diff options
Diffstat (limited to 'arch/arm64')
56 files changed, 742 insertions, 507 deletions
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts index b0c64f75792c..8974b5a1d3b1 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts @@ -188,6 +188,7 @@ reg = <0x3a3>; interrupt-parent = <&r_intc>; interrupts = <0 IRQ_TYPE_LEVEL_LOW>; + x-powers,drive-vbus-en; /* set N_VBUSEN as output pin */ }; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi index 837a03dee875..2abb335145a6 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi @@ -390,7 +390,7 @@ }; video-codec@1c0e000 { - compatible = "allwinner,sun50i-h5-video-engine"; + compatible = "allwinner,sun50i-a64-video-engine"; reg = <0x01c0e000 0x1000>; clocks = <&ccu CLK_BUS_VE>, <&ccu CLK_VE>, <&ccu CLK_DRAM_VE>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi index e14e0ce7e89f..016641a41694 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi @@ -187,8 +187,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vddio_boot>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts index 8cd50b75171d..ade2ee09ae96 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts @@ -305,8 +305,7 @@ max-frequency = <200000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddio_ao3v3>; vqmmc-supply = <&vddio_tf>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts index 4cf7f6e80c6a..25105ac96d55 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts @@ -238,8 +238,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vddio_card>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts index 2e1cd5e3a246..1cc9dc68ef00 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts @@ -258,8 +258,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&tflash_vdd>; vqmmc-supply = <&tf_io>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi index ce862266b9aa..0be0f2a5d2fe 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi @@ -196,8 +196,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vddio_card>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi index 93a4acf2c46c..ad4d50bd9d77 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi @@ -154,8 +154,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vcc_3v3>; }; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-wetek.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb-wetek.dtsi index ec09bb5792b7..2d2db783c44c 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-wetek.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-wetek.dtsi @@ -211,8 +211,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vcc_3v3>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts index f1c410e2da2b..796baea7a0bf 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts @@ -131,8 +131,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vddio_card>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts index db293440e4ca..255cede7b447 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts @@ -238,8 +238,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vcc_3v3>; vqmmc-supply = <&vcc_card>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts index 6739697be1de..9cbdb85fb591 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts @@ -183,8 +183,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vddio_card>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi index a1b31013ab6e..bc811a2faf42 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi @@ -137,8 +137,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vddio_boot>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts b/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts index 3c3a667a8df8..3f086ed7de05 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts @@ -356,8 +356,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vddio_boot>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts b/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts index f7a1cffab4a8..8acfd40090d2 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts @@ -147,8 +147,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vddio_boot>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm-rbox-pro.dts b/arch/arm64/boot/dts/amlogic/meson-gxm-rbox-pro.dts index 7212dc4531e4..7fa20a8ede17 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxm-rbox-pro.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxm-rbox-pro.dts @@ -170,8 +170,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vddio_boot>; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a-rdb.dts b/arch/arm64/boot/dts/freescale/fsl-ls1028a-rdb.dts index fdeb4176fc33..f86b054a74ae 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1028a-rdb.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a-rdb.dts @@ -71,3 +71,20 @@ &duart1 { status = "okay"; }; + +&enetc_port0 { + phy-handle = <&sgmii_phy0>; + phy-connection-type = "sgmii"; + + mdio { + #address-cells = <1>; + #size-cells = <0>; + sgmii_phy0: ethernet-phy@2 { + reg = <0x2>; + }; + }; +}; + +&enetc_port1 { + status = "disabled"; +}; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi index a8cf92af05fb..2896bbcfa3bb 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi @@ -335,5 +335,40 @@ <GIC_SPI 206 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 207 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 208 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 209 IRQ_TYPE_LEVEL_HIGH>; }; + + pcie@1f0000000 { /* Integrated Endpoint Root Complex */ + compatible = "pci-host-ecam-generic"; + reg = <0x01 0xf0000000 0x0 0x100000>; + #address-cells = <3>; + #size-cells = <2>; + #interrupt-cells = <1>; + msi-parent = <&its>; + device_type = "pci"; + bus-range = <0x0 0x0>; + dma-coherent; + msi-map = <0 &its 0x17 0xe>; + iommu-map = <0 &smmu 0x17 0xe>; + /* PF0-6 BAR0 - non-prefetchable memory */ + ranges = <0x82000000 0x0 0x00000000 0x1 0xf8000000 0x0 0x160000 + /* PF0-6 BAR2 - prefetchable memory */ + 0xc2000000 0x0 0x00000000 0x1 0xf8160000 0x0 0x070000 + /* PF0: VF0-1 BAR0 - non-prefetchable memory */ + 0x82000000 0x0 0x00000000 0x1 0xf81d0000 0x0 0x020000 + /* PF0: VF0-1 BAR2 - prefetchable memory */ + 0xc2000000 0x0 0x00000000 0x1 0xf81f0000 0x0 0x020000 + /* PF1: VF0-1 BAR0 - non-prefetchable memory */ + 0x82000000 0x0 0x00000000 0x1 0xf8210000 0x0 0x020000 + /* PF1: VF0-1 BAR2 - prefetchable memory */ + 0xc2000000 0x0 0x00000000 0x1 0xf8230000 0x0 0x020000>; + + enetc_port0: ethernet@0,0 { + compatible = "fsl,enetc"; + reg = <0x000000 0 0 0 0>; + }; + enetc_port1: ethernet@0,1 { + compatible = "fsl,enetc"; + reg = <0x000100 0 0 0 0>; + }; + }; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mq-evk.dts b/arch/arm64/boot/dts/freescale/imx8mq-evk.dts index 64acccc4bfcb..f74b13aa5aa5 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx8mq-evk.dts @@ -227,34 +227,34 @@ pinctrl_usdhc1_100mhz: usdhc1-100grp { fsl,pins = < - MX8MQ_IOMUXC_SD1_CLK_USDHC1_CLK 0x85 - MX8MQ_IOMUXC_SD1_CMD_USDHC1_CMD 0xc5 - MX8MQ_IOMUXC_SD1_DATA0_USDHC1_DATA0 0xc5 - MX8MQ_IOMUXC_SD1_DATA1_USDHC1_DATA1 0xc5 - MX8MQ_IOMUXC_SD1_DATA2_USDHC1_DATA2 0xc5 - MX8MQ_IOMUXC_SD1_DATA3_USDHC1_DATA3 0xc5 - MX8MQ_IOMUXC_SD1_DATA4_USDHC1_DATA4 0xc5 - MX8MQ_IOMUXC_SD1_DATA5_USDHC1_DATA5 0xc5 - MX8MQ_IOMUXC_SD1_DATA6_USDHC1_DATA6 0xc5 - MX8MQ_IOMUXC_SD1_DATA7_USDHC1_DATA7 0xc5 - MX8MQ_IOMUXC_SD1_STROBE_USDHC1_STROBE 0x85 + MX8MQ_IOMUXC_SD1_CLK_USDHC1_CLK 0x8d + MX8MQ_IOMUXC_SD1_CMD_USDHC1_CMD 0xcd + MX8MQ_IOMUXC_SD1_DATA0_USDHC1_DATA0 0xcd + MX8MQ_IOMUXC_SD1_DATA1_USDHC1_DATA1 0xcd + MX8MQ_IOMUXC_SD1_DATA2_USDHC1_DATA2 0xcd + MX8MQ_IOMUXC_SD1_DATA3_USDHC1_DATA3 0xcd + MX8MQ_IOMUXC_SD1_DATA4_USDHC1_DATA4 0xcd + MX8MQ_IOMUXC_SD1_DATA5_USDHC1_DATA5 0xcd + MX8MQ_IOMUXC_SD1_DATA6_USDHC1_DATA6 0xcd + MX8MQ_IOMUXC_SD1_DATA7_USDHC1_DATA7 0xcd + MX8MQ_IOMUXC_SD1_STROBE_USDHC1_STROBE 0x8d MX8MQ_IOMUXC_SD1_RESET_B_USDHC1_RESET_B 0xc1 >; }; pinctrl_usdhc1_200mhz: usdhc1-200grp { fsl,pins = < - MX8MQ_IOMUXC_SD1_CLK_USDHC1_CLK 0x87 - MX8MQ_IOMUXC_SD1_CMD_USDHC1_CMD 0xc7 - MX8MQ_IOMUXC_SD1_DATA0_USDHC1_DATA0 0xc7 - MX8MQ_IOMUXC_SD1_DATA1_USDHC1_DATA1 0xc7 - MX8MQ_IOMUXC_SD1_DATA2_USDHC1_DATA2 0xc7 - MX8MQ_IOMUXC_SD1_DATA3_USDHC1_DATA3 0xc7 - MX8MQ_IOMUXC_SD1_DATA4_USDHC1_DATA4 0xc7 - MX8MQ_IOMUXC_SD1_DATA5_USDHC1_DATA5 0xc7 - MX8MQ_IOMUXC_SD1_DATA6_USDHC1_DATA6 0xc7 - MX8MQ_IOMUXC_SD1_DATA7_USDHC1_DATA7 0xc7 - MX8MQ_IOMUXC_SD1_STROBE_USDHC1_STROBE 0x87 + MX8MQ_IOMUXC_SD1_CLK_USDHC1_CLK 0x9f + MX8MQ_IOMUXC_SD1_CMD_USDHC1_CMD 0xdf + MX8MQ_IOMUXC_SD1_DATA0_USDHC1_DATA0 0xdf + MX8MQ_IOMUXC_SD1_DATA1_USDHC1_DATA1 0xdf + MX8MQ_IOMUXC_SD1_DATA2_USDHC1_DATA2 0xdf + MX8MQ_IOMUXC_SD1_DATA3_USDHC1_DATA3 0xdf + MX8MQ_IOMUXC_SD1_DATA4_USDHC1_DATA4 0xdf + MX8MQ_IOMUXC_SD1_DATA5_USDHC1_DATA5 0xdf + MX8MQ_IOMUXC_SD1_DATA6_USDHC1_DATA6 0xdf + MX8MQ_IOMUXC_SD1_DATA7_USDHC1_DATA7 0xdf + MX8MQ_IOMUXC_SD1_STROBE_USDHC1_STROBE 0x9f MX8MQ_IOMUXC_SD1_RESET_B_USDHC1_RESET_B 0xc1 >; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mq.dtsi b/arch/arm64/boot/dts/freescale/imx8mq.dtsi index 8e9d6d5ed7b2..b6d31499fb43 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mq.dtsi @@ -360,6 +360,8 @@ <&clk IMX8MQ_CLK_NAND_USDHC_BUS>, <&clk IMX8MQ_CLK_USDHC1_ROOT>; clock-names = "ipg", "ahb", "per"; + assigned-clocks = <&clk IMX8MQ_CLK_USDHC1>; + assigned-clock-rates = <400000000>; fsl,tuning-start-tap = <20>; fsl,tuning-step = <2>; bus-width = <4>; diff --git a/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts b/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts index 5b4a9609e31f..2468762283a5 100644 --- a/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts +++ b/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts @@ -351,7 +351,7 @@ reg = <0>; pinctrl-names = "default"; pinctrl-0 = <&cp0_copper_eth_phy_reset>; - reset-gpios = <&cp1_gpio1 11 GPIO_ACTIVE_LOW>; + reset-gpios = <&cp0_gpio2 11 GPIO_ACTIVE_LOW>; reset-assert-us = <10000>; }; diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi index 99b7495455a6..838e32cc14c9 100644 --- a/arch/arm64/boot/dts/qcom/msm8996.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi @@ -404,7 +404,7 @@ }; intc: interrupt-controller@9bc0000 { - compatible = "arm,gic-v3"; + compatible = "qcom,msm8996-gic-v3", "arm,gic-v3"; #interrupt-cells = <3>; interrupt-controller; #redistributor-regions = <1>; diff --git a/arch/arm64/boot/dts/qcom/msm8998.dtsi b/arch/arm64/boot/dts/qcom/msm8998.dtsi index 8d41b69ec2da..99bccaac31ad 100644 --- a/arch/arm64/boot/dts/qcom/msm8998.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8998.dtsi @@ -37,7 +37,7 @@ }; memory@86200000 { - reg = <0x0 0x86200000 0x0 0x2600000>; + reg = <0x0 0x86200000 0x0 0x2d00000>; no-map; }; diff --git a/arch/arm64/boot/dts/renesas/r8a774a1.dtsi b/arch/arm64/boot/dts/renesas/r8a774a1.dtsi index 20745a8528c5..719ed9d9067d 100644 --- a/arch/arm64/boot/dts/renesas/r8a774a1.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a774a1.dtsi @@ -1011,6 +1011,9 @@ <&cpg CPG_CORE R8A774A1_CLK_S3D1>, <&scif_clk>; clock-names = "fck", "brg_int", "scif_clk"; + dmas = <&dmac1 0x13>, <&dmac1 0x12>, + <&dmac2 0x13>, <&dmac2 0x12>; + dma-names = "tx", "rx", "tx", "rx"; power-domains = <&sysc R8A774A1_PD_ALWAYS_ON>; resets = <&cpg 310>; status = "disabled"; diff --git a/arch/arm64/boot/dts/renesas/r8a7796.dtsi b/arch/arm64/boot/dts/renesas/r8a7796.dtsi index afedbf5728ec..0648d12778ed 100644 --- a/arch/arm64/boot/dts/renesas/r8a7796.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a7796.dtsi @@ -1262,6 +1262,9 @@ <&cpg CPG_CORE R8A7796_CLK_S3D1>, <&scif_clk>; clock-names = "fck", "brg_int", "scif_clk"; + dmas = <&dmac1 0x13>, <&dmac1 0x12>, + <&dmac2 0x13>, <&dmac2 0x12>; + dma-names = "tx", "rx", "tx", "rx"; power-domains = <&sysc R8A7796_PD_ALWAYS_ON>; resets = <&cpg 310>; status = "disabled"; diff --git a/arch/arm64/boot/dts/renesas/r8a77965.dtsi b/arch/arm64/boot/dts/renesas/r8a77965.dtsi index 6dc9b1fef830..4b3730f640ef 100644 --- a/arch/arm64/boot/dts/renesas/r8a77965.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a77965.dtsi @@ -1068,6 +1068,9 @@ <&cpg CPG_CORE R8A77965_CLK_S3D1>, <&scif_clk>; clock-names = "fck", "brg_int", "scif_clk"; + dmas = <&dmac1 0x13>, <&dmac1 0x12>, + <&dmac2 0x13>, <&dmac2 0x12>; + dma-names = "tx", "rx", "tx", "rx"; power-domains = <&sysc R8A77965_PD_ALWAYS_ON>; resets = <&cpg 310>; status = "disabled"; diff --git a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts index bd937d68ca3b..040b36ef0dd2 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts +++ b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts @@ -40,6 +40,7 @@ pinctrl-0 = <&usb30_host_drv>; regulator-name = "vcc_host_5v"; regulator-always-on; + regulator-boot-on; vin-supply = <&vcc_sys>; }; @@ -51,6 +52,7 @@ pinctrl-0 = <&usb20_host_drv>; regulator-name = "vcc_host1_5v"; regulator-always-on; + regulator-boot-on; vin-supply = <&vcc_sys>; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-bob.dts b/arch/arm64/boot/dts/rockchip/rk3399-gru-bob.dts index 1ee0dc0d9f10..d1cf404b8708 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-gru-bob.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-bob.dts @@ -22,7 +22,7 @@ backlight = <&backlight>; power-supply = <&pp3300_disp>; - ports { + port { panel_in_edp: endpoint { remote-endpoint = <&edp_out_panel>; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi index c400be64170e..931640e9aed4 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi @@ -200,6 +200,19 @@ pinctrl-0 = <&bl_en>; pwm-delay-us = <10000>; }; + + gpio_keys: gpio-keys { + compatible = "gpio-keys"; + pinctrl-names = "default"; + pinctrl-0 = <&bt_host_wake_l>; + + wake_on_bt: wake-on-bt { + label = "Wake-on-Bluetooth"; + gpios = <&gpio0 3 GPIO_ACTIVE_LOW>; + linux,code = <KEY_WAKEUP>; + wakeup-source; + }; + }; }; &ppvar_bigcpu { diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-kevin.dts b/arch/arm64/boot/dts/rockchip/rk3399-gru-kevin.dts index 81e73103fa78..15e254a77391 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-gru-kevin.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-kevin.dts @@ -43,7 +43,7 @@ backlight = <&backlight>; power-supply = <&pp3300_disp>; - ports { + port { panel_in_edp: endpoint { remote-endpoint = <&edp_out_panel>; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi index fc50b3ef758c..62ea7d6a7d4a 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi @@ -175,6 +175,21 @@ pinctrl-0 = <&dmic_en>; wakeup-delay-ms = <250>; }; + + gpio_keys: gpio-keys { + compatible = "gpio-keys"; + pinctrl-names = "default"; + pinctrl-0 = <&pen_eject_odl>; + + pen-insert { + label = "Pen Insert"; + /* Insert = low, eject = high */ + gpios = <&gpio1 1 GPIO_ACTIVE_LOW>; + linux,code = <SW_PEN_INSERTED>; + linux,input-type = <EV_SW>; + wakeup-source; + }; + }; }; /* pp900_s0 aliases */ @@ -328,20 +343,6 @@ camera: &i2c7 { <400000000>; }; -&gpio_keys { - pinctrl-names = "default"; - pinctrl-0 = <&bt_host_wake_l>, <&pen_eject_odl>; - - pen-insert { - label = "Pen Insert"; - /* Insert = low, eject = high */ - gpios = <&gpio1 1 GPIO_ACTIVE_LOW>; - linux,code = <SW_PEN_INSERTED>; - linux,input-type = <EV_SW>; - wakeup-source; - }; -}; - &i2c_tunnel { google,remote-bus = <0>; }; @@ -437,8 +438,19 @@ camera: &i2c7 { status = "okay"; }; -&wake_on_bt { - gpios = <&gpio1 2 GPIO_ACTIVE_LOW>; +&usb_host0_ohci { + #address-cells = <1>; + #size-cells = <0>; + + qca_bt: bluetooth@1 { + compatible = "usbcf3,e300", "usb4ca,301a"; + reg = <1>; + pinctrl-names = "default"; + pinctrl-0 = <&bt_host_wake_l>; + interrupt-parent = <&gpio1>; + interrupts = <2 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "wakeup"; + }; }; /* PINCTRL OVERRIDES */ @@ -455,7 +467,7 @@ camera: &i2c7 { }; &bt_host_wake_l { - rockchip,pins = <1 2 RK_FUNC_GPIO &pcfg_pull_up>; + rockchip,pins = <1 2 RK_FUNC_GPIO &pcfg_pull_none>; }; &ec_ap_int_l { diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi index ea607a601a86..da03fa9c5662 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi @@ -269,19 +269,6 @@ #clock-cells = <0>; }; - gpio_keys: gpio-keys { - compatible = "gpio-keys"; - pinctrl-names = "default"; - pinctrl-0 = <&bt_host_wake_l>; - - wake_on_bt: wake-on-bt { - label = "Wake-on-Bluetooth"; - gpios = <&gpio0 3 GPIO_ACTIVE_LOW>; - linux,code = <KEY_WAKEUP>; - wakeup-source; - }; - }; - max98357a: max98357a { compatible = "maxim,max98357a"; pinctrl-names = "default"; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-sapphire-excavator.dts b/arch/arm64/boot/dts/rockchip/rk3399-sapphire-excavator.dts index 0b8f1edbd746..b48a63c3efc3 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-sapphire-excavator.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-sapphire-excavator.dts @@ -91,7 +91,7 @@ pinctrl-0 = <&lcd_panel_reset>; power-supply = <&vcc3v3_s0>; - ports { + port { panel_in_edp: endpoint { remote-endpoint = <&edp_out_panel>; }; diff --git a/arch/arm64/crypto/aes-ce-ccm-core.S b/arch/arm64/crypto/aes-ce-ccm-core.S index e3a375c4cb83..1b151442dac1 100644 --- a/arch/arm64/crypto/aes-ce-ccm-core.S +++ b/arch/arm64/crypto/aes-ce-ccm-core.S @@ -74,12 +74,13 @@ ENTRY(ce_aes_ccm_auth_data) beq 10f ext v0.16b, v0.16b, v0.16b, #1 /* rotate out the mac bytes */ b 7b -8: mov w7, w8 +8: cbz w8, 91f + mov w7, w8 add w8, w8, #16 9: ext v1.16b, v1.16b, v1.16b, #1 adds w7, w7, #1 bne 9b - eor v0.16b, v0.16b, v1.16b +91: eor v0.16b, v0.16b, v1.16b st1 {v0.16b}, [x0] 10: str w8, [x3] ret diff --git a/arch/arm64/crypto/aes-ce-ccm-glue.c b/arch/arm64/crypto/aes-ce-ccm-glue.c index 68b11aa690e4..5fc6f51908fd 100644 --- a/arch/arm64/crypto/aes-ce-ccm-glue.c +++ b/arch/arm64/crypto/aes-ce-ccm-glue.c @@ -125,7 +125,7 @@ static void ccm_update_mac(struct crypto_aes_ctx *key, u8 mac[], u8 const in[], abytes -= added; } - while (abytes > AES_BLOCK_SIZE) { + while (abytes >= AES_BLOCK_SIZE) { __aes_arm64_encrypt(key->key_enc, mac, mac, num_rounds(key)); crypto_xor(mac, in, AES_BLOCK_SIZE); @@ -139,8 +139,6 @@ static void ccm_update_mac(struct crypto_aes_ctx *key, u8 mac[], u8 const in[], num_rounds(key)); crypto_xor(mac, in, abytes); *macp = abytes; - } else { - *macp = 0; } } } @@ -255,7 +253,7 @@ static int ccm_encrypt(struct aead_request *req) /* preserve the original iv for the final round */ memcpy(buf, req->iv, AES_BLOCK_SIZE); - err = skcipher_walk_aead_encrypt(&walk, req, true); + err = skcipher_walk_aead_encrypt(&walk, req, false); if (may_use_simd()) { while (walk.nbytes) { @@ -313,7 +311,7 @@ static int ccm_decrypt(struct aead_request *req) /* preserve the original iv for the final round */ memcpy(buf, req->iv, AES_BLOCK_SIZE); - err = skcipher_walk_aead_decrypt(&walk, req, true); + err = skcipher_walk_aead_decrypt(&walk, req, false); if (may_use_simd()) { while (walk.nbytes) { diff --git a/arch/arm64/crypto/aes-modes.S b/arch/arm64/crypto/aes-modes.S index 67700045a0e0..4c7ce231963c 100644 --- a/arch/arm64/crypto/aes-modes.S +++ b/arch/arm64/crypto/aes-modes.S @@ -320,8 +320,7 @@ AES_ENTRY(aes_ctr_encrypt) .Lctrtailblock: st1 {v0.16b}, [x0] - ldp x29, x30, [sp], #16 - ret + b .Lctrout .Lctrcarry: umov x7, v4.d[0] /* load upper word of ctr */ diff --git a/arch/arm64/crypto/aes-neonbs-core.S b/arch/arm64/crypto/aes-neonbs-core.S index e613a87f8b53..8432c8d0dea6 100644 --- a/arch/arm64/crypto/aes-neonbs-core.S +++ b/arch/arm64/crypto/aes-neonbs-core.S @@ -971,18 +971,22 @@ CPU_LE( rev x8, x8 ) 8: next_ctr v0 st1 {v0.16b}, [x24] - cbz x23, 0f + cbz x23, .Lctr_done cond_yield_neon 98b b 99b -0: frame_pop +.Lctr_done: + frame_pop ret /* * If we are handling the tail of the input (x6 != NULL), return the * final keystream block back to the caller. */ +0: cbz x25, 8b + st1 {v0.16b}, [x25] + b 8b 1: cbz x25, 8b st1 {v1.16b}, [x25] b 8b diff --git a/arch/arm64/crypto/chacha-neon-core.S b/arch/arm64/crypto/chacha-neon-core.S index 021bb9e9784b..706c4e10e9e2 100644 --- a/arch/arm64/crypto/chacha-neon-core.S +++ b/arch/arm64/crypto/chacha-neon-core.S @@ -158,8 +158,8 @@ ENTRY(hchacha_block_neon) mov w3, w2 bl chacha_permute - st1 {v0.16b}, [x1], #16 - st1 {v3.16b}, [x1] + st1 {v0.4s}, [x1], #16 + st1 {v3.4s}, [x1] ldp x29, x30, [sp], #16 ret @@ -532,6 +532,10 @@ ENTRY(chacha_4block_xor_neon) add v3.4s, v3.4s, v19.4s add a2, a2, w8 add a3, a3, w9 +CPU_BE( rev a0, a0 ) +CPU_BE( rev a1, a1 ) +CPU_BE( rev a2, a2 ) +CPU_BE( rev a3, a3 ) ld4r {v24.4s-v27.4s}, [x0], #16 ld4r {v28.4s-v31.4s}, [x0] @@ -552,6 +556,10 @@ ENTRY(chacha_4block_xor_neon) add v7.4s, v7.4s, v23.4s add a6, a6, w8 add a7, a7, w9 +CPU_BE( rev a4, a4 ) +CPU_BE( rev a5, a5 ) +CPU_BE( rev a6, a6 ) +CPU_BE( rev a7, a7 ) // x8[0-3] += s2[0] // x9[0-3] += s2[1] @@ -569,6 +577,10 @@ ENTRY(chacha_4block_xor_neon) add v11.4s, v11.4s, v27.4s add a10, a10, w8 add a11, a11, w9 +CPU_BE( rev a8, a8 ) +CPU_BE( rev a9, a9 ) +CPU_BE( rev a10, a10 ) +CPU_BE( rev a11, a11 ) // x12[0-3] += s3[0] // x13[0-3] += s3[1] @@ -586,6 +598,10 @@ ENTRY(chacha_4block_xor_neon) add v15.4s, v15.4s, v31.4s add a14, a14, w8 add a15, a15, w9 +CPU_BE( rev a12, a12 ) +CPU_BE( rev a13, a13 ) +CPU_BE( rev a14, a14 ) +CPU_BE( rev a15, a15 ) // interleave 32-bit words in state n, n+1 ldp w6, w7, [x2], #64 diff --git a/arch/arm64/crypto/crct10dif-ce-core.S b/arch/arm64/crypto/crct10dif-ce-core.S index 9e82e8e8ed05..e545b42e6a46 100644 --- a/arch/arm64/crypto/crct10dif-ce-core.S +++ b/arch/arm64/crypto/crct10dif-ce-core.S @@ -2,12 +2,14 @@ // Accelerated CRC-T10DIF using arm64 NEON and Crypto Extensions instructions // // Copyright (C) 2016 Linaro Ltd <ard.biesheuvel@linaro.org> +// Copyright (C) 2019 Google LLC <ebiggers@google.com> // // This program is free software; you can redistribute it and/or modify // it under the terms of the GNU General Public License version 2 as // published by the Free Software Foundation. // +// Derived from the x86 version: // // Implement fast CRC-T10DIF computation with SSE and PCLMULQDQ instructions // @@ -54,19 +56,11 @@ // NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS // SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. // -// Function API: -// UINT16 crc_t10dif_pcl( -// UINT16 init_crc, //initial CRC value, 16 bits -// const unsigned char *buf, //buffer pointer to calculate CRC on -// UINT64 len //buffer length in bytes (64-bit data) -// ); -// // Reference paper titled "Fast CRC Computation for Generic // Polynomials Using PCLMULQDQ Instruction" // URL: http://www.intel.com/content/dam/www/public/us/en/documents // /white-papers/fast-crc-computation-generic-polynomials-pclmulqdq-paper.pdf // -// #include <linux/linkage.h> #include <asm/assembler.h> @@ -74,14 +68,14 @@ .text .cpu generic+crypto - arg1_low32 .req w19 - arg2 .req x20 - arg3 .req x21 + init_crc .req w19 + buf .req x20 + len .req x21 + fold_consts_ptr .req x22 - vzr .req v13 + fold_consts .req v10 ad .req v14 - bd .req v10 k00_16 .req v15 k32_48 .req v16 @@ -143,11 +137,11 @@ __pmull_p8_core: ext t5.8b, ad.8b, ad.8b, #2 // A2 ext t6.8b, ad.8b, ad.8b, #3 // A3 - pmull t4.8h, t4.8b, bd.8b // F = A1*B + pmull t4.8h, t4.8b, fold_consts.8b // F = A1*B pmull t8.8h, ad.8b, bd1.8b // E = A*B1 - pmull t5.8h, t5.8b, bd.8b // H = A2*B + pmull t5.8h, t5.8b, fold_consts.8b // H = A2*B pmull t7.8h, ad.8b, bd2.8b // G = A*B2 - pmull t6.8h, t6.8b, bd.8b // J = A3*B + pmull t6.8h, t6.8b, fold_consts.8b // J = A3*B pmull t9.8h, ad.8b, bd3.8b // I = A*B3 pmull t3.8h, ad.8b, bd4.8b // K = A*B4 b 0f @@ -157,11 +151,11 @@ __pmull_p8_core: tbl t5.16b, {ad.16b}, perm2.16b // A2 tbl t6.16b, {ad.16b}, perm3.16b // A3 - pmull2 t4.8h, t4.16b, bd.16b // F = A1*B + pmull2 t4.8h, t4.16b, fold_consts.16b // F = A1*B pmull2 t8.8h, ad.16b, bd1.16b // E = A*B1 - pmull2 t5.8h, t5.16b, bd.16b // H = A2*B + pmull2 t5.8h, t5.16b, fold_consts.16b // H = A2*B pmull2 t7.8h, ad.16b, bd2.16b // G = A*B2 - pmull2 t6.8h, t6.16b, bd.16b // J = A3*B + pmull2 t6.8h, t6.16b, fold_consts.16b // J = A3*B pmull2 t9.8h, ad.16b, bd3.16b // I = A*B3 pmull2 t3.8h, ad.16b, bd4.16b // K = A*B4 @@ -203,14 +197,14 @@ __pmull_p8_core: ENDPROC(__pmull_p8_core) .macro __pmull_p8, rq, ad, bd, i - .ifnc \bd, v10 + .ifnc \bd, fold_consts .err .endif mov ad.16b, \ad\().16b .ifb \i - pmull \rq\().8h, \ad\().8b, bd.8b // D = A*B + pmull \rq\().8h, \ad\().8b, \bd\().8b // D = A*B .else - pmull2 \rq\().8h, \ad\().16b, bd.16b // D = A*B + pmull2 \rq\().8h, \ad\().16b, \bd\().16b // D = A*B .endif bl .L__pmull_p8_core\i @@ -219,17 +213,19 @@ ENDPROC(__pmull_p8_core) eor \rq\().16b, \rq\().16b, t6.16b .endm - .macro fold64, p, reg1, reg2 - ldp q11, q12, [arg2], #0x20 + // Fold reg1, reg2 into the next 32 data bytes, storing the result back + // into reg1, reg2. + .macro fold_32_bytes, p, reg1, reg2 + ldp q11, q12, [buf], #0x20 - __pmull_\p v8, \reg1, v10, 2 - __pmull_\p \reg1, \reg1, v10 + __pmull_\p v8, \reg1, fold_consts, 2 + __pmull_\p \reg1, \reg1, fold_consts CPU_LE( rev64 v11.16b, v11.16b ) CPU_LE( rev64 v12.16b, v12.16b ) - __pmull_\p v9, \reg2, v10, 2 - __pmull_\p \reg2, \reg2, v10 + __pmull_\p v9, \reg2, fold_consts, 2 + __pmull_\p \reg2, \reg2, fold_consts CPU_LE( ext v11.16b, v11.16b, v11.16b, #8 ) CPU_LE( ext v12.16b, v12.16b, v12.16b, #8 ) @@ -240,15 +236,16 @@ CPU_LE( ext v12.16b, v12.16b, v12.16b, #8 ) eor \reg2\().16b, \reg2\().16b, v12.16b .endm - .macro fold16, p, reg, rk - __pmull_\p v8, \reg, v10 - __pmull_\p \reg, \reg, v10, 2 - .ifnb \rk - ldr_l q10, \rk, x8 - __pmull_pre_\p v10 + // Fold src_reg into dst_reg, optionally loading the next fold constants + .macro fold_16_bytes, p, src_reg, dst_reg, load_next_consts + __pmull_\p v8, \src_reg, fold_consts + __pmull_\p \src_reg, \src_reg, fold_consts, 2 + .ifnb \load_next_consts + ld1 {fold_consts.2d}, [fold_consts_ptr], #16 + __pmull_pre_\p fold_consts .endif - eor v7.16b, v7.16b, v8.16b - eor v7.16b, v7.16b, \reg\().16b + eor \dst_reg\().16b, \dst_reg\().16b, v8.16b + eor \dst_reg\().16b, \dst_reg\().16b, \src_reg\().16b .endm .macro __pmull_p64, rd, rn, rm, n @@ -260,40 +257,27 @@ CPU_LE( ext v12.16b, v12.16b, v12.16b, #8 ) .endm .macro crc_t10dif_pmull, p - frame_push 3, 128 + frame_push 4, 128 - mov arg1_low32, w0 - mov arg2, x1 - mov arg3, x2 - - movi vzr.16b, #0 // init zero register + mov init_crc, w0 + mov buf, x1 + mov len, x2 __pmull_init_\p - // adjust the 16-bit initial_crc value, scale it to 32 bits - lsl arg1_low32, arg1_low32, #16 - - // check if smaller than 256 - cmp arg3, #256 - - // for sizes less than 128, we can't fold 64B at a time... - b.lt .L_less_than_128_\@ + // For sizes less than 256 bytes, we can't fold 128 bytes at a time. + cmp len, #256 + b.lt .Lless_than_256_bytes_\@ - // load the initial crc value - // crc value does not need to be byte-reflected, but it needs - // to be moved to the high part of the register. - // because data will be byte-reflected and will align with - // initial crc at correct place. - movi v10.16b, #0 - mov v10.s[3], arg1_low32 // initial crc - - // receive the initial 64B data, xor the initial crc value - ldp q0, q1, [arg2] - ldp q2, q3, [arg2, #0x20] - ldp q4, q5, [arg2, #0x40] - ldp q6, q7, [arg2, #0x60] - add arg2, arg2, #0x80 + adr_l fold_consts_ptr, .Lfold_across_128_bytes_consts + // Load the first 128 data bytes. Byte swapping is necessary to make + // the bit order match the polynomial coefficient order. + ldp q0, q1, [buf] + ldp q2, q3, [buf, #0x20] + ldp q4, q5, [buf, #0x40] + ldp q6, q7, [buf, #0x60] + add buf, buf, #0x80 CPU_LE( rev64 v0.16b, v0.16b ) CPU_LE( rev64 v1.16b, v1.16b ) CPU_LE( rev64 v2.16b, v2.16b ) @@ -302,7 +286,6 @@ CPU_LE( rev64 v4.16b, v4.16b ) CPU_LE( rev64 v5.16b, v5.16b ) CPU_LE( rev64 v6.16b, v6.16b ) CPU_LE( rev64 v7.16b, v7.16b ) - CPU_LE( ext v0.16b, v0.16b, v0.16b, #8 ) CPU_LE( ext v1.16b, v1.16b, v1.16b, #8 ) CPU_LE( ext v2.16b, v2.16b, v2.16b, #8 ) @@ -312,36 +295,29 @@ CPU_LE( ext v5.16b, v5.16b, v5.16b, #8 ) CPU_LE( ext v6.16b, v6.16b, v6.16b, #8 ) CPU_LE( ext v7.16b, v7.16b, v7.16b, #8 ) - // XOR the initial_crc value - eor v0.16b, v0.16b, v10.16b - - ldr_l q10, rk3, x8 // xmm10 has rk3 and rk4 - // type of pmull instruction - // will determine which constant to use - __pmull_pre_\p v10 + // XOR the first 16 data *bits* with the initial CRC value. + movi v8.16b, #0 + mov v8.h[7], init_crc + eor v0.16b, v0.16b, v8.16b - // - // we subtract 256 instead of 128 to save one instruction from the loop - // - sub arg3, arg3, #256 + // Load the constants for folding across 128 bytes. + ld1 {fold_consts.2d}, [fold_consts_ptr] + __pmull_pre_\p fold_consts - // at this section of the code, there is 64*x+y (0<=y<64) bytes of - // buffer. The _fold_64_B_loop will fold 64B at a time - // until we have 64+y Bytes of buffer + // Subtract 128 for the 128 data bytes just consumed. Subtract another + // 128 to simplify the termination condition of the following loop. + sub len, len, #256 - // fold 64B at a time. This section of the code folds 4 vector - // registers in parallel -.L_fold_64_B_loop_\@: + // While >= 128 data bytes remain (not counting v0-v7), fold the 128 + // bytes v0-v7 into them, storing the result back into v0-v7. +.Lfold_128_bytes_loop_\@: + fold_32_bytes \p, v0, v1 + fold_32_bytes \p, v2, v3 + fold_32_bytes \p, v4, v5 + fold_32_bytes \p, v6, v7 - fold64 \p, v0, v1 - fold64 \p, v2, v3 - fold64 \p, v4, v5 - fold64 \p, v6, v7 - - subs arg3, arg3, #128 - - // check if there is another 64B in the buffer to be able to fold - b.lt .L_fold_64_B_end_\@ + subs len, len, #128 + b.lt .Lfold_128_bytes_loop_done_\@ if_will_cond_yield_neon stp q0, q1, [sp, #.Lframe_local_offset] @@ -353,228 +329,207 @@ CPU_LE( ext v7.16b, v7.16b, v7.16b, #8 ) ldp q2, q3, [sp, #.Lframe_local_offset + 32] ldp q4, q5, [sp, #.Lframe_local_offset + 64] ldp q6, q7, [sp, #.Lframe_local_offset + 96] - ldr_l q10, rk3, x8 - movi vzr.16b, #0 // init zero register + ld1 {fold_consts.2d}, [fold_consts_ptr] __pmull_init_\p - __pmull_pre_\p v10 + __pmull_pre_\p fold_consts endif_yield_neon - b .L_fold_64_B_loop_\@ - -.L_fold_64_B_end_\@: - // at this point, the buffer pointer is pointing at the last y Bytes - // of the buffer the 64B of folded data is in 4 of the vector - // registers: v0, v1, v2, v3 - - // fold the 8 vector registers to 1 vector register with different - // constants - - ldr_l q10, rk9, x8 - __pmull_pre_\p v10 - - fold16 \p, v0, rk11 - fold16 \p, v1, rk13 - fold16 \p, v2, rk15 - fold16 \p, v3, rk17 - fold16 \p, v4, rk19 - fold16 \p, v5, rk1 - fold16 \p, v6 - - // instead of 64, we add 48 to the loop counter to save 1 instruction - // from the loop instead of a cmp instruction, we use the negative - // flag with the jl instruction - adds arg3, arg3, #(128-16) - b.lt .L_final_reduction_for_128_\@ - - // now we have 16+y bytes left to reduce. 16 Bytes is in register v7 - // and the rest is in memory. We can fold 16 bytes at a time if y>=16 - // continue folding 16B at a time - -.L_16B_reduction_loop_\@: - __pmull_\p v8, v7, v10 - __pmull_\p v7, v7, v10, 2 + b .Lfold_128_bytes_loop_\@ + +.Lfold_128_bytes_loop_done_\@: + + // Now fold the 112 bytes in v0-v6 into the 16 bytes in v7. + + // Fold across 64 bytes. + add fold_consts_ptr, fold_consts_ptr, #16 + ld1 {fold_consts.2d}, [fold_consts_ptr], #16 + __pmull_pre_\p fold_consts + fold_16_bytes \p, v0, v4 + fold_16_bytes \p, v1, v5 + fold_16_bytes \p, v2, v6 + fold_16_bytes \p, v3, v7, 1 + // Fold across 32 bytes. + fold_16_bytes \p, v4, v6 + fold_16_bytes \p, v5, v7, 1 + // Fold across 16 bytes. + fold_16_bytes \p, v6, v7 + + // Add 128 to get the correct number of data bytes remaining in 0...127 + // (not counting v7), following the previous extra subtraction by 128. + // Then subtract 16 to simplify the termination condition of the + // following loop. + adds len, len, #(128-16) + + // While >= 16 data bytes remain (not counting v7), fold the 16 bytes v7 + // into them, storing the result back into v7. + b.lt .Lfold_16_bytes_loop_done_\@ +.Lfold_16_bytes_loop_\@: + __pmull_\p v8, v7, fold_consts + __pmull_\p v7, v7, fold_consts, 2 eor v7.16b, v7.16b, v8.16b - - ldr q0, [arg2], #16 + ldr q0, [buf], #16 CPU_LE( rev64 v0.16b, v0.16b ) CPU_LE( ext v0.16b, v0.16b, v0.16b, #8 ) eor v7.16b, v7.16b, v0.16b - subs arg3, arg3, #16 - - // instead of a cmp instruction, we utilize the flags with the - // jge instruction equivalent of: cmp arg3, 16-16 - // check if there is any more 16B in the buffer to be able to fold - b.ge .L_16B_reduction_loop_\@ - - // now we have 16+z bytes left to reduce, where 0<= z < 16. - // first, we reduce the data in the xmm7 register - -.L_final_reduction_for_128_\@: - // check if any more data to fold. If not, compute the CRC of - // the final 128 bits - adds arg3, arg3, #16 - b.eq .L_128_done_\@ - - // here we are getting data that is less than 16 bytes. - // since we know that there was data before the pointer, we can - // offset the input pointer before the actual point, to receive - // exactly 16 bytes. after that the registers need to be adjusted. -.L_get_last_two_regs_\@: - add arg2, arg2, arg3 - ldr q1, [arg2, #-16] -CPU_LE( rev64 v1.16b, v1.16b ) -CPU_LE( ext v1.16b, v1.16b, v1.16b, #8 ) - - // get rid of the extra data that was loaded before - // load the shift constant - adr_l x4, tbl_shf_table + 16 - sub x4, x4, arg3 - ld1 {v0.16b}, [x4] - - // shift v2 to the left by arg3 bytes - tbl v2.16b, {v7.16b}, v0.16b - - // shift v7 to the right by 16-arg3 bytes - movi v9.16b, #0x80 - eor v0.16b, v0.16b, v9.16b - tbl v7.16b, {v7.16b}, v0.16b - - // blend - sshr v0.16b, v0.16b, #7 // convert to 8-bit mask - bsl v0.16b, v2.16b, v1.16b - - // fold 16 Bytes - __pmull_\p v8, v7, v10 - __pmull_\p v7, v7, v10, 2 - eor v7.16b, v7.16b, v8.16b - eor v7.16b, v7.16b, v0.16b + subs len, len, #16 + b.ge .Lfold_16_bytes_loop_\@ + +.Lfold_16_bytes_loop_done_\@: + // Add 16 to get the correct number of data bytes remaining in 0...15 + // (not counting v7), following the previous extra subtraction by 16. + adds len, len, #16 + b.eq .Lreduce_final_16_bytes_\@ + +.Lhandle_partial_segment_\@: + // Reduce the last '16 + len' bytes where 1 <= len <= 15 and the first + // 16 bytes are in v7 and the rest are the remaining data in 'buf'. To + // do this without needing a fold constant for each possible 'len', + // redivide the bytes into a first chunk of 'len' bytes and a second + // chunk of 16 bytes, then fold the first chunk into the second. + + // v0 = last 16 original data bytes + add buf, buf, len + ldr q0, [buf, #-16] +CPU_LE( rev64 v0.16b, v0.16b ) +CPU_LE( ext v0.16b, v0.16b, v0.16b, #8 ) -.L_128_done_\@: - // compute crc of a 128-bit value - ldr_l q10, rk5, x8 // rk5 and rk6 in xmm10 - __pmull_pre_\p v10 + // v1 = high order part of second chunk: v7 left-shifted by 'len' bytes. + adr_l x4, .Lbyteshift_table + 16 + sub x4, x4, len + ld1 {v2.16b}, [x4] + tbl v1.16b, {v7.16b}, v2.16b - // 64b fold - ext v0.16b, vzr.16b, v7.16b, #8 - mov v7.d[0], v7.d[1] - __pmull_\p v7, v7, v10 - eor v7.16b, v7.16b, v0.16b + // v3 = first chunk: v7 right-shifted by '16-len' bytes. + movi v3.16b, #0x80 + eor v2.16b, v2.16b, v3.16b + tbl v3.16b, {v7.16b}, v2.16b - // 32b fold - ext v0.16b, v7.16b, vzr.16b, #4 - mov v7.s[3], vzr.s[0] - __pmull_\p v0, v0, v10, 2 - eor v7.16b, v7.16b, v0.16b + // Convert to 8-bit masks: 'len' 0x00 bytes, then '16-len' 0xff bytes. + sshr v2.16b, v2.16b, #7 - // barrett reduction - ldr_l q10, rk7, x8 - __pmull_pre_\p v10 - mov v0.d[0], v7.d[1] + // v2 = second chunk: 'len' bytes from v0 (low-order bytes), + // then '16-len' bytes from v1 (high-order bytes). + bsl v2.16b, v1.16b, v0.16b - __pmull_\p v0, v0, v10 - ext v0.16b, vzr.16b, v0.16b, #12 - __pmull_\p v0, v0, v10, 2 - ext v0.16b, vzr.16b, v0.16b, #12 + // Fold the first chunk into the second chunk, storing the result in v7. + __pmull_\p v0, v3, fold_consts + __pmull_\p v7, v3, fold_consts, 2 eor v7.16b, v7.16b, v0.16b - mov w0, v7.s[1] - -.L_cleanup_\@: - // scale the result back to 16 bits - lsr x0, x0, #16 + eor v7.16b, v7.16b, v2.16b + +.Lreduce_final_16_bytes_\@: + // Reduce the 128-bit value M(x), stored in v7, to the final 16-bit CRC. + + movi v2.16b, #0 // init zero register + + // Load 'x^48 * (x^48 mod G(x))' and 'x^48 * (x^80 mod G(x))'. + ld1 {fold_consts.2d}, [fold_consts_ptr], #16 + __pmull_pre_\p fold_consts + + // Fold the high 64 bits into the low 64 bits, while also multiplying by + // x^64. This produces a 128-bit value congruent to x^64 * M(x) and + // whose low 48 bits are 0. + ext v0.16b, v2.16b, v7.16b, #8 + __pmull_\p v7, v7, fold_consts, 2 // high bits * x^48 * (x^80 mod G(x)) + eor v0.16b, v0.16b, v7.16b // + low bits * x^64 + + // Fold the high 32 bits into the low 96 bits. This produces a 96-bit + // value congruent to x^64 * M(x) and whose low 48 bits are 0. + ext v1.16b, v0.16b, v2.16b, #12 // extract high 32 bits + mov v0.s[3], v2.s[0] // zero high 32 bits + __pmull_\p v1, v1, fold_consts // high 32 bits * x^48 * (x^48 mod G(x)) + eor v0.16b, v0.16b, v1.16b // + low bits + + // Load G(x) and floor(x^48 / G(x)). + ld1 {fold_consts.2d}, [fold_consts_ptr] + __pmull_pre_\p fold_consts + + // Use Barrett reduction to compute the final CRC value. + __pmull_\p v1, v0, fold_consts, 2 // high 32 bits * floor(x^48 / G(x)) + ushr v1.2d, v1.2d, #32 // /= x^32 + __pmull_\p v1, v1, fold_consts // *= G(x) + ushr v0.2d, v0.2d, #48 + eor v0.16b, v0.16b, v1.16b // + low 16 nonzero bits + // Final CRC value (x^16 * M(x)) mod G(x) is in low 16 bits of v0. + + umov w0, v0.h[0] frame_pop ret -.L_less_than_128_\@: - cbz arg3, .L_cleanup_\@ +.Lless_than_256_bytes_\@: + // Checksumming a buffer of length 16...255 bytes - movi v0.16b, #0 - mov v0.s[3], arg1_low32 // get the initial crc value + adr_l fold_consts_ptr, .Lfold_across_16_bytes_consts - ldr q7, [arg2], #0x10 + // Load the first 16 data bytes. + ldr q7, [buf], #0x10 CPU_LE( rev64 v7.16b, v7.16b ) CPU_LE( ext v7.16b, v7.16b, v7.16b, #8 ) - eor v7.16b, v7.16b, v0.16b // xor the initial crc value - - cmp arg3, #16 - b.eq .L_128_done_\@ // exactly 16 left - b.lt .L_less_than_16_left_\@ - - ldr_l q10, rk1, x8 // rk1 and rk2 in xmm10 - __pmull_pre_\p v10 - - // update the counter. subtract 32 instead of 16 to save one - // instruction from the loop - subs arg3, arg3, #32 - b.ge .L_16B_reduction_loop_\@ - - add arg3, arg3, #16 - b .L_get_last_two_regs_\@ - -.L_less_than_16_left_\@: - // shl r9, 4 - adr_l x0, tbl_shf_table + 16 - sub x0, x0, arg3 - ld1 {v0.16b}, [x0] - movi v9.16b, #0x80 - eor v0.16b, v0.16b, v9.16b - tbl v7.16b, {v7.16b}, v0.16b - b .L_128_done_\@ + + // XOR the first 16 data *bits* with the initial CRC value. + movi v0.16b, #0 + mov v0.h[7], init_crc + eor v7.16b, v7.16b, v0.16b + + // Load the fold-across-16-bytes constants. + ld1 {fold_consts.2d}, [fold_consts_ptr], #16 + __pmull_pre_\p fold_consts + + cmp len, #16 + b.eq .Lreduce_final_16_bytes_\@ // len == 16 + subs len, len, #32 + b.ge .Lfold_16_bytes_loop_\@ // 32 <= len <= 255 + add len, len, #16 + b .Lhandle_partial_segment_\@ // 17 <= len <= 31 .endm +// +// u16 crc_t10dif_pmull_p8(u16 init_crc, const u8 *buf, size_t len); +// +// Assumes len >= 16. +// ENTRY(crc_t10dif_pmull_p8) crc_t10dif_pmull p8 ENDPROC(crc_t10dif_pmull_p8) .align 5 +// +// u16 crc_t10dif_pmull_p64(u16 init_crc, const u8 *buf, size_t len); +// +// Assumes len >= 16. +// ENTRY(crc_t10dif_pmull_p64) crc_t10dif_pmull p64 ENDPROC(crc_t10dif_pmull_p64) -// precomputed constants -// these constants are precomputed from the poly: -// 0x8bb70000 (0x8bb7 scaled to 32 bits) .section ".rodata", "a" .align 4 -// Q = 0x18BB70000 -// rk1 = 2^(32*3) mod Q << 32 -// rk2 = 2^(32*5) mod Q << 32 -// rk3 = 2^(32*15) mod Q << 32 -// rk4 = 2^(32*17) mod Q << 32 -// rk5 = 2^(32*3) mod Q << 32 -// rk6 = 2^(32*2) mod Q << 32 -// rk7 = floor(2^64/Q) -// rk8 = Q - -rk1: .octa 0x06df0000000000002d56000000000000 -rk3: .octa 0x7cf50000000000009d9d000000000000 -rk5: .octa 0x13680000000000002d56000000000000 -rk7: .octa 0x000000018bb7000000000001f65a57f8 -rk9: .octa 0xbfd6000000000000ceae000000000000 -rk11: .octa 0x713c0000000000001e16000000000000 -rk13: .octa 0x80a6000000000000f7f9000000000000 -rk15: .octa 0xe658000000000000044c000000000000 -rk17: .octa 0xa497000000000000ad18000000000000 -rk19: .octa 0xe7b50000000000006ee3000000000000 - -tbl_shf_table: -// use these values for shift constants for the tbl/tbx instruction -// different alignments result in values as shown: -// DDQ 0x008f8e8d8c8b8a898887868584838281 # shl 15 (16-1) / shr1 -// DDQ 0x01008f8e8d8c8b8a8988878685848382 # shl 14 (16-3) / shr2 -// DDQ 0x0201008f8e8d8c8b8a89888786858483 # shl 13 (16-4) / shr3 -// DDQ 0x030201008f8e8d8c8b8a898887868584 # shl 12 (16-4) / shr4 -// DDQ 0x04030201008f8e8d8c8b8a8988878685 # shl 11 (16-5) / shr5 -// DDQ 0x0504030201008f8e8d8c8b8a89888786 # shl 10 (16-6) / shr6 -// DDQ 0x060504030201008f8e8d8c8b8a898887 # shl 9 (16-7) / shr7 -// DDQ 0x07060504030201008f8e8d8c8b8a8988 # shl 8 (16-8) / shr8 -// DDQ 0x0807060504030201008f8e8d8c8b8a89 # shl 7 (16-9) / shr9 -// DDQ 0x090807060504030201008f8e8d8c8b8a # shl 6 (16-10) / shr10 -// DDQ 0x0a090807060504030201008f8e8d8c8b # shl 5 (16-11) / shr11 -// DDQ 0x0b0a090807060504030201008f8e8d8c # shl 4 (16-12) / shr12 -// DDQ 0x0c0b0a090807060504030201008f8e8d # shl 3 (16-13) / shr13 -// DDQ 0x0d0c0b0a090807060504030201008f8e # shl 2 (16-14) / shr14 -// DDQ 0x0e0d0c0b0a090807060504030201008f # shl 1 (16-15) / shr15 +// Fold constants precomputed from the polynomial 0x18bb7 +// G(x) = x^16 + x^15 + x^11 + x^9 + x^8 + x^7 + x^5 + x^4 + x^2 + x^1 + x^0 +.Lfold_across_128_bytes_consts: + .quad 0x0000000000006123 // x^(8*128) mod G(x) + .quad 0x0000000000002295 // x^(8*128+64) mod G(x) +// .Lfold_across_64_bytes_consts: + .quad 0x0000000000001069 // x^(4*128) mod G(x) + .quad 0x000000000000dd31 // x^(4*128+64) mod G(x) +// .Lfold_across_32_bytes_consts: + .quad 0x000000000000857d // x^(2*128) mod G(x) + .quad 0x0000000000007acc // x^(2*128+64) mod G(x) +.Lfold_across_16_bytes_consts: + .quad 0x000000000000a010 // x^(1*128) mod G(x) + .quad 0x0000000000001faa // x^(1*128+64) mod G(x) +// .Lfinal_fold_consts: + .quad 0x1368000000000000 // x^48 * (x^48 mod G(x)) + .quad 0x2d56000000000000 // x^48 * (x^80 mod G(x)) +// .Lbarrett_reduction_consts: + .quad 0x0000000000018bb7 // G(x) + .quad 0x00000001f65a57f8 // floor(x^48 / G(x)) + +// For 1 <= len <= 15, the 16-byte vector beginning at &byteshift_table[16 - +// len] is the index vector to shift left by 'len' bytes, and is also {0x80, +// ..., 0x80} XOR the index vector to shift right by '16 - len' bytes. +.Lbyteshift_table: .byte 0x0, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87 .byte 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f .byte 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7 diff --git a/arch/arm64/crypto/crct10dif-ce-glue.c b/arch/arm64/crypto/crct10dif-ce-glue.c index b461d62023f2..dd325829ee44 100644 --- a/arch/arm64/crypto/crct10dif-ce-glue.c +++ b/arch/arm64/crypto/crct10dif-ce-glue.c @@ -22,10 +22,8 @@ #define CRC_T10DIF_PMULL_CHUNK_SIZE 16U -asmlinkage u16 crc_t10dif_pmull_p64(u16 init_crc, const u8 buf[], u64 len); -asmlinkage u16 crc_t10dif_pmull_p8(u16 init_crc, const u8 buf[], u64 len); - -static u16 (*crc_t10dif_pmull)(u16 init_crc, const u8 buf[], u64 len); +asmlinkage u16 crc_t10dif_pmull_p8(u16 init_crc, const u8 *buf, size_t len); +asmlinkage u16 crc_t10dif_pmull_p64(u16 init_crc, const u8 *buf, size_t len); static int crct10dif_init(struct shash_desc *desc) { @@ -35,30 +33,33 @@ static int crct10dif_init(struct shash_desc *desc) return 0; } -static int crct10dif_update(struct shash_desc *desc, const u8 *data, +static int crct10dif_update_pmull_p8(struct shash_desc *desc, const u8 *data, unsigned int length) { u16 *crc = shash_desc_ctx(desc); - unsigned int l; - if (unlikely((u64)data % CRC_T10DIF_PMULL_CHUNK_SIZE)) { - l = min_t(u32, length, CRC_T10DIF_PMULL_CHUNK_SIZE - - ((u64)data % CRC_T10DIF_PMULL_CHUNK_SIZE)); + if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE && may_use_simd()) { + kernel_neon_begin(); + *crc = crc_t10dif_pmull_p8(*crc, data, length); + kernel_neon_end(); + } else { + *crc = crc_t10dif_generic(*crc, data, length); + } - *crc = crc_t10dif_generic(*crc, data, l); + return 0; +} - length -= l; - data += l; - } +static int crct10dif_update_pmull_p64(struct shash_desc *desc, const u8 *data, + unsigned int length) +{ + u16 *crc = shash_desc_ctx(desc); - if (length > 0) { - if (may_use_simd()) { - kernel_neon_begin(); - *crc = crc_t10dif_pmull(*crc, data, length); - kernel_neon_end(); - } else { - *crc = crc_t10dif_generic(*crc, data, length); - } + if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE && may_use_simd()) { + kernel_neon_begin(); + *crc = crc_t10dif_pmull_p64(*crc, data, length); + kernel_neon_end(); + } else { + *crc = crc_t10dif_generic(*crc, data, length); } return 0; @@ -72,10 +73,22 @@ static int crct10dif_final(struct shash_desc *desc, u8 *out) return 0; } -static struct shash_alg crc_t10dif_alg = { +static struct shash_alg crc_t10dif_alg[] = {{ .digestsize = CRC_T10DIF_DIGEST_SIZE, .init = crct10dif_init, - .update = crct10dif_update, + .update = crct10dif_update_pmull_p8, + .final = crct10dif_final, + .descsize = CRC_T10DIF_DIGEST_SIZE, + + .base.cra_name = "crct10dif", + .base.cra_driver_name = "crct10dif-arm64-neon", + .base.cra_priority = 100, + .base.cra_blocksize = CRC_T10DIF_BLOCK_SIZE, + .base.cra_module = THIS_MODULE, +}, { + .digestsize = CRC_T10DIF_DIGEST_SIZE, + .init = crct10dif_init, + .update = crct10dif_update_pmull_p64, .final = crct10dif_final, .descsize = CRC_T10DIF_DIGEST_SIZE, @@ -84,21 +97,25 @@ static struct shash_alg crc_t10dif_alg = { .base.cra_priority = 200, .base.cra_blocksize = CRC_T10DIF_BLOCK_SIZE, .base.cra_module = THIS_MODULE, -}; +}}; static int __init crc_t10dif_mod_init(void) { if (elf_hwcap & HWCAP_PMULL) - crc_t10dif_pmull = crc_t10dif_pmull_p64; + return crypto_register_shashes(crc_t10dif_alg, + ARRAY_SIZE(crc_t10dif_alg)); else - crc_t10dif_pmull = crc_t10dif_pmull_p8; - - return crypto_register_shash(&crc_t10dif_alg); + /* only register the first array element */ + return crypto_register_shash(crc_t10dif_alg); } static void __exit crc_t10dif_mod_exit(void) { - crypto_unregister_shash(&crc_t10dif_alg); + if (elf_hwcap & HWCAP_PMULL) + crypto_unregister_shashes(crc_t10dif_alg, + ARRAY_SIZE(crc_t10dif_alg)); + else + crypto_unregister_shash(crc_t10dif_alg); } module_cpu_feature_match(ASIMD, crc_t10dif_mod_init); diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c index 067d8937d5af..791ad422c427 100644 --- a/arch/arm64/crypto/ghash-ce-glue.c +++ b/arch/arm64/crypto/ghash-ce-glue.c @@ -60,10 +60,6 @@ asmlinkage void pmull_ghash_update_p8(int blocks, u64 dg[], const char *src, struct ghash_key const *k, const char *head); -static void (*pmull_ghash_update)(int blocks, u64 dg[], const char *src, - struct ghash_key const *k, - const char *head); - asmlinkage void pmull_gcm_encrypt(int blocks, u64 dg[], u8 dst[], const u8 src[], struct ghash_key const *k, u8 ctr[], u32 const rk[], int rounds, @@ -87,11 +83,15 @@ static int ghash_init(struct shash_desc *desc) } static void ghash_do_update(int blocks, u64 dg[], const char *src, - struct ghash_key *key, const char *head) + struct ghash_key *key, const char *head, + void (*simd_update)(int blocks, u64 dg[], + const char *src, + struct ghash_key const *k, + const char *head)) { if (likely(may_use_simd())) { kernel_neon_begin(); - pmull_ghash_update(blocks, dg, src, key, head); + simd_update(blocks, dg, src, key, head); kernel_neon_end(); } else { be128 dst = { cpu_to_be64(dg[1]), cpu_to_be64(dg[0]) }; @@ -119,8 +119,12 @@ static void ghash_do_update(int blocks, u64 dg[], const char *src, /* avoid hogging the CPU for too long */ #define MAX_BLOCKS (SZ_64K / GHASH_BLOCK_SIZE) -static int ghash_update(struct shash_desc *desc, const u8 *src, - unsigned int len) +static int __ghash_update(struct shash_desc *desc, const u8 *src, + unsigned int len, + void (*simd_update)(int blocks, u64 dg[], + const char *src, + struct ghash_key const *k, + const char *head)) { struct ghash_desc_ctx *ctx = shash_desc_ctx(desc); unsigned int partial = ctx->count % GHASH_BLOCK_SIZE; @@ -146,7 +150,8 @@ static int ghash_update(struct shash_desc *desc, const u8 *src, int chunk = min(blocks, MAX_BLOCKS); ghash_do_update(chunk, ctx->digest, src, key, - partial ? ctx->buf : NULL); + partial ? ctx->buf : NULL, + simd_update); blocks -= chunk; src += chunk * GHASH_BLOCK_SIZE; @@ -158,7 +163,19 @@ static int ghash_update(struct shash_desc *desc, const u8 *src, return 0; } -static int ghash_final(struct shash_desc *desc, u8 *dst) +static int ghash_update_p8(struct shash_desc *desc, const u8 *src, + unsigned int len) +{ + return __ghash_update(desc, src, len, pmull_ghash_update_p8); +} + +static int ghash_update_p64(struct shash_desc *desc, const u8 *src, + unsigned int len) +{ + return __ghash_update(desc, src, len, pmull_ghash_update_p64); +} + +static int ghash_final_p8(struct shash_desc *desc, u8 *dst) { struct ghash_desc_ctx *ctx = shash_desc_ctx(desc); unsigned int partial = ctx->count % GHASH_BLOCK_SIZE; @@ -168,7 +185,28 @@ static int ghash_final(struct shash_desc *desc, u8 *dst) memset(ctx->buf + partial, 0, GHASH_BLOCK_SIZE - partial); - ghash_do_update(1, ctx->digest, ctx->buf, key, NULL); + ghash_do_update(1, ctx->digest, ctx->buf, key, NULL, + pmull_ghash_update_p8); + } + put_unaligned_be64(ctx->digest[1], dst); + put_unaligned_be64(ctx->digest[0], dst + 8); + + *ctx = (struct ghash_desc_ctx){}; + return 0; +} + +static int ghash_final_p64(struct shash_desc *desc, u8 *dst) +{ + struct ghash_desc_ctx *ctx = shash_desc_ctx(desc); + unsigned int partial = ctx->count % GHASH_BLOCK_SIZE; + + if (partial) { + struct ghash_key *key = crypto_shash_ctx(desc->tfm); + + memset(ctx->buf + partial, 0, GHASH_BLOCK_SIZE - partial); + + ghash_do_update(1, ctx->digest, ctx->buf, key, NULL, + pmull_ghash_update_p64); } put_unaligned_be64(ctx->digest[1], dst); put_unaligned_be64(ctx->digest[0], dst + 8); @@ -224,7 +262,21 @@ static int ghash_setkey(struct crypto_shash *tfm, return __ghash_setkey(key, inkey, keylen); } -static struct shash_alg ghash_alg = { +static struct shash_alg ghash_alg[] = {{ + .base.cra_name = "ghash", + .base.cra_driver_name = "ghash-neon", + .base.cra_priority = 100, + .base.cra_blocksize = GHASH_BLOCK_SIZE, + .base.cra_ctxsize = sizeof(struct ghash_key), + .base.cra_module = THIS_MODULE, + + .digestsize = GHASH_DIGEST_SIZE, + .init = ghash_init, + .update = ghash_update_p8, + .final = ghash_final_p8, + .setkey = ghash_setkey, + .descsize = sizeof(struct ghash_desc_ctx), +}, { .base.cra_name = "ghash", .base.cra_driver_name = "ghash-ce", .base.cra_priority = 200, @@ -234,11 +286,11 @@ static struct shash_alg ghash_alg = { .digestsize = GHASH_DIGEST_SIZE, .init = ghash_init, - .update = ghash_update, - .final = ghash_final, + .update = ghash_update_p64, + .final = ghash_final_p64, .setkey = ghash_setkey, .descsize = sizeof(struct ghash_desc_ctx), -}; +}}; static int num_rounds(struct crypto_aes_ctx *ctx) { @@ -301,7 +353,8 @@ static void gcm_update_mac(u64 dg[], const u8 *src, int count, u8 buf[], int blocks = count / GHASH_BLOCK_SIZE; ghash_do_update(blocks, dg, src, &ctx->ghash_key, - *buf_count ? buf : NULL); + *buf_count ? buf : NULL, + pmull_ghash_update_p64); src += blocks * GHASH_BLOCK_SIZE; count %= GHASH_BLOCK_SIZE; @@ -345,7 +398,8 @@ static void gcm_calculate_auth_mac(struct aead_request *req, u64 dg[]) if (buf_count) { memset(&buf[buf_count], 0, GHASH_BLOCK_SIZE - buf_count); - ghash_do_update(1, dg, buf, &ctx->ghash_key, NULL); + ghash_do_update(1, dg, buf, &ctx->ghash_key, NULL, + pmull_ghash_update_p64); } } @@ -358,7 +412,8 @@ static void gcm_final(struct aead_request *req, struct gcm_aes_ctx *ctx, lengths.a = cpu_to_be64(req->assoclen * 8); lengths.b = cpu_to_be64(cryptlen * 8); - ghash_do_update(1, dg, (void *)&lengths, &ctx->ghash_key, NULL); + ghash_do_update(1, dg, (void *)&lengths, &ctx->ghash_key, NULL, + pmull_ghash_update_p64); put_unaligned_be64(dg[1], mac); put_unaligned_be64(dg[0], mac + 8); @@ -434,7 +489,7 @@ static int gcm_encrypt(struct aead_request *req) ghash_do_update(walk.nbytes / AES_BLOCK_SIZE, dg, walk.dst.virt.addr, &ctx->ghash_key, - NULL); + NULL, pmull_ghash_update_p64); err = skcipher_walk_done(&walk, walk.nbytes % (2 * AES_BLOCK_SIZE)); @@ -469,7 +524,8 @@ static int gcm_encrypt(struct aead_request *req) memcpy(buf, dst, nbytes); memset(buf + nbytes, 0, GHASH_BLOCK_SIZE - nbytes); - ghash_do_update(!!nbytes, dg, buf, &ctx->ghash_key, head); + ghash_do_update(!!nbytes, dg, buf, &ctx->ghash_key, head, + pmull_ghash_update_p64); err = skcipher_walk_done(&walk, 0); } @@ -558,7 +614,8 @@ static int gcm_decrypt(struct aead_request *req) u8 *src = walk.src.virt.addr; ghash_do_update(blocks, dg, walk.src.virt.addr, - &ctx->ghash_key, NULL); + &ctx->ghash_key, NULL, + pmull_ghash_update_p64); do { __aes_arm64_encrypt(ctx->aes_key.key_enc, @@ -602,7 +659,8 @@ static int gcm_decrypt(struct aead_request *req) memcpy(buf, src, nbytes); memset(buf + nbytes, 0, GHASH_BLOCK_SIZE - nbytes); - ghash_do_update(!!nbytes, dg, buf, &ctx->ghash_key, head); + ghash_do_update(!!nbytes, dg, buf, &ctx->ghash_key, head, + pmull_ghash_update_p64); crypto_xor_cpy(walk.dst.virt.addr, walk.src.virt.addr, iv, walk.nbytes); @@ -650,26 +708,30 @@ static int __init ghash_ce_mod_init(void) return -ENODEV; if (elf_hwcap & HWCAP_PMULL) - pmull_ghash_update = pmull_ghash_update_p64; - + ret = crypto_register_shashes(ghash_alg, + ARRAY_SIZE(ghash_alg)); else - pmull_ghash_update = pmull_ghash_update_p8; + /* only register the first array element */ + ret = crypto_register_shash(ghash_alg); - ret = crypto_register_shash(&ghash_alg); if (ret) return ret; if (elf_hwcap & HWCAP_PMULL) { ret = crypto_register_aead(&gcm_aes_alg); if (ret) - crypto_unregister_shash(&ghash_alg); + crypto_unregister_shashes(ghash_alg, + ARRAY_SIZE(ghash_alg)); } return ret; } static void __exit ghash_ce_mod_exit(void) { - crypto_unregister_shash(&ghash_alg); + if (elf_hwcap & HWCAP_PMULL) + crypto_unregister_shashes(ghash_alg, ARRAY_SIZE(ghash_alg)); + else + crypto_unregister_shash(ghash_alg); crypto_unregister_aead(&gcm_aes_alg); } diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 7732d0ba4e60..da3fc7324d68 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -48,6 +48,7 @@ #define KVM_REQ_SLEEP \ KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_IRQ_PENDING KVM_ARCH_REQ(1) +#define KVM_REQ_VCPU_RESET KVM_ARCH_REQ(2) DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use); @@ -208,6 +209,13 @@ struct kvm_cpu_context { typedef struct kvm_cpu_context kvm_cpu_context_t; +struct vcpu_reset_state { + unsigned long pc; + unsigned long r0; + bool be; + bool reset; +}; + struct kvm_vcpu_arch { struct kvm_cpu_context ctxt; @@ -297,6 +305,9 @@ struct kvm_vcpu_arch { /* Virtual SError ESR to restore when HCR_EL2.VSE is set */ u64 vsesr_el2; + /* Additional reset state */ + struct vcpu_reset_state reset_state; + /* True when deferrable sysregs are loaded on the physical CPU, * see kvm_vcpu_load_sysregs and kvm_vcpu_put_sysregs. */ bool sysregs_loaded_on_cpu; diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index e1ec947e7c0c..0c656850eeea 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -332,6 +332,17 @@ static inline void *phys_to_virt(phys_addr_t x) #define virt_addr_valid(kaddr) \ (_virt_addr_is_linear(kaddr) && _virt_addr_valid(kaddr)) +/* + * Given that the GIC architecture permits ITS implementations that can only be + * configured with a LPI table address once, GICv3 systems with many CPUs may + * end up reserving a lot of different regions after a kexec for their LPI + * tables (one per CPU), as we are forced to reuse the same memory after kexec + * (and thus reserve it persistently with EFI beforehand) + */ +#if defined(CONFIG_EFI) && defined(CONFIG_ARM_GIC_V3_ITS) +# define INIT_MEMBLOCK_RESERVED_REGIONS (INIT_MEMBLOCK_REGIONS + NR_CPUS + 1) +#endif + #include <asm-generic/memory_model.h> #endif diff --git a/arch/arm64/include/asm/neon-intrinsics.h b/arch/arm64/include/asm/neon-intrinsics.h index 2ba6c6b9541f..71abfc7612b2 100644 --- a/arch/arm64/include/asm/neon-intrinsics.h +++ b/arch/arm64/include/asm/neon-intrinsics.h @@ -36,4 +36,8 @@ #include <arm_neon.h> #endif +#ifdef CONFIG_CC_IS_CLANG +#pragma clang diagnostic ignored "-Wincompatible-pointer-types" +#endif + #endif /* __ASM_NEON_INTRINSICS_H */ diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h index 547d7a0c9d05..f1e5c9165809 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -34,7 +34,6 @@ #include <asm/memory.h> #include <asm/extable.h> -#define get_ds() (KERNEL_DS) #define get_fs() (current_thread_info()->addr_limit) static inline void set_fs(mm_segment_t fs) diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 15d79a8e5e5e..eecf7927dab0 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -539,8 +539,7 @@ set_hcr: /* GICv3 system register access */ mrs x0, id_aa64pfr0_el1 ubfx x0, x0, #24, #4 - cmp x0, #1 - b.ne 3f + cbz x0, 3f mrs_s x0, SYS_ICC_SRE_EL2 orr x0, x0, #ICC_SRE_EL2_SRE // Set ICC_SRE_EL2.SRE==1 diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c index f2c211a6229b..58871333737a 100644 --- a/arch/arm64/kernel/machine_kexec_file.c +++ b/arch/arm64/kernel/machine_kexec_file.c @@ -120,10 +120,12 @@ static int create_dtb(struct kimage *image, { void *buf; size_t buf_size; + size_t cmdline_len; int ret; + cmdline_len = cmdline ? strlen(cmdline) : 0; buf_size = fdt_totalsize(initial_boot_params) - + strlen(cmdline) + DTB_EXTRA_SPACE; + + cmdline_len + DTB_EXTRA_SPACE; for (;;) { buf = vmalloc(buf_size); diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 9dce33b0e260..ddaea0fd2fa4 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -1702,19 +1702,20 @@ void syscall_trace_exit(struct pt_regs *regs) } /* - * SPSR_ELx bits which are always architecturally RES0 per ARM DDI 0487C.a - * We also take into account DIT (bit 24), which is not yet documented, and - * treat PAN and UAO as RES0 bits, as they are meaningless at EL0, and may be - * allocated an EL0 meaning in future. + * SPSR_ELx bits which are always architecturally RES0 per ARM DDI 0487D.a. + * We permit userspace to set SSBS (AArch64 bit 12, AArch32 bit 23) which is + * not described in ARM DDI 0487D.a. + * We treat PAN and UAO as RES0 bits, as they are meaningless at EL0, and may + * be allocated an EL0 meaning in future. * Userspace cannot use these until they have an architectural meaning. * Note that this follows the SPSR_ELx format, not the AArch32 PSR format. * We also reserve IL for the kernel; SS is handled dynamically. */ #define SPSR_EL1_AARCH64_RES0_BITS \ - (GENMASK_ULL(63,32) | GENMASK_ULL(27, 25) | GENMASK_ULL(23, 22) | \ - GENMASK_ULL(20, 10) | GENMASK_ULL(5, 5)) + (GENMASK_ULL(63, 32) | GENMASK_ULL(27, 25) | GENMASK_ULL(23, 22) | \ + GENMASK_ULL(20, 13) | GENMASK_ULL(11, 10) | GENMASK_ULL(5, 5)) #define SPSR_EL1_AARCH32_RES0_BITS \ - (GENMASK_ULL(63,32) | GENMASK_ULL(23, 22) | GENMASK_ULL(20,20)) + (GENMASK_ULL(63, 32) | GENMASK_ULL(22, 22) | GENMASK_ULL(20, 20)) static int valid_compat_regs(struct user_pt_regs *regs) { diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 4b0e1231625c..009849328289 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -313,7 +313,6 @@ void __init setup_arch(char **cmdline_p) arm64_memblock_init(); paging_init(); - efi_apply_persistent_mem_reservations(); acpi_table_upgrade(); @@ -340,6 +339,9 @@ void __init setup_arch(char **cmdline_p) smp_init_cpus(); smp_build_mpidr_hash(); + /* Init percpu seeds for random tags after cpus are set up. */ + kasan_init_tags(); + #ifdef CONFIG_ARM64_SW_TTBR0_PAN /* * Make sure init_thread_info.ttbr0 always generates translation diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index b0b1478094b4..421ebf6f7086 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -23,6 +23,7 @@ #include <kvm/arm_psci.h> #include <asm/cpufeature.h> +#include <asm/kprobes.h> #include <asm/kvm_asm.h> #include <asm/kvm_emulate.h> #include <asm/kvm_host.h> @@ -107,6 +108,7 @@ static void activate_traps_vhe(struct kvm_vcpu *vcpu) write_sysreg(kvm_get_hyp_vector(), vbar_el1); } +NOKPROBE_SYMBOL(activate_traps_vhe); static void __hyp_text __activate_traps_nvhe(struct kvm_vcpu *vcpu) { @@ -154,6 +156,7 @@ static void deactivate_traps_vhe(void) write_sysreg(CPACR_EL1_DEFAULT, cpacr_el1); write_sysreg(vectors, vbar_el1); } +NOKPROBE_SYMBOL(deactivate_traps_vhe); static void __hyp_text __deactivate_traps_nvhe(void) { @@ -513,6 +516,7 @@ int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) return exit_code; } +NOKPROBE_SYMBOL(kvm_vcpu_run_vhe); /* Switch to the guest for legacy non-VHE systems */ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu) @@ -620,6 +624,7 @@ static void __hyp_call_panic_vhe(u64 spsr, u64 elr, u64 par, read_sysreg_el2(esr), read_sysreg_el2(far), read_sysreg(hpfar_el2), par, vcpu); } +NOKPROBE_SYMBOL(__hyp_call_panic_vhe); void __hyp_text __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt) { diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c index 68d6f7c3b237..b426e2cf973c 100644 --- a/arch/arm64/kvm/hyp/sysreg-sr.c +++ b/arch/arm64/kvm/hyp/sysreg-sr.c @@ -18,6 +18,7 @@ #include <linux/compiler.h> #include <linux/kvm_host.h> +#include <asm/kprobes.h> #include <asm/kvm_asm.h> #include <asm/kvm_emulate.h> #include <asm/kvm_hyp.h> @@ -98,12 +99,14 @@ void sysreg_save_host_state_vhe(struct kvm_cpu_context *ctxt) { __sysreg_save_common_state(ctxt); } +NOKPROBE_SYMBOL(sysreg_save_host_state_vhe); void sysreg_save_guest_state_vhe(struct kvm_cpu_context *ctxt) { __sysreg_save_common_state(ctxt); __sysreg_save_el2_return_state(ctxt); } +NOKPROBE_SYMBOL(sysreg_save_guest_state_vhe); static void __hyp_text __sysreg_restore_common_state(struct kvm_cpu_context *ctxt) { @@ -188,12 +191,14 @@ void sysreg_restore_host_state_vhe(struct kvm_cpu_context *ctxt) { __sysreg_restore_common_state(ctxt); } +NOKPROBE_SYMBOL(sysreg_restore_host_state_vhe); void sysreg_restore_guest_state_vhe(struct kvm_cpu_context *ctxt) { __sysreg_restore_common_state(ctxt); __sysreg_restore_el2_return_state(ctxt); } +NOKPROBE_SYMBOL(sysreg_restore_guest_state_vhe); void __hyp_text __sysreg32_save_state(struct kvm_vcpu *vcpu) { diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index b72a3dd56204..f16a5f8ff2b4 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -32,6 +32,7 @@ #include <asm/kvm_arm.h> #include <asm/kvm_asm.h> #include <asm/kvm_coproc.h> +#include <asm/kvm_emulate.h> #include <asm/kvm_mmu.h> /* Maximum phys_shift supported for any VM on this host */ @@ -105,16 +106,33 @@ int kvm_arch_vm_ioctl_check_extension(struct kvm *kvm, long ext) * This function finds the right table above and sets the registers on * the virtual CPU struct to their architecturally defined reset * values. + * + * Note: This function can be called from two paths: The KVM_ARM_VCPU_INIT + * ioctl or as part of handling a request issued by another VCPU in the PSCI + * handling code. In the first case, the VCPU will not be loaded, and in the + * second case the VCPU will be loaded. Because this function operates purely + * on the memory-backed valus of system registers, we want to do a full put if + * we were loaded (handling a request) and load the values back at the end of + * the function. Otherwise we leave the state alone. In both cases, we + * disable preemption around the vcpu reset as we would otherwise race with + * preempt notifiers which also call put/load. */ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) { const struct kvm_regs *cpu_reset; + int ret = -EINVAL; + bool loaded; + + preempt_disable(); + loaded = (vcpu->cpu != -1); + if (loaded) + kvm_arch_vcpu_put(vcpu); switch (vcpu->arch.target) { default: if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) { if (!cpu_has_32bit_el1()) - return -EINVAL; + goto out; cpu_reset = &default_regs_reset32; } else { cpu_reset = &default_regs_reset; @@ -129,6 +147,29 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) /* Reset system registers */ kvm_reset_sys_regs(vcpu); + /* + * Additional reset state handling that PSCI may have imposed on us. + * Must be done after all the sys_reg reset. + */ + if (vcpu->arch.reset_state.reset) { + unsigned long target_pc = vcpu->arch.reset_state.pc; + + /* Gracefully handle Thumb2 entry point */ + if (vcpu_mode_is_32bit(vcpu) && (target_pc & 1)) { + target_pc &= ~1UL; + vcpu_set_thumb(vcpu); + } + + /* Propagate caller endianness */ + if (vcpu->arch.reset_state.be) + kvm_vcpu_set_be(vcpu); + + *vcpu_pc(vcpu) = target_pc; + vcpu_set_reg(vcpu, 0, vcpu->arch.reset_state.r0); + + vcpu->arch.reset_state.reset = false; + } + /* Reset PMU */ kvm_pmu_vcpu_reset(vcpu); @@ -137,7 +178,12 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) vcpu->arch.workaround_flags |= VCPU_WORKAROUND_2_FLAG; /* Reset timer */ - return kvm_timer_vcpu_reset(vcpu); + ret = kvm_timer_vcpu_reset(vcpu); +out: + if (loaded) + kvm_arch_vcpu_load(vcpu, smp_processor_id()); + preempt_enable(); + return ret; } void kvm_set_ipa_limit(void) diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index e3e37228ae4e..c936aa40c3f4 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -314,12 +314,29 @@ static bool trap_raz_wi(struct kvm_vcpu *vcpu, return read_zero(vcpu, p); } -static bool trap_undef(struct kvm_vcpu *vcpu, - struct sys_reg_params *p, - const struct sys_reg_desc *r) +/* + * ARMv8.1 mandates at least a trivial LORegion implementation, where all the + * RW registers are RES0 (which we can implement as RAZ/WI). On an ARMv8.0 + * system, these registers should UNDEF. LORID_EL1 being a RO register, we + * treat it separately. + */ +static bool trap_loregion(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *r) { - kvm_inject_undefined(vcpu); - return false; + u64 val = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1); + u32 sr = sys_reg((u32)r->Op0, (u32)r->Op1, + (u32)r->CRn, (u32)r->CRm, (u32)r->Op2); + + if (!(val & (0xfUL << ID_AA64MMFR1_LOR_SHIFT))) { + kvm_inject_undefined(vcpu); + return false; + } + + if (p->is_write && sr == SYS_LORID_EL1) + return write_to_read_only(vcpu, p, r); + + return trap_raz_wi(vcpu, p, r); } static bool trap_oslsr_el1(struct kvm_vcpu *vcpu, @@ -1048,11 +1065,6 @@ static u64 read_id_reg(struct sys_reg_desc const *r, bool raz) if (val & ptrauth_mask) kvm_debug("ptrauth unsupported for guests, suppressing\n"); val &= ~ptrauth_mask; - } else if (id == SYS_ID_AA64MMFR1_EL1) { - if (val & (0xfUL << ID_AA64MMFR1_LOR_SHIFT)) - kvm_debug("LORegions unsupported for guests, suppressing\n"); - - val &= ~(0xfUL << ID_AA64MMFR1_LOR_SHIFT); } return val; @@ -1338,11 +1350,11 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_MAIR_EL1), access_vm_reg, reset_unknown, MAIR_EL1 }, { SYS_DESC(SYS_AMAIR_EL1), access_vm_reg, reset_amair_el1, AMAIR_EL1 }, - { SYS_DESC(SYS_LORSA_EL1), trap_undef }, - { SYS_DESC(SYS_LOREA_EL1), trap_undef }, - { SYS_DESC(SYS_LORN_EL1), trap_undef }, - { SYS_DESC(SYS_LORC_EL1), trap_undef }, - { SYS_DESC(SYS_LORID_EL1), trap_undef }, + { SYS_DESC(SYS_LORSA_EL1), trap_loregion }, + { SYS_DESC(SYS_LOREA_EL1), trap_loregion }, + { SYS_DESC(SYS_LORN_EL1), trap_loregion }, + { SYS_DESC(SYS_LORC_EL1), trap_loregion }, + { SYS_DESC(SYS_LORID_EL1), trap_loregion }, { SYS_DESC(SYS_VBAR_EL1), NULL, reset_val, VBAR_EL1, 0 }, { SYS_DESC(SYS_DISR_EL1), NULL, reset_val, DISR_EL1, 0 }, @@ -2596,7 +2608,9 @@ void kvm_reset_sys_regs(struct kvm_vcpu *vcpu) table = get_target_table(vcpu->arch.target, true, &num); reset_sys_reg_descs(vcpu, table, num); - for (num = 1; num < NR_SYS_REGS; num++) - if (__vcpu_sys_reg(vcpu, num) == 0x4242424242424242) - panic("Didn't reset __vcpu_sys_reg(%zi)", num); + for (num = 1; num < NR_SYS_REGS; num++) { + if (WARN(__vcpu_sys_reg(vcpu, num) == 0x4242424242424242, + "Didn't reset __vcpu_sys_reg(%zi)\n", num)) + break; + } } diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c index fcb1f2a6d7c6..99bb8facb5cb 100644 --- a/arch/arm64/mm/dump.c +++ b/arch/arm64/mm/dump.c @@ -286,74 +286,73 @@ static void note_page(struct pg_state *st, unsigned long addr, unsigned level, } -static void walk_pte(struct pg_state *st, pmd_t *pmdp, unsigned long start) +static void walk_pte(struct pg_state *st, pmd_t *pmdp, unsigned long start, + unsigned long end) { - pte_t *ptep = pte_offset_kernel(pmdp, 0UL); - unsigned long addr; - unsigned i; + unsigned long addr = start; + pte_t *ptep = pte_offset_kernel(pmdp, start); - for (i = 0; i < PTRS_PER_PTE; i++, ptep++) { - addr = start + i * PAGE_SIZE; + do { note_page(st, addr, 4, READ_ONCE(pte_val(*ptep))); - } + } while (ptep++, addr += PAGE_SIZE, addr != end); } -static void walk_pmd(struct pg_state *st, pud_t *pudp, unsigned long start) +static void walk_pmd(struct pg_state *st, pud_t *pudp, unsigned long start, + unsigned long end) { - pmd_t *pmdp = pmd_offset(pudp, 0UL); - unsigned long addr; - unsigned i; + unsigned long next, addr = start; + pmd_t *pmdp = pmd_offset(pudp, start); - for (i = 0; i < PTRS_PER_PMD; i++, pmdp++) { + do { pmd_t pmd = READ_ONCE(*pmdp); + next = pmd_addr_end(addr, end); - addr = start + i * PMD_SIZE; if (pmd_none(pmd) || pmd_sect(pmd)) { note_page(st, addr, 3, pmd_val(pmd)); } else { BUG_ON(pmd_bad(pmd)); - walk_pte(st, pmdp, addr); + walk_pte(st, pmdp, addr, next); } - } + } while (pmdp++, addr = next, addr != end); } -static void walk_pud(struct pg_state *st, pgd_t *pgdp, unsigned long start) +static void walk_pud(struct pg_state *st, pgd_t *pgdp, unsigned long start, + unsigned long end) { - pud_t *pudp = pud_offset(pgdp, 0UL); - unsigned long addr; - unsigned i; + unsigned long next, addr = start; + pud_t *pudp = pud_offset(pgdp, start); - for (i = 0; i < PTRS_PER_PUD; i++, pudp++) { + do { pud_t pud = READ_ONCE(*pudp); + next = pud_addr_end(addr, end); - addr = start + i * PUD_SIZE; if (pud_none(pud) || pud_sect(pud)) { note_page(st, addr, 2, pud_val(pud)); } else { BUG_ON(pud_bad(pud)); - walk_pmd(st, pudp, addr); + walk_pmd(st, pudp, addr, next); } - } + } while (pudp++, addr = next, addr != end); } static void walk_pgd(struct pg_state *st, struct mm_struct *mm, unsigned long start) { - pgd_t *pgdp = pgd_offset(mm, 0UL); - unsigned i; - unsigned long addr; + unsigned long end = (start < TASK_SIZE_64) ? TASK_SIZE_64 : 0; + unsigned long next, addr = start; + pgd_t *pgdp = pgd_offset(mm, start); - for (i = 0; i < PTRS_PER_PGD; i++, pgdp++) { + do { pgd_t pgd = READ_ONCE(*pgdp); + next = pgd_addr_end(addr, end); - addr = start + i * PGDIR_SIZE; if (pgd_none(pgd)) { note_page(st, addr, 1, pgd_val(pgd)); } else { BUG_ON(pgd_bad(pgd)); - walk_pud(st, pgdp, addr); + walk_pud(st, pgdp, addr, next); } - } + } while (pgdp++, addr = next, addr != end); } void ptdump_walk_pgd(struct seq_file *m, struct ptdump_info *info) diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c index 4b55b15707a3..f37a86d2a69d 100644 --- a/arch/arm64/mm/kasan_init.c +++ b/arch/arm64/mm/kasan_init.c @@ -252,8 +252,6 @@ void __init kasan_init(void) memset(kasan_early_shadow_page, KASAN_SHADOW_INIT, PAGE_SIZE); cpu_replace_ttbr1(lm_alias(swapper_pg_dir)); - kasan_init_tags(); - /* At this point kasan is fully initialized. Enable error messages */ init_task.kasan_depth = 0; pr_info("KernelAddressSanitizer initialized\n"); diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 1542df00b23c..aaddc0217e73 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -362,7 +362,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, const s16 off = insn->off; const s32 imm = insn->imm; const int i = insn - ctx->prog->insnsi; - const bool is64 = BPF_CLASS(code) == BPF_ALU64; + const bool is64 = BPF_CLASS(code) == BPF_ALU64 || + BPF_CLASS(code) == BPF_JMP; const bool isdw = BPF_SIZE(code) == BPF_DW; u8 jmp_cond; s32 jmp_offset; @@ -559,7 +560,17 @@ emit_bswap_uxt: case BPF_JMP | BPF_JSLT | BPF_X: case BPF_JMP | BPF_JSGE | BPF_X: case BPF_JMP | BPF_JSLE | BPF_X: - emit(A64_CMP(1, dst, src), ctx); + case BPF_JMP32 | BPF_JEQ | BPF_X: + case BPF_JMP32 | BPF_JGT | BPF_X: + case BPF_JMP32 | BPF_JLT | BPF_X: + case BPF_JMP32 | BPF_JGE | BPF_X: + case BPF_JMP32 | BPF_JLE | BPF_X: + case BPF_JMP32 | BPF_JNE | BPF_X: + case BPF_JMP32 | BPF_JSGT | BPF_X: + case BPF_JMP32 | BPF_JSLT | BPF_X: + case BPF_JMP32 | BPF_JSGE | BPF_X: + case BPF_JMP32 | BPF_JSLE | BPF_X: + emit(A64_CMP(is64, dst, src), ctx); emit_cond_jmp: jmp_offset = bpf2a64_offset(i + off, i, ctx); check_imm19(jmp_offset); @@ -601,7 +612,8 @@ emit_cond_jmp: emit(A64_B_(jmp_cond, jmp_offset), ctx); break; case BPF_JMP | BPF_JSET | BPF_X: - emit(A64_TST(1, dst, src), ctx); + case BPF_JMP32 | BPF_JSET | BPF_X: + emit(A64_TST(is64, dst, src), ctx); goto emit_cond_jmp; /* IF (dst COND imm) JUMP off */ case BPF_JMP | BPF_JEQ | BPF_K: @@ -614,12 +626,23 @@ emit_cond_jmp: case BPF_JMP | BPF_JSLT | BPF_K: case BPF_JMP | BPF_JSGE | BPF_K: case BPF_JMP | BPF_JSLE | BPF_K: - emit_a64_mov_i(1, tmp, imm, ctx); - emit(A64_CMP(1, dst, tmp), ctx); + case BPF_JMP32 | BPF_JEQ | BPF_K: + case BPF_JMP32 | BPF_JGT | BPF_K: + case BPF_JMP32 | BPF_JLT | BPF_K: + case BPF_JMP32 | BPF_JGE | BPF_K: + case BPF_JMP32 | BPF_JLE | BPF_K: + case BPF_JMP32 | BPF_JNE | BPF_K: + case BPF_JMP32 | BPF_JSGT | BPF_K: + case BPF_JMP32 | BPF_JSLT | BPF_K: + case BPF_JMP32 | BPF_JSGE | BPF_K: + case BPF_JMP32 | BPF_JSLE | BPF_K: + emit_a64_mov_i(is64, tmp, imm, ctx); + emit(A64_CMP(is64, dst, tmp), ctx); goto emit_cond_jmp; case BPF_JMP | BPF_JSET | BPF_K: - emit_a64_mov_i(1, tmp, imm, ctx); - emit(A64_TST(1, dst, tmp), ctx); + case BPF_JMP32 | BPF_JSET | BPF_K: + emit_a64_mov_i(is64, tmp, imm, ctx); + emit(A64_TST(is64, dst, tmp), ctx); goto emit_cond_jmp; /* function call */ case BPF_JMP | BPF_CALL: |