diff options
Diffstat (limited to 'arch/arm64')
65 files changed, 587 insertions, 352 deletions
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index e296ae3e20f4..e76f74874a42 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -450,7 +450,7 @@ config ARM64_ERRATUM_1024718 help This option adds work around for Arm Cortex-A55 Erratum 1024718. - Affected Cortex-A55 cores (r0p0, r0p1, r1p0) could cause incorrect + Affected Cortex-A55 cores (all revisions) could cause incorrect update of the hardware dirty bit when the DBM/AP bits are updated without a break-before-make. The work around is to disable the usage of hardware DBM locally on the affected cores. CPUs not affected by diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms index 456d21542250..cdfd37c7fb67 100644 --- a/arch/arm64/Kconfig.platforms +++ b/arch/arm64/Kconfig.platforms @@ -46,6 +46,7 @@ config ARCH_BCM_IPROC config ARCH_BERLIN bool "Marvell Berlin SoC Family" select DW_APB_ICTL + select DW_APB_TIMER_OF select GPIOLIB select PINCTRL help diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 8c4bc5a2c61f..5efb4e095069 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -10,7 +10,7 @@ # # Copyright (C) 1995-2001 by Russell King -LDFLAGS_vmlinux :=--no-undefined -X +LDFLAGS_vmlinux :=--no-undefined -X -z norelro CPPFLAGS_vmlinux.lds = -DTEXT_OFFSET=$(TEXT_OFFSET) GZFLAGS :=-9 @@ -18,7 +18,7 @@ ifeq ($(CONFIG_RELOCATABLE), y) # Pass --no-apply-dynamic-relocs to restore pre-binutils-2.27 behaviour # for relative relocs, since this leads to better Image compression # with the relocation offsets always being zero. -LDFLAGS_vmlinux += -shared -Bsymbolic -z notext -z norelro \ +LDFLAGS_vmlinux += -shared -Bsymbolic -z notext \ $(call ld-option, --no-apply-dynamic-relocs) endif diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi index 3c3057944960..3ee6c4bae08f 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi @@ -245,6 +245,11 @@ }; }; +&hwrng { + clocks = <&clkc CLKID_RNG0>; + clock-names = "core"; +}; + &i2c_A { clocks = <&clkc CLKID_I2C>; }; diff --git a/arch/arm64/boot/dts/arm/juno-base.dtsi b/arch/arm64/boot/dts/arm/juno-base.dtsi index 13ee8ffa9bbf..76902ea7288f 100644 --- a/arch/arm64/boot/dts/arm/juno-base.dtsi +++ b/arch/arm64/boot/dts/arm/juno-base.dtsi @@ -513,13 +513,13 @@ clocks { compatible = "arm,scpi-clocks"; - scpi_dvfs: scpi-dvfs { + scpi_dvfs: clocks-0 { compatible = "arm,scpi-dvfs-clocks"; #clock-cells = <1>; clock-indices = <0>, <1>, <2>; clock-output-names = "atlclk", "aplclk","gpuclk"; }; - scpi_clk: scpi-clk { + scpi_clk: clocks-1 { compatible = "arm,scpi-variable-clocks"; #clock-cells = <1>; clock-indices = <3>; @@ -527,7 +527,7 @@ }; }; - scpi_devpd: scpi-power-domains { + scpi_devpd: power-controller { compatible = "arm,scpi-power-domains"; num-domains = <2>; #power-domain-cells = <1>; diff --git a/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi b/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi index 0b72094bcf5a..05f82819ae2d 100644 --- a/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi +++ b/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi @@ -745,7 +745,7 @@ }; qspi: spi@66470200 { - compatible = "brcm,spi-bcm-qspi", "brcm,spi-ns2-qspi"; + compatible = "brcm,spi-ns2-qspi", "brcm,spi-bcm-qspi"; reg = <0x66470200 0x184>, <0x66470000 0x124>, <0x67017408 0x004>, diff --git a/arch/arm64/boot/dts/exynos/exynos5433-tm2-common.dtsi b/arch/arm64/boot/dts/exynos/exynos5433-tm2-common.dtsi index 297597442c44..7de6a187ba8f 100644 --- a/arch/arm64/boot/dts/exynos/exynos5433-tm2-common.dtsi +++ b/arch/arm64/boot/dts/exynos/exynos5433-tm2-common.dtsi @@ -343,7 +343,7 @@ s2mps13-pmic@66 { compatible = "samsung,s2mps13-pmic"; interrupt-parent = <&gpa0>; - interrupts = <7 IRQ_TYPE_NONE>; + interrupts = <7 IRQ_TYPE_LEVEL_LOW>; reg = <0x66>; samsung,s2mps11-wrstbi-ground; diff --git a/arch/arm64/boot/dts/exynos/exynos7-espresso.dts b/arch/arm64/boot/dts/exynos/exynos7-espresso.dts index 4a8b1fb51243..a85ad9f55cda 100644 --- a/arch/arm64/boot/dts/exynos/exynos7-espresso.dts +++ b/arch/arm64/boot/dts/exynos/exynos7-espresso.dts @@ -88,7 +88,7 @@ s2mps15_pmic@66 { compatible = "samsung,s2mps15-pmic"; reg = <0x66>; - interrupts = <2 IRQ_TYPE_NONE>; + interrupts = <2 IRQ_TYPE_LEVEL_LOW>; interrupt-parent = <&gpa0>; pinctrl-names = "default"; pinctrl-0 = <&pmic_irq>; @@ -155,6 +155,7 @@ regulator-min-microvolt = <700000>; regulator-max-microvolt = <1150000>; regulator-enable-ramp-delay = <125>; + regulator-always-on; }; ldo8_reg: LDO8 { diff --git a/arch/arm64/boot/dts/exynos/exynos7.dtsi b/arch/arm64/boot/dts/exynos/exynos7.dtsi index 9a3fbed1765a..331dcf94acf0 100644 --- a/arch/arm64/boot/dts/exynos/exynos7.dtsi +++ b/arch/arm64/boot/dts/exynos/exynos7.dtsi @@ -65,8 +65,10 @@ }; psci { - compatible = "arm,psci-0.2"; + compatible = "arm,psci"; method = "smc"; + cpu_off = <0x84000002>; + cpu_on = <0xC4000003>; }; soc: soc { @@ -92,7 +94,7 @@ #address-cells = <0>; interrupt-controller; reg = <0x11001000 0x1000>, - <0x11002000 0x1000>, + <0x11002000 0x2000>, <0x11004000 0x2000>, <0x11006000 0x2000>; }; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1012a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1012a.dtsi index df83915d6ea6..2bdd787190c9 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1012a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1012a.dtsi @@ -164,6 +164,7 @@ ranges = <0x0 0x00 0x1700000 0x100000>; reg = <0x00 0x1700000 0x0 0x100000>; interrupts = <GIC_SPI 75 IRQ_TYPE_LEVEL_HIGH>; + dma-coherent; sec_jr0: jr@10000 { compatible = "fsl,sec-v5.4-job-ring", diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi index d16b9cc1e825..990b576b2b7b 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi @@ -219,6 +219,7 @@ ranges = <0x0 0x00 0x1700000 0x100000>; reg = <0x00 0x1700000 0x0 0x100000>; interrupts = <0 75 0x4>; + dma-coherent; sec_jr0: jr@10000 { compatible = "fsl,sec-v5.4-job-ring", diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi index c8ff0baddf1d..24bee3b7f3ee 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi @@ -244,6 +244,7 @@ ranges = <0x0 0x00 0x1700000 0x100000>; reg = <0x00 0x1700000 0x0 0x100000>; interrupts = <GIC_SPI 75 IRQ_TYPE_LEVEL_HIGH>; + dma-coherent; sec_jr0: jr@10000 { compatible = "fsl,sec-v5.4-job-ring", @@ -304,7 +305,7 @@ dcfg: dcfg@1ee0000 { compatible = "fsl,ls1046a-dcfg", "syscon"; - reg = <0x0 0x1ee0000 0x0 0x10000>; + reg = <0x0 0x1ee0000 0x0 0x1000>; big-endian; }; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi index 4fb9a0966a84..4b459167a746 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi @@ -515,7 +515,6 @@ clocks = <&clockgen 4 3>; clock-names = "dspi"; spi-num-chipselects = <5>; - bus-num = <0>; }; esdhc: esdhc@2140000 { diff --git a/arch/arm64/boot/dts/hisilicon/hi3660-hikey960.dts b/arch/arm64/boot/dts/hisilicon/hi3660-hikey960.dts index e9f87cb61ade..8587912e1eb0 100644 --- a/arch/arm64/boot/dts/hisilicon/hi3660-hikey960.dts +++ b/arch/arm64/boot/dts/hisilicon/hi3660-hikey960.dts @@ -210,6 +210,17 @@ status = "ok"; compatible = "adi,adv7533"; reg = <0x39>; + adi,dsi-lanes = <4>; + ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + }; + port@1 { + reg = <1>; + }; + }; }; }; diff --git a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts index 6887cc1a743d..f78e6468b02f 100644 --- a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts +++ b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts @@ -513,7 +513,7 @@ reg = <0x39>; interrupt-parent = <&gpio1>; interrupts = <1 2>; - pd-gpio = <&gpio0 4 0>; + pd-gpios = <&gpio0 4 0>; adi,dsi-lanes = <4>; #sound-dai-cells = <0>; diff --git a/arch/arm64/boot/dts/marvell/armada-3720-db.dts b/arch/arm64/boot/dts/marvell/armada-3720-db.dts index 9df0f06ce607..0a0e9e19e879 100644 --- a/arch/arm64/boot/dts/marvell/armada-3720-db.dts +++ b/arch/arm64/boot/dts/marvell/armada-3720-db.dts @@ -155,6 +155,9 @@ /* CON15(V2.0)/CON17(V1.4) : PCIe / CON15(V2.0)/CON12(V1.4) :mini-PCIe */ &pcie0 { + pinctrl-names = "default"; + pinctrl-0 = <&pcie_reset_pins &pcie_clkreq_pins>; + reset-gpios = <&gpiosb 3 GPIO_ACTIVE_LOW>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dts b/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dts index 2ce52ba74f73..89c7385390f4 100644 --- a/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dts +++ b/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dts @@ -52,6 +52,10 @@ model = "Globalscale Marvell ESPRESSOBin Board"; compatible = "globalscale,espressobin", "marvell,armada3720", "marvell,armada3710"; + aliases { + ethernet0 = ð0; + }; + chosen { stdout-path = "serial0:115200n8"; }; @@ -78,6 +82,9 @@ /* J9 */ &pcie0 { + pinctrl-names = "default"; + pinctrl-0 = <&pcie_reset_pins &pcie_clkreq_pins>; + reset-gpios = <&gpiosb 3 GPIO_ACTIVE_LOW>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi index b554cdaf5e53..b369356e7419 100644 --- a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi @@ -239,6 +239,15 @@ function = "mii"; }; + pcie_reset_pins: pcie-reset-pins { + groups = "pcie1"; + function = "gpio"; + }; + + pcie_clkreq_pins: pcie-clkreq-pins { + groups = "pcie1_clkreq"; + function = "pcie"; + }; }; eth0: ethernet@30000 { @@ -347,8 +356,15 @@ #interrupt-cells = <1>; msi-parent = <&pcie0>; msi-controller; - ranges = <0x82000000 0 0xe8000000 0 0xe8000000 0 0x1000000 /* Port 0 MEM */ - 0x81000000 0 0xe9000000 0 0xe9000000 0 0x10000>; /* Port 0 IO*/ + /* + * The 128 MiB address range [0xe8000000-0xf0000000] is + * dedicated for PCIe and can be assigned to 8 windows + * with size a power of two. Use one 64 KiB window for + * IO at the end and the remaining seven windows + * (totaling 127 MiB) for MEM. + */ + ranges = <0x82000000 0 0xe8000000 0 0xe8000000 0 0x07f00000 /* Port 0 MEM */ + 0x81000000 0 0xefff0000 0 0xefff0000 0 0x00010000>; /* Port 0 IO */ interrupt-map-mask = <0 0 0 7>; interrupt-map = <0 0 0 1 &pcie_intc 0>, <0 0 0 2 &pcie_intc 1>, diff --git a/arch/arm64/boot/dts/mediatek/mt8173.dtsi b/arch/arm64/boot/dts/mediatek/mt8173.dtsi index da64e1cab233..a21210ff9686 100644 --- a/arch/arm64/boot/dts/mediatek/mt8173.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8173.dtsi @@ -1029,7 +1029,7 @@ <&mmsys CLK_MM_DSI1_DIGITAL>, <&mipi_tx1>; clock-names = "engine", "digital", "hs"; - phy = <&mipi_tx1>; + phys = <&mipi_tx1>; phy-names = "dphy"; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/nvidia/tegra210.dtsi b/arch/arm64/boot/dts/nvidia/tegra210.dtsi index 466199766848..979af7a7848b 100644 --- a/arch/arm64/boot/dts/nvidia/tegra210.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra210.dtsi @@ -810,6 +810,7 @@ <&tegra_car 128>, /* hda2hdmi */ <&tegra_car 111>; /* hda2codec_2x */ reset-names = "hda", "hda2hdmi", "hda2codec_2x"; + power-domains = <&pd_sor>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/qcom/ipq8074-hk01.dts b/arch/arm64/boot/dts/qcom/ipq8074-hk01.dts index 6a838b5d321e..1ab7deeb2497 100644 --- a/arch/arm64/boot/dts/qcom/ipq8074-hk01.dts +++ b/arch/arm64/boot/dts/qcom/ipq8074-hk01.dts @@ -27,7 +27,7 @@ stdout-path = "serial0"; }; - memory { + memory@40000000 { device_type = "memory"; reg = <0x0 0x40000000 0x0 0x20000000>; }; diff --git a/arch/arm64/boot/dts/qcom/msm8916-pins.dtsi b/arch/arm64/boot/dts/qcom/msm8916-pins.dtsi index 4cb0b5834143..b24493ad44b0 100644 --- a/arch/arm64/boot/dts/qcom/msm8916-pins.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8916-pins.dtsi @@ -542,7 +542,7 @@ pins = "gpio63", "gpio64", "gpio65", "gpio66", "gpio67", "gpio68"; drive-strength = <8>; - bias-pull-none; + bias-disable; }; }; cdc_pdm_lines_sus: pdm_lines_off { @@ -555,7 +555,7 @@ pins = "gpio63", "gpio64", "gpio65", "gpio66", "gpio67", "gpio68"; drive-strength = <2>; - bias-disable; + bias-pull-down; }; }; }; @@ -571,7 +571,7 @@ pins = "gpio113", "gpio114", "gpio115", "gpio116"; drive-strength = <8>; - bias-pull-none; + bias-disable; }; }; @@ -599,7 +599,7 @@ pinconf { pins = "gpio110"; drive-strength = <8>; - bias-pull-none; + bias-disable; }; }; @@ -625,7 +625,7 @@ pinconf { pins = "gpio116"; drive-strength = <8>; - bias-pull-none; + bias-disable; }; }; ext_mclk_tlmm_lines_sus: mclk_lines_off { @@ -653,7 +653,7 @@ pins = "gpio112", "gpio117", "gpio118", "gpio119"; drive-strength = <8>; - bias-pull-none; + bias-disable; }; }; ext_sec_tlmm_lines_sus: tlmm_lines_off { diff --git a/arch/arm64/boot/dts/qcom/msm8916.dtsi b/arch/arm64/boot/dts/qcom/msm8916.dtsi index 3cc449425a03..94697bab3805 100644 --- a/arch/arm64/boot/dts/qcom/msm8916.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8916.dtsi @@ -63,7 +63,7 @@ no-map; }; - reserved@8668000 { + reserved@86680000 { reg = <0x0 0x86680000 0x0 0x80000>; no-map; }; @@ -73,7 +73,7 @@ no-map; }; - rfsa@867e00000 { + rfsa@867e0000 { reg = <0x0 0x867e0000 0x0 0x20000>; no-map; }; @@ -818,7 +818,7 @@ reg-names = "mdp_phys"; interrupt-parent = <&mdss>; - interrupts = <0 0>; + interrupts = <0>; clocks = <&gcc GCC_MDSS_AHB_CLK>, <&gcc GCC_MDSS_AXI_CLK>, @@ -850,7 +850,7 @@ reg-names = "dsi_ctrl"; interrupt-parent = <&mdss>; - interrupts = <4 0>; + interrupts = <4>; assigned-clocks = <&gcc BYTE0_CLK_SRC>, <&gcc PCLK0_CLK_SRC>; diff --git a/arch/arm64/boot/dts/renesas/ulcb.dtsi b/arch/arm64/boot/dts/renesas/ulcb.dtsi index e95d99265af9..38f846530fcd 100644 --- a/arch/arm64/boot/dts/renesas/ulcb.dtsi +++ b/arch/arm64/boot/dts/renesas/ulcb.dtsi @@ -397,6 +397,7 @@ bus-width = <8>; mmc-hs200-1_8v; non-removable; + full-pwr-cycle-in-suspend; status = "okay"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi index c34daae3c37c..a3fb072f20ba 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi @@ -289,13 +289,13 @@ #address-cells = <1>; #size-cells = <0>; - pd_hevc@RK3328_PD_HEVC { + power-domain@RK3328_PD_HEVC { reg = <RK3328_PD_HEVC>; }; - pd_video@RK3328_PD_VIDEO { + power-domain@RK3328_PD_VIDEO { reg = <RK3328_PD_VIDEO>; }; - pd_vpu@RK3328_PD_VPU { + power-domain@RK3328_PD_VPU { reg = <RK3328_PD_VPU>; }; }; @@ -1062,8 +1062,8 @@ uart0 { uart0_xfer: uart0-xfer { - rockchip,pins = <1 RK_PB1 1 &pcfg_pull_up>, - <1 RK_PB0 1 &pcfg_pull_none>; + rockchip,pins = <1 RK_PB1 1 &pcfg_pull_none>, + <1 RK_PB0 1 &pcfg_pull_up>; }; uart0_cts: uart0-cts { @@ -1081,8 +1081,8 @@ uart1 { uart1_xfer: uart1-xfer { - rockchip,pins = <3 RK_PA4 4 &pcfg_pull_up>, - <3 RK_PA6 4 &pcfg_pull_none>; + rockchip,pins = <3 RK_PA4 4 &pcfg_pull_none>, + <3 RK_PA6 4 &pcfg_pull_up>; }; uart1_cts: uart1-cts { @@ -1100,15 +1100,15 @@ uart2-0 { uart2m0_xfer: uart2m0-xfer { - rockchip,pins = <1 RK_PA0 2 &pcfg_pull_up>, - <1 RK_PA1 2 &pcfg_pull_none>; + rockchip,pins = <1 RK_PA0 2 &pcfg_pull_none>, + <1 RK_PA1 2 &pcfg_pull_up>; }; }; uart2-1 { uart2m1_xfer: uart2m1-xfer { - rockchip,pins = <2 RK_PA0 1 &pcfg_pull_up>, - <2 RK_PA1 1 &pcfg_pull_none>; + rockchip,pins = <2 RK_PA0 1 &pcfg_pull_none>, + <2 RK_PA1 1 &pcfg_pull_up>; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi index 1fc5060d7027..0d5679380b2a 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi @@ -138,7 +138,7 @@ vcc5v0_host: vcc5v0-host-regulator { compatible = "regulator-fixed"; - gpio = <&gpio4 RK_PA3 GPIO_ACTIVE_HIGH>; + gpio = <&gpio4 RK_PA3 GPIO_ACTIVE_LOW>; enable-active-low; pinctrl-names = "default"; pinctrl-0 = <&vcc5v0_host_en>; @@ -193,7 +193,7 @@ phy-mode = "rgmii"; pinctrl-names = "default"; pinctrl-0 = <&rgmii_pins>; - snps,reset-gpio = <&gpio3 RK_PC0 GPIO_ACTIVE_HIGH>; + snps,reset-gpio = <&gpio3 RK_PC0 GPIO_ACTIVE_LOW>; snps,reset-active-low; snps,reset-delays-us = <0 10000 50000>; tx_delay = <0x10>; diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi index ff8df7fd44a7..029d4578bca3 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi @@ -66,6 +66,9 @@ i2c6 = &i2c6; i2c7 = &i2c7; i2c8 = &i2c8; + mmc0 = &sdio0; + mmc1 = &sdmmc; + mmc2 = &sdhci; serial0 = &uart0; serial1 = &uart1; serial2 = &uart2; @@ -228,6 +231,7 @@ reg = <0x0 0xf8000000 0x0 0x2000000>, <0x0 0xfd000000 0x0 0x1000000>; reg-names = "axi-base", "apb-base"; + device_type = "pci"; #address-cells = <3>; #size-cells = <2>; #interrupt-cells = <1>; @@ -246,7 +250,6 @@ <0 0 0 2 &pcie0_intc 1>, <0 0 0 3 &pcie0_intc 2>, <0 0 0 4 &pcie0_intc 3>; - linux,pci-domain = <0>; max-link-speed = <1>; msi-map = <0x0 &its 0x0 0x1000>; phys = <&pcie_phy 0>, <&pcie_phy 1>, @@ -1691,10 +1694,10 @@ gpu: gpu@ff9a0000 { compatible = "rockchip,rk3399-mali", "arm,mali-t860"; reg = <0x0 0xff9a0000 0x0 0x10000>; - interrupts = <GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH 0>, - <GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH 0>, - <GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH 0>; - interrupt-names = "gpu", "job", "mmu"; + interrupts = <GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH 0>, + <GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH 0>, + <GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH 0>; + interrupt-names = "job", "mmu", "gpu"; clocks = <&cru ACLK_GPU>; power-domains = <&power RK3399_PD_GPU>; status = "disabled"; @@ -2071,7 +2074,7 @@ }; }; - sleep { + suspend { ap_pwroff: ap-pwroff { rockchip,pins = <1 5 RK_FUNC_1 &pcfg_pull_none>; }; diff --git a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi index 7665fbddff28..58028f23ad9a 100644 --- a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi +++ b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi @@ -410,7 +410,7 @@ }; i2c0: i2c@ff020000 { - compatible = "cdns,i2c-r1p14", "cdns,i2c-r1p10"; + compatible = "cdns,i2c-r1p14"; status = "disabled"; interrupt-parent = <&gic>; interrupts = <0 17 4>; @@ -420,7 +420,7 @@ }; i2c1: i2c@ff030000 { - compatible = "cdns,i2c-r1p14", "cdns,i2c-r1p10"; + compatible = "cdns,i2c-r1p14"; status = "disabled"; interrupt-parent = <&gic>; interrupts = <0 18 4>; @@ -573,7 +573,7 @@ }; uart0: serial@ff000000 { - compatible = "cdns,uart-r1p12", "xlnx,xuartps"; + compatible = "xlnx,zynqmp-uart", "cdns,uart-r1p12"; status = "disabled"; interrupt-parent = <&gic>; interrupts = <0 21 4>; @@ -582,7 +582,7 @@ }; uart1: serial@ff010000 { - compatible = "cdns,uart-r1p12", "xlnx,xuartps"; + compatible = "xlnx,zynqmp-uart", "cdns,uart-r1p12"; status = "disabled"; interrupt-parent = <&gic>; interrupts = <0 22 4>; diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h index 4ed869845a23..ad986cfa592d 100644 --- a/arch/arm64/include/asm/alternative.h +++ b/arch/arm64/include/asm/alternative.h @@ -68,13 +68,13 @@ void apply_alternatives(void *start, size_t length); ".pushsection .altinstructions,\"a\"\n" \ ALTINSTR_ENTRY(feature) \ ".popsection\n" \ - ".pushsection .altinstr_replacement, \"a\"\n" \ + ".subsection 1\n" \ "663:\n\t" \ newinstr "\n" \ "664:\n\t" \ - ".popsection\n\t" \ ".org . - (664b-663b) + (662b-661b)\n\t" \ - ".org . - (662b-661b) + (664b-663b)\n" \ + ".org . - (662b-661b) + (664b-663b)\n\t" \ + ".previous\n" \ ".endif\n" #define __ALTERNATIVE_CFG_CB(oldinstr, feature, cfg_enabled, cb) \ @@ -112,11 +112,11 @@ void apply_alternatives(void *start, size_t length); 662: .pushsection .altinstructions, "a" altinstruction_entry 661b, 663f, \cap, 662b-661b, 664f-663f .popsection - .pushsection .altinstr_replacement, "ax" + .subsection 1 663: \insn2 -664: .popsection - .org . - (664b-663b) + (662b-661b) +664: .org . - (664b-663b) + (662b-661b) .org . - (662b-661b) + (664b-663b) + .previous .endif .endm @@ -155,7 +155,7 @@ void apply_alternatives(void *start, size_t length); .pushsection .altinstructions, "a" altinstruction_entry 663f, 661f, \cap, 664f-663f, 662f-661f .popsection - .pushsection .altinstr_replacement, "ax" + .subsection 1 .align 2 /* So GAS knows label 661 is suitably aligned */ 661: .endm @@ -174,9 +174,9 @@ void apply_alternatives(void *start, size_t length); .macro alternative_else 662: .if .Lasm_alt_mode==0 - .pushsection .altinstr_replacement, "ax" + .subsection 1 .else - .popsection + .previous .endif 663: .endm @@ -186,11 +186,11 @@ void apply_alternatives(void *start, size_t length); */ .macro alternative_endif 664: - .if .Lasm_alt_mode==0 - .popsection - .endif .org . - (664b-663b) + (662b-661b) .org . - (662b-661b) + (664b-663b) + .if .Lasm_alt_mode==0 + .previous + .endif .endm /* diff --git a/arch/arm64/include/asm/atomic_ll_sc.h b/arch/arm64/include/asm/atomic_ll_sc.h index f5a2d09afb38..1cc42441bc67 100644 --- a/arch/arm64/include/asm/atomic_ll_sc.h +++ b/arch/arm64/include/asm/atomic_ll_sc.h @@ -37,7 +37,7 @@ * (the optimize attribute silently ignores these options). */ -#define ATOMIC_OP(op, asm_op) \ +#define ATOMIC_OP(op, asm_op, constraint) \ __LL_SC_INLINE void \ __LL_SC_PREFIX(atomic_##op(int i, atomic_t *v)) \ { \ @@ -51,11 +51,11 @@ __LL_SC_PREFIX(atomic_##op(int i, atomic_t *v)) \ " stxr %w1, %w0, %2\n" \ " cbnz %w1, 1b" \ : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ - : "Ir" (i)); \ + : #constraint "r" (i)); \ } \ __LL_SC_EXPORT(atomic_##op); -#define ATOMIC_OP_RETURN(name, mb, acq, rel, cl, op, asm_op) \ +#define ATOMIC_OP_RETURN(name, mb, acq, rel, cl, op, asm_op, constraint)\ __LL_SC_INLINE int \ __LL_SC_PREFIX(atomic_##op##_return##name(int i, atomic_t *v)) \ { \ @@ -70,14 +70,14 @@ __LL_SC_PREFIX(atomic_##op##_return##name(int i, atomic_t *v)) \ " cbnz %w1, 1b\n" \ " " #mb \ : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ - : "Ir" (i) \ + : #constraint "r" (i) \ : cl); \ \ return result; \ } \ __LL_SC_EXPORT(atomic_##op##_return##name); -#define ATOMIC_FETCH_OP(name, mb, acq, rel, cl, op, asm_op) \ +#define ATOMIC_FETCH_OP(name, mb, acq, rel, cl, op, asm_op, constraint) \ __LL_SC_INLINE int \ __LL_SC_PREFIX(atomic_fetch_##op##name(int i, atomic_t *v)) \ { \ @@ -92,7 +92,7 @@ __LL_SC_PREFIX(atomic_fetch_##op##name(int i, atomic_t *v)) \ " cbnz %w2, 1b\n" \ " " #mb \ : "=&r" (result), "=&r" (val), "=&r" (tmp), "+Q" (v->counter) \ - : "Ir" (i) \ + : #constraint "r" (i) \ : cl); \ \ return result; \ @@ -110,8 +110,8 @@ __LL_SC_EXPORT(atomic_fetch_##op##name); ATOMIC_FETCH_OP (_acquire, , a, , "memory", __VA_ARGS__)\ ATOMIC_FETCH_OP (_release, , , l, "memory", __VA_ARGS__) -ATOMIC_OPS(add, add) -ATOMIC_OPS(sub, sub) +ATOMIC_OPS(add, add, I) +ATOMIC_OPS(sub, sub, J) #undef ATOMIC_OPS #define ATOMIC_OPS(...) \ @@ -121,17 +121,17 @@ ATOMIC_OPS(sub, sub) ATOMIC_FETCH_OP (_acquire, , a, , "memory", __VA_ARGS__)\ ATOMIC_FETCH_OP (_release, , , l, "memory", __VA_ARGS__) -ATOMIC_OPS(and, and) -ATOMIC_OPS(andnot, bic) -ATOMIC_OPS(or, orr) -ATOMIC_OPS(xor, eor) +ATOMIC_OPS(and, and, ) +ATOMIC_OPS(andnot, bic, ) +ATOMIC_OPS(or, orr, ) +ATOMIC_OPS(xor, eor, ) #undef ATOMIC_OPS #undef ATOMIC_FETCH_OP #undef ATOMIC_OP_RETURN #undef ATOMIC_OP -#define ATOMIC64_OP(op, asm_op) \ +#define ATOMIC64_OP(op, asm_op, constraint) \ __LL_SC_INLINE void \ __LL_SC_PREFIX(atomic64_##op(long i, atomic64_t *v)) \ { \ @@ -145,11 +145,11 @@ __LL_SC_PREFIX(atomic64_##op(long i, atomic64_t *v)) \ " stxr %w1, %0, %2\n" \ " cbnz %w1, 1b" \ : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ - : "Ir" (i)); \ + : #constraint "r" (i)); \ } \ __LL_SC_EXPORT(atomic64_##op); -#define ATOMIC64_OP_RETURN(name, mb, acq, rel, cl, op, asm_op) \ +#define ATOMIC64_OP_RETURN(name, mb, acq, rel, cl, op, asm_op, constraint)\ __LL_SC_INLINE long \ __LL_SC_PREFIX(atomic64_##op##_return##name(long i, atomic64_t *v)) \ { \ @@ -164,14 +164,14 @@ __LL_SC_PREFIX(atomic64_##op##_return##name(long i, atomic64_t *v)) \ " cbnz %w1, 1b\n" \ " " #mb \ : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ - : "Ir" (i) \ + : #constraint "r" (i) \ : cl); \ \ return result; \ } \ __LL_SC_EXPORT(atomic64_##op##_return##name); -#define ATOMIC64_FETCH_OP(name, mb, acq, rel, cl, op, asm_op) \ +#define ATOMIC64_FETCH_OP(name, mb, acq, rel, cl, op, asm_op, constraint)\ __LL_SC_INLINE long \ __LL_SC_PREFIX(atomic64_fetch_##op##name(long i, atomic64_t *v)) \ { \ @@ -186,7 +186,7 @@ __LL_SC_PREFIX(atomic64_fetch_##op##name(long i, atomic64_t *v)) \ " cbnz %w2, 1b\n" \ " " #mb \ : "=&r" (result), "=&r" (val), "=&r" (tmp), "+Q" (v->counter) \ - : "Ir" (i) \ + : #constraint "r" (i) \ : cl); \ \ return result; \ @@ -204,8 +204,8 @@ __LL_SC_EXPORT(atomic64_fetch_##op##name); ATOMIC64_FETCH_OP (_acquire,, a, , "memory", __VA_ARGS__) \ ATOMIC64_FETCH_OP (_release,, , l, "memory", __VA_ARGS__) -ATOMIC64_OPS(add, add) -ATOMIC64_OPS(sub, sub) +ATOMIC64_OPS(add, add, I) +ATOMIC64_OPS(sub, sub, J) #undef ATOMIC64_OPS #define ATOMIC64_OPS(...) \ @@ -215,10 +215,10 @@ ATOMIC64_OPS(sub, sub) ATOMIC64_FETCH_OP (_acquire,, a, , "memory", __VA_ARGS__) \ ATOMIC64_FETCH_OP (_release,, , l, "memory", __VA_ARGS__) -ATOMIC64_OPS(and, and) -ATOMIC64_OPS(andnot, bic) -ATOMIC64_OPS(or, orr) -ATOMIC64_OPS(xor, eor) +ATOMIC64_OPS(and, and, L) +ATOMIC64_OPS(andnot, bic, ) +ATOMIC64_OPS(or, orr, L) +ATOMIC64_OPS(xor, eor, L) #undef ATOMIC64_OPS #undef ATOMIC64_FETCH_OP @@ -248,48 +248,54 @@ __LL_SC_PREFIX(atomic64_dec_if_positive(atomic64_t *v)) } __LL_SC_EXPORT(atomic64_dec_if_positive); -#define __CMPXCHG_CASE(w, sz, name, mb, acq, rel, cl) \ -__LL_SC_INLINE unsigned long \ -__LL_SC_PREFIX(__cmpxchg_case_##name(volatile void *ptr, \ - unsigned long old, \ - unsigned long new)) \ +#define __CMPXCHG_CASE(w, sfx, name, sz, mb, acq, rel, cl, constraint) \ +__LL_SC_INLINE u##sz \ +__LL_SC_PREFIX(__cmpxchg_case_##name##sz(volatile void *ptr, \ + unsigned long old, \ + u##sz new)) \ { \ - unsigned long tmp, oldval; \ + unsigned long tmp; \ + u##sz oldval; \ \ asm volatile( \ " prfm pstl1strm, %[v]\n" \ - "1: ld" #acq "xr" #sz "\t%" #w "[oldval], %[v]\n" \ + "1: ld" #acq "xr" #sfx "\t%" #w "[oldval], %[v]\n" \ " eor %" #w "[tmp], %" #w "[oldval], %" #w "[old]\n" \ " cbnz %" #w "[tmp], 2f\n" \ - " st" #rel "xr" #sz "\t%w[tmp], %" #w "[new], %[v]\n" \ + " st" #rel "xr" #sfx "\t%w[tmp], %" #w "[new], %[v]\n" \ " cbnz %w[tmp], 1b\n" \ " " #mb "\n" \ "2:" \ : [tmp] "=&r" (tmp), [oldval] "=&r" (oldval), \ - [v] "+Q" (*(unsigned long *)ptr) \ - : [old] "Lr" (old), [new] "r" (new) \ + [v] "+Q" (*(u##sz *)ptr) \ + : [old] #constraint "r" (old), [new] "r" (new) \ : cl); \ \ return oldval; \ } \ -__LL_SC_EXPORT(__cmpxchg_case_##name); +__LL_SC_EXPORT(__cmpxchg_case_##name##sz); -__CMPXCHG_CASE(w, b, 1, , , , ) -__CMPXCHG_CASE(w, h, 2, , , , ) -__CMPXCHG_CASE(w, , 4, , , , ) -__CMPXCHG_CASE( , , 8, , , , ) -__CMPXCHG_CASE(w, b, acq_1, , a, , "memory") -__CMPXCHG_CASE(w, h, acq_2, , a, , "memory") -__CMPXCHG_CASE(w, , acq_4, , a, , "memory") -__CMPXCHG_CASE( , , acq_8, , a, , "memory") -__CMPXCHG_CASE(w, b, rel_1, , , l, "memory") -__CMPXCHG_CASE(w, h, rel_2, , , l, "memory") -__CMPXCHG_CASE(w, , rel_4, , , l, "memory") -__CMPXCHG_CASE( , , rel_8, , , l, "memory") -__CMPXCHG_CASE(w, b, mb_1, dmb ish, , l, "memory") -__CMPXCHG_CASE(w, h, mb_2, dmb ish, , l, "memory") -__CMPXCHG_CASE(w, , mb_4, dmb ish, , l, "memory") -__CMPXCHG_CASE( , , mb_8, dmb ish, , l, "memory") +/* + * Earlier versions of GCC (no later than 8.1.0) appear to incorrectly + * handle the 'K' constraint for the value 4294967295 - thus we use no + * constraint for 32 bit operations. + */ +__CMPXCHG_CASE(w, b, , 8, , , , , ) +__CMPXCHG_CASE(w, h, , 16, , , , , ) +__CMPXCHG_CASE(w, , , 32, , , , , ) +__CMPXCHG_CASE( , , , 64, , , , , L) +__CMPXCHG_CASE(w, b, acq_, 8, , a, , "memory", ) +__CMPXCHG_CASE(w, h, acq_, 16, , a, , "memory", ) +__CMPXCHG_CASE(w, , acq_, 32, , a, , "memory", ) +__CMPXCHG_CASE( , , acq_, 64, , a, , "memory", L) +__CMPXCHG_CASE(w, b, rel_, 8, , , l, "memory", ) +__CMPXCHG_CASE(w, h, rel_, 16, , , l, "memory", ) +__CMPXCHG_CASE(w, , rel_, 32, , , l, "memory", ) +__CMPXCHG_CASE( , , rel_, 64, , , l, "memory", L) +__CMPXCHG_CASE(w, b, mb_, 8, dmb ish, , l, "memory", ) +__CMPXCHG_CASE(w, h, mb_, 16, dmb ish, , l, "memory", ) +__CMPXCHG_CASE(w, , mb_, 32, dmb ish, , l, "memory", ) +__CMPXCHG_CASE( , , mb_, 64, dmb ish, , l, "memory", L) #undef __CMPXCHG_CASE diff --git a/arch/arm64/include/asm/atomic_lse.h b/arch/arm64/include/asm/atomic_lse.h index f9b0b09153e0..4d6f917b654e 100644 --- a/arch/arm64/include/asm/atomic_lse.h +++ b/arch/arm64/include/asm/atomic_lse.h @@ -446,22 +446,22 @@ static inline long atomic64_dec_if_positive(atomic64_t *v) #define __LL_SC_CMPXCHG(op) __LL_SC_CALL(__cmpxchg_case_##op) -#define __CMPXCHG_CASE(w, sz, name, mb, cl...) \ -static inline unsigned long __cmpxchg_case_##name(volatile void *ptr, \ - unsigned long old, \ - unsigned long new) \ +#define __CMPXCHG_CASE(w, sfx, name, sz, mb, cl...) \ +static inline u##sz __cmpxchg_case_##name##sz(volatile void *ptr, \ + unsigned long old, \ + u##sz new) \ { \ register unsigned long x0 asm ("x0") = (unsigned long)ptr; \ register unsigned long x1 asm ("x1") = old; \ - register unsigned long x2 asm ("x2") = new; \ + register u##sz x2 asm ("x2") = new; \ \ asm volatile(ARM64_LSE_ATOMIC_INSN( \ /* LL/SC */ \ - __LL_SC_CMPXCHG(name) \ + __LL_SC_CMPXCHG(name##sz) \ __nops(2), \ /* LSE atomics */ \ " mov " #w "30, %" #w "[old]\n" \ - " cas" #mb #sz "\t" #w "30, %" #w "[new], %[v]\n" \ + " cas" #mb #sfx "\t" #w "30, %" #w "[new], %[v]\n" \ " mov %" #w "[ret], " #w "30") \ : [ret] "+r" (x0), [v] "+Q" (*(unsigned long *)ptr) \ : [old] "r" (x1), [new] "r" (x2) \ @@ -470,22 +470,22 @@ static inline unsigned long __cmpxchg_case_##name(volatile void *ptr, \ return x0; \ } -__CMPXCHG_CASE(w, b, 1, ) -__CMPXCHG_CASE(w, h, 2, ) -__CMPXCHG_CASE(w, , 4, ) -__CMPXCHG_CASE(x, , 8, ) -__CMPXCHG_CASE(w, b, acq_1, a, "memory") -__CMPXCHG_CASE(w, h, acq_2, a, "memory") -__CMPXCHG_CASE(w, , acq_4, a, "memory") -__CMPXCHG_CASE(x, , acq_8, a, "memory") -__CMPXCHG_CASE(w, b, rel_1, l, "memory") -__CMPXCHG_CASE(w, h, rel_2, l, "memory") -__CMPXCHG_CASE(w, , rel_4, l, "memory") -__CMPXCHG_CASE(x, , rel_8, l, "memory") -__CMPXCHG_CASE(w, b, mb_1, al, "memory") -__CMPXCHG_CASE(w, h, mb_2, al, "memory") -__CMPXCHG_CASE(w, , mb_4, al, "memory") -__CMPXCHG_CASE(x, , mb_8, al, "memory") +__CMPXCHG_CASE(w, b, , 8, ) +__CMPXCHG_CASE(w, h, , 16, ) +__CMPXCHG_CASE(w, , , 32, ) +__CMPXCHG_CASE(x, , , 64, ) +__CMPXCHG_CASE(w, b, acq_, 8, a, "memory") +__CMPXCHG_CASE(w, h, acq_, 16, a, "memory") +__CMPXCHG_CASE(w, , acq_, 32, a, "memory") +__CMPXCHG_CASE(x, , acq_, 64, a, "memory") +__CMPXCHG_CASE(w, b, rel_, 8, l, "memory") +__CMPXCHG_CASE(w, h, rel_, 16, l, "memory") +__CMPXCHG_CASE(w, , rel_, 32, l, "memory") +__CMPXCHG_CASE(x, , rel_, 64, l, "memory") +__CMPXCHG_CASE(w, b, mb_, 8, al, "memory") +__CMPXCHG_CASE(w, h, mb_, 16, al, "memory") +__CMPXCHG_CASE(w, , mb_, 32, al, "memory") +__CMPXCHG_CASE(x, , mb_, 64, al, "memory") #undef __LL_SC_CMPXCHG #undef __CMPXCHG_CASE diff --git a/arch/arm64/include/asm/checksum.h b/arch/arm64/include/asm/checksum.h index 0b6f5a7d4027..fd11e0d70e44 100644 --- a/arch/arm64/include/asm/checksum.h +++ b/arch/arm64/include/asm/checksum.h @@ -30,16 +30,17 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl) { __uint128_t tmp; u64 sum; + int n = ihl; /* we want it signed */ tmp = *(const __uint128_t *)iph; iph += 16; - ihl -= 4; + n -= 4; tmp += ((tmp >> 64) | (tmp << 64)); sum = tmp >> 64; do { sum += *(const u32 *)iph; iph += 4; - } while (--ihl); + } while (--n > 0); sum += ((sum >> 32) | (sum << 32)); return csum_fold((__force u32)(sum >> 32)); diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h index 9b2e2e2e728a..ed6a1aae6fbb 100644 --- a/arch/arm64/include/asm/cmpxchg.h +++ b/arch/arm64/include/asm/cmpxchg.h @@ -29,46 +29,46 @@ * barrier case is generated as release+dmb for the former and * acquire+release for the latter. */ -#define __XCHG_CASE(w, sz, name, mb, nop_lse, acq, acq_lse, rel, cl) \ -static inline unsigned long __xchg_case_##name(unsigned long x, \ - volatile void *ptr) \ -{ \ - unsigned long ret, tmp; \ - \ - asm volatile(ARM64_LSE_ATOMIC_INSN( \ - /* LL/SC */ \ - " prfm pstl1strm, %2\n" \ - "1: ld" #acq "xr" #sz "\t%" #w "0, %2\n" \ - " st" #rel "xr" #sz "\t%w1, %" #w "3, %2\n" \ - " cbnz %w1, 1b\n" \ - " " #mb, \ - /* LSE atomics */ \ - " swp" #acq_lse #rel #sz "\t%" #w "3, %" #w "0, %2\n" \ - __nops(3) \ - " " #nop_lse) \ - : "=&r" (ret), "=&r" (tmp), "+Q" (*(unsigned long *)ptr) \ - : "r" (x) \ - : cl); \ - \ - return ret; \ +#define __XCHG_CASE(w, sfx, name, sz, mb, nop_lse, acq, acq_lse, rel, cl) \ +static inline u##sz __xchg_case_##name##sz(u##sz x, volatile void *ptr) \ +{ \ + u##sz ret; \ + unsigned long tmp; \ + \ + asm volatile(ARM64_LSE_ATOMIC_INSN( \ + /* LL/SC */ \ + " prfm pstl1strm, %2\n" \ + "1: ld" #acq "xr" #sfx "\t%" #w "0, %2\n" \ + " st" #rel "xr" #sfx "\t%w1, %" #w "3, %2\n" \ + " cbnz %w1, 1b\n" \ + " " #mb, \ + /* LSE atomics */ \ + " swp" #acq_lse #rel #sfx "\t%" #w "3, %" #w "0, %2\n" \ + __nops(3) \ + " " #nop_lse) \ + : "=&r" (ret), "=&r" (tmp), "+Q" (*(u##sz *)ptr) \ + : "r" (x) \ + : cl); \ + \ + return ret; \ } -__XCHG_CASE(w, b, 1, , , , , , ) -__XCHG_CASE(w, h, 2, , , , , , ) -__XCHG_CASE(w, , 4, , , , , , ) -__XCHG_CASE( , , 8, , , , , , ) -__XCHG_CASE(w, b, acq_1, , , a, a, , "memory") -__XCHG_CASE(w, h, acq_2, , , a, a, , "memory") -__XCHG_CASE(w, , acq_4, , , a, a, , "memory") -__XCHG_CASE( , , acq_8, , , a, a, , "memory") -__XCHG_CASE(w, b, rel_1, , , , , l, "memory") -__XCHG_CASE(w, h, rel_2, , , , , l, "memory") -__XCHG_CASE(w, , rel_4, , , , , l, "memory") -__XCHG_CASE( , , rel_8, , , , , l, "memory") -__XCHG_CASE(w, b, mb_1, dmb ish, nop, , a, l, "memory") -__XCHG_CASE(w, h, mb_2, dmb ish, nop, , a, l, "memory") -__XCHG_CASE(w, , mb_4, dmb ish, nop, , a, l, "memory") -__XCHG_CASE( , , mb_8, dmb ish, nop, , a, l, "memory") +__XCHG_CASE(w, b, , 8, , , , , , ) +__XCHG_CASE(w, h, , 16, , , , , , ) +__XCHG_CASE(w, , , 32, , , , , , ) +__XCHG_CASE( , , , 64, , , , , , ) +__XCHG_CASE(w, b, acq_, 8, , , a, a, , "memory") +__XCHG_CASE(w, h, acq_, 16, , , a, a, , "memory") +__XCHG_CASE(w, , acq_, 32, , , a, a, , "memory") +__XCHG_CASE( , , acq_, 64, , , a, a, , "memory") +__XCHG_CASE(w, b, rel_, 8, , , , , l, "memory") +__XCHG_CASE(w, h, rel_, 16, , , , , l, "memory") +__XCHG_CASE(w, , rel_, 32, , , , , l, "memory") +__XCHG_CASE( , , rel_, 64, , , , , l, "memory") +__XCHG_CASE(w, b, mb_, 8, dmb ish, nop, , a, l, "memory") +__XCHG_CASE(w, h, mb_, 16, dmb ish, nop, , a, l, "memory") +__XCHG_CASE(w, , mb_, 32, dmb ish, nop, , a, l, "memory") +__XCHG_CASE( , , mb_, 64, dmb ish, nop, , a, l, "memory") #undef __XCHG_CASE @@ -79,13 +79,13 @@ static __always_inline unsigned long __xchg##sfx(unsigned long x, \ { \ switch (size) { \ case 1: \ - return __xchg_case##sfx##_1(x, ptr); \ + return __xchg_case##sfx##_8(x, ptr); \ case 2: \ - return __xchg_case##sfx##_2(x, ptr); \ + return __xchg_case##sfx##_16(x, ptr); \ case 4: \ - return __xchg_case##sfx##_4(x, ptr); \ + return __xchg_case##sfx##_32(x, ptr); \ case 8: \ - return __xchg_case##sfx##_8(x, ptr); \ + return __xchg_case##sfx##_64(x, ptr); \ default: \ BUILD_BUG(); \ } \ @@ -122,13 +122,13 @@ static __always_inline unsigned long __cmpxchg##sfx(volatile void *ptr, \ { \ switch (size) { \ case 1: \ - return __cmpxchg_case##sfx##_1(ptr, (u8)old, new); \ + return __cmpxchg_case##sfx##_8(ptr, (u8)old, new); \ case 2: \ - return __cmpxchg_case##sfx##_2(ptr, (u16)old, new); \ + return __cmpxchg_case##sfx##_16(ptr, (u16)old, new); \ case 4: \ - return __cmpxchg_case##sfx##_4(ptr, old, new); \ + return __cmpxchg_case##sfx##_32(ptr, old, new); \ case 8: \ - return __cmpxchg_case##sfx##_8(ptr, old, new); \ + return __cmpxchg_case##sfx##_64(ptr, old, new); \ default: \ BUILD_BUG(); \ } \ @@ -222,16 +222,16 @@ __CMPXCHG_GEN(_mb) __ret; \ }) -#define __CMPWAIT_CASE(w, sz, name) \ -static inline void __cmpwait_case_##name(volatile void *ptr, \ - unsigned long val) \ +#define __CMPWAIT_CASE(w, sfx, sz) \ +static inline void __cmpwait_case_##sz(volatile void *ptr, \ + unsigned long val) \ { \ unsigned long tmp; \ \ asm volatile( \ " sevl\n" \ " wfe\n" \ - " ldxr" #sz "\t%" #w "[tmp], %[v]\n" \ + " ldxr" #sfx "\t%" #w "[tmp], %[v]\n" \ " eor %" #w "[tmp], %" #w "[tmp], %" #w "[val]\n" \ " cbnz %" #w "[tmp], 1f\n" \ " wfe\n" \ @@ -240,10 +240,10 @@ static inline void __cmpwait_case_##name(volatile void *ptr, \ : [val] "r" (val)); \ } -__CMPWAIT_CASE(w, b, 1); -__CMPWAIT_CASE(w, h, 2); -__CMPWAIT_CASE(w, , 4); -__CMPWAIT_CASE( , , 8); +__CMPWAIT_CASE(w, b, 8); +__CMPWAIT_CASE(w, h, 16); +__CMPWAIT_CASE(w, , 32); +__CMPWAIT_CASE( , , 64); #undef __CMPWAIT_CASE @@ -254,13 +254,13 @@ static __always_inline void __cmpwait##sfx(volatile void *ptr, \ { \ switch (size) { \ case 1: \ - return __cmpwait_case##sfx##_1(ptr, (u8)val); \ + return __cmpwait_case##sfx##_8(ptr, (u8)val); \ case 2: \ - return __cmpwait_case##sfx##_2(ptr, (u16)val); \ + return __cmpwait_case##sfx##_16(ptr, (u16)val); \ case 4: \ - return __cmpwait_case##sfx##_4(ptr, val); \ + return __cmpwait_case##sfx##_32(ptr, val); \ case 8: \ - return __cmpwait_case##sfx##_8(ptr, val); \ + return __cmpwait_case##sfx##_64(ptr, val); \ default: \ BUILD_BUG(); \ } \ diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h index a44cf5225429..41b065f1be88 100644 --- a/arch/arm64/include/asm/debug-monitors.h +++ b/arch/arm64/include/asm/debug-monitors.h @@ -119,6 +119,8 @@ void disable_debug_monitors(enum dbg_active_el el); void user_rewind_single_step(struct task_struct *task); void user_fastforward_single_step(struct task_struct *task); +void user_regs_reset_single_step(struct user_pt_regs *regs, + struct task_struct *task); void kernel_enable_single_step(struct pt_regs *regs); void kernel_disable_single_step(void); diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 1d6d980f80ac..72ed11292df3 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -78,10 +78,11 @@ * IMO: Override CPSR.I and enable signaling with VI * FMO: Override CPSR.F and enable signaling with VF * SWIO: Turn set/way invalidates into set/way clean+invalidate + * PTW: Take a stage2 fault if a stage1 walk steps in device memory */ #define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWE | HCR_TWI | HCR_VM | \ HCR_TVM | HCR_BSU_IS | HCR_FB | HCR_TAC | \ - HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW) + HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW | HCR_PTW) #define HCR_VIRT_EXCP_MASK (HCR_VSE | HCR_VI | HCR_VF) #define HCR_INT_OVERRIDE (HCR_FMO | HCR_IMO) #define HCR_HOST_NVHE_FLAGS (HCR_RW | HCR_API | HCR_APK) @@ -190,6 +191,7 @@ #define CPTR_EL2_DEFAULT 0x000033ff /* Hyp Debug Configuration Register bits */ +#define MDCR_EL2_TTRF (1 << 19) #define MDCR_EL2_TPMS (1 << 14) #define MDCR_EL2_E2PB_MASK (UL(0x3)) #define MDCR_EL2_E2PB_SHIFT (UL(12)) diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index c59e81b65132..b0f0fb81f5f5 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -83,6 +83,34 @@ extern u32 __init_stage2_translation(void); *__hyp_this_cpu_ptr(sym); \ }) +#define __KVM_EXTABLE(from, to) \ + " .pushsection __kvm_ex_table, \"a\"\n" \ + " .align 3\n" \ + " .long (" #from " - .), (" #to " - .)\n" \ + " .popsection\n" + + +#define __kvm_at(at_op, addr) \ +( { \ + int __kvm_at_err = 0; \ + u64 spsr, elr; \ + asm volatile( \ + " mrs %1, spsr_el2\n" \ + " mrs %2, elr_el2\n" \ + "1: at "at_op", %3\n" \ + " isb\n" \ + " b 9f\n" \ + "2: msr spsr_el2, %1\n" \ + " msr elr_el2, %2\n" \ + " mov %w0, %4\n" \ + "9:\n" \ + __KVM_EXTABLE(1b, 2b) \ + : "+r" (__kvm_at_err), "=&r" (spsr), "=&r" (elr) \ + : "r" (addr), "i" (-EFAULT)); \ + __kvm_at_err; \ +} ) + + #else /* __ASSEMBLY__ */ .macro hyp_adr_this_cpu reg, sym, tmp @@ -107,6 +135,21 @@ extern u32 __init_stage2_translation(void); kern_hyp_va \vcpu .endm +/* + * KVM extable for unexpected exceptions. + * In the same format _asm_extable, but output to a different section so that + * it can be mapped to EL2. The KVM version is not sorted. The caller must + * ensure: + * x18 has the hypervisor value to allow any Shadow-Call-Stack instrumented + * code to write to it, and that SPSR_EL2 and ELR_EL2 are restored by the fixup. + */ +.macro _kvm_extable, from, to + .pushsection __kvm_ex_table, "a" + .align 3 + .long (\from - .), (\to - .) + .popsection +.endm + #endif #endif /* __ARM_KVM_ASM_H__ */ diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index f982c9d1d10b..8d94404829f0 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -158,6 +158,7 @@ enum vcpu_sysreg { #define c2_TTBR1 (TTBR1_EL1 * 2) /* Translation Table Base Register 1 */ #define c2_TTBR1_high (c2_TTBR1 + 1) /* TTBR1 top 32 bits */ #define c2_TTBCR (TCR_EL1 * 2) /* Translation Table Base Control R. */ +#define c2_TTBCR2 (c2_TTBCR + 1) /* Translation Table Base Control R. 2 */ #define c3_DACR (DACR32_EL2 * 2)/* Domain Access Control Register */ #define c5_DFSR (ESR_EL1 * 2) /* Data Fault Status Register */ #define c5_IFSR (IFSR32_EL2 * 2)/* Instruction Fault Status Register */ @@ -185,6 +186,7 @@ enum vcpu_sysreg { #define cp14_DBGWCR0 (DBGWCR0_EL1 * 2) #define cp14_DBGWVR0 (DBGWVR0_EL1 * 2) #define cp14_DBGDCCINT (MDCCINT_EL1 * 2) +#define cp14_DBGVCR (DBGVCR32_EL2 * 2) #define NR_COPRO_REGS (NR_SYS_REGS * 2) @@ -292,8 +294,10 @@ struct kvm_vcpu_arch { * CP14 and CP15 live in the same array, as they are backed by the * same system registers. */ -#define vcpu_cp14(v,r) ((v)->arch.ctxt.copro[(r)]) -#define vcpu_cp15(v,r) ((v)->arch.ctxt.copro[(r)]) +#define CPx_BIAS IS_ENABLED(CONFIG_CPU_BIG_ENDIAN) + +#define vcpu_cp14(v,r) ((v)->arch.ctxt.copro[(r) ^ CPx_BIAS]) +#define vcpu_cp15(v,r) ((v)->arch.ctxt.copro[(r) ^ CPx_BIAS]) #ifdef CONFIG_CPU_BIG_ENDIAN #define vcpu_cp15_64_high(v,r) vcpu_cp15((v),(r)) diff --git a/arch/arm64/include/asm/numa.h b/arch/arm64/include/asm/numa.h index 01bc46d5b43a..9bde63602767 100644 --- a/arch/arm64/include/asm/numa.h +++ b/arch/arm64/include/asm/numa.h @@ -25,6 +25,9 @@ const struct cpumask *cpumask_of_node(int node); /* Returns a pointer to the cpumask of CPUs on Node 'node'. */ static inline const struct cpumask *cpumask_of_node(int node) { + if (node == NUMA_NO_NODE) + return cpu_all_mask; + return node_to_cpumask_map[node]; } #endif diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h index 26efe251f076..6415677ffe8d 100644 --- a/arch/arm64/include/asm/pgtable-prot.h +++ b/arch/arm64/include/asm/pgtable-prot.h @@ -65,7 +65,7 @@ #define PAGE_HYP __pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_HYP_XN) #define PAGE_HYP_EXEC __pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY) #define PAGE_HYP_RO __pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY | PTE_HYP_XN) -#define PAGE_HYP_DEVICE __pgprot(PROT_DEVICE_nGnRE | PTE_HYP) +#define PAGE_HYP_DEVICE __pgprot(_PROT_DEFAULT | PTE_ATTRINDX(MT_DEVICE_nGnRE) | PTE_HYP | PTE_HYP_XN) #define PAGE_S2 __pgprot(_PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY) #define PAGE_S2_DEVICE __pgprot(_PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_UXN) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 324db23b37de..6147e58babf0 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -92,8 +92,6 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; #define pte_valid(pte) (!!(pte_val(pte) & PTE_VALID)) #define pte_valid_not_user(pte) \ ((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID) -#define pte_valid_young(pte) \ - ((pte_val(pte) & (PTE_VALID | PTE_AF)) == (PTE_VALID | PTE_AF)) #define pte_valid_user(pte) \ ((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER)) @@ -101,9 +99,12 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; * Could the pte be present in the TLB? We must check mm_tlb_flush_pending * so that we don't erroneously return false for pages that have been * remapped as PROT_NONE but are yet to be flushed from the TLB. + * Note that we can't make any assumptions based on the state of the access + * flag, since ptep_clear_flush_young() elides a DSB when invalidating the + * TLB. */ #define pte_accessible(mm, pte) \ - (mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid_young(pte)) + (mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid(pte)) /* * p??_access_permitted() is true for valid user mappings (subject to the @@ -129,13 +130,6 @@ static inline pte_t set_pte_bit(pte_t pte, pgprot_t prot) return pte; } -static inline pte_t pte_wrprotect(pte_t pte) -{ - pte = clear_pte_bit(pte, __pgprot(PTE_WRITE)); - pte = set_pte_bit(pte, __pgprot(PTE_RDONLY)); - return pte; -} - static inline pte_t pte_mkwrite(pte_t pte) { pte = set_pte_bit(pte, __pgprot(PTE_WRITE)); @@ -161,6 +155,20 @@ static inline pte_t pte_mkdirty(pte_t pte) return pte; } +static inline pte_t pte_wrprotect(pte_t pte) +{ + /* + * If hardware-dirty (PTE_WRITE/DBM bit set and PTE_RDONLY + * clear), set the PTE_DIRTY bit. + */ + if (pte_hw_dirty(pte)) + pte = pte_mkdirty(pte); + + pte = clear_pte_bit(pte, __pgprot(PTE_WRITE)); + pte = set_pte_bit(pte, __pgprot(PTE_RDONLY)); + return pte; +} + static inline pte_t pte_mkold(pte_t pte) { return clear_pte_bit(pte, __pgprot(PTE_AF)); @@ -642,12 +650,6 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addres pte = READ_ONCE(*ptep); do { old_pte = pte; - /* - * If hardware-dirty (PTE_WRITE/DBM bit set and PTE_RDONLY - * clear), set the PTE_DIRTY bit. - */ - if (pte_hw_dirty(pte)) - pte = pte_mkdirty(pte); pte = pte_wrprotect(pte); pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep), pte_val(old_pte), pte_val(pte)); diff --git a/arch/arm64/include/asm/word-at-a-time.h b/arch/arm64/include/asm/word-at-a-time.h index b0d708ff7f4e..a2601c1ccf43 100644 --- a/arch/arm64/include/asm/word-at-a-time.h +++ b/arch/arm64/include/asm/word-at-a-time.h @@ -64,7 +64,7 @@ static inline unsigned long find_zero(unsigned long mask) */ static inline unsigned long load_unaligned_zeropad(const void *addr) { - unsigned long ret, offset; + unsigned long ret, tmp; /* Load word from unaligned pointer addr */ asm( @@ -72,9 +72,9 @@ static inline unsigned long load_unaligned_zeropad(const void *addr) "2:\n" " .pushsection .fixup,\"ax\"\n" " .align 2\n" - "3: and %1, %2, #0x7\n" - " bic %2, %2, #0x7\n" - " ldr %0, [%2]\n" + "3: bic %1, %2, #0x7\n" + " ldr %0, [%1]\n" + " and %1, %2, #0x7\n" " lsl %1, %1, #0x3\n" #ifndef __AARCH64EB__ " lsr %0, %0, %1\n" @@ -84,7 +84,7 @@ static inline unsigned long load_unaligned_zeropad(const void *addr) " b 2b\n" " .popsection\n" _ASM_EXTABLE(1b, 3b) - : "=&r" (ret), "=&r" (offset) + : "=&r" (ret), "=&r" (tmp) : "r" (addr), "Q" (*(unsigned long *)addr)); return ret; diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c index 5c4bce4ac381..4c385763c361 100644 --- a/arch/arm64/kernel/alternative.c +++ b/arch/arm64/kernel/alternative.c @@ -44,20 +44,8 @@ struct alt_region { */ static bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc) { - unsigned long replptr; - - if (kernel_text_address(pc)) - return 1; - - replptr = (unsigned long)ALT_REPL_PTR(alt); - if (pc >= replptr && pc <= (replptr + alt->alt_len)) - return 0; - - /* - * Branching into *another* alternate sequence is doomed, and - * we're not even trying to fix it up. - */ - BUG(); + unsigned long replptr = (unsigned long)ALT_REPL_PTR(alt); + return !(pc >= replptr && pc <= (replptr + alt->alt_len)); } #define align_down(x, a) ((unsigned long)(x) & ~(((unsigned long)(a)) - 1)) diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 6b3bb67596ae..1481e18aa5ca 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -136,11 +136,10 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_GIC_SHIFT, 4, 0), S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_ASIMD_SHIFT, 4, ID_AA64PFR0_ASIMD_NI), S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_FP_SHIFT, 4, ID_AA64PFR0_FP_NI), - /* Linux doesn't care about the EL3 */ ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL3_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL2_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_SHIFT, 4, ID_AA64PFR0_EL1_64BIT_ONLY), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL0_SHIFT, 4, ID_AA64PFR0_EL0_64BIT_ONLY), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL2_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_SHIFT, 4, ID_AA64PFR0_EL1_64BIT_ONLY), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL0_SHIFT, 4, ID_AA64PFR0_EL0_64BIT_ONLY), ARM64_FTR_END, }; @@ -231,7 +230,6 @@ static const struct arm64_ftr_bits ftr_id_aa64dfr0[] = { * of support. */ S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_AA64DFR0_PMUVER_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64DFR0_TRACEVER_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64DFR0_DEBUGVER_SHIFT, 4, 0x6), ARM64_FTR_END, }; @@ -273,7 +271,7 @@ static const struct arm64_ftr_bits ftr_id_pfr0[] = { }; static const struct arm64_ftr_bits ftr_id_dfr0[] = { - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 28, 4, 0), + /* [31:28] TraceFilt */ S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 24, 4, 0xf), /* PerfMon */ ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 0), @@ -627,9 +625,6 @@ void update_cpu_features(int cpu, taint |= check_update_ftr_reg(SYS_ID_AA64MMFR2_EL1, cpu, info->reg_id_aa64mmfr2, boot->reg_id_aa64mmfr2); - /* - * EL3 is not our concern. - */ taint |= check_update_ftr_reg(SYS_ID_AA64PFR0_EL1, cpu, info->reg_id_aa64pfr0, boot->reg_id_aa64pfr0); taint |= check_update_ftr_reg(SYS_ID_AA64PFR1_EL1, cpu, diff --git a/arch/arm64/kernel/crash_dump.c b/arch/arm64/kernel/crash_dump.c index f46d57c31443..76905a258550 100644 --- a/arch/arm64/kernel/crash_dump.c +++ b/arch/arm64/kernel/crash_dump.c @@ -67,5 +67,7 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf, ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos) { memcpy(buf, phys_to_virt((phys_addr_t)*ppos), count); + *ppos += count; + return count; } diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c index edb63bf2ac1c..2ccd0a99d8b3 100644 --- a/arch/arm64/kernel/debug-monitors.c +++ b/arch/arm64/kernel/debug-monitors.c @@ -150,17 +150,20 @@ postcore_initcall(debug_monitors_init); /* * Single step API and exception handling. */ -static void set_regs_spsr_ss(struct pt_regs *regs) +static void set_user_regs_spsr_ss(struct user_pt_regs *regs) { regs->pstate |= DBG_SPSR_SS; } -NOKPROBE_SYMBOL(set_regs_spsr_ss); +NOKPROBE_SYMBOL(set_user_regs_spsr_ss); -static void clear_regs_spsr_ss(struct pt_regs *regs) +static void clear_user_regs_spsr_ss(struct user_pt_regs *regs) { regs->pstate &= ~DBG_SPSR_SS; } -NOKPROBE_SYMBOL(clear_regs_spsr_ss); +NOKPROBE_SYMBOL(clear_user_regs_spsr_ss); + +#define set_regs_spsr_ss(r) set_user_regs_spsr_ss(&(r)->user_regs) +#define clear_regs_spsr_ss(r) clear_user_regs_spsr_ss(&(r)->user_regs) /* EL1 Single Step Handler hooks */ static LIST_HEAD(step_hook); @@ -386,17 +389,26 @@ void user_rewind_single_step(struct task_struct *task) * If single step is active for this thread, then set SPSR.SS * to 1 to avoid returning to the active-pending state. */ - if (test_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP)) + if (test_tsk_thread_flag(task, TIF_SINGLESTEP)) set_regs_spsr_ss(task_pt_regs(task)); } NOKPROBE_SYMBOL(user_rewind_single_step); void user_fastforward_single_step(struct task_struct *task) { - if (test_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP)) + if (test_tsk_thread_flag(task, TIF_SINGLESTEP)) clear_regs_spsr_ss(task_pt_regs(task)); } +void user_regs_reset_single_step(struct user_pt_regs *regs, + struct task_struct *task) +{ + if (test_tsk_thread_flag(task, TIF_SINGLESTEP)) + set_user_regs_spsr_ss(regs); + else + clear_user_regs_spsr_ss(regs); +} + /* Kernel API */ void kernel_enable_single_step(struct pt_regs *regs) { diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index bd24c8aed612..30d1e850b16a 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -756,6 +756,7 @@ __primary_switch: tlbi vmalle1 // Remove any stale TLB entries dsb nsh + isb msr sctlr_el1, x19 // re-enable the MMU isb diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index 95697a9c1245..6e96cea99a4e 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -738,6 +738,27 @@ static u64 get_distance_from_watchpoint(unsigned long addr, u64 val, return 0; } +static int watchpoint_report(struct perf_event *wp, unsigned long addr, + struct pt_regs *regs) +{ + int step = is_default_overflow_handler(wp); + struct arch_hw_breakpoint *info = counter_arch_bp(wp); + + info->trigger = addr; + + /* + * If we triggered a user watchpoint from a uaccess routine, then + * handle the stepping ourselves since userspace really can't help + * us with this. + */ + if (!user_mode(regs) && info->ctrl.privilege == AARCH64_BREAKPOINT_EL0) + step = 1; + else + perf_bp_event(wp, regs); + + return step; +} + static int watchpoint_handler(unsigned long addr, unsigned int esr, struct pt_regs *regs) { @@ -747,7 +768,6 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr, u64 val; struct perf_event *wp, **slots; struct debug_info *debug_info; - struct arch_hw_breakpoint *info; struct arch_hw_breakpoint_ctrl ctrl; slots = this_cpu_ptr(wp_on_reg); @@ -785,25 +805,13 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr, if (dist != 0) continue; - info = counter_arch_bp(wp); - info->trigger = addr; - perf_bp_event(wp, regs); - - /* Do we need to handle the stepping? */ - if (is_default_overflow_handler(wp)) - step = 1; + step = watchpoint_report(wp, addr, regs); } - if (min_dist > 0 && min_dist != -1) { - /* No exact match found. */ - wp = slots[closest_match]; - info = counter_arch_bp(wp); - info->trigger = addr; - perf_bp_event(wp, regs); - /* Do we need to handle the stepping? */ - if (is_default_overflow_handler(wp)) - step = 1; - } + /* No exact match found? */ + if (min_dist > 0 && min_dist != -1) + step = watchpoint_report(slots[closest_match], addr, regs); + rcu_read_unlock(); if (!step) diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c index 470afb3a04ca..7fd7a9cd8616 100644 --- a/arch/arm64/kernel/kgdb.c +++ b/arch/arm64/kernel/kgdb.c @@ -258,7 +258,7 @@ static int kgdb_step_brk_fn(struct pt_regs *regs, unsigned int esr) if (user_mode(regs) || !kgdb_single_step) return DBG_HOOK_ERROR; - kgdb_handle_exception(1, SIGTRAP, 0, regs); + kgdb_handle_exception(0, SIGTRAP, 0, regs); return DBG_HOOK_HANDLED; } NOKPROBE_SYMBOL(kgdb_step_brk_fn); diff --git a/arch/arm64/kernel/module.lds b/arch/arm64/kernel/module.lds index 22e36a21c113..09a0eef71d12 100644 --- a/arch/arm64/kernel/module.lds +++ b/arch/arm64/kernel/module.lds @@ -1,5 +1,5 @@ SECTIONS { - .plt (NOLOAD) : { BYTE(0) } - .init.plt (NOLOAD) : { BYTE(0) } - .text.ftrace_trampoline (NOLOAD) : { BYTE(0) } + .plt 0 (NOLOAD) : { BYTE(0) } + .init.plt 0 (NOLOAD) : { BYTE(0) } + .text.ftrace_trampoline 0 (NOLOAD) : { BYTE(0) } } diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index 53df84b2a07f..4ee1228d29eb 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -670,6 +670,28 @@ static void armv8pmu_disable_event(struct perf_event *event) raw_spin_unlock_irqrestore(&events->pmu_lock, flags); } +static void armv8pmu_start(struct arm_pmu *cpu_pmu) +{ + unsigned long flags; + struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events); + + raw_spin_lock_irqsave(&events->pmu_lock, flags); + /* Enable all counters */ + armv8pmu_pmcr_write(armv8pmu_pmcr_read() | ARMV8_PMU_PMCR_E); + raw_spin_unlock_irqrestore(&events->pmu_lock, flags); +} + +static void armv8pmu_stop(struct arm_pmu *cpu_pmu) +{ + unsigned long flags; + struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events); + + raw_spin_lock_irqsave(&events->pmu_lock, flags); + /* Disable all counters */ + armv8pmu_pmcr_write(armv8pmu_pmcr_read() & ~ARMV8_PMU_PMCR_E); + raw_spin_unlock_irqrestore(&events->pmu_lock, flags); +} + static irqreturn_t armv8pmu_handle_irq(int irq_num, void *dev) { u32 pmovsr; @@ -695,6 +717,11 @@ static irqreturn_t armv8pmu_handle_irq(int irq_num, void *dev) */ regs = get_irq_regs(); + /* + * Stop the PMU while processing the counter overflows + * to prevent skews in group events. + */ + armv8pmu_stop(cpu_pmu); for (idx = 0; idx < cpu_pmu->num_events; ++idx) { struct perf_event *event = cpuc->events[idx]; struct hw_perf_event *hwc; @@ -719,6 +746,7 @@ static irqreturn_t armv8pmu_handle_irq(int irq_num, void *dev) if (perf_event_overflow(event, &data, regs)) cpu_pmu->disable(event); } + armv8pmu_start(cpu_pmu); /* * Handle the pending perf events. @@ -732,28 +760,6 @@ static irqreturn_t armv8pmu_handle_irq(int irq_num, void *dev) return IRQ_HANDLED; } -static void armv8pmu_start(struct arm_pmu *cpu_pmu) -{ - unsigned long flags; - struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events); - - raw_spin_lock_irqsave(&events->pmu_lock, flags); - /* Enable all counters */ - armv8pmu_pmcr_write(armv8pmu_pmcr_read() | ARMV8_PMU_PMCR_E); - raw_spin_unlock_irqrestore(&events->pmu_lock, flags); -} - -static void armv8pmu_stop(struct arm_pmu *cpu_pmu) -{ - unsigned long flags; - struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events); - - raw_spin_lock_irqsave(&events->pmu_lock, flags); - /* Disable all counters */ - armv8pmu_pmcr_write(armv8pmu_pmcr_read() & ~ARMV8_PMU_PMCR_E); - raw_spin_unlock_irqrestore(&events->pmu_lock, flags); -} - static int armv8pmu_get_event_idx(struct pmu_hw_events *cpuc, struct perf_event *event) { diff --git a/arch/arm64/kernel/perf_regs.c b/arch/arm64/kernel/perf_regs.c index 1d091d048d04..0819db91ca94 100644 --- a/arch/arm64/kernel/perf_regs.c +++ b/arch/arm64/kernel/perf_regs.c @@ -15,15 +15,34 @@ u64 perf_reg_value(struct pt_regs *regs, int idx) return 0; /* - * Compat (i.e. 32 bit) mode: - * - PC has been set in the pt_regs struct in kernel_entry, - * - Handle SP and LR here. + * Our handling of compat tasks (PERF_SAMPLE_REGS_ABI_32) is weird, but + * we're stuck with it for ABI compatability reasons. + * + * For a 32-bit consumer inspecting a 32-bit task, then it will look at + * the first 16 registers (see arch/arm/include/uapi/asm/perf_regs.h). + * These correspond directly to a prefix of the registers saved in our + * 'struct pt_regs', with the exception of the PC, so we copy that down + * (x15 corresponds to SP_hyp in the architecture). + * + * So far, so good. + * + * The oddity arises when a 64-bit consumer looks at a 32-bit task and + * asks for registers beyond PERF_REG_ARM_MAX. In this case, we return + * SP_usr, LR_usr and PC in the positions where the AArch64 SP, LR and + * PC registers would normally live. The initial idea was to allow a + * 64-bit unwinder to unwind a 32-bit task and, although it's not clear + * how well that works in practice, somebody might be relying on it. + * + * At the time we make a sample, we don't know whether the consumer is + * 32-bit or 64-bit, so we have to cater for both possibilities. */ if (compat_user_mode(regs)) { if ((u32)idx == PERF_REG_ARM64_SP) return regs->compat_sp; if ((u32)idx == PERF_REG_ARM64_LR) return regs->compat_lr; + if (idx == 15) + return regs->pc; } if ((u32)idx == PERF_REG_ARM64_SP) diff --git a/arch/arm64/kernel/probes/uprobes.c b/arch/arm64/kernel/probes/uprobes.c index 636ca0119c0e..6aeb11aa7e28 100644 --- a/arch/arm64/kernel/probes/uprobes.c +++ b/arch/arm64/kernel/probes/uprobes.c @@ -41,7 +41,7 @@ int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, /* TODO: Currently we do not support AARCH32 instruction probing */ if (mm->context.flags & MMCF_AARCH32) - return -ENOTSUPP; + return -EOPNOTSUPP; else if (!IS_ALIGNED(addr, AARCH64_INSN_SIZE)) return -EINVAL; diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 2ff327651ebe..dac14125f8a2 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -61,7 +61,7 @@ #ifdef CONFIG_CC_STACKPROTECTOR #include <linux/stackprotector.h> -unsigned long __stack_chk_guard __read_mostly; +unsigned long __stack_chk_guard __ro_after_init; EXPORT_SYMBOL(__stack_chk_guard); #endif diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c index 3856d51c645b..3ebb2a56e5f7 100644 --- a/arch/arm64/kernel/psci.c +++ b/arch/arm64/kernel/psci.c @@ -69,7 +69,6 @@ static int cpu_psci_cpu_disable(unsigned int cpu) static void cpu_psci_cpu_die(unsigned int cpu) { - int ret; /* * There are no known implementations of PSCI actually using the * power state field, pass a sensible default for now. @@ -77,9 +76,7 @@ static void cpu_psci_cpu_die(unsigned int cpu) u32 state = PSCI_POWER_STATE_TYPE_POWER_DOWN << PSCI_0_2_POWER_STATE_TYPE_SHIFT; - ret = psci_ops.cpu_off(state); - - pr_crit("unable to power off CPU%u (%d)\n", cpu, ret); + psci_ops.cpu_off(state); } static int cpu_psci_cpu_kill(unsigned int cpu) diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index e8574b95bda8..947dbe5be43f 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -1496,8 +1496,8 @@ static int valid_native_regs(struct user_pt_regs *regs) */ int valid_user_regs(struct user_pt_regs *regs, struct task_struct *task) { - if (!test_tsk_thread_flag(task, TIF_SINGLESTEP)) - regs->pstate &= ~DBG_SPSR_SS; + /* https://lore.kernel.org/lkml/20191118131525.GA4180@willie-the-truck */ + user_regs_reset_single_step(regs, task); if (is_compat_thread(task_thread_info(task))) return valid_compat_regs(regs); diff --git a/arch/arm64/kernel/vdso/vdso.lds.S b/arch/arm64/kernel/vdso/vdso.lds.S index beca249bc2f3..b3e6c4d5b75c 100644 --- a/arch/arm64/kernel/vdso/vdso.lds.S +++ b/arch/arm64/kernel/vdso/vdso.lds.S @@ -39,6 +39,13 @@ SECTIONS .gnu.version_d : { *(.gnu.version_d) } .gnu.version_r : { *(.gnu.version_r) } + /* + * Discard .note.gnu.property sections which are unused and have + * different alignment requirement from vDSO note sections. + */ + /DISCARD/ : { + *(.note.GNU-stack .note.gnu.property) + } .note : { *(.note.*) } :text :note . = ALIGN(16); @@ -59,7 +66,6 @@ SECTIONS PROVIDE(end = .); /DISCARD/ : { - *(.note.GNU-stack) *(.data .data.* .gnu.linkonce.d.* .sdata*) *(.bss .sbss .dynbss .dynsbss) } diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index 6edfdf5b061d..4c11d3e64aef 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -24,6 +24,13 @@ ENTRY(_text) jiffies = jiffies_64; + +#define HYPERVISOR_EXTABLE \ + . = ALIGN(SZ_8); \ + VMLINUX_SYMBOL(__start___kvm_ex_table) = .; \ + *(__kvm_ex_table) \ + VMLINUX_SYMBOL(__stop___kvm_ex_table) = .; + #define HYPERVISOR_TEXT \ /* \ * Align to 4 KB so that \ @@ -39,6 +46,7 @@ jiffies = jiffies_64; VMLINUX_SYMBOL(__hyp_idmap_text_end) = .; \ VMLINUX_SYMBOL(__hyp_text_start) = .; \ *(.hyp.text) \ + HYPERVISOR_EXTABLE \ VMLINUX_SYMBOL(__hyp_text_end) = .; #define IDMAP_TEXT \ @@ -154,9 +162,6 @@ SECTIONS *(.altinstructions) __alt_instructions_end = .; } - .altinstr_replacement : { - *(.altinstr_replacement) - } . = ALIGN(PAGE_SIZE); __inittext_end = .; diff --git a/arch/arm64/kvm/debug.c b/arch/arm64/kvm/debug.c index dbadfaf850a7..2da4f45ab0bb 100644 --- a/arch/arm64/kvm/debug.c +++ b/arch/arm64/kvm/debug.c @@ -96,6 +96,7 @@ void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu) * - Debug ROM Address (MDCR_EL2_TDRA) * - OS related registers (MDCR_EL2_TDOSA) * - Statistical profiler (MDCR_EL2_TPMS/MDCR_EL2_E2PB) + * - Self-hosted Trace Filter controls (MDCR_EL2_TTRF) * * Additionally, KVM only traps guest accesses to the debug registers if * the guest is not actively using them (see the KVM_ARM64_DEBUG_DIRTY @@ -118,6 +119,7 @@ void kvm_arm_setup_debug(struct kvm_vcpu *vcpu) vcpu->arch.mdcr_el2 = __this_cpu_read(mdcr_el2) & MDCR_EL2_HPMN_MASK; vcpu->arch.mdcr_el2 |= (MDCR_EL2_TPM | MDCR_EL2_TPMS | + MDCR_EL2_TTRF | MDCR_EL2_TPMCR | MDCR_EL2_TDRA | MDCR_EL2_TDOSA); diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S index dea20651a5f1..cb28c12d0a64 100644 --- a/arch/arm64/kvm/hyp-init.S +++ b/arch/arm64/kvm/hyp-init.S @@ -147,11 +147,15 @@ ENTRY(__kvm_handle_stub_hvc) 1: cmp x0, #HVC_RESET_VECTORS b.ne 1f -reset: + /* - * Reset kvm back to the hyp stub. Do not clobber x0-x4 in - * case we coming via HVC_SOFT_RESTART. + * Set the HVC_RESET_VECTORS return code before entering the common + * path so that we do not clobber x0-x2 in case we are coming via + * HVC_SOFT_RESTART. */ + mov x0, xzr +reset: + /* Reset kvm back to the hyp stub. */ mrs x5, sctlr_el2 ldr x6, =SCTLR_ELx_FLAGS bic x5, x5, x6 // Clear SCTL_M and etc @@ -162,7 +166,6 @@ reset: /* Install stub vectors */ adr_l x5, __hyp_stub_vectors msr vbar_el2, x5 - mov x0, xzr eret 1: /* Bad stub call */ diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S index a360ac6e89e9..4e0eac361f87 100644 --- a/arch/arm64/kvm/hyp/entry.S +++ b/arch/arm64/kvm/hyp/entry.S @@ -17,6 +17,7 @@ #include <linux/linkage.h> +#include <asm/alternative.h> #include <asm/asm-offsets.h> #include <asm/assembler.h> #include <asm/fpsimdmacros.h> @@ -62,6 +63,15 @@ ENTRY(__guest_enter) // Store the host regs save_callee_saved_regs x1 + // Now the host state is stored if we have a pending RAS SError it must + // affect the host. If any asynchronous exception is pending we defer + // the guest entry. + mrs x1, isr_el1 + cbz x1, 1f + mov x0, #ARM_EXCEPTION_IRQ + ret + +1: add x18, x0, #VCPU_CONTEXT // Restore guest regs x0-x17 @@ -135,18 +145,22 @@ ENTRY(__guest_exit) // This is our single instruction exception window. A pending // SError is guaranteed to occur at the earliest when we unmask // it, and at the latest just after the ISB. - .global abort_guest_exit_start abort_guest_exit_start: isb - .global abort_guest_exit_end abort_guest_exit_end: + msr daifset, #4 // Mask aborts + ret + + _kvm_extable abort_guest_exit_start, 9997f + _kvm_extable abort_guest_exit_end, 9997f +9997: + msr daifset, #4 // Mask aborts + mov x0, #(1 << ARM_EXIT_WITH_SERROR_BIT) - // If the exception took place, restore the EL1 exception - // context so that we can report some information. - // Merge the exception code with the SError pending bit. - tbz x0, #ARM_EXIT_WITH_SERROR_BIT, 1f + // restore the EL1 exception context so that we can report some + // information. Merge the exception code with the SError pending bit. msr elr_el2, x2 msr esr_el2, x3 msr spsr_el2, x4 diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S index 3c283fd8c8f5..5e041eabdd03 100644 --- a/arch/arm64/kvm/hyp/hyp-entry.S +++ b/arch/arm64/kvm/hyp/hyp-entry.S @@ -25,6 +25,30 @@ #include <asm/kvm_asm.h> #include <asm/kvm_mmu.h> +.macro save_caller_saved_regs_vect + stp x0, x1, [sp, #-16]! + stp x2, x3, [sp, #-16]! + stp x4, x5, [sp, #-16]! + stp x6, x7, [sp, #-16]! + stp x8, x9, [sp, #-16]! + stp x10, x11, [sp, #-16]! + stp x12, x13, [sp, #-16]! + stp x14, x15, [sp, #-16]! + stp x16, x17, [sp, #-16]! +.endm + +.macro restore_caller_saved_regs_vect + ldp x16, x17, [sp], #16 + ldp x14, x15, [sp], #16 + ldp x12, x13, [sp], #16 + ldp x10, x11, [sp], #16 + ldp x8, x9, [sp], #16 + ldp x6, x7, [sp], #16 + ldp x4, x5, [sp], #16 + ldp x2, x3, [sp], #16 + ldp x0, x1, [sp], #16 +.endm + .text .pushsection .hyp.text, "ax" @@ -183,26 +207,24 @@ el1_error: mov x0, #ARM_EXCEPTION_EL1_SERROR b __guest_exit +el2_sync: + save_caller_saved_regs_vect + stp x29, x30, [sp, #-16]! + bl kvm_unexpected_el2_exception + ldp x29, x30, [sp], #16 + restore_caller_saved_regs_vect + + eret + el2_error: - /* - * Only two possibilities: - * 1) Either we come from the exit path, having just unmasked - * PSTATE.A: change the return code to an EL2 fault, and - * carry on, as we're already in a sane state to handle it. - * 2) Or we come from anywhere else, and that's a bug: we panic. - * - * For (1), x0 contains the original return code and x1 doesn't - * contain anything meaningful at that stage. We can reuse them - * as temp registers. - * For (2), who cares? - */ - mrs x0, elr_el2 - adr x1, abort_guest_exit_start - cmp x0, x1 - adr x1, abort_guest_exit_end - ccmp x0, x1, #4, ne - b.ne __hyp_panic - mov x0, #(1 << ARM_EXIT_WITH_SERROR_BIT) + save_caller_saved_regs_vect + stp x29, x30, [sp, #-16]! + + bl kvm_unexpected_el2_exception + + ldp x29, x30, [sp], #16 + restore_caller_saved_regs_vect + eret ENTRY(__hyp_do_panic) @@ -231,7 +253,6 @@ ENDPROC(\label) invalid_vector el2t_irq_invalid invalid_vector el2t_fiq_invalid invalid_vector el2t_error_invalid - invalid_vector el2h_sync_invalid invalid_vector el2h_irq_invalid invalid_vector el2h_fiq_invalid invalid_vector el1_sync_invalid @@ -248,7 +269,7 @@ ENTRY(__kvm_hyp_vector) ventry el2t_fiq_invalid // FIQ EL2t ventry el2t_error_invalid // Error EL2t - ventry el2h_sync_invalid // Synchronous EL2h + ventry el2_sync // Synchronous EL2h ventry el2h_irq_invalid // IRQ EL2h ventry el2h_fiq_invalid // FIQ EL2h ventry el2_error // Error EL2h diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index 4a8fdbb29286..99ae75a43985 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -22,11 +22,15 @@ #include <kvm/arm_psci.h> +#include <asm/extable.h> #include <asm/kvm_asm.h> #include <asm/kvm_emulate.h> #include <asm/kvm_hyp.h> #include <asm/fpsimd.h> +extern struct exception_table_entry __start___kvm_ex_table; +extern struct exception_table_entry __stop___kvm_ex_table; + static bool __hyp_text __fpsimd_enabled_nvhe(void) { return !(read_sysreg(cptr_el2) & CPTR_EL2_TFP); @@ -216,10 +220,10 @@ static bool __hyp_text __translate_far_to_hpfar(u64 far, u64 *hpfar) * saved the guest context yet, and we may return early... */ par = read_sysreg(par_el1); - asm volatile("at s1e1r, %0" : : "r" (far)); - isb(); - - tmp = read_sysreg(par_el1); + if (!__kvm_at("s1e1r", far)) + tmp = read_sysreg(par_el1); + else + tmp = 1; /* back to the guest */ write_sysreg(par, par_el1); if (unlikely(tmp & 1)) @@ -444,7 +448,7 @@ static void __hyp_text __hyp_call_panic_nvhe(u64 spsr, u64 elr, u64 par, * making sure it is a kernel address and not a PC-relative * reference. */ - asm volatile("ldr %0, =__hyp_panic_string" : "=r" (str_va)); + asm volatile("ldr %0, =%1" : "=r" (str_va) : "S" (__hyp_panic_string)); __hyp_do_panic(str_va, spsr, elr, @@ -486,3 +490,30 @@ void __hyp_text __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt) unreachable(); } + +asmlinkage void __hyp_text kvm_unexpected_el2_exception(void) +{ + unsigned long addr, fixup; + struct kvm_cpu_context *host_ctxt; + struct exception_table_entry *entry, *end; + unsigned long elr_el2 = read_sysreg(elr_el2); + + entry = hyp_symbol_addr(__start___kvm_ex_table); + end = hyp_symbol_addr(__stop___kvm_ex_table); + host_ctxt = __hyp_this_cpu_ptr(kvm_host_cpu_state); + + while (entry < end) { + addr = (unsigned long)&entry->insn + entry->insn; + fixup = (unsigned long)&entry->fixup + entry->fixup; + + if (addr != elr_el2) { + entry++; + continue; + } + + write_sysreg(fixup, elr_el2); + return; + } + + hyp_panic(host_ctxt); +} diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 32ae5c9daac4..1a006101f527 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -470,6 +470,10 @@ static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { u64 pmcr, val; + /* No PMU available, PMCR_EL0 may UNDEF... */ + if (!kvm_arm_support_pmu_v3()) + return; + pmcr = read_sysreg(pmcr_el0); /* * Writable bits of PMCR_EL0 (ARMV8_PMU_PMCR_MASK) are reset to UNKNOWN @@ -1178,9 +1182,9 @@ static const struct sys_reg_desc cp14_regs[] = { { Op1( 0), CRn( 0), CRm( 1), Op2( 0), trap_raz_wi }, DBG_BCR_BVR_WCR_WVR(1), /* DBGDCCINT */ - { Op1( 0), CRn( 0), CRm( 2), Op2( 0), trap_debug32 }, + { Op1( 0), CRn( 0), CRm( 2), Op2( 0), trap_debug32, NULL, cp14_DBGDCCINT }, /* DBGDSCRext */ - { Op1( 0), CRn( 0), CRm( 2), Op2( 2), trap_debug32 }, + { Op1( 0), CRn( 0), CRm( 2), Op2( 2), trap_debug32, NULL, cp14_DBGDSCRext }, DBG_BCR_BVR_WCR_WVR(2), /* DBGDTR[RT]Xint */ { Op1( 0), CRn( 0), CRm( 3), Op2( 0), trap_raz_wi }, @@ -1195,7 +1199,7 @@ static const struct sys_reg_desc cp14_regs[] = { { Op1( 0), CRn( 0), CRm( 6), Op2( 2), trap_raz_wi }, DBG_BCR_BVR_WCR_WVR(6), /* DBGVCR */ - { Op1( 0), CRn( 0), CRm( 7), Op2( 0), trap_debug32 }, + { Op1( 0), CRn( 0), CRm( 7), Op2( 0), trap_debug32, NULL, cp14_DBGVCR }, DBG_BCR_BVR_WCR_WVR(7), DBG_BCR_BVR_WCR_WVR(8), DBG_BCR_BVR_WCR_WVR(9), @@ -1286,6 +1290,7 @@ static const struct sys_reg_desc cp15_regs[] = { { Op1( 0), CRn( 2), CRm( 0), Op2( 0), access_vm_reg, NULL, c2_TTBR0 }, { Op1( 0), CRn( 2), CRm( 0), Op2( 1), access_vm_reg, NULL, c2_TTBR1 }, { Op1( 0), CRn( 2), CRm( 0), Op2( 2), access_vm_reg, NULL, c2_TTBCR }, + { Op1( 0), CRn( 2), CRm( 0), Op2( 3), access_vm_reg, NULL, c2_TTBCR2 }, { Op1( 0), CRn( 3), CRm( 0), Op2( 0), access_vm_reg, NULL, c3_DACR }, { Op1( 0), CRn( 5), CRm( 0), Op2( 0), access_vm_reg, NULL, c5_DFSR }, { Op1( 0), CRn( 5), CRm( 0), Op2( 1), access_vm_reg, NULL, c5_IFSR }, diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c index e9c843e0c172..6b42af182aa7 100644 --- a/arch/arm64/mm/numa.c +++ b/arch/arm64/mm/numa.c @@ -58,7 +58,11 @@ EXPORT_SYMBOL(node_to_cpumask_map); */ const struct cpumask *cpumask_of_node(int node) { - if (WARN_ON(node >= nr_node_ids)) + + if (node == NUMA_NO_NODE) + return cpu_all_mask; + + if (WARN_ON(node < 0 || node >= nr_node_ids)) return cpu_none_mask; if (WARN_ON(node_to_cpumask_map[node] == NULL)) diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index ecbc060807d2..a9ff7fb41832 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -455,8 +455,8 @@ ENTRY(__cpu_setup) cmp x9, #2 b.lt 1f #ifdef CONFIG_ARM64_ERRATUM_1024718 - /* Disable hardware DBM on Cortex-A55 r0p0, r0p1 & r1p0 */ - cpu_midr_match MIDR_CORTEX_A55, MIDR_CPU_VAR_REV(0, 0), MIDR_CPU_VAR_REV(1, 0), x1, x2, x3, x4 + /* Disable hardware DBM on Cortex-A55 all versions */ + cpu_midr_match MIDR_CORTEX_A55, MIDR_CPU_VAR_REV(0, 0), MIDR_CPU_VAR_REV(0xf, 0xf), x1, x2, x3, x4 cbnz x1, 1f #endif orr x10, x10, #TCR_HD // hardware Dirty flag update |