the per-op policy index list */ + ctx->dump_map = 0; + } - if (ctrl_dumppolicy_put_op(skb, cb, &op)) + while (ctx->dump_map) { + if (ctrl_dumppolicy_put_op(skb, cb, + &ctx->op_iter->doit, + &ctx->op_iter->dumpit)) return skb->len; - ctx->opidx++; + ctx->dump_map = genl_op_iter_next(ctx->op_iter); } - - /* completed with the per-op policy index list */ - ctx->policies = true; } while (netlink_policy_dump_loop(ctx->state)) { @@ -1375,18 +1618,27 @@ static int ctrl_dumppolicy_done(struct netlink_callback *cb) { struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx; + kfree(ctx->op_iter); netlink_policy_dump_free(ctx->state); return 0; } -static const struct genl_ops genl_ctrl_ops[] = { +static const struct genl_split_ops genl_ctrl_ops[] = { { .cmd = CTRL_CMD_GETFAMILY, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .validate = GENL_DONT_VALIDATE_STRICT, .policy = ctrl_policy_family, .maxattr = ARRAY_SIZE(ctrl_policy_family) - 1, .doit = ctrl_getfamily, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = CTRL_CMD_GETFAMILY, + .validate = GENL_DONT_VALIDATE_DUMP, + .policy = ctrl_policy_family, + .maxattr = ARRAY_SIZE(ctrl_policy_family) - 1, .dumpit = ctrl_dumpfamily, + .flags = GENL_CMD_CAP_DUMP, }, { .cmd = CTRL_CMD_GETPOLICY, @@ -1395,6 +1647,7 @@ static const struct genl_ops genl_ctrl_ops[] = { .start = ctrl_dumppolicy_start, .dumpit = ctrl_dumppolicy, .done = ctrl_dumppolicy_done, + .flags = GENL_CMD_CAP_DUMP, }, }; @@ -1404,8 +1657,8 @@ static const struct genl_multicast_group genl_ctrl_groups[] = { static struct genl_family genl_ctrl __ro_after_init = { .module = THIS_MODULE, - .ops = genl_ctrl_ops, - .n_ops = ARRAY_SIZE(genl_ctrl_ops), + .split_ops = genl_ctrl_ops, + .n_split_ops = ARRAY_SIZE(genl_ctrl_ops), .resv_start_op = CTRL_CMD_GETPOLICY + 1, .mcgrps = genl_ctrl_groups, .n_mcgrps = ARRAY_SIZE(genl_ctrl_groups), diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index c7b10234cf7c..4348321856af 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -434,65 +434,6 @@ static int ovs_ct_set_labels(struct nf_conn *ct, struct sw_flow_key *key, return 0; } -/* 'skb' should already be pulled to nh_ofs. */ -static int ovs_ct_helper(struct sk_buff *skb, u16 proto) -{ - const struct nf_conntrack_helper *helper; - const struct nf_conn_help *help; - enum ip_conntrack_info ctinfo; - unsigned int protoff; - struct nf_conn *ct; - int err; - - ct = nf_ct_get(skb, &ctinfo); - if (!ct || ctinfo == IP_CT_RELATED_REPLY) - return NF_ACCEPT; - - help = nfct_help(ct); - if (!help) - return NF_ACCEPT; - - helper = rcu_dereference(help->helper); - if (!helper) - return NF_ACCEPT; - - switch (proto) { - case NFPROTO_IPV4: - protoff = ip_hdrlen(skb); - break; - case NFPROTO_IPV6: { - u8 nexthdr = ipv6_hdr(skb)->nexthdr; - __be16 frag_off; - int ofs; - - ofs = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, - &frag_off); - if (ofs < 0 || (frag_off & htons(~0x7)) != 0) { - pr_debug("proto header not found\n"); - return NF_ACCEPT; - } - protoff = ofs; - break; - } - default: - WARN_ONCE(1, "helper invoked on non-IP family!"); - return NF_DROP; - } - - err = helper->help(skb, protoff, ct, ctinfo); - if (err != NF_ACCEPT) - return err; - - /* Adjust seqs after helper. This is needed due to some helpers (e.g., - * FTP with NAT) adusting the TCP payload size when mangling IP - * addresses and/or port numbers in the text-based control connection. - */ - if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) && - !nf_ct_seq_adjust(skb, ct, ctinfo, protoff)) - return NF_DROP; - return NF_ACCEPT; -} - /* Returns 0 on success, -EINPROGRESS if 'skb' is stolen, or other nonzero * value if 'skb' is freed. */ @@ -1038,7 +979,7 @@ static int __ovs_ct_lookup(struct net *net, struct sw_flow_key *key, */ if ((nf_ct_is_confirmed(ct) ? !cached || add_helper : info->commit) && - ovs_ct_helper(skb, info->family) != NF_ACCEPT) { + nf_ct_helper(skb, ct, ctinfo, info->family) != NF_ACCEPT) { return -EINVAL; } @@ -1350,43 +1291,6 @@ int ovs_ct_clear(struct sk_buff *skb, struct sw_flow_key *key) return 0; } -static int ovs_ct_add_helper(struct ovs_conntrack_info *info, const char *name, - const struct sw_flow_key *key, bool log) -{ - struct nf_conntrack_helper *helper; - struct nf_conn_help *help; - int ret = 0; - - helper = nf_conntrack_helper_try_module_get(name, info->family, - key->ip.proto); - if (!helper) { - OVS_NLERR(log, "Unknown helper \"%s\"", name); - return -EINVAL; - } - - help = nf_ct_helper_ext_add(info->ct, GFP_KERNEL); - if (!help) { - nf_conntrack_helper_put(helper); - return -ENOMEM; - } - -#if IS_ENABLED(CONFIG_NF_NAT) - if (info->nat) { - ret = nf_nat_helper_try_module_get(name, info->family, - key->ip.proto); - if (ret) { - nf_conntrack_helper_put(helper); - OVS_NLERR(log, "Failed to load \"%s\" NAT helper, error: %d", - name, ret); - return ret; - } - } -#endif - rcu_assign_pointer(help->helper, helper); - info->helper = helper; - return ret; -} - #if IS_ENABLED(CONFIG_NF_NAT) static int parse_nat(const struct nlattr *attr, struct ovs_conntrack_info *info, bool log) @@ -1720,9 +1624,12 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr, } if (helper) { - err = ovs_ct_add_helper(&ct_info, helper, key, log); - if (err) + err = nf_ct_add_helper(ct_info.ct, helper, ct_info.family, + key->ip.proto, ct_info.nat, &ct_info.helper); + if (err) { + OVS_NLERR(log, "Failed to add %s helper %d", helper, err); goto err_free_ct; + } } err = ovs_nla_add_action(sfa, OVS_ACTION_ATTR_CT, &ct_info, diff --git a/net/rds/send.c b/net/rds/send.c index 0c5504068e3c..5e57a1581dc6 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -1114,7 +1114,7 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) struct rds_conn_path *cpath; struct in6_addr daddr; __u32 scope_id = 0; - size_t total_payload_len = payload_len, rdma_payload_len = 0; + size_t rdma_payload_len = 0; bool zcopy = ((msg->msg_flags & MSG_ZEROCOPY) && sock_flag(rds_rs_to_sk(rs), SOCK_ZEROCOPY)); int num_sgs = DIV_ROUND_UP(payload_len, PAGE_SIZE); @@ -1243,7 +1243,6 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) if (ret) goto out; - total_payload_len += rdma_payload_len; if (max_t(size_t, payload_len, rdma_payload_len) > RDS_MAX_MSG_SIZE) { ret = -EMSGSIZE; goto out; diff --git a/net/rxrpc/Makefile b/net/rxrpc/Makefile index b11281bed2a4..fdeba488fc6e 100644 --- a/net/rxrpc/Makefile +++ b/net/rxrpc/Makefile @@ -30,6 +30,7 @@ rxrpc-y := \ sendmsg.o \ server_key.o \ skbuff.o \ + txbuf.o \ utils.o rxrpc-$(CONFIG_PROC_FS) += proc.o diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index ceba28e9dce6..2f3991cf8715 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -39,7 +39,7 @@ atomic_t rxrpc_debug_id; EXPORT_SYMBOL(rxrpc_debug_id); /* count of skbs currently in use */ -atomic_t rxrpc_n_tx_skbs, rxrpc_n_rx_skbs; +atomic_t rxrpc_n_rx_skbs; struct workqueue_struct *rxrpc_workqueue; @@ -979,7 +979,7 @@ static int __init af_rxrpc_init(void) goto error_call_jar; } - rxrpc_workqueue = alloc_workqueue("krxrpcd", 0, 1); + rxrpc_workqueue = alloc_workqueue("krxrpcd", WQ_HIGHPRI | WQ_MEM_RECLAIM | WQ_UNBOUND, 1); if (!rxrpc_workqueue) { pr_notice("Failed to allocate work queue\n"); goto error_work_queue; @@ -1059,7 +1059,6 @@ static void __exit af_rxrpc_exit(void) sock_unregister(PF_RXRPC); proto_unregister(&rxrpc_proto); unregister_pernet_device(&rxrpc_net_ops); - ASSERTCMP(atomic_read(&rxrpc_n_tx_skbs), ==, 0); ASSERTCMP(atomic_read(&rxrpc_n_rx_skbs), ==, 0); /* Make sure the local and peer records pinned by any dying connections diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 1ad0ec5afb50..0273a9029229 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -29,6 +29,7 @@ struct rxrpc_crypt { struct key_preparsed_payload; struct rxrpc_connection; +struct rxrpc_txbuf; /* * Mark applied to socket buffers in skb->mark. skb->priority is used @@ -93,6 +94,22 @@ struct rxrpc_net { struct list_head peer_keepalive_new; struct timer_list peer_keepalive_timer; struct work_struct peer_keepalive_work; + + atomic_t stat_tx_data; + atomic_t stat_tx_data_retrans; + atomic_t stat_tx_data_send; + atomic_t stat_tx_data_send_frag; + atomic_t stat_rx_data; + atomic_t stat_rx_data_reqack; + atomic_t stat_rx_data_jumbo; + + atomic_t stat_tx_ack_fill; + atomic_t stat_tx_ack_send; + atomic_t stat_tx_ack_skip; + atomic_t stat_tx_acks[256]; + atomic_t stat_rx_acks[256]; + + atomic_t stat_why_req_ack[8]; }; /* @@ -178,20 +195,12 @@ struct rxrpc_host_header { * - max 48 bytes (struct sk_buff::cb) */ struct rxrpc_skb_priv { - atomic_t nr_ring_pins; /* Number of rxtx ring pins */ - u8 nr_subpackets; /* Number of subpackets */ - u8 rx_flags; /* Received packet flags */ -#define RXRPC_SKB_INCL_LAST 0x01 /* - Includes last packet */ -#define RXRPC_SKB_TX_BUFFER 0x02 /* - Is transmit buffer */ - union { - int remain; /* amount of space remaining for next write */ - - /* List of requested ACKs on subpackets */ - unsigned long rx_req_ack[(RXRPC_MAX_NR_JUMBO + BITS_PER_LONG - 1) / - BITS_PER_LONG]; - }; + u16 offset; /* Offset of data */ + u16 len; /* Length of data */ + u8 flags; +#define RXRPC_RX_VERIFIED 0x01 - struct rxrpc_host_header hdr; /* RxRPC packet header from this packet */ + struct rxrpc_host_header hdr; /* RxRPC packet header from this packet */ }; #define rxrpc_skb(__skb) ((struct rxrpc_skb_priv *) &(__skb)->cb) @@ -233,19 +242,14 @@ struct rxrpc_security { size_t *, size_t *, size_t *); /* impose security on a packet */ - int (*secure_packet)(struct rxrpc_call *, struct sk_buff *, size_t); + int (*secure_packet)(struct rxrpc_call *, struct rxrpc_txbuf *); /* verify the security on a received packet */ - int (*verify_packet)(struct rxrpc_call *, struct sk_buff *, - unsigned int, unsigned int, rxrpc_seq_t, u16); + int (*verify_packet)(struct rxrpc_call *, struct sk_buff *); /* Free crypto request on a call */ void (*free_call_crypto)(struct rxrpc_call *); - /* Locate the data in a received packet that has been verified. */ - void (*locate_data)(struct rxrpc_call *, struct sk_buff *, - unsigned int *, unsigned int *); - /* issue a challenge */ int (*issue_challenge)(struct rxrpc_connection *); @@ -276,6 +280,8 @@ struct rxrpc_local { struct hlist_node link; struct socket *socket; /* my UDP socket */ struct work_struct processor; + struct list_head ack_tx_queue; /* List of ACKs that need sending */ + spinlock_t ack_tx_lock; /* ACK list lock */ struct rxrpc_sock __rcu *service; /* Service(s) listening on this endpoint */ struct rw_semaphore defrag_sem; /* control re-enablement of IP DF bit */ struct sk_buff_head reject_queue; /* packets awaiting rejection */ @@ -326,7 +332,7 @@ struct rxrpc_peer { u32 rto_j; /* Retransmission timeout in jiffies */ u8 backoff; /* Backoff timeout */ - u8 cong_cwnd; /* Congestion window size */ + u8 cong_ssthresh; /* Congestion slow-start threshold */ }; /* @@ -490,6 +496,7 @@ enum rxrpc_call_flag { RXRPC_CALL_EXPOSED, /* The call was exposed to the world */ RXRPC_CALL_RX_LAST, /* Received the last packet (at rxtx_top) */ RXRPC_CALL_TX_LAST, /* Last packet in Tx buffer (at rxtx_top) */ + RXRPC_CALL_TX_ALL_ACKED, /* Last packet has been hard-acked */ RXRPC_CALL_SEND_PING, /* A ping will need to be sent */ RXRPC_CALL_RETRANS_TIMEOUT, /* Retransmission due to timeout occurred */ RXRPC_CALL_BEGAN_RX_TIMER, /* We began the expect_rx_by timer */ @@ -498,16 +505,16 @@ enum rxrpc_call_flag { RXRPC_CALL_DISCONNECTED, /* The call has been disconnected */ RXRPC_CALL_KERNEL, /* The call was made by the kernel */ RXRPC_CALL_UPGRADE, /* Service upgrade was requested for the call */ + RXRPC_CALL_DELAY_ACK_PENDING, /* DELAY ACK generation is pending */ + RXRPC_CALL_IDLE_ACK_PENDING, /* IDLE ACK generation is pending */ }; /* * Events that can be raised on a call. */ enum rxrpc_call_event { - RXRPC_CALL_EV_ACK, /* need to generate ACK */ RXRPC_CALL_EV_ABORT, /* need to generate abort */ RXRPC_CALL_EV_RESEND, /* Tx resend required */ - RXRPC_CALL_EV_PING, /* Ping send required */ RXRPC_CALL_EV_EXPIRED, /* Expiry occurred */ RXRPC_CALL_EV_ACK_LOST, /* ACK may be lost, send ping */ }; @@ -566,7 +573,7 @@ struct rxrpc_call { struct rxrpc_net *rxnet; /* Network namespace to which call belongs */ const struct rxrpc_security *security; /* applied security module */ struct mutex user_mutex; /* User access mutex */ - unsigned long ack_at; /* When deferred ACK needs to happen */ + unsigned long delay_ack_at; /* When DELAY ACK needs to happen */ unsigned long ack_lost_at; /* When ACK is figured as lost */ unsigned long resend_at; /* When next resend needs to happen */ unsigned long ping_at; /* When next to send a ping */ @@ -576,7 +583,6 @@ struct rxrpc_call { unsigned long expect_term_by; /* When we expect call termination by */ u32 next_rx_timo; /* Timeout for next Rx packet (jif) */ u32 next_req_timo; /* Timeout for next Rx request packet (jif) */ - struct skcipher_request *cipher_req; /* Packet cipher request buffer */ struct timer_list timer; /* Combined event timer */ struct work_struct processor; /* Event processor */ rxrpc_notify_rx_t notify_rx; /* kernel service Rx notification function */ @@ -587,14 +593,12 @@ struct rxrpc_call { struct list_head recvmsg_link; /* Link in rx->recvmsg_q */ struct list_head sock_link; /* Link in rx->sock_calls */ struct rb_node sock_node; /* Node in rx->calls */ - struct sk_buff *tx_pending; /* Tx socket buffer being filled */ + struct rxrpc_txbuf *tx_pending; /* Tx buffer being filled */ wait_queue_head_t waitq; /* Wait queue for channel or Tx */ s64 tx_total_len; /* Total length left to be transmitted (or -1) */ - __be32 crypto_buf[2]; /* Temporary packet crypto buffer */ unsigned long user_call_ID; /* user-defined call ID */ unsigned long flags; unsigned long events; - spinlock_t lock; spinlock_t notify_lock; /* Kernel notification lock */ rwlock_t state_lock; /* lock for state transition */ u32 abort_code; /* Local/remote abort code */ @@ -610,37 +614,27 @@ struct rxrpc_call { int debug_id; /* debug ID for printks */ unsigned short rx_pkt_offset; /* Current recvmsg packet offset */ unsigned short rx_pkt_len; /* Current recvmsg packet len */ - bool rx_pkt_last; /* Current recvmsg packet is last */ - - /* Rx/Tx circular buffer, depending on phase. - * - * In the Rx phase, packets are annotated with 0 or the number of the - * segment of a jumbo packet each buffer refers to. There can be up to - * 47 segments in a maximum-size UDP packet. - * - * In the Tx phase, packets are annotated with which buffers have been - * acked. - */ -#define RXRPC_RXTX_BUFF_SIZE 64 -#define RXRPC_RXTX_BUFF_MASK (RXRPC_RXTX_BUFF_SIZE - 1) -#define RXRPC_INIT_RX_WINDOW_SIZE 63 - struct sk_buff **rxtx_buffer; - u8 *rxtx_annotations; -#define RXRPC_TX_ANNO_ACK 0 -#define RXRPC_TX_ANNO_UNACK 1 -#define RXRPC_TX_ANNO_NAK 2 -#define RXRPC_TX_ANNO_RETRANS 3 -#define RXRPC_TX_ANNO_MASK 0x03 -#define RXRPC_TX_ANNO_LAST 0x04 -#define RXRPC_TX_ANNO_RESENT 0x08 - -#define RXRPC_RX_ANNO_SUBPACKET 0x3f /* Subpacket number in jumbogram */ -#define RXRPC_RX_ANNO_VERIFIED 0x80 /* Set if verified and decrypted */ - rxrpc_seq_t tx_hard_ack; /* Dead slot in buffer; the first transmitted but - * not hard-ACK'd packet follows this. - */ + + /* Transmitted data tracking. */ + spinlock_t tx_lock; /* Transmit queue lock */ + struct list_head tx_buffer; /* Buffer of transmissible packets */ + rxrpc_seq_t tx_bottom; /* First packet in buffer */ + rxrpc_seq_t tx_transmitted; /* Highest packet transmitted */ rxrpc_seq_t tx_top; /* Highest Tx slot allocated. */ u16 tx_backoff; /* Delay to insert due to Tx failure */ + u8 tx_winsize; /* Maximum size of Tx window */ +#define RXRPC_TX_MAX_WINDOW 128 + ktime_t tx_last_sent; /* Last time a transmission occurred */ + + /* Received data tracking */ + struct sk_buff_head recvmsg_queue; /* Queue of packets ready for recvmsg() */ + struct sk_buff_head rx_oos_queue; /* Queue of out of sequence packets */ + + rxrpc_seq_t rx_highest_seq; /* Higest sequence number received */ + rxrpc_seq_t rx_consumed; /* Highest packet consumed */ + rxrpc_serial_t rx_serial; /* Highest serial received for this call */ + u8 rx_winsize; /* Size of Rx window */ + spinlock_t input_lock; /* Lock for packet input to this call */ /* TCP-style slow-start congestion control [RFC5681]. Since the SMSS * is fixed, we keep these numbers in terms of segments (ie. DATA @@ -655,25 +649,17 @@ struct rxrpc_call { u8 cong_cumul_acks; /* Cumulative ACK count */ ktime_t cong_tstamp; /* Last time cwnd was changed */ - rxrpc_seq_t rx_hard_ack; /* Dead slot in buffer; the first received but not - * consumed packet follows this. - */ - rxrpc_seq_t rx_top; /* Highest Rx slot allocated. */ - rxrpc_seq_t rx_expect_next; /* Expected next packet sequence number */ - rxrpc_serial_t rx_serial; /* Highest serial received for this call */ - u8 rx_winsize; /* Size of Rx window */ - u8 tx_winsize; /* Maximum size of Tx window */ - bool tx_phase; /* T if transmission phase, F if receive phase */ - u8 nr_jumbo_bad; /* Number of jumbo dups/exceeds-windows */ - - spinlock_t input_lock; /* Lock for packet input to this call */ - /* Receive-phase ACK management (ACKs we send). */ u8 ackr_reason; /* reason to ACK */ rxrpc_serial_t ackr_serial; /* serial of packet being ACK'd */ - rxrpc_seq_t ackr_highest_seq; /* Higest sequence number received */ + atomic64_t ackr_window; /* Base (in LSW) and top (in MSW) of SACK window */ atomic_t ackr_nr_unacked; /* Number of unacked packets */ atomic_t ackr_nr_consumed; /* Number of packets needing hard ACK */ + struct { +#define RXRPC_SACK_SIZE 256 + /* SACK table for soft-acked packets */ + u8 ackr_sack_table[RXRPC_SACK_SIZE]; + } __aligned(8); /* RTT management */ rxrpc_serial_t rtt_serial[4]; /* Serial number of DATA or PING sent */ @@ -687,21 +673,24 @@ struct rxrpc_call { ktime_t acks_latest_ts; /* Timestamp of latest ACK received */ rxrpc_seq_t acks_first_seq; /* first sequence number received */ rxrpc_seq_t acks_prev_seq; /* Highest previousPacket received */ + rxrpc_seq_t acks_hard_ack; /* Latest hard-ack point */ rxrpc_seq_t acks_lowest_nak; /* Lowest NACK in the buffer (or ==tx_hard_ack) */ rxrpc_seq_t acks_lost_top; /* tx_top at the time lost-ack ping sent */ rxrpc_serial_t acks_lost_ping; /* Serial number of probe ACK */ + rxrpc_serial_t acks_highest_serial; /* Highest serial number ACK'd */ + struct sk_buff *acks_soft_tbl; /* The last ACK packet with NAKs in it */ + spinlock_t acks_ack_lock; /* Access to ->acks_last_ack */ }; /* * Summary of a new ACK and the changes it made to the Tx buffer packet states. */ struct rxrpc_ack_summary { + u16 nr_acks; /* Number of ACKs in packet */ + u16 nr_new_acks; /* Number of new ACKs in packet */ + u16 nr_rot_new_acks; /* Number of rotated new ACKs */ u8 ack_reason; - u8 nr_acks; /* Number of ACKs in packet */ - u8 nr_nacks; /* Number of NACKs in packet */ - u8 nr_new_acks; /* Number of new ACKs in packet */ - u8 nr_new_nacks; /* Number of new NACKs in packet */ - u8 nr_rot_new_acks; /* Number of rotated new ACKs */ + bool saw_nacks; /* Saw NACKs in packet */ bool new_low_nack; /* T if new low NACK found */ bool retrans_timeo; /* T if reTx due to timeout happened */ u8 flight_size; /* Number of unreceived transmissions */ @@ -744,12 +733,58 @@ struct rxrpc_send_params { bool upgrade; /* If the connection is upgradeable */ }; +/* + * Buffer of data to be output as a packet. + */ +struct rxrpc_txbuf { + struct rcu_head rcu; + struct list_head call_link; /* Link in call->tx_queue */ + struct list_head tx_link; /* Link in live Enc queue or Tx queue */ + struct rxrpc_call *call; /* Call to which belongs */ + ktime_t last_sent; /* Time at which last transmitted */ + refcount_t ref; + rxrpc_seq_t seq; /* Sequence number of this packet */ + unsigned int call_debug_id; + unsigned int debug_id; + unsigned int len; /* Amount of data in buffer */ + unsigned int space; /* Remaining data space */ + unsigned int offset; /* Offset of fill point */ + unsigned long flags; +#define RXRPC_TXBUF_LAST 0 /* Set if last packet in Tx phase */ +#define RXRPC_TXBUF_RESENT 1 /* Set if has been resent */ + u8 /*enum rxrpc_propose_ack_trace*/ ack_why; /* If ack, why */ + struct { + /* The packet for encrypting and DMA'ing. We align it such + * that data[] aligns correctly for any crypto blocksize. + */ + u8 pad[64 - sizeof(struct rxrpc_wire_header)]; + struct rxrpc_wire_header wire; /* Network-ready header */ + union { + u8 data[RXRPC_JUMBO_DATALEN]; /* Data packet */ + struct { + struct rxrpc_ackpacket ack; + u8 acks[0]; + }; + }; + } __aligned(64); +}; + +static inline bool rxrpc_sending_to_server(const struct rxrpc_txbuf *txb) +{ + return txb->wire.flags & RXRPC_CLIENT_INITIATED; +} + +static inline bool rxrpc_sending_to_client(const struct rxrpc_txbuf *txb) +{ + return !rxrpc_sending_to_server(txb); +} + #include <trace/events/rxrpc.h> /* * af_rxrpc.c */ -extern atomic_t rxrpc_n_tx_skbs, rxrpc_n_rx_skbs; +extern atomic_t rxrpc_n_rx_skbs; extern struct workqueue_struct *rxrpc_workqueue; /* @@ -766,8 +801,12 @@ int rxrpc_user_charge_accept(struct rxrpc_sock *, unsigned long); /* * call_event.c */ -void rxrpc_propose_ACK(struct rxrpc_call *, u8, u32, bool, bool, - enum rxrpc_propose_ack_trace); +void rxrpc_propose_ping(struct rxrpc_call *call, u32 serial, + enum rxrpc_propose_ack_trace why); +void rxrpc_send_ACK(struct rxrpc_call *, u8, rxrpc_serial_t, enum rxrpc_propose_ack_trace); +void rxrpc_propose_delay_ACK(struct rxrpc_call *, rxrpc_serial_t, + enum rxrpc_propose_ack_trace); +void rxrpc_shrink_call_tx_buffer(struct rxrpc_call *); void rxrpc_process_call(struct work_struct *); void rxrpc_reduce_call_timer(struct rxrpc_call *call, @@ -949,15 +988,12 @@ static inline bool __rxrpc_use_local(struct rxrpc_local *local) * misc.c */ extern unsigned int rxrpc_max_backlog __read_mostly; -extern unsigned long rxrpc_requested_ack_delay; extern unsigned long rxrpc_soft_ack_delay; extern unsigned long rxrpc_idle_ack_delay; extern unsigned int rxrpc_rx_window_size; extern unsigned int rxrpc_rx_mtu; extern unsigned int rxrpc_rx_jumbo_max; -extern const s8 rxrpc_ack_priority[]; - /* * net_ns.c */ @@ -972,16 +1008,15 @@ static inline struct rxrpc_net *rxrpc_net(struct net *net) /* * output.c */ -int rxrpc_send_ack_packet(struct rxrpc_call *, bool, rxrpc_serial_t *); +void rxrpc_transmit_ack_packets(struct rxrpc_local *); int rxrpc_send_abort_packet(struct rxrpc_call *); -int rxrpc_send_data_packet(struct rxrpc_call *, struct sk_buff *, bool); +int rxrpc_send_data_packet(struct rxrpc_call *, struct rxrpc_txbuf *); void rxrpc_reject_packets(struct rxrpc_local *); void rxrpc_send_keepalive(struct rxrpc_peer *); /* * peer_event.c */ -void rxrpc_encap_err_rcv(struct sock *sk, struct sk_buff *skb, unsigned int udp_offset); void rxrpc_error_report(struct sock *); void rxrpc_peer_keepalive_worker(struct work_struct *); @@ -1092,6 +1127,15 @@ void rxrpc_free_skb(struct sk_buff *, enum rxrpc_skb_trace); void rxrpc_purge_queue(struct sk_buff_head *); /* + * stats.c + */ +int rxrpc_stats_show(struct seq_file *seq, void *v); +int rxrpc_stats_clear(struct file *file, char *buf, size_t size); + +#define rxrpc_inc_stat(rxnet, s) atomic_inc(&(rxnet)->s) +#define rxrpc_dec_stat(rxnet, s) atomic_dec(&(rxnet)->s) + +/* * sysctl.c */ #ifdef CONFIG_SYSCTL @@ -1103,6 +1147,16 @@ static inline void rxrpc_sysctl_exit(void) {} #endif /* + * txbuf.c + */ +extern atomic_t rxrpc_nr_txbuf; +struct rxrpc_txbuf *rxrpc_alloc_txbuf(struct rxrpc_call *call, u8 packet_type, + gfp_t gfp); +void rxrpc_get_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what); +void rxrpc_see_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what); +void rxrpc_put_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what); + +/* * utils.c */ int rxrpc_extract_addr_from_skb(struct sockaddr_rxrpc *, struct sk_buff *); diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 99e10eea3732..48790ee77019 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -248,9 +248,8 @@ static void rxrpc_send_ping(struct rxrpc_call *call, struct sk_buff *skb) if (call->peer->rtt_count < 3 || ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), now)) - rxrpc_propose_ACK(call, RXRPC_ACK_PING, sp->hdr.serial, - true, true, - rxrpc_propose_ack_ping_for_params); + rxrpc_send_ACK(call, RXRPC_ACK_PING, sp->hdr.serial, + rxrpc_propose_ack_ping_for_params); } /* @@ -325,7 +324,8 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, call->security = conn->security; call->security_ix = conn->security_ix; call->peer = rxrpc_get_peer(conn->params.peer); - call->cong_cwnd = call->peer->cong_cwnd; + call->cong_ssthresh = call->peer->cong_ssthresh; + call->tx_last_sent = ktime_get_real(); return call; } diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 2a93e7b5fbd0..1e21a708390e 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -20,127 +20,103 @@ /* * Propose a PING ACK be sent. */ -static void rxrpc_propose_ping(struct rxrpc_call *call, - bool immediate, bool background) +void rxrpc_propose_ping(struct rxrpc_call *call, u32 serial, + enum rxrpc_propose_ack_trace why) { - if (immediate) { - if (background && - !test_and_set_bit(RXRPC_CALL_EV_PING, &call->events)) - rxrpc_queue_call(call); - } else { - unsigned long now = jiffies; - unsigned long ping_at = now + rxrpc_idle_ack_delay; - - if (time_before(ping_at, call->ping_at)) { - WRITE_ONCE(call->ping_at, ping_at); - rxrpc_reduce_call_timer(call, ping_at, now, - rxrpc_timer_set_for_ping); - } + unsigned long now = jiffies; + unsigned long ping_at = now + rxrpc_idle_ack_delay; + + if (time_before(ping_at, call->ping_at)) { + WRITE_ONCE(call->ping_at, ping_at); + rxrpc_reduce_call_timer(call, ping_at, now, + rxrpc_timer_set_for_ping); + trace_rxrpc_propose_ack(call, why, RXRPC_ACK_PING, serial); } } /* - * propose an ACK be sent + * Propose a DELAY ACK be sent in the future. */ -static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, - u32 serial, bool immediate, bool background, - enum rxrpc_propose_ack_trace why) +void rxrpc_propose_delay_ACK(struct rxrpc_call *call, rxrpc_serial_t serial, + enum rxrpc_propose_ack_trace why) { - enum rxrpc_propose_ack_outcome outcome = rxrpc_propose_ack_use; unsigned long expiry = rxrpc_soft_ack_delay; - s8 prior = rxrpc_ack_priority[ack_reason]; - - /* Pings are handled specially because we don't want to accidentally - * lose a ping response by subsuming it into a ping. - */ - if (ack_reason == RXRPC_ACK_PING) { - rxrpc_propose_ping(call, immediate, background); - goto trace; + unsigned long now = jiffies, ack_at; + + call->ackr_serial = serial; + + if (rxrpc_soft_ack_delay < expiry) + expiry = rxrpc_soft_ack_delay; + if (call->peer->srtt_us != 0) + ack_at = usecs_to_jiffies(call->peer->srtt_us >> 3); + else + ack_at = expiry; + + ack_at += READ_ONCE(call->tx_backoff); + ack_at += now; + if (time_before(ack_at, call->delay_ack_at)) { + WRITE_ONCE(call->delay_ack_at, ack_at); + rxrpc_reduce_call_timer(call, ack_at, now, + rxrpc_timer_set_for_ack); } - /* Update DELAY, IDLE, REQUESTED and PING_RESPONSE ACK serial - * numbers, but we don't alter the timeout. - */ - _debug("prior %u %u vs %u %u", - ack_reason, prior, - call->ackr_reason, rxrpc_ack_priority[call->ackr_reason]); - if (ack_reason == call->ackr_reason) { - if (RXRPC_ACK_UPDATEABLE & (1 << ack_reason)) { - outcome = rxrpc_propose_ack_update; - call->ackr_serial = serial; - } - if (!immediate) - goto trace; - } else if (prior > rxrpc_ack_priority[call->ackr_reason]) { - call->ackr_reason = ack_reason; - call->ackr_serial = serial; - } else { - outcome = rxrpc_propose_ack_subsume; + trace_rxrpc_propose_ack(call, why, RXRPC_ACK_DELAY, serial); +} + +/* + * Queue an ACK for immediate transmission. + */ +void rxrpc_send_ACK(struct rxrpc_call *call, u8 ack_reason, + rxrpc_serial_t serial, enum rxrpc_propose_ack_trace why) +{ + struct rxrpc_local *local = call->conn->params.local; + struct rxrpc_txbuf *txb; + + if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) + return; + if (ack_reason == RXRPC_ACK_DELAY && + test_and_set_bit(RXRPC_CALL_DELAY_ACK_PENDING, &call->flags)) { + trace_rxrpc_drop_ack(call, why, ack_reason, serial, false); + return; } - switch (ack_reason) { - case RXRPC_ACK_REQUESTED: - if (rxrpc_requested_ack_delay < expiry) - expiry = rxrpc_requested_ack_delay; - if (serial == 1) - immediate = false; - break; - - case RXRPC_ACK_DELAY: - if (rxrpc_soft_ack_delay < expiry) - expiry = rxrpc_soft_ack_delay; - break; - - case RXRPC_ACK_IDLE: - if (rxrpc_idle_ack_delay < expiry) - expiry = rxrpc_idle_ack_delay; - break; - - default: - immediate = true; - break; + rxrpc_inc_stat(call->rxnet, stat_tx_acks[ack_reason]); + + txb = rxrpc_alloc_txbuf(call, RXRPC_PACKET_TYPE_ACK, + in_softirq() ? GFP_ATOMIC | __GFP_NOWARN : GFP_NOFS); + if (!txb) { + kleave(" = -ENOMEM"); + return; } - if (test_bit(RXRPC_CALL_EV_ACK, &call->events)) { - _debug("already scheduled"); - } else if (immediate || expiry == 0) { - _debug("immediate ACK %lx", call->events); - if (!test_and_set_bit(RXRPC_CALL_EV_ACK, &call->events) && - background) - rxrpc_queue_call(call); - } else { - unsigned long now = jiffies, ack_at; - - if (call->peer->srtt_us != 0) - ack_at = usecs_to_jiffies(call->peer->srtt_us >> 3); - else - ack_at = expiry; - - ack_at += READ_ONCE(call->tx_backoff); - ack_at += now; - if (time_before(ack_at, call->ack_at)) { - WRITE_ONCE(call->ack_at, ack_at); - rxrpc_reduce_call_timer(call, ack_at, now, - rxrpc_timer_set_for_ack); - } + txb->ack_why = why; + txb->wire.seq = 0; + txb->wire.type = RXRPC_PACKET_TYPE_ACK; + txb->wire.flags |= RXRPC_SLOW_START_OK; + txb->ack.bufferSpace = 0; + txb->ack.maxSkew = 0; + txb->ack.firstPacket = 0; + txb->ack.previousPacket = 0; + txb->ack.serial = htonl(serial); + txb->ack.reason = ack_reason; + txb->ack.nAcks = 0; + + if (!rxrpc_try_get_call(call, rxrpc_call_got)) { + rxrpc_put_txbuf(txb, rxrpc_txbuf_put_nomem); + return; } -trace: - trace_rxrpc_propose_ack(call, why, ack_reason, serial, immediate, - background, outcome); -} + spin_lock_bh(&local->ack_tx_lock); + list_add_tail(&txb->tx_link, &local->ack_tx_queue); + spin_unlock_bh(&local->ack_tx_lock); + trace_rxrpc_send_ack(call, why, ack_reason, serial); -/* - * propose an ACK be sent, locking the call structure - */ -void rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, - u32 serial, bool immediate, bool background, - enum rxrpc_propose_ack_trace why) -{ - spin_lock_bh(&call->lock); - __rxrpc_propose_ACK(call, ack_reason, serial, - immediate, background, why); - spin_unlock_bh(&call->lock); + if (in_task()) { + rxrpc_transmit_ack_packets(call->peer->local); + } else { + rxrpc_get_local(local); + rxrpc_queue_local(local); + } } /* @@ -156,62 +132,131 @@ static void rxrpc_congestion_timeout(struct rxrpc_call *call) */ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) { - struct sk_buff *skb; + struct rxrpc_ackpacket *ack = NULL; + struct rxrpc_txbuf *txb; + struct sk_buff *ack_skb = NULL; unsigned long resend_at; - rxrpc_seq_t cursor, seq, top; + rxrpc_seq_t transmitted = READ_ONCE(call->tx_transmitted); ktime_t now, max_age, oldest, ack_ts; - int ix; - u8 annotation, anno_type, retrans = 0, unacked = 0; + bool unacked = false; + unsigned int i; + LIST_HEAD(retrans_queue); - _enter("{%d,%d}", call->tx_hard_ack, call->tx_top); + _enter("{%d,%d}", call->acks_hard_ack, call->tx_top); now = ktime_get_real(); max_age = ktime_sub_us(now, jiffies_to_usecs(call->peer->rto_j)); + oldest = now; + + /* See if there's an ACK saved with a soft-ACK table in it. */ + if (call->acks_soft_tbl) { + spin_lock_bh(&call->acks_ack_lock); + ack_skb = call->acks_soft_tbl; + if (ack_skb) { + rxrpc_get_skb(ack_skb, rxrpc_skb_ack); + ack = (void *)ack_skb->data + sizeof(struct rxrpc_wire_header); + } + spin_unlock_bh(&call->acks_ack_lock); + } - spin_lock_bh(&call->lock); + if (list_empty(&call->tx_buffer)) + goto no_resend; - cursor = call->tx_hard_ack; - top = call->tx_top; - ASSERT(before_eq(cursor, top)); - if (cursor == top) - goto out_unlock; + spin_lock(&call->tx_lock); - /* Scan the packet list without dropping the lock and decide which of - * the packets in the Tx buffer we're going to resend and what the new - * resend timeout will be. - */ - trace_rxrpc_resend(call, (cursor + 1) & RXRPC_RXTX_BUFF_MASK); - oldest = now; - for (seq = cursor + 1; before_eq(seq, top); seq++) { - ix = seq & RXRPC_RXTX_BUFF_MASK; - annotation = call->rxtx_annotations[ix]; - anno_type = annotation & RXRPC_TX_ANNO_MASK; - annotation &= ~RXRPC_TX_ANNO_MASK; - if (anno_type == RXRPC_TX_ANNO_ACK) - continue; + if (list_empty(&call->tx_buffer)) + goto no_further_resend; + + trace_rxrpc_resend(call); + txb = list_first_entry(&call->tx_buffer, struct rxrpc_txbuf, call_link); - skb = call->rxtx_buffer[ix]; - rxrpc_see_skb(skb, rxrpc_skb_seen); + /* Scan the soft ACK table without dropping the lock and resend any + * explicitly NAK'd packets. + */ + if (ack) { + for (i = 0; i < ack->nAcks; i++) { + rxrpc_seq_t seq; - if (anno_type == RXRPC_TX_ANNO_UNACK) { - if (ktime_after(skb->tstamp, max_age)) { - if (ktime_before(skb->tstamp, oldest)) - oldest = skb->tstamp; + if (ack->acks[i] & 1) continue; + seq = ntohl(ack->firstPacket) + i; + if (after(txb->seq, transmitted)) + break; + if (after(txb->seq, seq)) + continue; /* A new hard ACK probably came in */ + list_for_each_entry_from(txb, &call->tx_buffer, call_link) { + if (txb->seq == seq) + goto found_txb; + } + goto no_further_resend; + + found_txb: + if (after(ntohl(txb->wire.serial), call->acks_highest_serial)) + continue; /* Ack point not yet reached */ + + rxrpc_see_txbuf(txb, rxrpc_txbuf_see_unacked); + + if (list_empty(&txb->tx_link)) { + rxrpc_get_txbuf(txb, rxrpc_txbuf_get_retrans); + rxrpc_get_call(call, rxrpc_call_got_tx); + list_add_tail(&txb->tx_link, &retrans_queue); + set_bit(RXRPC_TXBUF_RESENT, &txb->flags); } - if (!(annotation & RXRPC_TX_ANNO_RESENT)) - unacked++; + + trace_rxrpc_retransmit(call, txb->seq, + ktime_to_ns(ktime_sub(txb->last_sent, + max_age))); + + if (list_is_last(&txb->call_link, &call->tx_buffer)) + goto no_further_resend; + txb = list_next_entry(txb, call_link); + } + } + + /* Fast-forward through the Tx queue to the point the peer says it has + * seen. Anything between the soft-ACK table and that point will get + * ACK'd or NACK'd in due course, so don't worry about it here; here we + * need to consider retransmitting anything beyond that point. + * + * Note that ACK for a packet can beat the update of tx_transmitted. + */ + if (after_eq(READ_ONCE(call->acks_prev_seq), READ_ONCE(call->tx_transmitted))) + goto no_further_resend; + + list_for_each_entry_from(txb, &call->tx_buffer, call_link) { + if (before_eq(txb->seq, READ_ONCE(call->acks_prev_seq))) + continue; + if (after(txb->seq, READ_ONCE(call->tx_transmitted))) + break; /* Not transmitted yet */ + + if (ack && ack->reason == RXRPC_ACK_PING_RESPONSE && + before(ntohl(txb->wire.serial), ntohl(ack->serial))) + goto do_resend; /* Wasn't accounted for by a more recent ping. */ + + if (ktime_after(txb->last_sent, max_age)) { + if (ktime_before(txb->last_sent, oldest)) + oldest = txb->last_sent; + continue; } - /* Okay, we need to retransmit a packet. */ - call->rxtx_annotations[ix] = RXRPC_TX_ANNO_RETRANS | annotation; - retrans++; - trace_rxrpc_retransmit(call, seq, annotation | anno_type, - ktime_to_ns(ktime_sub(skb->tstamp, max_age))); + do_resend: + unacked = true; + if (list_empty(&txb->tx_link)) { + rxrpc_get_txbuf(txb, rxrpc_txbuf_get_retrans); + list_add_tail(&txb->tx_link, &retrans_queue); + set_bit(RXRPC_TXBUF_RESENT, &txb->flags); + rxrpc_inc_stat(call->rxnet, stat_tx_data_retrans); + } } +no_further_resend: + spin_unlock(&call->tx_lock); +no_resend: + rxrpc_free_skb(ack_skb, rxrpc_skb_freed); + resend_at = nsecs_to_jiffies(ktime_to_ns(ktime_sub(now, oldest))); - resend_at += jiffies + rxrpc_get_rto_backoff(call->peer, retrans); + resend_at += jiffies + rxrpc_get_rto_backoff(call->peer, + !list_empty(&retrans_queue)); WRITE_ONCE(call->resend_at, resend_at); if (unacked) @@ -221,62 +266,28 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) * that an ACK got lost somewhere. Send a ping to find out instead of * retransmitting data. */ - if (!retrans) { + if (list_empty(&retrans_queue)) { rxrpc_reduce_call_timer(call, resend_at, now_j, rxrpc_timer_set_for_resend); - spin_unlock_bh(&call->lock); ack_ts = ktime_sub(now, call->acks_latest_ts); if (ktime_to_us(ack_ts) < (call->peer->srtt_us >> 3)) goto out; - rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, true, false, - rxrpc_propose_ack_ping_for_lost_ack); - rxrpc_send_ack_packet(call, true, NULL); + rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, + rxrpc_propose_ack_ping_for_lost_ack); goto out; } - /* Now go through the Tx window and perform the retransmissions. We - * have to drop the lock for each send. If an ACK comes in whilst the - * lock is dropped, it may clear some of the retransmission markers for - * packets that it soft-ACKs. - */ - for (seq = cursor + 1; before_eq(seq, top); seq++) { - ix = seq & RXRPC_RXTX_BUFF_MASK; - annotation = call->rxtx_annotations[ix]; - anno_type = annotation & RXRPC_TX_ANNO_MASK; - if (anno_type != RXRPC_TX_ANNO_RETRANS) - continue; - - /* We need to reset the retransmission state, but we need to do - * so before we drop the lock as a new ACK/NAK may come in and - * confuse things - */ - annotation &= ~RXRPC_TX_ANNO_MASK; - annotation |= RXRPC_TX_ANNO_UNACK | RXRPC_TX_ANNO_RESENT; - call->rxtx_annotations[ix] = annotation; - - skb = call->rxtx_buffer[ix]; - if (!skb) - continue; - - rxrpc_get_skb(skb, rxrpc_skb_got); - spin_unlock_bh(&call->lock); - - if (rxrpc_send_data_packet(call, skb, true) < 0) { - rxrpc_free_skb(skb, rxrpc_skb_freed); - return; - } + while ((txb = list_first_entry_or_null(&retrans_queue, + struct rxrpc_txbuf, tx_link))) { + list_del_init(&txb->tx_link); + rxrpc_send_data_packet(call, txb); + rxrpc_put_txbuf(txb, rxrpc_txbuf_put_trans); - if (rxrpc_is_client_call(call)) - rxrpc_expose_client_call(call); - - rxrpc_free_skb(skb, rxrpc_skb_freed); - spin_lock_bh(&call->lock); - if (after(call->tx_hard_ack, seq)) - seq = call->tx_hard_ack; + trace_rxrpc_retransmit(call, txb->seq, + ktime_to_ns(ktime_sub(txb->last_sent, + max_age))); } -out_unlock: - spin_unlock_bh(&call->lock); out: _leave(""); } @@ -288,9 +299,9 @@ void rxrpc_process_call(struct work_struct *work) { struct rxrpc_call *call = container_of(work, struct rxrpc_call, processor); - rxrpc_serial_t *send_ack; unsigned long now, next, t; unsigned int iterations = 0; + rxrpc_serial_t ackr_serial; rxrpc_see_call(call); @@ -309,6 +320,9 @@ recheck_state: goto recheck_state; } + if (READ_ONCE(call->acks_hard_ack) != call->tx_bottom) + rxrpc_shrink_call_tx_buffer(call); + if (call->state == RXRPC_CALL_COMPLETE) { rxrpc_delete_call_timer(call); goto out_put; @@ -335,11 +349,13 @@ recheck_state: set_bit(RXRPC_CALL_EV_EXPIRED, &call->events); } - t = READ_ONCE(call->ack_at); + t = READ_ONCE(call->delay_ack_at); if (time_after_eq(now, t)) { trace_rxrpc_timer(call, rxrpc_timer_exp_ack, now); - cmpxchg(&call->ack_at, t, now + MAX_JIFFY_OFFSET); - set_bit(RXRPC_CALL_EV_ACK, &call->events); + cmpxchg(&call->delay_ack_at, t, now + MAX_JIFFY_OFFSET); + ackr_serial = xchg(&call->ackr_serial, 0); + rxrpc_send_ACK(call, RXRPC_ACK_DELAY, ackr_serial, + rxrpc_propose_ack_ping_for_lost_ack); } t = READ_ONCE(call->ack_lost_at); @@ -353,16 +369,16 @@ recheck_state: if (time_after_eq(now, t)) { trace_rxrpc_timer(call, rxrpc_timer_exp_keepalive, now); cmpxchg(&call->keepalive_at, t, now + MAX_JIFFY_OFFSET); - rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, true, true, - rxrpc_propose_ack_ping_for_keepalive); - set_bit(RXRPC_CALL_EV_PING, &call->events); + rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, + rxrpc_propose_ack_ping_for_keepalive); } t = READ_ONCE(call->ping_at); if (time_after_eq(now, t)) { trace_rxrpc_timer(call, rxrpc_timer_exp_ping, now); cmpxchg(&call->ping_at, t, now + MAX_JIFFY_OFFSET); - set_bit(RXRPC_CALL_EV_PING, &call->events); + rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, + rxrpc_propose_ack_ping_for_keepalive); } t = READ_ONCE(call->resend_at); @@ -385,25 +401,10 @@ recheck_state: goto recheck_state; } - send_ack = NULL; if (test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events)) { call->acks_lost_top = call->tx_top; - rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, true, false, - rxrpc_propose_ack_ping_for_lost_ack); - send_ack = &call->acks_lost_ping; - } - - if (test_and_clear_bit(RXRPC_CALL_EV_ACK, &call->events) || - send_ack) { - if (call->ackr_reason) { - rxrpc_send_ack_packet(call, false, send_ack); - goto recheck_state; - } - } - - if (test_and_clear_bit(RXRPC_CALL_EV_PING, &call->events)) { - rxrpc_send_ack_packet(call, true, NULL); - goto recheck_state; + rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, + rxrpc_propose_ack_ping_for_lost_ack); } if (test_and_clear_bit(RXRPC_CALL_EV_RESEND, &call->events) && @@ -419,7 +420,7 @@ recheck_state: set(call->expect_req_by); set(call->expect_term_by); - set(call->ack_at); + set(call->delay_ack_at); set(call->ack_lost_at); set(call->resend_at); set(call->keepalive_at); diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 6401cdf7a624..1befe22cd301 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -52,7 +52,7 @@ static void rxrpc_call_timer_expired(struct timer_list *t) _enter("%d", call->debug_id); if (call->state < RXRPC_CALL_COMPLETE) { - trace_rxrpc_timer(call, rxrpc_timer_expired, jiffies); + trace_rxrpc_timer_expired(call, jiffies); __rxrpc_queue_call(call); } else { rxrpc_put_call(call, rxrpc_call_put); @@ -129,16 +129,6 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, if (!call) return NULL; - call->rxtx_buffer = kcalloc(RXRPC_RXTX_BUFF_SIZE, - sizeof(struct sk_buff *), - gfp); - if (!call->rxtx_buffer) - goto nomem; - - call->rxtx_annotations = kcalloc(RXRPC_RXTX_BUFF_SIZE, sizeof(u8), gfp); - if (!call->rxtx_annotations) - goto nomem_2; - mutex_init(&call->user_mutex); /* Prevent lockdep reporting a deadlock false positive between the afs @@ -155,37 +145,39 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, INIT_LIST_HEAD(&call->accept_link); INIT_LIST_HEAD(&call->recvmsg_link); INIT_LIST_HEAD(&call->sock_link); + INIT_LIST_HEAD(&call->tx_buffer); + skb_queue_head_init(&call->recvmsg_queue); + skb_queue_head_init(&call->rx_oos_queue); init_waitqueue_head(&call->waitq); - spin_lock_init(&call->lock); spin_lock_init(&call->notify_lock); + spin_lock_init(&call->tx_lock); spin_lock_init(&call->input_lock); + spin_lock_init(&call->acks_ack_lock); rwlock_init(&call->state_lock); refcount_set(&call->ref, 1); call->debug_id = debug_id; call->tx_total_len = -1; call->next_rx_timo = 20 * HZ; call->next_req_timo = 1 * HZ; + atomic64_set(&call->ackr_window, 0x100000001ULL); memset(&call->sock_node, 0xed, sizeof(call->sock_node)); - /* Leave space in the ring to handle a maxed-out jumbo packet */ call->rx_winsize = rxrpc_rx_window_size; call->tx_winsize = 16; - call->rx_expect_next = 1; - call->cong_cwnd = 2; - call->cong_ssthresh = RXRPC_RXTX_BUFF_SIZE - 1; + if (RXRPC_TX_SMSS > 2190) + call->cong_cwnd = 2; + else if (RXRPC_TX_SMSS > 1095) + call->cong_cwnd = 3; + else + call->cong_cwnd = 4; + call->cong_ssthresh = RXRPC_TX_MAX_WINDOW; call->rxnet = rxnet; call->rtt_avail = RXRPC_CALL_RTT_AVAIL_MASK; atomic_inc(&rxnet->nr_calls); return call; - -nomem_2: - kfree(call->rxtx_buffer); -nomem: - kmem_cache_free(rxrpc_call_jar, call); - return NULL; } /* @@ -206,7 +198,6 @@ static struct rxrpc_call *rxrpc_alloc_client_call(struct rxrpc_sock *rx, return ERR_PTR(-ENOMEM); call->state = RXRPC_CALL_CLIENT_AWAIT_CONN; call->service_id = srx->srx_service; - call->tx_phase = true; now = ktime_get_real(); call->acks_latest_ts = now; call->cong_tstamp = now; @@ -223,7 +214,7 @@ static void rxrpc_start_call_timer(struct rxrpc_call *call) unsigned long now = jiffies; unsigned long j = now + MAX_JIFFY_OFFSET; - call->ack_at = j; + call->delay_ack_at = j; call->ack_lost_at = j; call->resend_at = j; call->ping_at = j; @@ -510,16 +501,12 @@ void rxrpc_get_call(struct rxrpc_call *call, enum rxrpc_call_trace op) } /* - * Clean up the RxTx skb ring. + * Clean up the Rx skb ring. */ static void rxrpc_cleanup_ring(struct rxrpc_call *call) { - int i; - - for (i = 0; i < RXRPC_RXTX_BUFF_SIZE; i++) { - rxrpc_free_skb(call->rxtx_buffer[i], rxrpc_skb_cleaned); - call->rxtx_buffer[i] = NULL; - } + skb_queue_purge(&call->recvmsg_queue); + skb_queue_purge(&call->rx_oos_queue); } /* @@ -539,10 +526,8 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE); - spin_lock_bh(&call->lock); if (test_and_set_bit(RXRPC_CALL_RELEASED, &call->flags)) BUG(); - spin_unlock_bh(&call->lock); rxrpc_put_call_slot(call); rxrpc_delete_call_timer(call); @@ -656,8 +641,6 @@ static void rxrpc_destroy_call(struct work_struct *work) rxrpc_put_connection(call->conn); rxrpc_put_peer(call->peer); - kfree(call->rxtx_buffer); - kfree(call->rxtx_annotations); kmem_cache_free(rxrpc_call_jar, call); if (atomic_dec_and_test(&rxnet->nr_calls)) wake_up_var(&rxnet->nr_calls); @@ -684,6 +667,8 @@ static void rxrpc_rcu_destroy_call(struct rcu_head *rcu) */ void rxrpc_cleanup_call(struct rxrpc_call *call) { + struct rxrpc_txbuf *txb; + _net("DESTROY CALL %d", call->debug_id); memset(&call->sock_node, 0xcd, sizeof(call->sock_node)); @@ -692,7 +677,13 @@ void rxrpc_cleanup_call(struct rxrpc_call *call) ASSERT(test_bit(RXRPC_CALL_RELEASED, &call->flags)); rxrpc_cleanup_ring(call); - rxrpc_free_skb(call->tx_pending, rxrpc_skb_cleaned); + while ((txb = list_first_entry_or_null(&call->tx_buffer, + struct rxrpc_txbuf, call_link))) { + list_del(&txb->call_link); + rxrpc_put_txbuf(txb, rxrpc_txbuf_put_cleaned); + } + rxrpc_put_txbuf(call->tx_pending, rxrpc_txbuf_put_cleaned); + rxrpc_free_skb(call->acks_soft_tbl, rxrpc_skb_cleaned); call_rcu(&call->rcu, rxrpc_rcu_destroy_call); } diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index 3c9eeb5b750c..f020f308ed9e 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -363,7 +363,8 @@ static struct rxrpc_bundle *rxrpc_prep_call(struct rxrpc_sock *rx, if (!cp->peer) goto error; - call->cong_cwnd = cp->peer->cong_cwnd; + call->tx_last_sent = ktime_get_real(); + call->cong_ssthresh = cp->peer->cong_ssthresh; if (call->cong_cwnd >= call->cong_ssthresh) call->cong_mode = RXRPC_CALL_CONGEST_AVOIDANCE; else diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 22089e37e97f..156bd26daf74 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -175,7 +175,7 @@ void __rxrpc_disconnect_call(struct rxrpc_connection *conn, trace_rxrpc_disconnect_call(call); switch (call->completion) { case RXRPC_CALL_SUCCEEDED: - chan->last_seq = call->rx_hard_ack; + chan->last_seq = call->rx_highest_seq; chan->last_type = RXRPC_PACKET_TYPE_ACK; break; case RXRPC_CALL_LOCALLY_ABORTED: @@ -207,7 +207,7 @@ void rxrpc_disconnect_call(struct rxrpc_call *call) { struct rxrpc_connection *conn = call->conn; - call->peer->cong_cwnd = call->cong_cwnd; + call->peer->cong_ssthresh = call->cong_ssthresh; if (!hlist_unhashed(&call->error_link)) { spin_lock_bh(&call->peer->lock); diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 721d847ba92b..bdf70b81addc 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -7,20 +7,6 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include <linux/module.h> -#include <linux/net.h> -#include <linux/skbuff.h> -#include <linux/errqueue.h> -#include <linux/udp.h> -#include <linux/in.h> -#include <linux/in6.h> -#include <linux/icmp.h> -#include <linux/gfp.h> -#include <net/sock.h> -#include <net/af_rxrpc.h> -#include <net/ip.h> -#include <net/udp.h> -#include <net/net_namespace.h> #include "ar-internal.h" static void rxrpc_proto_abort(const char *why, @@ -46,7 +32,7 @@ static void rxrpc_congestion_management(struct rxrpc_call *call, bool resend = false; summary->flight_size = - (call->tx_top - call->tx_hard_ack) - summary->nr_acks; + (call->tx_top - call->acks_hard_ack) - summary->nr_acks; if (test_and_clear_bit(RXRPC_CALL_RETRANS_TIMEOUT, &call->flags)) { summary->retrans_timeo = true; @@ -72,9 +58,28 @@ static void rxrpc_congestion_management(struct rxrpc_call *call, summary->cumulative_acks = cumulative_acks; summary->dup_acks = call->cong_dup_acks; + /* If we haven't transmitted anything for >1RTT, we should reset the + * congestion management state. + */ + if ((call->cong_mode == RXRPC_CALL_SLOW_START || + call->cong_mode == RXRPC_CALL_CONGEST_AVOIDANCE) && + ktime_before(ktime_add_us(call->tx_last_sent, + call->peer->srtt_us >> 3), + ktime_get_real()) + ) { + change = rxrpc_cong_idle_reset; + summary->mode = RXRPC_CALL_SLOW_START; + if (RXRPC_TX_SMSS > 2190) + summary->cwnd = 2; + else if (RXRPC_TX_SMSS > 1095) + summary->cwnd = 3; + else + summary->cwnd = 4; + } + switch (call->cong_mode) { case RXRPC_CALL_SLOW_START: - if (summary->nr_nacks > 0) + if (summary->saw_nacks) goto packet_loss_detected; if (summary->cumulative_acks > 0) cwnd += 1; @@ -85,7 +90,7 @@ static void rxrpc_congestion_management(struct rxrpc_call *call, goto out; case RXRPC_CALL_CONGEST_AVOIDANCE: - if (summary->nr_nacks > 0) + if (summary->saw_nacks) goto packet_loss_detected; /* We analyse the number of packets that get ACK'd per RTT @@ -104,7 +109,7 @@ static void rxrpc_congestion_management(struct rxrpc_call *call, goto out; case RXRPC_CALL_PACKET_LOSS: - if (summary->nr_nacks == 0) + if (!summary->saw_nacks) goto resume_normality; if (summary->new_low_nack) { @@ -142,7 +147,7 @@ static void rxrpc_congestion_management(struct rxrpc_call *call, } else { change = rxrpc_cong_progress; cwnd = call->cong_ssthresh; - if (summary->nr_nacks == 0) + if (!summary->saw_nacks) goto resume_normality; } goto out; @@ -164,8 +169,8 @@ resume_normality: out: cumulative_acks = 0; out_no_clear_ca: - if (cwnd >= RXRPC_RXTX_BUFF_SIZE - 1) - cwnd = RXRPC_RXTX_BUFF_SIZE - 1; + if (cwnd >= RXRPC_TX_MAX_WINDOW) + cwnd = RXRPC_TX_MAX_WINDOW; call->cong_cwnd = cwnd; call->cong_cumul_acks = cumulative_acks; trace_rxrpc_congest(call, summary, acked_serial, change); @@ -183,9 +188,8 @@ send_extra_data: /* Send some previously unsent DATA if we have some to advance the ACK * state. */ - if (call->rxtx_annotations[call->tx_top & RXRPC_RXTX_BUFF_MASK] & - RXRPC_TX_ANNO_LAST || - summary->nr_acks != call->tx_top - call->tx_hard_ack) { + if (test_bit(RXRPC_CALL_TX_LAST, &call->flags) || + summary->nr_acks != call->tx_top - call->acks_hard_ack) { call->cong_extra++; wake_up(&call->waitq); } @@ -198,53 +202,39 @@ send_extra_data: static bool rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to, struct rxrpc_ack_summary *summary) { - struct sk_buff *skb, *list = NULL; + struct rxrpc_txbuf *txb; bool rot_last = false; - int ix; - u8 annotation; - - if (call->acks_lowest_nak == call->tx_hard_ack) { - call->acks_lowest_nak = to; - } else if (before_eq(call->acks_lowest_nak, to)) { - summary->new_low_nack = true; - call->acks_lowest_nak = to; - } - - spin_lock(&call->lock); - - while (before(call->tx_hard_ack, to)) { - call->tx_hard_ack++; - ix = call->tx_hard_ack & RXRPC_RXTX_BUFF_MASK; - skb = call->rxtx_buffer[ix]; - annotation = call->rxtx_annotations[ix]; - rxrpc_see_skb(skb, rxrpc_skb_rotated); - call->rxtx_buffer[ix] = NULL; - call->rxtx_annotations[ix] = 0; - skb->next = list; - list = skb; - if (annotation & RXRPC_TX_ANNO_LAST) { + list_for_each_entry_rcu(txb, &call->tx_buffer, call_link, false) { + if (before_eq(txb->seq, call->acks_hard_ack)) + continue; + summary->nr_rot_new_acks++; + if (test_bit(RXRPC_TXBUF_LAST, &txb->flags)) { set_bit(RXRPC_CALL_TX_LAST, &call->flags); rot_last = true; } - if ((annotation & RXRPC_TX_ANNO_MASK) != RXRPC_TX_ANNO_ACK) - summary->nr_rot_new_acks++; + if (txb->seq == to) + break; } - spin_unlock(&call->lock); + if (rot_last) + set_bit(RXRPC_CALL_TX_ALL_ACKED, &call->flags); - trace_rxrpc_transmit(call, (rot_last ? - rxrpc_transmit_rotate_last : - rxrpc_transmit_rotate)); - wake_up(&call->waitq); + _enter("%x,%x,%x,%d", to, call->acks_hard_ack, call->tx_top, rot_last); - while (list) { - skb = list; - list = skb->next; - skb_mark_not_on_list(skb); - rxrpc_free_skb(skb, rxrpc_skb_freed); + if (call->acks_lowest_nak == call->acks_hard_ack) { + call->acks_lowest_nak = to; + } else if (after(to, call->acks_lowest_nak)) { + summary->new_low_nack = true; + call->acks_lowest_nak = to; } + smp_store_release(&call->acks_hard_ack, to); + + trace_rxrpc_txqueue(call, (rot_last ? + rxrpc_txqueue_rotate_last : + rxrpc_txqueue_rotate)); + wake_up(&call->waitq); return rot_last; } @@ -284,9 +274,9 @@ static bool rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun, write_unlock(&call->state_lock); if (state == RXRPC_CALL_CLIENT_AWAIT_REPLY) - trace_rxrpc_transmit(call, rxrpc_transmit_await_reply); + trace_rxrpc_txqueue(call, rxrpc_txqueue_await_reply); else - trace_rxrpc_transmit(call, rxrpc_transmit_end); + trace_rxrpc_txqueue(call, rxrpc_txqueue_end); _leave(" = ok"); return true; @@ -307,13 +297,10 @@ static bool rxrpc_receiving_reply(struct rxrpc_call *call) rxrpc_seq_t top = READ_ONCE(call->tx_top); if (call->ackr_reason) { - spin_lock_bh(&call->lock); - call->ackr_reason = 0; - spin_unlock_bh(&call->lock); now = jiffies; timo = now + MAX_JIFFY_OFFSET; WRITE_ONCE(call->resend_at, timo); - WRITE_ONCE(call->ack_at, timo); + WRITE_ONCE(call->delay_ack_at, timo); trace_rxrpc_timer(call, rxrpc_timer_init_for_reply, now); } @@ -323,85 +310,230 @@ static bool rxrpc_receiving_reply(struct rxrpc_call *call) return false; } } - if (!rxrpc_end_tx_phase(call, true, "ETD")) - return false; - call->tx_phase = false; - return true; + return rxrpc_end_tx_phase(call, true, "ETD"); +} + +static void rxrpc_input_update_ack_window(struct rxrpc_call *call, + rxrpc_seq_t window, rxrpc_seq_t wtop) +{ + atomic64_set_release(&call->ackr_window, ((u64)wtop) << 32 | window); } /* - * Scan a data packet to validate its structure and to work out how many - * subpackets it contains. - * - * A jumbo packet is a collection of consecutive packets glued together with - * little headers between that indicate how to change the initial header for - * each subpacket. - * - * RXRPC_JUMBO_PACKET must be set on all but the last subpacket - and all but - * the last are RXRPC_JUMBO_DATALEN in size. The last subpacket may be of any - * size. + * Push a DATA packet onto the Rx queue. */ -static bool rxrpc_validate_data(struct sk_buff *skb) +static void rxrpc_input_queue_data(struct rxrpc_call *call, struct sk_buff *skb, + rxrpc_seq_t window, rxrpc_seq_t wtop, + enum rxrpc_receive_trace why) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - unsigned int offset = sizeof(struct rxrpc_wire_header); - unsigned int len = skb->len; - u8 flags = sp->hdr.flags; + bool last = sp->hdr.flags & RXRPC_LAST_PACKET; - for (;;) { - if (flags & RXRPC_REQUEST_ACK) - __set_bit(sp->nr_subpackets, sp->rx_req_ack); - sp->nr_subpackets++; + __skb_queue_tail(&call->recvmsg_queue, skb); + rxrpc_input_update_ack_window(call, window, wtop); - if (!(flags & RXRPC_JUMBO_PACKET)) - break; + trace_rxrpc_receive(call, last ? why + 1 : why, sp->hdr.serial, sp->hdr.seq); +} - if (len - offset < RXRPC_JUMBO_SUBPKTLEN) - goto protocol_error; - if (flags & RXRPC_LAST_PACKET) - goto protocol_error; - offset += RXRPC_JUMBO_DATALEN; - if (skb_copy_bits(skb, offset, &flags, 1) < 0) - goto protocol_error; - offset += sizeof(struct rxrpc_jumbo_header); +/* + * Process a DATA packet. + */ +static void rxrpc_input_data_one(struct rxrpc_call *call, struct sk_buff *skb) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + struct sk_buff *oos; + rxrpc_serial_t serial = sp->hdr.serial; + u64 win = atomic64_read(&call->ackr_window); + rxrpc_seq_t window = lower_32_bits(win); + rxrpc_seq_t wtop = upper_32_bits(win); + rxrpc_seq_t wlimit = window + call->rx_winsize - 1; + rxrpc_seq_t seq = sp->hdr.seq; + bool last = sp->hdr.flags & RXRPC_LAST_PACKET; + int ack_reason = -1; + + rxrpc_inc_stat(call->rxnet, stat_rx_data); + if (sp->hdr.flags & RXRPC_REQUEST_ACK) + rxrpc_inc_stat(call->rxnet, stat_rx_data_reqack); + if (sp->hdr.flags & RXRPC_JUMBO_PACKET) + rxrpc_inc_stat(call->rxnet, stat_rx_data_jumbo); + + if (last) { + if (test_and_set_bit(RXRPC_CALL_RX_LAST, &call->flags) && + seq + 1 != wtop) { + rxrpc_proto_abort("LSN", call, seq); + goto err_free; + } + } else { + if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) && + after_eq(seq, wtop)) { + pr_warn("Packet beyond last: c=%x q=%x window=%x-%x wlimit=%x\n", + call->debug_id, seq, window, wtop, wlimit); + rxrpc_proto_abort("LSA", call, seq); + goto err_free; + } } - if (flags & RXRPC_LAST_PACKET) - sp->rx_flags |= RXRPC_SKB_INCL_LAST; - return true; + if (after(seq, call->rx_highest_seq)) + call->rx_highest_seq = seq; -protocol_error: - return false; + trace_rxrpc_rx_data(call->debug_id, seq, serial, sp->hdr.flags); + + if (before(seq, window)) { + ack_reason = RXRPC_ACK_DUPLICATE; + goto send_ack; + } + if (after(seq, wlimit)) { + ack_reason = RXRPC_ACK_EXCEEDS_WINDOW; + goto send_ack; + } + + /* Queue the packet. */ + if (seq == window) { + rxrpc_seq_t reset_from; + bool reset_sack = false; + + if (sp->hdr.flags & RXRPC_REQUEST_ACK) + ack_reason = RXRPC_ACK_REQUESTED; + /* Send an immediate ACK if we fill in a hole */ + else if (!skb_queue_empty(&call->rx_oos_queue)) + ack_reason = RXRPC_ACK_DELAY; + + window++; + if (after(window, wtop)) + wtop = window; + + spin_lock(&call->recvmsg_queue.lock); + rxrpc_input_queue_data(call, skb, window, wtop, rxrpc_receive_queue); + skb = NULL; + + while ((oos = skb_peek(&call->rx_oos_queue))) { + struct rxrpc_skb_priv *osp = rxrpc_skb(oos); + + if (after(osp->hdr.seq, window)) + break; + + __skb_unlink(oos, &call->rx_oos_queue); + last = osp->hdr.flags & RXRPC_LAST_PACKET; + seq = osp->hdr.seq; + if (!reset_sack) { + reset_from = seq; + reset_sack = true; + } + + window++; + rxrpc_input_queue_data(call, oos, window, wtop, + rxrpc_receive_queue_oos); + } + + spin_unlock(&call->recvmsg_queue.lock); + + if (reset_sack) { + do { + call->ackr_sack_table[reset_from % RXRPC_SACK_SIZE] = 0; + } while (reset_from++, before(reset_from, window)); + } + } else { + bool keep = false; + + ack_reason = RXRPC_ACK_OUT_OF_SEQUENCE; + + if (!call->ackr_sack_table[seq % RXRPC_SACK_SIZE]) { + call->ackr_sack_table[seq % RXRPC_SACK_SIZE] = 1; + keep = 1; + } + + if (after(seq + 1, wtop)) { + wtop = seq + 1; + rxrpc_input_update_ack_window(call, window, wtop); + } + + if (!keep) { + ack_reason = RXRPC_ACK_DUPLICATE; + goto send_ack; + } + + skb_queue_walk(&call->rx_oos_queue, oos) { + struct rxrpc_skb_priv *osp = rxrpc_skb(oos); + + if (after(osp->hdr.seq, seq)) { + __skb_queue_before(&call->rx_oos_queue, oos, skb); + goto oos_queued; + } + } + + __skb_queue_tail(&call->rx_oos_queue, skb); + oos_queued: + trace_rxrpc_receive(call, last ? rxrpc_receive_oos_last : rxrpc_receive_oos, + sp->hdr.serial, sp->hdr.seq); + skb = NULL; + } + +send_ack: + if (ack_reason < 0 && + atomic_inc_return(&call->ackr_nr_unacked) > 2 && + test_and_set_bit(RXRPC_CALL_IDLE_ACK_PENDING, &call->flags)) { + ack_reason = RXRPC_ACK_IDLE; + } else if (ack_reason >= 0) { + set_bit(RXRPC_CALL_IDLE_ACK_PENDING, &call->flags); + } + + if (ack_reason >= 0) + rxrpc_send_ACK(call, ack_reason, serial, + rxrpc_propose_ack_input_data); + else + rxrpc_propose_delay_ACK(call, serial, + rxrpc_propose_ack_input_data); + +err_free: + rxrpc_free_skb(skb, rxrpc_skb_freed); } /* - * Handle reception of a duplicate packet. - * - * We have to take care to avoid an attack here whereby we're given a series of - * jumbograms, each with a sequence number one before the preceding one and - * filled up to maximum UDP size. If they never send us the first packet in - * the sequence, they can cause us to have to hold on to around 2MiB of kernel - * space until the call times out. - * - * We limit the space usage by only accepting three duplicate jumbo packets per - * call. After that, we tell the other side we're no longer accepting jumbos - * (that information is encoded in the ACK packet). + * Split a jumbo packet and file the bits separately. */ -static void rxrpc_input_dup_data(struct rxrpc_call *call, rxrpc_seq_t seq, - bool is_jumbo, bool *_jumbo_bad) +static bool rxrpc_input_split_jumbo(struct rxrpc_call *call, struct sk_buff *skb) { - /* Discard normal packets that are duplicates. */ - if (is_jumbo) - return; + struct rxrpc_jumbo_header jhdr; + struct rxrpc_skb_priv *sp = rxrpc_skb(skb), *jsp; + struct sk_buff *jskb; + unsigned int offset = sizeof(struct rxrpc_wire_header); + unsigned int len = skb->len - offset; - /* Skip jumbo subpackets that are duplicates. When we've had three or - * more partially duplicate jumbo packets, we refuse to take any more - * jumbos for this call. - */ - if (!*_jumbo_bad) { - call->nr_jumbo_bad++; - *_jumbo_bad = true; + while (sp->hdr.flags & RXRPC_JUMBO_PACKET) { + if (len < RXRPC_JUMBO_SUBPKTLEN) + goto protocol_error; + if (sp->hdr.flags & RXRPC_LAST_PACKET) + goto protocol_error; + if (skb_copy_bits(skb, offset + RXRPC_JUMBO_DATALEN, + &jhdr, sizeof(jhdr)) < 0) + goto protocol_error; + + jskb = skb_clone(skb, GFP_ATOMIC); + if (!jskb) { + kdebug("couldn't clone"); + return false; + } + rxrpc_new_skb(jskb, rxrpc_skb_cloned_jumbo); + jsp = rxrpc_skb(jskb); + jsp->offset = offset; + jsp->len = RXRPC_JUMBO_DATALEN; + rxrpc_input_data_one(call, jskb); + + sp->hdr.flags = jhdr.flags; + sp->hdr._rsvd = ntohs(jhdr._rsvd); + sp->hdr.seq++; + sp->hdr.serial++; + offset += RXRPC_JUMBO_SUBPKTLEN; + len -= RXRPC_JUMBO_SUBPKTLEN; } + + sp->offset = offset; + sp->len = len; + rxrpc_input_data_one(call, skb); + return true; + +protocol_error: + return false; } /* @@ -412,17 +544,15 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); enum rxrpc_call_state state; - unsigned int j, nr_subpackets, nr_unacked = 0; - rxrpc_serial_t serial = sp->hdr.serial, ack_serial = serial; - rxrpc_seq_t seq0 = sp->hdr.seq, hard_ack; - bool immediate_ack = false, jumbo_bad = false; - u8 ack = 0; + rxrpc_serial_t serial = sp->hdr.serial; + rxrpc_seq_t seq0 = sp->hdr.seq; - _enter("{%u,%u},{%u,%u}", - call->rx_hard_ack, call->rx_top, skb->len, seq0); + _enter("{%llx,%x},{%u,%x}", + atomic64_read(&call->ackr_window), call->rx_highest_seq, + skb->len, seq0); - _proto("Rx DATA %%%u { #%u f=%02x n=%u }", - sp->hdr.serial, seq0, sp->hdr.flags, sp->nr_subpackets); + _proto("Rx DATA %%%u { #%u f=%02x }", + sp->hdr.serial, seq0, sp->hdr.flags); state = READ_ONCE(call->state); if (state >= RXRPC_CALL_COMPLETE) { @@ -430,6 +560,24 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) return; } + /* Unshare the packet so that it can be modified for in-place + * decryption. + */ + if (sp->hdr.securityIndex != 0) { + struct sk_buff *nskb = skb_unshare(skb, GFP_ATOMIC); + if (!nskb) { + rxrpc_eaten_skb(skb, rxrpc_skb_unshared_nomem); + return; + } + + if (nskb != skb) { + rxrpc_eaten_skb(skb, rxrpc_skb_received); + skb = nskb; + rxrpc_new_skb(skb, rxrpc_skb_unshared); + sp = rxrpc_skb(skb); + } + } + if (state == RXRPC_CALL_SERVER_RECV_REQUEST) { unsigned long timo = READ_ONCE(call->next_req_timo); unsigned long now, expect_req_by; @@ -451,166 +599,18 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) if ((state == RXRPC_CALL_CLIENT_SEND_REQUEST || state == RXRPC_CALL_CLIENT_AWAIT_REPLY) && !rxrpc_receiving_reply(call)) - goto unlock; - - hard_ack = READ_ONCE(call->rx_hard_ack); - - nr_subpackets = sp->nr_subpackets; - if (nr_subpackets > 1) { - if (call->nr_jumbo_bad > 3) { - ack = RXRPC_ACK_NOSPACE; - ack_serial = serial; - goto ack; - } - } - - for (j = 0; j < nr_subpackets; j++) { - rxrpc_serial_t serial = sp->hdr.serial + j; - rxrpc_seq_t seq = seq0 + j; - unsigned int ix = seq & RXRPC_RXTX_BUFF_MASK; - bool terminal = (j == nr_subpackets - 1); - bool last = terminal && (sp->rx_flags & RXRPC_SKB_INCL_LAST); - u8 flags, annotation = j; - - _proto("Rx DATA+%u %%%u { #%x t=%u l=%u }", - j, serial, seq, terminal, last); - - if (last) { - if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) && - seq != call->rx_top) { - rxrpc_proto_abort("LSN", call, seq); - goto unlock; - } - } else { - if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) && - after_eq(seq, call->rx_top)) { - rxrpc_proto_abort("LSA", call, seq); - goto unlock; - } - } - - flags = 0; - if (last) - flags |= RXRPC_LAST_PACKET; - if (!terminal) - flags |= RXRPC_JUMBO_PACKET; - if (test_bit(j, sp->rx_req_ack)) - flags |= RXRPC_REQUEST_ACK; - trace_rxrpc_rx_data(call->debug_id, seq, serial, flags, annotation); - - if (before_eq(seq, hard_ack)) { - ack = RXRPC_ACK_DUPLICATE; - ack_serial = serial; - continue; - } - - if (call->rxtx_buffer[ix]) { - rxrpc_input_dup_data(call, seq, nr_subpackets > 1, - &jumbo_bad); - if (ack != RXRPC_ACK_DUPLICATE) { - ack = RXRPC_ACK_DUPLICATE; - ack_serial = serial; - } - immediate_ack = true; - continue; - } - - if (after(seq, hard_ack + call->rx_winsize)) { - ack = RXRPC_ACK_EXCEEDS_WINDOW; - ack_serial = serial; - if (flags & RXRPC_JUMBO_PACKET) { - if (!jumbo_bad) { - call->nr_jumbo_bad++; - jumbo_bad = true; - } - } - - goto ack; - } - - if (flags & RXRPC_REQUEST_ACK && !ack) { - ack = RXRPC_ACK_REQUESTED; - ack_serial = serial; - } - - if (after(seq0, call->ackr_highest_seq)) - call->ackr_highest_seq = seq0; - - /* Queue the packet. We use a couple of memory barriers here as need - * to make sure that rx_top is perceived to be set after the buffer - * pointer and that the buffer pointer is set after the annotation and - * the skb data. - * - * Barriers against rxrpc_recvmsg_data() and rxrpc_rotate_rx_window() - * and also rxrpc_fill_out_ack(). - */ - if (!terminal) - rxrpc_get_skb(skb, rxrpc_skb_got); - call->rxtx_annotations[ix] = annotation; - smp_wmb(); - call->rxtx_buffer[ix] = skb; - if (after(seq, call->rx_top)) { - smp_store_release(&call->rx_top, seq); - } else if (before(seq, call->rx_top)) { - /* Send an immediate ACK if we fill in a hole */ - if (!ack) { - ack = RXRPC_ACK_DELAY; - ack_serial = serial; - } - immediate_ack = true; - } - - if (terminal) { - /* From this point on, we're not allowed to touch the - * packet any longer as its ref now belongs to the Rx - * ring. - */ - skb = NULL; - sp = NULL; - } - - nr_unacked++; - - if (last) { - set_bit(RXRPC_CALL_RX_LAST, &call->flags); - if (!ack) { - ack = RXRPC_ACK_DELAY; - ack_serial = serial; - } - trace_rxrpc_receive(call, rxrpc_receive_queue_last, serial, seq); - } else { - trace_rxrpc_receive(call, rxrpc_receive_queue, serial, seq); - } + goto out; - if (after_eq(seq, call->rx_expect_next)) { - if (after(seq, call->rx_expect_next)) { - _net("OOS %u > %u", seq, call->rx_expect_next); - ack = RXRPC_ACK_OUT_OF_SEQUENCE; - ack_serial = serial; - } - call->rx_expect_next = seq + 1; - } - if (!ack) - ack_serial = serial; + if (!rxrpc_input_split_jumbo(call, skb)) { + rxrpc_proto_abort("VLD", call, sp->hdr.seq); + goto out; } + skb = NULL; -ack: - if (atomic_add_return(nr_unacked, &call->ackr_nr_unacked) > 2 && !ack) - ack = RXRPC_ACK_IDLE; - - if (ack) - rxrpc_propose_ACK(call, ack, ack_serial, - immediate_ack, true, - rxrpc_propose_ack_input_data); - else - rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, serial, - false, true, - rxrpc_propose_ack_input_data); - +out: trace_rxrpc_notify_socket(call->debug_id, serial); rxrpc_notify_socket(call); -unlock: spin_unlock(&call->input_lock); rxrpc_free_skb(skb, rxrpc_skb_freed); _leave(" [queued]"); @@ -679,31 +679,8 @@ static void rxrpc_complete_rtt_probe(struct rxrpc_call *call, */ static void rxrpc_input_check_for_lost_ack(struct rxrpc_call *call) { - rxrpc_seq_t top, bottom, seq; - bool resend = false; - - spin_lock_bh(&call->lock); - - bottom = call->tx_hard_ack + 1; - top = call->acks_lost_top; - if (before(bottom, top)) { - for (seq = bottom; before_eq(seq, top); seq++) { - int ix = seq & RXRPC_RXTX_BUFF_MASK; - u8 annotation = call->rxtx_annotations[ix]; - u8 anno_type = annotation & RXRPC_TX_ANNO_MASK; - - if (anno_type != RXRPC_TX_ANNO_UNACK) - continue; - annotation &= ~RXRPC_TX_ANNO_MASK; - annotation |= RXRPC_TX_ANNO_RETRANS; - call->rxtx_annotations[ix] = annotation; - resend = true; - } - } - - spin_unlock_bh(&call->lock); - - if (resend && !test_and_set_bit(RXRPC_CALL_EV_RESEND, &call->events)) + if (after(call->acks_lost_top, call->acks_prev_seq) && + !test_and_set_bit(RXRPC_CALL_EV_RESEND, &call->events)) rxrpc_queue_call(call); } @@ -736,8 +713,8 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb, ntohl(ackinfo->rxMTU), ntohl(ackinfo->maxMTU), rwind, ntohl(ackinfo->jumbo_max)); - if (rwind > RXRPC_RXTX_BUFF_SIZE - 1) - rwind = RXRPC_RXTX_BUFF_SIZE - 1; + if (rwind > RXRPC_TX_MAX_WINDOW) + rwind = RXRPC_TX_MAX_WINDOW; if (call->tx_winsize != rwind) { if (rwind > call->tx_winsize) wake = true; @@ -776,40 +753,19 @@ static void rxrpc_input_soft_acks(struct rxrpc_call *call, u8 *acks, rxrpc_seq_t seq, int nr_acks, struct rxrpc_ack_summary *summary) { - int ix; - u8 annotation, anno_type; - - for (; nr_acks > 0; nr_acks--, seq++) { - ix = seq & RXRPC_RXTX_BUFF_MASK; - annotation = call->rxtx_annotations[ix]; - anno_type = annotation & RXRPC_TX_ANNO_MASK; - annotation &= ~RXRPC_TX_ANNO_MASK; - switch (*acks++) { - case RXRPC_ACK_TYPE_ACK: + unsigned int i; + + for (i = 0; i < nr_acks; i++) { + if (acks[i] == RXRPC_ACK_TYPE_ACK) { summary->nr_acks++; - if (anno_type == RXRPC_TX_ANNO_ACK) - continue; summary->nr_new_acks++; - call->rxtx_annotations[ix] = - RXRPC_TX_ANNO_ACK | annotation; - break; - case RXRPC_ACK_TYPE_NACK: - if (!summary->nr_nacks && - call->acks_lowest_nak != seq) { - call->acks_lowest_nak = seq; + } else { + if (!summary->saw_nacks && + call->acks_lowest_nak != seq + i) { + call->acks_lowest_nak = seq + i; summary->new_low_nack = true; } - summary->nr_nacks++; - if (anno_type == RXRPC_TX_ANNO_NAK) - continue; - summary->nr_new_nacks++; - if (anno_type == RXRPC_TX_ANNO_RETRANS) - continue; - call->rxtx_annotations[ix] = - RXRPC_TX_ANNO_NAK | annotation; - break; - default: - return rxrpc_proto_abort("SFT", call, 0); + summary->saw_nacks = true; } } } @@ -851,12 +807,10 @@ static bool rxrpc_is_ack_valid(struct rxrpc_call *call, static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_ack_summary summary = { 0 }; + struct rxrpc_ackpacket ack; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - union { - struct rxrpc_ackpacket ack; - struct rxrpc_ackinfo info; - u8 acks[RXRPC_MAXACKS]; - } buf; + struct rxrpc_ackinfo info; + struct sk_buff *skb_old = NULL, *skb_put = skb; rxrpc_serial_t ack_serial, acked_serial; rxrpc_seq_t first_soft_ack, hard_ack, prev_pkt; int nr_acks, offset, ioffset; @@ -864,29 +818,28 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) _enter(""); offset = sizeof(struct rxrpc_wire_header); - if (skb_copy_bits(skb, offset, &buf.ack, sizeof(buf.ack)) < 0) { - _debug("extraction failure"); - return rxrpc_proto_abort("XAK", call, 0); + if (skb_copy_bits(skb, offset, &ack, sizeof(ack)) < 0) { + rxrpc_proto_abort("XAK", call, 0); + goto out_not_locked; } - offset += sizeof(buf.ack); + offset += sizeof(ack); ack_serial = sp->hdr.serial; - acked_serial = ntohl(buf.ack.serial); - first_soft_ack = ntohl(buf.ack.firstPacket); - prev_pkt = ntohl(buf.ack.previousPacket); + acked_serial = ntohl(ack.serial); + first_soft_ack = ntohl(ack.firstPacket); + prev_pkt = ntohl(ack.previousPacket); hard_ack = first_soft_ack - 1; - nr_acks = buf.ack.nAcks; - summary.ack_reason = (buf.ack.reason < RXRPC_ACK__INVALID ? - buf.ack.reason : RXRPC_ACK__INVALID); + nr_acks = ack.nAcks; + summary.ack_reason = (ack.reason < RXRPC_ACK__INVALID ? + ack.reason : RXRPC_ACK__INVALID); trace_rxrpc_rx_ack(call, ack_serial, acked_serial, first_soft_ack, prev_pkt, summary.ack_reason, nr_acks); + rxrpc_inc_stat(call->rxnet, stat_rx_acks[ack.reason]); - switch (buf.ack.reason) { + switch (ack.reason) { case RXRPC_ACK_PING_RESPONSE: - rxrpc_input_ping_response(call, skb->tstamp, acked_serial, - ack_serial); rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial, rxrpc_rtt_rx_ping_response); break; @@ -901,22 +854,20 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) break; } - if (buf.ack.reason == RXRPC_ACK_PING) { + if (ack.reason == RXRPC_ACK_PING) { _proto("Rx ACK %%%u PING Request", ack_serial); - rxrpc_propose_ACK(call, RXRPC_ACK_PING_RESPONSE, - ack_serial, true, true, - rxrpc_propose_ack_respond_to_ping); + rxrpc_send_ACK(call, RXRPC_ACK_PING_RESPONSE, ack_serial, + rxrpc_propose_ack_respond_to_ping); } else if (sp->hdr.flags & RXRPC_REQUEST_ACK) { - rxrpc_propose_ACK(call, RXRPC_ACK_REQUESTED, - ack_serial, true, true, - rxrpc_propose_ack_respond_to_ack); + rxrpc_send_ACK(call, RXRPC_ACK_REQUESTED, ack_serial, + rxrpc_propose_ack_respond_to_ack); } /* If we get an EXCEEDS_WINDOW ACK from the server, it probably * indicates that the client address changed due to NAT. The server * lost the call because it switched to a different peer. */ - if (unlikely(buf.ack.reason == RXRPC_ACK_EXCEEDS_WINDOW) && + if (unlikely(ack.reason == RXRPC_ACK_EXCEEDS_WINDOW) && first_soft_ack == 1 && prev_pkt == 0 && rxrpc_is_client_call(call)) { @@ -929,10 +880,10 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) * indicate a change of address. However, we can retransmit the call * if we still have it buffered to the beginning. */ - if (unlikely(buf.ack.reason == RXRPC_ACK_OUT_OF_SEQUENCE) && + if (unlikely(ack.reason == RXRPC_ACK_OUT_OF_SEQUENCE) && first_soft_ack == 1 && prev_pkt == 0 && - call->tx_hard_ack == 0 && + call->acks_hard_ack == 0 && rxrpc_is_client_call(call)) { rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED, 0, -ENETRESET); @@ -944,14 +895,19 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) trace_rxrpc_rx_discard_ack(call->debug_id, ack_serial, first_soft_ack, call->acks_first_seq, prev_pkt, call->acks_prev_seq); - return; + goto out_not_locked; } - buf.info.rxMTU = 0; + info.rxMTU = 0; ioffset = offset + nr_acks + 3; - if (skb->len >= ioffset + sizeof(buf.info) && - skb_copy_bits(skb, ioffset, &buf.info, sizeof(buf.info)) < 0) - return rxrpc_proto_abort("XAI", call, 0); + if (skb->len >= ioffset + sizeof(info) && + skb_copy_bits(skb, ioffset, &info, sizeof(info)) < 0) { + rxrpc_proto_abort("XAI", call, 0); + goto out_not_locked; + } + + if (nr_acks > 0) + skb_condense(skb); spin_lock(&call->input_lock); @@ -967,9 +923,22 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) call->acks_first_seq = first_soft_ack; call->acks_prev_seq = prev_pkt; + switch (ack.reason) { + case RXRPC_ACK_PING: + break; + case RXRPC_ACK_PING_RESPONSE: + rxrpc_input_ping_response(call, skb->tstamp, acked_serial, + ack_serial); + fallthrough; + default: + if (after(acked_serial, call->acks_highest_serial)) + call->acks_highest_serial = acked_serial; + break; + } + /* Parse rwind and mtu sizes if provided. */ - if (buf.info.rxMTU) - rxrpc_input_ackinfo(call, skb, &buf.info); + if (info.rxMTU) + rxrpc_input_ackinfo(call, skb, &info); if (first_soft_ack == 0) { rxrpc_proto_abort("AK0", call, 0); @@ -987,7 +956,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) goto out; } - if (before(hard_ack, call->tx_hard_ack) || + if (before(hard_ack, call->acks_hard_ack) || after(hard_ack, call->tx_top)) { rxrpc_proto_abort("AKW", call, 0); goto out; @@ -997,7 +966,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) goto out; } - if (after(hard_ack, call->tx_hard_ack)) { + if (after(hard_ack, call->acks_hard_ack)) { if (rxrpc_rotate_tx_window(call, hard_ack, &summary)) { rxrpc_end_tx_phase(call, false, "ETA"); goto out; @@ -1005,25 +974,38 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) } if (nr_acks > 0) { - if (skb_copy_bits(skb, offset, buf.acks, nr_acks) < 0) { + if (offset > (int)skb->len - nr_acks) { rxrpc_proto_abort("XSA", call, 0); goto out; } - rxrpc_input_soft_acks(call, buf.acks, first_soft_ack, nr_acks, - &summary); + + spin_lock(&call->acks_ack_lock); + skb_old = call->acks_soft_tbl; + call->acks_soft_tbl = skb; + spin_unlock(&call->acks_ack_lock); + + rxrpc_input_soft_acks(call, skb->data + offset, first_soft_ack, + nr_acks, &summary); + skb_put = NULL; + } else if (call->acks_soft_tbl) { + spin_lock(&call->acks_ack_lock); + skb_old = call->acks_soft_tbl; + call->acks_soft_tbl = NULL; + spin_unlock(&call->acks_ack_lock); } - if (call->rxtx_annotations[call->tx_top & RXRPC_RXTX_BUFF_MASK] & - RXRPC_TX_ANNO_LAST && + if (test_bit(RXRPC_CALL_TX_LAST, &call->flags) && summary.nr_acks == call->tx_top - hard_ack && rxrpc_is_client_call(call)) - rxrpc_propose_ACK(call, RXRPC_ACK_PING, ack_serial, - false, true, - rxrpc_propose_ack_ping_for_lost_reply); + rxrpc_propose_ping(call, ack_serial, + rxrpc_propose_ack_ping_for_lost_reply); rxrpc_congestion_management(call, skb, &summary, acked_serial); out: spin_unlock(&call->input_lock); +out_not_locked: + rxrpc_free_skb(skb_put, rxrpc_skb_freed); + rxrpc_free_skb(skb_old, rxrpc_skb_freed); } /* @@ -1096,7 +1078,7 @@ static void rxrpc_input_call_packet(struct rxrpc_call *call, case RXRPC_PACKET_TYPE_ACK: rxrpc_input_ack(call, skb); - break; + goto no_free; case RXRPC_PACKET_TYPE_BUSY: _proto("Rx BUSY %%%u", sp->hdr.serial); @@ -1307,8 +1289,6 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) if (sp->hdr.callNumber == 0 || sp->hdr.seq == 0) goto bad_message; - if (!rxrpc_validate_data(skb)) - goto bad_message; /* Unshare the packet so that it can be modified for in-place * decryption. @@ -1422,7 +1402,7 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) trace_rxrpc_rx_data(chan->call_debug_id, sp->hdr.seq, sp->hdr.serial, - sp->hdr.flags, 0); + sp->hdr.flags); rxrpc_post_packet_to_conn(conn, skb); goto out; } diff --git a/net/rxrpc/insecure.c b/net/rxrpc/insecure.c index 9aae99d67833..0eb8471bfc53 100644 --- a/net/rxrpc/insecure.c +++ b/net/rxrpc/insecure.c @@ -25,16 +25,16 @@ static int none_how_much_data(struct rxrpc_call *call, size_t remain, return 0; } -static int none_secure_packet(struct rxrpc_call *call, struct sk_buff *skb, - size_t data_size) +static int none_secure_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) { return 0; } -static int none_verify_packet(struct rxrpc_call *call, struct sk_buff *skb, - unsigned int offset, unsigned int len, - rxrpc_seq_t seq, u16 expected_cksum) +static int none_verify_packet(struct rxrpc_call *call, struct sk_buff *skb) { + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + + sp->flags |= RXRPC_RX_VERIFIED; return 0; } @@ -42,11 +42,6 @@ static void none_free_call_crypto(struct rxrpc_call *call) { } -static void none_locate_data(struct rxrpc_call *call, struct sk_buff *skb, - unsigned int *_offset, unsigned int *_len) -{ -} - static int none_respond_to_challenge(struct rxrpc_connection *conn, struct sk_buff *skb, u32 *_abort_code) @@ -95,7 +90,6 @@ const struct rxrpc_security rxrpc_no_security = { .how_much_data = none_how_much_data, .secure_packet = none_secure_packet, .verify_packet = none_verify_packet, - .locate_data = none_locate_data, .respond_to_challenge = none_respond_to_challenge, .verify_response = none_verify_response, .clear = none_clear, diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index 38ea98ff426b..a178f71e5082 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -24,6 +24,19 @@ static void rxrpc_local_processor(struct work_struct *); static void rxrpc_local_rcu(struct rcu_head *); /* + * Handle an ICMP/ICMP6 error turning up at the tunnel. Push it through the + * usual mechanism so that it gets parsed and presented through the UDP + * socket's error_report(). + */ +static void rxrpc_encap_err_rcv(struct sock *sk, struct sk_buff *skb, int err, + __be16 port, u32 info, u8 *payload) +{ + if (ip_hdr(skb)->version == IPVERSION) + return ip_icmp_error(sk, skb, err, port, info, payload); + return ipv6_icmp_error(sk, skb, err, port, info, payload); +} + +/* * Compare a local to an address. Return -ve, 0 or +ve to indicate less than, * same or greater than. * @@ -84,6 +97,8 @@ static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet, local->rxnet = rxnet; INIT_HLIST_NODE(&local->link); INIT_WORK(&local->processor, rxrpc_local_processor); + INIT_LIST_HEAD(&local->ack_tx_queue); + spin_lock_init(&local->ack_tx_lock); init_rwsem(&local->defrag_sem); skb_queue_head_init(&local->reject_queue); skb_queue_head_init(&local->event_queue); @@ -419,6 +434,11 @@ static void rxrpc_local_processor(struct work_struct *work) break; } + if (!list_empty(&local->ack_tx_queue)) { + rxrpc_transmit_ack_packets(local); + again = true; + } + if (!skb_queue_empty(&local->reject_queue)) { rxrpc_reject_packets(local); again = true; diff --git a/net/rxrpc/misc.c b/net/rxrpc/misc.c index d4144fd86f84..056c428d8bf3 100644 --- a/net/rxrpc/misc.c +++ b/net/rxrpc/misc.c @@ -17,12 +17,6 @@ unsigned int rxrpc_max_backlog __read_mostly = 10; /* - * How long to wait before scheduling ACK generation after seeing a - * packet with RXRPC_REQUEST_ACK set (in jiffies). - */ -unsigned long rxrpc_requested_ack_delay = 1; - -/* * How long to wait before scheduling an ACK with subtype DELAY (in jiffies). * * We use this when we've received new data packets. If those packets aren't @@ -46,10 +40,7 @@ unsigned long rxrpc_idle_ack_delay = HZ / 2; * limit is hit, we should generate an EXCEEDS_WINDOW ACK and discard further * packets. */ -unsigned int rxrpc_rx_window_size = RXRPC_INIT_RX_WINDOW_SIZE; -#if (RXRPC_RXTX_BUFF_SIZE - 1) < RXRPC_INIT_RX_WINDOW_SIZE -#error Need to reduce RXRPC_INIT_RX_WINDOW_SIZE -#endif +unsigned int rxrpc_rx_window_size = 255; /* * Maximum Rx MTU size. This indicates to the sender the size of jumbo packet @@ -62,15 +53,3 @@ unsigned int rxrpc_rx_mtu = 5692; * sender that we're willing to handle. */ unsigned int rxrpc_rx_jumbo_max = 4; - -const s8 rxrpc_ack_priority[] = { - [0] = 0, - [RXRPC_ACK_DELAY] = 1, - [RXRPC_ACK_REQUESTED] = 2, - [RXRPC_ACK_IDLE] = 3, - [RXRPC_ACK_DUPLICATE] = 4, - [RXRPC_ACK_OUT_OF_SEQUENCE] = 5, - [RXRPC_ACK_EXCEEDS_WINDOW] = 6, - [RXRPC_ACK_NOSPACE] = 7, - [RXRPC_ACK_PING_RESPONSE] = 8, -}; diff --git a/net/rxrpc/net_ns.c b/net/rxrpc/net_ns.c index bb4c25d6df64..84242c0e467c 100644 --- a/net/rxrpc/net_ns.c +++ b/net/rxrpc/net_ns.c @@ -101,6 +101,8 @@ static __net_init int rxrpc_init_net(struct net *net) proc_create_net("locals", 0444, rxnet->proc_net, &rxrpc_local_seq_ops, sizeof(struct seq_net_private)); + proc_create_net_single_write("stats", S_IFREG | 0644, rxnet->proc_net, + rxrpc_stats_show, rxrpc_stats_clear, NULL); return 0; err_proc: diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 9683617db704..46432e70a16b 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -13,15 +13,21 @@ #include <linux/export.h> #include <net/sock.h> #include <net/af_rxrpc.h> +#include <net/udp.h> #include "ar-internal.h" -struct rxrpc_ack_buffer { - struct rxrpc_wire_header whdr; - struct rxrpc_ackpacket ack; - u8 acks[255]; - u8 pad[3]; - struct rxrpc_ackinfo ackinfo; -}; +extern int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len); + +static ssize_t do_udp_sendmsg(struct socket *sk, struct msghdr *msg, size_t len) +{ +#if IS_ENABLED(CONFIG_AF_RXRPC_IPV6) + struct sockaddr *sa = msg->msg_name; + + if (sa->sa_family == AF_INET6) + return udpv6_sendmsg(sk->sk, msg, len); +#endif + return udp_sendmsg(sk->sk, msg, len); +} struct rxrpc_abort_buffer { struct rxrpc_wire_header whdr; @@ -68,66 +74,83 @@ static void rxrpc_set_keepalive(struct rxrpc_call *call) */ static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn, struct rxrpc_call *call, - struct rxrpc_ack_buffer *pkt, - rxrpc_seq_t *_hard_ack, - rxrpc_seq_t *_top, - u8 reason) + struct rxrpc_txbuf *txb) { - rxrpc_serial_t serial; - unsigned int tmp; - rxrpc_seq_t hard_ack, top, seq; - int ix; + struct rxrpc_ackinfo ackinfo; + unsigned int qsize; + rxrpc_seq_t window, wtop, wrap_point, ix, first; + int rsize; + u64 wtmp; u32 mtu, jmax; - u8 *ackp = pkt->acks; + u8 *ackp = txb->acks; + u8 sack_buffer[sizeof(call->ackr_sack_table)] __aligned(8); - tmp = atomic_xchg(&call->ackr_nr_unacked, 0); - tmp |= atomic_xchg(&call->ackr_nr_consumed, 0); - if (!tmp && (reason == RXRPC_ACK_DELAY || - reason == RXRPC_ACK_IDLE)) - return 0; + atomic_set(&call->ackr_nr_unacked, 0); + atomic_set(&call->ackr_nr_consumed, 0); + rxrpc_inc_stat(call->rxnet, stat_tx_ack_fill); /* Barrier against rxrpc_input_data(). */ - serial = call->ackr_serial; - hard_ack = READ_ONCE(call->rx_hard_ack); - top = smp_load_acquire(&call->rx_top); - *_hard_ack = hard_ack; - *_top = top; - - pkt->ack.bufferSpace = htons(8); - pkt->ack.maxSkew = htons(0); - pkt->ack.firstPacket = htonl(hard_ack + 1); - pkt->ack.previousPacket = htonl(call->ackr_highest_seq); - pkt->ack.serial = htonl(serial); - pkt->ack.reason = reason; - pkt->ack.nAcks = top - hard_ack; - - if (reason == RXRPC_ACK_PING) - pkt->whdr.flags |= RXRPC_REQUEST_ACK; - - if (after(top, hard_ack)) { - seq = hard_ack + 1; - do { - ix = seq & RXRPC_RXTX_BUFF_MASK; - if (call->rxtx_buffer[ix]) - *ackp++ = RXRPC_ACK_TYPE_ACK; - else - *ackp++ = RXRPC_ACK_TYPE_NACK; - seq++; - } while (before_eq(seq, top)); +retry: + wtmp = atomic64_read_acquire(&call->ackr_window); + window = lower_32_bits(wtmp); + wtop = upper_32_bits(wtmp); + txb->ack.firstPacket = htonl(window); + txb->ack.nAcks = 0; + + if (after(wtop, window)) { + /* Try to copy the SACK ring locklessly. We can use the copy, + * only if the now-current top of the window didn't go past the + * previously read base - otherwise we can't know whether we + * have old data or new data. + */ + memcpy(sack_buffer, call->ackr_sack_table, sizeof(sack_buffer)); + wrap_point = window + RXRPC_SACK_SIZE - 1; + wtmp = atomic64_read_acquire(&call->ackr_window); + window = lower_32_bits(wtmp); + wtop = upper_32_bits(wtmp); + if (after(wtop, wrap_point)) { + cond_resched(); + goto retry; + } + + /* The buffer is maintained as a ring with an invariant mapping + * between bit position and sequence number, so we'll probably + * need to rotate it. + */ + txb->ack.nAcks = wtop - window; + ix = window % RXRPC_SACK_SIZE; + first = sizeof(sack_buffer) - ix; + + if (ix + txb->ack.nAcks <= RXRPC_SACK_SIZE) { + memcpy(txb->acks, sack_buffer + ix, txb->ack.nAcks); + } else { + memcpy(txb->acks, sack_buffer + ix, first); + memcpy(txb->acks + first, sack_buffer, + txb->ack.nAcks - first); + } + + ackp += txb->ack.nAcks; + } else if (before(wtop, window)) { + pr_warn("ack window backward %x %x", window, wtop); + } else if (txb->ack.reason == RXRPC_ACK_DELAY) { + txb->ack.reason = RXRPC_ACK_IDLE; } mtu = conn->params.peer->if_mtu; mtu -= conn->params.peer->hdrsize; - jmax = (call->nr_jumbo_bad > 3) ? 1 : rxrpc_rx_jumbo_max; - pkt->ackinfo.rxMTU = htonl(rxrpc_rx_mtu); - pkt->ackinfo.maxMTU = htonl(mtu); - pkt->ackinfo.rwind = htonl(call->rx_winsize); - pkt->ackinfo.jumbo_max = htonl(jmax); + jmax = rxrpc_rx_jumbo_max; + qsize = (window - 1) - call->rx_consumed; + rsize = max_t(int, call->rx_winsize - qsize, 0); + ackinfo.rxMTU = htonl(rxrpc_rx_mtu); + ackinfo.maxMTU = htonl(mtu); + ackinfo.rwind = htonl(rsize); + ackinfo.jumbo_max = htonl(jmax); *ackp++ = 0; *ackp++ = 0; *ackp++ = 0; - return top - hard_ack + 3; + memcpy(ackp, &ackinfo, sizeof(ackinfo)); + return txb->ack.nAcks + 3 + sizeof(ackinfo); } /* @@ -176,26 +199,20 @@ static void rxrpc_cancel_rtt_probe(struct rxrpc_call *call, /* * Send an ACK call packet. */ -int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, - rxrpc_serial_t *_serial) +static int rxrpc_send_ack_packet(struct rxrpc_local *local, struct rxrpc_txbuf *txb) { struct rxrpc_connection *conn; struct rxrpc_ack_buffer *pkt; + struct rxrpc_call *call = txb->call; struct msghdr msg; - struct kvec iov[2]; + struct kvec iov[1]; rxrpc_serial_t serial; - rxrpc_seq_t hard_ack, top; size_t len, n; int ret, rtt_slot = -1; - u8 reason; if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) return -ECONNRESET; - pkt = kzalloc(sizeof(*pkt), GFP_KERNEL); - if (!pkt) - return -ENOMEM; - conn = call->conn; msg.msg_name = &call->peer->srx.transport; @@ -204,83 +221,98 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, msg.msg_controllen = 0; msg.msg_flags = 0; - pkt->whdr.epoch = htonl(conn->proto.epoch); - pkt->whdr.cid = htonl(call->cid); - pkt->whdr.callNumber = htonl(call->call_id); - pkt->whdr.seq = 0; - pkt->whdr.type = RXRPC_PACKET_TYPE_ACK; - pkt->whdr.flags = RXRPC_SLOW_START_OK | conn->out_clientflag; - pkt->whdr.userStatus = 0; - pkt->whdr.securityIndex = call->security_ix; - pkt->whdr._rsvd = 0; - pkt->whdr.serviceId = htons(call->service_id); - - spin_lock_bh(&call->lock); - if (ping) { - reason = RXRPC_ACK_PING; - } else { - reason = call->ackr_reason; - if (!call->ackr_reason) { - spin_unlock_bh(&call->lock); - ret = 0; - goto out; - } - call->ackr_reason = 0; - } - n = rxrpc_fill_out_ack(conn, call, pkt, &hard_ack, &top, reason); + if (txb->ack.reason == RXRPC_ACK_PING) + txb->wire.flags |= RXRPC_REQUEST_ACK; - spin_unlock_bh(&call->lock); - if (n == 0) { - kfree(pkt); + if (txb->ack.reason == RXRPC_ACK_DELAY) + clear_bit(RXRPC_CALL_DELAY_ACK_PENDING, &call->flags); + if (txb->ack.reason == RXRPC_ACK_IDLE) + clear_bit(RXRPC_CALL_IDLE_ACK_PENDING, &call->flags); + + n = rxrpc_fill_out_ack(conn, call, txb); + if (n == 0) return 0; - } - iov[0].iov_base = pkt; - iov[0].iov_len = sizeof(pkt->whdr) + sizeof(pkt->ack) + n; - iov[1].iov_base = &pkt->ackinfo; - iov[1].iov_len = sizeof(pkt->ackinfo); - len = iov[0].iov_len + iov[1].iov_len; + iov[0].iov_base = &txb->wire; + iov[0].iov_len = sizeof(txb->wire) + sizeof(txb->ack) + n; + len = iov[0].iov_len; serial = atomic_inc_return(&conn->serial); - pkt->whdr.serial = htonl(serial); + txb->wire.serial = htonl(serial); trace_rxrpc_tx_ack(call->debug_id, serial, - ntohl(pkt->ack.firstPacket), - ntohl(pkt->ack.serial), - pkt->ack.reason, pkt->ack.nAcks); - if (_serial) - *_serial = serial; + ntohl(txb->ack.firstPacket), + ntohl(txb->ack.serial), txb->ack.reason, txb->ack.nAcks); + if (txb->ack_why == rxrpc_propose_ack_ping_for_lost_ack) + call->acks_lost_ping = serial; - if (ping) + if (txb->ack.reason == RXRPC_ACK_PING) rtt_slot = rxrpc_begin_rtt_probe(call, serial, rxrpc_rtt_tx_ping); - ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len); - conn->params.peer->last_tx_at = ktime_get_seconds(); + rxrpc_inc_stat(call->rxnet, stat_tx_ack_send); + + /* Grab the highest received seq as late as possible */ + txb->ack.previousPacket = htonl(call->rx_highest_seq); + + iov_iter_kvec(&msg.msg_iter, WRITE, iov, 1, len); + ret = do_udp_sendmsg(conn->params.local->socket, &msg, len); + call->peer->last_tx_at = ktime_get_seconds(); if (ret < 0) trace_rxrpc_tx_fail(call->debug_id, serial, ret, rxrpc_tx_point_call_ack); else - trace_rxrpc_tx_packet(call->debug_id, &pkt->whdr, + trace_rxrpc_tx_packet(call->debug_id, &txb->wire, rxrpc_tx_point_call_ack); rxrpc_tx_backoff(call, ret); if (call->state < RXRPC_CALL_COMPLETE) { - if (ret < 0) { + if (ret < 0) rxrpc_cancel_rtt_probe(call, serial, rtt_slot); - rxrpc_propose_ACK(call, pkt->ack.reason, - ntohl(pkt->ack.serial), - false, true, - rxrpc_propose_ack_retry_tx); - } - rxrpc_set_keepalive(call); } -out: kfree(pkt); return ret; } /* + * ACK transmitter for a local endpoint. The UDP socket locks around each + * transmission, so we can only transmit one packet at a time, ACK, DATA or + * otherwise. + */ +void rxrpc_transmit_ack_packets(struct rxrpc_local *local) +{ + LIST_HEAD(queue); + int ret; + + trace_rxrpc_local(local->debug_id, rxrpc_local_tx_ack, + refcount_read(&local->ref), NULL); + + if (list_empty(&local->ack_tx_queue)) + return; + + spin_lock_bh(&local->ack_tx_lock); + list_splice_tail_init(&local->ack_tx_queue, &queue); + spin_unlock_bh(&local->ack_tx_lock); + + while (!list_empty(&queue)) { + struct rxrpc_txbuf *txb = + list_entry(queue.next, struct rxrpc_txbuf, tx_link); + + ret = rxrpc_send_ack_packet(local, txb); + if (ret < 0 && ret != -ECONNRESET) { + spin_lock_bh(&local->ack_tx_lock); + list_splice_init(&queue, &local->ack_tx_queue); + spin_unlock_bh(&local->ack_tx_lock); + break; + } + + list_del_init(&txb->tx_link); + rxrpc_put_call(txb->call, rxrpc_call_put); + rxrpc_put_txbuf(txb, rxrpc_txbuf_put_ack_tx); + } +} + +/* * Send an ABORT call packet. */ int rxrpc_send_abort_packet(struct rxrpc_call *call) @@ -299,7 +331,7 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call) * channel instead, thereby closing off this call. */ if (rxrpc_is_client_call(call) && - test_bit(RXRPC_CALL_TX_LAST, &call->flags)) + test_bit(RXRPC_CALL_TX_ALL_ACKED, &call->flags)) return 0; if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) @@ -331,8 +363,8 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call) serial = atomic_inc_return(&conn->serial); pkt.whdr.serial = htonl(serial); - ret = kernel_sendmsg(conn->params.local->socket, - &msg, iov, 1, sizeof(pkt)); + iov_iter_kvec(&msg.msg_iter, WRITE, iov, 1, sizeof(pkt)); + ret = do_udp_sendmsg(conn->params.local->socket, &msg, sizeof(pkt)); conn->params.peer->last_tx_at = ktime_get_seconds(); if (ret < 0) trace_rxrpc_tx_fail(call->debug_id, serial, ret, @@ -347,19 +379,17 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call) /* * send a packet through the transport endpoint */ -int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, - bool retrans) +int rxrpc_send_data_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) { + enum rxrpc_req_ack_trace why; struct rxrpc_connection *conn = call->conn; - struct rxrpc_wire_header whdr; - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct msghdr msg; - struct kvec iov[2]; + struct kvec iov[1]; rxrpc_serial_t serial; size_t len; int ret, rtt_slot = -1; - _enter(",{%d}", skb->len); + _enter("%x,{%d}", txb->seq, txb->len); if (hlist_unhashed(&call->error_link)) { spin_lock_bh(&call->peer->lock); @@ -369,28 +399,16 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, /* Each transmission of a Tx packet needs a new serial number */ serial = atomic_inc_return(&conn->serial); - - whdr.epoch = htonl(conn->proto.epoch); - whdr.cid = htonl(call->cid); - whdr.callNumber = htonl(call->call_id); - whdr.seq = htonl(sp->hdr.seq); - whdr.serial = htonl(serial); - whdr.type = RXRPC_PACKET_TYPE_DATA; - whdr.flags = sp->hdr.flags; - whdr.userStatus = 0; - whdr.securityIndex = call->security_ix; - whdr._rsvd = htons(sp->hdr._rsvd); - whdr.serviceId = htons(call->service_id); + txb->wire.serial = htonl(serial); if (test_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags) && - sp->hdr.seq == 1) - whdr.userStatus = RXRPC_USERSTATUS_SERVICE_UPGRADE; + txb->seq == 1) + txb->wire.userStatus = RXRPC_USERSTATUS_SERVICE_UPGRADE; - iov[0].iov_base = &whdr; - iov[0].iov_len = sizeof(whdr); - iov[1].iov_base = skb->head; - iov[1].iov_len = skb->len; - len = iov[0].iov_len + iov[1].iov_len; + iov[0].iov_base = &txb->wire; + iov[0].iov_len = sizeof(txb->wire) + txb->len; + len = iov[0].iov_len; + iov_iter_kvec(&msg.msg_iter, WRITE, iov, 1, len); msg.msg_name = &call->peer->srx.transport; msg.msg_namelen = call->peer->srx.transport_len; @@ -405,41 +423,56 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, * service call, lest OpenAFS incorrectly send us an ACK with some * soft-ACKs in it and then never follow up with a proper hard ACK. */ - if ((!(sp->hdr.flags & RXRPC_LAST_PACKET) || - rxrpc_to_server(sp) - ) && - (test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events) || - retrans || - call->cong_mode == RXRPC_CALL_SLOW_START || - (call->peer->rtt_count < 3 && sp->hdr.seq & 1) || - ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), - ktime_get_real()))) - whdr.flags |= RXRPC_REQUEST_ACK; + if (txb->wire.flags & RXRPC_REQUEST_ACK) + why = rxrpc_reqack_already_on; + else if (test_bit(RXRPC_TXBUF_LAST, &txb->flags) && rxrpc_sending_to_client(txb)) + why = rxrpc_reqack_no_srv_last; + else if (test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events)) + why = rxrpc_reqack_ack_lost; + else if (test_bit(RXRPC_TXBUF_RESENT, &txb->flags)) + why = rxrpc_reqack_retrans; + else if (call->cong_mode == RXRPC_CALL_SLOW_START && call->cong_cwnd <= 2) + why = rxrpc_reqack_slow_start; + else if (call->tx_winsize <= 2) + why = rxrpc_reqack_small_txwin; + else if (call->peer->rtt_count < 3 && txb->seq & 1) + why = rxrpc_reqack_more_rtt; + else if (ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), ktime_get_real())) + why = rxrpc_reqack_old_rtt; + else + goto dont_set_request_ack; + + rxrpc_inc_stat(call->rxnet, stat_why_req_ack[why]); + trace_rxrpc_req_ack(call->debug_id, txb->seq, why); + if (why != rxrpc_reqack_no_srv_last) + txb->wire.flags |= RXRPC_REQUEST_ACK; +dont_set_request_ack: if (IS_ENABLED(CONFIG_AF_RXRPC_INJECT_LOSS)) { static int lose; if ((lose++ & 7) == 7) { ret = 0; - trace_rxrpc_tx_data(call, sp->hdr.seq, serial, - whdr.flags, retrans, true); + trace_rxrpc_tx_data(call, txb->seq, serial, + txb->wire.flags, + test_bit(RXRPC_TXBUF_RESENT, &txb->flags), + true); goto done; } } - trace_rxrpc_tx_data(call, sp->hdr.seq, serial, whdr.flags, retrans, - false); + trace_rxrpc_tx_data(call, txb->seq, serial, txb->wire.flags, + test_bit(RXRPC_TXBUF_RESENT, &txb->flags), false); + cmpxchg(&call->tx_transmitted, txb->seq - 1, txb->seq); /* send the packet with the don't fragment bit set if we currently * think it's small enough */ - if (iov[1].iov_len >= call->peer->maxdata) + if (txb->len >= call->peer->maxdata) goto send_fragmentable; down_read(&conn->params.local->defrag_sem); - sp->hdr.serial = serial; - smp_wmb(); /* Set serial before timestamp */ - skb->tstamp = ktime_get_real(); - if (whdr.flags & RXRPC_REQUEST_ACK) + txb->last_sent = ktime_get_real(); + if (txb->wire.flags & RXRPC_REQUEST_ACK) rtt_slot = rxrpc_begin_rtt_probe(call, serial, rxrpc_rtt_tx_data); /* send the packet by UDP @@ -448,7 +481,8 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, * - in which case, we'll have processed the ICMP error * message and update the peer record */ - ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len); + rxrpc_inc_stat(call->rxnet, stat_tx_data_send); + ret = do_udp_sendmsg(conn->params.local->socket, &msg, len); conn->params.peer->last_tx_at = ktime_get_seconds(); up_read(&conn->params.local->defrag_sem); @@ -457,7 +491,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, trace_rxrpc_tx_fail(call->debug_id, serial, ret, rxrpc_tx_point_call_data_nofrag); } else { - trace_rxrpc_tx_packet(call->debug_id, &whdr, + trace_rxrpc_tx_packet(call->debug_id, &txb->wire, rxrpc_tx_point_call_data_nofrag); } @@ -467,8 +501,9 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, done: if (ret >= 0) { - if (whdr.flags & RXRPC_REQUEST_ACK) { - call->peer->rtt_last_req = skb->tstamp; + call->tx_last_sent = txb->last_sent; + if (txb->wire.flags & RXRPC_REQUEST_ACK) { + call->peer->rtt_last_req = txb->last_sent; if (call->peer->rtt_count > 1) { unsigned long nowj = jiffies, ack_lost_at; @@ -480,7 +515,7 @@ done: } } - if (sp->hdr.seq == 1 && + if (txb->seq == 1 && !test_and_set_bit(RXRPC_CALL_BEGAN_RX_TIMER, &call->flags)) { unsigned long nowj = jiffies, expect_rx_by; @@ -512,23 +547,21 @@ send_fragmentable: down_write(&conn->params.local->defrag_sem); - sp->hdr.serial = serial; - smp_wmb(); /* Set serial before timestamp */ - skb->tstamp = ktime_get_real(); - if (whdr.flags & RXRPC_REQUEST_ACK) + txb->last_sent = ktime_get_real(); + if (txb->wire.flags & RXRPC_REQUEST_ACK) rtt_slot = rxrpc_begin_rtt_probe(call, serial, rxrpc_rtt_tx_data); switch (conn->params.local->srx.transport.family) { case AF_INET6: case AF_INET: ip_sock_set_mtu_discover(conn->params.local->socket->sk, - IP_PMTUDISC_DONT); - ret = kernel_sendmsg(conn->params.local->socket, &msg, - iov, 2, len); + IP_PMTUDISC_DONT); + rxrpc_inc_stat(call->rxnet, stat_tx_data_send_frag); + ret = do_udp_sendmsg(conn->params.local->socket, &msg, len); conn->params.peer->last_tx_at = ktime_get_seconds(); ip_sock_set_mtu_discover(conn->params.local->socket->sk, - IP_PMTUDISC_DO); + IP_PMTUDISC_DO); break; default: @@ -540,7 +573,7 @@ send_fragmentable: trace_rxrpc_tx_fail(call->debug_id, serial, ret, rxrpc_tx_point_call_data_frag); } else { - trace_rxrpc_tx_packet(call->debug_id, &whdr, + trace_rxrpc_tx_packet(call->debug_id, &txb->wire, rxrpc_tx_point_call_data_frag); } rxrpc_tx_backoff(call, ret); @@ -610,8 +643,8 @@ void rxrpc_reject_packets(struct rxrpc_local *local) whdr.flags ^= RXRPC_CLIENT_INITIATED; whdr.flags &= RXRPC_CLIENT_INITIATED; - ret = kernel_sendmsg(local->socket, &msg, - iov, ioc, size); + iov_iter_kvec(&msg.msg_iter, WRITE, iov, ioc, size); + ret = do_udp_sendmsg(local->socket, &msg, size); if (ret < 0) trace_rxrpc_tx_fail(local->debug_id, 0, ret, rxrpc_tx_point_reject); @@ -666,7 +699,8 @@ void rxrpc_send_keepalive(struct rxrpc_peer *peer) _proto("Tx VERSION (keepalive)"); - ret = kernel_sendmsg(peer->local->socket, &msg, iov, 2, len); + iov_iter_kvec(&msg.msg_iter, WRITE, iov, 2, len); + ret = do_udp_sendmsg(peer->local->socket, &msg, len); if (ret < 0) trace_rxrpc_tx_fail(peer->debug_id, 0, ret, rxrpc_tx_point_version_keepalive); diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index 32561e9567fe..cda3890657a9 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -16,258 +16,13 @@ #include <net/sock.h> #include <net/af_rxrpc.h> #include <net/ip.h> -#include <net/icmp.h> #include "ar-internal.h" -static void rxrpc_adjust_mtu(struct rxrpc_peer *, unsigned int); static void rxrpc_store_error(struct rxrpc_peer *, struct sock_exterr_skb *); static void rxrpc_distribute_error(struct rxrpc_peer *, int, enum rxrpc_call_completion); /* - * Find the peer associated with an ICMPv4 packet. - */ -static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local, - struct sk_buff *skb, - unsigned int udp_offset, - unsigned int *info, - struct sockaddr_rxrpc *srx) -{ - struct iphdr *ip, *ip0 = ip_hdr(skb); - struct icmphdr *icmp = icmp_hdr(skb); - struct udphdr *udp = (struct udphdr *)(skb->data + udp_offset); - - _enter("%u,%u,%u", ip0->protocol, icmp->type, icmp->code); - - switch (icmp->type) { - case ICMP_DEST_UNREACH: - *info = ntohs(icmp->un.frag.mtu); - fallthrough; - case ICMP_TIME_EXCEEDED: - case ICMP_PARAMETERPROB: - ip = (struct iphdr *)((void *)icmp + 8); - break; - default: - return NULL; - } - - memset(srx, 0, sizeof(*srx)); - srx->transport_type = local->srx.transport_type; - srx->transport_len = local->srx.transport_len; - srx->transport.family = local->srx.transport.family; - - /* Can we see an ICMP4 packet on an ICMP6 listening socket? and vice - * versa? - */ - switch (srx->transport.family) { - case AF_INET: - srx->transport_len = sizeof(srx->transport.sin); - srx->transport.family = AF_INET; - srx->transport.sin.sin_port = udp->dest; - memcpy(&srx->transport.sin.sin_addr, &ip->daddr, - sizeof(struct in_addr)); - break; - -#ifdef CONFIG_AF_RXRPC_IPV6 - case AF_INET6: - srx->transport_len = sizeof(srx->transport.sin); - srx->transport.family = AF_INET; - srx->transport.sin.sin_port = udp->dest; - memcpy(&srx->transport.sin.sin_addr, &ip->daddr, - sizeof(struct in_addr)); - break; -#endif - - default: - WARN_ON_ONCE(1); - return NULL; - } - - _net("ICMP {%pISp}", &srx->transport); - return rxrpc_lookup_peer_rcu(local, srx); -} - -#ifdef CONFIG_AF_RXRPC_IPV6 -/* - * Find the peer associated with an ICMPv6 packet. - */ -static struct rxrpc_peer *rxrpc_lookup_peer_icmp6_rcu(struct rxrpc_local *local, - struct sk_buff *skb, - unsigned int udp_offset, - unsigned int *info, - struct sockaddr_rxrpc *srx) -{ - struct icmp6hdr *icmp = icmp6_hdr(skb); - struct ipv6hdr *ip, *ip0 = ipv6_hdr(skb); - struct udphdr *udp = (struct udphdr *)(skb->data + udp_offset); - - _enter("%u,%u,%u", ip0->nexthdr, icmp->icmp6_type, icmp->icmp6_code); - - switch (icmp->icmp6_type) { - case ICMPV6_DEST_UNREACH: - *info = ntohl(icmp->icmp6_mtu); - fallthrough; - case ICMPV6_PKT_TOOBIG: - case ICMPV6_TIME_EXCEED: - case ICMPV6_PARAMPROB: - ip = (struct ipv6hdr *)((void *)icmp + 8); - break; - default: - return NULL; - } - - memset(srx, 0, sizeof(*srx)); - srx->transport_type = local->srx.transport_type; - srx->transport_len = local->srx.transport_len; - srx->transport.family = local->srx.transport.family; - - /* Can we see an ICMP4 packet on an ICMP6 listening socket? and vice - * versa? - */ - switch (srx->transport.family) { - case AF_INET: - _net("Rx ICMP6 on v4 sock"); - srx->transport_len = sizeof(srx->transport.sin); - srx->transport.family = AF_INET; - srx->transport.sin.sin_port = udp->dest; - memcpy(&srx->transport.sin.sin_addr, - &ip->daddr.s6_addr32[3], sizeof(struct in_addr)); - break; - case AF_INET6: - _net("Rx ICMP6"); - srx->transport.sin.sin_port = udp->dest; - memcpy(&srx->transport.sin6.sin6_addr, &ip->daddr, - sizeof(struct in6_addr)); - break; - default: - WARN_ON_ONCE(1); - return NULL; - } - - _net("ICMP {%pISp}", &srx->transport); - return rxrpc_lookup_peer_rcu(local, srx); -} -#endif /* CONFIG_AF_RXRPC_IPV6 */ - -/* - * Handle an error received on the local endpoint as a tunnel. - */ -void rxrpc_encap_err_rcv(struct sock *sk, struct sk_buff *skb, - unsigned int udp_offset) -{ - struct sock_extended_err ee; - struct sockaddr_rxrpc srx; - struct rxrpc_local *local; - struct rxrpc_peer *peer; - unsigned int info = 0; - int err; - u8 version = ip_hdr(skb)->version; - u8 type = icmp_hdr(skb)->type; - u8 code = icmp_hdr(skb)->code; - - rcu_read_lock(); - local = rcu_dereference_sk_user_data(sk); - if (unlikely(!local)) { - rcu_read_unlock(); - return; - } - - rxrpc_new_skb(skb, rxrpc_skb_received); - - switch (ip_hdr(skb)->version) { - case IPVERSION: - peer = rxrpc_lookup_peer_icmp_rcu(local, skb, udp_offset, - &info, &srx); - break; -#ifdef CONFIG_AF_RXRPC_IPV6 - case 6: - peer = rxrpc_lookup_peer_icmp6_rcu(local, skb, udp_offset, - &info, &srx); - break; -#endif - default: - rcu_read_unlock(); - return; - } - - if (peer && !rxrpc_get_peer_maybe(peer)) - peer = NULL; - if (!peer) { - rcu_read_unlock(); - return; - } - - memset(&ee, 0, sizeof(ee)); - - switch (version) { - case IPVERSION: - switch (type) { - case ICMP_DEST_UNREACH: - switch (code) { - case ICMP_FRAG_NEEDED: - rxrpc_adjust_mtu(peer, info); - rcu_read_unlock(); - rxrpc_put_peer(peer); - return; - default: - break; - } - - err = EHOSTUNREACH; - if (code <= NR_ICMP_UNREACH) { - /* Might want to do something different with - * non-fatal errors - */ - //harderr = icmp_err_convert[code].fatal; - err = icmp_err_convert[code].errno; - } - break; - - case ICMP_TIME_EXCEEDED: - err = EHOSTUNREACH; - break; - default: - err = EPROTO; - break; - } - - ee.ee_origin = SO_EE_ORIGIN_ICMP; - ee.ee_type = type; - ee.ee_code = code; - ee.ee_errno = err; - break; - -#ifdef CONFIG_AF_RXRPC_IPV6 - case 6: - switch (type) { - case ICMPV6_PKT_TOOBIG: - rxrpc_adjust_mtu(peer, info); - rcu_read_unlock(); - rxrpc_put_peer(peer); - return; - } - - icmpv6_err_convert(type, code, &err); - - if (err == EACCES) - err = EHOSTUNREACH; - - ee.ee_origin = SO_EE_ORIGIN_ICMP6; - ee.ee_type = type; - ee.ee_code = code; - ee.ee_errno = err; - break; -#endif - } - - trace_rxrpc_rx_icmp(peer, &ee, &srx); - - rxrpc_distribute_error(peer, err, RXRPC_CALL_NETWORK_ERROR); - rcu_read_unlock(); - rxrpc_put_peer(peer); -} - -/* * Find the peer associated with a local error. */ static struct rxrpc_peer *rxrpc_lookup_peer_local_rcu(struct rxrpc_local *local, @@ -283,6 +38,9 @@ static struct rxrpc_peer *rxrpc_lookup_peer_local_rcu(struct rxrpc_local *local, srx->transport_len = local->srx.transport_len; srx->transport.family = local->srx.transport.family; + /* Can we see an ICMP4 packet on an ICMP6 listening socket? and vice + * versa? + */ switch (srx->transport.family) { case AF_INET: srx->transport_len = sizeof(srx->transport.sin); @@ -412,20 +170,38 @@ void rxrpc_error_report(struct sock *sk) } rxrpc_new_skb(skb, rxrpc_skb_received); serr = SKB_EXT_ERR(skb); + if (!skb->len && serr->ee.ee_origin == SO_EE_ORIGIN_TIMESTAMPING) { + _leave("UDP empty message"); + rcu_read_unlock(); + rxrpc_free_skb(skb, rxrpc_skb_freed); + return; + } - if (serr->ee.ee_origin == SO_EE_ORIGIN_LOCAL) { - peer = rxrpc_lookup_peer_local_rcu(local, skb, &srx); - if (peer && !rxrpc_get_peer_maybe(peer)) - peer = NULL; - if (peer) { - trace_rxrpc_rx_icmp(peer, &serr->ee, &srx); - rxrpc_store_error(peer, serr); - } + peer = rxrpc_lookup_peer_local_rcu(local, skb, &srx); + if (peer && !rxrpc_get_peer_maybe(peer)) + peer = NULL; + if (!peer) { + rcu_read_unlock(); + rxrpc_free_skb(skb, rxrpc_skb_freed); + _leave(" [no peer]"); + return; } + trace_rxrpc_rx_icmp(peer, &serr->ee, &srx); + + if ((serr->ee.ee_origin == SO_EE_ORIGIN_ICMP && + serr->ee.ee_type == ICMP_DEST_UNREACH && + serr->ee.ee_code == ICMP_FRAG_NEEDED)) { + rxrpc_adjust_mtu(peer, serr->ee.ee_info); + goto out; + } + + rxrpc_store_error(peer, serr); +out: rcu_read_unlock(); rxrpc_free_skb(skb, rxrpc_skb_freed); rxrpc_put_peer(peer); + _leave(""); } diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index 26d2ae9baaf2..041a51225c5f 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -227,12 +227,7 @@ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp) rxrpc_peer_init_rtt(peer); - if (RXRPC_TX_SMSS > 2190) - peer->cong_cwnd = 2; - else if (RXRPC_TX_SMSS > 1095) - peer->cong_cwnd = 3; - else - peer->cong_cwnd = 4; + peer->cong_ssthresh = RXRPC_TX_MAX_WINDOW; trace_rxrpc_peer(peer->debug_id, rxrpc_peer_new, 1, here); } diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index 245418943e01..fae22a8b38d6 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -54,8 +54,9 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) struct rxrpc_call *call; struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq)); unsigned long timeout = 0; - rxrpc_seq_t tx_hard_ack, rx_hard_ack; + rxrpc_seq_t acks_hard_ack; char lbuff[50], rbuff[50]; + u64 wtmp; if (v == &rxnet->calls) { seq_puts(seq, @@ -90,8 +91,8 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) timeout -= jiffies; } - tx_hard_ack = READ_ONCE(call->tx_hard_ack); - rx_hard_ack = READ_ONCE(call->rx_hard_ack); + acks_hard_ack = READ_ONCE(call->acks_hard_ack); + wtmp = atomic64_read_acquire(&call->ackr_window); seq_printf(seq, "UDP %-47.47s %-47.47s %4x %08x %08x %s %3u" " %-8.8s %08x %08x %08x %02x %08x %02x %08x %06lx\n", @@ -105,8 +106,8 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) rxrpc_call_states[call->state], call->abort_code, call->debug_id, - tx_hard_ack, READ_ONCE(call->tx_top) - tx_hard_ack, - rx_hard_ack, READ_ONCE(call->rx_top) - rx_hard_ack, + acks_hard_ack, READ_ONCE(call->tx_top) - acks_hard_ack, + lower_32_bits(wtmp), upper_32_bits(wtmp) - lower_32_bits(wtmp), call->rx_serial, timeout); @@ -216,7 +217,7 @@ static int rxrpc_peer_seq_show(struct seq_file *seq, void *v) seq_puts(seq, "Proto Local " " Remote " - " Use CW MTU LastUse RTT RTO\n" + " Use SST MTU LastUse RTT RTO\n" ); return 0; } @@ -234,7 +235,7 @@ static int rxrpc_peer_seq_show(struct seq_file *seq, void *v) lbuff, rbuff, refcount_read(&peer->ref), - peer->cong_cwnd, + peer->cong_ssthresh, peer->mtu, now - peer->last_tx_at, peer->srtt_us >> 3, @@ -397,3 +398,98 @@ const struct seq_operations rxrpc_local_seq_ops = { .stop = rxrpc_local_seq_stop, .show = rxrpc_local_seq_show, }; + +/* + * Display stats in /proc/net/rxrpc/stats + */ +int rxrpc_stats_show(struct seq_file *seq, void *v) +{ + struct rxrpc_net *rxnet = rxrpc_net(seq_file_single_net(seq)); + + seq_printf(seq, + "Data : send=%u sendf=%u\n", + atomic_read(&rxnet->stat_tx_data_send), + atomic_read(&rxnet->stat_tx_data_send_frag)); + seq_printf(seq, + "Data-Tx : nr=%u retrans=%u\n", + atomic_read(&rxnet->stat_tx_data), + atomic_read(&rxnet->stat_tx_data_retrans)); + seq_printf(seq, + "Data-Rx : nr=%u reqack=%u jumbo=%u\n", + atomic_read(&rxnet->stat_rx_data), + atomic_read(&rxnet->stat_rx_data_reqack), + atomic_read(&rxnet->stat_rx_data_jumbo)); + seq_printf(seq, + "Ack : fill=%u send=%u skip=%u\n", + atomic_read(&rxnet->stat_tx_ack_fill), + atomic_read(&rxnet->stat_tx_ack_send), + atomic_read(&rxnet->stat_tx_ack_skip)); + seq_printf(seq, + "Ack-Tx : req=%u dup=%u oos=%u exw=%u nos=%u png=%u prs=%u dly=%u idl=%u\n", + atomic_read(&rxnet->stat_tx_acks[RXRPC_ACK_REQUESTED]), + atomic_read(&rxnet->stat_tx_acks[RXRPC_ACK_DUPLICATE]), + atomic_read(&rxnet->stat_tx_acks[RXRPC_ACK_OUT_OF_SEQUENCE]), + atomic_read(&rxnet->stat_tx_acks[RXRPC_ACK_EXCEEDS_WINDOW]), + atomic_read(&rxnet->stat_tx_acks[RXRPC_ACK_NOSPACE]), + atomic_read(&rxnet->stat_tx_acks[RXRPC_ACK_PING]), + atomic_read(&rxnet->stat_tx_acks[RXRPC_ACK_PING_RESPONSE]), + atomic_read(&rxnet->stat_tx_acks[RXRPC_ACK_DELAY]), + atomic_read(&rxnet->stat_tx_acks[RXRPC_ACK_IDLE])); + seq_printf(seq, + "Ack-Rx : req=%u dup=%u oos=%u exw=%u nos=%u png=%u prs=%u dly=%u idl=%u\n", + atomic_read(&rxnet->stat_rx_acks[RXRPC_ACK_REQUESTED]), + atomic_read(&rxnet->stat_rx_acks[RXRPC_ACK_DUPLICATE]), + atomic_read(&rxnet->stat_rx_acks[RXRPC_ACK_OUT_OF_SEQUENCE]), + atomic_read(&rxnet->stat_rx_acks[RXRPC_ACK_EXCEEDS_WINDOW]), + atomic_read(&rxnet->stat_rx_acks[RXRPC_ACK_NOSPACE]), + atomic_read(&rxnet->stat_rx_acks[RXRPC_ACK_PING]), + atomic_read(&rxnet->stat_rx_acks[RXRPC_ACK_PING_RESPONSE]), + atomic_read(&rxnet->stat_rx_acks[RXRPC_ACK_DELAY]), + atomic_read(&rxnet->stat_rx_acks[RXRPC_ACK_IDLE])); + seq_printf(seq, + "Why-Req-A: acklost=%u already=%u mrtt=%u ortt=%u\n", + atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_ack_lost]), + atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_already_on]), + atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_more_rtt]), + atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_old_rtt])); + seq_printf(seq, + "Why-Req-A: nolast=%u retx=%u slows=%u smtxw=%u\n", + atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_no_srv_last]), + atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_retrans]), + atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_slow_start]), + atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_small_txwin])); + seq_printf(seq, + "Buffers : txb=%u rxb=%u\n", + atomic_read(&rxrpc_nr_txbuf), + atomic_read(&rxrpc_n_rx_skbs)); + return 0; +} + +/* + * Clear stats if /proc/net/rxrpc/stats is written to. + */ +int rxrpc_stats_clear(struct file *file, char *buf, size_t size) +{ + struct seq_file *m = file->private_data; + struct rxrpc_net *rxnet = rxrpc_net(seq_file_single_net(m)); + + if (size > 1 || (size == 1 && buf[0] != '\n')) + return -EINVAL; + + atomic_set(&rxnet->stat_tx_data, 0); + atomic_set(&rxnet->stat_tx_data_retrans, 0); + atomic_set(&rxnet->stat_tx_data_send, 0); + atomic_set(&rxnet->stat_tx_data_send_frag, 0); + atomic_set(&rxnet->stat_rx_data, 0); + atomic_set(&rxnet->stat_rx_data_reqack, 0); + atomic_set(&rxnet->stat_rx_data_jumbo, 0); + + atomic_set(&rxnet->stat_tx_ack_fill, 0); + atomic_set(&rxnet->stat_tx_ack_send, 0); + atomic_set(&rxnet->stat_tx_ack_skip, 0); + memset(&rxnet->stat_tx_acks, 0, sizeof(rxnet->stat_tx_acks)); + memset(&rxnet->stat_rx_acks, 0, sizeof(rxnet->stat_rx_acks)); + + memset(&rxnet->stat_why_req_ack, 0, sizeof(rxnet->stat_why_req_ack)); + return size; +} diff --git a/net/rxrpc/protocol.h b/net/rxrpc/protocol.h index d2cf8e1d218f..6760cb99c6d6 100644 --- a/net/rxrpc/protocol.h +++ b/net/rxrpc/protocol.h @@ -84,7 +84,7 @@ struct rxrpc_jumbo_header { __be16 _rsvd; /* reserved */ __be16 cksum; /* kerberos security checksum */ }; -}; +} __packed; #define RXRPC_JUMBO_DATALEN 1412 /* non-terminal jumbo packet data length */ #define RXRPC_JUMBO_SUBPKTLEN (RXRPC_JUMBO_DATALEN + sizeof(struct rxrpc_jumbo_header)) @@ -132,13 +132,6 @@ struct rxrpc_ackpacket { } __packed; -/* Some ACKs refer to specific packets and some are general and can be updated. */ -#define RXRPC_ACK_UPDATEABLE ((1 << RXRPC_ACK_REQUESTED) | \ - (1 << RXRPC_ACK_PING_RESPONSE) | \ - (1 << RXRPC_ACK_DELAY) | \ - (1 << RXRPC_ACK_IDLE)) - - /* * ACK packets can have a further piece of information tagged on the end */ diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 7e39c262fd79..efb85f983657 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -173,8 +173,9 @@ static int rxrpc_recvmsg_term(struct rxrpc_call *call, struct msghdr *msg) break; } - trace_rxrpc_recvmsg(call, rxrpc_recvmsg_terminal, call->rx_hard_ack, - call->rx_pkt_offset, call->rx_pkt_len, ret); + trace_rxrpc_recvdata(call, rxrpc_recvmsg_terminal, + lower_32_bits(atomic64_read(&call->ackr_window)) - 1, + call->rx_pkt_offset, call->rx_pkt_len, ret); return ret; } @@ -183,16 +184,14 @@ static int rxrpc_recvmsg_term(struct rxrpc_call *call, struct msghdr *msg) */ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial) { + rxrpc_seq_t whigh = READ_ONCE(call->rx_highest_seq); + _enter("%d,%s", call->debug_id, rxrpc_call_states[call->state]); - trace_rxrpc_receive(call, rxrpc_receive_end, 0, call->rx_top); - ASSERTCMP(call->rx_hard_ack, ==, call->rx_top); + trace_rxrpc_receive(call, rxrpc_receive_end, 0, whigh); - if (call->state == RXRPC_CALL_CLIENT_RECV_REPLY) { - rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, serial, false, true, - rxrpc_propose_ack_terminal_ack); - //rxrpc_send_ack_packet(call, false, NULL); - } + if (call->state == RXRPC_CALL_CLIENT_RECV_REPLY) + rxrpc_propose_delay_ACK(call, serial, rxrpc_propose_ack_terminal_ack); write_lock_bh(&call->state_lock); @@ -203,12 +202,11 @@ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial) break; case RXRPC_CALL_SERVER_RECV_REQUEST: - call->tx_phase = true; call->state = RXRPC_CALL_SERVER_ACK_REQUEST; call->expect_req_by = jiffies + MAX_JIFFY_OFFSET; write_unlock_bh(&call->state_lock); - rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, serial, false, true, - rxrpc_propose_ack_processing_op); + rxrpc_propose_delay_ACK(call, serial, + rxrpc_propose_ack_processing_op); break; default: write_unlock_bh(&call->state_lock); @@ -224,126 +222,66 @@ static void rxrpc_rotate_rx_window(struct rxrpc_call *call) struct rxrpc_skb_priv *sp; struct sk_buff *skb; rxrpc_serial_t serial; - rxrpc_seq_t hard_ack, top; - bool last = false; - u8 subpacket; - int ix; + rxrpc_seq_t old_consumed = call->rx_consumed, tseq; + bool last; + int acked; _enter("%d", call->debug_id); - hard_ack = call->rx_hard_ack; - top = smp_load_acquire(&call->rx_top); - ASSERT(before(hard_ack, top)); - - hard_ack++; - ix = hard_ack & RXRPC_RXTX_BUFF_MASK; - skb = call->rxtx_buffer[ix]; +further_rotation: + skb = skb_dequeue(&call->recvmsg_queue); rxrpc_see_skb(skb, rxrpc_skb_rotated); - sp = rxrpc_skb(skb); - - subpacket = call->rxtx_annotations[ix] & RXRPC_RX_ANNO_SUBPACKET; - serial = sp->hdr.serial + subpacket; - if (subpacket == sp->nr_subpackets - 1 && - sp->rx_flags & RXRPC_SKB_INCL_LAST) - last = true; + sp = rxrpc_skb(skb); + tseq = sp->hdr.seq; + serial = sp->hdr.serial; + last = sp->hdr.flags & RXRPC_LAST_PACKET; - call->rxtx_buffer[ix] = NULL; - call->rxtx_annotations[ix] = 0; /* Barrier against rxrpc_input_data(). */ - smp_store_release(&call->rx_hard_ack, hard_ack); + if (after(tseq, call->rx_consumed)) + smp_store_release(&call->rx_consumed, tseq); rxrpc_free_skb(skb, rxrpc_skb_freed); - trace_rxrpc_receive(call, rxrpc_receive_rotate, serial, hard_ack); + trace_rxrpc_receive(call, last ? rxrpc_receive_rotate_last : rxrpc_receive_rotate, + serial, call->rx_consumed); if (last) { rxrpc_end_rx_phase(call, serial); - } else { - /* Check to see if there's an ACK that needs sending. */ - if (atomic_inc_return(&call->ackr_nr_consumed) > 2) - rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, serial, - true, false, - rxrpc_propose_ack_rotate_rx); - if (call->ackr_reason && call->ackr_reason != RXRPC_ACK_DELAY) - rxrpc_send_ack_packet(call, false, NULL); + return; } -} - -/* - * Decrypt and verify a (sub)packet. The packet's length may be changed due to - * padding, but if this is the case, the packet length will be resident in the - * socket buffer. Note that we can't modify the master skb info as the skb may - * be the home to multiple subpackets. - */ -static int rxrpc_verify_packet(struct rxrpc_call *call, struct sk_buff *skb, - u8 annotation, - unsigned int offset, unsigned int len) -{ - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - rxrpc_seq_t seq = sp->hdr.seq; - u16 cksum = sp->hdr.cksum; - u8 subpacket = annotation & RXRPC_RX_ANNO_SUBPACKET; - _enter(""); - - /* For all but the head jumbo subpacket, the security checksum is in a - * jumbo header immediately prior to the data. + /* The next packet on the queue might entirely overlap with the one we + * just consumed; if so, rotate that away also. */ - if (subpacket > 0) { - __be16 tmp; - if (skb_copy_bits(skb, offset - 2, &tmp, 2) < 0) - BUG(); - cksum = ntohs(tmp); - seq += subpacket; + skb = skb_peek(&call->recvmsg_queue); + if (skb) { + sp = rxrpc_skb(skb); + if (sp->hdr.seq != call->rx_consumed && + after_eq(call->rx_consumed, sp->hdr.seq)) + goto further_rotation; } - return call->security->verify_packet(call, skb, offset, len, - seq, cksum); + /* Check to see if there's an ACK that needs sending. */ + acked = atomic_add_return(call->rx_consumed - old_consumed, + &call->ackr_nr_consumed); + if (acked > 2 && + !test_and_set_bit(RXRPC_CALL_IDLE_ACK_PENDING, &call->flags)) { + rxrpc_send_ACK(call, RXRPC_ACK_IDLE, serial, + rxrpc_propose_ack_rotate_rx); + rxrpc_transmit_ack_packets(call->peer->local); + } } /* - * Locate the data within a packet. This is complicated by: - * - * (1) An skb may contain a jumbo packet - so we have to find the appropriate - * subpacket. - * - * (2) The (sub)packets may be encrypted and, if so, the encrypted portion - * contains an extra header which includes the true length of the data, - * excluding any encrypted padding. + * Decrypt and verify a DATA packet. */ -static int rxrpc_locate_data(struct rxrpc_call *call, struct sk_buff *skb, - u8 *_annotation, - unsigned int *_offset, unsigned int *_len, - bool *_last) +static int rxrpc_verify_data(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - unsigned int offset = sizeof(struct rxrpc_wire_header); - unsigned int len; - bool last = false; - int ret; - u8 annotation = *_annotation; - u8 subpacket = annotation & RXRPC_RX_ANNO_SUBPACKET; - - /* Locate the subpacket */ - offset += subpacket * RXRPC_JUMBO_SUBPKTLEN; - len = skb->len - offset; - if (subpacket < sp->nr_subpackets - 1) - len = RXRPC_JUMBO_DATALEN; - else if (sp->rx_flags & RXRPC_SKB_INCL_LAST) - last = true; - - if (!(annotation & RXRPC_RX_ANNO_VERIFIED)) { - ret = rxrpc_verify_packet(call, skb, annotation, offset, len); - if (ret < 0) - return ret; - *_annotation |= RXRPC_RX_ANNO_VERIFIED; - } - *_offset = offset; - *_len = len; - *_last = last; - call->security->locate_data(call, skb, _offset, _len); - return 0; + if (sp->flags & RXRPC_RX_VERIFIED) + return 0; + return call->security->verify_packet(call, skb); } /* @@ -357,69 +295,55 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, { struct rxrpc_skb_priv *sp; struct sk_buff *skb; - rxrpc_serial_t serial; - rxrpc_seq_t hard_ack, top, seq; + rxrpc_seq_t seq = 0; size_t remain; - bool rx_pkt_last; unsigned int rx_pkt_offset, rx_pkt_len; - int ix, copy, ret = -EAGAIN, ret2; - - if (test_and_clear_bit(RXRPC_CALL_RX_UNDERRUN, &call->flags) && - call->ackr_reason) - rxrpc_send_ack_packet(call, false, NULL); + int copy, ret = -EAGAIN, ret2; rx_pkt_offset = call->rx_pkt_offset; rx_pkt_len = call->rx_pkt_len; - rx_pkt_last = call->rx_pkt_last; if (call->state >= RXRPC_CALL_SERVER_ACK_REQUEST) { - seq = call->rx_hard_ack; + seq = lower_32_bits(atomic64_read(&call->ackr_window)) - 1; ret = 1; goto done; } - /* Barriers against rxrpc_input_data(). */ - hard_ack = call->rx_hard_ack; - seq = hard_ack + 1; - - while (top = smp_load_acquire(&call->rx_top), - before_eq(seq, top) - ) { - ix = seq & RXRPC_RXTX_BUFF_MASK; - skb = call->rxtx_buffer[ix]; - if (!skb) { - trace_rxrpc_recvmsg(call, rxrpc_recvmsg_hole, seq, - rx_pkt_offset, rx_pkt_len, 0); - break; - } - smp_rmb(); + /* No one else can be removing stuff from the queue, so we shouldn't + * need the Rx lock to walk it. + */ + skb = skb_peek(&call->recvmsg_queue); + while (skb) { rxrpc_see_skb(skb, rxrpc_skb_seen); sp = rxrpc_skb(skb); + seq = sp->hdr.seq; - if (!(flags & MSG_PEEK)) { - serial = sp->hdr.serial; - serial += call->rxtx_annotations[ix] & RXRPC_RX_ANNO_SUBPACKET; - trace_rxrpc_receive(call, rxrpc_receive_front, - serial, seq); + if (after_eq(call->rx_consumed, seq)) { + kdebug("obsolete %x %x", call->rx_consumed, seq); + goto skip_obsolete; } + if (!(flags & MSG_PEEK)) + trace_rxrpc_receive(call, rxrpc_receive_front, + sp->hdr.serial, seq); + if (msg) sock_recv_timestamp(msg, sock->sk, skb); if (rx_pkt_offset == 0) { - ret2 = rxrpc_locate_data(call, skb, - &call->rxtx_annotations[ix], - &rx_pkt_offset, &rx_pkt_len, - &rx_pkt_last); - trace_rxrpc_recvmsg(call, rxrpc_recvmsg_next, seq, - rx_pkt_offset, rx_pkt_len, ret2); + ret2 = rxrpc_verify_data(call, skb); + rx_pkt_offset = sp->offset; + rx_pkt_len = sp->len; + trace_rxrpc_recvdata(call, rxrpc_recvmsg_next, seq, + rx_pkt_offset, rx_pkt_len, ret2); if (ret2 < 0) { ret = ret2; goto out; } + rxrpc_transmit_ack_packets(call->peer->local); } else { - trace_rxrpc_recvmsg(call, rxrpc_recvmsg_cont, seq, - rx_pkt_offset, rx_pkt_len, 0); + trace_rxrpc_recvdata(call, rxrpc_recvmsg_cont, seq, + rx_pkt_offset, rx_pkt_len, 0); } /* We have to handle short, empty and used-up DATA packets. */ @@ -442,37 +366,34 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, } if (rx_pkt_len > 0) { - trace_rxrpc_recvmsg(call, rxrpc_recvmsg_full, seq, - rx_pkt_offset, rx_pkt_len, 0); + trace_rxrpc_recvdata(call, rxrpc_recvmsg_full, seq, + rx_pkt_offset, rx_pkt_len, 0); ASSERTCMP(*_offset, ==, len); ret = 0; break; } + skip_obsolete: /* The whole packet has been transferred. */ - if (!(flags & MSG_PEEK)) - rxrpc_rotate_rx_window(call); + if (sp->hdr.flags & RXRPC_LAST_PACKET) + ret = 1; rx_pkt_offset = 0; rx_pkt_len = 0; - if (rx_pkt_last) { - ASSERTCMP(seq, ==, READ_ONCE(call->rx_top)); - ret = 1; - goto out; - } + skb = skb_peek_next(skb, &call->recvmsg_queue); - seq++; + if (!(flags & MSG_PEEK)) + rxrpc_rotate_rx_window(call); } out: if (!(flags & MSG_PEEK)) { call->rx_pkt_offset = rx_pkt_offset; call->rx_pkt_len = rx_pkt_len; - call->rx_pkt_last = rx_pkt_last; } done: - trace_rxrpc_recvmsg(call, rxrpc_recvmsg_data_return, seq, - rx_pkt_offset, rx_pkt_len, ret); + trace_rxrpc_recvdata(call, rxrpc_recvmsg_data_return, seq, + rx_pkt_offset, rx_pkt_len, ret); if (ret == -EAGAIN) set_bit(RXRPC_CALL_RX_UNDERRUN, &call->flags); return ret; @@ -495,7 +416,7 @@ int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, DEFINE_WAIT(wait); - trace_rxrpc_recvmsg(NULL, rxrpc_recvmsg_enter, 0, 0, 0, 0); + trace_rxrpc_recvmsg(NULL, rxrpc_recvmsg_enter, 0); if (flags & (MSG_OOB | MSG_TRUNC)) return -EOPNOTSUPP; @@ -532,8 +453,7 @@ try_again: if (list_empty(&rx->recvmsg_q)) { if (signal_pending(current)) goto wait_interrupted; - trace_rxrpc_recvmsg(NULL, rxrpc_recvmsg_wait, - 0, 0, 0, 0); + trace_rxrpc_recvmsg(NULL, rxrpc_recvmsg_wait, 0); timeo = schedule_timeout(timeo); } finish_wait(sk_sleep(&rx->sk), &wait); @@ -552,7 +472,7 @@ try_again: rxrpc_get_call(call, rxrpc_call_got); write_unlock_bh(&rx->recvmsg_lock); - trace_rxrpc_recvmsg(call, rxrpc_recvmsg_dequeue, 0, 0, 0, 0); + trace_rxrpc_recvmsg(call, rxrpc_recvmsg_dequeue, 0); /* We're going to drop the socket lock, so we need to lock the call * against interference by sendmsg. @@ -605,8 +525,8 @@ try_again: if (ret == -EAGAIN) ret = 0; - if (after(call->rx_top, call->rx_hard_ack) && - call->rxtx_buffer[(call->rx_hard_ack + 1) & RXRPC_RXTX_BUFF_MASK]) + rxrpc_transmit_ack_packets(call->peer->local); + if (!skb_queue_empty(&call->recvmsg_queue)) rxrpc_notify_socket(call); break; default: @@ -636,7 +556,7 @@ try_again: error_unlock_call: mutex_unlock(&call->user_mutex); rxrpc_put_call(call, rxrpc_call_put); - trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, 0, 0, 0, ret); + trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, ret); return ret; error_requeue_call: @@ -644,14 +564,14 @@ error_requeue_call: write_lock_bh(&rx->recvmsg_lock); list_add(&call->recvmsg_link, &rx->recvmsg_q); write_unlock_bh(&rx->recvmsg_lock); - trace_rxrpc_recvmsg(call, rxrpc_recvmsg_requeue, 0, 0, 0, 0); + trace_rxrpc_recvmsg(call, rxrpc_recvmsg_requeue, 0); } else { rxrpc_put_call(call, rxrpc_call_put); } error_no_call: release_sock(&rx->sk); error_trace: - trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, 0, 0, 0, ret); + trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, ret); return ret; wait_interrupted: @@ -735,17 +655,7 @@ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call, read_phase_complete: ret = 1; out: - switch (call->ackr_reason) { - case RXRPC_ACK_IDLE: - break; - case RXRPC_ACK_DELAY: - if (ret != -EAGAIN) - break; - fallthrough; - default: - rxrpc_send_ack_packet(call, false, NULL); - } - + rxrpc_transmit_ack_packets(call->peer->local); if (_service) *_service = call->service_id; mutex_unlock(&call->user_mutex); diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index 78fa0524156f..2706e59bf992 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -233,16 +233,8 @@ static int rxkad_prime_packet_security(struct rxrpc_connection *conn, static struct skcipher_request *rxkad_get_call_crypto(struct rxrpc_call *call) { struct crypto_skcipher *tfm = &call->conn->rxkad.cipher->base; - struct skcipher_request *cipher_req = call->cipher_req; - if (!cipher_req) { - cipher_req = skcipher_request_alloc(tfm, GFP_NOFS); - if (!cipher_req) - return NULL; - call->cipher_req = cipher_req; - } - - return cipher_req; + return skcipher_request_alloc(tfm, GFP_NOFS); } /* @@ -250,20 +242,16 @@ static struct skcipher_request *rxkad_get_call_crypto(struct rxrpc_call *call) */ static void rxkad_free_call_crypto(struct rxrpc_call *call) { - if (call->cipher_req) - skcipher_request_free(call->cipher_req); - call->cipher_req = NULL; } /* * partially encrypt a packet (level 1 security) */ static int rxkad_secure_packet_auth(const struct rxrpc_call *call, - struct sk_buff *skb, u32 data_size, + struct rxrpc_txbuf *txb, struct skcipher_request *req) { - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - struct rxkad_level1_hdr hdr; + struct rxkad_level1_hdr *hdr = (void *)txb->data; struct rxrpc_crypt iv; struct scatterlist sg; size_t pad; @@ -271,22 +259,22 @@ static int rxkad_secure_packet_auth(const struct rxrpc_call *call, _enter(""); - check = sp->hdr.seq ^ call->call_id; - data_size |= (u32)check << 16; + check = txb->seq ^ ntohl(txb->wire.callNumber); + hdr->data_size = htonl((u32)check << 16 | txb->len); - hdr.data_size = htonl(data_size); - memcpy(skb->head, &hdr, sizeof(hdr)); - - pad = sizeof(struct rxkad_level1_hdr) + data_size; + txb->len += sizeof(struct rxkad_level1_hdr); + pad = txb->len; pad = RXKAD_ALIGN - pad; pad &= RXKAD_ALIGN - 1; - if (pad) - skb_put_zero(skb, pad); + if (pad) { + memset(txb->data + txb->offset, 0, pad); + txb->len += pad; + } /* start the encryption afresh */ memset(&iv, 0, sizeof(iv)); - sg_init_one(&sg, skb->head, 8); + sg_init_one(&sg, txb->data, 8); skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher); skcipher_request_set_callback(req, 0, NULL, NULL); skcipher_request_set_crypt(req, &sg, &sg, 8, iv.x); @@ -301,87 +289,63 @@ static int rxkad_secure_packet_auth(const struct rxrpc_call *call, * wholly encrypt a packet (level 2 security) */ static int rxkad_secure_packet_encrypt(const struct rxrpc_call *call, - struct sk_buff *skb, - u32 data_size, + struct rxrpc_txbuf *txb, struct skcipher_request *req) { const struct rxrpc_key_token *token; - struct rxkad_level2_hdr rxkhdr; - struct rxrpc_skb_priv *sp; + struct rxkad_level2_hdr *rxkhdr = (void *)txb->data; struct rxrpc_crypt iv; - struct scatterlist sg[16]; - unsigned int len; + struct scatterlist sg; size_t pad; u16 check; - int err; - - sp = rxrpc_skb(skb); + int ret; _enter(""); - check = sp->hdr.seq ^ call->call_id; + check = txb->seq ^ ntohl(txb->wire.callNumber); - rxkhdr.data_size = htonl(data_size | (u32)check << 16); - rxkhdr.checksum = 0; - memcpy(skb->head, &rxkhdr, sizeof(rxkhdr)); + rxkhdr->data_size = htonl(txb->len | (u32)check << 16); + rxkhdr->checksum = 0; - pad = sizeof(struct rxkad_level2_hdr) + data_size; + txb->len += sizeof(struct rxkad_level2_hdr); + pad = txb->len; pad = RXKAD_ALIGN - pad; pad &= RXKAD_ALIGN - 1; - if (pad) - skb_put_zero(skb, pad); + if (pad) { + memset(txb->data + txb->offset, 0, pad); + txb->len += pad; + } /* encrypt from the session key */ token = call->conn->params.key->payload.data[0]; memcpy(&iv, token->kad->session_key, sizeof(iv)); - sg_init_one(&sg[0], skb->head, sizeof(rxkhdr)); + sg_init_one(&sg, txb->data, txb->len); skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher); skcipher_request_set_callback(req, 0, NULL, NULL); - skcipher_request_set_crypt(req, &sg[0], &sg[0], sizeof(rxkhdr), iv.x); - crypto_skcipher_encrypt(req); - - /* we want to encrypt the skbuff in-place */ - err = -EMSGSIZE; - if (skb_shinfo(skb)->nr_frags > 16) - goto out; - - len = round_up(data_size, RXKAD_ALIGN); - - sg_init_table(sg, ARRAY_SIZE(sg)); - err = skb_to_sgvec(skb, sg, 8, len); - if (unlikely(err < 0)) - goto out; - skcipher_request_set_crypt(req, sg, sg, len, iv.x); - crypto_skcipher_encrypt(req); - - _leave(" = 0"); - err = 0; - -out: + skcipher_request_set_crypt(req, &sg, &sg, txb->len, iv.x); + ret = crypto_skcipher_encrypt(req); skcipher_request_zero(req); - return err; + return ret; } /* * checksum an RxRPC packet header */ -static int rxkad_secure_packet(struct rxrpc_call *call, - struct sk_buff *skb, - size_t data_size) +static int rxkad_secure_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) { - struct rxrpc_skb_priv *sp; struct skcipher_request *req; struct rxrpc_crypt iv; struct scatterlist sg; + union { + __be32 buf[2]; + } crypto __aligned(8); u32 x, y; int ret; - sp = rxrpc_skb(skb); - - _enter("{%d{%x}},{#%u},%zu,", + _enter("{%d{%x}},{#%u},%u,", call->debug_id, key_serial(call->conn->params.key), - sp->hdr.seq, data_size); + txb->seq, txb->len); if (!call->conn->rxkad.cipher) return 0; @@ -398,39 +362,40 @@ static int rxkad_secure_packet(struct rxrpc_call *call, memcpy(&iv, call->conn->rxkad.csum_iv.x, sizeof(iv)); /* calculate the security checksum */ - x = (call->cid & RXRPC_CHANNELMASK) << (32 - RXRPC_CIDSHIFT); - x |= sp->hdr.seq & 0x3fffffff; - call->crypto_buf[0] = htonl(call->call_id); - call->crypto_buf[1] = htonl(x); + x = (ntohl(txb->wire.cid) & RXRPC_CHANNELMASK) << (32 - RXRPC_CIDSHIFT); + x |= txb->seq & 0x3fffffff; + crypto.buf[0] = txb->wire.callNumber; + crypto.buf[1] = htonl(x); - sg_init_one(&sg, call->crypto_buf, 8); + sg_init_one(&sg, crypto.buf, 8); skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher); skcipher_request_set_callback(req, 0, NULL, NULL); skcipher_request_set_crypt(req, &sg, &sg, 8, iv.x); crypto_skcipher_encrypt(req); skcipher_request_zero(req); - y = ntohl(call->crypto_buf[1]); + y = ntohl(crypto.buf[1]); y = (y >> 16) & 0xffff; if (y == 0) y = 1; /* zero checksums are not permitted */ - sp->hdr.cksum = y; + txb->wire.cksum = htons(y); switch (call->conn->params.security_level) { case RXRPC_SECURITY_PLAIN: ret = 0; break; case RXRPC_SECURITY_AUTH: - ret = rxkad_secure_packet_auth(call, skb, data_size, req); + ret = rxkad_secure_packet_auth(call, txb, req); break; case RXRPC_SECURITY_ENCRYPT: - ret = rxkad_secure_packet_encrypt(call, skb, data_size, req); + ret = rxkad_secure_packet_encrypt(call, txb, req); break; default: ret = -EPERM; break; } + skcipher_request_free(req); _leave(" = %d [set %x]", ret, y); return ret; } @@ -439,11 +404,11 @@ static int rxkad_secure_packet(struct rxrpc_call *call, * decrypt partial encryption on a packet (level 1 security) */ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb, - unsigned int offset, unsigned int len, rxrpc_seq_t seq, struct skcipher_request *req) { struct rxkad_level1_hdr sechdr; + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_crypt iv; struct scatterlist sg[16]; bool aborted; @@ -453,9 +418,9 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb, _enter(""); - if (len < 8) { + if (sp->len < 8) { aborted = rxrpc_abort_eproto(call, skb, "rxkad_1_hdr", "V1H", - RXKADSEALEDINCON); + RXKADSEALEDINCON); goto protocol_error; } @@ -463,7 +428,7 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb, * directly into the target buffer. */ sg_init_table(sg, ARRAY_SIZE(sg)); - ret = skb_to_sgvec(skb, sg, offset, 8); + ret = skb_to_sgvec(skb, sg, sp->offset, 8); if (unlikely(ret < 0)) return ret; @@ -477,12 +442,13 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb, skcipher_request_zero(req); /* Extract the decrypted packet length */ - if (skb_copy_bits(skb, offset, &sechdr, sizeof(sechdr)) < 0) { + if (skb_copy_bits(skb, sp->offset, &sechdr, sizeof(sechdr)) < 0) { aborted = rxrpc_abort_eproto(call, skb, "rxkad_1_len", "XV1", RXKADDATALEN); goto protocol_error; } - len -= sizeof(sechdr); + sp->offset += sizeof(sechdr); + sp->len -= sizeof(sechdr); buf = ntohl(sechdr.data_size); data_size = buf & 0xffff; @@ -496,11 +462,12 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb, goto protocol_error; } - if (data_size > len) { + if (data_size > sp->len) { aborted = rxrpc_abort_eproto(call, skb, "rxkad_1_datalen", "V1L", RXKADDATALEN); goto protocol_error; } + sp->len = data_size; _leave(" = 0 [dlen=%x]", data_size); return 0; @@ -515,12 +482,12 @@ protocol_error: * wholly decrypt a packet (level 2 security) */ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, - unsigned int offset, unsigned int len, rxrpc_seq_t seq, struct skcipher_request *req) { const struct rxrpc_key_token *token; struct rxkad_level2_hdr sechdr; + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_crypt iv; struct scatterlist _sg[4], *sg; bool aborted; @@ -528,9 +495,9 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, u16 check; int nsg, ret; - _enter(",{%d}", skb->len); + _enter(",{%d}", sp->len); - if (len < 8) { + if (sp->len < 8) { aborted = rxrpc_abort_eproto(call, skb, "rxkad_2_hdr", "V2H", RXKADSEALEDINCON); goto protocol_error; @@ -550,7 +517,7 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, } sg_init_table(sg, nsg); - ret = skb_to_sgvec(skb, sg, offset, len); + ret = skb_to_sgvec(skb, sg, sp->offset, sp->len); if (unlikely(ret < 0)) { if (sg != _sg) kfree(sg); @@ -563,19 +530,20 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher); skcipher_request_set_callback(req, 0, NULL, NULL); - skcipher_request_set_crypt(req, sg, sg, len, iv.x); + skcipher_request_set_crypt(req, sg, sg, sp->len, iv.x); crypto_skcipher_decrypt(req); skcipher_request_zero(req); if (sg != _sg) kfree(sg); /* Extract the decrypted packet length */ - if (skb_copy_bits(skb, offset, &sechdr, sizeof(sechdr)) < 0) { + if (skb_copy_bits(skb, sp->offset, &sechdr, sizeof(sechdr)) < 0) { aborted = rxrpc_abort_eproto(call, skb, "rxkad_2_len", "XV2", RXKADDATALEN); goto protocol_error; } - len -= sizeof(sechdr); + sp->offset += sizeof(sechdr); + sp->len -= sizeof(sechdr); buf = ntohl(sechdr.data_size); data_size = buf & 0xffff; @@ -589,12 +557,13 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, goto protocol_error; } - if (data_size > len) { + if (data_size > sp->len) { aborted = rxrpc_abort_eproto(call, skb, "rxkad_2_datalen", "V2L", RXKADDATALEN); goto protocol_error; } + sp->len = data_size; _leave(" = 0 [dlen=%x]", data_size); return 0; @@ -609,17 +578,20 @@ nomem: } /* - * Verify the security on a received packet or subpacket (if part of a - * jumbo packet). + * Verify the security on a received packet and the subpackets therein. */ -static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb, - unsigned int offset, unsigned int len, - rxrpc_seq_t seq, u16 expected_cksum) +static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb) { + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct skcipher_request *req; struct rxrpc_crypt iv; struct scatterlist sg; + union { + __be32 buf[2]; + } crypto __aligned(8); + rxrpc_seq_t seq = sp->hdr.seq; bool aborted; + int ret; u16 cksum; u32 x, y; @@ -639,22 +611,22 @@ static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb, /* validate the security checksum */ x = (call->cid & RXRPC_CHANNELMASK) << (32 - RXRPC_CIDSHIFT); x |= seq & 0x3fffffff; - call->crypto_buf[0] = htonl(call->call_id); - call->crypto_buf[1] = htonl(x); + crypto.buf[0] = htonl(call->call_id); + crypto.buf[1] = htonl(x); - sg_init_one(&sg, call->crypto_buf, 8); + sg_init_one(&sg, crypto.buf, 8); skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher); skcipher_request_set_callback(req, 0, NULL, NULL); skcipher_request_set_crypt(req, &sg, &sg, 8, iv.x); crypto_skcipher_encrypt(req); skcipher_request_zero(req); - y = ntohl(call->crypto_buf[1]); + y = ntohl(crypto.buf[1]); cksum = (y >> 16) & 0xffff; if (cksum == 0) cksum = 1; /* zero checksums are not permitted */ - if (cksum != expected_cksum) { + if (cksum != sp->hdr.cksum) { aborted = rxrpc_abort_eproto(call, skb, "rxkad_csum", "VCK", RXKADSEALEDINCON); goto protocol_error; @@ -662,15 +634,22 @@ static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb, switch (call->conn->params.security_level) { case RXRPC_SECURITY_PLAIN: - return 0; + ret = 0; + break; case RXRPC_SECURITY_AUTH: - return rxkad_verify_packet_1(call, skb, offset, len, seq, req); + ret = rxkad_verify_packet_1(call, skb, seq, req); + break; case RXRPC_SECURITY_ENCRYPT: - return rxkad_verify_packet_2(call, skb, offset, len, seq, req); + ret = rxkad_verify_packet_2(call, skb, seq, req); + break; default: - return -ENOANO; + ret = -ENOANO; + break; } + skcipher_request_free(req); + return ret; + protocol_error: if (aborted) rxrpc_send_abort_packet(call); @@ -678,52 +657,6 @@ protocol_error: } /* - * Locate the data contained in a packet that was partially encrypted. - */ -static void rxkad_locate_data_1(struct rxrpc_call *call, struct sk_buff *skb, - unsigned int *_offset, unsigned int *_len) -{ - struct rxkad_level1_hdr sechdr; - - if (skb_copy_bits(skb, *_offset, &sechdr, sizeof(sechdr)) < 0) - BUG(); - *_offset += sizeof(sechdr); - *_len = ntohl(sechdr.data_size) & 0xffff; -} - -/* - * Locate the data contained in a packet that was completely encrypted. - */ -static void rxkad_locate_data_2(struct rxrpc_call *call, struct sk_buff *skb, - unsigned int *_offset, unsigned int *_len) -{ - struct rxkad_level2_hdr sechdr; - - if (skb_copy_bits(skb, *_offset, &sechdr, sizeof(sechdr)) < 0) - BUG(); - *_offset += sizeof(sechdr); - *_len = ntohl(sechdr.data_size) & 0xffff; -} - -/* - * Locate the data contained in an already decrypted packet. - */ -static void rxkad_locate_data(struct rxrpc_call *call, struct sk_buff *skb, - unsigned int *_offset, unsigned int *_len) -{ - switch (call->conn->params.security_level) { - case RXRPC_SECURITY_AUTH: - rxkad_locate_data_1(call, skb, _offset, _len); - return; - case RXRPC_SECURITY_ENCRYPT: - rxkad_locate_data_2(call, skb, _offset, _len); - return; - default: - return; - } -} - -/* * issue a challenge */ static int rxkad_issue_challenge(struct rxrpc_connection *conn) @@ -1234,7 +1167,6 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, abort_code = RXKADPACKETSHORT; if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header) + sizeof(*response), ticket, ticket_len) < 0) - goto protocol_error_free; ret = rxkad_decrypt_ticket(conn, server_key, skb, ticket, ticket_len, &session_key, &expiry, _abort_code); @@ -1397,7 +1329,6 @@ const struct rxrpc_security rxkad = { .secure_packet = rxkad_secure_packet, .verify_packet = rxkad_verify_packet, .free_call_crypto = rxkad_free_call_crypto, - .locate_data = rxkad_locate_data, .issue_challenge = rxkad_issue_challenge, .respond_to_challenge = rxkad_respond_to_challenge, .verify_response = rxkad_verify_response, diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 3c3a626459de..e5fd8a95bf71 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -22,10 +22,26 @@ */ static bool rxrpc_check_tx_space(struct rxrpc_call *call, rxrpc_seq_t *_tx_win) { - unsigned int win_size = - min_t(unsigned int, call->tx_winsize, - call->cong_cwnd + call->cong_extra); - rxrpc_seq_t tx_win = READ_ONCE(call->tx_hard_ack); + unsigned int win_size; + rxrpc_seq_t tx_win = smp_load_acquire(&call->acks_hard_ack); + + /* If we haven't transmitted anything for >1RTT, we should reset the + * congestion management state. + */ + if (ktime_before(ktime_add_us(call->tx_last_sent, + call->peer->srtt_us >> 3), + ktime_get_real())) { + if (RXRPC_TX_SMSS > 2190) + win_size = 2; + else if (RXRPC_TX_SMSS > 1095) + win_size = 3; + else + win_size = 4; + win_size += call->cong_extra; + } else { + win_size = min_t(unsigned int, call->tx_winsize, + call->cong_cwnd + call->cong_extra); + } if (_tx_win) *_tx_win = tx_win; @@ -50,7 +66,12 @@ static int rxrpc_wait_for_tx_window_intr(struct rxrpc_sock *rx, if (signal_pending(current)) return sock_intr_errno(*timeo); - trace_rxrpc_transmit(call, rxrpc_transmit_wait); + if (READ_ONCE(call->acks_hard_ack) != call->tx_bottom) { + rxrpc_shrink_call_tx_buffer(call); + continue; + } + + trace_rxrpc_txqueue(call, rxrpc_txqueue_wait); *timeo = schedule_timeout(*timeo); } } @@ -71,12 +92,11 @@ static int rxrpc_wait_for_tx_window_waitall(struct rxrpc_sock *rx, rtt = 2; timeout = rtt; - tx_start = READ_ONCE(call->tx_hard_ack); + tx_start = smp_load_acquire(&call->acks_hard_ack); for (;;) { set_current_state(TASK_UNINTERRUPTIBLE); - tx_win = READ_ONCE(call->tx_hard_ack); if (rxrpc_check_tx_space(call, &tx_win)) return 0; @@ -87,12 +107,17 @@ static int rxrpc_wait_for_tx_window_waitall(struct rxrpc_sock *rx, tx_win == tx_start && signal_pending(current)) return -EINTR; + if (READ_ONCE(call->acks_hard_ack) != call->tx_bottom) { + rxrpc_shrink_call_tx_buffer(call); + continue; + } + if (tx_win != tx_start) { timeout = rtt; tx_start = tx_win; } - trace_rxrpc_transmit(call, rxrpc_transmit_wait); + trace_rxrpc_txqueue(call, rxrpc_txqueue_wait); timeout = schedule_timeout(timeout); } } @@ -112,7 +137,12 @@ static int rxrpc_wait_for_tx_window_nonintr(struct rxrpc_sock *rx, if (call->state >= RXRPC_CALL_COMPLETE) return call->error; - trace_rxrpc_transmit(call, rxrpc_transmit_wait); + if (READ_ONCE(call->acks_hard_ack) != call->tx_bottom) { + rxrpc_shrink_call_tx_buffer(call); + continue; + } + + trace_rxrpc_txqueue(call, rxrpc_txqueue_wait); *timeo = schedule_timeout(*timeo); } } @@ -129,8 +159,8 @@ static int rxrpc_wait_for_tx_window(struct rxrpc_sock *rx, DECLARE_WAITQUEUE(myself, current); int ret; - _enter(",{%u,%u,%u}", - call->tx_hard_ack, call->tx_top, call->tx_winsize); + _enter(",{%u,%u,%u,%u}", + call->tx_bottom, call->acks_hard_ack, call->tx_top, call->tx_winsize); add_wait_queue(&call->waitq, &myself); @@ -155,24 +185,6 @@ static int rxrpc_wait_for_tx_window(struct rxrpc_sock *rx, } /* - * Schedule an instant Tx resend. - */ -static inline void rxrpc_instant_resend(struct rxrpc_call *call, int ix) -{ - spin_lock_bh(&call->lock); - - if (call->state < RXRPC_CALL_COMPLETE) { - call->rxtx_annotations[ix] = - (call->rxtx_annotations[ix] & RXRPC_TX_ANNO_LAST) | - RXRPC_TX_ANNO_RETRANS; - if (!test_and_set_bit(RXRPC_CALL_EV_RESEND, &call->events)) - rxrpc_queue_call(call); - } - - spin_unlock_bh(&call->lock); -} - -/* * Notify the owner of the call that the transmit phase is ended and the last * packet has been queued. */ @@ -188,38 +200,35 @@ static void rxrpc_notify_end_tx(struct rxrpc_sock *rx, struct rxrpc_call *call, * the packet immediately. Returns the error from rxrpc_send_data_packet() * in case the caller wants to do something with it. */ -static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, - struct sk_buff *skb, bool last, - rxrpc_notify_end_tx_t notify_end_tx) +static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, + struct rxrpc_txbuf *txb, + rxrpc_notify_end_tx_t notify_end_tx) { - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); unsigned long now; - rxrpc_seq_t seq = sp->hdr.seq; - int ret, ix; - u8 annotation = RXRPC_TX_ANNO_UNACK; + rxrpc_seq_t seq = txb->seq; + bool last = test_bit(RXRPC_TXBUF_LAST, &txb->flags); + int ret; - _net("queue skb %p [%d]", skb, seq); + rxrpc_inc_stat(call->rxnet, stat_tx_data); ASSERTCMP(seq, ==, call->tx_top + 1); - if (last) - annotation |= RXRPC_TX_ANNO_LAST; - /* We have to set the timestamp before queueing as the retransmit * algorithm can see the packet as soon as we queue it. */ - skb->tstamp = ktime_get_real(); + txb->last_sent = ktime_get_real(); - ix = seq & RXRPC_RXTX_BUFF_MASK; - rxrpc_get_skb(skb, rxrpc_skb_got); - call->rxtx_annotations[ix] = annotation; - smp_wmb(); - call->rxtx_buffer[ix] = skb; + /* Add the packet to the call's output buffer */ + rxrpc_get_txbuf(txb, rxrpc_txbuf_get_buffer); + spin_lock(&call->tx_lock); + list_add_tail(&txb->call_link, &call->tx_buffer); call->tx_top = seq; + spin_unlock(&call->tx_lock); + if (last) - trace_rxrpc_transmit(call, rxrpc_transmit_queue_last); + trace_rxrpc_txqueue(call, rxrpc_txqueue_queue_last); else - trace_rxrpc_transmit(call, rxrpc_transmit_queue); + trace_rxrpc_txqueue(call, rxrpc_txqueue_queue); if (last || call->state == RXRPC_CALL_SERVER_ACK_REQUEST) { _debug("________awaiting reply/ACK__________"); @@ -232,7 +241,7 @@ static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, case RXRPC_CALL_SERVER_ACK_REQUEST: call->state = RXRPC_CALL_SERVER_SEND_REPLY; now = jiffies; - WRITE_ONCE(call->ack_at, now + MAX_JIFFY_OFFSET); + WRITE_ONCE(call->delay_ack_at, now + MAX_JIFFY_OFFSET); if (call->ackr_reason == RXRPC_ACK_DELAY) call->ackr_reason = 0; trace_rxrpc_timer(call, rxrpc_timer_init_for_send_reply, now); @@ -252,7 +261,7 @@ static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, if (seq == 1 && rxrpc_is_client_call(call)) rxrpc_expose_client_call(call); - ret = rxrpc_send_data_packet(call, skb, false); + ret = rxrpc_send_data_packet(call, txb); if (ret < 0) { switch (ret) { case -ENETUNREACH: @@ -262,8 +271,6 @@ static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, 0, ret); goto out; } - _debug("need instant resend %d", ret); - rxrpc_instant_resend(call, ix); } else { unsigned long now = jiffies; unsigned long resend_at = now + call->peer->rto_j; @@ -274,9 +281,7 @@ static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, } out: - rxrpc_free_skb(skb, rxrpc_skb_freed); - _leave(" = %d", ret); - return ret; + rxrpc_put_txbuf(txb, rxrpc_txbuf_put_trans); } /* @@ -290,8 +295,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, rxrpc_notify_end_tx_t notify_end_tx, bool *_dropped_lock) { - struct rxrpc_skb_priv *sp; - struct sk_buff *skb; + struct rxrpc_txbuf *txb; struct sock *sk = &rx->sk; enum rxrpc_call_state state; long timeo; @@ -325,16 +329,15 @@ reload: goto maybe_error; } - skb = call->tx_pending; + txb = call->tx_pending; call->tx_pending = NULL; - rxrpc_see_skb(skb, rxrpc_skb_seen); + if (txb) + rxrpc_see_txbuf(txb, rxrpc_txbuf_see_send_more); do { - /* Check to see if there's a ping ACK to reply to. */ - if (call->ackr_reason == RXRPC_ACK_PING_RESPONSE) - rxrpc_send_ack_packet(call, false, NULL); + rxrpc_transmit_ack_packets(call->peer->local); - if (!skb) { + if (!txb) { size_t remain, bufsize, chunk, offset; _debug("alloc"); @@ -355,53 +358,31 @@ reload: _debug("SIZE: %zu/%zu @%zu", chunk, bufsize, offset); /* create a buffer that we can retain until it's ACK'd */ - skb = sock_alloc_send_skb( - sk, bufsize, msg->msg_flags & MSG_DONTWAIT, &ret); - if (!skb) + ret = -ENOMEM; + txb = rxrpc_alloc_txbuf(call, RXRPC_PACKET_TYPE_DATA, + GFP_KERNEL); + if (!txb) goto maybe_error; - sp = rxrpc_skb(skb); - sp->rx_flags |= RXRPC_SKB_TX_BUFFER; - rxrpc_new_skb(skb, rxrpc_skb_new); - - _debug("ALLOC SEND %p", skb); - - ASSERTCMP(skb->mark, ==, 0); - - __skb_put(skb, offset); - - sp->remain = chunk; - if (sp->remain > skb_tailroom(skb)) - sp->remain = skb_tailroom(skb); - - _net("skb: hr %d, tr %d, hl %d, rm %d", - skb_headroom(skb), - skb_tailroom(skb), - skb_headlen(skb), - sp->remain); - - skb->ip_summed = CHECKSUM_UNNECESSARY; + txb->offset = offset; + txb->space -= offset; + txb->space = min_t(size_t, chunk, txb->space); } _debug("append"); - sp = rxrpc_skb(skb); /* append next segment of data to the current buffer */ if (msg_data_left(msg) > 0) { - int copy = skb_tailroom(skb); - ASSERTCMP(copy, >, 0); - if (copy > msg_data_left(msg)) - copy = msg_data_left(msg); - if (copy > sp->remain) - copy = sp->remain; - - _debug("add"); - ret = skb_add_data(skb, &msg->msg_iter, copy); - _debug("added"); - if (ret < 0) + size_t copy = min_t(size_t, txb->space, msg_data_left(msg)); + + _debug("add %zu", copy); + if (!copy_from_iter_full(txb->data + txb->offset, copy, + &msg->msg_iter)) goto efault; - sp->remain -= copy; - skb->mark += copy; + _debug("added"); + txb->space -= copy; + txb->len += copy; + txb->offset += copy; copied += copy; if (call->tx_total_len != -1) call->tx_total_len -= copy; @@ -413,32 +394,22 @@ reload: goto call_terminated; /* add the packet to the send queue if it's now full */ - if (sp->remain <= 0 || + if (!txb->space || (msg_data_left(msg) == 0 && !more)) { - struct rxrpc_connection *conn = call->conn; - uint32_t seq; - - seq = call->tx_top + 1; - - sp->hdr.seq = seq; - sp->hdr._rsvd = 0; - sp->hdr.flags = conn->out_clientflag; - - if (msg_data_left(msg) == 0 && !more) - sp->hdr.flags |= RXRPC_LAST_PACKET; - else if (call->tx_top - call->tx_hard_ack < + if (msg_data_left(msg) == 0 && !more) { + txb->wire.flags |= RXRPC_LAST_PACKET; + __set_bit(RXRPC_TXBUF_LAST, &txb->flags); + } + else if (call->tx_top - call->acks_hard_ack < call->tx_winsize) - sp->hdr.flags |= RXRPC_MORE_PACKETS; + txb->wire.flags |= RXRPC_MORE_PACKETS; - ret = call->security->secure_packet(call, skb, skb->mark); + ret = call->security->secure_packet(call, txb); if (ret < 0) goto out; - ret = rxrpc_queue_packet(rx, call, skb, - !msg_data_left(msg) && !more, - notify_end_tx); - /* Should check for failure here */ - skb = NULL; + rxrpc_queue_packet(rx, call, txb, notify_end_tx); + txb = NULL; } } while (msg_data_left(msg) > 0); @@ -451,12 +422,12 @@ success: read_unlock_bh(&call->state_lock); } out: - call->tx_pending = skb; + call->tx_pending = txb; _leave(" = %d", ret); return ret; call_terminated: - rxrpc_free_skb(skb, rxrpc_skb_freed); + rxrpc_put_txbuf(txb, rxrpc_txbuf_put_send_aborted); _leave(" = %d", call->error); return call->error; @@ -645,7 +616,6 @@ rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, */ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) __releases(&rx->sk.sk_lock.slock) - __releases(&call->user_mutex) { enum rxrpc_call_state state; struct rxrpc_call *call; diff --git a/net/rxrpc/skbuff.c b/net/rxrpc/skbuff.c index 580a5acffee7..0c827d5bb2b8 100644 --- a/net/rxrpc/skbuff.c +++ b/net/rxrpc/skbuff.c @@ -14,8 +14,7 @@ #include <net/af_rxrpc.h> #include "ar-internal.h" -#define is_tx_skb(skb) (rxrpc_skb(skb)->rx_flags & RXRPC_SKB_TX_BUFFER) -#define select_skb_count(skb) (is_tx_skb(skb) ? &rxrpc_n_tx_skbs : &rxrpc_n_rx_skbs) +#define select_skb_count(skb) (&rxrpc_n_rx_skbs) /* * Note the allocation or reception of a socket buffer. @@ -24,8 +23,7 @@ void rxrpc_new_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) { const void *here = __builtin_return_address(0); int n = atomic_inc_return(select_skb_count(skb)); - trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, - rxrpc_skb(skb)->rx_flags, here); + trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here); } /* @@ -36,8 +34,7 @@ void rxrpc_see_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) const void *here = __builtin_return_address(0); if (skb) { int n = atomic_read(select_skb_count(skb)); - trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, - rxrpc_skb(skb)->rx_flags, here); + trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here); } } @@ -48,8 +45,7 @@ void rxrpc_get_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) { const void *here = __builtin_return_address(0); int n = atomic_inc_return(select_skb_count(skb)); - trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, - rxrpc_skb(skb)->rx_flags, here); + trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here); skb_get(skb); } @@ -60,7 +56,7 @@ void rxrpc_eaten_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) { const void *here = __builtin_return_address(0); int n = atomic_inc_return(&rxrpc_n_rx_skbs); - trace_rxrpc_skb(skb, op, 0, n, 0, here); + trace_rxrpc_skb(skb, op, 0, n, here); } /* @@ -72,8 +68,7 @@ void rxrpc_free_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) if (skb) { int n; n = atomic_dec_return(select_skb_count(skb)); - trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, - rxrpc_skb(skb)->rx_flags, here); + trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here); kfree_skb(skb); } } @@ -88,8 +83,7 @@ void rxrpc_purge_queue(struct sk_buff_head *list) while ((skb = skb_dequeue((list))) != NULL) { int n = atomic_dec_return(select_skb_count(skb)); trace_rxrpc_skb(skb, rxrpc_skb_purged, - refcount_read(&skb->users), n, - rxrpc_skb(skb)->rx_flags, here); + refcount_read(&skb->users), n, here); kfree_skb(skb); } } diff --git a/net/rxrpc/sysctl.c b/net/rxrpc/sysctl.c index 555e0910786b..cde3224a5cd2 100644 --- a/net/rxrpc/sysctl.c +++ b/net/rxrpc/sysctl.c @@ -14,7 +14,7 @@ static struct ctl_table_header *rxrpc_sysctl_reg_table; static const unsigned int four = 4; static const unsigned int max_backlog = RXRPC_BACKLOG_MAX - 1; static const unsigned int n_65535 = 65535; -static const unsigned int n_max_acks = RXRPC_RXTX_BUFF_SIZE - 1; +static const unsigned int n_max_acks = 255; static const unsigned long one_jiffy = 1; static const unsigned long max_jiffies = MAX_JIFFY_OFFSET; @@ -27,15 +27,6 @@ static const unsigned long max_jiffies = MAX_JIFFY_OFFSET; static struct ctl_table rxrpc_sysctl_table[] = { /* Values measured in milliseconds but used in jiffies */ { - .procname = "req_ack_delay", - .data = &rxrpc_requested_ack_delay, - .maxlen = sizeof(unsigned long), - .mode = 0644, - .proc_handler = proc_doulongvec_ms_jiffies_minmax, - .extra1 = (void *)&one_jiffy, - .extra2 = (void *)&max_jiffies, - }, - { .procname = "soft_ack_delay", .data = &rxrpc_soft_ack_delay, .maxlen = sizeof(unsigned long), diff --git a/net/rxrpc/txbuf.c b/net/rxrpc/txbuf.c new file mode 100644 index 000000000000..96bfee89927b --- /dev/null +++ b/net/rxrpc/txbuf.c @@ -0,0 +1,135 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* RxRPC Tx data buffering. + * + * Copyright (C) 2022 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/slab.h> +#include "ar-internal.h" + +static atomic_t rxrpc_txbuf_debug_ids; +atomic_t rxrpc_nr_txbuf; + +/* + * Allocate and partially initialise an I/O request structure. + */ +struct rxrpc_txbuf *rxrpc_alloc_txbuf(struct rxrpc_call *call, u8 packet_type, + gfp_t gfp) +{ + struct rxrpc_txbuf *txb; + + txb = kmalloc(sizeof(*txb), gfp); + if (txb) { + INIT_LIST_HEAD(&txb->call_link); + INIT_LIST_HEAD(&txb->tx_link); + refcount_set(&txb->ref, 1); + txb->call = call; + txb->call_debug_id = call->debug_id; + txb->debug_id = atomic_inc_return(&rxrpc_txbuf_debug_ids); + txb->space = sizeof(txb->data); + txb->len = 0; + txb->offset = 0; + txb->flags = 0; + txb->ack_why = 0; + txb->seq = call->tx_top + 1; + txb->wire.epoch = htonl(call->conn->proto.epoch); + txb->wire.cid = htonl(call->cid); + txb->wire.callNumber = htonl(call->call_id); + txb->wire.seq = htonl(txb->seq); + txb->wire.type = packet_type; + txb->wire.flags = call->conn->out_clientflag; + txb->wire.userStatus = 0; + txb->wire.securityIndex = call->security_ix; + txb->wire._rsvd = 0; + txb->wire.serviceId = htons(call->service_id); + + trace_rxrpc_txbuf(txb->debug_id, + txb->call_debug_id, txb->seq, 1, + packet_type == RXRPC_PACKET_TYPE_DATA ? + rxrpc_txbuf_alloc_data : + rxrpc_txbuf_alloc_ack); + atomic_inc(&rxrpc_nr_txbuf); + } + + return txb; +} + +void rxrpc_get_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what) +{ + int r; + + __refcount_inc(&txb->ref, &r); + trace_rxrpc_txbuf(txb->debug_id, txb->call_debug_id, txb->seq, r + 1, what); +} + +void rxrpc_see_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what) +{ + int r = refcount_read(&txb->ref); + + trace_rxrpc_txbuf(txb->debug_id, txb->call_debug_id, txb->seq, r, what); +} + +static void rxrpc_free_txbuf(struct rcu_head *rcu) +{ + struct rxrpc_txbuf *txb = container_of(rcu, struct rxrpc_txbuf, rcu); + + trace_rxrpc_txbuf(txb->debug_id, txb->call_debug_id, txb->seq, 0, + rxrpc_txbuf_free); + kfree(txb); + atomic_dec(&rxrpc_nr_txbuf); +} + +void rxrpc_put_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what) +{ + unsigned int debug_id, call_debug_id; + rxrpc_seq_t seq; + bool dead; + int r; + + if (txb) { + debug_id = txb->debug_id; + call_debug_id = txb->call_debug_id; + seq = txb->seq; + dead = __refcount_dec_and_test(&txb->ref, &r); + trace_rxrpc_txbuf(debug_id, call_debug_id, seq, r - 1, what); + if (dead) + call_rcu(&txb->rcu, rxrpc_free_txbuf); + } +} + +/* + * Shrink the transmit buffer. + */ +void rxrpc_shrink_call_tx_buffer(struct rxrpc_call *call) +{ + struct rxrpc_txbuf *txb; + rxrpc_seq_t hard_ack = smp_load_acquire(&call->acks_hard_ack); + + _enter("%x/%x/%x", call->tx_bottom, call->acks_hard_ack, call->tx_top); + + for (;;) { + spin_lock(&call->tx_lock); + txb = list_first_entry_or_null(&call->tx_buffer, + struct rxrpc_txbuf, call_link); + if (!txb) + break; + hard_ack = smp_load_acquire(&call->acks_hard_ack); + if (before(hard_ack, txb->seq)) + break; + + ASSERTCMP(txb->seq, ==, call->tx_bottom + 1); + call->tx_bottom++; + list_del_rcu(&txb->call_link); + + trace_rxrpc_txqueue(call, rxrpc_txqueue_dequeue); + + spin_unlock(&call->tx_lock); + + rxrpc_put_txbuf(txb, rxrpc_txbuf_put_rotated); + } + + spin_unlock(&call->tx_lock); +} diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index b38d91d6b249..da0b7f665277 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -33,6 +33,7 @@ #include <net/netfilter/nf_conntrack_acct.h> #include <net/netfilter/ipv6/nf_defrag_ipv6.h> #include <net/netfilter/nf_conntrack_act_ct.h> +#include <net/netfilter/nf_conntrack_seqadj.h> #include <uapi/linux/netfilter/nf_nat.h> static struct workqueue_struct *act_ct_wq; @@ -345,11 +346,9 @@ static void tcf_ct_flow_table_cleanup_work(struct work_struct *work) module_put(THIS_MODULE); } -static void tcf_ct_flow_table_put(struct tcf_ct_params *params) +static void tcf_ct_flow_table_put(struct tcf_ct_flow_table *ct_ft) { - struct tcf_ct_flow_table *ct_ft = params->ct_ft; - - if (refcount_dec_and_test(¶ms->ct_ft->ref)) { + if (refcount_dec_and_test(&ct_ft->ref)) { rhashtable_remove_fast(&zones_ht, &ct_ft->node, zones_params); INIT_RCU_WORK(&ct_ft->rwork, tcf_ct_flow_table_cleanup_work); queue_rcu_work(act_ct_wq, &ct_ft->rwork); @@ -657,7 +656,7 @@ struct tc_ct_action_net { /* Determine whether skb->_nfct is equal to the result of conntrack lookup. */ static bool tcf_ct_skb_nfct_cached(struct net *net, struct sk_buff *skb, - u16 zone_id, bool force) + struct tcf_ct_params *p) { enum ip_conntrack_info ctinfo; struct nf_conn *ct; @@ -667,11 +666,19 @@ static bool tcf_ct_skb_nfct_cached(struct net *net, struct sk_buff *skb, return false; if (!net_eq(net, read_pnet(&ct->ct_net))) goto drop_ct; - if (nf_ct_zone(ct)->id != zone_id) + if (nf_ct_zone(ct)->id != p->zone) goto drop_ct; + if (p->helper) { + struct nf_conn_help *help; + + help = nf_ct_ext_find(ct, NF_CT_EXT_HELPER); + if (help && rcu_access_pointer(help->helper) != p->helper) + goto drop_ct; + } /* Force conntrack entry direction. */ - if (force && CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) { + if ((p->ct_action & TCA_CT_ACT_FORCE) && + CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) { if (nf_ct_is_confirmed(ct)) nf_ct_kill(ct); @@ -832,18 +839,30 @@ out_free: return err; } -static void tcf_ct_params_free(struct rcu_head *head) +static void tcf_ct_params_free(struct tcf_ct_params *params) { - struct tcf_ct_params *params = container_of(head, - struct tcf_ct_params, rcu); - - tcf_ct_flow_table_put(params); - + if (params->helper) { +#if IS_ENABLED(CONFIG_NF_NAT) + if (params->ct_action & TCA_CT_ACT_NAT) + nf_nat_helper_put(params->helper); +#endif + nf_conntrack_helper_put(params->helper); + } + if (params->ct_ft) + tcf_ct_flow_table_put(params->ct_ft); if (params->tmpl) nf_ct_put(params->tmpl); kfree(params); } +static void tcf_ct_params_free_rcu(struct rcu_head *head) +{ + struct tcf_ct_params *params; + + params = container_of(head, struct tcf_ct_params, rcu); + tcf_ct_params_free(params); +} + #if IS_ENABLED(CONFIG_NF_NAT) /* Modelled after nf_nat_ipv[46]_fn(). * range is only used for new, uninitialized NAT state. @@ -1023,13 +1042,14 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct net *net = dev_net(skb->dev); - bool cached, commit, clear, force; enum ip_conntrack_info ctinfo; struct tcf_ct *c = to_ct(a); struct nf_conn *tmpl = NULL; struct nf_hook_state state; + bool cached, commit, clear; int nh_ofs, err, retval; struct tcf_ct_params *p; + bool add_helper = false; bool skip_add = false; bool defrag = false; struct nf_conn *ct; @@ -1040,7 +1060,6 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a, retval = READ_ONCE(c->tcf_action); commit = p->ct_action & TCA_CT_ACT_COMMIT; clear = p->ct_action & TCA_CT_ACT_CLEAR; - force = p->ct_action & TCA_CT_ACT_FORCE; tmpl = p->tmpl; tcf_lastuse_update(&c->tcf_tm); @@ -1083,7 +1102,7 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a, * actually run the packet through conntrack twice unless it's for a * different zone. */ - cached = tcf_ct_skb_nfct_cached(net, skb, p->zone, force); + cached = tcf_ct_skb_nfct_cached(net, skb, p); if (!cached) { if (tcf_ct_flow_table_lookup(p, skb, family)) { skip_add = true; @@ -1116,6 +1135,22 @@ do_nat: if (err != NF_ACCEPT) goto drop; + if (!nf_ct_is_confirmed(ct) && commit && p->helper && !nfct_help(ct)) { + err = __nf_ct_try_assign_helper(ct, p->tmpl, GFP_ATOMIC); + if (err) + goto drop; + add_helper = true; + if (p->ct_action & TCA_CT_ACT_NAT && !nfct_seqadj(ct)) { + if (!nfct_seqadj_ext_add(ct)) + goto drop; + } + } + + if (nf_ct_is_confirmed(ct) ? ((!cached && !skip_add) || add_helper) : commit) { + if (nf_ct_helper(skb, ct, ctinfo, family) != NF_ACCEPT) + goto drop; + } + if (commit) { tcf_ct_act_set_mark(ct, p->mark, p->mark_mask); tcf_ct_act_set_labels(ct, p->labels, p->labels_mask); @@ -1164,6 +1199,9 @@ static const struct nla_policy ct_policy[TCA_CT_MAX + 1] = { [TCA_CT_NAT_IPV6_MAX] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), [TCA_CT_NAT_PORT_MIN] = { .type = NLA_U16 }, [TCA_CT_NAT_PORT_MAX] = { .type = NLA_U16 }, + [TCA_CT_HELPER_NAME] = { .type = NLA_STRING, .len = NF_CT_HELPER_NAME_LEN }, + [TCA_CT_HELPER_FAMILY] = { .type = NLA_U8 }, + [TCA_CT_HELPER_PROTO] = { .type = NLA_U8 }, }; static int tcf_ct_fill_params_nat(struct tcf_ct_params *p, @@ -1253,8 +1291,9 @@ static int tcf_ct_fill_params(struct net *net, { struct tc_ct_action_net *tn = net_generic(net, act_ct_ops.net_id); struct nf_conntrack_zone zone; + int err, family, proto, len; struct nf_conn *tmpl; - int err; + char *name; p->zone = NF_CT_DEFAULT_ZONE_ID; @@ -1315,10 +1354,31 @@ static int tcf_ct_fill_params(struct net *net, NL_SET_ERR_MSG_MOD(extack, "Failed to allocate conntrack template"); return -ENOMEM; } - __set_bit(IPS_CONFIRMED_BIT, &tmpl->status); p->tmpl = tmpl; + if (tb[TCA_CT_HELPER_NAME]) { + name = nla_data(tb[TCA_CT_HELPER_NAME]); + len = nla_len(tb[TCA_CT_HELPER_NAME]); + if (len > 16 || name[len - 1] != '\0') { + NL_SET_ERR_MSG_MOD(extack, "Failed to parse helper name."); + err = -EINVAL; + goto err; + } + family = tb[TCA_CT_HELPER_FAMILY] ? nla_get_u8(tb[TCA_CT_HELPER_FAMILY]) : AF_INET; + proto = tb[TCA_CT_HELPER_PROTO] ? nla_get_u8(tb[TCA_CT_HELPER_PROTO]) : IPPROTO_TCP; + err = nf_ct_add_helper(tmpl, name, family, proto, + p->ct_action & TCA_CT_ACT_NAT, &p->helper); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Failed to add helper"); + goto err; + } + } + __set_bit(IPS_CONFIRMED_BIT, &tmpl->status); return 0; +err: + nf_ct_put(p->tmpl); + p->tmpl = NULL; + return err; } static int tcf_ct_init(struct net *net, struct nlattr *nla, @@ -1390,7 +1450,7 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla, err = tcf_ct_flow_table_get(net, params); if (err) - goto cleanup_params; + goto cleanup; spin_lock_bh(&c->tcf_lock); goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); @@ -1401,17 +1461,15 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla, if (goto_ch) tcf_chain_put_by_act(goto_ch); if (params) - call_rcu(¶ms->rcu, tcf_ct_params_free); + call_rcu(¶ms->rcu, tcf_ct_params_free_rcu); return res; -cleanup_params: - if (params->tmpl) - nf_ct_put(params->tmpl); cleanup: if (goto_ch) tcf_chain_put_by_act(goto_ch); - kfree(params); + if (params) + tcf_ct_params_free(params); tcf_idr_release(*a, bind); return err; } @@ -1423,7 +1481,7 @@ static void tcf_ct_cleanup(struct tc_action *a) params = rcu_dereference_protected(c->params, 1); if (params) - call_rcu(¶ms->rcu, tcf_ct_params_free); + call_rcu(¶ms->rcu, tcf_ct_params_free_rcu); } static int tcf_ct_dump_key_val(struct sk_buff *skb, @@ -1489,6 +1547,19 @@ static int tcf_ct_dump_nat(struct sk_buff *skb, struct tcf_ct_params *p) return 0; } +static int tcf_ct_dump_helper(struct sk_buff *skb, struct nf_conntrack_helper *helper) +{ + if (!helper) + return 0; + + if (nla_put_string(skb, TCA_CT_HELPER_NAME, helper->name) || + nla_put_u8(skb, TCA_CT_HELPER_FAMILY, helper->tuple.src.l3num) || + nla_put_u8(skb, TCA_CT_HELPER_PROTO, helper->tuple.dst.protonum)) + return -1; + + return 0; +} + static inline int tcf_ct_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { @@ -1541,6 +1612,9 @@ static inline int tcf_ct_dump(struct sk_buff *skb, struct tc_action *a, if (tcf_ct_dump_nat(skb, p)) goto nla_put_failure; + if (tcf_ct_dump_helper(skb, p->helper)) + goto nla_put_failure; + skip_dump: if (nla_put(skb, TCA_CT_PARMS, sizeof(opt), &opt)) goto nla_put_failure; diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index e213aaf45d67..20831079fb09 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -384,6 +384,7 @@ static int sctp_prsctp_prune_unsent(struct sctp_association *asoc, { struct sctp_outq *q = &asoc->outqueue; struct sctp_chunk *chk, *temp; + struct sctp_stream_out *sout; q->sched->unsched_all(&asoc->stream); @@ -398,12 +399,14 @@ static int sctp_prsctp_prune_unsent(struct sctp_association *asoc, sctp_sched_dequeue_common(q, chk); asoc->sent_cnt_removable--; asoc->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++; - if (chk->sinfo.sinfo_stream < asoc->stream.outcnt) { - struct sctp_stream_out *streamout = - SCTP_SO(&asoc->stream, chk->sinfo.sinfo_stream); - streamout->ext->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++; - } + sout = SCTP_SO(&asoc->stream, chk->sinfo.sinfo_stream); + sout->ext->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++; + + /* clear out_curr if all frag chunks are pruned */ + if (asoc->stream.out_curr == sout && + list_is_last(&chk->frag_list, &chk->msg->chunks)) + asoc->stream.out_curr = NULL; msg_len -= chk->skb->truesize + sizeof(struct sctp_chunk); sctp_chunk_free(chk); diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index fc68733673ba..dfea27a906f2 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -880,7 +880,7 @@ static int tipc_nl_compat_name_table_dump_header(struct tipc_nl_compat_msg *msg) }; ntq = (struct tipc_name_table_query *)TLV_DATA(msg->req); - if (TLV_GET_DATA_LEN(msg->req) < sizeof(struct tipc_name_table_query)) + if (TLV_GET_DATA_LEN(msg->req) < (int)sizeof(struct tipc_name_table_query)) return -EINVAL; depth = ntohl(ntq->depth); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 148f66edb015..1ad0326ff4dc 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -16140,7 +16140,8 @@ static u32 nl80211_internal_flags[] = { #undef SELECTOR }; -static int nl80211_pre_doit(const struct genl_ops *ops, struct sk_buff *skb, +static int nl80211_pre_doit(const struct genl_split_ops *ops, + struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = NULL; @@ -16241,7 +16242,8 @@ out_unlock: return err; } -static void nl80211_post_doit(const struct genl_ops *ops, struct sk_buff *skb, +static void nl80211_post_doit(const struct genl_split_ops *ops, + struct sk_buff *skb, struct genl_info *info) { u32 internal_flags = nl80211_internal_flags[ops->internal_flags]; diff --git a/net/wireless/reg.c b/net/wireless/reg.c index d5c7a5aa6853..c3d950d29432 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -1084,6 +1084,8 @@ MODULE_FIRMWARE("regulatory.db"); static int query_regdb_file(const char *alpha2) { + int err; + ASSERT_RTNL(); if (regdb) @@ -1093,9 +1095,13 @@ static int query_regdb_file(const char *alpha2) if (!alpha2) return -ENOMEM; - return request_firmware_nowait(THIS_MODULE, true, "regulatory.db", - ®_pdev->dev, GFP_KERNEL, - (void *)alpha2, regdb_fw_cb); + err = request_firmware_nowait(THIS_MODULE, true, "regulatory.db", + ®_pdev->dev, GFP_KERNEL, + (void *)alpha2, regdb_fw_cb); + if (err) + kfree(alpha2); + + return err; } int reg_reload_regdb(void) diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 806a5f1330ff..da752b0cc752 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -1674,7 +1674,9 @@ cfg80211_update_known_bss(struct cfg80211_registered_device *rdev, if (old == rcu_access_pointer(known->pub.ies)) rcu_assign_pointer(known->pub.ies, new->pub.beacon_ies); - cfg80211_update_hidden_bsses(known, new->pub.beacon_ies, old); + cfg80211_update_hidden_bsses(known, + rcu_access_pointer(new->pub.beacon_ies), + old); if (old) kfree_rcu((struct cfg80211_bss_ies *)old, rcu_head); diff --git a/net/wireless/util.c b/net/wireless/util.c index eb277105a878..8f403f9fe816 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1559,10 +1559,12 @@ static u32 cfg80211_calculate_bitrate_eht(struct rate_info *rate) tmp = result; tmp *= SCALE; do_div(tmp, mcs_divisors[rate->mcs]); - result = tmp; /* and take NSS */ - result = (result * rate->nss) / 8; + tmp *= rate->nss; + do_div(tmp, 8); + + result = tmp; return result / 10000; } diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost index 8489a3402eb8..e41dee64d429 100644 --- a/scripts/Makefile.modpost +++ b/scripts/Makefile.modpost @@ -122,7 +122,7 @@ quiet_cmd_modpost = MODPOST $@ sed 's/ko$$/o/' $(or $(modorder-if-needed), /dev/null) | $(MODPOST) $(modpost-args) -T - $(vmlinux.o-if-present) targets += $(output-symdump) -$(output-symdump): $(modorder-if-needed) $(vmlinux.o-if-present) $(moudle.symvers-if-present) $(MODPOST) FORCE +$(output-symdump): $(modorder-if-needed) $(vmlinux.o-if-present) $(module.symvers-if-present) $(MODPOST) FORCE $(call if_changed,modpost) __modpost: $(output-symdump) diff --git a/scripts/kconfig/menu.c b/scripts/kconfig/menu.c index 62b6313f51c8..109325f31bef 100644 --- a/scripts/kconfig/menu.c +++ b/scripts/kconfig/menu.c @@ -722,8 +722,8 @@ static void get_prompt_str(struct gstr *r, struct property *prop, if (!expr_eq(prop->menu->dep, prop->visible.expr)) get_dep_str(r, prop->visible.expr, " Visible if: "); - menu = prop->menu->parent; - for (i = 0; menu && i < 8; menu = menu->parent) { + menu = prop->menu; + for (i = 0; menu != &rootmenu && i < 8; menu = menu->parent) { bool accessible = menu_is_visible(menu); submenu[i++] = menu; @@ -733,16 +733,7 @@ static void get_prompt_str(struct gstr *r, struct property *prop, if (head && location) { jump = xmalloc(sizeof(struct jump_key)); - if (menu_is_visible(prop->menu)) { - /* - * There is not enough room to put the hint at the - * beginning of the "Prompt" line. Put the hint on the - * last "Location" line even when it would belong on - * the former. - */ - jump->target = prop->menu; - } else - jump->target = location; + jump->target = location; if (list_empty(head)) jump->index = 0; @@ -758,13 +749,7 @@ static void get_prompt_str(struct gstr *r, struct property *prop, menu = submenu[i]; if (jump && menu == location) jump->offset = strlen(r->s); - - if (menu == &rootmenu) - /* The real rootmenu prompt is ugly */ - str_printf(r, "%*cMain menu", j, ' '); - else - str_printf(r, "%*c-> %s", j, ' ', menu_get_prompt(menu)); - + str_printf(r, "%*c-> %s", j, ' ', menu_get_prompt(menu)); if (menu->sym) { str_printf(r, " (%s [=%s])", menu->sym->name ? menu->sym->name : "<choice>", diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index d9f7b1299b03..c90b756945e3 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -302,6 +302,9 @@ int do_pin_any(int argc, char **argv, int (*get_fd)(int *, char ***)) int err; int fd; + if (!REQ_ARGS(3)) + return -EINVAL; + fd = get_fd(&argc, &argv); if (fd < 0) return fd; diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h index f243ce665f74..07a4cb149305 100644 --- a/tools/include/uapi/linux/in.h +++ b/tools/include/uapi/linux/in.h @@ -20,6 +20,7 @@ #define _UAPI_LINUX_IN_H #include <linux/types.h> +#include <linux/stddef.h> #include <linux/libc-compat.h> #include <linux/socket.h> diff --git a/tools/include/uapi/linux/stddef.h b/tools/include/uapi/linux/stddef.h new file mode 100644 index 000000000000..bb6ea517efb5 --- /dev/null +++ b/tools/include/uapi/linux/stddef.h @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _LINUX_STDDEF_H +#define _LINUX_STDDEF_H + + + +#ifndef __always_inline +#define __always_inline __inline__ +#endif + +/** + * __struct_group() - Create a mirrored named and anonyomous struct + * + * @TAG: The tag name for the named sub-struct (usually empty) + * @NAME: The identifier name of the mirrored sub-struct + * @ATTRS: Any struct attributes (usually empty) + * @MEMBERS: The member declarations for the mirrored structs + * + * Used to create an anonymous union of two structs with identical layout + * and size: one anonymous and one named. The former's members can be used + * normally without sub-struct naming, and the latter can be used to + * reason about the start, end, and size of the group of struct members. + * The named struct can also be explicitly tagged for layer reuse, as well + * as both having struct attributes appended. + */ +#define __struct_group(TAG, NAME, ATTRS, MEMBERS...) \ + union { \ + struct { MEMBERS } ATTRS; \ + struct TAG { MEMBERS } ATTRS NAME; \ + } + +/** + * __DECLARE_FLEX_ARRAY() - Declare a flexible array usable in a union + * + * @TYPE: The type of each flexible array element + * @NAME: The name of the flexible array member + * + * In order to have a flexible array member in a union or alone in a + * struct, it needs to be wrapped in an anonymous struct with at least 1 + * named member, but that member can be empty. + */ +#define __DECLARE_FLEX_ARRAY(TYPE, NAME) \ + struct { \ + struct { } __empty_ ## NAME; \ + TYPE NAME[]; \ + } +#endif diff --git a/tools/testing/cxl/test/cxl.c b/tools/testing/cxl/test/cxl.c index a072b2d3e726..7edce12fd2ce 100644 --- a/tools/testing/cxl/test/cxl.c +++ b/tools/testing/cxl/test/cxl.c @@ -12,30 +12,62 @@ #include "mock.h" #define NR_CXL_HOST_BRIDGES 2 +#define NR_CXL_SINGLE_HOST 1 #define NR_CXL_ROOT_PORTS 2 #define NR_CXL_SWITCH_PORTS 2 #define NR_CXL_PORT_DECODERS 8 static struct platform_device *cxl_acpi; static struct platform_device *cxl_host_bridge[NR_CXL_HOST_BRIDGES]; -static struct platform_device - *cxl_root_port[NR_CXL_HOST_BRIDGES * NR_CXL_ROOT_PORTS]; -static struct platform_device - *cxl_switch_uport[NR_CXL_HOST_BRIDGES * NR_CXL_ROOT_PORTS]; -static struct platform_device - *cxl_switch_dport[NR_CXL_HOST_BRIDGES * NR_CXL_ROOT_PORTS * - NR_CXL_SWITCH_PORTS]; -struct platform_device - *cxl_mem[NR_CXL_HOST_BRIDGES * NR_CXL_ROOT_PORTS * NR_CXL_SWITCH_PORTS]; +#define NR_MULTI_ROOT (NR_CXL_HOST_BRIDGES * NR_CXL_ROOT_PORTS) +static struct platform_device *cxl_root_port[NR_MULTI_ROOT]; +static struct platform_device *cxl_switch_uport[NR_MULTI_ROOT]; +#define NR_MEM_MULTI \ + (NR_CXL_HOST_BRIDGES * NR_CXL_ROOT_PORTS * NR_CXL_SWITCH_PORTS) +static struct platform_device *cxl_switch_dport[NR_MEM_MULTI]; + +static struct platform_device *cxl_hb_single[NR_CXL_SINGLE_HOST]; +static struct platform_device *cxl_root_single[NR_CXL_SINGLE_HOST]; +static struct platform_device *cxl_swu_single[NR_CXL_SINGLE_HOST]; +#define NR_MEM_SINGLE (NR_CXL_SINGLE_HOST * NR_CXL_SWITCH_PORTS) +static struct platform_device *cxl_swd_single[NR_MEM_SINGLE]; + +struct platform_device *cxl_mem[NR_MEM_MULTI]; +struct platform_device *cxl_mem_single[NR_MEM_SINGLE]; + + +static inline bool is_multi_bridge(struct device *dev) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(cxl_host_bridge); i++) + if (&cxl_host_bridge[i]->dev == dev) + return true; + return false; +} + +static inline bool is_single_bridge(struct device *dev) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(cxl_hb_single); i++) + if (&cxl_hb_single[i]->dev == dev) + return true; + return false; +} static struct acpi_device acpi0017_mock; -static struct acpi_device host_bridge[NR_CXL_HOST_BRIDGES] = { +static struct acpi_device host_bridge[NR_CXL_HOST_BRIDGES + NR_CXL_SINGLE_HOST] = { [0] = { .handle = &host_bridge[0], }, [1] = { .handle = &host_bridge[1], }, + [2] = { + .handle = &host_bridge[2], + }, + }; static bool is_mock_dev(struct device *dev) @@ -45,6 +77,9 @@ static bool is_mock_dev(struct device *dev) for (i = 0; i < ARRAY_SIZE(cxl_mem); i++) if (dev == &cxl_mem[i]->dev) return true; + for (i = 0; i < ARRAY_SIZE(cxl_mem_single); i++) + if (dev == &cxl_mem_single[i]->dev) + return true; if (dev == &cxl_acpi->dev) return true; return false; @@ -66,7 +101,7 @@ static bool is_mock_adev(struct acpi_device *adev) static struct { struct acpi_table_cedt cedt; - struct acpi_cedt_chbs chbs[NR_CXL_HOST_BRIDGES]; + struct acpi_cedt_chbs chbs[NR_CXL_HOST_BRIDGES + NR_CXL_SINGLE_HOST]; struct { struct acpi_cedt_cfmws cfmws; u32 target[1]; @@ -83,6 +118,10 @@ static struct { struct acpi_cedt_cfmws cfmws; u32 target[2]; } cfmws3; + struct { + struct acpi_cedt_cfmws cfmws; + u32 target[1]; + } cfmws4; } __packed mock_cedt = { .cedt = { .header = { @@ -107,6 +146,14 @@ static struct { .uid = 1, .cxl_version = ACPI_CEDT_CHBS_VERSION_CXL20, }, + .chbs[2] = { + .header = { + .type = ACPI_CEDT_TYPE_CHBS, + .length = sizeof(mock_cedt.chbs[0]), + }, + .uid = 2, + .cxl_version = ACPI_CEDT_CHBS_VERSION_CXL20, + }, .cfmws0 = { .cfmws = { .header = { @@ -167,13 +214,29 @@ static struct { }, .target = { 0, 1, }, }, + .cfmws4 = { + .cfmws = { + .header = { + .type = ACPI_CEDT_TYPE_CFMWS, + .length = sizeof(mock_cedt.cfmws4), + }, + .interleave_ways = 0, + .granularity = 4, + .restrictions = ACPI_CEDT_CFMWS_RESTRICT_TYPE3 | + ACPI_CEDT_CFMWS_RESTRICT_PMEM, + .qtg_id = 4, + .window_size = SZ_256M * 4UL, + }, + .target = { 2 }, + }, }; -struct acpi_cedt_cfmws *mock_cfmws[4] = { +struct acpi_cedt_cfmws *mock_cfmws[] = { [0] = &mock_cedt.cfmws0.cfmws, [1] = &mock_cedt.cfmws1.cfmws, [2] = &mock_cedt.cfmws2.cfmws, [3] = &mock_cedt.cfmws3.cfmws, + [4] = &mock_cedt.cfmws4.cfmws, }; struct cxl_mock_res { @@ -304,6 +367,9 @@ static bool is_mock_bridge(struct device *dev) for (i = 0; i < ARRAY_SIZE(cxl_host_bridge); i++) if (dev == &cxl_host_bridge[i]->dev) return true; + for (i = 0; i < ARRAY_SIZE(cxl_hb_single); i++) + if (dev == &cxl_hb_single[i]->dev) + return true; return false; } @@ -326,6 +392,18 @@ static bool is_mock_port(struct device *dev) if (dev == &cxl_switch_dport[i]->dev) return true; + for (i = 0; i < ARRAY_SIZE(cxl_root_single); i++) + if (dev == &cxl_root_single[i]->dev) + return true; + + for (i = 0; i < ARRAY_SIZE(cxl_swu_single); i++) + if (dev == &cxl_swu_single[i]->dev) + return true; + + for (i = 0; i < ARRAY_SIZE(cxl_swd_single); i++) + if (dev == &cxl_swd_single[i]->dev) + return true; + if (is_cxl_memdev(dev)) return is_mock_dev(dev->parent); @@ -561,11 +639,31 @@ static int mock_cxl_port_enumerate_dports(struct cxl_port *port) int i, array_size; if (port->depth == 1) { - array_size = ARRAY_SIZE(cxl_root_port); - array = cxl_root_port; + if (is_multi_bridge(port->uport)) { + array_size = ARRAY_SIZE(cxl_root_port); + array = cxl_root_port; + } else if (is_single_bridge(port->uport)) { + array_size = ARRAY_SIZE(cxl_root_single); + array = cxl_root_single; + } else { + dev_dbg(&port->dev, "%s: unknown bridge type\n", + dev_name(port->uport)); + return -ENXIO; + } } else if (port->depth == 2) { - array_size = ARRAY_SIZE(cxl_switch_dport); - array = cxl_switch_dport; + struct cxl_port *parent = to_cxl_port(port->dev.parent); + + if (is_multi_bridge(parent->uport)) { + array_size = ARRAY_SIZE(cxl_switch_dport); + array = cxl_switch_dport; + } else if (is_single_bridge(parent->uport)) { + array_size = ARRAY_SIZE(cxl_swd_single); + array = cxl_swd_single; + } else { + dev_dbg(&port->dev, "%s: unknown bridge type\n", + dev_name(port->uport)); + return -ENXIO; + } } else { dev_WARN_ONCE(&port->dev, 1, "unexpected depth %d\n", port->depth); @@ -576,8 +674,12 @@ static int mock_cxl_port_enumerate_dports(struct cxl_port *port) struct platform_device *pdev = array[i]; struct cxl_dport *dport; - if (pdev->dev.parent != port->uport) + if (pdev->dev.parent != port->uport) { + dev_dbg(&port->dev, "%s: mismatch parent %s\n", + dev_name(port->uport), + dev_name(pdev->dev.parent)); continue; + } dport = devm_cxl_add_dport(port, &pdev->dev, pdev->id, CXL_RESOURCE_NONE); @@ -627,6 +729,157 @@ static void mock_companion(struct acpi_device *adev, struct device *dev) #define SZ_512G (SZ_64G * 8) #endif +static __init int cxl_single_init(void) +{ + int i, rc; + + for (i = 0; i < ARRAY_SIZE(cxl_hb_single); i++) { + struct acpi_device *adev = + &host_bridge[NR_CXL_HOST_BRIDGES + i]; + struct platform_device *pdev; + + pdev = platform_device_alloc("cxl_host_bridge", + NR_CXL_HOST_BRIDGES + i); + if (!pdev) + goto err_bridge; + + mock_companion(adev, &pdev->dev); + rc = platform_device_add(pdev); + if (rc) { + platform_device_put(pdev); + goto err_bridge; + } + + cxl_hb_single[i] = pdev; + rc = sysfs_create_link(&pdev->dev.kobj, &pdev->dev.kobj, + "physical_node"); + if (rc) + goto err_bridge; + } + + for (i = 0; i < ARRAY_SIZE(cxl_root_single); i++) { + struct platform_device *bridge = + cxl_hb_single[i % ARRAY_SIZE(cxl_hb_single)]; + struct platform_device *pdev; + + pdev = platform_device_alloc("cxl_root_port", + NR_MULTI_ROOT + i); + if (!pdev) + goto err_port; + pdev->dev.parent = &bridge->dev; + + rc = platform_device_add(pdev); + if (rc) { + platform_device_put(pdev); + goto err_port; + } + cxl_root_single[i] = pdev; + } + + for (i = 0; i < ARRAY_SIZE(cxl_swu_single); i++) { + struct platform_device *root_port = cxl_root_single[i]; + struct platform_device *pdev; + + pdev = platform_device_alloc("cxl_switch_uport", + NR_MULTI_ROOT + i); + if (!pdev) + goto err_uport; + pdev->dev.parent = &root_port->dev; + + rc = platform_device_add(pdev); + if (rc) { + platform_device_put(pdev); + goto err_uport; + } + cxl_swu_single[i] = pdev; + } + + for (i = 0; i < ARRAY_SIZE(cxl_swd_single); i++) { + struct platform_device *uport = + cxl_swu_single[i % ARRAY_SIZE(cxl_swu_single)]; + struct platform_device *pdev; + + pdev = platform_device_alloc("cxl_switch_dport", + i + NR_MEM_MULTI); + if (!pdev) + goto err_dport; + pdev->dev.parent = &uport->dev; + + rc = platform_device_add(pdev); + if (rc) { + platform_device_put(pdev); + goto err_dport; + } + cxl_swd_single[i] = pdev; + } + + for (i = 0; i < ARRAY_SIZE(cxl_mem_single); i++) { + struct platform_device *dport = cxl_swd_single[i]; + struct platform_device *pdev; + + pdev = platform_device_alloc("cxl_mem", NR_MEM_MULTI + i); + if (!pdev) + goto err_mem; + pdev->dev.parent = &dport->dev; + set_dev_node(&pdev->dev, i % 2); + + rc = platform_device_add(pdev); + if (rc) { + platform_device_put(pdev); + goto err_mem; + } + cxl_mem_single[i] = pdev; + } + + return 0; + +err_mem: + for (i = ARRAY_SIZE(cxl_mem_single) - 1; i >= 0; i--) + platform_device_unregister(cxl_mem_single[i]); +err_dport: + for (i = ARRAY_SIZE(cxl_swd_single) - 1; i >= 0; i--) + platform_device_unregister(cxl_swd_single[i]); +err_uport: + for (i = ARRAY_SIZE(cxl_swu_single) - 1; i >= 0; i--) + platform_device_unregister(cxl_swu_single[i]); +err_port: + for (i = ARRAY_SIZE(cxl_root_single) - 1; i >= 0; i--) + platform_device_unregister(cxl_root_single[i]); +err_bridge: + for (i = ARRAY_SIZE(cxl_hb_single) - 1; i >= 0; i--) { + struct platform_device *pdev = cxl_hb_single[i]; + + if (!pdev) + continue; + sysfs_remove_link(&pdev->dev.kobj, "physical_node"); + platform_device_unregister(cxl_hb_single[i]); + } + + return rc; +} + +static void cxl_single_exit(void) +{ + int i; + + for (i = ARRAY_SIZE(cxl_mem_single) - 1; i >= 0; i--) + platform_device_unregister(cxl_mem_single[i]); + for (i = ARRAY_SIZE(cxl_swd_single) - 1; i >= 0; i--) + platform_device_unregister(cxl_swd_single[i]); + for (i = ARRAY_SIZE(cxl_swu_single) - 1; i >= 0; i--) + platform_device_unregister(cxl_swu_single[i]); + for (i = ARRAY_SIZE(cxl_root_single) - 1; i >= 0; i--) + platform_device_unregister(cxl_root_single[i]); + for (i = ARRAY_SIZE(cxl_hb_single) - 1; i >= 0; i--) { + struct platform_device *pdev = cxl_hb_single[i]; + + if (!pdev) + continue; + sysfs_remove_link(&pdev->dev.kobj, "physical_node"); + platform_device_unregister(cxl_hb_single[i]); + } +} + static __init int cxl_test_init(void) { int rc, i; @@ -695,7 +948,7 @@ static __init int cxl_test_init(void) pdev = platform_device_alloc("cxl_switch_uport", i); if (!pdev) - goto err_port; + goto err_uport; pdev->dev.parent = &root_port->dev; rc = platform_device_add(pdev); @@ -713,7 +966,7 @@ static __init int cxl_test_init(void) pdev = platform_device_alloc("cxl_switch_dport", i); if (!pdev) - goto err_port; + goto err_dport; pdev->dev.parent = &uport->dev; rc = platform_device_add(pdev); @@ -724,7 +977,6 @@ static __init int cxl_test_init(void) cxl_switch_dport[i] = pdev; } - BUILD_BUG_ON(ARRAY_SIZE(cxl_mem) != ARRAY_SIZE(cxl_switch_dport)); for (i = 0; i < ARRAY_SIZE(cxl_mem); i++) { struct platform_device *dport = cxl_switch_dport[i]; struct platform_device *pdev; @@ -743,9 +995,13 @@ static __init int cxl_test_init(void) cxl_mem[i] = pdev; } + rc = cxl_single_init(); + if (rc) + goto err_mem; + cxl_acpi = platform_device_alloc("cxl_acpi", 0); if (!cxl_acpi) - goto err_mem; + goto err_single; mock_companion(&acpi0017_mock, &cxl_acpi->dev); acpi0017_mock.dev.bus = &platform_bus_type; @@ -758,6 +1014,8 @@ static __init int cxl_test_init(void) err_add: platform_device_put(cxl_acpi); +err_single: + cxl_single_exit(); err_mem: for (i = ARRAY_SIZE(cxl_mem) - 1; i >= 0; i--) platform_device_unregister(cxl_mem[i]); @@ -793,6 +1051,7 @@ static __exit void cxl_test_exit(void) int i; platform_device_unregister(cxl_acpi); + cxl_single_exit(); for (i = ARRAY_SIZE(cxl_mem) - 1; i >= 0; i--) platform_device_unregister(cxl_mem[i]); for (i = ARRAY_SIZE(cxl_switch_dport) - 1; i >= 0; i--) diff --git a/tools/testing/selftests/bpf/verifier/ref_tracking.c b/tools/testing/selftests/bpf/verifier/ref_tracking.c index f18ce867271f..fd683a32a276 100644 --- a/tools/testing/selftests/bpf/verifier/ref_tracking.c +++ b/tools/testing/selftests/bpf/verifier/ref_tracking.c @@ -1044,3 +1044,39 @@ .result_unpriv = REJECT, .errstr_unpriv = "unknown func", }, +{ + "reference tracking: try to leak released ptr reg", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -4), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_9, BPF_REG_0), + + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_2, 8), + BPF_MOV64_IMM(BPF_REG_3, 0), + BPF_EMIT_CALL(BPF_FUNC_ringbuf_reserve), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_8, BPF_REG_0), + + BPF_MOV64_REG(BPF_REG_1, BPF_REG_8), + BPF_MOV64_IMM(BPF_REG_2, 0), + BPF_EMIT_CALL(BPF_FUNC_ringbuf_discard), + BPF_MOV64_IMM(BPF_REG_0, 0), + + BPF_STX_MEM(BPF_DW, BPF_REG_9, BPF_REG_8, 0), + BPF_EXIT_INSN() + }, + .fixup_map_array_48b = { 4 }, + .fixup_map_ringbuf = { 11 }, + .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv = "R8 !read_ok" +}, diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_control.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_control.sh index d3a891d421ab..64153bbf95df 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_control.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_control.sh @@ -83,6 +83,7 @@ ALL_TESTS=" ptp_general_test flow_action_sample_test flow_action_trap_test + eapol_test " NUM_NETIFS=4 source $lib_dir/lib.sh @@ -677,6 +678,27 @@ flow_action_trap_test() tc qdisc del dev $rp1 clsact } +eapol_payload_get() +{ + local source_mac=$1; shift + local p + + p=$(: + )"01:80:C2:00:00:03:"$( : ETH daddr + )"$source_mac:"$( : ETH saddr + )"88:8E:"$( : ETH type + ) + echo $p +} + +eapol_test() +{ + local h1mac=$(mac_get $h1) + + devlink_trap_stats_test "EAPOL" "eapol" $MZ $h1 -c 1 \ + $(eapol_payload_get $h1mac) -p 100 -q +} + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l2_drops.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l2_drops.sh index a4c2812e9807..8d4b2c6265b3 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l2_drops.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l2_drops.sh @@ -14,6 +14,7 @@ ALL_TESTS=" ingress_stp_filter_test port_list_is_empty_test port_loopback_filter_test + locked_port_test " NUM_NETIFS=4 source $lib_dir/tc_common.sh @@ -420,6 +421,110 @@ port_loopback_filter_test() port_loopback_filter_uc_test } +locked_port_miss_test() +{ + local trap_name="locked_port" + local smac=00:11:22:33:44:55 + + bridge link set dev $swp1 learning off + bridge link set dev $swp1 locked on + + RET=0 + + devlink_trap_stats_check $trap_name $MZ $h1 -c 1 \ + -a $smac -b $(mac_get $h2) -A 192.0.2.1 -B 192.0.2.2 -p 100 -q + check_fail $? "Trap stats increased before setting action to \"trap\"" + + devlink_trap_action_set $trap_name "trap" + + devlink_trap_stats_check $trap_name $MZ $h1 -c 1 \ + -a $smac -b $(mac_get $h2) -A 192.0.2.1 -B 192.0.2.2 -p 100 -q + check_err $? "Trap stats did not increase when should" + + devlink_trap_action_set $trap_name "drop" + + devlink_trap_stats_check $trap_name $MZ $h1 -c 1 \ + -a $smac -b $(mac_get $h2) -A 192.0.2.1 -B 192.0.2.2 -p 100 -q + check_fail $? "Trap stats increased after setting action to \"drop\"" + + devlink_trap_action_set $trap_name "trap" + + bridge fdb replace $smac dev $swp1 master static vlan 1 + + devlink_trap_stats_check $trap_name $MZ $h1 -c 1 \ + -a $smac -b $(mac_get $h2) -A 192.0.2.1 -B 192.0.2.2 -p 100 -q + check_fail $? "Trap stats increased after adding an FDB entry" + + bridge fdb del $smac dev $swp1 master static vlan 1 + bridge link set dev $swp1 locked off + + devlink_trap_stats_check $trap_name $MZ $h1 -c 1 \ + -a $smac -b $(mac_get $h2) -A 192.0.2.1 -B 192.0.2.2 -p 100 -q + check_fail $? "Trap stats increased after unlocking port" + + log_test "Locked port - FDB miss" + + devlink_trap_action_set $trap_name "drop" + bridge link set dev $swp1 learning on +} + +locked_port_mismatch_test() +{ + local trap_name="locked_port" + local smac=00:11:22:33:44:55 + + bridge link set dev $swp1 learning off + bridge link set dev $swp1 locked on + + RET=0 + + bridge fdb replace $smac dev $swp2 master static vlan 1 + + devlink_trap_stats_check $trap_name $MZ $h1 -c 1 \ + -a $smac -b $(mac_get $h2) -A 192.0.2.1 -B 192.0.2.2 -p 100 -q + check_fail $? "Trap stats increased before setting action to \"trap\"" + + devlink_trap_action_set $trap_name "trap" + + devlink_trap_stats_check $trap_name $MZ $h1 -c 1 \ + -a $smac -b $(mac_get $h2) -A 192.0.2.1 -B 192.0.2.2 -p 100 -q + check_err $? "Trap stats did not increase when should" + + devlink_trap_action_set $trap_name "drop" + + devlink_trap_stats_check $trap_name $MZ $h1 -c 1 \ + -a $smac -b $(mac_get $h2) -A 192.0.2.1 -B 192.0.2.2 -p 100 -q + check_fail $? "Trap stats increased after setting action to \"drop\"" + + devlink_trap_action_set $trap_name "trap" + bridge link set dev $swp1 locked off + + devlink_trap_stats_check $trap_name $MZ $h1 -c 1 \ + -a $smac -b $(mac_get $h2) -A 192.0.2.1 -B 192.0.2.2 -p 100 -q + check_fail $? "Trap stats increased after unlocking port" + + bridge link set dev $swp1 locked on + bridge fdb replace $smac dev $swp1 master static vlan 1 + + devlink_trap_stats_check $trap_name $MZ $h1 -c 1 \ + -a $smac -b $(mac_get $h2) -A 192.0.2.1 -B 192.0.2.2 -p 100 -q + check_fail $? "Trap stats increased after replacing an FDB entry" + + bridge fdb del $smac dev $swp1 master static vlan 1 + devlink_trap_action_set $trap_name "drop" + + log_test "Locked port - FDB mismatch" + + bridge link set dev $swp1 locked off + bridge link set dev $swp1 learning on +} + +locked_port_test() +{ + locked_port_miss_test + locked_port_mismatch_test +} + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh index 04f03ae9d8fb..5e89657857c7 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh @@ -34,6 +34,7 @@ ALL_TESTS=" nexthop_obj_bucket_offload_test nexthop_obj_blackhole_offload_test nexthop_obj_route_offload_test + bridge_locked_port_test devlink_reload_test " NUM_NETIFS=2 @@ -917,6 +918,36 @@ nexthop_obj_route_offload_test() simple_if_fini $swp1 192.0.2.1/24 2001:db8:1::1/64 } +bridge_locked_port_test() +{ + RET=0 + + ip link add name br1 up type bridge vlan_filtering 0 + + ip link add link $swp1 name $swp1.10 type vlan id 10 + ip link set dev $swp1.10 master br1 + + bridge link set dev $swp1.10 locked on + check_fail $? "managed to set locked flag on a VLAN upper" + + ip link set dev $swp1.10 nomaster + ip link set dev $swp1 master br1 + + bridge link set dev $swp1 locked on + check_fail $? "managed to set locked flag on a bridge port that has a VLAN upper" + + ip link del dev $swp1.10 + bridge link set dev $swp1 locked on + + ip link add link $swp1 name $swp1.10 type vlan id 10 + check_fail $? "managed to configure a VLAN upper on a locked port" + + log_test "bridge locked port" + + ip link del dev $swp1.10 &> /dev/null + ip link del dev br1 +} + devlink_reload_test() { # Test that after executing all the above configuration tests, a diff --git a/tools/testing/selftests/landlock/Makefile b/tools/testing/selftests/landlock/Makefile index 6632bfff486b..348e2dbdb4e0 100644 --- a/tools/testing/selftests/landlock/Makefile +++ b/tools/testing/selftests/landlock/Makefile @@ -3,7 +3,6 @@ # First run: make -C ../../../.. headers_install CFLAGS += -Wall -O2 $(KHDR_INCLUDES) -LDLIBS += -lcap LOCAL_HDRS += common.h @@ -13,10 +12,12 @@ TEST_GEN_PROGS := $(src_test:.c=) TEST_GEN_PROGS_EXTENDED := true -# Static linking for short targets: +# Short targets: +$(TEST_GEN_PROGS): LDLIBS += -lcap $(TEST_GEN_PROGS_EXTENDED): LDFLAGS += -static include ../lib.mk -# Static linking for targets with $(OUTPUT)/ prefix: +# Targets with $(OUTPUT)/ prefix: +$(TEST_GEN_PROGS): LDLIBS += -lcap $(TEST_GEN_PROGS_EXTENDED): LDFLAGS += -static diff --git a/tools/testing/selftests/net/forwarding/bridge_locked_port.sh b/tools/testing/selftests/net/forwarding/bridge_locked_port.sh index 5b02b6b60ce7..dc92d32464f6 100755 --- a/tools/testing/selftests/net/forwarding/bridge_locked_port.sh +++ b/tools/testing/selftests/net/forwarding/bridge_locked_port.sh @@ -1,7 +1,16 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 -ALL_TESTS="locked_port_ipv4 locked_port_ipv6 locked_port_vlan" +ALL_TESTS=" + locked_port_ipv4 + locked_port_ipv6 + locked_port_vlan + locked_port_mab + locked_port_mab_roam + locked_port_mab_config + locked_port_mab_flush +" + NUM_NETIFS=4 CHECK_TC="no" source lib.sh @@ -166,6 +175,150 @@ locked_port_ipv6() log_test "Locked port ipv6" } +locked_port_mab() +{ + RET=0 + check_port_mab_support || return 0 + + ping_do $h1 192.0.2.2 + check_err $? "Ping did not work before locking port" + + bridge link set dev $swp1 learning on locked on + + ping_do $h1 192.0.2.2 + check_fail $? "Ping worked on a locked port without an FDB entry" + + bridge fdb get `mac_get $h1` br br0 vlan 1 &> /dev/null + check_fail $? "FDB entry created before enabling MAB" + + bridge link set dev $swp1 learning on locked on mab on + + ping_do $h1 192.0.2.2 + check_fail $? "Ping worked on MAB enabled port without an FDB entry" + + bridge fdb get `mac_get $h1` br br0 vlan 1 | grep "dev $swp1" | grep -q "locked" + check_err $? "Locked FDB entry not created" + + bridge fdb replace `mac_get $h1` dev $swp1 master static + + ping_do $h1 192.0.2.2 + check_err $? "Ping did not work after replacing FDB entry" + + bridge fdb get `mac_get $h1` br br0 vlan 1 | grep "dev $swp1" | grep -q "locked" + check_fail $? "FDB entry marked as locked after replacement" + + bridge fdb del `mac_get $h1` dev $swp1 master + bridge link set dev $swp1 learning off locked off mab off + + log_test "Locked port MAB" +} + +# Check that entries cannot roam to a locked port, but that entries can roam +# to an unlocked port. +locked_port_mab_roam() +{ + local mac=a0:b0:c0:c0:b0:a0 + + RET=0 + check_port_mab_support || return 0 + + bridge link set dev $swp1 learning on locked on mab on + + $MZ $h1 -q -c 5 -d 100msec -t udp -a $mac -b rand + bridge fdb get $mac br br0 vlan 1 | grep "dev $swp1" | grep -q "locked" + check_err $? "No locked entry on first injection" + + $MZ $h2 -q -c 5 -d 100msec -t udp -a $mac -b rand + bridge fdb get $mac br br0 vlan 1 | grep -q "dev $swp2" + check_err $? "Entry did not roam to an unlocked port" + + bridge fdb get $mac br br0 vlan 1 | grep -q "locked" + check_fail $? "Entry roamed with locked flag on" + + $MZ $h1 -q -c 5 -d 100msec -t udp -a $mac -b rand + bridge fdb get $mac br br0 vlan 1 | grep -q "dev $swp1" + check_fail $? "Entry roamed back to locked port" + + bridge fdb del $mac vlan 1 dev $swp2 master + bridge link set dev $swp1 learning off locked off mab off + + log_test "Locked port MAB roam" +} + +# Check that MAB can only be enabled on a port that is both locked and has +# learning enabled. +locked_port_mab_config() +{ + RET=0 + check_port_mab_support || return 0 + + bridge link set dev $swp1 learning on locked off mab on &> /dev/null + check_fail $? "MAB enabled while port is unlocked" + + bridge link set dev $swp1 learning off locked on mab on &> /dev/null + check_fail $? "MAB enabled while port has learning disabled" + + bridge link set dev $swp1 learning on locked on mab on + check_err $? "Failed to enable MAB when port is locked and has learning enabled" + + bridge link set dev $swp1 learning off locked off mab off + + log_test "Locked port MAB configuration" +} + +# Check that locked FDB entries are flushed from a port when MAB is disabled. +locked_port_mab_flush() +{ + local locked_mac1=00:01:02:03:04:05 + local unlocked_mac1=00:01:02:03:04:06 + local locked_mac2=00:01:02:03:04:07 + local unlocked_mac2=00:01:02:03:04:08 + + RET=0 + check_port_mab_support || return 0 + + bridge link set dev $swp1 learning on locked on mab on + bridge link set dev $swp2 learning on locked on mab on + + # Create regular and locked FDB entries on each port. + bridge fdb add $unlocked_mac1 dev $swp1 vlan 1 master static + bridge fdb add $unlocked_mac2 dev $swp2 vlan 1 master static + + $MZ $h1 -q -c 5 -d 100msec -t udp -a $locked_mac1 -b rand + bridge fdb get $locked_mac1 br br0 vlan 1 | grep "dev $swp1" | \ + grep -q "locked" + check_err $? "Failed to create locked FDB entry on first port" + + $MZ $h2 -q -c 5 -d 100msec -t udp -a $locked_mac2 -b rand + bridge fdb get $locked_mac2 br br0 vlan 1 | grep "dev $swp2" | \ + grep -q "locked" + check_err $? "Failed to create locked FDB entry on second port" + + # Disable MAB on the first port and check that only the first locked + # FDB entry was flushed. + bridge link set dev $swp1 mab off + + bridge fdb get $unlocked_mac1 br br0 vlan 1 &> /dev/null + check_err $? "Regular FDB entry on first port was flushed after disabling MAB" + + bridge fdb get $unlocked_mac2 br br0 vlan 1 &> /dev/null + check_err $? "Regular FDB entry on second port was flushed after disabling MAB" + + bridge fdb get $locked_mac1 br br0 vlan 1 &> /dev/null + check_fail $? "Locked FDB entry on first port was not flushed after disabling MAB" + + bridge fdb get $locked_mac2 br br0 vlan 1 &> /dev/null + check_err $? "Locked FDB entry on second port was flushed after disabling MAB" + + bridge fdb del $unlocked_mac2 dev $swp2 vlan 1 master static + bridge fdb del $unlocked_mac1 dev $swp1 vlan 1 master static + + bridge link set dev $swp2 learning on locked off mab off + bridge link set dev $swp1 learning off locked off mab off + + log_test "Locked port MAB FDB flush" +} + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/net/forwarding/devlink_lib.sh b/tools/testing/selftests/net/forwarding/devlink_lib.sh index 601990c6881b..f1de525cfa55 100644 --- a/tools/testing/selftests/net/forwarding/devlink_lib.sh +++ b/tools/testing/selftests/net/forwarding/devlink_lib.sh @@ -503,25 +503,30 @@ devlink_trap_drop_cleanup() tc filter del dev $dev egress protocol $proto pref $pref handle $handle flower } -devlink_trap_stats_test() +devlink_trap_stats_check() { - local test_name=$1; shift local trap_name=$1; shift local send_one="$@" local t0_packets local t1_packets - RET=0 - t0_packets=$(devlink_trap_rx_packets_get $trap_name) $send_one && sleep 1 t1_packets=$(devlink_trap_rx_packets_get $trap_name) - if [[ $t1_packets -eq $t0_packets ]]; then - check_err 1 "Trap stats did not increase" - fi + [[ $t1_packets -ne $t0_packets ]] +} + +devlink_trap_stats_test() +{ + local test_name=$1; shift + + RET=0 + + devlink_trap_stats_check "$@" + check_err $? "Trap stats did not increase" log_test "$test_name" } diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 3ffb9d6c0950..1c4f866de7d7 100755 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -137,6 +137,14 @@ check_locked_port_support() fi } +check_port_mab_support() +{ + if ! bridge -d link show | grep -q "mab"; then + echo "SKIP: iproute2 too old; MacAuth feature not supported." + return $ksft_skip + fi +} + if [[ "$(id -u)" -ne 0 ]]; then echo "SKIP: need root privileges" exit $ksft_skip diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh index ebbd0b282432..6a443ca3cd3a 100755 --- a/tools/testing/selftests/net/udpgro.sh +++ b/tools/testing/selftests/net/udpgro.sh @@ -50,7 +50,7 @@ run_one() { echo "failed" & # Hack: let bg programs complete the startup - sleep 0.1 + sleep 0.2 ./udpgso_bench_tx ${tx_args} ret=$? wait $(jobs -p) @@ -117,7 +117,7 @@ run_one_2sock() { echo "failed" & # Hack: let bg programs complete the startup - sleep 0.1 + sleep 0.2 ./udpgso_bench_tx ${tx_args} -p 12345 sleep 0.1 # first UDP GSO socket should be closed at this point diff --git a/tools/testing/selftests/net/udpgro_bench.sh b/tools/testing/selftests/net/udpgro_bench.sh index fad2d1a71cac..8a1109a545db 100755 --- a/tools/testing/selftests/net/udpgro_bench.sh +++ b/tools/testing/selftests/net/udpgro_bench.sh @@ -39,7 +39,7 @@ run_one() { ip netns exec "${PEER_NS}" ./udpgso_bench_rx -t ${rx_args} -r & # Hack: let bg programs complete the startup - sleep 0.1 + sleep 0.2 ./udpgso_bench_tx ${tx_args} } diff --git a/tools/testing/selftests/net/udpgro_frglist.sh b/tools/testing/selftests/net/udpgro_frglist.sh index 832c738cc3c2..7fe85ba51075 100755 --- a/tools/testing/selftests/net/udpgro_frglist.sh +++ b/tools/testing/selftests/net/udpgro_frglist.sh @@ -44,7 +44,7 @@ run_one() { ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} -r & # Hack: let bg programs complete the startup - sleep 0.1 + sleep 0.2 ./udpgso_bench_tx ${tx_args} } diff --git a/tools/testing/selftests/netfilter/rpath.sh b/tools/testing/selftests/netfilter/rpath.sh index 2d8da7bd8ab7..f7311e66d219 100755 --- a/tools/testing/selftests/netfilter/rpath.sh +++ b/tools/testing/selftests/netfilter/rpath.sh @@ -15,7 +15,7 @@ fi if ip6tables-legacy --version >/dev/null 2>&1; then ip6tables='ip6tables-legacy' -elif ! ip6tables --version >/dev/null 2>&1; then +elif ip6tables --version >/dev/null 2>&1; then ip6tables='ip6tables' else ip6tables='' @@ -62,9 +62,11 @@ ip -net "$ns1" a a fec0:42::2/64 dev v0 nodad ip -net "$ns2" a a fec0:42::1/64 dev d0 nodad # firewall matches to test -ip netns exec "$ns2" "$iptables" -t raw -A PREROUTING -s 192.168.0.0/16 -m rpfilter -ip netns exec "$ns2" "$ip6tables" -t raw -A PREROUTING -s fec0::/16 -m rpfilter -ip netns exec "$ns2" nft -f - <<EOF +[ -n "$iptables" ] && ip netns exec "$ns2" \ + "$iptables" -t raw -A PREROUTING -s 192.168.0.0/16 -m rpfilter +[ -n "$ip6tables" ] && ip netns exec "$ns2" \ + "$ip6tables" -t raw -A PREROUTING -s fec0::/16 -m rpfilter +[ -n "$nft" ] && ip netns exec "$ns2" $nft -f - <<EOF table inet t { chain c { type filter hook prerouting priority raw; @@ -106,8 +108,8 @@ testrun() { if [ -n "$nft" ]; then ( echo "delete table inet t"; - ip netns exec "$ns2" nft -s list table inet t; - ) | ip netns exec "$ns2" nft -f - + ip netns exec "$ns2" $nft -s list table inet t; + ) | ip netns exec "$ns2" $nft -f - fi # test 1: martian traffic should fail rpfilter matches diff --git a/tools/testing/selftests/pidfd/Makefile b/tools/testing/selftests/pidfd/Makefile index f4a2f28f926b..778b6cdc8aed 100644 --- a/tools/testing/selftests/pidfd/Makefile +++ b/tools/testing/selftests/pidfd/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only -CFLAGS += -g -I../../../../usr/include/ -pthread +CFLAGS += -g -I../../../../usr/include/ -pthread -Wall TEST_GEN_PROGS := pidfd_test pidfd_fdinfo_test pidfd_open_test \ pidfd_poll_test pidfd_wait pidfd_getfd_test pidfd_setns_test diff --git a/tools/testing/selftests/pidfd/pidfd_test.c b/tools/testing/selftests/pidfd/pidfd_test.c index 9a2d64901d59..e2dd4ed84984 100644 --- a/tools/testing/selftests/pidfd/pidfd_test.c +++ b/tools/testing/selftests/pidfd/pidfd_test.c @@ -413,7 +413,7 @@ static void poll_pidfd(const char *test_name, int pidfd) c = epoll_wait(epoll_fd, events, MAX_EVENTS, 5000); if (c != 1 || !(events[0].events & EPOLLIN)) - ksft_exit_fail_msg("%s test: Unexpected epoll_wait result (c=%d, events=%x) ", + ksft_exit_fail_msg("%s test: Unexpected epoll_wait result (c=%d, events=%x) " "(errno %d)\n", test_name, c, events[0].events, errno); @@ -435,6 +435,8 @@ static int child_poll_exec_test(void *args) */ while (1) sleep(1); + + return 0; } static void test_pidfd_poll_exec(int use_waitpid) diff --git a/tools/testing/selftests/pidfd/pidfd_wait.c b/tools/testing/selftests/pidfd/pidfd_wait.c index 070c1c876df1..0dcb8365ddc3 100644 --- a/tools/testing/selftests/pidfd/pidfd_wait.c +++ b/tools/testing/selftests/pidfd/pidfd_wait.c @@ -95,20 +95,28 @@ TEST(wait_states) .flags = CLONE_PIDFD | CLONE_PARENT_SETTID, .exit_signal = SIGCHLD, }; + int pfd[2]; pid_t pid; siginfo_t info = { .si_signo = 0, }; + ASSERT_EQ(pipe(pfd), 0); pid = sys_clone3(&args); ASSERT_GE(pid, 0); if (pid == 0) { + char buf[2]; + + close(pfd[1]); kill(getpid(), SIGSTOP); + ASSERT_EQ(read(pfd[0], buf, 1), 1); + close(pfd[0]); kill(getpid(), SIGSTOP); exit(EXIT_SUCCESS); } + close(pfd[0]); ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WSTOPPED, NULL), 0); ASSERT_EQ(info.si_signo, SIGCHLD); ASSERT_EQ(info.si_code, CLD_STOPPED); @@ -117,6 +125,8 @@ TEST(wait_states) ASSERT_EQ(sys_pidfd_send_signal(pidfd, SIGCONT, NULL, 0), 0); ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WCONTINUED, NULL), 0); + ASSERT_EQ(write(pfd[1], "C", 1), 1); + close(pfd[1]); ASSERT_EQ(info.si_signo, SIGCHLD); ASSERT_EQ(info.si_code, CLD_CONTINUED); ASSERT_EQ(info.si_pid, parent_tid); @@ -138,7 +148,7 @@ TEST(wait_states) TEST(wait_nonblock) { - int pidfd, status = 0; + int pidfd; unsigned int flags = 0; pid_t parent_tid = -1; struct clone_args args = { diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index f1df24c2bc84..25d7872b29c1 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -4585,6 +4585,9 @@ static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm, } case KVM_CAP_DIRTY_LOG_RING: case KVM_CAP_DIRTY_LOG_RING_ACQ_REL: + if (!kvm_vm_ioctl_check_extension_generic(kvm, cap->cap)) + return -EINVAL; + return kvm_vm_ioctl_enable_dirty_log_ring(kvm, cap->args[0]); default: return kvm_vm_ioctl_enable_cap(kvm, cap); |