diff --git a/Documentation/ABI/testing/sysfs-bus-optee-devices b/Documentation/ABI/testing/sysfs-bus-optee-devices index 0f58701367b66..af31e5a22d89f 100644 --- a/Documentation/ABI/testing/sysfs-bus-optee-devices +++ b/Documentation/ABI/testing/sysfs-bus-optee-devices @@ -6,3 +6,12 @@ Description: OP-TEE bus provides reference to registered drivers under this directory. The matches Trusted Application (TA) driver and corresponding TA in secure OS. Drivers are free to create needed API under optee-ta- directory. + +What: /sys/bus/tee/devices/optee-ta-/need_supplicant +Date: November 2023 +KernelVersion: 6.7 +Contact: op-tee@lists.trustedfirmware.org +Description: + Allows to distinguish whether an OP-TEE based TA/device requires user-space + tee-supplicant to function properly or not. This attribute will be present for + devices which depend on tee-supplicant to be running. diff --git a/Documentation/ABI/testing/sysfs-class-led b/Documentation/ABI/testing/sysfs-class-led index b2ff0012c0f2b..2e24ac3bd7efa 100644 --- a/Documentation/ABI/testing/sysfs-class-led +++ b/Documentation/ABI/testing/sysfs-class-led @@ -59,15 +59,6 @@ Description: brightness. Reading this file when no hw brightness change event has happened will return an ENODATA error. -What: /sys/class/leds//color -Date: June 2023 -KernelVersion: 6.5 -Description: - Color of the LED. - - This is a read-only file. Reading this file returns the color - of the LED as a string (e.g: "red", "green", "multicolor"). - What: /sys/class/leds//trigger Date: March 2006 KernelVersion: 2.6.17 diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 0a1731a0f0ef3..41644336e3587 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -5858,6 +5858,13 @@ This feature may be more efficiently disabled using the csdlock_debug- kernel parameter. + smp.panic_on_ipistall= [KNL] + If a csd_lock_timeout extends for more than + the specified number of milliseconds, panic the + system. By default, let CSD-lock acquisition + take as long as they take. Specifying 300,000 + for this value provides a 5-minute timeout. + smsc-ircc2.nopnp [HW] Don't use PNP to discover SMC devices smsc-ircc2.ircc_cfg= [HW] Device configuration I/O port smsc-ircc2.ircc_sir= [HW] SIR base I/O port diff --git a/Documentation/devicetree/bindings/interrupt-controller/qcom,mpm.yaml b/Documentation/devicetree/bindings/interrupt-controller/qcom,mpm.yaml index 509d20c091af8..6a206111d4e0f 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/qcom,mpm.yaml +++ b/Documentation/devicetree/bindings/interrupt-controller/qcom,mpm.yaml @@ -62,6 +62,9 @@ properties: - description: MPM pin number - description: GIC SPI number for the MPM pin + '#power-domain-cells': + const: 0 + required: - compatible - reg @@ -93,4 +96,5 @@ examples: <86 183>, <90 260>, <91 260>; + #power-domain-cells = <0>; }; diff --git a/Documentation/devicetree/bindings/nvmem/mxs-ocotp.yaml b/Documentation/devicetree/bindings/nvmem/mxs-ocotp.yaml index a9b822aeaa7ed..e436650f0faf7 100644 --- a/Documentation/devicetree/bindings/nvmem/mxs-ocotp.yaml +++ b/Documentation/devicetree/bindings/nvmem/mxs-ocotp.yaml @@ -14,9 +14,11 @@ allOf: properties: compatible: - enum: - - fsl,imx23-ocotp - - fsl,imx28-ocotp + items: + - enum: + - fsl,imx23-ocotp + - fsl,imx28-ocotp + - const: fsl,ocotp reg: maxItems: 1 @@ -34,7 +36,7 @@ unevaluatedProperties: false examples: - | ocotp: efuse@8002c000 { - compatible = "fsl,imx28-ocotp"; + compatible = "fsl,imx28-ocotp", "fsl,ocotp"; #address-cells = <1>; #size-cells = <1>; reg = <0x8002c000 0x2000>; diff --git a/Documentation/devicetree/bindings/phy/qcom,snps-eusb2-repeater.yaml b/Documentation/devicetree/bindings/phy/qcom,snps-eusb2-repeater.yaml index 029569d5fcf35..24c733c10e0e9 100644 --- a/Documentation/devicetree/bindings/phy/qcom,snps-eusb2-repeater.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,snps-eusb2-repeater.yaml @@ -32,6 +32,27 @@ properties: vdd3-supply: true + qcom,tune-usb2-disc-thres: + $ref: /schemas/types.yaml#/definitions/uint8 + description: High-Speed disconnect threshold + minimum: 0 + maximum: 7 + default: 0 + + qcom,tune-usb2-amplitude: + $ref: /schemas/types.yaml#/definitions/uint8 + description: High-Speed trasmit amplitude + minimum: 0 + maximum: 15 + default: 8 + + qcom,tune-usb2-preem: + $ref: /schemas/types.yaml#/definitions/uint8 + description: High-Speed TX pre-emphasis tuning + minimum: 0 + maximum: 7 + default: 5 + required: - compatible - reg diff --git a/Documentation/devicetree/bindings/serial/serial.yaml b/Documentation/devicetree/bindings/serial/serial.yaml index ea277560a5966..5727bd549deca 100644 --- a/Documentation/devicetree/bindings/serial/serial.yaml +++ b/Documentation/devicetree/bindings/serial/serial.yaml @@ -96,7 +96,7 @@ then: rts-gpios: false patternProperties: - "^bluetooth|gnss|gps|mcu$": + "^(bluetooth|gnss|gps|mcu)$": if: type: object then: diff --git a/Documentation/devicetree/bindings/timer/renesas,rz-mtu3.yaml b/Documentation/devicetree/bindings/timer/renesas,rz-mtu3.yaml index bffdab0b01859..fbac40b958dde 100644 --- a/Documentation/devicetree/bindings/timer/renesas,rz-mtu3.yaml +++ b/Documentation/devicetree/bindings/timer/renesas,rz-mtu3.yaml @@ -169,27 +169,27 @@ properties: - const: tgib0 - const: tgic0 - const: tgid0 - - const: tgiv0 + - const: tciv0 - const: tgie0 - const: tgif0 - const: tgia1 - const: tgib1 - - const: tgiv1 - - const: tgiu1 + - const: tciv1 + - const: tciu1 - const: tgia2 - const: tgib2 - - const: tgiv2 - - const: tgiu2 + - const: tciv2 + - const: tciu2 - const: tgia3 - const: tgib3 - const: tgic3 - const: tgid3 - - const: tgiv3 + - const: tciv3 - const: tgia4 - const: tgib4 - const: tgic4 - const: tgid4 - - const: tgiv4 + - const: tciv4 - const: tgiu5 - const: tgiv5 - const: tgiw5 @@ -197,18 +197,18 @@ properties: - const: tgib6 - const: tgic6 - const: tgid6 - - const: tgiv6 + - const: tciv6 - const: tgia7 - const: tgib7 - const: tgic7 - const: tgid7 - - const: tgiv7 + - const: tciv7 - const: tgia8 - const: tgib8 - const: tgic8 - const: tgid8 - - const: tgiv8 - - const: tgiu8 + - const: tciv8 + - const: tciu8 clocks: maxItems: 1 @@ -285,16 +285,16 @@ examples: , , ; - interrupt-names = "tgia0", "tgib0", "tgic0", "tgid0", "tgiv0", "tgie0", + interrupt-names = "tgia0", "tgib0", "tgic0", "tgid0", "tciv0", "tgie0", "tgif0", - "tgia1", "tgib1", "tgiv1", "tgiu1", - "tgia2", "tgib2", "tgiv2", "tgiu2", - "tgia3", "tgib3", "tgic3", "tgid3", "tgiv3", - "tgia4", "tgib4", "tgic4", "tgid4", "tgiv4", + "tgia1", "tgib1", "tciv1", "tciu1", + "tgia2", "tgib2", "tciv2", "tciu2", + "tgia3", "tgib3", "tgic3", "tgid3", "tciv3", + "tgia4", "tgib4", "tgic4", "tgid4", "tciv4", "tgiu5", "tgiv5", "tgiw5", - "tgia6", "tgib6", "tgic6", "tgid6", "tgiv6", - "tgia7", "tgib7", "tgic7", "tgid7", "tgiv7", - "tgia8", "tgib8", "tgic8", "tgid8", "tgiv8", "tgiu8"; + "tgia6", "tgib6", "tgic6", "tgid6", "tciv6", + "tgia7", "tgib7", "tgic7", "tgid7", "tciv7", + "tgia8", "tgib8", "tgic8", "tgid8", "tciv8", "tciu8"; clocks = <&cpg CPG_MOD R9A07G044_MTU_X_MCK_MTU3>; power-domains = <&cpg>; resets = <&cpg R9A07G044_MTU_X_PRESET_MTU3>; diff --git a/Documentation/devicetree/bindings/usb/microchip,usb5744.yaml b/Documentation/devicetree/bindings/usb/microchip,usb5744.yaml index ff3a1707ef570..6d4cfd943f584 100644 --- a/Documentation/devicetree/bindings/usb/microchip,usb5744.yaml +++ b/Documentation/devicetree/bindings/usb/microchip,usb5744.yaml @@ -36,7 +36,11 @@ properties: vdd-supply: description: - VDD power supply to the hub + 3V3 power supply to the hub + + vdd2-supply: + description: + 1V2 power supply to the hub peer-hub: $ref: /schemas/types.yaml#/definitions/phandle @@ -62,6 +66,7 @@ allOf: properties: reset-gpios: false vdd-supply: false + vdd2-supply: false peer-hub: false i2c-bus: false else: diff --git a/Documentation/i2c/busses/i2c-i801.rst b/Documentation/i2c/busses/i2c-i801.rst index e76e68ccf7182..10eced6c2e462 100644 --- a/Documentation/i2c/busses/i2c-i801.rst +++ b/Documentation/i2c/busses/i2c-i801.rst @@ -47,6 +47,7 @@ Supported adapters: * Intel Alder Lake (PCH) * Intel Raptor Lake (PCH) * Intel Meteor Lake (SOC and PCH) + * Intel Birch Stream (SOC) Datasheets: Publicly available at the Intel website diff --git a/Makefile b/Makefile index c5d9880154963..6cab2192da5dd 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 PATCHLEVEL = 6 -SUBLEVEL = 2 +SUBLEVEL = 10 NAME = Hurr durr I'ma ninja sloth ifndef EXTRAVERSION diff --git a/arch/arm/boot/dts/broadcom/bcm2711-rpi-400.dts b/arch/arm/boot/dts/broadcom/bcm2711-rpi-400.dts index 1ab8184302db4..5a2869a18bd55 100644 --- a/arch/arm/boot/dts/broadcom/bcm2711-rpi-400.dts +++ b/arch/arm/boot/dts/broadcom/bcm2711-rpi-400.dts @@ -36,9 +36,7 @@ gpios = <&gpio 42 GPIO_ACTIVE_HIGH>; }; -&leds { - /delete-node/ led_act; -}; +/delete-node/ &led_act; &pm { /delete-property/ system-power-controller; diff --git a/arch/arm/boot/dts/nxp/imx/imx6q-skov-reve-mi1010ait-1cp1.dts b/arch/arm/boot/dts/nxp/imx/imx6q-skov-reve-mi1010ait-1cp1.dts index a3f247c722b43..0342a79ccd5db 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6q-skov-reve-mi1010ait-1cp1.dts +++ b/arch/arm/boot/dts/nxp/imx/imx6q-skov-reve-mi1010ait-1cp1.dts @@ -37,9 +37,9 @@ &clks { assigned-clocks = <&clks IMX6QDL_CLK_LDB_DI0_SEL>, - <&clks IMX6QDL_CLK_LDB_DI1_SEL>; + <&clks IMX6QDL_CLK_LDB_DI1_SEL>, <&clks IMX6QDL_CLK_ENET_REF_SEL>; assigned-clock-parents = <&clks IMX6QDL_CLK_PLL5_VIDEO_DIV>, - <&clks IMX6QDL_CLK_PLL5_VIDEO_DIV>; + <&clks IMX6QDL_CLK_PLL5_VIDEO_DIV>, <&clk50m_phy>; }; &hdmi { diff --git a/arch/arm/boot/dts/nxp/imx/imx6ul-pico.dtsi b/arch/arm/boot/dts/nxp/imx/imx6ul-pico.dtsi index 4ffe99ed55ca2..07dcecbe485dc 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6ul-pico.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx6ul-pico.dtsi @@ -121,6 +121,8 @@ max-speed = <100>; interrupt-parent = <&gpio5>; interrupts = <6 IRQ_TYPE_LEVEL_LOW>; + clocks = <&clks IMX6UL_CLK_ENET_REF>; + clock-names = "rmii-ref"; }; }; }; diff --git a/arch/arm/boot/dts/nxp/imx/imx7s.dtsi b/arch/arm/boot/dts/nxp/imx/imx7s.dtsi index e152d08f27d49..bc79163c49b51 100644 --- a/arch/arm/boot/dts/nxp/imx/imx7s.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx7s.dtsi @@ -454,7 +454,7 @@ }; gpt1: timer@302d0000 { - compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt"; + compatible = "fsl,imx7d-gpt", "fsl,imx6dl-gpt"; reg = <0x302d0000 0x10000>; interrupts = ; clocks = <&clks IMX7D_GPT1_ROOT_CLK>, @@ -463,7 +463,7 @@ }; gpt2: timer@302e0000 { - compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt"; + compatible = "fsl,imx7d-gpt", "fsl,imx6dl-gpt"; reg = <0x302e0000 0x10000>; interrupts = ; clocks = <&clks IMX7D_GPT2_ROOT_CLK>, @@ -473,7 +473,7 @@ }; gpt3: timer@302f0000 { - compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt"; + compatible = "fsl,imx7d-gpt", "fsl,imx6dl-gpt"; reg = <0x302f0000 0x10000>; interrupts = ; clocks = <&clks IMX7D_GPT3_ROOT_CLK>, @@ -483,7 +483,7 @@ }; gpt4: timer@30300000 { - compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt"; + compatible = "fsl,imx7d-gpt", "fsl,imx6dl-gpt"; reg = <0x30300000 0x10000>; interrupts = ; clocks = <&clks IMX7D_GPT4_ROOT_CLK>, diff --git a/arch/arm/boot/dts/nxp/mxs/imx28-xea.dts b/arch/arm/boot/dts/nxp/mxs/imx28-xea.dts index a400c108f66a2..6c5e6856648af 100644 --- a/arch/arm/boot/dts/nxp/mxs/imx28-xea.dts +++ b/arch/arm/boot/dts/nxp/mxs/imx28-xea.dts @@ -8,6 +8,7 @@ #include "imx28-lwe.dtsi" / { + model = "Liebherr XEA board"; compatible = "lwn,imx28-xea", "fsl,imx28"; }; diff --git a/arch/arm/boot/dts/rockchip/rk3128.dtsi b/arch/arm/boot/dts/rockchip/rk3128.dtsi index 88a4b0d6d928d..80d81af5fe0ef 100644 --- a/arch/arm/boot/dts/rockchip/rk3128.dtsi +++ b/arch/arm/boot/dts/rockchip/rk3128.dtsi @@ -795,7 +795,7 @@ }; sdmmc_pwren: sdmmc-pwren { - rockchip,pins = <1 RK_PB6 1 &pcfg_pull_default>; + rockchip,pins = <1 RK_PB6 RK_FUNC_GPIO &pcfg_pull_default>; }; sdmmc_bus4: sdmmc-bus4 { diff --git a/arch/arm/boot/dts/ti/omap/am33xx.dtsi b/arch/arm/boot/dts/ti/omap/am33xx.dtsi index 1a2cd5baf4021..5b9e01a8aa5d5 100644 --- a/arch/arm/boot/dts/ti/omap/am33xx.dtsi +++ b/arch/arm/boot/dts/ti/omap/am33xx.dtsi @@ -359,6 +359,7 @@ , , ; + ti,sysc-delay-us = <2>; clocks = <&l3s_clkctrl AM3_L3S_USB_OTG_HS_CLKCTRL 0>; clock-names = "fck"; #address-cells = <1>; diff --git a/arch/arm/boot/dts/ti/omap/dra7.dtsi b/arch/arm/boot/dts/ti/omap/dra7.dtsi index 3f3e52e3b3752..6509c742fb58c 100644 --- a/arch/arm/boot/dts/ti/omap/dra7.dtsi +++ b/arch/arm/boot/dts/ti/omap/dra7.dtsi @@ -147,7 +147,7 @@ l3-noc@44000000 { compatible = "ti,dra7-l3-noc"; - reg = <0x44000000 0x1000>, + reg = <0x44000000 0x1000000>, <0x45000000 0x1000>; interrupts-extended = <&crossbar_mpu GIC_SPI 4 IRQ_TYPE_LEVEL_HIGH>, <&wakeupgen GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>; diff --git a/arch/arm/include/asm/exception.h b/arch/arm/include/asm/exception.h index 58e039a851af0..3c82975d46db3 100644 --- a/arch/arm/include/asm/exception.h +++ b/arch/arm/include/asm/exception.h @@ -10,10 +10,6 @@ #include -#ifdef CONFIG_FUNCTION_GRAPH_TRACER #define __exception_irq_entry __irq_entry -#else -#define __exception_irq_entry -#endif #endif /* __ASM_ARM_EXCEPTION_H */ diff --git a/arch/arm/include/asm/kexec.h b/arch/arm/include/asm/kexec.h index e62832dcba760..a8287e7ab9d41 100644 --- a/arch/arm/include/asm/kexec.h +++ b/arch/arm/include/asm/kexec.h @@ -2,8 +2,6 @@ #ifndef _ARM_KEXEC_H #define _ARM_KEXEC_H -#ifdef CONFIG_KEXEC - /* Maximum physical address we can use pages from */ #define KEXEC_SOURCE_MEMORY_LIMIT (-1UL) /* Maximum address we can reach in physical address mode */ @@ -82,6 +80,4 @@ static inline struct page *boot_pfn_to_page(unsigned long boot_pfn) #endif /* __ASSEMBLY__ */ -#endif /* CONFIG_KEXEC */ - #endif /* _ARM_KEXEC_H */ diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile index d53f56d6f8408..771264d4726a7 100644 --- a/arch/arm/kernel/Makefile +++ b/arch/arm/kernel/Makefile @@ -59,7 +59,7 @@ obj-$(CONFIG_FUNCTION_TRACER) += entry-ftrace.o obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o insn.o patch.o obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o insn.o patch.o obj-$(CONFIG_JUMP_LABEL) += jump_label.o insn.o patch.o -obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o +obj-$(CONFIG_KEXEC_CORE) += machine_kexec.o relocate_kernel.o # Main staffs in KPROBES are in arch/arm/probes/ . obj-$(CONFIG_KPROBES) += patch.o insn.o obj-$(CONFIG_OABI_COMPAT) += sys_oabi-compat.o diff --git a/arch/arm/mach-imx/mmdc.c b/arch/arm/mach-imx/mmdc.c index 2157493b78a9b..df69af9323754 100644 --- a/arch/arm/mach-imx/mmdc.c +++ b/arch/arm/mach-imx/mmdc.c @@ -501,6 +501,10 @@ static int imx_mmdc_perf_init(struct platform_device *pdev, void __iomem *mmdc_b name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "mmdc%d", ret); + if (!name) { + ret = -ENOMEM; + goto pmu_release_id; + } pmu_mmdc->mmdc_ipg_clk = mmdc_ipg_clk; pmu_mmdc->devtype_data = (struct fsl_mmdc_devtype_data *)of_id->data; @@ -523,9 +527,10 @@ static int imx_mmdc_perf_init(struct platform_device *pdev, void __iomem *mmdc_b pmu_register_err: pr_warn("MMDC Perf PMU failed (%d), disabled\n", ret); - ida_simple_remove(&mmdc_ida, pmu_mmdc->id); cpuhp_state_remove_instance_nocalls(cpuhp_mmdc_state, &pmu_mmdc->node); hrtimer_cancel(&pmu_mmdc->hrtimer); +pmu_release_id: + ida_simple_remove(&mmdc_ida, pmu_mmdc->id); pmu_free: kfree(pmu_mmdc); return ret; diff --git a/arch/arm/mach-omap2/id.c b/arch/arm/mach-omap2/id.c index 98999aa8cc0c0..7f387706368a6 100644 --- a/arch/arm/mach-omap2/id.c +++ b/arch/arm/mach-omap2/id.c @@ -793,11 +793,16 @@ void __init omap_soc_device_init(void) soc_dev_attr->machine = soc_name; soc_dev_attr->family = omap_get_family(); + if (!soc_dev_attr->family) { + kfree(soc_dev_attr); + return; + } soc_dev_attr->revision = soc_rev; soc_dev_attr->custom_attr_group = omap_soc_groups[0]; soc_dev = soc_device_register(soc_dev_attr); if (IS_ERR(soc_dev)) { + kfree(soc_dev_attr->family); kfree(soc_dev_attr); return; } diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index 9afdc4c4a5dc1..a395b6c0aae2a 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -484,7 +484,8 @@ static int __init xen_guest_init(void) * for secondary CPUs as they are brought up. * For uniformity we use VCPUOP_register_vcpu_info even on cpu0. */ - xen_vcpu_info = alloc_percpu(struct vcpu_info); + xen_vcpu_info = __alloc_percpu(sizeof(struct vcpu_info), + 1 << fls(sizeof(struct vcpu_info) - 1)); if (xen_vcpu_info == NULL) return -ENOMEM; diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 78f20e6327120..6062a52a084ff 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1368,6 +1368,8 @@ choice config CPU_BIG_ENDIAN bool "Build big-endian kernel" depends on !LD_IS_LLD || LLD_VERSION >= 130000 + # https://github.com/llvm/llvm-project/commit/1379b150991f70a5782e9a143c2ba5308da1161c + depends on AS_IS_GNU || AS_VERSION >= 150000 help Say Y if you plan on running a kernel with a big-endian userspace. diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 2d49aea0ff67a..26b8c7630a214 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -158,7 +158,7 @@ endif all: $(notdir $(KBUILD_IMAGE)) - +vmlinuz.efi: Image Image vmlinuz.efi: vmlinux $(Q)$(MAKE) $(build)=$(boot) $(boot)/$@ diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h616-orangepi-zero.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-h616-orangepi-zero.dtsi index 15290e6892fca..fc7315b944065 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h616-orangepi-zero.dtsi +++ b/arch/arm64/boot/dts/allwinner/sun50i-h616-orangepi-zero.dtsi @@ -68,10 +68,7 @@ &emac0 { pinctrl-names = "default"; pinctrl-0 = <&ext_rgmii_pins>; - phy-mode = "rgmii"; phy-handle = <&ext_rgmii_phy>; - allwinner,rx-delay-ps = <3100>; - allwinner,tx-delay-ps = <700>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h616-orangepi-zero2.dts b/arch/arm64/boot/dts/allwinner/sun50i-h616-orangepi-zero2.dts index d83852e72f063..b5d713926a341 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h616-orangepi-zero2.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h616-orangepi-zero2.dts @@ -13,6 +13,9 @@ }; &emac0 { + allwinner,rx-delay-ps = <3100>; + allwinner,tx-delay-ps = <700>; + phy-mode = "rgmii"; phy-supply = <®_dcdce>; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h618-orangepi-zero3.dts b/arch/arm64/boot/dts/allwinner/sun50i-h618-orangepi-zero3.dts index 00fe28caac939..b3b1b8692125f 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h618-orangepi-zero3.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h618-orangepi-zero3.dts @@ -13,6 +13,8 @@ }; &emac0 { + allwinner,tx-delay-ps = <700>; + phy-mode = "rgmii-rxid"; phy-supply = <®_dldo1>; }; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi index d2f5345d05600..717288bbdb8b6 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi @@ -1186,26 +1186,34 @@ dma-coherent; }; - usb0: usb@3100000 { - status = "disabled"; - compatible = "snps,dwc3"; - reg = <0x0 0x3100000 0x0 0x10000>; - interrupts = <0 80 0x4>; /* Level high type */ - dr_mode = "host"; - snps,quirk-frame-length-adjustment = <0x20>; - snps,dis_rxdet_inp3_quirk; - snps,incr-burst-type-adjustment = <1>, <4>, <8>, <16>; - }; + bus: bus { + #address-cells = <2>; + #size-cells = <2>; + compatible = "simple-bus"; + ranges; + dma-ranges = <0x0 0x0 0x0 0x0 0x100 0x00000000>; + + usb0: usb@3100000 { + compatible = "snps,dwc3"; + reg = <0x0 0x3100000 0x0 0x10000>; + interrupts = <0 80 0x4>; /* Level high type */ + dr_mode = "host"; + snps,quirk-frame-length-adjustment = <0x20>; + snps,dis_rxdet_inp3_quirk; + snps,incr-burst-type-adjustment = <1>, <4>, <8>, <16>; + status = "disabled"; + }; - usb1: usb@3110000 { - status = "disabled"; - compatible = "snps,dwc3"; - reg = <0x0 0x3110000 0x0 0x10000>; - interrupts = <0 81 0x4>; /* Level high type */ - dr_mode = "host"; - snps,quirk-frame-length-adjustment = <0x20>; - snps,dis_rxdet_inp3_quirk; - snps,incr-burst-type-adjustment = <1>, <4>, <8>, <16>; + usb1: usb@3110000 { + compatible = "snps,dwc3"; + reg = <0x0 0x3110000 0x0 0x10000>; + interrupts = <0 81 0x4>; /* Level high type */ + dr_mode = "host"; + snps,quirk-frame-length-adjustment = <0x20>; + snps,dis_rxdet_inp3_quirk; + snps,incr-burst-type-adjustment = <1>, <4>, <8>, <16>; + status = "disabled"; + }; }; ccn@4000000 { diff --git a/arch/arm64/boot/dts/freescale/imx8-apalis-v1.1.dtsi b/arch/arm64/boot/dts/freescale/imx8-apalis-v1.1.dtsi index 9b1b522517f8e..0878a15acc1ba 100644 --- a/arch/arm64/boot/dts/freescale/imx8-apalis-v1.1.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8-apalis-v1.1.dtsi @@ -82,12 +82,9 @@ pinctrl-0 = <&pinctrl_wifi_pdn>; gpio = <&lsio_gpio1 28 GPIO_ACTIVE_HIGH>; enable-active-high; + regulator-always-on; regulator-name = "wifi_pwrdn_fake_regulator"; regulator-settling-time-us = <100>; - - regulator-state-mem { - regulator-off-in-suspend; - }; }; reg_pcie_switch: regulator-pcie-switch { diff --git a/arch/arm64/boot/dts/freescale/imx8-ss-lsio.dtsi b/arch/arm64/boot/dts/freescale/imx8-ss-lsio.dtsi index ea8c93757521b..133f2b1ce1d2e 100644 --- a/arch/arm64/boot/dts/freescale/imx8-ss-lsio.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8-ss-lsio.dtsi @@ -36,7 +36,8 @@ lsio_subsys: bus@5d000000 { <&pwm0_lpcg 1>; assigned-clocks = <&clk IMX_SC_R_PWM_0 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <24000000>; - #pwm-cells = <2>; + #pwm-cells = <3>; + interrupts = ; status = "disabled"; }; @@ -48,7 +49,8 @@ lsio_subsys: bus@5d000000 { <&pwm1_lpcg 1>; assigned-clocks = <&clk IMX_SC_R_PWM_1 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <24000000>; - #pwm-cells = <2>; + #pwm-cells = <3>; + interrupts = ; status = "disabled"; }; @@ -60,7 +62,8 @@ lsio_subsys: bus@5d000000 { <&pwm2_lpcg 1>; assigned-clocks = <&clk IMX_SC_R_PWM_2 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <24000000>; - #pwm-cells = <2>; + #pwm-cells = <3>; + interrupts = ; status = "disabled"; }; @@ -72,7 +75,8 @@ lsio_subsys: bus@5d000000 { <&pwm3_lpcg 1>; assigned-clocks = <&clk IMX_SC_R_PWM_3 IMX_SC_PM_CLK_PER>; assigned-clock-rates = <24000000>; - #pwm-cells = <2>; + #pwm-cells = <3>; + interrupts = ; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi index 83d907294fbc7..4b50920ac2049 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi @@ -2030,6 +2030,7 @@ phys = <&usb3_phy0>, <&usb3_phy0>; phy-names = "usb2-phy", "usb3-phy"; snps,gfladj-refclk-lpm-sel-quirk; + snps,parkmode-disable-ss-quirk; }; }; @@ -2072,6 +2073,7 @@ phys = <&usb3_phy1>, <&usb3_phy1>; phy-names = "usb2-phy", "usb3-phy"; snps,gfladj-refclk-lpm-sel-quirk; + snps,parkmode-disable-ss-quirk; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mq.dtsi b/arch/arm64/boot/dts/freescale/imx8mq.dtsi index 35f07dfb4ca8d..052ba9baa400f 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mq.dtsi @@ -1649,6 +1649,7 @@ phys = <&usb3_phy0>, <&usb3_phy0>; phy-names = "usb2-phy", "usb3-phy"; power-domains = <&pgc_otg1>; + snps,parkmode-disable-ss-quirk; status = "disabled"; }; @@ -1680,6 +1681,7 @@ phys = <&usb3_phy1>, <&usb3_phy1>; phy-names = "usb2-phy", "usb3-phy"; power-domains = <&pgc_otg2>; + snps,parkmode-disable-ss-quirk; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxla.dts b/arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxla.dts index f06139bdff97e..3c5c67ebee5d3 100644 --- a/arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxla.dts +++ b/arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxla.dts @@ -577,7 +577,7 @@ fsl,pins = < MX93_PAD_UART2_TXD__LPUART2_TX 0x31e MX93_PAD_UART2_RXD__LPUART2_RX 0x31e - MX93_PAD_SAI1_TXD0__LPUART2_RTS_B 0x31e + MX93_PAD_SAI1_TXD0__LPUART2_RTS_B 0x51e >; }; diff --git a/arch/arm64/boot/dts/freescale/imx93.dtsi b/arch/arm64/boot/dts/freescale/imx93.dtsi index dcf6e4846ac9d..943b7e6655634 100644 --- a/arch/arm64/boot/dts/freescale/imx93.dtsi +++ b/arch/arm64/boot/dts/freescale/imx93.dtsi @@ -373,7 +373,7 @@ compatible = "fsl,imx93-src-slice"; reg = <0x44462400 0x400>, <0x44465800 0x400>; #power-domain-cells = <0>; - clocks = <&clk IMX93_CLK_MEDIA_AXI>, + clocks = <&clk IMX93_CLK_NIC_MEDIA_GATE>, <&clk IMX93_CLK_MEDIA_APB>; }; }; diff --git a/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts b/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts index 86cedb0bf1a90..94e1cc9fbea33 100644 --- a/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts +++ b/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts @@ -73,7 +73,7 @@ }; }; - memory { + memory@40000000 { reg = <0 0x40000000 0 0x40000000>; }; diff --git a/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts b/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts index dad8e683aac5b..c435984ca7674 100644 --- a/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts +++ b/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts @@ -55,7 +55,7 @@ }; }; - memory { + memory@40000000 { reg = <0 0x40000000 0 0x20000000>; }; diff --git a/arch/arm64/boot/dts/mediatek/mt7986a-bananapi-bpi-r3.dts b/arch/arm64/boot/dts/mediatek/mt7986a-bananapi-bpi-r3.dts index af4a4309bda4b..b876e501216be 100644 --- a/arch/arm64/boot/dts/mediatek/mt7986a-bananapi-bpi-r3.dts +++ b/arch/arm64/boot/dts/mediatek/mt7986a-bananapi-bpi-r3.dts @@ -126,6 +126,7 @@ compatible = "sff,sfp"; i2c-bus = <&i2c_sfp1>; los-gpios = <&pio 46 GPIO_ACTIVE_HIGH>; + maximum-power-milliwatt = <3000>; mod-def0-gpios = <&pio 49 GPIO_ACTIVE_LOW>; tx-disable-gpios = <&pio 20 GPIO_ACTIVE_HIGH>; tx-fault-gpios = <&pio 7 GPIO_ACTIVE_HIGH>; @@ -137,6 +138,7 @@ i2c-bus = <&i2c_sfp2>; los-gpios = <&pio 31 GPIO_ACTIVE_HIGH>; mod-def0-gpios = <&pio 47 GPIO_ACTIVE_LOW>; + maximum-power-milliwatt = <3000>; tx-disable-gpios = <&pio 15 GPIO_ACTIVE_HIGH>; tx-fault-gpios = <&pio 48 GPIO_ACTIVE_HIGH>; }; @@ -150,16 +152,16 @@ trip = <&cpu_trip_active_high>; }; - cpu-active-low { + cpu-active-med { /* active: set fan to cooling level 1 */ cooling-device = <&fan 1 1>; - trip = <&cpu_trip_active_low>; + trip = <&cpu_trip_active_med>; }; - cpu-passive { - /* passive: set fan to cooling level 0 */ + cpu-active-low { + /* active: set fan to cooling level 0 */ cooling-device = <&fan 0 0>; - trip = <&cpu_trip_passive>; + trip = <&cpu_trip_active_low>; }; }; }; diff --git a/arch/arm64/boot/dts/mediatek/mt7986a.dtsi b/arch/arm64/boot/dts/mediatek/mt7986a.dtsi index 24eda00e320d3..fc751e049953c 100644 --- a/arch/arm64/boot/dts/mediatek/mt7986a.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt7986a.dtsi @@ -374,6 +374,10 @@ reg = <0 0x11230000 0 0x1000>, <0 0x11c20000 0 0x1000>; interrupts = ; + assigned-clocks = <&topckgen CLK_TOP_EMMC_416M_SEL>, + <&topckgen CLK_TOP_EMMC_250M_SEL>; + assigned-clock-parents = <&apmixedsys CLK_APMIXED_MPLL>, + <&topckgen CLK_TOP_NET1PLL_D5_D2>; clocks = <&topckgen CLK_TOP_EMMC_416M_SEL>, <&infracfg CLK_INFRA_MSDC_HCK_CK>, <&infracfg CLK_INFRA_MSDC_CK>, @@ -610,22 +614,34 @@ thermal-sensors = <&thermal 0>; trips { + cpu_trip_crit: crit { + temperature = <125000>; + hysteresis = <2000>; + type = "critical"; + }; + + cpu_trip_hot: hot { + temperature = <120000>; + hysteresis = <2000>; + type = "hot"; + }; + cpu_trip_active_high: active-high { temperature = <115000>; hysteresis = <2000>; type = "active"; }; - cpu_trip_active_low: active-low { + cpu_trip_active_med: active-med { temperature = <85000>; hysteresis = <2000>; type = "active"; }; - cpu_trip_passive: passive { - temperature = <40000>; + cpu_trip_active_low: active-low { + temperature = <60000>; hysteresis = <2000>; - type = "passive"; + type = "active"; }; }; }; diff --git a/arch/arm64/boot/dts/mediatek/mt8173-evb.dts b/arch/arm64/boot/dts/mediatek/mt8173-evb.dts index 5122963d8743a..d258c80213b26 100644 --- a/arch/arm64/boot/dts/mediatek/mt8173-evb.dts +++ b/arch/arm64/boot/dts/mediatek/mt8173-evb.dts @@ -44,7 +44,7 @@ id-gpio = <&pio 16 GPIO_ACTIVE_HIGH>; }; - usb_p1_vbus: regulator@0 { + usb_p1_vbus: regulator-usb-p1 { compatible = "regulator-fixed"; regulator-name = "usb_vbus"; regulator-min-microvolt = <5000000>; @@ -53,7 +53,7 @@ enable-active-high; }; - usb_p0_vbus: regulator@1 { + usb_p0_vbus: regulator-usb-p0 { compatible = "regulator-fixed"; regulator-name = "vbus"; regulator-min-microvolt = <5000000>; diff --git a/arch/arm64/boot/dts/mediatek/mt8183-evb.dts b/arch/arm64/boot/dts/mediatek/mt8183-evb.dts index d8bd518076832..77f9ab94c00bd 100644 --- a/arch/arm64/boot/dts/mediatek/mt8183-evb.dts +++ b/arch/arm64/boot/dts/mediatek/mt8183-evb.dts @@ -31,14 +31,14 @@ #address-cells = <2>; #size-cells = <2>; ranges; - scp_mem_reserved: scp_mem_region { + scp_mem_reserved: memory@50000000 { compatible = "shared-dma-pool"; reg = <0 0x50000000 0 0x2900000>; no-map; }; }; - ntc@0 { + thermal-sensor { compatible = "murata,ncp03wf104"; pullup-uv = <1800000>; pullup-ohm = <390000>; @@ -155,8 +155,8 @@ }; &pio { - i2c_pins_0: i2c0{ - pins_i2c{ + i2c_pins_0: i2c0 { + pins_i2c { pinmux = , ; mediatek,pull-up-adv = <3>; @@ -164,8 +164,8 @@ }; }; - i2c_pins_1: i2c1{ - pins_i2c{ + i2c_pins_1: i2c1 { + pins_i2c { pinmux = , ; mediatek,pull-up-adv = <3>; @@ -173,8 +173,8 @@ }; }; - i2c_pins_2: i2c2{ - pins_i2c{ + i2c_pins_2: i2c2 { + pins_i2c { pinmux = , ; mediatek,pull-up-adv = <3>; @@ -182,8 +182,8 @@ }; }; - i2c_pins_3: i2c3{ - pins_i2c{ + i2c_pins_3: i2c3 { + pins_i2c { pinmux = , ; mediatek,pull-up-adv = <3>; @@ -191,8 +191,8 @@ }; }; - i2c_pins_4: i2c4{ - pins_i2c{ + i2c_pins_4: i2c4 { + pins_i2c { pinmux = , ; mediatek,pull-up-adv = <3>; @@ -200,8 +200,8 @@ }; }; - i2c_pins_5: i2c5{ - pins_i2c{ + i2c_pins_5: i2c5 { + pins_i2c { pinmux = , ; mediatek,pull-up-adv = <3>; @@ -209,8 +209,8 @@ }; }; - spi_pins_0: spi0{ - pins_spi{ + spi_pins_0: spi0 { + pins_spi { pinmux = , , , @@ -324,8 +324,8 @@ }; }; - spi_pins_1: spi1{ - pins_spi{ + spi_pins_1: spi1 { + pins_spi { pinmux = , , , @@ -334,8 +334,8 @@ }; }; - spi_pins_2: spi2{ - pins_spi{ + spi_pins_2: spi2 { + pins_spi { pinmux = , , , @@ -344,8 +344,8 @@ }; }; - spi_pins_3: spi3{ - pins_spi{ + spi_pins_3: spi3 { + pins_spi { pinmux = , , , @@ -354,8 +354,8 @@ }; }; - spi_pins_4: spi4{ - pins_spi{ + spi_pins_4: spi4 { + pins_spi { pinmux = , , , @@ -364,8 +364,8 @@ }; }; - spi_pins_5: spi5{ - pins_spi{ + spi_pins_5: spi5 { + pins_spi { pinmux = , , , diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi.dtsi index bf97b60ae4d17..820260348de9b 100644 --- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi.dtsi @@ -91,6 +91,8 @@ &dsi0 { status = "okay"; + /delete-property/#size-cells; + /delete-property/#address-cells; /delete-node/panel@0; ports { port { @@ -441,20 +443,20 @@ }; touchscreen_pins: touchscreen-pins { - touch_int_odl { + touch-int-odl { pinmux = ; input-enable; bias-pull-up; }; - touch_rst_l { + touch-rst-l { pinmux = ; output-high; }; }; trackpad_pins: trackpad-pins { - trackpad_int { + trackpad-int { pinmux = ; input-enable; bias-disable; /* pulled externally */ diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi index 6ce16a265e053..6f333f5cbeb98 100644 --- a/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi @@ -108,7 +108,7 @@ #size-cells = <2>; ranges; - scp_mem_reserved: scp_mem_region { + scp_mem_reserved: memory@50000000 { compatible = "shared-dma-pool"; reg = <0 0x50000000 0 0x2900000>; no-map; @@ -432,7 +432,7 @@ &pio { aud_pins_default: audiopins { - pins_bus { + pins-bus { pinmux = , , , @@ -454,7 +454,7 @@ }; aud_pins_tdm_out_on: audiotdmouton { - pins_bus { + pins-bus { pinmux = , , , @@ -466,7 +466,7 @@ }; aud_pins_tdm_out_off: audiotdmoutoff { - pins_bus { + pins-bus { pinmux = , , , @@ -480,13 +480,13 @@ }; bt_pins: bt-pins { - pins_bt_en { + pins-bt-en { pinmux = ; output-low; }; }; - ec_ap_int_odl: ec_ap_int_odl { + ec_ap_int_odl: ec-ap-int-odl { pins1 { pinmux = ; input-enable; @@ -494,7 +494,7 @@ }; }; - h1_int_od_l: h1_int_od_l { + h1_int_od_l: h1-int-od-l { pins1 { pinmux = ; input-enable; @@ -502,7 +502,7 @@ }; i2c0_pins: i2c0 { - pins_bus { + pins-bus { pinmux = , ; mediatek,pull-up-adv = <3>; @@ -511,7 +511,7 @@ }; i2c1_pins: i2c1 { - pins_bus { + pins-bus { pinmux = , ; mediatek,pull-up-adv = <3>; @@ -520,7 +520,7 @@ }; i2c2_pins: i2c2 { - pins_bus { + pins-bus { pinmux = , ; bias-disable; @@ -529,7 +529,7 @@ }; i2c3_pins: i2c3 { - pins_bus { + pins-bus { pinmux = , ; mediatek,pull-up-adv = <3>; @@ -538,7 +538,7 @@ }; i2c4_pins: i2c4 { - pins_bus { + pins-bus { pinmux = , ; bias-disable; @@ -547,7 +547,7 @@ }; i2c5_pins: i2c5 { - pins_bus { + pins-bus { pinmux = , ; mediatek,pull-up-adv = <3>; @@ -556,7 +556,7 @@ }; i2c6_pins: i2c6 { - pins_bus { + pins-bus { pinmux = , ; bias-disable; @@ -564,7 +564,7 @@ }; mmc0_pins_default: mmc0-pins-default { - pins_cmd_dat { + pins-cmd-dat { pinmux = , , , @@ -579,13 +579,13 @@ mediatek,pull-up-adv = <01>; }; - pins_clk { + pins-clk { pinmux = ; drive-strength = ; mediatek,pull-down-adv = <10>; }; - pins_rst { + pins-rst { pinmux = ; drive-strength = ; mediatek,pull-down-adv = <01>; @@ -593,7 +593,7 @@ }; mmc0_pins_uhs: mmc0-pins-uhs { - pins_cmd_dat { + pins-cmd-dat { pinmux = , , , @@ -608,19 +608,19 @@ mediatek,pull-up-adv = <01>; }; - pins_clk { + pins-clk { pinmux = ; drive-strength = ; mediatek,pull-down-adv = <10>; }; - pins_ds { + pins-ds { pinmux = ; drive-strength = ; mediatek,pull-down-adv = <10>; }; - pins_rst { + pins-rst { pinmux = ; drive-strength = ; mediatek,pull-up-adv = <01>; @@ -628,7 +628,7 @@ }; mmc1_pins_default: mmc1-pins-default { - pins_cmd_dat { + pins-cmd-dat { pinmux = , , , @@ -638,7 +638,7 @@ mediatek,pull-up-adv = <10>; }; - pins_clk { + pins-clk { pinmux = ; input-enable; mediatek,pull-down-adv = <10>; @@ -646,7 +646,7 @@ }; mmc1_pins_uhs: mmc1-pins-uhs { - pins_cmd_dat { + pins-cmd-dat { pinmux = , , , @@ -657,7 +657,7 @@ mediatek,pull-up-adv = <10>; }; - pins_clk { + pins-clk { pinmux = ; drive-strength = ; mediatek,pull-down-adv = <10>; @@ -665,15 +665,15 @@ }; }; - panel_pins_default: panel_pins_default { - panel_reset { + panel_pins_default: panel-pins-default { + panel-reset { pinmux = ; output-low; bias-pull-up; }; }; - pwm0_pin_default: pwm0_pin_default { + pwm0_pin_default: pwm0-pin-default { pins1 { pinmux = ; output-high; @@ -685,14 +685,14 @@ }; scp_pins: scp { - pins_scp_uart { + pins-scp-uart { pinmux = , ; }; }; spi0_pins: spi0 { - pins_spi{ + pins-spi { pinmux = , , , @@ -702,7 +702,7 @@ }; spi1_pins: spi1 { - pins_spi{ + pins-spi { pinmux = , , , @@ -712,20 +712,20 @@ }; spi2_pins: spi2 { - pins_spi{ + pins-spi { pinmux = , , ; bias-disable; }; - pins_spi_mi { + pins-spi-mi { pinmux = ; mediatek,pull-down-adv = <00>; }; }; spi3_pins: spi3 { - pins_spi{ + pins-spi { pinmux = , , , @@ -735,7 +735,7 @@ }; spi4_pins: spi4 { - pins_spi{ + pins-spi { pinmux = , , , @@ -745,7 +745,7 @@ }; spi5_pins: spi5 { - pins_spi{ + pins-spi { pinmux = , , , @@ -755,63 +755,63 @@ }; uart0_pins_default: uart0-pins-default { - pins_rx { + pins-rx { pinmux = ; input-enable; bias-pull-up; }; - pins_tx { + pins-tx { pinmux = ; }; }; uart1_pins_default: uart1-pins-default { - pins_rx { + pins-rx { pinmux = ; input-enable; bias-pull-up; }; - pins_tx { + pins-tx { pinmux = ; }; - pins_rts { + pins-rts { pinmux = ; output-enable; }; - pins_cts { + pins-cts { pinmux = ; input-enable; }; }; uart1_pins_sleep: uart1-pins-sleep { - pins_rx { + pins-rx { pinmux = ; input-enable; bias-pull-up; }; - pins_tx { + pins-tx { pinmux = ; }; - pins_rts { + pins-rts { pinmux = ; output-enable; }; - pins_cts { + pins-cts { pinmux = ; input-enable; }; }; wifi_pins_pwrseq: wifi-pins-pwrseq { - pins_wifi_enable { + pins-wifi-enable { pinmux = ; output-low; }; }; wifi_pins_wakeup: wifi-pins-wakeup { - pins_wifi_wakeup { + pins-wifi-wakeup { pinmux = ; input-enable; }; diff --git a/arch/arm64/boot/dts/mediatek/mt8183-pumpkin.dts b/arch/arm64/boot/dts/mediatek/mt8183-pumpkin.dts index 526bcae7a3f8f..b5784a60c315d 100644 --- a/arch/arm64/boot/dts/mediatek/mt8183-pumpkin.dts +++ b/arch/arm64/boot/dts/mediatek/mt8183-pumpkin.dts @@ -193,7 +193,7 @@ &pio { i2c_pins_0: i2c0 { - pins_i2c{ + pins_i2c { pinmux = , ; mediatek,pull-up-adv = <3>; @@ -202,7 +202,7 @@ }; i2c_pins_1: i2c1 { - pins_i2c{ + pins_i2c { pinmux = , ; mediatek,pull-up-adv = <3>; @@ -211,7 +211,7 @@ }; i2c_pins_2: i2c2 { - pins_i2c{ + pins_i2c { pinmux = , ; mediatek,pull-up-adv = <3>; @@ -220,7 +220,7 @@ }; i2c_pins_3: i2c3 { - pins_i2c{ + pins_i2c { pinmux = , ; mediatek,pull-up-adv = <3>; @@ -229,7 +229,7 @@ }; i2c_pins_4: i2c4 { - pins_i2c{ + pins_i2c { pinmux = , ; mediatek,pull-up-adv = <3>; @@ -238,7 +238,7 @@ }; i2c_pins_5: i2c5 { - pins_i2c{ + pins_i2c { pinmux = , ; mediatek,pull-up-adv = <3>; diff --git a/arch/arm64/boot/dts/mediatek/mt8183.dtsi b/arch/arm64/boot/dts/mediatek/mt8183.dtsi index 5169779d01dfb..976dc968b3ca1 100644 --- a/arch/arm64/boot/dts/mediatek/mt8183.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8183.dtsi @@ -1210,127 +1210,6 @@ nvmem-cell-names = "calibration-data"; }; - thermal_zones: thermal-zones { - cpu_thermal: cpu-thermal { - polling-delay-passive = <100>; - polling-delay = <500>; - thermal-sensors = <&thermal 0>; - sustainable-power = <5000>; - - trips { - threshold: trip-point0 { - temperature = <68000>; - hysteresis = <2000>; - type = "passive"; - }; - - target: trip-point1 { - temperature = <80000>; - hysteresis = <2000>; - type = "passive"; - }; - - cpu_crit: cpu-crit { - temperature = <115000>; - hysteresis = <2000>; - type = "critical"; - }; - }; - - cooling-maps { - map0 { - trip = <&target>; - cooling-device = <&cpu0 - THERMAL_NO_LIMIT - THERMAL_NO_LIMIT>, - <&cpu1 - THERMAL_NO_LIMIT - THERMAL_NO_LIMIT>, - <&cpu2 - THERMAL_NO_LIMIT - THERMAL_NO_LIMIT>, - <&cpu3 - THERMAL_NO_LIMIT - THERMAL_NO_LIMIT>; - contribution = <3072>; - }; - map1 { - trip = <&target>; - cooling-device = <&cpu4 - THERMAL_NO_LIMIT - THERMAL_NO_LIMIT>, - <&cpu5 - THERMAL_NO_LIMIT - THERMAL_NO_LIMIT>, - <&cpu6 - THERMAL_NO_LIMIT - THERMAL_NO_LIMIT>, - <&cpu7 - THERMAL_NO_LIMIT - THERMAL_NO_LIMIT>; - contribution = <1024>; - }; - }; - }; - - /* The tzts1 ~ tzts6 don't need to polling */ - /* The tzts1 ~ tzts6 don't need to thermal throttle */ - - tzts1: tzts1 { - polling-delay-passive = <0>; - polling-delay = <0>; - thermal-sensors = <&thermal 1>; - sustainable-power = <5000>; - trips {}; - cooling-maps {}; - }; - - tzts2: tzts2 { - polling-delay-passive = <0>; - polling-delay = <0>; - thermal-sensors = <&thermal 2>; - sustainable-power = <5000>; - trips {}; - cooling-maps {}; - }; - - tzts3: tzts3 { - polling-delay-passive = <0>; - polling-delay = <0>; - thermal-sensors = <&thermal 3>; - sustainable-power = <5000>; - trips {}; - cooling-maps {}; - }; - - tzts4: tzts4 { - polling-delay-passive = <0>; - polling-delay = <0>; - thermal-sensors = <&thermal 4>; - sustainable-power = <5000>; - trips {}; - cooling-maps {}; - }; - - tzts5: tzts5 { - polling-delay-passive = <0>; - polling-delay = <0>; - thermal-sensors = <&thermal 5>; - sustainable-power = <5000>; - trips {}; - cooling-maps {}; - }; - - tztsABB: tztsABB { - polling-delay-passive = <0>; - polling-delay = <0>; - thermal-sensors = <&thermal 6>; - sustainable-power = <5000>; - trips {}; - cooling-maps {}; - }; - }; - pwm0: pwm@1100e000 { compatible = "mediatek,mt8183-disp-pwm"; reg = <0 0x1100e000 0 0x1000>; @@ -2105,4 +1984,125 @@ power-domains = <&spm MT8183_POWER_DOMAIN_CAM>; }; }; + + thermal_zones: thermal-zones { + cpu_thermal: cpu-thermal { + polling-delay-passive = <100>; + polling-delay = <500>; + thermal-sensors = <&thermal 0>; + sustainable-power = <5000>; + + trips { + threshold: trip-point0 { + temperature = <68000>; + hysteresis = <2000>; + type = "passive"; + }; + + target: trip-point1 { + temperature = <80000>; + hysteresis = <2000>; + type = "passive"; + }; + + cpu_crit: cpu-crit { + temperature = <115000>; + hysteresis = <2000>; + type = "critical"; + }; + }; + + cooling-maps { + map0 { + trip = <&target>; + cooling-device = <&cpu0 + THERMAL_NO_LIMIT + THERMAL_NO_LIMIT>, + <&cpu1 + THERMAL_NO_LIMIT + THERMAL_NO_LIMIT>, + <&cpu2 + THERMAL_NO_LIMIT + THERMAL_NO_LIMIT>, + <&cpu3 + THERMAL_NO_LIMIT + THERMAL_NO_LIMIT>; + contribution = <3072>; + }; + map1 { + trip = <&target>; + cooling-device = <&cpu4 + THERMAL_NO_LIMIT + THERMAL_NO_LIMIT>, + <&cpu5 + THERMAL_NO_LIMIT + THERMAL_NO_LIMIT>, + <&cpu6 + THERMAL_NO_LIMIT + THERMAL_NO_LIMIT>, + <&cpu7 + THERMAL_NO_LIMIT + THERMAL_NO_LIMIT>; + contribution = <1024>; + }; + }; + }; + + /* The tzts1 ~ tzts6 don't need to polling */ + /* The tzts1 ~ tzts6 don't need to thermal throttle */ + + tzts1: tzts1 { + polling-delay-passive = <0>; + polling-delay = <0>; + thermal-sensors = <&thermal 1>; + sustainable-power = <5000>; + trips {}; + cooling-maps {}; + }; + + tzts2: tzts2 { + polling-delay-passive = <0>; + polling-delay = <0>; + thermal-sensors = <&thermal 2>; + sustainable-power = <5000>; + trips {}; + cooling-maps {}; + }; + + tzts3: tzts3 { + polling-delay-passive = <0>; + polling-delay = <0>; + thermal-sensors = <&thermal 3>; + sustainable-power = <5000>; + trips {}; + cooling-maps {}; + }; + + tzts4: tzts4 { + polling-delay-passive = <0>; + polling-delay = <0>; + thermal-sensors = <&thermal 4>; + sustainable-power = <5000>; + trips {}; + cooling-maps {}; + }; + + tzts5: tzts5 { + polling-delay-passive = <0>; + polling-delay = <0>; + thermal-sensors = <&thermal 5>; + sustainable-power = <5000>; + trips {}; + cooling-maps {}; + }; + + tztsABB: tztsABB { + polling-delay-passive = <0>; + polling-delay = <0>; + thermal-sensors = <&thermal 6>; + sustainable-power = <5000>; + trips {}; + cooling-maps {}; + }; + }; }; diff --git a/arch/arm64/boot/dts/mediatek/mt8186.dtsi b/arch/arm64/boot/dts/mediatek/mt8186.dtsi index f04ae70c470aa..df0c04f2ba1da 100644 --- a/arch/arm64/boot/dts/mediatek/mt8186.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8186.dtsi @@ -924,7 +924,8 @@ reg = ; clocks = <&topckgen CLK_TOP_SENINF>, <&topckgen CLK_TOP_SENINF1>; - clock-names = "csirx_top0", "csirx_top1"; + clock-names = "subsys-csirx-top0", + "subsys-csirx-top1"; #power-domain-cells = <0>; }; @@ -942,7 +943,8 @@ reg = ; clocks = <&topckgen CLK_TOP_AUDIODSP>, <&topckgen CLK_TOP_ADSP_BUS>; - clock-names = "audioadsp", "adsp_bus"; + clock-names = "audioadsp", + "subsys-adsp-bus"; #address-cells = <1>; #size-cells = <0>; #power-domain-cells = <1>; @@ -975,8 +977,11 @@ <&mmsys CLK_MM_SMI_COMMON>, <&mmsys CLK_MM_SMI_GALS>, <&mmsys CLK_MM_SMI_IOMMU>; - clock-names = "disp", "mdp", "smi_infra", "smi_common", - "smi_gals", "smi_iommu"; + clock-names = "disp", "mdp", + "subsys-smi-infra", + "subsys-smi-common", + "subsys-smi-gals", + "subsys-smi-iommu"; mediatek,infracfg = <&infracfg_ao>; #address-cells = <1>; #size-cells = <0>; @@ -993,15 +998,17 @@ power-domain@MT8186_POWER_DOMAIN_CAM { reg = ; - clocks = <&topckgen CLK_TOP_CAM>, - <&topckgen CLK_TOP_SENINF>, + clocks = <&topckgen CLK_TOP_SENINF>, <&topckgen CLK_TOP_SENINF1>, <&topckgen CLK_TOP_SENINF2>, <&topckgen CLK_TOP_SENINF3>, + <&camsys CLK_CAM2MM_GALS>, <&topckgen CLK_TOP_CAMTM>, - <&camsys CLK_CAM2MM_GALS>; - clock-names = "cam-top", "cam0", "cam1", "cam2", - "cam3", "cam-tm", "gals"; + <&topckgen CLK_TOP_CAM>; + clock-names = "cam0", "cam1", "cam2", + "cam3", "gals", + "subsys-cam-tm", + "subsys-cam-top"; mediatek,infracfg = <&infracfg_ao>; #address-cells = <1>; #size-cells = <0>; @@ -1020,9 +1027,9 @@ power-domain@MT8186_POWER_DOMAIN_IMG { reg = ; - clocks = <&topckgen CLK_TOP_IMG1>, - <&imgsys1 CLK_IMG1_GALS_IMG1>; - clock-names = "img-top", "gals"; + clocks = <&imgsys1 CLK_IMG1_GALS_IMG1>, + <&topckgen CLK_TOP_IMG1>; + clock-names = "gals", "subsys-img-top"; mediatek,infracfg = <&infracfg_ao>; #address-cells = <1>; #size-cells = <0>; @@ -1041,8 +1048,11 @@ <&ipesys CLK_IPE_LARB20>, <&ipesys CLK_IPE_SMI_SUBCOM>, <&ipesys CLK_IPE_GALS_IPE>; - clock-names = "ipe-top", "ipe-larb0", "ipe-larb1", - "ipe-smi", "ipe-gals"; + clock-names = "subsys-ipe-top", + "subsys-ipe-larb0", + "subsys-ipe-larb1", + "subsys-ipe-smi", + "subsys-ipe-gals"; mediatek,infracfg = <&infracfg_ao>; #power-domain-cells = <0>; }; @@ -1061,7 +1071,9 @@ clocks = <&topckgen CLK_TOP_WPE>, <&wpesys CLK_WPE_SMI_LARB8_CK_EN>, <&wpesys CLK_WPE_SMI_LARB8_PCLK_EN>; - clock-names = "wpe0", "larb-ck", "larb-pclk"; + clock-names = "wpe0", + "subsys-larb-ck", + "subsys-larb-pclk"; mediatek,infracfg = <&infracfg_ao>; #power-domain-cells = <0>; }; @@ -1656,7 +1668,7 @@ #address-cells = <1>; #size-cells = <1>; - gpu_speedbin: gpu-speed-bin@59c { + gpu_speedbin: gpu-speedbin@59c { reg = <0x59c 0x4>; bits = <0 3>; }; diff --git a/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi b/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi index 37a3e9de90ff7..3f508e5c18434 100644 --- a/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi @@ -362,7 +362,7 @@ pinctrl-0 = <&i2c7_pins>; pmic@34 { - #interrupt-cells = <1>; + #interrupt-cells = <2>; compatible = "mediatek,mt6360"; reg = <0x34>; interrupt-controller; diff --git a/arch/arm64/boot/dts/mediatek/mt8195.dtsi b/arch/arm64/boot/dts/mediatek/mt8195.dtsi index 54c674c45b49a..e0ac2e9f5b720 100644 --- a/arch/arm64/boot/dts/mediatek/mt8195.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8195.dtsi @@ -627,6 +627,8 @@ power-domain@MT8195_POWER_DOMAIN_VENC_CORE1 { reg = ; + clocks = <&vencsys_core1 CLK_VENC_CORE1_LARB>; + clock-names = "venc1-larb"; mediatek,infracfg = <&infracfg_ao>; #power-domain-cells = <0>; }; @@ -689,6 +691,8 @@ power-domain@MT8195_POWER_DOMAIN_VENC { reg = ; + clocks = <&vencsys CLK_VENC_LARB>; + clock-names = "venc0-larb"; mediatek,infracfg = <&infracfg_ao>; #power-domain-cells = <0>; }; @@ -2665,7 +2669,7 @@ reg = <0 0x1b010000 0 0x1000>; mediatek,larb-id = <20>; mediatek,smi = <&smi_common_vpp>; - clocks = <&vencsys_core1 CLK_VENC_CORE1_LARB>, + clocks = <&vencsys_core1 CLK_VENC_CORE1_VENC>, <&vencsys_core1 CLK_VENC_CORE1_GALS>, <&vppsys0 CLK_VPP0_GALS_VDO0_VDO1_VENCSYS_CORE1>; clock-names = "apb", "smi", "gals"; diff --git a/arch/arm64/boot/dts/qcom/ipq5332.dtsi b/arch/arm64/boot/dts/qcom/ipq5332.dtsi index 8bfc2db44624a..e40c55adff23d 100644 --- a/arch/arm64/boot/dts/qcom/ipq5332.dtsi +++ b/arch/arm64/boot/dts/qcom/ipq5332.dtsi @@ -135,7 +135,7 @@ reg = <0x0 0x4a800000 0x0 0x100000>; no-map; - hwlocks = <&tcsr_mutex 0>; + hwlocks = <&tcsr_mutex 3>; }; }; diff --git a/arch/arm64/boot/dts/qcom/ipq6018.dtsi b/arch/arm64/boot/dts/qcom/ipq6018.dtsi index 47b8b1d6730ac..264845cecf925 100644 --- a/arch/arm64/boot/dts/qcom/ipq6018.dtsi +++ b/arch/arm64/boot/dts/qcom/ipq6018.dtsi @@ -211,7 +211,7 @@ smem { compatible = "qcom,smem"; memory-region = <&smem_region>; - hwlocks = <&tcsr_mutex 0>; + hwlocks = <&tcsr_mutex 3>; }; soc: soc@0 { @@ -393,7 +393,7 @@ tcsr_mutex: hwlock@1905000 { compatible = "qcom,ipq6018-tcsr-mutex", "qcom,tcsr-mutex"; - reg = <0x0 0x01905000 0x0 0x1000>; + reg = <0x0 0x01905000 0x0 0x20000>; #hwlock-cells = <1>; }; diff --git a/arch/arm64/boot/dts/qcom/ipq8074.dtsi b/arch/arm64/boot/dts/qcom/ipq8074.dtsi index 00ed71936b472..92fd924bbdbe5 100644 --- a/arch/arm64/boot/dts/qcom/ipq8074.dtsi +++ b/arch/arm64/boot/dts/qcom/ipq8074.dtsi @@ -101,7 +101,7 @@ reg = <0x0 0x4ab00000 0x0 0x100000>; no-map; - hwlocks = <&tcsr_mutex 0>; + hwlocks = <&tcsr_mutex 3>; }; memory@4ac00000 { diff --git a/arch/arm64/boot/dts/qcom/ipq9574.dtsi b/arch/arm64/boot/dts/qcom/ipq9574.dtsi index 51aba071c1eb3..8a72ad4afd032 100644 --- a/arch/arm64/boot/dts/qcom/ipq9574.dtsi +++ b/arch/arm64/boot/dts/qcom/ipq9574.dtsi @@ -195,7 +195,7 @@ smem@4aa00000 { compatible = "qcom,smem"; reg = <0x0 0x4aa00000 0x0 0x100000>; - hwlocks = <&tcsr_mutex 0>; + hwlocks = <&tcsr_mutex 3>; no-map; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi index e729e7a22b23a..cc8209795c3e5 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi @@ -668,7 +668,7 @@ vdec: video-codec@ff360000 { compatible = "rockchip,rk3328-vdec", "rockchip,rk3399-vdec"; - reg = <0x0 0xff360000 0x0 0x400>; + reg = <0x0 0xff360000 0x0 0x480>; interrupts = ; clocks = <&cru ACLK_RKVDEC>, <&cru HCLK_RKVDEC>, <&cru SCLK_VDEC_CABAC>, <&cru SCLK_VDEC_CORE>; diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi index 5bc2d4faeea6d..4a3d0af5ecfe2 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi @@ -1109,7 +1109,9 @@ power-domain@RK3399_PD_VDU { reg = ; clocks = <&cru ACLK_VDU>, - <&cru HCLK_VDU>; + <&cru HCLK_VDU>, + <&cru SCLK_VDU_CA>, + <&cru SCLK_VDU_CORE>; pm_qos = <&qos_video_m1_r>, <&qos_video_m1_w>; #power-domain-cells = <0>; @@ -1385,7 +1387,7 @@ vdec: video-codec@ff660000 { compatible = "rockchip,rk3399-vdec"; - reg = <0x0 0xff660000 0x0 0x400>; + reg = <0x0 0xff660000 0x0 0x480>; interrupts = ; clocks = <&cru ACLK_VDU>, <&cru HCLK_VDU>, <&cru SCLK_VDU_CA>, <&cru SCLK_VDU_CORE>; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-nanopc-t6.dts b/arch/arm64/boot/dts/rockchip/rk3588-nanopc-t6.dts index 0bd80e5157544..97af4f9128285 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-nanopc-t6.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588-nanopc-t6.dts @@ -137,6 +137,18 @@ vin-supply = <&vcc5v0_sys>; }; + vcc3v3_pcie2x1l0: vcc3v3-pcie2x1l0-regulator { + compatible = "regulator-fixed"; + enable-active-high; + gpio = <&gpio4 RK_PC2 GPIO_ACTIVE_HIGH>; + pinctrl-names = "default"; + pinctrl-0 = <&pcie_m2_1_pwren>; + regulator-name = "vcc3v3_pcie2x1l0"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + vin-supply = <&vcc5v0_sys>; + }; + vcc3v3_pcie30: vcc3v3-pcie30-regulator { compatible = "regulator-fixed"; enable-active-high; @@ -421,6 +433,14 @@ status = "okay"; }; +&pcie2x1l1 { + reset-gpios = <&gpio4 RK_PA2 GPIO_ACTIVE_HIGH>; + vpcie3v3-supply = <&vcc3v3_pcie2x1l0>; + pinctrl-names = "default"; + pinctrl-0 = <&pcie2_1_rst>; + status = "okay"; +}; + &pcie2x1l2 { reset-gpios = <&gpio4 RK_PA4 GPIO_ACTIVE_HIGH>; vpcie3v3-supply = <&vcc_3v3_pcie20>; @@ -467,6 +487,10 @@ rockchip,pins = <4 RK_PB3 RK_FUNC_GPIO &pcfg_pull_none>; }; + pcie2_1_rst: pcie2-1-rst { + rockchip,pins = <4 RK_PA2 RK_FUNC_GPIO &pcfg_pull_none>; + }; + pcie2_2_rst: pcie2-2-rst { rockchip,pins = <4 RK_PA4 RK_FUNC_GPIO &pcfg_pull_none>; }; @@ -474,6 +498,10 @@ pcie_m2_0_pwren: pcie-m20-pwren { rockchip,pins = <2 RK_PC5 RK_FUNC_GPIO &pcfg_pull_none>; }; + + pcie_m2_1_pwren: pcie-m21-pwren { + rockchip,pins = <4 RK_PC2 RK_FUNC_GPIO &pcfg_pull_none>; + }; }; usb { diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-pinctrl.dtsi b/arch/arm64/boot/dts/rockchip/rk3588s-pinctrl.dtsi index 48181671eacb0..0933652bafc30 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588s-pinctrl.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3588s-pinctrl.dtsi @@ -369,7 +369,7 @@ emmc_data_strobe: emmc-data-strobe { rockchip,pins = /* emmc_data_strobe */ - <2 RK_PA2 1 &pcfg_pull_none>; + <2 RK_PA2 1 &pcfg_pull_down>; }; }; diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 7f7d9b1df4e5a..07bdf5dd8ebef 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -826,6 +826,12 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) pte = set_pte_bit(pte, __pgprot(PTE_DIRTY)); pte_val(pte) = (pte_val(pte) & ~mask) | (pgprot_val(newprot) & mask); + /* + * If we end up clearing hw dirtiness for a sw-dirty PTE, set hardware + * dirtiness again. + */ + if (pte_sw_dirty(pte)) + pte = pte_mkdirty(pte); return pte; } diff --git a/arch/arm64/include/asm/setup.h b/arch/arm64/include/asm/setup.h index f4af547ef54ca..2e4d7da74fb87 100644 --- a/arch/arm64/include/asm/setup.h +++ b/arch/arm64/include/asm/setup.h @@ -21,9 +21,22 @@ static inline bool arch_parse_debug_rodata(char *arg) extern bool rodata_enabled; extern bool rodata_full; - if (arg && !strcmp(arg, "full")) { + if (!arg) + return false; + + if (!strcmp(arg, "full")) { + rodata_enabled = rodata_full = true; + return true; + } + + if (!strcmp(arg, "off")) { + rodata_enabled = rodata_full = false; + return true; + } + + if (!strcmp(arg, "on")) { rodata_enabled = true; - rodata_full = true; + rodata_full = false; return true; } diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c index bd69a4e7cd605..79200f21e1239 100644 --- a/arch/arm64/kernel/module-plts.c +++ b/arch/arm64/kernel/module-plts.c @@ -167,9 +167,6 @@ static unsigned int count_plts(Elf64_Sym *syms, Elf64_Rela *rela, int num, switch (ELF64_R_TYPE(rela[i].r_info)) { case R_AARCH64_JUMP26: case R_AARCH64_CALL26: - if (!IS_ENABLED(CONFIG_RANDOMIZE_BASE)) - break; - /* * We only have to consider branch targets that resolve * to symbols that are defined in a different section. @@ -269,9 +266,6 @@ static int partition_branch_plt_relas(Elf64_Sym *syms, Elf64_Rela *rela, { int i = 0, j = numrels - 1; - if (!IS_ENABLED(CONFIG_RANDOMIZE_BASE)) - return 0; - while (i < j) { if (branch_rela_needs_plt(syms, &rela[i], dstidx)) i++; diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 4866b3f7b4ea3..685cc436146a5 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -407,7 +407,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_cache); kvm_timer_vcpu_terminate(vcpu); kvm_pmu_vcpu_destroy(vcpu); - + kvm_vgic_vcpu_destroy(vcpu); kvm_arm_vcpu_destroy(vcpu); } diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index c8c3cb8127832..e949e1d0fd9f7 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -368,7 +368,7 @@ static void kvm_vgic_dist_destroy(struct kvm *kvm) vgic_v4_teardown(kvm); } -void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) +static void __kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; @@ -379,29 +379,39 @@ void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) vgic_flush_pending_lpis(vcpu); INIT_LIST_HEAD(&vgic_cpu->ap_list_head); - vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF; + if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) { + vgic_unregister_redist_iodev(vcpu); + vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF; + } } -static void __kvm_vgic_destroy(struct kvm *kvm) +void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + + mutex_lock(&kvm->slots_lock); + __kvm_vgic_vcpu_destroy(vcpu); + mutex_unlock(&kvm->slots_lock); +} + +void kvm_vgic_destroy(struct kvm *kvm) { struct kvm_vcpu *vcpu; unsigned long i; - lockdep_assert_held(&kvm->arch.config_lock); + mutex_lock(&kvm->slots_lock); vgic_debug_destroy(kvm); kvm_for_each_vcpu(i, vcpu, kvm) - kvm_vgic_vcpu_destroy(vcpu); + __kvm_vgic_vcpu_destroy(vcpu); + + mutex_lock(&kvm->arch.config_lock); kvm_vgic_dist_destroy(kvm); -} -void kvm_vgic_destroy(struct kvm *kvm) -{ - mutex_lock(&kvm->arch.config_lock); - __kvm_vgic_destroy(kvm); mutex_unlock(&kvm->arch.config_lock); + mutex_unlock(&kvm->slots_lock); } /** @@ -469,25 +479,26 @@ int kvm_vgic_map_resources(struct kvm *kvm) type = VGIC_V3; } - if (ret) { - __kvm_vgic_destroy(kvm); + if (ret) goto out; - } + dist->ready = true; dist_base = dist->vgic_dist_base; mutex_unlock(&kvm->arch.config_lock); ret = vgic_register_dist_iodev(kvm, dist_base, type); - if (ret) { + if (ret) kvm_err("Unable to register VGIC dist MMIO regions\n"); - kvm_vgic_destroy(kvm); - } - mutex_unlock(&kvm->slots_lock); - return ret; + goto out_slots; out: mutex_unlock(&kvm->arch.config_lock); +out_slots: mutex_unlock(&kvm->slots_lock); + + if (ret) + kvm_vgic_destroy(kvm); + return ret; } diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c index 188d2187eede9..871a45d4fc84c 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c +++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c @@ -820,7 +820,7 @@ int vgic_register_redist_iodev(struct kvm_vcpu *vcpu) return ret; } -static void vgic_unregister_redist_iodev(struct kvm_vcpu *vcpu) +void vgic_unregister_redist_iodev(struct kvm_vcpu *vcpu) { struct vgic_io_device *rd_dev = &vcpu->arch.vgic_cpu.rd_iodev; diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h index 0ab09b0d44404..8d134569d0a1f 100644 --- a/arch/arm64/kvm/vgic/vgic.h +++ b/arch/arm64/kvm/vgic/vgic.h @@ -241,6 +241,7 @@ int vgic_v3_lpi_sync_pending_status(struct kvm *kvm, struct vgic_irq *irq); int vgic_v3_save_pending_tables(struct kvm *kvm); int vgic_v3_set_redist_base(struct kvm *kvm, u32 index, u64 addr, u32 count); int vgic_register_redist_iodev(struct kvm_vcpu *vcpu); +void vgic_unregister_redist_iodev(struct kvm_vcpu *vcpu); bool vgic_v3_check_base(struct kvm *kvm); void vgic_v3_load(struct kvm_vcpu *vcpu); diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c index 8e2017ba5f1b1..924843f1f661b 100644 --- a/arch/arm64/mm/pageattr.c +++ b/arch/arm64/mm/pageattr.c @@ -29,8 +29,8 @@ bool can_set_direct_map(void) * * KFENCE pool requires page-granular mapping if initialized late. */ - return (rodata_enabled && rodata_full) || debug_pagealloc_enabled() || - arm64_kfence_can_set_direct_map(); + return rodata_full || debug_pagealloc_enabled() || + arm64_kfence_can_set_direct_map(); } static int change_page_range(pte_t *ptep, unsigned long addr, void *data) @@ -105,8 +105,7 @@ static int change_memory_common(unsigned long addr, int numpages, * If we are manipulating read-only permissions, apply the same * change to the linear mapping of the pages that back this VM area. */ - if (rodata_enabled && - rodata_full && (pgprot_val(set_mask) == PTE_RDONLY || + if (rodata_full && (pgprot_val(set_mask) == PTE_RDONLY || pgprot_val(clear_mask) == PTE_RDONLY)) { for (i = 0; i < area->nr_pages; i++) { __change_memory_common((u64)page_address(area->pages[i]), diff --git a/arch/loongarch/Makefile b/arch/loongarch/Makefile index fb0fada43197e..96747bfec1a10 100644 --- a/arch/loongarch/Makefile +++ b/arch/loongarch/Makefile @@ -142,6 +142,8 @@ vdso_install: all: $(notdir $(KBUILD_IMAGE)) +vmlinuz.efi: vmlinux.efi + vmlinux.elf vmlinux.efi vmlinuz.efi: vmlinux $(Q)$(MAKE) $(build)=$(boot) $(bootvars-y) $(boot)/$@ diff --git a/arch/loongarch/include/asm/asmmacro.h b/arch/loongarch/include/asm/asmmacro.h index c9544f358c339..655db7d7a4279 100644 --- a/arch/loongarch/include/asm/asmmacro.h +++ b/arch/loongarch/include/asm/asmmacro.h @@ -609,8 +609,7 @@ lu32i.d \reg, 0 lu52i.d \reg, \reg, 0 .pushsection ".la_abs", "aw", %progbits - 768: - .dword 768b-766b + .dword 766b .dword \sym .popsection #endif diff --git a/arch/loongarch/include/asm/percpu.h b/arch/loongarch/include/asm/percpu.h index b9f567e660166..ed5da02b1cf6f 100644 --- a/arch/loongarch/include/asm/percpu.h +++ b/arch/loongarch/include/asm/percpu.h @@ -32,7 +32,7 @@ static inline void set_my_cpu_offset(unsigned long off) #define __my_cpu_offset __my_cpu_offset #define PERCPU_OP(op, asm_op, c_op) \ -static inline unsigned long __percpu_##op(void *ptr, \ +static __always_inline unsigned long __percpu_##op(void *ptr, \ unsigned long val, int size) \ { \ unsigned long ret; \ @@ -63,7 +63,7 @@ PERCPU_OP(and, and, &) PERCPU_OP(or, or, |) #undef PERCPU_OP -static inline unsigned long __percpu_read(void *ptr, int size) +static __always_inline unsigned long __percpu_read(void *ptr, int size) { unsigned long ret; @@ -100,7 +100,7 @@ static inline unsigned long __percpu_read(void *ptr, int size) return ret; } -static inline void __percpu_write(void *ptr, unsigned long val, int size) +static __always_inline void __percpu_write(void *ptr, unsigned long val, int size) { switch (size) { case 1: @@ -132,8 +132,8 @@ static inline void __percpu_write(void *ptr, unsigned long val, int size) } } -static inline unsigned long __percpu_xchg(void *ptr, unsigned long val, - int size) +static __always_inline unsigned long __percpu_xchg(void *ptr, unsigned long val, + int size) { switch (size) { case 1: diff --git a/arch/loongarch/include/asm/setup.h b/arch/loongarch/include/asm/setup.h index a0bc159ce8bdc..ee52fb1e99631 100644 --- a/arch/loongarch/include/asm/setup.h +++ b/arch/loongarch/include/asm/setup.h @@ -25,7 +25,7 @@ extern void set_merr_handler(unsigned long offset, void *addr, unsigned long len #ifdef CONFIG_RELOCATABLE struct rela_la_abs { - long offset; + long pc; long symvalue; }; diff --git a/arch/loongarch/kernel/relocate.c b/arch/loongarch/kernel/relocate.c index 6c3eff9af9fb1..1acfa704c8d09 100644 --- a/arch/loongarch/kernel/relocate.c +++ b/arch/loongarch/kernel/relocate.c @@ -52,7 +52,7 @@ static inline void __init relocate_absolute(long random_offset) for (p = begin; (void *)p < end; p++) { long v = p->symvalue; uint32_t lu12iw, ori, lu32id, lu52id; - union loongarch_instruction *insn = (void *)p - p->offset; + union loongarch_instruction *insn = (void *)p->pc; lu12iw = (v >> 12) & 0xfffff; ori = v & 0xfff; @@ -102,6 +102,14 @@ static inline __init unsigned long get_random_boot(void) return hash; } +static int __init nokaslr(char *p) +{ + pr_info("KASLR is disabled.\n"); + + return 0; /* Print a notice and silence the boot warning */ +} +early_param("nokaslr", nokaslr); + static inline __init bool kaslr_disabled(void) { char *str; diff --git a/arch/loongarch/kernel/time.c b/arch/loongarch/kernel/time.c index 3064af94db9c2..e7015f7b70e37 100644 --- a/arch/loongarch/kernel/time.c +++ b/arch/loongarch/kernel/time.c @@ -58,14 +58,16 @@ static int constant_set_state_oneshot(struct clock_event_device *evt) return 0; } -static int constant_set_state_oneshot_stopped(struct clock_event_device *evt) +static int constant_set_state_periodic(struct clock_event_device *evt) { + unsigned long period; unsigned long timer_config; raw_spin_lock(&state_lock); - timer_config = csr_read64(LOONGARCH_CSR_TCFG); - timer_config &= ~CSR_TCFG_EN; + period = const_clock_freq / HZ; + timer_config = period & CSR_TCFG_VAL; + timer_config |= (CSR_TCFG_PERIOD | CSR_TCFG_EN); csr_write64(timer_config, LOONGARCH_CSR_TCFG); raw_spin_unlock(&state_lock); @@ -73,16 +75,14 @@ static int constant_set_state_oneshot_stopped(struct clock_event_device *evt) return 0; } -static int constant_set_state_periodic(struct clock_event_device *evt) +static int constant_set_state_shutdown(struct clock_event_device *evt) { - unsigned long period; unsigned long timer_config; raw_spin_lock(&state_lock); - period = const_clock_freq / HZ; - timer_config = period & CSR_TCFG_VAL; - timer_config |= (CSR_TCFG_PERIOD | CSR_TCFG_EN); + timer_config = csr_read64(LOONGARCH_CSR_TCFG); + timer_config &= ~CSR_TCFG_EN; csr_write64(timer_config, LOONGARCH_CSR_TCFG); raw_spin_unlock(&state_lock); @@ -90,11 +90,6 @@ static int constant_set_state_periodic(struct clock_event_device *evt) return 0; } -static int constant_set_state_shutdown(struct clock_event_device *evt) -{ - return 0; -} - static int constant_timer_next_event(unsigned long delta, struct clock_event_device *evt) { unsigned long timer_config; @@ -161,7 +156,7 @@ int constant_clockevent_init(void) cd->rating = 320; cd->cpumask = cpumask_of(cpu); cd->set_state_oneshot = constant_set_state_oneshot; - cd->set_state_oneshot_stopped = constant_set_state_oneshot_stopped; + cd->set_state_oneshot_stopped = constant_set_state_shutdown; cd->set_state_periodic = constant_set_state_periodic; cd->set_state_shutdown = constant_set_state_shutdown; cd->set_next_event = constant_timer_next_event; diff --git a/arch/loongarch/mm/pgtable.c b/arch/loongarch/mm/pgtable.c index 71d0539e2d0b0..2aae72e638713 100644 --- a/arch/loongarch/mm/pgtable.c +++ b/arch/loongarch/mm/pgtable.c @@ -13,13 +13,13 @@ struct page *dmw_virt_to_page(unsigned long kaddr) { return pfn_to_page(virt_to_pfn(kaddr)); } -EXPORT_SYMBOL_GPL(dmw_virt_to_page); +EXPORT_SYMBOL(dmw_virt_to_page); struct page *tlb_virt_to_page(unsigned long kaddr) { return pfn_to_page(pte_pfn(*virt_to_kpte(kaddr))); } -EXPORT_SYMBOL_GPL(tlb_virt_to_page); +EXPORT_SYMBOL(tlb_virt_to_page); pgd_t *pgd_alloc(struct mm_struct *mm) { diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c index db9342b2d0e66..00915fb3cb82c 100644 --- a/arch/loongarch/net/bpf_jit.c +++ b/arch/loongarch/net/bpf_jit.c @@ -855,8 +855,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext /* function return */ case BPF_JMP | BPF_EXIT: - emit_sext_32(ctx, regmap[BPF_REG_0], true); - if (i == ctx->prog->len - 1) break; @@ -907,14 +905,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext } break; case BPF_DW: - if (is_signed_imm12(off)) { - emit_insn(ctx, ldd, dst, src, off); - } else if (is_signed_imm14(off)) { - emit_insn(ctx, ldptrd, dst, src, off); - } else { - move_imm(ctx, t1, off, is32); - emit_insn(ctx, ldxd, dst, src, t1); - } + move_imm(ctx, t1, off, is32); + emit_insn(ctx, ldxd, dst, src, t1); break; } diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index bc8421859006f..91c3a502156b3 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -482,6 +482,7 @@ config MACH_LOONGSON2EF config MACH_LOONGSON64 bool "Loongson 64-bit family of machines" + select ARCH_DMA_DEFAULT_COHERENT select ARCH_SPARSEMEM_ENABLE select ARCH_MIGHT_HAVE_PC_PARPORT select ARCH_MIGHT_HAVE_PC_SERIO @@ -1273,6 +1274,7 @@ config CPU_LOONGSON64 select CPU_SUPPORTS_MSA select CPU_DIEI_BROKEN if !LOONGSON3_ENHANCEMENT select CPU_MIPSR2_IRQ_VI + select DMA_NONCOHERENT select WEAK_ORDERING select WEAK_REORDERING_BEYOND_LLSC select MIPS_ASID_BITS_VARIABLE diff --git a/arch/mips/include/asm/mach-loongson64/boot_param.h b/arch/mips/include/asm/mach-loongson64/boot_param.h index 035b1a69e2d00..e007edd6b60a7 100644 --- a/arch/mips/include/asm/mach-loongson64/boot_param.h +++ b/arch/mips/include/asm/mach-loongson64/boot_param.h @@ -14,7 +14,11 @@ #define ADAPTER_ROM 8 #define ACPI_TABLE 9 #define SMBIOS_TABLE 10 -#define MAX_MEMORY_TYPE 11 +#define UMA_VIDEO_RAM 11 +#define VUMA_VIDEO_RAM 12 +#define MAX_MEMORY_TYPE 13 + +#define MEM_SIZE_IS_IN_BYTES (1 << 31) #define LOONGSON3_BOOT_MEM_MAP_MAX 128 struct efi_memory_map_loongson { @@ -117,7 +121,8 @@ struct irq_source_routing_table { u64 pci_io_start_addr; u64 pci_io_end_addr; u64 pci_config_addr; - u32 dma_mask_bits; + u16 dma_mask_bits; + u16 dma_noncoherent; } __packed; struct interface_info { diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index 5387ed0a51862..b630604c577f9 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -121,6 +121,19 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) /* Put the stack after the struct pt_regs. */ childksp = (unsigned long) childregs; p->thread.cp0_status = (read_c0_status() & ~(ST0_CU2|ST0_CU1)) | ST0_KERNEL_CUMASK; + + /* + * New tasks lose permission to use the fpu. This accelerates context + * switching for most programs since they don't use the fpu. + */ + clear_tsk_thread_flag(p, TIF_USEDFPU); + clear_tsk_thread_flag(p, TIF_USEDMSA); + clear_tsk_thread_flag(p, TIF_MSA_CTX_LIVE); + +#ifdef CONFIG_MIPS_MT_FPAFF + clear_tsk_thread_flag(p, TIF_FPUBOUND); +#endif /* CONFIG_MIPS_MT_FPAFF */ + if (unlikely(args->fn)) { /* kernel thread */ unsigned long status = p->thread.cp0_status; @@ -149,20 +162,8 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) p->thread.reg29 = (unsigned long) childregs; p->thread.reg31 = (unsigned long) ret_from_fork; - /* - * New tasks lose permission to use the fpu. This accelerates context - * switching for most programs since they don't use the fpu. - */ childregs->cp0_status &= ~(ST0_CU2|ST0_CU1); - clear_tsk_thread_flag(p, TIF_USEDFPU); - clear_tsk_thread_flag(p, TIF_USEDMSA); - clear_tsk_thread_flag(p, TIF_MSA_CTX_LIVE); - -#ifdef CONFIG_MIPS_MT_FPAFF - clear_tsk_thread_flag(p, TIF_FPUBOUND); -#endif /* CONFIG_MIPS_MT_FPAFF */ - #ifdef CONFIG_MIPS_FP_SUPPORT atomic_set(&p->thread.bd_emu_frame, BD_EMUFRAME_NONE); #endif diff --git a/arch/mips/loongson64/env.c b/arch/mips/loongson64/env.c index c961e2999f15a..ef3750a6ffacf 100644 --- a/arch/mips/loongson64/env.c +++ b/arch/mips/loongson64/env.c @@ -13,6 +13,8 @@ * Copyright (C) 2009 Lemote Inc. * Author: Wu Zhangjin, wuzhangjin@gmail.com */ + +#include #include #include #include @@ -147,8 +149,14 @@ void __init prom_lefi_init_env(void) loongson_sysconf.dma_mask_bits = eirq_source->dma_mask_bits; if (loongson_sysconf.dma_mask_bits < 32 || - loongson_sysconf.dma_mask_bits > 64) + loongson_sysconf.dma_mask_bits > 64) { loongson_sysconf.dma_mask_bits = 32; + dma_default_coherent = true; + } else { + dma_default_coherent = !eirq_source->dma_noncoherent; + } + + pr_info("Firmware: Coherent DMA: %s\n", dma_default_coherent ? "on" : "off"); loongson_sysconf.restart_addr = boot_p->reset_system.ResetWarm; loongson_sysconf.poweroff_addr = boot_p->reset_system.Shutdown; diff --git a/arch/mips/loongson64/init.c b/arch/mips/loongson64/init.c index ee8de1735b7c0..f25caa6aa9d30 100644 --- a/arch/mips/loongson64/init.c +++ b/arch/mips/loongson64/init.c @@ -49,8 +49,7 @@ void virtual_early_config(void) void __init szmem(unsigned int node) { u32 i, mem_type; - static unsigned long num_physpages; - u64 node_id, node_psize, start_pfn, end_pfn, mem_start, mem_size; + phys_addr_t node_id, mem_start, mem_size; /* Otherwise come from DTB */ if (loongson_sysconf.fw_interface != LOONGSON_LEFI) @@ -64,30 +63,46 @@ void __init szmem(unsigned int node) mem_type = loongson_memmap->map[i].mem_type; mem_size = loongson_memmap->map[i].mem_size; - mem_start = loongson_memmap->map[i].mem_start; + + /* Memory size comes in MB if MEM_SIZE_IS_IN_BYTES not set */ + if (mem_size & MEM_SIZE_IS_IN_BYTES) + mem_size &= ~MEM_SIZE_IS_IN_BYTES; + else + mem_size = mem_size << 20; + + mem_start = (node_id << 44) | loongson_memmap->map[i].mem_start; switch (mem_type) { case SYSTEM_RAM_LOW: case SYSTEM_RAM_HIGH: - start_pfn = ((node_id << 44) + mem_start) >> PAGE_SHIFT; - node_psize = (mem_size << 20) >> PAGE_SHIFT; - end_pfn = start_pfn + node_psize; - num_physpages += node_psize; - pr_info("Node%d: mem_type:%d, mem_start:0x%llx, mem_size:0x%llx MB\n", - (u32)node_id, mem_type, mem_start, mem_size); - pr_info(" start_pfn:0x%llx, end_pfn:0x%llx, num_physpages:0x%lx\n", - start_pfn, end_pfn, num_physpages); - memblock_add_node(PFN_PHYS(start_pfn), - PFN_PHYS(node_psize), node, + case UMA_VIDEO_RAM: + pr_info("Node %d, mem_type:%d\t[%pa], %pa bytes usable\n", + (u32)node_id, mem_type, &mem_start, &mem_size); + memblock_add_node(mem_start, mem_size, node, MEMBLOCK_NONE); break; case SYSTEM_RAM_RESERVED: - pr_info("Node%d: mem_type:%d, mem_start:0x%llx, mem_size:0x%llx MB\n", - (u32)node_id, mem_type, mem_start, mem_size); - memblock_reserve(((node_id << 44) + mem_start), mem_size << 20); + case VIDEO_ROM: + case ADAPTER_ROM: + case ACPI_TABLE: + case SMBIOS_TABLE: + pr_info("Node %d, mem_type:%d\t[%pa], %pa bytes reserved\n", + (u32)node_id, mem_type, &mem_start, &mem_size); + memblock_reserve(mem_start, mem_size); + break; + /* We should not reserve VUMA_VIDEO_RAM as it overlaps with MMIO */ + case VUMA_VIDEO_RAM: + default: + pr_info("Node %d, mem_type:%d\t[%pa], %pa bytes unhandled\n", + (u32)node_id, mem_type, &mem_start, &mem_size); break; } } + + /* Reserve vgabios if it comes from firmware */ + if (loongson_sysconf.vgabios_addr) + memblock_reserve(virt_to_phys((void *)loongson_sysconf.vgabios_addr), + SZ_256K); } #ifndef CONFIG_NUMA diff --git a/arch/mips/mm/cache.c b/arch/mips/mm/cache.c index 02042100e2671..7f830634dbe7d 100644 --- a/arch/mips/mm/cache.c +++ b/arch/mips/mm/cache.c @@ -117,7 +117,7 @@ void __flush_dcache_pages(struct page *page, unsigned int nr) * get faulted into the tlb (and thus flushed) anyways. */ for (i = 0; i < nr; i++) { - addr = (unsigned long)kmap_local_page(page + i); + addr = (unsigned long)kmap_local_page(nth_page(page, i)); flush_data_cache_page(addr); kunmap_local((void *)addr); } diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index a15ab147af2e0..8c45b98dfe0e4 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -113,9 +113,12 @@ config ARCH_HAS_ILOG2_U64 default n config GENERIC_BUG - bool - default y + def_bool y depends on BUG + select GENERIC_BUG_RELATIVE_POINTERS if 64BIT + +config GENERIC_BUG_RELATIVE_POINTERS + bool config GENERIC_HWEIGHT bool @@ -138,11 +141,11 @@ config ARCH_MMAP_RND_COMPAT_BITS_MIN default 8 config ARCH_MMAP_RND_BITS_MAX - default 24 if 64BIT - default 17 + default 18 if 64BIT + default 13 config ARCH_MMAP_RND_COMPAT_BITS_MAX - default 17 + default 13 # unless you want to implement ACPI on PA-RISC ... ;-) config PM diff --git a/arch/parisc/include/asm/alternative.h b/arch/parisc/include/asm/alternative.h index 1ed45fd085d3b..1eb488f25b838 100644 --- a/arch/parisc/include/asm/alternative.h +++ b/arch/parisc/include/asm/alternative.h @@ -34,7 +34,8 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end, /* Alternative SMP implementation. */ #define ALTERNATIVE(cond, replacement) "!0:" \ - ".section .altinstructions, \"aw\" !" \ + ".section .altinstructions, \"a\" !" \ + ".align 4 !" \ ".word (0b-4-.) !" \ ".hword 1, " __stringify(cond) " !" \ ".word " __stringify(replacement) " !" \ @@ -44,7 +45,8 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end, /* to replace one single instructions by a new instruction */ #define ALTERNATIVE(from, to, cond, replacement)\ - .section .altinstructions, "aw" ! \ + .section .altinstructions, "a" ! \ + .align 4 ! \ .word (from - .) ! \ .hword (to - from)/4, cond ! \ .word replacement ! \ @@ -52,7 +54,8 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end, /* to replace multiple instructions by new code */ #define ALTERNATIVE_CODE(from, num_instructions, cond, new_instr_ptr)\ - .section .altinstructions, "aw" ! \ + .section .altinstructions, "a" ! \ + .align 4 ! \ .word (from - .) ! \ .hword -num_instructions, cond ! \ .word (new_instr_ptr - .) ! \ diff --git a/arch/parisc/include/asm/assembly.h b/arch/parisc/include/asm/assembly.h index 75677b526b2bb..74d17d7e759da 100644 --- a/arch/parisc/include/asm/assembly.h +++ b/arch/parisc/include/asm/assembly.h @@ -574,6 +574,7 @@ */ #define ASM_EXCEPTIONTABLE_ENTRY(fault_addr, except_addr) \ .section __ex_table,"aw" ! \ + .align 4 ! \ .word (fault_addr - .), (except_addr - .) ! \ .previous diff --git a/arch/parisc/include/asm/bug.h b/arch/parisc/include/asm/bug.h index 4b6d60b941247..833555f74ffa7 100644 --- a/arch/parisc/include/asm/bug.h +++ b/arch/parisc/include/asm/bug.h @@ -17,24 +17,27 @@ #define PARISC_BUG_BREAK_ASM "break 0x1f, 0x1fff" #define PARISC_BUG_BREAK_INSN 0x03ffe01f /* PARISC_BUG_BREAK_ASM */ -#if defined(CONFIG_64BIT) -#define ASM_WORD_INSN ".dword\t" +#ifdef CONFIG_GENERIC_BUG_RELATIVE_POINTERS +# define __BUG_REL(val) ".word " __stringify(val) " - ." #else -#define ASM_WORD_INSN ".word\t" +# define __BUG_REL(val) ".word " __stringify(val) #endif + #ifdef CONFIG_DEBUG_BUGVERBOSE #define BUG() \ do { \ asm volatile("\n" \ "1:\t" PARISC_BUG_BREAK_ASM "\n" \ - "\t.pushsection __bug_table,\"aw\"\n" \ - "2:\t" ASM_WORD_INSN "1b, %c0\n" \ - "\t.short %c1, %c2\n" \ - "\t.org 2b+%c3\n" \ + "\t.pushsection __bug_table,\"a\"\n" \ + "\t.align 4\n" \ + "2:\t" __BUG_REL(1b) "\n" \ + "\t" __BUG_REL(%c0) "\n" \ + "\t.short %1, %2\n" \ + "\t.blockz %3-2*4-2*2\n" \ "\t.popsection" \ : : "i" (__FILE__), "i" (__LINE__), \ - "i" (0), "i" (sizeof(struct bug_entry)) ); \ + "i" (0), "i" (sizeof(struct bug_entry)) ); \ unreachable(); \ } while(0) @@ -51,10 +54,12 @@ do { \ asm volatile("\n" \ "1:\t" PARISC_BUG_BREAK_ASM "\n" \ - "\t.pushsection __bug_table,\"aw\"\n" \ - "2:\t" ASM_WORD_INSN "1b, %c0\n" \ - "\t.short %c1, %c2\n" \ - "\t.org 2b+%c3\n" \ + "\t.pushsection __bug_table,\"a\"\n" \ + "\t.align 4\n" \ + "2:\t" __BUG_REL(1b) "\n" \ + "\t" __BUG_REL(%c0) "\n" \ + "\t.short %1, %2\n" \ + "\t.blockz %3-2*4-2*2\n" \ "\t.popsection" \ : : "i" (__FILE__), "i" (__LINE__), \ "i" (BUGFLAG_WARNING|(flags)), \ @@ -65,10 +70,11 @@ do { \ asm volatile("\n" \ "1:\t" PARISC_BUG_BREAK_ASM "\n" \ - "\t.pushsection __bug_table,\"aw\"\n" \ - "2:\t" ASM_WORD_INSN "1b\n" \ - "\t.short %c0\n" \ - "\t.org 2b+%c1\n" \ + "\t.pushsection __bug_table,\"a\"\n" \ + "\t.align 4\n" \ + "2:\t" __BUG_REL(1b) "\n" \ + "\t.short %0\n" \ + "\t.blockz %1-4-2\n" \ "\t.popsection" \ : : "i" (BUGFLAG_WARNING|(flags)), \ "i" (sizeof(struct bug_entry)) ); \ diff --git a/arch/parisc/include/asm/elf.h b/arch/parisc/include/asm/elf.h index 140eaa97bf215..2d73d3c3cd37f 100644 --- a/arch/parisc/include/asm/elf.h +++ b/arch/parisc/include/asm/elf.h @@ -349,15 +349,7 @@ struct pt_regs; /* forward declaration... */ #define ELF_HWCAP 0 -/* Masks for stack and mmap randomization */ -#define BRK_RND_MASK (is_32bit_task() ? 0x07ffUL : 0x3ffffUL) -#define MMAP_RND_MASK (is_32bit_task() ? 0x1fffUL : 0x3ffffUL) -#define STACK_RND_MASK MMAP_RND_MASK - -struct mm_struct; -extern unsigned long arch_randomize_brk(struct mm_struct *); -#define arch_randomize_brk arch_randomize_brk - +#define STACK_RND_MASK 0x7ff /* 8MB of VA */ #define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1 struct linux_binprm; diff --git a/arch/parisc/include/asm/jump_label.h b/arch/parisc/include/asm/jump_label.h index af2a598bc0f81..94428798b6aa6 100644 --- a/arch/parisc/include/asm/jump_label.h +++ b/arch/parisc/include/asm/jump_label.h @@ -15,10 +15,12 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool bran asm_volatile_goto("1:\n\t" "nop\n\t" ".pushsection __jump_table, \"aw\"\n\t" + ".align %1\n\t" ".word 1b - ., %l[l_yes] - .\n\t" __stringify(ASM_ULONG_INSN) " %c0 - .\n\t" ".popsection\n\t" - : : "i" (&((char *)key)[branch]) : : l_yes); + : : "i" (&((char *)key)[branch]), "i" (sizeof(long)) + : : l_yes); return false; l_yes: @@ -30,10 +32,12 @@ static __always_inline bool arch_static_branch_jump(struct static_key *key, bool asm_volatile_goto("1:\n\t" "b,n %l[l_yes]\n\t" ".pushsection __jump_table, \"aw\"\n\t" + ".align %1\n\t" ".word 1b - ., %l[l_yes] - .\n\t" __stringify(ASM_ULONG_INSN) " %c0 - .\n\t" ".popsection\n\t" - : : "i" (&((char *)key)[branch]) : : l_yes); + : : "i" (&((char *)key)[branch]), "i" (sizeof(long)) + : : l_yes); return false; l_yes: diff --git a/arch/parisc/include/asm/ldcw.h b/arch/parisc/include/asm/ldcw.h index ee9e071859b2f..47ebc4c91eaff 100644 --- a/arch/parisc/include/asm/ldcw.h +++ b/arch/parisc/include/asm/ldcw.h @@ -55,7 +55,7 @@ }) #ifdef CONFIG_SMP -# define __lock_aligned __section(".data..lock_aligned") +# define __lock_aligned __section(".data..lock_aligned") __aligned(16) #endif #endif /* __PARISC_LDCW_H */ diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h index ff6cbdb6903bc..ece4b3046515c 100644 --- a/arch/parisc/include/asm/processor.h +++ b/arch/parisc/include/asm/processor.h @@ -47,6 +47,8 @@ #ifndef __ASSEMBLY__ +struct rlimit; +unsigned long mmap_upper_limit(struct rlimit *rlim_stack); unsigned long calc_max_stack_size(unsigned long stack_max); /* diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h index 2bf660eabe421..4165079898d9e 100644 --- a/arch/parisc/include/asm/uaccess.h +++ b/arch/parisc/include/asm/uaccess.h @@ -41,6 +41,7 @@ struct exception_table_entry { #define ASM_EXCEPTIONTABLE_ENTRY( fault_addr, except_addr )\ ".section __ex_table,\"aw\"\n" \ + ".align 4\n" \ ".word (" #fault_addr " - .), (" #except_addr " - .)\n\t" \ ".previous\n" diff --git a/arch/parisc/include/uapi/asm/errno.h b/arch/parisc/include/uapi/asm/errno.h index 87245c584784e..8d94739d75c67 100644 --- a/arch/parisc/include/uapi/asm/errno.h +++ b/arch/parisc/include/uapi/asm/errno.h @@ -75,7 +75,6 @@ /* We now return you to your regularly scheduled HPUX. */ -#define ENOSYM 215 /* symbol does not exist in executable */ #define ENOTSOCK 216 /* Socket operation on non-socket */ #define EDESTADDRREQ 217 /* Destination address required */ #define EMSGSIZE 218 /* Message too long */ @@ -101,7 +100,6 @@ #define ETIMEDOUT 238 /* Connection timed out */ #define ECONNREFUSED 239 /* Connection refused */ #define EREFUSED ECONNREFUSED /* for HP's NFS apparently */ -#define EREMOTERELEASE 240 /* Remote peer released connection */ #define EHOSTDOWN 241 /* Host is down */ #define EHOSTUNREACH 242 /* No route to host */ diff --git a/arch/parisc/include/uapi/asm/pdc.h b/arch/parisc/include/uapi/asm/pdc.h index 7a90070136e82..8e38a86996fc6 100644 --- a/arch/parisc/include/uapi/asm/pdc.h +++ b/arch/parisc/include/uapi/asm/pdc.h @@ -472,6 +472,7 @@ struct pdc_model { /* for PDC_MODEL */ unsigned long arch_rev; unsigned long pot_key; unsigned long curr_key; + unsigned long width; /* default of PSW_W bit (1=enabled) */ }; struct pdc_cache_cf { /* for PDC_CACHE (I/D-caches) */ diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S index ae03b8679696e..ab23e61a6f016 100644 --- a/arch/parisc/kernel/entry.S +++ b/arch/parisc/kernel/entry.S @@ -36,6 +36,24 @@ .level 2.0 #endif +/* + * We need seven instructions after a TLB insert for it to take effect. + * The PA8800/PA8900 processors are an exception and need 12 instructions. + * The RFI changes both IAOQ_Back and IAOQ_Front, so it counts as one. + */ +#ifdef CONFIG_64BIT +#define NUM_PIPELINE_INSNS 12 +#else +#define NUM_PIPELINE_INSNS 7 +#endif + + /* Insert num nops */ + .macro insert_nops num + .rept \num + nop + .endr + .endm + /* Get aligned page_table_lock address for this mm from cr28/tr4 */ .macro get_ptl reg mfctl %cr28,\reg @@ -415,24 +433,20 @@ 3: .endm - /* Release page_table_lock without reloading lock address. - We use an ordered store to ensure all prior accesses are - performed prior to releasing the lock. */ - .macro ptl_unlock0 spc,tmp,tmp2 + /* Release page_table_lock if for user space. We use an ordered + store to ensure all prior accesses are performed prior to + releasing the lock. Note stw may not be executed, so we + provide one extra nop when CONFIG_TLB_PTLOCK is defined. */ + .macro ptl_unlock spc,tmp,tmp2 #ifdef CONFIG_TLB_PTLOCK -98: ldi __ARCH_SPIN_LOCK_UNLOCKED_VAL, \tmp2 +98: get_ptl \tmp + ldi __ARCH_SPIN_LOCK_UNLOCKED_VAL, \tmp2 or,COND(=) %r0,\spc,%r0 stw,ma \tmp2,0(\tmp) 99: ALTERNATIVE(98b, 99b, ALT_COND_NO_SMP, INSN_NOP) -#endif - .endm - - /* Release page_table_lock. */ - .macro ptl_unlock1 spc,tmp,tmp2 -#ifdef CONFIG_TLB_PTLOCK -98: get_ptl \tmp - ptl_unlock0 \spc,\tmp,\tmp2 -99: ALTERNATIVE(98b, 99b, ALT_COND_NO_SMP, INSN_NOP) + insert_nops NUM_PIPELINE_INSNS - 4 +#else + insert_nops NUM_PIPELINE_INSNS - 1 #endif .endm @@ -461,13 +475,13 @@ * to a CPU TLB 4k PFN (4k => 12 bits to shift) */ #define PAGE_ADD_SHIFT (PAGE_SHIFT-12) #define PAGE_ADD_HUGE_SHIFT (REAL_HPAGE_SHIFT-12) + #define PFN_START_BIT (63-ASM_PFN_PTE_SHIFT+(63-58)-PAGE_ADD_SHIFT) /* Drop prot bits and convert to page addr for iitlbt and idtlbt */ .macro convert_for_tlb_insert20 pte,tmp #ifdef CONFIG_HUGETLB_PAGE copy \pte,\tmp - extrd,u \tmp,(63-ASM_PFN_PTE_SHIFT)+(63-58)+PAGE_ADD_SHIFT,\ - 64-PAGE_SHIFT-PAGE_ADD_SHIFT,\pte + extrd,u \tmp,PFN_START_BIT,PFN_START_BIT+1,\pte depdi _PAGE_SIZE_ENCODING_DEFAULT,63,\ (63-58)+PAGE_ADD_SHIFT,\pte @@ -475,8 +489,7 @@ depdi _HUGE_PAGE_SIZE_ENCODING_DEFAULT,63,\ (63-58)+PAGE_ADD_HUGE_SHIFT,\pte #else /* Huge pages disabled */ - extrd,u \pte,(63-ASM_PFN_PTE_SHIFT)+(63-58)+PAGE_ADD_SHIFT,\ - 64-PAGE_SHIFT-PAGE_ADD_SHIFT,\pte + extrd,u \pte,PFN_START_BIT,PFN_START_BIT+1,\pte depdi _PAGE_SIZE_ENCODING_DEFAULT,63,\ (63-58)+PAGE_ADD_SHIFT,\pte #endif @@ -1124,7 +1137,7 @@ dtlb_miss_20w: idtlbt pte,prot - ptl_unlock1 spc,t0,t1 + ptl_unlock spc,t0,t1 rfir nop @@ -1133,6 +1146,7 @@ dtlb_check_alias_20w: idtlbt pte,prot + insert_nops NUM_PIPELINE_INSNS - 1 rfir nop @@ -1150,7 +1164,7 @@ nadtlb_miss_20w: idtlbt pte,prot - ptl_unlock1 spc,t0,t1 + ptl_unlock spc,t0,t1 rfir nop @@ -1159,6 +1173,7 @@ nadtlb_check_alias_20w: idtlbt pte,prot + insert_nops NUM_PIPELINE_INSNS - 1 rfir nop @@ -1184,7 +1199,7 @@ dtlb_miss_11: mtsp t1, %sr1 /* Restore sr1 */ - ptl_unlock1 spc,t0,t1 + ptl_unlock spc,t0,t1 rfir nop @@ -1194,6 +1209,7 @@ dtlb_check_alias_11: idtlba pte,(va) idtlbp prot,(va) + insert_nops NUM_PIPELINE_INSNS - 1 rfir nop @@ -1217,7 +1233,7 @@ nadtlb_miss_11: mtsp t1, %sr1 /* Restore sr1 */ - ptl_unlock1 spc,t0,t1 + ptl_unlock spc,t0,t1 rfir nop @@ -1227,6 +1243,7 @@ nadtlb_check_alias_11: idtlba pte,(va) idtlbp prot,(va) + insert_nops NUM_PIPELINE_INSNS - 1 rfir nop @@ -1246,7 +1263,7 @@ dtlb_miss_20: idtlbt pte,prot - ptl_unlock1 spc,t0,t1 + ptl_unlock spc,t0,t1 rfir nop @@ -1255,6 +1272,7 @@ dtlb_check_alias_20: idtlbt pte,prot + insert_nops NUM_PIPELINE_INSNS - 1 rfir nop @@ -1274,7 +1292,7 @@ nadtlb_miss_20: idtlbt pte,prot - ptl_unlock1 spc,t0,t1 + ptl_unlock spc,t0,t1 rfir nop @@ -1283,6 +1301,7 @@ nadtlb_check_alias_20: idtlbt pte,prot + insert_nops NUM_PIPELINE_INSNS - 1 rfir nop @@ -1319,7 +1338,7 @@ itlb_miss_20w: iitlbt pte,prot - ptl_unlock1 spc,t0,t1 + ptl_unlock spc,t0,t1 rfir nop @@ -1343,7 +1362,7 @@ naitlb_miss_20w: iitlbt pte,prot - ptl_unlock1 spc,t0,t1 + ptl_unlock spc,t0,t1 rfir nop @@ -1352,6 +1371,7 @@ naitlb_check_alias_20w: iitlbt pte,prot + insert_nops NUM_PIPELINE_INSNS - 1 rfir nop @@ -1377,7 +1397,7 @@ itlb_miss_11: mtsp t1, %sr1 /* Restore sr1 */ - ptl_unlock1 spc,t0,t1 + ptl_unlock spc,t0,t1 rfir nop @@ -1401,7 +1421,7 @@ naitlb_miss_11: mtsp t1, %sr1 /* Restore sr1 */ - ptl_unlock1 spc,t0,t1 + ptl_unlock spc,t0,t1 rfir nop @@ -1411,6 +1431,7 @@ naitlb_check_alias_11: iitlba pte,(%sr0, va) iitlbp prot,(%sr0, va) + insert_nops NUM_PIPELINE_INSNS - 1 rfir nop @@ -1431,7 +1452,7 @@ itlb_miss_20: iitlbt pte,prot - ptl_unlock1 spc,t0,t1 + ptl_unlock spc,t0,t1 rfir nop @@ -1451,7 +1472,7 @@ naitlb_miss_20: iitlbt pte,prot - ptl_unlock1 spc,t0,t1 + ptl_unlock spc,t0,t1 rfir nop @@ -1460,6 +1481,7 @@ naitlb_check_alias_20: iitlbt pte,prot + insert_nops NUM_PIPELINE_INSNS - 1 rfir nop @@ -1481,7 +1503,7 @@ dbit_trap_20w: idtlbt pte,prot - ptl_unlock0 spc,t0,t1 + ptl_unlock spc,t0,t1 rfir nop #else @@ -1507,7 +1529,7 @@ dbit_trap_11: mtsp t1, %sr1 /* Restore sr1 */ - ptl_unlock0 spc,t0,t1 + ptl_unlock spc,t0,t1 rfir nop @@ -1527,7 +1549,7 @@ dbit_trap_20: idtlbt pte,prot - ptl_unlock0 spc,t0,t1 + ptl_unlock spc,t0,t1 rfir nop #endif diff --git a/arch/parisc/kernel/head.S b/arch/parisc/kernel/head.S index a171bf3c6b318..96e0264ac9616 100644 --- a/arch/parisc/kernel/head.S +++ b/arch/parisc/kernel/head.S @@ -70,9 +70,8 @@ $bss_loop: stw,ma %arg2,4(%r1) stw,ma %arg3,4(%r1) -#if !defined(CONFIG_64BIT) && defined(CONFIG_PA20) - /* This 32-bit kernel was compiled for PA2.0 CPUs. Check current CPU - * and halt kernel if we detect a PA1.x CPU. */ +#if defined(CONFIG_PA20) + /* check for 64-bit capable CPU as required by current kernel */ ldi 32,%r10 mtctl %r10,%cr11 .level 2.0 diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c index ab896eff7a1de..98af719d5f85b 100644 --- a/arch/parisc/kernel/sys_parisc.c +++ b/arch/parisc/kernel/sys_parisc.c @@ -77,7 +77,7 @@ unsigned long calc_max_stack_size(unsigned long stack_max) * indicating that "current" should be used instead of a passed-in * value from the exec bprm as done with arch_pick_mmap_layout(). */ -static unsigned long mmap_upper_limit(struct rlimit *rlim_stack) +unsigned long mmap_upper_limit(struct rlimit *rlim_stack) { unsigned long stack_base; diff --git a/arch/parisc/kernel/vmlinux.lds.S b/arch/parisc/kernel/vmlinux.lds.S index 58694d1989c23..548051b0b4aff 100644 --- a/arch/parisc/kernel/vmlinux.lds.S +++ b/arch/parisc/kernel/vmlinux.lds.S @@ -130,6 +130,7 @@ SECTIONS RO_DATA(8) /* unwind info */ + . = ALIGN(4); .PARISC.unwind : { __start___unwind = .; *(.PARISC.unwind) diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index d5d5388973ac7..4640cee33f123 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -607,10 +607,10 @@ config ARCH_SUPPORTS_KEXEC def_bool PPC_BOOK3S || PPC_E500 || (44x && !SMP) config ARCH_SUPPORTS_KEXEC_FILE - def_bool PPC64 && CRYPTO=y && CRYPTO_SHA256=y + def_bool PPC64 config ARCH_SUPPORTS_KEXEC_PURGATORY - def_bool KEXEC_FILE + def_bool y config ARCH_SELECTS_KEXEC_FILE def_bool y diff --git a/arch/powerpc/configs/skiroot_defconfig b/arch/powerpc/configs/skiroot_defconfig index 8d3eacb50d560..9d44e6630908d 100644 --- a/arch/powerpc/configs/skiroot_defconfig +++ b/arch/powerpc/configs/skiroot_defconfig @@ -301,7 +301,6 @@ CONFIG_WQ_WATCHDOG=y CONFIG_DEBUG_SG=y CONFIG_DEBUG_NOTIFIERS=y CONFIG_BUG_ON_DATA_CORRUPTION=y -CONFIG_DEBUG_CREDENTIALS=y # CONFIG_FTRACE is not set CONFIG_XMON=y # CONFIG_RUNTIME_TESTING_MENU is not set diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S index 6a9acfb690c9f..2f8f3f93cbb67 100644 --- a/arch/powerpc/kernel/fpu.S +++ b/arch/powerpc/kernel/fpu.S @@ -23,6 +23,15 @@ #include #ifdef CONFIG_VSX +#define __REST_1FPVSR(n,c,base) \ +BEGIN_FTR_SECTION \ + b 2f; \ +END_FTR_SECTION_IFSET(CPU_FTR_VSX); \ + REST_FPR(n,base); \ + b 3f; \ +2: REST_VSR(n,c,base); \ +3: + #define __REST_32FPVSRS(n,c,base) \ BEGIN_FTR_SECTION \ b 2f; \ @@ -41,9 +50,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX); \ 2: SAVE_32VSRS(n,c,base); \ 3: #else +#define __REST_1FPVSR(n,b,base) REST_FPR(n, base) #define __REST_32FPVSRS(n,b,base) REST_32FPRS(n, base) #define __SAVE_32FPVSRS(n,b,base) SAVE_32FPRS(n, base) #endif +#define REST_1FPVSR(n,c,base) __REST_1FPVSR(n,__REG_##c,__REG_##base) #define REST_32FPVSRS(n,c,base) __REST_32FPVSRS(n,__REG_##c,__REG_##base) #define SAVE_32FPVSRS(n,c,base) __SAVE_32FPVSRS(n,__REG_##c,__REG_##base) @@ -67,6 +78,7 @@ _GLOBAL(store_fp_state) SAVE_32FPVSRS(0, R4, R3) mffs fr0 stfd fr0,FPSTATE_FPSCR(r3) + REST_1FPVSR(0, R4, R3) blr EXPORT_SYMBOL(store_fp_state) @@ -138,4 +150,5 @@ _GLOBAL(save_fpu) 2: SAVE_32FPVSRS(0, R4, R6) mffs fr0 stfd fr0,FPSTATE_FPSCR(r6) + REST_1FPVSR(0, R4, R6) blr diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 392404688cec3..9452a54d356c9 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1198,11 +1198,11 @@ void kvmppc_save_user_regs(void) usermsr = current->thread.regs->msr; + /* Caller has enabled FP/VEC/VSX/TM in MSR */ if (usermsr & MSR_FP) - save_fpu(current); - + __giveup_fpu(current); if (usermsr & MSR_VEC) - save_altivec(current); + __giveup_altivec(current); #ifdef CONFIG_PPC_TRANSACTIONAL_MEM if (usermsr & MSR_TM) { diff --git a/arch/powerpc/kernel/trace/ftrace_entry.S b/arch/powerpc/kernel/trace/ftrace_entry.S index 90701885762cf..40677416d7b26 100644 --- a/arch/powerpc/kernel/trace/ftrace_entry.S +++ b/arch/powerpc/kernel/trace/ftrace_entry.S @@ -62,7 +62,7 @@ .endif /* Save previous stack pointer (r1) */ - addi r8, r1, SWITCH_FRAME_SIZE + addi r8, r1, SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE PPC_STL r8, GPR1(r1) .if \allregs == 1 @@ -182,7 +182,7 @@ ftrace_no_trace: mflr r3 mtctr r3 REST_GPR(3, r1) - addi r1, r1, SWITCH_FRAME_SIZE + addi r1, r1, SWITCH_FRAME_SIZE+STACK_FRAME_MIN_SIZE mtlr r0 bctr #endif diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S index 4094e4c4c77a7..80b3f6e476b66 100644 --- a/arch/powerpc/kernel/vector.S +++ b/arch/powerpc/kernel/vector.S @@ -33,6 +33,7 @@ _GLOBAL(store_vr_state) mfvscr v0 li r4, VRSTATE_VSCR stvx v0, r4, r3 + lvx v0, 0, r3 blr EXPORT_SYMBOL(store_vr_state) @@ -109,6 +110,7 @@ _GLOBAL(save_altivec) mfvscr v0 li r4,VRSTATE_VSCR stvx v0,r4,r7 + lvx v0,0,r7 blr #ifdef CONFIG_VSX diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 8c1f7def596e4..10b946e9c6e75 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -1371,8 +1371,7 @@ static void power_pmu_disable(struct pmu *pmu) /* * Disable instruction sampling if it was enabled */ - if (cpuhw->mmcr.mmcra & MMCRA_SAMPLE_ENABLE) - val &= ~MMCRA_SAMPLE_ENABLE; + val &= ~MMCRA_SAMPLE_ENABLE; /* Disable BHRB via mmcra (BHRBRD) for p10 */ if (ppmu->flags & PPMU_ARCH_31) @@ -1383,7 +1382,7 @@ static void power_pmu_disable(struct pmu *pmu) * instruction sampling or BHRB. */ if (val != mmcra) { - mtspr(SPRN_MMCRA, mmcra); + mtspr(SPRN_MMCRA, val); mb(); isync(); } diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 16d93b580f61f..496e16c588aaa 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -914,7 +914,8 @@ static int remove_ddw(struct device_node *np, bool remove_prop, const char *win_ return 0; } -static bool find_existing_ddw(struct device_node *pdn, u64 *dma_addr, int *window_shift) +static bool find_existing_ddw(struct device_node *pdn, u64 *dma_addr, int *window_shift, + bool *direct_mapping) { struct dma_win *window; const struct dynamic_dma_window_prop *dma64; @@ -927,6 +928,7 @@ static bool find_existing_ddw(struct device_node *pdn, u64 *dma_addr, int *windo dma64 = window->prop; *dma_addr = be64_to_cpu(dma64->dma_base); *window_shift = be32_to_cpu(dma64->window_shift); + *direct_mapping = window->direct; found = true; break; } @@ -1270,10 +1272,8 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn) mutex_lock(&dma_win_init_mutex); - if (find_existing_ddw(pdn, &dev->dev.archdata.dma_offset, &len)) { - direct_mapping = (len >= max_ram_len); + if (find_existing_ddw(pdn, &dev->dev.archdata.dma_offset, &len, &direct_mapping)) goto out_unlock; - } /* * If we already went through this for a previous function of diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 9c48fecc67191..9e6d442773eea 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -669,7 +669,7 @@ config RISCV_BOOT_SPINWAIT If unsure what to do here, say N. config ARCH_SUPPORTS_KEXEC - def_bool MMU + def_bool y config ARCH_SELECTS_KEXEC def_bool y @@ -677,7 +677,7 @@ config ARCH_SELECTS_KEXEC select HOTPLUG_CPU if SMP config ARCH_SUPPORTS_KEXEC_FILE - def_bool 64BIT && MMU + def_bool 64BIT config ARCH_SELECTS_KEXEC_FILE def_bool y @@ -686,9 +686,7 @@ config ARCH_SELECTS_KEXEC_FILE select KEXEC_ELF config ARCH_SUPPORTS_KEXEC_PURGATORY - def_bool KEXEC_FILE - depends on CRYPTO=y - depends on CRYPTO_SHA256=y + def_bool ARCH_SUPPORTS_KEXEC_FILE config ARCH_SUPPORTS_CRASH_DUMP def_bool y diff --git a/arch/riscv/Kconfig.socs b/arch/riscv/Kconfig.socs index 6833d01e2e707..30fd6a5128285 100644 --- a/arch/riscv/Kconfig.socs +++ b/arch/riscv/Kconfig.socs @@ -29,6 +29,7 @@ config SOC_STARFIVE bool "StarFive SoCs" select PINCTRL select RESET_CONTROLLER + select ARM_AMBA help This enables support for StarFive SoC platform hardware. diff --git a/arch/riscv/errata/andes/errata.c b/arch/riscv/errata/andes/errata.c index 197db68cc8daf..17a9048697246 100644 --- a/arch/riscv/errata/andes/errata.c +++ b/arch/riscv/errata/andes/errata.c @@ -38,29 +38,35 @@ static long ax45mp_iocp_sw_workaround(void) return ret.error ? 0 : ret.value; } -static bool errata_probe_iocp(unsigned int stage, unsigned long arch_id, unsigned long impid) +static void errata_probe_iocp(unsigned int stage, unsigned long arch_id, unsigned long impid) { + static bool done; + if (!IS_ENABLED(CONFIG_ERRATA_ANDES_CMO)) - return false; + return; + + if (done) + return; + + done = true; if (arch_id != ANDESTECH_AX45MP_MARCHID || impid != ANDESTECH_AX45MP_MIMPID) - return false; + return; if (!ax45mp_iocp_sw_workaround()) - return false; + return; /* Set this just to make core cbo code happy */ riscv_cbom_block_size = 1; riscv_noncoherent_supported(); - - return true; } void __init_or_module andes_errata_patch_func(struct alt_entry *begin, struct alt_entry *end, unsigned long archid, unsigned long impid, unsigned int stage) { - errata_probe_iocp(stage, archid, impid); + if (stage == RISCV_ALTERNATIVES_BOOT) + errata_probe_iocp(stage, archid, impid); /* we have nothing to patch here ATM so just return back */ } diff --git a/arch/riscv/include/asm/asm-prototypes.h b/arch/riscv/include/asm/asm-prototypes.h index 61ba8ed43d8fe..36b955c762ba0 100644 --- a/arch/riscv/include/asm/asm-prototypes.h +++ b/arch/riscv/include/asm/asm-prototypes.h @@ -25,7 +25,6 @@ DECLARE_DO_ERROR_INFO(do_trap_ecall_s); DECLARE_DO_ERROR_INFO(do_trap_ecall_m); DECLARE_DO_ERROR_INFO(do_trap_break); -asmlinkage unsigned long get_overflow_stack(void); asmlinkage void handle_bad_stack(struct pt_regs *regs); asmlinkage void do_page_fault(struct pt_regs *regs); asmlinkage void do_irq(struct pt_regs *regs); diff --git a/arch/riscv/include/asm/asm.h b/arch/riscv/include/asm/asm.h index 114bbadaef41e..bfb4c26f113c4 100644 --- a/arch/riscv/include/asm/asm.h +++ b/arch/riscv/include/asm/asm.h @@ -82,6 +82,28 @@ .endr .endm +#ifdef CONFIG_SMP +#ifdef CONFIG_32BIT +#define PER_CPU_OFFSET_SHIFT 2 +#else +#define PER_CPU_OFFSET_SHIFT 3 +#endif + +.macro asm_per_cpu dst sym tmp + REG_L \tmp, TASK_TI_CPU_NUM(tp) + slli \tmp, \tmp, PER_CPU_OFFSET_SHIFT + la \dst, __per_cpu_offset + add \dst, \dst, \tmp + REG_L \tmp, 0(\dst) + la \dst, \sym + add \dst, \dst, \tmp +.endm +#else /* CONFIG_SMP */ +.macro asm_per_cpu dst sym tmp + la \dst, \sym +.endm +#endif /* CONFIG_SMP */ + /* save all GPs except x1 ~ x5 */ .macro save_from_x6_to_x31 REG_S x6, PT_T1(sp) diff --git a/arch/riscv/include/asm/hwprobe.h b/arch/riscv/include/asm/hwprobe.h index 78936f4ff5133..7cad513538d8d 100644 --- a/arch/riscv/include/asm/hwprobe.h +++ b/arch/riscv/include/asm/hwprobe.h @@ -10,4 +10,9 @@ #define RISCV_HWPROBE_MAX_KEY 5 +static inline bool riscv_hwprobe_key_is_valid(__s64 key) +{ + return key >= 0 && key <= RISCV_HWPROBE_MAX_KEY; +} + #endif diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h index 5488ecc337b63..57e887bfa34cb 100644 --- a/arch/riscv/include/asm/page.h +++ b/arch/riscv/include/asm/page.h @@ -33,8 +33,8 @@ #define PAGE_OFFSET _AC(CONFIG_PAGE_OFFSET, UL) #endif /* - * By default, CONFIG_PAGE_OFFSET value corresponds to SV48 address space so - * define the PAGE_OFFSET value for SV39. + * By default, CONFIG_PAGE_OFFSET value corresponds to SV57 address space so + * define the PAGE_OFFSET value for SV48 and SV39. */ #define PAGE_OFFSET_L4 _AC(0xffffaf8000000000, UL) #define PAGE_OFFSET_L3 _AC(0xffffffd800000000, UL) diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h index 1833beb00489c..d18ce0113ca1f 100644 --- a/arch/riscv/include/asm/thread_info.h +++ b/arch/riscv/include/asm/thread_info.h @@ -34,9 +34,6 @@ #ifndef __ASSEMBLY__ -extern long shadow_stack[SHADOW_OVERFLOW_STACK_SIZE / sizeof(long)]; -extern unsigned long spin_shadow_stack; - #include #include diff --git a/arch/riscv/include/asm/vdso/processor.h b/arch/riscv/include/asm/vdso/processor.h index 14f5d27783b85..96b65a5396dfc 100644 --- a/arch/riscv/include/asm/vdso/processor.h +++ b/arch/riscv/include/asm/vdso/processor.h @@ -14,7 +14,7 @@ static inline void cpu_relax(void) __asm__ __volatile__ ("div %0, %0, zero" : "=r" (dummy)); #endif -#ifdef __riscv_zihintpause +#ifdef CONFIG_TOOLCHAIN_HAS_ZIHINTPAUSE /* * Reduce instruction retirement. * This assumes the PC changes. diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c index d6a75aac1d27a..9f535d5de33f9 100644 --- a/arch/riscv/kernel/asm-offsets.c +++ b/arch/riscv/kernel/asm-offsets.c @@ -39,6 +39,7 @@ void asm_offsets(void) OFFSET(TASK_TI_KERNEL_SP, task_struct, thread_info.kernel_sp); OFFSET(TASK_TI_USER_SP, task_struct, thread_info.user_sp); + OFFSET(TASK_TI_CPU_NUM, task_struct, thread_info.cpu); OFFSET(TASK_THREAD_F0, task_struct, thread.fstate.f[0]); OFFSET(TASK_THREAD_F1, task_struct, thread.fstate.f[1]); OFFSET(TASK_THREAD_F2, task_struct, thread.fstate.f[2]); diff --git a/arch/riscv/kernel/crash_core.c b/arch/riscv/kernel/crash_core.c index 55f1d7856b544..8706736fd4e2d 100644 --- a/arch/riscv/kernel/crash_core.c +++ b/arch/riscv/kernel/crash_core.c @@ -5,17 +5,19 @@ void arch_crash_save_vmcoreinfo(void) { - VMCOREINFO_NUMBER(VA_BITS); VMCOREINFO_NUMBER(phys_ram_base); vmcoreinfo_append_str("NUMBER(PAGE_OFFSET)=0x%lx\n", PAGE_OFFSET); vmcoreinfo_append_str("NUMBER(VMALLOC_START)=0x%lx\n", VMALLOC_START); vmcoreinfo_append_str("NUMBER(VMALLOC_END)=0x%lx\n", VMALLOC_END); +#ifdef CONFIG_MMU + VMCOREINFO_NUMBER(VA_BITS); vmcoreinfo_append_str("NUMBER(VMEMMAP_START)=0x%lx\n", VMEMMAP_START); vmcoreinfo_append_str("NUMBER(VMEMMAP_END)=0x%lx\n", VMEMMAP_END); #ifdef CONFIG_64BIT vmcoreinfo_append_str("NUMBER(MODULES_VADDR)=0x%lx\n", MODULES_VADDR); vmcoreinfo_append_str("NUMBER(MODULES_END)=0x%lx\n", MODULES_END); +#endif #endif vmcoreinfo_append_str("NUMBER(KERNEL_LINK_ADDR)=0x%lx\n", KERNEL_LINK_ADDR); vmcoreinfo_append_str("NUMBER(va_kernel_pa_offset)=0x%lx\n", diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index 143a2bb3e6976..278d01d2911fd 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -10,9 +10,13 @@ #include #include #include +#include #include #include #include +#include + + .section .irqentry.text, "ax" SYM_CODE_START(handle_exception) /* @@ -170,67 +174,15 @@ SYM_CODE_END(ret_from_exception) #ifdef CONFIG_VMAP_STACK SYM_CODE_START_LOCAL(handle_kernel_stack_overflow) - /* - * Takes the psuedo-spinlock for the shadow stack, in case multiple - * harts are concurrently overflowing their kernel stacks. We could - * store any value here, but since we're overflowing the kernel stack - * already we only have SP to use as a scratch register. So we just - * swap in the address of the spinlock, as that's definately non-zero. - * - * Pairs with a store_release in handle_bad_stack(). - */ -1: la sp, spin_shadow_stack - REG_AMOSWAP_AQ sp, sp, (sp) - bnez sp, 1b - - la sp, shadow_stack - addi sp, sp, SHADOW_OVERFLOW_STACK_SIZE - - //save caller register to shadow stack - addi sp, sp, -(PT_SIZE_ON_STACK) - REG_S x1, PT_RA(sp) - REG_S x5, PT_T0(sp) - REG_S x6, PT_T1(sp) - REG_S x7, PT_T2(sp) - REG_S x10, PT_A0(sp) - REG_S x11, PT_A1(sp) - REG_S x12, PT_A2(sp) - REG_S x13, PT_A3(sp) - REG_S x14, PT_A4(sp) - REG_S x15, PT_A5(sp) - REG_S x16, PT_A6(sp) - REG_S x17, PT_A7(sp) - REG_S x28, PT_T3(sp) - REG_S x29, PT_T4(sp) - REG_S x30, PT_T5(sp) - REG_S x31, PT_T6(sp) - - la ra, restore_caller_reg - tail get_overflow_stack - -restore_caller_reg: - //save per-cpu overflow stack - REG_S a0, -8(sp) - //restore caller register from shadow_stack - REG_L x1, PT_RA(sp) - REG_L x5, PT_T0(sp) - REG_L x6, PT_T1(sp) - REG_L x7, PT_T2(sp) - REG_L x10, PT_A0(sp) - REG_L x11, PT_A1(sp) - REG_L x12, PT_A2(sp) - REG_L x13, PT_A3(sp) - REG_L x14, PT_A4(sp) - REG_L x15, PT_A5(sp) - REG_L x16, PT_A6(sp) - REG_L x17, PT_A7(sp) - REG_L x28, PT_T3(sp) - REG_L x29, PT_T4(sp) - REG_L x30, PT_T5(sp) - REG_L x31, PT_T6(sp) + /* we reach here from kernel context, sscratch must be 0 */ + csrrw x31, CSR_SCRATCH, x31 + asm_per_cpu sp, overflow_stack, x31 + li x31, OVERFLOW_STACK_SIZE + add sp, sp, x31 + /* zero out x31 again and restore x31 */ + xor x31, x31, x31 + csrrw x31, CSR_SCRATCH, x31 - //load per-cpu overflow stack - REG_L sp, -8(sp) addi sp, sp, -(PT_SIZE_ON_STACK) //save context to overflow stack diff --git a/arch/riscv/kernel/probes/simulate-insn.c b/arch/riscv/kernel/probes/simulate-insn.c index d3099d67816d0..6c166029079c4 100644 --- a/arch/riscv/kernel/probes/simulate-insn.c +++ b/arch/riscv/kernel/probes/simulate-insn.c @@ -24,7 +24,7 @@ static inline bool rv_insn_reg_set_val(struct pt_regs *regs, u32 index, unsigned long val) { if (index == 0) - return false; + return true; else if (index <= 31) *((unsigned long *)regs + index) = val; else diff --git a/arch/riscv/kernel/probes/uprobes.c b/arch/riscv/kernel/probes/uprobes.c index 194f166b2cc40..4b3dc8beaf77d 100644 --- a/arch/riscv/kernel/probes/uprobes.c +++ b/arch/riscv/kernel/probes/uprobes.c @@ -3,6 +3,7 @@ #include #include #include +#include #include "decode-insn.h" @@ -17,6 +18,11 @@ bool is_swbp_insn(uprobe_opcode_t *insn) #endif } +bool is_trap_insn(uprobe_opcode_t *insn) +{ + return riscv_insn_is_ebreak(*insn) || riscv_insn_is_c_ebreak(*insn); +} + unsigned long uprobe_get_swbp_addr(struct pt_regs *regs) { return instruction_pointer(regs); diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index fae8f610d867f..67d0073fb624d 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -410,48 +410,14 @@ int is_valid_bugaddr(unsigned long pc) #endif /* CONFIG_GENERIC_BUG */ #ifdef CONFIG_VMAP_STACK -/* - * Extra stack space that allows us to provide panic messages when the kernel - * has overflowed its stack. - */ -static DEFINE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], +DEFINE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack)__aligned(16); -/* - * A temporary stack for use by handle_kernel_stack_overflow. This is used so - * we can call into C code to get the per-hart overflow stack. Usage of this - * stack must be protected by spin_shadow_stack. - */ -long shadow_stack[SHADOW_OVERFLOW_STACK_SIZE/sizeof(long)] __aligned(16); - -/* - * A pseudo spinlock to protect the shadow stack from being used by multiple - * harts concurrently. This isn't a real spinlock because the lock side must - * be taken without a valid stack and only a single register, it's only taken - * while in the process of panicing anyway so the performance and error - * checking a proper spinlock gives us doesn't matter. - */ -unsigned long spin_shadow_stack; - -asmlinkage unsigned long get_overflow_stack(void) -{ - return (unsigned long)this_cpu_ptr(overflow_stack) + - OVERFLOW_STACK_SIZE; -} asmlinkage void handle_bad_stack(struct pt_regs *regs) { unsigned long tsk_stk = (unsigned long)current->stack; unsigned long ovf_stk = (unsigned long)this_cpu_ptr(overflow_stack); - /* - * We're done with the shadow stack by this point, as we're on the - * overflow stack. Tell any other concurrent overflowing harts that - * they can proceed with panicing by releasing the pseudo-spinlock. - * - * This pairs with an amoswap.aq in handle_kernel_stack_overflow. - */ - smp_store_release(&spin_shadow_stack, 0); - console_verbose(); pr_emerg("Insufficient stack space to handle exception!\n"); diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c index 378f5b1514435..5348d842c7453 100644 --- a/arch/riscv/kernel/traps_misaligned.c +++ b/arch/riscv/kernel/traps_misaligned.c @@ -342,16 +342,14 @@ int handle_misaligned_store(struct pt_regs *regs) } else if ((insn & INSN_MASK_C_SD) == INSN_MATCH_C_SD) { len = 8; val.data_ulong = GET_RS2S(insn, regs); - } else if ((insn & INSN_MASK_C_SDSP) == INSN_MATCH_C_SDSP && - ((insn >> SH_RD) & 0x1f)) { + } else if ((insn & INSN_MASK_C_SDSP) == INSN_MATCH_C_SDSP) { len = 8; val.data_ulong = GET_RS2C(insn, regs); #endif } else if ((insn & INSN_MASK_C_SW) == INSN_MATCH_C_SW) { len = 4; val.data_ulong = GET_RS2S(insn, regs); - } else if ((insn & INSN_MASK_C_SWSP) == INSN_MATCH_C_SWSP && - ((insn >> SH_RD) & 0x1f)) { + } else if ((insn & INSN_MASK_C_SWSP) == INSN_MATCH_C_SWSP) { len = 4; val.data_ulong = GET_RS2C(insn, regs); } else { diff --git a/arch/riscv/kernel/vdso/hwprobe.c b/arch/riscv/kernel/vdso/hwprobe.c index d40bec6ac0786..cadf725ef7983 100644 --- a/arch/riscv/kernel/vdso/hwprobe.c +++ b/arch/riscv/kernel/vdso/hwprobe.c @@ -37,7 +37,7 @@ int __vdso_riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count, /* This is something we can handle, fill out the pairs. */ while (p < end) { - if (p->key <= RISCV_HWPROBE_MAX_KEY) { + if (riscv_hwprobe_key_is_valid(p->key)) { p->value = avd->all_cpu_hwprobe_values[p->key]; } else { diff --git a/arch/riscv/mm/Makefile b/arch/riscv/mm/Makefile index 9c454f90fd3da..3a4dfc8babcf8 100644 --- a/arch/riscv/mm/Makefile +++ b/arch/riscv/mm/Makefile @@ -36,3 +36,4 @@ endif obj-$(CONFIG_DEBUG_VIRTUAL) += physaddr.o obj-$(CONFIG_RISCV_DMA_NONCOHERENT) += dma-noncoherent.o +obj-$(CONFIG_RISCV_NONSTANDARD_CACHE_OPS) += cache-ops.o diff --git a/arch/riscv/mm/cache-ops.c b/arch/riscv/mm/cache-ops.c new file mode 100644 index 0000000000000..a993ad11d0eca --- /dev/null +++ b/arch/riscv/mm/cache-ops.c @@ -0,0 +1,17 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2021 Western Digital Corporation or its affiliates. + */ + +#include + +struct riscv_nonstd_cache_ops noncoherent_cache_ops __ro_after_init; + +void +riscv_noncoherent_register_cache_ops(const struct riscv_nonstd_cache_ops *ops) +{ + if (!ops) + return; + noncoherent_cache_ops = *ops; +} +EXPORT_SYMBOL_GPL(riscv_noncoherent_register_cache_ops); diff --git a/arch/riscv/mm/dma-noncoherent.c b/arch/riscv/mm/dma-noncoherent.c index b76e7e192eb18..341bd6706b4c5 100644 --- a/arch/riscv/mm/dma-noncoherent.c +++ b/arch/riscv/mm/dma-noncoherent.c @@ -15,12 +15,6 @@ static bool noncoherent_supported __ro_after_init; int dma_cache_alignment __ro_after_init = ARCH_DMA_MINALIGN; EXPORT_SYMBOL_GPL(dma_cache_alignment); -struct riscv_nonstd_cache_ops noncoherent_cache_ops __ro_after_init = { - .wback = NULL, - .inv = NULL, - .wback_inv = NULL, -}; - static inline void arch_dma_cache_wback(phys_addr_t paddr, size_t size) { void *vaddr = phys_to_virt(paddr); @@ -162,12 +156,3 @@ void __init riscv_set_dma_cache_alignment(void) if (!noncoherent_supported) dma_cache_alignment = 1; } - -void riscv_noncoherent_register_cache_ops(const struct riscv_nonstd_cache_ops *ops) -{ - if (!ops) - return; - - noncoherent_cache_ops = *ops; -} -EXPORT_SYMBOL_GPL(riscv_noncoherent_register_cache_ops); diff --git a/arch/riscv/mm/ptdump.c b/arch/riscv/mm/ptdump.c index 20a9f991a6d74..e9090b38f8117 100644 --- a/arch/riscv/mm/ptdump.c +++ b/arch/riscv/mm/ptdump.c @@ -384,6 +384,9 @@ static int __init ptdump_init(void) kernel_ptd_info.base_addr = KERN_VIRT_START; + pg_level[1].name = pgtable_l5_enabled ? "P4D" : "PGD"; + pg_level[2].name = pgtable_l4_enabled ? "PUD" : "PGD"; + for (i = 0; i < ARRAY_SIZE(pg_level); i++) for (j = 0; j < ARRAY_SIZE(pte_bits); j++) pg_level[i].mask |= pte_bits[j].mask; diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index ae29e4392664a..bd4782f23f66d 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -252,13 +252,13 @@ config ARCH_SUPPORTS_KEXEC def_bool y config ARCH_SUPPORTS_KEXEC_FILE - def_bool CRYPTO && CRYPTO_SHA256 && CRYPTO_SHA256_S390 + def_bool y config ARCH_SUPPORTS_KEXEC_SIG def_bool MODULE_SIG_FORMAT config ARCH_SUPPORTS_KEXEC_PURGATORY - def_bool KEXEC_FILE + def_bool y config ARCH_SUPPORTS_CRASH_DUMP def_bool y diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 438cd92e60801..dd06086293106 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -834,7 +834,6 @@ CONFIG_DEBUG_IRQFLAGS=y CONFIG_DEBUG_LIST=y CONFIG_DEBUG_SG=y CONFIG_DEBUG_NOTIFIERS=y -CONFIG_DEBUG_CREDENTIALS=y CONFIG_RCU_TORTURE_TEST=m CONFIG_RCU_REF_SCALE_TEST=m CONFIG_RCU_CPU_STALL_TIMEOUT=300 diff --git a/arch/s390/include/asm/fpu/api.h b/arch/s390/include/asm/fpu/api.h index b714ed0ef6885..9acf48e53a87f 100644 --- a/arch/s390/include/asm/fpu/api.h +++ b/arch/s390/include/asm/fpu/api.h @@ -79,7 +79,7 @@ static inline int test_fp_ctl(u32 fpc) #define KERNEL_VXR_HIGH (KERNEL_VXR_V16V23|KERNEL_VXR_V24V31) #define KERNEL_VXR (KERNEL_VXR_LOW|KERNEL_VXR_HIGH) -#define KERNEL_FPR (KERNEL_FPC|KERNEL_VXR_V0V7) +#define KERNEL_FPR (KERNEL_FPC|KERNEL_VXR_LOW) struct kernel_fpu; diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index 05e51666db033..8d0b95c173129 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -666,6 +666,7 @@ static int __init ipl_init(void) &ipl_ccw_attr_group_lpar); break; case IPL_TYPE_ECKD: + case IPL_TYPE_ECKD_DUMP: rc = sysfs_create_group(&ipl_kset->kobj, &ipl_eckd_attr_group); break; case IPL_TYPE_FCP: diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index 906a7bfc2a787..20786f6883b29 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -21,10 +21,22 @@ #include #include +#include #include #define GMAP_SHADOW_FAKE_TABLE 1ULL +static struct page *gmap_alloc_crst(void) +{ + struct page *page; + + page = alloc_pages(GFP_KERNEL_ACCOUNT, CRST_ALLOC_ORDER); + if (!page) + return NULL; + arch_set_page_dat(page, CRST_ALLOC_ORDER); + return page; +} + /** * gmap_alloc - allocate and initialize a guest address space * @limit: maximum address of the gmap address space @@ -67,7 +79,7 @@ static struct gmap *gmap_alloc(unsigned long limit) spin_lock_init(&gmap->guest_table_lock); spin_lock_init(&gmap->shadow_lock); refcount_set(&gmap->ref_count, 1); - page = alloc_pages(GFP_KERNEL_ACCOUNT, CRST_ALLOC_ORDER); + page = gmap_alloc_crst(); if (!page) goto out_free; page->index = 0; @@ -308,7 +320,7 @@ static int gmap_alloc_table(struct gmap *gmap, unsigned long *table, unsigned long *new; /* since we dont free the gmap table until gmap_free we can unlock */ - page = alloc_pages(GFP_KERNEL_ACCOUNT, CRST_ALLOC_ORDER); + page = gmap_alloc_crst(); if (!page) return -ENOMEM; new = page_to_virt(page); @@ -1759,7 +1771,7 @@ int gmap_shadow_r2t(struct gmap *sg, unsigned long saddr, unsigned long r2t, BUG_ON(!gmap_is_shadow(sg)); /* Allocate a shadow region second table */ - page = alloc_pages(GFP_KERNEL_ACCOUNT, CRST_ALLOC_ORDER); + page = gmap_alloc_crst(); if (!page) return -ENOMEM; page->index = r2t & _REGION_ENTRY_ORIGIN; @@ -1843,7 +1855,7 @@ int gmap_shadow_r3t(struct gmap *sg, unsigned long saddr, unsigned long r3t, BUG_ON(!gmap_is_shadow(sg)); /* Allocate a shadow region second table */ - page = alloc_pages(GFP_KERNEL_ACCOUNT, CRST_ALLOC_ORDER); + page = gmap_alloc_crst(); if (!page) return -ENOMEM; page->index = r3t & _REGION_ENTRY_ORIGIN; @@ -1927,7 +1939,7 @@ int gmap_shadow_sgt(struct gmap *sg, unsigned long saddr, unsigned long sgt, BUG_ON(!gmap_is_shadow(sg) || (sgt & _REGION3_ENTRY_LARGE)); /* Allocate a shadow segment table */ - page = alloc_pages(GFP_KERNEL_ACCOUNT, CRST_ALLOC_ORDER); + page = gmap_alloc_crst(); if (!page) return -ENOMEM; page->index = sgt & _REGION_ENTRY_ORIGIN; @@ -2855,7 +2867,7 @@ int s390_replace_asce(struct gmap *gmap) if ((gmap->asce & _ASCE_TYPE_MASK) == _ASCE_TYPE_SEGMENT) return -EINVAL; - page = alloc_pages(GFP_KERNEL_ACCOUNT, CRST_ALLOC_ORDER); + page = gmap_alloc_crst(); if (!page) return -ENOMEM; page->index = 0; diff --git a/arch/s390/mm/page-states.c b/arch/s390/mm/page-states.c index 1e2ea706aa228..79a037f49f707 100644 --- a/arch/s390/mm/page-states.c +++ b/arch/s390/mm/page-states.c @@ -121,7 +121,7 @@ static void mark_kernel_pud(p4d_t *p4d, unsigned long addr, unsigned long end) continue; if (!pud_folded(*pud)) { page = phys_to_page(pud_val(*pud)); - for (i = 0; i < 3; i++) + for (i = 0; i < 4; i++) set_bit(PG_arch_1, &page[i].flags); } mark_kernel_pmd(pud, addr, next); @@ -142,7 +142,7 @@ static void mark_kernel_p4d(pgd_t *pgd, unsigned long addr, unsigned long end) continue; if (!p4d_folded(*p4d)) { page = phys_to_page(p4d_val(*p4d)); - for (i = 0; i < 3; i++) + for (i = 0; i < 4; i++) set_bit(PG_arch_1, &page[i].flags); } mark_kernel_pud(p4d, addr, next); @@ -164,7 +164,7 @@ static void mark_kernel_pgd(void) continue; if (!pgd_folded(*pgd)) { page = phys_to_page(pgd_val(*pgd)); - for (i = 0; i < 3; i++) + for (i = 0; i < 4; i++) set_bit(PG_arch_1, &page[i].flags); } mark_kernel_p4d(pgd, addr, next); @@ -181,6 +181,12 @@ void __init cmma_init_nodat(void) return; /* Mark pages used in kernel page tables */ mark_kernel_pgd(); + page = virt_to_page(&swapper_pg_dir); + for (i = 0; i < 4; i++) + set_bit(PG_arch_1, &page[i].flags); + page = virt_to_page(&invalid_pg_dir); + for (i = 0; i < 4; i++) + set_bit(PG_arch_1, &page[i].flags); /* Set all kernel pages not used for page tables to stable/no-dat */ for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, NULL) { diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c index 07fc660a24aa2..6396d6b06a3a2 100644 --- a/arch/s390/mm/pgalloc.c +++ b/arch/s390/mm/pgalloc.c @@ -146,6 +146,7 @@ struct page *page_table_alloc_pgste(struct mm_struct *mm) ptdesc = pagetable_alloc(GFP_KERNEL, 0); if (ptdesc) { table = (u64 *)ptdesc_to_virt(ptdesc); + arch_set_page_dat(virt_to_page(table), 0); memset64(table, _PAGE_INVALID, PTRS_PER_PTE); memset64(table + PTRS_PER_PTE, 0, PTRS_PER_PTE); } diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 3bd2ab2a9a344..5cb92941540b3 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -756,7 +756,7 @@ void ptep_zap_unused(struct mm_struct *mm, unsigned long addr, pte_clear(mm, addr, ptep); } if (reset) - pgste_val(pgste) &= ~_PGSTE_GPS_USAGE_MASK; + pgste_val(pgste) &= ~(_PGSTE_GPS_USAGE_MASK | _PGSTE_GPS_NODAT); pgste_set_unlock(ptep, pgste); preempt_enable(); } diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index 6957d2ed97bf0..6d276103c6d58 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -45,8 +46,11 @@ void *vmem_crst_alloc(unsigned long val) unsigned long *table; table = vmem_alloc_pages(CRST_ALLOC_ORDER); - if (table) - crst_table_init(table, val); + if (!table) + return NULL; + crst_table_init(table, val); + if (slab_is_available()) + arch_set_page_dat(virt_to_page(table), CRST_ALLOC_ORDER); return table; } diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 856ee1b3b7c70..2d318f426cc6c 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2048,7 +2048,7 @@ config ARCH_SUPPORTS_KEXEC def_bool y config ARCH_SUPPORTS_KEXEC_FILE - def_bool X86_64 && CRYPTO && CRYPTO_SHA256 + def_bool X86_64 config ARCH_SELECTS_KEXEC_FILE def_bool y @@ -2056,7 +2056,7 @@ config ARCH_SELECTS_KEXEC_FILE select HAVE_IMA_KEXEC if IMA config ARCH_SUPPORTS_KEXEC_PURGATORY - def_bool KEXEC_FILE + def_bool y config ARCH_SUPPORTS_KEXEC_SIG def_bool y diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c index 1d6b863c42b00..f3c75809fed26 100644 --- a/arch/x86/coco/tdx/tdx.c +++ b/arch/x86/coco/tdx/tdx.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c index 44340a1139e0b..959afa705e95c 100644 --- a/arch/x86/crypto/sha1_ssse3_glue.c +++ b/arch/x86/crypto/sha1_ssse3_glue.c @@ -24,8 +24,17 @@ #include #include #include +#include #include +static const struct x86_cpu_id module_cpu_ids[] = { + X86_MATCH_FEATURE(X86_FEATURE_AVX2, NULL), + X86_MATCH_FEATURE(X86_FEATURE_AVX, NULL), + X86_MATCH_FEATURE(X86_FEATURE_SSSE3, NULL), + {} +}; +MODULE_DEVICE_TABLE(x86cpu, module_cpu_ids); + static int sha1_update(struct shash_desc *desc, const u8 *data, unsigned int len, sha1_block_fn *sha1_xform) { @@ -301,6 +310,9 @@ static inline void unregister_sha1_ni(void) { } static int __init sha1_ssse3_mod_init(void) { + if (!x86_match_cpu(module_cpu_ids)) + return -ENODEV; + if (register_sha1_ssse3()) goto fail; diff --git a/arch/x86/crypto/sha256_ssse3_glue.c b/arch/x86/crypto/sha256_ssse3_glue.c index 3a5f6be7dbba4..d25235f0ccafc 100644 --- a/arch/x86/crypto/sha256_ssse3_glue.c +++ b/arch/x86/crypto/sha256_ssse3_glue.c @@ -38,11 +38,20 @@ #include #include #include +#include #include asmlinkage void sha256_transform_ssse3(struct sha256_state *state, const u8 *data, int blocks); +static const struct x86_cpu_id module_cpu_ids[] = { + X86_MATCH_FEATURE(X86_FEATURE_AVX2, NULL), + X86_MATCH_FEATURE(X86_FEATURE_AVX, NULL), + X86_MATCH_FEATURE(X86_FEATURE_SSSE3, NULL), + {} +}; +MODULE_DEVICE_TABLE(x86cpu, module_cpu_ids); + static int _sha256_update(struct shash_desc *desc, const u8 *data, unsigned int len, sha256_block_fn *sha256_xform) { @@ -366,6 +375,9 @@ static inline void unregister_sha256_ni(void) { } static int __init sha256_ssse3_mod_init(void) { + if (!x86_match_cpu(module_cpu_ids)) + return -ENODEV; + if (register_sha256_ssse3()) goto fail; diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 93c60c0c9d4a7..9c0b26ae51069 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -25,6 +25,7 @@ #include #endif +#include #include #include #include @@ -96,6 +97,10 @@ static __always_inline int syscall_32_enter(struct pt_regs *regs) return (int)regs->orig_ax; } +#ifdef CONFIG_IA32_EMULATION +bool __ia32_enabled __ro_after_init = true; +#endif + /* * Invoke a 32-bit syscall. Called with IRQs on in CONTEXT_KERNEL. */ @@ -115,7 +120,96 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs, int nr) } } -/* Handles int $0x80 */ +#ifdef CONFIG_IA32_EMULATION +static __always_inline bool int80_is_external(void) +{ + const unsigned int offs = (0x80 / 32) * 0x10; + const u32 bit = BIT(0x80 % 32); + + /* The local APIC on XENPV guests is fake */ + if (cpu_feature_enabled(X86_FEATURE_XENPV)) + return false; + + /* + * If vector 0x80 is set in the APIC ISR then this is an external + * interrupt. Either from broken hardware or injected by a VMM. + * + * Note: In guest mode this is only valid for secure guests where + * the secure module fully controls the vAPIC exposed to the guest. + */ + return apic_read(APIC_ISR + offs) & bit; +} + +/** + * int80_emulation - 32-bit legacy syscall entry + * + * This entry point can be used by 32-bit and 64-bit programs to perform + * 32-bit system calls. Instances of INT $0x80 can be found inline in + * various programs and libraries. It is also used by the vDSO's + * __kernel_vsyscall fallback for hardware that doesn't support a faster + * entry method. Restarted 32-bit system calls also fall back to INT + * $0x80 regardless of what instruction was originally used to do the + * system call. + * + * This is considered a slow path. It is not used by most libc + * implementations on modern hardware except during process startup. + * + * The arguments for the INT $0x80 based syscall are on stack in the + * pt_regs structure: + * eax: system call number + * ebx, ecx, edx, esi, edi, ebp: arg1 - arg 6 + */ +DEFINE_IDTENTRY_RAW(int80_emulation) +{ + int nr; + + /* Kernel does not use INT $0x80! */ + if (unlikely(!user_mode(regs))) { + irqentry_enter(regs); + instrumentation_begin(); + panic("Unexpected external interrupt 0x80\n"); + } + + /* + * Establish kernel context for instrumentation, including for + * int80_is_external() below which calls into the APIC driver. + * Identical for soft and external interrupts. + */ + enter_from_user_mode(regs); + + instrumentation_begin(); + add_random_kstack_offset(); + + /* Validate that this is a soft interrupt to the extent possible */ + if (unlikely(int80_is_external())) + panic("Unexpected external interrupt 0x80\n"); + + /* + * The low level idtentry code pushed -1 into regs::orig_ax + * and regs::ax contains the syscall number. + * + * User tracing code (ptrace or signal handlers) might assume + * that the regs::orig_ax contains a 32-bit number on invoking + * a 32-bit syscall. + * + * Establish the syscall convention by saving the 32bit truncated + * syscall number in regs::orig_ax and by invalidating regs::ax. + */ + regs->orig_ax = regs->ax & GENMASK(31, 0); + regs->ax = -ENOSYS; + + nr = syscall_32_enter(regs); + + local_irq_enable(); + nr = syscall_enter_from_user_mode_work(regs, nr); + do_syscall_32_irqs_on(regs, nr); + + instrumentation_end(); + syscall_exit_to_user_mode(regs); +} +#else /* CONFIG_IA32_EMULATION */ + +/* Handles int $0x80 on a 32bit kernel */ __visible noinstr void do_int80_syscall_32(struct pt_regs *regs) { int nr = syscall_32_enter(regs); @@ -134,6 +228,7 @@ __visible noinstr void do_int80_syscall_32(struct pt_regs *regs) instrumentation_end(); syscall_exit_to_user_mode(regs); } +#endif /* !CONFIG_IA32_EMULATION */ static noinstr bool __do_fast_syscall_32(struct pt_regs *regs) { diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 70150298f8bdf..4e88f84387061 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -276,80 +276,3 @@ SYM_INNER_LABEL(entry_SYSRETL_compat_end, SYM_L_GLOBAL) ANNOTATE_NOENDBR int3 SYM_CODE_END(entry_SYSCALL_compat) - -/* - * 32-bit legacy system call entry. - * - * 32-bit x86 Linux system calls traditionally used the INT $0x80 - * instruction. INT $0x80 lands here. - * - * This entry point can be used by 32-bit and 64-bit programs to perform - * 32-bit system calls. Instances of INT $0x80 can be found inline in - * various programs and libraries. It is also used by the vDSO's - * __kernel_vsyscall fallback for hardware that doesn't support a faster - * entry method. Restarted 32-bit system calls also fall back to INT - * $0x80 regardless of what instruction was originally used to do the - * system call. - * - * This is considered a slow path. It is not used by most libc - * implementations on modern hardware except during process startup. - * - * Arguments: - * eax system call number - * ebx arg1 - * ecx arg2 - * edx arg3 - * esi arg4 - * edi arg5 - * ebp arg6 - */ -SYM_CODE_START(entry_INT80_compat) - UNWIND_HINT_ENTRY - ENDBR - /* - * Interrupts are off on entry. - */ - ASM_CLAC /* Do this early to minimize exposure */ - ALTERNATIVE "swapgs", "", X86_FEATURE_XENPV - - /* - * User tracing code (ptrace or signal handlers) might assume that - * the saved RAX contains a 32-bit number when we're invoking a 32-bit - * syscall. Just in case the high bits are nonzero, zero-extend - * the syscall number. (This could almost certainly be deleted - * with no ill effects.) - */ - movl %eax, %eax - - /* switch to thread stack expects orig_ax and rdi to be pushed */ - pushq %rax /* pt_regs->orig_ax */ - - /* Need to switch before accessing the thread stack. */ - SWITCH_TO_KERNEL_CR3 scratch_reg=%rax - - /* In the Xen PV case we already run on the thread stack. */ - ALTERNATIVE "", "jmp .Lint80_keep_stack", X86_FEATURE_XENPV - - movq %rsp, %rax - movq PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %rsp - - pushq 5*8(%rax) /* regs->ss */ - pushq 4*8(%rax) /* regs->rsp */ - pushq 3*8(%rax) /* regs->eflags */ - pushq 2*8(%rax) /* regs->cs */ - pushq 1*8(%rax) /* regs->ip */ - pushq 0*8(%rax) /* regs->orig_ax */ -.Lint80_keep_stack: - - PUSH_AND_CLEAR_REGS rax=$-ENOSYS - UNWIND_HINT_REGS - - cld - - IBRS_ENTER - UNTRAIN_RET - - movq %rsp, %rdi - call do_int80_syscall_32 - jmp swapgs_restore_regs_and_return_to_usermode -SYM_CODE_END(entry_INT80_compat) diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 21556ad87f4ba..8f3a4d16bb791 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -286,15 +287,31 @@ static int hv_cpu_die(unsigned int cpu) static int __init hv_pci_init(void) { - int gen2vm = efi_enabled(EFI_BOOT); + bool gen2vm = efi_enabled(EFI_BOOT); /* - * For Generation-2 VM, we exit from pci_arch_init() by returning 0. - * The purpose is to suppress the harmless warning: + * A Generation-2 VM doesn't support legacy PCI/PCIe, so both + * raw_pci_ops and raw_pci_ext_ops are NULL, and pci_subsys_init() -> + * pcibios_init() doesn't call pcibios_resource_survey() -> + * e820__reserve_resources_late(); as a result, any emulated persistent + * memory of E820_TYPE_PRAM (12) via the kernel parameter + * memmap=nn[KMG]!ss is not added into iomem_resource and hence can't be + * detected by register_e820_pmem(). Fix this by directly calling + * e820__reserve_resources_late() here: e820__reserve_resources_late() + * depends on e820__reserve_resources(), which has been called earlier + * from setup_arch(). Note: e820__reserve_resources_late() also adds + * any memory of E820_TYPE_PMEM (7) into iomem_resource, and + * acpi_nfit_register_region() -> acpi_nfit_insert_resource() -> + * region_intersects() returns REGION_INTERSECTS, so the memory of + * E820_TYPE_PMEM won't get added twice. + * + * We return 0 here so that pci_arch_init() won't print the warning: * "PCI: Fatal: No config space access function found" */ - if (gen2vm) + if (gen2vm) { + e820__reserve_resources_late(); return 0; + } /* For Generation-1 VM, we'll proceed in pci_arch_init(). */ return 1; diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index c8a7fc23f63c6..f896eed4516c7 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -16,6 +16,9 @@ #include #include #include +#include + +#include #ifdef CONFIG_ACPI_APEI # include @@ -127,6 +130,17 @@ static inline void arch_acpi_set_proc_cap_bits(u32 *cap) if (!cpu_has(c, X86_FEATURE_MWAIT) || boot_option_idle_override == IDLE_NOMWAIT) *cap &= ~(ACPI_PROC_CAP_C_C1_FFH | ACPI_PROC_CAP_C_C2C3_FFH); + + if (xen_initial_domain()) { + /* + * When Linux is running as Xen dom0, the hypervisor is the + * entity in charge of the processor power management, and so + * Xen needs to check the OS capabilities reported in the + * processor capabilities buffer matches what the hypervisor + * driver supports. + */ + xen_sanitize_proc_cap_bits(cap); + } } static inline bool acpi_has_cpu_in_madt(void) diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 9c4da699e11af..65f79092c9d9e 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -58,7 +58,7 @@ #define ANNOTATE_IGNORE_ALTERNATIVE \ "999:\n\t" \ ".pushsection .discard.ignore_alts\n\t" \ - ".long 999b - .\n\t" \ + ".long 999b\n\t" \ ".popsection\n\t" /* @@ -352,7 +352,7 @@ static inline int alternatives_text_reserved(void *start, void *end) .macro ANNOTATE_IGNORE_ALTERNATIVE .Lannotate_\@: .pushsection .discard.ignore_alts - .long .Lannotate_\@ - . + .long .Lannotate_\@ .popsection .endm diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h index fada857f0a1ed..9805629479d96 100644 --- a/arch/x86/include/asm/ia32.h +++ b/arch/x86/include/asm/ia32.h @@ -68,6 +68,27 @@ extern void ia32_pick_mmap_layout(struct mm_struct *mm); #endif -#endif /* CONFIG_IA32_EMULATION */ +extern bool __ia32_enabled; + +static inline bool ia32_enabled(void) +{ + return __ia32_enabled; +} + +static inline void ia32_disable(void) +{ + __ia32_enabled = false; +} + +#else /* !CONFIG_IA32_EMULATION */ + +static inline bool ia32_enabled(void) +{ + return IS_ENABLED(CONFIG_X86_32); +} + +static inline void ia32_disable(void) {} + +#endif #endif /* _ASM_X86_IA32_H */ diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h index 05fd175cec7d5..13639e57e1f8a 100644 --- a/arch/x86/include/asm/idtentry.h +++ b/arch/x86/include/asm/idtentry.h @@ -569,6 +569,10 @@ DECLARE_IDTENTRY_RAW(X86_TRAP_UD, exc_invalid_op); DECLARE_IDTENTRY_RAW(X86_TRAP_BP, exc_int3); DECLARE_IDTENTRY_RAW_ERRORCODE(X86_TRAP_PF, exc_page_fault); +#if defined(CONFIG_IA32_EMULATION) +DECLARE_IDTENTRY_RAW(IA32_SYSCALL_VECTOR, int80_emulation); +#endif + #ifdef CONFIG_X86_MCE #ifdef CONFIG_X86_64 DECLARE_IDTENTRY_MCE(X86_TRAP_MC, exc_machine_check); diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index e3054e3e46d52..9b419f0de713c 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -108,6 +108,7 @@ KVM_X86_OP_OPTIONAL(vcpu_blocking) KVM_X86_OP_OPTIONAL(vcpu_unblocking) KVM_X86_OP_OPTIONAL(pi_update_irte) KVM_X86_OP_OPTIONAL(pi_start_assignment) +KVM_X86_OP_OPTIONAL(apicv_pre_state_restore) KVM_X86_OP_OPTIONAL(apicv_post_state_restore) KVM_X86_OP_OPTIONAL_RET0(dy_apicv_has_pending_interrupt) KVM_X86_OP_OPTIONAL(set_hv_timer) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 70d139406bc80..fb9f5fa96cc96 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1708,6 +1708,7 @@ struct kvm_x86_ops { int (*pi_update_irte)(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, bool set); void (*pi_start_assignment)(struct kvm *kvm); + void (*apicv_pre_state_restore)(struct kvm_vcpu *vcpu); void (*apicv_post_state_restore)(struct kvm_vcpu *vcpu); bool (*dy_apicv_has_pending_interrupt)(struct kvm_vcpu *vcpu); diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index b37abb55e948b..389f9594746ef 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -553,6 +553,7 @@ #define MSR_AMD64_CPUID_FN_1 0xc0011004 #define MSR_AMD64_LS_CFG 0xc0011020 #define MSR_AMD64_DC_CFG 0xc0011022 +#define MSR_AMD64_TW_CFG 0xc0011023 #define MSR_AMD64_DE_CFG 0xc0011029 #define MSR_AMD64_DE_CFG_LFENCE_SERIALIZE_BIT 1 diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 197ff4f4d1ceb..0396458c201f8 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -196,7 +196,7 @@ .macro ANNOTATE_RETPOLINE_SAFE .Lhere_\@: .pushsection .discard.retpoline_safe - .long .Lhere_\@ - . + .long .Lhere_\@ .popsection .endm @@ -334,7 +334,7 @@ #define ANNOTATE_RETPOLINE_SAFE \ "999:\n\t" \ ".pushsection .discard.retpoline_safe\n\t" \ - ".long 999b - .\n\t" \ + ".long 999b\n\t" \ ".popsection\n\t" typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE]; diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h index e3bae2b60a0db..ef2844d691735 100644 --- a/arch/x86/include/asm/numa.h +++ b/arch/x86/include/asm/numa.h @@ -12,13 +12,6 @@ #define NR_NODE_MEMBLKS (MAX_NUMNODES*2) -/* - * Too small node sizes may confuse the VM badly. Usually they - * result from BIOS bugs. So dont recognize nodes as standalone - * NUMA entities that have less than this amount of RAM listed: - */ -#define NODE_MIN_SIZE (4*1024*1024) - extern int numa_off; /* diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h index 12ef86b19910d..84294b66b9162 100644 --- a/arch/x86/include/asm/proto.h +++ b/arch/x86/include/asm/proto.h @@ -32,10 +32,6 @@ void entry_SYSCALL_compat(void); void entry_SYSCALL_compat_safe_stack(void); void entry_SYSRETL_compat_unsafe_stack(void); void entry_SYSRETL_compat_end(void); -void entry_INT80_compat(void); -#ifdef CONFIG_XEN_PV -void xen_entry_INT80_compat(void); -#endif #endif void x86_configure_nx(void); diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h index 7048dfacc04b2..a9088250770f2 100644 --- a/arch/x86/include/asm/xen/hypervisor.h +++ b/arch/x86/include/asm/xen/hypervisor.h @@ -100,4 +100,13 @@ static inline void leave_lazy(enum xen_lazy_mode mode) enum xen_lazy_mode xen_get_lazy_mode(void); +#if defined(CONFIG_XEN_DOM0) && defined(CONFIG_ACPI) +void xen_sanitize_proc_cap_bits(uint32_t *buf); +#else +static inline void xen_sanitize_proc_cap_bits(uint32_t *buf) +{ + BUG(); +} +#endif + #endif /* _ASM_X86_XEN_HYPERVISOR_H */ diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 73be3931e4f06..aae7456ece070 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -255,6 +255,16 @@ static void __init_or_module noinline optimize_nops(u8 *instr, size_t len) } } +static void __init_or_module noinline optimize_nops_inplace(u8 *instr, size_t len) +{ + unsigned long flags; + + local_irq_save(flags); + optimize_nops(instr, len); + sync_core(); + local_irq_restore(flags); +} + /* * In this context, "source" is where the instructions are placed in the * section .altinstr_replacement, for example during kernel build by the @@ -438,7 +448,7 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start, * patch if feature is *NOT* present. */ if (!boot_cpu_has(a->cpuid) == !(a->flags & ALT_FLAG_NOT)) { - optimize_nops(instr, a->instrlen); + optimize_nops_inplace(instr, a->instrlen); continue; } @@ -1685,8 +1695,8 @@ void __init_or_module text_poke_early(void *addr, const void *opcode, } else { local_irq_save(flags); memcpy(addr, opcode, len); - local_irq_restore(flags); sync_core(); + local_irq_restore(flags); /* * Could also do a CLFLUSH here to speed up CPU recovery; but diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c index 6b6b711678fe0..d9651f15ae4f7 100644 --- a/arch/x86/kernel/apic/msi.c +++ b/arch/x86/kernel/apic/msi.c @@ -55,14 +55,14 @@ msi_set_affinity(struct irq_data *irqd, const struct cpumask *mask, bool force) * caused by the non-atomic update of the address/data pair. * * Direct update is possible when: - * - The MSI is maskable (remapped MSI does not use this code path)). - * The quirk bit is not set in this case. + * - The MSI is maskable (remapped MSI does not use this code path). + * The reservation mode bit is set in this case. * - The new vector is the same as the old vector * - The old vector is MANAGED_IRQ_SHUTDOWN_VECTOR (interrupt starts up) * - The interrupt is not yet started up * - The new destination CPU is the same as the old destination CPU */ - if (!irqd_msi_nomask_quirk(irqd) || + if (!irqd_can_reserve(irqd) || cfg->vector == old_cfg.vector || old_cfg.vector == MANAGED_IRQ_SHUTDOWN_VECTOR || !irqd_is_started(irqd) || @@ -215,8 +215,6 @@ static bool x86_init_dev_msi_info(struct device *dev, struct irq_domain *domain, if (WARN_ON_ONCE(domain != real_parent)) return false; info->chip->irq_set_affinity = msi_set_affinity; - /* See msi_set_affinity() for the gory details */ - info->flags |= MSI_FLAG_NOMASK_QUIRK; break; case DOMAIN_BUS_DMAR: case DOMAIN_BUS_AMDVI: diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index ece2b5b7b0fe4..6e4f23f314ac5 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -1315,6 +1315,9 @@ static void zenbleed_check_cpu(void *unused) void amd_check_microcode(void) { + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) + return; + on_each_cpu(zenbleed_check_cpu, NULL, 1); } diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index a55a3864df1c9..0bc55472f303a 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -2422,10 +2422,8 @@ static void __init srso_select_mitigation(void) setup_force_cpu_cap(X86_FEATURE_SRSO_NO); return; } - } - if (retbleed_mitigation == RETBLEED_MITIGATION_IBPB) { - if (has_microcode) { + if (retbleed_mitigation == RETBLEED_MITIGATION_IBPB) { srso_mitigation = SRSO_MITIGATION_IBPB; goto out; } diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c index defdc594be14d..a7b3ef4c4de91 100644 --- a/arch/x86/kernel/cpu/hygon.c +++ b/arch/x86/kernel/cpu/hygon.c @@ -87,8 +87,12 @@ static void hygon_get_topology(struct cpuinfo_x86 *c) if (!err) c->x86_coreid_bits = get_count_order(c->x86_max_cores); - /* Socket ID is ApicId[6] for these processors. */ - c->phys_proc_id = c->apicid >> APICID_SOCKET_ID_BIT; + /* + * Socket ID is ApicId[6] for the processors with model <= 0x3 + * when running on host. + */ + if (!boot_cpu_has(X86_FEATURE_HYPERVISOR) && c->x86_model <= 0x3) + c->phys_proc_id = c->apicid >> APICID_SOCKET_ID_BIT; cacheinfo_hygon_init_llc_id(c, cpu); } else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) { diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index ea6995920b7aa..e6eaee8509cee 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -256,6 +256,22 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) testl $X2APIC_ENABLE, %eax jnz .Lread_apicid_msr +#ifdef CONFIG_X86_X2APIC + /* + * If system is in X2APIC mode then MMIO base might not be + * mapped causing the MMIO read below to fault. Faults can't + * be handled at that point. + */ + cmpl $0, x2apic_mode(%rip) + jz .Lread_apicid_mmio + + /* Force the AP into X2APIC mode. */ + orl $X2APIC_ENABLE, %eax + wrmsr + jmp .Lread_apicid_msr +#endif + +.Lread_apicid_mmio: /* Read the APIC ID from the fix-mapped MMIO space. */ movq apic_mmio_base(%rip), %rcx addq $APIC_ID, %rcx diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c index b786d48f5a0fa..fc77a96040b7e 100644 --- a/arch/x86/kernel/idt.c +++ b/arch/x86/kernel/idt.c @@ -117,7 +117,7 @@ static const __initconst struct idt_data def_idts[] = { SYSG(X86_TRAP_OF, asm_exc_overflow), #if defined(CONFIG_IA32_EMULATION) - SYSG(IA32_SYSCALL_VECTOR, entry_INT80_compat), + SYSG(IA32_SYSCALL_VECTOR, asm_int80_emulation), #elif defined(CONFIG_X86_32) SYSG(IA32_SYSCALL_VECTOR, entry_INT80_32), #endif diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c index 6395bfd87b68b..d87c6ff1f5136 100644 --- a/arch/x86/kernel/sev.c +++ b/arch/x86/kernel/sev.c @@ -1234,10 +1234,6 @@ void setup_ghcb(void) if (!cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT)) return; - /* First make sure the hypervisor talks a supported protocol. */ - if (!sev_es_negotiate_protocol()) - sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ); - /* * Check whether the runtime #VC exception handler is active. It uses * the per-CPU GHCB page which is set up by sev_es_init_vc_handling(). @@ -1254,6 +1250,13 @@ void setup_ghcb(void) return; } + /* + * Make sure the hypervisor talks a supported protocol. + * This gets called only in the BSP boot phase. + */ + if (!sev_es_negotiate_protocol()) + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ); + /* * Clear the boot_ghcb. The first exception comes in before the bss * section is cleared. diff --git a/arch/x86/kernel/signal_64.c b/arch/x86/kernel/signal_64.c index cacf2ede62175..23d8aaf8d9fd1 100644 --- a/arch/x86/kernel/signal_64.c +++ b/arch/x86/kernel/signal_64.c @@ -175,9 +175,6 @@ int x64_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs) frame = get_sigframe(ksig, regs, sizeof(struct rt_sigframe), &fp); uc_flags = frame_uc_flags(regs); - if (setup_signal_shadow_stack(ksig)) - return -EFAULT; - if (!user_access_begin(frame, sizeof(*frame))) return -EFAULT; @@ -198,6 +195,9 @@ int x64_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs) return -EFAULT; } + if (setup_signal_shadow_stack(ksig)) + return -EFAULT; + /* Set up registers for signal handler */ regs->di = ksig->sig; /* In case the signal handler was declared without prototypes */ diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 7c2dac6824e26..238afd7335e46 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -727,10 +727,12 @@ static int stimer_set_count(struct kvm_vcpu_hv_stimer *stimer, u64 count, stimer_cleanup(stimer); stimer->count = count; - if (stimer->count == 0) - stimer->config.enable = 0; - else if (stimer->config.auto_enable) - stimer->config.enable = 1; + if (!host) { + if (stimer->count == 0) + stimer->config.enable = 0; + else if (stimer->config.auto_enable) + stimer->config.enable = 1; + } if (stimer->config.enable) stimer_mark_pending(stimer, false); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 3e977dbbf9933..245b20973caee 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2444,22 +2444,22 @@ EXPORT_SYMBOL_GPL(kvm_lapic_set_eoi); void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset) { struct kvm_lapic *apic = vcpu->arch.apic; - u64 val; /* - * ICR is a single 64-bit register when x2APIC is enabled. For legacy - * xAPIC, ICR writes need to go down the common (slightly slower) path - * to get the upper half from ICR2. + * ICR is a single 64-bit register when x2APIC is enabled, all others + * registers hold 32-bit values. For legacy xAPIC, ICR writes need to + * go down the common path to get the upper half from ICR2. + * + * Note, using the write helpers may incur an unnecessary write to the + * virtual APIC state, but KVM needs to conditionally modify the value + * in certain cases, e.g. to clear the ICR busy bit. The cost of extra + * conditional branches is likely a wash relative to the cost of the + * maybe-unecessary write, and both are in the noise anyways. */ - if (apic_x2apic_mode(apic) && offset == APIC_ICR) { - val = kvm_lapic_get_reg64(apic, APIC_ICR); - kvm_apic_send_ipi(apic, (u32)val, (u32)(val >> 32)); - trace_kvm_apic_write(APIC_ICR, val); - } else { - /* TODO: optimize to just emulate side effect w/o one more write */ - val = kvm_lapic_get_reg(apic, offset); - kvm_lapic_reg_write(apic, offset, (u32)val); - } + if (apic_x2apic_mode(apic) && offset == APIC_ICR) + kvm_x2apic_icr_write(apic, kvm_lapic_get_reg64(apic, APIC_ICR)); + else + kvm_lapic_reg_write(apic, offset, kvm_lapic_get_reg(apic, offset)); } EXPORT_SYMBOL_GPL(kvm_apic_write_nodecode); @@ -2670,6 +2670,8 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) u64 msr_val; int i; + static_call_cond(kvm_x86_apicv_pre_state_restore)(vcpu); + if (!init_event) { msr_val = APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE; if (kvm_vcpu_is_reset_bsp(vcpu)) @@ -2981,6 +2983,8 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) struct kvm_lapic *apic = vcpu->arch.apic; int r; + static_call_cond(kvm_x86_apicv_pre_state_restore)(vcpu); + kvm_lapic_set_base(vcpu, vcpu->arch.apic_base); /* set SPIV separately to get count of SW disabled APICs right */ apic_set_spiv(apic, *((u32 *)(s->regs + APIC_SPIV))); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index beea99c8e8e05..77f1eeefcd34b 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1873,15 +1873,17 @@ void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) bool old_paging = is_paging(vcpu); #ifdef CONFIG_X86_64 - if (vcpu->arch.efer & EFER_LME && !vcpu->arch.guest_state_protected) { + if (vcpu->arch.efer & EFER_LME) { if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) { vcpu->arch.efer |= EFER_LMA; - svm->vmcb->save.efer |= EFER_LMA | EFER_LME; + if (!vcpu->arch.guest_state_protected) + svm->vmcb->save.efer |= EFER_LMA | EFER_LME; } if (is_paging(vcpu) && !(cr0 & X86_CR0_PG)) { vcpu->arch.efer &= ~EFER_LMA; - svm->vmcb->save.efer &= ~(EFER_LMA | EFER_LME); + if (!vcpu->arch.guest_state_protected) + svm->vmcb->save.efer &= ~(EFER_LMA | EFER_LME); } } #endif diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 72e3943f36935..9bba5352582c3 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -6912,7 +6912,7 @@ static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) vmcs_write64(EOI_EXIT_BITMAP3, eoi_exit_bitmap[3]); } -static void vmx_apicv_post_state_restore(struct kvm_vcpu *vcpu) +static void vmx_apicv_pre_state_restore(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -8286,7 +8286,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .set_apic_access_page_addr = vmx_set_apic_access_page_addr, .refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl, .load_eoi_exitmap = vmx_load_eoi_exitmap, - .apicv_post_state_restore = vmx_apicv_post_state_restore, + .apicv_pre_state_restore = vmx_apicv_pre_state_restore, .required_apicv_inhibits = VMX_REQUIRED_APICV_INHIBITS, .hwapic_irr_update = vmx_hwapic_irr_update, .hwapic_isr_update = vmx_hwapic_isr_update, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 41cce5031126a..e179db7c17dad 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3641,6 +3641,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_AMD64_PATCH_LOADER: case MSR_AMD64_BU_CFG2: case MSR_AMD64_DC_CFG: + case MSR_AMD64_TW_CFG: case MSR_F15H_EX_CFG: break; @@ -4065,6 +4066,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_AMD64_BU_CFG2: case MSR_IA32_PERF_CTL: case MSR_AMD64_DC_CFG: + case MSR_AMD64_TW_CFG: case MSR_F15H_EX_CFG: /* * Intel Sandy Bridge CPUs must support the RAPL (running average power diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c index 6faea41e99b6b..45ff95264a097 100644 --- a/arch/x86/mm/mem_encrypt_amd.c +++ b/arch/x86/mm/mem_encrypt_amd.c @@ -34,6 +34,7 @@ #include #include #include +#include #include "mm_internal.h" @@ -517,6 +518,16 @@ void __init sme_early_init(void) */ if (sev_status & MSR_AMD64_SEV_ES_ENABLED) x86_cpuinit.parallel_bringup = false; + + /* + * The VMM is capable of injecting interrupt 0x80 and triggering the + * compatibility syscall path. + * + * By default, the 32-bit emulation is disabled in order to ensure + * the safety of the VM. + */ + if (sev_status & MSR_AMD64_SEV_ENABLED) + ia32_disable(); } void __init mem_encrypt_free_decrypted_mem(void) diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index c01c5506fd4ae..aa39d678fe81d 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -602,13 +602,6 @@ static int __init numa_register_memblks(struct numa_meminfo *mi) if (start >= end) continue; - /* - * Don't confuse VM with a node that doesn't have the - * minimum amount of memory: - */ - if (end && (end - start) < NODE_MIN_SIZE) - continue; - alloc_node_data(nid); } diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 52f36c48c1b9e..955133077c105 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -2929,3 +2929,49 @@ void bpf_jit_free(struct bpf_prog *prog) bpf_prog_unlock_free(prog); } + +void bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke, + struct bpf_prog *new, struct bpf_prog *old) +{ + u8 *old_addr, *new_addr, *old_bypass_addr; + int ret; + + old_bypass_addr = old ? NULL : poke->bypass_addr; + old_addr = old ? (u8 *)old->bpf_func + poke->adj_off : NULL; + new_addr = new ? (u8 *)new->bpf_func + poke->adj_off : NULL; + + /* + * On program loading or teardown, the program's kallsym entry + * might not be in place, so we use __bpf_arch_text_poke to skip + * the kallsyms check. + */ + if (new) { + ret = __bpf_arch_text_poke(poke->tailcall_target, + BPF_MOD_JUMP, + old_addr, new_addr); + BUG_ON(ret < 0); + if (!old) { + ret = __bpf_arch_text_poke(poke->tailcall_bypass, + BPF_MOD_JUMP, + poke->bypass_addr, + NULL); + BUG_ON(ret < 0); + } + } else { + ret = __bpf_arch_text_poke(poke->tailcall_bypass, + BPF_MOD_JUMP, + old_bypass_addr, + poke->bypass_addr); + BUG_ON(ret < 0); + /* let other CPUs finish the execution of program + * so that it will not possible to expose them + * to invalid nop, stack unwind, nop state + */ + if (!ret) + synchronize_rcu(); + ret = __bpf_arch_text_poke(poke->tailcall_target, + BPF_MOD_JUMP, + old_addr, NULL); + BUG_ON(ret < 0); + } +} diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index e3ec02e6ac9fe..f347c20247d30 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -3,9 +3,11 @@ * Exceptions for specific devices. Usually work-arounds for fatal design flaws. */ +#include #include #include #include +#include #include #include #include @@ -904,3 +906,60 @@ static void chromeos_fixup_apl_pci_l1ss_capability(struct pci_dev *dev) } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x5ad6, chromeos_save_apl_pci_l1ss_capability); DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL, 0x5ad6, chromeos_fixup_apl_pci_l1ss_capability); + +#ifdef CONFIG_SUSPEND +/* + * Root Ports on some AMD SoCs advertise PME_Support for D3hot and D3cold, but + * if the SoC is put into a hardware sleep state by the amd-pmc driver, the + * Root Ports don't generate wakeup interrupts for USB devices. + * + * When suspending, remove D3hot and D3cold from the PME_Support advertised + * by the Root Port so we don't use those states if we're expecting wakeup + * interrupts. Restore the advertised PME_Support when resuming. + */ +static void amd_rp_pme_suspend(struct pci_dev *dev) +{ + struct pci_dev *rp; + + /* + * PM_SUSPEND_ON means we're doing runtime suspend, which means + * amd-pmc will not be involved so PMEs during D3 work as advertised. + * + * The PMEs *do* work if amd-pmc doesn't put the SoC in the hardware + * sleep state, but we assume amd-pmc is always present. + */ + if (pm_suspend_target_state == PM_SUSPEND_ON) + return; + + rp = pcie_find_root_port(dev); + if (!rp->pm_cap) + return; + + rp->pme_support &= ~((PCI_PM_CAP_PME_D3hot|PCI_PM_CAP_PME_D3cold) >> + PCI_PM_CAP_PME_SHIFT); + dev_info_once(&rp->dev, "quirk: disabling D3cold for suspend\n"); +} + +static void amd_rp_pme_resume(struct pci_dev *dev) +{ + struct pci_dev *rp; + u16 pmc; + + rp = pcie_find_root_port(dev); + if (!rp->pm_cap) + return; + + pci_read_config_word(rp, rp->pm_cap + PCI_PM_PMC, &pmc); + rp->pme_support = FIELD_GET(PCI_PM_CAP_PME_MASK, pmc); +} +/* Rembrandt (yellow_carp) */ +DECLARE_PCI_FIXUP_SUSPEND(PCI_VENDOR_ID_AMD, 0x162e, amd_rp_pme_suspend); +DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x162e, amd_rp_pme_resume); +DECLARE_PCI_FIXUP_SUSPEND(PCI_VENDOR_ID_AMD, 0x162f, amd_rp_pme_suspend); +DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x162f, amd_rp_pme_resume); +/* Phoenix (pink_sardine) */ +DECLARE_PCI_FIXUP_SUSPEND(PCI_VENDOR_ID_AMD, 0x1668, amd_rp_pme_suspend); +DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x1668, amd_rp_pme_resume); +DECLARE_PCI_FIXUP_SUSPEND(PCI_VENDOR_ID_AMD, 0x1669, amd_rp_pme_suspend); +DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x1669, amd_rp_pme_resume); +#endif /* CONFIG_SUSPEND */ diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig index 9b1ec5d8c99c8..a65fc2ae15b49 100644 --- a/arch/x86/xen/Kconfig +++ b/arch/x86/xen/Kconfig @@ -9,6 +9,7 @@ config XEN select PARAVIRT_CLOCK select X86_HV_CALLBACK_VECTOR depends on X86_64 || (X86_32 && X86_PAE) + depends on X86_64 || (X86_GENERIC || MPENTIUM4 || MCORE2 || MATOM || MK8) depends on X86_LOCAL_APIC && X86_TSC help This is the Linux Xen port. Enabling this will allow the diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 0337392a31214..3c61bb98c10e2 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -33,9 +33,12 @@ EXPORT_SYMBOL_GPL(hypercall_page); * and xen_vcpu_setup for details. By default it points to share_info->vcpu_info * but during boot it is switched to point to xen_vcpu_info. * The pointer is used in xen_evtchn_do_upcall to acknowledge pending events. + * Make sure that xen_vcpu_info doesn't cross a page boundary by making it + * cache-line aligned (the struct is guaranteed to have a size of 64 bytes, + * which matches the cache line size of 64-bit x86 processors). */ DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu); -DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info); +DEFINE_PER_CPU_ALIGNED(struct vcpu_info, xen_vcpu_info); /* Linux <-> Xen vCPU id mapping */ DEFINE_PER_CPU(uint32_t, xen_vcpu_id); @@ -160,6 +163,7 @@ void xen_vcpu_setup(int cpu) int err; struct vcpu_info *vcpup; + BUILD_BUG_ON(sizeof(*vcpup) > SMP_CACHE_BYTES); BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info); /* diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index bbbfdd495ebd3..aeb33e0a3f763 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -704,7 +704,7 @@ static struct trap_array_entry trap_array[] = { TRAP_ENTRY(exc_int3, false ), TRAP_ENTRY(exc_overflow, false ), #ifdef CONFIG_IA32_EMULATION - { entry_INT80_compat, xen_entry_INT80_compat, false }, + TRAP_ENTRY(int80_emulation, false ), #endif TRAP_ENTRY(exc_page_fault, false ), TRAP_ENTRY(exc_divide_error, false ), diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S index 9e5e680087853..1a9cd18dfbd31 100644 --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -156,7 +156,7 @@ xen_pv_trap asm_xenpv_exc_machine_check #endif /* CONFIG_X86_MCE */ xen_pv_trap asm_exc_simd_coprocessor_error #ifdef CONFIG_IA32_EMULATION -xen_pv_trap entry_INT80_compat +xen_pv_trap asm_int80_emulation #endif xen_pv_trap asm_exc_xen_unknown_trap xen_pv_trap asm_exc_xen_hypervisor_callback diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 408a2aa66c692..a87ab36889e76 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -21,7 +21,7 @@ extern void *xen_initial_gdt; struct trap_info; void xen_copy_trap_info(struct trap_info *traps); -DECLARE_PER_CPU(struct vcpu_info, xen_vcpu_info); +DECLARE_PER_CPU_ALIGNED(struct vcpu_info, xen_vcpu_info); DECLARE_PER_CPU(unsigned long, xen_cr3); DECLARE_PER_CPU(unsigned long, xen_current_cr3); diff --git a/block/bdev.c b/block/bdev.c index f3b13aa1b7d42..04dba25b0019e 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -425,6 +425,8 @@ void bdev_set_nr_sectors(struct block_device *bdev, sector_t sectors) void bdev_add(struct block_device *bdev, dev_t dev) { + if (bdev_stable_writes(bdev)) + mapping_set_stable_writes(bdev->bd_inode->i_mapping); bdev->bd_dev = dev; bdev->bd_inode->i_rdev = dev; bdev->bd_inode->i_ino = dev; diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 4a42ea2972ad8..4b48c2c440981 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -577,6 +577,7 @@ static void blkg_destroy_all(struct gendisk *disk) struct request_queue *q = disk->queue; struct blkcg_gq *blkg, *n; int count = BLKG_DESTROY_BATCH_SIZE; + int i; restart: spin_lock_irq(&q->queue_lock); @@ -602,6 +603,18 @@ static void blkg_destroy_all(struct gendisk *disk) } } + /* + * Mark policy deactivated since policy offline has been done, and + * the free is scheduled, so future blkcg_deactivate_policy() can + * be bypassed + */ + for (i = 0; i < BLKCG_MAX_POLS; i++) { + struct blkcg_policy *pol = blkcg_policy[i]; + + if (pol) + __clear_bit(pol->plid, q->blkcg_pols); + } + q->root_blkg = NULL; spin_unlock_irq(&q->queue_lock); } diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h index 624c03c8fe64e..fd482439afbc9 100644 --- a/block/blk-cgroup.h +++ b/block/blk-cgroup.h @@ -249,8 +249,6 @@ static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, { struct blkcg_gq *blkg; - WARN_ON_ONCE(!rcu_read_lock_held()); - if (blkcg == &blkcg_root) return q->root_blkg; diff --git a/block/blk-mq.c b/block/blk-mq.c index 1fafd54dce3cb..6ab7f360ff2ac 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2875,11 +2875,8 @@ static struct request *blk_mq_get_new_requests(struct request_queue *q, }; struct request *rq; - if (unlikely(bio_queue_enter(bio))) - return NULL; - if (blk_mq_attempt_bio_merge(q, bio, nsegs)) - goto queue_exit; + return NULL; rq_qos_throttle(q, bio); @@ -2895,35 +2892,23 @@ static struct request *blk_mq_get_new_requests(struct request_queue *q, rq_qos_cleanup(q, bio); if (bio->bi_opf & REQ_NOWAIT) bio_wouldblock_error(bio); -queue_exit: - blk_queue_exit(q); return NULL; } -static inline struct request *blk_mq_get_cached_request(struct request_queue *q, - struct blk_plug *plug, struct bio **bio, unsigned int nsegs) +/* return true if this @rq can be used for @bio */ +static bool blk_mq_can_use_cached_rq(struct request *rq, struct blk_plug *plug, + struct bio *bio) { - struct request *rq; - enum hctx_type type, hctx_type; + enum hctx_type type = blk_mq_get_hctx_type(bio->bi_opf); + enum hctx_type hctx_type = rq->mq_hctx->type; - if (!plug) - return NULL; - rq = rq_list_peek(&plug->cached_rq); - if (!rq || rq->q != q) - return NULL; + WARN_ON_ONCE(rq_list_peek(&plug->cached_rq) != rq); - if (blk_mq_attempt_bio_merge(q, *bio, nsegs)) { - *bio = NULL; - return NULL; - } - - type = blk_mq_get_hctx_type((*bio)->bi_opf); - hctx_type = rq->mq_hctx->type; if (type != hctx_type && !(type == HCTX_TYPE_READ && hctx_type == HCTX_TYPE_DEFAULT)) - return NULL; - if (op_is_flush(rq->cmd_flags) != op_is_flush((*bio)->bi_opf)) - return NULL; + return false; + if (op_is_flush(rq->cmd_flags) != op_is_flush(bio->bi_opf)) + return false; /* * If any qos ->throttle() end up blocking, we will have flushed the @@ -2931,12 +2916,12 @@ static inline struct request *blk_mq_get_cached_request(struct request_queue *q, * before we throttle. */ plug->cached_rq = rq_list_next(rq); - rq_qos_throttle(q, *bio); + rq_qos_throttle(rq->q, bio); blk_mq_rq_time_init(rq, 0); - rq->cmd_flags = (*bio)->bi_opf; + rq->cmd_flags = bio->bi_opf; INIT_LIST_HEAD(&rq->queuelist); - return rq; + return true; } static void bio_set_ioprio(struct bio *bio) @@ -2966,7 +2951,7 @@ void blk_mq_submit_bio(struct bio *bio) struct blk_plug *plug = blk_mq_plug(bio); const int is_sync = op_is_sync(bio->bi_opf); struct blk_mq_hw_ctx *hctx; - struct request *rq; + struct request *rq = NULL; unsigned int nr_segs = 1; blk_status_t ret; @@ -2977,20 +2962,36 @@ void blk_mq_submit_bio(struct bio *bio) return; } - if (!bio_integrity_prep(bio)) - return; - bio_set_ioprio(bio); - rq = blk_mq_get_cached_request(q, plug, &bio, nr_segs); - if (!rq) { - if (!bio) + if (plug) { + rq = rq_list_peek(&plug->cached_rq); + if (rq && rq->q != q) + rq = NULL; + } + if (rq) { + if (!bio_integrity_prep(bio)) return; - rq = blk_mq_get_new_requests(q, plug, bio, nr_segs); - if (unlikely(!rq)) + if (blk_mq_attempt_bio_merge(q, bio, nr_segs)) return; + if (blk_mq_can_use_cached_rq(rq, plug, bio)) + goto done; + percpu_ref_get(&q->q_usage_counter); + } else { + if (unlikely(bio_queue_enter(bio))) + return; + if (!bio_integrity_prep(bio)) + goto fail; + } + + rq = blk_mq_get_new_requests(q, plug, bio, nr_segs); + if (unlikely(!rq)) { +fail: + blk_queue_exit(q); + return; } +done: trace_block_getrq(bio); rq_qos_track(q, rq, bio); diff --git a/block/blk-throttle.c b/block/blk-throttle.c index 13e4377a8b286..16f5766620a41 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -1320,6 +1320,7 @@ static void tg_conf_updated(struct throtl_grp *tg, bool global) tg_bps_limit(tg, READ), tg_bps_limit(tg, WRITE), tg_iops_limit(tg, READ), tg_iops_limit(tg, WRITE)); + rcu_read_lock(); /* * Update has_rules[] flags for the updated tg's subtree. A tg is * considered to have rules if either the tg itself or any of its @@ -1347,6 +1348,7 @@ static void tg_conf_updated(struct throtl_grp *tg, bool global) this_tg->latency_target = max(this_tg->latency_target, parent_tg->latency_target); } + rcu_read_unlock(); /* * We're already holding queue_lock and know @tg is valid. Let's diff --git a/crypto/pcrypt.c b/crypto/pcrypt.c index 8c1d0ca412137..d0d954fe9d54f 100644 --- a/crypto/pcrypt.c +++ b/crypto/pcrypt.c @@ -117,6 +117,8 @@ static int pcrypt_aead_encrypt(struct aead_request *req) err = padata_do_parallel(ictx->psenc, padata, &ctx->cb_cpu); if (!err) return -EINPROGRESS; + if (err == -EBUSY) + return -EAGAIN; return err; } @@ -164,6 +166,8 @@ static int pcrypt_aead_decrypt(struct aead_request *req) err = padata_do_parallel(ictx->psdec, padata, &ctx->cb_cpu); if (!err) return -EINPROGRESS; + if (err == -EBUSY) + return -EAGAIN; return err; } diff --git a/drivers/accel/ivpu/ivpu_drv.h b/drivers/accel/ivpu/ivpu_drv.h index 2adc349126bb6..6853dfe1c7e58 100644 --- a/drivers/accel/ivpu/ivpu_drv.h +++ b/drivers/accel/ivpu/ivpu_drv.h @@ -76,6 +76,11 @@ #define IVPU_WA(wa_name) (vdev->wa.wa_name) +#define IVPU_PRINT_WA(wa_name) do { \ + if (IVPU_WA(wa_name)) \ + ivpu_dbg(vdev, MISC, "Using WA: " #wa_name "\n"); \ +} while (0) + struct ivpu_wa_table { bool punit_disabled; bool clear_runtime_mem; diff --git a/drivers/accel/ivpu/ivpu_hw_37xx.c b/drivers/accel/ivpu/ivpu_hw_37xx.c index 18be8b98e9a8b..ddf03498fd4c1 100644 --- a/drivers/accel/ivpu/ivpu_hw_37xx.c +++ b/drivers/accel/ivpu/ivpu_hw_37xx.c @@ -53,10 +53,12 @@ #define ICB_0_1_IRQ_MASK ((((u64)ICB_1_IRQ_MASK) << 32) | ICB_0_IRQ_MASK) -#define BUTTRESS_IRQ_MASK ((REG_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, FREQ_CHANGE)) | \ - (REG_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, ATS_ERR)) | \ +#define BUTTRESS_IRQ_MASK ((REG_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, ATS_ERR)) | \ (REG_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, UFI_ERR))) +#define BUTTRESS_ALL_IRQ_MASK (BUTTRESS_IRQ_MASK | \ + (REG_FLD(VPU_37XX_BUTTRESS_INTERRUPT_STAT, FREQ_CHANGE))) + #define BUTTRESS_IRQ_ENABLE_MASK ((u32)~BUTTRESS_IRQ_MASK) #define BUTTRESS_IRQ_DISABLE_MASK ((u32)-1) @@ -102,8 +104,17 @@ static void ivpu_hw_wa_init(struct ivpu_device *vdev) vdev->wa.clear_runtime_mem = false; vdev->wa.d3hot_after_power_off = true; - if (ivpu_device_id(vdev) == PCI_DEVICE_ID_MTL && ivpu_revision(vdev) < 4) + REGB_WR32(VPU_37XX_BUTTRESS_INTERRUPT_STAT, BUTTRESS_ALL_IRQ_MASK); + if (REGB_RD32(VPU_37XX_BUTTRESS_INTERRUPT_STAT) == BUTTRESS_ALL_IRQ_MASK) { + /* Writing 1s does not clear the interrupt status register */ vdev->wa.interrupt_clear_with_0 = true; + REGB_WR32(VPU_37XX_BUTTRESS_INTERRUPT_STAT, 0x0); + } + + IVPU_PRINT_WA(punit_disabled); + IVPU_PRINT_WA(clear_runtime_mem); + IVPU_PRINT_WA(d3hot_after_power_off); + IVPU_PRINT_WA(interrupt_clear_with_0); } static void ivpu_hw_timeouts_init(struct ivpu_device *vdev) @@ -536,6 +547,16 @@ static int ivpu_boot_pwr_domain_enable(struct ivpu_device *vdev) return ret; } +static int ivpu_boot_pwr_domain_disable(struct ivpu_device *vdev) +{ + ivpu_boot_dpu_active_drive(vdev, false); + ivpu_boot_pwr_island_isolation_drive(vdev, true); + ivpu_boot_pwr_island_trickle_drive(vdev, false); + ivpu_boot_pwr_island_drive(vdev, false); + + return ivpu_boot_wait_for_pwr_island_status(vdev, 0x0); +} + static void ivpu_boot_no_snoop_enable(struct ivpu_device *vdev) { u32 val = REGV_RD32(VPU_37XX_HOST_IF_TCU_PTW_OVERRIDES); @@ -625,30 +646,26 @@ static int ivpu_hw_37xx_info_init(struct ivpu_device *vdev) ivpu_hw_init_range(&hw->ranges.shave, 0x180000000, SZ_2G); ivpu_hw_init_range(&hw->ranges.dma, 0x200000000, SZ_8G); + ivpu_hw_read_platform(vdev); + ivpu_hw_wa_init(vdev); + ivpu_hw_timeouts_init(vdev); + return 0; } static int ivpu_hw_37xx_reset(struct ivpu_device *vdev) { - int ret; - u32 val; - - if (IVPU_WA(punit_disabled)) - return 0; + int ret = 0; - ret = REGB_POLL_FLD(VPU_37XX_BUTTRESS_VPU_IP_RESET, TRIGGER, 0, TIMEOUT_US); - if (ret) { - ivpu_err(vdev, "Timed out waiting for TRIGGER bit\n"); - return ret; + if (ivpu_boot_pwr_domain_disable(vdev)) { + ivpu_err(vdev, "Failed to disable power domain\n"); + ret = -EIO; } - val = REGB_RD32(VPU_37XX_BUTTRESS_VPU_IP_RESET); - val = REG_SET_FLD(VPU_37XX_BUTTRESS_VPU_IP_RESET, TRIGGER, val); - REGB_WR32(VPU_37XX_BUTTRESS_VPU_IP_RESET, val); - - ret = REGB_POLL_FLD(VPU_37XX_BUTTRESS_VPU_IP_RESET, TRIGGER, 0, TIMEOUT_US); - if (ret) - ivpu_err(vdev, "Timed out waiting for RESET completion\n"); + if (ivpu_pll_disable(vdev)) { + ivpu_err(vdev, "Failed to disable PLL\n"); + ret = -EIO; + } return ret; } @@ -681,14 +698,6 @@ static int ivpu_hw_37xx_power_up(struct ivpu_device *vdev) { int ret; - ivpu_hw_read_platform(vdev); - ivpu_hw_wa_init(vdev); - ivpu_hw_timeouts_init(vdev); - - ret = ivpu_hw_37xx_reset(vdev); - if (ret) - ivpu_warn(vdev, "Failed to reset HW: %d\n", ret); - ret = ivpu_hw_37xx_d0i3_disable(vdev); if (ret) ivpu_warn(vdev, "Failed to disable D0I3: %d\n", ret); @@ -756,11 +765,11 @@ static int ivpu_hw_37xx_power_down(struct ivpu_device *vdev) { int ret = 0; - if (!ivpu_hw_37xx_is_idle(vdev) && ivpu_hw_37xx_reset(vdev)) - ivpu_err(vdev, "Failed to reset the VPU\n"); + if (!ivpu_hw_37xx_is_idle(vdev)) + ivpu_warn(vdev, "VPU not idle during power down\n"); - if (ivpu_pll_disable(vdev)) { - ivpu_err(vdev, "Failed to disable PLL\n"); + if (ivpu_hw_37xx_reset(vdev)) { + ivpu_err(vdev, "Failed to reset VPU\n"); ret = -EIO; } diff --git a/drivers/accel/ivpu/ivpu_hw_40xx.c b/drivers/accel/ivpu/ivpu_hw_40xx.c index 85171a408363f..03600a7a5aca8 100644 --- a/drivers/accel/ivpu/ivpu_hw_40xx.c +++ b/drivers/accel/ivpu/ivpu_hw_40xx.c @@ -125,6 +125,10 @@ static void ivpu_hw_wa_init(struct ivpu_device *vdev) if (ivpu_hw_gen(vdev) == IVPU_HW_40XX) vdev->wa.disable_clock_relinquish = true; + + IVPU_PRINT_WA(punit_disabled); + IVPU_PRINT_WA(clear_runtime_mem); + IVPU_PRINT_WA(disable_clock_relinquish); } static void ivpu_hw_timeouts_init(struct ivpu_device *vdev) @@ -728,6 +732,10 @@ static int ivpu_hw_40xx_info_init(struct ivpu_device *vdev) ivpu_hw_init_range(&vdev->hw->ranges.shave, 0x80000000 + SZ_256M, SZ_2G - SZ_256M); ivpu_hw_init_range(&vdev->hw->ranges.dma, 0x200000000, SZ_8G); + ivpu_hw_read_platform(vdev); + ivpu_hw_wa_init(vdev); + ivpu_hw_timeouts_init(vdev); + return 0; } @@ -819,10 +827,6 @@ static int ivpu_hw_40xx_power_up(struct ivpu_device *vdev) return ret; } - ivpu_hw_read_platform(vdev); - ivpu_hw_wa_init(vdev); - ivpu_hw_timeouts_init(vdev); - ret = ivpu_hw_40xx_d0i3_disable(vdev); if (ret) ivpu_warn(vdev, "Failed to disable D0I3: %d\n", ret); diff --git a/drivers/acpi/acpi_fpdt.c b/drivers/acpi/acpi_fpdt.c index a2056c4c8cb70..271092f2700a1 100644 --- a/drivers/acpi/acpi_fpdt.c +++ b/drivers/acpi/acpi_fpdt.c @@ -194,12 +194,19 @@ static int fpdt_process_subtable(u64 address, u32 subtable_type) record_header = (void *)subtable_header + offset; offset += record_header->length; + if (!record_header->length) { + pr_err(FW_BUG "Zero-length record found in FPTD.\n"); + result = -EINVAL; + goto err; + } + switch (record_header->type) { case RECORD_S3_RESUME: if (subtable_type != SUBTABLE_S3PT) { pr_err(FW_BUG "Invalid record %d for subtable %s\n", record_header->type, signature); - return -EINVAL; + result = -EINVAL; + goto err; } if (record_resume) { pr_err("Duplicate resume performance record found.\n"); @@ -208,7 +215,7 @@ static int fpdt_process_subtable(u64 address, u32 subtable_type) record_resume = (struct resume_performance_record *)record_header; result = sysfs_create_group(fpdt_kobj, &resume_attr_group); if (result) - return result; + goto err; break; case RECORD_S3_SUSPEND: if (subtable_type != SUBTABLE_S3PT) { @@ -223,13 +230,14 @@ static int fpdt_process_subtable(u64 address, u32 subtable_type) record_suspend = (struct suspend_performance_record *)record_header; result = sysfs_create_group(fpdt_kobj, &suspend_attr_group); if (result) - return result; + goto err; break; case RECORD_BOOT: if (subtable_type != SUBTABLE_FBPT) { pr_err(FW_BUG "Invalid %d for subtable %s\n", record_header->type, signature); - return -EINVAL; + result = -EINVAL; + goto err; } if (record_boot) { pr_err("Duplicate boot performance record found.\n"); @@ -238,7 +246,7 @@ static int fpdt_process_subtable(u64 address, u32 subtable_type) record_boot = (struct boot_performance_record *)record_header; result = sysfs_create_group(fpdt_kobj, &boot_attr_group); if (result) - return result; + goto err; break; default: @@ -247,6 +255,18 @@ static int fpdt_process_subtable(u64 address, u32 subtable_type) } } return 0; + +err: + if (record_boot) + sysfs_remove_group(fpdt_kobj, &boot_attr_group); + + if (record_suspend) + sysfs_remove_group(fpdt_kobj, &suspend_attr_group); + + if (record_resume) + sysfs_remove_group(fpdt_kobj, &resume_attr_group); + + return result; } static int __init acpi_init_fpdt(void) @@ -255,6 +275,7 @@ static int __init acpi_init_fpdt(void) struct acpi_table_header *header; struct fpdt_subtable_entry *subtable; u32 offset = sizeof(*header); + int result; status = acpi_get_table(ACPI_SIG_FPDT, 0, &header); @@ -263,8 +284,8 @@ static int __init acpi_init_fpdt(void) fpdt_kobj = kobject_create_and_add("fpdt", acpi_kobj); if (!fpdt_kobj) { - acpi_put_table(header); - return -ENOMEM; + result = -ENOMEM; + goto err_nomem; } while (offset < header->length) { @@ -272,8 +293,10 @@ static int __init acpi_init_fpdt(void) switch (subtable->type) { case SUBTABLE_FBPT: case SUBTABLE_S3PT: - fpdt_process_subtable(subtable->address, + result = fpdt_process_subtable(subtable->address, subtable->type); + if (result) + goto err_subtable; break; default: /* Other types are reserved in ACPI 6.4 spec. */ @@ -282,6 +305,12 @@ static int __init acpi_init_fpdt(void) offset += sizeof(*subtable); } return 0; +err_subtable: + kobject_put(fpdt_kobj); + +err_nomem: + acpi_put_table(header); + return result; } fs_initcall(acpi_init_fpdt); diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c index b411948594ff8..35f071ad95324 100644 --- a/drivers/acpi/acpi_video.c +++ b/drivers/acpi/acpi_video.c @@ -253,8 +253,7 @@ static const struct backlight_ops acpi_backlight_ops = { static int video_get_max_state(struct thermal_cooling_device *cooling_dev, unsigned long *state) { - struct acpi_device *device = cooling_dev->devdata; - struct acpi_video_device *video = acpi_driver_data(device); + struct acpi_video_device *video = cooling_dev->devdata; *state = video->brightness->count - ACPI_VIDEO_FIRST_LEVEL - 1; return 0; @@ -263,8 +262,7 @@ static int video_get_max_state(struct thermal_cooling_device *cooling_dev, static int video_get_cur_state(struct thermal_cooling_device *cooling_dev, unsigned long *state) { - struct acpi_device *device = cooling_dev->devdata; - struct acpi_video_device *video = acpi_driver_data(device); + struct acpi_video_device *video = cooling_dev->devdata; unsigned long long level; int offset; @@ -283,8 +281,7 @@ static int video_get_cur_state(struct thermal_cooling_device *cooling_dev, static int video_set_cur_state(struct thermal_cooling_device *cooling_dev, unsigned long state) { - struct acpi_device *device = cooling_dev->devdata; - struct acpi_video_device *video = acpi_driver_data(device); + struct acpi_video_device *video = cooling_dev->devdata; int level; if (state >= video->brightness->count - ACPI_VIDEO_FIRST_LEVEL) @@ -1125,7 +1122,6 @@ static int acpi_video_bus_get_one_device(struct acpi_device *device, void *arg) strcpy(acpi_device_name(device), ACPI_VIDEO_DEVICE_NAME); strcpy(acpi_device_class(device), ACPI_VIDEO_CLASS); - device->driver_data = data; data->device_id = device_id; data->video = video; @@ -1747,8 +1743,8 @@ static void acpi_video_dev_register_backlight(struct acpi_video_device *device) device->backlight->props.brightness = acpi_video_get_brightness(device->backlight); - device->cooling_dev = thermal_cooling_device_register("LCD", - device->dev, &video_cooling_ops); + device->cooling_dev = thermal_cooling_device_register("LCD", device, + &video_cooling_ops); if (IS_ERR(device->cooling_dev)) { /* * Set cooling_dev to NULL so we don't crash trying to free it. @@ -2031,7 +2027,7 @@ static int acpi_video_bus_add(struct acpi_device *device) * HP ZBook Fury 16 G10 requires ACPI video's child devices have _PS0 * evaluated to have functional panel brightness control. */ - acpi_device_fix_up_power_extended(device); + acpi_device_fix_up_power_children(device); pr_info("%s [%s] (multi-head: %s rom: %s post: %s)\n", ACPI_VIDEO_DEVICE_NAME, acpi_device_bid(device), diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index ef59d6ea16da0..63ad0541db381 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -209,6 +209,20 @@ int ghes_estatus_pool_init(unsigned int num_ghes) return -ENOMEM; } +/** + * ghes_estatus_pool_region_free - free previously allocated memory + * from the ghes_estatus_pool. + * @addr: address of memory to free. + * @size: size of memory to free. + * + * Returns none. + */ +void ghes_estatus_pool_region_free(unsigned long addr, u32 size) +{ + gen_pool_free(ghes_estatus_pool, addr, size); +} +EXPORT_SYMBOL_GPL(ghes_estatus_pool_region_free); + static int map_gen_v2(struct ghes *ghes) { return apei_map_generic_address(&ghes->generic_v2->read_ack_register); @@ -564,6 +578,7 @@ static void ghes_handle_aer(struct acpi_hest_generic_data *gdata) pcie_err->validation_bits & CPER_PCIE_VALID_AER_INFO) { unsigned int devfn; int aer_severity; + u8 *aer_info; devfn = PCI_DEVFN(pcie_err->device_id.device, pcie_err->device_id.function); @@ -577,11 +592,17 @@ static void ghes_handle_aer(struct acpi_hest_generic_data *gdata) if (gdata->flags & CPER_SEC_RESET) aer_severity = AER_FATAL; + aer_info = (void *)gen_pool_alloc(ghes_estatus_pool, + sizeof(struct aer_capability_regs)); + if (!aer_info) + return; + memcpy(aer_info, pcie_err->aer_info, sizeof(struct aer_capability_regs)); + aer_recover_queue(pcie_err->device_id.segment, pcie_err->device_id.bus, devfn, aer_severity, (struct aer_capability_regs *) - pcie_err->aer_info); + aer_info); } #endif } diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c index f007116a84276..3b4d048c49417 100644 --- a/drivers/acpi/device_pm.c +++ b/drivers/acpi/device_pm.c @@ -397,6 +397,19 @@ void acpi_device_fix_up_power_extended(struct acpi_device *adev) } EXPORT_SYMBOL_GPL(acpi_device_fix_up_power_extended); +/** + * acpi_device_fix_up_power_children - Force a device's children into D0. + * @adev: Parent device object whose children's power state is to be fixed up. + * + * Call acpi_device_fix_up_power() for @adev's children so long as they + * are reported as present and enabled. + */ +void acpi_device_fix_up_power_children(struct acpi_device *adev) +{ + acpi_dev_for_each_child(adev, fix_up_power_if_applicable, NULL); +} +EXPORT_SYMBOL_GPL(acpi_device_fix_up_power_children); + int acpi_device_update_power(struct acpi_device *device, int *state_p) { int state; diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index c95d0edb0be9e..a59c11df73754 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -1924,6 +1924,16 @@ static const struct dmi_system_id ec_dmi_table[] __initconst = { DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion Gaming Laptop 15-dk1xxx"), }, }, + { + /* + * HP 250 G7 Notebook PC + */ + .callback = ec_honor_dsdt_gpe, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "HP"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP 250 G7 Notebook PC"), + }, + }, { /* * Samsung hardware diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index 3a34a8c425fe4..55437f5e0c3ae 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -592,7 +592,7 @@ static int acpi_idle_play_dead(struct cpuidle_device *dev, int index) while (1) { if (cx->entry_method == ACPI_CSTATE_HALT) - safe_halt(); + raw_safe_halt(); else if (cx->entry_method == ACPI_CSTATE_SYSTEMIO) { io_idle(cx->address); } else diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index 297a88587031e..d09e3e7bcb585 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -446,6 +446,13 @@ static const struct dmi_system_id asus_laptop[] = { DMI_MATCH(DMI_BOARD_NAME, "B1402CBA"), }, }, + { + /* Asus ExpertBook B1402CVA */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_BOARD_NAME, "B1402CVA"), + }, + }, { .ident = "Asus ExpertBook B1502CBA", .matches = { @@ -495,6 +502,18 @@ static const struct dmi_system_id maingear_laptop[] = { DMI_MATCH(DMI_PRODUCT_NAME, "MG-VCP2-15A3070T"), } }, + { + /* TongFang GMxXGxx/TUXEDO Polaris 15 Gen5 AMD */ + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "GMxXGxx"), + }, + }, + { + /* TongFang GM6XGxX/TUXEDO Stellaris 16 Gen5 AMD */ + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "GM6XGxX"), + }, + }, { .ident = "MAINGEAR Vector Pro 2 17", .matches = { diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 691d4b7686ee7..1d249d0f61ae4 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -1568,17 +1568,22 @@ static const struct iommu_ops *acpi_iommu_configure_id(struct device *dev, int err; const struct iommu_ops *ops; + /* Serialise to make dev->iommu stable under our potential fwspec */ + mutex_lock(&iommu_probe_device_lock); /* * If we already translated the fwspec there is nothing left to do, * return the iommu_ops. */ ops = acpi_iommu_fwspec_ops(dev); - if (ops) + if (ops) { + mutex_unlock(&iommu_probe_device_lock); return ops; + } err = iort_iommu_configure_id(dev, id_in); if (err && err != -EPROBE_DEFER) err = viot_iommu_configure(dev); + mutex_unlock(&iommu_probe_device_lock); /* * If we have reason to believe the IOMMU driver missed the initial diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 9638182447dd0..b05a8f12f4d47 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1055,9 +1055,14 @@ int ata_scsi_dev_config(struct scsi_device *sdev, struct ata_device *dev) * Ask the sd driver to issue START STOP UNIT on runtime suspend * and resume and shutdown only. For system level suspend/resume, * devices power state is handled directly by libata EH. + * Given that disks are always spun up on system resume, also + * make sure that the sd driver forces runtime suspended disks + * to be resumed to correctly reflect the power state of the + * device. */ - sdev->manage_runtime_start_stop = true; - sdev->manage_shutdown = true; + sdev->manage_runtime_start_stop = 1; + sdev->manage_shutdown = 1; + sdev->force_runtime_start_on_system_start = 1; } /* diff --git a/drivers/ata/pata_isapnp.c b/drivers/ata/pata_isapnp.c index 25a63d043c8e1..0f77e04240661 100644 --- a/drivers/ata/pata_isapnp.c +++ b/drivers/ata/pata_isapnp.c @@ -82,6 +82,9 @@ static int isapnp_init_one(struct pnp_dev *idev, const struct pnp_device_id *dev if (pnp_port_valid(idev, 1)) { ctl_addr = devm_ioport_map(&idev->dev, pnp_port_start(idev, 1), 1); + if (!ctl_addr) + return -ENOMEM; + ap->ioaddr.altstatus_addr = ctl_addr; ap->ioaddr.ctl_addr = ctl_addr; ap->ops = &isapnp_port_ops; diff --git a/drivers/atm/iphase.c b/drivers/atm/iphase.c index 3241486869530..9bba8f280a4d4 100644 --- a/drivers/atm/iphase.c +++ b/drivers/atm/iphase.c @@ -2291,19 +2291,21 @@ static int get_esi(struct atm_dev *dev) static int reset_sar(struct atm_dev *dev) { IADEV *iadev; - int i, error = 1; + int i, error; unsigned int pci[64]; iadev = INPH_IA_DEV(dev); - for(i=0; i<64; i++) - if ((error = pci_read_config_dword(iadev->pci, - i*4, &pci[i])) != PCIBIOS_SUCCESSFUL) - return error; + for (i = 0; i < 64; i++) { + error = pci_read_config_dword(iadev->pci, i * 4, &pci[i]); + if (error != PCIBIOS_SUCCESSFUL) + return error; + } writel(0, iadev->reg+IPHASE5575_EXT_RESET); - for(i=0; i<64; i++) - if ((error = pci_write_config_dword(iadev->pci, - i*4, pci[i])) != PCIBIOS_SUCCESSFUL) - return error; + for (i = 0; i < 64; i++) { + error = pci_write_config_dword(iadev->pci, i * 4, pci[i]); + if (error != PCIBIOS_SUCCESSFUL) + return error; + } udelay(5); return 0; } diff --git a/drivers/atm/solos-pci.c b/drivers/atm/solos-pci.c index 94fbc3abe60e6..d3c30a28c410e 100644 --- a/drivers/atm/solos-pci.c +++ b/drivers/atm/solos-pci.c @@ -449,9 +449,9 @@ static ssize_t console_show(struct device *dev, struct device_attribute *attr, struct sk_buff *skb; unsigned int len; - spin_lock(&card->cli_queue_lock); + spin_lock_bh(&card->cli_queue_lock); skb = skb_dequeue(&card->cli_queue[SOLOS_CHAN(atmdev)]); - spin_unlock(&card->cli_queue_lock); + spin_unlock_bh(&card->cli_queue_lock); if(skb == NULL) return sprintf(buf, "No data.\n"); @@ -956,14 +956,14 @@ static void pclose(struct atm_vcc *vcc) struct pkt_hdr *header; /* Remove any yet-to-be-transmitted packets from the pending queue */ - spin_lock(&card->tx_queue_lock); + spin_lock_bh(&card->tx_queue_lock); skb_queue_walk_safe(&card->tx_queue[port], skb, tmpskb) { if (SKB_CB(skb)->vcc == vcc) { skb_unlink(skb, &card->tx_queue[port]); solos_pop(vcc, skb); } } - spin_unlock(&card->tx_queue_lock); + spin_unlock_bh(&card->tx_queue_lock); skb = alloc_skb(sizeof(*header), GFP_KERNEL); if (!skb) { diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 9ea22e165acd6..548491de818ef 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -144,7 +144,7 @@ static DEVICE_ATTR(release, S_IWUSR, NULL, cpu_release_store); #endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */ #endif /* CONFIG_HOTPLUG_CPU */ -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE #include static ssize_t crash_notes_show(struct device *dev, @@ -189,14 +189,14 @@ static const struct attribute_group crash_note_cpu_attr_group = { #endif static const struct attribute_group *common_cpu_attr_groups[] = { -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE &crash_note_cpu_attr_group, #endif NULL }; static const struct attribute_group *hotplugable_cpu_attr_groups[] = { -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE &crash_note_cpu_attr_group, #endif NULL diff --git a/drivers/base/dd.c b/drivers/base/dd.c index a528cec24264a..0c3725c3eefa4 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -1274,8 +1274,8 @@ static void __device_release_driver(struct device *dev, struct device *parent) if (dev->bus && dev->bus->dma_cleanup) dev->bus->dma_cleanup(dev); - device_links_driver_cleanup(dev); device_unbind_cleanup(dev); + device_links_driver_cleanup(dev); klist_remove(&dev->p->knode_driver); device_pm_check_callbacks(dev); diff --git a/drivers/base/devcoredump.c b/drivers/base/devcoredump.c index 91536ee05f144..7e2d1f0d903a6 100644 --- a/drivers/base/devcoredump.c +++ b/drivers/base/devcoredump.c @@ -362,6 +362,7 @@ void dev_coredumpm(struct device *dev, struct module *owner, devcd->devcd_dev.class = &devcd_class; mutex_lock(&devcd->mutex); + dev_set_uevent_suppress(&devcd->devcd_dev, true); if (device_add(&devcd->devcd_dev)) goto put_device; @@ -376,6 +377,8 @@ void dev_coredumpm(struct device *dev, struct module *owner, "devcoredump")) dev_warn(dev, "devcoredump create_link failed\n"); + dev_set_uevent_suppress(&devcd->devcd_dev, false); + kobject_uevent(&devcd->devcd_dev.kobj, KOBJ_ADD); INIT_DELAYED_WORK(&devcd->del_wk, devcd_del); schedule_delayed_work(&devcd->del_wk, DEVCD_TIMEOUT); mutex_unlock(&devcd->mutex); diff --git a/drivers/base/memory.c b/drivers/base/memory.c index f3b9a4d0fa3bb..8a13babd826ce 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -180,6 +180,9 @@ static inline unsigned long memblk_nr_poison(struct memory_block *mem) } #endif +/* + * Must acquire mem_hotplug_lock in write mode. + */ static int memory_block_online(struct memory_block *mem) { unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr); @@ -204,10 +207,11 @@ static int memory_block_online(struct memory_block *mem) if (mem->altmap) nr_vmemmap_pages = mem->altmap->free; + mem_hotplug_begin(); if (nr_vmemmap_pages) { ret = mhp_init_memmap_on_memory(start_pfn, nr_vmemmap_pages, zone); if (ret) - return ret; + goto out; } ret = online_pages(start_pfn + nr_vmemmap_pages, @@ -215,7 +219,7 @@ static int memory_block_online(struct memory_block *mem) if (ret) { if (nr_vmemmap_pages) mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages); - return ret; + goto out; } /* @@ -227,9 +231,14 @@ static int memory_block_online(struct memory_block *mem) nr_vmemmap_pages); mem->zone = zone; +out: + mem_hotplug_done(); return ret; } +/* + * Must acquire mem_hotplug_lock in write mode. + */ static int memory_block_offline(struct memory_block *mem) { unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr); @@ -247,6 +256,7 @@ static int memory_block_offline(struct memory_block *mem) if (mem->altmap) nr_vmemmap_pages = mem->altmap->free; + mem_hotplug_begin(); if (nr_vmemmap_pages) adjust_present_page_count(pfn_to_page(start_pfn), mem->group, -nr_vmemmap_pages); @@ -258,13 +268,15 @@ static int memory_block_offline(struct memory_block *mem) if (nr_vmemmap_pages) adjust_present_page_count(pfn_to_page(start_pfn), mem->group, nr_vmemmap_pages); - return ret; + goto out; } if (nr_vmemmap_pages) mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages); mem->zone = NULL; +out: + mem_hotplug_done(); return ret; } diff --git a/drivers/base/regmap/regcache.c b/drivers/base/regmap/regcache.c index c5d151e9c4815..ac63a73ccdaaa 100644 --- a/drivers/base/regmap/regcache.c +++ b/drivers/base/regmap/regcache.c @@ -334,6 +334,11 @@ static int regcache_default_sync(struct regmap *map, unsigned int min, return 0; } +static int rbtree_all(const void *key, const struct rb_node *node) +{ + return 0; +} + /** * regcache_sync - Sync the register cache with the hardware. * @@ -351,6 +356,7 @@ int regcache_sync(struct regmap *map) unsigned int i; const char *name; bool bypass; + struct rb_node *node; if (WARN_ON(map->cache_type == REGCACHE_NONE)) return -EINVAL; @@ -392,6 +398,29 @@ int regcache_sync(struct regmap *map) /* Restore the bypass state */ map->cache_bypass = bypass; map->no_sync_defaults = false; + + /* + * If we did any paging with cache bypassed and a cached + * paging register then the register and cache state might + * have gone out of sync, force writes of all the paging + * registers. + */ + rb_for_each(node, 0, &map->range_tree, rbtree_all) { + struct regmap_range_node *this = + rb_entry(node, struct regmap_range_node, node); + + /* If there's nothing in the cache there's nothing to sync */ + if (regcache_read(map, this->selector_reg, &i) != 0) + continue; + + ret = _regmap_write(map, this->selector_reg, i); + if (ret != 0) { + dev_err(map->dev, "Failed to write %x = %x: %d\n", + this->selector_reg, i, ret); + break; + } + } + map->unlock(map->lock_arg); regmap_async_complete(map); diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 855fdf5c3b4ea..b6414e1e645b7 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -67,6 +67,7 @@ struct nbd_sock { struct recv_thread_args { struct work_struct work; struct nbd_device *nbd; + struct nbd_sock *nsock; int index; }; @@ -395,6 +396,22 @@ static u32 req_to_nbd_cmd_type(struct request *req) } } +static struct nbd_config *nbd_get_config_unlocked(struct nbd_device *nbd) +{ + if (refcount_inc_not_zero(&nbd->config_refs)) { + /* + * Add smp_mb__after_atomic to ensure that reading nbd->config_refs + * and reading nbd->config is ordered. The pair is the barrier in + * nbd_alloc_and_init_config(), avoid nbd->config_refs is set + * before nbd->config. + */ + smp_mb__after_atomic(); + return nbd->config; + } + + return NULL; +} + static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req) { struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req); @@ -409,13 +426,13 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req) return BLK_EH_DONE; } - if (!refcount_inc_not_zero(&nbd->config_refs)) { + config = nbd_get_config_unlocked(nbd); + if (!config) { cmd->status = BLK_STS_TIMEOUT; __clear_bit(NBD_CMD_INFLIGHT, &cmd->flags); mutex_unlock(&cmd->lock); goto done; } - config = nbd->config; if (config->num_connections > 1 || (config->num_connections == 1 && nbd->tag_set.timeout)) { @@ -489,15 +506,9 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req) return BLK_EH_DONE; } -/* - * Send or receive packet. Return a positive value on success and - * negtive value on failue, and never return 0. - */ -static int sock_xmit(struct nbd_device *nbd, int index, int send, - struct iov_iter *iter, int msg_flags, int *sent) +static int __sock_xmit(struct nbd_device *nbd, struct socket *sock, int send, + struct iov_iter *iter, int msg_flags, int *sent) { - struct nbd_config *config = nbd->config; - struct socket *sock = config->socks[index]->sock; int result; struct msghdr msg; unsigned int noreclaim_flag; @@ -540,6 +551,19 @@ static int sock_xmit(struct nbd_device *nbd, int index, int send, return result; } +/* + * Send or receive packet. Return a positive value on success and + * negtive value on failure, and never return 0. + */ +static int sock_xmit(struct nbd_device *nbd, int index, int send, + struct iov_iter *iter, int msg_flags, int *sent) +{ + struct nbd_config *config = nbd->config; + struct socket *sock = config->socks[index]->sock; + + return __sock_xmit(nbd, sock, send, iter, msg_flags, sent); +} + /* * Different settings for sk->sk_sndtimeo can result in different return values * if there is a signal pending when we enter sendmsg, because reasons? @@ -696,7 +720,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) return 0; } -static int nbd_read_reply(struct nbd_device *nbd, int index, +static int nbd_read_reply(struct nbd_device *nbd, struct socket *sock, struct nbd_reply *reply) { struct kvec iov = {.iov_base = reply, .iov_len = sizeof(*reply)}; @@ -705,7 +729,7 @@ static int nbd_read_reply(struct nbd_device *nbd, int index, reply->magic = 0; iov_iter_kvec(&to, ITER_DEST, &iov, 1, sizeof(*reply)); - result = sock_xmit(nbd, index, 0, &to, MSG_WAITALL, NULL); + result = __sock_xmit(nbd, sock, 0, &to, MSG_WAITALL, NULL); if (result < 0) { if (!nbd_disconnected(nbd->config)) dev_err(disk_to_dev(nbd->disk), @@ -829,14 +853,14 @@ static void recv_work(struct work_struct *work) struct nbd_device *nbd = args->nbd; struct nbd_config *config = nbd->config; struct request_queue *q = nbd->disk->queue; - struct nbd_sock *nsock; + struct nbd_sock *nsock = args->nsock; struct nbd_cmd *cmd; struct request *rq; while (1) { struct nbd_reply reply; - if (nbd_read_reply(nbd, args->index, &reply)) + if (nbd_read_reply(nbd, nsock->sock, &reply)) break; /* @@ -871,7 +895,6 @@ static void recv_work(struct work_struct *work) percpu_ref_put(&q->q_usage_counter); } - nsock = config->socks[args->index]; mutex_lock(&nsock->tx_lock); nbd_mark_nsock_dead(nbd, nsock, 1); mutex_unlock(&nsock->tx_lock); @@ -977,12 +1000,12 @@ static int nbd_handle_cmd(struct nbd_cmd *cmd, int index) struct nbd_sock *nsock; int ret; - if (!refcount_inc_not_zero(&nbd->config_refs)) { + config = nbd_get_config_unlocked(nbd); + if (!config) { dev_err_ratelimited(disk_to_dev(nbd->disk), "Socks array is empty\n"); return -EINVAL; } - config = nbd->config; if (index >= config->num_connections) { dev_err_ratelimited(disk_to_dev(nbd->disk), @@ -1215,6 +1238,7 @@ static int nbd_reconnect_socket(struct nbd_device *nbd, unsigned long arg) INIT_WORK(&args->work, recv_work); args->index = i; args->nbd = nbd; + args->nsock = nsock; nsock->cookie++; mutex_unlock(&nsock->tx_lock); sockfd_put(old); @@ -1397,6 +1421,7 @@ static int nbd_start_device(struct nbd_device *nbd) refcount_inc(&nbd->config_refs); INIT_WORK(&args->work, recv_work); args->nbd = nbd; + args->nsock = config->socks[i]; args->index = i; queue_work(nbd->recv_workq, &args->work); } @@ -1530,17 +1555,20 @@ static int nbd_ioctl(struct block_device *bdev, blk_mode_t mode, return error; } -static struct nbd_config *nbd_alloc_config(void) +static int nbd_alloc_and_init_config(struct nbd_device *nbd) { struct nbd_config *config; + if (WARN_ON(nbd->config)) + return -EINVAL; + if (!try_module_get(THIS_MODULE)) - return ERR_PTR(-ENODEV); + return -ENODEV; config = kzalloc(sizeof(struct nbd_config), GFP_NOFS); if (!config) { module_put(THIS_MODULE); - return ERR_PTR(-ENOMEM); + return -ENOMEM; } atomic_set(&config->recv_threads, 0); @@ -1548,12 +1576,24 @@ static struct nbd_config *nbd_alloc_config(void) init_waitqueue_head(&config->conn_wait); config->blksize_bits = NBD_DEF_BLKSIZE_BITS; atomic_set(&config->live_connections, 0); - return config; + + nbd->config = config; + /* + * Order refcount_set(&nbd->config_refs, 1) and nbd->config assignment, + * its pair is the barrier in nbd_get_config_unlocked(). + * So nbd_get_config_unlocked() won't see nbd->config as null after + * refcount_inc_not_zero() succeed. + */ + smp_mb__before_atomic(); + refcount_set(&nbd->config_refs, 1); + + return 0; } static int nbd_open(struct gendisk *disk, blk_mode_t mode) { struct nbd_device *nbd; + struct nbd_config *config; int ret = 0; mutex_lock(&nbd_index_mutex); @@ -1566,27 +1606,25 @@ static int nbd_open(struct gendisk *disk, blk_mode_t mode) ret = -ENXIO; goto out; } - if (!refcount_inc_not_zero(&nbd->config_refs)) { - struct nbd_config *config; + config = nbd_get_config_unlocked(nbd); + if (!config) { mutex_lock(&nbd->config_lock); if (refcount_inc_not_zero(&nbd->config_refs)) { mutex_unlock(&nbd->config_lock); goto out; } - config = nbd_alloc_config(); - if (IS_ERR(config)) { - ret = PTR_ERR(config); + ret = nbd_alloc_and_init_config(nbd); + if (ret) { mutex_unlock(&nbd->config_lock); goto out; } - nbd->config = config; - refcount_set(&nbd->config_refs, 1); + refcount_inc(&nbd->refs); mutex_unlock(&nbd->config_lock); if (max_part) set_bit(GD_NEED_PART_SCAN, &disk->state); - } else if (nbd_disconnected(nbd->config)) { + } else if (nbd_disconnected(config)) { if (max_part) set_bit(GD_NEED_PART_SCAN, &disk->state); } @@ -1990,22 +2028,17 @@ static int nbd_genl_connect(struct sk_buff *skb, struct genl_info *info) pr_err("nbd%d already in use\n", index); return -EBUSY; } - if (WARN_ON(nbd->config)) { - mutex_unlock(&nbd->config_lock); - nbd_put(nbd); - return -EINVAL; - } - config = nbd_alloc_config(); - if (IS_ERR(config)) { + + ret = nbd_alloc_and_init_config(nbd); + if (ret) { mutex_unlock(&nbd->config_lock); nbd_put(nbd); pr_err("couldn't allocate config\n"); - return PTR_ERR(config); + return ret; } - nbd->config = config; - refcount_set(&nbd->config_refs, 1); - set_bit(NBD_RT_BOUND, &config->runtime_flags); + config = nbd->config; + set_bit(NBD_RT_BOUND, &config->runtime_flags); ret = nbd_genl_size_set(info, nbd); if (ret) goto out; @@ -2208,7 +2241,8 @@ static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info) } mutex_unlock(&nbd_index_mutex); - if (!refcount_inc_not_zero(&nbd->config_refs)) { + config = nbd_get_config_unlocked(nbd); + if (!config) { dev_err(nbd_to_dev(nbd), "not configured, cannot reconfigure\n"); nbd_put(nbd); @@ -2216,7 +2250,6 @@ static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info) } mutex_lock(&nbd->config_lock); - config = nbd->config; if (!test_bit(NBD_RT_BOUND, &config->runtime_flags) || !nbd->pid) { dev_err(nbd_to_dev(nbd), diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 1fe011676d070..4a4b9bad551e8 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -1313,6 +1313,7 @@ static int virtblk_probe(struct virtio_device *vdev) u16 min_io_size; u8 physical_block_exp, alignment_offset; unsigned int queue_depth; + size_t max_dma_size; if (!vdev->config->get) { dev_err(&vdev->dev, "%s failure: config access disabled\n", @@ -1411,7 +1412,8 @@ static int virtblk_probe(struct virtio_device *vdev) /* No real sector limit. */ blk_queue_max_hw_sectors(q, UINT_MAX); - max_size = virtio_max_dma_size(vdev); + max_dma_size = virtio_max_dma_size(vdev); + max_size = max_dma_size > U32_MAX ? U32_MAX : max_dma_size; /* Host can optionally specify maximum segment size and number of * segments. */ diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 499f4809fcdf3..66080fae072f2 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -543,6 +543,10 @@ static const struct usb_device_id quirks_table[] = { BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x0bda, 0x887b), .driver_info = BTUSB_REALTEK | BTUSB_WIDEBAND_SPEECH }, + { USB_DEVICE(0x0bda, 0xb85b), .driver_info = BTUSB_REALTEK | + BTUSB_WIDEBAND_SPEECH }, + { USB_DEVICE(0x13d3, 0x3570), .driver_info = BTUSB_REALTEK | + BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x13d3, 0x3571), .driver_info = BTUSB_REALTEK | BTUSB_WIDEBAND_SPEECH }, @@ -2818,6 +2822,9 @@ static int btusb_mtk_hci_wmt_sync(struct hci_dev *hdev, goto err_free_wc; } + if (data->evt_skb == NULL) + goto err_free_wc; + /* Parse and handle the return WMT event */ wmt_evt = (struct btmtk_hci_wmt_evt *)data->evt_skb->data; if (wmt_evt->whdr.op != hdr->op) { diff --git a/drivers/bluetooth/hci_vhci.c b/drivers/bluetooth/hci_vhci.c index f3892e9ce800f..572d68d52965f 100644 --- a/drivers/bluetooth/hci_vhci.c +++ b/drivers/bluetooth/hci_vhci.c @@ -11,6 +11,7 @@ #include #include +#include #include #include #include @@ -44,6 +45,7 @@ struct vhci_data { bool wakeup; __u16 msft_opcode; bool aosp_capable; + atomic_t initialized; }; static int vhci_open_dev(struct hci_dev *hdev) @@ -75,11 +77,10 @@ static int vhci_send_frame(struct hci_dev *hdev, struct sk_buff *skb) memcpy(skb_push(skb, 1), &hci_skb_pkt_type(skb), 1); - mutex_lock(&data->open_mutex); skb_queue_tail(&data->readq, skb); - mutex_unlock(&data->open_mutex); - wake_up_interruptible(&data->read_wait); + if (atomic_read(&data->initialized)) + wake_up_interruptible(&data->read_wait); return 0; } @@ -464,7 +465,8 @@ static int __vhci_create_device(struct vhci_data *data, __u8 opcode) skb_put_u8(skb, 0xff); skb_put_u8(skb, opcode); put_unaligned_le16(hdev->id, skb_put(skb, 2)); - skb_queue_tail(&data->readq, skb); + skb_queue_head(&data->readq, skb); + atomic_inc(&data->initialized); wake_up_interruptible(&data->read_wait); return 0; diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index d57bc066dce6b..9ed9239b1228f 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -2158,13 +2158,23 @@ static int sysc_reset(struct sysc *ddata) sysc_val = sysc_read_sysconfig(ddata); sysc_val |= sysc_mask; sysc_write(ddata, sysc_offset, sysc_val); - /* Flush posted write */ + + /* + * Some devices need a delay before reading registers + * after reset. Presumably a srst_udelay is not needed + * for devices that use a rstctrl register reset. + */ + if (ddata->cfg.srst_udelay) + fsleep(ddata->cfg.srst_udelay); + + /* + * Flush posted write. For devices needing srst_udelay + * this should trigger an interconnect error if the + * srst_udelay value is needed but not configured. + */ sysc_val = sysc_read_sysconfig(ddata); } - if (ddata->cfg.srst_udelay) - fsleep(ddata->cfg.srst_udelay); - if (ddata->post_reset_quirk) ddata->post_reset_quirk(ddata); diff --git a/drivers/char/agp/parisc-agp.c b/drivers/char/agp/parisc-agp.c index c6f181702b9a7..edbc4d3381177 100644 --- a/drivers/char/agp/parisc-agp.c +++ b/drivers/char/agp/parisc-agp.c @@ -38,7 +38,7 @@ static struct _parisc_agp_info { int lba_cap_offset; - u64 *gatt; + __le64 *gatt; u64 gatt_entries; u64 gart_base; @@ -104,7 +104,7 @@ parisc_agp_create_gatt_table(struct agp_bridge_data *bridge) int i; for (i = 0; i < info->gatt_entries; i++) { - info->gatt[i] = (unsigned long)agp_bridge->scratch_page; + info->gatt[i] = cpu_to_le64(agp_bridge->scratch_page); } return 0; @@ -158,9 +158,9 @@ parisc_agp_insert_memory(struct agp_memory *mem, off_t pg_start, int type) for (k = 0; k < info->io_pages_per_kpage; k++, j++, paddr += info->io_page_size) { - info->gatt[j] = + info->gatt[j] = cpu_to_le64( parisc_agp_mask_memory(agp_bridge, - paddr, type); + paddr, type)); asm_io_fdc(&info->gatt[j]); } } @@ -184,7 +184,7 @@ parisc_agp_remove_memory(struct agp_memory *mem, off_t pg_start, int type) io_pg_start = info->io_pages_per_kpage * pg_start; io_pg_count = info->io_pages_per_kpage * mem->page_count; for (i = io_pg_start; i < io_pg_count + io_pg_start; i++) { - info->gatt[i] = agp_bridge->scratch_page; + info->gatt[i] = cpu_to_le64(agp_bridge->scratch_page); } agp_bridge->driver->tlb_flush(mem); @@ -204,7 +204,8 @@ parisc_agp_mask_memory(struct agp_bridge_data *bridge, dma_addr_t addr, pa |= (ci >> PAGE_SHIFT) & 0xff;/* move CI (8 bits) into lowest byte */ pa |= SBA_PDIR_VALID_BIT; /* set "valid" bit */ - return cpu_to_le64(pa); + /* return native (big-endian) PDIR entry */ + return pa; } static void @@ -251,7 +252,8 @@ static int __init agp_ioc_init(void __iomem *ioc_regs) { struct _parisc_agp_info *info = &parisc_agp_info; - u64 iova_base, *io_pdir, io_tlb_ps; + u64 iova_base, io_tlb_ps; + __le64 *io_pdir; int io_tlb_shift; printk(KERN_INFO DRVPFX "IO PDIR shared with sba_iommu\n"); diff --git a/drivers/clk/qcom/gcc-ipq6018.c b/drivers/clk/qcom/gcc-ipq6018.c index 6120fbbc5de05..f9494fa1b8716 100644 --- a/drivers/clk/qcom/gcc-ipq6018.c +++ b/drivers/clk/qcom/gcc-ipq6018.c @@ -72,7 +72,6 @@ static struct clk_fixed_factor gpll0_out_main_div2 = { &gpll0_main.clkr.hw }, .num_parents = 1, .ops = &clk_fixed_factor_ops, - .flags = CLK_SET_RATE_PARENT, }, }; @@ -86,7 +85,6 @@ static struct clk_alpha_pll_postdiv gpll0 = { &gpll0_main.clkr.hw }, .num_parents = 1, .ops = &clk_alpha_pll_postdiv_ro_ops, - .flags = CLK_SET_RATE_PARENT, }, }; @@ -161,7 +159,6 @@ static struct clk_alpha_pll_postdiv gpll6 = { &gpll6_main.clkr.hw }, .num_parents = 1, .ops = &clk_alpha_pll_postdiv_ro_ops, - .flags = CLK_SET_RATE_PARENT, }, }; @@ -192,7 +189,6 @@ static struct clk_alpha_pll_postdiv gpll4 = { &gpll4_main.clkr.hw }, .num_parents = 1, .ops = &clk_alpha_pll_postdiv_ro_ops, - .flags = CLK_SET_RATE_PARENT, }, }; @@ -243,7 +239,6 @@ static struct clk_alpha_pll_postdiv gpll2 = { &gpll2_main.clkr.hw }, .num_parents = 1, .ops = &clk_alpha_pll_postdiv_ro_ops, - .flags = CLK_SET_RATE_PARENT, }, }; @@ -274,7 +269,6 @@ static struct clk_alpha_pll_postdiv nss_crypto_pll = { &nss_crypto_pll_main.clkr.hw }, .num_parents = 1, .ops = &clk_alpha_pll_postdiv_ro_ops, - .flags = CLK_SET_RATE_PARENT, }, }; diff --git a/drivers/clk/qcom/gcc-ipq8074.c b/drivers/clk/qcom/gcc-ipq8074.c index 63ac2ced76bb9..b7faf12a511a1 100644 --- a/drivers/clk/qcom/gcc-ipq8074.c +++ b/drivers/clk/qcom/gcc-ipq8074.c @@ -75,7 +75,6 @@ static struct clk_fixed_factor gpll0_out_main_div2 = { &gpll0_main.clkr.hw }, .num_parents = 1, .ops = &clk_fixed_factor_ops, - .flags = CLK_SET_RATE_PARENT, }, }; @@ -121,7 +120,6 @@ static struct clk_alpha_pll_postdiv gpll2 = { &gpll2_main.clkr.hw }, .num_parents = 1, .ops = &clk_alpha_pll_postdiv_ro_ops, - .flags = CLK_SET_RATE_PARENT, }, }; @@ -154,7 +152,6 @@ static struct clk_alpha_pll_postdiv gpll4 = { &gpll4_main.clkr.hw }, .num_parents = 1, .ops = &clk_alpha_pll_postdiv_ro_ops, - .flags = CLK_SET_RATE_PARENT, }, }; @@ -188,7 +185,6 @@ static struct clk_alpha_pll_postdiv gpll6 = { &gpll6_main.clkr.hw }, .num_parents = 1, .ops = &clk_alpha_pll_postdiv_ro_ops, - .flags = CLK_SET_RATE_PARENT, }, }; @@ -201,7 +197,6 @@ static struct clk_fixed_factor gpll6_out_main_div2 = { &gpll6_main.clkr.hw }, .num_parents = 1, .ops = &clk_fixed_factor_ops, - .flags = CLK_SET_RATE_PARENT, }, }; @@ -266,7 +261,6 @@ static struct clk_alpha_pll_postdiv nss_crypto_pll = { &nss_crypto_pll_main.clkr.hw }, .num_parents = 1, .ops = &clk_alpha_pll_postdiv_ro_ops, - .flags = CLK_SET_RATE_PARENT, }, }; diff --git a/drivers/clk/socfpga/stratix10-clk.h b/drivers/clk/socfpga/stratix10-clk.h index 75234e0783e1c..83fe4eb3133cb 100644 --- a/drivers/clk/socfpga/stratix10-clk.h +++ b/drivers/clk/socfpga/stratix10-clk.h @@ -7,8 +7,10 @@ #define __STRATIX10_CLK_H struct stratix10_clock_data { - struct clk_hw_onecell_data clk_data; void __iomem *base; + + /* Must be last */ + struct clk_hw_onecell_data clk_data; }; struct stratix10_pll_clock { diff --git a/drivers/clk/visconti/pll.h b/drivers/clk/visconti/pll.h index 01d07f1bf01b1..c4bd40676da4b 100644 --- a/drivers/clk/visconti/pll.h +++ b/drivers/clk/visconti/pll.h @@ -15,8 +15,10 @@ struct visconti_pll_provider { void __iomem *reg_base; - struct clk_hw_onecell_data clk_data; struct device_node *node; + + /* Must be last */ + struct clk_hw_onecell_data clk_data; }; #define VISCONTI_PLL_RATE(_rate, _dacen, _dsmen, \ diff --git a/drivers/clocksource/timer-atmel-tcb.c b/drivers/clocksource/timer-atmel-tcb.c index 27af17c995900..2a90c92a9182a 100644 --- a/drivers/clocksource/timer-atmel-tcb.c +++ b/drivers/clocksource/timer-atmel-tcb.c @@ -315,6 +315,7 @@ static void __init tcb_setup_dual_chan(struct atmel_tc *tc, int mck_divisor_idx) writel(mck_divisor_idx /* likely divide-by-8 */ | ATMEL_TC_WAVE | ATMEL_TC_WAVESEL_UP /* free-run */ + | ATMEL_TC_ASWTRG_SET /* TIOA0 rises at software trigger */ | ATMEL_TC_ACPA_SET /* TIOA0 rises at 0 */ | ATMEL_TC_ACPC_CLEAR, /* (duty cycle 50%) */ tcaddr + ATMEL_TC_REG(0, CMR)); diff --git a/drivers/clocksource/timer-imx-gpt.c b/drivers/clocksource/timer-imx-gpt.c index 28ab4f1a7c713..6a878d227a13b 100644 --- a/drivers/clocksource/timer-imx-gpt.c +++ b/drivers/clocksource/timer-imx-gpt.c @@ -434,12 +434,16 @@ static int __init mxc_timer_init_dt(struct device_node *np, enum imx_gpt_type t return -ENOMEM; imxtm->base = of_iomap(np, 0); - if (!imxtm->base) - return -ENXIO; + if (!imxtm->base) { + ret = -ENXIO; + goto err_kfree; + } imxtm->irq = irq_of_parse_and_map(np, 0); - if (imxtm->irq <= 0) - return -EINVAL; + if (imxtm->irq <= 0) { + ret = -EINVAL; + goto err_kfree; + } imxtm->clk_ipg = of_clk_get_by_name(np, "ipg"); @@ -452,11 +456,15 @@ static int __init mxc_timer_init_dt(struct device_node *np, enum imx_gpt_type t ret = _mxc_timer_init(imxtm); if (ret) - return ret; + goto err_kfree; initialized = 1; return 0; + +err_kfree: + kfree(imxtm); + return ret; } static int __init imx1_timer_init_dt(struct device_node *np) diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index 9a1e194d5cf88..1f6186475715e 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -307,11 +307,11 @@ static int pstate_init_perf(struct amd_cpudata *cpudata) highest_perf = AMD_CPPC_HIGHEST_PERF(cap1); WRITE_ONCE(cpudata->highest_perf, highest_perf); - + WRITE_ONCE(cpudata->max_limit_perf, highest_perf); WRITE_ONCE(cpudata->nominal_perf, AMD_CPPC_NOMINAL_PERF(cap1)); WRITE_ONCE(cpudata->lowest_nonlinear_perf, AMD_CPPC_LOWNONLIN_PERF(cap1)); WRITE_ONCE(cpudata->lowest_perf, AMD_CPPC_LOWEST_PERF(cap1)); - + WRITE_ONCE(cpudata->min_limit_perf, AMD_CPPC_LOWEST_PERF(cap1)); return 0; } @@ -329,11 +329,12 @@ static int cppc_init_perf(struct amd_cpudata *cpudata) highest_perf = cppc_perf.highest_perf; WRITE_ONCE(cpudata->highest_perf, highest_perf); - + WRITE_ONCE(cpudata->max_limit_perf, highest_perf); WRITE_ONCE(cpudata->nominal_perf, cppc_perf.nominal_perf); WRITE_ONCE(cpudata->lowest_nonlinear_perf, cppc_perf.lowest_nonlinear_perf); WRITE_ONCE(cpudata->lowest_perf, cppc_perf.lowest_perf); + WRITE_ONCE(cpudata->min_limit_perf, cppc_perf.lowest_perf); if (cppc_state == AMD_PSTATE_ACTIVE) return 0; @@ -432,6 +433,10 @@ static void amd_pstate_update(struct amd_cpudata *cpudata, u32 min_perf, u64 prev = READ_ONCE(cpudata->cppc_req_cached); u64 value = prev; + min_perf = clamp_t(unsigned long, min_perf, cpudata->min_limit_perf, + cpudata->max_limit_perf); + max_perf = clamp_t(unsigned long, max_perf, cpudata->min_limit_perf, + cpudata->max_limit_perf); des_perf = clamp_t(unsigned long, des_perf, min_perf, max_perf); if ((cppc_state == AMD_PSTATE_GUIDED) && (gov_flags & CPUFREQ_GOV_DYNAMIC_SWITCHING)) { @@ -470,6 +475,22 @@ static int amd_pstate_verify(struct cpufreq_policy_data *policy) return 0; } +static int amd_pstate_update_min_max_limit(struct cpufreq_policy *policy) +{ + u32 max_limit_perf, min_limit_perf; + struct amd_cpudata *cpudata = policy->driver_data; + + max_limit_perf = div_u64(policy->max * cpudata->highest_perf, cpudata->max_freq); + min_limit_perf = div_u64(policy->min * cpudata->highest_perf, cpudata->max_freq); + + WRITE_ONCE(cpudata->max_limit_perf, max_limit_perf); + WRITE_ONCE(cpudata->min_limit_perf, min_limit_perf); + WRITE_ONCE(cpudata->max_limit_freq, policy->max); + WRITE_ONCE(cpudata->min_limit_freq, policy->min); + + return 0; +} + static int amd_pstate_update_freq(struct cpufreq_policy *policy, unsigned int target_freq, bool fast_switch) { @@ -480,6 +501,9 @@ static int amd_pstate_update_freq(struct cpufreq_policy *policy, if (!cpudata->max_freq) return -ENODEV; + if (policy->min != cpudata->min_limit_freq || policy->max != cpudata->max_limit_freq) + amd_pstate_update_min_max_limit(policy); + cap_perf = READ_ONCE(cpudata->highest_perf); min_perf = READ_ONCE(cpudata->lowest_perf); max_perf = cap_perf; @@ -518,7 +542,9 @@ static int amd_pstate_target(struct cpufreq_policy *policy, static unsigned int amd_pstate_fast_switch(struct cpufreq_policy *policy, unsigned int target_freq) { - return amd_pstate_update_freq(policy, target_freq, true); + if (!amd_pstate_update_freq(policy, target_freq, true)) + return target_freq; + return policy->cur; } static void amd_pstate_adjust_perf(unsigned int cpu, @@ -532,6 +558,10 @@ static void amd_pstate_adjust_perf(unsigned int cpu, struct amd_cpudata *cpudata = policy->driver_data; unsigned int target_freq; + if (policy->min != cpudata->min_limit_freq || policy->max != cpudata->max_limit_freq) + amd_pstate_update_min_max_limit(policy); + + cap_perf = READ_ONCE(cpudata->highest_perf); lowest_nonlinear_perf = READ_ONCE(cpudata->lowest_nonlinear_perf); max_freq = READ_ONCE(cpudata->max_freq); @@ -745,6 +775,8 @@ static int amd_pstate_cpu_init(struct cpufreq_policy *policy) /* Initial processor data capability frequencies */ cpudata->max_freq = max_freq; cpudata->min_freq = min_freq; + cpudata->max_limit_freq = max_freq; + cpudata->min_limit_freq = min_freq; cpudata->nominal_freq = nominal_freq; cpudata->lowest_nonlinear_freq = lowest_nonlinear_freq; @@ -850,11 +882,16 @@ static ssize_t show_energy_performance_available_preferences( { int i = 0; int offset = 0; + struct amd_cpudata *cpudata = policy->driver_data; + + if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE) + return sysfs_emit_at(buf, offset, "%s\n", + energy_perf_strings[EPP_INDEX_PERFORMANCE]); while (energy_perf_strings[i] != NULL) offset += sysfs_emit_at(buf, offset, "%s ", energy_perf_strings[i++]); - sysfs_emit_at(buf, offset, "\n"); + offset += sysfs_emit_at(buf, offset, "\n"); return offset; } @@ -1183,16 +1220,25 @@ static int amd_pstate_epp_cpu_exit(struct cpufreq_policy *policy) return 0; } -static void amd_pstate_epp_init(unsigned int cpu) +static void amd_pstate_epp_update_limit(struct cpufreq_policy *policy) { - struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); struct amd_cpudata *cpudata = policy->driver_data; - u32 max_perf, min_perf; + u32 max_perf, min_perf, min_limit_perf, max_limit_perf; u64 value; s16 epp; max_perf = READ_ONCE(cpudata->highest_perf); min_perf = READ_ONCE(cpudata->lowest_perf); + max_limit_perf = div_u64(policy->max * cpudata->highest_perf, cpudata->max_freq); + min_limit_perf = div_u64(policy->min * cpudata->highest_perf, cpudata->max_freq); + + max_perf = clamp_t(unsigned long, max_perf, cpudata->min_limit_perf, + cpudata->max_limit_perf); + min_perf = clamp_t(unsigned long, min_perf, cpudata->min_limit_perf, + cpudata->max_limit_perf); + + WRITE_ONCE(cpudata->max_limit_perf, max_limit_perf); + WRITE_ONCE(cpudata->min_limit_perf, min_limit_perf); value = READ_ONCE(cpudata->cppc_req_cached); @@ -1210,9 +1256,6 @@ static void amd_pstate_epp_init(unsigned int cpu) value &= ~AMD_CPPC_DES_PERF(~0L); value |= AMD_CPPC_DES_PERF(0); - if (cpudata->epp_policy == cpudata->policy) - goto skip_epp; - cpudata->epp_policy = cpudata->policy; /* Get BIOS pre-defined epp value */ @@ -1222,7 +1265,7 @@ static void amd_pstate_epp_init(unsigned int cpu) * This return value can only be negative for shared_memory * systems where EPP register read/write not supported. */ - goto skip_epp; + return; } if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE) @@ -1236,8 +1279,6 @@ static void amd_pstate_epp_init(unsigned int cpu) WRITE_ONCE(cpudata->cppc_req_cached, value); amd_pstate_set_epp(cpudata, epp); -skip_epp: - cpufreq_cpu_put(policy); } static int amd_pstate_epp_set_policy(struct cpufreq_policy *policy) @@ -1252,7 +1293,7 @@ static int amd_pstate_epp_set_policy(struct cpufreq_policy *policy) cpudata->policy = policy->policy; - amd_pstate_epp_init(policy->cpu); + amd_pstate_epp_update_limit(policy); return 0; } diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c index a33df3c66c88c..40a9ff18da068 100644 --- a/drivers/cpufreq/cpufreq_stats.c +++ b/drivers/cpufreq/cpufreq_stats.c @@ -131,23 +131,23 @@ static ssize_t show_trans_table(struct cpufreq_policy *policy, char *buf) len += sysfs_emit_at(buf, len, " From : To\n"); len += sysfs_emit_at(buf, len, " : "); for (i = 0; i < stats->state_num; i++) { - if (len >= PAGE_SIZE) + if (len >= PAGE_SIZE - 1) break; len += sysfs_emit_at(buf, len, "%9u ", stats->freq_table[i]); } - if (len >= PAGE_SIZE) - return PAGE_SIZE; + if (len >= PAGE_SIZE - 1) + return PAGE_SIZE - 1; len += sysfs_emit_at(buf, len, "\n"); for (i = 0; i < stats->state_num; i++) { - if (len >= PAGE_SIZE) + if (len >= PAGE_SIZE - 1) break; len += sysfs_emit_at(buf, len, "%9u: ", stats->freq_table[i]); for (j = 0; j < stats->state_num; j++) { - if (len >= PAGE_SIZE) + if (len >= PAGE_SIZE - 1) break; if (pending) @@ -157,12 +157,12 @@ static ssize_t show_trans_table(struct cpufreq_policy *policy, char *buf) len += sysfs_emit_at(buf, len, "%9u ", count); } - if (len >= PAGE_SIZE) + if (len >= PAGE_SIZE - 1) break; len += sysfs_emit_at(buf, len, "\n"); } - if (len >= PAGE_SIZE) { + if (len >= PAGE_SIZE - 1) { pr_warn_once("cpufreq transition table exceeds PAGE_SIZE. Disabling\n"); return -EFBIG; } diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c index 494d044b9e720..33728c242f66c 100644 --- a/drivers/cpufreq/imx6q-cpufreq.c +++ b/drivers/cpufreq/imx6q-cpufreq.c @@ -327,7 +327,7 @@ static int imx6ul_opp_check_speed_grading(struct device *dev) imx6x_disable_freq_in_opp(dev, 696000000); if (of_machine_is_compatible("fsl,imx6ull")) { - if (val != OCOTP_CFG3_6ULL_SPEED_792MHZ) + if (val < OCOTP_CFG3_6ULL_SPEED_792MHZ) imx6x_disable_freq_in_opp(dev, 792000000); if (val != OCOTP_CFG3_6ULL_SPEED_900MHZ) diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c index 1638c0a7df310..193b0b3a77cda 100644 --- a/drivers/crypto/hisilicon/qm.c +++ b/drivers/crypto/hisilicon/qm.c @@ -847,6 +847,8 @@ static void qm_poll_req_cb(struct hisi_qp *qp) qm_db(qm, qp->qp_id, QM_DOORBELL_CMD_CQ, qp->qp_status.cq_head, 0); atomic_dec(&qp->qp_status.used); + + cond_resched(); } /* set c_flag */ diff --git a/drivers/cxl/core/hdm.c b/drivers/cxl/core/hdm.c index 64e86b786db52..22829267ccd86 100644 --- a/drivers/cxl/core/hdm.c +++ b/drivers/cxl/core/hdm.c @@ -373,10 +373,9 @@ resource_size_t cxl_dpa_resource_start(struct cxl_endpoint_decoder *cxled) { resource_size_t base = -1; - down_read(&cxl_dpa_rwsem); + lockdep_assert_held(&cxl_dpa_rwsem); if (cxled->dpa_res) base = cxled->dpa_res->start; - up_read(&cxl_dpa_rwsem); return base; } diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c index 2c6001592fe20..1e0558d18b965 100644 --- a/drivers/cxl/core/port.c +++ b/drivers/cxl/core/port.c @@ -219,9 +219,9 @@ static ssize_t dpa_resource_show(struct device *dev, struct device_attribute *at char *buf) { struct cxl_endpoint_decoder *cxled = to_cxl_endpoint_decoder(dev); - u64 base = cxl_dpa_resource_start(cxled); - return sysfs_emit(buf, "%#llx\n", base); + guard(rwsem_read)(&cxl_dpa_rwsem); + return sysfs_emit(buf, "%#llx\n", (u64)cxl_dpa_resource_start(cxled)); } static DEVICE_ATTR_RO(dpa_resource); @@ -1242,35 +1242,39 @@ static struct device *grandparent(struct device *dev) return NULL; } +static struct device *endpoint_host(struct cxl_port *endpoint) +{ + struct cxl_port *port = to_cxl_port(endpoint->dev.parent); + + if (is_cxl_root(port)) + return port->uport_dev; + return &port->dev; +} + static void delete_endpoint(void *data) { struct cxl_memdev *cxlmd = data; struct cxl_port *endpoint = cxlmd->endpoint; - struct cxl_port *parent_port; - struct device *parent; - - parent_port = cxl_mem_find_port(cxlmd, NULL); - if (!parent_port) - goto out; - parent = &parent_port->dev; + struct device *host = endpoint_host(endpoint); - device_lock(parent); - if (parent->driver && !endpoint->dead) { - devm_release_action(parent, cxl_unlink_parent_dport, endpoint); - devm_release_action(parent, cxl_unlink_uport, endpoint); - devm_release_action(parent, unregister_port, endpoint); + device_lock(host); + if (host->driver && !endpoint->dead) { + devm_release_action(host, cxl_unlink_parent_dport, endpoint); + devm_release_action(host, cxl_unlink_uport, endpoint); + devm_release_action(host, unregister_port, endpoint); } cxlmd->endpoint = NULL; - device_unlock(parent); - put_device(parent); -out: + device_unlock(host); put_device(&endpoint->dev); + put_device(host); } int cxl_endpoint_autoremove(struct cxl_memdev *cxlmd, struct cxl_port *endpoint) { + struct device *host = endpoint_host(endpoint); struct device *dev = &cxlmd->dev; + get_device(host); get_device(&endpoint->dev); cxlmd->endpoint = endpoint; cxlmd->depth = endpoint->depth; diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c index 85c0881fba442..9d60020c5cb3b 100644 --- a/drivers/cxl/core/region.c +++ b/drivers/cxl/core/region.c @@ -1127,7 +1127,14 @@ static int cxl_port_setup_targets(struct cxl_port *port, } if (is_cxl_root(parent_port)) { - parent_ig = cxlrd->cxlsd.cxld.interleave_granularity; + /* + * Root decoder IG is always set to value in CFMWS which + * may be different than this region's IG. We can use the + * region's IG here since interleave_granularity_store() + * does not allow interleaved host-bridges with + * root IG != region IG. + */ + parent_ig = p->interleave_granularity; parent_iw = cxlrd->cxlsd.cxld.interleave_ways; /* * For purposes of address bit routing, use power-of-2 math for @@ -1675,6 +1682,12 @@ static int cxl_region_attach(struct cxl_region *cxlr, return -ENXIO; } + if (p->nr_targets >= p->interleave_ways) { + dev_dbg(&cxlr->dev, "region already has %d endpoints\n", + p->nr_targets); + return -EINVAL; + } + ep_port = cxled_to_port(cxled); root_port = cxlrd_to_port(cxlrd); dport = cxl_find_dport_by_dev(root_port, ep_port->host_bridge); @@ -1767,7 +1780,7 @@ static int cxl_region_attach(struct cxl_region *cxlr, if (p->nr_targets == p->interleave_ways) { rc = cxl_region_setup_targets(cxlr); if (rc) - goto err_decrement; + return rc; p->state = CXL_CONFIG_ACTIVE; } @@ -1799,12 +1812,6 @@ static int cxl_region_attach(struct cxl_region *cxlr, } return 0; - -err_decrement: - p->nr_targets--; - cxled->pos = -1; - p->targets[pos] = NULL; - return rc; } static int cxl_region_detach(struct cxl_endpoint_decoder *cxled) diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c index 38b4110378de0..eb8b733065b24 100644 --- a/drivers/dma-buf/dma-resv.c +++ b/drivers/dma-buf/dma-resv.c @@ -301,7 +301,7 @@ void dma_resv_add_fence(struct dma_resv *obj, struct dma_fence *fence, dma_resv_list_entry(fobj, i, obj, &old, &old_usage); if ((old->context == fence->context && old_usage >= usage && - dma_fence_is_later(fence, old)) || + dma_fence_is_later_or_same(fence, old)) || dma_fence_is_signaled(old)) { dma_resv_list_set(fobj, i, fence, usage); dma_fence_put(old); diff --git a/drivers/dma/fsl-edma-common.c b/drivers/dma/fsl-edma-common.c index 6a3abe5b17908..b53f46245c377 100644 --- a/drivers/dma/fsl-edma-common.c +++ b/drivers/dma/fsl-edma-common.c @@ -828,6 +828,7 @@ void fsl_edma_free_chan_resources(struct dma_chan *chan) dma_pool_destroy(fsl_chan->tcd_pool); fsl_chan->tcd_pool = NULL; fsl_chan->is_sw = false; + fsl_chan->srcid = 0; } void fsl_edma_cleanup_vchan(struct dma_device *dmadev) diff --git a/drivers/dma/stm32-dma.c b/drivers/dma/stm32-dma.c index 0b30151fb45c4..9840594a6aaa1 100644 --- a/drivers/dma/stm32-dma.c +++ b/drivers/dma/stm32-dma.c @@ -1249,8 +1249,8 @@ static struct dma_async_tx_descriptor *stm32_dma_prep_dma_memcpy( enum dma_slave_buswidth max_width; struct stm32_dma_desc *desc; size_t xfer_count, offset; - u32 num_sgs, best_burst, dma_burst, threshold; - int i; + u32 num_sgs, best_burst, threshold; + int dma_burst, i; num_sgs = DIV_ROUND_UP(len, STM32_DMA_ALIGNED_MAX_DATA_ITEMS); desc = kzalloc(struct_size(desc, sg_req, num_sgs), GFP_NOWAIT); @@ -1268,6 +1268,10 @@ static struct dma_async_tx_descriptor *stm32_dma_prep_dma_memcpy( best_burst = stm32_dma_get_best_burst(len, STM32_DMA_MAX_BURST, threshold, max_width); dma_burst = stm32_dma_get_burst(chan, best_burst); + if (dma_burst < 0) { + kfree(desc); + return NULL; + } stm32_dma_clear_reg(&desc->sg_req[i].chan_reg); desc->sg_req[i].chan_reg.dma_scr = diff --git a/drivers/dma/stm32-mdma.c b/drivers/dma/stm32-mdma.c index bae08b3f55c73..f414efdbd809e 100644 --- a/drivers/dma/stm32-mdma.c +++ b/drivers/dma/stm32-mdma.c @@ -489,7 +489,7 @@ static int stm32_mdma_set_xfer_param(struct stm32_mdma_chan *chan, src_maxburst = chan->dma_config.src_maxburst; dst_maxburst = chan->dma_config.dst_maxburst; - ccr = stm32_mdma_read(dmadev, STM32_MDMA_CCR(chan->id)); + ccr = stm32_mdma_read(dmadev, STM32_MDMA_CCR(chan->id)) & ~STM32_MDMA_CCR_EN; ctcr = stm32_mdma_read(dmadev, STM32_MDMA_CTCR(chan->id)); ctbr = stm32_mdma_read(dmadev, STM32_MDMA_CTBR(chan->id)); @@ -965,7 +965,7 @@ stm32_mdma_prep_dma_memcpy(struct dma_chan *c, dma_addr_t dest, dma_addr_t src, if (!desc) return NULL; - ccr = stm32_mdma_read(dmadev, STM32_MDMA_CCR(chan->id)); + ccr = stm32_mdma_read(dmadev, STM32_MDMA_CCR(chan->id)) & ~STM32_MDMA_CCR_EN; ctcr = stm32_mdma_read(dmadev, STM32_MDMA_CTCR(chan->id)); ctbr = stm32_mdma_read(dmadev, STM32_MDMA_CTBR(chan->id)); cbndtr = stm32_mdma_read(dmadev, STM32_MDMA_CBNDTR(chan->id)); diff --git a/drivers/firewire/core-device.c b/drivers/firewire/core-device.c index aa597cda0d887..2828e9573e90b 100644 --- a/drivers/firewire/core-device.c +++ b/drivers/firewire/core-device.c @@ -717,14 +717,11 @@ static void create_units(struct fw_device *device) fw_unit_attributes, &unit->attribute_group); - if (device_register(&unit->device) < 0) - goto skip_unit; - fw_device_get(device); - continue; - - skip_unit: - kfree(unit); + if (device_register(&unit->device) < 0) { + put_device(&unit->device); + continue; + } } } diff --git a/drivers/firewire/sbp2.c b/drivers/firewire/sbp2.c index 7edf2c95282fa..e779d866022b9 100644 --- a/drivers/firewire/sbp2.c +++ b/drivers/firewire/sbp2.c @@ -1519,9 +1519,9 @@ static int sbp2_scsi_slave_configure(struct scsi_device *sdev) sdev->use_10_for_rw = 1; if (sbp2_param_exclusive_login) { - sdev->manage_system_start_stop = true; - sdev->manage_runtime_start_stop = true; - sdev->manage_shutdown = true; + sdev->manage_system_start_stop = 1; + sdev->manage_runtime_start_stop = 1; + sdev->manage_shutdown = 1; } if (sdev->type == TYPE_ROM) diff --git a/drivers/firmware/arm_scmi/perf.c b/drivers/firmware/arm_scmi/perf.c index 30dedd6ebfde6..e887fd1690434 100644 --- a/drivers/firmware/arm_scmi/perf.c +++ b/drivers/firmware/arm_scmi/perf.c @@ -145,7 +145,6 @@ struct scmi_msg_resp_perf_describe_levels_v4 { struct perf_dom_info { u32 id; bool set_limits; - bool set_perf; bool perf_limit_notify; bool perf_level_notify; bool perf_fastchannels; @@ -153,8 +152,8 @@ struct perf_dom_info { u32 opp_count; u32 sustained_freq_khz; u32 sustained_perf_level; - u32 mult_factor; - char name[SCMI_MAX_STR_SIZE]; + unsigned long mult_factor; + struct scmi_perf_domain_info info; struct scmi_opp opp[MAX_OPPS]; struct scmi_fc_info *fc_info; struct xarray opps_by_idx; @@ -257,7 +256,7 @@ scmi_perf_domain_attributes_get(const struct scmi_protocol_handle *ph, flags = le32_to_cpu(attr->flags); dom_info->set_limits = SUPPORTS_SET_LIMITS(flags); - dom_info->set_perf = SUPPORTS_SET_PERF_LVL(flags); + dom_info->info.set_perf = SUPPORTS_SET_PERF_LVL(flags); dom_info->perf_limit_notify = SUPPORTS_PERF_LIMIT_NOTIFY(flags); dom_info->perf_level_notify = SUPPORTS_PERF_LEVEL_NOTIFY(flags); dom_info->perf_fastchannels = SUPPORTS_PERF_FASTCHANNELS(flags); @@ -269,14 +268,16 @@ scmi_perf_domain_attributes_get(const struct scmi_protocol_handle *ph, dom_info->sustained_perf_level = le32_to_cpu(attr->sustained_perf_level); if (!dom_info->sustained_freq_khz || - !dom_info->sustained_perf_level) + !dom_info->sustained_perf_level || + dom_info->level_indexing_mode) /* CPUFreq converts to kHz, hence default 1000 */ dom_info->mult_factor = 1000; else dom_info->mult_factor = - (dom_info->sustained_freq_khz * 1000) / - dom_info->sustained_perf_level; - strscpy(dom_info->name, attr->name, SCMI_SHORT_NAME_MAX_SIZE); + (dom_info->sustained_freq_khz * 1000UL) + / dom_info->sustained_perf_level; + strscpy(dom_info->info.name, attr->name, + SCMI_SHORT_NAME_MAX_SIZE); } ph->xops->xfer_put(ph, t); @@ -288,7 +289,7 @@ scmi_perf_domain_attributes_get(const struct scmi_protocol_handle *ph, if (!ret && PROTOCOL_REV_MAJOR(version) >= 0x3 && SUPPORTS_EXTENDED_NAMES(flags)) ph->hops->extended_name_get(ph, PERF_DOMAIN_NAME_GET, - dom_info->id, dom_info->name, + dom_info->id, dom_info->info.name, SCMI_MAX_STR_SIZE); if (dom_info->level_indexing_mode) { @@ -423,6 +424,36 @@ scmi_perf_describe_levels_get(const struct scmi_protocol_handle *ph, return ret; } +static int scmi_perf_num_domains_get(const struct scmi_protocol_handle *ph) +{ + struct scmi_perf_info *pi = ph->get_priv(ph); + + return pi->num_domains; +} + +static inline struct perf_dom_info * +scmi_perf_domain_lookup(const struct scmi_protocol_handle *ph, u32 domain) +{ + struct scmi_perf_info *pi = ph->get_priv(ph); + + if (domain >= pi->num_domains) + return ERR_PTR(-EINVAL); + + return pi->dom_info + domain; +} + +static const struct scmi_perf_domain_info * +scmi_perf_info_get(const struct scmi_protocol_handle *ph, u32 domain) +{ + struct perf_dom_info *dom; + + dom = scmi_perf_domain_lookup(ph, domain); + if (IS_ERR(dom)) + return ERR_PTR(-EINVAL); + + return &dom->info; +} + static int scmi_perf_msg_limits_set(const struct scmi_protocol_handle *ph, u32 domain, u32 max_perf, u32 min_perf) { @@ -446,17 +477,6 @@ static int scmi_perf_msg_limits_set(const struct scmi_protocol_handle *ph, return ret; } -static inline struct perf_dom_info * -scmi_perf_domain_lookup(const struct scmi_protocol_handle *ph, u32 domain) -{ - struct scmi_perf_info *pi = ph->get_priv(ph); - - if (domain >= pi->num_domains) - return ERR_PTR(-EINVAL); - - return pi->dom_info + domain; -} - static int __scmi_perf_limits_set(const struct scmi_protocol_handle *ph, struct perf_dom_info *dom, u32 max_perf, u32 min_perf) @@ -780,7 +800,6 @@ static int scmi_dvfs_device_opps_add(const struct scmi_protocol_handle *ph, { int idx, ret, domain; unsigned long freq; - struct scmi_opp *opp; struct perf_dom_info *dom; domain = scmi_dev_domain_id(dev); @@ -791,28 +810,21 @@ static int scmi_dvfs_device_opps_add(const struct scmi_protocol_handle *ph, if (IS_ERR(dom)) return PTR_ERR(dom); - for (opp = dom->opp, idx = 0; idx < dom->opp_count; idx++, opp++) { + for (idx = 0; idx < dom->opp_count; idx++) { if (!dom->level_indexing_mode) - freq = opp->perf * dom->mult_factor; + freq = dom->opp[idx].perf * dom->mult_factor; else - freq = opp->indicative_freq * 1000; + freq = dom->opp[idx].indicative_freq * dom->mult_factor; ret = dev_pm_opp_add(dev, freq, 0); if (ret) { dev_warn(dev, "failed to add opp %luHz\n", freq); - - while (idx-- > 0) { - if (!dom->level_indexing_mode) - freq = (--opp)->perf * dom->mult_factor; - else - freq = (--opp)->indicative_freq * 1000; - dev_pm_opp_remove(dev, freq); - } + dev_pm_opp_remove_all_dynamic(dev); return ret; } dev_dbg(dev, "[%d][%s]:: Registered OPP[%d] %lu\n", - domain, dom->name, idx, freq); + domain, dom->info.name, idx, freq); } return 0; } @@ -851,7 +863,8 @@ static int scmi_dvfs_freq_set(const struct scmi_protocol_handle *ph, u32 domain, } else { struct scmi_opp *opp; - opp = LOOKUP_BY_FREQ(dom->opps_by_freq, freq / 1000); + opp = LOOKUP_BY_FREQ(dom->opps_by_freq, + freq / dom->mult_factor); if (!opp) return -EIO; @@ -885,7 +898,7 @@ static int scmi_dvfs_freq_get(const struct scmi_protocol_handle *ph, u32 domain, if (!opp) return -EIO; - *freq = opp->indicative_freq * 1000; + *freq = opp->indicative_freq * dom->mult_factor; } return ret; @@ -908,7 +921,7 @@ static int scmi_dvfs_est_power_get(const struct scmi_protocol_handle *ph, if (!dom->level_indexing_mode) opp_freq = opp->perf * dom->mult_factor; else - opp_freq = opp->indicative_freq * 1000; + opp_freq = opp->indicative_freq * dom->mult_factor; if (opp_freq < *freq) continue; @@ -948,6 +961,8 @@ scmi_power_scale_get(const struct scmi_protocol_handle *ph) } static const struct scmi_perf_proto_ops perf_proto_ops = { + .num_domains_get = scmi_perf_num_domains_get, + .info_get = scmi_perf_info_get, .limits_set = scmi_perf_limits_set, .limits_get = scmi_perf_limits_get, .level_set = scmi_perf_level_set, diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c index 9d5df683f8821..70b325a2f1f31 100644 --- a/drivers/firmware/efi/libstub/x86-stub.c +++ b/drivers/firmware/efi/libstub/x86-stub.c @@ -307,17 +307,20 @@ static void setup_unaccepted_memory(void) efi_err("Memory acceptance protocol failed\n"); } +static efi_char16_t *efistub_fw_vendor(void) +{ + unsigned long vendor = efi_table_attr(efi_system_table, fw_vendor); + + return (efi_char16_t *)vendor; +} + static const efi_char16_t apple[] = L"Apple"; static void setup_quirks(struct boot_params *boot_params) { - efi_char16_t *fw_vendor = (efi_char16_t *)(unsigned long) - efi_table_attr(efi_system_table, fw_vendor); - - if (!memcmp(fw_vendor, apple, sizeof(apple))) { - if (IS_ENABLED(CONFIG_APPLE_PROPERTIES)) - retrieve_apple_device_properties(boot_params); - } + if (IS_ENABLED(CONFIG_APPLE_PROPERTIES) && + !memcmp(efistub_fw_vendor(), apple, sizeof(apple))) + retrieve_apple_device_properties(boot_params); } /* @@ -799,11 +802,25 @@ static efi_status_t efi_decompress_kernel(unsigned long *kernel_entry) if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && !efi_nokaslr) { u64 range = KERNEL_IMAGE_SIZE - LOAD_PHYSICAL_ADDR - kernel_total_size; + static const efi_char16_t ami[] = L"American Megatrends"; efi_get_seed(seed, sizeof(seed)); virt_addr += (range * seed[1]) >> 32; virt_addr &= ~(CONFIG_PHYSICAL_ALIGN - 1); + + /* + * Older Dell systems with AMI UEFI firmware v2.0 may hang + * while decompressing the kernel if physical address + * randomization is enabled. + * + * https://bugzilla.kernel.org/show_bug.cgi?id=218173 + */ + if (efi_system_table->hdr.revision <= EFI_2_00_SYSTEM_TABLE_REVISION && + !memcmp(efistub_fw_vendor(), ami, sizeof(ami))) { + efi_debug("AMI firmware v2.0 or older detected - disabling physical KASLR\n"); + seed[0] = 0; + } } status = efi_random_alloc(alloc_size, CONFIG_PHYSICAL_ALIGN, &addr, diff --git a/drivers/firmware/efi/unaccepted_memory.c b/drivers/firmware/efi/unaccepted_memory.c index 135278ddaf627..79fb687bb90f9 100644 --- a/drivers/firmware/efi/unaccepted_memory.c +++ b/drivers/firmware/efi/unaccepted_memory.c @@ -100,7 +100,7 @@ void accept_memory(phys_addr_t start, phys_addr_t end) * overlap on physical address level. */ list_for_each_entry(entry, &accepting_list, list) { - if (entry->end < range.start) + if (entry->end <= range.start) continue; if (entry->start >= range.end) continue; diff --git a/drivers/firmware/qcom_scm.c b/drivers/firmware/qcom_scm.c index 06fe8aca870d7..69831f1d91e3f 100644 --- a/drivers/firmware/qcom_scm.c +++ b/drivers/firmware/qcom_scm.c @@ -167,6 +167,12 @@ static enum qcom_scm_convention __get_convention(void) if (likely(qcom_scm_convention != SMC_CONVENTION_UNKNOWN)) return qcom_scm_convention; + /* + * Per the "SMC calling convention specification", the 64-bit calling + * convention can only be used when the client is 64-bit, otherwise + * system will encounter the undefined behaviour. + */ +#if IS_ENABLED(CONFIG_ARM64) /* * Device isn't required as there is only one argument - no device * needed to dma_map_single to secure world @@ -187,6 +193,7 @@ static enum qcom_scm_convention __get_convention(void) forced = true; goto found; } +#endif probed_convention = SMC_CONVENTION_ARM_32; ret = __scm_smc_call(NULL, &desc, probed_convention, &res, true); diff --git a/drivers/gpio/gpio-dwapb.c b/drivers/gpio/gpio-dwapb.c index c22fcaa44a614..6b7d47a52b10a 100644 --- a/drivers/gpio/gpio-dwapb.c +++ b/drivers/gpio/gpio-dwapb.c @@ -283,13 +283,15 @@ static void dwapb_irq_enable(struct irq_data *d) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); struct dwapb_gpio *gpio = to_dwapb_gpio(gc); + irq_hw_number_t hwirq = irqd_to_hwirq(d); unsigned long flags; u32 val; raw_spin_lock_irqsave(&gc->bgpio_lock, flags); - val = dwapb_read(gpio, GPIO_INTEN); - val |= BIT(irqd_to_hwirq(d)); + val = dwapb_read(gpio, GPIO_INTEN) | BIT(hwirq); dwapb_write(gpio, GPIO_INTEN, val); + val = dwapb_read(gpio, GPIO_INTMASK) & ~BIT(hwirq); + dwapb_write(gpio, GPIO_INTMASK, val); raw_spin_unlock_irqrestore(&gc->bgpio_lock, flags); } @@ -297,12 +299,14 @@ static void dwapb_irq_disable(struct irq_data *d) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); struct dwapb_gpio *gpio = to_dwapb_gpio(gc); + irq_hw_number_t hwirq = irqd_to_hwirq(d); unsigned long flags; u32 val; raw_spin_lock_irqsave(&gc->bgpio_lock, flags); - val = dwapb_read(gpio, GPIO_INTEN); - val &= ~BIT(irqd_to_hwirq(d)); + val = dwapb_read(gpio, GPIO_INTMASK) | BIT(hwirq); + dwapb_write(gpio, GPIO_INTMASK, val); + val = dwapb_read(gpio, GPIO_INTEN) & ~BIT(hwirq); dwapb_write(gpio, GPIO_INTEN, val); raw_spin_unlock_irqrestore(&gc->bgpio_lock, flags); } diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c index 51e41676de0b8..5d04720107ef5 100644 --- a/drivers/gpio/gpiolib-acpi.c +++ b/drivers/gpio/gpiolib-acpi.c @@ -1655,6 +1655,26 @@ static const struct dmi_system_id gpiolib_acpi_quirks[] __initconst = { .ignore_wake = "SYNA1202:00@16", }, }, + { + /* + * On the Peaq C1010 2-in-1 INT33FC:00 pin 3 is connected to + * a "dolby" button. At the ACPI level an _AEI event-handler + * is connected which sets an ACPI variable to 1 on both + * edges. This variable can be polled + cleared to 0 using + * WMI. But since the variable is set on both edges the WMI + * interface is pretty useless even when polling. + * So instead the x86-android-tablets code instantiates + * a gpio-keys platform device for it. + * Ignore the _AEI handler for the pin, so that it is not busy. + */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "PEAQ"), + DMI_MATCH(DMI_PRODUCT_NAME, "PEAQ PMM C1010 MD99187"), + }, + .driver_data = &(struct acpi_gpiolib_dmi_quirk) { + .ignore_interrupt = "INT33FC:00@3", + }, + }, {} /* Terminating entry */ }; diff --git a/drivers/gpio/gpiolib-cdev.c b/drivers/gpio/gpiolib-cdev.c index e39d344feb289..4f3e66ece7f78 100644 --- a/drivers/gpio/gpiolib-cdev.c +++ b/drivers/gpio/gpiolib-cdev.c @@ -2482,10 +2482,7 @@ static int lineinfo_unwatch(struct gpio_chardev_data *cdev, void __user *ip) return 0; } -/* - * gpio_ioctl() - ioctl handler for the GPIO chardev - */ -static long gpio_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +static long gpio_ioctl_unlocked(struct file *file, unsigned int cmd, unsigned long arg) { struct gpio_chardev_data *cdev = file->private_data; struct gpio_device *gdev = cdev->gdev; @@ -2522,6 +2519,17 @@ static long gpio_ioctl(struct file *file, unsigned int cmd, unsigned long arg) } } +/* + * gpio_ioctl() - ioctl handler for the GPIO chardev + */ +static long gpio_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + struct gpio_chardev_data *cdev = file->private_data; + + return call_ioctl_locked(file, cmd, arg, cdev->gdev, + gpio_ioctl_unlocked); +} + #ifdef CONFIG_COMPAT static long gpio_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg) diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c index 531faabead0f4..d9525d95e818d 100644 --- a/drivers/gpio/gpiolib-of.c +++ b/drivers/gpio/gpiolib-of.c @@ -512,6 +512,10 @@ static struct gpio_desc *of_find_gpio_rename(struct device_node *np, #if IS_ENABLED(CONFIG_SND_SOC_CS42L56) { "reset", "cirrus,gpio-nreset", "cirrus,cs42l56" }, #endif +#if IS_ENABLED(CONFIG_SND_SOC_MT2701_CS42448) + { "i2s1-in-sel-gpio1", NULL, "mediatek,mt2701-cs42448-machine" }, + { "i2s1-in-sel-gpio2", NULL, "mediatek,mt2701-cs42448-machine" }, +#endif #if IS_ENABLED(CONFIG_SND_SOC_TLV320AIC3X) { "reset", "gpio-reset", "ti,tlv320aic3x" }, { "reset", "gpio-reset", "ti,tlv320aic33" }, diff --git a/drivers/gpio/gpiolib-sysfs.c b/drivers/gpio/gpiolib-sysfs.c index 50503a4525eb0..c7c5c19ebc66f 100644 --- a/drivers/gpio/gpiolib-sysfs.c +++ b/drivers/gpio/gpiolib-sysfs.c @@ -474,14 +474,17 @@ static ssize_t export_store(const struct class *class, goto done; status = gpiod_set_transitory(desc, false); - if (!status) { - status = gpiod_export(desc, true); - if (status < 0) - gpiod_free(desc); - else - set_bit(FLAG_SYSFS, &desc->flags); + if (status) { + gpiod_free(desc); + goto done; } + status = gpiod_export(desc, true); + if (status < 0) + gpiod_free(desc); + else + set_bit(FLAG_SYSFS, &desc->flags); + done: if (status) pr_debug("%s: status %d\n", __func__, status); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c index 38ccec913f009..f3a09ecb76992 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c @@ -29,6 +29,7 @@ #include "amdgpu.h" #include "atom.h" +#include #include #include #include @@ -287,6 +288,10 @@ static bool amdgpu_atrm_get_bios(struct amdgpu_device *adev) if (adev->flags & AMD_IS_APU) return false; + /* ATRM is for on-platform devices only */ + if (dev_is_removable(&adev->pdev->dev)) + return false; + while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_VGA << 8, pdev)) != NULL) { dhandle = ACPI_HANDLE(&pdev->dev); if (!dhandle) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c index b6298e901cbd4..9a53ca555e708 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c @@ -183,6 +183,7 @@ int amdgpu_bo_list_get(struct amdgpu_fpriv *fpriv, int id, } rcu_read_unlock(); + *result = NULL; return -ENOENT; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index d93a8961274c6..c0a3afe81bb1a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -207,7 +207,7 @@ static int amdgpu_cs_pass1(struct amdgpu_cs_parser *p, } for (i = 0; i < p->nchunks; i++) { - struct drm_amdgpu_cs_chunk __user **chunk_ptr = NULL; + struct drm_amdgpu_cs_chunk __user *chunk_ptr = NULL; struct drm_amdgpu_cs_chunk user_chunk; uint32_t __user *cdata; @@ -1411,7 +1411,7 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) if (r == -ENOMEM) DRM_ERROR("Not enough memory for command submission!\n"); else if (r != -ERESTARTSYS && r != -EAGAIN) - DRM_ERROR("Failed to process the buffer list %d!\n", r); + DRM_DEBUG("Failed to process the buffer list %d!\n", r); goto error_fini; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c index a4faea4fa0b59..05405da51e7a2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c @@ -748,6 +748,9 @@ static ssize_t amdgpu_debugfs_regs_smc_read(struct file *f, char __user *buf, ssize_t result = 0; int r; + if (!adev->smc_rreg) + return -EPERM; + if (size & 0x3 || *pos & 0x3) return -EINVAL; @@ -804,6 +807,9 @@ static ssize_t amdgpu_debugfs_regs_smc_write(struct file *f, const char __user * ssize_t result = 0; int r; + if (!adev->smc_wreg) + return -EPERM; + if (size & 0x3 || *pos & 0x3) return -EINVAL; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 2b8356699f235..94e91516952c4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -43,6 +43,7 @@ #include #include #include +#include #include #include #include @@ -2018,7 +2019,6 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev) */ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev) { - struct drm_device *dev = adev_to_drm(adev); struct pci_dev *parent; int i, r; bool total; @@ -2089,7 +2089,7 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev) (amdgpu_is_atpx_hybrid() || amdgpu_has_atpx_dgpu_power_cntl()) && ((adev->flags & AMD_IS_APU) == 0) && - !pci_is_thunderbolt_attached(to_pci_dev(dev->dev))) + !dev_is_removable(&adev->pdev->dev)) adev->flags |= AMD_IS_PX; if (!(adev->flags & AMD_IS_APU)) { @@ -2103,6 +2103,8 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev) adev->pm.pp_feature &= ~PP_GFXOFF_MASK; if (amdgpu_sriov_vf(adev) && adev->asic_type == CHIP_SIENNA_CICHLID) adev->pm.pp_feature &= ~PP_OVERDRIVE_MASK; + if (!amdgpu_device_pcie_dynamic_switching_supported()) + adev->pm.pp_feature &= ~PP_PCIE_DPM_MASK; total = true; for (i = 0; i < adev->num_ip_blocks; i++) { @@ -3476,10 +3478,6 @@ static void amdgpu_device_set_mcbp(struct amdgpu_device *adev) adev->gfx.mcbp = true; else if (amdgpu_mcbp == 0) adev->gfx.mcbp = false; - else if ((adev->ip_versions[GC_HWIP][0] >= IP_VERSION(9, 0, 0)) && - (adev->ip_versions[GC_HWIP][0] < IP_VERSION(10, 0, 0)) && - adev->gfx.num_gfx_rings) - adev->gfx.mcbp = true; if (amdgpu_sriov_vf(adev)) adev->gfx.mcbp = true; @@ -3901,7 +3899,7 @@ int amdgpu_device_init(struct amdgpu_device *adev, px = amdgpu_device_supports_px(ddev); - if (px || (!pci_is_thunderbolt_attached(adev->pdev) && + if (px || (!dev_is_removable(&adev->pdev->dev) && apple_gmux_detect(NULL, NULL))) vga_switcheroo_register_client(adev->pdev, &amdgpu_switcheroo_ops, px); @@ -4046,7 +4044,7 @@ void amdgpu_device_fini_sw(struct amdgpu_device *adev) px = amdgpu_device_supports_px(adev_to_drm(adev)); - if (px || (!pci_is_thunderbolt_attached(adev->pdev) && + if (px || (!dev_is_removable(&adev->pdev->dev) && apple_gmux_detect(NULL, NULL))) vga_switcheroo_unregister_client(adev->pdev); @@ -5183,7 +5181,8 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, * Flush RAM to disk so that after reboot * the user can read log and see why the system rebooted. */ - if (need_emergency_restart && amdgpu_ras_get_context(adev)->reboot) { + if (need_emergency_restart && amdgpu_ras_get_context(adev) && + amdgpu_ras_get_context(adev)->reboot) { DRM_WARN("Emergency reboot."); ksys_sync_helper(); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c index 7d5e7ad28ba82..68a901287264f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c @@ -93,6 +93,7 @@ MODULE_FIRMWARE(FIRMWARE_IP_DISCOVERY); #define mmRCC_CONFIG_MEMSIZE 0xde3 +#define mmMP0_SMN_C2PMSG_33 0x16061 #define mmMM_INDEX 0x0 #define mmMM_INDEX_HI 0x6 #define mmMM_DATA 0x1 @@ -231,8 +232,26 @@ static int amdgpu_discovery_read_binary_from_sysmem(struct amdgpu_device *adev, static int amdgpu_discovery_read_binary_from_mem(struct amdgpu_device *adev, uint8_t *binary) { - uint64_t vram_size = (uint64_t)RREG32(mmRCC_CONFIG_MEMSIZE) << 20; - int ret = 0; + uint64_t vram_size; + u32 msg; + int i, ret = 0; + + /* It can take up to a second for IFWI init to complete on some dGPUs, + * but generally it should be in the 60-100ms range. Normally this starts + * as soon as the device gets power so by the time the OS loads this has long + * completed. However, when a card is hotplugged via e.g., USB4, we need to + * wait for this to complete. Once the C2PMSG is updated, we can + * continue. + */ + if (dev_is_removable(&adev->pdev->dev)) { + for (i = 0; i < 1000; i++) { + msg = RREG32(mmMP0_SMN_C2PMSG_33); + if (msg & 0x80000000) + break; + msleep(1); + } + } + vram_size = (uint64_t)RREG32(mmRCC_CONFIG_MEMSIZE) << 20; if (vram_size) { uint64_t pos = vram_size - DISCOVERY_TMR_OFFSET; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index 363e6a2cad8c2..578aeba49ea8e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -340,14 +340,11 @@ int amdgpu_display_crtc_set_config(struct drm_mode_set *set, adev->have_disp_power_ref = true; return ret; } - /* if we have no active crtcs, then drop the power ref - * we got before + /* if we have no active crtcs, then go to + * drop the power ref we got before */ - if (!active && adev->have_disp_power_ref) { - pm_runtime_put_autosuspend(dev->dev); + if (!active && adev->have_disp_power_ref) adev->have_disp_power_ref = false; - } - out: /* drop the power reference we got coming in here */ pm_runtime_put_autosuspend(dev->dev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_doorbell.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_doorbell.h index 09f6727e7c73a..4a8b33f55f6bc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_doorbell.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_doorbell.h @@ -357,8 +357,9 @@ int amdgpu_doorbell_init(struct amdgpu_device *adev); void amdgpu_doorbell_fini(struct amdgpu_device *adev); int amdgpu_doorbell_create_kernel_doorbells(struct amdgpu_device *adev); uint32_t amdgpu_doorbell_index_on_bar(struct amdgpu_device *adev, - struct amdgpu_bo *db_bo, - uint32_t doorbell_index); + struct amdgpu_bo *db_bo, + uint32_t doorbell_index, + uint32_t db_size); #define RDOORBELL32(index) amdgpu_mm_rdoorbell(adev, (index)) #define WDOORBELL32(index, v) amdgpu_mm_wdoorbell(adev, (index), (v)) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_doorbell_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_doorbell_mgr.c index 8eee5d783a92b..3f3662e8b8710 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_doorbell_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_doorbell_mgr.c @@ -113,20 +113,25 @@ void amdgpu_mm_wdoorbell64(struct amdgpu_device *adev, u32 index, u64 v) * * @adev: amdgpu_device pointer * @db_bo: doorbell object's bo - * @db_index: doorbell relative index in this doorbell object + * @doorbell_index: doorbell relative index in this doorbell object + * @db_size: doorbell size is in byte * * returns doorbell's absolute index in BAR */ uint32_t amdgpu_doorbell_index_on_bar(struct amdgpu_device *adev, - struct amdgpu_bo *db_bo, - uint32_t doorbell_index) + struct amdgpu_bo *db_bo, + uint32_t doorbell_index, + uint32_t db_size) { int db_bo_offset; db_bo_offset = amdgpu_bo_gpu_offset_no_check(db_bo); - /* doorbell index is 32 bit but doorbell's size is 64-bit, so *2 */ - return db_bo_offset / sizeof(u32) + doorbell_index * 2; + /* doorbell index is 32 bit but doorbell's size can be 32 bit + * or 64 bit, so *db_size(in byte)/4 for alignment. + */ + return db_bo_offset / sizeof(u32) + doorbell_index * + DIV_ROUND_UP(db_size, 4); } /** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 81edf66dbea8b..2c35036e4ba25 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -2195,6 +2195,8 @@ static int amdgpu_pci_probe(struct pci_dev *pdev, pm_runtime_mark_last_busy(ddev->dev); pm_runtime_put_autosuspend(ddev->dev); + pci_wake_from_d3(pdev, TRUE); + /* * For runpm implemented via BACO, PMFW will handle the * timing for BACO in and out: diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index ca4d2d430e28c..a1b15d0d6c489 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -962,6 +962,7 @@ static int amdgpu_debugfs_gem_info_show(struct seq_file *m, void *unused) list_for_each_entry(file, &dev->filelist, lhead) { struct task_struct *task; struct drm_gem_object *gobj; + struct pid *pid; int id; /* @@ -971,8 +972,9 @@ static int amdgpu_debugfs_gem_info_show(struct seq_file *m, void *unused) * Therefore, we need to protect this ->comm access using RCU. */ rcu_read_lock(); - task = pid_task(file->pid, PIDTYPE_TGID); - seq_printf(m, "pid %8d command %s:\n", pid_nr(file->pid), + pid = rcu_dereference(file->pid); + task = pid_task(pid, PIDTYPE_TGID); + seq_printf(m, "pid %8d command %s:\n", pid_nr(pid), task ? task->comm : ""); rcu_read_unlock(); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c index b6015157763af..6aa75052309ff 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c @@ -556,8 +556,20 @@ static void amdgpu_mes_queue_init_mqd(struct amdgpu_device *adev, mqd_prop.hqd_queue_priority = p->hqd_queue_priority; mqd_prop.hqd_active = false; + if (p->queue_type == AMDGPU_RING_TYPE_GFX || + p->queue_type == AMDGPU_RING_TYPE_COMPUTE) { + mutex_lock(&adev->srbm_mutex); + amdgpu_gfx_select_me_pipe_q(adev, p->ring->me, p->ring->pipe, 0, 0, 0); + } + mqd_mgr->init_mqd(adev, q->mqd_cpu_ptr, &mqd_prop); + if (p->queue_type == AMDGPU_RING_TYPE_GFX || + p->queue_type == AMDGPU_RING_TYPE_COMPUTE) { + amdgpu_gfx_select_me_pipe_q(adev, 0, 0, 0, 0, 0); + mutex_unlock(&adev->srbm_mutex); + } + amdgpu_bo_unreserve(q->mqd_obj); } @@ -993,9 +1005,13 @@ int amdgpu_mes_add_ring(struct amdgpu_device *adev, int gang_id, switch (queue_type) { case AMDGPU_RING_TYPE_GFX: ring->funcs = adev->gfx.gfx_ring[0].funcs; + ring->me = adev->gfx.gfx_ring[0].me; + ring->pipe = adev->gfx.gfx_ring[0].pipe; break; case AMDGPU_RING_TYPE_COMPUTE: ring->funcs = adev->gfx.compute_ring[0].funcs; + ring->me = adev->gfx.compute_ring[0].me; + ring->pipe = adev->gfx.compute_ring[0].pipe; break; case AMDGPU_RING_TYPE_SDMA: ring->funcs = adev->sdma.instance[0].ring.funcs; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 163445baa4fc8..6f6341f702789 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -1373,7 +1373,8 @@ static void amdgpu_ras_sysfs_remove_bad_page_node(struct amdgpu_device *adev) { struct amdgpu_ras *con = amdgpu_ras_get_context(adev); - sysfs_remove_file_from_group(&adev->dev->kobj, + if (adev->dev->kobj.sd) + sysfs_remove_file_from_group(&adev->dev->kobj, &con->badpages_attr.attr, RAS_FS_NAME); } @@ -1390,7 +1391,8 @@ static int amdgpu_ras_sysfs_remove_feature_node(struct amdgpu_device *adev) .attrs = attrs, }; - sysfs_remove_group(&adev->dev->kobj, &group); + if (adev->dev->kobj.sd) + sysfs_remove_group(&adev->dev->kobj, &group); return 0; } @@ -1437,7 +1439,8 @@ int amdgpu_ras_sysfs_remove(struct amdgpu_device *adev, if (!obj || !obj->attr_inuse) return -EINVAL; - sysfs_remove_file_from_group(&adev->dev->kobj, + if (adev->dev->kobj.sd) + sysfs_remove_file_from_group(&adev->dev->kobj, &obj->sysfs_attr.attr, RAS_FS_NAME); obj->attr_inuse = 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c index 595d5e535aca6..9d82701d365bb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c @@ -214,6 +214,12 @@ static bool __get_eeprom_i2c_addr(struct amdgpu_device *adev, control->i2c_address = EEPROM_I2C_MADDR_0; return true; case IP_VERSION(13, 0, 0): + if (strnstr(atom_ctx->vbios_pn, "D707", + sizeof(atom_ctx->vbios_pn))) + control->i2c_address = EEPROM_I2C_MADDR_0; + else + control->i2c_address = EEPROM_I2C_MADDR_4; + return true; case IP_VERSION(13, 0, 6): case IP_VERSION(13, 0, 10): control->i2c_address = EEPROM_I2C_MADDR_4; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c index 36b55d2bd51a9..03b4bcfca1963 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c @@ -292,8 +292,15 @@ int amdgpu_vcn_suspend(struct amdgpu_device *adev) void *ptr; int i, idx; + bool in_ras_intr = amdgpu_ras_intr_triggered(); + cancel_delayed_work_sync(&adev->vcn.idle_work); + /* err_event_athub will corrupt VCPU buffer, so we need to + * restore fw data and clear buffer in amdgpu_vcn_resume() */ + if (in_ras_intr) + return 0; + for (i = 0; i < adev->vcn.num_vcn_inst; ++i) { if (adev->vcn.harvest_config & (1 << i)) continue; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c index 7148a216ae2fe..db6fc0cb18eb8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c @@ -239,6 +239,8 @@ static int amdgpu_vkms_conn_get_modes(struct drm_connector *connector) for (i = 0; i < ARRAY_SIZE(common_modes); i++) { mode = drm_cvt_mode(dev, common_modes[i].w, common_modes[i].h, 60, false, false, false); + if (!mode) + continue; drm_mode_probed_add(connector, mode); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 82f25996ff5ef..9fe1278fd5861 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -285,6 +285,7 @@ static void amdgpu_vm_bo_reset_state_machine(struct amdgpu_vm *vm) list_for_each_entry_safe(vm_bo, tmp, &vm->idle, vm_status) { struct amdgpu_bo *bo = vm_bo->bo; + vm_bo->moved = true; if (!bo || bo->tbo.type != ttm_bo_type_kernel) list_move(&vm_bo->vm_status, &vm_bo->vm->moved); else if (bo->parent) @@ -1095,8 +1096,8 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va, bo = gem_to_amdgpu_bo(gobj); } mem = bo->tbo.resource; - if (mem->mem_type == TTM_PL_TT || - mem->mem_type == AMDGPU_PL_PREEMPT) + if (mem && (mem->mem_type == TTM_PL_TT || + mem->mem_type == AMDGPU_PL_PREEMPT)) pages_addr = bo->tbo.ttm->dma_address; } @@ -2125,7 +2126,8 @@ long amdgpu_vm_wait_idle(struct amdgpu_vm *vm, long timeout) * Returns: * 0 for success, error for failure. */ -int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, int32_t xcp_id) +int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, + int32_t xcp_id) { struct amdgpu_bo *root_bo; struct amdgpu_bo_vm *root; @@ -2144,6 +2146,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, int32_t xcp INIT_LIST_HEAD(&vm->done); INIT_LIST_HEAD(&vm->pt_freed); INIT_WORK(&vm->pt_free_work, amdgpu_vm_pt_free_work); + INIT_KFIFO(vm->faults); r = amdgpu_vm_init_entities(adev, vm); if (r) @@ -2178,34 +2181,33 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, int32_t xcp false, &root, xcp_id); if (r) goto error_free_delayed; - root_bo = &root->bo; + + root_bo = amdgpu_bo_ref(&root->bo); r = amdgpu_bo_reserve(root_bo, true); - if (r) - goto error_free_root; + if (r) { + amdgpu_bo_unref(&root->shadow); + amdgpu_bo_unref(&root_bo); + goto error_free_delayed; + } + amdgpu_vm_bo_base_init(&vm->root, vm, root_bo); r = dma_resv_reserve_fences(root_bo->tbo.base.resv, 1); if (r) - goto error_unreserve; - - amdgpu_vm_bo_base_init(&vm->root, vm, root_bo); + goto error_free_root; r = amdgpu_vm_pt_clear(adev, vm, root, false); if (r) - goto error_unreserve; + goto error_free_root; amdgpu_bo_unreserve(vm->root.bo); - - INIT_KFIFO(vm->faults); + amdgpu_bo_unref(&root_bo); return 0; -error_unreserve: - amdgpu_bo_unreserve(vm->root.bo); - error_free_root: - amdgpu_bo_unref(&root->shadow); + amdgpu_vm_pt_free_root(adev, vm); + amdgpu_bo_unreserve(vm->root.bo); amdgpu_bo_unref(&root_bo); - vm->root.bo = NULL; error_free_delayed: dma_fence_put(vm->last_tlb_flush); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c index 96d601e209b8b..0d51222f6f8eb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c @@ -642,13 +642,14 @@ static void amdgpu_vm_pt_free(struct amdgpu_vm_bo_base *entry) if (!entry->bo) return; + + entry->bo->vm_bo = NULL; shadow = amdgpu_bo_shadowed(entry->bo); if (shadow) { ttm_bo_set_bulk_move(&shadow->tbo, NULL); amdgpu_bo_unref(&shadow); } ttm_bo_set_bulk_move(&entry->bo->tbo, NULL); - entry->bo->vm_bo = NULL; spin_lock(&entry->vm->status_lock); list_del(&entry->vm_status); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index 43d066bc5245b..b346eb0a0db11 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -83,6 +83,10 @@ MODULE_FIRMWARE("amdgpu/gc_11_0_4_me.bin"); MODULE_FIRMWARE("amdgpu/gc_11_0_4_mec.bin"); MODULE_FIRMWARE("amdgpu/gc_11_0_4_rlc.bin"); +static const struct soc15_reg_golden golden_settings_gc_11_0[] = { + SOC15_REG_GOLDEN_VALUE(GC, 0, regTCP_CNTL, 0x20000000, 0x20000000) +}; + static const struct soc15_reg_golden golden_settings_gc_11_0_1[] = { SOC15_REG_GOLDEN_VALUE(GC, 0, regCGTT_GS_NGG_CLK_CTRL, 0x9fff8fff, 0x00000010), @@ -275,6 +279,10 @@ static void gfx_v11_0_init_golden_registers(struct amdgpu_device *adev) default: break; } + soc15_program_register_sequence(adev, + golden_settings_gc_11_0, + (const u32)ARRAY_SIZE(golden_settings_gc_11_0)); + } static void gfx_v11_0_write_data_to_reg(struct amdgpu_ring *ring, int eng_sel, @@ -390,7 +398,7 @@ static int gfx_v11_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) adev->wb.wb[index] = cpu_to_le32(0xCAFEDEAD); cpu_ptr = &adev->wb.wb[index]; - r = amdgpu_ib_get(adev, NULL, 16, AMDGPU_IB_POOL_DIRECT, &ib); + r = amdgpu_ib_get(adev, NULL, 20, AMDGPU_IB_POOL_DIRECT, &ib); if (r) { DRM_ERROR("amdgpu: failed to get ib (%ld).\n", r); goto err1; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index 885ebd703260f..1943beb135c4c 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -883,8 +883,8 @@ static int gfx_v8_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index * 4); adev->wb.wb[index] = cpu_to_le32(0xCAFEDEAD); memset(&ib, 0, sizeof(ib)); - r = amdgpu_ib_get(adev, NULL, 16, - AMDGPU_IB_POOL_DIRECT, &ib); + + r = amdgpu_ib_get(adev, NULL, 20, AMDGPU_IB_POOL_DIRECT, &ib); if (r) goto err1; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index fd61574a737cb..2e23d08b45f4a 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -1039,8 +1039,8 @@ static int gfx_v9_0_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index * 4); adev->wb.wb[index] = cpu_to_le32(0xCAFEDEAD); memset(&ib, 0, sizeof(ib)); - r = amdgpu_ib_get(adev, NULL, 16, - AMDGPU_IB_POOL_DIRECT, &ib); + + r = amdgpu_ib_get(adev, NULL, 20, AMDGPU_IB_POOL_DIRECT, &ib); if (r) goto err1; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c index 18ce5fe45f6f8..e481ef73af6e5 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c @@ -296,8 +296,8 @@ static int gfx_v9_4_3_ring_test_ib(struct amdgpu_ring *ring, long timeout) gpu_addr = adev->wb.gpu_addr + (index * 4); adev->wb.wb[index] = cpu_to_le32(0xCAFEDEAD); memset(&ib, 0, sizeof(ib)); - r = amdgpu_ib_get(adev, NULL, 16, - AMDGPU_IB_POOL_DIRECT, &ib); + + r = amdgpu_ib_get(adev, NULL, 20, AMDGPU_IB_POOL_DIRECT, &ib); if (r) goto err1; diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index f9a5a2c0573e4..89550d3df68d8 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -2220,8 +2220,6 @@ static int gmc_v9_0_sw_fini(void *handle) if (adev->ip_versions[GC_HWIP][0] == IP_VERSION(9, 4, 3)) amdgpu_gmc_sysfs_fini(adev); - adev->gmc.num_mem_partitions = 0; - kfree(adev->gmc.mem_partitions); amdgpu_gmc_ras_fini(adev); amdgpu_gem_force_release(adev); @@ -2235,6 +2233,9 @@ static int gmc_v9_0_sw_fini(void *handle) amdgpu_bo_free_kernel(&adev->gmc.pdb0_bo, NULL, &adev->gmc.ptr_pdb0); amdgpu_bo_fini(adev); + adev->gmc.num_mem_partitions = 0; + kfree(adev->gmc.mem_partitions); + return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c index 784c4e0774707..3d8e579d5c4e8 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c @@ -130,6 +130,9 @@ static void mmhub_v1_8_init_system_aperture_regs(struct amdgpu_device *adev) uint64_t value; int i; + if (amdgpu_sriov_vf(adev)) + return; + inst_mask = adev->aid_mask; for_each_inst(i, inst_mask) { /* Program the AGP BAR */ @@ -139,9 +142,6 @@ static void mmhub_v1_8_init_system_aperture_regs(struct amdgpu_device *adev) WREG32_SOC15(MMHUB, i, regMC_VM_AGP_TOP, adev->gmc.agp_end >> 24); - if (amdgpu_sriov_vf(adev)) - return; - /* Program the system aperture low logical page number. */ WREG32_SOC15(MMHUB, i, regMC_VM_SYSTEM_APERTURE_LOW_ADDR, min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18); diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c index 4038455d79984..ef368ca79a668 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c @@ -28,6 +28,7 @@ #include "nbio/nbio_2_3_offset.h" #include "nbio/nbio_2_3_sh_mask.h" #include +#include #include #define smnPCIE_CONFIG_CNTL 0x11180044 @@ -361,7 +362,7 @@ static void nbio_v2_3_enable_aspm(struct amdgpu_device *adev, data |= NAVI10_PCIE__LC_L0S_INACTIVITY_DEFAULT << PCIE_LC_CNTL__LC_L0S_INACTIVITY__SHIFT; - if (pci_is_thunderbolt_attached(adev->pdev)) + if (dev_is_removable(&adev->pdev->dev)) data |= NAVI10_PCIE__LC_L1_INACTIVITY_TBT_DEFAULT << PCIE_LC_CNTL__LC_L1_INACTIVITY__SHIFT; else data |= NAVI10_PCIE__LC_L1_INACTIVITY_DEFAULT << PCIE_LC_CNTL__LC_L1_INACTIVITY__SHIFT; @@ -480,7 +481,7 @@ static void nbio_v2_3_program_aspm(struct amdgpu_device *adev) def = data = RREG32_PCIE(smnPCIE_LC_CNTL); data |= NAVI10_PCIE__LC_L0S_INACTIVITY_DEFAULT << PCIE_LC_CNTL__LC_L0S_INACTIVITY__SHIFT; - if (pci_is_thunderbolt_attached(adev->pdev)) + if (dev_is_removable(&adev->pdev->dev)) data |= NAVI10_PCIE__LC_L1_INACTIVITY_TBT_DEFAULT << PCIE_LC_CNTL__LC_L1_INACTIVITY__SHIFT; else data |= NAVI10_PCIE__LC_L1_INACTIVITY_DEFAULT << PCIE_LC_CNTL__LC_L1_INACTIVITY__SHIFT; diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c index 469eed084976c..fe1995ed13be7 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c @@ -59,6 +59,9 @@ MODULE_FIRMWARE("amdgpu/psp_14_0_0_ta.bin"); /* Read USB-PD from LFB */ #define GFX_CMD_USB_PD_USE_LFB 0x480 +/* Retry times for vmbx ready wait */ +#define PSP_VMBX_POLLING_LIMIT 3000 + /* VBIOS gfl defines */ #define MBOX_READY_MASK 0x80000000 #define MBOX_STATUS_MASK 0x0000FFFF @@ -138,7 +141,7 @@ static int psp_v13_0_wait_for_vmbx_ready(struct psp_context *psp) struct amdgpu_device *adev = psp->adev; int retry_loop, ret; - for (retry_loop = 0; retry_loop < 70; retry_loop++) { + for (retry_loop = 0; retry_loop < PSP_VMBX_POLLING_LIMIT; retry_loop++) { /* Wait for bootloader to signify that is ready having bit 31 of C2PMSG_33 set to 1 */ ret = psp_wait_for( @@ -158,14 +161,18 @@ static int psp_v13_0_wait_for_vmbx_ready(struct psp_context *psp) static int psp_v13_0_wait_for_bootloader(struct psp_context *psp) { struct amdgpu_device *adev = psp->adev; - int retry_loop, ret; + int retry_loop, retry_cnt, ret; + retry_cnt = + (adev->ip_versions[MP0_HWIP][0] == IP_VERSION(13, 0, 6)) ? + PSP_VMBX_POLLING_LIMIT : + 10; /* Wait for bootloader to signify that it is ready having bit 31 of * C2PMSG_35 set to 1. All other bits are expected to be cleared. * If there is an error in processing command, bits[7:0] will be set. * This is applicable for PSP v13.0.6 and newer. */ - for (retry_loop = 0; retry_loop < 10; retry_loop++) { + for (retry_loop = 0; retry_loop < retry_cnt; retry_loop++) { ret = psp_wait_for( psp, SOC15_REG_OFFSET(MP0, 0, regMP0_SMN_C2PMSG_35), 0x80000000, 0xffffffff, false); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c index 2b3ebebc4299c..0f930fd8a3836 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c @@ -1651,6 +1651,32 @@ static void sdma_v5_2_get_clockgating_state(void *handle, u64 *flags) *flags |= AMD_CG_SUPPORT_SDMA_LS; } +static void sdma_v5_2_ring_begin_use(struct amdgpu_ring *ring) +{ + struct amdgpu_device *adev = ring->adev; + + /* SDMA 5.2.3 (RMB) FW doesn't seem to properly + * disallow GFXOFF in some cases leading to + * hangs in SDMA. Disallow GFXOFF while SDMA is active. + * We can probably just limit this to 5.2.3, + * but it shouldn't hurt for other parts since + * this GFXOFF will be disallowed anyway when SDMA is + * active, this just makes it explicit. + */ + amdgpu_gfx_off_ctrl(adev, false); +} + +static void sdma_v5_2_ring_end_use(struct amdgpu_ring *ring) +{ + struct amdgpu_device *adev = ring->adev; + + /* SDMA 5.2.3 (RMB) FW doesn't seem to properly + * disallow GFXOFF in some cases leading to + * hangs in SDMA. Allow GFXOFF when SDMA is complete. + */ + amdgpu_gfx_off_ctrl(adev, true); +} + const struct amd_ip_funcs sdma_v5_2_ip_funcs = { .name = "sdma_v5_2", .early_init = sdma_v5_2_early_init, @@ -1698,6 +1724,8 @@ static const struct amdgpu_ring_funcs sdma_v5_2_ring_funcs = { .test_ib = sdma_v5_2_ring_test_ib, .insert_nop = sdma_v5_2_ring_insert_nop, .pad_ib = sdma_v5_2_ring_pad_ib, + .begin_use = sdma_v5_2_ring_begin_use, + .end_use = sdma_v5_2_ring_end_use, .emit_wreg = sdma_v5_2_ring_emit_wreg, .emit_reg_wait = sdma_v5_2_ring_emit_reg_wait, .emit_reg_write_reg_wait = sdma_v5_2_ring_emit_reg_write_reg_wait, diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index f5be40d7ba367..28094cd7d9c21 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -325,7 +325,8 @@ static u32 soc15_get_xclk(struct amdgpu_device *adev) u32 reference_clock = adev->clock.spll.reference_freq; if (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(12, 0, 0) || - adev->ip_versions[MP1_HWIP][0] == IP_VERSION(12, 0, 1)) + adev->ip_versions[MP1_HWIP][0] == IP_VERSION(12, 0, 1) || + adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 6)) return 10000; if (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(10, 0, 0) || adev->ip_versions[MP1_HWIP][0] == IP_VERSION(10, 0, 1)) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index 0d3d538b64ebc..e07652e724965 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -407,7 +407,8 @@ static int allocate_doorbell(struct qcm_process_device *qpd, q->properties.doorbell_off = amdgpu_doorbell_index_on_bar(dev->adev, qpd->proc_doorbells, - q->doorbell_id); + q->doorbell_id, + dev->kfd->device_info.doorbell_size); return 0; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c index 7b38537c7c99b..05c74887fd6fd 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c @@ -161,7 +161,10 @@ void __iomem *kfd_get_kernel_doorbell(struct kfd_dev *kfd, if (inx >= KFD_MAX_NUM_OF_QUEUES_PER_PROCESS) return NULL; - *doorbell_off = amdgpu_doorbell_index_on_bar(kfd->adev, kfd->doorbells, inx); + *doorbell_off = amdgpu_doorbell_index_on_bar(kfd->adev, + kfd->doorbells, + inx, + kfd->device_info.doorbell_size); inx *= 2; pr_debug("Get kernel queue doorbell\n" @@ -240,7 +243,10 @@ phys_addr_t kfd_get_process_doorbells(struct kfd_process_device *pdd) return 0; } - first_db_index = amdgpu_doorbell_index_on_bar(adev, pdd->qpd.proc_doorbells, 0); + first_db_index = amdgpu_doorbell_index_on_bar(adev, + pdd->qpd.proc_doorbells, + 0, + pdd->dev->kfd->device_info.doorbell_size); return adev->doorbell.base + first_db_index * sizeof(uint32_t); } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c index c7991e07b6be5..a7697ec8188e0 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c @@ -268,7 +268,7 @@ static void event_interrupt_wq_v10(struct kfd_node *dev, SQ_INTERRUPT_WORD_WAVE_CTXID1, ENCODING); switch (encoding) { case SQ_INTERRUPT_WORD_ENCODING_AUTO: - pr_debug( + pr_debug_ratelimited( "sq_intr: auto, se %d, ttrace %d, wlt %d, ttrac_buf0_full %d, ttrac_buf1_full %d, ttrace_utc_err %d\n", REG_GET_FIELD(context_id1, SQ_INTERRUPT_WORD_AUTO_CTXID1, SE_ID), @@ -284,7 +284,7 @@ static void event_interrupt_wq_v10(struct kfd_node *dev, THREAD_TRACE_UTC_ERROR)); break; case SQ_INTERRUPT_WORD_ENCODING_INST: - pr_debug("sq_intr: inst, se %d, data 0x%x, sa %d, priv %d, wave_id %d, simd_id %d, wgp_id %d\n", + pr_debug_ratelimited("sq_intr: inst, se %d, data 0x%x, sa %d, priv %d, wave_id %d, simd_id %d, wgp_id %d\n", REG_GET_FIELD(context_id1, SQ_INTERRUPT_WORD_WAVE_CTXID1, SE_ID), REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_WAVE_CTXID0, @@ -310,7 +310,7 @@ static void event_interrupt_wq_v10(struct kfd_node *dev, case SQ_INTERRUPT_WORD_ENCODING_ERROR: sq_intr_err_type = REG_GET_FIELD(context_id0, KFD_CTXID0, ERR_TYPE); - pr_warn("sq_intr: error, se %d, data 0x%x, sa %d, priv %d, wave_id %d, simd_id %d, wgp_id %d, err_type %d\n", + pr_warn_ratelimited("sq_intr: error, se %d, data 0x%x, sa %d, priv %d, wave_id %d, simd_id %d, wgp_id %d, err_type %d\n", REG_GET_FIELD(context_id1, SQ_INTERRUPT_WORD_WAVE_CTXID1, SE_ID), REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_WAVE_CTXID0, diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c index f933bd231fb9c..2a65792fd1162 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c @@ -150,7 +150,7 @@ enum SQ_INTERRUPT_ERROR_TYPE { static void print_sq_intr_info_auto(uint32_t context_id0, uint32_t context_id1) { - pr_debug( + pr_debug_ratelimited( "sq_intr: auto, ttrace %d, wlt %d, ttrace_buf_full %d, reg_tms %d, cmd_tms %d, host_cmd_ovf %d, host_reg_ovf %d, immed_ovf %d, ttrace_utc_err %d\n", REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_AUTO_CTXID0, THREAD_TRACE), REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_AUTO_CTXID0, WLT), @@ -165,7 +165,7 @@ static void print_sq_intr_info_auto(uint32_t context_id0, uint32_t context_id1) static void print_sq_intr_info_inst(uint32_t context_id0, uint32_t context_id1) { - pr_debug( + pr_debug_ratelimited( "sq_intr: inst, data 0x%08x, sh %d, priv %d, wave_id %d, simd_id %d, wgp_id %d\n", REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_WAVE_CTXID0, DATA), REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_WAVE_CTXID0, SH_ID), @@ -177,7 +177,7 @@ static void print_sq_intr_info_inst(uint32_t context_id0, uint32_t context_id1) static void print_sq_intr_info_error(uint32_t context_id0, uint32_t context_id1) { - pr_warn( + pr_warn_ratelimited( "sq_intr: error, detail 0x%08x, type %d, sh %d, priv %d, wave_id %d, simd_id %d, wgp_id %d\n", REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_ERROR_CTXID0, DETAIL), REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_ERROR_CTXID0, TYPE), diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c index 830396b1c3b14..27cdaea405017 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c @@ -333,7 +333,7 @@ static void event_interrupt_wq_v9(struct kfd_node *dev, encoding = REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_WAVE_CTXID, ENCODING); switch (encoding) { case SQ_INTERRUPT_WORD_ENCODING_AUTO: - pr_debug( + pr_debug_ratelimited( "sq_intr: auto, se %d, ttrace %d, wlt %d, ttrac_buf_full %d, reg_tms %d, cmd_tms %d, host_cmd_ovf %d, host_reg_ovf %d, immed_ovf %d, ttrace_utc_err %d\n", REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_AUTO_CTXID, SE_ID), REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_AUTO_CTXID, THREAD_TRACE), @@ -347,7 +347,7 @@ static void event_interrupt_wq_v9(struct kfd_node *dev, REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_AUTO_CTXID, THREAD_TRACE_UTC_ERROR)); break; case SQ_INTERRUPT_WORD_ENCODING_INST: - pr_debug("sq_intr: inst, se %d, data 0x%x, sh %d, priv %d, wave_id %d, simd_id %d, cu_id %d, intr_data 0x%x\n", + pr_debug_ratelimited("sq_intr: inst, se %d, data 0x%x, sh %d, priv %d, wave_id %d, simd_id %d, cu_id %d, intr_data 0x%x\n", REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_WAVE_CTXID, SE_ID), REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_WAVE_CTXID, DATA), REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_WAVE_CTXID, SH_ID), @@ -366,7 +366,7 @@ static void event_interrupt_wq_v9(struct kfd_node *dev, break; case SQ_INTERRUPT_WORD_ENCODING_ERROR: sq_intr_err = REG_GET_FIELD(sq_int_data, KFD_SQ_INT_DATA, ERR_TYPE); - pr_warn("sq_intr: error, se %d, data 0x%x, sh %d, priv %d, wave_id %d, simd_id %d, cu_id %d, err_type %d\n", + pr_warn_ratelimited("sq_intr: error, se %d, data 0x%x, sh %d, priv %d, wave_id %d, simd_id %d, cu_id %d, err_type %d\n", REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_WAVE_CTXID, SE_ID), REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_WAVE_CTXID, DATA), REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_WAVE_CTXID, SH_ID), diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c index adb5e4bdc0b20..77649392e2331 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c @@ -377,7 +377,8 @@ int pqm_create_queue(struct process_queue_manager *pqm, */ uint32_t first_db_index = amdgpu_doorbell_index_on_bar(pdd->dev->adev, pdd->qpd.proc_doorbells, - 0); + 0, + pdd->dev->kfd->device_info.doorbell_size); *p_doorbell_offset_in_process = (q->properties.doorbell_off - first_db_index) * sizeof(uint32_t); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index 2a42fbddcb7ae..63ce30ea68915 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -628,8 +628,15 @@ svm_range_vram_node_new(struct kfd_node *node, struct svm_range *prange, void svm_range_vram_node_free(struct svm_range *prange) { - svm_range_bo_unref(prange->svm_bo); - prange->ttm_res = NULL; + /* serialize prange->svm_bo unref */ + mutex_lock(&prange->lock); + /* prange->svm_bo has not been unref */ + if (prange->ttm_res) { + prange->ttm_res = NULL; + mutex_unlock(&prange->lock); + svm_range_bo_unref(prange->svm_bo); + } else + mutex_unlock(&prange->lock); } struct kfd_node * @@ -760,7 +767,7 @@ svm_range_apply_attrs(struct kfd_process *p, struct svm_range *prange, prange->flags &= ~attrs[i].value; break; case KFD_IOCTL_SVM_ATTR_GRANULARITY: - prange->granularity = attrs[i].value; + prange->granularity = min_t(uint32_t, attrs[i].value, 0x3F); break; default: WARN_ONCE(1, "svm_range_check_attrs wasn't called?"); 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 34f011cedd065..d63360127834b 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2084,7 +2084,7 @@ static int dm_dmub_sw_init(struct amdgpu_device *adev) struct dmub_srv_create_params create_params; struct dmub_srv_region_params region_params; struct dmub_srv_region_info region_info; - struct dmub_srv_fb_params fb_params; + struct dmub_srv_memory_params memory_params; struct dmub_srv_fb_info *fb_info; struct dmub_srv *dmub_srv; const struct dmcub_firmware_header_v1_0 *hdr; @@ -2184,6 +2184,7 @@ static int dm_dmub_sw_init(struct amdgpu_device *adev) adev->dm.dmub_fw->data + le32_to_cpu(hdr->header.ucode_array_offset_bytes) + PSP_HEADER_BYTES; + region_params.is_mailbox_in_inbox = false; status = dmub_srv_calc_region_info(dmub_srv, ®ion_params, ®ion_info); @@ -2207,10 +2208,10 @@ static int dm_dmub_sw_init(struct amdgpu_device *adev) return r; /* Rebase the regions on the framebuffer address. */ - memset(&fb_params, 0, sizeof(fb_params)); - fb_params.cpu_addr = adev->dm.dmub_bo_cpu_addr; - fb_params.gpu_addr = adev->dm.dmub_bo_gpu_addr; - fb_params.region_info = ®ion_info; + memset(&memory_params, 0, sizeof(memory_params)); + memory_params.cpu_fb_addr = adev->dm.dmub_bo_cpu_addr; + memory_params.gpu_fb_addr = adev->dm.dmub_bo_gpu_addr; + memory_params.region_info = ®ion_info; adev->dm.dmub_fb_info = kzalloc(sizeof(*adev->dm.dmub_fb_info), GFP_KERNEL); @@ -2222,7 +2223,7 @@ static int dm_dmub_sw_init(struct amdgpu_device *adev) return -ENOMEM; } - status = dmub_srv_calc_fb_info(dmub_srv, &fb_params, fb_info); + status = dmub_srv_calc_mem_info(dmub_srv, &memory_params, fb_info); if (status != DMUB_STATUS_OK) { DRM_ERROR("Error calculating DMUB FB info: %d\n", status); return -EINVAL; @@ -5169,6 +5170,9 @@ static void fill_dc_dirty_rects(struct drm_plane *plane, if (plane->type == DRM_PLANE_TYPE_CURSOR) return; + if (new_plane_state->rotation != DRM_MODE_ROTATE_0) + goto ffu; + num_clips = drm_plane_get_damage_clips_count(new_plane_state); clips = drm_plane_get_damage_clips(new_plane_state); @@ -6235,7 +6239,7 @@ int amdgpu_dm_connector_atomic_set_property(struct drm_connector *connector, dm_new_state->underscan_enable = val; ret = 0; } else if (property == adev->mode_info.abm_level_property) { - dm_new_state->abm_level = val; + dm_new_state->abm_level = val ?: ABM_LEVEL_IMMEDIATE_DISABLE; ret = 0; } @@ -6280,7 +6284,8 @@ int amdgpu_dm_connector_atomic_get_property(struct drm_connector *connector, *val = dm_state->underscan_enable; ret = 0; } else if (property == adev->mode_info.abm_level_property) { - *val = dm_state->abm_level; + *val = (dm_state->abm_level != ABM_LEVEL_IMMEDIATE_DISABLE) ? + dm_state->abm_level : 0; ret = 0; } @@ -6353,7 +6358,8 @@ void amdgpu_dm_connector_funcs_reset(struct drm_connector *connector) state->pbn = 0; if (connector->connector_type == DRM_MODE_CONNECTOR_eDP) - state->abm_level = amdgpu_dm_abm_level; + state->abm_level = amdgpu_dm_abm_level ?: + ABM_LEVEL_IMMEDIATE_DISABLE; __drm_atomic_helper_connector_reset(connector, &state->base); } @@ -7430,6 +7436,9 @@ static int amdgpu_dm_i2c_xfer(struct i2c_adapter *i2c_adap, int i; int result = -EIO; + if (!ddc_service->ddc_pin || !ddc_service->ddc_pin->hw_info.hw_supported) + return result; + cmd.payloads = kcalloc(num, sizeof(struct i2c_payload), GFP_KERNEL); if (!cmd.payloads) @@ -9538,14 +9547,14 @@ static bool should_reset_plane(struct drm_atomic_state *state, struct drm_plane *other; struct drm_plane_state *old_other_state, *new_other_state; struct drm_crtc_state *new_crtc_state; + struct amdgpu_device *adev = drm_to_adev(plane->dev); int i; /* - * TODO: Remove this hack once the checks below are sufficient - * enough to determine when we need to reset all the planes on - * the stream. + * TODO: Remove this hack for all asics once it proves that the + * fast updates works fine on DCN3.2+. */ - if (state->allow_modeset) + if (adev->ip_versions[DCE_HWIP][0] < IP_VERSION(3, 2, 0) && state->allow_modeset) return true; /* Exit early if we know that we're adding or removing the plane. */ diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 57230661132bd..28f5eb9ecbd3e 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -1598,31 +1598,31 @@ enum dc_status dm_dp_mst_is_port_support_mode( unsigned int upper_link_bw_in_kbps = 0, down_link_bw_in_kbps = 0; unsigned int max_compressed_bw_in_kbps = 0; struct dc_dsc_bw_range bw_range = {0}; - struct drm_dp_mst_topology_mgr *mst_mgr; + uint16_t full_pbn = aconnector->mst_output_port->full_pbn; /* - * check if the mode could be supported if DSC pass-through is supported - * AND check if there enough bandwidth available to support the mode - * with DSC enabled. + * Consider the case with the depth of the mst topology tree is equal or less than 2 + * A. When dsc bitstream can be transmitted along the entire path + * 1. dsc is possible between source and branch/leaf device (common dsc params is possible), AND + * 2. dsc passthrough supported at MST branch, or + * 3. dsc decoding supported at leaf MST device + * Use maximum dsc compression as bw constraint + * B. When dsc bitstream cannot be transmitted along the entire path + * Use native bw as bw constraint */ if (is_dsc_common_config_possible(stream, &bw_range) && - aconnector->mst_output_port->passthrough_aux) { - mst_mgr = aconnector->mst_output_port->mgr; - mutex_lock(&mst_mgr->lock); - + (aconnector->mst_output_port->passthrough_aux || + aconnector->dsc_aux == &aconnector->mst_output_port->aux)) { cur_link_settings = stream->link->verified_link_cap; upper_link_bw_in_kbps = dc_link_bandwidth_kbps(aconnector->dc_link, - &cur_link_settings - ); - down_link_bw_in_kbps = kbps_from_pbn(aconnector->mst_output_port->full_pbn); + &cur_link_settings); + down_link_bw_in_kbps = kbps_from_pbn(full_pbn); /* pick the bottleneck */ end_to_end_bw_in_kbps = min(upper_link_bw_in_kbps, down_link_bw_in_kbps); - mutex_unlock(&mst_mgr->lock); - /* * use the maximum dsc compression bandwidth as the required * bandwidth for the mode @@ -1637,8 +1637,7 @@ enum dc_status dm_dp_mst_is_port_support_mode( /* check if mode could be supported within full_pbn */ bpp = convert_dc_color_depth_into_bpc(stream->timing.display_color_depth) * 3; pbn = drm_dp_calc_pbn_mode(stream->timing.pix_clk_100hz / 10, bpp, false); - - if (pbn > aconnector->mst_output_port->full_pbn) + if (pbn > full_pbn) return DC_FAIL_BANDWIDTH_VALIDATE; } diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index d08e60dff46de..a1be93f6385c6 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -990,7 +990,8 @@ static bool dc_construct(struct dc *dc, /* set i2c speed if not done by the respective dcnxxx__resource.c */ if (dc->caps.i2c_speed_in_khz_hdcp == 0) dc->caps.i2c_speed_in_khz_hdcp = dc->caps.i2c_speed_in_khz; - + if (dc->caps.max_optimizable_video_width == 0) + dc->caps.max_optimizable_video_width = 5120; dc->clk_mgr = dc_clk_mgr_create(dc->ctx, dc->res_pool->pp_smu, dc->res_pool->dccg); if (!dc->clk_mgr) goto fail; @@ -1069,53 +1070,6 @@ static void apply_ctx_interdependent_lock(struct dc *dc, } } -static void phantom_pipe_blank( - struct dc *dc, - struct timing_generator *tg, - int width, - int height) -{ - struct dce_hwseq *hws = dc->hwseq; - enum dc_color_space color_space; - struct tg_color black_color = {0}; - struct output_pixel_processor *opp = NULL; - uint32_t num_opps, opp_id_src0, opp_id_src1; - uint32_t otg_active_width, otg_active_height; - uint32_t i; - - /* program opp dpg blank color */ - color_space = COLOR_SPACE_SRGB; - color_space_to_black_color(dc, color_space, &black_color); - - otg_active_width = width; - otg_active_height = height; - - /* get the OPTC source */ - tg->funcs->get_optc_source(tg, &num_opps, &opp_id_src0, &opp_id_src1); - ASSERT(opp_id_src0 < dc->res_pool->res_cap->num_opp); - - for (i = 0; i < dc->res_pool->res_cap->num_opp; i++) { - if (dc->res_pool->opps[i] != NULL && dc->res_pool->opps[i]->inst == opp_id_src0) { - opp = dc->res_pool->opps[i]; - break; - } - } - - if (opp && opp->funcs->opp_set_disp_pattern_generator) - opp->funcs->opp_set_disp_pattern_generator( - opp, - CONTROLLER_DP_TEST_PATTERN_SOLID_COLOR, - CONTROLLER_DP_COLOR_SPACE_UDEFINED, - COLOR_DEPTH_UNDEFINED, - &black_color, - otg_active_width, - otg_active_height, - 0); - - if (tg->funcs->is_tg_enabled(tg)) - hws->funcs.wait_for_blank_complete(opp); -} - static void dc_update_viusal_confirm_color(struct dc *dc, struct dc_state *context, struct pipe_ctx *pipe_ctx) { if (dc->ctx->dce_version >= DCN_VERSION_1_0) { @@ -1206,7 +1160,8 @@ static void disable_dangling_plane(struct dc *dc, struct dc_state *context) main_pipe_width = old_stream->mall_stream_config.paired_stream->dst.width; main_pipe_height = old_stream->mall_stream_config.paired_stream->dst.height; - phantom_pipe_blank(dc, tg, main_pipe_width, main_pipe_height); + if (dc->hwss.blank_phantom) + dc->hwss.blank_phantom(dc, tg, main_pipe_width, main_pipe_height); tg->funcs->enable_crtc(tg); } } @@ -1888,7 +1843,7 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c if (dc->hwss.subvp_pipe_control_lock) dc->hwss.subvp_pipe_control_lock(dc, context, true, true, NULL, subvp_prev_use); - if (dc->debug.enable_double_buffered_dsc_pg_support) + if (dc->hwss.update_dsc_pg) dc->hwss.update_dsc_pg(dc, context, false); disable_dangling_plane(dc, context); @@ -1995,7 +1950,7 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c dc->hwss.optimize_bandwidth(dc, context); } - if (dc->debug.enable_double_buffered_dsc_pg_support) + if (dc->hwss.update_dsc_pg) dc->hwss.update_dsc_pg(dc, context, true); if (dc->ctx->dce_version >= DCE_VERSION_MAX) @@ -2242,7 +2197,7 @@ void dc_post_update_surfaces_to_stream(struct dc *dc) dc->hwss.optimize_bandwidth(dc, context); - if (dc->debug.enable_double_buffered_dsc_pg_support) + if (dc->hwss.update_dsc_pg) dc->hwss.update_dsc_pg(dc, context, true); } @@ -2488,6 +2443,7 @@ static enum surface_update_type get_plane_info_update_type(const struct dc_surfa } static enum surface_update_type get_scaling_info_update_type( + const struct dc *dc, const struct dc_surface_update *u) { union surface_update_flags *update_flags = &u->surface->update_flags; @@ -2520,6 +2476,12 @@ static enum surface_update_type get_scaling_info_update_type( update_flags->bits.clock_change = 1; } + if (u->scaling_info->src_rect.width > dc->caps.max_optimizable_video_width && + (u->scaling_info->clip_rect.width > u->surface->clip_rect.width || + u->scaling_info->clip_rect.height > u->surface->clip_rect.height)) + /* Changing clip size of a large surface may result in MPC slice count change */ + update_flags->bits.bandwidth_change = 1; + if (u->scaling_info->src_rect.x != u->surface->src_rect.x || u->scaling_info->src_rect.y != u->surface->src_rect.y || u->scaling_info->clip_rect.x != u->surface->clip_rect.x @@ -2557,7 +2519,7 @@ static enum surface_update_type det_surface_update(const struct dc *dc, type = get_plane_info_update_type(u); elevate_update_type(&overall_type, type); - type = get_scaling_info_update_type(u); + type = get_scaling_info_update_type(dc, u); elevate_update_type(&overall_type, type); if (u->flip_addr) { @@ -3571,7 +3533,7 @@ static void commit_planes_for_stream(struct dc *dc, if (get_seamless_boot_stream_count(context) == 0) dc->hwss.prepare_bandwidth(dc, context); - if (dc->debug.enable_double_buffered_dsc_pg_support) + if (dc->hwss.update_dsc_pg) dc->hwss.update_dsc_pg(dc, context, false); context_clock_trace(dc, context); @@ -4374,6 +4336,14 @@ bool dc_update_planes_and_stream(struct dc *dc, update_type, context); } else { + if (!stream_update && + dc->hwss.is_pipe_topology_transition_seamless && + !dc->hwss.is_pipe_topology_transition_seamless( + dc, dc->current_state, context)) { + + DC_LOG_ERROR("performing non-seamless pipe topology transition with surface only update!\n"); + BREAK_TO_DEBUGGER(); + } commit_planes_for_stream( dc, srf_updates, @@ -5284,3 +5254,24 @@ void dc_query_current_properties(struct dc *dc, struct dc_current_properties *pr properties->cursor_size_limit = subvp_in_use ? 64 : dc->caps.max_cursor_size; } +/** + ***************************************************************************** + * dc_set_edp_power() - DM controls eDP power to be ON/OFF + * + * Called when DM wants to power on/off eDP. + * Only work on links with flag skip_implict_edp_power_control is set. + * + ***************************************************************************** + */ +void dc_set_edp_power(const struct dc *dc, struct dc_link *edp_link, + bool powerOn) +{ + if (edp_link->connector_signal != SIGNAL_TYPE_EDP) + return; + + if (edp_link->skip_implict_edp_power_control == false) + return; + + edp_link->dc->link_srv->edp_set_panel_power(edp_link, powerOn); +} + diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index f7b51aca60200..8873acfe309c8 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -996,7 +996,7 @@ static void adjust_recout_for_visual_confirm(struct rect *recout, struct dc *dc = pipe_ctx->stream->ctx->dc; int dpp_offset, base_offset; - if (dc->debug.visual_confirm == VISUAL_CONFIRM_DISABLE) + if (dc->debug.visual_confirm == VISUAL_CONFIRM_DISABLE || !pipe_ctx->plane_res.dpp) return; dpp_offset = pipe_ctx->stream->timing.v_addressable / VISUAL_CONFIRM_DPP_OFFSET_DENO; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c index 01fe2d2fd2417..ebe571fcefe32 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c @@ -582,7 +582,7 @@ uint32_t dc_stream_get_vblank_counter(const struct dc_stream_state *stream) for (i = 0; i < MAX_PIPES; i++) { struct timing_generator *tg = res_ctx->pipe_ctx[i].stream_res.tg; - if (res_ctx->pipe_ctx[i].stream != stream) + if (res_ctx->pipe_ctx[i].stream != stream || !tg) continue; return tg->funcs->get_frame_count(tg); @@ -641,7 +641,7 @@ bool dc_stream_get_scanoutpos(const struct dc_stream_state *stream, for (i = 0; i < MAX_PIPES; i++) { struct timing_generator *tg = res_ctx->pipe_ctx[i].stream_res.tg; - if (res_ctx->pipe_ctx[i].stream != stream) + if (res_ctx->pipe_ctx[i].stream != stream || !tg) continue; tg->funcs->get_scanoutpos(tg, diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 31e3183497a7f..3f33740e2f659 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -231,6 +231,11 @@ struct dc_caps { uint32_t dmdata_alloc_size; unsigned int max_cursor_size; unsigned int max_video_width; + /* + * max video plane width that can be safely assumed to be always + * supported by single DPP pipe. + */ + unsigned int max_optimizable_video_width; unsigned int min_horizontal_blanking_period; int linear_pitch_alignment; bool dcc_const_color; @@ -1533,7 +1538,6 @@ struct dc_link { enum edp_revision edp_revision; union dpcd_sink_ext_caps dpcd_sink_ext_caps; - struct backlight_settings backlight_settings; struct psr_settings psr_settings; struct replay_settings replay_settings; @@ -1573,6 +1577,7 @@ struct dc_link { struct phy_state phy_state; // BW ALLOCATON USB4 ONLY struct dc_dpia_bw_alloc dpia_bw_alloc_config; + bool skip_implict_edp_power_control; }; /* Return an enumerated dc_link. @@ -1592,6 +1597,9 @@ void dc_get_edp_links(const struct dc *dc, struct dc_link **edp_links, int *edp_num); +void dc_set_edp_power(const struct dc *dc, struct dc_link *edp_link, + bool powerOn); + /* The function initiates detection handshake over the given link. It first * determines if there are display connections over the link. If so it initiates * detection protocols supported by the connected receiver device. The function diff --git a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h index 100d62162b717..99880b08cda0c 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h @@ -465,6 +465,7 @@ struct dc_cursor_mi_param { struct fixed31_32 v_scale_ratio; enum dc_rotation_angle rotation; bool mirror; + struct dc_stream_state *stream; }; /* IPP related types */ diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h index 3697ea1d14c1b..d5b3e3a32cc6d 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_stream.h +++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h @@ -302,7 +302,6 @@ struct dc_stream_state { bool vblank_synchronized; bool fpo_in_use; struct mall_stream_config mall_stream_config; - bool skip_edp_power_down; }; #define ABM_LEVEL_IMMEDIATE_DISABLE 255 diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h index 445ad79001ce2..accffba5a6834 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_types.h @@ -189,6 +189,7 @@ struct dc_panel_patch { unsigned int disable_fams; unsigned int skip_avmute; unsigned int mst_start_top_delay; + unsigned int remove_sink_ext_caps; }; struct dc_edid_caps { @@ -1002,10 +1003,6 @@ struct link_mst_stream_allocation_table { struct link_mst_stream_allocation stream_allocations[MAX_CONTROLLER_NUM]; }; -struct backlight_settings { - uint32_t backlight_millinits; -}; - /* PSR feature flags */ struct psr_settings { bool psr_feature_enabled; // PSR is supported by sink diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c index 2a6157555fd1e..9c78e42418f34 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c @@ -1226,7 +1226,7 @@ void dce110_blank_stream(struct pipe_ctx *pipe_ctx) struct dce_hwseq *hws = link->dc->hwseq; if (link->local_sink && link->local_sink->sink_signal == SIGNAL_TYPE_EDP) { - if (!stream->skip_edp_power_down) + if (!link->skip_implict_edp_power_control) hws->funcs.edp_backlight_control(link, false); link->dc->hwss.set_abm_immediate_disable(pipe_ctx); } diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index 9834b75f1837b..13ccb57379c7a 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -111,7 +111,8 @@ void dcn10_lock_all_pipes(struct dc *dc, if (pipe_ctx->top_pipe || !pipe_ctx->stream || (!pipe_ctx->plane_state && !old_pipe_ctx->plane_state) || - !tg->funcs->is_tg_enabled(tg)) + !tg->funcs->is_tg_enabled(tg) || + pipe_ctx->stream->mall_stream_config.type == SUBVP_PHANTOM) continue; if (lock) @@ -3406,7 +3407,8 @@ void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx) .h_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.horz, .v_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.vert, .rotation = pipe_ctx->plane_state->rotation, - .mirror = pipe_ctx->plane_state->horizontal_mirror + .mirror = pipe_ctx->plane_state->horizontal_mirror, + .stream = pipe_ctx->stream, }; bool pipe_split_on = false; bool odm_combine_on = (pipe_ctx->next_odm_pipe != NULL) || 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 4566bc7abf17e..aa252dc263267 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c @@ -1075,8 +1075,16 @@ void hubp2_cursor_set_position( if (src_y_offset < 0) src_y_offset = 0; /* Save necessary cursor info x, y position. w, h is saved in attribute func. */ - hubp->cur_rect.x = src_x_offset + param->viewport.x; - hubp->cur_rect.y = src_y_offset + param->viewport.y; + if (param->stream->link->psr_settings.psr_version >= DC_PSR_VERSION_SU_1 && + param->rotation != ROTATION_ANGLE_0) { + hubp->cur_rect.x = 0; + hubp->cur_rect.y = 0; + hubp->cur_rect.w = param->stream->timing.h_addressable; + hubp->cur_rect.h = param->stream->timing.v_addressable; + } else { + hubp->cur_rect.x = src_x_offset + param->viewport.x; + hubp->cur_rect.y = src_y_offset + param->viewport.y; + } } void hubp2_clk_cntl(struct hubp *hubp, bool enable) diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index aeadc587433fd..a2e1ca3b93e86 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -1830,8 +1830,16 @@ void dcn20_program_front_end_for_ctx( dc->current_state->res_ctx.pipe_ctx[i].stream->mall_stream_config.type == SUBVP_PHANTOM) { struct timing_generator *tg = dc->current_state->res_ctx.pipe_ctx[i].stream_res.tg; - if (tg->funcs->enable_crtc) + if (tg->funcs->enable_crtc) { + if (dc->hwss.blank_phantom) { + int main_pipe_width, main_pipe_height; + + main_pipe_width = dc->current_state->res_ctx.pipe_ctx[i].stream->mall_stream_config.paired_stream->dst.width; + main_pipe_height = dc->current_state->res_ctx.pipe_ctx[i].stream->mall_stream_config.paired_stream->dst.height; + dc->hwss.blank_phantom(dc, tg, main_pipe_width, main_pipe_height); + } tg->funcs->enable_crtc(tg); + } } } /* OTG blank before disabling all front ends */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c index 4d2820ffe4682..33a8626bda735 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c @@ -476,7 +476,8 @@ void dcn314_disable_link_output(struct dc_link *link, struct dmcu *dmcu = dc->res_pool->dmcu; if (signal == SIGNAL_TYPE_EDP && - link->dc->hwss.edp_backlight_control) + link->dc->hwss.edp_backlight_control && + !link->skip_implict_edp_power_control) link->dc->hwss.edp_backlight_control(link, false); else if (dmcu != NULL && dmcu->funcs->lock_phy) dmcu->funcs->lock_phy(dmcu); 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 004beed9bd444..3e65e683db0ac 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c @@ -869,7 +869,7 @@ static const struct dc_plane_cap plane_cap = { static const struct dc_debug_options debug_defaults_drv = { .disable_z10 = false, .enable_z9_disable_interface = true, - .minimum_z8_residency_time = 2000, + .minimum_z8_residency_time = 2100, .psr_skip_crtc_disable = true, .replay_skip_crtc_disabled = true, .disable_dmcu = true, diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c index 680e7fa8d18ab..650e1598bddcb 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c @@ -77,6 +77,9 @@ void dcn32_dsc_pg_control( if (hws->ctx->dc->debug.disable_dsc_power_gate) return; + if (!hws->ctx->dc->debug.enable_double_buffered_dsc_pg_support) + return; + REG_GET(DC_IP_REQUEST_CNTL, IP_REQUEST_EN, &org_ip_request_cntl); if (org_ip_request_cntl == 0) REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 1); @@ -214,7 +217,7 @@ static bool dcn32_check_no_memory_request_for_cab(struct dc *dc) static uint32_t dcn32_calculate_cab_allocation(struct dc *dc, struct dc_state *ctx) { int i; - uint8_t num_ways = 0; + uint32_t num_ways = 0; uint32_t mall_ss_size_bytes = 0; mall_ss_size_bytes = ctx->bw_ctx.bw.dcn.mall_ss_size_bytes; @@ -244,7 +247,8 @@ static uint32_t dcn32_calculate_cab_allocation(struct dc *dc, struct dc_state *c bool dcn32_apply_idle_power_optimizations(struct dc *dc, bool enable) { union dmub_rb_cmd cmd; - uint8_t ways, i; + uint8_t i; + uint32_t ways; int j; bool mall_ss_unsupported = false; struct dc_plane_state *plane = NULL; @@ -304,7 +308,7 @@ bool dcn32_apply_idle_power_optimizations(struct dc *dc, bool enable) cmd.cab.header.type = DMUB_CMD__CAB_FOR_SS; cmd.cab.header.sub_type = DMUB_CMD__CAB_DCN_SS_FIT_IN_CAB; cmd.cab.header.payload_bytes = sizeof(cmd.cab) - sizeof(cmd.cab.header); - cmd.cab.cab_alloc_ways = ways; + cmd.cab.cab_alloc_ways = (uint8_t)ways; dm_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_NO_WAIT); @@ -482,8 +486,7 @@ bool dcn32_set_mcm_luts( if (plane_state->blend_tf->type == TF_TYPE_HWPWL) lut_params = &plane_state->blend_tf->pwl; else if (plane_state->blend_tf->type == TF_TYPE_DISTRIBUTED_POINTS) { - cm_helper_translate_curve_to_hw_format(plane_state->ctx, - plane_state->blend_tf, + cm3_helper_translate_curve_to_hw_format(plane_state->blend_tf, &dpp_base->regamma_params, false); lut_params = &dpp_base->regamma_params; } @@ -497,8 +500,7 @@ bool dcn32_set_mcm_luts( else if (plane_state->in_shaper_func->type == TF_TYPE_DISTRIBUTED_POINTS) { // TODO: dpp_base replace ASSERT(false); - cm_helper_translate_curve_to_hw_format(plane_state->ctx, - plane_state->in_shaper_func, + cm3_helper_translate_curve_to_hw_format(plane_state->in_shaper_func, &dpp_base->shaper_params, true); lut_params = &dpp_base->shaper_params; } @@ -1573,3 +1575,101 @@ void dcn32_init_blank( if (opp) hws->funcs.wait_for_blank_complete(opp); } + +void dcn32_blank_phantom(struct dc *dc, + struct timing_generator *tg, + int width, + int height) +{ + struct dce_hwseq *hws = dc->hwseq; + enum dc_color_space color_space; + struct tg_color black_color = {0}; + struct output_pixel_processor *opp = NULL; + uint32_t num_opps, opp_id_src0, opp_id_src1; + uint32_t otg_active_width, otg_active_height; + uint32_t i; + + /* program opp dpg blank color */ + color_space = COLOR_SPACE_SRGB; + color_space_to_black_color(dc, color_space, &black_color); + + otg_active_width = width; + otg_active_height = height; + + /* get the OPTC source */ + tg->funcs->get_optc_source(tg, &num_opps, &opp_id_src0, &opp_id_src1); + ASSERT(opp_id_src0 < dc->res_pool->res_cap->num_opp); + + for (i = 0; i < dc->res_pool->res_cap->num_opp; i++) { + if (dc->res_pool->opps[i] != NULL && dc->res_pool->opps[i]->inst == opp_id_src0) { + opp = dc->res_pool->opps[i]; + break; + } + } + + if (opp && opp->funcs->opp_set_disp_pattern_generator) + opp->funcs->opp_set_disp_pattern_generator( + opp, + CONTROLLER_DP_TEST_PATTERN_SOLID_COLOR, + CONTROLLER_DP_COLOR_SPACE_UDEFINED, + COLOR_DEPTH_UNDEFINED, + &black_color, + otg_active_width, + otg_active_height, + 0); + + if (tg->funcs->is_tg_enabled(tg)) + hws->funcs.wait_for_blank_complete(opp); +} + +bool dcn32_is_pipe_topology_transition_seamless(struct dc *dc, + const struct dc_state *cur_ctx, + const struct dc_state *new_ctx) +{ + int i; + const struct pipe_ctx *cur_pipe, *new_pipe; + bool is_seamless = true; + + for (i = 0; i < dc->res_pool->pipe_count; i++) { + cur_pipe = &cur_ctx->res_ctx.pipe_ctx[i]; + new_pipe = &new_ctx->res_ctx.pipe_ctx[i]; + + if (resource_is_pipe_type(cur_pipe, FREE_PIPE) || + resource_is_pipe_type(new_pipe, FREE_PIPE)) + /* adding or removing free pipes is always seamless */ + continue; + else if (resource_is_pipe_type(cur_pipe, OTG_MASTER)) { + if (resource_is_pipe_type(new_pipe, OTG_MASTER)) + if (cur_pipe->stream->stream_id == new_pipe->stream->stream_id) + /* OTG master with the same stream is seamless */ + continue; + } else if (resource_is_pipe_type(cur_pipe, OPP_HEAD)) { + if (resource_is_pipe_type(new_pipe, OPP_HEAD)) { + if (cur_pipe->stream_res.tg == new_pipe->stream_res.tg) + /* + * OPP heads sharing the same timing + * generator is seamless + */ + continue; + } + } else if (resource_is_pipe_type(cur_pipe, DPP_PIPE)) { + if (resource_is_pipe_type(new_pipe, DPP_PIPE)) { + if (cur_pipe->stream_res.opp == new_pipe->stream_res.opp) + /* + * DPP pipes sharing the same OPP head is + * seamless + */ + continue; + } + } + + /* + * This pipe's transition doesn't fall under any seamless + * conditions + */ + is_seamless = false; + break; + } + + return is_seamless; +} diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.h b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.h index 2d2628f31bed7..9992e40acd217 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.h +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.h @@ -115,4 +115,13 @@ void dcn32_init_blank( struct dc *dc, struct timing_generator *tg); +void dcn32_blank_phantom(struct dc *dc, + struct timing_generator *tg, + int width, + int height); + +bool dcn32_is_pipe_topology_transition_seamless(struct dc *dc, + const struct dc_state *cur_ctx, + const struct dc_state *new_ctx); + #endif /* __DC_HWSS_DCN32_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c index c7417147dff19..1edadff39a5ef 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c @@ -115,6 +115,8 @@ static const struct hw_sequencer_funcs dcn32_funcs = { .update_phantom_vp_position = dcn32_update_phantom_vp_position, .update_dsc_pg = dcn32_update_dsc_pg, .apply_update_flags_for_phantom = dcn32_apply_update_flags_for_phantom, + .blank_phantom = dcn32_blank_phantom, + .is_pipe_topology_transition_seamless = dcn32_is_pipe_topology_transition_seamless, }; static const struct hwseq_private_funcs dcn32_private_funcs = { 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 5805fb02af14e..f2de0c7584947 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 @@ -948,10 +948,8 @@ static enum dcn_zstate_support_state decide_zstate_support(struct dc *dc, struc { int plane_count; int i; - unsigned int min_dst_y_next_start_us; plane_count = 0; - min_dst_y_next_start_us = 0; for (i = 0; i < dc->res_pool->pipe_count; i++) { if (context->res_ctx.pipe_ctx[i].plane_state) plane_count++; @@ -973,26 +971,15 @@ static enum dcn_zstate_support_state decide_zstate_support(struct dc *dc, struc else if (context->stream_count == 1 && context->streams[0]->signal == SIGNAL_TYPE_EDP) { struct dc_link *link = context->streams[0]->sink->link; struct dc_stream_status *stream_status = &context->stream_status[0]; - struct dc_stream_state *current_stream = context->streams[0]; int minmum_z8_residency = dc->debug.minimum_z8_residency_time > 0 ? dc->debug.minimum_z8_residency_time : 1000; bool allow_z8 = context->bw_ctx.dml.vba.StutterPeriod > (double)minmum_z8_residency; bool is_pwrseq0 = link->link_index == 0; - bool isFreesyncVideo; - - isFreesyncVideo = current_stream->adjust.v_total_min == current_stream->adjust.v_total_max; - isFreesyncVideo = isFreesyncVideo && current_stream->timing.v_total < current_stream->adjust.v_total_min; - for (i = 0; i < dc->res_pool->pipe_count; i++) { - if (context->res_ctx.pipe_ctx[i].stream == current_stream && isFreesyncVideo) { - min_dst_y_next_start_us = context->res_ctx.pipe_ctx[i].dlg_regs.min_dst_y_next_start_us; - break; - } - } /* Don't support multi-plane configurations */ if (stream_status->plane_count > 1) return DCN_ZSTATE_SUPPORT_DISALLOW; - if (is_pwrseq0 && (context->bw_ctx.dml.vba.StutterPeriod > 5000.0 || min_dst_y_next_start_us > 5000)) + if (is_pwrseq0 && context->bw_ctx.dml.vba.StutterPeriod > 5000.0) return DCN_ZSTATE_SUPPORT_ALLOW; else if (is_pwrseq0 && link->psr_settings.psr_version == DC_PSR_VERSION_1 && !link->panel_config.psr.disable_psr) return allow_z8 ? DCN_ZSTATE_SUPPORT_ALLOW_Z8_Z10_ONLY : DCN_ZSTATE_SUPPORT_ALLOW_Z10_ONLY; 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 711d4085b33b8..cf3b400c8619b 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 @@ -1964,6 +1964,7 @@ void dcn32_calculate_wm_and_dlg_fpu(struct dc *dc, struct dc_state *context, int i, pipe_idx, vlevel_temp = 0; double dcfclk = dcn3_2_soc.clock_limits[0].dcfclk_mhz; double dcfclk_from_validation = context->bw_ctx.dml.vba.DCFCLKState[vlevel][context->bw_ctx.dml.vba.maxMpcComb]; + double dram_speed_from_validation = context->bw_ctx.dml.vba.DRAMSpeed; double dcfclk_from_fw_based_mclk_switching = dcfclk_from_validation; bool pstate_en = context->bw_ctx.dml.vba.DRAMClockChangeSupport[vlevel][context->bw_ctx.dml.vba.maxMpcComb] != dm_dram_clock_change_unsupported; @@ -2151,7 +2152,7 @@ void dcn32_calculate_wm_and_dlg_fpu(struct dc *dc, struct dc_state *context, } if (dc->clk_mgr->bw_params->wm_table.nv_entries[WM_C].valid) { - min_dram_speed_mts = context->bw_ctx.dml.vba.DRAMSpeed; + min_dram_speed_mts = dram_speed_from_validation; min_dram_speed_mts_margin = 160; context->bw_ctx.dml.soc.dram_clock_change_latency_us = diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h index 02ff99f7bec2b..66e680902c95c 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h @@ -388,6 +388,11 @@ struct hw_sequencer_funcs { void (*z10_restore)(const struct dc *dc); void (*z10_save_init)(struct dc *dc); + void (*blank_phantom)(struct dc *dc, + struct timing_generator *tg, + int width, + int height); + void (*update_visual_confirm_color)(struct dc *dc, struct pipe_ctx *pipe_ctx, int mpcc_id); @@ -396,6 +401,9 @@ struct hw_sequencer_funcs { struct dc_state *context, struct pipe_ctx *phantom_pipe); void (*apply_update_flags_for_phantom)(struct pipe_ctx *phantom_pipe); + bool (*is_pipe_topology_transition_seamless)(struct dc *dc, + const struct dc_state *cur_ctx, + const struct dc_state *new_ctx); void (*commit_subvp_config)(struct dc *dc, struct dc_state *context); void (*enable_phantom_streams)(struct dc *dc, struct dc_state *context); diff --git a/drivers/gpu/drm/amd/display/dc/inc/link.h b/drivers/gpu/drm/amd/display/dc/inc/link.h index e3e8c76c17cfa..d7685368140ab 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/link.h +++ b/drivers/gpu/drm/amd/display/dc/inc/link.h @@ -295,6 +295,7 @@ struct link_service { bool (*edp_receiver_ready_T9)(struct dc_link *link); bool (*edp_receiver_ready_T7)(struct dc_link *link); bool (*edp_power_alpm_dpcd_enable)(struct dc_link *link, bool enable); + void (*edp_set_panel_power)(struct dc_link *link, bool powerOn); /*************************** DP CTS ************************************/ diff --git a/drivers/gpu/drm/amd/display/dc/link/link_detection.c b/drivers/gpu/drm/amd/display/dc/link/link_detection.c index c9b6676eaf53b..c7a9e286a5d4d 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_detection.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_detection.c @@ -876,7 +876,7 @@ static bool detect_link_and_local_sink(struct dc_link *link, (link->dpcd_sink_ext_caps.bits.oled == 1)) { dpcd_set_source_specific_data(link); msleep(post_oui_delay); - set_cached_brightness_aux(link); + set_default_brightness_aux(link); } return true; @@ -1085,6 +1085,9 @@ static bool detect_link_and_local_sink(struct dc_link *link, if (sink->edid_caps.panel_patch.skip_scdc_overwrite) link->ctx->dc->debug.hdmi20_disable = true; + if (sink->edid_caps.panel_patch.remove_sink_ext_caps) + link->dpcd_sink_ext_caps.raw = 0; + if (dc_is_hdmi_signal(link->connector_signal)) read_scdc_caps(link->ddc, link->local_sink); @@ -1163,6 +1166,12 @@ static bool detect_link_and_local_sink(struct dc_link *link, dm_helpers_init_panel_settings(dc_ctx, &link->panel_config, sink); // Override dc_panel_config if system has specific settings dm_helpers_override_panel_settings(dc_ctx, &link->panel_config); + + //sink only can use supported link rate table, we are foreced to enable it + if (link->reported_link_cap.link_rate == LINK_RATE_UNKNOWN) + link->panel_config.ilr.optimize_edp_link_rate = true; + if (edp_is_ilr_optimization_enabled(link)) + link->reported_link_cap.link_rate = get_max_link_rate_from_ilr_table(link); } } else { diff --git a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c index 79aef205598b7..35d087cf1980f 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c @@ -1930,7 +1930,7 @@ static void disable_link_dp(struct dc_link *link, dp_disable_link_phy(link, link_res, signal); if (link->connector_signal == SIGNAL_TYPE_EDP) { - if (!link->dc->config.edp_no_power_sequencing) + if (!link->skip_implict_edp_power_control) link->dc->hwss.edp_power_control(link, false); } @@ -2140,8 +2140,7 @@ static enum dc_status enable_link_dp(struct dc_state *state, if (link->dpcd_sink_ext_caps.bits.oled == 1 || link->dpcd_sink_ext_caps.bits.sdr_aux_backlight_control == 1 || link->dpcd_sink_ext_caps.bits.hdr_aux_backlight_control == 1) { - set_cached_brightness_aux(link); - + set_default_brightness_aux(link); if (link->dpcd_sink_ext_caps.bits.oled == 1) msleep(bl_oled_enable_delay); edp_backlight_enable_aux(link, true); @@ -2219,7 +2218,7 @@ static enum dc_status enable_link( * link settings. Need to call disable first before enabling at * new link settings. */ - if (link->link_status.link_active && !stream->skip_edp_power_down) + if (link->link_status.link_active) disable_link(link, &pipe_ctx->link_res, pipe_ctx->stream->signal); switch (pipe_ctx->stream->signal) { @@ -2338,9 +2337,7 @@ void link_set_dpms_off(struct pipe_ctx *pipe_ctx) dc->hwss.disable_stream(pipe_ctx); } else { dc->hwss.disable_stream(pipe_ctx); - if (!pipe_ctx->stream->skip_edp_power_down) { - disable_link(pipe_ctx->stream->link, &pipe_ctx->link_res, pipe_ctx->stream->signal); - } + disable_link(pipe_ctx->stream->link, &pipe_ctx->link_res, pipe_ctx->stream->signal); } if (pipe_ctx->stream->timing.flags.DSC) { diff --git a/drivers/gpu/drm/amd/display/dc/link/link_factory.c b/drivers/gpu/drm/amd/display/dc/link/link_factory.c index 0895742a31024..e406561c2c237 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_factory.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_factory.c @@ -223,6 +223,7 @@ static void construct_link_service_edp_panel_control(struct link_service *link_s link_srv->edp_receiver_ready_T9 = edp_receiver_ready_T9; link_srv->edp_receiver_ready_T7 = edp_receiver_ready_T7; link_srv->edp_power_alpm_dpcd_enable = edp_power_alpm_dpcd_enable; + link_srv->edp_set_panel_power = edp_set_panel_power; } /* link dp cts implements dp compliance test automation protocols and manual diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c index 237e0ff955f3c..db87aa7b5c90f 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c @@ -707,8 +707,7 @@ bool edp_decide_link_settings(struct dc_link *link, * edp_supported_link_rates_count is only valid for eDP v1.4 or higher. * Per VESA eDP spec, "The DPCD revision for eDP v1.4 is 13h" */ - if (link->dpcd_caps.dpcd_rev.raw < DPCD_REV_13 || - link->dpcd_caps.edp_supported_link_rates_count == 0) { + if (!edp_is_ilr_optimization_enabled(link)) { *link_setting = link->verified_link_cap; return true; } @@ -772,8 +771,7 @@ bool decide_edp_link_settings_with_dsc(struct dc_link *link, * edp_supported_link_rates_count is only valid for eDP v1.4 or higher. * Per VESA eDP spec, "The DPCD revision for eDP v1.4 is 13h" */ - if ((link->dpcd_caps.dpcd_rev.raw < DPCD_REV_13 || - link->dpcd_caps.edp_supported_link_rates_count == 0)) { + if (!edp_is_ilr_optimization_enabled(link)) { /* for DSC enabled case, we search for minimum lane count */ memset(&initial_link_setting, 0, sizeof(initial_link_setting)); initial_link_setting.lane_count = LANE_COUNT_ONE; @@ -1938,9 +1936,7 @@ void detect_edp_sink_caps(struct dc_link *link) * edp_supported_link_rates_count is only valid for eDP v1.4 or higher. * Per VESA eDP spec, "The DPCD revision for eDP v1.4 is 13h" */ - if (link->dpcd_caps.dpcd_rev.raw >= DPCD_REV_13 && - (link->panel_config.ilr.optimize_edp_link_rate || - link->reported_link_cap.link_rate == LINK_RATE_UNKNOWN)) { + if (link->dpcd_caps.dpcd_rev.raw >= DPCD_REV_13) { // Read DPCD 00010h - 0001Fh 16 bytes at one shot core_link_read_dpcd(link, DP_SUPPORTED_LINK_RATES, supported_link_rates, sizeof(supported_link_rates)); @@ -1958,12 +1954,10 @@ void detect_edp_sink_caps(struct dc_link *link) link_rate = linkRateInKHzToLinkRateMultiplier(link_rate_in_khz); link->dpcd_caps.edp_supported_link_rates[link->dpcd_caps.edp_supported_link_rates_count] = link_rate; link->dpcd_caps.edp_supported_link_rates_count++; - - if (link->reported_link_cap.link_rate < link_rate) - link->reported_link_cap.link_rate = link_rate; } } } + core_link_read_dpcd(link, DP_EDP_BACKLIGHT_ADJUSTMENT_CAP, &backlight_adj_cap, sizeof(backlight_adj_cap)); diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_phy.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_phy.c index b7abba55bc2fd..0050e0a06cbc2 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_phy.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_phy.c @@ -73,7 +73,8 @@ void dp_disable_link_phy(struct dc_link *link, { struct dc *dc = link->ctx->dc; - if (!link->wa_flags.dp_keep_receiver_powered) + if (!link->wa_flags.dp_keep_receiver_powered && + !link->skip_implict_edp_power_control) dpcd_write_rx_power_ctrl(link, false); dc->hwss.disable_link_output(link, link_res, signal); diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_fixed_vs_pe_retimer.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_fixed_vs_pe_retimer.c index fd8f6f1981461..68096d12f52fd 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_fixed_vs_pe_retimer.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training_fixed_vs_pe_retimer.c @@ -115,7 +115,7 @@ static enum link_training_result perform_fixed_vs_pe_nontransparent_training_seq lt_settings->cr_pattern_time = 16000; /* Fixed VS/PE specific: Toggle link rate */ - apply_toggle_rate_wa = (link->vendor_specific_lttpr_link_rate_wa == target_rate); + apply_toggle_rate_wa = ((link->vendor_specific_lttpr_link_rate_wa == target_rate) || (link->vendor_specific_lttpr_link_rate_wa == 0)); target_rate = get_dpcd_link_rate(<_settings->link_settings); toggle_rate = (target_rate == 0x6) ? 0xA : 0x6; @@ -271,7 +271,7 @@ enum link_training_result dp_perform_fixed_vs_pe_training_sequence_legacy( /* Vendor specific: Toggle link rate */ toggle_rate = (rate == 0x6) ? 0xA : 0x6; - if (link->vendor_specific_lttpr_link_rate_wa == rate) { + if (link->vendor_specific_lttpr_link_rate_wa == rate || link->vendor_specific_lttpr_link_rate_wa == 0) { core_link_write_dpcd( link, DP_LINK_BW_SET, @@ -617,7 +617,7 @@ enum link_training_result dp_perform_fixed_vs_pe_training_sequence( /* Vendor specific: Toggle link rate */ toggle_rate = (rate == 0x6) ? 0xA : 0x6; - if (link->vendor_specific_lttpr_link_rate_wa == rate) { + if (link->vendor_specific_lttpr_link_rate_wa == rate || link->vendor_specific_lttpr_link_rate_wa == 0) { core_link_write_dpcd( link, DP_LINK_BW_SET, diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c index 98e715aa6d8e3..13c3d7ff61395 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.c @@ -33,6 +33,7 @@ #include "link_dp_capability.h" #include "dm_helpers.h" #include "dal_asic_id.h" +#include "link_dp_phy.h" #include "dce/dmub_psr.h" #include "dc/dc_dmub_srv.h" #include "dce/dmub_replay.h" @@ -167,7 +168,6 @@ bool edp_set_backlight_level_nits(struct dc_link *link, *(uint32_t *)&dpcd_backlight_set.backlight_level_millinits = backlight_millinits; *(uint16_t *)&dpcd_backlight_set.backlight_transition_time_ms = (uint16_t)transition_time_in_ms; - link->backlight_settings.backlight_millinits = backlight_millinits; if (!link->dpcd_caps.panel_luminance_control) { if (core_link_write_dpcd(link, DP_SOURCE_BACKLIGHT_LEVEL, @@ -280,9 +280,9 @@ bool set_default_brightness_aux(struct dc_link *link) if (link && link->dpcd_sink_ext_caps.bits.oled == 1) { if (!read_default_bl_aux(link, &default_backlight)) default_backlight = 150000; - // if < 5 nits or > 5000, it might be wrong readback - if (default_backlight < 5000 || default_backlight > 5000000) - default_backlight = 150000; // + // if < 1 nits or > 5000, it might be wrong readback + if (default_backlight < 1000 || default_backlight > 5000000) + default_backlight = 150000; return edp_set_backlight_level_nits(link, true, default_backlight, 0); @@ -290,14 +290,23 @@ bool set_default_brightness_aux(struct dc_link *link) return false; } -bool set_cached_brightness_aux(struct dc_link *link) +bool edp_is_ilr_optimization_enabled(struct dc_link *link) { - if (link->backlight_settings.backlight_millinits) - return edp_set_backlight_level_nits(link, true, - link->backlight_settings.backlight_millinits, 0); - else - return set_default_brightness_aux(link); - return false; + if (link->dpcd_caps.edp_supported_link_rates_count == 0 || !link->panel_config.ilr.optimize_edp_link_rate) + return false; + return true; +} + +enum dc_link_rate get_max_link_rate_from_ilr_table(struct dc_link *link) +{ + enum dc_link_rate link_rate = link->reported_link_cap.link_rate; + + for (int i = 0; i < link->dpcd_caps.edp_supported_link_rates_count; i++) { + if (link_rate < link->dpcd_caps.edp_supported_link_rates[i]) + link_rate = link->dpcd_caps.edp_supported_link_rates[i]; + } + + return link_rate; } bool edp_is_ilr_optimization_required(struct dc_link *link, @@ -311,8 +320,7 @@ bool edp_is_ilr_optimization_required(struct dc_link *link, ASSERT(link || crtc_timing); // invalid input - if (link->dpcd_caps.edp_supported_link_rates_count == 0 || - !link->panel_config.ilr.optimize_edp_link_rate) + if (!edp_is_ilr_optimization_enabled(link)) return false; @@ -362,6 +370,34 @@ void edp_panel_backlight_power_on(struct dc_link *link, bool wait_for_hpd) link->dc->hwss.edp_backlight_control(link, true); } +void edp_set_panel_power(struct dc_link *link, bool powerOn) +{ + if (powerOn) { + // 1. panel VDD on + if (!link->dc->config.edp_no_power_sequencing) + link->dc->hwss.edp_power_control(link, true); + link->dc->hwss.edp_wait_for_hpd_ready(link, true); + + // 2. panel BL on + if (link->dc->hwss.edp_backlight_control) + link->dc->hwss.edp_backlight_control(link, true); + + // 3. Rx power on + dpcd_write_rx_power_ctrl(link, true); + } else { + // 3. Rx power off + dpcd_write_rx_power_ctrl(link, false); + + // 2. panel BL off + if (link->dc->hwss.edp_backlight_control) + link->dc->hwss.edp_backlight_control(link, false); + + // 1. panel VDD off + if (!link->dc->config.edp_no_power_sequencing) + link->dc->hwss.edp_power_control(link, false); + } +} + bool edp_wait_for_t12(struct dc_link *link) { if (link->connector_signal == SIGNAL_TYPE_EDP && link->dc->hwss.edp_wait_for_T12) { diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.h b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.h index 0a5bbda8c739c..a034288ad75d4 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.h +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_edp_panel_control.h @@ -30,7 +30,6 @@ enum dp_panel_mode dp_get_panel_mode(struct dc_link *link); void dp_set_panel_mode(struct dc_link *link, enum dp_panel_mode panel_mode); bool set_default_brightness_aux(struct dc_link *link); -bool set_cached_brightness_aux(struct dc_link *link); void edp_panel_backlight_power_on(struct dc_link *link, bool wait_for_hpd); int edp_get_backlight_level(const struct dc_link *link); bool edp_get_backlight_level_nits(struct dc_link *link, @@ -64,9 +63,12 @@ bool edp_get_replay_state(const struct dc_link *link, uint64_t *state); bool edp_wait_for_t12(struct dc_link *link); bool edp_is_ilr_optimization_required(struct dc_link *link, struct dc_crtc_timing *crtc_timing); +bool edp_is_ilr_optimization_enabled(struct dc_link *link); +enum dc_link_rate get_max_link_rate_from_ilr_table(struct dc_link *link); bool edp_backlight_enable_aux(struct dc_link *link, bool enable); void edp_add_delay_for_T9(struct dc_link *link); bool edp_receiver_ready_T9(struct dc_link *link); bool edp_receiver_ready_T7(struct dc_link *link); bool edp_power_alpm_dpcd_enable(struct dc_link *link, bool enable); +void edp_set_panel_power(struct dc_link *link, bool powerOn); #endif /* __DC_LINK_EDP_POWER_CONTROL_H__ */ diff --git a/drivers/gpu/drm/amd/display/dmub/dmub_srv.h b/drivers/gpu/drm/amd/display/dmub/dmub_srv.h index 2d995c87fbb98..d3c4a9a577eea 100644 --- a/drivers/gpu/drm/amd/display/dmub/dmub_srv.h +++ b/drivers/gpu/drm/amd/display/dmub/dmub_srv.h @@ -186,6 +186,7 @@ struct dmub_srv_region_params { uint32_t vbios_size; const uint8_t *fw_inst_const; const uint8_t *fw_bss_data; + bool is_mailbox_in_inbox; }; /** @@ -205,20 +206,25 @@ struct dmub_srv_region_params { */ struct dmub_srv_region_info { uint32_t fb_size; + uint32_t inbox_size; uint8_t num_regions; struct dmub_region regions[DMUB_WINDOW_TOTAL]; }; /** - * struct dmub_srv_fb_params - parameters used for driver fb setup + * struct dmub_srv_memory_params - parameters used for driver fb setup * @region_info: region info calculated by dmub service - * @cpu_addr: base cpu address for the framebuffer - * @gpu_addr: base gpu virtual address for the framebuffer + * @cpu_fb_addr: base cpu address for the framebuffer + * @cpu_inbox_addr: base cpu address for the gart + * @gpu_fb_addr: base gpu virtual address for the framebuffer + * @gpu_inbox_addr: base gpu virtual address for the gart */ -struct dmub_srv_fb_params { +struct dmub_srv_memory_params { const struct dmub_srv_region_info *region_info; - void *cpu_addr; - uint64_t gpu_addr; + void *cpu_fb_addr; + void *cpu_inbox_addr; + uint64_t gpu_fb_addr; + uint64_t gpu_inbox_addr; }; /** @@ -546,8 +552,8 @@ dmub_srv_calc_region_info(struct dmub_srv *dmub, * DMUB_STATUS_OK - success * DMUB_STATUS_INVALID - unspecified error */ -enum dmub_status dmub_srv_calc_fb_info(struct dmub_srv *dmub, - const struct dmub_srv_fb_params *params, +enum dmub_status dmub_srv_calc_mem_info(struct dmub_srv *dmub, + const struct dmub_srv_memory_params *params, struct dmub_srv_fb_info *out); /** diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c index 93624ffe4eb82..6c45e216c709c 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c @@ -386,7 +386,7 @@ dmub_srv_calc_region_info(struct dmub_srv *dmub, uint32_t fw_state_size = DMUB_FW_STATE_SIZE; uint32_t trace_buffer_size = DMUB_TRACE_BUFFER_SIZE; uint32_t scratch_mem_size = DMUB_SCRATCH_MEM_SIZE; - + uint32_t previous_top = 0; if (!dmub->sw_init) return DMUB_STATUS_INVALID; @@ -411,8 +411,15 @@ dmub_srv_calc_region_info(struct dmub_srv *dmub, bios->base = dmub_align(stack->top, 256); bios->top = bios->base + params->vbios_size; - mail->base = dmub_align(bios->top, 256); - mail->top = mail->base + DMUB_MAILBOX_SIZE; + if (params->is_mailbox_in_inbox) { + mail->base = 0; + mail->top = mail->base + DMUB_MAILBOX_SIZE; + previous_top = bios->top; + } else { + mail->base = dmub_align(bios->top, 256); + mail->top = mail->base + DMUB_MAILBOX_SIZE; + previous_top = mail->top; + } fw_info = dmub_get_fw_meta_info(params); @@ -431,7 +438,7 @@ dmub_srv_calc_region_info(struct dmub_srv *dmub, dmub->fw_version = fw_info->fw_version; } - trace_buff->base = dmub_align(mail->top, 256); + trace_buff->base = dmub_align(previous_top, 256); trace_buff->top = trace_buff->base + dmub_align(trace_buffer_size, 64); fw_state->base = dmub_align(trace_buff->top, 256); @@ -442,11 +449,14 @@ dmub_srv_calc_region_info(struct dmub_srv *dmub, out->fb_size = dmub_align(scratch_mem->top, 4096); + if (params->is_mailbox_in_inbox) + out->inbox_size = dmub_align(mail->top, 4096); + return DMUB_STATUS_OK; } -enum dmub_status dmub_srv_calc_fb_info(struct dmub_srv *dmub, - const struct dmub_srv_fb_params *params, +enum dmub_status dmub_srv_calc_mem_info(struct dmub_srv *dmub, + const struct dmub_srv_memory_params *params, struct dmub_srv_fb_info *out) { uint8_t *cpu_base; @@ -461,8 +471,8 @@ enum dmub_status dmub_srv_calc_fb_info(struct dmub_srv *dmub, if (params->region_info->num_regions != DMUB_NUM_WINDOWS) return DMUB_STATUS_INVALID; - cpu_base = (uint8_t *)params->cpu_addr; - gpu_base = params->gpu_addr; + cpu_base = (uint8_t *)params->cpu_fb_addr; + gpu_base = params->gpu_fb_addr; for (i = 0; i < DMUB_NUM_WINDOWS; ++i) { const struct dmub_region *reg = @@ -470,6 +480,12 @@ enum dmub_status dmub_srv_calc_fb_info(struct dmub_srv *dmub, out->fb[i].cpu_addr = cpu_base + reg->base; out->fb[i].gpu_addr = gpu_base + reg->base; + + if (i == DMUB_WINDOW_4_MAILBOX && params->cpu_inbox_addr != 0) { + out->fb[i].cpu_addr = (uint8_t *)params->cpu_inbox_addr + reg->base; + out->fb[i].gpu_addr = params->gpu_inbox_addr + reg->base; + } + out->fb[i].size = reg->top - reg->base; } @@ -658,9 +674,16 @@ enum dmub_status dmub_srv_sync_inbox1(struct dmub_srv *dmub) return DMUB_STATUS_INVALID; if (dmub->hw_funcs.get_inbox1_rptr && dmub->hw_funcs.get_inbox1_wptr) { - dmub->inbox1_rb.rptr = dmub->hw_funcs.get_inbox1_rptr(dmub); - dmub->inbox1_rb.wrpt = dmub->hw_funcs.get_inbox1_wptr(dmub); - dmub->inbox1_last_wptr = dmub->inbox1_rb.wrpt; + uint32_t rptr = dmub->hw_funcs.get_inbox1_rptr(dmub); + uint32_t wptr = dmub->hw_funcs.get_inbox1_wptr(dmub); + + if (rptr > dmub->inbox1_rb.capacity || wptr > dmub->inbox1_rb.capacity) { + return DMUB_STATUS_HW_FAILURE; + } else { + dmub->inbox1_rb.rptr = rptr; + dmub->inbox1_rb.wrpt = wptr; + dmub->inbox1_last_wptr = dmub->inbox1_rb.wrpt; + } } return DMUB_STATUS_OK; @@ -694,6 +717,11 @@ enum dmub_status dmub_srv_cmd_queue(struct dmub_srv *dmub, if (!dmub->hw_init) return DMUB_STATUS_INVALID; + if (dmub->inbox1_rb.rptr > dmub->inbox1_rb.capacity || + dmub->inbox1_rb.wrpt > dmub->inbox1_rb.capacity) { + return DMUB_STATUS_HW_FAILURE; + } + if (dmub_rb_push_front(&dmub->inbox1_rb, cmd)) return DMUB_STATUS_OK; @@ -969,6 +997,7 @@ enum dmub_status dmub_srv_wait_for_inbox0_ack(struct dmub_srv *dmub, uint32_t ti ack = dmub->hw_funcs.read_inbox0_ack_register(dmub); if (ack) return DMUB_STATUS_OK; + udelay(1); } return DMUB_STATUS_TIMEOUT; } diff --git a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c index 73a2b37fbbd75..2b3d5183818ac 100644 --- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c +++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c @@ -839,6 +839,8 @@ bool is_psr_su_specific_panel(struct dc_link *link) ((dpcd_caps->sink_dev_id_str[1] == 0x08 && dpcd_caps->sink_dev_id_str[0] == 0x08) || (dpcd_caps->sink_dev_id_str[1] == 0x08 && dpcd_caps->sink_dev_id_str[0] == 0x07))) isPSRSUSupported = false; + else if (dpcd_caps->sink_dev_id_str[1] == 0x08 && dpcd_caps->sink_dev_id_str[0] == 0x03) + isPSRSUSupported = false; else if (dpcd_caps->psr_info.force_psrsu_cap == 0x1) isPSRSUSupported = true; } diff --git a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_11_0_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_11_0_0_offset.h index c92c4b83253f8..4bff1ef8a9a64 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_11_0_0_offset.h +++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_11_0_0_offset.h @@ -6369,6 +6369,8 @@ #define regTCP_INVALIDATE_BASE_IDX 1 #define regTCP_STATUS 0x19a1 #define regTCP_STATUS_BASE_IDX 1 +#define regTCP_CNTL 0x19a2 +#define regTCP_CNTL_BASE_IDX 1 #define regTCP_CNTL2 0x19a3 #define regTCP_CNTL2_BASE_IDX 1 #define regTCP_DEBUG_INDEX 0x19a5 diff --git a/drivers/gpu/drm/amd/include/pptable.h b/drivers/gpu/drm/amd/include/pptable.h index 0b6a057e0a4c4..5aac8d545bdc6 100644 --- a/drivers/gpu/drm/amd/include/pptable.h +++ b/drivers/gpu/drm/amd/include/pptable.h @@ -78,7 +78,7 @@ typedef struct _ATOM_PPLIB_THERMALCONTROLLER typedef struct _ATOM_PPLIB_STATE { UCHAR ucNonClockStateIndex; - UCHAR ucClockStateIndices[1]; // variable-sized + UCHAR ucClockStateIndices[]; // variable-sized } ATOM_PPLIB_STATE; @@ -473,7 +473,7 @@ typedef struct _ATOM_PPLIB_STATE_V2 /** * Driver will read the first ucNumDPMLevels in this array */ - UCHAR clockInfoIndex[1]; + UCHAR clockInfoIndex[]; } ATOM_PPLIB_STATE_V2; typedef struct _StateArray{ diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c index 8bb2da13826f1..b4c9fedaa51de 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c @@ -734,7 +734,7 @@ static ssize_t amdgpu_set_pp_od_clk_voltage(struct device *dev, if (adev->in_suspend && !adev->in_runpm) return -EPERM; - if (count > 127) + if (count > 127 || count == 0) return -EINVAL; if (*buf == 's') @@ -754,7 +754,8 @@ static ssize_t amdgpu_set_pp_od_clk_voltage(struct device *dev, else return -EINVAL; - memcpy(buf_cpy, buf, count+1); + memcpy(buf_cpy, buf, count); + buf_cpy[count] = 0; tmp_str = buf_cpy; @@ -771,6 +772,9 @@ static ssize_t amdgpu_set_pp_od_clk_voltage(struct device *dev, return -EINVAL; parameter_size++; + if (!tmp_str) + break; + while (isspace(*tmp_str)) tmp_str++; } diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pptable_v1_0.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pptable_v1_0.h index 7a31cfa5e7fb4..9fcad69a9f344 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pptable_v1_0.h +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pptable_v1_0.h @@ -164,7 +164,7 @@ typedef struct _ATOM_Tonga_State { typedef struct _ATOM_Tonga_State_Array { UCHAR ucRevId; UCHAR ucNumEntries; /* Number of entries. */ - ATOM_Tonga_State entries[1]; /* Dynamically allocate entries. */ + ATOM_Tonga_State entries[]; /* Dynamically allocate entries. */ } ATOM_Tonga_State_Array; typedef struct _ATOM_Tonga_MCLK_Dependency_Record { @@ -179,7 +179,7 @@ typedef struct _ATOM_Tonga_MCLK_Dependency_Record { typedef struct _ATOM_Tonga_MCLK_Dependency_Table { UCHAR ucRevId; UCHAR ucNumEntries; /* Number of entries. */ - ATOM_Tonga_MCLK_Dependency_Record entries[1]; /* Dynamically allocate entries. */ + ATOM_Tonga_MCLK_Dependency_Record entries[]; /* Dynamically allocate entries. */ } ATOM_Tonga_MCLK_Dependency_Table; typedef struct _ATOM_Tonga_SCLK_Dependency_Record { @@ -194,7 +194,7 @@ typedef struct _ATOM_Tonga_SCLK_Dependency_Record { typedef struct _ATOM_Tonga_SCLK_Dependency_Table { UCHAR ucRevId; UCHAR ucNumEntries; /* Number of entries. */ - ATOM_Tonga_SCLK_Dependency_Record entries[1]; /* Dynamically allocate entries. */ + ATOM_Tonga_SCLK_Dependency_Record entries[]; /* Dynamically allocate entries. */ } ATOM_Tonga_SCLK_Dependency_Table; typedef struct _ATOM_Polaris_SCLK_Dependency_Record { @@ -210,7 +210,7 @@ typedef struct _ATOM_Polaris_SCLK_Dependency_Record { typedef struct _ATOM_Polaris_SCLK_Dependency_Table { UCHAR ucRevId; UCHAR ucNumEntries; /* Number of entries. */ - ATOM_Polaris_SCLK_Dependency_Record entries[1]; /* Dynamically allocate entries. */ + ATOM_Polaris_SCLK_Dependency_Record entries[]; /* Dynamically allocate entries. */ } ATOM_Polaris_SCLK_Dependency_Table; typedef struct _ATOM_Tonga_PCIE_Record { @@ -222,7 +222,7 @@ typedef struct _ATOM_Tonga_PCIE_Record { typedef struct _ATOM_Tonga_PCIE_Table { UCHAR ucRevId; UCHAR ucNumEntries; /* Number of entries. */ - ATOM_Tonga_PCIE_Record entries[1]; /* Dynamically allocate entries. */ + ATOM_Tonga_PCIE_Record entries[]; /* Dynamically allocate entries. */ } ATOM_Tonga_PCIE_Table; typedef struct _ATOM_Polaris10_PCIE_Record { @@ -235,7 +235,7 @@ typedef struct _ATOM_Polaris10_PCIE_Record { typedef struct _ATOM_Polaris10_PCIE_Table { UCHAR ucRevId; UCHAR ucNumEntries; /* Number of entries. */ - ATOM_Polaris10_PCIE_Record entries[1]; /* Dynamically allocate entries. */ + ATOM_Polaris10_PCIE_Record entries[]; /* Dynamically allocate entries. */ } ATOM_Polaris10_PCIE_Table; @@ -252,7 +252,7 @@ typedef struct _ATOM_Tonga_MM_Dependency_Record { typedef struct _ATOM_Tonga_MM_Dependency_Table { UCHAR ucRevId; UCHAR ucNumEntries; /* Number of entries. */ - ATOM_Tonga_MM_Dependency_Record entries[1]; /* Dynamically allocate entries. */ + ATOM_Tonga_MM_Dependency_Record entries[]; /* Dynamically allocate entries. */ } ATOM_Tonga_MM_Dependency_Table; typedef struct _ATOM_Tonga_Voltage_Lookup_Record { @@ -265,7 +265,7 @@ typedef struct _ATOM_Tonga_Voltage_Lookup_Record { typedef struct _ATOM_Tonga_Voltage_Lookup_Table { UCHAR ucRevId; UCHAR ucNumEntries; /* Number of entries. */ - ATOM_Tonga_Voltage_Lookup_Record entries[1]; /* Dynamically allocate entries. */ + ATOM_Tonga_Voltage_Lookup_Record entries[]; /* Dynamically allocate entries. */ } ATOM_Tonga_Voltage_Lookup_Table; typedef struct _ATOM_Tonga_Fan_Table { diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c index 5a2371484a58c..11372fcc59c8f 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c @@ -1823,9 +1823,7 @@ static void smu7_init_dpm_defaults(struct pp_hwmgr *hwmgr) data->mclk_dpm_key_disabled = hwmgr->feature_mask & PP_MCLK_DPM_MASK ? false : true; data->sclk_dpm_key_disabled = hwmgr->feature_mask & PP_SCLK_DPM_MASK ? false : true; - data->pcie_dpm_key_disabled = - !amdgpu_device_pcie_dynamic_switching_supported() || - !(hwmgr->feature_mask & PP_PCIE_DPM_MASK); + data->pcie_dpm_key_disabled = !(hwmgr->feature_mask & PP_PCIE_DPM_MASK); /* need to set voltage control types before EVV patching */ data->voltage_control = SMU7_VOLTAGE_CONTROL_NONE; data->vddci_control = SMU7_VOLTAGE_CONTROL_NONE; diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index f005a90c35af4..b47fd42414f46 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -1232,7 +1232,7 @@ static int smu_smc_hw_setup(struct smu_context *smu) { struct smu_feature *feature = &smu->smu_feature; struct amdgpu_device *adev = smu->adev; - uint32_t pcie_gen = 0, pcie_width = 0; + uint8_t pcie_gen = 0, pcie_width = 0; uint64_t features_supported; int ret = 0; diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h index 5a52098bcf166..72ed836328966 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h @@ -844,7 +844,7 @@ struct pptable_funcs { * &pcie_gen_cap: Maximum allowed PCIe generation. * &pcie_width_cap: Maximum allowed PCIe width. */ - int (*update_pcie_parameters)(struct smu_context *smu, uint32_t pcie_gen_cap, uint32_t pcie_width_cap); + int (*update_pcie_parameters)(struct smu_context *smu, uint8_t pcie_gen_cap, uint8_t pcie_width_cap); /** * @i2c_init: Initialize i2c. diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h index 355c156d871af..cc02f979e9e98 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h @@ -296,8 +296,8 @@ int smu_v13_0_get_pptable_from_firmware(struct smu_context *smu, uint32_t pptable_id); int smu_v13_0_update_pcie_parameters(struct smu_context *smu, - uint32_t pcie_gen_cap, - uint32_t pcie_width_cap); + uint8_t pcie_gen_cap, + uint8_t pcie_width_cap); #endif #endif diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c index 18487ae10bcff..c564f6e191f84 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c @@ -2376,8 +2376,8 @@ static int navi10_get_power_limit(struct smu_context *smu, } static int navi10_update_pcie_parameters(struct smu_context *smu, - uint32_t pcie_gen_cap, - uint32_t pcie_width_cap) + uint8_t pcie_gen_cap, + uint8_t pcie_width_cap) { struct smu_11_0_dpm_context *dpm_context = smu->smu_dpm.dpm_context; PPTable_t *pptable = smu->smu_table.driver_pptable; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c index da2860da60188..a7f4f82d23b4b 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c @@ -2085,14 +2085,14 @@ static int sienna_cichlid_display_disable_memory_clock_switch(struct smu_context #define MAX(a, b) ((a) > (b) ? (a) : (b)) static int sienna_cichlid_update_pcie_parameters(struct smu_context *smu, - uint32_t pcie_gen_cap, - uint32_t pcie_width_cap) + uint8_t pcie_gen_cap, + uint8_t pcie_width_cap) { struct smu_11_0_dpm_context *dpm_context = smu->smu_dpm.dpm_context; struct smu_11_0_pcie_table *pcie_table = &dpm_context->dpm_tables.pcie_table; uint8_t *table_member1, *table_member2; - uint32_t min_gen_speed, max_gen_speed; - uint32_t min_lane_width, max_lane_width; + uint8_t min_gen_speed, max_gen_speed; + uint8_t min_lane_width, max_lane_width; uint32_t smu_pcie_arg; int ret, i; @@ -2108,7 +2108,7 @@ static int sienna_cichlid_update_pcie_parameters(struct smu_context *smu, min_lane_width = min_lane_width > max_lane_width ? max_lane_width : min_lane_width; - if (!amdgpu_device_pcie_dynamic_switching_supported()) { + if (!(smu->adev->pm.pp_feature & PP_PCIE_DPM_MASK)) { pcie_table->pcie_gen[0] = max_gen_speed; pcie_table->pcie_lane[0] = max_lane_width; } else { diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c index cc3169400c9b0..08fff9600bd29 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c @@ -257,8 +257,11 @@ static int aldebaran_tables_init(struct smu_context *smu) } smu_table->ecc_table = kzalloc(tables[SMU_TABLE_ECCINFO].size, GFP_KERNEL); - if (!smu_table->ecc_table) + if (!smu_table->ecc_table) { + kfree(smu_table->metrics_table); + kfree(smu_table->gpu_metrics_table); return -ENOMEM; + } return 0; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c index 0232adb95df3a..5355f621388bb 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c @@ -2420,8 +2420,8 @@ int smu_v13_0_mode1_reset(struct smu_context *smu) } int smu_v13_0_update_pcie_parameters(struct smu_context *smu, - uint32_t pcie_gen_cap, - uint32_t pcie_width_cap) + uint8_t pcie_gen_cap, + uint8_t pcie_width_cap) { struct smu_13_0_dpm_context *dpm_context = smu->smu_dpm.dpm_context; struct smu_13_0_pcie_table *pcie_table = @@ -2430,7 +2430,10 @@ int smu_v13_0_update_pcie_parameters(struct smu_context *smu, uint32_t smu_pcie_arg; int ret, i; - if (!amdgpu_device_pcie_dynamic_switching_supported()) { + if (!num_of_levels) + return 0; + + if (!(smu->adev->pm.pp_feature & PP_PCIE_DPM_MASK)) { if (pcie_table->pcie_gen[num_of_levels - 1] < pcie_gen_cap) pcie_gen_cap = pcie_table->pcie_gen[num_of_levels - 1]; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index 3903a47669e43..4022dd44ebb2b 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -352,12 +352,12 @@ static int smu_v13_0_0_check_powerplay_table(struct smu_context *smu) if (powerplay_table->platform_caps & SMU_13_0_0_PP_PLATFORM_CAP_HARDWAREDC) smu->dc_controlled_by_gpio = true; - if (powerplay_table->platform_caps & SMU_13_0_0_PP_PLATFORM_CAP_BACO || - powerplay_table->platform_caps & SMU_13_0_0_PP_PLATFORM_CAP_MACO) + if (powerplay_table->platform_caps & SMU_13_0_0_PP_PLATFORM_CAP_BACO) { smu_baco->platform_support = true; - if (powerplay_table->platform_caps & SMU_13_0_0_PP_PLATFORM_CAP_MACO) - smu_baco->maco_support = true; + if (powerplay_table->platform_caps & SMU_13_0_0_PP_PLATFORM_CAP_MACO) + smu_baco->maco_support = true; + } /* * We are in the transition to a new OD mechanism. @@ -2163,38 +2163,10 @@ static int smu_v13_0_0_set_power_profile_mode(struct smu_context *smu, } } - if (smu->power_profile_mode == PP_SMC_POWER_PROFILE_COMPUTE && - (((smu->adev->pdev->device == 0x744C) && (smu->adev->pdev->revision == 0xC8)) || - ((smu->adev->pdev->device == 0x744C) && (smu->adev->pdev->revision == 0xCC)))) { - ret = smu_cmn_update_table(smu, - SMU_TABLE_ACTIVITY_MONITOR_COEFF, - WORKLOAD_PPLIB_COMPUTE_BIT, - (void *)(&activity_monitor_external), - false); - if (ret) { - dev_err(smu->adev->dev, "[%s] Failed to get activity monitor!", __func__); - return ret; - } - - ret = smu_cmn_update_table(smu, - SMU_TABLE_ACTIVITY_MONITOR_COEFF, - WORKLOAD_PPLIB_CUSTOM_BIT, - (void *)(&activity_monitor_external), - true); - if (ret) { - dev_err(smu->adev->dev, "[%s] Failed to set activity monitor!", __func__); - return ret; - } - - workload_type = smu_cmn_to_asic_specific_index(smu, - CMN2ASIC_MAPPING_WORKLOAD, - PP_SMC_POWER_PROFILE_CUSTOM); - } else { - /* conv PP_SMC_POWER_PROFILE* to WORKLOAD_PPLIB_*_BIT */ - workload_type = smu_cmn_to_asic_specific_index(smu, + /* conv PP_SMC_POWER_PROFILE* to WORKLOAD_PPLIB_*_BIT */ + workload_type = smu_cmn_to_asic_specific_index(smu, CMN2ASIC_MAPPING_WORKLOAD, smu->power_profile_mode); - } if (workload_type < 0) return -EINVAL; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c index 94ef5b4d116d7..51ae41cb43ea0 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c @@ -341,12 +341,13 @@ static int smu_v13_0_7_check_powerplay_table(struct smu_context *smu) if (powerplay_table->platform_caps & SMU_13_0_7_PP_PLATFORM_CAP_HARDWAREDC) smu->dc_controlled_by_gpio = true; - if (powerplay_table->platform_caps & SMU_13_0_7_PP_PLATFORM_CAP_BACO || - powerplay_table->platform_caps & SMU_13_0_7_PP_PLATFORM_CAP_MACO) + if (powerplay_table->platform_caps & SMU_13_0_7_PP_PLATFORM_CAP_BACO) { smu_baco->platform_support = true; - if (smu_baco->platform_support && (BoardTable->HsrEnabled || BoardTable->VddqOffEnabled)) - smu_baco->maco_support = true; + if ((powerplay_table->platform_caps & SMU_13_0_7_PP_PLATFORM_CAP_MACO) + && (BoardTable->HsrEnabled || BoardTable->VddqOffEnabled)) + smu_baco->maco_support = true; + } #if 0 if (!overdrive_lowerlimits->FeatureCtrlMask || diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c b/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c index 4618687a8f4d6..f3e744172673c 100644 --- a/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c +++ b/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c @@ -1223,7 +1223,7 @@ int komeda_build_display_data_flow(struct komeda_crtc *kcrtc, return 0; } -static void +static int komeda_pipeline_unbound_components(struct komeda_pipeline *pipe, struct komeda_pipeline_state *new) { @@ -1243,8 +1243,12 @@ komeda_pipeline_unbound_components(struct komeda_pipeline *pipe, c = komeda_pipeline_get_component(pipe, id); c_st = komeda_component_get_state_and_set_user(c, drm_st, NULL, new->crtc); + if (PTR_ERR(c_st) == -EDEADLK) + return -EDEADLK; WARN_ON(IS_ERR(c_st)); } + + return 0; } /* release unclaimed pipeline resource */ @@ -1266,9 +1270,8 @@ int komeda_release_unclaimed_resources(struct komeda_pipeline *pipe, if (WARN_ON(IS_ERR_OR_NULL(st))) return -EINVAL; - komeda_pipeline_unbound_components(pipe, st); + return komeda_pipeline_unbound_components(pipe, st); - return 0; } /* Since standalone disabled components must be disabled separately and in the diff --git a/drivers/gpu/drm/ast/ast_drv.h b/drivers/gpu/drm/ast/ast_drv.h index 848a9f1403e89..f7053f2972bb9 100644 --- a/drivers/gpu/drm/ast/ast_drv.h +++ b/drivers/gpu/drm/ast/ast_drv.h @@ -172,6 +172,17 @@ to_ast_sil164_connector(struct drm_connector *connector) return container_of(connector, struct ast_sil164_connector, base); } +struct ast_bmc_connector { + struct drm_connector base; + struct drm_connector *physical_connector; +}; + +static inline struct ast_bmc_connector * +to_ast_bmc_connector(struct drm_connector *connector) +{ + return container_of(connector, struct ast_bmc_connector, base); +} + /* * Device */ @@ -216,7 +227,7 @@ struct ast_device { } astdp; struct { struct drm_encoder encoder; - struct drm_connector connector; + struct ast_bmc_connector bmc_connector; } bmc; } output; diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c index 32f04ec6c386f..3de0f457fff6a 100644 --- a/drivers/gpu/drm/ast/ast_mode.c +++ b/drivers/gpu/drm/ast/ast_mode.c @@ -1767,6 +1767,30 @@ static const struct drm_encoder_funcs ast_bmc_encoder_funcs = { .destroy = drm_encoder_cleanup, }; +static int ast_bmc_connector_helper_detect_ctx(struct drm_connector *connector, + struct drm_modeset_acquire_ctx *ctx, + bool force) +{ + struct ast_bmc_connector *bmc_connector = to_ast_bmc_connector(connector); + struct drm_connector *physical_connector = bmc_connector->physical_connector; + + /* + * Most user-space compositors cannot handle more than one connected + * connector per CRTC. Hence, we only mark the BMC as connected if the + * physical connector is disconnected. If the physical connector's status + * is connected or unknown, the BMC remains disconnected. This has no + * effect on the output of the BMC. + * + * FIXME: Remove this logic once user-space compositors can handle more + * than one connector per CRTC. The BMC should always be connected. + */ + + if (physical_connector && physical_connector->status == connector_status_disconnected) + return connector_status_connected; + + return connector_status_disconnected; +} + static int ast_bmc_connector_helper_get_modes(struct drm_connector *connector) { return drm_add_modes_noedid(connector, 4096, 4096); @@ -1774,6 +1798,7 @@ static int ast_bmc_connector_helper_get_modes(struct drm_connector *connector) static const struct drm_connector_helper_funcs ast_bmc_connector_helper_funcs = { .get_modes = ast_bmc_connector_helper_get_modes, + .detect_ctx = ast_bmc_connector_helper_detect_ctx, }; static const struct drm_connector_funcs ast_bmc_connector_funcs = { @@ -1784,12 +1809,33 @@ static const struct drm_connector_funcs ast_bmc_connector_funcs = { .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, }; -static int ast_bmc_output_init(struct ast_device *ast) +static int ast_bmc_connector_init(struct drm_device *dev, + struct ast_bmc_connector *bmc_connector, + struct drm_connector *physical_connector) +{ + struct drm_connector *connector = &bmc_connector->base; + int ret; + + ret = drm_connector_init(dev, connector, &ast_bmc_connector_funcs, + DRM_MODE_CONNECTOR_VIRTUAL); + if (ret) + return ret; + + drm_connector_helper_add(connector, &ast_bmc_connector_helper_funcs); + + bmc_connector->physical_connector = physical_connector; + + return 0; +} + +static int ast_bmc_output_init(struct ast_device *ast, + struct drm_connector *physical_connector) { struct drm_device *dev = &ast->base; struct drm_crtc *crtc = &ast->crtc; struct drm_encoder *encoder = &ast->output.bmc.encoder; - struct drm_connector *connector = &ast->output.bmc.connector; + struct ast_bmc_connector *bmc_connector = &ast->output.bmc.bmc_connector; + struct drm_connector *connector = &bmc_connector->base; int ret; ret = drm_encoder_init(dev, encoder, @@ -1799,13 +1845,10 @@ static int ast_bmc_output_init(struct ast_device *ast) return ret; encoder->possible_crtcs = drm_crtc_mask(crtc); - ret = drm_connector_init(dev, connector, &ast_bmc_connector_funcs, - DRM_MODE_CONNECTOR_VIRTUAL); + ret = ast_bmc_connector_init(dev, bmc_connector, physical_connector); if (ret) return ret; - drm_connector_helper_add(connector, &ast_bmc_connector_helper_funcs); - ret = drm_connector_attach_encoder(connector, encoder); if (ret) return ret; @@ -1864,6 +1907,7 @@ static const struct drm_mode_config_funcs ast_mode_config_funcs = { int ast_mode_config_init(struct ast_device *ast) { struct drm_device *dev = &ast->base; + struct drm_connector *physical_connector = NULL; int ret; ret = drmm_mode_config_init(dev); @@ -1904,23 +1948,27 @@ int ast_mode_config_init(struct ast_device *ast) ret = ast_vga_output_init(ast); if (ret) return ret; + physical_connector = &ast->output.vga.vga_connector.base; } if (ast->tx_chip_types & AST_TX_SIL164_BIT) { ret = ast_sil164_output_init(ast); if (ret) return ret; + physical_connector = &ast->output.sil164.sil164_connector.base; } if (ast->tx_chip_types & AST_TX_DP501_BIT) { ret = ast_dp501_output_init(ast); if (ret) return ret; + physical_connector = &ast->output.dp501.connector; } if (ast->tx_chip_types & AST_TX_ASTDP_BIT) { ret = ast_astdp_output_init(ast); if (ret) return ret; + physical_connector = &ast->output.astdp.connector; } - ret = ast_bmc_output_init(ast); + ret = ast_bmc_output_init(ast, physical_connector); if (ret) return ret; diff --git a/drivers/gpu/drm/bridge/Kconfig b/drivers/gpu/drm/bridge/Kconfig index ba82a1142adf7..3e6a4e2044c0e 100644 --- a/drivers/gpu/drm/bridge/Kconfig +++ b/drivers/gpu/drm/bridge/Kconfig @@ -313,6 +313,7 @@ config DRM_TOSHIBA_TC358768 select REGMAP_I2C select DRM_PANEL select DRM_MIPI_DSI + select VIDEOMODE_HELPERS help Toshiba TC358768AXBG/TC358778XBG DSI bridge chip driver. diff --git a/drivers/gpu/drm/bridge/ite-it66121.c b/drivers/gpu/drm/bridge/ite-it66121.c index fc7f5ec5fb381..8f5846b76d594 100644 --- a/drivers/gpu/drm/bridge/ite-it66121.c +++ b/drivers/gpu/drm/bridge/ite-it66121.c @@ -884,14 +884,14 @@ static struct edid *it66121_bridge_get_edid(struct drm_bridge *bridge, mutex_lock(&ctx->lock); ret = it66121_preamble_ddc(ctx); if (ret) { - edid = ERR_PTR(ret); + edid = NULL; goto out_unlock; } ret = regmap_write(ctx->regmap, IT66121_DDC_HEADER_REG, IT66121_DDC_HEADER_EDID); if (ret) { - edid = ERR_PTR(ret); + edid = NULL; goto out_unlock; } diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index 60794fcde1d50..554d4468aa7c0 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -2012,7 +2012,7 @@ int drm_atomic_helper_commit(struct drm_device *dev, return ret; drm_atomic_helper_async_commit(dev, state); - drm_atomic_helper_cleanup_planes(dev, state); + drm_atomic_helper_unprepare_planes(dev, state); return 0; } @@ -2072,7 +2072,7 @@ int drm_atomic_helper_commit(struct drm_device *dev, return 0; err: - drm_atomic_helper_cleanup_planes(dev, state); + drm_atomic_helper_unprepare_planes(dev, state); return ret; } EXPORT_SYMBOL(drm_atomic_helper_commit); @@ -2650,6 +2650,39 @@ int drm_atomic_helper_prepare_planes(struct drm_device *dev, } EXPORT_SYMBOL(drm_atomic_helper_prepare_planes); +/** + * drm_atomic_helper_unprepare_planes - release plane resources on aborts + * @dev: DRM device + * @state: atomic state object with old state structures + * + * This function cleans up plane state, specifically framebuffers, from the + * atomic state. It undoes the effects of drm_atomic_helper_prepare_planes() + * when aborting an atomic commit. For cleaning up after a successful commit + * use drm_atomic_helper_cleanup_planes(). + */ +void drm_atomic_helper_unprepare_planes(struct drm_device *dev, + struct drm_atomic_state *state) +{ + struct drm_plane *plane; + struct drm_plane_state *new_plane_state; + int i; + + for_each_new_plane_in_state(state, plane, new_plane_state, i) { + const struct drm_plane_helper_funcs *funcs = plane->helper_private; + + if (funcs->end_fb_access) + funcs->end_fb_access(plane, new_plane_state); + } + + for_each_new_plane_in_state(state, plane, new_plane_state, i) { + const struct drm_plane_helper_funcs *funcs = plane->helper_private; + + if (funcs->cleanup_fb) + funcs->cleanup_fb(plane, new_plane_state); + } +} +EXPORT_SYMBOL(drm_atomic_helper_unprepare_planes); + static bool plane_crtc_active(const struct drm_plane_state *state) { return state->crtc && state->crtc->state->active; @@ -2784,6 +2817,17 @@ void drm_atomic_helper_commit_planes(struct drm_device *dev, funcs->atomic_flush(crtc, old_state); } + + /* + * Signal end of framebuffer access here before hw_done. After hw_done, + * a later commit might have already released the plane state. + */ + for_each_old_plane_in_state(old_state, plane, old_plane_state, i) { + const struct drm_plane_helper_funcs *funcs = plane->helper_private; + + if (funcs->end_fb_access) + funcs->end_fb_access(plane, old_plane_state); + } } EXPORT_SYMBOL(drm_atomic_helper_commit_planes); @@ -2911,40 +2955,22 @@ EXPORT_SYMBOL(drm_atomic_helper_disable_planes_on_crtc); * configuration. Hence the old configuration must be perserved in @old_state to * be able to call this function. * - * This function must also be called on the new state when the atomic update - * fails at any point after calling drm_atomic_helper_prepare_planes(). + * This function may not be called on the new state when the atomic update + * fails at any point after calling drm_atomic_helper_prepare_planes(). Use + * drm_atomic_helper_unprepare_planes() in this case. */ void drm_atomic_helper_cleanup_planes(struct drm_device *dev, struct drm_atomic_state *old_state) { struct drm_plane *plane; - struct drm_plane_state *old_plane_state, *new_plane_state; + struct drm_plane_state *old_plane_state; int i; - for_each_oldnew_plane_in_state(old_state, plane, old_plane_state, new_plane_state, i) { + for_each_old_plane_in_state(old_state, plane, old_plane_state, i) { const struct drm_plane_helper_funcs *funcs = plane->helper_private; - if (funcs->end_fb_access) - funcs->end_fb_access(plane, new_plane_state); - } - - for_each_oldnew_plane_in_state(old_state, plane, old_plane_state, new_plane_state, i) { - const struct drm_plane_helper_funcs *funcs; - struct drm_plane_state *plane_state; - - /* - * This might be called before swapping when commit is aborted, - * in which case we have to cleanup the new state. - */ - if (old_plane_state == plane->state) - plane_state = new_plane_state; - else - plane_state = old_plane_state; - - funcs = plane->helper_private; - if (funcs->cleanup_fb) - funcs->cleanup_fb(plane, plane_state); + funcs->cleanup_fb(plane, old_plane_state); } } EXPORT_SYMBOL(drm_atomic_helper_cleanup_planes); diff --git a/drivers/gpu/drm/drm_auth.c b/drivers/gpu/drm/drm_auth.c index cf92a9ae8034c..6899b3dc1f12a 100644 --- a/drivers/gpu/drm/drm_auth.c +++ b/drivers/gpu/drm/drm_auth.c @@ -235,7 +235,8 @@ static int drm_new_set_master(struct drm_device *dev, struct drm_file *fpriv) static int drm_master_check_perm(struct drm_device *dev, struct drm_file *file_priv) { - if (file_priv->pid == task_pid(current) && file_priv->was_master) + if (file_priv->was_master && + rcu_access_pointer(file_priv->pid) == task_tgid(current)) return 0; if (!capable(CAP_SYS_ADMIN)) diff --git a/drivers/gpu/drm/drm_debugfs.c b/drivers/gpu/drm/drm_debugfs.c index 2de43ff3ce0a4..41b0682c638ef 100644 --- a/drivers/gpu/drm/drm_debugfs.c +++ b/drivers/gpu/drm/drm_debugfs.c @@ -92,15 +92,17 @@ static int drm_clients_info(struct seq_file *m, void *data) */ mutex_lock(&dev->filelist_mutex); list_for_each_entry_reverse(priv, &dev->filelist, lhead) { - struct task_struct *task; bool is_current_master = drm_is_current_master(priv); + struct task_struct *task; + struct pid *pid; - rcu_read_lock(); /* locks pid_task()->comm */ - task = pid_task(priv->pid, PIDTYPE_TGID); + rcu_read_lock(); /* Locks priv->pid and pid_task()->comm! */ + pid = rcu_dereference(priv->pid); + task = pid_task(pid, PIDTYPE_TGID); uid = task ? __task_cred(task)->euid : GLOBAL_ROOT_UID; seq_printf(m, "%20s %5d %3d %c %c %5d %10u\n", task ? task->comm : "", - pid_vnr(priv->pid), + pid_vnr(pid), priv->minor->index, is_current_master ? 'y' : 'n', priv->authenticated ? 'y' : 'n', diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index 4b71040ae5be5..a491280ca48c8 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -2308,7 +2308,8 @@ int drm_edid_override_connector_update(struct drm_connector *connector) override = drm_edid_override_get(connector); if (override) { - num_modes = drm_edid_connector_update(connector, override); + if (drm_edid_connector_update(connector, override) == 0) + num_modes = drm_edid_connector_add_modes(connector); drm_edid_free(override); @@ -3499,11 +3500,19 @@ static struct drm_display_mode *drm_mode_detailed(struct drm_connector *connecto mode->vsync_end = mode->vsync_start + vsync_pulse_width; mode->vtotal = mode->vdisplay + vblank; - /* Some EDIDs have bogus h/vtotal values */ - if (mode->hsync_end > mode->htotal) - mode->htotal = mode->hsync_end + 1; - if (mode->vsync_end > mode->vtotal) - mode->vtotal = mode->vsync_end + 1; + /* Some EDIDs have bogus h/vsync_end values */ + if (mode->hsync_end > mode->htotal) { + drm_dbg_kms(dev, "[CONNECTOR:%d:%s] reducing hsync_end %d->%d\n", + connector->base.id, connector->name, + mode->hsync_end, mode->htotal); + mode->hsync_end = mode->htotal; + } + if (mode->vsync_end > mode->vtotal) { + drm_dbg_kms(dev, "[CONNECTOR:%d:%s] reducing vsync_end %d->%d\n", + connector->base.id, connector->name, + mode->vsync_end, mode->vtotal); + mode->vsync_end = mode->vtotal; + } drm_mode_do_interlace_quirk(mode, pt); diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c index 883d83bc0e3d5..e692770ef6d3c 100644 --- a/drivers/gpu/drm/drm_file.c +++ b/drivers/gpu/drm/drm_file.c @@ -160,7 +160,7 @@ struct drm_file *drm_file_alloc(struct drm_minor *minor) /* Get a unique identifier for fdinfo: */ file->client_id = atomic64_inc_return(&ident); - file->pid = get_pid(task_tgid(current)); + rcu_assign_pointer(file->pid, get_pid(task_tgid(current))); file->minor = minor; /* for compatibility root is always authenticated */ @@ -200,7 +200,7 @@ struct drm_file *drm_file_alloc(struct drm_minor *minor) drm_syncobj_release(file); if (drm_core_check_feature(dev, DRIVER_GEM)) drm_gem_release(dev, file); - put_pid(file->pid); + put_pid(rcu_access_pointer(file->pid)); kfree(file); return ERR_PTR(ret); @@ -291,7 +291,7 @@ void drm_file_free(struct drm_file *file) WARN_ON(!list_empty(&file->event_list)); - put_pid(file->pid); + put_pid(rcu_access_pointer(file->pid)); kfree(file); } @@ -505,6 +505,40 @@ int drm_release(struct inode *inode, struct file *filp) } EXPORT_SYMBOL(drm_release); +void drm_file_update_pid(struct drm_file *filp) +{ + struct drm_device *dev; + struct pid *pid, *old; + + /* + * Master nodes need to keep the original ownership in order for + * drm_master_check_perm to keep working correctly. (See comment in + * drm_auth.c.) + */ + if (filp->was_master) + return; + + pid = task_tgid(current); + + /* + * Quick unlocked check since the model is a single handover followed by + * exclusive repeated use. + */ + if (pid == rcu_access_pointer(filp->pid)) + return; + + dev = filp->minor->dev; + mutex_lock(&dev->filelist_mutex); + old = rcu_replace_pointer(filp->pid, pid, 1); + mutex_unlock(&dev->filelist_mutex); + + if (pid != old) { + get_pid(pid); + synchronize_rcu(); + put_pid(old); + } +} + /** * drm_release_noglobal - release method for DRM file * @inode: device inode diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c index f03ffbacfe9b4..77590b0f38fa3 100644 --- a/drivers/gpu/drm/drm_ioctl.c +++ b/drivers/gpu/drm/drm_ioctl.c @@ -776,6 +776,9 @@ long drm_ioctl_kernel(struct file *file, drm_ioctl_t *func, void *kdata, struct drm_device *dev = file_priv->minor->dev; int retcode; + /* Update drm_file owner if fd was passed along. */ + drm_file_update_pid(file_priv); + if (drm_dev_is_unplugged(dev)) return -ENODEV; diff --git a/drivers/gpu/drm/drm_lease.c b/drivers/gpu/drm/drm_lease.c index 150fe15550680..94375c6a54256 100644 --- a/drivers/gpu/drm/drm_lease.c +++ b/drivers/gpu/drm/drm_lease.c @@ -510,8 +510,8 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev, /* Handle leased objects, if any */ idr_init(&leases); if (object_count != 0) { - object_ids = memdup_user(u64_to_user_ptr(cl->object_ids), - array_size(object_count, sizeof(__u32))); + object_ids = memdup_array_user(u64_to_user_ptr(cl->object_ids), + object_count, sizeof(__u32)); if (IS_ERR(object_ids)) { ret = PTR_ERR(object_ids); idr_destroy(&leases); diff --git a/drivers/gpu/drm/gma500/psb_drv.h b/drivers/gpu/drm/gma500/psb_drv.h index f7f709df99b49..70d9adafa2333 100644 --- a/drivers/gpu/drm/gma500/psb_drv.h +++ b/drivers/gpu/drm/gma500/psb_drv.h @@ -424,6 +424,7 @@ struct drm_psb_private { uint32_t pipestat[PSB_NUM_PIPE]; spinlock_t irqmask_lock; + bool irq_enabled; /* Power */ bool pm_initialized; diff --git a/drivers/gpu/drm/gma500/psb_irq.c b/drivers/gpu/drm/gma500/psb_irq.c index 343c51250207d..7bbb79b0497d8 100644 --- a/drivers/gpu/drm/gma500/psb_irq.c +++ b/drivers/gpu/drm/gma500/psb_irq.c @@ -327,6 +327,8 @@ int gma_irq_install(struct drm_device *dev) gma_irq_postinstall(dev); + dev_priv->irq_enabled = true; + return 0; } @@ -337,6 +339,9 @@ void gma_irq_uninstall(struct drm_device *dev) unsigned long irqflags; unsigned int i; + if (!dev_priv->irq_enabled) + return; + spin_lock_irqsave(&dev_priv->irqmask_lock, irqflags); if (dev_priv->ops->hotplug_enable) diff --git a/drivers/gpu/drm/i915/display/g4x_dp.c b/drivers/gpu/drm/i915/display/g4x_dp.c index 4c7187f7913ea..e8ee0a08947e8 100644 --- a/drivers/gpu/drm/i915/display/g4x_dp.c +++ b/drivers/gpu/drm/i915/display/g4x_dp.c @@ -141,7 +141,7 @@ static void intel_dp_prepare(struct intel_encoder *encoder, intel_de_rmw(dev_priv, TRANS_DP_CTL(crtc->pipe), TRANS_DP_ENH_FRAMING, - drm_dp_enhanced_frame_cap(intel_dp->dpcd) ? + pipe_config->enhanced_framing ? TRANS_DP_ENH_FRAMING : 0); } else { if (IS_G4X(dev_priv) && pipe_config->limited_color_range) @@ -153,7 +153,7 @@ static void intel_dp_prepare(struct intel_encoder *encoder, intel_dp->DP |= DP_SYNC_VS_HIGH; intel_dp->DP |= DP_LINK_TRAIN_OFF; - if (drm_dp_enhanced_frame_cap(intel_dp->dpcd)) + if (pipe_config->enhanced_framing) intel_dp->DP |= DP_ENHANCED_FRAMING; if (IS_CHERRYVIEW(dev_priv)) @@ -351,6 +351,9 @@ static void intel_dp_get_config(struct intel_encoder *encoder, u32 trans_dp = intel_de_read(dev_priv, TRANS_DP_CTL(crtc->pipe)); + if (trans_dp & TRANS_DP_ENH_FRAMING) + pipe_config->enhanced_framing = true; + if (trans_dp & TRANS_DP_HSYNC_ACTIVE_HIGH) flags |= DRM_MODE_FLAG_PHSYNC; else @@ -361,6 +364,9 @@ static void intel_dp_get_config(struct intel_encoder *encoder, else flags |= DRM_MODE_FLAG_NVSYNC; } else { + if (tmp & DP_ENHANCED_FRAMING) + pipe_config->enhanced_framing = true; + if (tmp & DP_SYNC_HS_HIGH) flags |= DRM_MODE_FLAG_PHSYNC; else diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c index ad6488e9c2b2b..5b8efe8e735a9 100644 --- a/drivers/gpu/drm/i915/display/icl_dsi.c +++ b/drivers/gpu/drm/i915/display/icl_dsi.c @@ -1440,6 +1440,13 @@ static void gen11_dsi_post_disable(struct intel_atomic_state *state, static enum drm_mode_status gen11_dsi_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) { + struct drm_i915_private *i915 = to_i915(connector->dev); + enum drm_mode_status status; + + status = intel_cpu_transcoder_mode_valid(i915, mode); + if (status != MODE_OK) + return status; + /* FIXME: DSC? */ return intel_dsi_mode_valid(connector, mode); } diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c index 2fb030b1ff1de..f99cf8037bd68 100644 --- a/drivers/gpu/drm/i915/display/intel_cdclk.c +++ b/drivers/gpu/drm/i915/display/intel_cdclk.c @@ -2688,6 +2688,18 @@ static int intel_compute_min_cdclk(struct intel_cdclk_state *cdclk_state) for_each_pipe(dev_priv, pipe) min_cdclk = max(cdclk_state->min_cdclk[pipe], min_cdclk); + /* + * Avoid glk_force_audio_cdclk() causing excessive screen + * blinking when multiple pipes are active by making sure + * CDCLK frequency is always high enough for audio. With a + * single active pipe we can always change CDCLK frequency + * by changing the cd2x divider (see glk_cdclk_table[]) and + * thus a full modeset won't be needed then. + */ + if (IS_GEMINILAKE(dev_priv) && cdclk_state->active_pipes && + !is_power_of_2(cdclk_state->active_pipes)) + min_cdclk = max(2 * 96000, min_cdclk); + if (min_cdclk > dev_priv->display.cdclk.max_cdclk_freq) { drm_dbg_kms(&dev_priv->drm, "required cdclk (%d kHz) exceeds max (%d kHz)\n", diff --git a/drivers/gpu/drm/i915/display/intel_crt.c b/drivers/gpu/drm/i915/display/intel_crt.c index 8090747586877..4352f90177615 100644 --- a/drivers/gpu/drm/i915/display/intel_crt.c +++ b/drivers/gpu/drm/i915/display/intel_crt.c @@ -348,8 +348,13 @@ intel_crt_mode_valid(struct drm_connector *connector, struct drm_device *dev = connector->dev; struct drm_i915_private *dev_priv = to_i915(dev); int max_dotclk = dev_priv->max_dotclk_freq; + enum drm_mode_status status; int max_clock; + status = intel_cpu_transcoder_mode_valid(dev_priv, mode); + if (status != MODE_OK) + return status; + if (mode->flags & DRM_MODE_FLAG_DBLSCAN) return MODE_NO_DBLESCAN; @@ -451,6 +456,8 @@ static int hsw_crt_compute_config(struct intel_encoder *encoder, /* FDI must always be 2.7 GHz */ pipe_config->port_clock = 135000 * 2; + pipe_config->enhanced_framing = true; + adjusted_mode->crtc_clock = lpt_iclkip(pipe_config); return 0; diff --git a/drivers/gpu/drm/i915/display/intel_crtc_state_dump.c b/drivers/gpu/drm/i915/display/intel_crtc_state_dump.c index 8d4640d0fd346..66fe880af8f3f 100644 --- a/drivers/gpu/drm/i915/display/intel_crtc_state_dump.c +++ b/drivers/gpu/drm/i915/display/intel_crtc_state_dump.c @@ -258,6 +258,9 @@ void intel_crtc_state_dump(const struct intel_crtc_state *pipe_config, intel_dump_m_n_config(pipe_config, "dp m2_n2", pipe_config->lane_count, &pipe_config->dp_m2_n2); + drm_dbg_kms(&i915->drm, "fec: %s, enhanced framing: %s\n", + str_enabled_disabled(pipe_config->fec_enable), + str_enabled_disabled(pipe_config->enhanced_framing)); } drm_dbg_kms(&i915->drm, "framestart delay: %d, MSA timing delay: %d\n", diff --git a/drivers/gpu/drm/i915/display/intel_cx0_phy.c b/drivers/gpu/drm/i915/display/intel_cx0_phy.c index 80e4ec6ee4031..048e581fda16c 100644 --- a/drivers/gpu/drm/i915/display/intel_cx0_phy.c +++ b/drivers/gpu/drm/i915/display/intel_cx0_phy.c @@ -2420,7 +2420,8 @@ static void intel_program_port_clock_ctl(struct intel_encoder *encoder, val |= XELPDP_FORWARD_CLOCK_UNGATE; - if (is_hdmi_frl(crtc_state->port_clock)) + if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI) && + is_hdmi_frl(crtc_state->port_clock)) val |= XELPDP_DDI_CLOCK_SELECT(XELPDP_DDI_CLOCK_SELECT_DIV18CLK); else val |= XELPDP_DDI_CLOCK_SELECT(XELPDP_DDI_CLOCK_SELECT_MAXPCLK); diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c index 84bbf854337aa..c7e00f57cb7ab 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.c +++ b/drivers/gpu/drm/i915/display/intel_ddi.c @@ -3432,7 +3432,7 @@ static void mtl_ddi_prepare_link_retrain(struct intel_dp *intel_dp, dp_tp_ctl |= DP_TP_CTL_MODE_MST; } else { dp_tp_ctl |= DP_TP_CTL_MODE_SST; - if (drm_dp_enhanced_frame_cap(intel_dp->dpcd)) + if (crtc_state->enhanced_framing) dp_tp_ctl |= DP_TP_CTL_ENHANCED_FRAME_ENABLE; } intel_de_write(dev_priv, dp_tp_ctl_reg(encoder, crtc_state), dp_tp_ctl); @@ -3489,7 +3489,7 @@ static void intel_ddi_prepare_link_retrain(struct intel_dp *intel_dp, dp_tp_ctl |= DP_TP_CTL_MODE_MST; } else { dp_tp_ctl |= DP_TP_CTL_MODE_SST; - if (drm_dp_enhanced_frame_cap(intel_dp->dpcd)) + if (crtc_state->enhanced_framing) dp_tp_ctl |= DP_TP_CTL_ENHANCED_FRAME_ENABLE; } intel_de_write(dev_priv, dp_tp_ctl_reg(encoder, crtc_state), dp_tp_ctl); @@ -3724,17 +3724,14 @@ static void intel_ddi_read_func_ctl(struct intel_encoder *encoder, intel_cpu_transcoder_get_m2_n2(crtc, cpu_transcoder, &pipe_config->dp_m2_n2); - if (DISPLAY_VER(dev_priv) >= 11) { - i915_reg_t dp_tp_ctl = dp_tp_ctl_reg(encoder, pipe_config); + pipe_config->enhanced_framing = + intel_de_read(dev_priv, dp_tp_ctl_reg(encoder, pipe_config)) & + DP_TP_CTL_ENHANCED_FRAME_ENABLE; + if (DISPLAY_VER(dev_priv) >= 11) pipe_config->fec_enable = - intel_de_read(dev_priv, dp_tp_ctl) & DP_TP_CTL_FEC_ENABLE; - - drm_dbg_kms(&dev_priv->drm, - "[ENCODER:%d:%s] Fec status: %u\n", - encoder->base.base.id, encoder->base.name, - pipe_config->fec_enable); - } + intel_de_read(dev_priv, + dp_tp_ctl_reg(encoder, pipe_config)) & DP_TP_CTL_FEC_ENABLE; if (dig_port->lspcon.active && intel_dp_has_hdmi_sink(&dig_port->dp)) pipe_config->infoframes.enable |= @@ -3747,6 +3744,9 @@ static void intel_ddi_read_func_ctl(struct intel_encoder *encoder, if (!HAS_DP20(dev_priv)) { /* FDI */ pipe_config->output_types |= BIT(INTEL_OUTPUT_ANALOG); + pipe_config->enhanced_framing = + intel_de_read(dev_priv, dp_tp_ctl_reg(encoder, pipe_config)) & + DP_TP_CTL_ENHANCED_FRAME_ENABLE; break; } fallthrough; /* 128b/132b */ diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 763ab569d8f32..2e0daad23aa61 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -5255,6 +5255,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config, PIPE_CONF_CHECK_BOOL(hdmi_scrambling); PIPE_CONF_CHECK_BOOL(hdmi_high_tmds_clock_ratio); PIPE_CONF_CHECK_BOOL(has_infoframe); + PIPE_CONF_CHECK_BOOL(enhanced_framing); PIPE_CONF_CHECK_BOOL(fec_enable); PIPE_CONF_CHECK_BOOL_INCOMPLETE(has_audio); @@ -5976,6 +5977,17 @@ static int intel_async_flip_check_hw(struct intel_atomic_state *state, struct in return -EINVAL; } + /* + * FIXME: Bigjoiner+async flip is busted currently. + * Remove this check once the issues are fixed. + */ + if (new_crtc_state->bigjoiner_pipes) { + drm_dbg_kms(&i915->drm, + "[CRTC:%d:%s] async flip disallowed with bigjoiner\n", + crtc->base.base.id, crtc->base.name); + return -EINVAL; + } + for_each_oldnew_intel_plane_in_state(state, plane, old_plane_state, new_plane_state, i) { if (plane->pipe != crtc->pipe) @@ -7279,7 +7291,7 @@ int intel_atomic_commit(struct drm_device *dev, struct drm_atomic_state *_state, for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) intel_color_cleanup_commit(new_crtc_state); - drm_atomic_helper_cleanup_planes(dev, &state->base); + drm_atomic_helper_unprepare_planes(dev, &state->base); intel_runtime_pm_put(&dev_priv->runtime_pm, state->wakeref); return ret; } @@ -7660,6 +7672,16 @@ enum drm_mode_status intel_mode_valid(struct drm_device *dev, mode->vtotal > vtotal_max) return MODE_V_ILLEGAL; + return MODE_OK; +} + +enum drm_mode_status intel_cpu_transcoder_mode_valid(struct drm_i915_private *dev_priv, + const struct drm_display_mode *mode) +{ + /* + * Additional transcoder timing limits, + * excluding BXT/GLK DSI transcoders. + */ if (DISPLAY_VER(dev_priv) >= 5) { if (mode->hdisplay < 64 || mode->htotal - mode->hdisplay < 32) diff --git a/drivers/gpu/drm/i915/display/intel_display.h b/drivers/gpu/drm/i915/display/intel_display.h index 49ac8473b988b..13b0904d42e3d 100644 --- a/drivers/gpu/drm/i915/display/intel_display.h +++ b/drivers/gpu/drm/i915/display/intel_display.h @@ -405,6 +405,9 @@ enum drm_mode_status intel_mode_valid_max_plane_size(struct drm_i915_private *dev_priv, const struct drm_display_mode *mode, bool bigjoiner); +enum drm_mode_status +intel_cpu_transcoder_mode_valid(struct drm_i915_private *i915, + const struct drm_display_mode *mode); enum phy intel_port_to_phy(struct drm_i915_private *i915, enum port port); bool is_trans_port_sync_mode(const struct intel_crtc_state *state); bool is_trans_port_sync_master(const struct intel_crtc_state *state); diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h index 731f2ec04d5cd..7fc92b1474cc4 100644 --- a/drivers/gpu/drm/i915/display/intel_display_types.h +++ b/drivers/gpu/drm/i915/display/intel_display_types.h @@ -1362,6 +1362,8 @@ struct intel_crtc_state { u16 linetime; u16 ips_linetime; + bool enhanced_framing; + /* Forward Error correction State */ bool fec_enable; diff --git a/drivers/gpu/drm/i915/display/intel_dmc.c b/drivers/gpu/drm/i915/display/intel_dmc.c index 5f479f3828bbe..8751973b5730f 100644 --- a/drivers/gpu/drm/i915/display/intel_dmc.c +++ b/drivers/gpu/drm/i915/display/intel_dmc.c @@ -389,7 +389,7 @@ disable_all_flip_queue_events(struct drm_i915_private *i915) enum intel_dmc_id dmc_id; /* TODO: check if the following applies to all D13+ platforms. */ - if (!IS_DG2(i915) && !IS_TIGERLAKE(i915)) + if (!IS_TIGERLAKE(i915)) return; for_each_dmc_id(dmc_id) { @@ -493,6 +493,45 @@ void intel_dmc_disable_pipe(struct drm_i915_private *i915, enum pipe pipe) intel_de_rmw(i915, PIPEDMC_CONTROL(pipe), PIPEDMC_ENABLE, 0); } +static bool is_dmc_evt_ctl_reg(struct drm_i915_private *i915, + enum intel_dmc_id dmc_id, i915_reg_t reg) +{ + u32 offset = i915_mmio_reg_offset(reg); + u32 start = i915_mmio_reg_offset(DMC_EVT_CTL(i915, dmc_id, 0)); + u32 end = i915_mmio_reg_offset(DMC_EVT_CTL(i915, dmc_id, DMC_EVENT_HANDLER_COUNT_GEN12)); + + return offset >= start && offset < end; +} + +static bool disable_dmc_evt(struct drm_i915_private *i915, + enum intel_dmc_id dmc_id, + i915_reg_t reg, u32 data) +{ + if (!is_dmc_evt_ctl_reg(i915, dmc_id, reg)) + return false; + + /* keep all pipe DMC events disabled by default */ + if (dmc_id != DMC_FW_MAIN) + return true; + + return false; +} + +static u32 dmc_mmiodata(struct drm_i915_private *i915, + struct intel_dmc *dmc, + enum intel_dmc_id dmc_id, int i) +{ + if (disable_dmc_evt(i915, dmc_id, + dmc->dmc_info[dmc_id].mmioaddr[i], + dmc->dmc_info[dmc_id].mmiodata[i])) + return REG_FIELD_PREP(DMC_EVT_CTL_TYPE_MASK, + DMC_EVT_CTL_TYPE_EDGE_0_1) | + REG_FIELD_PREP(DMC_EVT_CTL_EVENT_ID_MASK, + DMC_EVT_CTL_EVENT_ID_FALSE); + else + return dmc->dmc_info[dmc_id].mmiodata[i]; +} + /** * intel_dmc_load_program() - write the firmware from memory to register. * @i915: i915 drm device. @@ -532,7 +571,7 @@ void intel_dmc_load_program(struct drm_i915_private *i915) for_each_dmc_id(dmc_id) { for (i = 0; i < dmc->dmc_info[dmc_id].mmio_count; i++) { intel_de_write(i915, dmc->dmc_info[dmc_id].mmioaddr[i], - dmc->dmc_info[dmc_id].mmiodata[i]); + dmc_mmiodata(i915, dmc, dmc_id, i)); } } diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index e0e4cb5292846..b4fb7ce39d06f 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -430,7 +430,7 @@ static int mtl_max_source_rate(struct intel_dp *intel_dp) enum phy phy = intel_port_to_phy(i915, dig_port->base.port); if (intel_is_c10phy(i915, phy)) - return intel_dp_is_edp(intel_dp) ? 675000 : 810000; + return 810000; return 2000000; } @@ -1127,6 +1127,10 @@ intel_dp_mode_valid(struct drm_connector *_connector, enum drm_mode_status status; bool dsc = false, bigjoiner = false; + status = intel_cpu_transcoder_mode_valid(dev_priv, mode); + if (status != MODE_OK) + return status; + if (mode->flags & DRM_MODE_FLAG_DBLCLK) return MODE_H_ILLEGAL; @@ -2308,6 +2312,9 @@ intel_dp_compute_config(struct intel_encoder *encoder, pipe_config->limited_color_range = intel_dp_limited_color_range(pipe_config, conn_state); + pipe_config->enhanced_framing = + drm_dp_enhanced_frame_cap(intel_dp->dpcd); + if (pipe_config->dsc.compression_enable) output_bpp = pipe_config->dsc.compressed_bpp; else @@ -5517,8 +5524,7 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp, * (eg. Acer Chromebook C710), so we'll check it only if multiple * ports are attempting to use the same AUX CH, according to VBT. */ - if (intel_bios_dp_has_shared_aux_ch(encoder->devdata) && - !intel_digital_port_connected(encoder)) { + if (intel_bios_dp_has_shared_aux_ch(encoder->devdata)) { /* * If this fails, presume the DPCD answer came * from some other port using the same AUX CH. @@ -5526,10 +5532,27 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp, * FIXME maybe cleaner to check this before the * DPCD read? Would need sort out the VDD handling... */ - drm_info(&dev_priv->drm, - "[ENCODER:%d:%s] HPD is down, disabling eDP\n", - encoder->base.base.id, encoder->base.name); - goto out_vdd_off; + if (!intel_digital_port_connected(encoder)) { + drm_info(&dev_priv->drm, + "[ENCODER:%d:%s] HPD is down, disabling eDP\n", + encoder->base.base.id, encoder->base.name); + goto out_vdd_off; + } + + /* + * Unfortunately even the HPD based detection fails on + * eg. Asus B360M-A (CFL+CNP), so as a last resort fall + * back to checking for a VGA branch device. Only do this + * on known affected platforms to minimize false positives. + */ + if (DISPLAY_VER(dev_priv) == 9 && drm_dp_is_branch(intel_dp->dpcd) && + (intel_dp->dpcd[DP_DOWNSTREAMPORT_PRESENT] & DP_DWN_STRM_PORT_TYPE_MASK) == + DP_DWN_STRM_PORT_TYPE_ANALOG) { + drm_info(&dev_priv->drm, + "[ENCODER:%d:%s] VGA converter detected, disabling eDP\n", + encoder->base.base.id, encoder->base.name); + goto out_vdd_off; + } } mutex_lock(&dev_priv->drm.mode_config.mutex); diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c index a263773f4d68a..a62bca622b0a1 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c +++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c @@ -650,19 +650,30 @@ intel_dp_update_link_bw_set(struct intel_dp *intel_dp, const struct intel_crtc_state *crtc_state, u8 link_bw, u8 rate_select) { - u8 link_config[2]; + u8 lane_count = crtc_state->lane_count; + + if (crtc_state->enhanced_framing) + lane_count |= DP_LANE_COUNT_ENHANCED_FRAME_EN; - /* Write the link configuration data */ - link_config[0] = link_bw; - link_config[1] = crtc_state->lane_count; - if (drm_dp_enhanced_frame_cap(intel_dp->dpcd)) - link_config[1] |= DP_LANE_COUNT_ENHANCED_FRAME_EN; - drm_dp_dpcd_write(&intel_dp->aux, DP_LINK_BW_SET, link_config, 2); - - /* eDP 1.4 rate select method. */ - if (!link_bw) - drm_dp_dpcd_write(&intel_dp->aux, DP_LINK_RATE_SET, - &rate_select, 1); + if (link_bw) { + /* DP and eDP v1.3 and earlier link bw set method. */ + u8 link_config[] = { link_bw, lane_count }; + + drm_dp_dpcd_write(&intel_dp->aux, DP_LINK_BW_SET, link_config, + ARRAY_SIZE(link_config)); + } else { + /* + * eDP v1.4 and later link rate set method. + * + * eDP v1.4x sinks shall ignore DP_LINK_RATE_SET if + * DP_LINK_BW_SET is set. Avoid writing DP_LINK_BW_SET. + * + * eDP v1.5 sinks allow choosing either, and the last choice + * shall be active. + */ + drm_dp_dpcd_writeb(&intel_dp->aux, DP_LANE_COUNT_SET, lane_count); + drm_dp_dpcd_writeb(&intel_dp->aux, DP_LINK_RATE_SET, rate_select); + } } /* diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c index e3f176a093d2f..77bd1313c808f 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c @@ -921,6 +921,10 @@ intel_dp_mst_mode_valid_ctx(struct drm_connector *connector, return 0; } + *status = intel_cpu_transcoder_mode_valid(dev_priv, mode); + if (*status != MODE_OK) + return 0; + if (mode->flags & DRM_MODE_FLAG_DBLSCAN) { *status = MODE_NO_DBLESCAN; return 0; @@ -955,6 +959,10 @@ intel_dp_mst_mode_valid_ctx(struct drm_connector *connector, if (intel_dp_need_bigjoiner(intel_dp, mode->hdisplay, target_clock)) { bigjoiner = true; max_dotclk *= 2; + + /* TODO: add support for bigjoiner */ + *status = MODE_CLOCK_HIGH; + return 0; } if (DISPLAY_VER(dev_priv) >= 10 && @@ -988,11 +996,15 @@ intel_dp_mst_mode_valid_ctx(struct drm_connector *connector, * Big joiner configuration needs DSC for TGL which is not true for * XE_LPD where uncompressed joiner is supported. */ - if (DISPLAY_VER(dev_priv) < 13 && bigjoiner && !dsc) - return MODE_CLOCK_HIGH; + if (DISPLAY_VER(dev_priv) < 13 && bigjoiner && !dsc) { + *status = MODE_CLOCK_HIGH; + return 0; + } - if (mode_rate > max_rate && !dsc) - return MODE_CLOCK_HIGH; + if (mode_rate > max_rate && !dsc) { + *status = MODE_CLOCK_HIGH; + return 0; + } *status = intel_mode_valid_max_plane_size(dev_priv, mode, false); return 0; diff --git a/drivers/gpu/drm/i915/display/intel_dvo.c b/drivers/gpu/drm/i915/display/intel_dvo.c index b386894c3a6db..d1cfa966d48da 100644 --- a/drivers/gpu/drm/i915/display/intel_dvo.c +++ b/drivers/gpu/drm/i915/display/intel_dvo.c @@ -217,11 +217,17 @@ intel_dvo_mode_valid(struct drm_connector *_connector, struct drm_display_mode *mode) { struct intel_connector *connector = to_intel_connector(_connector); + struct drm_i915_private *i915 = to_i915(connector->base.dev); struct intel_dvo *intel_dvo = intel_attached_dvo(connector); const struct drm_display_mode *fixed_mode = intel_panel_fixed_mode(connector, mode); int max_dotclk = to_i915(connector->base.dev)->max_dotclk_freq; int target_clock = mode->clock; + enum drm_mode_status status; + + status = intel_cpu_transcoder_mode_valid(i915, mode); + if (status != MODE_OK) + return status; if (mode->flags & DRM_MODE_FLAG_DBLSCAN) return MODE_NO_DBLESCAN; diff --git a/drivers/gpu/drm/i915/display/intel_fb.c b/drivers/gpu/drm/i915/display/intel_fb.c index 446bbf7986b6f..689b7c16d3007 100644 --- a/drivers/gpu/drm/i915/display/intel_fb.c +++ b/drivers/gpu/drm/i915/display/intel_fb.c @@ -1370,7 +1370,8 @@ plane_view_scanout_stride(const struct intel_framebuffer *fb, int color_plane, struct drm_i915_private *i915 = to_i915(fb->base.dev); unsigned int stride_tiles; - if (IS_ALDERLAKE_P(i915) || DISPLAY_VER(i915) >= 14) + if ((IS_ALDERLAKE_P(i915) || DISPLAY_VER(i915) >= 14) && + src_stride_tiles < dst_stride_tiles) stride_tiles = src_stride_tiles; else stride_tiles = dst_stride_tiles; @@ -1497,8 +1498,20 @@ static u32 calc_plane_remap_info(const struct intel_framebuffer *fb, int color_p size += remap_info->size; } else { - unsigned int dst_stride = plane_view_dst_stride_tiles(fb, color_plane, - remap_info->width); + unsigned int dst_stride; + + /* + * The hardware automagically calculates the CCS AUX surface + * stride from the main surface stride so can't really remap a + * smaller subset (unless we'd remap in whole AUX page units). + */ + if (intel_fb_needs_pot_stride_remap(fb) && + intel_fb_is_ccs_modifier(fb->base.modifier)) + dst_stride = remap_info->src_stride; + else + dst_stride = remap_info->width; + + dst_stride = plane_view_dst_stride_tiles(fb, color_plane, dst_stride); assign_chk_ovf(i915, remap_info->dst_stride, dst_stride); color_plane_info->mapping_stride = dst_stride * diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c index 94a7e1537f427..bc975918e0eb4 100644 --- a/drivers/gpu/drm/i915/display/intel_hdmi.c +++ b/drivers/gpu/drm/i915/display/intel_hdmi.c @@ -1986,6 +1986,10 @@ intel_hdmi_mode_valid(struct drm_connector *connector, bool ycbcr_420_only; enum intel_output_format sink_format; + status = intel_cpu_transcoder_mode_valid(dev_priv, mode); + if (status != MODE_OK) + return status; + if ((mode->flags & DRM_MODE_FLAG_3D_MASK) == DRM_MODE_FLAG_3D_FRAME_PACKING) clock *= 2; diff --git a/drivers/gpu/drm/i915/display/intel_lvds.c b/drivers/gpu/drm/i915/display/intel_lvds.c index 3ace56979b70e..dcb07d9a739d9 100644 --- a/drivers/gpu/drm/i915/display/intel_lvds.c +++ b/drivers/gpu/drm/i915/display/intel_lvds.c @@ -389,11 +389,16 @@ intel_lvds_mode_valid(struct drm_connector *_connector, struct drm_display_mode *mode) { struct intel_connector *connector = to_intel_connector(_connector); + struct drm_i915_private *i915 = to_i915(connector->base.dev); const struct drm_display_mode *fixed_mode = intel_panel_fixed_mode(connector, mode); int max_pixclk = to_i915(connector->base.dev)->max_dotclk_freq; enum drm_mode_status status; + status = intel_cpu_transcoder_mode_valid(i915, mode); + if (status != MODE_OK) + return status; + if (mode->flags & DRM_MODE_FLAG_DBLSCAN) return MODE_NO_DBLESCAN; diff --git a/drivers/gpu/drm/i915/display/intel_sdvo.c b/drivers/gpu/drm/i915/display/intel_sdvo.c index 7d25a64698e2f..0ce935efe5dfd 100644 --- a/drivers/gpu/drm/i915/display/intel_sdvo.c +++ b/drivers/gpu/drm/i915/display/intel_sdvo.c @@ -1906,13 +1906,19 @@ static enum drm_mode_status intel_sdvo_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) { + struct drm_i915_private *i915 = to_i915(connector->dev); struct intel_sdvo *intel_sdvo = intel_attached_sdvo(to_intel_connector(connector)); struct intel_sdvo_connector *intel_sdvo_connector = to_intel_sdvo_connector(connector); - int max_dotclk = to_i915(connector->dev)->max_dotclk_freq; bool has_hdmi_sink = intel_has_hdmi_sink(intel_sdvo_connector, connector->state); + int max_dotclk = i915->max_dotclk_freq; + enum drm_mode_status status; int clock = mode->clock; + status = intel_cpu_transcoder_mode_valid(i915, mode); + if (status != MODE_OK) + return status; + if (mode->flags & DRM_MODE_FLAG_DBLSCAN) return MODE_NO_DBLESCAN; diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c index 3ebf41859043e..cdf2455440bea 100644 --- a/drivers/gpu/drm/i915/display/intel_tc.c +++ b/drivers/gpu/drm/i915/display/intel_tc.c @@ -58,7 +58,7 @@ struct intel_tc_port { struct delayed_work link_reset_work; int link_refcount; bool legacy_port:1; - char port_name[8]; + const char *port_name; enum tc_port_mode mode; enum tc_port_mode init_mode; enum phy_fia phy_fia; @@ -1841,8 +1841,12 @@ int intel_tc_port_init(struct intel_digital_port *dig_port, bool is_legacy) else tc->phy_ops = &icl_tc_phy_ops; - snprintf(tc->port_name, sizeof(tc->port_name), - "%c/TC#%d", port_name(port), tc_port + 1); + tc->port_name = kasprintf(GFP_KERNEL, "%c/TC#%d", port_name(port), + tc_port + 1); + if (!tc->port_name) { + kfree(tc); + return -ENOMEM; + } mutex_init(&tc->lock); /* TODO: Combine the two works */ @@ -1863,6 +1867,7 @@ void intel_tc_port_cleanup(struct intel_digital_port *dig_port) { intel_tc_port_suspend(dig_port); + kfree(dig_port->tc->port_name); kfree(dig_port->tc); dig_port->tc = NULL; } diff --git a/drivers/gpu/drm/i915/display/intel_tv.c b/drivers/gpu/drm/i915/display/intel_tv.c index 36b479b46b600..d84a79491da23 100644 --- a/drivers/gpu/drm/i915/display/intel_tv.c +++ b/drivers/gpu/drm/i915/display/intel_tv.c @@ -958,8 +958,14 @@ static enum drm_mode_status intel_tv_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) { + struct drm_i915_private *i915 = to_i915(connector->dev); const struct tv_mode *tv_mode = intel_tv_mode_find(connector->state); - int max_dotclk = to_i915(connector->dev)->max_dotclk_freq; + int max_dotclk = i915->max_dotclk_freq; + enum drm_mode_status status; + + status = intel_cpu_transcoder_mode_valid(i915, mode); + if (status != MODE_OK) + return status; if (mode->flags & DRM_MODE_FLAG_DBLSCAN) return MODE_NO_DBLESCAN; diff --git a/drivers/gpu/drm/i915/display/skl_scaler.c b/drivers/gpu/drm/i915/display/skl_scaler.c index 1e7c97243fcf5..8a934bada6245 100644 --- a/drivers/gpu/drm/i915/display/skl_scaler.c +++ b/drivers/gpu/drm/i915/display/skl_scaler.c @@ -504,7 +504,6 @@ int intel_atomic_setup_scalers(struct drm_i915_private *dev_priv, { struct drm_plane *plane = NULL; struct intel_plane *intel_plane; - struct intel_plane_state *plane_state = NULL; struct intel_crtc_scaler_state *scaler_state = &crtc_state->scaler_state; struct drm_atomic_state *drm_state = crtc_state->uapi.state; @@ -536,6 +535,7 @@ int intel_atomic_setup_scalers(struct drm_i915_private *dev_priv, /* walkthrough scaler_users bits and start assigning scalers */ for (i = 0; i < sizeof(scaler_state->scaler_users) * 8; i++) { + struct intel_plane_state *plane_state = NULL; int *scaler_id; const char *name; int idx, ret; diff --git a/drivers/gpu/drm/i915/display/vlv_dsi.c b/drivers/gpu/drm/i915/display/vlv_dsi.c index a96e7d028c5c6..d778b88413b77 100644 --- a/drivers/gpu/drm/i915/display/vlv_dsi.c +++ b/drivers/gpu/drm/i915/display/vlv_dsi.c @@ -1540,9 +1540,25 @@ static const struct drm_encoder_funcs intel_dsi_funcs = { .destroy = intel_dsi_encoder_destroy, }; +static enum drm_mode_status vlv_dsi_mode_valid(struct drm_connector *connector, + struct drm_display_mode *mode) +{ + struct drm_i915_private *i915 = to_i915(connector->dev); + + if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)) { + enum drm_mode_status status; + + status = intel_cpu_transcoder_mode_valid(i915, mode); + if (status != MODE_OK) + return status; + } + + return intel_dsi_mode_valid(connector, mode); +} + static const struct drm_connector_helper_funcs intel_dsi_connector_helper_funcs = { .get_modes = intel_dsi_get_modes, - .mode_valid = intel_dsi_mode_valid, + .mode_valid = vlv_dsi_mode_valid, .atomic_check = intel_digital_connector_atomic_check, }; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c index 9a9ff84c90d7e..e38f06a6e56eb 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c @@ -844,6 +844,7 @@ static int set_proto_ctx_sseu(struct drm_i915_file_private *fpriv, if (idx >= pc->num_user_engines) return -EINVAL; + idx = array_index_nospec(idx, pc->num_user_engines); pe = &pc->user_engines[idx]; /* Only render engine supports RPCS configuration. */ diff --git a/drivers/gpu/drm/i915/gt/intel_engine_user.c b/drivers/gpu/drm/i915/gt/intel_engine_user.c index dcedff41a825f..d304e0a948f0d 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_user.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_user.c @@ -42,12 +42,15 @@ void intel_engine_add_user(struct intel_engine_cs *engine) (struct llist_head *)&engine->i915->uabi_engines); } -static const u8 uabi_classes[] = { +#define I915_NO_UABI_CLASS ((u16)(-1)) + +static const u16 uabi_classes[] = { [RENDER_CLASS] = I915_ENGINE_CLASS_RENDER, [COPY_ENGINE_CLASS] = I915_ENGINE_CLASS_COPY, [VIDEO_DECODE_CLASS] = I915_ENGINE_CLASS_VIDEO, [VIDEO_ENHANCEMENT_CLASS] = I915_ENGINE_CLASS_VIDEO_ENHANCE, [COMPUTE_CLASS] = I915_ENGINE_CLASS_COMPUTE, + [OTHER_CLASS] = I915_NO_UABI_CLASS, /* Not exposed to users, no uabi class. */ }; static int engine_cmp(void *priv, const struct list_head *A, @@ -202,6 +205,7 @@ static void engine_rename(struct intel_engine_cs *engine, const char *name, u16 void intel_engines_driver_register(struct drm_i915_private *i915) { + u16 name_instance, other_instance = 0; struct legacy_ring ring = {}; struct list_head *it, *next; struct rb_node **p, *prev; @@ -219,27 +223,28 @@ void intel_engines_driver_register(struct drm_i915_private *i915) if (intel_gt_has_unrecoverable_error(engine->gt)) continue; /* ignore incomplete engines */ - /* - * We don't want to expose the GSC engine to the users, but we - * still rename it so it is easier to identify in the debug logs - */ - if (engine->id == GSC0) { - engine_rename(engine, "gsc", 0); - continue; - } - GEM_BUG_ON(engine->class >= ARRAY_SIZE(uabi_classes)); engine->uabi_class = uabi_classes[engine->class]; + if (engine->uabi_class == I915_NO_UABI_CLASS) { + name_instance = other_instance++; + } else { + GEM_BUG_ON(engine->uabi_class >= + ARRAY_SIZE(i915->engine_uabi_class_count)); + name_instance = + i915->engine_uabi_class_count[engine->uabi_class]++; + } + engine->uabi_instance = name_instance; - GEM_BUG_ON(engine->uabi_class >= - ARRAY_SIZE(i915->engine_uabi_class_count)); - engine->uabi_instance = - i915->engine_uabi_class_count[engine->uabi_class]++; - - /* Replace the internal name with the final user facing name */ + /* + * Replace the internal name with the final user and log facing + * name. + */ engine_rename(engine, intel_engine_class_repr(engine->class), - engine->uabi_instance); + name_instance); + + if (engine->uabi_class == I915_NO_UABI_CLASS) + continue; rb_link_node(&engine->uabi_node, prev, p); rb_insert_color(&engine->uabi_node, &i915->uabi_engines); diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c index da21f2786b5d7..b20d8fe8aa95d 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c @@ -190,6 +190,21 @@ void gen6_ggtt_invalidate(struct i915_ggtt *ggtt) spin_unlock_irq(&uncore->lock); } +static bool needs_wc_ggtt_mapping(struct drm_i915_private *i915) +{ + /* + * On BXT+/ICL+ writes larger than 64 bit to the GTT pagetable range + * will be dropped. For WC mappings in general we have 64 byte burst + * writes when the WC buffer is flushed, so we can't use it, but have to + * resort to an uncached mapping. The WC issue is easily caught by the + * readback check when writing GTT PTE entries. + */ + if (!IS_GEN9_LP(i915) && GRAPHICS_VER(i915) < 11) + return true; + + return false; +} + static void gen8_ggtt_invalidate(struct i915_ggtt *ggtt) { struct intel_uncore *uncore = ggtt->vm.gt->uncore; @@ -197,8 +212,12 @@ static void gen8_ggtt_invalidate(struct i915_ggtt *ggtt) /* * Note that as an uncached mmio write, this will flush the * WCB of the writes into the GGTT before it triggers the invalidate. + * + * Only perform this when GGTT is mapped as WC, see ggtt_probe_common(). */ - intel_uncore_write_fw(uncore, GFX_FLSH_CNTL_GEN6, GFX_FLSH_CNTL_EN); + if (needs_wc_ggtt_mapping(ggtt->vm.i915)) + intel_uncore_write_fw(uncore, GFX_FLSH_CNTL_GEN6, + GFX_FLSH_CNTL_EN); } static void guc_ggtt_invalidate(struct i915_ggtt *ggtt) @@ -902,17 +921,11 @@ static int ggtt_probe_common(struct i915_ggtt *ggtt, u64 size) GEM_WARN_ON(pci_resource_len(pdev, GEN4_GTTMMADR_BAR) != gen6_gttmmadr_size(i915)); phys_addr = pci_resource_start(pdev, GEN4_GTTMMADR_BAR) + gen6_gttadr_offset(i915); - /* - * On BXT+/ICL+ writes larger than 64 bit to the GTT pagetable range - * will be dropped. For WC mappings in general we have 64 byte burst - * writes when the WC buffer is flushed, so we can't use it, but have to - * resort to an uncached mapping. The WC issue is easily caught by the - * readback check when writing GTT PTE entries. - */ - if (IS_GEN9_LP(i915) || GRAPHICS_VER(i915) >= 11) - ggtt->gsm = ioremap(phys_addr, size); - else + if (needs_wc_ggtt_mapping(i915)) ggtt->gsm = ioremap_wc(phys_addr, size); + else + ggtt->gsm = ioremap(phys_addr, size); + if (!ggtt->gsm) { drm_err(&i915->drm, "Failed to map the ggtt page table\n"); return -ENOMEM; diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c index 449f0b7fc8434..95631e8f39e7b 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.c +++ b/drivers/gpu/drm/i915/gt/intel_gt.c @@ -967,8 +967,6 @@ int intel_gt_probe_all(struct drm_i915_private *i915) err: i915_probe_error(i915, "Failed to initialize %s! (%d)\n", gtdef->name, ret); - intel_gt_release_all(i915); - return ret; } @@ -987,15 +985,6 @@ int intel_gt_tiles_init(struct drm_i915_private *i915) return 0; } -void intel_gt_release_all(struct drm_i915_private *i915) -{ - struct intel_gt *gt; - unsigned int id; - - for_each_gt(gt, i915, id) - i915->gt[id] = NULL; -} - void intel_gt_info_print(const struct intel_gt_info *info, struct drm_printer *p) { diff --git a/drivers/gpu/drm/i915/gt/intel_rc6.c b/drivers/gpu/drm/i915/gt/intel_rc6.c index 58bb1c55294c9..ccdc1afbf11b5 100644 --- a/drivers/gpu/drm/i915/gt/intel_rc6.c +++ b/drivers/gpu/drm/i915/gt/intel_rc6.c @@ -584,19 +584,23 @@ static void __intel_rc6_disable(struct intel_rc6 *rc6) static void rc6_res_reg_init(struct intel_rc6 *rc6) { - memset(rc6->res_reg, INVALID_MMIO_REG.reg, sizeof(rc6->res_reg)); + i915_reg_t res_reg[INTEL_RC6_RES_MAX] = { + [0 ... INTEL_RC6_RES_MAX - 1] = INVALID_MMIO_REG, + }; switch (rc6_to_gt(rc6)->type) { case GT_MEDIA: - rc6->res_reg[INTEL_RC6_RES_RC6] = MTL_MEDIA_MC6; + res_reg[INTEL_RC6_RES_RC6] = MTL_MEDIA_MC6; break; default: - rc6->res_reg[INTEL_RC6_RES_RC6_LOCKED] = GEN6_GT_GFX_RC6_LOCKED; - rc6->res_reg[INTEL_RC6_RES_RC6] = GEN6_GT_GFX_RC6; - rc6->res_reg[INTEL_RC6_RES_RC6p] = GEN6_GT_GFX_RC6p; - rc6->res_reg[INTEL_RC6_RES_RC6pp] = GEN6_GT_GFX_RC6pp; + res_reg[INTEL_RC6_RES_RC6_LOCKED] = GEN6_GT_GFX_RC6_LOCKED; + res_reg[INTEL_RC6_RES_RC6] = GEN6_GT_GFX_RC6; + res_reg[INTEL_RC6_RES_RC6p] = GEN6_GT_GFX_RC6p; + res_reg[INTEL_RC6_RES_RC6pp] = GEN6_GT_GFX_RC6pp; break; } + + memcpy(rc6->res_reg, res_reg, sizeof(res_reg)); } void intel_rc6_init(struct intel_rc6 *rc6) diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c index cc6bd21a3e51f..5fa57a34cf4bb 100644 --- a/drivers/gpu/drm/i915/gt/intel_reset.c +++ b/drivers/gpu/drm/i915/gt/intel_reset.c @@ -1297,7 +1297,7 @@ int __intel_engine_reset_bh(struct intel_engine_cs *engine, const char *msg) if (msg) drm_notice(&engine->i915->drm, "Resetting %s for %s\n", engine->name, msg); - atomic_inc(&engine->i915->gpu_error.reset_engine_count[engine->uabi_class]); + i915_increase_reset_engine_count(&engine->i915->gpu_error, engine); ret = intel_gt_reset_engine(engine); if (ret) { diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index dc7b40e06e38a..836e4d9d65ef6 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -4774,7 +4774,8 @@ static void capture_error_state(struct intel_guc *guc, if (match) { intel_engine_set_hung_context(e, ce); engine_mask |= e->mask; - atomic_inc(&i915->gpu_error.reset_engine_count[e->uabi_class]); + i915_increase_reset_engine_count(&i915->gpu_error, + e); } } @@ -4786,7 +4787,7 @@ static void capture_error_state(struct intel_guc *guc, } else { intel_engine_set_hung_context(ce->engine, ce); engine_mask = ce->engine->mask; - atomic_inc(&i915->gpu_error.reset_engine_count[ce->engine->uabi_class]); + i915_increase_reset_engine_count(&i915->gpu_error, ce->engine); } with_intel_runtime_pm(&i915->runtime_pm, wakeref) diff --git a/drivers/gpu/drm/i915/i915_driver.c b/drivers/gpu/drm/i915/i915_driver.c index ec4d26b3c17cc..8dc5f85b7747b 100644 --- a/drivers/gpu/drm/i915/i915_driver.c +++ b/drivers/gpu/drm/i915/i915_driver.c @@ -777,7 +777,7 @@ int i915_driver_probe(struct pci_dev *pdev, const struct pci_device_id *ent) ret = i915_driver_mmio_probe(i915); if (ret < 0) - goto out_tiles_cleanup; + goto out_runtime_pm_put; ret = i915_driver_hw_probe(i915); if (ret < 0) @@ -837,8 +837,6 @@ int i915_driver_probe(struct pci_dev *pdev, const struct pci_device_id *ent) i915_ggtt_driver_late_release(i915); out_cleanup_mmio: i915_driver_mmio_release(i915); -out_tiles_cleanup: - intel_gt_release_all(i915); out_runtime_pm_put: enable_rpm_wakeref_asserts(&i915->runtime_pm); i915_driver_late_release(i915); diff --git a/drivers/gpu/drm/i915/i915_gpu_error.h b/drivers/gpu/drm/i915/i915_gpu_error.h index 9f5971f5e9801..48f6c00402c47 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.h +++ b/drivers/gpu/drm/i915/i915_gpu_error.h @@ -16,6 +16,7 @@ #include "display/intel_display_device.h" #include "gt/intel_engine.h" +#include "gt/intel_engine_types.h" #include "gt/intel_gt_types.h" #include "gt/uc/intel_uc_fw.h" @@ -232,7 +233,7 @@ struct i915_gpu_error { atomic_t reset_count; /** Number of times an engine has been reset */ - atomic_t reset_engine_count[I915_NUM_ENGINES]; + atomic_t reset_engine_count[MAX_ENGINE_CLASS]; }; struct drm_i915_error_state_buf { @@ -255,7 +256,14 @@ static inline u32 i915_reset_count(struct i915_gpu_error *error) static inline u32 i915_reset_engine_count(struct i915_gpu_error *error, const struct intel_engine_cs *engine) { - return atomic_read(&error->reset_engine_count[engine->uabi_class]); + return atomic_read(&error->reset_engine_count[engine->class]); +} + +static inline void +i915_increase_reset_engine_count(struct i915_gpu_error *error, + const struct intel_engine_cs *engine) +{ + atomic_inc(&error->reset_engine_count[engine->class]); } #define CORE_DUMP_FLAG_NONE 0x0 diff --git a/drivers/gpu/drm/i915/i915_hwmon.c b/drivers/gpu/drm/i915/i915_hwmon.c index 975da8e7f2a9f..8c3f443c8347e 100644 --- a/drivers/gpu/drm/i915/i915_hwmon.c +++ b/drivers/gpu/drm/i915/i915_hwmon.c @@ -175,7 +175,7 @@ hwm_power1_max_interval_show(struct device *dev, struct device_attribute *attr, * tau4 = (4 | x) << y * but add 2 when doing the final right shift to account for units */ - tau4 = ((1 << x_w) | x) << y; + tau4 = (u64)((1 << x_w) | x) << y; /* val in hwmon interface units (millisec) */ out = mul_u64_u32_shr(tau4, SF_TIME, hwmon->scl_shift_time + x_w); @@ -211,7 +211,7 @@ hwm_power1_max_interval_store(struct device *dev, r = FIELD_PREP(PKG_MAX_WIN, PKG_MAX_WIN_DEFAULT); x = REG_FIELD_GET(PKG_MAX_WIN_X, r); y = REG_FIELD_GET(PKG_MAX_WIN_Y, r); - tau4 = ((1 << x_w) | x) << y; + tau4 = (u64)((1 << x_w) | x) << y; max_win = mul_u64_u32_shr(tau4, SF_TIME, hwmon->scl_shift_time + x_w); if (val > max_win) diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 59e1e21df2710..109135fcfca28 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -4286,11 +4286,8 @@ int i915_perf_open_ioctl(struct drm_device *dev, void *data, u32 known_open_flags; int ret; - if (!perf->i915) { - drm_dbg(&perf->i915->drm, - "i915 perf interface not available for this system\n"); + if (!perf->i915) return -ENOTSUPP; - } known_open_flags = I915_PERF_FLAG_FD_CLOEXEC | I915_PERF_FLAG_FD_NONBLOCK | @@ -4666,11 +4663,8 @@ int i915_perf_add_config_ioctl(struct drm_device *dev, void *data, struct i915_oa_reg *regs; int err, id; - if (!perf->i915) { - drm_dbg(&perf->i915->drm, - "i915 perf interface not available for this system\n"); + if (!perf->i915) return -ENOTSUPP; - } if (!perf->metrics_kobj) { drm_dbg(&perf->i915->drm, @@ -4832,11 +4826,8 @@ int i915_perf_remove_config_ioctl(struct drm_device *dev, void *data, struct i915_oa_config *oa_config; int ret; - if (!perf->i915) { - drm_dbg(&perf->i915->drm, - "i915 perf interface not available for this system\n"); + if (!perf->i915) return -ENOTSUPP; - } if (i915_perf_stream_paranoid && !perfmon_capable()) { drm_dbg(&perf->i915->drm, diff --git a/drivers/gpu/drm/i915/selftests/igt_live_test.c b/drivers/gpu/drm/i915/selftests/igt_live_test.c index 4ddc6d902752a..7d41874a49c58 100644 --- a/drivers/gpu/drm/i915/selftests/igt_live_test.c +++ b/drivers/gpu/drm/i915/selftests/igt_live_test.c @@ -37,8 +37,9 @@ int igt_live_test_begin(struct igt_live_test *t, } for_each_engine(engine, gt, id) - t->reset_engine[id] = - i915_reset_engine_count(&i915->gpu_error, engine); + t->reset_engine[i][id] = + i915_reset_engine_count(&i915->gpu_error, + engine); } t->reset_global = i915_reset_count(&i915->gpu_error); @@ -66,14 +67,14 @@ int igt_live_test_end(struct igt_live_test *t) for_each_gt(gt, i915, i) { for_each_engine(engine, gt, id) { - if (t->reset_engine[id] == + if (t->reset_engine[i][id] == i915_reset_engine_count(&i915->gpu_error, engine)) continue; gt_err(gt, "%s(%s): engine '%s' was reset %d times!\n", t->func, t->name, engine->name, i915_reset_engine_count(&i915->gpu_error, engine) - - t->reset_engine[id]); + t->reset_engine[i][id]); return -EIO; } } diff --git a/drivers/gpu/drm/i915/selftests/igt_live_test.h b/drivers/gpu/drm/i915/selftests/igt_live_test.h index 36ed42736c521..83e3ad430922f 100644 --- a/drivers/gpu/drm/i915/selftests/igt_live_test.h +++ b/drivers/gpu/drm/i915/selftests/igt_live_test.h @@ -7,6 +7,7 @@ #ifndef IGT_LIVE_TEST_H #define IGT_LIVE_TEST_H +#include "gt/intel_gt_defines.h" /* for I915_MAX_GT */ #include "gt/intel_engine.h" /* for I915_NUM_ENGINES */ struct drm_i915_private; @@ -17,7 +18,7 @@ struct igt_live_test { const char *name; unsigned int reset_global; - unsigned int reset_engine[I915_NUM_ENGINES]; + unsigned int reset_engine[I915_MAX_GT][I915_NUM_ENGINES]; }; /* diff --git a/drivers/gpu/drm/mediatek/mtk_dp.c b/drivers/gpu/drm/mediatek/mtk_dp.c index 2cb47f6637568..0e285df6577ea 100644 --- a/drivers/gpu/drm/mediatek/mtk_dp.c +++ b/drivers/gpu/drm/mediatek/mtk_dp.c @@ -2034,7 +2034,6 @@ static struct edid *mtk_dp_get_edid(struct drm_bridge *bridge, bool enabled = mtk_dp->enabled; struct edid *new_edid = NULL; struct mtk_dp_audio_cfg *audio_caps = &mtk_dp->info.audio_cur_cfg; - struct cea_sad *sads; if (!enabled) { drm_atomic_bridge_chain_pre_enable(bridge, connector->state->state); @@ -2049,11 +2048,16 @@ static struct edid *mtk_dp_get_edid(struct drm_bridge *bridge, */ if (mtk_dp_parse_capabilities(mtk_dp)) { drm_err(mtk_dp->drm_dev, "Can't parse capabilities\n"); + kfree(new_edid); new_edid = NULL; } if (new_edid) { + struct cea_sad *sads; + audio_caps->sad_count = drm_edid_to_sad(new_edid, &sads); + kfree(sads); + audio_caps->detect_monitor = drm_detect_monitor_audio(new_edid); } diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c index 0a511d7688a3a..80e34b39a6b11 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c @@ -747,6 +747,7 @@ static void mtk_drm_crtc_atomic_begin(struct drm_crtc *crtc, crtc); struct mtk_crtc_state *mtk_crtc_state = to_mtk_crtc_state(crtc_state); struct mtk_drm_crtc *mtk_crtc = to_mtk_crtc(crtc); + unsigned long flags; if (mtk_crtc->event && mtk_crtc_state->base.event) DRM_ERROR("new event while there is still a pending event\n"); @@ -754,7 +755,11 @@ static void mtk_drm_crtc_atomic_begin(struct drm_crtc *crtc, if (mtk_crtc_state->base.event) { mtk_crtc_state->base.event->pipe = drm_crtc_index(crtc); WARN_ON(drm_crtc_vblank_get(crtc) != 0); + + spin_lock_irqsave(&crtc->dev->event_lock, flags); mtk_crtc->event = mtk_crtc_state->base.event; + spin_unlock_irqrestore(&crtc->dev->event_lock, flags); + mtk_crtc_state->base.event = NULL; } } @@ -880,7 +885,14 @@ static int mtk_drm_crtc_init_comp_planes(struct drm_device *drm_dev, struct device *mtk_drm_crtc_dma_dev_get(struct drm_crtc *crtc) { - struct mtk_drm_crtc *mtk_crtc = to_mtk_crtc(crtc); + struct mtk_drm_crtc *mtk_crtc = NULL; + + if (!crtc) + return NULL; + + mtk_crtc = to_mtk_crtc(crtc); + if (!mtk_crtc) + return NULL; return mtk_crtc->dma_dev; } diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c index 2d6a979afe8f9..cdd506c803733 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c @@ -421,6 +421,7 @@ static int mtk_drm_kms_init(struct drm_device *drm) struct mtk_drm_private *private = drm->dev_private; struct mtk_drm_private *priv_n; struct device *dma_dev = NULL; + struct drm_crtc *crtc; int ret, i, j; if (drm_firmware_drivers_only()) @@ -495,7 +496,9 @@ static int mtk_drm_kms_init(struct drm_device *drm) } /* Use OVL device for all DMA memory allocations */ - dma_dev = mtk_drm_crtc_dma_dev_get(drm_crtc_from_index(drm, 0)); + crtc = drm_crtc_from_index(drm, 0); + if (crtc) + dma_dev = mtk_drm_crtc_dma_dev_get(crtc); if (!dma_dev) { ret = -ENODEV; dev_err(drm->dev, "Need at least one OVL device\n"); diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h index 58f5e25679b15..ff9adb8000acd 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h @@ -419,6 +419,7 @@ static const struct dpu_perf_cfg sc8280xp_perf_data = { .min_llcc_ib = 0, .min_dram_ib = 800000, .danger_lut_tbl = {0xf, 0xffff, 0x0}, + .safe_lut_tbl = {0xfe00, 0xfe00, 0xffff}, .qos_lut_tbl = { {.nentry = ARRAY_SIZE(sc8180x_qos_linear), .entries = sc8180x_qos_linear diff --git a/drivers/gpu/drm/msm/dp/dp_panel.c b/drivers/gpu/drm/msm/dp/dp_panel.c index 42d52510ffd4a..86a8e06c7a60f 100644 --- a/drivers/gpu/drm/msm/dp/dp_panel.c +++ b/drivers/gpu/drm/msm/dp/dp_panel.c @@ -289,26 +289,9 @@ int dp_panel_get_modes(struct dp_panel *dp_panel, static u8 dp_panel_get_edid_checksum(struct edid *edid) { - struct edid *last_block; - u8 *raw_edid; - bool is_edid_corrupt = false; + edid += edid->extensions; - if (!edid) { - DRM_ERROR("invalid edid input\n"); - return 0; - } - - raw_edid = (u8 *)edid; - raw_edid += (edid->extensions * EDID_LENGTH); - last_block = (struct edid *)raw_edid; - - /* block type extension */ - drm_edid_block_valid(raw_edid, 1, false, &is_edid_corrupt); - if (!is_edid_corrupt) - return last_block->checksum; - - DRM_ERROR("Invalid block, no checksum\n"); - return 0; + return edid->checksum; } void dp_panel_handle_sink_request(struct dp_panel *dp_panel) diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c index 3b1ed02f644d2..89a6344bc8653 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c @@ -918,7 +918,7 @@ static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy, if ((phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V5_2)) { if (phy->cphy_mode) { vreg_ctrl_0 = 0x45; - vreg_ctrl_1 = 0x45; + vreg_ctrl_1 = 0x41; glbl_rescode_top_ctrl = 0x00; glbl_rescode_bot_ctrl = 0x00; } else { diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index 4e7c9c353c511..617162aac060f 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -2310,7 +2310,7 @@ nv50_disp_atomic_commit(struct drm_device *dev, err_cleanup: if (ret) - drm_atomic_helper_cleanup_planes(dev, state); + drm_atomic_helper_unprepare_planes(dev, state); done: pm_runtime_put_autosuspend(dev->dev); return ret; diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/event.h b/drivers/gpu/drm/nouveau/include/nvkm/core/event.h index 82b267c111470..460459af272d6 100644 --- a/drivers/gpu/drm/nouveau/include/nvkm/core/event.h +++ b/drivers/gpu/drm/nouveau/include/nvkm/core/event.h @@ -14,7 +14,7 @@ struct nvkm_event { int index_nr; spinlock_t refs_lock; - spinlock_t list_lock; + rwlock_t list_lock; int *refs; struct list_head ntfy; @@ -38,7 +38,7 @@ nvkm_event_init(const struct nvkm_event_func *func, struct nvkm_subdev *subdev, int types_nr, int index_nr, struct nvkm_event *event) { spin_lock_init(&event->refs_lock); - spin_lock_init(&event->list_lock); + rwlock_init(&event->list_lock); return __nvkm_event_init(func, subdev, types_nr, index_nr, event); } diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 0f3bd187ede67..280d1d9a559ba 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -318,8 +318,9 @@ nouveau_bo_alloc(struct nouveau_cli *cli, u64 *size, int *align, u32 domain, (!vmm->page[i].host || vmm->page[i].shift > PAGE_SHIFT)) continue; - if (pi < 0) - pi = i; + /* pick the last one as it will be smallest. */ + pi = i; + /* Stop once the buffer is larger than the current page size. */ if (*size >= 1ULL << vmm->page[i].shift) break; diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index 4396f501b16a3..50589f982d1a4 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -1133,7 +1133,10 @@ nouveau_drm_open(struct drm_device *dev, struct drm_file *fpriv) } get_task_comm(tmpname, current); - snprintf(name, sizeof(name), "%s[%d]", tmpname, pid_nr(fpriv->pid)); + rcu_read_lock(); + snprintf(name, sizeof(name), "%s[%d]", + tmpname, pid_nr(rcu_dereference(fpriv->pid))); + rcu_read_unlock(); if (!(cli = kzalloc(sizeof(*cli), GFP_KERNEL))) { ret = -ENOMEM; diff --git a/drivers/gpu/drm/nouveau/nvkm/core/event.c b/drivers/gpu/drm/nouveau/nvkm/core/event.c index a6c877135598f..61fed7792e415 100644 --- a/drivers/gpu/drm/nouveau/nvkm/core/event.c +++ b/drivers/gpu/drm/nouveau/nvkm/core/event.c @@ -81,17 +81,17 @@ nvkm_event_ntfy_state(struct nvkm_event_ntfy *ntfy) static void nvkm_event_ntfy_remove(struct nvkm_event_ntfy *ntfy) { - spin_lock_irq(&ntfy->event->list_lock); + write_lock_irq(&ntfy->event->list_lock); list_del_init(&ntfy->head); - spin_unlock_irq(&ntfy->event->list_lock); + write_unlock_irq(&ntfy->event->list_lock); } static void nvkm_event_ntfy_insert(struct nvkm_event_ntfy *ntfy) { - spin_lock_irq(&ntfy->event->list_lock); + write_lock_irq(&ntfy->event->list_lock); list_add_tail(&ntfy->head, &ntfy->event->ntfy); - spin_unlock_irq(&ntfy->event->list_lock); + write_unlock_irq(&ntfy->event->list_lock); } static void @@ -176,7 +176,7 @@ nvkm_event_ntfy(struct nvkm_event *event, int id, u32 bits) return; nvkm_trace(event->subdev, "event: ntfy %08x on %d\n", bits, id); - spin_lock_irqsave(&event->list_lock, flags); + read_lock_irqsave(&event->list_lock, flags); list_for_each_entry_safe(ntfy, ntmp, &event->ntfy, head) { if (ntfy->id == id && ntfy->bits & bits) { @@ -185,7 +185,7 @@ nvkm_event_ntfy(struct nvkm_event *event, int id, u32 bits) } } - spin_unlock_irqrestore(&event->list_lock, flags); + read_unlock_irqrestore(&event->list_lock, flags); } void diff --git a/drivers/gpu/drm/panel/panel-arm-versatile.c b/drivers/gpu/drm/panel/panel-arm-versatile.c index abb0788843c60..503ecea72c5ea 100644 --- a/drivers/gpu/drm/panel/panel-arm-versatile.c +++ b/drivers/gpu/drm/panel/panel-arm-versatile.c @@ -267,6 +267,8 @@ static int versatile_panel_get_modes(struct drm_panel *panel, connector->display_info.bus_flags = vpanel->panel_type->bus_flags; mode = drm_mode_duplicate(connector->dev, &vpanel->panel_type->mode); + if (!mode) + return -ENOMEM; drm_mode_set_name(mode); mode->type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED; diff --git a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c index c9087f474cbc5..29e63cdfb8954 100644 --- a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c +++ b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c @@ -2049,6 +2049,7 @@ static const struct panel_desc auo_b101uan08_3_desc = { .mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_SYNC_PULSE | MIPI_DSI_MODE_LPM, .init_cmds = auo_b101uan08_3_init_cmd, + .lp11_before_reset = true, }; static const struct drm_display_mode boe_tv105wum_nw0_default_mode = { @@ -2103,14 +2104,15 @@ static const struct panel_desc starry_qfh032011_53g_desc = { .mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_SYNC_PULSE | MIPI_DSI_MODE_LPM, .init_cmds = starry_qfh032011_53g_init_cmd, + .lp11_before_reset = true, }; static const struct drm_display_mode starry_himax83102_j02_default_mode = { - .clock = 161600, + .clock = 162850, .hdisplay = 1200, - .hsync_start = 1200 + 40, - .hsync_end = 1200 + 40 + 20, - .htotal = 1200 + 40 + 20 + 40, + .hsync_start = 1200 + 50, + .hsync_end = 1200 + 50 + 20, + .htotal = 1200 + 50 + 20 + 50, .vdisplay = 1920, .vsync_start = 1920 + 116, .vsync_end = 1920 + 116 + 8, diff --git a/drivers/gpu/drm/panel/panel-novatek-nt36523.c b/drivers/gpu/drm/panel/panel-novatek-nt36523.c index 9632b9e95b715..c4a804c5d6aac 100644 --- a/drivers/gpu/drm/panel/panel-novatek-nt36523.c +++ b/drivers/gpu/drm/panel/panel-novatek-nt36523.c @@ -1266,9 +1266,9 @@ static int nt36523_probe(struct mipi_dsi_device *dsi) return dev_err_probe(dev, -EPROBE_DEFER, "cannot get secondary DSI host\n"); pinfo->dsi[1] = mipi_dsi_device_register_full(dsi1_host, info); - if (!pinfo->dsi[1]) { + if (IS_ERR(pinfo->dsi[1])) { dev_err(dev, "cannot get secondary DSI device\n"); - return -ENODEV; + return PTR_ERR(pinfo->dsi[1]); } } diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c index dd7928d9570f7..6e46e55d29a9a 100644 --- a/drivers/gpu/drm/panel/panel-simple.c +++ b/drivers/gpu/drm/panel/panel-simple.c @@ -2326,13 +2326,13 @@ static const struct panel_desc innolux_g070y2_t02 = { static const struct display_timing innolux_g101ice_l01_timing = { .pixelclock = { 60400000, 71100000, 74700000 }, .hactive = { 1280, 1280, 1280 }, - .hfront_porch = { 41, 80, 100 }, - .hback_porch = { 40, 79, 99 }, - .hsync_len = { 1, 1, 1 }, + .hfront_porch = { 30, 60, 70 }, + .hback_porch = { 30, 60, 70 }, + .hsync_len = { 22, 40, 60 }, .vactive = { 800, 800, 800 }, - .vfront_porch = { 5, 11, 14 }, - .vback_porch = { 4, 11, 14 }, - .vsync_len = { 1, 1, 1 }, + .vfront_porch = { 3, 8, 14 }, + .vback_porch = { 3, 8, 14 }, + .vsync_len = { 4, 7, 12 }, .flags = DISPLAY_FLAGS_DE_HIGH, }; @@ -2349,6 +2349,7 @@ static const struct panel_desc innolux_g101ice_l01 = { .disable = 200, }, .bus_format = MEDIA_BUS_FMT_RGB888_1X7X4_SPWG, + .bus_flags = DRM_BUS_FLAG_DE_HIGH, .connector_type = DRM_MODE_CONNECTOR_LVDS, }; diff --git a/drivers/gpu/drm/panel/panel-sitronix-st7703.c b/drivers/gpu/drm/panel/panel-sitronix-st7703.c index 6a39456395350..7bb723d445ade 100644 --- a/drivers/gpu/drm/panel/panel-sitronix-st7703.c +++ b/drivers/gpu/drm/panel/panel-sitronix-st7703.c @@ -506,29 +506,30 @@ static int st7703_prepare(struct drm_panel *panel) return 0; dev_dbg(ctx->dev, "Resetting the panel\n"); - ret = regulator_enable(ctx->vcc); + gpiod_set_value_cansleep(ctx->reset_gpio, 1); + + ret = regulator_enable(ctx->iovcc); if (ret < 0) { - dev_err(ctx->dev, "Failed to enable vcc supply: %d\n", ret); + dev_err(ctx->dev, "Failed to enable iovcc supply: %d\n", ret); return ret; } - ret = regulator_enable(ctx->iovcc); + + ret = regulator_enable(ctx->vcc); if (ret < 0) { - dev_err(ctx->dev, "Failed to enable iovcc supply: %d\n", ret); - goto disable_vcc; + dev_err(ctx->dev, "Failed to enable vcc supply: %d\n", ret); + regulator_disable(ctx->iovcc); + return ret; } - gpiod_set_value_cansleep(ctx->reset_gpio, 1); - usleep_range(20, 40); + /* Give power supplies time to stabilize before deasserting reset. */ + usleep_range(10000, 20000); + gpiod_set_value_cansleep(ctx->reset_gpio, 0); - msleep(20); + usleep_range(15000, 20000); ctx->prepared = true; return 0; - -disable_vcc: - regulator_disable(ctx->vcc); - return ret; } static const u32 mantix_bus_formats[] = { diff --git a/drivers/gpu/drm/panel/panel-tpo-tpg110.c b/drivers/gpu/drm/panel/panel-tpo-tpg110.c index 845304435e235..f6a212e542cb9 100644 --- a/drivers/gpu/drm/panel/panel-tpo-tpg110.c +++ b/drivers/gpu/drm/panel/panel-tpo-tpg110.c @@ -379,6 +379,8 @@ static int tpg110_get_modes(struct drm_panel *panel, connector->display_info.bus_flags = tpg->panel_mode->bus_flags; mode = drm_mode_duplicate(connector->dev, &tpg->panel_mode->mode); + if (!mode) + return -ENOMEM; drm_mode_set_name(mode); mode->type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED; diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c index 6492a70e3c396..404b0483bb7cb 100644 --- a/drivers/gpu/drm/qxl/qxl_display.c +++ b/drivers/gpu/drm/qxl/qxl_display.c @@ -1229,6 +1229,9 @@ int qxl_destroy_monitors_object(struct qxl_device *qdev) if (!qdev->monitors_config_bo) return 0; + kfree(qdev->dumb_heads); + qdev->dumb_heads = NULL; + qdev->monitors_config = NULL; qdev->ram_header->monitors_config = 0; diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c index d2f02c3dfce29..b84b58926106a 100644 --- a/drivers/gpu/drm/radeon/radeon_connectors.c +++ b/drivers/gpu/drm/radeon/radeon_connectors.c @@ -1119,6 +1119,8 @@ static int radeon_tv_get_modes(struct drm_connector *connector) else { /* only 800x600 is supported right now on pre-avivo chips */ tv_mode = drm_cvt_mode(dev, 800, 600, 60, false, false, false); + if (!tv_mode) + return 0; tv_mode->type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED; drm_mode_probed_add(connector, tv_mode); } diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c index 41cd12d5f2fa2..4b338cb89d32d 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c @@ -247,14 +247,22 @@ static inline void vop_cfg_done(struct vop *vop) VOP_REG_SET(vop, common, cfg_done, 1); } -static bool has_rb_swapped(uint32_t format) +static bool has_rb_swapped(uint32_t version, uint32_t format) { switch (format) { case DRM_FORMAT_XBGR8888: case DRM_FORMAT_ABGR8888: - case DRM_FORMAT_BGR888: case DRM_FORMAT_BGR565: return true; + /* + * full framework (IP version 3.x) only need rb swapped for RGB888 and + * little framework (IP version 2.x) only need rb swapped for BGR888, + * check for 3.x to also only rb swap BGR888 for unknown vop version + */ + case DRM_FORMAT_RGB888: + return VOP_MAJOR(version) == 3; + case DRM_FORMAT_BGR888: + return VOP_MAJOR(version) != 3; default: return false; } @@ -1013,7 +1021,7 @@ static void vop_plane_atomic_update(struct drm_plane *plane, VOP_WIN_SET(vop, win, dsp_info, dsp_info); VOP_WIN_SET(vop, win, dsp_st, dsp_st); - rb_swap = has_rb_swapped(fb->format->format); + rb_swap = has_rb_swapped(vop->data->version, fb->format->format); VOP_WIN_SET(vop, win, rb_swap, rb_swap); /* diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c b/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c index 8b1eb0061610c..12787bb9c111d 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c @@ -244,6 +244,7 @@ static int vmw_debugfs_gem_info_show(struct seq_file *m, void *unused) list_for_each_entry(file, &dev->filelist, lhead) { struct task_struct *task; struct drm_gem_object *gobj; + struct pid *pid; int id; /* @@ -253,8 +254,9 @@ static int vmw_debugfs_gem_info_show(struct seq_file *m, void *unused) * Therefore, we need to protect this ->comm access using RCU. */ rcu_read_lock(); - task = pid_task(file->pid, PIDTYPE_TGID); - seq_printf(m, "pid %8d command %s:\n", pid_nr(file->pid), + pid = rcu_dereference(file->pid); + task = pid_task(pid, PIDTYPE_TGID); + seq_printf(m, "pid %8d command %s:\n", pid_nr(pid), task ? task->comm : ""); rcu_read_unlock(); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c index 3829be282ff00..17463aeeef28f 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c @@ -774,9 +774,9 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data, sizeof(metadata->mip_levels)); metadata->num_sizes = num_sizes; metadata->sizes = - memdup_user((struct drm_vmw_size __user *)(unsigned long) + memdup_array_user((struct drm_vmw_size __user *)(unsigned long) req->size_addr, - sizeof(*metadata->sizes) * metadata->num_sizes); + metadata->num_sizes, sizeof(*metadata->sizes)); if (IS_ERR(metadata->sizes)) { ret = PTR_ERR(metadata->sizes); goto out_no_sizes; diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c index 3ca45975c686e..d9e9829b22001 100644 --- a/drivers/hid/hid-apple.c +++ b/drivers/hid/hid-apple.c @@ -345,6 +345,8 @@ static const struct apple_non_apple_keyboard non_apple_keyboards[] = { { "AONE" }, { "GANSS" }, { "Hailuck" }, + { "Jamesdonkey" }, + { "A3R" }, }; static bool apple_is_non_apple_keyboard(struct hid_device *hdev) diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c index fd61dba882338..78cdfb8b9a7ae 100644 --- a/drivers/hid/hid-asus.c +++ b/drivers/hid/hid-asus.c @@ -381,7 +381,7 @@ static int asus_raw_event(struct hid_device *hdev, return 0; } -static int asus_kbd_set_report(struct hid_device *hdev, u8 *buf, size_t buf_size) +static int asus_kbd_set_report(struct hid_device *hdev, const u8 *buf, size_t buf_size) { unsigned char *dmabuf; int ret; @@ -404,7 +404,7 @@ static int asus_kbd_set_report(struct hid_device *hdev, u8 *buf, size_t buf_size static int asus_kbd_init(struct hid_device *hdev) { - u8 buf[] = { FEATURE_KBD_REPORT_ID, 0x41, 0x53, 0x55, 0x53, 0x20, 0x54, + const u8 buf[] = { FEATURE_KBD_REPORT_ID, 0x41, 0x53, 0x55, 0x53, 0x20, 0x54, 0x65, 0x63, 0x68, 0x2e, 0x49, 0x6e, 0x63, 0x2e, 0x00 }; int ret; @@ -418,7 +418,7 @@ static int asus_kbd_init(struct hid_device *hdev) static int asus_kbd_get_functions(struct hid_device *hdev, unsigned char *kbd_func) { - u8 buf[] = { FEATURE_KBD_REPORT_ID, 0x05, 0x20, 0x31, 0x00, 0x08 }; + const u8 buf[] = { FEATURE_KBD_REPORT_ID, 0x05, 0x20, 0x31, 0x00, 0x08 }; u8 *readbuf; int ret; @@ -449,7 +449,7 @@ static int asus_kbd_get_functions(struct hid_device *hdev, static int rog_nkey_led_init(struct hid_device *hdev) { - u8 buf_init_start[] = { FEATURE_KBD_LED_REPORT_ID1, 0xB9 }; + const u8 buf_init_start[] = { FEATURE_KBD_LED_REPORT_ID1, 0xB9 }; u8 buf_init2[] = { FEATURE_KBD_LED_REPORT_ID1, 0x41, 0x53, 0x55, 0x53, 0x20, 0x54, 0x65, 0x63, 0x68, 0x2e, 0x49, 0x6e, 0x63, 0x2e, 0x00 }; u8 buf_init3[] = { FEATURE_KBD_LED_REPORT_ID1, @@ -1000,6 +1000,24 @@ static int asus_start_multitouch(struct hid_device *hdev) return 0; } +static int __maybe_unused asus_resume(struct hid_device *hdev) { + struct asus_drvdata *drvdata = hid_get_drvdata(hdev); + int ret = 0; + + if (drvdata->kbd_backlight) { + const u8 buf[] = { FEATURE_KBD_REPORT_ID, 0xba, 0xc5, 0xc4, + drvdata->kbd_backlight->cdev.brightness }; + ret = asus_kbd_set_report(hdev, buf, sizeof(buf)); + if (ret < 0) { + hid_err(hdev, "Asus failed to set keyboard backlight: %d\n", ret); + goto asus_resume_err; + } + } + +asus_resume_err: + return ret; +} + static int __maybe_unused asus_reset_resume(struct hid_device *hdev) { struct asus_drvdata *drvdata = hid_get_drvdata(hdev); @@ -1294,6 +1312,7 @@ static struct hid_driver asus_driver = { .input_configured = asus_input_configured, #ifdef CONFIG_PM .reset_resume = asus_reset_resume, + .resume = asus_resume, #endif .event = asus_event, .raw_event = asus_raw_event diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 8992e3c1e7698..e0181218ad857 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -702,15 +702,22 @@ static void hid_close_report(struct hid_device *device) * Free a device structure, all reports, and all fields. */ -static void hid_device_release(struct device *dev) +void hiddev_free(struct kref *ref) { - struct hid_device *hid = to_hid_device(dev); + struct hid_device *hid = container_of(ref, struct hid_device, ref); hid_close_report(hid); kfree(hid->dev_rdesc); kfree(hid); } +static void hid_device_release(struct device *dev) +{ + struct hid_device *hid = to_hid_device(dev); + + kref_put(&hid->ref, hiddev_free); +} + /* * Fetch a report description item from the data stream. We support long * items, though they are not used yet. @@ -2846,6 +2853,7 @@ struct hid_device *hid_allocate_device(void) spin_lock_init(&hdev->debug_list_lock); sema_init(&hdev->driver_input_lock, 1); mutex_init(&hdev->ll_open_lock); + kref_init(&hdev->ref); hid_bpf_device_init(hdev); diff --git a/drivers/hid/hid-debug.c b/drivers/hid/hid-debug.c index e7ef1ea107c9e..7dd83ec74f8a9 100644 --- a/drivers/hid/hid-debug.c +++ b/drivers/hid/hid-debug.c @@ -1135,6 +1135,7 @@ static int hid_debug_events_open(struct inode *inode, struct file *file) goto out; } list->hdev = (struct hid_device *) inode->i_private; + kref_get(&list->hdev->ref); file->private_data = list; mutex_init(&list->read_mutex); @@ -1227,6 +1228,8 @@ static int hid_debug_events_release(struct inode *inode, struct file *file) list_del(&list->node); spin_unlock_irqrestore(&list->hdev->debug_list_lock, flags); kfifo_free(&list->hid_debug_fifo); + + kref_put(&list->hdev->ref, hiddev_free); kfree(list); return 0; diff --git a/drivers/hid/hid-glorious.c b/drivers/hid/hid-glorious.c index 558eb08c19ef9..281b3a7187cec 100644 --- a/drivers/hid/hid-glorious.c +++ b/drivers/hid/hid-glorious.c @@ -21,6 +21,10 @@ MODULE_DESCRIPTION("HID driver for Glorious PC Gaming Race mice"); * Glorious Model O and O- specify the const flag in the consumer input * report descriptor, which leads to inputs being ignored. Fix this * by patching the descriptor. + * + * Glorious Model I incorrectly specifes the Usage Minimum for its + * keyboard HID report, causing keycodes to be misinterpreted. + * Fix this by setting Usage Minimum to 0 in that report. */ static __u8 *glorious_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) @@ -32,6 +36,10 @@ static __u8 *glorious_report_fixup(struct hid_device *hdev, __u8 *rdesc, rdesc[85] = rdesc[113] = rdesc[141] = \ HID_MAIN_ITEM_VARIABLE | HID_MAIN_ITEM_RELATIVE; } + if (*rsize == 156 && rdesc[41] == 1) { + hid_info(hdev, "patching Glorious Model I keyboard report descriptor\n"); + rdesc[41] = 0; + } return rdesc; } @@ -44,6 +52,8 @@ static void glorious_update_name(struct hid_device *hdev) model = "Model O"; break; case USB_DEVICE_ID_GLORIOUS_MODEL_D: model = "Model D"; break; + case USB_DEVICE_ID_GLORIOUS_MODEL_I: + model = "Model I"; break; } snprintf(hdev->name, sizeof(hdev->name), "%s %s", "Glorious", model); @@ -66,10 +76,12 @@ static int glorious_probe(struct hid_device *hdev, } static const struct hid_device_id glorious_devices[] = { - { HID_USB_DEVICE(USB_VENDOR_ID_GLORIOUS, + { HID_USB_DEVICE(USB_VENDOR_ID_SINOWEALTH, USB_DEVICE_ID_GLORIOUS_MODEL_O) }, - { HID_USB_DEVICE(USB_VENDOR_ID_GLORIOUS, + { HID_USB_DEVICE(USB_VENDOR_ID_SINOWEALTH, USB_DEVICE_ID_GLORIOUS_MODEL_D) }, + { HID_USB_DEVICE(USB_VENDOR_ID_LAVIEW, + USB_DEVICE_ID_GLORIOUS_MODEL_I) }, { } }; MODULE_DEVICE_TABLE(hid, glorious_devices); diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index e4d2dfd5d2536..72046039d1be7 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -366,6 +366,7 @@ #define USB_VENDOR_ID_DELL 0x413c #define USB_DEVICE_ID_DELL_PIXART_USB_OPTICAL_MOUSE 0x301a +#define USB_DEVICE_ID_DELL_PRO_WIRELESS_KM5221W 0x4503 #define USB_VENDOR_ID_DELORME 0x1163 #define USB_DEVICE_ID_DELORME_EARTHMATE 0x0100 @@ -510,10 +511,6 @@ #define USB_DEVICE_ID_GENERAL_TOUCH_WIN8_PIT_010A 0x010a #define USB_DEVICE_ID_GENERAL_TOUCH_WIN8_PIT_E100 0xe100 -#define USB_VENDOR_ID_GLORIOUS 0x258a -#define USB_DEVICE_ID_GLORIOUS_MODEL_D 0x0033 -#define USB_DEVICE_ID_GLORIOUS_MODEL_O 0x0036 - #define I2C_VENDOR_ID_GOODIX 0x27c6 #define I2C_DEVICE_ID_GOODIX_01F0 0x01f0 @@ -743,6 +740,10 @@ #define USB_VENDOR_ID_LABTEC 0x1020 #define USB_DEVICE_ID_LABTEC_WIRELESS_KEYBOARD 0x0006 +#define USB_DEVICE_ID_LABTEC_ODDOR_HANDBRAKE 0x8888 + +#define USB_VENDOR_ID_LAVIEW 0x22D4 +#define USB_DEVICE_ID_GLORIOUS_MODEL_I 0x1503 #define USB_VENDOR_ID_LCPOWER 0x1241 #define USB_DEVICE_ID_LCPOWER_LC1000 0xf767 @@ -868,7 +869,6 @@ #define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_2 0xc534 #define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_LIGHTSPEED_1 0xc539 #define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_LIGHTSPEED_1_1 0xc53f -#define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_LIGHTSPEED_1_2 0xc547 #define USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_POWERPLAY 0xc53a #define USB_DEVICE_ID_SPACETRAVELLER 0xc623 #define USB_DEVICE_ID_SPACENAVIGATOR 0xc626 @@ -1159,6 +1159,10 @@ #define USB_VENDOR_ID_SIGMATEL 0x066F #define USB_DEVICE_ID_SIGMATEL_STMP3780 0x3780 +#define USB_VENDOR_ID_SINOWEALTH 0x258a +#define USB_DEVICE_ID_GLORIOUS_MODEL_D 0x0033 +#define USB_DEVICE_ID_GLORIOUS_MODEL_O 0x0036 + #define USB_VENDOR_ID_SIS_TOUCH 0x0457 #define USB_DEVICE_ID_SIS9200_TOUCH 0x9200 #define USB_DEVICE_ID_SIS817_TOUCH 0x0817 diff --git a/drivers/hid/hid-lenovo.c b/drivers/hid/hid-lenovo.c index 44763c0da4441..149a3c74346b4 100644 --- a/drivers/hid/hid-lenovo.c +++ b/drivers/hid/hid-lenovo.c @@ -51,7 +51,12 @@ struct lenovo_drvdata { int select_right; int sensitivity; int press_speed; - u8 middlebutton_state; /* 0:Up, 1:Down (undecided), 2:Scrolling */ + /* 0: Up + * 1: Down (undecided) + * 2: Scrolling + * 3: Patched firmware, disable workaround + */ + u8 middlebutton_state; bool fn_lock; }; @@ -521,6 +526,19 @@ static void lenovo_features_set_cptkbd(struct hid_device *hdev) int ret; struct lenovo_drvdata *cptkbd_data = hid_get_drvdata(hdev); + /* + * Tell the keyboard a driver understands it, and turn F7, F9, F11 into + * regular keys + */ + ret = lenovo_send_cmd_cptkbd(hdev, 0x01, 0x03); + if (ret) + hid_warn(hdev, "Failed to switch F7/9/11 mode: %d\n", ret); + + /* Switch middle button to native mode */ + ret = lenovo_send_cmd_cptkbd(hdev, 0x09, 0x01); + if (ret) + hid_warn(hdev, "Failed to switch middle button: %d\n", ret); + ret = lenovo_send_cmd_cptkbd(hdev, 0x05, cptkbd_data->fn_lock); if (ret) hid_err(hdev, "Fn-lock setting failed: %d\n", ret); @@ -668,31 +686,49 @@ static int lenovo_event_cptkbd(struct hid_device *hdev, { struct lenovo_drvdata *cptkbd_data = hid_get_drvdata(hdev); - /* "wheel" scroll events */ - if (usage->type == EV_REL && (usage->code == REL_WHEEL || - usage->code == REL_HWHEEL)) { - /* Scroll events disable middle-click event */ - cptkbd_data->middlebutton_state = 2; - return 0; - } + if (cptkbd_data->middlebutton_state != 3) { + /* REL_X and REL_Y events during middle button pressed + * are only possible on patched, bug-free firmware + * so set middlebutton_state to 3 + * to never apply workaround anymore + */ + if (hdev->product == USB_DEVICE_ID_LENOVO_CUSBKBD && + cptkbd_data->middlebutton_state == 1 && + usage->type == EV_REL && + (usage->code == REL_X || usage->code == REL_Y)) { + cptkbd_data->middlebutton_state = 3; + /* send middle button press which was hold before */ + input_event(field->hidinput->input, + EV_KEY, BTN_MIDDLE, 1); + input_sync(field->hidinput->input); + } + + /* "wheel" scroll events */ + if (usage->type == EV_REL && (usage->code == REL_WHEEL || + usage->code == REL_HWHEEL)) { + /* Scroll events disable middle-click event */ + cptkbd_data->middlebutton_state = 2; + return 0; + } - /* Middle click events */ - if (usage->type == EV_KEY && usage->code == BTN_MIDDLE) { - if (value == 1) { - cptkbd_data->middlebutton_state = 1; - } else if (value == 0) { - if (cptkbd_data->middlebutton_state == 1) { - /* No scrolling inbetween, send middle-click */ - input_event(field->hidinput->input, - EV_KEY, BTN_MIDDLE, 1); - input_sync(field->hidinput->input); - input_event(field->hidinput->input, - EV_KEY, BTN_MIDDLE, 0); - input_sync(field->hidinput->input); + /* Middle click events */ + if (usage->type == EV_KEY && usage->code == BTN_MIDDLE) { + if (value == 1) { + cptkbd_data->middlebutton_state = 1; + } else if (value == 0) { + if (cptkbd_data->middlebutton_state == 1) { + /* No scrolling inbetween, send middle-click */ + input_event(field->hidinput->input, + EV_KEY, BTN_MIDDLE, 1); + input_sync(field->hidinput->input); + input_event(field->hidinput->input, + EV_KEY, BTN_MIDDLE, 0); + input_sync(field->hidinput->input); + } + cptkbd_data->middlebutton_state = 0; } - cptkbd_data->middlebutton_state = 0; + return 1; } - return 1; } if (usage->type == EV_KEY && usage->code == KEY_FN_ESC && value == 1) { @@ -1126,22 +1162,6 @@ static int lenovo_probe_cptkbd(struct hid_device *hdev) } hid_set_drvdata(hdev, cptkbd_data); - /* - * Tell the keyboard a driver understands it, and turn F7, F9, F11 into - * regular keys (Compact only) - */ - if (hdev->product == USB_DEVICE_ID_LENOVO_CUSBKBD || - hdev->product == USB_DEVICE_ID_LENOVO_CBTKBD) { - ret = lenovo_send_cmd_cptkbd(hdev, 0x01, 0x03); - if (ret) - hid_warn(hdev, "Failed to switch F7/9/11 mode: %d\n", ret); - } - - /* Switch middle button to native mode */ - ret = lenovo_send_cmd_cptkbd(hdev, 0x09, 0x01); - if (ret) - hid_warn(hdev, "Failed to switch middle button: %d\n", ret); - /* Set keyboard settings to known state */ cptkbd_data->middlebutton_state = 0; cptkbd_data->fn_lock = true; @@ -1264,6 +1284,24 @@ static int lenovo_probe(struct hid_device *hdev, return ret; } +#ifdef CONFIG_PM +static int lenovo_reset_resume(struct hid_device *hdev) +{ + switch (hdev->product) { + case USB_DEVICE_ID_LENOVO_CUSBKBD: + case USB_DEVICE_ID_LENOVO_TPIIUSBKBD: + if (hdev->type == HID_TYPE_USBMOUSE) + lenovo_features_set_cptkbd(hdev); + + break; + default: + break; + } + + return 0; +} +#endif + static void lenovo_remove_tpkbd(struct hid_device *hdev) { struct lenovo_drvdata *data_pointer = hid_get_drvdata(hdev); @@ -1380,6 +1418,9 @@ static struct hid_driver lenovo_driver = { .raw_event = lenovo_raw_event, .event = lenovo_event, .report_fixup = lenovo_report_fixup, +#ifdef CONFIG_PM + .reset_resume = lenovo_reset_resume, +#endif }; module_hid_driver(lenovo_driver); diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c index 8afe3be683ba2..e6a8b6d8eab70 100644 --- a/drivers/hid/hid-logitech-dj.c +++ b/drivers/hid/hid-logitech-dj.c @@ -1695,12 +1695,11 @@ static int logi_dj_raw_event(struct hid_device *hdev, } /* * Mouse-only receivers send unnumbered mouse data. The 27 MHz - * receiver uses 6 byte packets, the nano receiver 8 bytes, - * the lightspeed receiver (Pro X Superlight) 13 bytes. + * receiver uses 6 byte packets, the nano receiver 8 bytes. */ if (djrcv_dev->unnumbered_application == HID_GD_MOUSE && - size <= 13){ - u8 mouse_report[14]; + size <= 8) { + u8 mouse_report[9]; /* Prepend report id */ mouse_report[0] = REPORT_TYPE_MOUSE; @@ -1984,10 +1983,6 @@ static const struct hid_device_id logi_dj_receivers[] = { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_LIGHTSPEED_1_1), .driver_data = recvr_type_gaming_hidpp}, - { /* Logitech lightspeed receiver (0xc547) */ - HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, - USB_DEVICE_ID_LOGITECH_NANO_RECEIVER_LIGHTSPEED_1_2), - .driver_data = recvr_type_gaming_hidpp}, { /* Logitech 27 MHz HID++ 1.0 receiver (0xc513) */ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_MX3000_RECEIVER), diff --git a/drivers/hid/hid-mcp2221.c b/drivers/hid/hid-mcp2221.c index 72883e0ce7575..aef0785c91cc2 100644 --- a/drivers/hid/hid-mcp2221.c +++ b/drivers/hid/hid-mcp2221.c @@ -1142,6 +1142,8 @@ static int mcp2221_probe(struct hid_device *hdev, if (ret) return ret; + hid_device_io_start(hdev); + /* Set I2C bus clock diviser */ if (i2c_clk_freq > 400) i2c_clk_freq = 400; @@ -1157,12 +1159,12 @@ static int mcp2221_probe(struct hid_device *hdev, snprintf(mcp->adapter.name, sizeof(mcp->adapter.name), "MCP2221 usb-i2c bridge"); + i2c_set_adapdata(&mcp->adapter, mcp); ret = devm_i2c_add_adapter(&hdev->dev, &mcp->adapter); if (ret) { hid_err(hdev, "can't add usb-i2c adapter: %d\n", ret); return ret; } - i2c_set_adapdata(&mcp->adapter, mcp); #if IS_REACHABLE(CONFIG_GPIOLIB) /* Setup GPIO chip */ diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index 8db4ae05febc8..5ec1f174127a3 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -2048,6 +2048,11 @@ static const struct hid_device_id mt_devices[] = { MT_USB_DEVICE(USB_VENDOR_ID_HANVON_ALT, USB_DEVICE_ID_HANVON_ALT_MULTITOUCH) }, + /* HONOR GLO-GXXX panel */ + { .driver_data = MT_CLS_VTL, + HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8, + 0x347d, 0x7853) }, + /* Ilitek dual touch panel */ { .driver_data = MT_CLS_NSMU, MT_USB_DEVICE(USB_VENDOR_ID_ILITEK, diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index 3983b4f282f8f..e0bbf0c6345d6 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -33,6 +33,7 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_AKAI, USB_DEVICE_ID_AKAI_MPKMINI2), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_ALPS, USB_DEVICE_ID_IBM_GAMEPAD), HID_QUIRK_BADPAD }, { HID_USB_DEVICE(USB_VENDOR_ID_AMI, USB_DEVICE_ID_AMI_VIRT_KEYBOARD_AND_MOUSE), HID_QUIRK_ALWAYS_POLL }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_REVB_ANSI), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_2PORTKVM), HID_QUIRK_NOGET }, { HID_USB_DEVICE(USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_4PORTKVMC), HID_QUIRK_NOGET }, { HID_USB_DEVICE(USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_4PORTKVM), HID_QUIRK_NOGET }, @@ -66,6 +67,7 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_STRAFE), HID_QUIRK_NO_INIT_REPORTS | HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_CREATIVELABS, USB_DEVICE_ID_CREATIVE_SB_OMNI_SURROUND_51), HID_QUIRK_NOGET }, { HID_USB_DEVICE(USB_VENDOR_ID_DELL, USB_DEVICE_ID_DELL_PIXART_USB_OPTICAL_MOUSE), HID_QUIRK_ALWAYS_POLL }, + { HID_USB_DEVICE(USB_VENDOR_ID_DELL, USB_DEVICE_ID_DELL_PRO_WIRELESS_KM5221W), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_DMI, USB_DEVICE_ID_DMI_ENC), HID_QUIRK_NOGET }, { HID_USB_DEVICE(USB_VENDOR_ID_DRACAL_RAPHNET, USB_DEVICE_ID_RAPHNET_2NES2SNES), HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_DRACAL_RAPHNET, USB_DEVICE_ID_RAPHNET_4NES4SNES), HID_QUIRK_MULTI_INPUT }, @@ -119,6 +121,7 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_EASYPEN_M406XE), HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_MOUSEPEN_I608X_V2), HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_PENSKETCH_T609A), HID_QUIRK_MULTI_INPUT }, + { HID_USB_DEVICE(USB_VENDOR_ID_LABTEC, USB_DEVICE_ID_LABTEC_ODDOR_HANDBRAKE), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_OPTICAL_USB_MOUSE_600E), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_608D), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_6019), HID_QUIRK_ALWAYS_POLL }, diff --git a/drivers/hid/i2c-hid/i2c-hid-acpi.c b/drivers/hid/i2c-hid/i2c-hid-acpi.c index ac918a9ea8d34..1b49243adb16a 100644 --- a/drivers/hid/i2c-hid/i2c-hid-acpi.c +++ b/drivers/hid/i2c-hid/i2c-hid-acpi.c @@ -40,6 +40,11 @@ static const struct acpi_device_id i2c_hid_acpi_blacklist[] = { * ICN8505 controller, has a _CID of PNP0C50 but is not HID compatible. */ { "CHPN0001" }, + /* + * The IDEA5002 ACPI device causes high interrupt usage and spurious + * wakeups from suspend. + */ + { "IDEA5002" }, { } }; diff --git a/drivers/hwmon/acpi_power_meter.c b/drivers/hwmon/acpi_power_meter.c index fa28d447f0dfb..b772c076a5aed 100644 --- a/drivers/hwmon/acpi_power_meter.c +++ b/drivers/hwmon/acpi_power_meter.c @@ -31,6 +31,7 @@ #define POWER_METER_CAN_NOTIFY (1 << 3) #define POWER_METER_IS_BATTERY (1 << 8) #define UNKNOWN_HYSTERESIS 0xFFFFFFFF +#define UNKNOWN_POWER 0xFFFFFFFF #define METER_NOTIFY_CONFIG 0x80 #define METER_NOTIFY_TRIP 0x81 @@ -348,6 +349,9 @@ static ssize_t show_power(struct device *dev, update_meter(resource); mutex_unlock(&resource->lock); + if (resource->power == UNKNOWN_POWER) + return -ENODATA; + return sprintf(buf, "%llu\n", resource->power * 1000); } diff --git a/drivers/hwmon/nzxt-kraken2.c b/drivers/hwmon/nzxt-kraken2.c index 428c77b5fce5a..7caf387eb1449 100644 --- a/drivers/hwmon/nzxt-kraken2.c +++ b/drivers/hwmon/nzxt-kraken2.c @@ -161,13 +161,13 @@ static int kraken2_probe(struct hid_device *hdev, ret = hid_hw_start(hdev, HID_CONNECT_HIDRAW); if (ret) { hid_err(hdev, "hid hw start failed with %d\n", ret); - goto fail_and_stop; + return ret; } ret = hid_hw_open(hdev); if (ret) { hid_err(hdev, "hid hw open failed with %d\n", ret); - goto fail_and_close; + goto fail_and_stop; } priv->hwmon_dev = hwmon_device_register_with_info(&hdev->dev, "kraken2", diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c index 5ca6278baff4f..89e8ed214ea49 100644 --- a/drivers/hwtracing/coresight/coresight-etm-perf.c +++ b/drivers/hwtracing/coresight/coresight-etm-perf.c @@ -493,7 +493,7 @@ static void etm_event_start(struct perf_event *event, int flags) goto fail_end_stop; /* Finally enable the tracer */ - if (coresight_enable_source(csdev, CS_MODE_PERF, event)) + if (source_ops(csdev)->enable(csdev, event, CS_MODE_PERF)) goto fail_disable_path; /* @@ -587,7 +587,7 @@ static void etm_event_stop(struct perf_event *event, int mode) return; /* stop tracer */ - coresight_disable_source(csdev, event); + source_ops(csdev)->disable(csdev, event); /* tell the core */ event->hw.state = PERF_HES_STOPPED; diff --git a/drivers/hwtracing/coresight/coresight-etm4x-core.c b/drivers/hwtracing/coresight/coresight-etm4x-core.c index 77b0271ce6eb9..34aee59dd1473 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x-core.c +++ b/drivers/hwtracing/coresight/coresight-etm4x-core.c @@ -2224,7 +2224,7 @@ static void clear_etmdrvdata(void *info) per_cpu(delayed_probe, cpu) = NULL; } -static void __exit etm4_remove_dev(struct etmv4_drvdata *drvdata) +static void etm4_remove_dev(struct etmv4_drvdata *drvdata) { bool had_delayed_probe; /* @@ -2253,7 +2253,7 @@ static void __exit etm4_remove_dev(struct etmv4_drvdata *drvdata) } } -static void __exit etm4_remove_amba(struct amba_device *adev) +static void etm4_remove_amba(struct amba_device *adev) { struct etmv4_drvdata *drvdata = dev_get_drvdata(&adev->dev); @@ -2261,7 +2261,7 @@ static void __exit etm4_remove_amba(struct amba_device *adev) etm4_remove_dev(drvdata); } -static int __exit etm4_remove_platform_dev(struct platform_device *pdev) +static int etm4_remove_platform_dev(struct platform_device *pdev) { struct etmv4_drvdata *drvdata = dev_get_drvdata(&pdev->dev); diff --git a/drivers/hwtracing/coresight/ultrasoc-smb.c b/drivers/hwtracing/coresight/ultrasoc-smb.c index e9a32a97fbee6..6e32d31a95fe0 100644 --- a/drivers/hwtracing/coresight/ultrasoc-smb.c +++ b/drivers/hwtracing/coresight/ultrasoc-smb.c @@ -99,7 +99,7 @@ static int smb_open(struct inode *inode, struct file *file) struct smb_drv_data, miscdev); int ret = 0; - mutex_lock(&drvdata->mutex); + spin_lock(&drvdata->spinlock); if (drvdata->reading) { ret = -EBUSY; @@ -115,7 +115,7 @@ static int smb_open(struct inode *inode, struct file *file) drvdata->reading = true; out: - mutex_unlock(&drvdata->mutex); + spin_unlock(&drvdata->spinlock); return ret; } @@ -132,10 +132,8 @@ static ssize_t smb_read(struct file *file, char __user *data, size_t len, if (!len) return 0; - mutex_lock(&drvdata->mutex); - if (!sdb->data_size) - goto out; + return 0; to_copy = min(sdb->data_size, len); @@ -145,20 +143,15 @@ static ssize_t smb_read(struct file *file, char __user *data, size_t len, if (copy_to_user(data, sdb->buf_base + sdb->buf_rdptr, to_copy)) { dev_dbg(dev, "Failed to copy data to user\n"); - to_copy = -EFAULT; - goto out; + return -EFAULT; } *ppos += to_copy; - smb_update_read_ptr(drvdata, to_copy); - - dev_dbg(dev, "%zu bytes copied\n", to_copy); -out: if (!sdb->data_size) smb_reset_buffer(drvdata); - mutex_unlock(&drvdata->mutex); + dev_dbg(dev, "%zu bytes copied\n", to_copy); return to_copy; } @@ -167,9 +160,9 @@ static int smb_release(struct inode *inode, struct file *file) struct smb_drv_data *drvdata = container_of(file->private_data, struct smb_drv_data, miscdev); - mutex_lock(&drvdata->mutex); + spin_lock(&drvdata->spinlock); drvdata->reading = false; - mutex_unlock(&drvdata->mutex); + spin_unlock(&drvdata->spinlock); return 0; } @@ -262,7 +255,7 @@ static int smb_enable(struct coresight_device *csdev, enum cs_mode mode, struct smb_drv_data *drvdata = dev_get_drvdata(csdev->dev.parent); int ret = 0; - mutex_lock(&drvdata->mutex); + spin_lock(&drvdata->spinlock); /* Do nothing, the trace data is reading by other interface now */ if (drvdata->reading) { @@ -294,7 +287,7 @@ static int smb_enable(struct coresight_device *csdev, enum cs_mode mode, dev_dbg(&csdev->dev, "Ultrasoc SMB enabled\n"); out: - mutex_unlock(&drvdata->mutex); + spin_unlock(&drvdata->spinlock); return ret; } @@ -304,7 +297,7 @@ static int smb_disable(struct coresight_device *csdev) struct smb_drv_data *drvdata = dev_get_drvdata(csdev->dev.parent); int ret = 0; - mutex_lock(&drvdata->mutex); + spin_lock(&drvdata->spinlock); if (drvdata->reading) { ret = -EBUSY; @@ -327,7 +320,7 @@ static int smb_disable(struct coresight_device *csdev) dev_dbg(&csdev->dev, "Ultrasoc SMB disabled\n"); out: - mutex_unlock(&drvdata->mutex); + spin_unlock(&drvdata->spinlock); return ret; } @@ -408,7 +401,7 @@ static unsigned long smb_update_buffer(struct coresight_device *csdev, if (!buf) return 0; - mutex_lock(&drvdata->mutex); + spin_lock(&drvdata->spinlock); /* Don't do anything if another tracer is using this sink. */ if (atomic_read(&csdev->refcnt) != 1) @@ -432,7 +425,7 @@ static unsigned long smb_update_buffer(struct coresight_device *csdev, if (!buf->snapshot && lost) perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED); out: - mutex_unlock(&drvdata->mutex); + spin_unlock(&drvdata->spinlock); return data_size; } @@ -484,7 +477,6 @@ static int smb_init_data_buffer(struct platform_device *pdev, static void smb_init_hw(struct smb_drv_data *drvdata) { smb_disable_hw(drvdata); - smb_reset_buffer(drvdata); writel(SMB_LB_CFG_LO_DEFAULT, drvdata->base + SMB_LB_CFG_LO_REG); writel(SMB_LB_CFG_HI_DEFAULT, drvdata->base + SMB_LB_CFG_HI_REG); @@ -590,37 +582,33 @@ static int smb_probe(struct platform_device *pdev) return ret; } - mutex_init(&drvdata->mutex); + ret = smb_config_inport(dev, true); + if (ret) + return ret; + + smb_reset_buffer(drvdata); + platform_set_drvdata(pdev, drvdata); + spin_lock_init(&drvdata->spinlock); drvdata->pid = -1; ret = smb_register_sink(pdev, drvdata); if (ret) { + smb_config_inport(&pdev->dev, false); dev_err(dev, "Failed to register SMB sink\n"); return ret; } - ret = smb_config_inport(dev, true); - if (ret) { - smb_unregister_sink(drvdata); - return ret; - } - - platform_set_drvdata(pdev, drvdata); - return 0; } static int smb_remove(struct platform_device *pdev) { struct smb_drv_data *drvdata = platform_get_drvdata(pdev); - int ret; - - ret = smb_config_inport(&pdev->dev, false); - if (ret) - return ret; smb_unregister_sink(drvdata); + smb_config_inport(&pdev->dev, false); + return 0; } diff --git a/drivers/hwtracing/coresight/ultrasoc-smb.h b/drivers/hwtracing/coresight/ultrasoc-smb.h index d2e14e8d2c8a8..82a44c14a8829 100644 --- a/drivers/hwtracing/coresight/ultrasoc-smb.h +++ b/drivers/hwtracing/coresight/ultrasoc-smb.h @@ -8,7 +8,7 @@ #define _ULTRASOC_SMB_H #include -#include +#include /* Offset of SMB global registers */ #define SMB_GLB_CFG_REG 0x00 @@ -105,7 +105,7 @@ struct smb_data_buffer { * @csdev: Component vitals needed by the framework. * @sdb: Data buffer for SMB. * @miscdev: Specifics to handle "/dev/xyz.smb" entry. - * @mutex: Control data access to one at a time. + * @spinlock: Control data access to one at a time. * @reading: Synchronise user space access to SMB buffer. * @pid: Process ID of the process being monitored by the * session that is using this component. @@ -116,7 +116,7 @@ struct smb_drv_data { struct coresight_device *csdev; struct smb_data_buffer sdb; struct miscdevice miscdev; - struct mutex mutex; + spinlock_t spinlock; bool reading; pid_t pid; enum cs_mode mode; diff --git a/drivers/hwtracing/ptt/hisi_ptt.c b/drivers/hwtracing/ptt/hisi_ptt.c index 49ea1b0f74890..3045d1894b81b 100644 --- a/drivers/hwtracing/ptt/hisi_ptt.c +++ b/drivers/hwtracing/ptt/hisi_ptt.c @@ -1178,6 +1178,10 @@ static void hisi_ptt_pmu_del(struct perf_event *event, int flags) hisi_ptt_pmu_stop(event, PERF_EF_UPDATE); } +static void hisi_ptt_pmu_read(struct perf_event *event) +{ +} + static void hisi_ptt_remove_cpuhp_instance(void *hotplug_node) { cpuhp_state_remove_instance_nocalls(hisi_ptt_pmu_online, hotplug_node); @@ -1221,6 +1225,7 @@ static int hisi_ptt_register_pmu(struct hisi_ptt *hisi_ptt) .stop = hisi_ptt_pmu_stop, .add = hisi_ptt_pmu_add, .del = hisi_ptt_pmu_del, + .read = hisi_ptt_pmu_read, }; reg = readl(hisi_ptt->iobase + HISI_PTT_LOCATION); diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig index 6644eebedaf3b..97d27e01a6ee2 100644 --- a/drivers/i2c/busses/Kconfig +++ b/drivers/i2c/busses/Kconfig @@ -158,6 +158,7 @@ config I2C_I801 Alder Lake (PCH) Raptor Lake (PCH) Meteor Lake (SOC and PCH) + Birch Stream (SOC) This driver can also be built as a module. If so, the module will be called i2c-i801. diff --git a/drivers/i2c/busses/i2c-aspeed.c b/drivers/i2c/busses/i2c-aspeed.c index 28e2a5fc45282..5511fd46a65ea 100644 --- a/drivers/i2c/busses/i2c-aspeed.c +++ b/drivers/i2c/busses/i2c-aspeed.c @@ -249,18 +249,46 @@ static u32 aspeed_i2c_slave_irq(struct aspeed_i2c_bus *bus, u32 irq_status) if (!slave) return 0; - command = readl(bus->base + ASPEED_I2C_CMD_REG); + /* + * Handle stop conditions early, prior to SLAVE_MATCH. Some masters may drive + * transfers with low enough latency between the nak/stop phase of the current + * command and the start/address phase of the following command that the + * interrupts are coalesced by the time we process them. + */ + if (irq_status & ASPEED_I2CD_INTR_NORMAL_STOP) { + irq_handled |= ASPEED_I2CD_INTR_NORMAL_STOP; + bus->slave_state = ASPEED_I2C_SLAVE_STOP; + } + + if (irq_status & ASPEED_I2CD_INTR_TX_NAK && + bus->slave_state == ASPEED_I2C_SLAVE_READ_PROCESSED) { + irq_handled |= ASPEED_I2CD_INTR_TX_NAK; + bus->slave_state = ASPEED_I2C_SLAVE_STOP; + } + + /* Propagate any stop conditions to the slave implementation. */ + if (bus->slave_state == ASPEED_I2C_SLAVE_STOP) { + i2c_slave_event(slave, I2C_SLAVE_STOP, &value); + bus->slave_state = ASPEED_I2C_SLAVE_INACTIVE; + } - /* Slave was requested, restart state machine. */ + /* + * Now that we've dealt with any potentially coalesced stop conditions, + * address any start conditions. + */ if (irq_status & ASPEED_I2CD_INTR_SLAVE_MATCH) { irq_handled |= ASPEED_I2CD_INTR_SLAVE_MATCH; bus->slave_state = ASPEED_I2C_SLAVE_START; } - /* Slave is not currently active, irq was for someone else. */ + /* + * If the slave has been stopped and not started then slave interrupt + * handling is complete. + */ if (bus->slave_state == ASPEED_I2C_SLAVE_INACTIVE) return irq_handled; + command = readl(bus->base + ASPEED_I2C_CMD_REG); dev_dbg(bus->dev, "slave irq status 0x%08x, cmd 0x%08x\n", irq_status, command); @@ -279,17 +307,6 @@ static u32 aspeed_i2c_slave_irq(struct aspeed_i2c_bus *bus, u32 irq_status) irq_handled |= ASPEED_I2CD_INTR_RX_DONE; } - /* Slave was asked to stop. */ - if (irq_status & ASPEED_I2CD_INTR_NORMAL_STOP) { - irq_handled |= ASPEED_I2CD_INTR_NORMAL_STOP; - bus->slave_state = ASPEED_I2C_SLAVE_STOP; - } - if (irq_status & ASPEED_I2CD_INTR_TX_NAK && - bus->slave_state == ASPEED_I2C_SLAVE_READ_PROCESSED) { - irq_handled |= ASPEED_I2CD_INTR_TX_NAK; - bus->slave_state = ASPEED_I2C_SLAVE_STOP; - } - switch (bus->slave_state) { case ASPEED_I2C_SLAVE_READ_REQUESTED: if (unlikely(irq_status & ASPEED_I2CD_INTR_TX_ACK)) @@ -324,8 +341,7 @@ static u32 aspeed_i2c_slave_irq(struct aspeed_i2c_bus *bus, u32 irq_status) i2c_slave_event(slave, I2C_SLAVE_WRITE_RECEIVED, &value); break; case ASPEED_I2C_SLAVE_STOP: - i2c_slave_event(slave, I2C_SLAVE_STOP, &value); - bus->slave_state = ASPEED_I2C_SLAVE_INACTIVE; + /* Stop event handling is done early. Unreachable. */ break; case ASPEED_I2C_SLAVE_START: /* Slave was just started. Waiting for the next event. */; diff --git a/drivers/i2c/busses/i2c-designware-common.c b/drivers/i2c/busses/i2c-designware-common.c index affcfb243f0f5..35f762872b8a5 100644 --- a/drivers/i2c/busses/i2c-designware-common.c +++ b/drivers/i2c/busses/i2c-designware-common.c @@ -63,7 +63,7 @@ static int dw_reg_read(void *context, unsigned int reg, unsigned int *val) { struct dw_i2c_dev *dev = context; - *val = readl_relaxed(dev->base + reg); + *val = readl(dev->base + reg); return 0; } @@ -72,7 +72,7 @@ static int dw_reg_write(void *context, unsigned int reg, unsigned int val) { struct dw_i2c_dev *dev = context; - writel_relaxed(val, dev->base + reg); + writel(val, dev->base + reg); return 0; } @@ -81,7 +81,7 @@ static int dw_reg_read_swab(void *context, unsigned int reg, unsigned int *val) { struct dw_i2c_dev *dev = context; - *val = swab32(readl_relaxed(dev->base + reg)); + *val = swab32(readl(dev->base + reg)); return 0; } @@ -90,7 +90,7 @@ static int dw_reg_write_swab(void *context, unsigned int reg, unsigned int val) { struct dw_i2c_dev *dev = context; - writel_relaxed(swab32(val), dev->base + reg); + writel(swab32(val), dev->base + reg); return 0; } @@ -99,8 +99,8 @@ static int dw_reg_read_word(void *context, unsigned int reg, unsigned int *val) { struct dw_i2c_dev *dev = context; - *val = readw_relaxed(dev->base + reg) | - (readw_relaxed(dev->base + reg + 2) << 16); + *val = readw(dev->base + reg) | + (readw(dev->base + reg + 2) << 16); return 0; } @@ -109,8 +109,8 @@ static int dw_reg_write_word(void *context, unsigned int reg, unsigned int val) { struct dw_i2c_dev *dev = context; - writew_relaxed(val, dev->base + reg); - writew_relaxed(val >> 16, dev->base + reg + 2); + writew(val, dev->base + reg); + writew(val >> 16, dev->base + reg + 2); return 0; } diff --git a/drivers/i2c/busses/i2c-designware-master.c b/drivers/i2c/busses/i2c-designware-master.c index ca1035e010c72..85dbd0eb5392c 100644 --- a/drivers/i2c/busses/i2c-designware-master.c +++ b/drivers/i2c/busses/i2c-designware-master.c @@ -519,10 +519,16 @@ i2c_dw_xfer_msg(struct dw_i2c_dev *dev) /* * Because we don't know the buffer length in the - * I2C_FUNC_SMBUS_BLOCK_DATA case, we can't stop - * the transaction here. + * I2C_FUNC_SMBUS_BLOCK_DATA case, we can't stop the + * transaction here. Also disable the TX_EMPTY IRQ + * while waiting for the data length byte to avoid the + * bogus interrupts flood. */ - if (buf_len > 0 || flags & I2C_M_RECV_LEN) { + if (flags & I2C_M_RECV_LEN) { + dev->status |= STATUS_WRITE_IN_PROGRESS; + intr_mask &= ~DW_IC_INTR_TX_EMPTY; + break; + } else if (buf_len > 0) { /* more bytes to be written */ dev->status |= STATUS_WRITE_IN_PROGRESS; break; @@ -558,6 +564,13 @@ i2c_dw_recv_len(struct dw_i2c_dev *dev, u8 len) msgs[dev->msg_read_idx].len = len; msgs[dev->msg_read_idx].flags &= ~I2C_M_RECV_LEN; + /* + * Received buffer length, re-enable TX_EMPTY interrupt + * to resume the SMBUS transaction. + */ + regmap_update_bits(dev->map, DW_IC_INTR_MASK, DW_IC_INTR_TX_EMPTY, + DW_IC_INTR_TX_EMPTY); + return len; } diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index 1d855258a45dc..a87e3c15e5fc6 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -79,6 +79,7 @@ * Meteor Lake-P (SOC) 0x7e22 32 hard yes yes yes * Meteor Lake SoC-S (SOC) 0xae22 32 hard yes yes yes * Meteor Lake PCH-S (PCH) 0x7f23 32 hard yes yes yes + * Birch Stream (SOC) 0x5796 32 hard yes yes yes * * Features supported by this driver: * Software PEC no @@ -231,6 +232,7 @@ #define PCI_DEVICE_ID_INTEL_JASPER_LAKE_SMBUS 0x4da3 #define PCI_DEVICE_ID_INTEL_ALDER_LAKE_P_SMBUS 0x51a3 #define PCI_DEVICE_ID_INTEL_ALDER_LAKE_M_SMBUS 0x54a3 +#define PCI_DEVICE_ID_INTEL_BIRCH_STREAM_SMBUS 0x5796 #define PCI_DEVICE_ID_INTEL_BROXTON_SMBUS 0x5ad4 #define PCI_DEVICE_ID_INTEL_RAPTOR_LAKE_S_SMBUS 0x7a23 #define PCI_DEVICE_ID_INTEL_ALDER_LAKE_S_SMBUS 0x7aa3 @@ -679,15 +681,11 @@ static int i801_block_transaction_byte_by_byte(struct i801_priv *priv, return result ? priv->status : -ETIMEDOUT; } - for (i = 1; i <= len; i++) { - if (i == len && read_write == I2C_SMBUS_READ) - smbcmd |= SMBHSTCNT_LAST_BYTE; - outb_p(smbcmd, SMBHSTCNT(priv)); - - if (i == 1) - outb_p(inb(SMBHSTCNT(priv)) | SMBHSTCNT_START, - SMBHSTCNT(priv)); + if (len == 1 && read_write == I2C_SMBUS_READ) + smbcmd |= SMBHSTCNT_LAST_BYTE; + outb_p(smbcmd | SMBHSTCNT_START, SMBHSTCNT(priv)); + for (i = 1; i <= len; i++) { status = i801_wait_byte_done(priv); if (status) return status; @@ -710,9 +708,12 @@ static int i801_block_transaction_byte_by_byte(struct i801_priv *priv, data->block[0] = len; } - /* Retrieve/store value in SMBBLKDAT */ - if (read_write == I2C_SMBUS_READ) + if (read_write == I2C_SMBUS_READ) { data->block[i] = inb_p(SMBBLKDAT(priv)); + if (i == len - 1) + outb_p(smbcmd | SMBHSTCNT_LAST_BYTE, SMBHSTCNT(priv)); + } + if (read_write == I2C_SMBUS_WRITE && i+1 <= len) outb_p(data->block[i+1], SMBBLKDAT(priv)); @@ -1044,6 +1045,7 @@ static const struct pci_device_id i801_ids[] = { { PCI_DEVICE_DATA(INTEL, METEOR_LAKE_P_SMBUS, FEATURES_ICH5 | FEATURE_TCO_CNL) }, { PCI_DEVICE_DATA(INTEL, METEOR_LAKE_SOC_S_SMBUS, FEATURES_ICH5 | FEATURE_TCO_CNL) }, { PCI_DEVICE_DATA(INTEL, METEOR_LAKE_PCH_S_SMBUS, FEATURES_ICH5 | FEATURE_TCO_CNL) }, + { PCI_DEVICE_DATA(INTEL, BIRCH_STREAM_SMBUS, FEATURES_ICH5 | FEATURE_TCO_CNL) }, { 0, } }; diff --git a/drivers/i2c/busses/i2c-ocores.c b/drivers/i2c/busses/i2c-ocores.c index 041a76f71a49c..e106af83cef4d 100644 --- a/drivers/i2c/busses/i2c-ocores.c +++ b/drivers/i2c/busses/i2c-ocores.c @@ -771,8 +771,8 @@ static int ocores_i2c_resume(struct device *dev) return ocores_init(dev, i2c); } -static DEFINE_SIMPLE_DEV_PM_OPS(ocores_i2c_pm, - ocores_i2c_suspend, ocores_i2c_resume); +static DEFINE_NOIRQ_DEV_PM_OPS(ocores_i2c_pm, + ocores_i2c_suspend, ocores_i2c_resume); static struct platform_driver ocores_i2c_driver = { .probe = ocores_i2c_probe, diff --git a/drivers/i2c/busses/i2c-pxa.c b/drivers/i2c/busses/i2c-pxa.c index 29be05af826b0..3bd406470940f 100644 --- a/drivers/i2c/busses/i2c-pxa.c +++ b/drivers/i2c/busses/i2c-pxa.c @@ -264,6 +264,9 @@ struct pxa_i2c { u32 hs_mask; struct i2c_bus_recovery_info recovery; + struct pinctrl *pinctrl; + struct pinctrl_state *pinctrl_default; + struct pinctrl_state *pinctrl_recovery; }; #define _IBMR(i2c) ((i2c)->reg_ibmr) @@ -1300,12 +1303,13 @@ static void i2c_pxa_prepare_recovery(struct i2c_adapter *adap) */ gpiod_set_value(i2c->recovery.scl_gpiod, ibmr & IBMR_SCLS); gpiod_set_value(i2c->recovery.sda_gpiod, ibmr & IBMR_SDAS); + + WARN_ON(pinctrl_select_state(i2c->pinctrl, i2c->pinctrl_recovery)); } static void i2c_pxa_unprepare_recovery(struct i2c_adapter *adap) { struct pxa_i2c *i2c = adap->algo_data; - struct i2c_bus_recovery_info *bri = adap->bus_recovery_info; u32 isr; /* @@ -1319,7 +1323,7 @@ static void i2c_pxa_unprepare_recovery(struct i2c_adapter *adap) i2c_pxa_do_reset(i2c); } - WARN_ON(pinctrl_select_state(bri->pinctrl, bri->pins_default)); + WARN_ON(pinctrl_select_state(i2c->pinctrl, i2c->pinctrl_default)); dev_dbg(&i2c->adap.dev, "recovery: IBMR 0x%08x ISR 0x%08x\n", readl(_IBMR(i2c)), readl(_ISR(i2c))); @@ -1341,20 +1345,76 @@ static int i2c_pxa_init_recovery(struct pxa_i2c *i2c) if (IS_ENABLED(CONFIG_I2C_PXA_SLAVE)) return 0; - bri->pinctrl = devm_pinctrl_get(dev); - if (PTR_ERR(bri->pinctrl) == -ENODEV) { - bri->pinctrl = NULL; + i2c->pinctrl = devm_pinctrl_get(dev); + if (PTR_ERR(i2c->pinctrl) == -ENODEV) + i2c->pinctrl = NULL; + if (IS_ERR(i2c->pinctrl)) + return PTR_ERR(i2c->pinctrl); + + if (!i2c->pinctrl) + return 0; + + i2c->pinctrl_default = pinctrl_lookup_state(i2c->pinctrl, + PINCTRL_STATE_DEFAULT); + i2c->pinctrl_recovery = pinctrl_lookup_state(i2c->pinctrl, "recovery"); + + if (IS_ERR(i2c->pinctrl_default) || IS_ERR(i2c->pinctrl_recovery)) { + dev_info(dev, "missing pinmux recovery information: %ld %ld\n", + PTR_ERR(i2c->pinctrl_default), + PTR_ERR(i2c->pinctrl_recovery)); + return 0; + } + + /* + * Claiming GPIOs can influence the pinmux state, and may glitch the + * I2C bus. Do this carefully. + */ + bri->scl_gpiod = devm_gpiod_get(dev, "scl", GPIOD_OUT_HIGH_OPEN_DRAIN); + if (bri->scl_gpiod == ERR_PTR(-EPROBE_DEFER)) + return -EPROBE_DEFER; + if (IS_ERR(bri->scl_gpiod)) { + dev_info(dev, "missing scl gpio recovery information: %pe\n", + bri->scl_gpiod); + return 0; + } + + /* + * We have SCL. Pull SCL low and wait a bit so that SDA glitches + * have no effect. + */ + gpiod_direction_output(bri->scl_gpiod, 0); + udelay(10); + bri->sda_gpiod = devm_gpiod_get(dev, "sda", GPIOD_OUT_HIGH_OPEN_DRAIN); + + /* Wait a bit in case of a SDA glitch, and then release SCL. */ + udelay(10); + gpiod_direction_output(bri->scl_gpiod, 1); + + if (bri->sda_gpiod == ERR_PTR(-EPROBE_DEFER)) + return -EPROBE_DEFER; + + if (IS_ERR(bri->sda_gpiod)) { + dev_info(dev, "missing sda gpio recovery information: %pe\n", + bri->sda_gpiod); return 0; } - if (IS_ERR(bri->pinctrl)) - return PTR_ERR(bri->pinctrl); bri->prepare_recovery = i2c_pxa_prepare_recovery; bri->unprepare_recovery = i2c_pxa_unprepare_recovery; + bri->recover_bus = i2c_generic_scl_recovery; i2c->adap.bus_recovery_info = bri; - return 0; + /* + * Claiming GPIOs can change the pinmux state, which confuses the + * pinctrl since pinctrl's idea of the current setting is unaffected + * by the pinmux change caused by claiming the GPIO. Work around that + * by switching pinctrl to the GPIO state here. We do it this way to + * avoid glitching the I2C bus. + */ + pinctrl_select_state(i2c->pinctrl, i2c->pinctrl_recovery); + + return pinctrl_select_state(i2c->pinctrl, i2c->pinctrl_default); } static int i2c_pxa_probe(struct platform_device *dev) diff --git a/drivers/i2c/busses/i2c-qcom-geni.c b/drivers/i2c/busses/i2c-qcom-geni.c index 229353e96e095..0a9d389df301b 100644 --- a/drivers/i2c/busses/i2c-qcom-geni.c +++ b/drivers/i2c/busses/i2c-qcom-geni.c @@ -857,6 +857,7 @@ static int geni_i2c_probe(struct platform_device *pdev) ret = geni_se_resources_on(&gi2c->se); if (ret) { dev_err(dev, "Error turning on resources %d\n", ret); + clk_disable_unprepare(gi2c->core_clk); return ret; } proto = geni_se_read_proto(&gi2c->se); @@ -876,8 +877,11 @@ static int geni_i2c_probe(struct platform_device *pdev) /* FIFO is disabled, so we can only use GPI DMA */ gi2c->gpi_mode = true; ret = setup_gpi_dma(gi2c); - if (ret) + if (ret) { + geni_se_resources_off(&gi2c->se); + clk_disable_unprepare(gi2c->core_clk); return dev_err_probe(dev, ret, "Failed to setup GPI DMA mode\n"); + } dev_dbg(dev, "Using GPI DMA mode for I2C\n"); } else { @@ -890,6 +894,8 @@ static int geni_i2c_probe(struct platform_device *pdev) if (!tx_depth) { dev_err(dev, "Invalid TX FIFO depth\n"); + geni_se_resources_off(&gi2c->se); + clk_disable_unprepare(gi2c->core_clk); return -EINVAL; } diff --git a/drivers/i2c/busses/i2c-sun6i-p2wi.c b/drivers/i2c/busses/i2c-sun6i-p2wi.c index fa6020dced595..85e035e7a1d75 100644 --- a/drivers/i2c/busses/i2c-sun6i-p2wi.c +++ b/drivers/i2c/busses/i2c-sun6i-p2wi.c @@ -201,6 +201,11 @@ static int p2wi_probe(struct platform_device *pdev) return -EINVAL; } + if (clk_freq == 0) { + dev_err(dev, "clock-frequency is set to 0 in DT\n"); + return -EINVAL; + } + if (of_get_child_count(np) > 1) { dev_err(dev, "P2WI only supports one slave device\n"); return -EINVAL; diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index 60746652fd525..7f30bcceebaed 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -931,8 +931,9 @@ int i2c_dev_irq_from_resources(const struct resource *resources, struct i2c_client * i2c_new_client_device(struct i2c_adapter *adap, struct i2c_board_info const *info) { - struct i2c_client *client; - int status; + struct i2c_client *client; + bool need_put = false; + int status; client = kzalloc(sizeof *client, GFP_KERNEL); if (!client) @@ -970,7 +971,6 @@ i2c_new_client_device(struct i2c_adapter *adap, struct i2c_board_info const *inf client->dev.fwnode = info->fwnode; device_enable_async_suspend(&client->dev); - i2c_dev_set_name(adap, client, info); if (info->swnode) { status = device_add_software_node(&client->dev, info->swnode); @@ -982,6 +982,7 @@ i2c_new_client_device(struct i2c_adapter *adap, struct i2c_board_info const *inf } } + i2c_dev_set_name(adap, client, info); status = device_register(&client->dev); if (status) goto out_remove_swnode; @@ -993,6 +994,7 @@ i2c_new_client_device(struct i2c_adapter *adap, struct i2c_board_info const *inf out_remove_swnode: device_remove_software_node(&client->dev); + need_put = true; out_err_put_of_node: of_node_put(info->of_node); out_err: @@ -1000,7 +1002,10 @@ i2c_new_client_device(struct i2c_adapter *adap, struct i2c_board_info const *inf "Failed to register i2c client %s at 0x%02x (%d)\n", client->name, client->addr, status); out_err_silent: - kfree(client); + if (need_put) + put_device(&client->dev); + else + kfree(client); return ERR_PTR(status); } EXPORT_SYMBOL_GPL(i2c_new_client_device); diff --git a/drivers/i2c/i2c-core.h b/drivers/i2c/i2c-core.h index 1247e6e6e9751..05b8b8dfa9bdd 100644 --- a/drivers/i2c/i2c-core.h +++ b/drivers/i2c/i2c-core.h @@ -29,7 +29,7 @@ int i2c_dev_irq_from_resources(const struct resource *resources, */ static inline bool i2c_in_atomic_xfer_mode(void) { - return system_state > SYSTEM_RUNNING && irqs_disabled(); + return system_state > SYSTEM_RUNNING && !preemptible(); } static inline int __i2c_lock_bus_helper(struct i2c_adapter *adap) diff --git a/drivers/i2c/i2c-dev.c b/drivers/i2c/i2c-dev.c index a01b59e3599b5..7d337380a05d9 100644 --- a/drivers/i2c/i2c-dev.c +++ b/drivers/i2c/i2c-dev.c @@ -450,8 +450,8 @@ static long i2cdev_ioctl(struct file *file, unsigned int cmd, unsigned long arg) if (rdwr_arg.nmsgs > I2C_RDWR_IOCTL_MAX_MSGS) return -EINVAL; - rdwr_pa = memdup_user(rdwr_arg.msgs, - rdwr_arg.nmsgs * sizeof(struct i2c_msg)); + rdwr_pa = memdup_array_user(rdwr_arg.msgs, + rdwr_arg.nmsgs, sizeof(struct i2c_msg)); if (IS_ERR(rdwr_pa)) return PTR_ERR(rdwr_pa); diff --git a/drivers/i3c/master/i3c-master-cdns.c b/drivers/i3c/master/i3c-master-cdns.c index 49551db71bc96..8f1fda3c7ac52 100644 --- a/drivers/i3c/master/i3c-master-cdns.c +++ b/drivers/i3c/master/i3c-master-cdns.c @@ -191,7 +191,7 @@ #define SLV_STATUS1_HJ_DIS BIT(18) #define SLV_STATUS1_MR_DIS BIT(17) #define SLV_STATUS1_PROT_ERR BIT(16) -#define SLV_STATUS1_DA(x) (((s) & GENMASK(15, 9)) >> 9) +#define SLV_STATUS1_DA(s) (((s) & GENMASK(15, 9)) >> 9) #define SLV_STATUS1_HAS_DA BIT(8) #define SLV_STATUS1_DDR_RX_FULL BIT(7) #define SLV_STATUS1_DDR_TX_FULL BIT(6) @@ -1623,13 +1623,13 @@ static int cdns_i3c_master_probe(struct platform_device *pdev) /* Device ID0 is reserved to describe this master. */ master->maxdevs = CONF_STATUS0_DEVS_NUM(val); master->free_rr_slots = GENMASK(master->maxdevs, 1); + master->caps.ibirfifodepth = CONF_STATUS0_IBIR_DEPTH(val); + master->caps.cmdrfifodepth = CONF_STATUS0_CMDR_DEPTH(val); val = readl(master->regs + CONF_STATUS1); master->caps.cmdfifodepth = CONF_STATUS1_CMD_DEPTH(val); master->caps.rxfifodepth = CONF_STATUS1_RX_DEPTH(val); master->caps.txfifodepth = CONF_STATUS1_TX_DEPTH(val); - master->caps.ibirfifodepth = CONF_STATUS0_IBIR_DEPTH(val); - master->caps.cmdrfifodepth = CONF_STATUS0_CMDR_DEPTH(val); spin_lock_init(&master->ibi.lock); master->ibi.num_slots = CONF_STATUS1_IBI_HW_RES(val); diff --git a/drivers/i3c/master/mipi-i3c-hci/dat_v1.c b/drivers/i3c/master/mipi-i3c-hci/dat_v1.c index 97bb49ff5b53b..47b9b4d4ed3fc 100644 --- a/drivers/i3c/master/mipi-i3c-hci/dat_v1.c +++ b/drivers/i3c/master/mipi-i3c-hci/dat_v1.c @@ -64,15 +64,17 @@ static int hci_dat_v1_init(struct i3c_hci *hci) return -EOPNOTSUPP; } - /* use a bitmap for faster free slot search */ - hci->DAT_data = bitmap_zalloc(hci->DAT_entries, GFP_KERNEL); - if (!hci->DAT_data) - return -ENOMEM; - - /* clear them */ - for (dat_idx = 0; dat_idx < hci->DAT_entries; dat_idx++) { - dat_w0_write(dat_idx, 0); - dat_w1_write(dat_idx, 0); + if (!hci->DAT_data) { + /* use a bitmap for faster free slot search */ + hci->DAT_data = bitmap_zalloc(hci->DAT_entries, GFP_KERNEL); + if (!hci->DAT_data) + return -ENOMEM; + + /* clear them */ + for (dat_idx = 0; dat_idx < hci->DAT_entries; dat_idx++) { + dat_w0_write(dat_idx, 0); + dat_w1_write(dat_idx, 0); + } } return 0; @@ -87,7 +89,13 @@ static void hci_dat_v1_cleanup(struct i3c_hci *hci) static int hci_dat_v1_alloc_entry(struct i3c_hci *hci) { unsigned int dat_idx; + int ret; + if (!hci->DAT_data) { + ret = hci_dat_v1_init(hci); + if (ret) + return ret; + } dat_idx = find_first_zero_bit(hci->DAT_data, hci->DAT_entries); if (dat_idx >= hci->DAT_entries) return -ENOENT; @@ -103,7 +111,8 @@ static void hci_dat_v1_free_entry(struct i3c_hci *hci, unsigned int dat_idx) { dat_w0_write(dat_idx, 0); dat_w1_write(dat_idx, 0); - __clear_bit(dat_idx, hci->DAT_data); + if (hci->DAT_data) + __clear_bit(dat_idx, hci->DAT_data); } static void hci_dat_v1_set_dynamic_addr(struct i3c_hci *hci, diff --git a/drivers/i3c/master/mipi-i3c-hci/dma.c b/drivers/i3c/master/mipi-i3c-hci/dma.c index 2990ac9eaade7..71b5dbe45c45c 100644 --- a/drivers/i3c/master/mipi-i3c-hci/dma.c +++ b/drivers/i3c/master/mipi-i3c-hci/dma.c @@ -734,7 +734,7 @@ static bool hci_dma_irq_handler(struct i3c_hci *hci, unsigned int mask) unsigned int i; bool handled = false; - for (i = 0; mask && i < 8; i++) { + for (i = 0; mask && i < rings->total; i++) { struct hci_rh_data *rh; u32 status; diff --git a/drivers/i3c/master/svc-i3c-master.c b/drivers/i3c/master/svc-i3c-master.c index 8f8295acdadb3..c395e52294140 100644 --- a/drivers/i3c/master/svc-i3c-master.c +++ b/drivers/i3c/master/svc-i3c-master.c @@ -93,6 +93,7 @@ #define SVC_I3C_MINTMASKED 0x098 #define SVC_I3C_MERRWARN 0x09C #define SVC_I3C_MERRWARN_NACK BIT(2) +#define SVC_I3C_MERRWARN_TIMEOUT BIT(20) #define SVC_I3C_MDMACTRL 0x0A0 #define SVC_I3C_MDATACTRL 0x0AC #define SVC_I3C_MDATACTRL_FLUSHTB BIT(0) @@ -175,6 +176,7 @@ struct svc_i3c_regs_save { * @ibi.slots: Available IBI slots * @ibi.tbq_slot: To be queued IBI slot * @ibi.lock: IBI lock + * @lock: Transfer lock, protect between IBI work thread and callbacks from master */ struct svc_i3c_master { struct i3c_master_controller base; @@ -203,6 +205,7 @@ struct svc_i3c_master { /* Prevent races within IBI handlers */ spinlock_t lock; } ibi; + struct mutex lock; }; /** @@ -225,6 +228,14 @@ static bool svc_i3c_master_error(struct svc_i3c_master *master) if (SVC_I3C_MSTATUS_ERRWARN(mstatus)) { merrwarn = readl(master->regs + SVC_I3C_MERRWARN); writel(merrwarn, master->regs + SVC_I3C_MERRWARN); + + /* Ignore timeout error */ + if (merrwarn & SVC_I3C_MERRWARN_TIMEOUT) { + dev_dbg(master->dev, "Warning condition: MSTATUS 0x%08x, MERRWARN 0x%08x\n", + mstatus, merrwarn); + return false; + } + dev_err(master->dev, "Error condition: MSTATUS 0x%08x, MERRWARN 0x%08x\n", mstatus, merrwarn); @@ -331,6 +342,7 @@ static int svc_i3c_master_handle_ibi(struct svc_i3c_master *master, struct i3c_ibi_slot *slot; unsigned int count; u32 mdatactrl; + int ret, val; u8 *buf; slot = i3c_generic_ibi_get_free_slot(data->ibi_pool); @@ -340,6 +352,13 @@ static int svc_i3c_master_handle_ibi(struct svc_i3c_master *master, slot->len = 0; buf = slot->data; + ret = readl_relaxed_poll_timeout(master->regs + SVC_I3C_MSTATUS, val, + SVC_I3C_MSTATUS_COMPLETE(val), 0, 1000); + if (ret) { + dev_err(master->dev, "Timeout when polling for COMPLETE\n"); + return ret; + } + while (SVC_I3C_MSTATUS_RXPEND(readl(master->regs + SVC_I3C_MSTATUS)) && slot->len < SVC_I3C_FIFO_SIZE) { mdatactrl = readl(master->regs + SVC_I3C_MDATACTRL); @@ -384,6 +403,7 @@ static void svc_i3c_master_ibi_work(struct work_struct *work) u32 status, val; int ret; + mutex_lock(&master->lock); /* Acknowledge the incoming interrupt with the AUTOIBI mechanism */ writel(SVC_I3C_MCTRL_REQUEST_AUTO_IBI | SVC_I3C_MCTRL_IBIRESP_AUTO, @@ -394,6 +414,7 @@ static void svc_i3c_master_ibi_work(struct work_struct *work) SVC_I3C_MSTATUS_IBIWON(val), 0, 1000); if (ret) { dev_err(master->dev, "Timeout when polling for IBIWON\n"); + svc_i3c_master_emit_stop(master); goto reenable_ibis; } @@ -460,12 +481,13 @@ static void svc_i3c_master_ibi_work(struct work_struct *work) reenable_ibis: svc_i3c_master_enable_interrupts(master, SVC_I3C_MINT_SLVSTART); + mutex_unlock(&master->lock); } static irqreturn_t svc_i3c_master_irq_handler(int irq, void *dev_id) { struct svc_i3c_master *master = (struct svc_i3c_master *)dev_id; - u32 active = readl(master->regs + SVC_I3C_MINTMASKED); + u32 active = readl(master->regs + SVC_I3C_MSTATUS); if (!SVC_I3C_MSTATUS_SLVSTART(active)) return IRQ_NONE; @@ -1007,6 +1029,9 @@ static int svc_i3c_master_xfer(struct svc_i3c_master *master, u32 reg; int ret; + /* clean SVC_I3C_MINT_IBIWON w1c bits */ + writel(SVC_I3C_MINT_IBIWON, master->regs + SVC_I3C_MSTATUS); + writel(SVC_I3C_MCTRL_REQUEST_START_ADDR | xfer_type | SVC_I3C_MCTRL_IBIRESP_NACK | @@ -1025,6 +1050,23 @@ static int svc_i3c_master_xfer(struct svc_i3c_master *master, goto emit_stop; } + /* + * According to I3C spec ver 1.1.1, 5.1.2.2.3 Consequence of Controller Starting a Frame + * with I3C Target Address. + * + * The I3C Controller normally should start a Frame, the Address may be arbitrated, and so + * the Controller shall monitor to see whether an In-Band Interrupt request, a Controller + * Role Request (i.e., Secondary Controller requests to become the Active Controller), or + * a Hot-Join Request has been made. + * + * If missed IBIWON check, the wrong data will be return. When IBIWON happen, return failure + * and yield the above events handler. + */ + if (SVC_I3C_MSTATUS_IBIWON(reg)) { + ret = -ENXIO; + goto emit_stop; + } + if (rnw) ret = svc_i3c_master_read(master, in, xfer_len); else @@ -1204,9 +1246,11 @@ static int svc_i3c_master_send_bdcast_ccc_cmd(struct svc_i3c_master *master, cmd->read_len = 0; cmd->continued = false; + mutex_lock(&master->lock); svc_i3c_master_enqueue_xfer(master, xfer); if (!wait_for_completion_timeout(&xfer->comp, msecs_to_jiffies(1000))) svc_i3c_master_dequeue_xfer(master, xfer); + mutex_unlock(&master->lock); ret = xfer->ret; kfree(buf); @@ -1250,9 +1294,11 @@ static int svc_i3c_master_send_direct_ccc_cmd(struct svc_i3c_master *master, cmd->read_len = read_len; cmd->continued = false; + mutex_lock(&master->lock); svc_i3c_master_enqueue_xfer(master, xfer); if (!wait_for_completion_timeout(&xfer->comp, msecs_to_jiffies(1000))) svc_i3c_master_dequeue_xfer(master, xfer); + mutex_unlock(&master->lock); if (cmd->read_len != xfer_len) ccc->dests[0].payload.len = cmd->read_len; @@ -1309,9 +1355,11 @@ static int svc_i3c_master_priv_xfers(struct i3c_dev_desc *dev, cmd->continued = (i + 1) < nxfers; } + mutex_lock(&master->lock); svc_i3c_master_enqueue_xfer(master, xfer); if (!wait_for_completion_timeout(&xfer->comp, msecs_to_jiffies(1000))) svc_i3c_master_dequeue_xfer(master, xfer); + mutex_unlock(&master->lock); ret = xfer->ret; svc_i3c_master_free_xfer(xfer); @@ -1347,9 +1395,11 @@ static int svc_i3c_master_i2c_xfers(struct i2c_dev_desc *dev, cmd->continued = (i + 1 < nxfers); } + mutex_lock(&master->lock); svc_i3c_master_enqueue_xfer(master, xfer); if (!wait_for_completion_timeout(&xfer->comp, msecs_to_jiffies(1000))) svc_i3c_master_dequeue_xfer(master, xfer); + mutex_unlock(&master->lock); ret = xfer->ret; svc_i3c_master_free_xfer(xfer); @@ -1540,6 +1590,8 @@ static int svc_i3c_master_probe(struct platform_device *pdev) INIT_WORK(&master->hj_work, svc_i3c_master_hj_work); INIT_WORK(&master->ibi_work, svc_i3c_master_ibi_work); + mutex_init(&master->lock); + ret = devm_request_irq(dev, master->irq, svc_i3c_master_irq_handler, IRQF_NO_SUSPEND, "svc-i3c-irq", master); if (ret) diff --git a/drivers/iio/accel/kionix-kx022a.c b/drivers/iio/accel/kionix-kx022a.c index 4ea3c6718ed49..971fc60efef01 100644 --- a/drivers/iio/accel/kionix-kx022a.c +++ b/drivers/iio/accel/kionix-kx022a.c @@ -273,17 +273,17 @@ static const unsigned int kx022a_odrs[] = { * (range / 2^bits) * g = (range / 2^bits) * 9.80665 m/s^2 * => KX022A uses 16 bit (HiRes mode - assume the low 8 bits are zeroed * in low-power mode(?) ) - * => +/-2G => 4 / 2^16 * 9,80665 * 10^6 (to scale to micro) - * => +/-2G - 598.550415 - * +/-4G - 1197.10083 - * +/-8G - 2394.20166 - * +/-16G - 4788.40332 + * => +/-2G => 4 / 2^16 * 9,80665 + * => +/-2G - 0.000598550415 + * +/-4G - 0.00119710083 + * +/-8G - 0.00239420166 + * +/-16G - 0.00478840332 */ static const int kx022a_scale_table[][2] = { - { 598, 550415 }, - { 1197, 100830 }, - { 2394, 201660 }, - { 4788, 403320 }, + { 0, 598550 }, + { 0, 1197101 }, + { 0, 2394202 }, + { 0, 4788403 }, }; static int kx022a_read_avail(struct iio_dev *indio_dev, @@ -302,7 +302,7 @@ static int kx022a_read_avail(struct iio_dev *indio_dev, *vals = (const int *)kx022a_scale_table; *length = ARRAY_SIZE(kx022a_scale_table) * ARRAY_SIZE(kx022a_scale_table[0]); - *type = IIO_VAL_INT_PLUS_MICRO; + *type = IIO_VAL_INT_PLUS_NANO; return IIO_AVAIL_LIST; default: return -EINVAL; @@ -366,6 +366,20 @@ static int kx022a_turn_on_unlock(struct kx022a_data *data) return ret; } +static int kx022a_write_raw_get_fmt(struct iio_dev *idev, + struct iio_chan_spec const *chan, + long mask) +{ + switch (mask) { + case IIO_CHAN_INFO_SCALE: + return IIO_VAL_INT_PLUS_NANO; + case IIO_CHAN_INFO_SAMP_FREQ: + return IIO_VAL_INT_PLUS_MICRO; + default: + return -EINVAL; + } +} + static int kx022a_write_raw(struct iio_dev *idev, struct iio_chan_spec const *chan, int val, int val2, long mask) @@ -510,7 +524,7 @@ static int kx022a_read_raw(struct iio_dev *idev, kx022a_reg2scale(regval, val, val2); - return IIO_VAL_INT_PLUS_MICRO; + return IIO_VAL_INT_PLUS_NANO; } return -EINVAL; @@ -712,6 +726,7 @@ static int kx022a_fifo_flush(struct iio_dev *idev, unsigned int samples) static const struct iio_info kx022a_info = { .read_raw = &kx022a_read_raw, .write_raw = &kx022a_write_raw, + .write_raw_get_fmt = &kx022a_write_raw_get_fmt, .read_avail = &kx022a_read_avail, .validate_trigger = iio_validate_own_trigger, diff --git a/drivers/iio/adc/imx93_adc.c b/drivers/iio/adc/imx93_adc.c index dce9ec91e4a77..512d7b95b08e6 100644 --- a/drivers/iio/adc/imx93_adc.c +++ b/drivers/iio/adc/imx93_adc.c @@ -93,6 +93,10 @@ static const struct iio_chan_spec imx93_adc_iio_channels[] = { IMX93_ADC_CHAN(1), IMX93_ADC_CHAN(2), IMX93_ADC_CHAN(3), + IMX93_ADC_CHAN(4), + IMX93_ADC_CHAN(5), + IMX93_ADC_CHAN(6), + IMX93_ADC_CHAN(7), }; static void imx93_adc_power_down(struct imx93_adc *adc) diff --git a/drivers/iio/adc/meson_saradc.c b/drivers/iio/adc/meson_saradc.c index 320e3e7e3d4d4..57cfabe80c826 100644 --- a/drivers/iio/adc/meson_saradc.c +++ b/drivers/iio/adc/meson_saradc.c @@ -1239,6 +1239,20 @@ static const struct meson_sar_adc_param meson_sar_adc_gxl_param = { .cmv_select = 1, }; +static const struct meson_sar_adc_param meson_sar_adc_axg_param = { + .has_bl30_integration = true, + .clock_rate = 1200000, + .bandgap_reg = MESON_SAR_ADC_REG11, + .regmap_config = &meson_sar_adc_regmap_config_gxbb, + .resolution = 12, + .disable_ring_counter = 1, + .has_reg11 = true, + .vref_volatge = 1, + .has_vref_select = true, + .vref_select = VREF_VDDA, + .cmv_select = 1, +}; + static const struct meson_sar_adc_param meson_sar_adc_g12a_param = { .has_bl30_integration = false, .clock_rate = 1200000, @@ -1283,7 +1297,7 @@ static const struct meson_sar_adc_data meson_sar_adc_gxm_data = { }; static const struct meson_sar_adc_data meson_sar_adc_axg_data = { - .param = &meson_sar_adc_gxl_param, + .param = &meson_sar_adc_axg_param, .name = "meson-axg-saradc", }; diff --git a/drivers/iio/adc/stm32-adc-core.c b/drivers/iio/adc/stm32-adc-core.c index 2f082006550fd..bbd5bdd732f01 100644 --- a/drivers/iio/adc/stm32-adc-core.c +++ b/drivers/iio/adc/stm32-adc-core.c @@ -708,6 +708,8 @@ static int stm32_adc_probe(struct platform_device *pdev) struct stm32_adc_priv *priv; struct device *dev = &pdev->dev; struct device_node *np = pdev->dev.of_node; + const struct of_device_id *of_id; + struct resource *res; u32 max_rate; int ret; @@ -720,8 +722,11 @@ static int stm32_adc_probe(struct platform_device *pdev) return -ENOMEM; platform_set_drvdata(pdev, &priv->common); - priv->cfg = (const struct stm32_adc_priv_cfg *) - of_match_device(dev->driver->of_match_table, dev)->data; + of_id = of_match_device(dev->driver->of_match_table, dev); + if (!of_id) + return -ENODEV; + + priv->cfg = (const struct stm32_adc_priv_cfg *)of_id->data; priv->nb_adc_max = priv->cfg->num_adcs; spin_lock_init(&priv->common.lock); diff --git a/drivers/iio/adc/ti_am335x_adc.c b/drivers/iio/adc/ti_am335x_adc.c index 8db7a01cb5fbf..5f87959869954 100644 --- a/drivers/iio/adc/ti_am335x_adc.c +++ b/drivers/iio/adc/ti_am335x_adc.c @@ -670,8 +670,10 @@ static int tiadc_probe(struct platform_device *pdev) platform_set_drvdata(pdev, indio_dev); err = tiadc_request_dma(pdev, adc_dev); - if (err && err == -EPROBE_DEFER) + if (err && err != -ENODEV) { + dev_err_probe(&pdev->dev, err, "DMA request failed\n"); goto err_dma; + } return 0; diff --git a/drivers/iio/buffer/industrialio-triggered-buffer.c b/drivers/iio/buffer/industrialio-triggered-buffer.c index c7671b1f5eada..c06515987e7a7 100644 --- a/drivers/iio/buffer/industrialio-triggered-buffer.c +++ b/drivers/iio/buffer/industrialio-triggered-buffer.c @@ -46,6 +46,16 @@ int iio_triggered_buffer_setup_ext(struct iio_dev *indio_dev, struct iio_buffer *buffer; int ret; + /* + * iio_triggered_buffer_cleanup() assumes that the buffer allocated here + * is assigned to indio_dev->buffer but this is only the case if this + * function is the first caller to iio_device_attach_buffer(). If + * indio_dev->buffer is already set then we can't proceed otherwise the + * cleanup function will try to free a buffer that was not allocated here. + */ + if (indio_dev->buffer) + return -EADDRINUSE; + buffer = iio_kfifo_allocate(); if (!buffer) { ret = -ENOMEM; diff --git a/drivers/iio/common/ms_sensors/ms_sensors_i2c.c b/drivers/iio/common/ms_sensors/ms_sensors_i2c.c index 6633b35a94e69..9c9bc77003c7f 100644 --- a/drivers/iio/common/ms_sensors/ms_sensors_i2c.c +++ b/drivers/iio/common/ms_sensors/ms_sensors_i2c.c @@ -15,8 +15,8 @@ /* Conversion times in us */ static const u16 ms_sensors_ht_t_conversion_time[] = { 50000, 25000, 13000, 7000 }; -static const u16 ms_sensors_ht_h_conversion_time[] = { 16000, 3000, - 5000, 8000 }; +static const u16 ms_sensors_ht_h_conversion_time[] = { 16000, 5000, + 3000, 8000 }; static const u16 ms_sensors_tp_conversion_time[] = { 500, 1100, 2100, 4100, 8220, 16440 }; diff --git a/drivers/iio/imu/adis16475.c b/drivers/iio/imu/adis16475.c index 17275a53ca2cd..0a9951a502101 100644 --- a/drivers/iio/imu/adis16475.c +++ b/drivers/iio/imu/adis16475.c @@ -1244,50 +1244,6 @@ static int adis16475_config_irq_pin(struct adis16475 *st) return 0; } -static const struct of_device_id adis16475_of_match[] = { - { .compatible = "adi,adis16470", - .data = &adis16475_chip_info[ADIS16470] }, - { .compatible = "adi,adis16475-1", - .data = &adis16475_chip_info[ADIS16475_1] }, - { .compatible = "adi,adis16475-2", - .data = &adis16475_chip_info[ADIS16475_2] }, - { .compatible = "adi,adis16475-3", - .data = &adis16475_chip_info[ADIS16475_3] }, - { .compatible = "adi,adis16477-1", - .data = &adis16475_chip_info[ADIS16477_1] }, - { .compatible = "adi,adis16477-2", - .data = &adis16475_chip_info[ADIS16477_2] }, - { .compatible = "adi,adis16477-3", - .data = &adis16475_chip_info[ADIS16477_3] }, - { .compatible = "adi,adis16465-1", - .data = &adis16475_chip_info[ADIS16465_1] }, - { .compatible = "adi,adis16465-2", - .data = &adis16475_chip_info[ADIS16465_2] }, - { .compatible = "adi,adis16465-3", - .data = &adis16475_chip_info[ADIS16465_3] }, - { .compatible = "adi,adis16467-1", - .data = &adis16475_chip_info[ADIS16467_1] }, - { .compatible = "adi,adis16467-2", - .data = &adis16475_chip_info[ADIS16467_2] }, - { .compatible = "adi,adis16467-3", - .data = &adis16475_chip_info[ADIS16467_3] }, - { .compatible = "adi,adis16500", - .data = &adis16475_chip_info[ADIS16500] }, - { .compatible = "adi,adis16505-1", - .data = &adis16475_chip_info[ADIS16505_1] }, - { .compatible = "adi,adis16505-2", - .data = &adis16475_chip_info[ADIS16505_2] }, - { .compatible = "adi,adis16505-3", - .data = &adis16475_chip_info[ADIS16505_3] }, - { .compatible = "adi,adis16507-1", - .data = &adis16475_chip_info[ADIS16507_1] }, - { .compatible = "adi,adis16507-2", - .data = &adis16475_chip_info[ADIS16507_2] }, - { .compatible = "adi,adis16507-3", - .data = &adis16475_chip_info[ADIS16507_3] }, - { }, -}; -MODULE_DEVICE_TABLE(of, adis16475_of_match); static int adis16475_probe(struct spi_device *spi) { @@ -1301,7 +1257,7 @@ static int adis16475_probe(struct spi_device *spi) st = iio_priv(indio_dev); - st->info = device_get_match_data(&spi->dev); + st->info = spi_get_device_match_data(spi); if (!st->info) return -EINVAL; @@ -1341,12 +1297,83 @@ static int adis16475_probe(struct spi_device *spi) return 0; } +static const struct of_device_id adis16475_of_match[] = { + { .compatible = "adi,adis16470", + .data = &adis16475_chip_info[ADIS16470] }, + { .compatible = "adi,adis16475-1", + .data = &adis16475_chip_info[ADIS16475_1] }, + { .compatible = "adi,adis16475-2", + .data = &adis16475_chip_info[ADIS16475_2] }, + { .compatible = "adi,adis16475-3", + .data = &adis16475_chip_info[ADIS16475_3] }, + { .compatible = "adi,adis16477-1", + .data = &adis16475_chip_info[ADIS16477_1] }, + { .compatible = "adi,adis16477-2", + .data = &adis16475_chip_info[ADIS16477_2] }, + { .compatible = "adi,adis16477-3", + .data = &adis16475_chip_info[ADIS16477_3] }, + { .compatible = "adi,adis16465-1", + .data = &adis16475_chip_info[ADIS16465_1] }, + { .compatible = "adi,adis16465-2", + .data = &adis16475_chip_info[ADIS16465_2] }, + { .compatible = "adi,adis16465-3", + .data = &adis16475_chip_info[ADIS16465_3] }, + { .compatible = "adi,adis16467-1", + .data = &adis16475_chip_info[ADIS16467_1] }, + { .compatible = "adi,adis16467-2", + .data = &adis16475_chip_info[ADIS16467_2] }, + { .compatible = "adi,adis16467-3", + .data = &adis16475_chip_info[ADIS16467_3] }, + { .compatible = "adi,adis16500", + .data = &adis16475_chip_info[ADIS16500] }, + { .compatible = "adi,adis16505-1", + .data = &adis16475_chip_info[ADIS16505_1] }, + { .compatible = "adi,adis16505-2", + .data = &adis16475_chip_info[ADIS16505_2] }, + { .compatible = "adi,adis16505-3", + .data = &adis16475_chip_info[ADIS16505_3] }, + { .compatible = "adi,adis16507-1", + .data = &adis16475_chip_info[ADIS16507_1] }, + { .compatible = "adi,adis16507-2", + .data = &adis16475_chip_info[ADIS16507_2] }, + { .compatible = "adi,adis16507-3", + .data = &adis16475_chip_info[ADIS16507_3] }, + { }, +}; +MODULE_DEVICE_TABLE(of, adis16475_of_match); + +static const struct spi_device_id adis16475_ids[] = { + { "adis16470", (kernel_ulong_t)&adis16475_chip_info[ADIS16470] }, + { "adis16475-1", (kernel_ulong_t)&adis16475_chip_info[ADIS16475_1] }, + { "adis16475-2", (kernel_ulong_t)&adis16475_chip_info[ADIS16475_2] }, + { "adis16475-3", (kernel_ulong_t)&adis16475_chip_info[ADIS16475_3] }, + { "adis16477-1", (kernel_ulong_t)&adis16475_chip_info[ADIS16477_1] }, + { "adis16477-2", (kernel_ulong_t)&adis16475_chip_info[ADIS16477_2] }, + { "adis16477-3", (kernel_ulong_t)&adis16475_chip_info[ADIS16477_3] }, + { "adis16465-1", (kernel_ulong_t)&adis16475_chip_info[ADIS16465_1] }, + { "adis16465-2", (kernel_ulong_t)&adis16475_chip_info[ADIS16465_2] }, + { "adis16465-3", (kernel_ulong_t)&adis16475_chip_info[ADIS16465_3] }, + { "adis16467-1", (kernel_ulong_t)&adis16475_chip_info[ADIS16467_1] }, + { "adis16467-2", (kernel_ulong_t)&adis16475_chip_info[ADIS16467_2] }, + { "adis16467-3", (kernel_ulong_t)&adis16475_chip_info[ADIS16467_3] }, + { "adis16500", (kernel_ulong_t)&adis16475_chip_info[ADIS16500] }, + { "adis16505-1", (kernel_ulong_t)&adis16475_chip_info[ADIS16505_1] }, + { "adis16505-2", (kernel_ulong_t)&adis16475_chip_info[ADIS16505_2] }, + { "adis16505-3", (kernel_ulong_t)&adis16475_chip_info[ADIS16505_3] }, + { "adis16507-1", (kernel_ulong_t)&adis16475_chip_info[ADIS16507_1] }, + { "adis16507-2", (kernel_ulong_t)&adis16475_chip_info[ADIS16507_2] }, + { "adis16507-3", (kernel_ulong_t)&adis16475_chip_info[ADIS16507_3] }, + { } +}; +MODULE_DEVICE_TABLE(spi, adis16475_ids); + static struct spi_driver adis16475_driver = { .driver = { .name = "adis16475", .of_match_table = adis16475_of_match, }, .probe = adis16475_probe, + .id_table = adis16475_ids, }; module_spi_driver(adis16475_driver); diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c index 29f906c884bd8..a9a5fb266ef13 100644 --- a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c +++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c @@ -749,13 +749,13 @@ inv_mpu6050_read_raw(struct iio_dev *indio_dev, ret = inv_mpu6050_sensor_show(st, st->reg->gyro_offset, chan->channel2, val); mutex_unlock(&st->lock); - return IIO_VAL_INT; + return ret; case IIO_ACCEL: mutex_lock(&st->lock); ret = inv_mpu6050_sensor_show(st, st->reg->accl_offset, chan->channel2, val); mutex_unlock(&st->lock); - return IIO_VAL_INT; + return ret; default: return -EINVAL; diff --git a/drivers/iio/magnetometer/tmag5273.c b/drivers/iio/magnetometer/tmag5273.c index c5e5c4ad681e6..e8c4ca142d21d 100644 --- a/drivers/iio/magnetometer/tmag5273.c +++ b/drivers/iio/magnetometer/tmag5273.c @@ -356,7 +356,7 @@ static int tmag5273_read_raw(struct iio_dev *indio_dev, case IIO_CHAN_INFO_OFFSET: switch (chan->type) { case IIO_TEMP: - *val = -266314; + *val = -16005; return IIO_VAL_INT; default: return -EINVAL; diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c index f9ab671c8eda5..07c571c7b6999 100644 --- a/drivers/infiniband/core/umem.c +++ b/drivers/infiniband/core/umem.c @@ -96,12 +96,6 @@ unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem, return page_size; } - /* rdma_for_each_block() has a bug if the page size is smaller than the - * page size used to build the umem. For now prevent smaller page sizes - * from being returned. - */ - pgsz_bitmap &= GENMASK(BITS_PER_LONG - 1, PAGE_SHIFT); - /* The best result is the smallest page size that results in the minimum * number of required pages. Compute the largest page size that could * work based on VA address bits that don't change. diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c index 41ff5595c8606..186ed3c22ec9e 100644 --- a/drivers/infiniband/core/verbs.c +++ b/drivers/infiniband/core/verbs.c @@ -1968,7 +1968,7 @@ int ib_get_eth_speed(struct ib_device *dev, u32 port_num, u16 *speed, u8 *width) int rc; u32 netdev_speed; struct net_device *netdev; - struct ethtool_link_ksettings lksettings; + struct ethtool_link_ksettings lksettings = {}; if (rdma_port_get_link_layer(dev, port_num) != IB_LINK_LAYER_ETHERNET) return -EINVAL; diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index c9066aade4125..039801d93ed8a 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -71,7 +71,7 @@ static char version[] = BNXT_RE_DESC "\n"; MODULE_AUTHOR("Eddie Wai "); -MODULE_DESCRIPTION(BNXT_RE_DESC " Driver"); +MODULE_DESCRIPTION(BNXT_RE_DESC); MODULE_LICENSE("Dual BSD/GPL"); /* globals */ diff --git a/drivers/infiniband/hw/hfi1/pcie.c b/drivers/infiniband/hw/hfi1/pcie.c index 08732e1ac9662..c132a9c073bff 100644 --- a/drivers/infiniband/hw/hfi1/pcie.c +++ b/drivers/infiniband/hw/hfi1/pcie.c @@ -3,6 +3,7 @@ * Copyright(c) 2015 - 2019 Intel Corporation. */ +#include #include #include #include @@ -210,12 +211,6 @@ static u32 extract_speed(u16 linkstat) return speed; } -/* return the PCIe link speed from the given link status */ -static u32 extract_width(u16 linkstat) -{ - return (linkstat & PCI_EXP_LNKSTA_NLW) >> PCI_EXP_LNKSTA_NLW_SHIFT; -} - /* read the link status and set dd->{lbus_width,lbus_speed,lbus_info} */ static void update_lbus_info(struct hfi1_devdata *dd) { @@ -228,7 +223,7 @@ static void update_lbus_info(struct hfi1_devdata *dd) return; } - dd->lbus_width = extract_width(linkstat); + dd->lbus_width = FIELD_GET(PCI_EXP_LNKSTA_NLW, linkstat); dd->lbus_speed = extract_speed(linkstat); snprintf(dd->lbus_info, sizeof(dd->lbus_info), "PCIe,%uMHz,x%u", dd->lbus_speed, dd->lbus_width); diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index 58d14f1562b9a..486d635b6e3ab 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -4755,10 +4755,15 @@ static int check_cong_type(struct ib_qp *ibqp, cong_alg->wnd_mode_sel = WND_LIMIT; break; default: - ibdev_err(&hr_dev->ib_dev, - "error type(%u) for congestion selection.\n", - hr_dev->caps.cong_type); - return -EINVAL; + ibdev_warn(&hr_dev->ib_dev, + "invalid type(%u) for congestion selection.\n", + hr_dev->caps.cong_type); + hr_dev->caps.cong_type = CONG_TYPE_DCQCN; + cong_alg->alg_sel = CONG_DCQCN; + cong_alg->alg_sub_sel = UNSUPPORT_CONG_LEVEL; + cong_alg->dip_vld = DIP_INVALID; + cong_alg->wnd_mode_sel = WND_LIMIT; + break; } return 0; diff --git a/drivers/infiniband/hw/irdma/hw.c b/drivers/infiniband/hw/irdma/hw.c index 7cbdd5433dba5..564c9188e1f84 100644 --- a/drivers/infiniband/hw/irdma/hw.c +++ b/drivers/infiniband/hw/irdma/hw.c @@ -321,7 +321,11 @@ static void irdma_process_aeq(struct irdma_pci_f *rf) break; case IRDMA_AE_QP_SUSPEND_COMPLETE: if (iwqp->iwdev->vsi.tc_change_pending) { - atomic_dec(&iwqp->sc_qp.vsi->qp_suspend_reqs); + if (!atomic_dec_return(&qp->vsi->qp_suspend_reqs)) + wake_up(&iwqp->iwdev->suspend_wq); + } + if (iwqp->suspend_pending) { + iwqp->suspend_pending = false; wake_up(&iwqp->iwdev->suspend_wq); } break; @@ -581,9 +585,6 @@ static void irdma_destroy_cqp(struct irdma_pci_f *rf) struct irdma_cqp *cqp = &rf->cqp; int status = 0; - if (rf->cqp_cmpl_wq) - destroy_workqueue(rf->cqp_cmpl_wq); - status = irdma_sc_cqp_destroy(dev->cqp); if (status) ibdev_dbg(to_ibdev(dev), "ERR: Destroy CQP failed %d\n", status); @@ -748,6 +749,9 @@ static void irdma_destroy_ccq(struct irdma_pci_f *rf) struct irdma_ccq *ccq = &rf->ccq; int status = 0; + if (rf->cqp_cmpl_wq) + destroy_workqueue(rf->cqp_cmpl_wq); + if (!rf->reset) status = irdma_sc_ccq_destroy(dev->ccq, 0, true); if (status) @@ -1180,7 +1184,6 @@ static int irdma_create_ceq(struct irdma_pci_f *rf, struct irdma_ceq *iwceq, int status; struct irdma_ceq_init_info info = {}; struct irdma_sc_dev *dev = &rf->sc_dev; - u64 scratch; u32 ceq_size; info.ceq_id = ceq_id; @@ -1201,14 +1204,13 @@ static int irdma_create_ceq(struct irdma_pci_f *rf, struct irdma_ceq *iwceq, iwceq->sc_ceq.ceq_id = ceq_id; info.dev = dev; info.vsi = vsi; - scratch = (uintptr_t)&rf->cqp.sc_cqp; status = irdma_sc_ceq_init(&iwceq->sc_ceq, &info); if (!status) { if (dev->ceq_valid) status = irdma_cqp_ceq_cmd(&rf->sc_dev, &iwceq->sc_ceq, IRDMA_OP_CEQ_CREATE); else - status = irdma_sc_cceq_create(&iwceq->sc_ceq, scratch); + status = irdma_sc_cceq_create(&iwceq->sc_ceq, 0); } if (status) { diff --git a/drivers/infiniband/hw/irdma/main.c b/drivers/infiniband/hw/irdma/main.c index 514453777e07d..be1030d1adfaf 100644 --- a/drivers/infiniband/hw/irdma/main.c +++ b/drivers/infiniband/hw/irdma/main.c @@ -48,7 +48,7 @@ static void irdma_prep_tc_change(struct irdma_device *iwdev) /* Wait for all qp's to suspend */ wait_event_timeout(iwdev->suspend_wq, !atomic_read(&iwdev->vsi.qp_suspend_reqs), - IRDMA_EVENT_TIMEOUT); + msecs_to_jiffies(IRDMA_EVENT_TIMEOUT_MS)); irdma_ws_reset(&iwdev->vsi); } diff --git a/drivers/infiniband/hw/irdma/main.h b/drivers/infiniband/hw/irdma/main.h index 82fc5f5b002c0..cbf0db72e1088 100644 --- a/drivers/infiniband/hw/irdma/main.h +++ b/drivers/infiniband/hw/irdma/main.h @@ -78,7 +78,7 @@ extern struct auxiliary_driver i40iw_auxiliary_drv; #define MAX_DPC_ITERATIONS 128 -#define IRDMA_EVENT_TIMEOUT 50000 +#define IRDMA_EVENT_TIMEOUT_MS 5000 #define IRDMA_VCHNL_EVENT_TIMEOUT 100000 #define IRDMA_RST_TIMEOUT_HZ 4 diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c index 3eb7a7a3a975d..2f1bedd3a5201 100644 --- a/drivers/infiniband/hw/irdma/verbs.c +++ b/drivers/infiniband/hw/irdma/verbs.c @@ -1157,6 +1157,21 @@ static u8 irdma_roce_get_vlan_prio(const struct ib_gid_attr *attr, u8 prio) return prio; } +static int irdma_wait_for_suspend(struct irdma_qp *iwqp) +{ + if (!wait_event_timeout(iwqp->iwdev->suspend_wq, + !iwqp->suspend_pending, + msecs_to_jiffies(IRDMA_EVENT_TIMEOUT_MS))) { + iwqp->suspend_pending = false; + ibdev_warn(&iwqp->iwdev->ibdev, + "modify_qp timed out waiting for suspend. qp_id = %d, last_ae = 0x%x\n", + iwqp->ibqp.qp_num, iwqp->last_aeq); + return -EBUSY; + } + + return 0; +} + /** * irdma_modify_qp_roce - modify qp request * @ibqp: qp's pointer for modify @@ -1420,17 +1435,11 @@ int irdma_modify_qp_roce(struct ib_qp *ibqp, struct ib_qp_attr *attr, info.next_iwarp_state = IRDMA_QP_STATE_SQD; issue_modify_qp = 1; + iwqp->suspend_pending = true; break; case IB_QPS_SQE: case IB_QPS_ERR: case IB_QPS_RESET: - if (iwqp->iwarp_state == IRDMA_QP_STATE_RTS) { - spin_unlock_irqrestore(&iwqp->lock, flags); - info.next_iwarp_state = IRDMA_QP_STATE_SQD; - irdma_hw_modify_qp(iwdev, iwqp, &info, true); - spin_lock_irqsave(&iwqp->lock, flags); - } - if (iwqp->iwarp_state == IRDMA_QP_STATE_ERROR) { spin_unlock_irqrestore(&iwqp->lock, flags); if (udata && udata->inlen) { @@ -1467,6 +1476,11 @@ int irdma_modify_qp_roce(struct ib_qp *ibqp, struct ib_qp_attr *attr, ctx_info->rem_endpoint_idx = udp_info->arp_idx; if (irdma_hw_modify_qp(iwdev, iwqp, &info, true)) return -EINVAL; + if (info.next_iwarp_state == IRDMA_QP_STATE_SQD) { + ret = irdma_wait_for_suspend(iwqp); + if (ret) + return ret; + } spin_lock_irqsave(&iwqp->lock, flags); if (iwqp->iwarp_state == info.curr_iwarp_state) { iwqp->iwarp_state = info.next_iwarp_state; @@ -2889,7 +2903,7 @@ static struct irdma_mr *irdma_alloc_iwmr(struct ib_umem *region, iwmr->type = reg_type; pgsz_bitmap = (reg_type == IRDMA_MEMREG_TYPE_MEM) ? - iwdev->rf->sc_dev.hw_attrs.page_size_cap : PAGE_SIZE; + iwdev->rf->sc_dev.hw_attrs.page_size_cap : SZ_4K; iwmr->page_size = ib_umem_find_best_pgsz(region, pgsz_bitmap, virt); if (unlikely(!iwmr->page_size)) { @@ -2921,6 +2935,11 @@ static int irdma_reg_user_mr_type_qp(struct irdma_mem_reg_req req, int err; u8 lvl; + /* iWarp: Catch page not starting on OS page boundary */ + if (!rdma_protocol_roce(&iwdev->ibdev, 1) && + ib_umem_offset(iwmr->region)) + return -EINVAL; + total = req.sq_pages + req.rq_pages + 1; if (total > iwmr->page_cnt) return -EINVAL; diff --git a/drivers/infiniband/hw/irdma/verbs.h b/drivers/infiniband/hw/irdma/verbs.h index 5d7b983f47a24..20297a14c9a61 100644 --- a/drivers/infiniband/hw/irdma/verbs.h +++ b/drivers/infiniband/hw/irdma/verbs.h @@ -196,6 +196,7 @@ struct irdma_qp { u8 flush_issued : 1; u8 sig_all : 1; u8 pau_mode : 1; + u8 suspend_pending : 1; u8 rsvd : 1; u8 iwarp_state; u16 term_sq_flush_code; diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 5d963abb7e609..102ead497196c 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include #include @@ -3175,6 +3176,13 @@ static void mlx5_ib_unbind_slave_port(struct mlx5_ib_dev *ibdev, lockdep_assert_held(&mlx5_ib_multiport_mutex); + mlx5_core_mp_event_replay(ibdev->mdev, + MLX5_DRIVER_EVENT_AFFILIATION_REMOVED, + NULL); + mlx5_core_mp_event_replay(mpi->mdev, + MLX5_DRIVER_EVENT_AFFILIATION_REMOVED, + NULL); + mlx5_ib_cleanup_cong_debugfs(ibdev, port_num); spin_lock(&port->mp.mpi_lock); @@ -3226,6 +3234,7 @@ static bool mlx5_ib_bind_slave_port(struct mlx5_ib_dev *ibdev, struct mlx5_ib_multiport_info *mpi) { u32 port_num = mlx5_core_native_port_num(mpi->mdev) - 1; + u64 key; int err; lockdep_assert_held(&mlx5_ib_multiport_mutex); @@ -3254,6 +3263,14 @@ static bool mlx5_ib_bind_slave_port(struct mlx5_ib_dev *ibdev, mlx5_ib_init_cong_debugfs(ibdev, port_num); + key = mpi->mdev->priv.adev_idx; + mlx5_core_mp_event_replay(mpi->mdev, + MLX5_DRIVER_EVENT_AFFILIATION_DONE, + &key); + mlx5_core_mp_event_replay(ibdev->mdev, + MLX5_DRIVER_EVENT_AFFILIATION_DONE, + &key); + return true; unbind: diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.c b/drivers/infiniband/ulp/rtrs/rtrs-clt.c index b6ee801fd0ffb..1aee62aa1515d 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs-clt.c +++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.c @@ -384,7 +384,7 @@ static void complete_rdma_req(struct rtrs_clt_io_req *req, int errno, struct rtrs_clt_path *clt_path; int err; - if (WARN_ON(!req->in_use)) + if (!req->in_use) return; if (WARN_ON(!req->con)) return; @@ -1694,7 +1694,7 @@ static int create_con_cq_qp(struct rtrs_clt_con *con) clt_path->s.dev_ref++; max_send_wr = min_t(int, wr_limit, /* QD * (REQ + RSP + FR REGS or INVS) + drain */ - clt_path->queue_depth * 3 + 1); + clt_path->queue_depth * 4 + 1); max_recv_wr = min_t(int, wr_limit, clt_path->queue_depth * 3 + 1); max_send_sge = 2; @@ -2345,8 +2345,6 @@ static int init_conns(struct rtrs_clt_path *clt_path) if (err) goto destroy; - rtrs_start_hb(&clt_path->s); - return 0; destroy: @@ -2620,6 +2618,7 @@ static int init_path(struct rtrs_clt_path *clt_path) goto out; } rtrs_clt_path_up(clt_path); + rtrs_start_hb(&clt_path->s); out: mutex_unlock(&clt_path->init_mutex); diff --git a/drivers/infiniband/ulp/rtrs/rtrs-srv.c b/drivers/infiniband/ulp/rtrs/rtrs-srv.c index 75e56604e4628..1d33efb8fb03b 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs-srv.c +++ b/drivers/infiniband/ulp/rtrs/rtrs-srv.c @@ -65,8 +65,9 @@ static bool rtrs_srv_change_state(struct rtrs_srv_path *srv_path, { enum rtrs_srv_state old_state; bool changed = false; + unsigned long flags; - spin_lock_irq(&srv_path->state_lock); + spin_lock_irqsave(&srv_path->state_lock, flags); old_state = srv_path->state; switch (new_state) { case RTRS_SRV_CONNECTED: @@ -87,7 +88,7 @@ static bool rtrs_srv_change_state(struct rtrs_srv_path *srv_path, } if (changed) srv_path->state = new_state; - spin_unlock_irq(&srv_path->state_lock); + spin_unlock_irqrestore(&srv_path->state_lock, flags); return changed; } @@ -550,7 +551,10 @@ static void unmap_cont_bufs(struct rtrs_srv_path *srv_path) struct rtrs_srv_mr *srv_mr; srv_mr = &srv_path->mrs[i]; - rtrs_iu_free(srv_mr->iu, srv_path->s.dev->ib_dev, 1); + + if (always_invalidate) + rtrs_iu_free(srv_mr->iu, srv_path->s.dev->ib_dev, 1); + ib_dereg_mr(srv_mr->mr); ib_dma_unmap_sg(srv_path->s.dev->ib_dev, srv_mr->sgt.sgl, srv_mr->sgt.nents, DMA_BIDIRECTIONAL); @@ -709,20 +713,23 @@ static void rtrs_srv_info_rsp_done(struct ib_cq *cq, struct ib_wc *wc) WARN_ON(wc->opcode != IB_WC_SEND); } -static void rtrs_srv_path_up(struct rtrs_srv_path *srv_path) +static int rtrs_srv_path_up(struct rtrs_srv_path *srv_path) { struct rtrs_srv_sess *srv = srv_path->srv; struct rtrs_srv_ctx *ctx = srv->ctx; - int up; + int up, ret = 0; mutex_lock(&srv->paths_ev_mutex); up = ++srv->paths_up; if (up == 1) - ctx->ops.link_ev(srv, RTRS_SRV_LINK_EV_CONNECTED, NULL); + ret = ctx->ops.link_ev(srv, RTRS_SRV_LINK_EV_CONNECTED, NULL); mutex_unlock(&srv->paths_ev_mutex); /* Mark session as established */ - srv_path->established = true; + if (!ret) + srv_path->established = true; + + return ret; } static void rtrs_srv_path_down(struct rtrs_srv_path *srv_path) @@ -851,7 +858,12 @@ static int process_info_req(struct rtrs_srv_con *con, goto iu_free; kobject_get(&srv_path->kobj); get_device(&srv_path->srv->dev); - rtrs_srv_change_state(srv_path, RTRS_SRV_CONNECTED); + err = rtrs_srv_change_state(srv_path, RTRS_SRV_CONNECTED); + if (!err) { + rtrs_err(s, "rtrs_srv_change_state(), err: %d\n", err); + goto iu_free; + } + rtrs_srv_start_hb(srv_path); /* @@ -860,7 +872,11 @@ static int process_info_req(struct rtrs_srv_con *con, * all connections are successfully established. Thus, simply notify * listener with a proper event if we are the first path. */ - rtrs_srv_path_up(srv_path); + err = rtrs_srv_path_up(srv_path); + if (err) { + rtrs_err(s, "rtrs_srv_path_up(), err: %d\n", err); + goto iu_free; + } ib_dma_sync_single_for_device(srv_path->s.dev->ib_dev, tx_iu->dma_addr, @@ -1516,7 +1532,6 @@ static void rtrs_srv_close_work(struct work_struct *work) srv_path = container_of(work, typeof(*srv_path), close_work); - rtrs_srv_destroy_path_files(srv_path); rtrs_srv_stop_hb(srv_path); for (i = 0; i < srv_path->s.con_num; i++) { @@ -1536,6 +1551,8 @@ static void rtrs_srv_close_work(struct work_struct *work) /* Wait for all completion */ wait_for_completion(&srv_path->complete_done); + rtrs_srv_destroy_path_files(srv_path); + /* Notify upper layer if we are the last path */ rtrs_srv_path_down(srv_path); diff --git a/drivers/input/keyboard/ipaq-micro-keys.c b/drivers/input/keyboard/ipaq-micro-keys.c index 7b509bce2b332..1d71dd79ffd28 100644 --- a/drivers/input/keyboard/ipaq-micro-keys.c +++ b/drivers/input/keyboard/ipaq-micro-keys.c @@ -105,6 +105,9 @@ static int micro_key_probe(struct platform_device *pdev) keys->codes = devm_kmemdup(&pdev->dev, micro_keycodes, keys->input->keycodesize * keys->input->keycodemax, GFP_KERNEL); + if (!keys->codes) + return -ENOMEM; + keys->input->keycode = keys->codes; __set_bit(EV_KEY, keys->input->evbit); diff --git a/drivers/input/misc/soc_button_array.c b/drivers/input/misc/soc_button_array.c index e79f5497948b8..9116f4248fd09 100644 --- a/drivers/input/misc/soc_button_array.c +++ b/drivers/input/misc/soc_button_array.c @@ -299,6 +299,11 @@ static int soc_button_parse_btn_desc(struct device *dev, info->name = "power"; info->event_code = KEY_POWER; info->wakeup = true; + } else if (upage == 0x01 && usage == 0xc6) { + info->name = "airplane mode switch"; + info->event_type = EV_SW; + info->event_code = SW_RFKILL_ALL; + info->active_low = false; } else if (upage == 0x01 && usage == 0xca) { info->name = "rotation lock switch"; info->event_type = EV_SW; diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c index dfab160ca5293..50bac2d79d9b5 100644 --- a/drivers/interconnect/core.c +++ b/drivers/interconnect/core.c @@ -395,6 +395,9 @@ struct icc_node_data *of_icc_get_from_provider(struct of_phandle_args *spec) } mutex_unlock(&icc_lock); + if (!node) + return ERR_PTR(-EINVAL); + if (IS_ERR(node)) return ERR_CAST(node); diff --git a/drivers/interconnect/qcom/sm8250.c b/drivers/interconnect/qcom/sm8250.c index 661dc18d99dba..2a2f56b993733 100644 --- a/drivers/interconnect/qcom/sm8250.c +++ b/drivers/interconnect/qcom/sm8250.c @@ -1995,6 +1995,7 @@ static struct platform_driver qnoc_driver = { .driver = { .name = "qnoc-sm8250", .of_match_table = qnoc_of_match, + .sync_state = icc_sync_state, }, }; module_platform_driver(qnoc_driver); diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index a3414afe11b07..23cb80d62a9ab 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -1522,6 +1522,15 @@ void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 pfsid, { struct qi_desc desc; + /* + * VT-d spec, section 4.3: + * + * Software is recommended to not submit any Device-TLB invalidation + * requests while address remapping hardware is disabled. + */ + if (!(iommu->gcmd & DMA_GCMD_TE)) + return; + if (mask) { addr |= (1ULL << (VTD_PAGE_SHIFT + mask - 1)) - 1; desc.qw1 = QI_DEV_IOTLB_ADDR(addr) | QI_DEV_IOTLB_SIZE; @@ -1587,6 +1596,15 @@ void qi_flush_dev_iotlb_pasid(struct intel_iommu *iommu, u16 sid, u16 pfsid, unsigned long mask = 1UL << (VTD_PAGE_SHIFT + size_order - 1); struct qi_desc desc = {.qw1 = 0, .qw2 = 0, .qw3 = 0}; + /* + * VT-d spec, section 4.3: + * + * Software is recommended to not submit any Device-TLB invalidation + * requests while address remapping hardware is disabled. + */ + if (!(iommu->gcmd & DMA_GCMD_TE)) + return; + desc.qw0 = QI_DEV_EIOTLB_PASID(pasid) | QI_DEV_EIOTLB_SID(sid) | QI_DEV_EIOTLB_QDEP(qdep) | QI_DEIOTLB_TYPE | QI_DEV_IOTLB_PFSID(pfsid); diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 3685ba90ec88e..4c3707384bd92 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -2487,7 +2487,8 @@ static int dmar_domain_attach_device(struct dmar_domain *domain, return ret; } - iommu_enable_pci_caps(info); + if (sm_supported(info->iommu) || !domain_type_is_si(info->domain)) + iommu_enable_pci_caps(info); return 0; } @@ -3922,8 +3923,8 @@ static int domain_context_clear_one_cb(struct pci_dev *pdev, u16 alias, void *op */ static void domain_context_clear(struct device_domain_info *info) { - if (!info->iommu || !info->dev || !dev_is_pci(info->dev)) - return; + if (!dev_is_pci(info->dev)) + domain_context_clear_one(info, info->bus, info->devfn); pci_for_each_dma_alias(to_pci_dev(info->dev), &domain_context_clear_one_cb, info); @@ -4928,7 +4929,7 @@ static void quirk_igfx_skip_te_disable(struct pci_dev *dev) ver = (dev->device >> 8) & 0xff; if (ver != 0x45 && ver != 0x46 && ver != 0x4c && ver != 0x4e && ver != 0x8a && ver != 0x98 && - ver != 0x9a && ver != 0xa7) + ver != 0x9a && ver != 0xa7 && ver != 0x7d) return; if (risky_device(dev)) diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c index 50a481c895b86..ac12f76c1212a 100644 --- a/drivers/iommu/intel/svm.c +++ b/drivers/iommu/intel/svm.c @@ -216,6 +216,27 @@ static void intel_flush_svm_range(struct intel_svm *svm, unsigned long address, rcu_read_unlock(); } +static void intel_flush_svm_all(struct intel_svm *svm) +{ + struct device_domain_info *info; + struct intel_svm_dev *sdev; + + rcu_read_lock(); + list_for_each_entry_rcu(sdev, &svm->devs, list) { + info = dev_iommu_priv_get(sdev->dev); + + qi_flush_piotlb(sdev->iommu, sdev->did, svm->pasid, 0, -1UL, 0); + if (info->ats_enabled) { + qi_flush_dev_iotlb_pasid(sdev->iommu, sdev->sid, info->pfsid, + svm->pasid, sdev->qdep, + 0, 64 - VTD_PAGE_SHIFT); + quirk_extra_dev_tlb_flush(info, 0, 64 - VTD_PAGE_SHIFT, + svm->pasid, sdev->qdep); + } + } + rcu_read_unlock(); +} + /* Pages have been freed at this point */ static void intel_arch_invalidate_secondary_tlbs(struct mmu_notifier *mn, struct mm_struct *mm, @@ -223,6 +244,11 @@ static void intel_arch_invalidate_secondary_tlbs(struct mmu_notifier *mn, { struct intel_svm *svm = container_of(mn, struct intel_svm, notifier); + if (start == 0 && end == -1UL) { + intel_flush_svm_all(svm); + return; + } + intel_flush_svm_range(svm, start, (end - start + PAGE_SIZE - 1) >> VTD_PAGE_SHIFT, 0); } diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index c146378c7d032..3a67e636287a7 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -479,11 +479,12 @@ static void iommu_deinit_device(struct device *dev) dev_iommu_free(dev); } +DEFINE_MUTEX(iommu_probe_device_lock); + static int __iommu_probe_device(struct device *dev, struct list_head *group_list) { const struct iommu_ops *ops = dev->bus->iommu_ops; struct iommu_group *group; - static DEFINE_MUTEX(iommu_probe_device_lock); struct group_device *gdev; int ret; @@ -496,17 +497,15 @@ static int __iommu_probe_device(struct device *dev, struct list_head *group_list * probably be able to use device_lock() here to minimise the scope, * but for now enforcing a simple global ordering is fine. */ - mutex_lock(&iommu_probe_device_lock); + lockdep_assert_held(&iommu_probe_device_lock); /* Device is probed already if in a group */ - if (dev->iommu_group) { - ret = 0; - goto out_unlock; - } + if (dev->iommu_group) + return 0; ret = iommu_init_device(dev, ops); if (ret) - goto out_unlock; + return ret; group = dev->iommu_group; gdev = iommu_group_alloc_device(group, dev); @@ -542,7 +541,6 @@ static int __iommu_probe_device(struct device *dev, struct list_head *group_list list_add_tail(&group->entry, group_list); } mutex_unlock(&group->mutex); - mutex_unlock(&iommu_probe_device_lock); if (dev_is_pci(dev)) iommu_dma_set_pci_32bit_workaround(dev); @@ -556,8 +554,6 @@ static int __iommu_probe_device(struct device *dev, struct list_head *group_list iommu_deinit_device(dev); mutex_unlock(&group->mutex); iommu_group_put(group); -out_unlock: - mutex_unlock(&iommu_probe_device_lock); return ret; } @@ -567,7 +563,9 @@ int iommu_probe_device(struct device *dev) const struct iommu_ops *ops; int ret; + mutex_lock(&iommu_probe_device_lock); ret = __iommu_probe_device(dev, NULL); + mutex_unlock(&iommu_probe_device_lock); if (ret) return ret; @@ -1783,7 +1781,9 @@ static int probe_iommu_group(struct device *dev, void *data) struct list_head *group_list = data; int ret; + mutex_lock(&iommu_probe_device_lock); ret = __iommu_probe_device(dev, group_list); + mutex_unlock(&iommu_probe_device_lock); if (ret == -ENODEV) ret = 0; diff --git a/drivers/iommu/iommufd/io_pagetable.c b/drivers/iommu/iommufd/io_pagetable.c index a4da1817e19dd..117a39ae2e4aa 100644 --- a/drivers/iommu/iommufd/io_pagetable.c +++ b/drivers/iommu/iommufd/io_pagetable.c @@ -1060,6 +1060,16 @@ static int iopt_area_split(struct iopt_area *area, unsigned long iova) if (WARN_ON(rc)) goto err_remove_lhs; + /* + * If the original area has filled a domain, domains_itree has to be + * updated. + */ + if (area->storage_domain) { + interval_tree_remove(&area->pages_node, &pages->domains_itree); + interval_tree_insert(&lhs->pages_node, &pages->domains_itree); + interval_tree_insert(&rhs->pages_node, &pages->domains_itree); + } + lhs->storage_domain = area->storage_domain; lhs->pages = area->pages; rhs->storage_domain = area->storage_domain; diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c index 157b286e36bf3..35ba090f3b5e2 100644 --- a/drivers/iommu/of_iommu.c +++ b/drivers/iommu/of_iommu.c @@ -112,16 +112,20 @@ const struct iommu_ops *of_iommu_configure(struct device *dev, const u32 *id) { const struct iommu_ops *ops = NULL; - struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); + struct iommu_fwspec *fwspec; int err = NO_IOMMU; if (!master_np) return NULL; + /* Serialise to make dev->iommu stable under our potential fwspec */ + mutex_lock(&iommu_probe_device_lock); + fwspec = dev_iommu_fwspec_get(dev); if (fwspec) { - if (fwspec->ops) + if (fwspec->ops) { + mutex_unlock(&iommu_probe_device_lock); return fwspec->ops; - + } /* In the deferred case, start again from scratch */ iommu_fwspec_free(dev); } @@ -155,6 +159,8 @@ const struct iommu_ops *of_iommu_configure(struct device *dev, fwspec = dev_iommu_fwspec_get(dev); ops = fwspec->ops; } + mutex_unlock(&iommu_probe_device_lock); + /* * If we have reason to believe the IOMMU driver missed the initial * probe for dev, replay it to get things in order. @@ -191,7 +197,7 @@ iommu_resv_region_get_type(struct device *dev, if (start == phys->start && end == phys->end) return IOMMU_RESV_DIRECT; - dev_warn(dev, "treating non-direct mapping [%pr] -> [%pap-%pap] as reservation\n", &phys, + dev_warn(dev, "treating non-direct mapping [%pr] -> [%pap-%pap] as reservation\n", phys, &start, &end); return IOMMU_RESV_RESERVED; } diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index a8c89df1a9978..9a7a74239eabb 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -2379,12 +2379,12 @@ static int its_setup_baser(struct its_node *its, struct its_baser *baser, break; } + if (!shr) + gic_flush_dcache_to_poc(base, PAGE_ORDER_TO_SIZE(order)); + its_write_baser(its, baser, val); tmp = baser->val; - if (its->flags & ITS_FLAGS_FORCE_NON_SHAREABLE) - tmp &= ~GITS_BASER_SHAREABILITY_MASK; - if ((val ^ tmp) & GITS_BASER_SHAREABILITY_MASK) { /* * Shareability didn't stick. Just use @@ -2394,10 +2394,9 @@ static int its_setup_baser(struct its_node *its, struct its_baser *baser, * non-cacheable as well. */ shr = tmp & GITS_BASER_SHAREABILITY_MASK; - if (!shr) { + if (!shr) cache = GITS_BASER_nC; - gic_flush_dcache_to_poc(base, PAGE_ORDER_TO_SIZE(order)); - } + goto retry_baser; } @@ -2609,6 +2608,11 @@ static int its_alloc_tables(struct its_node *its) /* erratum 24313: ignore memory access type */ cache = GITS_BASER_nCnB; + if (its->flags & ITS_FLAGS_FORCE_NON_SHAREABLE) { + cache = GITS_BASER_nC; + shr = 0; + } + for (i = 0; i < GITS_BASER_NR_REGS; i++) { struct its_baser *baser = its->tables + i; u64 val = its_read_baser(its, baser); diff --git a/drivers/leds/led-class.c b/drivers/leds/led-class.c index 974b84f6bd6af..ba1be15cfd8ea 100644 --- a/drivers/leds/led-class.c +++ b/drivers/leds/led-class.c @@ -75,19 +75,6 @@ static ssize_t max_brightness_show(struct device *dev, } static DEVICE_ATTR_RO(max_brightness); -static ssize_t color_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - const char *color_text = "invalid"; - struct led_classdev *led_cdev = dev_get_drvdata(dev); - - if (led_cdev->color < LED_COLOR_ID_MAX) - color_text = led_colors[led_cdev->color]; - - return sysfs_emit(buf, "%s\n", color_text); -} -static DEVICE_ATTR_RO(color); - #ifdef CONFIG_LEDS_TRIGGERS static BIN_ATTR(trigger, 0644, led_trigger_read, led_trigger_write, 0); static struct bin_attribute *led_trigger_bin_attrs[] = { @@ -102,7 +89,6 @@ static const struct attribute_group led_trigger_group = { static struct attribute *led_class_attrs[] = { &dev_attr_brightness.attr, &dev_attr_max_brightness.attr, - &dev_attr_color.attr, NULL, }; diff --git a/drivers/leds/trigger/ledtrig-netdev.c b/drivers/leds/trigger/ledtrig-netdev.c index 58f3352539e8e..d76214fa9ad86 100644 --- a/drivers/leds/trigger/ledtrig-netdev.c +++ b/drivers/leds/trigger/ledtrig-netdev.c @@ -221,8 +221,16 @@ static ssize_t device_name_show(struct device *dev, static int set_device_name(struct led_netdev_data *trigger_data, const char *name, size_t size) { + if (size >= IFNAMSIZ) + return -EINVAL; + cancel_delayed_work_sync(&trigger_data->work); + /* + * Take RTNL lock before trigger_data lock to prevent potential + * deadlock with netdev notifier registration. + */ + rtnl_lock(); mutex_lock(&trigger_data->lock); if (trigger_data->net_dev) { @@ -242,16 +250,14 @@ static int set_device_name(struct led_netdev_data *trigger_data, trigger_data->carrier_link_up = false; trigger_data->link_speed = SPEED_UNKNOWN; trigger_data->duplex = DUPLEX_UNKNOWN; - if (trigger_data->net_dev != NULL) { - rtnl_lock(); + if (trigger_data->net_dev) get_device_state(trigger_data); - rtnl_unlock(); - } trigger_data->last_activity = 0; set_baseline_state(trigger_data); mutex_unlock(&trigger_data->lock); + rtnl_unlock(); return 0; } @@ -263,9 +269,6 @@ static ssize_t device_name_store(struct device *dev, struct led_netdev_data *trigger_data = led_trigger_get_drvdata(dev); int ret; - if (size >= IFNAMSIZ) - return -EINVAL; - ret = set_device_name(trigger_data, buf, size); if (ret < 0) diff --git a/drivers/mcb/mcb-core.c b/drivers/mcb/mcb-core.c index 0cac5bead84fa..d4eec09009809 100644 --- a/drivers/mcb/mcb-core.c +++ b/drivers/mcb/mcb-core.c @@ -246,6 +246,7 @@ int mcb_device_register(struct mcb_bus *bus, struct mcb_device *dev) return 0; out: + put_device(&dev->dev); return ret; } diff --git a/drivers/mcb/mcb-parse.c b/drivers/mcb/mcb-parse.c index 656b6b71c7682..1ae37e693de04 100644 --- a/drivers/mcb/mcb-parse.c +++ b/drivers/mcb/mcb-parse.c @@ -106,7 +106,7 @@ static int chameleon_parse_gdd(struct mcb_bus *bus, return 0; err: - put_device(&mdev->dev); + mcb_free_dev(mdev); return ret; } diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index 5a79bb3c272f1..83eb7f27db3d4 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -265,6 +265,7 @@ struct bcache_device { #define BCACHE_DEV_WB_RUNNING 3 #define BCACHE_DEV_RATE_DW_RUNNING 4 int nr_stripes; +#define BCH_MIN_STRIPE_SZ ((4 << 20) >> SECTOR_SHIFT) unsigned int stripe_size; atomic_t *stripe_sectors_dirty; unsigned long *full_dirty_stripes; diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index fd121a61f17cc..b709c2fde782a 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -995,6 +995,9 @@ static struct btree *mca_alloc(struct cache_set *c, struct btree_op *op, * * The btree node will have either a read or a write lock held, depending on * level and op->lock. + * + * Note: Only error code or btree pointer will be returned, it is unncessary + * for callers to check NULL pointer. */ struct btree *bch_btree_node_get(struct cache_set *c, struct btree_op *op, struct bkey *k, int level, bool write, @@ -1106,6 +1109,10 @@ static void btree_node_free(struct btree *b) mutex_unlock(&b->c->bucket_lock); } +/* + * Only error code or btree pointer will be returned, it is unncessary for + * callers to check NULL pointer. + */ struct btree *__bch_btree_node_alloc(struct cache_set *c, struct btree_op *op, int level, bool wait, struct btree *parent) @@ -1363,7 +1370,7 @@ static int btree_gc_coalesce(struct btree *b, struct btree_op *op, memset(new_nodes, 0, sizeof(new_nodes)); closure_init_stack(&cl); - while (nodes < GC_MERGE_NODES && !IS_ERR(r[nodes].b)) + while (nodes < GC_MERGE_NODES && !IS_ERR_OR_NULL(r[nodes].b)) keys += r[nodes++].keys; blocks = btree_default_blocks(b->c) * 2 / 3; @@ -1510,7 +1517,7 @@ static int btree_gc_coalesce(struct btree *b, struct btree_op *op, bch_keylist_free(&keylist); for (i = 0; i < nodes; i++) - if (!IS_ERR(new_nodes[i])) { + if (!IS_ERR_OR_NULL(new_nodes[i])) { btree_node_free(new_nodes[i]); rw_unlock(true, new_nodes[i]); } @@ -1527,6 +1534,8 @@ static int btree_gc_rewrite_node(struct btree *b, struct btree_op *op, return 0; n = btree_node_alloc_replacement(replace, NULL); + if (IS_ERR(n)) + return 0; /* recheck reserve after allocating replacement node */ if (btree_check_reserve(b, NULL)) { diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 0ae2b36762930..1e677af385211 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -905,6 +905,8 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size, if (!d->stripe_size) d->stripe_size = 1 << 31; + else if (d->stripe_size < BCH_MIN_STRIPE_SZ) + d->stripe_size = roundup(BCH_MIN_STRIPE_SZ, d->stripe_size); n = DIV_ROUND_UP_ULL(sectors, d->stripe_size); if (!n || n > max_stripes) { @@ -2015,7 +2017,7 @@ static int run_cache_set(struct cache_set *c) c->root = bch_btree_node_get(c, NULL, k, j->btree_level, true, NULL); - if (IS_ERR_OR_NULL(c->root)) + if (IS_ERR(c->root)) goto err; list_del_init(&c->root->list); diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c index 0e2c1880f60b2..18ac98dc89223 100644 --- a/drivers/md/bcache/sysfs.c +++ b/drivers/md/bcache/sysfs.c @@ -1103,7 +1103,7 @@ SHOW(__bch_cache) sum += INITIAL_PRIO - cached[i]; if (n) - do_div(sum, n); + sum = div64_u64(sum, n); for (i = 0; i < ARRAY_SIZE(q); i++) q[i] = INITIAL_PRIO - cached[n * (i + 1) / diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c index 24c049067f61a..3accfdaee6b19 100644 --- a/drivers/md/bcache/writeback.c +++ b/drivers/md/bcache/writeback.c @@ -913,7 +913,7 @@ static int bch_dirty_init_thread(void *arg) int cur_idx, prev_idx, skip_nr; k = p = NULL; - cur_idx = prev_idx = 0; + prev_idx = 0; bch_btree_iter_init(&c->root->keys, &iter, NULL); k = bch_btree_iter_next_filter(&iter, &c->root->keys, bch_ptr_bad); @@ -977,24 +977,35 @@ static int bch_btre_dirty_init_thread_nr(void) void bch_sectors_dirty_init(struct bcache_device *d) { int i; + struct btree *b = NULL; struct bkey *k = NULL; struct btree_iter iter; struct sectors_dirty_init op; struct cache_set *c = d->c; struct bch_dirty_init_state state; +retry_lock: + b = c->root; + rw_lock(0, b, b->level); + if (b != c->root) { + rw_unlock(0, b); + goto retry_lock; + } + /* Just count root keys if no leaf node */ - rw_lock(0, c->root, c->root->level); if (c->root->level == 0) { bch_btree_op_init(&op.op, -1); op.inode = d->id; op.count = 0; for_each_key_filter(&c->root->keys, - k, &iter, bch_ptr_invalid) + k, &iter, bch_ptr_invalid) { + if (KEY_INODE(k) != op.inode) + continue; sectors_dirty_init_fn(&op.op, c->root, k); + } - rw_unlock(0, c->root); + rw_unlock(0, b); return; } @@ -1014,23 +1025,24 @@ void bch_sectors_dirty_init(struct bcache_device *d) if (atomic_read(&state.enough)) break; + atomic_inc(&state.started); state.infos[i].state = &state; state.infos[i].thread = kthread_run(bch_dirty_init_thread, &state.infos[i], "bch_dirtcnt[%d]", i); if (IS_ERR(state.infos[i].thread)) { pr_err("fails to run thread bch_dirty_init[%d]\n", i); + atomic_dec(&state.started); for (--i; i >= 0; i--) kthread_stop(state.infos[i].thread); goto out; } - atomic_inc(&state.started); } out: /* Must wait for all threads to stop. */ wait_event(state.wait, atomic_read(&state.started) == 0); - rw_unlock(0, c->root); + rw_unlock(0, b); } void bch_cached_dev_writeback_init(struct cached_dev *dc) diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index bc309e41d074a..486e1180cc3a3 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -254,7 +254,7 @@ enum evict_result { typedef enum evict_result (*le_predicate)(struct lru_entry *le, void *context); -static struct lru_entry *lru_evict(struct lru *lru, le_predicate pred, void *context) +static struct lru_entry *lru_evict(struct lru *lru, le_predicate pred, void *context, bool no_sleep) { unsigned long tested = 0; struct list_head *h = lru->cursor; @@ -295,7 +295,8 @@ static struct lru_entry *lru_evict(struct lru *lru, le_predicate pred, void *con h = h->next; - cond_resched(); + if (!no_sleep) + cond_resched(); } return NULL; @@ -382,7 +383,10 @@ struct dm_buffer { */ struct buffer_tree { - struct rw_semaphore lock; + union { + struct rw_semaphore lock; + rwlock_t spinlock; + } u; struct rb_root root; } ____cacheline_aligned_in_smp; @@ -393,9 +397,12 @@ struct dm_buffer_cache { * on the locks. */ unsigned int num_locks; + bool no_sleep; struct buffer_tree trees[]; }; +static DEFINE_STATIC_KEY_FALSE(no_sleep_enabled); + static inline unsigned int cache_index(sector_t block, unsigned int num_locks) { return dm_hash_locks_index(block, num_locks); @@ -403,22 +410,34 @@ static inline unsigned int cache_index(sector_t block, unsigned int num_locks) static inline void cache_read_lock(struct dm_buffer_cache *bc, sector_t block) { - down_read(&bc->trees[cache_index(block, bc->num_locks)].lock); + if (static_branch_unlikely(&no_sleep_enabled) && bc->no_sleep) + read_lock_bh(&bc->trees[cache_index(block, bc->num_locks)].u.spinlock); + else + down_read(&bc->trees[cache_index(block, bc->num_locks)].u.lock); } static inline void cache_read_unlock(struct dm_buffer_cache *bc, sector_t block) { - up_read(&bc->trees[cache_index(block, bc->num_locks)].lock); + if (static_branch_unlikely(&no_sleep_enabled) && bc->no_sleep) + read_unlock_bh(&bc->trees[cache_index(block, bc->num_locks)].u.spinlock); + else + up_read(&bc->trees[cache_index(block, bc->num_locks)].u.lock); } static inline void cache_write_lock(struct dm_buffer_cache *bc, sector_t block) { - down_write(&bc->trees[cache_index(block, bc->num_locks)].lock); + if (static_branch_unlikely(&no_sleep_enabled) && bc->no_sleep) + write_lock_bh(&bc->trees[cache_index(block, bc->num_locks)].u.spinlock); + else + down_write(&bc->trees[cache_index(block, bc->num_locks)].u.lock); } static inline void cache_write_unlock(struct dm_buffer_cache *bc, sector_t block) { - up_write(&bc->trees[cache_index(block, bc->num_locks)].lock); + if (static_branch_unlikely(&no_sleep_enabled) && bc->no_sleep) + write_unlock_bh(&bc->trees[cache_index(block, bc->num_locks)].u.spinlock); + else + up_write(&bc->trees[cache_index(block, bc->num_locks)].u.lock); } /* @@ -442,18 +461,32 @@ static void lh_init(struct lock_history *lh, struct dm_buffer_cache *cache, bool static void __lh_lock(struct lock_history *lh, unsigned int index) { - if (lh->write) - down_write(&lh->cache->trees[index].lock); - else - down_read(&lh->cache->trees[index].lock); + if (lh->write) { + if (static_branch_unlikely(&no_sleep_enabled) && lh->cache->no_sleep) + write_lock_bh(&lh->cache->trees[index].u.spinlock); + else + down_write(&lh->cache->trees[index].u.lock); + } else { + if (static_branch_unlikely(&no_sleep_enabled) && lh->cache->no_sleep) + read_lock_bh(&lh->cache->trees[index].u.spinlock); + else + down_read(&lh->cache->trees[index].u.lock); + } } static void __lh_unlock(struct lock_history *lh, unsigned int index) { - if (lh->write) - up_write(&lh->cache->trees[index].lock); - else - up_read(&lh->cache->trees[index].lock); + if (lh->write) { + if (static_branch_unlikely(&no_sleep_enabled) && lh->cache->no_sleep) + write_unlock_bh(&lh->cache->trees[index].u.spinlock); + else + up_write(&lh->cache->trees[index].u.lock); + } else { + if (static_branch_unlikely(&no_sleep_enabled) && lh->cache->no_sleep) + read_unlock_bh(&lh->cache->trees[index].u.spinlock); + else + up_read(&lh->cache->trees[index].u.lock); + } } /* @@ -502,14 +535,18 @@ static struct dm_buffer *list_to_buffer(struct list_head *l) return le_to_buffer(le); } -static void cache_init(struct dm_buffer_cache *bc, unsigned int num_locks) +static void cache_init(struct dm_buffer_cache *bc, unsigned int num_locks, bool no_sleep) { unsigned int i; bc->num_locks = num_locks; + bc->no_sleep = no_sleep; for (i = 0; i < bc->num_locks; i++) { - init_rwsem(&bc->trees[i].lock); + if (no_sleep) + rwlock_init(&bc->trees[i].u.spinlock); + else + init_rwsem(&bc->trees[i].u.lock); bc->trees[i].root = RB_ROOT; } @@ -648,7 +685,7 @@ static struct dm_buffer *__cache_evict(struct dm_buffer_cache *bc, int list_mode struct lru_entry *le; struct dm_buffer *b; - le = lru_evict(&bc->lru[list_mode], __evict_pred, &w); + le = lru_evict(&bc->lru[list_mode], __evict_pred, &w, bc->no_sleep); if (!le) return NULL; @@ -702,7 +739,7 @@ static void __cache_mark_many(struct dm_buffer_cache *bc, int old_mode, int new_ struct evict_wrapper w = {.lh = lh, .pred = pred, .context = context}; while (true) { - le = lru_evict(&bc->lru[old_mode], __evict_pred, &w); + le = lru_evict(&bc->lru[old_mode], __evict_pred, &w, bc->no_sleep); if (!le) break; @@ -915,10 +952,11 @@ static void cache_remove_range(struct dm_buffer_cache *bc, { unsigned int i; + BUG_ON(bc->no_sleep); for (i = 0; i < bc->num_locks; i++) { - down_write(&bc->trees[i].lock); + down_write(&bc->trees[i].u.lock); __remove_range(bc, &bc->trees[i].root, begin, end, pred, release); - up_write(&bc->trees[i].lock); + up_write(&bc->trees[i].u.lock); } } @@ -979,8 +1017,6 @@ struct dm_bufio_client { struct dm_buffer_cache cache; /* must be last member */ }; -static DEFINE_STATIC_KEY_FALSE(no_sleep_enabled); - /*----------------------------------------------------------------*/ #define dm_bufio_in_request() (!!current->bio_list) @@ -1871,7 +1907,8 @@ static void *new_read(struct dm_bufio_client *c, sector_t block, if (need_submit) submit_io(b, REQ_OP_READ, read_endio); - wait_on_bit_io(&b->state, B_READING, TASK_UNINTERRUPTIBLE); + if (nf != NF_GET) /* we already tested this condition above */ + wait_on_bit_io(&b->state, B_READING, TASK_UNINTERRUPTIBLE); if (b->read_error) { int error = blk_status_to_errno(b->read_error); @@ -2421,7 +2458,7 @@ struct dm_bufio_client *dm_bufio_client_create(struct block_device *bdev, unsign r = -ENOMEM; goto bad_client; } - cache_init(&c->cache, num_locks); + cache_init(&c->cache, num_locks, (flags & DM_BUFIO_CLIENT_NO_SLEEP) != 0); c->bdev = bdev; c->block_size = block_size; diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 5315fd261c23b..17ffbf7fbe73e 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -1679,7 +1679,7 @@ static struct bio *crypt_alloc_buffer(struct dm_crypt_io *io, unsigned int size) unsigned int nr_iovecs = (size + PAGE_SIZE - 1) >> PAGE_SHIFT; gfp_t gfp_mask = GFP_NOWAIT | __GFP_HIGHMEM; unsigned int remaining_size; - unsigned int order = MAX_ORDER - 1; + unsigned int order = MAX_ORDER; retry: if (unlikely(gfp_mask & __GFP_DIRECT_RECLAIM)) @@ -1699,11 +1699,17 @@ static struct bio *crypt_alloc_buffer(struct dm_crypt_io *io, unsigned int size) order = min(order, remaining_order); while (order > 0) { + if (unlikely(percpu_counter_read_positive(&cc->n_allocated_pages) + + (1 << order) > dm_crypt_pages_per_client)) + goto decrease_order; pages = alloc_pages(gfp_mask | __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN | __GFP_COMP, order); - if (likely(pages != NULL)) + if (likely(pages != NULL)) { + percpu_counter_add(&cc->n_allocated_pages, 1 << order); goto have_pages; + } +decrease_order: order--; } @@ -1741,10 +1747,13 @@ static void crypt_free_buffer_pages(struct crypt_config *cc, struct bio *clone) if (clone->bi_vcnt > 0) { /* bio_for_each_folio_all crashes with an empty bio */ bio_for_each_folio_all(fi, clone) { - if (folio_test_large(fi.folio)) + if (folio_test_large(fi.folio)) { + percpu_counter_sub(&cc->n_allocated_pages, + 1 << folio_order(fi.folio)); folio_put(fi.folio); - else + } else { mempool_free(&fi.folio->page, &cc->page_pool); + } } } } diff --git a/drivers/md/dm-delay.c b/drivers/md/dm-delay.c index 7433525e59856..3726fae3006e3 100644 --- a/drivers/md/dm-delay.c +++ b/drivers/md/dm-delay.c @@ -31,7 +31,7 @@ struct delay_c { struct workqueue_struct *kdelayd_wq; struct work_struct flush_expired_bios; struct list_head delayed_bios; - atomic_t may_delay; + bool may_delay; struct delay_class read; struct delay_class write; @@ -192,7 +192,7 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv) INIT_WORK(&dc->flush_expired_bios, flush_expired_bios); INIT_LIST_HEAD(&dc->delayed_bios); mutex_init(&dc->timer_lock); - atomic_set(&dc->may_delay, 1); + dc->may_delay = true; dc->argc = argc; ret = delay_class_ctr(ti, &dc->read, argv); @@ -247,7 +247,7 @@ static int delay_bio(struct delay_c *dc, struct delay_class *c, struct bio *bio) struct dm_delay_info *delayed; unsigned long expires = 0; - if (!c->delay || !atomic_read(&dc->may_delay)) + if (!c->delay) return DM_MAPIO_REMAPPED; delayed = dm_per_bio_data(bio, sizeof(struct dm_delay_info)); @@ -256,6 +256,10 @@ static int delay_bio(struct delay_c *dc, struct delay_class *c, struct bio *bio) delayed->expires = expires = jiffies + msecs_to_jiffies(c->delay); mutex_lock(&delayed_bios_lock); + if (unlikely(!dc->may_delay)) { + mutex_unlock(&delayed_bios_lock); + return DM_MAPIO_REMAPPED; + } c->ops++; list_add_tail(&delayed->list, &dc->delayed_bios); mutex_unlock(&delayed_bios_lock); @@ -269,7 +273,10 @@ static void delay_presuspend(struct dm_target *ti) { struct delay_c *dc = ti->private; - atomic_set(&dc->may_delay, 0); + mutex_lock(&delayed_bios_lock); + dc->may_delay = false; + mutex_unlock(&delayed_bios_lock); + del_timer_sync(&dc->delay_timer); flush_bios(flush_delayed_bios(dc, 1)); } @@ -278,7 +285,7 @@ static void delay_resume(struct dm_target *ti) { struct delay_c *dc = ti->private; - atomic_set(&dc->may_delay, 1); + dc->may_delay = true; } static int delay_map(struct dm_target *ti, struct bio *bio) diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index 97a8d5fc9ebb6..9261bbebd662a 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -1765,11 +1765,12 @@ static void integrity_metadata(struct work_struct *w) sectors_to_process = dio->range.n_sectors; __bio_for_each_segment(bv, bio, iter, dio->bio_details.bi_iter) { + struct bio_vec bv_copy = bv; unsigned int pos; char *mem, *checksums_ptr; again: - mem = bvec_kmap_local(&bv); + mem = bvec_kmap_local(&bv_copy); pos = 0; checksums_ptr = checksums; do { @@ -1778,7 +1779,7 @@ static void integrity_metadata(struct work_struct *w) sectors_to_process -= ic->sectors_per_block; pos += ic->sectors_per_block << SECTOR_SHIFT; sector += ic->sectors_per_block; - } while (pos < bv.bv_len && sectors_to_process && checksums != checksums_onstack); + } while (pos < bv_copy.bv_len && sectors_to_process && checksums != checksums_onstack); kunmap_local(mem); r = dm_integrity_rw_tag(ic, checksums, &dio->metadata_block, &dio->metadata_offset, @@ -1803,9 +1804,9 @@ static void integrity_metadata(struct work_struct *w) if (!sectors_to_process) break; - if (unlikely(pos < bv.bv_len)) { - bv.bv_offset += pos; - bv.bv_len -= pos; + if (unlikely(pos < bv_copy.bv_len)) { + bv_copy.bv_offset += pos; + bv_copy.bv_len -= pos; goto again; } } diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c index 3ef9f018da60c..b475200d8586a 100644 --- a/drivers/md/dm-verity-fec.c +++ b/drivers/md/dm-verity-fec.c @@ -24,7 +24,8 @@ bool verity_fec_is_enabled(struct dm_verity *v) */ static inline struct dm_verity_fec_io *fec_io(struct dm_verity_io *io) { - return (struct dm_verity_fec_io *) verity_io_digest_end(io->v, io); + return (struct dm_verity_fec_io *) + ((char *)io + io->v->ti->per_io_data_size - sizeof(struct dm_verity_fec_io)); } /* @@ -185,7 +186,7 @@ static int fec_is_erasure(struct dm_verity *v, struct dm_verity_io *io, { if (unlikely(verity_hash(v, verity_io_hash_req(v, io), data, 1 << v->data_dev_block_bits, - verity_io_real_digest(v, io)))) + verity_io_real_digest(v, io), true))) return 0; return memcmp(verity_io_real_digest(v, io), want_digest, @@ -386,7 +387,7 @@ static int fec_decode_rsb(struct dm_verity *v, struct dm_verity_io *io, /* Always re-validate the corrected block against the expected hash */ r = verity_hash(v, verity_io_hash_req(v, io), fio->output, 1 << v->data_dev_block_bits, - verity_io_real_digest(v, io)); + verity_io_real_digest(v, io), true); if (unlikely(r < 0)) return r; diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index 26adcfea03022..14e58ae705218 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -135,20 +135,21 @@ static int verity_hash_update(struct dm_verity *v, struct ahash_request *req, * Wrapper for crypto_ahash_init, which handles verity salting. */ static int verity_hash_init(struct dm_verity *v, struct ahash_request *req, - struct crypto_wait *wait) + struct crypto_wait *wait, bool may_sleep) { int r; ahash_request_set_tfm(req, v->tfm); - ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP | - CRYPTO_TFM_REQ_MAY_BACKLOG, - crypto_req_done, (void *)wait); + ahash_request_set_callback(req, + may_sleep ? CRYPTO_TFM_REQ_MAY_SLEEP | CRYPTO_TFM_REQ_MAY_BACKLOG : 0, + crypto_req_done, (void *)wait); crypto_init_wait(wait); r = crypto_wait_req(crypto_ahash_init(req), wait); if (unlikely(r < 0)) { - DMERR("crypto_ahash_init failed: %d", r); + if (r != -ENOMEM) + DMERR("crypto_ahash_init failed: %d", r); return r; } @@ -179,12 +180,12 @@ static int verity_hash_final(struct dm_verity *v, struct ahash_request *req, } int verity_hash(struct dm_verity *v, struct ahash_request *req, - const u8 *data, size_t len, u8 *digest) + const u8 *data, size_t len, u8 *digest, bool may_sleep) { int r; struct crypto_wait wait; - r = verity_hash_init(v, req, &wait); + r = verity_hash_init(v, req, &wait, may_sleep); if (unlikely(r < 0)) goto out; @@ -322,7 +323,7 @@ static int verity_verify_level(struct dm_verity *v, struct dm_verity_io *io, r = verity_hash(v, verity_io_hash_req(v, io), data, 1 << v->hash_dev_block_bits, - verity_io_real_digest(v, io)); + verity_io_real_digest(v, io), !io->in_tasklet); if (unlikely(r < 0)) goto release_ret_r; @@ -556,7 +557,7 @@ static int verity_verify_io(struct dm_verity_io *io) continue; } - r = verity_hash_init(v, req, &wait); + r = verity_hash_init(v, req, &wait, !io->in_tasklet); if (unlikely(r < 0)) return r; @@ -641,7 +642,6 @@ static void verity_work(struct work_struct *w) io->in_tasklet = false; - verity_fec_init_io(io); verity_finish_io(io, errno_to_blk_status(verity_verify_io(io))); } @@ -652,7 +652,7 @@ static void verity_tasklet(unsigned long data) io->in_tasklet = true; err = verity_verify_io(io); - if (err == -EAGAIN) { + if (err == -EAGAIN || err == -ENOMEM) { /* fallback to retrying with work-queue */ INIT_WORK(&io->work, verity_work); queue_work(io->v->verify_wq, &io->work); @@ -667,7 +667,9 @@ static void verity_end_io(struct bio *bio) struct dm_verity_io *io = bio->bi_private; if (bio->bi_status && - (!verity_fec_is_enabled(io->v) || verity_is_system_shutting_down())) { + (!verity_fec_is_enabled(io->v) || + verity_is_system_shutting_down() || + (bio->bi_opf & REQ_RAHEAD))) { verity_finish_io(io, bio->bi_status); return; } @@ -791,6 +793,8 @@ static int verity_map(struct dm_target *ti, struct bio *bio) bio->bi_private = io; io->iter = bio->bi_iter; + verity_fec_init_io(io); + verity_submit_prefetch(v, io); submit_bio_noacct(bio); @@ -1033,7 +1037,7 @@ static int verity_alloc_zero_digest(struct dm_verity *v) goto out; r = verity_hash(v, req, zero_data, 1 << v->data_dev_block_bits, - v->zero_digest); + v->zero_digest, true); out: kfree(req); diff --git a/drivers/md/dm-verity.h b/drivers/md/dm-verity.h index 2f555b4203679..f9d522c870e61 100644 --- a/drivers/md/dm-verity.h +++ b/drivers/md/dm-verity.h @@ -115,12 +115,6 @@ static inline u8 *verity_io_want_digest(struct dm_verity *v, return (u8 *)(io + 1) + v->ahash_reqsize + v->digest_size; } -static inline u8 *verity_io_digest_end(struct dm_verity *v, - struct dm_verity_io *io) -{ - return verity_io_want_digest(v, io) + v->digest_size; -} - extern int verity_for_bv_block(struct dm_verity *v, struct dm_verity_io *io, struct bvec_iter *iter, int (*process)(struct dm_verity *v, @@ -128,7 +122,7 @@ extern int verity_for_bv_block(struct dm_verity *v, struct dm_verity_io *io, u8 *data, size_t len)); extern int verity_hash(struct dm_verity *v, struct ahash_request *req, - const u8 *data, size_t len, u8 *digest); + const u8 *data, size_t len, u8 *digest, bool may_sleep); extern int verity_hash_for_block(struct dm_verity *v, struct dm_verity_io *io, sector_t block, u8 *digest, bool *is_zero); diff --git a/drivers/md/md.c b/drivers/md/md.c index a104a025084dc..b2ef6af8376a5 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -449,7 +449,7 @@ void mddev_suspend(struct mddev *mddev) set_bit(MD_ALLOW_SB_UPDATE, &mddev->flags); percpu_ref_kill(&mddev->active_io); - if (mddev->pers->prepare_suspend) + if (mddev->pers && mddev->pers->prepare_suspend) mddev->pers->prepare_suspend(mddev); wait_event(mddev->sb_wait, percpu_ref_is_zero(&mddev->active_io)); @@ -6316,6 +6316,9 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev) int err = 0; int did_freeze = 0; + if (mddev->external && test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)) + return -EBUSY; + if (!test_bit(MD_RECOVERY_FROZEN, &mddev->recovery)) { did_freeze = 1; set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); @@ -6330,8 +6333,6 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev) */ md_wakeup_thread_directly(mddev->sync_thread); - if (mddev->external && test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)) - return -EBUSY; mddev_unlock(mddev); wait_event(resync_wait, !test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)); @@ -6344,29 +6345,30 @@ static int md_set_readonly(struct mddev *mddev, struct block_device *bdev) mddev->sync_thread || test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) { pr_warn("md: %s still in use.\n",mdname(mddev)); - if (did_freeze) { - clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); - set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); - md_wakeup_thread(mddev->thread); - } err = -EBUSY; goto out; } + if (mddev->pers) { __md_stop_writes(mddev); - err = -ENXIO; - if (mddev->ro == MD_RDONLY) + if (mddev->ro == MD_RDONLY) { + err = -ENXIO; goto out; + } + mddev->ro = MD_RDONLY; set_disk_ro(mddev->gendisk, 1); + } + +out: + if ((mddev->pers && !err) || did_freeze) { clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); md_wakeup_thread(mddev->thread); sysfs_notify_dirent_safe(mddev->sysfs_state); - err = 0; } -out: + mutex_unlock(&mddev->open_mutex); return err; } @@ -8669,7 +8671,8 @@ static void md_end_clone_io(struct bio *bio) struct bio *orig_bio = md_io_clone->orig_bio; struct mddev *mddev = md_io_clone->mddev; - orig_bio->bi_status = bio->bi_status; + if (bio->bi_status && !orig_bio->bi_status) + orig_bio->bi_status = bio->bi_status; if (md_io_clone->start_time) bio_end_io_acct(orig_bio, md_io_clone->start_time); diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 284cd71bcc685..68d86dbecb4ac 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -5892,11 +5892,11 @@ static bool stripe_ahead_of_reshape(struct mddev *mddev, struct r5conf *conf, int dd_idx; for (dd_idx = 0; dd_idx < sh->disks; dd_idx++) { - if (dd_idx == sh->pd_idx) + if (dd_idx == sh->pd_idx || dd_idx == sh->qd_idx) continue; min_sector = min(min_sector, sh->dev[dd_idx].sector); - max_sector = min(max_sector, sh->dev[dd_idx].sector); + max_sector = max(max_sector, sh->dev[dd_idx].sector); } spin_lock_irq(&conf->device_lock); diff --git a/drivers/media/i2c/ccs/ccs-core.c b/drivers/media/i2c/ccs/ccs-core.c index 49e0d9a095302..6f8fbd82e21c8 100644 --- a/drivers/media/i2c/ccs/ccs-core.c +++ b/drivers/media/i2c/ccs/ccs-core.c @@ -3097,7 +3097,7 @@ static int ccs_open(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh) try_fmt->code = sensor->internal_csi_format->code; try_fmt->field = V4L2_FIELD_NONE; - if (ssd != sensor->pixel_array) + if (ssd == sensor->pixel_array) continue; try_comp = v4l2_subdev_get_try_compose(sd, fh->state, i); diff --git a/drivers/media/i2c/ccs/ccs-quirk.h b/drivers/media/i2c/ccs/ccs-quirk.h index 5838fcda92fd4..0b1a64958d714 100644 --- a/drivers/media/i2c/ccs/ccs-quirk.h +++ b/drivers/media/i2c/ccs/ccs-quirk.h @@ -32,12 +32,10 @@ struct ccs_sensor; * @reg: Pointer to the register to access * @value: Register value, set by the caller on write, or * by the quirk on read - * - * @flags: Quirk flags - * * @return: 0 on success, -ENOIOCTLCMD if no register * access may be done by the caller (default read * value is zero), else negative error code on error + * @flags: Quirk flags */ struct ccs_quirk { int (*limits)(struct ccs_sensor *sensor); diff --git a/drivers/media/pci/cobalt/cobalt-driver.c b/drivers/media/pci/cobalt/cobalt-driver.c index 74edcc76d12f4..6e1a0614e6d06 100644 --- a/drivers/media/pci/cobalt/cobalt-driver.c +++ b/drivers/media/pci/cobalt/cobalt-driver.c @@ -8,6 +8,7 @@ * All rights reserved. */ +#include #include #include #include @@ -210,17 +211,17 @@ void cobalt_pcie_status_show(struct cobalt *cobalt) pcie_capability_read_word(pci_dev, PCI_EXP_LNKSTA, &stat); cobalt_info("PCIe link capability 0x%08x: %s per lane and %u lanes\n", capa, get_link_speed(capa), - (capa & PCI_EXP_LNKCAP_MLW) >> 4); + FIELD_GET(PCI_EXP_LNKCAP_MLW, capa)); cobalt_info("PCIe link control 0x%04x\n", ctrl); cobalt_info("PCIe link status 0x%04x: %s per lane and %u lanes\n", stat, get_link_speed(stat), - (stat & PCI_EXP_LNKSTA_NLW) >> 4); + FIELD_GET(PCI_EXP_LNKSTA_NLW, stat)); /* Bus */ pcie_capability_read_dword(pci_bus_dev, PCI_EXP_LNKCAP, &capa); cobalt_info("PCIe bus link capability 0x%08x: %s per lane and %u lanes\n", capa, get_link_speed(capa), - (capa & PCI_EXP_LNKCAP_MLW) >> 4); + FIELD_GET(PCI_EXP_LNKCAP_MLW, capa)); /* Slot */ pcie_capability_read_dword(pci_dev, PCI_EXP_SLTCAP, &capa); @@ -239,7 +240,7 @@ static unsigned pcie_link_get_lanes(struct cobalt *cobalt) if (!pci_is_pcie(pci_dev)) return 0; pcie_capability_read_word(pci_dev, PCI_EXP_LNKSTA, &link); - return (link & PCI_EXP_LNKSTA_NLW) >> 4; + return FIELD_GET(PCI_EXP_LNKSTA_NLW, link); } static unsigned pcie_bus_link_get_lanes(struct cobalt *cobalt) @@ -250,7 +251,7 @@ static unsigned pcie_bus_link_get_lanes(struct cobalt *cobalt) if (!pci_is_pcie(pci_dev)) return 0; pcie_capability_read_dword(pci_dev, PCI_EXP_LNKCAP, &link); - return (link & PCI_EXP_LNKCAP_MLW) >> 4; + return FIELD_GET(PCI_EXP_LNKCAP_MLW, link); } static void msi_config_show(struct cobalt *cobalt, struct pci_dev *pci_dev) diff --git a/drivers/media/platform/qcom/camss/camss-csid-gen2.c b/drivers/media/platform/qcom/camss/camss-csid-gen2.c index 0f8ac29d038db..23acc387be5f0 100644 --- a/drivers/media/platform/qcom/camss/camss-csid-gen2.c +++ b/drivers/media/platform/qcom/camss/camss-csid-gen2.c @@ -355,9 +355,6 @@ static void __csid_configure_stream(struct csid_device *csid, u8 enable, u8 vc) u8 dt_id = vc; if (tg->enabled) { - /* Config Test Generator */ - vc = 0xa; - /* configure one DT, infinite frames */ val = vc << TPG_VC_CFG0_VC_NUM; val |= INTELEAVING_MODE_ONE_SHOT << TPG_VC_CFG0_LINE_INTERLEAVING_MODE; @@ -370,14 +367,14 @@ static void __csid_configure_stream(struct csid_device *csid, u8 enable, u8 vc) writel_relaxed(0x12345678, csid->base + CSID_TPG_LFSR_SEED); - val = input_format->height & 0x1fff << TPG_DT_n_CFG_0_FRAME_HEIGHT; - val |= input_format->width & 0x1fff << TPG_DT_n_CFG_0_FRAME_WIDTH; + val = (input_format->height & 0x1fff) << TPG_DT_n_CFG_0_FRAME_HEIGHT; + val |= (input_format->width & 0x1fff) << TPG_DT_n_CFG_0_FRAME_WIDTH; writel_relaxed(val, csid->base + CSID_TPG_DT_n_CFG_0(0)); val = format->data_type << TPG_DT_n_CFG_1_DATA_TYPE; writel_relaxed(val, csid->base + CSID_TPG_DT_n_CFG_1(0)); - val = tg->mode << TPG_DT_n_CFG_2_PAYLOAD_MODE; + val = (tg->mode - 1) << TPG_DT_n_CFG_2_PAYLOAD_MODE; val |= 0xBE << TPG_DT_n_CFG_2_USER_SPECIFIED_PAYLOAD; val |= format->decode_format << TPG_DT_n_CFG_2_ENCODE_FORMAT; writel_relaxed(val, csid->base + CSID_TPG_DT_n_CFG_2(0)); @@ -449,6 +446,8 @@ static void __csid_configure_stream(struct csid_device *csid, u8 enable, u8 vc) writel_relaxed(val, csid->base + CSID_CSI2_RX_CFG0); val = 1 << CSI2_RX_CFG1_PACKET_ECC_CORRECTION_EN; + if (vc > 3) + val |= 1 << CSI2_RX_CFG1_VC_MODE; val |= 1 << CSI2_RX_CFG1_MISR_EN; writel_relaxed(val, csid->base + CSID_CSI2_RX_CFG1); diff --git a/drivers/media/platform/qcom/camss/camss-csiphy-3ph-1-0.c b/drivers/media/platform/qcom/camss/camss-csiphy-3ph-1-0.c index 04baa80494c66..4dba61b8d3f2a 100644 --- a/drivers/media/platform/qcom/camss/camss-csiphy-3ph-1-0.c +++ b/drivers/media/platform/qcom/camss/camss-csiphy-3ph-1-0.c @@ -476,7 +476,7 @@ static void csiphy_lanes_enable(struct csiphy_device *csiphy, settle_cnt = csiphy_settle_cnt_calc(link_freq, csiphy->timer_clk_rate); - val = is_gen2 ? BIT(7) : CSIPHY_3PH_CMN_CSI_COMMON_CTRL5_CLK_ENABLE; + val = CSIPHY_3PH_CMN_CSI_COMMON_CTRL5_CLK_ENABLE; for (i = 0; i < c->num_data; i++) val |= BIT(c->data[i].pos * 2); diff --git a/drivers/media/platform/qcom/camss/camss-vfe-170.c b/drivers/media/platform/qcom/camss/camss-vfe-170.c index 02494c89da91c..168baaa80d4e6 100644 --- a/drivers/media/platform/qcom/camss/camss-vfe-170.c +++ b/drivers/media/platform/qcom/camss/camss-vfe-170.c @@ -7,7 +7,6 @@ * Copyright (C) 2020-2021 Linaro Ltd. */ -#include #include #include #include @@ -494,35 +493,20 @@ static int vfe_enable_output(struct vfe_line *line) return 0; } -static int vfe_disable_output(struct vfe_line *line) +static void vfe_disable_output(struct vfe_line *line) { struct vfe_device *vfe = to_vfe(line); struct vfe_output *output = &line->output; unsigned long flags; unsigned int i; - bool done; - int timeout = 0; - - do { - spin_lock_irqsave(&vfe->output_lock, flags); - done = !output->gen2.active_num; - spin_unlock_irqrestore(&vfe->output_lock, flags); - usleep_range(10000, 20000); - - if (timeout++ == 100) { - dev_err(vfe->camss->dev, "VFE idle timeout - resetting\n"); - vfe_reset(vfe); - output->gen2.active_num = 0; - return 0; - } - } while (!done); spin_lock_irqsave(&vfe->output_lock, flags); for (i = 0; i < output->wm_num; i++) vfe_wm_stop(vfe, output->wm_idx[i]); + output->gen2.active_num = 0; spin_unlock_irqrestore(&vfe->output_lock, flags); - return 0; + vfe_reset(vfe); } /* diff --git a/drivers/media/platform/qcom/camss/camss-vfe-480.c b/drivers/media/platform/qcom/camss/camss-vfe-480.c index f70aad2e8c237..8ddb8016434ae 100644 --- a/drivers/media/platform/qcom/camss/camss-vfe-480.c +++ b/drivers/media/platform/qcom/camss/camss-vfe-480.c @@ -8,7 +8,6 @@ * Copyright (C) 2021 Jonathan Marek */ -#include #include #include #include @@ -328,35 +327,20 @@ static int vfe_enable_output(struct vfe_line *line) return 0; } -static int vfe_disable_output(struct vfe_line *line) +static void vfe_disable_output(struct vfe_line *line) { struct vfe_device *vfe = to_vfe(line); struct vfe_output *output = &line->output; unsigned long flags; unsigned int i; - bool done; - int timeout = 0; - - do { - spin_lock_irqsave(&vfe->output_lock, flags); - done = !output->gen2.active_num; - spin_unlock_irqrestore(&vfe->output_lock, flags); - usleep_range(10000, 20000); - - if (timeout++ == 100) { - dev_err(vfe->camss->dev, "VFE idle timeout - resetting\n"); - vfe_reset(vfe); - output->gen2.active_num = 0; - return 0; - } - } while (!done); spin_lock_irqsave(&vfe->output_lock, flags); for (i = 0; i < output->wm_num; i++) vfe_wm_stop(vfe, output->wm_idx[i]); + output->gen2.active_num = 0; spin_unlock_irqrestore(&vfe->output_lock, flags); - return 0; + vfe_reset(vfe); } /* diff --git a/drivers/media/platform/qcom/camss/camss-vfe.c b/drivers/media/platform/qcom/camss/camss-vfe.c index 06c95568e5af4..965500b83d073 100644 --- a/drivers/media/platform/qcom/camss/camss-vfe.c +++ b/drivers/media/platform/qcom/camss/camss-vfe.c @@ -535,7 +535,8 @@ static int vfe_check_clock_rates(struct vfe_device *vfe) struct camss_clock *clock = &vfe->clock[i]; if (!strcmp(clock->name, "vfe0") || - !strcmp(clock->name, "vfe1")) { + !strcmp(clock->name, "vfe1") || + !strcmp(clock->name, "vfe_lite")) { u64 min_rate = 0; unsigned long rate; @@ -611,7 +612,7 @@ int vfe_get(struct vfe_device *vfe) } else { ret = vfe_check_clock_rates(vfe); if (ret < 0) - goto error_pm_runtime_get; + goto error_pm_domain; } vfe->power_count++; diff --git a/drivers/media/platform/qcom/camss/camss.c b/drivers/media/platform/qcom/camss/camss.c index f11dc59135a5a..75991d849b571 100644 --- a/drivers/media/platform/qcom/camss/camss.c +++ b/drivers/media/platform/qcom/camss/camss.c @@ -1619,6 +1619,12 @@ static int camss_probe(struct platform_device *pdev) if (ret < 0) goto err_cleanup; + ret = camss_configure_pd(camss); + if (ret < 0) { + dev_err(dev, "Failed to configure power domains: %d\n", ret); + goto err_cleanup; + } + ret = camss_init_subdevices(camss); if (ret < 0) goto err_cleanup; @@ -1678,12 +1684,6 @@ static int camss_probe(struct platform_device *pdev) } } - ret = camss_configure_pd(camss); - if (ret < 0) { - dev_err(dev, "Failed to configure power domains: %d\n", ret); - return ret; - } - pm_runtime_enable(dev); return 0; diff --git a/drivers/media/platform/qcom/venus/hfi_msgs.c b/drivers/media/platform/qcom/venus/hfi_msgs.c index 7cab685a2ec80..0a041b4db9efc 100644 --- a/drivers/media/platform/qcom/venus/hfi_msgs.c +++ b/drivers/media/platform/qcom/venus/hfi_msgs.c @@ -398,7 +398,7 @@ session_get_prop_buf_req(struct hfi_msg_session_property_info_pkt *pkt, memcpy(&bufreq[idx], buf_req, sizeof(*bufreq)); idx++; - if (idx > HFI_BUFFER_TYPE_MAX) + if (idx >= HFI_BUFFER_TYPE_MAX) return HFI_ERR_SESSION_INVALID_PARAMETER; req_bytes -= sizeof(struct hfi_buffer_requirements); diff --git a/drivers/media/platform/qcom/venus/hfi_parser.c b/drivers/media/platform/qcom/venus/hfi_parser.c index 6cf74b2bc5ae3..c43839539d4dd 100644 --- a/drivers/media/platform/qcom/venus/hfi_parser.c +++ b/drivers/media/platform/qcom/venus/hfi_parser.c @@ -19,6 +19,9 @@ static void init_codecs(struct venus_core *core) struct hfi_plat_caps *caps = core->caps, *cap; unsigned long bit; + if (hweight_long(core->dec_codecs) + hweight_long(core->enc_codecs) > MAX_CODEC_NUM) + return; + for_each_set_bit(bit, &core->dec_codecs, MAX_CODEC_NUM) { cap = &caps[core->codecs_count++]; cap->codec = BIT(bit); @@ -86,6 +89,9 @@ static void fill_profile_level(struct hfi_plat_caps *cap, const void *data, { const struct hfi_profile_level *pl = data; + if (cap->num_pl + num >= HFI_MAX_PROFILE_COUNT) + return; + memcpy(&cap->pl[cap->num_pl], pl, num * sizeof(*pl)); cap->num_pl += num; } @@ -111,6 +117,9 @@ fill_caps(struct hfi_plat_caps *cap, const void *data, unsigned int num) { const struct hfi_capability *caps = data; + if (cap->num_caps + num >= MAX_CAP_ENTRIES) + return; + memcpy(&cap->caps[cap->num_caps], caps, num * sizeof(*caps)); cap->num_caps += num; } @@ -137,6 +146,9 @@ static void fill_raw_fmts(struct hfi_plat_caps *cap, const void *fmts, { const struct raw_formats *formats = fmts; + if (cap->num_fmts + num_fmts >= MAX_FMT_ENTRIES) + return; + memcpy(&cap->fmts[cap->num_fmts], formats, num_fmts * sizeof(*formats)); cap->num_fmts += num_fmts; } @@ -159,6 +171,9 @@ parse_raw_formats(struct venus_core *core, u32 codecs, u32 domain, void *data) rawfmts[i].buftype = fmt->buffer_type; i++; + if (i >= MAX_FMT_ENTRIES) + return; + if (pinfo->num_planes > MAX_PLANES) break; diff --git a/drivers/media/platform/qcom/venus/hfi_venus.c b/drivers/media/platform/qcom/venus/hfi_venus.c index 19fc6575a4891..f9437b6412b91 100644 --- a/drivers/media/platform/qcom/venus/hfi_venus.c +++ b/drivers/media/platform/qcom/venus/hfi_venus.c @@ -205,6 +205,11 @@ static int venus_write_queue(struct venus_hfi_device *hdev, new_wr_idx = wr_idx + dwords; wr_ptr = (u32 *)(queue->qmem.kva + (wr_idx << 2)); + + if (wr_ptr < (u32 *)queue->qmem.kva || + wr_ptr > (u32 *)(queue->qmem.kva + queue->qmem.size - sizeof(*wr_ptr))) + return -EINVAL; + if (new_wr_idx < qsize) { memcpy(wr_ptr, packet, dwords << 2); } else { @@ -272,6 +277,11 @@ static int venus_read_queue(struct venus_hfi_device *hdev, } rd_ptr = (u32 *)(queue->qmem.kva + (rd_idx << 2)); + + if (rd_ptr < (u32 *)queue->qmem.kva || + rd_ptr > (u32 *)(queue->qmem.kva + queue->qmem.size - sizeof(*rd_ptr))) + return -EINVAL; + dwords = *rd_ptr >> 2; if (!dwords) return -EINVAL; diff --git a/drivers/media/rc/imon.c b/drivers/media/rc/imon.c index 74546f7e34691..5719dda6e0f0e 100644 --- a/drivers/media/rc/imon.c +++ b/drivers/media/rc/imon.c @@ -2427,6 +2427,12 @@ static int imon_probe(struct usb_interface *interface, goto fail; } + if (first_if->dev.driver != interface->dev.driver) { + dev_err(&interface->dev, "inconsistent driver matching\n"); + ret = -EINVAL; + goto fail; + } + if (ifnum == 0) { ictx = imon_init_intf0(interface, id); if (!ictx) { diff --git a/drivers/media/rc/ir-sharp-decoder.c b/drivers/media/rc/ir-sharp-decoder.c index 3d8488c39c561..3311099cbd573 100644 --- a/drivers/media/rc/ir-sharp-decoder.c +++ b/drivers/media/rc/ir-sharp-decoder.c @@ -15,7 +15,9 @@ #define SHARP_UNIT 40 /* us */ #define SHARP_BIT_PULSE (8 * SHARP_UNIT) /* 320us */ #define SHARP_BIT_0_PERIOD (25 * SHARP_UNIT) /* 1ms (680us space) */ -#define SHARP_BIT_1_PERIOD (50 * SHARP_UNIT) /* 2ms (1680ms space) */ +#define SHARP_BIT_1_PERIOD (50 * SHARP_UNIT) /* 2ms (1680us space) */ +#define SHARP_BIT_0_SPACE (17 * SHARP_UNIT) /* 680us space */ +#define SHARP_BIT_1_SPACE (42 * SHARP_UNIT) /* 1680us space */ #define SHARP_ECHO_SPACE (1000 * SHARP_UNIT) /* 40 ms */ #define SHARP_TRAILER_SPACE (125 * SHARP_UNIT) /* 5 ms (even longer) */ @@ -168,8 +170,8 @@ static const struct ir_raw_timings_pd ir_sharp_timings = { .header_pulse = 0, .header_space = 0, .bit_pulse = SHARP_BIT_PULSE, - .bit_space[0] = SHARP_BIT_0_PERIOD, - .bit_space[1] = SHARP_BIT_1_PERIOD, + .bit_space[0] = SHARP_BIT_0_SPACE, + .bit_space[1] = SHARP_BIT_1_SPACE, .trailer_pulse = SHARP_BIT_PULSE, .trailer_space = SHARP_ECHO_SPACE, .msb_first = 1, diff --git a/drivers/media/rc/lirc_dev.c b/drivers/media/rc/lirc_dev.c index 043d23aaa3cbc..a537734832c50 100644 --- a/drivers/media/rc/lirc_dev.c +++ b/drivers/media/rc/lirc_dev.c @@ -276,7 +276,11 @@ static ssize_t lirc_transmit(struct file *file, const char __user *buf, if (ret < 0) goto out_kfree_raw; - count = ret; + /* drop trailing space */ + if (!(ret % 2)) + count = ret - 1; + else + count = ret; txbuf = kmalloc_array(count, sizeof(unsigned int), GFP_KERNEL); if (!txbuf) { diff --git a/drivers/media/test-drivers/vivid/vivid-rds-gen.c b/drivers/media/test-drivers/vivid/vivid-rds-gen.c index b5b104ee64c99..c57771119a34b 100644 --- a/drivers/media/test-drivers/vivid/vivid-rds-gen.c +++ b/drivers/media/test-drivers/vivid/vivid-rds-gen.c @@ -145,7 +145,7 @@ void vivid_rds_gen_fill(struct vivid_rds_gen *rds, unsigned freq, rds->ta = alt; rds->ms = true; snprintf(rds->psname, sizeof(rds->psname), "%6d.%1d", - freq / 16, ((freq & 0xf) * 10) / 16); + (freq / 16) % 1000000, (((freq & 0xf) * 10) / 16) % 10); if (alt) strscpy(rds->radiotext, " The Radio Data System can switch between different Radio Texts ", diff --git a/drivers/media/usb/gspca/cpia1.c b/drivers/media/usb/gspca/cpia1.c index 46ed95483e222..5f5fa851ca640 100644 --- a/drivers/media/usb/gspca/cpia1.c +++ b/drivers/media/usb/gspca/cpia1.c @@ -18,6 +18,7 @@ #include #include +#include #include "gspca.h" @@ -1028,6 +1029,8 @@ static int set_flicker(struct gspca_dev *gspca_dev, int on, int apply) sd->params.exposure.expMode = 2; sd->exposure_status = EXPOSURE_NORMAL; } + if (sd->params.exposure.gain >= BITS_PER_TYPE(currentexp)) + return -EINVAL; currentexp = currentexp << sd->params.exposure.gain; sd->params.exposure.gain = 0; /* round down current exposure to nearest value */ diff --git a/drivers/mfd/intel-lpss-pci.c b/drivers/mfd/intel-lpss-pci.c index 699f44ffff0e4..ae5759200622c 100644 --- a/drivers/mfd/intel-lpss-pci.c +++ b/drivers/mfd/intel-lpss-pci.c @@ -561,6 +561,19 @@ static const struct pci_device_id intel_lpss_pci_ids[] = { { PCI_VDEVICE(INTEL, 0xa3e2), (kernel_ulong_t)&spt_i2c_info }, { PCI_VDEVICE(INTEL, 0xa3e3), (kernel_ulong_t)&spt_i2c_info }, { PCI_VDEVICE(INTEL, 0xa3e6), (kernel_ulong_t)&spt_uart_info }, + /* LNL-M */ + { PCI_VDEVICE(INTEL, 0xa825), (kernel_ulong_t)&bxt_uart_info }, + { PCI_VDEVICE(INTEL, 0xa826), (kernel_ulong_t)&bxt_uart_info }, + { PCI_VDEVICE(INTEL, 0xa827), (kernel_ulong_t)&tgl_info }, + { PCI_VDEVICE(INTEL, 0xa830), (kernel_ulong_t)&tgl_info }, + { PCI_VDEVICE(INTEL, 0xa846), (kernel_ulong_t)&tgl_info }, + { PCI_VDEVICE(INTEL, 0xa850), (kernel_ulong_t)&ehl_i2c_info }, + { PCI_VDEVICE(INTEL, 0xa851), (kernel_ulong_t)&ehl_i2c_info }, + { PCI_VDEVICE(INTEL, 0xa852), (kernel_ulong_t)&bxt_uart_info }, + { PCI_VDEVICE(INTEL, 0xa878), (kernel_ulong_t)&ehl_i2c_info }, + { PCI_VDEVICE(INTEL, 0xa879), (kernel_ulong_t)&ehl_i2c_info }, + { PCI_VDEVICE(INTEL, 0xa87a), (kernel_ulong_t)&ehl_i2c_info }, + { PCI_VDEVICE(INTEL, 0xa87b), (kernel_ulong_t)&ehl_i2c_info }, { } }; MODULE_DEVICE_TABLE(pci, intel_lpss_pci_ids); diff --git a/drivers/mfd/qcom-spmi-pmic.c b/drivers/mfd/qcom-spmi-pmic.c index 7e2cd79d17ebf..8e449cff5cec4 100644 --- a/drivers/mfd/qcom-spmi-pmic.c +++ b/drivers/mfd/qcom-spmi-pmic.c @@ -30,6 +30,8 @@ struct qcom_spmi_dev { struct qcom_spmi_pmic pmic; }; +static DEFINE_MUTEX(pmic_spmi_revid_lock); + #define N_USIDS(n) ((void *)n) static const struct of_device_id pmic_spmi_id_table[] = { @@ -76,24 +78,21 @@ static const struct of_device_id pmic_spmi_id_table[] = { * * This only supports PMICs with 1 or 2 USIDs. */ -static struct spmi_device *qcom_pmic_get_base_usid(struct device *dev) +static struct spmi_device *qcom_pmic_get_base_usid(struct spmi_device *sdev, struct qcom_spmi_dev *ctx) { - struct spmi_device *sdev; - struct qcom_spmi_dev *ctx; struct device_node *spmi_bus; - struct device_node *other_usid = NULL; + struct device_node *child; int function_parent_usid, ret; u32 pmic_addr; - sdev = to_spmi_device(dev); - ctx = dev_get_drvdata(&sdev->dev); - /* * Quick return if the function device is already in the base * USID. This will always be hit for PMICs with only 1 USID. */ - if (sdev->usid % ctx->num_usids == 0) + if (sdev->usid % ctx->num_usids == 0) { + get_device(&sdev->dev); return sdev; + } function_parent_usid = sdev->usid; @@ -105,28 +104,61 @@ static struct spmi_device *qcom_pmic_get_base_usid(struct device *dev) * device for USID 2. */ spmi_bus = of_get_parent(sdev->dev.of_node); - do { - other_usid = of_get_next_child(spmi_bus, other_usid); - - ret = of_property_read_u32_index(other_usid, "reg", 0, &pmic_addr); - if (ret) - return ERR_PTR(ret); + sdev = ERR_PTR(-ENODATA); + for_each_child_of_node(spmi_bus, child) { + ret = of_property_read_u32_index(child, "reg", 0, &pmic_addr); + if (ret) { + of_node_put(child); + sdev = ERR_PTR(ret); + break; + } - sdev = spmi_device_from_of(other_usid); if (pmic_addr == function_parent_usid - (ctx->num_usids - 1)) { - if (!sdev) + sdev = spmi_device_from_of(child); + if (!sdev) { /* - * If the base USID for this PMIC hasn't probed yet - * but the secondary USID has, then we need to defer - * the function driver so that it will attempt to - * probe again when the base USID is ready. + * If the base USID for this PMIC hasn't been + * registered yet then we need to defer. */ - return ERR_PTR(-EPROBE_DEFER); - return sdev; + sdev = ERR_PTR(-EPROBE_DEFER); + } + of_node_put(child); + break; } - } while (other_usid->sibling); + } - return ERR_PTR(-ENODATA); + of_node_put(spmi_bus); + + return sdev; +} + +static int pmic_spmi_get_base_revid(struct spmi_device *sdev, struct qcom_spmi_dev *ctx) +{ + struct qcom_spmi_dev *base_ctx; + struct spmi_device *base; + int ret = 0; + + base = qcom_pmic_get_base_usid(sdev, ctx); + if (IS_ERR(base)) + return PTR_ERR(base); + + /* + * Copy revid info from base device if it has probed and is still + * bound to its driver. + */ + mutex_lock(&pmic_spmi_revid_lock); + base_ctx = spmi_device_get_drvdata(base); + if (!base_ctx) { + ret = -EPROBE_DEFER; + goto out_unlock; + } + memcpy(&ctx->pmic, &base_ctx->pmic, sizeof(ctx->pmic)); +out_unlock: + mutex_unlock(&pmic_spmi_revid_lock); + + put_device(&base->dev); + + return ret; } static int pmic_spmi_load_revid(struct regmap *map, struct device *dev, @@ -204,11 +236,7 @@ const struct qcom_spmi_pmic *qcom_pmic_get(struct device *dev) if (!of_match_device(pmic_spmi_id_table, dev->parent)) return ERR_PTR(-EINVAL); - sdev = qcom_pmic_get_base_usid(dev->parent); - - if (IS_ERR(sdev)) - return ERR_CAST(sdev); - + sdev = to_spmi_device(dev->parent); spmi = dev_get_drvdata(&sdev->dev); return &spmi->pmic; @@ -243,16 +271,31 @@ static int pmic_spmi_probe(struct spmi_device *sdev) ret = pmic_spmi_load_revid(regmap, &sdev->dev, &ctx->pmic); if (ret < 0) return ret; + } else { + ret = pmic_spmi_get_base_revid(sdev, ctx); + if (ret) + return ret; } + + mutex_lock(&pmic_spmi_revid_lock); spmi_device_set_drvdata(sdev, ctx); + mutex_unlock(&pmic_spmi_revid_lock); return devm_of_platform_populate(&sdev->dev); } +static void pmic_spmi_remove(struct spmi_device *sdev) +{ + mutex_lock(&pmic_spmi_revid_lock); + spmi_device_set_drvdata(sdev, NULL); + mutex_unlock(&pmic_spmi_revid_lock); +} + MODULE_DEVICE_TABLE(of, pmic_spmi_id_table); static struct spmi_driver pmic_spmi_driver = { .probe = pmic_spmi_probe, + .remove = pmic_spmi_remove, .driver = { .name = "pmic-spmi", .of_match_table = pmic_spmi_id_table, diff --git a/drivers/misc/mei/client.c b/drivers/misc/mei/client.c index 5c19097266fe0..32f2287823184 100644 --- a/drivers/misc/mei/client.c +++ b/drivers/misc/mei/client.c @@ -2011,7 +2011,7 @@ ssize_t mei_cl_write(struct mei_cl *cl, struct mei_cl_cb *cb, unsigned long time mei_hdr = mei_msg_hdr_init(cb); if (IS_ERR(mei_hdr)) { - rets = -PTR_ERR(mei_hdr); + rets = PTR_ERR(mei_hdr); mei_hdr = NULL; goto err; } @@ -2032,7 +2032,7 @@ ssize_t mei_cl_write(struct mei_cl *cl, struct mei_cl_cb *cb, unsigned long time hbuf_slots = mei_hbuf_empty_slots(dev); if (hbuf_slots < 0) { - rets = -EOVERFLOW; + buf_len = -EOVERFLOW; goto out; } diff --git a/drivers/misc/pci_endpoint_test.c b/drivers/misc/pci_endpoint_test.c index 7e1acc68d4359..af519088732d9 100644 --- a/drivers/misc/pci_endpoint_test.c +++ b/drivers/misc/pci_endpoint_test.c @@ -82,6 +82,7 @@ #define PCI_DEVICE_ID_RENESAS_R8A774B1 0x002b #define PCI_DEVICE_ID_RENESAS_R8A774C0 0x002d #define PCI_DEVICE_ID_RENESAS_R8A774E1 0x0025 +#define PCI_DEVICE_ID_RENESAS_R8A779F0 0x0031 static DEFINE_IDA(pci_endpoint_test_ida); @@ -991,6 +992,9 @@ static const struct pci_device_id pci_endpoint_test_tbl[] = { { PCI_DEVICE(PCI_VENDOR_ID_RENESAS, PCI_DEVICE_ID_RENESAS_R8A774B1),}, { PCI_DEVICE(PCI_VENDOR_ID_RENESAS, PCI_DEVICE_ID_RENESAS_R8A774C0),}, { PCI_DEVICE(PCI_VENDOR_ID_RENESAS, PCI_DEVICE_ID_RENESAS_R8A774E1),}, + { PCI_DEVICE(PCI_VENDOR_ID_RENESAS, PCI_DEVICE_ID_RENESAS_R8A779F0), + .driver_data = (kernel_ulong_t)&default_data, + }, { PCI_DEVICE(PCI_VENDOR_ID_TI, PCI_DEVICE_ID_TI_J721E), .driver_data = (kernel_ulong_t)&j721e_data, }, diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 3a8f27c3e310a..f9a5cffa64b1f 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -1482,6 +1482,8 @@ static void mmc_blk_cqe_complete_rq(struct mmc_queue *mq, struct request *req) blk_mq_requeue_request(req, true); else __blk_mq_end_request(req, BLK_STS_OK); + } else if (mq->in_recovery) { + blk_mq_requeue_request(req, true); } else { blk_mq_end_request(req, BLK_STS_OK); } @@ -2381,8 +2383,10 @@ enum mmc_issued mmc_blk_mq_issue_rq(struct mmc_queue *mq, struct request *req) } ret = mmc_blk_cqe_issue_flush(mq, req); break; - case REQ_OP_READ: case REQ_OP_WRITE: + card->written_flag = true; + fallthrough; + case REQ_OP_READ: if (host->cqe_enabled) ret = mmc_blk_cqe_issue_rw_rq(mq, req); else diff --git a/drivers/mmc/core/card.h b/drivers/mmc/core/card.h index 4edf9057fa79d..b7754a1b8d978 100644 --- a/drivers/mmc/core/card.h +++ b/drivers/mmc/core/card.h @@ -280,4 +280,8 @@ static inline int mmc_card_broken_sd_cache(const struct mmc_card *c) return c->quirks & MMC_QUIRK_BROKEN_SD_CACHE; } +static inline int mmc_card_broken_cache_flush(const struct mmc_card *c) +{ + return c->quirks & MMC_QUIRK_BROKEN_CACHE_FLUSH; +} #endif diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c index 3d3e0ca526148..a8c17b4cd7379 100644 --- a/drivers/mmc/core/core.c +++ b/drivers/mmc/core/core.c @@ -551,7 +551,9 @@ int mmc_cqe_recovery(struct mmc_host *host) cmd.flags = MMC_RSP_R1B | MMC_CMD_AC; cmd.flags &= ~MMC_RSP_CRC; /* Ignore CRC */ cmd.busy_timeout = MMC_CQE_RECOVERY_TIMEOUT; - mmc_wait_for_cmd(host, &cmd, 0); + mmc_wait_for_cmd(host, &cmd, MMC_CMD_RETRIES); + + mmc_poll_for_busy(host->card, MMC_CQE_RECOVERY_TIMEOUT, true, MMC_BUSY_IO); memset(&cmd, 0, sizeof(cmd)); cmd.opcode = MMC_CMDQ_TASK_MGMT; @@ -559,10 +561,13 @@ int mmc_cqe_recovery(struct mmc_host *host) cmd.flags = MMC_RSP_R1B | MMC_CMD_AC; cmd.flags &= ~MMC_RSP_CRC; /* Ignore CRC */ cmd.busy_timeout = MMC_CQE_RECOVERY_TIMEOUT; - err = mmc_wait_for_cmd(host, &cmd, 0); + err = mmc_wait_for_cmd(host, &cmd, MMC_CMD_RETRIES); host->cqe_ops->cqe_recovery_finish(host); + if (err) + err = mmc_wait_for_cmd(host, &cmd, MMC_CMD_RETRIES); + mmc_retune_release(host); return err; diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c index 89cd48fcec79f..a46ce0868fe1f 100644 --- a/drivers/mmc/core/mmc.c +++ b/drivers/mmc/core/mmc.c @@ -2081,13 +2081,17 @@ static int _mmc_flush_cache(struct mmc_host *host) { int err = 0; + if (mmc_card_broken_cache_flush(host->card) && !host->card->written_flag) + return 0; + if (_mmc_cache_enabled(host)) { err = mmc_switch(host->card, EXT_CSD_CMD_SET_NORMAL, EXT_CSD_FLUSH_CACHE, 1, CACHE_FLUSH_TIMEOUT_MS); if (err) - pr_err("%s: cache flush error %d\n", - mmc_hostname(host), err); + pr_err("%s: cache flush error %d\n", mmc_hostname(host), err); + else + host->card->written_flag = false; } return err; diff --git a/drivers/mmc/core/quirks.h b/drivers/mmc/core/quirks.h index 32b64b564fb1f..cca71867bc4ad 100644 --- a/drivers/mmc/core/quirks.h +++ b/drivers/mmc/core/quirks.h @@ -110,11 +110,12 @@ static const struct mmc_fixup __maybe_unused mmc_blk_fixups[] = { MMC_QUIRK_TRIM_BROKEN), /* - * Micron MTFC4GACAJCN-1M advertises TRIM but it does not seems to - * support being used to offload WRITE_ZEROES. + * Micron MTFC4GACAJCN-1M supports TRIM but does not appear to support + * WRITE_ZEROES offloading. It also supports caching, but the cache can + * only be flushed after a write has occurred. */ MMC_FIXUP("Q2J54A", CID_MANFID_MICRON, 0x014e, add_quirk_mmc, - MMC_QUIRK_TRIM_BROKEN), + MMC_QUIRK_TRIM_BROKEN | MMC_QUIRK_BROKEN_CACHE_FLUSH), /* * Kingston EMMC04G-M627 advertises TRIM but it does not seems to diff --git a/drivers/mmc/host/cqhci-core.c b/drivers/mmc/host/cqhci-core.c index b3d7d6d8d6548..41e94cd141098 100644 --- a/drivers/mmc/host/cqhci-core.c +++ b/drivers/mmc/host/cqhci-core.c @@ -942,8 +942,8 @@ static bool cqhci_clear_all_tasks(struct mmc_host *mmc, unsigned int timeout) ret = cqhci_tasks_cleared(cq_host); if (!ret) - pr_debug("%s: cqhci: Failed to clear tasks\n", - mmc_hostname(mmc)); + pr_warn("%s: cqhci: Failed to clear tasks\n", + mmc_hostname(mmc)); return ret; } @@ -976,7 +976,7 @@ static bool cqhci_halt(struct mmc_host *mmc, unsigned int timeout) ret = cqhci_halted(cq_host); if (!ret) - pr_debug("%s: cqhci: Failed to halt\n", mmc_hostname(mmc)); + pr_warn("%s: cqhci: Failed to halt\n", mmc_hostname(mmc)); return ret; } @@ -984,10 +984,10 @@ static bool cqhci_halt(struct mmc_host *mmc, unsigned int timeout) /* * After halting we expect to be able to use the command line. We interpret the * failure to halt to mean the data lines might still be in use (and the upper - * layers will need to send a STOP command), so we set the timeout based on a - * generous command timeout. + * layers will need to send a STOP command), however failing to halt complicates + * the recovery, so set a timeout that would reasonably allow I/O to complete. */ -#define CQHCI_START_HALT_TIMEOUT 5 +#define CQHCI_START_HALT_TIMEOUT 500 static void cqhci_recovery_start(struct mmc_host *mmc) { @@ -1075,28 +1075,28 @@ static void cqhci_recovery_finish(struct mmc_host *mmc) ok = cqhci_halt(mmc, CQHCI_FINISH_HALT_TIMEOUT); - if (!cqhci_clear_all_tasks(mmc, CQHCI_CLEAR_TIMEOUT)) - ok = false; - /* * The specification contradicts itself, by saying that tasks cannot be * cleared if CQHCI does not halt, but if CQHCI does not halt, it should * be disabled/re-enabled, but not to disable before clearing tasks. * Have a go anyway. */ - if (!ok) { - pr_debug("%s: cqhci: disable / re-enable\n", mmc_hostname(mmc)); - cqcfg = cqhci_readl(cq_host, CQHCI_CFG); - cqcfg &= ~CQHCI_ENABLE; - cqhci_writel(cq_host, cqcfg, CQHCI_CFG); - cqcfg |= CQHCI_ENABLE; - cqhci_writel(cq_host, cqcfg, CQHCI_CFG); - /* Be sure that there are no tasks */ - ok = cqhci_halt(mmc, CQHCI_FINISH_HALT_TIMEOUT); - if (!cqhci_clear_all_tasks(mmc, CQHCI_CLEAR_TIMEOUT)) - ok = false; - WARN_ON(!ok); - } + if (!cqhci_clear_all_tasks(mmc, CQHCI_CLEAR_TIMEOUT)) + ok = false; + + /* Disable to make sure tasks really are cleared */ + cqcfg = cqhci_readl(cq_host, CQHCI_CFG); + cqcfg &= ~CQHCI_ENABLE; + cqhci_writel(cq_host, cqcfg, CQHCI_CFG); + + cqcfg = cqhci_readl(cq_host, CQHCI_CFG); + cqcfg |= CQHCI_ENABLE; + cqhci_writel(cq_host, cqcfg, CQHCI_CFG); + + cqhci_halt(mmc, CQHCI_FINISH_HALT_TIMEOUT); + + if (!ok) + cqhci_clear_all_tasks(mmc, CQHCI_CLEAR_TIMEOUT); cqhci_recover_mrqs(cq_host); diff --git a/drivers/mmc/host/meson-gx-mmc.c b/drivers/mmc/host/meson-gx-mmc.c index 9837dab096e64..c7c067b9415a4 100644 --- a/drivers/mmc/host/meson-gx-mmc.c +++ b/drivers/mmc/host/meson-gx-mmc.c @@ -801,7 +801,6 @@ static void meson_mmc_start_cmd(struct mmc_host *mmc, struct mmc_command *cmd) cmd_cfg |= FIELD_PREP(CMD_CFG_CMD_INDEX_MASK, cmd->opcode); cmd_cfg |= CMD_CFG_OWNER; /* owned by CPU */ - cmd_cfg |= CMD_CFG_ERROR; /* stop in case of error */ meson_mmc_set_response_bits(cmd, &cmd_cfg); diff --git a/drivers/mmc/host/sdhci-pci-gli.c b/drivers/mmc/host/sdhci-pci-gli.c index 109d4b010f978..77911a57b12cf 100644 --- a/drivers/mmc/host/sdhci-pci-gli.c +++ b/drivers/mmc/host/sdhci-pci-gli.c @@ -25,6 +25,12 @@ #define GLI_9750_WT_EN_ON 0x1 #define GLI_9750_WT_EN_OFF 0x0 +#define PCI_GLI_9750_PM_CTRL 0xFC +#define PCI_GLI_9750_PM_STATE GENMASK(1, 0) + +#define PCI_GLI_9750_CORRERR_MASK 0x214 +#define PCI_GLI_9750_CORRERR_MASK_REPLAY_TIMER_TIMEOUT BIT(12) + #define SDHCI_GLI_9750_CFG2 0x848 #define SDHCI_GLI_9750_CFG2_L1DLY GENMASK(28, 24) #define GLI_9750_CFG2_L1DLY_VALUE 0x1F @@ -149,6 +155,9 @@ #define PCI_GLI_9755_PM_CTRL 0xFC #define PCI_GLI_9755_PM_STATE GENMASK(1, 0) +#define PCI_GLI_9755_CORRERR_MASK 0x214 +#define PCI_GLI_9755_CORRERR_MASK_REPLAY_TIMER_TIMEOUT BIT(12) + #define SDHCI_GLI_9767_GM_BURST_SIZE 0x510 #define SDHCI_GLI_9767_GM_BURST_SIZE_AXI_ALWAYS_SET BIT(8) @@ -536,8 +545,12 @@ static void sdhci_gl9750_set_clock(struct sdhci_host *host, unsigned int clock) static void gl9750_hw_setting(struct sdhci_host *host) { + struct sdhci_pci_slot *slot = sdhci_priv(host); + struct pci_dev *pdev; u32 value; + pdev = slot->chip->pdev; + gl9750_wt_on(host); value = sdhci_readl(host, SDHCI_GLI_9750_CFG2); @@ -547,6 +560,18 @@ static void gl9750_hw_setting(struct sdhci_host *host) GLI_9750_CFG2_L1DLY_VALUE); sdhci_writel(host, value, SDHCI_GLI_9750_CFG2); + /* toggle PM state to allow GL9750 to enter ASPM L1.2 */ + pci_read_config_dword(pdev, PCI_GLI_9750_PM_CTRL, &value); + value |= PCI_GLI_9750_PM_STATE; + pci_write_config_dword(pdev, PCI_GLI_9750_PM_CTRL, value); + value &= ~PCI_GLI_9750_PM_STATE; + pci_write_config_dword(pdev, PCI_GLI_9750_PM_CTRL, value); + + /* mask the replay timer timeout of AER */ + pci_read_config_dword(pdev, PCI_GLI_9750_CORRERR_MASK, &value); + value |= PCI_GLI_9750_CORRERR_MASK_REPLAY_TIMER_TIMEOUT; + pci_write_config_dword(pdev, PCI_GLI_9750_CORRERR_MASK, value); + gl9750_wt_off(host); } @@ -756,6 +781,11 @@ static void gl9755_hw_setting(struct sdhci_pci_slot *slot) value &= ~PCI_GLI_9755_PM_STATE; pci_write_config_dword(pdev, PCI_GLI_9755_PM_CTRL, value); + /* mask the replay timer timeout of AER */ + pci_read_config_dword(pdev, PCI_GLI_9755_CORRERR_MASK, &value); + value |= PCI_GLI_9755_CORRERR_MASK_REPLAY_TIMER_TIMEOUT; + pci_write_config_dword(pdev, PCI_GLI_9755_CORRERR_MASK, value); + gl9755_wt_off(pdev); } @@ -1159,6 +1189,32 @@ static void gl9763e_hs400_enhanced_strobe(struct mmc_host *mmc, sdhci_writel(host, val, SDHCI_GLI_9763E_HS400_ES_REG); } +static void gl9763e_set_low_power_negotiation(struct sdhci_pci_slot *slot, + bool enable) +{ + struct pci_dev *pdev = slot->chip->pdev; + u32 value; + + pci_read_config_dword(pdev, PCIE_GLI_9763E_VHS, &value); + value &= ~GLI_9763E_VHS_REV; + value |= FIELD_PREP(GLI_9763E_VHS_REV, GLI_9763E_VHS_REV_W); + pci_write_config_dword(pdev, PCIE_GLI_9763E_VHS, value); + + pci_read_config_dword(pdev, PCIE_GLI_9763E_CFG, &value); + + if (enable) + value &= ~GLI_9763E_CFG_LPSN_DIS; + else + value |= GLI_9763E_CFG_LPSN_DIS; + + pci_write_config_dword(pdev, PCIE_GLI_9763E_CFG, value); + + pci_read_config_dword(pdev, PCIE_GLI_9763E_VHS, &value); + value &= ~GLI_9763E_VHS_REV; + value |= FIELD_PREP(GLI_9763E_VHS_REV, GLI_9763E_VHS_REV_R); + pci_write_config_dword(pdev, PCIE_GLI_9763E_VHS, value); +} + static void sdhci_set_gl9763e_signaling(struct sdhci_host *host, unsigned int timing) { @@ -1267,6 +1323,9 @@ static int gl9763e_add_host(struct sdhci_pci_slot *slot) if (ret) goto cleanup; + /* Disable LPM negotiation to avoid entering L1 state. */ + gl9763e_set_low_power_negotiation(slot, false); + return 0; cleanup: @@ -1310,31 +1369,6 @@ static void gli_set_gl9763e(struct sdhci_pci_slot *slot) } #ifdef CONFIG_PM -static void gl9763e_set_low_power_negotiation(struct sdhci_pci_slot *slot, bool enable) -{ - struct pci_dev *pdev = slot->chip->pdev; - u32 value; - - pci_read_config_dword(pdev, PCIE_GLI_9763E_VHS, &value); - value &= ~GLI_9763E_VHS_REV; - value |= FIELD_PREP(GLI_9763E_VHS_REV, GLI_9763E_VHS_REV_W); - pci_write_config_dword(pdev, PCIE_GLI_9763E_VHS, value); - - pci_read_config_dword(pdev, PCIE_GLI_9763E_CFG, &value); - - if (enable) - value &= ~GLI_9763E_CFG_LPSN_DIS; - else - value |= GLI_9763E_CFG_LPSN_DIS; - - pci_write_config_dword(pdev, PCIE_GLI_9763E_CFG, value); - - pci_read_config_dword(pdev, PCIE_GLI_9763E_VHS, &value); - value &= ~GLI_9763E_VHS_REV; - value |= FIELD_PREP(GLI_9763E_VHS_REV, GLI_9763E_VHS_REV_R); - pci_write_config_dword(pdev, PCIE_GLI_9763E_VHS, value); -} - static int gl9763e_runtime_suspend(struct sdhci_pci_chip *chip) { struct sdhci_pci_slot *slot = chip->slots[0]; diff --git a/drivers/mmc/host/sdhci-sprd.c b/drivers/mmc/host/sdhci-sprd.c index 6b84ba27e6ab0..6b8a57e2d20f0 100644 --- a/drivers/mmc/host/sdhci-sprd.c +++ b/drivers/mmc/host/sdhci-sprd.c @@ -416,12 +416,33 @@ static void sdhci_sprd_request_done(struct sdhci_host *host, mmc_request_done(host->mmc, mrq); } +static void sdhci_sprd_set_power(struct sdhci_host *host, unsigned char mode, + unsigned short vdd) +{ + struct mmc_host *mmc = host->mmc; + + switch (mode) { + case MMC_POWER_OFF: + mmc_regulator_set_ocr(host->mmc, mmc->supply.vmmc, 0); + + mmc_regulator_disable_vqmmc(mmc); + break; + case MMC_POWER_ON: + mmc_regulator_enable_vqmmc(mmc); + break; + case MMC_POWER_UP: + mmc_regulator_set_ocr(host->mmc, mmc->supply.vmmc, vdd); + break; + } +} + static struct sdhci_ops sdhci_sprd_ops = { .read_l = sdhci_sprd_readl, .write_l = sdhci_sprd_writel, .write_w = sdhci_sprd_writew, .write_b = sdhci_sprd_writeb, .set_clock = sdhci_sprd_set_clock, + .set_power = sdhci_sprd_set_power, .get_max_clock = sdhci_sprd_get_max_clock, .get_min_clock = sdhci_sprd_get_min_clock, .set_bus_width = sdhci_set_bus_width, @@ -823,6 +844,10 @@ static int sdhci_sprd_probe(struct platform_device *pdev) host->caps1 &= ~(SDHCI_SUPPORT_SDR50 | SDHCI_SUPPORT_SDR104 | SDHCI_SUPPORT_DDR50); + ret = mmc_regulator_get_supply(host->mmc); + if (ret) + goto pm_runtime_disable; + ret = sdhci_setup_host(host); if (ret) goto pm_runtime_disable; diff --git a/drivers/mmc/host/sdhci_am654.c b/drivers/mmc/host/sdhci_am654.c index c125485ba80e9..967bd2dfcda1b 100644 --- a/drivers/mmc/host/sdhci_am654.c +++ b/drivers/mmc/host/sdhci_am654.c @@ -598,7 +598,7 @@ static int sdhci_am654_get_otap_delay(struct sdhci_host *host, return 0; } - for (i = MMC_TIMING_MMC_HS; i <= MMC_TIMING_MMC_HS400; i++) { + for (i = MMC_TIMING_LEGACY; i <= MMC_TIMING_MMC_HS400; i++) { ret = device_property_read_u32(dev, td[i].otap_binding, &sdhci_am654->otap_del_sel[i]); diff --git a/drivers/mmc/host/vub300.c b/drivers/mmc/host/vub300.c index 9ec593d52f0fa..cef0e716ad16f 100644 --- a/drivers/mmc/host/vub300.c +++ b/drivers/mmc/host/vub300.c @@ -2309,6 +2309,7 @@ static int vub300_probe(struct usb_interface *interface, vub300->read_only = (0x0010 & vub300->system_port_status.port_flags) ? 1 : 0; } else { + retval = -EINVAL; goto error5; } usb_set_intfdata(interface, vub300); diff --git a/drivers/mtd/chips/cfi_cmdset_0001.c b/drivers/mtd/chips/cfi_cmdset_0001.c index 11b06fefaa0e2..c10693ba265ba 100644 --- a/drivers/mtd/chips/cfi_cmdset_0001.c +++ b/drivers/mtd/chips/cfi_cmdset_0001.c @@ -422,9 +422,25 @@ read_pri_intelext(struct map_info *map, __u16 adr) extra_size = 0; /* Protection Register info */ - if (extp->NumProtectionFields) + if (extp->NumProtectionFields) { + struct cfi_intelext_otpinfo *otp = + (struct cfi_intelext_otpinfo *)&extp->extra[0]; + extra_size += (extp->NumProtectionFields - 1) * - sizeof(struct cfi_intelext_otpinfo); + sizeof(struct cfi_intelext_otpinfo); + + if (extp_size >= sizeof(*extp) + extra_size) { + int i; + + /* Do some byteswapping if necessary */ + for (i = 0; i < extp->NumProtectionFields - 1; i++) { + otp->ProtRegAddr = le32_to_cpu(otp->ProtRegAddr); + otp->FactGroups = le16_to_cpu(otp->FactGroups); + otp->UserGroups = le16_to_cpu(otp->UserGroups); + otp++; + } + } + } } if (extp->MinorVersion >= '1') { diff --git a/drivers/mtd/nand/raw/intel-nand-controller.c b/drivers/mtd/nand/raw/intel-nand-controller.c index cb5d88f42297b..f0ad2308f6d50 100644 --- a/drivers/mtd/nand/raw/intel-nand-controller.c +++ b/drivers/mtd/nand/raw/intel-nand-controller.c @@ -619,6 +619,11 @@ static int ebu_nand_probe(struct platform_device *pdev) ebu_host->cs_num = cs; resname = devm_kasprintf(dev, GFP_KERNEL, "nand_cs%d", cs); + if (!resname) { + ret = -ENOMEM; + goto err_of_node_put; + } + ebu_host->cs[cs].chipaddr = devm_platform_ioremap_resource_byname(pdev, resname); if (IS_ERR(ebu_host->cs[cs].chipaddr)) { @@ -649,6 +654,11 @@ static int ebu_nand_probe(struct platform_device *pdev) } resname = devm_kasprintf(dev, GFP_KERNEL, "addr_sel%d", cs); + if (!resname) { + ret = -ENOMEM; + goto err_cleanup_dma; + } + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, resname); if (!res) { ret = -EINVAL; diff --git a/drivers/mtd/nand/raw/meson_nand.c b/drivers/mtd/nand/raw/meson_nand.c index 25e3c1cb605e7..a506e658d4624 100644 --- a/drivers/mtd/nand/raw/meson_nand.c +++ b/drivers/mtd/nand/raw/meson_nand.c @@ -1134,6 +1134,9 @@ static int meson_nfc_clk_init(struct meson_nfc *nfc) init.name = devm_kasprintf(nfc->dev, GFP_KERNEL, "%s#div", dev_name(nfc->dev)); + if (!init.name) + return -ENOMEM; + init.ops = &clk_divider_ops; nfc_divider_parent_data[0].fw_name = "device"; init.parent_data = nfc_divider_parent_data; diff --git a/drivers/mtd/nand/raw/tegra_nand.c b/drivers/mtd/nand/raw/tegra_nand.c index eb0b9d16e8dae..a553e3ac8ff41 100644 --- a/drivers/mtd/nand/raw/tegra_nand.c +++ b/drivers/mtd/nand/raw/tegra_nand.c @@ -1197,6 +1197,10 @@ static int tegra_nand_probe(struct platform_device *pdev) init_completion(&ctrl->dma_complete); ctrl->irq = platform_get_irq(pdev, 0); + if (ctrl->irq < 0) { + err = ctrl->irq; + goto err_put_pm; + } err = devm_request_irq(&pdev->dev, ctrl->irq, tegra_nand_irq, 0, dev_name(&pdev->dev), ctrl); if (err) { diff --git a/drivers/net/arcnet/arcdevice.h b/drivers/net/arcnet/arcdevice.h index 19e996a829c9d..b54275389f8ac 100644 --- a/drivers/net/arcnet/arcdevice.h +++ b/drivers/net/arcnet/arcdevice.h @@ -186,6 +186,8 @@ do { \ #define ARC_IS_5MBIT 1 /* card default speed is 5MBit */ #define ARC_CAN_10MBIT 2 /* card uses COM20022, supporting 10MBit, but default is 2.5MBit. */ +#define ARC_HAS_LED 4 /* card has software controlled LEDs */ +#define ARC_HAS_ROTARY 8 /* card has rotary encoder */ /* information needed to define an encapsulation driver */ struct ArcProto { diff --git a/drivers/net/arcnet/com20020-pci.c b/drivers/net/arcnet/com20020-pci.c index c580acb8b1d34..7b5c8bb02f119 100644 --- a/drivers/net/arcnet/com20020-pci.c +++ b/drivers/net/arcnet/com20020-pci.c @@ -213,12 +213,13 @@ static int com20020pci_probe(struct pci_dev *pdev, if (!strncmp(ci->name, "EAE PLX-PCI FB2", 15)) lp->backplane = 1; - /* Get the dev_id from the PLX rotary coder */ - if (!strncmp(ci->name, "EAE PLX-PCI MA1", 15)) - dev_id_mask = 0x3; - dev->dev_id = (inb(priv->misc + ci->rotary) >> 4) & dev_id_mask; - - snprintf(dev->name, sizeof(dev->name), "arc%d-%d", dev->dev_id, i); + if (ci->flags & ARC_HAS_ROTARY) { + /* Get the dev_id from the PLX rotary coder */ + if (!strncmp(ci->name, "EAE PLX-PCI MA1", 15)) + dev_id_mask = 0x3; + dev->dev_id = (inb(priv->misc + ci->rotary) >> 4) & dev_id_mask; + snprintf(dev->name, sizeof(dev->name), "arc%d-%d", dev->dev_id, i); + } if (arcnet_inb(ioaddr, COM20020_REG_R_STATUS) == 0xFF) { pr_err("IO address %Xh is empty!\n", ioaddr); @@ -230,6 +231,10 @@ static int com20020pci_probe(struct pci_dev *pdev, goto err_free_arcdev; } + ret = com20020_found(dev, IRQF_SHARED); + if (ret) + goto err_free_arcdev; + card = devm_kzalloc(&pdev->dev, sizeof(struct com20020_dev), GFP_KERNEL); if (!card) { @@ -239,41 +244,39 @@ static int com20020pci_probe(struct pci_dev *pdev, card->index = i; card->pci_priv = priv; - card->tx_led.brightness_set = led_tx_set; - card->tx_led.default_trigger = devm_kasprintf(&pdev->dev, - GFP_KERNEL, "arc%d-%d-tx", - dev->dev_id, i); - card->tx_led.name = devm_kasprintf(&pdev->dev, GFP_KERNEL, - "pci:green:tx:%d-%d", - dev->dev_id, i); - - card->tx_led.dev = &dev->dev; - card->recon_led.brightness_set = led_recon_set; - card->recon_led.default_trigger = devm_kasprintf(&pdev->dev, - GFP_KERNEL, "arc%d-%d-recon", - dev->dev_id, i); - card->recon_led.name = devm_kasprintf(&pdev->dev, GFP_KERNEL, - "pci:red:recon:%d-%d", - dev->dev_id, i); - card->recon_led.dev = &dev->dev; - card->dev = dev; - - ret = devm_led_classdev_register(&pdev->dev, &card->tx_led); - if (ret) - goto err_free_arcdev; - ret = devm_led_classdev_register(&pdev->dev, &card->recon_led); - if (ret) - goto err_free_arcdev; - - dev_set_drvdata(&dev->dev, card); - - ret = com20020_found(dev, IRQF_SHARED); - if (ret) - goto err_free_arcdev; - - devm_arcnet_led_init(dev, dev->dev_id, i); + if (ci->flags & ARC_HAS_LED) { + card->tx_led.brightness_set = led_tx_set; + card->tx_led.default_trigger = devm_kasprintf(&pdev->dev, + GFP_KERNEL, "arc%d-%d-tx", + dev->dev_id, i); + card->tx_led.name = devm_kasprintf(&pdev->dev, GFP_KERNEL, + "pci:green:tx:%d-%d", + dev->dev_id, i); + + card->tx_led.dev = &dev->dev; + card->recon_led.brightness_set = led_recon_set; + card->recon_led.default_trigger = devm_kasprintf(&pdev->dev, + GFP_KERNEL, "arc%d-%d-recon", + dev->dev_id, i); + card->recon_led.name = devm_kasprintf(&pdev->dev, GFP_KERNEL, + "pci:red:recon:%d-%d", + dev->dev_id, i); + card->recon_led.dev = &dev->dev; + + ret = devm_led_classdev_register(&pdev->dev, &card->tx_led); + if (ret) + goto err_free_arcdev; + + ret = devm_led_classdev_register(&pdev->dev, &card->recon_led); + if (ret) + goto err_free_arcdev; + + dev_set_drvdata(&dev->dev, card); + devm_arcnet_led_init(dev, dev->dev_id, i); + } + card->dev = dev; list_add(&card->list, &priv->list_dev); continue; @@ -329,7 +332,7 @@ static struct com20020_pci_card_info card_info_5mbit = { }; static struct com20020_pci_card_info card_info_sohard = { - .name = "PLX-PCI", + .name = "SOHARD SH ARC-PCI", .devcount = 1, /* SOHARD needs PCI base addr 4 */ .chan_map_tbl = { @@ -364,7 +367,7 @@ static struct com20020_pci_card_info card_info_eae_arc1 = { }, }, .rotary = 0x0, - .flags = ARC_CAN_10MBIT, + .flags = ARC_HAS_ROTARY | ARC_HAS_LED | ARC_CAN_10MBIT, }; static struct com20020_pci_card_info card_info_eae_ma1 = { @@ -396,7 +399,7 @@ static struct com20020_pci_card_info card_info_eae_ma1 = { }, }, .rotary = 0x0, - .flags = ARC_CAN_10MBIT, + .flags = ARC_HAS_ROTARY | ARC_HAS_LED | ARC_CAN_10MBIT, }; static struct com20020_pci_card_info card_info_eae_fb2 = { @@ -421,7 +424,7 @@ static struct com20020_pci_card_info card_info_eae_fb2 = { }, }, .rotary = 0x0, - .flags = ARC_CAN_10MBIT, + .flags = ARC_HAS_ROTARY | ARC_HAS_LED | ARC_CAN_10MBIT, }; static const struct pci_device_id com20020pci_id_table[] = { diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 51d47eda1c873..8e6cc0e133b7f 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1500,6 +1500,10 @@ static void bond_compute_features(struct bonding *bond) static void bond_setup_by_slave(struct net_device *bond_dev, struct net_device *slave_dev) { + bool was_up = !!(bond_dev->flags & IFF_UP); + + dev_close(bond_dev); + bond_dev->header_ops = slave_dev->header_ops; bond_dev->type = slave_dev->type; @@ -1514,6 +1518,8 @@ static void bond_setup_by_slave(struct net_device *bond_dev, bond_dev->flags &= ~(IFF_BROADCAST | IFF_MULTICAST); bond_dev->flags |= (IFF_POINTOPOINT | IFF_NOARP); } + if (was_up) + dev_open(bond_dev, NULL); } /* On bonding slaves other than the currently active slave, suppress diff --git a/drivers/net/dsa/lan9303_mdio.c b/drivers/net/dsa/lan9303_mdio.c index d8ab2b77d201e..167a86f39f277 100644 --- a/drivers/net/dsa/lan9303_mdio.c +++ b/drivers/net/dsa/lan9303_mdio.c @@ -32,7 +32,7 @@ static int lan9303_mdio_write(void *ctx, uint32_t reg, uint32_t val) struct lan9303_mdio *sw_dev = (struct lan9303_mdio *)ctx; reg <<= 2; /* reg num to offset */ - mutex_lock(&sw_dev->device->bus->mdio_lock); + mutex_lock_nested(&sw_dev->device->bus->mdio_lock, MDIO_MUTEX_NESTED); lan9303_mdio_real_write(sw_dev->device, reg, val & 0xffff); lan9303_mdio_real_write(sw_dev->device, reg + 2, (val >> 16) & 0xffff); mutex_unlock(&sw_dev->device->bus->mdio_lock); @@ -50,7 +50,7 @@ static int lan9303_mdio_read(void *ctx, uint32_t reg, uint32_t *val) struct lan9303_mdio *sw_dev = (struct lan9303_mdio *)ctx; reg <<= 2; /* reg num to offset */ - mutex_lock(&sw_dev->device->bus->mdio_lock); + mutex_lock_nested(&sw_dev->device->bus->mdio_lock, MDIO_MUTEX_NESTED); *val = lan9303_mdio_real_read(sw_dev->device, reg); *val |= (lan9303_mdio_real_read(sw_dev->device, reg + 2) << 16); mutex_unlock(&sw_dev->device->bus->mdio_lock); diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 42db7679c3606..286e20f340e5c 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -2624,10 +2624,18 @@ static int ksz_connect_tag_protocol(struct dsa_switch *ds, { struct ksz_tagger_data *tagger_data; - tagger_data = ksz_tagger_data(ds); - tagger_data->xmit_work_fn = ksz_port_deferred_xmit; - - return 0; + switch (proto) { + case DSA_TAG_PROTO_KSZ8795: + return 0; + case DSA_TAG_PROTO_KSZ9893: + case DSA_TAG_PROTO_KSZ9477: + case DSA_TAG_PROTO_LAN937X: + tagger_data = ksz_tagger_data(ds); + tagger_data->xmit_work_fn = ksz_port_deferred_xmit; + return 0; + default: + return -EPROTONOSUPPORT; + } } static int ksz_port_vlan_filtering(struct dsa_switch *ds, int port, diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index ab434a77b059a..dc7f9b99f409f 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -577,6 +577,18 @@ static void mv88e6250_phylink_get_caps(struct mv88e6xxx_chip *chip, int port, config->mac_capabilities = MAC_SYM_PAUSE | MAC_10 | MAC_100; } +static void mv88e6351_phylink_get_caps(struct mv88e6xxx_chip *chip, int port, + struct phylink_config *config) +{ + unsigned long *supported = config->supported_interfaces; + + /* Translate the default cmode */ + mv88e6xxx_translate_cmode(chip->ports[port].cmode, supported); + + config->mac_capabilities = MAC_SYM_PAUSE | MAC_10 | MAC_100 | + MAC_1000FD; +} + static int mv88e6352_get_port4_serdes_cmode(struct mv88e6xxx_chip *chip) { u16 reg, val; @@ -3880,7 +3892,8 @@ static int mv88e6xxx_port_setup(struct dsa_switch *ds, int port) struct mv88e6xxx_chip *chip = ds->priv; int err; - if (chip->info->ops->pcs_ops->pcs_init) { + if (chip->info->ops->pcs_ops && + chip->info->ops->pcs_ops->pcs_init) { err = chip->info->ops->pcs_ops->pcs_init(chip, port); if (err) return err; @@ -3895,7 +3908,8 @@ static void mv88e6xxx_port_teardown(struct dsa_switch *ds, int port) mv88e6xxx_teardown_devlink_regions_port(ds, port); - if (chip->info->ops->pcs_ops->pcs_teardown) + if (chip->info->ops->pcs_ops && + chip->info->ops->pcs_ops->pcs_teardown) chip->info->ops->pcs_ops->pcs_teardown(chip, port); } @@ -4340,7 +4354,7 @@ static const struct mv88e6xxx_ops mv88e6171_ops = { .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, .stu_getnext = mv88e6352_g1_stu_getnext, .stu_loadpurge = mv88e6352_g1_stu_loadpurge, - .phylink_get_caps = mv88e6185_phylink_get_caps, + .phylink_get_caps = mv88e6351_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6172_ops = { @@ -4440,7 +4454,7 @@ static const struct mv88e6xxx_ops mv88e6175_ops = { .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, .stu_getnext = mv88e6352_g1_stu_getnext, .stu_loadpurge = mv88e6352_g1_stu_loadpurge, - .phylink_get_caps = mv88e6185_phylink_get_caps, + .phylink_get_caps = mv88e6351_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6176_ops = { @@ -5069,7 +5083,7 @@ static const struct mv88e6xxx_ops mv88e6350_ops = { .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, .stu_getnext = mv88e6352_g1_stu_getnext, .stu_loadpurge = mv88e6352_g1_stu_loadpurge, - .phylink_get_caps = mv88e6185_phylink_get_caps, + .phylink_get_caps = mv88e6351_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6351_ops = { @@ -5117,7 +5131,7 @@ static const struct mv88e6xxx_ops mv88e6351_ops = { .stu_loadpurge = mv88e6352_g1_stu_loadpurge, .avb_ops = &mv88e6352_avb_ops, .ptp_ops = &mv88e6352_ptp_ops, - .phylink_get_caps = mv88e6185_phylink_get_caps, + .phylink_get_caps = mv88e6351_phylink_get_caps, }; static const struct mv88e6xxx_ops mv88e6352_ops = { diff --git a/drivers/net/dsa/mv88e6xxx/pcs-639x.c b/drivers/net/dsa/mv88e6xxx/pcs-639x.c index ba373656bfe14..c31f0e54f1e64 100644 --- a/drivers/net/dsa/mv88e6xxx/pcs-639x.c +++ b/drivers/net/dsa/mv88e6xxx/pcs-639x.c @@ -465,6 +465,7 @@ mv88e639x_pcs_select(struct mv88e6xxx_chip *chip, int port, case PHY_INTERFACE_MODE_10GBASER: case PHY_INTERFACE_MODE_XAUI: case PHY_INTERFACE_MODE_RXAUI: + case PHY_INTERFACE_MODE_USXGMII: return &mpcs->xg_pcs; default: @@ -873,7 +874,8 @@ static int mv88e6393x_xg_pcs_post_config(struct phylink_pcs *pcs, struct mv88e639x_pcs *mpcs = xg_pcs_to_mv88e639x_pcs(pcs); int err; - if (interface == PHY_INTERFACE_MODE_10GBASER) { + if (interface == PHY_INTERFACE_MODE_10GBASER || + interface == PHY_INTERFACE_MODE_USXGMII) { err = mv88e6393x_erratum_5_2(mpcs); if (err) return err; @@ -886,12 +888,37 @@ static int mv88e6393x_xg_pcs_post_config(struct phylink_pcs *pcs, return mv88e639x_xg_pcs_enable(mpcs); } +static void mv88e6393x_xg_pcs_get_state(struct phylink_pcs *pcs, + struct phylink_link_state *state) +{ + struct mv88e639x_pcs *mpcs = xg_pcs_to_mv88e639x_pcs(pcs); + u16 status, lp_status; + int err; + + if (state->interface != PHY_INTERFACE_MODE_USXGMII) + return mv88e639x_xg_pcs_get_state(pcs, state); + + state->link = false; + + err = mv88e639x_read(mpcs, MV88E6390_USXGMII_PHY_STATUS, &status); + err = err ? : mv88e639x_read(mpcs, MV88E6390_USXGMII_LP_STATUS, &lp_status); + if (err) { + dev_err(mpcs->mdio.dev.parent, + "can't read USXGMII status: %pe\n", ERR_PTR(err)); + return; + } + + state->link = !!(status & MDIO_USXGMII_LINK); + state->an_complete = state->link; + phylink_decode_usxgmii_word(state, lp_status); +} + static const struct phylink_pcs_ops mv88e6393x_xg_pcs_ops = { .pcs_enable = mv88e6393x_xg_pcs_enable, .pcs_disable = mv88e6393x_xg_pcs_disable, .pcs_pre_config = mv88e6393x_xg_pcs_pre_config, .pcs_post_config = mv88e6393x_xg_pcs_post_config, - .pcs_get_state = mv88e639x_xg_pcs_get_state, + .pcs_get_state = mv88e6393x_xg_pcs_get_state, .pcs_config = mv88e639x_xg_pcs_config, }; diff --git a/drivers/net/ethernet/amazon/ena/ena_eth_com.c b/drivers/net/ethernet/amazon/ena/ena_eth_com.c index 3d6f0a466a9ed..f9f886289b970 100644 --- a/drivers/net/ethernet/amazon/ena/ena_eth_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_eth_com.c @@ -328,9 +328,6 @@ static int ena_com_create_and_store_tx_meta_desc(struct ena_com_io_sq *io_sq, * compare it to the stored version, just create the meta */ if (io_sq->disable_meta_caching) { - if (unlikely(!ena_tx_ctx->meta_valid)) - return -EINVAL; - *have_meta = true; return ena_com_create_meta(io_sq, ena_meta); } diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index f955bde10cf90..14e41eb57731b 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -74,6 +74,8 @@ static void ena_unmap_tx_buff(struct ena_ring *tx_ring, struct ena_tx_buffer *tx_info); static int ena_create_io_tx_queues_in_range(struct ena_adapter *adapter, int first_index, int count); +static void ena_free_all_io_tx_resources_in_range(struct ena_adapter *adapter, + int first_index, int count); /* Increase a stat by cnt while holding syncp seqlock on 32bit machines */ static void ena_increase_stat(u64 *statp, u64 cnt, @@ -457,23 +459,22 @@ static void ena_init_all_xdp_queues(struct ena_adapter *adapter) static int ena_setup_and_create_all_xdp_queues(struct ena_adapter *adapter) { + u32 xdp_first_ring = adapter->xdp_first_ring; + u32 xdp_num_queues = adapter->xdp_num_queues; int rc = 0; - rc = ena_setup_tx_resources_in_range(adapter, adapter->xdp_first_ring, - adapter->xdp_num_queues); + rc = ena_setup_tx_resources_in_range(adapter, xdp_first_ring, xdp_num_queues); if (rc) goto setup_err; - rc = ena_create_io_tx_queues_in_range(adapter, - adapter->xdp_first_ring, - adapter->xdp_num_queues); + rc = ena_create_io_tx_queues_in_range(adapter, xdp_first_ring, xdp_num_queues); if (rc) goto create_err; return 0; create_err: - ena_free_all_io_tx_resources(adapter); + ena_free_all_io_tx_resources_in_range(adapter, xdp_first_ring, xdp_num_queues); setup_err: return rc; } @@ -1492,11 +1493,6 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring, if (unlikely(!skb)) return NULL; - /* sync this buffer for CPU use */ - dma_sync_single_for_cpu(rx_ring->dev, - dma_unmap_addr(&rx_info->ena_buf, paddr) + pkt_offset, - len, - DMA_FROM_DEVICE); skb_copy_to_linear_data(skb, buf_addr + buf_offset, len); dma_sync_single_for_device(rx_ring->dev, dma_unmap_addr(&rx_info->ena_buf, paddr) + pkt_offset, @@ -1515,17 +1511,10 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring, buf_len = SKB_DATA_ALIGN(len + buf_offset + tailroom); - pre_reuse_paddr = dma_unmap_addr(&rx_info->ena_buf, paddr); - /* If XDP isn't loaded try to reuse part of the RX buffer */ reuse_rx_buf_page = !is_xdp_loaded && ena_try_rx_buf_page_reuse(rx_info, buf_len, len, pkt_offset); - dma_sync_single_for_cpu(rx_ring->dev, - pre_reuse_paddr + pkt_offset, - len, - DMA_FROM_DEVICE); - if (!reuse_rx_buf_page) ena_unmap_rx_buff_attrs(rx_ring, rx_info, DMA_ATTR_SKIP_CPU_SYNC); @@ -1671,20 +1660,23 @@ static void ena_set_rx_hash(struct ena_ring *rx_ring, } } -static int ena_xdp_handle_buff(struct ena_ring *rx_ring, struct xdp_buff *xdp) +static int ena_xdp_handle_buff(struct ena_ring *rx_ring, struct xdp_buff *xdp, u16 num_descs) { struct ena_rx_buffer *rx_info; int ret; + /* XDP multi-buffer packets not supported */ + if (unlikely(num_descs > 1)) { + netdev_err_once(rx_ring->adapter->netdev, + "xdp: dropped unsupported multi-buffer packets\n"); + ena_increase_stat(&rx_ring->rx_stats.xdp_drop, 1, &rx_ring->syncp); + return ENA_XDP_DROP; + } + rx_info = &rx_ring->rx_buffer_info[rx_ring->ena_bufs[0].req_id]; xdp_prepare_buff(xdp, page_address(rx_info->page), rx_info->buf_offset, rx_ring->ena_bufs[0].len, false); - /* If for some reason we received a bigger packet than - * we expect, then we simply drop it - */ - if (unlikely(rx_ring->ena_bufs[0].len > ENA_XDP_MAX_MTU)) - return ENA_XDP_DROP; ret = ena_xdp_execute(rx_ring, xdp); @@ -1719,6 +1711,7 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi, int xdp_flags = 0; int total_len = 0; int xdp_verdict; + u8 pkt_offset; int rc = 0; int i; @@ -1745,15 +1738,21 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi, /* First descriptor might have an offset set by the device */ rx_info = &rx_ring->rx_buffer_info[rx_ring->ena_bufs[0].req_id]; - rx_info->buf_offset += ena_rx_ctx.pkt_offset; + pkt_offset = ena_rx_ctx.pkt_offset; + rx_info->buf_offset += pkt_offset; netif_dbg(rx_ring->adapter, rx_status, rx_ring->netdev, "rx_poll: q %d got packet from ena. descs #: %d l3 proto %d l4 proto %d hash: %x\n", rx_ring->qid, ena_rx_ctx.descs, ena_rx_ctx.l3_proto, ena_rx_ctx.l4_proto, ena_rx_ctx.hash); + dma_sync_single_for_cpu(rx_ring->dev, + dma_unmap_addr(&rx_info->ena_buf, paddr) + pkt_offset, + rx_ring->ena_bufs[0].len, + DMA_FROM_DEVICE); + if (ena_xdp_present_ring(rx_ring)) - xdp_verdict = ena_xdp_handle_buff(rx_ring, &xdp); + xdp_verdict = ena_xdp_handle_buff(rx_ring, &xdp, ena_rx_ctx.descs); /* allocate skb and fill it */ if (xdp_verdict == ENA_XDP_PASS) @@ -1777,7 +1776,7 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi, if (xdp_verdict & ENA_XDP_FORWARDED) { ena_unmap_rx_buff_attrs(rx_ring, &rx_ring->rx_buffer_info[req_id], - 0); + DMA_ATTR_SKIP_CPU_SYNC); rx_ring->rx_buffer_info[req_id].page = NULL; } } diff --git a/drivers/net/ethernet/amd/pds_core/adminq.c b/drivers/net/ethernet/amd/pds_core/adminq.c index 045fe133f6ee9..5beadabc21361 100644 --- a/drivers/net/ethernet/amd/pds_core/adminq.c +++ b/drivers/net/ethernet/amd/pds_core/adminq.c @@ -146,7 +146,7 @@ irqreturn_t pdsc_adminq_isr(int irq, void *data) } queue_work(pdsc->wq, &qcq->work); - pds_core_intr_mask(&pdsc->intr_ctrl[irq], PDS_CORE_INTR_MASK_CLEAR); + pds_core_intr_mask(&pdsc->intr_ctrl[qcq->intx], PDS_CORE_INTR_MASK_CLEAR); return IRQ_HANDLED; } diff --git a/drivers/net/ethernet/amd/pds_core/core.h b/drivers/net/ethernet/amd/pds_core/core.h index e545fafc48196..b1c1f1007b065 100644 --- a/drivers/net/ethernet/amd/pds_core/core.h +++ b/drivers/net/ethernet/amd/pds_core/core.h @@ -15,7 +15,7 @@ #define PDSC_DRV_DESCRIPTION "AMD/Pensando Core Driver" #define PDSC_WATCHDOG_SECS 5 -#define PDSC_QUEUE_NAME_MAX_SZ 32 +#define PDSC_QUEUE_NAME_MAX_SZ 16 #define PDSC_ADMINQ_MIN_LENGTH 16 /* must be a power of two */ #define PDSC_NOTIFYQ_LENGTH 64 /* must be a power of two */ #define PDSC_TEARDOWN_RECOVERY false diff --git a/drivers/net/ethernet/amd/pds_core/dev.c b/drivers/net/ethernet/amd/pds_core/dev.c index f77cd9f5a2fda..eb178728edba9 100644 --- a/drivers/net/ethernet/amd/pds_core/dev.c +++ b/drivers/net/ethernet/amd/pds_core/dev.c @@ -254,10 +254,14 @@ static int pdsc_identify(struct pdsc *pdsc) struct pds_core_drv_identity drv = {}; size_t sz; int err; + int n; drv.drv_type = cpu_to_le32(PDS_DRIVER_LINUX); - snprintf(drv.driver_ver_str, sizeof(drv.driver_ver_str), - "%s %s", PDS_CORE_DRV_NAME, utsname()->release); + /* Catching the return quiets a Wformat-truncation complaint */ + n = snprintf(drv.driver_ver_str, sizeof(drv.driver_ver_str), + "%s %s", PDS_CORE_DRV_NAME, utsname()->release); + if (n > sizeof(drv.driver_ver_str)) + dev_dbg(pdsc->dev, "release name truncated, don't care\n"); /* Next let's get some info about the device * We use the devcmd_lock at this level in order to diff --git a/drivers/net/ethernet/amd/pds_core/devlink.c b/drivers/net/ethernet/amd/pds_core/devlink.c index d9607033bbf21..d2abf32b93fe3 100644 --- a/drivers/net/ethernet/amd/pds_core/devlink.c +++ b/drivers/net/ethernet/amd/pds_core/devlink.c @@ -104,7 +104,7 @@ int pdsc_dl_info_get(struct devlink *dl, struct devlink_info_req *req, struct pds_core_fw_list_info fw_list; struct pdsc *pdsc = devlink_priv(dl); union pds_core_dev_comp comp; - char buf[16]; + char buf[32]; int listlen; int err; int i; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index 614c0278419bc..6b73648b37793 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -682,10 +682,24 @@ static void xgbe_service(struct work_struct *work) static void xgbe_service_timer(struct timer_list *t) { struct xgbe_prv_data *pdata = from_timer(pdata, t, service_timer); + struct xgbe_channel *channel; + unsigned int i; queue_work(pdata->dev_workqueue, &pdata->service_work); mod_timer(&pdata->service_timer, jiffies + HZ); + + if (!pdata->tx_usecs) + return; + + for (i = 0; i < pdata->channel_count; i++) { + channel = pdata->channel[i]; + if (!channel->tx_ring || channel->tx_timer_active) + break; + channel->tx_timer_active = 1; + mod_timer(&channel->tx_timer, + jiffies + usecs_to_jiffies(pdata->tx_usecs)); + } } static void xgbe_init_timers(struct xgbe_prv_data *pdata) diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c index 6e83ff59172a3..32fab5e772462 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c @@ -314,10 +314,15 @@ static int xgbe_get_link_ksettings(struct net_device *netdev, cmd->base.phy_address = pdata->phy.address; - cmd->base.autoneg = pdata->phy.autoneg; - cmd->base.speed = pdata->phy.speed; - cmd->base.duplex = pdata->phy.duplex; + if (netif_carrier_ok(netdev)) { + cmd->base.speed = pdata->phy.speed; + cmd->base.duplex = pdata->phy.duplex; + } else { + cmd->base.speed = SPEED_UNKNOWN; + cmd->base.duplex = DUPLEX_UNKNOWN; + } + cmd->base.autoneg = pdata->phy.autoneg; cmd->base.port = PORT_NONE; XGBE_LM_COPY(cmd, supported, lks, supported); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c index 32d2c6fac6526..4a2dc705b5280 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c @@ -1193,7 +1193,19 @@ static int xgbe_phy_config_fixed(struct xgbe_prv_data *pdata) if (pdata->phy.duplex != DUPLEX_FULL) return -EINVAL; - xgbe_set_mode(pdata, mode); + /* Force the mode change for SFI in Fixed PHY config. + * Fixed PHY configs needs PLL to be enabled while doing mode set. + * When the SFP module isn't connected during boot, driver assumes + * AN is ON and attempts autonegotiation. However, if the connected + * SFP comes up in Fixed PHY config, the link will not come up as + * PLL isn't enabled while the initial mode set command is issued. + * So, force the mode change for SFI in Fixed PHY configuration to + * fix link issues. + */ + if (mode == XGBE_MODE_SFI) + xgbe_change_mode(pdata, mode); + else + xgbe_set_mode(pdata, mode); return 0; } diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c b/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c index 80b44043e6c53..28c9b6f1a54f1 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c @@ -553,17 +553,17 @@ void aq_ptp_tx_hwtstamp(struct aq_nic_s *aq_nic, u64 timestamp) /* aq_ptp_rx_hwtstamp - utility function which checks for RX time stamp * @adapter: pointer to adapter struct - * @skb: particular skb to send timestamp with + * @shhwtstamps: particular skb_shared_hwtstamps to save timestamp * * if the timestamp is valid, we convert it into the timecounter ns * value, then store that result into the hwtstamps structure which * is passed up the network stack */ -static void aq_ptp_rx_hwtstamp(struct aq_ptp_s *aq_ptp, struct sk_buff *skb, +static void aq_ptp_rx_hwtstamp(struct aq_ptp_s *aq_ptp, struct skb_shared_hwtstamps *shhwtstamps, u64 timestamp) { timestamp -= atomic_read(&aq_ptp->offset_ingress); - aq_ptp_convert_to_hwtstamp(aq_ptp, skb_hwtstamps(skb), timestamp); + aq_ptp_convert_to_hwtstamp(aq_ptp, shhwtstamps, timestamp); } void aq_ptp_hwtstamp_config_get(struct aq_ptp_s *aq_ptp, @@ -639,7 +639,7 @@ bool aq_ptp_ring(struct aq_nic_s *aq_nic, struct aq_ring_s *ring) &aq_ptp->ptp_rx == ring || &aq_ptp->hwts_rx == ring; } -u16 aq_ptp_extract_ts(struct aq_nic_s *aq_nic, struct sk_buff *skb, u8 *p, +u16 aq_ptp_extract_ts(struct aq_nic_s *aq_nic, struct skb_shared_hwtstamps *shhwtstamps, u8 *p, unsigned int len) { struct aq_ptp_s *aq_ptp = aq_nic->aq_ptp; @@ -648,7 +648,7 @@ u16 aq_ptp_extract_ts(struct aq_nic_s *aq_nic, struct sk_buff *skb, u8 *p, p, len, ×tamp); if (ret > 0) - aq_ptp_rx_hwtstamp(aq_ptp, skb, timestamp); + aq_ptp_rx_hwtstamp(aq_ptp, shhwtstamps, timestamp); return ret; } diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ptp.h b/drivers/net/ethernet/aquantia/atlantic/aq_ptp.h index 28ccb7ca2df9e..210b723f22072 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ptp.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ptp.h @@ -67,7 +67,7 @@ int aq_ptp_hwtstamp_config_set(struct aq_ptp_s *aq_ptp, /* Return either ring is belong to PTP or not*/ bool aq_ptp_ring(struct aq_nic_s *aq_nic, struct aq_ring_s *ring); -u16 aq_ptp_extract_ts(struct aq_nic_s *aq_nic, struct sk_buff *skb, u8 *p, +u16 aq_ptp_extract_ts(struct aq_nic_s *aq_nic, struct skb_shared_hwtstamps *shhwtstamps, u8 *p, unsigned int len); struct ptp_clock *aq_ptp_get_ptp_clock(struct aq_ptp_s *aq_ptp); @@ -143,7 +143,7 @@ static inline bool aq_ptp_ring(struct aq_nic_s *aq_nic, struct aq_ring_s *ring) } static inline u16 aq_ptp_extract_ts(struct aq_nic_s *aq_nic, - struct sk_buff *skb, u8 *p, + struct skb_shared_hwtstamps *shhwtstamps, u8 *p, unsigned int len) { return 0; diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index 4de22eed099a8..e1885c1eb100a 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -647,7 +647,7 @@ static int __aq_ring_rx_clean(struct aq_ring_s *self, struct napi_struct *napi, } if (is_ptp_ring) buff->len -= - aq_ptp_extract_ts(self->aq_nic, skb, + aq_ptp_extract_ts(self->aq_nic, skb_hwtstamps(skb), aq_buf_vaddr(&buff->rxdata), buff->len); @@ -742,6 +742,8 @@ static int __aq_ring_xdp_clean(struct aq_ring_s *rx_ring, struct aq_ring_buff_s *buff = &rx_ring->buff_ring[rx_ring->sw_head]; bool is_ptp_ring = aq_ptp_ring(rx_ring->aq_nic, rx_ring); struct aq_ring_buff_s *buff_ = NULL; + u16 ptp_hwtstamp_len = 0; + struct skb_shared_hwtstamps shhwtstamps; struct sk_buff *skb = NULL; unsigned int next_ = 0U; struct xdp_buff xdp; @@ -810,11 +812,12 @@ static int __aq_ring_xdp_clean(struct aq_ring_s *rx_ring, hard_start = page_address(buff->rxdata.page) + buff->rxdata.pg_off - rx_ring->page_offset; - if (is_ptp_ring) - buff->len -= - aq_ptp_extract_ts(rx_ring->aq_nic, skb, - aq_buf_vaddr(&buff->rxdata), - buff->len); + if (is_ptp_ring) { + ptp_hwtstamp_len = aq_ptp_extract_ts(rx_ring->aq_nic, &shhwtstamps, + aq_buf_vaddr(&buff->rxdata), + buff->len); + buff->len -= ptp_hwtstamp_len; + } xdp_init_buff(&xdp, frame_sz, &rx_ring->xdp_rxq); xdp_prepare_buff(&xdp, hard_start, rx_ring->page_offset, @@ -834,6 +837,9 @@ static int __aq_ring_xdp_clean(struct aq_ring_s *rx_ring, if (IS_ERR(skb) || !skb) continue; + if (ptp_hwtstamp_len > 0) + *skb_hwtstamps(skb) = shhwtstamps; + if (buff->is_vlan) __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), buff->vlan_rx_tag); @@ -932,11 +938,14 @@ void aq_ring_free(struct aq_ring_s *self) return; kfree(self->buff_ring); + self->buff_ring = NULL; - if (self->dx_ring) + if (self->dx_ring) { dma_free_coherent(aq_nic_get_dev(self->aq_nic), self->size * self->dx_size, self->dx_ring, self->dx_ring_pa); + self->dx_ring = NULL; + } } unsigned int aq_ring_fill_stats_data(struct aq_ring_s *self, u64 *data) diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c.h b/drivers/net/ethernet/atheros/atl1c/atl1c.h index 43d821fe7a542..63ba64dbb7310 100644 --- a/drivers/net/ethernet/atheros/atl1c/atl1c.h +++ b/drivers/net/ethernet/atheros/atl1c/atl1c.h @@ -504,15 +504,12 @@ struct atl1c_rrd_ring { u16 next_to_use; u16 next_to_clean; struct napi_struct napi; - struct page *rx_page; - unsigned int rx_page_offset; }; /* board specific private data structure */ struct atl1c_adapter { struct net_device *netdev; struct pci_dev *pdev; - unsigned int rx_frag_size; struct atl1c_hw hw; struct atl1c_hw_stats hw_stats; struct mii_if_info mii; /* MII interface info */ diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c index 940c5d1ff9cfc..74b78164cf74a 100644 --- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c +++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c @@ -483,15 +483,10 @@ static int atl1c_set_mac_addr(struct net_device *netdev, void *p) static void atl1c_set_rxbufsize(struct atl1c_adapter *adapter, struct net_device *dev) { - unsigned int head_size; int mtu = dev->mtu; adapter->rx_buffer_len = mtu > AT_RX_BUF_SIZE ? roundup(mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN, 8) : AT_RX_BUF_SIZE; - - head_size = SKB_DATA_ALIGN(adapter->rx_buffer_len + NET_SKB_PAD + NET_IP_ALIGN) + - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - adapter->rx_frag_size = roundup_pow_of_two(head_size); } static netdev_features_t atl1c_fix_features(struct net_device *netdev, @@ -964,7 +959,6 @@ static void atl1c_init_ring_ptrs(struct atl1c_adapter *adapter) static void atl1c_free_ring_resources(struct atl1c_adapter *adapter) { struct pci_dev *pdev = adapter->pdev; - int i; dma_free_coherent(&pdev->dev, adapter->ring_header.size, adapter->ring_header.desc, adapter->ring_header.dma); @@ -977,12 +971,6 @@ static void atl1c_free_ring_resources(struct atl1c_adapter *adapter) kfree(adapter->tpd_ring[0].buffer_info); adapter->tpd_ring[0].buffer_info = NULL; } - for (i = 0; i < adapter->rx_queue_count; ++i) { - if (adapter->rrd_ring[i].rx_page) { - put_page(adapter->rrd_ring[i].rx_page); - adapter->rrd_ring[i].rx_page = NULL; - } - } } /** @@ -1754,48 +1742,11 @@ static inline void atl1c_rx_checksum(struct atl1c_adapter *adapter, skb_checksum_none_assert(skb); } -static struct sk_buff *atl1c_alloc_skb(struct atl1c_adapter *adapter, - u32 queue, bool napi_mode) -{ - struct atl1c_rrd_ring *rrd_ring = &adapter->rrd_ring[queue]; - struct sk_buff *skb; - struct page *page; - - if (adapter->rx_frag_size > PAGE_SIZE) { - if (likely(napi_mode)) - return napi_alloc_skb(&rrd_ring->napi, - adapter->rx_buffer_len); - else - return netdev_alloc_skb_ip_align(adapter->netdev, - adapter->rx_buffer_len); - } - - page = rrd_ring->rx_page; - if (!page) { - page = alloc_page(GFP_ATOMIC); - if (unlikely(!page)) - return NULL; - rrd_ring->rx_page = page; - rrd_ring->rx_page_offset = 0; - } - - skb = build_skb(page_address(page) + rrd_ring->rx_page_offset, - adapter->rx_frag_size); - if (likely(skb)) { - skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN); - rrd_ring->rx_page_offset += adapter->rx_frag_size; - if (rrd_ring->rx_page_offset >= PAGE_SIZE) - rrd_ring->rx_page = NULL; - else - get_page(page); - } - return skb; -} - static int atl1c_alloc_rx_buffer(struct atl1c_adapter *adapter, u32 queue, bool napi_mode) { struct atl1c_rfd_ring *rfd_ring = &adapter->rfd_ring[queue]; + struct atl1c_rrd_ring *rrd_ring = &adapter->rrd_ring[queue]; struct pci_dev *pdev = adapter->pdev; struct atl1c_buffer *buffer_info, *next_info; struct sk_buff *skb; @@ -1814,13 +1765,27 @@ static int atl1c_alloc_rx_buffer(struct atl1c_adapter *adapter, u32 queue, while (next_info->flags & ATL1C_BUFFER_FREE) { rfd_desc = ATL1C_RFD_DESC(rfd_ring, rfd_next_to_use); - skb = atl1c_alloc_skb(adapter, queue, napi_mode); + /* When DMA RX address is set to something like + * 0x....fc0, it will be very likely to cause DMA + * RFD overflow issue. + * + * To work around it, we apply rx skb with 64 bytes + * longer space, and offset the address whenever + * 0x....fc0 is detected. + */ + if (likely(napi_mode)) + skb = napi_alloc_skb(&rrd_ring->napi, adapter->rx_buffer_len + 64); + else + skb = netdev_alloc_skb(adapter->netdev, adapter->rx_buffer_len + 64); if (unlikely(!skb)) { if (netif_msg_rx_err(adapter)) dev_warn(&pdev->dev, "alloc rx buffer failed\n"); break; } + if (((unsigned long)skb->data & 0xfff) == 0xfc0) + skb_reserve(skb, 64); + /* * Make buffer alignment 2 beyond a 16 byte boundary * this will result in a 16 byte aligned IP header after diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c index 5935be190b9e2..5f2a6fcba9670 100644 --- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c +++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c @@ -866,10 +866,13 @@ static int atl1e_setup_ring_resources(struct atl1e_adapter *adapter) netdev_err(adapter->netdev, "offset(%d) > ring size(%d) !!\n", offset, adapter->ring_size); err = -1; - goto failed; + goto free_buffer; } return 0; +free_buffer: + kfree(tx_ring->tx_buffer); + tx_ring->tx_buffer = NULL; failed: if (adapter->ring_vir_addr != NULL) { dma_free_coherent(&pdev->dev, adapter->ring_size, diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 7551aa8068f8f..f811d59fd71fd 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -1749,16 +1749,32 @@ static void bnxt_tpa_agg(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, static void bnxt_deliver_skb(struct bnxt *bp, struct bnxt_napi *bnapi, struct sk_buff *skb) { + skb_mark_for_recycle(skb); + if (skb->dev != bp->dev) { /* this packet belongs to a vf-rep */ bnxt_vf_rep_rx(bp, skb); return; } skb_record_rx_queue(skb, bnapi->index); - skb_mark_for_recycle(skb); napi_gro_receive(&bnapi->napi, skb); } +static bool bnxt_rx_ts_valid(struct bnxt *bp, u32 flags, + struct rx_cmp_ext *rxcmp1, u32 *cmpl_ts) +{ + u32 ts = le32_to_cpu(rxcmp1->rx_cmp_timestamp); + + if (BNXT_PTP_RX_TS_VALID(flags)) + goto ts_valid; + if (!bp->ptp_all_rx_tstamp || !ts || !BNXT_ALL_RX_TS_VALID(flags)) + return false; + +ts_valid: + *cmpl_ts = ts; + return true; +} + /* returns the following: * 1 - 1 packet successfully received * 0 - successful TPA_START, packet not completed yet @@ -1784,6 +1800,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, struct sk_buff *skb; struct xdp_buff xdp; u32 flags, misc; + u32 cmpl_ts; void *data; int rc = 0; @@ -2006,10 +2023,8 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, } } - if (unlikely((flags & RX_CMP_FLAGS_ITYPES_MASK) == - RX_CMP_FLAGS_ITYPE_PTP_W_TS) || bp->ptp_all_rx_tstamp) { + if (bnxt_rx_ts_valid(bp, flags, rxcmp1, &cmpl_ts)) { if (bp->flags & BNXT_FLAG_CHIP_P5) { - u32 cmpl_ts = le32_to_cpu(rxcmp1->rx_cmp_timestamp); u64 ns, ts; if (!bnxt_get_rx_ts_p5(bp, &ts, cmpl_ts)) { @@ -10703,10 +10718,8 @@ static void __bnxt_close_nic(struct bnxt *bp, bool irq_re_init, bnxt_free_mem(bp, irq_re_init); } -int bnxt_close_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) +void bnxt_close_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) { - int rc = 0; - if (test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) { /* If we get here, it means firmware reset is in progress * while we are trying to close. We can safely proceed with @@ -10721,15 +10734,18 @@ int bnxt_close_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) #ifdef CONFIG_BNXT_SRIOV if (bp->sriov_cfg) { + int rc; + rc = wait_event_interruptible_timeout(bp->sriov_cfg_wait, !bp->sriov_cfg, BNXT_SRIOV_CFG_WAIT_TMO); - if (rc) - netdev_warn(bp->dev, "timeout waiting for SRIOV config operation to complete!\n"); + if (!rc) + netdev_warn(bp->dev, "timeout waiting for SRIOV config operation to complete, proceeding to close!\n"); + else if (rc < 0) + netdev_warn(bp->dev, "SRIOV config operation interrupted, proceeding to close!\n"); } #endif __bnxt_close_nic(bp, irq_re_init, link_re_init); - return rc; } static int bnxt_close(struct net_device *dev) @@ -13897,6 +13913,8 @@ static int bnxt_resume(struct device *device) if (rc) goto resume_exit; + bnxt_clear_reservations(bp, true); + if (bnxt_hwrm_func_drv_rgtr(bp, NULL, 0, false)) { rc = -ENODEV; goto resume_exit; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 84cbcfa61bc12..0116f67593e3a 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -161,7 +161,7 @@ struct rx_cmp { #define RX_CMP_FLAGS_ERROR (1 << 6) #define RX_CMP_FLAGS_PLACEMENT (7 << 7) #define RX_CMP_FLAGS_RSS_VALID (1 << 10) - #define RX_CMP_FLAGS_UNUSED (1 << 11) + #define RX_CMP_FLAGS_PKT_METADATA_PRESENT (1 << 11) #define RX_CMP_FLAGS_ITYPES_SHIFT 12 #define RX_CMP_FLAGS_ITYPES_MASK 0xf000 #define RX_CMP_FLAGS_ITYPE_UNKNOWN (0 << 12) @@ -188,6 +188,12 @@ struct rx_cmp { __le32 rx_cmp_rss_hash; }; +#define BNXT_PTP_RX_TS_VALID(flags) \ + (((flags) & RX_CMP_FLAGS_ITYPES_MASK) == RX_CMP_FLAGS_ITYPE_PTP_W_TS) + +#define BNXT_ALL_RX_TS_VALID(flags) \ + !((flags) & RX_CMP_FLAGS_PKT_METADATA_PRESENT) + #define RX_CMP_HASH_VALID(rxcmp) \ ((rxcmp)->rx_cmp_len_flags_type & cpu_to_le32(RX_CMP_FLAGS_RSS_VALID)) @@ -2362,7 +2368,7 @@ int bnxt_open_nic(struct bnxt *, bool, bool); int bnxt_half_open_nic(struct bnxt *bp); void bnxt_half_close_nic(struct bnxt *bp); void bnxt_reenable_sriov(struct bnxt *bp); -int bnxt_close_nic(struct bnxt *, bool, bool); +void bnxt_close_nic(struct bnxt *, bool, bool); void bnxt_get_ring_err_stats(struct bnxt *bp, struct bnxt_total_ring_err_stats *stats); int bnxt_dbg_hwrm_rd_reg(struct bnxt *bp, u32 reg_off, u16 num_words, diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c index 8b3e7697390f7..9d39f194b260f 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c @@ -478,15 +478,8 @@ static int bnxt_dl_reload_down(struct devlink *dl, bool netns_change, return -ENODEV; } bnxt_ulp_stop(bp); - if (netif_running(bp->dev)) { - rc = bnxt_close_nic(bp, true, true); - if (rc) { - NL_SET_ERR_MSG_MOD(extack, "Failed to close"); - dev_close(bp->dev); - rtnl_unlock(); - break; - } - } + if (netif_running(bp->dev)) + bnxt_close_nic(bp, true, true); bnxt_vf_reps_free(bp); rc = bnxt_hwrm_func_drv_unrgtr(bp); if (rc) { diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 547247d98eba2..3c36dd8051485 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -164,9 +164,8 @@ static int bnxt_set_coalesce(struct net_device *dev, reset_coalesce: if (test_bit(BNXT_STATE_OPEN, &bp->state)) { if (update_stats) { - rc = bnxt_close_nic(bp, true, false); - if (!rc) - rc = bnxt_open_nic(bp, true, false); + bnxt_close_nic(bp, true, false); + rc = bnxt_open_nic(bp, true, false); } else { rc = bnxt_hwrm_set_coal(bp); } @@ -955,12 +954,7 @@ static int bnxt_set_channels(struct net_device *dev, * before PF unload */ } - rc = bnxt_close_nic(bp, true, false); - if (rc) { - netdev_err(bp->dev, "Set channel failure rc :%x\n", - rc); - return rc; - } + bnxt_close_nic(bp, true, false); } if (sh) { @@ -3737,12 +3731,7 @@ static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest, bnxt_run_fw_tests(bp, test_mask, &test_results); } else { bnxt_ulp_stop(bp); - rc = bnxt_close_nic(bp, true, false); - if (rc) { - etest->flags |= ETH_TEST_FL_FAILED; - bnxt_ulp_start(bp, rc); - return; - } + bnxt_close_nic(bp, true, false); bnxt_run_fw_tests(bp, test_mask, &test_results); buf[BNXT_MACLPBK_TEST_IDX] = 1; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c index f3886710e7787..6e3da3362bd61 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c @@ -521,9 +521,8 @@ static int bnxt_hwrm_ptp_cfg(struct bnxt *bp) if (netif_running(bp->dev)) { if (ptp->rx_filter == HWTSTAMP_FILTER_ALL) { - rc = bnxt_close_nic(bp, false, false); - if (!rc) - rc = bnxt_open_nic(bp, false, false); + bnxt_close_nic(bp, false, false); + rc = bnxt_open_nic(bp, false, false); } else { bnxt_ptp_cfg_tstamp_filters(bp); } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c index 38d89d80b4a9c..273c9ba48f09a 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c @@ -2075,6 +2075,7 @@ int bnxt_init_tc(struct bnxt *bp) rhashtable_destroy(&tc_info->flow_table); free_tc_info: kfree(tc_info); + bp->tc_info = NULL; return rc; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c index 96f5ca778c67d..8cb9a99154aad 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c @@ -59,7 +59,6 @@ struct bnxt_sw_tx_bd *bnxt_xmit_bd(struct bnxt *bp, for (i = 0; i < num_frags ; i++) { skb_frag_t *frag = &sinfo->frags[i]; struct bnxt_sw_tx_bd *frag_tx_buf; - struct pci_dev *pdev = bp->pdev; dma_addr_t frag_mapping; int frag_len; @@ -73,16 +72,10 @@ struct bnxt_sw_tx_bd *bnxt_xmit_bd(struct bnxt *bp, txbd = &txr->tx_desc_ring[TX_RING(prod)][TX_IDX(prod)]; frag_len = skb_frag_size(frag); - frag_mapping = skb_frag_dma_map(&pdev->dev, frag, 0, - frag_len, DMA_TO_DEVICE); - - if (unlikely(dma_mapping_error(&pdev->dev, frag_mapping))) - return NULL; - - dma_unmap_addr_set(frag_tx_buf, mapping, frag_mapping); - flags = frag_len << TX_BD_LEN_SHIFT; txbd->tx_bd_len_flags_type = cpu_to_le32(flags); + frag_mapping = page_pool_get_dma_addr(skb_frag_page(frag)) + + skb_frag_off(frag); txbd->tx_bd_haddr = cpu_to_le64(frag_mapping); len = frag_len; diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 22b00912f7ac8..b7acd994a393b 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -6845,7 +6845,7 @@ static int tg3_rx(struct tg3_napi *tnapi, int budget) desc_idx, *post_ptr); drop_it_no_recycle: /* Other statistics kept track of by card. */ - tp->rx_dropped++; + tnapi->rx_dropped++; goto next_pkt; } @@ -7874,8 +7874,10 @@ static int tg3_tso_bug(struct tg3 *tp, struct tg3_napi *tnapi, segs = skb_gso_segment(skb, tp->dev->features & ~(NETIF_F_TSO | NETIF_F_TSO6)); - if (IS_ERR(segs) || !segs) + if (IS_ERR(segs) || !segs) { + tnapi->tx_dropped++; goto tg3_tso_bug_end; + } skb_list_walk_safe(segs, seg, next) { skb_mark_not_on_list(seg); @@ -8146,7 +8148,7 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev) drop: dev_kfree_skb_any(skb); drop_nofree: - tp->tx_dropped++; + tnapi->tx_dropped++; return NETDEV_TX_OK; } @@ -9325,7 +9327,7 @@ static void __tg3_set_rx_mode(struct net_device *); /* tp->lock is held. */ static int tg3_halt(struct tg3 *tp, int kind, bool silent) { - int err; + int err, i; tg3_stop_fw(tp); @@ -9346,6 +9348,13 @@ static int tg3_halt(struct tg3 *tp, int kind, bool silent) /* And make sure the next sample is new data */ memset(tp->hw_stats, 0, sizeof(struct tg3_hw_stats)); + + for (i = 0; i < TG3_IRQ_MAX_VECS; ++i) { + struct tg3_napi *tnapi = &tp->napi[i]; + + tnapi->rx_dropped = 0; + tnapi->tx_dropped = 0; + } } return err; @@ -11895,6 +11904,9 @@ static void tg3_get_nstats(struct tg3 *tp, struct rtnl_link_stats64 *stats) { struct rtnl_link_stats64 *old_stats = &tp->net_stats_prev; struct tg3_hw_stats *hw_stats = tp->hw_stats; + unsigned long rx_dropped; + unsigned long tx_dropped; + int i; stats->rx_packets = old_stats->rx_packets + get_stat64(&hw_stats->rx_ucast_packets) + @@ -11941,8 +11953,26 @@ static void tg3_get_nstats(struct tg3 *tp, struct rtnl_link_stats64 *stats) stats->rx_missed_errors = old_stats->rx_missed_errors + get_stat64(&hw_stats->rx_discards); - stats->rx_dropped = tp->rx_dropped; - stats->tx_dropped = tp->tx_dropped; + /* Aggregate per-queue counters. The per-queue counters are updated + * by a single writer, race-free. The result computed by this loop + * might not be 100% accurate (counters can be updated in the middle of + * the loop) but the next tg3_get_nstats() will recompute the current + * value so it is acceptable. + * + * Note that these counters wrap around at 4G on 32bit machines. + */ + rx_dropped = (unsigned long)(old_stats->rx_dropped); + tx_dropped = (unsigned long)(old_stats->tx_dropped); + + for (i = 0; i < tp->irq_cnt; i++) { + struct tg3_napi *tnapi = &tp->napi[i]; + + rx_dropped += tnapi->rx_dropped; + tx_dropped += tnapi->tx_dropped; + } + + stats->rx_dropped = rx_dropped; + stats->tx_dropped = tx_dropped; } static int tg3_get_regs_len(struct net_device *dev) diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h index 1000c894064f0..8d753f8c5b065 100644 --- a/drivers/net/ethernet/broadcom/tg3.h +++ b/drivers/net/ethernet/broadcom/tg3.h @@ -3018,6 +3018,7 @@ struct tg3_napi { u16 *rx_rcb_prod_idx; struct tg3_rx_prodring_set prodring; struct tg3_rx_buffer_desc *rx_rcb; + unsigned long rx_dropped; u32 tx_prod ____cacheline_aligned; u32 tx_cons; @@ -3026,6 +3027,7 @@ struct tg3_napi { u32 prodmbox; struct tg3_tx_buffer_desc *tx_ring; struct tg3_tx_ring_info *tx_buffers; + unsigned long tx_dropped; dma_addr_t status_mapping; dma_addr_t rx_rcb_mapping; @@ -3219,8 +3221,6 @@ struct tg3 { /* begin "everything else" cacheline(s) section */ - unsigned long rx_dropped; - unsigned long tx_dropped; struct rtnl_link_stats64 net_stats_prev; struct tg3_ethtool_stats estats_prev; diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index a8b9d1a3e4d57..636949737d72f 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -432,8 +432,8 @@ static const struct gmac_max_framelen gmac_maxlens[] = { .val = CONFIG0_MAXLEN_1536, }, { - .max_l3_len = 1542, - .val = CONFIG0_MAXLEN_1542, + .max_l3_len = 1548, + .val = CONFIG0_MAXLEN_1548, }, { .max_l3_len = 9212, @@ -1145,6 +1145,7 @@ static int gmac_map_tx_bufs(struct net_device *netdev, struct sk_buff *skb, dma_addr_t mapping; unsigned short mtu; void *buffer; + int ret; mtu = ETH_HLEN; mtu += netdev->mtu; @@ -1159,9 +1160,30 @@ static int gmac_map_tx_bufs(struct net_device *netdev, struct sk_buff *skb, word3 |= mtu; } - if (skb->ip_summed != CHECKSUM_NONE) { + if (skb->len >= ETH_FRAME_LEN) { + /* Hardware offloaded checksumming isn't working on frames + * bigger than 1514 bytes. A hypothesis about this is that the + * checksum buffer is only 1518 bytes, so when the frames get + * bigger they get truncated, or the last few bytes get + * overwritten by the FCS. + * + * Just use software checksumming and bypass on bigger frames. + */ + if (skb->ip_summed == CHECKSUM_PARTIAL) { + ret = skb_checksum_help(skb); + if (ret) + return ret; + } + word1 |= TSS_BYPASS_BIT; + } else if (skb->ip_summed == CHECKSUM_PARTIAL) { int tcp = 0; + /* We do not switch off the checksumming on non TCP/UDP + * frames: as is shown from tests, the checksumming engine + * is smart enough to see that a frame is not actually TCP + * or UDP and then just pass it through without any changes + * to the frame. + */ if (skb->protocol == htons(ETH_P_IP)) { word1 |= TSS_IP_CHKSUM_BIT; tcp = ip_hdr(skb)->protocol == IPPROTO_TCP; @@ -1978,15 +2000,6 @@ static int gmac_change_mtu(struct net_device *netdev, int new_mtu) return 0; } -static netdev_features_t gmac_fix_features(struct net_device *netdev, - netdev_features_t features) -{ - if (netdev->mtu + ETH_HLEN + VLAN_HLEN > MTU_SIZE_BIT_MASK) - features &= ~GMAC_OFFLOAD_FEATURES; - - return features; -} - static int gmac_set_features(struct net_device *netdev, netdev_features_t features) { @@ -2212,7 +2225,6 @@ static const struct net_device_ops gmac_351x_ops = { .ndo_set_mac_address = gmac_set_mac_address, .ndo_get_stats64 = gmac_get_stats64, .ndo_change_mtu = gmac_change_mtu, - .ndo_fix_features = gmac_fix_features, .ndo_set_features = gmac_set_features, }; @@ -2464,11 +2476,12 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev) netdev->hw_features = GMAC_OFFLOAD_FEATURES; netdev->features |= GMAC_OFFLOAD_FEATURES | NETIF_F_GRO; - /* We can handle jumbo frames up to 10236 bytes so, let's accept - * payloads of 10236 bytes minus VLAN and ethernet header + /* We can receive jumbo frames up to 10236 bytes but only + * transmit 2047 bytes so, let's accept payloads of 2047 + * bytes minus VLAN and ethernet header */ netdev->min_mtu = ETH_MIN_MTU; - netdev->max_mtu = 10236 - VLAN_ETH_HLEN; + netdev->max_mtu = MTU_SIZE_BIT_MASK - VLAN_ETH_HLEN; port->freeq_refill = 0; netif_napi_add(netdev, &port->napi, gmac_napi_poll); diff --git a/drivers/net/ethernet/cortina/gemini.h b/drivers/net/ethernet/cortina/gemini.h index 9fdf77d5eb374..24bb989981f23 100644 --- a/drivers/net/ethernet/cortina/gemini.h +++ b/drivers/net/ethernet/cortina/gemini.h @@ -502,7 +502,7 @@ union gmac_txdesc_3 { #define SOF_BIT 0x80000000 #define EOF_BIT 0x40000000 #define EOFIE_BIT BIT(29) -#define MTU_SIZE_BIT_MASK 0x1fff +#define MTU_SIZE_BIT_MASK 0x7ff /* Max MTU 2047 bytes */ /* GMAC Tx Descriptor */ struct gmac_txdesc { @@ -787,7 +787,7 @@ union gmac_config0 { #define CONFIG0_MAXLEN_1536 0 #define CONFIG0_MAXLEN_1518 1 #define CONFIG0_MAXLEN_1522 2 -#define CONFIG0_MAXLEN_1542 3 +#define CONFIG0_MAXLEN_1548 3 #define CONFIG0_MAXLEN_9k 4 /* 9212 */ #define CONFIG0_MAXLEN_10k 5 /* 10236 */ #define CONFIG0_MAXLEN_1518__6 6 diff --git a/drivers/net/ethernet/engleder/tsnep.h b/drivers/net/ethernet/engleder/tsnep.h index 6e14c918e3fb7..f188fba021a62 100644 --- a/drivers/net/ethernet/engleder/tsnep.h +++ b/drivers/net/ethernet/engleder/tsnep.h @@ -143,7 +143,7 @@ struct tsnep_rx { struct tsnep_queue { struct tsnep_adapter *adapter; - char name[IFNAMSIZ + 9]; + char name[IFNAMSIZ + 16]; struct tsnep_tx *tx; struct tsnep_rx *rx; diff --git a/drivers/net/ethernet/engleder/tsnep_main.c b/drivers/net/ethernet/engleder/tsnep_main.c index 8b992dc9bb52b..38da2d6c250e6 100644 --- a/drivers/net/ethernet/engleder/tsnep_main.c +++ b/drivers/net/ethernet/engleder/tsnep_main.c @@ -1779,14 +1779,14 @@ static int tsnep_request_irq(struct tsnep_queue *queue, bool first) dev = queue->adapter; } else { if (queue->tx && queue->rx) - sprintf(queue->name, "%s-txrx-%d", name, - queue->rx->queue_index); + snprintf(queue->name, sizeof(queue->name), "%s-txrx-%d", + name, queue->rx->queue_index); else if (queue->tx) - sprintf(queue->name, "%s-tx-%d", name, - queue->tx->queue_index); + snprintf(queue->name, sizeof(queue->name), "%s-tx-%d", + name, queue->tx->queue_index); else - sprintf(queue->name, "%s-rx-%d", name, - queue->rx->queue_index); + snprintf(queue->name, sizeof(queue->name), "%s-rx-%d", + name, queue->rx->queue_index); handler = tsnep_irq_txrx; dev = queue; } diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index 15bab41cee48d..888509cf1f210 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -516,8 +516,6 @@ struct sk_buff *dpaa2_eth_alloc_skb(struct dpaa2_eth_priv *priv, memcpy(skb->data, fd_vaddr + fd_offset, fd_length); - dpaa2_eth_recycle_buf(priv, ch, dpaa2_fd_get_addr(fd)); - return skb; } @@ -589,6 +587,7 @@ void dpaa2_eth_rx(struct dpaa2_eth_priv *priv, struct rtnl_link_stats64 *percpu_stats; struct dpaa2_eth_drv_stats *percpu_extras; struct device *dev = priv->net_dev->dev.parent; + bool recycle_rx_buf = false; void *buf_data; u32 xdp_act; @@ -618,6 +617,8 @@ void dpaa2_eth_rx(struct dpaa2_eth_priv *priv, dma_unmap_page(dev, addr, priv->rx_buf_size, DMA_BIDIRECTIONAL); skb = dpaa2_eth_build_linear_skb(ch, fd, vaddr); + } else { + recycle_rx_buf = true; } } else if (fd_format == dpaa2_fd_sg) { WARN_ON(priv->xdp_prog); @@ -637,6 +638,9 @@ void dpaa2_eth_rx(struct dpaa2_eth_priv *priv, goto err_build_skb; dpaa2_eth_receive_skb(priv, ch, fd, vaddr, fq, percpu_stats, skb); + + if (recycle_rx_buf) + dpaa2_eth_recycle_buf(priv, ch, dpaa2_fd_get_addr(fd)); return; err_build_skb: @@ -1073,14 +1077,12 @@ static int dpaa2_eth_build_single_fd(struct dpaa2_eth_priv *priv, dma_addr_t addr; buffer_start = skb->data - dpaa2_eth_needed_headroom(skb); - - /* If there's enough room to align the FD address, do it. - * It will help hardware optimize accesses. - */ aligned_start = PTR_ALIGN(buffer_start - DPAA2_ETH_TX_BUF_ALIGN, DPAA2_ETH_TX_BUF_ALIGN); if (aligned_start >= skb->head) buffer_start = aligned_start; + else + return -ENOMEM; /* Store a backpointer to the skb at the beginning of the buffer * (in the private data area) such that we can release it @@ -4967,6 +4969,8 @@ static int dpaa2_eth_probe(struct fsl_mc_device *dpni_dev) if (err) goto err_dl_port_add; + net_dev->needed_headroom = DPAA2_ETH_SWA_SIZE + DPAA2_ETH_TX_BUF_ALIGN; + err = register_netdev(net_dev); if (err < 0) { dev_err(dev, "register_netdev() failed\n"); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h index bfb6c96c3b2f0..834cba8c3a416 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h @@ -740,7 +740,7 @@ static inline bool dpaa2_eth_rx_pause_enabled(u64 link_options) static inline unsigned int dpaa2_eth_needed_headroom(struct sk_buff *skb) { - unsigned int headroom = DPAA2_ETH_SWA_SIZE; + unsigned int headroom = DPAA2_ETH_SWA_SIZE + DPAA2_ETH_TX_BUF_ALIGN; /* If we don't have an skb (e.g. XDP buffer), we only need space for * the software annotation area diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c index 4798fb7fe35d1..b6a534a3e0b12 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c @@ -139,7 +139,8 @@ int dpaa2_switch_acl_entry_add(struct dpaa2_switch_filter_block *filter_block, err = dpsw_acl_add_entry(ethsw->mc_io, 0, ethsw->dpsw_handle, filter_block->acl_id, acl_entry_cfg); - dma_unmap_single(dev, acl_entry_cfg->key_iova, sizeof(cmd_buff), + dma_unmap_single(dev, acl_entry_cfg->key_iova, + DPAA2_ETHSW_PORT_ACL_CMD_BUF_SIZE, DMA_TO_DEVICE); if (err) { dev_err(dev, "dpsw_acl_add_entry() failed %d\n", err); @@ -181,8 +182,8 @@ dpaa2_switch_acl_entry_remove(struct dpaa2_switch_filter_block *block, err = dpsw_acl_remove_entry(ethsw->mc_io, 0, ethsw->dpsw_handle, block->acl_id, acl_entry_cfg); - dma_unmap_single(dev, acl_entry_cfg->key_iova, sizeof(cmd_buff), - DMA_TO_DEVICE); + dma_unmap_single(dev, acl_entry_cfg->key_iova, + DPAA2_ETHSW_PORT_ACL_CMD_BUF_SIZE, DMA_TO_DEVICE); if (err) { dev_err(dev, "dpsw_acl_remove_entry() failed %d\n", err); kfree(cmd_buff); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c index 97d3151076d53..e01a246124ac6 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c @@ -1998,9 +1998,6 @@ static int dpaa2_switch_port_attr_set_event(struct net_device *netdev, return notifier_from_errno(err); } -static struct notifier_block dpaa2_switch_port_switchdev_nb; -static struct notifier_block dpaa2_switch_port_switchdev_blocking_nb; - static int dpaa2_switch_port_bridge_join(struct net_device *netdev, struct net_device *upper_dev, struct netlink_ext_ack *extack) @@ -2043,9 +2040,7 @@ static int dpaa2_switch_port_bridge_join(struct net_device *netdev, goto err_egress_flood; err = switchdev_bridge_port_offload(netdev, netdev, NULL, - &dpaa2_switch_port_switchdev_nb, - &dpaa2_switch_port_switchdev_blocking_nb, - false, extack); + NULL, NULL, false, extack); if (err) goto err_switchdev_offload; @@ -2079,9 +2074,7 @@ static int dpaa2_switch_port_restore_rxvlan(struct net_device *vdev, int vid, vo static void dpaa2_switch_port_pre_bridge_leave(struct net_device *netdev) { - switchdev_bridge_port_unoffload(netdev, NULL, - &dpaa2_switch_port_switchdev_nb, - &dpaa2_switch_port_switchdev_blocking_nb); + switchdev_bridge_port_unoffload(netdev, NULL, NULL, NULL); } static int dpaa2_switch_port_bridge_leave(struct net_device *netdev) diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 77c8e9cfb4456..35c95f07fd6d7 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -3710,31 +3710,26 @@ static int fec_set_features(struct net_device *netdev, return 0; } -static u16 fec_enet_get_raw_vlan_tci(struct sk_buff *skb) -{ - struct vlan_ethhdr *vhdr; - unsigned short vlan_TCI = 0; - - if (skb->protocol == htons(ETH_P_ALL)) { - vhdr = (struct vlan_ethhdr *)(skb->data); - vlan_TCI = ntohs(vhdr->h_vlan_TCI); - } - - return vlan_TCI; -} - static u16 fec_enet_select_queue(struct net_device *ndev, struct sk_buff *skb, struct net_device *sb_dev) { struct fec_enet_private *fep = netdev_priv(ndev); - u16 vlan_tag; + u16 vlan_tag = 0; if (!(fep->quirks & FEC_QUIRK_HAS_AVB)) return netdev_pick_tx(ndev, skb, NULL); - vlan_tag = fec_enet_get_raw_vlan_tci(skb); - if (!vlan_tag) + /* VLAN is present in the payload.*/ + if (eth_type_vlan(skb->protocol)) { + struct vlan_ethhdr *vhdr = skb_vlan_eth_hdr(skb); + + vlan_tag = ntohs(vhdr->h_vlan_TCI); + /* VLAN is present in the skb but not yet pushed in the payload.*/ + } else if (skb_vlan_tag_present(skb)) { + vlan_tag = skb->vlan_tci; + } else { return vlan_tag; + } return fec_enet_vlan_pri_to_queue[vlan_tag >> 13]; } diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 83b09dcfafc4f..5703240474e5b 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -254,10 +254,13 @@ static int gve_napi_poll(struct napi_struct *napi, int budget) if (block->tx) { if (block->tx->q_num < priv->tx_cfg.num_queues) reschedule |= gve_tx_poll(block, budget); - else + else if (budget) reschedule |= gve_xdp_poll(block, budget); } + if (!budget) + return 0; + if (block->rx) { work_done = gve_rx_poll(block, budget); reschedule |= work_done == budget; @@ -298,6 +301,9 @@ static int gve_napi_poll_dqo(struct napi_struct *napi, int budget) if (block->tx) reschedule |= gve_tx_poll_dqo(block, /*do_clean=*/true); + if (!budget) + return 0; + if (block->rx) { work_done = gve_rx_poll_dqo(block, budget); reschedule |= work_done == budget; diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c index e84a066aa1a40..73655347902d2 100644 --- a/drivers/net/ethernet/google/gve/gve_rx.c +++ b/drivers/net/ethernet/google/gve/gve_rx.c @@ -1007,10 +1007,6 @@ int gve_rx_poll(struct gve_notify_block *block, int budget) feat = block->napi.dev->features; - /* If budget is 0, do all the work */ - if (budget == 0) - budget = INT_MAX; - if (budget > 0) work_done = gve_clean_rx_done(rx, budget, feat); diff --git a/drivers/net/ethernet/google/gve/gve_tx.c b/drivers/net/ethernet/google/gve/gve_tx.c index 6957a865cff37..9f6ffc4a54f0b 100644 --- a/drivers/net/ethernet/google/gve/gve_tx.c +++ b/drivers/net/ethernet/google/gve/gve_tx.c @@ -925,10 +925,6 @@ bool gve_xdp_poll(struct gve_notify_block *block, int budget) bool repoll; u32 to_do; - /* If budget is 0, do all the work */ - if (budget == 0) - budget = INT_MAX; - /* Find out how much work there is to be done */ nic_done = gve_tx_load_event_counter(priv, tx); to_do = min_t(u32, (nic_done - tx->done), budget); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c index 928d934cb21a5..f75668c479351 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c @@ -66,6 +66,27 @@ static enum mac_mode hns_get_enet_interface(const struct hns_mac_cb *mac_cb) } } +static u32 hns_mac_link_anti_shake(struct mac_driver *mac_ctrl_drv) +{ +#define HNS_MAC_LINK_WAIT_TIME 5 +#define HNS_MAC_LINK_WAIT_CNT 40 + + u32 link_status = 0; + int i; + + if (!mac_ctrl_drv->get_link_status) + return link_status; + + for (i = 0; i < HNS_MAC_LINK_WAIT_CNT; i++) { + msleep(HNS_MAC_LINK_WAIT_TIME); + mac_ctrl_drv->get_link_status(mac_ctrl_drv, &link_status); + if (!link_status) + break; + } + + return link_status; +} + void hns_mac_get_link_status(struct hns_mac_cb *mac_cb, u32 *link_status) { struct mac_driver *mac_ctrl_drv; @@ -83,6 +104,14 @@ void hns_mac_get_link_status(struct hns_mac_cb *mac_cb, u32 *link_status) &sfp_prsnt); if (!ret) *link_status = *link_status && sfp_prsnt; + + /* for FIBER port, it may have a fake link up. + * when the link status changes from down to up, we need to do + * anti-shake. the anti-shake time is base on tests. + * only FIBER port need to do this. + */ + if (*link_status && !mac_cb->link) + *link_status = hns_mac_link_anti_shake(mac_ctrl_drv); } mac_cb->link = *link_status; diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index 7cf10d1e2b311..85722afe21770 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -142,7 +142,8 @@ MODULE_DEVICE_TABLE(acpi, hns_enet_acpi_match); static void fill_desc(struct hnae_ring *ring, void *priv, int size, dma_addr_t dma, int frag_end, - int buf_num, enum hns_desc_type type, int mtu) + int buf_num, enum hns_desc_type type, int mtu, + bool is_gso) { struct hnae_desc *desc = &ring->desc[ring->next_to_use]; struct hnae_desc_cb *desc_cb = &ring->desc_cb[ring->next_to_use]; @@ -275,6 +276,15 @@ static int hns_nic_maybe_stop_tso( return 0; } +static int hns_nic_maybe_stop_tx_v2(struct sk_buff **out_skb, int *bnum, + struct hnae_ring *ring) +{ + if (skb_is_gso(*out_skb)) + return hns_nic_maybe_stop_tso(out_skb, bnum, ring); + else + return hns_nic_maybe_stop_tx(out_skb, bnum, ring); +} + static void fill_tso_desc(struct hnae_ring *ring, void *priv, int size, dma_addr_t dma, int frag_end, int buf_num, enum hns_desc_type type, int mtu) @@ -300,6 +310,19 @@ static void fill_tso_desc(struct hnae_ring *ring, void *priv, mtu); } +static void fill_desc_v2(struct hnae_ring *ring, void *priv, + int size, dma_addr_t dma, int frag_end, + int buf_num, enum hns_desc_type type, int mtu, + bool is_gso) +{ + if (is_gso) + fill_tso_desc(ring, priv, size, dma, frag_end, buf_num, type, + mtu); + else + fill_v2_desc(ring, priv, size, dma, frag_end, buf_num, type, + mtu); +} + netdev_tx_t hns_nic_net_xmit_hw(struct net_device *ndev, struct sk_buff *skb, struct hns_nic_ring_data *ring_data) @@ -313,6 +336,7 @@ netdev_tx_t hns_nic_net_xmit_hw(struct net_device *ndev, int seg_num; dma_addr_t dma; int size, next_to_use; + bool is_gso; int i; switch (priv->ops.maybe_stop_tx(&skb, &buf_num, ring)) { @@ -339,8 +363,9 @@ netdev_tx_t hns_nic_net_xmit_hw(struct net_device *ndev, ring->stats.sw_err_cnt++; goto out_err_tx_ok; } + is_gso = skb_is_gso(skb); priv->ops.fill_desc(ring, skb, size, dma, seg_num == 1 ? 1 : 0, - buf_num, DESC_TYPE_SKB, ndev->mtu); + buf_num, DESC_TYPE_SKB, ndev->mtu, is_gso); /* fill the fragments */ for (i = 1; i < seg_num; i++) { @@ -354,7 +379,7 @@ netdev_tx_t hns_nic_net_xmit_hw(struct net_device *ndev, } priv->ops.fill_desc(ring, skb_frag_page(frag), size, dma, seg_num - 1 == i ? 1 : 0, buf_num, - DESC_TYPE_PAGE, ndev->mtu); + DESC_TYPE_PAGE, ndev->mtu, is_gso); } /*complete translate all packets*/ @@ -1776,15 +1801,6 @@ static int hns_nic_set_features(struct net_device *netdev, netdev_info(netdev, "enet v1 do not support tso!\n"); break; default: - if (features & (NETIF_F_TSO | NETIF_F_TSO6)) { - priv->ops.fill_desc = fill_tso_desc; - priv->ops.maybe_stop_tx = hns_nic_maybe_stop_tso; - /* The chip only support 7*4096 */ - netif_set_tso_max_size(netdev, 7 * 4096); - } else { - priv->ops.fill_desc = fill_v2_desc; - priv->ops.maybe_stop_tx = hns_nic_maybe_stop_tx; - } break; } netdev->features = features; @@ -2159,16 +2175,9 @@ static void hns_nic_set_priv_ops(struct net_device *netdev) priv->ops.maybe_stop_tx = hns_nic_maybe_stop_tx; } else { priv->ops.get_rxd_bnum = get_v2rx_desc_bnum; - if ((netdev->features & NETIF_F_TSO) || - (netdev->features & NETIF_F_TSO6)) { - priv->ops.fill_desc = fill_tso_desc; - priv->ops.maybe_stop_tx = hns_nic_maybe_stop_tso; - /* This chip only support 7*4096 */ - netif_set_tso_max_size(netdev, 7 * 4096); - } else { - priv->ops.fill_desc = fill_v2_desc; - priv->ops.maybe_stop_tx = hns_nic_maybe_stop_tx; - } + priv->ops.fill_desc = fill_desc_v2; + priv->ops.maybe_stop_tx = hns_nic_maybe_stop_tx_v2; + netif_set_tso_max_size(netdev, 7 * 4096); /* enable tso when init * control tso on/off through TSE bit in bd */ diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.h b/drivers/net/ethernet/hisilicon/hns/hns_enet.h index ffa9d6573f54b..3f3ee032f631c 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.h @@ -44,7 +44,8 @@ struct hns_nic_ring_data { struct hns_nic_ops { void (*fill_desc)(struct hnae_ring *ring, void *priv, int size, dma_addr_t dma, int frag_end, - int buf_num, enum hns_desc_type type, int mtu); + int buf_num, enum hns_desc_type type, int mtu, + bool is_gso); int (*maybe_stop_tx)(struct sk_buff **out_skb, int *bnum, struct hnae_ring *ring); void (*get_rxd_bnum)(u32 bnum_flag, int *out_bnum); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c index b8508533878be..4f385a18d288e 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c @@ -500,11 +500,14 @@ static void hns3_get_coal_info(struct hns3_enet_tqp_vector *tqp_vector, } sprintf(result[j++], "%d", i); - sprintf(result[j++], "%s", dim_state_str[dim->state]); + sprintf(result[j++], "%s", dim->state < ARRAY_SIZE(dim_state_str) ? + dim_state_str[dim->state] : "unknown"); sprintf(result[j++], "%u", dim->profile_ix); - sprintf(result[j++], "%s", dim_cqe_mode_str[dim->mode]); + sprintf(result[j++], "%s", dim->mode < ARRAY_SIZE(dim_cqe_mode_str) ? + dim_cqe_mode_str[dim->mode] : "unknown"); sprintf(result[j++], "%s", - dim_tune_stat_str[dim->tune_state]); + dim->tune_state < ARRAY_SIZE(dim_tune_stat_str) ? + dim_tune_stat_str[dim->tune_state] : "unknown"); sprintf(result[j++], "%u", dim->steps_left); sprintf(result[j++], "%u", dim->steps_right); sprintf(result[j++], "%u", dim->tired); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index cf50368441b78..677cfaa5fe08c 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -5140,7 +5140,7 @@ static int hns3_init_mac_addr(struct net_device *netdev) struct hns3_nic_priv *priv = netdev_priv(netdev); char format_mac_addr[HNAE3_FORMAT_MAC_ADDR_LEN]; struct hnae3_handle *h = priv->ae_handle; - u8 mac_addr_temp[ETH_ALEN]; + u8 mac_addr_temp[ETH_ALEN] = {0}; int ret = 0; if (h->ae_algo->ops->get_mac_addr) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index c42574e297476..a61d9fd732b96 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -61,6 +61,7 @@ static void hclge_sync_fd_table(struct hclge_dev *hdev); static void hclge_update_fec_stats(struct hclge_dev *hdev); static int hclge_mac_link_status_wait(struct hclge_dev *hdev, int link_ret, int wait_cnt); +static int hclge_update_port_info(struct hclge_dev *hdev); static struct hnae3_ae_algo ae_algo; @@ -3043,6 +3044,9 @@ static void hclge_update_link_status(struct hclge_dev *hdev) if (state != hdev->hw.mac.link) { hdev->hw.mac.link = state; + if (state == HCLGE_LINK_STATUS_UP) + hclge_update_port_info(hdev); + client->ops->link_status_change(handle, state); hclge_config_mac_tnl_int(hdev, state); if (rclient && rclient->ops->link_status_change) @@ -10026,8 +10030,6 @@ static void hclge_rm_vport_vlan_table(struct hclge_vport *vport, u16 vlan_id, struct hclge_vport_vlan_cfg *vlan, *tmp; struct hclge_dev *hdev = vport->back; - mutex_lock(&hdev->vport_lock); - list_for_each_entry_safe(vlan, tmp, &vport->vlan_list, node) { if (vlan->vlan_id == vlan_id) { if (is_write_tbl && vlan->hd_tbl_status) @@ -10042,8 +10044,6 @@ static void hclge_rm_vport_vlan_table(struct hclge_vport *vport, u16 vlan_id, break; } } - - mutex_unlock(&hdev->vport_lock); } void hclge_rm_vport_all_vlan_table(struct hclge_vport *vport, bool is_del_list) @@ -10452,11 +10452,16 @@ int hclge_set_vlan_filter(struct hnae3_handle *handle, __be16 proto, * handle mailbox. Just record the vlan id, and remove it after * reset finished. */ + mutex_lock(&hdev->vport_lock); if ((test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state) || test_bit(HCLGE_STATE_RST_FAIL, &hdev->state)) && is_kill) { set_bit(vlan_id, vport->vlan_del_fail_bmap); + mutex_unlock(&hdev->vport_lock); return -EBUSY; + } else if (!is_kill && test_bit(vlan_id, vport->vlan_del_fail_bmap)) { + clear_bit(vlan_id, vport->vlan_del_fail_bmap); } + mutex_unlock(&hdev->vport_lock); /* when port base vlan enabled, we use port base vlan as the vlan * filter entry. In this case, we don't update vlan filter table @@ -10471,17 +10476,22 @@ int hclge_set_vlan_filter(struct hnae3_handle *handle, __be16 proto, } if (!ret) { - if (!is_kill) + if (!is_kill) { hclge_add_vport_vlan_table(vport, vlan_id, writen_to_tbl); - else if (is_kill && vlan_id != 0) + } else if (is_kill && vlan_id != 0) { + mutex_lock(&hdev->vport_lock); hclge_rm_vport_vlan_table(vport, vlan_id, false); + mutex_unlock(&hdev->vport_lock); + } } else if (is_kill) { /* when remove hw vlan filter failed, record the vlan id, * and try to remove it from hw later, to be consistence * with stack */ + mutex_lock(&hdev->vport_lock); set_bit(vlan_id, vport->vlan_del_fail_bmap); + mutex_unlock(&hdev->vport_lock); } hclge_set_vport_vlan_fltr_change(vport); @@ -10521,6 +10531,7 @@ static void hclge_sync_vlan_filter(struct hclge_dev *hdev) int i, ret, sync_cnt = 0; u16 vlan_id; + mutex_lock(&hdev->vport_lock); /* start from vport 1 for PF is always alive */ for (i = 0; i < hdev->num_alloc_vport; i++) { struct hclge_vport *vport = &hdev->vport[i]; @@ -10531,21 +10542,26 @@ static void hclge_sync_vlan_filter(struct hclge_dev *hdev) ret = hclge_set_vlan_filter_hw(hdev, htons(ETH_P_8021Q), vport->vport_id, vlan_id, true); - if (ret && ret != -EINVAL) + if (ret && ret != -EINVAL) { + mutex_unlock(&hdev->vport_lock); return; + } clear_bit(vlan_id, vport->vlan_del_fail_bmap); hclge_rm_vport_vlan_table(vport, vlan_id, false); hclge_set_vport_vlan_fltr_change(vport); sync_cnt++; - if (sync_cnt >= HCLGE_MAX_SYNC_COUNT) + if (sync_cnt >= HCLGE_MAX_SYNC_COUNT) { + mutex_unlock(&hdev->vport_lock); return; + } vlan_id = find_first_bit(vport->vlan_del_fail_bmap, VLAN_N_VID); } } + mutex_unlock(&hdev->vport_lock); hclge_sync_vlan_fltr_state(hdev); } @@ -11652,6 +11668,7 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) goto err_msi_irq_uninit; if (hdev->hw.mac.media_type == HNAE3_MEDIA_TYPE_COPPER) { + clear_bit(HNAE3_DEV_SUPPORT_FEC_B, ae_dev->caps); if (hnae3_dev_phy_imp_supported(hdev)) ret = hclge_update_tp_port_info(hdev); else diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index a4d68fb216fb9..0aa9beefd1c7e 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -1206,6 +1206,8 @@ static int hclgevf_set_vlan_filter(struct hnae3_handle *handle, test_bit(HCLGEVF_STATE_RST_FAIL, &hdev->state)) && is_kill) { set_bit(vlan_id, hdev->vlan_del_fail_bmap); return -EBUSY; + } else if (!is_kill && test_bit(vlan_id, hdev->vlan_del_fail_bmap)) { + clear_bit(vlan_id, hdev->vlan_del_fail_bmap); } hclgevf_build_send_msg(&send_msg, HCLGE_MBX_SET_VLAN, @@ -1233,20 +1235,25 @@ static void hclgevf_sync_vlan_filter(struct hclgevf_dev *hdev) int ret, sync_cnt = 0; u16 vlan_id; + if (bitmap_empty(hdev->vlan_del_fail_bmap, VLAN_N_VID)) + return; + + rtnl_lock(); vlan_id = find_first_bit(hdev->vlan_del_fail_bmap, VLAN_N_VID); while (vlan_id != VLAN_N_VID) { ret = hclgevf_set_vlan_filter(handle, htons(ETH_P_8021Q), vlan_id, true); if (ret) - return; + break; clear_bit(vlan_id, hdev->vlan_del_fail_bmap); sync_cnt++; if (sync_cnt >= HCLGEVF_MAX_SYNC_COUNT) - return; + break; vlan_id = find_first_bit(hdev->vlan_del_fail_bmap, VLAN_N_VID); } + rtnl_unlock(); } static int hclgevf_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable) @@ -1974,8 +1981,18 @@ static enum hclgevf_evt_cause hclgevf_check_evt_cause(struct hclgevf_dev *hdev, return HCLGEVF_VECTOR0_EVENT_OTHER; } +static void hclgevf_reset_timer(struct timer_list *t) +{ + struct hclgevf_dev *hdev = from_timer(hdev, t, reset_timer); + + hclgevf_clear_event_cause(hdev, HCLGEVF_VECTOR0_EVENT_RST); + hclgevf_reset_task_schedule(hdev); +} + static irqreturn_t hclgevf_misc_irq_handle(int irq, void *data) { +#define HCLGEVF_RESET_DELAY 5 + enum hclgevf_evt_cause event_cause; struct hclgevf_dev *hdev = data; u32 clearval; @@ -1987,7 +2004,8 @@ static irqreturn_t hclgevf_misc_irq_handle(int irq, void *data) switch (event_cause) { case HCLGEVF_VECTOR0_EVENT_RST: - hclgevf_reset_task_schedule(hdev); + mod_timer(&hdev->reset_timer, + jiffies + msecs_to_jiffies(HCLGEVF_RESET_DELAY)); break; case HCLGEVF_VECTOR0_EVENT_MBX: hclgevf_mbx_handler(hdev); @@ -2930,6 +2948,7 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev) HCLGEVF_DRIVER_NAME); hclgevf_task_schedule(hdev, round_jiffies_relative(HZ)); + timer_setup(&hdev->reset_timer, hclgevf_reset_timer, 0); return 0; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h index 81c16b8c8da29..a73f2bf3a56a6 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h @@ -219,6 +219,7 @@ struct hclgevf_dev { enum hnae3_reset_type reset_level; unsigned long reset_pending; enum hnae3_reset_type reset_type; + struct timer_list reset_timer; #define HCLGEVF_RESET_REQUESTED 0 #define HCLGEVF_RESET_PENDING 1 diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c index bbf7b14079de3..85c2a634c8f96 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c @@ -63,6 +63,9 @@ static int hclgevf_get_mbx_resp(struct hclgevf_dev *hdev, u16 code0, u16 code1, i++; } + /* ensure additional_info will be seen after received_resp */ + smp_rmb(); + if (i >= HCLGEVF_MAX_TRY_TIMES) { dev_err(&hdev->pdev->dev, "VF could not get mbx(%u,%u) resp(=%d) from PF in %d tries\n", @@ -178,6 +181,10 @@ static void hclgevf_handle_mbx_response(struct hclgevf_dev *hdev, resp->resp_status = hclgevf_resp_to_errno(resp_status); memcpy(resp->additional_info, req->msg.resp_data, HCLGE_MBX_MAX_RESP_DATA_SIZE * sizeof(u8)); + + /* ensure additional_info will be seen before setting received_resp */ + smp_wmb(); + if (match_id) { /* If match_id is not zero, it means PF support match_id. * if the match_id is right, VF get the right response, or diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 00ca2b88165cb..a9f5a8a7d3f05 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -16195,7 +16195,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) I40E_PRTGL_SAH_MFS_MASK) >> I40E_PRTGL_SAH_MFS_SHIFT; if (val < MAX_FRAME_SIZE_DEFAULT) dev_warn(&pdev->dev, "MFS for port %x has been set below the default: %x\n", - i, val); + pf->hw.port, val); /* Add a filter to drop all Flow control frames from any VSI from being * transmitted. By doing so we stop a malicious VF from sending out diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index d3d6415553ed6..4441b00297f47 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -3842,7 +3842,7 @@ static int i40e_vc_add_cloud_filter(struct i40e_vf *vf, u8 *msg) struct i40e_pf *pf = vf->pf; struct i40e_vsi *vsi = NULL; int aq_ret = 0; - int i, ret; + int i; if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { aq_ret = -EINVAL; @@ -3866,8 +3866,10 @@ static int i40e_vc_add_cloud_filter(struct i40e_vf *vf, u8 *msg) } cfilter = kzalloc(sizeof(*cfilter), GFP_KERNEL); - if (!cfilter) - return -ENOMEM; + if (!cfilter) { + aq_ret = -ENOMEM; + goto err_out; + } /* parse destination mac address */ for (i = 0; i < ETH_ALEN; i++) @@ -3915,13 +3917,13 @@ static int i40e_vc_add_cloud_filter(struct i40e_vf *vf, u8 *msg) /* Adding cloud filter programmed as TC filter */ if (tcf.dst_port) - ret = i40e_add_del_cloud_filter_big_buf(vsi, cfilter, true); + aq_ret = i40e_add_del_cloud_filter_big_buf(vsi, cfilter, true); else - ret = i40e_add_del_cloud_filter(vsi, cfilter, true); - if (ret) { + aq_ret = i40e_add_del_cloud_filter(vsi, cfilter, true); + if (aq_ret) { dev_err(&pf->pdev->dev, "VF %d: Failed to add cloud filter, err %pe aq_err %s\n", - vf->vf_id, ERR_PTR(ret), + vf->vf_id, ERR_PTR(aq_ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); goto err_free; } diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index d8d7b62ceb24e..431d9d62c8c66 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -303,6 +303,7 @@ struct iavf_adapter { #define IAVF_FLAG_QUEUES_DISABLED BIT(17) #define IAVF_FLAG_SETUP_NETDEV_FEATURES BIT(18) #define IAVF_FLAG_REINIT_MSIX_NEEDED BIT(20) +#define IAVF_FLAG_FDIR_ENABLED BIT(21) /* duplicates for common code */ #define IAVF_FLAG_DCB_ENABLED 0 /* flags for admin queue service task */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index 90397293525f7..892c6a4f03bb8 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -829,18 +829,10 @@ static int __iavf_set_coalesce(struct net_device *netdev, struct iavf_adapter *adapter = netdev_priv(netdev); int i; - if (ec->rx_coalesce_usecs == 0) { - if (ec->use_adaptive_rx_coalesce) - netif_info(adapter, drv, netdev, "rx-usecs=0, need to disable adaptive-rx for a complete disable\n"); - } else if ((ec->rx_coalesce_usecs < IAVF_MIN_ITR) || - (ec->rx_coalesce_usecs > IAVF_MAX_ITR)) { + if (ec->rx_coalesce_usecs > IAVF_MAX_ITR) { netif_info(adapter, drv, netdev, "Invalid value, rx-usecs range is 0-8160\n"); return -EINVAL; - } else if (ec->tx_coalesce_usecs == 0) { - if (ec->use_adaptive_tx_coalesce) - netif_info(adapter, drv, netdev, "tx-usecs=0, need to disable adaptive-tx for a complete disable\n"); - } else if ((ec->tx_coalesce_usecs < IAVF_MIN_ITR) || - (ec->tx_coalesce_usecs > IAVF_MAX_ITR)) { + } else if (ec->tx_coalesce_usecs > IAVF_MAX_ITR) { netif_info(adapter, drv, netdev, "Invalid value, tx-usecs range is 0-8160\n"); return -EINVAL; } @@ -1071,7 +1063,7 @@ iavf_get_ethtool_fdir_entry(struct iavf_adapter *adapter, struct iavf_fdir_fltr *rule = NULL; int ret = 0; - if (!FDIR_FLTR_SUPPORT(adapter)) + if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED)) return -EOPNOTSUPP; spin_lock_bh(&adapter->fdir_fltr_lock); @@ -1213,7 +1205,7 @@ iavf_get_fdir_fltr_ids(struct iavf_adapter *adapter, struct ethtool_rxnfc *cmd, unsigned int cnt = 0; int val = 0; - if (!FDIR_FLTR_SUPPORT(adapter)) + if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED)) return -EOPNOTSUPP; cmd->data = IAVF_MAX_FDIR_FILTERS; @@ -1405,7 +1397,7 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx int count = 50; int err; - if (!FDIR_FLTR_SUPPORT(adapter)) + if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED)) return -EOPNOTSUPP; if (fsp->flow_type & FLOW_MAC_EXT) @@ -1446,12 +1438,16 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx spin_lock_bh(&adapter->fdir_fltr_lock); iavf_fdir_list_add_fltr(adapter, fltr); adapter->fdir_active_fltr++; - fltr->state = IAVF_FDIR_FLTR_ADD_REQUEST; - adapter->aq_required |= IAVF_FLAG_AQ_ADD_FDIR_FILTER; + if (adapter->link_up) { + fltr->state = IAVF_FDIR_FLTR_ADD_REQUEST; + adapter->aq_required |= IAVF_FLAG_AQ_ADD_FDIR_FILTER; + } else { + fltr->state = IAVF_FDIR_FLTR_INACTIVE; + } spin_unlock_bh(&adapter->fdir_fltr_lock); - mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0); - + if (adapter->link_up) + mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0); ret: if (err && fltr) kfree(fltr); @@ -1473,7 +1469,7 @@ static int iavf_del_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx struct iavf_fdir_fltr *fltr = NULL; int err = 0; - if (!FDIR_FLTR_SUPPORT(adapter)) + if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED)) return -EOPNOTSUPP; spin_lock_bh(&adapter->fdir_fltr_lock); @@ -1482,6 +1478,11 @@ static int iavf_del_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx if (fltr->state == IAVF_FDIR_FLTR_ACTIVE) { fltr->state = IAVF_FDIR_FLTR_DEL_REQUEST; adapter->aq_required |= IAVF_FLAG_AQ_DEL_FDIR_FILTER; + } else if (fltr->state == IAVF_FDIR_FLTR_INACTIVE) { + list_del(&fltr->list); + kfree(fltr); + adapter->fdir_active_fltr--; + fltr = NULL; } else { err = -EBUSY; } @@ -1790,7 +1791,7 @@ static int iavf_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, ret = 0; break; case ETHTOOL_GRXCLSRLCNT: - if (!FDIR_FLTR_SUPPORT(adapter)) + if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED)) break; spin_lock_bh(&adapter->fdir_fltr_lock); cmd->rule_cnt = adapter->fdir_active_fltr; diff --git a/drivers/net/ethernet/intel/iavf/iavf_fdir.h b/drivers/net/ethernet/intel/iavf/iavf_fdir.h index 9eb9f73f6adf3..d31bd923ba8cb 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_fdir.h +++ b/drivers/net/ethernet/intel/iavf/iavf_fdir.h @@ -6,12 +6,25 @@ struct iavf_adapter; -/* State of Flow Director filter */ +/* State of Flow Director filter + * + * *_REQUEST states are used to mark filter to be sent to PF driver to perform + * an action (either add or delete filter). *_PENDING states are an indication + * that request was sent to PF and the driver is waiting for response. + * + * Both DELETE and DISABLE states are being used to delete a filter in PF. + * The difference is that after a successful response filter in DEL_PENDING + * state is being deleted from VF driver as well and filter in DIS_PENDING state + * is being changed to INACTIVE state. + */ enum iavf_fdir_fltr_state_t { IAVF_FDIR_FLTR_ADD_REQUEST, /* User requests to add filter */ IAVF_FDIR_FLTR_ADD_PENDING, /* Filter pending add by the PF */ IAVF_FDIR_FLTR_DEL_REQUEST, /* User requests to delete filter */ IAVF_FDIR_FLTR_DEL_PENDING, /* Filter pending delete by the PF */ + IAVF_FDIR_FLTR_DIS_REQUEST, /* Filter scheduled to be disabled */ + IAVF_FDIR_FLTR_DIS_PENDING, /* Filter pending disable by the PF */ + IAVF_FDIR_FLTR_INACTIVE, /* Filter inactive on link down */ IAVF_FDIR_FLTR_ACTIVE, /* Filter is active */ }; diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 68783a7b70962..257865647c865 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -277,27 +277,6 @@ void iavf_free_virt_mem(struct iavf_hw *hw, struct iavf_virt_mem *mem) kfree(mem->va); } -/** - * iavf_lock_timeout - try to lock mutex but give up after timeout - * @lock: mutex that should be locked - * @msecs: timeout in msecs - * - * Returns 0 on success, negative on failure - **/ -static int iavf_lock_timeout(struct mutex *lock, unsigned int msecs) -{ - unsigned int wait, delay = 10; - - for (wait = 0; wait < msecs; wait += delay) { - if (mutex_trylock(lock)) - return 0; - - msleep(delay); - } - - return -1; -} - /** * iavf_schedule_reset - Set the flags and schedule a reset event * @adapter: board private structure @@ -1356,18 +1335,20 @@ static void iavf_clear_cloud_filters(struct iavf_adapter *adapter) **/ static void iavf_clear_fdir_filters(struct iavf_adapter *adapter) { - struct iavf_fdir_fltr *fdir, *fdirtmp; + struct iavf_fdir_fltr *fdir; /* remove all Flow Director filters */ spin_lock_bh(&adapter->fdir_fltr_lock); - list_for_each_entry_safe(fdir, fdirtmp, &adapter->fdir_list_head, - list) { + list_for_each_entry(fdir, &adapter->fdir_list_head, list) { if (fdir->state == IAVF_FDIR_FLTR_ADD_REQUEST) { - list_del(&fdir->list); - kfree(fdir); - adapter->fdir_active_fltr--; - } else { - fdir->state = IAVF_FDIR_FLTR_DEL_REQUEST; + /* Cancel a request, keep filter as inactive */ + fdir->state = IAVF_FDIR_FLTR_INACTIVE; + } else if (fdir->state == IAVF_FDIR_FLTR_ADD_PENDING || + fdir->state == IAVF_FDIR_FLTR_ACTIVE) { + /* Disable filters which are active or have a pending + * request to PF to be added + */ + fdir->state = IAVF_FDIR_FLTR_DIS_REQUEST; } } spin_unlock_bh(&adapter->fdir_fltr_lock); @@ -4174,6 +4155,33 @@ static int iavf_setup_tc(struct net_device *netdev, enum tc_setup_type type, } } +/** + * iavf_restore_fdir_filters + * @adapter: board private structure + * + * Restore existing FDIR filters when VF netdev comes back up. + **/ +static void iavf_restore_fdir_filters(struct iavf_adapter *adapter) +{ + struct iavf_fdir_fltr *f; + + spin_lock_bh(&adapter->fdir_fltr_lock); + list_for_each_entry(f, &adapter->fdir_list_head, list) { + if (f->state == IAVF_FDIR_FLTR_DIS_REQUEST) { + /* Cancel a request, keep filter as active */ + f->state = IAVF_FDIR_FLTR_ACTIVE; + } else if (f->state == IAVF_FDIR_FLTR_DIS_PENDING || + f->state == IAVF_FDIR_FLTR_INACTIVE) { + /* Add filters which are inactive or have a pending + * request to PF to be deleted + */ + f->state = IAVF_FDIR_FLTR_ADD_REQUEST; + adapter->aq_required |= IAVF_FLAG_AQ_ADD_FDIR_FILTER; + } + } + spin_unlock_bh(&adapter->fdir_fltr_lock); +} + /** * iavf_open - Called when a network interface is made active * @netdev: network interface device structure @@ -4241,8 +4249,9 @@ static int iavf_open(struct net_device *netdev) spin_unlock_bh(&adapter->mac_vlan_list_lock); - /* Restore VLAN filters that were removed with IFF_DOWN */ + /* Restore filters that were removed with IFF_DOWN */ iavf_restore_filters(adapter); + iavf_restore_fdir_filters(adapter); iavf_configure(adapter); @@ -4379,6 +4388,49 @@ static int iavf_change_mtu(struct net_device *netdev, int new_mtu) return ret; } +/** + * iavf_disable_fdir - disable Flow Director and clear existing filters + * @adapter: board private structure + **/ +static void iavf_disable_fdir(struct iavf_adapter *adapter) +{ + struct iavf_fdir_fltr *fdir, *fdirtmp; + bool del_filters = false; + + adapter->flags &= ~IAVF_FLAG_FDIR_ENABLED; + + /* remove all Flow Director filters */ + spin_lock_bh(&adapter->fdir_fltr_lock); + list_for_each_entry_safe(fdir, fdirtmp, &adapter->fdir_list_head, + list) { + if (fdir->state == IAVF_FDIR_FLTR_ADD_REQUEST || + fdir->state == IAVF_FDIR_FLTR_INACTIVE) { + /* Delete filters not registered in PF */ + list_del(&fdir->list); + kfree(fdir); + adapter->fdir_active_fltr--; + } else if (fdir->state == IAVF_FDIR_FLTR_ADD_PENDING || + fdir->state == IAVF_FDIR_FLTR_DIS_REQUEST || + fdir->state == IAVF_FDIR_FLTR_ACTIVE) { + /* Filters registered in PF, schedule their deletion */ + fdir->state = IAVF_FDIR_FLTR_DEL_REQUEST; + del_filters = true; + } else if (fdir->state == IAVF_FDIR_FLTR_DIS_PENDING) { + /* Request to delete filter already sent to PF, change + * state to DEL_PENDING to delete filter after PF's + * response, not set as INACTIVE + */ + fdir->state = IAVF_FDIR_FLTR_DEL_PENDING; + } + } + spin_unlock_bh(&adapter->fdir_fltr_lock); + + if (del_filters) { + adapter->aq_required |= IAVF_FLAG_AQ_DEL_FDIR_FILTER; + mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0); + } +} + #define NETIF_VLAN_OFFLOAD_FEATURES (NETIF_F_HW_VLAN_CTAG_RX | \ NETIF_F_HW_VLAN_CTAG_TX | \ NETIF_F_HW_VLAN_STAG_RX | \ @@ -4401,6 +4453,13 @@ static int iavf_set_features(struct net_device *netdev, iavf_set_vlan_offload_features(adapter, netdev->features, features); + if ((netdev->features & NETIF_F_NTUPLE) ^ (features & NETIF_F_NTUPLE)) { + if (features & NETIF_F_NTUPLE) + adapter->flags |= IAVF_FLAG_FDIR_ENABLED; + else + iavf_disable_fdir(adapter); + } + return 0; } @@ -4696,6 +4755,9 @@ static netdev_features_t iavf_fix_features(struct net_device *netdev, { struct iavf_adapter *adapter = netdev_priv(netdev); + if (!FDIR_FLTR_SUPPORT(adapter)) + features &= ~NETIF_F_NTUPLE; + return iavf_fix_netdev_vlan_features(adapter, features); } @@ -4813,6 +4875,12 @@ int iavf_process_config(struct iavf_adapter *adapter) if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN) netdev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; + if (FDIR_FLTR_SUPPORT(adapter)) { + netdev->hw_features |= NETIF_F_NTUPLE; + netdev->features |= NETIF_F_NTUPLE; + adapter->flags |= IAVF_FLAG_FDIR_ENABLED; + } + netdev->priv_flags |= IFF_UNICAST_FLT; /* Do not turn on offloads when they are requested to be turned off. @@ -4836,34 +4904,6 @@ int iavf_process_config(struct iavf_adapter *adapter) return 0; } -/** - * iavf_shutdown - Shutdown the device in preparation for a reboot - * @pdev: pci device structure - **/ -static void iavf_shutdown(struct pci_dev *pdev) -{ - struct iavf_adapter *adapter = iavf_pdev_to_adapter(pdev); - struct net_device *netdev = adapter->netdev; - - netif_device_detach(netdev); - - if (netif_running(netdev)) - iavf_close(netdev); - - if (iavf_lock_timeout(&adapter->crit_lock, 5000)) - 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; - mutex_unlock(&adapter->crit_lock); - -#ifdef CONFIG_PM - pci_save_state(pdev); - -#endif - pci_disable_device(pdev); -} - /** * iavf_probe - Device Initialization Routine * @pdev: PCI device information struct @@ -5077,17 +5117,22 @@ static int __maybe_unused iavf_resume(struct device *dev_d) **/ static void iavf_remove(struct pci_dev *pdev) { - struct iavf_adapter *adapter = iavf_pdev_to_adapter(pdev); struct iavf_fdir_fltr *fdir, *fdirtmp; struct iavf_vlan_filter *vlf, *vlftmp; struct iavf_cloud_filter *cf, *cftmp; struct iavf_adv_rss *rss, *rsstmp; struct iavf_mac_filter *f, *ftmp; + struct iavf_adapter *adapter; struct net_device *netdev; struct iavf_hw *hw; int err; - netdev = adapter->netdev; + /* Don't proceed with remove if netdev is already freed */ + netdev = pci_get_drvdata(pdev); + if (!netdev) + return; + + adapter = iavf_pdev_to_adapter(pdev); hw = &adapter->hw; if (test_and_set_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section)) @@ -5215,11 +5260,25 @@ static void iavf_remove(struct pci_dev *pdev) destroy_workqueue(adapter->wq); + pci_set_drvdata(pdev, NULL); + free_netdev(netdev); pci_disable_device(pdev); } +/** + * iavf_shutdown - Shutdown the device in preparation for a reboot + * @pdev: pci device structure + **/ +static void iavf_shutdown(struct pci_dev *pdev) +{ + iavf_remove(pdev); + + if (system_state == SYSTEM_POWER_OFF) + pci_set_power_state(pdev, PCI_D3hot); +} + static SIMPLE_DEV_PM_OPS(iavf_pm_ops, iavf_suspend, iavf_resume); static struct pci_driver iavf_driver = { diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.h b/drivers/net/ethernet/intel/iavf/iavf_txrx.h index 7e6ee32d19b69..10ba36602c0c1 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_txrx.h +++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.h @@ -15,7 +15,6 @@ */ #define IAVF_ITR_DYNAMIC 0x8000 /* use top bit as a flag */ #define IAVF_ITR_MASK 0x1FFE /* mask for ITR register value */ -#define IAVF_MIN_ITR 2 /* reg uses 2 usec resolution */ #define IAVF_ITR_100K 10 /* all values below must be even */ #define IAVF_ITR_50K 20 #define IAVF_ITR_20K 50 diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 0b97b424e487a..b95a4f903204b 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -1738,8 +1738,8 @@ void iavf_add_fdir_filter(struct iavf_adapter *adapter) **/ void iavf_del_fdir_filter(struct iavf_adapter *adapter) { + struct virtchnl_fdir_del f = {}; struct iavf_fdir_fltr *fdir; - struct virtchnl_fdir_del f; bool process_fltr = false; int len; @@ -1756,11 +1756,16 @@ void iavf_del_fdir_filter(struct iavf_adapter *adapter) list_for_each_entry(fdir, &adapter->fdir_list_head, list) { if (fdir->state == IAVF_FDIR_FLTR_DEL_REQUEST) { process_fltr = true; - memset(&f, 0, len); f.vsi_id = fdir->vc_add_msg.vsi_id; f.flow_id = fdir->flow_id; fdir->state = IAVF_FDIR_FLTR_DEL_PENDING; break; + } else if (fdir->state == IAVF_FDIR_FLTR_DIS_REQUEST) { + process_fltr = true; + f.vsi_id = fdir->vc_add_msg.vsi_id; + f.flow_id = fdir->flow_id; + fdir->state = IAVF_FDIR_FLTR_DIS_PENDING; + break; } } spin_unlock_bh(&adapter->fdir_fltr_lock); @@ -1904,6 +1909,48 @@ static void iavf_netdev_features_vlan_strip_set(struct net_device *netdev, netdev->features &= ~NETIF_F_HW_VLAN_CTAG_RX; } +/** + * iavf_activate_fdir_filters - Reactivate all FDIR filters after a reset + * @adapter: private adapter structure + * + * Called after a reset to re-add all FDIR filters and delete some of them + * if they were pending to be deleted. + */ +static void iavf_activate_fdir_filters(struct iavf_adapter *adapter) +{ + struct iavf_fdir_fltr *f, *ftmp; + bool add_filters = false; + + spin_lock_bh(&adapter->fdir_fltr_lock); + list_for_each_entry_safe(f, ftmp, &adapter->fdir_list_head, list) { + if (f->state == IAVF_FDIR_FLTR_ADD_REQUEST || + f->state == IAVF_FDIR_FLTR_ADD_PENDING || + f->state == IAVF_FDIR_FLTR_ACTIVE) { + /* All filters and requests have been removed in PF, + * restore them + */ + f->state = IAVF_FDIR_FLTR_ADD_REQUEST; + add_filters = true; + } else if (f->state == IAVF_FDIR_FLTR_DIS_REQUEST || + f->state == IAVF_FDIR_FLTR_DIS_PENDING) { + /* Link down state, leave filters as inactive */ + f->state = IAVF_FDIR_FLTR_INACTIVE; + } else if (f->state == IAVF_FDIR_FLTR_DEL_REQUEST || + f->state == IAVF_FDIR_FLTR_DEL_PENDING) { + /* Delete filters that were pending to be deleted, the + * list on PF is already cleared after a reset + */ + list_del(&f->list); + kfree(f); + adapter->fdir_active_fltr--; + } + } + spin_unlock_bh(&adapter->fdir_fltr_lock); + + if (add_filters) + adapter->aq_required |= IAVF_FLAG_AQ_ADD_FDIR_FILTER; +} + /** * iavf_virtchnl_completion * @adapter: adapter structure @@ -2081,7 +2128,8 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, spin_lock_bh(&adapter->fdir_fltr_lock); list_for_each_entry(fdir, &adapter->fdir_list_head, list) { - if (fdir->state == IAVF_FDIR_FLTR_DEL_PENDING) { + if (fdir->state == IAVF_FDIR_FLTR_DEL_PENDING || + fdir->state == IAVF_FDIR_FLTR_DIS_PENDING) { fdir->state = IAVF_FDIR_FLTR_ACTIVE; dev_info(&adapter->pdev->dev, "Failed to del Flow Director filter, error %s\n", iavf_stat_str(&adapter->hw, @@ -2217,6 +2265,8 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, spin_unlock_bh(&adapter->mac_vlan_list_lock); + iavf_activate_fdir_filters(adapter); + iavf_parse_vf_resource_msg(adapter); /* negotiated VIRTCHNL_VF_OFFLOAD_VLAN_V2, so wait for the @@ -2406,7 +2456,9 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, list_for_each_entry_safe(fdir, fdir_tmp, &adapter->fdir_list_head, list) { if (fdir->state == IAVF_FDIR_FLTR_DEL_PENDING) { - if (del_fltr->status == VIRTCHNL_FDIR_SUCCESS) { + if (del_fltr->status == VIRTCHNL_FDIR_SUCCESS || + del_fltr->status == + VIRTCHNL_FDIR_FAILURE_RULE_NONEXIST) { dev_info(&adapter->pdev->dev, "Flow Director filter with location %u is deleted\n", fdir->loc); list_del(&fdir->list); @@ -2418,6 +2470,17 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, del_fltr->status); iavf_print_fdir_fltr(adapter, fdir); } + } else if (fdir->state == IAVF_FDIR_FLTR_DIS_PENDING) { + if (del_fltr->status == VIRTCHNL_FDIR_SUCCESS || + del_fltr->status == + VIRTCHNL_FDIR_FAILURE_RULE_NONEXIST) { + fdir->state = IAVF_FDIR_FLTR_INACTIVE; + } else { + fdir->state = IAVF_FDIR_FLTR_ACTIVE; + dev_info(&adapter->pdev->dev, "Failed to disable Flow Director filter with status: %d\n", + del_fltr->status); + iavf_print_fdir_fltr(adapter, fdir); + } } } spin_unlock_bh(&adapter->fdir_fltr_lock); diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index ad4d4702129f0..9be13e9840917 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -1757,14 +1757,14 @@ ice_phy_type_to_ethtool(struct net_device *netdev, linkmode_zero(ks->link_modes.supported); linkmode_zero(ks->link_modes.advertising); - for (i = 0; i < BITS_PER_TYPE(u64); i++) { + for (i = 0; i < ARRAY_SIZE(phy_type_low_lkup); i++) { if (phy_types_low & BIT_ULL(i)) ice_linkmode_set_bit(&phy_type_low_lkup[i], ks, req_speeds, advert_phy_type_lo, i); } - for (i = 0; i < BITS_PER_TYPE(u64); i++) { + for (i = 0; i < ARRAY_SIZE(phy_type_high_lkup); i++) { if (phy_types_high & BIT_ULL(i)) ice_linkmode_set_bit(&phy_type_high_lkup[i], ks, req_speeds, advert_phy_type_hi, diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c index fb40ad98e6aad..23e197c3d02a7 100644 --- a/drivers/net/ethernet/intel/ice/ice_lag.c +++ b/drivers/net/ethernet/intel/ice/ice_lag.c @@ -536,6 +536,50 @@ ice_lag_move_vf_node_tc(struct ice_lag *lag, u8 oldport, u8 newport, dev_dbg(dev, "Problem restarting traffic for LAG node move\n"); } +/** + * ice_lag_build_netdev_list - populate the lag struct's netdev list + * @lag: local lag struct + * @ndlist: pointer to netdev list to populate + */ +static void ice_lag_build_netdev_list(struct ice_lag *lag, + struct ice_lag_netdev_list *ndlist) +{ + struct ice_lag_netdev_list *nl; + struct net_device *tmp_nd; + + INIT_LIST_HEAD(&ndlist->node); + rcu_read_lock(); + for_each_netdev_in_bond_rcu(lag->upper_netdev, tmp_nd) { + nl = kzalloc(sizeof(*nl), GFP_ATOMIC); + if (!nl) + break; + + nl->netdev = tmp_nd; + list_add(&nl->node, &ndlist->node); + } + rcu_read_unlock(); + lag->netdev_head = &ndlist->node; +} + +/** + * ice_lag_destroy_netdev_list - free lag struct's netdev list + * @lag: pointer to local lag struct + * @ndlist: pointer to lag struct netdev list + */ +static void ice_lag_destroy_netdev_list(struct ice_lag *lag, + struct ice_lag_netdev_list *ndlist) +{ + struct ice_lag_netdev_list *entry, *n; + + rcu_read_lock(); + list_for_each_entry_safe(entry, n, &ndlist->node, node) { + list_del(&entry->node); + kfree(entry); + } + rcu_read_unlock(); + lag->netdev_head = NULL; +} + /** * ice_lag_move_single_vf_nodes - Move Tx scheduling nodes for single VF * @lag: primary interface LAG struct @@ -564,7 +608,6 @@ ice_lag_move_single_vf_nodes(struct ice_lag *lag, u8 oldport, u8 newport, void ice_lag_move_new_vf_nodes(struct ice_vf *vf) { struct ice_lag_netdev_list ndlist; - struct list_head *tmp, *n; u8 pri_port, act_port; struct ice_lag *lag; struct ice_vsi *vsi; @@ -588,38 +631,15 @@ void ice_lag_move_new_vf_nodes(struct ice_vf *vf) pri_port = pf->hw.port_info->lport; act_port = lag->active_port; - if (lag->upper_netdev) { - struct ice_lag_netdev_list *nl; - struct net_device *tmp_nd; - - INIT_LIST_HEAD(&ndlist.node); - rcu_read_lock(); - for_each_netdev_in_bond_rcu(lag->upper_netdev, tmp_nd) { - nl = kzalloc(sizeof(*nl), GFP_ATOMIC); - if (!nl) - break; - - nl->netdev = tmp_nd; - list_add(&nl->node, &ndlist.node); - } - rcu_read_unlock(); - } - - lag->netdev_head = &ndlist.node; + if (lag->upper_netdev) + ice_lag_build_netdev_list(lag, &ndlist); if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG) && lag->bonded && lag->primary && pri_port != act_port && !list_empty(lag->netdev_head)) ice_lag_move_single_vf_nodes(lag, pri_port, act_port, vsi->idx); - list_for_each_safe(tmp, n, &ndlist.node) { - struct ice_lag_netdev_list *entry; - - entry = list_entry(tmp, struct ice_lag_netdev_list, node); - list_del(&entry->node); - kfree(entry); - } - lag->netdev_head = NULL; + ice_lag_destroy_netdev_list(lag, &ndlist); new_vf_unlock: mutex_unlock(&pf->lag_mutex); @@ -646,6 +666,29 @@ static void ice_lag_move_vf_nodes(struct ice_lag *lag, u8 oldport, u8 newport) ice_lag_move_single_vf_nodes(lag, oldport, newport, i); } +/** + * ice_lag_move_vf_nodes_cfg - move vf nodes outside LAG netdev event context + * @lag: local lag struct + * @src_prt: lport value for source port + * @dst_prt: lport value for destination port + * + * This function is used to move nodes during an out-of-netdev-event situation, + * primarily when the driver needs to reconfigure or recreate resources. + * + * Must be called while holding the lag_mutex to avoid lag events from + * processing while out-of-sync moves are happening. Also, paired moves, + * such as used in a reset flow, should both be called under the same mutex + * lock to avoid changes between start of reset and end of reset. + */ +void ice_lag_move_vf_nodes_cfg(struct ice_lag *lag, u8 src_prt, u8 dst_prt) +{ + struct ice_lag_netdev_list ndlist; + + ice_lag_build_netdev_list(lag, &ndlist); + ice_lag_move_vf_nodes(lag, src_prt, dst_prt); + ice_lag_destroy_netdev_list(lag, &ndlist); +} + #define ICE_LAG_SRIOV_CP_RECIPE 10 #define ICE_LAG_SRIOV_TRAIN_PKT_LEN 16 @@ -1920,6 +1963,8 @@ int ice_init_lag(struct ice_pf *pf) int n, err; ice_lag_init_feature_support_flag(pf); + if (!ice_is_feature_supported(pf, ICE_F_SRIOV_LAG)) + return 0; pf->lag = kzalloc(sizeof(*lag), GFP_KERNEL); if (!pf->lag) @@ -2022,7 +2067,6 @@ void ice_lag_rebuild(struct ice_pf *pf) { struct ice_lag_netdev_list ndlist; struct ice_lag *lag, *prim_lag; - struct list_head *tmp, *n; u8 act_port, loc_port; if (!pf->lag || !pf->lag->bonded) @@ -2034,21 +2078,7 @@ void ice_lag_rebuild(struct ice_pf *pf) if (lag->primary) { prim_lag = lag; } else { - struct ice_lag_netdev_list *nl; - struct net_device *tmp_nd; - - INIT_LIST_HEAD(&ndlist.node); - rcu_read_lock(); - for_each_netdev_in_bond_rcu(lag->upper_netdev, tmp_nd) { - nl = kzalloc(sizeof(*nl), GFP_ATOMIC); - if (!nl) - break; - - nl->netdev = tmp_nd; - list_add(&nl->node, &ndlist.node); - } - rcu_read_unlock(); - lag->netdev_head = &ndlist.node; + ice_lag_build_netdev_list(lag, &ndlist); prim_lag = ice_lag_find_primary(lag); } @@ -2078,13 +2108,7 @@ void ice_lag_rebuild(struct ice_pf *pf) ice_clear_rdma_cap(pf); lag_rebuild_out: - list_for_each_safe(tmp, n, &ndlist.node) { - struct ice_lag_netdev_list *entry; - - entry = list_entry(tmp, struct ice_lag_netdev_list, node); - list_del(&entry->node); - kfree(entry); - } + ice_lag_destroy_netdev_list(lag, &ndlist); mutex_unlock(&pf->lag_mutex); } diff --git a/drivers/net/ethernet/intel/ice/ice_lag.h b/drivers/net/ethernet/intel/ice/ice_lag.h index facb6c894b6dd..7f22987675012 100644 --- a/drivers/net/ethernet/intel/ice/ice_lag.h +++ b/drivers/net/ethernet/intel/ice/ice_lag.h @@ -63,4 +63,5 @@ int ice_init_lag(struct ice_pf *pf); void ice_deinit_lag(struct ice_pf *pf); void ice_lag_rebuild(struct ice_pf *pf); bool ice_lag_is_switchdev_running(struct ice_pf *pf); +void ice_lag_move_vf_nodes_cfg(struct ice_lag *lag, u8 src_prt, u8 dst_prt); #endif /* _ICE_LAG_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 73bbf06a76db9..a66c3b6ccec1e 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -2384,6 +2384,9 @@ static int ice_vsi_cfg_tc_lan(struct ice_pf *pf, struct ice_vsi *vsi) } else { max_txqs[i] = vsi->alloc_txq; } + + if (vsi->type == ICE_VSI_PF) + max_txqs[i] += vsi->num_xdp_txq; } dev_dbg(dev, "vsi->tc_cfg.ena_tc = %d\n", vsi->tc_cfg.ena_tc); @@ -2633,10 +2636,6 @@ void ice_vsi_decfg(struct ice_vsi *vsi) if (vsi->type == ICE_VSI_VF && vsi->agg_node && vsi->agg_node->valid) vsi->agg_node->num_vsis--; - if (vsi->agg_node) { - vsi->agg_node->valid = false; - vsi->agg_node->agg_id = 0; - } } /** diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c index 24e4f4d897b66..d488c7156d093 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c @@ -827,12 +827,16 @@ static void ice_notify_vf_reset(struct ice_vf *vf) int ice_reset_vf(struct ice_vf *vf, u32 flags) { struct ice_pf *pf = vf->pf; + struct ice_lag *lag; struct ice_vsi *vsi; + u8 act_prt, pri_prt; struct device *dev; int err = 0; bool rsd; dev = ice_pf_to_dev(pf); + act_prt = ICE_LAG_INVALID_PORT; + pri_prt = pf->hw.port_info->lport; if (flags & ICE_VF_RESET_NOTIFY) ice_notify_vf_reset(vf); @@ -843,6 +847,17 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags) return 0; } + lag = pf->lag; + mutex_lock(&pf->lag_mutex); + if (lag && lag->bonded && lag->primary) { + act_prt = lag->active_port; + if (act_prt != pri_prt && act_prt != ICE_LAG_INVALID_PORT && + lag->upper_netdev) + ice_lag_move_vf_nodes_cfg(lag, act_prt, pri_prt); + else + act_prt = ICE_LAG_INVALID_PORT; + } + if (flags & ICE_VF_RESET_LOCK) mutex_lock(&vf->cfg_lock); else @@ -935,6 +950,11 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags) if (flags & ICE_VF_RESET_LOCK) mutex_unlock(&vf->cfg_lock); + if (lag && lag->bonded && lag->primary && + act_prt != ICE_LAG_INVALID_PORT) + ice_lag_move_vf_nodes_cfg(lag, pri_prt, act_prt); + mutex_unlock(&pf->lag_mutex); + return err; } diff --git a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c index d7b10dc67f035..80dc4bcdd3a41 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c @@ -32,7 +32,6 @@ static void ice_port_vlan_on(struct ice_vsi *vsi) /* setup outer VLAN ops */ vlan_ops->set_port_vlan = ice_vsi_set_outer_port_vlan; vlan_ops->clear_port_vlan = ice_vsi_clear_outer_port_vlan; - vlan_ops->clear_port_vlan = ice_vsi_clear_outer_port_vlan; /* setup inner VLAN ops */ vlan_ops = &vsi->inner_vlan_ops; @@ -47,8 +46,13 @@ static void ice_port_vlan_on(struct ice_vsi *vsi) vlan_ops->set_port_vlan = ice_vsi_set_inner_port_vlan; vlan_ops->clear_port_vlan = ice_vsi_clear_inner_port_vlan; - vlan_ops->clear_port_vlan = ice_vsi_clear_inner_port_vlan; } + + /* all Rx traffic should be in the domain of the assigned port VLAN, + * so prevent disabling Rx VLAN filtering + */ + vlan_ops->dis_rx_filtering = noop_vlan; + vlan_ops->ena_rx_filtering = ice_vsi_ena_rx_vlan_filtering; } @@ -77,6 +81,8 @@ static void ice_port_vlan_off(struct ice_vsi *vsi) vlan_ops->del_vlan = ice_vsi_del_vlan; } + vlan_ops->dis_rx_filtering = ice_vsi_dis_rx_vlan_filtering; + if (!test_bit(ICE_FLAG_VF_VLAN_PRUNING, pf->flags)) vlan_ops->ena_rx_filtering = noop_vlan; else @@ -141,7 +147,6 @@ void ice_vf_vsi_init_vlan_ops(struct ice_vsi *vsi) &vsi->outer_vlan_ops : &vsi->inner_vlan_ops; vlan_ops->add_vlan = ice_vsi_add_vlan; - vlan_ops->dis_rx_filtering = ice_vsi_dis_rx_vlan_filtering; vlan_ops->ena_tx_filtering = ice_vsi_ena_tx_vlan_filtering; vlan_ops->dis_tx_filtering = ice_vsi_dis_tx_vlan_filtering; } diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index db97353efd067..62337e6569b23 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -1600,9 +1600,24 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) (struct virtchnl_vsi_queue_config_info *)msg; struct virtchnl_queue_pair_info *qpi; struct ice_pf *pf = vf->pf; + struct ice_lag *lag; struct ice_vsi *vsi; + u8 act_prt, pri_prt; int i = -1, q_idx; + lag = pf->lag; + mutex_lock(&pf->lag_mutex); + act_prt = ICE_LAG_INVALID_PORT; + pri_prt = pf->hw.port_info->lport; + if (lag && lag->bonded && lag->primary) { + act_prt = lag->active_port; + if (act_prt != pri_prt && act_prt != ICE_LAG_INVALID_PORT && + lag->upper_netdev) + ice_lag_move_vf_nodes_cfg(lag, act_prt, pri_prt); + else + act_prt = ICE_LAG_INVALID_PORT; + } + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) goto error_param; @@ -1710,6 +1725,11 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) } } + if (lag && lag->bonded && lag->primary && + act_prt != ICE_LAG_INVALID_PORT) + ice_lag_move_vf_nodes_cfg(lag, pri_prt, act_prt); + mutex_unlock(&pf->lag_mutex); + /* send the response to the VF */ return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_CONFIG_VSI_QUEUES, VIRTCHNL_STATUS_SUCCESS, NULL, 0); @@ -1724,6 +1744,11 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) vf->vf_id, i); } + if (lag && lag->bonded && lag->primary && + act_prt != ICE_LAG_INVALID_PORT) + ice_lag_move_vf_nodes_cfg(lag, pri_prt, act_prt); + mutex_unlock(&pf->lag_mutex); + ice_lag_move_new_vf_nodes(vf); /* send the response to the VF */ diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index d483b8c00ec0e..165f76d1231c1 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -4790,14 +4790,17 @@ static void mvneta_ethtool_get_strings(struct net_device *netdev, u32 sset, u8 *data) { if (sset == ETH_SS_STATS) { + struct mvneta_port *pp = netdev_priv(netdev); int i; for (i = 0; i < ARRAY_SIZE(mvneta_statistics); i++) memcpy(data + i * ETH_GSTRING_LEN, mvneta_statistics[i].name, ETH_GSTRING_LEN); - data += ETH_GSTRING_LEN * ARRAY_SIZE(mvneta_statistics); - page_pool_ethtool_stats_get_strings(data); + if (!pp->bm_priv) { + data += ETH_GSTRING_LEN * ARRAY_SIZE(mvneta_statistics); + page_pool_ethtool_stats_get_strings(data); + } } } @@ -4915,8 +4918,10 @@ static void mvneta_ethtool_pp_stats(struct mvneta_port *pp, u64 *data) struct page_pool_stats stats = {}; int i; - for (i = 0; i < rxq_number; i++) - page_pool_get_stats(pp->rxqs[i].page_pool, &stats); + for (i = 0; i < rxq_number; i++) { + if (pp->rxqs[i].page_pool) + page_pool_get_stats(pp->rxqs[i].page_pool, &stats); + } page_pool_ethtool_stats_get(data, &stats); } @@ -4932,14 +4937,21 @@ static void mvneta_ethtool_get_stats(struct net_device *dev, for (i = 0; i < ARRAY_SIZE(mvneta_statistics); i++) *data++ = pp->ethtool_stats[i]; - mvneta_ethtool_pp_stats(pp, data); + if (!pp->bm_priv) + mvneta_ethtool_pp_stats(pp, data); } static int mvneta_ethtool_get_sset_count(struct net_device *dev, int sset) { - if (sset == ETH_SS_STATS) - return ARRAY_SIZE(mvneta_statistics) + - page_pool_ethtool_stats_get_count(); + if (sset == ETH_SS_STATS) { + int count = ARRAY_SIZE(mvneta_statistics); + struct mvneta_port *pp = netdev_priv(dev); + + if (!pp->bm_priv) + count += page_pool_ethtool_stats_get_count(); + + return count; + } return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c index 5b46ca47c8e59..2ee1374db4c06 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c @@ -1076,7 +1076,8 @@ static bool get_fw_ready_status(struct pci_dev *pdev) pci_read_config_byte(pdev, (pos + 8), &status); dev_info(&pdev->dev, "Firmware ready status = %u\n", status); - return status; +#define FW_STATUS_READY 1ULL + return status == FW_STATUS_READY; } return false; } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h index 6b5b06c2b4e99..31bd9aeb41e7e 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h @@ -1938,7 +1938,7 @@ struct mcs_hw_info { u8 tcam_entries; /* RX/TX Tcam entries per mcs block */ u8 secy_entries; /* RX/TX SECY entries per mcs block */ u8 sc_entries; /* RX/TX SC CAM entries per mcs block */ - u8 sa_entries; /* PN table entries = SA entries */ + u16 sa_entries; /* PN table entries = SA entries */ u64 rsvd[16]; }; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mcs.c b/drivers/net/ethernet/marvell/octeontx2/af/mcs.c index c43f19dfbd744..c1775bd01c2b4 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mcs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/mcs.c @@ -117,7 +117,7 @@ void mcs_get_rx_secy_stats(struct mcs *mcs, struct mcs_secy_stats *stats, int id reg = MCSX_CSE_RX_MEM_SLAVE_INPKTSSECYTAGGEDCTLX(id); stats->pkt_tagged_ctl_cnt = mcs_reg_read(mcs, reg); - reg = MCSX_CSE_RX_MEM_SLAVE_INPKTSSECYUNTAGGEDORNOTAGX(id); + reg = MCSX_CSE_RX_MEM_SLAVE_INPKTSSECYUNTAGGEDX(id); stats->pkt_untaged_cnt = mcs_reg_read(mcs, reg); reg = MCSX_CSE_RX_MEM_SLAVE_INPKTSSECYCTLX(id); @@ -215,7 +215,7 @@ void mcs_get_sc_stats(struct mcs *mcs, struct mcs_sc_stats *stats, reg = MCSX_CSE_RX_MEM_SLAVE_INPKTSSCNOTVALIDX(id); stats->pkt_notvalid_cnt = mcs_reg_read(mcs, reg); - reg = MCSX_CSE_RX_MEM_SLAVE_INPKTSSCUNCHECKEDOROKX(id); + reg = MCSX_CSE_RX_MEM_SLAVE_INPKTSSCUNCHECKEDX(id); stats->pkt_unchecked_cnt = mcs_reg_read(mcs, reg); if (mcs->hw->mcs_blks > 1) { @@ -1219,6 +1219,17 @@ struct mcs *mcs_get_pdata(int mcs_id) return NULL; } +bool is_mcs_bypass(int mcs_id) +{ + struct mcs *mcs_dev; + + list_for_each_entry(mcs_dev, &mcs_list, mcs_list) { + if (mcs_dev->mcs_id == mcs_id) + return mcs_dev->bypass; + } + return true; +} + void mcs_set_port_cfg(struct mcs *mcs, struct mcs_port_cfg_set_req *req) { u64 val = 0; @@ -1436,7 +1447,7 @@ static int mcs_x2p_calibration(struct mcs *mcs) return err; } -static void mcs_set_external_bypass(struct mcs *mcs, u8 bypass) +static void mcs_set_external_bypass(struct mcs *mcs, bool bypass) { u64 val; @@ -1447,6 +1458,7 @@ static void mcs_set_external_bypass(struct mcs *mcs, u8 bypass) else val &= ~BIT_ULL(6); mcs_reg_write(mcs, MCSX_MIL_GLOBAL, val); + mcs->bypass = bypass; } static void mcs_global_cfg(struct mcs *mcs) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mcs.h b/drivers/net/ethernet/marvell/octeontx2/af/mcs.h index 0f89dcb764654..f927cc61dfd21 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mcs.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mcs.h @@ -149,6 +149,7 @@ struct mcs { u16 num_vec; void *rvu; u16 *tx_sa_active; + bool bypass; }; struct mcs_ops { @@ -206,6 +207,7 @@ void mcs_get_custom_tag_cfg(struct mcs *mcs, struct mcs_custom_tag_cfg_get_req * int mcs_alloc_ctrlpktrule(struct rsrc_bmap *rsrc, u16 *pf_map, u16 offset, u16 pcifunc); int mcs_free_ctrlpktrule(struct mcs *mcs, struct mcs_free_ctrl_pkt_rule_req *req); int mcs_ctrlpktrule_write(struct mcs *mcs, struct mcs_ctrl_pkt_rule_write_req *req); +bool is_mcs_bypass(int mcs_id); /* CN10K-B APIs */ void cn10kb_mcs_set_hw_capabilities(struct mcs *mcs); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mcs_reg.h b/drivers/net/ethernet/marvell/octeontx2/af/mcs_reg.h index f3ab01fc363c8..f4c6de89002c1 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mcs_reg.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mcs_reg.h @@ -810,14 +810,37 @@ offset = 0x9d8ull; \ offset; }) +#define MCSX_CSE_RX_MEM_SLAVE_INPKTSSCUNCHECKEDX(a) ({ \ + u64 offset; \ + \ + offset = 0xee80ull; \ + if (mcs->hw->mcs_blks > 1) \ + offset = 0xe818ull; \ + offset += (a) * 0x8ull; \ + offset; }) + +#define MCSX_CSE_RX_MEM_SLAVE_INPKTSSECYUNTAGGEDX(a) ({ \ + u64 offset; \ + \ + offset = 0xa680ull; \ + if (mcs->hw->mcs_blks > 1) \ + offset = 0xd018ull; \ + offset += (a) * 0x8ull; \ + offset; }) + +#define MCSX_CSE_RX_MEM_SLAVE_INPKTSSCLATEORDELAYEDX(a) ({ \ + u64 offset; \ + \ + offset = 0xf680ull; \ + if (mcs->hw->mcs_blks > 1) \ + offset = 0xe018ull; \ + offset += (a) * 0x8ull; \ + offset; }) + #define MCSX_CSE_RX_MEM_SLAVE_INOCTETSSCDECRYPTEDX(a) (0xe680ull + (a) * 0x8ull) #define MCSX_CSE_RX_MEM_SLAVE_INOCTETSSCVALIDATEX(a) (0xde80ull + (a) * 0x8ull) -#define MCSX_CSE_RX_MEM_SLAVE_INPKTSSECYUNTAGGEDORNOTAGX(a) (0xa680ull + (a) * 0x8ull) #define MCSX_CSE_RX_MEM_SLAVE_INPKTSSECYNOTAGX(a) (0xd218 + (a) * 0x8ull) -#define MCSX_CSE_RX_MEM_SLAVE_INPKTSSECYUNTAGGEDX(a) (0xd018ull + (a) * 0x8ull) -#define MCSX_CSE_RX_MEM_SLAVE_INPKTSSCUNCHECKEDOROKX(a) (0xee80ull + (a) * 0x8ull) #define MCSX_CSE_RX_MEM_SLAVE_INPKTSSECYCTLX(a) (0xb680ull + (a) * 0x8ull) -#define MCSX_CSE_RX_MEM_SLAVE_INPKTSSCLATEORDELAYEDX(a) (0xf680ull + (a) * 0x8ull) #define MCSX_CSE_RX_MEM_SLAVE_INPKTSSAINVALIDX(a) (0x12680ull + (a) * 0x8ull) #define MCSX_CSE_RX_MEM_SLAVE_INPKTSSANOTUSINGSAERRORX(a) (0x15680ull + (a) * 0x8ull) #define MCSX_CSE_RX_MEM_SLAVE_INPKTSSANOTVALIDX(a) (0x13680ull + (a) * 0x8ull) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c index af21e2030cff2..4728ba34b0e34 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c @@ -373,6 +373,11 @@ void rpm_lmac_pause_frm_config(void *rpmd, int lmac_id, bool enable) cfg |= RPMX_MTI_MAC100X_COMMAND_CONFIG_TX_P_DISABLE; rpm_write(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG, cfg); + /* Disable forward pause to driver */ + cfg = rpm_read(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG); + cfg &= ~RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_FWD; + rpm_write(rpm, lmac_id, RPMX_MTI_MAC100X_COMMAND_CONFIG, cfg); + /* Enable channel mask for all LMACS */ if (is_dev_rpm2(rpm)) rpm_write(rpm, lmac_id, RPM2_CMR_CHAN_MSK_OR, 0xffff); @@ -616,12 +621,10 @@ int rpm_lmac_pfc_config(void *rpmd, int lmac_id, u8 tx_pause, u8 rx_pause, u16 p if (rx_pause) { cfg &= ~(RPMX_MTI_MAC100X_COMMAND_CONFIG_RX_P_DISABLE | - RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE | - RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_FWD); + RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE); } else { cfg |= (RPMX_MTI_MAC100X_COMMAND_CONFIG_RX_P_DISABLE | - RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE | - RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_FWD); + RPMX_MTI_MAC100X_COMMAND_CONFIG_PAUSE_IGNORE); } if (tx_pause) { diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c index 22c395c7d040b..731bb82b577c2 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c @@ -2631,6 +2631,9 @@ static void __rvu_flr_handler(struct rvu *rvu, u16 pcifunc) rvu_npc_free_mcam_entries(rvu, pcifunc, -1); rvu_mac_reset(rvu, pcifunc); + if (rvu->mcs_blk_cnt) + rvu_mcs_flr_handler(rvu, pcifunc); + mutex_unlock(&rvu->flr_lock); } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index c4d999ef5ab4b..cce2806aaa50c 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -345,6 +345,7 @@ struct nix_hw { struct nix_txvlan txvlan; struct nix_ipolicer *ipolicer; u64 *tx_credits; + u8 cc_mcs_cnt; }; /* RVU block's capabilities or functionality, diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c index 41df5ac23f927..bffe04e6d0254 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c @@ -642,7 +642,7 @@ static int rvu_nix_register_reporters(struct rvu_devlink *rvu_dl) rvu_dl->devlink_wq = create_workqueue("rvu_devlink_wq"); if (!rvu_dl->devlink_wq) - goto err; + return -ENOMEM; INIT_WORK(&rvu_reporters->intr_work, rvu_nix_intr_work); INIT_WORK(&rvu_reporters->gen_work, rvu_nix_gen_work); @@ -650,9 +650,6 @@ static int rvu_nix_register_reporters(struct rvu_devlink *rvu_dl) INIT_WORK(&rvu_reporters->ras_work, rvu_nix_ras_work); return 0; -err: - rvu_nix_health_reporters_destroy(rvu_dl); - return -ENOMEM; } static int rvu_nix_health_reporters_create(struct rvu_devlink *rvu_dl) @@ -1285,7 +1282,7 @@ static int rvu_npa_register_reporters(struct rvu_devlink *rvu_dl) rvu_dl->devlink_wq = create_workqueue("rvu_devlink_wq"); if (!rvu_dl->devlink_wq) - goto err; + return -ENOMEM; INIT_WORK(&rvu_reporters->intr_work, rvu_npa_intr_work); INIT_WORK(&rvu_reporters->err_work, rvu_npa_err_work); @@ -1293,9 +1290,6 @@ static int rvu_npa_register_reporters(struct rvu_devlink *rvu_dl) INIT_WORK(&rvu_reporters->ras_work, rvu_npa_ras_work); return 0; -err: - rvu_npa_health_reporters_destroy(rvu_dl); - return -ENOMEM; } static int rvu_npa_health_reporters_create(struct rvu_devlink *rvu_dl) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index 23c2f2ed2fb83..4227ebb4a758d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -12,6 +12,7 @@ #include "rvu_reg.h" #include "rvu.h" #include "npc.h" +#include "mcs.h" #include "cgx.h" #include "lmac_common.h" #include "rvu_npc_hash.h" @@ -4389,6 +4390,12 @@ static void nix_link_config(struct rvu *rvu, int blkaddr, SDP_HW_MAX_FRS << 16 | NIC_HW_MIN_FRS); } + /* Get MCS external bypass status for CN10K-B */ + if (mcs_get_blkcnt() == 1) { + /* Adjust for 2 credits when external bypass is disabled */ + nix_hw->cc_mcs_cnt = is_mcs_bypass(0) ? 0 : 2; + } + /* Set credits for Tx links assuming max packet length allowed. * This will be reconfigured based on MTU set for PF/VF. */ @@ -4412,6 +4419,7 @@ static void nix_link_config(struct rvu *rvu, int blkaddr, tx_credits = (lmac_fifo_len - lmac_max_frs) / 16; /* Enable credits and set credit pkt count to max allowed */ cfg = (tx_credits << 12) | (0x1FF << 2) | BIT_ULL(1); + cfg |= FIELD_PREP(NIX_AF_LINKX_MCS_CNT_MASK, nix_hw->cc_mcs_cnt); link = iter + slink; nix_hw->tx_credits[link] = tx_credits; @@ -5505,6 +5513,8 @@ int rvu_mbox_handler_nix_bandprof_free(struct rvu *rvu, ipolicer = &nix_hw->ipolicer[layer]; for (idx = 0; idx < req->prof_count[layer]; idx++) { + if (idx == MAX_BANDPROF_PER_PFFUNC) + break; prof_idx = req->prof_idx[layer][idx]; if (prof_idx >= ipolicer->band_prof.max || ipolicer->pfvf_map[prof_idx] != pcifunc) @@ -5518,8 +5528,6 @@ int rvu_mbox_handler_nix_bandprof_free(struct rvu *rvu, ipolicer->pfvf_map[prof_idx] = 0x00; ipolicer->match_id[prof_idx] = 0; rvu_free_rsrc(&ipolicer->band_prof, prof_idx); - if (idx == MAX_BANDPROF_PER_PFFUNC) - break; } } mutex_unlock(&rvu->rsrc_lock); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index 16cfc802e348d..0bcf3e5592806 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -389,7 +389,13 @@ static u64 npc_get_default_entry_action(struct rvu *rvu, struct npc_mcam *mcam, int bank, nixlf, index; /* get ucast entry rule entry index */ - nix_get_nixlf(rvu, pf_func, &nixlf, NULL); + if (nix_get_nixlf(rvu, pf_func, &nixlf, NULL)) { + dev_err(rvu->dev, "%s: nixlf not attached to pcifunc:0x%x\n", + __func__, pf_func); + /* Action 0 is drop */ + return 0; + } + index = npc_get_nixlf_mcam_index(mcam, pf_func, nixlf, NIXLF_UCAST_ENTRY); bank = npc_get_bank(mcam, index); @@ -665,6 +671,7 @@ void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc, int blkaddr, ucast_idx, index; struct nix_rx_action action = { 0 }; u64 relaxed_mask; + u8 flow_key_alg; if (!hw->cap.nix_rx_multicast && is_cgx_vf(rvu, pcifunc)) return; @@ -695,6 +702,8 @@ void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc, action.op = NIX_RX_ACTIONOP_UCAST; } + flow_key_alg = action.flow_key_alg; + /* RX_ACTION set to MCAST for CGX PF's */ if (hw->cap.nix_rx_multicast && pfvf->use_mce_list && is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc))) { @@ -734,7 +743,7 @@ void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc, req.vf = pcifunc; req.index = action.index; req.match_id = action.match_id; - req.flow_key_alg = action.flow_key_alg; + req.flow_key_alg = flow_key_alg; rvu_mbox_handler_npc_install_flow(rvu, &req, &rsp); } @@ -848,6 +857,7 @@ void rvu_npc_install_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf, u8 mac_addr[ETH_ALEN] = { 0 }; struct nix_rx_action action = { 0 }; struct rvu_pfvf *pfvf; + u8 flow_key_alg; u16 vf_func; /* Only CGX PF/VF can add allmulticast entry */ @@ -882,6 +892,7 @@ void rvu_npc_install_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf, *(u64 *)&action = npc_get_mcam_action(rvu, mcam, blkaddr, ucast_idx); + flow_key_alg = action.flow_key_alg; if (action.op != NIX_RX_ACTIONOP_RSS) { *(u64 *)&action = 0; action.op = NIX_RX_ACTIONOP_UCAST; @@ -918,7 +929,7 @@ void rvu_npc_install_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf, req.vf = pcifunc | vf_func; req.index = action.index; req.match_id = action.match_id; - req.flow_key_alg = action.flow_key_alg; + req.flow_key_alg = flow_key_alg; rvu_mbox_handler_npc_install_flow(rvu, &req, &rsp); } @@ -984,11 +995,38 @@ static void npc_update_vf_flow_entry(struct rvu *rvu, struct npc_mcam *mcam, mutex_unlock(&mcam->lock); } +static void npc_update_rx_action_with_alg_idx(struct rvu *rvu, struct nix_rx_action action, + struct rvu_pfvf *pfvf, int mcam_index, int blkaddr, + int alg_idx) + +{ + struct npc_mcam *mcam = &rvu->hw->mcam; + struct rvu_hwinfo *hw = rvu->hw; + int bank, op_rss; + + if (!is_mcam_entry_enabled(rvu, mcam, blkaddr, mcam_index)) + return; + + op_rss = (!hw->cap.nix_rx_multicast || !pfvf->use_mce_list); + + bank = npc_get_bank(mcam, mcam_index); + mcam_index &= (mcam->banksize - 1); + + /* If Rx action is MCAST update only RSS algorithm index */ + if (!op_rss) { + *(u64 *)&action = rvu_read64(rvu, blkaddr, + NPC_AF_MCAMEX_BANKX_ACTION(mcam_index, bank)); + + action.flow_key_alg = alg_idx; + } + rvu_write64(rvu, blkaddr, + NPC_AF_MCAMEX_BANKX_ACTION(mcam_index, bank), *(u64 *)&action); +} + void rvu_npc_update_flowkey_alg_idx(struct rvu *rvu, u16 pcifunc, int nixlf, int group, int alg_idx, int mcam_index) { struct npc_mcam *mcam = &rvu->hw->mcam; - struct rvu_hwinfo *hw = rvu->hw; struct nix_rx_action action; int blkaddr, index, bank; struct rvu_pfvf *pfvf; @@ -1044,15 +1082,16 @@ void rvu_npc_update_flowkey_alg_idx(struct rvu *rvu, u16 pcifunc, int nixlf, /* If PF's promiscuous entry is enabled, * Set RSS action for that entry as well */ - if ((!hw->cap.nix_rx_multicast || !pfvf->use_mce_list) && - is_mcam_entry_enabled(rvu, mcam, blkaddr, index)) { - bank = npc_get_bank(mcam, index); - index &= (mcam->banksize - 1); + npc_update_rx_action_with_alg_idx(rvu, action, pfvf, index, blkaddr, + alg_idx); - rvu_write64(rvu, blkaddr, - NPC_AF_MCAMEX_BANKX_ACTION(index, bank), - *(u64 *)&action); - } + index = npc_get_nixlf_mcam_index(mcam, pcifunc, + nixlf, NIXLF_ALLMULTI_ENTRY); + /* If PF's allmulti entry is enabled, + * Set RSS action for that entry as well + */ + npc_update_rx_action_with_alg_idx(rvu, action, pfvf, index, blkaddr, + alg_idx); } void npc_enadis_default_mce_entry(struct rvu *rvu, u16 pcifunc, diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.c index b3150f0532919..d46ac29adb966 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.c @@ -31,8 +31,8 @@ static struct hw_reg_map txsch_reg_map[NIX_TXSCH_LVL_CNT] = { {NIX_TXSCH_LVL_TL4, 3, 0xFFFF, {{0x0B00, 0x0B08}, {0x0B10, 0x0B18}, {0x1200, 0x12E0} } }, {NIX_TXSCH_LVL_TL3, 4, 0xFFFF, {{0x1000, 0x10E0}, {0x1600, 0x1608}, - {0x1610, 0x1618}, {0x1700, 0x17B0} } }, - {NIX_TXSCH_LVL_TL2, 2, 0xFFFF, {{0x0E00, 0x0EE0}, {0x1700, 0x17B0} } }, + {0x1610, 0x1618}, {0x1700, 0x17C8} } }, + {NIX_TXSCH_LVL_TL2, 2, 0xFFFF, {{0x0E00, 0x0EE0}, {0x1700, 0x17C8} } }, {NIX_TXSCH_LVL_TL1, 1, 0xFFFF, {{0x0C00, 0x0D98} } }, }; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h index b42e631e52d0f..18c1c9f361cc6 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h @@ -437,6 +437,7 @@ #define NIX_AF_LINKX_BASE_MASK GENMASK_ULL(11, 0) #define NIX_AF_LINKX_RANGE_MASK GENMASK_ULL(19, 16) +#define NIX_AF_LINKX_MCS_CNT_MASK GENMASK_ULL(33, 32) /* SSO */ #define SSO_AF_CONST (0x1000) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c index a4a258da8dd59..c1c99d7054f87 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c @@ -450,6 +450,9 @@ int cn10k_set_ipolicer_rate(struct otx2_nic *pfvf, u16 profile, aq->prof.pebs_mantissa = 0; aq->prof_mask.pebs_mantissa = 0xFF; + aq->prof.hl_en = 0; + aq->prof_mask.hl_en = 1; + /* Fill AQ info */ aq->qidx = profile; aq->ctype = NIX_AQ_CTYPE_BANDPROF; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h index e7c69b57147e0..06910307085ef 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h @@ -1070,6 +1070,8 @@ int otx2_init_tc(struct otx2_nic *nic); void otx2_shutdown_tc(struct otx2_nic *nic); int otx2_setup_tc(struct net_device *netdev, enum tc_setup_type type, void *type_data); +void otx2_tc_apply_ingress_police_rules(struct otx2_nic *nic); + /* CGX/RPM DMAC filters support */ int otx2_dmacflt_get_max_cnt(struct otx2_nic *pf); int otx2_dmacflt_add(struct otx2_nic *pf, const u8 *mac, u32 bit_pos); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c index bfddbff7bcdfb..28fb643d2917f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_dcbnl.c @@ -399,9 +399,10 @@ static int otx2_dcbnl_ieee_getpfc(struct net_device *dev, struct ieee_pfc *pfc) static int otx2_dcbnl_ieee_setpfc(struct net_device *dev, struct ieee_pfc *pfc) { struct otx2_nic *pfvf = netdev_priv(dev); + u8 old_pfc_en; int err; - /* Save PFC configuration to interface */ + old_pfc_en = pfvf->pfc_en; pfvf->pfc_en = pfc->pfc_en; if (pfvf->hw.tx_queues >= NIX_PF_PFC_PRIO_MAX) @@ -411,13 +412,17 @@ static int otx2_dcbnl_ieee_setpfc(struct net_device *dev, struct ieee_pfc *pfc) * supported by the tx queue configuration */ err = otx2_check_pfc_config(pfvf); - if (err) + if (err) { + pfvf->pfc_en = old_pfc_en; return err; + } process_pfc: err = otx2_config_priority_flow_ctrl(pfvf); - if (err) + if (err) { + pfvf->pfc_en = old_pfc_en; return err; + } /* Request Per channel Bpids */ if (pfc->pfc_en) @@ -425,6 +430,12 @@ static int otx2_dcbnl_ieee_setpfc(struct net_device *dev, struct ieee_pfc *pfc) err = otx2_pfc_txschq_update(pfvf); if (err) { + if (pfc->pfc_en) + otx2_nix_config_bp(pfvf, false); + + otx2_pfc_txschq_stop(pfvf); + pfvf->pfc_en = old_pfc_en; + otx2_config_priority_flow_ctrl(pfvf); dev_err(pfvf->dev, "%s failed to update TX schedulers\n", __func__); return err; } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c index 9efcec549834e..53f6258a973c2 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c @@ -334,9 +334,12 @@ static void otx2_get_pauseparam(struct net_device *netdev, if (is_otx2_lbkvf(pfvf->pdev)) return; + mutex_lock(&pfvf->mbox.lock); req = otx2_mbox_alloc_msg_cgx_cfg_pause_frm(&pfvf->mbox); - if (!req) + if (!req) { + mutex_unlock(&pfvf->mbox.lock); return; + } if (!otx2_sync_mbox_msg(&pfvf->mbox)) { rsp = (struct cgx_pause_frm_cfg *) @@ -344,6 +347,7 @@ static void otx2_get_pauseparam(struct net_device *netdev, pause->rx_pause = rsp->rx_pause; pause->tx_pause = rsp->tx_pause; } + mutex_unlock(&pfvf->mbox.lock); } static int otx2_set_pauseparam(struct net_device *netdev, diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c index 4762dbea64a12..97a71e9b85637 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c @@ -1088,6 +1088,7 @@ int otx2_add_flow(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc) struct ethhdr *eth_hdr; bool new = false; int err = 0; + u64 vf_num; u32 ring; if (!flow_cfg->max_flows) { @@ -1100,7 +1101,21 @@ int otx2_add_flow(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc) if (!(pfvf->flags & OTX2_FLAG_NTUPLE_SUPPORT)) return -ENOMEM; - if (ring >= pfvf->hw.rx_queues && fsp->ring_cookie != RX_CLS_FLOW_DISC) + /* Number of queues on a VF can be greater or less than + * the PF's queue. Hence no need to check for the + * queue count. Hence no need to check queue count if PF + * is installing for its VF. Below is the expected vf_num value + * based on the ethtool commands. + * + * e.g. + * 1. ethtool -U ... action -1 ==> vf_num:255 + * 2. ethtool -U ... action ==> vf_num:0 + * 3. ethtool -U ... vf queue ==> + * vf_num:vf_idx+1 + */ + vf_num = ethtool_get_flow_spec_ring_vf(fsp->ring_cookie); + if (!is_otx2_vf(pfvf->pcifunc) && !vf_num && + ring >= pfvf->hw.rx_queues && fsp->ring_cookie != RX_CLS_FLOW_DISC) return -EINVAL; if (fsp->location >= otx2_get_maxflows(flow_cfg)) @@ -1182,6 +1197,9 @@ int otx2_add_flow(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc) flow_cfg->nr_flows++; } + if (flow->is_vf) + netdev_info(pfvf->netdev, + "Make sure that VF's queue number is within its queue limit\n"); return 0; } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index 91b99fd703616..a57455aebff6f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -566,7 +566,9 @@ static irqreturn_t otx2_pfvf_mbox_intr_handler(int irq, void *pf_irq) otx2_write64(pf, RVU_PF_VFPF_MBOX_INTX(1), intr); otx2_queue_work(mbox, pf->mbox_pfvf_wq, 64, vfs, intr, TYPE_PFVF); - vfs -= 64; + if (intr) + trace_otx2_msg_interrupt(mbox->mbox.pdev, "VF(s) to PF", intr); + vfs = 64; } intr = otx2_read64(pf, RVU_PF_VFPF_MBOX_INTX(0)); @@ -574,7 +576,8 @@ static irqreturn_t otx2_pfvf_mbox_intr_handler(int irq, void *pf_irq) otx2_queue_work(mbox, pf->mbox_pfvf_wq, 0, vfs, intr, TYPE_PFVF); - trace_otx2_msg_interrupt(mbox->mbox.pdev, "VF(s) to PF", intr); + if (intr) + trace_otx2_msg_interrupt(mbox->mbox.pdev, "VF(s) to PF", intr); return IRQ_HANDLED; } @@ -1647,6 +1650,21 @@ static void otx2_free_hw_resources(struct otx2_nic *pf) mutex_unlock(&mbox->lock); } +static bool otx2_promisc_use_mce_list(struct otx2_nic *pfvf) +{ + int vf; + + /* The AF driver will determine whether to allow the VF netdev or not */ + if (is_otx2_vf(pfvf->pcifunc)) + return true; + + /* check if there are any trusted VFs associated with the PF netdev */ + for (vf = 0; vf < pci_num_vf(pfvf->pdev); vf++) + if (pfvf->vf_configs[vf].trusted) + return true; + return false; +} + static void otx2_do_set_rx_mode(struct otx2_nic *pf) { struct net_device *netdev = pf->netdev; @@ -1679,12 +1697,21 @@ static void otx2_do_set_rx_mode(struct otx2_nic *pf) if (netdev->flags & (IFF_ALLMULTI | IFF_MULTICAST)) req->mode |= NIX_RX_MODE_ALLMULTI; - req->mode |= NIX_RX_MODE_USE_MCE; + if (otx2_promisc_use_mce_list(pf)) + req->mode |= NIX_RX_MODE_USE_MCE; otx2_sync_mbox_msg(&pf->mbox); mutex_unlock(&pf->mbox.lock); } +static void otx2_set_irq_coalesce(struct otx2_nic *pfvf) +{ + int cint; + + for (cint = 0; cint < pfvf->hw.cint_cnt; cint++) + otx2_config_irq_coalescing(pfvf, cint); +} + static void otx2_dim_work(struct work_struct *w) { struct dim_cq_moder cur_moder; @@ -1700,6 +1727,7 @@ static void otx2_dim_work(struct work_struct *w) CQ_TIMER_THRESH_MAX : cur_moder.usec; pfvf->hw.cq_ecount_wait = (cur_moder.pkts > NAPI_POLL_WEIGHT) ? NAPI_POLL_WEIGHT : cur_moder.pkts; + otx2_set_irq_coalesce(pfvf); dim->state = DIM_START_MEASURE; } @@ -1870,6 +1898,8 @@ int otx2_open(struct net_device *netdev) if (pf->flags & OTX2_FLAG_DMACFLTR_SUPPORT) otx2_dmacflt_reinstall_flows(pf); + otx2_tc_apply_ingress_police_rules(pf); + err = otx2_rxtx_enable(pf, true); /* If a mbox communication error happens at this point then interface * will end up in a state such that it is in down state but hardware @@ -1934,6 +1964,8 @@ int otx2_stop(struct net_device *netdev) /* Clear RSS enable flag */ rss = &pf->hw.rss_info; rss->enable = false; + if (!netif_is_rxfh_configured(netdev)) + kfree(rss->rss_ctx[DEFAULT_RSS_CONTEXT_GROUP]); /* Cleanup Queue IRQ */ vec = pci_irq_vector(pf->pdev, @@ -2675,11 +2707,14 @@ static int otx2_ndo_set_vf_trust(struct net_device *netdev, int vf, pf->vf_configs[vf].trusted = enable; rc = otx2_set_vf_permissions(pf, vf, OTX2_TRUSTED_VF); - if (rc) + if (rc) { pf->vf_configs[vf].trusted = !enable; - else + } else { netdev_info(pf->netdev, "VF %d is %strusted\n", vf, enable ? "" : "not "); + otx2_set_rx_mode(netdev); + } + return rc; } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c index fab9d85bfb371..423ce54eaea69 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c @@ -45,6 +45,9 @@ struct otx2_tc_flow { bool is_act_police; u32 prio; struct npc_install_flow_req req; + u64 rate; + u32 burst; + bool is_pps; }; static void otx2_get_egress_burst_cfg(struct otx2_nic *nic, u32 burst, @@ -282,21 +285,10 @@ static int otx2_tc_egress_matchall_delete(struct otx2_nic *nic, return err; } -static int otx2_tc_act_set_police(struct otx2_nic *nic, - struct otx2_tc_flow *node, - struct flow_cls_offload *f, - u64 rate, u32 burst, u32 mark, - struct npc_install_flow_req *req, bool pps) +static int otx2_tc_act_set_hw_police(struct otx2_nic *nic, + struct otx2_tc_flow *node) { - struct netlink_ext_ack *extack = f->common.extack; - struct otx2_hw *hw = &nic->hw; - int rq_idx, rc; - - rq_idx = find_first_zero_bit(&nic->rq_bmap, hw->rx_queues); - if (rq_idx >= hw->rx_queues) { - NL_SET_ERR_MSG_MOD(extack, "Police action rules exceeded"); - return -EINVAL; - } + int rc; mutex_lock(&nic->mbox.lock); @@ -306,23 +298,17 @@ static int otx2_tc_act_set_police(struct otx2_nic *nic, return rc; } - rc = cn10k_set_ipolicer_rate(nic, node->leaf_profile, burst, rate, pps); + rc = cn10k_set_ipolicer_rate(nic, node->leaf_profile, + node->burst, node->rate, node->is_pps); if (rc) goto free_leaf; - rc = cn10k_map_unmap_rq_policer(nic, rq_idx, node->leaf_profile, true); + rc = cn10k_map_unmap_rq_policer(nic, node->rq, node->leaf_profile, true); if (rc) goto free_leaf; mutex_unlock(&nic->mbox.lock); - req->match_id = mark & 0xFFFFULL; - req->index = rq_idx; - req->op = NIX_RX_ACTIONOP_UCAST; - set_bit(rq_idx, &nic->rq_bmap); - node->is_act_police = true; - node->rq = rq_idx; - return 0; free_leaf: @@ -334,6 +320,39 @@ static int otx2_tc_act_set_police(struct otx2_nic *nic, return rc; } +static int otx2_tc_act_set_police(struct otx2_nic *nic, + struct otx2_tc_flow *node, + struct flow_cls_offload *f, + u64 rate, u32 burst, u32 mark, + struct npc_install_flow_req *req, bool pps) +{ + struct netlink_ext_ack *extack = f->common.extack; + struct otx2_hw *hw = &nic->hw; + int rq_idx, rc; + + rq_idx = find_first_zero_bit(&nic->rq_bmap, hw->rx_queues); + if (rq_idx >= hw->rx_queues) { + NL_SET_ERR_MSG_MOD(extack, "Police action rules exceeded"); + return -EINVAL; + } + + req->match_id = mark & 0xFFFFULL; + req->index = rq_idx; + req->op = NIX_RX_ACTIONOP_UCAST; + + node->is_act_police = true; + node->rq = rq_idx; + node->burst = burst; + node->rate = rate; + node->is_pps = pps; + + rc = otx2_tc_act_set_hw_police(nic, node); + if (!rc) + set_bit(rq_idx, &nic->rq_bmap); + + return rc; +} + static int otx2_tc_parse_actions(struct otx2_nic *nic, struct flow_action *flow_action, struct npc_install_flow_req *req, @@ -986,6 +1005,11 @@ static int otx2_tc_del_flow(struct otx2_nic *nic, } if (flow_node->is_act_police) { + __clear_bit(flow_node->rq, &nic->rq_bmap); + + if (nic->flags & OTX2_FLAG_INTF_DOWN) + goto free_mcam_flow; + mutex_lock(&nic->mbox.lock); err = cn10k_map_unmap_rq_policer(nic, flow_node->rq, @@ -1001,11 +1025,10 @@ static int otx2_tc_del_flow(struct otx2_nic *nic, "Unable to free leaf bandwidth profile(%d)\n", flow_node->leaf_profile); - __clear_bit(flow_node->rq, &nic->rq_bmap); - mutex_unlock(&nic->mbox.lock); } +free_mcam_flow: otx2_del_mcam_flow_entry(nic, flow_node->entry, NULL); otx2_tc_update_mcam_table(nic, flow_cfg, flow_node, false); kfree_rcu(flow_node, rcu); @@ -1025,6 +1048,11 @@ static int otx2_tc_add_flow(struct otx2_nic *nic, if (!(nic->flags & OTX2_FLAG_TC_FLOWER_SUPPORT)) return -ENOMEM; + if (nic->flags & OTX2_FLAG_INTF_DOWN) { + NL_SET_ERR_MSG_MOD(extack, "Interface not initialized"); + return -EINVAL; + } + if (flow_cfg->nr_flows == flow_cfg->max_flows) { NL_SET_ERR_MSG_MOD(extack, "Free MCAM entry not available to add the flow"); @@ -1384,3 +1412,45 @@ void otx2_shutdown_tc(struct otx2_nic *nic) otx2_destroy_tc_flow_list(nic); } EXPORT_SYMBOL(otx2_shutdown_tc); + +static void otx2_tc_config_ingress_rule(struct otx2_nic *nic, + struct otx2_tc_flow *node) +{ + struct npc_install_flow_req *req; + + if (otx2_tc_act_set_hw_police(nic, node)) + return; + + mutex_lock(&nic->mbox.lock); + + req = otx2_mbox_alloc_msg_npc_install_flow(&nic->mbox); + if (!req) + goto err; + + memcpy(req, &node->req, sizeof(struct npc_install_flow_req)); + + if (otx2_sync_mbox_msg(&nic->mbox)) + netdev_err(nic->netdev, + "Failed to install MCAM flow entry for ingress rule"); +err: + mutex_unlock(&nic->mbox.lock); +} + +void otx2_tc_apply_ingress_police_rules(struct otx2_nic *nic) +{ + struct otx2_flow_config *flow_cfg = nic->flow_cfg; + struct otx2_tc_flow *node; + + /* If any ingress policer rules exist for the interface then + * apply those rules. Ingress policer rules depend on bandwidth + * profiles linked to the receive queues. Since no receive queues + * exist when interface is down, ingress policer rules are stored + * and configured in hardware after all receive queues are allocated + * in otx2_open. + */ + list_for_each_entry(node, &flow_cfg->flow_list_tc, list) { + if (node->is_act_police) + otx2_tc_config_ingress_rule(nic, node); + } +} +EXPORT_SYMBOL(otx2_tc_apply_ingress_police_rules); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c index 6ee15f3c25ede..4d519ea833b2c 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c @@ -512,11 +512,18 @@ static void otx2_adjust_adaptive_coalese(struct otx2_nic *pfvf, struct otx2_cq_p { struct dim_sample dim_sample; u64 rx_frames, rx_bytes; + u64 tx_frames, tx_bytes; rx_frames = OTX2_GET_RX_STATS(RX_BCAST) + OTX2_GET_RX_STATS(RX_MCAST) + OTX2_GET_RX_STATS(RX_UCAST); rx_bytes = OTX2_GET_RX_STATS(RX_OCTS); - dim_update_sample(pfvf->napi_events, rx_frames, rx_bytes, &dim_sample); + tx_bytes = OTX2_GET_TX_STATS(TX_OCTS); + tx_frames = OTX2_GET_TX_STATS(TX_UCAST); + + dim_update_sample(pfvf->napi_events, + rx_frames + tx_frames, + rx_bytes + tx_bytes, + &dim_sample); net_dim(&cq_poll->dim, dim_sample); } @@ -558,16 +565,9 @@ int otx2_napi_handler(struct napi_struct *napi, int budget) if (pfvf->flags & OTX2_FLAG_INTF_DOWN) return workdone; - /* Check for adaptive interrupt coalesce */ - if (workdone != 0 && - ((pfvf->flags & OTX2_FLAG_ADPTV_INT_COAL_ENABLED) == - OTX2_FLAG_ADPTV_INT_COAL_ENABLED)) { - /* Adjust irq coalese using net_dim */ + /* Adjust irq coalese using net_dim */ + if (pfvf->flags & OTX2_FLAG_ADPTV_INT_COAL_ENABLED) otx2_adjust_adaptive_coalese(pfvf, cq_poll); - /* Update irq coalescing */ - for (i = 0; i < pfvf->hw.cint_cnt; i++) - otx2_config_irq_coalescing(pfvf, i); - } if (unlikely(!filled_cnt)) { struct refill_work *work; diff --git a/drivers/net/ethernet/mediatek/mtk_wed_wo.c b/drivers/net/ethernet/mediatek/mtk_wed_wo.c index 3bd51a3d66500..ae44ad5f8ce8a 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed_wo.c +++ b/drivers/net/ethernet/mediatek/mtk_wed_wo.c @@ -291,6 +291,9 @@ mtk_wed_wo_queue_tx_clean(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q) for (i = 0; i < q->n_desc; i++) { struct mtk_wed_wo_queue_entry *entry = &q->entry[i]; + if (!entry->buf) + continue; + dma_unmap_single(wo->hw->dev, entry->addr, entry->len, DMA_TO_DEVICE); skb_free_frag(entry->buf); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index c22b0ad0c8701..7013e1c8741a3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -156,15 +156,18 @@ static u8 alloc_token(struct mlx5_cmd *cmd) return token; } -static int cmd_alloc_index(struct mlx5_cmd *cmd) +static int cmd_alloc_index(struct mlx5_cmd *cmd, struct mlx5_cmd_work_ent *ent) { unsigned long flags; int ret; spin_lock_irqsave(&cmd->alloc_lock, flags); ret = find_first_bit(&cmd->vars.bitmask, cmd->vars.max_reg_cmds); - if (ret < cmd->vars.max_reg_cmds) + if (ret < cmd->vars.max_reg_cmds) { clear_bit(ret, &cmd->vars.bitmask); + ent->idx = ret; + cmd->ent_arr[ent->idx] = ent; + } spin_unlock_irqrestore(&cmd->alloc_lock, flags); return ret < cmd->vars.max_reg_cmds ? ret : -ENOMEM; @@ -977,7 +980,7 @@ static void cmd_work_handler(struct work_struct *work) sem = ent->page_queue ? &cmd->vars.pages_sem : &cmd->vars.sem; down(sem); if (!ent->page_queue) { - alloc_ret = cmd_alloc_index(cmd); + alloc_ret = cmd_alloc_index(cmd, ent); if (alloc_ret < 0) { mlx5_core_err_rl(dev, "failed to allocate command entry\n"); if (ent->callback) { @@ -992,15 +995,14 @@ static void cmd_work_handler(struct work_struct *work) up(sem); return; } - ent->idx = alloc_ret; } else { ent->idx = cmd->vars.max_reg_cmds; spin_lock_irqsave(&cmd->alloc_lock, flags); clear_bit(ent->idx, &cmd->vars.bitmask); + cmd->ent_arr[ent->idx] = ent; spin_unlock_irqrestore(&cmd->alloc_lock, flags); } - cmd->ent_arr[ent->idx] = ent; lay = get_inst(cmd, ent->idx); ent->lay = lay; memset(lay, 0, sizeof(*lay)); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c index ad789349c06e6..85d3bfa0780c6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -718,7 +718,7 @@ static void mlx5_fw_tracer_handle_traces(struct work_struct *work) while (block_timestamp > tracer->last_timestamp) { /* Check block override if it's not the first block */ - if (!tracer->last_timestamp) { + if (tracer->last_timestamp) { u64 *ts_event; /* To avoid block override be the HW in case of buffer * wraparound, the time stamp of the previous block diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 86f2690c5e015..20a6bc1a234f4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -818,6 +818,7 @@ enum { MLX5E_STATE_DESTROYING, MLX5E_STATE_XDP_TX_ENABLED, MLX5E_STATE_XDP_ACTIVE, + MLX5E_STATE_CHANNELS_ACTIVE, }; struct mlx5e_modify_sq_param { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c b/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c index be83ad9db82a4..e1283531e0b81 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c @@ -154,6 +154,7 @@ static int fs_udp_create_groups(struct mlx5e_flow_table *ft, enum fs_udp_type ty in = kvzalloc(inlen, GFP_KERNEL); if (!in || !ft->g) { kfree(ft->g); + ft->g = NULL; kvfree(in); return -ENOMEM; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c index bb11e644d24f7..af3928eddafd1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c @@ -177,6 +177,8 @@ static void mlx5e_ptpsq_mark_ts_cqes_undelivered(struct mlx5e_ptpsq *ptpsq, static void mlx5e_ptp_handle_ts_cqe(struct mlx5e_ptpsq *ptpsq, struct mlx5_cqe64 *cqe, + u8 *md_buff, + u8 *md_buff_sz, int budget) { struct mlx5e_ptp_port_ts_cqe_list *pending_cqe_list = ptpsq->ts_cqe_pending_list; @@ -211,19 +213,24 @@ static void mlx5e_ptp_handle_ts_cqe(struct mlx5e_ptpsq *ptpsq, mlx5e_ptpsq_mark_ts_cqes_undelivered(ptpsq, hwtstamp); out: napi_consume_skb(skb, budget); - mlx5e_ptp_metadata_fifo_push(&ptpsq->metadata_freelist, metadata_id); + md_buff[*md_buff_sz++] = metadata_id; if (unlikely(mlx5e_ptp_metadata_map_unhealthy(&ptpsq->metadata_map)) && !test_and_set_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state)) queue_work(ptpsq->txqsq.priv->wq, &ptpsq->report_unhealthy_work); } -static bool mlx5e_ptp_poll_ts_cq(struct mlx5e_cq *cq, int budget) +static bool mlx5e_ptp_poll_ts_cq(struct mlx5e_cq *cq, int napi_budget) { struct mlx5e_ptpsq *ptpsq = container_of(cq, struct mlx5e_ptpsq, ts_cq); - struct mlx5_cqwq *cqwq = &cq->wq; + int budget = min(napi_budget, MLX5E_TX_CQ_POLL_BUDGET); + u8 metadata_buff[MLX5E_TX_CQ_POLL_BUDGET]; + u8 metadata_buff_sz = 0; + struct mlx5_cqwq *cqwq; struct mlx5_cqe64 *cqe; int work_done = 0; + cqwq = &cq->wq; + if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &ptpsq->txqsq.state))) return false; @@ -234,7 +241,8 @@ static bool mlx5e_ptp_poll_ts_cq(struct mlx5e_cq *cq, int budget) do { mlx5_cqwq_pop(cqwq); - mlx5e_ptp_handle_ts_cqe(ptpsq, cqe, budget); + mlx5e_ptp_handle_ts_cqe(ptpsq, cqe, + metadata_buff, &metadata_buff_sz, napi_budget); } while ((++work_done < budget) && (cqe = mlx5_cqwq_get_cqe(cqwq))); mlx5_cqwq_update_db_record(cqwq); @@ -242,6 +250,10 @@ static bool mlx5e_ptp_poll_ts_cq(struct mlx5e_cq *cq, int budget) /* ensure cq space is freed before enabling more cqes */ wmb(); + while (metadata_buff_sz > 0) + mlx5e_ptp_metadata_fifo_push(&ptpsq->metadata_freelist, + metadata_buff[--metadata_buff_sz]); + mlx5e_txqsq_wake(&ptpsq->txqsq); return work_done == budget; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c index e8eea9ffd5eb6..03b119a434bc9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c @@ -702,11 +702,11 @@ static int mlx5e_rx_reporter_dump(struct devlink_health_reporter *reporter, void mlx5e_reporter_rx_timeout(struct mlx5e_rq *rq) { - char icosq_str[MLX5E_REPORTER_PER_Q_MAX_LEN] = {}; char err_str[MLX5E_REPORTER_PER_Q_MAX_LEN]; struct mlx5e_icosq *icosq = rq->icosq; struct mlx5e_priv *priv = rq->priv; struct mlx5e_err_ctx err_ctx = {}; + char icosq_str[32] = {}; err_ctx.ctx = rq; err_ctx.recover = mlx5e_rx_reporter_timeout_recover; @@ -715,7 +715,7 @@ void mlx5e_reporter_rx_timeout(struct mlx5e_rq *rq) if (icosq) snprintf(icosq_str, sizeof(icosq_str), "ICOSQ: 0x%x, ", icosq->sqn); snprintf(err_str, sizeof(err_str), - "RX timeout on channel: %d, %sRQ: 0x%x, CQ: 0x%x", + "RX timeout on channel: %d, %s RQ: 0x%x, CQ: 0x%x", rq->ix, icosq_str, rq->rqn, rq->cq.mcq.cqn); mlx5e_health_report(priv, priv->rx_reporter, err_str, &err_ctx); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c index f63402c480280..1b418095b79a3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c @@ -197,7 +197,7 @@ parse_mirred_encap(struct mlx5e_tc_act_parse_state *parse_state, } esw_attr->dests[esw_attr->out_count].flags |= MLX5_ESW_DEST_ENCAP; esw_attr->out_count++; - /* attr->dests[].rep is resolved when we handle encap */ + /* attr->dests[].vport is resolved when we handle encap */ return 0; } @@ -270,7 +270,8 @@ parse_mirred(struct mlx5e_tc_act_parse_state *parse_state, out_priv = netdev_priv(out_dev); rpriv = out_priv->ppriv; - esw_attr->dests[esw_attr->out_count].rep = rpriv->rep; + esw_attr->dests[esw_attr->out_count].vport_valid = true; + esw_attr->dests[esw_attr->out_count].vport = rpriv->rep->vport; esw_attr->dests[esw_attr->out_count].mdev = out_priv->mdev; esw_attr->out_count++; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c index 4e923a2874aef..86bf007fd05b7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c @@ -83,6 +83,9 @@ mlx5e_tc_post_act_offload(struct mlx5e_post_act *post_act, struct mlx5_flow_spec *spec; int err; + if (IS_ERR(post_act)) + return PTR_ERR(post_act); + spec = kvzalloc(sizeof(*spec), GFP_KERNEL); if (!spec) return -ENOMEM; @@ -111,6 +114,9 @@ mlx5e_tc_post_act_add(struct mlx5e_post_act *post_act, struct mlx5_flow_attr *po struct mlx5e_post_act_handle *handle; int err; + if (IS_ERR(post_act)) + return ERR_CAST(post_act); + handle = kzalloc(sizeof(*handle), GFP_KERNEL); if (!handle) return ERR_PTR(-ENOMEM); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c index b10e40e1a9c14..f1d1e1542e81b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c @@ -1064,7 +1064,8 @@ int mlx5e_tc_tun_encap_dests_set(struct mlx5e_priv *priv, out_priv = netdev_priv(encap_dev); rpriv = out_priv->ppriv; - esw_attr->dests[out_index].rep = rpriv->rep; + esw_attr->dests[out_index].vport_valid = true; + esw_attr->dests[out_index].vport = rpriv->rep->vport; esw_attr->dests[out_index].mdev = out_priv->mdev; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index 8bed17d8fe564..b723ff5e5249c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -493,6 +493,7 @@ mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd, dma_addr_t dma_addr = xdptxd->dma_addr; u32 dma_len = xdptxd->len; u16 ds_cnt, inline_hdr_sz; + unsigned int frags_size; u8 num_wqebbs = 1; int num_frags = 0; bool inline_ok; @@ -503,8 +504,9 @@ mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd, inline_ok = sq->min_inline_mode == MLX5_INLINE_MODE_NONE || dma_len >= MLX5E_XDP_MIN_INLINE; + frags_size = xdptxd->has_frags ? xdptxdf->sinfo->xdp_frags_size : 0; - if (unlikely(!inline_ok || sq->hw_mtu < dma_len)) { + if (unlikely(!inline_ok || sq->hw_mtu < dma_len + frags_size)) { stats->err++; return false; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c index 7d4ceb9b9c16f..5834e47e72d82 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c @@ -121,7 +121,14 @@ static bool mlx5e_ipsec_update_esn_state(struct mlx5e_ipsec_sa_entry *sa_entry) if (x->xso.type == XFRM_DEV_OFFLOAD_CRYPTO) esn_msb = xfrm_replay_seqhi(x, htonl(seq_bottom)); - sa_entry->esn_state.esn = esn; + if (sa_entry->esn_state.esn_msb) + sa_entry->esn_state.esn = esn; + else + /* According to RFC4303, section "3.3.3. Sequence Number Generation", + * the first packet sent using a given SA will contain a sequence + * number of 1. + */ + sa_entry->esn_state.esn = max_t(u32, esn, 1); sa_entry->esn_state.esn_msb = esn_msb; if (unlikely(overlap && seq_bottom < MLX5E_IPSEC_ESN_SCOPE_MID)) { @@ -335,6 +342,27 @@ void mlx5e_ipsec_build_accel_xfrm_attrs(struct mlx5e_ipsec_sa_entry *sa_entry, attrs->replay_esn.esn = sa_entry->esn_state.esn; attrs->replay_esn.esn_msb = sa_entry->esn_state.esn_msb; attrs->replay_esn.overlap = sa_entry->esn_state.overlap; + switch (x->replay_esn->replay_window) { + case 32: + attrs->replay_esn.replay_window = + MLX5_IPSEC_ASO_REPLAY_WIN_32BIT; + break; + case 64: + attrs->replay_esn.replay_window = + MLX5_IPSEC_ASO_REPLAY_WIN_64BIT; + break; + case 128: + attrs->replay_esn.replay_window = + MLX5_IPSEC_ASO_REPLAY_WIN_128BIT; + break; + case 256: + attrs->replay_esn.replay_window = + MLX5_IPSEC_ASO_REPLAY_WIN_256BIT; + break; + default: + WARN_ON(true); + return; + } } attrs->dir = x->xso.dir; @@ -901,9 +929,11 @@ void mlx5e_ipsec_cleanup(struct mlx5e_priv *priv) return; mlx5e_accel_ipsec_fs_cleanup(ipsec); - if (mlx5_ipsec_device_caps(priv->mdev) & MLX5_IPSEC_CAP_TUNNEL) + if (ipsec->netevent_nb.notifier_call) { unregister_netevent_notifier(&ipsec->netevent_nb); - if (mlx5_ipsec_device_caps(priv->mdev) & MLX5_IPSEC_CAP_PACKET_OFFLOAD) + ipsec->netevent_nb.notifier_call = NULL; + } + if (ipsec->aso) mlx5e_ipsec_aso_cleanup(ipsec); destroy_workqueue(ipsec->wq); kfree(ipsec); @@ -1012,6 +1042,12 @@ static int mlx5e_xfrm_validate_policy(struct mlx5_core_dev *mdev, } } + if (x->xdo.type == XFRM_DEV_OFFLOAD_PACKET && + !(mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_PACKET_OFFLOAD)) { + NL_SET_ERR_MSG_MOD(extack, "Packet offload is not supported"); + return -EINVAL; + } + return 0; } @@ -1107,14 +1143,6 @@ static const struct xfrmdev_ops mlx5e_ipsec_xfrmdev_ops = { .xdo_dev_state_free = mlx5e_xfrm_free_state, .xdo_dev_offload_ok = mlx5e_ipsec_offload_ok, .xdo_dev_state_advance_esn = mlx5e_xfrm_advance_esn_state, -}; - -static const struct xfrmdev_ops mlx5e_ipsec_packet_xfrmdev_ops = { - .xdo_dev_state_add = mlx5e_xfrm_add_state, - .xdo_dev_state_delete = mlx5e_xfrm_del_state, - .xdo_dev_state_free = mlx5e_xfrm_free_state, - .xdo_dev_offload_ok = mlx5e_ipsec_offload_ok, - .xdo_dev_state_advance_esn = mlx5e_xfrm_advance_esn_state, .xdo_dev_state_update_curlft = mlx5e_xfrm_update_curlft, .xdo_dev_policy_add = mlx5e_xfrm_add_policy, @@ -1132,11 +1160,7 @@ void mlx5e_ipsec_build_netdev(struct mlx5e_priv *priv) mlx5_core_info(mdev, "mlx5e: IPSec ESP acceleration enabled\n"); - if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_PACKET_OFFLOAD) - netdev->xfrmdev_ops = &mlx5e_ipsec_packet_xfrmdev_ops; - else - netdev->xfrmdev_ops = &mlx5e_ipsec_xfrmdev_ops; - + netdev->xfrmdev_ops = &mlx5e_ipsec_xfrmdev_ops; netdev->features |= NETIF_F_HW_ESP; netdev->hw_enc_features |= NETIF_F_HW_ESP; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c index 7dba4221993f0..81e6aa6434cf2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c @@ -128,63 +128,166 @@ static struct mlx5_flow_table *ipsec_ft_create(struct mlx5_flow_namespace *ns, return mlx5_create_auto_grouped_flow_table(ns, &ft_attr); } -static int ipsec_status_rule(struct mlx5_core_dev *mdev, - struct mlx5e_ipsec_rx *rx, - struct mlx5_flow_destination *dest) +static void ipsec_rx_status_drop_destroy(struct mlx5e_ipsec *ipsec, + struct mlx5e_ipsec_rx *rx) { - u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {}; + mlx5_del_flow_rules(rx->status_drop.rule); + mlx5_destroy_flow_group(rx->status_drop.group); + mlx5_fc_destroy(ipsec->mdev, rx->status_drop_cnt); +} + +static void ipsec_rx_status_pass_destroy(struct mlx5e_ipsec *ipsec, + struct mlx5e_ipsec_rx *rx) +{ + mlx5_del_flow_rules(rx->status.rule); + + if (rx != ipsec->rx_esw) + return; + +#ifdef CONFIG_MLX5_ESWITCH + mlx5_chains_put_table(esw_chains(ipsec->mdev->priv.eswitch), 0, 1, 0); +#endif +} + +static int ipsec_rx_status_drop_create(struct mlx5e_ipsec *ipsec, + struct mlx5e_ipsec_rx *rx) +{ + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + struct mlx5_flow_table *ft = rx->ft.status; + struct mlx5_core_dev *mdev = ipsec->mdev; + struct mlx5_flow_destination dest = {}; struct mlx5_flow_act flow_act = {}; - struct mlx5_modify_hdr *modify_hdr; - struct mlx5_flow_handle *fte; + struct mlx5_flow_handle *rule; + struct mlx5_fc *flow_counter; struct mlx5_flow_spec *spec; - int err; + struct mlx5_flow_group *g; + u32 *flow_group_in; + int err = 0; + flow_group_in = kvzalloc(inlen, GFP_KERNEL); spec = kvzalloc(sizeof(*spec), GFP_KERNEL); - if (!spec) - return -ENOMEM; + if (!flow_group_in || !spec) { + err = -ENOMEM; + goto err_out; + } - /* Action to copy 7 bit ipsec_syndrome to regB[24:30] */ - MLX5_SET(copy_action_in, action, action_type, MLX5_ACTION_TYPE_COPY); - MLX5_SET(copy_action_in, action, src_field, MLX5_ACTION_IN_FIELD_IPSEC_SYNDROME); - MLX5_SET(copy_action_in, action, src_offset, 0); - MLX5_SET(copy_action_in, action, length, 7); - MLX5_SET(copy_action_in, action, dst_field, MLX5_ACTION_IN_FIELD_METADATA_REG_B); - MLX5_SET(copy_action_in, action, dst_offset, 24); + MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ft->max_fte - 1); + MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, ft->max_fte - 1); + g = mlx5_create_flow_group(ft, flow_group_in); + if (IS_ERR(g)) { + err = PTR_ERR(g); + mlx5_core_err(mdev, + "Failed to add ipsec rx status drop flow group, err=%d\n", err); + goto err_out; + } - modify_hdr = mlx5_modify_header_alloc(mdev, MLX5_FLOW_NAMESPACE_KERNEL, - 1, action); + flow_counter = mlx5_fc_create(mdev, false); + if (IS_ERR(flow_counter)) { + err = PTR_ERR(flow_counter); + mlx5_core_err(mdev, + "Failed to add ipsec rx status drop rule counter, err=%d\n", err); + goto err_cnt; + } - if (IS_ERR(modify_hdr)) { - err = PTR_ERR(modify_hdr); + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT; + dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; + dest.counter_id = mlx5_fc_id(flow_counter); + if (rx == ipsec->rx_esw) + spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK; + rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1); + if (IS_ERR(rule)) { + err = PTR_ERR(rule); mlx5_core_err(mdev, - "fail to alloc ipsec copy modify_header_id err=%d\n", err); - goto out_spec; + "Failed to add ipsec rx status drop rule, err=%d\n", err); + goto err_rule; } - /* create fte */ - flow_act.action = MLX5_FLOW_CONTEXT_ACTION_MOD_HDR | - MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | + rx->status_drop.group = g; + rx->status_drop.rule = rule; + rx->status_drop_cnt = flow_counter; + + kvfree(flow_group_in); + kvfree(spec); + return 0; + +err_rule: + mlx5_fc_destroy(mdev, flow_counter); +err_cnt: + mlx5_destroy_flow_group(g); +err_out: + kvfree(flow_group_in); + kvfree(spec); + return err; +} + +static int ipsec_rx_status_pass_create(struct mlx5e_ipsec *ipsec, + struct mlx5e_ipsec_rx *rx, + struct mlx5_flow_destination *dest) +{ + struct mlx5_flow_act flow_act = {}; + struct mlx5_flow_handle *rule; + struct mlx5_flow_spec *spec; + int err; + + spec = kvzalloc(sizeof(*spec), GFP_KERNEL); + if (!spec) + return -ENOMEM; + + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, + misc_parameters_2.ipsec_syndrome); + MLX5_SET(fte_match_param, spec->match_value, + misc_parameters_2.ipsec_syndrome, 0); + if (rx == ipsec->rx_esw) + spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK; + spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2; + flow_act.flags = FLOW_ACT_NO_APPEND; + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_COUNT; - flow_act.modify_hdr = modify_hdr; - fte = mlx5_add_flow_rules(rx->ft.status, spec, &flow_act, dest, 2); - if (IS_ERR(fte)) { - err = PTR_ERR(fte); - mlx5_core_err(mdev, "fail to add ipsec rx err copy rule err=%d\n", err); - goto out; + rule = mlx5_add_flow_rules(rx->ft.status, spec, &flow_act, dest, 2); + if (IS_ERR(rule)) { + err = PTR_ERR(rule); + mlx5_core_warn(ipsec->mdev, + "Failed to add ipsec rx status pass rule, err=%d\n", err); + goto err_rule; } + rx->status.rule = rule; kvfree(spec); - rx->status.rule = fte; - rx->status.modify_hdr = modify_hdr; return 0; -out: - mlx5_modify_header_dealloc(mdev, modify_hdr); -out_spec: +err_rule: kvfree(spec); return err; } +static void mlx5_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec, + struct mlx5e_ipsec_rx *rx) +{ + ipsec_rx_status_pass_destroy(ipsec, rx); + ipsec_rx_status_drop_destroy(ipsec, rx); +} + +static int mlx5_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec, + struct mlx5e_ipsec_rx *rx, + struct mlx5_flow_destination *dest) +{ + int err; + + err = ipsec_rx_status_drop_create(ipsec, rx); + if (err) + return err; + + err = ipsec_rx_status_pass_create(ipsec, rx, dest); + if (err) + goto err_pass_create; + + return 0; + +err_pass_create: + ipsec_rx_status_drop_destroy(ipsec, rx); + return err; +} + static int ipsec_miss_create(struct mlx5_core_dev *mdev, struct mlx5_flow_table *ft, struct mlx5e_ipsec_miss *miss, @@ -256,12 +359,7 @@ static void rx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec, mlx5_destroy_flow_table(rx->ft.sa); if (rx->allow_tunnel_mode) mlx5_eswitch_unblock_encap(mdev); - if (rx == ipsec->rx_esw) { - mlx5_esw_ipsec_rx_status_destroy(ipsec, rx); - } else { - mlx5_del_flow_rules(rx->status.rule); - mlx5_modify_header_dealloc(mdev, rx->status.modify_hdr); - } + mlx5_ipsec_rx_status_destroy(ipsec, rx); mlx5_destroy_flow_table(rx->ft.status); mlx5_ipsec_fs_roce_rx_destroy(ipsec->roce, family); @@ -351,10 +449,7 @@ static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec, dest[1].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; dest[1].counter_id = mlx5_fc_id(rx->fc->cnt); - if (rx == ipsec->rx_esw) - err = mlx5_esw_ipsec_rx_status_create(ipsec, rx, dest); - else - err = ipsec_status_rule(mdev, rx, dest); + err = mlx5_ipsec_rx_status_create(ipsec, rx, dest); if (err) goto err_add; @@ -879,13 +974,22 @@ static void setup_fte_esp(struct mlx5_flow_spec *spec) MLX5_SET(fte_match_param, spec->match_value, outer_headers.ip_protocol, IPPROTO_ESP); } -static void setup_fte_spi(struct mlx5_flow_spec *spec, u32 spi) +static void setup_fte_spi(struct mlx5_flow_spec *spec, u32 spi, bool encap) { /* SPI number */ spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS; - MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters.outer_esp_spi); - MLX5_SET(fte_match_param, spec->match_value, misc_parameters.outer_esp_spi, spi); + if (encap) { + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, + misc_parameters.inner_esp_spi); + MLX5_SET(fte_match_param, spec->match_value, + misc_parameters.inner_esp_spi, spi); + } else { + MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, + misc_parameters.outer_esp_spi); + MLX5_SET(fte_match_param, spec->match_value, + misc_parameters.outer_esp_spi, spi); + } } static void setup_fte_no_frags(struct mlx5_flow_spec *spec) @@ -1244,8 +1348,9 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry) else setup_fte_addr6(spec, attrs->saddr.a6, attrs->daddr.a6); - setup_fte_spi(spec, attrs->spi); - setup_fte_esp(spec); + setup_fte_spi(spec, attrs->spi, attrs->encap); + if (!attrs->encap) + setup_fte_esp(spec); setup_fte_no_frags(spec); setup_fte_upper_proto_match(spec, &attrs->upspec); @@ -1348,7 +1453,7 @@ static int tx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry) switch (attrs->type) { case XFRM_DEV_OFFLOAD_CRYPTO: - setup_fte_spi(spec, attrs->spi); + setup_fte_spi(spec, attrs->spi, false); setup_fte_esp(spec); setup_fte_reg_a(spec); break; @@ -1729,8 +1834,11 @@ static int mlx5e_ipsec_block_tc_offload(struct mlx5_core_dev *mdev) struct mlx5_eswitch *esw = mdev->priv.eswitch; int err = 0; - if (esw) - down_write(&esw->mode_lock); + if (esw) { + err = mlx5_esw_lock(esw); + if (err) + return err; + } if (mdev->num_block_ipsec) { err = -EBUSY; @@ -1741,7 +1849,7 @@ static int mlx5e_ipsec_block_tc_offload(struct mlx5_core_dev *mdev) unlock: if (esw) - up_write(&esw->mode_lock); + mlx5_esw_unlock(esw); return err; } @@ -1758,7 +1866,7 @@ static int mlx5e_ipsec_block_tc_offload(struct mlx5_core_dev *mdev) static void mlx5e_ipsec_unblock_tc_offload(struct mlx5_core_dev *mdev) { - mdev->num_block_tc++; + mdev->num_block_tc--; } int mlx5e_accel_ipsec_fs_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c index 3245d1c9d5392..ce29e31721208 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c @@ -5,6 +5,8 @@ #include "en.h" #include "ipsec.h" #include "lib/crypto.h" +#include "fs_core.h" +#include "eswitch.h" enum { MLX5_IPSEC_ASO_REMOVE_FLOW_PKT_CNT_OFFSET, @@ -37,7 +39,10 @@ u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev) MLX5_CAP_ETH(mdev, insert_trailer) && MLX5_CAP_ETH(mdev, swp)) caps |= MLX5_IPSEC_CAP_CRYPTO; - if (MLX5_CAP_IPSEC(mdev, ipsec_full_offload)) { + if (MLX5_CAP_IPSEC(mdev, ipsec_full_offload) && + (mdev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_DMFS || + (mdev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_SMFS && + is_mdev_legacy_mode(mdev)))) { if (MLX5_CAP_FLOWTABLE_NIC_TX(mdev, reformat_add_esp_trasport) && MLX5_CAP_FLOWTABLE_NIC_RX(mdev, @@ -94,7 +99,7 @@ static void mlx5e_ipsec_packet_setup(void *obj, u32 pdn, if (attrs->dir == XFRM_DEV_OFFLOAD_IN) { MLX5_SET(ipsec_aso, aso_ctx, window_sz, - attrs->replay_esn.replay_window / 64); + attrs->replay_esn.replay_window); MLX5_SET(ipsec_aso, aso_ctx, mode, MLX5_IPSEC_ASO_REPLAY_PROTECTION); } @@ -558,6 +563,7 @@ void mlx5e_ipsec_aso_cleanup(struct mlx5e_ipsec *ipsec) dma_unmap_single(pdev, aso->dma_addr, sizeof(aso->ctx), DMA_BIDIRECTIONAL); kfree(aso); + ipsec->aso = NULL; } static void mlx5e_ipsec_aso_copy(struct mlx5_wqe_aso_ctrl_seg *ctrl, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index dff02434ff458..38263d5c98b34 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -43,12 +43,17 @@ void mlx5e_ethtool_get_drvinfo(struct mlx5e_priv *priv, struct ethtool_drvinfo *drvinfo) { struct mlx5_core_dev *mdev = priv->mdev; + int count; strscpy(drvinfo->driver, KBUILD_MODNAME, sizeof(drvinfo->driver)); - snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), - "%d.%d.%04d (%.16s)", - fw_rev_maj(mdev), fw_rev_min(mdev), fw_rev_sub(mdev), - mdev->board_id); + count = snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), + "%d.%d.%04d (%.16s)", fw_rev_maj(mdev), + fw_rev_min(mdev), fw_rev_sub(mdev), mdev->board_id); + if (count >= sizeof(drvinfo->fw_version)) + snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), + "%d.%d.%04d", fw_rev_maj(mdev), + fw_rev_min(mdev), fw_rev_sub(mdev)); + strscpy(drvinfo->bus_info, dev_name(mdev->device), sizeof(drvinfo->bus_info)); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index acb40770cf0cf..c3961c2bbc57c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -2668,6 +2668,7 @@ void mlx5e_close_channels(struct mlx5e_channels *chs) { int i; + ASSERT_RTNL(); if (chs->ptp) { mlx5e_ptp_close(chs->ptp); chs->ptp = NULL; @@ -2945,17 +2946,29 @@ void mlx5e_activate_priv_channels(struct mlx5e_priv *priv) if (mlx5e_is_vport_rep(priv)) mlx5e_rep_activate_channels(priv); + set_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state); + mlx5e_wait_channels_min_rx_wqes(&priv->channels); if (priv->rx_res) mlx5e_rx_res_channels_activate(priv->rx_res, &priv->channels); } +static void mlx5e_cancel_tx_timeout_work(struct mlx5e_priv *priv) +{ + WARN_ON_ONCE(test_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state)); + if (current_work() != &priv->tx_timeout_work) + cancel_work_sync(&priv->tx_timeout_work); +} + void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv) { if (priv->rx_res) mlx5e_rx_res_channels_deactivate(priv->rx_res); + clear_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state); + mlx5e_cancel_tx_timeout_work(priv); + if (mlx5e_is_vport_rep(priv)) mlx5e_rep_deactivate_channels(priv); @@ -4734,8 +4747,17 @@ static void mlx5e_tx_timeout_work(struct work_struct *work) struct net_device *netdev = priv->netdev; int i; - rtnl_lock(); - mutex_lock(&priv->state_lock); + /* Take rtnl_lock to ensure no change in netdev->real_num_tx_queues + * through this flow. However, channel closing flows have to wait for + * this work to finish while holding rtnl lock too. So either get the + * lock or find that channels are being closed for other reason and + * this work is not relevant anymore. + */ + while (!rtnl_trylock()) { + if (!test_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state)) + return; + msleep(20); + } if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) goto unlock; @@ -4754,7 +4776,6 @@ static void mlx5e_tx_timeout_work(struct work_struct *work) } unlock: - mutex_unlock(&priv->state_lock); rtnl_unlock(); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index fd1cce542b680..751d3ffcd2f6c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -71,13 +71,17 @@ static void mlx5e_rep_get_drvinfo(struct net_device *dev, { struct mlx5e_priv *priv = netdev_priv(dev); struct mlx5_core_dev *mdev = priv->mdev; + int count; strscpy(drvinfo->driver, mlx5e_rep_driver_name, sizeof(drvinfo->driver)); - snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), - "%d.%d.%04d (%.16s)", - fw_rev_maj(mdev), fw_rev_min(mdev), - fw_rev_sub(mdev), mdev->board_id); + count = snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), + "%d.%d.%04d (%.16s)", fw_rev_maj(mdev), + fw_rev_min(mdev), fw_rev_sub(mdev), mdev->board_id); + if (count >= sizeof(drvinfo->fw_version)) + snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), + "%d.%d.%04d", fw_rev_maj(mdev), + fw_rev_min(mdev), fw_rev_sub(mdev)); } static const struct counter_desc sw_rep_stats_desc[] = { @@ -1499,7 +1503,7 @@ mlx5e_vport_vf_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) dl_port = mlx5_esw_offloads_devlink_port(dev->priv.eswitch, rpriv->rep->vport); - if (dl_port) { + if (!IS_ERR(dl_port)) { SET_NETDEV_DEVLINK_PORT(netdev, dl_port); mlx5e_rep_vnic_reporter_create(priv, dl_port); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index c8590483ddc64..25e44ee5121a9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -444,6 +444,9 @@ mlx5e_tc_add_flow_meter(struct mlx5e_priv *priv, struct mlx5e_flow_meter_handle *meter; enum mlx5e_post_meter_type type; + if (IS_ERR(post_act)) + return PTR_ERR(post_act); + meter = mlx5e_tc_meter_replace(priv->mdev, &attr->meter_attr.params); if (IS_ERR(meter)) { mlx5_core_err(priv->mdev, "Failed to get flow meter\n"); @@ -3145,7 +3148,7 @@ static struct mlx5_fields fields[] = { OFFLOAD(DIPV6_31_0, 32, U32_MAX, ip6.daddr.s6_addr32[3], 0, dst_ipv4_dst_ipv6.ipv6_layout.ipv6[12]), OFFLOAD(IPV6_HOPLIMIT, 8, U8_MAX, ip6.hop_limit, 0, ttl_hoplimit), - OFFLOAD(IP_DSCP, 16, 0xc00f, ip6, 0, ip_dscp), + OFFLOAD(IP_DSCP, 16, 0x0fc0, ip6, 0, ip_dscp), OFFLOAD(TCP_SPORT, 16, U16_MAX, tcp.source, 0, tcp_sport), OFFLOAD(TCP_DPORT, 16, U16_MAX, tcp.dest, 0, tcp_dport), @@ -3156,21 +3159,31 @@ static struct mlx5_fields fields[] = { OFFLOAD(UDP_DPORT, 16, U16_MAX, udp.dest, 0, udp_dport), }; -static unsigned long mask_to_le(unsigned long mask, int size) +static u32 mask_field_get(void *mask, struct mlx5_fields *f) { - __be32 mask_be32; - __be16 mask_be16; - - if (size == 32) { - mask_be32 = (__force __be32)(mask); - mask = (__force unsigned long)cpu_to_le32(be32_to_cpu(mask_be32)); - } else if (size == 16) { - mask_be32 = (__force __be32)(mask); - mask_be16 = *(__be16 *)&mask_be32; - mask = (__force unsigned long)cpu_to_le16(be16_to_cpu(mask_be16)); + switch (f->field_bsize) { + case 32: + return be32_to_cpu(*(__be32 *)mask) & f->field_mask; + case 16: + return be16_to_cpu(*(__be16 *)mask) & (u16)f->field_mask; + default: + return *(u8 *)mask & (u8)f->field_mask; } +} - return mask; +static void mask_field_clear(void *mask, struct mlx5_fields *f) +{ + switch (f->field_bsize) { + case 32: + *(__be32 *)mask &= ~cpu_to_be32(f->field_mask); + break; + case 16: + *(__be16 *)mask &= ~cpu_to_be16((u16)f->field_mask); + break; + default: + *(u8 *)mask &= ~(u8)f->field_mask; + break; + } } static int offload_pedit_fields(struct mlx5e_priv *priv, @@ -3182,11 +3195,12 @@ static int offload_pedit_fields(struct mlx5e_priv *priv, struct pedit_headers *set_masks, *add_masks, *set_vals, *add_vals; struct pedit_headers_action *hdrs = parse_attr->hdrs; void *headers_c, *headers_v, *action, *vals_p; - u32 *s_masks_p, *a_masks_p, s_mask, a_mask; struct mlx5e_tc_mod_hdr_acts *mod_acts; - unsigned long mask, field_mask; + void *s_masks_p, *a_masks_p; int i, first, last, next_z; struct mlx5_fields *f; + unsigned long mask; + u32 s_mask, a_mask; u8 cmd; mod_acts = &parse_attr->mod_hdr_acts; @@ -3202,15 +3216,11 @@ static int offload_pedit_fields(struct mlx5e_priv *priv, bool skip; f = &fields[i]; - /* avoid seeing bits set from previous iterations */ - s_mask = 0; - a_mask = 0; - s_masks_p = (void *)set_masks + f->offset; a_masks_p = (void *)add_masks + f->offset; - s_mask = *s_masks_p & f->field_mask; - a_mask = *a_masks_p & f->field_mask; + s_mask = mask_field_get(s_masks_p, f); + a_mask = mask_field_get(a_masks_p, f); if (!s_mask && !a_mask) /* nothing to offload here */ continue; @@ -3237,22 +3247,20 @@ static int offload_pedit_fields(struct mlx5e_priv *priv, match_mask, f->field_bsize)) skip = true; /* clear to denote we consumed this field */ - *s_masks_p &= ~f->field_mask; + mask_field_clear(s_masks_p, f); } else { cmd = MLX5_ACTION_TYPE_ADD; mask = a_mask; vals_p = (void *)add_vals + f->offset; /* add 0 is no change */ - if ((*(u32 *)vals_p & f->field_mask) == 0) + if (!mask_field_get(vals_p, f)) skip = true; /* clear to denote we consumed this field */ - *a_masks_p &= ~f->field_mask; + mask_field_clear(a_masks_p, f); } if (skip) continue; - mask = mask_to_le(mask, f->field_bsize); - first = find_first_bit(&mask, f->field_bsize); next_z = find_next_zero_bit(&mask, f->field_bsize, first); last = find_last_bit(&mask, f->field_bsize); @@ -3279,10 +3287,9 @@ static int offload_pedit_fields(struct mlx5e_priv *priv, MLX5_SET(set_action_in, action, field, f->field); if (cmd == MLX5_ACTION_TYPE_SET) { + unsigned long field_mask = f->field_mask; int start; - field_mask = mask_to_le(f->field_mask, f->field_bsize); - /* if field is bit sized it can start not from first bit */ start = find_first_bit(&field_mask, f->field_bsize); @@ -3732,6 +3739,20 @@ alloc_flow_post_acts(struct mlx5e_tc_flow *flow, struct netlink_ext_ack *extack) return err; } +static int +set_branch_dest_ft(struct mlx5e_priv *priv, struct mlx5_flow_attr *attr) +{ + struct mlx5e_post_act *post_act = get_post_action(priv); + + if (IS_ERR(post_act)) + return PTR_ERR(post_act); + + attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + attr->dest_ft = mlx5e_tc_post_act_get_ft(post_act); + + return 0; +} + static int alloc_branch_attr(struct mlx5e_tc_flow *flow, struct mlx5e_tc_act_branch_ctrl *cond, @@ -3755,8 +3776,9 @@ alloc_branch_attr(struct mlx5e_tc_flow *flow, break; case FLOW_ACTION_ACCEPT: case FLOW_ACTION_PIPE: - attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; - attr->dest_ft = mlx5e_tc_post_act_get_ft(get_post_action(flow->priv)); + err = set_branch_dest_ft(flow->priv, attr); + if (err) + goto out_err; break; case FLOW_ACTION_JUMP: if (*jump_count) { @@ -3765,8 +3787,9 @@ alloc_branch_attr(struct mlx5e_tc_flow *flow, goto out_err; } *jump_count = cond->extval; - attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; - attr->dest_ft = mlx5e_tc_post_act_get_ft(get_post_action(flow->priv)); + err = set_branch_dest_ft(flow->priv, attr); + if (err) + goto out_err; break; default: err = -EOPNOTSUPP; @@ -5713,8 +5736,10 @@ int mlx5e_tc_action_miss_mapping_get(struct mlx5e_priv *priv, struct mlx5_flow_a esw = priv->mdev->priv.eswitch; attr->act_id_restore_rule = esw_add_restore_rule(esw, *act_miss_mapping); - if (IS_ERR(attr->act_id_restore_rule)) + if (IS_ERR(attr->act_id_restore_rule)) { + err = PTR_ERR(attr->act_id_restore_rule); goto err_rule; + } 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 d41435c22ce56..f0b506e562df3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -399,9 +399,9 @@ mlx5e_txwqe_complete(struct mlx5e_txqsq *sq, struct sk_buff *skb, u8 metadata_index = be32_to_cpu(eseg->flow_table_metadata); mlx5e_skb_cb_hwtstamp_init(skb); - mlx5e_ptpsq_track_metadata(sq->ptpsq, metadata_index); mlx5e_ptp_metadata_map_put(&sq->ptpsq->metadata_map, skb, metadata_index); + mlx5e_ptpsq_track_metadata(sq->ptpsq, metadata_index); if (!netif_tx_queue_stopped(sq->txq) && mlx5e_ptpsq_metadata_freelist_empty(sq->ptpsq)) { netif_tx_stop_queue(sq->txq); @@ -494,10 +494,10 @@ mlx5e_sq_xmit_wqe(struct mlx5e_txqsq *sq, struct sk_buff *skb, err_drop: stats->dropped++; - dev_kfree_skb_any(skb); if (unlikely(sq->ptpsq && (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))) mlx5e_ptp_metadata_fifo_push(&sq->ptpsq->metadata_freelist, be32_to_cpu(eseg->flow_table_metadata)); + dev_kfree_skb_any(skb); mlx5e_tx_flush(sq); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index ea0405e0a43fa..40a6cb052a2da 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -885,11 +885,14 @@ static void comp_irq_release_sf(struct mlx5_core_dev *dev, u16 vecidx) { struct mlx5_eq_table *table = dev->priv.eq_table; struct mlx5_irq *irq; + int cpu; irq = xa_load(&table->comp_irqs, vecidx); if (!irq) return; + cpu = cpumask_first(mlx5_irq_get_affinity_mask(irq)); + cpumask_clear_cpu(cpu, &table->used_cpus); xa_erase(&table->comp_irqs, vecidx); mlx5_irq_affinity_irq_release(dev, irq); } @@ -897,16 +900,26 @@ static void comp_irq_release_sf(struct mlx5_core_dev *dev, u16 vecidx) static int comp_irq_request_sf(struct mlx5_core_dev *dev, u16 vecidx) { struct mlx5_eq_table *table = dev->priv.eq_table; + struct mlx5_irq_pool *pool = mlx5_irq_pool_get(dev); + struct irq_affinity_desc af_desc = {}; struct mlx5_irq *irq; - irq = mlx5_irq_affinity_irq_request_auto(dev, &table->used_cpus, vecidx); - if (IS_ERR(irq)) { - /* In case SF irq pool does not exist, fallback to the PF irqs*/ - if (PTR_ERR(irq) == -ENOENT) - return comp_irq_request_pci(dev, vecidx); + /* In case SF irq pool does not exist, fallback to the PF irqs*/ + if (!mlx5_irq_pool_is_sf_pool(pool)) + return comp_irq_request_pci(dev, vecidx); + af_desc.is_managed = 1; + cpumask_copy(&af_desc.mask, cpu_online_mask); + cpumask_andnot(&af_desc.mask, &af_desc.mask, &table->used_cpus); + irq = mlx5_irq_affinity_request(pool, &af_desc); + if (IS_ERR(irq)) return PTR_ERR(irq); - } + + cpumask_or(&table->used_cpus, &table->used_cpus, mlx5_irq_get_affinity_mask(irq)); + mlx5_core_dbg(pool->dev, "IRQ %u mapped to cpu %*pbl, %u EQs on this irq\n", + pci_irq_vector(dev->pdev, mlx5_irq_get_index(irq)), + cpumask_pr_args(mlx5_irq_get_affinity_mask(irq)), + mlx5_irq_read_locked(irq) / MLX5_EQ_REFS_PER_IRQ); return xa_err(xa_store(&table->comp_irqs, vecidx, irq, GFP_KERNEL)); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c index 095f31f380fa3..d5d33c3b3aa2a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c @@ -21,158 +21,6 @@ enum { MLX5_ESW_IPSEC_TX_ESP_FT_CNT_LEVEL, }; -static void esw_ipsec_rx_status_drop_destroy(struct mlx5e_ipsec *ipsec, - struct mlx5e_ipsec_rx *rx) -{ - mlx5_del_flow_rules(rx->status_drop.rule); - mlx5_destroy_flow_group(rx->status_drop.group); - mlx5_fc_destroy(ipsec->mdev, rx->status_drop_cnt); -} - -static void esw_ipsec_rx_status_pass_destroy(struct mlx5e_ipsec *ipsec, - struct mlx5e_ipsec_rx *rx) -{ - mlx5_del_flow_rules(rx->status.rule); - mlx5_chains_put_table(esw_chains(ipsec->mdev->priv.eswitch), 0, 1, 0); -} - -static int esw_ipsec_rx_status_drop_create(struct mlx5e_ipsec *ipsec, - struct mlx5e_ipsec_rx *rx) -{ - int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); - struct mlx5_flow_table *ft = rx->ft.status; - struct mlx5_core_dev *mdev = ipsec->mdev; - struct mlx5_flow_destination dest = {}; - struct mlx5_flow_act flow_act = {}; - struct mlx5_flow_handle *rule; - struct mlx5_fc *flow_counter; - struct mlx5_flow_spec *spec; - struct mlx5_flow_group *g; - u32 *flow_group_in; - int err = 0; - - flow_group_in = kvzalloc(inlen, GFP_KERNEL); - spec = kvzalloc(sizeof(*spec), GFP_KERNEL); - if (!flow_group_in || !spec) { - err = -ENOMEM; - goto err_out; - } - - MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ft->max_fte - 1); - MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, ft->max_fte - 1); - g = mlx5_create_flow_group(ft, flow_group_in); - if (IS_ERR(g)) { - err = PTR_ERR(g); - mlx5_core_err(mdev, - "Failed to add ipsec rx status drop flow group, err=%d\n", err); - goto err_out; - } - - flow_counter = mlx5_fc_create(mdev, false); - if (IS_ERR(flow_counter)) { - err = PTR_ERR(flow_counter); - mlx5_core_err(mdev, - "Failed to add ipsec rx status drop rule counter, err=%d\n", err); - goto err_cnt; - } - - flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT; - dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; - dest.counter_id = mlx5_fc_id(flow_counter); - spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK; - rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1); - if (IS_ERR(rule)) { - err = PTR_ERR(rule); - mlx5_core_err(mdev, - "Failed to add ipsec rx status drop rule, err=%d\n", err); - goto err_rule; - } - - rx->status_drop.group = g; - rx->status_drop.rule = rule; - rx->status_drop_cnt = flow_counter; - - kvfree(flow_group_in); - kvfree(spec); - return 0; - -err_rule: - mlx5_fc_destroy(mdev, flow_counter); -err_cnt: - mlx5_destroy_flow_group(g); -err_out: - kvfree(flow_group_in); - kvfree(spec); - return err; -} - -static int esw_ipsec_rx_status_pass_create(struct mlx5e_ipsec *ipsec, - struct mlx5e_ipsec_rx *rx, - struct mlx5_flow_destination *dest) -{ - struct mlx5_flow_act flow_act = {}; - struct mlx5_flow_handle *rule; - struct mlx5_flow_spec *spec; - int err; - - spec = kvzalloc(sizeof(*spec), GFP_KERNEL); - if (!spec) - return -ENOMEM; - - MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, - misc_parameters_2.ipsec_syndrome); - MLX5_SET(fte_match_param, spec->match_value, - misc_parameters_2.ipsec_syndrome, 0); - spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK; - spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2; - flow_act.flags = FLOW_ACT_NO_APPEND; - flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | - MLX5_FLOW_CONTEXT_ACTION_COUNT; - rule = mlx5_add_flow_rules(rx->ft.status, spec, &flow_act, dest, 2); - if (IS_ERR(rule)) { - err = PTR_ERR(rule); - mlx5_core_warn(ipsec->mdev, - "Failed to add ipsec rx status pass rule, err=%d\n", err); - goto err_rule; - } - - rx->status.rule = rule; - kvfree(spec); - return 0; - -err_rule: - kvfree(spec); - return err; -} - -void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec, - struct mlx5e_ipsec_rx *rx) -{ - esw_ipsec_rx_status_pass_destroy(ipsec, rx); - esw_ipsec_rx_status_drop_destroy(ipsec, rx); -} - -int mlx5_esw_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec, - struct mlx5e_ipsec_rx *rx, - struct mlx5_flow_destination *dest) -{ - int err; - - err = esw_ipsec_rx_status_drop_create(ipsec, rx); - if (err) - return err; - - err = esw_ipsec_rx_status_pass_create(ipsec, rx, dest); - if (err) - goto err_pass_create; - - return 0; - -err_pass_create: - esw_ipsec_rx_status_drop_destroy(ipsec, rx); - return err; -} - void mlx5_esw_ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_rx_create_attr *attr) { @@ -304,7 +152,7 @@ void mlx5_esw_ipsec_restore_dest_uplink(struct mlx5_core_dev *mdev) xa_for_each(&esw->offloads.vport_reps, i, rep) { rpriv = rep->rep_data[REP_ETH].priv; - if (!rpriv || !rpriv->netdev) + if (!rpriv || !rpriv->netdev || !atomic_read(&rpriv->tc_ht.nelems)) continue; rhashtable_walk_enter(&rpriv->tc_ht, &iter); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h index 0c90f7a8b0d32..ac9c65b89166e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h @@ -8,11 +8,6 @@ struct mlx5e_ipsec; struct mlx5e_ipsec_sa_entry; #ifdef CONFIG_MLX5_ESWITCH -void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec, - struct mlx5e_ipsec_rx *rx); -int mlx5_esw_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec, - struct mlx5e_ipsec_rx *rx, - struct mlx5_flow_destination *dest); void mlx5_esw_ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_rx_create_attr *attr); int mlx5_esw_ipsec_rx_status_pass_dest_get(struct mlx5e_ipsec *ipsec, @@ -26,16 +21,6 @@ void mlx5_esw_ipsec_tx_create_attr_set(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx_create_attr *attr); void mlx5_esw_ipsec_restore_dest_uplink(struct mlx5_core_dev *mdev); #else -static inline void mlx5_esw_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec, - struct mlx5e_ipsec_rx *rx) {} - -static inline int mlx5_esw_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec, - struct mlx5e_ipsec_rx *rx, - struct mlx5_flow_destination *dest) -{ - return -EINVAL; -} - static inline void mlx5_esw_ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_rx_create_attr *attr) {} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 8d0b915a31214..3047d7015c525 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1463,7 +1463,7 @@ int mlx5_eswitch_enable_locked(struct mlx5_eswitch *esw, int num_vfs) { int err; - lockdep_assert_held(&esw->mode_lock); + devl_assert_locked(priv_to_devlink(esw->dev)); if (!MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ft_support)) { esw_warn(esw->dev, "FDB is not supported, aborting ...\n"); @@ -1531,7 +1531,6 @@ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs) if (toggle_lag) mlx5_lag_disable_change(esw->dev); - down_write(&esw->mode_lock); if (!mlx5_esw_is_fdb_created(esw)) { ret = mlx5_eswitch_enable_locked(esw, num_vfs); } else { @@ -1554,8 +1553,6 @@ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int num_vfs) } } - up_write(&esw->mode_lock); - if (toggle_lag) mlx5_lag_enable_change(esw->dev); @@ -1569,12 +1566,11 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw, bool clear_vf) return; devl_assert_locked(priv_to_devlink(esw->dev)); - down_write(&esw->mode_lock); /* If driver is unloaded, this function is called twice by remove_one() * and mlx5_unload(). Prevent the second call. */ if (!esw->esw_funcs.num_vfs && !esw->esw_funcs.num_ec_vfs && !clear_vf) - goto unlock; + return; esw_info(esw->dev, "Unload vfs: mode(%s), nvfs(%d), necvfs(%d), active vports(%d)\n", esw->mode == MLX5_ESWITCH_LEGACY ? "LEGACY" : "OFFLOADS", @@ -1603,9 +1599,6 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw, bool clear_vf) esw->esw_funcs.num_vfs = 0; else esw->esw_funcs.num_ec_vfs = 0; - -unlock: - up_write(&esw->mode_lock); } /* Free resources for corresponding eswitch mode. It is called by devlink @@ -1647,10 +1640,8 @@ void mlx5_eswitch_disable(struct mlx5_eswitch *esw) devl_assert_locked(priv_to_devlink(esw->dev)); mlx5_lag_disable_change(esw->dev); - down_write(&esw->mode_lock); mlx5_eswitch_disable_locked(esw); esw->mode = MLX5_ESWITCH_LEGACY; - up_write(&esw->mode_lock); mlx5_lag_enable_change(esw->dev); } @@ -2254,8 +2245,13 @@ bool mlx5_esw_hold(struct mlx5_core_dev *mdev) if (!mlx5_esw_allowed(esw)) return true; - if (down_read_trylock(&esw->mode_lock) != 0) + if (down_read_trylock(&esw->mode_lock) != 0) { + if (esw->eswitch_operation_in_progress) { + up_read(&esw->mode_lock); + return false; + } return true; + } return false; } @@ -2312,7 +2308,8 @@ int mlx5_esw_try_lock(struct mlx5_eswitch *esw) if (down_write_trylock(&esw->mode_lock) == 0) return -EINVAL; - if (atomic64_read(&esw->user_count) > 0) { + if (esw->eswitch_operation_in_progress || + atomic64_read(&esw->user_count) > 0) { up_write(&esw->mode_lock); return -EBUSY; } @@ -2320,6 +2317,18 @@ int mlx5_esw_try_lock(struct mlx5_eswitch *esw) return esw->mode; } +int mlx5_esw_lock(struct mlx5_eswitch *esw) +{ + down_write(&esw->mode_lock); + + if (esw->eswitch_operation_in_progress) { + up_write(&esw->mode_lock); + return -EBUSY; + } + + return 0; +} + /** * mlx5_esw_unlock() - Release write lock on esw mode lock * @esw: eswitch device. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 37ab66e7b403f..b4eb17141edf3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -383,6 +383,7 @@ struct mlx5_eswitch { struct xarray paired; struct mlx5_devcom_comp_dev *devcom; u16 enabled_ipsec_vf_count; + bool eswitch_operation_in_progress; }; void esw_offloads_disable(struct mlx5_eswitch *esw); @@ -525,7 +526,8 @@ struct mlx5_esw_flow_attr { u8 total_vlan; struct { u32 flags; - struct mlx5_eswitch_rep *rep; + bool vport_valid; + u16 vport; struct mlx5_pkt_reformat *pkt_reformat; struct mlx5_core_dev *mdev; struct mlx5_termtbl_handle *termtbl; @@ -827,6 +829,7 @@ void mlx5_esw_release(struct mlx5_core_dev *dev); void mlx5_esw_get(struct mlx5_core_dev *dev); void mlx5_esw_put(struct mlx5_core_dev *dev); int mlx5_esw_try_lock(struct mlx5_eswitch *esw); +int mlx5_esw_lock(struct mlx5_eswitch *esw); void mlx5_esw_unlock(struct mlx5_eswitch *esw); void esw_vport_change_handle_locked(struct mlx5_vport *vport); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index b296ac52a4397..b0455134c98ef 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -287,10 +287,9 @@ static void esw_put_dest_tables_loop(struct mlx5_eswitch *esw, struct mlx5_flow_ for (i = from; i < to; i++) if (esw_attr->dests[i].flags & MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE) mlx5_chains_put_table(chains, 0, 1, 0); - else if (mlx5_esw_indir_table_needed(esw, attr, esw_attr->dests[i].rep->vport, + else if (mlx5_esw_indir_table_needed(esw, attr, esw_attr->dests[i].vport, esw_attr->dests[i].mdev)) - mlx5_esw_indir_table_put(esw, esw_attr->dests[i].rep->vport, - false); + mlx5_esw_indir_table_put(esw, esw_attr->dests[i].vport, false); } static bool @@ -358,8 +357,8 @@ esw_is_indir_table(struct mlx5_eswitch *esw, struct mlx5_flow_attr *attr) * this criteria. */ for (i = esw_attr->split_count; i < esw_attr->out_count; i++) { - if (esw_attr->dests[i].rep && - mlx5_esw_indir_table_needed(esw, attr, esw_attr->dests[i].rep->vport, + if (esw_attr->dests[i].vport_valid && + mlx5_esw_indir_table_needed(esw, attr, esw_attr->dests[i].vport, esw_attr->dests[i].mdev)) { result = true; } else { @@ -388,7 +387,7 @@ esw_setup_indir_table(struct mlx5_flow_destination *dest, dest[*i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; dest[*i].ft = mlx5_esw_indir_table_get(esw, attr, - esw_attr->dests[j].rep->vport, false); + esw_attr->dests[j].vport, false); if (IS_ERR(dest[*i].ft)) { err = PTR_ERR(dest[*i].ft); goto err_indir_tbl_get; @@ -432,11 +431,11 @@ static bool esw_setup_uplink_fwd_ipsec_needed(struct mlx5_eswitch *esw, int attr_idx) { if (esw->offloads.ft_ipsec_tx_pol && - esw_attr->dests[attr_idx].rep && - esw_attr->dests[attr_idx].rep->vport == MLX5_VPORT_UPLINK && + esw_attr->dests[attr_idx].vport_valid && + esw_attr->dests[attr_idx].vport == MLX5_VPORT_UPLINK && /* To be aligned with software, encryption is needed only for tunnel device */ (esw_attr->dests[attr_idx].flags & MLX5_ESW_DEST_ENCAP_VALID) && - esw_attr->dests[attr_idx].rep != esw_attr->in_rep && + esw_attr->dests[attr_idx].vport != esw_attr->in_rep->vport && esw_same_vhca_id(esw_attr->dests[attr_idx].mdev, esw->dev)) return true; @@ -469,7 +468,7 @@ esw_setup_dest_fwd_vport(struct mlx5_flow_destination *dest, struct mlx5_flow_ac int attr_idx, int dest_idx, bool pkt_reformat) { dest[dest_idx].type = MLX5_FLOW_DESTINATION_TYPE_VPORT; - dest[dest_idx].vport.num = esw_attr->dests[attr_idx].rep->vport; + dest[dest_idx].vport.num = esw_attr->dests[attr_idx].vport; if (MLX5_CAP_ESW(esw->dev, merged_eswitch)) { dest[dest_idx].vport.vhca_id = MLX5_CAP_GEN(esw_attr->dests[attr_idx].mdev, vhca_id); @@ -984,7 +983,8 @@ mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *on_esw, dest.vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID; flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; - if (rep->vport == MLX5_VPORT_UPLINK && on_esw->offloads.ft_ipsec_tx_pol) { + if (rep->vport == MLX5_VPORT_UPLINK && + on_esw == from_esw && on_esw->offloads.ft_ipsec_tx_pol) { dest.ft = on_esw->offloads.ft_ipsec_tx_pol; flow_act.flags = FLOW_ACT_IGNORE_FLOW_LEVEL; dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; @@ -1176,9 +1176,9 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw, struct mlx5_flow_handle *flow; struct mlx5_flow_spec *spec; struct mlx5_vport *vport; + int err, pfindex; unsigned long i; void *misc; - int err; if (!MLX5_VPORT_MANAGER(esw->dev) && !mlx5_core_is_ecpf_esw_manager(esw->dev)) return 0; @@ -1254,7 +1254,15 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw, flows[vport->index] = flow; } } - esw->fdb_table.offloads.peer_miss_rules[mlx5_get_dev_index(peer_dev)] = flows; + + pfindex = mlx5_get_dev_index(peer_dev); + if (pfindex >= MLX5_MAX_PORTS) { + esw_warn(esw->dev, "Peer dev index(%d) is over the max num defined(%d)\n", + pfindex, MLX5_MAX_PORTS); + err = -EINVAL; + goto add_ec_vf_flow_err; + } + esw->fdb_table.offloads.peer_miss_rules[pfindex] = flows; kvfree(spec); return 0; @@ -3652,14 +3660,18 @@ static int esw_inline_mode_to_devlink(u8 mlx5_mode, u8 *mode) static bool esw_offloads_devlink_ns_eq_netdev_ns(struct devlink *devlink) { + struct mlx5_core_dev *dev = devlink_priv(devlink); struct net *devl_net, *netdev_net; - struct mlx5_eswitch *esw; - - esw = mlx5_devlink_eswitch_nocheck_get(devlink); - netdev_net = dev_net(esw->dev->mlx5e_res.uplink_netdev); - devl_net = devlink_net(devlink); + bool ret = false; - return net_eq(devl_net, netdev_net); + mutex_lock(&dev->mlx5e_res.uplink_netdev_lock); + if (dev->mlx5e_res.uplink_netdev) { + netdev_net = dev_net(dev->mlx5e_res.uplink_netdev); + devl_net = devlink_net(devlink); + ret = net_eq(devl_net, netdev_net); + } + mutex_unlock(&dev->mlx5e_res.uplink_netdev_lock); + return ret; } int mlx5_eswitch_block_mode(struct mlx5_core_dev *dev) @@ -3732,13 +3744,16 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode, goto unlock; } + esw->eswitch_operation_in_progress = true; + up_write(&esw->mode_lock); + mlx5_eswitch_disable_locked(esw); if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV) { if (mlx5_devlink_trap_get_num_active(esw->dev)) { NL_SET_ERR_MSG_MOD(extack, "Can't change mode while devlink traps are active"); err = -EOPNOTSUPP; - goto unlock; + goto skip; } err = esw_offloads_start(esw, extack); } else if (mode == DEVLINK_ESWITCH_MODE_LEGACY) { @@ -3748,6 +3763,9 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode, err = -EINVAL; } +skip: + down_write(&esw->mode_lock); + esw->eswitch_operation_in_progress = false; unlock: mlx5_esw_unlock(esw); enable_lag: @@ -3758,16 +3776,12 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode, int mlx5_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode) { struct mlx5_eswitch *esw; - int err; esw = mlx5_devlink_eswitch_get(devlink); if (IS_ERR(esw)) return PTR_ERR(esw); - down_read(&esw->mode_lock); - err = esw_mode_to_devlink(esw->mode, mode); - up_read(&esw->mode_lock); - return err; + return esw_mode_to_devlink(esw->mode, mode); } static int mlx5_esw_vports_inline_set(struct mlx5_eswitch *esw, u8 mlx5_mode, @@ -3861,11 +3875,15 @@ int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode, if (err) goto out; + esw->eswitch_operation_in_progress = true; + up_write(&esw->mode_lock); + err = mlx5_esw_vports_inline_set(esw, mlx5_mode, extack); - if (err) - goto out; + if (!err) + esw->offloads.inline_mode = mlx5_mode; - esw->offloads.inline_mode = mlx5_mode; + down_write(&esw->mode_lock); + esw->eswitch_operation_in_progress = false; up_write(&esw->mode_lock); return 0; @@ -3877,16 +3895,12 @@ int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode, int mlx5_devlink_eswitch_inline_mode_get(struct devlink *devlink, u8 *mode) { struct mlx5_eswitch *esw; - int err; esw = mlx5_devlink_eswitch_get(devlink); if (IS_ERR(esw)) return PTR_ERR(esw); - down_read(&esw->mode_lock); - err = esw_inline_mode_to_devlink(esw->offloads.inline_mode, mode); - up_read(&esw->mode_lock); - return err; + return esw_inline_mode_to_devlink(esw->offloads.inline_mode, mode); } bool mlx5_eswitch_block_encap(struct mlx5_core_dev *dev) @@ -3968,6 +3982,9 @@ int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink, goto unlock; } + esw->eswitch_operation_in_progress = true; + up_write(&esw->mode_lock); + esw_destroy_offloads_fdb_tables(esw); esw->offloads.encap = encap; @@ -3981,6 +3998,9 @@ int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink, (void)esw_create_offloads_fdb_tables(esw); } + down_write(&esw->mode_lock); + esw->eswitch_operation_in_progress = false; + unlock: up_write(&esw->mode_lock); return err; @@ -3995,9 +4015,7 @@ int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink, if (IS_ERR(esw)) return PTR_ERR(esw); - down_read(&esw->mode_lock); *encap = esw->offloads.encap; - up_read(&esw->mode_lock); return 0; } 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 edd9102583144..40bdc677f051d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c @@ -233,8 +233,8 @@ mlx5_eswitch_termtbl_required(struct mlx5_eswitch *esw, /* hairpin */ for (i = esw_attr->split_count; i < esw_attr->out_count; i++) - if (!esw_attr->dest_int_port && esw_attr->dests[i].rep && - esw_attr->dests[i].rep->vport == MLX5_VPORT_UPLINK) + if (!esw_attr->dest_int_port && esw_attr->dests[i].vport_valid && + esw_attr->dests[i].vport == MLX5_VPORT_UPLINK) return true; return false; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c index b568988e92e3e..c4e19d627da21 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c @@ -325,6 +325,29 @@ static void mlx5_fw_live_patch_event(struct work_struct *work) mlx5_core_err(dev, "Failed to reload FW tracer\n"); } +#if IS_ENABLED(CONFIG_HOTPLUG_PCI_PCIE) +static int mlx5_check_hotplug_interrupt(struct mlx5_core_dev *dev) +{ + struct pci_dev *bridge = dev->pdev->bus->self; + u16 reg16; + int err; + + if (!bridge) + return -EOPNOTSUPP; + + err = pcie_capability_read_word(bridge, PCI_EXP_SLTCTL, ®16); + if (err) + return err; + + if ((reg16 & PCI_EXP_SLTCTL_HPIE) && (reg16 & PCI_EXP_SLTCTL_DLLSCE)) { + mlx5_core_warn(dev, "FW reset is not supported as HotPlug is enabled\n"); + return -EOPNOTSUPP; + } + + return 0; +} +#endif + static int mlx5_check_dev_ids(struct mlx5_core_dev *dev, u16 dev_id) { struct pci_bus *bridge_bus = dev->pdev->bus; @@ -357,6 +380,12 @@ static bool mlx5_is_reset_now_capable(struct mlx5_core_dev *dev) return false; } +#if IS_ENABLED(CONFIG_HOTPLUG_PCI_PCIE) + err = mlx5_check_hotplug_interrupt(dev); + if (err) + return false; +#endif + err = pci_read_config_word(dev->pdev, PCI_DEVICE_ID, &dev_id); if (err) return false; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c b/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c index 047d5fed5f89e..612e666ec2635 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c @@ -168,45 +168,3 @@ void mlx5_irq_affinity_irq_release(struct mlx5_core_dev *dev, struct mlx5_irq *i if (pool->irqs_per_cpu) cpu_put(pool, cpu); } - -/** - * mlx5_irq_affinity_irq_request_auto - request one IRQ for mlx5 device. - * @dev: mlx5 device that is requesting the IRQ. - * @used_cpus: cpumask of bounded cpus by the device - * @vecidx: vector index to request an IRQ for. - * - * Each IRQ is bounded to at most 1 CPU. - * This function is requesting an IRQ according to the default assignment. - * The default assignment policy is: - * - request the least loaded IRQ which is not bound to any - * CPU of the previous IRQs requested. - * - * On success, this function updates used_cpus mask and returns an irq pointer. - * In case of an error, an appropriate error pointer is returned. - */ -struct mlx5_irq *mlx5_irq_affinity_irq_request_auto(struct mlx5_core_dev *dev, - struct cpumask *used_cpus, u16 vecidx) -{ - struct mlx5_irq_pool *pool = mlx5_irq_pool_get(dev); - struct irq_affinity_desc af_desc = {}; - struct mlx5_irq *irq; - - if (!mlx5_irq_pool_is_sf_pool(pool)) - return ERR_PTR(-ENOENT); - - af_desc.is_managed = 1; - cpumask_copy(&af_desc.mask, cpu_online_mask); - cpumask_andnot(&af_desc.mask, &af_desc.mask, used_cpus); - irq = mlx5_irq_affinity_request(pool, &af_desc); - - if (IS_ERR(irq)) - return irq; - - cpumask_or(used_cpus, used_cpus, mlx5_irq_get_affinity_mask(irq)); - mlx5_core_dbg(pool->dev, "IRQ %u mapped to cpu %*pbl, %u EQs on this irq\n", - pci_irq_vector(dev->pdev, mlx5_irq_get_index(irq)), - cpumask_pr_args(mlx5_irq_get_affinity_mask(irq)), - mlx5_irq_read_locked(irq) / MLX5_EQ_REFS_PER_IRQ); - - return irq; -} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index aa29f09e83564..0c83ef174275a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -384,7 +384,12 @@ static int mlx5_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) static int mlx5_ptp_adjphase(struct ptp_clock_info *ptp, s32 delta) { - return mlx5_ptp_adjtime(ptp, delta); + struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info); + struct mlx5_core_dev *mdev; + + mdev = container_of(clock, struct mlx5_core_dev, clock); + + return mlx5_ptp_adjtime_real_time(mdev, delta); } static int mlx5_ptp_freq_adj_real_time(struct mlx5_core_dev *mdev, long scaled_ppm) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 15561965d2afa..6ca91c0e8a6a5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -361,6 +361,12 @@ void mlx5_core_uplink_netdev_event_replay(struct mlx5_core_dev *dev) } EXPORT_SYMBOL(mlx5_core_uplink_netdev_event_replay); +void mlx5_core_mp_event_replay(struct mlx5_core_dev *dev, u32 event, void *data) +{ + mlx5_blocking_notifier_call_chain(dev, event, data); +} +EXPORT_SYMBOL(mlx5_core_mp_event_replay); + int mlx5_core_get_caps_mode(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type, enum mlx5_cap_mode cap_mode) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index 653648216730a..4dcf995cb1a20 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -28,7 +28,7 @@ struct mlx5_irq { struct atomic_notifier_head nh; cpumask_var_t mask; - char name[MLX5_MAX_IRQ_NAME]; + char name[MLX5_MAX_IRQ_FORMATTED_NAME]; struct mlx5_irq_pool *pool; int refcount; struct msi_map map; @@ -292,8 +292,8 @@ struct mlx5_irq *mlx5_irq_alloc(struct mlx5_irq_pool *pool, int i, else irq_sf_set_name(pool, name, i); ATOMIC_INIT_NOTIFIER_HEAD(&irq->nh); - snprintf(irq->name, MLX5_MAX_IRQ_NAME, - "%s@pci:%s", name, pci_name(dev->pdev)); + snprintf(irq->name, MLX5_MAX_IRQ_FORMATTED_NAME, + MLX5_IRQ_NAME_FORMAT_STR, name, pci_name(dev->pdev)); err = request_irq(irq->map.virq, irq_int_handler, 0, irq->name, &irq->nh); if (err) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h index d3a77a0ab8488..c4d377f8df308 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h @@ -7,6 +7,9 @@ #include #define MLX5_MAX_IRQ_NAME (32) +#define MLX5_IRQ_NAME_FORMAT_STR ("%s@pci:%s") +#define MLX5_MAX_IRQ_FORMATTED_NAME \ + (MLX5_MAX_IRQ_NAME + sizeof(MLX5_IRQ_NAME_FORMAT_STR)) /* max irq_index is 2047, so four chars */ #define MLX5_MAX_IRQ_IDX_CHARS (4) #define MLX5_EQ_REFS_PER_IRQ (2) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c index 4e8527a724f50..6fa06ba2d3465 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c @@ -52,7 +52,6 @@ struct dr_qp_init_attr { u32 cqn; u32 pdn; u32 max_send_wr; - u32 max_send_sge; struct mlx5_uars_page *uar; u8 isolate_vl_tc:1; }; @@ -247,37 +246,6 @@ static int dr_poll_cq(struct mlx5dr_cq *dr_cq, int ne) return err == CQ_POLL_ERR ? err : npolled; } -static int dr_qp_get_args_update_send_wqe_size(struct dr_qp_init_attr *attr) -{ - return roundup_pow_of_two(sizeof(struct mlx5_wqe_ctrl_seg) + - sizeof(struct mlx5_wqe_flow_update_ctrl_seg) + - sizeof(struct mlx5_wqe_header_modify_argument_update_seg)); -} - -/* We calculate for specific RC QP with the required functionality */ -static int dr_qp_calc_rc_send_wqe(struct dr_qp_init_attr *attr) -{ - int update_arg_size; - int inl_size = 0; - int tot_size; - int size; - - update_arg_size = dr_qp_get_args_update_send_wqe_size(attr); - - size = sizeof(struct mlx5_wqe_ctrl_seg) + - sizeof(struct mlx5_wqe_raddr_seg); - inl_size = size + ALIGN(sizeof(struct mlx5_wqe_inline_seg) + - DR_STE_SIZE, 16); - - size += attr->max_send_sge * sizeof(struct mlx5_wqe_data_seg); - - size = max(size, update_arg_size); - - tot_size = max(size, inl_size); - - return ALIGN(tot_size, MLX5_SEND_WQE_BB); -} - static struct mlx5dr_qp *dr_create_rc_qp(struct mlx5_core_dev *mdev, struct dr_qp_init_attr *attr) { @@ -285,7 +253,6 @@ static struct mlx5dr_qp *dr_create_rc_qp(struct mlx5_core_dev *mdev, u32 temp_qpc[MLX5_ST_SZ_DW(qpc)] = {}; struct mlx5_wq_param wqp; struct mlx5dr_qp *dr_qp; - int wqe_size; int inlen; void *qpc; void *in; @@ -365,15 +332,6 @@ static struct mlx5dr_qp *dr_create_rc_qp(struct mlx5_core_dev *mdev, if (err) goto err_in; dr_qp->uar = attr->uar; - wqe_size = dr_qp_calc_rc_send_wqe(attr); - dr_qp->max_inline_data = min(wqe_size - - (sizeof(struct mlx5_wqe_ctrl_seg) + - sizeof(struct mlx5_wqe_raddr_seg) + - sizeof(struct mlx5_wqe_inline_seg)), - (2 * MLX5_SEND_WQE_BB - - (sizeof(struct mlx5_wqe_ctrl_seg) + - sizeof(struct mlx5_wqe_raddr_seg) + - sizeof(struct mlx5_wqe_inline_seg)))); return dr_qp; @@ -437,48 +395,8 @@ dr_rdma_handle_flow_access_arg_segments(struct mlx5_wqe_ctrl_seg *wq_ctrl, MLX5_SEND_WQE_DS; } -static int dr_set_data_inl_seg(struct mlx5dr_qp *dr_qp, - struct dr_data_seg *data_seg, void *wqe) -{ - int inline_header_size = sizeof(struct mlx5_wqe_ctrl_seg) + - sizeof(struct mlx5_wqe_raddr_seg) + - sizeof(struct mlx5_wqe_inline_seg); - struct mlx5_wqe_inline_seg *seg; - int left_space; - int inl = 0; - void *addr; - int len; - int idx; - - seg = wqe; - wqe += sizeof(*seg); - addr = (void *)(unsigned long)(data_seg->addr); - len = data_seg->length; - inl += len; - left_space = MLX5_SEND_WQE_BB - inline_header_size; - - if (likely(len > left_space)) { - memcpy(wqe, addr, left_space); - len -= left_space; - addr += left_space; - idx = (dr_qp->sq.pc + 1) & (dr_qp->sq.wqe_cnt - 1); - wqe = mlx5_wq_cyc_get_wqe(&dr_qp->wq.sq, idx); - } - - memcpy(wqe, addr, len); - - if (likely(inl)) { - seg->byte_count = cpu_to_be32(inl | MLX5_INLINE_SEG); - return DIV_ROUND_UP(inl + sizeof(seg->byte_count), - MLX5_SEND_WQE_DS); - } else { - return 0; - } -} - static void -dr_rdma_handle_icm_write_segments(struct mlx5dr_qp *dr_qp, - struct mlx5_wqe_ctrl_seg *wq_ctrl, +dr_rdma_handle_icm_write_segments(struct mlx5_wqe_ctrl_seg *wq_ctrl, u64 remote_addr, u32 rkey, struct dr_data_seg *data_seg, @@ -494,17 +412,15 @@ dr_rdma_handle_icm_write_segments(struct mlx5dr_qp *dr_qp, wq_raddr->reserved = 0; wq_dseg = (void *)(wq_raddr + 1); - /* WQE ctrl segment + WQE remote addr segment */ - *size = (sizeof(*wq_ctrl) + sizeof(*wq_raddr)) / MLX5_SEND_WQE_DS; - if (data_seg->send_flags & IB_SEND_INLINE) { - *size += dr_set_data_inl_seg(dr_qp, data_seg, wq_dseg); - } else { - wq_dseg->byte_count = cpu_to_be32(data_seg->length); - wq_dseg->lkey = cpu_to_be32(data_seg->lkey); - wq_dseg->addr = cpu_to_be64(data_seg->addr); - *size += sizeof(*wq_dseg) / MLX5_SEND_WQE_DS; /* WQE data segment */ - } + wq_dseg->byte_count = cpu_to_be32(data_seg->length); + wq_dseg->lkey = cpu_to_be32(data_seg->lkey); + wq_dseg->addr = cpu_to_be64(data_seg->addr); + + *size = (sizeof(*wq_ctrl) + /* WQE ctrl segment */ + sizeof(*wq_dseg) + /* WQE data segment */ + sizeof(*wq_raddr)) / /* WQE remote addr segment */ + MLX5_SEND_WQE_DS; } static void dr_set_ctrl_seg(struct mlx5_wqe_ctrl_seg *wq_ctrl, @@ -535,7 +451,7 @@ static void dr_rdma_segments(struct mlx5dr_qp *dr_qp, u64 remote_addr, switch (opcode) { case MLX5_OPCODE_RDMA_READ: case MLX5_OPCODE_RDMA_WRITE: - dr_rdma_handle_icm_write_segments(dr_qp, wq_ctrl, remote_addr, + dr_rdma_handle_icm_write_segments(wq_ctrl, remote_addr, rkey, data_seg, &size); break; case MLX5_OPCODE_FLOW_TBL_ACCESS: @@ -656,7 +572,7 @@ static void dr_fill_write_args_segs(struct mlx5dr_send_ring *send_ring, if (send_ring->pending_wqe % send_ring->signal_th == 0) send_info->write.send_flags |= IB_SEND_SIGNALED; else - send_info->write.send_flags &= ~IB_SEND_SIGNALED; + send_info->write.send_flags = 0; } static void dr_fill_write_icm_segs(struct mlx5dr_domain *dmn, @@ -680,13 +596,9 @@ static void dr_fill_write_icm_segs(struct mlx5dr_domain *dmn, } send_ring->pending_wqe++; - if (!send_info->write.lkey) - send_info->write.send_flags |= IB_SEND_INLINE; if (send_ring->pending_wqe % send_ring->signal_th == 0) send_info->write.send_flags |= IB_SEND_SIGNALED; - else - send_info->write.send_flags &= ~IB_SEND_SIGNALED; send_ring->pending_wqe++; send_info->read.length = send_info->write.length; @@ -696,9 +608,9 @@ static void dr_fill_write_icm_segs(struct mlx5dr_domain *dmn, send_info->read.lkey = send_ring->sync_mr->mkey; if (send_ring->pending_wqe % send_ring->signal_th == 0) - send_info->read.send_flags |= IB_SEND_SIGNALED; + send_info->read.send_flags = IB_SEND_SIGNALED; else - send_info->read.send_flags &= ~IB_SEND_SIGNALED; + send_info->read.send_flags = 0; } static void dr_fill_data_segs(struct mlx5dr_domain *dmn, @@ -1345,7 +1257,6 @@ int mlx5dr_send_ring_alloc(struct mlx5dr_domain *dmn) dmn->send_ring->cq->qp = dmn->send_ring->qp; dmn->info.max_send_wr = QUEUE_SIZE; - init_attr.max_send_sge = 1; dmn->info.max_inline_size = min(dmn->send_ring->qp->max_inline_data, DR_STE_SIZE); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index 5a31fb47ffa58..21753f3278685 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -277,7 +277,7 @@ int mlx5_query_nic_vport_mac_list(struct mlx5_core_dev *dev, req_list_size = max_list_size; } - out_sz = MLX5_ST_SZ_BYTES(query_nic_vport_context_in) + + out_sz = MLX5_ST_SZ_BYTES(query_nic_vport_context_out) + req_list_size * MLX5_ST_SZ_BYTES(mac_address_layout); out = kvzalloc(out_sz, GFP_KERNEL); diff --git a/drivers/net/ethernet/micrel/ks8851.h b/drivers/net/ethernet/micrel/ks8851.h index fecd43754cead..e5ec0a363aff8 100644 --- a/drivers/net/ethernet/micrel/ks8851.h +++ b/drivers/net/ethernet/micrel/ks8851.h @@ -350,6 +350,8 @@ union ks8851_tx_hdr { * @rxd: Space for receiving SPI data, in DMA-able space. * @txd: Space for transmitting SPI data, in DMA-able space. * @msg_enable: The message flags controlling driver output (see ethtool). + * @tx_space: Free space in the hardware TX buffer (cached copy of KS_TXMIR). + * @queued_len: Space required in hardware TX buffer for queued packets in txq. * @fid: Incrementing frame id tag. * @rc_ier: Cached copy of KS_IER. * @rc_ccr: Cached copy of KS_CCR. @@ -399,6 +401,7 @@ struct ks8851_net { struct work_struct rxctrl_work; struct sk_buff_head txq; + unsigned int queued_len; struct eeprom_93cx6 eeprom; struct regulator *vdd_reg; diff --git a/drivers/net/ethernet/micrel/ks8851_common.c b/drivers/net/ethernet/micrel/ks8851_common.c index cfbc900d4aeb9..0bf13b38b8f5b 100644 --- a/drivers/net/ethernet/micrel/ks8851_common.c +++ b/drivers/net/ethernet/micrel/ks8851_common.c @@ -362,16 +362,18 @@ static irqreturn_t ks8851_irq(int irq, void *_ks) handled |= IRQ_RXPSI; if (status & IRQ_TXI) { - handled |= IRQ_TXI; + unsigned short tx_space = ks8851_rdreg16(ks, KS_TXMIR); - /* no lock here, tx queue should have been stopped */ + netif_dbg(ks, intr, ks->netdev, + "%s: txspace %d\n", __func__, tx_space); - /* update our idea of how much tx space is available to the - * system */ - ks->tx_space = ks8851_rdreg16(ks, KS_TXMIR); + spin_lock(&ks->statelock); + ks->tx_space = tx_space; + if (netif_queue_stopped(ks->netdev)) + netif_wake_queue(ks->netdev); + spin_unlock(&ks->statelock); - netif_dbg(ks, intr, ks->netdev, - "%s: txspace %d\n", __func__, ks->tx_space); + handled |= IRQ_TXI; } if (status & IRQ_RXI) @@ -414,9 +416,6 @@ static irqreturn_t ks8851_irq(int irq, void *_ks) if (status & IRQ_LCI) mii_check_link(&ks->mii); - if (status & IRQ_TXI) - netif_wake_queue(ks->netdev); - return IRQ_HANDLED; } @@ -500,6 +499,7 @@ static int ks8851_net_open(struct net_device *dev) ks8851_wrreg16(ks, KS_ISR, ks->rc_ier); ks8851_wrreg16(ks, KS_IER, ks->rc_ier); + ks->queued_len = 0; netif_start_queue(ks->netdev); netif_dbg(ks, ifup, ks->netdev, "network device up\n"); diff --git a/drivers/net/ethernet/micrel/ks8851_spi.c b/drivers/net/ethernet/micrel/ks8851_spi.c index 70bc7253454f6..88e26c120b483 100644 --- a/drivers/net/ethernet/micrel/ks8851_spi.c +++ b/drivers/net/ethernet/micrel/ks8851_spi.c @@ -286,6 +286,18 @@ static void ks8851_wrfifo_spi(struct ks8851_net *ks, struct sk_buff *txp, netdev_err(ks->netdev, "%s: spi_sync() failed\n", __func__); } +/** + * calc_txlen - calculate size of message to send packet + * @len: Length of data + * + * Returns the size of the TXFIFO message needed to send + * this packet. + */ +static unsigned int calc_txlen(unsigned int len) +{ + return ALIGN(len + 4, 4); +} + /** * ks8851_rx_skb_spi - receive skbuff * @ks: The device state @@ -305,7 +317,9 @@ static void ks8851_rx_skb_spi(struct ks8851_net *ks, struct sk_buff *skb) */ static void ks8851_tx_work(struct work_struct *work) { + unsigned int dequeued_len = 0; struct ks8851_net_spi *kss; + unsigned short tx_space; struct ks8851_net *ks; unsigned long flags; struct sk_buff *txb; @@ -322,6 +336,8 @@ static void ks8851_tx_work(struct work_struct *work) last = skb_queue_empty(&ks->txq); if (txb) { + dequeued_len += calc_txlen(txb->len); + ks8851_wrreg16_spi(ks, KS_RXQCR, ks->rc_rxqcr | RXQCR_SDA); ks8851_wrfifo_spi(ks, txb, last); @@ -332,6 +348,13 @@ static void ks8851_tx_work(struct work_struct *work) } } + tx_space = ks8851_rdreg16_spi(ks, KS_TXMIR); + + spin_lock(&ks->statelock); + ks->queued_len -= dequeued_len; + ks->tx_space = tx_space; + spin_unlock(&ks->statelock); + ks8851_unlock_spi(ks, &flags); } @@ -346,18 +369,6 @@ static void ks8851_flush_tx_work_spi(struct ks8851_net *ks) flush_work(&kss->tx_work); } -/** - * calc_txlen - calculate size of message to send packet - * @len: Length of data - * - * Returns the size of the TXFIFO message needed to send - * this packet. - */ -static unsigned int calc_txlen(unsigned int len) -{ - return ALIGN(len + 4, 4); -} - /** * ks8851_start_xmit_spi - transmit packet using SPI * @skb: The buffer to transmit @@ -386,16 +397,17 @@ static netdev_tx_t ks8851_start_xmit_spi(struct sk_buff *skb, spin_lock(&ks->statelock); - if (needed > ks->tx_space) { + if (ks->queued_len + needed > ks->tx_space) { netif_stop_queue(dev); ret = NETDEV_TX_BUSY; } else { - ks->tx_space -= needed; + ks->queued_len += needed; skb_queue_tail(&ks->txq, skb); } spin_unlock(&ks->statelock); - schedule_work(&kss->tx_work); + if (ret == NETDEV_TX_OK) + schedule_work(&kss->tx_work); return ret; } diff --git a/drivers/net/ethernet/microsoft/Kconfig b/drivers/net/ethernet/microsoft/Kconfig index 090e6b9832431..01eb7445ead95 100644 --- a/drivers/net/ethernet/microsoft/Kconfig +++ b/drivers/net/ethernet/microsoft/Kconfig @@ -20,6 +20,7 @@ config MICROSOFT_MANA depends on PCI_MSI && X86_64 depends on PCI_HYPERV select AUXILIARY_BUS + select PAGE_POOL 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/mscc/ocelot_stats.c b/drivers/net/ethernet/mscc/ocelot_stats.c index 5c55197c7327d..c018783757fb2 100644 --- a/drivers/net/ethernet/mscc/ocelot_stats.c +++ b/drivers/net/ethernet/mscc/ocelot_stats.c @@ -582,10 +582,10 @@ static void ocelot_port_rmon_stats_cb(struct ocelot *ocelot, int port, void *pri rmon_stats->hist_tx[0] = s[OCELOT_STAT_TX_64]; rmon_stats->hist_tx[1] = s[OCELOT_STAT_TX_65_127]; rmon_stats->hist_tx[2] = s[OCELOT_STAT_TX_128_255]; - rmon_stats->hist_tx[3] = s[OCELOT_STAT_TX_128_255]; - rmon_stats->hist_tx[4] = s[OCELOT_STAT_TX_256_511]; - rmon_stats->hist_tx[5] = s[OCELOT_STAT_TX_512_1023]; - rmon_stats->hist_tx[6] = s[OCELOT_STAT_TX_1024_1526]; + rmon_stats->hist_tx[3] = s[OCELOT_STAT_TX_256_511]; + rmon_stats->hist_tx[4] = s[OCELOT_STAT_TX_512_1023]; + rmon_stats->hist_tx[5] = s[OCELOT_STAT_TX_1024_1526]; + rmon_stats->hist_tx[6] = s[OCELOT_STAT_TX_1527_MAX]; } static void ocelot_port_pmac_rmon_stats_cb(struct ocelot *ocelot, int port, @@ -610,10 +610,10 @@ static void ocelot_port_pmac_rmon_stats_cb(struct ocelot *ocelot, int port, rmon_stats->hist_tx[0] = s[OCELOT_STAT_TX_PMAC_64]; rmon_stats->hist_tx[1] = s[OCELOT_STAT_TX_PMAC_65_127]; rmon_stats->hist_tx[2] = s[OCELOT_STAT_TX_PMAC_128_255]; - rmon_stats->hist_tx[3] = s[OCELOT_STAT_TX_PMAC_128_255]; - rmon_stats->hist_tx[4] = s[OCELOT_STAT_TX_PMAC_256_511]; - rmon_stats->hist_tx[5] = s[OCELOT_STAT_TX_PMAC_512_1023]; - rmon_stats->hist_tx[6] = s[OCELOT_STAT_TX_PMAC_1024_1526]; + rmon_stats->hist_tx[3] = s[OCELOT_STAT_TX_PMAC_256_511]; + rmon_stats->hist_tx[4] = s[OCELOT_STAT_TX_PMAC_512_1023]; + rmon_stats->hist_tx[5] = s[OCELOT_STAT_TX_PMAC_1024_1526]; + rmon_stats->hist_tx[6] = s[OCELOT_STAT_TX_PMAC_1527_MAX]; } void ocelot_port_get_rmon_stats(struct ocelot *ocelot, int port, diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c index 060a77f2265d9..e522845c7c211 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c +++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c @@ -160,6 +160,18 @@ struct nfp_tun_mac_addr_offload { u8 addr[ETH_ALEN]; }; +/** + * struct nfp_neigh_update_work - update neighbour information to nfp + * @work: Work queue for writing neigh to the nfp + * @n: neighbour entry + * @app: Back pointer to app + */ +struct nfp_neigh_update_work { + struct work_struct work; + struct neighbour *n; + struct nfp_app *app; +}; + enum nfp_flower_mac_offload_cmd { NFP_TUNNEL_MAC_OFFLOAD_ADD = 0, NFP_TUNNEL_MAC_OFFLOAD_DEL = 1, @@ -607,38 +619,30 @@ nfp_tun_write_neigh(struct net_device *netdev, struct nfp_app *app, nfp_flower_cmsg_warn(app, "Neighbour configuration failed.\n"); } -static int -nfp_tun_neigh_event_handler(struct notifier_block *nb, unsigned long event, - void *ptr) +static void +nfp_tun_release_neigh_update_work(struct nfp_neigh_update_work *update_work) { - struct nfp_flower_priv *app_priv; - struct netevent_redirect *redir; - struct neighbour *n; + neigh_release(update_work->n); + kfree(update_work); +} + +static void nfp_tun_neigh_update(struct work_struct *work) +{ + struct nfp_neigh_update_work *update_work; struct nfp_app *app; + struct neighbour *n; bool neigh_invalid; int err; - switch (event) { - case NETEVENT_REDIRECT: - redir = (struct netevent_redirect *)ptr; - n = redir->neigh; - break; - case NETEVENT_NEIGH_UPDATE: - n = (struct neighbour *)ptr; - break; - default: - return NOTIFY_DONE; - } - - neigh_invalid = !(n->nud_state & NUD_VALID) || n->dead; - - app_priv = container_of(nb, struct nfp_flower_priv, tun.neigh_nb); - app = app_priv->app; + update_work = container_of(work, struct nfp_neigh_update_work, work); + app = update_work->app; + n = update_work->n; if (!nfp_flower_get_port_id_from_netdev(app, n->dev)) - return NOTIFY_DONE; + goto out; #if IS_ENABLED(CONFIG_INET) + neigh_invalid = !(n->nud_state & NUD_VALID) || n->dead; if (n->tbl->family == AF_INET6) { #if IS_ENABLED(CONFIG_IPV6) struct flowi6 flow6 = {}; @@ -655,13 +659,11 @@ nfp_tun_neigh_event_handler(struct notifier_block *nb, unsigned long event, dst = ip6_dst_lookup_flow(dev_net(n->dev), NULL, &flow6, NULL); if (IS_ERR(dst)) - return NOTIFY_DONE; + goto out; dst_release(dst); } nfp_tun_write_neigh(n->dev, app, &flow6, n, true, false); -#else - return NOTIFY_DONE; #endif /* CONFIG_IPV6 */ } else { struct flowi4 flow4 = {}; @@ -678,17 +680,71 @@ nfp_tun_neigh_event_handler(struct notifier_block *nb, unsigned long event, rt = ip_route_output_key(dev_net(n->dev), &flow4); err = PTR_ERR_OR_ZERO(rt); if (err) - return NOTIFY_DONE; + goto out; ip_rt_put(rt); } nfp_tun_write_neigh(n->dev, app, &flow4, n, false, false); } -#else - return NOTIFY_DONE; #endif /* CONFIG_INET */ +out: + nfp_tun_release_neigh_update_work(update_work); +} - return NOTIFY_OK; +static struct nfp_neigh_update_work * +nfp_tun_alloc_neigh_update_work(struct nfp_app *app, struct neighbour *n) +{ + struct nfp_neigh_update_work *update_work; + + update_work = kzalloc(sizeof(*update_work), GFP_ATOMIC); + if (!update_work) + return NULL; + + INIT_WORK(&update_work->work, nfp_tun_neigh_update); + neigh_hold(n); + update_work->n = n; + update_work->app = app; + + return update_work; +} + +static int +nfp_tun_neigh_event_handler(struct notifier_block *nb, unsigned long event, + void *ptr) +{ + struct nfp_neigh_update_work *update_work; + struct nfp_flower_priv *app_priv; + struct netevent_redirect *redir; + struct neighbour *n; + struct nfp_app *app; + + switch (event) { + case NETEVENT_REDIRECT: + redir = (struct netevent_redirect *)ptr; + n = redir->neigh; + break; + case NETEVENT_NEIGH_UPDATE: + n = (struct neighbour *)ptr; + break; + default: + return NOTIFY_DONE; + } +#if IS_ENABLED(CONFIG_IPV6) + if (n->tbl != ipv6_stub->nd_tbl && n->tbl != &arp_tbl) +#else + if (n->tbl != &arp_tbl) +#endif + return NOTIFY_DONE; + + app_priv = container_of(nb, struct nfp_flower_priv, tun.neigh_nb); + app = app_priv->app; + update_work = nfp_tun_alloc_neigh_update_work(app, n); + if (!update_work) + return NOTIFY_DONE; + + queue_work(system_highpri_wq, &update_work->work); + + return NOTIFY_DONE; } void nfp_tunnel_request_route_v4(struct nfp_app *app, struct sk_buff *skb) @@ -706,6 +762,7 @@ void nfp_tunnel_request_route_v4(struct nfp_app *app, struct sk_buff *skb) netdev = nfp_app_dev_get(app, be32_to_cpu(payload->ingress_port), NULL); if (!netdev) goto fail_rcu_unlock; + dev_hold(netdev); flow.daddr = payload->ipv4_addr; flow.flowi4_proto = IPPROTO_UDP; @@ -725,13 +782,16 @@ void nfp_tunnel_request_route_v4(struct nfp_app *app, struct sk_buff *skb) ip_rt_put(rt); if (!n) goto fail_rcu_unlock; + rcu_read_unlock(); + nfp_tun_write_neigh(n->dev, app, &flow, n, false, true); neigh_release(n); - rcu_read_unlock(); + dev_put(netdev); return; fail_rcu_unlock: rcu_read_unlock(); + dev_put(netdev); nfp_flower_cmsg_warn(app, "Requested route not found.\n"); } @@ -749,6 +809,7 @@ void nfp_tunnel_request_route_v6(struct nfp_app *app, struct sk_buff *skb) netdev = nfp_app_dev_get(app, be32_to_cpu(payload->ingress_port), NULL); if (!netdev) goto fail_rcu_unlock; + dev_hold(netdev); flow.daddr = payload->ipv6_addr; flow.flowi6_proto = IPPROTO_UDP; @@ -766,14 +827,16 @@ void nfp_tunnel_request_route_v6(struct nfp_app *app, struct sk_buff *skb) dst_release(dst); if (!n) goto fail_rcu_unlock; + rcu_read_unlock(); nfp_tun_write_neigh(n->dev, app, &flow, n, true, true); neigh_release(n); - rcu_read_unlock(); + dev_put(netdev); return; fail_rcu_unlock: rcu_read_unlock(); + dev_put(netdev); nfp_flower_cmsg_warn(app, "Requested IPv6 route not found.\n"); } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.h b/drivers/net/ethernet/pensando/ionic/ionic_dev.h index aae4131f146a8..bd2d4a26f5438 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_dev.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.h @@ -222,7 +222,7 @@ struct ionic_desc_info { void *cb_arg; }; -#define IONIC_QUEUE_NAME_MAX_SZ 32 +#define IONIC_QUEUE_NAME_MAX_SZ 16 struct ionic_queue { struct device *dev; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 2c3e36b2dd7f2..c9bd2c57a37d2 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -49,24 +49,24 @@ static void ionic_lif_queue_identify(struct ionic_lif *lif); static void ionic_dim_work(struct work_struct *work) { struct dim *dim = container_of(work, struct dim, work); + struct ionic_intr_info *intr; struct dim_cq_moder cur_moder; struct ionic_qcq *qcq; + struct ionic_lif *lif; u32 new_coal; cur_moder = net_dim_get_rx_moderation(dim->mode, dim->profile_ix); qcq = container_of(dim, struct ionic_qcq, dim); - new_coal = ionic_coal_usec_to_hw(qcq->q.lif->ionic, cur_moder.usec); + lif = qcq->q.lif; + new_coal = ionic_coal_usec_to_hw(lif->ionic, cur_moder.usec); new_coal = new_coal ? new_coal : 1; - if (qcq->intr.dim_coal_hw != new_coal) { - unsigned int qi = qcq->cq.bound_q->index; - struct ionic_lif *lif = qcq->q.lif; - - qcq->intr.dim_coal_hw = new_coal; + intr = &qcq->intr; + if (intr->dim_coal_hw != new_coal) { + intr->dim_coal_hw = new_coal; ionic_intr_coal_init(lif->ionic->idev.intr_ctrl, - lif->rxqcqs[qi]->intr.index, - qcq->intr.dim_coal_hw); + intr->index, intr->dim_coal_hw); } dim->state = DIM_START_MEASURE; diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c index 65e20693c549e..33f4f58ee51c6 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c +++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c @@ -933,6 +933,7 @@ static void qed_ilt_shadow_free(struct qed_hwfn *p_hwfn) p_dma->virt_addr = NULL; } kfree(p_mngr->ilt_shadow); + p_mngr->ilt_shadow = NULL; } static int qed_ilt_blk_alloc(struct qed_hwfn *p_hwfn, diff --git a/drivers/net/ethernet/qualcomm/qca_debug.c b/drivers/net/ethernet/qualcomm/qca_debug.c index 6f2fa2a42770a..1822f2ad8f0dd 100644 --- a/drivers/net/ethernet/qualcomm/qca_debug.c +++ b/drivers/net/ethernet/qualcomm/qca_debug.c @@ -30,6 +30,8 @@ #define QCASPI_MAX_REGS 0x20 +#define QCASPI_RX_MAX_FRAMES 4 + static const u16 qcaspi_spi_regs[] = { SPI_REG_BFR_SIZE, SPI_REG_WRBUF_SPC_AVA, @@ -252,9 +254,9 @@ qcaspi_get_ringparam(struct net_device *dev, struct ethtool_ringparam *ring, { struct qcaspi *qca = netdev_priv(dev); - ring->rx_max_pending = 4; + ring->rx_max_pending = QCASPI_RX_MAX_FRAMES; ring->tx_max_pending = TX_RING_MAX_LEN; - ring->rx_pending = 4; + ring->rx_pending = QCASPI_RX_MAX_FRAMES; ring->tx_pending = qca->txr.count; } @@ -263,22 +265,21 @@ qcaspi_set_ringparam(struct net_device *dev, struct ethtool_ringparam *ring, struct kernel_ethtool_ringparam *kernel_ring, struct netlink_ext_ack *extack) { - const struct net_device_ops *ops = dev->netdev_ops; struct qcaspi *qca = netdev_priv(dev); - if ((ring->rx_pending) || + if (ring->rx_pending != QCASPI_RX_MAX_FRAMES || (ring->rx_mini_pending) || (ring->rx_jumbo_pending)) return -EINVAL; - if (netif_running(dev)) - ops->ndo_stop(dev); + if (qca->spi_thread) + kthread_park(qca->spi_thread); qca->txr.count = max_t(u32, ring->tx_pending, TX_RING_MIN_LEN); qca->txr.count = min_t(u16, qca->txr.count, TX_RING_MAX_LEN); - if (netif_running(dev)) - ops->ndo_open(dev); + if (qca->spi_thread) + kthread_unpark(qca->spi_thread); return 0; } diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c index bec723028e96c..5f3c11fb3fa27 100644 --- a/drivers/net/ethernet/qualcomm/qca_spi.c +++ b/drivers/net/ethernet/qualcomm/qca_spi.c @@ -580,6 +580,18 @@ qcaspi_spi_thread(void *data) netdev_info(qca->net_dev, "SPI thread created\n"); while (!kthread_should_stop()) { set_current_state(TASK_INTERRUPTIBLE); + if (kthread_should_park()) { + netif_tx_disable(qca->net_dev); + netif_carrier_off(qca->net_dev); + qcaspi_flush_tx_ring(qca); + kthread_parkme(); + if (qca->sync == QCASPI_SYNC_READY) { + netif_carrier_on(qca->net_dev); + netif_wake_queue(qca->net_dev); + } + continue; + } + if ((qca->intr_req == qca->intr_svc) && !qca->txr.skb[qca->txr.head]) schedule(); @@ -608,11 +620,17 @@ qcaspi_spi_thread(void *data) if (intr_cause & SPI_INT_CPU_ON) { qcaspi_qca7k_sync(qca, QCASPI_EVENT_CPUON); + /* Frame decoding in progress */ + if (qca->frm_handle.state != qca->frm_handle.init) + qca->net_dev->stats.rx_dropped++; + + qcafrm_fsm_init_spi(&qca->frm_handle); + qca->stats.device_reset++; + /* not synced. */ if (qca->sync != QCASPI_SYNC_READY) continue; - qca->stats.device_reset++; netif_wake_queue(qca->net_dev); netif_carrier_on(qca->net_dev); } diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 0c76c162b8a9f..bb787a52bc754 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -196,6 +196,7 @@ enum rtl_registers { /* No threshold before first PCI xfer */ #define RX_FIFO_THRESH (7 << RXCFG_FIFO_SHIFT) #define RX_EARLY_OFF (1 << 11) +#define RX_PAUSE_SLOT_ON (1 << 11) /* 8125b and later */ #define RXCFG_DMA_SHIFT 8 /* Unlimited maximum PCI burst. */ #define RX_DMA_BURST (7 << RXCFG_DMA_SHIFT) @@ -579,6 +580,7 @@ struct rtl8169_tc_offsets { enum rtl_flag { RTL_FLAG_TASK_ENABLED = 0, RTL_FLAG_TASK_RESET_PENDING, + RTL_FLAG_TASK_RESET_NO_QUEUE_WAKE, RTL_FLAG_TASK_TX_TIMEOUT, RTL_FLAG_MAX }; @@ -624,6 +626,7 @@ struct rtl8169_private { unsigned supports_gmii:1; unsigned aspm_manageable:1; + unsigned dash_enabled:1; dma_addr_t counters_phys_addr; struct rtl8169_counters *counters; struct rtl8169_tc_offsets tc_offset; @@ -1253,14 +1256,26 @@ static bool r8168ep_check_dash(struct rtl8169_private *tp) return r8168ep_ocp_read(tp, 0x128) & BIT(0); } -static enum rtl_dash_type rtl_check_dash(struct rtl8169_private *tp) +static bool rtl_dash_is_enabled(struct rtl8169_private *tp) +{ + switch (tp->dash_type) { + case RTL_DASH_DP: + return r8168dp_check_dash(tp); + case RTL_DASH_EP: + return r8168ep_check_dash(tp); + default: + return false; + } +} + +static enum rtl_dash_type rtl_get_dash_type(struct rtl8169_private *tp) { switch (tp->mac_version) { case RTL_GIGA_MAC_VER_28: case RTL_GIGA_MAC_VER_31: - return r8168dp_check_dash(tp) ? RTL_DASH_DP : RTL_DASH_NONE; + return RTL_DASH_DP; case RTL_GIGA_MAC_VER_51 ... RTL_GIGA_MAC_VER_53: - return r8168ep_check_dash(tp) ? RTL_DASH_EP : RTL_DASH_NONE; + return RTL_DASH_EP; default: return RTL_DASH_NONE; } @@ -1453,7 +1468,7 @@ static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts) device_set_wakeup_enable(tp_to_dev(tp), wolopts); - if (tp->dash_type == RTL_DASH_NONE) { + if (!tp->dash_enabled) { rtl_set_d3_pll_down(tp, !wolopts); tp->dev->wol_enabled = wolopts ? 1 : 0; } @@ -2292,9 +2307,13 @@ static void rtl_init_rxcfg(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_53: RTL_W32(tp, RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST | RX_EARLY_OFF); break; - case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_63: + case RTL_GIGA_MAC_VER_61: RTL_W32(tp, RxConfig, RX_FETCH_DFLT_8125 | RX_DMA_BURST); break; + case RTL_GIGA_MAC_VER_63: + RTL_W32(tp, RxConfig, RX_FETCH_DFLT_8125 | RX_DMA_BURST | + RX_PAUSE_SLOT_ON); + break; default: RTL_W32(tp, RxConfig, RX128_INT_EN | RX_DMA_BURST); break; @@ -2512,7 +2531,7 @@ static void rtl_wol_enable_rx(struct rtl8169_private *tp) static void rtl_prepare_power_down(struct rtl8169_private *tp) { - if (tp->dash_type != RTL_DASH_NONE) + if (tp->dash_enabled) return; if (tp->mac_version == RTL_GIGA_MAC_VER_32 || @@ -2586,9 +2605,7 @@ static void rtl_set_rx_mode(struct net_device *dev) rx_mode &= ~AcceptMulticast; } else if (netdev_mc_count(dev) > MC_FILTER_LIMIT || dev->flags & IFF_ALLMULTI || - tp->mac_version == RTL_GIGA_MAC_VER_35 || - tp->mac_version == RTL_GIGA_MAC_VER_46 || - tp->mac_version == RTL_GIGA_MAC_VER_48) { + tp->mac_version == RTL_GIGA_MAC_VER_35) { /* accept all multicasts */ } else if (netdev_mc_empty(dev)) { rx_mode &= ~AcceptMulticast; @@ -4571,6 +4588,8 @@ static void rtl_task(struct work_struct *work) reset: rtl_reset_work(tp); netif_wake_queue(tp->dev); + } else if (test_and_clear_bit(RTL_FLAG_TASK_RESET_NO_QUEUE_WAKE, tp->wk.flags)) { + rtl_reset_work(tp); } out_unlock: rtnl_unlock(); @@ -4604,7 +4623,7 @@ static void r8169_phylink_handler(struct net_device *ndev) } else { /* In few cases rx is broken after link-down otherwise */ if (rtl_is_8125(tp)) - rtl_reset_work(tp); + rtl_schedule_task(tp, RTL_FLAG_TASK_RESET_NO_QUEUE_WAKE); pm_runtime_idle(d); } @@ -4648,10 +4667,16 @@ static void rtl8169_down(struct rtl8169_private *tp) rtl8169_cleanup(tp); rtl_disable_exit_l1(tp); rtl_prepare_power_down(tp); + + if (tp->dash_type != RTL_DASH_NONE) + rtl8168_driver_stop(tp); } static void rtl8169_up(struct rtl8169_private *tp) { + if (tp->dash_type != RTL_DASH_NONE) + rtl8168_driver_start(tp); + pci_set_master(tp->pci_dev); phy_init_hw(tp->phydev); phy_resume(tp->phydev); @@ -4674,7 +4699,7 @@ static int rtl8169_close(struct net_device *dev) rtl8169_down(tp); rtl8169_rx_clear(tp); - cancel_work_sync(&tp->wk.work); + cancel_work(&tp->wk.work); free_irq(tp->irq, tp); @@ -4869,7 +4894,7 @@ static int rtl8169_runtime_idle(struct device *device) { struct rtl8169_private *tp = dev_get_drvdata(device); - if (tp->dash_type != RTL_DASH_NONE) + if (tp->dash_enabled) return -EBUSY; if (!netif_running(tp->dev) || !netif_carrier_ok(tp->dev)) @@ -4895,8 +4920,7 @@ static void rtl_shutdown(struct pci_dev *pdev) /* Restore original MAC address */ rtl_rar_set(tp, tp->dev->perm_addr); - if (system_state == SYSTEM_POWER_OFF && - tp->dash_type == RTL_DASH_NONE) { + if (system_state == SYSTEM_POWER_OFF && !tp->dash_enabled) { pci_wake_from_d3(pdev, tp->saved_wolopts); pci_set_power_state(pdev, PCI_D3hot); } @@ -4909,6 +4933,8 @@ static void rtl_remove_one(struct pci_dev *pdev) if (pci_dev_run_wake(pdev)) pm_runtime_get_noresume(&pdev->dev); + cancel_work_sync(&tp->wk.work); + unregister_netdev(tp->dev); if (tp->dash_type != RTL_DASH_NONE) @@ -5254,7 +5280,8 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) rc = pci_disable_link_state(pdev, PCIE_LINK_STATE_L1); tp->aspm_manageable = !rc; - tp->dash_type = rtl_check_dash(tp); + tp->dash_type = rtl_get_dash_type(tp); + tp->dash_enabled = rtl_dash_is_enabled(tp); tp->cp_cmd = RTL_R16(tp, CPlusCmd) & CPCMD_MASK; @@ -5325,7 +5352,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) /* configure chip for default features */ rtl8169_set_features(dev, dev->features); - if (tp->dash_type == RTL_DASH_NONE) { + if (!tp->dash_enabled) { rtl_set_d3_pll_down(tp, true); } else { rtl_set_d3_pll_down(tp, false); @@ -5365,7 +5392,8 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) "ok" : "ko"); if (tp->dash_type != RTL_DASH_NONE) { - netdev_info(dev, "DASH enabled\n"); + netdev_info(dev, "DASH %s\n", + tp->dash_enabled ? "enabled" : "disabled"); rtl8168_driver_start(tp); } diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 0ef0b88b71459..bb56cf4090423 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -515,6 +515,15 @@ static void ravb_emac_init_gbeth(struct net_device *ndev) { struct ravb_private *priv = netdev_priv(ndev); + if (priv->phy_interface == PHY_INTERFACE_MODE_MII) { + ravb_write(ndev, (1000 << 16) | CXR35_SEL_XMII_MII, CXR35); + ravb_modify(ndev, CXR31, CXR31_SEL_LINK0 | CXR31_SEL_LINK1, 0); + } else { + ravb_write(ndev, (1000 << 16) | CXR35_SEL_XMII_RGMII, CXR35); + ravb_modify(ndev, CXR31, CXR31_SEL_LINK0 | CXR31_SEL_LINK1, + CXR31_SEL_LINK0); + } + /* Receive frame limit set register */ ravb_write(ndev, GBETH_RX_BUFF_MAX + ETH_FCS_LEN, RFLR); @@ -537,14 +546,6 @@ static void ravb_emac_init_gbeth(struct net_device *ndev) /* E-MAC interrupt enable register */ ravb_write(ndev, ECSIPR_ICDIP, ECSIPR); - - if (priv->phy_interface == PHY_INTERFACE_MODE_MII) { - ravb_modify(ndev, CXR31, CXR31_SEL_LINK0 | CXR31_SEL_LINK1, 0); - ravb_write(ndev, (1000 << 16) | CXR35_SEL_XMII_MII, CXR35); - } else { - ravb_modify(ndev, CXR31, CXR31_SEL_LINK0 | CXR31_SEL_LINK1, - CXR31_SEL_LINK0); - } } static void ravb_emac_init_rcar(struct net_device *ndev) @@ -1811,19 +1812,20 @@ static int ravb_open(struct net_device *ndev) if (info->gptp) ravb_ptp_init(ndev, priv->pdev); - netif_tx_start_all_queues(ndev); - /* PHY control start */ error = ravb_phy_start(ndev); if (error) goto out_ptp_stop; + netif_tx_start_all_queues(ndev); + return 0; out_ptp_stop: /* Stop PTP Clock driver */ if (info->gptp) ravb_ptp_stop(ndev); + ravb_stop_dma(ndev); out_free_irq_mgmta: if (!info->multi_irqs) goto out_free_irq; @@ -1874,6 +1876,12 @@ static void ravb_tx_timeout_work(struct work_struct *work) struct net_device *ndev = priv->ndev; int error; + if (!rtnl_trylock()) { + usleep_range(1000, 2000); + schedule_work(&priv->work); + return; + } + netif_tx_stop_all_queues(ndev); /* Stop PTP Clock driver */ @@ -1907,7 +1915,7 @@ static void ravb_tx_timeout_work(struct work_struct *work) */ netdev_err(ndev, "%s: ravb_dmac_init() failed, error %d\n", __func__, error); - return; + goto out_unlock; } ravb_emac_init(ndev); @@ -1917,6 +1925,9 @@ static void ravb_tx_timeout_work(struct work_struct *work) ravb_ptp_init(ndev, priv->pdev); netif_tx_start_all_queues(ndev); + +out_unlock: + rtnl_unlock(); } /* Packet transmit function for Ethernet AVB */ @@ -2645,9 +2656,14 @@ static int ravb_probe(struct platform_device *pdev) ndev->features = info->net_features; ndev->hw_features = info->net_hw_features; - reset_control_deassert(rstc); + error = reset_control_deassert(rstc); + if (error) + goto out_free_netdev; + pm_runtime_enable(&pdev->dev); - pm_runtime_get_sync(&pdev->dev); + error = pm_runtime_resume_and_get(&pdev->dev); + if (error < 0) + goto out_rpm_disable; if (info->multi_irqs) { if (info->err_mgmt_irqs) @@ -2872,11 +2888,12 @@ static int ravb_probe(struct platform_device *pdev) out_disable_refclk: clk_disable_unprepare(priv->refclk); out_release: - free_netdev(ndev); - pm_runtime_put(&pdev->dev); +out_rpm_disable: pm_runtime_disable(&pdev->dev); reset_control_assert(rstc); +out_free_netdev: + free_netdev(ndev); return error; } @@ -2886,22 +2903,26 @@ static int ravb_remove(struct platform_device *pdev) struct ravb_private *priv = netdev_priv(ndev); const struct ravb_hw_info *info = priv->info; - /* Stop PTP Clock driver */ - if (info->ccc_gac) - ravb_ptp_stop(ndev); - - clk_disable_unprepare(priv->gptp_clk); - clk_disable_unprepare(priv->refclk); - - /* Set reset mode */ - ravb_write(ndev, CCC_OPC_RESET, CCC); unregister_netdev(ndev); if (info->nc_queues) netif_napi_del(&priv->napi[RAVB_NC]); netif_napi_del(&priv->napi[RAVB_BE]); + ravb_mdio_release(priv); + + /* Stop PTP Clock driver */ + if (info->ccc_gac) + ravb_ptp_stop(ndev); + dma_free_coherent(ndev->dev.parent, priv->desc_bat_size, priv->desc_bat, priv->desc_bat_dma); + + /* Set reset mode */ + ravb_write(ndev, CCC_OPC_RESET, CCC); + + clk_disable_unprepare(priv->gptp_clk); + clk_disable_unprepare(priv->refclk); + pm_runtime_put_sync(&pdev->dev); pm_runtime_disable(&pdev->dev); reset_control_assert(priv->rstc); diff --git a/drivers/net/ethernet/renesas/rswitch.c b/drivers/net/ethernet/renesas/rswitch.c index 0fc0b6bea7530..ae9d8722b76f7 100644 --- a/drivers/net/ethernet/renesas/rswitch.c +++ b/drivers/net/ethernet/renesas/rswitch.c @@ -1501,8 +1501,8 @@ static netdev_tx_t rswitch_start_xmit(struct sk_buff *skb, struct net_device *nd { struct rswitch_device *rdev = netdev_priv(ndev); struct rswitch_gwca_queue *gq = rdev->tx_queue; + netdev_tx_t ret = NETDEV_TX_OK; struct rswitch_ext_desc *desc; - int ret = NETDEV_TX_OK; dma_addr_t dma_addr; if (rswitch_get_num_cur_queues(gq) >= gq->ring_size - 1) { @@ -1514,10 +1514,8 @@ static netdev_tx_t rswitch_start_xmit(struct sk_buff *skb, struct net_device *nd return ret; dma_addr = dma_map_single(ndev->dev.parent, skb->data, skb->len, DMA_TO_DEVICE); - if (dma_mapping_error(ndev->dev.parent, dma_addr)) { - dev_kfree_skb_any(skb); - return ret; - } + if (dma_mapping_error(ndev->dev.parent, dma_addr)) + goto err_kfree; gq->skbs[gq->cur] = skb; desc = &gq->tx_ring[gq->cur]; @@ -1530,10 +1528,8 @@ static netdev_tx_t rswitch_start_xmit(struct sk_buff *skb, struct net_device *nd struct rswitch_gwca_ts_info *ts_info; ts_info = kzalloc(sizeof(*ts_info), GFP_ATOMIC); - if (!ts_info) { - dma_unmap_single(ndev->dev.parent, dma_addr, skb->len, DMA_TO_DEVICE); - return -ENOMEM; - } + if (!ts_info) + goto err_unmap; skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; rdev->ts_tag++; @@ -1555,6 +1551,14 @@ static netdev_tx_t rswitch_start_xmit(struct sk_buff *skb, struct net_device *nd gq->cur = rswitch_next_queue_index(gq, true, 1); rswitch_modify(rdev->addr, GWTRC(gq->index), 0, BIT(gq->index % 32)); + return ret; + +err_unmap: + dma_unmap_single(ndev->dev.parent, dma_addr, skb->len, DMA_TO_DEVICE); + +err_kfree: + dev_kfree_skb_any(skb); + return ret; } diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig index 06c6871f87886..25f2d42de406d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/Kconfig +++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig @@ -269,7 +269,7 @@ config DWMAC_INTEL config DWMAC_LOONGSON tristate "Loongson PCI DWMAC support" default MACH_LOONGSON64 - depends on STMMAC_ETH && PCI + depends on (MACH_LOONGSON64 || COMPILE_TEST) && STMMAC_ETH && PCI depends on COMMON_CLK help This selects the LOONGSON PCI bus support for the stmmac driver, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c index 2cd6fce5c9934..e7701326adc6a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c @@ -68,17 +68,15 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id if (!plat) return -ENOMEM; + plat->mdio_bus_data = devm_kzalloc(&pdev->dev, + sizeof(*plat->mdio_bus_data), + GFP_KERNEL); + if (!plat->mdio_bus_data) + return -ENOMEM; + plat->mdio_node = of_get_child_by_name(np, "mdio"); if (plat->mdio_node) { dev_info(&pdev->dev, "Found MDIO subnode\n"); - - plat->mdio_bus_data = devm_kzalloc(&pdev->dev, - sizeof(*plat->mdio_bus_data), - GFP_KERNEL); - if (!plat->mdio_bus_data) { - ret = -ENOMEM; - goto err_put_node; - } plat->mdio_bus_data->needs_reset = true; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c index d3bf42d0fceb6..31631e3f89d0a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c @@ -34,6 +34,7 @@ #define RGMII_CONFIG_LOOPBACK_EN BIT(2) #define RGMII_CONFIG_PROG_SWAP BIT(1) #define RGMII_CONFIG_DDR_MODE BIT(0) +#define RGMII_CONFIG_SGMII_CLK_DVDR GENMASK(18, 10) /* SDCC_HC_REG_DLL_CONFIG fields */ #define SDCC_DLL_CONFIG_DLL_RST BIT(30) @@ -78,6 +79,8 @@ #define ETHQOS_MAC_CTRL_SPEED_MODE BIT(14) #define ETHQOS_MAC_CTRL_PORT_SEL BIT(15) +#define SGMII_10M_RX_CLK_DVDR 0x31 + struct ethqos_emac_por { unsigned int offset; unsigned int value; @@ -598,6 +601,9 @@ static int ethqos_configure_rgmii(struct qcom_ethqos *ethqos) return 0; } +/* On interface toggle MAC registers gets reset. + * Configure MAC block for SGMII on ethernet phy link up + */ static int ethqos_configure_sgmii(struct qcom_ethqos *ethqos) { int val; @@ -617,6 +623,10 @@ static int ethqos_configure_sgmii(struct qcom_ethqos *ethqos) case SPEED_10: val |= ETHQOS_MAC_CTRL_PORT_SEL; val &= ~ETHQOS_MAC_CTRL_SPEED_MODE; + rgmii_updatel(ethqos, RGMII_CONFIG_SGMII_CLK_DVDR, + FIELD_PREP(RGMII_CONFIG_SGMII_CLK_DVDR, + SGMII_10M_RX_CLK_DVDR), + RGMII_IO_MACRO_CONFIG); break; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c index e95d35f1e5a0c..8fd167501fa0e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c @@ -710,28 +710,22 @@ void dwmac5_est_irq_status(void __iomem *ioaddr, struct net_device *dev, } } -void dwmac5_fpe_configure(void __iomem *ioaddr, u32 num_txq, u32 num_rxq, +void dwmac5_fpe_configure(void __iomem *ioaddr, struct stmmac_fpe_cfg *cfg, + u32 num_txq, u32 num_rxq, bool enable) { u32 value; - if (!enable) { - value = readl(ioaddr + MAC_FPE_CTRL_STS); - - value &= ~EFPE; - - writel(value, ioaddr + MAC_FPE_CTRL_STS); - return; + if (enable) { + cfg->fpe_csr = EFPE; + value = readl(ioaddr + GMAC_RXQ_CTRL1); + value &= ~GMAC_RXQCTRL_FPRQ; + value |= (num_rxq - 1) << GMAC_RXQCTRL_FPRQ_SHIFT; + writel(value, ioaddr + GMAC_RXQ_CTRL1); + } else { + cfg->fpe_csr = 0; } - - value = readl(ioaddr + GMAC_RXQ_CTRL1); - value &= ~GMAC_RXQCTRL_FPRQ; - value |= (num_rxq - 1) << GMAC_RXQCTRL_FPRQ_SHIFT; - writel(value, ioaddr + GMAC_RXQ_CTRL1); - - value = readl(ioaddr + MAC_FPE_CTRL_STS); - value |= EFPE; - writel(value, ioaddr + MAC_FPE_CTRL_STS); + writel(cfg->fpe_csr, ioaddr + MAC_FPE_CTRL_STS); } int dwmac5_fpe_irq_status(void __iomem *ioaddr, struct net_device *dev) @@ -741,6 +735,9 @@ int dwmac5_fpe_irq_status(void __iomem *ioaddr, struct net_device *dev) status = FPE_EVENT_UNKNOWN; + /* Reads from the MAC_FPE_CTRL_STS register should only be performed + * here, since the status flags of MAC_FPE_CTRL_STS are "clear on read" + */ value = readl(ioaddr + MAC_FPE_CTRL_STS); if (value & TRSP) { @@ -766,19 +763,15 @@ int dwmac5_fpe_irq_status(void __iomem *ioaddr, struct net_device *dev) return status; } -void dwmac5_fpe_send_mpacket(void __iomem *ioaddr, enum stmmac_mpacket_type type) +void dwmac5_fpe_send_mpacket(void __iomem *ioaddr, struct stmmac_fpe_cfg *cfg, + enum stmmac_mpacket_type type) { - u32 value; + u32 value = cfg->fpe_csr; - value = readl(ioaddr + MAC_FPE_CTRL_STS); - - if (type == MPACKET_VERIFY) { - value &= ~SRSP; + if (type == MPACKET_VERIFY) value |= SVER; - } else { - value &= ~SVER; + else if (type == MPACKET_RESPONSE) value |= SRSP; - } writel(value, ioaddr + MAC_FPE_CTRL_STS); } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.h b/drivers/net/ethernet/stmicro/stmmac/dwmac5.h index 53c138d0ff480..34e620790eb37 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.h @@ -153,9 +153,11 @@ int dwmac5_est_configure(void __iomem *ioaddr, struct stmmac_est *cfg, unsigned int ptp_rate); void dwmac5_est_irq_status(void __iomem *ioaddr, struct net_device *dev, struct stmmac_extra_stats *x, u32 txqcnt); -void dwmac5_fpe_configure(void __iomem *ioaddr, u32 num_txq, u32 num_rxq, +void dwmac5_fpe_configure(void __iomem *ioaddr, struct stmmac_fpe_cfg *cfg, + u32 num_txq, u32 num_rxq, bool enable); void dwmac5_fpe_send_mpacket(void __iomem *ioaddr, + struct stmmac_fpe_cfg *cfg, enum stmmac_mpacket_type type); int dwmac5_fpe_irq_status(void __iomem *ioaddr, struct net_device *dev); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c index 453e88b75be08..a74e71db79f94 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c @@ -1484,7 +1484,8 @@ static int dwxgmac3_est_configure(void __iomem *ioaddr, struct stmmac_est *cfg, return 0; } -static void dwxgmac3_fpe_configure(void __iomem *ioaddr, u32 num_txq, +static void dwxgmac3_fpe_configure(void __iomem *ioaddr, struct stmmac_fpe_cfg *cfg, + u32 num_txq, u32 num_rxq, bool enable) { u32 value; diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h index b95d3e1378136..68aa2d5ca6e56 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.h +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h @@ -412,9 +412,11 @@ struct stmmac_ops { unsigned int ptp_rate); void (*est_irq_status)(void __iomem *ioaddr, struct net_device *dev, struct stmmac_extra_stats *x, u32 txqcnt); - void (*fpe_configure)(void __iomem *ioaddr, u32 num_txq, u32 num_rxq, + void (*fpe_configure)(void __iomem *ioaddr, struct stmmac_fpe_cfg *cfg, + u32 num_txq, u32 num_rxq, bool enable); void (*fpe_send_mpacket)(void __iomem *ioaddr, + struct stmmac_fpe_cfg *cfg, enum stmmac_mpacket_type type); int (*fpe_irq_status)(void __iomem *ioaddr, struct net_device *dev); }; diff --git a/drivers/net/ethernet/stmicro/stmmac/mmc_core.c b/drivers/net/ethernet/stmicro/stmmac/mmc_core.c index ea4910ae0921a..6a7c1d325c464 100644 --- a/drivers/net/ethernet/stmicro/stmmac/mmc_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/mmc_core.c @@ -177,8 +177,10 @@ #define MMC_XGMAC_RX_DISCARD_OCT_GB 0x1b4 #define MMC_XGMAC_RX_ALIGN_ERR_PKT 0x1bc +#define MMC_XGMAC_TX_FPE_INTR_MASK 0x204 #define MMC_XGMAC_TX_FPE_FRAG 0x208 #define MMC_XGMAC_TX_HOLD_REQ 0x20c +#define MMC_XGMAC_RX_FPE_INTR_MASK 0x224 #define MMC_XGMAC_RX_PKT_ASSEMBLY_ERR 0x228 #define MMC_XGMAC_RX_PKT_SMD_ERR 0x22c #define MMC_XGMAC_RX_PKT_ASSEMBLY_OK 0x230 @@ -352,6 +354,8 @@ static void dwxgmac_mmc_intr_all_mask(void __iomem *mmcaddr) { writel(0x0, mmcaddr + MMC_RX_INTR_MASK); writel(0x0, mmcaddr + MMC_TX_INTR_MASK); + writel(MMC_DEFAULT_MASK, mmcaddr + MMC_XGMAC_TX_FPE_INTR_MASK); + writel(MMC_DEFAULT_MASK, mmcaddr + MMC_XGMAC_RX_FPE_INTR_MASK); writel(MMC_DEFAULT_MASK, mmcaddr + MMC_XGMAC_RX_IPC_INTR_MASK); } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c index 540f6a4ec0b81..f05bd757dfe52 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c @@ -237,7 +237,7 @@ static void timestamp_interrupt(struct stmmac_priv *priv) */ ts_status = readl(priv->ioaddr + GMAC_TIMESTAMP_STATUS); - if (priv->plat->flags & STMMAC_FLAG_EXT_SNAPSHOT_EN) + if (!(priv->plat->flags & STMMAC_FLAG_EXT_SNAPSHOT_EN)) return; num_snapshot = (ts_status & GMAC_TIMESTAMP_ATSNS_MASK) >> diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 5801f4d50f951..69b9c71f0eded 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -964,7 +964,8 @@ static void stmmac_fpe_link_state_handle(struct stmmac_priv *priv, bool is_up) bool *hs_enable = &fpe_cfg->hs_enable; if (is_up && *hs_enable) { - stmmac_fpe_send_mpacket(priv, priv->ioaddr, MPACKET_VERIFY); + stmmac_fpe_send_mpacket(priv, priv->ioaddr, fpe_cfg, + MPACKET_VERIFY); } else { *lo_state = FPE_STATE_OFF; *lp_state = FPE_STATE_OFF; @@ -5267,6 +5268,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) dma_dir = page_pool_get_dma_dir(rx_q->page_pool); buf_sz = DIV_ROUND_UP(priv->dma_conf.dma_buf_sz, PAGE_SIZE) * PAGE_SIZE; + limit = min(priv->dma_conf.dma_rx_size - 1, (unsigned int)limit); if (netif_msg_rx_status(priv)) { void *rx_head; @@ -5302,10 +5304,10 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) len = 0; } +read_again: if (count >= limit) break; -read_again: buf1_len = 0; buf2_len = 0; entry = next_entry; @@ -5802,6 +5804,7 @@ static void stmmac_fpe_event_status(struct stmmac_priv *priv, int status) /* If user has requested FPE enable, quickly response */ if (*hs_enable) stmmac_fpe_send_mpacket(priv, priv->ioaddr, + fpe_cfg, MPACKET_RESPONSE); } @@ -7226,6 +7229,7 @@ static void stmmac_fpe_lp_task(struct work_struct *work) if (*lo_state == FPE_STATE_ENTERING_ON && *lp_state == FPE_STATE_ENTERING_ON) { stmmac_fpe_configure(priv, priv->ioaddr, + fpe_cfg, priv->plat->tx_queues_to_use, priv->plat->rx_queues_to_use, *enable); @@ -7244,6 +7248,7 @@ static void stmmac_fpe_lp_task(struct work_struct *work) netdev_info(priv->dev, SEND_VERIFY_MPAKCET_FMT, *lo_state, *lp_state); stmmac_fpe_send_mpacket(priv, priv->ioaddr, + fpe_cfg, MPACKET_VERIFY); } /* Sleep then retry */ @@ -7258,6 +7263,7 @@ void stmmac_fpe_handshake(struct stmmac_priv *priv, bool enable) if (priv->plat->fpe_cfg->hs_enable != enable) { if (enable) { stmmac_fpe_send_mpacket(priv, priv->ioaddr, + priv->plat->fpe_cfg, MPACKET_VERIFY); } else { priv->plat->fpe_cfg->lo_fpe_state = FPE_STATE_OFF; @@ -7718,6 +7724,7 @@ int stmmac_suspend(struct device *dev) if (priv->dma_cap.fpesel) { /* Disable FPE */ stmmac_fpe_configure(priv, priv->ioaddr, + priv->plat->fpe_cfg, priv->plat->tx_queues_to_use, priv->plat->rx_queues_to_use, false); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c index fa9e7e7040b94..0542cfd1817e6 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c @@ -591,7 +591,11 @@ int stmmac_mdio_register(struct net_device *ndev) new_bus->parent = priv->device; err = of_mdiobus_register(new_bus, mdio_node); - if (err != 0) { + if (err == -ENODEV) { + err = 0; + dev_info(dev, "MDIO bus is disabled\n"); + goto bus_register_fail; + } else if (err) { dev_err_probe(dev, err, "Cannot register the MDIO bus\n"); goto bus_register_fail; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c index ac41ef4cbd2f0..6ad3e0a119366 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c @@ -1079,6 +1079,7 @@ static int tc_setup_taprio(struct stmmac_priv *priv, priv->plat->fpe_cfg->enable = false; stmmac_fpe_configure(priv, priv->ioaddr, + priv->plat->fpe_cfg, priv->plat->tx_queues_to_use, priv->plat->rx_queues_to_use, false); diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c index 4914d0ef58e9b..c09ecb3da7723 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c @@ -2050,7 +2050,7 @@ static int prueth_probe(struct platform_device *pdev) &prueth->shram); if (ret) { dev_err(dev, "unable to get PRUSS SHRD RAM2: %d\n", ret); - pruss_put(prueth->pruss); + goto put_pruss; } prueth->sram_pool = of_gen_pool_get(np, "sram", 0); @@ -2092,10 +2092,7 @@ static int prueth_probe(struct platform_device *pdev) prueth->iep1 = icss_iep_get_idx(np, 1); if (IS_ERR(prueth->iep1)) { ret = dev_err_probe(dev, PTR_ERR(prueth->iep1), "iep1 get failed\n"); - icss_iep_put(prueth->iep0); - prueth->iep0 = NULL; - prueth->iep1 = NULL; - goto free_pool; + goto put_iep0; } if (prueth->pdata.quirk_10m_link_issue) { @@ -2185,6 +2182,12 @@ static int prueth_probe(struct platform_device *pdev) exit_iep: if (prueth->pdata.quirk_10m_link_issue) icss_iep_exit_fw(prueth->iep1); + icss_iep_put(prueth->iep1); + +put_iep0: + icss_iep_put(prueth->iep0); + prueth->iep0 = NULL; + prueth->iep1 = NULL; free_pool: gen_pool_free(prueth->sram_pool, @@ -2192,6 +2195,8 @@ static int prueth_probe(struct platform_device *pdev) put_mem: pruss_release_mem_region(prueth->pruss, &prueth->shram); + +put_pruss: pruss_put(prueth->pruss); put_cores: diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.c b/drivers/net/ethernet/wangxun/libwx/wx_hw.c index 85dc16faca544..52130df26aee5 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_hw.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.c @@ -1677,10 +1677,12 @@ int wx_sw_init(struct wx *wx) wx->subsystem_device_id = pdev->subsystem_device; } else { err = wx_flash_read_dword(wx, 0xfffdc, &ssid); - if (!err) - wx->subsystem_device_id = swab16((u16)ssid); + if (err < 0) { + wx_err(wx, "read of internal subsystem device id failed\n"); + return err; + } - return err; + wx->subsystem_device_id = swab16((u16)ssid); } wx->mac_table = kcalloc(wx->mac.num_rar_entries, diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_lib.c index e04d4a5eed7ba..21505920136c6 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_lib.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.c @@ -1965,11 +1965,11 @@ void wx_reset_interrupt_capability(struct wx *wx) if (!pdev->msi_enabled && !pdev->msix_enabled) return; - pci_free_irq_vectors(wx->pdev); if (pdev->msix_enabled) { kfree(wx->msix_entries); wx->msix_entries = NULL; } + pci_free_irq_vectors(wx->pdev); } EXPORT_SYMBOL(wx_reset_interrupt_capability); diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c index 2b431db6085a6..a4d63d2f3c5bb 100644 --- a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c +++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c @@ -121,10 +121,8 @@ static int ngbe_sw_init(struct wx *wx) /* PCI config space info */ err = wx_sw_init(wx); - if (err < 0) { - wx_err(wx, "read of internal subsystem device id failed\n"); + if (err < 0) return err; - } /* mac type, phy type , oem type */ ngbe_init_type_code(wx); diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c index 5c3aed516ac20..d60c26ba0ba4c 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c @@ -362,10 +362,8 @@ static int txgbe_sw_init(struct wx *wx) /* PCI config space info */ err = wx_sw_init(wx); - if (err < 0) { - wx_err(wx, "read of internal subsystem device id failed\n"); + if (err < 0) return err; - } txgbe_init_type_code(wx); diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index b7ec4dafae90c..3297aff969c80 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -822,7 +822,7 @@ axienet_start_xmit(struct sk_buff *skb, struct net_device *ndev) if (lp->features & XAE_FEATURE_FULL_TX_CSUM) { /* Tx Full Checksum Offload Enabled */ cur_p->app0 |= 2; - } else if (lp->features & XAE_FEATURE_PARTIAL_RX_CSUM) { + } else if (lp->features & XAE_FEATURE_PARTIAL_TX_CSUM) { csum_start_off = skb_transport_offset(skb); csum_index_off = csum_start_off + skb->csum_offset; /* Tx Partial Checksum Offload Enabled */ diff --git a/drivers/net/hyperv/Kconfig b/drivers/net/hyperv/Kconfig index ca7bf7f897d36..c8cbd85adcf99 100644 --- a/drivers/net/hyperv/Kconfig +++ b/drivers/net/hyperv/Kconfig @@ -3,5 +3,6 @@ config HYPERV_NET tristate "Microsoft Hyper-V virtual network driver" depends on HYPERV select UCS2_STRING + select NLS help Select this option to enable the Hyper-V virtual network driver. diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 3ba3c8fb28a5d..706ea5263e879 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -2206,9 +2206,6 @@ static int netvsc_vf_join(struct net_device *vf_netdev, goto upper_link_failed; } - /* set slave flag before open to prevent IPv6 addrconf */ - vf_netdev->flags |= IFF_SLAVE; - schedule_delayed_work(&ndev_ctx->vf_takeover, VF_TAKEOVER_INT); call_netdevice_notifiers(NETDEV_JOIN, vf_netdev); @@ -2315,16 +2312,18 @@ static struct net_device *get_netvsc_byslot(const struct net_device *vf_netdev) } - /* Fallback path to check synthetic vf with - * help of mac addr + /* Fallback path to check synthetic vf with help of mac addr. + * Because this function can be called before vf_netdev is + * initialized (NETDEV_POST_INIT) when its perm_addr has not been copied + * from dev_addr, also try to match to its dev_addr. + * Note: On Hyper-V and Azure, it's not possible to set a MAC address + * on a VF that matches to the MAC of a unrelated NETVSC device. */ list_for_each_entry(ndev_ctx, &netvsc_dev_list, list) { ndev = hv_get_drvdata(ndev_ctx->device_ctx); - if (ether_addr_equal(vf_netdev->perm_addr, ndev->perm_addr)) { - netdev_notice(vf_netdev, - "falling back to mac addr based matching\n"); + if (ether_addr_equal(vf_netdev->perm_addr, ndev->perm_addr) || + ether_addr_equal(vf_netdev->dev_addr, ndev->perm_addr)) return ndev; - } } netdev_notice(vf_netdev, @@ -2332,6 +2331,19 @@ static struct net_device *get_netvsc_byslot(const struct net_device *vf_netdev) return NULL; } +static int netvsc_prepare_bonding(struct net_device *vf_netdev) +{ + struct net_device *ndev; + + ndev = get_netvsc_byslot(vf_netdev); + if (!ndev) + return NOTIFY_DONE; + + /* set slave flag before open to prevent IPv6 addrconf */ + vf_netdev->flags |= IFF_SLAVE; + return NOTIFY_DONE; +} + static int netvsc_register_vf(struct net_device *vf_netdev) { struct net_device_context *net_device_ctx; @@ -2531,15 +2543,6 @@ static int netvsc_probe(struct hv_device *dev, goto devinfo_failed; } - nvdev = rndis_filter_device_add(dev, device_info); - if (IS_ERR(nvdev)) { - ret = PTR_ERR(nvdev); - netdev_err(net, "unable to add netvsc device (ret %d)\n", ret); - goto rndis_failed; - } - - eth_hw_addr_set(net, device_info->mac_adr); - /* We must get rtnl lock before scheduling nvdev->subchan_work, * otherwise netvsc_subchan_work() can get rtnl lock first and wait * all subchannels to show up, but that may not happen because @@ -2547,9 +2550,23 @@ static int netvsc_probe(struct hv_device *dev, * -> ... -> device_add() -> ... -> __device_attach() can't get * the device lock, so all the subchannels can't be processed -- * finally netvsc_subchan_work() hangs forever. + * + * The rtnl lock also needs to be held before rndis_filter_device_add() + * which advertises nvsp_2_vsc_capability / sriov bit, and triggers + * VF NIC offering and registering. If VF NIC finished register_netdev() + * earlier it may cause name based config failure. */ rtnl_lock(); + nvdev = rndis_filter_device_add(dev, device_info); + if (IS_ERR(nvdev)) { + ret = PTR_ERR(nvdev); + netdev_err(net, "unable to add netvsc device (ret %d)\n", ret); + goto rndis_failed; + } + + eth_hw_addr_set(net, device_info->mac_adr); + if (nvdev->num_chn > 1) schedule_work(&nvdev->subchan_work); @@ -2586,9 +2603,9 @@ static int netvsc_probe(struct hv_device *dev, return 0; register_failed: - rtnl_unlock(); rndis_filter_device_remove(dev, nvdev); rndis_failed: + rtnl_unlock(); netvsc_devinfo_put(device_info); devinfo_failed: free_percpu(net_device_ctx->vf_stats); @@ -2753,6 +2770,8 @@ static int netvsc_netdev_event(struct notifier_block *this, return NOTIFY_DONE; switch (event) { + case NETDEV_POST_INIT: + return netvsc_prepare_bonding(event_dev); case NETDEV_REGISTER: return netvsc_register_vf(event_dev); case NETDEV_UNREGISTER: @@ -2788,12 +2807,17 @@ static int __init netvsc_drv_init(void) } netvsc_ring_bytes = ring_size * PAGE_SIZE; + register_netdevice_notifier(&netvsc_netdev_notifier); + ret = vmbus_driver_register(&netvsc_drv); if (ret) - return ret; + goto err_vmbus_reg; - register_netdevice_notifier(&netvsc_netdev_notifier); return 0; + +err_vmbus_reg: + unregister_netdevice_notifier(&netvsc_netdev_notifier); + return ret; } MODULE_LICENSE("GPL"); diff --git a/drivers/net/ipa/reg/gsi_reg-v5.0.c b/drivers/net/ipa/reg/gsi_reg-v5.0.c index d7b81a36d673b..145eb0bd096d6 100644 --- a/drivers/net/ipa/reg/gsi_reg-v5.0.c +++ b/drivers/net/ipa/reg/gsi_reg-v5.0.c @@ -78,7 +78,7 @@ REG_STRIDE_FIELDS(EV_CH_E_CNTXT_0, ev_ch_e_cntxt_0, 0x0001c000 + 0x12000 * GSI_EE_AP, 0x80); static const u32 reg_ev_ch_e_cntxt_1_fmask[] = { - [R_LENGTH] = GENMASK(19, 0), + [R_LENGTH] = GENMASK(23, 0), }; REG_STRIDE_FIELDS(EV_CH_E_CNTXT_1, ev_ch_e_cntxt_1, diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index 21e9cac731218..2d5b021b4ea60 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -411,7 +411,7 @@ struct ipvl_addr *ipvlan_addr_lookup(struct ipvl_port *port, void *lyr3h, return addr; } -static int ipvlan_process_v4_outbound(struct sk_buff *skb) +static noinline_for_stack int ipvlan_process_v4_outbound(struct sk_buff *skb) { const struct iphdr *ip4h = ip_hdr(skb); struct net_device *dev = skb->dev; @@ -453,13 +453,11 @@ static int ipvlan_process_v4_outbound(struct sk_buff *skb) } #if IS_ENABLED(CONFIG_IPV6) -static int ipvlan_process_v6_outbound(struct sk_buff *skb) + +static noinline_for_stack int +ipvlan_route_v6_outbound(struct net_device *dev, struct sk_buff *skb) { const struct ipv6hdr *ip6h = ipv6_hdr(skb); - struct net_device *dev = skb->dev; - struct net *net = dev_net(dev); - struct dst_entry *dst; - int err, ret = NET_XMIT_DROP; struct flowi6 fl6 = { .flowi6_oif = dev->ifindex, .daddr = ip6h->daddr, @@ -469,27 +467,38 @@ static int ipvlan_process_v6_outbound(struct sk_buff *skb) .flowi6_mark = skb->mark, .flowi6_proto = ip6h->nexthdr, }; + struct dst_entry *dst; + int err; - dst = ip6_route_output(net, NULL, &fl6); - if (dst->error) { - ret = dst->error; + dst = ip6_route_output(dev_net(dev), NULL, &fl6); + err = dst->error; + if (err) { dst_release(dst); - goto err; + return err; } skb_dst_set(skb, dst); + return 0; +} + +static int ipvlan_process_v6_outbound(struct sk_buff *skb) +{ + struct net_device *dev = skb->dev; + int err, ret = NET_XMIT_DROP; + + err = ipvlan_route_v6_outbound(dev, skb); + if (unlikely(err)) { + DEV_STATS_INC(dev, tx_errors); + kfree_skb(skb); + return err; + } memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); - err = ip6_local_out(net, skb->sk, skb); + err = ip6_local_out(dev_net(dev), skb->sk, skb); if (unlikely(net_xmit_eval(err))) DEV_STATS_INC(dev, tx_errors); else ret = NET_XMIT_SUCCESS; - goto out; -err: - DEV_STATS_INC(dev, tx_errors); - kfree_skb(skb); -out: return ret; } #else diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 02bd201bc7e58..c8da94af4161a 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -780,7 +780,7 @@ static void macvlan_change_rx_flags(struct net_device *dev, int change) if (dev->flags & IFF_UP) { if (change & IFF_ALLMULTI) dev_set_allmulti(lowerdev, dev->flags & IFF_ALLMULTI ? 1 : -1); - if (change & IFF_PROMISC) + if (!macvlan_passthru(vlan->port) && change & IFF_PROMISC) dev_set_promiscuity(lowerdev, dev->flags & IFF_PROMISC ? 1 : -1); diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c index f60eb97e3a627..608953d4f98da 100644 --- a/drivers/net/netdevsim/bpf.c +++ b/drivers/net/netdevsim/bpf.c @@ -93,7 +93,7 @@ static void nsim_prog_set_loaded(struct bpf_prog *prog, bool loaded) { struct nsim_bpf_bound_prog *state; - if (!prog || !prog->aux->offload) + if (!prog || !bpf_prog_is_offloaded(prog->aux)) return; state = prog->aux->offload->dev_priv; @@ -311,7 +311,7 @@ nsim_setup_prog_hw_checks(struct netdevsim *ns, struct netdev_bpf *bpf) if (!bpf->prog) return 0; - if (!bpf->prog->aux->offload) { + if (!bpf_prog_is_offloaded(bpf->prog->aux)) { NSIM_EA(bpf->extack, "xdpoffload of non-bound program"); return -EINVAL; } diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 2ce74593d6e4a..a42df2c1bd043 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1548,7 +1548,8 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, goto error; phy_resume(phydev); - phy_led_triggers_register(phydev); + if (!phydev->is_on_sfp_module) + phy_led_triggers_register(phydev); /** * If the external phy used by current mac interface is managed by @@ -1817,7 +1818,8 @@ void phy_detach(struct phy_device *phydev) } phydev->phylink = NULL; - phy_led_triggers_unregister(phydev); + if (!phydev->is_on_sfp_module) + phy_led_triggers_unregister(phydev); if (phydev->mdio.dev.driver) module_put(phydev->mdio.dev.driver->owner); diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 0d7354955d626..b5f012619e42d 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -1631,6 +1631,7 @@ struct phylink *phylink_create(struct phylink_config *config, pl->config = config; if (config->type == PHYLINK_NETDEV) { pl->netdev = to_net_dev(config->dev); + netif_carrier_off(pl->netdev); } else if (config->type == PHYLINK_DEV) { pl->dev = config->dev; } else { diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index 4ecfac2278651..3679a43f4eb02 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -452,6 +452,11 @@ static const struct sfp_quirk sfp_quirks[] = { // Rollball protocol to talk to the PHY. SFP_QUIRK_F("FS", "SFP-10G-T", sfp_fixup_fs_10gt), + // Fiberstore GPON-ONU-34-20BI can operate at 2500base-X, but report 1.2GBd + // NRZ in their EEPROM + SFP_QUIRK("FS", "GPON-ONU-34-20BI", sfp_quirk_2500basex, + sfp_fixup_ignore_tx_fault), + SFP_QUIRK_F("HALNy", "HL-GSFP", sfp_fixup_halny_gsfp), // HG MXPD-483II-F 2.5G supports 2500Base-X, but incorrectly reports @@ -463,6 +468,9 @@ static const struct sfp_quirk sfp_quirks[] = { SFP_QUIRK("HUAWEI", "MA5671A", sfp_quirk_2500basex, sfp_fixup_ignore_tx_fault), + // FS 2.5G Base-T + SFP_QUIRK_M("FS", "SFP-2.5G-T", sfp_quirk_oem_2_5g), + // Lantech 8330-262D-E can operate at 2500base-X, but incorrectly report // 2500MBd NRZ in their EEPROM SFP_QUIRK_M("Lantech", "8330-262D-E", sfp_quirk_2500basex), diff --git a/drivers/net/ppp/ppp_synctty.c b/drivers/net/ppp/ppp_synctty.c index ebcdffdf4f0e0..52d05ce4a2819 100644 --- a/drivers/net/ppp/ppp_synctty.c +++ b/drivers/net/ppp/ppp_synctty.c @@ -453,6 +453,10 @@ ppp_sync_ioctl(struct ppp_channel *chan, unsigned int cmd, unsigned long arg) case PPPIOCSMRU: if (get_user(val, (int __user *) argp)) break; + if (val > U16_MAX) { + err = -EINVAL; + break; + } if (val < PPP_MRU) val = PPP_MRU; ap->mru = val; @@ -687,7 +691,7 @@ ppp_sync_input(struct syncppp *ap, const u8 *buf, const u8 *flags, int count) /* strip address/control field if present */ p = skb->data; - if (p[0] == PPP_ALLSTATIONS && p[1] == PPP_UI) { + if (skb->len >= 2 && p[0] == PPP_ALLSTATIONS && p[1] == PPP_UI) { /* chop off address/control */ if (skb->len < 3) goto err; diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 508d9a392ab18..f575f225d4178 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -281,8 +281,10 @@ static int __team_options_register(struct team *team, return 0; inst_rollback: - for (i--; i >= 0; i--) + for (i--; i >= 0; i--) { __team_option_inst_del_option(team, dst_opts[i]); + list_del(&dst_opts[i]->list); + } i = option_count; alloc_rollback: diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c index a017e9de2119d..7b8afa589a53c 100644 --- a/drivers/net/usb/aqc111.c +++ b/drivers/net/usb/aqc111.c @@ -1079,17 +1079,17 @@ static int aqc111_rx_fixup(struct usbnet *dev, struct sk_buff *skb) u16 pkt_count = 0; u64 desc_hdr = 0; u16 vlan_tag = 0; - u32 skb_len = 0; + u32 skb_len; if (!skb) goto err; - if (skb->len == 0) + skb_len = skb->len; + if (skb_len < sizeof(desc_hdr)) goto err; - skb_len = skb->len; /* RX Descriptor Header */ - skb_trim(skb, skb->len - sizeof(desc_hdr)); + skb_trim(skb, skb_len - sizeof(desc_hdr)); desc_hdr = le64_to_cpup((u64 *)skb_tail_pointer(skb)); /* Check these packets */ diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index aff39bf3161de..5a1bf42ce1566 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -173,6 +173,7 @@ struct ax88179_data { u8 in_pm; u32 wol_supported; u32 wolopts; + u8 disconnecting; }; struct ax88179_int_data { @@ -208,6 +209,7 @@ static int __ax88179_read_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index, { int ret; int (*fn)(struct usbnet *, u8, u8, u16, u16, void *, u16); + struct ax88179_data *ax179_data = dev->driver_priv; BUG_ON(!dev); @@ -219,7 +221,7 @@ static int __ax88179_read_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index, ret = fn(dev, cmd, USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE, value, index, data, size); - if (unlikely(ret < 0)) + if (unlikely((ret < 0) && !(ret == -ENODEV && ax179_data->disconnecting))) netdev_warn(dev->net, "Failed to read reg index 0x%04x: %d\n", index, ret); @@ -231,6 +233,7 @@ static int __ax88179_write_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index, { int ret; int (*fn)(struct usbnet *, u8, u8, u16, u16, const void *, u16); + struct ax88179_data *ax179_data = dev->driver_priv; BUG_ON(!dev); @@ -242,7 +245,7 @@ static int __ax88179_write_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index, ret = fn(dev, cmd, USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE, value, index, data, size); - if (unlikely(ret < 0)) + if (unlikely((ret < 0) && !(ret == -ENODEV && ax179_data->disconnecting))) netdev_warn(dev->net, "Failed to write reg index 0x%04x: %d\n", index, ret); @@ -492,6 +495,20 @@ static int ax88179_resume(struct usb_interface *intf) return usbnet_resume(intf); } +static void ax88179_disconnect(struct usb_interface *intf) +{ + struct usbnet *dev = usb_get_intfdata(intf); + struct ax88179_data *ax179_data; + + if (!dev) + return; + + ax179_data = dev->driver_priv; + ax179_data->disconnecting = 1; + + usbnet_disconnect(intf); +} + static void ax88179_get_wol(struct net_device *net, struct ethtool_wolinfo *wolinfo) { @@ -1583,11 +1600,11 @@ static int ax88179_reset(struct usbnet *dev) *tmp16 = AX_PHYPWR_RSTCTL_IPRL; ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_PHYPWR_RSTCTL, 2, 2, tmp16); - msleep(200); + msleep(500); *tmp = AX_CLK_SELECT_ACS | AX_CLK_SELECT_BCS; ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_CLK_SELECT, 1, 1, tmp); - msleep(100); + msleep(200); /* Ethernet PHY Auto Detach*/ ax88179_auto_detach(dev); @@ -1906,7 +1923,7 @@ static struct usb_driver ax88179_178a_driver = { .suspend = ax88179_suspend, .resume = ax88179_resume, .reset_resume = ax88179_resume, - .disconnect = usbnet_disconnect, + .disconnect = ax88179_disconnect, .supports_autosuspend = 1, .disable_hub_initiated_lpm = 1, }; diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 344af3c5c8366..e2e181378f412 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1289,6 +1289,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x19d2, 0x0168, 4)}, {QMI_FIXED_INTF(0x19d2, 0x0176, 3)}, {QMI_FIXED_INTF(0x19d2, 0x0178, 3)}, + {QMI_FIXED_INTF(0x19d2, 0x0189, 4)}, /* ZTE MF290 */ {QMI_FIXED_INTF(0x19d2, 0x0191, 4)}, /* ZTE EuFi890 */ {QMI_FIXED_INTF(0x19d2, 0x0199, 1)}, /* ZTE MF820S */ {QMI_FIXED_INTF(0x19d2, 0x0200, 1)}, diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index be18d72cefcce..127b34dcc5b37 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -2967,6 +2967,8 @@ static void rtl8152_nic_reset(struct r8152 *tp) ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CR, CR_RST); for (i = 0; i < 1000; i++) { + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) + break; if (!(ocp_read_byte(tp, MCU_TYPE_PLA, PLA_CR) & CR_RST)) break; usleep_range(100, 400); @@ -3296,6 +3298,8 @@ static void rtl_disable(struct r8152 *tp) rxdy_gated_en(tp, true); for (i = 0; i < 1000; i++) { + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) + break; ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL); if ((ocp_data & FIFO_EMPTY) == FIFO_EMPTY) break; @@ -3303,6 +3307,8 @@ static void rtl_disable(struct r8152 *tp) } for (i = 0; i < 1000; i++) { + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) + break; if (ocp_read_word(tp, MCU_TYPE_PLA, PLA_TCR0) & TCR0_TX_EMPTY) break; usleep_range(1000, 2000); @@ -5466,6 +5472,8 @@ static void wait_oob_link_list_ready(struct r8152 *tp) int i; for (i = 0; i < 1000; i++) { + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) + break; ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL); if (ocp_data & LINK_LIST_READY) break; @@ -5480,6 +5488,8 @@ static void r8156b_wait_loading_flash(struct r8152 *tp) int i; for (i = 0; i < 100; i++) { + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) + break; if (ocp_read_word(tp, MCU_TYPE_USB, USB_GPHY_CTRL) & GPHY_PATCH_DONE) break; usleep_range(1000, 2000); @@ -5602,6 +5612,8 @@ static int r8153_pre_firmware_1(struct r8152 *tp) for (i = 0; i < 104; i++) { u32 ocp_data = ocp_read_byte(tp, MCU_TYPE_USB, USB_WDT1_CTRL); + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) + return -ENODEV; if (!(ocp_data & WTD1_EN)) break; usleep_range(1000, 2000); @@ -5758,6 +5770,8 @@ static void r8153_aldps_en(struct r8152 *tp, bool enable) data &= ~EN_ALDPS; ocp_reg_write(tp, OCP_POWER_CFG, data); for (i = 0; i < 20; i++) { + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) + return; usleep_range(1000, 2000); if (ocp_read_word(tp, MCU_TYPE_PLA, 0xe000) & 0x0100) break; @@ -8364,6 +8378,8 @@ static int rtl8152_pre_reset(struct usb_interface *intf) struct r8152 *tp = usb_get_intfdata(intf); struct net_device *netdev; + rtnl_lock(); + if (!tp || !test_bit(PROBED_WITH_NO_ERRORS, &tp->flags)) return 0; @@ -8395,20 +8411,17 @@ static int rtl8152_post_reset(struct usb_interface *intf) struct sockaddr sa; if (!tp || !test_bit(PROBED_WITH_NO_ERRORS, &tp->flags)) - return 0; + goto exit; rtl_set_accessible(tp); /* reset the MAC address in case of policy change */ - if (determine_ethernet_addr(tp, &sa) >= 0) { - rtnl_lock(); + if (determine_ethernet_addr(tp, &sa) >= 0) dev_set_mac_address (tp->netdev, &sa, NULL); - rtnl_unlock(); - } netdev = tp->netdev; if (!netif_running(netdev)) - return 0; + goto exit; set_bit(WORK_ENABLE, &tp->flags); if (netif_carrier_ok(netdev)) { @@ -8427,6 +8440,8 @@ static int rtl8152_post_reset(struct usb_interface *intf) if (!list_empty(&tp->rx_done)) napi_schedule(&tp->napi); +exit: + rtnl_unlock(); return 0; } @@ -10001,6 +10016,7 @@ static const struct usb_device_id rtl8152_table[] = { { USB_DEVICE(VENDOR_ID_NVIDIA, 0x09ff) }, { USB_DEVICE(VENDOR_ID_TPLINK, 0x0601) }, { USB_DEVICE(VENDOR_ID_DLINK, 0xb301) }, + { USB_DEVICE(VENDOR_ID_ASUS, 0x1976) }, {} }; diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 0deefd1573cf2..0f798bcbe25cd 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -236,8 +236,8 @@ static void veth_get_ethtool_stats(struct net_device *dev, data[tx_idx + j] += *(u64 *)(base + offset); } } while (u64_stats_fetch_retry(&rq_stats->syncp, start)); - pp_idx = tx_idx + VETH_TQ_STATS_LEN; } + pp_idx = idx + dev->real_num_tx_queues * VETH_TQ_STATS_LEN; page_pool_stats: veth_get_page_pool_stats(dev, &data[pp_idx]); @@ -373,7 +373,7 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev) skb_tx_timestamp(skb); if (likely(veth_forward_skb(rcv, skb, rq, use_napi) == NET_RX_SUCCESS)) { if (!use_napi) - dev_lstats_add(dev, length); + dev_sw_netstats_tx_add(dev, 1, length); else __veth_xdp_flush(rq); } else { @@ -387,14 +387,6 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev) return ret; } -static u64 veth_stats_tx(struct net_device *dev, u64 *packets, u64 *bytes) -{ - struct veth_priv *priv = netdev_priv(dev); - - dev_lstats_read(dev, packets, bytes); - return atomic64_read(&priv->dropped); -} - static void veth_stats_rx(struct veth_stats *result, struct net_device *dev) { struct veth_priv *priv = netdev_priv(dev); @@ -432,24 +424,24 @@ static void veth_get_stats64(struct net_device *dev, struct veth_priv *priv = netdev_priv(dev); struct net_device *peer; struct veth_stats rx; - u64 packets, bytes; - tot->tx_dropped = veth_stats_tx(dev, &packets, &bytes); - tot->tx_bytes = bytes; - tot->tx_packets = packets; + tot->tx_dropped = atomic64_read(&priv->dropped); + dev_fetch_sw_netstats(tot, dev->tstats); veth_stats_rx(&rx, dev); tot->tx_dropped += rx.xdp_tx_err; tot->rx_dropped = rx.rx_drops + rx.peer_tq_xdp_xmit_err; - tot->rx_bytes = rx.xdp_bytes; - tot->rx_packets = rx.xdp_packets; + tot->rx_bytes += rx.xdp_bytes; + tot->rx_packets += rx.xdp_packets; rcu_read_lock(); peer = rcu_dereference(priv->peer); if (peer) { - veth_stats_tx(peer, &packets, &bytes); - tot->rx_bytes += bytes; - tot->rx_packets += packets; + struct rtnl_link_stats64 tot_peer = {}; + + dev_fetch_sw_netstats(&tot_peer, peer->tstats); + tot->rx_bytes += tot_peer.tx_bytes; + tot->rx_packets += tot_peer.tx_packets; veth_stats_rx(&rx, peer); tot->tx_dropped += rx.peer_tq_xdp_xmit_err; @@ -1499,25 +1491,12 @@ static void veth_free_queues(struct net_device *dev) static int veth_dev_init(struct net_device *dev) { - int err; - - dev->lstats = netdev_alloc_pcpu_stats(struct pcpu_lstats); - if (!dev->lstats) - return -ENOMEM; - - err = veth_alloc_queues(dev); - if (err) { - free_percpu(dev->lstats); - return err; - } - - return 0; + return veth_alloc_queues(dev); } static void veth_dev_free(struct net_device *dev) { veth_free_queues(dev); - free_percpu(dev->lstats); } #ifdef CONFIG_NET_POLL_CONTROLLER @@ -1789,6 +1768,7 @@ static void veth_setup(struct net_device *dev) NETIF_F_HW_VLAN_STAG_RX); dev->needs_free_netdev = true; dev->priv_destructor = veth_dev_free; + dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; dev->max_mtu = ETH_MAX_MTU; dev->hw_features = VETH_FEATURES; diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index a3408e4e1491b..b90dccdc2d33c 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -121,22 +121,12 @@ struct net_vrf { int ifindex; }; -struct pcpu_dstats { - u64 tx_pkts; - u64 tx_bytes; - u64 tx_drps; - u64 rx_pkts; - u64 rx_bytes; - u64 rx_drps; - struct u64_stats_sync syncp; -}; - static void vrf_rx_stats(struct net_device *dev, int len) { struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats); u64_stats_update_begin(&dstats->syncp); - dstats->rx_pkts++; + dstats->rx_packets++; dstats->rx_bytes += len; u64_stats_update_end(&dstats->syncp); } @@ -161,10 +151,10 @@ static void vrf_get_stats64(struct net_device *dev, do { start = u64_stats_fetch_begin(&dstats->syncp); tbytes = dstats->tx_bytes; - tpkts = dstats->tx_pkts; - tdrops = dstats->tx_drps; + tpkts = dstats->tx_packets; + tdrops = dstats->tx_drops; rbytes = dstats->rx_bytes; - rpkts = dstats->rx_pkts; + rpkts = dstats->rx_packets; } while (u64_stats_fetch_retry(&dstats->syncp, start)); stats->tx_bytes += tbytes; stats->tx_packets += tpkts; @@ -421,7 +411,7 @@ static int vrf_local_xmit(struct sk_buff *skb, struct net_device *dev, if (likely(__netif_rx(skb) == NET_RX_SUCCESS)) vrf_rx_stats(dev, len); else - this_cpu_inc(dev->dstats->rx_drps); + this_cpu_inc(dev->dstats->rx_drops); return NETDEV_TX_OK; } @@ -616,11 +606,11 @@ static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev) struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats); u64_stats_update_begin(&dstats->syncp); - dstats->tx_pkts++; + dstats->tx_packets++; dstats->tx_bytes += len; u64_stats_update_end(&dstats->syncp); } else { - this_cpu_inc(dev->dstats->tx_drps); + this_cpu_inc(dev->dstats->tx_drops); } return ret; @@ -1174,22 +1164,15 @@ static void vrf_dev_uninit(struct net_device *dev) vrf_rtable_release(dev, vrf); vrf_rt6_release(dev, vrf); - - free_percpu(dev->dstats); - dev->dstats = NULL; } static int vrf_dev_init(struct net_device *dev) { struct net_vrf *vrf = netdev_priv(dev); - dev->dstats = netdev_alloc_pcpu_stats(struct pcpu_dstats); - if (!dev->dstats) - goto out_nomem; - /* create the default dst which points back to us */ if (vrf_rtable_create(dev) != 0) - goto out_stats; + goto out_nomem; if (vrf_rt6_create(dev) != 0) goto out_rth; @@ -1203,9 +1186,6 @@ static int vrf_dev_init(struct net_device *dev) out_rth: vrf_rtable_release(dev, vrf); -out_stats: - free_percpu(dev->dstats); - dev->dstats = NULL; out_nomem: return -ENOMEM; } @@ -1704,6 +1684,8 @@ static void vrf_setup(struct net_device *dev) dev->min_mtu = IPV6_MIN_MTU; dev->max_mtu = IP6_MAX_MTU; dev->mtu = dev->max_mtu; + + dev->pcpu_stat_type = NETDEV_PCPU_STAT_DSTATS; } static int vrf_validate(struct nlattr *tb[], struct nlattr *data[], diff --git a/drivers/net/wireguard/device.c b/drivers/net/wireguard/device.c index 258dcc1039216..deb9636b0ecf8 100644 --- a/drivers/net/wireguard/device.c +++ b/drivers/net/wireguard/device.c @@ -210,7 +210,7 @@ static netdev_tx_t wg_xmit(struct sk_buff *skb, struct net_device *dev) */ while (skb_queue_len(&peer->staged_packet_queue) > MAX_STAGED_PACKETS) { dev_kfree_skb(__skb_dequeue(&peer->staged_packet_queue)); - ++dev->stats.tx_dropped; + DEV_STATS_INC(dev, tx_dropped); } skb_queue_splice_tail(&packets, &peer->staged_packet_queue); spin_unlock_bh(&peer->staged_packet_queue.lock); @@ -228,7 +228,7 @@ static netdev_tx_t wg_xmit(struct sk_buff *skb, struct net_device *dev) else if (skb->protocol == htons(ETH_P_IPV6)) icmpv6_ndo_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0); err: - ++dev->stats.tx_errors; + DEV_STATS_INC(dev, tx_errors); kfree_skb(skb); return ret; } diff --git a/drivers/net/wireguard/receive.c b/drivers/net/wireguard/receive.c index 0b3f0c8435509..a176653c88616 100644 --- a/drivers/net/wireguard/receive.c +++ b/drivers/net/wireguard/receive.c @@ -416,20 +416,20 @@ static void wg_packet_consume_data_done(struct wg_peer *peer, net_dbg_skb_ratelimited("%s: Packet has unallowed src IP (%pISc) from peer %llu (%pISpfsc)\n", dev->name, skb, peer->internal_id, &peer->endpoint.addr); - ++dev->stats.rx_errors; - ++dev->stats.rx_frame_errors; + DEV_STATS_INC(dev, rx_errors); + DEV_STATS_INC(dev, rx_frame_errors); goto packet_processed; dishonest_packet_type: net_dbg_ratelimited("%s: Packet is neither ipv4 nor ipv6 from peer %llu (%pISpfsc)\n", dev->name, peer->internal_id, &peer->endpoint.addr); - ++dev->stats.rx_errors; - ++dev->stats.rx_frame_errors; + DEV_STATS_INC(dev, rx_errors); + DEV_STATS_INC(dev, rx_frame_errors); goto packet_processed; dishonest_packet_size: net_dbg_ratelimited("%s: Packet has incorrect size from peer %llu (%pISpfsc)\n", dev->name, peer->internal_id, &peer->endpoint.addr); - ++dev->stats.rx_errors; - ++dev->stats.rx_length_errors; + DEV_STATS_INC(dev, rx_errors); + DEV_STATS_INC(dev, rx_length_errors); goto packet_processed; packet_processed: dev_kfree_skb(skb); diff --git a/drivers/net/wireguard/send.c b/drivers/net/wireguard/send.c index 95c853b59e1da..0d48e0f4a1ba3 100644 --- a/drivers/net/wireguard/send.c +++ b/drivers/net/wireguard/send.c @@ -333,7 +333,8 @@ static void wg_packet_create_data(struct wg_peer *peer, struct sk_buff *first) void wg_packet_purge_staged_packets(struct wg_peer *peer) { spin_lock_bh(&peer->staged_packet_queue.lock); - peer->device->dev->stats.tx_dropped += peer->staged_packet_queue.qlen; + DEV_STATS_ADD(peer->device->dev, tx_dropped, + peer->staged_packet_queue.qlen); __skb_queue_purge(&peer->staged_packet_queue); spin_unlock_bh(&peer->staged_packet_queue.lock); } diff --git a/drivers/net/wireless/ath/ath10k/debug.c b/drivers/net/wireless/ath/ath10k/debug.c index f9518e1c99039..fe89bc61e5317 100644 --- a/drivers/net/wireless/ath/ath10k/debug.c +++ b/drivers/net/wireless/ath/ath10k/debug.c @@ -1140,7 +1140,7 @@ void ath10k_debug_get_et_strings(struct ieee80211_hw *hw, u32 sset, u8 *data) { if (sset == ETH_SS_STATS) - memcpy(data, *ath10k_gstrings_stats, + memcpy(data, ath10k_gstrings_stats, sizeof(ath10k_gstrings_stats)); } diff --git a/drivers/net/wireless/ath/ath10k/snoc.c b/drivers/net/wireless/ath/ath10k/snoc.c index 26214c00cd0d7..2c39bad7ebfb9 100644 --- a/drivers/net/wireless/ath/ath10k/snoc.c +++ b/drivers/net/wireless/ath/ath10k/snoc.c @@ -828,12 +828,20 @@ static void ath10k_snoc_hif_get_default_pipe(struct ath10k *ar, static inline void ath10k_snoc_irq_disable(struct ath10k *ar) { - ath10k_ce_disable_interrupts(ar); + struct ath10k_snoc *ar_snoc = ath10k_snoc_priv(ar); + int id; + + for (id = 0; id < CE_COUNT_MAX; id++) + disable_irq(ar_snoc->ce_irqs[id].irq_line); } static inline void ath10k_snoc_irq_enable(struct ath10k *ar) { - ath10k_ce_enable_interrupts(ar); + struct ath10k_snoc *ar_snoc = ath10k_snoc_priv(ar); + int id; + + for (id = 0; id < CE_COUNT_MAX; id++) + enable_irq(ar_snoc->ce_irqs[id].irq_line); } static void ath10k_snoc_rx_pipe_cleanup(struct ath10k_snoc_pipe *snoc_pipe) @@ -1090,6 +1098,8 @@ static int ath10k_snoc_hif_power_up(struct ath10k *ar, goto err_free_rri; } + ath10k_ce_enable_interrupts(ar); + return 0; err_free_rri: @@ -1253,8 +1263,8 @@ static int ath10k_snoc_request_irq(struct ath10k *ar) for (id = 0; id < CE_COUNT_MAX; id++) { ret = request_irq(ar_snoc->ce_irqs[id].irq_line, - ath10k_snoc_per_engine_handler, 0, - ce_name[id], ar); + ath10k_snoc_per_engine_handler, + IRQF_NO_AUTOEN, ce_name[id], ar); if (ret) { ath10k_err(ar, "failed to register IRQ handler for CE %d: %d\n", diff --git a/drivers/net/wireless/ath/ath11k/dp_rx.c b/drivers/net/wireless/ath/ath11k/dp_rx.c index 62bc98852f0f7..a993e74bbae83 100644 --- a/drivers/net/wireless/ath/ath11k/dp_rx.c +++ b/drivers/net/wireless/ath/ath11k/dp_rx.c @@ -1621,14 +1621,20 @@ static void ath11k_htt_pktlog(struct ath11k_base *ab, struct sk_buff *skb) u8 pdev_id; pdev_id = FIELD_GET(HTT_T2H_PPDU_STATS_INFO_PDEV_ID, data->hdr); + + rcu_read_lock(); + ar = ath11k_mac_get_ar_by_pdev_id(ab, pdev_id); if (!ar) { ath11k_warn(ab, "invalid pdev id %d on htt pktlog\n", pdev_id); - return; + goto out; } trace_ath11k_htt_pktlog(ar, data->payload, hdr->size, ar->ab->pktlog_defs_checksum); + +out: + rcu_read_unlock(); } static void ath11k_htt_backpressure_event_handler(struct ath11k_base *ab, diff --git a/drivers/net/wireless/ath/ath11k/wmi.c b/drivers/net/wireless/ath/ath11k/wmi.c index 23ad6825e5be5..1c07f55c25e67 100644 --- a/drivers/net/wireless/ath/ath11k/wmi.c +++ b/drivers/net/wireless/ath/ath11k/wmi.c @@ -8337,6 +8337,8 @@ ath11k_wmi_pdev_dfs_radar_detected_event(struct ath11k_base *ab, struct sk_buff ev->detector_id, ev->segment_id, ev->timestamp, ev->is_chirp, ev->freq_offset, ev->sidx); + rcu_read_lock(); + ar = ath11k_mac_get_ar_by_pdev_id(ab, ev->pdev_id); if (!ar) { @@ -8354,6 +8356,8 @@ ath11k_wmi_pdev_dfs_radar_detected_event(struct ath11k_base *ab, struct sk_buff ieee80211_radar_detected(ar->hw); exit: + rcu_read_unlock(); + kfree(tb); } @@ -8383,15 +8387,19 @@ ath11k_wmi_pdev_temperature_event(struct ath11k_base *ab, ath11k_dbg(ab, ATH11K_DBG_WMI, "event pdev temperature ev temp %d pdev_id %d\n", ev->temp, ev->pdev_id); + rcu_read_lock(); + ar = ath11k_mac_get_ar_by_pdev_id(ab, ev->pdev_id); if (!ar) { ath11k_warn(ab, "invalid pdev id in pdev temperature ev %d", ev->pdev_id); - kfree(tb); - return; + goto exit; } ath11k_thermal_event_temperature(ar, ev->temp); +exit: + rcu_read_unlock(); + kfree(tb); } @@ -8611,12 +8619,13 @@ static void ath11k_wmi_gtk_offload_status_event(struct ath11k_base *ab, return; } + rcu_read_lock(); + arvif = ath11k_mac_get_arvif_by_vdev_id(ab, ev->vdev_id); if (!arvif) { ath11k_warn(ab, "failed to get arvif for vdev_id:%d\n", ev->vdev_id); - kfree(tb); - return; + goto exit; } ath11k_dbg(ab, ATH11K_DBG_WMI, "event gtk offload refresh_cnt %d\n", @@ -8633,6 +8642,8 @@ static void ath11k_wmi_gtk_offload_status_event(struct ath11k_base *ab, ieee80211_gtk_rekey_notify(arvif->vif, arvif->bssid, (void *)&replay_ctr_be, GFP_ATOMIC); +exit: + rcu_read_unlock(); kfree(tb); } diff --git a/drivers/net/wireless/ath/ath12k/dp.c b/drivers/net/wireless/ath/ath12k/dp.c index f933896f2a68d..6893466f61f04 100644 --- a/drivers/net/wireless/ath/ath12k/dp.c +++ b/drivers/net/wireless/ath/ath12k/dp.c @@ -38,6 +38,7 @@ void ath12k_dp_peer_cleanup(struct ath12k *ar, int vdev_id, const u8 *addr) ath12k_dp_rx_peer_tid_cleanup(ar, peer); crypto_free_shash(peer->tfm_mmic); + peer->dp_setup_done = false; spin_unlock_bh(&ab->base_lock); } diff --git a/drivers/net/wireless/ath/ath12k/dp_rx.c b/drivers/net/wireless/ath/ath12k/dp_rx.c index 17da39bd3ab4d..dbcbe7e0cd2a7 100644 --- a/drivers/net/wireless/ath/ath12k/dp_rx.c +++ b/drivers/net/wireless/ath/ath12k/dp_rx.c @@ -1555,6 +1555,13 @@ static int ath12k_htt_pull_ppdu_stats(struct ath12k_base *ab, msg = (struct ath12k_htt_ppdu_stats_msg *)skb->data; len = le32_get_bits(msg->info, HTT_T2H_PPDU_STATS_INFO_PAYLOAD_SIZE); + if (len > (skb->len - struct_size(msg, data, 0))) { + ath12k_warn(ab, + "HTT PPDU STATS event has unexpected payload size %u, should be smaller than %u\n", + len, skb->len); + return -EINVAL; + } + pdev_id = le32_get_bits(msg->info, HTT_T2H_PPDU_STATS_INFO_PDEV_ID); ppdu_id = le32_to_cpu(msg->ppdu_id); @@ -1583,6 +1590,16 @@ static int ath12k_htt_pull_ppdu_stats(struct ath12k_base *ab, goto exit; } + if (ppdu_info->ppdu_stats.common.num_users >= HTT_PPDU_STATS_MAX_USERS) { + spin_unlock_bh(&ar->data_lock); + ath12k_warn(ab, + "HTT PPDU STATS event has unexpected num_users %u, should be smaller than %u\n", + ppdu_info->ppdu_stats.common.num_users, + HTT_PPDU_STATS_MAX_USERS); + ret = -EINVAL; + goto exit; + } + /* back up data rate tlv for all peers */ if (ppdu_info->frame_type == HTT_STATS_PPDU_FTYPE_DATA && (ppdu_info->tlv_bitmap & (1 << HTT_PPDU_STATS_TAG_USR_COMMON)) && @@ -1641,11 +1658,12 @@ static void ath12k_htt_mlo_offset_event_handler(struct ath12k_base *ab, msg = (struct ath12k_htt_mlo_offset_msg *)skb->data; pdev_id = u32_get_bits(__le32_to_cpu(msg->info), HTT_T2H_MLO_OFFSET_INFO_PDEV_ID); - ar = ath12k_mac_get_ar_by_pdev_id(ab, pdev_id); + rcu_read_lock(); + ar = ath12k_mac_get_ar_by_pdev_id(ab, pdev_id); if (!ar) { ath12k_warn(ab, "invalid pdev id %d on htt mlo offset\n", pdev_id); - return; + goto exit; } spin_lock_bh(&ar->data_lock); @@ -1661,6 +1679,8 @@ static void ath12k_htt_mlo_offset_event_handler(struct ath12k_base *ab, pdev->timestamp.mlo_comp_timer = __le32_to_cpu(msg->mlo_comp_timer); spin_unlock_bh(&ar->data_lock); +exit: + rcu_read_unlock(); } void ath12k_dp_htt_htc_t2h_msg_handler(struct ath12k_base *ab, @@ -2748,6 +2768,7 @@ int ath12k_dp_rx_peer_frag_setup(struct ath12k *ar, const u8 *peer_mac, int vdev } peer->tfm_mmic = tfm; + peer->dp_setup_done = true; spin_unlock_bh(&ab->base_lock); return 0; @@ -3214,6 +3235,14 @@ static int ath12k_dp_rx_frag_h_mpdu(struct ath12k *ar, ret = -ENOENT; goto out_unlock; } + + if (!peer->dp_setup_done) { + ath12k_warn(ab, "The peer %pM [%d] has uninitialized datapath\n", + peer->addr, peer_id); + ret = -ENOENT; + goto out_unlock; + } + rx_tid = &peer->rx_tid[tid]; if ((!skb_queue_empty(&rx_tid->rx_frags) && seqno != rx_tid->cur_sn) || diff --git a/drivers/net/wireless/ath/ath12k/mhi.c b/drivers/net/wireless/ath/ath12k/mhi.c index 42f1140baa4fe..f83d3e09ae366 100644 --- a/drivers/net/wireless/ath/ath12k/mhi.c +++ b/drivers/net/wireless/ath/ath12k/mhi.c @@ -370,8 +370,7 @@ int ath12k_mhi_register(struct ath12k_pci *ab_pci) ret = ath12k_mhi_get_msi(ab_pci); if (ret) { ath12k_err(ab, "failed to get msi for mhi\n"); - mhi_free_controller(mhi_ctrl); - return ret; + goto free_controller; } mhi_ctrl->iova_start = 0; @@ -388,11 +387,15 @@ int ath12k_mhi_register(struct ath12k_pci *ab_pci) ret = mhi_register_controller(mhi_ctrl, ab->hw_params->mhi_config); if (ret) { ath12k_err(ab, "failed to register to mhi bus, err = %d\n", ret); - mhi_free_controller(mhi_ctrl); - return ret; + goto free_controller; } return 0; + +free_controller: + mhi_free_controller(mhi_ctrl); + ab_pci->mhi_ctrl = NULL; + return ret; } void ath12k_mhi_unregister(struct ath12k_pci *ab_pci) diff --git a/drivers/net/wireless/ath/ath12k/peer.h b/drivers/net/wireless/ath/ath12k/peer.h index b296dc0e2f671..c6edb24cbedd8 100644 --- a/drivers/net/wireless/ath/ath12k/peer.h +++ b/drivers/net/wireless/ath/ath12k/peer.h @@ -44,6 +44,9 @@ struct ath12k_peer { struct ppdu_user_delayba ppdu_stats_delayba; bool delayba_flag; bool is_authorized; + + /* protected by ab->data_lock */ + bool dp_setup_done; }; void ath12k_peer_unmap_event(struct ath12k_base *ab, u16 peer_id); diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c index ef0f3cf35cfd1..d217b70a7a8fb 100644 --- a/drivers/net/wireless/ath/ath12k/wmi.c +++ b/drivers/net/wireless/ath/ath12k/wmi.c @@ -3876,6 +3876,12 @@ static int ath12k_wmi_ext_hal_reg_caps(struct ath12k_base *soc, ath12k_warn(soc, "failed to extract reg cap %d\n", i); return ret; } + + if (reg_cap.phy_id >= MAX_RADIOS) { + ath12k_warn(soc, "unexpected phy id %u\n", reg_cap.phy_id); + return -EINVAL; + } + soc->hal_reg_cap[reg_cap.phy_id] = reg_cap; } return 0; @@ -6476,6 +6482,8 @@ ath12k_wmi_pdev_dfs_radar_detected_event(struct ath12k_base *ab, struct sk_buff ev->detector_id, ev->segment_id, ev->timestamp, ev->is_chirp, ev->freq_offset, ev->sidx); + rcu_read_lock(); + ar = ath12k_mac_get_ar_by_pdev_id(ab, le32_to_cpu(ev->pdev_id)); if (!ar) { @@ -6493,6 +6501,8 @@ ath12k_wmi_pdev_dfs_radar_detected_event(struct ath12k_base *ab, struct sk_buff ieee80211_radar_detected(ar->hw); exit: + rcu_read_unlock(); + kfree(tb); } @@ -6511,11 +6521,16 @@ ath12k_wmi_pdev_temperature_event(struct ath12k_base *ab, ath12k_dbg(ab, ATH12K_DBG_WMI, "pdev temperature ev temp %d pdev_id %d\n", ev.temp, ev.pdev_id); + rcu_read_lock(); + ar = ath12k_mac_get_ar_by_pdev_id(ab, le32_to_cpu(ev.pdev_id)); if (!ar) { ath12k_warn(ab, "invalid pdev id in pdev temperature ev %d", ev.pdev_id); - return; + goto exit; } + +exit: + rcu_read_unlock(); } static void ath12k_fils_discovery_event(struct ath12k_base *ab, diff --git a/drivers/net/wireless/ath/ath9k/debug.c b/drivers/net/wireless/ath/ath9k/debug.c index 9bc57c5a89bfe..a0376a6787b8d 100644 --- a/drivers/net/wireless/ath/ath9k/debug.c +++ b/drivers/net/wireless/ath/ath9k/debug.c @@ -1293,7 +1293,7 @@ void ath9k_get_et_strings(struct ieee80211_hw *hw, u32 sset, u8 *data) { if (sset == ETH_SS_STATS) - memcpy(data, *ath9k_gstrings_stats, + memcpy(data, ath9k_gstrings_stats, sizeof(ath9k_gstrings_stats)); } diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_debug.c b/drivers/net/wireless/ath/ath9k/htc_drv_debug.c index c549ff3abcdc4..278ddc713fdc2 100644 --- a/drivers/net/wireless/ath/ath9k/htc_drv_debug.c +++ b/drivers/net/wireless/ath/ath9k/htc_drv_debug.c @@ -423,7 +423,7 @@ void ath9k_htc_get_et_strings(struct ieee80211_hw *hw, u32 sset, u8 *data) { if (sset == ETH_SS_STATS) - memcpy(data, *ath9k_htc_gstrings_stats, + memcpy(data, ath9k_htc_gstrings_stats, sizeof(ath9k_htc_gstrings_stats)); } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/link.c b/drivers/net/wireless/intel/iwlwifi/mvm/link.c index 6e1ad65527d12..4ab55a1fcbf04 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/link.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/link.c @@ -60,7 +60,7 @@ int iwl_mvm_add_link(struct iwl_mvm *mvm, struct ieee80211_vif *vif, if (link_info->fw_link_id == IWL_MVM_FW_LINK_ID_INVALID) { link_info->fw_link_id = iwl_mvm_get_free_fw_link_id(mvm, mvmvif); - if (link_info->fw_link_id == IWL_MVM_FW_LINK_ID_INVALID) + if (link_info->fw_link_id >= ARRAY_SIZE(mvm->link_id_to_link_conf)) return -EINVAL; rcu_assign_pointer(mvm->link_id_to_link_conf[link_info->fw_link_id], @@ -243,7 +243,7 @@ int iwl_mvm_remove_link(struct iwl_mvm *mvm, struct ieee80211_vif *vif, int ret; if (WARN_ON(!link_info || - link_info->fw_link_id == IWL_MVM_FW_LINK_ID_INVALID)) + link_info->fw_link_id >= ARRAY_SIZE(mvm->link_id_to_link_conf))) return -EINVAL; RCU_INIT_POINTER(mvm->link_id_to_link_conf[link_info->fw_link_id], diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c index 56f51344c193c..1ccbe8c1eeb42 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c @@ -705,8 +705,10 @@ int iwl_mvm_mld_add_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif, rcu_dereference_protected(mvm_sta->link[link_id], lockdep_is_held(&mvm->mutex)); - if (WARN_ON(!link_conf || !mvm_link_sta)) + if (WARN_ON(!link_conf || !mvm_link_sta)) { + ret = -EINVAL; goto err; + } ret = iwl_mvm_mld_cfg_sta(mvm, sta, vif, link_sta, link_conf, mvm_link_sta); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c index 2ede69132fee9..177a4628a913e 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c @@ -536,16 +536,20 @@ iwl_mvm_set_tx_params(struct iwl_mvm *mvm, struct sk_buff *skb, flags |= IWL_TX_FLAGS_ENCRYPT_DIS; /* - * For data packets rate info comes from the fw. Only - * set rate/antenna during connection establishment or in case - * no station is given. + * For data and mgmt packets rate info comes from the fw. Only + * set rate/antenna for injected frames with fixed rate, or + * when no sta is given. */ - if (!sta || !ieee80211_is_data(hdr->frame_control) || - mvmsta->sta_state < IEEE80211_STA_AUTHORIZED) { + if (unlikely(!sta || + info->control.flags & IEEE80211_TX_CTRL_RATE_INJECT)) { flags |= IWL_TX_FLAGS_CMD_RATE; rate_n_flags = iwl_mvm_get_tx_rate_n_flags(mvm, info, sta, hdr->frame_control); + } else if (!ieee80211_is_data(hdr->frame_control) || + mvmsta->sta_state < IEEE80211_STA_AUTHORIZED) { + /* These are important frames */ + flags |= IWL_TX_FLAGS_HIGH_PRI; } if (mvm->trans->trans_cfg->device_family >= diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c index 583d1011963ec..2e23ccd7d7938 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c @@ -3088,7 +3088,7 @@ static u32 iwl_trans_pcie_dump_rbs(struct iwl_trans *trans, struct iwl_rxq *rxq = &trans_pcie->rxq[0]; u32 i, r, j, rb_len = 0; - spin_lock(&rxq->lock); + spin_lock_bh(&rxq->lock); r = le16_to_cpu(iwl_get_closed_rb_stts(trans, rxq)) & 0x0FFF; @@ -3112,7 +3112,7 @@ static u32 iwl_trans_pcie_dump_rbs(struct iwl_trans *trans, *data = iwl_fw_error_next_data(*data); } - spin_unlock(&rxq->lock); + spin_unlock_bh(&rxq->lock); return rb_len; } diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c index 6ca7b494c2c26..cd04865970643 100644 --- a/drivers/net/wireless/mediatek/mt76/dma.c +++ b/drivers/net/wireless/mediatek/mt76/dma.c @@ -776,7 +776,7 @@ mt76_dma_rx_reset(struct mt76_dev *dev, enum mt76_rxq_id qid) static void mt76_add_fragment(struct mt76_dev *dev, struct mt76_queue *q, void *data, - int len, bool more, u32 info) + int len, bool more, u32 info, bool allow_direct) { struct sk_buff *skb = q->rx_head; struct skb_shared_info *shinfo = skb_shinfo(skb); @@ -788,7 +788,7 @@ mt76_add_fragment(struct mt76_dev *dev, struct mt76_queue *q, void *data, skb_add_rx_frag(skb, nr_frags, page, offset, len, q->buf_size); } else { - mt76_put_page_pool_buf(data, true); + mt76_put_page_pool_buf(data, allow_direct); } if (more) @@ -808,6 +808,7 @@ mt76_dma_rx_process(struct mt76_dev *dev, struct mt76_queue *q, int budget) struct sk_buff *skb; unsigned char *data; bool check_ddone = false; + bool allow_direct = !mt76_queue_is_wed_rx(q); bool more; if (IS_ENABLED(CONFIG_NET_MEDIATEK_SOC_WED) && @@ -848,7 +849,8 @@ mt76_dma_rx_process(struct mt76_dev *dev, struct mt76_queue *q, int budget) } if (q->rx_head) { - mt76_add_fragment(dev, q, data, len, more, info); + mt76_add_fragment(dev, q, data, len, more, info, + allow_direct); continue; } @@ -877,7 +879,7 @@ mt76_dma_rx_process(struct mt76_dev *dev, struct mt76_queue *q, int budget) continue; free_frag: - mt76_put_page_pool_buf(data, true); + mt76_put_page_pool_buf(data, allow_direct); } mt76_dma_rx_fill(dev, q, true); diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/main.c b/drivers/net/wireless/mediatek/mt76/mt7915/main.c index d06c25dda325e..d85105a43d704 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/main.c @@ -1388,7 +1388,7 @@ void mt7915_get_et_strings(struct ieee80211_hw *hw, if (sset != ETH_SS_STATS) return; - memcpy(data, *mt7915_gstrings_stats, sizeof(mt7915_gstrings_stats)); + memcpy(data, mt7915_gstrings_stats, sizeof(mt7915_gstrings_stats)); data += sizeof(mt7915_gstrings_stats); page_pool_ethtool_stats_get_strings(data); } diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c index 3dda84a937175..f04e7095e1810 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c @@ -17,6 +17,8 @@ static const struct pci_device_id mt7921_pci_device_table[] = { .driver_data = (kernel_ulong_t)MT7921_FIRMWARE_WM }, { PCI_DEVICE(PCI_VENDOR_ID_MEDIATEK, 0x7922), .driver_data = (kernel_ulong_t)MT7922_FIRMWARE_WM }, + { PCI_DEVICE(PCI_VENDOR_ID_ITTIM, 0x7922), + .driver_data = (kernel_ulong_t)MT7922_FIRMWARE_WM }, { PCI_DEVICE(PCI_VENDOR_ID_MEDIATEK, 0x0608), .driver_data = (kernel_ulong_t)MT7921_FIRMWARE_WM }, { PCI_DEVICE(PCI_VENDOR_ID_MEDIATEK, 0x0616), diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_core.c b/drivers/net/wireless/mediatek/mt76/mt792x_core.c index ec98450a938ff..f111c47fdca56 100644 --- a/drivers/net/wireless/mediatek/mt76/mt792x_core.c +++ b/drivers/net/wireless/mediatek/mt76/mt792x_core.c @@ -358,7 +358,7 @@ void mt792x_get_et_strings(struct ieee80211_hw *hw, struct ieee80211_vif *vif, if (sset != ETH_SS_STATS) return; - memcpy(data, *mt792x_gstrings_stats, sizeof(mt792x_gstrings_stats)); + memcpy(data, mt792x_gstrings_stats, sizeof(mt792x_gstrings_stats)); data += sizeof(mt792x_gstrings_stats); page_pool_ethtool_stats_get_strings(data); diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c index 6e0f0c100db84..620880e560e00 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c @@ -1198,7 +1198,7 @@ void mt7996_get_et_strings(struct ieee80211_hw *hw, u32 sset, u8 *data) { if (sset == ETH_SS_STATS) - memcpy(data, *mt7996_gstrings_stats, + memcpy(data, mt7996_gstrings_stats, sizeof(mt7996_gstrings_stats)); } diff --git a/drivers/net/wireless/microchip/wilc1000/wlan.c b/drivers/net/wireless/microchip/wilc1000/wlan.c index 58bbf50081e47..9eb115c79c90a 100644 --- a/drivers/net/wireless/microchip/wilc1000/wlan.c +++ b/drivers/net/wireless/microchip/wilc1000/wlan.c @@ -1492,7 +1492,7 @@ int wilc_wlan_init(struct net_device *dev) } if (!wilc->vmm_table) - wilc->vmm_table = kzalloc(WILC_VMM_TBL_SIZE, GFP_KERNEL); + wilc->vmm_table = kcalloc(WILC_VMM_TBL_SIZE, sizeof(u32), GFP_KERNEL); if (!wilc->vmm_table) { ret = -ENOBUFS; diff --git a/drivers/net/wireless/purelifi/plfxlc/mac.c b/drivers/net/wireless/purelifi/plfxlc/mac.c index 94ee831b5de35..506d2f31efb5a 100644 --- a/drivers/net/wireless/purelifi/plfxlc/mac.c +++ b/drivers/net/wireless/purelifi/plfxlc/mac.c @@ -666,7 +666,7 @@ static void plfxlc_get_et_strings(struct ieee80211_hw *hw, u32 sset, u8 *data) { if (sset == ETH_SS_STATS) - memcpy(data, *et_strings, sizeof(et_strings)); + memcpy(data, et_strings, sizeof(et_strings)); } static void plfxlc_get_et_stats(struct ieee80211_hw *hw, diff --git a/drivers/net/wireless/virtual/mac80211_hwsim.c b/drivers/net/wireless/virtual/mac80211_hwsim.c index 1f524030b186e..f5a0880da3fcc 100644 --- a/drivers/net/wireless/virtual/mac80211_hwsim.c +++ b/drivers/net/wireless/virtual/mac80211_hwsim.c @@ -3170,7 +3170,7 @@ static void mac80211_hwsim_get_et_strings(struct ieee80211_hw *hw, u32 sset, u8 *data) { if (sset == ETH_SS_STATS) - memcpy(data, *mac80211_hwsim_gstrings_stats, + memcpy(data, mac80211_hwsim_gstrings_stats, sizeof(mac80211_hwsim_gstrings_stats)); } diff --git a/drivers/nfc/virtual_ncidev.c b/drivers/nfc/virtual_ncidev.c index b027be0b0b6ff..590b038e449e5 100644 --- a/drivers/nfc/virtual_ncidev.c +++ b/drivers/nfc/virtual_ncidev.c @@ -26,10 +26,14 @@ struct virtual_nci_dev { struct mutex mtx; struct sk_buff *send_buff; struct wait_queue_head wq; + bool running; }; static int virtual_nci_open(struct nci_dev *ndev) { + struct virtual_nci_dev *vdev = nci_get_drvdata(ndev); + + vdev->running = true; return 0; } @@ -40,6 +44,7 @@ static int virtual_nci_close(struct nci_dev *ndev) mutex_lock(&vdev->mtx); kfree_skb(vdev->send_buff); vdev->send_buff = NULL; + vdev->running = false; mutex_unlock(&vdev->mtx); return 0; @@ -50,7 +55,7 @@ static int virtual_nci_send(struct nci_dev *ndev, struct sk_buff *skb) struct virtual_nci_dev *vdev = nci_get_drvdata(ndev); mutex_lock(&vdev->mtx); - if (vdev->send_buff) { + if (vdev->send_buff || !vdev->running) { mutex_unlock(&vdev->mtx); kfree_skb(skb); return -1; diff --git a/drivers/nvme/host/auth.c b/drivers/nvme/host/auth.c index 064592a5d546a..811541ce206bf 100644 --- a/drivers/nvme/host/auth.c +++ b/drivers/nvme/host/auth.c @@ -840,6 +840,8 @@ static void nvme_queue_auth_work(struct work_struct *work) } fail2: + if (chap->status == 0) + chap->status = NVME_AUTH_DHCHAP_FAILURE_FAILED; dev_dbg(ctrl->device, "%s: qid %d send failure2, status %x\n", __func__, chap->qid, chap->status); tl = nvme_auth_set_dhchap_failure2_data(ctrl, chap); diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 9c6564e03fc04..91ae4d144c3fc 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1813,16 +1813,18 @@ static int nvme_init_ms(struct nvme_ns *ns, struct nvme_id_ns *id) return ret; } -static void nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id) +static int nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id) { struct nvme_ctrl *ctrl = ns->ctrl; + int ret; - if (nvme_init_ms(ns, id)) - return; + ret = nvme_init_ms(ns, id); + if (ret) + return ret; ns->features &= ~(NVME_NS_METADATA_SUPPORTED | NVME_NS_EXT_LBAS); if (!ns->ms || !(ctrl->ops->flags & NVME_F_METADATA_SUPPORTED)) - return; + return 0; if (ctrl->ops->flags & NVME_F_FABRICS) { /* @@ -1831,7 +1833,7 @@ static void nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id) * remap the separate metadata buffer from the block layer. */ if (WARN_ON_ONCE(!(id->flbas & NVME_NS_FLBAS_META_EXT))) - return; + return 0; ns->features |= NVME_NS_EXT_LBAS; @@ -1858,6 +1860,7 @@ static void nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id) else ns->features |= NVME_NS_METADATA_SUPPORTED; } + return 0; } static void nvme_set_queue_limits(struct nvme_ctrl *ctrl, @@ -2026,12 +2029,23 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns, if (ret) return ret; + if (id->ncap == 0) { + /* namespace not allocated or attached */ + info->is_removed = true; + ret = -ENODEV; + goto error; + } + blk_mq_freeze_queue(ns->disk->queue); lbaf = nvme_lbaf_index(id->flbas); ns->lba_shift = id->lbaf[lbaf].ds; nvme_set_queue_limits(ns->ctrl, ns->queue); - nvme_configure_metadata(ns, id); + ret = nvme_configure_metadata(ns, id); + if (ret < 0) { + blk_mq_unfreeze_queue(ns->disk->queue); + goto out; + } nvme_set_chunk_sectors(ns, id); nvme_update_disk_info(ns->disk, ns, id); @@ -2083,6 +2097,8 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns, set_bit(NVME_NS_READY, &ns->flags); ret = 0; } + +error: kfree(id); return ret; } @@ -4085,6 +4101,8 @@ static void nvme_fw_act_work(struct work_struct *work) struct nvme_ctrl, fw_act_work); unsigned long fw_act_timeout; + nvme_auth_stop(ctrl); + if (ctrl->mtfa) fw_act_timeout = jiffies + msecs_to_jiffies(ctrl->mtfa * 100); @@ -4140,7 +4158,6 @@ static bool nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result) * firmware activation. */ if (nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING)) { - nvme_auth_stop(ctrl); requeue = false; queue_work(nvme_wq, &ctrl->fw_act_work); } diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index 8175d49f29090..92ba315cfe19e 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -645,8 +645,10 @@ static const match_table_t opt_tokens = { { NVMF_OPT_TOS, "tos=%d" }, { NVMF_OPT_FAIL_FAST_TMO, "fast_io_fail_tmo=%d" }, { NVMF_OPT_DISCOVERY, "discovery" }, +#ifdef CONFIG_NVME_HOST_AUTH { NVMF_OPT_DHCHAP_SECRET, "dhchap_secret=%s" }, { NVMF_OPT_DHCHAP_CTRL_SECRET, "dhchap_ctrl_secret=%s" }, +#endif { NVMF_OPT_ERR, NULL } }; diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index a15b37750d6e9..206f1b4e5eb1c 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -2548,24 +2548,17 @@ nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg) * the controller. Abort any ios on the association and let the * create_association error path resolve things. */ - enum nvme_ctrl_state state; - unsigned long flags; - - spin_lock_irqsave(&ctrl->lock, flags); - state = ctrl->ctrl.state; - if (state == NVME_CTRL_CONNECTING) { - set_bit(ASSOC_FAILED, &ctrl->flags); - spin_unlock_irqrestore(&ctrl->lock, flags); + if (ctrl->ctrl.state == NVME_CTRL_CONNECTING) { __nvme_fc_abort_outstanding_ios(ctrl, true); + set_bit(ASSOC_FAILED, &ctrl->flags); dev_warn(ctrl->ctrl.device, "NVME-FC{%d}: transport error during (re)connect\n", ctrl->cnum); return; } - spin_unlock_irqrestore(&ctrl->lock, flags); /* Otherwise, only proceed if in LIVE state - e.g. on first error */ - if (state != NVME_CTRL_LIVE) + if (ctrl->ctrl.state != NVME_CTRL_LIVE) return; dev_warn(ctrl->ctrl.device, @@ -3179,16 +3172,12 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) else ret = nvme_fc_recreate_io_queues(ctrl); } - - spin_lock_irqsave(&ctrl->lock, flags); if (!ret && test_bit(ASSOC_FAILED, &ctrl->flags)) ret = -EIO; - if (ret) { - spin_unlock_irqrestore(&ctrl->lock, flags); + if (ret) goto out_term_aen_ops; - } + changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE); - spin_unlock_irqrestore(&ctrl->lock, flags); ctrl->ctrl.nr_reconnects = 0; diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index f35647c470afa..74f74b459f5fa 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -156,6 +156,11 @@ enum nvme_quirks { * No temperature thresholds for channels other than 0 (Composite). */ NVME_QUIRK_NO_SECONDARY_TEMP_THRESH = (1 << 19), + + /* + * Disables simple suspend/resume path. + */ + NVME_QUIRK_FORCE_NO_SIMPLE_SUSPEND = (1 << 20), }; /* diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 3f0c9ee09a12b..5c2a3af26d4de 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2903,6 +2903,18 @@ static unsigned long check_vendor_combination_bug(struct pci_dev *pdev) if ((dmi_match(DMI_BOARD_VENDOR, "LENOVO")) && dmi_match(DMI_BOARD_NAME, "LNVNB161216")) return NVME_QUIRK_SIMPLE_SUSPEND; + } else if (pdev->vendor == 0x2646 && (pdev->device == 0x2263 || + pdev->device == 0x500f)) { + /* + * Exclude some Kingston NV1 and A2000 devices from + * NVME_QUIRK_SIMPLE_SUSPEND. Do a full suspend to save a + * lot fo energy with s2idle sleep on some TUXEDO platforms. + */ + if (dmi_match(DMI_BOARD_NAME, "NS5X_NS7XAU") || + dmi_match(DMI_BOARD_NAME, "NS5x_7xAU") || + dmi_match(DMI_BOARD_NAME, "NS5x_7xPU") || + dmi_match(DMI_BOARD_NAME, "PH4PRX1_PH6PRX1")) + return NVME_QUIRK_FORCE_NO_SIMPLE_SUSPEND; } return 0; @@ -2933,7 +2945,9 @@ static struct nvme_dev *nvme_pci_alloc_dev(struct pci_dev *pdev, dev->dev = get_device(&pdev->dev); quirks |= check_vendor_combination_bug(pdev); - if (!noacpi && acpi_storage_d3(&pdev->dev)) { + if (!noacpi && + !(quirks & NVME_QUIRK_FORCE_NO_SIMPLE_SUSPEND) && + acpi_storage_d3(&pdev->dev)) { /* * Some systems use a bios work around to ask for D3 on * platforms that support kernel managed suspend. diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c index 43b5bd8bb6a52..d8da840a1c0ed 100644 --- a/drivers/nvme/target/fabrics-cmd.c +++ b/drivers/nvme/target/fabrics-cmd.c @@ -244,6 +244,8 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req) goto out; } + d->subsysnqn[NVMF_NQN_FIELD_LEN - 1] = '\0'; + d->hostnqn[NVMF_NQN_FIELD_LEN - 1] = '\0'; status = nvmet_alloc_ctrl(d->subsysnqn, d->hostnqn, req, le32_to_cpu(c->kato), &ctrl); if (status) @@ -313,6 +315,8 @@ static void nvmet_execute_io_connect(struct nvmet_req *req) goto out; } + d->subsysnqn[NVMF_NQN_FIELD_LEN - 1] = '\0'; + d->hostnqn[NVMF_NQN_FIELD_LEN - 1] = '\0'; ctrl = nvmet_ctrl_find_get(d->subsysnqn, d->hostnqn, le16_to_cpu(d->cntlid), req); if (!ctrl) { diff --git a/drivers/nvmem/brcm_nvram.c b/drivers/nvmem/brcm_nvram.c index 9737104f3b76b..5cdf339cfbec0 100644 --- a/drivers/nvmem/brcm_nvram.c +++ b/drivers/nvmem/brcm_nvram.c @@ -17,9 +17,23 @@ #define NVRAM_MAGIC "FLSH" +/** + * struct brcm_nvram - driver state internal struct + * + * @dev: NVMEM device pointer + * @nvmem_size: Size of the whole space available for NVRAM + * @data: NVRAM data copy stored to avoid poking underlaying flash controller + * @data_len: NVRAM data size + * @padding_byte: Padding value used to fill remaining space + * @cells: Array of discovered NVMEM cells + * @ncells: Number of elements in cells + */ struct brcm_nvram { struct device *dev; - void __iomem *base; + size_t nvmem_size; + uint8_t *data; + size_t data_len; + uint8_t padding_byte; struct nvmem_cell_info *cells; int ncells; }; @@ -36,10 +50,47 @@ static int brcm_nvram_read(void *context, unsigned int offset, void *val, size_t bytes) { struct brcm_nvram *priv = context; - u8 *dst = val; + size_t to_copy; + + if (offset + bytes > priv->data_len) + to_copy = max_t(ssize_t, (ssize_t)priv->data_len - offset, 0); + else + to_copy = bytes; + + memcpy(val, priv->data + offset, to_copy); + + memset((uint8_t *)val + to_copy, priv->padding_byte, bytes - to_copy); + + return 0; +} + +static int brcm_nvram_copy_data(struct brcm_nvram *priv, struct platform_device *pdev) +{ + struct resource *res; + void __iomem *base; + + base = devm_platform_get_and_ioremap_resource(pdev, 0, &res); + if (IS_ERR(base)) + return PTR_ERR(base); + + priv->nvmem_size = resource_size(res); + + priv->padding_byte = readb(base + priv->nvmem_size - 1); + for (priv->data_len = priv->nvmem_size; + priv->data_len; + priv->data_len--) { + if (readb(base + priv->data_len - 1) != priv->padding_byte) + break; + } + WARN(priv->data_len > SZ_128K, "Unexpected (big) NVRAM size: %zu B\n", priv->data_len); + + priv->data = devm_kzalloc(priv->dev, priv->data_len, GFP_KERNEL); + if (!priv->data) + return -ENOMEM; + + memcpy_fromio(priv->data, base, priv->data_len); - while (bytes--) - *dst++ = readb(priv->base + offset++); + bcm47xx_nvram_init_from_iomem(base, priv->data_len); return 0; } @@ -67,8 +118,13 @@ static int brcm_nvram_add_cells(struct brcm_nvram *priv, uint8_t *data, size_t len) { struct device *dev = priv->dev; - char *var, *value, *eq; + char *var, *value; + uint8_t tmp; int idx; + int err = 0; + + tmp = priv->data[len - 1]; + priv->data[len - 1] = '\0'; priv->ncells = 0; for (var = data + sizeof(struct brcm_nvram_header); @@ -78,67 +134,68 @@ static int brcm_nvram_add_cells(struct brcm_nvram *priv, uint8_t *data, } priv->cells = devm_kcalloc(dev, priv->ncells, sizeof(*priv->cells), GFP_KERNEL); - if (!priv->cells) - return -ENOMEM; + if (!priv->cells) { + err = -ENOMEM; + goto out; + } for (var = data + sizeof(struct brcm_nvram_header), idx = 0; var < (char *)data + len && *var; var = value + strlen(value) + 1, idx++) { + char *eq, *name; + eq = strchr(var, '='); if (!eq) break; *eq = '\0'; + name = devm_kstrdup(dev, var, GFP_KERNEL); + *eq = '='; + if (!name) { + err = -ENOMEM; + goto out; + } value = eq + 1; - priv->cells[idx].name = devm_kstrdup(dev, var, GFP_KERNEL); - if (!priv->cells[idx].name) - return -ENOMEM; + priv->cells[idx].name = name; priv->cells[idx].offset = value - (char *)data; priv->cells[idx].bytes = strlen(value); priv->cells[idx].np = of_get_child_by_name(dev->of_node, priv->cells[idx].name); - if (!strcmp(var, "et0macaddr") || - !strcmp(var, "et1macaddr") || - !strcmp(var, "et2macaddr")) { + if (!strcmp(name, "et0macaddr") || + !strcmp(name, "et1macaddr") || + !strcmp(name, "et2macaddr")) { priv->cells[idx].raw_len = strlen(value); priv->cells[idx].bytes = ETH_ALEN; priv->cells[idx].read_post_process = brcm_nvram_read_post_process_macaddr; } } - return 0; +out: + priv->data[len - 1] = tmp; + return err; } static int brcm_nvram_parse(struct brcm_nvram *priv) { + struct brcm_nvram_header *header = (struct brcm_nvram_header *)priv->data; struct device *dev = priv->dev; - struct brcm_nvram_header header; - uint8_t *data; size_t len; int err; - memcpy_fromio(&header, priv->base, sizeof(header)); - - if (memcmp(header.magic, NVRAM_MAGIC, 4)) { + if (memcmp(header->magic, NVRAM_MAGIC, 4)) { dev_err(dev, "Invalid NVRAM magic\n"); return -EINVAL; } - len = le32_to_cpu(header.len); - - data = kzalloc(len, GFP_KERNEL); - if (!data) - return -ENOMEM; - - memcpy_fromio(data, priv->base, len); - data[len - 1] = '\0'; - - err = brcm_nvram_add_cells(priv, data, len); - if (err) { - dev_err(dev, "Failed to add cells: %d\n", err); - return err; + len = le32_to_cpu(header->len); + if (len > priv->nvmem_size) { + dev_err(dev, "NVRAM length (%zd) exceeds mapped size (%zd)\n", len, + priv->nvmem_size); + return -EINVAL; } - kfree(data); + err = brcm_nvram_add_cells(priv, priv->data, len); + if (err) + dev_err(dev, "Failed to add cells: %d\n", err); return 0; } @@ -150,7 +207,6 @@ static int brcm_nvram_probe(struct platform_device *pdev) .reg_read = brcm_nvram_read, }; struct device *dev = &pdev->dev; - struct resource *res; struct brcm_nvram *priv; int err; @@ -159,21 +215,19 @@ static int brcm_nvram_probe(struct platform_device *pdev) return -ENOMEM; priv->dev = dev; - priv->base = devm_platform_get_and_ioremap_resource(pdev, 0, &res); - if (IS_ERR(priv->base)) - return PTR_ERR(priv->base); + err = brcm_nvram_copy_data(priv, pdev); + if (err) + return err; err = brcm_nvram_parse(priv); if (err) return err; - bcm47xx_nvram_init_from_iomem(priv->base, resource_size(res)); - config.dev = dev; config.cells = priv->cells; config.ncells = priv->ncells; config.priv = priv; - config.size = resource_size(res); + config.size = priv->nvmem_size; return PTR_ERR_OR_ZERO(devm_nvmem_register(dev, &config)); } diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index eaf6a3fe8ca6d..5b3955ad40534 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -796,6 +796,12 @@ static struct nvmem_layout *nvmem_layout_get(struct nvmem_device *nvmem) if (!layout_np) return NULL; + /* Fixed layouts don't have a matching driver */ + if (of_device_is_compatible(layout_np, "fixed-layout")) { + of_node_put(layout_np); + return NULL; + } + /* * In case the nvmem device was built-in while the layout was built as a * module, we shall manually request the layout driver loading otherwise diff --git a/drivers/of/address.c b/drivers/of/address.c index e692809ff8227..3219c51777507 100644 --- a/drivers/of/address.c +++ b/drivers/of/address.c @@ -100,6 +100,32 @@ static unsigned int of_bus_default_get_flags(const __be32 *addr) return IORESOURCE_MEM; } +static u64 of_bus_default_flags_map(__be32 *addr, const __be32 *range, int na, + int ns, int pna) +{ + u64 cp, s, da; + + /* Check that flags match */ + if (*addr != *range) + return OF_BAD_ADDR; + + /* Read address values, skipping high cell */ + cp = of_read_number(range + 1, na - 1); + s = of_read_number(range + na + pna, ns); + da = of_read_number(addr + 1, na - 1); + + pr_debug("default flags map, cp=%llx, s=%llx, da=%llx\n", cp, s, da); + + if (da < cp || da >= (cp + s)) + return OF_BAD_ADDR; + return da - cp; +} + +static int of_bus_default_flags_translate(__be32 *addr, u64 offset, int na) +{ + /* Keep "flags" part (high cell) in translated address */ + return of_bus_default_translate(addr + 1, offset, na - 1); +} #ifdef CONFIG_PCI static unsigned int of_bus_pci_get_flags(const __be32 *addr) @@ -374,8 +400,8 @@ static struct of_bus of_busses[] = { .addresses = "reg", .match = of_bus_default_flags_match, .count_cells = of_bus_default_count_cells, - .map = of_bus_default_map, - .translate = of_bus_default_translate, + .map = of_bus_default_flags_map, + .translate = of_bus_default_flags_translate, .has_flags = true, .get_flags = of_bus_default_flags_get_flags, }, diff --git a/drivers/of/dynamic.c b/drivers/of/dynamic.c index f63250c650caf..3bf27052832f3 100644 --- a/drivers/of/dynamic.c +++ b/drivers/of/dynamic.c @@ -98,8 +98,9 @@ int of_reconfig_notify(unsigned long action, struct of_reconfig_data *p) * * Returns the new state of a device based on the notifier used. * - * Return: 0 on device going from enabled to disabled, 1 on device - * going from disabled to enabled and -1 on no change. + * Return: OF_RECONFIG_CHANGE_REMOVE on device going from enabled to + * disabled, OF_RECONFIG_CHANGE_ADD on device going from disabled to + * enabled and OF_RECONFIG_NO_CHANGE on no change. */ int of_reconfig_get_state_change(unsigned long action, struct of_reconfig_data *pr) { diff --git a/drivers/parisc/power.c b/drivers/parisc/power.c index 6f5e5f0230d39..332bcc0053a5e 100644 --- a/drivers/parisc/power.c +++ b/drivers/parisc/power.c @@ -197,6 +197,14 @@ static struct notifier_block parisc_panic_block = { .priority = INT_MAX, }; +/* qemu soft power-off function */ +static int qemu_power_off(struct sys_off_data *data) +{ + /* this turns the system off via SeaBIOS */ + gsc_writel(0, (unsigned long) data->cb_data); + pdc_soft_power_button(1); + return NOTIFY_DONE; +} static int __init power_init(void) { @@ -226,7 +234,13 @@ static int __init power_init(void) soft_power_reg); } - power_task = kthread_run(kpowerswd, (void*)soft_power_reg, KTHREAD_NAME); + power_task = NULL; + if (running_on_qemu && soft_power_reg) + register_sys_off_handler(SYS_OFF_MODE_POWER_OFF, SYS_OFF_PRIO_DEFAULT, + qemu_power_off, (void *)soft_power_reg); + else + power_task = kthread_run(kpowerswd, (void*)soft_power_reg, + KTHREAD_NAME); if (IS_ERR(power_task)) { printk(KERN_ERR DRIVER_NAME ": thread creation failed. Driver not loaded.\n"); pdc_soft_power_button(0); diff --git a/drivers/parport/parport_pc.c b/drivers/parport/parport_pc.c index 1f236aaf7867a..f33b5d1ddfc16 100644 --- a/drivers/parport/parport_pc.c +++ b/drivers/parport/parport_pc.c @@ -2658,6 +2658,8 @@ enum parport_pc_pci_cards { asix_ax99100, quatech_sppxp100, wch_ch382l, + brainboxes_uc146, + brainboxes_px203, }; @@ -2737,6 +2739,8 @@ static struct parport_pc_pci { /* asix_ax99100 */ { 1, { { 0, 1 }, } }, /* quatech_sppxp100 */ { 1, { { 0, 1 }, } }, /* wch_ch382l */ { 1, { { 2, -1 }, } }, + /* brainboxes_uc146 */ { 1, { { 3, -1 }, } }, + /* brainboxes_px203 */ { 1, { { 0, -1 }, } }, }; static const struct pci_device_id parport_pc_pci_tbl[] = { @@ -2833,6 +2837,23 @@ static const struct pci_device_id parport_pc_pci_tbl[] = { PCI_ANY_ID, PCI_ANY_ID, 0, 0, quatech_sppxp100 }, /* WCH CH382L PCI-E single parallel port card */ { 0x1c00, 0x3050, 0x1c00, 0x3050, 0, 0, wch_ch382l }, + /* Brainboxes IX-500/550 */ + { PCI_VENDOR_ID_INTASHIELD, 0x402a, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, oxsemi_pcie_pport }, + /* Brainboxes UC-146/UC-157 */ + { PCI_VENDOR_ID_INTASHIELD, 0x0be1, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, brainboxes_uc146 }, + { PCI_VENDOR_ID_INTASHIELD, 0x0be2, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, brainboxes_uc146 }, + /* Brainboxes PX-146/PX-257 */ + { PCI_VENDOR_ID_INTASHIELD, 0x401c, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, oxsemi_pcie_pport }, + /* Brainboxes PX-203 */ + { PCI_VENDOR_ID_INTASHIELD, 0x4007, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, brainboxes_px203 }, + /* Brainboxes PX-475 */ + { PCI_VENDOR_ID_INTASHIELD, 0x401f, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, oxsemi_pcie_pport }, { 0, } /* terminate list */ }; MODULE_DEVICE_TABLE(pci, parport_pc_pci_tbl); diff --git a/drivers/pci/controller/dwc/pci-exynos.c b/drivers/pci/controller/dwc/pci-exynos.c index 6319082301d68..c6bede3469320 100644 --- a/drivers/pci/controller/dwc/pci-exynos.c +++ b/drivers/pci/controller/dwc/pci-exynos.c @@ -375,7 +375,7 @@ static int exynos_pcie_probe(struct platform_device *pdev) return ret; } -static int __exit exynos_pcie_remove(struct platform_device *pdev) +static int exynos_pcie_remove(struct platform_device *pdev) { struct exynos_pcie *ep = platform_get_drvdata(pdev); @@ -431,7 +431,7 @@ static const struct of_device_id exynos_pcie_of_match[] = { static struct platform_driver exynos_pcie_driver = { .probe = exynos_pcie_probe, - .remove = __exit_p(exynos_pcie_remove), + .remove = exynos_pcie_remove, .driver = { .name = "exynos-pcie", .of_match_table = exynos_pcie_of_match, diff --git a/drivers/pci/controller/dwc/pci-keystone.c b/drivers/pci/controller/dwc/pci-keystone.c index 49aea6ce3e878..0def919f89faf 100644 --- a/drivers/pci/controller/dwc/pci-keystone.c +++ b/drivers/pci/controller/dwc/pci-keystone.c @@ -1100,7 +1100,7 @@ static const struct of_device_id ks_pcie_of_match[] = { { }, }; -static int __init ks_pcie_probe(struct platform_device *pdev) +static int ks_pcie_probe(struct platform_device *pdev) { const struct dw_pcie_host_ops *host_ops; const struct dw_pcie_ep_ops *ep_ops; @@ -1302,7 +1302,7 @@ static int __init ks_pcie_probe(struct platform_device *pdev) return ret; } -static int __exit ks_pcie_remove(struct platform_device *pdev) +static int ks_pcie_remove(struct platform_device *pdev) { struct keystone_pcie *ks_pcie = platform_get_drvdata(pdev); struct device_link **link = ks_pcie->link; @@ -1318,9 +1318,9 @@ static int __exit ks_pcie_remove(struct platform_device *pdev) return 0; } -static struct platform_driver ks_pcie_driver __refdata = { +static struct platform_driver ks_pcie_driver = { .probe = ks_pcie_probe, - .remove = __exit_p(ks_pcie_remove), + .remove = ks_pcie_remove, .driver = { .name = "keystone-pcie", .of_match_table = ks_pcie_of_match, diff --git a/drivers/pci/controller/dwc/pcie-designware.c b/drivers/pci/controller/dwc/pcie-designware.c index 1c1c7348972b0..2b60d20dfdf59 100644 --- a/drivers/pci/controller/dwc/pcie-designware.c +++ b/drivers/pci/controller/dwc/pcie-designware.c @@ -732,6 +732,53 @@ static void dw_pcie_link_set_max_speed(struct dw_pcie *pci, u32 link_gen) } +static void dw_pcie_link_set_max_link_width(struct dw_pcie *pci, u32 num_lanes) +{ + u32 lnkcap, lwsc, plc; + u8 cap; + + if (!num_lanes) + return; + + /* Set the number of lanes */ + plc = dw_pcie_readl_dbi(pci, PCIE_PORT_LINK_CONTROL); + plc &= ~PORT_LINK_FAST_LINK_MODE; + plc &= ~PORT_LINK_MODE_MASK; + + /* Set link width speed control register */ + lwsc = dw_pcie_readl_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL); + lwsc &= ~PORT_LOGIC_LINK_WIDTH_MASK; + switch (num_lanes) { + case 1: + plc |= PORT_LINK_MODE_1_LANES; + lwsc |= PORT_LOGIC_LINK_WIDTH_1_LANES; + break; + case 2: + plc |= PORT_LINK_MODE_2_LANES; + lwsc |= PORT_LOGIC_LINK_WIDTH_2_LANES; + break; + case 4: + plc |= PORT_LINK_MODE_4_LANES; + lwsc |= PORT_LOGIC_LINK_WIDTH_4_LANES; + break; + case 8: + plc |= PORT_LINK_MODE_8_LANES; + lwsc |= PORT_LOGIC_LINK_WIDTH_8_LANES; + break; + default: + dev_err(pci->dev, "num-lanes %u: invalid value\n", num_lanes); + return; + } + dw_pcie_writel_dbi(pci, PCIE_PORT_LINK_CONTROL, plc); + dw_pcie_writel_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL, lwsc); + + cap = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + lnkcap = dw_pcie_readl_dbi(pci, cap + PCI_EXP_LNKCAP); + lnkcap &= ~PCI_EXP_LNKCAP_MLW; + lnkcap |= FIELD_PREP(PCI_EXP_LNKCAP_MLW, num_lanes); + dw_pcie_writel_dbi(pci, cap + PCI_EXP_LNKCAP, lnkcap); +} + void dw_pcie_iatu_detect(struct dw_pcie *pci) { int max_region, ob, ib; @@ -1013,49 +1060,5 @@ void dw_pcie_setup(struct dw_pcie *pci) val |= PORT_LINK_DLL_LINK_EN; dw_pcie_writel_dbi(pci, PCIE_PORT_LINK_CONTROL, val); - if (!pci->num_lanes) { - dev_dbg(pci->dev, "Using h/w default number of lanes\n"); - return; - } - - /* Set the number of lanes */ - val &= ~PORT_LINK_FAST_LINK_MODE; - val &= ~PORT_LINK_MODE_MASK; - switch (pci->num_lanes) { - case 1: - val |= PORT_LINK_MODE_1_LANES; - break; - case 2: - val |= PORT_LINK_MODE_2_LANES; - break; - case 4: - val |= PORT_LINK_MODE_4_LANES; - break; - case 8: - val |= PORT_LINK_MODE_8_LANES; - break; - default: - dev_err(pci->dev, "num-lanes %u: invalid value\n", pci->num_lanes); - return; - } - dw_pcie_writel_dbi(pci, PCIE_PORT_LINK_CONTROL, val); - - /* Set link width speed control register */ - val = dw_pcie_readl_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL); - val &= ~PORT_LOGIC_LINK_WIDTH_MASK; - switch (pci->num_lanes) { - case 1: - val |= PORT_LOGIC_LINK_WIDTH_1_LANES; - break; - case 2: - val |= PORT_LOGIC_LINK_WIDTH_2_LANES; - break; - case 4: - val |= PORT_LOGIC_LINK_WIDTH_4_LANES; - break; - case 8: - val |= PORT_LOGIC_LINK_WIDTH_8_LANES; - break; - } - dw_pcie_writel_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL, val); + dw_pcie_link_set_max_link_width(pci, pci->num_lanes); } diff --git a/drivers/pci/controller/dwc/pcie-kirin.c b/drivers/pci/controller/dwc/pcie-kirin.c index d93bc29069502..2ee146767971c 100644 --- a/drivers/pci/controller/dwc/pcie-kirin.c +++ b/drivers/pci/controller/dwc/pcie-kirin.c @@ -741,7 +741,7 @@ static int kirin_pcie_power_on(struct platform_device *pdev, return ret; } -static int __exit kirin_pcie_remove(struct platform_device *pdev) +static int kirin_pcie_remove(struct platform_device *pdev) { struct kirin_pcie *kirin_pcie = platform_get_drvdata(pdev); @@ -818,7 +818,7 @@ static int kirin_pcie_probe(struct platform_device *pdev) static struct platform_driver kirin_pcie_driver = { .probe = kirin_pcie_probe, - .remove = __exit_p(kirin_pcie_remove), + .remove = kirin_pcie_remove, .driver = { .name = "kirin-pcie", .of_match_table = kirin_pcie_match, diff --git a/drivers/pci/controller/dwc/pcie-qcom-ep.c b/drivers/pci/controller/dwc/pcie-qcom-ep.c index 8bd8107690a6c..9b62ee6992f0e 100644 --- a/drivers/pci/controller/dwc/pcie-qcom-ep.c +++ b/drivers/pci/controller/dwc/pcie-qcom-ep.c @@ -123,6 +123,7 @@ /* ELBI registers */ #define ELBI_SYS_STTS 0x08 +#define ELBI_CS2_ENABLE 0xa4 /* DBI registers */ #define DBI_CON_STATUS 0x44 @@ -263,6 +264,21 @@ static void qcom_pcie_dw_stop_link(struct dw_pcie *pci) disable_irq(pcie_ep->perst_irq); } +static void qcom_pcie_dw_write_dbi2(struct dw_pcie *pci, void __iomem *base, + u32 reg, size_t size, u32 val) +{ + struct qcom_pcie_ep *pcie_ep = to_pcie_ep(pci); + int ret; + + writel(1, pcie_ep->elbi + ELBI_CS2_ENABLE); + + ret = dw_pcie_write(pci->dbi_base2 + reg, size, val); + if (ret) + dev_err(pci->dev, "Failed to write DBI2 register (0x%x): %d\n", reg, ret); + + writel(0, pcie_ep->elbi + ELBI_CS2_ENABLE); +} + static void qcom_pcie_ep_icc_update(struct qcom_pcie_ep *pcie_ep) { struct dw_pcie *pci = &pcie_ep->pci; @@ -519,6 +535,7 @@ static const struct dw_pcie_ops pci_ops = { .link_up = qcom_pcie_dw_link_up, .start_link = qcom_pcie_dw_start_link, .stop_link = qcom_pcie_dw_stop_link, + .write_dbi2 = qcom_pcie_dw_write_dbi2, }; static int qcom_pcie_ep_get_io_resources(struct platform_device *pdev, diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c index 4bba31502ce1d..248cd9347e8fd 100644 --- a/drivers/pci/controller/dwc/pcie-tegra194.c +++ b/drivers/pci/controller/dwc/pcie-tegra194.c @@ -9,6 +9,7 @@ * Author: Vidya Sagar */ +#include #include #include #include @@ -346,8 +347,7 @@ static void apply_bad_link_workaround(struct dw_pcie_rp *pp) */ val = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base + PCI_EXP_LNKSTA); if (val & PCI_EXP_LNKSTA_LBMS) { - current_link_width = (val & PCI_EXP_LNKSTA_NLW) >> - PCI_EXP_LNKSTA_NLW_SHIFT; + current_link_width = FIELD_GET(PCI_EXP_LNKSTA_NLW, val); if (pcie->init_link_width > current_link_width) { dev_warn(pci->dev, "PCIe link is bad, width reduced\n"); val = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base + @@ -760,8 +760,7 @@ static void tegra_pcie_enable_system_interrupts(struct dw_pcie_rp *pp) val_w = dw_pcie_readw_dbi(&pcie->pci, pcie->pcie_cap_base + PCI_EXP_LNKSTA); - pcie->init_link_width = (val_w & PCI_EXP_LNKSTA_NLW) >> - PCI_EXP_LNKSTA_NLW_SHIFT; + pcie->init_link_width = FIELD_GET(PCI_EXP_LNKSTA_NLW, val_w); val_w = dw_pcie_readw_dbi(&pcie->pci, pcie->pcie_cap_base + PCI_EXP_LNKCTL); @@ -920,7 +919,7 @@ static int tegra_pcie_dw_host_init(struct dw_pcie_rp *pp) /* Configure Max lane width from DT */ val = dw_pcie_readl_dbi(pci, pcie->pcie_cap_base + PCI_EXP_LNKCAP); val &= ~PCI_EXP_LNKCAP_MLW; - val |= (pcie->num_lanes << PCI_EXP_LNKSTA_NLW_SHIFT); + val |= FIELD_PREP(PCI_EXP_LNKCAP_MLW, pcie->num_lanes); dw_pcie_writel_dbi(pci, pcie->pcie_cap_base + PCI_EXP_LNKCAP, val); /* Clear Slot Clock Configuration bit if SRNS configuration */ diff --git a/drivers/pci/controller/pci-loongson.c b/drivers/pci/controller/pci-loongson.c index d45e7b8dc530d..8b34ccff073a9 100644 --- a/drivers/pci/controller/pci-loongson.c +++ b/drivers/pci/controller/pci-loongson.c @@ -80,13 +80,49 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, DEV_LS7A_LPC, system_bus_quirk); +/* + * Some Loongson PCIe ports have hardware limitations on their Maximum Read + * Request Size. They can't handle anything larger than this. Sane + * firmware will set proper MRRS at boot, so we only need no_inc_mrrs for + * bridges. However, some MIPS Loongson firmware doesn't set MRRS properly, + * so we have to enforce maximum safe MRRS, which is 256 bytes. + */ +#ifdef CONFIG_MIPS +static void loongson_set_min_mrrs_quirk(struct pci_dev *pdev) +{ + struct pci_bus *bus = pdev->bus; + struct pci_dev *bridge; + static const struct pci_device_id bridge_devids[] = { + { PCI_VDEVICE(LOONGSON, DEV_LS2K_PCIE_PORT0) }, + { PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT0) }, + { PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT1) }, + { PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT2) }, + { PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT3) }, + { PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT4) }, + { PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT5) }, + { PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT6) }, + { 0, }, + }; + + /* look for the matching bridge */ + while (!pci_is_root_bus(bus)) { + bridge = bus->self; + bus = bus->parent; + + if (pci_match_id(bridge_devids, bridge)) { + if (pcie_get_readrq(pdev) > 256) { + pci_info(pdev, "limiting MRRS to 256\n"); + pcie_set_readrq(pdev, 256); + } + break; + } + } +} +DECLARE_PCI_FIXUP_ENABLE(PCI_ANY_ID, PCI_ANY_ID, loongson_set_min_mrrs_quirk); +#endif + static void loongson_mrrs_quirk(struct pci_dev *pdev) { - /* - * Some Loongson PCIe ports have h/w limitations of maximum read - * request size. They can't handle anything larger than this. So - * force this limit on any devices attached under these ports. - */ struct pci_host_bridge *bridge = pci_find_host_bridge(pdev->bus); bridge->no_inc_mrrs = 1; diff --git a/drivers/pci/controller/pci-mvebu.c b/drivers/pci/controller/pci-mvebu.c index 60810a1fbfb75..29fe09c99e7d9 100644 --- a/drivers/pci/controller/pci-mvebu.c +++ b/drivers/pci/controller/pci-mvebu.c @@ -264,7 +264,7 @@ static void mvebu_pcie_setup_hw(struct mvebu_pcie_port *port) */ lnkcap = mvebu_readl(port, PCIE_CAP_PCIEXP + PCI_EXP_LNKCAP); lnkcap &= ~PCI_EXP_LNKCAP_MLW; - lnkcap |= (port->is_x4 ? 4 : 1) << 4; + lnkcap |= FIELD_PREP(PCI_EXP_LNKCAP_MLW, port->is_x4 ? 4 : 1); mvebu_writel(port, lnkcap, PCIE_CAP_PCIEXP + PCI_EXP_LNKCAP); /* Disable Root Bridge I/O space, memory space and bus mastering. */ diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c index 1c1c1aa940a51..6ac0afae0ca18 100644 --- a/drivers/pci/controller/vmd.c +++ b/drivers/pci/controller/vmd.c @@ -751,7 +751,7 @@ static int vmd_pm_enable_quirk(struct pci_dev *pdev, void *userdata) if (!(features & VMD_FEAT_BIOS_PM_QUIRK)) return 0; - pci_enable_link_state(pdev, PCIE_LINK_STATE_ALL); + pci_enable_link_state_locked(pdev, PCIE_LINK_STATE_ALL); pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_LTR); if (!pos) diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c index 601129772b2d5..5b1f271c6034b 100644 --- a/drivers/pci/hotplug/acpiphp_glue.c +++ b/drivers/pci/hotplug/acpiphp_glue.c @@ -512,15 +512,12 @@ static void enable_slot(struct acpiphp_slot *slot, bool bridge) if (pass && dev->subordinate) { check_hotplug_bridge(slot, dev); pcibios_resource_survey_bus(dev->subordinate); - if (pci_is_root_bus(bus)) - __pci_bus_size_bridges(dev->subordinate, &add_list); + __pci_bus_size_bridges(dev->subordinate, + &add_list); } } } - if (pci_is_root_bus(bus)) - __pci_bus_assign_resources(bus, &add_list, NULL); - else - pci_assign_unassigned_bridge_resources(bus->self); + __pci_bus_assign_resources(bus, &add_list, NULL); } acpiphp_sanitize_bus(bus); diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c index a05350a4e49cb..05b7357bd2586 100644 --- a/drivers/pci/pci-acpi.c +++ b/drivers/pci/pci-acpi.c @@ -911,7 +911,7 @@ pci_power_t acpi_pci_choose_state(struct pci_dev *pdev) { int acpi_state, d_max; - if (pdev->no_d3cold) + if (pdev->no_d3cold || !pdev->d3cold_allowed) d_max = ACPI_STATE_D3_HOT; else d_max = ACPI_STATE_D3_COLD; diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index d9eede2dbc0e1..3317b93547167 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -12,7 +12,7 @@ * Modeled after usb's driverfs.c */ - +#include #include #include #include @@ -230,8 +230,7 @@ static ssize_t current_link_width_show(struct device *dev, if (err) return -EINVAL; - return sysfs_emit(buf, "%u\n", - (linkstat & PCI_EXP_LNKSTA_NLW) >> PCI_EXP_LNKSTA_NLW_SHIFT); + return sysfs_emit(buf, "%u\n", FIELD_GET(PCI_EXP_LNKSTA_NLW, linkstat)); } static DEVICE_ATTR_RO(current_link_width); @@ -530,10 +529,7 @@ static ssize_t d3cold_allowed_store(struct device *dev, return -EINVAL; pdev->d3cold_allowed = !!val; - if (pdev->d3cold_allowed) - pci_d3cold_enable(pdev); - else - pci_d3cold_disable(pdev); + pci_bridge_d3_update(pdev); pm_runtime_resume(dev); diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 59c01d68c6d5e..a607f277ccf10 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -732,15 +732,18 @@ u16 pci_find_vsec_capability(struct pci_dev *dev, u16 vendor, int cap) { u16 vsec = 0; u32 header; + int ret; if (vendor != dev->vendor) return 0; while ((vsec = pci_find_next_ext_capability(dev, vsec, PCI_EXT_CAP_ID_VNDR))) { - if (pci_read_config_dword(dev, vsec + PCI_VNDR_HEADER, - &header) == PCIBIOS_SUCCESSFUL && - PCI_VNDR_HEADER_ID(header) == cap) + ret = pci_read_config_dword(dev, vsec + PCI_VNDR_HEADER, &header); + if (ret != PCIBIOS_SUCCESSFUL) + continue; + + if (PCI_VNDR_HEADER_ID(header) == cap) return vsec; } @@ -3752,14 +3755,14 @@ u32 pci_rebar_get_possible_sizes(struct pci_dev *pdev, int bar) return 0; pci_read_config_dword(pdev, pos + PCI_REBAR_CAP, &cap); - cap &= PCI_REBAR_CAP_SIZES; + cap = FIELD_GET(PCI_REBAR_CAP_SIZES, cap); /* Sapphire RX 5600 XT Pulse has an invalid cap dword for BAR 0 */ if (pdev->vendor == PCI_VENDOR_ID_ATI && pdev->device == 0x731f && - bar == 0 && cap == 0x7000) - cap = 0x3f000; + bar == 0 && cap == 0x700) + return 0x3f00; - return cap >> 4; + return cap; } EXPORT_SYMBOL(pci_rebar_get_possible_sizes); @@ -6257,8 +6260,7 @@ u32 pcie_bandwidth_available(struct pci_dev *dev, struct pci_dev **limiting_dev, pcie_capability_read_word(dev, PCI_EXP_LNKSTA, &lnksta); next_speed = pcie_link_speed[lnksta & PCI_EXP_LNKSTA_CLS]; - next_width = (lnksta & PCI_EXP_LNKSTA_NLW) >> - PCI_EXP_LNKSTA_NLW_SHIFT; + next_width = FIELD_GET(PCI_EXP_LNKSTA_NLW, lnksta); next_bw = next_width * PCIE_SPEED2MBS_ENC(next_speed); @@ -6330,7 +6332,7 @@ enum pcie_link_width pcie_get_width_cap(struct pci_dev *dev) pcie_capability_read_dword(dev, PCI_EXP_LNKCAP, &lnkcap); if (lnkcap) - return (lnkcap & PCI_EXP_LNKCAP_MLW) >> 4; + return FIELD_GET(PCI_EXP_LNKCAP_MLW, lnkcap); return PCIE_LNK_WIDTH_UNKNOWN; } diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c index 9c8fd69ae5ad8..40d84cb0c601e 100644 --- a/drivers/pci/pcie/aer.c +++ b/drivers/pci/pcie/aer.c @@ -29,6 +29,7 @@ #include #include #include +#include #include #include "../pci.h" @@ -997,6 +998,15 @@ static void aer_recover_work_func(struct work_struct *work) continue; } cper_print_aer(pdev, entry.severity, entry.regs); + /* + * Memory for aer_capability_regs(entry.regs) is being allocated from the + * ghes_estatus_pool to protect it from overwriting when multiple sections + * are present in the error status. Thus free the same after processing + * the data. + */ + ghes_estatus_pool_region_free((unsigned long)entry.regs, + sizeof(struct aer_capability_regs)); + if (entry.severity == AER_NONFATAL) pcie_do_recovery(pdev, pci_channel_io_normal, aer_root_reset); diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index 530c3bb5708c5..67b13f26ba7c7 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -1102,17 +1102,7 @@ int pci_disable_link_state(struct pci_dev *pdev, int state) } EXPORT_SYMBOL(pci_disable_link_state); -/** - * pci_enable_link_state - Clear and set the default device link state so that - * the link may be allowed to enter the specified states. Note that if the - * BIOS didn't grant ASPM control to the OS, this does nothing because we can't - * touch the LNKCTL register. Also note that this does not enable states - * disabled by pci_disable_link_state(). Return 0 or a negative errno. - * - * @pdev: PCI device - * @state: Mask of ASPM link states to enable - */ -int pci_enable_link_state(struct pci_dev *pdev, int state) +static int __pci_enable_link_state(struct pci_dev *pdev, int state, bool locked) { struct pcie_link_state *link = pcie_aspm_get_link(pdev); @@ -1129,7 +1119,8 @@ int pci_enable_link_state(struct pci_dev *pdev, int state) return -EPERM; } - down_read(&pci_bus_sem); + if (!locked) + down_read(&pci_bus_sem); mutex_lock(&aspm_lock); link->aspm_default = 0; if (state & PCIE_LINK_STATE_L0S) @@ -1150,12 +1141,48 @@ int pci_enable_link_state(struct pci_dev *pdev, int state) link->clkpm_default = (state & PCIE_LINK_STATE_CLKPM) ? 1 : 0; pcie_set_clkpm(link, policy_to_clkpm_state(link)); mutex_unlock(&aspm_lock); - up_read(&pci_bus_sem); + if (!locked) + up_read(&pci_bus_sem); return 0; } + +/** + * pci_enable_link_state - Clear and set the default device link state so that + * the link may be allowed to enter the specified states. Note that if the + * BIOS didn't grant ASPM control to the OS, this does nothing because we can't + * touch the LNKCTL register. Also note that this does not enable states + * disabled by pci_disable_link_state(). Return 0 or a negative errno. + * + * @pdev: PCI device + * @state: Mask of ASPM link states to enable + */ +int pci_enable_link_state(struct pci_dev *pdev, int state) +{ + return __pci_enable_link_state(pdev, state, false); +} EXPORT_SYMBOL(pci_enable_link_state); +/** + * pci_enable_link_state_locked - Clear and set the default device link state + * so that the link may be allowed to enter the specified states. Note that if + * the BIOS didn't grant ASPM control to the OS, this does nothing because we + * can't touch the LNKCTL register. Also note that this does not enable states + * disabled by pci_disable_link_state(). Return 0 or a negative errno. + * + * @pdev: PCI device + * @state: Mask of ASPM link states to enable + * + * Context: Caller holds pci_bus_sem read lock. + */ +int pci_enable_link_state_locked(struct pci_dev *pdev, int state) +{ + lockdep_assert_held_read(&pci_bus_sem); + + return __pci_enable_link_state(pdev, state, true); +} +EXPORT_SYMBOL(pci_enable_link_state_locked); + static int pcie_aspm_set_policy(const char *val, const struct kernel_param *kp) { @@ -1248,6 +1275,8 @@ static ssize_t aspm_attr_store_common(struct device *dev, link->aspm_disable &= ~ASPM_STATE_L1; } else { link->aspm_disable |= state; + if (state & ASPM_STATE_L1) + link->aspm_disable |= ASPM_STATE_L1SS; } pcie_config_aspm_link(link, policy_to_aspm_state(link)); diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 795534589b985..43159965e09e9 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -1652,15 +1652,15 @@ static void pci_set_removable(struct pci_dev *dev) static bool pci_ext_cfg_is_aliased(struct pci_dev *dev) { #ifdef CONFIG_PCI_QUIRKS - int pos; + int pos, ret; u32 header, tmp; pci_read_config_dword(dev, PCI_VENDOR_ID, &header); for (pos = PCI_CFG_SPACE_SIZE; pos < PCI_CFG_SPACE_EXP_SIZE; pos += PCI_CFG_SPACE_SIZE) { - if (pci_read_config_dword(dev, pos, &tmp) != PCIBIOS_SUCCESSFUL - || header != tmp) + ret = pci_read_config_dword(dev, pos, &tmp); + if ((ret != PCIBIOS_SUCCESSFUL) || (header != tmp)) return false; } diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index e3e915329510f..ae95d09507722 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -5385,7 +5385,7 @@ int pci_dev_specific_disable_acs_redir(struct pci_dev *dev) */ static void quirk_intel_qat_vf_cap(struct pci_dev *pdev) { - int pos, i = 0; + int pos, i = 0, ret; u8 next_cap; u16 reg16, *cap; struct pci_cap_saved_state *state; @@ -5431,8 +5431,8 @@ static void quirk_intel_qat_vf_cap(struct pci_dev *pdev) pdev->pcie_mpss = reg16 & PCI_EXP_DEVCAP_PAYLOAD; pdev->cfg_size = PCI_CFG_SPACE_EXP_SIZE; - if (pci_read_config_dword(pdev, PCI_CFG_SPACE_SIZE, &status) != - PCIBIOS_SUCCESSFUL || (status == 0xffffffff)) + ret = pci_read_config_dword(pdev, PCI_CFG_SPACE_SIZE, &status); + if ((ret != PCIBIOS_SUCCESSFUL) || (PCI_POSSIBLE_ERROR(status))) pdev->cfg_size = PCI_CFG_SPACE_SIZE; if (pci_find_saved_cap(pdev, PCI_CAP_ID_EXP)) @@ -5509,6 +5509,12 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, 0x0420, quirk_no_ext_tags); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, 0x0422, quirk_no_ext_tags); #ifdef CONFIG_PCI_ATS +static void quirk_no_ats(struct pci_dev *pdev) +{ + pci_info(pdev, "disabling ATS\n"); + pdev->ats_cap = 0; +} + /* * Some devices require additional driver setup to enable ATS. Don't use * ATS for those devices as ATS will be enabled before the driver has had a @@ -5522,14 +5528,10 @@ static void quirk_amd_harvest_no_ats(struct pci_dev *pdev) (pdev->subsystem_device == 0xce19 || pdev->subsystem_device == 0xcc10 || pdev->subsystem_device == 0xcc08)) - goto no_ats; - else - return; + quirk_no_ats(pdev); + } else { + quirk_no_ats(pdev); } - -no_ats: - pci_info(pdev, "disabling ATS\n"); - pdev->ats_cap = 0; } /* AMD Stoney platform GPU */ @@ -5552,6 +5554,25 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7347, quirk_amd_harvest_no_ats); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x734f, quirk_amd_harvest_no_ats); /* AMD Raven platform iGPU */ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x15d8, quirk_amd_harvest_no_ats); + +/* + * Intel IPU E2000 revisions before C0 implement incorrect endianness + * in ATS Invalidate Request message body. Disable ATS for those devices. + */ +static void quirk_intel_e2000_no_ats(struct pci_dev *pdev) +{ + if (pdev->revision < 0x20) + quirk_no_ats(pdev); +} +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x1451, quirk_intel_e2000_no_ats); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x1452, quirk_intel_e2000_no_ats); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x1453, quirk_intel_e2000_no_ats); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x1454, quirk_intel_e2000_no_ats); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x1455, quirk_intel_e2000_no_ats); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x1457, quirk_intel_e2000_no_ats); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x1459, quirk_intel_e2000_no_ats); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x145a, quirk_intel_e2000_no_ats); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x145c, quirk_intel_e2000_no_ats); #endif /* CONFIG_PCI_ATS */ /* Freescale PCIe doesn't support MSI in RC mode */ @@ -6190,3 +6211,15 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a31, dpc_log_size); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_XILINX, 0x5020, of_pci_make_dev_node); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_XILINX, 0x5021, of_pci_make_dev_node); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_REDHAT, 0x0005, of_pci_make_dev_node); + +/* + * Devices known to require a longer delay before first config space access + * after reset recovery or resume from D3cold: + * + * VideoPropulsion (aka Genroco) Torrent QN16e MPEG QAM Modulator + */ +static void pci_fixup_d3cold_delay_1sec(struct pci_dev *pdev) +{ + pdev->d3cold_delay = 1000; +} +DECLARE_PCI_FIXUP_FINAL(0x5555, 0x0004, pci_fixup_d3cold_delay_1sec); diff --git a/drivers/perf/arm_cspmu/arm_cspmu.c b/drivers/perf/arm_cspmu/arm_cspmu.c index e2b7827c45635..9363c31f31b89 100644 --- a/drivers/perf/arm_cspmu/arm_cspmu.c +++ b/drivers/perf/arm_cspmu/arm_cspmu.c @@ -635,6 +635,9 @@ static int arm_cspmu_event_init(struct perf_event *event) cspmu = to_arm_cspmu(event->pmu); + if (event->attr.type != event->pmu->type) + return -ENOENT; + /* * Following other "uncore" PMUs, we do not support sampling mode or * attach to a task (per-process mode). diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c index fcb0c70ca2225..cd8a2b9efd787 100644 --- a/drivers/perf/riscv_pmu_sbi.c +++ b/drivers/perf/riscv_pmu_sbi.c @@ -687,6 +687,11 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev) /* Firmware counter don't support overflow yet */ fidx = find_first_bit(cpu_hw_evt->used_hw_ctrs, RISCV_MAX_COUNTERS); + if (fidx == RISCV_MAX_COUNTERS) { + csr_clear(CSR_SIP, BIT(riscv_pmu_irq_num)); + return IRQ_NONE; + } + event = cpu_hw_evt->events[fidx]; if (!event) { csr_clear(CSR_SIP, BIT(riscv_pmu_irq_num)); diff --git a/drivers/phy/Kconfig b/drivers/phy/Kconfig index d1670bbe6d6bc..e4502958fd62d 100644 --- a/drivers/phy/Kconfig +++ b/drivers/phy/Kconfig @@ -87,7 +87,6 @@ source "drivers/phy/motorola/Kconfig" source "drivers/phy/mscc/Kconfig" source "drivers/phy/qualcomm/Kconfig" source "drivers/phy/ralink/Kconfig" -source "drivers/phy/realtek/Kconfig" source "drivers/phy/renesas/Kconfig" source "drivers/phy/rockchip/Kconfig" source "drivers/phy/samsung/Kconfig" diff --git a/drivers/phy/Makefile b/drivers/phy/Makefile index 868a220ed0f6d..fb3dc9de61115 100644 --- a/drivers/phy/Makefile +++ b/drivers/phy/Makefile @@ -26,7 +26,6 @@ obj-y += allwinner/ \ mscc/ \ qualcomm/ \ ralink/ \ - realtek/ \ renesas/ \ rockchip/ \ samsung/ \ diff --git a/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c b/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c index 52c275fbb2a1c..d4fb85c20eb0f 100644 --- a/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c +++ b/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c @@ -24,23 +24,73 @@ #define EUSB2_FORCE_VAL_5 0xeD #define V_CLK_19P2M_EN BIT(6) +#define EUSB2_TUNE_USB2_CROSSOVER 0x50 #define EUSB2_TUNE_IUSB2 0x51 +#define EUSB2_TUNE_RES_FSDIF 0x52 +#define EUSB2_TUNE_HSDISC 0x53 #define EUSB2_TUNE_SQUELCH_U 0x54 +#define EUSB2_TUNE_USB2_SLEW 0x55 +#define EUSB2_TUNE_USB2_EQU 0x56 #define EUSB2_TUNE_USB2_PREEM 0x57 +#define EUSB2_TUNE_USB2_HS_COMP_CUR 0x58 +#define EUSB2_TUNE_EUSB_SLEW 0x59 +#define EUSB2_TUNE_EUSB_EQU 0x5A +#define EUSB2_TUNE_EUSB_HS_COMP_CUR 0x5B -#define QCOM_EUSB2_REPEATER_INIT_CFG(o, v) \ +#define QCOM_EUSB2_REPEATER_INIT_CFG(r, v) \ { \ - .offset = o, \ + .reg = r, \ .val = v, \ } -struct eusb2_repeater_init_tbl { - unsigned int offset; - unsigned int val; +enum reg_fields { + F_TUNE_EUSB_HS_COMP_CUR, + F_TUNE_EUSB_EQU, + F_TUNE_EUSB_SLEW, + F_TUNE_USB2_HS_COMP_CUR, + F_TUNE_USB2_PREEM, + F_TUNE_USB2_EQU, + F_TUNE_USB2_SLEW, + F_TUNE_SQUELCH_U, + F_TUNE_HSDISC, + F_TUNE_RES_FSDIF, + F_TUNE_IUSB2, + F_TUNE_USB2_CROSSOVER, + F_NUM_TUNE_FIELDS, + + F_FORCE_VAL_5 = F_NUM_TUNE_FIELDS, + F_FORCE_EN_5, + + F_EN_CTL1, + + F_RPTR_STATUS, + F_NUM_FIELDS, +}; + +static struct reg_field eusb2_repeater_tune_reg_fields[F_NUM_FIELDS] = { + [F_TUNE_EUSB_HS_COMP_CUR] = REG_FIELD(EUSB2_TUNE_EUSB_HS_COMP_CUR, 0, 1), + [F_TUNE_EUSB_EQU] = REG_FIELD(EUSB2_TUNE_EUSB_EQU, 0, 1), + [F_TUNE_EUSB_SLEW] = REG_FIELD(EUSB2_TUNE_EUSB_SLEW, 0, 1), + [F_TUNE_USB2_HS_COMP_CUR] = REG_FIELD(EUSB2_TUNE_USB2_HS_COMP_CUR, 0, 1), + [F_TUNE_USB2_PREEM] = REG_FIELD(EUSB2_TUNE_USB2_PREEM, 0, 2), + [F_TUNE_USB2_EQU] = REG_FIELD(EUSB2_TUNE_USB2_EQU, 0, 1), + [F_TUNE_USB2_SLEW] = REG_FIELD(EUSB2_TUNE_USB2_SLEW, 0, 1), + [F_TUNE_SQUELCH_U] = REG_FIELD(EUSB2_TUNE_SQUELCH_U, 0, 2), + [F_TUNE_HSDISC] = REG_FIELD(EUSB2_TUNE_HSDISC, 0, 2), + [F_TUNE_RES_FSDIF] = REG_FIELD(EUSB2_TUNE_RES_FSDIF, 0, 2), + [F_TUNE_IUSB2] = REG_FIELD(EUSB2_TUNE_IUSB2, 0, 3), + [F_TUNE_USB2_CROSSOVER] = REG_FIELD(EUSB2_TUNE_USB2_CROSSOVER, 0, 2), + + [F_FORCE_VAL_5] = REG_FIELD(EUSB2_FORCE_VAL_5, 0, 7), + [F_FORCE_EN_5] = REG_FIELD(EUSB2_FORCE_EN_5, 0, 7), + + [F_EN_CTL1] = REG_FIELD(EUSB2_EN_CTL1, 0, 7), + + [F_RPTR_STATUS] = REG_FIELD(EUSB2_RPTR_STATUS, 0, 7), }; struct eusb2_repeater_cfg { - const struct eusb2_repeater_init_tbl *init_tbl; + const u32 *init_tbl; int init_tbl_num; const char * const *vreg_list; int num_vregs; @@ -48,11 +98,10 @@ struct eusb2_repeater_cfg { struct eusb2_repeater { struct device *dev; - struct regmap *regmap; + struct regmap_field *regs[F_NUM_FIELDS]; struct phy *phy; struct regulator_bulk_data *vregs; const struct eusb2_repeater_cfg *cfg; - u16 base; enum phy_mode mode; }; @@ -60,10 +109,10 @@ static const char * const pm8550b_vreg_l[] = { "vdd18", "vdd3", }; -static const struct eusb2_repeater_init_tbl pm8550b_init_tbl[] = { - QCOM_EUSB2_REPEATER_INIT_CFG(EUSB2_TUNE_IUSB2, 0x8), - QCOM_EUSB2_REPEATER_INIT_CFG(EUSB2_TUNE_SQUELCH_U, 0x3), - QCOM_EUSB2_REPEATER_INIT_CFG(EUSB2_TUNE_USB2_PREEM, 0x5), +static const u32 pm8550b_init_tbl[F_NUM_TUNE_FIELDS] = { + [F_TUNE_IUSB2] = 0x8, + [F_TUNE_SQUELCH_U] = 0x3, + [F_TUNE_USB2_PREEM] = 0x5, }; static const struct eusb2_repeater_cfg pm8550b_eusb2_cfg = { @@ -91,9 +140,9 @@ static int eusb2_repeater_init_vregs(struct eusb2_repeater *rptr) static int eusb2_repeater_init(struct phy *phy) { + struct reg_field *regfields = eusb2_repeater_tune_reg_fields; struct eusb2_repeater *rptr = phy_get_drvdata(phy); - const struct eusb2_repeater_init_tbl *init_tbl = rptr->cfg->init_tbl; - int num = rptr->cfg->init_tbl_num; + const u32 *init_tbl = rptr->cfg->init_tbl; u32 val; int ret; int i; @@ -102,17 +151,21 @@ static int eusb2_repeater_init(struct phy *phy) if (ret) return ret; - regmap_update_bits(rptr->regmap, rptr->base + EUSB2_EN_CTL1, - EUSB2_RPTR_EN, EUSB2_RPTR_EN); + regmap_field_update_bits(rptr->regs[F_EN_CTL1], EUSB2_RPTR_EN, EUSB2_RPTR_EN); - for (i = 0; i < num; i++) - regmap_update_bits(rptr->regmap, - rptr->base + init_tbl[i].offset, - init_tbl[i].val, init_tbl[i].val); + for (i = 0; i < F_NUM_TUNE_FIELDS; i++) { + if (init_tbl[i]) { + regmap_field_update_bits(rptr->regs[i], init_tbl[i], init_tbl[i]); + } else { + /* Write 0 if there's no value set */ + u32 mask = GENMASK(regfields[i].msb, regfields[i].lsb); + + regmap_field_update_bits(rptr->regs[i], mask, 0); + } + } - ret = regmap_read_poll_timeout(rptr->regmap, - rptr->base + EUSB2_RPTR_STATUS, val, - val & RPTR_OK, 10, 5); + ret = regmap_field_read_poll_timeout(rptr->regs[F_RPTR_STATUS], + val, val & RPTR_OK, 10, 5); if (ret) dev_err(rptr->dev, "initialization timed-out\n"); @@ -131,10 +184,10 @@ static int eusb2_repeater_set_mode(struct phy *phy, * per eUSB 1.2 Spec. Below implement software workaround until * PHY and controller is fixing seen observation. */ - regmap_update_bits(rptr->regmap, rptr->base + EUSB2_FORCE_EN_5, - F_CLK_19P2M_EN, F_CLK_19P2M_EN); - regmap_update_bits(rptr->regmap, rptr->base + EUSB2_FORCE_VAL_5, - V_CLK_19P2M_EN, V_CLK_19P2M_EN); + regmap_field_update_bits(rptr->regs[F_FORCE_EN_5], + F_CLK_19P2M_EN, F_CLK_19P2M_EN); + regmap_field_update_bits(rptr->regs[F_FORCE_VAL_5], + V_CLK_19P2M_EN, V_CLK_19P2M_EN); break; case PHY_MODE_USB_DEVICE: /* @@ -143,10 +196,10 @@ static int eusb2_repeater_set_mode(struct phy *phy, * repeater doesn't clear previous value due to shared * regulators (say host <-> device mode switch). */ - regmap_update_bits(rptr->regmap, rptr->base + EUSB2_FORCE_EN_5, - F_CLK_19P2M_EN, 0); - regmap_update_bits(rptr->regmap, rptr->base + EUSB2_FORCE_VAL_5, - V_CLK_19P2M_EN, 0); + regmap_field_update_bits(rptr->regs[F_FORCE_EN_5], + F_CLK_19P2M_EN, 0); + regmap_field_update_bits(rptr->regs[F_FORCE_VAL_5], + V_CLK_19P2M_EN, 0); break; default: return -EINVAL; @@ -175,8 +228,9 @@ static int eusb2_repeater_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct phy_provider *phy_provider; struct device_node *np = dev->of_node; + struct regmap *regmap; + int i, ret; u32 res; - int ret; rptr = devm_kzalloc(dev, sizeof(*rptr), GFP_KERNEL); if (!rptr) @@ -189,15 +243,22 @@ static int eusb2_repeater_probe(struct platform_device *pdev) if (!rptr->cfg) return -EINVAL; - rptr->regmap = dev_get_regmap(dev->parent, NULL); - if (!rptr->regmap) + regmap = dev_get_regmap(dev->parent, NULL); + if (!regmap) return -ENODEV; ret = of_property_read_u32(np, "reg", &res); if (ret < 0) return ret; - rptr->base = res; + for (i = 0; i < F_NUM_FIELDS; i++) + eusb2_repeater_tune_reg_fields[i].reg += res; + + ret = devm_regmap_field_bulk_alloc(dev, regmap, rptr->regs, + eusb2_repeater_tune_reg_fields, + F_NUM_FIELDS); + if (ret) + return ret; ret = eusb2_repeater_init_vregs(rptr); if (ret < 0) { diff --git a/drivers/phy/realtek/Kconfig b/drivers/phy/realtek/Kconfig deleted file mode 100644 index 75ac7e7c31aec..0000000000000 --- a/drivers/phy/realtek/Kconfig +++ /dev/null @@ -1,32 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -# -# Phy drivers for Realtek platforms -# - -if ARCH_REALTEK || COMPILE_TEST - -config PHY_RTK_RTD_USB2PHY - tristate "Realtek RTD USB2 PHY Transceiver Driver" - depends on USB_SUPPORT - select GENERIC_PHY - select USB_PHY - select USB_COMMON - help - Enable this to support Realtek SoC USB2 phy transceiver. - The DHC (digital home center) RTD series SoCs used the Synopsys - DWC3 USB IP. This driver will do the PHY initialization - of the parameters. - -config PHY_RTK_RTD_USB3PHY - tristate "Realtek RTD USB3 PHY Transceiver Driver" - depends on USB_SUPPORT - select GENERIC_PHY - select USB_PHY - select USB_COMMON - help - Enable this to support Realtek SoC USB3 phy transceiver. - The DHC (digital home center) RTD series SoCs used the Synopsys - DWC3 USB IP. This driver will do the PHY initialization - of the parameters. - -endif # ARCH_REALTEK || COMPILE_TEST diff --git a/drivers/phy/realtek/Makefile b/drivers/phy/realtek/Makefile deleted file mode 100644 index ed7b47ff8a268..0000000000000 --- a/drivers/phy/realtek/Makefile +++ /dev/null @@ -1,3 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -obj-$(CONFIG_PHY_RTK_RTD_USB2PHY) += phy-rtk-usb2.o -obj-$(CONFIG_PHY_RTK_RTD_USB3PHY) += phy-rtk-usb3.o diff --git a/drivers/phy/realtek/phy-rtk-usb2.c b/drivers/phy/realtek/phy-rtk-usb2.c deleted file mode 100644 index aedc78bd37f73..0000000000000 --- a/drivers/phy/realtek/phy-rtk-usb2.c +++ /dev/null @@ -1,1325 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * phy-rtk-usb2.c RTK usb2.0 PHY driver - * - * Copyright (C) 2023 Realtek Semiconductor Corporation - * - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -/* GUSB2PHYACCn register */ -#define PHY_NEW_REG_REQ BIT(25) -#define PHY_VSTS_BUSY BIT(23) -#define PHY_VCTRL_SHIFT 8 -#define PHY_REG_DATA_MASK 0xff - -#define GET_LOW_NIBBLE(addr) ((addr) & 0x0f) -#define GET_HIGH_NIBBLE(addr) (((addr) & 0xf0) >> 4) - -#define EFUS_USB_DC_CAL_RATE 2 -#define EFUS_USB_DC_CAL_MAX 7 - -#define EFUS_USB_DC_DIS_RATE 1 -#define EFUS_USB_DC_DIS_MAX 7 - -#define MAX_PHY_DATA_SIZE 20 -#define OFFEST_PHY_READ 0x20 - -#define MAX_USB_PHY_NUM 4 -#define MAX_USB_PHY_PAGE0_DATA_SIZE 16 -#define MAX_USB_PHY_PAGE1_DATA_SIZE 16 -#define MAX_USB_PHY_PAGE2_DATA_SIZE 8 - -#define SET_PAGE_OFFSET 0xf4 -#define SET_PAGE_0 0x9b -#define SET_PAGE_1 0xbb -#define SET_PAGE_2 0xdb - -#define PAGE_START 0xe0 -#define PAGE0_0XE4 0xe4 -#define PAGE0_0XE6 0xe6 -#define PAGE0_0XE7 0xe7 -#define PAGE1_0XE0 0xe0 -#define PAGE1_0XE2 0xe2 - -#define SENSITIVITY_CTRL (BIT(4) | BIT(5) | BIT(6)) -#define ENABLE_AUTO_SENSITIVITY_CALIBRATION BIT(2) -#define DEFAULT_DC_DRIVING_VALUE (0x8) -#define DEFAULT_DC_DISCONNECTION_VALUE (0x6) -#define HS_CLK_SELECT BIT(6) - -struct phy_reg { - void __iomem *reg_wrap_vstatus; - void __iomem *reg_gusb2phyacc0; - int vstatus_index; -}; - -struct phy_data { - u8 addr; - u8 data; -}; - -struct phy_cfg { - int page0_size; - struct phy_data page0[MAX_USB_PHY_PAGE0_DATA_SIZE]; - int page1_size; - struct phy_data page1[MAX_USB_PHY_PAGE1_DATA_SIZE]; - int page2_size; - struct phy_data page2[MAX_USB_PHY_PAGE2_DATA_SIZE]; - - int num_phy; - - bool check_efuse; - int check_efuse_version; -#define CHECK_EFUSE_V1 1 -#define CHECK_EFUSE_V2 2 - int efuse_dc_driving_rate; - int efuse_dc_disconnect_rate; - int dc_driving_mask; - int dc_disconnect_mask; - bool usb_dc_disconnect_at_page0; - int driving_updated_for_dev_dis; - - bool do_toggle; - bool do_toggle_driving; - bool use_default_parameter; - bool is_double_sensitivity_mode; -}; - -struct phy_parameter { - struct phy_reg phy_reg; - - /* Get from efuse */ - s8 efuse_usb_dc_cal; - s8 efuse_usb_dc_dis; - - /* Get from dts */ - bool inverse_hstx_sync_clock; - u32 driving_level; - s32 driving_level_compensate; - s32 disconnection_compensate; -}; - -struct rtk_phy { - struct usb_phy phy; - struct device *dev; - - struct phy_cfg *phy_cfg; - int num_phy; - struct phy_parameter *phy_parameter; - - struct dentry *debug_dir; -}; - -/* mapping 0xE0 to 0 ... 0xE7 to 7, 0xF0 to 8 ,,, 0xF7 to 15 */ -static inline int page_addr_to_array_index(u8 addr) -{ - return (int)((((addr) - PAGE_START) & 0x7) + - ((((addr) - PAGE_START) & 0x10) >> 1)); -} - -static inline u8 array_index_to_page_addr(int index) -{ - return ((((index) + PAGE_START) & 0x7) + - ((((index) & 0x8) << 1) + PAGE_START)); -} - -#define PHY_IO_TIMEOUT_USEC (50000) -#define PHY_IO_DELAY_US (100) - -static inline int utmi_wait_register(void __iomem *reg, u32 mask, u32 result) -{ - int ret; - unsigned int val; - - ret = read_poll_timeout(readl, val, ((val & mask) == result), - PHY_IO_DELAY_US, PHY_IO_TIMEOUT_USEC, false, reg); - if (ret) { - pr_err("%s can't program USB phy\n", __func__); - return -ETIMEDOUT; - } - - return 0; -} - -static char rtk_phy_read(struct phy_reg *phy_reg, char addr) -{ - void __iomem *reg_gusb2phyacc0 = phy_reg->reg_gusb2phyacc0; - unsigned int val; - int ret = 0; - - addr -= OFFEST_PHY_READ; - - /* polling until VBusy == 0 */ - ret = utmi_wait_register(reg_gusb2phyacc0, PHY_VSTS_BUSY, 0); - if (ret) - return (char)ret; - - /* VCtrl = low nibble of addr, and set PHY_NEW_REG_REQ */ - val = PHY_NEW_REG_REQ | (GET_LOW_NIBBLE(addr) << PHY_VCTRL_SHIFT); - writel(val, reg_gusb2phyacc0); - ret = utmi_wait_register(reg_gusb2phyacc0, PHY_VSTS_BUSY, 0); - if (ret) - return (char)ret; - - /* VCtrl = high nibble of addr, and set PHY_NEW_REG_REQ */ - val = PHY_NEW_REG_REQ | (GET_HIGH_NIBBLE(addr) << PHY_VCTRL_SHIFT); - writel(val, reg_gusb2phyacc0); - ret = utmi_wait_register(reg_gusb2phyacc0, PHY_VSTS_BUSY, 0); - if (ret) - return (char)ret; - - val = readl(reg_gusb2phyacc0); - - return (char)(val & PHY_REG_DATA_MASK); -} - -static int rtk_phy_write(struct phy_reg *phy_reg, char addr, char data) -{ - unsigned int val; - void __iomem *reg_wrap_vstatus = phy_reg->reg_wrap_vstatus; - void __iomem *reg_gusb2phyacc0 = phy_reg->reg_gusb2phyacc0; - int shift_bits = phy_reg->vstatus_index * 8; - int ret = 0; - - /* write data to VStatusOut2 (data output to phy) */ - writel((u32)data << shift_bits, reg_wrap_vstatus); - - ret = utmi_wait_register(reg_gusb2phyacc0, PHY_VSTS_BUSY, 0); - if (ret) - return ret; - - /* VCtrl = low nibble of addr, set PHY_NEW_REG_REQ */ - val = PHY_NEW_REG_REQ | (GET_LOW_NIBBLE(addr) << PHY_VCTRL_SHIFT); - - writel(val, reg_gusb2phyacc0); - ret = utmi_wait_register(reg_gusb2phyacc0, PHY_VSTS_BUSY, 0); - if (ret) - return ret; - - /* VCtrl = high nibble of addr, set PHY_NEW_REG_REQ */ - val = PHY_NEW_REG_REQ | (GET_HIGH_NIBBLE(addr) << PHY_VCTRL_SHIFT); - - writel(val, reg_gusb2phyacc0); - ret = utmi_wait_register(reg_gusb2phyacc0, PHY_VSTS_BUSY, 0); - if (ret) - return ret; - - return 0; -} - -static int rtk_phy_set_page(struct phy_reg *phy_reg, int page) -{ - switch (page) { - case 0: - return rtk_phy_write(phy_reg, SET_PAGE_OFFSET, SET_PAGE_0); - case 1: - return rtk_phy_write(phy_reg, SET_PAGE_OFFSET, SET_PAGE_1); - case 2: - return rtk_phy_write(phy_reg, SET_PAGE_OFFSET, SET_PAGE_2); - default: - pr_err("%s error page=%d\n", __func__, page); - } - - return -EINVAL; -} - -static u8 __updated_dc_disconnect_level_page0_0xe4(struct phy_cfg *phy_cfg, - struct phy_parameter *phy_parameter, u8 data) -{ - u8 ret; - s32 val; - s32 dc_disconnect_mask = phy_cfg->dc_disconnect_mask; - int offset = 4; - - val = (s32)((data >> offset) & dc_disconnect_mask) - + phy_parameter->efuse_usb_dc_dis - + phy_parameter->disconnection_compensate; - - if (val > dc_disconnect_mask) - val = dc_disconnect_mask; - else if (val < 0) - val = 0; - - ret = (data & (~(dc_disconnect_mask << offset))) | - (val & dc_disconnect_mask) << offset; - - return ret; -} - -/* updated disconnect level at page0 */ -static void update_dc_disconnect_level_at_page0(struct rtk_phy *rtk_phy, - struct phy_parameter *phy_parameter, bool update) -{ - struct phy_cfg *phy_cfg; - struct phy_reg *phy_reg; - struct phy_data *phy_data_page; - struct phy_data *phy_data; - u8 addr, data; - int offset = 4; - s32 dc_disconnect_mask; - int i; - - phy_cfg = rtk_phy->phy_cfg; - phy_reg = &phy_parameter->phy_reg; - - /* Set page 0 */ - phy_data_page = phy_cfg->page0; - rtk_phy_set_page(phy_reg, 0); - - i = page_addr_to_array_index(PAGE0_0XE4); - phy_data = phy_data_page + i; - if (!phy_data->addr) { - phy_data->addr = PAGE0_0XE4; - phy_data->data = rtk_phy_read(phy_reg, PAGE0_0XE4); - } - - addr = phy_data->addr; - data = phy_data->data; - dc_disconnect_mask = phy_cfg->dc_disconnect_mask; - - if (update) - data = __updated_dc_disconnect_level_page0_0xe4(phy_cfg, phy_parameter, data); - else - data = (data & ~(dc_disconnect_mask << offset)) | - (DEFAULT_DC_DISCONNECTION_VALUE << offset); - - if (rtk_phy_write(phy_reg, addr, data)) - dev_err(rtk_phy->dev, - "%s: Error to set page1 parameter addr=0x%x value=0x%x\n", - __func__, addr, data); -} - -static u8 __updated_dc_disconnect_level_page1_0xe2(struct phy_cfg *phy_cfg, - struct phy_parameter *phy_parameter, u8 data) -{ - u8 ret; - s32 val; - s32 dc_disconnect_mask = phy_cfg->dc_disconnect_mask; - - if (phy_cfg->check_efuse_version == CHECK_EFUSE_V1) { - val = (s32)(data & dc_disconnect_mask) - + phy_parameter->efuse_usb_dc_dis - + phy_parameter->disconnection_compensate; - } else { /* for CHECK_EFUSE_V2 or no efuse */ - if (phy_parameter->efuse_usb_dc_dis) - val = (s32)(phy_parameter->efuse_usb_dc_dis + - phy_parameter->disconnection_compensate); - else - val = (s32)((data & dc_disconnect_mask) + - phy_parameter->disconnection_compensate); - } - - if (val > dc_disconnect_mask) - val = dc_disconnect_mask; - else if (val < 0) - val = 0; - - ret = (data & (~dc_disconnect_mask)) | (val & dc_disconnect_mask); - - return ret; -} - -/* updated disconnect level at page1 */ -static void update_dc_disconnect_level_at_page1(struct rtk_phy *rtk_phy, - struct phy_parameter *phy_parameter, bool update) -{ - struct phy_cfg *phy_cfg; - struct phy_data *phy_data_page; - struct phy_data *phy_data; - struct phy_reg *phy_reg; - u8 addr, data; - s32 dc_disconnect_mask; - int i; - - phy_cfg = rtk_phy->phy_cfg; - phy_reg = &phy_parameter->phy_reg; - - /* Set page 1 */ - phy_data_page = phy_cfg->page1; - rtk_phy_set_page(phy_reg, 1); - - i = page_addr_to_array_index(PAGE1_0XE2); - phy_data = phy_data_page + i; - if (!phy_data->addr) { - phy_data->addr = PAGE1_0XE2; - phy_data->data = rtk_phy_read(phy_reg, PAGE1_0XE2); - } - - addr = phy_data->addr; - data = phy_data->data; - dc_disconnect_mask = phy_cfg->dc_disconnect_mask; - - if (update) - data = __updated_dc_disconnect_level_page1_0xe2(phy_cfg, phy_parameter, data); - else - data = (data & ~dc_disconnect_mask) | DEFAULT_DC_DISCONNECTION_VALUE; - - if (rtk_phy_write(phy_reg, addr, data)) - dev_err(rtk_phy->dev, - "%s: Error to set page1 parameter addr=0x%x value=0x%x\n", - __func__, addr, data); -} - -static void update_dc_disconnect_level(struct rtk_phy *rtk_phy, - struct phy_parameter *phy_parameter, bool update) -{ - struct phy_cfg *phy_cfg = rtk_phy->phy_cfg; - - if (phy_cfg->usb_dc_disconnect_at_page0) - update_dc_disconnect_level_at_page0(rtk_phy, phy_parameter, update); - else - update_dc_disconnect_level_at_page1(rtk_phy, phy_parameter, update); -} - -static u8 __update_dc_driving_page0_0xe4(struct phy_cfg *phy_cfg, - struct phy_parameter *phy_parameter, u8 data) -{ - s32 driving_level_compensate = phy_parameter->driving_level_compensate; - s32 dc_driving_mask = phy_cfg->dc_driving_mask; - s32 val; - u8 ret; - - if (phy_cfg->check_efuse_version == CHECK_EFUSE_V1) { - val = (s32)(data & dc_driving_mask) + driving_level_compensate - + phy_parameter->efuse_usb_dc_cal; - } else { /* for CHECK_EFUSE_V2 or no efuse */ - if (phy_parameter->efuse_usb_dc_cal) - val = (s32)((phy_parameter->efuse_usb_dc_cal & dc_driving_mask) - + driving_level_compensate); - else - val = (s32)(data & dc_driving_mask); - } - - if (val > dc_driving_mask) - val = dc_driving_mask; - else if (val < 0) - val = 0; - - ret = (data & (~dc_driving_mask)) | (val & dc_driving_mask); - - return ret; -} - -static void update_dc_driving_level(struct rtk_phy *rtk_phy, - struct phy_parameter *phy_parameter) -{ - struct phy_cfg *phy_cfg; - struct phy_reg *phy_reg; - - phy_reg = &phy_parameter->phy_reg; - phy_cfg = rtk_phy->phy_cfg; - if (!phy_cfg->page0[4].addr) { - rtk_phy_set_page(phy_reg, 0); - phy_cfg->page0[4].addr = PAGE0_0XE4; - phy_cfg->page0[4].data = rtk_phy_read(phy_reg, PAGE0_0XE4); - } - - if (phy_parameter->driving_level != DEFAULT_DC_DRIVING_VALUE) { - u32 dc_driving_mask; - u8 driving_level; - u8 data; - - data = phy_cfg->page0[4].data; - dc_driving_mask = phy_cfg->dc_driving_mask; - driving_level = data & dc_driving_mask; - - dev_dbg(rtk_phy->dev, "%s driving_level=%d => dts driving_level=%d\n", - __func__, driving_level, phy_parameter->driving_level); - - phy_cfg->page0[4].data = (data & (~dc_driving_mask)) | - (phy_parameter->driving_level & dc_driving_mask); - } - - phy_cfg->page0[4].data = __update_dc_driving_page0_0xe4(phy_cfg, - phy_parameter, - phy_cfg->page0[4].data); -} - -static void update_hs_clk_select(struct rtk_phy *rtk_phy, - struct phy_parameter *phy_parameter) -{ - struct phy_cfg *phy_cfg; - struct phy_reg *phy_reg; - - phy_cfg = rtk_phy->phy_cfg; - phy_reg = &phy_parameter->phy_reg; - - if (phy_parameter->inverse_hstx_sync_clock) { - if (!phy_cfg->page0[6].addr) { - rtk_phy_set_page(phy_reg, 0); - phy_cfg->page0[6].addr = PAGE0_0XE6; - phy_cfg->page0[6].data = rtk_phy_read(phy_reg, PAGE0_0XE6); - } - - phy_cfg->page0[6].data = phy_cfg->page0[6].data | HS_CLK_SELECT; - } -} - -static void do_rtk_phy_toggle(struct rtk_phy *rtk_phy, - int index, bool connect) -{ - struct phy_parameter *phy_parameter; - struct phy_cfg *phy_cfg; - struct phy_reg *phy_reg; - struct phy_data *phy_data_page; - u8 addr, data; - int i; - - phy_cfg = rtk_phy->phy_cfg; - phy_parameter = &((struct phy_parameter *)rtk_phy->phy_parameter)[index]; - phy_reg = &phy_parameter->phy_reg; - - if (!phy_cfg->do_toggle) - goto out; - - if (phy_cfg->is_double_sensitivity_mode) - goto do_toggle_driving; - - /* Set page 0 */ - rtk_phy_set_page(phy_reg, 0); - - addr = PAGE0_0XE7; - data = rtk_phy_read(phy_reg, addr); - - if (connect) - rtk_phy_write(phy_reg, addr, data & (~SENSITIVITY_CTRL)); - else - rtk_phy_write(phy_reg, addr, data | (SENSITIVITY_CTRL)); - -do_toggle_driving: - - if (!phy_cfg->do_toggle_driving) - goto do_toggle; - - /* Page 0 addr 0xE4 driving capability */ - - /* Set page 0 */ - phy_data_page = phy_cfg->page0; - rtk_phy_set_page(phy_reg, 0); - - i = page_addr_to_array_index(PAGE0_0XE4); - addr = phy_data_page[i].addr; - data = phy_data_page[i].data; - - if (connect) { - rtk_phy_write(phy_reg, addr, data); - } else { - u8 value; - s32 tmp; - s32 driving_updated = - phy_cfg->driving_updated_for_dev_dis; - s32 dc_driving_mask = phy_cfg->dc_driving_mask; - - tmp = (s32)(data & dc_driving_mask) + driving_updated; - - if (tmp > dc_driving_mask) - tmp = dc_driving_mask; - else if (tmp < 0) - tmp = 0; - - value = (data & (~dc_driving_mask)) | (tmp & dc_driving_mask); - - rtk_phy_write(phy_reg, addr, value); - } - -do_toggle: - /* restore dc disconnect level before toggle */ - update_dc_disconnect_level(rtk_phy, phy_parameter, false); - - /* Set page 1 */ - rtk_phy_set_page(phy_reg, 1); - - addr = PAGE1_0XE0; - data = rtk_phy_read(phy_reg, addr); - - rtk_phy_write(phy_reg, addr, data & - (~ENABLE_AUTO_SENSITIVITY_CALIBRATION)); - mdelay(1); - rtk_phy_write(phy_reg, addr, data | - (ENABLE_AUTO_SENSITIVITY_CALIBRATION)); - - /* update dc disconnect level after toggle */ - update_dc_disconnect_level(rtk_phy, phy_parameter, true); - -out: - return; -} - -static int do_rtk_phy_init(struct rtk_phy *rtk_phy, int index) -{ - struct phy_parameter *phy_parameter; - struct phy_cfg *phy_cfg; - struct phy_data *phy_data_page; - struct phy_reg *phy_reg; - int i; - - phy_cfg = rtk_phy->phy_cfg; - phy_parameter = &((struct phy_parameter *)rtk_phy->phy_parameter)[index]; - phy_reg = &phy_parameter->phy_reg; - - if (phy_cfg->use_default_parameter) { - dev_dbg(rtk_phy->dev, "%s phy#%d use default parameter\n", - __func__, index); - goto do_toggle; - } - - /* Set page 0 */ - phy_data_page = phy_cfg->page0; - rtk_phy_set_page(phy_reg, 0); - - for (i = 0; i < phy_cfg->page0_size; i++) { - struct phy_data *phy_data = phy_data_page + i; - u8 addr = phy_data->addr; - u8 data = phy_data->data; - - if (!addr) - continue; - - if (rtk_phy_write(phy_reg, addr, data)) { - dev_err(rtk_phy->dev, - "%s: Error to set page0 parameter addr=0x%x value=0x%x\n", - __func__, addr, data); - return -EINVAL; - } - } - - /* Set page 1 */ - phy_data_page = phy_cfg->page1; - rtk_phy_set_page(phy_reg, 1); - - for (i = 0; i < phy_cfg->page1_size; i++) { - struct phy_data *phy_data = phy_data_page + i; - u8 addr = phy_data->addr; - u8 data = phy_data->data; - - if (!addr) - continue; - - if (rtk_phy_write(phy_reg, addr, data)) { - dev_err(rtk_phy->dev, - "%s: Error to set page1 parameter addr=0x%x value=0x%x\n", - __func__, addr, data); - return -EINVAL; - } - } - - if (phy_cfg->page2_size == 0) - goto do_toggle; - - /* Set page 2 */ - phy_data_page = phy_cfg->page2; - rtk_phy_set_page(phy_reg, 2); - - for (i = 0; i < phy_cfg->page2_size; i++) { - struct phy_data *phy_data = phy_data_page + i; - u8 addr = phy_data->addr; - u8 data = phy_data->data; - - if (!addr) - continue; - - if (rtk_phy_write(phy_reg, addr, data)) { - dev_err(rtk_phy->dev, - "%s: Error to set page2 parameter addr=0x%x value=0x%x\n", - __func__, addr, data); - return -EINVAL; - } - } - -do_toggle: - do_rtk_phy_toggle(rtk_phy, index, false); - - return 0; -} - -static int rtk_phy_init(struct phy *phy) -{ - struct rtk_phy *rtk_phy = phy_get_drvdata(phy); - unsigned long phy_init_time = jiffies; - int i, ret = 0; - - if (!rtk_phy) - return -EINVAL; - - for (i = 0; i < rtk_phy->num_phy; i++) - ret = do_rtk_phy_init(rtk_phy, i); - - dev_dbg(rtk_phy->dev, "Initialized RTK USB 2.0 PHY (take %dms)\n", - jiffies_to_msecs(jiffies - phy_init_time)); - return ret; -} - -static int rtk_phy_exit(struct phy *phy) -{ - return 0; -} - -static const struct phy_ops ops = { - .init = rtk_phy_init, - .exit = rtk_phy_exit, - .owner = THIS_MODULE, -}; - -static void rtk_phy_toggle(struct usb_phy *usb2_phy, bool connect, int port) -{ - int index = port; - struct rtk_phy *rtk_phy = NULL; - - rtk_phy = dev_get_drvdata(usb2_phy->dev); - - if (index > rtk_phy->num_phy) { - dev_err(rtk_phy->dev, "%s: The port=%d is not in usb phy (num_phy=%d)\n", - __func__, index, rtk_phy->num_phy); - return; - } - - do_rtk_phy_toggle(rtk_phy, index, connect); -} - -static int rtk_phy_notify_port_status(struct usb_phy *x, int port, - u16 portstatus, u16 portchange) -{ - bool connect = false; - - pr_debug("%s port=%d portstatus=0x%x portchange=0x%x\n", - __func__, port, (int)portstatus, (int)portchange); - if (portstatus & USB_PORT_STAT_CONNECTION) - connect = true; - - if (portchange & USB_PORT_STAT_C_CONNECTION) - rtk_phy_toggle(x, connect, port); - - return 0; -} - -#ifdef CONFIG_DEBUG_FS -static struct dentry *create_phy_debug_root(void) -{ - struct dentry *phy_debug_root; - - phy_debug_root = debugfs_lookup("phy", usb_debug_root); - if (!phy_debug_root) - phy_debug_root = debugfs_create_dir("phy", usb_debug_root); - - return phy_debug_root; -} - -static int rtk_usb2_parameter_show(struct seq_file *s, void *unused) -{ - struct rtk_phy *rtk_phy = s->private; - struct phy_cfg *phy_cfg; - int i, index; - - phy_cfg = rtk_phy->phy_cfg; - - seq_puts(s, "Property:\n"); - seq_printf(s, " check_efuse: %s\n", - phy_cfg->check_efuse ? "Enable" : "Disable"); - seq_printf(s, " check_efuse_version: %d\n", - phy_cfg->check_efuse_version); - seq_printf(s, " efuse_dc_driving_rate: %d\n", - phy_cfg->efuse_dc_driving_rate); - seq_printf(s, " dc_driving_mask: 0x%x\n", - phy_cfg->dc_driving_mask); - seq_printf(s, " efuse_dc_disconnect_rate: %d\n", - phy_cfg->efuse_dc_disconnect_rate); - seq_printf(s, " dc_disconnect_mask: 0x%x\n", - phy_cfg->dc_disconnect_mask); - seq_printf(s, " usb_dc_disconnect_at_page0: %s\n", - phy_cfg->usb_dc_disconnect_at_page0 ? "true" : "false"); - seq_printf(s, " do_toggle: %s\n", - phy_cfg->do_toggle ? "Enable" : "Disable"); - seq_printf(s, " do_toggle_driving: %s\n", - phy_cfg->do_toggle_driving ? "Enable" : "Disable"); - seq_printf(s, " driving_updated_for_dev_dis: 0x%x\n", - phy_cfg->driving_updated_for_dev_dis); - seq_printf(s, " use_default_parameter: %s\n", - phy_cfg->use_default_parameter ? "Enable" : "Disable"); - seq_printf(s, " is_double_sensitivity_mode: %s\n", - phy_cfg->is_double_sensitivity_mode ? "Enable" : "Disable"); - - for (index = 0; index < rtk_phy->num_phy; index++) { - struct phy_parameter *phy_parameter; - struct phy_reg *phy_reg; - struct phy_data *phy_data_page; - - phy_parameter = &((struct phy_parameter *)rtk_phy->phy_parameter)[index]; - phy_reg = &phy_parameter->phy_reg; - - seq_printf(s, "PHY %d:\n", index); - - seq_puts(s, "Page 0:\n"); - /* Set page 0 */ - phy_data_page = phy_cfg->page0; - rtk_phy_set_page(phy_reg, 0); - - for (i = 0; i < phy_cfg->page0_size; i++) { - struct phy_data *phy_data = phy_data_page + i; - u8 addr = array_index_to_page_addr(i); - u8 data = phy_data->data; - u8 value = rtk_phy_read(phy_reg, addr); - - if (phy_data->addr) - seq_printf(s, " Page 0: addr=0x%x data=0x%02x ==> read value=0x%02x\n", - addr, data, value); - else - seq_printf(s, " Page 0: addr=0x%x data=none ==> read value=0x%02x\n", - addr, value); - } - - seq_puts(s, "Page 1:\n"); - /* Set page 1 */ - phy_data_page = phy_cfg->page1; - rtk_phy_set_page(phy_reg, 1); - - for (i = 0; i < phy_cfg->page1_size; i++) { - struct phy_data *phy_data = phy_data_page + i; - u8 addr = array_index_to_page_addr(i); - u8 data = phy_data->data; - u8 value = rtk_phy_read(phy_reg, addr); - - if (phy_data->addr) - seq_printf(s, " Page 1: addr=0x%x data=0x%02x ==> read value=0x%02x\n", - addr, data, value); - else - seq_printf(s, " Page 1: addr=0x%x data=none ==> read value=0x%02x\n", - addr, value); - } - - if (phy_cfg->page2_size == 0) - goto out; - - seq_puts(s, "Page 2:\n"); - /* Set page 2 */ - phy_data_page = phy_cfg->page2; - rtk_phy_set_page(phy_reg, 2); - - for (i = 0; i < phy_cfg->page2_size; i++) { - struct phy_data *phy_data = phy_data_page + i; - u8 addr = array_index_to_page_addr(i); - u8 data = phy_data->data; - u8 value = rtk_phy_read(phy_reg, addr); - - if (phy_data->addr) - seq_printf(s, " Page 2: addr=0x%x data=0x%02x ==> read value=0x%02x\n", - addr, data, value); - else - seq_printf(s, " Page 2: addr=0x%x data=none ==> read value=0x%02x\n", - addr, value); - } - -out: - seq_puts(s, "PHY Property:\n"); - seq_printf(s, " efuse_usb_dc_cal: %d\n", - (int)phy_parameter->efuse_usb_dc_cal); - seq_printf(s, " efuse_usb_dc_dis: %d\n", - (int)phy_parameter->efuse_usb_dc_dis); - seq_printf(s, " inverse_hstx_sync_clock: %s\n", - phy_parameter->inverse_hstx_sync_clock ? "Enable" : "Disable"); - seq_printf(s, " driving_level: %d\n", - phy_parameter->driving_level); - seq_printf(s, " driving_level_compensate: %d\n", - phy_parameter->driving_level_compensate); - seq_printf(s, " disconnection_compensate: %d\n", - phy_parameter->disconnection_compensate); - } - - return 0; -} -DEFINE_SHOW_ATTRIBUTE(rtk_usb2_parameter); - -static inline void create_debug_files(struct rtk_phy *rtk_phy) -{ - struct dentry *phy_debug_root = NULL; - - phy_debug_root = create_phy_debug_root(); - if (!phy_debug_root) - return; - - rtk_phy->debug_dir = debugfs_create_dir(dev_name(rtk_phy->dev), - phy_debug_root); - - debugfs_create_file("parameter", 0444, rtk_phy->debug_dir, rtk_phy, - &rtk_usb2_parameter_fops); - - return; -} - -static inline void remove_debug_files(struct rtk_phy *rtk_phy) -{ - debugfs_remove_recursive(rtk_phy->debug_dir); -} -#else -static inline void create_debug_files(struct rtk_phy *rtk_phy) { } -static inline void remove_debug_files(struct rtk_phy *rtk_phy) { } -#endif /* CONFIG_DEBUG_FS */ - -static int get_phy_data_by_efuse(struct rtk_phy *rtk_phy, - struct phy_parameter *phy_parameter, int index) -{ - struct phy_cfg *phy_cfg = rtk_phy->phy_cfg; - u8 value = 0; - struct nvmem_cell *cell; - struct soc_device_attribute rtk_soc_groot[] = { - { .family = "Realtek Groot",}, - { /* empty */ } }; - - if (!phy_cfg->check_efuse) - goto out; - - /* Read efuse for usb dc cal */ - cell = nvmem_cell_get(rtk_phy->dev, "usb-dc-cal"); - if (IS_ERR(cell)) { - dev_dbg(rtk_phy->dev, "%s no usb-dc-cal: %ld\n", - __func__, PTR_ERR(cell)); - } else { - unsigned char *buf; - size_t buf_size; - - buf = nvmem_cell_read(cell, &buf_size); - if (!IS_ERR(buf)) { - value = buf[0] & phy_cfg->dc_driving_mask; - kfree(buf); - } - nvmem_cell_put(cell); - } - - if (phy_cfg->check_efuse_version == CHECK_EFUSE_V1) { - int rate = phy_cfg->efuse_dc_driving_rate; - - if (value <= EFUS_USB_DC_CAL_MAX) - phy_parameter->efuse_usb_dc_cal = (int8_t)(value * rate); - else - phy_parameter->efuse_usb_dc_cal = -(int8_t) - ((EFUS_USB_DC_CAL_MAX & value) * rate); - - if (soc_device_match(rtk_soc_groot)) { - dev_dbg(rtk_phy->dev, "For groot IC we need a workaround to adjust efuse_usb_dc_cal\n"); - - /* We don't multiple dc_cal_rate=2 for positive dc cal compensate */ - if (value <= EFUS_USB_DC_CAL_MAX) - phy_parameter->efuse_usb_dc_cal = (int8_t)(value); - - /* We set max dc cal compensate is 0x8 if otp is 0x7 */ - if (value == 0x7) - phy_parameter->efuse_usb_dc_cal = (int8_t)(value + 1); - } - } else { /* for CHECK_EFUSE_V2 */ - phy_parameter->efuse_usb_dc_cal = value & phy_cfg->dc_driving_mask; - } - - /* Read efuse for usb dc disconnect level */ - value = 0; - cell = nvmem_cell_get(rtk_phy->dev, "usb-dc-dis"); - if (IS_ERR(cell)) { - dev_dbg(rtk_phy->dev, "%s no usb-dc-dis: %ld\n", - __func__, PTR_ERR(cell)); - } else { - unsigned char *buf; - size_t buf_size; - - buf = nvmem_cell_read(cell, &buf_size); - if (!IS_ERR(buf)) { - value = buf[0] & phy_cfg->dc_disconnect_mask; - kfree(buf); - } - nvmem_cell_put(cell); - } - - if (phy_cfg->check_efuse_version == CHECK_EFUSE_V1) { - int rate = phy_cfg->efuse_dc_disconnect_rate; - - if (value <= EFUS_USB_DC_DIS_MAX) - phy_parameter->efuse_usb_dc_dis = (int8_t)(value * rate); - else - phy_parameter->efuse_usb_dc_dis = -(int8_t) - ((EFUS_USB_DC_DIS_MAX & value) * rate); - } else { /* for CHECK_EFUSE_V2 */ - phy_parameter->efuse_usb_dc_dis = value & phy_cfg->dc_disconnect_mask; - } - -out: - return 0; -} - -static int parse_phy_data(struct rtk_phy *rtk_phy) -{ - struct device *dev = rtk_phy->dev; - struct device_node *np = dev->of_node; - struct phy_parameter *phy_parameter; - int ret = 0; - int index; - - rtk_phy->phy_parameter = devm_kzalloc(dev, sizeof(struct phy_parameter) * - rtk_phy->num_phy, GFP_KERNEL); - if (!rtk_phy->phy_parameter) - return -ENOMEM; - - for (index = 0; index < rtk_phy->num_phy; index++) { - phy_parameter = &((struct phy_parameter *)rtk_phy->phy_parameter)[index]; - - phy_parameter->phy_reg.reg_wrap_vstatus = of_iomap(np, 0); - phy_parameter->phy_reg.reg_gusb2phyacc0 = of_iomap(np, 1) + index; - phy_parameter->phy_reg.vstatus_index = index; - - if (of_property_read_bool(np, "realtek,inverse-hstx-sync-clock")) - phy_parameter->inverse_hstx_sync_clock = true; - else - phy_parameter->inverse_hstx_sync_clock = false; - - if (of_property_read_u32_index(np, "realtek,driving-level", - index, &phy_parameter->driving_level)) - phy_parameter->driving_level = DEFAULT_DC_DRIVING_VALUE; - - if (of_property_read_u32_index(np, "realtek,driving-level-compensate", - index, &phy_parameter->driving_level_compensate)) - phy_parameter->driving_level_compensate = 0; - - if (of_property_read_u32_index(np, "realtek,disconnection-compensate", - index, &phy_parameter->disconnection_compensate)) - phy_parameter->disconnection_compensate = 0; - - get_phy_data_by_efuse(rtk_phy, phy_parameter, index); - - update_dc_driving_level(rtk_phy, phy_parameter); - - update_hs_clk_select(rtk_phy, phy_parameter); - } - - return ret; -} - -static int rtk_usb2phy_probe(struct platform_device *pdev) -{ - struct rtk_phy *rtk_phy; - struct device *dev = &pdev->dev; - struct phy *generic_phy; - struct phy_provider *phy_provider; - const struct phy_cfg *phy_cfg; - int ret = 0; - - phy_cfg = of_device_get_match_data(dev); - if (!phy_cfg) { - dev_err(dev, "phy config are not assigned!\n"); - return -EINVAL; - } - - rtk_phy = devm_kzalloc(dev, sizeof(*rtk_phy), GFP_KERNEL); - if (!rtk_phy) - return -ENOMEM; - - rtk_phy->dev = &pdev->dev; - rtk_phy->phy.dev = rtk_phy->dev; - rtk_phy->phy.label = "rtk-usb2phy"; - rtk_phy->phy.notify_port_status = rtk_phy_notify_port_status; - - rtk_phy->phy_cfg = devm_kzalloc(dev, sizeof(*phy_cfg), GFP_KERNEL); - - memcpy(rtk_phy->phy_cfg, phy_cfg, sizeof(*phy_cfg)); - - rtk_phy->num_phy = phy_cfg->num_phy; - - ret = parse_phy_data(rtk_phy); - if (ret) - goto err; - - platform_set_drvdata(pdev, rtk_phy); - - generic_phy = devm_phy_create(rtk_phy->dev, NULL, &ops); - if (IS_ERR(generic_phy)) - return PTR_ERR(generic_phy); - - phy_set_drvdata(generic_phy, rtk_phy); - - phy_provider = devm_of_phy_provider_register(rtk_phy->dev, - of_phy_simple_xlate); - if (IS_ERR(phy_provider)) - return PTR_ERR(phy_provider); - - ret = usb_add_phy_dev(&rtk_phy->phy); - if (ret) - goto err; - - create_debug_files(rtk_phy); - -err: - return ret; -} - -static void rtk_usb2phy_remove(struct platform_device *pdev) -{ - struct rtk_phy *rtk_phy = platform_get_drvdata(pdev); - - remove_debug_files(rtk_phy); - - usb_remove_phy(&rtk_phy->phy); -} - -static const struct phy_cfg rtd1295_phy_cfg = { - .page0_size = MAX_USB_PHY_PAGE0_DATA_SIZE, - .page0 = { [0] = {0xe0, 0x90}, - [3] = {0xe3, 0x3a}, - [4] = {0xe4, 0x68}, - [6] = {0xe6, 0x91}, - [13] = {0xf5, 0x81}, - [15] = {0xf7, 0x02}, }, - .page1_size = 8, - .page1 = { /* default parameter */ }, - .page2_size = 0, - .page2 = { /* no parameter */ }, - .num_phy = 1, - .check_efuse = false, - .check_efuse_version = CHECK_EFUSE_V1, - .efuse_dc_driving_rate = 1, - .dc_driving_mask = 0xf, - .efuse_dc_disconnect_rate = EFUS_USB_DC_DIS_RATE, - .dc_disconnect_mask = 0xf, - .usb_dc_disconnect_at_page0 = true, - .do_toggle = true, - .do_toggle_driving = false, - .driving_updated_for_dev_dis = 0xf, - .use_default_parameter = false, - .is_double_sensitivity_mode = false, -}; - -static const struct phy_cfg rtd1395_phy_cfg = { - .page0_size = MAX_USB_PHY_PAGE0_DATA_SIZE, - .page0 = { [4] = {0xe4, 0xac}, - [13] = {0xf5, 0x00}, - [15] = {0xf7, 0x02}, }, - .page1_size = 8, - .page1 = { /* default parameter */ }, - .page2_size = 0, - .page2 = { /* no parameter */ }, - .num_phy = 1, - .check_efuse = false, - .check_efuse_version = CHECK_EFUSE_V1, - .efuse_dc_driving_rate = 1, - .dc_driving_mask = 0xf, - .efuse_dc_disconnect_rate = EFUS_USB_DC_DIS_RATE, - .dc_disconnect_mask = 0xf, - .usb_dc_disconnect_at_page0 = true, - .do_toggle = true, - .do_toggle_driving = false, - .driving_updated_for_dev_dis = 0xf, - .use_default_parameter = false, - .is_double_sensitivity_mode = false, -}; - -static const struct phy_cfg rtd1395_phy_cfg_2port = { - .page0_size = MAX_USB_PHY_PAGE0_DATA_SIZE, - .page0 = { [4] = {0xe4, 0xac}, - [13] = {0xf5, 0x00}, - [15] = {0xf7, 0x02}, }, - .page1_size = 8, - .page1 = { /* default parameter */ }, - .page2_size = 0, - .page2 = { /* no parameter */ }, - .num_phy = 2, - .check_efuse = false, - .check_efuse_version = CHECK_EFUSE_V1, - .efuse_dc_driving_rate = 1, - .dc_driving_mask = 0xf, - .efuse_dc_disconnect_rate = EFUS_USB_DC_DIS_RATE, - .dc_disconnect_mask = 0xf, - .usb_dc_disconnect_at_page0 = true, - .do_toggle = true, - .do_toggle_driving = false, - .driving_updated_for_dev_dis = 0xf, - .use_default_parameter = false, - .is_double_sensitivity_mode = false, -}; - -static const struct phy_cfg rtd1619_phy_cfg = { - .page0_size = MAX_USB_PHY_PAGE0_DATA_SIZE, - .page0 = { [4] = {0xe4, 0x68}, }, - .page1_size = 8, - .page1 = { /* default parameter */ }, - .page2_size = 0, - .page2 = { /* no parameter */ }, - .num_phy = 1, - .check_efuse = true, - .check_efuse_version = CHECK_EFUSE_V1, - .efuse_dc_driving_rate = 1, - .dc_driving_mask = 0xf, - .efuse_dc_disconnect_rate = EFUS_USB_DC_DIS_RATE, - .dc_disconnect_mask = 0xf, - .usb_dc_disconnect_at_page0 = true, - .do_toggle = true, - .do_toggle_driving = false, - .driving_updated_for_dev_dis = 0xf, - .use_default_parameter = false, - .is_double_sensitivity_mode = false, -}; - -static const struct phy_cfg rtd1319_phy_cfg = { - .page0_size = MAX_USB_PHY_PAGE0_DATA_SIZE, - .page0 = { [0] = {0xe0, 0x18}, - [4] = {0xe4, 0x6a}, - [7] = {0xe7, 0x71}, - [13] = {0xf5, 0x15}, - [15] = {0xf7, 0x32}, }, - .page1_size = 8, - .page1 = { [3] = {0xe3, 0x44}, }, - .page2_size = MAX_USB_PHY_PAGE2_DATA_SIZE, - .page2 = { [0] = {0xe0, 0x01}, }, - .num_phy = 1, - .check_efuse = true, - .check_efuse_version = CHECK_EFUSE_V1, - .efuse_dc_driving_rate = 1, - .dc_driving_mask = 0xf, - .efuse_dc_disconnect_rate = EFUS_USB_DC_DIS_RATE, - .dc_disconnect_mask = 0xf, - .usb_dc_disconnect_at_page0 = true, - .do_toggle = true, - .do_toggle_driving = true, - .driving_updated_for_dev_dis = 0xf, - .use_default_parameter = false, - .is_double_sensitivity_mode = true, -}; - -static const struct phy_cfg rtd1312c_phy_cfg = { - .page0_size = MAX_USB_PHY_PAGE0_DATA_SIZE, - .page0 = { [0] = {0xe0, 0x14}, - [4] = {0xe4, 0x67}, - [5] = {0xe5, 0x55}, }, - .page1_size = 8, - .page1 = { [3] = {0xe3, 0x23}, - [6] = {0xe6, 0x58}, }, - .page2_size = MAX_USB_PHY_PAGE2_DATA_SIZE, - .page2 = { /* default parameter */ }, - .num_phy = 1, - .check_efuse = true, - .check_efuse_version = CHECK_EFUSE_V1, - .efuse_dc_driving_rate = 1, - .dc_driving_mask = 0xf, - .efuse_dc_disconnect_rate = EFUS_USB_DC_DIS_RATE, - .dc_disconnect_mask = 0xf, - .usb_dc_disconnect_at_page0 = true, - .do_toggle = true, - .do_toggle_driving = true, - .driving_updated_for_dev_dis = 0xf, - .use_default_parameter = false, - .is_double_sensitivity_mode = true, -}; - -static const struct phy_cfg rtd1619b_phy_cfg = { - .page0_size = MAX_USB_PHY_PAGE0_DATA_SIZE, - .page0 = { [0] = {0xe0, 0xa3}, - [4] = {0xe4, 0x88}, - [5] = {0xe5, 0x4f}, - [6] = {0xe6, 0x02}, }, - .page1_size = 8, - .page1 = { [3] = {0xe3, 0x64}, }, - .page2_size = MAX_USB_PHY_PAGE2_DATA_SIZE, - .page2 = { [7] = {0xe7, 0x45}, }, - .num_phy = 1, - .check_efuse = true, - .check_efuse_version = CHECK_EFUSE_V1, - .efuse_dc_driving_rate = EFUS_USB_DC_CAL_RATE, - .dc_driving_mask = 0x1f, - .efuse_dc_disconnect_rate = EFUS_USB_DC_DIS_RATE, - .dc_disconnect_mask = 0xf, - .usb_dc_disconnect_at_page0 = false, - .do_toggle = true, - .do_toggle_driving = true, - .driving_updated_for_dev_dis = 0x8, - .use_default_parameter = false, - .is_double_sensitivity_mode = true, -}; - -static const struct phy_cfg rtd1319d_phy_cfg = { - .page0_size = MAX_USB_PHY_PAGE0_DATA_SIZE, - .page0 = { [0] = {0xe0, 0xa3}, - [4] = {0xe4, 0x8e}, - [5] = {0xe5, 0x4f}, - [6] = {0xe6, 0x02}, }, - .page1_size = MAX_USB_PHY_PAGE1_DATA_SIZE, - .page1 = { [14] = {0xf5, 0x1}, }, - .page2_size = MAX_USB_PHY_PAGE2_DATA_SIZE, - .page2 = { [7] = {0xe7, 0x44}, }, - .check_efuse = true, - .num_phy = 1, - .check_efuse_version = CHECK_EFUSE_V1, - .efuse_dc_driving_rate = EFUS_USB_DC_CAL_RATE, - .dc_driving_mask = 0x1f, - .efuse_dc_disconnect_rate = EFUS_USB_DC_DIS_RATE, - .dc_disconnect_mask = 0xf, - .usb_dc_disconnect_at_page0 = false, - .do_toggle = true, - .do_toggle_driving = false, - .driving_updated_for_dev_dis = 0x8, - .use_default_parameter = false, - .is_double_sensitivity_mode = true, -}; - -static const struct phy_cfg rtd1315e_phy_cfg = { - .page0_size = MAX_USB_PHY_PAGE0_DATA_SIZE, - .page0 = { [0] = {0xe0, 0xa3}, - [4] = {0xe4, 0x8c}, - [5] = {0xe5, 0x4f}, - [6] = {0xe6, 0x02}, }, - .page1_size = MAX_USB_PHY_PAGE1_DATA_SIZE, - .page1 = { [3] = {0xe3, 0x7f}, - [14] = {0xf5, 0x01}, }, - .page2_size = MAX_USB_PHY_PAGE2_DATA_SIZE, - .page2 = { [7] = {0xe7, 0x44}, }, - .num_phy = 1, - .check_efuse = true, - .check_efuse_version = CHECK_EFUSE_V2, - .efuse_dc_driving_rate = EFUS_USB_DC_CAL_RATE, - .dc_driving_mask = 0x1f, - .efuse_dc_disconnect_rate = EFUS_USB_DC_DIS_RATE, - .dc_disconnect_mask = 0xf, - .usb_dc_disconnect_at_page0 = false, - .do_toggle = true, - .do_toggle_driving = false, - .driving_updated_for_dev_dis = 0x8, - .use_default_parameter = false, - .is_double_sensitivity_mode = true, -}; - -static const struct of_device_id usbphy_rtk_dt_match[] = { - { .compatible = "realtek,rtd1295-usb2phy", .data = &rtd1295_phy_cfg }, - { .compatible = "realtek,rtd1312c-usb2phy", .data = &rtd1312c_phy_cfg }, - { .compatible = "realtek,rtd1315e-usb2phy", .data = &rtd1315e_phy_cfg }, - { .compatible = "realtek,rtd1319-usb2phy", .data = &rtd1319_phy_cfg }, - { .compatible = "realtek,rtd1319d-usb2phy", .data = &rtd1319d_phy_cfg }, - { .compatible = "realtek,rtd1395-usb2phy", .data = &rtd1395_phy_cfg }, - { .compatible = "realtek,rtd1395-usb2phy-2port", .data = &rtd1395_phy_cfg_2port }, - { .compatible = "realtek,rtd1619-usb2phy", .data = &rtd1619_phy_cfg }, - { .compatible = "realtek,rtd1619b-usb2phy", .data = &rtd1619b_phy_cfg }, - {}, -}; -MODULE_DEVICE_TABLE(of, usbphy_rtk_dt_match); - -static struct platform_driver rtk_usb2phy_driver = { - .probe = rtk_usb2phy_probe, - .remove_new = rtk_usb2phy_remove, - .driver = { - .name = "rtk-usb2phy", - .of_match_table = usbphy_rtk_dt_match, - }, -}; - -module_platform_driver(rtk_usb2phy_driver); - -MODULE_LICENSE("GPL"); -MODULE_ALIAS("platform: rtk-usb2phy"); -MODULE_AUTHOR("Stanley Chang "); -MODULE_DESCRIPTION("Realtek usb 2.0 phy driver"); diff --git a/drivers/phy/realtek/phy-rtk-usb3.c b/drivers/phy/realtek/phy-rtk-usb3.c deleted file mode 100644 index dfb3122f3f114..0000000000000 --- a/drivers/phy/realtek/phy-rtk-usb3.c +++ /dev/null @@ -1,761 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * phy-rtk-usb3.c RTK usb3.0 phy driver - * - * copyright (c) 2023 realtek semiconductor corporation - * - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#define USB_MDIO_CTRL_PHY_BUSY BIT(7) -#define USB_MDIO_CTRL_PHY_WRITE BIT(0) -#define USB_MDIO_CTRL_PHY_ADDR_SHIFT 8 -#define USB_MDIO_CTRL_PHY_DATA_SHIFT 16 - -#define MAX_USB_PHY_DATA_SIZE 0x30 -#define PHY_ADDR_0X09 0x09 -#define PHY_ADDR_0X0B 0x0b -#define PHY_ADDR_0X0D 0x0d -#define PHY_ADDR_0X10 0x10 -#define PHY_ADDR_0X1F 0x1f -#define PHY_ADDR_0X20 0x20 -#define PHY_ADDR_0X21 0x21 -#define PHY_ADDR_0X30 0x30 - -#define REG_0X09_FORCE_CALIBRATION BIT(9) -#define REG_0X0B_RX_OFFSET_RANGE_MASK 0xc -#define REG_0X0D_RX_DEBUG_TEST_EN BIT(6) -#define REG_0X10_DEBUG_MODE_SETTING 0x3c0 -#define REG_0X10_DEBUG_MODE_SETTING_MASK 0x3f8 -#define REG_0X1F_RX_OFFSET_CODE_MASK 0x1e - -#define USB_U3_TX_LFPS_SWING_TRIM_SHIFT 4 -#define USB_U3_TX_LFPS_SWING_TRIM_MASK 0xf -#define AMPLITUDE_CONTROL_COARSE_MASK 0xff -#define AMPLITUDE_CONTROL_FINE_MASK 0xffff -#define AMPLITUDE_CONTROL_COARSE_DEFAULT 0xff -#define AMPLITUDE_CONTROL_FINE_DEFAULT 0xffff - -#define PHY_ADDR_MAP_ARRAY_INDEX(addr) (addr) -#define ARRAY_INDEX_MAP_PHY_ADDR(index) (index) - -struct phy_reg { - void __iomem *reg_mdio_ctl; -}; - -struct phy_data { - u8 addr; - u16 data; -}; - -struct phy_cfg { - int param_size; - struct phy_data param[MAX_USB_PHY_DATA_SIZE]; - - bool check_efuse; - bool do_toggle; - bool do_toggle_once; - bool use_default_parameter; - bool check_rx_front_end_offset; -}; - -struct phy_parameter { - struct phy_reg phy_reg; - - /* Get from efuse */ - u8 efuse_usb_u3_tx_lfps_swing_trim; - - /* Get from dts */ - u32 amplitude_control_coarse; - u32 amplitude_control_fine; -}; - -struct rtk_phy { - struct usb_phy phy; - struct device *dev; - - struct phy_cfg *phy_cfg; - int num_phy; - struct phy_parameter *phy_parameter; - - struct dentry *debug_dir; -}; - -#define PHY_IO_TIMEOUT_USEC (50000) -#define PHY_IO_DELAY_US (100) - -static inline int utmi_wait_register(void __iomem *reg, u32 mask, u32 result) -{ - int ret; - unsigned int val; - - ret = read_poll_timeout(readl, val, ((val & mask) == result), - PHY_IO_DELAY_US, PHY_IO_TIMEOUT_USEC, false, reg); - if (ret) { - pr_err("%s can't program USB phy\n", __func__); - return -ETIMEDOUT; - } - - return 0; -} - -static int rtk_phy3_wait_vbusy(struct phy_reg *phy_reg) -{ - return utmi_wait_register(phy_reg->reg_mdio_ctl, USB_MDIO_CTRL_PHY_BUSY, 0); -} - -static u16 rtk_phy_read(struct phy_reg *phy_reg, char addr) -{ - unsigned int tmp; - u32 value; - - tmp = (addr << USB_MDIO_CTRL_PHY_ADDR_SHIFT); - - writel(tmp, phy_reg->reg_mdio_ctl); - - rtk_phy3_wait_vbusy(phy_reg); - - value = readl(phy_reg->reg_mdio_ctl); - value = value >> USB_MDIO_CTRL_PHY_DATA_SHIFT; - - return (u16)value; -} - -static int rtk_phy_write(struct phy_reg *phy_reg, char addr, u16 data) -{ - unsigned int val; - - val = USB_MDIO_CTRL_PHY_WRITE | - (addr << USB_MDIO_CTRL_PHY_ADDR_SHIFT) | - (data << USB_MDIO_CTRL_PHY_DATA_SHIFT); - - writel(val, phy_reg->reg_mdio_ctl); - - rtk_phy3_wait_vbusy(phy_reg); - - return 0; -} - -static void do_rtk_usb3_phy_toggle(struct rtk_phy *rtk_phy, int index, bool connect) -{ - struct phy_cfg *phy_cfg = rtk_phy->phy_cfg; - struct phy_reg *phy_reg; - struct phy_parameter *phy_parameter; - struct phy_data *phy_data; - u8 addr; - u16 data; - int i; - - phy_parameter = &((struct phy_parameter *)rtk_phy->phy_parameter)[index]; - phy_reg = &phy_parameter->phy_reg; - - if (!phy_cfg->do_toggle) - return; - - i = PHY_ADDR_MAP_ARRAY_INDEX(PHY_ADDR_0X09); - phy_data = phy_cfg->param + i; - addr = phy_data->addr; - data = phy_data->data; - - if (!addr && !data) { - addr = PHY_ADDR_0X09; - data = rtk_phy_read(phy_reg, addr); - phy_data->addr = addr; - phy_data->data = data; - } - - rtk_phy_write(phy_reg, addr, data & (~REG_0X09_FORCE_CALIBRATION)); - mdelay(1); - rtk_phy_write(phy_reg, addr, data | REG_0X09_FORCE_CALIBRATION); -} - -static int do_rtk_phy_init(struct rtk_phy *rtk_phy, int index) -{ - struct phy_cfg *phy_cfg; - struct phy_reg *phy_reg; - struct phy_parameter *phy_parameter; - int i = 0; - - phy_cfg = rtk_phy->phy_cfg; - phy_parameter = &((struct phy_parameter *)rtk_phy->phy_parameter)[index]; - phy_reg = &phy_parameter->phy_reg; - - if (phy_cfg->use_default_parameter) - goto do_toggle; - - for (i = 0; i < phy_cfg->param_size; i++) { - struct phy_data *phy_data = phy_cfg->param + i; - u8 addr = phy_data->addr; - u16 data = phy_data->data; - - if (!addr && !data) - continue; - - rtk_phy_write(phy_reg, addr, data); - } - -do_toggle: - if (phy_cfg->do_toggle_once) - phy_cfg->do_toggle = true; - - do_rtk_usb3_phy_toggle(rtk_phy, index, false); - - if (phy_cfg->do_toggle_once) { - u16 check_value = 0; - int count = 10; - u16 value_0x0d, value_0x10; - - /* Enable Debug mode by set 0x0D and 0x10 */ - value_0x0d = rtk_phy_read(phy_reg, PHY_ADDR_0X0D); - value_0x10 = rtk_phy_read(phy_reg, PHY_ADDR_0X10); - - rtk_phy_write(phy_reg, PHY_ADDR_0X0D, - value_0x0d | REG_0X0D_RX_DEBUG_TEST_EN); - rtk_phy_write(phy_reg, PHY_ADDR_0X10, - (value_0x10 & ~REG_0X10_DEBUG_MODE_SETTING_MASK) | - REG_0X10_DEBUG_MODE_SETTING); - - check_value = rtk_phy_read(phy_reg, PHY_ADDR_0X30); - - while (!(check_value & BIT(15))) { - check_value = rtk_phy_read(phy_reg, PHY_ADDR_0X30); - mdelay(1); - if (count-- < 0) - break; - } - - if (!(check_value & BIT(15))) - dev_info(rtk_phy->dev, "toggle fail addr=0x%02x, data=0x%04x\n", - PHY_ADDR_0X30, check_value); - - /* Disable Debug mode by set 0x0D and 0x10 to default*/ - rtk_phy_write(phy_reg, PHY_ADDR_0X0D, value_0x0d); - rtk_phy_write(phy_reg, PHY_ADDR_0X10, value_0x10); - - phy_cfg->do_toggle = false; - } - - if (phy_cfg->check_rx_front_end_offset) { - u16 rx_offset_code, rx_offset_range; - u16 code_mask = REG_0X1F_RX_OFFSET_CODE_MASK; - u16 range_mask = REG_0X0B_RX_OFFSET_RANGE_MASK; - bool do_update = false; - - rx_offset_code = rtk_phy_read(phy_reg, PHY_ADDR_0X1F); - if (((rx_offset_code & code_mask) == 0x0) || - ((rx_offset_code & code_mask) == code_mask)) - do_update = true; - - rx_offset_range = rtk_phy_read(phy_reg, PHY_ADDR_0X0B); - if (((rx_offset_range & range_mask) == range_mask) && do_update) { - dev_warn(rtk_phy->dev, "Don't update rx_offset_range (rx_offset_code=0x%x, rx_offset_range=0x%x)\n", - rx_offset_code, rx_offset_range); - do_update = false; - } - - if (do_update) { - u16 tmp1, tmp2; - - tmp1 = rx_offset_range & (~range_mask); - tmp2 = rx_offset_range & range_mask; - tmp2 += (1 << 2); - rx_offset_range = tmp1 | (tmp2 & range_mask); - rtk_phy_write(phy_reg, PHY_ADDR_0X0B, rx_offset_range); - goto do_toggle; - } - } - - return 0; -} - -static int rtk_phy_init(struct phy *phy) -{ - struct rtk_phy *rtk_phy = phy_get_drvdata(phy); - int ret = 0; - int i; - unsigned long phy_init_time = jiffies; - - for (i = 0; i < rtk_phy->num_phy; i++) - ret = do_rtk_phy_init(rtk_phy, i); - - dev_dbg(rtk_phy->dev, "Initialized RTK USB 3.0 PHY (take %dms)\n", - jiffies_to_msecs(jiffies - phy_init_time)); - - return ret; -} - -static int rtk_phy_exit(struct phy *phy) -{ - return 0; -} - -static const struct phy_ops ops = { - .init = rtk_phy_init, - .exit = rtk_phy_exit, - .owner = THIS_MODULE, -}; - -static void rtk_phy_toggle(struct usb_phy *usb3_phy, bool connect, int port) -{ - int index = port; - struct rtk_phy *rtk_phy = NULL; - - rtk_phy = dev_get_drvdata(usb3_phy->dev); - - if (index > rtk_phy->num_phy) { - dev_err(rtk_phy->dev, "%s: The port=%d is not in usb phy (num_phy=%d)\n", - __func__, index, rtk_phy->num_phy); - return; - } - - do_rtk_usb3_phy_toggle(rtk_phy, index, connect); -} - -static int rtk_phy_notify_port_status(struct usb_phy *x, int port, - u16 portstatus, u16 portchange) -{ - bool connect = false; - - pr_debug("%s port=%d portstatus=0x%x portchange=0x%x\n", - __func__, port, (int)portstatus, (int)portchange); - if (portstatus & USB_PORT_STAT_CONNECTION) - connect = true; - - if (portchange & USB_PORT_STAT_C_CONNECTION) - rtk_phy_toggle(x, connect, port); - - return 0; -} - -#ifdef CONFIG_DEBUG_FS -static struct dentry *create_phy_debug_root(void) -{ - struct dentry *phy_debug_root; - - phy_debug_root = debugfs_lookup("phy", usb_debug_root); - if (!phy_debug_root) - phy_debug_root = debugfs_create_dir("phy", usb_debug_root); - - return phy_debug_root; -} - -static int rtk_usb3_parameter_show(struct seq_file *s, void *unused) -{ - struct rtk_phy *rtk_phy = s->private; - struct phy_cfg *phy_cfg; - int i, index; - - phy_cfg = rtk_phy->phy_cfg; - - seq_puts(s, "Property:\n"); - seq_printf(s, " check_efuse: %s\n", - phy_cfg->check_efuse ? "Enable" : "Disable"); - seq_printf(s, " do_toggle: %s\n", - phy_cfg->do_toggle ? "Enable" : "Disable"); - seq_printf(s, " do_toggle_once: %s\n", - phy_cfg->do_toggle_once ? "Enable" : "Disable"); - seq_printf(s, " use_default_parameter: %s\n", - phy_cfg->use_default_parameter ? "Enable" : "Disable"); - - for (index = 0; index < rtk_phy->num_phy; index++) { - struct phy_reg *phy_reg; - struct phy_parameter *phy_parameter; - - phy_parameter = &((struct phy_parameter *)rtk_phy->phy_parameter)[index]; - phy_reg = &phy_parameter->phy_reg; - - seq_printf(s, "PHY %d:\n", index); - - for (i = 0; i < phy_cfg->param_size; i++) { - struct phy_data *phy_data = phy_cfg->param + i; - u8 addr = ARRAY_INDEX_MAP_PHY_ADDR(i); - u16 data = phy_data->data; - - if (!phy_data->addr && !data) - seq_printf(s, " addr = 0x%02x, data = none ==> read value = 0x%04x\n", - addr, rtk_phy_read(phy_reg, addr)); - else - seq_printf(s, " addr = 0x%02x, data = 0x%04x ==> read value = 0x%04x\n", - addr, data, rtk_phy_read(phy_reg, addr)); - } - - seq_puts(s, "PHY Property:\n"); - seq_printf(s, " efuse_usb_u3_tx_lfps_swing_trim: 0x%x\n", - (int)phy_parameter->efuse_usb_u3_tx_lfps_swing_trim); - seq_printf(s, " amplitude_control_coarse: 0x%x\n", - (int)phy_parameter->amplitude_control_coarse); - seq_printf(s, " amplitude_control_fine: 0x%x\n", - (int)phy_parameter->amplitude_control_fine); - } - - return 0; -} -DEFINE_SHOW_ATTRIBUTE(rtk_usb3_parameter); - -static inline void create_debug_files(struct rtk_phy *rtk_phy) -{ - struct dentry *phy_debug_root = NULL; - - phy_debug_root = create_phy_debug_root(); - - if (!phy_debug_root) - return; - - rtk_phy->debug_dir = debugfs_create_dir(dev_name(rtk_phy->dev), phy_debug_root); - - debugfs_create_file("parameter", 0444, rtk_phy->debug_dir, rtk_phy, - &rtk_usb3_parameter_fops); - - return; -} - -static inline void remove_debug_files(struct rtk_phy *rtk_phy) -{ - debugfs_remove_recursive(rtk_phy->debug_dir); -} -#else -static inline void create_debug_files(struct rtk_phy *rtk_phy) { } -static inline void remove_debug_files(struct rtk_phy *rtk_phy) { } -#endif /* CONFIG_DEBUG_FS */ - -static int get_phy_data_by_efuse(struct rtk_phy *rtk_phy, - struct phy_parameter *phy_parameter, int index) -{ - struct phy_cfg *phy_cfg = rtk_phy->phy_cfg; - u8 value = 0; - struct nvmem_cell *cell; - - if (!phy_cfg->check_efuse) - goto out; - - cell = nvmem_cell_get(rtk_phy->dev, "usb_u3_tx_lfps_swing_trim"); - if (IS_ERR(cell)) { - dev_dbg(rtk_phy->dev, "%s no usb_u3_tx_lfps_swing_trim: %ld\n", - __func__, PTR_ERR(cell)); - } else { - unsigned char *buf; - size_t buf_size; - - buf = nvmem_cell_read(cell, &buf_size); - if (!IS_ERR(buf)) { - value = buf[0] & USB_U3_TX_LFPS_SWING_TRIM_MASK; - kfree(buf); - } - nvmem_cell_put(cell); - } - - if (value > 0 && value < 0x8) - phy_parameter->efuse_usb_u3_tx_lfps_swing_trim = 0x8; - else - phy_parameter->efuse_usb_u3_tx_lfps_swing_trim = (u8)value; - -out: - return 0; -} - -static void update_amplitude_control_value(struct rtk_phy *rtk_phy, - struct phy_parameter *phy_parameter) -{ - struct phy_cfg *phy_cfg; - struct phy_reg *phy_reg; - - phy_reg = &phy_parameter->phy_reg; - phy_cfg = rtk_phy->phy_cfg; - - if (phy_parameter->amplitude_control_coarse != AMPLITUDE_CONTROL_COARSE_DEFAULT) { - u16 val_mask = AMPLITUDE_CONTROL_COARSE_MASK; - u16 data; - - if (!phy_cfg->param[PHY_ADDR_0X20].addr && !phy_cfg->param[PHY_ADDR_0X20].data) { - phy_cfg->param[PHY_ADDR_0X20].addr = PHY_ADDR_0X20; - data = rtk_phy_read(phy_reg, PHY_ADDR_0X20); - } else { - data = phy_cfg->param[PHY_ADDR_0X20].data; - } - - data &= (~val_mask); - data |= (phy_parameter->amplitude_control_coarse & val_mask); - - phy_cfg->param[PHY_ADDR_0X20].data = data; - } - - if (phy_parameter->efuse_usb_u3_tx_lfps_swing_trim) { - u8 efuse_val = phy_parameter->efuse_usb_u3_tx_lfps_swing_trim; - u16 val_mask = USB_U3_TX_LFPS_SWING_TRIM_MASK; - int val_shift = USB_U3_TX_LFPS_SWING_TRIM_SHIFT; - u16 data; - - if (!phy_cfg->param[PHY_ADDR_0X20].addr && !phy_cfg->param[PHY_ADDR_0X20].data) { - phy_cfg->param[PHY_ADDR_0X20].addr = PHY_ADDR_0X20; - data = rtk_phy_read(phy_reg, PHY_ADDR_0X20); - } else { - data = phy_cfg->param[PHY_ADDR_0X20].data; - } - - data &= ~(val_mask << val_shift); - data |= ((efuse_val & val_mask) << val_shift); - - phy_cfg->param[PHY_ADDR_0X20].data = data; - } - - if (phy_parameter->amplitude_control_fine != AMPLITUDE_CONTROL_FINE_DEFAULT) { - u16 val_mask = AMPLITUDE_CONTROL_FINE_MASK; - - if (!phy_cfg->param[PHY_ADDR_0X21].addr && !phy_cfg->param[PHY_ADDR_0X21].data) - phy_cfg->param[PHY_ADDR_0X21].addr = PHY_ADDR_0X21; - - phy_cfg->param[PHY_ADDR_0X21].data = - phy_parameter->amplitude_control_fine & val_mask; - } -} - -static int parse_phy_data(struct rtk_phy *rtk_phy) -{ - struct device *dev = rtk_phy->dev; - struct phy_parameter *phy_parameter; - int ret = 0; - int index; - - rtk_phy->phy_parameter = devm_kzalloc(dev, sizeof(struct phy_parameter) * - rtk_phy->num_phy, GFP_KERNEL); - if (!rtk_phy->phy_parameter) - return -ENOMEM; - - for (index = 0; index < rtk_phy->num_phy; index++) { - phy_parameter = &((struct phy_parameter *)rtk_phy->phy_parameter)[index]; - - phy_parameter->phy_reg.reg_mdio_ctl = of_iomap(dev->of_node, 0) + index; - - /* Amplitude control address 0x20 bit 0 to bit 7 */ - if (of_property_read_u32(dev->of_node, "realtek,amplitude-control-coarse-tuning", - &phy_parameter->amplitude_control_coarse)) - phy_parameter->amplitude_control_coarse = AMPLITUDE_CONTROL_COARSE_DEFAULT; - - /* Amplitude control address 0x21 bit 0 to bit 16 */ - if (of_property_read_u32(dev->of_node, "realtek,amplitude-control-fine-tuning", - &phy_parameter->amplitude_control_fine)) - phy_parameter->amplitude_control_fine = AMPLITUDE_CONTROL_FINE_DEFAULT; - - get_phy_data_by_efuse(rtk_phy, phy_parameter, index); - - update_amplitude_control_value(rtk_phy, phy_parameter); - } - - return ret; -} - -static int rtk_usb3phy_probe(struct platform_device *pdev) -{ - struct rtk_phy *rtk_phy; - struct device *dev = &pdev->dev; - struct phy *generic_phy; - struct phy_provider *phy_provider; - const struct phy_cfg *phy_cfg; - int ret; - - phy_cfg = of_device_get_match_data(dev); - if (!phy_cfg) { - dev_err(dev, "phy config are not assigned!\n"); - return -EINVAL; - } - - rtk_phy = devm_kzalloc(dev, sizeof(*rtk_phy), GFP_KERNEL); - if (!rtk_phy) - return -ENOMEM; - - rtk_phy->dev = &pdev->dev; - rtk_phy->phy.dev = rtk_phy->dev; - rtk_phy->phy.label = "rtk-usb3phy"; - rtk_phy->phy.notify_port_status = rtk_phy_notify_port_status; - - rtk_phy->phy_cfg = devm_kzalloc(dev, sizeof(*phy_cfg), GFP_KERNEL); - - memcpy(rtk_phy->phy_cfg, phy_cfg, sizeof(*phy_cfg)); - - rtk_phy->num_phy = 1; - - ret = parse_phy_data(rtk_phy); - if (ret) - goto err; - - platform_set_drvdata(pdev, rtk_phy); - - generic_phy = devm_phy_create(rtk_phy->dev, NULL, &ops); - if (IS_ERR(generic_phy)) - return PTR_ERR(generic_phy); - - phy_set_drvdata(generic_phy, rtk_phy); - - phy_provider = devm_of_phy_provider_register(rtk_phy->dev, of_phy_simple_xlate); - if (IS_ERR(phy_provider)) - return PTR_ERR(phy_provider); - - ret = usb_add_phy_dev(&rtk_phy->phy); - if (ret) - goto err; - - create_debug_files(rtk_phy); - -err: - return ret; -} - -static void rtk_usb3phy_remove(struct platform_device *pdev) -{ - struct rtk_phy *rtk_phy = platform_get_drvdata(pdev); - - remove_debug_files(rtk_phy); - - usb_remove_phy(&rtk_phy->phy); -} - -static const struct phy_cfg rtd1295_phy_cfg = { - .param_size = MAX_USB_PHY_DATA_SIZE, - .param = { [0] = {0x01, 0x4008}, [1] = {0x01, 0xe046}, - [2] = {0x02, 0x6046}, [3] = {0x03, 0x2779}, - [4] = {0x04, 0x72f5}, [5] = {0x05, 0x2ad3}, - [6] = {0x06, 0x000e}, [7] = {0x07, 0x2e00}, - [8] = {0x08, 0x3591}, [9] = {0x09, 0x525c}, - [10] = {0x0a, 0xa600}, [11] = {0x0b, 0xa904}, - [12] = {0x0c, 0xc000}, [13] = {0x0d, 0xef1c}, - [14] = {0x0e, 0x2000}, [15] = {0x0f, 0x0000}, - [16] = {0x10, 0x000c}, [17] = {0x11, 0x4c00}, - [18] = {0x12, 0xfc00}, [19] = {0x13, 0x0c81}, - [20] = {0x14, 0xde01}, [21] = {0x15, 0x0000}, - [22] = {0x16, 0x0000}, [23] = {0x17, 0x0000}, - [24] = {0x18, 0x0000}, [25] = {0x19, 0x4004}, - [26] = {0x1a, 0x1260}, [27] = {0x1b, 0xff00}, - [28] = {0x1c, 0xcb00}, [29] = {0x1d, 0xa03f}, - [30] = {0x1e, 0xc2e0}, [31] = {0x1f, 0x2807}, - [32] = {0x20, 0x947a}, [33] = {0x21, 0x88aa}, - [34] = {0x22, 0x0057}, [35] = {0x23, 0xab66}, - [36] = {0x24, 0x0800}, [37] = {0x25, 0x0000}, - [38] = {0x26, 0x040a}, [39] = {0x27, 0x01d6}, - [40] = {0x28, 0xf8c2}, [41] = {0x29, 0x3080}, - [42] = {0x2a, 0x3082}, [43] = {0x2b, 0x2078}, - [44] = {0x2c, 0xffff}, [45] = {0x2d, 0xffff}, - [46] = {0x2e, 0x0000}, [47] = {0x2f, 0x0040}, }, - .check_efuse = false, - .do_toggle = true, - .do_toggle_once = false, - .use_default_parameter = false, - .check_rx_front_end_offset = false, -}; - -static const struct phy_cfg rtd1619_phy_cfg = { - .param_size = MAX_USB_PHY_DATA_SIZE, - .param = { [8] = {0x08, 0x3591}, - [38] = {0x26, 0x840b}, - [40] = {0x28, 0xf842}, }, - .check_efuse = false, - .do_toggle = true, - .do_toggle_once = false, - .use_default_parameter = false, - .check_rx_front_end_offset = false, -}; - -static const struct phy_cfg rtd1319_phy_cfg = { - .param_size = MAX_USB_PHY_DATA_SIZE, - .param = { [1] = {0x01, 0xac86}, - [6] = {0x06, 0x0003}, - [9] = {0x09, 0x924c}, - [10] = {0x0a, 0xa608}, - [11] = {0x0b, 0xb905}, - [14] = {0x0e, 0x2010}, - [32] = {0x20, 0x705a}, - [33] = {0x21, 0xf645}, - [34] = {0x22, 0x0013}, - [35] = {0x23, 0xcb66}, - [41] = {0x29, 0xff00}, }, - .check_efuse = true, - .do_toggle = true, - .do_toggle_once = false, - .use_default_parameter = false, - .check_rx_front_end_offset = false, -}; - -static const struct phy_cfg rtd1619b_phy_cfg = { - .param_size = MAX_USB_PHY_DATA_SIZE, - .param = { [1] = {0x01, 0xac8c}, - [6] = {0x06, 0x0017}, - [9] = {0x09, 0x724c}, - [10] = {0x0a, 0xb610}, - [11] = {0x0b, 0xb90d}, - [13] = {0x0d, 0xef2a}, - [15] = {0x0f, 0x9050}, - [16] = {0x10, 0x000c}, - [32] = {0x20, 0x70ff}, - [34] = {0x22, 0x0013}, - [35] = {0x23, 0xdb66}, - [38] = {0x26, 0x8609}, - [41] = {0x29, 0xff13}, - [42] = {0x2a, 0x3070}, }, - .check_efuse = true, - .do_toggle = false, - .do_toggle_once = true, - .use_default_parameter = false, - .check_rx_front_end_offset = false, -}; - -static const struct phy_cfg rtd1319d_phy_cfg = { - .param_size = MAX_USB_PHY_DATA_SIZE, - .param = { [1] = {0x01, 0xac89}, - [4] = {0x04, 0xf2f5}, - [6] = {0x06, 0x0017}, - [9] = {0x09, 0x424c}, - [10] = {0x0a, 0x9610}, - [11] = {0x0b, 0x9901}, - [12] = {0x0c, 0xf000}, - [13] = {0x0d, 0xef2a}, - [14] = {0x0e, 0x1000}, - [15] = {0x0f, 0x9050}, - [32] = {0x20, 0x7077}, - [35] = {0x23, 0x0b62}, - [37] = {0x25, 0x10ec}, - [42] = {0x2a, 0x3070}, }, - .check_efuse = true, - .do_toggle = false, - .do_toggle_once = true, - .use_default_parameter = false, - .check_rx_front_end_offset = true, -}; - -static const struct of_device_id usbphy_rtk_dt_match[] = { - { .compatible = "realtek,rtd1295-usb3phy", .data = &rtd1295_phy_cfg }, - { .compatible = "realtek,rtd1319-usb3phy", .data = &rtd1319_phy_cfg }, - { .compatible = "realtek,rtd1319d-usb3phy", .data = &rtd1319d_phy_cfg }, - { .compatible = "realtek,rtd1619-usb3phy", .data = &rtd1619_phy_cfg }, - { .compatible = "realtek,rtd1619b-usb3phy", .data = &rtd1619b_phy_cfg }, - {}, -}; -MODULE_DEVICE_TABLE(of, usbphy_rtk_dt_match); - -static struct platform_driver rtk_usb3phy_driver = { - .probe = rtk_usb3phy_probe, - .remove_new = rtk_usb3phy_remove, - .driver = { - .name = "rtk-usb3phy", - .of_match_table = usbphy_rtk_dt_match, - }, -}; - -module_platform_driver(rtk_usb3phy_driver); - -MODULE_LICENSE("GPL"); -MODULE_ALIAS("platform: rtk-usb3phy"); -MODULE_AUTHOR("Stanley Chang "); -MODULE_DESCRIPTION("Realtek usb 3.0 phy driver"); diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c index e9dc9638120a5..184ec92241ca8 100644 --- a/drivers/pinctrl/core.c +++ b/drivers/pinctrl/core.c @@ -1253,17 +1253,17 @@ static void pinctrl_link_add(struct pinctrl_dev *pctldev, static int pinctrl_commit_state(struct pinctrl *p, struct pinctrl_state *state) { struct pinctrl_setting *setting, *setting2; - struct pinctrl_state *old_state = p->state; + struct pinctrl_state *old_state = READ_ONCE(p->state); int ret; - if (p->state) { + if (old_state) { /* * For each pinmux setting in the old state, forget SW's record * of mux owner for that pingroup. Any pingroups which are * still owned by the new state will be re-acquired by the call * to pinmux_enable_setting() in the loop below. */ - list_for_each_entry(setting, &p->state->settings, node) { + list_for_each_entry(setting, &old_state->settings, node) { if (setting->type != PIN_MAP_TYPE_MUX_GROUP) continue; pinmux_disable_setting(setting); diff --git a/drivers/pinctrl/pinctrl-at91-pio4.c b/drivers/pinctrl/pinctrl-at91-pio4.c index 383309e533c3d..a27c01fcbb47e 100644 --- a/drivers/pinctrl/pinctrl-at91-pio4.c +++ b/drivers/pinctrl/pinctrl-at91-pio4.c @@ -1068,6 +1068,13 @@ static const struct of_device_id atmel_pctrl_of_match[] = { } }; +/* + * This lock class allows to tell lockdep that parent IRQ and children IRQ do + * not share the same class so it does not raise false positive + */ +static struct lock_class_key atmel_lock_key; +static struct lock_class_key atmel_request_key; + static int atmel_pinctrl_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -1214,6 +1221,7 @@ static int atmel_pinctrl_probe(struct platform_device *pdev) irq_set_chip_and_handler(irq, &atmel_gpio_irq_chip, handle_simple_irq); irq_set_chip_data(irq, atmel_pioctrl); + irq_set_lockdep_class(irq, &atmel_lock_key, &atmel_request_key); dev_dbg(dev, "atmel gpio irq domain: hwirq: %d, linux irq: %d\n", i, irq); diff --git a/drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c b/drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c index 530fe340a9a15..561fd0c6b9b0a 100644 --- a/drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c +++ b/drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c @@ -492,7 +492,7 @@ static int starfive_dt_node_to_map(struct pinctrl_dev *pctldev, nmaps = 0; ngroups = 0; - for_each_child_of_node(np, child) { + for_each_available_child_of_node(np, child) { int npinmux = of_property_count_u32_elems(child, "pinmux"); int npins = of_property_count_u32_elems(child, "pins"); @@ -527,7 +527,7 @@ static int starfive_dt_node_to_map(struct pinctrl_dev *pctldev, nmaps = 0; ngroups = 0; mutex_lock(&sfp->mutex); - for_each_child_of_node(np, child) { + for_each_available_child_of_node(np, child) { int npins; int i; diff --git a/drivers/pinctrl/starfive/pinctrl-starfive-jh7110.c b/drivers/pinctrl/starfive/pinctrl-starfive-jh7110.c index 640f827a9b2ca..b4f7995726894 100644 --- a/drivers/pinctrl/starfive/pinctrl-starfive-jh7110.c +++ b/drivers/pinctrl/starfive/pinctrl-starfive-jh7110.c @@ -135,7 +135,7 @@ static int jh7110_dt_node_to_map(struct pinctrl_dev *pctldev, int ret; ngroups = 0; - for_each_child_of_node(np, child) + for_each_available_child_of_node(np, child) ngroups += 1; nmaps = 2 * ngroups; @@ -150,7 +150,7 @@ static int jh7110_dt_node_to_map(struct pinctrl_dev *pctldev, nmaps = 0; ngroups = 0; mutex_lock(&sfp->mutex); - for_each_child_of_node(np, child) { + for_each_available_child_of_node(np, child) { int npins = of_property_count_u32_elems(child, "pinmux"); int *pins; u32 *pinmux; diff --git a/drivers/pinctrl/stm32/pinctrl-stm32.c b/drivers/pinctrl/stm32/pinctrl-stm32.c index a73385a431de9..346a31f31bba8 100644 --- a/drivers/pinctrl/stm32/pinctrl-stm32.c +++ b/drivers/pinctrl/stm32/pinctrl-stm32.c @@ -1283,9 +1283,11 @@ static struct stm32_desc_pin *stm32_pctrl_get_desc_pin_from_gpio(struct stm32_pi int i; /* With few exceptions (e.g. bank 'Z'), pin number matches with pin index in array */ - pin_desc = pctl->pins + stm32_pin_nb; - if (pin_desc->pin.number == stm32_pin_nb) - return pin_desc; + if (stm32_pin_nb < pctl->npins) { + pin_desc = pctl->pins + stm32_pin_nb; + if (pin_desc->pin.number == stm32_pin_nb) + return pin_desc; + } /* Otherwise, loop all array to find the pin with the right number */ for (i = 0; i < pctl->npins; i++) { @@ -1378,6 +1380,11 @@ static int stm32_gpiolib_register_bank(struct stm32_pinctrl *pctl, struct fwnode } names = devm_kcalloc(dev, npins, sizeof(char *), GFP_KERNEL); + if (!names) { + err = -ENOMEM; + goto err_clk; + } + for (i = 0; i < npins; i++) { stm32_pin = stm32_pctrl_get_desc_pin_from_gpio(pctl, bank, i); if (stm32_pin && stm32_pin->pin.name) diff --git a/drivers/platform/chrome/cros_ec_proto_test.c b/drivers/platform/chrome/cros_ec_proto_test.c index 5b9748e0463bc..63e38671e95a6 100644 --- a/drivers/platform/chrome/cros_ec_proto_test.c +++ b/drivers/platform/chrome/cros_ec_proto_test.c @@ -2668,6 +2668,7 @@ static int cros_ec_proto_test_init(struct kunit *test) ec_dev->dev->release = cros_ec_proto_test_release; ec_dev->cmd_xfer = cros_kunit_ec_xfer_mock; ec_dev->pkt_xfer = cros_kunit_ec_xfer_mock; + mutex_init(&ec_dev->lock); priv->msg = (struct cros_ec_command *)priv->_msg; diff --git a/drivers/platform/mellanox/mlxbf-bootctl.c b/drivers/platform/mellanox/mlxbf-bootctl.c index 4ee7bb431b7c0..e278092f889b9 100644 --- a/drivers/platform/mellanox/mlxbf-bootctl.c +++ b/drivers/platform/mellanox/mlxbf-bootctl.c @@ -20,6 +20,7 @@ #define MLXBF_BOOTCTL_SB_SECURE_MASK 0x03 #define MLXBF_BOOTCTL_SB_TEST_MASK 0x0c +#define MLXBF_BOOTCTL_SB_DEV_MASK BIT(4) #define MLXBF_SB_KEY_NUM 4 @@ -40,11 +41,18 @@ static struct mlxbf_bootctl_name boot_names[] = { { MLXBF_BOOTCTL_NONE, "none" }, }; +enum { + MLXBF_BOOTCTL_SB_LIFECYCLE_PRODUCTION = 0, + MLXBF_BOOTCTL_SB_LIFECYCLE_GA_SECURE = 1, + MLXBF_BOOTCTL_SB_LIFECYCLE_GA_NON_SECURE = 2, + MLXBF_BOOTCTL_SB_LIFECYCLE_RMA = 3 +}; + static const char * const mlxbf_bootctl_lifecycle_states[] = { - [0] = "Production", - [1] = "GA Secured", - [2] = "GA Non-Secured", - [3] = "RMA", + [MLXBF_BOOTCTL_SB_LIFECYCLE_PRODUCTION] = "Production", + [MLXBF_BOOTCTL_SB_LIFECYCLE_GA_SECURE] = "GA Secured", + [MLXBF_BOOTCTL_SB_LIFECYCLE_GA_NON_SECURE] = "GA Non-Secured", + [MLXBF_BOOTCTL_SB_LIFECYCLE_RMA] = "RMA", }; /* Log header format. */ @@ -247,25 +255,30 @@ static ssize_t second_reset_action_store(struct device *dev, static ssize_t lifecycle_state_show(struct device *dev, struct device_attribute *attr, char *buf) { + int status_bits; + int use_dev_key; + int test_state; int lc_state; - lc_state = mlxbf_bootctl_smc(MLXBF_BOOTCTL_GET_TBB_FUSE_STATUS, - MLXBF_BOOTCTL_FUSE_STATUS_LIFECYCLE); - if (lc_state < 0) - return lc_state; + status_bits = mlxbf_bootctl_smc(MLXBF_BOOTCTL_GET_TBB_FUSE_STATUS, + MLXBF_BOOTCTL_FUSE_STATUS_LIFECYCLE); + if (status_bits < 0) + return status_bits; - lc_state &= - MLXBF_BOOTCTL_SB_TEST_MASK | MLXBF_BOOTCTL_SB_SECURE_MASK; + use_dev_key = status_bits & MLXBF_BOOTCTL_SB_DEV_MASK; + test_state = status_bits & MLXBF_BOOTCTL_SB_TEST_MASK; + lc_state = status_bits & MLXBF_BOOTCTL_SB_SECURE_MASK; /* * If the test bits are set, we specify that the current state may be * due to using the test bits. */ - if (lc_state & MLXBF_BOOTCTL_SB_TEST_MASK) { - lc_state &= MLXBF_BOOTCTL_SB_SECURE_MASK; - + if (test_state) { return sprintf(buf, "%s(test)\n", mlxbf_bootctl_lifecycle_states[lc_state]); + } else if (use_dev_key && + (lc_state == MLXBF_BOOTCTL_SB_LIFECYCLE_GA_SECURE)) { + return sprintf(buf, "Secured (development)\n"); } return sprintf(buf, "%s\n", mlxbf_bootctl_lifecycle_states[lc_state]); diff --git a/drivers/platform/mellanox/mlxbf-pmc.c b/drivers/platform/mellanox/mlxbf-pmc.c index 2d4bbe99959ef..db7a1d360cd2c 100644 --- a/drivers/platform/mellanox/mlxbf-pmc.c +++ b/drivers/platform/mellanox/mlxbf-pmc.c @@ -1202,6 +1202,8 @@ static int mlxbf_pmc_init_perftype_counter(struct device *dev, int blk_num) attr->dev_attr.show = mlxbf_pmc_event_list_show; attr->nr = blk_num; attr->dev_attr.attr.name = devm_kasprintf(dev, GFP_KERNEL, "event_list"); + if (!attr->dev_attr.attr.name) + return -ENOMEM; pmc->block[blk_num].block_attr[i] = &attr->dev_attr.attr; attr = NULL; @@ -1214,6 +1216,8 @@ static int mlxbf_pmc_init_perftype_counter(struct device *dev, int blk_num) attr->nr = blk_num; attr->dev_attr.attr.name = devm_kasprintf(dev, GFP_KERNEL, "enable"); + if (!attr->dev_attr.attr.name) + return -ENOMEM; pmc->block[blk_num].block_attr[++i] = &attr->dev_attr.attr; attr = NULL; } @@ -1240,6 +1244,8 @@ static int mlxbf_pmc_init_perftype_counter(struct device *dev, int blk_num) attr->nr = blk_num; attr->dev_attr.attr.name = devm_kasprintf(dev, GFP_KERNEL, "counter%d", j); + if (!attr->dev_attr.attr.name) + return -ENOMEM; pmc->block[blk_num].block_attr[++i] = &attr->dev_attr.attr; attr = NULL; @@ -1251,6 +1257,8 @@ static int mlxbf_pmc_init_perftype_counter(struct device *dev, int blk_num) attr->nr = blk_num; attr->dev_attr.attr.name = devm_kasprintf(dev, GFP_KERNEL, "event%d", j); + if (!attr->dev_attr.attr.name) + return -ENOMEM; pmc->block[blk_num].block_attr[++i] = &attr->dev_attr.attr; attr = NULL; } @@ -1283,6 +1291,8 @@ static int mlxbf_pmc_init_perftype_reg(struct device *dev, int blk_num) attr->nr = blk_num; attr->dev_attr.attr.name = devm_kasprintf(dev, GFP_KERNEL, events[j].evt_name); + if (!attr->dev_attr.attr.name) + return -ENOMEM; pmc->block[blk_num].block_attr[i] = &attr->dev_attr.attr; attr = NULL; i++; @@ -1311,6 +1321,8 @@ static int mlxbf_pmc_create_groups(struct device *dev, int blk_num) pmc->block[blk_num].block_attr_grp.attrs = pmc->block[blk_num].block_attr; pmc->block[blk_num].block_attr_grp.name = devm_kasprintf( dev, GFP_KERNEL, pmc->block_name[blk_num]); + if (!pmc->block[blk_num].block_attr_grp.name) + return -ENOMEM; pmc->groups[blk_num] = &pmc->block[blk_num].block_attr_grp; return 0; @@ -1442,6 +1454,8 @@ static int mlxbf_pmc_probe(struct platform_device *pdev) pmc->hwmon_dev = devm_hwmon_device_register_with_groups( dev, "bfperf", pmc, pmc->groups); + if (IS_ERR(pmc->hwmon_dev)) + return PTR_ERR(pmc->hwmon_dev); platform_set_drvdata(pdev, pmc); return 0; diff --git a/drivers/platform/surface/aggregator/core.c b/drivers/platform/surface/aggregator/core.c index 1a6373dea109c..6152be38398c4 100644 --- a/drivers/platform/surface/aggregator/core.c +++ b/drivers/platform/surface/aggregator/core.c @@ -231,9 +231,12 @@ static int ssam_receive_buf(struct serdev_device *dev, const unsigned char *buf, size_t n) { struct ssam_controller *ctrl; + int ret; ctrl = serdev_device_get_drvdata(dev); - return ssam_controller_receive_buf(ctrl, buf, n); + ret = ssam_controller_receive_buf(ctrl, buf, n); + + return ret < 0 ? 0 : ret; } static void ssam_write_wakeup(struct serdev_device *dev) diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig index 2a10705433911..07eea525091b0 100644 --- a/drivers/platform/x86/Kconfig +++ b/drivers/platform/x86/Kconfig @@ -263,6 +263,7 @@ config ASUS_WMI depends on RFKILL || RFKILL = n depends on HOTPLUG_PCI depends on ACPI_VIDEO || ACPI_VIDEO = n + depends on SERIO_I8042 || SERIO_I8042 = n select INPUT_SPARSEKMAP select LEDS_CLASS select NEW_LEDS @@ -279,7 +280,6 @@ config ASUS_WMI config ASUS_NB_WMI tristate "Asus Notebook WMI Driver" depends on ASUS_WMI - depends on SERIO_I8042 || SERIO_I8042 = n help This is a driver for newer Asus notebooks. It adds extra features like wireless radio and bluetooth control, leds, hotkeys, backlight... diff --git a/drivers/platform/x86/amd/pmc/pmc.c b/drivers/platform/x86/amd/pmc/pmc.c index c1e788b67a748..212f164bc3dba 100644 --- a/drivers/platform/x86/amd/pmc/pmc.c +++ b/drivers/platform/x86/amd/pmc/pmc.c @@ -912,33 +912,6 @@ static const struct pci_device_id pmc_pci_ids[] = { { } }; -static int amd_pmc_get_dram_size(struct amd_pmc_dev *dev) -{ - int ret; - - switch (dev->cpu_id) { - case AMD_CPU_ID_YC: - if (!(dev->major > 90 || (dev->major == 90 && dev->minor > 39))) { - ret = -EINVAL; - goto err_dram_size; - } - break; - default: - ret = -EINVAL; - goto err_dram_size; - } - - ret = amd_pmc_send_cmd(dev, S2D_DRAM_SIZE, &dev->dram_size, dev->s2d_msg_id, true); - if (ret || !dev->dram_size) - goto err_dram_size; - - return 0; - -err_dram_size: - dev_err(dev->dev, "DRAM size command not supported for this platform\n"); - return ret; -} - static int amd_pmc_s2d_init(struct amd_pmc_dev *dev) { u32 phys_addr_low, phys_addr_hi; @@ -957,8 +930,8 @@ static int amd_pmc_s2d_init(struct amd_pmc_dev *dev) return -EIO; /* Get DRAM size */ - ret = amd_pmc_get_dram_size(dev); - if (ret) + ret = amd_pmc_send_cmd(dev, S2D_DRAM_SIZE, &dev->dram_size, dev->s2d_msg_id, true); + if (ret || !dev->dram_size) dev->dram_size = S2D_TELEMETRY_DRAMBYTES_MAX; /* Get STB DRAM address */ diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c index df1db54d4e183..af3da303e2b15 100644 --- a/drivers/platform/x86/asus-nb-wmi.c +++ b/drivers/platform/x86/asus-nb-wmi.c @@ -501,8 +501,6 @@ static const struct dmi_system_id asus_quirks[] = { static void asus_nb_wmi_quirks(struct asus_wmi_driver *driver) { - int ret; - quirks = &quirk_asus_unknown; dmi_check_system(asus_quirks); @@ -517,15 +515,6 @@ static void asus_nb_wmi_quirks(struct asus_wmi_driver *driver) if (tablet_mode_sw != -1) quirks->tablet_switch_mode = tablet_mode_sw; - - if (quirks->i8042_filter) { - ret = i8042_install_filter(quirks->i8042_filter); - if (ret) { - pr_warn("Unable to install key filter\n"); - return; - } - pr_info("Using i8042 filter function for receiving events\n"); - } } static const struct key_entry asus_nb_wmi_keymap[] = { diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index 19bfd30861aa8..9c6321c2fc3c5 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -4437,6 +4437,12 @@ static int asus_wmi_add(struct platform_device *pdev) goto fail_wmi_handler; } + if (asus->driver->quirks->i8042_filter) { + err = i8042_install_filter(asus->driver->quirks->i8042_filter); + if (err) + pr_warn("Unable to install key filter - %d\n", err); + } + asus_wmi_battery_init(asus); asus_wmi_debugfs_init(asus); @@ -4471,6 +4477,8 @@ static int asus_wmi_remove(struct platform_device *device) struct asus_wmi *asus; asus = platform_get_drvdata(device); + if (asus->driver->quirks->i8042_filter) + i8042_remove_filter(asus->driver->quirks->i8042_filter); wmi_remove_notify_handler(asus->driver->event_guid); asus_wmi_backlight_exit(asus); asus_wmi_input_exit(asus); diff --git a/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c b/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c index 5798b49ddaba9..6ddca857cc4d1 100644 --- a/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c +++ b/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c @@ -592,13 +592,11 @@ static int hp_add_other_attributes(int attr_type) int ret; char *attr_name; - mutex_lock(&bioscfg_drv.mutex); - attr_name_kobj = kzalloc(sizeof(*attr_name_kobj), GFP_KERNEL); - if (!attr_name_kobj) { - ret = -ENOMEM; - goto err_other_attr_init; - } + if (!attr_name_kobj) + return -ENOMEM; + + mutex_lock(&bioscfg_drv.mutex); /* Check if attribute type is supported */ switch (attr_type) { @@ -615,14 +613,14 @@ static int hp_add_other_attributes(int attr_type) default: pr_err("Error: Unknown attr_type: %d\n", attr_type); ret = -EINVAL; - goto err_other_attr_init; + kfree(attr_name_kobj); + goto unlock_drv_mutex; } ret = kobject_init_and_add(attr_name_kobj, &attr_name_ktype, NULL, "%s", attr_name); if (ret) { pr_err("Error encountered [%d]\n", ret); - kobject_put(attr_name_kobj); goto err_other_attr_init; } @@ -630,25 +628,25 @@ static int hp_add_other_attributes(int attr_type) switch (attr_type) { case HPWMI_SECURE_PLATFORM_TYPE: ret = hp_populate_secure_platform_data(attr_name_kobj); - if (ret) - goto err_other_attr_init; break; case HPWMI_SURE_START_TYPE: ret = hp_populate_sure_start_data(attr_name_kobj); - if (ret) - goto err_other_attr_init; break; default: ret = -EINVAL; - goto err_other_attr_init; } + if (ret) + goto err_other_attr_init; + mutex_unlock(&bioscfg_drv.mutex); return 0; err_other_attr_init: + kobject_put(attr_name_kobj); +unlock_drv_mutex: mutex_unlock(&bioscfg_drv.mutex); kfree(obj); return ret; diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c index ac037540acfc6..88eefccb6ed27 100644 --- a/drivers/platform/x86/ideapad-laptop.c +++ b/drivers/platform/x86/ideapad-laptop.c @@ -1425,18 +1425,17 @@ static int ideapad_kbd_bl_init(struct ideapad_private *priv) if (WARN_ON(priv->kbd_bl.initialized)) return -EEXIST; - brightness = ideapad_kbd_bl_brightness_get(priv); - if (brightness < 0) - return brightness; - - priv->kbd_bl.last_brightness = brightness; - if (ideapad_kbd_bl_check_tristate(priv->kbd_bl.type)) { priv->kbd_bl.led.max_brightness = 2; } else { priv->kbd_bl.led.max_brightness = 1; } + brightness = ideapad_kbd_bl_brightness_get(priv); + if (brightness < 0) + return brightness; + + priv->kbd_bl.last_brightness = brightness; priv->kbd_bl.led.name = "platform::" LED_FUNCTION_KBD_BACKLIGHT; priv->kbd_bl.led.brightness_get = ideapad_kbd_bl_led_cdev_brightness_get; priv->kbd_bl.led.brightness_set_blocking = ideapad_kbd_bl_led_cdev_brightness_set; diff --git a/drivers/platform/x86/intel/pmc/adl.c b/drivers/platform/x86/intel/pmc/adl.c index 5006008e01bea..606f7678bcb0a 100644 --- a/drivers/platform/x86/intel/pmc/adl.c +++ b/drivers/platform/x86/intel/pmc/adl.c @@ -314,16 +314,13 @@ int adl_core_init(struct pmc_dev *pmcdev) struct pmc *pmc = pmcdev->pmcs[PMC_IDX_MAIN]; int ret; + pmcdev->suspend = cnl_suspend; + pmcdev->resume = cnl_resume; + pmc->map = &adl_reg_map; ret = get_primary_reg_base(pmc); if (ret) return ret; - /* Due to a hardware limitation, the GBE LTR blocks PC10 - * when a cable is attached. Tell the PMC to ignore it. - */ - dev_dbg(&pmcdev->pdev->dev, "ignoring GBE LTR\n"); - pmc_core_send_ltr_ignore(pmcdev, 3); - return 0; } diff --git a/drivers/platform/x86/intel/pmc/cnp.c b/drivers/platform/x86/intel/pmc/cnp.c index 420aaa1d7c769..98b36651201a0 100644 --- a/drivers/platform/x86/intel/pmc/cnp.c +++ b/drivers/platform/x86/intel/pmc/cnp.c @@ -204,21 +204,35 @@ const struct pmc_reg_map cnp_reg_map = { .etr3_offset = ETR3_OFFSET, }; +void cnl_suspend(struct pmc_dev *pmcdev) +{ + /* + * Due to a hardware limitation, the GBE LTR blocks PC10 + * when a cable is attached. To unblock PC10 during suspend, + * tell the PMC to ignore it. + */ + pmc_core_send_ltr_ignore(pmcdev, 3, 1); +} + +int cnl_resume(struct pmc_dev *pmcdev) +{ + pmc_core_send_ltr_ignore(pmcdev, 3, 0); + + return pmc_core_resume_common(pmcdev); +} + int cnp_core_init(struct pmc_dev *pmcdev) { struct pmc *pmc = pmcdev->pmcs[PMC_IDX_MAIN]; int ret; + pmcdev->suspend = cnl_suspend; + pmcdev->resume = cnl_resume; + pmc->map = &cnp_reg_map; ret = get_primary_reg_base(pmc); if (ret) return ret; - /* Due to a hardware limitation, the GBE LTR blocks PC10 - * when a cable is attached. Tell the PMC to ignore it. - */ - dev_dbg(&pmcdev->pdev->dev, "ignoring GBE LTR\n"); - pmc_core_send_ltr_ignore(pmcdev, 3); - return 0; } diff --git a/drivers/platform/x86/intel/pmc/core.c b/drivers/platform/x86/intel/pmc/core.c index 84c175b9721a0..022afb97d531c 100644 --- a/drivers/platform/x86/intel/pmc/core.c +++ b/drivers/platform/x86/intel/pmc/core.c @@ -460,7 +460,7 @@ static int pmc_core_pll_show(struct seq_file *s, void *unused) } DEFINE_SHOW_ATTRIBUTE(pmc_core_pll); -int pmc_core_send_ltr_ignore(struct pmc_dev *pmcdev, u32 value) +int pmc_core_send_ltr_ignore(struct pmc_dev *pmcdev, u32 value, int ignore) { struct pmc *pmc; const struct pmc_reg_map *map; @@ -472,7 +472,7 @@ int pmc_core_send_ltr_ignore(struct pmc_dev *pmcdev, u32 value) * is based on the contiguous indexes from ltr_show output. * pmc index and ltr index needs to be calculated from it. */ - for (pmc_index = 0; pmc_index < ARRAY_SIZE(pmcdev->pmcs) && ltr_index > 0; pmc_index++) { + for (pmc_index = 0; pmc_index < ARRAY_SIZE(pmcdev->pmcs) && ltr_index >= 0; pmc_index++) { pmc = pmcdev->pmcs[pmc_index]; if (!pmc) @@ -498,7 +498,10 @@ int pmc_core_send_ltr_ignore(struct pmc_dev *pmcdev, u32 value) mutex_lock(&pmcdev->lock); reg = pmc_core_reg_read(pmc, map->ltr_ignore_offset); - reg |= BIT(ltr_index); + if (ignore) + reg |= BIT(ltr_index); + else + reg &= ~BIT(ltr_index); pmc_core_reg_write(pmc, map->ltr_ignore_offset, reg); mutex_unlock(&pmcdev->lock); @@ -521,7 +524,7 @@ static ssize_t pmc_core_ltr_ignore_write(struct file *file, if (err) return err; - err = pmc_core_send_ltr_ignore(pmcdev, value); + err = pmc_core_send_ltr_ignore(pmcdev, value, 1); return err == 0 ? count : err; } @@ -1279,6 +1282,9 @@ static __maybe_unused int pmc_core_suspend(struct device *dev) struct pmc_dev *pmcdev = dev_get_drvdata(dev); struct pmc *pmc = pmcdev->pmcs[PMC_IDX_MAIN]; + if (pmcdev->suspend) + pmcdev->suspend(pmcdev); + /* Check if the syspend will actually use S0ix */ if (pm_suspend_via_firmware()) return 0; diff --git a/drivers/platform/x86/intel/pmc/core.h b/drivers/platform/x86/intel/pmc/core.h index 0729f593c6a75..b66dacbfb94bf 100644 --- a/drivers/platform/x86/intel/pmc/core.h +++ b/drivers/platform/x86/intel/pmc/core.h @@ -363,6 +363,7 @@ struct pmc { * @s0ix_counter: S0ix residency (step adjusted) * @num_lpm_modes: Count of enabled modes * @lpm_en_modes: Array of enabled modes from lowest to highest priority + * @suspend: Function to perform platform specific suspend * @resume: Function to perform platform specific resume * * pmc_dev contains info about power management controller device. @@ -379,6 +380,7 @@ struct pmc_dev { u64 s0ix_counter; int num_lpm_modes; int lpm_en_modes[LPM_MAX_NUM_MODES]; + void (*suspend)(struct pmc_dev *pmcdev); int (*resume)(struct pmc_dev *pmcdev); bool has_die_c6; @@ -486,7 +488,7 @@ extern const struct pmc_bit_map *mtl_ioem_lpm_maps[]; extern const struct pmc_reg_map mtl_ioem_reg_map; extern void pmc_core_get_tgl_lpm_reqs(struct platform_device *pdev); -extern int pmc_core_send_ltr_ignore(struct pmc_dev *pmcdev, u32 value); +int pmc_core_send_ltr_ignore(struct pmc_dev *pmcdev, u32 value, int ignore); int pmc_core_resume_common(struct pmc_dev *pmcdev); int get_primary_reg_base(struct pmc *pmc); @@ -500,6 +502,9 @@ int tgl_core_init(struct pmc_dev *pmcdev); int adl_core_init(struct pmc_dev *pmcdev); int mtl_core_init(struct pmc_dev *pmcdev); +void cnl_suspend(struct pmc_dev *pmcdev); +int cnl_resume(struct pmc_dev *pmcdev); + #define pmc_for_each_mode(i, mode, pmcdev) \ for (i = 0, mode = pmcdev->lpm_en_modes[i]; \ i < pmcdev->num_lpm_modes; \ diff --git a/drivers/platform/x86/intel/pmc/mtl.c b/drivers/platform/x86/intel/pmc/mtl.c index 2204bc666980e..504e3e273c323 100644 --- a/drivers/platform/x86/intel/pmc/mtl.c +++ b/drivers/platform/x86/intel/pmc/mtl.c @@ -979,6 +979,8 @@ static void mtl_d3_fixup(void) static int mtl_resume(struct pmc_dev *pmcdev) { mtl_d3_fixup(); + pmc_core_send_ltr_ignore(pmcdev, 3, 0); + return pmc_core_resume_common(pmcdev); } @@ -989,6 +991,7 @@ int mtl_core_init(struct pmc_dev *pmcdev) mtl_d3_fixup(); + pmcdev->suspend = cnl_suspend; pmcdev->resume = mtl_resume; pmcdev->regmap_list = mtl_pmc_info_list; @@ -1002,11 +1005,5 @@ int mtl_core_init(struct pmc_dev *pmcdev) return ret; } - /* Due to a hardware limitation, the GBE LTR blocks PC10 - * when a cable is attached. Tell the PMC to ignore it. - */ - dev_dbg(&pmcdev->pdev->dev, "ignoring GBE LTR\n"); - pmc_core_send_ltr_ignore(pmcdev, 3); - return 0; } diff --git a/drivers/platform/x86/intel/pmc/tgl.c b/drivers/platform/x86/intel/pmc/tgl.c index 2449940102db4..e88d3d00c8539 100644 --- a/drivers/platform/x86/intel/pmc/tgl.c +++ b/drivers/platform/x86/intel/pmc/tgl.c @@ -259,16 +259,15 @@ int tgl_core_init(struct pmc_dev *pmcdev) int ret; pmc->map = &tgl_reg_map; + + pmcdev->suspend = cnl_suspend; + pmcdev->resume = cnl_resume; + ret = get_primary_reg_base(pmc); if (ret) return ret; pmc_core_get_tgl_lpm_reqs(pmcdev->pdev); - /* Due to a hardware limitation, the GBE LTR blocks PC10 - * when a cable is attached. Tell the PMC to ignore it. - */ - dev_dbg(&pmcdev->pdev->dev, "ignoring GBE LTR\n"); - pmc_core_send_ltr_ignore(pmcdev, 3); return 0; } diff --git a/drivers/platform/x86/intel/telemetry/core.c b/drivers/platform/x86/intel/telemetry/core.c index fdf55b5d69480..e4be40f73eebf 100644 --- a/drivers/platform/x86/intel/telemetry/core.c +++ b/drivers/platform/x86/intel/telemetry/core.c @@ -102,7 +102,7 @@ static const struct telemetry_core_ops telm_defpltops = { /** * telemetry_update_events() - Update telemetry Configuration * @pss_evtconfig: PSS related config. No change if num_evts = 0. - * @pss_evtconfig: IOSS related config. No change if num_evts = 0. + * @ioss_evtconfig: IOSS related config. No change if num_evts = 0. * * This API updates the IOSS & PSS Telemetry configuration. Old config * is overwritten. Call telemetry_reset_events when logging is over @@ -176,7 +176,7 @@ EXPORT_SYMBOL_GPL(telemetry_reset_events); /** * telemetry_get_eventconfig() - Returns the pss and ioss events enabled * @pss_evtconfig: Pointer to PSS related configuration. - * @pss_evtconfig: Pointer to IOSS related configuration. + * @ioss_evtconfig: Pointer to IOSS related configuration. * @pss_len: Number of u32 elements allocated for pss_evtconfig array * @ioss_len: Number of u32 elements allocated for ioss_evtconfig array * diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 41584427dc323..a46fc417cb200 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -9816,6 +9816,7 @@ static const struct tpacpi_quirk battery_quirk_table[] __initconst = { * Individual addressing is broken on models that expose the * primary battery as BAT1. */ + TPACPI_Q_LNV('8', 'F', true), /* Thinkpad X120e */ TPACPI_Q_LNV('J', '7', true), /* B5400 */ TPACPI_Q_LNV('J', 'I', true), /* Thinkpad 11e */ TPACPI_Q_LNV3('R', '0', 'B', true), /* Thinkpad 11e gen 3 */ diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c index 317c907304149..d75a0ae9cd0c5 100644 --- a/drivers/platform/x86/wmi.c +++ b/drivers/platform/x86/wmi.c @@ -1285,6 +1285,11 @@ static int parse_wdg(struct device *wmi_bus_dev, struct acpi_device *device) if (debug_dump_wdg) wmi_dump_wdg(&gblock[i]); + if (!gblock[i].instance_count) { + dev_info(wmi_bus_dev, FW_INFO "%pUL has zero instances\n", &gblock[i].guid); + continue; + } + if (guid_already_parsed_for_legacy(device, &gblock[i].guid)) continue; diff --git a/drivers/pmdomain/amlogic/meson-ee-pwrc.c b/drivers/pmdomain/amlogic/meson-ee-pwrc.c index cfb796d40d9d2..0dd71cd814c52 100644 --- a/drivers/pmdomain/amlogic/meson-ee-pwrc.c +++ b/drivers/pmdomain/amlogic/meson-ee-pwrc.c @@ -228,7 +228,7 @@ static struct meson_ee_pwrc_mem_domain sm1_pwrc_mem_audio[] = { static struct meson_ee_pwrc_mem_domain g12a_pwrc_mem_nna[] = { { G12A_HHI_NANOQ_MEM_PD_REG0, GENMASK(31, 0) }, - { G12A_HHI_NANOQ_MEM_PD_REG1, GENMASK(23, 0) }, + { G12A_HHI_NANOQ_MEM_PD_REG1, GENMASK(31, 0) }, }; #define VPU_PD(__name, __top_pd, __mem, __is_pwr_off, __resets, __clks) \ diff --git a/drivers/pmdomain/bcm/bcm2835-power.c b/drivers/pmdomain/bcm/bcm2835-power.c index 1a179d4e011cf..d2f0233cb6206 100644 --- a/drivers/pmdomain/bcm/bcm2835-power.c +++ b/drivers/pmdomain/bcm/bcm2835-power.c @@ -175,7 +175,7 @@ static int bcm2835_asb_control(struct bcm2835_power *power, u32 reg, bool enable } writel(PM_PASSWORD | val, base + reg); - while (readl(base + reg) & ASB_ACK) { + while (!!(readl(base + reg) & ASB_ACK) == enable) { cpu_relax(); if (ktime_get_ns() - start >= 1000) return -ETIMEDOUT; diff --git a/drivers/pmdomain/imx/gpc.c b/drivers/pmdomain/imx/gpc.c index 90a8b2c0676ff..419ed15cc10c4 100644 --- a/drivers/pmdomain/imx/gpc.c +++ b/drivers/pmdomain/imx/gpc.c @@ -498,6 +498,7 @@ static int imx_gpc_probe(struct platform_device *pdev) pd_pdev->dev.parent = &pdev->dev; pd_pdev->dev.of_node = np; + pd_pdev->dev.fwnode = of_fwnode_handle(np); ret = platform_device_add(pd_pdev); if (ret) { diff --git a/drivers/powercap/dtpm_cpu.c b/drivers/powercap/dtpm_cpu.c index 2ff7717530bf8..9193c3b8edebe 100644 --- a/drivers/powercap/dtpm_cpu.c +++ b/drivers/powercap/dtpm_cpu.c @@ -24,7 +24,6 @@ #include #include #include -#include struct dtpm_cpu { struct dtpm dtpm; @@ -104,8 +103,7 @@ static u64 get_pd_power_uw(struct dtpm *dtpm) if (pd->table[i].frequency < freq) continue; - return scale_pd_power_uw(pd_mask, pd->table[i].power * - MICROWATT_PER_MILLIWATT); + return scale_pd_power_uw(pd_mask, pd->table[i].power); } return 0; @@ -122,11 +120,9 @@ static int update_pd_power_uw(struct dtpm *dtpm) nr_cpus = cpumask_weight(&cpus); dtpm->power_min = em->table[0].power; - dtpm->power_min *= MICROWATT_PER_MILLIWATT; dtpm->power_min *= nr_cpus; dtpm->power_max = em->table[em->nr_perf_states - 1].power; - dtpm->power_max *= MICROWATT_PER_MILLIWATT; dtpm->power_max *= nr_cpus; return 0; @@ -144,6 +140,8 @@ static void pd_release(struct dtpm *dtpm) if (policy) { for_each_cpu(dtpm_cpu->cpu, policy->related_cpus) per_cpu(dtpm_per_cpu, dtpm_cpu->cpu) = NULL; + + cpufreq_cpu_put(policy); } kfree(dtpm_cpu); @@ -195,12 +193,16 @@ static int __dtpm_cpu_setup(int cpu, struct dtpm *parent) return 0; pd = em_cpu_get(cpu); - if (!pd || em_is_artificial(pd)) - return -EINVAL; + if (!pd || em_is_artificial(pd)) { + ret = -EINVAL; + goto release_policy; + } dtpm_cpu = kzalloc(sizeof(*dtpm_cpu), GFP_KERNEL); - if (!dtpm_cpu) - return -ENOMEM; + if (!dtpm_cpu) { + ret = -ENOMEM; + goto release_policy; + } dtpm_init(&dtpm_cpu->dtpm, &dtpm_ops); dtpm_cpu->cpu = cpu; @@ -220,6 +222,7 @@ static int __dtpm_cpu_setup(int cpu, struct dtpm *parent) if (ret) goto out_dtpm_unregister; + cpufreq_cpu_put(policy); return 0; out_dtpm_unregister: @@ -231,6 +234,8 @@ static int __dtpm_cpu_setup(int cpu, struct dtpm *parent) per_cpu(dtpm_per_cpu, cpu) = NULL; kfree(dtpm_cpu); +release_policy: + cpufreq_cpu_put(policy); return ret; } diff --git a/drivers/powercap/dtpm_devfreq.c b/drivers/powercap/dtpm_devfreq.c index 91276761a31d9..612c3b59dd5be 100644 --- a/drivers/powercap/dtpm_devfreq.c +++ b/drivers/powercap/dtpm_devfreq.c @@ -39,10 +39,8 @@ static int update_pd_power_uw(struct dtpm *dtpm) struct em_perf_domain *pd = em_pd_get(dev); dtpm->power_min = pd->table[0].power; - dtpm->power_min *= MICROWATT_PER_MILLIWATT; dtpm->power_max = pd->table[pd->nr_perf_states - 1].power; - dtpm->power_max *= MICROWATT_PER_MILLIWATT; return 0; } @@ -54,13 +52,10 @@ static u64 set_pd_power_limit(struct dtpm *dtpm, u64 power_limit) struct device *dev = devfreq->dev.parent; struct em_perf_domain *pd = em_pd_get(dev); unsigned long freq; - u64 power; int i; for (i = 0; i < pd->nr_perf_states; i++) { - - power = pd->table[i].power * MICROWATT_PER_MILLIWATT; - if (power > power_limit) + if (pd->table[i].power > power_limit) break; } @@ -68,7 +63,7 @@ static u64 set_pd_power_limit(struct dtpm *dtpm, u64 power_limit) dev_pm_qos_update_request(&dtpm_devfreq->qos_req, freq); - power_limit = pd->table[i - 1].power * MICROWATT_PER_MILLIWATT; + power_limit = pd->table[i - 1].power; return power_limit; } @@ -110,7 +105,7 @@ static u64 get_pd_power_uw(struct dtpm *dtpm) if (pd->table[i].frequency < freq) continue; - power = pd->table[i].power * MICROWATT_PER_MILLIWATT; + power = pd->table[i].power; power *= status.busy_time; power >>= 10; diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c index 40a2cc649c79b..2feed036c1cd4 100644 --- a/drivers/powercap/intel_rapl_common.c +++ b/drivers/powercap/intel_rapl_common.c @@ -892,7 +892,7 @@ static int rapl_write_pl_data(struct rapl_domain *rd, int pl, return -EINVAL; if (rd->rpl[pl].locked) { - pr_warn("%s:%s:%s locked by BIOS\n", rd->rp->name, rd->name, pl_names[pl]); + pr_debug("%s:%s:%s locked by BIOS\n", rd->rp->name, rd->name, pl_names[pl]); return -EACCES; } diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c index 362bf756e6b78..5a3a4cc0bec82 100644 --- a/drivers/ptp/ptp_chardev.c +++ b/drivers/ptp/ptp_chardev.c @@ -490,7 +490,8 @@ ssize_t ptp_read(struct posix_clock *pc, for (i = 0; i < cnt; i++) { event[i] = queue->buf[queue->head]; - queue->head = (queue->head + 1) % PTP_MAX_TIMESTAMPS; + /* Paired with READ_ONCE() in queue_cnt() */ + WRITE_ONCE(queue->head, (queue->head + 1) % PTP_MAX_TIMESTAMPS); } spin_unlock_irqrestore(&queue->lock, flags); diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c index 80f74e38c2da4..9a50bfb56453c 100644 --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -56,10 +56,11 @@ static void enqueue_external_timestamp(struct timestamp_event_queue *queue, dst->t.sec = seconds; dst->t.nsec = remainder; + /* Both WRITE_ONCE() are paired with READ_ONCE() in queue_cnt() */ if (!queue_free(queue)) - queue->head = (queue->head + 1) % PTP_MAX_TIMESTAMPS; + WRITE_ONCE(queue->head, (queue->head + 1) % PTP_MAX_TIMESTAMPS); - queue->tail = (queue->tail + 1) % PTP_MAX_TIMESTAMPS; + WRITE_ONCE(queue->tail, (queue->tail + 1) % PTP_MAX_TIMESTAMPS); spin_unlock_irqrestore(&queue->lock, flags); } diff --git a/drivers/ptp/ptp_private.h b/drivers/ptp/ptp_private.h index 75f58fc468a71..b8d4f61f14be4 100644 --- a/drivers/ptp/ptp_private.h +++ b/drivers/ptp/ptp_private.h @@ -76,9 +76,13 @@ struct ptp_vclock { * that a writer might concurrently increment the tail does not * matter, since the queue remains nonempty nonetheless. */ -static inline int queue_cnt(struct timestamp_event_queue *q) +static inline int queue_cnt(const struct timestamp_event_queue *q) { - int cnt = q->tail - q->head; + /* + * Paired with WRITE_ONCE() in enqueue_external_timestamp(), + * ptp_read(), extts_fifo_show(). + */ + int cnt = READ_ONCE(q->tail) - READ_ONCE(q->head); return cnt < 0 ? PTP_MAX_TIMESTAMPS + cnt : cnt; } diff --git a/drivers/ptp/ptp_sysfs.c b/drivers/ptp/ptp_sysfs.c index 6e4d5456a8851..34ea5c16123a1 100644 --- a/drivers/ptp/ptp_sysfs.c +++ b/drivers/ptp/ptp_sysfs.c @@ -90,7 +90,8 @@ static ssize_t extts_fifo_show(struct device *dev, qcnt = queue_cnt(queue); if (qcnt) { event = queue->buf[queue->head]; - queue->head = (queue->head + 1) % PTP_MAX_TIMESTAMPS; + /* Paired with READ_ONCE() in queue_cnt() */ + WRITE_ONCE(queue->head, (queue->head + 1) % PTP_MAX_TIMESTAMPS); } spin_unlock_irqrestore(&queue->lock, flags); diff --git a/drivers/reset/core.c b/drivers/reset/core.c index f0a076e94118f..92cc13ef3e566 100644 --- a/drivers/reset/core.c +++ b/drivers/reset/core.c @@ -807,6 +807,9 @@ static void __reset_control_put_internal(struct reset_control *rstc) { lockdep_assert_held(&reset_list_mutex); + if (IS_ERR_OR_NULL(rstc)) + return; + kref_put(&rstc->refcnt, __reset_control_release); } @@ -1017,11 +1020,8 @@ EXPORT_SYMBOL_GPL(reset_control_put); void reset_control_bulk_put(int num_rstcs, struct reset_control_bulk_data *rstcs) { mutex_lock(&reset_list_mutex); - while (num_rstcs--) { - if (IS_ERR_OR_NULL(rstcs[num_rstcs].rstc)) - continue; + while (num_rstcs--) __reset_control_put_internal(rstcs[num_rstcs].rstc); - } mutex_unlock(&reset_list_mutex); } EXPORT_SYMBOL_GPL(reset_control_bulk_put); diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index 215597f73be4f..5b11ee9234573 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -674,18 +674,20 @@ static void dasd_profile_start(struct dasd_block *block, * we count each request only once. */ device = cqr->startdev; - if (device->profile.data) { - counter = 1; /* request is not yet queued on the start device */ - list_for_each(l, &device->ccw_queue) - if (++counter >= 31) - break; - } + if (!device->profile.data) + return; + + spin_lock(get_ccwdev_lock(device->cdev)); + counter = 1; /* request is not yet queued on the start device */ + list_for_each(l, &device->ccw_queue) + if (++counter >= 31) + break; + spin_unlock(get_ccwdev_lock(device->cdev)); + spin_lock(&device->profile.lock); - if (device->profile.data) { - device->profile.data->dasd_io_nr_req[counter]++; - if (rq_data_dir(req) == READ) - device->profile.data->dasd_read_nr_req[counter]++; - } + device->profile.data->dasd_io_nr_req[counter]++; + if (rq_data_dir(req) == READ) + device->profile.data->dasd_read_nr_req[counter]++; spin_unlock(&device->profile.lock); } diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index d09e08b71cfba..d6ad437883fad 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -1022,6 +1022,10 @@ EXPORT_SYMBOL(ap_driver_unregister); void ap_bus_force_rescan(void) { + /* Only trigger AP bus scans after the initial scan is done */ + if (atomic64_read(&ap_scan_bus_count) <= 0) + return; + /* processing a asynchronous bus rescan */ del_timer(&ap_config_timer); queue_work(system_long_wq, &ap_scan_work); diff --git a/drivers/s390/net/Kconfig b/drivers/s390/net/Kconfig index 4902d45e929ce..c61e6427384c3 100644 --- a/drivers/s390/net/Kconfig +++ b/drivers/s390/net/Kconfig @@ -103,10 +103,11 @@ config CCWGROUP config ISM tristate "Support for ISM vPCI Adapter" depends on PCI + imply SMC default n help Select this option if you want to use the Internal Shared Memory - vPCI Adapter. + vPCI Adapter. The adapter can be used with the SMC network protocol. To compile as a module choose M. The module name is ism. If unsure, choose N. diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c index 6df7f377d2f90..81aabbfbbe2ca 100644 --- a/drivers/s390/net/ism_drv.c +++ b/drivers/s390/net/ism_drv.c @@ -30,7 +30,6 @@ static const struct pci_device_id ism_device_table[] = { MODULE_DEVICE_TABLE(pci, ism_device_table); static debug_info_t *ism_debug_info; -static const struct smcd_ops ism_ops; #define NO_CLIENT 0xff /* must be >= MAX_CLIENTS */ static struct ism_client *clients[MAX_CLIENTS]; /* use an array rather than */ @@ -289,22 +288,6 @@ static int ism_read_local_gid(struct ism_dev *ism) return ret; } -static int ism_query_rgid(struct ism_dev *ism, u64 rgid, u32 vid_valid, - u32 vid) -{ - union ism_query_rgid cmd; - - memset(&cmd, 0, sizeof(cmd)); - cmd.request.hdr.cmd = ISM_QUERY_RGID; - cmd.request.hdr.len = sizeof(cmd.request); - - cmd.request.rgid = rgid; - cmd.request.vlan_valid = vid_valid; - cmd.request.vlan_id = vid; - - return ism_cmd(ism, &cmd); -} - static void ism_free_dmb(struct ism_dev *ism, struct ism_dmb *dmb) { clear_bit(dmb->sba_idx, ism->sba_bitmap); @@ -429,23 +412,6 @@ static int ism_del_vlan_id(struct ism_dev *ism, u64 vlan_id) return ism_cmd(ism, &cmd); } -static int ism_signal_ieq(struct ism_dev *ism, u64 rgid, u32 trigger_irq, - u32 event_code, u64 info) -{ - union ism_sig_ieq cmd; - - memset(&cmd, 0, sizeof(cmd)); - cmd.request.hdr.cmd = ISM_SIGNAL_IEQ; - cmd.request.hdr.len = sizeof(cmd.request); - - cmd.request.rgid = rgid; - cmd.request.trigger_irq = trigger_irq; - cmd.request.event_code = event_code; - cmd.request.info = info; - - return ism_cmd(ism, &cmd); -} - static unsigned int max_bytes(unsigned int start, unsigned int len, unsigned int boundary) { @@ -503,14 +469,6 @@ u8 *ism_get_seid(void) } EXPORT_SYMBOL_GPL(ism_get_seid); -static u16 ism_get_chid(struct ism_dev *ism) -{ - if (!ism || !ism->pdev) - return 0; - - return to_zpci(ism->pdev)->pchid; -} - static void ism_handle_event(struct ism_dev *ism) { struct ism_event *entry; @@ -569,11 +527,6 @@ static irqreturn_t ism_handle_irq(int irq, void *data) return IRQ_HANDLED; } -static u64 ism_get_local_gid(struct ism_dev *ism) -{ - return ism->local_gid; -} - static int ism_dev_init(struct ism_dev *ism) { struct pci_dev *pdev = ism->pdev; @@ -774,6 +727,22 @@ module_exit(ism_exit); /*************************** SMC-D Implementation *****************************/ #if IS_ENABLED(CONFIG_SMC) +static int ism_query_rgid(struct ism_dev *ism, u64 rgid, u32 vid_valid, + u32 vid) +{ + union ism_query_rgid cmd; + + memset(&cmd, 0, sizeof(cmd)); + cmd.request.hdr.cmd = ISM_QUERY_RGID; + cmd.request.hdr.len = sizeof(cmd.request); + + cmd.request.rgid = rgid; + cmd.request.vlan_valid = vid_valid; + cmd.request.vlan_id = vid; + + return ism_cmd(ism, &cmd); +} + static int smcd_query_rgid(struct smcd_dev *smcd, u64 rgid, u32 vid_valid, u32 vid) { @@ -811,6 +780,23 @@ static int smcd_reset_vlan_required(struct smcd_dev *smcd) return ism_cmd_simple(smcd->priv, ISM_RESET_VLAN); } +static int ism_signal_ieq(struct ism_dev *ism, u64 rgid, u32 trigger_irq, + u32 event_code, u64 info) +{ + union ism_sig_ieq cmd; + + memset(&cmd, 0, sizeof(cmd)); + cmd.request.hdr.cmd = ISM_SIGNAL_IEQ; + cmd.request.hdr.len = sizeof(cmd.request); + + cmd.request.rgid = rgid; + cmd.request.trigger_irq = trigger_irq; + cmd.request.event_code = event_code; + cmd.request.info = info; + + return ism_cmd(ism, &cmd); +} + static int smcd_signal_ieq(struct smcd_dev *smcd, u64 rgid, u32 trigger_irq, u32 event_code, u64 info) { @@ -830,11 +816,24 @@ static int smcd_supports_v2(void) SYSTEM_EID.type[0] != '0'; } +static u64 ism_get_local_gid(struct ism_dev *ism) +{ + return ism->local_gid; +} + static u64 smcd_get_local_gid(struct smcd_dev *smcd) { return ism_get_local_gid(smcd->priv); } +static u16 ism_get_chid(struct ism_dev *ism) +{ + if (!ism || !ism->pdev) + return 0; + + return to_zpci(ism->pdev)->pchid; +} + static u16 smcd_get_chid(struct smcd_dev *smcd) { return ism_get_chid(smcd->priv); diff --git a/drivers/scsi/aacraid/aacraid.h b/drivers/scsi/aacraid/aacraid.h index 73b6ac0c01f54..7d5a155073c62 100644 --- a/drivers/scsi/aacraid/aacraid.h +++ b/drivers/scsi/aacraid/aacraid.h @@ -1678,7 +1678,6 @@ struct aac_dev u32 handle_pci_error; bool init_reset; u8 soft_reset_support; - u8 use_map_queue; }; #define aac_adapter_interrupt(dev) \ diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c index 013a9a334972e..25cee03d7f973 100644 --- a/drivers/scsi/aacraid/commsup.c +++ b/drivers/scsi/aacraid/commsup.c @@ -223,12 +223,8 @@ int aac_fib_setup(struct aac_dev * dev) struct fib *aac_fib_alloc_tag(struct aac_dev *dev, struct scsi_cmnd *scmd) { struct fib *fibptr; - u32 blk_tag; - int i; - blk_tag = blk_mq_unique_tag(scsi_cmd_to_rq(scmd)); - i = blk_mq_unique_tag_to_tag(blk_tag); - fibptr = &dev->fibs[i]; + fibptr = &dev->fibs[scsi_cmd_to_rq(scmd)->tag]; /* * Null out fields that depend on being zero at the start of * each I/O diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c index c4a36c0be527c..68f4dbcfff492 100644 --- a/drivers/scsi/aacraid/linit.c +++ b/drivers/scsi/aacraid/linit.c @@ -19,7 +19,6 @@ #include #include -#include #include #include #include @@ -505,15 +504,6 @@ static int aac_slave_configure(struct scsi_device *sdev) return 0; } -static void aac_map_queues(struct Scsi_Host *shost) -{ - struct aac_dev *aac = (struct aac_dev *)shost->hostdata; - - blk_mq_pci_map_queues(&shost->tag_set.map[HCTX_TYPE_DEFAULT], - aac->pdev, 0); - aac->use_map_queue = true; -} - /** * aac_change_queue_depth - alter queue depths * @sdev: SCSI device we are considering @@ -1498,7 +1488,6 @@ static const struct scsi_host_template aac_driver_template = { .bios_param = aac_biosparm, .shost_groups = aac_host_groups, .slave_configure = aac_slave_configure, - .map_queues = aac_map_queues, .change_queue_depth = aac_change_queue_depth, .sdev_groups = aac_dev_groups, .eh_abort_handler = aac_eh_abort, @@ -1786,8 +1775,6 @@ static int aac_probe_one(struct pci_dev *pdev, const struct pci_device_id *id) shost->max_lun = AAC_MAX_LUN; pci_set_drvdata(pdev, shost); - shost->nr_hw_queues = aac->max_msix; - shost->host_tagset = 1; error = scsi_add_host(shost, &pdev->dev); if (error) @@ -1919,7 +1906,6 @@ static void aac_remove_one(struct pci_dev *pdev) struct aac_dev *aac = (struct aac_dev *)shost->hostdata; aac_cancel_rescan_worker(aac); - aac->use_map_queue = false; scsi_remove_host(shost); __aac_shutdown(aac); diff --git a/drivers/scsi/aacraid/src.c b/drivers/scsi/aacraid/src.c index 61949f3741886..11ef58204e96f 100644 --- a/drivers/scsi/aacraid/src.c +++ b/drivers/scsi/aacraid/src.c @@ -493,10 +493,6 @@ static int aac_src_deliver_message(struct fib *fib) #endif u16 vector_no; - struct scsi_cmnd *scmd; - u32 blk_tag; - struct Scsi_Host *shost = dev->scsi_host_ptr; - struct blk_mq_queue_map *qmap; atomic_inc(&q->numpending); @@ -509,25 +505,8 @@ static int aac_src_deliver_message(struct fib *fib) if ((dev->comm_interface == AAC_COMM_MESSAGE_TYPE3) && dev->sa_firmware) vector_no = aac_get_vector(dev); - else { - if (!fib->vector_no || !fib->callback_data) { - if (shost && dev->use_map_queue) { - qmap = &shost->tag_set.map[HCTX_TYPE_DEFAULT]; - vector_no = qmap->mq_map[raw_smp_processor_id()]; - } - /* - * We hardcode the vector_no for - * reserved commands as a valid shost is - * absent during the init - */ - else - vector_no = 0; - } else { - scmd = (struct scsi_cmnd *)fib->callback_data; - blk_tag = blk_mq_unique_tag(scsi_cmd_to_rq(scmd)); - vector_no = blk_mq_unique_tag_to_hwq(blk_tag); - } - } + else + vector_no = fib->vector_no; if (native_hba) { if (fib->flags & FIB_CONTEXT_FLAG_NATIVE_HBA_TMF) { diff --git a/drivers/scsi/be2iscsi/be_main.c b/drivers/scsi/be2iscsi/be_main.c index e48f14ad6dfd8..06acb5ff609ee 100644 --- a/drivers/scsi/be2iscsi/be_main.c +++ b/drivers/scsi/be2iscsi/be_main.c @@ -2710,6 +2710,7 @@ static int beiscsi_init_wrb_handle(struct beiscsi_hba *phba) kfree(pwrb_context->pwrb_handle_base); kfree(pwrb_context->pwrb_handle_basestd); } + kfree(phwi_ctxt->be_wrbq); return -ENOMEM; } diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c index 05ddbb9bb7d8a..451a58e0fd969 100644 --- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c +++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c @@ -429,7 +429,6 @@ static int bnx2fc_rcv(struct sk_buff *skb, struct net_device *dev, struct fcoe_ctlr *ctlr; struct fcoe_rcv_info *fr; struct fcoe_percpu_s *bg; - struct sk_buff *tmp_skb; interface = container_of(ptype, struct bnx2fc_interface, fcoe_packet_type); @@ -441,11 +440,9 @@ static int bnx2fc_rcv(struct sk_buff *skb, struct net_device *dev, goto err; } - tmp_skb = skb_share_check(skb, GFP_ATOMIC); - if (!tmp_skb) - goto err; - - skb = tmp_skb; + skb = skb_share_check(skb, GFP_ATOMIC); + if (!skb) + return -1; if (unlikely(eth_hdr(skb)->h_proto != htons(ETH_P_FCOE))) { printk(KERN_ERR PFX "bnx2fc_rcv: Wrong FC type frame\n"); diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c index bbb64ee6afd7c..089186fe17915 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c @@ -4865,6 +4865,12 @@ static void debugfs_bist_init_v3_hw(struct hisi_hba *hisi_hba) hisi_hba->debugfs_bist_linkrate = SAS_LINK_RATE_1_5_GBPS; } +static void debugfs_exit_v3_hw(struct hisi_hba *hisi_hba) +{ + debugfs_remove_recursive(hisi_hba->debugfs_dir); + hisi_hba->debugfs_dir = NULL; +} + static void debugfs_init_v3_hw(struct hisi_hba *hisi_hba) { struct device *dev = hisi_hba->dev; @@ -4888,18 +4894,13 @@ static void debugfs_init_v3_hw(struct hisi_hba *hisi_hba) for (i = 0; i < hisi_sas_debugfs_dump_count; i++) { if (debugfs_alloc_v3_hw(hisi_hba, i)) { - debugfs_remove_recursive(hisi_hba->debugfs_dir); + debugfs_exit_v3_hw(hisi_hba); dev_dbg(dev, "failed to init debugfs!\n"); break; } } } -static void debugfs_exit_v3_hw(struct hisi_hba *hisi_hba) -{ - debugfs_remove_recursive(hisi_hba->debugfs_dir); -} - static int hisi_sas_v3_probe(struct pci_dev *pdev, const struct pci_device_id *id) { diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c index 470e8e6c41b62..c98346e464b48 100644 --- a/drivers/scsi/ibmvscsi/ibmvfc.c +++ b/drivers/scsi/ibmvscsi/ibmvfc.c @@ -1518,7 +1518,11 @@ static struct ibmvfc_event *ibmvfc_get_event(struct ibmvfc_queue *queue) unsigned long flags; spin_lock_irqsave(&queue->l_lock, flags); - BUG_ON(list_empty(&queue->free)); + if (list_empty(&queue->free)) { + ibmvfc_log(queue->vhost, 4, "empty event pool on queue:%ld\n", queue->hwq_id); + spin_unlock_irqrestore(&queue->l_lock, flags); + return NULL; + } evt = list_entry(queue->free.next, struct ibmvfc_event, queue_list); atomic_set(&evt->free, 0); list_del(&evt->queue_list); @@ -1947,9 +1951,15 @@ static int ibmvfc_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *cmnd) if (vhost->using_channels) { scsi_channel = hwq % vhost->scsi_scrqs.active_queues; evt = ibmvfc_get_event(&vhost->scsi_scrqs.scrqs[scsi_channel]); + if (!evt) + return SCSI_MLQUEUE_HOST_BUSY; + evt->hwq = hwq % vhost->scsi_scrqs.active_queues; - } else + } else { evt = ibmvfc_get_event(&vhost->crq); + if (!evt) + return SCSI_MLQUEUE_HOST_BUSY; + } ibmvfc_init_event(evt, ibmvfc_scsi_done, IBMVFC_CMD_FORMAT); evt->cmnd = cmnd; @@ -2037,6 +2047,11 @@ static int ibmvfc_bsg_timeout(struct bsg_job *job) vhost->aborting_passthru = 1; evt = ibmvfc_get_event(&vhost->crq); + if (!evt) { + spin_unlock_irqrestore(vhost->host->host_lock, flags); + return -ENOMEM; + } + ibmvfc_init_event(evt, ibmvfc_bsg_timeout_done, IBMVFC_MAD_FORMAT); tmf = &evt->iu.tmf; @@ -2095,6 +2110,10 @@ static int ibmvfc_bsg_plogi(struct ibmvfc_host *vhost, unsigned int port_id) goto unlock_out; evt = ibmvfc_get_event(&vhost->crq); + if (!evt) { + rc = -ENOMEM; + goto unlock_out; + } ibmvfc_init_event(evt, ibmvfc_sync_completion, IBMVFC_MAD_FORMAT); plogi = &evt->iu.plogi; memset(plogi, 0, sizeof(*plogi)); @@ -2213,6 +2232,11 @@ static int ibmvfc_bsg_request(struct bsg_job *job) } evt = ibmvfc_get_event(&vhost->crq); + if (!evt) { + spin_unlock_irqrestore(vhost->host->host_lock, flags); + rc = -ENOMEM; + goto out; + } ibmvfc_init_event(evt, ibmvfc_sync_completion, IBMVFC_MAD_FORMAT); mad = &evt->iu.passthru; @@ -2301,6 +2325,11 @@ static int ibmvfc_reset_device(struct scsi_device *sdev, int type, char *desc) else evt = ibmvfc_get_event(&vhost->crq); + if (!evt) { + spin_unlock_irqrestore(vhost->host->host_lock, flags); + return -ENOMEM; + } + ibmvfc_init_event(evt, ibmvfc_sync_completion, IBMVFC_CMD_FORMAT); tmf = ibmvfc_init_vfc_cmd(evt, sdev); iu = ibmvfc_get_fcp_iu(vhost, tmf); @@ -2504,6 +2533,8 @@ static struct ibmvfc_event *ibmvfc_init_tmf(struct ibmvfc_queue *queue, struct ibmvfc_tmf *tmf; evt = ibmvfc_get_event(queue); + if (!evt) + return NULL; ibmvfc_init_event(evt, ibmvfc_sync_completion, IBMVFC_MAD_FORMAT); tmf = &evt->iu.tmf; @@ -2560,6 +2591,11 @@ static int ibmvfc_cancel_all_mq(struct scsi_device *sdev, int type) if (found_evt && vhost->logged_in) { evt = ibmvfc_init_tmf(&queues[i], sdev, type); + if (!evt) { + spin_unlock(queues[i].q_lock); + spin_unlock_irqrestore(vhost->host->host_lock, flags); + return -ENOMEM; + } evt->sync_iu = &queues[i].cancel_rsp; ibmvfc_send_event(evt, vhost, default_timeout); list_add_tail(&evt->cancel, &cancelq); @@ -2773,6 +2809,10 @@ static int ibmvfc_abort_task_set(struct scsi_device *sdev) if (vhost->state == IBMVFC_ACTIVE) { evt = ibmvfc_get_event(&vhost->crq); + if (!evt) { + spin_unlock_irqrestore(vhost->host->host_lock, flags); + return -ENOMEM; + } ibmvfc_init_event(evt, ibmvfc_sync_completion, IBMVFC_CMD_FORMAT); tmf = ibmvfc_init_vfc_cmd(evt, sdev); iu = ibmvfc_get_fcp_iu(vhost, tmf); @@ -4031,6 +4071,12 @@ static void ibmvfc_tgt_send_prli(struct ibmvfc_target *tgt) kref_get(&tgt->kref); evt = ibmvfc_get_event(&vhost->crq); + if (!evt) { + ibmvfc_set_tgt_action(tgt, IBMVFC_TGT_ACTION_NONE); + kref_put(&tgt->kref, ibmvfc_release_tgt); + __ibmvfc_reset_host(vhost); + return; + } vhost->discovery_threads++; ibmvfc_init_event(evt, ibmvfc_tgt_prli_done, IBMVFC_MAD_FORMAT); evt->tgt = tgt; @@ -4138,6 +4184,12 @@ static void ibmvfc_tgt_send_plogi(struct ibmvfc_target *tgt) kref_get(&tgt->kref); tgt->logo_rcvd = 0; evt = ibmvfc_get_event(&vhost->crq); + if (!evt) { + ibmvfc_set_tgt_action(tgt, IBMVFC_TGT_ACTION_NONE); + kref_put(&tgt->kref, ibmvfc_release_tgt); + __ibmvfc_reset_host(vhost); + return; + } vhost->discovery_threads++; ibmvfc_set_tgt_action(tgt, IBMVFC_TGT_ACTION_INIT_WAIT); ibmvfc_init_event(evt, ibmvfc_tgt_plogi_done, IBMVFC_MAD_FORMAT); @@ -4214,6 +4266,8 @@ static struct ibmvfc_event *__ibmvfc_tgt_get_implicit_logout_evt(struct ibmvfc_t kref_get(&tgt->kref); evt = ibmvfc_get_event(&vhost->crq); + if (!evt) + return NULL; ibmvfc_init_event(evt, done, IBMVFC_MAD_FORMAT); evt->tgt = tgt; mad = &evt->iu.implicit_logout; @@ -4241,6 +4295,13 @@ static void ibmvfc_tgt_implicit_logout(struct ibmvfc_target *tgt) vhost->discovery_threads++; evt = __ibmvfc_tgt_get_implicit_logout_evt(tgt, ibmvfc_tgt_implicit_logout_done); + if (!evt) { + vhost->discovery_threads--; + ibmvfc_set_tgt_action(tgt, IBMVFC_TGT_ACTION_NONE); + kref_put(&tgt->kref, ibmvfc_release_tgt); + __ibmvfc_reset_host(vhost); + return; + } ibmvfc_set_tgt_action(tgt, IBMVFC_TGT_ACTION_INIT_WAIT); if (ibmvfc_send_event(evt, vhost, default_timeout)) { @@ -4380,6 +4441,12 @@ static void ibmvfc_tgt_move_login(struct ibmvfc_target *tgt) kref_get(&tgt->kref); evt = ibmvfc_get_event(&vhost->crq); + if (!evt) { + ibmvfc_set_tgt_action(tgt, IBMVFC_TGT_ACTION_DEL_RPORT); + kref_put(&tgt->kref, ibmvfc_release_tgt); + __ibmvfc_reset_host(vhost); + return; + } vhost->discovery_threads++; ibmvfc_set_tgt_action(tgt, IBMVFC_TGT_ACTION_INIT_WAIT); ibmvfc_init_event(evt, ibmvfc_tgt_move_login_done, IBMVFC_MAD_FORMAT); @@ -4546,6 +4613,14 @@ static void ibmvfc_adisc_timeout(struct timer_list *t) vhost->abort_threads++; kref_get(&tgt->kref); evt = ibmvfc_get_event(&vhost->crq); + if (!evt) { + tgt_err(tgt, "Failed to get cancel event for ADISC.\n"); + vhost->abort_threads--; + kref_put(&tgt->kref, ibmvfc_release_tgt); + __ibmvfc_reset_host(vhost); + spin_unlock_irqrestore(vhost->host->host_lock, flags); + return; + } ibmvfc_init_event(evt, ibmvfc_tgt_adisc_cancel_done, IBMVFC_MAD_FORMAT); evt->tgt = tgt; @@ -4596,6 +4671,12 @@ static void ibmvfc_tgt_adisc(struct ibmvfc_target *tgt) kref_get(&tgt->kref); evt = ibmvfc_get_event(&vhost->crq); + if (!evt) { + ibmvfc_set_tgt_action(tgt, IBMVFC_TGT_ACTION_NONE); + kref_put(&tgt->kref, ibmvfc_release_tgt); + __ibmvfc_reset_host(vhost); + return; + } vhost->discovery_threads++; ibmvfc_init_event(evt, ibmvfc_tgt_adisc_done, IBMVFC_MAD_FORMAT); evt->tgt = tgt; @@ -4699,6 +4780,12 @@ static void ibmvfc_tgt_query_target(struct ibmvfc_target *tgt) kref_get(&tgt->kref); evt = ibmvfc_get_event(&vhost->crq); + if (!evt) { + ibmvfc_set_tgt_action(tgt, IBMVFC_TGT_ACTION_NONE); + kref_put(&tgt->kref, ibmvfc_release_tgt); + __ibmvfc_reset_host(vhost); + return; + } vhost->discovery_threads++; evt->tgt = tgt; ibmvfc_init_event(evt, ibmvfc_tgt_query_target_done, IBMVFC_MAD_FORMAT); @@ -4871,6 +4958,13 @@ static void ibmvfc_discover_targets(struct ibmvfc_host *vhost) { struct ibmvfc_discover_targets *mad; struct ibmvfc_event *evt = ibmvfc_get_event(&vhost->crq); + int level = IBMVFC_DEFAULT_LOG_LEVEL; + + if (!evt) { + ibmvfc_log(vhost, level, "Discover Targets failed: no available events\n"); + ibmvfc_hard_reset_host(vhost); + return; + } ibmvfc_init_event(evt, ibmvfc_discover_targets_done, IBMVFC_MAD_FORMAT); mad = &evt->iu.discover_targets; @@ -4948,8 +5042,15 @@ static void ibmvfc_channel_setup(struct ibmvfc_host *vhost) struct ibmvfc_scsi_channels *scrqs = &vhost->scsi_scrqs; unsigned int num_channels = min(vhost->client_scsi_channels, vhost->max_vios_scsi_channels); + int level = IBMVFC_DEFAULT_LOG_LEVEL; int i; + if (!evt) { + ibmvfc_log(vhost, level, "Channel Setup failed: no available events\n"); + ibmvfc_hard_reset_host(vhost); + return; + } + memset(setup_buf, 0, sizeof(*setup_buf)); if (num_channels == 0) setup_buf->flags = cpu_to_be32(IBMVFC_CANCEL_CHANNELS); @@ -5011,6 +5112,13 @@ static void ibmvfc_channel_enquiry(struct ibmvfc_host *vhost) { struct ibmvfc_channel_enquiry *mad; struct ibmvfc_event *evt = ibmvfc_get_event(&vhost->crq); + int level = IBMVFC_DEFAULT_LOG_LEVEL; + + if (!evt) { + ibmvfc_log(vhost, level, "Channel Enquiry failed: no available events\n"); + ibmvfc_hard_reset_host(vhost); + return; + } ibmvfc_init_event(evt, ibmvfc_channel_enquiry_done, IBMVFC_MAD_FORMAT); mad = &evt->iu.channel_enquiry; @@ -5133,6 +5241,12 @@ static void ibmvfc_npiv_login(struct ibmvfc_host *vhost) struct ibmvfc_npiv_login_mad *mad; struct ibmvfc_event *evt = ibmvfc_get_event(&vhost->crq); + if (!evt) { + ibmvfc_dbg(vhost, "NPIV Login failed: no available events\n"); + ibmvfc_hard_reset_host(vhost); + return; + } + ibmvfc_gather_partition_info(vhost); ibmvfc_set_login_info(vhost); ibmvfc_init_event(evt, ibmvfc_npiv_login_done, IBMVFC_MAD_FORMAT); @@ -5197,6 +5311,12 @@ static void ibmvfc_npiv_logout(struct ibmvfc_host *vhost) struct ibmvfc_event *evt; evt = ibmvfc_get_event(&vhost->crq); + if (!evt) { + ibmvfc_dbg(vhost, "NPIV Logout failed: no available events\n"); + ibmvfc_hard_reset_host(vhost); + return; + } + ibmvfc_init_event(evt, ibmvfc_npiv_logout_done, IBMVFC_MAD_FORMAT); mad = &evt->iu.npiv_logout; diff --git a/drivers/scsi/libfc/fc_lport.c b/drivers/scsi/libfc/fc_lport.c index 9c02c9523c4d4..ab06e9aeb613e 100644 --- a/drivers/scsi/libfc/fc_lport.c +++ b/drivers/scsi/libfc/fc_lport.c @@ -241,6 +241,12 @@ static void fc_lport_ptp_setup(struct fc_lport *lport, } mutex_lock(&lport->disc.disc_mutex); lport->ptp_rdata = fc_rport_create(lport, remote_fid); + if (!lport->ptp_rdata) { + printk(KERN_WARNING "libfc: Failed to setup lport 0x%x\n", + lport->port_id); + mutex_unlock(&lport->disc.disc_mutex); + return; + } kref_get(&lport->ptp_rdata->kref); lport->ptp_rdata->ids.port_name = remote_wwpn; lport->ptp_rdata->ids.node_name = remote_wwnn; diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index e1aa667dae662..3d4f13da1ae87 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -263,13 +263,13 @@ u32 megasas_readl(struct megasas_instance *instance, * Fusion registers could intermittently return all zeroes. * This behavior is transient in nature and subsequent reads will * return valid value. As a workaround in driver, retry readl for - * upto three times until a non-zero value is read. + * up to thirty times until a non-zero value is read. */ if (instance->adapter_type == AERO_SERIES) { do { ret_val = readl(addr); i++; - } while (ret_val == 0 && i < 3); + } while (ret_val == 0 && i < 30); return ret_val; } else { return readl(addr); diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 61a32bf00747e..a75f670bf5519 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -223,8 +223,8 @@ _base_readl_ext_retry(const void __iomem *addr) for (i = 0 ; i < 30 ; i++) { ret_val = readl(addr); - if (ret_val == 0) - continue; + if (ret_val != 0) + break; } return ret_val; diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index dcae09a37d498..c45eef743c457 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -1836,8 +1836,16 @@ static void qla2x00_abort_srb(struct qla_qpair *qp, srb_t *sp, const int res, } spin_lock_irqsave(qp->qp_lock_ptr, *flags); - if (ret_cmd && blk_mq_request_started(scsi_cmd_to_rq(cmd))) - sp->done(sp, res); + switch (sp->type) { + case SRB_SCSI_CMD: + if (ret_cmd && blk_mq_request_started(scsi_cmd_to_rq(cmd))) + sp->done(sp, res); + break; + default: + if (ret_cmd) + sp->done(sp, res); + break; + } } else { sp->done(sp, res); } diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index c67cdcdc3ba86..1223d34c04da3 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -1152,6 +1152,7 @@ static enum scsi_disposition scsi_send_eh_cmnd(struct scsi_cmnd *scmd, scsi_log_send(scmd); scmd->submitter = SUBMITTED_BY_SCSI_ERROR_HANDLER; + scmd->flags |= SCMD_LAST; /* * Lock sdev->state_mutex to avoid that scsi_device_quiesce() can @@ -2459,6 +2460,7 @@ scsi_ioctl_reset(struct scsi_device *dev, int __user *arg) scsi_init_command(dev, scmd); scmd->submitter = SUBMITTED_BY_SCSI_RESET_IOCTL; + scmd->flags |= SCMD_LAST; memset(&scmd->sdb, 0, sizeof(scmd->sdb)); scmd->cmd_len = 0; diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index d84fcd7a226dd..b24b722a6b286 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -1642,24 +1642,21 @@ static unsigned int sd_check_events(struct gendisk *disk, unsigned int clearing) return disk_changed ? DISK_EVENT_MEDIA_CHANGE : 0; } -static int sd_sync_cache(struct scsi_disk *sdkp, struct scsi_sense_hdr *sshdr) +static int sd_sync_cache(struct scsi_disk *sdkp) { int retries, res; struct scsi_device *sdp = sdkp->device; const int timeout = sdp->request_queue->rq_timeout * SD_FLUSH_TIMEOUT_MULTIPLIER; - struct scsi_sense_hdr my_sshdr; + struct scsi_sense_hdr sshdr; const struct scsi_exec_args exec_args = { .req_flags = BLK_MQ_REQ_PM, - /* caller might not be interested in sense, but we need it */ - .sshdr = sshdr ? : &my_sshdr, + .sshdr = &sshdr, }; if (!scsi_device_online(sdp)) return -ENODEV; - sshdr = exec_args.sshdr; - for (retries = 3; retries > 0; --retries) { unsigned char cmd[16] = { 0 }; @@ -1684,15 +1681,23 @@ static int sd_sync_cache(struct scsi_disk *sdkp, struct scsi_sense_hdr *sshdr) return res; if (scsi_status_is_check_condition(res) && - scsi_sense_valid(sshdr)) { - sd_print_sense_hdr(sdkp, sshdr); + scsi_sense_valid(&sshdr)) { + sd_print_sense_hdr(sdkp, &sshdr); /* we need to evaluate the error return */ - if (sshdr->asc == 0x3a || /* medium not present */ - sshdr->asc == 0x20 || /* invalid command */ - (sshdr->asc == 0x74 && sshdr->ascq == 0x71)) /* drive is password locked */ + if (sshdr.asc == 0x3a || /* medium not present */ + sshdr.asc == 0x20 || /* invalid command */ + (sshdr.asc == 0x74 && sshdr.ascq == 0x71)) /* drive is password locked */ /* this is no error here */ return 0; + /* + * This drive doesn't support sync and there's not much + * we can do because this is called during shutdown + * or suspend so just return success so those operations + * can proceed. + */ + if (sshdr.sense_key == ILLEGAL_REQUEST) + return 0; } switch (host_byte(res)) { @@ -3851,7 +3856,7 @@ static void sd_shutdown(struct device *dev) if (sdkp->WCE && sdkp->media_present) { sd_printk(KERN_NOTICE, sdkp, "Synchronizing SCSI cache\n"); - sd_sync_cache(sdkp, NULL); + sd_sync_cache(sdkp); } if ((system_state != SYSTEM_RESTART && @@ -3872,7 +3877,6 @@ static inline bool sd_do_start_stop(struct scsi_device *sdev, bool runtime) static int sd_suspend_common(struct device *dev, bool runtime) { struct scsi_disk *sdkp = dev_get_drvdata(dev); - struct scsi_sense_hdr sshdr; int ret = 0; if (!sdkp) /* E.g.: runtime suspend following sd_remove() */ @@ -3881,24 +3885,13 @@ static int sd_suspend_common(struct device *dev, bool runtime) if (sdkp->WCE && sdkp->media_present) { if (!sdkp->device->silence_suspend) sd_printk(KERN_NOTICE, sdkp, "Synchronizing SCSI cache\n"); - ret = sd_sync_cache(sdkp, &sshdr); - - if (ret) { - /* ignore OFFLINE device */ - if (ret == -ENODEV) - return 0; - - if (!scsi_sense_valid(&sshdr) || - sshdr.sense_key != ILLEGAL_REQUEST) - return ret; + ret = sd_sync_cache(sdkp); + /* ignore OFFLINE device */ + if (ret == -ENODEV) + return 0; - /* - * sshdr.sense_key == ILLEGAL_REQUEST means this drive - * doesn't support sync. There's not much to do and - * suspend shouldn't fail. - */ - ret = 0; - } + if (ret) + return ret; } if (sd_do_start_stop(sdkp->device, runtime)) { @@ -3957,8 +3950,15 @@ static int sd_resume(struct device *dev, bool runtime) static int sd_resume_system(struct device *dev) { - if (pm_runtime_suspended(dev)) + if (pm_runtime_suspended(dev)) { + struct scsi_disk *sdkp = dev_get_drvdata(dev); + struct scsi_device *sdp = sdkp ? sdkp->device : NULL; + + if (sdp && sdp->force_runtime_start_on_system_start) + pm_request_resume(dev); + return 0; + } return sd_resume(dev, false); } diff --git a/drivers/soc/qcom/pmic_glink_altmode.c b/drivers/soc/qcom/pmic_glink_altmode.c index 974c14d1e0bfc..6f8b2f7ae3cc1 100644 --- a/drivers/soc/qcom/pmic_glink_altmode.c +++ b/drivers/soc/qcom/pmic_glink_altmode.c @@ -444,6 +444,7 @@ static int pmic_glink_altmode_probe(struct auxiliary_device *adev, ret = fwnode_property_read_u32(fwnode, "reg", &port); if (ret < 0) { dev_err(dev, "missing reg property of %pOFn\n", fwnode); + fwnode_handle_put(fwnode); return ret; } @@ -454,6 +455,7 @@ static int pmic_glink_altmode_probe(struct auxiliary_device *adev, if (altmode->ports[port].altmode) { dev_err(dev, "multiple connector definition for port %u\n", port); + fwnode_handle_put(fwnode); return -EINVAL; } @@ -468,45 +470,59 @@ static int pmic_glink_altmode_probe(struct auxiliary_device *adev, alt_port->bridge.type = DRM_MODE_CONNECTOR_DisplayPort; ret = devm_drm_bridge_add(dev, &alt_port->bridge); - if (ret) + if (ret) { + fwnode_handle_put(fwnode); return ret; + } alt_port->dp_alt.svid = USB_TYPEC_DP_SID; alt_port->dp_alt.mode = USB_TYPEC_DP_MODE; alt_port->dp_alt.active = 1; alt_port->typec_mux = fwnode_typec_mux_get(fwnode); - if (IS_ERR(alt_port->typec_mux)) + if (IS_ERR(alt_port->typec_mux)) { + fwnode_handle_put(fwnode); return dev_err_probe(dev, PTR_ERR(alt_port->typec_mux), "failed to acquire mode-switch for port: %d\n", port); + } ret = devm_add_action_or_reset(dev, pmic_glink_altmode_put_mux, alt_port->typec_mux); - if (ret) + if (ret) { + fwnode_handle_put(fwnode); return ret; + } alt_port->typec_retimer = fwnode_typec_retimer_get(fwnode); - if (IS_ERR(alt_port->typec_retimer)) + if (IS_ERR(alt_port->typec_retimer)) { + fwnode_handle_put(fwnode); return dev_err_probe(dev, PTR_ERR(alt_port->typec_retimer), "failed to acquire retimer-switch for port: %d\n", port); + } ret = devm_add_action_or_reset(dev, pmic_glink_altmode_put_retimer, alt_port->typec_retimer); - if (ret) + if (ret) { + fwnode_handle_put(fwnode); return ret; + } alt_port->typec_switch = fwnode_typec_switch_get(fwnode); - if (IS_ERR(alt_port->typec_switch)) + if (IS_ERR(alt_port->typec_switch)) { + fwnode_handle_put(fwnode); return dev_err_probe(dev, PTR_ERR(alt_port->typec_switch), "failed to acquire orientation-switch for port: %d\n", port); + } ret = devm_add_action_or_reset(dev, pmic_glink_altmode_put_switch, alt_port->typec_switch); - if (ret) + if (ret) { + fwnode_handle_put(fwnode); return ret; + } } altmode->client = devm_pmic_glink_register_client(dev, diff --git a/drivers/soundwire/dmi-quirks.c b/drivers/soundwire/dmi-quirks.c index 2a1096dab63d3..9ebdd0cd0b1cf 100644 --- a/drivers/soundwire/dmi-quirks.c +++ b/drivers/soundwire/dmi-quirks.c @@ -141,7 +141,7 @@ static const struct dmi_system_id adr_remap_quirk_table[] = { { .matches = { DMI_MATCH(DMI_SYS_VENDOR, "HP"), - DMI_MATCH(DMI_PRODUCT_NAME, "OMEN by HP Gaming Laptop 16-k0xxx"), + DMI_MATCH(DMI_PRODUCT_NAME, "OMEN by HP Gaming Laptop 16"), }, .driver_data = (void *)hp_omen_16, }, diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c index d77a8a0d42c8d..68d54887992d9 100644 --- a/drivers/soundwire/stream.c +++ b/drivers/soundwire/stream.c @@ -742,14 +742,15 @@ static int sdw_bank_switch(struct sdw_bus *bus, int m_rt_count) * sdw_ml_sync_bank_switch: Multilink register bank switch * * @bus: SDW bus instance + * @multi_link: whether this is a multi-link stream with hardware-based sync * * Caller function should free the buffers on error */ -static int sdw_ml_sync_bank_switch(struct sdw_bus *bus) +static int sdw_ml_sync_bank_switch(struct sdw_bus *bus, bool multi_link) { unsigned long time_left; - if (!bus->multi_link) + if (!multi_link) return 0; /* Wait for completion of transfer */ @@ -847,7 +848,7 @@ static int do_bank_switch(struct sdw_stream_runtime *stream) bus->bank_switch_timeout = DEFAULT_BANK_SWITCH_TIMEOUT; /* Check if bank switch was successful */ - ret = sdw_ml_sync_bank_switch(bus); + ret = sdw_ml_sync_bank_switch(bus, multi_link); if (ret < 0) { dev_err(bus->dev, "multi link bank switch failed: %d\n", ret); diff --git a/drivers/spi/spi-atmel.c b/drivers/spi/spi-atmel.c index 6aa8adbe4170c..e073d54873b1f 100644 --- a/drivers/spi/spi-atmel.c +++ b/drivers/spi/spi-atmel.c @@ -22,6 +22,7 @@ #include #include #include +#include #include /* SPI register offsets */ @@ -279,6 +280,7 @@ struct atmel_spi { bool keep_cs; u32 fifo_size; + bool last_polarity; u8 native_cs_free; u8 native_cs_for_gpio; }; @@ -291,6 +293,22 @@ struct atmel_spi_device { #define SPI_MAX_DMA_XFER 65535 /* true for both PDC and DMA */ #define INVALID_DMA_ADDRESS 0xffffffff +/* + * This frequency can be anything supported by the controller, but to avoid + * unnecessary delay, the highest possible frequency is chosen. + * + * This frequency is the highest possible which is not interfering with other + * chip select registers (see Note for Serial Clock Bit Rate configuration in + * Atmel-11121F-ATARM-SAMA5D3-Series-Datasheet_02-Feb-16, page 1283) + */ +#define DUMMY_MSG_FREQUENCY 0x02 +/* + * 8 bits is the minimum data the controller is capable of sending. + * + * This message can be anything as it should not be treated by any SPI device. + */ +#define DUMMY_MSG 0xAA + /* * Version 2 of the SPI controller has * - CR.LASTXFER @@ -304,6 +322,43 @@ static bool atmel_spi_is_v2(struct atmel_spi *as) return as->caps.is_spi2; } +/* + * Send a dummy message. + * + * This is sometimes needed when using a CS GPIO to force clock transition when + * switching between devices with different polarities. + */ +static void atmel_spi_send_dummy(struct atmel_spi *as, struct spi_device *spi, int chip_select) +{ + u32 status; + u32 csr; + + /* + * Set a clock frequency to allow sending message on SPI bus. + * The frequency here can be anything, but is needed for + * the controller to send the data. + */ + csr = spi_readl(as, CSR0 + 4 * chip_select); + csr = SPI_BFINS(SCBR, DUMMY_MSG_FREQUENCY, csr); + spi_writel(as, CSR0 + 4 * chip_select, csr); + + /* + * Read all data coming from SPI bus, needed to be able to send + * the message. + */ + spi_readl(as, RDR); + while (spi_readl(as, SR) & SPI_BIT(RDRF)) { + spi_readl(as, RDR); + cpu_relax(); + } + + spi_writel(as, TDR, DUMMY_MSG); + + readl_poll_timeout_atomic(as->regs + SPI_SR, status, + (status & SPI_BIT(TXEMPTY)), 1, 1000); +} + + /* * Earlier SPI controllers (e.g. on at91rm9200) have a design bug whereby * they assume that spi slave device state will not change on deselect, so @@ -320,11 +375,17 @@ static bool atmel_spi_is_v2(struct atmel_spi *as) * Master on Chip Select 0.") No workaround exists for that ... so for * nCS0 on that chip, we (a) don't use the GPIO, (b) can't support CS_HIGH, * and (c) will trigger that first erratum in some cases. + * + * When changing the clock polarity, the SPI controller waits for the next + * transmission to enforce the default clock state. This may be an issue when + * using a GPIO as Chip Select: the clock level is applied only when the first + * packet is sent, once the CS has already been asserted. The workaround is to + * avoid this by sending a first (dummy) message before toggling the CS state. */ - static void cs_activate(struct atmel_spi *as, struct spi_device *spi) { struct atmel_spi_device *asd = spi->controller_state; + bool new_polarity; int chip_select; u32 mr; @@ -353,6 +414,25 @@ static void cs_activate(struct atmel_spi *as, struct spi_device *spi) } mr = spi_readl(as, MR); + + /* + * Ensures the clock polarity is valid before we actually + * assert the CS to avoid spurious clock edges to be + * processed by the spi devices. + */ + if (spi_get_csgpiod(spi, 0)) { + new_polarity = (asd->csr & SPI_BIT(CPOL)) != 0; + if (new_polarity != as->last_polarity) { + /* + * Need to disable the GPIO before sending the dummy + * message because it is already set by the spi core. + */ + gpiod_set_value_cansleep(spi_get_csgpiod(spi, 0), 0); + atmel_spi_send_dummy(as, spi, chip_select); + as->last_polarity = new_polarity; + gpiod_set_value_cansleep(spi_get_csgpiod(spi, 0), 1); + } + } } else { u32 cpol = (spi->mode & SPI_CPOL) ? SPI_BIT(CPOL) : 0; int i; @@ -1336,12 +1416,10 @@ static int atmel_spi_one_transfer(struct spi_controller *host, } dma_timeout = msecs_to_jiffies(spi_controller_xfer_timeout(host, xfer)); - ret_timeout = wait_for_completion_interruptible_timeout(&as->xfer_completion, - dma_timeout); - if (ret_timeout <= 0) { - dev_err(&spi->dev, "spi transfer %s\n", - !ret_timeout ? "timeout" : "canceled"); - as->done_status = ret_timeout < 0 ? ret_timeout : -EIO; + ret_timeout = wait_for_completion_timeout(&as->xfer_completion, dma_timeout); + if (!ret_timeout) { + dev_err(&spi->dev, "spi transfer timeout\n"); + as->done_status = -EIO; } if (as->done_status) diff --git a/drivers/spi/spi-cadence.c b/drivers/spi/spi-cadence.c index 12c940ba074ab..bd96d8b546cdb 100644 --- a/drivers/spi/spi-cadence.c +++ b/drivers/spi/spi-cadence.c @@ -451,7 +451,6 @@ static int cdns_transfer_one(struct spi_controller *ctlr, udelay(10); cdns_spi_process_fifo(xspi, xspi->tx_fifo_depth, 0); - spi_transfer_delay_exec(transfer); cdns_spi_write(xspi, CDNS_SPI_IER, CDNS_SPI_IXR_DEFAULT); return transfer->len; diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c index 498e35c8db2c1..272bc871a848b 100644 --- a/drivers/spi/spi-imx.c +++ b/drivers/spi/spi-imx.c @@ -659,11 +659,18 @@ static int mx51_ecspi_prepare_transfer(struct spi_imx_data *spi_imx, ctrl |= (spi_imx->target_burst * 8 - 1) << MX51_ECSPI_CTRL_BL_OFFSET; else { - if (spi_imx->count >= 512) - ctrl |= 0xFFF << MX51_ECSPI_CTRL_BL_OFFSET; - else - ctrl |= (spi_imx->count * spi_imx->bits_per_word - 1) + if (spi_imx->usedma) { + ctrl |= (spi_imx->bits_per_word * + spi_imx_bytes_per_word(spi_imx->bits_per_word) - 1) << MX51_ECSPI_CTRL_BL_OFFSET; + } else { + if (spi_imx->count >= MX51_ECSPI_CTRL_MAX_BURST) + ctrl |= (MX51_ECSPI_CTRL_MAX_BURST - 1) + << MX51_ECSPI_CTRL_BL_OFFSET; + else + ctrl |= (spi_imx->count * spi_imx->bits_per_word - 1) + << MX51_ECSPI_CTRL_BL_OFFSET; + } } /* set clock speed */ diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 8d6304cb061ec..399e81d37b3ba 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -3323,33 +3323,52 @@ void spi_unregister_controller(struct spi_controller *ctlr) } EXPORT_SYMBOL_GPL(spi_unregister_controller); +static inline int __spi_check_suspended(const struct spi_controller *ctlr) +{ + return ctlr->flags & SPI_CONTROLLER_SUSPENDED ? -ESHUTDOWN : 0; +} + +static inline void __spi_mark_suspended(struct spi_controller *ctlr) +{ + mutex_lock(&ctlr->bus_lock_mutex); + ctlr->flags |= SPI_CONTROLLER_SUSPENDED; + mutex_unlock(&ctlr->bus_lock_mutex); +} + +static inline void __spi_mark_resumed(struct spi_controller *ctlr) +{ + mutex_lock(&ctlr->bus_lock_mutex); + ctlr->flags &= ~SPI_CONTROLLER_SUSPENDED; + mutex_unlock(&ctlr->bus_lock_mutex); +} + int spi_controller_suspend(struct spi_controller *ctlr) { - int ret; + int ret = 0; /* Basically no-ops for non-queued controllers */ - if (!ctlr->queued) - return 0; - - ret = spi_stop_queue(ctlr); - if (ret) - dev_err(&ctlr->dev, "queue stop failed\n"); + if (ctlr->queued) { + ret = spi_stop_queue(ctlr); + if (ret) + dev_err(&ctlr->dev, "queue stop failed\n"); + } + __spi_mark_suspended(ctlr); return ret; } EXPORT_SYMBOL_GPL(spi_controller_suspend); int spi_controller_resume(struct spi_controller *ctlr) { - int ret; - - if (!ctlr->queued) - return 0; + int ret = 0; - ret = spi_start_queue(ctlr); - if (ret) - dev_err(&ctlr->dev, "queue restart failed\n"); + __spi_mark_resumed(ctlr); + if (ctlr->queued) { + ret = spi_start_queue(ctlr); + if (ret) + dev_err(&ctlr->dev, "queue restart failed\n"); + } return ret; } EXPORT_SYMBOL_GPL(spi_controller_resume); @@ -4153,8 +4172,7 @@ static void __spi_transfer_message_noqueue(struct spi_controller *ctlr, struct s ctlr->cur_msg = msg; ret = __spi_pump_transfer_message(ctlr, msg, was_busy); if (ret) - goto out; - + dev_err(&ctlr->dev, "noqueue transfer failed\n"); ctlr->cur_msg = NULL; ctlr->fallback = false; @@ -4170,7 +4188,6 @@ static void __spi_transfer_message_noqueue(struct spi_controller *ctlr, struct s spi_idle_runtime_pm(ctlr); } -out: mutex_unlock(&ctlr->io_mutex); } @@ -4193,6 +4210,11 @@ static int __spi_sync(struct spi_device *spi, struct spi_message *message) int status; struct spi_controller *ctlr = spi->controller; + if (__spi_check_suspended(ctlr)) { + dev_warn_once(&spi->dev, "Attempted to sync while suspend\n"); + return -ESHUTDOWN; + } + status = __spi_validate(spi, message); if (status != 0) return status; diff --git a/drivers/tee/optee/device.c b/drivers/tee/optee/device.c index 64f0e047c23d2..4b10921276942 100644 --- a/drivers/tee/optee/device.c +++ b/drivers/tee/optee/device.c @@ -60,7 +60,16 @@ static void optee_release_device(struct device *dev) kfree(optee_device); } -static int optee_register_device(const uuid_t *device_uuid) +static ssize_t need_supplicant_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + return 0; +} + +static DEVICE_ATTR_RO(need_supplicant); + +static int optee_register_device(const uuid_t *device_uuid, u32 func) { struct tee_client_device *optee_device = NULL; int rc; @@ -83,6 +92,10 @@ static int optee_register_device(const uuid_t *device_uuid) put_device(&optee_device->dev); } + if (func == PTA_CMD_GET_DEVICES_SUPP) + device_create_file(&optee_device->dev, + &dev_attr_need_supplicant); + return rc; } @@ -142,7 +155,7 @@ static int __optee_enumerate_devices(u32 func) num_devices = shm_size / sizeof(uuid_t); for (idx = 0; idx < num_devices; idx++) { - rc = optee_register_device(&device_uuid[idx]); + rc = optee_register_device(&device_uuid[idx], func); if (rc) goto out_shm; } diff --git a/drivers/thermal/intel/intel_powerclamp.c b/drivers/thermal/intel/intel_powerclamp.c index 36243a3972fd7..5ac5cb60bae67 100644 --- a/drivers/thermal/intel/intel_powerclamp.c +++ b/drivers/thermal/intel/intel_powerclamp.c @@ -256,7 +256,7 @@ static int max_idle_set(const char *arg, const struct kernel_param *kp) static const struct kernel_param_ops max_idle_ops = { .set = max_idle_set, - .get = param_get_int, + .get = param_get_byte, }; module_param_cb(max_idle, &max_idle_ops, &max_idle, 0644); diff --git a/drivers/thunderbolt/debugfs.c b/drivers/thunderbolt/debugfs.c index c9ddd49138d82..e324cd8997193 100644 --- a/drivers/thunderbolt/debugfs.c +++ b/drivers/thunderbolt/debugfs.c @@ -959,7 +959,7 @@ static void margining_port_remove(struct tb_port *port) snprintf(dir_name, sizeof(dir_name), "port%d", port->port); parent = debugfs_lookup(dir_name, port->sw->debugfs_dir); if (parent) - debugfs_remove_recursive(debugfs_lookup("margining", parent)); + debugfs_lookup_and_remove("margining", parent); kfree(port->usb4->margining); port->usb4->margining = NULL; diff --git a/drivers/thunderbolt/quirks.c b/drivers/thunderbolt/quirks.c index 488138a28ae13..e6bfa63b40aee 100644 --- a/drivers/thunderbolt/quirks.c +++ b/drivers/thunderbolt/quirks.c @@ -31,6 +31,9 @@ static void quirk_usb3_maximum_bandwidth(struct tb_switch *sw) { struct tb_port *port; + if (tb_switch_is_icm(sw)) + return; + tb_switch_for_each_port(sw, port) { if (!tb_port_is_usb3_down(port)) continue; diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index bd5815f8f23bd..509b99af5087b 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -1082,7 +1082,7 @@ int tb_port_lane_bonding_enable(struct tb_port *port) * Only set bonding if the link was not already bonded. This * avoids the lane adapter to re-enter bonding state. */ - if (width == TB_LINK_WIDTH_SINGLE) { + if (width == TB_LINK_WIDTH_SINGLE && !tb_is_upstream_port(port)) { ret = tb_port_set_lane_bonding(port, true); if (ret) goto err_lane1; diff --git a/drivers/tty/hvc/hvc_xen.c b/drivers/tty/hvc/hvc_xen.c index 98764e740c078..34c01874f45be 100644 --- a/drivers/tty/hvc/hvc_xen.c +++ b/drivers/tty/hvc/hvc_xen.c @@ -377,18 +377,21 @@ void xen_console_resume(void) #ifdef CONFIG_HVC_XEN_FRONTEND static void xencons_disconnect_backend(struct xencons_info *info) { - if (info->irq > 0) - unbind_from_irqhandler(info->irq, NULL); - info->irq = 0; + if (info->hvc != NULL) + hvc_remove(info->hvc); + info->hvc = NULL; + if (info->irq > 0) { + evtchn_put(info->evtchn); + info->irq = 0; + info->evtchn = 0; + } + /* evtchn_put() will also close it so this is only an error path */ if (info->evtchn > 0) xenbus_free_evtchn(info->xbdev, info->evtchn); info->evtchn = 0; if (info->gntref > 0) gnttab_free_grant_references(info->gntref); info->gntref = 0; - if (info->hvc != NULL) - hvc_remove(info->hvc); - info->hvc = NULL; } static void xencons_free(struct xencons_info *info) @@ -433,7 +436,7 @@ static int xencons_connect_backend(struct xenbus_device *dev, if (ret) return ret; info->evtchn = evtchn; - irq = bind_interdomain_evtchn_to_irq_lateeoi(dev, evtchn); + irq = bind_evtchn_to_irq_lateeoi(evtchn); if (irq < 0) return irq; info->irq = irq; @@ -553,10 +556,23 @@ static void xencons_backend_changed(struct xenbus_device *dev, if (dev->state == XenbusStateClosed) break; fallthrough; /* Missed the backend's CLOSING state */ - case XenbusStateClosing: + case XenbusStateClosing: { + struct xencons_info *info = dev_get_drvdata(&dev->dev);; + + /* + * Don't tear down the evtchn and grant ref before the other + * end has disconnected, but do stop userspace from trying + * to use the device before we allow the backend to close. + */ + if (info->hvc) { + hvc_remove(info->hvc); + info->hvc = NULL; + } + xenbus_frontend_closed(dev); break; } + } } static const struct xenbus_device_id xencons_ids[] = { @@ -588,7 +604,7 @@ static int __init xen_hvc_init(void) ops = &dom0_hvc_ops; r = xen_initial_domain_console_init(); if (r < 0) - return r; + goto register_fe; info = vtermno_to_xencons(HVC_COOKIE); } else { ops = &domU_hvc_ops; @@ -597,7 +613,7 @@ static int __init xen_hvc_init(void) else r = xen_pv_console_init(); if (r < 0) - return r; + goto register_fe; info = vtermno_to_xencons(HVC_COOKIE); info->irq = bind_evtchn_to_irq_lateeoi(info->evtchn); @@ -616,12 +632,13 @@ static int __init xen_hvc_init(void) list_del(&info->list); spin_unlock_irqrestore(&xencons_lock, flags); if (info->irq) - unbind_from_irqhandler(info->irq, NULL); + evtchn_put(info->evtchn); kfree(info); return r; } r = 0; + register_fe: #ifdef CONFIG_HVC_XEN_FRONTEND r = xenbus_register_frontend(&xencons_driver); #endif diff --git a/drivers/tty/serial/8250/8250_dw.c b/drivers/tty/serial/8250/8250_dw.c index f4cafca1a7dad..a1f2259cc9a98 100644 --- a/drivers/tty/serial/8250/8250_dw.c +++ b/drivers/tty/serial/8250/8250_dw.c @@ -798,6 +798,7 @@ static const struct acpi_device_id dw8250_acpi_match[] = { { "INT33C5", (kernel_ulong_t)&dw8250_dw_apb }, { "INT3434", (kernel_ulong_t)&dw8250_dw_apb }, { "INT3435", (kernel_ulong_t)&dw8250_dw_apb }, + { "INTC10EE", (kernel_ulong_t)&dw8250_dw_apb }, { }, }; MODULE_DEVICE_TABLE(acpi, dw8250_acpi_match); diff --git a/drivers/tty/serial/8250/8250_early.c b/drivers/tty/serial/8250/8250_early.c index 9837a27739fdf..e3f482fd3de48 100644 --- a/drivers/tty/serial/8250/8250_early.c +++ b/drivers/tty/serial/8250/8250_early.c @@ -189,5 +189,6 @@ static int __init early_omap8250_setup(struct earlycon_device *device, OF_EARLYCON_DECLARE(omap8250, "ti,omap2-uart", early_omap8250_setup); OF_EARLYCON_DECLARE(omap8250, "ti,omap3-uart", early_omap8250_setup); OF_EARLYCON_DECLARE(omap8250, "ti,omap4-uart", early_omap8250_setup); +OF_EARLYCON_DECLARE(omap8250, "ti,am654-uart", early_omap8250_setup); #endif diff --git a/drivers/tty/serial/8250/8250_omap.c b/drivers/tty/serial/8250/8250_omap.c index ca972fd377256..1122f37fe744e 100644 --- a/drivers/tty/serial/8250/8250_omap.c +++ b/drivers/tty/serial/8250/8250_omap.c @@ -914,7 +914,7 @@ static void __dma_rx_do_complete(struct uart_8250_port *p) if (priv->habit & UART_HAS_RHR_IT_DIS) { reg = serial_in(p, UART_OMAP_IER2); reg &= ~UART_OMAP_IER2_RHR_IT_DIS; - serial_out(p, UART_OMAP_IER2, UART_OMAP_IER2_RHR_IT_DIS); + serial_out(p, UART_OMAP_IER2, reg); } dmaengine_tx_status(rxchan, cookie, &state); @@ -1060,7 +1060,7 @@ static int omap_8250_rx_dma(struct uart_8250_port *p) if (priv->habit & UART_HAS_RHR_IT_DIS) { reg = serial_in(p, UART_OMAP_IER2); reg |= UART_OMAP_IER2_RHR_IT_DIS; - serial_out(p, UART_OMAP_IER2, UART_OMAP_IER2_RHR_IT_DIS); + serial_out(p, UART_OMAP_IER2, reg); } dma_async_issue_pending(dma->rxchan); @@ -1282,10 +1282,12 @@ static int omap_8250_dma_handle_irq(struct uart_port *port) status = serial_port_in(port, UART_LSR); - if (priv->habit & UART_HAS_EFR2) - am654_8250_handle_rx_dma(up, iir, status); - else - status = omap_8250_handle_rx_dma(up, iir, status); + if ((iir & 0x3f) != UART_IIR_THRI) { + if (priv->habit & UART_HAS_EFR2) + am654_8250_handle_rx_dma(up, iir, status); + else + status = omap_8250_handle_rx_dma(up, iir, status); + } serial8250_modem_status(up); if (status & UART_LSR_THRE && up->dma->tx_err) { diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c index 3dc9b0fcab1c6..cd3913b933c76 100644 --- a/drivers/tty/serial/amba-pl011.c +++ b/drivers/tty/serial/amba-pl011.c @@ -218,17 +218,18 @@ static struct vendor_data vendor_st = { /* Deals with DMA transactions */ -struct pl011_sgbuf { - struct scatterlist sg; - char *buf; +struct pl011_dmabuf { + dma_addr_t dma; + size_t len; + char *buf; }; struct pl011_dmarx_data { struct dma_chan *chan; struct completion complete; bool use_buf_b; - struct pl011_sgbuf sgbuf_a; - struct pl011_sgbuf sgbuf_b; + struct pl011_dmabuf dbuf_a; + struct pl011_dmabuf dbuf_b; dma_cookie_t cookie; bool running; struct timer_list timer; @@ -241,7 +242,8 @@ struct pl011_dmarx_data { struct pl011_dmatx_data { struct dma_chan *chan; - struct scatterlist sg; + dma_addr_t dma; + size_t len; char *buf; bool queued; }; @@ -366,32 +368,24 @@ static int pl011_fifo_to_tty(struct uart_amba_port *uap) #define PL011_DMA_BUFFER_SIZE PAGE_SIZE -static int pl011_sgbuf_init(struct dma_chan *chan, struct pl011_sgbuf *sg, +static int pl011_dmabuf_init(struct dma_chan *chan, struct pl011_dmabuf *db, enum dma_data_direction dir) { - dma_addr_t dma_addr; - - sg->buf = dma_alloc_coherent(chan->device->dev, - PL011_DMA_BUFFER_SIZE, &dma_addr, GFP_KERNEL); - if (!sg->buf) + db->buf = dma_alloc_coherent(chan->device->dev, PL011_DMA_BUFFER_SIZE, + &db->dma, GFP_KERNEL); + if (!db->buf) return -ENOMEM; - - sg_init_table(&sg->sg, 1); - sg_set_page(&sg->sg, phys_to_page(dma_addr), - PL011_DMA_BUFFER_SIZE, offset_in_page(dma_addr)); - sg_dma_address(&sg->sg) = dma_addr; - sg_dma_len(&sg->sg) = PL011_DMA_BUFFER_SIZE; + db->len = PL011_DMA_BUFFER_SIZE; return 0; } -static void pl011_sgbuf_free(struct dma_chan *chan, struct pl011_sgbuf *sg, +static void pl011_dmabuf_free(struct dma_chan *chan, struct pl011_dmabuf *db, enum dma_data_direction dir) { - if (sg->buf) { + if (db->buf) { dma_free_coherent(chan->device->dev, - PL011_DMA_BUFFER_SIZE, sg->buf, - sg_dma_address(&sg->sg)); + PL011_DMA_BUFFER_SIZE, db->buf, db->dma); } } @@ -552,8 +546,8 @@ static void pl011_dma_tx_callback(void *data) spin_lock_irqsave(&uap->port.lock, flags); if (uap->dmatx.queued) - dma_unmap_sg(dmatx->chan->device->dev, &dmatx->sg, 1, - DMA_TO_DEVICE); + dma_unmap_single(dmatx->chan->device->dev, dmatx->dma, + dmatx->len, DMA_TO_DEVICE); dmacr = uap->dmacr; uap->dmacr = dmacr & ~UART011_TXDMAE; @@ -639,18 +633,19 @@ static int pl011_dma_tx_refill(struct uart_amba_port *uap) memcpy(&dmatx->buf[first], &xmit->buf[0], second); } - dmatx->sg.length = count; - - if (dma_map_sg(dma_dev->dev, &dmatx->sg, 1, DMA_TO_DEVICE) != 1) { + dmatx->len = count; + dmatx->dma = dma_map_single(dma_dev->dev, dmatx->buf, count, + DMA_TO_DEVICE); + if (dmatx->dma == DMA_MAPPING_ERROR) { uap->dmatx.queued = false; dev_dbg(uap->port.dev, "unable to map TX DMA\n"); return -EBUSY; } - desc = dmaengine_prep_slave_sg(chan, &dmatx->sg, 1, DMA_MEM_TO_DEV, + desc = dmaengine_prep_slave_single(chan, dmatx->dma, dmatx->len, DMA_MEM_TO_DEV, DMA_PREP_INTERRUPT | DMA_CTRL_ACK); if (!desc) { - dma_unmap_sg(dma_dev->dev, &dmatx->sg, 1, DMA_TO_DEVICE); + dma_unmap_single(dma_dev->dev, dmatx->dma, dmatx->len, DMA_TO_DEVICE); uap->dmatx.queued = false; /* * If DMA cannot be used right now, we complete this @@ -813,8 +808,8 @@ __acquires(&uap->port.lock) dmaengine_terminate_async(uap->dmatx.chan); if (uap->dmatx.queued) { - dma_unmap_sg(uap->dmatx.chan->device->dev, &uap->dmatx.sg, 1, - DMA_TO_DEVICE); + dma_unmap_single(uap->dmatx.chan->device->dev, uap->dmatx.dma, + uap->dmatx.len, DMA_TO_DEVICE); uap->dmatx.queued = false; uap->dmacr &= ~UART011_TXDMAE; pl011_write(uap->dmacr, uap, REG_DMACR); @@ -828,15 +823,15 @@ static int pl011_dma_rx_trigger_dma(struct uart_amba_port *uap) struct dma_chan *rxchan = uap->dmarx.chan; struct pl011_dmarx_data *dmarx = &uap->dmarx; struct dma_async_tx_descriptor *desc; - struct pl011_sgbuf *sgbuf; + struct pl011_dmabuf *dbuf; if (!rxchan) return -EIO; /* Start the RX DMA job */ - sgbuf = uap->dmarx.use_buf_b ? - &uap->dmarx.sgbuf_b : &uap->dmarx.sgbuf_a; - desc = dmaengine_prep_slave_sg(rxchan, &sgbuf->sg, 1, + dbuf = uap->dmarx.use_buf_b ? + &uap->dmarx.dbuf_b : &uap->dmarx.dbuf_a; + desc = dmaengine_prep_slave_single(rxchan, dbuf->dma, dbuf->len, DMA_DEV_TO_MEM, DMA_PREP_INTERRUPT | DMA_CTRL_ACK); /* @@ -876,8 +871,8 @@ static void pl011_dma_rx_chars(struct uart_amba_port *uap, bool readfifo) { struct tty_port *port = &uap->port.state->port; - struct pl011_sgbuf *sgbuf = use_buf_b ? - &uap->dmarx.sgbuf_b : &uap->dmarx.sgbuf_a; + struct pl011_dmabuf *dbuf = use_buf_b ? + &uap->dmarx.dbuf_b : &uap->dmarx.dbuf_a; int dma_count = 0; u32 fifotaken = 0; /* only used for vdbg() */ @@ -886,7 +881,7 @@ static void pl011_dma_rx_chars(struct uart_amba_port *uap, if (uap->dmarx.poll_rate) { /* The data can be taken by polling */ - dmataken = sgbuf->sg.length - dmarx->last_residue; + dmataken = dbuf->len - dmarx->last_residue; /* Recalculate the pending size */ if (pending >= dmataken) pending -= dmataken; @@ -900,7 +895,7 @@ static void pl011_dma_rx_chars(struct uart_amba_port *uap, * Note that tty_insert_flip_buf() tries to take as many chars * as it can. */ - dma_count = tty_insert_flip_string(port, sgbuf->buf + dmataken, + dma_count = tty_insert_flip_string(port, dbuf->buf + dmataken, pending); uap->port.icount.rx += dma_count; @@ -911,7 +906,7 @@ static void pl011_dma_rx_chars(struct uart_amba_port *uap, /* Reset the last_residue for Rx DMA poll */ if (uap->dmarx.poll_rate) - dmarx->last_residue = sgbuf->sg.length; + dmarx->last_residue = dbuf->len; /* * Only continue with trying to read the FIFO if all DMA chars have @@ -946,8 +941,8 @@ static void pl011_dma_rx_irq(struct uart_amba_port *uap) { struct pl011_dmarx_data *dmarx = &uap->dmarx; struct dma_chan *rxchan = dmarx->chan; - struct pl011_sgbuf *sgbuf = dmarx->use_buf_b ? - &dmarx->sgbuf_b : &dmarx->sgbuf_a; + struct pl011_dmabuf *dbuf = dmarx->use_buf_b ? + &dmarx->dbuf_b : &dmarx->dbuf_a; size_t pending; struct dma_tx_state state; enum dma_status dmastat; @@ -969,7 +964,7 @@ static void pl011_dma_rx_irq(struct uart_amba_port *uap) pl011_write(uap->dmacr, uap, REG_DMACR); uap->dmarx.running = false; - pending = sgbuf->sg.length - state.residue; + pending = dbuf->len - state.residue; BUG_ON(pending > PL011_DMA_BUFFER_SIZE); /* Then we terminate the transfer - we now know our residue */ dmaengine_terminate_all(rxchan); @@ -996,8 +991,8 @@ static void pl011_dma_rx_callback(void *data) struct pl011_dmarx_data *dmarx = &uap->dmarx; struct dma_chan *rxchan = dmarx->chan; bool lastbuf = dmarx->use_buf_b; - struct pl011_sgbuf *sgbuf = dmarx->use_buf_b ? - &dmarx->sgbuf_b : &dmarx->sgbuf_a; + struct pl011_dmabuf *dbuf = dmarx->use_buf_b ? + &dmarx->dbuf_b : &dmarx->dbuf_a; size_t pending; struct dma_tx_state state; int ret; @@ -1015,7 +1010,7 @@ static void pl011_dma_rx_callback(void *data) * the DMA irq handler. So we check the residue here. */ rxchan->device->device_tx_status(rxchan, dmarx->cookie, &state); - pending = sgbuf->sg.length - state.residue; + pending = dbuf->len - state.residue; BUG_ON(pending > PL011_DMA_BUFFER_SIZE); /* Then we terminate the transfer - we now know our residue */ dmaengine_terminate_all(rxchan); @@ -1067,16 +1062,16 @@ static void pl011_dma_rx_poll(struct timer_list *t) unsigned long flags; unsigned int dmataken = 0; unsigned int size = 0; - struct pl011_sgbuf *sgbuf; + struct pl011_dmabuf *dbuf; int dma_count; struct dma_tx_state state; - sgbuf = dmarx->use_buf_b ? &uap->dmarx.sgbuf_b : &uap->dmarx.sgbuf_a; + dbuf = dmarx->use_buf_b ? &uap->dmarx.dbuf_b : &uap->dmarx.dbuf_a; rxchan->device->device_tx_status(rxchan, dmarx->cookie, &state); if (likely(state.residue < dmarx->last_residue)) { - dmataken = sgbuf->sg.length - dmarx->last_residue; + dmataken = dbuf->len - dmarx->last_residue; size = dmarx->last_residue - state.residue; - dma_count = tty_insert_flip_string(port, sgbuf->buf + dmataken, + dma_count = tty_insert_flip_string(port, dbuf->buf + dmataken, size); if (dma_count == size) dmarx->last_residue = state.residue; @@ -1123,7 +1118,7 @@ static void pl011_dma_startup(struct uart_amba_port *uap) return; } - sg_init_one(&uap->dmatx.sg, uap->dmatx.buf, PL011_DMA_BUFFER_SIZE); + uap->dmatx.len = PL011_DMA_BUFFER_SIZE; /* The DMA buffer is now the FIFO the TTY subsystem can use */ uap->port.fifosize = PL011_DMA_BUFFER_SIZE; @@ -1133,7 +1128,7 @@ static void pl011_dma_startup(struct uart_amba_port *uap) goto skip_rx; /* Allocate and map DMA RX buffers */ - ret = pl011_sgbuf_init(uap->dmarx.chan, &uap->dmarx.sgbuf_a, + ret = pl011_dmabuf_init(uap->dmarx.chan, &uap->dmarx.dbuf_a, DMA_FROM_DEVICE); if (ret) { dev_err(uap->port.dev, "failed to init DMA %s: %d\n", @@ -1141,12 +1136,12 @@ static void pl011_dma_startup(struct uart_amba_port *uap) goto skip_rx; } - ret = pl011_sgbuf_init(uap->dmarx.chan, &uap->dmarx.sgbuf_b, + ret = pl011_dmabuf_init(uap->dmarx.chan, &uap->dmarx.dbuf_b, DMA_FROM_DEVICE); if (ret) { dev_err(uap->port.dev, "failed to init DMA %s: %d\n", "RX buffer B", ret); - pl011_sgbuf_free(uap->dmarx.chan, &uap->dmarx.sgbuf_a, + pl011_dmabuf_free(uap->dmarx.chan, &uap->dmarx.dbuf_a, DMA_FROM_DEVICE); goto skip_rx; } @@ -1200,8 +1195,9 @@ static void pl011_dma_shutdown(struct uart_amba_port *uap) /* In theory, this should already be done by pl011_dma_flush_buffer */ dmaengine_terminate_all(uap->dmatx.chan); if (uap->dmatx.queued) { - dma_unmap_sg(uap->dmatx.chan->device->dev, &uap->dmatx.sg, 1, - DMA_TO_DEVICE); + dma_unmap_single(uap->dmatx.chan->device->dev, + uap->dmatx.dma, uap->dmatx.len, + DMA_TO_DEVICE); uap->dmatx.queued = false; } @@ -1212,8 +1208,8 @@ static void pl011_dma_shutdown(struct uart_amba_port *uap) if (uap->using_rx_dma) { dmaengine_terminate_all(uap->dmarx.chan); /* Clean up the RX DMA */ - pl011_sgbuf_free(uap->dmarx.chan, &uap->dmarx.sgbuf_a, DMA_FROM_DEVICE); - pl011_sgbuf_free(uap->dmarx.chan, &uap->dmarx.sgbuf_b, DMA_FROM_DEVICE); + pl011_dmabuf_free(uap->dmarx.chan, &uap->dmarx.dbuf_a, DMA_FROM_DEVICE); + pl011_dmabuf_free(uap->dmarx.chan, &uap->dmarx.dbuf_b, DMA_FROM_DEVICE); if (uap->dmarx.poll_rate) del_timer_sync(&uap->dmarx.timer); uap->using_rx_dma = false; diff --git a/drivers/tty/serial/ma35d1_serial.c b/drivers/tty/serial/ma35d1_serial.c index 465b1def9e119..69da24565b997 100644 --- a/drivers/tty/serial/ma35d1_serial.c +++ b/drivers/tty/serial/ma35d1_serial.c @@ -552,11 +552,19 @@ static void ma35d1serial_console_putchar(struct uart_port *port, unsigned char c */ static void ma35d1serial_console_write(struct console *co, const char *s, u32 count) { - struct uart_ma35d1_port *up = &ma35d1serial_ports[co->index]; + struct uart_ma35d1_port *up; unsigned long flags; int locked = 1; u32 ier; + if ((co->index < 0) || (co->index >= MA35_UART_NR)) { + pr_warn("Failed to write on ononsole port %x, out of range\n", + co->index); + return; + } + + up = &ma35d1serial_ports[co->index]; + if (up->port.sysrq) locked = 0; else if (oops_in_progress) diff --git a/drivers/tty/serial/meson_uart.c b/drivers/tty/serial/meson_uart.c index 790d910dafa5d..9388b9ddea3bd 100644 --- a/drivers/tty/serial/meson_uart.c +++ b/drivers/tty/serial/meson_uart.c @@ -380,10 +380,14 @@ static void meson_uart_set_termios(struct uart_port *port, else val |= AML_UART_STOP_BIT_1SB; - if (cflags & CRTSCTS) - val &= ~AML_UART_TWO_WIRE_EN; - else + if (cflags & CRTSCTS) { + if (port->flags & UPF_HARD_FLOW) + val &= ~AML_UART_TWO_WIRE_EN; + else + termios->c_cflag &= ~CRTSCTS; + } else { val |= AML_UART_TWO_WIRE_EN; + } writel(val, port->membase + AML_UART_CONTROL); @@ -705,6 +709,7 @@ static int meson_uart_probe(struct platform_device *pdev) u32 fifosize = 64; /* Default is 64, 128 for EE UART_0 */ int ret = 0; int irq; + bool has_rtscts; if (pdev->dev.of_node) pdev->id = of_alias_get_id(pdev->dev.of_node, "serial"); @@ -732,6 +737,7 @@ static int meson_uart_probe(struct platform_device *pdev) return irq; of_property_read_u32(pdev->dev.of_node, "fifo-size", &fifosize); + has_rtscts = of_property_read_bool(pdev->dev.of_node, "uart-has-rtscts"); if (meson_ports[pdev->id]) { return dev_err_probe(&pdev->dev, -EBUSY, @@ -762,6 +768,8 @@ static int meson_uart_probe(struct platform_device *pdev) port->mapsize = resource_size(res_mem); port->irq = irq; port->flags = UPF_BOOT_AUTOCONF | UPF_LOW_LATENCY; + if (has_rtscts) + port->flags |= UPF_HARD_FLOW; port->has_sysrq = IS_ENABLED(CONFIG_SERIAL_MESON_CONSOLE); port->dev = &pdev->dev; port->line = pdev->id; diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c index f61d98e09dc39..6a0a3208d0900 100644 --- a/drivers/tty/serial/sc16is7xx.c +++ b/drivers/tty/serial/sc16is7xx.c @@ -767,6 +767,18 @@ static bool sc16is7xx_port_irq(struct sc16is7xx_port *s, int portno) case SC16IS7XX_IIR_RTOI_SRC: case SC16IS7XX_IIR_XOFFI_SRC: rxlen = sc16is7xx_port_read(port, SC16IS7XX_RXLVL_REG); + + /* + * There is a silicon bug that makes the chip report a + * time-out interrupt but no data in the FIFO. This is + * described in errata section 18.1.4. + * + * When this happens, read one byte from the FIFO to + * clear the interrupt. + */ + if (iir == SC16IS7XX_IIR_RTOI_SRC && !rxlen) + rxlen = 1; + if (rxlen) sc16is7xx_handle_rx(port, rxlen, iir); break; diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c index 23198e3f1461a..6b4a28bcf2f5f 100644 --- a/drivers/tty/sysrq.c +++ b/drivers/tty/sysrq.c @@ -262,13 +262,14 @@ static void sysrq_handle_showallcpus(u8 key) if (in_hardirq()) regs = get_irq_regs(); - pr_info("CPU%d:\n", smp_processor_id()); + pr_info("CPU%d:\n", get_cpu()); if (regs) show_regs(regs); else show_stack(NULL, NULL, KERN_INFO); schedule_work(&sysrq_showallcpus); + put_cpu(); } } diff --git a/drivers/tty/vcc.c b/drivers/tty/vcc.c index a39ed981bfd3e..5b625f20233b4 100644 --- a/drivers/tty/vcc.c +++ b/drivers/tty/vcc.c @@ -579,18 +579,22 @@ static int vcc_probe(struct vio_dev *vdev, const struct vio_device_id *id) return -ENOMEM; name = kstrdup(dev_name(&vdev->dev), GFP_KERNEL); + if (!name) { + rv = -ENOMEM; + goto free_port; + } rv = vio_driver_init(&port->vio, vdev, VDEV_CONSOLE_CON, vcc_versions, ARRAY_SIZE(vcc_versions), NULL, name); if (rv) - goto free_port; + goto free_name; port->vio.debug = vcc_dbg_vio; vcc_ldc_cfg.debug = vcc_dbg_ldc; rv = vio_ldc_alloc(&port->vio, &vcc_ldc_cfg, port); if (rv) - goto free_port; + goto free_name; spin_lock_init(&port->lock); @@ -624,6 +628,11 @@ static int vcc_probe(struct vio_dev *vdev, const struct vio_device_id *id) goto unreg_tty; } port->domain = kstrdup(domain, GFP_KERNEL); + if (!port->domain) { + rv = -ENOMEM; + goto unreg_tty; + } + mdesc_release(hp); @@ -653,8 +662,9 @@ static int vcc_probe(struct vio_dev *vdev, const struct vio_device_id *id) vcc_table_remove(port->index); free_ldc: vio_ldc_free(&port->vio); -free_port: +free_name: kfree(name); +free_port: kfree(port); return rv; diff --git a/drivers/ufs/core/ufs-mcq.c b/drivers/ufs/core/ufs-mcq.c index 2ba8ec254dcee..0787456c2b892 100644 --- a/drivers/ufs/core/ufs-mcq.c +++ b/drivers/ufs/core/ufs-mcq.c @@ -436,7 +436,7 @@ int ufshcd_mcq_init(struct ufs_hba *hba) for (i = 0; i < hba->nr_hw_queues; i++) { hwq = &hba->uhq[i]; - hwq->max_entries = hba->nutrs; + hwq->max_entries = hba->nutrs + 1; spin_lock_init(&hwq->sq_lock); spin_lock_init(&hwq->cq_lock); mutex_init(&hwq->sq_mutex); @@ -630,6 +630,7 @@ int ufshcd_mcq_abort(struct scsi_cmnd *cmd) int tag = scsi_cmd_to_rq(cmd)->tag; struct ufshcd_lrb *lrbp = &hba->lrb[tag]; struct ufs_hw_queue *hwq; + unsigned long flags; int err = FAILED; if (!ufshcd_cmd_inflight(lrbp->cmd)) { @@ -670,8 +671,10 @@ int ufshcd_mcq_abort(struct scsi_cmnd *cmd) } err = SUCCESS; + spin_lock_irqsave(&hwq->cq_lock, flags); if (ufshcd_cmd_inflight(lrbp->cmd)) ufshcd_release_scsi_cmd(hba, lrbp); + spin_unlock_irqrestore(&hwq->cq_lock, flags); out: return err; diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 5767642982c13..a885cc177cff7 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -2172,9 +2172,10 @@ void ufshcd_send_command(struct ufs_hba *hba, unsigned int task_tag, if (is_mcq_enabled(hba)) { int utrd_size = sizeof(struct utp_transfer_req_desc); struct utp_transfer_req_desc *src = lrbp->utr_descriptor_ptr; - struct utp_transfer_req_desc *dest = hwq->sqe_base_addr + hwq->sq_tail_slot; + struct utp_transfer_req_desc *dest; spin_lock(&hwq->sq_lock); + dest = hwq->sqe_base_addr + hwq->sq_tail_slot; memcpy(dest, src, utrd_size); ufshcd_inc_sq_tail(hwq); spin_unlock(&hwq->sq_lock); @@ -6347,11 +6348,24 @@ static bool ufshcd_abort_one(struct request *rq, void *priv) struct scsi_device *sdev = cmd->device; struct Scsi_Host *shost = sdev->host; struct ufs_hba *hba = shost_priv(shost); + struct ufshcd_lrb *lrbp = &hba->lrb[tag]; + struct ufs_hw_queue *hwq; + unsigned long flags; *ret = ufshcd_try_to_abort_task(hba, tag); dev_err(hba->dev, "Aborting tag %d / CDB %#02x %s\n", tag, hba->lrb[tag].cmd ? hba->lrb[tag].cmd->cmnd[0] : -1, *ret ? "failed" : "succeeded"); + + /* Release cmd in MCQ mode if abort succeeds */ + if (is_mcq_enabled(hba) && (*ret == 0)) { + hwq = ufshcd_mcq_req_to_hwq(hba, scsi_cmd_to_rq(lrbp->cmd)); + spin_lock_irqsave(&hwq->cq_lock, flags); + if (ufshcd_cmd_inflight(lrbp->cmd)) + ufshcd_release_scsi_cmd(hba, lrbp); + spin_unlock_irqrestore(&hwq->cq_lock, flags); + } + return *ret == 0; } @@ -8723,7 +8737,8 @@ static int ufshcd_probe_hba(struct ufs_hba *hba, bool init_dev_params) if (ret) goto out; - if (hba->quirks & UFSHCD_QUIRK_REINIT_AFTER_MAX_GEAR_SWITCH) { + if (!hba->pm_op_in_progress && + (hba->quirks & UFSHCD_QUIRK_REINIT_AFTER_MAX_GEAR_SWITCH)) { /* Reset the device and controller before doing reinit */ ufshcd_device_reset(hba); ufshcd_hba_stop(hba); diff --git a/drivers/ufs/host/ufs-qcom.c b/drivers/ufs/host/ufs-qcom.c index d1149b1c3ed50..fc40726e13c26 100644 --- a/drivers/ufs/host/ufs-qcom.c +++ b/drivers/ufs/host/ufs-qcom.c @@ -909,8 +909,13 @@ static int ufs_qcom_pwr_change_notify(struct ufs_hba *hba, return ret; } - /* Use the agreed gear */ - host->hs_gear = dev_req_params->gear_tx; + /* + * Update hs_gear only when the gears are scaled to a higher value. This is because, + * the PHY gear settings are backwards compatible and we only need to change the PHY + * settings while scaling to higher gears. + */ + if (dev_req_params->gear_tx > host->hs_gear) + host->hs_gear = dev_req_params->gear_tx; /* enable the device ref clock before changing to HS mode */ if (!ufshcd_is_hs_mode(&hba->pwr_info) && @@ -1394,9 +1399,11 @@ static int ufs_qcom_clk_scale_notify(struct ufs_hba *hba, err = ufs_qcom_clk_scale_up_pre_change(hba); else err = ufs_qcom_clk_scale_down_pre_change(hba); - if (err) - ufshcd_uic_hibern8_exit(hba); + if (err) { + ufshcd_uic_hibern8_exit(hba); + return err; + } } else { if (scale_up) err = ufs_qcom_clk_scale_up_post_change(hba); diff --git a/drivers/usb/cdns3/cdnsp-ring.c b/drivers/usb/cdns3/cdnsp-ring.c index 07f6068342d46..275a6a2fa671e 100644 --- a/drivers/usb/cdns3/cdnsp-ring.c +++ b/drivers/usb/cdns3/cdnsp-ring.c @@ -1529,6 +1529,7 @@ irqreturn_t cdnsp_thread_irq_handler(int irq, void *data) unsigned long flags; int counter = 0; + local_bh_disable(); spin_lock_irqsave(&pdev->lock, flags); if (pdev->cdnsp_state & (CDNSP_STATE_HALTED | CDNSP_STATE_DYING)) { @@ -1541,6 +1542,7 @@ irqreturn_t cdnsp_thread_irq_handler(int irq, void *data) cdnsp_died(pdev); spin_unlock_irqrestore(&pdev->lock, flags); + local_bh_enable(); return IRQ_HANDLED; } @@ -1557,6 +1559,7 @@ irqreturn_t cdnsp_thread_irq_handler(int irq, void *data) cdnsp_update_erst_dequeue(pdev, event_ring_deq, 1); spin_unlock_irqrestore(&pdev->lock, flags); + local_bh_enable(); return IRQ_HANDLED; } diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c index b19e38d5fd10c..7f8d33f92ddb5 100644 --- a/drivers/usb/core/config.c +++ b/drivers/usb/core/config.c @@ -1047,7 +1047,7 @@ int usb_get_bos_descriptor(struct usb_device *dev) if (cap->bDescriptorType != USB_DT_DEVICE_CAPABILITY) { dev_notice(ddev, "descriptor type invalid, skip\n"); - continue; + goto skip_to_next_descriptor; } switch (cap_type) { @@ -1078,6 +1078,7 @@ int usb_get_bos_descriptor(struct usb_device *dev) break; } +skip_to_next_descriptor: total_len -= length; buffer += length; } diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 0ff47eeffb490..dfc30cebd4c4c 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -622,29 +622,6 @@ static int hub_ext_port_status(struct usb_hub *hub, int port1, int type, ret = 0; } mutex_unlock(&hub->status_mutex); - - /* - * There is no need to lock status_mutex here, because status_mutex - * protects hub->status, and the phy driver only checks the port - * status without changing the status. - */ - if (!ret) { - struct usb_device *hdev = hub->hdev; - - /* - * Only roothub will be notified of port state changes, - * since the USB PHY only cares about changes at the next - * level. - */ - if (is_root_hub(hdev)) { - struct usb_hcd *hcd = bus_to_hcd(hdev->bus); - - if (hcd->usb_phy) - usb_phy_notify_port_status(hcd->usb_phy, - port1 - 1, *status, *change); - } - } - return ret; } diff --git a/drivers/usb/dwc2/hcd_intr.c b/drivers/usb/dwc2/hcd_intr.c index 0144ca8350c31..5c7538d498dd1 100644 --- a/drivers/usb/dwc2/hcd_intr.c +++ b/drivers/usb/dwc2/hcd_intr.c @@ -2015,15 +2015,17 @@ static void dwc2_hc_n_intr(struct dwc2_hsotg *hsotg, int chnum) { struct dwc2_qtd *qtd; struct dwc2_host_chan *chan; - u32 hcint, hcintmsk; + u32 hcint, hcintraw, hcintmsk; chan = hsotg->hc_ptr_array[chnum]; - hcint = dwc2_readl(hsotg, HCINT(chnum)); + hcintraw = dwc2_readl(hsotg, HCINT(chnum)); hcintmsk = dwc2_readl(hsotg, HCINTMSK(chnum)); + hcint = hcintraw & hcintmsk; + dwc2_writel(hsotg, hcint, HCINT(chnum)); + if (!chan) { dev_err(hsotg->dev, "## hc_ptr_array for channel is NULL ##\n"); - dwc2_writel(hsotg, hcint, HCINT(chnum)); return; } @@ -2032,11 +2034,9 @@ static void dwc2_hc_n_intr(struct dwc2_hsotg *hsotg, int chnum) chnum); dev_vdbg(hsotg->dev, " hcint 0x%08x, hcintmsk 0x%08x, hcint&hcintmsk 0x%08x\n", - hcint, hcintmsk, hcint & hcintmsk); + hcintraw, hcintmsk, hcint); } - dwc2_writel(hsotg, hcint, HCINT(chnum)); - /* * If we got an interrupt after someone called * dwc2_hcd_endpoint_disable() we don't want to crash below @@ -2046,8 +2046,7 @@ static void dwc2_hc_n_intr(struct dwc2_hsotg *hsotg, int chnum) return; } - chan->hcint = hcint; - hcint &= hcintmsk; + chan->hcint = hcintraw; /* * If the channel was halted due to a dequeue, the qtd list might diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 343d2570189ff..8d5af9ccb6027 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -1094,6 +1094,111 @@ static void dwc3_set_power_down_clk_scale(struct dwc3 *dwc) } } +static void dwc3_config_threshold(struct dwc3 *dwc) +{ + u32 reg; + u8 rx_thr_num; + u8 rx_maxburst; + u8 tx_thr_num; + u8 tx_maxburst; + + /* + * Must config both number of packets and max burst settings to enable + * RX and/or TX threshold. + */ + if (!DWC3_IP_IS(DWC3) && dwc->dr_mode == USB_DR_MODE_HOST) { + rx_thr_num = dwc->rx_thr_num_pkt_prd; + rx_maxburst = dwc->rx_max_burst_prd; + tx_thr_num = dwc->tx_thr_num_pkt_prd; + tx_maxburst = dwc->tx_max_burst_prd; + + if (rx_thr_num && rx_maxburst) { + reg = dwc3_readl(dwc->regs, DWC3_GRXTHRCFG); + reg |= DWC31_RXTHRNUMPKTSEL_PRD; + + reg &= ~DWC31_RXTHRNUMPKT_PRD(~0); + reg |= DWC31_RXTHRNUMPKT_PRD(rx_thr_num); + + reg &= ~DWC31_MAXRXBURSTSIZE_PRD(~0); + reg |= DWC31_MAXRXBURSTSIZE_PRD(rx_maxburst); + + dwc3_writel(dwc->regs, DWC3_GRXTHRCFG, reg); + } + + if (tx_thr_num && tx_maxburst) { + reg = dwc3_readl(dwc->regs, DWC3_GTXTHRCFG); + reg |= DWC31_TXTHRNUMPKTSEL_PRD; + + reg &= ~DWC31_TXTHRNUMPKT_PRD(~0); + reg |= DWC31_TXTHRNUMPKT_PRD(tx_thr_num); + + reg &= ~DWC31_MAXTXBURSTSIZE_PRD(~0); + reg |= DWC31_MAXTXBURSTSIZE_PRD(tx_maxburst); + + dwc3_writel(dwc->regs, DWC3_GTXTHRCFG, reg); + } + } + + rx_thr_num = dwc->rx_thr_num_pkt; + rx_maxburst = dwc->rx_max_burst; + tx_thr_num = dwc->tx_thr_num_pkt; + tx_maxburst = dwc->tx_max_burst; + + if (DWC3_IP_IS(DWC3)) { + if (rx_thr_num && rx_maxburst) { + reg = dwc3_readl(dwc->regs, DWC3_GRXTHRCFG); + reg |= DWC3_GRXTHRCFG_PKTCNTSEL; + + reg &= ~DWC3_GRXTHRCFG_RXPKTCNT(~0); + reg |= DWC3_GRXTHRCFG_RXPKTCNT(rx_thr_num); + + reg &= ~DWC3_GRXTHRCFG_MAXRXBURSTSIZE(~0); + reg |= DWC3_GRXTHRCFG_MAXRXBURSTSIZE(rx_maxburst); + + dwc3_writel(dwc->regs, DWC3_GRXTHRCFG, reg); + } + + if (tx_thr_num && tx_maxburst) { + reg = dwc3_readl(dwc->regs, DWC3_GTXTHRCFG); + reg |= DWC3_GTXTHRCFG_PKTCNTSEL; + + reg &= ~DWC3_GTXTHRCFG_TXPKTCNT(~0); + reg |= DWC3_GTXTHRCFG_TXPKTCNT(tx_thr_num); + + reg &= ~DWC3_GTXTHRCFG_MAXTXBURSTSIZE(~0); + reg |= DWC3_GTXTHRCFG_MAXTXBURSTSIZE(tx_maxburst); + + dwc3_writel(dwc->regs, DWC3_GTXTHRCFG, reg); + } + } else { + if (rx_thr_num && rx_maxburst) { + reg = dwc3_readl(dwc->regs, DWC3_GRXTHRCFG); + reg |= DWC31_GRXTHRCFG_PKTCNTSEL; + + reg &= ~DWC31_GRXTHRCFG_RXPKTCNT(~0); + reg |= DWC31_GRXTHRCFG_RXPKTCNT(rx_thr_num); + + reg &= ~DWC31_GRXTHRCFG_MAXRXBURSTSIZE(~0); + reg |= DWC31_GRXTHRCFG_MAXRXBURSTSIZE(rx_maxburst); + + dwc3_writel(dwc->regs, DWC3_GRXTHRCFG, reg); + } + + if (tx_thr_num && tx_maxburst) { + reg = dwc3_readl(dwc->regs, DWC3_GTXTHRCFG); + reg |= DWC31_GTXTHRCFG_PKTCNTSEL; + + reg &= ~DWC31_GTXTHRCFG_TXPKTCNT(~0); + reg |= DWC31_GTXTHRCFG_TXPKTCNT(tx_thr_num); + + reg &= ~DWC31_GTXTHRCFG_MAXTXBURSTSIZE(~0); + reg |= DWC31_GTXTHRCFG_MAXTXBURSTSIZE(tx_maxburst); + + dwc3_writel(dwc->regs, DWC3_GTXTHRCFG, reg); + } + } +} + /** * dwc3_core_init - Low-level initialization of DWC3 Core * @dwc: Pointer to our controller context structure @@ -1246,42 +1351,7 @@ static int dwc3_core_init(struct dwc3 *dwc) dwc3_writel(dwc->regs, DWC3_GUCTL1, reg); } - /* - * Must config both number of packets and max burst settings to enable - * RX and/or TX threshold. - */ - if (!DWC3_IP_IS(DWC3) && dwc->dr_mode == USB_DR_MODE_HOST) { - u8 rx_thr_num = dwc->rx_thr_num_pkt_prd; - u8 rx_maxburst = dwc->rx_max_burst_prd; - u8 tx_thr_num = dwc->tx_thr_num_pkt_prd; - u8 tx_maxburst = dwc->tx_max_burst_prd; - - if (rx_thr_num && rx_maxburst) { - reg = dwc3_readl(dwc->regs, DWC3_GRXTHRCFG); - reg |= DWC31_RXTHRNUMPKTSEL_PRD; - - reg &= ~DWC31_RXTHRNUMPKT_PRD(~0); - reg |= DWC31_RXTHRNUMPKT_PRD(rx_thr_num); - - reg &= ~DWC31_MAXRXBURSTSIZE_PRD(~0); - reg |= DWC31_MAXRXBURSTSIZE_PRD(rx_maxburst); - - dwc3_writel(dwc->regs, DWC3_GRXTHRCFG, reg); - } - - if (tx_thr_num && tx_maxburst) { - reg = dwc3_readl(dwc->regs, DWC3_GTXTHRCFG); - reg |= DWC31_TXTHRNUMPKTSEL_PRD; - - reg &= ~DWC31_TXTHRNUMPKT_PRD(~0); - reg |= DWC31_TXTHRNUMPKT_PRD(tx_thr_num); - - reg &= ~DWC31_MAXTXBURSTSIZE_PRD(~0); - reg |= DWC31_MAXTXBURSTSIZE_PRD(tx_maxburst); - - dwc3_writel(dwc->regs, DWC3_GTXTHRCFG, reg); - } - } + dwc3_config_threshold(dwc); return 0; @@ -1417,6 +1487,10 @@ static void dwc3_get_properties(struct dwc3 *dwc) u8 lpm_nyet_threshold; u8 tx_de_emphasis; u8 hird_threshold; + u8 rx_thr_num_pkt = 0; + u8 rx_max_burst = 0; + u8 tx_thr_num_pkt = 0; + u8 tx_max_burst = 0; u8 rx_thr_num_pkt_prd = 0; u8 rx_max_burst_prd = 0; u8 tx_thr_num_pkt_prd = 0; @@ -1479,6 +1553,14 @@ static void dwc3_get_properties(struct dwc3 *dwc) "snps,usb2-lpm-disable"); dwc->usb2_gadget_lpm_disable = device_property_read_bool(dev, "snps,usb2-gadget-lpm-disable"); + device_property_read_u8(dev, "snps,rx-thr-num-pkt", + &rx_thr_num_pkt); + device_property_read_u8(dev, "snps,rx-max-burst", + &rx_max_burst); + device_property_read_u8(dev, "snps,tx-thr-num-pkt", + &tx_thr_num_pkt); + device_property_read_u8(dev, "snps,tx-max-burst", + &tx_max_burst); device_property_read_u8(dev, "snps,rx-thr-num-pkt-prd", &rx_thr_num_pkt_prd); device_property_read_u8(dev, "snps,rx-max-burst-prd", @@ -1560,6 +1642,12 @@ static void dwc3_get_properties(struct dwc3 *dwc) dwc->hird_threshold = hird_threshold; + dwc->rx_thr_num_pkt = rx_thr_num_pkt; + dwc->rx_max_burst = rx_max_burst; + + dwc->tx_thr_num_pkt = tx_thr_num_pkt; + dwc->tx_max_burst = tx_max_burst; + dwc->rx_thr_num_pkt_prd = rx_thr_num_pkt_prd; dwc->rx_max_burst_prd = rx_max_burst_prd; @@ -1918,6 +2006,8 @@ static int dwc3_probe(struct platform_device *pdev) pm_runtime_put(dev); + dma_set_max_seg_size(dev, UINT_MAX); + return 0; err_exit_debugfs: diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index a69ac67d89fe6..6782ec8bfd64c 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -211,6 +211,11 @@ #define DWC3_GRXTHRCFG_RXPKTCNT(n) (((n) & 0xf) << 24) #define DWC3_GRXTHRCFG_PKTCNTSEL BIT(29) +/* Global TX Threshold Configuration Register */ +#define DWC3_GTXTHRCFG_MAXTXBURSTSIZE(n) (((n) & 0xff) << 16) +#define DWC3_GTXTHRCFG_TXPKTCNT(n) (((n) & 0xf) << 24) +#define DWC3_GTXTHRCFG_PKTCNTSEL BIT(29) + /* Global RX Threshold Configuration Register for DWC_usb31 only */ #define DWC31_GRXTHRCFG_MAXRXBURSTSIZE(n) (((n) & 0x1f) << 16) #define DWC31_GRXTHRCFG_RXPKTCNT(n) (((n) & 0x1f) << 21) @@ -1045,6 +1050,10 @@ struct dwc3_scratchpad_array { * @test_mode_nr: test feature selector * @lpm_nyet_threshold: LPM NYET response threshold * @hird_threshold: HIRD threshold + * @rx_thr_num_pkt: USB receive packet count + * @rx_max_burst: max USB receive burst size + * @tx_thr_num_pkt: USB transmit packet count + * @tx_max_burst: max USB transmit burst size * @rx_thr_num_pkt_prd: periodic ESS receive packet count * @rx_max_burst_prd: max periodic ESS receive burst size * @tx_thr_num_pkt_prd: periodic ESS transmit packet count @@ -1273,6 +1282,10 @@ struct dwc3 { u8 test_mode_nr; u8 lpm_nyet_threshold; u8 hird_threshold; + u8 rx_thr_num_pkt; + u8 rx_max_burst; + u8 tx_thr_num_pkt; + u8 tx_max_burst; u8 rx_thr_num_pkt_prd; u8 rx_max_burst_prd; u8 tx_thr_num_pkt_prd; diff --git a/drivers/usb/dwc3/drd.c b/drivers/usb/dwc3/drd.c index 039bf241769af..57ddd2e43022e 100644 --- a/drivers/usb/dwc3/drd.c +++ b/drivers/usb/dwc3/drd.c @@ -505,6 +505,7 @@ static int dwc3_setup_role_switch(struct dwc3 *dwc) dwc->role_switch_default_mode = USB_DR_MODE_PERIPHERAL; mode = DWC3_GCTL_PRTCAP_DEVICE; } + dwc3_set_mode(dwc, mode); dwc3_role_switch.fwnode = dev_fwnode(dwc->dev); dwc3_role_switch.set = dwc3_usb_role_switch_set; @@ -526,7 +527,6 @@ static int dwc3_setup_role_switch(struct dwc3 *dwc) } } - dwc3_set_mode(dwc, mode); return 0; } #else diff --git a/drivers/usb/dwc3/dwc3-qcom.c b/drivers/usb/dwc3/dwc3-qcom.c index 3de43df6bbe81..82544374110b0 100644 --- a/drivers/usb/dwc3/dwc3-qcom.c +++ b/drivers/usb/dwc3/dwc3-qcom.c @@ -549,7 +549,7 @@ static int dwc3_qcom_setup_irq(struct platform_device *pdev) irq_set_status_flags(irq, IRQ_NOAUTOEN); ret = devm_request_threaded_irq(qcom->dev, irq, NULL, qcom_dwc3_resume_irq, - IRQF_TRIGGER_HIGH | IRQF_ONESHOT, + IRQF_ONESHOT, "qcom_dwc3 HS", qcom); if (ret) { dev_err(qcom->dev, "hs_phy_irq failed: %d\n", ret); @@ -564,7 +564,7 @@ static int dwc3_qcom_setup_irq(struct platform_device *pdev) irq_set_status_flags(irq, IRQ_NOAUTOEN); ret = devm_request_threaded_irq(qcom->dev, irq, NULL, qcom_dwc3_resume_irq, - IRQF_TRIGGER_HIGH | IRQF_ONESHOT, + IRQF_ONESHOT, "qcom_dwc3 DP_HS", qcom); if (ret) { dev_err(qcom->dev, "dp_hs_phy_irq failed: %d\n", ret); @@ -579,7 +579,7 @@ static int dwc3_qcom_setup_irq(struct platform_device *pdev) irq_set_status_flags(irq, IRQ_NOAUTOEN); ret = devm_request_threaded_irq(qcom->dev, irq, NULL, qcom_dwc3_resume_irq, - IRQF_TRIGGER_HIGH | IRQF_ONESHOT, + IRQF_ONESHOT, "qcom_dwc3 DM_HS", qcom); if (ret) { dev_err(qcom->dev, "dm_hs_phy_irq failed: %d\n", ret); @@ -594,7 +594,7 @@ static int dwc3_qcom_setup_irq(struct platform_device *pdev) irq_set_status_flags(irq, IRQ_NOAUTOEN); ret = devm_request_threaded_irq(qcom->dev, irq, NULL, qcom_dwc3_resume_irq, - IRQF_TRIGGER_HIGH | IRQF_ONESHOT, + IRQF_ONESHOT, "qcom_dwc3 SS", qcom); if (ret) { dev_err(qcom->dev, "ss_phy_irq failed: %d\n", ret); @@ -758,6 +758,7 @@ static int dwc3_qcom_of_register_core(struct platform_device *pdev) if (!qcom->dwc3) { ret = -ENODEV; dev_err(dev, "failed to get dwc3 platform device\n"); + of_platform_depopulate(dev); } node_put: @@ -766,9 +767,9 @@ static int dwc3_qcom_of_register_core(struct platform_device *pdev) return ret; } -static struct platform_device * -dwc3_qcom_create_urs_usb_platdev(struct device *dev) +static struct platform_device *dwc3_qcom_create_urs_usb_platdev(struct device *dev) { + struct platform_device *urs_usb = NULL; struct fwnode_handle *fwh; struct acpi_device *adev; char name[8]; @@ -788,9 +789,26 @@ dwc3_qcom_create_urs_usb_platdev(struct device *dev) adev = to_acpi_device_node(fwh); if (!adev) - return NULL; + goto err_put_handle; + + urs_usb = acpi_create_platform_device(adev, NULL); + if (IS_ERR_OR_NULL(urs_usb)) + goto err_put_handle; + + return urs_usb; + +err_put_handle: + fwnode_handle_put(fwh); + + return urs_usb; +} - return acpi_create_platform_device(adev, NULL); +static void dwc3_qcom_destroy_urs_usb_platdev(struct platform_device *urs_usb) +{ + struct fwnode_handle *fwh = urs_usb->dev.fwnode; + + platform_device_unregister(urs_usb); + fwnode_handle_put(fwh); } static int dwc3_qcom_probe(struct platform_device *pdev) @@ -874,13 +892,13 @@ static int dwc3_qcom_probe(struct platform_device *pdev) qcom->qscratch_base = devm_ioremap_resource(dev, parent_res); if (IS_ERR(qcom->qscratch_base)) { ret = PTR_ERR(qcom->qscratch_base); - goto clk_disable; + goto free_urs; } ret = dwc3_qcom_setup_irq(pdev); if (ret) { dev_err(dev, "failed to setup IRQs, err=%d\n", ret); - goto clk_disable; + goto free_urs; } /* @@ -899,7 +917,7 @@ static int dwc3_qcom_probe(struct platform_device *pdev) if (ret) { dev_err(dev, "failed to register DWC3 Core, err=%d\n", ret); - goto depopulate; + goto free_urs; } ret = dwc3_qcom_interconnect_init(qcom); @@ -931,10 +949,16 @@ static int dwc3_qcom_probe(struct platform_device *pdev) interconnect_exit: dwc3_qcom_interconnect_exit(qcom); depopulate: - if (np) + if (np) { of_platform_depopulate(&pdev->dev); - else - platform_device_put(pdev); + } else { + device_remove_software_node(&qcom->dwc3->dev); + platform_device_del(qcom->dwc3); + } + platform_device_put(qcom->dwc3); +free_urs: + if (qcom->urs_usb) + dwc3_qcom_destroy_urs_usb_platdev(qcom->urs_usb); clk_disable: for (i = qcom->num_clocks - 1; i >= 0; i--) { clk_disable_unprepare(qcom->clks[i]); @@ -953,11 +977,16 @@ static void dwc3_qcom_remove(struct platform_device *pdev) struct device *dev = &pdev->dev; int i; - device_remove_software_node(&qcom->dwc3->dev); - if (np) + if (np) { of_platform_depopulate(&pdev->dev); - else - platform_device_put(pdev); + } else { + device_remove_software_node(&qcom->dwc3->dev); + platform_device_del(qcom->dwc3); + } + platform_device_put(qcom->dwc3); + + if (qcom->urs_usb) + dwc3_qcom_destroy_urs_usb_platdev(qcom->urs_usb); for (i = qcom->num_clocks - 1; i >= 0; i--) { clk_disable_unprepare(qcom->clks[i]); diff --git a/drivers/usb/fotg210/fotg210-hcd.c b/drivers/usb/fotg210/fotg210-hcd.c index 929106c16b29b..7bf810a0c98a9 100644 --- a/drivers/usb/fotg210/fotg210-hcd.c +++ b/drivers/usb/fotg210/fotg210-hcd.c @@ -428,8 +428,6 @@ static void qh_lines(struct fotg210_hcd *fotg210, struct fotg210_qh *qh, temp = size; size -= temp; next += temp; - if (temp == size) - goto done; } temp = snprintf(next, size, "\n"); @@ -439,7 +437,6 @@ static void qh_lines(struct fotg210_hcd *fotg210, struct fotg210_qh *qh, size -= temp; next += temp; -done: *sizep = size; *nextp = next; } diff --git a/drivers/usb/gadget/function/f_hid.c b/drivers/usb/gadget/function/f_hid.c index ea85e2c701a15..3c8a9dd585c09 100644 --- a/drivers/usb/gadget/function/f_hid.c +++ b/drivers/usb/gadget/function/f_hid.c @@ -92,6 +92,7 @@ static void hidg_release(struct device *dev) { struct f_hidg *hidg = container_of(dev, struct f_hidg, dev); + kfree(hidg->report_desc); kfree(hidg->set_report_buf); kfree(hidg); } @@ -1287,9 +1288,9 @@ static struct usb_function *hidg_alloc(struct usb_function_instance *fi) hidg->report_length = opts->report_length; hidg->report_desc_length = opts->report_desc_length; if (opts->report_desc) { - hidg->report_desc = devm_kmemdup(&hidg->dev, opts->report_desc, - opts->report_desc_length, - GFP_KERNEL); + hidg->report_desc = kmemdup(opts->report_desc, + opts->report_desc_length, + GFP_KERNEL); if (!hidg->report_desc) { ret = -ENOMEM; goto err_put_device; diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c index e6ab8cc225ffd..cc0ed29a4adc0 100644 --- a/drivers/usb/gadget/function/f_ncm.c +++ b/drivers/usb/gadget/function/f_ncm.c @@ -1410,7 +1410,7 @@ static int ncm_bind(struct usb_configuration *c, struct usb_function *f) struct usb_composite_dev *cdev = c->cdev; struct f_ncm *ncm = func_to_ncm(f); struct usb_string *us; - int status; + int status = 0; struct usb_ep *ep; struct f_ncm_opts *ncm_opts; @@ -1428,22 +1428,17 @@ static int ncm_bind(struct usb_configuration *c, struct usb_function *f) f->os_desc_table[0].os_desc = &ncm_opts->ncm_os_desc; } - /* - * in drivers/usb/gadget/configfs.c:configfs_composite_bind() - * configurations are bound in sequence with list_for_each_entry, - * in each configuration its functions are bound in sequence - * with list_for_each_entry, so we assume no race condition - * with regard to ncm_opts->bound access - */ - if (!ncm_opts->bound) { - mutex_lock(&ncm_opts->lock); - gether_set_gadget(ncm_opts->net, cdev->gadget); + mutex_lock(&ncm_opts->lock); + gether_set_gadget(ncm_opts->net, cdev->gadget); + if (!ncm_opts->bound) status = gether_register_netdev(ncm_opts->net); - mutex_unlock(&ncm_opts->lock); - if (status) - goto fail; - ncm_opts->bound = true; - } + mutex_unlock(&ncm_opts->lock); + + if (status) + goto fail; + + ncm_opts->bound = true; + us = usb_gstrings_attach(cdev, ncm_strings, ARRAY_SIZE(ncm_string_defs)); if (IS_ERR(us)) { diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c index 7166d1117742a..781c8338546fd 100644 --- a/drivers/usb/gadget/udc/core.c +++ b/drivers/usb/gadget/udc/core.c @@ -1635,8 +1635,6 @@ static void gadget_unbind_driver(struct device *dev) dev_dbg(&udc->dev, "unbinding gadget driver [%s]\n", driver->function); - kobject_uevent(&udc->dev.kobj, KOBJ_CHANGE); - udc->allow_connect = false; cancel_work_sync(&udc->vbus_work); mutex_lock(&udc->connect_lock); @@ -1656,6 +1654,8 @@ static void gadget_unbind_driver(struct device *dev) driver->is_bound = false; udc->driver = NULL; mutex_unlock(&udc_lock); + + kobject_uevent(&udc->dev.kobj, KOBJ_CHANGE); } /* ------------------------------------------------------------------------- */ diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index bde43cef8846c..d6fc08e5db8fb 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -535,8 +535,6 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) /* xHC spec requires PCI devices to support D3hot and D3cold */ if (xhci->hci_version >= 0x120) xhci->quirks |= XHCI_DEFAULT_PM_RUNTIME_ALLOW; - else if (pdev->vendor == PCI_VENDOR_ID_AMD && xhci->hci_version >= 0x110) - xhci->quirks |= XHCI_DEFAULT_PM_RUNTIME_ALLOW; if (xhci->quirks & XHCI_RESET_ON_RESUME) xhci_dbg_trace(xhci, trace_xhci_dbg_quirks, @@ -695,7 +693,9 @@ static int xhci_pci_probe(struct pci_dev *dev, const struct pci_device_id *id) /* USB-2 and USB-3 roothubs initialized, allow runtime pm suspend */ pm_runtime_put_noidle(&dev->dev); - if (xhci->quirks & XHCI_DEFAULT_PM_RUNTIME_ALLOW) + if (pci_choose_state(dev, PMSG_SUSPEND) == PCI_D0) + pm_runtime_forbid(&dev->dev); + else if (xhci->quirks & XHCI_DEFAULT_PM_RUNTIME_ALLOW) pm_runtime_allow(&dev->dev); dma_set_max_seg_size(&dev->dev, UINT_MAX); diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c index b93161374293b..732cdeb739202 100644 --- a/drivers/usb/host/xhci-plat.c +++ b/drivers/usb/host/xhci-plat.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -148,7 +149,7 @@ int xhci_plat_probe(struct platform_device *pdev, struct device *sysdev, const s int ret; int irq; struct xhci_plat_priv *priv = NULL; - + bool of_match; if (usb_disabled()) return -ENODEV; @@ -253,16 +254,23 @@ int xhci_plat_probe(struct platform_device *pdev, struct device *sysdev, const s &xhci->imod_interval); } - hcd->usb_phy = devm_usb_get_phy_by_phandle(sysdev, "usb-phy", 0); - if (IS_ERR(hcd->usb_phy)) { - ret = PTR_ERR(hcd->usb_phy); - if (ret == -EPROBE_DEFER) - goto disable_clk; - hcd->usb_phy = NULL; - } else { - ret = usb_phy_init(hcd->usb_phy); - if (ret) - goto disable_clk; + /* + * Drivers such as dwc3 manages PHYs themself (and rely on driver name + * matching for the xhci platform device). + */ + of_match = of_match_device(pdev->dev.driver->of_match_table, &pdev->dev); + if (of_match) { + hcd->usb_phy = devm_usb_get_phy_by_phandle(sysdev, "usb-phy", 0); + if (IS_ERR(hcd->usb_phy)) { + ret = PTR_ERR(hcd->usb_phy); + if (ret == -EPROBE_DEFER) + goto disable_clk; + hcd->usb_phy = NULL; + } else { + ret = usb_phy_init(hcd->usb_phy); + if (ret) + goto disable_clk; + } } hcd->tpl_support = of_usb_host_tpl_support(sysdev->of_node); @@ -285,15 +293,17 @@ int xhci_plat_probe(struct platform_device *pdev, struct device *sysdev, const s goto dealloc_usb2_hcd; } - xhci->shared_hcd->usb_phy = devm_usb_get_phy_by_phandle(sysdev, - "usb-phy", 1); - if (IS_ERR(xhci->shared_hcd->usb_phy)) { - xhci->shared_hcd->usb_phy = NULL; - } else { - ret = usb_phy_init(xhci->shared_hcd->usb_phy); - if (ret) - dev_err(sysdev, "%s init usb3phy fail (ret=%d)\n", - __func__, ret); + if (of_match) { + xhci->shared_hcd->usb_phy = devm_usb_get_phy_by_phandle(sysdev, + "usb-phy", 1); + if (IS_ERR(xhci->shared_hcd->usb_phy)) { + xhci->shared_hcd->usb_phy = NULL; + } else { + ret = usb_phy_init(xhci->shared_hcd->usb_phy); + if (ret) + dev_err(sysdev, "%s init usb3phy fail (ret=%d)\n", + __func__, ret); + } } xhci->shared_hcd->tpl_support = hcd->tpl_support; diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index e1b1b64a07232..132b76fa7ca60 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -968,6 +968,7 @@ int xhci_resume(struct xhci_hcd *xhci, pm_message_t msg) int retval = 0; bool comp_timer_running = false; bool pending_portevent = false; + bool suspended_usb3_devs = false; bool reinit_xhc = false; if (!hcd->state) @@ -1115,10 +1116,17 @@ int xhci_resume(struct xhci_hcd *xhci, pm_message_t msg) /* * Resume roothubs only if there are pending events. * USB 3 devices resend U3 LFPS wake after a 100ms delay if - * the first wake signalling failed, give it that chance. + * the first wake signalling failed, give it that chance if + * there are suspended USB 3 devices. */ + if (xhci->usb3_rhub.bus_state.suspended_ports || + xhci->usb3_rhub.bus_state.bus_suspended) + suspended_usb3_devs = true; + pending_portevent = xhci_pending_portevent(xhci); - if (!pending_portevent && msg.event == PM_EVENT_AUTO_RESUME) { + + if (suspended_usb3_devs && !pending_portevent && + msg.event == PM_EVENT_AUTO_RESUME) { msleep(120); pending_portevent = xhci_pending_portevent(xhci); } diff --git a/drivers/usb/misc/onboard_usb_hub.c b/drivers/usb/misc/onboard_usb_hub.c index 57bbe13090948..d72130eda57d6 100644 --- a/drivers/usb/misc/onboard_usb_hub.c +++ b/drivers/usb/misc/onboard_usb_hub.c @@ -437,6 +437,8 @@ static const struct usb_device_id onboard_hub_id_table[] = { { USB_DEVICE(VENDOR_ID_MICROCHIP, 0x2412) }, /* USB2412 USB 2.0 */ { USB_DEVICE(VENDOR_ID_MICROCHIP, 0x2514) }, /* USB2514B USB 2.0 */ { USB_DEVICE(VENDOR_ID_MICROCHIP, 0x2517) }, /* USB2517 USB 2.0 */ + { USB_DEVICE(VENDOR_ID_MICROCHIP, 0x2744) }, /* USB5744 USB 2.0 */ + { USB_DEVICE(VENDOR_ID_MICROCHIP, 0x5744) }, /* USB5744 USB 3.0 */ { USB_DEVICE(VENDOR_ID_REALTEK, 0x0411) }, /* RTS5411 USB 3.1 */ { USB_DEVICE(VENDOR_ID_REALTEK, 0x5411) }, /* RTS5411 USB 2.1 */ { USB_DEVICE(VENDOR_ID_REALTEK, 0x0414) }, /* RTS5414 USB 3.2 */ diff --git a/drivers/usb/misc/onboard_usb_hub.h b/drivers/usb/misc/onboard_usb_hub.h index 2a4ab5ac0ebed..8af34e6d1afff 100644 --- a/drivers/usb/misc/onboard_usb_hub.h +++ b/drivers/usb/misc/onboard_usb_hub.h @@ -16,6 +16,11 @@ static const struct onboard_hub_pdata microchip_usb424_data = { .num_supplies = 1, }; +static const struct onboard_hub_pdata microchip_usb5744_data = { + .reset_us = 0, + .num_supplies = 2, +}; + static const struct onboard_hub_pdata realtek_rts5411_data = { .reset_us = 0, .num_supplies = 1, @@ -50,6 +55,8 @@ static const struct of_device_id onboard_hub_match[] = { { .compatible = "usb424,2412", .data = µchip_usb424_data, }, { .compatible = "usb424,2514", .data = µchip_usb424_data, }, { .compatible = "usb424,2517", .data = µchip_usb424_data, }, + { .compatible = "usb424,2744", .data = µchip_usb5744_data, }, + { .compatible = "usb424,5744", .data = µchip_usb5744_data, }, { .compatible = "usb451,8140", .data = &ti_tusb8041_data, }, { .compatible = "usb451,8142", .data = &ti_tusb8041_data, }, { .compatible = "usb4b4,6504", .data = &cypress_hx3_data, }, diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index 1bf23611be122..13a56783830df 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -1033,9 +1033,9 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(FTDI_VID, ACTISENSE_USG_PID) }, { USB_DEVICE(FTDI_VID, ACTISENSE_NGT_PID) }, { USB_DEVICE(FTDI_VID, ACTISENSE_NGW_PID) }, - { USB_DEVICE(FTDI_VID, ACTISENSE_D9AC_PID) }, - { USB_DEVICE(FTDI_VID, ACTISENSE_D9AD_PID) }, - { USB_DEVICE(FTDI_VID, ACTISENSE_D9AE_PID) }, + { USB_DEVICE(FTDI_VID, ACTISENSE_UID_PID) }, + { USB_DEVICE(FTDI_VID, ACTISENSE_USA_PID) }, + { USB_DEVICE(FTDI_VID, ACTISENSE_NGX_PID) }, { USB_DEVICE(FTDI_VID, ACTISENSE_D9AF_PID) }, { USB_DEVICE(FTDI_VID, CHETCO_SEAGAUGE_PID) }, { USB_DEVICE(FTDI_VID, CHETCO_SEASWITCH_PID) }, diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h index e2099445db708..21a2b5a25fc09 100644 --- a/drivers/usb/serial/ftdi_sio_ids.h +++ b/drivers/usb/serial/ftdi_sio_ids.h @@ -1568,9 +1568,9 @@ #define ACTISENSE_USG_PID 0xD9A9 /* USG USB Serial Adapter */ #define ACTISENSE_NGT_PID 0xD9AA /* NGT NMEA2000 Interface */ #define ACTISENSE_NGW_PID 0xD9AB /* NGW NMEA2000 Gateway */ -#define ACTISENSE_D9AC_PID 0xD9AC /* Actisense Reserved */ -#define ACTISENSE_D9AD_PID 0xD9AD /* Actisense Reserved */ -#define ACTISENSE_D9AE_PID 0xD9AE /* Actisense Reserved */ +#define ACTISENSE_UID_PID 0xD9AC /* USB Isolating Device */ +#define ACTISENSE_USA_PID 0xD9AD /* USB to Serial Adapter */ +#define ACTISENSE_NGX_PID 0xD9AE /* NGX NMEA2000 Gateway */ #define ACTISENSE_D9AF_PID 0xD9AF /* Actisense Reserved */ #define CHETCO_SEAGAUGE_PID 0xA548 /* SeaGauge USB Adapter */ #define CHETCO_SEASWITCH_PID 0xA549 /* SeaSwitch USB Adapter */ diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 45dcfaadaf98e..72390dbf07692 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -203,8 +203,8 @@ static void option_instat_callback(struct urb *urb); #define DELL_PRODUCT_5829E_ESIM 0x81e4 #define DELL_PRODUCT_5829E 0x81e6 -#define DELL_PRODUCT_FM101R 0x8213 -#define DELL_PRODUCT_FM101R_ESIM 0x8215 +#define DELL_PRODUCT_FM101R_ESIM 0x8213 +#define DELL_PRODUCT_FM101R 0x8215 #define KYOCERA_VENDOR_ID 0x0c88 #define KYOCERA_PRODUCT_KPC650 0x17da @@ -272,6 +272,7 @@ static void option_instat_callback(struct urb *urb); #define QUECTEL_PRODUCT_RM500Q 0x0800 #define QUECTEL_PRODUCT_RM520N 0x0801 #define QUECTEL_PRODUCT_EC200U 0x0901 +#define QUECTEL_PRODUCT_EG912Y 0x6001 #define QUECTEL_PRODUCT_EC200S_CN 0x6002 #define QUECTEL_PRODUCT_EC200A 0x6005 #define QUECTEL_PRODUCT_EM061K_LWW 0x6008 @@ -609,6 +610,8 @@ static void option_instat_callback(struct urb *urb); #define UNISOC_VENDOR_ID 0x1782 /* TOZED LT70-C based on UNISOC SL8563 uses UNISOC's vendor ID */ #define TOZED_PRODUCT_LT70C 0x4055 +/* Luat Air72*U series based on UNISOC UIS8910 uses UNISOC's vendor ID */ +#define LUAT_PRODUCT_AIR720U 0x4e00 /* Device flags */ @@ -1230,6 +1233,7 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, 0x0700, 0xff), /* BG95 */ .driver_info = RSVD(3) | ZLP }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500Q, 0xff, 0xff, 0x30) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500Q, 0xff, 0, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500Q, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500Q, 0xff, 0xff, 0x10), .driver_info = ZLP }, @@ -1242,6 +1246,7 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200U, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200S_CN, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200T, 0xff, 0, 0) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EG912Y, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500K, 0xff, 0x00, 0x00) }, { USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6001) }, @@ -1546,7 +1551,8 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0165, 0xff, 0xff, 0xff) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0167, 0xff, 0xff, 0xff), .driver_info = RSVD(4) }, - { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0189, 0xff, 0xff, 0xff) }, + { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0189, 0xff, 0xff, 0xff), + .driver_info = RSVD(4) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0191, 0xff, 0xff, 0xff), /* ZTE EuFi890 */ .driver_info = RSVD(4) }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0196, 0xff, 0xff, 0xff) }, @@ -2239,6 +2245,8 @@ static const struct usb_device_id option_ids[] = { .driver_info = RSVD(0) | RSVD(1) | RSVD(6) }, { USB_DEVICE(0x0489, 0xe0b5), /* Foxconn T77W968 ESIM */ .driver_info = RSVD(0) | RSVD(1) | RSVD(6) }, + { USB_DEVICE_INTERFACE_CLASS(0x0489, 0xe0da, 0xff), /* Foxconn T99W265 MBIM variant */ + .driver_info = RSVD(3) | RSVD(5) }, { USB_DEVICE_INTERFACE_CLASS(0x0489, 0xe0db, 0xff), /* Foxconn T99W265 MBIM */ .driver_info = RSVD(3) }, { USB_DEVICE_INTERFACE_CLASS(0x0489, 0xe0ee, 0xff), /* Foxconn T99W368 MBIM */ @@ -2249,6 +2257,7 @@ static const struct usb_device_id option_ids[] = { .driver_info = RSVD(4) | RSVD(5) | RSVD(6) }, { USB_DEVICE(0x1782, 0x4d10) }, /* Fibocom L610 (AT mode) */ { USB_DEVICE_INTERFACE_CLASS(0x1782, 0x4d11, 0xff) }, /* Fibocom L610 (ECM/RNDIS mode) */ + { USB_DEVICE_AND_INTERFACE_INFO(0x2cb7, 0x0001, 0xff, 0xff, 0xff) }, /* Fibocom L716-EU (ECM/RNDIS mode) */ { USB_DEVICE(0x2cb7, 0x0104), /* Fibocom NL678 series */ .driver_info = RSVD(4) | RSVD(5) }, { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0105, 0xff), /* Fibocom NL678 series */ @@ -2271,6 +2280,7 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0xff, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, TOZED_PRODUCT_LT70C, 0xff, 0, 0) }, + { USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, LUAT_PRODUCT_AIR720U, 0xff, 0, 0) }, { } /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, option_ids); diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h index 20dcbccb290b3..fd68204374f2c 100644 --- a/drivers/usb/storage/unusual_devs.h +++ b/drivers/usb/storage/unusual_devs.h @@ -1305,6 +1305,17 @@ UNUSUAL_DEV( 0x090c, 0x6000, 0x0100, 0x0100, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_INITIAL_READ10 ), +/* + * Patch by Tasos Sahanidis + * This flash drive always shows up with write protect enabled + * during the first mode sense. + */ +UNUSUAL_DEV(0x0951, 0x1697, 0x0100, 0x0100, + "Kingston", + "DT Ultimate G3", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_NO_WP_DETECT), + /* * This Pentax still camera is not conformant * to the USB storage specification: - diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c index 9c1dbf3c00e0a..6e80fab11788c 100644 --- a/drivers/usb/typec/class.c +++ b/drivers/usb/typec/class.c @@ -266,7 +266,7 @@ static void typec_altmode_put_partner(struct altmode *altmode) if (!partner) return; - adev = &partner->adev; + adev = &altmode->adev; if (is_typec_plug(adev->dev.parent)) { struct typec_plug *plug = to_typec_plug(adev->dev.parent); @@ -496,7 +496,8 @@ static void typec_altmode_release(struct device *dev) { struct altmode *alt = to_altmode(to_typec_altmode(dev)); - typec_altmode_put_partner(alt); + if (!is_typec_port(dev->parent)) + typec_altmode_put_partner(alt); altmode_id_remove(alt->adev.dev.parent, alt->id); kfree(alt); diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 25e7e14da2a77..6d455ca76125e 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -4273,7 +4273,8 @@ static void run_state_machine(struct tcpm_port *port) current_lim = PD_P_SNK_STDBY_MW / 5; tcpm_set_current_limit(port, current_lim, 5000); /* Not sink vbus if operational current is 0mA */ - tcpm_set_charge(port, !!pdo_max_current(port->snk_pdo[0])); + tcpm_set_charge(port, !port->pd_supported || + pdo_max_current(port->snk_pdo[0])); if (!port->pd_supported) tcpm_set_state(port, SNK_READY, 0); @@ -5391,6 +5392,15 @@ static void _tcpm_pd_hard_reset(struct tcpm_port *port) if (port->bist_request == BDO_MODE_TESTDATA && port->tcpc->set_bist_data) port->tcpc->set_bist_data(port->tcpc, false); + switch (port->state) { + case ERROR_RECOVERY: + case PORT_RESET: + case PORT_RESET_WAIT_OFF: + return; + default: + break; + } + if (port->ams != NONE_AMS) port->ams = NONE_AMS; if (port->hard_reset_count < PD_N_HARD_RESET_COUNT) diff --git a/drivers/usb/typec/ucsi/ucsi_glink.c b/drivers/usb/typec/ucsi/ucsi_glink.c index bb1854b3311dc..4853141cd10c8 100644 --- a/drivers/usb/typec/ucsi/ucsi_glink.c +++ b/drivers/usb/typec/ucsi/ucsi_glink.c @@ -8,9 +8,13 @@ #include #include #include +#include +#include #include #include "ucsi.h" +#define PMIC_GLINK_MAX_PORTS 2 + #define UCSI_BUF_SIZE 48 #define MSG_TYPE_REQ_RESP 1 @@ -52,6 +56,9 @@ struct ucsi_notify_ind_msg { struct pmic_glink_ucsi { struct device *dev; + struct gpio_desc *port_orientation[PMIC_GLINK_MAX_PORTS]; + struct typec_switch *port_switch[PMIC_GLINK_MAX_PORTS]; + struct pmic_glink_client *client; struct ucsi *ucsi; @@ -220,8 +227,20 @@ static void pmic_glink_ucsi_notify(struct work_struct *work) } con_num = UCSI_CCI_CONNECTOR(cci); - if (con_num) + if (con_num) { + if (con_num <= PMIC_GLINK_MAX_PORTS && + ucsi->port_orientation[con_num - 1]) { + int orientation = gpiod_get_value(ucsi->port_orientation[con_num - 1]); + + if (orientation >= 0) { + typec_switch_set(ucsi->port_switch[con_num - 1], + orientation ? TYPEC_ORIENTATION_REVERSE + : TYPEC_ORIENTATION_NORMAL); + } + } + ucsi_connector_change(ucsi->ucsi, con_num); + } if (ucsi->sync_pending && cci & UCSI_CCI_BUSY) { ucsi->sync_val = -EBUSY; @@ -282,6 +301,7 @@ static int pmic_glink_ucsi_probe(struct auxiliary_device *adev, { struct pmic_glink_ucsi *ucsi; struct device *dev = &adev->dev; + struct fwnode_handle *fwnode; int ret; ucsi = devm_kzalloc(dev, sizeof(*ucsi), GFP_KERNEL); @@ -309,6 +329,38 @@ static int pmic_glink_ucsi_probe(struct auxiliary_device *adev, ucsi_set_drvdata(ucsi->ucsi, ucsi); + device_for_each_child_node(dev, fwnode) { + struct gpio_desc *desc; + u32 port; + + ret = fwnode_property_read_u32(fwnode, "reg", &port); + if (ret < 0) { + dev_err(dev, "missing reg property of %pOFn\n", fwnode); + return ret; + } + + if (port >= PMIC_GLINK_MAX_PORTS) { + dev_warn(dev, "invalid connector number, ignoring\n"); + continue; + } + + desc = devm_gpiod_get_index_optional(&adev->dev, "orientation", port, GPIOD_IN); + + /* If GPIO isn't found, continue */ + if (!desc) + continue; + + if (IS_ERR(desc)) + return dev_err_probe(dev, PTR_ERR(desc), + "unable to acquire orientation gpio\n"); + ucsi->port_orientation[port] = desc; + + ucsi->port_switch[port] = fwnode_typec_switch_get(fwnode); + if (IS_ERR(ucsi->port_switch[port])) + return dev_err_probe(dev, PTR_ERR(ucsi->port_switch[port]), + "failed to acquire orientation-switch\n"); + } + ucsi->client = devm_pmic_glink_register_client(dev, PMIC_GLINK_OWNER_USBC, pmic_glink_ucsi_callback, diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 946488b8989f4..ca972af3c89a2 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -2795,13 +2795,18 @@ static int setup_cvq_vring(struct mlx5_vdpa_dev *mvdev) struct mlx5_control_vq *cvq = &mvdev->cvq; int err = 0; - if (mvdev->actual_features & BIT_ULL(VIRTIO_NET_F_CTRL_VQ)) + if (mvdev->actual_features & BIT_ULL(VIRTIO_NET_F_CTRL_VQ)) { + u16 idx = cvq->vring.last_avail_idx; + err = vringh_init_iotlb(&cvq->vring, mvdev->actual_features, MLX5_CVQ_MAX_ENT, false, (struct vring_desc *)(uintptr_t)cvq->desc_addr, (struct vring_avail *)(uintptr_t)cvq->driver_addr, (struct vring_used *)(uintptr_t)cvq->device_addr); + if (!err) + cvq->vring.last_avail_idx = cvq->vring.last_used_idx = idx; + } return err; } diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c b/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c index b3a3cb1657955..b137f36793439 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c @@ -437,7 +437,7 @@ static int vdpasim_blk_dev_add(struct vdpa_mgmt_dev *mdev, const char *name, if (blk->shared_backend) { blk->buffer = shared_buffer; } else { - blk->buffer = kvmalloc(VDPASIM_BLK_CAPACITY << SECTOR_SHIFT, + blk->buffer = kvzalloc(VDPASIM_BLK_CAPACITY << SECTOR_SHIFT, GFP_KERNEL); if (!blk->buffer) { ret = -ENOMEM; @@ -495,7 +495,7 @@ static int __init vdpasim_blk_init(void) goto parent_err; if (shared_backend) { - shared_buffer = kvmalloc(VDPASIM_BLK_CAPACITY << SECTOR_SHIFT, + shared_buffer = kvzalloc(VDPASIM_BLK_CAPACITY << SECTOR_SHIFT, GFP_KERNEL); if (!shared_buffer) { ret = -ENOMEM; diff --git a/drivers/vfio/pci/pds/pci_drv.c b/drivers/vfio/pci/pds/pci_drv.c index ab4b5958e4131..caffa1a2cf591 100644 --- a/drivers/vfio/pci/pds/pci_drv.c +++ b/drivers/vfio/pci/pds/pci_drv.c @@ -55,10 +55,10 @@ static void pds_vfio_recovery(struct pds_vfio_pci_device *pds_vfio) * VFIO_DEVICE_STATE_RUNNING. */ if (deferred_reset_needed) { - spin_lock(&pds_vfio->reset_lock); + mutex_lock(&pds_vfio->reset_mutex); pds_vfio->deferred_reset = true; pds_vfio->deferred_reset_state = VFIO_DEVICE_STATE_ERROR; - spin_unlock(&pds_vfio->reset_lock); + mutex_unlock(&pds_vfio->reset_mutex); } } diff --git a/drivers/vfio/pci/pds/vfio_dev.c b/drivers/vfio/pci/pds/vfio_dev.c index 649b18ee394bb..4c351c59d05a9 100644 --- a/drivers/vfio/pci/pds/vfio_dev.c +++ b/drivers/vfio/pci/pds/vfio_dev.c @@ -29,7 +29,7 @@ struct pds_vfio_pci_device *pds_vfio_pci_drvdata(struct pci_dev *pdev) void pds_vfio_state_mutex_unlock(struct pds_vfio_pci_device *pds_vfio) { again: - spin_lock(&pds_vfio->reset_lock); + mutex_lock(&pds_vfio->reset_mutex); if (pds_vfio->deferred_reset) { pds_vfio->deferred_reset = false; if (pds_vfio->state == VFIO_DEVICE_STATE_ERROR) { @@ -39,23 +39,23 @@ void pds_vfio_state_mutex_unlock(struct pds_vfio_pci_device *pds_vfio) } pds_vfio->state = pds_vfio->deferred_reset_state; pds_vfio->deferred_reset_state = VFIO_DEVICE_STATE_RUNNING; - spin_unlock(&pds_vfio->reset_lock); + mutex_unlock(&pds_vfio->reset_mutex); goto again; } mutex_unlock(&pds_vfio->state_mutex); - spin_unlock(&pds_vfio->reset_lock); + mutex_unlock(&pds_vfio->reset_mutex); } void pds_vfio_reset(struct pds_vfio_pci_device *pds_vfio) { - spin_lock(&pds_vfio->reset_lock); + mutex_lock(&pds_vfio->reset_mutex); pds_vfio->deferred_reset = true; pds_vfio->deferred_reset_state = VFIO_DEVICE_STATE_RUNNING; if (!mutex_trylock(&pds_vfio->state_mutex)) { - spin_unlock(&pds_vfio->reset_lock); + mutex_unlock(&pds_vfio->reset_mutex); return; } - spin_unlock(&pds_vfio->reset_lock); + mutex_unlock(&pds_vfio->reset_mutex); pds_vfio_state_mutex_unlock(pds_vfio); } @@ -155,6 +155,9 @@ static int pds_vfio_init_device(struct vfio_device *vdev) pds_vfio->vf_id = vf_id; + mutex_init(&pds_vfio->state_mutex); + mutex_init(&pds_vfio->reset_mutex); + vdev->migration_flags = VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_P2P; vdev->mig_ops = &pds_vfio_lm_ops; vdev->log_ops = &pds_vfio_log_ops; @@ -168,6 +171,17 @@ static int pds_vfio_init_device(struct vfio_device *vdev) return 0; } +static void pds_vfio_release_device(struct vfio_device *vdev) +{ + struct pds_vfio_pci_device *pds_vfio = + container_of(vdev, struct pds_vfio_pci_device, + vfio_coredev.vdev); + + mutex_destroy(&pds_vfio->state_mutex); + mutex_destroy(&pds_vfio->reset_mutex); + vfio_pci_core_release_dev(vdev); +} + static int pds_vfio_open_device(struct vfio_device *vdev) { struct pds_vfio_pci_device *pds_vfio = @@ -179,7 +193,6 @@ static int pds_vfio_open_device(struct vfio_device *vdev) if (err) return err; - mutex_init(&pds_vfio->state_mutex); pds_vfio->state = VFIO_DEVICE_STATE_RUNNING; pds_vfio->deferred_reset_state = VFIO_DEVICE_STATE_RUNNING; @@ -199,14 +212,13 @@ static void pds_vfio_close_device(struct vfio_device *vdev) pds_vfio_put_save_file(pds_vfio); pds_vfio_dirty_disable(pds_vfio, true); mutex_unlock(&pds_vfio->state_mutex); - mutex_destroy(&pds_vfio->state_mutex); vfio_pci_core_close_device(vdev); } static const struct vfio_device_ops pds_vfio_ops = { .name = "pds-vfio", .init = pds_vfio_init_device, - .release = vfio_pci_core_release_dev, + .release = pds_vfio_release_device, .open_device = pds_vfio_open_device, .close_device = pds_vfio_close_device, .ioctl = vfio_pci_core_ioctl, diff --git a/drivers/vfio/pci/pds/vfio_dev.h b/drivers/vfio/pci/pds/vfio_dev.h index b8f2d667608f3..e7b01080a1ec3 100644 --- a/drivers/vfio/pci/pds/vfio_dev.h +++ b/drivers/vfio/pci/pds/vfio_dev.h @@ -18,7 +18,7 @@ struct pds_vfio_pci_device { struct pds_vfio_dirty dirty; struct mutex state_mutex; /* protect migration state */ enum vfio_device_mig_state state; - spinlock_t reset_lock; /* protect reset_done flow */ + struct mutex reset_mutex; /* protect reset_done flow */ u8 deferred_reset; enum vfio_device_mig_state deferred_reset_state; struct notifier_block nb; diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 78379ffd23363..fb590e346e43d 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -1511,7 +1511,6 @@ static int vhost_vdpa_probe(struct vdpa_device *vdpa) err: put_device(&v->dev); - ida_simple_remove(&vhost_vdpa_ida, v->minor); return r; } diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 51d8f3299c105..49299b1f9ec74 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -3219,8 +3219,7 @@ void virtqueue_dma_sync_single_range_for_cpu(struct virtqueue *_vq, if (!vq->use_dma_api) return; - dma_sync_single_range_for_cpu(dev, addr, offset, size, - DMA_BIDIRECTIONAL); + dma_sync_single_range_for_cpu(dev, addr, offset, size, dir); } EXPORT_SYMBOL_GPL(virtqueue_dma_sync_single_range_for_cpu); @@ -3246,8 +3245,7 @@ void virtqueue_dma_sync_single_range_for_device(struct virtqueue *_vq, if (!vq->use_dma_api) return; - dma_sync_single_range_for_device(dev, addr, offset, size, - DMA_BIDIRECTIONAL); + dma_sync_single_range_for_device(dev, addr, offset, size, dir); } EXPORT_SYMBOL_GPL(virtqueue_dma_sync_single_range_for_device); diff --git a/drivers/watchdog/sbsa_gwdt.c b/drivers/watchdog/sbsa_gwdt.c index 421ebcda62e64..5f23913ce3b49 100644 --- a/drivers/watchdog/sbsa_gwdt.c +++ b/drivers/watchdog/sbsa_gwdt.c @@ -152,14 +152,14 @@ static int sbsa_gwdt_set_timeout(struct watchdog_device *wdd, timeout = clamp_t(unsigned int, timeout, 1, wdd->max_hw_heartbeat_ms / 1000); if (action) - sbsa_gwdt_reg_write(gwdt->clk * timeout, gwdt); + sbsa_gwdt_reg_write((u64)gwdt->clk * timeout, gwdt); else /* * In the single stage mode, The first signal (WS0) is ignored, * the timeout is (WOR * 2), so the WOR should be configured * to half value of timeout. */ - sbsa_gwdt_reg_write(gwdt->clk / 2 * timeout, gwdt); + sbsa_gwdt_reg_write(((u64)gwdt->clk / 2) * timeout, gwdt); return 0; } diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index 1b2136fe0fa51..c50419638ac0a 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -164,6 +164,8 @@ static DEFINE_PER_CPU(int [NR_VIRQS], virq_to_irq) = {[0 ... NR_VIRQS-1] = -1}; /* IRQ <-> IPI mapping */ static DEFINE_PER_CPU(int [XEN_NR_IPIS], ipi_to_irq) = {[0 ... XEN_NR_IPIS-1] = -1}; +/* Cache for IPI event channels - needed for hot cpu unplug (avoid RCU usage). */ +static DEFINE_PER_CPU(evtchn_port_t [XEN_NR_IPIS], ipi_to_evtchn) = {[0 ... XEN_NR_IPIS-1] = 0}; /* Event channel distribution data */ static atomic_t channels_on_cpu[NR_CPUS]; @@ -366,6 +368,7 @@ static int xen_irq_info_ipi_setup(unsigned cpu, info->u.ipi = ipi; per_cpu(ipi_to_irq, cpu)[ipi] = irq; + per_cpu(ipi_to_evtchn, cpu)[ipi] = evtchn; return xen_irq_info_common_setup(info, irq, IRQT_IPI, evtchn, 0); } @@ -601,7 +604,9 @@ static void lateeoi_list_add(struct irq_info *info) spin_lock_irqsave(&eoi->eoi_list_lock, flags); - if (list_empty(&eoi->eoi_list)) { + elem = list_first_entry_or_null(&eoi->eoi_list, struct irq_info, + eoi_list); + if (!elem || info->eoi_time < elem->eoi_time) { list_add(&info->eoi_list, &eoi->eoi_list); mod_delayed_work_on(info->eoi_cpu, system_wq, &eoi->delayed, delay); @@ -981,6 +986,7 @@ static void __unbind_from_irq(unsigned int irq) break; case IRQT_IPI: per_cpu(ipi_to_irq, cpu)[ipi_from_irq(irq)] = -1; + per_cpu(ipi_to_evtchn, cpu)[ipi_from_irq(irq)] = 0; break; case IRQT_EVTCHN: dev = info->u.interdomain; @@ -1631,7 +1637,7 @@ EXPORT_SYMBOL_GPL(evtchn_put); void xen_send_IPI_one(unsigned int cpu, enum ipi_vector vector) { - int irq; + evtchn_port_t evtchn; #ifdef CONFIG_X86 if (unlikely(vector == XEN_NMI_VECTOR)) { @@ -1642,9 +1648,9 @@ void xen_send_IPI_one(unsigned int cpu, enum ipi_vector vector) return; } #endif - irq = per_cpu(ipi_to_irq, cpu)[vector]; - BUG_ON(irq < 0); - notify_remote_via_irq(irq); + evtchn = per_cpu(ipi_to_evtchn, cpu)[vector]; + BUG_ON(evtchn == 0); + notify_remote_via_evtchn(evtchn); } struct evtchn_loop_ctrl { diff --git a/drivers/xen/pcpu.c b/drivers/xen/pcpu.c index b3e3d1bb37f3e..5086552731453 100644 --- a/drivers/xen/pcpu.c +++ b/drivers/xen/pcpu.c @@ -47,6 +47,9 @@ #include #include +#ifdef CONFIG_ACPI +#include +#endif /* * @cpu_id: Xen physical cpu logic number @@ -400,4 +403,23 @@ bool __init xen_processor_present(uint32_t acpi_id) return online; } + +void xen_sanitize_proc_cap_bits(uint32_t *cap) +{ + struct xen_platform_op op = { + .cmd = XENPF_set_processor_pminfo, + .u.set_pminfo.id = -1, + .u.set_pminfo.type = XEN_PM_PDC, + }; + u32 buf[3] = { ACPI_PDC_REVISION_ID, 1, *cap }; + int ret; + + set_xen_guest_handle(op.u.set_pminfo.pdc, buf); + ret = HYPERVISOR_platform_op(&op); + if (ret) + pr_err("sanitize of _PDC buffer bits from Xen failed: %d\n", + ret); + else + *cap = buf[2]; +} #endif diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index 946bd56f0ac53..0e6c6c25d154f 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -405,4 +405,5 @@ const struct dma_map_ops xen_swiotlb_dma_ops = { .get_sgtable = dma_common_get_sgtable, .alloc_pages = dma_common_alloc_pages, .free_pages = dma_common_free_pages, + .max_mapping_size = swiotlb_max_mapping_size, }; diff --git a/fs/9p/xattr.c b/fs/9p/xattr.c index e00cf8109b3f3..3c4572ef3a488 100644 --- a/fs/9p/xattr.c +++ b/fs/9p/xattr.c @@ -68,7 +68,7 @@ ssize_t v9fs_xattr_get(struct dentry *dentry, const char *name, struct p9_fid *fid; int ret; - p9_debug(P9_DEBUG_VFS, "name = %s value_len = %zu\n", + p9_debug(P9_DEBUG_VFS, "name = '%s' value_len = %zu\n", name, buffer_size); fid = v9fs_fid_lookup(dentry); if (IS_ERR(fid)) @@ -139,7 +139,8 @@ int v9fs_fid_xattr_set(struct p9_fid *fid, const char *name, ssize_t v9fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) { - return v9fs_xattr_get(dentry, NULL, buffer, buffer_size); + /* Txattrwalk with an empty string lists xattrs instead */ + return v9fs_xattr_get(dentry, "", buffer, buffer_size); } static int v9fs_xattr_handler_get(const struct xattr_handler *handler, diff --git a/fs/afs/cell.c b/fs/afs/cell.c index 988c2ac7cecec..926cb1188eba6 100644 --- a/fs/afs/cell.c +++ b/fs/afs/cell.c @@ -409,10 +409,12 @@ static int afs_update_cell(struct afs_cell *cell) if (ret == -ENOMEM) goto out_wake; - ret = -ENOMEM; vllist = afs_alloc_vlserver_list(0); - if (!vllist) + if (!vllist) { + if (ret >= 0) + ret = -ENOMEM; goto out_wake; + } switch (ret) { case -ENODATA: diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c index 95bcbd7654d1b..10905a53d5b27 100644 --- a/fs/afs/dynroot.c +++ b/fs/afs/dynroot.c @@ -114,6 +114,7 @@ static int afs_probe_cell_name(struct dentry *dentry) struct afs_net *net = afs_d2net(dentry); const char *name = dentry->d_name.name; size_t len = dentry->d_name.len; + char *result = NULL; int ret; /* Names prefixed with a dot are R/W mounts. */ @@ -131,9 +132,22 @@ static int afs_probe_cell_name(struct dentry *dentry) } ret = dns_query(net->net, "afsdb", name, len, "srv=1", - NULL, NULL, false); - if (ret == -ENODATA) - ret = -EDESTADDRREQ; + &result, NULL, false); + if (ret == -ENODATA || ret == -ENOKEY || ret == 0) + ret = -ENOENT; + if (ret > 0 && ret >= sizeof(struct dns_server_list_v1_header)) { + struct dns_server_list_v1_header *v1 = (void *)result; + + if (v1->hdr.zero == 0 && + v1->hdr.content == DNS_PAYLOAD_IS_SERVER_LIST && + v1->hdr.version == 1 && + (v1->status != DNS_LOOKUP_GOOD && + v1->status != DNS_LOOKUP_GOOD_WITH_BAD)) + return -ENOENT; + + } + + kfree(result); return ret; } @@ -252,20 +266,9 @@ static int afs_dynroot_d_revalidate(struct dentry *dentry, unsigned int flags) return 1; } -/* - * Allow the VFS to enquire as to whether a dentry should be unhashed (mustn't - * sleep) - * - called from dput() when d_count is going to 0. - * - return 1 to request dentry be unhashed, 0 otherwise - */ -static int afs_dynroot_d_delete(const struct dentry *dentry) -{ - return d_really_is_positive(dentry); -} - const struct dentry_operations afs_dynroot_dentry_operations = { .d_revalidate = afs_dynroot_d_revalidate, - .d_delete = afs_dynroot_d_delete, + .d_delete = always_delete_dentry, .d_release = afs_d_release, .d_automount = afs_d_automount, }; diff --git a/fs/afs/internal.h b/fs/afs/internal.h index da73b97e19a9a..c4bf8439bc9c9 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -553,6 +553,7 @@ struct afs_server_entry { }; struct afs_server_list { + struct rcu_head rcu; afs_volid_t vids[AFS_MAXTYPES]; /* Volume IDs */ refcount_t usage; unsigned char nr_servers; @@ -585,6 +586,7 @@ struct afs_volume { #define AFS_VOLUME_OFFLINE 4 /* - T if volume offline notice given */ #define AFS_VOLUME_BUSY 5 /* - T if volume busy notice given */ #define AFS_VOLUME_MAYBE_NO_IBULK 6 /* - T if some servers don't have InlineBulkStatus */ +#define AFS_VOLUME_RM_TREE 7 /* - Set if volume removed from cell->volumes */ #ifdef CONFIG_AFS_FSCACHE struct fscache_volume *cache; /* Caching cookie */ #endif @@ -1512,6 +1514,7 @@ extern struct afs_vlserver_list *afs_extract_vlserver_list(struct afs_cell *, extern struct afs_volume *afs_create_volume(struct afs_fs_context *); extern int afs_activate_volume(struct afs_volume *); extern void afs_deactivate_volume(struct afs_volume *); +bool afs_try_get_volume(struct afs_volume *volume, enum afs_volume_trace reason); extern struct afs_volume *afs_get_volume(struct afs_volume *, enum afs_volume_trace); extern void afs_put_volume(struct afs_net *, struct afs_volume *, enum afs_volume_trace); extern int afs_check_volume_status(struct afs_volume *, struct afs_operation *); diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index ed1644e7683f4..d642d06a453be 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -424,7 +424,7 @@ void afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, gfp_t gfp) if (call->async) { if (cancel_work_sync(&call->async_work)) afs_put_call(call); - afs_put_call(call); + afs_set_call_complete(call, ret, 0); } ac->error = ret; diff --git a/fs/afs/server_list.c b/fs/afs/server_list.c index ed9056703505f..b59896b1de0af 100644 --- a/fs/afs/server_list.c +++ b/fs/afs/server_list.c @@ -17,7 +17,7 @@ void afs_put_serverlist(struct afs_net *net, struct afs_server_list *slist) for (i = 0; i < slist->nr_servers; i++) afs_unuse_server(net, slist->servers[i].server, afs_server_trace_put_slist); - kfree(slist); + kfree_rcu(slist, rcu); } } diff --git a/fs/afs/super.c b/fs/afs/super.c index 95d713074dc81..e95fb4cb4fcd2 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -407,6 +407,8 @@ static int afs_validate_fc(struct fs_context *fc) return PTR_ERR(volume); ctx->volume = volume; + if (volume->type != AFSVL_RWVOL) + ctx->flock_mode = afs_flock_mode_local; } return 0; diff --git a/fs/afs/vl_rotate.c b/fs/afs/vl_rotate.c index 488e58490b16e..eb415ce563600 100644 --- a/fs/afs/vl_rotate.c +++ b/fs/afs/vl_rotate.c @@ -58,6 +58,12 @@ static bool afs_start_vl_iteration(struct afs_vl_cursor *vc) } /* Status load is ordered after lookup counter load */ + if (cell->dns_status == DNS_LOOKUP_GOT_NOT_FOUND) { + pr_warn("No record of cell %s\n", cell->name); + vc->error = -ENOENT; + return false; + } + if (cell->dns_source == DNS_RECORD_UNAVAILABLE) { vc->error = -EDESTADDRREQ; return false; @@ -285,6 +291,7 @@ bool afs_select_vlserver(struct afs_vl_cursor *vc) */ static void afs_vl_dump_edestaddrreq(const struct afs_vl_cursor *vc) { + struct afs_cell *cell = vc->cell; static int count; int i; @@ -294,6 +301,9 @@ static void afs_vl_dump_edestaddrreq(const struct afs_vl_cursor *vc) rcu_read_lock(); pr_notice("EDESTADDR occurred\n"); + pr_notice("CELL: %s err=%d\n", cell->name, cell->error); + pr_notice("DNS: src=%u st=%u lc=%x\n", + cell->dns_source, cell->dns_status, cell->dns_lookup_count); pr_notice("VC: ut=%lx ix=%u ni=%hu fl=%hx err=%hd\n", vc->untried, vc->index, vc->nr_iterations, vc->flags, vc->error); diff --git a/fs/afs/volume.c b/fs/afs/volume.c index 29d483c802813..115c081a8e2ce 100644 --- a/fs/afs/volume.c +++ b/fs/afs/volume.c @@ -32,8 +32,13 @@ static struct afs_volume *afs_insert_volume_into_cell(struct afs_cell *cell, } else if (p->vid > volume->vid) { pp = &(*pp)->rb_right; } else { - volume = afs_get_volume(p, afs_volume_trace_get_cell_insert); - goto found; + if (afs_try_get_volume(p, afs_volume_trace_get_cell_insert)) { + volume = p; + goto found; + } + + set_bit(AFS_VOLUME_RM_TREE, &volume->flags); + rb_replace_node_rcu(&p->cell_node, &volume->cell_node, &cell->volumes); } } @@ -56,7 +61,8 @@ static void afs_remove_volume_from_cell(struct afs_volume *volume) afs_volume_trace_remove); write_seqlock(&cell->volume_lock); hlist_del_rcu(&volume->proc_link); - rb_erase(&volume->cell_node, &cell->volumes); + if (!test_and_set_bit(AFS_VOLUME_RM_TREE, &volume->flags)) + rb_erase(&volume->cell_node, &cell->volumes); write_sequnlock(&cell->volume_lock); } } @@ -231,6 +237,20 @@ static void afs_destroy_volume(struct afs_net *net, struct afs_volume *volume) _leave(" [destroyed]"); } +/* + * Try to get a reference on a volume record. + */ +bool afs_try_get_volume(struct afs_volume *volume, enum afs_volume_trace reason) +{ + int r; + + if (__refcount_inc_not_zero(&volume->ref, &r)) { + trace_afs_volume(volume->vid, r + 1, reason); + return true; + } + return false; +} + /* * Get a reference on a volume record. */ diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index b2e5107b7cecc..5a97db9888107 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -2601,7 +2601,7 @@ static int insert_dev_extent(struct btrfs_trans_handle *trans, btrfs_set_dev_extent_chunk_offset(leaf, extent, chunk_offset); btrfs_set_dev_extent_length(leaf, extent, num_bytes); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); out: btrfs_free_path(path); return ret; @@ -3025,7 +3025,7 @@ static int update_block_group_item(struct btrfs_trans_handle *trans, cache->global_root_id); btrfs_set_stack_block_group_flags(&bgi, cache->flags); write_extent_buffer(leaf, &bgi, bi, sizeof(bgi)); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); fail: btrfs_release_path(path); /* diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 617d4827eec26..118ad4d2cbbe2 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -359,7 +359,7 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans, return ret; } - btrfs_mark_buffer_dirty(cow); + btrfs_mark_buffer_dirty(trans, cow); *cow_ret = cow; return 0; } @@ -627,7 +627,7 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, cow->start); btrfs_set_node_ptr_generation(parent, parent_slot, trans->transid); - btrfs_mark_buffer_dirty(parent); + btrfs_mark_buffer_dirty(trans, parent); if (last_ref) { ret = btrfs_tree_mod_log_free_eb(buf); if (ret) { @@ -643,7 +643,7 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, if (unlock_orig) btrfs_tree_unlock(buf); free_extent_buffer_stale(buf); - btrfs_mark_buffer_dirty(cow); + btrfs_mark_buffer_dirty(trans, cow); *cow_ret = cow; return 0; } @@ -1197,7 +1197,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, goto out; } btrfs_set_node_key(parent, &right_key, pslot + 1); - btrfs_mark_buffer_dirty(parent); + btrfs_mark_buffer_dirty(trans, parent); } } if (btrfs_header_nritems(mid) == 1) { @@ -1255,7 +1255,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, goto out; } btrfs_set_node_key(parent, &mid_key, pslot); - btrfs_mark_buffer_dirty(parent); + btrfs_mark_buffer_dirty(trans, parent); } /* update the path */ @@ -1362,7 +1362,7 @@ static noinline int push_nodes_for_insert(struct btrfs_trans_handle *trans, return ret; } btrfs_set_node_key(parent, &disk_key, pslot); - btrfs_mark_buffer_dirty(parent); + btrfs_mark_buffer_dirty(trans, parent); if (btrfs_header_nritems(left) > orig_slot) { path->nodes[level] = left; path->slots[level + 1] -= 1; @@ -1422,7 +1422,7 @@ static noinline int push_nodes_for_insert(struct btrfs_trans_handle *trans, return ret; } btrfs_set_node_key(parent, &disk_key, pslot + 1); - btrfs_mark_buffer_dirty(parent); + btrfs_mark_buffer_dirty(trans, parent); if (btrfs_header_nritems(mid) <= orig_slot) { path->nodes[level] = right; @@ -2678,7 +2678,8 @@ int btrfs_get_next_valid_item(struct btrfs_root *root, struct btrfs_key *key, * higher levels * */ -static void fixup_low_keys(struct btrfs_path *path, +static void fixup_low_keys(struct btrfs_trans_handle *trans, + struct btrfs_path *path, struct btrfs_disk_key *key, int level) { int i; @@ -2695,7 +2696,7 @@ static void fixup_low_keys(struct btrfs_path *path, BTRFS_MOD_LOG_KEY_REPLACE); BUG_ON(ret < 0); btrfs_set_node_key(t, key, tslot); - btrfs_mark_buffer_dirty(path->nodes[i]); + btrfs_mark_buffer_dirty(trans, path->nodes[i]); if (tslot != 0) break; } @@ -2707,10 +2708,11 @@ static void fixup_low_keys(struct btrfs_path *path, * This function isn't completely safe. It's the caller's responsibility * that the new key won't break the order */ -void btrfs_set_item_key_safe(struct btrfs_fs_info *fs_info, +void btrfs_set_item_key_safe(struct btrfs_trans_handle *trans, struct btrfs_path *path, const struct btrfs_key *new_key) { + struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_disk_key disk_key; struct extent_buffer *eb; int slot; @@ -2748,9 +2750,9 @@ void btrfs_set_item_key_safe(struct btrfs_fs_info *fs_info, btrfs_cpu_key_to_disk(&disk_key, new_key); btrfs_set_item_key(eb, &disk_key, slot); - btrfs_mark_buffer_dirty(eb); + btrfs_mark_buffer_dirty(trans, eb); if (slot == 0) - fixup_low_keys(path, &disk_key, 1); + fixup_low_keys(trans, path, &disk_key, 1); } /* @@ -2881,8 +2883,8 @@ static int push_node_left(struct btrfs_trans_handle *trans, } btrfs_set_header_nritems(src, src_nritems - push_items); btrfs_set_header_nritems(dst, dst_nritems + push_items); - btrfs_mark_buffer_dirty(src); - btrfs_mark_buffer_dirty(dst); + btrfs_mark_buffer_dirty(trans, src); + btrfs_mark_buffer_dirty(trans, dst); return ret; } @@ -2957,8 +2959,8 @@ static int balance_node_right(struct btrfs_trans_handle *trans, btrfs_set_header_nritems(src, src_nritems - push_items); btrfs_set_header_nritems(dst, dst_nritems + push_items); - btrfs_mark_buffer_dirty(src); - btrfs_mark_buffer_dirty(dst); + btrfs_mark_buffer_dirty(trans, src); + btrfs_mark_buffer_dirty(trans, dst); return ret; } @@ -3007,7 +3009,7 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans, btrfs_set_node_ptr_generation(c, 0, lower_gen); - btrfs_mark_buffer_dirty(c); + btrfs_mark_buffer_dirty(trans, c); old = root->node; ret = btrfs_tree_mod_log_insert_root(root->node, c, false); @@ -3079,7 +3081,7 @@ static int insert_ptr(struct btrfs_trans_handle *trans, WARN_ON(trans->transid == 0); btrfs_set_node_ptr_generation(lower, slot, trans->transid); btrfs_set_header_nritems(lower, nritems + 1); - btrfs_mark_buffer_dirty(lower); + btrfs_mark_buffer_dirty(trans, lower); return 0; } @@ -3158,8 +3160,8 @@ static noinline int split_node(struct btrfs_trans_handle *trans, btrfs_set_header_nritems(split, c_nritems - mid); btrfs_set_header_nritems(c, mid); - btrfs_mark_buffer_dirty(c); - btrfs_mark_buffer_dirty(split); + btrfs_mark_buffer_dirty(trans, c); + btrfs_mark_buffer_dirty(trans, split); ret = insert_ptr(trans, path, &disk_key, split->start, path->slots[level + 1] + 1, level + 1); @@ -3325,15 +3327,15 @@ static noinline int __push_leaf_right(struct btrfs_trans_handle *trans, btrfs_set_header_nritems(left, left_nritems); if (left_nritems) - btrfs_mark_buffer_dirty(left); + btrfs_mark_buffer_dirty(trans, left); else btrfs_clear_buffer_dirty(trans, left); - btrfs_mark_buffer_dirty(right); + btrfs_mark_buffer_dirty(trans, right); btrfs_item_key(right, &disk_key, 0); btrfs_set_node_key(upper, &disk_key, slot + 1); - btrfs_mark_buffer_dirty(upper); + btrfs_mark_buffer_dirty(trans, upper); /* then fixup the leaf pointer in the path */ if (path->slots[0] >= left_nritems) { @@ -3545,14 +3547,14 @@ static noinline int __push_leaf_left(struct btrfs_trans_handle *trans, btrfs_set_token_item_offset(&token, i, push_space); } - btrfs_mark_buffer_dirty(left); + btrfs_mark_buffer_dirty(trans, left); if (right_nritems) - btrfs_mark_buffer_dirty(right); + btrfs_mark_buffer_dirty(trans, right); else btrfs_clear_buffer_dirty(trans, right); btrfs_item_key(right, &disk_key, 0); - fixup_low_keys(path, &disk_key, 1); + fixup_low_keys(trans, path, &disk_key, 1); /* then fixup the leaf pointer in the path */ if (path->slots[0] < push_items) { @@ -3683,8 +3685,8 @@ static noinline int copy_for_split(struct btrfs_trans_handle *trans, if (ret < 0) return ret; - btrfs_mark_buffer_dirty(right); - btrfs_mark_buffer_dirty(l); + btrfs_mark_buffer_dirty(trans, right); + btrfs_mark_buffer_dirty(trans, l); BUG_ON(path->slots[0] != slot); if (mid <= slot) { @@ -3925,7 +3927,7 @@ static noinline int split_leaf(struct btrfs_trans_handle *trans, path->nodes[0] = right; path->slots[0] = 0; if (path->slots[1] == 0) - fixup_low_keys(path, &disk_key, 1); + fixup_low_keys(trans, path, &disk_key, 1); } /* * We create a new leaf 'right' for the required ins_len and @@ -4024,7 +4026,8 @@ static noinline int setup_leaf_for_split(struct btrfs_trans_handle *trans, return ret; } -static noinline int split_item(struct btrfs_path *path, +static noinline int split_item(struct btrfs_trans_handle *trans, + struct btrfs_path *path, const struct btrfs_key *new_key, unsigned long split_offset) { @@ -4083,7 +4086,7 @@ static noinline int split_item(struct btrfs_path *path, write_extent_buffer(leaf, buf + split_offset, btrfs_item_ptr_offset(leaf, slot), item_size - split_offset); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); BUG_ON(btrfs_leaf_free_space(leaf) < 0); kfree(buf); @@ -4117,7 +4120,7 @@ int btrfs_split_item(struct btrfs_trans_handle *trans, if (ret) return ret; - ret = split_item(path, new_key, split_offset); + ret = split_item(trans, path, new_key, split_offset); return ret; } @@ -4127,7 +4130,8 @@ int btrfs_split_item(struct btrfs_trans_handle *trans, * off the end of the item or if we shift the item to chop bytes off * the front. */ -void btrfs_truncate_item(struct btrfs_path *path, u32 new_size, int from_end) +void btrfs_truncate_item(struct btrfs_trans_handle *trans, + struct btrfs_path *path, u32 new_size, int from_end) { int slot; struct extent_buffer *leaf; @@ -4203,11 +4207,11 @@ void btrfs_truncate_item(struct btrfs_path *path, u32 new_size, int from_end) btrfs_set_disk_key_offset(&disk_key, offset + size_diff); btrfs_set_item_key(leaf, &disk_key, slot); if (slot == 0) - fixup_low_keys(path, &disk_key, 1); + fixup_low_keys(trans, path, &disk_key, 1); } btrfs_set_item_size(leaf, slot, new_size); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); if (btrfs_leaf_free_space(leaf) < 0) { btrfs_print_leaf(leaf); @@ -4218,7 +4222,8 @@ void btrfs_truncate_item(struct btrfs_path *path, u32 new_size, int from_end) /* * make the item pointed to by the path bigger, data_size is the added size. */ -void btrfs_extend_item(struct btrfs_path *path, u32 data_size) +void btrfs_extend_item(struct btrfs_trans_handle *trans, + struct btrfs_path *path, u32 data_size) { int slot; struct extent_buffer *leaf; @@ -4268,7 +4273,7 @@ void btrfs_extend_item(struct btrfs_path *path, u32 data_size) data_end = old_data; old_size = btrfs_item_size(leaf, slot); btrfs_set_item_size(leaf, slot, old_size + data_size); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); if (btrfs_leaf_free_space(leaf) < 0) { btrfs_print_leaf(leaf); @@ -4279,6 +4284,7 @@ void btrfs_extend_item(struct btrfs_path *path, u32 data_size) /* * Make space in the node before inserting one or more items. * + * @trans: transaction handle * @root: root we are inserting items to * @path: points to the leaf/slot where we are going to insert new items * @batch: information about the batch of items to insert @@ -4286,7 +4292,8 @@ void btrfs_extend_item(struct btrfs_path *path, u32 data_size) * Main purpose is to save stack depth by doing the bulk of the work in a * function that doesn't call btrfs_search_slot */ -static void setup_items_for_insert(struct btrfs_root *root, struct btrfs_path *path, +static void setup_items_for_insert(struct btrfs_trans_handle *trans, + struct btrfs_root *root, struct btrfs_path *path, const struct btrfs_item_batch *batch) { struct btrfs_fs_info *fs_info = root->fs_info; @@ -4306,7 +4313,7 @@ static void setup_items_for_insert(struct btrfs_root *root, struct btrfs_path *p */ if (path->slots[0] == 0) { btrfs_cpu_key_to_disk(&disk_key, &batch->keys[0]); - fixup_low_keys(path, &disk_key, 1); + fixup_low_keys(trans, path, &disk_key, 1); } btrfs_unlock_up_safe(path, 1); @@ -4365,7 +4372,7 @@ static void setup_items_for_insert(struct btrfs_root *root, struct btrfs_path *p } btrfs_set_header_nritems(leaf, nritems + batch->nr); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); if (btrfs_leaf_free_space(leaf) < 0) { btrfs_print_leaf(leaf); @@ -4376,12 +4383,14 @@ static void setup_items_for_insert(struct btrfs_root *root, struct btrfs_path *p /* * Insert a new item into a leaf. * + * @trans: Transaction handle. * @root: The root of the btree. * @path: A path pointing to the target leaf and slot. * @key: The key of the new item. * @data_size: The size of the data associated with the new key. */ -void btrfs_setup_item_for_insert(struct btrfs_root *root, +void btrfs_setup_item_for_insert(struct btrfs_trans_handle *trans, + struct btrfs_root *root, struct btrfs_path *path, const struct btrfs_key *key, u32 data_size) @@ -4393,7 +4402,7 @@ void btrfs_setup_item_for_insert(struct btrfs_root *root, batch.total_data_size = data_size; batch.nr = 1; - setup_items_for_insert(root, path, &batch); + setup_items_for_insert(trans, root, path, &batch); } /* @@ -4419,7 +4428,7 @@ int btrfs_insert_empty_items(struct btrfs_trans_handle *trans, slot = path->slots[0]; BUG_ON(slot < 0); - setup_items_for_insert(root, path, batch); + setup_items_for_insert(trans, root, path, batch); return 0; } @@ -4444,7 +4453,7 @@ int btrfs_insert_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, leaf = path->nodes[0]; ptr = btrfs_item_ptr_offset(leaf, path->slots[0]); write_extent_buffer(leaf, data, ptr, data_size); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); } btrfs_free_path(path); return ret; @@ -4475,7 +4484,7 @@ int btrfs_duplicate_item(struct btrfs_trans_handle *trans, return ret; path->slots[0]++; - btrfs_setup_item_for_insert(root, path, new_key, item_size); + btrfs_setup_item_for_insert(trans, root, path, new_key, item_size); leaf = path->nodes[0]; memcpy_extent_buffer(leaf, btrfs_item_ptr_offset(leaf, path->slots[0]), @@ -4533,9 +4542,9 @@ int btrfs_del_ptr(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_disk_key disk_key; btrfs_node_key(parent, &disk_key, 0); - fixup_low_keys(path, &disk_key, level + 1); + fixup_low_keys(trans, path, &disk_key, level + 1); } - btrfs_mark_buffer_dirty(parent); + btrfs_mark_buffer_dirty(trans, parent); return 0; } @@ -4632,7 +4641,7 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_disk_key disk_key; btrfs_item_key(leaf, &disk_key, 0); - fixup_low_keys(path, &disk_key, 1); + fixup_low_keys(trans, path, &disk_key, 1); } /* @@ -4697,11 +4706,11 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, * dirtied this buffer */ if (path->nodes[0] == leaf) - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); free_extent_buffer(leaf); } } else { - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); } } return ret; diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index ff40acd63a374..06333a74d6c4c 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -518,7 +518,7 @@ int btrfs_previous_item(struct btrfs_root *root, int type); int btrfs_previous_extent_item(struct btrfs_root *root, struct btrfs_path *path, u64 min_objectid); -void btrfs_set_item_key_safe(struct btrfs_fs_info *fs_info, +void btrfs_set_item_key_safe(struct btrfs_trans_handle *trans, struct btrfs_path *path, const struct btrfs_key *new_key); struct extent_buffer *btrfs_root_node(struct btrfs_root *root); @@ -545,8 +545,10 @@ int btrfs_block_can_be_shared(struct btrfs_trans_handle *trans, struct extent_buffer *buf); int btrfs_del_ptr(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, int level, int slot); -void btrfs_extend_item(struct btrfs_path *path, u32 data_size); -void btrfs_truncate_item(struct btrfs_path *path, u32 new_size, int from_end); +void btrfs_extend_item(struct btrfs_trans_handle *trans, + struct btrfs_path *path, u32 data_size); +void btrfs_truncate_item(struct btrfs_trans_handle *trans, + struct btrfs_path *path, u32 new_size, int from_end); int btrfs_split_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, @@ -610,7 +612,8 @@ struct btrfs_item_batch { int nr; }; -void btrfs_setup_item_for_insert(struct btrfs_root *root, +void btrfs_setup_item_for_insert(struct btrfs_trans_handle *trans, + struct btrfs_root *root, struct btrfs_path *path, const struct btrfs_key *key, u32 data_size); diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c index 427abaf608b8c..eef341bbcc60e 100644 --- a/fs/btrfs/delalloc-space.c +++ b/fs/btrfs/delalloc-space.c @@ -199,7 +199,7 @@ void btrfs_free_reserved_data_space(struct btrfs_inode *inode, start = round_down(start, fs_info->sectorsize); btrfs_free_reserved_data_space_noquota(fs_info, len); - btrfs_qgroup_free_data(inode, reserved, start, len); + btrfs_qgroup_free_data(inode, reserved, start, len, NULL); } /* @@ -322,9 +322,6 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes, } else { if (current->journal_info) flush = BTRFS_RESERVE_FLUSH_LIMIT; - - if (btrfs_transaction_in_commit(fs_info)) - schedule_timeout(1); } num_bytes = ALIGN(num_bytes, fs_info->sectorsize); diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 90aaedce1548a..16f9e5f474cca 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1030,7 +1030,7 @@ static int __btrfs_update_delayed_inode(struct btrfs_trans_handle *trans, struct btrfs_inode_item); write_extent_buffer(leaf, &node->inode_item, (unsigned long)inode_item, sizeof(struct btrfs_inode_item)); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); if (!test_bit(BTRFS_DELAYED_NODE_DEL_IREF, &node->flags)) goto out; diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index fff22ed55c428..fe6ba17a05099 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -442,7 +442,7 @@ int btrfs_run_dev_replace(struct btrfs_trans_handle *trans) dev_replace->item_needs_writeback = 0; up_write(&dev_replace->rwsem); - btrfs_mark_buffer_dirty(eb); + btrfs_mark_buffer_dirty(trans, eb); out: btrfs_free_path(path); diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c index 082eb0e195981..9c07d5c3e5ad2 100644 --- a/fs/btrfs/dir-item.c +++ b/fs/btrfs/dir-item.c @@ -38,7 +38,7 @@ static struct btrfs_dir_item *insert_with_overflow(struct btrfs_trans_handle di = btrfs_match_dir_item_name(fs_info, path, name, name_len); if (di) return ERR_PTR(-EEXIST); - btrfs_extend_item(path, data_size); + btrfs_extend_item(trans, path, data_size); } else if (ret < 0) return ERR_PTR(ret); WARN_ON(ret > 0); @@ -93,7 +93,7 @@ int btrfs_insert_xattr_item(struct btrfs_trans_handle *trans, write_extent_buffer(leaf, name, name_ptr, name_len); write_extent_buffer(leaf, data, data_ptr, data_len); - btrfs_mark_buffer_dirty(path->nodes[0]); + btrfs_mark_buffer_dirty(trans, path->nodes[0]); return ret; } @@ -153,7 +153,7 @@ int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, name_ptr = (unsigned long)(dir_item + 1); write_extent_buffer(leaf, name->name, name_ptr, name->len); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); second_insert: /* FIXME, use some real flag for selecting the extra index */ @@ -439,7 +439,7 @@ int btrfs_delete_one_dir_name(struct btrfs_trans_handle *trans, start = btrfs_item_ptr_offset(leaf, path->slots[0]); memmove_extent_buffer(leaf, ptr, ptr + sub_item_len, item_len - (ptr + sub_item_len - start)); - btrfs_truncate_item(path, item_len - sub_item_len, 1); + btrfs_truncate_item(trans, path, item_len - sub_item_len, 1); } return ret; } diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 68f60d50e1fd0..b79781df70714 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -867,7 +867,7 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans, } root->node = leaf; - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); root->commit_root = btrfs_root_node(root); set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); @@ -942,7 +942,7 @@ int btrfs_alloc_log_tree_node(struct btrfs_trans_handle *trans, root->node = leaf; - btrfs_mark_buffer_dirty(root->node); + btrfs_mark_buffer_dirty(trans, root->node); btrfs_tree_unlock(root->node); return 0; @@ -3197,6 +3197,7 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device goto fail_alloc; } + btrfs_info(fs_info, "first mount of filesystem %pU", disk_super->fsid); /* * Verify the type first, if that or the checksum value are * corrupted, we'll find out @@ -4423,7 +4424,8 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) btrfs_close_devices(fs_info->fs_devices); } -void btrfs_mark_buffer_dirty(struct extent_buffer *buf) +void btrfs_mark_buffer_dirty(struct btrfs_trans_handle *trans, + struct extent_buffer *buf) { struct btrfs_fs_info *fs_info = buf->fs_info; u64 transid = btrfs_header_generation(buf); @@ -4437,10 +4439,14 @@ void btrfs_mark_buffer_dirty(struct extent_buffer *buf) if (unlikely(test_bit(EXTENT_BUFFER_UNMAPPED, &buf->bflags))) return; #endif + /* This is an active transaction (its state < TRANS_STATE_UNBLOCKED). */ + ASSERT(trans->transid == fs_info->generation); btrfs_assert_tree_write_locked(buf); - if (transid != fs_info->generation) + if (transid != fs_info->generation) { WARN(1, KERN_CRIT "btrfs transid mismatch buffer %llu, found %llu running %llu\n", buf->start, transid, fs_info->generation); + btrfs_abort_transaction(trans, -EUCLEAN); + } set_extent_buffer_dirty(buf); #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY /* @@ -4830,6 +4836,32 @@ void btrfs_cleanup_dirty_bgs(struct btrfs_transaction *cur_trans, } } +static void btrfs_free_all_qgroup_pertrans(struct btrfs_fs_info *fs_info) +{ + struct btrfs_root *gang[8]; + int i; + int ret; + + spin_lock(&fs_info->fs_roots_radix_lock); + while (1) { + ret = radix_tree_gang_lookup_tag(&fs_info->fs_roots_radix, + (void **)gang, 0, + ARRAY_SIZE(gang), + BTRFS_ROOT_TRANS_TAG); + if (ret == 0) + break; + for (i = 0; i < ret; i++) { + struct btrfs_root *root = gang[i]; + + btrfs_qgroup_free_meta_all_pertrans(root); + radix_tree_tag_clear(&fs_info->fs_roots_radix, + (unsigned long)root->root_key.objectid, + BTRFS_ROOT_TRANS_TAG); + } + } + spin_unlock(&fs_info->fs_roots_radix_lock); +} + void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans, struct btrfs_fs_info *fs_info) { @@ -4858,6 +4890,8 @@ void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans, EXTENT_DIRTY); btrfs_destroy_pinned_extent(fs_info, &cur_trans->pinned_extents); + btrfs_free_all_qgroup_pertrans(fs_info); + cur_trans->state =TRANS_STATE_COMPLETED; wake_up(&cur_trans->commit_wait); } diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index 02b645744a822..50dab8f639dcc 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -104,7 +104,8 @@ static inline struct btrfs_root *btrfs_grab_root(struct btrfs_root *root) } void btrfs_put_root(struct btrfs_root *root); -void btrfs_mark_buffer_dirty(struct extent_buffer *buf); +void btrfs_mark_buffer_dirty(struct btrfs_trans_handle *trans, + struct extent_buffer *buf); int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid, int atomic); int btrfs_read_extent_buffer(struct extent_buffer *buf, diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index fc313fce5bbdc..91fe57e87583c 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -575,7 +575,7 @@ static noinline int insert_extent_data_ref(struct btrfs_trans_handle *trans, btrfs_set_extent_data_ref_count(leaf, ref, num_refs); } } - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); ret = 0; fail: btrfs_release_path(path); @@ -623,7 +623,7 @@ static noinline int remove_extent_data_ref(struct btrfs_trans_handle *trans, btrfs_set_extent_data_ref_count(leaf, ref1, num_refs); else if (key.type == BTRFS_SHARED_DATA_REF_KEY) btrfs_set_shared_data_ref_count(leaf, ref2, num_refs); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); } return ret; } @@ -976,7 +976,7 @@ int lookup_inline_extent_backref(struct btrfs_trans_handle *trans, * helper to add new inline back ref */ static noinline_for_stack -void setup_inline_extent_backref(struct btrfs_fs_info *fs_info, +void setup_inline_extent_backref(struct btrfs_trans_handle *trans, struct btrfs_path *path, struct btrfs_extent_inline_ref *iref, u64 parent, u64 root_objectid, @@ -999,7 +999,7 @@ void setup_inline_extent_backref(struct btrfs_fs_info *fs_info, type = extent_ref_type(parent, owner); size = btrfs_extent_inline_ref_size(type); - btrfs_extend_item(path, size); + btrfs_extend_item(trans, path, size); ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item); refs = btrfs_extent_refs(leaf, ei); @@ -1033,7 +1033,7 @@ void setup_inline_extent_backref(struct btrfs_fs_info *fs_info, } else { btrfs_set_extent_inline_ref_offset(leaf, iref, root_objectid); } - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); } static int lookup_extent_backref(struct btrfs_trans_handle *trans, @@ -1066,7 +1066,9 @@ static int lookup_extent_backref(struct btrfs_trans_handle *trans, /* * helper to update/remove inline back ref */ -static noinline_for_stack int update_inline_extent_backref(struct btrfs_path *path, +static noinline_for_stack int update_inline_extent_backref( + struct btrfs_trans_handle *trans, + struct btrfs_path *path, struct btrfs_extent_inline_ref *iref, int refs_to_mod, struct btrfs_delayed_extent_op *extent_op) @@ -1174,9 +1176,9 @@ static noinline_for_stack int update_inline_extent_backref(struct btrfs_path *pa memmove_extent_buffer(leaf, ptr, ptr + size, end - ptr - size); item_size -= size; - btrfs_truncate_item(path, item_size, 1); + btrfs_truncate_item(trans, path, item_size, 1); } - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); return 0; } @@ -1206,9 +1208,10 @@ int insert_inline_extent_backref(struct btrfs_trans_handle *trans, bytenr, num_bytes, root_objectid, path->slots[0]); return -EUCLEAN; } - ret = update_inline_extent_backref(path, iref, refs_to_add, extent_op); + ret = update_inline_extent_backref(trans, path, iref, + refs_to_add, extent_op); } else if (ret == -ENOENT) { - setup_inline_extent_backref(trans->fs_info, path, iref, parent, + setup_inline_extent_backref(trans, path, iref, parent, root_objectid, owner, offset, refs_to_add, extent_op); ret = 0; @@ -1226,7 +1229,8 @@ static int remove_extent_backref(struct btrfs_trans_handle *trans, BUG_ON(!is_data && refs_to_drop != 1); if (iref) - ret = update_inline_extent_backref(path, iref, -refs_to_drop, NULL); + ret = update_inline_extent_backref(trans, path, iref, + -refs_to_drop, NULL); else if (is_data) ret = remove_extent_data_ref(trans, root, path, refs_to_drop); else @@ -1510,7 +1514,7 @@ static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, if (extent_op) __run_delayed_extent_op(extent_op, leaf, item); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); btrfs_release_path(path); /* now insert the actual backref */ @@ -1678,7 +1682,7 @@ static int run_delayed_extent_op(struct btrfs_trans_handle *trans, ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item); __run_delayed_extent_op(extent_op, leaf, ei); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); out: btrfs_free_path(path); return err; @@ -3151,7 +3155,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, } } else { btrfs_set_extent_refs(leaf, ei, refs); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); } if (found_extent) { ret = remove_extent_backref(trans, extent_root, path, @@ -4659,7 +4663,7 @@ static int alloc_reserved_file_extent(struct btrfs_trans_handle *trans, btrfs_set_extent_data_ref_count(leaf, ref, ref_mod); } - btrfs_mark_buffer_dirty(path->nodes[0]); + btrfs_mark_buffer_dirty(trans, path->nodes[0]); btrfs_free_path(path); return alloc_reserved_extent(trans, ins->objectid, ins->offset); @@ -4734,7 +4738,7 @@ static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans, btrfs_set_extent_inline_ref_offset(leaf, iref, ref->root); } - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); btrfs_free_path(path); return alloc_reserved_extent(trans, node->bytenr, fs_info->nodesize); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index caccd0376342b..03c10e0ba0e27 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -675,8 +675,8 @@ static void end_bio_extent_readpage(struct btrfs_bio *bbio) * the array will be skipped * * Return: 0 if all pages were able to be allocated; - * -ENOMEM otherwise, and the caller is responsible for freeing all - * non-null page pointers in the array. + * -ENOMEM otherwise, the partially allocated pages would be freed and + * the array slots zeroed */ int btrfs_alloc_page_array(unsigned int nr_pages, struct page **page_array) { @@ -695,8 +695,13 @@ int btrfs_alloc_page_array(unsigned int nr_pages, struct page **page_array) * though alloc_pages_bulk_array() falls back to alloc_page() * if it could not bulk-allocate. So we must be out of memory. */ - if (allocated == last) + if (allocated == last) { + for (int i = 0; i < allocated; i++) { + __free_page(page_array[i]); + page_array[i] = NULL; + } return -ENOMEM; + } memalloc_retry_wait(GFP_NOFS); } @@ -2298,7 +2303,8 @@ static int try_release_extent_state(struct extent_io_tree *tree, ret = 0; } else { u32 clear_bits = ~(EXTENT_LOCKED | EXTENT_NODATASUM | - EXTENT_DELALLOC_NEW | EXTENT_CTLBITS); + EXTENT_DELALLOC_NEW | EXTENT_CTLBITS | + EXTENT_QGROUP_RESERVED); /* * At this point we can safely clear everything except the diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index 1ce5dd1544995..45cae356e89ba 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -194,7 +194,7 @@ int btrfs_insert_hole_extent(struct btrfs_trans_handle *trans, btrfs_set_file_extent_encryption(leaf, item, 0); btrfs_set_file_extent_other_encoding(leaf, item, 0); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); out: btrfs_free_path(path); return ret; @@ -811,11 +811,12 @@ blk_status_t btrfs_alloc_dummy_sum(struct btrfs_bio *bbio) * This calls btrfs_truncate_item with the correct args based on the overlap, * and fixes up the key as required. */ -static noinline void truncate_one_csum(struct btrfs_fs_info *fs_info, +static noinline void truncate_one_csum(struct btrfs_trans_handle *trans, struct btrfs_path *path, struct btrfs_key *key, u64 bytenr, u64 len) { + struct btrfs_fs_info *fs_info = trans->fs_info; struct extent_buffer *leaf; const u32 csum_size = fs_info->csum_size; u64 csum_end; @@ -836,7 +837,7 @@ static noinline void truncate_one_csum(struct btrfs_fs_info *fs_info, */ u32 new_size = (bytenr - key->offset) >> blocksize_bits; new_size *= csum_size; - btrfs_truncate_item(path, new_size, 1); + btrfs_truncate_item(trans, path, new_size, 1); } else if (key->offset >= bytenr && csum_end > end_byte && end_byte > key->offset) { /* @@ -848,10 +849,10 @@ static noinline void truncate_one_csum(struct btrfs_fs_info *fs_info, u32 new_size = (csum_end - end_byte) >> blocksize_bits; new_size *= csum_size; - btrfs_truncate_item(path, new_size, 0); + btrfs_truncate_item(trans, path, new_size, 0); key->offset = end_byte; - btrfs_set_item_key_safe(fs_info, path, key); + btrfs_set_item_key_safe(trans, path, key); } else { BUG(); } @@ -994,7 +995,7 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans, key.offset = end_byte - 1; } else { - truncate_one_csum(fs_info, path, &key, bytenr, len); + truncate_one_csum(trans, path, &key, bytenr, len); if (key.offset < bytenr) break; } @@ -1202,7 +1203,7 @@ int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans, diff /= csum_size; diff *= csum_size; - btrfs_extend_item(path, diff); + btrfs_extend_item(trans, path, diff); ret = 0; goto csum; } @@ -1249,7 +1250,7 @@ int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans, ins_size /= csum_size; total_bytes += ins_size * fs_info->sectorsize; - btrfs_mark_buffer_dirty(path->nodes[0]); + btrfs_mark_buffer_dirty(trans, path->nodes[0]); if (total_bytes < sums->len) { btrfs_release_path(path); cond_resched(); diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 361535c71c0f5..c997b790568fa 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -368,7 +368,7 @@ int btrfs_drop_extents(struct btrfs_trans_handle *trans, btrfs_set_file_extent_offset(leaf, fi, extent_offset); btrfs_set_file_extent_num_bytes(leaf, fi, extent_end - args->start); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); if (update_refs && disk_bytenr > 0) { btrfs_init_generic_ref(&ref, @@ -405,13 +405,13 @@ int btrfs_drop_extents(struct btrfs_trans_handle *trans, memcpy(&new_key, &key, sizeof(new_key)); new_key.offset = args->end; - btrfs_set_item_key_safe(fs_info, path, &new_key); + btrfs_set_item_key_safe(trans, path, &new_key); extent_offset += args->end - key.offset; btrfs_set_file_extent_offset(leaf, fi, extent_offset); btrfs_set_file_extent_num_bytes(leaf, fi, extent_end - args->end); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); if (update_refs && disk_bytenr > 0) args->bytes_found += args->end - key.offset; break; @@ -431,7 +431,7 @@ int btrfs_drop_extents(struct btrfs_trans_handle *trans, btrfs_set_file_extent_num_bytes(leaf, fi, args->start - key.offset); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); if (update_refs && disk_bytenr > 0) args->bytes_found += extent_end - args->start; if (args->end == extent_end) @@ -536,7 +536,8 @@ int btrfs_drop_extents(struct btrfs_trans_handle *trans, if (btrfs_comp_cpu_keys(&key, &slot_key) > 0) path->slots[0]++; } - btrfs_setup_item_for_insert(root, path, &key, args->extent_item_size); + btrfs_setup_item_for_insert(trans, root, path, &key, + args->extent_item_size); args->extent_inserted = true; } @@ -593,7 +594,6 @@ static int extent_mergeable(struct extent_buffer *leaf, int slot, int btrfs_mark_extent_written(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, u64 start, u64 end) { - struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_root *root = inode->root; struct extent_buffer *leaf; struct btrfs_path *path; @@ -664,7 +664,7 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans, ino, bytenr, orig_offset, &other_start, &other_end)) { new_key.offset = end; - btrfs_set_item_key_safe(fs_info, path, &new_key); + btrfs_set_item_key_safe(trans, path, &new_key); fi = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); btrfs_set_file_extent_generation(leaf, fi, @@ -679,7 +679,7 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans, trans->transid); btrfs_set_file_extent_num_bytes(leaf, fi, end - other_start); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); goto out; } } @@ -698,7 +698,7 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans, trans->transid); path->slots[0]++; new_key.offset = start; - btrfs_set_item_key_safe(fs_info, path, &new_key); + btrfs_set_item_key_safe(trans, path, &new_key); fi = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); @@ -708,7 +708,7 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans, other_end - start); btrfs_set_file_extent_offset(leaf, fi, start - orig_offset); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); goto out; } } @@ -742,7 +742,7 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans, btrfs_set_file_extent_offset(leaf, fi, split - orig_offset); btrfs_set_file_extent_num_bytes(leaf, fi, extent_end - split); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); btrfs_init_generic_ref(&ref, BTRFS_ADD_DELAYED_REF, bytenr, num_bytes, 0); @@ -814,7 +814,7 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans, btrfs_set_file_extent_type(leaf, fi, BTRFS_FILE_EXTENT_REG); btrfs_set_file_extent_generation(leaf, fi, trans->transid); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); } else { fi = btrfs_item_ptr(leaf, del_slot - 1, struct btrfs_file_extent_item); @@ -823,7 +823,7 @@ int btrfs_mark_extent_written(struct btrfs_trans_handle *trans, btrfs_set_file_extent_generation(leaf, fi, trans->transid); btrfs_set_file_extent_num_bytes(leaf, fi, extent_end - key.offset); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); ret = btrfs_del_items(trans, root, path, del_slot, del_nr); if (ret < 0) { @@ -2104,7 +2104,7 @@ static int fill_holes(struct btrfs_trans_handle *trans, btrfs_set_file_extent_ram_bytes(leaf, fi, num_bytes); btrfs_set_file_extent_offset(leaf, fi, 0); btrfs_set_file_extent_generation(leaf, fi, trans->transid); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); goto out; } @@ -2112,7 +2112,7 @@ static int fill_holes(struct btrfs_trans_handle *trans, u64 num_bytes; key.offset = offset; - btrfs_set_item_key_safe(fs_info, path, &key); + btrfs_set_item_key_safe(trans, path, &key); fi = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); num_bytes = btrfs_file_extent_num_bytes(leaf, fi) + end - @@ -2121,7 +2121,7 @@ static int fill_holes(struct btrfs_trans_handle *trans, btrfs_set_file_extent_ram_bytes(leaf, fi, num_bytes); btrfs_set_file_extent_offset(leaf, fi, 0); btrfs_set_file_extent_generation(leaf, fi, trans->transid); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); goto out; } btrfs_release_path(path); @@ -2273,7 +2273,7 @@ static int btrfs_insert_replace_extent(struct btrfs_trans_handle *trans, btrfs_set_file_extent_num_bytes(leaf, extent, replace_len); if (extent_info->is_new_extent) btrfs_set_file_extent_generation(leaf, extent, trans->transid); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); btrfs_release_path(path); ret = btrfs_inode_set_file_extent_range(inode, extent_info->file_offset, @@ -3187,7 +3187,7 @@ static long btrfs_fallocate(struct file *file, int mode, qgroup_reserved -= range->len; } else if (qgroup_reserved > 0) { btrfs_qgroup_free_data(BTRFS_I(inode), data_reserved, - range->start, range->len); + range->start, range->len, NULL); qgroup_reserved -= range->len; } list_del(&range->list); diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 27fad70451aad..8dd8ef760321e 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -195,7 +195,7 @@ static int __create_free_space_inode(struct btrfs_root *root, btrfs_set_inode_nlink(leaf, inode_item, 1); btrfs_set_inode_transid(leaf, inode_item, trans->transid); btrfs_set_inode_block_group(leaf, inode_item, offset); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); btrfs_release_path(path); key.objectid = BTRFS_FREE_SPACE_OBJECTID; @@ -213,7 +213,7 @@ static int __create_free_space_inode(struct btrfs_root *root, struct btrfs_free_space_header); memzero_extent_buffer(leaf, (unsigned long)header, sizeof(*header)); btrfs_set_free_space_key(leaf, header, &disk_key); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); btrfs_release_path(path); return 0; @@ -1185,7 +1185,7 @@ update_cache_item(struct btrfs_trans_handle *trans, btrfs_set_free_space_entries(leaf, header, entries); btrfs_set_free_space_bitmaps(leaf, header, bitmaps); btrfs_set_free_space_generation(leaf, header, trans->transid); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); btrfs_release_path(path); return 0; diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c index c0e734082dcc4..7b598b070700e 100644 --- a/fs/btrfs/free-space-tree.c +++ b/fs/btrfs/free-space-tree.c @@ -89,7 +89,7 @@ static int add_new_free_space_info(struct btrfs_trans_handle *trans, struct btrfs_free_space_info); btrfs_set_free_space_extent_count(leaf, info, 0); btrfs_set_free_space_flags(leaf, info, 0); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); ret = 0; out: @@ -287,7 +287,7 @@ int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans, flags |= BTRFS_FREE_SPACE_USING_BITMAPS; btrfs_set_free_space_flags(leaf, info, flags); expected_extent_count = btrfs_free_space_extent_count(leaf, info); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); btrfs_release_path(path); if (extent_count != expected_extent_count) { @@ -324,7 +324,7 @@ int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans, ptr = btrfs_item_ptr_offset(leaf, path->slots[0]); write_extent_buffer(leaf, bitmap_cursor, ptr, data_size); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); btrfs_release_path(path); i += extent_size; @@ -430,7 +430,7 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans, flags &= ~BTRFS_FREE_SPACE_USING_BITMAPS; btrfs_set_free_space_flags(leaf, info, flags); expected_extent_count = btrfs_free_space_extent_count(leaf, info); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); btrfs_release_path(path); nrbits = block_group->length >> block_group->fs_info->sectorsize_bits; @@ -495,7 +495,7 @@ static int update_free_space_extent_count(struct btrfs_trans_handle *trans, extent_count += new_extents; btrfs_set_free_space_extent_count(path->nodes[0], info, extent_count); - btrfs_mark_buffer_dirty(path->nodes[0]); + btrfs_mark_buffer_dirty(trans, path->nodes[0]); btrfs_release_path(path); if (!(flags & BTRFS_FREE_SPACE_USING_BITMAPS) && @@ -533,7 +533,8 @@ int free_space_test_bit(struct btrfs_block_group *block_group, return !!extent_buffer_test_bit(leaf, ptr, i); } -static void free_space_set_bits(struct btrfs_block_group *block_group, +static void free_space_set_bits(struct btrfs_trans_handle *trans, + struct btrfs_block_group *block_group, struct btrfs_path *path, u64 *start, u64 *size, int bit) { @@ -563,7 +564,7 @@ static void free_space_set_bits(struct btrfs_block_group *block_group, extent_buffer_bitmap_set(leaf, ptr, first, last - first); else extent_buffer_bitmap_clear(leaf, ptr, first, last - first); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); *size -= end - *start; *start = end; @@ -656,7 +657,7 @@ static int modify_free_space_bitmap(struct btrfs_trans_handle *trans, cur_start = start; cur_size = size; while (1) { - free_space_set_bits(block_group, path, &cur_start, &cur_size, + free_space_set_bits(trans, block_group, path, &cur_start, &cur_size, !remove); if (cur_size == 0) break; diff --git a/fs/btrfs/inode-item.c b/fs/btrfs/inode-item.c index 4c322b720a80a..d3ff97374d48a 100644 --- a/fs/btrfs/inode-item.c +++ b/fs/btrfs/inode-item.c @@ -167,7 +167,7 @@ static int btrfs_del_inode_extref(struct btrfs_trans_handle *trans, memmove_extent_buffer(leaf, ptr, ptr + del_len, item_size - (ptr + del_len - item_start)); - btrfs_truncate_item(path, item_size - del_len, 1); + btrfs_truncate_item(trans, path, item_size - del_len, 1); out: btrfs_free_path(path); @@ -229,7 +229,7 @@ int btrfs_del_inode_ref(struct btrfs_trans_handle *trans, item_start = btrfs_item_ptr_offset(leaf, path->slots[0]); memmove_extent_buffer(leaf, ptr, ptr + sub_item_len, item_size - (ptr + sub_item_len - item_start)); - btrfs_truncate_item(path, item_size - sub_item_len, 1); + btrfs_truncate_item(trans, path, item_size - sub_item_len, 1); out: btrfs_free_path(path); @@ -282,7 +282,7 @@ static int btrfs_insert_inode_extref(struct btrfs_trans_handle *trans, name)) goto out; - btrfs_extend_item(path, ins_len); + btrfs_extend_item(trans, path, ins_len); ret = 0; } if (ret < 0) @@ -299,7 +299,7 @@ static int btrfs_insert_inode_extref(struct btrfs_trans_handle *trans, ptr = (unsigned long)&extref->name; write_extent_buffer(path->nodes[0], name->name, ptr, name->len); - btrfs_mark_buffer_dirty(path->nodes[0]); + btrfs_mark_buffer_dirty(trans, path->nodes[0]); out: btrfs_free_path(path); @@ -338,7 +338,7 @@ int btrfs_insert_inode_ref(struct btrfs_trans_handle *trans, goto out; old_size = btrfs_item_size(path->nodes[0], path->slots[0]); - btrfs_extend_item(path, ins_len); + btrfs_extend_item(trans, path, ins_len); ref = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_inode_ref); ref = (struct btrfs_inode_ref *)((unsigned long)ref + old_size); @@ -364,7 +364,7 @@ int btrfs_insert_inode_ref(struct btrfs_trans_handle *trans, ptr = (unsigned long)(ref + 1); } write_extent_buffer(path->nodes[0], name->name, ptr, name->len); - btrfs_mark_buffer_dirty(path->nodes[0]); + btrfs_mark_buffer_dirty(trans, path->nodes[0]); out: btrfs_free_path(path); @@ -591,7 +591,7 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, num_dec = (orig_num_bytes - extent_num_bytes); if (extent_start != 0) control->sub_bytes += num_dec; - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); } else { extent_num_bytes = btrfs_file_extent_disk_num_bytes(leaf, fi); @@ -617,7 +617,7 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, btrfs_set_file_extent_ram_bytes(leaf, fi, size); size = btrfs_file_extent_calc_inline_size(size); - btrfs_truncate_item(path, size, 1); + btrfs_truncate_item(trans, path, size, 1); } else if (!del_item) { /* * We have to bail so the last_size is set to diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 7814b9d654ce1..7bf5c2c1a54d8 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -573,7 +573,7 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans, kunmap_local(kaddr); put_page(page); } - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); btrfs_release_path(path); /* @@ -687,7 +687,7 @@ static noinline int cow_file_range_inline(struct btrfs_inode *inode, u64 size, * And at reserve time, it's always aligned to page size, so * just free one page here. */ - btrfs_qgroup_free_data(inode, NULL, 0, PAGE_SIZE); + btrfs_qgroup_free_data(inode, NULL, 0, PAGE_SIZE, NULL); btrfs_free_path(path); btrfs_end_transaction(trans); return ret; @@ -2912,7 +2912,7 @@ static int insert_reserved_file_extent(struct btrfs_trans_handle *trans, btrfs_item_ptr_offset(leaf, path->slots[0]), sizeof(struct btrfs_file_extent_item)); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); btrfs_release_path(path); /* @@ -3981,7 +3981,7 @@ static noinline int btrfs_update_inode_item(struct btrfs_trans_handle *trans, struct btrfs_inode_item); fill_inode_item(trans, leaf, inode_item, &inode->vfs_inode); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); btrfs_set_inode_last_trans(trans, inode); ret = 0; failed: @@ -5129,7 +5129,7 @@ static void evict_inode_truncate_pages(struct inode *inode) */ if (state_flags & EXTENT_DELALLOC) btrfs_qgroup_free_data(BTRFS_I(inode), NULL, start, - end - start + 1); + end - start + 1, NULL); clear_extent_bit(io_tree, start, end, EXTENT_CLEAR_ALL_BITS | EXTENT_DO_ACCOUNTING, @@ -6310,7 +6310,7 @@ int btrfs_create_new_inode(struct btrfs_trans_handle *trans, } } - btrfs_mark_buffer_dirty(path->nodes[0]); + btrfs_mark_buffer_dirty(trans, path->nodes[0]); /* * We don't need the path anymore, plus inheriting properties, adding * ACLs, security xattrs, orphan item or adding the link, will result in @@ -6974,8 +6974,15 @@ static struct extent_map *btrfs_new_extent_direct(struct btrfs_inode *inode, int ret; alloc_hint = get_extent_allocation_hint(inode, start, len); +again: ret = btrfs_reserve_extent(root, len, len, fs_info->sectorsize, 0, alloc_hint, &ins, 1, 1); + if (ret == -EAGAIN) { + ASSERT(btrfs_is_zoned(fs_info)); + wait_on_bit_io(&inode->root->fs_info->flags, BTRFS_FS_NEED_ZONE_FINISH, + TASK_UNINTERRUPTIBLE); + goto again; + } if (ret) return ERR_PTR(ret); @@ -8044,7 +8051,7 @@ static void btrfs_invalidate_folio(struct folio *folio, size_t offset, * reserved data space. * Since the IO will never happen for this page. */ - btrfs_qgroup_free_data(inode, NULL, cur, range_end + 1 - cur); + btrfs_qgroup_free_data(inode, NULL, cur, range_end + 1 - cur, NULL); if (!inode_evicting) { clear_extent_bit(tree, cur, range_end, EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_UPTODATE | @@ -9446,7 +9453,7 @@ static int btrfs_symlink(struct mnt_idmap *idmap, struct inode *dir, ptr = btrfs_file_extent_inline_start(ei); write_extent_buffer(leaf, symname, ptr, name_len); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); btrfs_free_path(path); d_instantiate_new(dentry, inode); @@ -9474,7 +9481,7 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent( struct btrfs_path *path; u64 start = ins->objectid; u64 len = ins->offset; - int qgroup_released; + u64 qgroup_released = 0; int ret; memset(&stack_fi, 0, sizeof(stack_fi)); @@ -9487,9 +9494,9 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent( btrfs_set_stack_file_extent_compression(&stack_fi, BTRFS_COMPRESS_NONE); /* Encryption and other encoding is reserved and all 0 */ - qgroup_released = btrfs_qgroup_release_data(inode, file_offset, len); - if (qgroup_released < 0) - return ERR_PTR(qgroup_released); + ret = btrfs_qgroup_release_data(inode, file_offset, len, &qgroup_released); + if (ret < 0) + return ERR_PTR(ret); if (trans) { ret = insert_reserved_file_extent(trans, inode, @@ -10384,7 +10391,7 @@ ssize_t btrfs_do_encoded_write(struct kiocb *iocb, struct iov_iter *from, btrfs_delalloc_release_metadata(inode, disk_num_bytes, ret < 0); out_qgroup_free_data: if (ret < 0) - btrfs_qgroup_free_data(inode, data_reserved, start, num_bytes); + btrfs_qgroup_free_data(inode, data_reserved, start, num_bytes, NULL); out_free_data_space: /* * If btrfs_reserve_extent() succeeded, then we already decremented diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 200dd780bc06f..e611b3a3ad388 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -663,7 +663,7 @@ static noinline int create_subvol(struct mnt_idmap *idmap, goto out; } - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); inode_item = &root_item->inode; btrfs_set_stack_inode_generation(inode_item, 1); @@ -1290,6 +1290,15 @@ static noinline int __btrfs_ioctl_snap_create(struct file *file, * are limited to own subvolumes only */ ret = -EPERM; + } else if (btrfs_ino(BTRFS_I(src_inode)) != BTRFS_FIRST_FREE_OBJECTID) { + /* + * Snapshots must be made with the src_inode referring + * to the subvolume inode, otherwise the permission + * checking above is useless because we may have + * permission on a lower directory but not the subvol + * itself. + */ + ret = -EINVAL; } else { ret = btrfs_mksnapshot(&file->f_path, idmap, name, namelen, @@ -2947,7 +2956,7 @@ static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp) btrfs_cpu_key_to_disk(&disk_key, &new_root->root_key); btrfs_set_dir_item_key(path->nodes[0], di, &disk_key); - btrfs_mark_buffer_dirty(path->nodes[0]); + btrfs_mark_buffer_dirty(trans, path->nodes[0]); btrfs_release_path(path); btrfs_set_fs_incompat(fs_info, DEFAULT_SUBVOL); @@ -4351,6 +4360,7 @@ static int _btrfs_ioctl_send(struct inode *inode, void __user *argp, bool compat arg->clone_sources = compat_ptr(args32.clone_sources); arg->parent_root = args32.parent_root; arg->flags = args32.flags; + arg->version = args32.version; memcpy(arg->reserved, args32.reserved, sizeof(args32.reserved)); #else diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 345c449d588cc..2b8ff8b53af04 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -153,11 +153,12 @@ static struct btrfs_ordered_extent *alloc_ordered_extent( { struct btrfs_ordered_extent *entry; int ret; + u64 qgroup_rsv = 0; if (flags & ((1 << BTRFS_ORDERED_NOCOW) | (1 << BTRFS_ORDERED_PREALLOC))) { /* For nocow write, we can release the qgroup rsv right now */ - ret = btrfs_qgroup_free_data(inode, NULL, file_offset, num_bytes); + ret = btrfs_qgroup_free_data(inode, NULL, file_offset, num_bytes, &qgroup_rsv); if (ret < 0) return ERR_PTR(ret); } else { @@ -165,7 +166,7 @@ static struct btrfs_ordered_extent *alloc_ordered_extent( * The ordered extent has reserved qgroup space, release now * and pass the reserved number for qgroup_record to free. */ - ret = btrfs_qgroup_release_data(inode, file_offset, num_bytes); + ret = btrfs_qgroup_release_data(inode, file_offset, num_bytes, &qgroup_rsv); if (ret < 0) return ERR_PTR(ret); } @@ -183,7 +184,7 @@ static struct btrfs_ordered_extent *alloc_ordered_extent( entry->inode = igrab(&inode->vfs_inode); entry->compress_type = compress_type; entry->truncated_len = (u64)-1; - entry->qgroup_rsv = ret; + entry->qgroup_rsv = qgroup_rsv; entry->flags = flags; refcount_set(&entry->refs, 1); init_waitqueue_head(&entry->wait); @@ -603,7 +604,9 @@ void btrfs_remove_ordered_extent(struct btrfs_inode *btrfs_inode, release = entry->disk_num_bytes; else release = entry->num_bytes; - btrfs_delalloc_release_metadata(btrfs_inode, release, false); + btrfs_delalloc_release_metadata(btrfs_inode, release, + test_bit(BTRFS_ORDERED_IOERR, + &entry->flags)); } percpu_counter_add_batch(&fs_info->ordered_bytes, -entry->num_bytes, diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index b99230db3c820..a006f5160e6b4 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -208,6 +208,7 @@ static struct btrfs_qgroup *add_qgroup_rb(struct btrfs_fs_info *fs_info, INIT_LIST_HEAD(&qgroup->groups); INIT_LIST_HEAD(&qgroup->members); INIT_LIST_HEAD(&qgroup->dirty); + INIT_LIST_HEAD(&qgroup->iterator); rb_link_node(&qgroup->node, parent, p); rb_insert_color(&qgroup->node, &fs_info->qgroup_tree); @@ -622,7 +623,7 @@ static int add_qgroup_relation_item(struct btrfs_trans_handle *trans, u64 src, ret = btrfs_insert_empty_item(trans, quota_root, path, &key, 0); - btrfs_mark_buffer_dirty(path->nodes[0]); + btrfs_mark_buffer_dirty(trans, path->nodes[0]); btrfs_free_path(path); return ret; @@ -700,7 +701,7 @@ static int add_qgroup_item(struct btrfs_trans_handle *trans, btrfs_set_qgroup_info_excl(leaf, qgroup_info, 0); btrfs_set_qgroup_info_excl_cmpr(leaf, qgroup_info, 0); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); btrfs_release_path(path); @@ -719,7 +720,7 @@ static int add_qgroup_item(struct btrfs_trans_handle *trans, btrfs_set_qgroup_limit_rsv_rfer(leaf, qgroup_limit, 0); btrfs_set_qgroup_limit_rsv_excl(leaf, qgroup_limit, 0); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); ret = 0; out: @@ -808,7 +809,7 @@ static int update_qgroup_limit_item(struct btrfs_trans_handle *trans, btrfs_set_qgroup_limit_rsv_rfer(l, qgroup_limit, qgroup->rsv_rfer); btrfs_set_qgroup_limit_rsv_excl(l, qgroup_limit, qgroup->rsv_excl); - btrfs_mark_buffer_dirty(l); + btrfs_mark_buffer_dirty(trans, l); out: btrfs_free_path(path); @@ -854,7 +855,7 @@ static int update_qgroup_info_item(struct btrfs_trans_handle *trans, btrfs_set_qgroup_info_excl(l, qgroup_info, qgroup->excl); btrfs_set_qgroup_info_excl_cmpr(l, qgroup_info, qgroup->excl_cmpr); - btrfs_mark_buffer_dirty(l); + btrfs_mark_buffer_dirty(trans, l); out: btrfs_free_path(path); @@ -896,7 +897,7 @@ static int update_qgroup_status_item(struct btrfs_trans_handle *trans) btrfs_set_qgroup_status_rescan(l, ptr, fs_info->qgroup_rescan_progress.objectid); - btrfs_mark_buffer_dirty(l); + btrfs_mark_buffer_dirty(trans, l); out: btrfs_free_path(path); @@ -1069,7 +1070,7 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info) BTRFS_QGROUP_STATUS_FLAGS_MASK); btrfs_set_qgroup_status_rescan(leaf, ptr, 0); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); key.objectid = 0; key.type = BTRFS_ROOT_REF_KEY; @@ -1342,6 +1343,24 @@ static void qgroup_dirty(struct btrfs_fs_info *fs_info, list_add(&qgroup->dirty, &fs_info->dirty_qgroups); } +static void qgroup_iterator_add(struct list_head *head, struct btrfs_qgroup *qgroup) +{ + if (!list_empty(&qgroup->iterator)) + return; + + list_add_tail(&qgroup->iterator, head); +} + +static void qgroup_iterator_clean(struct list_head *head) +{ + while (!list_empty(head)) { + struct btrfs_qgroup *qgroup; + + qgroup = list_first_entry(head, struct btrfs_qgroup, iterator); + list_del_init(&qgroup->iterator); + } +} + /* * The easy accounting, we're updating qgroup relationship whose child qgroup * only has exclusive extents. @@ -3125,8 +3144,7 @@ static int qgroup_reserve(struct btrfs_root *root, u64 num_bytes, bool enforce, struct btrfs_fs_info *fs_info = root->fs_info; u64 ref_root = root->root_key.objectid; int ret = 0; - struct ulist_node *unode; - struct ulist_iterator uiter; + LIST_HEAD(qgroup_list); if (!is_fstree(ref_root)) return 0; @@ -3146,49 +3164,28 @@ static int qgroup_reserve(struct btrfs_root *root, u64 num_bytes, bool enforce, if (!qgroup) goto out; - /* - * in a first step, we check all affected qgroups if any limits would - * be exceeded - */ - ulist_reinit(fs_info->qgroup_ulist); - ret = ulist_add(fs_info->qgroup_ulist, qgroup->qgroupid, - qgroup_to_aux(qgroup), GFP_ATOMIC); - if (ret < 0) - goto out; - ULIST_ITER_INIT(&uiter); - while ((unode = ulist_next(fs_info->qgroup_ulist, &uiter))) { - struct btrfs_qgroup *qg; + qgroup_iterator_add(&qgroup_list, qgroup); + list_for_each_entry(qgroup, &qgroup_list, iterator) { struct btrfs_qgroup_list *glist; - qg = unode_aux_to_qgroup(unode); - - if (enforce && !qgroup_check_limits(qg, num_bytes)) { + if (enforce && !qgroup_check_limits(qgroup, num_bytes)) { ret = -EDQUOT; goto out; } - list_for_each_entry(glist, &qg->groups, next_group) { - ret = ulist_add(fs_info->qgroup_ulist, - glist->group->qgroupid, - qgroup_to_aux(glist->group), GFP_ATOMIC); - if (ret < 0) - goto out; - } + list_for_each_entry(glist, &qgroup->groups, next_group) + qgroup_iterator_add(&qgroup_list, glist->group); } + ret = 0; /* * no limits exceeded, now record the reservation into all qgroups */ - ULIST_ITER_INIT(&uiter); - while ((unode = ulist_next(fs_info->qgroup_ulist, &uiter))) { - struct btrfs_qgroup *qg; - - qg = unode_aux_to_qgroup(unode); - - qgroup_rsv_add(fs_info, qg, num_bytes, type); - } + list_for_each_entry(qgroup, &qgroup_list, iterator) + qgroup_rsv_add(fs_info, qgroup, num_bytes, type); out: + qgroup_iterator_clean(&qgroup_list); spin_unlock(&fs_info->qgroup_lock); return ret; } @@ -3855,13 +3852,14 @@ int btrfs_qgroup_reserve_data(struct btrfs_inode *inode, /* Free ranges specified by @reserved, normally in error path */ static int qgroup_free_reserved_data(struct btrfs_inode *inode, - struct extent_changeset *reserved, u64 start, u64 len) + struct extent_changeset *reserved, + u64 start, u64 len, u64 *freed_ret) { struct btrfs_root *root = inode->root; struct ulist_node *unode; struct ulist_iterator uiter; struct extent_changeset changeset; - int freed = 0; + u64 freed = 0; int ret; extent_changeset_init(&changeset); @@ -3902,7 +3900,9 @@ static int qgroup_free_reserved_data(struct btrfs_inode *inode, } btrfs_qgroup_free_refroot(root->fs_info, root->root_key.objectid, freed, BTRFS_QGROUP_RSV_DATA); - ret = freed; + if (freed_ret) + *freed_ret = freed; + ret = 0; out: extent_changeset_release(&changeset); return ret; @@ -3910,7 +3910,7 @@ static int qgroup_free_reserved_data(struct btrfs_inode *inode, static int __btrfs_qgroup_release_data(struct btrfs_inode *inode, struct extent_changeset *reserved, u64 start, u64 len, - int free) + u64 *released, int free) { struct extent_changeset changeset; int trace_op = QGROUP_RELEASE; @@ -3922,7 +3922,7 @@ static int __btrfs_qgroup_release_data(struct btrfs_inode *inode, /* In release case, we shouldn't have @reserved */ WARN_ON(!free && reserved); if (free && reserved) - return qgroup_free_reserved_data(inode, reserved, start, len); + return qgroup_free_reserved_data(inode, reserved, start, len, released); extent_changeset_init(&changeset); ret = clear_record_extent_bits(&inode->io_tree, start, start + len -1, EXTENT_QGROUP_RESERVED, &changeset); @@ -3937,7 +3937,8 @@ static int __btrfs_qgroup_release_data(struct btrfs_inode *inode, btrfs_qgroup_free_refroot(inode->root->fs_info, inode->root->root_key.objectid, changeset.bytes_changed, BTRFS_QGROUP_RSV_DATA); - ret = changeset.bytes_changed; + if (released) + *released = changeset.bytes_changed; out: extent_changeset_release(&changeset); return ret; @@ -3956,9 +3957,10 @@ static int __btrfs_qgroup_release_data(struct btrfs_inode *inode, * NOTE: This function may sleep for memory allocation. */ int btrfs_qgroup_free_data(struct btrfs_inode *inode, - struct extent_changeset *reserved, u64 start, u64 len) + struct extent_changeset *reserved, + u64 start, u64 len, u64 *freed) { - return __btrfs_qgroup_release_data(inode, reserved, start, len, 1); + return __btrfs_qgroup_release_data(inode, reserved, start, len, freed, 1); } /* @@ -3976,9 +3978,9 @@ int btrfs_qgroup_free_data(struct btrfs_inode *inode, * * NOTE: This function may sleep for memory allocation. */ -int btrfs_qgroup_release_data(struct btrfs_inode *inode, u64 start, u64 len) +int btrfs_qgroup_release_data(struct btrfs_inode *inode, u64 start, u64 len, u64 *released) { - return __btrfs_qgroup_release_data(inode, NULL, start, len, 0); + return __btrfs_qgroup_release_data(inode, NULL, start, len, released, 0); } static void add_root_meta_rsv(struct btrfs_root *root, int num_bytes, @@ -4104,9 +4106,7 @@ static void qgroup_convert_meta(struct btrfs_fs_info *fs_info, u64 ref_root, int num_bytes) { struct btrfs_qgroup *qgroup; - struct ulist_node *unode; - struct ulist_iterator uiter; - int ret = 0; + LIST_HEAD(qgroup_list); if (num_bytes == 0) return; @@ -4117,31 +4117,22 @@ static void qgroup_convert_meta(struct btrfs_fs_info *fs_info, u64 ref_root, qgroup = find_qgroup_rb(fs_info, ref_root); if (!qgroup) goto out; - ulist_reinit(fs_info->qgroup_ulist); - ret = ulist_add(fs_info->qgroup_ulist, qgroup->qgroupid, - qgroup_to_aux(qgroup), GFP_ATOMIC); - if (ret < 0) - goto out; - ULIST_ITER_INIT(&uiter); - while ((unode = ulist_next(fs_info->qgroup_ulist, &uiter))) { - struct btrfs_qgroup *qg; - struct btrfs_qgroup_list *glist; - qg = unode_aux_to_qgroup(unode); + qgroup_iterator_add(&qgroup_list, qgroup); + list_for_each_entry(qgroup, &qgroup_list, iterator) { + struct btrfs_qgroup_list *glist; - qgroup_rsv_release(fs_info, qg, num_bytes, + qgroup_rsv_release(fs_info, qgroup, num_bytes, BTRFS_QGROUP_RSV_META_PREALLOC); - qgroup_rsv_add(fs_info, qg, num_bytes, - BTRFS_QGROUP_RSV_META_PERTRANS); - list_for_each_entry(glist, &qg->groups, next_group) { - ret = ulist_add(fs_info->qgroup_ulist, - glist->group->qgroupid, - qgroup_to_aux(glist->group), GFP_ATOMIC); - if (ret < 0) - goto out; - } + if (!sb_rdonly(fs_info->sb)) + qgroup_rsv_add(fs_info, qgroup, num_bytes, + BTRFS_QGROUP_RSV_META_PERTRANS); + + list_for_each_entry(glist, &qgroup->groups, next_group) + qgroup_iterator_add(&qgroup_list, glist->group); } out: + qgroup_iterator_clean(&qgroup_list); spin_unlock(&fs_info->qgroup_lock); } diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h index 7bffa10589d6b..1203f06320991 100644 --- a/fs/btrfs/qgroup.h +++ b/fs/btrfs/qgroup.h @@ -220,6 +220,15 @@ struct btrfs_qgroup { struct list_head groups; /* groups this group is member of */ struct list_head members; /* groups that are members of this group */ struct list_head dirty; /* dirty groups */ + + /* + * For qgroup iteration usage. + * + * The iteration list should always be empty until qgroup_iterator_add() + * is called. And should be reset to empty after the iteration is + * finished. + */ + struct list_head iterator; struct rb_node node; /* tree of qgroups */ /* @@ -363,10 +372,10 @@ int btrfs_verify_qgroup_counts(struct btrfs_fs_info *fs_info, u64 qgroupid, /* New io_tree based accurate qgroup reserve API */ int btrfs_qgroup_reserve_data(struct btrfs_inode *inode, struct extent_changeset **reserved, u64 start, u64 len); -int btrfs_qgroup_release_data(struct btrfs_inode *inode, u64 start, u64 len); +int btrfs_qgroup_release_data(struct btrfs_inode *inode, u64 start, u64 len, u64 *released); int btrfs_qgroup_free_data(struct btrfs_inode *inode, struct extent_changeset *reserved, u64 start, - u64 len); + u64 len, u64 *freed); int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes, enum btrfs_qgroup_rsv_type type, bool enforce); int __btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes, diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c index 95d28497de7c2..e646662e61c6b 100644 --- a/fs/btrfs/ref-verify.c +++ b/fs/btrfs/ref-verify.c @@ -791,6 +791,7 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info, dump_ref_action(fs_info, ra); kfree(ref); kfree(ra); + kfree(re); goto out_unlock; } else if (be->num_refs == 0) { btrfs_err(fs_info, @@ -800,6 +801,7 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info, dump_ref_action(fs_info, ra); kfree(ref); kfree(ra); + kfree(re); goto out_unlock; } diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index c6d4bb8cbe299..4eaac3ae5c365 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -1181,7 +1181,7 @@ int replace_file_extents(struct btrfs_trans_handle *trans, } } if (dirty) - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); if (inode) btrfs_add_delayed_iput(BTRFS_I(inode)); return ret; @@ -1374,13 +1374,13 @@ int replace_path(struct btrfs_trans_handle *trans, struct reloc_control *rc, */ btrfs_set_node_blockptr(parent, slot, new_bytenr); btrfs_set_node_ptr_generation(parent, slot, new_ptr_gen); - btrfs_mark_buffer_dirty(parent); + btrfs_mark_buffer_dirty(trans, parent); btrfs_set_node_blockptr(path->nodes[level], path->slots[level], old_bytenr); btrfs_set_node_ptr_generation(path->nodes[level], path->slots[level], old_ptr_gen); - btrfs_mark_buffer_dirty(path->nodes[level]); + btrfs_mark_buffer_dirty(trans, path->nodes[level]); btrfs_init_generic_ref(&ref, BTRFS_ADD_DELAYED_REF, old_bytenr, blocksize, path->nodes[level]->start); @@ -2517,7 +2517,7 @@ static int do_relocation(struct btrfs_trans_handle *trans, node->eb->start); btrfs_set_node_ptr_generation(upper->eb, slot, trans->transid); - btrfs_mark_buffer_dirty(upper->eb); + btrfs_mark_buffer_dirty(trans, upper->eb); btrfs_init_generic_ref(&ref, BTRFS_ADD_DELAYED_REF, node->eb->start, blocksize, @@ -3835,7 +3835,7 @@ static int __insert_orphan_inode(struct btrfs_trans_handle *trans, btrfs_set_inode_mode(leaf, item, S_IFREG | 0600); btrfs_set_inode_flags(leaf, item, BTRFS_INODE_NOCOMPRESS | BTRFS_INODE_PREALLOC); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); out: btrfs_free_path(path); return ret; diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index 859874579456f..5b0f1bccc409c 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -191,7 +191,7 @@ int btrfs_update_root(struct btrfs_trans_handle *trans, struct btrfs_root btrfs_set_root_generation_v2(item, btrfs_root_generation(item)); write_extent_buffer(l, item, ptr, sizeof(*item)); - btrfs_mark_buffer_dirty(path->nodes[0]); + btrfs_mark_buffer_dirty(trans, path->nodes[0]); out: btrfs_free_path(path); return ret; @@ -438,7 +438,7 @@ int btrfs_add_root_ref(struct btrfs_trans_handle *trans, u64 root_id, btrfs_set_root_ref_name_len(leaf, ref, name->len); ptr = (unsigned long)(ref + 1); write_extent_buffer(leaf, name->name, ptr, name->len); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); if (key.type == BTRFS_ROOT_BACKREF_KEY) { btrfs_release_path(path); diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 3a566150c531a..db94eefda27e2 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -8158,7 +8158,7 @@ long btrfs_ioctl_send(struct inode *inode, struct btrfs_ioctl_send_args *arg) } sctx->send_filp = fget(arg->send_fd); - if (!sctx->send_filp) { + if (!sctx->send_filp || !(sctx->send_filp->f_mode & FMODE_WRITE)) { ret = -EBADF; goto out; } diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 1a093ec0f7e36..de0bfebce1269 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -79,7 +79,10 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data); static void btrfs_put_super(struct super_block *sb) { - close_ctree(btrfs_sb(sb)); + struct btrfs_fs_info *fs_info = btrfs_sb(sb); + + btrfs_info(fs_info, "last unmount of filesystem %pU", fs_info->fs_devices->fsid); + close_ctree(fs_info); } enum { diff --git a/fs/btrfs/tests/extent-buffer-tests.c b/fs/btrfs/tests/extent-buffer-tests.c index 5ef0b90e25c3b..6a43a64ba55ad 100644 --- a/fs/btrfs/tests/extent-buffer-tests.c +++ b/fs/btrfs/tests/extent-buffer-tests.c @@ -61,7 +61,11 @@ static int test_btrfs_split_item(u32 sectorsize, u32 nodesize) key.type = BTRFS_EXTENT_CSUM_KEY; key.offset = 0; - btrfs_setup_item_for_insert(root, path, &key, value_len); + /* + * Passing a NULL trans handle is fine here, we have a dummy root eb + * and the tree is a single node (level 0). + */ + btrfs_setup_item_for_insert(NULL, root, path, &key, value_len); write_extent_buffer(eb, value, btrfs_item_ptr_offset(eb, 0), value_len); diff --git a/fs/btrfs/tests/inode-tests.c b/fs/btrfs/tests/inode-tests.c index 05b03f5eab83b..492d69d2fa737 100644 --- a/fs/btrfs/tests/inode-tests.c +++ b/fs/btrfs/tests/inode-tests.c @@ -34,7 +34,11 @@ static void insert_extent(struct btrfs_root *root, u64 start, u64 len, key.type = BTRFS_EXTENT_DATA_KEY; key.offset = start; - btrfs_setup_item_for_insert(root, &path, &key, value_len); + /* + * Passing a NULL trans handle is fine here, we have a dummy root eb + * and the tree is a single node (level 0). + */ + btrfs_setup_item_for_insert(NULL, root, &path, &key, value_len); fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item); btrfs_set_file_extent_generation(leaf, fi, 1); btrfs_set_file_extent_type(leaf, fi, type); @@ -64,7 +68,11 @@ static void insert_inode_item_key(struct btrfs_root *root) key.type = BTRFS_INODE_ITEM_KEY; key.offset = 0; - btrfs_setup_item_for_insert(root, &path, &key, value_len); + /* + * Passing a NULL trans handle is fine here, we have a dummy root eb + * and the tree is a single node (level 0). + */ + btrfs_setup_item_for_insert(NULL, root, &path, &key, value_len); } /* diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index c780d37294636..0ac2d191cd34f 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -37,8 +37,6 @@ static struct kmem_cache *btrfs_trans_handle_cachep; -#define BTRFS_ROOT_TRANS_TAG 0 - /* * Transaction states and transitions * diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 93869cda6af99..238a0ab85df9b 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -12,6 +12,9 @@ #include "ctree.h" #include "misc.h" +/* Radix-tree tag for roots that are part of the trasaction. */ +#define BTRFS_ROOT_TRANS_TAG 0 + enum btrfs_trans_state { TRANS_STATE_RUNNING, TRANS_STATE_COMMIT_PREP, diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index cbb17b5421317..9fb64af608d12 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -504,9 +504,9 @@ static int overwrite_item(struct btrfs_trans_handle *trans, found_size = btrfs_item_size(path->nodes[0], path->slots[0]); if (found_size > item_size) - btrfs_truncate_item(path, item_size, 1); + btrfs_truncate_item(trans, path, item_size, 1); else if (found_size < item_size) - btrfs_extend_item(path, item_size - found_size); + btrfs_extend_item(trans, path, item_size - found_size); } else if (ret) { return ret; } @@ -574,7 +574,7 @@ static int overwrite_item(struct btrfs_trans_handle *trans, } } no_copy: - btrfs_mark_buffer_dirty(path->nodes[0]); + btrfs_mark_buffer_dirty(trans, path->nodes[0]); btrfs_release_path(path); return 0; } @@ -3530,7 +3530,7 @@ static noinline int insert_dir_log_key(struct btrfs_trans_handle *trans, last_offset = max(last_offset, curr_end); } btrfs_set_dir_log_end(path->nodes[0], item, last_offset); - btrfs_mark_buffer_dirty(path->nodes[0]); + btrfs_mark_buffer_dirty(trans, path->nodes[0]); btrfs_release_path(path); return 0; } @@ -4488,7 +4488,7 @@ static noinline int copy_items(struct btrfs_trans_handle *trans, dst_index++; } - btrfs_mark_buffer_dirty(dst_path->nodes[0]); + btrfs_mark_buffer_dirty(trans, dst_path->nodes[0]); btrfs_release_path(dst_path); out: kfree(ins_data); @@ -4693,7 +4693,7 @@ static int log_one_extent(struct btrfs_trans_handle *trans, write_extent_buffer(leaf, &fi, btrfs_item_ptr_offset(leaf, path->slots[0]), sizeof(fi)); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); btrfs_release_path(path); diff --git a/fs/btrfs/uuid-tree.c b/fs/btrfs/uuid-tree.c index 7c7001f42b14c..5be74f9e47ebf 100644 --- a/fs/btrfs/uuid-tree.c +++ b/fs/btrfs/uuid-tree.c @@ -124,7 +124,7 @@ int btrfs_uuid_tree_add(struct btrfs_trans_handle *trans, u8 *uuid, u8 type, * An item with that type already exists. * Extend the item and store the new subid at the end. */ - btrfs_extend_item(path, sizeof(subid_le)); + btrfs_extend_item(trans, path, sizeof(subid_le)); eb = path->nodes[0]; slot = path->slots[0]; offset = btrfs_item_ptr_offset(eb, slot); @@ -139,7 +139,7 @@ int btrfs_uuid_tree_add(struct btrfs_trans_handle *trans, u8 *uuid, u8 type, ret = 0; subid_le = cpu_to_le64(subid_cpu); write_extent_buffer(eb, &subid_le, offset, sizeof(subid_le)); - btrfs_mark_buffer_dirty(eb); + btrfs_mark_buffer_dirty(trans, eb); out: btrfs_free_path(path); @@ -221,7 +221,7 @@ int btrfs_uuid_tree_remove(struct btrfs_trans_handle *trans, u8 *uuid, u8 type, move_src = offset + sizeof(subid); move_len = item_size - (move_src - btrfs_item_ptr_offset(eb, slot)); memmove_extent_buffer(eb, move_dst, move_src, move_len); - btrfs_truncate_item(path, item_size - sizeof(subid), 1); + btrfs_truncate_item(trans, path, item_size - sizeof(subid), 1); out: btrfs_free_path(path); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index b9ef6f54635ca..722a1dde75636 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1894,7 +1894,7 @@ static int btrfs_add_dev_item(struct btrfs_trans_handle *trans, ptr = btrfs_device_fsid(dev_item); write_extent_buffer(leaf, trans->fs_info->fs_devices->metadata_uuid, ptr, BTRFS_FSID_SIZE); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); ret = 0; out: @@ -2597,7 +2597,7 @@ static int btrfs_finish_sprout(struct btrfs_trans_handle *trans) if (device->fs_devices->seeding) { btrfs_set_device_generation(leaf, dev_item, device->generation); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); } path->slots[0]++; @@ -2895,7 +2895,7 @@ static noinline int btrfs_update_device(struct btrfs_trans_handle *trans, btrfs_device_get_disk_total_bytes(device)); btrfs_set_device_bytes_used(leaf, dev_item, btrfs_device_get_bytes_used(device)); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); out: btrfs_free_path(path); @@ -3045,15 +3045,16 @@ struct extent_map *btrfs_get_chunk_map(struct btrfs_fs_info *fs_info, read_unlock(&em_tree->lock); if (!em) { - btrfs_crit(fs_info, "unable to find logical %llu length %llu", + btrfs_crit(fs_info, + "unable to find chunk map for logical %llu length %llu", logical, length); return ERR_PTR(-EINVAL); } - if (em->start > logical || em->start + em->len < logical) { + if (em->start > logical || em->start + em->len <= logical) { btrfs_crit(fs_info, - "found a bad mapping, wanted %llu-%llu, found %llu-%llu", - logical, length, em->start, em->start + em->len); + "found a bad chunk map, wanted %llu-%llu, found %llu-%llu", + logical, logical + length, em->start, em->start + em->len); free_extent_map(em); return ERR_PTR(-EINVAL); } @@ -3483,7 +3484,7 @@ static int insert_balance_item(struct btrfs_fs_info *fs_info, btrfs_set_balance_flags(leaf, item, bctl->flags); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); out: btrfs_free_path(path); err = btrfs_commit_transaction(trans); @@ -7534,7 +7535,7 @@ static int update_dev_stat_item(struct btrfs_trans_handle *trans, for (i = 0; i < BTRFS_DEV_STAT_VALUES_MAX; i++) btrfs_set_dev_stats_value(eb, ptr, i, btrfs_dev_stat_read(device, i)); - btrfs_mark_buffer_dirty(eb); + btrfs_mark_buffer_dirty(trans, eb); out: btrfs_free_path(path); diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index 96828a13dd43d..b906f809650ef 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -188,15 +188,15 @@ int btrfs_setxattr(struct btrfs_trans_handle *trans, struct inode *inode, if (old_data_len + name_len + sizeof(*di) == item_size) { /* No other xattrs packed in the same leaf item. */ if (size > old_data_len) - btrfs_extend_item(path, size - old_data_len); + btrfs_extend_item(trans, path, size - old_data_len); else if (size < old_data_len) - btrfs_truncate_item(path, data_size, 1); + btrfs_truncate_item(trans, path, data_size, 1); } else { /* There are other xattrs packed in the same item. */ ret = btrfs_delete_one_dir_name(trans, root, path, di); if (ret) goto out; - btrfs_extend_item(path, data_size); + btrfs_extend_item(trans, path, data_size); } ptr = btrfs_item_ptr(leaf, slot, char); @@ -205,7 +205,7 @@ int btrfs_setxattr(struct btrfs_trans_handle *trans, struct inode *inode, btrfs_set_dir_data_len(leaf, di, size); data_ptr = ((unsigned long)(di + 1)) + name_len; write_extent_buffer(leaf, value, data_ptr, size); - btrfs_mark_buffer_dirty(leaf); + btrfs_mark_buffer_dirty(trans, leaf); } else { /* * Insert, and we had space for the xattr, so path->slots[0] is diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index 992d9c7e64ae6..5ab4b87888a79 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -998,6 +998,14 @@ static int ecryptfs_getattr_link(struct mnt_idmap *idmap, return rc; } +static int ecryptfs_do_getattr(const struct path *path, struct kstat *stat, + u32 request_mask, unsigned int flags) +{ + if (flags & AT_GETATTR_NOSEC) + return vfs_getattr_nosec(path, stat, request_mask, flags); + return vfs_getattr(path, stat, request_mask, flags); +} + static int ecryptfs_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags) @@ -1006,8 +1014,8 @@ static int ecryptfs_getattr(struct mnt_idmap *idmap, struct kstat lower_stat; int rc; - rc = vfs_getattr(ecryptfs_dentry_to_lower_path(dentry), &lower_stat, - request_mask, flags); + rc = ecryptfs_do_getattr(ecryptfs_dentry_to_lower_path(dentry), + &lower_stat, request_mask, flags); if (!rc) { fsstack_copy_attr_all(d_inode(dentry), ecryptfs_inode_to_lower(d_inode(dentry))); diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c index 1b9f587f6cca5..95c51b025b917 100644 --- a/fs/exfat/namei.c +++ b/fs/exfat/namei.c @@ -351,14 +351,20 @@ static int exfat_find_empty_entry(struct inode *inode, if (exfat_check_max_dentries(inode)) return -ENOSPC; - /* we trust p_dir->size regardless of FAT type */ - if (exfat_find_last_cluster(sb, p_dir, &last_clu)) - return -EIO; - /* * Allocate new cluster to this directory */ - exfat_chain_set(&clu, last_clu + 1, 0, p_dir->flags); + if (ei->start_clu != EXFAT_EOF_CLUSTER) { + /* we trust p_dir->size regardless of FAT type */ + if (exfat_find_last_cluster(sb, p_dir, &last_clu)) + return -EIO; + + exfat_chain_set(&clu, last_clu + 1, 0, p_dir->flags); + } else { + /* This directory is empty */ + exfat_chain_set(&clu, EXFAT_EOF_CLUSTER, 0, + ALLOC_NO_FAT_CHAIN); + } /* allocate a cluster */ ret = exfat_alloc_cluster(inode, 1, &clu, IS_DIRSYNC(inode)); @@ -368,6 +374,11 @@ static int exfat_find_empty_entry(struct inode *inode, if (exfat_zeroed_cluster(inode, clu.dir)) return -EIO; + if (ei->start_clu == EXFAT_EOF_CLUSTER) { + ei->start_clu = clu.dir; + p_dir->dir = clu.dir; + } + /* append to the FAT chain */ if (clu.flags != p_dir->flags) { /* no-fat-chain bit is disabled, @@ -645,7 +656,7 @@ static int exfat_find(struct inode *dir, struct qstr *qname, info->type = exfat_get_entry_type(ep); info->attr = le16_to_cpu(ep->dentry.file.attr); info->size = le64_to_cpu(ep2->dentry.stream.valid_size); - if ((info->type == TYPE_FILE) && (info->size == 0)) { + if (info->size == 0) { info->flags = ALLOC_NO_FAT_CHAIN; info->start_clu = EXFAT_EOF_CLUSTER; } else { @@ -888,6 +899,9 @@ static int exfat_check_dir_empty(struct super_block *sb, dentries_per_clu = sbi->dentries_per_clu; + if (p_dir->dir == EXFAT_EOF_CLUSTER) + return 0; + exfat_chain_dup(&clu, p_dir); while (clu.dir != EXFAT_EOF_CLUSTER) { @@ -1255,7 +1269,8 @@ static int __exfat_rename(struct inode *old_parent_inode, } /* Free the clusters if new_inode is a dir(as if exfat_rmdir) */ - if (new_entry_type == TYPE_DIR) { + if (new_entry_type == TYPE_DIR && + new_ei->start_clu != EXFAT_EOF_CLUSTER) { /* new_ei, new_clu_to_free */ struct exfat_chain new_clu_to_free; diff --git a/fs/ext2/file.c b/fs/ext2/file.c index 1039e5bf90afd..4ddc36f4dbd40 100644 --- a/fs/ext2/file.c +++ b/fs/ext2/file.c @@ -258,7 +258,6 @@ static ssize_t ext2_dio_write_iter(struct kiocb *iocb, struct iov_iter *from) goto out_unlock; } - iocb->ki_pos += status; ret += status; endbyte = pos + status - 1; ret2 = filemap_write_and_wait_range(inode->i_mapping, pos, diff --git a/fs/ext4/acl.h b/fs/ext4/acl.h index 0c5a79c3b5d48..ef4c19e5f5706 100644 --- a/fs/ext4/acl.h +++ b/fs/ext4/acl.h @@ -68,6 +68,11 @@ extern int ext4_init_acl(handle_t *, struct inode *, struct inode *); static inline int ext4_init_acl(handle_t *handle, struct inode *inode, struct inode *dir) { + /* usually, the umask is applied by posix_acl_create(), but if + ext4 ACL support is disabled at compile time, we need to do + it here, because posix_acl_create() will never be called */ + inode->i_mode &= ~current_umask(); + return 0; } #endif /* CONFIG_EXT4_FS_POSIX_ACL */ diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 9418359b1d9d3..cd4ccae1e28a1 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1676,7 +1676,8 @@ struct ext4_sb_info { /* * Barrier between writepages ops and changing any inode's JOURNAL_DATA - * or EXTENTS flag. + * or EXTENTS flag or between writepages ops and changing DELALLOC or + * DIOREAD_NOLOCK mount options on remount. */ struct percpu_rw_semaphore s_writepages_rwsem; struct dax_device *s_daxdev; diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c index 6f7de14c0fa86..f4b50652f0cce 100644 --- a/fs/ext4/extents_status.c +++ b/fs/ext4/extents_status.c @@ -152,8 +152,9 @@ static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk, static int es_reclaim_extents(struct ext4_inode_info *ei, int *nr_to_scan); static int __es_shrink(struct ext4_sb_info *sbi, int nr_to_scan, struct ext4_inode_info *locked_ei); -static void __revise_pending(struct inode *inode, ext4_lblk_t lblk, - ext4_lblk_t len); +static int __revise_pending(struct inode *inode, ext4_lblk_t lblk, + ext4_lblk_t len, + struct pending_reservation **prealloc); int __init ext4_init_es(void) { @@ -448,6 +449,19 @@ static void ext4_es_list_del(struct inode *inode) spin_unlock(&sbi->s_es_lock); } +static inline struct pending_reservation *__alloc_pending(bool nofail) +{ + if (!nofail) + return kmem_cache_alloc(ext4_pending_cachep, GFP_ATOMIC); + + return kmem_cache_zalloc(ext4_pending_cachep, GFP_KERNEL | __GFP_NOFAIL); +} + +static inline void __free_pending(struct pending_reservation *pr) +{ + kmem_cache_free(ext4_pending_cachep, pr); +} + /* * Returns true if we cannot fail to allocate memory for this extent_status * entry and cannot reclaim it until its status changes. @@ -836,11 +850,12 @@ void ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk, { struct extent_status newes; ext4_lblk_t end = lblk + len - 1; - int err1 = 0; - int err2 = 0; + int err1 = 0, err2 = 0, err3 = 0; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct extent_status *es1 = NULL; struct extent_status *es2 = NULL; + struct pending_reservation *pr = NULL; + bool revise_pending = false; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return; @@ -868,11 +883,17 @@ void ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk, ext4_es_insert_extent_check(inode, &newes); + revise_pending = sbi->s_cluster_ratio > 1 && + test_opt(inode->i_sb, DELALLOC) && + (status & (EXTENT_STATUS_WRITTEN | + EXTENT_STATUS_UNWRITTEN)); retry: if (err1 && !es1) es1 = __es_alloc_extent(true); if ((err1 || err2) && !es2) es2 = __es_alloc_extent(true); + if ((err1 || err2 || err3) && revise_pending && !pr) + pr = __alloc_pending(true); write_lock(&EXT4_I(inode)->i_es_lock); err1 = __es_remove_extent(inode, lblk, end, NULL, es1); @@ -897,13 +918,18 @@ void ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk, es2 = NULL; } - if (sbi->s_cluster_ratio > 1 && test_opt(inode->i_sb, DELALLOC) && - (status & EXTENT_STATUS_WRITTEN || - status & EXTENT_STATUS_UNWRITTEN)) - __revise_pending(inode, lblk, len); + if (revise_pending) { + err3 = __revise_pending(inode, lblk, len, &pr); + if (err3 != 0) + goto error; + if (pr) { + __free_pending(pr); + pr = NULL; + } + } error: write_unlock(&EXT4_I(inode)->i_es_lock); - if (err1 || err2) + if (err1 || err2 || err3) goto retry; ext4_es_print_tree(inode); @@ -1311,7 +1337,7 @@ static unsigned int get_rsvd(struct inode *inode, ext4_lblk_t end, rc->ndelonly--; node = rb_next(&pr->rb_node); rb_erase(&pr->rb_node, &tree->root); - kmem_cache_free(ext4_pending_cachep, pr); + __free_pending(pr); if (!node) break; pr = rb_entry(node, struct pending_reservation, @@ -1405,8 +1431,8 @@ static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk, } } if (count_reserved) - count_rsvd(inode, lblk, orig_es.es_len - len1 - len2, - &orig_es, &rc); + count_rsvd(inode, orig_es.es_lblk + len1, + orig_es.es_len - len1 - len2, &orig_es, &rc); goto out_get_reserved; } @@ -1907,11 +1933,13 @@ static struct pending_reservation *__get_pending(struct inode *inode, * * @inode - file containing the cluster * @lblk - logical block in the cluster to be added + * @prealloc - preallocated pending entry * * Returns 0 on successful insertion and -ENOMEM on failure. If the * pending reservation is already in the set, returns successfully. */ -static int __insert_pending(struct inode *inode, ext4_lblk_t lblk) +static int __insert_pending(struct inode *inode, ext4_lblk_t lblk, + struct pending_reservation **prealloc) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_pending_tree *tree = &EXT4_I(inode)->i_pending_tree; @@ -1937,10 +1965,15 @@ static int __insert_pending(struct inode *inode, ext4_lblk_t lblk) } } - pr = kmem_cache_alloc(ext4_pending_cachep, GFP_ATOMIC); - if (pr == NULL) { - ret = -ENOMEM; - goto out; + if (likely(*prealloc == NULL)) { + pr = __alloc_pending(false); + if (!pr) { + ret = -ENOMEM; + goto out; + } + } else { + pr = *prealloc; + *prealloc = NULL; } pr->lclu = lclu; @@ -1970,7 +2003,7 @@ static void __remove_pending(struct inode *inode, ext4_lblk_t lblk) if (pr != NULL) { tree = &EXT4_I(inode)->i_pending_tree; rb_erase(&pr->rb_node, &tree->root); - kmem_cache_free(ext4_pending_cachep, pr); + __free_pending(pr); } } @@ -2029,10 +2062,10 @@ void ext4_es_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk, bool allocated) { struct extent_status newes; - int err1 = 0; - int err2 = 0; + int err1 = 0, err2 = 0, err3 = 0; struct extent_status *es1 = NULL; struct extent_status *es2 = NULL; + struct pending_reservation *pr = NULL; if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return; @@ -2052,6 +2085,8 @@ void ext4_es_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk, es1 = __es_alloc_extent(true); if ((err1 || err2) && !es2) es2 = __es_alloc_extent(true); + if ((err1 || err2 || err3) && allocated && !pr) + pr = __alloc_pending(true); write_lock(&EXT4_I(inode)->i_es_lock); err1 = __es_remove_extent(inode, lblk, lblk, NULL, es1); @@ -2074,11 +2109,18 @@ void ext4_es_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk, es2 = NULL; } - if (allocated) - __insert_pending(inode, lblk); + if (allocated) { + err3 = __insert_pending(inode, lblk, &pr); + if (err3 != 0) + goto error; + if (pr) { + __free_pending(pr); + pr = NULL; + } + } error: write_unlock(&EXT4_I(inode)->i_es_lock); - if (err1 || err2) + if (err1 || err2 || err3) goto retry; ext4_es_print_tree(inode); @@ -2184,21 +2226,24 @@ unsigned int ext4_es_delayed_clu(struct inode *inode, ext4_lblk_t lblk, * @inode - file containing the range * @lblk - logical block defining the start of range * @len - length of range in blocks + * @prealloc - preallocated pending entry * * Used after a newly allocated extent is added to the extents status tree. * Requires that the extents in the range have either written or unwritten * status. Must be called while holding i_es_lock. */ -static void __revise_pending(struct inode *inode, ext4_lblk_t lblk, - ext4_lblk_t len) +static int __revise_pending(struct inode *inode, ext4_lblk_t lblk, + ext4_lblk_t len, + struct pending_reservation **prealloc) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); ext4_lblk_t end = lblk + len - 1; ext4_lblk_t first, last; bool f_del = false, l_del = false; + int ret = 0; if (len == 0) - return; + return 0; /* * Two cases - block range within single cluster and block range @@ -2219,7 +2264,9 @@ static void __revise_pending(struct inode *inode, ext4_lblk_t lblk, f_del = __es_scan_range(inode, &ext4_es_is_delonly, first, lblk - 1); if (f_del) { - __insert_pending(inode, first); + ret = __insert_pending(inode, first, prealloc); + if (ret < 0) + goto out; } else { last = EXT4_LBLK_CMASK(sbi, end) + sbi->s_cluster_ratio - 1; @@ -2227,9 +2274,11 @@ static void __revise_pending(struct inode *inode, ext4_lblk_t lblk, l_del = __es_scan_range(inode, &ext4_es_is_delonly, end + 1, last); - if (l_del) - __insert_pending(inode, last); - else + if (l_del) { + ret = __insert_pending(inode, last, prealloc); + if (ret < 0) + goto out; + } else __remove_pending(inode, last); } } else { @@ -2237,18 +2286,24 @@ static void __revise_pending(struct inode *inode, ext4_lblk_t lblk, if (first != lblk) f_del = __es_scan_range(inode, &ext4_es_is_delonly, first, lblk - 1); - if (f_del) - __insert_pending(inode, first); - else + if (f_del) { + ret = __insert_pending(inode, first, prealloc); + if (ret < 0) + goto out; + } else __remove_pending(inode, first); last = EXT4_LBLK_CMASK(sbi, end) + sbi->s_cluster_ratio - 1; if (last != end) l_del = __es_scan_range(inode, &ext4_es_is_delonly, end + 1, last); - if (l_del) - __insert_pending(inode, last); - else + if (l_del) { + ret = __insert_pending(inode, last, prealloc); + if (ret < 0) + goto out; + } else __remove_pending(inode, last); } +out: + return ret; } diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 6830ea3a6c59c..6aa15dafc6778 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -306,80 +306,38 @@ static ssize_t ext4_buffered_write_iter(struct kiocb *iocb, } static ssize_t ext4_handle_inode_extension(struct inode *inode, loff_t offset, - ssize_t written, size_t count) + ssize_t count) { handle_t *handle; - bool truncate = false; - u8 blkbits = inode->i_blkbits; - ext4_lblk_t written_blk, end_blk; - int ret; - - /* - * Note that EXT4_I(inode)->i_disksize can get extended up to - * inode->i_size while the I/O was running due to writeback of delalloc - * blocks. But, the code in ext4_iomap_alloc() is careful to use - * zeroed/unwritten extents if this is possible; thus we won't leave - * uninitialized blocks in a file even if we didn't succeed in writing - * as much as we intended. - */ - WARN_ON_ONCE(i_size_read(inode) < EXT4_I(inode)->i_disksize); - if (offset + count <= EXT4_I(inode)->i_disksize) { - /* - * We need to ensure that the inode is removed from the orphan - * list if it has been added prematurely, due to writeback of - * delalloc blocks. - */ - if (!list_empty(&EXT4_I(inode)->i_orphan) && inode->i_nlink) { - handle = ext4_journal_start(inode, EXT4_HT_INODE, 2); - - if (IS_ERR(handle)) { - ext4_orphan_del(NULL, inode); - return PTR_ERR(handle); - } - - ext4_orphan_del(handle, inode); - ext4_journal_stop(handle); - } - - return written; - } - - if (written < 0) - goto truncate; + lockdep_assert_held_write(&inode->i_rwsem); handle = ext4_journal_start(inode, EXT4_HT_INODE, 2); - if (IS_ERR(handle)) { - written = PTR_ERR(handle); - goto truncate; - } + if (IS_ERR(handle)) + return PTR_ERR(handle); - if (ext4_update_inode_size(inode, offset + written)) { - ret = ext4_mark_inode_dirty(handle, inode); + if (ext4_update_inode_size(inode, offset + count)) { + int ret = ext4_mark_inode_dirty(handle, inode); if (unlikely(ret)) { - written = ret; ext4_journal_stop(handle); - goto truncate; + return ret; } } - /* - * We may need to truncate allocated but not written blocks beyond EOF. - */ - written_blk = ALIGN(offset + written, 1 << blkbits); - end_blk = ALIGN(offset + count, 1 << blkbits); - if (written_blk < end_blk && ext4_can_truncate(inode)) - truncate = true; - - /* - * Remove the inode from the orphan list if it has been extended and - * everything went OK. - */ - if (!truncate && inode->i_nlink) + if (inode->i_nlink) ext4_orphan_del(handle, inode); ext4_journal_stop(handle); - if (truncate) { -truncate: + return count; +} + +/* + * Clean up the inode after DIO or DAX extending write has completed and the + * inode size has been updated using ext4_handle_inode_extension(). + */ +static void ext4_inode_extension_cleanup(struct inode *inode, ssize_t count) +{ + lockdep_assert_held_write(&inode->i_rwsem); + if (count < 0) { ext4_truncate_failed_write(inode); /* * If the truncate operation failed early, then the inode may @@ -388,9 +346,29 @@ static ssize_t ext4_handle_inode_extension(struct inode *inode, loff_t offset, */ if (inode->i_nlink) ext4_orphan_del(NULL, inode); + return; } + /* + * If i_disksize got extended either due to writeback of delalloc + * blocks or extending truncate while the DIO was running we could fail + * to cleanup the orphan list in ext4_handle_inode_extension(). Do it + * now. + */ + if (!list_empty(&EXT4_I(inode)->i_orphan) && inode->i_nlink) { + handle_t *handle = ext4_journal_start(inode, EXT4_HT_INODE, 2); - return written; + if (IS_ERR(handle)) { + /* + * The write has successfully completed. Not much to + * do with the error here so just cleanup the orphan + * list and hope for the best. + */ + ext4_orphan_del(NULL, inode); + return; + } + ext4_orphan_del(handle, inode); + ext4_journal_stop(handle); + } } static int ext4_dio_write_end_io(struct kiocb *iocb, ssize_t size, @@ -399,31 +377,23 @@ static int ext4_dio_write_end_io(struct kiocb *iocb, ssize_t size, loff_t pos = iocb->ki_pos; struct inode *inode = file_inode(iocb->ki_filp); + if (!error && size && flags & IOMAP_DIO_UNWRITTEN) + error = ext4_convert_unwritten_extents(NULL, inode, pos, size); if (error) return error; - - if (size && flags & IOMAP_DIO_UNWRITTEN) { - error = ext4_convert_unwritten_extents(NULL, inode, pos, size); - if (error < 0) - return error; - } /* - * If we are extending the file, we have to update i_size here before - * page cache gets invalidated in iomap_dio_rw(). Otherwise racing - * buffered reads could zero out too much from page cache pages. Update - * of on-disk size will happen later in ext4_dio_write_iter() where - * we have enough information to also perform orphan list handling etc. - * Note that we perform all extending writes synchronously under - * i_rwsem held exclusively so i_size update is safe here in that case. - * If the write was not extending, we cannot see pos > i_size here - * because operations reducing i_size like truncate wait for all - * outstanding DIO before updating i_size. + * Note that EXT4_I(inode)->i_disksize can get extended up to + * inode->i_size while the I/O was running due to writeback of delalloc + * blocks. But the code in ext4_iomap_alloc() is careful to use + * zeroed/unwritten extents if this is possible; thus we won't leave + * uninitialized blocks in a file even if we didn't succeed in writing + * as much as we intended. Also we can race with truncate or write + * expanding the file so we have to be a bit careful here. */ - pos += size; - if (pos > i_size_read(inode)) - i_size_write(inode, pos); - - return 0; + if (pos + size <= READ_ONCE(EXT4_I(inode)->i_disksize) && + pos + size <= i_size_read(inode)) + return size; + return ext4_handle_inode_extension(inode, pos, size); } static const struct iomap_dio_ops ext4_dio_write_ops = { @@ -569,18 +539,20 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from) return ext4_buffered_write_iter(iocb, from); } + /* + * Prevent inline data from being created since we are going to allocate + * blocks for DIO. We know the inode does not currently have inline data + * because ext4_should_use_dio() checked for it, but we have to clear + * the state flag before the write checks because a lock cycle could + * introduce races with other writers. + */ + ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); + ret = ext4_dio_write_checks(iocb, from, &ilock_shared, &extend, &unwritten, &dio_flags); if (ret <= 0) return ret; - /* - * Make sure inline data cannot be created anymore since we are going - * to allocate blocks for DIO. We know the inode does not have any - * inline data now because ext4_dio_supported() checked for that. - */ - ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); - offset = iocb->ki_pos; count = ret; @@ -606,9 +578,16 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from) dio_flags, NULL, 0); if (ret == -ENOTBLK) ret = 0; - - if (extend) - ret = ext4_handle_inode_extension(inode, offset, ret, count); + if (extend) { + /* + * We always perform extending DIO write synchronously so by + * now the IO is completed and ext4_handle_inode_extension() + * was called. Cleanup the inode in case of error or race with + * writeback of delalloc blocks. + */ + WARN_ON_ONCE(ret == -EIOCBQUEUED); + ext4_inode_extension_cleanup(inode, ret); + } out: if (ilock_shared) @@ -689,8 +668,10 @@ ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from) ret = dax_iomap_rw(iocb, from, &ext4_iomap_ops); - if (extend) - ret = ext4_handle_inode_extension(inode, offset, ret, count); + if (extend) { + ret = ext4_handle_inode_extension(inode, offset, ret); + ext4_inode_extension_cleanup(inode, ret); + } out: inode_unlock(inode); if (ret > 0) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 4ce35f1c8b0a8..d7732320431ac 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -789,10 +789,22 @@ int ext4_get_block(struct inode *inode, sector_t iblock, int ext4_get_block_unwritten(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { + int ret = 0; + ext4_debug("ext4_get_block_unwritten: inode %lu, create flag %d\n", inode->i_ino, create); - return _ext4_get_block(inode, iblock, bh_result, + ret = _ext4_get_block(inode, iblock, bh_result, EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT); + + /* + * If the buffer is marked unwritten, mark it as new to make sure it is + * zeroed out correctly in case of partial writes. Otherwise, there is + * a chance of stale data getting exposed. + */ + if (ret == 0 && buffer_unwritten(bh_result)) + set_buffer_new(bh_result); + + return ret; } /* Maximum number of blocks we map for direct IO at once. */ diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 1e599305d85fa..d70f7a06bab47 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -417,8 +417,6 @@ static const char * const ext4_groupinfo_slab_names[NR_GRPINFO_CACHES] = { static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap, ext4_group_t group); -static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap, - ext4_group_t group); static void ext4_mb_new_preallocation(struct ext4_allocation_context *ac); static bool ext4_mb_good_group(struct ext4_allocation_context *ac, @@ -1361,17 +1359,17 @@ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp) * We place the buddy block and bitmap block * close together */ + grinfo = ext4_get_group_info(sb, group); + if (!grinfo) { + err = -EFSCORRUPTED; + goto out; + } if ((first_block + i) & 1) { /* this is block of buddy */ BUG_ON(incore == NULL); mb_debug(sb, "put buddy for group %u in page %lu/%x\n", group, page->index, i * blocksize); trace_ext4_mb_buddy_bitmap_load(sb, group); - grinfo = ext4_get_group_info(sb, group); - if (!grinfo) { - err = -EFSCORRUPTED; - goto out; - } grinfo->bb_fragments = 0; memset(grinfo->bb_counters, 0, sizeof(*grinfo->bb_counters) * @@ -1398,7 +1396,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp) /* mark all preallocated blks used in in-core bitmap */ ext4_mb_generate_from_pa(sb, data, group); - ext4_mb_generate_from_freelist(sb, data, group); + WARN_ON_ONCE(!RB_EMPTY_ROOT(&grinfo->bb_free_root)); ext4_unlock_group(sb, group); /* set incore so that the buddy information can be @@ -4491,6 +4489,10 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac, start = max(start, rounddown(ac->ac_o_ex.fe_logical, (ext4_lblk_t)EXT4_BLOCKS_PER_GROUP(ac->ac_sb))); + /* avoid unnecessary preallocation that may trigger assertions */ + if (start + size > EXT_MAX_BLOCKS) + size = EXT_MAX_BLOCKS - start; + /* don't cover already allocated blocks in selected range */ if (ar->pleft && start <= ar->lleft) { size -= ar->lleft + 1 - start; @@ -4958,31 +4960,6 @@ ext4_mb_use_preallocated(struct ext4_allocation_context *ac) return false; } -/* - * the function goes through all block freed in the group - * but not yet committed and marks them used in in-core bitmap. - * buddy must be generated from this bitmap - * Need to be called with the ext4 group lock held - */ -static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap, - ext4_group_t group) -{ - struct rb_node *n; - struct ext4_group_info *grp; - struct ext4_free_data *entry; - - grp = ext4_get_group_info(sb, group); - if (!grp) - return; - n = rb_first(&(grp->bb_free_root)); - - while (n) { - entry = rb_entry(n, struct ext4_free_data, efd_node); - mb_set_bits(bitmap, entry->efd_start_cluster, entry->efd_count); - n = rb_next(n); - } -} - /* * the function goes through all preallocation in this group and marks them * used in in-core bitmap. buddy must be generated from this bitmap diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 0361c20910def..667381180b261 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -560,13 +560,8 @@ static int setup_new_flex_group_blocks(struct super_block *sb, if (meta_bg == 0 && !ext4_bg_has_super(sb, group)) goto handle_itb; - if (meta_bg == 1) { - ext4_group_t first_group; - first_group = ext4_meta_bg_first_group(sb, group); - if (first_group != group + 1 && - first_group != group + EXT4_DESC_PER_BLOCK(sb) - 1) - goto handle_itb; - } + if (meta_bg == 1) + goto handle_itb; block = start + ext4_bg_has_super(sb, group); /* Copy all of the GDT blocks into the backup in this group */ @@ -1191,8 +1186,10 @@ static void update_backups(struct super_block *sb, sector_t blk_off, char *data, ext4_group_first_block_no(sb, group)); BUFFER_TRACE(bh, "get_write_access"); if ((err = ext4_journal_get_write_access(handle, sb, bh, - EXT4_JTR_NONE))) + EXT4_JTR_NONE))) { + brelse(bh); break; + } lock_buffer(bh); memcpy(bh->b_data, data, size); if (rest) @@ -1601,6 +1598,8 @@ static int ext4_flex_group_add(struct super_block *sb, int gdb_num_end = ((group + flex_gd->count - 1) / EXT4_DESC_PER_BLOCK(sb)); int meta_bg = ext4_has_feature_meta_bg(sb); + sector_t padding_blocks = meta_bg ? 0 : sbi->s_sbh->b_blocknr - + ext4_group_first_block_no(sb, 0); sector_t old_gdb = 0; update_backups(sb, ext4_group_first_block_no(sb, 0), @@ -1612,8 +1611,8 @@ static int ext4_flex_group_add(struct super_block *sb, gdb_num); if (old_gdb == gdb_bh->b_blocknr) continue; - update_backups(sb, gdb_bh->b_blocknr, gdb_bh->b_data, - gdb_bh->b_size, meta_bg); + update_backups(sb, gdb_bh->b_blocknr - padding_blocks, + gdb_bh->b_data, gdb_bh->b_size, meta_bg); old_gdb = gdb_bh->b_blocknr; } } @@ -1980,9 +1979,7 @@ static int ext4_convert_meta_bg(struct super_block *sb, struct inode *inode) errout: ret = ext4_journal_stop(handle); - if (!err) - err = ret; - return ret; + return err ? err : ret; invalid_resize_inode: ext4_error(sb, "corrupted/inconsistent resize inode"); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 6f48dec19f4a2..d062383ea50ef 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -6443,6 +6443,7 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb) struct ext4_mount_options old_opts; ext4_group_t g; int err = 0; + int alloc_ctx; #ifdef CONFIG_QUOTA int enable_quota = 0; int i, j; @@ -6483,7 +6484,16 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb) } + /* + * Changing the DIOREAD_NOLOCK or DELALLOC mount options may cause + * two calls to ext4_should_dioread_nolock() to return inconsistent + * values, triggering WARN_ON in ext4_add_complete_io(). we grab + * here s_writepages_rwsem to avoid race between writepages ops and + * remount. + */ + alloc_ctx = ext4_writepages_down_write(sb); ext4_apply_options(fc, sb); + ext4_writepages_up_write(sb, alloc_ctx); if ((old_opts.s_mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) ^ test_opt(sb, JOURNAL_CHECKSUM)) { @@ -6701,6 +6711,8 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb) if (sb_rdonly(sb) && !(old_sb_flags & SB_RDONLY) && sb_any_quota_suspended(sb)) dquot_resume(sb, -1); + + alloc_ctx = ext4_writepages_down_write(sb); sb->s_flags = old_sb_flags; sbi->s_mount_opt = old_opts.s_mount_opt; sbi->s_mount_opt2 = old_opts.s_mount_opt2; @@ -6709,6 +6721,8 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb) sbi->s_commit_interval = old_opts.s_commit_interval; sbi->s_min_batch_time = old_opts.s_min_batch_time; sbi->s_max_batch_time = old_opts.s_max_batch_time; + ext4_writepages_up_write(sb, alloc_ctx); + if (!test_opt(sb, BLOCK_VALIDITY) && sbi->s_system_blks) ext4_release_system_zone(sb); #ifdef CONFIG_QUOTA diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c index d820801f473e5..7514661bbfbb1 100644 --- a/fs/f2fs/compress.c +++ b/fs/f2fs/compress.c @@ -1976,7 +1976,7 @@ void f2fs_destroy_compress_inode(struct f2fs_sb_info *sbi) int f2fs_init_page_array_cache(struct f2fs_sb_info *sbi) { dev_t dev = sbi->sb->s_bdev->bd_dev; - char slab_name[32]; + char slab_name[35]; if (!f2fs_sb_has_compression(sbi)) return 0; diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c index 0e2d49140c07f..ad8dfac73bd44 100644 --- a/fs/f2fs/extent_cache.c +++ b/fs/f2fs/extent_cache.c @@ -74,40 +74,14 @@ static void __set_extent_info(struct extent_info *ei, } } -static bool __may_read_extent_tree(struct inode *inode) -{ - struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - - if (!test_opt(sbi, READ_EXTENT_CACHE)) - return false; - if (is_inode_flag_set(inode, FI_NO_EXTENT)) - return false; - if (is_inode_flag_set(inode, FI_COMPRESSED_FILE) && - !f2fs_sb_has_readonly(sbi)) - return false; - return S_ISREG(inode->i_mode); -} - -static bool __may_age_extent_tree(struct inode *inode) -{ - struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - - if (!test_opt(sbi, AGE_EXTENT_CACHE)) - return false; - if (is_inode_flag_set(inode, FI_COMPRESSED_FILE)) - return false; - if (file_is_cold(inode)) - return false; - - return S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode); -} - static bool __init_may_extent_tree(struct inode *inode, enum extent_type type) { if (type == EX_READ) - return __may_read_extent_tree(inode); - else if (type == EX_BLOCK_AGE) - return __may_age_extent_tree(inode); + return test_opt(F2FS_I_SB(inode), READ_EXTENT_CACHE) && + S_ISREG(inode->i_mode); + if (type == EX_BLOCK_AGE) + return test_opt(F2FS_I_SB(inode), AGE_EXTENT_CACHE) && + (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)); return false; } @@ -120,7 +94,22 @@ static bool __may_extent_tree(struct inode *inode, enum extent_type type) if (list_empty(&F2FS_I_SB(inode)->s_list)) return false; - return __init_may_extent_tree(inode, type); + if (!__init_may_extent_tree(inode, type)) + return false; + + if (type == EX_READ) { + if (is_inode_flag_set(inode, FI_NO_EXTENT)) + return false; + if (is_inode_flag_set(inode, FI_COMPRESSED_FILE) && + !f2fs_sb_has_readonly(F2FS_I_SB(inode))) + return false; + } else if (type == EX_BLOCK_AGE) { + if (is_inode_flag_set(inode, FI_COMPRESSED_FILE)) + return false; + if (file_is_cold(inode)) + return false; + } + return true; } static void __try_update_largest_extent(struct extent_tree *et, diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index d034703eb323a..a06f03d23762f 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -4006,6 +4006,15 @@ static int f2fs_ioc_set_compress_option(struct file *filp, unsigned long arg) F2FS_I(inode)->i_compress_algorithm = option.algorithm; F2FS_I(inode)->i_log_cluster_size = option.log_cluster_size; F2FS_I(inode)->i_cluster_size = BIT(option.log_cluster_size); + /* Set default level */ + if (F2FS_I(inode)->i_compress_algorithm == COMPRESS_ZSTD) + F2FS_I(inode)->i_compress_level = F2FS_ZSTD_DEFAULT_CLEVEL; + else + F2FS_I(inode)->i_compress_level = 0; + /* Adjust mount option level */ + if (option.algorithm == F2FS_OPTION(sbi).compress_algorithm && + F2FS_OPTION(sbi).compress_level) + F2FS_I(inode)->i_compress_level = F2FS_OPTION(sbi).compress_level; f2fs_mark_inode_dirty_sync(inode, true); if (!f2fs_is_compress_backend_ready(inode)) diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index ee2e1dd64f256..8b30f11f37b46 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -1467,7 +1467,8 @@ static struct page *__get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid, ofs_of_node(page), cpver_of_node(page), next_blkaddr_of_node(page)); set_sbi_flag(sbi, SBI_NEED_FSCK); - err = -EINVAL; + f2fs_handle_error(sbi, ERROR_INCONSISTENT_FOOTER); + err = -EFSCORRUPTED; out_err: ClearPageUptodate(page); out_put_err: @@ -2389,7 +2390,7 @@ static int scan_nat_page(struct f2fs_sb_info *sbi, blk_addr = le32_to_cpu(nat_blk->entries[i].block_addr); if (blk_addr == NEW_ADDR) - return -EINVAL; + return -EFSCORRUPTED; if (blk_addr == NULL_ADDR) { add_free_nid(sbi, start_nid, true, true); @@ -2504,7 +2505,14 @@ static int __f2fs_build_free_nids(struct f2fs_sb_info *sbi, if (ret) { f2fs_up_read(&nm_i->nat_tree_lock); - f2fs_err(sbi, "NAT is corrupt, run fsck to fix it"); + + if (ret == -EFSCORRUPTED) { + f2fs_err(sbi, "NAT is corrupt, run fsck to fix it"); + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_handle_error(sbi, + ERROR_INCONSISTENT_NAT); + } + return ret; } } @@ -2743,7 +2751,9 @@ int f2fs_recover_xattr_data(struct inode *inode, struct page *page) f2fs_update_inode_page(inode); /* 3: update and set xattr node page dirty */ - memcpy(F2FS_NODE(xpage), F2FS_NODE(page), VALID_XATTR_BLOCK_SIZE); + if (page) + memcpy(F2FS_NODE(xpage), F2FS_NODE(page), + VALID_XATTR_BLOCK_SIZE); set_page_dirty(xpage); f2fs_put_page(xpage, 1); diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index a657284faee30..465d145360de3 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -364,10 +364,10 @@ static int lookup_all_xattrs(struct inode *inode, struct page *ipage, *xe = __find_xattr(cur_addr, last_txattr_addr, NULL, index, len, name); if (!*xe) { - f2fs_err(F2FS_I_SB(inode), "inode (%lu) has corrupted xattr", + f2fs_err(F2FS_I_SB(inode), "lookup inode (%lu) has corrupted xattr", inode->i_ino); set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_FSCK); - err = -EFSCORRUPTED; + err = -ENODATA; f2fs_handle_error(F2FS_I_SB(inode), ERROR_CORRUPTED_XATTR); goto out; @@ -584,13 +584,12 @@ ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) if ((void *)(entry) + sizeof(__u32) > last_base_addr || (void *)XATTR_NEXT_ENTRY(entry) > last_base_addr) { - f2fs_err(F2FS_I_SB(inode), "inode (%lu) has corrupted xattr", + f2fs_err(F2FS_I_SB(inode), "list inode (%lu) has corrupted xattr", inode->i_ino); set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_FSCK); - error = -EFSCORRUPTED; f2fs_handle_error(F2FS_I_SB(inode), ERROR_CORRUPTED_XATTR); - goto cleanup; + break; } if (!prefix) @@ -650,7 +649,7 @@ static int __f2fs_setxattr(struct inode *inode, int index, if (size > MAX_VALUE_LEN(inode)) return -E2BIG; - +retry: error = read_all_xattrs(inode, ipage, &base_addr); if (error) return error; @@ -660,7 +659,14 @@ static int __f2fs_setxattr(struct inode *inode, int index, /* find entry with wanted name. */ here = __find_xattr(base_addr, last_base_addr, NULL, index, len, name); if (!here) { - f2fs_err(F2FS_I_SB(inode), "inode (%lu) has corrupted xattr", + if (!F2FS_I(inode)->i_xattr_nid) { + f2fs_notice(F2FS_I_SB(inode), + "recover xattr in inode (%lu)", inode->i_ino); + f2fs_recover_xattr_data(inode, NULL); + kfree(base_addr); + goto retry; + } + f2fs_err(F2FS_I_SB(inode), "set inode (%lu) has corrupted xattr", inode->i_ino); set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_FSCK); error = -EFSCORRUPTED; diff --git a/fs/fuse/dax.c b/fs/fuse/dax.c index 23904a6a9a96f..12ef91d170bb3 100644 --- a/fs/fuse/dax.c +++ b/fs/fuse/dax.c @@ -1222,6 +1222,7 @@ void fuse_dax_conn_free(struct fuse_conn *fc) if (fc->dax) { fuse_free_dax_mem_ranges(&fc->dax->free_ranges); kfree(fc->dax); + fc->dax = NULL; } } diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 1cdb6327511ef..a660f1f21540a 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1448,7 +1448,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter, if (!ia) return -ENOMEM; - if (fopen_direct_io && fc->direct_io_relax) { + if (fopen_direct_io && fc->direct_io_allow_mmap) { res = filemap_write_and_wait_range(mapping, pos, pos + count - 1); if (res) { fuse_io_free(ia); @@ -1574,6 +1574,7 @@ static ssize_t fuse_direct_write_iter(struct kiocb *iocb, struct iov_iter *from) ssize_t res; bool exclusive_lock = !(ff->open_flags & FOPEN_PARALLEL_DIRECT_WRITES) || + get_fuse_conn(inode)->direct_io_allow_mmap || iocb->ki_flags & IOCB_APPEND || fuse_direct_write_extending_i_size(iocb, from); @@ -1581,6 +1582,7 @@ static ssize_t fuse_direct_write_iter(struct kiocb *iocb, struct iov_iter *from) * Take exclusive lock if * - Parallel direct writes are disabled - a user space decision * - Parallel direct writes are enabled and i_size is being extended. + * - Shared mmap on direct_io file is supported (FUSE_DIRECT_IO_ALLOW_MMAP). * This might not be needed at all, but needs further investigation. */ if (exclusive_lock) @@ -2466,9 +2468,9 @@ static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma) if (ff->open_flags & FOPEN_DIRECT_IO) { /* Can't provide the coherency needed for MAP_SHARED - * if FUSE_DIRECT_IO_RELAX isn't set. + * if FUSE_DIRECT_IO_ALLOW_MMAP isn't set. */ - if ((vma->vm_flags & VM_MAYSHARE) && !fc->direct_io_relax) + if ((vma->vm_flags & VM_MAYSHARE) && !fc->direct_io_allow_mmap) return -ENODEV; invalidate_inode_pages2(file->f_mapping); diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index bf0b85d0b95c7..9377c46f14c4a 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -63,6 +63,19 @@ struct fuse_forget_link { struct fuse_forget_link *next; }; +/* Submount lookup tracking */ +struct fuse_submount_lookup { + /** Refcount */ + refcount_t count; + + /** Unique ID, which identifies the inode between userspace + * and kernel */ + u64 nodeid; + + /** The request used for sending the FORGET message */ + struct fuse_forget_link *forget; +}; + /** FUSE inode */ struct fuse_inode { /** Inode data */ @@ -158,6 +171,8 @@ struct fuse_inode { */ struct fuse_inode_dax *dax; #endif + /** Submount specific lookup tracking */ + struct fuse_submount_lookup *submount_lookup; }; /** FUSE inode state bits */ @@ -797,8 +812,8 @@ struct fuse_conn { /* Is tmpfile not implemented by fs? */ unsigned int no_tmpfile:1; - /* relax restrictions in FOPEN_DIRECT_IO mode */ - unsigned int direct_io_relax:1; + /* Relax restrictions to allow shared mmap in FOPEN_DIRECT_IO mode */ + unsigned int direct_io_allow_mmap:1; /* Is statx not implemented by fs? */ unsigned int no_statx:1; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 2e4eb7cf26fb3..59743813563e5 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -68,6 +68,24 @@ struct fuse_forget_link *fuse_alloc_forget(void) return kzalloc(sizeof(struct fuse_forget_link), GFP_KERNEL_ACCOUNT); } +static struct fuse_submount_lookup *fuse_alloc_submount_lookup(void) +{ + struct fuse_submount_lookup *sl; + + sl = kzalloc(sizeof(struct fuse_submount_lookup), GFP_KERNEL_ACCOUNT); + if (!sl) + return NULL; + sl->forget = fuse_alloc_forget(); + if (!sl->forget) + goto out_free; + + return sl; + +out_free: + kfree(sl); + return NULL; +} + static struct inode *fuse_alloc_inode(struct super_block *sb) { struct fuse_inode *fi; @@ -83,6 +101,7 @@ static struct inode *fuse_alloc_inode(struct super_block *sb) fi->attr_version = 0; fi->orig_ino = 0; fi->state = 0; + fi->submount_lookup = NULL; mutex_init(&fi->mutex); spin_lock_init(&fi->lock); fi->forget = fuse_alloc_forget(); @@ -113,6 +132,17 @@ static void fuse_free_inode(struct inode *inode) kmem_cache_free(fuse_inode_cachep, fi); } +static void fuse_cleanup_submount_lookup(struct fuse_conn *fc, + struct fuse_submount_lookup *sl) +{ + if (!refcount_dec_and_test(&sl->count)) + return; + + fuse_queue_forget(fc, sl->forget, sl->nodeid, 1); + sl->forget = NULL; + kfree(sl); +} + static void fuse_evict_inode(struct inode *inode) { struct fuse_inode *fi = get_fuse_inode(inode); @@ -132,6 +162,11 @@ static void fuse_evict_inode(struct inode *inode) fi->nlookup); fi->forget = NULL; } + + if (fi->submount_lookup) { + fuse_cleanup_submount_lookup(fc, fi->submount_lookup); + fi->submount_lookup = NULL; + } } if (S_ISREG(inode->i_mode) && !fuse_is_bad(inode)) { WARN_ON(!list_empty(&fi->write_files)); @@ -332,6 +367,13 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr, fuse_dax_dontcache(inode, attr->flags); } +static void fuse_init_submount_lookup(struct fuse_submount_lookup *sl, + u64 nodeid) +{ + sl->nodeid = nodeid; + refcount_set(&sl->count, 1); +} + static void fuse_init_inode(struct inode *inode, struct fuse_attr *attr, struct fuse_conn *fc) { @@ -395,12 +437,22 @@ struct inode *fuse_iget(struct super_block *sb, u64 nodeid, */ if (fc->auto_submounts && (attr->flags & FUSE_ATTR_SUBMOUNT) && S_ISDIR(attr->mode)) { + struct fuse_inode *fi; + inode = new_inode(sb); if (!inode) return NULL; fuse_init_inode(inode, attr, fc); - get_fuse_inode(inode)->nodeid = nodeid; + fi = get_fuse_inode(inode); + fi->nodeid = nodeid; + fi->submount_lookup = fuse_alloc_submount_lookup(); + if (!fi->submount_lookup) { + iput(inode); + return NULL; + } + /* Sets nlookup = 1 on fi->submount_lookup->nlookup */ + fuse_init_submount_lookup(fi->submount_lookup, nodeid); inode->i_flags |= S_AUTOMOUNT; goto done; } @@ -423,11 +475,11 @@ struct inode *fuse_iget(struct super_block *sb, u64 nodeid, iput(inode); goto retry; } -done: fi = get_fuse_inode(inode); spin_lock(&fi->lock); fi->nlookup++; spin_unlock(&fi->lock); +done: fuse_change_attributes(inode, attr, NULL, attr_valid, attr_version); return inode; @@ -1232,8 +1284,8 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args, fc->init_security = 1; if (flags & FUSE_CREATE_SUPP_GROUP) fc->create_supp_group = 1; - if (flags & FUSE_DIRECT_IO_RELAX) - fc->direct_io_relax = 1; + if (flags & FUSE_DIRECT_IO_ALLOW_MMAP) + fc->direct_io_allow_mmap = 1; } else { ra_pages = fc->max_read / PAGE_SIZE; fc->no_lock = 1; @@ -1280,7 +1332,7 @@ void fuse_send_init(struct fuse_mount *fm) FUSE_NO_OPENDIR_SUPPORT | FUSE_EXPLICIT_INVAL_DATA | FUSE_HANDLE_KILLPRIV_V2 | FUSE_SETXATTR_EXT | FUSE_INIT_EXT | FUSE_SECURITY_CTX | FUSE_CREATE_SUPP_GROUP | - FUSE_HAS_EXPIRE_ONLY | FUSE_DIRECT_IO_RELAX; + FUSE_HAS_EXPIRE_ONLY | FUSE_DIRECT_IO_ALLOW_MMAP; #ifdef CONFIG_FUSE_DAX if (fm->fc->dax) flags |= FUSE_MAP_ALIGNMENT; @@ -1465,6 +1517,8 @@ static int fuse_fill_super_submount(struct super_block *sb, struct super_block *parent_sb = parent_fi->inode.i_sb; struct fuse_attr root_attr; struct inode *root; + struct fuse_submount_lookup *sl; + struct fuse_inode *fi; fuse_sb_defaults(sb); fm->sb = sb; @@ -1487,12 +1541,27 @@ static int fuse_fill_super_submount(struct super_block *sb, * its nlookup should not be incremented. fuse_iget() does * that, though, so undo it here. */ - get_fuse_inode(root)->nlookup--; + fi = get_fuse_inode(root); + fi->nlookup--; + sb->s_d_op = &fuse_dentry_operations; sb->s_root = d_make_root(root); if (!sb->s_root) return -ENOMEM; + /* + * Grab the parent's submount_lookup pointer and take a + * reference on the shared nlookup from the parent. This is to + * prevent the last forget for this nodeid from getting + * triggered until all users have finished with it. + */ + sl = parent_fi->submount_lookup; + WARN_ON(!sl); + if (sl) { + refcount_inc(&sl->count); + fi->submount_lookup = sl; + } + return 0; } diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 0eac045079047..4e63fbb63151c 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -1866,16 +1866,24 @@ static const char *gfs2_get_link(struct dentry *dentry, int gfs2_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { + int may_not_block = mask & MAY_NOT_BLOCK; struct gfs2_inode *ip; struct gfs2_holder i_gh; + struct gfs2_glock *gl; int error; gfs2_holder_mark_uninitialized(&i_gh); ip = GFS2_I(inode); - if (gfs2_glock_is_locked_by_me(ip->i_gl) == NULL) { - if (mask & MAY_NOT_BLOCK) + gl = rcu_dereference_check(ip->i_gl, !may_not_block); + if (unlikely(!gl)) { + /* inode is getting torn down, must be RCU mode */ + WARN_ON_ONCE(!may_not_block); + return -ECHILD; + } + if (gfs2_glock_is_locked_by_me(gl) == NULL) { + if (may_not_block) return -ECHILD; - error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &i_gh); + error = gfs2_glock_nq_init(gl, LM_ST_SHARED, LM_FLAG_ANY, &i_gh); if (error) return error; } diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 33ca04733e933..dd64140ae6d7b 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -1281,10 +1281,8 @@ static int gfs2_fill_super(struct super_block *sb, struct fs_context *fc) if (!sb_rdonly(sb)) { error = init_threads(sdp); - if (error) { - gfs2_withdraw_delayed(sdp); + if (error) goto fail_per_node; - } } error = gfs2_freeze_lock_shared(sdp); diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 171b2713d2e5e..41d0232532a03 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -457,6 +457,17 @@ static int qd_check_sync(struct gfs2_sbd *sdp, struct gfs2_quota_data *qd, (sync_gen && (qd->qd_sync_gen >= *sync_gen))) return 0; + /* + * If qd_change is 0 it means a pending quota change was negated. + * We should not sync it, but we still have a qd reference and slot + * reference taken by gfs2_quota_change -> do_qc that need to be put. + */ + if (!qd->qd_change && test_and_clear_bit(QDF_CHANGE, &qd->qd_flags)) { + slot_put(qd); + qd_put(qd); + return 0; + } + if (!lockref_get_not_dead(&qd->qd_lockref)) return 0; diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 02d93da21b2b0..5f4ebe279aaae 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -602,13 +602,15 @@ static void gfs2_put_super(struct super_block *sb) } spin_unlock(&sdp->sd_jindex_spin); - if (!sb_rdonly(sb)) { + if (!sb_rdonly(sb)) gfs2_make_fs_ro(sdp); - } - if (gfs2_withdrawn(sdp)) { - gfs2_destroy_threads(sdp); + else { + if (gfs2_withdrawn(sdp)) + gfs2_destroy_threads(sdp); + gfs2_quota_cleanup(sdp); } + WARN_ON(gfs2_withdrawing(sdp)); /* At this point, we're through modifying the disk */ @@ -1550,7 +1552,7 @@ static void gfs2_evict_inode(struct inode *inode) wait_on_bit_io(&ip->i_flags, GIF_GLOP_PENDING, TASK_UNINTERRUPTIBLE); gfs2_glock_add_to_lru(ip->i_gl); gfs2_glock_put_eventually(ip->i_gl); - ip->i_gl = NULL; + rcu_assign_pointer(ip->i_gl, NULL); } } diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 316c4cebd3f3d..60fce26ff9378 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -295,7 +295,7 @@ static size_t adjust_range_hwpoison(struct page *page, size_t offset, size_t byt size_t res = 0; /* First subpage to start the loop. */ - page += offset / PAGE_SIZE; + page = nth_page(page, offset / PAGE_SIZE); offset %= PAGE_SIZE; while (1) { if (is_raw_hwpoison_page_in_hugepage(page)) @@ -309,7 +309,7 @@ static size_t adjust_range_hwpoison(struct page *page, size_t offset, size_t byt break; offset += n; if (offset == PAGE_SIZE) { - page++; + page = nth_page(page, 1); offset = 0; } } diff --git a/fs/inode.c b/fs/inode.c index 84bc3c76e5ccb..ae1a6410b53d7 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -215,6 +215,8 @@ int inode_init_always(struct super_block *sb, struct inode *inode) lockdep_set_class_and_name(&mapping->invalidate_lock, &sb->s_type->invalidate_lock_key, "mapping.invalidate_lock"); + if (sb->s_iflags & SB_I_STABLE_WRITES) + mapping_set_stable_writes(mapping); inode->i_private = NULL; inode->i_mapping = mapping; INIT_HLIST_HEAD(&inode->i_dentry); /* buggered by rcu freeing */ diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c index c269a7d29a465..5b771a3d8d9ae 100644 --- a/fs/jbd2/recovery.c +++ b/fs/jbd2/recovery.c @@ -289,6 +289,8 @@ int jbd2_journal_recover(journal_t *journal) journal_superblock_t * sb; struct recovery_info info; + errseq_t wb_err; + struct address_space *mapping; memset(&info, 0, sizeof(info)); sb = journal->j_superblock; @@ -306,6 +308,9 @@ int jbd2_journal_recover(journal_t *journal) return 0; } + wb_err = 0; + mapping = journal->j_fs_dev->bd_inode->i_mapping; + errseq_check_and_advance(&mapping->wb_err, &wb_err); err = do_one_pass(journal, &info, PASS_SCAN); if (!err) err = do_one_pass(journal, &info, PASS_REVOKE); @@ -327,6 +332,9 @@ int jbd2_journal_recover(journal_t *journal) jbd2_journal_clear_revoke(journal); err2 = sync_blockdev(journal->j_fs_dev); + if (!err) + err = err2; + err2 = errseq_check_and_advance(&mapping->wb_err, &wb_err); if (!err) err = err2; /* Make sure all replayed data is on permanent storage */ diff --git a/fs/jfs/jfs_dmap.c b/fs/jfs/jfs_dmap.c index 88afd108c2dd2..11c77757ead9e 100644 --- a/fs/jfs/jfs_dmap.c +++ b/fs/jfs/jfs_dmap.c @@ -87,7 +87,7 @@ static int dbAllocCtl(struct bmap * bmp, s64 nblocks, int l2nb, s64 blkno, static int dbExtend(struct inode *ip, s64 blkno, s64 nblocks, s64 addnblocks); static int dbFindBits(u32 word, int l2nb); static int dbFindCtl(struct bmap * bmp, int l2nb, int level, s64 * blkno); -static int dbFindLeaf(dmtree_t * tp, int l2nb, int *leafidx); +static int dbFindLeaf(dmtree_t *tp, int l2nb, int *leafidx, bool is_ctl); static int dbFreeBits(struct bmap * bmp, struct dmap * dp, s64 blkno, int nblocks); static int dbFreeDmap(struct bmap * bmp, struct dmap * dp, s64 blkno, @@ -180,7 +180,8 @@ int dbMount(struct inode *ipbmap) bmp->db_nfree = le64_to_cpu(dbmp_le->dn_nfree); bmp->db_l2nbperpage = le32_to_cpu(dbmp_le->dn_l2nbperpage); - if (bmp->db_l2nbperpage > L2PSIZE - L2MINBLOCKSIZE) { + if (bmp->db_l2nbperpage > L2PSIZE - L2MINBLOCKSIZE || + bmp->db_l2nbperpage < 0) { err = -EINVAL; goto err_release_metapage; } @@ -194,6 +195,12 @@ int dbMount(struct inode *ipbmap) bmp->db_maxlevel = le32_to_cpu(dbmp_le->dn_maxlevel); bmp->db_maxag = le32_to_cpu(dbmp_le->dn_maxag); bmp->db_agpref = le32_to_cpu(dbmp_le->dn_agpref); + if (bmp->db_maxag >= MAXAG || bmp->db_maxag < 0 || + bmp->db_agpref >= MAXAG || bmp->db_agpref < 0) { + err = -EINVAL; + goto err_release_metapage; + } + bmp->db_aglevel = le32_to_cpu(dbmp_le->dn_aglevel); bmp->db_agheight = le32_to_cpu(dbmp_le->dn_agheight); bmp->db_agwidth = le32_to_cpu(dbmp_le->dn_agwidth); @@ -1710,7 +1717,7 @@ static int dbFindCtl(struct bmap * bmp, int l2nb, int level, s64 * blkno) * dbFindLeaf() returns the index of the leaf at which * free space was found. */ - rc = dbFindLeaf((dmtree_t *) dcp, l2nb, &leafidx); + rc = dbFindLeaf((dmtree_t *) dcp, l2nb, &leafidx, true); /* release the buffer. */ @@ -1957,7 +1964,7 @@ dbAllocDmapLev(struct bmap * bmp, * free space. if sufficient free space is found, dbFindLeaf() * returns the index of the leaf at which free space was found. */ - if (dbFindLeaf((dmtree_t *) & dp->tree, l2nb, &leafidx)) + if (dbFindLeaf((dmtree_t *) &dp->tree, l2nb, &leafidx, false)) return -ENOSPC; if (leafidx < 0) @@ -2921,14 +2928,18 @@ static void dbAdjTree(dmtree_t * tp, int leafno, int newval) * leafidx - return pointer to be set to the index of the leaf * describing at least l2nb free blocks if sufficient * free blocks are found. + * is_ctl - determines if the tree is of type ctl * * RETURN VALUES: * 0 - success * -ENOSPC - insufficient free blocks. */ -static int dbFindLeaf(dmtree_t * tp, int l2nb, int *leafidx) +static int dbFindLeaf(dmtree_t *tp, int l2nb, int *leafidx, bool is_ctl) { int ti, n = 0, k, x = 0; + int max_size; + + max_size = is_ctl ? CTLTREESIZE : TREESIZE; /* first check the root of the tree to see if there is * sufficient free space. @@ -2949,6 +2960,8 @@ static int dbFindLeaf(dmtree_t * tp, int l2nb, int *leafidx) /* sufficient free space found. move to the next * level (or quit if this is the last level). */ + if (x + n > max_size) + return -ENOSPC; if (l2nb <= tp->dmt_stree[x + n]) break; } diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c index 923a58422c461..1b267eec3f367 100644 --- a/fs/jfs/jfs_imap.c +++ b/fs/jfs/jfs_imap.c @@ -1320,7 +1320,7 @@ diInitInode(struct inode *ip, int iagno, int ino, int extno, struct iag * iagp) int diAlloc(struct inode *pip, bool dir, struct inode *ip) { int rc, ino, iagno, addext, extno, bitno, sword; - int nwords, rem, i, agno; + int nwords, rem, i, agno, dn_numag; u32 mask, inosmap, extsmap; struct inode *ipimap; struct metapage *mp; @@ -1356,6 +1356,9 @@ int diAlloc(struct inode *pip, bool dir, struct inode *ip) /* get the ag number of this iag */ agno = BLKTOAG(JFS_IP(pip)->agstart, JFS_SBI(pip->i_sb)); + dn_numag = JFS_SBI(pip->i_sb)->bmap->db_numag; + if (agno < 0 || agno > dn_numag) + return -EIO; if (atomic_read(&JFS_SBI(pip->i_sb)->bmap->db_active[agno])) { /* diff --git a/fs/libfs.c b/fs/libfs.c index 37f2d34ee090b..dc0f7519045f1 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -396,6 +396,8 @@ static loff_t offset_dir_llseek(struct file *file, loff_t offset, int whence) return -EINVAL; } + /* In this case, ->private_data is protected by f_pos_lock */ + file->private_data = NULL; return vfs_setpos(file, offset, U32_MAX); } @@ -425,7 +427,7 @@ static bool offset_dir_emit(struct dir_context *ctx, struct dentry *dentry) inode->i_ino, fs_umode_to_dtype(inode->i_mode)); } -static void offset_iterate_dir(struct inode *inode, struct dir_context *ctx) +static void *offset_iterate_dir(struct inode *inode, struct dir_context *ctx) { struct offset_ctx *so_ctx = inode->i_op->get_offset_ctx(inode); XA_STATE(xas, &so_ctx->xa, ctx->pos); @@ -434,7 +436,7 @@ static void offset_iterate_dir(struct inode *inode, struct dir_context *ctx) while (true) { dentry = offset_find_next(&xas); if (!dentry) - break; + return ERR_PTR(-ENOENT); if (!offset_dir_emit(ctx, dentry)) { dput(dentry); @@ -444,6 +446,7 @@ static void offset_iterate_dir(struct inode *inode, struct dir_context *ctx) dput(dentry); ctx->pos = xas.xa_index + 1; } + return NULL; } /** @@ -476,7 +479,12 @@ static int offset_readdir(struct file *file, struct dir_context *ctx) if (!dir_emit_dots(file, ctx)) return 0; - offset_iterate_dir(d_inode(dir), ctx); + /* In this case, ->private_data is protected by f_pos_lock */ + if (ctx->pos == 2) + file->private_data = NULL; + else if (file->private_data == ERR_PTR(-ENOENT)) + return 0; + file->private_data = offset_iterate_dir(d_inode(dir), ctx); return 0; } @@ -541,7 +549,8 @@ void simple_recursive_removal(struct dentry *dentry, dput(victim); // unpin it } if (victim == dentry) { - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, + inode_set_ctime_current(inode)); if (d_is_dir(dentry)) drop_nlink(inode); inode_unlock(inode); @@ -582,7 +591,7 @@ static int pseudo_fs_fill_super(struct super_block *s, struct fs_context *fc) */ root->i_ino = 1; root->i_mode = S_IFDIR | S_IRUSR | S_IWUSR; - root->i_atime = root->i_mtime = inode_set_ctime_current(root); + simple_inode_init_ts(root); s->s_root = d_make_root(root); if (!s->s_root) return -ENOMEM; @@ -638,8 +647,8 @@ int simple_link(struct dentry *old_dentry, struct inode *dir, struct dentry *den { struct inode *inode = d_inode(old_dentry); - dir->i_mtime = inode_set_ctime_to_ts(dir, - inode_set_ctime_current(inode)); + inode_set_mtime_to_ts(dir, + inode_set_ctime_to_ts(dir, inode_set_ctime_current(inode))); inc_nlink(inode); ihold(inode); dget(dentry); @@ -673,8 +682,8 @@ int simple_unlink(struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(dentry); - dir->i_mtime = inode_set_ctime_to_ts(dir, - inode_set_ctime_current(inode)); + inode_set_mtime_to_ts(dir, + inode_set_ctime_to_ts(dir, inode_set_ctime_current(inode))); drop_nlink(inode); dput(dentry); return 0; @@ -709,9 +718,10 @@ void simple_rename_timestamp(struct inode *old_dir, struct dentry *old_dentry, { struct inode *newino = d_inode(new_dentry); - old_dir->i_mtime = inode_set_ctime_current(old_dir); + inode_set_mtime_to_ts(old_dir, inode_set_ctime_current(old_dir)); if (new_dir != old_dir) - new_dir->i_mtime = inode_set_ctime_current(new_dir); + inode_set_mtime_to_ts(new_dir, + inode_set_ctime_current(new_dir)); inode_set_ctime_current(d_inode(old_dentry)); if (newino) inode_set_ctime_current(newino); @@ -926,7 +936,7 @@ int simple_fill_super(struct super_block *s, unsigned long magic, */ inode->i_ino = 1; inode->i_mode = S_IFDIR | 0755; - inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); inode->i_op = &simple_dir_inode_operations; inode->i_fop = &simple_dir_operations; set_nlink(inode, 2); @@ -952,7 +962,7 @@ int simple_fill_super(struct super_block *s, unsigned long magic, goto out; } inode->i_mode = S_IFREG | files->mode; - inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); inode->i_fop = files->ops; inode->i_ino = i; d_add(dentry, inode); @@ -1520,7 +1530,7 @@ struct inode *alloc_anon_inode(struct super_block *s) inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); inode->i_flags |= S_PRIVATE; - inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); return inode; } EXPORT_SYMBOL(alloc_anon_inode); @@ -1912,3 +1922,20 @@ ssize_t direct_write_fallback(struct kiocb *iocb, struct iov_iter *iter, return direct_written + buffered_written; } EXPORT_SYMBOL_GPL(direct_write_fallback); + +/** + * simple_inode_init_ts - initialize the timestamps for a new inode + * @inode: inode to be initialized + * + * When a new inode is created, most filesystems set the timestamps to the + * current time. Add a helper to do this. + */ +struct timespec64 simple_inode_init_ts(struct inode *inode) +{ + struct timespec64 ts = inode_set_ctime_current(inode); + + inode_set_atime_to_ts(inode, ts); + inode_set_mtime_to_ts(inode, ts); + return ts; +} +EXPORT_SYMBOL(simple_inode_init_ts); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 19eba711b32fc..3b01f4b12e9b2 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5629,7 +5629,7 @@ static void nfs4_proc_write_setup(struct nfs_pgio_header *hdr, msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_WRITE]; nfs4_init_sequence(&hdr->args.seq_args, &hdr->res.seq_res, 0, 0); - nfs4_state_protect_write(server->nfs_client, clnt, msg, hdr); + nfs4_state_protect_write(hdr->ds_clp ? hdr->ds_clp : server->nfs_client, clnt, msg, hdr); } static void nfs4_proc_commit_rpc_prepare(struct rpc_task *task, struct nfs_commit_data *data) @@ -5670,7 +5670,8 @@ static void nfs4_proc_commit_setup(struct nfs_commit_data *data, struct rpc_mess data->res.server = server; msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_COMMIT]; nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 1, 0); - nfs4_state_protect(server->nfs_client, NFS_SP4_MACH_CRED_COMMIT, clnt, msg); + nfs4_state_protect(data->ds_clp ? data->ds_clp : server->nfs_client, + NFS_SP4_MACH_CRED_COMMIT, clnt, msg); } static int _nfs4_proc_commit(struct file *dst, struct nfs_commitargs *args, @@ -9443,6 +9444,7 @@ void nfs4_test_session_trunk(struct rpc_clnt *clnt, struct rpc_xprt *xprt, sp4_how = (adata->clp->cl_sp4_flags == 0 ? SP4_NONE : SP4_MACH_CRED); +try_again: /* Test connection for session trunking. Async exchange_id call */ task = nfs4_run_exchange_id(adata->clp, adata->cred, sp4_how, xprt); if (IS_ERR(task)) @@ -9455,11 +9457,15 @@ void nfs4_test_session_trunk(struct rpc_clnt *clnt, struct rpc_xprt *xprt, if (status == 0) rpc_clnt_xprt_switch_add_xprt(clnt, xprt); - else if (rpc_clnt_xprt_switch_has_addr(clnt, + else if (status != -NFS4ERR_DELAY && rpc_clnt_xprt_switch_has_addr(clnt, (struct sockaddr *)&xprt->addr)) rpc_clnt_xprt_switch_remove_xprt(clnt, xprt); rpc_put_task(task); + if (status == -NFS4ERR_DELAY) { + ssleep(1); + goto try_again; + } } EXPORT_SYMBOL_GPL(nfs4_test_session_trunk); diff --git a/fs/nfsd/auth.c b/fs/nfsd/auth.c index fdf2aad734709..e6beaaf4f1700 100644 --- a/fs/nfsd/auth.c +++ b/fs/nfsd/auth.c @@ -26,8 +26,6 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp) int i; int flags = nfsexp_flags(rqstp, exp); - validate_process_creds(); - /* discard any old override before preparing the new set */ revert_creds(get_cred(current_real_cred())); new = prepare_creds(); @@ -81,10 +79,8 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp) else new->cap_effective = cap_raise_nfsd_set(new->cap_effective, new->cap_permitted); - validate_process_creds(); put_cred(override_creds(new)); put_cred(new); - validate_process_creds(); return 0; oom: diff --git a/fs/nfsd/cache.h b/fs/nfsd/cache.h index 929248c6ca84c..4cbe0434cbb8c 100644 --- a/fs/nfsd/cache.h +++ b/fs/nfsd/cache.h @@ -84,8 +84,8 @@ int nfsd_net_reply_cache_init(struct nfsd_net *nn); void nfsd_net_reply_cache_destroy(struct nfsd_net *nn); int nfsd_reply_cache_init(struct nfsd_net *); void nfsd_reply_cache_shutdown(struct nfsd_net *); -int nfsd_cache_lookup(struct svc_rqst *rqstp, - struct nfsd_cacherep **cacherep); +int nfsd_cache_lookup(struct svc_rqst *rqstp, unsigned int start, + unsigned int len, struct nfsd_cacherep **cacherep); void nfsd_cache_update(struct svc_rqst *rqstp, struct nfsd_cacherep *rp, int cachetype, __be32 *statp); int nfsd_reply_cache_stats_show(struct seq_file *m, void *v); diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 8534693eb6a49..529b3ed3b3177 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -2797,7 +2797,7 @@ static int client_opens_release(struct inode *inode, struct file *file) /* XXX: alternatively, we could get/drop in seq start/stop */ drop_client(clp); - return 0; + return seq_release(inode, file); } static const struct file_operations client_states_fops = { diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index 80621a7095107..6cd36af2f97e1 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -368,33 +368,52 @@ nfsd_reply_cache_scan(struct shrinker *shrink, struct shrink_control *sc) return freed; } -/* - * Walk an xdr_buf and get a CRC for at most the first RC_CSUMLEN bytes +/** + * nfsd_cache_csum - Checksum incoming NFS Call arguments + * @buf: buffer containing a whole RPC Call message + * @start: starting byte of the NFS Call header + * @remaining: size of the NFS Call header, in bytes + * + * Compute a weak checksum of the leading bytes of an NFS procedure + * call header to help verify that a retransmitted Call matches an + * entry in the duplicate reply cache. + * + * To avoid assumptions about how the RPC message is laid out in + * @buf and what else it might contain (eg, a GSS MIC suffix), the + * caller passes us the exact location and length of the NFS Call + * header. + * + * Returns a 32-bit checksum value, as defined in RFC 793. */ -static __wsum -nfsd_cache_csum(struct svc_rqst *rqstp) +static __wsum nfsd_cache_csum(struct xdr_buf *buf, unsigned int start, + unsigned int remaining) { + unsigned int base, len; + struct xdr_buf subbuf; + __wsum csum = 0; + void *p; int idx; - unsigned int base; - __wsum csum; - struct xdr_buf *buf = &rqstp->rq_arg; - const unsigned char *p = buf->head[0].iov_base; - size_t csum_len = min_t(size_t, buf->head[0].iov_len + buf->page_len, - RC_CSUMLEN); - size_t len = min(buf->head[0].iov_len, csum_len); + + if (remaining > RC_CSUMLEN) + remaining = RC_CSUMLEN; + if (xdr_buf_subsegment(buf, &subbuf, start, remaining)) + return csum; /* rq_arg.head first */ - csum = csum_partial(p, len, 0); - csum_len -= len; + if (subbuf.head[0].iov_len) { + len = min_t(unsigned int, subbuf.head[0].iov_len, remaining); + csum = csum_partial(subbuf.head[0].iov_base, len, csum); + remaining -= len; + } /* Continue into page array */ - idx = buf->page_base / PAGE_SIZE; - base = buf->page_base & ~PAGE_MASK; - while (csum_len) { - p = page_address(buf->pages[idx]) + base; - len = min_t(size_t, PAGE_SIZE - base, csum_len); + idx = subbuf.page_base / PAGE_SIZE; + base = subbuf.page_base & ~PAGE_MASK; + while (remaining) { + p = page_address(subbuf.pages[idx]) + base; + len = min_t(unsigned int, PAGE_SIZE - base, remaining); csum = csum_partial(p, len, csum); - csum_len -= len; + remaining -= len; base = 0; ++idx; } @@ -465,6 +484,8 @@ nfsd_cache_insert(struct nfsd_drc_bucket *b, struct nfsd_cacherep *key, /** * nfsd_cache_lookup - Find an entry in the duplicate reply cache * @rqstp: Incoming Call to find + * @start: starting byte in @rqstp->rq_arg of the NFS Call header + * @len: size of the NFS Call header, in bytes * @cacherep: OUT: DRC entry for this request * * Try to find an entry matching the current call in the cache. When none @@ -478,7 +499,8 @@ nfsd_cache_insert(struct nfsd_drc_bucket *b, struct nfsd_cacherep *key, * %RC_REPLY: Reply from cache * %RC_DROPIT: Do not process the request further */ -int nfsd_cache_lookup(struct svc_rqst *rqstp, struct nfsd_cacherep **cacherep) +int nfsd_cache_lookup(struct svc_rqst *rqstp, unsigned int start, + unsigned int len, struct nfsd_cacherep **cacherep) { struct nfsd_net *nn; struct nfsd_cacherep *rp, *found; @@ -494,7 +516,7 @@ int nfsd_cache_lookup(struct svc_rqst *rqstp, struct nfsd_cacherep **cacherep) goto out; } - csum = nfsd_cache_csum(rqstp); + csum = nfsd_cache_csum(&rqstp->rq_arg, start, len); /* * Since the common case is a cache miss followed by an insert, @@ -640,24 +662,17 @@ void nfsd_cache_update(struct svc_rqst *rqstp, struct nfsd_cacherep *rp, return; } -/* - * Copy cached reply to current reply buffer. Should always fit. - * FIXME as reply is in a page, we should just attach the page, and - * keep a refcount.... - */ static int nfsd_cache_append(struct svc_rqst *rqstp, struct kvec *data) { - struct kvec *vec = &rqstp->rq_res.head[0]; - - if (vec->iov_len + data->iov_len > PAGE_SIZE) { - printk(KERN_WARNING "nfsd: cached reply too large (%zd).\n", - data->iov_len); - return 0; - } - memcpy((char*)vec->iov_base + vec->iov_len, data->iov_base, data->iov_len); - vec->iov_len += data->iov_len; - return 1; + __be32 *p; + + p = xdr_reserve_space(&rqstp->rq_res_stream, data->iov_len); + if (unlikely(!p)) + return false; + memcpy(p, data->iov_base, data->iov_len); + xdr_commit_encode(&rqstp->rq_res_stream); + return true; } /* diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 7ed02fb88a362..98854dd3c1502 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -704,8 +704,10 @@ static ssize_t __write_ports_addfd(char *buf, struct net *net, const struct cred err = svc_addsock(nn->nfsd_serv, net, fd, buf, SIMPLE_TRANSACTION_LIMIT, cred); - if (err >= 0 && - !nn->nfsd_serv->sv_nrthreads && !xchg(&nn->keep_active, 1)) + if (err < 0 && !nn->nfsd_serv->sv_nrthreads && !nn->keep_active) + nfsd_last_thread(net); + else if (err >= 0 && + !nn->nfsd_serv->sv_nrthreads && !xchg(&nn->keep_active, 1)) svc_get(nn->nfsd_serv); nfsd_put(net); @@ -756,6 +758,9 @@ static ssize_t __write_ports_addxprt(char *buf, struct net *net, const struct cr svc_xprt_put(xprt); } out_err: + if (!nn->nfsd_serv->sv_nrthreads && !nn->keep_active) + nfsd_last_thread(net); + nfsd_put(net); return err; } diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 8dce90410251f..bf9705a84eb00 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -138,6 +138,7 @@ int nfsd_vers(struct nfsd_net *nn, int vers, enum vers_op change); int nfsd_minorversion(struct nfsd_net *nn, u32 minorversion, enum vers_op change); void nfsd_reset_versions(struct nfsd_net *nn); int nfsd_create_serv(struct net *net); +void nfsd_last_thread(struct net *net); extern int nfsd_max_blksize; diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index c7af1095f6b54..7ef6af908faac 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -542,7 +542,7 @@ static struct notifier_block nfsd_inet6addr_notifier = { /* Only used under nfsd_mutex, so this atomic may be overkill: */ static atomic_t nfsd_notifier_refcount = ATOMIC_INIT(0); -static void nfsd_last_thread(struct net *net) +void nfsd_last_thread(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct svc_serv *serv = nn->nfsd_serv; @@ -962,7 +962,6 @@ nfsd(void *vrqstp) rqstp->rq_server->sv_maxconn = nn->max_connections; svc_recv(rqstp); - validate_process_creds(); } atomic_dec(&nfsdstats.th_cnt); @@ -988,6 +987,8 @@ int nfsd_dispatch(struct svc_rqst *rqstp) const struct svc_procedure *proc = rqstp->rq_procinfo; __be32 *statp = rqstp->rq_accept_statp; struct nfsd_cacherep *rp; + unsigned int start, len; + __be32 *nfs_reply; /* * Give the xdr decoder a chance to change this if it wants @@ -995,11 +996,18 @@ int nfsd_dispatch(struct svc_rqst *rqstp) */ rqstp->rq_cachetype = proc->pc_cachetype; + /* + * ->pc_decode advances the argument stream past the NFS + * Call header, so grab the header's starting location and + * size now for the call to nfsd_cache_lookup(). + */ + start = xdr_stream_pos(&rqstp->rq_arg_stream); + len = xdr_stream_remaining(&rqstp->rq_arg_stream); if (!proc->pc_decode(rqstp, &rqstp->rq_arg_stream)) goto out_decode_err; rp = NULL; - switch (nfsd_cache_lookup(rqstp, &rp)) { + switch (nfsd_cache_lookup(rqstp, start, len, &rp)) { case RC_DOIT: break; case RC_REPLY: @@ -1008,6 +1016,7 @@ int nfsd_dispatch(struct svc_rqst *rqstp) goto out_dropit; } + nfs_reply = xdr_inline_decode(&rqstp->rq_res_stream, 0); *statp = proc->pc_func(rqstp); if (test_bit(RQ_DROPME, &rqstp->rq_flags)) goto out_update_drop; @@ -1015,7 +1024,7 @@ int nfsd_dispatch(struct svc_rqst *rqstp) if (!proc->pc_encode(rqstp, &rqstp->rq_res_stream)) goto out_encode_err; - nfsd_cache_update(rqstp, rp, rqstp->rq_cachetype, statp + 1); + nfsd_cache_update(rqstp, rp, rqstp->rq_cachetype, nfs_reply); out_cached_reply: return 1; diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 2073f52fb20b0..8f4a9051d713c 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -898,7 +898,6 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, int host_err; bool retried = false; - validate_process_creds(); /* * If we get here, then the client has already done an "open", * and (hopefully) checked permission - so allow OWNER_OVERRIDE @@ -923,7 +922,6 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type, } err = nfserrno(host_err); } - validate_process_creds(); return err; } @@ -940,12 +938,7 @@ int nfsd_open_verified(struct svc_rqst *rqstp, struct svc_fh *fhp, int may_flags, struct file **filp) { - int err; - - validate_process_creds(); - err = __nfsd_open(rqstp, fhp, S_IFREG, may_flags, filp); - validate_process_creds(); - return err; + return __nfsd_open(rqstp, fhp, S_IFREG, may_flags, filp); } /* diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c index 2c6078a6b8ecb..58ca7c936393c 100644 --- a/fs/nilfs2/sufile.c +++ b/fs/nilfs2/sufile.c @@ -501,15 +501,38 @@ int nilfs_sufile_mark_dirty(struct inode *sufile, __u64 segnum) down_write(&NILFS_MDT(sufile)->mi_sem); ret = nilfs_sufile_get_segment_usage_block(sufile, segnum, 0, &bh); - if (!ret) { - mark_buffer_dirty(bh); - nilfs_mdt_mark_dirty(sufile); - kaddr = kmap_atomic(bh->b_page); - su = nilfs_sufile_block_get_segment_usage(sufile, segnum, bh, kaddr); + if (ret) + goto out_sem; + + kaddr = kmap_atomic(bh->b_page); + su = nilfs_sufile_block_get_segment_usage(sufile, segnum, bh, kaddr); + if (unlikely(nilfs_segment_usage_error(su))) { + struct the_nilfs *nilfs = sufile->i_sb->s_fs_info; + + kunmap_atomic(kaddr); + brelse(bh); + if (nilfs_segment_is_active(nilfs, segnum)) { + nilfs_error(sufile->i_sb, + "active segment %llu is erroneous", + (unsigned long long)segnum); + } else { + /* + * Segments marked erroneous are never allocated by + * nilfs_sufile_alloc(); only active segments, ie, + * the segments indexed by ns_segnum or ns_nextnum, + * can be erroneous here. + */ + WARN_ON_ONCE(1); + } + ret = -EIO; + } else { nilfs_segment_usage_set_dirty(su); kunmap_atomic(kaddr); + mark_buffer_dirty(bh); + nilfs_mdt_mark_dirty(sufile); brelse(bh); } +out_sem: up_write(&NILFS_MDT(sufile)->mi_sem); return ret; } @@ -536,9 +559,14 @@ int nilfs_sufile_set_segment_usage(struct inode *sufile, __u64 segnum, kaddr = kmap_atomic(bh->b_page); su = nilfs_sufile_block_get_segment_usage(sufile, segnum, bh, kaddr); - WARN_ON(nilfs_segment_usage_error(su)); - if (modtime) + if (modtime) { + /* + * Check segusage error and set su_lastmod only when updating + * this entry with a valid timestamp, not for cancellation. + */ + WARN_ON_ONCE(nilfs_segment_usage_error(su)); su->su_lastmod = cpu_to_le64(modtime); + } su->su_nblocks = cpu_to_le32(nblocks); kunmap_atomic(kaddr); diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index 0f0667957c810..71400496ed365 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -716,7 +716,11 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb, char *data) goto failed_sbh; } nilfs_release_super_block(nilfs); - sb_set_blocksize(sb, blocksize); + if (!sb_set_blocksize(sb, blocksize)) { + nilfs_err(sb, "bad blocksize %d", blocksize); + err = -EINVAL; + goto out; + } err = nilfs_load_super_block(nilfs, sb, blocksize, &sbp); if (err) diff --git a/fs/open.c b/fs/open.c index 98f6601fbac65..54723fceb7767 100644 --- a/fs/open.c +++ b/fs/open.c @@ -1069,8 +1069,6 @@ struct file *dentry_open(const struct path *path, int flags, int error; struct file *f; - validate_creds(cred); - /* We must always pass in a valid mount pointer. */ BUG_ON(!path->mnt); @@ -1109,7 +1107,6 @@ struct file *dentry_create(const struct path *path, int flags, umode_t mode, struct file *f; int error; - validate_creds(cred); f = alloc_empty_file(flags, cred); if (IS_ERR(f)) return f; diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index 83ef66644c213..fca29dba7b146 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -171,7 +171,7 @@ int ovl_getattr(struct mnt_idmap *idmap, const struct path *path, type = ovl_path_real(dentry, &realpath); old_cred = ovl_override_creds(dentry->d_sb); - err = vfs_getattr(&realpath, stat, request_mask, flags); + err = ovl_do_getattr(&realpath, stat, request_mask, flags); if (err) goto out; @@ -196,8 +196,8 @@ int ovl_getattr(struct mnt_idmap *idmap, const struct path *path, (!is_dir ? STATX_NLINK : 0); ovl_path_lower(dentry, &realpath); - err = vfs_getattr(&realpath, &lowerstat, - lowermask, flags); + err = ovl_do_getattr(&realpath, &lowerstat, lowermask, + flags); if (err) goto out; @@ -249,8 +249,8 @@ int ovl_getattr(struct mnt_idmap *idmap, const struct path *path, ovl_path_lowerdata(dentry, &realpath); if (realpath.dentry) { - err = vfs_getattr(&realpath, &lowerdatastat, - lowermask, flags); + err = ovl_do_getattr(&realpath, &lowerdatastat, + lowermask, flags); if (err) goto out; } else { diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index 9817b2dcb132c..09ca82ed0f8ce 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -397,6 +397,14 @@ static inline bool ovl_open_flags_need_copy_up(int flags) return ((OPEN_FMODE(flags) & FMODE_WRITE) || (flags & O_TRUNC)); } +static inline int ovl_do_getattr(const struct path *path, struct kstat *stat, + u32 request_mask, unsigned int flags) +{ + if (flags & AT_GETATTR_NOSEC) + return vfs_getattr_nosec(path, stat, request_mask, flags); + return vfs_getattr(path, stat, request_mask, flags); +} + /* util.c */ int ovl_want_write(struct dentry *dentry); void ovl_drop_write(struct dentry *dentry); diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 3fa2416264a4e..c71d185980c08 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -1489,7 +1489,7 @@ int ovl_fill_super(struct super_block *sb, struct fs_context *fc) ovl_trusted_xattr_handlers; sb->s_fs_info = ofs; sb->s_flags |= SB_POSIXACL; - sb->s_iflags |= SB_I_SKIP_SYNC | SB_I_IMA_UNVERIFIABLE_SIGNATURE; + sb->s_iflags |= SB_I_SKIP_SYNC; err = -ENOMEM; root_dentry = ovl_get_root(sb, ctx->upper.dentry, oe); diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index c88854df0b624..de484195f49fe 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -1576,7 +1576,6 @@ static const struct sysctl_alias sysctl_aliases[] = { {"hung_task_panic", "kernel.hung_task_panic" }, {"numa_zonelist_order", "vm.numa_zonelist_order" }, {"softlockup_all_cpu_backtrace", "kernel.softlockup_all_cpu_backtrace" }, - {"softlockup_panic", "kernel.softlockup_panic" }, { } }; @@ -1592,6 +1591,13 @@ static const char *sysctl_find_alias(char *param) return NULL; } +bool sysctl_is_alias(char *param) +{ + const char *alias = sysctl_find_alias(param); + + return alias != NULL; +} + /* Set sysctl value passed on kernel command line. */ static int process_sysctl_arg(char *param, char *val, const char *unused, void *arg) diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 31e897ad5e6a7..023b91b4e1f0a 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -2351,6 +2351,20 @@ static int vfs_setup_quota_inode(struct inode *inode, int type) if (sb_has_quota_loaded(sb, type)) return -EBUSY; + /* + * Quota files should never be encrypted. They should be thought of as + * filesystem metadata, not user data. New-style internal quota files + * cannot be encrypted by users anyway, but old-style external quota + * files could potentially be incorrectly created in an encrypted + * directory, hence this explicit check. Some reasons why encrypted + * quota files don't work include: (1) some filesystems that support + * encryption don't handle it in their quota_read and quota_write, and + * (2) cleaning up encrypted quota files at unmount would need special + * consideration, as quota files are cleaned up later than user files. + */ + if (IS_ENCRYPTED(inode)) + return -EINVAL; + dqopt->files[type] = igrab(inode); if (!dqopt->files[type]) return -EIO; diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c index fe1bf5b6e0cb3..d64a306a414be 100644 --- a/fs/smb/client/cached_dir.c +++ b/fs/smb/client/cached_dir.c @@ -32,7 +32,7 @@ static struct cached_fid *find_or_create_cached_dir(struct cached_fids *cfids, * fully cached or it may be in the process of * being deleted due to a lease break. */ - if (!cfid->has_lease) { + if (!cfid->time || !cfid->has_lease) { spin_unlock(&cfids->cfid_list_lock); return NULL; } @@ -193,9 +193,19 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, npath = path_no_prefix(cifs_sb, path); if (IS_ERR(npath)) { rc = PTR_ERR(npath); - kfree(utf16_path); - return rc; + goto out; + } + + if (!npath[0]) { + dentry = dget(cifs_sb->root); + } else { + dentry = path_to_dentry(cifs_sb, npath); + if (IS_ERR(dentry)) { + rc = -ENOENT; + goto out; + } } + cfid->dentry = dentry; /* * We do not hold the lock for the open because in case @@ -249,6 +259,15 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, smb2_set_related(&rqst[1]); + /* + * Set @cfid->has_lease to true before sending out compounded request so + * its lease reference can be put in cached_dir_lease_break() due to a + * potential lease break right after the request is sent or while @cfid + * is still being cached. Concurrent processes won't be to use it yet + * due to @cfid->time being zero. + */ + cfid->has_lease = true; + rc = compound_send_recv(xid, ses, server, flags, 2, rqst, resp_buftype, rsp_iov); @@ -263,6 +282,8 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, cfid->tcon = tcon; cfid->is_open = true; + spin_lock(&cfids->cfid_list_lock); + o_rsp = (struct smb2_create_rsp *)rsp_iov[0].iov_base; oparms.fid->persistent_fid = o_rsp->PersistentFileId; oparms.fid->volatile_fid = o_rsp->VolatileFileId; @@ -270,18 +291,32 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, oparms.fid->mid = le64_to_cpu(o_rsp->hdr.MessageId); #endif /* CIFS_DEBUG2 */ - if (o_rsp->OplockLevel != SMB2_OPLOCK_LEVEL_LEASE) + + if (o_rsp->OplockLevel != SMB2_OPLOCK_LEVEL_LEASE) { + spin_unlock(&cfids->cfid_list_lock); + rc = -EINVAL; + goto oshr_free; + } + + rc = smb2_parse_contexts(server, rsp_iov, + &oparms.fid->epoch, + oparms.fid->lease_key, + &oplock, NULL, NULL); + if (rc) { + spin_unlock(&cfids->cfid_list_lock); goto oshr_free; + } - smb2_parse_contexts(server, o_rsp, - &oparms.fid->epoch, - oparms.fid->lease_key, &oplock, - NULL, NULL); - if (!(oplock & SMB2_LEASE_READ_CACHING_HE)) + rc = -EINVAL; + if (!(oplock & SMB2_LEASE_READ_CACHING_HE)) { + spin_unlock(&cfids->cfid_list_lock); goto oshr_free; + } qi_rsp = (struct smb2_query_info_rsp *)rsp_iov[1].iov_base; - if (le32_to_cpu(qi_rsp->OutputBufferLength) < sizeof(struct smb2_file_all_info)) + if (le32_to_cpu(qi_rsp->OutputBufferLength) < sizeof(struct smb2_file_all_info)) { + spin_unlock(&cfids->cfid_list_lock); goto oshr_free; + } if (!smb2_validate_and_copy_iov( le16_to_cpu(qi_rsp->OutputBufferOffset), sizeof(struct smb2_file_all_info), @@ -289,37 +324,24 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, (char *)&cfid->file_all_info)) cfid->file_all_info_is_valid = true; - if (!npath[0]) - dentry = dget(cifs_sb->root); - else { - dentry = path_to_dentry(cifs_sb, npath); - if (IS_ERR(dentry)) { - rc = -ENOENT; - goto oshr_free; - } - } - spin_lock(&cfids->cfid_list_lock); - cfid->dentry = dentry; cfid->time = jiffies; - cfid->has_lease = true; spin_unlock(&cfids->cfid_list_lock); + /* At this point the directory handle is fully cached */ + rc = 0; oshr_free: - kfree(utf16_path); SMB2_open_free(&rqst[0]); SMB2_query_info_free(&rqst[1]); free_rsp_buf(resp_buftype[0], rsp_iov[0].iov_base); free_rsp_buf(resp_buftype[1], rsp_iov[1].iov_base); - spin_lock(&cfids->cfid_list_lock); - if (!cfid->has_lease) { - if (rc) { - if (cfid->on_list) { - list_del(&cfid->entry); - cfid->on_list = false; - cfids->num_entries--; - } - rc = -ENOENT; - } else { + if (rc) { + spin_lock(&cfids->cfid_list_lock); + if (cfid->on_list) { + list_del(&cfid->entry); + cfid->on_list = false; + cfids->num_entries--; + } + if (cfid->has_lease) { /* * We are guaranteed to have two references at this * point. One for the caller and one for a potential @@ -327,25 +349,24 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, * will be closed when the caller closes the cached * handle. */ + cfid->has_lease = false; spin_unlock(&cfids->cfid_list_lock); kref_put(&cfid->refcount, smb2_close_cached_fid); goto out; } + spin_unlock(&cfids->cfid_list_lock); } - spin_unlock(&cfids->cfid_list_lock); +out: if (rc) { if (cfid->is_open) SMB2_close(0, cfid->tcon, cfid->fid.persistent_fid, cfid->fid.volatile_fid); free_cached_dir(cfid); - cfid = NULL; - } -out: - if (rc == 0) { + } else { *ret_cfid = cfid; atomic_inc(&tcon->num_remote_opens); } - + kfree(utf16_path); return rc; } diff --git a/fs/smb/client/cifs_debug.c b/fs/smb/client/cifs_debug.c index dfe1bc4b3ee31..027e8e1a061fc 100644 --- a/fs/smb/client/cifs_debug.c +++ b/fs/smb/client/cifs_debug.c @@ -43,11 +43,13 @@ void cifs_dump_detail(void *buf, struct TCP_Server_Info *server) #ifdef CONFIG_CIFS_DEBUG2 struct smb_hdr *smb = buf; - cifs_dbg(VFS, "Cmd: %d Err: 0x%x Flags: 0x%x Flgs2: 0x%x Mid: %d Pid: %d\n", - smb->Command, smb->Status.CifsError, - smb->Flags, smb->Flags2, smb->Mid, smb->Pid); - cifs_dbg(VFS, "smb buf %p len %u\n", smb, - server->ops->calc_smb_size(smb)); + cifs_dbg(VFS, "Cmd: %d Err: 0x%x Flags: 0x%x Flgs2: 0x%x Mid: %d Pid: %d Wct: %d\n", + smb->Command, smb->Status.CifsError, smb->Flags, + smb->Flags2, smb->Mid, smb->Pid, smb->WordCount); + if (!server->ops->check_message(buf, server->total_read, server)) { + cifs_dbg(VFS, "smb buf %p len %u\n", smb, + server->ops->calc_smb_size(smb)); + } #endif /* CONFIG_CIFS_DEBUG2 */ } @@ -282,6 +284,8 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v) struct cifs_ses *ses; struct cifs_tcon *tcon; struct cifs_server_iface *iface; + size_t iface_weight = 0, iface_min_speed = 0; + struct cifs_server_iface *last_iface = NULL; int c, i, j; seq_puts(m, @@ -455,6 +459,11 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v) seq_printf(m, "\n\n\tSessions: "); i = 0; list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { + spin_lock(&ses->ses_lock); + if (ses->ses_status == SES_EXITING) { + spin_unlock(&ses->ses_lock); + continue; + } i++; if ((ses->serverDomain == NULL) || (ses->serverOS == NULL) || @@ -475,6 +484,7 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v) ses->ses_count, ses->serverOS, ses->serverNOS, ses->capabilities, ses->ses_status); } + spin_unlock(&ses->ses_lock); seq_printf(m, "\n\tSecurity type: %s ", get_security_type_str(server->ops->select_sectype(server, ses->sectype))); @@ -539,11 +549,25 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v) "\tLast updated: %lu seconds ago", ses->iface_count, (jiffies - ses->iface_last_update) / HZ); + + last_iface = list_last_entry(&ses->iface_list, + struct cifs_server_iface, + iface_head); + iface_min_speed = last_iface->speed; + j = 0; list_for_each_entry(iface, &ses->iface_list, iface_head) { seq_printf(m, "\n\t%d)", ++j); cifs_dump_iface(m, iface); + + iface_weight = iface->speed / iface_min_speed; + seq_printf(m, "\t\tWeight (cur,total): (%zu,%zu)" + "\n\t\tAllocated channels: %u\n", + iface->weight_fulfilled, + iface_weight, + iface->num_channels); + if (is_ses_using_iface(ses, iface)) seq_puts(m, "\t\t[CONNECTED]\n"); } diff --git a/fs/smb/client/cifs_ioctl.h b/fs/smb/client/cifs_ioctl.h index 332588e77c311..26327442e383b 100644 --- a/fs/smb/client/cifs_ioctl.h +++ b/fs/smb/client/cifs_ioctl.h @@ -26,6 +26,11 @@ struct smb_mnt_fs_info { __u64 cifs_posix_caps; } __packed; +struct smb_mnt_tcon_info { + __u32 tid; + __u64 session_id; +} __packed; + struct smb_snapshot_array { __u32 number_of_snapshots; __u32 number_of_snapshots_returned; @@ -108,6 +113,7 @@ struct smb3_notify_info { #define CIFS_IOC_NOTIFY _IOW(CIFS_IOCTL_MAGIC, 9, struct smb3_notify) #define CIFS_DUMP_FULL_KEY _IOWR(CIFS_IOCTL_MAGIC, 10, struct smb3_full_key_debug_info) #define CIFS_IOC_NOTIFY_INFO _IOWR(CIFS_IOCTL_MAGIC, 11, struct smb3_notify_info) +#define CIFS_IOC_GET_TCON_INFO _IOR(CIFS_IOCTL_MAGIC, 12, struct smb_mnt_tcon_info) #define CIFS_IOC_SHUTDOWN _IOR('X', 125, __u32) /* diff --git a/fs/smb/client/cifs_spnego.c b/fs/smb/client/cifs_spnego.c index 6f3285f1dfee5..af7849e5974ff 100644 --- a/fs/smb/client/cifs_spnego.c +++ b/fs/smb/client/cifs_spnego.c @@ -64,8 +64,8 @@ struct key_type cifs_spnego_key_type = { * strlen(";sec=ntlmsspi") */ #define MAX_MECH_STR_LEN 13 -/* strlen of "host=" */ -#define HOST_KEY_LEN 5 +/* strlen of ";host=" */ +#define HOST_KEY_LEN 6 /* strlen of ";ip4=" or ";ip6=" */ #define IP_KEY_LEN 5 diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index 22869cda13565..2131638f26d0b 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -1191,36 +1191,108 @@ const char *cifs_get_link(struct dentry *dentry, struct inode *inode, const struct inode_operations cifs_symlink_inode_ops = { .get_link = cifs_get_link, + .setattr = cifs_setattr, .permission = cifs_permission, .listxattr = cifs_listxattr, }; +/* + * Advance the EOF marker to after the source range. + */ +static int cifs_precopy_set_eof(struct inode *src_inode, struct cifsInodeInfo *src_cifsi, + struct cifs_tcon *src_tcon, + unsigned int xid, loff_t src_end) +{ + struct cifsFileInfo *writeable_srcfile; + int rc = -EINVAL; + + writeable_srcfile = find_writable_file(src_cifsi, FIND_WR_FSUID_ONLY); + if (writeable_srcfile) { + if (src_tcon->ses->server->ops->set_file_size) + rc = src_tcon->ses->server->ops->set_file_size( + xid, src_tcon, writeable_srcfile, + src_inode->i_size, true /* no need to set sparse */); + else + rc = -ENOSYS; + cifsFileInfo_put(writeable_srcfile); + cifs_dbg(FYI, "SetFSize for copychunk rc = %d\n", rc); + } + + if (rc < 0) + goto set_failed; + + netfs_resize_file(&src_cifsi->netfs, src_end); + fscache_resize_cookie(cifs_inode_cookie(src_inode), src_end); + return 0; + +set_failed: + return filemap_write_and_wait(src_inode->i_mapping); +} + +/* + * Flush out either the folio that overlaps the beginning of a range in which + * pos resides or the folio that overlaps the end of a range unless that folio + * is entirely within the range we're going to invalidate. We extend the flush + * bounds to encompass the folio. + */ +static int cifs_flush_folio(struct inode *inode, loff_t pos, loff_t *_fstart, loff_t *_fend, + bool first) +{ + struct folio *folio; + unsigned long long fpos, fend; + pgoff_t index = pos / PAGE_SIZE; + size_t size; + int rc = 0; + + folio = filemap_get_folio(inode->i_mapping, index); + if (IS_ERR(folio)) + return 0; + + size = folio_size(folio); + fpos = folio_pos(folio); + fend = fpos + size - 1; + *_fstart = min_t(unsigned long long, *_fstart, fpos); + *_fend = max_t(unsigned long long, *_fend, fend); + if ((first && pos == fpos) || (!first && pos == fend)) + goto out; + + rc = filemap_write_and_wait_range(inode->i_mapping, fpos, fend); +out: + folio_put(folio); + return rc; +} + static loff_t cifs_remap_file_range(struct file *src_file, loff_t off, struct file *dst_file, loff_t destoff, loff_t len, unsigned int remap_flags) { struct inode *src_inode = file_inode(src_file); struct inode *target_inode = file_inode(dst_file); + struct cifsInodeInfo *src_cifsi = CIFS_I(src_inode); + struct cifsInodeInfo *target_cifsi = CIFS_I(target_inode); struct cifsFileInfo *smb_file_src = src_file->private_data; - struct cifsFileInfo *smb_file_target; - struct cifs_tcon *target_tcon; + struct cifsFileInfo *smb_file_target = dst_file->private_data; + struct cifs_tcon *target_tcon, *src_tcon; + unsigned long long destend, fstart, fend, new_size; unsigned int xid; int rc; - if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY)) + if (remap_flags & REMAP_FILE_DEDUP) + return -EOPNOTSUPP; + if (remap_flags & ~REMAP_FILE_ADVISORY) return -EINVAL; cifs_dbg(FYI, "clone range\n"); xid = get_xid(); - if (!src_file->private_data || !dst_file->private_data) { + if (!smb_file_src || !smb_file_target) { rc = -EBADF; cifs_dbg(VFS, "missing cifsFileInfo on copy range src file\n"); goto out; } - smb_file_target = dst_file->private_data; + src_tcon = tlink_tcon(smb_file_src->tlink); target_tcon = tlink_tcon(smb_file_target->tlink); /* @@ -1233,20 +1305,63 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off, if (len == 0) len = src_inode->i_size - off; - cifs_dbg(FYI, "about to flush pages\n"); - /* should we flush first and last page first */ - truncate_inode_pages_range(&target_inode->i_data, destoff, - PAGE_ALIGN(destoff + len)-1); + cifs_dbg(FYI, "clone range\n"); + + /* Flush the source buffer */ + rc = filemap_write_and_wait_range(src_inode->i_mapping, off, + off + len - 1); + if (rc) + goto unlock; + + /* The server-side copy will fail if the source crosses the EOF marker. + * Advance the EOF marker after the flush above to the end of the range + * if it's short of that. + */ + if (src_cifsi->netfs.remote_i_size < off + len) { + rc = cifs_precopy_set_eof(src_inode, src_cifsi, src_tcon, xid, off + len); + if (rc < 0) + goto unlock; + } + + new_size = destoff + len; + destend = destoff + len - 1; + + /* Flush the folios at either end of the destination range to prevent + * accidental loss of dirty data outside of the range. + */ + fstart = destoff; + fend = destend; - if (target_tcon->ses->server->ops->duplicate_extents) + rc = cifs_flush_folio(target_inode, destoff, &fstart, &fend, true); + if (rc) + goto unlock; + rc = cifs_flush_folio(target_inode, destend, &fstart, &fend, false); + if (rc) + goto unlock; + + /* Discard all the folios that overlap the destination region. */ + cifs_dbg(FYI, "about to discard pages %llx-%llx\n", fstart, fend); + truncate_inode_pages_range(&target_inode->i_data, fstart, fend); + + fscache_invalidate(cifs_inode_cookie(target_inode), NULL, + i_size_read(target_inode), 0); + + rc = -EOPNOTSUPP; + if (target_tcon->ses->server->ops->duplicate_extents) { rc = target_tcon->ses->server->ops->duplicate_extents(xid, smb_file_src, smb_file_target, off, len, destoff); - else - rc = -EOPNOTSUPP; + if (rc == 0 && new_size > i_size_read(target_inode)) { + truncate_setsize(target_inode, new_size); + netfs_resize_file(&target_cifsi->netfs, new_size); + fscache_resize_cookie(cifs_inode_cookie(target_inode), + new_size); + } + } /* force revalidate of size and timestamps of target file now that target is updated on the server */ CIFS_I(target_inode)->time = 0; +unlock: /* although unlocking in the reverse order from locking is not strictly necessary here it is a little cleaner to be consistent */ unlock_two_nondirectories(src_inode, target_inode); @@ -1262,10 +1377,12 @@ ssize_t cifs_file_copychunk_range(unsigned int xid, { struct inode *src_inode = file_inode(src_file); struct inode *target_inode = file_inode(dst_file); + struct cifsInodeInfo *src_cifsi = CIFS_I(src_inode); struct cifsFileInfo *smb_file_src; struct cifsFileInfo *smb_file_target; struct cifs_tcon *src_tcon; struct cifs_tcon *target_tcon; + unsigned long long destend, fstart, fend; ssize_t rc; cifs_dbg(FYI, "copychunk range\n"); @@ -1305,13 +1422,41 @@ ssize_t cifs_file_copychunk_range(unsigned int xid, if (rc) goto unlock; - /* should we flush first and last page first */ - truncate_inode_pages(&target_inode->i_data, 0); + /* The server-side copy will fail if the source crosses the EOF marker. + * Advance the EOF marker after the flush above to the end of the range + * if it's short of that. + */ + if (src_cifsi->server_eof < off + len) { + rc = cifs_precopy_set_eof(src_inode, src_cifsi, src_tcon, xid, off + len); + if (rc < 0) + goto unlock; + } + + destend = destoff + len - 1; + + /* Flush the folios at either end of the destination range to prevent + * accidental loss of dirty data outside of the range. + */ + fstart = destoff; + fend = destend; + + rc = cifs_flush_folio(target_inode, destoff, &fstart, &fend, true); + if (rc) + goto unlock; + rc = cifs_flush_folio(target_inode, destend, &fstart, &fend, false); + if (rc) + goto unlock; + + /* Discard all the folios that overlap the destination region. */ + truncate_inode_pages_range(&target_inode->i_data, fstart, fend); rc = file_modified(dst_file); - if (!rc) + if (!rc) { rc = target_tcon->ses->server->ops->copychunk_range(xid, smb_file_src, smb_file_target, off, len, destoff); + if (rc > 0 && destoff + rc > i_size_read(target_inode)) + truncate_setsize(target_inode, destoff + rc); + } file_accessed(src_file); diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 4ca7efc965ebb..d8f4ac6609e1d 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -191,7 +191,13 @@ struct cifs_open_info_data { bool reparse_point; bool symlink; }; - __u32 reparse_tag; + struct { + __u32 tag; + union { + struct reparse_data_buffer *buf; + struct reparse_posix_data *posix; + }; + } reparse; char *symlink_target; union { struct smb2_file_all_info fi; @@ -395,8 +401,7 @@ struct smb_version_operations { struct cifs_tcon *tcon, struct cifs_sb_info *cifs_sb, const char *full_path, - char **target_path, - struct kvec *rsp_iov); + char **target_path); /* open a file for non-posix mounts */ int (*open)(const unsigned int xid, struct cifs_open_parms *oparms, __u32 *oplock, void *buf); @@ -527,7 +532,8 @@ struct smb_version_operations { struct mid_q_entry **, char **, int *); enum securityEnum (*select_sectype)(struct TCP_Server_Info *, enum securityEnum); - int (*next_header)(char *); + int (*next_header)(struct TCP_Server_Info *server, char *buf, + unsigned int *noff); /* ioctl passthrough for query_info */ int (*ioctl_query_info)(const unsigned int xid, struct cifs_tcon *tcon, @@ -551,6 +557,9 @@ struct smb_version_operations { bool (*is_status_io_timeout)(char *buf); /* Check for STATUS_NETWORK_NAME_DELETED */ bool (*is_network_name_deleted)(char *buf, struct TCP_Server_Info *srv); + int (*parse_reparse_point)(struct cifs_sb_info *cifs_sb, + struct kvec *rsp_iov, + struct cifs_open_info_data *data); }; struct smb_version_values { @@ -969,6 +978,8 @@ struct cifs_server_iface { struct list_head iface_head; struct kref refcount; size_t speed; + size_t weight_fulfilled; + unsigned int num_channels; unsigned int rdma_capable : 1; unsigned int rss_capable : 1; unsigned int is_active : 1; /* unset if non existent */ @@ -2147,6 +2158,7 @@ static inline int cifs_get_num_sgs(const struct smb_rqst *rqst, unsigned int len, skip; unsigned int nents = 0; unsigned long addr; + size_t data_size; int i, j; /* @@ -2162,17 +2174,21 @@ static inline int cifs_get_num_sgs(const struct smb_rqst *rqst, * rqst[1+].rq_iov[0+] data to be encrypted/decrypted */ for (i = 0; i < num_rqst; i++) { + data_size = iov_iter_count(&rqst[i].rq_iter); + /* We really don't want a mixture of pinned and unpinned pages * in the sglist. It's hard to keep track of which is what. * Instead, we convert to a BVEC-type iterator higher up. */ - if (WARN_ON_ONCE(user_backed_iter(&rqst[i].rq_iter))) + if (data_size && + WARN_ON_ONCE(user_backed_iter(&rqst[i].rq_iter))) return -EIO; /* We also don't want to have any extra refs or pins to clean * up in the sglist. */ - if (WARN_ON_ONCE(iov_iter_extract_will_pin(&rqst[i].rq_iter))) + if (data_size && + WARN_ON_ONCE(iov_iter_extract_will_pin(&rqst[i].rq_iter))) return -EIO; for (j = 0; j < rqst[i].rq_nvec; j++) { @@ -2188,7 +2204,8 @@ static inline int cifs_get_num_sgs(const struct smb_rqst *rqst, } skip = 0; } - nents += iov_iter_npages(&rqst[i].rq_iter, INT_MAX); + if (data_size) + nents += iov_iter_npages(&rqst[i].rq_iter, INT_MAX); } nents += DIV_ROUND_UP(offset_in_page(sig) + SMB2_SIGNATURE_SIZE, PAGE_SIZE); return nents; diff --git a/fs/smb/client/cifspdu.h b/fs/smb/client/cifspdu.h index e17222fec9d29..83ccc51a54d03 100644 --- a/fs/smb/client/cifspdu.h +++ b/fs/smb/client/cifspdu.h @@ -1356,7 +1356,7 @@ typedef struct smb_com_transaction_ioctl_rsp { __le32 DataDisplacement; __u8 SetupCount; /* 1 */ __le16 ReturnedDataLen; - __u16 ByteCount; + __le16 ByteCount; } __attribute__((packed)) TRANSACT_IOCTL_RSP; #define CIFS_ACL_OWNER 1 @@ -1509,7 +1509,7 @@ struct reparse_posix_data { __le16 ReparseDataLength; __u16 Reserved; __le64 InodeType; /* LNK, FIFO, CHR etc. */ - char PathBuffer[]; + __u8 DataBuffer[]; } __attribute__((packed)); struct cifs_quota_data { @@ -2570,7 +2570,7 @@ typedef struct { struct win_dev { - unsigned char type[8]; /* IntxCHR or IntxBLK */ + unsigned char type[8]; /* IntxCHR or IntxBLK or LnxFIFO*/ __le64 major; __le64 minor; } __attribute__((packed)); diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h index 158a67e584b41..bbd43ed22a64c 100644 --- a/fs/smb/client/cifsproto.h +++ b/fs/smb/client/cifsproto.h @@ -81,7 +81,7 @@ extern char *cifs_build_path_to_root(struct smb3_fs_context *ctx, extern char *build_wildcard_path_from_dentry(struct dentry *direntry); char *cifs_build_devname(char *nodename, const char *prepath); extern void delete_mid(struct mid_q_entry *mid); -extern void release_mid(struct mid_q_entry *mid); +void __release_mid(struct kref *refcount); extern void cifs_wake_up_task(struct mid_q_entry *mid); extern int cifs_handle_standard(struct TCP_Server_Info *server, struct mid_q_entry *mid); @@ -209,7 +209,7 @@ int cifs_get_inode_info(struct inode **inode, const char *full_path, const struct cifs_fid *fid); bool cifs_reparse_point_to_fattr(struct cifs_sb_info *cifs_sb, struct cifs_fattr *fattr, - u32 tag); + struct cifs_open_info_data *data); extern int smb311_posix_get_inode_info(struct inode **pinode, const char *search_path, struct super_block *sb, unsigned int xid); extern int cifs_get_inode_info_unix(struct inode **pinode, @@ -457,6 +457,12 @@ extern int CIFSSMBUnixQuerySymLink(const unsigned int xid, struct cifs_tcon *tcon, const unsigned char *searchName, char **syminfo, const struct nls_table *nls_codepage, int remap); +extern int cifs_query_reparse_point(const unsigned int xid, + struct cifs_tcon *tcon, + struct cifs_sb_info *cifs_sb, + const char *full_path, + u32 *tag, struct kvec *rsp, + int *rsp_buftype); extern int CIFSSMBQuerySymLink(const unsigned int xid, struct cifs_tcon *tcon, __u16 fid, char **symlinkinfo, const struct nls_table *nls_codepage); @@ -610,7 +616,7 @@ void cifs_free_hash(struct shash_desc **sdesc); struct cifs_chan * cifs_ses_find_chan(struct cifs_ses *ses, struct TCP_Server_Info *server); -int cifs_try_adding_channels(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses); +int cifs_try_adding_channels(struct cifs_ses *ses); bool is_server_using_iface(struct TCP_Server_Info *server, struct cifs_server_iface *iface); bool is_ses_using_iface(struct cifs_ses *ses, struct cifs_server_iface *iface); @@ -656,6 +662,9 @@ void cifs_put_tcp_super(struct super_block *sb); int cifs_update_super_prepath(struct cifs_sb_info *cifs_sb, char *prefix); char *extract_hostname(const char *unc); char *extract_sharename(const char *unc); +int parse_reparse_point(struct reparse_data_buffer *buf, + u32 plen, struct cifs_sb_info *cifs_sb, + bool unicode, struct cifs_open_info_data *data); #ifdef CONFIG_TRUENAS int ntsd_to_zfsacl_xattr(struct cifs_ntsd *pacl, @@ -752,4 +761,9 @@ static inline bool dfs_src_pathname_equal(const char *s1, const char *s2) return true; } +static inline void release_mid(struct mid_q_entry *mid) +{ + kref_put(&mid->refcount, __release_mid); +} + #endif /* _CIFSPROTO_H */ diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c index 25503f1a4fd21..bad91ba6c3a9c 100644 --- a/fs/smb/client/cifssmb.c +++ b/fs/smb/client/cifssmb.c @@ -2690,136 +2690,97 @@ CIFSSMBUnixQuerySymLink(const unsigned int xid, struct cifs_tcon *tcon, return rc; } -/* - * Recent Windows versions now create symlinks more frequently - * and they use the "reparse point" mechanism below. We can of course - * do symlinks nicely to Samba and other servers which support the - * CIFS Unix Extensions and we can also do SFU symlinks and "client only" - * "MF" symlinks optionally, but for recent Windows we really need to - * reenable the code below and fix the cifs_symlink callers to handle this. - * In the interim this code has been moved to its own config option so - * it is not compiled in by default until callers fixed up and more tested. - */ -int -CIFSSMBQuerySymLink(const unsigned int xid, struct cifs_tcon *tcon, - __u16 fid, char **symlinkinfo, - const struct nls_table *nls_codepage) +int cifs_query_reparse_point(const unsigned int xid, + struct cifs_tcon *tcon, + struct cifs_sb_info *cifs_sb, + const char *full_path, + u32 *tag, struct kvec *rsp, + int *rsp_buftype) { - int rc = 0; - int bytes_returned; - struct smb_com_transaction_ioctl_req *pSMB; - struct smb_com_transaction_ioctl_rsp *pSMBr; - bool is_unicode; - unsigned int sub_len; - char *sub_start; - struct reparse_symlink_data *reparse_buf; - struct reparse_posix_data *posix_buf; + struct cifs_open_parms oparms; + TRANSACT_IOCTL_REQ *io_req = NULL; + TRANSACT_IOCTL_RSP *io_rsp = NULL; + struct cifs_fid fid; __u32 data_offset, data_count; - char *end_of_smb; + __u8 *start, *end; + int io_rsp_len; + int oplock = 0; + int rc; - cifs_dbg(FYI, "In Windows reparse style QueryLink for fid %u\n", fid); - rc = smb_init(SMB_COM_NT_TRANSACT, 23, tcon, (void **) &pSMB, - (void **) &pSMBr); + cifs_tcon_dbg(FYI, "%s: path=%s\n", __func__, full_path); + + if (cap_unix(tcon->ses)) + return -EOPNOTSUPP; + + oparms = (struct cifs_open_parms) { + .tcon = tcon, + .cifs_sb = cifs_sb, + .desired_access = FILE_READ_ATTRIBUTES, + .create_options = cifs_create_options(cifs_sb, + OPEN_REPARSE_POINT), + .disposition = FILE_OPEN, + .path = full_path, + .fid = &fid, + }; + + rc = CIFS_open(xid, &oparms, &oplock, NULL); if (rc) return rc; - pSMB->TotalParameterCount = 0 ; - pSMB->TotalDataCount = 0; - pSMB->MaxParameterCount = cpu_to_le32(2); - /* BB find exact data count max from sess structure BB */ - pSMB->MaxDataCount = cpu_to_le32(CIFSMaxBufSize & 0xFFFFFF00); - pSMB->MaxSetupCount = 4; - pSMB->Reserved = 0; - pSMB->ParameterOffset = 0; - pSMB->DataCount = 0; - pSMB->DataOffset = 0; - pSMB->SetupCount = 4; - pSMB->SubCommand = cpu_to_le16(NT_TRANSACT_IOCTL); - pSMB->ParameterCount = pSMB->TotalParameterCount; - pSMB->FunctionCode = cpu_to_le32(FSCTL_GET_REPARSE_POINT); - pSMB->IsFsctl = 1; /* FSCTL */ - pSMB->IsRootFlag = 0; - pSMB->Fid = fid; /* file handle always le */ - pSMB->ByteCount = 0; + rc = smb_init(SMB_COM_NT_TRANSACT, 23, tcon, + (void **)&io_req, (void **)&io_rsp); + if (rc) + goto error; - rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB, - (struct smb_hdr *) pSMBr, &bytes_returned, 0); - if (rc) { - cifs_dbg(FYI, "Send error in QueryReparseLinkInfo = %d\n", rc); - goto qreparse_out; - } + io_req->TotalParameterCount = 0; + io_req->TotalDataCount = 0; + io_req->MaxParameterCount = cpu_to_le32(2); + /* BB find exact data count max from sess structure BB */ + io_req->MaxDataCount = cpu_to_le32(CIFSMaxBufSize & 0xFFFFFF00); + io_req->MaxSetupCount = 4; + io_req->Reserved = 0; + io_req->ParameterOffset = 0; + io_req->DataCount = 0; + io_req->DataOffset = 0; + io_req->SetupCount = 4; + io_req->SubCommand = cpu_to_le16(NT_TRANSACT_IOCTL); + io_req->ParameterCount = io_req->TotalParameterCount; + io_req->FunctionCode = cpu_to_le32(FSCTL_GET_REPARSE_POINT); + io_req->IsFsctl = 1; + io_req->IsRootFlag = 0; + io_req->Fid = fid.netfid; + io_req->ByteCount = 0; + + rc = SendReceive(xid, tcon->ses, (struct smb_hdr *)io_req, + (struct smb_hdr *)io_rsp, &io_rsp_len, 0); + if (rc) + goto error; - data_offset = le32_to_cpu(pSMBr->DataOffset); - data_count = le32_to_cpu(pSMBr->DataCount); - if (get_bcc(&pSMBr->hdr) < 2 || data_offset > 512) { - /* BB also check enough total bytes returned */ - rc = -EIO; /* bad smb */ - goto qreparse_out; - } - if (!data_count || (data_count > 2048)) { + data_offset = le32_to_cpu(io_rsp->DataOffset); + data_count = le32_to_cpu(io_rsp->DataCount); + if (get_bcc(&io_rsp->hdr) < 2 || data_offset > 512 || + !data_count || data_count > 2048) { rc = -EIO; - cifs_dbg(FYI, "Invalid return data count on get reparse info ioctl\n"); - goto qreparse_out; - } - end_of_smb = 2 + get_bcc(&pSMBr->hdr) + (char *)&pSMBr->ByteCount; - reparse_buf = (struct reparse_symlink_data *) - ((char *)&pSMBr->hdr.Protocol + data_offset); - if ((char *)reparse_buf >= end_of_smb) { - rc = -EIO; - goto qreparse_out; - } - if (reparse_buf->ReparseTag == cpu_to_le32(IO_REPARSE_TAG_NFS)) { - cifs_dbg(FYI, "NFS style reparse tag\n"); - posix_buf = (struct reparse_posix_data *)reparse_buf; - - if (posix_buf->InodeType != cpu_to_le64(NFS_SPECFILE_LNK)) { - cifs_dbg(FYI, "unsupported file type 0x%llx\n", - le64_to_cpu(posix_buf->InodeType)); - rc = -EOPNOTSUPP; - goto qreparse_out; - } - is_unicode = true; - sub_len = le16_to_cpu(reparse_buf->ReparseDataLength); - if (posix_buf->PathBuffer + sub_len > end_of_smb) { - cifs_dbg(FYI, "reparse buf beyond SMB\n"); - rc = -EIO; - goto qreparse_out; - } - *symlinkinfo = cifs_strndup_from_utf16(posix_buf->PathBuffer, - sub_len, is_unicode, nls_codepage); - goto qreparse_out; - } else if (reparse_buf->ReparseTag != - cpu_to_le32(IO_REPARSE_TAG_SYMLINK)) { - rc = -EOPNOTSUPP; - goto qreparse_out; + goto error; } - /* Reparse tag is NTFS symlink */ - sub_start = le16_to_cpu(reparse_buf->SubstituteNameOffset) + - reparse_buf->PathBuffer; - sub_len = le16_to_cpu(reparse_buf->SubstituteNameLength); - if (sub_start + sub_len > end_of_smb) { - cifs_dbg(FYI, "reparse buf beyond SMB\n"); + end = 2 + get_bcc(&io_rsp->hdr) + (__u8 *)&io_rsp->ByteCount; + start = (__u8 *)&io_rsp->hdr.Protocol + data_offset; + if (start >= end) { rc = -EIO; - goto qreparse_out; + goto error; } - if (pSMBr->hdr.Flags2 & SMBFLG2_UNICODE) - is_unicode = true; - else - is_unicode = false; - - /* BB FIXME investigate remapping reserved chars here */ - *symlinkinfo = cifs_strndup_from_utf16(sub_start, sub_len, is_unicode, - nls_codepage); - if (!*symlinkinfo) - rc = -ENOMEM; -qreparse_out: - cifs_buf_release(pSMB); - /* - * Note: On -EAGAIN error only caller can retry on handle based calls - * since file handle passed in no longer valid. - */ + *tag = le32_to_cpu(((struct reparse_data_buffer *)start)->ReparseTag); + rsp->iov_base = io_rsp; + rsp->iov_len = io_rsp_len; + *rsp_buftype = CIFS_LARGE_BUFFER; + CIFSSMBClose(xid, tcon, fid.netfid); + return 0; + +error: + cifs_buf_release(io_req); + CIFSSMBClose(xid, tcon, fid.netfid); return rc; } diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index 7b923e36501b0..76ccbdba58558 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -156,13 +156,14 @@ cifs_signal_cifsd_for_reconnect(struct TCP_Server_Info *server, /* If server is a channel, select the primary channel */ pserver = SERVER_IS_CHAN(server) ? server->primary_server : server; - spin_lock(&pserver->srv_lock); + /* if we need to signal just this channel */ if (!all_channels) { - pserver->tcpStatus = CifsNeedReconnect; - spin_unlock(&pserver->srv_lock); + spin_lock(&server->srv_lock); + if (server->tcpStatus != CifsExiting) + server->tcpStatus = CifsNeedReconnect; + spin_unlock(&server->srv_lock); return; } - spin_unlock(&pserver->srv_lock); spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { @@ -1179,7 +1180,12 @@ cifs_demultiplex_thread(void *p) server->total_read += length; if (server->ops->next_header) { - next_offset = server->ops->next_header(buf); + if (server->ops->next_header(server, buf, &next_offset)) { + cifs_dbg(VFS, "%s: malformed response (next_offset=%u)\n", + __func__, next_offset); + cifs_reconnect(server, true); + continue; + } if (next_offset) server->pdu_size = next_offset; } @@ -2033,6 +2039,12 @@ void __cifs_put_smb_ses(struct cifs_ses *ses) } } + /* we now account for primary channel in iface->refcount */ + if (ses->chans[0].iface) { + kref_put(&ses->chans[0].iface->refcount, release_iface); + ses->chans[0].server = NULL; + } + sesInfoFree(ses); cifs_put_tcp_session(server, 0); } @@ -3560,7 +3572,7 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx) ctx->prepath = NULL; out: - cifs_try_adding_channels(cifs_sb, mnt_ctx.ses); + cifs_try_adding_channels(mnt_ctx.ses); rc = mount_setup_tlink(cifs_sb, mnt_ctx.ses, mnt_ctx.tcon); if (rc) goto error; @@ -3849,8 +3861,12 @@ cifs_setup_session(const unsigned int xid, struct cifs_ses *ses, is_binding = !CIFS_ALL_CHANS_NEED_RECONNECT(ses); spin_unlock(&ses->chan_lock); - if (!is_binding) + if (!is_binding) { ses->ses_status = SES_IN_SETUP; + + /* force iface_list refresh */ + ses->iface_last_update = 0; + } spin_unlock(&ses->ses_lock); /* update ses ip_addr only for primary chan */ diff --git a/fs/smb/client/dfs.c b/fs/smb/client/dfs.c index 81b84151450d2..a8a1d386da656 100644 --- a/fs/smb/client/dfs.c +++ b/fs/smb/client/dfs.c @@ -263,15 +263,23 @@ static int __dfs_mount_share(struct cifs_mount_ctx *mnt_ctx) return rc; } -/* Resolve UNC hostname in @ctx->source and set ip addr in @ctx->dstaddr */ +/* + * If @ctx->dfs_automount, then update @ctx->dstaddr earlier with the DFS root + * server from where we'll start following any referrals. Otherwise rely on the + * value provided by mount(2) as the user might not have dns_resolver key set up + * and therefore failing to upcall to resolve UNC hostname under @ctx->source. + */ static int update_fs_context_dstaddr(struct smb3_fs_context *ctx) { struct sockaddr *addr = (struct sockaddr *)&ctx->dstaddr; - int rc; + int rc = 0; - rc = dns_resolve_server_name_to_ip(ctx->source, addr, NULL); - if (!rc) - cifs_set_port(addr, ctx->port); + if (!ctx->nodfs && ctx->dfs_automount) { + rc = dns_resolve_server_name_to_ip(ctx->source, addr, NULL); + if (!rc) + cifs_set_port(addr, ctx->port); + ctx->dfs_automount = false; + } return rc; } diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index 2108b3b40ce92..32a8525415d96 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -1085,7 +1085,8 @@ int cifs_close(struct inode *inode, struct file *file) !test_bit(CIFS_INO_CLOSE_ON_LOCK, &cinode->flags) && dclose) { if (test_and_clear_bit(CIFS_INO_MODIFIED_ATTR, &cinode->flags)) { - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, + inode_set_ctime_current(inode)); } spin_lock(&cinode->deferred_lock); cifs_add_deferred_close(cfile, dclose); @@ -2596,7 +2597,7 @@ static int cifs_partialpagewrite(struct page *page, unsigned from, unsigned to) write_data, to - from, &offset); cifsFileInfo_put(open_file); /* Does mm or vfs already set times? */ - inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode); + simple_inode_init_ts(inode); if ((bytes_written > 0) && (offset)) rc = 0; else if (bytes_written < 0) @@ -4647,11 +4648,13 @@ static void cifs_readahead(struct readahead_control *ractl) static int cifs_readpage_worker(struct file *file, struct page *page, loff_t *poffset) { + struct inode *inode = file_inode(file); + struct timespec64 atime, mtime; char *read_data; int rc; /* Is the page cached? */ - rc = cifs_readpage_from_fscache(file_inode(file), page); + rc = cifs_readpage_from_fscache(inode, page); if (rc == 0) goto read_complete; @@ -4666,11 +4669,10 @@ static int cifs_readpage_worker(struct file *file, struct page *page, cifs_dbg(FYI, "Bytes read %d\n", rc); /* we do not want atime to be less than mtime, it broke some apps */ - file_inode(file)->i_atime = current_time(file_inode(file)); - if (timespec64_compare(&(file_inode(file)->i_atime), &(file_inode(file)->i_mtime))) - file_inode(file)->i_atime = file_inode(file)->i_mtime; - else - file_inode(file)->i_atime = current_time(file_inode(file)); + atime = inode_set_atime_to_ts(inode, current_time(inode)); + mtime = inode_get_mtime(inode); + if (timespec64_compare(&atime, &mtime) < 0) + inode_set_atime_to_ts(inode, inode_get_mtime(inode)); if (PAGE_SIZE > rc) memset(read_data + rc, 0, PAGE_SIZE - rc); diff --git a/fs/smb/client/fs_context.h b/fs/smb/client/fs_context.h index 9d8d34af02114..cf46916286d02 100644 --- a/fs/smb/client/fs_context.h +++ b/fs/smb/client/fs_context.h @@ -268,6 +268,7 @@ struct smb3_fs_context { bool witness:1; /* use witness protocol */ char *leaf_fullpath; struct cifs_ses *dfs_root_ses; + bool dfs_automount:1; /* set for dfs automount only */ }; extern const struct fs_parameter_spec smb3_fs_parameters[]; diff --git a/fs/smb/client/fscache.h b/fs/smb/client/fscache.h index 84f3b09367d2c..a3d73720914f8 100644 --- a/fs/smb/client/fscache.h +++ b/fs/smb/client/fscache.h @@ -49,12 +49,12 @@ static inline void cifs_fscache_fill_coherency(struct inode *inode, struct cifs_fscache_inode_coherency_data *cd) { - struct cifsInodeInfo *cifsi = CIFS_I(inode); struct timespec64 ctime = inode_get_ctime(inode); + struct timespec64 mtime = inode_get_mtime(inode); memset(cd, 0, sizeof(*cd)); - cd->last_write_time_sec = cpu_to_le64(cifsi->netfs.inode.i_mtime.tv_sec); - cd->last_write_time_nsec = cpu_to_le32(cifsi->netfs.inode.i_mtime.tv_nsec); + cd->last_write_time_sec = cpu_to_le64(mtime.tv_sec); + cd->last_write_time_nsec = cpu_to_le32(mtime.tv_nsec); cd->last_change_time_sec = cpu_to_le64(ctime.tv_sec); cd->last_change_time_nsec = cpu_to_le32(ctime.tv_nsec); } diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index d7c302442c1ec..09c5c0f5c96e2 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -82,6 +82,7 @@ cifs_revalidate_cache(struct inode *inode, struct cifs_fattr *fattr) { struct cifs_fscache_inode_coherency_data cd; struct cifsInodeInfo *cifs_i = CIFS_I(inode); + struct timespec64 mtime; cifs_dbg(FYI, "%s: revalidating inode %llu\n", __func__, cifs_i->uniqueid); @@ -101,7 +102,8 @@ cifs_revalidate_cache(struct inode *inode, struct cifs_fattr *fattr) /* revalidate if mtime or size have changed */ fattr->cf_mtime = timestamp_truncate(fattr->cf_mtime, inode); - if (timespec64_equal(&inode->i_mtime, &fattr->cf_mtime) && + mtime = inode_get_mtime(inode); + if (timespec64_equal(&mtime, &fattr->cf_mtime) && cifs_i->server_eof == fattr->cf_eof) { cifs_dbg(FYI, "%s: inode %llu is unchanged\n", __func__, cifs_i->uniqueid); @@ -164,10 +166,10 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr) fattr->cf_ctime = timestamp_truncate(fattr->cf_ctime, inode); /* we do not want atime to be less than mtime, it broke some apps */ if (timespec64_compare(&fattr->cf_atime, &fattr->cf_mtime) < 0) - inode->i_atime = fattr->cf_mtime; + inode_set_atime_to_ts(inode, fattr->cf_mtime); else - inode->i_atime = fattr->cf_atime; - inode->i_mtime = fattr->cf_mtime; + inode_set_atime_to_ts(inode, fattr->cf_atime); + inode_set_mtime_to_ts(inode, fattr->cf_mtime); inode_set_ctime_to_ts(inode, fattr->cf_ctime); inode->i_rdev = fattr->cf_rdev; cifs_nlink_fattr_to_inode(inode, fattr); @@ -457,8 +459,7 @@ static int cifs_get_unix_fattr(const unsigned char *full_path, return -EOPNOTSUPP; rc = server->ops->query_symlink(xid, tcon, cifs_sb, full_path, - &fattr->cf_symlink_target, - NULL); + &fattr->cf_symlink_target); cifs_dbg(FYI, "%s: query_symlink: %d\n", __func__, rc); } return rc; @@ -592,6 +593,10 @@ cifs_sfu_type(struct cifs_fattr *fattr, const char *path, cifs_dbg(FYI, "Symlink\n"); fattr->cf_mode |= S_IFLNK; fattr->cf_dtype = DT_LNK; + } else if (memcmp("LnxFIFO", pbuf, 8) == 0) { + cifs_dbg(FYI, "FIFO\n"); + fattr->cf_mode |= S_IFIFO; + fattr->cf_dtype = DT_FIFO; } else { fattr->cf_mode |= S_IFREG; /* file? */ fattr->cf_dtype = DT_REG; @@ -716,10 +721,51 @@ static void smb311_posix_info_to_fattr(struct cifs_fattr *fattr, fattr->cf_mode, fattr->cf_uniqueid, fattr->cf_nlink); } +static inline dev_t nfs_mkdev(struct reparse_posix_data *buf) +{ + u64 v = le64_to_cpu(*(__le64 *)buf->DataBuffer); + + return MKDEV(v >> 32, v & 0xffffffff); +} + bool cifs_reparse_point_to_fattr(struct cifs_sb_info *cifs_sb, struct cifs_fattr *fattr, - u32 tag) + struct cifs_open_info_data *data) { + struct reparse_posix_data *buf = data->reparse.posix; + u32 tag = data->reparse.tag; + + if (tag == IO_REPARSE_TAG_NFS && buf) { + switch (le64_to_cpu(buf->InodeType)) { + case NFS_SPECFILE_CHR: + fattr->cf_mode |= S_IFCHR | cifs_sb->ctx->file_mode; + fattr->cf_dtype = DT_CHR; + fattr->cf_rdev = nfs_mkdev(buf); + break; + case NFS_SPECFILE_BLK: + fattr->cf_mode |= S_IFBLK | cifs_sb->ctx->file_mode; + fattr->cf_dtype = DT_BLK; + fattr->cf_rdev = nfs_mkdev(buf); + break; + case NFS_SPECFILE_FIFO: + fattr->cf_mode |= S_IFIFO | cifs_sb->ctx->file_mode; + fattr->cf_dtype = DT_FIFO; + break; + case NFS_SPECFILE_SOCK: + fattr->cf_mode |= S_IFSOCK | cifs_sb->ctx->file_mode; + fattr->cf_dtype = DT_SOCK; + break; + case NFS_SPECFILE_LNK: + fattr->cf_mode = S_IFLNK | cifs_sb->ctx->file_mode; + fattr->cf_dtype = DT_LNK; + break; + default: + WARN_ON_ONCE(1); + return false; + } + return true; + } + switch (tag) { case IO_REPARSE_TAG_LX_SYMLINK: fattr->cf_mode |= S_IFLNK | cifs_sb->ctx->file_mode; @@ -744,7 +790,7 @@ bool cifs_reparse_point_to_fattr(struct cifs_sb_info *cifs_sb, case 0: /* SMB1 symlink */ case IO_REPARSE_TAG_SYMLINK: case IO_REPARSE_TAG_NFS: - fattr->cf_mode = S_IFLNK; + fattr->cf_mode = S_IFLNK | cifs_sb->ctx->file_mode; fattr->cf_dtype = DT_LNK; break; default: @@ -785,7 +831,7 @@ static void cifs_open_info_to_fattr(struct cifs_fattr *fattr, fattr->cf_nlink = le32_to_cpu(info->NumberOfLinks); if (cifs_open_data_reparse(data) && - cifs_reparse_point_to_fattr(cifs_sb, fattr, data->reparse_tag)) + cifs_reparse_point_to_fattr(cifs_sb, fattr, data)) goto out_reparse; if (fattr->cf_cifsattrs & ATTR_DIRECTORY) { @@ -819,6 +865,8 @@ static void cifs_open_info_to_fattr(struct cifs_fattr *fattr, out_reparse: if (S_ISLNK(fattr->cf_mode)) { + if (likely(data->symlink_target)) + fattr->cf_eof = strnlen(data->symlink_target, PATH_MAX); fattr->cf_symlink_target = data->symlink_target; data->symlink_target = NULL; } @@ -850,7 +898,7 @@ cifs_get_file_info(struct file *filp) data.adjust_tz = false; if (data.symlink_target) { data.symlink = true; - data.reparse_tag = IO_REPARSE_TAG_SYMLINK; + data.reparse.tag = IO_REPARSE_TAG_SYMLINK; } cifs_open_info_to_fattr(&fattr, &data, inode->i_sb); break; @@ -1019,7 +1067,7 @@ static int reparse_info_to_fattr(struct cifs_open_info_data *data, struct cifs_sb_info *cifs_sb = CIFS_SB(sb); struct kvec rsp_iov, *iov = NULL; int rsp_buftype = CIFS_NO_BUFFER; - u32 tag = data->reparse_tag; + u32 tag = data->reparse.tag; int rc = 0; if (!tag && server->ops->query_reparse_point) { @@ -1029,22 +1077,28 @@ static int reparse_info_to_fattr(struct cifs_open_info_data *data, if (!rc) iov = &rsp_iov; } - switch ((data->reparse_tag = tag)) { + + rc = -EOPNOTSUPP; + switch ((data->reparse.tag = tag)) { case 0: /* SMB1 symlink */ - iov = NULL; - fallthrough; - case IO_REPARSE_TAG_NFS: - case IO_REPARSE_TAG_SYMLINK: - if (!data->symlink_target && server->ops->query_symlink) { + if (server->ops->query_symlink) { rc = server->ops->query_symlink(xid, tcon, cifs_sb, full_path, - &data->symlink_target, - iov); + &data->symlink_target); } break; case IO_REPARSE_TAG_MOUNT_POINT: cifs_create_junction_fattr(fattr, sb); + rc = 0; goto out; + default: + if (data->symlink_target) { + rc = 0; + } else if (server->ops->parse_reparse_point) { + rc = server->ops->parse_reparse_point(cifs_sb, + iov, data); + } + break; } cifs_open_info_to_fattr(fattr, data, sb); @@ -1816,7 +1870,7 @@ int cifs_unlink(struct inode *dir, struct dentry *dentry) when needed */ inode_set_ctime_current(inode); } - dir->i_mtime = inode_set_ctime_current(dir); + inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); cifs_inode = CIFS_I(dir); CIFS_I(dir)->time = 0; /* force revalidate of dir as well */ unlink_out: @@ -2131,7 +2185,7 @@ int cifs_rmdir(struct inode *inode, struct dentry *direntry) cifsInode->time = 0; inode_set_ctime_current(d_inode(direntry)); - inode->i_mtime = inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); rmdir_exit: free_dentry_path(page); @@ -2337,9 +2391,6 @@ cifs_rename2(struct mnt_idmap *idmap, struct inode *source_dir, /* force revalidate to go get info when needed */ CIFS_I(source_dir)->time = CIFS_I(target_dir)->time = 0; - source_dir->i_mtime = target_dir->i_mtime = inode_set_ctime_to_ts(source_dir, - inode_set_ctime_current(target_dir)); - cifs_rename_exit: kfree(info_buf_source); free_dentry_path(page2); diff --git a/fs/smb/client/ioctl.c b/fs/smb/client/ioctl.c index f7160003e0ed9..73ededa8eba5c 100644 --- a/fs/smb/client/ioctl.c +++ b/fs/smb/client/ioctl.c @@ -117,6 +117,20 @@ static long cifs_ioctl_copychunk(unsigned int xid, struct file *dst_file, return rc; } +static long smb_mnt_get_tcon_info(struct cifs_tcon *tcon, void __user *arg) +{ + int rc = 0; + struct smb_mnt_tcon_info tcon_inf; + + tcon_inf.tid = tcon->tid; + tcon_inf.session_id = tcon->ses->Suid; + + if (copy_to_user(arg, &tcon_inf, sizeof(struct smb_mnt_tcon_info))) + rc = -EFAULT; + + return rc; +} + static long smb_mnt_get_fsinfo(unsigned int xid, struct cifs_tcon *tcon, void __user *arg) { @@ -414,6 +428,17 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) tcon = tlink_tcon(pSMBFile->tlink); rc = smb_mnt_get_fsinfo(xid, tcon, (void __user *)arg); break; + case CIFS_IOC_GET_TCON_INFO: + cifs_sb = CIFS_SB(inode->i_sb); + tlink = cifs_sb_tlink(cifs_sb); + if (IS_ERR(tlink)) { + rc = PTR_ERR(tlink); + break; + } + tcon = tlink_tcon(tlink); + rc = smb_mnt_get_tcon_info(tcon, (void __user *)arg); + cifs_put_tlink(tlink); + break; case CIFS_ENUMERATE_SNAPSHOTS: if (pSMBFile == NULL) break; diff --git a/fs/smb/client/misc.c b/fs/smb/client/misc.c index 35b176457bbed..c2137ea3c2538 100644 --- a/fs/smb/client/misc.c +++ b/fs/smb/client/misc.c @@ -363,6 +363,10 @@ checkSMB(char *buf, unsigned int total_read, struct TCP_Server_Info *server) cifs_dbg(VFS, "Length less than smb header size\n"); } return -EIO; + } else if (total_read < sizeof(*smb) + 2 * smb->WordCount) { + cifs_dbg(VFS, "%s: can't read BCC due to invalid WordCount(%u)\n", + __func__, smb->WordCount); + return -EIO; } /* otherwise, there is enough to get to the BCC */ diff --git a/fs/smb/client/namespace.c b/fs/smb/client/namespace.c index c8f5ed8a69f1c..a6968573b775e 100644 --- a/fs/smb/client/namespace.c +++ b/fs/smb/client/namespace.c @@ -117,6 +117,18 @@ cifs_build_devname(char *nodename, const char *prepath) return dev; } +static bool is_dfs_mount(struct dentry *dentry) +{ + struct cifs_sb_info *cifs_sb = CIFS_SB(dentry->d_sb); + struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb); + bool ret; + + spin_lock(&tcon->tc_lock); + ret = !!tcon->origin_fullpath; + spin_unlock(&tcon->tc_lock); + return ret; +} + /* Return full path out of a dentry set for automount */ static char *automount_fullpath(struct dentry *dentry, void *page) { @@ -212,8 +224,9 @@ static struct vfsmount *cifs_do_automount(struct path *path) ctx->source = NULL; goto out; } - cifs_dbg(FYI, "%s: ctx: source=%s UNC=%s prepath=%s\n", - __func__, ctx->source, ctx->UNC, ctx->prepath); + ctx->dfs_automount = is_dfs_mount(mntpt); + cifs_dbg(FYI, "%s: ctx: source=%s UNC=%s prepath=%s dfs_automount=%d\n", + __func__, ctx->source, ctx->UNC, ctx->prepath, ctx->dfs_automount); mnt = fc_mount(fc); out: diff --git a/fs/smb/client/readdir.c b/fs/smb/client/readdir.c index 47fc22de8d20c..d30ea2005eb36 100644 --- a/fs/smb/client/readdir.c +++ b/fs/smb/client/readdir.c @@ -153,6 +153,10 @@ static bool reparse_file_needs_reval(const struct cifs_fattr *fattr) static void cifs_fill_common_info(struct cifs_fattr *fattr, struct cifs_sb_info *cifs_sb) { + struct cifs_open_info_data data = { + .reparse = { .tag = fattr->cf_cifstag, }, + }; + fattr->cf_uid = cifs_sb->ctx->linux_uid; fattr->cf_gid = cifs_sb->ctx->linux_gid; @@ -165,7 +169,7 @@ cifs_fill_common_info(struct cifs_fattr *fattr, struct cifs_sb_info *cifs_sb) * reasonably map some of them to directories vs. files vs. symlinks */ if ((fattr->cf_cifsattrs & ATTR_REPARSE) && - cifs_reparse_point_to_fattr(cifs_sb, fattr, fattr->cf_cifstag)) + cifs_reparse_point_to_fattr(cifs_sb, fattr, &data)) goto out_reparse; if (fattr->cf_cifsattrs & ATTR_DIRECTORY) { diff --git a/fs/smb/client/sess.c b/fs/smb/client/sess.c index 79f26c560edf8..80050e36f0451 100644 --- a/fs/smb/client/sess.c +++ b/fs/smb/client/sess.c @@ -24,7 +24,7 @@ #include "fs_context.h" static int -cifs_ses_add_channel(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses, +cifs_ses_add_channel(struct cifs_ses *ses, struct cifs_server_iface *iface); bool @@ -157,14 +157,16 @@ cifs_chan_is_iface_active(struct cifs_ses *ses, } /* returns number of channels added */ -int cifs_try_adding_channels(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses) +int cifs_try_adding_channels(struct cifs_ses *ses) { struct TCP_Server_Info *server = ses->server; int old_chan_count, new_chan_count; int left; int rc = 0; int tries = 0; + size_t iface_weight = 0, iface_min_speed = 0; struct cifs_server_iface *iface = NULL, *niface = NULL; + struct cifs_server_iface *last_iface = NULL; spin_lock(&ses->chan_lock); @@ -186,28 +188,17 @@ int cifs_try_adding_channels(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses) } if (!(server->capabilities & SMB2_GLOBAL_CAP_MULTI_CHANNEL)) { - ses->chan_max = 1; spin_unlock(&ses->chan_lock); cifs_server_dbg(VFS, "no multichannel support\n"); return 0; } spin_unlock(&ses->chan_lock); - /* - * Keep connecting to same, fastest, iface for all channels as - * long as its RSS. Try next fastest one if not RSS or channel - * creation fails. - */ - spin_lock(&ses->iface_lock); - iface = list_first_entry(&ses->iface_list, struct cifs_server_iface, - iface_head); - spin_unlock(&ses->iface_lock); - while (left > 0) { tries++; if (tries > 3*ses->chan_max) { - cifs_dbg(FYI, "too many channel open attempts (%d channels left to open)\n", + cifs_dbg(VFS, "too many channel open attempts (%d channels left to open)\n", left); break; } @@ -215,23 +206,41 @@ int cifs_try_adding_channels(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses) spin_lock(&ses->iface_lock); if (!ses->iface_count) { spin_unlock(&ses->iface_lock); + cifs_dbg(VFS, "server %s does not advertise interfaces\n", + ses->server->hostname); break; } + if (!iface) + iface = list_first_entry(&ses->iface_list, struct cifs_server_iface, + iface_head); + last_iface = list_last_entry(&ses->iface_list, struct cifs_server_iface, + iface_head); + iface_min_speed = last_iface->speed; + list_for_each_entry_safe_from(iface, niface, &ses->iface_list, iface_head) { + /* do not mix rdma and non-rdma interfaces */ + if (iface->rdma_capable != ses->server->rdma) + continue; + /* skip ifaces that are unusable */ if (!iface->is_active || (is_ses_using_iface(ses, iface) && - !iface->rss_capable)) { + !iface->rss_capable)) + continue; + + /* check if we already allocated enough channels */ + iface_weight = iface->speed / iface_min_speed; + + if (iface->weight_fulfilled >= iface_weight) continue; - } /* take ref before unlock */ kref_get(&iface->refcount); spin_unlock(&ses->iface_lock); - rc = cifs_ses_add_channel(cifs_sb, ses, iface); + rc = cifs_ses_add_channel(ses, iface); spin_lock(&ses->iface_lock); if (rc) { @@ -242,10 +251,21 @@ int cifs_try_adding_channels(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses) continue; } - cifs_dbg(FYI, "successfully opened new channel on iface:%pIS\n", + iface->num_channels++; + iface->weight_fulfilled++; + cifs_dbg(VFS, "successfully opened new channel on iface:%pIS\n", &iface->sockaddr); break; } + + /* reached end of list. reset weight_fulfilled and start over */ + if (list_entry_is_head(iface, &ses->iface_list, iface_head)) { + list_for_each_entry(iface, &ses->iface_list, iface_head) + iface->weight_fulfilled = 0; + spin_unlock(&ses->iface_lock); + iface = NULL; + continue; + } spin_unlock(&ses->iface_lock); left--; @@ -264,8 +284,11 @@ int cifs_chan_update_iface(struct cifs_ses *ses, struct TCP_Server_Info *server) { unsigned int chan_index; + size_t iface_weight = 0, iface_min_speed = 0; struct cifs_server_iface *iface = NULL; struct cifs_server_iface *old_iface = NULL; + struct cifs_server_iface *last_iface = NULL; + struct sockaddr_storage ss; int rc = 0; spin_lock(&ses->chan_lock); @@ -284,14 +307,49 @@ cifs_chan_update_iface(struct cifs_ses *ses, struct TCP_Server_Info *server) } spin_unlock(&ses->chan_lock); + spin_lock(&server->srv_lock); + ss = server->dstaddr; + spin_unlock(&server->srv_lock); + spin_lock(&ses->iface_lock); + if (!ses->iface_count) { + spin_unlock(&ses->iface_lock); + cifs_dbg(VFS, "server %s does not advertise interfaces\n", ses->server->hostname); + return 0; + } + + last_iface = list_last_entry(&ses->iface_list, struct cifs_server_iface, + iface_head); + iface_min_speed = last_iface->speed; + /* then look for a new one */ list_for_each_entry(iface, &ses->iface_list, iface_head) { + if (!chan_index) { + /* if we're trying to get the updated iface for primary channel */ + if (!cifs_match_ipaddr((struct sockaddr *) &ss, + (struct sockaddr *) &iface->sockaddr)) + continue; + + kref_get(&iface->refcount); + break; + } + + /* do not mix rdma and non-rdma interfaces */ + if (iface->rdma_capable != server->rdma) + continue; + if (!iface->is_active || (is_ses_using_iface(ses, iface) && !iface->rss_capable)) { continue; } + + /* check if we already allocated enough channels */ + iface_weight = iface->speed / iface_min_speed; + + if (iface->weight_fulfilled >= iface_weight) + continue; + kref_get(&iface->refcount); break; } @@ -302,16 +360,41 @@ cifs_chan_update_iface(struct cifs_ses *ses, struct TCP_Server_Info *server) cifs_dbg(FYI, "unable to find a suitable iface\n"); } + if (!chan_index && !iface) { + cifs_dbg(FYI, "unable to get the interface matching: %pIS\n", + &ss); + spin_unlock(&ses->iface_lock); + return 0; + } + /* now drop the ref to the current iface */ if (old_iface && iface) { cifs_dbg(FYI, "replacing iface: %pIS with %pIS\n", &old_iface->sockaddr, &iface->sockaddr); + + old_iface->num_channels--; + if (old_iface->weight_fulfilled) + old_iface->weight_fulfilled--; + iface->num_channels++; + iface->weight_fulfilled++; + kref_put(&old_iface->refcount, release_iface); } else if (old_iface) { cifs_dbg(FYI, "releasing ref to iface: %pIS\n", &old_iface->sockaddr); + + old_iface->num_channels--; + if (old_iface->weight_fulfilled) + old_iface->weight_fulfilled--; + kref_put(&old_iface->refcount, release_iface); + } else if (!chan_index) { + /* special case: update interface for primary channel */ + cifs_dbg(FYI, "referencing primary channel iface: %pIS\n", + &iface->sockaddr); + iface->num_channels++; + iface->weight_fulfilled++; } else { WARN_ON(!iface); cifs_dbg(FYI, "adding new iface: %pIS\n", &iface->sockaddr); @@ -355,7 +438,7 @@ cifs_ses_find_chan(struct cifs_ses *ses, struct TCP_Server_Info *server) } static int -cifs_ses_add_channel(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses, +cifs_ses_add_channel(struct cifs_ses *ses, struct cifs_server_iface *iface) { struct TCP_Server_Info *chan_server; @@ -434,7 +517,7 @@ cifs_ses_add_channel(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses, * This will be used for encoding/decoding user/domain/pw * during sess setup auth. */ - ctx->local_nls = cifs_sb->local_nls; + ctx->local_nls = ses->local_nls; /* Use RDMA if possible */ ctx->rdma = iface->rdma_capable; @@ -480,7 +563,7 @@ cifs_ses_add_channel(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses, rc = cifs_negotiate_protocol(xid, ses, chan->server); if (!rc) - rc = cifs_setup_session(xid, ses, chan->server, cifs_sb->local_nls); + rc = cifs_setup_session(xid, ses, chan->server, ses->local_nls); mutex_unlock(&ses->session_mutex); diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c index 9bf8735cdd1e8..64e25233e85de 100644 --- a/fs/smb/client/smb1ops.c +++ b/fs/smb/client/smb1ops.c @@ -976,64 +976,37 @@ static int cifs_query_symlink(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_sb_info *cifs_sb, const char *full_path, - char **target_path, - struct kvec *rsp_iov) + char **target_path) { int rc; - int oplock = 0; - bool is_reparse_point = !!rsp_iov; - struct cifs_fid fid; - struct cifs_open_parms oparms; - cifs_dbg(FYI, "%s: path: %s\n", __func__, full_path); + cifs_tcon_dbg(FYI, "%s: path=%s\n", __func__, full_path); - if (is_reparse_point) { - cifs_dbg(VFS, "reparse points not handled for SMB1 symlinks\n"); + if (!cap_unix(tcon->ses)) return -EOPNOTSUPP; - } - - /* Check for unix extensions */ - if (cap_unix(tcon->ses)) { - rc = CIFSSMBUnixQuerySymLink(xid, tcon, full_path, target_path, - cifs_sb->local_nls, - cifs_remap(cifs_sb)); - if (rc == -EREMOTE) - rc = cifs_unix_dfs_readlink(xid, tcon, full_path, - target_path, - cifs_sb->local_nls); - - goto out; - } - oparms = (struct cifs_open_parms) { - .tcon = tcon, - .cifs_sb = cifs_sb, - .desired_access = FILE_READ_ATTRIBUTES, - .create_options = cifs_create_options(cifs_sb, - OPEN_REPARSE_POINT), - .disposition = FILE_OPEN, - .path = full_path, - .fid = &fid, - }; - - rc = CIFS_open(xid, &oparms, &oplock, NULL); - if (rc) - goto out; - - rc = CIFSSMBQuerySymLink(xid, tcon, fid.netfid, target_path, - cifs_sb->local_nls); - if (rc) - goto out_close; - - convert_delimiter(*target_path, '/'); -out_close: - CIFSSMBClose(xid, tcon, fid.netfid); -out: - if (!rc) - cifs_dbg(FYI, "%s: target path: %s\n", __func__, *target_path); + rc = CIFSSMBUnixQuerySymLink(xid, tcon, full_path, target_path, + cifs_sb->local_nls, cifs_remap(cifs_sb)); + if (rc == -EREMOTE) + rc = cifs_unix_dfs_readlink(xid, tcon, full_path, + target_path, cifs_sb->local_nls); return rc; } +static int cifs_parse_reparse_point(struct cifs_sb_info *cifs_sb, + struct kvec *rsp_iov, + struct cifs_open_info_data *data) +{ + struct reparse_data_buffer *buf; + TRANSACT_IOCTL_RSP *io = rsp_iov->iov_base; + bool unicode = !!(io->hdr.Flags2 & SMBFLG2_UNICODE); + u32 plen = le16_to_cpu(io->ByteCount); + + buf = (struct reparse_data_buffer *)((__u8 *)&io->hdr.Protocol + + le32_to_cpu(io->DataOffset)); + return parse_reparse_point(buf, plen, cifs_sb, unicode, data); +} + static bool cifs_is_read_op(__u32 oplock) { @@ -1214,6 +1187,7 @@ struct smb_version_operations smb1_operations = { .is_path_accessible = cifs_is_path_accessible, .can_echo = cifs_can_echo, .query_path_info = cifs_query_path_info, + .query_reparse_point = cifs_query_reparse_point, .query_file_info = cifs_query_file_info, .get_srv_inum = cifs_get_srv_inum, .set_path_size = CIFSSMBSetEOF, @@ -1229,6 +1203,7 @@ struct smb_version_operations smb1_operations = { .rename = CIFSSMBRename, .create_hardlink = CIFSCreateHardLink, .query_symlink = cifs_query_symlink, + .parse_reparse_point = cifs_parse_reparse_point, .open = cifs_open_file, .set_fid = cifs_set_fid, .close = cifs_close_file, diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c index 0b89f7008ac0f..c94940af5d4b8 100644 --- a/fs/smb/client/smb2inode.c +++ b/fs/smb/client/smb2inode.c @@ -555,7 +555,7 @@ static int parse_create_response(struct cifs_open_info_data *data, break; } data->reparse_point = reparse_point; - data->reparse_tag = tag; + data->reparse.tag = tag; return rc; } diff --git a/fs/smb/client/smb2misc.c b/fs/smb/client/smb2misc.c index 25f7cd6f23d64..e20b4354e703b 100644 --- a/fs/smb/client/smb2misc.c +++ b/fs/smb/client/smb2misc.c @@ -313,6 +313,9 @@ static const bool has_smb2_data_area[NUMBER_OF_SMB2_COMMANDS] = { char * smb2_get_data_area_len(int *off, int *len, struct smb2_hdr *shdr) { + const int max_off = 4096; + const int max_len = 128 * 1024; + *off = 0; *len = 0; @@ -384,29 +387,20 @@ smb2_get_data_area_len(int *off, int *len, struct smb2_hdr *shdr) * Invalid length or offset probably means data area is invalid, but * we have little choice but to ignore the data area in this case. */ - if (*off > 4096) { - cifs_dbg(VFS, "offset %d too large, data area ignored\n", *off); - *len = 0; - *off = 0; - } else if (*off < 0) { - cifs_dbg(VFS, "negative offset %d to data invalid ignore data area\n", - *off); + if (unlikely(*off < 0 || *off > max_off || + *len < 0 || *len > max_len)) { + cifs_dbg(VFS, "%s: invalid data area (off=%d len=%d)\n", + __func__, *off, *len); *off = 0; *len = 0; - } else if (*len < 0) { - cifs_dbg(VFS, "negative data length %d invalid, data area ignored\n", - *len); - *len = 0; - } else if (*len > 128 * 1024) { - cifs_dbg(VFS, "data area larger than 128K: %d\n", *len); + } else if (*off == 0) { *len = 0; } /* return pointer to beginning of data area, ie offset from SMB start */ - if ((*off != 0) && (*len != 0)) + if (*off > 0 && *len > 0) return (char *)shdr + *off; - else - return NULL; + return NULL; } /* @@ -787,7 +781,7 @@ __smb2_handle_cancelled_cmd(struct cifs_tcon *tcon, __u16 cmd, __u64 mid, { struct close_cancelled_open *cancelled; - cancelled = kzalloc(sizeof(*cancelled), GFP_ATOMIC); + cancelled = kzalloc(sizeof(*cancelled), GFP_KERNEL); if (!cancelled) return -ENOMEM; diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 9aeecee6b91b3..e917eeba9c772 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -756,6 +756,7 @@ SMB3_request_interfaces(const unsigned int xid, struct cifs_tcon *tcon, bool in_ unsigned int ret_data_len = 0; struct network_interface_info_ioctl_rsp *out_buf = NULL; struct cifs_ses *ses = tcon->ses; + struct TCP_Server_Info *pserver; /* do not query too frequently */ if (ses->iface_last_update && @@ -780,6 +781,11 @@ SMB3_request_interfaces(const unsigned int xid, struct cifs_tcon *tcon, bool in_ if (rc) goto out; + /* check if iface is still active */ + pserver = ses->chans[0].server; + if (pserver && !cifs_chan_is_iface_active(ses, pserver)) + cifs_chan_update_iface(ses, pserver); + out: kfree(out_buf); return rc; @@ -1403,12 +1409,14 @@ smb2_close_getattr(const unsigned int xid, struct cifs_tcon *tcon, /* Creation time should not need to be updated on close */ if (file_inf.LastWriteTime) - inode->i_mtime = cifs_NTtimeToUnix(file_inf.LastWriteTime); + inode_set_mtime_to_ts(inode, + cifs_NTtimeToUnix(file_inf.LastWriteTime)); if (file_inf.ChangeTime) inode_set_ctime_to_ts(inode, cifs_NTtimeToUnix(file_inf.ChangeTime)); if (file_inf.LastAccessTime) - inode->i_atime = cifs_NTtimeToUnix(file_inf.LastAccessTime); + inode_set_atime_to_ts(inode, + cifs_NTtimeToUnix(file_inf.LastAccessTime)); /* * i_blocks is not related to (i_size / i_blksize), @@ -2828,6 +2836,8 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses, usleep_range(512, 2048); } while (++retry_count < 5); + if (!rc && !dfs_rsp) + rc = -EIO; if (rc) { if (!is_retryable_error(rc) && rc != -ENOENT && rc != -EOPNOTSUPP) cifs_tcon_dbg(VFS, "%s: ioctl error: rc=%d\n", __func__, rc); @@ -2858,115 +2868,119 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses, return rc; } -static int -parse_reparse_posix(struct reparse_posix_data *symlink_buf, - u32 plen, char **target_path, - struct cifs_sb_info *cifs_sb) +/* See MS-FSCC 2.1.2.6 for the 'NFS' style reparse tags */ +static int parse_reparse_posix(struct reparse_posix_data *buf, + struct cifs_sb_info *cifs_sb, + struct cifs_open_info_data *data) { unsigned int len; - - /* See MS-FSCC 2.1.2.6 for the 'NFS' style reparse tags */ - len = le16_to_cpu(symlink_buf->ReparseDataLength); - - if (le64_to_cpu(symlink_buf->InodeType) != NFS_SPECFILE_LNK) { - cifs_dbg(VFS, "%lld not a supported symlink type\n", - le64_to_cpu(symlink_buf->InodeType)); + u64 type; + + switch ((type = le64_to_cpu(buf->InodeType))) { + case NFS_SPECFILE_LNK: + len = le16_to_cpu(buf->ReparseDataLength); + data->symlink_target = cifs_strndup_from_utf16(buf->DataBuffer, + len, true, + cifs_sb->local_nls); + if (!data->symlink_target) + return -ENOMEM; + convert_delimiter(data->symlink_target, '/'); + cifs_dbg(FYI, "%s: target path: %s\n", + __func__, data->symlink_target); + break; + case NFS_SPECFILE_CHR: + case NFS_SPECFILE_BLK: + case NFS_SPECFILE_FIFO: + case NFS_SPECFILE_SOCK: + break; + default: + cifs_dbg(VFS, "%s: unhandled inode type: 0x%llx\n", + __func__, type); return -EOPNOTSUPP; } - - *target_path = cifs_strndup_from_utf16( - symlink_buf->PathBuffer, - len, true, cifs_sb->local_nls); - if (!(*target_path)) - return -ENOMEM; - - convert_delimiter(*target_path, '/'); - cifs_dbg(FYI, "%s: target path: %s\n", __func__, *target_path); - return 0; } -static int -parse_reparse_symlink(struct reparse_symlink_data_buffer *symlink_buf, - u32 plen, char **target_path, - struct cifs_sb_info *cifs_sb) +static int parse_reparse_symlink(struct reparse_symlink_data_buffer *sym, + u32 plen, bool unicode, + struct cifs_sb_info *cifs_sb, + struct cifs_open_info_data *data) { - unsigned int sub_len; - unsigned int sub_offset; + unsigned int len; + unsigned int offs; /* We handle Symbolic Link reparse tag here. See: MS-FSCC 2.1.2.4 */ - sub_offset = le16_to_cpu(symlink_buf->SubstituteNameOffset); - sub_len = le16_to_cpu(symlink_buf->SubstituteNameLength); - if (sub_offset + 20 > plen || - sub_offset + sub_len + 20 > plen) { + offs = le16_to_cpu(sym->SubstituteNameOffset); + len = le16_to_cpu(sym->SubstituteNameLength); + if (offs + 20 > plen || offs + len + 20 > plen) { cifs_dbg(VFS, "srv returned malformed symlink buffer\n"); return -EIO; } - *target_path = cifs_strndup_from_utf16( - symlink_buf->PathBuffer + sub_offset, - sub_len, true, cifs_sb->local_nls); - if (!(*target_path)) + data->symlink_target = cifs_strndup_from_utf16(sym->PathBuffer + offs, + len, unicode, + cifs_sb->local_nls); + if (!data->symlink_target) return -ENOMEM; - convert_delimiter(*target_path, '/'); - cifs_dbg(FYI, "%s: target path: %s\n", __func__, *target_path); + convert_delimiter(data->symlink_target, '/'); + cifs_dbg(FYI, "%s: target path: %s\n", __func__, data->symlink_target); return 0; } -static int -parse_reparse_point(struct reparse_data_buffer *buf, - u32 plen, char **target_path, - struct cifs_sb_info *cifs_sb) +int parse_reparse_point(struct reparse_data_buffer *buf, + u32 plen, struct cifs_sb_info *cifs_sb, + bool unicode, struct cifs_open_info_data *data) { - if (plen < sizeof(struct reparse_data_buffer)) { - cifs_dbg(VFS, "reparse buffer is too small. Must be at least 8 bytes but was %d\n", - plen); + if (plen < sizeof(*buf)) { + cifs_dbg(VFS, "%s: reparse buffer is too small. Must be at least 8 bytes but was %d\n", + __func__, plen); return -EIO; } - if (plen < le16_to_cpu(buf->ReparseDataLength) + - sizeof(struct reparse_data_buffer)) { - cifs_dbg(VFS, "srv returned invalid reparse buf length: %d\n", - plen); + if (plen < le16_to_cpu(buf->ReparseDataLength) + sizeof(*buf)) { + cifs_dbg(VFS, "%s: invalid reparse buf length: %d\n", + __func__, plen); return -EIO; } + data->reparse.buf = buf; + /* See MS-FSCC 2.1.2 */ switch (le32_to_cpu(buf->ReparseTag)) { case IO_REPARSE_TAG_NFS: - return parse_reparse_posix( - (struct reparse_posix_data *)buf, - plen, target_path, cifs_sb); + return parse_reparse_posix((struct reparse_posix_data *)buf, + cifs_sb, data); case IO_REPARSE_TAG_SYMLINK: return parse_reparse_symlink( (struct reparse_symlink_data_buffer *)buf, - plen, target_path, cifs_sb); + plen, unicode, cifs_sb, data); + case IO_REPARSE_TAG_LX_SYMLINK: + case IO_REPARSE_TAG_AF_UNIX: + case IO_REPARSE_TAG_LX_FIFO: + case IO_REPARSE_TAG_LX_CHR: + case IO_REPARSE_TAG_LX_BLK: + return 0; default: - cifs_dbg(VFS, "srv returned unknown symlink buffer tag:0x%08x\n", - le32_to_cpu(buf->ReparseTag)); + cifs_dbg(VFS, "%s: unhandled reparse tag: 0x%08x\n", + __func__, le32_to_cpu(buf->ReparseTag)); return -EOPNOTSUPP; } } -static int smb2_query_symlink(const unsigned int xid, - struct cifs_tcon *tcon, - struct cifs_sb_info *cifs_sb, - const char *full_path, - char **target_path, - struct kvec *rsp_iov) +static int smb2_parse_reparse_point(struct cifs_sb_info *cifs_sb, + struct kvec *rsp_iov, + struct cifs_open_info_data *data) { struct reparse_data_buffer *buf; struct smb2_ioctl_rsp *io = rsp_iov->iov_base; u32 plen = le32_to_cpu(io->OutputCount); - cifs_dbg(FYI, "%s: path: %s\n", __func__, full_path); - buf = (struct reparse_data_buffer *)((u8 *)io + le32_to_cpu(io->OutputOffset)); - return parse_reparse_point(buf, plen, target_path, cifs_sb); + return parse_reparse_point(buf, plen, cifs_sb, true, data); } static int smb2_query_reparse_point(const unsigned int xid, @@ -2989,7 +3003,7 @@ static int smb2_query_reparse_point(const unsigned int xid, struct kvec *rsp_iov; struct smb2_ioctl_rsp *ioctl_rsp; struct reparse_data_buffer *reparse_buf; - u32 plen; + u32 off, count, len; cifs_dbg(FYI, "%s: path: %s\n", __func__, full_path); @@ -3070,16 +3084,22 @@ static int smb2_query_reparse_point(const unsigned int xid, */ if (rc == 0) { /* See MS-FSCC 2.3.23 */ + off = le32_to_cpu(ioctl_rsp->OutputOffset); + count = le32_to_cpu(ioctl_rsp->OutputCount); + if (check_add_overflow(off, count, &len) || + len > rsp_iov[1].iov_len) { + cifs_tcon_dbg(VFS, "%s: invalid ioctl: off=%d count=%d\n", + __func__, off, count); + rc = -EIO; + goto query_rp_exit; + } - reparse_buf = (struct reparse_data_buffer *) - ((char *)ioctl_rsp + - le32_to_cpu(ioctl_rsp->OutputOffset)); - plen = le32_to_cpu(ioctl_rsp->OutputCount); - - if (plen + le32_to_cpu(ioctl_rsp->OutputOffset) > - rsp_iov[1].iov_len) { - cifs_tcon_dbg(FYI, "srv returned invalid ioctl len: %d\n", - plen); + reparse_buf = (void *)((u8 *)ioctl_rsp + off); + len = sizeof(*reparse_buf); + if (count < len || + count < le16_to_cpu(reparse_buf->ReparseDataLength) + len) { + cifs_tcon_dbg(VFS, "%s: invalid ioctl: off=%d count=%d\n", + __func__, off, count); rc = -EIO; goto query_rp_exit; } @@ -3299,6 +3319,7 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, struct inode *inode = file_inode(file); struct cifsInodeInfo *cifsi = CIFS_I(inode); struct cifsFileInfo *cfile = file->private_data; + unsigned long long new_size; long rc; unsigned int xid; __le64 eof; @@ -3329,10 +3350,15 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, /* * do we also need to change the size of the file? */ - if (keep_size == false && i_size_read(inode) < offset + len) { - eof = cpu_to_le64(offset + len); + new_size = offset + len; + if (keep_size == false && (unsigned long long)i_size_read(inode) < new_size) { + eof = cpu_to_le64(new_size); rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, cfile->pid, &eof); + if (rc >= 0) { + truncate_setsize(inode, new_size); + fscache_resize_cookie(cifs_inode_cookie(inode), new_size); + } } zero_range_exit: @@ -3727,6 +3753,9 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon, if (rc < 0) goto out_2; + truncate_setsize(inode, old_eof + len); + fscache_resize_cookie(cifs_inode_cookie(inode), i_size_read(inode)); + rc = smb2_copychunk_range(xid, cfile, cfile, off, count, off + len); if (rc < 0) goto out_2; @@ -4920,6 +4949,7 @@ receive_encrypted_standard(struct TCP_Server_Info *server, struct smb2_hdr *shdr; unsigned int pdu_length = server->pdu_size; unsigned int buf_size; + unsigned int next_cmd; struct mid_q_entry *mid_entry; int next_is_large; char *next_buffer = NULL; @@ -4948,14 +4978,15 @@ receive_encrypted_standard(struct TCP_Server_Info *server, next_is_large = server->large_buf; one_more: shdr = (struct smb2_hdr *)buf; - if (shdr->NextCommand) { + next_cmd = le32_to_cpu(shdr->NextCommand); + if (next_cmd) { + if (WARN_ON_ONCE(next_cmd > pdu_length)) + return -1; if (next_is_large) next_buffer = (char *)cifs_buf_get(); else next_buffer = (char *)cifs_small_buf_get(); - memcpy(next_buffer, - buf + le32_to_cpu(shdr->NextCommand), - pdu_length - le32_to_cpu(shdr->NextCommand)); + memcpy(next_buffer, buf + next_cmd, pdu_length - next_cmd); } mid_entry = smb2_find_mid(server, buf); @@ -4979,8 +5010,8 @@ receive_encrypted_standard(struct TCP_Server_Info *server, else ret = cifs_handle_standard(server, mid_entry); - if (ret == 0 && shdr->NextCommand) { - pdu_length -= le32_to_cpu(shdr->NextCommand); + if (ret == 0 && next_cmd) { + pdu_length -= next_cmd; server->large_buf = next_is_large; if (next_is_large) server->bigbuf = buf = next_buffer; @@ -5043,17 +5074,22 @@ smb3_handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid) NULL, 0, false); } -static int -smb2_next_header(char *buf) +static int smb2_next_header(struct TCP_Server_Info *server, char *buf, + unsigned int *noff) { struct smb2_hdr *hdr = (struct smb2_hdr *)buf; struct smb2_transform_hdr *t_hdr = (struct smb2_transform_hdr *)buf; - if (hdr->ProtocolId == SMB2_TRANSFORM_PROTO_NUM) - return sizeof(struct smb2_transform_hdr) + - le32_to_cpu(t_hdr->OriginalMessageSize); - - return le32_to_cpu(hdr->NextCommand); + if (hdr->ProtocolId == SMB2_TRANSFORM_PROTO_NUM) { + *noff = le32_to_cpu(t_hdr->OriginalMessageSize); + if (unlikely(check_add_overflow(*noff, sizeof(*t_hdr), noff))) + return -EINVAL; + } else { + *noff = le32_to_cpu(hdr->NextCommand); + } + if (unlikely(*noff && *noff < MID_HEADER_SIZE(server))) + return -EINVAL; + return 0; } static int @@ -5087,7 +5123,7 @@ smb2_make_node(unsigned int xid, struct inode *inode, * over SMB2/SMB3 and Samba will do this with SMB3.1.1 POSIX Extensions */ - if (!S_ISCHR(mode) && !S_ISBLK(mode)) + if (!S_ISCHR(mode) && !S_ISBLK(mode) && !S_ISFIFO(mode)) return rc; cifs_dbg(FYI, "sfu compat create special file\n"); @@ -5135,6 +5171,12 @@ smb2_make_node(unsigned int xid, struct inode *inode, pdev->minor = cpu_to_le64(MINOR(dev)); rc = tcon->ses->server->ops->sync_write(xid, &fid, &io_parms, &bytes_written, iov, 1); + } else if (S_ISFIFO(mode)) { + memcpy(pdev->type, "LnxFIFO", 8); + pdev->major = 0; + pdev->minor = 0; + rc = tcon->ses->server->ops->sync_write(xid, &fid, &io_parms, + &bytes_written, iov, 1); } tcon->ses->server->ops->close(xid, tcon, &fid); d_drop(dentry); @@ -5195,7 +5237,7 @@ struct smb_version_operations smb20_operations = { .unlink = smb2_unlink, .rename = smb2_rename_path, .create_hardlink = smb2_create_hardlink, - .query_symlink = smb2_query_symlink, + .parse_reparse_point = smb2_parse_reparse_point, .query_mf_symlink = smb3_query_mf_symlink, .create_mf_symlink = smb3_create_mf_symlink, .open = smb2_open_file, @@ -5297,7 +5339,7 @@ struct smb_version_operations smb21_operations = { .unlink = smb2_unlink, .rename = smb2_rename_path, .create_hardlink = smb2_create_hardlink, - .query_symlink = smb2_query_symlink, + .parse_reparse_point = smb2_parse_reparse_point, .query_mf_symlink = smb3_query_mf_symlink, .create_mf_symlink = smb3_create_mf_symlink, .open = smb2_open_file, @@ -5402,7 +5444,7 @@ struct smb_version_operations smb30_operations = { .unlink = smb2_unlink, .rename = smb2_rename_path, .create_hardlink = smb2_create_hardlink, - .query_symlink = smb2_query_symlink, + .parse_reparse_point = smb2_parse_reparse_point, .query_mf_symlink = smb3_query_mf_symlink, .create_mf_symlink = smb3_create_mf_symlink, .open = smb2_open_file, @@ -5516,7 +5558,7 @@ struct smb_version_operations smb311_operations = { .unlink = smb2_unlink, .rename = smb2_rename_path, .create_hardlink = smb2_create_hardlink, - .query_symlink = smb2_query_symlink, + .parse_reparse_point = smb2_parse_reparse_point, .query_mf_symlink = smb3_query_mf_symlink, .create_mf_symlink = smb3_create_mf_symlink, .open = smb2_open_file, diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index c75a80bb6d9ee..76a0b9dbcf755 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -376,10 +376,15 @@ static int __smb2_plain_req_init(__le16 smb2_command, struct cifs_tcon *tcon, void **request_buf, unsigned int *total_len) { /* BB eventually switch this to SMB2 specific small buf size */ - if (smb2_command == SMB2_SET_INFO) + switch (smb2_command) { + case SMB2_SET_INFO: + case SMB2_QUERY_INFO: *request_buf = cifs_buf_get(); - else + break; + default: *request_buf = cifs_small_buf_get(); + break; + } if (*request_buf == NULL) { /* BB should we add a retry in here if not a writepage? */ return -ENOMEM; @@ -2141,17 +2146,18 @@ parse_posix_ctxt(struct create_context *cc, struct smb2_file_all_info *info, posix->nlink, posix->mode, posix->reparse_tag); } -void -smb2_parse_contexts(struct TCP_Server_Info *server, - struct smb2_create_rsp *rsp, - unsigned int *epoch, char *lease_key, __u8 *oplock, - struct smb2_file_all_info *buf, - struct create_posix_rsp *posix) +int smb2_parse_contexts(struct TCP_Server_Info *server, + struct kvec *rsp_iov, + unsigned int *epoch, + char *lease_key, __u8 *oplock, + struct smb2_file_all_info *buf, + struct create_posix_rsp *posix) { - char *data_offset; + struct smb2_create_rsp *rsp = rsp_iov->iov_base; struct create_context *cc; - unsigned int next; - unsigned int remaining; + size_t rem, off, len; + size_t doff, dlen; + size_t noff, nlen; char *name; static const char smb3_create_tag_posix[] = { 0x93, 0xAD, 0x25, 0x50, 0x9C, @@ -2160,45 +2166,63 @@ smb2_parse_contexts(struct TCP_Server_Info *server, }; *oplock = 0; - data_offset = (char *)rsp + le32_to_cpu(rsp->CreateContextsOffset); - remaining = le32_to_cpu(rsp->CreateContextsLength); - cc = (struct create_context *)data_offset; + + off = le32_to_cpu(rsp->CreateContextsOffset); + rem = le32_to_cpu(rsp->CreateContextsLength); + if (check_add_overflow(off, rem, &len) || len > rsp_iov->iov_len) + return -EINVAL; + cc = (struct create_context *)((u8 *)rsp + off); /* Initialize inode number to 0 in case no valid data in qfid context */ if (buf) buf->IndexNumber = 0; - while (remaining >= sizeof(struct create_context)) { - name = le16_to_cpu(cc->NameOffset) + (char *)cc; - if (le16_to_cpu(cc->NameLength) == 4 && - strncmp(name, SMB2_CREATE_REQUEST_LEASE, 4) == 0) - *oplock = server->ops->parse_lease_buf(cc, epoch, - lease_key); - else if (buf && (le16_to_cpu(cc->NameLength) == 4) && - strncmp(name, SMB2_CREATE_QUERY_ON_DISK_ID, 4) == 0) - parse_query_id_ctxt(cc, buf); - else if ((le16_to_cpu(cc->NameLength) == 16)) { - if (posix && - memcmp(name, smb3_create_tag_posix, 16) == 0) + while (rem >= sizeof(*cc)) { + doff = le16_to_cpu(cc->DataOffset); + dlen = le32_to_cpu(cc->DataLength); + if (check_add_overflow(doff, dlen, &len) || len > rem) + return -EINVAL; + + noff = le16_to_cpu(cc->NameOffset); + nlen = le16_to_cpu(cc->NameLength); + if (noff + nlen >= doff) + return -EINVAL; + + name = (char *)cc + noff; + switch (nlen) { + case 4: + if (!strncmp(name, SMB2_CREATE_REQUEST_LEASE, 4)) { + *oplock = server->ops->parse_lease_buf(cc, epoch, + lease_key); + } else if (buf && + !strncmp(name, SMB2_CREATE_QUERY_ON_DISK_ID, 4)) { + parse_query_id_ctxt(cc, buf); + } + break; + case 16: + if (posix && !memcmp(name, smb3_create_tag_posix, 16)) parse_posix_ctxt(cc, buf, posix); + break; + default: + cifs_dbg(FYI, "%s: unhandled context (nlen=%zu dlen=%zu)\n", + __func__, nlen, dlen); + if (IS_ENABLED(CONFIG_CIFS_DEBUG2)) + cifs_dump_mem("context data: ", cc, dlen); + break; } - /* else { - cifs_dbg(FYI, "Context not matched with len %d\n", - le16_to_cpu(cc->NameLength)); - cifs_dump_mem("Cctxt name: ", name, 4); - } */ - - next = le32_to_cpu(cc->Next); - if (!next) + + off = le32_to_cpu(cc->Next); + if (!off) break; - remaining -= next; - cc = (struct create_context *)((char *)cc + next); + if (check_sub_overflow(rem, off, &rem)) + return -EINVAL; + cc = (struct create_context *)((u8 *)cc + off); } if (rsp->OplockLevel != SMB2_OPLOCK_LEVEL_LEASE) *oplock = rsp->OplockLevel; - return; + return 0; } static int @@ -3029,8 +3053,8 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, } - smb2_parse_contexts(server, rsp, &oparms->fid->epoch, - oparms->fid->lease_key, oplock, buf, posix); + rc = smb2_parse_contexts(server, &rsp_iov, &oparms->fid->epoch, + oparms->fid->lease_key, oplock, buf, posix); creat_exit: SMB2_open_free(&rqst); free_rsp_buf(resp_buftype, rsp); @@ -3475,8 +3499,13 @@ SMB2_query_info_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server, struct smb2_query_info_req *req; struct kvec *iov = rqst->rq_iov; unsigned int total_len; + size_t len; int rc; + if (unlikely(check_add_overflow(input_len, sizeof(*req), &len) || + len > CIFSMaxBufSize)) + return -EINVAL; + rc = smb2_plain_req_init(SMB2_QUERY_INFO, tcon, server, (void **) &req, &total_len); if (rc) @@ -3498,7 +3527,7 @@ SMB2_query_info_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server, iov[0].iov_base = (char *)req; /* 1 for Buffer */ - iov[0].iov_len = total_len - 1 + input_len; + iov[0].iov_len = len; return 0; } @@ -3506,7 +3535,7 @@ void SMB2_query_info_free(struct smb_rqst *rqst) { if (rqst && rqst->rq_iov) - cifs_small_buf_release(rqst->rq_iov[0].iov_base); /* request */ + cifs_buf_release(rqst->rq_iov[0].iov_base); /* request */ } static int @@ -5373,6 +5402,11 @@ build_qfs_info_req(struct kvec *iov, struct cifs_tcon *tcon, return 0; } +static inline void free_qfs_info_req(struct kvec *iov) +{ + cifs_buf_release(iov->iov_base); +} + int SMB311_posix_qfs_info(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, struct kstatfs *fsdata) @@ -5404,7 +5438,7 @@ SMB311_posix_qfs_info(const unsigned int xid, struct cifs_tcon *tcon, rc = cifs_send_recv(xid, ses, server, &rqst, &resp_buftype, flags, &rsp_iov); - cifs_small_buf_release(iov.iov_base); + free_qfs_info_req(&iov); if (rc) { cifs_stats_fail_inc(tcon, SMB2_QUERY_INFO_HE); goto posix_qfsinf_exit; @@ -5455,7 +5489,7 @@ SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon, rc = cifs_send_recv(xid, ses, server, &rqst, &resp_buftype, flags, &rsp_iov); - cifs_small_buf_release(iov.iov_base); + free_qfs_info_req(&iov); if (rc) { cifs_stats_fail_inc(tcon, SMB2_QUERY_INFO_HE); goto qfsinf_exit; @@ -5522,7 +5556,7 @@ SMB2_QFS_attr(const unsigned int xid, struct cifs_tcon *tcon, rc = cifs_send_recv(xid, ses, server, &rqst, &resp_buftype, flags, &rsp_iov); - cifs_small_buf_release(iov.iov_base); + free_qfs_info_req(&iov); if (rc) { cifs_stats_fail_inc(tcon, SMB2_QUERY_INFO_HE); goto qfsattr_exit; diff --git a/fs/smb/client/smb2proto.h b/fs/smb/client/smb2proto.h index 46eff9ec302aa..0e371f7e2854b 100644 --- a/fs/smb/client/smb2proto.h +++ b/fs/smb/client/smb2proto.h @@ -251,11 +251,13 @@ extern int smb3_validate_negotiate(const unsigned int, struct cifs_tcon *); extern enum securityEnum smb2_select_sectype(struct TCP_Server_Info *, enum securityEnum); -extern void smb2_parse_contexts(struct TCP_Server_Info *server, - struct smb2_create_rsp *rsp, - unsigned int *epoch, char *lease_key, - __u8 *oplock, struct smb2_file_all_info *buf, - struct create_posix_rsp *posix); +int smb2_parse_contexts(struct TCP_Server_Info *server, + struct kvec *rsp_iov, + unsigned int *epoch, + char *lease_key, __u8 *oplock, + struct smb2_file_all_info *buf, + struct create_posix_rsp *posix); + extern int smb3_encryption_required(const struct cifs_tcon *tcon); extern int smb2_validate_iov(unsigned int offset, unsigned int buffer_length, struct kvec *iov, unsigned int min_buf_size); diff --git a/fs/smb/client/smb2transport.c b/fs/smb/client/smb2transport.c index 23c50ed7d4b59..a136fc4cc2b5f 100644 --- a/fs/smb/client/smb2transport.c +++ b/fs/smb/client/smb2transport.c @@ -452,6 +452,8 @@ generate_smb3signingkey(struct cifs_ses *ses, ptriplet->encryption.context, ses->smb3encryptionkey, SMB3_ENC_DEC_KEY_SIZE); + if (rc) + return rc; rc = generate_key(ses, ptriplet->decryption.label, ptriplet->decryption.context, ses->smb3decryptionkey, @@ -460,9 +462,6 @@ generate_smb3signingkey(struct cifs_ses *ses, return rc; } - if (rc) - return rc; - #ifdef CONFIG_CIFS_DEBUG_DUMP_KEYS cifs_dbg(VFS, "%s: dumping generated AES session keys\n", __func__); /* diff --git a/fs/smb/client/transport.c b/fs/smb/client/transport.c index 14710afdc2a36..d553b7a54621b 100644 --- a/fs/smb/client/transport.c +++ b/fs/smb/client/transport.c @@ -76,7 +76,7 @@ alloc_mid(const struct smb_hdr *smb_buffer, struct TCP_Server_Info *server) return temp; } -static void __release_mid(struct kref *refcount) +void __release_mid(struct kref *refcount) { struct mid_q_entry *midEntry = container_of(refcount, struct mid_q_entry, refcount); @@ -156,15 +156,6 @@ static void __release_mid(struct kref *refcount) mempool_free(midEntry, cifs_mid_poolp); } -void release_mid(struct mid_q_entry *mid) -{ - struct TCP_Server_Info *server = mid->server; - - spin_lock(&server->mid_lock); - kref_put(&mid->refcount, __release_mid); - spin_unlock(&server->mid_lock); -} - void delete_mid(struct mid_q_entry *mid) { diff --git a/fs/smb/client/xattr.c b/fs/smb/client/xattr.c index ca78b49cda141..2c59ee4e2c0f0 100644 --- a/fs/smb/client/xattr.c +++ b/fs/smb/client/xattr.c @@ -159,10 +159,13 @@ static int cifs_xattr_set(const struct xattr_handler *handler, if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR) goto out; - if (pTcon->ses->server->ops->set_EA) + if (pTcon->ses->server->ops->set_EA) { rc = pTcon->ses->server->ops->set_EA(xid, pTcon, full_path, name, value, (__u16)size, cifs_sb->local_nls, cifs_sb); + if (rc == 0) + inode_set_ctime_current(inode); + } break; case XATTR_CIFS_ACL: diff --git a/fs/smb/common/smb2pdu.h b/fs/smb/common/smb2pdu.h index 319fb9ffc6a03..d58550c1c9378 100644 --- a/fs/smb/common/smb2pdu.h +++ b/fs/smb/common/smb2pdu.h @@ -1120,7 +1120,7 @@ struct smb2_change_notify_rsp { #define SMB2_CREATE_SD_BUFFER "SecD" /* security descriptor */ #define SMB2_CREATE_DURABLE_HANDLE_REQUEST "DHnQ" #define SMB2_CREATE_DURABLE_HANDLE_RECONNECT "DHnC" -#define SMB2_CREATE_ALLOCATION_SIZE "AISi" +#define SMB2_CREATE_ALLOCATION_SIZE "AlSi" #define SMB2_CREATE_QUERY_MAXIMAL_ACCESS_REQUEST "MxAc" #define SMB2_CREATE_TIMEWARP_REQUEST "TWrp" #define SMB2_CREATE_QUERY_ON_DISK_ID "QFid" @@ -1228,6 +1228,7 @@ struct create_mxac_rsp { #define SMB2_LEASE_WRITE_CACHING_LE cpu_to_le32(0x04) #define SMB2_LEASE_FLAG_BREAK_IN_PROGRESS_LE cpu_to_le32(0x02) +#define SMB2_LEASE_FLAG_PARENT_LEASE_KEY_SET_LE cpu_to_le32(0x04) #define SMB2_LEASE_KEY_SIZE 16 diff --git a/fs/smb/server/connection.c b/fs/smb/server/connection.c index 4b38c3a285f60..b6fa1e285c401 100644 --- a/fs/smb/server/connection.c +++ b/fs/smb/server/connection.c @@ -167,23 +167,7 @@ void ksmbd_all_conn_set_status(u64 sess_id, u32 status) void ksmbd_conn_wait_idle(struct ksmbd_conn *conn, u64 sess_id) { - struct ksmbd_conn *bind_conn; - wait_event(conn->req_running_q, atomic_read(&conn->req_running) < 2); - - down_read(&conn_list_lock); - list_for_each_entry(bind_conn, &conn_list, conns_list) { - if (bind_conn == conn) - continue; - - if ((bind_conn->binding || xa_load(&bind_conn->sessions, sess_id)) && - !ksmbd_conn_releasing(bind_conn) && - atomic_read(&bind_conn->req_running)) { - wait_event(bind_conn->req_running_q, - atomic_read(&bind_conn->req_running) == 0); - } - } - up_read(&conn_list_lock); } int ksmbd_conn_write(struct ksmbd_work *work) diff --git a/fs/smb/server/ksmbd_work.c b/fs/smb/server/ksmbd_work.c index 51def3ca74c01..d7c676c151e20 100644 --- a/fs/smb/server/ksmbd_work.c +++ b/fs/smb/server/ksmbd_work.c @@ -56,6 +56,9 @@ void ksmbd_free_work_struct(struct ksmbd_work *work) kfree(work->tr_buf); kvfree(work->request_buf); kfree(work->iov); + if (!list_empty(&work->interim_entry)) + list_del(&work->interim_entry); + if (work->async_id) ksmbd_release_id(&work->conn->async_ida, work->async_id); kmem_cache_free(work_cache, work); @@ -95,32 +98,42 @@ bool ksmbd_queue_work(struct ksmbd_work *work) return queue_work(ksmbd_wq, &work->work); } -static int ksmbd_realloc_iov_pin(struct ksmbd_work *work, void *ib, - unsigned int ib_len) +static inline void __ksmbd_iov_pin(struct ksmbd_work *work, void *ib, + unsigned int ib_len) +{ + work->iov[++work->iov_idx].iov_base = ib; + work->iov[work->iov_idx].iov_len = ib_len; + work->iov_cnt++; +} + +static int __ksmbd_iov_pin_rsp(struct ksmbd_work *work, void *ib, int len, + void *aux_buf, unsigned int aux_size) { + struct aux_read *ar = NULL; + int need_iov_cnt = 1; + + if (aux_size) { + need_iov_cnt++; + ar = kmalloc(sizeof(struct aux_read), GFP_KERNEL); + if (!ar) + return -ENOMEM; + } - if (work->iov_alloc_cnt <= work->iov_cnt) { + if (work->iov_alloc_cnt < work->iov_cnt + need_iov_cnt) { struct kvec *new; work->iov_alloc_cnt += 4; new = krealloc(work->iov, sizeof(struct kvec) * work->iov_alloc_cnt, GFP_KERNEL | __GFP_ZERO); - if (!new) + if (!new) { + kfree(ar); + work->iov_alloc_cnt -= 4; return -ENOMEM; + } work->iov = new; } - work->iov[++work->iov_idx].iov_base = ib; - work->iov[work->iov_idx].iov_len = ib_len; - work->iov_cnt++; - - return 0; -} - -static int __ksmbd_iov_pin_rsp(struct ksmbd_work *work, void *ib, int len, - void *aux_buf, unsigned int aux_size) -{ /* Plus rfc_length size on first iov */ if (!work->iov_idx) { work->iov[work->iov_idx].iov_base = work->response_buf; @@ -129,19 +142,13 @@ static int __ksmbd_iov_pin_rsp(struct ksmbd_work *work, void *ib, int len, work->iov_cnt++; } - ksmbd_realloc_iov_pin(work, ib, len); + __ksmbd_iov_pin(work, ib, len); inc_rfc1001_len(work->iov[0].iov_base, len); if (aux_size) { - struct aux_read *ar; - - ksmbd_realloc_iov_pin(work, aux_buf, aux_size); + __ksmbd_iov_pin(work, aux_buf, aux_size); inc_rfc1001_len(work->iov[0].iov_base, aux_size); - ar = kmalloc(sizeof(struct aux_read), GFP_KERNEL); - if (!ar) - return -ENOMEM; - ar->buf = aux_buf; list_add(&ar->entry, &work->aux_read_list); } diff --git a/fs/smb/server/mgmt/user_config.h b/fs/smb/server/mgmt/user_config.h index 6a44109617f14..e068a19fd9049 100644 --- a/fs/smb/server/mgmt/user_config.h +++ b/fs/smb/server/mgmt/user_config.h @@ -18,7 +18,6 @@ struct ksmbd_user { size_t passkey_sz; char *passkey; - unsigned int failed_login_count; }; static inline bool user_guest(struct ksmbd_user *user) diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index 9bc0103720f57..562b180459a1a 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -102,9 +102,10 @@ static int alloc_lease(struct oplock_info *opinfo, struct lease_ctx_info *lctx) lease->new_state = 0; lease->flags = lctx->flags; lease->duration = lctx->duration; + lease->is_dir = lctx->is_dir; memcpy(lease->parent_lease_key, lctx->parent_lease_key, SMB2_LEASE_KEY_SIZE); lease->version = lctx->version; - lease->epoch = 0; + lease->epoch = le16_to_cpu(lctx->epoch); INIT_LIST_HEAD(&opinfo->lease_entry); opinfo->o_lease = lease; @@ -395,8 +396,8 @@ void close_id_del_oplock(struct ksmbd_file *fp) { struct oplock_info *opinfo; - if (S_ISDIR(file_inode(fp->filp)->i_mode)) - return; + if (fp->reserve_lease_break) + smb_lazy_parent_lease_break_close(fp); opinfo = opinfo_get(fp); if (!opinfo) @@ -543,12 +544,13 @@ static struct oplock_info *same_client_has_lease(struct ksmbd_inode *ci, /* upgrading lease */ if ((atomic_read(&ci->op_count) + atomic_read(&ci->sop_count)) == 1) { - if (lease->state == - (lctx->req_state & lease->state)) { + if (lease->state != SMB2_LEASE_NONE_LE && + lease->state == (lctx->req_state & lease->state)) { lease->state |= lctx->req_state; if (lctx->req_state & SMB2_LEASE_WRITE_CACHING_LE) lease_read_to_write(opinfo); + } } else if ((atomic_read(&ci->op_count) + atomic_read(&ci->sop_count)) > 1) { @@ -833,7 +835,8 @@ static int smb2_lease_break_noti(struct oplock_info *opinfo) interim_entry); setup_async_work(in_work, NULL, NULL); smb2_send_interim_resp(in_work, STATUS_PENDING); - list_del(&in_work->interim_entry); + list_del_init(&in_work->interim_entry); + release_async_work(in_work); } INIT_WORK(&work->work, __smb2_lease_break_noti); ksmbd_queue_work(work); @@ -899,7 +902,8 @@ static int oplock_break(struct oplock_info *brk_opinfo, int req_op_level) lease->new_state = SMB2_LEASE_READ_CACHING_LE; } else { - if (lease->state & SMB2_LEASE_HANDLE_CACHING_LE) + if (lease->state & SMB2_LEASE_HANDLE_CACHING_LE && + !lease->is_dir) lease->new_state = SMB2_LEASE_READ_CACHING_LE; else @@ -1031,6 +1035,7 @@ static void copy_lease(struct oplock_info *op1, struct oplock_info *op2) SMB2_LEASE_KEY_SIZE); lease2->duration = lease1->duration; lease2->flags = lease1->flags; + lease2->epoch = lease1->epoch++; } static int add_lease_global_list(struct oplock_info *opinfo) @@ -1080,6 +1085,89 @@ static void set_oplock_level(struct oplock_info *opinfo, int level, } } +void smb_send_parent_lease_break_noti(struct ksmbd_file *fp, + struct lease_ctx_info *lctx) +{ + struct oplock_info *opinfo; + struct ksmbd_inode *p_ci = NULL; + + if (lctx->version != 2) + return; + + p_ci = ksmbd_inode_lookup_lock(fp->filp->f_path.dentry->d_parent); + if (!p_ci) + return; + + read_lock(&p_ci->m_lock); + list_for_each_entry(opinfo, &p_ci->m_op_list, op_entry) { + if (!opinfo->is_lease) + continue; + + if (opinfo->o_lease->state != SMB2_OPLOCK_LEVEL_NONE && + (!(lctx->flags & SMB2_LEASE_FLAG_PARENT_LEASE_KEY_SET_LE) || + !compare_guid_key(opinfo, fp->conn->ClientGUID, + lctx->parent_lease_key))) { + if (!atomic_inc_not_zero(&opinfo->refcount)) + continue; + + atomic_inc(&opinfo->conn->r_count); + if (ksmbd_conn_releasing(opinfo->conn)) { + atomic_dec(&opinfo->conn->r_count); + continue; + } + + read_unlock(&p_ci->m_lock); + oplock_break(opinfo, SMB2_OPLOCK_LEVEL_NONE); + opinfo_conn_put(opinfo); + read_lock(&p_ci->m_lock); + } + } + read_unlock(&p_ci->m_lock); + + ksmbd_inode_put(p_ci); +} + +void smb_lazy_parent_lease_break_close(struct ksmbd_file *fp) +{ + struct oplock_info *opinfo; + struct ksmbd_inode *p_ci = NULL; + + rcu_read_lock(); + opinfo = rcu_dereference(fp->f_opinfo); + rcu_read_unlock(); + + if (!opinfo->is_lease || opinfo->o_lease->version != 2) + return; + + p_ci = ksmbd_inode_lookup_lock(fp->filp->f_path.dentry->d_parent); + if (!p_ci) + return; + + read_lock(&p_ci->m_lock); + list_for_each_entry(opinfo, &p_ci->m_op_list, op_entry) { + if (!opinfo->is_lease) + continue; + + if (opinfo->o_lease->state != SMB2_OPLOCK_LEVEL_NONE) { + if (!atomic_inc_not_zero(&opinfo->refcount)) + continue; + + atomic_inc(&opinfo->conn->r_count); + if (ksmbd_conn_releasing(opinfo->conn)) { + atomic_dec(&opinfo->conn->r_count); + continue; + } + read_unlock(&p_ci->m_lock); + oplock_break(opinfo, SMB2_OPLOCK_LEVEL_NONE); + opinfo_conn_put(opinfo); + read_lock(&p_ci->m_lock); + } + } + read_unlock(&p_ci->m_lock); + + ksmbd_inode_put(p_ci); +} + /** * smb_grant_oplock() - handle oplock/lease request on file open * @work: smb work @@ -1103,10 +1191,6 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid, bool prev_op_has_lease; __le32 prev_op_state = 0; - /* not support directory lease */ - if (S_ISDIR(file_inode(fp->filp)->i_mode)) - return 0; - opinfo = alloc_opinfo(work, pid, tid); if (!opinfo) return -ENOMEM; @@ -1363,6 +1447,7 @@ void create_lease_buf(u8 *rbuf, struct lease *lease) memcpy(buf->lcontext.LeaseKey, lease->lease_key, SMB2_LEASE_KEY_SIZE); buf->lcontext.LeaseFlags = lease->flags; + buf->lcontext.Epoch = cpu_to_le16(++lease->epoch); buf->lcontext.LeaseState = lease->state; memcpy(buf->lcontext.ParentLeaseKey, lease->parent_lease_key, SMB2_LEASE_KEY_SIZE); @@ -1399,10 +1484,11 @@ void create_lease_buf(u8 *rbuf, struct lease *lease) /** * parse_lease_state() - parse lease context containted in file open request * @open_req: buffer containing smb2 file open(create) request + * @is_dir: whether leasing file is directory * * Return: oplock state, -ENOENT if create lease context not found */ -struct lease_ctx_info *parse_lease_state(void *open_req) +struct lease_ctx_info *parse_lease_state(void *open_req, bool is_dir) { struct create_context *cc; struct smb2_create_req *req = (struct smb2_create_req *)open_req; @@ -1420,8 +1506,14 @@ struct lease_ctx_info *parse_lease_state(void *open_req) struct create_lease_v2 *lc = (struct create_lease_v2 *)cc; memcpy(lreq->lease_key, lc->lcontext.LeaseKey, SMB2_LEASE_KEY_SIZE); - lreq->req_state = lc->lcontext.LeaseState; + if (is_dir) { + lreq->req_state = lc->lcontext.LeaseState & + ~SMB2_LEASE_WRITE_CACHING_LE; + lreq->is_dir = true; + } else + lreq->req_state = lc->lcontext.LeaseState; lreq->flags = lc->lcontext.LeaseFlags; + lreq->epoch = lc->lcontext.Epoch; lreq->duration = lc->lcontext.LeaseDuration; memcpy(lreq->parent_lease_key, lc->lcontext.ParentLeaseKey, SMB2_LEASE_KEY_SIZE); diff --git a/fs/smb/server/oplock.h b/fs/smb/server/oplock.h index 4b0fe6da76940..5b93ea9196c01 100644 --- a/fs/smb/server/oplock.h +++ b/fs/smb/server/oplock.h @@ -34,7 +34,9 @@ struct lease_ctx_info { __le32 flags; __le64 duration; __u8 parent_lease_key[SMB2_LEASE_KEY_SIZE]; + __le16 epoch; int version; + bool is_dir; }; struct lease_table { @@ -53,6 +55,7 @@ struct lease { __u8 parent_lease_key[SMB2_LEASE_KEY_SIZE]; int version; unsigned short epoch; + bool is_dir; struct lease_table *l_lb; }; @@ -108,7 +111,7 @@ void opinfo_put(struct oplock_info *opinfo); /* Lease related functions */ void create_lease_buf(u8 *rbuf, struct lease *lease); -struct lease_ctx_info *parse_lease_state(void *open_req); +struct lease_ctx_info *parse_lease_state(void *open_req, bool is_dir); __u8 smb2_map_lease_to_oplock(__le32 lease_state); int lease_read_to_write(struct oplock_info *opinfo); @@ -124,4 +127,7 @@ struct oplock_info *lookup_lease_in_table(struct ksmbd_conn *conn, int find_same_lease_key(struct ksmbd_session *sess, struct ksmbd_inode *ci, struct lease_ctx_info *lctx); void destroy_lease_table(struct ksmbd_conn *conn); +void smb_send_parent_lease_break_noti(struct ksmbd_file *fp, + struct lease_ctx_info *lctx); +void smb_lazy_parent_lease_break_close(struct ksmbd_file *fp); #endif /* __KSMBD_OPLOCK_H */ diff --git a/fs/smb/server/smb2misc.c b/fs/smb/server/smb2misc.c index 23bd3d1209dfa..03dded29a9804 100644 --- a/fs/smb/server/smb2misc.c +++ b/fs/smb/server/smb2misc.c @@ -106,16 +106,25 @@ static int smb2_get_data_area_len(unsigned int *off, unsigned int *len, break; case SMB2_CREATE: { + unsigned short int name_off = + le16_to_cpu(((struct smb2_create_req *)hdr)->NameOffset); + unsigned short int name_len = + le16_to_cpu(((struct smb2_create_req *)hdr)->NameLength); + if (((struct smb2_create_req *)hdr)->CreateContextsLength) { *off = le32_to_cpu(((struct smb2_create_req *) hdr)->CreateContextsOffset); *len = le32_to_cpu(((struct smb2_create_req *) hdr)->CreateContextsLength); - break; + if (!name_len) + break; + + if (name_off + name_len < (u64)*off + *len) + break; } - *off = le16_to_cpu(((struct smb2_create_req *)hdr)->NameOffset); - *len = le16_to_cpu(((struct smb2_create_req *)hdr)->NameLength); + *off = name_off; + *len = name_len; break; } case SMB2_QUERY_INFO: diff --git a/fs/smb/server/smb2ops.c b/fs/smb/server/smb2ops.c index aed7704a06728..27a9dce3e03ab 100644 --- a/fs/smb/server/smb2ops.c +++ b/fs/smb/server/smb2ops.c @@ -221,7 +221,8 @@ void init_smb3_0_server(struct ksmbd_conn *conn) conn->signing_algorithm = SIGNING_ALG_AES_CMAC_LE; if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_LEASES) - conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING; + conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING | + SMB2_GLOBAL_CAP_DIRECTORY_LEASING; if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION && conn->cli_cap & SMB2_GLOBAL_CAP_ENCRYPTION) @@ -245,7 +246,8 @@ void init_smb3_02_server(struct ksmbd_conn *conn) conn->signing_algorithm = SIGNING_ALG_AES_CMAC_LE; if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_LEASES) - conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING; + conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING | + SMB2_GLOBAL_CAP_DIRECTORY_LEASING; if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION || (!(server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION_OFF) && @@ -270,7 +272,8 @@ int init_smb3_11_server(struct ksmbd_conn *conn) conn->signing_algorithm = SIGNING_ALG_AES_CMAC_LE; if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_LEASES) - conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING; + conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING | + SMB2_GLOBAL_CAP_DIRECTORY_LEASING; if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION || (!(server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION_OFF) && diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 93262ca3f58a7..fbd708bb4a5b2 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -657,13 +657,9 @@ smb2_get_name(const char *src, const int maxlen, struct nls_table *local_nls) int setup_async_work(struct ksmbd_work *work, void (*fn)(void **), void **arg) { - struct smb2_hdr *rsp_hdr; struct ksmbd_conn *conn = work->conn; int id; - rsp_hdr = ksmbd_resp_buf_next(work); - rsp_hdr->Flags |= SMB2_FLAGS_ASYNC_COMMAND; - id = ksmbd_acquire_async_msg_id(&conn->async_ida); if (id < 0) { pr_err("Failed to alloc async message id\n"); @@ -671,7 +667,6 @@ int setup_async_work(struct ksmbd_work *work, void (*fn)(void **), void **arg) } work->asynchronous = true; work->async_id = id; - rsp_hdr->Id.AsyncId = cpu_to_le64(id); ksmbd_debug(SMB, "Send interim Response to inform async request id : %d\n", @@ -723,6 +718,8 @@ void smb2_send_interim_resp(struct ksmbd_work *work, __le32 status) __SMB2_HEADER_STRUCTURE_SIZE); rsp_hdr = smb2_get_msg(in_work->response_buf); + rsp_hdr->Flags |= SMB2_FLAGS_ASYNC_COMMAND; + rsp_hdr->Id.AsyncId = cpu_to_le64(work->async_id); smb2_set_err_rsp(in_work); rsp_hdr->Status = status; @@ -2380,7 +2377,8 @@ static int smb2_set_ea(struct smb2_ea_info *eabuf, unsigned int buf_len, rc = 0; } else { rc = ksmbd_vfs_setxattr(idmap, path, attr_name, value, - le16_to_cpu(eabuf->EaValueLength), 0); + le16_to_cpu(eabuf->EaValueLength), + 0, true); if (rc < 0) { ksmbd_debug(SMB, "ksmbd_vfs_setxattr is failed(%d)\n", @@ -2443,7 +2441,7 @@ static noinline int smb2_set_stream_name_xattr(const struct path *path, return -EBADF; } - rc = ksmbd_vfs_setxattr(idmap, path, xattr_stream_name, NULL, 0, 0); + rc = ksmbd_vfs_setxattr(idmap, path, xattr_stream_name, NULL, 0, 0, false); if (rc < 0) pr_err("Failed to store XATTR stream name :%d\n", rc); return 0; @@ -2518,7 +2516,7 @@ static void smb2_new_xattrs(struct ksmbd_tree_connect *tcon, const struct path * da.flags = XATTR_DOSINFO_ATTRIB | XATTR_DOSINFO_CREATE_TIME | XATTR_DOSINFO_ITIME; - rc = ksmbd_vfs_set_dos_attrib_xattr(mnt_idmap(path->mnt), path, &da); + rc = ksmbd_vfs_set_dos_attrib_xattr(mnt_idmap(path->mnt), path, &da, false); if (rc) ksmbd_debug(SMB, "failed to store file attribute into xattr\n"); } @@ -2608,7 +2606,7 @@ static int smb2_create_sd_buffer(struct ksmbd_work *work, sizeof(struct create_sd_buf_req)) return -EINVAL; return set_info_sec(work->conn, work->tcon, path, &sd_buf->ntsd, - le32_to_cpu(sd_buf->ccontext.DataLength), true); + le32_to_cpu(sd_buf->ccontext.DataLength), true, false); } static void ksmbd_acls_fattr(struct smb_fattr *fattr, @@ -2690,7 +2688,7 @@ int smb2_open(struct ksmbd_work *work) *(char *)req->Buffer == '\\') { pr_err("not allow directory name included leading slash\n"); rc = -EINVAL; - goto err_out1; + goto err_out2; } name = smb2_get_name(req->Buffer, @@ -2701,7 +2699,7 @@ int smb2_open(struct ksmbd_work *work) if (rc != -ENOMEM) rc = -ENOENT; name = NULL; - goto err_out1; + goto err_out2; } ksmbd_debug(SMB, "converted name = %s\n", name); @@ -2709,48 +2707,44 @@ int smb2_open(struct ksmbd_work *work) if (!test_share_config_flag(work->tcon->share_conf, KSMBD_SHARE_FLAG_STREAMS)) { rc = -EBADF; - goto err_out1; + goto err_out2; } rc = parse_stream_name(name, &stream_name, &s_type); if (rc < 0) - goto err_out1; + goto err_out2; } rc = ksmbd_validate_filename(name); if (rc < 0) - goto err_out1; + goto err_out2; if (ksmbd_share_veto_filename(share, name)) { rc = -ENOENT; ksmbd_debug(SMB, "Reject open(), vetoed file: %s\n", name); - goto err_out1; + goto err_out2; } } else { name = kstrdup("", GFP_KERNEL); if (!name) { rc = -ENOMEM; - goto err_out1; + goto err_out2; } } - req_op_level = req->RequestedOplockLevel; - if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE) - lc = parse_lease_state(req); - if (le32_to_cpu(req->ImpersonationLevel) > le32_to_cpu(IL_DELEGATE)) { pr_err("Invalid impersonationlevel : 0x%x\n", le32_to_cpu(req->ImpersonationLevel)); rc = -EIO; rsp->hdr.Status = STATUS_BAD_IMPERSONATION_LEVEL; - goto err_out1; + goto err_out2; } if (req->CreateOptions && !(req->CreateOptions & CREATE_OPTIONS_MASK_LE)) { pr_err("Invalid create options : 0x%x\n", le32_to_cpu(req->CreateOptions)); rc = -EINVAL; - goto err_out1; + goto err_out2; } else { if (req->CreateOptions & FILE_SEQUENTIAL_ONLY_LE && req->CreateOptions & FILE_RANDOM_ACCESS_LE) @@ -2760,13 +2754,13 @@ int smb2_open(struct ksmbd_work *work) (FILE_OPEN_BY_FILE_ID_LE | CREATE_TREE_CONNECTION | FILE_RESERVE_OPFILTER_LE)) { rc = -EOPNOTSUPP; - goto err_out1; + goto err_out2; } if (req->CreateOptions & FILE_DIRECTORY_FILE_LE) { if (req->CreateOptions & FILE_NON_DIRECTORY_FILE_LE) { rc = -EINVAL; - goto err_out1; + goto err_out2; } else if (req->CreateOptions & FILE_NO_COMPRESSION_LE) { req->CreateOptions = ~(FILE_NO_COMPRESSION_LE); } @@ -2778,21 +2772,21 @@ int smb2_open(struct ksmbd_work *work) pr_err("Invalid create disposition : 0x%x\n", le32_to_cpu(req->CreateDisposition)); rc = -EINVAL; - goto err_out1; + goto err_out2; } if (!(req->DesiredAccess & DESIRED_ACCESS_MASK)) { pr_err("Invalid desired access : 0x%x\n", le32_to_cpu(req->DesiredAccess)); rc = -EACCES; - goto err_out1; + goto err_out2; } if (req->FileAttributes && !(req->FileAttributes & FILE_ATTRIBUTE_MASK_LE)) { pr_err("Invalid file attribute : 0x%x\n", le32_to_cpu(req->FileAttributes)); rc = -EINVAL; - goto err_out1; + goto err_out2; } if (req->CreateContextsOffset) { @@ -2800,19 +2794,19 @@ int smb2_open(struct ksmbd_work *work) context = smb2_find_context_vals(req, SMB2_CREATE_EA_BUFFER, 4); if (IS_ERR(context)) { rc = PTR_ERR(context); - goto err_out1; + goto err_out2; } else if (context) { ea_buf = (struct create_ea_buf_req *)context; if (le16_to_cpu(context->DataOffset) + le32_to_cpu(context->DataLength) < sizeof(struct create_ea_buf_req)) { rc = -EINVAL; - goto err_out1; + goto err_out2; } if (req->CreateOptions & FILE_NO_EA_KNOWLEDGE_LE) { rsp->hdr.Status = STATUS_ACCESS_DENIED; rc = -EACCES; - goto err_out1; + goto err_out2; } } @@ -2820,7 +2814,7 @@ int smb2_open(struct ksmbd_work *work) SMB2_CREATE_QUERY_MAXIMAL_ACCESS_REQUEST, 4); if (IS_ERR(context)) { rc = PTR_ERR(context); - goto err_out1; + goto err_out2; } else if (context) { ksmbd_debug(SMB, "get query maximal access context\n"); @@ -2831,11 +2825,11 @@ int smb2_open(struct ksmbd_work *work) SMB2_CREATE_TIMEWARP_REQUEST, 4); if (IS_ERR(context)) { rc = PTR_ERR(context); - goto err_out1; + goto err_out2; } else if (context) { ksmbd_debug(SMB, "get timewarp context\n"); rc = -EBADF; - goto err_out1; + goto err_out2; } if (tcon->posix_extensions) { @@ -2843,7 +2837,7 @@ int smb2_open(struct ksmbd_work *work) SMB2_CREATE_TAG_POSIX, 16); if (IS_ERR(context)) { rc = PTR_ERR(context); - goto err_out1; + goto err_out2; } else if (context) { struct create_posix *posix = (struct create_posix *)context; @@ -2851,7 +2845,7 @@ int smb2_open(struct ksmbd_work *work) le32_to_cpu(context->DataLength) < sizeof(struct create_posix) - 4) { rc = -EINVAL; - goto err_out1; + goto err_out2; } ksmbd_debug(SMB, "get posix context\n"); @@ -2863,7 +2857,7 @@ int smb2_open(struct ksmbd_work *work) if (ksmbd_override_fsids(work)) { rc = -ENOMEM; - goto err_out1; + goto err_out2; } rc = ksmbd_vfs_kern_path_locked(work, name, LOOKUP_NO_SYMLINKS, @@ -3038,7 +3032,7 @@ int smb2_open(struct ksmbd_work *work) } } - rc = ksmbd_query_inode_status(d_inode(path.dentry->d_parent)); + rc = ksmbd_query_inode_status(path.dentry->d_parent); if (rc == KSMBD_INODE_STATUS_PENDING_DELETE) { rc = -EBUSY; goto err_out; @@ -3152,7 +3146,8 @@ int smb2_open(struct ksmbd_work *work) idmap, &path, pntsd, - pntsd_size); + pntsd_size, + false); kfree(pntsd); if (rc) pr_err("failed to store ntacl in xattr : %d\n", @@ -3175,11 +3170,6 @@ int smb2_open(struct ksmbd_work *work) fp->attrib_only = !(req->DesiredAccess & ~(FILE_READ_ATTRIBUTES_LE | FILE_WRITE_ATTRIBUTES_LE | FILE_SYNCHRONIZE_LE)); - if (!S_ISDIR(file_inode(filp)->i_mode) && open_flags & O_TRUNC && - !fp->attrib_only && !stream_name) { - smb_break_all_oplock(work, fp); - need_truncate = 1; - } /* fp should be searchable through ksmbd_inode.m_fp_list * after daccess, saccess, attrib_only, and stream are @@ -3195,23 +3185,60 @@ int smb2_open(struct ksmbd_work *work) goto err_out; } + rc = ksmbd_vfs_getattr(&path, &stat); + if (rc) + goto err_out; + + if (stat.result_mask & STATX_BTIME) + fp->create_time = ksmbd_UnixTimeToNT(stat.btime); + else + fp->create_time = ksmbd_UnixTimeToNT(stat.ctime); + if (req->FileAttributes || fp->f_ci->m_fattr == 0) + fp->f_ci->m_fattr = + cpu_to_le32(smb2_get_dos_mode(&stat, le32_to_cpu(req->FileAttributes))); + + if (!created) + smb2_update_xattrs(tcon, &path, fp); + else + smb2_new_xattrs(tcon, &path, fp); + + if (file_present || created) + ksmbd_vfs_kern_path_unlock(&parent_path, &path); + + if (!S_ISDIR(file_inode(filp)->i_mode) && open_flags & O_TRUNC && + !fp->attrib_only && !stream_name) { + smb_break_all_oplock(work, fp); + need_truncate = 1; + } + + req_op_level = req->RequestedOplockLevel; + if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE) + lc = parse_lease_state(req, S_ISDIR(file_inode(filp)->i_mode)); + share_ret = ksmbd_smb_check_shared_mode(fp->filp, fp); if (!test_share_config_flag(work->tcon->share_conf, KSMBD_SHARE_FLAG_OPLOCKS) || (req_op_level == SMB2_OPLOCK_LEVEL_LEASE && !(conn->vals->capabilities & SMB2_GLOBAL_CAP_LEASING))) { if (share_ret < 0 && !S_ISDIR(file_inode(fp->filp)->i_mode)) { rc = share_ret; - goto err_out; + goto err_out1; } } else { if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE) { + /* + * Compare parent lease using parent key. If there is no + * a lease that has same parent key, Send lease break + * notification. + */ + smb_send_parent_lease_break_noti(fp, lc); + req_op_level = smb2_map_lease_to_oplock(lc->req_state); ksmbd_debug(SMB, "lease req for(%s) req oplock state 0x%x, lease state 0x%x\n", name, req_op_level, lc->req_state); rc = find_same_lease_key(sess, fp->f_ci, lc); if (rc) - goto err_out; + goto err_out1; } else if (open_flags == O_RDONLY && (req_op_level == SMB2_OPLOCK_LEVEL_BATCH || req_op_level == SMB2_OPLOCK_LEVEL_EXCLUSIVE)) @@ -3222,16 +3249,16 @@ int smb2_open(struct ksmbd_work *work) le32_to_cpu(req->hdr.Id.SyncId.TreeId), lc, share_ret); if (rc < 0) - goto err_out; + goto err_out1; } if (req->CreateOptions & FILE_DELETE_ON_CLOSE_LE) ksmbd_fd_set_delete_on_close(fp, file_info); if (need_truncate) { - rc = smb2_create_truncate(&path); + rc = smb2_create_truncate(&fp->filp->f_path); if (rc) - goto err_out; + goto err_out1; } if (req->CreateContextsOffset) { @@ -3241,7 +3268,7 @@ int smb2_open(struct ksmbd_work *work) SMB2_CREATE_ALLOCATION_SIZE, 4); if (IS_ERR(az_req)) { rc = PTR_ERR(az_req); - goto err_out; + goto err_out1; } else if (az_req) { loff_t alloc_size; int err; @@ -3250,7 +3277,7 @@ int smb2_open(struct ksmbd_work *work) le32_to_cpu(az_req->ccontext.DataLength) < sizeof(struct create_alloc_size_req)) { rc = -EINVAL; - goto err_out; + goto err_out1; } alloc_size = le64_to_cpu(az_req->AllocationSize); ksmbd_debug(SMB, @@ -3268,30 +3295,13 @@ int smb2_open(struct ksmbd_work *work) context = smb2_find_context_vals(req, SMB2_CREATE_QUERY_ON_DISK_ID, 4); if (IS_ERR(context)) { rc = PTR_ERR(context); - goto err_out; + goto err_out1; } else if (context) { ksmbd_debug(SMB, "get query on disk id context\n"); query_disk_id = 1; } } - rc = ksmbd_vfs_getattr(&path, &stat); - if (rc) - goto err_out; - - if (stat.result_mask & STATX_BTIME) - fp->create_time = ksmbd_UnixTimeToNT(stat.btime); - else - fp->create_time = ksmbd_UnixTimeToNT(stat.ctime); - if (req->FileAttributes || fp->f_ci->m_fattr == 0) - fp->f_ci->m_fattr = - cpu_to_le32(smb2_get_dos_mode(&stat, le32_to_cpu(req->FileAttributes))); - - if (!created) - smb2_update_xattrs(tcon, &path, fp); - else - smb2_new_xattrs(tcon, &path, fp); - memcpy(fp->client_guid, conn->ClientGUID, SMB2_CLIENT_GUID_SIZE); rsp->StructureSize = cpu_to_le16(89); @@ -3398,13 +3408,13 @@ int smb2_open(struct ksmbd_work *work) } err_out: - if (file_present || created) { - inode_unlock(d_inode(parent_path.dentry)); - path_put(&path); - path_put(&parent_path); - } - ksmbd_revert_fsids(work); + if (rc && (file_present || created)) + ksmbd_vfs_kern_path_unlock(&parent_path, &path); + err_out1: + ksmbd_revert_fsids(work); + +err_out2: if (!rc) { ksmbd_update_fstate(&work->sess->file_table, fp, FP_INITED); rc = ksmbd_iov_pin_rsp(work, (void *)rsp, iov_len); @@ -5537,7 +5547,7 @@ static int smb2_rename(struct ksmbd_work *work, rc = ksmbd_vfs_setxattr(file_mnt_idmap(fp->filp), &fp->filp->f_path, xattr_stream_name, - NULL, 0, 0); + NULL, 0, 0, true); if (rc < 0) { pr_err("failed to store stream name in xattr: %d\n", rc); @@ -5630,11 +5640,9 @@ static int smb2_create_link(struct ksmbd_work *work, if (rc) rc = -EINVAL; out: - if (file_present) { - inode_unlock(d_inode(parent_path.dentry)); - path_put(&path); - path_put(&parent_path); - } + if (file_present) + ksmbd_vfs_kern_path_unlock(&parent_path, &path); + if (!IS_ERR(link_name)) kfree(link_name); kfree(pathname); @@ -5701,7 +5709,8 @@ static int set_file_basic_info(struct ksmbd_file *fp, da.flags = XATTR_DOSINFO_ATTRIB | XATTR_DOSINFO_CREATE_TIME | XATTR_DOSINFO_ITIME; - rc = ksmbd_vfs_set_dos_attrib_xattr(idmap, &filp->f_path, &da); + rc = ksmbd_vfs_set_dos_attrib_xattr(idmap, &filp->f_path, &da, + true); if (rc) ksmbd_debug(SMB, "failed to restore file attribute in EA\n"); @@ -6013,7 +6022,7 @@ static int smb2_set_info_sec(struct ksmbd_file *fp, int addition_info, fp->saccess |= FILE_SHARE_DELETE_LE; return set_info_sec(fp->conn, fp->tcon, &fp->filp->f_path, pntsd, - buf_len, false); + buf_len, false, true); } /** @@ -7078,6 +7087,7 @@ int smb2_lock(struct ksmbd_work *work) smb2_remove_blocked_lock, argv); if (rc) { + kfree(argv); err = -ENOMEM; goto out; } @@ -7582,7 +7592,8 @@ static inline int fsctl_set_sparse(struct ksmbd_work *work, u64 id, da.attr = le32_to_cpu(fp->f_ci->m_fattr); ret = ksmbd_vfs_set_dos_attrib_xattr(idmap, - &fp->filp->f_path, &da); + &fp->filp->f_path, + &da, true); if (ret) fp->f_ci->m_fattr = old_fattr; } @@ -8208,6 +8219,11 @@ static void smb21_lease_break_ack(struct ksmbd_work *work) le32_to_cpu(req->LeaseState)); } + if (ret < 0) { + rsp->hdr.Status = err; + goto err_out; + } + lease_state = lease->state; opinfo->op_state = OPLOCK_STATE_NONE; wake_up_interruptible_all(&opinfo->oplock_q); @@ -8215,11 +8231,6 @@ static void smb21_lease_break_ack(struct ksmbd_work *work) wake_up_interruptible_all(&opinfo->oplock_brk); opinfo_put(opinfo); - if (ret < 0) { - rsp->hdr.Status = err; - goto err_out; - } - rsp->StructureSize = cpu_to_le16(36); rsp->Reserved = 0; rsp->Flags = 0; @@ -8231,7 +8242,6 @@ static void smb21_lease_break_ack(struct ksmbd_work *work) return; err_out: - opinfo->op_state = OPLOCK_STATE_NONE; wake_up_interruptible_all(&opinfo->oplock_q); atomic_dec(&opinfo->breaking_cnt); wake_up_interruptible_all(&opinfo->oplock_brk); diff --git a/fs/smb/server/smb_common.c b/fs/smb/server/smb_common.c index e6ba1e9b8589a..6691ae68af0c0 100644 --- a/fs/smb/server/smb_common.c +++ b/fs/smb/server/smb_common.c @@ -366,11 +366,22 @@ static int smb1_allocate_rsp_buf(struct ksmbd_work *work) return 0; } +/** + * set_smb1_rsp_status() - set error type in smb response header + * @work: smb work containing smb response header + * @err: error code to set in response + */ +static void set_smb1_rsp_status(struct ksmbd_work *work, __le32 err) +{ + work->send_no_response = 1; +} + static struct smb_version_ops smb1_server_ops = { .get_cmd_val = get_smb1_cmd_val, .init_rsp_hdr = init_smb1_rsp_hdr, .allocate_rsp_buf = smb1_allocate_rsp_buf, .check_user_session = smb1_check_user_session, + .set_rsp_status = set_smb1_rsp_status, }; static int smb1_negotiate(struct ksmbd_work *work) diff --git a/fs/smb/server/smbacl.c b/fs/smb/server/smbacl.c index 6c0305be895e5..1164365533f08 100644 --- a/fs/smb/server/smbacl.c +++ b/fs/smb/server/smbacl.c @@ -1107,6 +1107,7 @@ int smb_inherit_dacl(struct ksmbd_conn *conn, struct smb_acl *pdacl; struct smb_sid *powner_sid = NULL, *pgroup_sid = NULL; int powner_sid_size = 0, pgroup_sid_size = 0, pntsd_size; + int pntsd_alloc_size; if (parent_pntsd->osidoffset) { powner_sid = (struct smb_sid *)((char *)parent_pntsd + @@ -1119,9 +1120,10 @@ int smb_inherit_dacl(struct ksmbd_conn *conn, pgroup_sid_size = 1 + 1 + 6 + (pgroup_sid->num_subauth * 4); } - pntsd = kzalloc(sizeof(struct smb_ntsd) + powner_sid_size + - pgroup_sid_size + sizeof(struct smb_acl) + - nt_size, GFP_KERNEL); + pntsd_alloc_size = sizeof(struct smb_ntsd) + powner_sid_size + + pgroup_sid_size + sizeof(struct smb_acl) + nt_size; + + pntsd = kzalloc(pntsd_alloc_size, GFP_KERNEL); if (!pntsd) { rc = -ENOMEM; goto free_aces_base; @@ -1136,6 +1138,27 @@ int smb_inherit_dacl(struct ksmbd_conn *conn, pntsd->gsidoffset = parent_pntsd->gsidoffset; pntsd->dacloffset = parent_pntsd->dacloffset; + if ((u64)le32_to_cpu(pntsd->osidoffset) + powner_sid_size > + pntsd_alloc_size) { + rc = -EINVAL; + kfree(pntsd); + goto free_aces_base; + } + + if ((u64)le32_to_cpu(pntsd->gsidoffset) + pgroup_sid_size > + pntsd_alloc_size) { + rc = -EINVAL; + kfree(pntsd); + goto free_aces_base; + } + + if ((u64)le32_to_cpu(pntsd->dacloffset) + sizeof(struct smb_acl) + nt_size > + pntsd_alloc_size) { + rc = -EINVAL; + kfree(pntsd); + goto free_aces_base; + } + if (pntsd->osidoffset) { struct smb_sid *owner_sid = (struct smb_sid *)((char *)pntsd + le32_to_cpu(pntsd->osidoffset)); @@ -1162,7 +1185,7 @@ int smb_inherit_dacl(struct ksmbd_conn *conn, pntsd_size += sizeof(struct smb_acl) + nt_size; } - ksmbd_vfs_set_sd_xattr(conn, idmap, path, pntsd, pntsd_size); + ksmbd_vfs_set_sd_xattr(conn, idmap, path, pntsd, pntsd_size, false); kfree(pntsd); } @@ -1354,7 +1377,7 @@ int smb_check_perm_dacl(struct ksmbd_conn *conn, const struct path *path, int set_info_sec(struct ksmbd_conn *conn, struct ksmbd_tree_connect *tcon, const struct path *path, struct smb_ntsd *pntsd, int ntsd_len, - bool type_check) + bool type_check, bool get_write) { int rc; struct smb_fattr fattr = {{0}}; @@ -1414,7 +1437,8 @@ int set_info_sec(struct ksmbd_conn *conn, struct ksmbd_tree_connect *tcon, if (test_share_config_flag(tcon->share_conf, KSMBD_SHARE_FLAG_ACL_XATTR)) { /* Update WinACL in xattr */ ksmbd_vfs_remove_sd_xattrs(idmap, path); - ksmbd_vfs_set_sd_xattr(conn, idmap, path, pntsd, ntsd_len); + ksmbd_vfs_set_sd_xattr(conn, idmap, path, pntsd, ntsd_len, + get_write); } out: diff --git a/fs/smb/server/smbacl.h b/fs/smb/server/smbacl.h index 49a8c292bd2e8..2b52861707d8c 100644 --- a/fs/smb/server/smbacl.h +++ b/fs/smb/server/smbacl.h @@ -207,7 +207,7 @@ int smb_check_perm_dacl(struct ksmbd_conn *conn, const struct path *path, __le32 *pdaccess, int uid); int set_info_sec(struct ksmbd_conn *conn, struct ksmbd_tree_connect *tcon, const struct path *path, struct smb_ntsd *pntsd, int ntsd_len, - bool type_check); + bool type_check, bool get_write); void id_to_sid(unsigned int cid, uint sidtype, struct smb_sid *ssid); void ksmbd_init_domain(u32 *sub_auth); diff --git a/fs/smb/server/transport_rdma.c b/fs/smb/server/transport_rdma.c index 3b269e1f523a1..c5629a68c8b73 100644 --- a/fs/smb/server/transport_rdma.c +++ b/fs/smb/server/transport_rdma.c @@ -2140,8 +2140,7 @@ static int smb_direct_ib_client_add(struct ib_device *ib_dev) if (ib_dev->node_type != RDMA_NODE_IB_CA) smb_direct_port = SMB_DIRECT_PORT_IWARP; - if (!ib_dev->ops.get_netdev || - !rdma_frwr_is_supported(&ib_dev->attrs)) + if (!rdma_frwr_is_supported(&ib_dev->attrs)) return 0; smb_dev = kzalloc(sizeof(*smb_dev), GFP_KERNEL); @@ -2241,17 +2240,38 @@ bool ksmbd_rdma_capable_netdev(struct net_device *netdev) for (i = 0; i < smb_dev->ib_dev->phys_port_cnt; i++) { struct net_device *ndev; - ndev = smb_dev->ib_dev->ops.get_netdev(smb_dev->ib_dev, - i + 1); - if (!ndev) - continue; + if (smb_dev->ib_dev->ops.get_netdev) { + ndev = smb_dev->ib_dev->ops.get_netdev( + smb_dev->ib_dev, i + 1); + if (!ndev) + continue; - if (ndev == netdev) { + if (ndev == netdev) { + dev_put(ndev); + rdma_capable = true; + goto out; + } dev_put(ndev); - rdma_capable = true; - goto out; + /* if ib_dev does not implement ops.get_netdev + * check for matching infiniband GUID in hw_addr + */ + } else if (netdev->type == ARPHRD_INFINIBAND) { + struct netdev_hw_addr *ha; + union ib_gid gid; + u32 port_num; + int ret; + + netdev_hw_addr_list_for_each( + ha, &netdev->dev_addrs) { + memcpy(&gid, ha->addr + 4, sizeof(gid)); + ret = ib_find_gid(smb_dev->ib_dev, &gid, + &port_num, NULL); + if (!ret) { + rdma_capable = true; + goto out; + } + } } - dev_put(ndev); } } out: diff --git a/fs/smb/server/unicode.c b/fs/smb/server/unicode.c index 393dd4a7432b6..43ed29ee44ead 100644 --- a/fs/smb/server/unicode.c +++ b/fs/smb/server/unicode.c @@ -13,46 +13,10 @@ #include "unicode.h" #include "smb_common.h" -/* - * smb_utf16_bytes() - how long will a string be after conversion? - * @from: pointer to input string - * @maxbytes: don't go past this many bytes of input string - * @codepage: destination codepage - * - * Walk a utf16le string and return the number of bytes that the string will - * be after being converted to the given charset, not including any null - * termination required. Don't walk past maxbytes in the source buffer. - * - * Return: string length after conversion - */ -static int smb_utf16_bytes(const __le16 *from, int maxbytes, - const struct nls_table *codepage) -{ - int i; - int charlen, outlen = 0; - int maxwords = maxbytes / 2; - char tmp[NLS_MAX_CHARSET_SIZE]; - __u16 ftmp; - - for (i = 0; i < maxwords; i++) { - ftmp = get_unaligned_le16(&from[i]); - if (ftmp == 0) - break; - - charlen = codepage->uni2char(ftmp, tmp, NLS_MAX_CHARSET_SIZE); - if (charlen > 0) - outlen += charlen; - else - outlen++; - } - - return outlen; -} - /* * cifs_mapchar() - convert a host-endian char to proper char in codepage * @target: where converted character should be copied - * @src_char: 2 byte host-endian source character + * @from: host-endian source string * @cp: codepage to which character should be converted * @mapchar: should character be mapped according to mapchars mount option? * @@ -63,10 +27,13 @@ static int smb_utf16_bytes(const __le16 *from, int maxbytes, * Return: string length after conversion */ static int -cifs_mapchar(char *target, const __u16 src_char, const struct nls_table *cp, +cifs_mapchar(char *target, const __u16 *from, const struct nls_table *cp, bool mapchar) { int len = 1; + __u16 src_char; + + src_char = *from; if (!mapchar) goto cp_convert; @@ -104,12 +71,66 @@ cifs_mapchar(char *target, const __u16 src_char, const struct nls_table *cp, cp_convert: len = cp->uni2char(src_char, target, NLS_MAX_CHARSET_SIZE); - if (len <= 0) { - *target = '?'; - len = 1; - } + if (len <= 0) + goto surrogate_pair; goto out; + +surrogate_pair: + /* convert SURROGATE_PAIR and IVS */ + if (strcmp(cp->charset, "utf8")) + goto unknown; + len = utf16s_to_utf8s(from, 3, UTF16_LITTLE_ENDIAN, target, 6); + if (len <= 0) + goto unknown; + return len; + +unknown: + *target = '?'; + len = 1; + goto out; +} + +/* + * smb_utf16_bytes() - compute converted string length + * @from: pointer to input string + * @maxbytes: input string length + * @codepage: destination codepage + * + * Walk a utf16le string and return the number of bytes that the string will + * be after being converted to the given charset, not including any null + * termination required. Don't walk past maxbytes in the source buffer. + * + * Return: string length after conversion + */ +static int smb_utf16_bytes(const __le16 *from, int maxbytes, + const struct nls_table *codepage) +{ + int i, j; + int charlen, outlen = 0; + int maxwords = maxbytes / 2; + char tmp[NLS_MAX_CHARSET_SIZE]; + __u16 ftmp[3]; + + for (i = 0; i < maxwords; i++) { + ftmp[0] = get_unaligned_le16(&from[i]); + if (ftmp[0] == 0) + break; + for (j = 1; j <= 2; j++) { + if (i + j < maxwords) + ftmp[j] = get_unaligned_le16(&from[i + j]); + else + ftmp[j] = 0; + } + + charlen = cifs_mapchar(tmp, ftmp, codepage, 0); + if (charlen > 0) + outlen += charlen; + else + outlen++; + } + + return outlen; } /* @@ -139,12 +160,12 @@ cifs_mapchar(char *target, const __u16 src_char, const struct nls_table *cp, static int smb_from_utf16(char *to, const __le16 *from, int tolen, int fromlen, const struct nls_table *codepage, bool mapchar) { - int i, charlen, safelen; + int i, j, charlen, safelen; int outlen = 0; int nullsize = nls_nullsize(codepage); int fromwords = fromlen / 2; char tmp[NLS_MAX_CHARSET_SIZE]; - __u16 ftmp; + __u16 ftmp[3]; /* ftmp[3] = 3array x 2bytes = 6bytes UTF-16 */ /* * because the chars can be of varying widths, we need to take care @@ -155,9 +176,15 @@ static int smb_from_utf16(char *to, const __le16 *from, int tolen, int fromlen, safelen = tolen - (NLS_MAX_CHARSET_SIZE + nullsize); for (i = 0; i < fromwords; i++) { - ftmp = get_unaligned_le16(&from[i]); - if (ftmp == 0) + ftmp[0] = get_unaligned_le16(&from[i]); + if (ftmp[0] == 0) break; + for (j = 1; j <= 2; j++) { + if (i + j < fromwords) + ftmp[j] = get_unaligned_le16(&from[i + j]); + else + ftmp[j] = 0; + } /* * check to see if converting this character might make the @@ -172,6 +199,19 @@ static int smb_from_utf16(char *to, const __le16 *from, int tolen, int fromlen, /* put converted char into 'to' buffer */ charlen = cifs_mapchar(&to[outlen], ftmp, codepage, mapchar); outlen += charlen; + + /* + * charlen (=bytes of UTF-8 for 1 character) + * 4bytes UTF-8(surrogate pair) is charlen=4 + * (4bytes UTF-16 code) + * 7-8bytes UTF-8(IVS) is charlen=3+4 or 4+4 + * (2 UTF-8 pairs divided to 2 UTF-16 pairs) + */ + if (charlen == 4) + i++; + else if (charlen >= 5) + /* 5-6bytes UTF-8 */ + i += 2; } /* properly null-terminate string */ @@ -306,6 +346,9 @@ int smbConvertToUTF16(__le16 *target, const char *source, int srclen, char src_char; __le16 dst_char; wchar_t tmp; + wchar_t wchar_to[6]; /* UTF-16 */ + int ret; + unicode_t u; if (!mapchars) return smb_strtoUTF16(target, source, srclen, cp); @@ -348,11 +391,57 @@ int smbConvertToUTF16(__le16 *target, const char *source, int srclen, * if no match, use question mark, which at least in * some cases serves as wild card */ - if (charlen < 1) { - dst_char = cpu_to_le16(0x003f); - charlen = 1; + if (charlen > 0) + goto ctoUTF16; + + /* convert SURROGATE_PAIR */ + if (strcmp(cp->charset, "utf8")) + goto unknown; + if (*(source + i) & 0x80) { + charlen = utf8_to_utf32(source + i, 6, &u); + if (charlen < 0) + goto unknown; + } else + goto unknown; + ret = utf8s_to_utf16s(source + i, charlen, + UTF16_LITTLE_ENDIAN, + wchar_to, 6); + if (ret < 0) + goto unknown; + + i += charlen; + dst_char = cpu_to_le16(*wchar_to); + if (charlen <= 3) + /* 1-3bytes UTF-8 to 2bytes UTF-16 */ + put_unaligned(dst_char, &target[j]); + else if (charlen == 4) { + /* + * 4bytes UTF-8(surrogate pair) to 4bytes UTF-16 + * 7-8bytes UTF-8(IVS) divided to 2 UTF-16 + * (charlen=3+4 or 4+4) + */ + put_unaligned(dst_char, &target[j]); + dst_char = cpu_to_le16(*(wchar_to + 1)); + j++; + put_unaligned(dst_char, &target[j]); + } else if (charlen >= 5) { + /* 5-6bytes UTF-8 to 6bytes UTF-16 */ + put_unaligned(dst_char, &target[j]); + dst_char = cpu_to_le16(*(wchar_to + 1)); + j++; + put_unaligned(dst_char, &target[j]); + dst_char = cpu_to_le16(*(wchar_to + 2)); + j++; + put_unaligned(dst_char, &target[j]); } + continue; + +unknown: + dst_char = cpu_to_le16(0x003f); + charlen = 1; } + +ctoUTF16: /* * character may take more than one byte in the source string, * but will take exactly two bytes in the target string diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c index b5a5e50fc9ca3..4277750a6da1b 100644 --- a/fs/smb/server/vfs.c +++ b/fs/smb/server/vfs.c @@ -97,6 +97,13 @@ static int ksmbd_vfs_path_lookup_locked(struct ksmbd_share_config *share_conf, return -ENOENT; } + err = mnt_want_write(parent_path->mnt); + if (err) { + path_put(parent_path); + putname(filename); + return -ENOENT; + } + inode_lock_nested(parent_path->dentry->d_inode, I_MUTEX_PARENT); d = lookup_one_qstr_excl(&last, parent_path->dentry, 0); if (IS_ERR(d)) @@ -123,6 +130,7 @@ static int ksmbd_vfs_path_lookup_locked(struct ksmbd_share_config *share_conf, err_out: inode_unlock(d_inode(parent_path->dentry)); + mnt_drop_write(parent_path->mnt); path_put(parent_path); putname(filename); return -ENOENT; @@ -173,10 +181,6 @@ int ksmbd_vfs_create(struct ksmbd_work *work, const char *name, umode_t mode) return err; } - err = mnt_want_write(path.mnt); - if (err) - goto out_err; - mode |= S_IFREG; err = vfs_create(mnt_idmap(path.mnt), d_inode(path.dentry), dentry, mode, true); @@ -186,9 +190,7 @@ int ksmbd_vfs_create(struct ksmbd_work *work, const char *name, umode_t mode) } else { pr_err("File(%s): creation failed (err:%d)\n", name, err); } - mnt_drop_write(path.mnt); -out_err: done_path_create(&path, dentry); return err; } @@ -219,10 +221,6 @@ int ksmbd_vfs_mkdir(struct ksmbd_work *work, const char *name, umode_t mode) return err; } - err = mnt_want_write(path.mnt); - if (err) - goto out_err2; - idmap = mnt_idmap(path.mnt); mode |= S_IFDIR; err = vfs_mkdir(idmap, d_inode(path.dentry), dentry, mode); @@ -233,21 +231,19 @@ int ksmbd_vfs_mkdir(struct ksmbd_work *work, const char *name, umode_t mode) dentry->d_name.len); if (IS_ERR(d)) { err = PTR_ERR(d); - goto out_err1; + goto out_err; } if (unlikely(d_is_negative(d))) { dput(d); err = -ENOENT; - goto out_err1; + goto out_err; } ksmbd_vfs_inherit_owner(work, d_inode(path.dentry), d_inode(d)); dput(d); } -out_err1: - mnt_drop_write(path.mnt); -out_err2: +out_err: done_path_create(&path, dentry); if (err) pr_err("mkdir(%s): creation failed (err:%d)\n", name, err); @@ -463,7 +459,8 @@ static int ksmbd_vfs_stream_write(struct ksmbd_file *fp, char *buf, loff_t *pos, fp->stream.name, (void *)stream_buf, size, - 0); + 0, + true); if (err < 0) goto out; @@ -520,6 +517,9 @@ int ksmbd_vfs_write(struct ksmbd_work *work, struct ksmbd_file *fp, } } + /* Reserve lease break for parent dir at closing time */ + fp->reserve_lease_break = true; + /* Do we need to break any of a levelII oplock? */ smb_break_all_levII_oplock(work, fp, 1); @@ -605,10 +605,6 @@ int ksmbd_vfs_remove_file(struct ksmbd_work *work, const struct path *path) goto out_err; } - err = mnt_want_write(path->mnt); - if (err) - goto out_err; - idmap = mnt_idmap(path->mnt); if (S_ISDIR(d_inode(path->dentry)->i_mode)) { err = vfs_rmdir(idmap, d_inode(parent), path->dentry); @@ -619,7 +615,6 @@ int ksmbd_vfs_remove_file(struct ksmbd_work *work, const struct path *path) if (err) ksmbd_debug(VFS, "unlink failed, err %d\n", err); } - mnt_drop_write(path->mnt); out_err: ksmbd_revert_fsids(work); @@ -665,16 +660,11 @@ int ksmbd_vfs_link(struct ksmbd_work *work, const char *oldname, goto out3; } - err = mnt_want_write(newpath.mnt); - if (err) - goto out3; - err = vfs_link(oldpath.dentry, mnt_idmap(newpath.mnt), d_inode(newpath.dentry), dentry, NULL); if (err) ksmbd_debug(VFS, "vfs_link failed err %d\n", err); - mnt_drop_write(newpath.mnt); out3: done_path_create(&newpath, dentry); @@ -732,7 +722,7 @@ int ksmbd_vfs_rename(struct ksmbd_work *work, const struct path *old_path, goto out3; } - parent_fp = ksmbd_lookup_fd_inode(d_inode(old_child->d_parent)); + parent_fp = ksmbd_lookup_fd_inode(old_child->d_parent); if (parent_fp) { if (parent_fp->daccess & FILE_DELETE_LE) { pr_err("parent dir is opened with delete access\n"); @@ -919,23 +909,27 @@ ssize_t ksmbd_vfs_getxattr(struct mnt_idmap *idmap, /** * ksmbd_vfs_setxattr() - vfs helper for smb set extended attributes value * @idmap: idmap of the relevant mount - * @dentry: dentry to set XATTR at + * @path: path of dentry to set XATTR at * @attr_name: xattr name for setxattr * @attr_value: xattr value to set * @attr_size: size of xattr value * @flags: destination buffer length + * @get_write: get write access to a mount * * Return: 0 on success, otherwise error */ int ksmbd_vfs_setxattr(struct mnt_idmap *idmap, const struct path *path, const char *attr_name, - void *attr_value, size_t attr_size, int flags) + void *attr_value, size_t attr_size, int flags, + bool get_write) { int err; - err = mnt_want_write(path->mnt); - if (err) - return err; + if (get_write == true) { + err = mnt_want_write(path->mnt); + if (err) + return err; + } err = vfs_setxattr(idmap, path->dentry, @@ -945,7 +939,8 @@ int ksmbd_vfs_setxattr(struct mnt_idmap *idmap, flags); if (err) ksmbd_debug(VFS, "setxattr failed, err %d\n", err); - mnt_drop_write(path->mnt); + if (get_write == true) + mnt_drop_write(path->mnt); return err; } @@ -1194,9 +1189,10 @@ static int ksmbd_vfs_lookup_in_dir(const struct path *dir, char *name, /** * ksmbd_vfs_kern_path_locked() - lookup a file and get path info - * @name: file path that is relative to share - * @flags: lookup flags - * @path: if lookup succeed, return path info + * @name: file path that is relative to share + * @flags: lookup flags + * @parent_path: if lookup succeed, return parent_path info + * @path: if lookup succeed, return path info * @caseless: caseless filename lookup * * Return: 0 on success, otherwise error @@ -1268,6 +1264,13 @@ int ksmbd_vfs_kern_path_locked(struct ksmbd_work *work, char *name, } if (!err) { + err = mnt_want_write(parent_path->mnt); + if (err) { + path_put(path); + path_put(parent_path); + return err; + } + err = ksmbd_vfs_lock_parent(parent_path->dentry, path->dentry); if (err) { path_put(path); @@ -1277,6 +1280,14 @@ int ksmbd_vfs_kern_path_locked(struct ksmbd_work *work, char *name, return err; } +void ksmbd_vfs_kern_path_unlock(struct path *parent_path, struct path *path) +{ + inode_unlock(d_inode(parent_path->dentry)); + mnt_drop_write(parent_path->mnt); + path_put(path); + path_put(parent_path); +} + struct dentry *ksmbd_vfs_kern_path_create(struct ksmbd_work *work, const char *name, unsigned int flags, @@ -1431,7 +1442,8 @@ static struct xattr_smb_acl *ksmbd_vfs_make_xattr_posix_acl(struct mnt_idmap *id int ksmbd_vfs_set_sd_xattr(struct ksmbd_conn *conn, struct mnt_idmap *idmap, const struct path *path, - struct smb_ntsd *pntsd, int len) + struct smb_ntsd *pntsd, int len, + bool get_write) { int rc; struct ndr sd_ndr = {0}, acl_ndr = {0}; @@ -1491,7 +1503,7 @@ int ksmbd_vfs_set_sd_xattr(struct ksmbd_conn *conn, rc = ksmbd_vfs_setxattr(idmap, path, XATTR_NAME_SD, sd_ndr.data, - sd_ndr.offset, 0); + sd_ndr.offset, 0, get_write); if (rc < 0) pr_err("Failed to store XATTR ntacl :%d\n", rc); @@ -1580,7 +1592,8 @@ int ksmbd_vfs_get_sd_xattr(struct ksmbd_conn *conn, int ksmbd_vfs_set_dos_attrib_xattr(struct mnt_idmap *idmap, const struct path *path, - struct xattr_dos_attrib *da) + struct xattr_dos_attrib *da, + bool get_write) { struct ndr n; int err; @@ -1590,7 +1603,7 @@ int ksmbd_vfs_set_dos_attrib_xattr(struct mnt_idmap *idmap, return err; err = ksmbd_vfs_setxattr(idmap, path, XATTR_NAME_DOS_ATTRIBUTE, - (void *)n.data, n.offset, 0); + (void *)n.data, n.offset, 0, get_write); if (err) ksmbd_debug(SMB, "failed to store dos attribute in xattr\n"); kfree(n.data); @@ -1862,10 +1875,6 @@ int ksmbd_vfs_set_init_posix_acl(struct mnt_idmap *idmap, } posix_state_to_acl(&acl_state, acls->a_entries); - rc = mnt_want_write(path->mnt); - if (rc) - goto out_err; - rc = set_posix_acl(idmap, dentry, ACL_TYPE_ACCESS, acls); if (rc < 0) ksmbd_debug(SMB, "Set posix acl(ACL_TYPE_ACCESS) failed, rc : %d\n", @@ -1877,9 +1886,7 @@ int ksmbd_vfs_set_init_posix_acl(struct mnt_idmap *idmap, ksmbd_debug(SMB, "Set posix acl(ACL_TYPE_DEFAULT) failed, rc : %d\n", rc); } - mnt_drop_write(path->mnt); -out_err: free_acl_state(&acl_state); posix_acl_release(acls); return rc; @@ -1909,10 +1916,6 @@ int ksmbd_vfs_inherit_posix_acl(struct mnt_idmap *idmap, } } - rc = mnt_want_write(path->mnt); - if (rc) - goto out_err; - rc = set_posix_acl(idmap, dentry, ACL_TYPE_ACCESS, acls); if (rc < 0) ksmbd_debug(SMB, "Set posix acl(ACL_TYPE_ACCESS) failed, rc : %d\n", @@ -1924,9 +1927,7 @@ int ksmbd_vfs_inherit_posix_acl(struct mnt_idmap *idmap, ksmbd_debug(SMB, "Set posix acl(ACL_TYPE_DEFAULT) failed, rc : %d\n", rc); } - mnt_drop_write(path->mnt); -out_err: posix_acl_release(acls); return rc; } diff --git a/fs/smb/server/vfs.h b/fs/smb/server/vfs.h index 00968081856e3..cfe1c8092f230 100644 --- a/fs/smb/server/vfs.h +++ b/fs/smb/server/vfs.h @@ -109,7 +109,8 @@ ssize_t ksmbd_vfs_casexattr_len(struct mnt_idmap *idmap, int attr_name_len); int ksmbd_vfs_setxattr(struct mnt_idmap *idmap, const struct path *path, const char *attr_name, - void *attr_value, size_t attr_size, int flags); + void *attr_value, size_t attr_size, int flags, + bool get_write); int ksmbd_vfs_xattr_stream_name(char *stream_name, char **xattr_stream_name, size_t *xattr_stream_name_size, int s_type); int ksmbd_vfs_remove_xattr(struct mnt_idmap *idmap, @@ -117,6 +118,7 @@ int ksmbd_vfs_remove_xattr(struct mnt_idmap *idmap, int ksmbd_vfs_kern_path_locked(struct ksmbd_work *work, char *name, unsigned int flags, struct path *parent_path, struct path *path, bool caseless); +void ksmbd_vfs_kern_path_unlock(struct path *parent_path, struct path *path); struct dentry *ksmbd_vfs_kern_path_create(struct ksmbd_work *work, const char *name, unsigned int flags, @@ -144,14 +146,16 @@ int ksmbd_vfs_remove_sd_xattrs(struct mnt_idmap *idmap, const struct path *path) int ksmbd_vfs_set_sd_xattr(struct ksmbd_conn *conn, struct mnt_idmap *idmap, const struct path *path, - struct smb_ntsd *pntsd, int len); + struct smb_ntsd *pntsd, int len, + bool get_write); int ksmbd_vfs_get_sd_xattr(struct ksmbd_conn *conn, struct mnt_idmap *idmap, struct dentry *dentry, struct smb_ntsd **pntsd); int ksmbd_vfs_set_dos_attrib_xattr(struct mnt_idmap *idmap, const struct path *path, - struct xattr_dos_attrib *da); + struct xattr_dos_attrib *da, + bool get_write); int ksmbd_vfs_get_dos_attrib_xattr(struct mnt_idmap *idmap, struct dentry *dentry, struct xattr_dos_attrib *da); diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c index c91eac6514dd9..4e82ff627d122 100644 --- a/fs/smb/server/vfs_cache.c +++ b/fs/smb/server/vfs_cache.c @@ -66,14 +66,14 @@ static unsigned long inode_hash(struct super_block *sb, unsigned long hashval) return tmp & inode_hash_mask; } -static struct ksmbd_inode *__ksmbd_inode_lookup(struct inode *inode) +static struct ksmbd_inode *__ksmbd_inode_lookup(struct dentry *de) { struct hlist_head *head = inode_hashtable + - inode_hash(inode->i_sb, inode->i_ino); + inode_hash(d_inode(de)->i_sb, (unsigned long)de); struct ksmbd_inode *ci = NULL, *ret_ci = NULL; hlist_for_each_entry(ci, head, m_hash) { - if (ci->m_inode == inode) { + if (ci->m_de == de) { if (atomic_inc_not_zero(&ci->m_count)) ret_ci = ci; break; @@ -84,26 +84,27 @@ static struct ksmbd_inode *__ksmbd_inode_lookup(struct inode *inode) static struct ksmbd_inode *ksmbd_inode_lookup(struct ksmbd_file *fp) { - return __ksmbd_inode_lookup(file_inode(fp->filp)); + return __ksmbd_inode_lookup(fp->filp->f_path.dentry); } -static struct ksmbd_inode *ksmbd_inode_lookup_by_vfsinode(struct inode *inode) +struct ksmbd_inode *ksmbd_inode_lookup_lock(struct dentry *d) { struct ksmbd_inode *ci; read_lock(&inode_hash_lock); - ci = __ksmbd_inode_lookup(inode); + ci = __ksmbd_inode_lookup(d); read_unlock(&inode_hash_lock); + return ci; } -int ksmbd_query_inode_status(struct inode *inode) +int ksmbd_query_inode_status(struct dentry *dentry) { struct ksmbd_inode *ci; int ret = KSMBD_INODE_STATUS_UNKNOWN; read_lock(&inode_hash_lock); - ci = __ksmbd_inode_lookup(inode); + ci = __ksmbd_inode_lookup(dentry); if (ci) { ret = KSMBD_INODE_STATUS_OK; if (ci->m_flags & (S_DEL_PENDING | S_DEL_ON_CLS)) @@ -143,7 +144,7 @@ void ksmbd_fd_set_delete_on_close(struct ksmbd_file *fp, static void ksmbd_inode_hash(struct ksmbd_inode *ci) { struct hlist_head *b = inode_hashtable + - inode_hash(ci->m_inode->i_sb, ci->m_inode->i_ino); + inode_hash(d_inode(ci->m_de)->i_sb, (unsigned long)ci->m_de); hlist_add_head(&ci->m_hash, b); } @@ -157,7 +158,6 @@ static void ksmbd_inode_unhash(struct ksmbd_inode *ci) static int ksmbd_inode_init(struct ksmbd_inode *ci, struct ksmbd_file *fp) { - ci->m_inode = file_inode(fp->filp); atomic_set(&ci->m_count, 1); atomic_set(&ci->op_count, 0); atomic_set(&ci->sop_count, 0); @@ -166,6 +166,7 @@ static int ksmbd_inode_init(struct ksmbd_inode *ci, struct ksmbd_file *fp) INIT_LIST_HEAD(&ci->m_fp_list); INIT_LIST_HEAD(&ci->m_op_list); rwlock_init(&ci->m_lock); + ci->m_de = fp->filp->f_path.dentry; return 0; } @@ -209,7 +210,7 @@ static void ksmbd_inode_free(struct ksmbd_inode *ci) kfree(ci); } -static void ksmbd_inode_put(struct ksmbd_inode *ci) +void ksmbd_inode_put(struct ksmbd_inode *ci) { if (atomic_dec_and_test(&ci->m_count)) ksmbd_inode_free(ci); @@ -488,12 +489,15 @@ struct ksmbd_file *ksmbd_lookup_fd_cguid(char *cguid) return fp; } -struct ksmbd_file *ksmbd_lookup_fd_inode(struct inode *inode) +struct ksmbd_file *ksmbd_lookup_fd_inode(struct dentry *dentry) { struct ksmbd_file *lfp; struct ksmbd_inode *ci; + struct inode *inode = d_inode(dentry); - ci = ksmbd_inode_lookup_by_vfsinode(inode); + read_lock(&inode_hash_lock); + ci = __ksmbd_inode_lookup(dentry); + read_unlock(&inode_hash_lock); if (!ci) return NULL; diff --git a/fs/smb/server/vfs_cache.h b/fs/smb/server/vfs_cache.h index 03d0bf941216f..a528f0cc775ae 100644 --- a/fs/smb/server/vfs_cache.h +++ b/fs/smb/server/vfs_cache.h @@ -51,7 +51,7 @@ struct ksmbd_inode { atomic_t op_count; /* opinfo count for streams */ atomic_t sop_count; - struct inode *m_inode; + struct dentry *m_de; unsigned int m_flags; struct hlist_node m_hash; struct list_head m_fp_list; @@ -105,6 +105,7 @@ struct ksmbd_file { struct ksmbd_readdir_data readdir_data; int dot_dotdot[2]; unsigned int f_state; + bool reserve_lease_break; }; static inline void set_ctx_actor(struct dir_context *ctx, @@ -138,9 +139,11 @@ struct ksmbd_file *ksmbd_lookup_foreign_fd(struct ksmbd_work *work, u64 id); struct ksmbd_file *ksmbd_lookup_fd_slow(struct ksmbd_work *work, u64 id, u64 pid); void ksmbd_fd_put(struct ksmbd_work *work, struct ksmbd_file *fp); +struct ksmbd_inode *ksmbd_inode_lookup_lock(struct dentry *d); +void ksmbd_inode_put(struct ksmbd_inode *ci); struct ksmbd_file *ksmbd_lookup_durable_fd(unsigned long long id); struct ksmbd_file *ksmbd_lookup_fd_cguid(char *cguid); -struct ksmbd_file *ksmbd_lookup_fd_inode(struct inode *inode); +struct ksmbd_file *ksmbd_lookup_fd_inode(struct dentry *dentry); unsigned int ksmbd_open_durable_fd(struct ksmbd_file *fp); struct ksmbd_file *ksmbd_open_fd(struct ksmbd_work *work, struct file *filp); void ksmbd_close_tree_conn_fds(struct ksmbd_work *work); @@ -164,7 +167,7 @@ enum KSMBD_INODE_STATUS { KSMBD_INODE_STATUS_PENDING_DELETE, }; -int ksmbd_query_inode_status(struct inode *inode); +int ksmbd_query_inode_status(struct dentry *dentry); bool ksmbd_inode_pending_delete(struct ksmbd_file *fp); void ksmbd_set_inode_pending_delete(struct ksmbd_file *fp); void ksmbd_clear_inode_pending_delete(struct ksmbd_file *fp); diff --git a/fs/stat.c b/fs/stat.c index d43a5cc1bfa46..5375be5f97ccf 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -133,7 +133,8 @@ int vfs_getattr_nosec(const struct path *path, struct kstat *stat, idmap = mnt_idmap(path->mnt); if (inode->i_op->getattr) return inode->i_op->getattr(idmap, path, stat, - request_mask, query_flags); + request_mask, + query_flags | AT_GETATTR_NOSEC); generic_fillattr(idmap, request_mask, inode, stat); return 0; @@ -166,6 +167,9 @@ int vfs_getattr(const struct path *path, struct kstat *stat, { int retval; + if (WARN_ON_ONCE(query_flags & AT_GETATTR_NOSEC)) + return -EPERM; + retval = security_inode_getattr(path); if (retval) return retval; diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index 891653ba9cf35..0292c6a2bed9f 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -509,20 +509,15 @@ struct dentry *eventfs_start_creating(const char *name, struct dentry *parent) struct dentry *dentry; int error; + /* Must always have a parent. */ + if (WARN_ON_ONCE(!parent)) + return ERR_PTR(-EINVAL); + error = simple_pin_fs(&trace_fs_type, &tracefs_mount, &tracefs_mount_count); if (error) return ERR_PTR(error); - /* - * If the parent is not specified, we create it in the root. - * We need the root dentry to do this, which is in the super - * block. A pointer to that is in the struct vfsmount that we - * have around. - */ - if (!parent) - parent = tracefs_mount->mnt_root; - if (unlikely(IS_DEADDIR(parent->d_inode))) dentry = ERR_PTR(-ENOENT); else diff --git a/fs/xfs/xfs_inode_item_recover.c b/fs/xfs/xfs_inode_item_recover.c index 0e5dba2343ea1..e6609067ef261 100644 --- a/fs/xfs/xfs_inode_item_recover.c +++ b/fs/xfs/xfs_inode_item_recover.c @@ -369,24 +369,26 @@ xlog_recover_inode_commit_pass2( * superblock flag to determine whether we need to look at di_flushiter * to skip replay when the on disk inode is newer than the log one */ - if (!xfs_has_v3inodes(mp) && - ldip->di_flushiter < be16_to_cpu(dip->di_flushiter)) { - /* - * Deal with the wrap case, DI_MAX_FLUSH is less - * than smaller numbers - */ - if (be16_to_cpu(dip->di_flushiter) == DI_MAX_FLUSH && - ldip->di_flushiter < (DI_MAX_FLUSH >> 1)) { - /* do nothing */ - } else { - trace_xfs_log_recover_inode_skip(log, in_f); - error = 0; - goto out_release; + if (!xfs_has_v3inodes(mp)) { + if (ldip->di_flushiter < be16_to_cpu(dip->di_flushiter)) { + /* + * Deal with the wrap case, DI_MAX_FLUSH is less + * than smaller numbers + */ + if (be16_to_cpu(dip->di_flushiter) == DI_MAX_FLUSH && + ldip->di_flushiter < (DI_MAX_FLUSH >> 1)) { + /* do nothing */ + } else { + trace_xfs_log_recover_inode_skip(log, in_f); + error = 0; + goto out_release; + } } + + /* Take the opportunity to reset the flush iteration count */ + ldip->di_flushiter = 0; } - /* Take the opportunity to reset the flush iteration count */ - ldip->di_flushiter = 0; if (unlikely(S_ISREG(ldip->di_mode))) { if ((ldip->di_format != XFS_DINODE_FMT_EXTENTS) && diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index 254685085c825..0b7eab0ef7d7f 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -539,6 +539,7 @@ int acpi_device_set_power(struct acpi_device *device, int state); int acpi_bus_init_power(struct acpi_device *device); int acpi_device_fix_up_power(struct acpi_device *device); void acpi_device_fix_up_power_extended(struct acpi_device *adev); +void acpi_device_fix_up_power_children(struct acpi_device *adev); int acpi_bus_update_power(acpi_handle handle, int *state_p); int acpi_device_update_power(struct acpi_device *device, int *state_p); bool acpi_bus_power_manageable(acpi_handle handle); diff --git a/include/acpi/ghes.h b/include/acpi/ghes.h index 3c8bba9f1114a..be1dd4c1a9174 100644 --- a/include/acpi/ghes.h +++ b/include/acpi/ghes.h @@ -73,8 +73,12 @@ int ghes_register_vendor_record_notifier(struct notifier_block *nb); void ghes_unregister_vendor_record_notifier(struct notifier_block *nb); struct list_head *ghes_get_devices(void); + +void ghes_estatus_pool_region_free(unsigned long addr, u32 size); #else static inline struct list_head *ghes_get_devices(void) { return NULL; } + +static inline void ghes_estatus_pool_region_free(unsigned long addr, u32 size) { return; } #endif int ghes_estatus_pool_init(unsigned int num_ghes); diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h index 995513fa26904..0655aa5b57b29 100644 --- a/include/asm-generic/qspinlock.h +++ b/include/asm-generic/qspinlock.h @@ -70,7 +70,7 @@ static __always_inline int queued_spin_is_locked(struct qspinlock *lock) */ static __always_inline int queued_spin_value_unlocked(struct qspinlock lock) { - return !atomic_read(&lock.val); + return !lock.val.counter; } /** diff --git a/include/drm/drm_atomic_helper.h b/include/drm/drm_atomic_helper.h index 536a0b0091c3a..006b5c977ad77 100644 --- a/include/drm/drm_atomic_helper.h +++ b/include/drm/drm_atomic_helper.h @@ -97,6 +97,8 @@ void drm_atomic_helper_commit_modeset_enables(struct drm_device *dev, int drm_atomic_helper_prepare_planes(struct drm_device *dev, struct drm_atomic_state *state); +void drm_atomic_helper_unprepare_planes(struct drm_device *dev, + struct drm_atomic_state *state); #define DRM_PLANE_COMMIT_ACTIVE_ONLY BIT(0) #define DRM_PLANE_COMMIT_NO_DISABLE_AFTER_MODESET BIT(1) diff --git a/include/drm/drm_file.h b/include/drm/drm_file.h index 010239392adfb..9c47a43f42a62 100644 --- a/include/drm/drm_file.h +++ b/include/drm/drm_file.h @@ -256,8 +256,15 @@ struct drm_file { /** @master_lookup_lock: Serializes @master. */ spinlock_t master_lookup_lock; - /** @pid: Process that opened this file. */ - struct pid *pid; + /** + * @pid: Process that is using this file. + * + * Must only be dereferenced under a rcu_read_lock or equivalent. + * + * Updates are guarded with dev->filelist_mutex and reference must be + * dropped after a RCU grace period to accommodate lockless readers. + */ + struct pid __rcu *pid; /** @client_id: A unique id for fdinfo */ u64 client_id; @@ -420,6 +427,8 @@ static inline bool drm_is_accel_client(const struct drm_file *file_priv) return file_priv->minor->type == DRM_MINOR_ACCEL; } +void drm_file_update_pid(struct drm_file *); + int drm_open(struct inode *inode, struct file *filp); int drm_open_helper(struct file *filp, struct drm_minor *minor); ssize_t drm_read(struct file *filp, char __user *buffer, diff --git a/include/linux/amd-pstate.h b/include/linux/amd-pstate.h index 446394f846064..6ad02ad9c7b42 100644 --- a/include/linux/amd-pstate.h +++ b/include/linux/amd-pstate.h @@ -70,6 +70,10 @@ struct amd_cpudata { u32 nominal_perf; u32 lowest_nonlinear_perf; u32 lowest_perf; + u32 min_limit_perf; + u32 max_limit_perf; + u32 min_limit_freq; + u32 max_limit_freq; u32 max_freq; u32 min_freq; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index eef450f259828..f59fcd5b499a5 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -538,7 +538,7 @@ struct request_queue { #define QUEUE_FLAG_ADD_RANDOM 10 /* Contributes to random pool */ #define QUEUE_FLAG_SYNCHRONOUS 11 /* always completes in submit context */ #define QUEUE_FLAG_SAME_FORCE 12 /* force complete on same CPU */ -#define QUEUE_FLAG_HW_WC 18 /* Write back caching supported */ +#define QUEUE_FLAG_HW_WC 13 /* Write back caching supported */ #define QUEUE_FLAG_INIT_DONE 14 /* queue is initialized */ #define QUEUE_FLAG_STABLE_WRITES 15 /* don't modify blks until WB is done */ #define QUEUE_FLAG_POLL 16 /* IO polling enabled if set */ diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 76055186d6248..75e039081f929 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -903,10 +903,14 @@ bpf_ctx_record_field_size(struct bpf_insn_access_aux *aux, u32 size) aux->ctx_field_size = size; } +static bool bpf_is_ldimm64(const struct bpf_insn *insn) +{ + return insn->code == (BPF_LD | BPF_IMM | BPF_DW); +} + static inline bool bpf_pseudo_func(const struct bpf_insn *insn) { - return insn->code == (BPF_LD | BPF_IMM | BPF_DW) && - insn->src_reg == BPF_PSEUDO_FUNC; + return bpf_is_ldimm64(insn) && insn->src_reg == BPF_PSEUDO_FUNC; } struct bpf_prog_ops { @@ -3139,6 +3143,9 @@ enum bpf_text_poke_type { int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, void *addr1, void *addr2); +void bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke, + struct bpf_prog *new, struct bpf_prog *old); + void *bpf_arch_text_copy(void *dst, void *src, size_t len); int bpf_arch_text_invalidate(void *dst, size_t len); diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 28c1d3d77b70f..624d4a38c358a 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -194,6 +194,7 @@ enum cpuhp_state { CPUHP_AP_ARM_CORESIGHT_CTI_STARTING, CPUHP_AP_ARM64_ISNDEP_STARTING, CPUHP_AP_SMPCFD_DYING, + CPUHP_AP_HRTIMERS_DYING, CPUHP_AP_X86_TBOOT_DYING, CPUHP_AP_ARM_CACHE_B15_RAC_DYING, CPUHP_AP_ONLINE, diff --git a/include/linux/cred.h b/include/linux/cred.h index f923528d5cc43..bb55703e11664 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -108,14 +108,7 @@ static inline int groups_search(const struct group_info *group_info, kgid_t grp) * same context as task->real_cred. */ struct cred { - atomic_t usage; -#ifdef CONFIG_DEBUG_CREDENTIALS - atomic_t subscribers; /* number of processes subscribed */ - void *put_addr; - unsigned magic; -#define CRED_MAGIC 0x43736564 -#define CRED_MAGIC_DEAD 0x44656144 -#endif + atomic_long_t usage; kuid_t uid; /* real UID of the task */ kgid_t gid; /* real GID of the task */ kuid_t suid; /* saved UID of the task */ @@ -171,46 +164,6 @@ extern int cred_fscmp(const struct cred *, const struct cred *); extern void __init cred_init(void); extern int set_cred_ucounts(struct cred *); -/* - * check for validity of credentials - */ -#ifdef CONFIG_DEBUG_CREDENTIALS -extern void __noreturn __invalid_creds(const struct cred *, const char *, unsigned); -extern void __validate_process_creds(struct task_struct *, - const char *, unsigned); - -extern bool creds_are_invalid(const struct cred *cred); - -static inline void __validate_creds(const struct cred *cred, - const char *file, unsigned line) -{ - if (unlikely(creds_are_invalid(cred))) - __invalid_creds(cred, file, line); -} - -#define validate_creds(cred) \ -do { \ - __validate_creds((cred), __FILE__, __LINE__); \ -} while(0) - -#define validate_process_creds() \ -do { \ - __validate_process_creds(current, __FILE__, __LINE__); \ -} while(0) - -extern void validate_creds_for_do_exit(struct task_struct *); -#else -static inline void validate_creds(const struct cred *cred) -{ -} -static inline void validate_creds_for_do_exit(struct task_struct *tsk) -{ -} -static inline void validate_process_creds(void) -{ -} -#endif - static inline bool cap_ambient_invariant_ok(const struct cred *cred) { return cap_issubset(cred->cap_ambient, @@ -227,7 +180,7 @@ static inline bool cap_ambient_invariant_ok(const struct cred *cred) */ static inline struct cred *get_new_cred(struct cred *cred) { - atomic_inc(&cred->usage); + atomic_long_inc(&cred->usage); return cred; } @@ -249,7 +202,6 @@ static inline const struct cred *get_cred(const struct cred *cred) struct cred *nonconst_cred = (struct cred *) cred; if (!cred) return cred; - validate_creds(cred); nonconst_cred->non_rcu = 0; return get_new_cred(nonconst_cred); } @@ -259,9 +211,8 @@ static inline const struct cred *get_cred_rcu(const struct cred *cred) struct cred *nonconst_cred = (struct cred *) cred; if (!cred) return NULL; - if (!atomic_inc_not_zero(&nonconst_cred->usage)) + if (!atomic_long_inc_not_zero(&nonconst_cred->usage)) return NULL; - validate_creds(cred); nonconst_cred->non_rcu = 0; return cred; } @@ -282,8 +233,7 @@ static inline void put_cred(const struct cred *_cred) struct cred *cred = (struct cred *) _cred; if (cred) { - validate_creds(cred); - if (atomic_dec_and_test(&(cred)->usage)) + if (atomic_long_dec_and_test(&(cred)->usage)) __put_cred(cred); } } diff --git a/include/linux/damon.h b/include/linux/damon.h index ae2664d1d5f1d..a953d7083cd59 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -522,8 +522,20 @@ struct damon_ctx { struct damon_attrs attrs; /* private: internal use only */ - struct timespec64 last_aggregation; - struct timespec64 last_ops_update; + /* number of sample intervals that passed since this context started */ + unsigned long passed_sample_intervals; + /* + * number of sample intervals that should be passed before next + * aggregation + */ + unsigned long next_aggregation_sis; + /* + * number of sample intervals that should be passed before next ops + * update + */ + unsigned long next_ops_update_sis; + /* for waiting until the execution of the kdamond_fn is started */ + struct completion kdamond_started; /* public: */ struct task_struct *kdamond; @@ -642,6 +654,13 @@ static inline bool damon_target_has_pid(const struct damon_ctx *ctx) return ctx->ops.id == DAMON_OPS_VADDR || ctx->ops.id == DAMON_OPS_FVADDR; } +static inline unsigned int damon_max_nr_accesses(const struct damon_attrs *attrs) +{ + /* {aggr,sample}_interval are unsigned long, hence could overflow */ + return min(attrs->aggr_interval / attrs->sample_interval, + (unsigned long)UINT_MAX); +} + int damon_start(struct damon_ctx **ctxs, int nr_ctxs, bool exclusive); int damon_stop(struct damon_ctx **ctxs, int nr_ctxs); diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index ebe78bd3d121d..b3772edca2e6e 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -498,6 +498,21 @@ static inline bool dma_fence_is_later(struct dma_fence *f1, return __dma_fence_is_later(f1->seqno, f2->seqno, f1->ops); } +/** + * dma_fence_is_later_or_same - return true if f1 is later or same as f2 + * @f1: the first fence from the same context + * @f2: the second fence from the same context + * + * Returns true if f1 is chronologically later than f2 or the same fence. Both + * fences must be from the same context, since a seqno is not re-used across + * contexts. + */ +static inline bool dma_fence_is_later_or_same(struct dma_fence *f1, + struct dma_fence *f2) +{ + return f1 == f2 || dma_fence_is_later(f1, f2); +} + /** * dma_fence_later - return the chronologically later fence * @f1: the first fence from the same context diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 62b61527bcc4f..1b523fd48586f 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -1045,10 +1045,10 @@ static inline int ethtool_mm_frag_size_min_to_add(u32 val_min, u32 *val_add, /** * ethtool_sprintf - Write formatted string to ethtool string data - * @data: Pointer to start of string to update + * @data: Pointer to a pointer to the start of string to update * @fmt: Format of string to write * - * Write formatted string to data. Update data to point at start of + * Write formatted string to *data. Update *data to point at start of * next string. */ extern __printf(2, 3) void ethtool_sprintf(u8 **data, const char *fmt, ...); diff --git a/include/linux/export-internal.h b/include/linux/export-internal.h index 45fca09b23194..5280194777340 100644 --- a/include/linux/export-internal.h +++ b/include/linux/export-internal.h @@ -16,10 +16,13 @@ * and eliminates the need for absolute relocations that require runtime * processing on relocatable kernels. */ +#define __KSYM_ALIGN ".balign 4" #define __KSYM_REF(sym) ".long " #sym "- ." #elif defined(CONFIG_64BIT) +#define __KSYM_ALIGN ".balign 8" #define __KSYM_REF(sym) ".quad " #sym #else +#define __KSYM_ALIGN ".balign 4" #define __KSYM_REF(sym) ".long " #sym #endif @@ -42,7 +45,7 @@ " .asciz \"" ns "\"" "\n" \ " .previous" "\n" \ " .section \"___ksymtab" sec "+" #name "\", \"a\"" "\n" \ - " .balign 4" "\n" \ + __KSYM_ALIGN "\n" \ "__ksymtab_" #name ":" "\n" \ __KSYM_REF(sym) "\n" \ __KSYM_REF(__kstrtab_ ##name) "\n" \ @@ -63,6 +66,7 @@ #define SYMBOL_CRC(sym, crc, sec) \ asm(".section \"___kcrctab" sec "+" #sym "\",\"a\"" "\n" \ + ".balign 4" "\n" \ "__crc_" #sym ":" "\n" \ ".long " #crc "\n" \ ".previous" "\n") diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index a82a4bb6ce68b..cf1adceb02697 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -104,6 +104,7 @@ enum f2fs_error { ERROR_CORRUPTED_VERITY_XATTR, ERROR_CORRUPTED_XATTR, ERROR_INVALID_NODE_REFERENCE, + ERROR_INCONSISTENT_NAT, ERROR_MAX, }; diff --git a/include/linux/fs.h b/include/linux/fs.h index ed24bce46cb39..e1ad2df9a9714 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1533,24 +1533,81 @@ static inline bool fsuidgid_has_mapping(struct super_block *sb, struct timespec64 current_time(struct inode *inode); struct timespec64 inode_set_ctime_current(struct inode *inode); -/** - * inode_get_ctime - fetch the current ctime from the inode - * @inode: inode from which to fetch ctime - * - * Grab the current ctime from the inode and return it. - */ +static inline time64_t inode_get_atime_sec(const struct inode *inode) +{ + return inode->i_atime.tv_sec; +} + +static inline long inode_get_atime_nsec(const struct inode *inode) +{ + return inode->i_atime.tv_nsec; +} + +static inline struct timespec64 inode_get_atime(const struct inode *inode) +{ + return inode->i_atime; +} + +static inline struct timespec64 inode_set_atime_to_ts(struct inode *inode, + struct timespec64 ts) +{ + inode->i_atime = ts; + return ts; +} + +static inline struct timespec64 inode_set_atime(struct inode *inode, + time64_t sec, long nsec) +{ + struct timespec64 ts = { .tv_sec = sec, + .tv_nsec = nsec }; + return inode_set_atime_to_ts(inode, ts); +} + +static inline time64_t inode_get_mtime_sec(const struct inode *inode) +{ + return inode->i_mtime.tv_sec; +} + +static inline long inode_get_mtime_nsec(const struct inode *inode) +{ + return inode->i_mtime.tv_nsec; +} + +static inline struct timespec64 inode_get_mtime(const struct inode *inode) +{ + return inode->i_mtime; +} + +static inline struct timespec64 inode_set_mtime_to_ts(struct inode *inode, + struct timespec64 ts) +{ + inode->i_mtime = ts; + return ts; +} + +static inline struct timespec64 inode_set_mtime(struct inode *inode, + time64_t sec, long nsec) +{ + struct timespec64 ts = { .tv_sec = sec, + .tv_nsec = nsec }; + return inode_set_mtime_to_ts(inode, ts); +} + +static inline time64_t inode_get_ctime_sec(const struct inode *inode) +{ + return inode->__i_ctime.tv_sec; +} + +static inline long inode_get_ctime_nsec(const struct inode *inode) +{ + return inode->__i_ctime.tv_nsec; +} + static inline struct timespec64 inode_get_ctime(const struct inode *inode) { return inode->__i_ctime; } -/** - * inode_set_ctime_to_ts - set the ctime in the inode - * @inode: inode in which to set the ctime - * @ts: value to set in the ctime field - * - * Set the ctime in @inode to @ts - */ static inline struct timespec64 inode_set_ctime_to_ts(struct inode *inode, struct timespec64 ts) { @@ -1575,6 +1632,8 @@ static inline struct timespec64 inode_set_ctime(struct inode *inode, return inode_set_ctime_to_ts(inode, ts); } +struct timespec64 simple_inode_init_ts(struct inode *inode); + /* * Snapshotting support. */ diff --git a/include/linux/generic-radix-tree.h b/include/linux/generic-radix-tree.h index 107613f7d7920..f6cd0f909d9fb 100644 --- a/include/linux/generic-radix-tree.h +++ b/include/linux/generic-radix-tree.h @@ -38,6 +38,7 @@ #include #include +#include #include #include #include @@ -184,6 +185,12 @@ void *__genradix_iter_peek(struct genradix_iter *, struct __genradix *, size_t); static inline void __genradix_iter_advance(struct genradix_iter *iter, size_t obj_size) { + if (iter->offset + obj_size < iter->offset) { + iter->offset = SIZE_MAX; + iter->pos = SIZE_MAX; + return; + } + iter->offset += obj_size; if (!is_power_of_2(obj_size) && diff --git a/include/linux/hid.h b/include/linux/hid.h index 964ca1f15e3f6..3b08a29572298 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -679,6 +679,7 @@ struct hid_device { /* device report descriptor */ struct list_head debug_list; spinlock_t debug_list_lock; wait_queue_head_t debug_wait; + struct kref ref; unsigned int id; /* system unique id */ @@ -687,6 +688,8 @@ struct hid_device { /* device report descriptor */ #endif /* CONFIG_BPF */ }; +void hiddev_free(struct kref *ref); + #define to_hid_device(pdev) \ container_of(pdev, struct hid_device, dev) diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 99c474de800dd..75607d4ba26cb 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -454,7 +454,7 @@ static inline void memcpy_from_folio(char *to, struct folio *folio, memcpy(to, from, chunk); kunmap_local(from); - from += chunk; + to += chunk; offset += chunk; len -= chunk; } while (len > 0); diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 0ee140176f102..f2044d5a652b5 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -531,9 +531,9 @@ extern void sysrq_timer_list_show(void); int hrtimers_prepare_cpu(unsigned int cpu); #ifdef CONFIG_HOTPLUG_CPU -int hrtimers_dead_cpu(unsigned int cpu); +int hrtimers_cpu_dying(unsigned int cpu); #else -#define hrtimers_dead_cpu NULL +#define hrtimers_cpu_dying NULL #endif #endif diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 47d25a5e1933d..31b2927ada73f 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -1265,10 +1265,7 @@ static inline bool __vma_shareable_lock(struct vm_area_struct *vma) return (vma->vm_flags & VM_MAYSHARE) && vma->vm_private_data; } -static inline bool __vma_private_lock(struct vm_area_struct *vma) -{ - return (!(vma->vm_flags & VM_MAYSHARE)) && vma->vm_private_data; -} +bool __vma_private_lock(struct vm_area_struct *vma); /* * Safe version of huge_pte_offset() to check the locks. See comments diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index b24fb80782c5a..2b0a73cb7cbb0 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -4381,7 +4381,8 @@ ieee80211_is_protected_dual_of_public_action(struct sk_buff *skb) action != WLAN_PUB_ACTION_LOC_TRACK_NOTI && action != WLAN_PUB_ACTION_FTM_REQUEST && action != WLAN_PUB_ACTION_FTM_RESPONSE && - action != WLAN_PUB_ACTION_FILS_DISCOVERY; + action != WLAN_PUB_ACTION_FILS_DISCOVERY && + action != WLAN_PUB_ACTION_VENDOR_SPECIFIC; } /** diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 13d19b9be9f4a..5fd664fb71c86 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -327,6 +327,9 @@ struct io_ring_ctx { struct list_head io_buffers_cache; + /* deferred free list, protected by ->uring_lock */ + struct hlist_head io_buf_list; + /* Keep this last, we don't need it for the fast path */ struct wait_queue_head poll_wq; struct io_restriction restrictions; diff --git a/include/linux/iommu.h b/include/linux/iommu.h index c50a769d569a6..0225cf7445de2 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -703,6 +703,7 @@ static inline void dev_iommu_priv_set(struct device *dev, void *priv) dev->iommu->priv = priv; } +extern struct mutex iommu_probe_device_lock; int iommu_probe_device(struct device *dev); int iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features f); diff --git a/include/linux/irq.h b/include/linux/irq.h index d8a6fdce93738..90081afa10ce5 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -215,8 +215,6 @@ struct irq_data { * IRQD_SINGLE_TARGET - IRQ allows only a single affinity target * IRQD_DEFAULT_TRIGGER_SET - Expected trigger already been set * IRQD_CAN_RESERVE - Can use reservation mode - * IRQD_MSI_NOMASK_QUIRK - Non-maskable MSI quirk for affinity change - * required * IRQD_HANDLE_ENFORCE_IRQCTX - Enforce that handle_irq_*() is only invoked * from actual interrupt context. * IRQD_AFFINITY_ON_ACTIVATE - Affinity is set on activation. Don't call @@ -247,11 +245,10 @@ enum { IRQD_SINGLE_TARGET = BIT(24), IRQD_DEFAULT_TRIGGER_SET = BIT(25), IRQD_CAN_RESERVE = BIT(26), - IRQD_MSI_NOMASK_QUIRK = BIT(27), - IRQD_HANDLE_ENFORCE_IRQCTX = BIT(28), - IRQD_AFFINITY_ON_ACTIVATE = BIT(29), - IRQD_IRQ_ENABLED_ON_SUSPEND = BIT(30), - IRQD_RESEND_WHEN_IN_PROGRESS = BIT(31), + IRQD_HANDLE_ENFORCE_IRQCTX = BIT(27), + IRQD_AFFINITY_ON_ACTIVATE = BIT(28), + IRQD_IRQ_ENABLED_ON_SUSPEND = BIT(29), + IRQD_RESEND_WHEN_IN_PROGRESS = BIT(30), }; #define __irqd_to_state(d) ACCESS_PRIVATE((d)->common, state_use_accessors) @@ -426,21 +423,6 @@ static inline bool irqd_can_reserve(struct irq_data *d) return __irqd_to_state(d) & IRQD_CAN_RESERVE; } -static inline void irqd_set_msi_nomask_quirk(struct irq_data *d) -{ - __irqd_to_state(d) |= IRQD_MSI_NOMASK_QUIRK; -} - -static inline void irqd_clr_msi_nomask_quirk(struct irq_data *d) -{ - __irqd_to_state(d) &= ~IRQD_MSI_NOMASK_QUIRK; -} - -static inline bool irqd_msi_nomask_quirk(struct irq_data *d) -{ - return __irqd_to_state(d) & IRQD_MSI_NOMASK_QUIRK; -} - static inline void irqd_set_affinity_on_activate(struct irq_data *d) { __irqd_to_state(d) |= IRQD_AFFINITY_ON_ACTIVATE; diff --git a/include/linux/key-type.h b/include/linux/key-type.h index 7d985a1dfe4af..5caf3ce823733 100644 --- a/include/linux/key-type.h +++ b/include/linux/key-type.h @@ -73,6 +73,7 @@ struct key_type { unsigned int flags; #define KEY_TYPE_NET_DOMAIN 0x00000001 /* Keys of this type have a net namespace domain */ +#define KEY_TYPE_INSTANT_REAP 0x00000002 /* Keys of this type don't have a delay after expiring */ /* vet a description */ int (*vet_description)(const char *description); diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 85a64cb95d755..8de5d51a0b5e7 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -140,7 +140,7 @@ static inline bool kprobe_ftrace(struct kprobe *p) * */ struct kretprobe_holder { - struct kretprobe *rp; + struct kretprobe __rcu *rp; refcount_t ref; }; @@ -202,10 +202,8 @@ extern int arch_trampoline_kprobe(struct kprobe *p); #ifdef CONFIG_KRETPROBE_ON_RETHOOK static nokprobe_inline struct kretprobe *get_kretprobe(struct kretprobe_instance *ri) { - RCU_LOCKDEP_WARN(!rcu_read_lock_any_held(), - "Kretprobe is accessed from instance under preemptive context"); - - return (struct kretprobe *)READ_ONCE(ri->node.rethook->data); + /* rethook::data is non-changed field, so that you can access it freely. */ + return (struct kretprobe *)ri->node.rethook->data; } static nokprobe_inline unsigned long get_kretprobe_retaddr(struct kretprobe_instance *ri) { @@ -250,10 +248,7 @@ unsigned long kretprobe_trampoline_handler(struct pt_regs *regs, static nokprobe_inline struct kretprobe *get_kretprobe(struct kretprobe_instance *ri) { - RCU_LOCKDEP_WARN(!rcu_read_lock_any_held(), - "Kretprobe is accessed from instance under preemptive context"); - - return READ_ONCE(ri->rph->rp); + return rcu_dereference_check(ri->rph->rp, rcu_read_lock_any_held()); } static nokprobe_inline unsigned long get_kretprobe_retaddr(struct kretprobe_instance *ri) diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index ac962c4cb44b1..2b8d85aae0832 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -48,7 +48,7 @@ LSM_HOOK(int, 0, quota_on, struct dentry *dentry) LSM_HOOK(int, 0, syslog, int type) LSM_HOOK(int, 0, settime, const struct timespec64 *ts, const struct timezone *tz) -LSM_HOOK(int, 0, vm_enough_memory, struct mm_struct *mm, long pages) +LSM_HOOK(int, 1, vm_enough_memory, struct mm_struct *mm, long pages) LSM_HOOK(int, 0, bprm_creds_for_exec, struct linux_binprm *bprm) LSM_HOOK(int, 0, bprm_creds_from_file, struct linux_binprm *bprm, struct file *file) LSM_HOOK(int, 0, bprm_check_security, struct linux_binprm *bprm) @@ -273,7 +273,7 @@ LSM_HOOK(void, LSM_RET_VOID, release_secctx, char *secdata, u32 seclen) LSM_HOOK(void, LSM_RET_VOID, inode_invalidate_secctx, struct inode *inode) LSM_HOOK(int, 0, inode_notifysecctx, struct inode *inode, void *ctx, u32 ctxlen) LSM_HOOK(int, 0, inode_setsecctx, struct dentry *dentry, void *ctx, u32 ctxlen) -LSM_HOOK(int, 0, inode_getsecctx, struct inode *inode, void **ctx, +LSM_HOOK(int, -EOPNOTSUPP, inode_getsecctx, struct inode *inode, void **ctx, u32 *ctxlen) #if defined(CONFIG_SECURITY) && defined(CONFIG_WATCH_QUEUE) diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 4d5be378fa8cc..26333d602a505 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -366,6 +366,8 @@ enum mlx5_driver_event { MLX5_DRIVER_EVENT_UPLINK_NETDEV, MLX5_DRIVER_EVENT_MACSEC_SA_ADDED, MLX5_DRIVER_EVENT_MACSEC_SA_DELETED, + MLX5_DRIVER_EVENT_AFFILIATION_DONE, + MLX5_DRIVER_EVENT_AFFILIATION_REMOVED, }; enum { diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 3033bbaeac81c..5ca4e085d8133 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1027,6 +1027,8 @@ bool mlx5_cmd_is_down(struct mlx5_core_dev *dev); void mlx5_core_uplink_netdev_set(struct mlx5_core_dev *mdev, struct net_device *netdev); void mlx5_core_uplink_netdev_event_replay(struct mlx5_core_dev *mdev); +void mlx5_core_mp_event_replay(struct mlx5_core_dev *dev, u32 event, void *data); + void mlx5_health_cleanup(struct mlx5_core_dev *dev); int mlx5_health_init(struct mlx5_core_dev *dev); void mlx5_start_health_poll(struct mlx5_core_dev *dev); diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index fc3db401f8a28..8ac6ae79e0835 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -620,7 +620,7 @@ struct mlx5_ifc_fte_match_set_misc_bits { u8 reserved_at_140[0x8]; u8 bth_dst_qp[0x18]; - u8 reserved_at_160[0x20]; + u8 inner_esp_spi[0x20]; u8 outer_esp_spi[0x20]; u8 reserved_at_1a0[0x60]; }; @@ -11936,6 +11936,13 @@ enum { MLX5_IPSEC_ASO_INC_SN = 0x2, }; +enum { + MLX5_IPSEC_ASO_REPLAY_WIN_32BIT = 0x0, + MLX5_IPSEC_ASO_REPLAY_WIN_64BIT = 0x1, + MLX5_IPSEC_ASO_REPLAY_WIN_128BIT = 0x2, + MLX5_IPSEC_ASO_REPLAY_WIN_256BIT = 0x3, +}; + struct mlx5_ifc_ipsec_aso_bits { u8 valid[0x1]; u8 reserved_at_201[0x1]; diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 8148b30a9df10..96b1c157554c0 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -231,22 +231,27 @@ static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, if (folio_test_unevictable(folio) || !lrugen->enabled) return false; /* - * There are three common cases for this page: - * 1. If it's hot, e.g., freshly faulted in or previously hot and - * migrated, add it to the youngest generation. - * 2. If it's cold but can't be evicted immediately, i.e., an anon page - * not in swapcache or a dirty page pending writeback, add it to the - * second oldest generation. - * 3. Everything else (clean, cold) is added to the oldest generation. + * There are four common cases for this page: + * 1. If it's hot, i.e., freshly faulted in, add it to the youngest + * generation, and it's protected over the rest below. + * 2. If it can't be evicted immediately, i.e., a dirty page pending + * writeback, add it to the second youngest generation. + * 3. If it should be evicted first, e.g., cold and clean from + * folio_rotate_reclaimable(), add it to the oldest generation. + * 4. Everything else falls between 2 & 3 above and is added to the + * second oldest generation if it's considered inactive, or the + * oldest generation otherwise. See lru_gen_is_active(). */ if (folio_test_active(folio)) seq = lrugen->max_seq; else if ((type == LRU_GEN_ANON && !folio_test_swapcache(folio)) || (folio_test_reclaim(folio) && (folio_test_dirty(folio) || folio_test_writeback(folio)))) - seq = lrugen->min_seq[type] + 1; - else + seq = lrugen->max_seq - 1; + else if (reclaiming || lrugen->min_seq[type] + MIN_NR_GENS >= lrugen->max_seq) seq = lrugen->min_seq[type]; + else + seq = lrugen->min_seq[type] + 1; gen = lru_gen_from_seq(seq); flags = (gen + 1UL) << LRU_GEN_PGOFF; diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index daa2f40d9ce65..7b12eebc5586d 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -295,7 +295,9 @@ struct mmc_card { #define MMC_QUIRK_BROKEN_HPI (1<<13) /* Disable broken HPI support */ #define MMC_QUIRK_BROKEN_SD_DISCARD (1<<14) /* Disable broken SD discard support */ #define MMC_QUIRK_BROKEN_SD_CACHE (1<<15) /* Disable broken SD cache support */ +#define MMC_QUIRK_BROKEN_CACHE_FLUSH (1<<16) /* Don't flush cache until the write has occurred */ + bool written_flag; /* Indicates eMMC has been written since power on */ bool reenable_cmdq; /* Re-enable Command Queue */ unsigned int erase_size; /* erase size in sectors */ diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 4106fbc5b4b32..b6b688b229ea9 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -505,33 +505,37 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw); * the old generation, is incremented when all its bins become empty. * * There are four operations: - * 1. MEMCG_LRU_HEAD, which moves an memcg to the head of a random bin in its + * 1. MEMCG_LRU_HEAD, which moves a memcg to the head of a random bin in its * current generation (old or young) and updates its "seg" to "head"; - * 2. MEMCG_LRU_TAIL, which moves an memcg to the tail of a random bin in its + * 2. MEMCG_LRU_TAIL, which moves a memcg to the tail of a random bin in its * current generation (old or young) and updates its "seg" to "tail"; - * 3. MEMCG_LRU_OLD, which moves an memcg to the head of a random bin in the old + * 3. MEMCG_LRU_OLD, which moves a memcg to the head of a random bin in the old * generation, updates its "gen" to "old" and resets its "seg" to "default"; - * 4. MEMCG_LRU_YOUNG, which moves an memcg to the tail of a random bin in the + * 4. MEMCG_LRU_YOUNG, which moves a memcg to the tail of a random bin in the * young generation, updates its "gen" to "young" and resets its "seg" to * "default". * * The events that trigger the above operations are: * 1. Exceeding the soft limit, which triggers MEMCG_LRU_HEAD; - * 2. The first attempt to reclaim an memcg below low, which triggers + * 2. The first attempt to reclaim a memcg below low, which triggers * MEMCG_LRU_TAIL; - * 3. The first attempt to reclaim an memcg below reclaimable size threshold, - * which triggers MEMCG_LRU_TAIL; - * 4. The second attempt to reclaim an memcg below reclaimable size threshold, - * which triggers MEMCG_LRU_YOUNG; - * 5. Attempting to reclaim an memcg below min, which triggers MEMCG_LRU_YOUNG; + * 3. The first attempt to reclaim a memcg offlined or below reclaimable size + * threshold, which triggers MEMCG_LRU_TAIL; + * 4. The second attempt to reclaim a memcg offlined or below reclaimable size + * threshold, which triggers MEMCG_LRU_YOUNG; + * 5. Attempting to reclaim a memcg below min, which triggers MEMCG_LRU_YOUNG; * 6. Finishing the aging on the eviction path, which triggers MEMCG_LRU_YOUNG; - * 7. Offlining an memcg, which triggers MEMCG_LRU_OLD. + * 7. Offlining a memcg, which triggers MEMCG_LRU_OLD. * - * Note that memcg LRU only applies to global reclaim, and the round-robin - * incrementing of their max_seq counters ensures the eventual fairness to all - * eligible memcgs. For memcg reclaim, it still relies on mem_cgroup_iter(). + * Notes: + * 1. Memcg LRU only applies to global reclaim, and the round-robin incrementing + * of their max_seq counters ensures the eventual fairness to all eligible + * memcgs. For memcg reclaim, it still relies on mem_cgroup_iter(). + * 2. There are only two valid generations: old (seq) and young (seq+1). + * MEMCG_NR_GENS is set to three so that when reading the generation counter + * locklessly, a stale value (seq-1) does not wraparound to young. */ -#define MEMCG_NR_GENS 2 +#define MEMCG_NR_GENS 3 #define MEMCG_NR_BINS 8 struct lru_gen_memcg { diff --git a/include/linux/msi.h b/include/linux/msi.h index a50ea79522f85..ddace8c34dcf9 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -547,12 +547,6 @@ enum { MSI_FLAG_ALLOC_SIMPLE_MSI_DESCS = (1 << 5), /* Free MSI descriptors */ MSI_FLAG_FREE_MSI_DESCS = (1 << 6), - /* - * Quirk to handle MSI implementations which do not provide - * masking. Currently known to affect x86, but has to be partially - * handled in the core MSI code. - */ - MSI_FLAG_NOMASK_QUIRK = (1 << 7), /* Mask for the generic functionality */ MSI_GENERIC_FLAGS_MASK = GENMASK(15, 0), diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b646609f09c05..b8e60a20416ba 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1774,6 +1774,13 @@ enum netdev_ml_priv_type { ML_PRIV_CAN, }; +enum netdev_stat_type { + NETDEV_PCPU_STAT_NONE, + NETDEV_PCPU_STAT_LSTATS, /* struct pcpu_lstats */ + NETDEV_PCPU_STAT_TSTATS, /* struct pcpu_sw_netstats */ + NETDEV_PCPU_STAT_DSTATS, /* struct pcpu_dstats */ +}; + /** * struct net_device - The DEVICE structure. * @@ -1968,10 +1975,14 @@ enum netdev_ml_priv_type { * * @ml_priv: Mid-layer private * @ml_priv_type: Mid-layer private type - * @lstats: Loopback statistics - * @tstats: Tunnel statistics - * @dstats: Dummy statistics - * @vstats: Virtual ethernet statistics + * + * @pcpu_stat_type: Type of device statistics which the core should + * allocate/free: none, lstats, tstats, dstats. none + * means the driver is handling statistics allocation/ + * freeing internally. + * @lstats: Loopback statistics: packets, bytes + * @tstats: Tunnel statistics: RX/TX packets, RX/TX bytes + * @dstats: Dummy statistics: RX/TX/drop packets, RX/TX bytes * * @garp_port: GARP * @mrp_port: MRP @@ -2328,6 +2339,7 @@ struct net_device { void *ml_priv; enum netdev_ml_priv_type ml_priv_type; + enum netdev_stat_type pcpu_stat_type:8; union { struct pcpu_lstats __percpu *lstats; struct pcpu_sw_netstats __percpu *tstats; @@ -2725,6 +2737,16 @@ struct pcpu_sw_netstats { struct u64_stats_sync syncp; } __aligned(4 * sizeof(u64)); +struct pcpu_dstats { + u64 rx_packets; + u64 rx_bytes; + u64 rx_drops; + u64 tx_packets; + u64 tx_bytes; + u64 tx_drops; + struct u64_stats_sync syncp; +} __aligned(8 * sizeof(u64)); + struct pcpu_lstats { u64_stats_t packets; u64_stats_t bytes; diff --git a/include/linux/objtool.h b/include/linux/objtool.h index b5440e7da55bf..33212e93f4a63 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -48,13 +48,13 @@ #define ANNOTATE_NOENDBR \ "986: \n\t" \ ".pushsection .discard.noendbr\n\t" \ - ".long 986b - .\n\t" \ + ".long 986b\n\t" \ ".popsection\n\t" #define ASM_REACHABLE \ "998:\n\t" \ ".pushsection .discard.reachable\n\t" \ - ".long 998b - .\n\t" \ + ".long 998b\n\t" \ ".popsection\n\t" #else /* __ASSEMBLY__ */ @@ -66,7 +66,7 @@ #define ANNOTATE_INTRA_FUNCTION_CALL \ 999: \ .pushsection .discard.intra_function_calls; \ - .long 999b - .; \ + .long 999b; \ .popsection; /* @@ -118,7 +118,7 @@ .macro ANNOTATE_NOENDBR .Lhere_\@: .pushsection .discard.noendbr - .long .Lhere_\@ - . + .long .Lhere_\@ .popsection .endm @@ -142,7 +142,7 @@ .macro REACHABLE .Lhere_\@: .pushsection .discard.reachable - .long .Lhere_\@ - . + .long .Lhere_\@ .popsection .endm diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 351c3b7f93a14..8c9608b217b00 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -204,6 +204,8 @@ enum mapping_flags { AS_NO_WRITEBACK_TAGS = 5, AS_LARGE_FOLIO_SUPPORT = 6, AS_RELEASE_ALWAYS, /* Call ->release_folio(), even if no private data */ + AS_STABLE_WRITES, /* must wait for writeback before modifying + folio contents */ }; /** @@ -289,6 +291,21 @@ static inline void mapping_clear_release_always(struct address_space *mapping) clear_bit(AS_RELEASE_ALWAYS, &mapping->flags); } +static inline bool mapping_stable_writes(const struct address_space *mapping) +{ + return test_bit(AS_STABLE_WRITES, &mapping->flags); +} + +static inline void mapping_set_stable_writes(struct address_space *mapping) +{ + set_bit(AS_STABLE_WRITES, &mapping->flags); +} + +static inline void mapping_clear_stable_writes(struct address_space *mapping) +{ + clear_bit(AS_STABLE_WRITES, &mapping->flags); +} + static inline gfp_t mapping_gfp_mask(struct address_space * mapping) { return mapping->gfp_mask; diff --git a/include/linux/pci.h b/include/linux/pci.h index b56417276042d..1596b1205b8d8 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1803,6 +1803,7 @@ extern bool pcie_ports_native; int pci_disable_link_state(struct pci_dev *pdev, int state); int pci_disable_link_state_locked(struct pci_dev *pdev, int state); int pci_enable_link_state(struct pci_dev *pdev, int state); +int pci_enable_link_state_locked(struct pci_dev *pdev, int state); void pcie_no_aspm(void); bool pcie_aspm_support_enabled(void); bool pcie_aspm_enabled(struct pci_dev *pdev); @@ -1813,6 +1814,8 @@ static inline int pci_disable_link_state_locked(struct pci_dev *pdev, int state) { return 0; } static inline int pci_enable_link_state(struct pci_dev *pdev, int state) { return 0; } +static inline int pci_enable_link_state_locked(struct pci_dev *pdev, int state) +{ return 0; } static inline void pcie_no_aspm(void) { } static inline bool pcie_aspm_support_enabled(void) { return false; } static inline bool pcie_aspm_enabled(struct pci_dev *pdev) { return false; } diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 3a8e24e9a93f9..fe4a3589bb3fd 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -180,6 +180,8 @@ #define PCI_DEVICE_ID_BERKOM_A4T 0xffa4 #define PCI_DEVICE_ID_BERKOM_SCITEL_QUADRO 0xffa8 +#define PCI_VENDOR_ID_ITTIM 0x0b48 + #define PCI_VENDOR_ID_COMPAQ 0x0e11 #define PCI_DEVICE_ID_COMPAQ_TOKENRING 0x0508 #define PCI_DEVICE_ID_COMPAQ_TACHYON 0xa0fc diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 16913318af930..e846f87e2d099 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -843,11 +843,11 @@ struct perf_event { }; /* - * ,-----------------------[1:n]----------------------. - * V V - * perf_event_context <-[1:n]-> perf_event_pmu_context <--- perf_event - * ^ ^ | | - * `--------[1:n]---------' `-[n:1]-> pmu <-[1:n]-' + * ,-----------------------[1:n]------------------------. + * V V + * perf_event_context <-[1:n]-> perf_event_pmu_context <-[1:n]- perf_event + * | | + * `--[n:1]-> pmu <-[1:n]--' * * * struct perf_event_pmu_context lifetime is refcount based and RCU freed @@ -865,6 +865,9 @@ struct perf_event { * ctx->mutex pinning the configuration. Since we hold a reference on * group_leader (through the filedesc) it can't go away, therefore it's * associated pmu_ctx must exist and cannot change due to ctx->mutex. + * + * perf_event holds a refcount on perf_event_context + * perf_event holds a refcount on perf_event_pmu_context */ struct perf_event_pmu_context { struct pmu *pmu; diff --git a/include/linux/preempt.h b/include/linux/preempt.h index 1424670df161d..9aa6358a1a16b 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -99,14 +99,21 @@ static __always_inline unsigned char interrupt_context_level(void) return level; } +/* + * These macro definitions avoid redundant invocations of preempt_count() + * because such invocations would result in redundant loads given that + * preempt_count() is commonly implemented with READ_ONCE(). + */ + #define nmi_count() (preempt_count() & NMI_MASK) #define hardirq_count() (preempt_count() & HARDIRQ_MASK) #ifdef CONFIG_PREEMPT_RT # define softirq_count() (current->softirq_disable_cnt & SOFTIRQ_MASK) +# define irq_count() ((preempt_count() & (NMI_MASK | HARDIRQ_MASK)) | softirq_count()) #else # define softirq_count() (preempt_count() & SOFTIRQ_MASK) +# define irq_count() (preempt_count() & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_MASK)) #endif -#define irq_count() (nmi_count() | hardirq_count() | softirq_count()) /* * Macros to retrieve the current execution context: @@ -119,7 +126,11 @@ static __always_inline unsigned char interrupt_context_level(void) #define in_nmi() (nmi_count()) #define in_hardirq() (hardirq_count()) #define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET) -#define in_task() (!(in_nmi() | in_hardirq() | in_serving_softirq())) +#ifdef CONFIG_PREEMPT_RT +# define in_task() (!((preempt_count() & (NMI_MASK | HARDIRQ_MASK)) | in_serving_softirq())) +#else +# define in_task() (!(preempt_count() & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET))) +#endif /* * The following macros are deprecated and should not be used in new code: diff --git a/include/linux/pwm.h b/include/linux/pwm.h index d2f9f690a9c14..fe0f38ce1bdee 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -41,8 +41,8 @@ struct pwm_args { }; enum { - PWMF_REQUESTED = 1 << 0, - PWMF_EXPORTED = 1 << 1, + PWMF_REQUESTED = 0, + PWMF_EXPORTED = 1, }; /* diff --git a/include/linux/rethook.h b/include/linux/rethook.h index 26b6f3c81a763..544e1bbfad284 100644 --- a/include/linux/rethook.h +++ b/include/linux/rethook.h @@ -29,7 +29,12 @@ typedef void (*rethook_handler_t) (struct rethook_node *, void *, unsigned long, */ struct rethook { void *data; - rethook_handler_t handler; + /* + * To avoid sparse warnings, this uses a raw function pointer with + * __rcu, instead of rethook_handler_t. But this must be same as + * rethook_handler_t. + */ + void (__rcu *handler) (struct rethook_node *, void *, unsigned long, struct pt_regs *); struct freelist_head pool; refcount_t ref; struct rcu_head rcu; diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h index 0ee96ea7a0e90..1b37fa8fc723d 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -91,4 +91,14 @@ static inline int get_dumpable(struct mm_struct *mm) MMF_DISABLE_THP_MASK | MMF_HAS_MDWE_MASK) #define MMF_VM_MERGE_ANY 29 +#define MMF_HAS_MDWE_NO_INHERIT 30 + +static inline unsigned long mmf_init_flags(unsigned long flags) +{ + if (flags & (1UL << MMF_HAS_MDWE_NO_INHERIT)) + flags &= ~((1UL << MMF_HAS_MDWE) | + (1UL << MMF_HAS_MDWE_NO_INHERIT)); + return flags & MMF_INIT_MASK; +} + #endif /* _LINUX_SCHED_COREDUMP_H */ diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index e6fe4f73ffe62..71923ae63b014 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -97,10 +97,17 @@ struct scmi_clk_proto_ops { u32 clk_id); }; +struct scmi_perf_domain_info { + char name[SCMI_MAX_STR_SIZE]; + bool set_perf; +}; + /** * struct scmi_perf_proto_ops - represents the various operations provided * by SCMI Performance Protocol * + * @num_domains_get: gets the number of supported performance domains + * @info_get: get the information of a performance domain * @limits_set: sets limits on the performance level of a domain * @limits_get: gets limits on the performance level of a domain * @level_set: sets the performance level of a domain @@ -120,6 +127,9 @@ struct scmi_clk_proto_ops { * or in some other (abstract) scale */ struct scmi_perf_proto_ops { + int (*num_domains_get)(const struct scmi_protocol_handle *ph); + const struct scmi_perf_domain_info __must_check *(*info_get) + (const struct scmi_protocol_handle *ph, u32 domain); int (*limits_set)(const struct scmi_protocol_handle *ph, u32 domain, u32 max_perf, u32 min_perf); int (*limits_get)(const struct scmi_protocol_handle *ph, u32 domain, diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index c1637515a8a41..c953b8c0d2f43 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -106,6 +106,7 @@ struct sk_psock { struct mutex work_mutex; struct sk_psock_work_state work_state; struct delayed_work work; + struct sock *sk_pair; struct rcu_work rwork; }; diff --git a/include/linux/socket.h b/include/linux/socket.h index 39b74d83c7c4a..cfcb7e2c3813f 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -383,6 +383,7 @@ struct ucred { #define SOL_MPTCP 284 #define SOL_MCTP 285 #define SOL_SMC 286 +#define SOL_VSOCK 287 /* IPX options */ #define IPX_TYPE 1 diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 7f8b478fdeb3d..8cc7a99927f95 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -566,6 +566,7 @@ struct spi_controller { #define SPI_CONTROLLER_MUST_RX BIT(3) /* Requires rx */ #define SPI_CONTROLLER_MUST_TX BIT(4) /* Requires tx */ #define SPI_CONTROLLER_GPIO_SS BIT(5) /* GPIO CS must select slave */ +#define SPI_CONTROLLER_SUSPENDED BIT(6) /* Currently suspended */ /* Flag indicating if the allocation of this struct is devres-managed */ bool devm_allocated; diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index ce89cc3e49135..e3f7ee169c086 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -174,6 +174,7 @@ struct stmmac_fpe_cfg { bool hs_enable; /* FPE handshake enable */ enum stmmac_fpe_state lp_fpe_state; /* Link Partner FPE state */ enum stmmac_fpe_state lo_fpe_state; /* Local station FPE state */ + u32 fpe_csr; /* MAC_FPE_CTRL_STS reg cache */ }; struct stmmac_safety_feature_cfg { diff --git a/include/linux/string.h b/include/linux/string.h index 9e3cb6923b0ef..5077776e995e0 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -5,7 +5,9 @@ #include /* for inline */ #include /* for size_t */ #include /* for NULL */ +#include /* for ERR_PTR() */ #include /* for E2BIG */ +#include /* for check_mul_overflow() */ #include #include @@ -14,6 +16,44 @@ extern void *memdup_user(const void __user *, size_t); extern void *vmemdup_user(const void __user *, size_t); extern void *memdup_user_nul(const void __user *, size_t); +/** + * memdup_array_user - duplicate array from user space + * @src: source address in user space + * @n: number of array members to copy + * @size: size of one array member + * + * Return: an ERR_PTR() on failure. Result is physically + * contiguous, to be freed by kfree(). + */ +static inline void *memdup_array_user(const void __user *src, size_t n, size_t size) +{ + size_t nbytes; + + if (check_mul_overflow(n, size, &nbytes)) + return ERR_PTR(-EOVERFLOW); + + return memdup_user(src, nbytes); +} + +/** + * vmemdup_array_user - duplicate array from user space + * @src: source address in user space + * @n: number of array members to copy + * @size: size of one array member + * + * Return: an ERR_PTR() on failure. Result may be not + * physically contiguous. Use kvfree() to free. + */ +static inline void *vmemdup_array_user(const void __user *src, size_t n, size_t size) +{ + size_t nbytes; + + if (check_mul_overflow(n, size, &nbytes)) + return ERR_PTR(-EOVERFLOW); + + return vmemdup_user(src, nbytes); +} + /* * Include machine specific inline routines */ diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index af7358277f1c3..e9d4377d03c6e 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -92,6 +92,7 @@ struct rpc_clnt { }; const struct cred *cl_cred; unsigned int cl_max_connect; /* max number of transports not to the same IP */ + struct super_block *pipefs_sb; }; /* diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 09d7429d67c0e..61b40ea81f4d3 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -242,6 +242,7 @@ extern void __register_sysctl_init(const char *path, struct ctl_table *table, extern struct ctl_table_header *register_sysctl_mount_point(const char *path); void do_sysctl_args(void); +bool sysctl_is_alias(char *param); int do_proc_douintvec(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos, int (*conv)(unsigned long *lvalp, @@ -287,6 +288,11 @@ static inline void setup_sysctl_set(struct ctl_table_set *p, static inline void do_sysctl_args(void) { } + +static inline bool sysctl_is_alias(char *param) +{ + return false; +} #endif /* CONFIG_SYSCTL */ int sysctl_max_threads(struct ctl_table *table, int write, void *buffer, diff --git a/include/linux/torture.h b/include/linux/torture.h index bb466eec01e42..017f0f710815a 100644 --- a/include/linux/torture.h +++ b/include/linux/torture.h @@ -81,7 +81,8 @@ static inline void torture_random_init(struct torture_random_state *trsp) } /* Definitions for high-resolution-timer sleeps. */ -int torture_hrtimeout_ns(ktime_t baset_ns, u32 fuzzt_ns, struct torture_random_state *trsp); +int torture_hrtimeout_ns(ktime_t baset_ns, u32 fuzzt_ns, const enum hrtimer_mode mode, + struct torture_random_state *trsp); int torture_hrtimeout_us(u32 baset_us, u32 fuzzt_ns, struct torture_random_state *trsp); int torture_hrtimeout_ms(u32 baset_ms, u32 fuzzt_us, struct torture_random_state *trsp); int torture_hrtimeout_jiffies(u32 baset_j, struct torture_random_state *trsp); diff --git a/include/linux/usb/phy.h b/include/linux/usb/phy.h index b513749582d77..e4de6bc1f69b6 100644 --- a/include/linux/usb/phy.h +++ b/include/linux/usb/phy.h @@ -144,10 +144,6 @@ struct usb_phy { */ int (*set_wakeup)(struct usb_phy *x, bool enabled); - /* notify phy port status change */ - int (*notify_port_status)(struct usb_phy *x, int port, - u16 portstatus, u16 portchange); - /* notify phy connect status change */ int (*notify_connect)(struct usb_phy *x, enum usb_device_speed speed); @@ -320,15 +316,6 @@ usb_phy_set_wakeup(struct usb_phy *x, bool enabled) return 0; } -static inline int -usb_phy_notify_port_status(struct usb_phy *x, int port, u16 portstatus, u16 portchange) -{ - if (x && x->notify_port_status) - return x->notify_port_status(x, port, portstatus, portchange); - else - return 0; -} - static inline int usb_phy_notify_connect(struct usb_phy *x, enum usb_device_speed speed) { diff --git a/include/linux/usb/r8152.h b/include/linux/usb/r8152.h index 287e9d83fb8bc..33a4c146dc19c 100644 --- a/include/linux/usb/r8152.h +++ b/include/linux/usb/r8152.h @@ -30,6 +30,7 @@ #define VENDOR_ID_NVIDIA 0x0955 #define VENDOR_ID_TPLINK 0x2357 #define VENDOR_ID_DLINK 0x2001 +#define VENDOR_ID_ASUS 0x0b05 #if IS_REACHABLE(CONFIG_USB_RTL8152) extern u8 rtl8152_get_version(struct usb_interface *intf); diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 454e9295970c4..a65b2513f8cdc 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -289,16 +289,12 @@ void vfio_combine_iova_ranges(struct rb_root_cached *root, u32 cur_nodes, /* * External user API */ -#if IS_ENABLED(CONFIG_VFIO_GROUP) struct iommu_group *vfio_file_iommu_group(struct file *file); + +#if IS_ENABLED(CONFIG_VFIO_GROUP) bool vfio_file_is_group(struct file *file); bool vfio_file_has_dev(struct file *file, struct vfio_device *device); #else -static inline struct iommu_group *vfio_file_iommu_group(struct file *file) -{ - return NULL; -} - static inline bool vfio_file_is_group(struct file *file) { return false; diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 1c1d06804d450..24b1e5070f4d4 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -274,18 +274,16 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } * to generate better code. */ #ifdef CONFIG_LOCKDEP -#define __INIT_WORK(_work, _func, _onstack) \ +#define __INIT_WORK_KEY(_work, _func, _onstack, _key) \ do { \ - static struct lock_class_key __key; \ - \ __init_work((_work), _onstack); \ (_work)->data = (atomic_long_t) WORK_DATA_INIT(); \ - lockdep_init_map(&(_work)->lockdep_map, "(work_completion)"#_work, &__key, 0); \ + lockdep_init_map(&(_work)->lockdep_map, "(work_completion)"#_work, (_key), 0); \ INIT_LIST_HEAD(&(_work)->entry); \ (_work)->func = (_func); \ } while (0) #else -#define __INIT_WORK(_work, _func, _onstack) \ +#define __INIT_WORK_KEY(_work, _func, _onstack, _key) \ do { \ __init_work((_work), _onstack); \ (_work)->data = (atomic_long_t) WORK_DATA_INIT(); \ @@ -294,12 +292,22 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; } } while (0) #endif +#define __INIT_WORK(_work, _func, _onstack) \ + do { \ + static __maybe_unused struct lock_class_key __key; \ + \ + __INIT_WORK_KEY(_work, _func, _onstack, &__key); \ + } while (0) + #define INIT_WORK(_work, _func) \ __INIT_WORK((_work), (_func), 0) #define INIT_WORK_ONSTACK(_work, _func) \ __INIT_WORK((_work), (_func), 1) +#define INIT_WORK_ONSTACK_KEY(_work, _func, _key) \ + __INIT_WORK_KEY((_work), (_func), 1, _key) + #define __INIT_DELAYED_WORK(_work, _func, _tflags) \ do { \ INIT_WORK(&(_work)->work, (_func)); \ @@ -693,8 +701,32 @@ static inline long work_on_cpu_safe(int cpu, long (*fn)(void *), void *arg) return fn(arg); } #else -long work_on_cpu(int cpu, long (*fn)(void *), void *arg); -long work_on_cpu_safe(int cpu, long (*fn)(void *), void *arg); +long work_on_cpu_key(int cpu, long (*fn)(void *), + void *arg, struct lock_class_key *key); +/* + * A new key is defined for each caller to make sure the work + * associated with the function doesn't share its locking class. + */ +#define work_on_cpu(_cpu, _fn, _arg) \ +({ \ + static struct lock_class_key __key; \ + \ + work_on_cpu_key(_cpu, _fn, _arg, &__key); \ +}) + +long work_on_cpu_safe_key(int cpu, long (*fn)(void *), + void *arg, struct lock_class_key *key); + +/* + * A new key is defined for each caller to make sure the work + * associated with the function doesn't share its locking class. + */ +#define work_on_cpu_safe(_cpu, _fn, _arg) \ +({ \ + static struct lock_class_key __key; \ + \ + work_on_cpu_safe_key(_cpu, _fn, _arg, &__key); \ +}) #endif /* CONFIG_SMP */ #ifdef CONFIG_FREEZER diff --git a/include/media/ipu-bridge.h b/include/media/ipu-bridge.h index bdc654a455216..783bda6d5cc3f 100644 --- a/include/media/ipu-bridge.h +++ b/include/media/ipu-bridge.h @@ -108,7 +108,7 @@ struct ipu_node_names { char ivsc_sensor_port[7]; char ivsc_ipu_port[7]; char endpoint[11]; - char remote_port[7]; + char remote_port[9]; char vcm[16]; }; diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 82da55101b5a3..61ebe723ee4d5 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -31,17 +31,22 @@ struct prefix_info { __u8 length; __u8 prefix_len; + union __packed { + __u8 flags; + struct __packed { #if defined(__BIG_ENDIAN_BITFIELD) - __u8 onlink : 1, + __u8 onlink : 1, autoconf : 1, reserved : 6; #elif defined(__LITTLE_ENDIAN_BITFIELD) - __u8 reserved : 6, + __u8 reserved : 6, autoconf : 1, onlink : 1; #else #error "Please fix " #endif + }; + }; __be32 valid; __be32 prefered; __be32 reserved2; @@ -49,6 +54,9 @@ struct prefix_info { struct in6_addr prefix; }; +/* rfc4861 4.6.2: IPv6 PIO is 32 bytes in size */ +static_assert(sizeof(struct prefix_info) == 32); + #include #include #include diff --git a/include/net/af_unix.h b/include/net/af_unix.h index 824c258143a3a..49c4640027d8a 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -75,6 +75,7 @@ struct unix_sock { }; #define unix_sk(ptr) container_of_const(ptr, struct unix_sock, sk) +#define unix_peer(sk) (unix_sk(sk)->peer) #define peer_wait peer_wq.wait diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 7fa95b72e5c85..7a4be33bd07aa 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -189,6 +189,7 @@ struct blocked_key { struct smp_csrk { bdaddr_t bdaddr; u8 bdaddr_type; + u8 link_type; u8 type; u8 val[16]; }; @@ -198,6 +199,7 @@ struct smp_ltk { struct rcu_head rcu; bdaddr_t bdaddr; u8 bdaddr_type; + u8 link_type; u8 authenticated; u8 type; u8 enc_size; @@ -212,6 +214,7 @@ struct smp_irk { bdaddr_t rpa; bdaddr_t bdaddr; u8 addr_type; + u8 link_type; u8 val[16]; }; @@ -219,6 +222,8 @@ struct link_key { struct list_head list; struct rcu_head rcu; bdaddr_t bdaddr; + u8 bdaddr_type; + u8 link_type; u8 type; u8 val[HCI_LINK_KEY_SIZE]; u8 pin_len; @@ -1227,11 +1232,11 @@ static inline struct hci_conn *hci_conn_hash_lookup_cis(struct hci_dev *hdev, continue; /* Match CIG ID if set */ - if (cig != BT_ISO_QOS_CIG_UNSET && cig != c->iso_qos.ucast.cig) + if (cig != c->iso_qos.ucast.cig) continue; /* Match CIS ID if set */ - if (id != BT_ISO_QOS_CIS_UNSET && id != c->iso_qos.ucast.cis) + if (id != c->iso_qos.ucast.cis) continue; /* Match destination address if set */ diff --git a/include/net/genetlink.h b/include/net/genetlink.h index e18a4c0d69eed..c53244f204370 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -12,10 +12,12 @@ * struct genl_multicast_group - generic netlink multicast group * @name: name of the multicast group, names are per-family * @flags: GENL_* flags (%GENL_ADMIN_PERM or %GENL_UNS_ADMIN_PERM) + * @cap_sys_admin: whether %CAP_SYS_ADMIN is required for binding */ struct genl_multicast_group { char name[GENL_NAMSIZ]; u8 flags; + u8 cap_sys_admin:1; }; struct genl_split_ops; diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index c8490729b4aea..31bf475eca762 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -22,10 +22,6 @@ #define IF_RS_SENT 0x10 #define IF_READY 0x80000000 -/* prefix flags */ -#define IF_PREFIX_ONLINK 0x01 -#define IF_PREFIX_AUTOCONF 0x02 - enum { INET6_IFADDR_STATE_PREDAD, INET6_IFADDR_STATE_DAD, diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 1ba9f4ddf2f6d..9ba6413fd2e3e 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -179,9 +179,6 @@ struct fib6_info { refcount_t fib6_ref; unsigned long expires; - - struct hlist_node gc_link; - struct dst_metrics *fib6_metrics; #define fib6_pmtu fib6_metrics->metrics[RTAX_MTU-1] @@ -250,6 +247,19 @@ static inline bool fib6_requires_src(const struct fib6_info *rt) return rt->fib6_src.plen > 0; } +static inline void fib6_clean_expires(struct fib6_info *f6i) +{ + f6i->fib6_flags &= ~RTF_EXPIRES; + f6i->expires = 0; +} + +static inline void fib6_set_expires(struct fib6_info *f6i, + unsigned long expires) +{ + f6i->expires = expires; + f6i->fib6_flags |= RTF_EXPIRES; +} + static inline bool fib6_check_expired(const struct fib6_info *f6i) { if (f6i->fib6_flags & RTF_EXPIRES) @@ -257,11 +267,6 @@ static inline bool fib6_check_expired(const struct fib6_info *f6i) return false; } -static inline bool fib6_has_expires(const struct fib6_info *f6i) -{ - return f6i->fib6_flags & RTF_EXPIRES; -} - /* Function to safely get fn->fn_sernum for passed in rt * and store result in passed in cookie. * Return true if we can get cookie safely @@ -383,7 +388,6 @@ struct fib6_table { struct inet_peer_base tb6_peers; unsigned int flags; unsigned int fib_seq; - struct hlist_head tb6_gc_hlist; /* GC candidates */ #define RT6_TABLE_HAS_DFLT_ROUTER BIT(0) }; @@ -500,48 +504,6 @@ void fib6_gc_cleanup(void); int fib6_init(void); -/* fib6_info must be locked by the caller, and fib6_info->fib6_table can be - * NULL. - */ -static inline void fib6_set_expires_locked(struct fib6_info *f6i, - unsigned long expires) -{ - struct fib6_table *tb6; - - tb6 = f6i->fib6_table; - f6i->expires = expires; - if (tb6 && !fib6_has_expires(f6i)) - hlist_add_head(&f6i->gc_link, &tb6->tb6_gc_hlist); - f6i->fib6_flags |= RTF_EXPIRES; -} - -/* fib6_info must be locked by the caller, and fib6_info->fib6_table can be - * NULL. If fib6_table is NULL, the fib6_info will no be inserted into the - * list of GC candidates until it is inserted into a table. - */ -static inline void fib6_set_expires(struct fib6_info *f6i, - unsigned long expires) -{ - spin_lock_bh(&f6i->fib6_table->tb6_lock); - fib6_set_expires_locked(f6i, expires); - spin_unlock_bh(&f6i->fib6_table->tb6_lock); -} - -static inline void fib6_clean_expires_locked(struct fib6_info *f6i) -{ - if (fib6_has_expires(f6i)) - hlist_del_init(&f6i->gc_link); - f6i->fib6_flags &= ~RTF_EXPIRES; - f6i->expires = 0; -} - -static inline void fib6_clean_expires(struct fib6_info *f6i) -{ - spin_lock_bh(&f6i->fib6_table->tb6_lock); - fib6_clean_expires_locked(f6i); - spin_unlock_bh(&f6i->fib6_table->tb6_lock); -} - struct ipv6_route_iter { struct seq_net_private p; struct fib6_walker w; diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 07022bb0d44d4..0d28172193fa6 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -162,7 +162,7 @@ struct neighbour { struct rcu_head rcu; struct net_device *dev; netdevice_tracker dev_tracker; - u8 primary_key[0]; + u8 primary_key[]; } __randomize_layout; struct neigh_ops { diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index fe1507c1db828..692d5955911c7 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -62,6 +62,8 @@ struct nf_flowtable_type { enum flow_offload_tuple_dir dir, struct nf_flow_rule *flow_rule); void (*free)(struct nf_flowtable *ft); + void (*get)(struct nf_flowtable *ft); + void (*put)(struct nf_flowtable *ft); nf_hookfn *hook; struct module *owner; }; @@ -240,6 +242,11 @@ nf_flow_table_offload_add_cb(struct nf_flowtable *flow_table, } list_add_tail(&block_cb->list, &block->cb_list); + up_write(&flow_table->flow_block_lock); + + if (flow_table->type->get) + flow_table->type->get(flow_table); + return 0; unlock: up_write(&flow_table->flow_block_lock); @@ -262,6 +269,9 @@ nf_flow_table_offload_del_cb(struct nf_flowtable *flow_table, WARN_ON(true); } up_write(&flow_table->flow_block_lock); + + if (flow_table->type->put) + flow_table->type->put(flow_table); } void flow_offload_route_init(struct flow_offload *flow, diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 7c816359d5a98..75972e211ba12 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -178,9 +178,9 @@ static inline __be32 nft_reg_load_be32(const u32 *sreg) return *(__force __be32 *)sreg; } -static inline void nft_reg_store64(u32 *dreg, u64 val) +static inline void nft_reg_store64(u64 *dreg, u64 val) { - put_unaligned(val, (u64 *)dreg); + put_unaligned(val, dreg); } static inline u64 nft_reg_load64(const u32 *sreg) diff --git a/include/net/sock.h b/include/net/sock.h index 92f7ea62a9159..1b7ca8f35dd60 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2006,21 +2006,33 @@ static inline void sk_tx_queue_set(struct sock *sk, int tx_queue) /* sk_tx_queue_mapping accept only upto a 16-bit value */ if (WARN_ON_ONCE((unsigned short)tx_queue >= USHRT_MAX)) return; - sk->sk_tx_queue_mapping = tx_queue; + /* Paired with READ_ONCE() in sk_tx_queue_get() and + * other WRITE_ONCE() because socket lock might be not held. + */ + WRITE_ONCE(sk->sk_tx_queue_mapping, tx_queue); } #define NO_QUEUE_MAPPING USHRT_MAX static inline void sk_tx_queue_clear(struct sock *sk) { - sk->sk_tx_queue_mapping = NO_QUEUE_MAPPING; + /* Paired with READ_ONCE() in sk_tx_queue_get() and + * other WRITE_ONCE() because socket lock might be not held. + */ + WRITE_ONCE(sk->sk_tx_queue_mapping, NO_QUEUE_MAPPING); } static inline int sk_tx_queue_get(const struct sock *sk) { - if (sk && sk->sk_tx_queue_mapping != NO_QUEUE_MAPPING) - return sk->sk_tx_queue_mapping; + if (sk) { + /* Paired with WRITE_ONCE() in sk_tx_queue_clear() + * and sk_tx_queue_set(). + */ + int val = READ_ONCE(sk->sk_tx_queue_mapping); + if (val != NO_QUEUE_MAPPING) + return val; + } return -1; } @@ -2169,7 +2181,7 @@ static inline void __dst_negative_advice(struct sock *sk) if (ndst != dst) { rcu_assign_pointer(sk->sk_dst_cache, ndst); sk_tx_queue_clear(sk); - sk->sk_dst_pending_confirm = 0; + WRITE_ONCE(sk->sk_dst_pending_confirm, 0); } } } @@ -2186,7 +2198,7 @@ __sk_dst_set(struct sock *sk, struct dst_entry *dst) struct dst_entry *old_dst; sk_tx_queue_clear(sk); - sk->sk_dst_pending_confirm = 0; + WRITE_ONCE(sk->sk_dst_pending_confirm, 0); old_dst = rcu_dereference_protected(sk->sk_dst_cache, lockdep_sock_is_held(sk)); rcu_assign_pointer(sk->sk_dst_cache, dst); @@ -2199,7 +2211,7 @@ sk_dst_set(struct sock *sk, struct dst_entry *dst) struct dst_entry *old_dst; sk_tx_queue_clear(sk); - sk->sk_dst_pending_confirm = 0; + WRITE_ONCE(sk->sk_dst_pending_confirm, 0); old_dst = xchg((__force struct dst_entry **)&sk->sk_dst_cache, dst); dst_release(old_dst); } @@ -2786,6 +2798,11 @@ static inline bool sk_is_tcp(const struct sock *sk) return sk->sk_type == SOCK_STREAM && sk->sk_protocol == IPPROTO_TCP; } +static inline bool sk_is_stream_unix(const struct sock *sk) +{ + return sk->sk_family == AF_UNIX && sk->sk_type == SOCK_STREAM; +} + /** * sk_eat_skb - Release a skb if it is no longer needed * @sk: socket to eat this skb from diff --git a/include/net/tc_act/tc_ct.h b/include/net/tc_act/tc_ct.h index b24ea2d9400ba..1dc2f827d0bcf 100644 --- a/include/net/tc_act/tc_ct.h +++ b/include/net/tc_act/tc_ct.h @@ -57,6 +57,11 @@ static inline struct nf_flowtable *tcf_ct_ft(const struct tc_action *a) return to_ct_params(a)->nf_ft; } +static inline struct nf_conntrack_helper *tcf_ct_helper(const struct tc_action *a) +{ + return to_ct_params(a)->helper; +} + #else static inline uint16_t tcf_ct_zone(const struct tc_action *a) { return 0; } static inline int tcf_ct_action(const struct tc_action *a) { return 0; } @@ -64,6 +69,10 @@ static inline struct nf_flowtable *tcf_ct_ft(const struct tc_action *a) { return NULL; } +static inline struct nf_conntrack_helper *tcf_ct_helper(const struct tc_action *a) +{ + return NULL; +} #endif /* CONFIG_NF_CONNTRACK */ #if IS_ENABLED(CONFIG_NET_ACT_CT) diff --git a/include/net/tcp.h b/include/net/tcp.h index 0239e815edf71..a88bf8f6db235 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1480,17 +1480,22 @@ static inline int tcp_full_space(const struct sock *sk) return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf)); } -static inline void tcp_adjust_rcv_ssthresh(struct sock *sk) +static inline void __tcp_adjust_rcv_ssthresh(struct sock *sk, u32 new_ssthresh) { int unused_mem = sk_unused_reserved_mem(sk); struct tcp_sock *tp = tcp_sk(sk); - tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss); + tp->rcv_ssthresh = min(tp->rcv_ssthresh, new_ssthresh); if (unused_mem) tp->rcv_ssthresh = max_t(u32, tp->rcv_ssthresh, tcp_win_from_space(sk, unused_mem)); } +static inline void tcp_adjust_rcv_ssthresh(struct sock *sk) +{ + __tcp_adjust_rcv_ssthresh(sk, 4U * tcp_sk(sk)->advmss); +} + void tcp_cleanup_rbuf(struct sock *sk, int copied); void __tcp_cleanup_rbuf(struct sock *sk, int copied); diff --git a/include/rdma/ib_umem.h b/include/rdma/ib_umem.h index 95896472a82bf..565a850445414 100644 --- a/include/rdma/ib_umem.h +++ b/include/rdma/ib_umem.h @@ -77,6 +77,13 @@ static inline void __rdma_umem_block_iter_start(struct ib_block_iter *biter, { __rdma_block_iter_start(biter, umem->sgt_append.sgt.sgl, umem->sgt_append.sgt.nents, pgsz); + biter->__sg_advance = ib_umem_offset(umem) & ~(pgsz - 1); + biter->__sg_numblocks = ib_umem_num_dma_blocks(umem, pgsz); +} + +static inline bool __rdma_umem_block_iter_next(struct ib_block_iter *biter) +{ + return __rdma_block_iter_next(biter) && biter->__sg_numblocks--; } /** @@ -92,7 +99,7 @@ static inline void __rdma_umem_block_iter_start(struct ib_block_iter *biter, */ #define rdma_umem_for_each_dma_block(umem, biter, pgsz) \ for (__rdma_umem_block_iter_start(biter, umem, pgsz); \ - __rdma_block_iter_next(biter);) + __rdma_umem_block_iter_next(biter);) #ifdef CONFIG_INFINIBAND_USER_MEM diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 533ab92684d81..62f9d126a71ad 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -2846,6 +2846,7 @@ struct ib_block_iter { /* internal states */ struct scatterlist *__sg; /* sg holding the current aligned block */ dma_addr_t __dma_addr; /* unaligned DMA address of this block */ + size_t __sg_numblocks; /* ib_umem_num_dma_blocks() */ unsigned int __sg_nents; /* number of SG entries */ unsigned int __sg_advance; /* number of bytes to advance in sg in next step */ unsigned int __pg_bit; /* alignment of current block */ diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index 03ffe3197e7d1..1422dec938d29 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -167,19 +167,25 @@ struct scsi_device { * power state for system suspend/resume (suspend to RAM and * hibernation) operations. */ - bool manage_system_start_stop; + unsigned manage_system_start_stop:1; /* * If true, let the high-level device driver (sd) manage the device * power state for runtime device suspand and resume operations. */ - bool manage_runtime_start_stop; + unsigned manage_runtime_start_stop:1; /* * If true, let the high-level device driver (sd) manage the device * power state for system shutdown (power off) operations. */ - bool manage_shutdown; + unsigned manage_shutdown:1; + + /* + * If set and if the device is runtime suspended, ask the high-level + * device driver (sd) to force a runtime resume of the device. + */ + unsigned force_runtime_start_on_system_start:1; unsigned removable:1; unsigned changed:1; /* Data invalid due to media change */ diff --git a/include/sound/soc-acpi.h b/include/sound/soc-acpi.h index 6d31d535e8f6d..23d6d6bfb0736 100644 --- a/include/sound/soc-acpi.h +++ b/include/sound/soc-acpi.h @@ -68,6 +68,10 @@ static inline struct snd_soc_acpi_mach *snd_soc_acpi_codec_list(void *arg) * @i2s_link_mask: I2S/TDM links enabled on the board * @num_dai_drivers: number of elements in @dai_drivers * @dai_drivers: pointer to dai_drivers, used e.g. in nocodec mode + * @subsystem_vendor: optional PCI SSID vendor value + * @subsystem_device: optional PCI SSID device value + * @subsystem_id_set: true if a value has been written to + * subsystem_vendor and subsystem_device. */ struct snd_soc_acpi_mach_params { u32 acpi_ipc_irq_index; @@ -80,6 +84,9 @@ struct snd_soc_acpi_mach_params { u32 i2s_link_mask; u32 num_dai_drivers; struct snd_soc_dai_driver *dai_drivers; + unsigned short subsystem_vendor; + unsigned short subsystem_device; + bool subsystem_id_set; }; /** diff --git a/include/sound/soc-card.h b/include/sound/soc-card.h index fc94dfb0021fd..e8ff2e089cd00 100644 --- a/include/sound/soc-card.h +++ b/include/sound/soc-card.h @@ -59,6 +59,43 @@ int snd_soc_card_add_dai_link(struct snd_soc_card *card, void snd_soc_card_remove_dai_link(struct snd_soc_card *card, struct snd_soc_dai_link *dai_link); +#ifdef CONFIG_PCI +static inline void snd_soc_card_set_pci_ssid(struct snd_soc_card *card, + unsigned short vendor, + unsigned short device) +{ + card->pci_subsystem_vendor = vendor; + card->pci_subsystem_device = device; + card->pci_subsystem_set = true; +} + +static inline int snd_soc_card_get_pci_ssid(struct snd_soc_card *card, + unsigned short *vendor, + unsigned short *device) +{ + if (!card->pci_subsystem_set) + return -ENOENT; + + *vendor = card->pci_subsystem_vendor; + *device = card->pci_subsystem_device; + + return 0; +} +#else /* !CONFIG_PCI */ +static inline void snd_soc_card_set_pci_ssid(struct snd_soc_card *card, + unsigned short vendor, + unsigned short device) +{ +} + +static inline int snd_soc_card_get_pci_ssid(struct snd_soc_card *card, + unsigned short *vendor, + unsigned short *device) +{ + return -ENOENT; +} +#endif /* CONFIG_PCI */ + /* device driver data */ static inline void snd_soc_card_set_drvdata(struct snd_soc_card *card, void *data) diff --git a/include/sound/soc-dai.h b/include/sound/soc-dai.h index 5fcfba47d98cc..adcd8719d3435 100644 --- a/include/sound/soc-dai.h +++ b/include/sound/soc-dai.h @@ -370,6 +370,7 @@ struct snd_soc_dai_ops { /* bit field */ unsigned int no_capture_mute:1; + unsigned int mute_unmute_on_trigger:1; }; struct snd_soc_cdai_ops { diff --git a/include/sound/soc.h b/include/sound/soc.h index 37f9d3fe302a6..49ec688eed606 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -932,6 +932,17 @@ struct snd_soc_card { #ifdef CONFIG_DMI char dmi_longname[80]; #endif /* CONFIG_DMI */ + +#ifdef CONFIG_PCI + /* + * PCI does not define 0 as invalid, so pci_subsystem_set indicates + * whether a value has been written to these fields. + */ + unsigned short pci_subsystem_vendor; + unsigned short pci_subsystem_device; + bool pci_subsystem_set; +#endif /* CONFIG_PCI */ + char topology_shortname[32]; struct device *dev; diff --git a/include/sound/sof.h b/include/sound/sof.h index d3c41f87ac319..51294f2ba302c 100644 --- a/include/sound/sof.h +++ b/include/sound/sof.h @@ -64,6 +64,14 @@ struct snd_sof_pdata { const char *name; const char *platform; + /* + * PCI SSID. As PCI does not define 0 as invalid, the subsystem_id_set + * flag indicates that a value has been written to these members. + */ + unsigned short subsystem_vendor; + unsigned short subsystem_device; + bool subsystem_id_set; + struct device *dev; /* diff --git a/include/trace/events/9p.h b/include/trace/events/9p.h index 4dfa6d7f83baa..cd104a1343e2d 100644 --- a/include/trace/events/9p.h +++ b/include/trace/events/9p.h @@ -178,18 +178,21 @@ TRACE_EVENT(9p_protocol_dump, __field( void *, clnt ) __field( __u8, type ) __field( __u16, tag ) - __array( unsigned char, line, P9_PROTO_DUMP_SZ ) + __dynamic_array(unsigned char, line, + min_t(size_t, pdu->capacity, P9_PROTO_DUMP_SZ)) ), TP_fast_assign( __entry->clnt = clnt; __entry->type = pdu->id; __entry->tag = pdu->tag; - memcpy(__entry->line, pdu->sdata, P9_PROTO_DUMP_SZ); + memcpy(__get_dynamic_array(line), pdu->sdata, + __get_dynamic_array_len(line)); ), - TP_printk("clnt %lu %s(tag = %d)\n%.3x: %16ph\n%.3x: %16ph\n", + TP_printk("clnt %lu %s(tag = %d)\n%*ph\n", (unsigned long)__entry->clnt, show_9p_op(__entry->type), - __entry->tag, 0, __entry->line, 16, __entry->line + 16) + __entry->tag, __get_dynamic_array_len(line), + __get_dynamic_array(line)) ); diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 4c53a5ef6257b..f7e537f64db45 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -328,7 +328,7 @@ E_(rxrpc_rtt_tx_ping, "PING") #define rxrpc_rtt_rx_traces \ - EM(rxrpc_rtt_rx_cancel, "CNCL") \ + EM(rxrpc_rtt_rx_other_ack, "OACK") \ EM(rxrpc_rtt_rx_obsolete, "OBSL") \ EM(rxrpc_rtt_rx_lost, "LOST") \ EM(rxrpc_rtt_rx_ping_response, "PONG") \ diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h index 6c80f96049bd0..282e90aeb163c 100644 --- a/include/uapi/linux/fcntl.h +++ b/include/uapi/linux/fcntl.h @@ -116,5 +116,8 @@ #define AT_HANDLE_FID AT_REMOVEDIR /* file handle is needed to compare object identity and may not be usable to open_by_handle_at(2) */ +#if defined(__KERNEL__) +#define AT_GETATTR_NOSEC 0x80000000 +#endif #endif /* _UAPI_LINUX_FCNTL_H */ diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index db92a7202b342..e7418d15fe390 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -209,7 +209,7 @@ * - add FUSE_HAS_EXPIRE_ONLY * * 7.39 - * - add FUSE_DIRECT_IO_RELAX + * - add FUSE_DIRECT_IO_ALLOW_MMAP * - add FUSE_STATX and related structures */ @@ -409,8 +409,7 @@ struct fuse_file_lock { * FUSE_CREATE_SUPP_GROUP: add supplementary group info to create, mkdir, * symlink and mknod (single group that matches parent) * FUSE_HAS_EXPIRE_ONLY: kernel supports expiry-only entry invalidation - * FUSE_DIRECT_IO_RELAX: relax restrictions in FOPEN_DIRECT_IO mode, for now - * allow shared mmap + * FUSE_DIRECT_IO_ALLOW_MMAP: allow shared mmap in FOPEN_DIRECT_IO mode. */ #define FUSE_ASYNC_READ (1 << 0) #define FUSE_POSIX_LOCKS (1 << 1) @@ -449,7 +448,10 @@ struct fuse_file_lock { #define FUSE_HAS_INODE_DAX (1ULL << 33) #define FUSE_CREATE_SUPP_GROUP (1ULL << 34) #define FUSE_HAS_EXPIRE_ONLY (1ULL << 35) -#define FUSE_DIRECT_IO_RELAX (1ULL << 36) +#define FUSE_DIRECT_IO_ALLOW_MMAP (1ULL << 36) + +/* Obsolete alias for FUSE_DIRECT_IO_ALLOW_MMAP */ +#define FUSE_DIRECT_IO_RELAX FUSE_DIRECT_IO_ALLOW_MMAP /** * CUSE INIT request/reply flags diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index 3c36aeade991e..370ed14b1ae09 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -283,7 +283,8 @@ struct prctl_mm_map { /* Memory deny write / execute */ #define PR_SET_MDWE 65 -# define PR_MDWE_REFUSE_EXEC_GAIN 1 +# define PR_MDWE_REFUSE_EXEC_GAIN (1UL << 0) +# define PR_MDWE_NO_INHERIT (1UL << 1) #define PR_GET_MDWE 66 diff --git a/include/uapi/linux/stddef.h b/include/uapi/linux/stddef.h index 5c6c4269f7efe..2ec6f35cda32e 100644 --- a/include/uapi/linux/stddef.h +++ b/include/uapi/linux/stddef.h @@ -27,7 +27,7 @@ union { \ struct { MEMBERS } ATTRS; \ struct TAG { MEMBERS } ATTRS NAME; \ - } + } ATTRS #ifdef __cplusplus /* sizeof(struct{}) is 1 in C++, not 0, can't use C version of the macro. */ diff --git a/include/uapi/linux/v4l2-subdev.h b/include/uapi/linux/v4l2-subdev.h index 4a195b68f28f6..b383c2fe0cf35 100644 --- a/include/uapi/linux/v4l2-subdev.h +++ b/include/uapi/linux/v4l2-subdev.h @@ -239,7 +239,7 @@ struct v4l2_subdev_routing { * set (which is the default), the 'stream' fields will be forced to 0 by the * kernel. */ - #define V4L2_SUBDEV_CLIENT_CAP_STREAMS (1U << 0) + #define V4L2_SUBDEV_CLIENT_CAP_STREAMS (1ULL << 0) /** * struct v4l2_subdev_client_capability - Capabilities of the client accessing diff --git a/include/uapi/linux/vm_sockets.h b/include/uapi/linux/vm_sockets.h index c60ca33eac594..ed07181d4eff9 100644 --- a/include/uapi/linux/vm_sockets.h +++ b/include/uapi/linux/vm_sockets.h @@ -191,4 +191,21 @@ struct sockaddr_vm { #define IOCTL_VM_SOCKETS_GET_LOCAL_CID _IO(7, 0xb9) +/* MSG_ZEROCOPY notifications are encoded in the standard error format, + * sock_extended_err. See Documentation/networking/msg_zerocopy.rst in + * kernel source tree for more details. + */ + +/* 'cmsg_level' field value of 'struct cmsghdr' for notification parsing + * when MSG_ZEROCOPY flag is used on transmissions. + */ + +#define SOL_VSOCK 287 + +/* 'cmsg_type' field value of 'struct cmsghdr' for notification parsing + * when MSG_ZEROCOPY flag is used on transmissions. + */ + +#define VSOCK_RECVERR 1 + #endif /* _UAPI_VM_SOCKETS_H */ diff --git a/include/video/sticore.h b/include/video/sticore.h index 945ad60463a18..012b5b46ad7d0 100644 --- a/include/video/sticore.h +++ b/include/video/sticore.h @@ -232,7 +232,7 @@ struct sti_rom_font { u8 height; u8 font_type; /* language type */ u8 bytes_per_char; - u32 next_font; + s32 next_font; /* note: signed int */ u8 underline_height; u8 underline_pos; u8 res008[2]; diff --git a/init/Makefile b/init/Makefile index ec557ada3c12e..cbac576c57d63 100644 --- a/init/Makefile +++ b/init/Makefile @@ -60,4 +60,5 @@ include/generated/utsversion.h: FORCE $(obj)/version-timestamp.o: include/generated/utsversion.h CFLAGS_version-timestamp.o := -include include/generated/utsversion.h KASAN_SANITIZE_version-timestamp.o := n +KCSAN_SANITIZE_version-timestamp.o := n GCOV_PROFILE_version-timestamp.o := n diff --git a/init/main.c b/init/main.c index 436d73261810b..e24b0780fdff7 100644 --- a/init/main.c +++ b/init/main.c @@ -530,6 +530,10 @@ static int __init unknown_bootoption(char *param, char *val, { size_t len = strlen(param); + /* Handle params aliased to sysctls */ + if (sysctl_is_alias(param)) + return 0; + repair_env_string(param, val); /* Handle obsolete-style parameters */ diff --git a/io_uring/fdinfo.c b/io_uring/fdinfo.c index f04a43044d917..976e9500f6518 100644 --- a/io_uring/fdinfo.c +++ b/io_uring/fdinfo.c @@ -145,13 +145,8 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *f) if (has_lock && (ctx->flags & IORING_SETUP_SQPOLL)) { struct io_sq_data *sq = ctx->sq_data; - if (mutex_trylock(&sq->lock)) { - if (sq->thread) { - sq_pid = task_pid_nr(sq->thread); - sq_cpu = task_cpu(sq->thread); - } - mutex_unlock(&sq->lock); - } + sq_pid = sq->task_pid; + sq_cpu = sq->sq_cpu; } seq_printf(m, "SqThread:\t%d\n", sq_pid); diff --git a/io_uring/fs.c b/io_uring/fs.c index 08e3b175469c6..eccea851dd5a2 100644 --- a/io_uring/fs.c +++ b/io_uring/fs.c @@ -254,7 +254,7 @@ int io_linkat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) newf = u64_to_user_ptr(READ_ONCE(sqe->addr2)); lnk->flags = READ_ONCE(sqe->hardlink_flags); - lnk->oldpath = getname(oldf); + lnk->oldpath = getname_uflags(oldf, lnk->flags); if (IS_ERR(lnk->oldpath)) return PTR_ERR(lnk->oldpath); diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 8d1bc6cdfe712..bb8880d1e084c 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -269,6 +269,7 @@ static __cold void io_fallback_req_func(struct work_struct *work) struct io_kiocb *req, *tmp; struct io_tw_state ts = { .locked = true, }; + percpu_ref_get(&ctx->refs); mutex_lock(&ctx->uring_lock); llist_for_each_entry_safe(req, tmp, node, io_task_work.node) req->io_task_work.func(req, &ts); @@ -276,6 +277,7 @@ static __cold void io_fallback_req_func(struct work_struct *work) return; io_submit_flush_completions(ctx); mutex_unlock(&ctx->uring_lock); + percpu_ref_put(&ctx->refs); } static int io_alloc_hash_table(struct io_hash_table *table, unsigned bits) @@ -323,6 +325,7 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) INIT_LIST_HEAD(&ctx->sqd_list); INIT_LIST_HEAD(&ctx->cq_overflow_list); INIT_LIST_HEAD(&ctx->io_buffers_cache); + INIT_HLIST_HEAD(&ctx->io_buf_list); io_alloc_cache_init(&ctx->rsrc_node_cache, IO_NODE_ALLOC_CACHE_MAX, sizeof(struct io_rsrc_node)); io_alloc_cache_init(&ctx->apoll_cache, IO_ALLOC_CACHE_MAX, @@ -2659,7 +2662,7 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, return READ_ONCE(rings->cq.head) == READ_ONCE(rings->cq.tail) ? ret : 0; } -static void io_mem_free(void *ptr) +void io_mem_free(void *ptr) { if (!ptr) return; @@ -2690,6 +2693,7 @@ static void *__io_uaddr_map(struct page ***pages, unsigned short *npages, { struct page **page_array; unsigned int nr_pages; + void *page_addr; int ret, i; *npages = 0; @@ -2711,27 +2715,29 @@ static void *__io_uaddr_map(struct page ***pages, unsigned short *npages, io_pages_free(&page_array, ret > 0 ? ret : 0); return ret < 0 ? ERR_PTR(ret) : ERR_PTR(-EFAULT); } - /* - * Should be a single page. If the ring is small enough that we can - * use a normal page, that is fine. If we need multiple pages, then - * userspace should use a huge page. That's the only way to guarantee - * that we get contigious memory, outside of just being lucky or - * (currently) having low memory fragmentation. - */ - if (page_array[0] != page_array[ret - 1]) - goto err; - /* - * Can't support mapping user allocated ring memory on 32-bit archs - * where it could potentially reside in highmem. Just fail those with - * -EINVAL, just like we did on kernels that didn't support this - * feature. - */ + page_addr = page_address(page_array[0]); for (i = 0; i < nr_pages; i++) { - if (PageHighMem(page_array[i])) { - ret = -EINVAL; + ret = -EINVAL; + + /* + * Can't support mapping user allocated ring memory on 32-bit + * archs where it could potentially reside in highmem. Just + * fail those with -EINVAL, just like we did on kernels that + * didn't support this feature. + */ + if (PageHighMem(page_array[i])) goto err; - } + + /* + * No support for discontig pages for now, should either be a + * single normal page, or a huge page. Later on we can add + * support for remapping discontig pages, for now we will + * just fail them with EINVAL. + */ + if (page_address(page_array[i]) != page_addr) + goto err; + page_addr += PAGE_SIZE; } *pages = page_array; @@ -2768,7 +2774,7 @@ static void io_rings_free(struct io_ring_ctx *ctx) } } -static void *io_mem_alloc(size_t size) +void *io_mem_alloc(size_t size) { gfp_t gfp = GFP_KERNEL_ACCOUNT | __GFP_ZERO | __GFP_NOWARN | __GFP_COMP; void *ret; @@ -2939,6 +2945,7 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx) ctx->mm_account = NULL; } io_rings_free(ctx); + io_kbuf_mmap_list_free(ctx); percpu_ref_exit(&ctx->refs); free_uid(ctx->user); @@ -3133,12 +3140,7 @@ static __cold void io_ring_exit_work(struct work_struct *work) init_completion(&exit.completion); init_task_work(&exit.task_work, io_tctx_exit_cb); exit.ctx = ctx; - /* - * Some may use context even when all refs and requests have been put, - * and they are free to do so while still holding uring_lock or - * completion_lock, see io_req_task_submit(). Apart from other work, - * this lock/unlock section also waits them to finish. - */ + mutex_lock(&ctx->uring_lock); while (!list_empty(&ctx->tctx_list)) { WARN_ON_ONCE(time_after(jiffies, timeout)); @@ -3433,25 +3435,27 @@ static void *io_uring_validate_mmap_request(struct file *file, struct page *page; void *ptr; - /* Don't allow mmap if the ring was setup without it */ - if (ctx->flags & IORING_SETUP_NO_MMAP) - return ERR_PTR(-EINVAL); - switch (offset & IORING_OFF_MMAP_MASK) { case IORING_OFF_SQ_RING: case IORING_OFF_CQ_RING: + /* Don't allow mmap if the ring was setup without it */ + if (ctx->flags & IORING_SETUP_NO_MMAP) + return ERR_PTR(-EINVAL); ptr = ctx->rings; break; case IORING_OFF_SQES: + /* Don't allow mmap if the ring was setup without it */ + if (ctx->flags & IORING_SETUP_NO_MMAP) + return ERR_PTR(-EINVAL); ptr = ctx->sq_sqes; break; case IORING_OFF_PBUF_RING: { unsigned int bgid; bgid = (offset & ~IORING_OFF_MMAP_MASK) >> IORING_OFF_PBUF_SHIFT; - mutex_lock(&ctx->uring_lock); + rcu_read_lock(); ptr = io_pbuf_get_address(ctx, bgid); - mutex_unlock(&ctx->uring_lock); + rcu_read_unlock(); if (!ptr) return ERR_PTR(-EINVAL); break; diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h index 0bc145614a6e6..d2bad1df347da 100644 --- a/io_uring/io_uring.h +++ b/io_uring/io_uring.h @@ -86,6 +86,9 @@ bool __io_alloc_req_refill(struct io_ring_ctx *ctx); bool io_match_task_safe(struct io_kiocb *head, struct task_struct *task, bool cancel_all); +void *io_mem_alloc(size_t size); +void io_mem_free(void *ptr); + #if defined(CONFIG_PROVE_LOCKING) static inline void io_lockdep_assert_cq_locked(struct io_ring_ctx *ctx) { diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c index f6e5ae026e4be..e8516f3bbbaaa 100644 --- a/io_uring/kbuf.c +++ b/io_uring/kbuf.c @@ -31,19 +31,42 @@ struct io_provide_buf { __u16 bid; }; +static struct io_buffer_list *__io_buffer_get_list(struct io_ring_ctx *ctx, + struct io_buffer_list *bl, + unsigned int bgid) +{ + if (bl && bgid < BGID_ARRAY) + return &bl[bgid]; + + return xa_load(&ctx->io_bl_xa, bgid); +} + +struct io_buf_free { + struct hlist_node list; + void *mem; + size_t size; + int inuse; +}; + static inline struct io_buffer_list *io_buffer_get_list(struct io_ring_ctx *ctx, unsigned int bgid) { - if (ctx->io_bl && bgid < BGID_ARRAY) - return &ctx->io_bl[bgid]; + lockdep_assert_held(&ctx->uring_lock); - return xa_load(&ctx->io_bl_xa, bgid); + return __io_buffer_get_list(ctx, ctx->io_bl, bgid); } static int io_buffer_add_list(struct io_ring_ctx *ctx, struct io_buffer_list *bl, unsigned int bgid) { + /* + * Store buffer group ID and finally mark the list as visible. + * The normal lookup doesn't care about the visibility as we're + * always under the ->uring_lock, but the RCU lookup from mmap does. + */ bl->bgid = bgid; + smp_store_release(&bl->is_ready, 1); + if (bgid < BGID_ARRAY) return 0; @@ -194,21 +217,40 @@ void __user *io_buffer_select(struct io_kiocb *req, size_t *len, static __cold int io_init_bl_list(struct io_ring_ctx *ctx) { + struct io_buffer_list *bl; int i; - ctx->io_bl = kcalloc(BGID_ARRAY, sizeof(struct io_buffer_list), - GFP_KERNEL); - if (!ctx->io_bl) + bl = kcalloc(BGID_ARRAY, sizeof(struct io_buffer_list), GFP_KERNEL); + if (!bl) return -ENOMEM; for (i = 0; i < BGID_ARRAY; i++) { - INIT_LIST_HEAD(&ctx->io_bl[i].buf_list); - ctx->io_bl[i].bgid = i; + INIT_LIST_HEAD(&bl[i].buf_list); + bl[i].bgid = i; } + smp_store_release(&ctx->io_bl, bl); return 0; } +/* + * Mark the given mapped range as free for reuse + */ +static void io_kbuf_mark_free(struct io_ring_ctx *ctx, struct io_buffer_list *bl) +{ + struct io_buf_free *ibf; + + hlist_for_each_entry(ibf, &ctx->io_buf_list, list) { + if (bl->buf_ring == ibf->mem) { + ibf->inuse = 0; + return; + } + } + + /* can't happen... */ + WARN_ON_ONCE(1); +} + static int __io_remove_buffers(struct io_ring_ctx *ctx, struct io_buffer_list *bl, unsigned nbufs) { @@ -221,7 +263,11 @@ static int __io_remove_buffers(struct io_ring_ctx *ctx, if (bl->is_mapped) { i = bl->buf_ring->tail - bl->head; if (bl->is_mmap) { - folio_put(virt_to_folio(bl->buf_ring)); + /* + * io_kbuf_list_free() will free the page(s) at + * ->release() time. + */ + io_kbuf_mark_free(ctx, bl); bl->buf_ring = NULL; bl->is_mmap = 0; } else if (bl->buf_nr_pages) { @@ -270,7 +316,7 @@ void io_destroy_buffers(struct io_ring_ctx *ctx) xa_for_each(&ctx->io_bl_xa, index, bl) { xa_erase(&ctx->io_bl_xa, bl->bgid); __io_remove_buffers(ctx, bl, -1U); - kfree(bl); + kfree_rcu(bl, rcu); } while (!list_empty(&ctx->io_buffers_pages)) { @@ -455,7 +501,16 @@ int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags) INIT_LIST_HEAD(&bl->buf_list); ret = io_buffer_add_list(ctx, bl, p->bgid); if (ret) { - kfree(bl); + /* + * Doesn't need rcu free as it was never visible, but + * let's keep it consistent throughout. Also can't + * be a lower indexed array group, as adding one + * where lookup failed cannot happen. + */ + if (p->bgid >= BGID_ARRAY) + kfree_rcu(bl, rcu); + else + WARN_ON_ONCE(1); goto err; } } @@ -526,19 +581,63 @@ static int io_pin_pbuf_ring(struct io_uring_buf_reg *reg, return -EINVAL; } -static int io_alloc_pbuf_ring(struct io_uring_buf_reg *reg, +/* + * See if we have a suitable region that we can reuse, rather than allocate + * both a new io_buf_free and mem region again. We leave it on the list as + * even a reused entry will need freeing at ring release. + */ +static struct io_buf_free *io_lookup_buf_free_entry(struct io_ring_ctx *ctx, + size_t ring_size) +{ + struct io_buf_free *ibf, *best = NULL; + size_t best_dist; + + hlist_for_each_entry(ibf, &ctx->io_buf_list, list) { + size_t dist; + + if (ibf->inuse || ibf->size < ring_size) + continue; + dist = ibf->size - ring_size; + if (!best || dist < best_dist) { + best = ibf; + if (!dist) + break; + best_dist = dist; + } + } + + return best; +} + +static int io_alloc_pbuf_ring(struct io_ring_ctx *ctx, + struct io_uring_buf_reg *reg, struct io_buffer_list *bl) { - gfp_t gfp = GFP_KERNEL_ACCOUNT | __GFP_ZERO | __GFP_NOWARN | __GFP_COMP; + struct io_buf_free *ibf; size_t ring_size; void *ptr; ring_size = reg->ring_entries * sizeof(struct io_uring_buf_ring); - ptr = (void *) __get_free_pages(gfp, get_order(ring_size)); - if (!ptr) - return -ENOMEM; - bl->buf_ring = ptr; + /* Reuse existing entry, if we can */ + ibf = io_lookup_buf_free_entry(ctx, ring_size); + if (!ibf) { + ptr = io_mem_alloc(ring_size); + if (IS_ERR(ptr)) + return PTR_ERR(ptr); + + /* Allocate and store deferred free entry */ + ibf = kmalloc(sizeof(*ibf), GFP_KERNEL_ACCOUNT); + if (!ibf) { + io_mem_free(ptr); + return -ENOMEM; + } + ibf->mem = ptr; + ibf->size = ring_size; + hlist_add_head(&ibf->list, &ctx->io_buf_list); + } + ibf->inuse = 1; + bl->buf_ring = ibf->mem; bl->is_mapped = 1; bl->is_mmap = 1; return 0; @@ -550,6 +649,8 @@ int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg) struct io_buffer_list *bl, *free_bl = NULL; int ret; + lockdep_assert_held(&ctx->uring_lock); + if (copy_from_user(®, arg, sizeof(reg))) return -EFAULT; @@ -594,7 +695,7 @@ int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg) if (!(reg.flags & IOU_PBUF_RING_MMAP)) ret = io_pin_pbuf_ring(®, bl); else - ret = io_alloc_pbuf_ring(®, bl); + ret = io_alloc_pbuf_ring(ctx, ®, bl); if (!ret) { bl->nr_entries = reg.ring_entries; @@ -604,7 +705,7 @@ int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg) return 0; } - kfree(free_bl); + kfree_rcu(free_bl, rcu); return ret; } @@ -613,6 +714,8 @@ int io_unregister_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg) struct io_uring_buf_reg reg; struct io_buffer_list *bl; + lockdep_assert_held(&ctx->uring_lock); + if (copy_from_user(®, arg, sizeof(reg))) return -EFAULT; if (reg.resv[0] || reg.resv[1] || reg.resv[2]) @@ -629,7 +732,7 @@ int io_unregister_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg) __io_remove_buffers(ctx, bl, -1U); if (bl->bgid >= BGID_ARRAY) { xa_erase(&ctx->io_bl_xa, bl->bgid); - kfree(bl); + kfree_rcu(bl, rcu); } return 0; } @@ -638,9 +741,33 @@ void *io_pbuf_get_address(struct io_ring_ctx *ctx, unsigned long bgid) { struct io_buffer_list *bl; - bl = io_buffer_get_list(ctx, bgid); + bl = __io_buffer_get_list(ctx, smp_load_acquire(&ctx->io_bl), bgid); + if (!bl || !bl->is_mmap) return NULL; + /* + * Ensure the list is fully setup. Only strictly needed for RCU lookup + * via mmap, and in that case only for the array indexed groups. For + * the xarray lookups, it's either visible and ready, or not at all. + */ + if (!smp_load_acquire(&bl->is_ready)) + return NULL; return bl->buf_ring; } + +/* + * Called at or after ->release(), free the mmap'ed buffers that we used + * for memory mapped provided buffer rings. + */ +void io_kbuf_mmap_list_free(struct io_ring_ctx *ctx) +{ + struct io_buf_free *ibf; + struct hlist_node *tmp; + + hlist_for_each_entry_safe(ibf, tmp, &ctx->io_buf_list, list) { + hlist_del(&ibf->list); + io_mem_free(ibf->mem); + kfree(ibf); + } +} diff --git a/io_uring/kbuf.h b/io_uring/kbuf.h index d14345ef61fc8..3d0cb6b8c1ed2 100644 --- a/io_uring/kbuf.h +++ b/io_uring/kbuf.h @@ -15,6 +15,7 @@ struct io_buffer_list { struct page **buf_pages; struct io_uring_buf_ring *buf_ring; }; + struct rcu_head rcu; }; __u16 bgid; @@ -28,6 +29,8 @@ struct io_buffer_list { __u8 is_mapped; /* ring mapped provided buffers, but mmap'ed by application */ __u8 is_mmap; + /* bl is visible from an RCU point of view for lookup */ + __u8 is_ready; }; struct io_buffer { @@ -51,6 +54,8 @@ int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags); int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg); int io_unregister_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg); +void io_kbuf_mmap_list_free(struct io_ring_ctx *ctx); + unsigned int __io_put_kbuf(struct io_kiocb *req, unsigned issue_flags); void io_kbuf_recycle_legacy(struct io_kiocb *req, unsigned issue_flags); diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c index d9c853d105878..dde501abd7196 100644 --- a/io_uring/rsrc.c +++ b/io_uring/rsrc.c @@ -1261,7 +1261,7 @@ int io_import_fixed(int ddir, struct iov_iter *iter, */ const struct bio_vec *bvec = imu->bvec; - if (offset <= bvec->bv_len) { + if (offset < bvec->bv_len) { /* * Note, huge pages buffers consists of one large * bvec entry and should always go this way. The other diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h index 8625181fb87ac..08ac0d8e07ef8 100644 --- a/io_uring/rsrc.h +++ b/io_uring/rsrc.h @@ -77,17 +77,10 @@ int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, int __io_scm_file_account(struct io_ring_ctx *ctx, struct file *file); -#if defined(CONFIG_UNIX) -static inline bool io_file_need_scm(struct file *filp) -{ - return !!unix_get_socket(filp); -} -#else static inline bool io_file_need_scm(struct file *filp) { return false; } -#endif static inline int io_scm_file_account(struct io_ring_ctx *ctx, struct file *file) diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c index bd6c2c7959a5b..65b5dbe3c850e 100644 --- a/io_uring/sqpoll.c +++ b/io_uring/sqpoll.c @@ -214,6 +214,7 @@ static bool io_sqd_handle_event(struct io_sq_data *sqd) did_sig = get_signal(&ksig); cond_resched(); mutex_lock(&sqd->lock); + sqd->sq_cpu = raw_smp_processor_id(); } return did_sig || test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state); } @@ -229,10 +230,15 @@ static int io_sq_thread(void *data) snprintf(buf, sizeof(buf), "iou-sqp-%d", sqd->task_pid); set_task_comm(current, buf); - if (sqd->sq_cpu != -1) + /* reset to our pid after we've set task_comm, for fdinfo */ + sqd->task_pid = current->pid; + + if (sqd->sq_cpu != -1) { set_cpus_allowed_ptr(current, cpumask_of(sqd->sq_cpu)); - else + } else { set_cpus_allowed_ptr(current, cpu_online_mask); + sqd->sq_cpu = raw_smp_processor_id(); + } mutex_lock(&sqd->lock); while (1) { @@ -261,6 +267,7 @@ static int io_sq_thread(void *data) mutex_unlock(&sqd->lock); cond_resched(); mutex_lock(&sqd->lock); + sqd->sq_cpu = raw_smp_processor_id(); } continue; } @@ -294,6 +301,7 @@ static int io_sq_thread(void *data) mutex_unlock(&sqd->lock); schedule(); mutex_lock(&sqd->lock); + sqd->sq_cpu = raw_smp_processor_id(); } list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) atomic_andnot(IORING_SQ_NEED_WAKEUP, diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c index 537795fddc87d..5fa19861cda54 100644 --- a/io_uring/uring_cmd.c +++ b/io_uring/uring_cmd.c @@ -7,7 +7,7 @@ #include #include -#include +#include #include "io_uring.h" #include "rsrc.h" diff --git a/kernel/Kconfig.kexec b/kernel/Kconfig.kexec index 9bfe68fe96762..37e488d5b4fc0 100644 --- a/kernel/Kconfig.kexec +++ b/kernel/Kconfig.kexec @@ -36,6 +36,8 @@ config KEXEC config KEXEC_FILE bool "Enable kexec file based system call" depends on ARCH_SUPPORTS_KEXEC_FILE + select CRYPTO + select CRYPTO_SHA256 select KEXEC_CORE help This is new version of kexec system call. This system call is @@ -94,10 +96,8 @@ config KEXEC_JUMP config CRASH_DUMP bool "kernel crash dumps" depends on ARCH_SUPPORTS_CRASH_DUMP - depends on ARCH_SUPPORTS_KEXEC select CRASH_CORE select KEXEC_CORE - select KEXEC help Generate crash dump after being started by kexec. This should be normally only set in special crash dump kernels diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c index 65075f1e4ac8c..7a98cd176a127 100644 --- a/kernel/audit_watch.c +++ b/kernel/audit_watch.c @@ -527,11 +527,18 @@ int audit_exe_compare(struct task_struct *tsk, struct audit_fsnotify_mark *mark) unsigned long ino; dev_t dev; - exe_file = get_task_exe_file(tsk); + /* only do exe filtering if we are recording @current events/records */ + if (tsk != current) + return 0; + + if (!current->mm) + return 0; + exe_file = get_mm_exe_file(current->mm); if (!exe_file) return 0; ino = file_inode(exe_file)->i_ino; dev = file_inode(exe_file)->i_sb->s_dev; fput(exe_file); + return audit_mark_compare(mark, ino, dev); } diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 2058e89b5ddd0..c85ff9162a5cd 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -1012,11 +1012,16 @@ static void prog_array_map_poke_untrack(struct bpf_map *map, mutex_unlock(&aux->poke_mutex); } +void __weak bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke, + struct bpf_prog *new, struct bpf_prog *old) +{ + WARN_ON_ONCE(1); +} + static void prog_array_map_poke_run(struct bpf_map *map, u32 key, struct bpf_prog *old, struct bpf_prog *new) { - u8 *old_addr, *new_addr, *old_bypass_addr; struct prog_poke_elem *elem; struct bpf_array_aux *aux; @@ -1025,7 +1030,7 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key, list_for_each_entry(elem, &aux->poke_progs, list) { struct bpf_jit_poke_descriptor *poke; - int i, ret; + int i; for (i = 0; i < elem->aux->size_poke_tab; i++) { poke = &elem->aux->poke_tab[i]; @@ -1044,21 +1049,10 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key, * activated, so tail call updates can arrive from here * while JIT is still finishing its final fixup for * non-activated poke entries. - * 3) On program teardown, the program's kallsym entry gets - * removed out of RCU callback, but we can only untrack - * from sleepable context, therefore bpf_arch_text_poke() - * might not see that this is in BPF text section and - * bails out with -EINVAL. As these are unreachable since - * RCU grace period already passed, we simply skip them. - * 4) Also programs reaching refcount of zero while patching + * 3) Also programs reaching refcount of zero while patching * is in progress is okay since we're protected under * poke_mutex and untrack the programs before the JIT - * buffer is freed. When we're still in the middle of - * patching and suddenly kallsyms entry of the program - * gets evicted, we just skip the rest which is fine due - * to point 3). - * 5) Any other error happening below from bpf_arch_text_poke() - * is a unexpected bug. + * buffer is freed. */ if (!READ_ONCE(poke->tailcall_target_stable)) continue; @@ -1068,39 +1062,7 @@ static void prog_array_map_poke_run(struct bpf_map *map, u32 key, poke->tail_call.key != key) continue; - old_bypass_addr = old ? NULL : poke->bypass_addr; - old_addr = old ? (u8 *)old->bpf_func + poke->adj_off : NULL; - new_addr = new ? (u8 *)new->bpf_func + poke->adj_off : NULL; - - if (new) { - ret = bpf_arch_text_poke(poke->tailcall_target, - BPF_MOD_JUMP, - old_addr, new_addr); - BUG_ON(ret < 0 && ret != -EINVAL); - if (!old) { - ret = bpf_arch_text_poke(poke->tailcall_bypass, - BPF_MOD_JUMP, - poke->bypass_addr, - NULL); - BUG_ON(ret < 0 && ret != -EINVAL); - } - } else { - ret = bpf_arch_text_poke(poke->tailcall_bypass, - BPF_MOD_JUMP, - old_bypass_addr, - poke->bypass_addr); - BUG_ON(ret < 0 && ret != -EINVAL); - /* let other CPUs finish the execution of program - * so that it will not possible to expose them - * to invalid nop, stack unwind, nop state - */ - if (!ret) - synchronize_rcu(); - ret = bpf_arch_text_poke(poke->tailcall_target, - BPF_MOD_JUMP, - old_addr, NULL); - BUG_ON(ret < 0 && ret != -EINVAL); - } + bpf_arch_poke_desc_update(poke, new, old); } } } diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 4e3ce0542e31f..5d1efe5200ba3 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -371,14 +371,18 @@ static int bpf_adj_delta_to_imm(struct bpf_insn *insn, u32 pos, s32 end_old, static int bpf_adj_delta_to_off(struct bpf_insn *insn, u32 pos, s32 end_old, s32 end_new, s32 curr, const bool probe_pass) { - const s32 off_min = S16_MIN, off_max = S16_MAX; + s64 off_min, off_max, off; s32 delta = end_new - end_old; - s32 off; - if (insn->code == (BPF_JMP32 | BPF_JA)) + if (insn->code == (BPF_JMP32 | BPF_JA)) { off = insn->imm; - else + off_min = S32_MIN; + off_max = S32_MAX; + } else { off = insn->off; + off_min = S16_MIN; + off_max = S16_MAX; + } if (curr < pos && curr + off + 1 >= end_old) off += delta; @@ -623,7 +627,11 @@ static __always_inline int bpf_tree_comp(void *key, struct latch_tree_node *n) if (val < ksym->start) return -1; - if (val >= ksym->end) + /* Ensure that we detect return addresses as part of the program, when + * the final instruction is a call for a program part of the stack + * trace. Therefore, do val > ksym->end instead of val >= ksym->end. + */ + if (val > ksym->end) return 1; return 0; diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c index d93ddac283d40..956f80ee6f5c5 100644 --- a/kernel/bpf/memalloc.c +++ b/kernel/bpf/memalloc.c @@ -958,6 +958,8 @@ void notrace *bpf_mem_cache_alloc_flags(struct bpf_mem_alloc *ma, gfp_t flags) memcg = get_memcg(c); old_memcg = set_active_memcg(memcg); ret = __alloc(c, NUMA_NO_NODE, GFP_KERNEL | __GFP_NOWARN | __GFP_ACCOUNT); + if (ret) + *(struct bpf_mem_cache **)ret = c; set_active_memcg(old_memcg); mem_cgroup_put(memcg); } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 82c9e5c470319..824531d4c262a 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1515,7 +1515,8 @@ static void print_verifier_state(struct bpf_verifier_env *env, if (state->in_async_callback_fn) verbose(env, " async_cb"); verbose(env, "\n"); - mark_verifier_state_clean(env); + if (!print_all) + mark_verifier_state_clean(env); } static inline u32 vlog_alignment(u32 pos) @@ -3200,12 +3201,29 @@ static int push_jmp_history(struct bpf_verifier_env *env, /* Backtrack one insn at a time. If idx is not at the top of recorded * history then previous instruction came from straight line execution. + * Return -ENOENT if we exhausted all instructions within given state. + * + * It's legal to have a bit of a looping with the same starting and ending + * insn index within the same state, e.g.: 3->4->5->3, so just because current + * instruction index is the same as state's first_idx doesn't mean we are + * done. If there is still some jump history left, we should keep going. We + * need to take into account that we might have a jump history between given + * state's parent and itself, due to checkpointing. In this case, we'll have + * history entry recording a jump from last instruction of parent state and + * first instruction of given state. */ static int get_prev_insn_idx(struct bpf_verifier_state *st, int i, u32 *history) { u32 cnt = *history; + if (i == st->first_insn_idx) { + if (cnt == 0) + return -ENOENT; + if (cnt == 1 && st->jmp_history[0].idx == i) + return -ENOENT; + } + if (cnt && st->jmp_history[cnt - 1].idx == i) { i = st->jmp_history[cnt - 1].prev_idx; (*history)--; @@ -3426,7 +3444,12 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx, if (class == BPF_ALU || class == BPF_ALU64) { if (!bt_is_reg_set(bt, dreg)) return 0; - if (opcode == BPF_MOV) { + if (opcode == BPF_END || opcode == BPF_NEG) { + /* sreg is reserved and unused + * dreg still need precision before this insn + */ + return 0; + } else if (opcode == BPF_MOV) { if (BPF_SRC(insn->code) == BPF_X) { /* dreg = sreg or dreg = (s8, s16, s32)sreg * dreg needs precision after this insn @@ -4080,10 +4103,10 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno) * Nothing to be tracked further in the parent state. */ return 0; - if (i == first_idx) - break; subseq_idx = i; i = get_prev_insn_idx(st, i, &history); + if (i == -ENOENT) + break; if (i >= env->prog->len) { /* This can happen if backtracking reached insn 0 * and there are still reg_mask or stack_mask @@ -4358,7 +4381,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, insn->imm != 0 && env->bpf_capable) { struct bpf_reg_state fake_reg = {}; - __mark_reg_known(&fake_reg, (u32)insn->imm); + __mark_reg_known(&fake_reg, insn->imm); fake_reg.type = SCALAR_VALUE; save_register_state(state, spi, &fake_reg, size); } else if (reg && is_spillable_regtype(reg->type)) { @@ -14139,6 +14162,8 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, !sanitize_speculative_path(env, insn, *insn_idx + 1, *insn_idx)) return -EFAULT; + if (env->log.level & BPF_LOG_LEVEL) + print_insn_state(env, this_branch->frame[this_branch->curframe]); *insn_idx += insn->off; return 0; } else if (pred == 0) { @@ -14151,6 +14176,8 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, *insn_idx + insn->off + 1, *insn_idx)) return -EFAULT; + if (env->log.level & BPF_LOG_LEVEL) + print_insn_state(env, this_branch->frame[this_branch->curframe]); return 0; } @@ -14729,8 +14756,7 @@ enum { * w - next instruction * e - edge */ -static int push_insn(int t, int w, int e, struct bpf_verifier_env *env, - bool loop_ok) +static int push_insn(int t, int w, int e, struct bpf_verifier_env *env) { int *insn_stack = env->cfg.insn_stack; int *insn_state = env->cfg.insn_state; @@ -14762,7 +14788,7 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env, insn_stack[env->cfg.cur_stack++] = w; return KEEP_EXPLORING; } else if ((insn_state[w] & 0xF0) == DISCOVERED) { - if (loop_ok && env->bpf_capable) + if (env->bpf_capable) return DONE_EXPLORING; verbose_linfo(env, t, "%d: ", t); verbose_linfo(env, w, "%d: ", w); @@ -14782,24 +14808,20 @@ static int visit_func_call_insn(int t, struct bpf_insn *insns, struct bpf_verifier_env *env, bool visit_callee) { - int ret; + int ret, insn_sz; - ret = push_insn(t, t + 1, FALLTHROUGH, env, false); + insn_sz = bpf_is_ldimm64(&insns[t]) ? 2 : 1; + ret = push_insn(t, t + insn_sz, FALLTHROUGH, env); if (ret) return ret; - mark_prune_point(env, t + 1); + mark_prune_point(env, t + insn_sz); /* when we exit from subprog, we need to record non-linear history */ - mark_jmp_point(env, t + 1); + mark_jmp_point(env, t + insn_sz); if (visit_callee) { mark_prune_point(env, t); - ret = push_insn(t, t + insns[t].imm + 1, BRANCH, env, - /* It's ok to allow recursion from CFG point of - * view. __check_func_call() will do the actual - * check. - */ - bpf_pseudo_func(insns + t)); + ret = push_insn(t, t + insns[t].imm + 1, BRANCH, env); } return ret; } @@ -14812,15 +14834,17 @@ static int visit_func_call_insn(int t, struct bpf_insn *insns, static int visit_insn(int t, struct bpf_verifier_env *env) { struct bpf_insn *insns = env->prog->insnsi, *insn = &insns[t]; - int ret, off; + int ret, off, insn_sz; if (bpf_pseudo_func(insn)) return visit_func_call_insn(t, insns, env, true); /* All non-branch instructions have a single fall-through edge. */ if (BPF_CLASS(insn->code) != BPF_JMP && - BPF_CLASS(insn->code) != BPF_JMP32) - return push_insn(t, t + 1, FALLTHROUGH, env, false); + BPF_CLASS(insn->code) != BPF_JMP32) { + insn_sz = bpf_is_ldimm64(insn) ? 2 : 1; + return push_insn(t, t + insn_sz, FALLTHROUGH, env); + } switch (BPF_OP(insn->code)) { case BPF_EXIT: @@ -14866,8 +14890,7 @@ static int visit_insn(int t, struct bpf_verifier_env *env) off = insn->imm; /* unconditional jump with single edge */ - ret = push_insn(t, t + off + 1, FALLTHROUGH, env, - true); + ret = push_insn(t, t + off + 1, FALLTHROUGH, env); if (ret) return ret; @@ -14880,11 +14903,11 @@ static int visit_insn(int t, struct bpf_verifier_env *env) /* conditional jump with two edges */ mark_prune_point(env, t); - ret = push_insn(t, t + 1, FALLTHROUGH, env, true); + ret = push_insn(t, t + 1, FALLTHROUGH, env); if (ret) return ret; - return push_insn(t, t + insn->off + 1, BRANCH, env, true); + return push_insn(t, t + insn->off + 1, BRANCH, env); } } @@ -14939,11 +14962,21 @@ static int check_cfg(struct bpf_verifier_env *env) } for (i = 0; i < insn_cnt; i++) { + struct bpf_insn *insn = &env->prog->insnsi[i]; + if (insn_state[i] != EXPLORED) { verbose(env, "unreachable insn %d\n", i); ret = -EINVAL; goto err_free; } + if (bpf_is_ldimm64(insn)) { + if (insn_state[i + 1] != 0) { + verbose(env, "jump into the middle of ldimm64 insn %d\n", i); + ret = -EINVAL; + goto err_free; + } + i++; /* skip second half of ldimm64 */ + } } ret = 0; /* cfg looks good */ diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 1fb7f562289d5..518725b57200c 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3867,14 +3867,6 @@ static __poll_t cgroup_pressure_poll(struct kernfs_open_file *of, return psi_trigger_poll(&ctx->psi.trigger, of->file, pt); } -static int cgroup_pressure_open(struct kernfs_open_file *of) -{ - if (of->file->f_mode & FMODE_WRITE && !capable(CAP_SYS_RESOURCE)) - return -EPERM; - - return 0; -} - static void cgroup_pressure_release(struct kernfs_open_file *of) { struct cgroup_file_ctx *ctx = of->priv; @@ -5275,7 +5267,6 @@ static struct cftype cgroup_psi_files[] = { { .name = "io.pressure", .file_offset = offsetof(struct cgroup, psi_files[PSI_IO]), - .open = cgroup_pressure_open, .seq_show = cgroup_io_pressure_show, .write = cgroup_io_pressure_write, .poll = cgroup_pressure_poll, @@ -5284,7 +5275,6 @@ static struct cftype cgroup_psi_files[] = { { .name = "memory.pressure", .file_offset = offsetof(struct cgroup, psi_files[PSI_MEM]), - .open = cgroup_pressure_open, .seq_show = cgroup_memory_pressure_show, .write = cgroup_memory_pressure_write, .poll = cgroup_pressure_poll, @@ -5293,7 +5283,6 @@ static struct cftype cgroup_psi_files[] = { { .name = "cpu.pressure", .file_offset = offsetof(struct cgroup, psi_files[PSI_CPU]), - .open = cgroup_pressure_open, .seq_show = cgroup_cpu_pressure_show, .write = cgroup_cpu_pressure_write, .poll = cgroup_pressure_poll, @@ -5303,7 +5292,6 @@ static struct cftype cgroup_psi_files[] = { { .name = "irq.pressure", .file_offset = offsetof(struct cgroup, psi_files[PSI_IRQ]), - .open = cgroup_pressure_open, .seq_show = cgroup_irq_pressure_show, .write = cgroup_irq_pressure_write, .poll = cgroup_pressure_poll, diff --git a/kernel/cgroup/legacy_freezer.c b/kernel/cgroup/legacy_freezer.c index 122dacb3a4439..66d1708042a72 100644 --- a/kernel/cgroup/legacy_freezer.c +++ b/kernel/cgroup/legacy_freezer.c @@ -66,9 +66,15 @@ static struct freezer *parent_freezer(struct freezer *freezer) bool cgroup_freezing(struct task_struct *task) { bool ret; + unsigned int state; rcu_read_lock(); - ret = task_freezer(task)->state & CGROUP_FREEZING; + /* Check if the cgroup is still FREEZING, but not FROZEN. The extra + * !FROZEN check is required, because the FREEZING bit is not cleared + * when the state FROZEN is reached. + */ + state = task_freezer(task)->state; + ret = (state & CGROUP_FREEZING) && !(state & CGROUP_FROZEN); rcu_read_unlock(); return ret; diff --git a/kernel/cpu.c b/kernel/cpu.c index 1a189da3bdac5..72e0f5380bf68 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -1523,11 +1523,14 @@ static int cpu_down_maps_locked(unsigned int cpu, enum cpuhp_state target) /* * Ensure that the control task does not run on the to be offlined * CPU to prevent a deadlock against cfs_b->period_timer. + * Also keep at least one housekeeping cpu onlined to avoid generating + * an empty sched_domain span. */ - cpu = cpumask_any_but(cpu_online_mask, cpu); - if (cpu >= nr_cpu_ids) - return -EBUSY; - return work_on_cpu(cpu, __cpu_down_maps_locked, &work); + for_each_cpu_and(cpu, cpu_online_mask, housekeeping_cpumask(HK_TYPE_DOMAIN)) { + if (cpu != work.cpu) + return work_on_cpu(cpu, __cpu_down_maps_locked, &work); + } + return -EBUSY; } static int cpu_down(unsigned int cpu, enum cpuhp_state target) @@ -2106,7 +2109,7 @@ static struct cpuhp_step cpuhp_hp_states[] = { [CPUHP_HRTIMERS_PREPARE] = { .name = "hrtimers:prepare", .startup.single = hrtimers_prepare_cpu, - .teardown.single = hrtimers_dead_cpu, + .teardown.single = NULL, }, [CPUHP_SMPCFD_PREPARE] = { .name = "smpcfd:prepare", @@ -2198,6 +2201,12 @@ static struct cpuhp_step cpuhp_hp_states[] = { .startup.single = NULL, .teardown.single = smpcfd_dying_cpu, }, + [CPUHP_AP_HRTIMERS_DYING] = { + .name = "hrtimers:dying", + .startup.single = NULL, + .teardown.single = hrtimers_cpu_dying, + }, + /* Entry state on starting. Interrupts enabled from here on. Transient * state for synchronsization */ [CPUHP_AP_ONLINE] = { diff --git a/kernel/cred.c b/kernel/cred.c index 98cb4eca23fb2..64404d51c0527 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -43,10 +43,6 @@ static struct group_info init_groups = { .usage = ATOMIC_INIT(2) }; */ struct cred init_cred = { .usage = ATOMIC_INIT(4), -#ifdef CONFIG_DEBUG_CREDENTIALS - .subscribers = ATOMIC_INIT(2), - .magic = CRED_MAGIC, -#endif .uid = GLOBAL_ROOT_UID, .gid = GLOBAL_ROOT_GID, .suid = GLOBAL_ROOT_UID, @@ -66,31 +62,6 @@ struct cred init_cred = { .ucounts = &init_ucounts, }; -static inline void set_cred_subscribers(struct cred *cred, int n) -{ -#ifdef CONFIG_DEBUG_CREDENTIALS - atomic_set(&cred->subscribers, n); -#endif -} - -static inline int read_cred_subscribers(const struct cred *cred) -{ -#ifdef CONFIG_DEBUG_CREDENTIALS - return atomic_read(&cred->subscribers); -#else - return 0; -#endif -} - -static inline void alter_cred_subscribers(const struct cred *_cred, int n) -{ -#ifdef CONFIG_DEBUG_CREDENTIALS - struct cred *cred = (struct cred *) _cred; - - atomic_add(n, &cred->subscribers); -#endif -} - /* * The RCU callback to actually dispose of a set of credentials */ @@ -100,20 +71,9 @@ static void put_cred_rcu(struct rcu_head *rcu) kdebug("put_cred_rcu(%p)", cred); -#ifdef CONFIG_DEBUG_CREDENTIALS - if (cred->magic != CRED_MAGIC_DEAD || - atomic_read(&cred->usage) != 0 || - read_cred_subscribers(cred) != 0) - panic("CRED: put_cred_rcu() sees %p with" - " mag %x, put %p, usage %d, subscr %d\n", - cred, cred->magic, cred->put_addr, - atomic_read(&cred->usage), - read_cred_subscribers(cred)); -#else - if (atomic_read(&cred->usage) != 0) - panic("CRED: put_cred_rcu() sees %p with usage %d\n", - cred, atomic_read(&cred->usage)); -#endif + if (atomic_long_read(&cred->usage) != 0) + panic("CRED: put_cred_rcu() sees %p with usage %ld\n", + cred, atomic_long_read(&cred->usage)); security_cred_free(cred); key_put(cred->session_keyring); @@ -137,16 +97,10 @@ static void put_cred_rcu(struct rcu_head *rcu) */ void __put_cred(struct cred *cred) { - kdebug("__put_cred(%p{%d,%d})", cred, - atomic_read(&cred->usage), - read_cred_subscribers(cred)); - - BUG_ON(atomic_read(&cred->usage) != 0); -#ifdef CONFIG_DEBUG_CREDENTIALS - BUG_ON(read_cred_subscribers(cred) != 0); - cred->magic = CRED_MAGIC_DEAD; - cred->put_addr = __builtin_return_address(0); -#endif + kdebug("__put_cred(%p{%ld})", cred, + atomic_long_read(&cred->usage)); + + BUG_ON(atomic_long_read(&cred->usage) != 0); BUG_ON(cred == current->cred); BUG_ON(cred == current->real_cred); @@ -164,20 +118,15 @@ void exit_creds(struct task_struct *tsk) { struct cred *cred; - kdebug("exit_creds(%u,%p,%p,{%d,%d})", tsk->pid, tsk->real_cred, tsk->cred, - atomic_read(&tsk->cred->usage), - read_cred_subscribers(tsk->cred)); + kdebug("exit_creds(%u,%p,%p,{%ld})", tsk->pid, tsk->real_cred, tsk->cred, + atomic_long_read(&tsk->cred->usage)); cred = (struct cred *) tsk->real_cred; tsk->real_cred = NULL; - validate_creds(cred); - alter_cred_subscribers(cred, -1); put_cred(cred); cred = (struct cred *) tsk->cred; tsk->cred = NULL; - validate_creds(cred); - alter_cred_subscribers(cred, -1); put_cred(cred); #ifdef CONFIG_KEYS_REQUEST_CACHE @@ -224,10 +173,7 @@ struct cred *cred_alloc_blank(void) if (!new) return NULL; - atomic_set(&new->usage, 1); -#ifdef CONFIG_DEBUG_CREDENTIALS - new->magic = CRED_MAGIC; -#endif + atomic_long_set(&new->usage, 1); if (security_cred_alloc_blank(new, GFP_KERNEL_ACCOUNT) < 0) goto error; @@ -258,8 +204,6 @@ struct cred *prepare_creds(void) const struct cred *old; struct cred *new; - validate_process_creds(); - new = kmem_cache_alloc(cred_jar, GFP_KERNEL); if (!new) return NULL; @@ -270,8 +214,7 @@ struct cred *prepare_creds(void) memcpy(new, old, sizeof(struct cred)); new->non_rcu = 0; - atomic_set(&new->usage, 1); - set_cred_subscribers(new, 0); + atomic_long_set(&new->usage, 1); get_group_info(new->group_info); get_uid(new->user); get_user_ns(new->user_ns); @@ -294,7 +237,6 @@ struct cred *prepare_creds(void) if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0) goto error; - validate_creds(new); return new; error: @@ -357,10 +299,8 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags) ) { p->real_cred = get_cred(p->cred); get_cred(p->cred); - alter_cred_subscribers(p->cred, 2); - kdebug("share_creds(%p{%d,%d})", - p->cred, atomic_read(&p->cred->usage), - read_cred_subscribers(p->cred)); + kdebug("share_creds(%p{%ld})", + p->cred, atomic_long_read(&p->cred->usage)); inc_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1); return 0; } @@ -399,8 +339,6 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags) p->cred = p->real_cred = get_cred(new); inc_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1); - alter_cred_subscribers(new, 2); - validate_creds(new); return 0; error_put: @@ -452,17 +390,11 @@ int commit_creds(struct cred *new) struct task_struct *task = current; const struct cred *old = task->real_cred; - kdebug("commit_creds(%p{%d,%d})", new, - atomic_read(&new->usage), - read_cred_subscribers(new)); + kdebug("commit_creds(%p{%ld})", new, + atomic_long_read(&new->usage)); BUG_ON(task->cred != old); -#ifdef CONFIG_DEBUG_CREDENTIALS - BUG_ON(read_cred_subscribers(old) < 2); - validate_creds(old); - validate_creds(new); -#endif - BUG_ON(atomic_read(&new->usage) < 1); + BUG_ON(atomic_long_read(&new->usage) < 1); get_cred(new); /* we will require a ref for the subj creds too */ @@ -497,14 +429,12 @@ int commit_creds(struct cred *new) * RLIMIT_NPROC limits on user->processes have already been checked * in set_user(). */ - alter_cred_subscribers(new, 2); if (new->user != old->user || new->user_ns != old->user_ns) inc_rlimit_ucounts(new->ucounts, UCOUNT_RLIMIT_NPROC, 1); rcu_assign_pointer(task->real_cred, new); rcu_assign_pointer(task->cred, new); if (new->user != old->user || new->user_ns != old->user_ns) dec_rlimit_ucounts(old->ucounts, UCOUNT_RLIMIT_NPROC, 1); - alter_cred_subscribers(old, -2); /* send notifications */ if (!uid_eq(new->uid, old->uid) || @@ -535,14 +465,10 @@ EXPORT_SYMBOL(commit_creds); */ void abort_creds(struct cred *new) { - kdebug("abort_creds(%p{%d,%d})", new, - atomic_read(&new->usage), - read_cred_subscribers(new)); + kdebug("abort_creds(%p{%ld})", new, + atomic_long_read(&new->usage)); -#ifdef CONFIG_DEBUG_CREDENTIALS - BUG_ON(read_cred_subscribers(new) != 0); -#endif - BUG_ON(atomic_read(&new->usage) < 1); + BUG_ON(atomic_long_read(&new->usage) < 1); put_cred(new); } EXPORT_SYMBOL(abort_creds); @@ -558,12 +484,8 @@ const struct cred *override_creds(const struct cred *new) { const struct cred *old = current->cred; - kdebug("override_creds(%p{%d,%d})", new, - atomic_read(&new->usage), - read_cred_subscribers(new)); - - validate_creds(old); - validate_creds(new); + kdebug("override_creds(%p{%ld})", new, + atomic_long_read(&new->usage)); /* * NOTE! This uses 'get_new_cred()' rather than 'get_cred()'. @@ -572,18 +494,12 @@ const struct cred *override_creds(const struct cred *new) * we are only installing the cred into the thread-synchronous * '->cred' pointer, not the '->real_cred' pointer that is * visible to other threads under RCU. - * - * Also note that we did validate_creds() manually, not depending - * on the validation in 'get_cred()'. */ get_new_cred((struct cred *)new); - alter_cred_subscribers(new, 1); rcu_assign_pointer(current->cred, new); - alter_cred_subscribers(old, -1); - kdebug("override_creds() = %p{%d,%d}", old, - atomic_read(&old->usage), - read_cred_subscribers(old)); + kdebug("override_creds() = %p{%ld}", old, + atomic_long_read(&old->usage)); return old; } EXPORT_SYMBOL(override_creds); @@ -599,15 +515,10 @@ void revert_creds(const struct cred *old) { const struct cred *override = current->cred; - kdebug("revert_creds(%p{%d,%d})", old, - atomic_read(&old->usage), - read_cred_subscribers(old)); + kdebug("revert_creds(%p{%ld})", old, + atomic_long_read(&old->usage)); - validate_creds(old); - validate_creds(override); - alter_cred_subscribers(old, 1); rcu_assign_pointer(current->cred, old); - alter_cred_subscribers(override, -1); put_cred(override); } EXPORT_SYMBOL(revert_creds); @@ -727,12 +638,10 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon) kdebug("prepare_kernel_cred() alloc %p", new); old = get_task_cred(daemon); - validate_creds(old); *new = *old; new->non_rcu = 0; - atomic_set(&new->usage, 1); - set_cred_subscribers(new, 0); + atomic_long_set(&new->usage, 1); get_uid(new->user); get_user_ns(new->user_ns); get_group_info(new->group_info); @@ -756,7 +665,6 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon) goto error; put_cred(old); - validate_creds(new); return new; error: @@ -821,109 +729,3 @@ int set_create_files_as(struct cred *new, struct inode *inode) return security_kernel_create_files_as(new, inode); } EXPORT_SYMBOL(set_create_files_as); - -#ifdef CONFIG_DEBUG_CREDENTIALS - -bool creds_are_invalid(const struct cred *cred) -{ - if (cred->magic != CRED_MAGIC) - return true; - return false; -} -EXPORT_SYMBOL(creds_are_invalid); - -/* - * dump invalid credentials - */ -static void dump_invalid_creds(const struct cred *cred, const char *label, - const struct task_struct *tsk) -{ - pr_err("%s credentials: %p %s%s%s\n", - label, cred, - cred == &init_cred ? "[init]" : "", - cred == tsk->real_cred ? "[real]" : "", - cred == tsk->cred ? "[eff]" : ""); - pr_err("->magic=%x, put_addr=%p\n", - cred->magic, cred->put_addr); - pr_err("->usage=%d, subscr=%d\n", - atomic_read(&cred->usage), - read_cred_subscribers(cred)); - pr_err("->*uid = { %d,%d,%d,%d }\n", - from_kuid_munged(&init_user_ns, cred->uid), - from_kuid_munged(&init_user_ns, cred->euid), - from_kuid_munged(&init_user_ns, cred->suid), - from_kuid_munged(&init_user_ns, cred->fsuid)); - pr_err("->*gid = { %d,%d,%d,%d }\n", - from_kgid_munged(&init_user_ns, cred->gid), - from_kgid_munged(&init_user_ns, cred->egid), - from_kgid_munged(&init_user_ns, cred->sgid), - from_kgid_munged(&init_user_ns, cred->fsgid)); -#ifdef CONFIG_SECURITY - pr_err("->security is %p\n", cred->security); - if ((unsigned long) cred->security >= PAGE_SIZE && - (((unsigned long) cred->security & 0xffffff00) != - (POISON_FREE << 24 | POISON_FREE << 16 | POISON_FREE << 8))) - pr_err("->security {%x, %x}\n", - ((u32*)cred->security)[0], - ((u32*)cred->security)[1]); -#endif -} - -/* - * report use of invalid credentials - */ -void __noreturn __invalid_creds(const struct cred *cred, const char *file, unsigned line) -{ - pr_err("Invalid credentials\n"); - pr_err("At %s:%u\n", file, line); - dump_invalid_creds(cred, "Specified", current); - BUG(); -} -EXPORT_SYMBOL(__invalid_creds); - -/* - * check the credentials on a process - */ -void __validate_process_creds(struct task_struct *tsk, - const char *file, unsigned line) -{ - if (tsk->cred == tsk->real_cred) { - if (unlikely(read_cred_subscribers(tsk->cred) < 2 || - creds_are_invalid(tsk->cred))) - goto invalid_creds; - } else { - if (unlikely(read_cred_subscribers(tsk->real_cred) < 1 || - read_cred_subscribers(tsk->cred) < 1 || - creds_are_invalid(tsk->real_cred) || - creds_are_invalid(tsk->cred))) - goto invalid_creds; - } - return; - -invalid_creds: - pr_err("Invalid process credentials\n"); - pr_err("At %s:%u\n", file, line); - - dump_invalid_creds(tsk->real_cred, "Real", tsk); - if (tsk->cred != tsk->real_cred) - dump_invalid_creds(tsk->cred, "Effective", tsk); - else - pr_err("Effective creds == Real creds\n"); - BUG(); -} -EXPORT_SYMBOL(__validate_process_creds); - -/* - * check creds for do_exit() - */ -void validate_creds_for_do_exit(struct task_struct *tsk) -{ - kdebug("validate_creds_for_do_exit(%p,%p{%d,%d})", - tsk->real_cred, tsk->cred, - atomic_read(&tsk->cred->usage), - read_cred_subscribers(tsk->cred)); - - __validate_process_creds(tsk, __FILE__, __LINE__); -} - -#endif /* CONFIG_DEBUG_CREDENTIALS */ diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index 621037a0aa870..ce1bb2301c061 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -1006,6 +1006,9 @@ void kgdb_panic(const char *msg) if (panic_timeout) return; + debug_locks_off(); + console_flush_on_panic(CONSOLE_FLUSH_PENDING); + if (dbg_kdb_mode) kdb_printf("PANIC: %s\n", msg); diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index dff067bd56b1e..2048194a03bed 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -283,7 +283,8 @@ static void swiotlb_init_io_tlb_pool(struct io_tlb_pool *mem, phys_addr_t start, } for (i = 0; i < mem->nslabs; i++) { - mem->slots[i].list = IO_TLB_SEGSIZE - io_tlb_offset(i); + mem->slots[i].list = min(IO_TLB_SEGSIZE - io_tlb_offset(i), + mem->nslabs - i); mem->slots[i].orig_addr = INVALID_PHYS_ADDR; mem->slots[i].alloc_size = 0; } @@ -558,29 +559,40 @@ void __init swiotlb_exit(void) * alloc_dma_pages() - allocate pages to be used for DMA * @gfp: GFP flags for the allocation. * @bytes: Size of the buffer. + * @phys_limit: Maximum allowed physical address of the buffer. * * Allocate pages from the buddy allocator. If successful, make the allocated * pages decrypted that they can be used for DMA. * - * Return: Decrypted pages, or %NULL on failure. + * Return: Decrypted pages, %NULL on allocation failure, or ERR_PTR(-EAGAIN) + * if the allocated physical address was above @phys_limit. */ -static struct page *alloc_dma_pages(gfp_t gfp, size_t bytes) +static struct page *alloc_dma_pages(gfp_t gfp, size_t bytes, u64 phys_limit) { unsigned int order = get_order(bytes); struct page *page; + phys_addr_t paddr; void *vaddr; page = alloc_pages(gfp, order); if (!page) return NULL; - vaddr = page_address(page); + paddr = page_to_phys(page); + if (paddr + bytes - 1 > phys_limit) { + __free_pages(page, order); + return ERR_PTR(-EAGAIN); + } + + vaddr = phys_to_virt(paddr); if (set_memory_decrypted((unsigned long)vaddr, PFN_UP(bytes))) goto error; return page; error: - __free_pages(page, order); + /* Intentional leak if pages cannot be encrypted again. */ + if (!set_memory_encrypted((unsigned long)vaddr, PFN_UP(bytes))) + __free_pages(page, order); return NULL; } @@ -618,11 +630,7 @@ static struct page *swiotlb_alloc_tlb(struct device *dev, size_t bytes, else if (phys_limit <= DMA_BIT_MASK(32)) gfp |= __GFP_DMA32; - while ((page = alloc_dma_pages(gfp, bytes)) && - page_to_phys(page) + bytes - 1 > phys_limit) { - /* allocated, but too high */ - __free_pages(page, get_order(bytes)); - + while (IS_ERR(page = alloc_dma_pages(gfp, bytes, phys_limit))) { if (IS_ENABLED(CONFIG_ZONE_DMA32) && phys_limit < DMA_BIT_MASK(64) && !(gfp & (__GFP_DMA32 | __GFP_DMA))) diff --git a/kernel/events/core.c b/kernel/events/core.c index 452c15d747328..58ecb1c243871 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1814,31 +1814,34 @@ static inline void perf_event__state_init(struct perf_event *event) PERF_EVENT_STATE_INACTIVE; } -static void __perf_event_read_size(struct perf_event *event, int nr_siblings) +static int __perf_event_read_size(u64 read_format, int nr_siblings) { int entry = sizeof(u64); /* value */ int size = 0; int nr = 1; - if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) size += sizeof(u64); - if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) size += sizeof(u64); - if (event->attr.read_format & PERF_FORMAT_ID) + if (read_format & PERF_FORMAT_ID) entry += sizeof(u64); - if (event->attr.read_format & PERF_FORMAT_LOST) + if (read_format & PERF_FORMAT_LOST) entry += sizeof(u64); - if (event->attr.read_format & PERF_FORMAT_GROUP) { + if (read_format & PERF_FORMAT_GROUP) { nr += nr_siblings; size += sizeof(u64); } - size += entry * nr; - event->read_size = size; + /* + * Since perf_event_validate_size() limits this to 16k and inhibits + * adding more siblings, this will never overflow. + */ + return size + nr * entry; } static void __perf_event_header_size(struct perf_event *event, u64 sample_type) @@ -1888,8 +1891,9 @@ static void __perf_event_header_size(struct perf_event *event, u64 sample_type) */ static void perf_event__header_size(struct perf_event *event) { - __perf_event_read_size(event, - event->group_leader->nr_siblings); + event->read_size = + __perf_event_read_size(event->attr.read_format, + event->group_leader->nr_siblings); __perf_event_header_size(event, event->attr.sample_type); } @@ -1920,23 +1924,44 @@ static void perf_event__id_header_size(struct perf_event *event) event->id_header_size = size; } +/* + * Check that adding an event to the group does not result in anybody + * overflowing the 64k event limit imposed by the output buffer. + * + * Specifically, check that the read_size for the event does not exceed 16k, + * read_size being the one term that grows with groups size. Since read_size + * depends on per-event read_format, also (re)check the existing events. + * + * This leaves 48k for the constant size fields and things like callchains, + * branch stacks and register sets. + */ static bool perf_event_validate_size(struct perf_event *event) { - /* - * The values computed here will be over-written when we actually - * attach the event. - */ - __perf_event_read_size(event, event->group_leader->nr_siblings + 1); - __perf_event_header_size(event, event->attr.sample_type & ~PERF_SAMPLE_READ); - perf_event__id_header_size(event); + struct perf_event *sibling, *group_leader = event->group_leader; + + if (__perf_event_read_size(event->attr.read_format, + group_leader->nr_siblings + 1) > 16*1024) + return false; + + if (__perf_event_read_size(group_leader->attr.read_format, + group_leader->nr_siblings + 1) > 16*1024) + return false; /* - * Sum the lot; should not exceed the 64k limit we have on records. - * Conservative limit to allow for callchains and other variable fields. + * When creating a new group leader, group_leader->ctx is initialized + * after the size has been validated, but we cannot safely use + * for_each_sibling_event() until group_leader->ctx is set. A new group + * leader cannot have any siblings yet, so we can safely skip checking + * the non-existent siblings. */ - if (event->read_size + event->header_size + - event->id_header_size + sizeof(struct perf_event_header) >= 16*1024) - return false; + if (event == group_leader) + return true; + + for_each_sibling_event(sibling, group_leader) { + if (__perf_event_read_size(sibling->attr.read_format, + group_leader->nr_siblings + 1) > 16*1024) + return false; + } return true; } @@ -4816,6 +4841,11 @@ find_get_pmu_context(struct pmu *pmu, struct perf_event_context *ctx, void *task_ctx_data = NULL; if (!ctx->task) { + /* + * perf_pmu_migrate_context() / __perf_pmu_install_event() + * relies on the fact that find_get_pmu_context() cannot fail + * for CPU contexts. + */ struct perf_cpu_pmu_context *cpc; cpc = per_cpu_ptr(pmu->cpu_pmu_context, event->cpu); @@ -12877,6 +12907,9 @@ static void __perf_pmu_install_event(struct pmu *pmu, int cpu, struct perf_event *event) { struct perf_event_pmu_context *epc; + struct perf_event_context *old_ctx = event->ctx; + + get_ctx(ctx); /* normally find_get_context() */ event->cpu = cpu; epc = find_get_pmu_context(pmu, ctx, event); @@ -12885,6 +12918,11 @@ static void __perf_pmu_install_event(struct pmu *pmu, if (event->state >= PERF_EVENT_STATE_OFF) event->state = PERF_EVENT_STATE_INACTIVE; perf_install_in_context(ctx, event, cpu); + + /* + * Now that event->ctx is updated and visible, put the old ctx. + */ + put_ctx(old_ctx); } static void __perf_pmu_install(struct perf_event_context *ctx, @@ -12923,6 +12961,10 @@ void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu) struct perf_event_context *src_ctx, *dst_ctx; LIST_HEAD(events); + /* + * Since per-cpu context is persistent, no need to grab an extra + * reference. + */ src_ctx = &per_cpu_ptr(&perf_cpu_context, src_cpu)->ctx; dst_ctx = &per_cpu_ptr(&perf_cpu_context, dst_cpu)->ctx; diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index fb1e180b5f0af..e8d82c2f07d0e 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -700,6 +700,12 @@ int rb_alloc_aux(struct perf_buffer *rb, struct perf_event *event, watermark = 0; } + /* + * kcalloc_node() is unable to allocate buffer if the size is larger + * than: PAGE_SIZE << MAX_ORDER; directly bail out in this case. + */ + if (get_order((unsigned long)nr_pages * sizeof(void *)) > MAX_ORDER) + return -ENOMEM; rb->aux_pages = kcalloc_node(nr_pages, sizeof(void *), GFP_KERNEL, node); if (!rb->aux_pages) diff --git a/kernel/exit.c b/kernel/exit.c index edb50b4c99728..21a59a6e1f2e8 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -824,8 +824,6 @@ void __noreturn do_exit(long code) ptrace_event(PTRACE_EVENT_EXIT, code); user_events_exit(tsk); - validate_creds_for_do_exit(tsk); - io_uring_files_cancel(); exit_signals(tsk); /* sets PF_EXITING */ @@ -912,7 +910,6 @@ void __noreturn do_exit(long code) if (tsk->task_frag.page) put_page(tsk->task_frag.page); - validate_creds_for_do_exit(tsk); exit_task_stack_account(tsk); check_stack_usage(); diff --git a/kernel/fork.c b/kernel/fork.c index 3b6d20dfb9a85..177ce7438db6b 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1288,7 +1288,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, hugetlb_count_init(mm); if (current->mm) { - mm->flags = current->mm->flags & MMF_INIT_MASK; + mm->flags = mmf_init_flags(current->mm->flags); mm->def_flags = current->mm->def_flags & VM_INIT_DEF_MASK; } else { mm->flags = default_dump_filter; diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c index 5971a66be0347..aae0402507ed7 100644 --- a/kernel/irq/debugfs.c +++ b/kernel/irq/debugfs.c @@ -121,7 +121,6 @@ static const struct irq_bit_descr irqdata_states[] = { BIT_MASK_DESCR(IRQD_AFFINITY_ON_ACTIVATE), BIT_MASK_DESCR(IRQD_MANAGED_SHUTDOWN), BIT_MASK_DESCR(IRQD_CAN_RESERVE), - BIT_MASK_DESCR(IRQD_MSI_NOMASK_QUIRK), BIT_MASK_DESCR(IRQD_FORWARDED_TO_VCPU), diff --git a/kernel/irq/generic-chip.c b/kernel/irq/generic-chip.c index c653cd31548d0..5a452b94b6434 100644 --- a/kernel/irq/generic-chip.c +++ b/kernel/irq/generic-chip.c @@ -544,21 +544,34 @@ EXPORT_SYMBOL_GPL(irq_setup_alt_chip); void irq_remove_generic_chip(struct irq_chip_generic *gc, u32 msk, unsigned int clr, unsigned int set) { - unsigned int i = gc->irq_base; + unsigned int i, virq; raw_spin_lock(&gc_lock); list_del(&gc->list); raw_spin_unlock(&gc_lock); - for (; msk; msk >>= 1, i++) { + for (i = 0; msk; msk >>= 1, i++) { if (!(msk & 0x01)) continue; + /* + * Interrupt domain based chips store the base hardware + * interrupt number in gc::irq_base. Otherwise gc::irq_base + * contains the base Linux interrupt number. + */ + if (gc->domain) { + virq = irq_find_mapping(gc->domain, gc->irq_base + i); + if (!virq) + continue; + } else { + virq = gc->irq_base + i; + } + /* Remove handler first. That will mask the irq line */ - irq_set_handler(i, NULL); - irq_set_chip(i, &no_irq_chip); - irq_set_chip_data(i, NULL); - irq_modify_status(i, clr, set); + irq_set_handler(virq, NULL); + irq_set_chip(virq, &no_irq_chip); + irq_set_chip_data(virq, NULL); + irq_modify_status(virq, clr, set); } } EXPORT_SYMBOL_GPL(irq_remove_generic_chip); diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index b4c31a5c11473..79b4a58ba9c3f 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -1204,7 +1204,6 @@ static int msi_handle_pci_fail(struct irq_domain *domain, struct msi_desc *desc, #define VIRQ_CAN_RESERVE 0x01 #define VIRQ_ACTIVATE 0x02 -#define VIRQ_NOMASK_QUIRK 0x04 static int msi_init_virq(struct irq_domain *domain, int virq, unsigned int vflags) { @@ -1213,8 +1212,6 @@ static int msi_init_virq(struct irq_domain *domain, int virq, unsigned int vflag if (!(vflags & VIRQ_CAN_RESERVE)) { irqd_clr_can_reserve(irqd); - if (vflags & VIRQ_NOMASK_QUIRK) - irqd_set_msi_nomask_quirk(irqd); /* * If the interrupt is managed but no CPU is available to @@ -1275,15 +1272,8 @@ static int __msi_domain_alloc_irqs(struct device *dev, struct irq_domain *domain * Interrupt can use a reserved vector and will not occupy * a real device vector until the interrupt is requested. */ - if (msi_check_reservation_mode(domain, info, dev)) { + if (msi_check_reservation_mode(domain, info, dev)) vflags |= VIRQ_CAN_RESERVE; - /* - * MSI affinity setting requires a special quirk (X86) when - * reservation mode is active. - */ - if (info->flags & MSI_FLAG_NOMASK_QUIRK) - vflags |= VIRQ_NOMASK_QUIRK; - } xa_for_each_range(xa, idx, desc, ctrl->first, ctrl->last) { if (!msi_desc_match(desc, MSI_DESC_NOTASSOCIATED)) diff --git a/kernel/kexec.c b/kernel/kexec.c index 107f355eac101..8f35a5a42af85 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -247,7 +247,7 @@ SYSCALL_DEFINE4(kexec_load, unsigned long, entry, unsigned long, nr_segments, ((flags & KEXEC_ARCH_MASK) != KEXEC_ARCH_DEFAULT)) return -EINVAL; - ksegments = memdup_user(segments, nr_segments * sizeof(ksegments[0])); + ksegments = memdup_array_user(segments, nr_segments, sizeof(ksegments[0])); if (IS_ERR(ksegments)) return PTR_ERR(ksegments); diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 0c6185aefaef5..b486504766fb1 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -2253,7 +2253,7 @@ int register_kretprobe(struct kretprobe *rp) if (!rp->rph) return -ENOMEM; - rp->rph->rp = rp; + rcu_assign_pointer(rp->rph->rp, rp); for (i = 0; i < rp->maxactive; i++) { inst = kzalloc(struct_size(inst, data, rp->data_size), GFP_KERNEL); if (inst == NULL) { @@ -2313,7 +2313,7 @@ void unregister_kretprobes(struct kretprobe **rps, int num) #ifdef CONFIG_KRETPROBE_ON_RETHOOK rethook_free(rps[i]->rh); #else - rps[i]->rph->rp = NULL; + rcu_assign_pointer(rps[i]->rph->rp, NULL); #endif } mutex_unlock(&kprobe_mutex); diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index e85b5ad3e2069..151bd3de59363 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -3497,7 +3497,8 @@ static int alloc_chain_hlocks(int req) size = chain_block_size(curr); if (likely(size >= req)) { del_chain_block(0, size, chain_block_next(curr)); - add_chain_block(curr + req, size - req); + if (size > req) + add_chain_block(curr + req, size - req); return curr; } } diff --git a/kernel/locking/test-ww_mutex.c b/kernel/locking/test-ww_mutex.c index 93cca6e698600..7c5a8f05497f2 100644 --- a/kernel/locking/test-ww_mutex.c +++ b/kernel/locking/test-ww_mutex.c @@ -466,7 +466,6 @@ static void stress_inorder_work(struct work_struct *work) } while (!time_after(jiffies, stress->timeout)); kfree(order); - kfree(stress); } struct reorder_lock { @@ -531,7 +530,6 @@ static void stress_reorder_work(struct work_struct *work) list_for_each_entry_safe(ll, ln, &locks, link) kfree(ll); kfree(order); - kfree(stress); } static void stress_one_work(struct work_struct *work) @@ -552,8 +550,6 @@ static void stress_one_work(struct work_struct *work) break; } } while (!time_after(jiffies, stress->timeout)); - - kfree(stress); } #define STRESS_INORDER BIT(0) @@ -564,15 +560,24 @@ static void stress_one_work(struct work_struct *work) static int stress(int nlocks, int nthreads, unsigned int flags) { struct ww_mutex *locks; - int n; + struct stress *stress_array; + int n, count; locks = kmalloc_array(nlocks, sizeof(*locks), GFP_KERNEL); if (!locks) return -ENOMEM; + stress_array = kmalloc_array(nthreads, sizeof(*stress_array), + GFP_KERNEL); + if (!stress_array) { + kfree(locks); + return -ENOMEM; + } + for (n = 0; n < nlocks; n++) ww_mutex_init(&locks[n], &ww_class); + count = 0; for (n = 0; nthreads; n++) { struct stress *stress; void (*fn)(struct work_struct *work); @@ -596,9 +601,7 @@ static int stress(int nlocks, int nthreads, unsigned int flags) if (!fn) continue; - stress = kmalloc(sizeof(*stress), GFP_KERNEL); - if (!stress) - break; + stress = &stress_array[count++]; INIT_WORK(&stress->work, fn); stress->locks = locks; @@ -613,6 +616,7 @@ static int stress(int nlocks, int nthreads, unsigned int flags) for (n = 0; n < nlocks; n++) ww_mutex_destroy(&locks[n]); + kfree(stress_array); kfree(locks); return 0; diff --git a/kernel/padata.c b/kernel/padata.c index ff349e1084c1d..179fb1518070c 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -202,7 +202,7 @@ int padata_do_parallel(struct padata_shell *ps, *cb_cpu = cpu; } - err = -EBUSY; + err = -EBUSY; if ((pinst->flags & PADATA_RESET)) goto out; diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 0f12e0a97e432..50a15408c3fca 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -2545,8 +2545,9 @@ static void *get_highmem_page_buffer(struct page *page, pbe->copy_page = tmp; } else { /* Copy of the page will be stored in normal memory */ - kaddr = safe_pages_list; - safe_pages_list = safe_pages_list->next; + kaddr = __get_safe_page(ca->gfp_mask); + if (!kaddr) + return ERR_PTR(-ENOMEM); pbe->copy_page = virt_to_page(kaddr); } pbe->next = highmem_pblist; @@ -2750,8 +2751,9 @@ static void *get_buffer(struct memory_bitmap *bm, struct chain_allocator *ca) return ERR_PTR(-ENOMEM); } pbe->orig_address = page_address(page); - pbe->address = safe_pages_list; - safe_pages_list = safe_pages_list->next; + pbe->address = __get_safe_page(ca->gfp_mask); + if (!pbe->address) + return ERR_PTR(-ENOMEM); pbe->next = restore_pblist; restore_pblist = pbe; return pbe->address; @@ -2783,8 +2785,6 @@ int snapshot_write_next(struct snapshot_handle *handle) if (handle->cur > 1 && handle->cur > nr_meta_pages + nr_copy_pages + nr_zero_pages) return 0; - handle->sync_read = 1; - if (!handle->cur) { if (!buffer) /* This makes the buffer be freed by swsusp_free() */ @@ -2827,7 +2827,6 @@ int snapshot_write_next(struct snapshot_handle *handle) memory_bm_position_reset(&zero_bm); restore_pblist = NULL; handle->buffer = get_buffer(&orig_bm, &ca); - handle->sync_read = 0; if (IS_ERR(handle->buffer)) return PTR_ERR(handle->buffer); } @@ -2837,9 +2836,8 @@ int snapshot_write_next(struct snapshot_handle *handle) handle->buffer = get_buffer(&orig_bm, &ca); if (IS_ERR(handle->buffer)) return PTR_ERR(handle->buffer); - if (handle->buffer != buffer) - handle->sync_read = 0; } + handle->sync_read = (handle->buffer == buffer); handle->cur++; /* Zero pages were not included in the image, memset it and move on. */ diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c index 253ed509b6abb..25285893e44e7 100644 --- a/kernel/rcu/srcutree.c +++ b/kernel/rcu/srcutree.c @@ -223,7 +223,7 @@ static bool init_srcu_struct_nodes(struct srcu_struct *ssp, gfp_t gfp_flags) snp->grplo = cpu; snp->grphi = cpu; } - sdp->grpmask = 1 << (cpu - sdp->mynode->grplo); + sdp->grpmask = 1UL << (cpu - sdp->mynode->grplo); } smp_store_release(&ssp->srcu_sup->srcu_size_state, SRCU_SIZE_WAIT_BARRIER); return true; @@ -782,8 +782,7 @@ static void srcu_gp_start(struct srcu_struct *ssp) spin_lock_rcu_node(sdp); /* Interrupts already disabled. */ rcu_segcblist_advance(&sdp->srcu_cblist, rcu_seq_current(&ssp->srcu_sup->srcu_gp_seq)); - (void)rcu_segcblist_accelerate(&sdp->srcu_cblist, - rcu_seq_snap(&ssp->srcu_sup->srcu_gp_seq)); + WARN_ON_ONCE(!rcu_segcblist_segempty(&sdp->srcu_cblist, RCU_NEXT_TAIL)); spin_unlock_rcu_node(sdp); /* Interrupts remain disabled. */ WRITE_ONCE(ssp->srcu_sup->srcu_gp_start, jiffies); WRITE_ONCE(ssp->srcu_sup->srcu_n_exp_nodelay, 0); @@ -833,7 +832,7 @@ static void srcu_schedule_cbs_snp(struct srcu_struct *ssp, struct srcu_node *snp int cpu; for (cpu = snp->grplo; cpu <= snp->grphi; cpu++) { - if (!(mask & (1 << (cpu - snp->grplo)))) + if (!(mask & (1UL << (cpu - snp->grplo)))) continue; srcu_schedule_cbs_sdp(per_cpu_ptr(ssp->sda, cpu), delay); } @@ -1719,6 +1718,7 @@ static void srcu_invoke_callbacks(struct work_struct *work) ssp = sdp->ssp; rcu_cblist_init(&ready_cbs); spin_lock_irq_rcu_node(sdp); + WARN_ON_ONCE(!rcu_segcblist_segempty(&sdp->srcu_cblist, RCU_NEXT_TAIL)); rcu_segcblist_advance(&sdp->srcu_cblist, rcu_seq_current(&ssp->srcu_sup->srcu_gp_seq)); if (sdp->srcu_cblist_invoking || @@ -1747,8 +1747,6 @@ static void srcu_invoke_callbacks(struct work_struct *work) */ spin_lock_irq_rcu_node(sdp); rcu_segcblist_add_len(&sdp->srcu_cblist, -len); - (void)rcu_segcblist_accelerate(&sdp->srcu_cblist, - rcu_seq_snap(&ssp->srcu_sup->srcu_gp_seq)); sdp->srcu_cblist_invoking = false; more = rcu_segcblist_ready_cbs(&sdp->srcu_cblist); spin_unlock_irq_rcu_node(sdp); diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index cb1caefa8bd07..7b4517dc46579 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include #include @@ -1556,10 +1557,22 @@ static bool rcu_gp_fqs_check_wake(int *gfp) */ static void rcu_gp_fqs(bool first_time) { + int nr_fqs = READ_ONCE(rcu_state.nr_fqs_jiffies_stall); struct rcu_node *rnp = rcu_get_root(); WRITE_ONCE(rcu_state.gp_activity, jiffies); WRITE_ONCE(rcu_state.n_force_qs, rcu_state.n_force_qs + 1); + + WARN_ON_ONCE(nr_fqs > 3); + /* Only countdown nr_fqs for stall purposes if jiffies moves. */ + if (nr_fqs) { + if (nr_fqs == 1) { + WRITE_ONCE(rcu_state.jiffies_stall, + jiffies + rcu_jiffies_till_stall_check()); + } + WRITE_ONCE(rcu_state.nr_fqs_jiffies_stall, --nr_fqs); + } + if (first_time) { /* Collect dyntick-idle snapshots. */ force_qs_rnp(dyntick_save_progress_counter); @@ -3388,6 +3401,14 @@ void kvfree_call_rcu(struct rcu_head *head, void *ptr) success = true; } + /* + * The kvfree_rcu() caller considers the pointer freed at this point + * and likely removes any references to it. Since the actual slab + * freeing (and kmemleak_free()) is deferred, tell kmemleak to ignore + * this object (no scanning or false positives reporting). + */ + kmemleak_ignore(ptr); + // Set timer to drain after KFREE_DRAIN_JIFFIES. if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING) schedule_delayed_monitor_work(krcp); diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 192536916f9a6..e9821a8422dbe 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -386,6 +386,10 @@ struct rcu_state { /* in jiffies. */ unsigned long jiffies_stall; /* Time at which to check */ /* for CPU stalls. */ + int nr_fqs_jiffies_stall; /* Number of fqs loops after + * which read jiffies and set + * jiffies_stall. Stall + * warnings disabled if !0. */ unsigned long jiffies_resched; /* Time at which to resched */ /* a reluctant CPU. */ unsigned long n_force_qs_gpstart; /* Snapshot of n_force_qs at */ diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h index 6f06dc12904ad..e09f4f624261e 100644 --- a/kernel/rcu/tree_stall.h +++ b/kernel/rcu/tree_stall.h @@ -149,12 +149,17 @@ static void panic_on_rcu_stall(void) /** * rcu_cpu_stall_reset - restart stall-warning timeout for current grace period * + * To perform the reset request from the caller, disable stall detection until + * 3 fqs loops have passed. This is required to ensure a fresh jiffies is + * loaded. It should be safe to do from the fqs loop as enough timer + * interrupts and context switches should have passed. + * * The caller must disable hard irqs. */ void rcu_cpu_stall_reset(void) { - WRITE_ONCE(rcu_state.jiffies_stall, - jiffies + rcu_jiffies_till_stall_check()); + WRITE_ONCE(rcu_state.nr_fqs_jiffies_stall, 3); + WRITE_ONCE(rcu_state.jiffies_stall, ULONG_MAX); } ////////////////////////////////////////////////////////////////////////////// @@ -170,6 +175,7 @@ static void record_gp_stall_check_time(void) WRITE_ONCE(rcu_state.gp_start, j); j1 = rcu_jiffies_till_stall_check(); smp_mb(); // ->gp_start before ->jiffies_stall and caller's ->gp_seq. + WRITE_ONCE(rcu_state.nr_fqs_jiffies_stall, 0); WRITE_ONCE(rcu_state.jiffies_stall, j + j1); rcu_state.jiffies_resched = j + j1 / 2; rcu_state.n_force_qs_gpstart = READ_ONCE(rcu_state.n_force_qs); @@ -725,6 +731,16 @@ static void check_cpu_stall(struct rcu_data *rdp) !rcu_gp_in_progress()) return; rcu_stall_kick_kthreads(); + + /* + * Check if it was requested (via rcu_cpu_stall_reset()) that the FQS + * loop has to set jiffies to ensure a non-stale jiffies value. This + * is required to have good jiffies value after coming out of long + * breaks of jiffies updates. Not doing so can cause false positives. + */ + if (READ_ONCE(rcu_state.nr_fqs_jiffies_stall) > 0) + return; + j = jiffies; /* diff --git a/kernel/reboot.c b/kernel/reboot.c index 3bba88c7ffc6b..6ebef11c88760 100644 --- a/kernel/reboot.c +++ b/kernel/reboot.c @@ -74,6 +74,7 @@ void __weak (*pm_power_off)(void); void emergency_restart(void) { kmsg_dump(KMSG_DUMP_EMERG); + system_state = SYSTEM_RESTART; machine_emergency_restart(); } EXPORT_SYMBOL_GPL(emergency_restart); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 9e9a45a3394fe..a854b71836dd5 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5378,8 +5378,6 @@ context_switch(struct rq *rq, struct task_struct *prev, /* switch_mm_cid() requires the memory barriers above. */ switch_mm_cid(rq, prev, next); - rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP); - prepare_lock_switch(rq, next, rf); /* Here we just switch the register state and the stack. */ @@ -6619,6 +6617,7 @@ static void __sched notrace __schedule(unsigned int sched_mode) /* Promote REQ to ACT */ rq->clock_update_flags <<= 1; update_rq_clock(rq); + rq->clock_update_flags = RQCF_UPDATED; switch_count = &prev->nivcsw; @@ -6698,8 +6697,6 @@ static void __sched notrace __schedule(unsigned int sched_mode) /* Also unlocks the rq: */ rq = context_switch(rq, prev, next, &rf); } else { - rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP); - rq_unpin_lock(rq, &rf); __balance_callbacks(rq); raw_spin_rq_unlock_irq(rq); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 1795f6fe991f3..fa9fff0f9620d 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3626,41 +3626,140 @@ static inline void dequeue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { } #endif +static void reweight_eevdf(struct cfs_rq *cfs_rq, struct sched_entity *se, + unsigned long weight) +{ + unsigned long old_weight = se->load.weight; + u64 avruntime = avg_vruntime(cfs_rq); + s64 vlag, vslice; + + /* + * VRUNTIME + * ======== + * + * COROLLARY #1: The virtual runtime of the entity needs to be + * adjusted if re-weight at !0-lag point. + * + * Proof: For contradiction assume this is not true, so we can + * re-weight without changing vruntime at !0-lag point. + * + * Weight VRuntime Avg-VRuntime + * before w v V + * after w' v' V' + * + * Since lag needs to be preserved through re-weight: + * + * lag = (V - v)*w = (V'- v')*w', where v = v' + * ==> V' = (V - v)*w/w' + v (1) + * + * Let W be the total weight of the entities before reweight, + * since V' is the new weighted average of entities: + * + * V' = (WV + w'v - wv) / (W + w' - w) (2) + * + * by using (1) & (2) we obtain: + * + * (WV + w'v - wv) / (W + w' - w) = (V - v)*w/w' + v + * ==> (WV-Wv+Wv+w'v-wv)/(W+w'-w) = (V - v)*w/w' + v + * ==> (WV - Wv)/(W + w' - w) + v = (V - v)*w/w' + v + * ==> (V - v)*W/(W + w' - w) = (V - v)*w/w' (3) + * + * Since we are doing at !0-lag point which means V != v, we + * can simplify (3): + * + * ==> W / (W + w' - w) = w / w' + * ==> Ww' = Ww + ww' - ww + * ==> W * (w' - w) = w * (w' - w) + * ==> W = w (re-weight indicates w' != w) + * + * So the cfs_rq contains only one entity, hence vruntime of + * the entity @v should always equal to the cfs_rq's weighted + * average vruntime @V, which means we will always re-weight + * at 0-lag point, thus breach assumption. Proof completed. + * + * + * COROLLARY #2: Re-weight does NOT affect weighted average + * vruntime of all the entities. + * + * Proof: According to corollary #1, Eq. (1) should be: + * + * (V - v)*w = (V' - v')*w' + * ==> v' = V' - (V - v)*w/w' (4) + * + * According to the weighted average formula, we have: + * + * V' = (WV - wv + w'v') / (W - w + w') + * = (WV - wv + w'(V' - (V - v)w/w')) / (W - w + w') + * = (WV - wv + w'V' - Vw + wv) / (W - w + w') + * = (WV + w'V' - Vw) / (W - w + w') + * + * ==> V'*(W - w + w') = WV + w'V' - Vw + * ==> V' * (W - w) = (W - w) * V (5) + * + * If the entity is the only one in the cfs_rq, then reweight + * always occurs at 0-lag point, so V won't change. Or else + * there are other entities, hence W != w, then Eq. (5) turns + * into V' = V. So V won't change in either case, proof done. + * + * + * So according to corollary #1 & #2, the effect of re-weight + * on vruntime should be: + * + * v' = V' - (V - v) * w / w' (4) + * = V - (V - v) * w / w' + * = V - vl * w / w' + * = V - vl' + */ + if (avruntime != se->vruntime) { + vlag = (s64)(avruntime - se->vruntime); + vlag = div_s64(vlag * old_weight, weight); + se->vruntime = avruntime - vlag; + } + + /* + * DEADLINE + * ======== + * + * When the weight changes, the virtual time slope changes and + * we should adjust the relative virtual deadline accordingly. + * + * d' = v' + (d - v)*w/w' + * = V' - (V - v)*w/w' + (d - v)*w/w' + * = V - (V - v)*w/w' + (d - v)*w/w' + * = V + (d - V)*w/w' + */ + vslice = (s64)(se->deadline - avruntime); + vslice = div_s64(vslice * old_weight, weight); + se->deadline = avruntime + vslice; +} + static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, unsigned long weight) { - unsigned long old_weight = se->load.weight; + bool curr = cfs_rq->curr == se; if (se->on_rq) { /* commit outstanding execution time */ - if (cfs_rq->curr == se) + if (curr) update_curr(cfs_rq); else - avg_vruntime_sub(cfs_rq, se); + __dequeue_entity(cfs_rq, se); update_load_sub(&cfs_rq->load, se->load.weight); } dequeue_load_avg(cfs_rq, se); - update_load_set(&se->load, weight); - if (!se->on_rq) { /* * Because we keep se->vlag = V - v_i, while: lag_i = w_i*(V - v_i), * we need to scale se->vlag when w_i changes. */ - se->vlag = div_s64(se->vlag * old_weight, weight); + se->vlag = div_s64(se->vlag * se->load.weight, weight); } else { - s64 deadline = se->deadline - se->vruntime; - /* - * When the weight changes, the virtual time slope changes and - * we should adjust the relative virtual deadline accordingly. - */ - deadline = div_s64(deadline * old_weight, weight); - se->deadline = se->vruntime + deadline; - if (se != cfs_rq->curr) - min_deadline_cb_propagate(&se->run_node, NULL); + reweight_eevdf(cfs_rq, se, weight); } + update_load_set(&se->load, weight); + #ifdef CONFIG_SMP do { u32 divider = get_pelt_divider(&se->avg); @@ -3672,8 +3771,17 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, enqueue_load_avg(cfs_rq, se); if (se->on_rq) { update_load_add(&cfs_rq->load, se->load.weight); - if (cfs_rq->curr != se) - avg_vruntime_add(cfs_rq, se); + if (!curr) { + /* + * The entity's vruntime has been adjusted, so let's check + * whether the rq-wide min_vruntime needs updated too. Since + * the calculations above require stable min_vruntime rather + * than up-to-date one, we do the update at the end of the + * reweight process. + */ + __enqueue_entity(cfs_rq, se); + update_min_vruntime(cfs_rq); + } } } @@ -3817,14 +3925,11 @@ static void update_cfs_group(struct sched_entity *se) #ifndef CONFIG_SMP shares = READ_ONCE(gcfs_rq->tg->shares); - - if (likely(se->load.weight == shares)) - return; #else - shares = calc_group_shares(gcfs_rq); + shares = calc_group_shares(gcfs_rq); #endif - - reweight_entity(cfs_rq_of(se), se, shares); + if (unlikely(se->load.weight != shares)) + reweight_entity(cfs_rq_of(se), se, shares); } #else /* CONFIG_FAIR_GROUP_SCHED */ @@ -11016,12 +11121,16 @@ static int should_we_balance(struct lb_env *env) continue; } - /* Are we the first idle CPU? */ + /* + * Are we the first idle core in a non-SMT domain or higher, + * or the first idle CPU in a SMT domain? + */ return cpu == env->dst_cpu; } - if (idle_smt == env->dst_cpu) - return true; + /* Are we the first idle CPU with busy siblings? */ + if (idle_smt != -1) + return idle_smt == env->dst_cpu; /* Are we the first CPU of this group ? */ return group_balance_cpu(sg) == env->dst_cpu; diff --git a/kernel/smp.c b/kernel/smp.c index 8455a53465af8..695eb13a276d2 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -170,6 +170,8 @@ static DEFINE_PER_CPU(void *, cur_csd_info); static ulong csd_lock_timeout = 5000; /* CSD lock timeout in milliseconds. */ module_param(csd_lock_timeout, ulong, 0444); +static int panic_on_ipistall; /* CSD panic timeout in milliseconds, 300000 for five minutes. */ +module_param(panic_on_ipistall, int, 0444); static atomic_t csd_bug_count = ATOMIC_INIT(0); @@ -230,6 +232,7 @@ static bool csd_lock_wait_toolong(struct __call_single_data *csd, u64 ts0, u64 * } ts2 = sched_clock(); + /* How long since we last checked for a stuck CSD lock.*/ ts_delta = ts2 - *ts1; if (likely(ts_delta <= csd_lock_timeout_ns || csd_lock_timeout_ns == 0)) return false; @@ -243,9 +246,17 @@ static bool csd_lock_wait_toolong(struct __call_single_data *csd, u64 ts0, u64 * else cpux = cpu; cpu_cur_csd = smp_load_acquire(&per_cpu(cur_csd, cpux)); /* Before func and info. */ + /* How long since this CSD lock was stuck. */ + ts_delta = ts2 - ts0; pr_alert("csd: %s non-responsive CSD lock (#%d) on CPU#%d, waiting %llu ns for CPU#%02d %pS(%ps).\n", - firsttime ? "Detected" : "Continued", *bug_id, raw_smp_processor_id(), ts2 - ts0, + firsttime ? "Detected" : "Continued", *bug_id, raw_smp_processor_id(), ts_delta, cpu, csd->func, csd->info); + /* + * If the CSD lock is still stuck after 5 minutes, it is unlikely + * to become unstuck. Use a signed comparison to avoid triggering + * on underflows when the TSC is out of sync between sockets. + */ + BUG_ON(panic_on_ipistall > 0 && (s64)ts_delta > ((s64)panic_on_ipistall * NSEC_PER_MSEC)); if (cpu_cur_csd && csd != cpu_cur_csd) { pr_alert("\tcsd: CSD lock (#%d) handling prior %pS(%ps) request.\n", *bug_id, READ_ONCE(per_cpu(cur_csd_func, cpux)), diff --git a/kernel/sys.c b/kernel/sys.c index 2410e3999ebe5..7a4ae6d5aecd5 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2368,19 +2368,45 @@ static int prctl_set_vma(unsigned long opt, unsigned long start, } #endif /* CONFIG_ANON_VMA_NAME */ +static inline unsigned long get_current_mdwe(void) +{ + unsigned long ret = 0; + + if (test_bit(MMF_HAS_MDWE, ¤t->mm->flags)) + ret |= PR_MDWE_REFUSE_EXEC_GAIN; + if (test_bit(MMF_HAS_MDWE_NO_INHERIT, ¤t->mm->flags)) + ret |= PR_MDWE_NO_INHERIT; + + return ret; +} + static inline int prctl_set_mdwe(unsigned long bits, unsigned long arg3, unsigned long arg4, unsigned long arg5) { + unsigned long current_bits; + if (arg3 || arg4 || arg5) return -EINVAL; - if (bits & ~(PR_MDWE_REFUSE_EXEC_GAIN)) + if (bits & ~(PR_MDWE_REFUSE_EXEC_GAIN | PR_MDWE_NO_INHERIT)) return -EINVAL; + /* NO_INHERIT only makes sense with REFUSE_EXEC_GAIN */ + if (bits & PR_MDWE_NO_INHERIT && !(bits & PR_MDWE_REFUSE_EXEC_GAIN)) + return -EINVAL; + + /* PARISC cannot allow mdwe as it needs writable stacks */ + if (IS_ENABLED(CONFIG_PARISC)) + return -EINVAL; + + current_bits = get_current_mdwe(); + if (current_bits && current_bits != bits) + return -EPERM; /* Cannot unset the flags */ + + if (bits & PR_MDWE_NO_INHERIT) + set_bit(MMF_HAS_MDWE_NO_INHERIT, ¤t->mm->flags); if (bits & PR_MDWE_REFUSE_EXEC_GAIN) set_bit(MMF_HAS_MDWE, ¤t->mm->flags); - else if (test_bit(MMF_HAS_MDWE, ¤t->mm->flags)) - return -EPERM; /* Cannot unset the flag */ return 0; } @@ -2390,9 +2416,7 @@ static inline int prctl_get_mdwe(unsigned long arg2, unsigned long arg3, { if (arg2 || arg3 || arg4 || arg5) return -EINVAL; - - return test_bit(MMF_HAS_MDWE, ¤t->mm->flags) ? - PR_MDWE_REFUSE_EXEC_GAIN : 0; + return get_current_mdwe(); } static int prctl_get_auxv(void __user *addr, unsigned long len) diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 238262e4aba7e..760793998cdd7 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -2219,29 +2219,22 @@ static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base, } } -int hrtimers_dead_cpu(unsigned int scpu) +int hrtimers_cpu_dying(unsigned int dying_cpu) { struct hrtimer_cpu_base *old_base, *new_base; - int i; + int i, ncpu = cpumask_first(cpu_active_mask); - BUG_ON(cpu_online(scpu)); - tick_cancel_sched_timer(scpu); + tick_cancel_sched_timer(dying_cpu); + + old_base = this_cpu_ptr(&hrtimer_bases); + new_base = &per_cpu(hrtimer_bases, ncpu); - /* - * this BH disable ensures that raise_softirq_irqoff() does - * not wakeup ksoftirqd (and acquire the pi-lock) while - * holding the cpu_base lock - */ - local_bh_disable(); - local_irq_disable(); - old_base = &per_cpu(hrtimer_bases, scpu); - new_base = this_cpu_ptr(&hrtimer_bases); /* * The caller is globally serialized and nobody else * takes two locks at once, deadlock is not possible. */ - raw_spin_lock(&new_base->lock); - raw_spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING); + raw_spin_lock(&old_base->lock); + raw_spin_lock_nested(&new_base->lock, SINGLE_DEPTH_NESTING); for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { migrate_hrtimer_list(&old_base->clock_base[i], @@ -2252,15 +2245,13 @@ int hrtimers_dead_cpu(unsigned int scpu) * The migration might have changed the first expiring softirq * timer on this CPU. Update it. */ - hrtimer_update_softirq_timer(new_base, false); + __hrtimer_get_next_event(new_base, HRTIMER_ACTIVE_SOFT); + /* Tell the other CPU to retrigger the next event */ + smp_call_function_single(ncpu, retrigger_next_event, NULL, 0); - raw_spin_unlock(&old_base->lock); raw_spin_unlock(&new_base->lock); + raw_spin_unlock(&old_base->lock); - /* Check, if we got expired work to do */ - __hrtimer_peek_ahead_timers(); - local_irq_enable(); - local_bh_enable(); return 0; } diff --git a/kernel/torture.c b/kernel/torture.c index b28b05bbef027..c7b475883b9a8 100644 --- a/kernel/torture.c +++ b/kernel/torture.c @@ -87,14 +87,15 @@ EXPORT_SYMBOL_GPL(verbose_torout_sleep); * nanosecond random fuzz. This function and its friends desynchronize * testing from the timer wheel. */ -int torture_hrtimeout_ns(ktime_t baset_ns, u32 fuzzt_ns, struct torture_random_state *trsp) +int torture_hrtimeout_ns(ktime_t baset_ns, u32 fuzzt_ns, const enum hrtimer_mode mode, + struct torture_random_state *trsp) { ktime_t hto = baset_ns; if (trsp) hto += torture_random(trsp) % fuzzt_ns; set_current_state(TASK_IDLE); - return schedule_hrtimeout(&hto, HRTIMER_MODE_REL); + return schedule_hrtimeout(&hto, mode); } EXPORT_SYMBOL_GPL(torture_hrtimeout_ns); @@ -106,7 +107,7 @@ int torture_hrtimeout_us(u32 baset_us, u32 fuzzt_ns, struct torture_random_state { ktime_t baset_ns = baset_us * NSEC_PER_USEC; - return torture_hrtimeout_ns(baset_ns, fuzzt_ns, trsp); + return torture_hrtimeout_ns(baset_ns, fuzzt_ns, HRTIMER_MODE_REL, trsp); } EXPORT_SYMBOL_GPL(torture_hrtimeout_us); @@ -123,7 +124,7 @@ int torture_hrtimeout_ms(u32 baset_ms, u32 fuzzt_us, struct torture_random_state fuzzt_ns = (u32)~0U; else fuzzt_ns = fuzzt_us * NSEC_PER_USEC; - return torture_hrtimeout_ns(baset_ns, fuzzt_ns, trsp); + return torture_hrtimeout_ns(baset_ns, fuzzt_ns, HRTIMER_MODE_REL, trsp); } EXPORT_SYMBOL_GPL(torture_hrtimeout_ms); @@ -136,7 +137,7 @@ int torture_hrtimeout_jiffies(u32 baset_j, struct torture_random_state *trsp) { ktime_t baset_ns = jiffies_to_nsecs(baset_j); - return torture_hrtimeout_ns(baset_ns, jiffies_to_nsecs(1), trsp); + return torture_hrtimeout_ns(baset_ns, jiffies_to_nsecs(1), HRTIMER_MODE_REL, trsp); } EXPORT_SYMBOL_GPL(torture_hrtimeout_jiffies); @@ -153,7 +154,7 @@ int torture_hrtimeout_s(u32 baset_s, u32 fuzzt_ms, struct torture_random_state * fuzzt_ns = (u32)~0U; else fuzzt_ns = fuzzt_ms * NSEC_PER_MSEC; - return torture_hrtimeout_ns(baset_ns, fuzzt_ns, trsp); + return torture_hrtimeout_ns(baset_ns, fuzzt_ns, HRTIMER_MODE_REL, trsp); } EXPORT_SYMBOL_GPL(torture_hrtimeout_s); @@ -720,7 +721,7 @@ static void torture_shutdown_cleanup(void) * suddenly applied to or removed from the system. */ static struct task_struct *stutter_task; -static int stutter_pause_test; +static ktime_t stutter_till_abs_time; static int stutter; static int stutter_gap; @@ -730,30 +731,16 @@ static int stutter_gap; */ bool stutter_wait(const char *title) { - unsigned int i = 0; bool ret = false; - int spt; + ktime_t till_ns; cond_resched_tasks_rcu_qs(); - spt = READ_ONCE(stutter_pause_test); - for (; spt; spt = READ_ONCE(stutter_pause_test)) { - if (!ret && !rt_task(current)) { - sched_set_normal(current, MAX_NICE); - ret = true; - } - if (spt == 1) { - torture_hrtimeout_jiffies(1, NULL); - } else if (spt == 2) { - while (READ_ONCE(stutter_pause_test)) { - if (!(i++ & 0xffff)) - torture_hrtimeout_us(10, 0, NULL); - cond_resched(); - } - } else { - torture_hrtimeout_jiffies(round_jiffies_relative(HZ), NULL); - } - torture_shutdown_absorb(title); + till_ns = READ_ONCE(stutter_till_abs_time); + if (till_ns && ktime_before(ktime_get(), till_ns)) { + torture_hrtimeout_ns(till_ns, 0, HRTIMER_MODE_ABS, NULL); + ret = true; } + torture_shutdown_absorb(title); return ret; } EXPORT_SYMBOL_GPL(stutter_wait); @@ -764,23 +751,16 @@ EXPORT_SYMBOL_GPL(stutter_wait); */ static int torture_stutter(void *arg) { - DEFINE_TORTURE_RANDOM(rand); - int wtime; + ktime_t till_ns; VERBOSE_TOROUT_STRING("torture_stutter task started"); do { if (!torture_must_stop() && stutter > 1) { - wtime = stutter; - if (stutter > 2) { - WRITE_ONCE(stutter_pause_test, 1); - wtime = stutter - 3; - torture_hrtimeout_jiffies(wtime, &rand); - wtime = 2; - } - WRITE_ONCE(stutter_pause_test, 2); - torture_hrtimeout_jiffies(wtime, NULL); + till_ns = ktime_add_ns(ktime_get(), + jiffies_to_nsecs(stutter)); + WRITE_ONCE(stutter_till_abs_time, till_ns); + torture_hrtimeout_jiffies(stutter - 1, NULL); } - WRITE_ONCE(stutter_pause_test, 0); if (!torture_must_stop()) torture_hrtimeout_jiffies(stutter_gap, NULL); torture_shutdown_absorb("torture_stutter"); diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 8de8bec5f3664..b01ae7d360218 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1183,18 +1183,19 @@ static void __add_hash_entry(struct ftrace_hash *hash, hash->count++; } -static int add_hash_entry(struct ftrace_hash *hash, unsigned long ip) +static struct ftrace_func_entry * +add_hash_entry(struct ftrace_hash *hash, unsigned long ip) { struct ftrace_func_entry *entry; entry = kmalloc(sizeof(*entry), GFP_KERNEL); if (!entry) - return -ENOMEM; + return NULL; entry->ip = ip; __add_hash_entry(hash, entry); - return 0; + return entry; } static void @@ -1349,7 +1350,6 @@ alloc_and_copy_ftrace_hash(int size_bits, struct ftrace_hash *hash) struct ftrace_func_entry *entry; struct ftrace_hash *new_hash; int size; - int ret; int i; new_hash = alloc_ftrace_hash(size_bits); @@ -1366,8 +1366,7 @@ alloc_and_copy_ftrace_hash(int size_bits, struct ftrace_hash *hash) size = 1 << hash->size_bits; for (i = 0; i < size; i++) { hlist_for_each_entry(entry, &hash->buckets[i], hlist) { - ret = add_hash_entry(new_hash, entry->ip); - if (ret < 0) + if (add_hash_entry(new_hash, entry->ip) == NULL) goto free_hash; } } @@ -2536,7 +2535,7 @@ ftrace_find_unique_ops(struct dyn_ftrace *rec) #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS /* Protected by rcu_tasks for reading, and direct_mutex for writing */ -static struct ftrace_hash *direct_functions = EMPTY_HASH; +static struct ftrace_hash __rcu *direct_functions = EMPTY_HASH; static DEFINE_MUTEX(direct_mutex); int ftrace_direct_func_count; @@ -2555,39 +2554,6 @@ unsigned long ftrace_find_rec_direct(unsigned long ip) return entry->direct; } -static struct ftrace_func_entry* -ftrace_add_rec_direct(unsigned long ip, unsigned long addr, - struct ftrace_hash **free_hash) -{ - struct ftrace_func_entry *entry; - - if (ftrace_hash_empty(direct_functions) || - direct_functions->count > 2 * (1 << direct_functions->size_bits)) { - struct ftrace_hash *new_hash; - int size = ftrace_hash_empty(direct_functions) ? 0 : - direct_functions->count + 1; - - if (size < 32) - size = 32; - - new_hash = dup_hash(direct_functions, size); - if (!new_hash) - return NULL; - - *free_hash = direct_functions; - direct_functions = new_hash; - } - - entry = kmalloc(sizeof(*entry), GFP_KERNEL); - if (!entry) - return NULL; - - entry->ip = ip; - entry->direct = addr; - __add_hash_entry(direct_functions, entry); - return entry; -} - static void call_direct_funcs(unsigned long ip, unsigned long pip, struct ftrace_ops *ops, struct ftrace_regs *fregs) { @@ -4223,8 +4189,8 @@ enter_record(struct ftrace_hash *hash, struct dyn_ftrace *rec, int clear_filter) /* Do nothing if it exists */ if (entry) return 0; - - ret = add_hash_entry(hash, rec->ip); + if (add_hash_entry(hash, rec->ip) == NULL) + ret = -ENOMEM; } return ret; } @@ -5266,7 +5232,8 @@ __ftrace_match_addr(struct ftrace_hash *hash, unsigned long ip, int remove) return 0; } - return add_hash_entry(hash, ip); + entry = add_hash_entry(hash, ip); + return entry ? 0 : -ENOMEM; } static int @@ -5410,7 +5377,7 @@ static void remove_direct_functions_hash(struct ftrace_hash *hash, unsigned long */ int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr) { - struct ftrace_hash *hash, *free_hash = NULL; + struct ftrace_hash *hash, *new_hash = NULL, *free_hash = NULL; struct ftrace_func_entry *entry, *new; int err = -EBUSY, size, i; @@ -5436,17 +5403,44 @@ int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr) } } - /* ... and insert them to direct_functions hash. */ err = -ENOMEM; + + /* Make a copy hash to place the new and the old entries in */ + size = hash->count + direct_functions->count; + if (size > 32) + size = 32; + new_hash = alloc_ftrace_hash(fls(size)); + if (!new_hash) + goto out_unlock; + + /* Now copy over the existing direct entries */ + size = 1 << direct_functions->size_bits; + for (i = 0; i < size; i++) { + hlist_for_each_entry(entry, &direct_functions->buckets[i], hlist) { + new = add_hash_entry(new_hash, entry->ip); + if (!new) + goto out_unlock; + new->direct = entry->direct; + } + } + + /* ... and add the new entries */ + size = 1 << hash->size_bits; for (i = 0; i < size; i++) { hlist_for_each_entry(entry, &hash->buckets[i], hlist) { - new = ftrace_add_rec_direct(entry->ip, addr, &free_hash); + new = add_hash_entry(new_hash, entry->ip); if (!new) - goto out_remove; + goto out_unlock; + /* Update both the copy and the hash entry */ + new->direct = addr; entry->direct = addr; } } + free_hash = direct_functions; + rcu_assign_pointer(direct_functions, new_hash); + new_hash = NULL; + ops->func = call_direct_funcs; ops->flags = MULTI_FLAGS; ops->trampoline = FTRACE_REGS_ADDR; @@ -5454,17 +5448,17 @@ int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr) err = register_ftrace_function_nolock(ops); - out_remove: - if (err) - remove_direct_functions_hash(hash, addr); - out_unlock: mutex_unlock(&direct_mutex); - if (free_hash) { + if (free_hash && free_hash != EMPTY_HASH) { synchronize_rcu_tasks(); free_ftrace_hash(free_hash); } + + if (new_hash) + free_ftrace_hash(new_hash); + return err; } EXPORT_SYMBOL_GPL(register_ftrace_direct); @@ -6309,7 +6303,7 @@ ftrace_graph_set_hash(struct ftrace_hash *hash, char *buffer) if (entry) continue; - if (add_hash_entry(hash, rec->ip) < 0) + if (add_hash_entry(hash, rec->ip) == NULL) goto out; } else { if (entry) { diff --git a/kernel/trace/rethook.c b/kernel/trace/rethook.c index 5eb9b598f4e9c..3cebcbaf35a44 100644 --- a/kernel/trace/rethook.c +++ b/kernel/trace/rethook.c @@ -63,7 +63,7 @@ static void rethook_free_rcu(struct rcu_head *head) */ void rethook_stop(struct rethook *rh) { - WRITE_ONCE(rh->handler, NULL); + rcu_assign_pointer(rh->handler, NULL); } /** @@ -78,11 +78,17 @@ void rethook_stop(struct rethook *rh) */ void rethook_free(struct rethook *rh) { - WRITE_ONCE(rh->handler, NULL); + rethook_stop(rh); call_rcu(&rh->rcu, rethook_free_rcu); } +static inline rethook_handler_t rethook_get_handler(struct rethook *rh) +{ + return (rethook_handler_t)rcu_dereference_check(rh->handler, + rcu_read_lock_any_held()); +} + /** * rethook_alloc() - Allocate struct rethook. * @data: a data to pass the @handler when hooking the return. @@ -102,7 +108,7 @@ struct rethook *rethook_alloc(void *data, rethook_handler_t handler) } rh->data = data; - rh->handler = handler; + rcu_assign_pointer(rh->handler, handler); rh->pool.head = NULL; refcount_set(&rh->ref, 1); @@ -142,9 +148,10 @@ static void free_rethook_node_rcu(struct rcu_head *head) */ void rethook_recycle(struct rethook_node *node) { - lockdep_assert_preemption_disabled(); + rethook_handler_t handler; - if (likely(READ_ONCE(node->rethook->handler))) + handler = rethook_get_handler(node->rethook); + if (likely(handler)) freelist_add(&node->freelist, &node->rethook->pool); else call_rcu(&node->rcu, free_rethook_node_rcu); @@ -160,11 +167,9 @@ NOKPROBE_SYMBOL(rethook_recycle); */ struct rethook_node *rethook_try_get(struct rethook *rh) { - rethook_handler_t handler = READ_ONCE(rh->handler); + rethook_handler_t handler = rethook_get_handler(rh); struct freelist_node *fn; - lockdep_assert_preemption_disabled(); - /* Check whether @rh is going to be freed. */ if (unlikely(!handler)) return NULL; @@ -312,7 +317,7 @@ unsigned long rethook_trampoline_handler(struct pt_regs *regs, rhn = container_of(first, struct rethook_node, llist); if (WARN_ON_ONCE(rhn->frame != frame)) break; - handler = READ_ONCE(rhn->rethook->handler); + handler = rethook_get_handler(rhn->rethook); if (handler) handler(rhn, rhn->rethook->data, correct_ret_addr, regs); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 515cafdb18d98..901a140e30fa1 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -644,8 +644,8 @@ static inline bool __rb_time_read(rb_time_t *t, u64 *ret, unsigned long *cnt) *cnt = rb_time_cnt(top); - /* If top and bottom counts don't match, this interrupted a write */ - if (*cnt != rb_time_cnt(bottom)) + /* If top, msb or bottom counts don't match, this interrupted a write */ + if (*cnt != rb_time_cnt(msb) || *cnt != rb_time_cnt(bottom)) return false; /* The shift to msb will lose its cnt bits */ @@ -700,44 +700,6 @@ rb_time_read_cmpxchg(local_t *l, unsigned long expect, unsigned long set) return local_try_cmpxchg(l, &expect, set); } -static bool rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set) -{ - unsigned long cnt, top, bottom, msb; - unsigned long cnt2, top2, bottom2, msb2; - u64 val; - - /* The cmpxchg always fails if it interrupted an update */ - if (!__rb_time_read(t, &val, &cnt2)) - return false; - - if (val != expect) - return false; - - cnt = local_read(&t->cnt); - if ((cnt & 3) != cnt2) - return false; - - cnt2 = cnt + 1; - - rb_time_split(val, &top, &bottom, &msb); - top = rb_time_val_cnt(top, cnt); - bottom = rb_time_val_cnt(bottom, cnt); - - rb_time_split(set, &top2, &bottom2, &msb2); - top2 = rb_time_val_cnt(top2, cnt2); - bottom2 = rb_time_val_cnt(bottom2, cnt2); - - if (!rb_time_read_cmpxchg(&t->cnt, cnt, cnt2)) - return false; - if (!rb_time_read_cmpxchg(&t->msb, msb, msb2)) - return false; - if (!rb_time_read_cmpxchg(&t->top, top, top2)) - return false; - if (!rb_time_read_cmpxchg(&t->bottom, bottom, bottom2)) - return false; - return true; -} - #else /* 64 bits */ /* local64_t always succeeds */ @@ -751,11 +713,6 @@ static void rb_time_set(rb_time_t *t, u64 val) { local64_set(&t->time, val); } - -static bool rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set) -{ - return local64_try_cmpxchg(&t->time, &expect, set); -} #endif /* @@ -924,9 +881,14 @@ static __always_inline bool full_hit(struct trace_buffer *buffer, int cpu, int f if (!nr_pages || !full) return true; - dirty = ring_buffer_nr_dirty_pages(buffer, cpu); + /* + * Add one as dirty will never equal nr_pages, as the sub-buffer + * that the writer is on is not counted as dirty. + * This is needed if "buffer_percent" is set to 100. + */ + dirty = ring_buffer_nr_dirty_pages(buffer, cpu) + 1; - return (dirty * 100) > (full * nr_pages); + return (dirty * 100) >= (full * nr_pages); } /* @@ -987,7 +949,8 @@ void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu) /* make sure the waiters see the new index */ smp_wmb(); - rb_wake_up_waiters(&rbwork->work); + /* This can be called in any context */ + irq_work_queue(&rbwork->work); } /** @@ -1787,6 +1750,8 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer) free_buffer_page(bpage); } + free_page((unsigned long)cpu_buffer->free_page); + kfree(cpu_buffer); } @@ -2407,7 +2372,7 @@ rb_iter_head_event(struct ring_buffer_iter *iter) */ barrier(); - if ((iter->head + length) > commit || length > BUF_MAX_DATA_SIZE) + if ((iter->head + length) > commit || length > BUF_PAGE_SIZE) /* Writer corrupted the read? */ goto reset; @@ -2981,25 +2946,6 @@ static unsigned rb_calculate_event_length(unsigned length) return length; } -static u64 rb_time_delta(struct ring_buffer_event *event) -{ - switch (event->type_len) { - case RINGBUF_TYPE_PADDING: - return 0; - - case RINGBUF_TYPE_TIME_EXTEND: - return rb_event_time_stamp(event); - - case RINGBUF_TYPE_TIME_STAMP: - return 0; - - case RINGBUF_TYPE_DATA: - return event->time_delta; - default: - return 0; - } -} - static inline bool rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer, struct ring_buffer_event *event) @@ -3007,8 +2953,6 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer, unsigned long new_index, old_index; struct buffer_page *bpage; unsigned long addr; - u64 write_stamp; - u64 delta; new_index = rb_event_index(event); old_index = new_index + rb_event_ts_length(event); @@ -3017,41 +2961,34 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer, bpage = READ_ONCE(cpu_buffer->tail_page); - delta = rb_time_delta(event); - - if (!rb_time_read(&cpu_buffer->write_stamp, &write_stamp)) - return false; - - /* Make sure the write stamp is read before testing the location */ - barrier(); - + /* + * Make sure the tail_page is still the same and + * the next write location is the end of this event + */ if (bpage->page == (void *)addr && rb_page_write(bpage) == old_index) { unsigned long write_mask = local_read(&bpage->write) & ~RB_WRITE_MASK; unsigned long event_length = rb_event_length(event); - /* Something came in, can't discard */ - if (!rb_time_cmpxchg(&cpu_buffer->write_stamp, - write_stamp, write_stamp - delta)) - return false; - /* - * It's possible that the event time delta is zero - * (has the same time stamp as the previous event) - * in which case write_stamp and before_stamp could - * be the same. In such a case, force before_stamp - * to be different than write_stamp. It doesn't - * matter what it is, as long as its different. + * For the before_stamp to be different than the write_stamp + * to make sure that the next event adds an absolute + * value and does not rely on the saved write stamp, which + * is now going to be bogus. + * + * By setting the before_stamp to zero, the next event + * is not going to use the write_stamp and will instead + * create an absolute timestamp. This means there's no + * reason to update the wirte_stamp! */ - if (!delta) - rb_time_set(&cpu_buffer->before_stamp, 0); + rb_time_set(&cpu_buffer->before_stamp, 0); /* * If an event were to come in now, it would see that the * write_stamp and the before_stamp are different, and assume * that this event just added itself before updating * the write stamp. The interrupting event will fix the - * write stamp for us, and use the before stamp as its delta. + * write stamp for us, and use an absolute timestamp. */ /* @@ -3488,7 +3425,7 @@ static void check_buffer(struct ring_buffer_per_cpu *cpu_buffer, return; /* - * If this interrupted another event, + * If this interrupted another event, */ if (atomic_inc_return(this_cpu_ptr(&checking)) != 1) goto out; @@ -3582,7 +3519,10 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, * absolute timestamp. * Don't bother if this is the start of a new page (w == 0). */ - if (unlikely(!a_ok || !b_ok || (info->before != info->after && w))) { + if (!w) { + /* Use the sub-buffer timestamp */ + info->delta = 0; + } else if (unlikely(!a_ok || !b_ok || info->before != info->after)) { info->add_timestamp |= RB_ADD_STAMP_FORCE | RB_ADD_STAMP_EXTEND; info->length += RB_LEN_TIME_EXTEND; } else { @@ -3605,26 +3545,19 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, /* See if we shot pass the end of this buffer page */ if (unlikely(write > BUF_PAGE_SIZE)) { - /* before and after may now different, fix it up*/ - b_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before); - a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after); - if (a_ok && b_ok && info->before != info->after) - (void)rb_time_cmpxchg(&cpu_buffer->before_stamp, - info->before, info->after); - if (a_ok && b_ok) - check_buffer(cpu_buffer, info, CHECK_FULL_PAGE); + check_buffer(cpu_buffer, info, CHECK_FULL_PAGE); return rb_move_tail(cpu_buffer, tail, info); } if (likely(tail == w)) { - u64 save_before; - bool s_ok; - /* Nothing interrupted us between A and C */ /*D*/ rb_time_set(&cpu_buffer->write_stamp, info->ts); - barrier(); - /*E*/ s_ok = rb_time_read(&cpu_buffer->before_stamp, &save_before); - RB_WARN_ON(cpu_buffer, !s_ok); + /* + * If something came in between C and D, the write stamp + * may now not be in sync. But that's fine as the before_stamp + * will be different and then next event will just be forced + * to use an absolute timestamp. + */ if (likely(!(info->add_timestamp & (RB_ADD_STAMP_FORCE | RB_ADD_STAMP_ABSOLUTE)))) /* This did not interrupt any time update */ @@ -3632,41 +3565,40 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, else /* Just use full timestamp for interrupting event */ info->delta = info->ts; - barrier(); check_buffer(cpu_buffer, info, tail); - if (unlikely(info->ts != save_before)) { - /* SLOW PATH - Interrupted between C and E */ - - a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after); - RB_WARN_ON(cpu_buffer, !a_ok); - - /* Write stamp must only go forward */ - if (save_before > info->after) { - /* - * We do not care about the result, only that - * it gets updated atomically. - */ - (void)rb_time_cmpxchg(&cpu_buffer->write_stamp, - info->after, save_before); - } - } } else { u64 ts; /* SLOW PATH - Interrupted between A and C */ - a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after); - /* Was interrupted before here, write_stamp must be valid */ + + /* Save the old before_stamp */ + a_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before); RB_WARN_ON(cpu_buffer, !a_ok); + + /* + * Read a new timestamp and update the before_stamp to make + * the next event after this one force using an absolute + * timestamp. This is in case an interrupt were to come in + * between E and F. + */ ts = rb_time_stamp(cpu_buffer->buffer); + rb_time_set(&cpu_buffer->before_stamp, ts); + + barrier(); + /*E*/ a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after); + /* Was interrupted before here, write_stamp must be valid */ + RB_WARN_ON(cpu_buffer, !a_ok); barrier(); - /*E*/ if (write == (local_read(&tail_page->write) & RB_WRITE_MASK) && - info->after < ts && - rb_time_cmpxchg(&cpu_buffer->write_stamp, - info->after, ts)) { - /* Nothing came after this event between C and E */ + /*F*/ if (write == (local_read(&tail_page->write) & RB_WRITE_MASK) && + info->after == info->before && info->after < ts) { + /* + * Nothing came after this event between C and F, it is + * safe to use info->after for the delta as it + * matched info->before and is still valid. + */ info->delta = ts - info->after; } else { /* - * Interrupted between C and E: + * Interrupted between C and F: * Lost the previous events time stamp. Just set the * delta to zero, and this will be the same time as * the event this event interrupted. And the events that @@ -3740,6 +3672,8 @@ rb_reserve_next_event(struct trace_buffer *buffer, if (ring_buffer_time_stamp_abs(cpu_buffer->buffer)) { add_ts_default = RB_ADD_STAMP_ABSOLUTE; info.length += RB_LEN_TIME_EXTEND; + if (info.length > BUF_MAX_DATA_SIZE) + goto out_fail; } else { add_ts_default = RB_ADD_STAMP_NONE; } @@ -5121,7 +5055,8 @@ ring_buffer_read_prepare(struct trace_buffer *buffer, int cpu, gfp_t flags) if (!iter) return NULL; - iter->event = kmalloc(BUF_MAX_DATA_SIZE, flags); + /* Holds the entire event: data and meta data */ + iter->event = kmalloc(BUF_PAGE_SIZE, flags); if (!iter->event) { kfree(iter); return NULL; diff --git a/kernel/trace/synth_event_gen_test.c b/kernel/trace/synth_event_gen_test.c index 8dfe85499d4a2..354c2117be43f 100644 --- a/kernel/trace/synth_event_gen_test.c +++ b/kernel/trace/synth_event_gen_test.c @@ -477,6 +477,17 @@ static int __init synth_event_gen_test_init(void) ret = test_trace_synth_event(); WARN_ON(ret); + + /* Disable when done */ + trace_array_set_clr_event(gen_synth_test->tr, + "synthetic", + "gen_synth_test", false); + trace_array_set_clr_event(empty_synth_test->tr, + "synthetic", + "empty_synth_test", false); + trace_array_set_clr_event(create_synth_test->tr, + "synthetic", + "create_synth_test", false); out: return ret; } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index a40d6baf101f0..a55f7d0913551 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1893,6 +1893,9 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu, __update_max_tr(tr, tsk, cpu); arch_spin_unlock(&tr->max_lock); + + /* Any waiters on the old snapshot buffer need to wake up */ + ring_buffer_wake_waiters(tr->array_buffer.buffer, RING_BUFFER_ALL_CPUS); } /** @@ -1944,12 +1947,23 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) static int wait_on_pipe(struct trace_iterator *iter, int full) { + int ret; + /* Iterators are static, they should be filled or empty */ if (trace_buffer_iter(iter, iter->cpu_file)) return 0; - return ring_buffer_wait(iter->array_buffer->buffer, iter->cpu_file, - full); + ret = ring_buffer_wait(iter->array_buffer->buffer, iter->cpu_file, full); + +#ifdef CONFIG_TRACER_MAX_TRACE + /* + * Make sure this is still the snapshot buffer, as if a snapshot were + * to happen, this would now be the main buffer. + */ + if (iter->snapshot) + iter->array_buffer = &iter->tr->max_buffer; +#endif + return ret; } #ifdef CONFIG_FTRACE_STARTUP_TEST @@ -2359,13 +2373,7 @@ int is_tracing_stopped(void) return global_trace.stop_count; } -/** - * tracing_start - quick start of the tracer - * - * If tracing is enabled but was stopped by tracing_stop, - * this will start the tracer back up. - */ -void tracing_start(void) +static void tracing_start_tr(struct trace_array *tr) { struct trace_buffer *buffer; unsigned long flags; @@ -2373,119 +2381,83 @@ void tracing_start(void) if (tracing_disabled) return; - raw_spin_lock_irqsave(&global_trace.start_lock, flags); - if (--global_trace.stop_count) { - if (global_trace.stop_count < 0) { + raw_spin_lock_irqsave(&tr->start_lock, flags); + if (--tr->stop_count) { + if (WARN_ON_ONCE(tr->stop_count < 0)) { /* Someone screwed up their debugging */ - WARN_ON_ONCE(1); - global_trace.stop_count = 0; + tr->stop_count = 0; } goto out; } /* Prevent the buffers from switching */ - arch_spin_lock(&global_trace.max_lock); + arch_spin_lock(&tr->max_lock); - buffer = global_trace.array_buffer.buffer; + buffer = tr->array_buffer.buffer; if (buffer) ring_buffer_record_enable(buffer); #ifdef CONFIG_TRACER_MAX_TRACE - buffer = global_trace.max_buffer.buffer; + buffer = tr->max_buffer.buffer; if (buffer) ring_buffer_record_enable(buffer); #endif - arch_spin_unlock(&global_trace.max_lock); - - out: - raw_spin_unlock_irqrestore(&global_trace.start_lock, flags); -} - -static void tracing_start_tr(struct trace_array *tr) -{ - struct trace_buffer *buffer; - unsigned long flags; - - if (tracing_disabled) - return; - - /* If global, we need to also start the max tracer */ - if (tr->flags & TRACE_ARRAY_FL_GLOBAL) - return tracing_start(); - - raw_spin_lock_irqsave(&tr->start_lock, flags); - - if (--tr->stop_count) { - if (tr->stop_count < 0) { - /* Someone screwed up their debugging */ - WARN_ON_ONCE(1); - tr->stop_count = 0; - } - goto out; - } - - buffer = tr->array_buffer.buffer; - if (buffer) - ring_buffer_record_enable(buffer); + arch_spin_unlock(&tr->max_lock); out: raw_spin_unlock_irqrestore(&tr->start_lock, flags); } /** - * tracing_stop - quick stop of the tracer + * tracing_start - quick start of the tracer * - * Light weight way to stop tracing. Use in conjunction with - * tracing_start. + * If tracing is enabled but was stopped by tracing_stop, + * this will start the tracer back up. */ -void tracing_stop(void) +void tracing_start(void) + +{ + return tracing_start_tr(&global_trace); +} + +static void tracing_stop_tr(struct trace_array *tr) { struct trace_buffer *buffer; unsigned long flags; - raw_spin_lock_irqsave(&global_trace.start_lock, flags); - if (global_trace.stop_count++) + raw_spin_lock_irqsave(&tr->start_lock, flags); + if (tr->stop_count++) goto out; /* Prevent the buffers from switching */ - arch_spin_lock(&global_trace.max_lock); + arch_spin_lock(&tr->max_lock); - buffer = global_trace.array_buffer.buffer; + buffer = tr->array_buffer.buffer; if (buffer) ring_buffer_record_disable(buffer); #ifdef CONFIG_TRACER_MAX_TRACE - buffer = global_trace.max_buffer.buffer; + buffer = tr->max_buffer.buffer; if (buffer) ring_buffer_record_disable(buffer); #endif - arch_spin_unlock(&global_trace.max_lock); + arch_spin_unlock(&tr->max_lock); out: - raw_spin_unlock_irqrestore(&global_trace.start_lock, flags); + raw_spin_unlock_irqrestore(&tr->start_lock, flags); } -static void tracing_stop_tr(struct trace_array *tr) +/** + * tracing_stop - quick stop of the tracer + * + * Light weight way to stop tracing. Use in conjunction with + * tracing_start. + */ +void tracing_stop(void) { - struct trace_buffer *buffer; - unsigned long flags; - - /* If global, we need to also stop the max tracer */ - if (tr->flags & TRACE_ARRAY_FL_GLOBAL) - return tracing_stop(); - - raw_spin_lock_irqsave(&tr->start_lock, flags); - if (tr->stop_count++) - goto out; - - buffer = tr->array_buffer.buffer; - if (buffer) - ring_buffer_record_disable(buffer); - - out: - raw_spin_unlock_irqrestore(&tr->start_lock, flags); + return tracing_stop_tr(&global_trace); } static int trace_save_cmdline(struct task_struct *tsk) @@ -2769,8 +2741,11 @@ void trace_buffered_event_enable(void) for_each_tracing_cpu(cpu) { page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL | __GFP_NORETRY, 0); - if (!page) - goto failed; + /* This is just an optimization and can handle failures */ + if (!page) { + pr_err("Failed to allocate event buffer\n"); + break; + } event = page_address(page); memset(event, 0, sizeof(*event)); @@ -2784,10 +2759,6 @@ void trace_buffered_event_enable(void) WARN_ON_ONCE(1); preempt_enable(); } - - return; - failed: - trace_buffered_event_disable(); } static void enable_trace_buffered_event(void *data) @@ -2822,11 +2793,9 @@ void trace_buffered_event_disable(void) if (--trace_buffered_event_ref) return; - preempt_disable(); /* For each CPU, set the buffer as used. */ - smp_call_function_many(tracing_buffer_mask, - disable_trace_buffered_event, NULL, 1); - preempt_enable(); + on_each_cpu_mask(tracing_buffer_mask, disable_trace_buffered_event, + NULL, true); /* Wait for all current users to finish */ synchronize_rcu(); @@ -2835,17 +2804,19 @@ void trace_buffered_event_disable(void) free_page((unsigned long)per_cpu(trace_buffered_event, cpu)); per_cpu(trace_buffered_event, cpu) = NULL; } + /* - * Make sure trace_buffered_event is NULL before clearing - * trace_buffered_event_cnt. + * Wait for all CPUs that potentially started checking if they can use + * their event buffer only after the previous synchronize_rcu() call and + * they still read a valid pointer from trace_buffered_event. It must be + * ensured they don't see cleared trace_buffered_event_cnt else they + * could wrongly decide to use the pointed-to buffer which is now freed. */ - smp_wmb(); + synchronize_rcu(); - preempt_disable(); - /* Do the work on each cpu */ - smp_call_function_many(tracing_buffer_mask, - enable_trace_buffered_event, NULL, 1); - preempt_enable(); + /* For each CPU, relinquish the buffer */ + on_each_cpu_mask(tracing_buffer_mask, enable_trace_buffered_event, NULL, + true); } static struct trace_buffer *temp_buffer; @@ -6395,13 +6366,15 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr, if (!tr->array_buffer.buffer) return 0; + /* Do not allow tracing while resizing ring buffer */ + tracing_stop_tr(tr); + ret = ring_buffer_resize(tr->array_buffer.buffer, size, cpu); if (ret < 0) - return ret; + goto out_start; #ifdef CONFIG_TRACER_MAX_TRACE - if (!(tr->flags & TRACE_ARRAY_FL_GLOBAL) || - !tr->current_trace->use_max_tr) + if (!tr->allocated_snapshot) goto out; ret = ring_buffer_resize(tr->max_buffer.buffer, size, cpu); @@ -6426,7 +6399,7 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr, WARN_ON(1); tracing_disabled = 1; } - return ret; + goto out_start; } update_buffer_entries(&tr->max_buffer, cpu); @@ -6435,7 +6408,8 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr, #endif /* CONFIG_TRACER_MAX_TRACE */ update_buffer_entries(&tr->array_buffer, cpu); - + out_start: + tracing_start_tr(tr); return ret; } @@ -8554,7 +8528,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, wait_index = READ_ONCE(iter->wait_index); - ret = wait_on_pipe(iter, iter->tr->buffer_percent); + ret = wait_on_pipe(iter, iter->snapshot ? 0 : iter->tr->buffer_percent); if (ret) goto out; diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c index 14cb275a0bab0..846e02c0fb59a 100644 --- a/kernel/trace/trace_events_synth.c +++ b/kernel/trace/trace_events_synth.c @@ -452,7 +452,7 @@ static unsigned int trace_string(struct synth_trace_event *entry, #ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE if ((unsigned long)str_val < TASK_SIZE) - ret = strncpy_from_user_nofault(str_field, str_val, STR_VAR_LEN_MAX); + ret = strncpy_from_user_nofault(str_field, (const void __user *)str_val, STR_VAR_LEN_MAX); else #endif ret = strncpy_from_kernel_nofault(str_field, str_val, STR_VAR_LEN_MAX); diff --git a/kernel/trace/trace_fprobe.c b/kernel/trace/trace_fprobe.c index 8bfe23af9c739..7d2ddbcfa377c 100644 --- a/kernel/trace/trace_fprobe.c +++ b/kernel/trace/trace_fprobe.c @@ -927,11 +927,12 @@ static int parse_symbol_and_return(int argc, const char *argv[], for (i = 2; i < argc; i++) { tmp = strstr(argv[i], "$retval"); if (tmp && !isalnum(tmp[7]) && tmp[7] != '_') { + if (is_tracepoint) { + trace_probe_log_set_index(i); + trace_probe_log_err(tmp - argv[i], RETVAL_ON_PROBE); + return -EINVAL; + } *is_return = true; - /* - * NOTE: Don't check is_tracepoint here, because it will - * be checked when the argument is parsed. - */ break; } } diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c index d0b6b390ee423..778b4056700ff 100644 --- a/kernel/watch_queue.c +++ b/kernel/watch_queue.c @@ -331,7 +331,7 @@ long watch_queue_set_filter(struct pipe_inode_info *pipe, filter.__reserved != 0) return -EINVAL; - tf = memdup_user(_filter->filters, filter.nr_filters * sizeof(*tf)); + tf = memdup_array_user(_filter->filters, filter.nr_filters, sizeof(*tf)); if (IS_ERR(tf)) return PTR_ERR(tf); diff --git a/kernel/watchdog.c b/kernel/watchdog.c index d145305d95fe8..5cd6d4e269157 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -283,6 +283,13 @@ static DEFINE_PER_CPU(struct hrtimer, watchdog_hrtimer); static DEFINE_PER_CPU(bool, softlockup_touch_sync); static unsigned long soft_lockup_nmi_warn; +static int __init softlockup_panic_setup(char *str) +{ + softlockup_panic = simple_strtoul(str, NULL, 0); + return 1; +} +__setup("softlockup_panic=", softlockup_panic_setup); + static int __init nowatchdog_setup(char *str) { watchdog_user_enabled = 0; diff --git a/kernel/workqueue.c b/kernel/workqueue.c index a3522b70218d3..e6a95bb74e228 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1684,9 +1684,6 @@ static int wq_select_unbound_cpu(int cpu) pr_warn_once("workqueue: round-robin CPU selection forced, expect performance impact\n"); } - if (cpumask_empty(wq_unbound_cpumask)) - return cpu; - new_cpu = __this_cpu_read(wq_rr_cpu_last); new_cpu = cpumask_next_and(new_cpu, wq_unbound_cpumask, cpu_online_mask); if (unlikely(new_cpu >= nr_cpu_ids)) { @@ -5622,50 +5619,54 @@ static void work_for_cpu_fn(struct work_struct *work) } /** - * work_on_cpu - run a function in thread context on a particular cpu + * work_on_cpu_key - run a function in thread context on a particular cpu * @cpu: the cpu to run on * @fn: the function to run * @arg: the function arg + * @key: The lock class key for lock debugging purposes * * It is up to the caller to ensure that the cpu doesn't go offline. * The caller must not hold any locks which would prevent @fn from completing. * * Return: The value @fn returns. */ -long work_on_cpu(int cpu, long (*fn)(void *), void *arg) +long work_on_cpu_key(int cpu, long (*fn)(void *), + void *arg, struct lock_class_key *key) { struct work_for_cpu wfc = { .fn = fn, .arg = arg }; - INIT_WORK_ONSTACK(&wfc.work, work_for_cpu_fn); + INIT_WORK_ONSTACK_KEY(&wfc.work, work_for_cpu_fn, key); schedule_work_on(cpu, &wfc.work); flush_work(&wfc.work); destroy_work_on_stack(&wfc.work); return wfc.ret; } -EXPORT_SYMBOL_GPL(work_on_cpu); +EXPORT_SYMBOL_GPL(work_on_cpu_key); /** - * work_on_cpu_safe - run a function in thread context on a particular cpu + * work_on_cpu_safe_key - run a function in thread context on a particular cpu * @cpu: the cpu to run on * @fn: the function to run * @arg: the function argument + * @key: The lock class key for lock debugging purposes * * Disables CPU hotplug and calls work_on_cpu(). The caller must not hold * any locks which would prevent @fn from completing. * * Return: The value @fn returns. */ -long work_on_cpu_safe(int cpu, long (*fn)(void *), void *arg) +long work_on_cpu_safe_key(int cpu, long (*fn)(void *), + void *arg, struct lock_class_key *key) { long ret = -ENODEV; cpus_read_lock(); if (cpu_online(cpu)) - ret = work_on_cpu(cpu, fn, arg); + ret = work_on_cpu_key(cpu, fn, arg, key); cpus_read_unlock(); return ret; } -EXPORT_SYMBOL_GPL(work_on_cpu_safe); +EXPORT_SYMBOL_GPL(work_on_cpu_safe_key); #endif /* CONFIG_SMP */ #ifdef CONFIG_FREEZER @@ -6511,6 +6512,17 @@ static inline void wq_watchdog_init(void) { } #endif /* CONFIG_WQ_WATCHDOG */ +static void __init restrict_unbound_cpumask(const char *name, const struct cpumask *mask) +{ + if (!cpumask_intersects(wq_unbound_cpumask, mask)) { + pr_warn("workqueue: Restricting unbound_cpumask (%*pb) with %s (%*pb) leaves no CPU, ignoring\n", + cpumask_pr_args(wq_unbound_cpumask), name, cpumask_pr_args(mask)); + return; + } + + cpumask_and(wq_unbound_cpumask, wq_unbound_cpumask, mask); +} + /** * workqueue_init_early - early init for workqueue subsystem * @@ -6530,11 +6542,11 @@ void __init workqueue_init_early(void) BUILD_BUG_ON(__alignof__(struct pool_workqueue) < __alignof__(long long)); BUG_ON(!alloc_cpumask_var(&wq_unbound_cpumask, GFP_KERNEL)); - cpumask_copy(wq_unbound_cpumask, housekeeping_cpumask(HK_TYPE_WQ)); - cpumask_and(wq_unbound_cpumask, wq_unbound_cpumask, housekeeping_cpumask(HK_TYPE_DOMAIN)); - + cpumask_copy(wq_unbound_cpumask, cpu_possible_mask); + restrict_unbound_cpumask("HK_TYPE_WQ", housekeeping_cpumask(HK_TYPE_WQ)); + restrict_unbound_cpumask("HK_TYPE_DOMAIN", housekeeping_cpumask(HK_TYPE_DOMAIN)); if (!cpumask_empty(&wq_cmdline_cpumask)) - cpumask_and(wq_unbound_cpumask, wq_unbound_cpumask, &wq_cmdline_cpumask); + restrict_unbound_cpumask("workqueue.unbound_cpus", &wq_cmdline_cpumask); pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC); diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index fa307f93fa2e2..1331f3186f2ad 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1730,21 +1730,6 @@ config DEBUG_MAPLE_TREE endmenu -config DEBUG_CREDENTIALS - bool "Debug credential management" - depends on DEBUG_KERNEL - help - Enable this to turn on some debug checking for credential - management. The additional code keeps track of the number of - pointers from task_structs to any given cred struct, and checks to - see that this number never exceeds the usage count of the cred - struct. - - Furthermore, if SELinux is enabled, this also checks that the - security pointer in the cred struct is never seen to be invalid. - - If unsure, say N. - source "kernel/rcu/Kconfig.debug" config DEBUG_WQ_FORCE_RR_CPU diff --git a/lib/errname.c b/lib/errname.c index 67739b174a8cc..0c336b0f12f60 100644 --- a/lib/errname.c +++ b/lib/errname.c @@ -111,9 +111,6 @@ static const char *names_0[] = { E(ENOSPC), E(ENOSR), E(ENOSTR), -#ifdef ENOSYM - E(ENOSYM), -#endif E(ENOSYS), E(ENOTBLK), E(ENOTCONN), @@ -144,9 +141,6 @@ static const char *names_0[] = { #endif E(EREMOTE), E(EREMOTEIO), -#ifdef EREMOTERELEASE - E(EREMOTERELEASE), -#endif E(ERESTART), E(ERFKILL), E(EROFS), diff --git a/lib/generic-radix-tree.c b/lib/generic-radix-tree.c index f25eb111c0516..7dfa88282b006 100644 --- a/lib/generic-radix-tree.c +++ b/lib/generic-radix-tree.c @@ -166,6 +166,10 @@ void *__genradix_iter_peek(struct genradix_iter *iter, struct genradix_root *r; struct genradix_node *n; unsigned level, i; + + if (iter->offset == SIZE_MAX) + return NULL; + restart: r = READ_ONCE(radix->root); if (!r) @@ -184,10 +188,17 @@ void *__genradix_iter_peek(struct genradix_iter *iter, (GENRADIX_ARY - 1); while (!n->children[i]) { + size_t objs_per_ptr = genradix_depth_size(level); + + if (iter->offset + objs_per_ptr < iter->offset) { + iter->offset = SIZE_MAX; + iter->pos = SIZE_MAX; + return NULL; + } + i++; - iter->offset = round_down(iter->offset + - genradix_depth_size(level), - genradix_depth_size(level)); + iter->offset = round_down(iter->offset + objs_per_ptr, + objs_per_ptr); iter->pos = (iter->offset >> PAGE_SHIFT) * objs_per_page; if (i == GENRADIX_ARY) diff --git a/lib/group_cpus.c b/lib/group_cpus.c index aa3f6815bb124..ee272c4cefcc1 100644 --- a/lib/group_cpus.c +++ b/lib/group_cpus.c @@ -366,13 +366,25 @@ struct cpumask *group_cpus_evenly(unsigned int numgrps) if (!masks) goto fail_node_to_cpumask; - /* Stabilize the cpumasks */ - cpus_read_lock(); build_node_to_cpumask(node_to_cpumask); + /* + * Make a local cache of 'cpu_present_mask', so the two stages + * spread can observe consistent 'cpu_present_mask' without holding + * cpu hotplug lock, then we can reduce deadlock risk with cpu + * hotplug code. + * + * Here CPU hotplug may happen when reading `cpu_present_mask`, and + * we can live with the case because it only affects that hotplug + * CPU is handled in the 1st or 2nd stage, and either way is correct + * from API user viewpoint since 2-stage spread is sort of + * optimization. + */ + cpumask_copy(npresmsk, data_race(cpu_present_mask)); + /* grouping present CPUs first */ ret = __group_cpus_evenly(curgrp, numgrps, node_to_cpumask, - cpu_present_mask, nmsk, masks); + npresmsk, nmsk, masks); if (ret < 0) goto fail_build_affinity; nr_present = ret; @@ -387,15 +399,13 @@ struct cpumask *group_cpus_evenly(unsigned int numgrps) curgrp = 0; else curgrp = nr_present; - cpumask_andnot(npresmsk, cpu_possible_mask, cpu_present_mask); + cpumask_andnot(npresmsk, cpu_possible_mask, npresmsk); ret = __group_cpus_evenly(curgrp, numgrps, node_to_cpumask, npresmsk, nmsk, masks); if (ret >= 0) nr_others = ret; fail_build_affinity: - cpus_read_unlock(); - if (ret >= 0) WARN_ON(nr_present + nr_others < numgrps); diff --git a/lib/maple_tree.c b/lib/maple_tree.c index bb24d84a4922f..684689457d77f 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -5501,6 +5501,17 @@ int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp) mas_wr_end_piv(&wr_mas); node_size = mas_wr_new_end(&wr_mas); + + /* Slot store, does not require additional nodes */ + if (node_size == wr_mas.node_end) { + /* reuse node */ + if (!mt_in_rcu(mas->tree)) + return 0; + /* shifting boundary */ + if (wr_mas.offset_end - mas->offset == 1) + return 0; + } + if (node_size >= mt_slots[wr_mas.type]) { /* Split, worst case for now. */ request = 1 + mas_mt_height(mas) * 2; diff --git a/lib/vsprintf.c b/lib/vsprintf.c index afb88b24fa748..2aa408441cd3e 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -2110,15 +2110,20 @@ char *fwnode_full_name_string(struct fwnode_handle *fwnode, char *buf, /* Loop starting from the root node to the current node. */ for (depth = fwnode_count_parents(fwnode); depth >= 0; depth--) { - struct fwnode_handle *__fwnode = - fwnode_get_nth_parent(fwnode, depth); + /* + * Only get a reference for other nodes (i.e. parent nodes). + * fwnode refcount may be 0 here. + */ + struct fwnode_handle *__fwnode = depth ? + fwnode_get_nth_parent(fwnode, depth) : fwnode; buf = string(buf, end, fwnode_get_name_prefix(__fwnode), default_str_spec); buf = string(buf, end, fwnode_get_name(__fwnode), default_str_spec); - fwnode_handle_put(__fwnode); + if (depth) + fwnode_handle_put(__fwnode); } return buf; diff --git a/lib/zstd/common/fse_decompress.c b/lib/zstd/common/fse_decompress.c index a0d06095be83d..8dcb8ca39767c 100644 --- a/lib/zstd/common/fse_decompress.c +++ b/lib/zstd/common/fse_decompress.c @@ -312,7 +312,7 @@ size_t FSE_decompress_wksp(void* dst, size_t dstCapacity, const void* cSrc, size typedef struct { short ncount[FSE_MAX_SYMBOL_VALUE + 1]; - FSE_DTable dtable[1]; /* Dynamically sized */ + FSE_DTable dtable[]; /* Dynamically sized */ } FSE_DecompressWksp; diff --git a/mm/cma.c b/mm/cma.c index da2967c6a2238..2b2494fd6b59a 100644 --- a/mm/cma.c +++ b/mm/cma.c @@ -505,7 +505,7 @@ struct page *cma_alloc(struct cma *cma, unsigned long count, */ if (page) { for (i = 0; i < count; i++) - page_kasan_tag_reset(page + i); + page_kasan_tag_reset(nth_page(page, i)); } if (ret && !no_warn) { diff --git a/mm/damon/core.c b/mm/damon/core.c index bcd2bd9d6c104..aff611b6eafe1 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -423,12 +423,16 @@ struct damon_ctx *damon_new_ctx(void) if (!ctx) return NULL; + init_completion(&ctx->kdamond_started); + ctx->attrs.sample_interval = 5 * 1000; ctx->attrs.aggr_interval = 100 * 1000; ctx->attrs.ops_update_interval = 60 * 1000 * 1000; - ktime_get_coarse_ts64(&ctx->last_aggregation); - ctx->last_ops_update = ctx->last_aggregation; + ctx->passed_sample_intervals = 0; + /* These will be set from kdamond_init_intervals_sis() */ + ctx->next_aggregation_sis = 0; + ctx->next_ops_update_sis = 0; mutex_init(&ctx->kdamond_lock); @@ -476,20 +480,14 @@ static unsigned int damon_age_for_new_attrs(unsigned int age, static unsigned int damon_accesses_bp_to_nr_accesses( unsigned int accesses_bp, struct damon_attrs *attrs) { - unsigned int max_nr_accesses = - attrs->aggr_interval / attrs->sample_interval; - - return accesses_bp * max_nr_accesses / 10000; + return accesses_bp * damon_max_nr_accesses(attrs) / 10000; } /* convert nr_accesses to access ratio in bp (per 10,000) */ static unsigned int damon_nr_accesses_to_accesses_bp( unsigned int nr_accesses, struct damon_attrs *attrs) { - unsigned int max_nr_accesses = - attrs->aggr_interval / attrs->sample_interval; - - return nr_accesses * 10000 / max_nr_accesses; + return nr_accesses * 10000 / damon_max_nr_accesses(attrs); } static unsigned int damon_nr_accesses_for_new_attrs(unsigned int nr_accesses, @@ -548,6 +546,9 @@ static void damon_update_monitoring_results(struct damon_ctx *ctx, */ int damon_set_attrs(struct damon_ctx *ctx, struct damon_attrs *attrs) { + unsigned long sample_interval = attrs->sample_interval ? + attrs->sample_interval : 1; + if (attrs->min_nr_regions < 3) return -EINVAL; if (attrs->min_nr_regions > attrs->max_nr_regions) @@ -555,6 +556,11 @@ int damon_set_attrs(struct damon_ctx *ctx, struct damon_attrs *attrs) if (attrs->sample_interval > attrs->aggr_interval) return -EINVAL; + ctx->next_aggregation_sis = ctx->passed_sample_intervals + + attrs->aggr_interval / sample_interval; + ctx->next_ops_update_sis = ctx->passed_sample_intervals + + attrs->ops_update_interval / sample_interval; + damon_update_monitoring_results(ctx, attrs); ctx->attrs = *attrs; return 0; @@ -632,11 +638,14 @@ static int __damon_start(struct damon_ctx *ctx) mutex_lock(&ctx->kdamond_lock); if (!ctx->kdamond) { err = 0; + reinit_completion(&ctx->kdamond_started); ctx->kdamond = kthread_run(kdamond_fn, ctx, "kdamond.%d", nr_running_ctxs); if (IS_ERR(ctx->kdamond)) { err = PTR_ERR(ctx->kdamond); ctx->kdamond = NULL; + } else { + wait_for_completion(&ctx->kdamond_started); } } mutex_unlock(&ctx->kdamond_lock); @@ -728,38 +737,6 @@ int damon_stop(struct damon_ctx **ctxs, int nr_ctxs) return err; } -/* - * damon_check_reset_time_interval() - Check if a time interval is elapsed. - * @baseline: the time to check whether the interval has elapsed since - * @interval: the time interval (microseconds) - * - * See whether the given time interval has passed since the given baseline - * time. If so, it also updates the baseline to current time for next check. - * - * Return: true if the time interval has passed, or false otherwise. - */ -static bool damon_check_reset_time_interval(struct timespec64 *baseline, - unsigned long interval) -{ - struct timespec64 now; - - ktime_get_coarse_ts64(&now); - if ((timespec64_to_ns(&now) - timespec64_to_ns(baseline)) < - interval * 1000) - return false; - *baseline = now; - return true; -} - -/* - * Check whether it is time to flush the aggregated information - */ -static bool kdamond_aggregate_interval_passed(struct damon_ctx *ctx) -{ - return damon_check_reset_time_interval(&ctx->last_aggregation, - ctx->attrs.aggr_interval); -} - /* * Reset the aggregated monitoring results ('nr_accesses' of each region). */ @@ -920,7 +897,7 @@ static bool __damos_filter_out(struct damon_ctx *ctx, struct damon_target *t, matched = true; break; default: - break; + return false; } return matched == filter->matching; @@ -1240,18 +1217,6 @@ static void kdamond_split_regions(struct damon_ctx *ctx) last_nr_regions = nr_regions; } -/* - * Check whether it is time to check and apply the operations-related data - * structures. - * - * Returns true if it is. - */ -static bool kdamond_need_update_operations(struct damon_ctx *ctx) -{ - return damon_check_reset_time_interval(&ctx->last_ops_update, - ctx->attrs.ops_update_interval); -} - /* * Check whether current monitoring should be stopped * @@ -1363,6 +1328,17 @@ static int kdamond_wait_activation(struct damon_ctx *ctx) return -EBUSY; } +static void kdamond_init_intervals_sis(struct damon_ctx *ctx) +{ + unsigned long sample_interval = ctx->attrs.sample_interval ? + ctx->attrs.sample_interval : 1; + + ctx->passed_sample_intervals = 0; + ctx->next_aggregation_sis = ctx->attrs.aggr_interval / sample_interval; + ctx->next_ops_update_sis = ctx->attrs.ops_update_interval / + sample_interval; +} + /* * The monitoring daemon that runs as a kernel thread */ @@ -1376,6 +1352,9 @@ static int kdamond_fn(void *data) pr_debug("kdamond (%d) starts\n", current->pid); + complete(&ctx->kdamond_started); + kdamond_init_intervals_sis(ctx); + if (ctx->ops.init) ctx->ops.init(ctx); if (ctx->callback.before_start && ctx->callback.before_start(ctx)) @@ -1384,6 +1363,17 @@ static int kdamond_fn(void *data) sz_limit = damon_region_sz_limit(ctx); while (!kdamond_need_stop(ctx)) { + /* + * ctx->attrs and ctx->next_{aggregation,ops_update}_sis could + * be changed from after_wmarks_check() or after_aggregation() + * callbacks. Read the values here, and use those for this + * iteration. That is, damon_set_attrs() updated new values + * are respected from next iteration. + */ + unsigned long next_aggregation_sis = ctx->next_aggregation_sis; + unsigned long next_ops_update_sis = ctx->next_ops_update_sis; + unsigned long sample_interval = ctx->attrs.sample_interval; + if (kdamond_wait_activation(ctx)) break; @@ -1393,12 +1383,17 @@ static int kdamond_fn(void *data) ctx->callback.after_sampling(ctx)) break; - kdamond_usleep(ctx->attrs.sample_interval); + kdamond_usleep(sample_interval); + ctx->passed_sample_intervals++; if (ctx->ops.check_accesses) max_nr_accesses = ctx->ops.check_accesses(ctx); - if (kdamond_aggregate_interval_passed(ctx)) { + sample_interval = ctx->attrs.sample_interval ? + ctx->attrs.sample_interval : 1; + if (ctx->passed_sample_intervals == next_aggregation_sis) { + ctx->next_aggregation_sis = next_aggregation_sis + + ctx->attrs.aggr_interval / sample_interval; kdamond_merge_regions(ctx, max_nr_accesses / 10, sz_limit); @@ -1413,7 +1408,10 @@ static int kdamond_fn(void *data) ctx->ops.reset_aggregated(ctx); } - if (kdamond_need_update_operations(ctx)) { + if (ctx->passed_sample_intervals == next_ops_update_sis) { + ctx->next_ops_update_sis = next_ops_update_sis + + ctx->attrs.ops_update_interval / + sample_interval; if (ctx->ops.update) ctx->ops.update(ctx); sz_limit = damon_region_sz_limit(ctx); diff --git a/mm/damon/lru_sort.c b/mm/damon/lru_sort.c index 7b8fce2f67a8d..3071e08e8b8f8 100644 --- a/mm/damon/lru_sort.c +++ b/mm/damon/lru_sort.c @@ -193,9 +193,7 @@ static int damon_lru_sort_apply_parameters(void) if (err) return err; - /* aggr_interval / sample_interval is the maximum nr_accesses */ - hot_thres = damon_lru_sort_mon_attrs.aggr_interval / - damon_lru_sort_mon_attrs.sample_interval * + hot_thres = damon_max_nr_accesses(&damon_lru_sort_mon_attrs) * hot_thres_access_freq / 1000; scheme = damon_lru_sort_new_hot_scheme(hot_thres); if (!scheme) diff --git a/mm/damon/ops-common.c b/mm/damon/ops-common.c index ac1c3fa80f984..d25d99cb5f2bb 100644 --- a/mm/damon/ops-common.c +++ b/mm/damon/ops-common.c @@ -73,7 +73,6 @@ void damon_pmdp_mkold(pmd_t *pmd, struct vm_area_struct *vma, unsigned long addr int damon_hot_score(struct damon_ctx *c, struct damon_region *r, struct damos *s) { - unsigned int max_nr_accesses; int freq_subscore; unsigned int age_in_sec; int age_in_log, age_subscore; @@ -81,8 +80,8 @@ int damon_hot_score(struct damon_ctx *c, struct damon_region *r, unsigned int age_weight = s->quota.weight_age; int hotness; - max_nr_accesses = c->attrs.aggr_interval / c->attrs.sample_interval; - freq_subscore = r->nr_accesses * DAMON_MAX_SUBSCORE / max_nr_accesses; + freq_subscore = r->nr_accesses * DAMON_MAX_SUBSCORE / + damon_max_nr_accesses(&c->attrs); age_in_sec = (unsigned long)r->age * c->attrs.aggr_interval / 1000000; for (age_in_log = 0; age_in_log < DAMON_MAX_AGE_IN_LOG && age_in_sec; diff --git a/mm/damon/sysfs-schemes.c b/mm/damon/sysfs-schemes.c index 527e7d17eb3b2..36dcd881a19c0 100644 --- a/mm/damon/sysfs-schemes.c +++ b/mm/damon/sysfs-schemes.c @@ -126,6 +126,9 @@ damon_sysfs_scheme_regions_alloc(void) struct damon_sysfs_scheme_regions *regions = kmalloc(sizeof(*regions), GFP_KERNEL); + if (!regions) + return NULL; + regions->kobj = (struct kobject){}; INIT_LIST_HEAD(®ions->regions_list); regions->nr_regions = 0; @@ -1752,6 +1755,8 @@ static int damon_sysfs_before_damos_apply(struct damon_ctx *ctx, return 0; region = damon_sysfs_scheme_region_alloc(r); + if (!region) + return 0; list_add_tail(®ion->list, &sysfs_regions->regions_list); sysfs_regions->nr_regions++; if (kobject_init_and_add(®ion->kobj, diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c index f60e56150feb6..b317f51dcc987 100644 --- a/mm/damon/sysfs.c +++ b/mm/damon/sysfs.c @@ -1150,58 +1150,75 @@ static int damon_sysfs_add_target(struct damon_sysfs_target *sys_target, return err; } -/* - * Search a target in a context that corresponds to the sysfs target input. - * - * Return: pointer to the target if found, NULL if not found, or negative - * error code if the search failed. - */ -static struct damon_target *damon_sysfs_existing_target( - struct damon_sysfs_target *sys_target, struct damon_ctx *ctx) +static int damon_sysfs_update_target_pid(struct damon_target *target, int pid) { - struct pid *pid; - struct damon_target *t; + struct pid *pid_new; - if (!damon_target_has_pid(ctx)) { - /* Up to only one target for paddr could exist */ - damon_for_each_target(t, ctx) - return t; - return NULL; + pid_new = find_get_pid(pid); + if (!pid_new) + return -EINVAL; + + if (pid_new == target->pid) { + put_pid(pid_new); + return 0; } - /* ops.id should be DAMON_OPS_VADDR or DAMON_OPS_FVADDR */ - pid = find_get_pid(sys_target->pid); - if (!pid) - return ERR_PTR(-EINVAL); - damon_for_each_target(t, ctx) { - if (t->pid == pid) { - put_pid(pid); - return t; - } + put_pid(target->pid); + target->pid = pid_new; + return 0; +} + +static int damon_sysfs_update_target(struct damon_target *target, + struct damon_ctx *ctx, + struct damon_sysfs_target *sys_target) +{ + int err = 0; + + if (damon_target_has_pid(ctx)) { + err = damon_sysfs_update_target_pid(target, sys_target->pid); + if (err) + return err; } - put_pid(pid); - return NULL; + + /* + * Do monitoring target region boundary update only if one or more + * regions are set by the user. This is for keeping current monitoring + * target results and range easier, especially for dynamic monitoring + * target regions update ops like 'vaddr'. + */ + if (sys_target->regions->nr) + err = damon_sysfs_set_regions(target, sys_target->regions); + return err; } static int damon_sysfs_set_targets(struct damon_ctx *ctx, struct damon_sysfs_targets *sysfs_targets) { - int i, err; + struct damon_target *t, *next; + int i = 0, err; /* Multiple physical address space monitoring targets makes no sense */ if (ctx->ops.id == DAMON_OPS_PADDR && sysfs_targets->nr > 1) return -EINVAL; - for (i = 0; i < sysfs_targets->nr; i++) { + damon_for_each_target_safe(t, next, ctx) { + if (i < sysfs_targets->nr) { + err = damon_sysfs_update_target(t, ctx, + sysfs_targets->targets_arr[i]); + if (err) + return err; + } else { + if (damon_target_has_pid(ctx)) + put_pid(t->pid); + damon_destroy_target(t); + } + i++; + } + + for (; i < sysfs_targets->nr; i++) { struct damon_sysfs_target *st = sysfs_targets->targets_arr[i]; - struct damon_target *t = damon_sysfs_existing_target(st, ctx); - - if (IS_ERR(t)) - return PTR_ERR(t); - if (!t) - err = damon_sysfs_add_target(st, ctx); - else - err = damon_sysfs_set_regions(t, st->regions); + + err = damon_sysfs_add_target(st, ctx); if (err) return err; } diff --git a/mm/filemap.c b/mm/filemap.c index f0a15ce1bd1ba..b1ef7be1205be 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2666,6 +2666,15 @@ ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter, goto put_folios; end_offset = min_t(loff_t, isize, iocb->ki_pos + iter->count); + /* + * Pairs with a barrier in + * block_write_end()->mark_buffer_dirty() or other page + * dirtying routines like iomap_write_end() to ensure + * changes to page contents are visible before we see + * increased inode size. + */ + smp_rmb(); + /* * Once we start copying data, we don't want to be touching any * cachelines that might be contended: @@ -3422,7 +3431,7 @@ static bool filemap_map_pmd(struct vm_fault *vmf, struct folio *folio, } } - if (pmd_none(*vmf->pmd)) + if (pmd_none(*vmf->pmd) && vmf->prealloc_pte) pmd_install(mm, vmf->pmd, &vmf->prealloc_pte); return false; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 064fbd90822b4..874000f97bfc1 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2737,13 +2737,15 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) int nr = folio_nr_pages(folio); xas_split(&xas, folio, folio_order(folio)); - if (folio_test_swapbacked(folio)) { - __lruvec_stat_mod_folio(folio, NR_SHMEM_THPS, - -nr); - } else { - __lruvec_stat_mod_folio(folio, NR_FILE_THPS, - -nr); - filemap_nr_thps_dec(mapping); + if (folio_test_pmd_mappable(folio)) { + if (folio_test_swapbacked(folio)) { + __lruvec_stat_mod_folio(folio, + NR_SHMEM_THPS, -nr); + } else { + __lruvec_stat_mod_folio(folio, + NR_FILE_THPS, -nr); + filemap_nr_thps_dec(mapping); + } } } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 1301ba7b2c9a9..5e6c4d367d33a 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1189,6 +1189,13 @@ static int is_vma_resv_set(struct vm_area_struct *vma, unsigned long flag) return (get_vma_private_data(vma) & flag) != 0; } +bool __vma_private_lock(struct vm_area_struct *vma) +{ + return !(vma->vm_flags & VM_MAYSHARE) && + get_vma_private_data(vma) & ~HPAGE_RESV_MASK && + is_vma_resv_set(vma, HPAGE_RESV_OWNER); +} + void hugetlb_dup_vma_private(struct vm_area_struct *vma) { VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); @@ -6520,7 +6527,7 @@ struct page *hugetlb_follow_page_mask(struct vm_area_struct *vma, } } - page += ((address & ~huge_page_mask(h)) >> PAGE_SHIFT); + page = nth_page(page, ((address & ~huge_page_mask(h)) >> PAGE_SHIFT)); /* * Note that page may be a sub-page, and with vmemmap diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 5b009b233ab89..8a881ab21f6cb 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2864,7 +2864,8 @@ static void commit_charge(struct folio *folio, struct mem_cgroup *memcg) * Moreover, it should not come from DMA buffer and is not readily * reclaimable. So those GFP bits should be masked off. */ -#define OBJCGS_CLEAR_MASK (__GFP_DMA | __GFP_RECLAIMABLE | __GFP_ACCOUNT) +#define OBJCGS_CLEAR_MASK (__GFP_DMA | __GFP_RECLAIMABLE | \ + __GFP_ACCOUNT | __GFP_NOFAIL) /* * mod_objcg_mlstate() may be called with irq enabled, so diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 4d6e43c88489a..16e002e08cf8f 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1571,7 +1571,7 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, * This check implies we don't kill processes if their pages * are in the swap cache early. Those are always late kills. */ - if (!page_mapped(hpage)) + if (!page_mapped(p)) return true; if (PageSwapCache(p)) { @@ -1622,10 +1622,10 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, try_to_unmap(folio, ttu); } - unmap_success = !page_mapped(hpage); + unmap_success = !page_mapped(p); if (!unmap_success) pr_err("%#lx: failed to unmap page (mapcount=%d)\n", - pfn, page_mapcount(hpage)); + pfn, page_mapcount(p)); /* * try_to_unmap() might put mlocked page in lru cache, so call @@ -1705,7 +1705,7 @@ static void unmap_and_kill(struct list_head *to_kill, unsigned long pfn, * mapping being torn down is communicated in siginfo, see * kill_proc() */ - loff_t start = (index << PAGE_SHIFT) & ~(size - 1); + loff_t start = ((loff_t)index << PAGE_SHIFT) & ~(size - 1); unmap_mapping_range(mapping, start, size, 0); } diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 1b03f4ec6fd21..144758820e3a3 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1129,6 +1129,9 @@ void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long nr_pages) kasan_remove_zero_shadow(__va(PFN_PHYS(pfn)), PFN_PHYS(nr_pages)); } +/* + * Must be called with mem_hotplug_lock in write mode. + */ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, struct zone *zone, struct memory_group *group) { @@ -1149,7 +1152,6 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, !IS_ALIGNED(pfn + nr_pages, PAGES_PER_SECTION))) return -EINVAL; - mem_hotplug_begin(); /* associate pfn range with the zone */ move_pfn_range_to_zone(zone, pfn, nr_pages, NULL, MIGRATE_ISOLATE); @@ -1208,7 +1210,6 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, writeback_set_ratelimit(); memory_notify(MEM_ONLINE, &arg); - mem_hotplug_done(); return 0; failed_addition: @@ -1217,7 +1218,6 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, (((unsigned long long) pfn + nr_pages) << PAGE_SHIFT) - 1); memory_notify(MEM_CANCEL_ONLINE, &arg); remove_pfn_range_from_zone(zone, pfn, nr_pages); - mem_hotplug_done(); return ret; } @@ -1458,7 +1458,7 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) /* create memory block devices after memory was added */ ret = create_memory_block_devices(start, size, params.altmap, group); if (ret) { - arch_remove_memory(start, size, NULL); + arch_remove_memory(start, size, params.altmap); goto error_free; } @@ -1689,7 +1689,7 @@ static int scan_movable_pages(unsigned long start, unsigned long end, */ if (HPageMigratable(head)) goto found; - skip = compound_nr(head) - (page - head); + skip = compound_nr(head) - (pfn - page_to_pfn(head)); pfn += skip - 1; } return -ENOENT; @@ -1863,6 +1863,9 @@ static int count_system_ram_pages_cb(unsigned long start_pfn, return 0; } +/* + * Must be called with mem_hotplug_lock in write mode. + */ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages, struct zone *zone, struct memory_group *group) { @@ -1885,8 +1888,6 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages, !IS_ALIGNED(start_pfn + nr_pages, PAGES_PER_SECTION))) return -EINVAL; - mem_hotplug_begin(); - /* * Don't allow to offline memory blocks that contain holes. * Consequently, memory blocks with holes can never get onlined @@ -2027,7 +2028,6 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages, memory_notify(MEM_OFFLINE, &arg); remove_pfn_range_from_zone(zone, start_pfn, nr_pages); - mem_hotplug_done(); return 0; failed_removal_isolated: @@ -2042,7 +2042,6 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages, (unsigned long long) start_pfn << PAGE_SHIFT, ((unsigned long long) end_pfn << PAGE_SHIFT) - 1, reason); - mem_hotplug_done(); return ret; } diff --git a/mm/migrate.c b/mm/migrate.c index 06086dc9da288..03bc2063ac871 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -405,6 +405,7 @@ int folio_migrate_mapping(struct address_space *mapping, int dirty; int expected_count = folio_expected_refs(mapping, folio) + extra_count; long nr = folio_nr_pages(folio); + long entries, i; if (!mapping) { /* Anonymous page without mapping */ @@ -442,8 +443,10 @@ int folio_migrate_mapping(struct address_space *mapping, folio_set_swapcache(newfolio); newfolio->private = folio_get_private(folio); } + entries = nr; } else { VM_BUG_ON_FOLIO(folio_test_swapcache(folio), folio); + entries = 1; } /* Move dirty while page refs frozen and newpage not yet exposed */ @@ -453,7 +456,11 @@ int folio_migrate_mapping(struct address_space *mapping, folio_set_dirty(newfolio); } - xas_store(&xas, newfolio); + /* Swap cache still stores N entries instead of a high-order entry */ + for (i = 0; i < entries; i++) { + xas_store(&xas, newfolio); + xas_next(&xas); + } /* * Drop cache reference from old page by unfreezing diff --git a/mm/page-writeback.c b/mm/page-writeback.c index b8d3d7040a506..4656534b8f5cc 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -3110,7 +3110,7 @@ EXPORT_SYMBOL_GPL(folio_wait_writeback_killable); */ void folio_wait_stable(struct folio *folio) { - if (folio_inode(folio)->i_sb->s_iflags & SB_I_STABLE_WRITES) + if (mapping_stable_writes(folio_mapping(folio))) folio_wait_writeback(folio); } EXPORT_SYMBOL_GPL(folio_wait_stable); diff --git a/mm/shmem.c b/mm/shmem.c index 69595d3418829..e826be732b9bb 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1098,7 +1098,24 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, } VM_BUG_ON_FOLIO(folio_test_writeback(folio), folio); - truncate_inode_folio(mapping, folio); + + if (!folio_test_large(folio)) { + truncate_inode_folio(mapping, folio); + } else if (truncate_inode_partial_folio(folio, lstart, lend)) { + /* + * If we split a page, reset the loop so + * that we pick up the new sub pages. + * Otherwise the THP was entirely + * dropped or the target range was + * zeroed, so just continue the loop as + * is. + */ + if (!folio_test_large(folio)) { + folio_unlock(folio); + index = start; + break; + } + } } folio_unlock(folio); } diff --git a/mm/util.c b/mm/util.c index 8cbbfd3a3d598..be798981acc7d 100644 --- a/mm/util.c +++ b/mm/util.c @@ -414,6 +414,15 @@ static int mmap_is_legacy(struct rlimit *rlim_stack) static unsigned long mmap_base(unsigned long rnd, struct rlimit *rlim_stack) { +#ifdef CONFIG_STACK_GROWSUP + /* + * For an upwards growing stack the calculation is much simpler. + * Memory for the maximum stack size is reserved at the top of the + * task. mmap_base starts directly below the stack and grows + * downwards. + */ + return PAGE_ALIGN_DOWN(mmap_upper_limit(rlim_stack) - rnd); +#else unsigned long gap = rlim_stack->rlim_cur; unsigned long pad = stack_guard_gap; @@ -431,6 +440,7 @@ static unsigned long mmap_base(unsigned long rnd, struct rlimit *rlim_stack) gap = MAX_GAP; return PAGE_ALIGN(STACK_TOP - gap - rnd); +#endif } void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) diff --git a/mm/vmscan.c b/mm/vmscan.c index 6f13394b112ea..dcc264d3c92f2 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -4790,6 +4790,9 @@ static void lru_gen_rotate_memcg(struct lruvec *lruvec, int op) else VM_WARN_ON_ONCE(true); + WRITE_ONCE(lruvec->lrugen.seg, seg); + WRITE_ONCE(lruvec->lrugen.gen, new); + hlist_nulls_del_rcu(&lruvec->lrugen.list); if (op == MEMCG_LRU_HEAD || op == MEMCG_LRU_OLD) @@ -4800,9 +4803,6 @@ static void lru_gen_rotate_memcg(struct lruvec *lruvec, int op) pgdat->memcg_lru.nr_memcgs[old]--; pgdat->memcg_lru.nr_memcgs[new]++; - lruvec->lrugen.gen = new; - WRITE_ONCE(lruvec->lrugen.seg, seg); - if (!pgdat->memcg_lru.nr_memcgs[old] && old == get_memcg_gen(pgdat->memcg_lru.seq)) WRITE_ONCE(pgdat->memcg_lru.seq, pgdat->memcg_lru.seq + 1); @@ -4825,11 +4825,11 @@ void lru_gen_online_memcg(struct mem_cgroup *memcg) gen = get_memcg_gen(pgdat->memcg_lru.seq); + lruvec->lrugen.gen = gen; + hlist_nulls_add_tail_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[gen][bin]); pgdat->memcg_lru.nr_memcgs[gen]++; - lruvec->lrugen.gen = gen; - spin_unlock_irq(&pgdat->memcg_lru.lock); } } @@ -4933,7 +4933,7 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_c } /* protected */ - if (tier > tier_idx) { + if (tier > tier_idx || refs == BIT(LRU_REFS_WIDTH)) { int hist = lru_hist_from_seq(lrugen->min_seq[type]); gen = folio_inc_gen(lruvec, folio, false); @@ -5291,7 +5291,12 @@ static bool should_run_aging(struct lruvec *lruvec, unsigned long max_seq, } /* try to scrape all its memory if this memcg was deleted */ - *nr_to_scan = mem_cgroup_online(memcg) ? (total >> sc->priority) : total; + if (!mem_cgroup_online(memcg)) { + *nr_to_scan = total; + return false; + } + + *nr_to_scan = total >> sc->priority; /* * The aging tries to be lazy to reduce the overhead, while the eviction @@ -5328,7 +5333,7 @@ static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, bool DEFINE_MAX_SEQ(lruvec); if (mem_cgroup_below_min(sc->target_mem_cgroup, memcg)) - return 0; + return -1; if (!should_run_aging(lruvec, max_seq, sc, can_swap, &nr_to_scan)) return nr_to_scan; @@ -5341,20 +5346,41 @@ static long get_nr_to_scan(struct lruvec *lruvec, struct scan_control *sc, bool return try_to_inc_max_seq(lruvec, max_seq, sc, can_swap, false) ? -1 : 0; } -static unsigned long get_nr_to_reclaim(struct scan_control *sc) +static bool should_abort_scan(struct lruvec *lruvec, struct scan_control *sc) { + int i; + enum zone_watermarks mark; + /* don't abort memcg reclaim to ensure fairness */ if (!root_reclaim(sc)) - return -1; + return false; + + if (sc->nr_reclaimed >= max(sc->nr_to_reclaim, compact_gap(sc->order))) + return true; + + /* check the order to exclude compaction-induced reclaim */ + if (!current_is_kswapd() || sc->order) + return false; + + mark = sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING ? + WMARK_PROMO : WMARK_HIGH; + + for (i = 0; i <= sc->reclaim_idx; i++) { + struct zone *zone = lruvec_pgdat(lruvec)->node_zones + i; + unsigned long size = wmark_pages(zone, mark) + MIN_LRU_BATCH; + + if (managed_zone(zone) && !zone_watermark_ok(zone, 0, size, sc->reclaim_idx, 0)) + return false; + } - return max(sc->nr_to_reclaim, compact_gap(sc->order)); + /* kswapd should abort if all eligible zones are safe */ + return true; } static bool try_to_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) { long nr_to_scan; unsigned long scanned = 0; - unsigned long nr_to_reclaim = get_nr_to_reclaim(sc); int swappiness = get_swappiness(lruvec, sc); /* clean file folios are more likely to exist */ @@ -5376,13 +5402,13 @@ static bool try_to_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) if (scanned >= nr_to_scan) break; - if (sc->nr_reclaimed >= nr_to_reclaim) + if (should_abort_scan(lruvec, sc)) break; cond_resched(); } - /* whether try_to_inc_max_seq() was successful */ + /* whether this lruvec should be rotated */ return nr_to_scan < 0; } @@ -5391,14 +5417,9 @@ static int shrink_one(struct lruvec *lruvec, struct scan_control *sc) bool success; unsigned long scanned = sc->nr_scanned; unsigned long reclaimed = sc->nr_reclaimed; - int seg = lru_gen_memcg_seg(lruvec); struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct pglist_data *pgdat = lruvec_pgdat(lruvec); - /* see the comment on MEMCG_NR_GENS */ - if (!lruvec_is_sizable(lruvec, sc)) - return seg != MEMCG_LRU_TAIL ? MEMCG_LRU_TAIL : MEMCG_LRU_YOUNG; - mem_cgroup_calculate_protection(NULL, memcg); if (mem_cgroup_below_min(NULL, memcg)) @@ -5406,7 +5427,7 @@ static int shrink_one(struct lruvec *lruvec, struct scan_control *sc) if (mem_cgroup_below_low(NULL, memcg)) { /* see the comment on MEMCG_NR_GENS */ - if (seg != MEMCG_LRU_TAIL) + if (lru_gen_memcg_seg(lruvec) != MEMCG_LRU_TAIL) return MEMCG_LRU_TAIL; memcg_memory_event(memcg, MEMCG_LOW); @@ -5422,7 +5443,15 @@ static int shrink_one(struct lruvec *lruvec, struct scan_control *sc) flush_reclaim_state(sc); - return success ? MEMCG_LRU_YOUNG : 0; + if (success && mem_cgroup_online(memcg)) + return MEMCG_LRU_YOUNG; + + if (!success && lruvec_is_sizable(lruvec, sc)) + return 0; + + /* one retry if offlined or too small */ + return lru_gen_memcg_seg(lruvec) != MEMCG_LRU_TAIL ? + MEMCG_LRU_TAIL : MEMCG_LRU_YOUNG; } #ifdef CONFIG_MEMCG @@ -5436,14 +5465,13 @@ static void shrink_many(struct pglist_data *pgdat, struct scan_control *sc) struct lruvec *lruvec; struct lru_gen_folio *lrugen; struct mem_cgroup *memcg; - const struct hlist_nulls_node *pos; - unsigned long nr_to_reclaim = get_nr_to_reclaim(sc); + struct hlist_nulls_node *pos; + gen = get_memcg_gen(READ_ONCE(pgdat->memcg_lru.seq)); bin = first_bin = get_random_u32_below(MEMCG_NR_BINS); restart: op = 0; memcg = NULL; - gen = get_memcg_gen(READ_ONCE(pgdat->memcg_lru.seq)); rcu_read_lock(); @@ -5454,6 +5482,10 @@ static void shrink_many(struct pglist_data *pgdat, struct scan_control *sc) } mem_cgroup_put(memcg); + memcg = NULL; + + if (gen != READ_ONCE(lrugen->gen)) + continue; lruvec = container_of(lrugen, struct lruvec, lrugen); memcg = lruvec_memcg(lruvec); @@ -5470,7 +5502,7 @@ static void shrink_many(struct pglist_data *pgdat, struct scan_control *sc) rcu_read_lock(); - if (sc->nr_reclaimed >= nr_to_reclaim) + if (should_abort_scan(lruvec, sc)) break; } @@ -5481,7 +5513,7 @@ static void shrink_many(struct pglist_data *pgdat, struct scan_control *sc) mem_cgroup_put(memcg); - if (sc->nr_reclaimed >= nr_to_reclaim) + if (!is_a_nulls(pos)) return; /* restart if raced with lru_gen_rotate_memcg() */ @@ -5538,16 +5570,14 @@ static void set_initial_priority(struct pglist_data *pgdat, struct scan_control if (sc->priority != DEF_PRIORITY || sc->nr_to_reclaim < MIN_LRU_BATCH) return; /* - * Determine the initial priority based on ((total / MEMCG_NR_GENS) >> - * priority) * reclaimed_to_scanned_ratio = nr_to_reclaim, where the - * estimated reclaimed_to_scanned_ratio = inactive / total. + * Determine the initial priority based on + * (total >> priority) * reclaimed_to_scanned_ratio = nr_to_reclaim, + * where reclaimed_to_scanned_ratio = inactive / total. */ reclaimable = node_page_state(pgdat, NR_INACTIVE_FILE); if (get_swappiness(lruvec, sc)) reclaimable += node_page_state(pgdat, NR_INACTIVE_ANON); - reclaimable /= MEMCG_NR_GENS; - /* round down reclaimable and round up sc->nr_to_reclaim */ priority = fls_long(reclaimable) - 1 - fls_long(sc->nr_to_reclaim - 1); diff --git a/mm/workingset.c b/mm/workingset.c index da58a26d0d4d7..2559a1f2fc1cf 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -313,10 +313,10 @@ static void lru_gen_refault(struct folio *folio, void *shadow) * 1. For pages accessed through page tables, hotter pages pushed out * hot pages which refaulted immediately. * 2. For pages accessed multiple times through file descriptors, - * numbers of accesses might have been out of the range. + * they would have been protected by sort_folio(). */ - if (lru_gen_in_fault() || refs == BIT(LRU_REFS_WIDTH)) { - folio_set_workingset(folio); + if (lru_gen_in_fault() || refs >= BIT(LRU_REFS_WIDTH) - 1) { + set_mask_bits(&folio->flags, 0, LRU_REFS_MASK | BIT(PG_workingset)); mod_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + type, delta); } unlock: diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index 0beb44f2fe1f0..f001582345052 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -407,6 +407,8 @@ int vlan_vids_add_by_dev(struct net_device *dev, return 0; list_for_each_entry(vid_info, &vlan_info->vid_list, list) { + if (!vlan_hw_filter_capable(by_dev, vid_info->proto)) + continue; err = vlan_vid_add(dev, vid_info->proto, vid_info->vid); if (err) goto unwind; @@ -417,6 +419,8 @@ int vlan_vids_add_by_dev(struct net_device *dev, list_for_each_entry_continue_reverse(vid_info, &vlan_info->vid_list, list) { + if (!vlan_hw_filter_capable(by_dev, vid_info->proto)) + continue; vlan_vid_del(dev, vid_info->proto, vid_info->vid); } @@ -436,8 +440,11 @@ void vlan_vids_del_by_dev(struct net_device *dev, if (!vlan_info) return; - list_for_each_entry(vid_info, &vlan_info->vid_list, list) + list_for_each_entry(vid_info, &vlan_info->vid_list, list) { + if (!vlan_hw_filter_capable(by_dev, vid_info->proto)) + continue; vlan_vid_del(dev, vid_info->proto, vid_info->vid); + } } EXPORT_SYMBOL(vlan_vids_del_by_dev); diff --git a/net/9p/client.c b/net/9p/client.c index b0e7cb7e1a54a..e265a0ca6bddd 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -1981,7 +1981,7 @@ struct p9_fid *p9_client_xattrwalk(struct p9_fid *file_fid, goto error; } p9_debug(P9_DEBUG_9P, - ">>> TXATTRWALK file_fid %d, attr_fid %d name %s\n", + ">>> TXATTRWALK file_fid %d, attr_fid %d name '%s'\n", file_fid->fid, attr_fid->fid, attr_name); req = p9_client_rpc(clnt, P9_TXATTRWALK, "dds", diff --git a/net/9p/protocol.c b/net/9p/protocol.c index 4e3a2a1ffcb3f..0e6603b1ec906 100644 --- a/net/9p/protocol.c +++ b/net/9p/protocol.c @@ -394,6 +394,8 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt, uint16_t *nwname = va_arg(ap, uint16_t *); char ***wnames = va_arg(ap, char ***); + *wnames = NULL; + errcode = p9pdu_readf(pdu, proto_version, "w", nwname); if (!errcode) { @@ -403,6 +405,8 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt, GFP_NOFS); if (!*wnames) errcode = -ENOMEM; + else + (*wnames)[0] = NULL; } if (!errcode) { @@ -414,8 +418,10 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt, proto_version, "s", &(*wnames)[i]); - if (errcode) + if (errcode) { + (*wnames)[i] = NULL; break; + } } } @@ -423,11 +429,14 @@ p9pdu_vreadf(struct p9_fcall *pdu, int proto_version, const char *fmt, if (*wnames) { int i; - for (i = 0; i < *nwname; i++) + for (i = 0; i < *nwname; i++) { + if (!(*wnames)[i]) + break; kfree((*wnames)[i]); + } + kfree(*wnames); + *wnames = NULL; } - kfree(*wnames); - *wnames = NULL; } } break; diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index c4015f30f9fa7..d0eb03ada704d 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -832,14 +832,21 @@ static int p9_fd_open(struct p9_client *client, int rfd, int wfd) goto out_free_ts; if (!(ts->rd->f_mode & FMODE_READ)) goto out_put_rd; - /* prevent workers from hanging on IO when fd is a pipe */ - ts->rd->f_flags |= O_NONBLOCK; + /* Prevent workers from hanging on IO when fd is a pipe. + * It's technically possible for userspace or concurrent mounts to + * modify this flag concurrently, which will likely result in a + * broken filesystem. However, just having bad flags here should + * not crash the kernel or cause any other sort of bug, so mark this + * particular data race as intentional so that tooling (like KCSAN) + * can allow it and detect further problems. + */ + data_race(ts->rd->f_flags |= O_NONBLOCK); ts->wr = fget(wfd); if (!ts->wr) goto out_put_rd; if (!(ts->wr->f_mode & FMODE_WRITE)) goto out_put_wr; - ts->wr->f_flags |= O_NONBLOCK; + data_race(ts->wr->f_flags |= O_NONBLOCK); client->trans = ts; client->status = Connected; diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index 8978fb6212ffb..b070a89912000 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -1811,15 +1811,14 @@ static int atalk_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) break; } case TIOCINQ: { - /* - * These two are safe on a single CPU system as only - * user tasks fiddle here - */ - struct sk_buff *skb = skb_peek(&sk->sk_receive_queue); + struct sk_buff *skb; long amount = 0; + spin_lock_irq(&sk->sk_receive_queue.lock); + skb = skb_peek(&sk->sk_receive_queue); if (skb) amount = skb->len - sizeof(struct ddpehdr); + spin_unlock_irq(&sk->sk_receive_queue.lock); rc = put_user(amount, (int __user *)argp); break; } diff --git a/net/atm/ioctl.c b/net/atm/ioctl.c index 838ebf0cabbfb..f81f8d56f5c0c 100644 --- a/net/atm/ioctl.c +++ b/net/atm/ioctl.c @@ -73,14 +73,17 @@ static int do_vcc_ioctl(struct socket *sock, unsigned int cmd, case SIOCINQ: { struct sk_buff *skb; + int amount; if (sock->state != SS_CONNECTED) { error = -EINVAL; goto done; } + spin_lock_irq(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); - error = put_user(skb ? skb->len : 0, - (int __user *)argp) ? -EFAULT : 0; + amount = skb ? skb->len : 0; + spin_unlock_irq(&sk->sk_receive_queue.lock); + error = put_user(amount, (int __user *)argp) ? -EFAULT : 0; goto done; } case ATM_SETSC: diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 336a761654546..b93464ac3517f 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -309,11 +309,14 @@ int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, if (flags & MSG_OOB) return -EOPNOTSUPP; + lock_sock(sk); + skb = skb_recv_datagram(sk, flags, &err); if (!skb) { if (sk->sk_shutdown & RCV_SHUTDOWN) - return 0; + err = 0; + release_sock(sk); return err; } @@ -343,6 +346,8 @@ int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, skb_free_datagram(sk, skb); + release_sock(sk); + if (flags & MSG_TRUNC) copied = skblen; diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 7450b550cff6d..f3139c4c20fc0 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -172,13 +172,11 @@ static void hci_conn_cleanup(struct hci_conn *conn) hdev->notify(hdev, HCI_NOTIFY_CONN_DEL); } - hci_conn_del_sysfs(conn); - debugfs_remove_recursive(conn->debugfs); - hci_dev_put(hdev); + hci_conn_del_sysfs(conn); - hci_conn_put(conn); + hci_dev_put(hdev); } static void hci_acl_create_connection(struct hci_conn *conn) diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index f6d3150bcbb03..f7ebbbd302182 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -516,6 +516,9 @@ static u8 hci_cc_read_class_of_dev(struct hci_dev *hdev, void *data, { struct hci_rp_read_class_of_dev *rp = data; + if (WARN_ON(!hdev)) + return HCI_ERROR_UNSPECIFIED; + bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); if (rp->status) @@ -747,9 +750,23 @@ static u8 hci_cc_read_enc_key_size(struct hci_dev *hdev, void *data, } else { conn->enc_key_size = rp->key_size; status = 0; + + if (conn->enc_key_size < hdev->min_enc_key_size) { + /* As slave role, the conn->state has been set to + * BT_CONNECTED and l2cap conn req might not be received + * yet, at this moment the l2cap layer almost does + * nothing with the non-zero status. + * So we also clear encrypt related bits, and then the + * handler of l2cap conn req will get the right secure + * state at a later time. + */ + status = HCI_ERROR_AUTH_FAILURE; + clear_bit(HCI_CONN_ENCRYPT, &conn->flags); + clear_bit(HCI_CONN_AES_CCM, &conn->flags); + } } - hci_encrypt_cfm(conn, 0); + hci_encrypt_cfm(conn, status); done: hci_dev_unlock(hdev); @@ -820,8 +837,6 @@ static u8 hci_cc_write_auth_payload_timeout(struct hci_dev *hdev, void *data, if (!rp->status) conn->auth_payload_timeout = get_unaligned_le16(sent + 2); - hci_encrypt_cfm(conn, 0); - unlock: hci_dev_unlock(hdev); @@ -2304,7 +2319,8 @@ static void hci_cs_inquiry(struct hci_dev *hdev, __u8 status) return; } - set_bit(HCI_INQUIRY, &hdev->flags); + if (hci_sent_cmd_data(hdev, HCI_OP_INQUIRY)) + set_bit(HCI_INQUIRY, &hdev->flags); } static void hci_cs_create_conn(struct hci_dev *hdev, __u8 status) @@ -3683,12 +3699,8 @@ static void hci_encrypt_change_evt(struct hci_dev *hdev, void *data, cp.handle = cpu_to_le16(conn->handle); cp.timeout = cpu_to_le16(hdev->auth_payload_timeout); if (hci_send_cmd(conn->hdev, HCI_OP_WRITE_AUTH_PAYLOAD_TO, - sizeof(cp), &cp)) { + sizeof(cp), &cp)) bt_dev_err(hdev, "write auth payload timeout failed"); - goto notify; - } - - goto unlock; } notify: diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c index 15b33579007cb..367e32fe30eb8 100644 --- a/net/bluetooth/hci_sysfs.c +++ b/net/bluetooth/hci_sysfs.c @@ -35,7 +35,7 @@ void hci_conn_init_sysfs(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; - BT_DBG("conn %p", conn); + bt_dev_dbg(hdev, "conn %p", conn); conn->dev.type = &bt_link; conn->dev.class = &bt_class; @@ -48,27 +48,30 @@ void hci_conn_add_sysfs(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; - BT_DBG("conn %p", conn); + bt_dev_dbg(hdev, "conn %p", conn); if (device_is_registered(&conn->dev)) return; dev_set_name(&conn->dev, "%s:%d", hdev->name, conn->handle); - if (device_add(&conn->dev) < 0) { + if (device_add(&conn->dev) < 0) bt_dev_err(hdev, "failed to register connection device"); - return; - } - - hci_dev_hold(hdev); } void hci_conn_del_sysfs(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; - if (!device_is_registered(&conn->dev)) + bt_dev_dbg(hdev, "conn %p", conn); + + if (!device_is_registered(&conn->dev)) { + /* If device_add() has *not* succeeded, use *only* put_device() + * to drop the reference count. + */ + put_device(&conn->dev); return; + } while (1) { struct device *dev; @@ -80,9 +83,7 @@ void hci_conn_del_sysfs(struct hci_conn *conn) put_device(dev); } - device_del(&conn->dev); - - hci_dev_put(hdev); + device_unregister(&conn->dev); } static void bt_host_release(struct device *dev) diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 17ca13e8c044c..baeebee41cd9e 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -6492,6 +6492,14 @@ static inline void l2cap_le_sig_channel(struct l2cap_conn *conn, kfree_skb(skb); } +static inline void l2cap_sig_send_rej(struct l2cap_conn *conn, u16 ident) +{ + struct l2cap_cmd_rej_unk rej; + + rej.reason = cpu_to_le16(L2CAP_REJ_NOT_UNDERSTOOD); + l2cap_send_cmd(conn, ident, L2CAP_COMMAND_REJ, sizeof(rej), &rej); +} + static inline void l2cap_sig_channel(struct l2cap_conn *conn, struct sk_buff *skb) { @@ -6517,23 +6525,24 @@ static inline void l2cap_sig_channel(struct l2cap_conn *conn, if (len > skb->len || !cmd->ident) { BT_DBG("corrupted command"); + l2cap_sig_send_rej(conn, cmd->ident); break; } err = l2cap_bredr_sig_cmd(conn, cmd, len, skb->data); if (err) { - struct l2cap_cmd_rej_unk rej; - BT_ERR("Wrong link type (%d)", err); - - rej.reason = cpu_to_le16(L2CAP_REJ_NOT_UNDERSTOOD); - l2cap_send_cmd(conn, cmd->ident, L2CAP_COMMAND_REJ, - sizeof(rej), &rej); + l2cap_sig_send_rej(conn, cmd->ident); } skb_pull(skb, len); } + if (skb->len > 0) { + BT_DBG("corrupted command"); + l2cap_sig_send_rej(conn, 0); + } + drop: kfree_skb(skb); } diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index ba2e00646e8e8..9dd815b6603fe 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -2897,7 +2897,8 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data, for (i = 0; i < key_count; i++) { struct mgmt_link_key_info *key = &cp->keys[i]; - if (key->addr.type != BDADDR_BREDR || key->type > 0x08) + /* Considering SMP over BREDR/LE, there is no need to check addr_type */ + if (key->type > 0x08) return mgmt_cmd_status(sk, hdev->id, MGMT_OP_LOAD_LINK_KEYS, MGMT_STATUS_INVALID_PARAMS); @@ -7130,6 +7131,7 @@ static int load_irks(struct sock *sk, struct hci_dev *hdev, void *cp_data, for (i = 0; i < irk_count; i++) { struct mgmt_irk_info *irk = &cp->irks[i]; + u8 addr_type = le_addr_type(irk->addr.type); if (hci_is_blocked_key(hdev, HCI_BLOCKED_KEY_TYPE_IRK, @@ -7139,8 +7141,12 @@ static int load_irks(struct sock *sk, struct hci_dev *hdev, void *cp_data, continue; } + /* When using SMP over BR/EDR, the addr type should be set to BREDR */ + if (irk->addr.type == BDADDR_BREDR) + addr_type = BDADDR_BREDR; + hci_add_irk(hdev, &irk->addr.bdaddr, - le_addr_type(irk->addr.type), irk->val, + addr_type, irk->val, BDADDR_ANY); } @@ -7221,6 +7227,7 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev, for (i = 0; i < key_count; i++) { struct mgmt_ltk_info *key = &cp->keys[i]; u8 type, authenticated; + u8 addr_type = le_addr_type(key->addr.type); if (hci_is_blocked_key(hdev, HCI_BLOCKED_KEY_TYPE_LTK, @@ -7255,8 +7262,12 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev, continue; } + /* When using SMP over BR/EDR, the addr type should be set to BREDR */ + if (key->addr.type == BDADDR_BREDR) + addr_type = BDADDR_BREDR; + hci_add_ltk(hdev, &key->addr.bdaddr, - le_addr_type(key->addr.type), type, authenticated, + addr_type, type, authenticated, key->val, key->enc_size, key->ediv, key->rand); } @@ -9523,7 +9534,7 @@ void mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key, ev.store_hint = persistent; bacpy(&ev.key.addr.bdaddr, &key->bdaddr); - ev.key.addr.type = BDADDR_BREDR; + ev.key.addr.type = link_to_bdaddr(key->link_type, key->bdaddr_type); ev.key.type = key->type; memcpy(ev.key.val, key->val, HCI_LINK_KEY_SIZE); ev.key.pin_len = key->pin_len; @@ -9574,7 +9585,7 @@ void mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, bool persistent) ev.store_hint = persistent; bacpy(&ev.key.addr.bdaddr, &key->bdaddr); - ev.key.addr.type = link_to_bdaddr(LE_LINK, key->bdaddr_type); + ev.key.addr.type = link_to_bdaddr(key->link_type, key->bdaddr_type); ev.key.type = mgmt_ltk_type(key); ev.key.enc_size = key->enc_size; ev.key.ediv = key->ediv; @@ -9603,7 +9614,7 @@ void mgmt_new_irk(struct hci_dev *hdev, struct smp_irk *irk, bool persistent) bacpy(&ev.rpa, &irk->rpa); bacpy(&ev.irk.addr.bdaddr, &irk->bdaddr); - ev.irk.addr.type = link_to_bdaddr(LE_LINK, irk->addr_type); + ev.irk.addr.type = link_to_bdaddr(irk->link_type, irk->addr_type); memcpy(ev.irk.val, irk->val, sizeof(irk->val)); mgmt_event(MGMT_EV_NEW_IRK, hdev, &ev, sizeof(ev), NULL); @@ -9632,7 +9643,7 @@ void mgmt_new_csrk(struct hci_dev *hdev, struct smp_csrk *csrk, ev.store_hint = persistent; bacpy(&ev.key.addr.bdaddr, &csrk->bdaddr); - ev.key.addr.type = link_to_bdaddr(LE_LINK, csrk->bdaddr_type); + ev.key.addr.type = link_to_bdaddr(csrk->link_type, csrk->bdaddr_type); ev.key.type = csrk->type; memcpy(ev.key.val, csrk->val, sizeof(csrk->val)); diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index f1a9fc0012f09..37f95ea8c7db5 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -1060,6 +1060,7 @@ static void smp_notify_keys(struct l2cap_conn *conn) } if (smp->remote_irk) { + smp->remote_irk->link_type = hcon->type; mgmt_new_irk(hdev, smp->remote_irk, persistent); /* Now that user space can be considered to know the @@ -1079,24 +1080,28 @@ static void smp_notify_keys(struct l2cap_conn *conn) } if (smp->csrk) { + smp->csrk->link_type = hcon->type; smp->csrk->bdaddr_type = hcon->dst_type; bacpy(&smp->csrk->bdaddr, &hcon->dst); mgmt_new_csrk(hdev, smp->csrk, persistent); } if (smp->responder_csrk) { + smp->responder_csrk->link_type = hcon->type; smp->responder_csrk->bdaddr_type = hcon->dst_type; bacpy(&smp->responder_csrk->bdaddr, &hcon->dst); mgmt_new_csrk(hdev, smp->responder_csrk, persistent); } if (smp->ltk) { + smp->ltk->link_type = hcon->type; smp->ltk->bdaddr_type = hcon->dst_type; bacpy(&smp->ltk->bdaddr, &hcon->dst); mgmt_new_ltk(hdev, smp->ltk, persistent); } if (smp->responder_ltk) { + smp->responder_ltk->link_type = hcon->type; smp->responder_ltk->bdaddr_type = hcon->dst_type; bacpy(&smp->responder_ltk->bdaddr, &hcon->dst); mgmt_new_ltk(hdev, smp->responder_ltk, persistent); @@ -1116,6 +1121,8 @@ static void smp_notify_keys(struct l2cap_conn *conn) key = hci_add_link_key(hdev, smp->conn->hcon, &hcon->dst, smp->link_key, type, 0, &persistent); if (key) { + key->link_type = hcon->type; + key->bdaddr_type = hcon->dst_type; mgmt_new_link_key(hdev, key, persistent); /* Don't keep debug keys around if the relevant diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c index 71056ee847736..0fcf357ea7ad3 100644 --- a/net/bridge/netfilter/nf_conntrack_bridge.c +++ b/net/bridge/netfilter/nf_conntrack_bridge.c @@ -37,7 +37,7 @@ static int nf_br_ip_fragment(struct net *net, struct sock *sk, ktime_t tstamp = skb->tstamp; struct ip_frag_state state; struct iphdr *iph; - int err; + int err = 0; /* for offloaded checksums cleanup checksum before fragmentation */ if (skb->ip_summed == CHECKSUM_PARTIAL && diff --git a/net/core/dev.c b/net/core/dev.c index 9f3f8930c6914..e480afb50d4c1 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3500,6 +3500,9 @@ static netdev_features_t gso_features_check(const struct sk_buff *skb, if (gso_segs > READ_ONCE(dev->gso_max_segs)) return features & ~NETIF_F_GSO_MASK; + if (unlikely(skb->len >= READ_ONCE(dev->gso_max_size))) + return features & ~NETIF_F_GSO_MASK; + if (!skb_shinfo(skb)->gso_type) { skb_warn_bad_offload(skb); return features & ~NETIF_F_GSO_MASK; @@ -10050,6 +10053,54 @@ void netif_tx_stop_all_queues(struct net_device *dev) } EXPORT_SYMBOL(netif_tx_stop_all_queues); +static int netdev_do_alloc_pcpu_stats(struct net_device *dev) +{ + void __percpu *v; + + /* Drivers implementing ndo_get_peer_dev must support tstat + * accounting, so that skb_do_redirect() can bump the dev's + * RX stats upon network namespace switch. + */ + if (dev->netdev_ops->ndo_get_peer_dev && + dev->pcpu_stat_type != NETDEV_PCPU_STAT_TSTATS) + return -EOPNOTSUPP; + + switch (dev->pcpu_stat_type) { + case NETDEV_PCPU_STAT_NONE: + return 0; + case NETDEV_PCPU_STAT_LSTATS: + v = dev->lstats = netdev_alloc_pcpu_stats(struct pcpu_lstats); + break; + case NETDEV_PCPU_STAT_TSTATS: + v = dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); + break; + case NETDEV_PCPU_STAT_DSTATS: + v = dev->dstats = netdev_alloc_pcpu_stats(struct pcpu_dstats); + break; + default: + return -EINVAL; + } + + return v ? 0 : -ENOMEM; +} + +static void netdev_do_free_pcpu_stats(struct net_device *dev) +{ + switch (dev->pcpu_stat_type) { + case NETDEV_PCPU_STAT_NONE: + return; + case NETDEV_PCPU_STAT_LSTATS: + free_percpu(dev->lstats); + break; + case NETDEV_PCPU_STAT_TSTATS: + free_percpu(dev->tstats); + break; + case NETDEV_PCPU_STAT_DSTATS: + free_percpu(dev->dstats); + break; + } +} + /** * register_netdevice() - register a network device * @dev: device to register @@ -10110,9 +10161,13 @@ int register_netdevice(struct net_device *dev) goto err_uninit; } + ret = netdev_do_alloc_pcpu_stats(dev); + if (ret) + goto err_uninit; + ret = dev_index_reserve(net, dev->ifindex); if (ret < 0) - goto err_uninit; + goto err_free_pcpu; dev->ifindex = ret; /* Transfer changeable features to wanted_features and enable @@ -10218,6 +10273,8 @@ int register_netdevice(struct net_device *dev) call_netdevice_notifiers(NETDEV_PRE_UNINIT, dev); err_ifindex_release: dev_index_release(net, dev->ifindex); +err_free_pcpu: + netdev_do_free_pcpu_stats(dev); err_uninit: if (dev->netdev_ops->ndo_uninit) dev->netdev_ops->ndo_uninit(dev); @@ -10470,6 +10527,7 @@ void netdev_run_todo(void) WARN_ON(rcu_access_pointer(dev->ip_ptr)); WARN_ON(rcu_access_pointer(dev->ip6_ptr)); + netdev_do_free_pcpu_stats(dev); if (dev->priv_destructor) dev->priv_destructor(dev); if (dev->needs_free_netdev) diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index aff31cd944c29..b240d9aae4a64 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -183,7 +183,7 @@ static struct sk_buff *reset_per_cpu_data(struct per_cpu_dm_data *data) } static const struct genl_multicast_group dropmon_mcgrps[] = { - { .name = "events", }, + { .name = "events", .cap_sys_admin = 1 }, }; static void send_dm_alert(struct work_struct *work) @@ -1619,11 +1619,13 @@ static const struct genl_small_ops dropmon_ops[] = { .cmd = NET_DM_CMD_START, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = net_dm_cmd_trace, + .flags = GENL_ADMIN_PERM, }, { .cmd = NET_DM_CMD_STOP, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = net_dm_cmd_trace, + .flags = GENL_ADMIN_PERM, }, { .cmd = NET_DM_CMD_CONFIG_GET, diff --git a/net/core/filter.c b/net/core/filter.c index a094694899c99..90fe3e7543833 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2489,6 +2489,7 @@ int skb_do_redirect(struct sk_buff *skb) net_eq(net, dev_net(dev)))) goto out_drop; skb->dev = dev; + dev_sw_netstats_rx_add(dev, skb->len); return -EAGAIN; } return flags & BPF_F_NEIGH ? @@ -2590,6 +2591,22 @@ BPF_CALL_2(bpf_msg_cork_bytes, struct sk_msg *, msg, u32, bytes) return 0; } +static void sk_msg_reset_curr(struct sk_msg *msg) +{ + u32 i = msg->sg.start; + u32 len = 0; + + do { + len += sk_msg_elem(msg, i)->length; + sk_msg_iter_var_next(i); + if (len >= msg->sg.size) + break; + } while (i != msg->sg.end); + + msg->sg.curr = i; + msg->sg.copybreak = 0; +} + static const struct bpf_func_proto bpf_msg_cork_bytes_proto = { .func = bpf_msg_cork_bytes, .gpl_only = false, @@ -2709,6 +2726,7 @@ BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start, msg->sg.end - shift + NR_MSG_FRAG_IDS : msg->sg.end - shift; out: + sk_msg_reset_curr(msg); msg->data = sg_virt(&msg->sg.data[first_sge]) + start - offset; msg->data_end = msg->data + bytes; return 0; @@ -2845,6 +2863,7 @@ BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start, msg->sg.data[new] = rsge; } + sk_msg_reset_curr(msg); sk_msg_compute_data_pointers(msg); return 0; } @@ -3013,6 +3032,7 @@ BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start, sk_mem_uncharge(msg->sk, len - pop); msg->sg.size -= (len - pop); + sk_msg_reset_curr(msg); sk_msg_compute_data_pointers(msg); return 0; } diff --git a/net/core/scm.c b/net/core/scm.c index 880027ecf5165..7dc47c17d8638 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -26,6 +26,7 @@ #include #include #include +#include #include @@ -103,6 +104,11 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp) if (fd < 0 || !(file = fget_raw(fd))) return -EBADF; + /* don't allow io_uring files */ + if (io_uring_get_socket(file)) { + fput(file); + return -EINVAL; + } *fpp++ = file; fpl->count++; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 97b4a42e6e347..6d204cf54c574 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4810,7 +4810,9 @@ static __always_inline unsigned int skb_ext_total_length(void) static void skb_extensions_init(void) { BUILD_BUG_ON(SKB_EXT_NUM >= 8); +#if !IS_ENABLED(CONFIG_KCOV_INSTRUMENT_ALL) BUILD_BUG_ON(skb_ext_total_length() > 255); +#endif skbuff_ext_cache = kmem_cache_create("skbuff_ext_cache", SKB_EXT_ALIGN_VALUE * skb_ext_total_length(), diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 6c31eefbd7778..93ecfceac1bc4 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -826,6 +826,8 @@ static void sk_psock_destroy(struct work_struct *work) if (psock->sk_redir) sock_put(psock->sk_redir); + if (psock->sk_pair) + sock_put(psock->sk_pair); sock_put(psock->sk); kfree(psock); } diff --git a/net/core/sock.c b/net/core/sock.c index 16584e2dd6481..bfaf47b3f3c7c 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -600,7 +600,7 @@ struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie) INDIRECT_CALL_INET(dst->ops->check, ip6_dst_check, ipv4_dst_check, dst, cookie) == NULL) { sk_tx_queue_clear(sk); - sk->sk_dst_pending_confirm = 0; + WRITE_ONCE(sk->sk_dst_pending_confirm, 0); RCU_INIT_POINTER(sk->sk_dst_cache, NULL); dst_release(dst); return NULL; diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 4292c2ed18286..27d733c0f65e1 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -536,6 +536,8 @@ static bool sock_map_sk_state_allowed(const struct sock *sk) { if (sk_is_tcp(sk)) return (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_LISTEN); + if (sk_is_stream_unix(sk)) + return (1 << sk->sk_state) & TCPF_ESTABLISHED; return true; } diff --git a/net/core/stream.c b/net/core/stream.c index 96fbcb9bbb30a..b16dfa568a2d5 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -79,7 +79,7 @@ int sk_stream_wait_connect(struct sock *sk, long *timeo_p) remove_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending--; } while (!done); - return 0; + return done < 0 ? done : 0; } EXPORT_SYMBOL(sk_stream_wait_connect); diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c index 01e54b46ae0b9..2a6d363763a2b 100644 --- a/net/dns_resolver/dns_key.c +++ b/net/dns_resolver/dns_key.c @@ -91,6 +91,7 @@ const struct cred *dns_resolver_cache; static int dns_resolver_preparse(struct key_preparsed_payload *prep) { + const struct dns_server_list_v1_header *v1; const struct dns_payload_header *bin; struct user_key_payload *upayload; unsigned long derrno; @@ -122,6 +123,13 @@ dns_resolver_preparse(struct key_preparsed_payload *prep) return -EINVAL; } + v1 = (const struct dns_server_list_v1_header *)bin; + if ((v1->status != DNS_LOOKUP_GOOD && + v1->status != DNS_LOOKUP_GOOD_WITH_BAD)) { + if (prep->expiry == TIME64_MAX) + prep->expiry = ktime_get_real_seconds() + 1; + } + result_len = datalen; goto store_result; } @@ -314,7 +322,7 @@ static long dns_resolver_read(const struct key *key, struct key_type key_type_dns_resolver = { .name = "dns_resolver", - .flags = KEY_TYPE_NET_DOMAIN, + .flags = KEY_TYPE_NET_DOMAIN | KEY_TYPE_INSTANT_REAP, .preparse = dns_resolver_preparse, .free_preparse = dns_resolver_free_preparse, .instantiate = generic_key_instantiate, diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index 3bbd5afb7b31c..fe3553f60bf39 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -505,6 +505,7 @@ static int ethnl_default_dumpit(struct sk_buff *skb, ret = skb->len; break; } + ret = 0; } rtnl_unlock(); diff --git a/net/ife/ife.c b/net/ife/ife.c index 13bbf8cb6a396..be05b690b9ef2 100644 --- a/net/ife/ife.c +++ b/net/ife/ife.c @@ -82,6 +82,7 @@ void *ife_decode(struct sk_buff *skb, u16 *metalen) if (unlikely(!pskb_may_pull(skb, total_pull))) return NULL; + ifehdr = (struct ifeheadr *)(skb->data + skb->dev->hard_header_len); skb_set_mac_header(skb, total_pull); __skb_pull(skb, total_pull); *metalen = ifehdrln - IFE_METAHDRLEN; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 418e5fb58fd3f..d515881d02a6f 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -216,8 +216,10 @@ static void igmp_start_timer(struct ip_mc_list *im, int max_delay) int tv = get_random_u32_below(max_delay); im->tm_running = 1; - if (!mod_timer(&im->timer, jiffies+tv+2)) - refcount_inc(&im->refcnt); + if (refcount_inc_not_zero(&im->refcnt)) { + if (mod_timer(&im->timer, jiffies + tv + 2)) + ip_ma_put(im); + } } static void igmp_gq_start_timer(struct in_device *in_dev) diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 598c1b114d2c2..a532f749e4778 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -751,12 +751,12 @@ int __inet_hash(struct sock *sk, struct sock *osk) if (err) goto unlock; } + sock_set_flag(sk, SOCK_RCU_FREE); if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport && sk->sk_family == AF_INET6) __sk_nulls_add_node_tail_rcu(sk, &ilb2->nulls_head); else __sk_nulls_add_node_rcu(sk, &ilb2->nulls_head); - sock_set_flag(sk, SOCK_RCU_FREE); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); unlock: spin_unlock(&ilb2->lock); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 22a26d1d29a09..5169c3c72cffe 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -635,15 +635,18 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb, } if (dev->header_ops) { + int pull_len = tunnel->hlen + sizeof(struct iphdr); + if (skb_cow_head(skb, 0)) goto free_skb; tnl_params = (const struct iphdr *)skb->data; - /* Pull skb since ip_tunnel_xmit() needs skb->data pointing - * to gre header. - */ - skb_pull(skb, tunnel->hlen + sizeof(struct iphdr)); + if (!pskb_network_may_pull(skb, pull_len)) + goto free_skb; + + /* ip_tunnel_xmit() needs skb->data pointing to gre header. */ + skb_pull(skb, pull_len); skb_reset_mac_header(skb); if (skb->ip_summed == CHECKSUM_PARTIAL && diff --git a/net/ipv4/route.c b/net/ipv4/route.c index b214b5a2e045f..3bad9aa066db3 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -780,7 +780,7 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow goto reject_redirect; } - n = __ipv4_neigh_lookup(rt->dst.dev, new_gw); + n = __ipv4_neigh_lookup(rt->dst.dev, (__force u32)new_gw); if (!n) n = neigh_create(&arp_tbl, &new_gw, rt->dst.dev); if (!IS_ERR(n)) { diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 3d3a24f795734..ec46d74c20938 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3368,9 +3368,25 @@ int tcp_set_window_clamp(struct sock *sk, int val) return -EINVAL; tp->window_clamp = 0; } else { - tp->window_clamp = val < SOCK_MIN_RCVBUF / 2 ? - SOCK_MIN_RCVBUF / 2 : val; - tp->rcv_ssthresh = min(tp->rcv_wnd, tp->window_clamp); + u32 new_rcv_ssthresh, old_window_clamp = tp->window_clamp; + u32 new_window_clamp = val < SOCK_MIN_RCVBUF / 2 ? + SOCK_MIN_RCVBUF / 2 : val; + + if (new_window_clamp == old_window_clamp) + return 0; + + tp->window_clamp = new_window_clamp; + if (new_window_clamp < old_window_clamp) { + /* need to apply the reserved mem provisioning only + * when shrinking the window clamp + */ + __tcp_adjust_rcv_ssthresh(sk, tp->window_clamp); + + } else { + new_rcv_ssthresh = min(tp->rcv_wnd, tp->window_clamp); + tp->rcv_ssthresh = max(new_rcv_ssthresh, + tp->rcv_ssthresh); + } } return 0; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 1f9d1d445fb3b..e6c4929549428 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3809,8 +3809,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) * then we can probably ignore it. */ if (before(ack, prior_snd_una)) { + u32 max_window; + + /* do not accept ACK for bytes we never sent. */ + max_window = min_t(u64, tp->max_window, tp->bytes_acked); /* RFC 5961 5.2 [Blind Data Injection Attack].[Mitigation] */ - if (before(ack, prior_snd_una - tp->max_window)) { + if (before(ack, prior_snd_una - max_window)) { if (!(flag & FLAG_NO_CHALLENGE_ACK)) tcp_send_challenge_ack(sk); return -SKB_DROP_REASON_TCP_TOO_OLD_ACK; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index f0723460753c5..cab3c1162c3a6 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1331,7 +1331,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, skb->destructor = skb_is_tcp_pure_ack(skb) ? __sock_wfree : tcp_wfree; refcount_add(skb->truesize, &sk->sk_wmem_alloc); - skb_set_dst_pending_confirm(skb, sk->sk_dst_pending_confirm); + skb_set_dst_pending_confirm(skb, READ_ONCE(sk->sk_dst_pending_confirm)); /* Build TCP header and checksum it. */ th = (struct tcphdr *)skb->data; @@ -3263,7 +3263,13 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) if (skb_still_in_host_queue(sk, skb)) return -EBUSY; +start: if (before(TCP_SKB_CB(skb)->seq, tp->snd_una)) { + if (unlikely(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) { + TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_SYN; + TCP_SKB_CB(skb)->seq++; + goto start; + } if (unlikely(before(TCP_SKB_CB(skb)->end_seq, tp->snd_una))) { WARN_ON_ONCE(1); return -EINVAL; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 0b6ee962c84e2..b007d098ffe2e 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -6137,11 +6137,7 @@ static int inet6_fill_prefix(struct sk_buff *skb, struct inet6_dev *idev, pmsg->prefix_len = pinfo->prefix_len; pmsg->prefix_type = pinfo->type; pmsg->prefix_pad3 = 0; - pmsg->prefix_flags = 0; - if (pinfo->onlink) - pmsg->prefix_flags |= IF_PREFIX_ONLINK; - if (pinfo->autoconf) - pmsg->prefix_flags |= IF_PREFIX_AUTOCONF; + pmsg->prefix_flags = pinfo->flags; if (nla_put(skb, PREFIX_ADDRESS, sizeof(pinfo->prefix), &pinfo->prefix)) goto nla_put_failure; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 28b01a068412a..4fc2cae0d116c 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -160,8 +160,6 @@ struct fib6_info *fib6_info_alloc(gfp_t gfp_flags, bool with_fib6_nh) INIT_LIST_HEAD(&f6i->fib6_siblings); refcount_set(&f6i->fib6_ref, 1); - INIT_HLIST_NODE(&f6i->gc_link); - return f6i; } @@ -248,7 +246,6 @@ static struct fib6_table *fib6_alloc_table(struct net *net, u32 id) net->ipv6.fib6_null_entry); table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; inet_peer_base_init(&table->tb6_peers); - INIT_HLIST_HEAD(&table->tb6_gc_hlist); } return table; @@ -1060,8 +1057,6 @@ static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn, lockdep_is_held(&table->tb6_lock)); } } - - fib6_clean_expires_locked(rt); } /* @@ -1123,10 +1118,9 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, if (!(iter->fib6_flags & RTF_EXPIRES)) return -EEXIST; if (!(rt->fib6_flags & RTF_EXPIRES)) - fib6_clean_expires_locked(iter); + fib6_clean_expires(iter); else - fib6_set_expires_locked(iter, - rt->expires); + fib6_set_expires(iter, rt->expires); if (rt->fib6_pmtu) fib6_metric_set(iter, RTAX_MTU, @@ -1485,10 +1479,6 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt, if (rt->nh) list_add(&rt->nh_list, &rt->nh->f6i_list); __fib6_update_sernum_upto_root(rt, fib6_new_sernum(info->nl_net)); - - if (fib6_has_expires(rt)) - hlist_add_head(&rt->gc_link, &table->tb6_gc_hlist); - fib6_start_gc(info->nl_net, rt); } @@ -1511,13 +1501,9 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt, if (!pn_leaf && !(pn->fn_flags & RTN_RTINFO)) { pn_leaf = fib6_find_prefix(info->nl_net, table, pn); -#if RT6_DEBUG >= 2 - if (!pn_leaf) { - WARN_ON(!pn_leaf); + if (!pn_leaf) pn_leaf = info->nl_net->ipv6.fib6_null_entry; - } -#endif fib6_info_hold(pn_leaf); rcu_assign_pointer(pn->leaf, pn_leaf); } @@ -2295,8 +2281,9 @@ static void fib6_flush_trees(struct net *net) * Garbage collection */ -static int fib6_age(struct fib6_info *rt, struct fib6_gc_args *gc_args) +static int fib6_age(struct fib6_info *rt, void *arg) { + struct fib6_gc_args *gc_args = arg; unsigned long now = jiffies; /* @@ -2304,7 +2291,7 @@ static int fib6_age(struct fib6_info *rt, struct fib6_gc_args *gc_args) * Routes are expired even if they are in use. */ - if (fib6_has_expires(rt) && rt->expires) { + if (rt->fib6_flags & RTF_EXPIRES && rt->expires) { if (time_after(now, rt->expires)) { RT6_TRACE("expiring %p\n", rt); return -1; @@ -2321,40 +2308,6 @@ static int fib6_age(struct fib6_info *rt, struct fib6_gc_args *gc_args) return 0; } -static void fib6_gc_table(struct net *net, - struct fib6_table *tb6, - struct fib6_gc_args *gc_args) -{ - struct fib6_info *rt; - struct hlist_node *n; - struct nl_info info = { - .nl_net = net, - .skip_notify = false, - }; - - hlist_for_each_entry_safe(rt, n, &tb6->tb6_gc_hlist, gc_link) - if (fib6_age(rt, gc_args) == -1) - fib6_del(rt, &info); -} - -static void fib6_gc_all(struct net *net, struct fib6_gc_args *gc_args) -{ - struct fib6_table *table; - struct hlist_head *head; - unsigned int h; - - rcu_read_lock(); - for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { - head = &net->ipv6.fib_table_hash[h]; - hlist_for_each_entry_rcu(table, head, tb6_hlist) { - spin_lock_bh(&table->tb6_lock); - fib6_gc_table(net, table, gc_args); - spin_unlock_bh(&table->tb6_lock); - } - } - rcu_read_unlock(); -} - void fib6_run_gc(unsigned long expires, struct net *net, bool force) { struct fib6_gc_args gc_args; @@ -2370,7 +2323,7 @@ void fib6_run_gc(unsigned long expires, struct net *net, bool force) net->ipv6.sysctl.ip6_rt_gc_interval; gc_args.more = 0; - fib6_gc_all(net, &gc_args); + fib6_clean_all(net, fib6_age, &gc_args); now = jiffies; net->ipv6.ip6_rt_last_gc = now; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 9c687b357e6a4..56525b5b95a2b 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3763,10 +3763,10 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg, rt->dst_nocount = true; if (cfg->fc_flags & RTF_EXPIRES) - fib6_set_expires_locked(rt, jiffies + - clock_t_to_jiffies(cfg->fc_expires)); + fib6_set_expires(rt, jiffies + + clock_t_to_jiffies(cfg->fc_expires)); else - fib6_clean_expires_locked(rt); + fib6_clean_expires(rt); if (cfg->fc_protocol == RTPROT_UNSPEC) cfg->fc_protocol = RTPROT_BOOT; diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 0e3a1753a51c6..f7cb50b0dd4ed 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1806,10 +1806,10 @@ static int sta_link_apply_parameters(struct ieee80211_local *local, lockdep_is_held(&local->sta_mtx)); /* - * If there are no changes, then accept a link that doesn't exist, + * If there are no changes, then accept a link that exist, * unless it's a new link. */ - if (params->link_id < 0 && !new_link && + if (params->link_id >= 0 && !new_link && !params->link_mac && !params->txpwr_set && !params->supported_rates_len && !params->ht_capa && !params->vht_capa && @@ -3121,6 +3121,10 @@ static int ieee80211_get_tx_power(struct wiphy *wiphy, else *dbm = sdata->vif.bss_conf.txpower; + /* INT_MIN indicates no power level was set yet */ + if (*dbm == INT_MIN) + return -EINVAL; + return 0; } diff --git a/net/mac80211/driver-ops.c b/net/mac80211/driver-ops.c index aa37a1410f377..f8af0c3d405ae 100644 --- a/net/mac80211/driver-ops.c +++ b/net/mac80211/driver-ops.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only /* * Copyright 2015 Intel Deutschland GmbH - * Copyright (C) 2022 Intel Corporation + * Copyright (C) 2022-2023 Intel Corporation */ #include #include "ieee80211_i.h" @@ -564,6 +564,10 @@ int drv_change_sta_links(struct ieee80211_local *local, if (ret) return ret; + /* during reconfig don't add it to debugfs again */ + if (local->in_reconfig) + return 0; + for_each_set_bit(link_id, &links_to_add, IEEE80211_MLD_MAX_NUM_LINKS) { link_sta = rcu_dereference_protected(info->link[link_id], lockdep_is_held(&local->sta_mtx)); diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index c4505593ba7a6..2bc2fbe58f944 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -23,7 +23,7 @@ static inline struct ieee80211_sub_if_data * get_bss_sdata(struct ieee80211_sub_if_data *sdata) { - if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) + if (sdata && sdata->vif.type == NL80211_IFTYPE_AP_VLAN) sdata = container_of(sdata->bss, struct ieee80211_sub_if_data, u.ap); @@ -638,10 +638,13 @@ static inline void drv_flush(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, u32 queues, bool drop) { - struct ieee80211_vif *vif = sdata ? &sdata->vif : NULL; + struct ieee80211_vif *vif; might_sleep(); + sdata = get_bss_sdata(sdata); + vif = sdata ? &sdata->vif : NULL; + if (sdata && !check_sdata_in_driver(sdata)) return; @@ -657,6 +660,8 @@ static inline void drv_flush_sta(struct ieee80211_local *local, { might_sleep(); + sdata = get_bss_sdata(sdata); + if (sdata && !check_sdata_in_driver(sdata)) return; diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c index a1e526419e9d2..cc62c2a01f54f 100644 --- a/net/mac80211/mesh_plink.c +++ b/net/mac80211/mesh_plink.c @@ -1064,8 +1064,8 @@ mesh_plink_get_event(struct ieee80211_sub_if_data *sdata, case WLAN_SP_MESH_PEERING_OPEN: if (!matches_local) event = OPN_RJCT; - if (!mesh_plink_free_count(sdata) || - (sta->mesh->plid && sta->mesh->plid != plid)) + else if (!mesh_plink_free_count(sdata) || + (sta->mesh->plid && sta->mesh->plid != plid)) event = OPN_IGNR; else event = OPN_ACPT; @@ -1073,9 +1073,9 @@ mesh_plink_get_event(struct ieee80211_sub_if_data *sdata, case WLAN_SP_MESH_PEERING_CONFIRM: if (!matches_local) event = CNF_RJCT; - if (!mesh_plink_free_count(sdata) || - sta->mesh->llid != llid || - (sta->mesh->plid && sta->mesh->plid != plid)) + else if (!mesh_plink_free_count(sdata) || + sta->mesh->llid != llid || + (sta->mesh->plid && sta->mesh->plid != plid)) event = CNF_IGNR; else event = CNF_ACPT; @@ -1243,6 +1243,8 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, return; } elems = ieee802_11_parse_elems(baseaddr, len - baselen, true, NULL); - mesh_process_plink_frame(sdata, mgmt, elems, rx_status); - kfree(elems); + if (elems) { + mesh_process_plink_frame(sdata, mgmt, elems, rx_status); + kfree(elems); + } } diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 0c9198997482b..73f8df03d159c 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -5805,7 +5805,7 @@ static void ieee80211_ml_reconfiguration(struct ieee80211_sub_if_data *sdata, { const struct ieee80211_multi_link_elem *ml; const struct element *sub; - size_t ml_len; + ssize_t ml_len; unsigned long removed_links = 0; u16 link_removal_timeout[IEEE80211_MLD_MAX_NUM_LINKS] = {}; u8 link_id; @@ -5821,6 +5821,8 @@ static void ieee80211_ml_reconfiguration(struct ieee80211_sub_if_data *sdata, elems->scratch + elems->scratch_len - elems->scratch_pos, WLAN_EID_FRAGMENT); + if (ml_len < 0) + return; elems->ml_reconf = (const void *)elems->scratch_pos; elems->ml_reconf_len = ml_len; diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 9661f38126826..3011bc378462b 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -1538,8 +1538,9 @@ void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list) struct mptcp_pm_addr_entry *entry; list_for_each_entry(entry, rm_list, list) { - remove_anno_list_by_saddr(msk, &entry->addr); - if (alist.nr < MPTCP_RM_IDS_MAX) + if ((remove_anno_list_by_saddr(msk, &entry->addr) || + lookup_subflow_by_saddr(&msk->conn_list, &entry->addr)) && + alist.nr < MPTCP_RM_IDS_MAX) alist.ids[alist.nr++] = entry->addr.id; } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 886ab689a8aea..5c003a0f0fe5b 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -893,6 +893,7 @@ static bool __mptcp_finish_join(struct mptcp_sock *msk, struct sock *ssk) mptcp_sockopt_sync_locked(msk, ssk); mptcp_subflow_joined(msk, ssk); mptcp_stop_tout_timer(sk); + __mptcp_propagate_sndbuf(sk, ssk); return true; } @@ -1079,15 +1080,16 @@ static void mptcp_enter_memory_pressure(struct sock *sk) struct mptcp_sock *msk = mptcp_sk(sk); bool first = true; - sk_stream_moderate_sndbuf(sk); mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); if (first) tcp_enter_memory_pressure(ssk); sk_stream_moderate_sndbuf(ssk); + first = false; } + __mptcp_sync_sndbuf(sk); } /* ensure we get enough memory for the frag hdr, beyond some minimal amount of @@ -1231,6 +1233,8 @@ static void mptcp_update_infinite_map(struct mptcp_sock *msk, mptcp_do_fallback(ssk); } +#define MPTCP_MAX_GSO_SIZE (GSO_LEGACY_MAX_SIZE - (MAX_TCP_HEADER + 1)) + static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, struct mptcp_data_frag *dfrag, struct mptcp_sendmsg_info *info) @@ -1257,6 +1261,8 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, return -EAGAIN; /* compute send limit */ + if (unlikely(ssk->sk_gso_max_size > MPTCP_MAX_GSO_SIZE)) + ssk->sk_gso_max_size = MPTCP_MAX_GSO_SIZE; info->mss_now = tcp_send_mss(ssk, &info->size_goal, info->flags); copy = info->size_goal; @@ -2448,6 +2454,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, WRITE_ONCE(msk->first, NULL); out: + __mptcp_sync_sndbuf(sk); if (need_push) __mptcp_push_pending(sk, 0); @@ -3219,7 +3226,7 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk, * uses the correct data */ mptcp_copy_inaddrs(nsk, ssk); - mptcp_propagate_sndbuf(nsk, ssk); + __mptcp_propagate_sndbuf(nsk, ssk); mptcp_rcv_space_init(msk, ssk); bh_unlock_sock(nsk); @@ -3390,13 +3397,16 @@ static void mptcp_release_cb(struct sock *sk) if (__test_and_clear_bit(MPTCP_CLEAN_UNA, &msk->cb_flags)) __mptcp_clean_una_wakeup(sk); if (unlikely(msk->cb_flags)) { - /* be sure to set the current sk state before tacking actions - * depending on sk_state, that is processing MPTCP_ERROR_REPORT + /* be sure to sync the msk state before taking actions + * depending on sk_state (MPTCP_ERROR_REPORT) + * On sk release avoid actions depending on the first subflow */ - if (__test_and_clear_bit(MPTCP_CONNECTED, &msk->cb_flags)) - __mptcp_set_connected(sk); + if (__test_and_clear_bit(MPTCP_SYNC_STATE, &msk->cb_flags) && msk->first) + __mptcp_sync_state(sk, msk->pending_state); if (__test_and_clear_bit(MPTCP_ERROR_REPORT, &msk->cb_flags)) __mptcp_error_report(sk); + if (__test_and_clear_bit(MPTCP_SYNC_SNDBUF, &msk->cb_flags)) + __mptcp_sync_sndbuf(sk); } __mptcp_update_rmem(sk); @@ -3441,6 +3451,14 @@ void mptcp_subflow_process_delegated(struct sock *ssk, long status) __set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->cb_flags); mptcp_data_unlock(sk); } + if (status & BIT(MPTCP_DELEGATE_SNDBUF)) { + mptcp_data_lock(sk); + if (!sock_owned_by_user(sk)) + __mptcp_sync_sndbuf(sk); + else + __set_bit(MPTCP_SYNC_SNDBUF, &mptcp_sk(sk)->cb_flags); + mptcp_data_unlock(sk); + } if (status & BIT(MPTCP_DELEGATE_ACK)) schedule_3rdack_retransmission(ssk); } @@ -3525,6 +3543,7 @@ bool mptcp_finish_join(struct sock *ssk) /* active subflow, already present inside the conn_list */ if (!list_empty(&subflow->node)) { mptcp_subflow_joined(msk, ssk); + mptcp_propagate_sndbuf(parent, ssk); return true; } diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 3612545fa62e0..07c5ac37d092b 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -122,7 +122,8 @@ #define MPTCP_ERROR_REPORT 3 #define MPTCP_RETRANSMIT 4 #define MPTCP_FLUSH_JOIN_LIST 5 -#define MPTCP_CONNECTED 6 +#define MPTCP_SYNC_STATE 6 +#define MPTCP_SYNC_SNDBUF 7 struct mptcp_skb_cb { u64 map_seq; @@ -292,6 +293,9 @@ struct mptcp_sock { bool use_64bit_ack; /* Set when we received a 64-bit DSN */ bool csum_enabled; bool allow_infinite_fallback; + u8 pending_state; /* A subflow asked to set this sk_state, + * protected by the msk data lock + */ u8 mpc_endpoint_id; u8 recvmsg_inq:1, cork:1, @@ -447,6 +451,7 @@ DECLARE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions); #define MPTCP_DELEGATE_SCHEDULED 0 #define MPTCP_DELEGATE_SEND 1 #define MPTCP_DELEGATE_ACK 2 +#define MPTCP_DELEGATE_SNDBUF 3 #define MPTCP_DELEGATE_ACTIONS_MASK (~BIT(MPTCP_DELEGATE_SCHEDULED)) /* MPTCP subflow context */ @@ -520,6 +525,9 @@ struct mptcp_subflow_context { u32 setsockopt_seq; u32 stale_rcv_tstamp; + int cached_sndbuf; /* sndbuf size when last synced with the msk sndbuf, + * protected by the msk socket lock + */ struct sock *tcp_sock; /* tcp sk backpointer */ struct sock *conn; /* parent mptcp_sock */ @@ -706,7 +714,7 @@ void mptcp_get_options(const struct sk_buff *skb, struct mptcp_options_received *mp_opt); void mptcp_finish_connect(struct sock *sk); -void __mptcp_set_connected(struct sock *sk); +void __mptcp_sync_state(struct sock *sk, int state); void mptcp_reset_tout_timer(struct mptcp_sock *msk, unsigned long fail_tout); static inline void mptcp_stop_tout_timer(struct sock *sk) @@ -762,13 +770,52 @@ static inline bool mptcp_data_fin_enabled(const struct mptcp_sock *msk) READ_ONCE(msk->write_seq) == READ_ONCE(msk->snd_nxt); } -static inline bool mptcp_propagate_sndbuf(struct sock *sk, struct sock *ssk) +static inline void __mptcp_sync_sndbuf(struct sock *sk) { - if ((sk->sk_userlocks & SOCK_SNDBUF_LOCK) || ssk->sk_sndbuf <= READ_ONCE(sk->sk_sndbuf)) - return false; + struct mptcp_subflow_context *subflow; + int ssk_sndbuf, new_sndbuf; + + if (sk->sk_userlocks & SOCK_SNDBUF_LOCK) + return; + + new_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[0]; + mptcp_for_each_subflow(mptcp_sk(sk), subflow) { + ssk_sndbuf = READ_ONCE(mptcp_subflow_tcp_sock(subflow)->sk_sndbuf); + + subflow->cached_sndbuf = ssk_sndbuf; + new_sndbuf += ssk_sndbuf; + } + + /* the msk max wmem limit is * tcp wmem[2] */ + WRITE_ONCE(sk->sk_sndbuf, new_sndbuf); +} + +/* The called held both the msk socket and the subflow socket locks, + * possibly under BH + */ +static inline void __mptcp_propagate_sndbuf(struct sock *sk, struct sock *ssk) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + + if (READ_ONCE(ssk->sk_sndbuf) != subflow->cached_sndbuf) + __mptcp_sync_sndbuf(sk); +} + +/* the caller held only the subflow socket lock, either in process or + * BH context. Additionally this can be called under the msk data lock, + * so we can't acquire such lock here: let the delegate action acquires + * the needed locks in suitable order. + */ +static inline void mptcp_propagate_sndbuf(struct sock *sk, struct sock *ssk) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + + if (likely(READ_ONCE(ssk->sk_sndbuf) == subflow->cached_sndbuf)) + return; - WRITE_ONCE(sk->sk_sndbuf, ssk->sk_sndbuf); - return true; + local_bh_disable(); + mptcp_subflow_delegate(subflow, MPTCP_DELEGATE_SNDBUF); + local_bh_enable(); } static inline void mptcp_write_space(struct sock *sk) @@ -1057,7 +1104,7 @@ static inline bool subflow_simultaneous_connect(struct sock *sk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); - return sk->sk_state == TCP_ESTABLISHED && + return (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_FIN_WAIT1) && is_active_ssk(subflow) && !subflow->conn_finished; } diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 8260202c00669..116e3008231bd 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -95,6 +95,7 @@ static void mptcp_sol_socket_sync_intval(struct mptcp_sock *msk, int optname, in case SO_SNDBUFFORCE: ssk->sk_userlocks |= SOCK_SNDBUF_LOCK; WRITE_ONCE(ssk->sk_sndbuf, sk->sk_sndbuf); + mptcp_subflow_ctx(ssk)->cached_sndbuf = sk->sk_sndbuf; break; case SO_RCVBUF: case SO_RCVBUFFORCE: @@ -737,8 +738,11 @@ static int mptcp_setsockopt_v4_set_tos(struct mptcp_sock *msk, int optname, val = inet_sk(sk)->tos; mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + bool slow; + slow = lock_sock_fast(ssk); __ip_sock_set_tos(ssk, val); + unlock_sock_fast(ssk, slow); } release_sock(sk); @@ -1415,8 +1419,10 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk) if (sk->sk_userlocks & tx_rx_locks) { ssk->sk_userlocks |= sk->sk_userlocks & tx_rx_locks; - if (sk->sk_userlocks & SOCK_SNDBUF_LOCK) + if (sk->sk_userlocks & SOCK_SNDBUF_LOCK) { WRITE_ONCE(ssk->sk_sndbuf, sk->sk_sndbuf); + mptcp_subflow_ctx(ssk)->cached_sndbuf = sk->sk_sndbuf; + } if (sk->sk_userlocks & SOCK_RCVBUF_LOCK) WRITE_ONCE(ssk->sk_rcvbuf, sk->sk_rcvbuf); } diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 9c1f8d1d63d24..f3a1e4aa0e5eb 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -419,21 +419,28 @@ static bool subflow_use_different_dport(struct mptcp_sock *msk, const struct soc return inet_sk(sk)->inet_dport != inet_sk((struct sock *)msk)->inet_dport; } -void __mptcp_set_connected(struct sock *sk) +void __mptcp_sync_state(struct sock *sk, int state) { + struct mptcp_sock *msk = mptcp_sk(sk); + + __mptcp_propagate_sndbuf(sk, msk->first); if (sk->sk_state == TCP_SYN_SENT) { - inet_sk_state_store(sk, TCP_ESTABLISHED); + inet_sk_state_store(sk, state); sk->sk_state_change(sk); } } -static void mptcp_set_connected(struct sock *sk) +static void mptcp_propagate_state(struct sock *sk, struct sock *ssk) { + struct mptcp_sock *msk = mptcp_sk(sk); + mptcp_data_lock(sk); - if (!sock_owned_by_user(sk)) - __mptcp_set_connected(sk); - else - __set_bit(MPTCP_CONNECTED, &mptcp_sk(sk)->cb_flags); + if (!sock_owned_by_user(sk)) { + __mptcp_sync_state(sk, ssk->sk_state); + } else { + msk->pending_state = ssk->sk_state; + __set_bit(MPTCP_SYNC_STATE, &msk->cb_flags); + } mptcp_data_unlock(sk); } @@ -472,7 +479,6 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) return; msk = mptcp_sk(parent); - mptcp_propagate_sndbuf(parent, sk); subflow->rel_write_seq = 1; subflow->conn_finished = 1; subflow->ssn_offset = TCP_SKB_CB(skb)->seq; @@ -496,7 +502,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) subflow_set_remote_key(msk, subflow, &mp_opt); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVEACK); mptcp_finish_connect(sk); - mptcp_set_connected(parent); + mptcp_propagate_state(parent, sk); } else if (subflow->request_join) { u8 hmac[SHA256_DIGEST_SIZE]; @@ -540,7 +546,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) } else if (mptcp_check_fallback(sk)) { fallback: mptcp_rcv_space_init(msk, sk); - mptcp_set_connected(parent); + mptcp_propagate_state(parent, sk); } return; @@ -1728,12 +1734,11 @@ static void subflow_state_change(struct sock *sk) msk = mptcp_sk(parent); if (subflow_simultaneous_connect(sk)) { - mptcp_propagate_sndbuf(parent, sk); mptcp_do_fallback(sk); mptcp_rcv_space_init(msk, sk); pr_fallback(msk); subflow->conn_finished = 1; - mptcp_set_connected(parent); + mptcp_propagate_state(parent, sk); } /* as recvmsg() does not acquire the subflow socket for ssk selection diff --git a/net/ncsi/ncsi-aen.c b/net/ncsi/ncsi-aen.c index f8854bff286cb..62fb1031763d1 100644 --- a/net/ncsi/ncsi-aen.c +++ b/net/ncsi/ncsi-aen.c @@ -89,11 +89,6 @@ static int ncsi_aen_handler_lsc(struct ncsi_dev_priv *ndp, if ((had_link == has_link) || chained) return 0; - if (had_link) - netif_carrier_off(ndp->ndev.dev); - else - netif_carrier_on(ndp->ndev.dev); - if (!ndp->multi_package && !nc->package->multi_channel) { if (had_link) { ndp->flags |= NCSI_DEV_RESHUFFLE; diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 35d2f9c9ada02..4c133e06be1de 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -61,6 +61,8 @@ MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_IPSET); ip_set_dereference((inst)->ip_set_list)[id] #define ip_set_ref_netlink(inst,id) \ rcu_dereference_raw((inst)->ip_set_list)[id] +#define ip_set_dereference_nfnl(p) \ + rcu_dereference_check(p, lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET)) /* The set types are implemented in modules and registered set types * can be found in ip_set_type_list. Adding/deleting types is @@ -708,15 +710,10 @@ __ip_set_put_netlink(struct ip_set *set) static struct ip_set * ip_set_rcu_get(struct net *net, ip_set_id_t index) { - struct ip_set *set; struct ip_set_net *inst = ip_set_pernet(net); - rcu_read_lock(); - /* ip_set_list itself needs to be protected */ - set = rcu_dereference(inst->ip_set_list)[index]; - rcu_read_unlock(); - - return set; + /* ip_set_list and the set pointer need to be protected */ + return ip_set_dereference_nfnl(inst->ip_set_list)[index]; } static inline void @@ -1397,6 +1394,9 @@ static int ip_set_swap(struct sk_buff *skb, const struct nfnl_info *info, ip_set(inst, to_id) = from; write_unlock_bh(&ip_set_ref_lock); + /* Make sure all readers of the old set pointers are completed. */ + synchronize_rcu(); + return 0; } diff --git a/net/netfilter/nf_bpf_link.c b/net/netfilter/nf_bpf_link.c index e502ec00b2fe1..0e4beae421f83 100644 --- a/net/netfilter/nf_bpf_link.c +++ b/net/netfilter/nf_bpf_link.c @@ -31,7 +31,7 @@ struct bpf_nf_link { #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) || IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) static const struct nf_defrag_hook * get_proto_defrag_hook(struct bpf_nf_link *link, - const struct nf_defrag_hook __rcu *global_hook, + const struct nf_defrag_hook __rcu **ptr_global_hook, const char *mod) { const struct nf_defrag_hook *hook; @@ -39,7 +39,7 @@ get_proto_defrag_hook(struct bpf_nf_link *link, /* RCU protects us from races against module unloading */ rcu_read_lock(); - hook = rcu_dereference(global_hook); + hook = rcu_dereference(*ptr_global_hook); if (!hook) { rcu_read_unlock(); err = request_module(mod); @@ -47,7 +47,7 @@ get_proto_defrag_hook(struct bpf_nf_link *link, return ERR_PTR(err < 0 ? err : -EINVAL); rcu_read_lock(); - hook = rcu_dereference(global_hook); + hook = rcu_dereference(*ptr_global_hook); } if (hook && try_module_get(hook->owner)) { @@ -78,7 +78,7 @@ static int bpf_nf_enable_defrag(struct bpf_nf_link *link) switch (link->hook_ops.pf) { #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) case NFPROTO_IPV4: - hook = get_proto_defrag_hook(link, nf_defrag_v4_hook, "nf_defrag_ipv4"); + hook = get_proto_defrag_hook(link, &nf_defrag_v4_hook, "nf_defrag_ipv4"); if (IS_ERR(hook)) return PTR_ERR(hook); @@ -87,7 +87,7 @@ static int bpf_nf_enable_defrag(struct bpf_nf_link *link) #endif #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) case NFPROTO_IPV6: - hook = get_proto_defrag_hook(link, nf_defrag_v6_hook, "nf_defrag_ipv6"); + hook = get_proto_defrag_hook(link, &nf_defrag_v6_hook, "nf_defrag_ipv6"); if (IS_ERR(hook)) return PTR_ERR(hook); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 3bf428a188ccf..5a14e1ab0b131 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -805,7 +805,7 @@ static struct nft_table *nft_table_lookup(const struct net *net, static struct nft_table *nft_table_lookup_byhandle(const struct net *net, const struct nlattr *nla, - u8 genmask, u32 nlpid) + int family, u8 genmask, u32 nlpid) { struct nftables_pernet *nft_net; struct nft_table *table; @@ -813,6 +813,7 @@ static struct nft_table *nft_table_lookup_byhandle(const struct net *net, nft_net = nft_pernet(net); list_for_each_entry(table, &nft_net->tables, list) { if (be64_to_cpu(nla_get_be64(nla)) == table->handle && + table->family == family && nft_active_genmask(table, genmask)) { if (nft_table_has_owner(table) && nlpid && table->nlpid != nlpid) @@ -1546,7 +1547,7 @@ static int nf_tables_deltable(struct sk_buff *skb, const struct nfnl_info *info, if (nla[NFTA_TABLE_HANDLE]) { attr = nla[NFTA_TABLE_HANDLE]; - table = nft_table_lookup_byhandle(net, attr, genmask, + table = nft_table_lookup_byhandle(net, attr, family, genmask, NETLINK_CB(skb).portid); } else { attr = nla[NFTA_TABLE_NAME]; @@ -6464,6 +6465,12 @@ static int nft_setelem_deactivate(const struct net *net, return ret; } +static void nft_setelem_catchall_destroy(struct nft_set_elem_catchall *catchall) +{ + list_del_rcu(&catchall->list); + kfree_rcu(catchall, rcu); +} + static void nft_setelem_catchall_remove(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem) @@ -6472,8 +6479,7 @@ static void nft_setelem_catchall_remove(const struct net *net, list_for_each_entry_safe(catchall, next, &set->catchall_list, list) { if (catchall->elem == elem->priv) { - list_del_rcu(&catchall->list); - kfree_rcu(catchall, rcu); + nft_setelem_catchall_destroy(catchall); break; } } @@ -7205,10 +7211,11 @@ static int nf_tables_delsetelem(struct sk_buff *skb, if (err < 0) { NL_SET_BAD_ATTR(extack, attr); - break; + return err; } } - return err; + + return 0; } /* @@ -9634,9 +9641,8 @@ void nft_trans_gc_queue_sync_done(struct nft_trans_gc *trans) call_rcu(&trans->rcu, nft_trans_gc_trans_free); } -static struct nft_trans_gc *nft_trans_gc_catchall(struct nft_trans_gc *gc, - unsigned int gc_seq, - bool sync) +struct nft_trans_gc *nft_trans_gc_catchall_async(struct nft_trans_gc *gc, + unsigned int gc_seq) { struct nft_set_elem_catchall *catchall; const struct nft_set *set = gc->set; @@ -9652,11 +9658,7 @@ static struct nft_trans_gc *nft_trans_gc_catchall(struct nft_trans_gc *gc, nft_set_elem_dead(ext); dead_elem: - if (sync) - gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); - else - gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC); - + gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC); if (!gc) return NULL; @@ -9666,15 +9668,34 @@ static struct nft_trans_gc *nft_trans_gc_catchall(struct nft_trans_gc *gc, return gc; } -struct nft_trans_gc *nft_trans_gc_catchall_async(struct nft_trans_gc *gc, - unsigned int gc_seq) -{ - return nft_trans_gc_catchall(gc, gc_seq, false); -} - struct nft_trans_gc *nft_trans_gc_catchall_sync(struct nft_trans_gc *gc) { - return nft_trans_gc_catchall(gc, 0, true); + struct nft_set_elem_catchall *catchall, *next; + const struct nft_set *set = gc->set; + struct nft_set_elem elem; + struct nft_set_ext *ext; + + WARN_ON_ONCE(!lockdep_commit_lock_is_held(gc->net)); + + list_for_each_entry_safe(catchall, next, &set->catchall_list, list) { + ext = nft_set_elem_ext(set, catchall->elem); + + if (!nft_set_elem_expired(ext)) + continue; + + gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL); + if (!gc) + return NULL; + + memset(&elem, 0, sizeof(elem)); + elem.priv = catchall->elem; + + nft_setelem_data_deactivate(gc->net, gc->set, &elem); + nft_setelem_catchall_destroy(catchall); + nft_trans_gc_elem_add(gc, elem.priv); + } + + return gc; } static void nf_tables_module_autoload_cleanup(struct net *net) @@ -9828,7 +9849,7 @@ static void nft_set_commit_update(struct list_head *set_update_list) list_for_each_entry_safe(set, next, set_update_list, pending_update) { list_del_init(&set->pending_update); - if (!set->ops->commit) + if (!set->ops->commit || set->dead) continue; set->ops->commit(set); diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c index e596d1a842f70..f6e791a681015 100644 --- a/net/netfilter/nft_byteorder.c +++ b/net/netfilter/nft_byteorder.c @@ -38,13 +38,14 @@ void nft_byteorder_eval(const struct nft_expr *expr, switch (priv->size) { case 8: { + u64 *dst64 = (void *)dst; u64 src64; switch (priv->op) { case NFT_BYTEORDER_NTOH: for (i = 0; i < priv->len / 8; i++) { src64 = nft_reg_load64(&src[i]); - nft_reg_store64(&dst[i], + nft_reg_store64(&dst64[i], be64_to_cpu((__force __be64)src64)); } break; @@ -52,7 +53,7 @@ void nft_byteorder_eval(const struct nft_expr *expr, for (i = 0; i < priv->len / 8; i++) { src64 = (__force __u64) cpu_to_be64(nft_reg_load64(&src[i])); - nft_reg_store64(&dst[i], src64); + nft_reg_store64(&dst64[i], src64); } break; } diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index 5c5cc01c73c5a..629a91a8c6141 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -279,10 +279,15 @@ static int nft_dynset_init(const struct nft_ctx *ctx, priv->expr_array[i] = dynset_expr; priv->num_exprs++; - if (set->num_exprs && - dynset_expr->ops != set->exprs[i]->ops) { - err = -EOPNOTSUPP; - goto err_expr_free; + if (set->num_exprs) { + if (i >= set->num_exprs) { + err = -EINVAL; + goto err_expr_free; + } + if (dynset_expr->ops != set->exprs[i]->ops) { + err = -EOPNOTSUPP; + goto err_expr_free; + } } i++; } diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index 3fbaa7bf41f9c..6eb571d0c3fdf 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -214,7 +214,7 @@ static void nft_exthdr_tcp_eval(const struct nft_expr *expr, offset = i + priv->offset; if (priv->flags & NFT_EXTHDR_F_PRESENT) { - *dest = 1; + nft_reg_store8(dest, 1); } else { if (priv->len % NFT_REG32_SIZE) dest[priv->len / NFT_REG32_SIZE] = 0; @@ -461,7 +461,7 @@ static void nft_exthdr_dccp_eval(const struct nft_expr *expr, type = bufp[0]; if (type == priv->type) { - *dest = 1; + nft_reg_store8(dest, 1); return; } diff --git a/net/netfilter/nft_fib.c b/net/netfilter/nft_fib.c index 04b51f2853321..ca905aa8227e5 100644 --- a/net/netfilter/nft_fib.c +++ b/net/netfilter/nft_fib.c @@ -145,11 +145,15 @@ void nft_fib_store_result(void *reg, const struct nft_fib *priv, switch (priv->result) { case NFT_FIB_RESULT_OIF: index = dev ? dev->ifindex : 0; - *dreg = (priv->flags & NFTA_FIB_F_PRESENT) ? !!index : index; + if (priv->flags & NFTA_FIB_F_PRESENT) + nft_reg_store8(dreg, !!index); + else + *dreg = index; + break; case NFT_FIB_RESULT_OIFNAME: if (priv->flags & NFTA_FIB_F_PRESENT) - *dreg = !!dev; + nft_reg_store8(dreg, !!dev); else strscpy_pad(reg, dev ? dev->name : "", IFNAMSIZ); break; diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index f7da7c43333b5..ba0d3683a45d3 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -63,7 +63,7 @@ nft_meta_get_eval_time(enum nft_meta_keys key, { switch (key) { case NFT_META_TIME_NS: - nft_reg_store64(dest, ktime_get_real_ns()); + nft_reg_store64((u64 *)dest, ktime_get_real_ns()); break; case NFT_META_TIME_DAY: nft_reg_store8(dest, nft_meta_weekday()); diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index c0dcc40de358f..3ff31043f7148 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -2041,6 +2041,9 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, e = f->mt[r].e; + if (!nft_set_elem_active(&e->ext, iter->genmask)) + goto cont; + elem.priv = e; iter->err = iter->fn(ctx, set, iter, &elem); diff --git a/net/netfilter/xt_owner.c b/net/netfilter/xt_owner.c index e85ce69924aee..50332888c8d23 100644 --- a/net/netfilter/xt_owner.c +++ b/net/netfilter/xt_owner.c @@ -76,18 +76,23 @@ owner_mt(const struct sk_buff *skb, struct xt_action_param *par) */ return false; - filp = sk->sk_socket->file; - if (filp == NULL) + read_lock_bh(&sk->sk_callback_lock); + filp = sk->sk_socket ? sk->sk_socket->file : NULL; + if (filp == NULL) { + read_unlock_bh(&sk->sk_callback_lock); return ((info->match ^ info->invert) & (XT_OWNER_UID | XT_OWNER_GID)) == 0; + } if (info->match & XT_OWNER_UID) { kuid_t uid_min = make_kuid(net->user_ns, info->uid_min); kuid_t uid_max = make_kuid(net->user_ns, info->uid_max); if ((uid_gte(filp->f_cred->fsuid, uid_min) && uid_lte(filp->f_cred->fsuid, uid_max)) ^ - !(info->invert & XT_OWNER_UID)) + !(info->invert & XT_OWNER_UID)) { + read_unlock_bh(&sk->sk_callback_lock); return false; + } } if (info->match & XT_OWNER_GID) { @@ -112,10 +117,13 @@ owner_mt(const struct sk_buff *skb, struct xt_action_param *par) } } - if (match ^ !(info->invert & XT_OWNER_GID)) + if (match ^ !(info->invert & XT_OWNER_GID)) { + read_unlock_bh(&sk->sk_callback_lock); return false; + } } + read_unlock_bh(&sk->sk_callback_lock); return true; } diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 8315d31b53db4..d41c4a936ad0c 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -1690,6 +1690,9 @@ static int genl_bind(struct net *net, int group) if ((grp->flags & GENL_UNS_ADMIN_PERM) && !ns_capable(net->user_ns, CAP_NET_ADMIN)) ret = -EPERM; + if (grp->cap_sys_admin && + !ns_capable(net->user_ns, CAP_SYS_ADMIN)) + ret = -EPERM; break; } diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index a84e00b5904be..7adf48549a3b7 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -4300,7 +4300,7 @@ static void packet_mm_open(struct vm_area_struct *vma) struct sock *sk = sock->sk; if (sk) - atomic_inc(&pkt_sk(sk)->mapped); + atomic_long_inc(&pkt_sk(sk)->mapped); } static void packet_mm_close(struct vm_area_struct *vma) @@ -4310,7 +4310,7 @@ static void packet_mm_close(struct vm_area_struct *vma) struct sock *sk = sock->sk; if (sk) - atomic_dec(&pkt_sk(sk)->mapped); + atomic_long_dec(&pkt_sk(sk)->mapped); } static const struct vm_operations_struct packet_mmap_ops = { @@ -4405,7 +4405,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, err = -EBUSY; if (!closing) { - if (atomic_read(&po->mapped)) + if (atomic_long_read(&po->mapped)) goto out; if (packet_read_pending(rb)) goto out; @@ -4508,7 +4508,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, err = -EBUSY; mutex_lock(&po->pg_vec_lock); - if (closing || atomic_read(&po->mapped) == 0) { + if (closing || atomic_long_read(&po->mapped) == 0) { err = 0; spin_lock_bh(&rb_queue->lock); swap(rb->pg_vec, pg_vec); @@ -4526,9 +4526,9 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, po->prot_hook.func = (po->rx_ring.pg_vec) ? tpacket_rcv : packet_rcv; skb_queue_purge(rb_queue); - if (atomic_read(&po->mapped)) - pr_err("packet_mmap: vma is busy: %d\n", - atomic_read(&po->mapped)); + if (atomic_long_read(&po->mapped)) + pr_err("packet_mmap: vma is busy: %ld\n", + atomic_long_read(&po->mapped)); } mutex_unlock(&po->pg_vec_lock); @@ -4606,7 +4606,7 @@ static int packet_mmap(struct file *file, struct socket *sock, } } - atomic_inc(&po->mapped); + atomic_long_inc(&po->mapped); vma->vm_ops = &packet_mmap_ops; err = 0; diff --git a/net/packet/internal.h b/net/packet/internal.h index 63f4865202c13..11ba8a78676ab 100644 --- a/net/packet/internal.h +++ b/net/packet/internal.h @@ -122,7 +122,7 @@ struct packet_sock { __be16 num; struct packet_rollover *rollover; struct packet_mclist *mclist; - atomic_t mapped; + atomic_long_t mapped; enum tpacket_versions tp_version; unsigned int tp_hdrlen; unsigned int tp_reserve; diff --git a/net/psample/psample.c b/net/psample/psample.c index 81a794e36f535..c34e902855dbe 100644 --- a/net/psample/psample.c +++ b/net/psample/psample.c @@ -31,7 +31,8 @@ enum psample_nl_multicast_groups { static const struct genl_multicast_group psample_nl_mcgrps[] = { [PSAMPLE_NL_MCGRP_CONFIG] = { .name = PSAMPLE_NL_MCGRP_CONFIG_NAME }, - [PSAMPLE_NL_MCGRP_SAMPLE] = { .name = PSAMPLE_NL_MCGRP_SAMPLE_NAME }, + [PSAMPLE_NL_MCGRP_SAMPLE] = { .name = PSAMPLE_NL_MCGRP_SAMPLE_NAME, + .flags = GENL_UNS_ADMIN_PERM }, }; static struct genl_family psample_nl_family __ro_after_init; diff --git a/net/rfkill/rfkill-gpio.c b/net/rfkill/rfkill-gpio.c index 5a81505fba9ac..4e32d659524e0 100644 --- a/net/rfkill/rfkill-gpio.c +++ b/net/rfkill/rfkill-gpio.c @@ -126,6 +126,14 @@ static int rfkill_gpio_probe(struct platform_device *pdev) return -EINVAL; } + ret = gpiod_direction_output(rfkill->reset_gpio, true); + if (ret) + return ret; + + ret = gpiod_direction_output(rfkill->shutdown_gpio, true); + if (ret) + return ret; + rfkill->rfkill_dev = rfkill_alloc(rfkill->name, &pdev->dev, rfkill->type, &rfkill_gpio_ops, rfkill); diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 49dafe9ac72f0..42e8b9e37516b 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -182,21 +182,47 @@ void rose_kill_by_neigh(struct rose_neigh *neigh) */ static void rose_kill_by_device(struct net_device *dev) { - struct sock *s; + struct sock *sk, *array[16]; + struct rose_sock *rose; + bool rescan; + int i, cnt; +start: + rescan = false; + cnt = 0; spin_lock_bh(&rose_list_lock); - sk_for_each(s, &rose_list) { - struct rose_sock *rose = rose_sk(s); + sk_for_each(sk, &rose_list) { + rose = rose_sk(sk); + if (rose->device == dev) { + if (cnt == ARRAY_SIZE(array)) { + rescan = true; + break; + } + sock_hold(sk); + array[cnt++] = sk; + } + } + spin_unlock_bh(&rose_list_lock); + for (i = 0; i < cnt; i++) { + sk = array[cnt]; + rose = rose_sk(sk); + lock_sock(sk); + spin_lock_bh(&rose_list_lock); if (rose->device == dev) { - rose_disconnect(s, ENETUNREACH, ROSE_OUT_OF_ORDER, 0); + rose_disconnect(sk, ENETUNREACH, ROSE_OUT_OF_ORDER, 0); if (rose->neighbour) rose->neighbour->use--; netdev_put(rose->device, &rose->dev_tracker); rose->device = NULL; } + spin_unlock_bh(&rose_list_lock); + release_sock(sk); + sock_put(sk); + cond_resched(); } - spin_unlock_bh(&rose_list_lock); + if (rescan) + goto start; } /* @@ -656,7 +682,10 @@ static int rose_release(struct socket *sock) break; } + spin_lock_bh(&rose_list_lock); netdev_put(rose->device, &rose->dev_tracker); + rose->device = NULL; + spin_unlock_bh(&rose_list_lock); sock->sk = NULL; release_sock(sk); sock_put(sk); @@ -1315,9 +1344,11 @@ static int rose_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) case TIOCINQ: { struct sk_buff *skb; long amount = 0L; - /* These two are safe on a single CPU system as only user tasks fiddle here */ + + spin_lock_irq(&sk->sk_receive_queue.lock); if ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) amount = skb->len; + spin_unlock_irq(&sk->sk_receive_queue.lock); return put_user(amount, (unsigned int __user *) argp); } diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index 981ca5b98bcb9..1d95f8bc769fa 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -73,6 +73,7 @@ static void rxrpc_destroy_client_conn_ids(struct rxrpc_local *local) static struct rxrpc_bundle *rxrpc_alloc_bundle(struct rxrpc_call *call, gfp_t gfp) { + static atomic_t rxrpc_bundle_id; struct rxrpc_bundle *bundle; bundle = kzalloc(sizeof(*bundle), gfp); @@ -85,6 +86,7 @@ static struct rxrpc_bundle *rxrpc_alloc_bundle(struct rxrpc_call *call, bundle->upgrade = test_bit(RXRPC_CALL_UPGRADE, &call->flags); bundle->service_id = call->dest_srx.srx_service; bundle->security_level = call->security_level; + bundle->debug_id = atomic_inc_return(&rxrpc_bundle_id); refcount_set(&bundle->ref, 1); atomic_set(&bundle->active, 1); INIT_LIST_HEAD(&bundle->waiting_calls); @@ -105,7 +107,8 @@ struct rxrpc_bundle *rxrpc_get_bundle(struct rxrpc_bundle *bundle, static void rxrpc_free_bundle(struct rxrpc_bundle *bundle) { - trace_rxrpc_bundle(bundle->debug_id, 1, rxrpc_bundle_free); + trace_rxrpc_bundle(bundle->debug_id, refcount_read(&bundle->ref), + rxrpc_bundle_free); rxrpc_put_peer(bundle->peer, rxrpc_peer_put_bundle); key_put(bundle->key); kfree(bundle); @@ -239,7 +242,6 @@ static bool rxrpc_may_reuse_conn(struct rxrpc_connection *conn) */ int rxrpc_look_up_bundle(struct rxrpc_call *call, gfp_t gfp) { - static atomic_t rxrpc_bundle_id; struct rxrpc_bundle *bundle, *candidate; struct rxrpc_local *local = call->local; struct rb_node *p, **pp, *parent; @@ -306,7 +308,6 @@ int rxrpc_look_up_bundle(struct rxrpc_call *call, gfp_t gfp) } _debug("new bundle"); - candidate->debug_id = atomic_inc_return(&rxrpc_bundle_id); rb_link_node(&candidate->local_node, parent, pp); rb_insert_color(&candidate->local_node, &local->client_bundles); call->bundle = rxrpc_get_bundle(candidate, rxrpc_bundle_get_client_call); diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 030d64f282f37..92495e73b8699 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -643,12 +643,8 @@ static void rxrpc_complete_rtt_probe(struct rxrpc_call *call, clear_bit(i + RXRPC_CALL_RTT_PEND_SHIFT, &call->rtt_avail); smp_mb(); /* Read data before setting avail bit */ set_bit(i, &call->rtt_avail); - if (type != rxrpc_rtt_rx_cancel) - rxrpc_peer_add_rtt(call, type, i, acked_serial, ack_serial, - sent_at, resp_time); - else - trace_rxrpc_rtt_rx(call, rxrpc_rtt_rx_cancel, i, - orig_serial, acked_serial, 0, 0); + rxrpc_peer_add_rtt(call, type, i, acked_serial, ack_serial, + sent_at, resp_time); matched = true; } @@ -801,28 +797,21 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) summary.ack_reason, nr_acks); rxrpc_inc_stat(call->rxnet, stat_rx_acks[ack.reason]); - switch (ack.reason) { - case RXRPC_ACK_PING_RESPONSE: - rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial, - rxrpc_rtt_rx_ping_response); - break; - case RXRPC_ACK_REQUESTED: - rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial, - rxrpc_rtt_rx_requested_ack); - break; - default: - if (acked_serial != 0) + if (acked_serial != 0) { + switch (ack.reason) { + case RXRPC_ACK_PING_RESPONSE: rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial, - rxrpc_rtt_rx_cancel); - break; - } - - if (ack.reason == RXRPC_ACK_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_send_ACK(call, RXRPC_ACK_REQUESTED, ack_serial, - rxrpc_propose_ack_respond_to_ack); + rxrpc_rtt_rx_ping_response); + break; + case RXRPC_ACK_REQUESTED: + rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial, + rxrpc_rtt_rx_requested_ack); + break; + default: + rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial, + rxrpc_rtt_rx_other_ack); + break; + } } /* If we get an EXCEEDS_WINDOW ACK from the server, it probably @@ -835,7 +824,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) rxrpc_is_client_call(call)) { rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED, 0, -ENETRESET); - return; + goto send_response; } /* If we get an OUT_OF_SEQUENCE ACK from the server, that can also @@ -849,7 +838,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) rxrpc_is_client_call(call)) { rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED, 0, -ENETRESET); - return; + goto send_response; } /* Discard any out-of-order or duplicate ACKs (outside lock). */ @@ -857,7 +846,7 @@ 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 send_response; } info.rxMTU = 0; @@ -897,7 +886,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) case RXRPC_CALL_SERVER_AWAIT_ACK: break; default: - return; + goto send_response; } if (before(hard_ack, call->acks_hard_ack) || @@ -909,7 +898,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) if (after(hard_ack, call->acks_hard_ack)) { if (rxrpc_rotate_tx_window(call, hard_ack, &summary)) { rxrpc_end_tx_phase(call, false, rxrpc_eproto_unexpected_ack); - return; + goto send_response; } } @@ -927,6 +916,14 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) rxrpc_propose_ack_ping_for_lost_reply); rxrpc_congestion_management(call, skb, &summary, acked_serial); + +send_response: + if (ack.reason == RXRPC_ACK_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_send_ACK(call, RXRPC_ACK_REQUESTED, ack_serial, + rxrpc_propose_ack_respond_to_ack); } /* diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 3922d825ef2d8..dd710fb9f4905 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -286,9 +286,31 @@ static bool tcf_ct_flow_is_outdated(const struct flow_offload *flow) !test_bit(NF_FLOW_HW_ESTABLISHED, &flow->flags); } +static void tcf_ct_flow_table_get_ref(struct tcf_ct_flow_table *ct_ft); + +static void tcf_ct_nf_get(struct nf_flowtable *ft) +{ + struct tcf_ct_flow_table *ct_ft = + container_of(ft, struct tcf_ct_flow_table, nf_ft); + + tcf_ct_flow_table_get_ref(ct_ft); +} + +static void tcf_ct_flow_table_put(struct tcf_ct_flow_table *ct_ft); + +static void tcf_ct_nf_put(struct nf_flowtable *ft) +{ + struct tcf_ct_flow_table *ct_ft = + container_of(ft, struct tcf_ct_flow_table, nf_ft); + + tcf_ct_flow_table_put(ct_ft); +} + static struct nf_flowtable_type flowtable_ct = { .gc = tcf_ct_flow_is_outdated, .action = tcf_ct_flow_table_fill_actions, + .get = tcf_ct_nf_get, + .put = tcf_ct_nf_put, .owner = THIS_MODULE, }; @@ -337,9 +359,13 @@ static int tcf_ct_flow_table_get(struct net *net, struct tcf_ct_params *params) return err; } +static void tcf_ct_flow_table_get_ref(struct tcf_ct_flow_table *ct_ft) +{ + refcount_inc(&ct_ft->ref); +} + static void tcf_ct_flow_table_cleanup_work(struct work_struct *work) { - struct flow_block_cb *block_cb, *tmp_cb; struct tcf_ct_flow_table *ct_ft; struct flow_block *block; @@ -347,13 +373,9 @@ static void tcf_ct_flow_table_cleanup_work(struct work_struct *work) rwork); nf_flow_table_free(&ct_ft->nf_ft); - /* Remove any remaining callbacks before cleanup */ block = &ct_ft->nf_ft.flow_block; down_write(&ct_ft->nf_ft.flow_block_lock); - list_for_each_entry_safe(block_cb, tmp_cb, &block->cb_list, list) { - list_del(&block_cb->list); - flow_block_cb_free(block_cb); - } + WARN_ON(!list_empty(&block->cb_list)); up_write(&ct_ft->nf_ft.flow_block_lock); kfree(ct_ft); @@ -1535,6 +1557,9 @@ static int tcf_ct_offload_act_setup(struct tc_action *act, void *entry_data, if (bind) { struct flow_action_entry *entry = entry_data; + if (tcf_ct_helper(act)) + return -EOPNOTSUPP; + entry->id = FLOW_ACTION_CT; entry->ct.action = tcf_ct_action(act); entry->ct.zone = tcf_ct_zone(act); diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 4c047e0e1625e..ef5b5d498ef3e 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -598,8 +598,12 @@ static int smcr_clnt_conf_first_link(struct smc_sock *smc) struct smc_llc_qentry *qentry; int rc; - /* receive CONFIRM LINK request from server over RoCE fabric */ - qentry = smc_llc_wait(link->lgr, NULL, SMC_LLC_WAIT_TIME, + /* Receive CONFIRM LINK request from server over RoCE fabric. + * Increasing the client's timeout by twice as much as the server's + * timeout by default can temporarily avoid decline messages of + * both sides crossing or colliding + */ + qentry = smc_llc_wait(link->lgr, NULL, 2 * SMC_LLC_WAIT_TIME, SMC_LLC_CONFIRM_LINK); if (!qentry) { struct smc_clc_msg_decline dclc; @@ -719,7 +723,7 @@ static void smcd_conn_save_peer_info(struct smc_sock *smc, int bufsize = smc_uncompress_bufsize(clc->d0.dmbe_size); smc->conn.peer_rmbe_idx = clc->d0.dmbe_idx; - smc->conn.peer_token = clc->d0.token; + smc->conn.peer_token = ntohll(clc->d0.token); /* msg header takes up space in the buffer */ smc->conn.peer_rmbe_size = bufsize - sizeof(struct smcd_cdc_msg); atomic_set(&smc->conn.peer_rmbe_space, smc->conn.peer_rmbe_size); @@ -1411,7 +1415,7 @@ static int smc_connect_ism(struct smc_sock *smc, if (rc) return rc; } - ini->ism_peer_gid[ini->ism_selected] = aclc->d0.gid; + ini->ism_peer_gid[ini->ism_selected] = ntohll(aclc->d0.gid); /* there is only one lgr role for SMC-D; use server lock */ mutex_lock(&smc_server_lgr_pending); diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 8deb46c28f1d5..72f4d81a3f41f 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -1004,6 +1004,7 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc, { struct smc_connection *conn = &smc->conn; struct smc_clc_first_contact_ext_v2x fce; + struct smcd_dev *smcd = conn->lgr->smcd; struct smc_clc_msg_accept_confirm *clc; struct smc_clc_fce_gid_ext gle; struct smc_clc_msg_trail trl; @@ -1021,17 +1022,15 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc, memcpy(clc->hdr.eyecatcher, SMCD_EYECATCHER, sizeof(SMCD_EYECATCHER)); clc->hdr.typev1 = SMC_TYPE_D; - clc->d0.gid = - conn->lgr->smcd->ops->get_local_gid(conn->lgr->smcd); - clc->d0.token = conn->rmb_desc->token; + clc->d0.gid = htonll(smcd->ops->get_local_gid(smcd)); + clc->d0.token = htonll(conn->rmb_desc->token); clc->d0.dmbe_size = conn->rmbe_size_comp; clc->d0.dmbe_idx = 0; memcpy(&clc->d0.linkid, conn->lgr->id, SMC_LGR_ID_SIZE); if (version == SMC_V1) { clc->hdr.length = htons(SMCD_CLC_ACCEPT_CONFIRM_LEN); } else { - clc_v2->d1.chid = - htons(smc_ism_get_chid(conn->lgr->smcd)); + clc_v2->d1.chid = htons(smc_ism_get_chid(smcd)); if (eid && eid[0]) memcpy(clc_v2->d1.eid, eid, SMC_MAX_EID_LEN); len = SMCD_CLC_ACCEPT_CONFIRM_LEN_V2; diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h index c5c8e7db775a7..08155a96a02a1 100644 --- a/net/smc/smc_clc.h +++ b/net/smc/smc_clc.h @@ -204,8 +204,8 @@ struct smcr_clc_msg_accept_confirm { /* SMCR accept/confirm */ } __packed; struct smcd_clc_msg_accept_confirm_common { /* SMCD accept/confirm */ - u64 gid; /* Sender GID */ - u64 token; /* DMB token */ + __be64 gid; /* Sender GID */ + __be64 token; /* DMB token */ u8 dmbe_idx; /* DMBE index */ #if defined(__BIG_ENDIAN_BITFIELD) u8 dmbe_size : 4, /* buf size (compressed) */ diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index 814b0169f9723..ec41b26af76e2 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -40,9 +40,6 @@ static unsigned long number_cred_unused; static struct cred machine_cred = { .usage = ATOMIC_INIT(1), -#ifdef CONFIG_DEBUG_CREDENTIALS - .magic = CRED_MAGIC, -#endif }; /* diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 9c210273d06b7..339dfc5b92246 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -111,7 +111,8 @@ static void rpc_clnt_remove_pipedir(struct rpc_clnt *clnt) pipefs_sb = rpc_get_sb_net(net); if (pipefs_sb) { - __rpc_clnt_remove_pipedir(clnt); + if (pipefs_sb == clnt->pipefs_sb) + __rpc_clnt_remove_pipedir(clnt); rpc_put_sb_net(net); } } @@ -151,6 +152,8 @@ rpc_setup_pipedir(struct super_block *pipefs_sb, struct rpc_clnt *clnt) { struct dentry *dentry; + clnt->pipefs_sb = pipefs_sb; + if (clnt->cl_program->pipe_dir_name != NULL) { dentry = rpc_setup_pipedir_sb(pipefs_sb, clnt); if (IS_ERR(dentry)) @@ -2171,6 +2174,7 @@ call_connect_status(struct rpc_task *task) task->tk_status = 0; switch (status) { case -ECONNREFUSED: + case -ECONNRESET: /* A positive refusal suggests a rebind is needed. */ if (RPC_IS_SOFTCONN(task)) break; @@ -2179,7 +2183,6 @@ call_connect_status(struct rpc_task *task) goto out_retry; } fallthrough; - case -ECONNRESET: case -ECONNABORTED: case -ENETDOWN: case -ENETUNREACH: diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index 5988a5c5ff3f0..102c3818bc54d 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -769,6 +769,10 @@ void rpcb_getport_async(struct rpc_task *task) child = rpcb_call_async(rpcb_clnt, map, proc); rpc_release_client(rpcb_clnt); + if (IS_ERR(child)) { + /* rpcb_map_release() has freed the arguments */ + return; + } xprt->stat.bind_count++; rpc_put_task(child); diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 4cfe9640df481..5cfe5c7408b74 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -666,9 +666,8 @@ static bool svc_alloc_arg(struct svc_rqst *rqstp) } for (filled = 0; filled < pages; filled = ret) { - ret = alloc_pages_bulk_array_node(GFP_KERNEL, - rqstp->rq_pool->sp_id, - pages, rqstp->rq_pages); + ret = alloc_pages_bulk_array(GFP_KERNEL, pages, + rqstp->rq_pages); if (ret > filled) /* Made progress, don't sleep yet */ continue; diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index 85c8bcaebb80f..3b05f90a3e50d 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -852,7 +852,8 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) if (ret == -EINVAL) svc_rdma_send_error(rdma_xprt, ctxt, ret); svc_rdma_recv_ctxt_put(rdma_xprt, ctxt); - return ret; + svc_xprt_deferred_close(xprt); + return -ENOTCONN; out_backchannel: svc_rdma_handle_bc_reply(rqstp, ctxt); diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index 5bc076f2fa74a..c763008a8adba 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -102,6 +102,7 @@ static int tipc_add_tlv(struct sk_buff *skb, u16 type, void *data, u16 len) return -EMSGSIZE; skb_put(skb, TLV_SPACE(len)); + memset(tlv, 0, TLV_SPACE(len)); tlv->tlv_type = htons(type); tlv->tlv_len = htons(TLV_LENGTH(len)); if (len && data) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 9634dfd636fd6..27cc0f0a90e1f 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -952,6 +952,8 @@ static int tls_sw_sendmsg_splice(struct sock *sk, struct msghdr *msg, } sk_msg_page_add(msg_pl, page, part, off); + msg_pl->sg.copybreak = 0; + msg_pl->sg.curr = msg_pl->sg.end; sk_mem_charge(sk, part); *copied += part; try_to_copy -= part; @@ -1232,11 +1234,14 @@ void tls_sw_splice_eof(struct socket *sock) lock_sock(sk); retry: + /* same checks as in tls_sw_push_pending_record() */ rec = ctx->open_rec; if (!rec) goto unlock; msg_pl = &rec->msg_plaintext; + if (msg_pl->sg.size == 0) + goto unlock; /* Check the BPF advisor and perform transmission. */ ret = bpf_exec_tx_verdict(msg_pl, sk, false, TLS_RECORD_TYPE_DATA, diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 3e8a04a136688..1e1a88bd4e688 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -212,8 +212,6 @@ static inline bool unix_secdata_eq(struct scm_cookie *scm, struct sk_buff *skb) } #endif /* CONFIG_SECURITY_NETWORK */ -#define unix_peer(sk) (unix_sk(sk)->peer) - static inline int unix_our_peer(struct sock *sk, struct sock *osk) { return unix_peer(osk) == sk; @@ -2553,15 +2551,16 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state) if (!(state->flags & MSG_PEEK)) WRITE_ONCE(u->oob_skb, NULL); - + else + skb_get(oob_skb); unix_state_unlock(sk); chunk = state->recv_actor(oob_skb, 0, chunk, state); - if (!(state->flags & MSG_PEEK)) { + if (!(state->flags & MSG_PEEK)) UNIXCB(oob_skb).consumed += 1; - kfree_skb(oob_skb); - } + + consume_skb(oob_skb); mutex_unlock(&u->iolock); diff --git a/net/unix/unix_bpf.c b/net/unix/unix_bpf.c index 2f9d8271c6ec7..7ea7c3a0d0d06 100644 --- a/net/unix/unix_bpf.c +++ b/net/unix/unix_bpf.c @@ -159,12 +159,17 @@ int unix_dgram_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool re int unix_stream_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore) { + struct sock *sk_pair; + if (restore) { sk->sk_write_space = psock->saved_write_space; sock_replace_proto(sk, psock->sk_proto); return 0; } + sk_pair = unix_peer(sk); + sock_hold(sk_pair); + psock->sk_pair = sk_pair; unix_stream_bpf_check_needs_rebuild(psock->sk_proto); sock_replace_proto(sk, &unix_stream_bpf_prot); return 0; diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 020cf17ab7e47..ccd8cefeea7ba 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -89,6 +89,7 @@ #include #include #include +#include #include #include #include @@ -110,6 +111,7 @@ #include #include #include +#include static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr); static void vsock_sk_destruct(struct sock *sk); @@ -2134,6 +2136,10 @@ vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int err; sk = sock->sk; + + if (unlikely(flags & MSG_ERRQUEUE)) + return sock_recv_errqueue(sk, msg, len, SOL_VSOCK, VSOCK_RECVERR); + vsk = vsock_sk(sk); err = 0; diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 8bc272b6003bb..4084578b0b911 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -679,7 +679,7 @@ static s64 virtio_transport_has_space(struct vsock_sock *vsk) struct virtio_vsock_sock *vvs = vsk->trans; s64 bytes; - bytes = vvs->peer_buf_alloc - (vvs->tx_cnt - vvs->peer_fwd_cnt); + bytes = (s64)vvs->peer_buf_alloc - (vvs->tx_cnt - vvs->peer_fwd_cnt); if (bytes < 0) bytes = 0; diff --git a/net/wireless/certs/wens.hex b/net/wireless/certs/wens.hex new file mode 100644 index 0000000000000..0d50369bede98 --- /dev/null +++ b/net/wireless/certs/wens.hex @@ -0,0 +1,87 @@ +/* Chen-Yu Tsai's regdb certificate */ +0x30, 0x82, 0x02, 0xa7, 0x30, 0x82, 0x01, 0x8f, +0x02, 0x14, 0x61, 0xc0, 0x38, 0x65, 0x1a, 0xab, +0xdc, 0xf9, 0x4b, 0xd0, 0xac, 0x7f, 0xf0, 0x6c, +0x72, 0x48, 0xdb, 0x18, 0xc6, 0x00, 0x30, 0x0d, +0x06, 0x09, 0x2a, 0x86, 0x48, 0x86, 0xf7, 0x0d, +0x01, 0x01, 0x0b, 0x05, 0x00, 0x30, 0x0f, 0x31, +0x0d, 0x30, 0x0b, 0x06, 0x03, 0x55, 0x04, 0x03, +0x0c, 0x04, 0x77, 0x65, 0x6e, 0x73, 0x30, 0x20, +0x17, 0x0d, 0x32, 0x33, 0x31, 0x32, 0x30, 0x31, +0x30, 0x37, 0x34, 0x31, 0x31, 0x34, 0x5a, 0x18, +0x0f, 0x32, 0x31, 0x32, 0x33, 0x31, 0x31, 0x30, +0x37, 0x30, 0x37, 0x34, 0x31, 0x31, 0x34, 0x5a, +0x30, 0x0f, 0x31, 0x0d, 0x30, 0x0b, 0x06, 0x03, +0x55, 0x04, 0x03, 0x0c, 0x04, 0x77, 0x65, 0x6e, +0x73, 0x30, 0x82, 0x01, 0x22, 0x30, 0x0d, 0x06, +0x09, 0x2a, 0x86, 0x48, 0x86, 0xf7, 0x0d, 0x01, +0x01, 0x01, 0x05, 0x00, 0x03, 0x82, 0x01, 0x0f, +0x00, 0x30, 0x82, 0x01, 0x0a, 0x02, 0x82, 0x01, +0x01, 0x00, 0xa9, 0x7a, 0x2c, 0x78, 0x4d, 0xa7, +0x19, 0x2d, 0x32, 0x52, 0xa0, 0x2e, 0x6c, 0xef, +0x88, 0x7f, 0x15, 0xc5, 0xb6, 0x69, 0x54, 0x16, +0x43, 0x14, 0x79, 0x53, 0xb7, 0xae, 0x88, 0xfe, +0xc0, 0xb7, 0x5d, 0x47, 0x8e, 0x1a, 0xe1, 0xef, +0xb3, 0x90, 0x86, 0xda, 0xd3, 0x64, 0x81, 0x1f, +0xce, 0x5d, 0x9e, 0x4b, 0x6e, 0x58, 0x02, 0x3e, +0xb2, 0x6f, 0x5e, 0x42, 0x47, 0x41, 0xf4, 0x2c, +0xb8, 0xa8, 0xd4, 0xaa, 0xc0, 0x0e, 0xe6, 0x48, +0xf0, 0xa8, 0xce, 0xcb, 0x08, 0xae, 0x37, 0xaf, +0xf6, 0x40, 0x39, 0xcb, 0x55, 0x6f, 0x5b, 0x4f, +0x85, 0x34, 0xe6, 0x69, 0x10, 0x50, 0x72, 0x5e, +0x4e, 0x9d, 0x4c, 0xba, 0x38, 0x36, 0x0d, 0xce, +0x73, 0x38, 0xd7, 0x27, 0x02, 0x2a, 0x79, 0x03, +0xe1, 0xac, 0xcf, 0xb0, 0x27, 0x85, 0x86, 0x93, +0x17, 0xab, 0xec, 0x42, 0x77, 0x37, 0x65, 0x8a, +0x44, 0xcb, 0xd6, 0x42, 0x93, 0x92, 0x13, 0xe3, +0x39, 0x45, 0xc5, 0x6e, 0x00, 0x4a, 0x7f, 0xcb, +0x42, 0x17, 0x2b, 0x25, 0x8c, 0xb8, 0x17, 0x3b, +0x15, 0x36, 0x59, 0xde, 0x42, 0xce, 0x21, 0xe6, +0xb6, 0xc7, 0x6e, 0x5e, 0x26, 0x1f, 0xf7, 0x8a, +0x57, 0x9e, 0xa5, 0x96, 0x72, 0xb7, 0x02, 0x32, +0xeb, 0x07, 0x2b, 0x73, 0xe2, 0x4f, 0x66, 0x58, +0x9a, 0xeb, 0x0f, 0x07, 0xb6, 0xab, 0x50, 0x8b, +0xc3, 0x8f, 0x17, 0xfa, 0x0a, 0x99, 0xc2, 0x16, +0x25, 0xbf, 0x2d, 0x6b, 0x1a, 0xaa, 0xe6, 0x3e, +0x5f, 0xeb, 0x6d, 0x9b, 0x5d, 0x4d, 0x42, 0x83, +0x2d, 0x39, 0xb8, 0xc9, 0xac, 0xdb, 0x3a, 0x91, +0x50, 0xdf, 0xbb, 0xb1, 0x76, 0x6d, 0x15, 0x73, +0xfd, 0xc6, 0xe6, 0x6b, 0x71, 0x9e, 0x67, 0x36, +0x22, 0x83, 0x79, 0xb1, 0xd6, 0xb8, 0x84, 0x52, +0xaf, 0x96, 0x5b, 0xc3, 0x63, 0x02, 0x4e, 0x78, +0x70, 0x57, 0x02, 0x03, 0x01, 0x00, 0x01, 0x30, +0x0d, 0x06, 0x09, 0x2a, 0x86, 0x48, 0x86, 0xf7, +0x0d, 0x01, 0x01, 0x0b, 0x05, 0x00, 0x03, 0x82, +0x01, 0x01, 0x00, 0x24, 0x28, 0xee, 0x22, 0x74, +0x7f, 0x7c, 0xfa, 0x6c, 0x1f, 0xb3, 0x18, 0xd1, +0xc2, 0x3d, 0x7d, 0x29, 0x42, 0x88, 0xad, 0x82, +0xa5, 0xb1, 0x8a, 0x05, 0xd0, 0xec, 0x5c, 0x91, +0x20, 0xf6, 0x82, 0xfd, 0xd5, 0x67, 0x60, 0x5f, +0x31, 0xf5, 0xbd, 0x88, 0x91, 0x70, 0xbd, 0xb8, +0xb9, 0x8c, 0x88, 0xfe, 0x53, 0xc9, 0x54, 0x9b, +0x43, 0xc4, 0x7a, 0x43, 0x74, 0x6b, 0xdd, 0xb0, +0xb1, 0x3b, 0x33, 0x45, 0x46, 0x78, 0xa3, 0x1c, +0xef, 0x54, 0x68, 0xf7, 0x85, 0x9c, 0xe4, 0x51, +0x6f, 0x06, 0xaf, 0x81, 0xdb, 0x2a, 0x7b, 0x7b, +0x6f, 0xa8, 0x9c, 0x67, 0xd8, 0xcb, 0xc9, 0x91, +0x40, 0x00, 0xae, 0xd9, 0xa1, 0x9f, 0xdd, 0xa6, +0x43, 0x0e, 0x28, 0x7b, 0xaa, 0x1b, 0xe9, 0x84, +0xdb, 0x76, 0x64, 0x42, 0x70, 0xc9, 0xc0, 0xeb, +0xae, 0x84, 0x11, 0x16, 0x68, 0x4e, 0x84, 0x9e, +0x7e, 0x92, 0x36, 0xee, 0x1c, 0x3b, 0x08, 0x63, +0xeb, 0x79, 0x84, 0x15, 0x08, 0x9d, 0xaf, 0xc8, +0x9a, 0xc7, 0x34, 0xd3, 0x94, 0x4b, 0xd1, 0x28, +0x97, 0xbe, 0xd1, 0x45, 0x75, 0xdc, 0x35, 0x62, +0xac, 0x1d, 0x1f, 0xb7, 0xb7, 0x15, 0x87, 0xc8, +0x98, 0xc0, 0x24, 0x31, 0x56, 0x8d, 0xed, 0xdb, +0x06, 0xc6, 0x46, 0xbf, 0x4b, 0x6d, 0xa6, 0xd5, +0xab, 0xcc, 0x60, 0xfc, 0xe5, 0x37, 0xb6, 0x53, +0x7d, 0x58, 0x95, 0xa9, 0x56, 0xc7, 0xf7, 0xee, +0xc3, 0xa0, 0x76, 0xf7, 0x65, 0x4d, 0x53, 0xfa, +0xff, 0x5f, 0x76, 0x33, 0x5a, 0x08, 0xfa, 0x86, +0x92, 0x5a, 0x13, 0xfa, 0x1a, 0xfc, 0xf2, 0x1b, +0x8c, 0x7f, 0x42, 0x6d, 0xb7, 0x7e, 0xb7, 0xb4, +0xf0, 0xc7, 0x83, 0xbb, 0xa2, 0x81, 0x03, 0x2d, +0xd4, 0x2a, 0x63, 0x3f, 0xf7, 0x31, 0x2e, 0x40, +0x33, 0x5c, 0x46, 0xbc, 0x9b, 0xc1, 0x05, 0xa5, +0x45, 0x4e, 0xc3, diff --git a/net/wireless/core.h b/net/wireless/core.h index e536c0b615a09..f0a3a23176385 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -299,6 +299,7 @@ struct cfg80211_cqm_config { u32 rssi_hyst; s32 last_rssi_event_value; enum nl80211_cqm_rssi_threshold_event last_rssi_event_type; + bool use_range_api; int n_rssi_thresholds; s32 rssi_thresholds[] __counted_by(n_rssi_thresholds); }; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 931a03f4549c9..0b0dfecedc50a 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -12824,10 +12824,6 @@ static int cfg80211_cqm_rssi_update(struct cfg80211_registered_device *rdev, int i, n, low_index; int err; - /* RSSI reporting disabled? */ - if (!cqm_config) - return rdev_set_cqm_rssi_range_config(rdev, dev, 0, 0); - /* * Obtain current RSSI value if possible, if not and no RSSI threshold * event has been received yet, we should receive an event after a @@ -12902,18 +12898,6 @@ static int nl80211_set_cqm_rssi(struct genl_info *info, wdev->iftype != NL80211_IFTYPE_P2P_CLIENT) return -EOPNOTSUPP; - if (n_thresholds <= 1 && rdev->ops->set_cqm_rssi_config) { - if (n_thresholds == 0 || thresholds[0] == 0) /* Disabling */ - return rdev_set_cqm_rssi_config(rdev, dev, 0, 0); - - return rdev_set_cqm_rssi_config(rdev, dev, - thresholds[0], hysteresis); - } - - if (!wiphy_ext_feature_isset(&rdev->wiphy, - NL80211_EXT_FEATURE_CQM_RSSI_LIST)) - return -EOPNOTSUPP; - if (n_thresholds == 1 && thresholds[0] == 0) /* Disabling */ n_thresholds = 0; @@ -12921,6 +12905,26 @@ static int nl80211_set_cqm_rssi(struct genl_info *info, old = rcu_dereference_protected(wdev->cqm_config, lockdep_is_held(&wdev->mtx)); + /* if already disabled just succeed */ + if (!n_thresholds && !old) { + err = 0; + goto unlock; + } + + if (n_thresholds > 1) { + if (!wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_CQM_RSSI_LIST) || + !rdev->ops->set_cqm_rssi_range_config) { + err = -EOPNOTSUPP; + goto unlock; + } + } else { + if (!rdev->ops->set_cqm_rssi_config) { + err = -EOPNOTSUPP; + goto unlock; + } + } + if (n_thresholds) { cqm_config = kzalloc(struct_size(cqm_config, rssi_thresholds, n_thresholds), @@ -12935,13 +12939,26 @@ static int nl80211_set_cqm_rssi(struct genl_info *info, memcpy(cqm_config->rssi_thresholds, thresholds, flex_array_size(cqm_config, rssi_thresholds, n_thresholds)); + cqm_config->use_range_api = n_thresholds > 1 || + !rdev->ops->set_cqm_rssi_config; rcu_assign_pointer(wdev->cqm_config, cqm_config); + + if (cqm_config->use_range_api) + err = cfg80211_cqm_rssi_update(rdev, dev, cqm_config); + else + err = rdev_set_cqm_rssi_config(rdev, dev, + thresholds[0], + hysteresis); } else { RCU_INIT_POINTER(wdev->cqm_config, NULL); + /* if enabled as range also disable via range */ + if (old->use_range_api) + err = rdev_set_cqm_rssi_range_config(rdev, dev, 0, 0); + else + err = rdev_set_cqm_rssi_config(rdev, dev, 0, 0); } - err = cfg80211_cqm_rssi_update(rdev, dev, cqm_config); if (err) { rcu_assign_pointer(wdev->cqm_config, old); kfree_rcu(cqm_config, rcu_head); @@ -19131,10 +19148,11 @@ void cfg80211_cqm_rssi_notify_work(struct wiphy *wiphy, struct wiphy_work *work) wdev_lock(wdev); cqm_config = rcu_dereference_protected(wdev->cqm_config, lockdep_is_held(&wdev->mtx)); - if (!wdev->cqm_config) + if (!cqm_config) goto unlock; - cfg80211_cqm_rssi_update(rdev, wdev->netdev, cqm_config); + if (cqm_config->use_range_api) + cfg80211_cqm_rssi_update(rdev, wdev->netdev, cqm_config); rssi_level = cqm_config->last_rssi_event_value; rssi_event = cqm_config->last_rssi_event_type; diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 55f8b9b0e06d1..3515e19852d88 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -919,7 +919,7 @@ static __poll_t xsk_poll(struct file *file, struct socket *sock, rcu_read_lock(); if (xsk_check_common(xs)) - goto skip_tx; + goto out; pool = xs->pool; @@ -931,12 +931,11 @@ static __poll_t xsk_poll(struct file *file, struct socket *sock, xsk_generic_xmit(sk); } -skip_tx: if (xs->rx && !xskq_prod_is_empty(xs->rx)) mask |= EPOLLIN | EPOLLRDNORM; if (xs->tx && xsk_tx_writeable(xs)) mask |= EPOLLOUT | EPOLLWRNORM; - +out: rcu_read_unlock(); return mask; } diff --git a/samples/bpf/syscall_tp_user.c b/samples/bpf/syscall_tp_user.c index 7a788bb837fc1..7a09ac74fac07 100644 --- a/samples/bpf/syscall_tp_user.c +++ b/samples/bpf/syscall_tp_user.c @@ -17,9 +17,9 @@ static void usage(const char *cmd) { - printf("USAGE: %s [-i num_progs] [-h]\n", cmd); - printf(" -i num_progs # number of progs of the test\n"); - printf(" -h # help\n"); + printf("USAGE: %s [-i nr_tests] [-h]\n", cmd); + printf(" -i nr_tests # rounds of test to run\n"); + printf(" -h # help\n"); } static void verify_map(int map_id) @@ -45,14 +45,14 @@ static void verify_map(int map_id) } } -static int test(char *filename, int num_progs) +static int test(char *filename, int nr_tests) { - int map0_fds[num_progs], map1_fds[num_progs], fd, i, j = 0; - struct bpf_link *links[num_progs * 4]; - struct bpf_object *objs[num_progs]; + int map0_fds[nr_tests], map1_fds[nr_tests], fd, i, j = 0; + struct bpf_link **links = NULL; + struct bpf_object *objs[nr_tests]; struct bpf_program *prog; - for (i = 0; i < num_progs; i++) { + for (i = 0; i < nr_tests; i++) { objs[i] = bpf_object__open_file(filename, NULL); if (libbpf_get_error(objs[i])) { fprintf(stderr, "opening BPF object file failed\n"); @@ -60,6 +60,19 @@ static int test(char *filename, int num_progs) goto cleanup; } + /* One-time initialization */ + if (!links) { + int nr_progs = 0; + + bpf_object__for_each_program(prog, objs[i]) + nr_progs += 1; + + links = calloc(nr_progs * nr_tests, sizeof(struct bpf_link *)); + + if (!links) + goto cleanup; + } + /* load BPF program */ if (bpf_object__load(objs[i])) { fprintf(stderr, "loading BPF object file failed\n"); @@ -101,14 +114,18 @@ static int test(char *filename, int num_progs) close(fd); /* verify the map */ - for (i = 0; i < num_progs; i++) { + for (i = 0; i < nr_tests; i++) { verify_map(map0_fds[i]); verify_map(map1_fds[i]); } cleanup: - for (j--; j >= 0; j--) - bpf_link__destroy(links[j]); + if (links) { + for (j--; j >= 0; j--) + bpf_link__destroy(links[j]); + + free(links); + } for (i--; i >= 0; i--) bpf_object__close(objs[i]); @@ -117,13 +134,13 @@ static int test(char *filename, int num_progs) int main(int argc, char **argv) { - int opt, num_progs = 1; + int opt, nr_tests = 1; char filename[256]; while ((opt = getopt(argc, argv, "i:h")) != -1) { switch (opt) { case 'i': - num_progs = atoi(optarg); + nr_tests = atoi(optarg); break; case 'h': default: @@ -134,5 +151,5 @@ int main(int argc, char **argv) snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); - return test(filename, num_progs); + return test(filename, nr_tests); } diff --git a/scripts/Makefile.vmlinux b/scripts/Makefile.vmlinux index 3cd6ca15f390d..c9f3e03124d7f 100644 --- a/scripts/Makefile.vmlinux +++ b/scripts/Makefile.vmlinux @@ -19,6 +19,7 @@ quiet_cmd_cc_o_c = CC $@ ifdef CONFIG_MODULES KASAN_SANITIZE_.vmlinux.export.o := n +KCSAN_SANITIZE_.vmlinux.export.o := n GCOV_PROFILE_.vmlinux.export.o := n targets += .vmlinux.export.o vmlinux: .vmlinux.export.o diff --git a/scripts/checkstack.pl b/scripts/checkstack.pl index 84f5fb7f1cecc..f27d552aec43f 100755 --- a/scripts/checkstack.pl +++ b/scripts/checkstack.pl @@ -97,8 +97,7 @@ # 11160: a7 fb ff 60 aghi %r15,-160 # or # 100092: e3 f0 ff c8 ff 71 lay %r15,-56(%r15) - $re = qr/.*(?:lay|ag?hi).*\%r15,-(([0-9]{2}|[3-9])[0-9]{2}) - (?:\(\%r15\))?$/ox; + $re = qr/.*(?:lay|ag?hi).*\%r15,-([0-9]+)(?:\(\%r15\))?$/o; } elsif ($arch eq 'sparc' || $arch eq 'sparc64') { # f0019d10: 9d e3 bf 90 save %sp, -112, %sp $re = qr/.*save.*%sp, -(([0-9]{2}|[3-9])[0-9]{2}), %sp/o; @@ -139,15 +138,11 @@ sub arm_push_handling { while (my $line = ) { if ($line =~ m/$funcre/) { $func = $1; - next if $line !~ m/^($xs*)/; + next if $line !~ m/^($x*)/; if ($total_size > $min_stack) { push @stack, "$intro$total_size\n"; } - - $addr = $1; - $addr =~ s/ /0/g; - $addr = "0x$addr"; - + $addr = "0x$1"; $intro = "$addr $func [$file]:"; my $padlen = 56 - length($intro); while ($padlen > 0) { diff --git a/scripts/dtc/dt-extract-compatibles b/scripts/dtc/dt-extract-compatibles index 9df9f1face832..2f9d0eb59f5b7 100755 --- a/scripts/dtc/dt-extract-compatibles +++ b/scripts/dtc/dt-extract-compatibles @@ -1,8 +1,8 @@ #!/usr/bin/env python3 # SPDX-License-Identifier: GPL-2.0-only +import fnmatch import os -import glob import re import argparse @@ -49,6 +49,24 @@ def print_compat(filename, compatibles): else: print(*compatibles, sep='\n') +def glob_without_symlinks(root, glob): + for path, dirs, files in os.walk(root): + # Ignore hidden directories + for d in dirs: + if fnmatch.fnmatch(d, ".*"): + dirs.remove(d) + for f in files: + if fnmatch.fnmatch(f, glob): + yield os.path.join(path, f) + +def files_to_parse(path_args): + for f in path_args: + if os.path.isdir(f): + for filename in glob_without_symlinks(f, "*.c"): + yield filename + else: + yield f + show_filename = False if __name__ == "__main__": @@ -59,11 +77,6 @@ if __name__ == "__main__": show_filename = args.with_filename - for f in args.cfile: - if os.path.isdir(f): - for filename in glob.iglob(f + "/**/*.c", recursive=True): - compat_list = parse_compatibles(filename) - print_compat(filename, compat_list) - else: - compat_list = parse_compatibles(f) - print_compat(f, compat_list) + for f in files_to_parse(args.cfile): + compat_list = parse_compatibles(f) + print_compat(f, compat_list) diff --git a/scripts/gcc-plugins/randomize_layout_plugin.c b/scripts/gcc-plugins/randomize_layout_plugin.c index 951b74ba1b242..746ff2d272f25 100644 --- a/scripts/gcc-plugins/randomize_layout_plugin.c +++ b/scripts/gcc-plugins/randomize_layout_plugin.c @@ -191,12 +191,14 @@ static void partition_struct(tree *fields, unsigned long length, struct partitio static void performance_shuffle(tree *newtree, unsigned long length, ranctx *prng_state) { - unsigned long i, x; + unsigned long i, x, index; struct partition_group size_group[length]; unsigned long num_groups = 0; unsigned long randnum; partition_struct(newtree, length, (struct partition_group *)&size_group, &num_groups); + + /* FIXME: this group shuffle is currently a no-op. */ for (i = num_groups - 1; i > 0; i--) { struct partition_group tmp; randnum = ranval(prng_state) % (i + 1); @@ -206,11 +208,14 @@ static void performance_shuffle(tree *newtree, unsigned long length, ranctx *prn } for (x = 0; x < num_groups; x++) { - for (i = size_group[x].start + size_group[x].length - 1; i > size_group[x].start; i--) { + for (index = size_group[x].length - 1; index > 0; index--) { tree tmp; + + i = size_group[x].start + index; if (DECL_BIT_FIELD_TYPE(newtree[i])) continue; - randnum = ranval(prng_state) % (i + 1); + randnum = ranval(prng_state) % (index + 1); + randnum += size_group[x].start; // we could handle this case differently if desired if (DECL_BIT_FIELD_TYPE(newtree[randnum])) continue; @@ -273,8 +278,6 @@ static bool is_flexible_array(const_tree field) { const_tree fieldtype; const_tree typesize; - const_tree elemtype; - const_tree elemsize; fieldtype = TREE_TYPE(field); typesize = TYPE_SIZE(fieldtype); @@ -282,20 +285,12 @@ static bool is_flexible_array(const_tree field) if (TREE_CODE(fieldtype) != ARRAY_TYPE) return false; - elemtype = TREE_TYPE(fieldtype); - elemsize = TYPE_SIZE(elemtype); - /* size of type is represented in bits */ if (typesize == NULL_TREE && TYPE_DOMAIN(fieldtype) != NULL_TREE && TYPE_MAX_VALUE(TYPE_DOMAIN(fieldtype)) == NULL_TREE) return true; - if (typesize != NULL_TREE && - (TREE_CONSTANT(typesize) && (!tree_to_uhwi(typesize) || - tree_to_uhwi(typesize) == tree_to_uhwi(elemsize)))) - return true; - return false; } @@ -344,8 +339,7 @@ static int relayout_struct(tree type) /* * enforce that we don't randomize the layout of the last - * element of a struct if it's a 0 or 1-length array - * or a proper flexible array + * element of a struct if it's a proper flexible array */ if (is_flexible_array(newtree[num_fields - 1])) { has_flexarray = true; diff --git a/scripts/gdb/linux/constants.py.in b/scripts/gdb/linux/constants.py.in index 04c87b570aabe..e810e0c27ff18 100644 --- a/scripts/gdb/linux/constants.py.in +++ b/scripts/gdb/linux/constants.py.in @@ -158,3 +158,4 @@ LX_CONFIG(CONFIG_STACKDEPOT) LX_CONFIG(CONFIG_PAGE_OWNER) LX_CONFIG(CONFIG_SLUB_DEBUG) LX_CONFIG(CONFIG_SLAB_FREELIST_HARDENED) +LX_CONFIG(CONFIG_MMU) diff --git a/scripts/gdb/linux/device.py b/scripts/gdb/linux/device.py index 16376c5cfec64..0eabc5f4f8ca2 100644 --- a/scripts/gdb/linux/device.py +++ b/scripts/gdb/linux/device.py @@ -36,26 +36,26 @@ def for_each_bus(): for kobj in kset_for_each_object(gdb.parse_and_eval('bus_kset')): subsys = container_of(kobj, kset_type.get_type().pointer(), 'kobj') subsys_priv = container_of(subsys, subsys_private_type.get_type().pointer(), 'subsys') - yield subsys_priv['bus'] + yield subsys_priv def for_each_class(): for kobj in kset_for_each_object(gdb.parse_and_eval('class_kset')): subsys = container_of(kobj, kset_type.get_type().pointer(), 'kobj') subsys_priv = container_of(subsys, subsys_private_type.get_type().pointer(), 'subsys') - yield subsys_priv['class'] + yield subsys_priv def get_bus_by_name(name): for item in for_each_bus(): - if item['name'].string() == name: + if item['bus']['name'].string() == name: return item raise gdb.GdbError("Can't find bus type {!r}".format(name)) def get_class_by_name(name): for item in for_each_class(): - if item['name'].string() == name: + if item['class']['name'].string() == name: return item raise gdb.GdbError("Can't find device class {!r}".format(name)) @@ -70,13 +70,13 @@ def klist_for_each(klist): def bus_for_each_device(bus): - for kn in klist_for_each(bus['p']['klist_devices']): + for kn in klist_for_each(bus['klist_devices']): dp = container_of(kn, device_private_type.get_type().pointer(), 'knode_bus') yield dp['device'] def class_for_each_device(cls): - for kn in klist_for_each(cls['p']['klist_devices']): + for kn in klist_for_each(cls['klist_devices']): dp = container_of(kn, device_private_type.get_type().pointer(), 'knode_class') yield dp['device'] @@ -103,7 +103,7 @@ def __init__(self): def invoke(self, arg, from_tty): if not arg: for bus in for_each_bus(): - gdb.write('bus {}:\t{}\n'.format(bus['name'].string(), bus)) + gdb.write('bus {}:\t{}\n'.format(bus['bus']['name'].string(), bus)) for dev in bus_for_each_device(bus): _show_device(dev, level=1) else: @@ -123,7 +123,7 @@ def __init__(self): def invoke(self, arg, from_tty): if not arg: for cls in for_each_class(): - gdb.write("class {}:\t{}\n".format(cls['name'].string(), cls)) + gdb.write("class {}:\t{}\n".format(cls['class']['name'].string(), cls)) for dev in class_for_each_device(cls): _show_device(dev, level=1) else: diff --git a/scripts/gdb/linux/vmalloc.py b/scripts/gdb/linux/vmalloc.py index 48e4a4fae7bbf..d3c8a0274d1ed 100644 --- a/scripts/gdb/linux/vmalloc.py +++ b/scripts/gdb/linux/vmalloc.py @@ -10,8 +10,9 @@ import re from linux import lists, utils, stackdepot, constants, mm -vmap_area_type = utils.CachedType('struct vmap_area') -vmap_area_ptr_type = vmap_area_type.get_type().pointer() +if constants.LX_CONFIG_MMU: + vmap_area_type = utils.CachedType('struct vmap_area') + vmap_area_ptr_type = vmap_area_type.get_type().pointer() def is_vmalloc_addr(x): pg_ops = mm.page_ops().ops @@ -25,6 +26,9 @@ def __init__(self): super(LxVmallocInfo, self).__init__("lx-vmallocinfo", gdb.COMMAND_DATA) def invoke(self, arg, from_tty): + if not constants.LX_CONFIG_MMU: + raise gdb.GdbError("Requires MMU support") + vmap_area_list = gdb.parse_and_eval('vmap_area_list') for vmap_area in lists.list_for_each_entry(vmap_area_list, vmap_area_ptr_type, "list"): if not vmap_area['vm']: diff --git a/scripts/kconfig/symbol.c b/scripts/kconfig/symbol.c index 0572330bf8a78..a76925b46ce63 100644 --- a/scripts/kconfig/symbol.c +++ b/scripts/kconfig/symbol.c @@ -122,9 +122,9 @@ static long long sym_get_range_val(struct symbol *sym, int base) static void sym_validate_range(struct symbol *sym) { struct property *prop; + struct symbol *range_sym; int base; long long val, val2; - char str[64]; switch (sym->type) { case S_INT: @@ -140,17 +140,15 @@ static void sym_validate_range(struct symbol *sym) if (!prop) return; val = strtoll(sym->curr.val, NULL, base); - val2 = sym_get_range_val(prop->expr->left.sym, base); + range_sym = prop->expr->left.sym; + val2 = sym_get_range_val(range_sym, base); if (val >= val2) { - val2 = sym_get_range_val(prop->expr->right.sym, base); + range_sym = prop->expr->right.sym; + val2 = sym_get_range_val(range_sym, base); if (val <= val2) return; } - if (sym->type == S_INT) - sprintf(str, "%lld", val2); - else - sprintf(str, "0x%llx", val2); - sym->curr.val = xstrdup(str); + sym->curr.val = range_sym->curr.val; } static void sym_set_changed(struct symbol *sym) diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index b3dee80497cb2..ac4ef3e206bbd 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -1496,13 +1496,15 @@ static void section_rela(struct module *mod, struct elf_info *elf, return; for (rela = start; rela < stop; rela++) { + Elf_Sym *tsym; Elf_Addr taddr, r_offset; unsigned int r_type, r_sym; r_offset = TO_NATIVE(rela->r_offset); get_rel_type_and_sym(elf, rela->r_info, &r_type, &r_sym); - taddr = TO_NATIVE(rela->r_addend); + tsym = elf->symtab_start + r_sym; + taddr = tsym->st_value + TO_NATIVE(rela->r_addend); switch (elf->hdr->e_machine) { case EM_RISCV: @@ -1517,7 +1519,7 @@ static void section_rela(struct module *mod, struct elf_info *elf, break; } - check_section_mismatch(mod, elf, elf->symtab_start + r_sym, + check_section_mismatch(mod, elf, tsym, fsecndx, fromsec, r_offset, taddr); } } diff --git a/scripts/sign-file.c b/scripts/sign-file.c index 598ef5465f825..3edb156ae52c3 100644 --- a/scripts/sign-file.c +++ b/scripts/sign-file.c @@ -322,7 +322,7 @@ int main(int argc, char **argv) CMS_NOSMIMECAP | use_keyid | use_signed_attrs), "CMS_add1_signer"); - ERR(CMS_final(cms, bm, NULL, CMS_NOCERTS | CMS_BINARY) < 0, + ERR(CMS_final(cms, bm, NULL, CMS_NOCERTS | CMS_BINARY) != 1, "CMS_final"); #else @@ -341,10 +341,10 @@ int main(int argc, char **argv) b = BIO_new_file(sig_file_name, "wb"); ERR(!b, "%s", sig_file_name); #ifndef USE_PKCS7 - ERR(i2d_CMS_bio_stream(b, cms, NULL, 0) < 0, + ERR(i2d_CMS_bio_stream(b, cms, NULL, 0) != 1, "%s", sig_file_name); #else - ERR(i2d_PKCS7_bio(b, pkcs7) < 0, + ERR(i2d_PKCS7_bio(b, pkcs7) != 1, "%s", sig_file_name); #endif BIO_free(b); @@ -374,9 +374,9 @@ int main(int argc, char **argv) if (!raw_sig) { #ifndef USE_PKCS7 - ERR(i2d_CMS_bio_stream(bd, cms, NULL, 0) < 0, "%s", dest_name); + ERR(i2d_CMS_bio_stream(bd, cms, NULL, 0) != 1, "%s", dest_name); #else - ERR(i2d_PKCS7_bio(bd, pkcs7) < 0, "%s", dest_name); + ERR(i2d_PKCS7_bio(bd, pkcs7) != 1, "%s", dest_name); #endif } else { BIO *b; @@ -396,7 +396,7 @@ int main(int argc, char **argv) ERR(BIO_write(bd, &sig_info, sizeof(sig_info)) < 0, "%s", dest_name); ERR(BIO_write(bd, magic_number, sizeof(magic_number) - 1) < 0, "%s", dest_name); - ERR(BIO_free(bd) < 0, "%s", dest_name); + ERR(BIO_free(bd) != 1, "%s", dest_name); /* Finally, if we're signing in place, replace the original. */ if (replace_orig) diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c index bd6a910f65282..261cef4c622fb 100644 --- a/security/apparmor/apparmorfs.c +++ b/security/apparmor/apparmorfs.c @@ -423,7 +423,7 @@ static ssize_t policy_update(u32 mask, const char __user *buf, size_t size, /* high level check about policy management - fine grained in * below after unpack */ - error = aa_may_manage_policy(label, ns, mask); + error = aa_may_manage_policy(current_cred(), label, ns, mask); if (error) goto end_section; @@ -486,7 +486,8 @@ static ssize_t profile_remove(struct file *f, const char __user *buf, /* high level check about policy management - fine grained in * below after unpack */ - error = aa_may_manage_policy(label, ns, AA_MAY_REMOVE_POLICY); + error = aa_may_manage_policy(current_cred(), label, ns, + AA_MAY_REMOVE_POLICY); if (error) goto out; @@ -1805,7 +1806,8 @@ static int ns_mkdir_op(struct mnt_idmap *idmap, struct inode *dir, int error; label = begin_current_label_crit_section(); - error = aa_may_manage_policy(label, NULL, AA_MAY_LOAD_POLICY); + error = aa_may_manage_policy(current_cred(), label, NULL, + AA_MAY_LOAD_POLICY); end_current_label_crit_section(label); if (error) return error; @@ -1854,7 +1856,8 @@ static int ns_rmdir_op(struct inode *dir, struct dentry *dentry) int error; label = begin_current_label_crit_section(); - error = aa_may_manage_policy(label, NULL, AA_MAY_LOAD_POLICY); + error = aa_may_manage_policy(current_cred(), label, NULL, + AA_MAY_LOAD_POLICY); end_current_label_crit_section(label); if (error) return error; diff --git a/security/apparmor/audit.c b/security/apparmor/audit.c index 5a7978aa4b19e..6933cb2f679b0 100644 --- a/security/apparmor/audit.c +++ b/security/apparmor/audit.c @@ -85,37 +85,36 @@ static const char *const aa_class_names[] = { /** * audit_pre() - core AppArmor function. * @ab: audit buffer to fill (NOT NULL) - * @ca: audit structure containing data to audit (NOT NULL) + * @va: audit structure containing data to audit (NOT NULL) * - * Record common AppArmor audit data from @sa + * Record common AppArmor audit data from @va */ -static void audit_pre(struct audit_buffer *ab, void *ca) +static void audit_pre(struct audit_buffer *ab, void *va) { - struct common_audit_data *sa = ca; + struct apparmor_audit_data *ad = aad_of_va(va); if (aa_g_audit_header) { audit_log_format(ab, "apparmor=\"%s\"", - aa_audit_type[aad(sa)->type]); + aa_audit_type[ad->type]); } - if (aad(sa)->op) { - audit_log_format(ab, " operation=\"%s\"", aad(sa)->op); - } + if (ad->op) + audit_log_format(ab, " operation=\"%s\"", ad->op); - if (aad(sa)->class) + if (ad->class) audit_log_format(ab, " class=\"%s\"", - aad(sa)->class <= AA_CLASS_LAST ? - aa_class_names[aad(sa)->class] : + ad->class <= AA_CLASS_LAST ? + aa_class_names[ad->class] : "unknown"); - if (aad(sa)->info) { - audit_log_format(ab, " info=\"%s\"", aad(sa)->info); - if (aad(sa)->error) - audit_log_format(ab, " error=%d", aad(sa)->error); + if (ad->info) { + audit_log_format(ab, " info=\"%s\"", ad->info); + if (ad->error) + audit_log_format(ab, " error=%d", ad->error); } - if (aad(sa)->label) { - struct aa_label *label = aad(sa)->label; + if (ad->subj_label) { + struct aa_label *label = ad->subj_label; if (label_isprofile(label)) { struct aa_profile *profile = labels_profile(label); @@ -134,42 +133,44 @@ static void audit_pre(struct audit_buffer *ab, void *ca) } } - if (aad(sa)->name) { + if (ad->name) { audit_log_format(ab, " name="); - audit_log_untrustedstring(ab, aad(sa)->name); + audit_log_untrustedstring(ab, ad->name); } } /** * aa_audit_msg - Log a message to the audit subsystem - * @sa: audit event structure (NOT NULL) + * @type: audit type for the message + * @ad: audit event structure (NOT NULL) * @cb: optional callback fn for type specific fields (MAYBE NULL) */ -void aa_audit_msg(int type, struct common_audit_data *sa, +void aa_audit_msg(int type, struct apparmor_audit_data *ad, void (*cb) (struct audit_buffer *, void *)) { - aad(sa)->type = type; - common_lsm_audit(sa, audit_pre, cb); + ad->type = type; + common_lsm_audit(&ad->common, audit_pre, cb); } /** * aa_audit - Log a profile based audit event to the audit subsystem * @type: audit type for the message * @profile: profile to check against (NOT NULL) - * @sa: audit event (NOT NULL) + * @ad: audit event (NOT NULL) * @cb: optional callback fn for type specific fields (MAYBE NULL) * * Handle default message switching based off of audit mode flags * * Returns: error on failure */ -int aa_audit(int type, struct aa_profile *profile, struct common_audit_data *sa, +int aa_audit(int type, struct aa_profile *profile, + struct apparmor_audit_data *ad, void (*cb) (struct audit_buffer *, void *)) { AA_BUG(!profile); if (type == AUDIT_APPARMOR_AUTO) { - if (likely(!aad(sa)->error)) { + if (likely(!ad->error)) { if (AUDIT_MODE(profile) != AUDIT_ALL) return 0; type = AUDIT_APPARMOR_AUDIT; @@ -181,24 +182,24 @@ int aa_audit(int type, struct aa_profile *profile, struct common_audit_data *sa, if (AUDIT_MODE(profile) == AUDIT_QUIET || (type == AUDIT_APPARMOR_DENIED && AUDIT_MODE(profile) == AUDIT_QUIET_DENIED)) - return aad(sa)->error; + return ad->error; if (KILL_MODE(profile) && type == AUDIT_APPARMOR_DENIED) type = AUDIT_APPARMOR_KILL; - aad(sa)->label = &profile->label; + ad->subj_label = &profile->label; - aa_audit_msg(type, sa, cb); + aa_audit_msg(type, ad, cb); - if (aad(sa)->type == AUDIT_APPARMOR_KILL) + if (ad->type == AUDIT_APPARMOR_KILL) (void)send_sig_info(SIGKILL, NULL, - sa->type == LSM_AUDIT_DATA_TASK && sa->u.tsk ? - sa->u.tsk : current); + ad->common.type == LSM_AUDIT_DATA_TASK && + ad->common.u.tsk ? ad->common.u.tsk : current); - if (aad(sa)->type == AUDIT_APPARMOR_ALLOWED) - return complain_error(aad(sa)->error); + if (ad->type == AUDIT_APPARMOR_ALLOWED) + return complain_error(ad->error); - return aad(sa)->error; + return ad->error; } struct aa_audit_rule { diff --git a/security/apparmor/capability.c b/security/apparmor/capability.c index 326a51838ef28..2fb6a2ea0b998 100644 --- a/security/apparmor/capability.c +++ b/security/apparmor/capability.c @@ -51,7 +51,7 @@ static void audit_cb(struct audit_buffer *ab, void *va) /** * audit_caps - audit a capability - * @sa: audit data + * @as: audit data * @profile: profile being tested for confinement (NOT NULL) * @cap: capability tested * @error: error code returned by test @@ -59,9 +59,9 @@ static void audit_cb(struct audit_buffer *ab, void *va) * Do auditing of capability and handle, audit/complain/kill modes switching * and duplicate message elimination. * - * Returns: 0 or sa->error on success, error code on failure + * Returns: 0 or ad->error on success, error code on failure */ -static int audit_caps(struct common_audit_data *sa, struct aa_profile *profile, +static int audit_caps(struct apparmor_audit_data *ad, struct aa_profile *profile, int cap, int error) { struct aa_ruleset *rules = list_first_entry(&profile->rules, @@ -69,7 +69,7 @@ static int audit_caps(struct common_audit_data *sa, struct aa_profile *profile, struct audit_cache *ent; int type = AUDIT_APPARMOR_AUTO; - aad(sa)->error = error; + ad->error = error; if (likely(!error)) { /* test if auditing is being forced */ @@ -101,7 +101,7 @@ static int audit_caps(struct common_audit_data *sa, struct aa_profile *profile, } put_cpu_var(audit_cache); - return aa_audit(type, profile, sa, audit_cb); + return aa_audit(type, profile, ad, audit_cb); } /** @@ -109,12 +109,12 @@ static int audit_caps(struct common_audit_data *sa, struct aa_profile *profile, * @profile: profile being enforced (NOT NULL, NOT unconfined) * @cap: capability to test if allowed * @opts: CAP_OPT_NOAUDIT bit determines whether audit record is generated - * @sa: audit data (MAY BE NULL indicating no auditing) + * @ad: audit data (MAY BE NULL indicating no auditing) * * Returns: 0 if allowed else -EPERM */ static int profile_capable(struct aa_profile *profile, int cap, - unsigned int opts, struct common_audit_data *sa) + unsigned int opts, struct apparmor_audit_data *ad) { struct aa_ruleset *rules = list_first_entry(&profile->rules, typeof(*rules), list); @@ -132,14 +132,15 @@ static int profile_capable(struct aa_profile *profile, int cap, /* audit the cap request in complain mode but note that it * should be optional. */ - aad(sa)->info = "optional: no audit"; + ad->info = "optional: no audit"; } - return audit_caps(sa, profile, cap, error); + return audit_caps(ad, profile, cap, error); } /** * aa_capable - test permission to use capability + * @subj_cread: cred we are testing capability against * @label: label being tested for capability (NOT NULL) * @cap: capability to be tested * @opts: CAP_OPT_NOAUDIT bit determines whether audit record is generated @@ -148,15 +149,17 @@ static int profile_capable(struct aa_profile *profile, int cap, * * Returns: 0 on success, or else an error code. */ -int aa_capable(struct aa_label *label, int cap, unsigned int opts) +int aa_capable(const struct cred *subj_cred, struct aa_label *label, + int cap, unsigned int opts) { struct aa_profile *profile; int error = 0; - DEFINE_AUDIT_DATA(sa, LSM_AUDIT_DATA_CAP, AA_CLASS_CAP, OP_CAPABLE); + DEFINE_AUDIT_DATA(ad, LSM_AUDIT_DATA_CAP, AA_CLASS_CAP, OP_CAPABLE); - sa.u.cap = cap; + ad.subj_cred = subj_cred; + ad.common.u.cap = cap; error = fn_for_each_confined(label, profile, - profile_capable(profile, cap, opts, &sa)); + profile_capable(profile, cap, opts, &ad)); return error; } diff --git a/security/apparmor/domain.c b/security/apparmor/domain.c index f3715cda59c52..543105cf7e334 100644 --- a/security/apparmor/domain.c +++ b/security/apparmor/domain.c @@ -31,6 +31,7 @@ /** * may_change_ptraced_domain - check if can change profile on ptraced task + * @cred: cred of task changing domain * @to_label: profile to change to (NOT NULL) * @info: message if there is an error * @@ -39,28 +40,34 @@ * * Returns: %0 or error if change not allowed */ -static int may_change_ptraced_domain(struct aa_label *to_label, +static int may_change_ptraced_domain(const struct cred *to_cred, + struct aa_label *to_label, const char **info) { struct task_struct *tracer; struct aa_label *tracerl = NULL; + const struct cred *tracer_cred = NULL; + int error = 0; rcu_read_lock(); tracer = ptrace_parent(current); - if (tracer) + if (tracer) { /* released below */ tracerl = aa_get_task_label(tracer); - + tracer_cred = get_task_cred(tracer); + } /* not ptraced */ if (!tracer || unconfined(tracerl)) goto out; - error = aa_may_ptrace(tracerl, to_label, PTRACE_MODE_ATTACH); + error = aa_may_ptrace(tracer_cred, tracerl, to_cred, to_label, + PTRACE_MODE_ATTACH); out: rcu_read_unlock(); aa_put_label(tracerl); + put_cred(tracer_cred); if (error) *info = "ptrace prevents transition"; @@ -619,7 +626,8 @@ static struct aa_label *x_to_label(struct aa_profile *profile, return new; } -static struct aa_label *profile_transition(struct aa_profile *profile, +static struct aa_label *profile_transition(const struct cred *subj_cred, + struct aa_profile *profile, const struct linux_binprm *bprm, char *buffer, struct path_cond *cond, bool *secure_exec) @@ -709,7 +717,8 @@ static struct aa_label *profile_transition(struct aa_profile *profile, } audit: - aa_audit_file(profile, &perms, OP_EXEC, MAY_EXEC, name, target, new, + aa_audit_file(subj_cred, profile, &perms, OP_EXEC, MAY_EXEC, name, + target, new, cond->uid, info, error); if (!new || nonewprivs) { aa_put_label(new); @@ -719,7 +728,8 @@ static struct aa_label *profile_transition(struct aa_profile *profile, return new; } -static int profile_onexec(struct aa_profile *profile, struct aa_label *onexec, +static int profile_onexec(const struct cred *subj_cred, + struct aa_profile *profile, struct aa_label *onexec, bool stack, const struct linux_binprm *bprm, char *buffer, struct path_cond *cond, bool *secure_exec) @@ -787,13 +797,15 @@ static int profile_onexec(struct aa_profile *profile, struct aa_label *onexec, } audit: - return aa_audit_file(profile, &perms, OP_EXEC, AA_MAY_ONEXEC, xname, + return aa_audit_file(subj_cred, profile, &perms, OP_EXEC, + AA_MAY_ONEXEC, xname, NULL, onexec, cond->uid, info, error); } /* ensure none ns domain transitions are correctly applied with onexec */ -static struct aa_label *handle_onexec(struct aa_label *label, +static struct aa_label *handle_onexec(const struct cred *subj_cred, + struct aa_label *label, struct aa_label *onexec, bool stack, const struct linux_binprm *bprm, char *buffer, struct path_cond *cond, @@ -810,26 +822,28 @@ static struct aa_label *handle_onexec(struct aa_label *label, if (!stack) { error = fn_for_each_in_ns(label, profile, - profile_onexec(profile, onexec, stack, + profile_onexec(subj_cred, profile, onexec, stack, bprm, buffer, cond, unsafe)); if (error) return ERR_PTR(error); new = fn_label_build_in_ns(label, profile, GFP_KERNEL, aa_get_newest_label(onexec), - profile_transition(profile, bprm, buffer, + profile_transition(subj_cred, profile, bprm, + buffer, cond, unsafe)); } else { /* TODO: determine how much we want to loosen this */ error = fn_for_each_in_ns(label, profile, - profile_onexec(profile, onexec, stack, bprm, + profile_onexec(subj_cred, profile, onexec, stack, bprm, buffer, cond, unsafe)); if (error) return ERR_PTR(error); new = fn_label_build_in_ns(label, profile, GFP_KERNEL, aa_label_merge(&profile->label, onexec, GFP_KERNEL), - profile_transition(profile, bprm, buffer, + profile_transition(subj_cred, profile, bprm, + buffer, cond, unsafe)); } @@ -838,7 +852,8 @@ static struct aa_label *handle_onexec(struct aa_label *label, /* TODO: get rid of GLOBAL_ROOT_UID */ error = fn_for_each_in_ns(label, profile, - aa_audit_file(profile, &nullperms, OP_CHANGE_ONEXEC, + aa_audit_file(subj_cred, profile, &nullperms, + OP_CHANGE_ONEXEC, AA_MAY_ONEXEC, bprm->filename, NULL, onexec, GLOBAL_ROOT_UID, "failed to build target label", -ENOMEM)); @@ -857,6 +872,7 @@ int apparmor_bprm_creds_for_exec(struct linux_binprm *bprm) { struct aa_task_ctx *ctx; struct aa_label *label, *new = NULL; + const struct cred *subj_cred; struct aa_profile *profile; char *buffer = NULL; const char *info = NULL; @@ -869,6 +885,7 @@ int apparmor_bprm_creds_for_exec(struct linux_binprm *bprm) file_inode(bprm->file)->i_mode }; + subj_cred = current_cred(); ctx = task_ctx(current); AA_BUG(!cred_label(bprm->cred)); AA_BUG(!ctx); @@ -895,11 +912,12 @@ int apparmor_bprm_creds_for_exec(struct linux_binprm *bprm) /* Test for onexec first as onexec override other x transitions. */ if (ctx->onexec) - new = handle_onexec(label, ctx->onexec, ctx->token, + new = handle_onexec(subj_cred, label, ctx->onexec, ctx->token, bprm, buffer, &cond, &unsafe); else new = fn_label_build(label, profile, GFP_KERNEL, - profile_transition(profile, bprm, buffer, + profile_transition(subj_cred, profile, bprm, + buffer, &cond, &unsafe)); AA_BUG(!new); @@ -934,7 +952,7 @@ int apparmor_bprm_creds_for_exec(struct linux_binprm *bprm) if (bprm->unsafe & (LSM_UNSAFE_PTRACE)) { /* TODO: test needs to be profile of label to new */ - error = may_change_ptraced_domain(new, &info); + error = may_change_ptraced_domain(bprm->cred, new, &info); if (error) goto audit; } @@ -971,7 +989,8 @@ int apparmor_bprm_creds_for_exec(struct linux_binprm *bprm) audit: error = fn_for_each(label, profile, - aa_audit_file(profile, &nullperms, OP_EXEC, MAY_EXEC, + aa_audit_file(current_cred(), profile, &nullperms, + OP_EXEC, MAY_EXEC, bprm->filename, NULL, new, vfsuid_into_kuid(vfsuid), info, error)); aa_put_label(new); @@ -987,7 +1006,8 @@ int apparmor_bprm_creds_for_exec(struct linux_binprm *bprm) * * Returns: label for hat transition OR ERR_PTR. Does NOT return NULL */ -static struct aa_label *build_change_hat(struct aa_profile *profile, +static struct aa_label *build_change_hat(const struct cred *subj_cred, + struct aa_profile *profile, const char *name, bool sibling) { struct aa_profile *root, *hat = NULL; @@ -1019,7 +1039,8 @@ static struct aa_label *build_change_hat(struct aa_profile *profile, aa_put_profile(root); audit: - aa_audit_file(profile, &nullperms, OP_CHANGE_HAT, AA_MAY_CHANGEHAT, + aa_audit_file(subj_cred, profile, &nullperms, OP_CHANGE_HAT, + AA_MAY_CHANGEHAT, name, hat ? hat->base.hname : NULL, hat ? &hat->label : NULL, GLOBAL_ROOT_UID, info, error); @@ -1035,7 +1056,8 @@ static struct aa_label *build_change_hat(struct aa_profile *profile, * * Returns: label for hat transition or ERR_PTR. Does not return NULL */ -static struct aa_label *change_hat(struct aa_label *label, const char *hats[], +static struct aa_label *change_hat(const struct cred *subj_cred, + struct aa_label *label, const char *hats[], int count, int flags) { struct aa_profile *profile, *root, *hat = NULL; @@ -1111,7 +1133,8 @@ static struct aa_label *change_hat(struct aa_label *label, const char *hats[], */ /* TODO: get rid of GLOBAL_ROOT_UID */ if (count > 1 || COMPLAIN_MODE(profile)) { - aa_audit_file(profile, &nullperms, OP_CHANGE_HAT, + aa_audit_file(subj_cred, profile, &nullperms, + OP_CHANGE_HAT, AA_MAY_CHANGEHAT, name, NULL, NULL, GLOBAL_ROOT_UID, info, error); } @@ -1120,7 +1143,8 @@ static struct aa_label *change_hat(struct aa_label *label, const char *hats[], build: new = fn_label_build_in_ns(label, profile, GFP_KERNEL, - build_change_hat(profile, name, sibling), + build_change_hat(subj_cred, profile, name, + sibling), aa_get_label(&profile->label)); if (!new) { info = "label build failed"; @@ -1150,7 +1174,7 @@ static struct aa_label *change_hat(struct aa_label *label, const char *hats[], */ int aa_change_hat(const char *hats[], int count, u64 token, int flags) { - const struct cred *cred; + const struct cred *subj_cred; struct aa_task_ctx *ctx = task_ctx(current); struct aa_label *label, *previous, *new = NULL, *target = NULL; struct aa_profile *profile; @@ -1159,8 +1183,8 @@ int aa_change_hat(const char *hats[], int count, u64 token, int flags) int error = 0; /* released below */ - cred = get_current_cred(); - label = aa_get_newest_cred_label(cred); + subj_cred = get_current_cred(); + label = aa_get_newest_cred_label(subj_cred); previous = aa_get_newest_label(ctx->previous); /* @@ -1180,7 +1204,7 @@ int aa_change_hat(const char *hats[], int count, u64 token, int flags) } if (count) { - new = change_hat(label, hats, count, flags); + new = change_hat(subj_cred, label, hats, count, flags); AA_BUG(!new); if (IS_ERR(new)) { error = PTR_ERR(new); @@ -1189,7 +1213,8 @@ int aa_change_hat(const char *hats[], int count, u64 token, int flags) goto out; } - error = may_change_ptraced_domain(new, &info); + /* target cred is the same as current except new label */ + error = may_change_ptraced_domain(subj_cred, new, &info); if (error) goto fail; @@ -1242,7 +1267,7 @@ int aa_change_hat(const char *hats[], int count, u64 token, int flags) aa_put_label(new); aa_put_label(previous); aa_put_label(label); - put_cred(cred); + put_cred(subj_cred); return error; @@ -1252,7 +1277,7 @@ int aa_change_hat(const char *hats[], int count, u64 token, int flags) fail: fn_for_each_in_ns(label, profile, - aa_audit_file(profile, &perms, OP_CHANGE_HAT, + aa_audit_file(subj_cred, profile, &perms, OP_CHANGE_HAT, AA_MAY_CHANGEHAT, NULL, NULL, target, GLOBAL_ROOT_UID, info, error)); @@ -1261,6 +1286,7 @@ int aa_change_hat(const char *hats[], int count, u64 token, int flags) static int change_profile_perms_wrapper(const char *op, const char *name, + const struct cred *subj_cred, struct aa_profile *profile, struct aa_label *target, bool stack, u32 request, struct aa_perms *perms) @@ -1275,7 +1301,8 @@ static int change_profile_perms_wrapper(const char *op, const char *name, rules->file.start[AA_CLASS_FILE], perms); if (error) - error = aa_audit_file(profile, perms, op, request, name, + error = aa_audit_file(subj_cred, profile, perms, op, request, + name, NULL, target, GLOBAL_ROOT_UID, info, error); @@ -1304,6 +1331,7 @@ int aa_change_profile(const char *fqname, int flags) const char *auditname = fqname; /* retain leading & if stack */ bool stack = flags & AA_CHANGE_STACK; struct aa_task_ctx *ctx = task_ctx(current); + const struct cred *subj_cred = get_current_cred(); int error = 0; char *op; u32 request; @@ -1381,6 +1409,7 @@ int aa_change_profile(const char *fqname, int flags) */ error = fn_for_each_in_ns(label, profile, change_profile_perms_wrapper(op, auditname, + subj_cred, profile, target, stack, request, &perms)); if (error) @@ -1391,7 +1420,7 @@ int aa_change_profile(const char *fqname, int flags) check: /* check if tracing task is allowed to trace target domain */ - error = may_change_ptraced_domain(target, &info); + error = may_change_ptraced_domain(subj_cred, target, &info); if (error && !fn_for_each_in_ns(label, profile, COMPLAIN_MODE(profile))) goto audit; @@ -1451,7 +1480,8 @@ int aa_change_profile(const char *fqname, int flags) audit: error = fn_for_each_in_ns(label, profile, - aa_audit_file(profile, &perms, op, request, auditname, + aa_audit_file(subj_cred, + profile, &perms, op, request, auditname, NULL, new ? new : target, GLOBAL_ROOT_UID, info, error)); @@ -1459,6 +1489,7 @@ int aa_change_profile(const char *fqname, int flags) aa_put_label(new); aa_put_label(target); aa_put_label(label); + put_cred(subj_cred); return error; } diff --git a/security/apparmor/file.c b/security/apparmor/file.c index 698b124e649f6..6fd21324a097f 100644 --- a/security/apparmor/file.c +++ b/security/apparmor/file.c @@ -44,38 +44,40 @@ static u32 map_mask_to_chr_mask(u32 mask) static void file_audit_cb(struct audit_buffer *ab, void *va) { struct common_audit_data *sa = va; - kuid_t fsuid = current_fsuid(); + struct apparmor_audit_data *ad = aad(sa); + kuid_t fsuid = ad->subj_cred ? ad->subj_cred->fsuid : current_fsuid(); char str[10]; - if (aad(sa)->request & AA_AUDIT_FILE_MASK) { + if (ad->request & AA_AUDIT_FILE_MASK) { aa_perm_mask_to_str(str, sizeof(str), aa_file_perm_chrs, - map_mask_to_chr_mask(aad(sa)->request)); + map_mask_to_chr_mask(ad->request)); audit_log_format(ab, " requested_mask=\"%s\"", str); } - if (aad(sa)->denied & AA_AUDIT_FILE_MASK) { + if (ad->denied & AA_AUDIT_FILE_MASK) { aa_perm_mask_to_str(str, sizeof(str), aa_file_perm_chrs, - map_mask_to_chr_mask(aad(sa)->denied)); + map_mask_to_chr_mask(ad->denied)); audit_log_format(ab, " denied_mask=\"%s\"", str); } - if (aad(sa)->request & AA_AUDIT_FILE_MASK) { + if (ad->request & AA_AUDIT_FILE_MASK) { audit_log_format(ab, " fsuid=%d", from_kuid(&init_user_ns, fsuid)); audit_log_format(ab, " ouid=%d", - from_kuid(&init_user_ns, aad(sa)->fs.ouid)); + from_kuid(&init_user_ns, ad->fs.ouid)); } - if (aad(sa)->peer) { + if (ad->peer) { audit_log_format(ab, " target="); - aa_label_xaudit(ab, labels_ns(aad(sa)->label), aad(sa)->peer, + aa_label_xaudit(ab, labels_ns(ad->subj_label), ad->peer, FLAG_VIEW_SUBNS, GFP_KERNEL); - } else if (aad(sa)->fs.target) { + } else if (ad->fs.target) { audit_log_format(ab, " target="); - audit_log_untrustedstring(ab, aad(sa)->fs.target); + audit_log_untrustedstring(ab, ad->fs.target); } } /** * aa_audit_file - handle the auditing of file operations + * @subj_cred: cred of the subject * @profile: the profile being enforced (NOT NULL) * @perms: the permissions computed for the request (NOT NULL) * @op: operation being mediated @@ -89,59 +91,74 @@ static void file_audit_cb(struct audit_buffer *ab, void *va) * * Returns: %0 or error on failure */ -int aa_audit_file(struct aa_profile *profile, struct aa_perms *perms, +int aa_audit_file(const struct cred *subj_cred, + struct aa_profile *profile, struct aa_perms *perms, const char *op, u32 request, const char *name, const char *target, struct aa_label *tlabel, kuid_t ouid, const char *info, int error) { int type = AUDIT_APPARMOR_AUTO; - DEFINE_AUDIT_DATA(sa, LSM_AUDIT_DATA_TASK, AA_CLASS_FILE, op); - - sa.u.tsk = NULL; - aad(&sa)->request = request; - aad(&sa)->name = name; - aad(&sa)->fs.target = target; - aad(&sa)->peer = tlabel; - aad(&sa)->fs.ouid = ouid; - aad(&sa)->info = info; - aad(&sa)->error = error; - sa.u.tsk = NULL; - - if (likely(!aad(&sa)->error)) { + DEFINE_AUDIT_DATA(ad, LSM_AUDIT_DATA_TASK, AA_CLASS_FILE, op); + + ad.subj_cred = subj_cred; + ad.request = request; + ad.name = name; + ad.fs.target = target; + ad.peer = tlabel; + ad.fs.ouid = ouid; + ad.info = info; + ad.error = error; + ad.common.u.tsk = NULL; + + if (likely(!ad.error)) { u32 mask = perms->audit; if (unlikely(AUDIT_MODE(profile) == AUDIT_ALL)) mask = 0xffff; /* mask off perms that are not being force audited */ - aad(&sa)->request &= mask; + ad.request &= mask; - if (likely(!aad(&sa)->request)) + if (likely(!ad.request)) return 0; type = AUDIT_APPARMOR_AUDIT; } else { /* only report permissions that were denied */ - aad(&sa)->request = aad(&sa)->request & ~perms->allow; - AA_BUG(!aad(&sa)->request); + ad.request = ad.request & ~perms->allow; + AA_BUG(!ad.request); - if (aad(&sa)->request & perms->kill) + if (ad.request & perms->kill) type = AUDIT_APPARMOR_KILL; /* quiet known rejects, assumes quiet and kill do not overlap */ - if ((aad(&sa)->request & perms->quiet) && + if ((ad.request & perms->quiet) && AUDIT_MODE(profile) != AUDIT_NOQUIET && AUDIT_MODE(profile) != AUDIT_ALL) - aad(&sa)->request &= ~perms->quiet; + ad.request &= ~perms->quiet; - if (!aad(&sa)->request) - return aad(&sa)->error; + if (!ad.request) + return ad.error; } - aad(&sa)->denied = aad(&sa)->request & ~perms->allow; - return aa_audit(type, profile, &sa, file_audit_cb); + ad.denied = ad.request & ~perms->allow; + return aa_audit(type, profile, &ad, file_audit_cb); } -static int path_name(const char *op, struct aa_label *label, +/** + * is_deleted - test if a file has been completely unlinked + * @dentry: dentry of file to test for deletion (NOT NULL) + * + * Returns: true if deleted else false + */ +static inline bool is_deleted(struct dentry *dentry) +{ + if (d_unlinked(dentry) && d_backing_inode(dentry)->i_nlink == 0) + return true; + return false; +} + +static int path_name(const char *op, const struct cred *subj_cred, + struct aa_label *label, const struct path *path, int flags, char *buffer, const char **name, struct path_cond *cond, u32 request) { @@ -153,7 +170,8 @@ static int path_name(const char *op, struct aa_label *label, labels_profile(label)->disconnected); if (error) { fn_for_each_confined(label, profile, - aa_audit_file(profile, &nullperms, op, request, *name, + aa_audit_file(subj_cred, + profile, &nullperms, op, request, *name, NULL, NULL, cond->uid, info, error)); return error; } @@ -207,9 +225,9 @@ aa_state_t aa_str_perms(struct aa_policydb *file_rules, aa_state_t start, return state; } -static int __aa_path_perm(const char *op, struct aa_profile *profile, - const char *name, u32 request, - struct path_cond *cond, int flags, +static int __aa_path_perm(const char *op, const struct cred *subj_cred, + struct aa_profile *profile, const char *name, + u32 request, struct path_cond *cond, int flags, struct aa_perms *perms) { struct aa_ruleset *rules = list_first_entry(&profile->rules, @@ -222,12 +240,14 @@ static int __aa_path_perm(const char *op, struct aa_profile *profile, name, cond, perms); if (request & ~perms->allow) e = -EACCES; - return aa_audit_file(profile, perms, op, request, name, NULL, NULL, + return aa_audit_file(subj_cred, + profile, perms, op, request, name, NULL, NULL, cond->uid, NULL, e); } -static int profile_path_perm(const char *op, struct aa_profile *profile, +static int profile_path_perm(const char *op, const struct cred *subj_cred, + struct aa_profile *profile, const struct path *path, char *buffer, u32 request, struct path_cond *cond, int flags, struct aa_perms *perms) @@ -238,18 +258,19 @@ static int profile_path_perm(const char *op, struct aa_profile *profile, if (profile_unconfined(profile)) return 0; - error = path_name(op, &profile->label, path, + error = path_name(op, subj_cred, &profile->label, path, flags | profile->path_flags, buffer, &name, cond, request); if (error) return error; - return __aa_path_perm(op, profile, name, request, cond, flags, - perms); + return __aa_path_perm(op, subj_cred, profile, name, request, cond, + flags, perms); } /** * aa_path_perm - do permissions check & audit for @path * @op: operation being checked + * @subj_cred: subject cred * @label: profile being enforced (NOT NULL) * @path: path to check permissions of (NOT NULL) * @flags: any additional path flags beyond what the profile specifies @@ -258,7 +279,8 @@ static int profile_path_perm(const char *op, struct aa_profile *profile, * * Returns: %0 else error if access denied or other error */ -int aa_path_perm(const char *op, struct aa_label *label, +int aa_path_perm(const char *op, const struct cred *subj_cred, + struct aa_label *label, const struct path *path, int flags, u32 request, struct path_cond *cond) { @@ -273,8 +295,8 @@ int aa_path_perm(const char *op, struct aa_label *label, if (!buffer) return -ENOMEM; error = fn_for_each_confined(label, profile, - profile_path_perm(op, profile, path, buffer, request, - cond, flags, &perms)); + profile_path_perm(op, subj_cred, profile, path, buffer, + request, cond, flags, &perms)); aa_put_buffer(buffer); @@ -301,7 +323,8 @@ static inline bool xindex_is_subset(u32 link, u32 target) return true; } -static int profile_path_link(struct aa_profile *profile, +static int profile_path_link(const struct cred *subj_cred, + struct aa_profile *profile, const struct path *link, char *buffer, const struct path *target, char *buffer2, struct path_cond *cond) @@ -315,13 +338,15 @@ static int profile_path_link(struct aa_profile *profile, aa_state_t state; int error; - error = path_name(OP_LINK, &profile->label, link, profile->path_flags, + error = path_name(OP_LINK, subj_cred, &profile->label, link, + profile->path_flags, buffer, &lname, cond, AA_MAY_LINK); if (error) goto audit; /* buffer2 freed below, tname is pointer in buffer2 */ - error = path_name(OP_LINK, &profile->label, target, profile->path_flags, + error = path_name(OP_LINK, subj_cred, &profile->label, target, + profile->path_flags, buffer2, &tname, cond, AA_MAY_LINK); if (error) goto audit; @@ -381,12 +406,14 @@ static int profile_path_link(struct aa_profile *profile, error = 0; audit: - return aa_audit_file(profile, &lperms, OP_LINK, request, lname, tname, + return aa_audit_file(subj_cred, + profile, &lperms, OP_LINK, request, lname, tname, NULL, cond->uid, info, error); } /** * aa_path_link - Handle hard link permission check + * @subj_cred: subject cred * @label: the label being enforced (NOT NULL) * @old_dentry: the target dentry (NOT NULL) * @new_dir: directory the new link will be created in (NOT NULL) @@ -403,7 +430,8 @@ static int profile_path_link(struct aa_profile *profile, * * Returns: %0 if allowed else error */ -int aa_path_link(struct aa_label *label, struct dentry *old_dentry, +int aa_path_link(const struct cred *subj_cred, + struct aa_label *label, struct dentry *old_dentry, const struct path *new_dir, struct dentry *new_dentry) { struct path link = { .mnt = new_dir->mnt, .dentry = new_dentry }; @@ -424,8 +452,8 @@ int aa_path_link(struct aa_label *label, struct dentry *old_dentry, goto out; error = fn_for_each_confined(label, profile, - profile_path_link(profile, &link, buffer, &target, - buffer2, &cond)); + profile_path_link(subj_cred, profile, &link, buffer, + &target, buffer2, &cond)); out: aa_put_buffer(buffer); aa_put_buffer(buffer2); @@ -453,7 +481,8 @@ static void update_file_ctx(struct aa_file_ctx *fctx, struct aa_label *label, spin_unlock(&fctx->lock); } -static int __file_path_perm(const char *op, struct aa_label *label, +static int __file_path_perm(const char *op, const struct cred *subj_cred, + struct aa_label *label, struct aa_label *flabel, struct file *file, u32 request, u32 denied, bool in_atomic) { @@ -480,7 +509,8 @@ static int __file_path_perm(const char *op, struct aa_label *label, /* check every profile in task label not in current cache */ error = fn_for_each_not_in_set(flabel, label, profile, - profile_path_perm(op, profile, &file->f_path, buffer, + profile_path_perm(op, subj_cred, profile, + &file->f_path, buffer, request, &cond, flags, &perms)); if (denied && !error) { /* @@ -493,12 +523,14 @@ static int __file_path_perm(const char *op, struct aa_label *label, */ if (label == flabel) error = fn_for_each(label, profile, - profile_path_perm(op, profile, &file->f_path, + profile_path_perm(op, subj_cred, + profile, &file->f_path, buffer, request, &cond, flags, &perms)); else error = fn_for_each_not_in_set(label, flabel, profile, - profile_path_perm(op, profile, &file->f_path, + profile_path_perm(op, subj_cred, + profile, &file->f_path, buffer, request, &cond, flags, &perms)); } @@ -510,7 +542,8 @@ static int __file_path_perm(const char *op, struct aa_label *label, return error; } -static int __file_sock_perm(const char *op, struct aa_label *label, +static int __file_sock_perm(const char *op, const struct cred *subj_cred, + struct aa_label *label, struct aa_label *flabel, struct file *file, u32 request, u32 denied) { @@ -524,11 +557,12 @@ static int __file_sock_perm(const char *op, struct aa_label *label, return 0; /* TODO: improve to skip profiles cached in flabel */ - error = aa_sock_file_perm(label, op, request, sock); + error = aa_sock_file_perm(subj_cred, label, op, request, sock); if (denied) { /* TODO: improve to skip profiles checked above */ /* check every profile in file label to is cached */ - last_error(error, aa_sock_file_perm(flabel, op, request, sock)); + last_error(error, aa_sock_file_perm(subj_cred, flabel, op, + request, sock)); } if (!error) update_file_ctx(file_ctx(file), label, request); @@ -539,6 +573,7 @@ static int __file_sock_perm(const char *op, struct aa_label *label, /** * aa_file_perm - do permission revalidation check & audit for @file * @op: operation being checked + * @subj_cred: subject cred * @label: label being enforced (NOT NULL) * @file: file to revalidate access permissions on (NOT NULL) * @request: requested permissions @@ -546,7 +581,8 @@ static int __file_sock_perm(const char *op, struct aa_label *label, * * Returns: %0 if access allowed else error */ -int aa_file_perm(const char *op, struct aa_label *label, struct file *file, +int aa_file_perm(const char *op, const struct cred *subj_cred, + struct aa_label *label, struct file *file, u32 request, bool in_atomic) { struct aa_file_ctx *fctx; @@ -582,19 +618,19 @@ int aa_file_perm(const char *op, struct aa_label *label, struct file *file, /* TODO: label cross check */ if (file->f_path.mnt && path_mediated_fs(file->f_path.dentry)) - error = __file_path_perm(op, label, flabel, file, request, - denied, in_atomic); + error = __file_path_perm(op, subj_cred, label, flabel, file, + request, denied, in_atomic); else if (S_ISSOCK(file_inode(file)->i_mode)) - error = __file_sock_perm(op, label, flabel, file, request, - denied); + error = __file_sock_perm(op, subj_cred, label, flabel, file, + request, denied); aa_put_label(flabel); done: return error; } -static void revalidate_tty(struct aa_label *label) +static void revalidate_tty(const struct cred *subj_cred, struct aa_label *label) { struct tty_struct *tty; int drop_tty = 0; @@ -612,8 +648,8 @@ static void revalidate_tty(struct aa_label *label) struct tty_file_private, list); file = file_priv->file; - if (aa_file_perm(OP_INHERIT, label, file, MAY_READ | MAY_WRITE, - IN_ATOMIC)) + if (aa_file_perm(OP_INHERIT, subj_cred, label, file, + MAY_READ | MAY_WRITE, IN_ATOMIC)) drop_tty = 1; } spin_unlock(&tty->files_lock); @@ -623,12 +659,17 @@ static void revalidate_tty(struct aa_label *label) no_tty(); } +struct cred_label { + const struct cred *cred; + struct aa_label *label; +}; + static int match_file(const void *p, struct file *file, unsigned int fd) { - struct aa_label *label = (struct aa_label *)p; + struct cred_label *cl = (struct cred_label *)p; - if (aa_file_perm(OP_INHERIT, label, file, aa_map_file_to_perms(file), - IN_ATOMIC)) + if (aa_file_perm(OP_INHERIT, cl->cred, cl->label, file, + aa_map_file_to_perms(file), IN_ATOMIC)) return fd + 1; return 0; } @@ -638,13 +679,17 @@ static int match_file(const void *p, struct file *file, unsigned int fd) void aa_inherit_files(const struct cred *cred, struct files_struct *files) { struct aa_label *label = aa_get_newest_cred_label(cred); + struct cred_label cl = { + .cred = cred, + .label = label, + }; struct file *devnull = NULL; unsigned int n; - revalidate_tty(label); + revalidate_tty(cred, label); /* Revalidate access to inherited open files. */ - n = iterate_fd(files, 0, match_file, label); + n = iterate_fd(files, 0, match_file, &cl); if (!n) /* none found? */ goto out; @@ -654,7 +699,7 @@ void aa_inherit_files(const struct cred *cred, struct files_struct *files) /* replace all the matching ones with this */ do { replace_fd(n - 1, devnull, 0); - } while ((n = iterate_fd(files, n, match_file, label)) != 0); + } while ((n = iterate_fd(files, n, match_file, &cl)) != 0); if (devnull) fput(devnull); out: diff --git a/security/apparmor/include/audit.h b/security/apparmor/include/audit.h index c328f07f11cd8..42d701fec5a6d 100644 --- a/security/apparmor/include/audit.h +++ b/security/apparmor/include/audit.h @@ -109,7 +109,8 @@ struct apparmor_audit_data { int type; u16 class; const char *op; - struct aa_label *label; + const struct cred *subj_cred; + struct aa_label *subj_label; const char *name; const char *info; u32 request; @@ -152,33 +153,35 @@ struct apparmor_audit_data { unsigned long flags; } mnt; }; + + struct common_audit_data common; }; /* macros for dealing with apparmor_audit_data structure */ -#define aad(SA) ((SA)->apparmor_audit_data) +#define aad(SA) (container_of(SA, struct apparmor_audit_data, common)) +#define aad_of_va(VA) aad((struct common_audit_data *)(VA)) + #define DEFINE_AUDIT_DATA(NAME, T, C, X) \ /* TODO: cleanup audit init so we don't need _aad = {0,} */ \ - struct apparmor_audit_data NAME ## _aad = { \ + struct apparmor_audit_data NAME = { \ .class = (C), \ .op = (X), \ - }; \ - struct common_audit_data NAME = \ - { \ - .type = (T), \ - .u.tsk = NULL, \ - }; \ - NAME.apparmor_audit_data = &(NAME ## _aad) - -void aa_audit_msg(int type, struct common_audit_data *sa, + .common.type = (T), \ + .common.u.tsk = NULL, \ + .common.apparmor_audit_data = &NAME, \ + }; + +void aa_audit_msg(int type, struct apparmor_audit_data *ad, void (*cb) (struct audit_buffer *, void *)); -int aa_audit(int type, struct aa_profile *profile, struct common_audit_data *sa, +int aa_audit(int type, struct aa_profile *profile, + struct apparmor_audit_data *ad, void (*cb) (struct audit_buffer *, void *)); -#define aa_audit_error(ERROR, SA, CB) \ +#define aa_audit_error(ERROR, AD, CB) \ ({ \ - aad((SA))->error = (ERROR); \ - aa_audit_msg(AUDIT_APPARMOR_ERROR, (SA), (CB)); \ - aad((SA))->error; \ + (AD)->error = (ERROR); \ + aa_audit_msg(AUDIT_APPARMOR_ERROR, (AD), (CB)); \ + (AD)->error; \ }) diff --git a/security/apparmor/include/capability.h b/security/apparmor/include/capability.h index d420e2d10b31b..d6dcc604ec0cc 100644 --- a/security/apparmor/include/capability.h +++ b/security/apparmor/include/capability.h @@ -36,7 +36,8 @@ struct aa_caps { extern struct aa_sfs_entry aa_sfs_entry_caps[]; -int aa_capable(struct aa_label *label, int cap, unsigned int opts); +int aa_capable(const struct cred *subj_cred, struct aa_label *label, + int cap, unsigned int opts); static inline void aa_free_cap_rules(struct aa_caps *caps) { diff --git a/security/apparmor/include/file.h b/security/apparmor/include/file.h index 5be620af33ba0..64dc6d1a7a05c 100644 --- a/security/apparmor/include/file.h +++ b/security/apparmor/include/file.h @@ -108,7 +108,8 @@ struct path_cond { #define COMBINED_PERM_MASK(X) ((X).allow | (X).audit | (X).quiet | (X).kill) -int aa_audit_file(struct aa_profile *profile, struct aa_perms *perms, +int aa_audit_file(const struct cred *cred, + struct aa_profile *profile, struct aa_perms *perms, const char *op, u32 request, const char *name, const char *target, struct aa_label *tlabel, kuid_t ouid, const char *info, int error); @@ -119,14 +120,16 @@ aa_state_t aa_str_perms(struct aa_policydb *file_rules, aa_state_t start, const char *name, struct path_cond *cond, struct aa_perms *perms); -int aa_path_perm(const char *op, struct aa_label *label, - const struct path *path, int flags, u32 request, - struct path_cond *cond); +int aa_path_perm(const char *op, const struct cred *subj_cred, + struct aa_label *label, const struct path *path, + int flags, u32 request, struct path_cond *cond); -int aa_path_link(struct aa_label *label, struct dentry *old_dentry, - const struct path *new_dir, struct dentry *new_dentry); +int aa_path_link(const struct cred *subj_cred, struct aa_label *label, + struct dentry *old_dentry, const struct path *new_dir, + struct dentry *new_dentry); -int aa_file_perm(const char *op, struct aa_label *label, struct file *file, +int aa_file_perm(const char *op, const struct cred *subj_cred, + struct aa_label *label, struct file *file, u32 request, bool in_atomic); void aa_inherit_files(const struct cred *cred, struct files_struct *files); diff --git a/security/apparmor/include/ipc.h b/security/apparmor/include/ipc.h index a1ac6ffb95e9c..74d17052f76bc 100644 --- a/security/apparmor/include/ipc.h +++ b/security/apparmor/include/ipc.h @@ -13,6 +13,8 @@ #include -int aa_may_signal(struct aa_label *sender, struct aa_label *target, int sig); +int aa_may_signal(const struct cred *subj_cred, struct aa_label *sender, + const struct cred *target_cred, struct aa_label *target, + int sig); #endif /* __AA_IPC_H */ diff --git a/security/apparmor/include/mount.h b/security/apparmor/include/mount.h index a710683b24965..46834f8281794 100644 --- a/security/apparmor/include/mount.h +++ b/security/apparmor/include/mount.h @@ -25,26 +25,36 @@ #define AA_MS_IGNORE_MASK (MS_KERNMOUNT | MS_NOSEC | MS_ACTIVE | MS_BORN) -int aa_remount(struct aa_label *label, const struct path *path, +int aa_remount(const struct cred *subj_cred, + struct aa_label *label, const struct path *path, unsigned long flags, void *data); -int aa_bind_mount(struct aa_label *label, const struct path *path, +int aa_bind_mount(const struct cred *subj_cred, + struct aa_label *label, const struct path *path, const char *old_name, unsigned long flags); -int aa_mount_change_type(struct aa_label *label, const struct path *path, +int aa_mount_change_type(const struct cred *subj_cred, + struct aa_label *label, const struct path *path, unsigned long flags); -int aa_move_mount(struct aa_label *label, const struct path *path, - const char *old_name); +int aa_move_mount_old(const struct cred *subj_cred, + struct aa_label *label, const struct path *path, + const char *old_name); +int aa_move_mount(const struct cred *subj_cred, + struct aa_label *label, const struct path *from_path, + const struct path *to_path); -int aa_new_mount(struct aa_label *label, const char *dev_name, +int aa_new_mount(const struct cred *subj_cred, + struct aa_label *label, const char *dev_name, const struct path *path, const char *type, unsigned long flags, void *data); -int aa_umount(struct aa_label *label, struct vfsmount *mnt, int flags); +int aa_umount(const struct cred *subj_cred, + struct aa_label *label, struct vfsmount *mnt, int flags); -int aa_pivotroot(struct aa_label *label, const struct path *old_path, +int aa_pivotroot(const struct cred *subj_cred, + struct aa_label *label, const struct path *old_path, const struct path *new_path); #endif /* __AA_MOUNT_H */ diff --git a/security/apparmor/include/net.h b/security/apparmor/include/net.h index 6fa440b5daed8..aa8515af677f0 100644 --- a/security/apparmor/include/net.h +++ b/security/apparmor/include/net.h @@ -61,9 +61,9 @@ struct aa_sk_ctx { LSM_AUDIT_DATA_NONE, \ AA_CLASS_NET, \ OP); \ - NAME.u.net = &(NAME ## _net); \ - aad(&NAME)->net.type = (T); \ - aad(&NAME)->net.protocol = (P) + NAME.common.u.net = &(NAME ## _net); \ + NAME.net.type = (T); \ + NAME.net.protocol = (P) #define DEFINE_AUDIT_SK(NAME, OP, SK) \ DEFINE_AUDIT_NET(NAME, OP, SK, (SK)->sk_family, (SK)->sk_type, \ @@ -90,21 +90,24 @@ struct aa_secmark { extern struct aa_sfs_entry aa_sfs_entry_network[]; void audit_net_cb(struct audit_buffer *ab, void *va); -int aa_profile_af_perm(struct aa_profile *profile, struct common_audit_data *sa, +int aa_profile_af_perm(struct aa_profile *profile, + struct apparmor_audit_data *ad, u32 request, u16 family, int type); -int aa_af_perm(struct aa_label *label, const char *op, u32 request, u16 family, +int aa_af_perm(const struct cred *subj_cred, struct aa_label *label, + const char *op, u32 request, u16 family, int type, int protocol); static inline int aa_profile_af_sk_perm(struct aa_profile *profile, - struct common_audit_data *sa, + struct apparmor_audit_data *ad, u32 request, struct sock *sk) { - return aa_profile_af_perm(profile, sa, request, sk->sk_family, + return aa_profile_af_perm(profile, ad, request, sk->sk_family, sk->sk_type); } int aa_sk_perm(const char *op, u32 request, struct sock *sk); -int aa_sock_file_perm(struct aa_label *label, const char *op, u32 request, +int aa_sock_file_perm(const struct cred *subj_cred, struct aa_label *label, + const char *op, u32 request, struct socket *sock); int apparmor_secmark_check(struct aa_label *label, char *op, u32 request, diff --git a/security/apparmor/include/perms.h b/security/apparmor/include/perms.h index 797a7a00644d2..83534df8939fd 100644 --- a/security/apparmor/include/perms.h +++ b/security/apparmor/include/perms.h @@ -212,8 +212,8 @@ void aa_profile_match_label(struct aa_profile *profile, int type, u32 request, struct aa_perms *perms); int aa_profile_label_perm(struct aa_profile *profile, struct aa_profile *target, u32 request, int type, u32 *deny, - struct common_audit_data *sa); + struct apparmor_audit_data *ad); int aa_check_perms(struct aa_profile *profile, struct aa_perms *perms, - u32 request, struct common_audit_data *sa, + u32 request, struct apparmor_audit_data *ad, void (*cb)(struct audit_buffer *, void *)); #endif /* __AA_PERM_H */ diff --git a/security/apparmor/include/policy.h b/security/apparmor/include/policy.h index 545f791cabdae..fa15a5c7febb8 100644 --- a/security/apparmor/include/policy.h +++ b/security/apparmor/include/policy.h @@ -370,9 +370,12 @@ static inline int AUDIT_MODE(struct aa_profile *profile) return profile->audit; } -bool aa_policy_view_capable(struct aa_label *label, struct aa_ns *ns); -bool aa_policy_admin_capable(struct aa_label *label, struct aa_ns *ns); -int aa_may_manage_policy(struct aa_label *label, struct aa_ns *ns, +bool aa_policy_view_capable(const struct cred *subj_cred, + struct aa_label *label, struct aa_ns *ns); +bool aa_policy_admin_capable(const struct cred *subj_cred, + struct aa_label *label, struct aa_ns *ns); +int aa_may_manage_policy(const struct cred *subj_cred, + struct aa_label *label, struct aa_ns *ns, u32 mask); bool aa_current_policy_view_capable(struct aa_ns *ns); bool aa_current_policy_admin_capable(struct aa_ns *ns); diff --git a/security/apparmor/include/resource.h b/security/apparmor/include/resource.h index 961d85d328ea9..ad2c0da8e64fc 100644 --- a/security/apparmor/include/resource.h +++ b/security/apparmor/include/resource.h @@ -33,7 +33,8 @@ struct aa_rlimit { extern struct aa_sfs_entry aa_sfs_entry_rlimit[]; int aa_map_resource(int resource); -int aa_task_setrlimit(struct aa_label *label, struct task_struct *task, +int aa_task_setrlimit(const struct cred *subj_cred, struct aa_label *label, + struct task_struct *task, unsigned int resource, struct rlimit *new_rlim); void __aa_transition_rlimits(struct aa_label *old, struct aa_label *new); diff --git a/security/apparmor/include/task.h b/security/apparmor/include/task.h index 13437d62c70f4..29ba55107b7d6 100644 --- a/security/apparmor/include/task.h +++ b/security/apparmor/include/task.h @@ -91,7 +91,8 @@ static inline void aa_clear_task_ctx_trans(struct aa_task_ctx *ctx) "segv usr2 pipe alrm term stkflt chld cont stop stp ttin ttou urg " \ "xcpu xfsz vtalrm prof winch io pwr sys emt lost" -int aa_may_ptrace(struct aa_label *tracer, struct aa_label *tracee, +int aa_may_ptrace(const struct cred *tracer_cred, struct aa_label *tracer, + const struct cred *tracee_cred, struct aa_label *tracee, u32 request); diff --git a/security/apparmor/ipc.c b/security/apparmor/ipc.c index 5acde746775f7..c0d0dbd7b4c4b 100644 --- a/security/apparmor/ipc.c +++ b/security/apparmor/ipc.c @@ -52,31 +52,33 @@ static const char *audit_signal_mask(u32 mask) static void audit_signal_cb(struct audit_buffer *ab, void *va) { struct common_audit_data *sa = va; + struct apparmor_audit_data *ad = aad(sa); - if (aad(sa)->request & AA_SIGNAL_PERM_MASK) { + if (ad->request & AA_SIGNAL_PERM_MASK) { audit_log_format(ab, " requested_mask=\"%s\"", - audit_signal_mask(aad(sa)->request)); - if (aad(sa)->denied & AA_SIGNAL_PERM_MASK) { + audit_signal_mask(ad->request)); + if (ad->denied & AA_SIGNAL_PERM_MASK) { audit_log_format(ab, " denied_mask=\"%s\"", - audit_signal_mask(aad(sa)->denied)); + audit_signal_mask(ad->denied)); } } - if (aad(sa)->signal == SIGUNKNOWN) + if (ad->signal == SIGUNKNOWN) audit_log_format(ab, "signal=unknown(%d)", - aad(sa)->unmappedsig); - else if (aad(sa)->signal < MAXMAPPED_SIGNAME) - audit_log_format(ab, " signal=%s", sig_names[aad(sa)->signal]); + ad->unmappedsig); + else if (ad->signal < MAXMAPPED_SIGNAME) + audit_log_format(ab, " signal=%s", sig_names[ad->signal]); else audit_log_format(ab, " signal=rtmin+%d", - aad(sa)->signal - SIGRT_BASE); + ad->signal - SIGRT_BASE); audit_log_format(ab, " peer="); - aa_label_xaudit(ab, labels_ns(aad(sa)->label), aad(sa)->peer, + aa_label_xaudit(ab, labels_ns(ad->subj_label), ad->peer, FLAGS_NONE, GFP_ATOMIC); } -static int profile_signal_perm(struct aa_profile *profile, +static int profile_signal_perm(const struct cred *cred, + struct aa_profile *profile, struct aa_label *peer, u32 request, - struct common_audit_data *sa) + struct apparmor_audit_data *ad) { struct aa_ruleset *rules = list_first_entry(&profile->rules, typeof(*rules), list); @@ -87,24 +89,29 @@ static int profile_signal_perm(struct aa_profile *profile, !ANY_RULE_MEDIATES(&profile->rules, AA_CLASS_SIGNAL)) return 0; - aad(sa)->peer = peer; + ad->subj_cred = cred; + ad->peer = peer; /* TODO: secondary cache check */ state = aa_dfa_next(rules->policy.dfa, rules->policy.start[AA_CLASS_SIGNAL], - aad(sa)->signal); + ad->signal); aa_label_match(profile, rules, peer, state, false, request, &perms); aa_apply_modes_to_perms(profile, &perms); - return aa_check_perms(profile, &perms, request, sa, audit_signal_cb); + return aa_check_perms(profile, &perms, request, ad, audit_signal_cb); } -int aa_may_signal(struct aa_label *sender, struct aa_label *target, int sig) +int aa_may_signal(const struct cred *subj_cred, struct aa_label *sender, + const struct cred *target_cred, struct aa_label *target, + int sig) { struct aa_profile *profile; - DEFINE_AUDIT_DATA(sa, LSM_AUDIT_DATA_NONE, AA_CLASS_SIGNAL, OP_SIGNAL); + DEFINE_AUDIT_DATA(ad, LSM_AUDIT_DATA_NONE, AA_CLASS_SIGNAL, OP_SIGNAL); - aad(&sa)->signal = map_signal_num(sig); - aad(&sa)->unmappedsig = sig; + ad.signal = map_signal_num(sig); + ad.unmappedsig = sig; return xcheck_labels(sender, target, profile, - profile_signal_perm(profile, target, MAY_WRITE, &sa), - profile_signal_perm(profile, sender, MAY_READ, &sa)); + profile_signal_perm(subj_cred, profile, target, + MAY_WRITE, &ad), + profile_signal_perm(target_cred, profile, sender, + MAY_READ, &ad)); } diff --git a/security/apparmor/lib.c b/security/apparmor/lib.c index a630c951bb3b8..c87bccafff446 100644 --- a/security/apparmor/lib.c +++ b/security/apparmor/lib.c @@ -27,7 +27,7 @@ struct aa_perms allperms = { .allow = ALL_PERMS_MASK, /** * aa_free_str_table - free entries str table - * @str: the string table to free (MAYBE NULL) + * @t: the string table to free (MAYBE NULL) */ void aa_free_str_table(struct aa_str_table *t) { @@ -85,6 +85,7 @@ char *aa_split_fqname(char *fqname, char **ns_name) /** * skipn_spaces - Removes leading whitespace from @str. * @str: The string to be stripped. + * @n: length of str to parse, will stop at \0 if encountered before n * * Returns a pointer to the first non-whitespace character in @str. * if all whitespace will return NULL @@ -143,10 +144,10 @@ const char *aa_splitn_fqname(const char *fqname, size_t n, const char **ns_name, void aa_info_message(const char *str) { if (audit_enabled) { - DEFINE_AUDIT_DATA(sa, LSM_AUDIT_DATA_NONE, AA_CLASS_NONE, NULL); + DEFINE_AUDIT_DATA(ad, LSM_AUDIT_DATA_NONE, AA_CLASS_NONE, NULL); - aad(&sa)->info = str; - aa_audit_msg(AUDIT_APPARMOR_STATUS, &sa, NULL); + ad.info = str; + aa_audit_msg(AUDIT_APPARMOR_STATUS, &ad, NULL); } printk(KERN_INFO "AppArmor: %s\n", str); } @@ -281,21 +282,22 @@ void aa_audit_perm_mask(struct audit_buffer *ab, u32 mask, const char *chrs, static void aa_audit_perms_cb(struct audit_buffer *ab, void *va) { struct common_audit_data *sa = va; + struct apparmor_audit_data *ad = aad(sa); - if (aad(sa)->request) { + if (ad->request) { audit_log_format(ab, " requested_mask="); - aa_audit_perm_mask(ab, aad(sa)->request, aa_file_perm_chrs, + aa_audit_perm_mask(ab, ad->request, aa_file_perm_chrs, PERMS_CHRS_MASK, aa_file_perm_names, PERMS_NAMES_MASK); } - if (aad(sa)->denied) { + if (ad->denied) { audit_log_format(ab, "denied_mask="); - aa_audit_perm_mask(ab, aad(sa)->denied, aa_file_perm_chrs, + aa_audit_perm_mask(ab, ad->denied, aa_file_perm_chrs, PERMS_CHRS_MASK, aa_file_perm_names, PERMS_NAMES_MASK); } audit_log_format(ab, " peer="); - aa_label_xaudit(ab, labels_ns(aad(sa)->label), aad(sa)->peer, + aa_label_xaudit(ab, labels_ns(ad->subj_label), ad->peer, FLAGS_NONE, GFP_ATOMIC); } @@ -349,21 +351,20 @@ void aa_profile_match_label(struct aa_profile *profile, /* currently unused */ int aa_profile_label_perm(struct aa_profile *profile, struct aa_profile *target, u32 request, int type, u32 *deny, - struct common_audit_data *sa) + struct apparmor_audit_data *ad) { struct aa_ruleset *rules = list_first_entry(&profile->rules, typeof(*rules), list); struct aa_perms perms; - aad(sa)->label = &profile->label; - aad(sa)->peer = &target->label; - aad(sa)->request = request; + ad->peer = &target->label; + ad->request = request; aa_profile_match_label(profile, rules, &target->label, type, request, &perms); aa_apply_modes_to_perms(profile, &perms); *deny |= request & perms.deny; - return aa_check_perms(profile, &perms, request, sa, aa_audit_perms_cb); + return aa_check_perms(profile, &perms, request, ad, aa_audit_perms_cb); } /** @@ -371,8 +372,7 @@ int aa_profile_label_perm(struct aa_profile *profile, struct aa_profile *target, * @profile: profile being checked * @perms: perms computed for the request * @request: requested perms - * @deny: Returns: explicit deny set - * @sa: initialized audit structure (MAY BE NULL if not auditing) + * @ad: initialized audit structure (MAY BE NULL if not auditing) * @cb: callback fn for type specific fields (MAY BE NULL) * * Returns: 0 if permission else error code @@ -385,7 +385,7 @@ int aa_profile_label_perm(struct aa_profile *profile, struct aa_profile *target, * with a positive value. */ int aa_check_perms(struct aa_profile *profile, struct aa_perms *perms, - u32 request, struct common_audit_data *sa, + u32 request, struct apparmor_audit_data *ad, void (*cb)(struct audit_buffer *, void *)) { int type, error; @@ -394,7 +394,7 @@ int aa_check_perms(struct aa_profile *profile, struct aa_perms *perms, if (likely(!denied)) { /* mask off perms that are not being force audited */ request &= perms->audit; - if (!request || !sa) + if (!request || !ad) return 0; type = AUDIT_APPARMOR_AUDIT; @@ -413,16 +413,16 @@ int aa_check_perms(struct aa_profile *profile, struct aa_perms *perms, error = -ENOENT; denied &= ~perms->quiet; - if (!sa || !denied) + if (!ad || !denied) return error; } - if (sa) { - aad(sa)->label = &profile->label; - aad(sa)->request = request; - aad(sa)->denied = denied; - aad(sa)->error = error; - aa_audit_msg(type, sa, cb); + if (ad) { + ad->subj_label = &profile->label; + ad->request = request; + ad->denied = denied; + ad->error = error; + aa_audit_msg(type, ad, cb); } if (type == AUDIT_APPARMOR_ALLOWED) diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index 108eccc5ada58..6fdab1b5ede5c 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -116,15 +116,17 @@ static int apparmor_ptrace_access_check(struct task_struct *child, unsigned int mode) { struct aa_label *tracer, *tracee; + const struct cred *cred; int error; + cred = get_task_cred(child); + tracee = cred_label(cred); /* ref count on cred */ tracer = __begin_current_label_crit_section(); - tracee = aa_get_task_label(child); - error = aa_may_ptrace(tracer, tracee, + error = aa_may_ptrace(current_cred(), tracer, cred, tracee, (mode & PTRACE_MODE_READ) ? AA_PTRACE_READ : AA_PTRACE_TRACE); - aa_put_label(tracee); __end_current_label_crit_section(tracer); + put_cred(cred); return error; } @@ -132,12 +134,15 @@ static int apparmor_ptrace_access_check(struct task_struct *child, static int apparmor_ptrace_traceme(struct task_struct *parent) { struct aa_label *tracer, *tracee; + const struct cred *cred; int error; tracee = __begin_current_label_crit_section(); - tracer = aa_get_task_label(parent); - error = aa_may_ptrace(tracer, tracee, AA_PTRACE_TRACE); - aa_put_label(tracer); + cred = get_task_cred(parent); + tracer = cred_label(cred); /* ref count on cred */ + error = aa_may_ptrace(cred, tracer, current_cred(), tracee, + AA_PTRACE_TRACE); + put_cred(cred); __end_current_label_crit_section(tracee); return error; @@ -188,7 +193,7 @@ static int apparmor_capable(const struct cred *cred, struct user_namespace *ns, label = aa_get_newest_cred_label(cred); if (!unconfined(label)) - error = aa_capable(label, cap, opts); + error = aa_capable(cred, label, cap, opts); aa_put_label(label); return error; @@ -211,7 +216,8 @@ static int common_perm(const char *op, const struct path *path, u32 mask, label = __begin_current_label_crit_section(); if (!unconfined(label)) - error = aa_path_perm(op, label, path, 0, mask, cond); + error = aa_path_perm(op, current_cred(), label, path, 0, mask, + cond); __end_current_label_crit_section(label); return error; @@ -357,7 +363,8 @@ static int apparmor_path_link(struct dentry *old_dentry, const struct path *new_ label = begin_current_label_crit_section(); if (!unconfined(label)) - error = aa_path_link(label, old_dentry, new_dir, new_dentry); + error = aa_path_link(current_cred(), label, old_dentry, new_dir, + new_dentry); end_current_label_crit_section(label); return error; @@ -396,23 +403,27 @@ static int apparmor_path_rename(const struct path *old_dir, struct dentry *old_d vfsuid = i_uid_into_vfsuid(idmap, d_backing_inode(old_dentry)); cond_exchange.uid = vfsuid_into_kuid(vfsuid); - error = aa_path_perm(OP_RENAME_SRC, label, &new_path, 0, + error = aa_path_perm(OP_RENAME_SRC, current_cred(), + label, &new_path, 0, MAY_READ | AA_MAY_GETATTR | MAY_WRITE | AA_MAY_SETATTR | AA_MAY_DELETE, &cond_exchange); if (!error) - error = aa_path_perm(OP_RENAME_DEST, label, &old_path, + error = aa_path_perm(OP_RENAME_DEST, current_cred(), + label, &old_path, 0, MAY_WRITE | AA_MAY_SETATTR | AA_MAY_CREATE, &cond_exchange); } if (!error) - error = aa_path_perm(OP_RENAME_SRC, label, &old_path, 0, + error = aa_path_perm(OP_RENAME_SRC, current_cred(), + label, &old_path, 0, MAY_READ | AA_MAY_GETATTR | MAY_WRITE | AA_MAY_SETATTR | AA_MAY_DELETE, &cond); if (!error) - error = aa_path_perm(OP_RENAME_DEST, label, &new_path, + error = aa_path_perm(OP_RENAME_DEST, current_cred(), + label, &new_path, 0, MAY_WRITE | AA_MAY_SETATTR | AA_MAY_CREATE, &cond); @@ -467,7 +478,8 @@ static int apparmor_file_open(struct file *file) vfsuid = i_uid_into_vfsuid(idmap, inode); cond.uid = vfsuid_into_kuid(vfsuid); - error = aa_path_perm(OP_OPEN, label, &file->f_path, 0, + error = aa_path_perm(OP_OPEN, file->f_cred, + label, &file->f_path, 0, aa_map_file_to_perms(file), &cond); /* todo cache full allowed permissions set and state */ fctx->allow = aa_map_file_to_perms(file); @@ -507,7 +519,7 @@ static int common_file_perm(const char *op, struct file *file, u32 mask, return -EACCES; label = __begin_current_label_crit_section(); - error = aa_file_perm(op, label, file, mask, in_atomic); + error = aa_file_perm(op, current_cred(), label, file, mask, in_atomic); __end_current_label_crit_section(label); return error; @@ -585,23 +597,42 @@ static int apparmor_sb_mount(const char *dev_name, const struct path *path, label = __begin_current_label_crit_section(); if (!unconfined(label)) { if (flags & MS_REMOUNT) - error = aa_remount(label, path, flags, data); + error = aa_remount(current_cred(), label, path, flags, + data); else if (flags & MS_BIND) - error = aa_bind_mount(label, path, dev_name, flags); + error = aa_bind_mount(current_cred(), label, path, + dev_name, flags); else if (flags & (MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE)) - error = aa_mount_change_type(label, path, flags); + error = aa_mount_change_type(current_cred(), label, + path, flags); else if (flags & MS_MOVE) - error = aa_move_mount(label, path, dev_name); + error = aa_move_mount_old(current_cred(), label, path, + dev_name); else - error = aa_new_mount(label, dev_name, path, type, - flags, data); + error = aa_new_mount(current_cred(), label, dev_name, + path, type, flags, data); } __end_current_label_crit_section(label); return error; } +static int apparmor_move_mount(const struct path *from_path, + const struct path *to_path) +{ + struct aa_label *label; + int error = 0; + + label = __begin_current_label_crit_section(); + if (!unconfined(label)) + error = aa_move_mount(current_cred(), label, from_path, + to_path); + __end_current_label_crit_section(label); + + return error; +} + static int apparmor_sb_umount(struct vfsmount *mnt, int flags) { struct aa_label *label; @@ -609,7 +640,7 @@ static int apparmor_sb_umount(struct vfsmount *mnt, int flags) label = __begin_current_label_crit_section(); if (!unconfined(label)) - error = aa_umount(label, mnt, flags); + error = aa_umount(current_cred(), label, mnt, flags); __end_current_label_crit_section(label); return error; @@ -623,7 +654,7 @@ static int apparmor_sb_pivotroot(const struct path *old_path, label = aa_get_current_label(); if (!unconfined(label)) - error = aa_pivotroot(label, old_path, new_path); + error = aa_pivotroot(current_cred(), label, old_path, new_path); aa_put_label(label); return error; @@ -662,7 +693,7 @@ static int apparmor_setprocattr(const char *name, void *value, char *command, *largs = NULL, *args = value; size_t arg_size; int error; - DEFINE_AUDIT_DATA(sa, LSM_AUDIT_DATA_NONE, AA_CLASS_NONE, + DEFINE_AUDIT_DATA(ad, LSM_AUDIT_DATA_NONE, AA_CLASS_NONE, OP_SETPROCATTR); if (size == 0) @@ -722,11 +753,11 @@ static int apparmor_setprocattr(const char *name, void *value, return error; fail: - aad(&sa)->label = begin_current_label_crit_section(); - aad(&sa)->info = name; - aad(&sa)->error = error = -EINVAL; - aa_audit_msg(AUDIT_APPARMOR_DENIED, &sa, NULL); - end_current_label_crit_section(aad(&sa)->label); + ad.subj_label = begin_current_label_crit_section(); + ad.info = name; + ad.error = error = -EINVAL; + aa_audit_msg(AUDIT_APPARMOR_DENIED, &ad, NULL); + end_current_label_crit_section(ad.subj_label); goto out; } @@ -785,7 +816,8 @@ static int apparmor_task_setrlimit(struct task_struct *task, int error = 0; if (!unconfined(label)) - error = aa_task_setrlimit(label, task, resource, new_rlim); + error = aa_task_setrlimit(current_cred(), label, task, + resource, new_rlim); __end_current_label_crit_section(label); return error; @@ -794,26 +826,27 @@ static int apparmor_task_setrlimit(struct task_struct *task, static int apparmor_task_kill(struct task_struct *target, struct kernel_siginfo *info, int sig, const struct cred *cred) { + const struct cred *tc; struct aa_label *cl, *tl; int error; + tc = get_task_cred(target); + tl = aa_get_newest_cred_label(tc); if (cred) { /* * Dealing with USB IO specific behavior */ cl = aa_get_newest_cred_label(cred); - tl = aa_get_task_label(target); - error = aa_may_signal(cl, tl, sig); + error = aa_may_signal(cred, cl, tc, tl, sig); aa_put_label(cl); - aa_put_label(tl); return error; + } else { + cl = __begin_current_label_crit_section(); + error = aa_may_signal(current_cred(), cl, tc, tl, sig); + __end_current_label_crit_section(cl); } - - cl = __begin_current_label_crit_section(); - tl = aa_get_task_label(target); - error = aa_may_signal(cl, tl, sig); aa_put_label(tl); - __end_current_label_crit_section(cl); + put_cred(tc); return error; } @@ -879,7 +912,8 @@ static int apparmor_socket_create(int family, int type, int protocol, int kern) if (!(kern || unconfined(label))) error = af_select(family, create_perm(label, family, type, protocol), - aa_af_perm(label, OP_CREATE, AA_MAY_CREATE, + aa_af_perm(current_cred(), label, + OP_CREATE, AA_MAY_CREATE, family, type, protocol)); end_current_label_crit_section(label); @@ -1221,6 +1255,7 @@ static struct security_hook_list apparmor_hooks[] __ro_after_init = { LSM_HOOK_INIT(capget, apparmor_capget), LSM_HOOK_INIT(capable, apparmor_capable), + LSM_HOOK_INIT(move_mount, apparmor_move_mount), LSM_HOOK_INIT(sb_mount, apparmor_sb_mount), LSM_HOOK_INIT(sb_umount, apparmor_sb_umount), LSM_HOOK_INIT(sb_pivotroot, apparmor_sb_pivotroot), diff --git a/security/apparmor/mount.c b/security/apparmor/mount.c index cdfa430ae2161..f2a114e540079 100644 --- a/security/apparmor/mount.c +++ b/security/apparmor/mount.c @@ -86,32 +86,34 @@ static void audit_mnt_flags(struct audit_buffer *ab, unsigned long flags) static void audit_cb(struct audit_buffer *ab, void *va) { struct common_audit_data *sa = va; + struct apparmor_audit_data *ad = aad(sa); - if (aad(sa)->mnt.type) { + if (ad->mnt.type) { audit_log_format(ab, " fstype="); - audit_log_untrustedstring(ab, aad(sa)->mnt.type); + audit_log_untrustedstring(ab, ad->mnt.type); } - if (aad(sa)->mnt.src_name) { + if (ad->mnt.src_name) { audit_log_format(ab, " srcname="); - audit_log_untrustedstring(ab, aad(sa)->mnt.src_name); + audit_log_untrustedstring(ab, ad->mnt.src_name); } - if (aad(sa)->mnt.trans) { + if (ad->mnt.trans) { audit_log_format(ab, " trans="); - audit_log_untrustedstring(ab, aad(sa)->mnt.trans); + audit_log_untrustedstring(ab, ad->mnt.trans); } - if (aad(sa)->mnt.flags) { + if (ad->mnt.flags) { audit_log_format(ab, " flags=\""); - audit_mnt_flags(ab, aad(sa)->mnt.flags); + audit_mnt_flags(ab, ad->mnt.flags); audit_log_format(ab, "\""); } - if (aad(sa)->mnt.data) { + if (ad->mnt.data) { audit_log_format(ab, " options="); - audit_log_untrustedstring(ab, aad(sa)->mnt.data); + audit_log_untrustedstring(ab, ad->mnt.data); } } /** * audit_mount - handle the auditing of mount operations + * @subj_cred: cred of the subject * @profile: the profile being enforced (NOT NULL) * @op: operation being mediated (NOT NULL) * @name: name of object being mediated (MAYBE NULL) @@ -127,14 +129,15 @@ static void audit_cb(struct audit_buffer *ab, void *va) * * Returns: %0 or error on failure */ -static int audit_mount(struct aa_profile *profile, const char *op, +static int audit_mount(const struct cred *subj_cred, + struct aa_profile *profile, const char *op, const char *name, const char *src_name, const char *type, const char *trans, unsigned long flags, const void *data, u32 request, struct aa_perms *perms, const char *info, int error) { int audit_type = AUDIT_APPARMOR_AUTO; - DEFINE_AUDIT_DATA(sa, LSM_AUDIT_DATA_NONE, AA_CLASS_MOUNT, op); + DEFINE_AUDIT_DATA(ad, LSM_AUDIT_DATA_NONE, AA_CLASS_MOUNT, op); if (likely(!error)) { u32 mask = perms->audit; @@ -165,17 +168,18 @@ static int audit_mount(struct aa_profile *profile, const char *op, return error; } - aad(&sa)->name = name; - aad(&sa)->mnt.src_name = src_name; - aad(&sa)->mnt.type = type; - aad(&sa)->mnt.trans = trans; - aad(&sa)->mnt.flags = flags; + ad.subj_cred = subj_cred; + ad.name = name; + ad.mnt.src_name = src_name; + ad.mnt.type = type; + ad.mnt.trans = trans; + ad.mnt.flags = flags; if (data && (perms->audit & AA_AUDIT_DATA)) - aad(&sa)->mnt.data = data; - aad(&sa)->info = info; - aad(&sa)->error = error; + ad.mnt.data = data; + ad.info = info; + ad.error = error; - return aa_audit(audit_type, profile, &sa, audit_cb); + return aa_audit(audit_type, profile, &ad, audit_cb); } /** @@ -283,6 +287,7 @@ static int path_flags(struct aa_profile *profile, const struct path *path) /** * match_mnt_path_str - handle path matching for mount + * @subj_cred: cred of confined subject * @profile: the confining profile * @mntpath: for the mntpnt (NOT NULL) * @buffer: buffer to be used to lookup mntpath @@ -295,7 +300,8 @@ static int path_flags(struct aa_profile *profile, const struct path *path) * * Returns: 0 on success else error */ -static int match_mnt_path_str(struct aa_profile *profile, +static int match_mnt_path_str(const struct cred *subj_cred, + struct aa_profile *profile, const struct path *mntpath, char *buffer, const char *devname, const char *type, unsigned long flags, void *data, bool binary, @@ -336,12 +342,14 @@ static int match_mnt_path_str(struct aa_profile *profile, error = 0; audit: - return audit_mount(profile, OP_MOUNT, mntpnt, devname, type, NULL, + return audit_mount(subj_cred, profile, OP_MOUNT, mntpnt, devname, + type, NULL, flags, data, AA_MAY_MOUNT, &perms, info, error); } /** * match_mnt - handle path matching for mount + * @subj_cred: cred of the subject * @profile: the confining profile * @path: for the mntpnt (NOT NULL) * @buffer: buffer to be used to lookup mntpath @@ -354,7 +362,8 @@ static int match_mnt_path_str(struct aa_profile *profile, * * Returns: 0 on success else error */ -static int match_mnt(struct aa_profile *profile, const struct path *path, +static int match_mnt(const struct cred *subj_cred, + struct aa_profile *profile, const struct path *path, char *buffer, const struct path *devpath, char *devbuffer, const char *type, unsigned long flags, void *data, bool binary) @@ -378,11 +387,12 @@ static int match_mnt(struct aa_profile *profile, const struct path *path, devname = ERR_PTR(error); } - return match_mnt_path_str(profile, path, buffer, devname, type, flags, - data, binary, info); + return match_mnt_path_str(subj_cred, profile, path, buffer, devname, + type, flags, data, binary, info); } -int aa_remount(struct aa_label *label, const struct path *path, +int aa_remount(const struct cred *subj_cred, + struct aa_label *label, const struct path *path, unsigned long flags, void *data) { struct aa_profile *profile; @@ -399,14 +409,16 @@ int aa_remount(struct aa_label *label, const struct path *path, if (!buffer) return -ENOMEM; error = fn_for_each_confined(label, profile, - match_mnt(profile, path, buffer, NULL, NULL, NULL, + match_mnt(subj_cred, profile, path, buffer, NULL, + NULL, NULL, flags, data, binary)); aa_put_buffer(buffer); return error; } -int aa_bind_mount(struct aa_label *label, const struct path *path, +int aa_bind_mount(const struct cred *subj_cred, + struct aa_label *label, const struct path *path, const char *dev_name, unsigned long flags) { struct aa_profile *profile; @@ -433,8 +445,8 @@ int aa_bind_mount(struct aa_label *label, const struct path *path, goto out; error = fn_for_each_confined(label, profile, - match_mnt(profile, path, buffer, &old_path, old_buffer, - NULL, flags, NULL, false)); + match_mnt(subj_cred, profile, path, buffer, &old_path, + old_buffer, NULL, flags, NULL, false)); out: aa_put_buffer(buffer); aa_put_buffer(old_buffer); @@ -443,7 +455,8 @@ int aa_bind_mount(struct aa_label *label, const struct path *path, return error; } -int aa_mount_change_type(struct aa_label *label, const struct path *path, +int aa_mount_change_type(const struct cred *subj_cred, + struct aa_label *label, const struct path *path, unsigned long flags) { struct aa_profile *profile; @@ -461,50 +474,63 @@ int aa_mount_change_type(struct aa_label *label, const struct path *path, if (!buffer) return -ENOMEM; error = fn_for_each_confined(label, profile, - match_mnt(profile, path, buffer, NULL, NULL, NULL, + match_mnt(subj_cred, profile, path, buffer, NULL, + NULL, NULL, flags, NULL, false)); aa_put_buffer(buffer); return error; } -int aa_move_mount(struct aa_label *label, const struct path *path, - const char *orig_name) +int aa_move_mount(const struct cred *subj_cred, + struct aa_label *label, const struct path *from_path, + const struct path *to_path) { struct aa_profile *profile; - char *buffer = NULL, *old_buffer = NULL; - struct path old_path; + char *to_buffer = NULL, *from_buffer = NULL; int error; AA_BUG(!label); - AA_BUG(!path); + AA_BUG(!from_path); + AA_BUG(!to_path); + + to_buffer = aa_get_buffer(false); + from_buffer = aa_get_buffer(false); + error = -ENOMEM; + if (!to_buffer || !from_buffer) + goto out; + error = fn_for_each_confined(label, profile, + match_mnt(subj_cred, profile, to_path, to_buffer, + from_path, from_buffer, + NULL, MS_MOVE, NULL, false)); +out: + aa_put_buffer(to_buffer); + aa_put_buffer(from_buffer); + + return error; +} + +int aa_move_mount_old(const struct cred *subj_cred, struct aa_label *label, + const struct path *path, const char *orig_name) +{ + struct path old_path; + int error; if (!orig_name || !*orig_name) return -EINVAL; - error = kern_path(orig_name, LOOKUP_FOLLOW, &old_path); if (error) return error; - buffer = aa_get_buffer(false); - old_buffer = aa_get_buffer(false); - error = -ENOMEM; - if (!buffer || !old_buffer) - goto out; - error = fn_for_each_confined(label, profile, - match_mnt(profile, path, buffer, &old_path, old_buffer, - NULL, MS_MOVE, NULL, false)); -out: - aa_put_buffer(buffer); - aa_put_buffer(old_buffer); + error = aa_move_mount(subj_cred, label, &old_path, path); path_put(&old_path); return error; } -int aa_new_mount(struct aa_label *label, const char *dev_name, - const struct path *path, const char *type, unsigned long flags, - void *data) +int aa_new_mount(const struct cred *subj_cred, struct aa_label *label, + const char *dev_name, const struct path *path, + const char *type, unsigned long flags, void *data) { struct aa_profile *profile; char *buffer = NULL, *dev_buffer = NULL; @@ -549,12 +575,14 @@ int aa_new_mount(struct aa_label *label, const char *dev_name, goto out; } error = fn_for_each_confined(label, profile, - match_mnt(profile, path, buffer, dev_path, dev_buffer, + match_mnt(subj_cred, profile, path, buffer, + dev_path, dev_buffer, type, flags, data, binary)); } else { error = fn_for_each_confined(label, profile, - match_mnt_path_str(profile, path, buffer, dev_name, - type, flags, data, binary, NULL)); + match_mnt_path_str(subj_cred, profile, path, + buffer, dev_name, + type, flags, data, binary, NULL)); } out: @@ -566,7 +594,8 @@ int aa_new_mount(struct aa_label *label, const char *dev_name, return error; } -static int profile_umount(struct aa_profile *profile, const struct path *path, +static int profile_umount(const struct cred *subj_cred, + struct aa_profile *profile, const struct path *path, char *buffer) { struct aa_ruleset *rules = list_first_entry(&profile->rules, @@ -595,11 +624,13 @@ static int profile_umount(struct aa_profile *profile, const struct path *path, error = -EACCES; audit: - return audit_mount(profile, OP_UMOUNT, name, NULL, NULL, NULL, 0, NULL, + return audit_mount(subj_cred, profile, OP_UMOUNT, name, NULL, NULL, + NULL, 0, NULL, AA_MAY_UMOUNT, &perms, info, error); } -int aa_umount(struct aa_label *label, struct vfsmount *mnt, int flags) +int aa_umount(const struct cred *subj_cred, struct aa_label *label, + struct vfsmount *mnt, int flags) { struct aa_profile *profile; char *buffer = NULL; @@ -614,7 +645,7 @@ int aa_umount(struct aa_label *label, struct vfsmount *mnt, int flags) return -ENOMEM; error = fn_for_each_confined(label, profile, - profile_umount(profile, &path, buffer)); + profile_umount(subj_cred, profile, &path, buffer)); aa_put_buffer(buffer); return error; @@ -624,7 +655,8 @@ int aa_umount(struct aa_label *label, struct vfsmount *mnt, int flags) * * Returns: label for transition or ERR_PTR. Does not return NULL */ -static struct aa_label *build_pivotroot(struct aa_profile *profile, +static struct aa_label *build_pivotroot(const struct cred *subj_cred, + struct aa_profile *profile, const struct path *new_path, char *new_buffer, const struct path *old_path, @@ -669,7 +701,8 @@ static struct aa_label *build_pivotroot(struct aa_profile *profile, error = 0; audit: - error = audit_mount(profile, OP_PIVOTROOT, new_name, old_name, + error = audit_mount(subj_cred, profile, OP_PIVOTROOT, new_name, + old_name, NULL, trans_name, 0, NULL, AA_MAY_PIVOTROOT, &perms, info, error); if (error) @@ -678,7 +711,8 @@ static struct aa_label *build_pivotroot(struct aa_profile *profile, return aa_get_newest_label(&profile->label); } -int aa_pivotroot(struct aa_label *label, const struct path *old_path, +int aa_pivotroot(const struct cred *subj_cred, struct aa_label *label, + const struct path *old_path, const struct path *new_path) { struct aa_profile *profile; @@ -696,7 +730,8 @@ int aa_pivotroot(struct aa_label *label, const struct path *old_path, if (!old_buffer || !new_buffer) goto out; target = fn_label_build(label, profile, GFP_KERNEL, - build_pivotroot(profile, new_path, new_buffer, + build_pivotroot(subj_cred, profile, new_path, + new_buffer, old_path, old_buffer)); if (!target) { info = "label build failed"; @@ -722,7 +757,8 @@ int aa_pivotroot(struct aa_label *label, const struct path *old_path, fail: /* TODO: add back in auditing of new_name and old_name */ error = fn_for_each(label, profile, - audit_mount(profile, OP_PIVOTROOT, NULL /*new_name */, + audit_mount(subj_cred, profile, OP_PIVOTROOT, + NULL /*new_name */, NULL /* old_name */, NULL, NULL, 0, NULL, AA_MAY_PIVOTROOT, &nullperms, info, diff --git a/security/apparmor/net.c b/security/apparmor/net.c index 788be1609a865..704c171232ab4 100644 --- a/security/apparmor/net.c +++ b/security/apparmor/net.c @@ -71,6 +71,7 @@ static const char * const net_mask_names[] = { void audit_net_cb(struct audit_buffer *ab, void *va) { struct common_audit_data *sa = va; + struct apparmor_audit_data *ad = aad(sa); if (address_family_names[sa->u.net->family]) audit_log_format(ab, " family=\"%s\"", @@ -78,35 +79,36 @@ void audit_net_cb(struct audit_buffer *ab, void *va) else audit_log_format(ab, " family=\"unknown(%d)\"", sa->u.net->family); - if (sock_type_names[aad(sa)->net.type]) + if (sock_type_names[ad->net.type]) audit_log_format(ab, " sock_type=\"%s\"", - sock_type_names[aad(sa)->net.type]); + sock_type_names[ad->net.type]); else audit_log_format(ab, " sock_type=\"unknown(%d)\"", - aad(sa)->net.type); - audit_log_format(ab, " protocol=%d", aad(sa)->net.protocol); + ad->net.type); + audit_log_format(ab, " protocol=%d", ad->net.protocol); - if (aad(sa)->request & NET_PERMS_MASK) { + if (ad->request & NET_PERMS_MASK) { audit_log_format(ab, " requested_mask="); - aa_audit_perm_mask(ab, aad(sa)->request, NULL, 0, + aa_audit_perm_mask(ab, ad->request, NULL, 0, net_mask_names, NET_PERMS_MASK); - if (aad(sa)->denied & NET_PERMS_MASK) { + if (ad->denied & NET_PERMS_MASK) { audit_log_format(ab, " denied_mask="); - aa_audit_perm_mask(ab, aad(sa)->denied, NULL, 0, + aa_audit_perm_mask(ab, ad->denied, NULL, 0, net_mask_names, NET_PERMS_MASK); } } - if (aad(sa)->peer) { + if (ad->peer) { audit_log_format(ab, " peer="); - aa_label_xaudit(ab, labels_ns(aad(sa)->label), aad(sa)->peer, + aa_label_xaudit(ab, labels_ns(ad->subj_label), ad->peer, FLAGS_NONE, GFP_ATOMIC); } } /* Generic af perm */ -int aa_profile_af_perm(struct aa_profile *profile, struct common_audit_data *sa, - u32 request, u16 family, int type) +int aa_profile_af_perm(struct aa_profile *profile, + struct apparmor_audit_data *ad, u32 request, u16 family, + int type) { struct aa_ruleset *rules = list_first_entry(&profile->rules, typeof(*rules), list); @@ -130,21 +132,23 @@ int aa_profile_af_perm(struct aa_profile *profile, struct common_audit_data *sa, perms = *aa_lookup_perms(&rules->policy, state); aa_apply_modes_to_perms(profile, &perms); - return aa_check_perms(profile, &perms, request, sa, audit_net_cb); + return aa_check_perms(profile, &perms, request, ad, audit_net_cb); } -int aa_af_perm(struct aa_label *label, const char *op, u32 request, u16 family, - int type, int protocol) +int aa_af_perm(const struct cred *subj_cred, struct aa_label *label, + const char *op, u32 request, u16 family, int type, int protocol) { struct aa_profile *profile; - DEFINE_AUDIT_NET(sa, op, NULL, family, type, protocol); + DEFINE_AUDIT_NET(ad, op, NULL, family, type, protocol); return fn_for_each_confined(label, profile, - aa_profile_af_perm(profile, &sa, request, family, + aa_profile_af_perm(profile, &ad, request, family, type)); } -static int aa_label_sk_perm(struct aa_label *label, const char *op, u32 request, +static int aa_label_sk_perm(const struct cred *subj_cred, + struct aa_label *label, + const char *op, u32 request, struct sock *sk) { struct aa_sk_ctx *ctx = SK_CTX(sk); @@ -155,10 +159,11 @@ static int aa_label_sk_perm(struct aa_label *label, const char *op, u32 request, if (ctx->label != kernel_t && !unconfined(label)) { struct aa_profile *profile; - DEFINE_AUDIT_SK(sa, op, sk); + DEFINE_AUDIT_SK(ad, op, sk); + ad.subj_cred = subj_cred; error = fn_for_each_confined(label, profile, - aa_profile_af_sk_perm(profile, &sa, request, sk)); + aa_profile_af_sk_perm(profile, &ad, request, sk)); } return error; @@ -174,21 +179,21 @@ int aa_sk_perm(const char *op, u32 request, struct sock *sk) /* TODO: switch to begin_current_label ???? */ label = begin_current_label_crit_section(); - error = aa_label_sk_perm(label, op, request, sk); + error = aa_label_sk_perm(current_cred(), label, op, request, sk); end_current_label_crit_section(label); return error; } -int aa_sock_file_perm(struct aa_label *label, const char *op, u32 request, - struct socket *sock) +int aa_sock_file_perm(const struct cred *subj_cred, struct aa_label *label, + const char *op, u32 request, struct socket *sock) { AA_BUG(!label); AA_BUG(!sock); AA_BUG(!sock->sk); - return aa_label_sk_perm(label, op, request, sock->sk); + return aa_label_sk_perm(subj_cred, label, op, request, sock->sk); } #ifdef CONFIG_NETWORK_SECMARK @@ -214,7 +219,7 @@ static int apparmor_secmark_init(struct aa_secmark *secmark) } static int aa_secmark_perm(struct aa_profile *profile, u32 request, u32 secid, - struct common_audit_data *sa) + struct apparmor_audit_data *ad) { int i, ret; struct aa_perms perms = { }; @@ -245,17 +250,17 @@ static int aa_secmark_perm(struct aa_profile *profile, u32 request, u32 secid, aa_apply_modes_to_perms(profile, &perms); - return aa_check_perms(profile, &perms, request, sa, audit_net_cb); + return aa_check_perms(profile, &perms, request, ad, audit_net_cb); } int apparmor_secmark_check(struct aa_label *label, char *op, u32 request, u32 secid, const struct sock *sk) { struct aa_profile *profile; - DEFINE_AUDIT_SK(sa, op, sk); + DEFINE_AUDIT_SK(ad, op, sk); return fn_for_each_confined(label, profile, aa_secmark_perm(profile, request, secid, - &sa)); + &ad)); } #endif diff --git a/security/apparmor/policy.c b/security/apparmor/policy.c index ec695a6caac7d..8a07793ce1032 100644 --- a/security/apparmor/policy.c +++ b/security/apparmor/policy.c @@ -286,6 +286,7 @@ void aa_free_profile(struct aa_profile *profile) /** * aa_alloc_profile - allocate, initialize and return a new profile * @hname: name of the profile (NOT NULL) + * @proxy: proxy to use OR null if to allocate a new one * @gfp: allocation type * * Returns: refcount profile or NULL on failure @@ -722,16 +723,17 @@ static int replacement_allowed(struct aa_profile *profile, int noreplace, static void audit_cb(struct audit_buffer *ab, void *va) { struct common_audit_data *sa = va; + struct apparmor_audit_data *ad = aad(sa); - if (aad(sa)->iface.ns) { + if (ad->iface.ns) { audit_log_format(ab, " ns="); - audit_log_untrustedstring(ab, aad(sa)->iface.ns); + audit_log_untrustedstring(ab, ad->iface.ns); } } /** * audit_policy - Do auditing of policy changes - * @label: label to check if it can manage policy + * @subj_label: label to check if it can manage policy * @op: policy operation being performed * @ns_name: name of namespace being manipulated * @name: name of profile being manipulated (NOT NULL) @@ -740,19 +742,19 @@ static void audit_cb(struct audit_buffer *ab, void *va) * * Returns: the error to be returned after audit is done */ -static int audit_policy(struct aa_label *label, const char *op, +static int audit_policy(struct aa_label *subj_label, const char *op, const char *ns_name, const char *name, const char *info, int error) { - DEFINE_AUDIT_DATA(sa, LSM_AUDIT_DATA_NONE, AA_CLASS_NONE, op); + DEFINE_AUDIT_DATA(ad, LSM_AUDIT_DATA_NONE, AA_CLASS_NONE, op); - aad(&sa)->iface.ns = ns_name; - aad(&sa)->name = name; - aad(&sa)->info = info; - aad(&sa)->error = error; - aad(&sa)->label = label; + ad.iface.ns = ns_name; + ad.name = name; + ad.info = info; + ad.error = error; + ad.subj_label = subj_label; - aa_audit_msg(AUDIT_APPARMOR_STATUS, &sa, audit_cb); + aa_audit_msg(AUDIT_APPARMOR_STATUS, &ad, audit_cb); return error; } @@ -760,31 +762,35 @@ static int audit_policy(struct aa_label *label, const char *op, /* don't call out to other LSMs in the stack for apparmor policy admin * permissions */ -static int policy_ns_capable(struct aa_label *label, +static int policy_ns_capable(const struct cred *subj_cred, + struct aa_label *label, struct user_namespace *userns, int cap) { int err; /* check for MAC_ADMIN cap in cred */ - err = cap_capable(current_cred(), userns, cap, CAP_OPT_NONE); + err = cap_capable(subj_cred, userns, cap, CAP_OPT_NONE); if (!err) - err = aa_capable(label, cap, CAP_OPT_NONE); + err = aa_capable(subj_cred, label, cap, CAP_OPT_NONE); return err; } /** * aa_policy_view_capable - check if viewing policy in at @ns is allowed - * label: label that is trying to view policy in ns - * ns: namespace being viewed by @label (may be NULL if @label's ns) + * @subj_cred: cred of subject + * @label: label that is trying to view policy in ns + * @ns: namespace being viewed by @label (may be NULL if @label's ns) + * * Returns: true if viewing policy is allowed * * If @ns is NULL then the namespace being viewed is assumed to be the * tasks current namespace. */ -bool aa_policy_view_capable(struct aa_label *label, struct aa_ns *ns) +bool aa_policy_view_capable(const struct cred *subj_cred, + struct aa_label *label, struct aa_ns *ns) { - struct user_namespace *user_ns = current_user_ns(); + struct user_namespace *user_ns = subj_cred->user_ns; struct aa_ns *view_ns = labels_view(label); bool root_in_user_ns = uid_eq(current_euid(), make_kuid(user_ns, 0)) || in_egroup_p(make_kgid(user_ns, 0)); @@ -801,15 +807,17 @@ bool aa_policy_view_capable(struct aa_label *label, struct aa_ns *ns) return response; } -bool aa_policy_admin_capable(struct aa_label *label, struct aa_ns *ns) +bool aa_policy_admin_capable(const struct cred *subj_cred, + struct aa_label *label, struct aa_ns *ns) { - struct user_namespace *user_ns = current_user_ns(); - bool capable = policy_ns_capable(label, user_ns, CAP_MAC_ADMIN) == 0; + struct user_namespace *user_ns = subj_cred->user_ns; + bool capable = policy_ns_capable(subj_cred, label, user_ns, + CAP_MAC_ADMIN) == 0; AA_DEBUG("cap_mac_admin? %d\n", capable); AA_DEBUG("policy locked? %d\n", aa_g_lock_policy); - return aa_policy_view_capable(label, ns) && capable && + return aa_policy_view_capable(subj_cred, label, ns) && capable && !aa_g_lock_policy; } @@ -819,7 +827,7 @@ bool aa_current_policy_view_capable(struct aa_ns *ns) bool res; label = __begin_current_label_crit_section(); - res = aa_policy_view_capable(label, ns); + res = aa_policy_view_capable(current_cred(), label, ns); __end_current_label_crit_section(label); return res; @@ -831,7 +839,7 @@ bool aa_current_policy_admin_capable(struct aa_ns *ns) bool res; label = __begin_current_label_crit_section(); - res = aa_policy_admin_capable(label, ns); + res = aa_policy_admin_capable(current_cred(), label, ns); __end_current_label_crit_section(label); return res; @@ -839,12 +847,15 @@ bool aa_current_policy_admin_capable(struct aa_ns *ns) /** * aa_may_manage_policy - can the current task manage policy + * @subj_cred; subjects cred * @label: label to check if it can manage policy + * @ns: namespace being managed by @label (may be NULL if @label's ns) * @mask: contains the policy manipulation operation being done * * Returns: 0 if the task is allowed to manipulate policy else error */ -int aa_may_manage_policy(struct aa_label *label, struct aa_ns *ns, u32 mask) +int aa_may_manage_policy(const struct cred *subj_cred, struct aa_label *label, + struct aa_ns *ns, u32 mask) { const char *op; @@ -860,7 +871,7 @@ int aa_may_manage_policy(struct aa_label *label, struct aa_ns *ns, u32 mask) return audit_policy(label, op, NULL, NULL, "policy_locked", -EACCES); - if (!aa_policy_admin_capable(label, ns)) + if (!aa_policy_admin_capable(subj_cred, label, ns)) return audit_policy(label, op, NULL, NULL, "not policy admin", -EACCES); @@ -951,11 +962,11 @@ static void __replace_profile(struct aa_profile *old, struct aa_profile *new) /** * __lookup_replace - lookup replacement information for a profile - * @ns - namespace the lookup occurs in - * @hname - name of profile to lookup - * @noreplace - true if not replacing an existing profile - * @p - Returns: profile to be replaced - * @info - Returns: info string on why lookup failed + * @ns: namespace the lookup occurs in + * @hname: name of profile to lookup + * @noreplace: true if not replacing an existing profile + * @p: Returns - profile to be replaced + * @info: Returns - info string on why lookup failed * * Returns: profile to replace (no ref) on success else ptr error */ diff --git a/security/apparmor/policy_unpack.c b/security/apparmor/policy_unpack.c index b49201306753c..dbc83455d900e 100644 --- a/security/apparmor/policy_unpack.c +++ b/security/apparmor/policy_unpack.c @@ -34,17 +34,18 @@ static void audit_cb(struct audit_buffer *ab, void *va) { struct common_audit_data *sa = va; + struct apparmor_audit_data *ad = aad(sa); - if (aad(sa)->iface.ns) { + if (ad->iface.ns) { audit_log_format(ab, " ns="); - audit_log_untrustedstring(ab, aad(sa)->iface.ns); + audit_log_untrustedstring(ab, ad->iface.ns); } - if (aad(sa)->name) { + if (ad->name) { audit_log_format(ab, " name="); - audit_log_untrustedstring(ab, aad(sa)->name); + audit_log_untrustedstring(ab, ad->name); } - if (aad(sa)->iface.pos) - audit_log_format(ab, " offset=%ld", aad(sa)->iface.pos); + if (ad->iface.pos) + audit_log_format(ab, " offset=%ld", ad->iface.pos); } /** @@ -63,18 +64,18 @@ static int audit_iface(struct aa_profile *new, const char *ns_name, int error) { struct aa_profile *profile = labels_profile(aa_current_raw_label()); - DEFINE_AUDIT_DATA(sa, LSM_AUDIT_DATA_NONE, AA_CLASS_NONE, NULL); + DEFINE_AUDIT_DATA(ad, LSM_AUDIT_DATA_NONE, AA_CLASS_NONE, NULL); if (e) - aad(&sa)->iface.pos = e->pos - e->start; - aad(&sa)->iface.ns = ns_name; + ad.iface.pos = e->pos - e->start; + ad.iface.ns = ns_name; if (new) - aad(&sa)->name = new->base.hname; + ad.name = new->base.hname; else - aad(&sa)->name = name; - aad(&sa)->info = info; - aad(&sa)->error = error; + ad.name = name; + ad.info = info; + ad.error = error; - return aa_audit(AUDIT_APPARMOR_STATUS, profile, &sa, audit_cb); + return aa_audit(AUDIT_APPARMOR_STATUS, profile, &ad, audit_cb); } void __aa_loaddata_update(struct aa_loaddata *data, long revision) diff --git a/security/apparmor/resource.c b/security/apparmor/resource.c index e859481648962..dcc94c3153d51 100644 --- a/security/apparmor/resource.c +++ b/security/apparmor/resource.c @@ -30,18 +30,20 @@ struct aa_sfs_entry aa_sfs_entry_rlimit[] = { static void audit_cb(struct audit_buffer *ab, void *va) { struct common_audit_data *sa = va; + struct apparmor_audit_data *ad = aad(sa); audit_log_format(ab, " rlimit=%s value=%lu", - rlim_names[aad(sa)->rlim.rlim], aad(sa)->rlim.max); - if (aad(sa)->peer) { + rlim_names[ad->rlim.rlim], ad->rlim.max); + if (ad->peer) { audit_log_format(ab, " peer="); - aa_label_xaudit(ab, labels_ns(aad(sa)->label), aad(sa)->peer, + aa_label_xaudit(ab, labels_ns(ad->subj_label), ad->peer, FLAGS_NONE, GFP_ATOMIC); } } /** * audit_resource - audit setting resource limit + * @subj_cred: cred setting the resource * @profile: profile being enforced (NOT NULL) * @resource: rlimit being auditing * @value: value being set @@ -49,22 +51,24 @@ static void audit_cb(struct audit_buffer *ab, void *va) * @info: info being auditing * @error: error value * - * Returns: 0 or sa->error else other error code on failure + * Returns: 0 or ad->error else other error code on failure */ -static int audit_resource(struct aa_profile *profile, unsigned int resource, +static int audit_resource(const struct cred *subj_cred, + struct aa_profile *profile, unsigned int resource, unsigned long value, struct aa_label *peer, const char *info, int error) { - DEFINE_AUDIT_DATA(sa, LSM_AUDIT_DATA_NONE, AA_CLASS_RLIMITS, + DEFINE_AUDIT_DATA(ad, LSM_AUDIT_DATA_NONE, AA_CLASS_RLIMITS, OP_SETRLIMIT); - aad(&sa)->rlim.rlim = resource; - aad(&sa)->rlim.max = value; - aad(&sa)->peer = peer; - aad(&sa)->info = info; - aad(&sa)->error = error; + ad.subj_cred = subj_cred; + ad.rlim.rlim = resource; + ad.rlim.max = value; + ad.peer = peer; + ad.info = info; + ad.error = error; - return aa_audit(AUDIT_APPARMOR_AUTO, profile, &sa, audit_cb); + return aa_audit(AUDIT_APPARMOR_AUTO, profile, &ad, audit_cb); } /** @@ -81,7 +85,8 @@ int aa_map_resource(int resource) return rlim_map[resource]; } -static int profile_setrlimit(struct aa_profile *profile, unsigned int resource, +static int profile_setrlimit(const struct cred *subj_cred, + struct aa_profile *profile, unsigned int resource, struct rlimit *new_rlim) { struct aa_ruleset *rules = list_first_entry(&profile->rules, @@ -91,22 +96,24 @@ static int profile_setrlimit(struct aa_profile *profile, unsigned int resource, if (rules->rlimits.mask & (1 << resource) && new_rlim->rlim_max > rules->rlimits.limits[resource].rlim_max) e = -EACCES; - return audit_resource(profile, resource, new_rlim->rlim_max, NULL, NULL, - e); + return audit_resource(subj_cred, profile, resource, new_rlim->rlim_max, + NULL, NULL, e); } /** * aa_task_setrlimit - test permission to set an rlimit - * @label - label confining the task (NOT NULL) - * @task - task the resource is being set on - * @resource - the resource being set - * @new_rlim - the new resource limit (NOT NULL) + * @subj_cred: cred setting the limit + * @label: label confining the task (NOT NULL) + * @task: task the resource is being set on + * @resource: the resource being set + * @new_rlim: the new resource limit (NOT NULL) * * Control raising the processes hard limit. * * Returns: 0 or error code if setting resource failed */ -int aa_task_setrlimit(struct aa_label *label, struct task_struct *task, +int aa_task_setrlimit(const struct cred *subj_cred, struct aa_label *label, + struct task_struct *task, unsigned int resource, struct rlimit *new_rlim) { struct aa_profile *profile; @@ -125,14 +132,15 @@ int aa_task_setrlimit(struct aa_label *label, struct task_struct *task, */ if (label != peer && - aa_capable(label, CAP_SYS_RESOURCE, CAP_OPT_NOAUDIT) != 0) + aa_capable(subj_cred, label, CAP_SYS_RESOURCE, CAP_OPT_NOAUDIT) != 0) error = fn_for_each(label, profile, - audit_resource(profile, resource, + audit_resource(subj_cred, profile, resource, new_rlim->rlim_max, peer, "cap_sys_resource", -EACCES)); else error = fn_for_each_confined(label, profile, - profile_setrlimit(profile, resource, new_rlim)); + profile_setrlimit(subj_cred, profile, resource, + new_rlim)); aa_put_label(peer); return error; diff --git a/security/apparmor/task.c b/security/apparmor/task.c index 84d16a29bfcbc..0d7af707cccdd 100644 --- a/security/apparmor/task.c +++ b/security/apparmor/task.c @@ -208,70 +208,75 @@ static const char *audit_ptrace_mask(u32 mask) static void audit_ptrace_cb(struct audit_buffer *ab, void *va) { struct common_audit_data *sa = va; + struct apparmor_audit_data *ad = aad(sa); - if (aad(sa)->request & AA_PTRACE_PERM_MASK) { + if (ad->request & AA_PTRACE_PERM_MASK) { audit_log_format(ab, " requested_mask=\"%s\"", - audit_ptrace_mask(aad(sa)->request)); + audit_ptrace_mask(ad->request)); - if (aad(sa)->denied & AA_PTRACE_PERM_MASK) { + if (ad->denied & AA_PTRACE_PERM_MASK) { audit_log_format(ab, " denied_mask=\"%s\"", - audit_ptrace_mask(aad(sa)->denied)); + audit_ptrace_mask(ad->denied)); } } audit_log_format(ab, " peer="); - aa_label_xaudit(ab, labels_ns(aad(sa)->label), aad(sa)->peer, + aa_label_xaudit(ab, labels_ns(ad->subj_label), ad->peer, FLAGS_NONE, GFP_ATOMIC); } /* assumes check for RULE_MEDIATES is already done */ /* TODO: conditionals */ -static int profile_ptrace_perm(struct aa_profile *profile, - struct aa_label *peer, u32 request, - struct common_audit_data *sa) +static int profile_ptrace_perm(const struct cred *cred, + struct aa_profile *profile, + struct aa_label *peer, u32 request, + struct apparmor_audit_data *ad) { struct aa_ruleset *rules = list_first_entry(&profile->rules, typeof(*rules), list); struct aa_perms perms = { }; - aad(sa)->peer = peer; + ad->subj_cred = cred; + ad->peer = peer; aa_profile_match_label(profile, rules, peer, AA_CLASS_PTRACE, request, &perms); aa_apply_modes_to_perms(profile, &perms); - return aa_check_perms(profile, &perms, request, sa, audit_ptrace_cb); + return aa_check_perms(profile, &perms, request, ad, audit_ptrace_cb); } -static int profile_tracee_perm(struct aa_profile *tracee, +static int profile_tracee_perm(const struct cred *cred, + struct aa_profile *tracee, struct aa_label *tracer, u32 request, - struct common_audit_data *sa) + struct apparmor_audit_data *ad) { if (profile_unconfined(tracee) || unconfined(tracer) || !ANY_RULE_MEDIATES(&tracee->rules, AA_CLASS_PTRACE)) return 0; - return profile_ptrace_perm(tracee, tracer, request, sa); + return profile_ptrace_perm(cred, tracee, tracer, request, ad); } -static int profile_tracer_perm(struct aa_profile *tracer, +static int profile_tracer_perm(const struct cred *cred, + struct aa_profile *tracer, struct aa_label *tracee, u32 request, - struct common_audit_data *sa) + struct apparmor_audit_data *ad) { if (profile_unconfined(tracer)) return 0; if (ANY_RULE_MEDIATES(&tracer->rules, AA_CLASS_PTRACE)) - return profile_ptrace_perm(tracer, tracee, request, sa); + return profile_ptrace_perm(cred, tracer, tracee, request, ad); /* profile uses the old style capability check for ptrace */ if (&tracer->label == tracee) return 0; - aad(sa)->label = &tracer->label; - aad(sa)->peer = tracee; - aad(sa)->request = 0; - aad(sa)->error = aa_capable(&tracer->label, CAP_SYS_PTRACE, - CAP_OPT_NONE); + ad->subj_label = &tracer->label; + ad->peer = tracee; + ad->request = 0; + ad->error = aa_capable(cred, &tracer->label, CAP_SYS_PTRACE, + CAP_OPT_NONE); - return aa_audit(AUDIT_APPARMOR_AUTO, tracer, sa, audit_ptrace_cb); + return aa_audit(AUDIT_APPARMOR_AUTO, tracer, ad, audit_ptrace_cb); } /** @@ -282,7 +287,8 @@ static int profile_tracer_perm(struct aa_profile *tracer, * * Returns: %0 else error code if permission denied or error */ -int aa_may_ptrace(struct aa_label *tracer, struct aa_label *tracee, +int aa_may_ptrace(const struct cred *tracer_cred, struct aa_label *tracer, + const struct cred *tracee_cred, struct aa_label *tracee, u32 request) { struct aa_profile *profile; @@ -290,6 +296,8 @@ int aa_may_ptrace(struct aa_label *tracer, struct aa_label *tracee, DEFINE_AUDIT_DATA(sa, LSM_AUDIT_DATA_NONE, AA_CLASS_PTRACE, OP_PTRACE); return xcheck_labels(tracer, tracee, profile, - profile_tracer_perm(profile, tracee, request, &sa), - profile_tracee_perm(profile, tracer, xrequest, &sa)); + profile_tracer_perm(tracer_cred, profile, tracee, + request, &sa), + profile_tracee_perm(tracee_cred, profile, tracer, + xrequest, &sa)); } diff --git a/security/integrity/Kconfig b/security/integrity/Kconfig index 232191ee09e31..b6e074ac02273 100644 --- a/security/integrity/Kconfig +++ b/security/integrity/Kconfig @@ -68,8 +68,6 @@ config INTEGRITY_MACHINE_KEYRING depends on INTEGRITY_ASYMMETRIC_KEYS depends on SYSTEM_BLACKLIST_KEYRING depends on LOAD_UEFI_KEYS || LOAD_PPC_KEYS - select INTEGRITY_CA_MACHINE_KEYRING if LOAD_PPC_KEYS - select INTEGRITY_CA_MACHINE_KEYRING_MAX if LOAD_PPC_KEYS help If set, provide a keyring to which Machine Owner Keys (MOK) may be added. This keyring shall contain just MOK keys. Unlike keys diff --git a/security/integrity/iint.c b/security/integrity/iint.c index a462df827de2d..27ea19fb1f54c 100644 --- a/security/integrity/iint.c +++ b/security/integrity/iint.c @@ -66,9 +66,32 @@ struct integrity_iint_cache *integrity_iint_find(struct inode *inode) return iint; } -static void iint_free(struct integrity_iint_cache *iint) +#define IMA_MAX_NESTING (FILESYSTEM_MAX_STACK_DEPTH+1) + +/* + * It is not clear that IMA should be nested at all, but as long is it measures + * files both on overlayfs and on underlying fs, we need to annotate the iint + * mutex to avoid lockdep false positives related to IMA + overlayfs. + * See ovl_lockdep_annotate_inode_mutex_key() for more details. + */ +static inline void iint_lockdep_annotate(struct integrity_iint_cache *iint, + struct inode *inode) +{ +#ifdef CONFIG_LOCKDEP + static struct lock_class_key iint_mutex_key[IMA_MAX_NESTING]; + + int depth = inode->i_sb->s_stack_depth; + + if (WARN_ON_ONCE(depth < 0 || depth >= IMA_MAX_NESTING)) + depth = 0; + + lockdep_set_class(&iint->mutex, &iint_mutex_key[depth]); +#endif +} + +static void iint_init_always(struct integrity_iint_cache *iint, + struct inode *inode) { - kfree(iint->ima_hash); iint->ima_hash = NULL; iint->version = 0; iint->flags = 0UL; @@ -80,6 +103,14 @@ static void iint_free(struct integrity_iint_cache *iint) iint->ima_creds_status = INTEGRITY_UNKNOWN; iint->evm_status = INTEGRITY_UNKNOWN; iint->measured_pcrs = 0; + mutex_init(&iint->mutex); + iint_lockdep_annotate(iint, inode); +} + +static void iint_free(struct integrity_iint_cache *iint) +{ + kfree(iint->ima_hash); + mutex_destroy(&iint->mutex); kmem_cache_free(iint_cache, iint); } @@ -104,6 +135,8 @@ struct integrity_iint_cache *integrity_inode_get(struct inode *inode) if (!iint) return NULL; + iint_init_always(iint, inode); + write_lock(&integrity_iint_lock); p = &integrity_iint_tree.rb_node; @@ -153,25 +186,18 @@ void integrity_inode_free(struct inode *inode) iint_free(iint); } -static void init_once(void *foo) +static void iint_init_once(void *foo) { struct integrity_iint_cache *iint = (struct integrity_iint_cache *) foo; memset(iint, 0, sizeof(*iint)); - iint->ima_file_status = INTEGRITY_UNKNOWN; - iint->ima_mmap_status = INTEGRITY_UNKNOWN; - iint->ima_bprm_status = INTEGRITY_UNKNOWN; - iint->ima_read_status = INTEGRITY_UNKNOWN; - iint->ima_creds_status = INTEGRITY_UNKNOWN; - iint->evm_status = INTEGRITY_UNKNOWN; - mutex_init(&iint->mutex); } static int __init integrity_iintcache_init(void) { iint_cache = kmem_cache_create("iint_cache", sizeof(struct integrity_iint_cache), - 0, SLAB_PANIC, init_once); + 0, SLAB_PANIC, iint_init_once); return 0; } DEFINE_LSM(integrity) = { diff --git a/security/integrity/ima/ima_api.c b/security/integrity/ima/ima_api.c index 452e80b541e54..597ea0c4d72f7 100644 --- a/security/integrity/ima/ima_api.c +++ b/security/integrity/ima/ima_api.c @@ -243,6 +243,7 @@ int ima_collect_measurement(struct integrity_iint_cache *iint, { const char *audit_cause = "failed"; struct inode *inode = file_inode(file); + struct inode *real_inode = d_real_inode(file_dentry(file)); const char *filename = file->f_path.dentry->d_name.name; struct ima_max_digest_data hash; struct kstat stat; @@ -302,6 +303,10 @@ int ima_collect_measurement(struct integrity_iint_cache *iint, iint->ima_hash = tmpbuf; memcpy(iint->ima_hash, &hash, length); iint->version = i_version; + if (real_inode != inode) { + iint->real_ino = real_inode->i_ino; + iint->real_dev = real_inode->i_sb->s_dev; + } /* Possibly temporary failure due to type of read (eg. O_DIRECT) */ if (!result) diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c index 365db0e43d7c2..cc1217ac2c6fa 100644 --- a/security/integrity/ima/ima_main.c +++ b/security/integrity/ima/ima_main.c @@ -25,6 +25,7 @@ #include #include #include +#include #include "ima.h" @@ -207,7 +208,7 @@ static int process_measurement(struct file *file, const struct cred *cred, u32 secid, char *buf, loff_t size, int mask, enum ima_hooks func) { - struct inode *inode = file_inode(file); + struct inode *backing_inode, *inode = file_inode(file); struct integrity_iint_cache *iint = NULL; struct ima_template_desc *template_desc = NULL; char *pathbuf = NULL; @@ -284,6 +285,19 @@ static int process_measurement(struct file *file, const struct cred *cred, iint->measured_pcrs = 0; } + /* Detect and re-evaluate changes made to the backing file. */ + backing_inode = d_real_inode(file_dentry(file)); + if (backing_inode != inode && + (action & IMA_DO_MASK) && (iint->flags & IMA_DONE_MASK)) { + if (!IS_I_VERSION(backing_inode) || + backing_inode->i_sb->s_dev != iint->real_dev || + backing_inode->i_ino != iint->real_ino || + !inode_eq_iversion(backing_inode, iint->version)) { + iint->flags &= ~IMA_DONE_MASK; + iint->measured_pcrs = 0; + } + } + /* Determine if already appraised/measured based on bitmask * (IMA_MEASURE, IMA_MEASURED, IMA_XXXX_APPRAISE, IMA_XXXX_APPRAISED, * IMA_AUDIT, IMA_AUDITED) diff --git a/security/integrity/integrity.h b/security/integrity/integrity.h index d7553c93f5c0d..9561db7cf6b42 100644 --- a/security/integrity/integrity.h +++ b/security/integrity/integrity.h @@ -164,6 +164,8 @@ struct integrity_iint_cache { unsigned long flags; unsigned long measured_pcrs; unsigned long atomic_flags; + unsigned long real_ino; + dev_t real_dev; enum integrity_status ima_file_status:4; enum integrity_status ima_mmap_status:4; enum integrity_status ima_bprm_status:4; diff --git a/security/keys/gc.c b/security/keys/gc.c index 3c90807476eb0..eaddaceda14ea 100644 --- a/security/keys/gc.c +++ b/security/keys/gc.c @@ -66,6 +66,19 @@ void key_schedule_gc(time64_t gc_at) } } +/* + * Set the expiration time on a key. + */ +void key_set_expiry(struct key *key, time64_t expiry) +{ + key->expiry = expiry; + if (expiry != TIME64_MAX) { + if (!(key->type->flags & KEY_TYPE_INSTANT_REAP)) + expiry += key_gc_delay; + key_schedule_gc(expiry); + } +} + /* * Schedule a dead links collection run. */ @@ -176,7 +189,6 @@ static void key_garbage_collector(struct work_struct *work) static u8 gc_state; /* Internal persistent state */ #define KEY_GC_REAP_AGAIN 0x01 /* - Need another cycle */ #define KEY_GC_REAPING_LINKS 0x02 /* - We need to reap links */ -#define KEY_GC_SET_TIMER 0x04 /* - We need to restart the timer */ #define KEY_GC_REAPING_DEAD_1 0x10 /* - We need to mark dead keys */ #define KEY_GC_REAPING_DEAD_2 0x20 /* - We need to reap dead key links */ #define KEY_GC_REAPING_DEAD_3 0x40 /* - We need to reap dead keys */ @@ -184,21 +196,17 @@ static void key_garbage_collector(struct work_struct *work) struct rb_node *cursor; struct key *key; - time64_t new_timer, limit; + time64_t new_timer, limit, expiry; kenter("[%lx,%x]", key_gc_flags, gc_state); limit = ktime_get_real_seconds(); - if (limit > key_gc_delay) - limit -= key_gc_delay; - else - limit = key_gc_delay; /* Work out what we're going to be doing in this pass */ gc_state &= KEY_GC_REAPING_DEAD_1 | KEY_GC_REAPING_DEAD_2; gc_state <<= 1; if (test_and_clear_bit(KEY_GC_KEY_EXPIRED, &key_gc_flags)) - gc_state |= KEY_GC_REAPING_LINKS | KEY_GC_SET_TIMER; + gc_state |= KEY_GC_REAPING_LINKS; if (test_and_clear_bit(KEY_GC_REAP_KEYTYPE, &key_gc_flags)) gc_state |= KEY_GC_REAPING_DEAD_1; @@ -233,8 +241,11 @@ static void key_garbage_collector(struct work_struct *work) } } - if (gc_state & KEY_GC_SET_TIMER) { - if (key->expiry > limit && key->expiry < new_timer) { + expiry = key->expiry; + if (expiry != TIME64_MAX) { + if (!(key->type->flags & KEY_TYPE_INSTANT_REAP)) + expiry += key_gc_delay; + if (expiry > limit && expiry < new_timer) { kdebug("will expire %x in %lld", key_serial(key), key->expiry - limit); new_timer = key->expiry; @@ -276,7 +287,7 @@ static void key_garbage_collector(struct work_struct *work) */ kdebug("pass complete"); - if (gc_state & KEY_GC_SET_TIMER && new_timer != (time64_t)TIME64_MAX) { + if (new_timer != TIME64_MAX) { new_timer += key_gc_delay; key_schedule_gc(new_timer); } diff --git a/security/keys/internal.h b/security/keys/internal.h index 3c1e7122076b9..ec2ec335b6133 100644 --- a/security/keys/internal.h +++ b/security/keys/internal.h @@ -174,6 +174,7 @@ extern unsigned key_gc_delay; extern void keyring_gc(struct key *keyring, time64_t limit); extern void keyring_restriction_gc(struct key *keyring, struct key_type *dead_type); +void key_set_expiry(struct key *key, time64_t expiry); extern void key_schedule_gc(time64_t gc_at); extern void key_schedule_gc_links(void); extern void key_gc_keytype(struct key_type *ktype); @@ -222,10 +223,18 @@ extern struct key *key_get_instantiation_authkey(key_serial_t target_id); */ static inline bool key_is_dead(const struct key *key, time64_t limit) { + time64_t expiry = key->expiry; + + if (expiry != TIME64_MAX) { + if (!(key->type->flags & KEY_TYPE_INSTANT_REAP)) + expiry += key_gc_delay; + if (expiry <= limit) + return true; + } + return key->flags & ((1 << KEY_FLAG_DEAD) | (1 << KEY_FLAG_INVALIDATED)) || - (key->expiry > 0 && key->expiry <= limit) || key->domain_tag->removed; } diff --git a/security/keys/key.c b/security/keys/key.c index 5c0c7df833f8a..5f103b2713c64 100644 --- a/security/keys/key.c +++ b/security/keys/key.c @@ -294,6 +294,7 @@ struct key *key_alloc(struct key_type *type, const char *desc, key->uid = uid; key->gid = gid; key->perm = perm; + key->expiry = TIME64_MAX; key->restrict_link = restrict_link; key->last_used_at = ktime_get_real_seconds(); @@ -463,10 +464,7 @@ static int __key_instantiate_and_link(struct key *key, if (authkey) key_invalidate(authkey); - if (prep->expiry != TIME64_MAX) { - key->expiry = prep->expiry; - key_schedule_gc(prep->expiry + key_gc_delay); - } + key_set_expiry(key, prep->expiry); } } @@ -606,8 +604,7 @@ int key_reject_and_link(struct key *key, atomic_inc(&key->user->nikeys); mark_key_instantiated(key, -error); notify_key(key, NOTIFY_KEY_INSTANTIATED, -error); - key->expiry = ktime_get_real_seconds() + timeout; - key_schedule_gc(key->expiry + key_gc_delay); + key_set_expiry(key, ktime_get_real_seconds() + timeout); if (test_and_clear_bit(KEY_FLAG_USER_CONSTRUCT, &key->flags)) awaken = 1; @@ -722,16 +719,14 @@ struct key_type *key_type_lookup(const char *type) void key_set_timeout(struct key *key, unsigned timeout) { - time64_t expiry = 0; + time64_t expiry = TIME64_MAX; /* make the changes with the locks held to prevent races */ down_write(&key->sem); if (timeout > 0) expiry = ktime_get_real_seconds() + timeout; - - key->expiry = expiry; - key_schedule_gc(key->expiry + key_gc_delay); + key_set_expiry(key, expiry); up_write(&key->sem); } diff --git a/security/keys/proc.c b/security/keys/proc.c index d0cde6685627f..4f4e2c1824f18 100644 --- a/security/keys/proc.c +++ b/security/keys/proc.c @@ -198,7 +198,7 @@ static int proc_keys_show(struct seq_file *m, void *v) /* come up with a suitable timeout value */ expiry = READ_ONCE(key->expiry); - if (expiry == 0) { + if (expiry == TIME64_MAX) { memcpy(xbuf, "perm", 5); } else if (now >= expiry) { memcpy(xbuf, "expd", 5); diff --git a/security/keys/trusted-keys/trusted_core.c b/security/keys/trusted-keys/trusted_core.c index 85fb5c22529a7..fee1ab2c734d3 100644 --- a/security/keys/trusted-keys/trusted_core.c +++ b/security/keys/trusted-keys/trusted_core.c @@ -358,17 +358,17 @@ static int __init init_trusted(void) if (!get_random) get_random = kernel_get_random; - static_call_update(trusted_key_seal, - trusted_key_sources[i].ops->seal); - static_call_update(trusted_key_unseal, - trusted_key_sources[i].ops->unseal); - static_call_update(trusted_key_get_random, - get_random); - trusted_key_exit = trusted_key_sources[i].ops->exit; - migratable = trusted_key_sources[i].ops->migratable; - ret = trusted_key_sources[i].ops->init(); - if (!ret) + if (!ret) { + static_call_update(trusted_key_seal, trusted_key_sources[i].ops->seal); + static_call_update(trusted_key_unseal, trusted_key_sources[i].ops->unseal); + static_call_update(trusted_key_get_random, get_random); + + trusted_key_exit = trusted_key_sources[i].ops->exit; + migratable = trusted_key_sources[i].ops->migratable; + } + + if (!ret || ret != -ENODEV) break; } diff --git a/security/keys/trusted-keys/trusted_tee.c b/security/keys/trusted-keys/trusted_tee.c index ac3e270ade69b..aa3d477de6db5 100644 --- a/security/keys/trusted-keys/trusted_tee.c +++ b/security/keys/trusted-keys/trusted_tee.c @@ -65,24 +65,16 @@ static int trusted_tee_seal(struct trusted_key_payload *p, char *datablob) int ret; struct tee_ioctl_invoke_arg inv_arg; struct tee_param param[4]; - struct tee_shm *reg_shm_in = NULL, *reg_shm_out = NULL; + struct tee_shm *reg_shm = NULL; memset(&inv_arg, 0, sizeof(inv_arg)); memset(¶m, 0, sizeof(param)); - reg_shm_in = tee_shm_register_kernel_buf(pvt_data.ctx, p->key, - p->key_len); - if (IS_ERR(reg_shm_in)) { - dev_err(pvt_data.dev, "key shm register failed\n"); - return PTR_ERR(reg_shm_in); - } - - reg_shm_out = tee_shm_register_kernel_buf(pvt_data.ctx, p->blob, - sizeof(p->blob)); - if (IS_ERR(reg_shm_out)) { - dev_err(pvt_data.dev, "blob shm register failed\n"); - ret = PTR_ERR(reg_shm_out); - goto out; + reg_shm = tee_shm_register_kernel_buf(pvt_data.ctx, p->key, + sizeof(p->key) + sizeof(p->blob)); + if (IS_ERR(reg_shm)) { + dev_err(pvt_data.dev, "shm register failed\n"); + return PTR_ERR(reg_shm); } inv_arg.func = TA_CMD_SEAL; @@ -90,13 +82,13 @@ static int trusted_tee_seal(struct trusted_key_payload *p, char *datablob) inv_arg.num_params = 4; param[0].attr = TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INPUT; - param[0].u.memref.shm = reg_shm_in; + param[0].u.memref.shm = reg_shm; param[0].u.memref.size = p->key_len; param[0].u.memref.shm_offs = 0; param[1].attr = TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT; - param[1].u.memref.shm = reg_shm_out; + param[1].u.memref.shm = reg_shm; param[1].u.memref.size = sizeof(p->blob); - param[1].u.memref.shm_offs = 0; + param[1].u.memref.shm_offs = sizeof(p->key); ret = tee_client_invoke_func(pvt_data.ctx, &inv_arg, param); if ((ret < 0) || (inv_arg.ret != 0)) { @@ -107,11 +99,7 @@ static int trusted_tee_seal(struct trusted_key_payload *p, char *datablob) p->blob_len = param[1].u.memref.size; } -out: - if (reg_shm_out) - tee_shm_free(reg_shm_out); - if (reg_shm_in) - tee_shm_free(reg_shm_in); + tee_shm_free(reg_shm); return ret; } @@ -124,24 +112,16 @@ static int trusted_tee_unseal(struct trusted_key_payload *p, char *datablob) int ret; struct tee_ioctl_invoke_arg inv_arg; struct tee_param param[4]; - struct tee_shm *reg_shm_in = NULL, *reg_shm_out = NULL; + struct tee_shm *reg_shm = NULL; memset(&inv_arg, 0, sizeof(inv_arg)); memset(¶m, 0, sizeof(param)); - reg_shm_in = tee_shm_register_kernel_buf(pvt_data.ctx, p->blob, - p->blob_len); - if (IS_ERR(reg_shm_in)) { - dev_err(pvt_data.dev, "blob shm register failed\n"); - return PTR_ERR(reg_shm_in); - } - - reg_shm_out = tee_shm_register_kernel_buf(pvt_data.ctx, p->key, - sizeof(p->key)); - if (IS_ERR(reg_shm_out)) { - dev_err(pvt_data.dev, "key shm register failed\n"); - ret = PTR_ERR(reg_shm_out); - goto out; + reg_shm = tee_shm_register_kernel_buf(pvt_data.ctx, p->key, + sizeof(p->key) + sizeof(p->blob)); + if (IS_ERR(reg_shm)) { + dev_err(pvt_data.dev, "shm register failed\n"); + return PTR_ERR(reg_shm); } inv_arg.func = TA_CMD_UNSEAL; @@ -149,11 +129,11 @@ static int trusted_tee_unseal(struct trusted_key_payload *p, char *datablob) inv_arg.num_params = 4; param[0].attr = TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INPUT; - param[0].u.memref.shm = reg_shm_in; + param[0].u.memref.shm = reg_shm; param[0].u.memref.size = p->blob_len; - param[0].u.memref.shm_offs = 0; + param[0].u.memref.shm_offs = sizeof(p->key); param[1].attr = TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT; - param[1].u.memref.shm = reg_shm_out; + param[1].u.memref.shm = reg_shm; param[1].u.memref.size = sizeof(p->key); param[1].u.memref.shm_offs = 0; @@ -166,11 +146,7 @@ static int trusted_tee_unseal(struct trusted_key_payload *p, char *datablob) p->key_len = param[1].u.memref.size; } -out: - if (reg_shm_out) - tee_shm_free(reg_shm_out); - if (reg_shm_in) - tee_shm_free(reg_shm_in); + tee_shm_free(reg_shm); return ret; } diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 2aa0e219d7217..208503340721f 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -1660,8 +1660,6 @@ static int inode_has_perm(const struct cred *cred, struct inode_security_struct *isec; u32 sid; - validate_creds(cred); - if (unlikely(IS_PRIVATE(inode))) return 0; @@ -3056,8 +3054,6 @@ static int selinux_inode_follow_link(struct dentry *dentry, struct inode *inode, struct inode_security_struct *isec; u32 sid; - validate_creds(cred); - ad.type = LSM_AUDIT_DATA_DENTRY; ad.u.dentry = dentry; sid = cred_sid(cred); @@ -3101,8 +3097,6 @@ static int selinux_inode_permission(struct inode *inode, int mask) if (!mask) return 0; - validate_creds(cred); - if (unlikely(IS_PRIVATE(inode))) return 0; diff --git a/sound/core/info.c b/sound/core/info.c index 0b2f04dcb5897..e2f302e55bbb2 100644 --- a/sound/core/info.c +++ b/sound/core/info.c @@ -56,7 +56,7 @@ struct snd_info_private_data { }; static int snd_info_version_init(void); -static void snd_info_disconnect(struct snd_info_entry *entry); +static void snd_info_clear_entries(struct snd_info_entry *entry); /* @@ -569,11 +569,16 @@ void snd_info_card_disconnect(struct snd_card *card) { if (!card) return; - mutex_lock(&info_mutex); + proc_remove(card->proc_root_link); - card->proc_root_link = NULL; if (card->proc_root) - snd_info_disconnect(card->proc_root); + proc_remove(card->proc_root->p); + + mutex_lock(&info_mutex); + if (card->proc_root) + snd_info_clear_entries(card->proc_root); + card->proc_root_link = NULL; + card->proc_root = NULL; mutex_unlock(&info_mutex); } @@ -745,15 +750,14 @@ struct snd_info_entry *snd_info_create_card_entry(struct snd_card *card, } EXPORT_SYMBOL(snd_info_create_card_entry); -static void snd_info_disconnect(struct snd_info_entry *entry) +static void snd_info_clear_entries(struct snd_info_entry *entry) { struct snd_info_entry *p; if (!entry->p) return; list_for_each_entry(p, &entry->children, list) - snd_info_disconnect(p); - proc_remove(entry->p); + snd_info_clear_entries(p); entry->p = NULL; } @@ -770,8 +774,9 @@ void snd_info_free_entry(struct snd_info_entry * entry) if (!entry) return; if (entry->p) { + proc_remove(entry->p); mutex_lock(&info_mutex); - snd_info_disconnect(entry); + snd_info_clear_entries(entry); mutex_unlock(&info_mutex); } diff --git a/sound/core/pcm.c b/sound/core/pcm.c index 20bb2d7c8d4bf..6d0c9c37796c2 100644 --- a/sound/core/pcm.c +++ b/sound/core/pcm.c @@ -253,6 +253,7 @@ static const char * const snd_pcm_state_names[] = { STATE(DRAINING), STATE(PAUSED), STATE(SUSPENDED), + STATE(DISCONNECTED), }; static const char * const snd_pcm_access_names[] = { diff --git a/sound/hda/hdac_stream.c b/sound/hda/hdac_stream.c index 2633a4bb1d85d..214a0680524b0 100644 --- a/sound/hda/hdac_stream.c +++ b/sound/hda/hdac_stream.c @@ -354,8 +354,10 @@ struct hdac_stream *snd_hdac_stream_assign(struct hdac_bus *bus, struct hdac_stream *res = NULL; /* make a non-zero unique key for the substream */ - int key = (substream->pcm->device << 16) | (substream->number << 2) | - (substream->stream + 1); + int key = (substream->number << 2) | (substream->stream + 1); + + if (substream->pcm) + key |= (substream->pcm->device << 16); spin_lock_irq(&bus->reg_lock); list_for_each_entry(azx_dev, &bus->stream_list, list) { diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index ca765ac4765f4..75148485b7553 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2218,6 +2218,8 @@ static const struct snd_pci_quirk power_save_denylist[] = { SND_PCI_QUIRK(0x17aa, 0x36a7, "Lenovo C50 All in one", 0), /* https://bugs.launchpad.net/bugs/1821663 */ SND_PCI_QUIRK(0x1631, 0xe017, "Packard Bell NEC IMEDIA 5204", 0), + /* KONTRON SinglePC may cause a stall at runtime resume */ + SND_PCI_QUIRK(0x1734, 0x1232, "KONTRON SinglePC", 0), {} }; #endif /* CONFIG_PM */ diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 1cde2a69bdb4b..78cee53fee02a 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -1993,7 +1993,10 @@ static const struct snd_pci_quirk force_connect_list[] = { SND_PCI_QUIRK(0x103c, 0x871a, "HP", 1), SND_PCI_QUIRK(0x103c, 0x8711, "HP", 1), SND_PCI_QUIRK(0x103c, 0x8715, "HP", 1), + SND_PCI_QUIRK(0x1043, 0x86ae, "ASUS", 1), /* Z170 PRO */ + SND_PCI_QUIRK(0x1043, 0x86c7, "ASUS", 1), /* Z170M PLUS */ SND_PCI_QUIRK(0x1462, 0xec94, "MS-7C94", 1), + SND_PCI_QUIRK(0x8086, 0x2060, "Intel NUC5CPYB", 1), SND_PCI_QUIRK(0x8086, 0x2081, "Intel NUC 10", 1), {} }; diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 3ed2cba5ee8ad..343732c062c70 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -1986,6 +1986,7 @@ enum { ALC887_FIXUP_ASUS_AUDIO, ALC887_FIXUP_ASUS_HMIC, ALCS1200A_FIXUP_MIC_VREF, + ALC888VD_FIXUP_MIC_100VREF, }; static void alc889_fixup_coef(struct hda_codec *codec, @@ -2539,6 +2540,13 @@ static const struct hda_fixup alc882_fixups[] = { {} } }, + [ALC888VD_FIXUP_MIC_100VREF] = { + .type = HDA_FIXUP_PINCTLS, + .v.pins = (const struct hda_pintbl[]) { + { 0x18, PIN_VREF100 }, /* headset mic */ + {} + } + }, }; static const struct snd_pci_quirk alc882_fixup_tbl[] = { @@ -2608,6 +2616,7 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = { SND_PCI_QUIRK(0x106b, 0x4a00, "Macbook 5,2", ALC889_FIXUP_MBA11_VREF), SND_PCI_QUIRK(0x1071, 0x8258, "Evesham Voyaeger", ALC882_FIXUP_EAPD), + SND_PCI_QUIRK(0x10ec, 0x12d8, "iBase Elo Touch", ALC888VD_FIXUP_MIC_100VREF), SND_PCI_QUIRK(0x13fe, 0x1009, "Advantech MIT-W101", ALC886_FIXUP_EAPD), SND_PCI_QUIRK(0x1458, 0xa002, "Gigabyte EP45-DS3/Z87X-UD3H", ALC889_FIXUP_FRONT_HP_NO_PRESENCE), SND_PCI_QUIRK(0x1458, 0xa0b8, "Gigabyte AZ370-Gaming", ALC1220_FIXUP_GB_DUAL_CODECS), @@ -3255,6 +3264,7 @@ static void alc_disable_headset_jack_key(struct hda_codec *codec) case 0x10ec0230: case 0x10ec0236: case 0x10ec0256: + case 0x10ec0257: case 0x19e58326: alc_write_coef_idx(codec, 0x48, 0x0); alc_update_coef_idx(codec, 0x49, 0x0045, 0x0); @@ -3284,6 +3294,7 @@ static void alc_enable_headset_jack_key(struct hda_codec *codec) case 0x10ec0230: case 0x10ec0236: case 0x10ec0256: + case 0x10ec0257: case 0x19e58326: alc_write_coef_idx(codec, 0x48, 0xd011); alc_update_coef_idx(codec, 0x49, 0x007f, 0x0045); @@ -6495,6 +6506,7 @@ static void alc_combo_jack_hp_jd_restart(struct hda_codec *codec) case 0x10ec0236: case 0x10ec0255: case 0x10ec0256: + case 0x10ec0257: case 0x19e58326: alc_update_coef_idx(codec, 0x1b, 0x8000, 1 << 15); /* Reset HP JD */ alc_update_coef_idx(codec, 0x1b, 0x8000, 0 << 15); @@ -7366,6 +7378,7 @@ enum { ALC287_FIXUP_MG_RTKC_CSAMP_CS35L41_I2C_THINKPAD, ALC2XX_FIXUP_HEADSET_MIC, ALC289_FIXUP_DELL_CS35L41_SPI_2, + ALC294_FIXUP_CS35L41_I2C_2, }; /* A special fixup for Lenovo C940 and Yoga Duet 7; @@ -9495,6 +9508,10 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC289_FIXUP_DUAL_SPK }, + [ALC294_FIXUP_CS35L41_I2C_2] = { + .type = HDA_FIXUP_FUNC, + .v.func = cs35l41_fixup_i2c_two, + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -9598,6 +9615,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x0b1a, "Dell Precision 5570", ALC289_FIXUP_DUAL_SPK), SND_PCI_QUIRK(0x1028, 0x0b37, "Dell Inspiron 16 Plus 7620 2-in-1", ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS), SND_PCI_QUIRK(0x1028, 0x0b71, "Dell Inspiron 16 Plus 7620", ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS), + SND_PCI_QUIRK(0x1028, 0x0beb, "Dell XPS 15 9530 (2023)", ALC289_FIXUP_DELL_CS35L41_SPI_2), SND_PCI_QUIRK(0x1028, 0x0c03, "Dell Precision 5340", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x0c19, "Dell Precision 3340", ALC236_FIXUP_DELL_DUAL_CODECS), SND_PCI_QUIRK(0x1028, 0x0c1a, "Dell Precision 3340", ALC236_FIXUP_DELL_DUAL_CODECS), @@ -9687,6 +9705,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x83b9, "HP Spectre x360", ALC269_FIXUP_HP_MUTE_LED_MIC3), SND_PCI_QUIRK(0x103c, 0x841c, "HP Pavilion 15-CK0xx", ALC269_FIXUP_HP_MUTE_LED_MIC3), SND_PCI_QUIRK(0x103c, 0x8497, "HP Envy x360", ALC269_FIXUP_HP_MUTE_LED_MIC3), + SND_PCI_QUIRK(0x103c, 0x84ae, "HP 15-db0403ng", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x84da, "HP OMEN dc0019-ur", ALC295_FIXUP_HP_OMEN), SND_PCI_QUIRK(0x103c, 0x84e7, "HP Pavilion 15", ALC269_FIXUP_HP_MUTE_LED_MIC3), SND_PCI_QUIRK(0x103c, 0x8519, "HP Spectre x360 15-df0xxx", ALC285_FIXUP_HP_SPECTRE_X360), @@ -9746,6 +9765,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8898, "HP EliteBook 845 G8 Notebook PC", ALC285_FIXUP_HP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x103c, 0x88d0, "HP Pavilion 15-eh1xxx (mainboard 88D0)", ALC287_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8902, "HP OMEN 16", ALC285_FIXUP_HP_MUTE_LED), + SND_PCI_QUIRK(0x103c, 0x890e, "HP 255 G8 Notebook PC", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x8919, "HP Pavilion Aero Laptop 13-be0xxx", ALC287_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x896d, "HP ZBook Firefly 16 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x896e, "HP EliteBook x360 830 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), @@ -9781,6 +9801,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8abb, "HP ZBook Firefly 14 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ad1, "HP EliteBook 840 14 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ad2, "HP EliteBook 860 16 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8b2f, "HP 255 15.6 inch G10 Notebook PC", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x8b42, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b43, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b44, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), @@ -9814,12 +9835,16 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8c70, "HP EliteBook 835 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c71, "HP EliteBook 845 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c72, "HP EliteBook 865 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8ca4, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8ca7, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8cf5, "HP ZBook Studio 16", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED), SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300), SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x1043, 0x10a1, "ASUS UX391UA", ALC294_FIXUP_ASUS_SPK), SND_PCI_QUIRK(0x1043, 0x10c0, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x10d0, "ASUS X540LA/X540LJ", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1043, 0x10d3, "ASUS K6500ZC", ALC294_FIXUP_ASUS_SPK), SND_PCI_QUIRK(0x1043, 0x115d, "Asus 1015E", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x1043, 0x11c0, "ASUS X556UR", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x125e, "ASUS Q524UQK", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE), @@ -9839,6 +9864,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1483, "ASUS GU603V", ALC285_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1493, "ASUS GV601V", ALC285_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1517, "Asus Zenbook UX31A", ALC269VB_FIXUP_ASUS_ZENBOOK_UX31A), + SND_PCI_QUIRK(0x1043, 0x1533, "ASUS GV302XA", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x1043, 0x1573, "ASUS GZ301V", ALC285_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1662, "ASUS GV301QH", ALC294_FIXUP_ASUS_DUAL_SPK), SND_PCI_QUIRK(0x1043, 0x1663, "ASUS GU603ZV", ALC285_FIXUP_ASUS_HEADSET_MIC), @@ -9850,6 +9876,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x17f3, "ROG Ally RC71L_RC71L", ALC294_FIXUP_ASUS_ALLY), SND_PCI_QUIRK(0x1043, 0x1881, "ASUS Zephyrus S/M", ALC294_FIXUP_ASUS_GX502_PINS), SND_PCI_QUIRK(0x1043, 0x18b1, "Asus MJ401TA", ALC256_FIXUP_ASUS_HEADSET_MIC), + SND_PCI_QUIRK(0x1043, 0x18d3, "ASUS UM3504DA", ALC294_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x1043, 0x18f1, "Asus FX505DT", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x194e, "ASUS UX563FD", ALC294_FIXUP_ASUS_HPE), SND_PCI_QUIRK(0x1043, 0x1970, "ASUS UX550VE", ALC289_FIXUP_ASUS_GA401), @@ -9858,12 +9885,17 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x19e1, "ASUS UX581LV", ALC295_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x1a13, "Asus G73Jw", ALC269_FIXUP_ASUS_G73JW), SND_PCI_QUIRK(0x1043, 0x1a30, "ASUS X705UD", ALC256_FIXUP_ASUS_MIC), + SND_PCI_QUIRK(0x1043, 0x1a63, "ASUS UX3405MA", ALC245_FIXUP_CS35L41_SPI_2), + SND_PCI_QUIRK(0x1043, 0x1a83, "ASUS UM5302LA", ALC294_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x1043, 0x1a8f, "ASUS UX582ZS", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x1b11, "ASUS UX431DA", ALC294_FIXUP_ASUS_COEF_1B), SND_PCI_QUIRK(0x1043, 0x1b13, "Asus U41SV", ALC269_FIXUP_INV_DMIC), SND_PCI_QUIRK(0x1043, 0x1b93, "ASUS G614JVR/JIR", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x1bbd, "ASUS Z550MA", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1043, 0x1c03, "ASUS UM3406HA", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x1043, 0x1c23, "Asus X55U", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), + SND_PCI_QUIRK(0x1043, 0x1c33, "ASUS UX5304MA", ALC245_FIXUP_CS35L41_SPI_2), + SND_PCI_QUIRK(0x1043, 0x1c43, "ASUS UX8406MA", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x1c62, "ASUS GU603", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x1c92, "ASUS ROG Strix G15", ALC285_FIXUP_ASUS_G533Z_PINS), SND_PCI_QUIRK(0x1043, 0x1c9f, "ASUS G614JI", ALC285_FIXUP_ASUS_HEADSET_MIC), @@ -9874,6 +9906,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1d4e, "ASUS TM420", ALC256_FIXUP_ASUS_HPE), SND_PCI_QUIRK(0x1043, 0x1e02, "ASUS UX3402ZA", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x16a3, "ASUS UX3402VA", ALC245_FIXUP_CS35L41_SPI_2), + SND_PCI_QUIRK(0x1043, 0x1f62, "ASUS UX7602ZM", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x1e11, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA502), SND_PCI_QUIRK(0x1043, 0x1e12, "ASUS UM3402", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x1043, 0x1e51, "ASUS Zephyrus M15", ALC294_FIXUP_ASUS_GU502_PINS), @@ -10085,6 +10118,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x387d, "Yoga S780-16 pro Quad AAC", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x387e, "Yoga S780-16 pro Quad YC", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x3881, "YB9 dual power mode2 YC", ALC287_FIXUP_TAS2781_I2C), + SND_PCI_QUIRK(0x17aa, 0x3882, "Lenovo Yoga Pro 7 14APH8", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN), SND_PCI_QUIRK(0x17aa, 0x3884, "Y780 YG DUAL", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x3886, "Y780 VECO DUAL", ALC287_FIXUP_TAS2781_I2C), SND_PCI_QUIRK(0x17aa, 0x38a7, "Y780P AMD YG dual", ALC287_FIXUP_TAS2781_I2C), @@ -10151,6 +10185,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x8086, 0x2081, "Intel NUC 10", ALC256_FIXUP_INTEL_NUC10), SND_PCI_QUIRK(0x8086, 0x3038, "Intel NUC 13", ALC295_FIXUP_CHROME_BOOK), SND_PCI_QUIRK(0xf111, 0x0001, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0xf111, 0x0005, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0xf111, 0x0006, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE), #if 0 /* Below is a quirk table taken from the old code. @@ -10733,22 +10769,6 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x12, 0x90a60130}, {0x17, 0x90170110}, {0x21, 0x03211020}), - SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE, - {0x14, 0x90170110}, - {0x21, 0x04211020}), - SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE, - {0x14, 0x90170110}, - {0x21, 0x04211030}), - SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE, - ALC295_STANDARD_PINS, - {0x17, 0x21014020}, - {0x18, 0x21a19030}), - SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE, - ALC295_STANDARD_PINS, - {0x17, 0x21014040}, - {0x18, 0x21a19050}), - SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE, - ALC295_STANDARD_PINS), SND_HDA_PIN_QUIRK(0x10ec0298, 0x1028, "Dell", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE, ALC298_STANDARD_PINS, {0x17, 0x90170110}), @@ -10792,6 +10812,9 @@ static const struct snd_hda_pin_quirk alc269_fallback_pin_fixup_tbl[] = { SND_HDA_PIN_QUIRK(0x10ec0289, 0x1028, "Dell", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE, {0x19, 0x40000000}, {0x1b, 0x40000000}), + SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE, + {0x19, 0x40000000}, + {0x1b, 0x40000000}), SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, {0x19, 0x40000000}, {0x1a, 0x40000000}), @@ -12089,6 +12112,7 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x32f7, "Lenovo ThinkCentre M90", ALC897_FIXUP_HEADSET_MIC_PIN), SND_PCI_QUIRK(0x17aa, 0x3321, "Lenovo ThinkCentre M70 Gen4", ALC897_FIXUP_HEADSET_MIC_PIN), SND_PCI_QUIRK(0x17aa, 0x331b, "Lenovo ThinkCentre M90 Gen4", ALC897_FIXUP_HEADSET_MIC_PIN), + SND_PCI_QUIRK(0x17aa, 0x3364, "Lenovo ThinkCentre M90 Gen5", ALC897_FIXUP_HEADSET_MIC_PIN), SND_PCI_QUIRK(0x17aa, 0x3742, "Lenovo TianYi510Pro-14IOB", ALC897_FIXUP_HEADSET_MIC_PIN2), SND_PCI_QUIRK(0x17aa, 0x38af, "Lenovo Ideapad Y550P", ALC662_FIXUP_IDEAPAD), SND_PCI_QUIRK(0x17aa, 0x3a0d, "Lenovo Ideapad Y550", ALC662_FIXUP_IDEAPAD), diff --git a/sound/pci/hda/tas2781_hda_i2c.c b/sound/pci/hda/tas2781_hda_i2c.c index fb802802939e1..2fb1a7037c82c 100644 --- a/sound/pci/hda/tas2781_hda_i2c.c +++ b/sound/pci/hda/tas2781_hda_i2c.c @@ -455,9 +455,9 @@ static int tas2781_save_calibration(struct tasdevice_priv *tas_priv) status = efi.get_variable(efi_name, &efi_guid, &attr, &tas_priv->cali_data.total_sz, tas_priv->cali_data.data); - if (status != EFI_SUCCESS) - return -EINVAL; } + if (status != EFI_SUCCESS) + return -EINVAL; tmp_val = (unsigned int *)tas_priv->cali_data.data; @@ -543,6 +543,10 @@ static void tasdev_fw_ready(const struct firmware *fmw, void *context) tas_priv->fw_state = TASDEVICE_DSP_FW_ALL_OK; tasdevice_prmg_load(tas_priv, 0); + if (tas_priv->fmw->nr_programs > 0) + tas_priv->cur_prog = 0; + if (tas_priv->fmw->nr_configurations > 0) + tas_priv->cur_conf = 0; /* If calibrated data occurs error, dsp will still works with default * calibrated data inside algo. @@ -550,11 +554,6 @@ static void tasdev_fw_ready(const struct firmware *fmw, void *context) tas2781_save_calibration(tas_priv); out: - if (tas_priv->fw_state == TASDEVICE_DSP_FW_FAIL) { - /*If DSP FW fail, kcontrol won't be created */ - tasdevice_config_info_remove(tas_priv); - tasdevice_dsp_remove(tas_priv); - } mutex_unlock(&tas_priv->codec_lock); if (fmw) release_firmware(fmw); @@ -612,9 +611,13 @@ static void tas2781_hda_unbind(struct device *dev, { struct tasdevice_priv *tas_priv = dev_get_drvdata(dev); struct hda_component *comps = master_data; + comps = &comps[tas_priv->index]; - if (comps[tas_priv->index].dev == dev) - memset(&comps[tas_priv->index], 0, sizeof(*comps)); + if (comps->dev == dev) { + comps->dev = NULL; + memset(comps->name, 0, sizeof(comps->name)); + comps->playback_hook = NULL; + } tasdevice_config_info_remove(tas_priv); tasdevice_dsp_remove(tas_priv); @@ -675,14 +678,14 @@ static int tas2781_hda_i2c_probe(struct i2c_client *clt) pm_runtime_put_autosuspend(tas_priv->dev); + tas2781_reset(tas_priv); + ret = component_add(tas_priv->dev, &tas2781_hda_comp_ops); if (ret) { dev_err(tas_priv->dev, "Register component failed: %d\n", ret); pm_runtime_disable(tas_priv->dev); - goto err; } - tas2781_reset(tas_priv); err: if (ret) tas2781_hda_remove(&clt->dev); diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index 15a864dcd7bd3..3babb17a56bb5 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -283,6 +283,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "M6500RC"), } }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "E1504FA"), + } + }, { .driver_data = &acp6x_card, .matches = { diff --git a/sound/soc/codecs/cs35l56.c b/sound/soc/codecs/cs35l56.c index f9059780b7a7b..32d4ab2cd6724 100644 --- a/sound/soc/codecs/cs35l56.c +++ b/sound/soc/codecs/cs35l56.c @@ -772,9 +772,20 @@ static int cs35l56_component_probe(struct snd_soc_component *component) { struct cs35l56_private *cs35l56 = snd_soc_component_get_drvdata(component); struct dentry *debugfs_root = component->debugfs_root; + unsigned short vendor, device; BUILD_BUG_ON(ARRAY_SIZE(cs35l56_tx_input_texts) != ARRAY_SIZE(cs35l56_tx_input_values)); + if (!cs35l56->dsp.system_name && + (snd_soc_card_get_pci_ssid(component->card, &vendor, &device) == 0)) { + cs35l56->dsp.system_name = devm_kasprintf(cs35l56->base.dev, + GFP_KERNEL, + "%04x%04x", + vendor, device); + if (!cs35l56->dsp.system_name) + return -ENOMEM; + } + if (!wait_for_completion_timeout(&cs35l56->init_completion, msecs_to_jiffies(5000))) { dev_err(cs35l56->base.dev, "%s: init_completion timed out\n", __func__); diff --git a/sound/soc/codecs/hdmi-codec.c b/sound/soc/codecs/hdmi-codec.c index 20da1eaa4f1c7..0938671700c62 100644 --- a/sound/soc/codecs/hdmi-codec.c +++ b/sound/soc/codecs/hdmi-codec.c @@ -850,8 +850,9 @@ static int hdmi_dai_probe(struct snd_soc_dai *dai) static void hdmi_codec_jack_report(struct hdmi_codec_priv *hcp, unsigned int jack_status) { - if (hcp->jack && jack_status != hcp->jack_status) { - snd_soc_jack_report(hcp->jack, jack_status, SND_JACK_LINEOUT); + if (jack_status != hcp->jack_status) { + if (hcp->jack) + snd_soc_jack_report(hcp->jack, jack_status, SND_JACK_LINEOUT); hcp->jack_status = jack_status; } } @@ -880,6 +881,13 @@ static int hdmi_codec_set_jack(struct snd_soc_component *component, if (hcp->hcd.ops->hook_plugged_cb) { hcp->jack = jack; + + /* + * Report the initial jack status which may have been provided + * by the parent hdmi driver while the hpd hook was registered. + */ + snd_soc_jack_report(jack, hcp->jack_status, SND_JACK_LINEOUT); + return 0; } diff --git a/sound/soc/codecs/lpass-tx-macro.c b/sound/soc/codecs/lpass-tx-macro.c index 3e33418898e82..ebddfa74ce0a0 100644 --- a/sound/soc/codecs/lpass-tx-macro.c +++ b/sound/soc/codecs/lpass-tx-macro.c @@ -2021,6 +2021,11 @@ static int tx_macro_probe(struct platform_device *pdev) tx->dev = dev; + /* Set active_decimator default value */ + tx->active_decimator[TX_MACRO_AIF1_CAP] = -1; + tx->active_decimator[TX_MACRO_AIF2_CAP] = -1; + tx->active_decimator[TX_MACRO_AIF3_CAP] = -1; + /* set MCLK and NPL rates */ clk_set_rate(tx->mclk, MCLK_FREQ); clk_set_rate(tx->npl, MCLK_FREQ); diff --git a/sound/soc/codecs/lpass-wsa-macro.c b/sound/soc/codecs/lpass-wsa-macro.c index fff4a8b862a73..7e21cec3c2fb9 100644 --- a/sound/soc/codecs/lpass-wsa-macro.c +++ b/sound/soc/codecs/lpass-wsa-macro.c @@ -1685,6 +1685,9 @@ static int wsa_macro_spk_boost_event(struct snd_soc_dapm_widget *w, boost_path_cfg1 = CDC_WSA_RX1_RX_PATH_CFG1; reg = CDC_WSA_RX1_RX_PATH_CTL; reg_mix = CDC_WSA_RX1_RX_PATH_MIX_CTL; + } else { + dev_warn(component->dev, "Incorrect widget name in the driver\n"); + return -EINVAL; } switch (event) { diff --git a/sound/soc/codecs/tas2781-fmwlib.c b/sound/soc/codecs/tas2781-fmwlib.c index eb55abae0d7bb..1dfac9b2fca25 100644 --- a/sound/soc/codecs/tas2781-fmwlib.c +++ b/sound/soc/codecs/tas2781-fmwlib.c @@ -2219,11 +2219,11 @@ int tasdevice_select_tuningprm_cfg(void *context, int prm_no, goto out; } - conf = &(tas_fmw->configs[cfg_no]); for (i = 0, prog_status = 0; i < tas_priv->ndev; i++) { if (cfg_info[rca_conf_no]->active_dev & (1 << i)) { - if (tas_priv->tasdevice[i].cur_prog != prm_no - || tas_priv->force_fwload_status) { + if (prm_no >= 0 + && (tas_priv->tasdevice[i].cur_prog != prm_no + || tas_priv->force_fwload_status)) { tas_priv->tasdevice[i].cur_conf = -1; tas_priv->tasdevice[i].is_loading = true; prog_status++; @@ -2258,7 +2258,8 @@ int tasdevice_select_tuningprm_cfg(void *context, int prm_no, } for (i = 0, status = 0; i < tas_priv->ndev; i++) { - if (tas_priv->tasdevice[i].cur_conf != cfg_no + if (cfg_no >= 0 + && tas_priv->tasdevice[i].cur_conf != cfg_no && (cfg_info[rca_conf_no]->active_dev & (1 << i)) && (tas_priv->tasdevice[i].is_loaderr == false)) { status++; @@ -2268,6 +2269,7 @@ int tasdevice_select_tuningprm_cfg(void *context, int prm_no, } if (status) { + conf = &(tas_fmw->configs[cfg_no]); status = 0; tasdevice_load_data(tas_priv, &(conf->dev_data)); for (i = 0; i < tas_priv->ndev; i++) { @@ -2311,7 +2313,7 @@ int tasdevice_prmg_load(void *context, int prm_no) } for (i = 0, prog_status = 0; i < tas_priv->ndev; i++) { - if (tas_priv->tasdevice[i].cur_prog != prm_no) { + if (prm_no >= 0 && tas_priv->tasdevice[i].cur_prog != prm_no) { tas_priv->tasdevice[i].cur_conf = -1; tas_priv->tasdevice[i].is_loading = true; prog_status++; @@ -2356,7 +2358,7 @@ int tasdevice_prmg_calibdata_load(void *context, int prm_no) } for (i = 0, prog_status = 0; i < tas_priv->ndev; i++) { - if (tas_priv->tasdevice[i].cur_prog != prm_no) { + if (prm_no >= 0 && tas_priv->tasdevice[i].cur_prog != prm_no) { tas_priv->tasdevice[i].cur_conf = -1; tas_priv->tasdevice[i].is_loading = true; prog_status++; diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c index d1b9238d391e8..cb654f1b09f10 100644 --- a/sound/soc/codecs/wm_adsp.c +++ b/sound/soc/codecs/wm_adsp.c @@ -1451,12 +1451,12 @@ static int wm_adsp_buffer_populate(struct wm_adsp_compr_buf *buf) ret = wm_adsp_buffer_read(buf, caps->region_defs[i].base_offset, ®ion->base_addr); if (ret < 0) - return ret; + goto err; ret = wm_adsp_buffer_read(buf, caps->region_defs[i].size_offset, &offset); if (ret < 0) - return ret; + goto err; region->cumulative_size = offset; @@ -1467,6 +1467,10 @@ static int wm_adsp_buffer_populate(struct wm_adsp_compr_buf *buf) } return 0; + +err: + kfree(buf->regions); + return ret; } static void wm_adsp_buffer_clear(struct wm_adsp_compr_buf *buf) diff --git a/sound/soc/codecs/wsa883x.c b/sound/soc/codecs/wsa883x.c index 197fae23762f5..cb83c569e18d6 100644 --- a/sound/soc/codecs/wsa883x.c +++ b/sound/soc/codecs/wsa883x.c @@ -1203,9 +1203,6 @@ static int wsa883x_spkr_event(struct snd_soc_dapm_widget *w, break; } - snd_soc_component_write_field(component, WSA883X_DRE_CTL_1, - WSA883X_DRE_GAIN_EN_MASK, - WSA883X_DRE_GAIN_FROM_CSR); if (wsa883x->port_enable[WSA883X_PORT_COMP]) snd_soc_component_write_field(component, WSA883X_DRE_CTL_0, WSA883X_DRE_OFFSET_MASK, @@ -1218,9 +1215,6 @@ static int wsa883x_spkr_event(struct snd_soc_dapm_widget *w, snd_soc_component_write_field(component, WSA883X_PDM_WD_CTL, WSA883X_PDM_EN_MASK, WSA883X_PDM_ENABLE); - snd_soc_component_write_field(component, WSA883X_PA_FSM_CTL, - WSA883X_GLOBAL_PA_EN_MASK, - WSA883X_GLOBAL_PA_ENABLE); break; case SND_SOC_DAPM_PRE_PMD: @@ -1346,6 +1340,7 @@ static const struct snd_soc_dai_ops wsa883x_dai_ops = { .hw_free = wsa883x_hw_free, .mute_stream = wsa883x_digital_mute, .set_stream = wsa883x_set_sdw_stream, + .mute_unmute_on_trigger = true, }; static struct snd_soc_dai_driver wsa883x_dais[] = { diff --git a/sound/soc/fsl/fsl_sai.c b/sound/soc/fsl/fsl_sai.c index 8a9a30dd31e20..3d202398c5411 100644 --- a/sound/soc/fsl/fsl_sai.c +++ b/sound/soc/fsl/fsl_sai.c @@ -674,6 +674,20 @@ static int fsl_sai_hw_params(struct snd_pcm_substream *substream, FSL_SAI_CR3_TRCE_MASK, FSL_SAI_CR3_TRCE((dl_cfg[dl_cfg_idx].mask[tx] & trce_mask))); + /* + * When the TERE and FSD_MSTR enabled before configuring the word width + * There will be no frame sync clock issue, because word width impact + * the generation of frame sync clock. + * + * TERE enabled earlier only for i.MX8MP case for the hardware limitation, + * We need to disable FSD_MSTR before configuring word width, then enable + * FSD_MSTR bit for this specific case. + */ + if (sai->soc_data->mclk_with_tere && sai->mclk_direction_output && + !sai->is_consumer_mode) + regmap_update_bits(sai->regmap, FSL_SAI_xCR4(tx, ofs), + FSL_SAI_CR4_FSD_MSTR, 0); + regmap_update_bits(sai->regmap, FSL_SAI_xCR4(tx, ofs), FSL_SAI_CR4_SYWD_MASK | FSL_SAI_CR4_FRSZ_MASK | FSL_SAI_CR4_CHMOD_MASK, @@ -681,6 +695,13 @@ static int fsl_sai_hw_params(struct snd_pcm_substream *substream, regmap_update_bits(sai->regmap, FSL_SAI_xCR5(tx, ofs), FSL_SAI_CR5_WNW_MASK | FSL_SAI_CR5_W0W_MASK | FSL_SAI_CR5_FBT_MASK, val_cr5); + + /* Enable FSD_MSTR after configuring word width */ + if (sai->soc_data->mclk_with_tere && sai->mclk_direction_output && + !sai->is_consumer_mode) + regmap_update_bits(sai->regmap, FSL_SAI_xCR4(tx, ofs), + FSL_SAI_CR4_FSD_MSTR, FSL_SAI_CR4_FSD_MSTR); + regmap_write(sai->regmap, FSL_SAI_xMR(tx), ~0UL - ((1 << min(channels, slots)) - 1)); @@ -694,6 +715,9 @@ static int fsl_sai_hw_free(struct snd_pcm_substream *substream, bool tx = substream->stream == SNDRV_PCM_STREAM_PLAYBACK; unsigned int ofs = sai->soc_data->reg_offset; + /* Clear xMR to avoid channel swap with mclk_with_tere enabled case */ + regmap_write(sai->regmap, FSL_SAI_xMR(tx), 0); + regmap_update_bits(sai->regmap, FSL_SAI_xCR3(tx, ofs), FSL_SAI_CR3_TRCE_MASK, 0); diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c index 47d22cab5af62..24e966a2ac2be 100644 --- a/sound/soc/intel/boards/sof_sdw.c +++ b/sound/soc/intel/boards/sof_sdw.c @@ -1934,6 +1934,12 @@ static int mc_probe(struct platform_device *pdev) for (i = 0; i < ARRAY_SIZE(codec_info_list); i++) codec_info_list[i].amp_num = 0; + if (mach->mach_params.subsystem_id_set) { + snd_soc_card_set_pci_ssid(card, + mach->mach_params.subsystem_vendor, + mach->mach_params.subsystem_device); + } + ret = sof_card_dai_links_create(card); if (ret < 0) return ret; diff --git a/sound/soc/intel/common/soc-acpi-intel-cht-match.c b/sound/soc/intel/common/soc-acpi-intel-cht-match.c index cdcbf04b8832f..5e2ec60e2954b 100644 --- a/sound/soc/intel/common/soc-acpi-intel-cht-match.c +++ b/sound/soc/intel/common/soc-acpi-intel-cht-match.c @@ -75,6 +75,39 @@ static struct snd_soc_acpi_mach *cht_ess8316_quirk(void *arg) return arg; } +/* + * The Lenovo Yoga Tab 3 Pro YT3-X90, with Android factory OS has a buggy DSDT + * with the coded not being listed at all. + */ +static const struct dmi_system_id lenovo_yoga_tab3_x90[] = { + { + /* Lenovo Yoga Tab 3 Pro YT3-X90, codec missing from DSDT */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Intel Corporation"), + DMI_MATCH(DMI_PRODUCT_NAME, "CHERRYVIEW D1 PLATFORM"), + DMI_MATCH(DMI_PRODUCT_VERSION, "Blade3-10A-001"), + }, + }, + { } +}; + +static struct snd_soc_acpi_mach cht_lenovo_yoga_tab3_x90_mach = { + .id = "10WM5102", + .drv_name = "bytcr_wm5102", + .fw_filename = "intel/fw_sst_22a8.bin", + .board = "bytcr_wm5102", + .sof_tplg_filename = "sof-cht-wm5102.tplg", +}; + +static struct snd_soc_acpi_mach *lenovo_yt3_x90_quirk(void *arg) +{ + if (dmi_check_system(lenovo_yoga_tab3_x90)) + return &cht_lenovo_yoga_tab3_x90_mach; + + /* Skip wildcard match snd_soc_acpi_intel_cherrytrail_machines[] entry */ + return NULL; +} + static const struct snd_soc_acpi_codecs rt5640_comp_ids = { .num_codecs = 2, .codecs = { "10EC5640", "10EC3276" }, @@ -175,6 +208,16 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_cherrytrail_machines[] = { .drv_name = "sof_pcm512x", .sof_tplg_filename = "sof-cht-src-50khz-pcm512x.tplg", }, + /* + * Special case for the Lenovo Yoga Tab 3 Pro YT3-X90 where the DSDT + * misses the codec. Match on the SST id instead, lenovo_yt3_x90_quirk() + * will return a YT3 specific mach or NULL when called on other hw, + * skipping this entry. + */ + { + .id = "808622A8", + .machine_quirk = lenovo_yt3_x90_quirk, + }, #if IS_ENABLED(CONFIG_SND_SOC_INTEL_BYT_CHT_NOCODEC_MACH) /* diff --git a/sound/soc/mediatek/mt8188/mt8188-mt6359.c b/sound/soc/mediatek/mt8188/mt8188-mt6359.c index 9017f48b6272b..f7e22abb75846 100644 --- a/sound/soc/mediatek/mt8188/mt8188-mt6359.c +++ b/sound/soc/mediatek/mt8188/mt8188-mt6359.c @@ -246,6 +246,11 @@ static const struct snd_soc_dapm_widget mt8188_mt6359_widgets[] = { SND_SOC_DAPM_MIC("Headset Mic", NULL), SND_SOC_DAPM_SINK("HDMI"), SND_SOC_DAPM_SINK("DP"), + + /* dynamic pinctrl */ + SND_SOC_DAPM_PINCTRL("ETDM_SPK_PIN", "aud_etdm_spk_on", "aud_etdm_spk_off"), + SND_SOC_DAPM_PINCTRL("ETDM_HP_PIN", "aud_etdm_hp_on", "aud_etdm_hp_off"), + SND_SOC_DAPM_PINCTRL("MTKAIF_PIN", "aud_mtkaif_on", "aud_mtkaif_off"), }; static const struct snd_kcontrol_new mt8188_mt6359_controls[] = { @@ -267,6 +272,7 @@ static int mt8188_mt6359_mtkaif_calibration(struct snd_soc_pcm_runtime *rtd) snd_soc_rtdcom_lookup(rtd, AFE_PCM_NAME); struct snd_soc_component *cmpnt_codec = asoc_rtd_to_codec(rtd, 0)->component; + struct snd_soc_dapm_widget *pin_w = NULL, *w; struct mtk_base_afe *afe; struct mt8188_afe_private *afe_priv; struct mtkaif_param *param; @@ -306,6 +312,18 @@ static int mt8188_mt6359_mtkaif_calibration(struct snd_soc_pcm_runtime *rtd) return 0; } + for_each_card_widgets(rtd->card, w) { + if (!strcmp(w->name, "MTKAIF_PIN")) { + pin_w = w; + break; + } + } + + if (pin_w) + dapm_pinctrl_event(pin_w, NULL, SND_SOC_DAPM_PRE_PMU); + else + dev_dbg(afe->dev, "%s(), no pinmux widget, please check if default on\n", __func__); + pm_runtime_get_sync(afe->dev); mt6359_mtkaif_calibration_enable(cmpnt_codec); @@ -403,6 +421,9 @@ static int mt8188_mt6359_mtkaif_calibration(struct snd_soc_pcm_runtime *rtd) for (i = 0; i < MT8188_MTKAIF_MISO_NUM; i++) param->mtkaif_phase_cycle[i] = mtkaif_phase_cycle[i]; + if (pin_w) + dapm_pinctrl_event(pin_w, NULL, SND_SOC_DAPM_POST_PMD); + dev_dbg(afe->dev, "%s(), end, calibration ok %d\n", __func__, param->mtkaif_calibration_ok); diff --git a/sound/soc/qcom/sc8280xp.c b/sound/soc/qcom/sc8280xp.c index 14d9fea33d16a..c61cad0180c87 100644 --- a/sound/soc/qcom/sc8280xp.c +++ b/sound/soc/qcom/sc8280xp.c @@ -27,6 +27,23 @@ struct sc8280xp_snd_data { static int sc8280xp_snd_init(struct snd_soc_pcm_runtime *rtd) { struct sc8280xp_snd_data *data = snd_soc_card_get_drvdata(rtd->card); + struct snd_soc_dai *cpu_dai = asoc_rtd_to_cpu(rtd, 0); + struct snd_soc_card *card = rtd->card; + + switch (cpu_dai->id) { + case WSA_CODEC_DMA_RX_0: + case WSA_CODEC_DMA_RX_1: + /* + * set limit of 0dB on Digital Volume for Speakers, + * this can prevent damage of speakers to some extent without + * active speaker protection + */ + snd_soc_limit_volume(card, "WSA_RX0 Digital Volume", 84); + snd_soc_limit_volume(card, "WSA_RX1 Digital Volume", 84); + break; + default: + break; + } return qcom_snd_wcd_jack_setup(rtd, &data->jack, &data->jack_setup); } diff --git a/sound/soc/soc-dai.c b/sound/soc/soc-dai.c index 3f33f0630ad8a..9a828e55c4f9e 100644 --- a/sound/soc/soc-dai.c +++ b/sound/soc/soc-dai.c @@ -658,6 +658,10 @@ int snd_soc_pcm_dai_trigger(struct snd_pcm_substream *substream, ret = soc_dai_trigger(dai, substream, cmd); if (ret < 0) break; + + if (dai->driver->ops && dai->driver->ops->mute_unmute_on_trigger) + snd_soc_dai_digital_mute(dai, 0, substream->stream); + soc_dai_mark_push(dai, substream, trigger); } break; @@ -668,6 +672,9 @@ int snd_soc_pcm_dai_trigger(struct snd_pcm_substream *substream, if (rollback && !soc_dai_mark_match(dai, substream, trigger)) continue; + if (dai->driver->ops && dai->driver->ops->mute_unmute_on_trigger) + snd_soc_dai_digital_mute(dai, 1, substream->stream); + r = soc_dai_trigger(dai, substream, cmd); if (r < 0) ret = r; /* use last ret */ diff --git a/sound/soc/soc-ops.c b/sound/soc/soc-ops.c index 55b009d3c6815..2d25748ca7066 100644 --- a/sound/soc/soc-ops.c +++ b/sound/soc/soc-ops.c @@ -661,7 +661,7 @@ int snd_soc_limit_volume(struct snd_soc_card *card, kctl = snd_soc_card_get_kcontrol(card, name); if (kctl) { struct soc_mixer_control *mc = (struct soc_mixer_control *)kctl->private_value; - if (max <= mc->max) { + if (max <= mc->max - mc->min) { mc->platform_max = max; ret = 0; } diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index 0a20122b3e555..511446a30c057 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -896,8 +896,10 @@ static int __soc_pcm_prepare(struct snd_soc_pcm_runtime *rtd, snd_soc_dapm_stream_event(rtd, substream->stream, SND_SOC_DAPM_STREAM_START); - for_each_rtd_dais(rtd, i, dai) - snd_soc_dai_digital_mute(dai, 0, substream->stream); + for_each_rtd_dais(rtd, i, dai) { + if (dai->driver->ops && !dai->driver->ops->mute_unmute_on_trigger) + snd_soc_dai_digital_mute(dai, 0, substream->stream); + } out: return soc_pcm_ret(rtd, ret); @@ -939,8 +941,10 @@ static int soc_pcm_hw_clean(struct snd_soc_pcm_runtime *rtd, if (snd_soc_dai_active(dai) == 1) soc_pcm_set_dai_params(dai, NULL); - if (snd_soc_dai_stream_active(dai, substream->stream) == 1) - snd_soc_dai_digital_mute(dai, 1, substream->stream); + if (snd_soc_dai_stream_active(dai, substream->stream) == 1) { + if (dai->driver->ops && !dai->driver->ops->mute_unmute_on_trigger) + snd_soc_dai_digital_mute(dai, 1, substream->stream); + } } /* run the stream event */ diff --git a/sound/soc/sof/ipc4.c b/sound/soc/sof/ipc4.c index ab6eddd91bb77..1b09496733fb8 100644 --- a/sound/soc/sof/ipc4.c +++ b/sound/soc/sof/ipc4.c @@ -614,6 +614,9 @@ static void sof_ipc4_rx_msg(struct snd_sof_dev *sdev) case SOF_IPC4_NOTIFY_LOG_BUFFER_STATUS: sof_ipc4_mtrace_update_pos(sdev, SOF_IPC4_LOG_CORE_GET(ipc4_msg->primary)); break; + case SOF_IPC4_NOTIFY_EXCEPTION_CAUGHT: + snd_sof_dsp_panic(sdev, 0, true); + break; default: dev_dbg(sdev->dev, "Unhandled DSP message: %#x|%#x\n", ipc4_msg->primary, ipc4_msg->extension); diff --git a/sound/soc/sof/sof-audio.c b/sound/soc/sof/sof-audio.c index e5405f854a910..563fe6f7789f7 100644 --- a/sound/soc/sof/sof-audio.c +++ b/sound/soc/sof/sof-audio.c @@ -1032,6 +1032,13 @@ int sof_machine_check(struct snd_sof_dev *sdev) mach = snd_sof_machine_select(sdev); if (mach) { sof_pdata->machine = mach; + + if (sof_pdata->subsystem_id_set) { + mach->mach_params.subsystem_vendor = sof_pdata->subsystem_vendor; + mach->mach_params.subsystem_device = sof_pdata->subsystem_device; + mach->mach_params.subsystem_id_set = true; + } + snd_sof_set_mach_params(mach, sdev); return 0; } diff --git a/sound/soc/sof/sof-pci-dev.c b/sound/soc/sof/sof-pci-dev.c index f42c85df88a80..69a2352f2e1a0 100644 --- a/sound/soc/sof/sof-pci-dev.c +++ b/sound/soc/sof/sof-pci-dev.c @@ -221,6 +221,14 @@ int sof_pci_probe(struct pci_dev *pci, const struct pci_device_id *pci_id) return ret; sof_pdata->name = pci_name(pci); + + /* PCI defines a vendor ID of 0xFFFF as invalid. */ + if (pci->subsystem_vendor != 0xFFFF) { + sof_pdata->subsystem_vendor = pci->subsystem_vendor; + sof_pdata->subsystem_device = pci->subsystem_device; + sof_pdata->subsystem_id_set = true; + } + sof_pdata->desc = desc; sof_pdata->dev = dev; diff --git a/sound/soc/ti/omap-mcbsp.c b/sound/soc/ti/omap-mcbsp.c index fdabed5133e83..b399d86f22777 100644 --- a/sound/soc/ti/omap-mcbsp.c +++ b/sound/soc/ti/omap-mcbsp.c @@ -74,14 +74,16 @@ static int omap2_mcbsp_set_clks_src(struct omap_mcbsp *mcbsp, u8 fck_src_id) return 0; } - pm_runtime_put_sync(mcbsp->dev); + if (mcbsp->active) + pm_runtime_put_sync(mcbsp->dev); r = clk_set_parent(mcbsp->fclk, fck_src); if (r) dev_err(mcbsp->dev, "CLKS: could not clk_set_parent() to %s\n", src); - pm_runtime_get_sync(mcbsp->dev); + if (mcbsp->active) + pm_runtime_get_sync(mcbsp->dev); clk_put(fck_src); diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c index ab0d459f42715..1f32e3ae3aa31 100644 --- a/sound/usb/mixer_quirks.c +++ b/sound/usb/mixer_quirks.c @@ -2978,6 +2978,7 @@ static int snd_bbfpro_controls_create(struct usb_mixer_interface *mixer) #define SND_DJM_850_IDX 0x2 #define SND_DJM_900NXS2_IDX 0x3 #define SND_DJM_750MK2_IDX 0x4 +#define SND_DJM_450_IDX 0x5 #define SND_DJM_CTL(_name, suffix, _default_value, _windex) { \ @@ -3108,6 +3109,31 @@ static const struct snd_djm_ctl snd_djm_ctls_250mk2[] = { }; +// DJM-450 +static const u16 snd_djm_opts_450_cap1[] = { + 0x0103, 0x0100, 0x0106, 0x0107, 0x0108, 0x0109, 0x010d, 0x010a }; + +static const u16 snd_djm_opts_450_cap2[] = { + 0x0203, 0x0200, 0x0206, 0x0207, 0x0208, 0x0209, 0x020d, 0x020a }; + +static const u16 snd_djm_opts_450_cap3[] = { + 0x030a, 0x0311, 0x0312, 0x0307, 0x0308, 0x0309, 0x030d }; + +static const u16 snd_djm_opts_450_pb1[] = { 0x0100, 0x0101, 0x0104 }; +static const u16 snd_djm_opts_450_pb2[] = { 0x0200, 0x0201, 0x0204 }; +static const u16 snd_djm_opts_450_pb3[] = { 0x0300, 0x0301, 0x0304 }; + +static const struct snd_djm_ctl snd_djm_ctls_450[] = { + SND_DJM_CTL("Capture Level", cap_level, 0, SND_DJM_WINDEX_CAPLVL), + SND_DJM_CTL("Ch1 Input", 450_cap1, 2, SND_DJM_WINDEX_CAP), + SND_DJM_CTL("Ch2 Input", 450_cap2, 2, SND_DJM_WINDEX_CAP), + SND_DJM_CTL("Ch3 Input", 450_cap3, 0, SND_DJM_WINDEX_CAP), + SND_DJM_CTL("Ch1 Output", 450_pb1, 0, SND_DJM_WINDEX_PB), + SND_DJM_CTL("Ch2 Output", 450_pb2, 1, SND_DJM_WINDEX_PB), + SND_DJM_CTL("Ch3 Output", 450_pb3, 2, SND_DJM_WINDEX_PB) +}; + + // DJM-750 static const u16 snd_djm_opts_750_cap1[] = { 0x0101, 0x0103, 0x0106, 0x0107, 0x0108, 0x0109, 0x010a, 0x010f }; @@ -3203,6 +3229,7 @@ static const struct snd_djm_device snd_djm_devices[] = { [SND_DJM_850_IDX] = SND_DJM_DEVICE(850), [SND_DJM_900NXS2_IDX] = SND_DJM_DEVICE(900nxs2), [SND_DJM_750MK2_IDX] = SND_DJM_DEVICE(750mk2), + [SND_DJM_450_IDX] = SND_DJM_DEVICE(450), }; @@ -3449,6 +3476,9 @@ int snd_usb_mixer_apply_create_quirk(struct usb_mixer_interface *mixer) case USB_ID(0x2b73, 0x0017): /* Pioneer DJ DJM-250MK2 */ err = snd_djm_controls_create(mixer, SND_DJM_250MK2_IDX); break; + case USB_ID(0x2b73, 0x0013): /* Pioneer DJ DJM-450 */ + err = snd_djm_controls_create(mixer, SND_DJM_450_IDX); + break; case USB_ID(0x08e4, 0x017f): /* Pioneer DJ DJM-750 */ err = snd_djm_controls_create(mixer, SND_DJM_750_IDX); break; diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index ab2b938502ebe..07cc6a201579a 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1387,7 +1387,7 @@ static int snd_usb_motu_microbookii_boot_quirk(struct usb_device *dev) static int snd_usb_motu_m_series_boot_quirk(struct usb_device *dev) { - msleep(2000); + msleep(4000); return 0; } @@ -1630,7 +1630,7 @@ int snd_usb_apply_boot_quirk_once(struct usb_device *dev, unsigned int id) { switch (id) { - case USB_ID(0x07fd, 0x0008): /* MOTU M Series */ + case USB_ID(0x07fd, 0x0008): /* MOTU M Series, 1st hardware version */ return snd_usb_motu_m_series_boot_quirk(dev); } diff --git a/tools/arch/parisc/include/uapi/asm/errno.h b/tools/arch/parisc/include/uapi/asm/errno.h index 87245c584784e..8d94739d75c67 100644 --- a/tools/arch/parisc/include/uapi/asm/errno.h +++ b/tools/arch/parisc/include/uapi/asm/errno.h @@ -75,7 +75,6 @@ /* We now return you to your regularly scheduled HPUX. */ -#define ENOSYM 215 /* symbol does not exist in executable */ #define ENOTSOCK 216 /* Socket operation on non-socket */ #define EDESTADDRREQ 217 /* Destination address required */ #define EMSGSIZE 218 /* Message too long */ @@ -101,7 +100,6 @@ #define ETIMEDOUT 238 /* Connection timed out */ #define ECONNREFUSED 239 /* Connection refused */ #define EREFUSED ECONNREFUSED /* for HP's NFS apparently */ -#define EREMOTERELEASE 240 /* Remote peer released connection */ #define EHOSTDOWN 241 /* Host is down */ #define EHOSTUNREACH 242 /* No route to host */ diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c index 264eeb9c46a9f..318e2dad27e04 100644 --- a/tools/hv/hv_kvp_daemon.c +++ b/tools/hv/hv_kvp_daemon.c @@ -1421,7 +1421,7 @@ static int kvp_set_ip_info(char *if_name, struct hv_kvp_ipaddr_value *new_val) if (error) goto setval_error; - if (new_val->addr_family == ADDR_FAMILY_IPV6) { + if (new_val->addr_family & ADDR_FAMILY_IPV6) { error = fprintf(nmfile, "\n[ipv6]\n"); if (error < 0) goto setval_error; @@ -1455,14 +1455,18 @@ static int kvp_set_ip_info(char *if_name, struct hv_kvp_ipaddr_value *new_val) if (error < 0) goto setval_error; - error = fprintf(nmfile, "gateway=%s\n", (char *)new_val->gate_way); - if (error < 0) - goto setval_error; - - error = fprintf(nmfile, "dns=%s\n", (char *)new_val->dns_addr); - if (error < 0) - goto setval_error; + /* we do not want ipv4 addresses in ipv6 section and vice versa */ + if (is_ipv6 != is_ipv4((char *)new_val->gate_way)) { + error = fprintf(nmfile, "gateway=%s\n", (char *)new_val->gate_way); + if (error < 0) + goto setval_error; + } + if (is_ipv6 != is_ipv4((char *)new_val->dns_addr)) { + error = fprintf(nmfile, "dns=%s\n", (char *)new_val->dns_addr); + if (error < 0) + goto setval_error; + } fclose(nmfile); fclose(ifcfg_file); diff --git a/tools/hv/hv_set_ifconfig.sh b/tools/hv/hv_set_ifconfig.sh index ae5a7a8249a20..440a91b35823b 100755 --- a/tools/hv/hv_set_ifconfig.sh +++ b/tools/hv/hv_set_ifconfig.sh @@ -53,7 +53,7 @@ # or "manual" if no boot-time protocol should be used) # # address1=ipaddr1/plen -# address=ipaddr2/plen +# address2=ipaddr2/plen # # gateway=gateway1;gateway2 # @@ -61,7 +61,7 @@ # # [ipv6] # address1=ipaddr1/plen -# address2=ipaddr1/plen +# address2=ipaddr2/plen # # gateway=gateway1;gateway2 # diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h index 3c36aeade991e..370ed14b1ae09 100644 --- a/tools/include/uapi/linux/prctl.h +++ b/tools/include/uapi/linux/prctl.h @@ -283,7 +283,8 @@ struct prctl_mm_map { /* Memory deny write / execute */ #define PR_SET_MDWE 65 -# define PR_MDWE_REFUSE_EXEC_GAIN 1 +# define PR_MDWE_REFUSE_EXEC_GAIN (1UL << 0) +# define PR_MDWE_NO_INHERIT (1UL << 1) #define PR_GET_MDWE 66 diff --git a/tools/objtool/noreturns.h b/tools/objtool/noreturns.h index e45c7cb1d5bcd..80a3e6acf31e4 100644 --- a/tools/objtool/noreturns.h +++ b/tools/objtool/noreturns.h @@ -6,7 +6,6 @@ * * Yes, this is unfortunate. A better solution is in the works. */ -NORETURN(__invalid_creds) NORETURN(__kunit_abort) NORETURN(__module_put_and_kthread_exit) NORETURN(__reiserfs_panic) diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c index a343823c8ddfc..61c2c96cc0701 100644 --- a/tools/perf/builtin-list.c +++ b/tools/perf/builtin-list.c @@ -434,6 +434,11 @@ static void json_print_metric(void *ps __maybe_unused, const char *group, strbuf_release(&buf); } +static bool json_skip_duplicate_pmus(void *ps __maybe_unused) +{ + return false; +} + static bool default_skip_duplicate_pmus(void *ps) { struct print_state *print_state = ps; @@ -503,6 +508,7 @@ int cmd_list(int argc, const char **argv) .print_end = json_print_end, .print_event = json_print_event, .print_metric = json_print_metric, + .skip_duplicate_pmus = json_skip_duplicate_pmus, }; ps = &json_ps; } else { diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/metrics.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/metrics.json index e2848a9d48487..afcdad58ef89c 100644 --- a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/metrics.json +++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/metrics.json @@ -231,6 +231,7 @@ "MetricName": "slots_lost_misspeculation_fraction", "MetricExpr": "100 * ((OP_SPEC - OP_RETIRED) / (CPU_CYCLES * #slots))", "BriefDescription": "Fraction of slots lost due to misspeculation", + "DefaultMetricgroupName": "TopdownL1", "MetricGroup": "Default;TopdownL1", "ScaleUnit": "1percent of slots" }, @@ -238,6 +239,7 @@ "MetricName": "retired_fraction", "MetricExpr": "100 * (OP_RETIRED / (CPU_CYCLES * #slots))", "BriefDescription": "Fraction of slots retiring, useful work", + "DefaultMetricgroupName": "TopdownL1", "MetricGroup": "Default;TopdownL1", "ScaleUnit": "1percent of slots" }, diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index dbf0bc71a63be..f38893e0b0369 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -1512,9 +1512,11 @@ static void intel_pt_sample_flags(struct intel_pt_queue *ptq) } else if (ptq->state->flags & INTEL_PT_ASYNC) { if (!ptq->state->to_ip) ptq->flags = PERF_IP_FLAG_BRANCH | + PERF_IP_FLAG_ASYNC | PERF_IP_FLAG_TRACE_END; else if (ptq->state->from_nr && !ptq->state->to_nr) ptq->flags = PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | + PERF_IP_FLAG_ASYNC | PERF_IP_FLAG_VMEXIT; else ptq->flags = PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index 6231044a491e2..bb5faaa25d510 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -225,7 +225,7 @@ static struct metric *metric__new(const struct pmu_metric *pm, m->pmu = pm->pmu ?: "cpu"; m->metric_name = pm->metric_name; - m->default_metricgroup_name = pm->default_metricgroup_name; + m->default_metricgroup_name = pm->default_metricgroup_name ?: ""; m->modifier = NULL; if (modifier) { m->modifier = strdup(modifier); diff --git a/tools/power/pm-graph/sleepgraph.py b/tools/power/pm-graph/sleepgraph.py index 4a356a7067855..40ad221e88811 100755 --- a/tools/power/pm-graph/sleepgraph.py +++ b/tools/power/pm-graph/sleepgraph.py @@ -4151,7 +4151,7 @@ def parseKernelLog(data): elif(re.match('Enabling non-boot CPUs .*', msg)): # start of first cpu resume cpu_start = ktime - elif(re.match('smpboot: CPU (?P[0-9]*) is now offline', msg)) \ + elif(re.match('smpboot: CPU (?P[0-9]*) is now offline', msg) \ or re.match('psci: CPU(?P[0-9]*) killed.*', msg)): # end of a cpu suspend, start of the next m = re.match('smpboot: CPU (?P[0-9]*) is now offline', msg) diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 9a10512e34078..785de89077de0 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -2180,7 +2180,7 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) if ((DO_BIC(BIC_CPU_c6) || soft_c1_residency_display(BIC_CPU_c6)) && !do_knl_cstates) { if (get_msr(cpu, MSR_CORE_C6_RESIDENCY, &c->c6)) return -7; - } else if (do_knl_cstates || soft_c1_residency_display(BIC_CPU_c6)) { + } else if (do_knl_cstates && soft_c1_residency_display(BIC_CPU_c6)) { if (get_msr(cpu, MSR_KNL_CORE_C6_RESIDENCY, &c->c6)) return -7; } @@ -5790,6 +5790,7 @@ void process_cpuid() rapl_probe(family, model); perf_limit_reasons_probe(family, model); automatic_cstate_conversion_probe(family, model); + prewake_cstate_probe(family, model); check_tcc_offset(model_orig); diff --git a/tools/testing/cxl/test/cxl.c b/tools/testing/cxl/test/cxl.c index fb6ab9cef84f7..b885462999022 100644 --- a/tools/testing/cxl/test/cxl.c +++ b/tools/testing/cxl/test/cxl.c @@ -831,7 +831,7 @@ static void mock_init_hdm_decoder(struct cxl_decoder *cxld) cxld->interleave_ways = 2; else cxld->interleave_ways = 1; - cxld->interleave_granularity = 256; + cxld->interleave_granularity = 4096; cxld->hpa_range = (struct range) { .start = base, .end = base + size - 1, diff --git a/tools/testing/radix-tree/maple.c b/tools/testing/radix-tree/maple.c index e5da1cad70baf..76a8990bb14e8 100644 --- a/tools/testing/radix-tree/maple.c +++ b/tools/testing/radix-tree/maple.c @@ -35538,7 +35538,7 @@ static noinline void __init check_prealloc(struct maple_tree *mt) MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0); allocated = mas_allocated(&mas); height = mas_mt_height(&mas); - MT_BUG_ON(mt, allocated != 1); + MT_BUG_ON(mt, allocated != 0); mas_store_prealloc(&mas, ptr); MT_BUG_ON(mt, mas_allocated(&mas) != 0); diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 1a21d6beebc68..697f13bbbc321 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -152,12 +152,10 @@ ifneq ($(KBUILD_OUTPUT),) abs_objtree := $(realpath $(abs_objtree)) BUILD := $(abs_objtree)/kselftest KHDR_INCLUDES := -isystem ${abs_objtree}/usr/include - KHDR_DIR := ${abs_objtree}/usr/include else BUILD := $(CURDIR) abs_srctree := $(shell cd $(top_srcdir) && pwd) KHDR_INCLUDES := -isystem ${abs_srctree}/usr/include - KHDR_DIR := ${abs_srctree}/usr/include DEFAULT_INSTALL_HDR_PATH := 1 endif @@ -171,7 +169,7 @@ export KHDR_INCLUDES # all isn't the first target in the file. .DEFAULT_GOAL := all -all: kernel_header_files +all: @ret=1; \ for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ @@ -182,23 +180,6 @@ all: kernel_header_files ret=$$((ret * $$?)); \ done; exit $$ret; -kernel_header_files: - @ls $(KHDR_DIR)/linux/*.h >/dev/null 2>/dev/null; \ - if [ $$? -ne 0 ]; then \ - RED='\033[1;31m'; \ - NOCOLOR='\033[0m'; \ - echo; \ - echo -e "$${RED}error$${NOCOLOR}: missing kernel header files."; \ - echo "Please run this and try again:"; \ - echo; \ - echo " cd $(top_srcdir)"; \ - echo " make headers"; \ - echo; \ - exit 1; \ - fi - -.PHONY: kernel_header_files - run_tests: all @for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ diff --git a/tools/testing/selftests/arm64/fp/za-fork.c b/tools/testing/selftests/arm64/fp/za-fork.c index b86cb1049497f..587b946482226 100644 --- a/tools/testing/selftests/arm64/fp/za-fork.c +++ b/tools/testing/selftests/arm64/fp/za-fork.c @@ -85,7 +85,7 @@ int main(int argc, char **argv) */ ret = open("/proc/sys/abi/sme_default_vector_length", O_RDONLY, 0); if (ret >= 0) { - ksft_test_result(fork_test(), "fork_test"); + ksft_test_result(fork_test(), "fork_test\n"); } else { ksft_print_msg("SME not supported\n"); diff --git a/tools/testing/selftests/bpf/config.x86_64 b/tools/testing/selftests/bpf/config.x86_64 index 2e70a60482784..49a29dbc19107 100644 --- a/tools/testing/selftests/bpf/config.x86_64 +++ b/tools/testing/selftests/bpf/config.x86_64 @@ -50,7 +50,6 @@ CONFIG_CRYPTO_SEQIV=y CONFIG_CRYPTO_XXHASH=y CONFIG_DCB=y CONFIG_DEBUG_ATOMIC_SLEEP=y -CONFIG_DEBUG_CREDENTIALS=y CONFIG_DEBUG_INFO_BTF=y CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y CONFIG_DEBUG_MEMORY_INIT=y diff --git a/tools/testing/selftests/bpf/progs/bpf_loop_bench.c b/tools/testing/selftests/bpf/progs/bpf_loop_bench.c index 4ce76eb064c41..d461746fd3c1e 100644 --- a/tools/testing/selftests/bpf/progs/bpf_loop_bench.c +++ b/tools/testing/selftests/bpf/progs/bpf_loop_bench.c @@ -15,13 +15,16 @@ static int empty_callback(__u32 index, void *data) return 0; } +static int outer_loop(__u32 index, void *data) +{ + bpf_loop(nr_loops, empty_callback, NULL, 0); + __sync_add_and_fetch(&hits, nr_loops); + return 0; +} + SEC("fentry/" SYS_PREFIX "sys_getpgid") int benchmark(void *ctx) { - for (int i = 0; i < 1000; i++) { - bpf_loop(nr_loops, empty_callback, NULL, 0); - - __sync_add_and_fetch(&hits, nr_loops); - } + bpf_loop(1000, outer_loop, NULL, 0); return 0; } diff --git a/tools/testing/selftests/bpf/progs/verifier_loops1.c b/tools/testing/selftests/bpf/progs/verifier_loops1.c index 5bc86af80a9ad..71735dbf33d4f 100644 --- a/tools/testing/selftests/bpf/progs/verifier_loops1.c +++ b/tools/testing/selftests/bpf/progs/verifier_loops1.c @@ -75,9 +75,10 @@ l0_%=: r0 += 1; \ " ::: __clobber_all); } -SEC("tracepoint") +SEC("socket") __description("bounded loop, start in the middle") -__failure __msg("back-edge") +__success +__failure_unpriv __msg_unpriv("back-edge") __naked void loop_start_in_the_middle(void) { asm volatile (" \ @@ -136,7 +137,9 @@ l0_%=: exit; \ SEC("tracepoint") __description("bounded recursion") -__failure __msg("back-edge") +__failure +/* verifier limitation in detecting max stack depth */ +__msg("the call stack of 8 frames is too deep !") __naked void bounded_recursion(void) { asm volatile (" \ diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c index 1bdf2b43e49ea..3d5cd51071f04 100644 --- a/tools/testing/selftests/bpf/verifier/calls.c +++ b/tools/testing/selftests/bpf/verifier/calls.c @@ -442,7 +442,7 @@ BPF_EXIT_INSN(), }, .prog_type = BPF_PROG_TYPE_TRACEPOINT, - .errstr = "back-edge from insn 0 to 0", + .errstr = "the call stack of 9 frames is too deep", .result = REJECT, }, { @@ -799,7 +799,7 @@ BPF_EXIT_INSN(), }, .prog_type = BPF_PROG_TYPE_TRACEPOINT, - .errstr = "back-edge", + .errstr = "the call stack of 9 frames is too deep", .result = REJECT, }, { @@ -811,7 +811,7 @@ BPF_EXIT_INSN(), }, .prog_type = BPF_PROG_TYPE_TRACEPOINT, - .errstr = "back-edge", + .errstr = "the call stack of 9 frames is too deep", .result = REJECT, }, { diff --git a/tools/testing/selftests/bpf/verifier/ld_imm64.c b/tools/testing/selftests/bpf/verifier/ld_imm64.c index f9297900cea6d..78f19c255f20b 100644 --- a/tools/testing/selftests/bpf/verifier/ld_imm64.c +++ b/tools/testing/selftests/bpf/verifier/ld_imm64.c @@ -9,8 +9,8 @@ BPF_MOV64_IMM(BPF_REG_0, 2), BPF_EXIT_INSN(), }, - .errstr = "invalid BPF_LD_IMM insn", - .errstr_unpriv = "R1 pointer comparison", + .errstr = "jump into the middle of ldimm64 insn 1", + .errstr_unpriv = "jump into the middle of ldimm64 insn 1", .result = REJECT, }, { @@ -23,8 +23,8 @@ BPF_LD_IMM64(BPF_REG_0, 1), BPF_EXIT_INSN(), }, - .errstr = "invalid BPF_LD_IMM insn", - .errstr_unpriv = "R1 pointer comparison", + .errstr = "jump into the middle of ldimm64 insn 1", + .errstr_unpriv = "jump into the middle of ldimm64 insn 1", .result = REJECT, }, { diff --git a/tools/testing/selftests/clone3/clone3.c b/tools/testing/selftests/clone3/clone3.c index e60cf4da8fb07..1c61e3c022cb8 100644 --- a/tools/testing/selftests/clone3/clone3.c +++ b/tools/testing/selftests/clone3/clone3.c @@ -196,7 +196,12 @@ int main(int argc, char *argv[]) CLONE3_ARGS_NO_TEST); /* Do a clone3() in a new time namespace */ - test_clone3(CLONE_NEWTIME, 0, 0, CLONE3_ARGS_NO_TEST); + if (access("/proc/self/ns/time", F_OK) == 0) { + test_clone3(CLONE_NEWTIME, 0, 0, CLONE3_ARGS_NO_TEST); + } else { + ksft_print_msg("Time namespaces are not supported\n"); + ksft_test_result_skip("Skipping clone3() with CLONE_NEWTIME\n"); + } /* Do a clone3() with exit signal (SIGCHLD) in flags */ test_clone3(SIGCHLD, 0, -EINVAL, CLONE3_ARGS_NO_TEST); diff --git a/tools/testing/selftests/efivarfs/create-read.c b/tools/testing/selftests/efivarfs/create-read.c index 9674a19396a32..7bc7af4eb2c17 100644 --- a/tools/testing/selftests/efivarfs/create-read.c +++ b/tools/testing/selftests/efivarfs/create-read.c @@ -32,8 +32,10 @@ int main(int argc, char **argv) rc = read(fd, buf, sizeof(buf)); if (rc != 0) { fprintf(stderr, "Reading a new var should return EOF\n"); + close(fd); return EXIT_FAILURE; } + close(fd); return EXIT_SUCCESS; } diff --git a/tools/testing/selftests/hid/config.common b/tools/testing/selftests/hid/config.common index 0617275d93cc7..0f456dbab62f3 100644 --- a/tools/testing/selftests/hid/config.common +++ b/tools/testing/selftests/hid/config.common @@ -46,7 +46,6 @@ CONFIG_CRYPTO_SEQIV=y CONFIG_CRYPTO_XXHASH=y CONFIG_DCB=y CONFIG_DEBUG_ATOMIC_SLEEP=y -CONFIG_DEBUG_CREDENTIALS=y CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y CONFIG_DEBUG_MEMORY_INIT=y CONFIG_DEFAULT_FQ_CODEL=y diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index 118e0964bda94..aa646e0661f36 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -44,26 +44,10 @@ endif selfdir = $(realpath $(dir $(filter %/lib.mk,$(MAKEFILE_LIST)))) top_srcdir = $(selfdir)/../../.. -ifeq ("$(origin O)", "command line") - KBUILD_OUTPUT := $(O) +ifeq ($(KHDR_INCLUDES),) +KHDR_INCLUDES := -isystem $(top_srcdir)/usr/include endif -ifneq ($(KBUILD_OUTPUT),) - # Make's built-in functions such as $(abspath ...), $(realpath ...) cannot - # expand a shell special character '~'. We use a somewhat tedious way here. - abs_objtree := $(shell cd $(top_srcdir) && mkdir -p $(KBUILD_OUTPUT) && cd $(KBUILD_OUTPUT) && pwd) - $(if $(abs_objtree),, \ - $(error failed to create output directory "$(KBUILD_OUTPUT)")) - # $(realpath ...) resolves symlinks - abs_objtree := $(realpath $(abs_objtree)) - KHDR_DIR := ${abs_objtree}/usr/include -else - abs_srctree := $(shell cd $(top_srcdir) && pwd) - KHDR_DIR := ${abs_srctree}/usr/include -endif - -KHDR_INCLUDES := -isystem $(KHDR_DIR) - # The following are built by lib.mk common compile rules. # TEST_CUSTOM_PROGS should be used by tests that require # custom build rule and prevent common build rule use. @@ -74,25 +58,7 @@ TEST_GEN_PROGS := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS)) TEST_GEN_PROGS_EXTENDED := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS_EXTENDED)) TEST_GEN_FILES := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_FILES)) -all: kernel_header_files $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) \ - $(TEST_GEN_FILES) - -kernel_header_files: - @ls $(KHDR_DIR)/linux/*.h >/dev/null 2>/dev/null; \ - if [ $$? -ne 0 ]; then \ - RED='\033[1;31m'; \ - NOCOLOR='\033[0m'; \ - echo; \ - echo -e "$${RED}error$${NOCOLOR}: missing kernel header files."; \ - echo "Please run this and try again:"; \ - echo; \ - echo " cd $(top_srcdir)"; \ - echo " make headers"; \ - echo; \ - exit 1; \ - fi - -.PHONY: kernel_header_files +all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) define RUN_TESTS BASE_DIR="$(selfdir)"; \ diff --git a/tools/testing/selftests/lkdtm/config b/tools/testing/selftests/lkdtm/config index 5d52f64dfb430..7afe05e8c4d79 100644 --- a/tools/testing/selftests/lkdtm/config +++ b/tools/testing/selftests/lkdtm/config @@ -9,7 +9,6 @@ CONFIG_INIT_ON_FREE_DEFAULT_ON=y CONFIG_INIT_ON_ALLOC_DEFAULT_ON=y CONFIG_UBSAN=y CONFIG_UBSAN_BOUNDS=y -CONFIG_UBSAN_TRAP=y CONFIG_STACKPROTECTOR_STRONG=y CONFIG_SLUB_DEBUG=y CONFIG_SLUB_DEBUG_ON=y diff --git a/tools/testing/selftests/lkdtm/tests.txt b/tools/testing/selftests/lkdtm/tests.txt index 607b8d7e3ea34..2f3a1b96da6e3 100644 --- a/tools/testing/selftests/lkdtm/tests.txt +++ b/tools/testing/selftests/lkdtm/tests.txt @@ -7,7 +7,7 @@ EXCEPTION #EXHAUST_STACK Corrupts memory on failure #CORRUPT_STACK Crashes entire system on success #CORRUPT_STACK_STRONG Crashes entire system on success -ARRAY_BOUNDS +ARRAY_BOUNDS call trace:|UBSAN: array-index-out-of-bounds CORRUPT_LIST_ADD list_add corruption CORRUPT_LIST_DEL list_del corruption STACK_GUARD_PAGE_LEADING diff --git a/tools/testing/selftests/mm/cow.c b/tools/testing/selftests/mm/cow.c index 7324ce5363c0c..6f2f839904416 100644 --- a/tools/testing/selftests/mm/cow.c +++ b/tools/testing/selftests/mm/cow.c @@ -1680,6 +1680,8 @@ int main(int argc, char **argv) { int err; + ksft_print_header(); + pagesize = getpagesize(); thpsize = read_pmd_pagesize(); if (thpsize) @@ -1689,7 +1691,6 @@ int main(int argc, char **argv) ARRAY_SIZE(hugetlbsizes)); detect_huge_zeropage(); - ksft_print_header(); ksft_set_plan(ARRAY_SIZE(anon_test_cases) * tests_per_anon_test_case() + ARRAY_SIZE(anon_thp_test_cases) * tests_per_anon_thp_test_case() + ARRAY_SIZE(non_anon_test_cases) * tests_per_non_anon_test_case()); diff --git a/tools/testing/selftests/mm/memfd_secret.c b/tools/testing/selftests/mm/memfd_secret.c index 957b9e18c7295..9b298f6a04b37 100644 --- a/tools/testing/selftests/mm/memfd_secret.c +++ b/tools/testing/selftests/mm/memfd_secret.c @@ -62,6 +62,9 @@ static void test_mlock_limit(int fd) char *mem; len = mlock_limit_cur; + if (len % page_size != 0) + len = (len/page_size) * page_size; + mem = mmap(NULL, len, prot, mode, fd, 0); if (mem == MAP_FAILED) { fail("unable to mmap secret memory\n"); diff --git a/tools/testing/selftests/net/af_unix/diag_uid.c b/tools/testing/selftests/net/af_unix/diag_uid.c index 5b88f7129fea4..79a3dd75590e8 100644 --- a/tools/testing/selftests/net/af_unix/diag_uid.c +++ b/tools/testing/selftests/net/af_unix/diag_uid.c @@ -148,7 +148,6 @@ void receive_response(struct __test_metadata *_metadata, .msg_iov = &iov, .msg_iovlen = 1 }; - struct unix_diag_req *udr; struct nlmsghdr *nlh; int ret; diff --git a/tools/testing/selftests/net/cmsg_sender.c b/tools/testing/selftests/net/cmsg_sender.c index 24b21b15ed3fb..6ff3e732f449f 100644 --- a/tools/testing/selftests/net/cmsg_sender.c +++ b/tools/testing/selftests/net/cmsg_sender.c @@ -416,9 +416,9 @@ int main(int argc, char *argv[]) { struct addrinfo hints, *ai; struct iovec iov[1]; + unsigned char *buf; struct msghdr msg; char cbuf[1024]; - char *buf; int err; int fd; diff --git a/tools/testing/selftests/net/ipsec.c b/tools/testing/selftests/net/ipsec.c index 9a8229abfa026..be4a30a0d02ae 100644 --- a/tools/testing/selftests/net/ipsec.c +++ b/tools/testing/selftests/net/ipsec.c @@ -2263,7 +2263,7 @@ static int check_results(void) int main(int argc, char **argv) { - unsigned int nr_process = 1; + long nr_process = 1; int route_sock = -1, ret = KSFT_SKIP; int test_desc_fd[2]; uint32_t route_seq; @@ -2284,7 +2284,7 @@ int main(int argc, char **argv) exit_usage(argv); } - if (nr_process > MAX_PROCESSES || !nr_process) { + if (nr_process > MAX_PROCESSES || nr_process < 1) { printk("nr_process should be between [1; %u]", MAX_PROCESSES); exit_usage(argv); diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c index c7f9ebeebc2c5..d2043ec3bf6d6 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.c +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c @@ -18,6 +18,7 @@ #include #include +#include #include #include #include @@ -1125,15 +1126,11 @@ int main_loop_s(int listensock) static void init_rng(void) { - int fd = open("/dev/urandom", O_RDONLY); unsigned int foo; - if (fd > 0) { - int ret = read(fd, &foo, sizeof(foo)); - - if (ret < 0) - srand(fd + foo); - close(fd); + if (getrandom(&foo, sizeof(foo), 0) == -1) { + perror("getrandom"); + exit(1); } srand(foo); diff --git a/tools/testing/selftests/net/mptcp/mptcp_inq.c b/tools/testing/selftests/net/mptcp/mptcp_inq.c index 8672d898f8cda..218aac4673212 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_inq.c +++ b/tools/testing/selftests/net/mptcp/mptcp_inq.c @@ -18,6 +18,7 @@ #include #include +#include #include #include #include @@ -519,15 +520,11 @@ static int client(int unixfd) static void init_rng(void) { - int fd = open("/dev/urandom", O_RDONLY); unsigned int foo; - if (fd > 0) { - int ret = read(fd, &foo, sizeof(foo)); - - if (ret < 0) - srand(fd + foo); - close(fd); + if (getrandom(&foo, sizeof(foo), 0) == -1) { + perror("getrandom"); + exit(1); } srand(foo); diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 5917a74b749d0..4632a954c73e6 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -2773,7 +2773,7 @@ backup_tests() fi if reset "mpc backup" && - continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then + continue_if mptcp_lib_kallsyms_doesnt_have "T mptcp_subflow_send_ack$"; then pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,backup speed=slow \ run_tests $ns1 $ns2 10.0.1.1 @@ -2782,7 +2782,7 @@ backup_tests() fi if reset "mpc backup both sides" && - continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then + continue_if mptcp_lib_kallsyms_doesnt_have "T mptcp_subflow_send_ack$"; then pm_nl_add_endpoint $ns1 10.0.1.1 flags subflow,backup pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,backup speed=slow \ @@ -2792,7 +2792,7 @@ backup_tests() fi if reset "mpc switch to backup" && - continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then + continue_if mptcp_lib_kallsyms_doesnt_have "T mptcp_subflow_send_ack$"; then pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow sflags=backup speed=slow \ run_tests $ns1 $ns2 10.0.1.1 @@ -2801,7 +2801,7 @@ backup_tests() fi if reset "mpc switch to backup both sides" && - continue_if mptcp_lib_kallsyms_doesnt_have "mptcp_subflow_send_ack$"; then + continue_if mptcp_lib_kallsyms_doesnt_have "T mptcp_subflow_send_ack$"; then pm_nl_add_endpoint $ns1 10.0.1.1 flags subflow pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow sflags=backup speed=slow \ @@ -3237,7 +3237,7 @@ fastclose_tests() if reset_check_counter "fastclose server test" "MPTcpExtMPFastcloseRx"; then test_linkfail=1024 fastclose=server \ run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr 0 0 0 + chk_join_nr 0 0 0 0 0 0 1 chk_fclose_nr 1 1 invert chk_rst_nr 1 1 fi diff --git a/tools/testing/selftests/resctrl/Makefile b/tools/testing/selftests/resctrl/Makefile index 5073dbc961258..2deac2031de9e 100644 --- a/tools/testing/selftests/resctrl/Makefile +++ b/tools/testing/selftests/resctrl/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 -CFLAGS = -g -Wall -O2 -D_FORTIFY_SOURCE=2 +CFLAGS = -g -Wall -O2 -D_FORTIFY_SOURCE=2 -D_GNU_SOURCE CFLAGS += $(KHDR_INCLUDES) TEST_GEN_PROGS := resctrl_tests diff --git a/tools/testing/selftests/resctrl/cache.c b/tools/testing/selftests/resctrl/cache.c index d3cbb829ff6a7..a0318bd3a63d8 100644 --- a/tools/testing/selftests/resctrl/cache.c +++ b/tools/testing/selftests/resctrl/cache.c @@ -205,10 +205,11 @@ int measure_cache_vals(struct resctrl_val_param *param, int bm_pid) * cache_val: execute benchmark and measure LLC occupancy resctrl * and perf cache miss for the benchmark * @param: parameters passed to cache_val() + * @span: buffer size for the benchmark * * Return: 0 on success. non-zero on failure. */ -int cat_val(struct resctrl_val_param *param) +int cat_val(struct resctrl_val_param *param, size_t span) { int memflush = 1, operation = 0, ret = 0; char *resctrl_val = param->resctrl_val; @@ -245,7 +246,7 @@ int cat_val(struct resctrl_val_param *param) if (ret) break; - if (run_fill_buf(param->span, memflush, operation, true)) { + if (run_fill_buf(span, memflush, operation, true)) { fprintf(stderr, "Error-running fill buffer\n"); ret = -1; goto pe_close; diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c index 3848dfb46aba4..224ba8544d8af 100644 --- a/tools/testing/selftests/resctrl/cat_test.c +++ b/tools/testing/selftests/resctrl/cat_test.c @@ -41,7 +41,7 @@ static int cat_setup(struct resctrl_val_param *p) return ret; } -static int check_results(struct resctrl_val_param *param) +static int check_results(struct resctrl_val_param *param, size_t span) { char *token_array[8], temp[512]; unsigned long sum_llc_perf_miss = 0; @@ -76,7 +76,7 @@ static int check_results(struct resctrl_val_param *param) fclose(fp); no_of_bits = count_bits(param->mask); - return show_cache_info(sum_llc_perf_miss, no_of_bits, param->span / 64, + return show_cache_info(sum_llc_perf_miss, no_of_bits, span / 64, MAX_DIFF, MAX_DIFF_PERCENT, runs - 1, get_vendor() == ARCH_INTEL, false); } @@ -96,6 +96,7 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type) char cbm_mask[256]; int count_of_bits; char pipe_message; + size_t span; /* Get default cbm mask for L3/L2 cache */ ret = get_cbm_mask(cache_type, cbm_mask); @@ -140,7 +141,7 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type) /* Set param values for parent thread which will be allocated bitmask * with (max_bits - n) bits */ - param.span = cache_size * (count_of_bits - n) / count_of_bits; + span = cache_size * (count_of_bits - n) / count_of_bits; strcpy(param.ctrlgrp, "c2"); strcpy(param.mongrp, "m2"); strcpy(param.filename, RESULT_FILE_NAME2); @@ -162,23 +163,17 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type) param.mask = l_mask_1; strcpy(param.ctrlgrp, "c1"); strcpy(param.mongrp, "m1"); - param.span = cache_size * n / count_of_bits; + span = cache_size * n / count_of_bits; strcpy(param.filename, RESULT_FILE_NAME1); param.num_of_runs = 0; param.cpu_no = sibling_cpu_no; - } else { - ret = signal_handler_register(); - if (ret) { - kill(bm_pid, SIGKILL); - goto out; - } } remove(param.filename); - ret = cat_val(¶m); + ret = cat_val(¶m, span); if (ret == 0) - ret = check_results(¶m); + ret = check_results(¶m, span); if (bm_pid == 0) { /* Tell parent that child is ready */ @@ -208,10 +203,8 @@ int cat_perf_miss_val(int cpu_no, int n, char *cache_type) } close(pipefd[0]); kill(bm_pid, SIGKILL); - signal_handler_unregister(); } -out: cat_test_cleanup(); return ret; diff --git a/tools/testing/selftests/resctrl/cmt_test.c b/tools/testing/selftests/resctrl/cmt_test.c index cb2197647c6cd..50bdbce9fba95 100644 --- a/tools/testing/selftests/resctrl/cmt_test.c +++ b/tools/testing/selftests/resctrl/cmt_test.c @@ -27,7 +27,7 @@ static int cmt_setup(struct resctrl_val_param *p) return 0; } -static int check_results(struct resctrl_val_param *param, int no_of_bits) +static int check_results(struct resctrl_val_param *param, size_t span, int no_of_bits) { char *token_array[8], temp[512]; unsigned long sum_llc_occu_resc = 0; @@ -58,7 +58,7 @@ static int check_results(struct resctrl_val_param *param, int no_of_bits) } fclose(fp); - return show_cache_info(sum_llc_occu_resc, no_of_bits, param->span, + return show_cache_info(sum_llc_occu_resc, no_of_bits, span, MAX_DIFF, MAX_DIFF_PERCENT, runs - 1, true, true); } @@ -68,16 +68,17 @@ void cmt_test_cleanup(void) remove(RESULT_FILE_NAME); } -int cmt_resctrl_val(int cpu_no, int n, char **benchmark_cmd) +int cmt_resctrl_val(int cpu_no, int n, const char * const *benchmark_cmd) { + const char * const *cmd = benchmark_cmd; + const char *new_cmd[BENCHMARK_ARGS]; unsigned long cache_size = 0; unsigned long long_mask; + char *span_str = NULL; char cbm_mask[256]; int count_of_bits; - int ret; - - if (!validate_resctrl_feature_request(CMT_STR)) - return -1; + size_t span; + int ret, i; ret = get_cbm_mask("L3", cbm_mask); if (ret) @@ -105,24 +106,36 @@ int cmt_resctrl_val(int cpu_no, int n, char **benchmark_cmd) .cpu_no = cpu_no, .filename = RESULT_FILE_NAME, .mask = ~(long_mask << n) & long_mask, - .span = cache_size * n / count_of_bits, .num_of_runs = 0, .setup = cmt_setup, }; - if (strcmp(benchmark_cmd[0], "fill_buf") == 0) - sprintf(benchmark_cmd[1], "%zu", param.span); + span = cache_size * n / count_of_bits; + + if (strcmp(cmd[0], "fill_buf") == 0) { + /* Duplicate the command to be able to replace span in it */ + for (i = 0; benchmark_cmd[i]; i++) + new_cmd[i] = benchmark_cmd[i]; + new_cmd[i] = NULL; + + ret = asprintf(&span_str, "%zu", span); + if (ret < 0) + return -1; + new_cmd[1] = span_str; + cmd = new_cmd; + } remove(RESULT_FILE_NAME); - ret = resctrl_val(benchmark_cmd, ¶m); + ret = resctrl_val(cmd, ¶m); if (ret) goto out; - ret = check_results(¶m, n); + ret = check_results(¶m, span, n); out: cmt_test_cleanup(); + free(span_str); return ret; } diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c index 4d2f145804b83..d3bf4368341ec 100644 --- a/tools/testing/selftests/resctrl/mba_test.c +++ b/tools/testing/selftests/resctrl/mba_test.c @@ -12,7 +12,7 @@ #define RESULT_FILE_NAME "result_mba" #define NUM_OF_RUNS 5 -#define MAX_DIFF_PERCENT 5 +#define MAX_DIFF_PERCENT 8 #define ALLOCATION_MAX 100 #define ALLOCATION_MIN 10 #define ALLOCATION_STEP 10 @@ -141,7 +141,7 @@ void mba_test_cleanup(void) remove(RESULT_FILE_NAME); } -int mba_schemata_change(int cpu_no, char *bw_report, char **benchmark_cmd) +int mba_schemata_change(int cpu_no, const char * const *benchmark_cmd) { struct resctrl_val_param param = { .resctrl_val = MBA_STR, @@ -149,7 +149,7 @@ int mba_schemata_change(int cpu_no, char *bw_report, char **benchmark_cmd) .mongrp = "m1", .cpu_no = cpu_no, .filename = RESULT_FILE_NAME, - .bw_report = bw_report, + .bw_report = "reads", .setup = mba_setup }; int ret; diff --git a/tools/testing/selftests/resctrl/mbm_test.c b/tools/testing/selftests/resctrl/mbm_test.c index c7de6f5977f69..d3c0d30c676a7 100644 --- a/tools/testing/selftests/resctrl/mbm_test.c +++ b/tools/testing/selftests/resctrl/mbm_test.c @@ -11,7 +11,7 @@ #include "resctrl.h" #define RESULT_FILE_NAME "result_mbm" -#define MAX_DIFF_PERCENT 5 +#define MAX_DIFF_PERCENT 8 #define NUM_OF_RUNS 5 static int @@ -109,16 +109,15 @@ void mbm_test_cleanup(void) remove(RESULT_FILE_NAME); } -int mbm_bw_change(size_t span, int cpu_no, char *bw_report, char **benchmark_cmd) +int mbm_bw_change(int cpu_no, const char * const *benchmark_cmd) { struct resctrl_val_param param = { .resctrl_val = MBM_STR, .ctrlgrp = "c1", .mongrp = "m1", - .span = span, .cpu_no = cpu_no, .filename = RESULT_FILE_NAME, - .bw_report = bw_report, + .bw_report = "reads", .setup = mbm_setup }; int ret; @@ -129,7 +128,7 @@ int mbm_bw_change(size_t span, int cpu_no, char *bw_report, char **benchmark_cmd if (ret) goto out; - ret = check_results(span); + ret = check_results(DEFAULT_SPAN); out: mbm_test_cleanup(); diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h index 838d1a438f335..8578a8b4e1459 100644 --- a/tools/testing/selftests/resctrl/resctrl.h +++ b/tools/testing/selftests/resctrl/resctrl.h @@ -1,5 +1,4 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#define _GNU_SOURCE #ifndef RESCTRL_H #define RESCTRL_H #include @@ -28,16 +27,16 @@ #define RESCTRL_PATH "/sys/fs/resctrl" #define PHYS_ID_PATH "/sys/devices/system/cpu/cpu" #define INFO_PATH "/sys/fs/resctrl/info" -#define L3_PATH "/sys/fs/resctrl/info/L3" -#define MB_PATH "/sys/fs/resctrl/info/MB" -#define L3_MON_PATH "/sys/fs/resctrl/info/L3_MON" -#define L3_MON_FEATURES_PATH "/sys/fs/resctrl/info/L3_MON/mon_features" #define ARCH_INTEL 1 #define ARCH_AMD 2 #define END_OF_TESTS 1 +#define BENCHMARK_ARGS 64 + +#define DEFAULT_SPAN (250 * MB) + #define PARENT_EXIT(err_msg) \ do { \ perror(err_msg); \ @@ -52,7 +51,6 @@ * @ctrlgrp: Name of the control monitor group (con_mon grp) * @mongrp: Name of the monitor group (mon grp) * @cpu_no: CPU number to which the benchmark would be binded - * @span: Memory bytes accessed in each benchmark iteration * @filename: Name of file to which the o/p should be written * @bw_report: Bandwidth report type (reads vs writes) * @setup: Call back function to setup test environment @@ -62,7 +60,6 @@ struct resctrl_val_param { char ctrlgrp[64]; char mongrp[64]; int cpu_no; - size_t span; char filename[64]; char *bw_report; unsigned long mask; @@ -86,7 +83,7 @@ int get_resource_id(int cpu_no, int *resource_id); int mount_resctrlfs(void); int umount_resctrlfs(void); int validate_bw_report_request(char *bw_report); -bool validate_resctrl_feature_request(const char *resctrl_val); +bool validate_resctrl_feature_request(const char *resource, const char *feature); char *fgrep(FILE *inf, const char *str); int taskset_benchmark(pid_t bm_pid, int cpu_no); void run_benchmark(int signum, siginfo_t *info, void *ucontext); @@ -97,21 +94,21 @@ int write_bm_pid_to_resctrl(pid_t bm_pid, char *ctrlgrp, char *mongrp, int perf_event_open(struct perf_event_attr *hw_event, pid_t pid, int cpu, int group_fd, unsigned long flags); int run_fill_buf(size_t span, int memflush, int op, bool once); -int resctrl_val(char **benchmark_cmd, struct resctrl_val_param *param); -int mbm_bw_change(size_t span, int cpu_no, char *bw_report, char **benchmark_cmd); +int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *param); +int mbm_bw_change(int cpu_no, const char * const *benchmark_cmd); void tests_cleanup(void); void mbm_test_cleanup(void); -int mba_schemata_change(int cpu_no, char *bw_report, char **benchmark_cmd); +int mba_schemata_change(int cpu_no, const char * const *benchmark_cmd); void mba_test_cleanup(void); int get_cbm_mask(char *cache_type, char *cbm_mask); int get_cache_size(int cpu_no, char *cache_type, unsigned long *cache_size); void ctrlc_handler(int signum, siginfo_t *info, void *ptr); int signal_handler_register(void); void signal_handler_unregister(void); -int cat_val(struct resctrl_val_param *param); +int cat_val(struct resctrl_val_param *param, size_t span); void cat_test_cleanup(void); int cat_perf_miss_val(int cpu_no, int no_of_bits, char *cache_type); -int cmt_resctrl_val(int cpu_no, int n, char **benchmark_cmd); +int cmt_resctrl_val(int cpu_no, int n, const char * const *benchmark_cmd); unsigned int count_bits(unsigned long n); void cmt_test_cleanup(void); int get_core_sibling(int cpu_no); diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c index 9e2bc8ba95f13..31373b69e675d 100644 --- a/tools/testing/selftests/resctrl/resctrl_tests.c +++ b/tools/testing/selftests/resctrl/resctrl_tests.c @@ -10,9 +10,6 @@ */ #include "resctrl.h" -#define BENCHMARK_ARGS 64 -#define BENCHMARK_ARG_SIZE 64 - static int detect_vendor(void) { FILE *inf = fopen("/proc/cpuinfo", "r"); @@ -70,72 +67,98 @@ void tests_cleanup(void) cat_test_cleanup(); } -static void run_mbm_test(char **benchmark_cmd, size_t span, - int cpu_no, char *bw_report) +static int test_prepare(void) { int res; - ksft_print_msg("Starting MBM BW change ...\n"); + res = signal_handler_register(); + if (res) { + ksft_print_msg("Failed to register signal handler\n"); + return res; + } res = mount_resctrlfs(); if (res) { - ksft_exit_fail_msg("Failed to mount resctrl FS\n"); + signal_handler_unregister(); + ksft_print_msg("Failed to mount resctrl FS\n"); + return res; + } + return 0; +} + +static void test_cleanup(void) +{ + umount_resctrlfs(); + signal_handler_unregister(); +} + +static void run_mbm_test(const char * const *benchmark_cmd, int cpu_no) +{ + int res; + + ksft_print_msg("Starting MBM BW change ...\n"); + + if (test_prepare()) { + ksft_exit_fail_msg("Abnormal failure when preparing for the test\n"); return; } - if (!validate_resctrl_feature_request(MBM_STR) || (get_vendor() != ARCH_INTEL)) { + if (!validate_resctrl_feature_request("L3_MON", "mbm_total_bytes") || + !validate_resctrl_feature_request("L3_MON", "mbm_local_bytes") || + (get_vendor() != ARCH_INTEL)) { ksft_test_result_skip("Hardware does not support MBM or MBM is disabled\n"); - goto umount; + goto cleanup; } - res = mbm_bw_change(span, cpu_no, bw_report, benchmark_cmd); + res = mbm_bw_change(cpu_no, benchmark_cmd); ksft_test_result(!res, "MBM: bw change\n"); if ((get_vendor() == ARCH_INTEL) && res) ksft_print_msg("Intel MBM may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n"); -umount: - umount_resctrlfs(); +cleanup: + test_cleanup(); } -static void run_mba_test(char **benchmark_cmd, int cpu_no, char *bw_report) +static void run_mba_test(const char * const *benchmark_cmd, int cpu_no) { int res; ksft_print_msg("Starting MBA Schemata change ...\n"); - res = mount_resctrlfs(); - if (res) { - ksft_exit_fail_msg("Failed to mount resctrl FS\n"); + if (test_prepare()) { + ksft_exit_fail_msg("Abnormal failure when preparing for the test\n"); return; } - if (!validate_resctrl_feature_request(MBA_STR) || (get_vendor() != ARCH_INTEL)) { + if (!validate_resctrl_feature_request("MB", NULL) || + !validate_resctrl_feature_request("L3_MON", "mbm_local_bytes") || + (get_vendor() != ARCH_INTEL)) { ksft_test_result_skip("Hardware does not support MBA or MBA is disabled\n"); - goto umount; + goto cleanup; } - res = mba_schemata_change(cpu_no, bw_report, benchmark_cmd); + res = mba_schemata_change(cpu_no, benchmark_cmd); ksft_test_result(!res, "MBA: schemata change\n"); -umount: - umount_resctrlfs(); +cleanup: + test_cleanup(); } -static void run_cmt_test(char **benchmark_cmd, int cpu_no) +static void run_cmt_test(const char * const *benchmark_cmd, int cpu_no) { int res; ksft_print_msg("Starting CMT test ...\n"); - res = mount_resctrlfs(); - if (res) { - ksft_exit_fail_msg("Failed to mount resctrl FS\n"); + if (test_prepare()) { + ksft_exit_fail_msg("Abnormal failure when preparing for the test\n"); return; } - if (!validate_resctrl_feature_request(CMT_STR)) { + if (!validate_resctrl_feature_request("L3_MON", "llc_occupancy") || + !validate_resctrl_feature_request("L3", NULL)) { ksft_test_result_skip("Hardware does not support CMT or CMT is disabled\n"); - goto umount; + goto cleanup; } res = cmt_resctrl_val(cpu_no, 5, benchmark_cmd); @@ -143,8 +166,8 @@ static void run_cmt_test(char **benchmark_cmd, int cpu_no) if ((get_vendor() == ARCH_INTEL) && res) ksft_print_msg("Intel CMT may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n"); -umount: - umount_resctrlfs(); +cleanup: + test_cleanup(); } static void run_cat_test(int cpu_no, int no_of_bits) @@ -153,33 +176,32 @@ static void run_cat_test(int cpu_no, int no_of_bits) ksft_print_msg("Starting CAT test ...\n"); - res = mount_resctrlfs(); - if (res) { - ksft_exit_fail_msg("Failed to mount resctrl FS\n"); + if (test_prepare()) { + ksft_exit_fail_msg("Abnormal failure when preparing for the test\n"); return; } - if (!validate_resctrl_feature_request(CAT_STR)) { + if (!validate_resctrl_feature_request("L3", NULL)) { ksft_test_result_skip("Hardware does not support CAT or CAT is disabled\n"); - goto umount; + goto cleanup; } res = cat_perf_miss_val(cpu_no, no_of_bits, "L3"); ksft_test_result(!res, "CAT: test\n"); -umount: - umount_resctrlfs(); +cleanup: + test_cleanup(); } int main(int argc, char **argv) { bool has_ben = false, mbm_test = true, mba_test = true, cmt_test = true; - char *benchmark_cmd[BENCHMARK_ARGS], bw_report[64], bm_type[64]; - char benchmark_cmd_area[BENCHMARK_ARGS][BENCHMARK_ARG_SIZE]; int c, cpu_no = 1, argc_new = argc, i, no_of_bits = 0; + const char *benchmark_cmd[BENCHMARK_ARGS]; int ben_ind, ben_count, tests = 0; - size_t span = 250 * MB; + char *span_str = NULL; bool cat_test = true; + int ret; for (i = 0; i < argc; i++) { if (strcmp(argv[i], "-b") == 0) { @@ -259,29 +281,22 @@ int main(int argc, char **argv) ksft_exit_fail_msg("Too long benchmark command.\n"); /* Extract benchmark command from command line. */ - for (i = ben_ind; i < argc; i++) { - benchmark_cmd[i - ben_ind] = benchmark_cmd_area[i]; - if (strlen(argv[i]) >= BENCHMARK_ARG_SIZE) - ksft_exit_fail_msg("Too long benchmark command argument.\n"); - sprintf(benchmark_cmd[i - ben_ind], "%s", argv[i]); - } + for (i = 0; i < argc - ben_ind; i++) + benchmark_cmd[i] = argv[i + ben_ind]; benchmark_cmd[ben_count] = NULL; } else { /* If no benchmark is given by "-b" argument, use fill_buf. */ - for (i = 0; i < 5; i++) - benchmark_cmd[i] = benchmark_cmd_area[i]; - - strcpy(benchmark_cmd[0], "fill_buf"); - sprintf(benchmark_cmd[1], "%zu", span); - strcpy(benchmark_cmd[2], "1"); - strcpy(benchmark_cmd[3], "0"); - strcpy(benchmark_cmd[4], "false"); + benchmark_cmd[0] = "fill_buf"; + ret = asprintf(&span_str, "%u", DEFAULT_SPAN); + if (ret < 0) + ksft_exit_fail_msg("Out of memory!\n"); + benchmark_cmd[1] = span_str; + benchmark_cmd[2] = "1"; + benchmark_cmd[3] = "0"; + benchmark_cmd[4] = "false"; benchmark_cmd[5] = NULL; } - sprintf(bw_report, "reads"); - sprintf(bm_type, "fill_buf"); - if (!check_resctrlfs_support()) return ksft_exit_skip("resctrl FS does not exist. Enable X86_CPU_RESCTRL config option.\n"); @@ -293,10 +308,10 @@ int main(int argc, char **argv) ksft_set_plan(tests ? : 4); if (mbm_test) - run_mbm_test(benchmark_cmd, span, cpu_no, bw_report); + run_mbm_test(benchmark_cmd, cpu_no); if (mba_test) - run_mba_test(benchmark_cmd, cpu_no, bw_report); + run_mba_test(benchmark_cmd, cpu_no); if (cmt_test) run_cmt_test(benchmark_cmd, cpu_no); @@ -304,5 +319,6 @@ int main(int argc, char **argv) if (cat_test) run_cat_test(cpu_no, no_of_bits); + free(span_str); ksft_finished(); } diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c index f0f6c5f6e98b9..b8ca6fa40b3bf 100644 --- a/tools/testing/selftests/resctrl/resctrl_val.c +++ b/tools/testing/selftests/resctrl/resctrl_val.c @@ -468,7 +468,9 @@ pid_t bm_pid, ppid; void ctrlc_handler(int signum, siginfo_t *info, void *ptr) { - kill(bm_pid, SIGKILL); + /* Only kill child after bm_pid is set after fork() */ + if (bm_pid) + kill(bm_pid, SIGKILL); umount_resctrlfs(); tests_cleanup(); ksft_print_msg("Ending\n\n"); @@ -482,9 +484,11 @@ void ctrlc_handler(int signum, siginfo_t *info, void *ptr) */ int signal_handler_register(void) { - struct sigaction sigact; + struct sigaction sigact = {}; int ret = 0; + bm_pid = 0; + sigact.sa_sigaction = ctrlc_handler; sigemptyset(&sigact.sa_mask); sigact.sa_flags = SA_SIGINFO; @@ -504,7 +508,7 @@ int signal_handler_register(void) */ void signal_handler_unregister(void) { - struct sigaction sigact; + struct sigaction sigact = {}; sigact.sa_handler = SIG_DFL; sigemptyset(&sigact.sa_mask); @@ -629,7 +633,7 @@ measure_vals(struct resctrl_val_param *param, unsigned long *bw_resc_start) * * Return: 0 on success. non-zero on failure. */ -int resctrl_val(char **benchmark_cmd, struct resctrl_val_param *param) +int resctrl_val(const char * const *benchmark_cmd, struct resctrl_val_param *param) { char *resctrl_val = param->resctrl_val; unsigned long bw_resc_start = 0; @@ -706,28 +710,30 @@ int resctrl_val(char **benchmark_cmd, struct resctrl_val_param *param) ksft_print_msg("Benchmark PID: %d\n", bm_pid); - ret = signal_handler_register(); - if (ret) - goto out; - - value.sival_ptr = benchmark_cmd; + /* + * The cast removes constness but nothing mutates benchmark_cmd within + * the context of this process. At the receiving process, it becomes + * argv, which is mutable, on exec() but that's after fork() so it + * doesn't matter for the process running the tests. + */ + value.sival_ptr = (void *)benchmark_cmd; /* Taskset benchmark to specified cpu */ ret = taskset_benchmark(bm_pid, param->cpu_no); if (ret) - goto unregister; + goto out; /* Write benchmark to specified control&monitoring grp in resctrl FS */ ret = write_bm_pid_to_resctrl(bm_pid, param->ctrlgrp, param->mongrp, resctrl_val); if (ret) - goto unregister; + goto out; if (!strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR)) || !strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR))) { ret = initialize_mem_bw_imc(); if (ret) - goto unregister; + goto out; initialize_mem_bw_resctrl(param->ctrlgrp, param->mongrp, param->cpu_no, resctrl_val); @@ -742,7 +748,7 @@ int resctrl_val(char **benchmark_cmd, struct resctrl_val_param *param) sizeof(pipe_message)) { perror("# failed reading message from child process"); close(pipefd[0]); - goto unregister; + goto out; } } close(pipefd[0]); @@ -751,7 +757,7 @@ int resctrl_val(char **benchmark_cmd, struct resctrl_val_param *param) if (sigqueue(bm_pid, SIGUSR1, value) == -1) { perror("# sigqueue SIGUSR1 to child"); ret = errno; - goto unregister; + goto out; } /* Give benchmark enough time to fully run */ @@ -780,8 +786,6 @@ int resctrl_val(char **benchmark_cmd, struct resctrl_val_param *param) } } -unregister: - signal_handler_unregister(); out: kill(bm_pid, SIGKILL); diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c index bd36ee2066020..3a8111362d262 100644 --- a/tools/testing/selftests/resctrl/resctrlfs.c +++ b/tools/testing/selftests/resctrl/resctrlfs.c @@ -8,6 +8,8 @@ * Sai Praneeth Prakhya , * Fenghua Yu */ +#include + #include "resctrl.h" static int find_resctrl_mount(char *buffer) @@ -604,63 +606,46 @@ char *fgrep(FILE *inf, const char *str) /* * validate_resctrl_feature_request - Check if requested feature is valid. - * @resctrl_val: Requested feature + * @resource: Required resource (e.g., MB, L3, L2, L3_MON, etc.) + * @feature: Required monitor feature (in mon_features file). Can only be + * set for L3_MON. Must be NULL for all other resources. * - * Return: True if the feature is supported, else false. False is also - * returned if resctrl FS is not mounted. + * Return: True if the resource/feature is supported, else false. False is + * also returned if resctrl FS is not mounted. */ -bool validate_resctrl_feature_request(const char *resctrl_val) +bool validate_resctrl_feature_request(const char *resource, const char *feature) { + char res_path[PATH_MAX]; struct stat statbuf; - bool found = false; char *res; FILE *inf; int ret; - if (!resctrl_val) + if (!resource) return false; ret = find_resctrl_mount(NULL); if (ret) return false; - if (!strncmp(resctrl_val, CAT_STR, sizeof(CAT_STR))) { - if (!stat(L3_PATH, &statbuf)) - return true; - } else if (!strncmp(resctrl_val, MBA_STR, sizeof(MBA_STR))) { - if (!stat(MB_PATH, &statbuf)) - return true; - } else if (!strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR)) || - !strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR))) { - if (!stat(L3_MON_PATH, &statbuf)) { - inf = fopen(L3_MON_FEATURES_PATH, "r"); - if (!inf) - return false; - - if (!strncmp(resctrl_val, CMT_STR, sizeof(CMT_STR))) { - res = fgrep(inf, "llc_occupancy"); - if (res) { - found = true; - free(res); - } - } - - if (!strncmp(resctrl_val, MBM_STR, sizeof(MBM_STR))) { - res = fgrep(inf, "mbm_total_bytes"); - if (res) { - free(res); - res = fgrep(inf, "mbm_local_bytes"); - if (res) { - found = true; - free(res); - } - } - } - fclose(inf); - } - } + snprintf(res_path, sizeof(res_path), "%s/%s", INFO_PATH, resource); + + if (stat(res_path, &statbuf)) + return false; + + if (!feature) + return true; + + snprintf(res_path, sizeof(res_path), "%s/%s/mon_features", INFO_PATH, resource); + inf = fopen(res_path, "r"); + if (!inf) + return false; + + res = fgrep(inf, feature); + free(res); + fclose(inf); - return found; + return !!res; } int filter_dmesg(void) diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c index 90718c2fd4ea9..5dc7767039f6f 100644 --- a/tools/testing/vsock/vsock_test.c +++ b/tools/testing/vsock/vsock_test.c @@ -392,11 +392,12 @@ static void test_stream_msg_peek_server(const struct test_opts *opts) } #define SOCK_BUF_SIZE (2 * 1024 * 1024) -#define MAX_MSG_SIZE (32 * 1024) +#define MAX_MSG_PAGES 4 static void test_seqpacket_msg_bounds_client(const struct test_opts *opts) { unsigned long curr_hash; + size_t max_msg_size; int page_size; int msg_count; int fd; @@ -412,7 +413,8 @@ static void test_seqpacket_msg_bounds_client(const struct test_opts *opts) curr_hash = 0; page_size = getpagesize(); - msg_count = SOCK_BUF_SIZE / MAX_MSG_SIZE; + max_msg_size = MAX_MSG_PAGES * page_size; + msg_count = SOCK_BUF_SIZE / max_msg_size; for (int i = 0; i < msg_count; i++) { ssize_t send_size; @@ -423,7 +425,7 @@ static void test_seqpacket_msg_bounds_client(const struct test_opts *opts) /* Use "small" buffers and "big" buffers. */ if (i & 1) buf_size = page_size + - (rand() % (MAX_MSG_SIZE - page_size)); + (rand() % (max_msg_size - page_size)); else buf_size = 1 + (rand() % page_size); @@ -479,7 +481,6 @@ static void test_seqpacket_msg_bounds_server(const struct test_opts *opts) unsigned long remote_hash; unsigned long curr_hash; int fd; - char buf[MAX_MSG_SIZE]; struct msghdr msg = {0}; struct iovec iov = {0}; @@ -507,8 +508,13 @@ static void test_seqpacket_msg_bounds_server(const struct test_opts *opts) control_writeln("SRVREADY"); /* Wait, until peer sends whole data. */ control_expectln("SENDDONE"); - iov.iov_base = buf; - iov.iov_len = sizeof(buf); + iov.iov_len = MAX_MSG_PAGES * getpagesize(); + iov.iov_base = malloc(iov.iov_len); + if (!iov.iov_base) { + perror("malloc"); + exit(EXIT_FAILURE); + } + msg.msg_iov = &iov; msg.msg_iovlen = 1; @@ -533,6 +539,7 @@ static void test_seqpacket_msg_bounds_server(const struct test_opts *opts) curr_hash += hash_djb2(msg.msg_iov[0].iov_base, recv_size); } + free(iov.iov_base); close(fd); remote_hash = control_readulong();