diff options
131 files changed, 1482 insertions, 612 deletions
@@ -416,6 +416,7 @@ Kenneth W Chen <kenneth.w.chen@intel.com> Kenneth Westfield <quic_kwestfie@quicinc.com> <kwestfie@codeaurora.org> Kiran Gunda <quic_kgunda@quicinc.com> <kgunda@codeaurora.org> Kirill Tkhai <tkhai@ya.ru> <ktkhai@virtuozzo.com> +Kirill A. Shutemov <kas@kernel.org> <kirill.shutemov@linux.intel.com> Kishon Vijay Abraham I <kishon@kernel.org> <kishon@ti.com> Konrad Dybcio <konradybcio@kernel.org> <konrad.dybcio@linaro.org> Konrad Dybcio <konradybcio@kernel.org> <konrad.dybcio@somainline.org> diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 0cc35a14afbe..bd98ea3175ec 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1732,12 +1732,6 @@ The following nested keys are defined. numa_hint_faults (npn) Number of NUMA hinting faults. - numa_task_migrated (npn) - Number of task migration by NUMA balancing. - - numa_task_swapped (npn) - Number of task swap by NUMA balancing. - pgdemote_kswapd Number of pages demoted by kswapd. diff --git a/Documentation/devicetree/bindings/clock/mediatek,mt8188-clock.yaml b/Documentation/devicetree/bindings/clock/mediatek,mt8188-clock.yaml index 2985c8c717d7..5403242545ab 100644 --- a/Documentation/devicetree/bindings/clock/mediatek,mt8188-clock.yaml +++ b/Documentation/devicetree/bindings/clock/mediatek,mt8188-clock.yaml @@ -52,6 +52,9 @@ properties: '#clock-cells': const: 1 + '#reset-cells': + const: 1 + required: - compatible - reg diff --git a/MAINTAINERS b/MAINTAINERS index 05841dc1d372..60bba48f5479 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10506,7 +10506,7 @@ S: Maintained F: block/partitions/efi.* HABANALABS PCI DRIVER -M: Ofir Bitton <obitton@habana.ai> +M: Yaron Avizrat <yaron.avizrat@intel.com> L: dri-devel@lists.freedesktop.org S: Supported C: irc://irc.oftc.net/dri-devel @@ -26939,7 +26939,7 @@ F: arch/x86/kernel/stacktrace.c F: arch/x86/kernel/unwind_*.c X86 TRUST DOMAIN EXTENSIONS (TDX) -M: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> +M: Kirill A. Shutemov <kas@kernel.org> R: Dave Hansen <dave.hansen@linux.intel.com> L: x86@kernel.org L: linux-coco@lists.linux.dev @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 16 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = -rc6 NAME = Baby Opossum Posse # *DOCUMENTATION* diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi index 0baf256b4400..983b2f0e8797 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi @@ -687,11 +687,12 @@ }; wdog0: watchdog@2ad0000 { - compatible = "fsl,imx21-wdt"; + compatible = "fsl,ls1046a-wdt", "fsl,imx21-wdt"; reg = <0x0 0x2ad0000 0x0 0x10000>; interrupts = <GIC_SPI 83 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL QORIQ_CLK_PLL_DIV(2)>; + big-endian; }; edma0: dma-controller@2c00000 { diff --git a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi index d29710772569..1594ce9182a5 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi @@ -464,6 +464,7 @@ }; reg_nvcc_sd: LDO5 { + regulator-always-on; regulator-max-microvolt = <3300000>; regulator-min-microvolt = <1800000>; regulator-name = "On-module +V3.3_1.8_SD (LDO5)"; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw71xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw71xx.dtsi index 2f740d74707b..4bf818873fe3 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw71xx.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw71xx.dtsi @@ -70,7 +70,7 @@ tpm@1 { compatible = "atmel,attpm20p", "tcg,tpm_tis-spi"; reg = <0x1>; - spi-max-frequency = <36000000>; + spi-max-frequency = <25000000>; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw72xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw72xx.dtsi index 5ab3ffe9931d..cf747ec6fa16 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw72xx.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw72xx.dtsi @@ -110,7 +110,7 @@ tpm@1 { compatible = "atmel,attpm20p", "tcg,tpm_tis-spi"; reg = <0x1>; - spi-max-frequency = <36000000>; + spi-max-frequency = <25000000>; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi index e2b5e7ac3e46..5eb114d2360a 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi @@ -122,7 +122,7 @@ tpm@1 { compatible = "atmel,attpm20p", "tcg,tpm_tis-spi"; reg = <0x1>; - spi-max-frequency = <36000000>; + spi-max-frequency = <25000000>; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts index 6daa2313f879..568d24265ddf 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts @@ -201,7 +201,7 @@ tpm@0 { compatible = "atmel,attpm20p", "tcg,tpm_tis-spi"; reg = <0x0>; - spi-max-frequency = <36000000>; + spi-max-frequency = <25000000>; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx95-15x15-evk.dts b/arch/arm64/boot/dts/freescale/imx95-15x15-evk.dts index 6c47f4b47356..9f4d0899a94d 100644 --- a/arch/arm64/boot/dts/freescale/imx95-15x15-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx95-15x15-evk.dts @@ -574,17 +574,17 @@ &scmi_iomuxc { pinctrl_emdio: emdiogrp { fsl,pins = < - IMX95_PAD_ENET2_MDC__NETCMIX_TOP_NETC_MDC 0x57e - IMX95_PAD_ENET2_MDIO__NETCMIX_TOP_NETC_MDIO 0x97e + IMX95_PAD_ENET2_MDC__NETCMIX_TOP_NETC_MDC 0x50e + IMX95_PAD_ENET2_MDIO__NETCMIX_TOP_NETC_MDIO 0x90e >; }; pinctrl_enetc0: enetc0grp { fsl,pins = < - IMX95_PAD_ENET1_TD3__NETCMIX_TOP_ETH0_RGMII_TD3 0x57e - IMX95_PAD_ENET1_TD2__NETCMIX_TOP_ETH0_RGMII_TD2 0x57e - IMX95_PAD_ENET1_TD1__NETCMIX_TOP_ETH0_RGMII_TD1 0x57e - IMX95_PAD_ENET1_TD0__NETCMIX_TOP_ETH0_RGMII_TD0 0x57e + IMX95_PAD_ENET1_TD3__NETCMIX_TOP_ETH0_RGMII_TD3 0x50e + IMX95_PAD_ENET1_TD2__NETCMIX_TOP_ETH0_RGMII_TD2 0x50e + IMX95_PAD_ENET1_TD1__NETCMIX_TOP_ETH0_RGMII_TD1 0x50e + IMX95_PAD_ENET1_TD0__NETCMIX_TOP_ETH0_RGMII_TD0 0x50e IMX95_PAD_ENET1_TX_CTL__NETCMIX_TOP_ETH0_RGMII_TX_CTL 0x57e IMX95_PAD_ENET1_TXC__NETCMIX_TOP_ETH0_RGMII_TX_CLK 0x58e IMX95_PAD_ENET1_RX_CTL__NETCMIX_TOP_ETH0_RGMII_RX_CTL 0x57e @@ -598,10 +598,10 @@ pinctrl_enetc1: enetc1grp { fsl,pins = < - IMX95_PAD_ENET2_TD3__NETCMIX_TOP_ETH1_RGMII_TD3 0x57e - IMX95_PAD_ENET2_TD2__NETCMIX_TOP_ETH1_RGMII_TD2 0x57e - IMX95_PAD_ENET2_TD1__NETCMIX_TOP_ETH1_RGMII_TD1 0x57e - IMX95_PAD_ENET2_TD0__NETCMIX_TOP_ETH1_RGMII_TD0 0x57e + IMX95_PAD_ENET2_TD3__NETCMIX_TOP_ETH1_RGMII_TD3 0x50e + IMX95_PAD_ENET2_TD2__NETCMIX_TOP_ETH1_RGMII_TD2 0x50e + IMX95_PAD_ENET2_TD1__NETCMIX_TOP_ETH1_RGMII_TD1 0x50e + IMX95_PAD_ENET2_TD0__NETCMIX_TOP_ETH1_RGMII_TD0 0x50e IMX95_PAD_ENET2_TX_CTL__NETCMIX_TOP_ETH1_RGMII_TX_CTL 0x57e IMX95_PAD_ENET2_TXC__NETCMIX_TOP_ETH1_RGMII_TX_CLK 0x58e IMX95_PAD_ENET2_RX_CTL__NETCMIX_TOP_ETH1_RGMII_RX_CTL 0x57e diff --git a/arch/arm64/boot/dts/freescale/imx95-19x19-evk.dts b/arch/arm64/boot/dts/freescale/imx95-19x19-evk.dts index 6886ea766655..d7d845231312 100644 --- a/arch/arm64/boot/dts/freescale/imx95-19x19-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx95-19x19-evk.dts @@ -566,17 +566,17 @@ &scmi_iomuxc { pinctrl_emdio: emdiogrp{ fsl,pins = < - IMX95_PAD_ENET1_MDC__NETCMIX_TOP_NETC_MDC 0x57e - IMX95_PAD_ENET1_MDIO__NETCMIX_TOP_NETC_MDIO 0x97e + IMX95_PAD_ENET1_MDC__NETCMIX_TOP_NETC_MDC 0x50e + IMX95_PAD_ENET1_MDIO__NETCMIX_TOP_NETC_MDIO 0x90e >; }; pinctrl_enetc0: enetc0grp { fsl,pins = < - IMX95_PAD_ENET1_TD3__NETCMIX_TOP_ETH0_RGMII_TD3 0x57e - IMX95_PAD_ENET1_TD2__NETCMIX_TOP_ETH0_RGMII_TD2 0x57e - IMX95_PAD_ENET1_TD1__NETCMIX_TOP_ETH0_RGMII_TD1 0x57e - IMX95_PAD_ENET1_TD0__NETCMIX_TOP_ETH0_RGMII_TD0 0x57e + IMX95_PAD_ENET1_TD3__NETCMIX_TOP_ETH0_RGMII_TD3 0x50e + IMX95_PAD_ENET1_TD2__NETCMIX_TOP_ETH0_RGMII_TD2 0x50e + IMX95_PAD_ENET1_TD1__NETCMIX_TOP_ETH0_RGMII_TD1 0x50e + IMX95_PAD_ENET1_TD0__NETCMIX_TOP_ETH0_RGMII_TD0 0x50e IMX95_PAD_ENET1_TX_CTL__NETCMIX_TOP_ETH0_RGMII_TX_CTL 0x57e IMX95_PAD_ENET1_TXC__NETCMIX_TOP_ETH0_RGMII_TX_CLK 0x58e IMX95_PAD_ENET1_RX_CTL__NETCMIX_TOP_ETH0_RGMII_RX_CTL 0x57e diff --git a/arch/arm64/boot/dts/freescale/imx95.dtsi b/arch/arm64/boot/dts/freescale/imx95.dtsi index 632631a29112..5aecdd9b62ff 100644 --- a/arch/arm64/boot/dts/freescale/imx95.dtsi +++ b/arch/arm64/boot/dts/freescale/imx95.dtsi @@ -1708,7 +1708,7 @@ <0x9 0 1 0>; reg-names = "dbi","atu", "dbi2", "app", "dma", "addr_space"; num-lanes = <1>; - interrupts = <GIC_SPI 317 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 311 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "dma"; clocks = <&scmi_clk IMX95_CLK_HSIO>, <&scmi_clk IMX95_CLK_HSIOPLL>, diff --git a/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts b/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts index ae7a275fd223..cefecb7a23cf 100644 --- a/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts +++ b/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts @@ -1090,6 +1090,8 @@ }; &pmk8280_rtc { + qcom,uefi-rtc-info; + status = "okay"; }; diff --git a/arch/arm64/boot/dts/qcom/x1e80100-pmics.dtsi b/arch/arm64/boot/dts/qcom/x1e80100-pmics.dtsi index c02fd4d15c96..e3888bc143a0 100644 --- a/arch/arm64/boot/dts/qcom/x1e80100-pmics.dtsi +++ b/arch/arm64/boot/dts/qcom/x1e80100-pmics.dtsi @@ -224,6 +224,7 @@ reg-names = "rtc", "alarm"; interrupts = <0x0 0x62 0x1 IRQ_TYPE_EDGE_RISING>; qcom,no-alarm; /* alarm owned by ADSP */ + qcom,uefi-rtc-info; }; pmk8550_sdam_2: nvram@7100 { diff --git a/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi b/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi index ab232e5c7ad6..4203b335a263 100644 --- a/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi +++ b/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi @@ -379,6 +379,18 @@ <0 RK_PA7 RK_FUNC_GPIO &pcfg_pull_up>; }; }; + + spi1 { + spi1_csn0_gpio_pin: spi1-csn0-gpio-pin { + rockchip,pins = + <3 RK_PB1 RK_FUNC_GPIO &pcfg_pull_up_4ma>; + }; + + spi1_csn1_gpio_pin: spi1-csn1-gpio-pin { + rockchip,pins = + <3 RK_PB2 RK_FUNC_GPIO &pcfg_pull_up_4ma>; + }; + }; }; &pmu_io_domains { @@ -396,6 +408,17 @@ vqmmc-supply = <&vccio_sd>; }; +&spi1 { + /* + * Hardware CS has a very slow rise time of about 6us, + * causing transmission errors. + * With cs-gpios we have a rise time of about 20ns. + */ + cs-gpios = <&gpio3 RK_PB1 GPIO_ACTIVE_LOW>, <&gpio3 RK_PB2 GPIO_ACTIVE_LOW>; + pinctrl-names = "default"; + pinctrl-0 = <&spi1_clk &spi1_csn0_gpio_pin &spi1_csn1_gpio_pin &spi1_miso &spi1_mosi>; +}; + &tsadc { status = "okay"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts b/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts index 3c127c5c2607..a9021c524afb 100644 --- a/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts +++ b/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts @@ -30,6 +30,7 @@ fan: gpio_fan { compatible = "gpio-fan"; + fan-supply = <&vcc12v_dcin>; gpios = <&gpio0 RK_PD5 GPIO_ACTIVE_HIGH>; gpio-fan,speed-map = < 0 0>, diff --git a/arch/arm64/boot/dts/rockchip/rk3576-armsom-sige5.dts b/arch/arm64/boot/dts/rockchip/rk3576-armsom-sige5.dts index b09e789c75c4..801b40fea4e8 100644 --- a/arch/arm64/boot/dts/rockchip/rk3576-armsom-sige5.dts +++ b/arch/arm64/boot/dts/rockchip/rk3576-armsom-sige5.dts @@ -211,10 +211,38 @@ status = "okay"; }; +&cpu_b0 { + cpu-supply = <&vdd_cpu_big_s0>; +}; + +&cpu_b1 { + cpu-supply = <&vdd_cpu_big_s0>; +}; + +&cpu_b2 { + cpu-supply = <&vdd_cpu_big_s0>; +}; + +&cpu_b3 { + cpu-supply = <&vdd_cpu_big_s0>; +}; + &cpu_l0 { cpu-supply = <&vdd_cpu_lit_s0>; }; +&cpu_l1 { + cpu-supply = <&vdd_cpu_lit_s0>; +}; + +&cpu_l2 { + cpu-supply = <&vdd_cpu_lit_s0>; +}; + +&cpu_l3 { + cpu-supply = <&vdd_cpu_lit_s0>; +}; + &gmac0 { phy-mode = "rgmii-id"; clock_in_out = "output"; diff --git a/arch/arm64/boot/dts/rockchip/rk3576.dtsi b/arch/arm64/boot/dts/rockchip/rk3576.dtsi index 1086482f0479..64812e3bcb61 100644 --- a/arch/arm64/boot/dts/rockchip/rk3576.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3576.dtsi @@ -615,7 +615,7 @@ <0 0 0 2 &pcie1_intc 1>, <0 0 0 3 &pcie1_intc 2>, <0 0 0 4 &pcie1_intc 3>; - linux,pci-domain = <0>; + linux,pci-domain = <1>; max-link-speed = <2>; num-ib-windows = <8>; num-viewport = <8>; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-base-pinctrl.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-base-pinctrl.dtsi index 7f874c77410c..6584d73660f6 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-base-pinctrl.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3588-base-pinctrl.dtsi @@ -578,14 +578,14 @@ hdmim0_tx0_scl: hdmim0-tx0-scl { rockchip,pins = /* hdmim0_tx0_scl */ - <4 RK_PB7 5 &pcfg_pull_none>; + <4 RK_PB7 5 &pcfg_pull_none_drv_level_5_smt>; }; /omit-if-no-ref/ hdmim0_tx0_sda: hdmim0-tx0-sda { rockchip,pins = /* hdmim0_tx0_sda */ - <4 RK_PC0 5 &pcfg_pull_none>; + <4 RK_PC0 5 &pcfg_pull_none_drv_level_1_smt>; }; /omit-if-no-ref/ @@ -640,14 +640,14 @@ hdmim1_tx0_scl: hdmim1-tx0-scl { rockchip,pins = /* hdmim1_tx0_scl */ - <0 RK_PD5 11 &pcfg_pull_none>; + <0 RK_PD5 11 &pcfg_pull_none_drv_level_5_smt>; }; /omit-if-no-ref/ hdmim1_tx0_sda: hdmim1-tx0-sda { rockchip,pins = /* hdmim1_tx0_sda */ - <0 RK_PD4 11 &pcfg_pull_none>; + <0 RK_PD4 11 &pcfg_pull_none_drv_level_1_smt>; }; /omit-if-no-ref/ @@ -668,14 +668,14 @@ hdmim1_tx1_scl: hdmim1-tx1-scl { rockchip,pins = /* hdmim1_tx1_scl */ - <3 RK_PC6 5 &pcfg_pull_none>; + <3 RK_PC6 5 &pcfg_pull_none_drv_level_5_smt>; }; /omit-if-no-ref/ hdmim1_tx1_sda: hdmim1-tx1-sda { rockchip,pins = /* hdmim1_tx1_sda */ - <3 RK_PC5 5 &pcfg_pull_none>; + <3 RK_PC5 5 &pcfg_pull_none_drv_level_1_smt>; }; /omit-if-no-ref/ hdmim2_rx_cec: hdmim2-rx-cec { @@ -709,14 +709,14 @@ hdmim2_tx0_scl: hdmim2-tx0-scl { rockchip,pins = /* hdmim2_tx0_scl */ - <3 RK_PC7 5 &pcfg_pull_none>; + <3 RK_PC7 5 &pcfg_pull_none_drv_level_5_smt>; }; /omit-if-no-ref/ hdmim2_tx0_sda: hdmim2-tx0-sda { rockchip,pins = /* hdmim2_tx0_sda */ - <3 RK_PD0 5 &pcfg_pull_none>; + <3 RK_PD0 5 &pcfg_pull_none_drv_level_1_smt>; }; /omit-if-no-ref/ @@ -730,14 +730,14 @@ hdmim2_tx1_scl: hdmim2-tx1-scl { rockchip,pins = /* hdmim2_tx1_scl */ - <1 RK_PA4 5 &pcfg_pull_none>; + <1 RK_PA4 5 &pcfg_pull_none_drv_level_5_smt>; }; /omit-if-no-ref/ hdmim2_tx1_sda: hdmim2-tx1-sda { rockchip,pins = /* hdmim2_tx1_sda */ - <1 RK_PA3 5 &pcfg_pull_none>; + <1 RK_PA3 5 &pcfg_pull_none_drv_level_1_smt>; }; /omit-if-no-ref/ diff --git a/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi index cc37f082adea..b07543315f87 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi @@ -321,6 +321,7 @@ bus-width = <4>; cap-mmc-highspeed; cap-sd-highspeed; + cd-gpios = <&gpio0 RK_PA4 GPIO_ACTIVE_LOW>; disable-wp; max-frequency = <150000000>; no-sdio; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-extra-pinctrl.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-extra-pinctrl.dtsi index 244c66faa161..fb48ddc04bcb 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-extra-pinctrl.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3588-extra-pinctrl.dtsi @@ -160,14 +160,15 @@ hdmim0_tx1_scl: hdmim0-tx1-scl { rockchip,pins = /* hdmim0_tx1_scl */ - <2 RK_PB5 4 &pcfg_pull_none>; + <2 RK_PB5 4 &pcfg_pull_none_drv_level_3_smt>; }; /omit-if-no-ref/ hdmim0_tx1_sda: hdmim0-tx1-sda { rockchip,pins = /* hdmim0_tx1_sda */ - <2 RK_PB4 4 &pcfg_pull_none>; + <2 RK_PB4 4 &pcfg_pull_none_drv_level_1_smt>; + }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-coolpi-4b.dts b/arch/arm64/boot/dts/rockchip/rk3588s-coolpi-4b.dts index 8b717c4017a4..b2947b36fada 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588s-coolpi-4b.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588s-coolpi-4b.dts @@ -474,6 +474,7 @@ bus-width = <4>; cap-mmc-highspeed; cap-sd-highspeed; + cd-gpios = <&gpio0 RK_PA4 GPIO_ACTIVE_LOW>; disable-wp; max-frequency = <150000000>; no-sdio; diff --git a/arch/arm64/boot/dts/rockchip/rockchip-pinconf.dtsi b/arch/arm64/boot/dts/rockchip/rockchip-pinconf.dtsi index 5c645437b507..b0475b7c655a 100644 --- a/arch/arm64/boot/dts/rockchip/rockchip-pinconf.dtsi +++ b/arch/arm64/boot/dts/rockchip/rockchip-pinconf.dtsi @@ -333,6 +333,41 @@ }; /omit-if-no-ref/ + pcfg_pull_none_drv_level_1_smt: pcfg-pull-none-drv-level-1-smt { + bias-disable; + drive-strength = <1>; + input-schmitt-enable; + }; + + /omit-if-no-ref/ + pcfg_pull_none_drv_level_2_smt: pcfg-pull-none-drv-level-2-smt { + bias-disable; + drive-strength = <2>; + input-schmitt-enable; + }; + + /omit-if-no-ref/ + pcfg_pull_none_drv_level_3_smt: pcfg-pull-none-drv-level-3-smt { + bias-disable; + drive-strength = <3>; + input-schmitt-enable; + }; + + /omit-if-no-ref/ + pcfg_pull_none_drv_level_4_smt: pcfg-pull-none-drv-level-4-smt { + bias-disable; + drive-strength = <4>; + input-schmitt-enable; + }; + + /omit-if-no-ref/ + pcfg_pull_none_drv_level_5_smt: pcfg-pull-none-drv-level-5-smt { + bias-disable; + drive-strength = <5>; + input-schmitt-enable; + }; + + /omit-if-no-ref/ pcfg_output_high: pcfg-output-high { output-high; }; diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index 7e04a2905ce4..eb5c17d4c7ec 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -1444,6 +1444,7 @@ CONFIG_PLATFORM_MHU=y CONFIG_BCM2835_MBOX=y CONFIG_QCOM_APCS_IPC=y CONFIG_MTK_ADSP_MBOX=m +CONFIG_QCOM_CPUCP_MBOX=m CONFIG_QCOM_IPCC=y CONFIG_ROCKCHIP_IOMMU=y CONFIG_TEGRA_IOMMU_SMMU=y diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 5b3362af7d65..8bed9030ad47 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -147,7 +147,7 @@ config X86 select ARCH_WANTS_DYNAMIC_TASK_STRUCT select ARCH_WANTS_NO_INSTR select ARCH_WANT_GENERAL_HUGETLB - select ARCH_WANT_HUGE_PMD_SHARE + select ARCH_WANT_HUGE_PMD_SHARE if X86_64 select ARCH_WANT_LD_ORPHAN_WARN select ARCH_WANT_OPTIMIZE_DAX_VMEMMAP if X86_64 select ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP if X86_64 diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index b7dded3c8113..5cfb5d74dd5f 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -628,6 +628,7 @@ #define MSR_AMD64_OSVW_STATUS 0xc0010141 #define MSR_AMD_PPIN_CTL 0xc00102f0 #define MSR_AMD_PPIN 0xc00102f1 +#define MSR_AMD64_CPUID_FN_7 0xc0011002 #define MSR_AMD64_CPUID_FN_1 0xc0011004 #define MSR_AMD64_LS_CFG 0xc0011020 #define MSR_AMD64_DC_CFG 0xc0011022 diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index b750ac008b78..329ee185d8cc 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -974,6 +974,16 @@ static void init_amd_zen2(struct cpuinfo_x86 *c) init_spectral_chicken(c); fix_erratum_1386(c); zen2_zenbleed_check(c); + + /* Disable RDSEED on AMD Cyan Skillfish because of an error. */ + if (c->x86_model == 0x47 && c->x86_stepping == 0x0) { + clear_cpu_cap(c, X86_FEATURE_RDSEED); + msr_clear_bit(MSR_AMD64_CPUID_FN_7, 18); + pr_emerg("RDSEED is not reliable on this platform; disabling.\n"); + } + + /* Correct misconfigured CPUID on some clients. */ + clear_cpu_cap(c, X86_FEATURE_INVLPGB); } static void init_amd_zen3(struct cpuinfo_x86 *c) diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index a6ab666ef48a..7a50af416cac 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -1280,6 +1280,22 @@ static void dpm_async_suspend_parent(struct device *dev, async_func_t func) dpm_async_with_cleanup(dev->parent, func); } +static void dpm_async_suspend_complete_all(struct list_head *device_list) +{ + struct device *dev; + + guard(mutex)(&async_wip_mtx); + + list_for_each_entry_reverse(dev, device_list, power.entry) { + /* + * In case the device is being waited for and async processing + * has not started for it yet, let the waiters make progress. + */ + if (!dev->power.work_in_progress) + complete_all(&dev->power.completion); + } +} + /** * resume_event - Return a "resume" message for given "suspend" sleep state. * @sleep_state: PM message representing a sleep state. @@ -1456,6 +1472,7 @@ static int dpm_noirq_suspend_devices(pm_message_t state) mutex_lock(&dpm_list_mtx); if (error || async_error) { + dpm_async_suspend_complete_all(&dpm_late_early_list); /* * Move all devices to the target list to resume them * properly. @@ -1658,6 +1675,7 @@ int dpm_suspend_late(pm_message_t state) mutex_lock(&dpm_list_mtx); if (error || async_error) { + dpm_async_suspend_complete_all(&dpm_suspended_list); /* * Move all devices to the target list to resume them * properly. @@ -1951,6 +1969,7 @@ int dpm_suspend(pm_message_t state) mutex_lock(&dpm_list_mtx); if (error || async_error) { + dpm_async_suspend_complete_all(&dpm_prepared_list); /* * Move all devices to the target list to resume them * properly. diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 7bdc7eb808ea..2592bd19ebc1 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -2198,9 +2198,7 @@ again: goto out; } } - ret = nbd_start_device(nbd); - if (ret) - goto out; + if (info->attrs[NBD_ATTR_BACKEND_IDENTIFIER]) { nbd->backend = nla_strdup(info->attrs[NBD_ATTR_BACKEND_IDENTIFIER], GFP_KERNEL); @@ -2216,6 +2214,8 @@ again: goto out; } set_bit(NBD_RT_HAS_BACKEND_FILE, &config->runtime_flags); + + ret = nbd_start_device(nbd); out: mutex_unlock(&nbd->config_lock); if (!ret) { diff --git a/drivers/char/agp/amd64-agp.c b/drivers/char/agp/amd64-agp.c index bf490967241a..2505df1f4e69 100644 --- a/drivers/char/agp/amd64-agp.c +++ b/drivers/char/agp/amd64-agp.c @@ -720,11 +720,6 @@ static const struct pci_device_id agp_amd64_pci_table[] = { MODULE_DEVICE_TABLE(pci, agp_amd64_pci_table); -static const struct pci_device_id agp_amd64_pci_promisc_table[] = { - { PCI_DEVICE_CLASS(0, 0) }, - { } -}; - static DEFINE_SIMPLE_DEV_PM_OPS(agp_amd64_pm_ops, NULL, agp_amd64_resume); static struct pci_driver agp_amd64_pci_driver = { @@ -739,6 +734,7 @@ static struct pci_driver agp_amd64_pci_driver = { /* Not static due to IOMMU code calling it early. */ int __init agp_amd64_init(void) { + struct pci_dev *pdev = NULL; int err = 0; if (agp_off) @@ -767,9 +763,13 @@ int __init agp_amd64_init(void) } /* Look for any AGP bridge */ - agp_amd64_pci_driver.id_table = agp_amd64_pci_promisc_table; - err = driver_attach(&agp_amd64_pci_driver.driver); - if (err == 0 && agp_bridges_found == 0) { + for_each_pci_dev(pdev) + if (pci_find_capability(pdev, PCI_CAP_ID_AGP)) + pci_add_dynid(&agp_amd64_pci_driver, + pdev->vendor, pdev->device, + pdev->subsystem_vendor, + pdev->subsystem_device, 0, 0, 0); + if (agp_bridges_found == 0) { pci_unregister_driver(&agp_amd64_pci_driver); err = -ENODEV; } diff --git a/drivers/clk/clk-scmi.c b/drivers/clk/clk-scmi.c index 15510c2ff21c..1b1561c84127 100644 --- a/drivers/clk/clk-scmi.c +++ b/drivers/clk/clk-scmi.c @@ -404,6 +404,7 @@ static int scmi_clocks_probe(struct scmi_device *sdev) const struct scmi_handle *handle = sdev->handle; struct scmi_protocol_handle *ph; const struct clk_ops *scmi_clk_ops_db[SCMI_MAX_CLK_OPS] = {}; + struct scmi_clk *sclks; if (!handle) return -ENODEV; @@ -430,18 +431,21 @@ static int scmi_clocks_probe(struct scmi_device *sdev) transport_is_atomic = handle->is_transport_atomic(handle, &atomic_threshold_us); + sclks = devm_kcalloc(dev, count, sizeof(*sclks), GFP_KERNEL); + if (!sclks) + return -ENOMEM; + + for (idx = 0; idx < count; idx++) + hws[idx] = &sclks[idx].hw; + for (idx = 0; idx < count; idx++) { - struct scmi_clk *sclk; + struct scmi_clk *sclk = &sclks[idx]; const struct clk_ops *scmi_ops; - sclk = devm_kzalloc(dev, sizeof(*sclk), GFP_KERNEL); - if (!sclk) - return -ENOMEM; - sclk->info = scmi_proto_clk_ops->info_get(ph, idx); if (!sclk->info) { dev_dbg(dev, "invalid clock info for idx %d\n", idx); - devm_kfree(dev, sclk); + hws[idx] = NULL; continue; } @@ -479,13 +483,11 @@ static int scmi_clocks_probe(struct scmi_device *sdev) if (err) { dev_err(dev, "failed to register clock %d\n", idx); devm_kfree(dev, sclk->parent_data); - devm_kfree(dev, sclk); hws[idx] = NULL; } else { dev_dbg(dev, "Registered clock:%s%s\n", sclk->info->name, scmi_ops->enable ? " (atomic ops)" : ""); - hws[idx] = &sclk->hw; } } diff --git a/drivers/clk/imx/clk-imx95-blk-ctl.c b/drivers/clk/imx/clk-imx95-blk-ctl.c index 25974947ad0c..cc2ee2be1819 100644 --- a/drivers/clk/imx/clk-imx95-blk-ctl.c +++ b/drivers/clk/imx/clk-imx95-blk-ctl.c @@ -219,11 +219,15 @@ static const struct imx95_blk_ctl_dev_data lvds_csr_dev_data = { .clk_reg_offset = 0, }; +static const char * const disp_engine_parents[] = { + "videopll1", "dsi_pll", "ldb_pll_div7" +}; + static const struct imx95_blk_ctl_clk_dev_data dispmix_csr_clk_dev_data[] = { [IMX95_CLK_DISPMIX_ENG0_SEL] = { .name = "disp_engine0_sel", - .parent_names = (const char *[]){"videopll1", "dsi_pll", "ldb_pll_div7", }, - .num_parents = 4, + .parent_names = disp_engine_parents, + .num_parents = ARRAY_SIZE(disp_engine_parents), .reg = 0, .bit_idx = 0, .bit_width = 2, @@ -232,8 +236,8 @@ static const struct imx95_blk_ctl_clk_dev_data dispmix_csr_clk_dev_data[] = { }, [IMX95_CLK_DISPMIX_ENG1_SEL] = { .name = "disp_engine1_sel", - .parent_names = (const char *[]){"videopll1", "dsi_pll", "ldb_pll_div7", }, - .num_parents = 4, + .parent_names = disp_engine_parents, + .num_parents = ARRAY_SIZE(disp_engine_parents), .reg = 0, .bit_idx = 2, .bit_width = 2, diff --git a/drivers/gpu/drm/drm_framebuffer.c b/drivers/gpu/drm/drm_framebuffer.c index b781601946db..63a70f285cce 100644 --- a/drivers/gpu/drm/drm_framebuffer.c +++ b/drivers/gpu/drm/drm_framebuffer.c @@ -862,11 +862,23 @@ EXPORT_SYMBOL_FOR_TESTS_ONLY(drm_framebuffer_free); int drm_framebuffer_init(struct drm_device *dev, struct drm_framebuffer *fb, const struct drm_framebuffer_funcs *funcs) { + unsigned int i; int ret; + bool exists; if (WARN_ON_ONCE(fb->dev != dev || !fb->format)) return -EINVAL; + for (i = 0; i < fb->format->num_planes; i++) { + if (drm_WARN_ON_ONCE(dev, fb->internal_flags & DRM_FRAMEBUFFER_HAS_HANDLE_REF(i))) + fb->internal_flags &= ~DRM_FRAMEBUFFER_HAS_HANDLE_REF(i); + if (fb->obj[i]) { + exists = drm_gem_object_handle_get_if_exists_unlocked(fb->obj[i]); + if (exists) + fb->internal_flags |= DRM_FRAMEBUFFER_HAS_HANDLE_REF(i); + } + } + INIT_LIST_HEAD(&fb->filp_head); fb->funcs = funcs; @@ -875,7 +887,7 @@ int drm_framebuffer_init(struct drm_device *dev, struct drm_framebuffer *fb, ret = __drm_mode_object_add(dev, &fb->base, DRM_MODE_OBJECT_FB, false, drm_framebuffer_free); if (ret) - goto out; + goto err; mutex_lock(&dev->mode_config.fb_lock); dev->mode_config.num_fb++; @@ -883,7 +895,16 @@ int drm_framebuffer_init(struct drm_device *dev, struct drm_framebuffer *fb, mutex_unlock(&dev->mode_config.fb_lock); drm_mode_object_register(dev, &fb->base); -out: + + return 0; + +err: + for (i = 0; i < fb->format->num_planes; i++) { + if (fb->internal_flags & DRM_FRAMEBUFFER_HAS_HANDLE_REF(i)) { + drm_gem_object_handle_put_unlocked(fb->obj[i]); + fb->internal_flags &= ~DRM_FRAMEBUFFER_HAS_HANDLE_REF(i); + } + } return ret; } EXPORT_SYMBOL(drm_framebuffer_init); @@ -960,6 +981,12 @@ EXPORT_SYMBOL(drm_framebuffer_unregister_private); void drm_framebuffer_cleanup(struct drm_framebuffer *fb) { struct drm_device *dev = fb->dev; + unsigned int i; + + for (i = 0; i < fb->format->num_planes; i++) { + if (fb->internal_flags & DRM_FRAMEBUFFER_HAS_HANDLE_REF(i)) + drm_gem_object_handle_put_unlocked(fb->obj[i]); + } mutex_lock(&dev->mode_config.fb_lock); list_del(&fb->head); diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index 4bf0a76bb35e..ac0524595bd6 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -223,23 +223,34 @@ static void drm_gem_object_handle_get(struct drm_gem_object *obj) } /** - * drm_gem_object_handle_get_unlocked - acquire reference on user-space handles + * drm_gem_object_handle_get_if_exists_unlocked - acquire reference on user-space handle, if any * @obj: GEM object * - * Acquires a reference on the GEM buffer object's handle. Required - * to keep the GEM object alive. Call drm_gem_object_handle_put_unlocked() - * to release the reference. + * Acquires a reference on the GEM buffer object's handle. Required to keep + * the GEM object alive. Call drm_gem_object_handle_put_if_exists_unlocked() + * to release the reference. Does nothing if the buffer object has no handle. + * + * Returns: + * True if a handle exists, or false otherwise */ -void drm_gem_object_handle_get_unlocked(struct drm_gem_object *obj) +bool drm_gem_object_handle_get_if_exists_unlocked(struct drm_gem_object *obj) { struct drm_device *dev = obj->dev; guard(mutex)(&dev->object_name_lock); - drm_WARN_ON(dev, !obj->handle_count); /* first ref taken in create-tail helper */ + /* + * First ref taken during GEM object creation, if any. Some + * drivers set up internal framebuffers with GEM objects that + * do not have a GEM handle. Hence, this counter can be zero. + */ + if (!obj->handle_count) + return false; + drm_gem_object_handle_get(obj); + + return true; } -EXPORT_SYMBOL(drm_gem_object_handle_get_unlocked); /** * drm_gem_object_handle_free - release resources bound to userspace handles @@ -272,7 +283,7 @@ static void drm_gem_object_exported_dma_buf_free(struct drm_gem_object *obj) } /** - * drm_gem_object_handle_put_unlocked - releases reference on user-space handles + * drm_gem_object_handle_put_unlocked - releases reference on user-space handle * @obj: GEM object * * Releases a reference on the GEM buffer object's handle. Possibly releases @@ -283,14 +294,14 @@ void drm_gem_object_handle_put_unlocked(struct drm_gem_object *obj) struct drm_device *dev = obj->dev; bool final = false; - if (WARN_ON(READ_ONCE(obj->handle_count) == 0)) + if (drm_WARN_ON(dev, READ_ONCE(obj->handle_count) == 0)) return; /* - * Must bump handle count first as this may be the last - * ref, in which case the object would disappear before we - * checked for a name - */ + * Must bump handle count first as this may be the last + * ref, in which case the object would disappear before + * we checked for a name. + */ mutex_lock(&dev->object_name_lock); if (--obj->handle_count == 0) { @@ -303,7 +314,6 @@ void drm_gem_object_handle_put_unlocked(struct drm_gem_object *obj) if (final) drm_gem_object_put(obj); } -EXPORT_SYMBOL(drm_gem_object_handle_put_unlocked); /* * Called at device or object close to release the file's @@ -315,6 +325,9 @@ drm_gem_object_release_handle(int id, void *ptr, void *data) struct drm_file *file_priv = data; struct drm_gem_object *obj = ptr; + if (drm_WARN_ON(obj->dev, !data)) + return 0; + if (obj->funcs->close) obj->funcs->close(obj, file_priv); @@ -435,7 +448,7 @@ drm_gem_handle_create_tail(struct drm_file *file_priv, idr_preload(GFP_KERNEL); spin_lock(&file_priv->table_lock); - ret = idr_alloc(&file_priv->object_idr, obj, 1, 0, GFP_NOWAIT); + ret = idr_alloc(&file_priv->object_idr, NULL, 1, 0, GFP_NOWAIT); spin_unlock(&file_priv->table_lock); idr_preload_end(); @@ -456,6 +469,11 @@ drm_gem_handle_create_tail(struct drm_file *file_priv, goto err_revoke; } + /* mirrors drm_gem_handle_delete to avoid races */ + spin_lock(&file_priv->table_lock); + obj = idr_replace(&file_priv->object_idr, obj, handle); + WARN_ON(obj != NULL); + spin_unlock(&file_priv->table_lock); *handlep = handle; return 0; diff --git a/drivers/gpu/drm/drm_gem_framebuffer_helper.c b/drivers/gpu/drm/drm_gem_framebuffer_helper.c index 14a87788695d..6f72e7a0f427 100644 --- a/drivers/gpu/drm/drm_gem_framebuffer_helper.c +++ b/drivers/gpu/drm/drm_gem_framebuffer_helper.c @@ -99,7 +99,7 @@ void drm_gem_fb_destroy(struct drm_framebuffer *fb) unsigned int i; for (i = 0; i < fb->format->num_planes; i++) - drm_gem_object_handle_put_unlocked(fb->obj[i]); + drm_gem_object_put(fb->obj[i]); drm_framebuffer_cleanup(fb); kfree(fb); @@ -182,10 +182,8 @@ int drm_gem_fb_init_with_funcs(struct drm_device *dev, if (!objs[i]) { drm_dbg_kms(dev, "Failed to lookup GEM object\n"); ret = -ENOENT; - goto err_gem_object_handle_put_unlocked; + goto err_gem_object_put; } - drm_gem_object_handle_get_unlocked(objs[i]); - drm_gem_object_put(objs[i]); min_size = (height - 1) * mode_cmd->pitches[i] + drm_format_info_min_pitch(info, i, width) @@ -195,22 +193,22 @@ int drm_gem_fb_init_with_funcs(struct drm_device *dev, drm_dbg_kms(dev, "GEM object size (%zu) smaller than minimum size (%u) for plane %d\n", objs[i]->size, min_size, i); - drm_gem_object_handle_put_unlocked(objs[i]); + drm_gem_object_put(objs[i]); ret = -EINVAL; - goto err_gem_object_handle_put_unlocked; + goto err_gem_object_put; } } ret = drm_gem_fb_init(dev, fb, mode_cmd, objs, i, funcs); if (ret) - goto err_gem_object_handle_put_unlocked; + goto err_gem_object_put; return 0; -err_gem_object_handle_put_unlocked: +err_gem_object_put: while (i > 0) { --i; - drm_gem_object_handle_put_unlocked(objs[i]); + drm_gem_object_put(objs[i]); } return ret; } diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h index be77d61a16ce..60c282881958 100644 --- a/drivers/gpu/drm/drm_internal.h +++ b/drivers/gpu/drm/drm_internal.h @@ -161,7 +161,7 @@ void drm_sysfs_lease_event(struct drm_device *dev); /* drm_gem.c */ int drm_gem_init(struct drm_device *dev); -void drm_gem_object_handle_get_unlocked(struct drm_gem_object *obj); +bool drm_gem_object_handle_get_if_exists_unlocked(struct drm_gem_object *obj); void drm_gem_object_handle_put_unlocked(struct drm_gem_object *obj); int drm_gem_handle_create_tail(struct drm_file *file_priv, struct drm_gem_object *obj, diff --git a/drivers/gpu/drm/drm_panic_qr.rs b/drivers/gpu/drm/drm_panic_qr.rs index dd55b1cb764d..18492daae4b3 100644 --- a/drivers/gpu/drm/drm_panic_qr.rs +++ b/drivers/gpu/drm/drm_panic_qr.rs @@ -27,7 +27,7 @@ //! * <https://github.com/erwanvivien/fast_qr> //! * <https://github.com/bjguillot/qr> -use kernel::{prelude::*, str::CStr}; +use kernel::prelude::*; #[derive(Debug, Clone, Copy, PartialEq, Eq, Ord, PartialOrd)] struct Version(usize); diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c index ba7b8938b17c..166ee11831ab 100644 --- a/drivers/gpu/drm/i915/display/intel_bios.c +++ b/drivers/gpu/drm/i915/display/intel_bios.c @@ -1938,7 +1938,7 @@ static int get_init_otp_deassert_fragment_len(struct intel_display *display, int index, len; if (drm_WARN_ON(display->drm, - !data || panel->vbt.dsi.seq_version != 1)) + !data || panel->vbt.dsi.seq_version >= 3)) return 0; /* index = 1 to skip sequence byte */ @@ -1961,7 +1961,7 @@ static int get_init_otp_deassert_fragment_len(struct intel_display *display, } /* - * Some v1 VBT MIPI sequences do the deassert in the init OTP sequence. + * Some v1/v2 VBT MIPI sequences do the deassert in the init OTP sequence. * The deassert must be done before calling intel_dsi_device_ready, so for * these devices we split the init OTP sequence into a deassert sequence and * the actual init OTP part. @@ -1972,9 +1972,9 @@ static void vlv_fixup_mipi_sequences(struct intel_display *display, u8 *init_otp; int len; - /* Limit this to v1 vid-mode sequences */ + /* Limit this to v1/v2 vid-mode sequences */ if (panel->vbt.dsi.config->is_cmd_mode || - panel->vbt.dsi.seq_version != 1) + panel->vbt.dsi.seq_version >= 3) return; /* Only do this if there are otp and assert seqs and no deassert seq */ diff --git a/drivers/gpu/drm/imagination/pvr_power.c b/drivers/gpu/drm/imagination/pvr_power.c index 41f5d89e78b8..3e349d039fc0 100644 --- a/drivers/gpu/drm/imagination/pvr_power.c +++ b/drivers/gpu/drm/imagination/pvr_power.c @@ -386,13 +386,13 @@ pvr_power_reset(struct pvr_device *pvr_dev, bool hard_reset) if (!err) { if (hard_reset) { pvr_dev->fw_dev.booted = false; - WARN_ON(pm_runtime_force_suspend(from_pvr_device(pvr_dev)->dev)); + WARN_ON(pvr_power_device_suspend(from_pvr_device(pvr_dev)->dev)); err = pvr_fw_hard_reset(pvr_dev); if (err) goto err_device_lost; - err = pm_runtime_force_resume(from_pvr_device(pvr_dev)->dev); + err = pvr_power_device_resume(from_pvr_device(pvr_dev)->dev); pvr_dev->fw_dev.booted = true; if (err) goto err_device_lost; diff --git a/drivers/gpu/drm/nouveau/nouveau_debugfs.c b/drivers/gpu/drm/nouveau/nouveau_debugfs.c index 200e65a7cefc..c7869a639bef 100644 --- a/drivers/gpu/drm/nouveau/nouveau_debugfs.c +++ b/drivers/gpu/drm/nouveau/nouveau_debugfs.c @@ -314,14 +314,10 @@ nouveau_debugfs_fini(struct nouveau_drm *drm) drm->debugfs = NULL; } -int +void nouveau_module_debugfs_init(void) { nouveau_debugfs_root = debugfs_create_dir("nouveau", NULL); - if (IS_ERR(nouveau_debugfs_root)) - return PTR_ERR(nouveau_debugfs_root); - - return 0; } void diff --git a/drivers/gpu/drm/nouveau/nouveau_debugfs.h b/drivers/gpu/drm/nouveau/nouveau_debugfs.h index b7617b344ee2..d05ed0e641c4 100644 --- a/drivers/gpu/drm/nouveau/nouveau_debugfs.h +++ b/drivers/gpu/drm/nouveau/nouveau_debugfs.h @@ -24,7 +24,7 @@ extern void nouveau_debugfs_fini(struct nouveau_drm *); extern struct dentry *nouveau_debugfs_root; -int nouveau_module_debugfs_init(void); +void nouveau_module_debugfs_init(void); void nouveau_module_debugfs_fini(void); #else static inline void @@ -42,10 +42,9 @@ nouveau_debugfs_fini(struct nouveau_drm *drm) { } -static inline int +static inline void nouveau_module_debugfs_init(void) { - return 0; } static inline void diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index 0c82a63cd49d..1527b801f013 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -1461,9 +1461,7 @@ nouveau_drm_init(void) if (!nouveau_modeset) return 0; - ret = nouveau_module_debugfs_init(); - if (ret) - return ret; + nouveau_module_debugfs_init(); #ifdef CONFIG_NOUVEAU_PLATFORM_DRIVER platform_driver_register(&nouveau_platform_driver); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/gsp.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/gsp.c index baf42339f93e..588cb4ab85cb 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/gsp.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/gsp.c @@ -719,7 +719,6 @@ r535_gsp_acpi_caps(acpi_handle handle, CAPS_METHOD_DATA *caps) union acpi_object argv4 = { .buffer.type = ACPI_TYPE_BUFFER, .buffer.length = 4, - .buffer.pointer = kmalloc(argv4.buffer.length, GFP_KERNEL), }, *obj; caps->status = 0xffff; @@ -727,17 +726,22 @@ r535_gsp_acpi_caps(acpi_handle handle, CAPS_METHOD_DATA *caps) if (!acpi_check_dsm(handle, &NVOP_DSM_GUID, NVOP_DSM_REV, BIT_ULL(0x1a))) return; + argv4.buffer.pointer = kmalloc(argv4.buffer.length, GFP_KERNEL); + if (!argv4.buffer.pointer) + return; + obj = acpi_evaluate_dsm(handle, &NVOP_DSM_GUID, NVOP_DSM_REV, 0x1a, &argv4); if (!obj) - return; + goto done; if (WARN_ON(obj->type != ACPI_TYPE_BUFFER) || WARN_ON(obj->buffer.length != 4)) - return; + goto done; caps->status = 0; caps->optimusCaps = *(u32 *)obj->buffer.pointer; +done: ACPI_FREE(obj); kfree(argv4.buffer.pointer); @@ -754,24 +758,28 @@ r535_gsp_acpi_jt(acpi_handle handle, JT_METHOD_DATA *jt) union acpi_object argv4 = { .buffer.type = ACPI_TYPE_BUFFER, .buffer.length = sizeof(caps), - .buffer.pointer = kmalloc(argv4.buffer.length, GFP_KERNEL), }, *obj; jt->status = 0xffff; + argv4.buffer.pointer = kmalloc(argv4.buffer.length, GFP_KERNEL); + if (!argv4.buffer.pointer) + return; + obj = acpi_evaluate_dsm(handle, &JT_DSM_GUID, JT_DSM_REV, 0x1, &argv4); if (!obj) - return; + goto done; if (WARN_ON(obj->type != ACPI_TYPE_BUFFER) || WARN_ON(obj->buffer.length != 4)) - return; + goto done; jt->status = 0; jt->jtCaps = *(u32 *)obj->buffer.pointer; jt->jtRevId = (jt->jtCaps & 0xfff00000) >> 20; jt->bSBIOSCaps = 0; +done: ACPI_FREE(obj); kfree(argv4.buffer.pointer); @@ -1744,6 +1752,13 @@ r535_gsp_fini(struct nvkm_gsp *gsp, bool suspend) nvkm_gsp_sg_free(gsp->subdev.device, &gsp->sr.sgt); return ret; } + + /* + * TODO: Debug the GSP firmware / RPC handling to find out why + * without this Turing (but none of the other architectures) + * ends up resetting all channels after resume. + */ + msleep(50); } ret = r535_gsp_rpc_unloading_guest_driver(gsp, suspend); diff --git a/drivers/gpu/drm/tegra/nvdec.c b/drivers/gpu/drm/tegra/nvdec.c index 2d9a0a3f6c38..7a38664e890e 100644 --- a/drivers/gpu/drm/tegra/nvdec.c +++ b/drivers/gpu/drm/tegra/nvdec.c @@ -261,10 +261,8 @@ static int nvdec_load_falcon_firmware(struct nvdec *nvdec) if (!client->group) { virt = dma_alloc_coherent(nvdec->dev, size, &iova, GFP_KERNEL); - - err = dma_mapping_error(nvdec->dev, iova); - if (err < 0) - return err; + if (!virt) + return -ENOMEM; } else { virt = tegra_drm_alloc(tegra, size, &iova); if (IS_ERR(virt)) diff --git a/drivers/gpu/drm/xe/xe_devcoredump.c b/drivers/gpu/drm/xe/xe_devcoredump.c index 7a8af2311318..11e60d687572 100644 --- a/drivers/gpu/drm/xe/xe_devcoredump.c +++ b/drivers/gpu/drm/xe/xe_devcoredump.c @@ -171,14 +171,32 @@ static void xe_devcoredump_snapshot_free(struct xe_devcoredump_snapshot *ss) #define XE_DEVCOREDUMP_CHUNK_MAX (SZ_512M + SZ_1G) +/** + * xe_devcoredump_read() - Read data from the Xe device coredump snapshot + * @buffer: Destination buffer to copy the coredump data into + * @offset: Offset in the coredump data to start reading from + * @count: Number of bytes to read + * @data: Pointer to the xe_devcoredump structure + * @datalen: Length of the data (unused) + * + * Reads a chunk of the coredump snapshot data into the provided buffer. + * If the devcoredump is smaller than 1.5 GB (XE_DEVCOREDUMP_CHUNK_MAX), + * it is read directly from a pre-written buffer. For larger devcoredumps, + * the pre-written buffer must be periodically repopulated from the snapshot + * state due to kmalloc size limitations. + * + * Return: Number of bytes copied on success, or a negative error code on failure. + */ static ssize_t xe_devcoredump_read(char *buffer, loff_t offset, size_t count, void *data, size_t datalen) { struct xe_devcoredump *coredump = data; struct xe_devcoredump_snapshot *ss; - ssize_t byte_copied; + ssize_t byte_copied = 0; u32 chunk_offset; ssize_t new_chunk_position; + bool pm_needed = false; + int ret = 0; if (!coredump) return -ENODEV; @@ -188,20 +206,19 @@ static ssize_t xe_devcoredump_read(char *buffer, loff_t offset, /* Ensure delayed work is captured before continuing */ flush_work(&ss->work); - if (ss->read.size > XE_DEVCOREDUMP_CHUNK_MAX) + pm_needed = ss->read.size > XE_DEVCOREDUMP_CHUNK_MAX; + if (pm_needed) xe_pm_runtime_get(gt_to_xe(ss->gt)); mutex_lock(&coredump->lock); if (!ss->read.buffer) { - mutex_unlock(&coredump->lock); - return -ENODEV; + ret = -ENODEV; + goto unlock; } - if (offset >= ss->read.size) { - mutex_unlock(&coredump->lock); - return 0; - } + if (offset >= ss->read.size) + goto unlock; new_chunk_position = div_u64_rem(offset, XE_DEVCOREDUMP_CHUNK_MAX, @@ -221,12 +238,13 @@ static ssize_t xe_devcoredump_read(char *buffer, loff_t offset, ss->read.size - offset; memcpy(buffer, ss->read.buffer + chunk_offset, byte_copied); +unlock: mutex_unlock(&coredump->lock); - if (ss->read.size > XE_DEVCOREDUMP_CHUNK_MAX) + if (pm_needed) xe_pm_runtime_put(gt_to_xe(ss->gt)); - return byte_copied; + return byte_copied ? byte_copied : ret; } static void xe_devcoredump_free(void *data) diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c index 10622ca471a2..6717a636b1d9 100644 --- a/drivers/gpu/drm/xe/xe_gt_pagefault.c +++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c @@ -444,6 +444,7 @@ static int xe_alloc_pf_queue(struct xe_gt *gt, struct pf_queue *pf_queue) #define PF_MULTIPLIER 8 pf_queue->num_dw = (num_eus + XE_NUM_HW_ENGINES) * PF_MSG_LEN_DW * PF_MULTIPLIER; + pf_queue->num_dw = roundup_pow_of_two(pf_queue->num_dw); #undef PF_MULTIPLIER pf_queue->gt = gt; diff --git a/drivers/gpu/drm/xe/xe_lmtt.c b/drivers/gpu/drm/xe/xe_lmtt.c index 63db66df064b..023ed6a6b49d 100644 --- a/drivers/gpu/drm/xe/xe_lmtt.c +++ b/drivers/gpu/drm/xe/xe_lmtt.c @@ -78,6 +78,9 @@ static struct xe_lmtt_pt *lmtt_pt_alloc(struct xe_lmtt *lmtt, unsigned int level } lmtt_assert(lmtt, xe_bo_is_vram(bo)); + lmtt_debug(lmtt, "level=%u addr=%#llx\n", level, (u64)xe_bo_main_addr(bo, XE_PAGE_SIZE)); + + xe_map_memset(lmtt_to_xe(lmtt), &bo->vmap, 0, 0, bo->size); pt->level = level; pt->bo = bo; @@ -91,6 +94,9 @@ out: static void lmtt_pt_free(struct xe_lmtt_pt *pt) { + lmtt_debug(&pt->bo->tile->sriov.pf.lmtt, "level=%u addr=%llx\n", + pt->level, (u64)xe_bo_main_addr(pt->bo, XE_PAGE_SIZE)); + xe_bo_unpin_map_no_vm(pt->bo); kfree(pt); } @@ -226,9 +232,14 @@ static void lmtt_write_pte(struct xe_lmtt *lmtt, struct xe_lmtt_pt *pt, switch (lmtt->ops->lmtt_pte_size(level)) { case sizeof(u32): + lmtt_assert(lmtt, !overflows_type(pte, u32)); + lmtt_assert(lmtt, !pte || !iosys_map_rd(&pt->bo->vmap, idx * sizeof(u32), u32)); + xe_map_wr(lmtt_to_xe(lmtt), &pt->bo->vmap, idx * sizeof(u32), u32, pte); break; case sizeof(u64): + lmtt_assert(lmtt, !pte || !iosys_map_rd(&pt->bo->vmap, idx * sizeof(u64), u64)); + xe_map_wr(lmtt_to_xe(lmtt), &pt->bo->vmap, idx * sizeof(u64), u64, pte); break; default: diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c index 7acdc4c78866..66bc02302c55 100644 --- a/drivers/gpu/drm/xe/xe_migrate.c +++ b/drivers/gpu/drm/xe/xe_migrate.c @@ -863,7 +863,7 @@ struct dma_fence *xe_migrate_copy(struct xe_migrate *m, if (src_is_vram && xe_migrate_allow_identity(src_L0, &src_it)) xe_res_next(&src_it, src_L0); else - emit_pte(m, bb, src_L0_pt, src_is_vram, copy_system_ccs, + emit_pte(m, bb, src_L0_pt, src_is_vram, copy_system_ccs || use_comp_pat, &src_it, src_L0, src); if (dst_is_vram && xe_migrate_allow_identity(src_L0, &dst_it)) diff --git a/drivers/gpu/drm/xe/xe_module.c b/drivers/gpu/drm/xe/xe_module.c index e4742e27e2cd..da6793c2f991 100644 --- a/drivers/gpu/drm/xe/xe_module.c +++ b/drivers/gpu/drm/xe/xe_module.c @@ -20,7 +20,7 @@ struct xe_modparam xe_modparam = { .probe_display = true, - .guc_log_level = 3, + .guc_log_level = IS_ENABLED(CONFIG_DRM_XE_DEBUG) ? 3 : 1, .force_probe = CONFIG_DRM_XE_FORCE_PROBE, .wedged_mode = 1, .svm_notifier_size = 512, diff --git a/drivers/gpu/drm/xe/xe_pci.c b/drivers/gpu/drm/xe/xe_pci.c index ac4beaed58ff..278af53c74dc 100644 --- a/drivers/gpu/drm/xe/xe_pci.c +++ b/drivers/gpu/drm/xe/xe_pci.c @@ -140,7 +140,6 @@ static const struct xe_graphics_desc graphics_xelpg = { .has_asid = 1, \ .has_atomic_enable_pte_bit = 1, \ .has_flat_ccs = 1, \ - .has_indirect_ring_state = 1, \ .has_range_tlb_invalidation = 1, \ .has_usm = 1, \ .has_64bit_timestamp = 1, \ diff --git a/drivers/gpu/drm/xe/xe_pm.c b/drivers/gpu/drm/xe/xe_pm.c index ff749edc005b..ad263de44111 100644 --- a/drivers/gpu/drm/xe/xe_pm.c +++ b/drivers/gpu/drm/xe/xe_pm.c @@ -134,7 +134,7 @@ int xe_pm_suspend(struct xe_device *xe) /* FIXME: Super racey... */ err = xe_bo_evict_all(xe); if (err) - goto err_pxp; + goto err_display; for_each_gt(gt, xe, id) { err = xe_gt_suspend(gt); @@ -151,7 +151,6 @@ int xe_pm_suspend(struct xe_device *xe) err_display: xe_display_pm_resume(xe); -err_pxp: xe_pxp_pm_resume(xe->pxp); err: drm_dbg(&xe->drm, "Device suspend failed %d\n", err); @@ -753,11 +752,13 @@ void xe_pm_assert_unbounded_bridge(struct xe_device *xe) } /** - * xe_pm_set_vram_threshold - Set a vram threshold for allowing/blocking D3Cold + * xe_pm_set_vram_threshold - Set a VRAM threshold for allowing/blocking D3Cold * @xe: xe device instance - * @threshold: VRAM size in bites for the D3cold threshold + * @threshold: VRAM size in MiB for the D3cold threshold * - * Returns 0 for success, negative error code otherwise. + * Return: + * * 0 - success + * * -EINVAL - invalid argument */ int xe_pm_set_vram_threshold(struct xe_device *xe, u32 threshold) { diff --git a/drivers/gpu/drm/xe/xe_uc_fw.c b/drivers/gpu/drm/xe/xe_uc_fw.c index 2741849bbf4d..a6612105201a 100644 --- a/drivers/gpu/drm/xe/xe_uc_fw.c +++ b/drivers/gpu/drm/xe/xe_uc_fw.c @@ -114,10 +114,10 @@ struct fw_blobs_by_type { #define XE_GT_TYPE_ANY XE_GT_TYPE_UNINITIALIZED #define XE_GUC_FIRMWARE_DEFS(fw_def, mmp_ver, major_ver) \ - fw_def(BATTLEMAGE, GT_TYPE_ANY, major_ver(xe, guc, bmg, 70, 44, 1)) \ - fw_def(LUNARLAKE, GT_TYPE_ANY, major_ver(xe, guc, lnl, 70, 44, 1)) \ + fw_def(BATTLEMAGE, GT_TYPE_ANY, major_ver(xe, guc, bmg, 70, 45, 2)) \ + fw_def(LUNARLAKE, GT_TYPE_ANY, major_ver(xe, guc, lnl, 70, 45, 2)) \ fw_def(METEORLAKE, GT_TYPE_ANY, major_ver(i915, guc, mtl, 70, 44, 1)) \ - fw_def(DG2, GT_TYPE_ANY, major_ver(i915, guc, dg2, 70, 44, 1)) \ + fw_def(DG2, GT_TYPE_ANY, major_ver(i915, guc, dg2, 70, 45, 2)) \ fw_def(DG1, GT_TYPE_ANY, major_ver(i915, guc, dg1, 70, 44, 1)) \ fw_def(ALDERLAKE_N, GT_TYPE_ANY, major_ver(i915, guc, tgl, 70, 44, 1)) \ fw_def(ALDERLAKE_P, GT_TYPE_ANY, major_ver(i915, guc, adlp, 70, 44, 1)) \ diff --git a/drivers/gpu/drm/xe/xe_wa_oob.rules b/drivers/gpu/drm/xe/xe_wa_oob.rules index 69c1d7fc695e..6d70109fcc43 100644 --- a/drivers/gpu/drm/xe/xe_wa_oob.rules +++ b/drivers/gpu/drm/xe/xe_wa_oob.rules @@ -38,10 +38,10 @@ GRAPHICS_VERSION(2004) GRAPHICS_VERSION_RANGE(3000, 3001) 22019338487 MEDIA_VERSION(2000) - GRAPHICS_VERSION(2001) + GRAPHICS_VERSION(2001), FUNC(xe_rtp_match_not_sriov_vf) MEDIA_VERSION(3000), MEDIA_STEP(A0, B0), FUNC(xe_rtp_match_not_sriov_vf) 22019338487_display PLATFORM(LUNARLAKE) -16023588340 GRAPHICS_VERSION(2001) +16023588340 GRAPHICS_VERSION(2001), FUNC(xe_rtp_match_not_sriov_vf) 14019789679 GRAPHICS_VERSION(1255) GRAPHICS_VERSION_RANGE(1270, 2004) no_media_l3 MEDIA_VERSION(3000) diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index b348d0464314..b31b8a2fd540 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -1883,9 +1883,12 @@ u8 *hid_alloc_report_buf(struct hid_report *report, gfp_t flags) /* * 7 extra bytes are necessary to achieve proper functionality * of implement() working on 8 byte chunks + * 1 extra byte for the report ID if it is null (not used) so + * we can reserve that extra byte in the first position of the buffer + * when sending it to .raw_request() */ - u32 len = hid_report_len(report) + 7; + u32 len = hid_report_len(report) + 7 + (report->id == 0); return kzalloc(len, flags); } @@ -1973,7 +1976,7 @@ static struct hid_report *hid_get_report(struct hid_report_enum *report_enum, int __hid_request(struct hid_device *hid, struct hid_report *report, enum hid_class_request reqtype) { - char *buf; + char *buf, *data_buf; int ret; u32 len; @@ -1981,13 +1984,19 @@ int __hid_request(struct hid_device *hid, struct hid_report *report, if (!buf) return -ENOMEM; + data_buf = buf; len = hid_report_len(report); + if (report->id == 0) { + /* reserve the first byte for the report ID */ + data_buf++; + len++; + } + if (reqtype == HID_REQ_SET_REPORT) - hid_output_report(report, buf); + hid_output_report(report, data_buf); - ret = hid->ll_driver->raw_request(hid, report->id, buf, len, - report->type, reqtype); + ret = hid_hw_raw_request(hid, report->id, buf, len, report->type, reqtype); if (ret < 0) { dbg_hid("unable to complete request: %d\n", ret); goto out; diff --git a/drivers/hid/hid-debug.c b/drivers/hid/hid-debug.c index c6b6b1029540..4424c0512bae 100644 --- a/drivers/hid/hid-debug.c +++ b/drivers/hid/hid-debug.c @@ -3299,7 +3299,7 @@ static const char *keys[KEY_MAX + 1] = { [BTN_STYLUS2] = "Stylus2", [BTN_TOOL_DOUBLETAP] = "ToolDoubleTap", [BTN_TOOL_TRIPLETAP] = "ToolTripleTap", [BTN_TOOL_QUADTAP] = "ToolQuadrupleTap", [BTN_GEAR_DOWN] = "BtnGearDown", [BTN_GEAR_UP] = "BtnGearUp", - [BTN_WHEEL] = "BtnWheel", [KEY_OK] = "Ok", + [KEY_OK] = "Ok", [KEY_SELECT] = "Select", [KEY_GOTO] = "Goto", [KEY_CLEAR] = "Clear", [KEY_POWER2] = "Power2", [KEY_OPTION] = "Option", [KEY_INFO] = "Info", diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index ec84ba5e93e5..ff7595caf440 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -2742,7 +2742,11 @@ static unsigned long __evict_a_few(unsigned long nr_buffers) __make_buffer_clean(b); __free_buffer_wake(b); - cond_resched(); + if (need_resched()) { + dm_bufio_unlock(c); + cond_resched(); + dm_bufio_lock(c); + } } dm_bufio_unlock(c); diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index bd694910b01b..7f524a26cebc 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -2366,8 +2366,7 @@ static int bitmap_get_stats(void *data, struct md_bitmap_stats *stats) if (!bitmap) return -ENOENT; - if (!bitmap->mddev->bitmap_info.external && - !bitmap->storage.sb_page) + if (!bitmap->storage.sb_page) return -EINVAL; sb = kmap_local_page(bitmap->storage.sb_page); stats->sync_size = le64_to_cpu(sb->sync_size); diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 19c5a0ce5a40..64b8176907a9 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1399,7 +1399,7 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio, } read_bio = bio_alloc_clone(mirror->rdev->bdev, bio, gfp, &mddev->bio_set); - + read_bio->bi_opf &= ~REQ_NOWAIT; r1_bio->bios[rdisk] = read_bio; read_bio->bi_iter.bi_sector = r1_bio->sector + @@ -1649,6 +1649,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, wait_for_serialization(rdev, r1_bio); } + mbio->bi_opf &= ~REQ_NOWAIT; r1_bio->bios[i] = mbio; mbio->bi_iter.bi_sector = (r1_bio->sector + rdev->data_offset); @@ -3428,6 +3429,7 @@ static int raid1_reshape(struct mddev *mddev) /* ok, everything is stopped */ oldpool = conf->r1bio_pool; conf->r1bio_pool = newpool; + init_waitqueue_head(&conf->r1bio_pool.wait); for (d = d2 = 0; d < conf->raid_disks; d++) { struct md_rdev *rdev = conf->mirrors[d].rdev; diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index b74780af4c22..c9bd2005bfd0 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1182,8 +1182,11 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio, } } - if (!regular_request_wait(mddev, conf, bio, r10_bio->sectors)) + if (!regular_request_wait(mddev, conf, bio, r10_bio->sectors)) { + raid_end_bio_io(r10_bio); return; + } + rdev = read_balance(conf, r10_bio, &max_sectors); if (!rdev) { if (err_rdev) { @@ -1221,6 +1224,7 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio, r10_bio->master_bio = bio; } read_bio = bio_alloc_clone(rdev->bdev, bio, gfp, &mddev->bio_set); + read_bio->bi_opf &= ~REQ_NOWAIT; r10_bio->devs[slot].bio = read_bio; r10_bio->devs[slot].rdev = rdev; @@ -1256,6 +1260,7 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio, conf->mirrors[devnum].rdev; mbio = bio_alloc_clone(rdev->bdev, bio, GFP_NOIO, &mddev->bio_set); + mbio->bi_opf &= ~REQ_NOWAIT; if (replacement) r10_bio->devs[n_copy].repl_bio = mbio; else @@ -1370,8 +1375,11 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio, } sectors = r10_bio->sectors; - if (!regular_request_wait(mddev, conf, bio, sectors)) + if (!regular_request_wait(mddev, conf, bio, sectors)) { + raid_end_bio_io(r10_bio); return; + } + if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) && (mddev->reshape_backwards ? (bio->bi_iter.bi_sector < conf->reshape_safe && diff --git a/drivers/pci/controller/pci-host-common.c b/drivers/pci/controller/pci-host-common.c index b0992325dd65..b37052863847 100644 --- a/drivers/pci/controller/pci-host-common.c +++ b/drivers/pci/controller/pci-host-common.c @@ -64,13 +64,13 @@ int pci_host_common_init(struct platform_device *pdev, of_pci_check_probe_only(); + platform_set_drvdata(pdev, bridge); + /* Parse and map our Configuration Space windows */ cfg = gen_pci_init(dev, bridge, ops); if (IS_ERR(cfg)) return PTR_ERR(cfg); - platform_set_drvdata(pdev, bridge); - bridge->sysdata = cfg; bridge->ops = (struct pci_ops *)&ops->pci_ops; bridge->enable_device = ops->enable_device; diff --git a/drivers/pci/controller/pcie-apple.c b/drivers/pci/controller/pcie-apple.c index 77fe73976654..0380d300adca 100644 --- a/drivers/pci/controller/pcie-apple.c +++ b/drivers/pci/controller/pcie-apple.c @@ -187,6 +187,7 @@ struct apple_pcie { const struct hw_info *hw; unsigned long *bitmap; struct list_head ports; + struct list_head entry; struct completion event; struct irq_fwspec fwspec; u32 nvecs; @@ -205,6 +206,9 @@ struct apple_pcie_port { int idx; }; +static LIST_HEAD(pcie_list); +static DEFINE_MUTEX(pcie_list_lock); + static void rmw_set(u32 set, void __iomem *addr) { writel_relaxed(readl_relaxed(addr) | set, addr); @@ -720,13 +724,45 @@ static int apple_msi_init(struct apple_pcie *pcie) return 0; } +static void apple_pcie_register(struct apple_pcie *pcie) +{ + guard(mutex)(&pcie_list_lock); + + list_add_tail(&pcie->entry, &pcie_list); +} + +static void apple_pcie_unregister(struct apple_pcie *pcie) +{ + guard(mutex)(&pcie_list_lock); + + list_del(&pcie->entry); +} + +static struct apple_pcie *apple_pcie_lookup(struct device *dev) +{ + struct apple_pcie *pcie; + + guard(mutex)(&pcie_list_lock); + + list_for_each_entry(pcie, &pcie_list, entry) { + if (pcie->dev == dev) + return pcie; + } + + return NULL; +} + static struct apple_pcie_port *apple_pcie_get_port(struct pci_dev *pdev) { struct pci_config_window *cfg = pdev->sysdata; - struct apple_pcie *pcie = cfg->priv; + struct apple_pcie *pcie; struct pci_dev *port_pdev; struct apple_pcie_port *port; + pcie = apple_pcie_lookup(cfg->parent); + if (WARN_ON(!pcie)) + return NULL; + /* Find the root port this device is on */ port_pdev = pcie_find_root_port(pdev); @@ -806,10 +842,14 @@ static void apple_pcie_disable_device(struct pci_host_bridge *bridge, struct pci static int apple_pcie_init(struct pci_config_window *cfg) { - struct apple_pcie *pcie = cfg->priv; struct device *dev = cfg->parent; + struct apple_pcie *pcie; int ret; + pcie = apple_pcie_lookup(dev); + if (WARN_ON(!pcie)) + return -ENOENT; + for_each_available_child_of_node_scoped(dev->of_node, of_port) { ret = apple_pcie_setup_port(pcie, of_port); if (ret) { @@ -852,13 +892,18 @@ static int apple_pcie_probe(struct platform_device *pdev) mutex_init(&pcie->lock); INIT_LIST_HEAD(&pcie->ports); - dev_set_drvdata(dev, pcie); ret = apple_msi_init(pcie); if (ret) return ret; - return pci_host_common_init(pdev, &apple_pcie_cfg_ecam_ops); + apple_pcie_register(pcie); + + ret = pci_host_common_init(pdev, &apple_pcie_cfg_ecam_ops); + if (ret) + apple_pcie_unregister(pcie); + + return ret; } static const struct of_device_id apple_pcie_of_match[] = { diff --git a/drivers/pci/ecam.c b/drivers/pci/ecam.c index 2c5e6446e00e..260b7de2dbd5 100644 --- a/drivers/pci/ecam.c +++ b/drivers/pci/ecam.c @@ -84,8 +84,6 @@ struct pci_config_window *pci_ecam_create(struct device *dev, goto err_exit_iomap; } - cfg->priv = dev_get_drvdata(dev); - if (ops->init) { err = ops->init(cfg); if (err) diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c index 6ede55a7c5e6..d686488f4111 100644 --- a/drivers/pci/msi/msi.c +++ b/drivers/pci/msi/msi.c @@ -934,10 +934,12 @@ int pci_msix_write_tph_tag(struct pci_dev *pdev, unsigned int index, u16 tag) if (!pdev->msix_enabled) return -ENXIO; - guard(msi_descs_lock)(&pdev->dev); virq = msi_get_virq(&pdev->dev, index); if (!virq) return -ENXIO; + + guard(msi_descs_lock)(&pdev->dev); + /* * This is a horrible hack, but short of implementing a PCI * specific interrupt chip callback and a huge pile of diff --git a/drivers/soc/aspeed/aspeed-lpc-snoop.c b/drivers/soc/aspeed/aspeed-lpc-snoop.c index ef8f355589a5..fc3a2c41cc10 100644 --- a/drivers/soc/aspeed/aspeed-lpc-snoop.c +++ b/drivers/soc/aspeed/aspeed-lpc-snoop.c @@ -58,6 +58,7 @@ struct aspeed_lpc_snoop_model_data { }; struct aspeed_lpc_snoop_channel { + bool enabled; struct kfifo fifo; wait_queue_head_t wq; struct miscdevice miscdev; @@ -190,6 +191,9 @@ static int aspeed_lpc_enable_snoop(struct aspeed_lpc_snoop *lpc_snoop, const struct aspeed_lpc_snoop_model_data *model_data = of_device_get_match_data(dev); + if (WARN_ON(lpc_snoop->chan[channel].enabled)) + return -EBUSY; + init_waitqueue_head(&lpc_snoop->chan[channel].wq); /* Create FIFO datastructure */ rc = kfifo_alloc(&lpc_snoop->chan[channel].fifo, @@ -236,6 +240,8 @@ static int aspeed_lpc_enable_snoop(struct aspeed_lpc_snoop *lpc_snoop, regmap_update_bits(lpc_snoop->regmap, HICRB, hicrb_en, hicrb_en); + lpc_snoop->chan[channel].enabled = true; + return 0; err_misc_deregister: @@ -248,6 +254,9 @@ err_free_fifo: static void aspeed_lpc_disable_snoop(struct aspeed_lpc_snoop *lpc_snoop, int channel) { + if (!lpc_snoop->chan[channel].enabled) + return; + switch (channel) { case 0: regmap_update_bits(lpc_snoop->regmap, HICR5, @@ -263,8 +272,10 @@ static void aspeed_lpc_disable_snoop(struct aspeed_lpc_snoop *lpc_snoop, return; } - kfifo_free(&lpc_snoop->chan[channel].fifo); + lpc_snoop->chan[channel].enabled = false; + /* Consider improving safety wrt concurrent reader(s) */ misc_deregister(&lpc_snoop->chan[channel].miscdev); + kfifo_free(&lpc_snoop->chan[channel].fifo); } static int aspeed_lpc_snoop_probe(struct platform_device *pdev) diff --git a/fs/bcachefs/btree_cache.c b/fs/bcachefs/btree_cache.c index 91e0aa796e6b..83c9860e6b82 100644 --- a/fs/bcachefs/btree_cache.c +++ b/fs/bcachefs/btree_cache.c @@ -85,7 +85,7 @@ void bch2_btree_node_to_freelist(struct bch_fs *c, struct btree *b) six_unlock_intent(&b->c.lock); } -static void __btree_node_data_free(struct btree_cache *bc, struct btree *b) +void __btree_node_data_free(struct btree *b) { BUG_ON(!list_empty(&b->list)); BUG_ON(btree_node_hashed(b)); @@ -112,16 +112,17 @@ static void __btree_node_data_free(struct btree_cache *bc, struct btree *b) munmap(b->aux_data, btree_aux_data_bytes(b)); #endif b->aux_data = NULL; - - btree_node_to_freedlist(bc, b); } static void btree_node_data_free(struct btree_cache *bc, struct btree *b) { BUG_ON(list_empty(&b->list)); list_del_init(&b->list); + + __btree_node_data_free(b); + --bc->nr_freeable; - __btree_node_data_free(bc, b); + btree_node_to_freedlist(bc, b); } static int bch2_btree_cache_cmp_fn(struct rhashtable_compare_arg *arg, @@ -185,10 +186,7 @@ static struct btree *__btree_node_mem_alloc(struct bch_fs *c, gfp_t gfp) struct btree *__bch2_btree_node_mem_alloc(struct bch_fs *c) { - struct btree_cache *bc = &c->btree_cache; - struct btree *b; - - b = __btree_node_mem_alloc(c, GFP_KERNEL); + struct btree *b = __btree_node_mem_alloc(c, GFP_KERNEL); if (!b) return NULL; @@ -198,8 +196,6 @@ struct btree *__bch2_btree_node_mem_alloc(struct bch_fs *c) } bch2_btree_lock_init(&b->c, 0, GFP_KERNEL); - - __bch2_btree_node_to_freelist(bc, b); return b; } @@ -524,7 +520,8 @@ restart: --touched;; } else if (!btree_node_reclaim(c, b)) { __bch2_btree_node_hash_remove(bc, b); - __btree_node_data_free(bc, b); + __btree_node_data_free(b); + btree_node_to_freedlist(bc, b); freed++; bc->nr_freed++; @@ -652,9 +649,12 @@ int bch2_fs_btree_cache_init(struct bch_fs *c) bch2_recalc_btree_reserve(c); - for (i = 0; i < bc->nr_reserve; i++) - if (!__bch2_btree_node_mem_alloc(c)) + for (i = 0; i < bc->nr_reserve; i++) { + struct btree *b = __bch2_btree_node_mem_alloc(c); + if (!b) goto err; + __bch2_btree_node_to_freelist(bc, b); + } list_splice_init(&bc->live[0].list, &bc->freeable); diff --git a/fs/bcachefs/btree_cache.h b/fs/bcachefs/btree_cache.h index ca3c1b145330..be275f87a60e 100644 --- a/fs/bcachefs/btree_cache.h +++ b/fs/bcachefs/btree_cache.h @@ -30,6 +30,7 @@ void bch2_btree_node_update_key_early(struct btree_trans *, enum btree_id, unsig void bch2_btree_cache_cannibalize_unlock(struct btree_trans *); int bch2_btree_cache_cannibalize_lock(struct btree_trans *, struct closure *); +void __btree_node_data_free(struct btree *); struct btree *__bch2_btree_node_mem_alloc(struct bch_fs *); struct btree *bch2_btree_node_mem_alloc(struct btree_trans *, bool); diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c index e874a4357f64..a4cc72986e36 100644 --- a/fs/bcachefs/btree_io.c +++ b/fs/bcachefs/btree_io.c @@ -568,9 +568,9 @@ static int __btree_err(int ret, bch2_mark_btree_validate_failure(failed, ca->dev_idx); struct extent_ptr_decoded pick; - have_retry = !bch2_bkey_pick_read_device(c, + have_retry = bch2_bkey_pick_read_device(c, bkey_i_to_s_c(&b->key), - failed, &pick, -1); + failed, &pick, -1) == 1; } if (!have_retry && ret == -BCH_ERR_btree_node_read_err_want_retry) @@ -615,7 +615,6 @@ static int __btree_err(int ret, goto out; case -BCH_ERR_btree_node_read_err_bad_node: prt_str(&out, ", "); - ret = __bch2_topology_error(c, &out); break; } @@ -644,7 +643,6 @@ static int __btree_err(int ret, goto out; case -BCH_ERR_btree_node_read_err_bad_node: prt_str(&out, ", "); - ret = __bch2_topology_error(c, &out); break; } print: @@ -1408,7 +1406,7 @@ static void btree_node_read_work(struct work_struct *work) ret = bch2_bkey_pick_read_device(c, bkey_i_to_s_c(&b->key), &failed, &rb->pick, -1); - if (ret) { + if (ret <= 0) { set_btree_node_read_error(b); break; } diff --git a/fs/bcachefs/btree_node_scan.c b/fs/bcachefs/btree_node_scan.c index 23d8c62ea4b6..42c9eb2c786e 100644 --- a/fs/bcachefs/btree_node_scan.c +++ b/fs/bcachefs/btree_node_scan.c @@ -75,39 +75,6 @@ static inline u64 bkey_journal_seq(struct bkey_s_c k) } } -static bool found_btree_node_is_readable(struct btree_trans *trans, - struct found_btree_node *f) -{ - struct { __BKEY_PADDED(k, BKEY_BTREE_PTR_VAL_U64s_MAX); } tmp; - - found_btree_node_to_key(&tmp.k, f); - - struct btree *b = bch2_btree_node_get_noiter(trans, &tmp.k, f->btree_id, f->level, false); - bool ret = !IS_ERR_OR_NULL(b); - if (!ret) - return ret; - - f->sectors_written = b->written; - f->journal_seq = le64_to_cpu(b->data->keys.journal_seq); - - struct bkey_s_c k; - struct bkey unpacked; - struct btree_node_iter iter; - for_each_btree_node_key_unpack(b, k, &iter, &unpacked) - f->journal_seq = max(f->journal_seq, bkey_journal_seq(k)); - - six_unlock_read(&b->c.lock); - - /* - * We might update this node's range; if that happens, we need the node - * to be re-read so the read path can trim keys that are no longer in - * this node - */ - if (b != btree_node_root(trans->c, b)) - bch2_btree_node_evict(trans, &tmp.k); - return ret; -} - static int found_btree_node_cmp_cookie(const void *_l, const void *_r) { const struct found_btree_node *l = _l; @@ -159,17 +126,17 @@ static const struct min_heap_callbacks found_btree_node_heap_cbs = { }; static void try_read_btree_node(struct find_btree_nodes *f, struct bch_dev *ca, - struct bio *bio, struct btree_node *bn, u64 offset) + struct btree *b, struct bio *bio, u64 offset) { struct bch_fs *c = container_of(f, struct bch_fs, found_btree_nodes); + struct btree_node *bn = b->data; bio_reset(bio, ca->disk_sb.bdev, REQ_OP_READ); bio->bi_iter.bi_sector = offset; - bch2_bio_map(bio, bn, PAGE_SIZE); + bch2_bio_map(bio, b->data, c->opts.block_size); u64 submit_time = local_clock(); submit_bio_wait(bio); - bch2_account_io_completion(ca, BCH_MEMBER_ERROR_read, submit_time, !bio->bi_status); if (bio->bi_status) { @@ -201,6 +168,14 @@ static void try_read_btree_node(struct find_btree_nodes *f, struct bch_dev *ca, if (BTREE_NODE_ID(bn) >= BTREE_ID_NR_MAX) return; + bio_reset(bio, ca->disk_sb.bdev, REQ_OP_READ); + bio->bi_iter.bi_sector = offset; + bch2_bio_map(bio, b->data, c->opts.btree_node_size); + + submit_time = local_clock(); + submit_bio_wait(bio); + bch2_account_io_completion(ca, BCH_MEMBER_ERROR_read, submit_time, !bio->bi_status); + rcu_read_lock(); struct found_btree_node n = { .btree_id = BTREE_NODE_ID(bn), @@ -217,7 +192,20 @@ static void try_read_btree_node(struct find_btree_nodes *f, struct bch_dev *ca, }; rcu_read_unlock(); - if (bch2_trans_run(c, found_btree_node_is_readable(trans, &n))) { + found_btree_node_to_key(&b->key, &n); + + CLASS(printbuf, buf)(); + if (!bch2_btree_node_read_done(c, ca, b, NULL, &buf)) { + /* read_done will swap out b->data for another buffer */ + bn = b->data; + /* + * Grab journal_seq here because we want the max journal_seq of + * any bset; read_done sorts down to a single set and picks the + * max journal_seq + */ + n.journal_seq = le64_to_cpu(bn->keys.journal_seq), + n.sectors_written = b->written; + mutex_lock(&f->lock); if (BSET_BIG_ENDIAN(&bn->keys) != CPU_BIG_ENDIAN) { bch_err(c, "try_read_btree_node() can't handle endian conversion"); @@ -237,12 +225,20 @@ static int read_btree_nodes_worker(void *p) struct find_btree_nodes_worker *w = p; struct bch_fs *c = container_of(w->f, struct bch_fs, found_btree_nodes); struct bch_dev *ca = w->ca; - void *buf = (void *) __get_free_page(GFP_KERNEL); - struct bio *bio = bio_alloc(NULL, 1, 0, GFP_KERNEL); unsigned long last_print = jiffies; + struct btree *b = NULL; + struct bio *bio = NULL; + + b = __bch2_btree_node_mem_alloc(c); + if (!b) { + bch_err(c, "read_btree_nodes_worker: error allocating buf"); + w->f->ret = -ENOMEM; + goto err; + } - if (!buf || !bio) { - bch_err(c, "read_btree_nodes_worker: error allocating bio/buf"); + bio = bio_alloc(NULL, buf_pages(b->data, c->opts.btree_node_size), 0, GFP_KERNEL); + if (!bio) { + bch_err(c, "read_btree_nodes_worker: error allocating bio"); w->f->ret = -ENOMEM; goto err; } @@ -266,11 +262,13 @@ static int read_btree_nodes_worker(void *p) !bch2_dev_btree_bitmap_marked_sectors(ca, sector, btree_sectors(c))) continue; - try_read_btree_node(w->f, ca, bio, buf, sector); + try_read_btree_node(w->f, ca, b, bio, sector); } err: + if (b) + __btree_node_data_free(b); + kfree(b); bio_put(bio); - free_page((unsigned long) buf); enumerated_ref_put(&ca->io_ref[READ], BCH_DEV_READ_REF_btree_node_scan); closure_put(w->cl); kfree(w); diff --git a/fs/bcachefs/debug.c b/fs/bcachefs/debug.c index 901f643ead83..07c2a0f73cc2 100644 --- a/fs/bcachefs/debug.c +++ b/fs/bcachefs/debug.c @@ -153,8 +153,6 @@ void __bch2_btree_verify(struct bch_fs *c, struct btree *b) c->verify_data = __bch2_btree_node_mem_alloc(c); if (!c->verify_data) goto out; - - list_del_init(&c->verify_data->list); } BUG_ON(b->nsets != 1); @@ -586,6 +584,8 @@ static ssize_t bch2_btree_transactions_read(struct file *file, char __user *buf, i->ubuf = buf; i->size = size; i->ret = 0; + + int srcu_idx = srcu_read_lock(&c->btree_trans_barrier); restart: seqmutex_lock(&c->btree_trans_lock); list_sort(&c->btree_trans_list, list_ptr_order_cmp); @@ -599,6 +599,11 @@ restart: if (!closure_get_not_zero(&trans->ref)) continue; + if (!trans->srcu_held) { + closure_put(&trans->ref); + continue; + } + u32 seq = seqmutex_unlock(&c->btree_trans_lock); bch2_btree_trans_to_text(&i->buf, trans); @@ -620,6 +625,8 @@ restart: } seqmutex_unlock(&c->btree_trans_lock); unlocked: + srcu_read_unlock(&c->btree_trans_barrier, srcu_idx); + if (i->buf.allocation_failure) ret = -ENOMEM; diff --git a/fs/bcachefs/errcode.h b/fs/bcachefs/errcode.h index 86a842f1e88e..acc3b7b67704 100644 --- a/fs/bcachefs/errcode.h +++ b/fs/bcachefs/errcode.h @@ -282,7 +282,6 @@ x(EIO, sb_not_downgraded) \ x(EIO, btree_node_write_all_failed) \ x(EIO, btree_node_read_error) \ - x(EIO, btree_node_read_validate_error) \ x(EIO, btree_need_topology_repair) \ x(EIO, bucket_ref_update) \ x(EIO, trigger_alloc) \ diff --git a/fs/bcachefs/error.c b/fs/bcachefs/error.c index b2a6c041e165..267e73d9d7e6 100644 --- a/fs/bcachefs/error.c +++ b/fs/bcachefs/error.c @@ -103,7 +103,7 @@ int __bch2_topology_error(struct bch_fs *c, struct printbuf *out) return bch_err_throw(c, btree_need_topology_repair); } else { return bch2_run_explicit_recovery_pass(c, out, BCH_RECOVERY_PASS_check_topology, 0) ?: - bch_err_throw(c, btree_node_read_validate_error); + bch_err_throw(c, btree_need_topology_repair); } } @@ -633,7 +633,9 @@ err: * log_fsck_err()s: that would require us to track for every error type * which recovery pass corrects it, to get the fsck exit status correct: */ - if (bch2_err_matches(ret, BCH_ERR_fsck_fix)) { + if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) { + /* nothing */ + } else if (bch2_err_matches(ret, BCH_ERR_fsck_fix)) { set_bit(BCH_FS_errors_fixed, &c->flags); } else { set_bit(BCH_FS_errors_not_fixed, &c->flags); diff --git a/fs/bcachefs/extents.c b/fs/bcachefs/extents.c index 036e4ad95987..83cbd77dcb9c 100644 --- a/fs/bcachefs/extents.c +++ b/fs/bcachefs/extents.c @@ -50,19 +50,17 @@ void bch2_io_failures_to_text(struct printbuf *out, struct bch_io_failures *failed) { static const char * const error_types[] = { - "io", "checksum", "ec reconstruct", NULL + "btree validate", "io", "checksum", "ec reconstruct", NULL }; for (struct bch_dev_io_failures *f = failed->devs; f < failed->devs + failed->nr; f++) { unsigned errflags = - ((!!f->failed_io) << 0) | - ((!!f->failed_csum_nr) << 1) | - ((!!f->failed_ec) << 2); - - if (!errflags) - continue; + ((!!f->failed_btree_validate) << 0) | + ((!!f->failed_io) << 1) | + ((!!f->failed_csum_nr) << 2) | + ((!!f->failed_ec) << 3); bch2_printbuf_make_room(out, 1024); out->atomic++; @@ -77,7 +75,9 @@ void bch2_io_failures_to_text(struct printbuf *out, prt_char(out, ' '); - if (is_power_of_2(errflags)) { + if (!errflags) { + prt_str(out, "no error - confused"); + } else if (is_power_of_2(errflags)) { prt_bitflags(out, error_types, errflags); prt_str(out, " error"); } else { diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c index dbf161e4311a..856eb2b41896 100644 --- a/fs/bcachefs/fsck.c +++ b/fs/bcachefs/fsck.c @@ -12,6 +12,7 @@ #include "fs.h" #include "fsck.h" #include "inode.h" +#include "io_misc.h" #include "keylist.h" #include "namei.h" #include "recovery_passes.h" @@ -1919,33 +1920,11 @@ static int check_extent(struct btree_trans *trans, struct btree_iter *iter, "extent type past end of inode %llu:%u, i_size %llu\n%s", i->inode.bi_inum, i->inode.bi_snapshot, i->inode.bi_size, (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) { - struct bkey_i *whiteout = bch2_trans_kmalloc(trans, sizeof(*whiteout)); - ret = PTR_ERR_OR_ZERO(whiteout); - if (ret) - goto err; - - bkey_init(&whiteout->k); - whiteout->k.p = SPOS(k.k->p.inode, - last_block, - i->inode.bi_snapshot); - bch2_key_resize(&whiteout->k, - min(KEY_SIZE_MAX & (~0 << c->block_bits), - U64_MAX - whiteout->k.p.offset)); - - - /* - * Need a normal (not BTREE_ITER_all_snapshots) - * iterator, if we're deleting in a different - * snapshot and need to emit a whiteout - */ - struct btree_iter iter2; - bch2_trans_iter_init(trans, &iter2, BTREE_ID_extents, - bkey_start_pos(&whiteout->k), - BTREE_ITER_intent); - ret = bch2_btree_iter_traverse(trans, &iter2) ?: - bch2_trans_update(trans, &iter2, whiteout, - BTREE_UPDATE_internal_snapshot_node); - bch2_trans_iter_exit(trans, &iter2); + ret = bch2_fpunch_snapshot(trans, + SPOS(i->inode.bi_inum, + last_block, + i->inode.bi_snapshot), + POS(i->inode.bi_inum, U64_MAX)); if (ret) goto err; diff --git a/fs/bcachefs/io_misc.c b/fs/bcachefs/io_misc.c index bf72b1d2e2cb..07023667a475 100644 --- a/fs/bcachefs/io_misc.c +++ b/fs/bcachefs/io_misc.c @@ -135,6 +135,33 @@ err_noprint: return ret; } +/* For fsck */ +int bch2_fpunch_snapshot(struct btree_trans *trans, struct bpos start, struct bpos end) +{ + u32 restart_count = trans->restart_count; + struct bch_fs *c = trans->c; + struct disk_reservation disk_res = bch2_disk_reservation_init(c, 0); + unsigned max_sectors = KEY_SIZE_MAX & (~0 << c->block_bits); + struct bkey_i delete; + + int ret = for_each_btree_key_max_commit(trans, iter, BTREE_ID_extents, + start, end, 0, k, + &disk_res, NULL, BCH_TRANS_COMMIT_no_enospc, ({ + bkey_init(&delete.k); + delete.k.p = iter.pos; + + /* create the biggest key we can */ + bch2_key_resize(&delete.k, max_sectors); + bch2_cut_back(end, &delete); + + bch2_extent_trim_atomic(trans, &iter, &delete) ?: + bch2_trans_update(trans, &iter, &delete, 0); + })); + + bch2_disk_reservation_put(c, &disk_res); + return ret ?: trans_was_restarted(trans, restart_count); +} + /* * Returns -BCH_ERR_transacton_restart if we had to drop locks: */ diff --git a/fs/bcachefs/io_misc.h b/fs/bcachefs/io_misc.h index 9cb44a7c43c1..b93e4d4b3c0c 100644 --- a/fs/bcachefs/io_misc.h +++ b/fs/bcachefs/io_misc.h @@ -5,6 +5,8 @@ int bch2_extent_fallocate(struct btree_trans *, subvol_inum, struct btree_iter *, u64, struct bch_io_opts, s64 *, struct write_point_specifier); + +int bch2_fpunch_snapshot(struct btree_trans *, struct bpos, struct bpos); int bch2_fpunch_at(struct btree_trans *, struct btree_iter *, subvol_inum, u64, s64 *); int bch2_fpunch(struct bch_fs *c, subvol_inum, u64, u64, s64 *); diff --git a/fs/bcachefs/journal_reclaim.c b/fs/bcachefs/journal_reclaim.c index cd6201741c59..0042d43b8e57 100644 --- a/fs/bcachefs/journal_reclaim.c +++ b/fs/bcachefs/journal_reclaim.c @@ -170,6 +170,12 @@ static struct journal_space __journal_space_available(struct journal *j, unsigne return (struct journal_space) { 0, 0 }; /* + * It's possible for bucket size to be misaligned w.r.t. the filesystem + * block size: + */ + min_bucket_size = round_down(min_bucket_size, block_sectors(c)); + + /* * We sorted largest to smallest, and we want the smallest out of the * @nr_devs_want largest devices: */ diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c index d0b7e3a36a54..c94debb12d2f 100644 --- a/fs/bcachefs/recovery.c +++ b/fs/bcachefs/recovery.c @@ -273,24 +273,35 @@ static int bch2_journal_replay_key(struct btree_trans *trans, goto out; struct btree_path *path = btree_iter_path(trans, &iter); - if (unlikely(!btree_path_node(path, k->level) && - !k->allocated)) { + if (unlikely(!btree_path_node(path, k->level))) { struct bch_fs *c = trans->c; + CLASS(printbuf, buf)(); + prt_str(&buf, "btree="); + bch2_btree_id_to_text(&buf, k->btree_id); + prt_printf(&buf, " level=%u ", k->level); + bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(k->k)); + if (!(c->recovery.passes_complete & (BIT_ULL(BCH_RECOVERY_PASS_scan_for_btree_nodes)| BIT_ULL(BCH_RECOVERY_PASS_check_topology)))) { - bch_err(c, "have key in journal replay for btree depth that does not exist, confused"); + bch_err(c, "have key in journal replay for btree depth that does not exist, confused\n%s", + buf.buf); ret = -EINVAL; } -#if 0 + + if (!k->allocated) { + bch_notice(c, "dropping key in journal replay for depth that does not exist because we're recovering from scan\n%s", + buf.buf); + k->overwritten = true; + goto out; + } + bch2_trans_iter_exit(trans, &iter); bch2_trans_node_iter_init(trans, &iter, k->btree_id, k->k->k.p, BTREE_MAX_DEPTH, 0, iter_flags); ret = bch2_btree_iter_traverse(trans, &iter) ?: bch2_btree_increase_depth(trans, iter.path, 0) ?: -BCH_ERR_transaction_restart_nested; -#endif - k->overwritten = true; goto out; } diff --git a/fs/bcachefs/recovery_passes.c b/fs/bcachefs/recovery_passes.c index c09ed2dd4639..6a039e011064 100644 --- a/fs/bcachefs/recovery_passes.c +++ b/fs/bcachefs/recovery_passes.c @@ -360,7 +360,7 @@ int __bch2_run_explicit_recovery_pass(struct bch_fs *c, !(r->passes_complete & BIT_ULL(pass)); bool ratelimit = flags & RUN_RECOVERY_PASS_ratelimit; - if (!(in_recovery && (flags & RUN_RECOVERY_PASS_nopersistent))) { + if (!(flags & RUN_RECOVERY_PASS_nopersistent)) { struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext); __set_bit_le64(bch2_recovery_pass_to_stable(pass), ext->recovery_passes_required); } diff --git a/fs/erofs/data.c b/fs/erofs/data.c index 6a329c329f43..16e4a6bd9b97 100644 --- a/fs/erofs/data.c +++ b/fs/erofs/data.c @@ -214,9 +214,11 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) /* * bit 30: I/O error occurred on this folio + * bit 29: CPU has dirty data in D-cache (needs aliasing handling); * bit 0 - 29: remaining parts to complete this folio */ -#define EROFS_ONLINEFOLIO_EIO (1 << 30) +#define EROFS_ONLINEFOLIO_EIO 30 +#define EROFS_ONLINEFOLIO_DIRTY 29 void erofs_onlinefolio_init(struct folio *folio) { @@ -233,19 +235,23 @@ void erofs_onlinefolio_split(struct folio *folio) atomic_inc((atomic_t *)&folio->private); } -void erofs_onlinefolio_end(struct folio *folio, int err) +void erofs_onlinefolio_end(struct folio *folio, int err, bool dirty) { int orig, v; do { orig = atomic_read((atomic_t *)&folio->private); - v = (orig - 1) | (err ? EROFS_ONLINEFOLIO_EIO : 0); + DBG_BUGON(orig <= 0); + v = dirty << EROFS_ONLINEFOLIO_DIRTY; + v |= (orig - 1) | (!!err << EROFS_ONLINEFOLIO_EIO); } while (atomic_cmpxchg((atomic_t *)&folio->private, orig, v) != orig); - if (v & ~EROFS_ONLINEFOLIO_EIO) + if (v & (BIT(EROFS_ONLINEFOLIO_DIRTY) - 1)) return; folio->private = 0; - folio_end_read(folio, !(v & EROFS_ONLINEFOLIO_EIO)); + if (v & BIT(EROFS_ONLINEFOLIO_DIRTY)) + flush_dcache_folio(folio); + folio_end_read(folio, !(v & BIT(EROFS_ONLINEFOLIO_EIO))); } static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length, @@ -351,11 +357,16 @@ int erofs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, */ static int erofs_read_folio(struct file *file, struct folio *folio) { + trace_erofs_read_folio(folio, true); + return iomap_read_folio(folio, &erofs_iomap_ops); } static void erofs_readahead(struct readahead_control *rac) { + trace_erofs_readahead(rac->mapping->host, readahead_index(rac), + readahead_count(rac), true); + return iomap_readahead(rac, &erofs_iomap_ops); } diff --git a/fs/erofs/decompressor.c b/fs/erofs/decompressor.c index bf62e2836b60..358061d7b660 100644 --- a/fs/erofs/decompressor.c +++ b/fs/erofs/decompressor.c @@ -301,13 +301,11 @@ static int z_erofs_transform_plain(struct z_erofs_decompress_req *rq, cur = min(cur, rq->outputsize); if (cur && rq->out[0]) { kin = kmap_local_page(rq->in[nrpages_in - 1]); - if (rq->out[0] == rq->in[nrpages_in - 1]) { + if (rq->out[0] == rq->in[nrpages_in - 1]) memmove(kin + rq->pageofs_out, kin + pi, cur); - flush_dcache_page(rq->out[0]); - } else { + else memcpy_to_page(rq->out[0], rq->pageofs_out, kin + pi, cur); - } kunmap_local(kin); } rq->outputsize -= cur; @@ -325,14 +323,12 @@ static int z_erofs_transform_plain(struct z_erofs_decompress_req *rq, po = (rq->pageofs_out + cur + pi) & ~PAGE_MASK; DBG_BUGON(no >= nrpages_out); cnt = min(insz - pi, PAGE_SIZE - po); - if (rq->out[no] == rq->in[ni]) { + if (rq->out[no] == rq->in[ni]) memmove(kin + po, kin + rq->pageofs_in + pi, cnt); - flush_dcache_page(rq->out[no]); - } else if (rq->out[no]) { + else if (rq->out[no]) memcpy_to_page(rq->out[no], po, kin + rq->pageofs_in + pi, cnt); - } pi += cnt; } while (pi < insz); kunmap_local(kin); diff --git a/fs/erofs/dir.c b/fs/erofs/dir.c index 2fae209d0274..3e4b38bec0aa 100644 --- a/fs/erofs/dir.c +++ b/fs/erofs/dir.c @@ -58,6 +58,11 @@ static int erofs_readdir(struct file *f, struct dir_context *ctx) struct erofs_dirent *de; unsigned int nameoff, maxsize; + if (fatal_signal_pending(current)) { + err = -ERESTARTSYS; + break; + } + de = erofs_bread(&buf, dbstart, true); if (IS_ERR(de)) { erofs_err(sb, "failed to readdir of logical block %llu of nid %llu", @@ -88,6 +93,7 @@ static int erofs_readdir(struct file *f, struct dir_context *ctx) break; ctx->pos = dbstart + maxsize; ofs = 0; + cond_resched(); } erofs_put_metabuf(&buf); if (EROFS_I(dir)->dot_omitted && ctx->pos == dir->i_size) { diff --git a/fs/erofs/fileio.c b/fs/erofs/fileio.c index df5cc63f2c01..91781718199e 100644 --- a/fs/erofs/fileio.c +++ b/fs/erofs/fileio.c @@ -38,7 +38,7 @@ static void erofs_fileio_ki_complete(struct kiocb *iocb, long ret) } else { bio_for_each_folio_all(fi, &rq->bio) { DBG_BUGON(folio_test_uptodate(fi.folio)); - erofs_onlinefolio_end(fi.folio, ret); + erofs_onlinefolio_end(fi.folio, ret, false); } } bio_uninit(&rq->bio); @@ -96,8 +96,6 @@ static int erofs_fileio_scan_folio(struct erofs_fileio *io, struct folio *folio) struct erofs_map_blocks *map = &io->map; unsigned int cur = 0, end = folio_size(folio), len, attached = 0; loff_t pos = folio_pos(folio), ofs; - struct iov_iter iter; - struct bio_vec bv; int err = 0; erofs_onlinefolio_init(folio); @@ -122,13 +120,7 @@ static int erofs_fileio_scan_folio(struct erofs_fileio *io, struct folio *folio) err = PTR_ERR(src); break; } - bvec_set_folio(&bv, folio, len, cur); - iov_iter_bvec(&iter, ITER_DEST, &bv, 1, len); - if (copy_to_iter(src, len, &iter) != len) { - erofs_put_metabuf(&buf); - err = -EIO; - break; - } + memcpy_to_folio(folio, cur, src, len); erofs_put_metabuf(&buf); } else if (!(map->m_flags & EROFS_MAP_MAPPED)) { folio_zero_segment(folio, cur, cur + len); @@ -162,7 +154,7 @@ io_retry: } cur += len; } - erofs_onlinefolio_end(folio, err); + erofs_onlinefolio_end(folio, err, false); return err; } diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index a32c03a80c70..06b867d2fc3b 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -315,10 +315,12 @@ static inline struct folio *erofs_grab_folio_nowait(struct address_space *as, /* The length of extent is full */ #define EROFS_MAP_FULL_MAPPED 0x0008 /* Located in the special packed inode */ -#define EROFS_MAP_FRAGMENT 0x0010 +#define __EROFS_MAP_FRAGMENT 0x0010 /* The extent refers to partial decompressed data */ #define EROFS_MAP_PARTIAL_REF 0x0020 +#define EROFS_MAP_FRAGMENT (EROFS_MAP_MAPPED | __EROFS_MAP_FRAGMENT) + struct erofs_map_blocks { struct erofs_buf buf; @@ -390,7 +392,7 @@ int erofs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, int erofs_map_blocks(struct inode *inode, struct erofs_map_blocks *map); void erofs_onlinefolio_init(struct folio *folio); void erofs_onlinefolio_split(struct folio *folio); -void erofs_onlinefolio_end(struct folio *folio, int err); +void erofs_onlinefolio_end(struct folio *folio, int err, bool dirty); struct inode *erofs_iget(struct super_block *sb, erofs_nid_t nid); int erofs_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index fe8071844724..e3f28a1bb945 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -1034,7 +1034,7 @@ static int z_erofs_scan_folio(struct z_erofs_frontend *f, if (!(map->m_flags & EROFS_MAP_MAPPED)) { folio_zero_segment(folio, cur, end); tight = false; - } else if (map->m_flags & EROFS_MAP_FRAGMENT) { + } else if (map->m_flags & __EROFS_MAP_FRAGMENT) { erofs_off_t fpos = offset + cur - map->m_la; err = z_erofs_read_fragment(inode->i_sb, folio, cur, @@ -1091,7 +1091,7 @@ static int z_erofs_scan_folio(struct z_erofs_frontend *f, tight = (bs == PAGE_SIZE); } } while ((end = cur) > 0); - erofs_onlinefolio_end(folio, err); + erofs_onlinefolio_end(folio, err, false); return err; } @@ -1196,7 +1196,7 @@ static void z_erofs_fill_other_copies(struct z_erofs_backend *be, int err) cur += len; } kunmap_local(dst); - erofs_onlinefolio_end(page_folio(bvi->bvec.page), err); + erofs_onlinefolio_end(page_folio(bvi->bvec.page), err, true); list_del(p); kfree(bvi); } @@ -1355,7 +1355,7 @@ static int z_erofs_decompress_pcluster(struct z_erofs_backend *be, int err) DBG_BUGON(z_erofs_page_is_invalidated(page)); if (!z_erofs_is_shortlived_page(page)) { - erofs_onlinefolio_end(page_folio(page), err); + erofs_onlinefolio_end(page_folio(page), err, true); continue; } if (pcl->algorithmformat != Z_EROFS_COMPRESSION_LZ4) { diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c index 0bebc6e3a4d7..f1a15ff22147 100644 --- a/fs/erofs/zmap.c +++ b/fs/erofs/zmap.c @@ -413,8 +413,7 @@ static int z_erofs_map_blocks_fo(struct inode *inode, !vi->z_tailextent_headlcn) { map->m_la = 0; map->m_llen = inode->i_size; - map->m_flags = EROFS_MAP_MAPPED | - EROFS_MAP_FULL_MAPPED | EROFS_MAP_FRAGMENT; + map->m_flags = EROFS_MAP_FRAGMENT; return 0; } initial_lcn = ofs >> lclusterbits; @@ -489,7 +488,7 @@ static int z_erofs_map_blocks_fo(struct inode *inode, goto unmap_out; } } else if (fragment && m.lcn == vi->z_tailextent_headlcn) { - map->m_flags |= EROFS_MAP_FRAGMENT; + map->m_flags = EROFS_MAP_FRAGMENT; } else { map->m_pa = erofs_pos(sb, m.pblk); err = z_erofs_get_extent_compressedlen(&m, initial_lcn); @@ -617,7 +616,7 @@ static int z_erofs_map_blocks_ext(struct inode *inode, if (lstart < lend) { map->m_la = lstart; if (last && (vi->z_advise & Z_EROFS_ADVISE_FRAGMENT_PCLUSTER)) { - map->m_flags |= EROFS_MAP_MAPPED | EROFS_MAP_FRAGMENT; + map->m_flags = EROFS_MAP_FRAGMENT; vi->z_fragmentoff = map->m_plen; if (recsz > offsetof(struct z_erofs_extent, pstart_lo)) vi->z_fragmentoff |= map->m_pa << 32; @@ -797,7 +796,7 @@ static int z_erofs_iomap_begin_report(struct inode *inode, loff_t offset, iomap->length = map.m_llen; if (map.m_flags & EROFS_MAP_MAPPED) { iomap->type = IOMAP_MAPPED; - iomap->addr = map.m_flags & EROFS_MAP_FRAGMENT ? + iomap->addr = map.m_flags & __EROFS_MAP_FRAGMENT ? IOMAP_NULL_ADDR : map.m_pa; } else { iomap->type = IOMAP_HOLE; diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 895256cd2786..0fbf5dfedb24 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -137,7 +137,13 @@ struct epitem { }; /* List header used to link this structure to the eventpoll ready list */ - struct llist_node rdllink; + struct list_head rdllink; + + /* + * Works together "struct eventpoll"->ovflist in keeping the + * single linked chain of items. + */ + struct epitem *next; /* The file descriptor information this item refers to */ struct epoll_filefd ffd; @@ -185,15 +191,22 @@ struct eventpoll { /* Wait queue used by file->poll() */ wait_queue_head_t poll_wait; - /* - * List of ready file descriptors. Adding to this list is lockless. Items can be removed - * only with eventpoll::mtx - */ - struct llist_head rdllist; + /* List of ready file descriptors */ + struct list_head rdllist; + + /* Lock which protects rdllist and ovflist */ + rwlock_t lock; /* RB tree root used to store monitored fd structs */ struct rb_root_cached rbr; + /* + * This is a single linked list that chains all the "struct epitem" that + * happened while transferring ready events to userspace w/out + * holding ->lock. + */ + struct epitem *ovflist; + /* wakeup_source used when ep_send_events or __ep_eventpoll_poll is running */ struct wakeup_source *ws; @@ -348,14 +361,10 @@ static inline int ep_cmp_ffd(struct epoll_filefd *p1, (p1->file < p2->file ? -1 : p1->fd - p2->fd)); } -/* - * Add the item to its container eventpoll's rdllist; do nothing if the item is already on rdllist. - */ -static void epitem_ready(struct epitem *epi) +/* Tells us if the item is currently linked */ +static inline int ep_is_linked(struct epitem *epi) { - if (&epi->rdllink == cmpxchg(&epi->rdllink.next, &epi->rdllink, NULL)) - llist_add(&epi->rdllink, &epi->ep->rdllist); - + return !list_empty(&epi->rdllink); } static inline struct eppoll_entry *ep_pwq_from_wait(wait_queue_entry_t *p) @@ -374,26 +383,13 @@ static inline struct epitem *ep_item_from_wait(wait_queue_entry_t *p) * * @ep: Pointer to the eventpoll context. * - * Return: true if ready events might be available, false otherwise. + * Return: a value different than %zero if ready events are available, + * or %zero otherwise. */ -static inline bool ep_events_available(struct eventpoll *ep) +static inline int ep_events_available(struct eventpoll *ep) { - bool available; - int locked; - - locked = mutex_trylock(&ep->mtx); - if (!locked) { - /* - * The lock held and someone might have removed all items while inspecting it. The - * llist_empty() check in this case is futile. Assume that something is enqueued and - * let ep_try_send_events() figure it out. - */ - return true; - } - - available = !llist_empty(&ep->rdllist); - mutex_unlock(&ep->mtx); - return available; + return !list_empty_careful(&ep->rdllist) || + READ_ONCE(ep->ovflist) != EP_UNACTIVE_PTR; } #ifdef CONFIG_NET_RX_BUSY_POLL @@ -728,6 +724,77 @@ static inline void ep_pm_stay_awake_rcu(struct epitem *epi) rcu_read_unlock(); } + +/* + * ep->mutex needs to be held because we could be hit by + * eventpoll_release_file() and epoll_ctl(). + */ +static void ep_start_scan(struct eventpoll *ep, struct list_head *txlist) +{ + /* + * Steal the ready list, and re-init the original one to the + * empty list. Also, set ep->ovflist to NULL so that events + * happening while looping w/out locks, are not lost. We cannot + * have the poll callback to queue directly on ep->rdllist, + * because we want the "sproc" callback to be able to do it + * in a lockless way. + */ + lockdep_assert_irqs_enabled(); + write_lock_irq(&ep->lock); + list_splice_init(&ep->rdllist, txlist); + WRITE_ONCE(ep->ovflist, NULL); + write_unlock_irq(&ep->lock); +} + +static void ep_done_scan(struct eventpoll *ep, + struct list_head *txlist) +{ + struct epitem *epi, *nepi; + + write_lock_irq(&ep->lock); + /* + * During the time we spent inside the "sproc" callback, some + * other events might have been queued by the poll callback. + * We re-insert them inside the main ready-list here. + */ + for (nepi = READ_ONCE(ep->ovflist); (epi = nepi) != NULL; + nepi = epi->next, epi->next = EP_UNACTIVE_PTR) { + /* + * We need to check if the item is already in the list. + * During the "sproc" callback execution time, items are + * queued into ->ovflist but the "txlist" might already + * contain them, and the list_splice() below takes care of them. + */ + if (!ep_is_linked(epi)) { + /* + * ->ovflist is LIFO, so we have to reverse it in order + * to keep in FIFO. + */ + list_add(&epi->rdllink, &ep->rdllist); + ep_pm_stay_awake(epi); + } + } + /* + * We need to set back ep->ovflist to EP_UNACTIVE_PTR, so that after + * releasing the lock, events will be queued in the normal way inside + * ep->rdllist. + */ + WRITE_ONCE(ep->ovflist, EP_UNACTIVE_PTR); + + /* + * Quickly re-inject items left on "txlist". + */ + list_splice(txlist, &ep->rdllist); + __pm_relax(ep->ws); + + if (!list_empty(&ep->rdllist)) { + if (waitqueue_active(&ep->wq)) + wake_up(&ep->wq); + } + + write_unlock_irq(&ep->lock); +} + static void ep_get(struct eventpoll *ep) { refcount_inc(&ep->refcount); @@ -765,12 +832,10 @@ static void ep_free(struct eventpoll *ep) static bool __ep_remove(struct eventpoll *ep, struct epitem *epi, bool force) { struct file *file = epi->ffd.file; - struct llist_node *put_back_last; struct epitems_head *to_free; struct hlist_head *head; - LLIST_HEAD(put_back); - lockdep_assert_held(&ep->mtx); + lockdep_assert_irqs_enabled(); /* * Removes poll wait queue hooks. @@ -802,20 +867,10 @@ static bool __ep_remove(struct eventpoll *ep, struct epitem *epi, bool force) rb_erase_cached(&epi->rbn, &ep->rbr); - if (llist_on_list(&epi->rdllink)) { - put_back_last = NULL; - while (true) { - struct llist_node *n = llist_del_first(&ep->rdllist); - - if (&epi->rdllink == n || WARN_ON(!n)) - break; - if (!put_back_last) - put_back_last = n; - __llist_add(n, &put_back); - } - if (put_back_last) - llist_add_batch(put_back.first, put_back_last, &ep->rdllist); - } + write_lock_irq(&ep->lock); + if (ep_is_linked(epi)) + list_del_init(&epi->rdllink); + write_unlock_irq(&ep->lock); wakeup_source_unregister(ep_wakeup_source(epi)); /* @@ -917,9 +972,8 @@ static __poll_t ep_item_poll(const struct epitem *epi, poll_table *pt, int depth static __poll_t __ep_eventpoll_poll(struct file *file, poll_table *wait, int depth) { struct eventpoll *ep = file->private_data; - struct wakeup_source *ws; - struct llist_node *n; - struct epitem *epi; + LIST_HEAD(txlist); + struct epitem *epi, *tmp; poll_table pt; __poll_t res = 0; @@ -933,39 +987,22 @@ static __poll_t __ep_eventpoll_poll(struct file *file, poll_table *wait, int dep * the ready list. */ mutex_lock_nested(&ep->mtx, depth); - while (true) { - n = llist_del_first_init(&ep->rdllist); - if (!n) - break; - - epi = llist_entry(n, struct epitem, rdllink); - + ep_start_scan(ep, &txlist); + list_for_each_entry_safe(epi, tmp, &txlist, rdllink) { if (ep_item_poll(epi, &pt, depth + 1)) { res = EPOLLIN | EPOLLRDNORM; - epitem_ready(epi); break; } else { /* - * We need to activate ep before deactivating epi, to prevent autosuspend - * just in case epi becomes active after ep_item_poll() above. - * - * This is similar to ep_send_events(). + * Item has been dropped into the ready list by the poll + * callback, but it's not actually ready, as far as + * caller requested events goes. We can remove it here. */ - ws = ep_wakeup_source(epi); - if (ws) { - if (ws->active) - __pm_stay_awake(ep->ws); - __pm_relax(ws); - } __pm_relax(ep_wakeup_source(epi)); - - /* Just in case epi becomes active right before __pm_relax() */ - if (unlikely(ep_item_poll(epi, &pt, depth + 1))) - ep_pm_stay_awake(epi); - - __pm_relax(ep->ws); + list_del_init(&epi->rdllink); } } + ep_done_scan(ep, &txlist); mutex_unlock(&ep->mtx); return res; } @@ -1114,10 +1151,12 @@ static int ep_alloc(struct eventpoll **pep) return -ENOMEM; mutex_init(&ep->mtx); + rwlock_init(&ep->lock); init_waitqueue_head(&ep->wq); init_waitqueue_head(&ep->poll_wait); - init_llist_head(&ep->rdllist); + INIT_LIST_HEAD(&ep->rdllist); ep->rbr = RB_ROOT_CACHED; + ep->ovflist = EP_UNACTIVE_PTR; ep->user = get_current_user(); refcount_set(&ep->refcount, 1); @@ -1200,10 +1239,93 @@ struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, #endif /* CONFIG_KCMP */ /* + * Adds a new entry to the tail of the list in a lockless way, i.e. + * multiple CPUs are allowed to call this function concurrently. + * + * Beware: it is necessary to prevent any other modifications of the + * existing list until all changes are completed, in other words + * concurrent list_add_tail_lockless() calls should be protected + * with a read lock, where write lock acts as a barrier which + * makes sure all list_add_tail_lockless() calls are fully + * completed. + * + * Also an element can be locklessly added to the list only in one + * direction i.e. either to the tail or to the head, otherwise + * concurrent access will corrupt the list. + * + * Return: %false if element has been already added to the list, %true + * otherwise. + */ +static inline bool list_add_tail_lockless(struct list_head *new, + struct list_head *head) +{ + struct list_head *prev; + + /* + * This is simple 'new->next = head' operation, but cmpxchg() + * is used in order to detect that same element has been just + * added to the list from another CPU: the winner observes + * new->next == new. + */ + if (!try_cmpxchg(&new->next, &new, head)) + return false; + + /* + * Initially ->next of a new element must be updated with the head + * (we are inserting to the tail) and only then pointers are atomically + * exchanged. XCHG guarantees memory ordering, thus ->next should be + * updated before pointers are actually swapped and pointers are + * swapped before prev->next is updated. + */ + + prev = xchg(&head->prev, new); + + /* + * It is safe to modify prev->next and new->prev, because a new element + * is added only to the tail and new->next is updated before XCHG. + */ + + prev->next = new; + new->prev = prev; + + return true; +} + +/* + * Chains a new epi entry to the tail of the ep->ovflist in a lockless way, + * i.e. multiple CPUs are allowed to call this function concurrently. + * + * Return: %false if epi element has been already chained, %true otherwise. + */ +static inline bool chain_epi_lockless(struct epitem *epi) +{ + struct eventpoll *ep = epi->ep; + + /* Fast preliminary check */ + if (epi->next != EP_UNACTIVE_PTR) + return false; + + /* Check that the same epi has not been just chained from another CPU */ + if (cmpxchg(&epi->next, EP_UNACTIVE_PTR, NULL) != EP_UNACTIVE_PTR) + return false; + + /* Atomically exchange tail */ + epi->next = xchg(&ep->ovflist, epi); + + return true; +} + +/* * This is the callback that is passed to the wait queue wakeup * mechanism. It is called by the stored file descriptors when they * have events to report. * + * This callback takes a read lock in order not to contend with concurrent + * events from another file descriptor, thus all modifications to ->rdllist + * or ->ovflist are lockless. Read lock is paired with the write lock from + * ep_start/done_scan(), which stops all list modifications and guarantees + * that lists state is seen correctly. + * * Another thing worth to mention is that ep_poll_callback() can be called * concurrently for the same @epi from different CPUs if poll table was inited * with several wait queues entries. Plural wakeup from different CPUs of a @@ -1213,11 +1335,15 @@ struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, */ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { + int pwake = 0; struct epitem *epi = ep_item_from_wait(wait); struct eventpoll *ep = epi->ep; __poll_t pollflags = key_to_poll(key); + unsigned long flags; int ewake = 0; + read_lock_irqsave(&ep->lock, flags); + ep_set_busy_poll_napi_id(epi); /* @@ -1227,7 +1353,7 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v * until the next EPOLL_CTL_MOD will be issued. */ if (!(epi->event.events & ~EP_PRIVATE_BITS)) - goto out; + goto out_unlock; /* * Check the events coming with the callback. At this stage, not @@ -1236,10 +1362,22 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v * test for "key" != NULL before the event match test. */ if (pollflags && !(pollflags & epi->event.events)) - goto out; + goto out_unlock; - ep_pm_stay_awake_rcu(epi); - epitem_ready(epi); + /* + * If we are transferring events to userspace, we can hold no locks + * (because we're accessing user memory, and because of linux f_op->poll() + * semantics). All the events that happen during that period of time are + * chained in ep->ovflist and requeued later on. + */ + if (READ_ONCE(ep->ovflist) != EP_UNACTIVE_PTR) { + if (chain_epi_lockless(epi)) + ep_pm_stay_awake_rcu(epi); + } else if (!ep_is_linked(epi)) { + /* In the usual case, add event to ready list. */ + if (list_add_tail_lockless(&epi->rdllink, &ep->rdllist)) + ep_pm_stay_awake_rcu(epi); + } /* * Wake up ( if active ) both the eventpoll wait list and the ->poll() @@ -1268,9 +1406,15 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v wake_up(&ep->wq); } if (waitqueue_active(&ep->poll_wait)) + pwake++; + +out_unlock: + read_unlock_irqrestore(&ep->lock, flags); + + /* We have to call this outside the lock */ + if (pwake) ep_poll_safewake(ep, epi, pollflags & EPOLL_URING_WAKE); -out: if (!(epi->event.events & EPOLLEXCLUSIVE)) ewake = 1; @@ -1515,6 +1659,8 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, if (is_file_epoll(tfile)) tep = tfile->private_data; + lockdep_assert_irqs_enabled(); + if (unlikely(percpu_counter_compare(&ep->user->epoll_watches, max_user_watches) >= 0)) return -ENOSPC; @@ -1526,10 +1672,11 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, } /* Item initialization follow here ... */ - init_llist_node(&epi->rdllink); + INIT_LIST_HEAD(&epi->rdllink); epi->ep = ep; ep_set_ffd(&epi->ffd, tfile, fd); epi->event = *event; + epi->next = EP_UNACTIVE_PTR; if (tep) mutex_lock_nested(&tep->mtx, 1); @@ -1596,13 +1743,16 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, return -ENOMEM; } + /* We have to drop the new item inside our item list to keep track of it */ + write_lock_irq(&ep->lock); + /* record NAPI ID of new item if present */ ep_set_busy_poll_napi_id(epi); /* If the file is already "ready" we drop it inside the ready list */ - if (revents) { + if (revents && !ep_is_linked(epi)) { + list_add_tail(&epi->rdllink, &ep->rdllist); ep_pm_stay_awake(epi); - epitem_ready(epi); /* Notify waiting tasks that events are available */ if (waitqueue_active(&ep->wq)) @@ -1611,6 +1761,8 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, pwake++; } + write_unlock_irq(&ep->lock); + /* We have to call this outside the lock */ if (pwake) ep_poll_safewake(ep, NULL, 0); @@ -1625,8 +1777,11 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, static int ep_modify(struct eventpoll *ep, struct epitem *epi, const struct epoll_event *event) { + int pwake = 0; poll_table pt; + lockdep_assert_irqs_enabled(); + init_poll_funcptr(&pt, NULL); /* @@ -1670,16 +1825,24 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi, * list, push it inside. */ if (ep_item_poll(epi, &pt, 1)) { - ep_pm_stay_awake(epi); - epitem_ready(epi); + write_lock_irq(&ep->lock); + if (!ep_is_linked(epi)) { + list_add_tail(&epi->rdllink, &ep->rdllist); + ep_pm_stay_awake(epi); - /* Notify waiting tasks that events are available */ - if (waitqueue_active(&ep->wq)) - wake_up(&ep->wq); - if (waitqueue_active(&ep->poll_wait)) - ep_poll_safewake(ep, NULL, 0); + /* Notify waiting tasks that events are available */ + if (waitqueue_active(&ep->wq)) + wake_up(&ep->wq); + if (waitqueue_active(&ep->poll_wait)) + pwake++; + } + write_unlock_irq(&ep->lock); } + /* We have to call this outside the lock */ + if (pwake) + ep_poll_safewake(ep, NULL, 0); + return 0; } @@ -1687,7 +1850,7 @@ static int ep_send_events(struct eventpoll *ep, struct epoll_event __user *events, int maxevents) { struct epitem *epi, *tmp; - LLIST_HEAD(txlist); + LIST_HEAD(txlist); poll_table pt; int res = 0; @@ -1702,18 +1865,19 @@ static int ep_send_events(struct eventpoll *ep, init_poll_funcptr(&pt, NULL); mutex_lock(&ep->mtx); + ep_start_scan(ep, &txlist); - while (res < maxevents) { + /* + * We can loop without lock because we are passed a task private list. + * Items cannot vanish during the loop we are holding ep->mtx. + */ + list_for_each_entry_safe(epi, tmp, &txlist, rdllink) { struct wakeup_source *ws; - struct llist_node *n; __poll_t revents; - n = llist_del_first(&ep->rdllist); - if (!n) + if (res >= maxevents) break; - epi = llist_entry(n, struct epitem, rdllink); - /* * Activate ep->ws before deactivating epi->ws to prevent * triggering auto-suspend here (in case we reactive epi->ws @@ -1730,30 +1894,21 @@ static int ep_send_events(struct eventpoll *ep, __pm_relax(ws); } + list_del_init(&epi->rdllink); + /* * If the event mask intersect the caller-requested one, * deliver the event to userspace. Again, we are holding ep->mtx, * so no operations coming from userspace can change the item. */ revents = ep_item_poll(epi, &pt, 1); - if (!revents) { - init_llist_node(n); - - /* - * Just in case epi becomes ready after ep_item_poll() above, but before - * init_llist_node(). Make sure to add it to the ready list, otherwise an - * event may be lost. - */ - if (unlikely(ep_item_poll(epi, &pt, 1))) { - ep_pm_stay_awake(epi); - epitem_ready(epi); - } + if (!revents) continue; - } events = epoll_put_uevent(revents, epi->event.data, events); if (!events) { - llist_add(&epi->rdllink, &ep->rdllist); + list_add(&epi->rdllink, &txlist); + ep_pm_stay_awake(epi); if (!res) res = -EFAULT; break; @@ -1761,31 +1916,25 @@ static int ep_send_events(struct eventpoll *ep, res++; if (epi->event.events & EPOLLONESHOT) epi->event.events &= EP_PRIVATE_BITS; - __llist_add(n, &txlist); - } - - llist_for_each_entry_safe(epi, tmp, txlist.first, rdllink) { - init_llist_node(&epi->rdllink); - - if (!(epi->event.events & EPOLLET)) { + else if (!(epi->event.events & EPOLLET)) { /* - * If this file has been added with Level Trigger mode, we need to insert - * back inside the ready list, so that the next call to epoll_wait() will - * check again the events availability. + * If this file has been added with Level + * Trigger mode, we need to insert back inside + * the ready list, so that the next call to + * epoll_wait() will check again the events + * availability. At this point, no one can insert + * into ep->rdllist besides us. The epoll_ctl() + * callers are locked out by + * ep_send_events() holding "mtx" and the + * poll callback will queue them in ep->ovflist. */ + list_add_tail(&epi->rdllink, &ep->rdllist); ep_pm_stay_awake(epi); - epitem_ready(epi); } } - - __pm_relax(ep->ws); + ep_done_scan(ep, &txlist); mutex_unlock(&ep->mtx); - if (!llist_empty(&ep->rdllist)) { - if (waitqueue_active(&ep->wq)) - wake_up(&ep->wq); - } - return res; } @@ -1878,6 +2027,8 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, wait_queue_entry_t wait; ktime_t expires, *to = NULL; + lockdep_assert_irqs_enabled(); + if (timeout && (timeout->tv_sec | timeout->tv_nsec)) { slack = select_estimate_accuracy(timeout); to = &expires; @@ -1937,15 +2088,54 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, init_wait(&wait); wait.func = ep_autoremove_wake_function; - prepare_to_wait_exclusive(&ep->wq, &wait, TASK_INTERRUPTIBLE); + write_lock_irq(&ep->lock); + /* + * Barrierless variant, waitqueue_active() is called under + * the same lock on wakeup ep_poll_callback() side, so it + * is safe to avoid an explicit barrier. + */ + __set_current_state(TASK_INTERRUPTIBLE); - if (!ep_events_available(ep)) + /* + * Do the final check under the lock. ep_start/done_scan() + * plays with two lists (->rdllist and ->ovflist) and there + * is always a race when both lists are empty for short + * period of time although events are pending, so lock is + * important. + */ + eavail = ep_events_available(ep); + if (!eavail) + __add_wait_queue_exclusive(&ep->wq, &wait); + + write_unlock_irq(&ep->lock); + + if (!eavail) timed_out = !ep_schedule_timeout(to) || !schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS); + __set_current_state(TASK_RUNNING); - finish_wait(&ep->wq, &wait); - eavail = ep_events_available(ep); + /* + * We were woken up, thus go and try to harvest some events. + * If timed out and still on the wait queue, recheck eavail + * carefully under lock, below. + */ + eavail = 1; + + if (!list_empty_careful(&wait.entry)) { + write_lock_irq(&ep->lock); + /* + * If the thread timed out and is not on the wait queue, + * it means that the thread was woken up after its + * timeout expired before it could reacquire the lock. + * Thus, when wait.entry is empty, it needs to harvest + * events. + */ + if (timed_out) + eavail = list_empty(&wait.entry); + __remove_wait_queue(&ep->wq, &wait); + write_unlock_irq(&ep->lock); + } } } diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 4be91eb6ea5c..751479eb128f 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -36,9 +36,9 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) unsigned long text, lib, swap, anon, file, shmem; unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss; - anon = get_mm_counter(mm, MM_ANONPAGES); - file = get_mm_counter(mm, MM_FILEPAGES); - shmem = get_mm_counter(mm, MM_SHMEMPAGES); + anon = get_mm_counter_sum(mm, MM_ANONPAGES); + file = get_mm_counter_sum(mm, MM_FILEPAGES); + shmem = get_mm_counter_sum(mm, MM_SHMEMPAGES); /* * Note: to minimize their overhead, mm maintains hiwater_vm and @@ -59,7 +59,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) text = min(text, mm->exec_vm << PAGE_SHIFT); lib = (mm->exec_vm << PAGE_SHIFT) - text; - swap = get_mm_counter(mm, MM_SWAPENTS); + swap = get_mm_counter_sum(mm, MM_SWAPENTS); SEQ_PUT_DEC("VmPeak:\t", hiwater_vm); SEQ_PUT_DEC(" kB\nVmSize:\t", total_vm); SEQ_PUT_DEC(" kB\nVmLck:\t", mm->locked_vm); @@ -92,12 +92,12 @@ unsigned long task_statm(struct mm_struct *mm, unsigned long *shared, unsigned long *text, unsigned long *data, unsigned long *resident) { - *shared = get_mm_counter(mm, MM_FILEPAGES) + - get_mm_counter(mm, MM_SHMEMPAGES); + *shared = get_mm_counter_sum(mm, MM_FILEPAGES) + + get_mm_counter_sum(mm, MM_SHMEMPAGES); *text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> PAGE_SHIFT; *data = mm->data_vm + mm->stack_vm; - *resident = *shared + get_mm_counter(mm, MM_ANONPAGES); + *resident = *shared + get_mm_counter_sum(mm, MM_ANONPAGES); return mm->total_vm; } diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index fafa86273f12..63d17cea2e95 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -8573,11 +8573,6 @@ static void smb20_oplock_break_ack(struct ksmbd_work *work) goto err_out; } - opinfo->op_state = OPLOCK_STATE_NONE; - wake_up_interruptible_all(&opinfo->oplock_q); - opinfo_put(opinfo); - ksmbd_fd_put(work, fp); - rsp->StructureSize = cpu_to_le16(24); rsp->OplockLevel = rsp_oplevel; rsp->Reserved = 0; @@ -8585,16 +8580,15 @@ static void smb20_oplock_break_ack(struct ksmbd_work *work) rsp->VolatileFid = volatile_id; rsp->PersistentFid = persistent_id; ret = ksmbd_iov_pin_rsp(work, rsp, sizeof(struct smb2_oplock_break)); - if (!ret) - return; - + if (ret) { err_out: + smb2_set_err_rsp(work); + } + opinfo->op_state = OPLOCK_STATE_NONE; wake_up_interruptible_all(&opinfo->oplock_q); - opinfo_put(opinfo); ksmbd_fd_put(work, fp); - smb2_set_err_rsp(work); } static int check_lease_state(struct lease *lease, __le32 req_state) @@ -8724,11 +8718,6 @@ static void smb21_lease_break_ack(struct ksmbd_work *work) } lease_state = lease->state; - 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); - opinfo_put(opinfo); rsp->StructureSize = cpu_to_le16(36); rsp->Reserved = 0; @@ -8737,16 +8726,16 @@ static void smb21_lease_break_ack(struct ksmbd_work *work) rsp->LeaseState = lease_state; rsp->LeaseDuration = 0; ret = ksmbd_iov_pin_rsp(work, rsp, sizeof(struct smb2_lease_ack)); - if (!ret) - return; - + if (ret) { err_out: + smb2_set_err_rsp(work); + } + + 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); - opinfo_put(opinfo); - smb2_set_err_rsp(work); } /** diff --git a/fs/smb/server/transport_rdma.c b/fs/smb/server/transport_rdma.c index 64a428a06ace..c6cbe0d56e32 100644 --- a/fs/smb/server/transport_rdma.c +++ b/fs/smb/server/transport_rdma.c @@ -433,7 +433,8 @@ static void free_transport(struct smb_direct_transport *t) if (t->qp) { ib_drain_qp(t->qp); ib_mr_pool_destroy(t->qp, &t->qp->rdma_mrs); - ib_destroy_qp(t->qp); + t->qp = NULL; + rdma_destroy_qp(t->cm_id); } ksmbd_debug(RDMA, "drain the reassembly queue\n"); @@ -1940,8 +1941,8 @@ static int smb_direct_create_qpair(struct smb_direct_transport *t, return 0; err: if (t->qp) { - ib_destroy_qp(t->qp); t->qp = NULL; + rdma_destroy_qp(t->cm_id); } if (t->recv_cq) { ib_destroy_cq(t->recv_cq); diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c index 0f3aad12e495..d3437f6644e3 100644 --- a/fs/smb/server/vfs.c +++ b/fs/smb/server/vfs.c @@ -1282,6 +1282,7 @@ out1: err = ksmbd_vfs_lock_parent(parent_path->dentry, path->dentry); if (err) { + mnt_drop_write(parent_path->mnt); path_put(path); path_put(parent_path); } diff --git a/include/drm/drm_file.h b/include/drm/drm_file.h index 5c3b2aa3e69d..d344d41e6cfe 100644 --- a/include/drm/drm_file.h +++ b/include/drm/drm_file.h @@ -300,6 +300,9 @@ struct drm_file { * * Mapping of mm object handles to object pointers. Used by the GEM * subsystem. Protected by @table_lock. + * + * Note that allocated entries might be NULL as a transient state when + * creating or deleting a handle. */ struct idr object_idr; diff --git a/include/drm/drm_framebuffer.h b/include/drm/drm_framebuffer.h index 668077009fce..38b24fc8978d 100644 --- a/include/drm/drm_framebuffer.h +++ b/include/drm/drm_framebuffer.h @@ -23,6 +23,7 @@ #ifndef __DRM_FRAMEBUFFER_H__ #define __DRM_FRAMEBUFFER_H__ +#include <linux/bits.h> #include <linux/ctype.h> #include <linux/list.h> #include <linux/sched.h> @@ -100,6 +101,8 @@ struct drm_framebuffer_funcs { unsigned num_clips); }; +#define DRM_FRAMEBUFFER_HAS_HANDLE_REF(_i) BIT(0u + (_i)) + /** * struct drm_framebuffer - frame buffer object * @@ -189,6 +192,10 @@ struct drm_framebuffer { */ int flags; /** + * @internal_flags: Framebuffer flags like DRM_FRAMEBUFFER_HAS_HANDLE_REF. + */ + unsigned int internal_flags; + /** * @filp_head: Placed on &drm_file.fbs, protected by &drm_file.fbs_lock. */ struct list_head filp_head; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index a59880c809c7..181a0deadc9e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -269,11 +269,16 @@ static inline dev_t disk_devt(struct gendisk *disk) return MKDEV(disk->major, disk->first_minor); } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * We should strive for 1 << (PAGE_SHIFT + MAX_PAGECACHE_ORDER) * however we constrain this to what we can validate and test. */ #define BLK_MAX_BLOCK_SIZE SZ_64K +#else +#define BLK_MAX_BLOCK_SIZE PAGE_SIZE +#endif + /* blk_validate_limits() validates bsize, so drivers don't usually need to */ static inline int blk_validate_block_size(unsigned long bsize) diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 2922635986f5..a7efcec2e3d0 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -698,6 +698,8 @@ struct io_kiocb { struct hlist_node hash_node; /* For IOPOLL setup queues, with hybrid polling */ u64 iopoll_start; + /* for private io_kiocb freeing */ + struct rcu_head rcu_head; }; /* internal polling, see IORING_FEAT_FAST_POLL */ struct async_poll *apoll; diff --git a/include/linux/irqchip/irq-msi-lib.h b/include/linux/irqchip/irq-msi-lib.h index dd8d1d138544..224ac28e88d7 100644 --- a/include/linux/irqchip/irq-msi-lib.h +++ b/include/linux/irqchip/irq-msi-lib.h @@ -17,6 +17,7 @@ #define MATCH_PLATFORM_MSI BIT(DOMAIN_BUS_PLATFORM_MSI) +struct msi_domain_info; int msi_lib_irq_domain_select(struct irq_domain *d, struct irq_fwspec *fwspec, enum irq_domain_bus_token bus_token); diff --git a/include/linux/mm.h b/include/linux/mm.h index 0ef2ba0c667a..fa538feaa8d9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2568,6 +2568,11 @@ static inline unsigned long get_mm_counter(struct mm_struct *mm, int member) return percpu_counter_read_positive(&mm->rss_stat[member]); } +static inline unsigned long get_mm_counter_sum(struct mm_struct *mm, int member) +{ + return percpu_counter_sum_positive(&mm->rss_stat[member]); +} + void mm_trace_rss_stat(struct mm_struct *mm, int member); static inline void add_mm_counter(struct mm_struct *mm, int member, long value) diff --git a/include/linux/sched.h b/include/linux/sched.h index 4f78a64beb52..aa9c5be7a632 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -548,10 +548,6 @@ struct sched_statistics { u64 nr_failed_migrations_running; u64 nr_failed_migrations_hot; u64 nr_forced_migrations; -#ifdef CONFIG_NUMA_BALANCING - u64 numa_task_migrated; - u64 numa_task_swapped; -#endif u64 nr_wakeups; u64 nr_wakeups_sync; diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 91a3ce9a2687..9e15a088ba38 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -66,8 +66,6 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, NUMA_HINT_FAULTS, NUMA_HINT_FAULTS_LOCAL, NUMA_PAGE_MIGRATE, - NUMA_TASK_MIGRATE, - NUMA_TASK_SWAP, #endif #ifdef CONFIG_MIGRATION PGMIGRATE_SUCCESS, PGMIGRATE_FAIL, diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 73648d26a622..5111ec040c53 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -1666,12 +1666,11 @@ static void io_iopoll_req_issued(struct io_kiocb *req, unsigned int issue_flags) io_req_flags_t io_file_get_flags(struct file *file) { - struct inode *inode = file_inode(file); io_req_flags_t res = 0; BUILD_BUG_ON(REQ_F_ISREG_BIT != REQ_F_SUPPORT_NOWAIT_BIT + 1); - if (S_ISREG(inode->i_mode) && !(inode->i_flags & S_ANON_INODE)) + if (S_ISREG(file_inode(file)->i_mode)) res |= REQ_F_ISREG; if ((file->f_flags & O_NONBLOCK) || (file->f_mode & FMODE_NOWAIT)) res |= REQ_F_SUPPORT_NOWAIT; diff --git a/io_uring/msg_ring.c b/io_uring/msg_ring.c index 71400d6cefc8..4c2578f2efcb 100644 --- a/io_uring/msg_ring.c +++ b/io_uring/msg_ring.c @@ -82,7 +82,7 @@ static void io_msg_tw_complete(struct io_kiocb *req, io_tw_token_t tw) spin_unlock(&ctx->msg_lock); } if (req) - kmem_cache_free(req_cachep, req); + kfree_rcu(req, rcu_head); percpu_ref_put(&ctx->refs); } @@ -90,7 +90,7 @@ static int io_msg_remote_post(struct io_ring_ctx *ctx, struct io_kiocb *req, int res, u32 cflags, u64 user_data) { if (!READ_ONCE(ctx->submitter_task)) { - kmem_cache_free(req_cachep, req); + kfree_rcu(req, rcu_head); return -EOWNERDEAD; } req->opcode = IORING_OP_NOP; diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c index 085eeed8cd50..00d0064b22a5 100644 --- a/io_uring/zcrx.c +++ b/io_uring/zcrx.c @@ -863,10 +863,7 @@ static int io_pp_zc_init(struct page_pool *pp) static void io_pp_zc_destroy(struct page_pool *pp) { struct io_zcrx_ifq *ifq = io_pp_to_ifq(pp); - struct io_zcrx_area *area = ifq->area; - if (WARN_ON_ONCE(area->free_count != area->nia.num_niovs)) - return; percpu_ref_put(&ifq->ctx->refs); } diff --git a/kernel/events/core.c b/kernel/events/core.c index 0db36b2b2448..22fdf0c187cd 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -7204,18 +7204,18 @@ void perf_event_wakeup(struct perf_event *event) static void perf_sigtrap(struct perf_event *event) { /* - * We'd expect this to only occur if the irq_work is delayed and either - * ctx->task or current has changed in the meantime. This can be the - * case on architectures that do not implement arch_irq_work_raise(). + * Both perf_pending_task() and perf_pending_irq() can race with the + * task exiting. */ - if (WARN_ON_ONCE(event->ctx->task != current)) + if (current->flags & PF_EXITING) return; /* - * Both perf_pending_task() and perf_pending_irq() can race with the - * task exiting. + * We'd expect this to only occur if the irq_work is delayed and either + * ctx->task or current has changed in the meantime. This can be the + * case on architectures that do not implement arch_irq_work_raise(). */ - if (current->flags & PF_EXITING) + if (WARN_ON_ONCE(event->ctx->task != current)) return; send_sig_perf((void __user *)event->pending_addr, diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index bb608b68fb30..b4ca17c2fecf 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -384,6 +384,7 @@ static int suspend_prepare(suspend_state_t state) return 0; dpm_save_failed_step(SUSPEND_FREEZE); + filesystems_thaw(); pm_notifier_call_chain(PM_POST_SUSPEND); Restore: pm_restore_console(); @@ -540,7 +541,6 @@ int suspend_devices_and_enter(suspend_state_t state) return error; Recover_platform: - pm_restore_gfp_mask(); platform_recover(state); goto Resume_devices; } @@ -593,8 +593,6 @@ static int enter_state(suspend_state_t state) ksys_sync_helper(); trace_suspend_resume(TPS("sync_filesystems"), 0, false); } - if (filesystem_freeze_enabled) - filesystems_freeze(); pm_pr_dbg("Preparing system for sleep (%s)\n", mem_sleep_labels[state]); pm_suspend_clear_flags(); @@ -614,7 +612,6 @@ static int enter_state(suspend_state_t state) pm_pr_dbg("Finishing wakeup.\n"); suspend_finish(); Unlock: - filesystems_thaw(); mutex_unlock(&system_transition_mutex); return error; } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index ec68fc686bd7..81c6df746df1 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3362,10 +3362,6 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) #ifdef CONFIG_NUMA_BALANCING static void __migrate_swap_task(struct task_struct *p, int cpu) { - __schedstat_inc(p->stats.numa_task_swapped); - count_vm_numa_event(NUMA_TASK_SWAP); - count_memcg_event_mm(p->mm, NUMA_TASK_SWAP); - if (task_on_rq_queued(p)) { struct rq *src_rq, *dst_rq; struct rq_flags srf, drf; @@ -7939,9 +7935,8 @@ int migrate_task_to(struct task_struct *p, int target_cpu) if (!cpumask_test_cpu(target_cpu, p->cpus_ptr)) return -EINVAL; - __schedstat_inc(p->stats.numa_task_migrated); - count_vm_numa_event(NUMA_TASK_MIGRATE); - count_memcg_event_mm(p->mm, NUMA_TASK_MIGRATE); + /* TODO: This is not properly updating schedstats */ + trace_sched_move_numa(p, curr_cpu, target_cpu); return stop_one_cpu(curr_cpu, migration_cpu_stop, &arg); } diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 9d71baf08075..557246880a7e 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -1210,10 +1210,6 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns, P_SCHEDSTAT(nr_failed_migrations_running); P_SCHEDSTAT(nr_failed_migrations_hot); P_SCHEDSTAT(nr_forced_migrations); -#ifdef CONFIG_NUMA_BALANCING - P_SCHEDSTAT(numa_task_migrated); - P_SCHEDSTAT(numa_task_swapped); -#endif P_SCHEDSTAT(nr_wakeups); P_SCHEDSTAT(nr_wakeups_sync); P_SCHEDSTAT(nr_wakeups_migrate); diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 424751cdf31f..40830a3ecd96 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -657,7 +657,7 @@ static int parse_btf_arg(char *varname, ret = query_btf_context(ctx); if (ret < 0 || ctx->nr_params == 0) { trace_probe_log_err(ctx->offset, NO_BTF_ENTRY); - return PTR_ERR(params); + return -ENOENT; } } params = ctx->params; diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c index 3a74d63a959e..0142bc916f73 100644 --- a/lib/alloc_tag.c +++ b/lib/alloc_tag.c @@ -135,6 +135,9 @@ size_t alloc_tag_top_users(struct codetag_bytes *tags, size_t count, bool can_sl struct codetag_bytes n; unsigned int i, nr = 0; + if (IS_ERR_OR_NULL(alloc_tag_cttype)) + return 0; + if (can_sleep) codetag_lock_module_list(alloc_tag_cttype, true); else if (!codetag_trylock_module_list(alloc_tag_cttype)) diff --git a/lib/maple_tree.c b/lib/maple_tree.c index 00524e55a21e..ef66be963798 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -5319,6 +5319,7 @@ static void mt_destroy_walk(struct maple_enode *enode, struct maple_tree *mt, struct maple_enode *start; if (mte_is_leaf(enode)) { + mte_set_node_dead(enode); node->type = mte_node_type(enode); goto free_leaf; } diff --git a/mm/damon/core.c b/mm/damon/core.c index b217e0120e09..979b29e16ef4 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -1449,6 +1449,7 @@ static unsigned long damon_get_intervals_score(struct damon_ctx *c) } } target_access_events = max_access_events * goal_bp / 10000; + target_access_events = target_access_events ? : 1; return access_events * 10000 / target_access_events; } @@ -2355,9 +2356,8 @@ static void kdamond_usleep(unsigned long usecs) * * If there is a &struct damon_call_control request that registered via * &damon_call() on @ctx, do or cancel the invocation of the function depending - * on @cancel. @cancel is set when the kdamond is deactivated by DAMOS - * watermarks, or the kdamond is already out of the main loop and therefore - * will be terminated. + * on @cancel. @cancel is set when the kdamond is already out of the main loop + * and therefore will be terminated. */ static void kdamond_call(struct damon_ctx *ctx, bool cancel) { @@ -2405,7 +2405,7 @@ static int kdamond_wait_activation(struct damon_ctx *ctx) if (ctx->callback.after_wmarks_check && ctx->callback.after_wmarks_check(ctx)) break; - kdamond_call(ctx, true); + kdamond_call(ctx, false); damos_walk_cancel(ctx); } return -EBUSY; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 9dc95eac558c..a0d285d20992 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2340,12 +2340,15 @@ struct folio *alloc_hugetlb_folio_reserve(struct hstate *h, int preferred_nid, struct folio *folio; spin_lock_irq(&hugetlb_lock); + if (!h->resv_huge_pages) { + spin_unlock_irq(&hugetlb_lock); + return NULL; + } + folio = dequeue_hugetlb_folio_nodemask(h, gfp_mask, preferred_nid, nmask); - if (folio) { - VM_BUG_ON(!h->resv_huge_pages); + if (folio) h->resv_huge_pages--; - } spin_unlock_irq(&hugetlb_lock); return folio; diff --git a/mm/kasan/report.c b/mm/kasan/report.c index 8357e1a33699..b0877035491f 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -370,36 +370,6 @@ static inline bool init_task_stack_addr(const void *addr) sizeof(init_thread_union.stack)); } -/* - * This function is invoked with report_lock (a raw_spinlock) held. A - * PREEMPT_RT kernel cannot call find_vm_area() as it will acquire a sleeping - * rt_spinlock. - * - * For !RT kernel, the PROVE_RAW_LOCK_NESTING config option will print a - * lockdep warning for this raw_spinlock -> spinlock dependency. This config - * option is enabled by default to ensure better test coverage to expose this - * kind of RT kernel problem. This lockdep splat, however, can be suppressed - * by using DEFINE_WAIT_OVERRIDE_MAP() if it serves a useful purpose and the - * invalid PREEMPT_RT case has been taken care of. - */ -static inline struct vm_struct *kasan_find_vm_area(void *addr) -{ - static DEFINE_WAIT_OVERRIDE_MAP(vmalloc_map, LD_WAIT_SLEEP); - struct vm_struct *va; - - if (IS_ENABLED(CONFIG_PREEMPT_RT)) - return NULL; - - /* - * Suppress lockdep warning and fetch vmalloc area of the - * offending address. - */ - lock_map_acquire_try(&vmalloc_map); - va = find_vm_area(addr); - lock_map_release(&vmalloc_map); - return va; -} - static void print_address_description(void *addr, u8 tag, struct kasan_report_info *info) { @@ -429,19 +399,8 @@ static void print_address_description(void *addr, u8 tag, } if (is_vmalloc_addr(addr)) { - struct vm_struct *va = kasan_find_vm_area(addr); - - if (va) { - pr_err("The buggy address belongs to the virtual mapping at\n" - " [%px, %px) created by:\n" - " %pS\n", - va->addr, va->addr + va->size, va->caller); - pr_err("\n"); - - page = vmalloc_to_page(addr); - } else { - pr_err("The buggy address %px belongs to a vmalloc virtual mapping\n", addr); - } + pr_err("The buggy address %px belongs to a vmalloc virtual mapping\n", addr); + page = vmalloc_to_page(addr); } if (page) { diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 902da8a9c643..70fdeda1120b 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -474,8 +474,6 @@ static const unsigned int memcg_vm_event_stat[] = { NUMA_PAGE_MIGRATE, NUMA_PTE_UPDATES, NUMA_HINT_FAULTS, - NUMA_TASK_MIGRATE, - NUMA_TASK_SWAP, #endif }; diff --git a/mm/migrate.c b/mm/migrate.c index 8cf0f9c9599d..2c88f3b33833 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -2399,6 +2399,7 @@ set_status: static int get_compat_pages_array(const void __user *chunk_pages[], const void __user * __user *pages, + unsigned long chunk_offset, unsigned long chunk_nr) { compat_uptr_t __user *pages32 = (compat_uptr_t __user *)pages; @@ -2406,7 +2407,7 @@ static int get_compat_pages_array(const void __user *chunk_pages[], int i; for (i = 0; i < chunk_nr; i++) { - if (get_user(p, pages32 + i)) + if (get_user(p, pages32 + chunk_offset + i)) return -EFAULT; chunk_pages[i] = compat_ptr(p); } @@ -2425,27 +2426,28 @@ static int do_pages_stat(struct mm_struct *mm, unsigned long nr_pages, #define DO_PAGES_STAT_CHUNK_NR 16UL const void __user *chunk_pages[DO_PAGES_STAT_CHUNK_NR]; int chunk_status[DO_PAGES_STAT_CHUNK_NR]; + unsigned long chunk_offset = 0; while (nr_pages) { unsigned long chunk_nr = min(nr_pages, DO_PAGES_STAT_CHUNK_NR); if (in_compat_syscall()) { if (get_compat_pages_array(chunk_pages, pages, - chunk_nr)) + chunk_offset, chunk_nr)) break; } else { - if (copy_from_user(chunk_pages, pages, + if (copy_from_user(chunk_pages, pages + chunk_offset, chunk_nr * sizeof(*chunk_pages))) break; } do_pages_stat_array(mm, chunk_nr, chunk_pages, chunk_status); - if (copy_to_user(status, chunk_status, chunk_nr * sizeof(*status))) + if (copy_to_user(status + chunk_offset, chunk_status, + chunk_nr * sizeof(*status))) break; - pages += chunk_nr; - status += chunk_nr; + chunk_offset += chunk_nr; nr_pages -= chunk_nr; } return nr_pages ? -EFAULT : 0; diff --git a/mm/rmap.c b/mm/rmap.c index fb63d9256f09..1320b88fab74 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1845,23 +1845,32 @@ void folio_remove_rmap_pud(struct folio *folio, struct page *page, #endif } -/* We support batch unmapping of PTEs for lazyfree large folios */ -static inline bool can_batch_unmap_folio_ptes(unsigned long addr, - struct folio *folio, pte_t *ptep) +static inline unsigned int folio_unmap_pte_batch(struct folio *folio, + struct page_vma_mapped_walk *pvmw, + enum ttu_flags flags, pte_t pte) { const fpb_t fpb_flags = FPB_IGNORE_DIRTY | FPB_IGNORE_SOFT_DIRTY; - int max_nr = folio_nr_pages(folio); - pte_t pte = ptep_get(ptep); + unsigned long end_addr, addr = pvmw->address; + struct vm_area_struct *vma = pvmw->vma; + unsigned int max_nr; + + if (flags & TTU_HWPOISON) + return 1; + if (!folio_test_large(folio)) + return 1; + /* We may only batch within a single VMA and a single page table. */ + end_addr = pmd_addr_end(addr, vma->vm_end); + max_nr = (end_addr - addr) >> PAGE_SHIFT; + + /* We only support lazyfree batching for now ... */ if (!folio_test_anon(folio) || folio_test_swapbacked(folio)) - return false; + return 1; if (pte_unused(pte)) - return false; - if (pte_pfn(pte) != folio_pfn(folio)) - return false; + return 1; - return folio_pte_batch(folio, addr, ptep, pte, max_nr, fpb_flags, NULL, - NULL, NULL) == max_nr; + return folio_pte_batch(folio, addr, pvmw->pte, pte, max_nr, fpb_flags, + NULL, NULL, NULL); } /* @@ -2024,9 +2033,7 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, if (pte_dirty(pteval)) folio_mark_dirty(folio); } else if (likely(pte_present(pteval))) { - if (folio_test_large(folio) && !(flags & TTU_HWPOISON) && - can_batch_unmap_folio_ptes(address, folio, pvmw.pte)) - nr_pages = folio_nr_pages(folio); + nr_pages = folio_unmap_pte_batch(folio, &pvmw, flags, pteval); end_addr = address + nr_pages * PAGE_SIZE; flush_cache_range(vma, address, end_addr); @@ -2206,13 +2213,16 @@ discard: hugetlb_remove_rmap(folio); } else { folio_remove_rmap_ptes(folio, subpage, nr_pages, vma); - folio_ref_sub(folio, nr_pages - 1); } if (vma->vm_flags & VM_LOCKED) mlock_drain_local(); - folio_put(folio); - /* We have already batched the entire folio */ - if (nr_pages > 1) + folio_put_refs(folio, nr_pages); + + /* + * If we are sure that we batched the entire folio and cleared + * all PTEs, we can just optimize and stop right here. + */ + if (nr_pages == folio_nr_pages(folio)) goto walk_done; continue; walk_abort: diff --git a/mm/vmalloc.c b/mm/vmalloc.c index ab986dd09b6a..6dbcdceecae1 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -514,6 +514,7 @@ static int vmap_pages_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, int *nr, pgtbl_mod_mask *mask) { + int err = 0; pte_t *pte; /* @@ -530,12 +531,18 @@ static int vmap_pages_pte_range(pmd_t *pmd, unsigned long addr, do { struct page *page = pages[*nr]; - if (WARN_ON(!pte_none(ptep_get(pte)))) - return -EBUSY; - if (WARN_ON(!page)) - return -ENOMEM; - if (WARN_ON(!pfn_valid(page_to_pfn(page)))) - return -EINVAL; + if (WARN_ON(!pte_none(ptep_get(pte)))) { + err = -EBUSY; + break; + } + if (WARN_ON(!page)) { + err = -ENOMEM; + break; + } + if (WARN_ON(!pfn_valid(page_to_pfn(page)))) { + err = -EINVAL; + break; + } set_pte_at(&init_mm, addr, pte, mk_pte(page, prot)); (*nr)++; @@ -543,7 +550,8 @@ static int vmap_pages_pte_range(pmd_t *pmd, unsigned long addr, arch_leave_lazy_mmu_mode(); *mask |= PGTBL_PTE_MODIFIED; - return 0; + + return err; } static int vmap_pages_pmd_range(pud_t *pud, unsigned long addr, diff --git a/mm/vmstat.c b/mm/vmstat.c index 429ae5339bfe..a78d70ddeacd 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1346,8 +1346,6 @@ const char * const vmstat_text[] = { "numa_hint_faults", "numa_hint_faults_local", "numa_pages_migrated", - "numa_task_migrated", - "numa_task_swapped", #endif #ifdef CONFIG_MIGRATION "pgmigrate_success", diff --git a/rust/kernel/drm/device.rs b/rust/kernel/drm/device.rs index 624d7a4c83ea..14c1aa402951 100644 --- a/rust/kernel/drm/device.rs +++ b/rust/kernel/drm/device.rs @@ -66,7 +66,7 @@ impl<T: drm::Driver> Device<T> { open: Some(drm::File::<T::File>::open_callback), postclose: Some(drm::File::<T::File>::postclose_callback), unload: None, - release: None, + release: Some(Self::release), master_set: None, master_drop: None, debugfs_init: None, @@ -162,6 +162,16 @@ impl<T: drm::Driver> Device<T> { // SAFETY: `ptr` is valid by the safety requirements of this function. unsafe { &*ptr.cast() } } + + extern "C" fn release(ptr: *mut bindings::drm_device) { + // SAFETY: `ptr` is a valid pointer to a `struct drm_device` and embedded in `Self`. + let this = unsafe { Self::from_drm_device(ptr) }; + + // SAFETY: + // - When `release` runs it is guaranteed that there is no further access to `this`. + // - `this` is valid for dropping. + unsafe { core::ptr::drop_in_place(this) }; + } } impl<T: drm::Driver> Deref for Device<T> { diff --git a/rust/kernel/drm/driver.rs b/rust/kernel/drm/driver.rs index acb638086131..af93d46d03d3 100644 --- a/rust/kernel/drm/driver.rs +++ b/rust/kernel/drm/driver.rs @@ -10,7 +10,6 @@ use crate::{ drm, error::{to_result, Result}, prelude::*, - str::CStr, types::ARef, }; use macros::vtable; diff --git a/samples/damon/mtier.c b/samples/damon/mtier.c index 36d2cd933f5a..c94254b77fc9 100644 --- a/samples/damon/mtier.c +++ b/samples/damon/mtier.c @@ -164,8 +164,12 @@ static int damon_sample_mtier_enable_store( if (enable == enabled) return 0; - if (enable) - return damon_sample_mtier_start(); + if (enable) { + err = damon_sample_mtier_start(); + if (err) + enable = false; + return err; + } damon_sample_mtier_stop(); return 0; } diff --git a/samples/damon/prcl.c b/samples/damon/prcl.c index 056b1b21a0fe..5597e6a08ab2 100644 --- a/samples/damon/prcl.c +++ b/samples/damon/prcl.c @@ -122,8 +122,12 @@ static int damon_sample_prcl_enable_store( if (enable == enabled) return 0; - if (enable) - return damon_sample_prcl_start(); + if (enable) { + err = damon_sample_prcl_start(); + if (err) + enable = false; + return err; + } damon_sample_prcl_stop(); return 0; } diff --git a/samples/damon/wsse.c b/samples/damon/wsse.c index 11be25803274..e20238a249e7 100644 --- a/samples/damon/wsse.c +++ b/samples/damon/wsse.c @@ -102,8 +102,12 @@ static int damon_sample_wsse_enable_store( if (enable == enabled) return 0; - if (enable) - return damon_sample_wsse_start(); + if (enable) { + err = damon_sample_wsse_start(); + if (err) + enable = false; + return err; + } damon_sample_wsse_stop(); return 0; } diff --git a/scripts/gdb/linux/constants.py.in b/scripts/gdb/linux/constants.py.in index fd6bd69c5096..f795302ddfa8 100644 --- a/scripts/gdb/linux/constants.py.in +++ b/scripts/gdb/linux/constants.py.in @@ -20,6 +20,7 @@ #include <linux/of_fdt.h> #include <linux/page_ext.h> #include <linux/radix-tree.h> +#include <linux/maple_tree.h> #include <linux/slab.h> #include <linux/threads.h> #include <linux/vmalloc.h> @@ -93,6 +94,12 @@ LX_GDBPARSED(RADIX_TREE_MAP_SIZE) LX_GDBPARSED(RADIX_TREE_MAP_SHIFT) LX_GDBPARSED(RADIX_TREE_MAP_MASK) +/* linux/maple_tree.h */ +LX_VALUE(MAPLE_NODE_SLOTS) +LX_VALUE(MAPLE_RANGE64_SLOTS) +LX_VALUE(MAPLE_ARANGE64_SLOTS) +LX_GDBPARSED(MAPLE_NODE_MASK) + /* linux/vmalloc.h */ LX_VALUE(VM_IOREMAP) LX_VALUE(VM_ALLOC) diff --git a/scripts/gdb/linux/interrupts.py b/scripts/gdb/linux/interrupts.py index 616a5f26377a..f4f715a8f0e3 100644 --- a/scripts/gdb/linux/interrupts.py +++ b/scripts/gdb/linux/interrupts.py @@ -7,7 +7,7 @@ import gdb from linux import constants from linux import cpus from linux import utils -from linux import radixtree +from linux import mapletree irq_desc_type = utils.CachedType("struct irq_desc") @@ -23,12 +23,12 @@ def irqd_is_level(desc): def show_irq_desc(prec, irq): text = "" - desc = radixtree.lookup(gdb.parse_and_eval("&irq_desc_tree"), irq) + desc = mapletree.mtree_load(gdb.parse_and_eval("&sparse_irqs"), irq) if desc is None: return text - desc = desc.cast(irq_desc_type.get_type()) - if desc is None: + desc = desc.cast(irq_desc_type.get_type().pointer()) + if desc == 0: return text if irq_settings_is_hidden(desc): @@ -110,7 +110,7 @@ def x86_show_mce(prec, var, pfx, desc): pvar = gdb.parse_and_eval(var) text = "%*s: " % (prec, pfx) for cpu in cpus.each_online_cpu(): - text += "%10u " % (cpus.per_cpu(pvar, cpu)) + text += "%10u " % (cpus.per_cpu(pvar, cpu).dereference()) text += " %s\n" % (desc) return text @@ -142,7 +142,7 @@ def x86_show_interupts(prec): if constants.LX_CONFIG_X86_MCE: text += x86_show_mce(prec, "&mce_exception_count", "MCE", "Machine check exceptions") - text == x86_show_mce(prec, "&mce_poll_count", "MCP", "Machine check polls") + text += x86_show_mce(prec, "&mce_poll_count", "MCP", "Machine check polls") text += show_irq_err_count(prec) @@ -221,8 +221,8 @@ class LxInterruptList(gdb.Command): gdb.write("CPU%-8d" % cpu) gdb.write("\n") - if utils.gdb_eval_or_none("&irq_desc_tree") is None: - return + if utils.gdb_eval_or_none("&sparse_irqs") is None: + raise gdb.GdbError("Unable to find the sparse IRQ tree, is CONFIG_SPARSE_IRQ enabled?") for irq in range(nr_irqs): gdb.write(show_irq_desc(prec, irq)) diff --git a/scripts/gdb/linux/mapletree.py b/scripts/gdb/linux/mapletree.py new file mode 100644 index 000000000000..d52d51c0a03f --- /dev/null +++ b/scripts/gdb/linux/mapletree.py @@ -0,0 +1,252 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Maple tree helpers +# +# Copyright (c) 2025 Broadcom +# +# Authors: +# Florian Fainelli <florian.fainelli@broadcom.com> + +import gdb + +from linux import utils +from linux import constants +from linux import xarray + +maple_tree_root_type = utils.CachedType("struct maple_tree") +maple_node_type = utils.CachedType("struct maple_node") +maple_enode_type = utils.CachedType("void") + +maple_dense = 0 +maple_leaf_64 = 1 +maple_range_64 = 2 +maple_arange_64 = 3 + +class Mas(object): + ma_active = 0 + ma_start = 1 + ma_root = 2 + ma_none = 3 + ma_pause = 4 + ma_overflow = 5 + ma_underflow = 6 + ma_error = 7 + + def __init__(self, mt, first, end): + if mt.type == maple_tree_root_type.get_type().pointer(): + self.tree = mt.dereference() + elif mt.type != maple_tree_root_type.get_type(): + raise gdb.GdbError("must be {} not {}" + .format(maple_tree_root_type.get_type().pointer(), mt.type)) + self.tree = mt + self.index = first + self.last = end + self.node = None + self.status = self.ma_start + self.min = 0 + self.max = -1 + + def is_start(self): + # mas_is_start() + return self.status == self.ma_start + + def is_ptr(self): + # mas_is_ptr() + return self.status == self.ma_root + + def is_none(self): + # mas_is_none() + return self.status == self.ma_none + + def root(self): + # mas_root() + return self.tree['ma_root'].cast(maple_enode_type.get_type().pointer()) + + def start(self): + # mas_start() + if self.is_start() is False: + return None + + self.min = 0 + self.max = ~0 + + while True: + self.depth = 0 + root = self.root() + if xarray.xa_is_node(root): + self.depth = 0 + self.status = self.ma_active + self.node = mte_safe_root(root) + self.offset = 0 + if mte_dead_node(self.node) is True: + continue + + return None + + self.node = None + # Empty tree + if root is None: + self.status = self.ma_none + self.offset = constants.LX_MAPLE_NODE_SLOTS + return None + + # Single entry tree + self.status = self.ma_root + self.offset = constants.LX_MAPLE_NODE_SLOTS + + if self.index != 0: + return None + + return root + + return None + + def reset(self): + # mas_reset() + self.status = self.ma_start + self.node = None + +def mte_safe_root(node): + if node.type != maple_enode_type.get_type().pointer(): + raise gdb.GdbError("{} must be {} not {}" + .format(mte_safe_root.__name__, maple_enode_type.get_type().pointer(), node.type)) + ulong_type = utils.get_ulong_type() + indirect_ptr = node.cast(ulong_type) & ~0x2 + val = indirect_ptr.cast(maple_enode_type.get_type().pointer()) + return val + +def mte_node_type(entry): + ulong_type = utils.get_ulong_type() + val = None + if entry.type == maple_enode_type.get_type().pointer(): + val = entry.cast(ulong_type) + elif entry.type == ulong_type: + val = entry + else: + raise gdb.GdbError("{} must be {} not {}" + .format(mte_node_type.__name__, maple_enode_type.get_type().pointer(), entry.type)) + return (val >> 0x3) & 0xf + +def ma_dead_node(node): + if node.type != maple_node_type.get_type().pointer(): + raise gdb.GdbError("{} must be {} not {}" + .format(ma_dead_node.__name__, maple_node_type.get_type().pointer(), node.type)) + ulong_type = utils.get_ulong_type() + parent = node['parent'] + indirect_ptr = node['parent'].cast(ulong_type) & ~constants.LX_MAPLE_NODE_MASK + return indirect_ptr == node + +def mte_to_node(enode): + ulong_type = utils.get_ulong_type() + if enode.type == maple_enode_type.get_type().pointer(): + indirect_ptr = enode.cast(ulong_type) + elif enode.type == ulong_type: + indirect_ptr = enode + else: + raise gdb.GdbError("{} must be {} not {}" + .format(mte_to_node.__name__, maple_enode_type.get_type().pointer(), enode.type)) + indirect_ptr = indirect_ptr & ~constants.LX_MAPLE_NODE_MASK + return indirect_ptr.cast(maple_node_type.get_type().pointer()) + +def mte_dead_node(enode): + if enode.type != maple_enode_type.get_type().pointer(): + raise gdb.GdbError("{} must be {} not {}" + .format(mte_dead_node.__name__, maple_enode_type.get_type().pointer(), enode.type)) + node = mte_to_node(enode) + return ma_dead_node(node) + +def ma_is_leaf(tp): + result = tp < maple_range_64 + return tp < maple_range_64 + +def mt_pivots(t): + if t == maple_dense: + return 0 + elif t == maple_leaf_64 or t == maple_range_64: + return constants.LX_MAPLE_RANGE64_SLOTS - 1 + elif t == maple_arange_64: + return constants.LX_MAPLE_ARANGE64_SLOTS - 1 + +def ma_pivots(node, t): + if node.type != maple_node_type.get_type().pointer(): + raise gdb.GdbError("{}: must be {} not {}" + .format(ma_pivots.__name__, maple_node_type.get_type().pointer(), node.type)) + if t == maple_arange_64: + return node['ma64']['pivot'] + elif t == maple_leaf_64 or t == maple_range_64: + return node['mr64']['pivot'] + else: + return None + +def ma_slots(node, tp): + if node.type != maple_node_type.get_type().pointer(): + raise gdb.GdbError("{}: must be {} not {}" + .format(ma_slots.__name__, maple_node_type.get_type().pointer(), node.type)) + if tp == maple_arange_64: + return node['ma64']['slot'] + elif tp == maple_range_64 or tp == maple_leaf_64: + return node['mr64']['slot'] + elif tp == maple_dense: + return node['slot'] + else: + return None + +def mt_slot(mt, slots, offset): + ulong_type = utils.get_ulong_type() + return slots[offset].cast(ulong_type) + +def mtree_lookup_walk(mas): + ulong_type = utils.get_ulong_type() + n = mas.node + + while True: + node = mte_to_node(n) + tp = mte_node_type(n) + pivots = ma_pivots(node, tp) + end = mt_pivots(tp) + offset = 0 + while True: + if pivots[offset] >= mas.index: + break + if offset >= end: + break + offset += 1 + + slots = ma_slots(node, tp) + n = mt_slot(mas.tree, slots, offset) + if ma_dead_node(node) is True: + mas.reset() + return None + break + + if ma_is_leaf(tp) is True: + break + + return n + +def mtree_load(mt, index): + ulong_type = utils.get_ulong_type() + # MT_STATE(...) + mas = Mas(mt, index, index) + entry = None + + while True: + entry = mas.start() + if mas.is_none(): + return None + + if mas.is_ptr(): + if index != 0: + entry = None + return entry + + entry = mtree_lookup_walk(mas) + if entry is None and mas.is_start(): + continue + else: + break + + if xarray.xa_is_zero(entry): + return None + + return entry diff --git a/scripts/gdb/linux/vfs.py b/scripts/gdb/linux/vfs.py index b5fbb18ccb77..9e921b645a68 100644 --- a/scripts/gdb/linux/vfs.py +++ b/scripts/gdb/linux/vfs.py @@ -22,7 +22,7 @@ def dentry_name(d): if parent == d or parent == 0: return "" p = dentry_name(d['d_parent']) + "/" - return p + d['d_shortname']['string'].string() + return p + d['d_name']['name'].string() class DentryName(gdb.Function): """Return string of the full path of a dentry. diff --git a/scripts/gdb/linux/xarray.py b/scripts/gdb/linux/xarray.py new file mode 100644 index 000000000000..f4477b5def75 --- /dev/null +++ b/scripts/gdb/linux/xarray.py @@ -0,0 +1,28 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Xarray helpers +# +# Copyright (c) 2025 Broadcom +# +# Authors: +# Florian Fainelli <florian.fainelli@broadcom.com> + +import gdb + +from linux import utils +from linux import constants + +def xa_is_internal(entry): + ulong_type = utils.get_ulong_type() + return ((entry.cast(ulong_type) & 3) == 2) + +def xa_mk_internal(v): + return ((v << 2) | 2) + +def xa_is_zero(entry): + ulong_type = utils.get_ulong_type() + return entry.cast(ulong_type) == xa_mk_internal(257) + +def xa_is_node(entry): + ulong_type = utils.get_ulong_type() + return xa_is_internal(entry) and (entry.cast(ulong_type) > 4096) diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index b7dded3c8113..5cfb5d74dd5f 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -628,6 +628,7 @@ #define MSR_AMD64_OSVW_STATUS 0xc0010141 #define MSR_AMD_PPIN_CTL 0xc00102f0 #define MSR_AMD_PPIN 0xc00102f1 +#define MSR_AMD64_CPUID_FN_7 0xc0011002 #define MSR_AMD64_CPUID_FN_1 0xc0011004 #define MSR_AMD64_LS_CFG 0xc0011020 #define MSR_AMD64_DC_CFG 0xc0011022 diff --git a/tools/include/linux/kallsyms.h b/tools/include/linux/kallsyms.h index 5a37ccbec54f..f61a01dd7eb7 100644 --- a/tools/include/linux/kallsyms.h +++ b/tools/include/linux/kallsyms.h @@ -18,6 +18,7 @@ static inline const char *kallsyms_lookup(unsigned long addr, return NULL; } +#ifdef HAVE_BACKTRACE_SUPPORT #include <execinfo.h> #include <stdlib.h> static inline void print_ip_sym(const char *loglvl, unsigned long ip) @@ -30,5 +31,8 @@ static inline void print_ip_sym(const char *loglvl, unsigned long ip) free(name); } +#else +static inline void print_ip_sym(const char *loglvl, unsigned long ip) {} +#endif #endif diff --git a/tools/testing/selftests/hid/tests/test_mouse.py b/tools/testing/selftests/hid/tests/test_mouse.py index 66daf7e5975c..eb4e15a0e53b 100644 --- a/tools/testing/selftests/hid/tests/test_mouse.py +++ b/tools/testing/selftests/hid/tests/test_mouse.py @@ -439,6 +439,68 @@ class BadResolutionMultiplierMouse(ResolutionMultiplierMouse): return 32 # EPIPE +class BadReportDescriptorMouse(BaseMouse): + """ + This "device" was one autogenerated by syzbot. There are a lot of issues in + it, and the most problematic is that it declares features that have no + size. + + This leads to report->size being set to 0 and can mess up with usbhid + internals. Fortunately, uhid merely passes the incoming buffer, without + touching it so a buffer of size 0 will be translated to [] without + triggering a kernel oops. + + Because the report descriptor is wrong, no input are created, and we need + to tweak a little bit the parameters to make it look correct. + """ + + # fmt: off + report_descriptor = [ + 0x96, 0x01, 0x00, # Report Count (1) 0 + 0x06, 0x01, 0x00, # Usage Page (Generic Desktop) 3 + # 0x03, 0x00, 0x00, 0x00, 0x00, # Ignored by the kernel somehow + 0x2a, 0x90, 0xa0, # Usage Maximum (41104) 6 + 0x27, 0x00, 0x00, 0x00, 0x00, # Logical Maximum (0) 9 + 0xb3, 0x81, 0x3e, 0x25, 0x03, # Feature (Cnst,Arr,Abs,Vol) 14 + 0x1b, 0xdd, 0xe8, 0x40, 0x50, # Usage Minimum (1346431197) 19 + 0x3b, 0x5d, 0x8c, 0x3d, 0xda, # Designator Index 24 + ] + # fmt: on + + def __init__( + self, rdesc=report_descriptor, name=None, input_info=(3, 0x045E, 0x07DA) + ): + super().__init__(rdesc, name, input_info) + self.high_resolution_report_called = False + + def get_evdev(self, application=None): + assert self._input_nodes is None + return ( + "Ok" # should be a list or None, but both would fail, so abusing the system + ) + + def next_sync_events(self, application=None): + # there are no evdev nodes, so no events + return [] + + def is_ready(self): + # we wait for the SET_REPORT command to come + return self.high_resolution_report_called + + def set_report(self, req, rnum, rtype, data): + if rtype != self.UHID_FEATURE_REPORT: + raise InvalidHIDCommunication(f"Unexpected report type: {rtype}") + if rnum != 0x0: + raise InvalidHIDCommunication(f"Unexpected report number: {rnum}") + + if len(data) != 1: + raise InvalidHIDCommunication(f"Unexpected data: {data}, expected '[0]'") + + self.high_resolution_report_called = True + + return 0 + + class ResolutionMultiplierHWheelMouse(TwoWheelMouse): # fmt: off report_descriptor = [ @@ -975,3 +1037,11 @@ class TestMiMouse(TestWheelMouse): # assert below print out the real error pass assert remaining == [] + + +class TestBadReportDescriptorMouse(base.BaseTestCase.TestUhid): + def create_device(self): + return BadReportDescriptorMouse() + + def assertName(self, uhdev): + pass |