diff options
Diffstat (limited to 'arch')
213 files changed, 1961 insertions, 854 deletions
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index d0040fb67c36..d5bf16462bdb 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -118,7 +118,7 @@ config ARM select HAVE_KERNEL_XZ select HAVE_KPROBES if !XIP_KERNEL && !CPU_ENDIAN_BE32 && !CPU_V7M select HAVE_KRETPROBES if HAVE_KPROBES - select HAVE_LD_DEAD_CODE_DATA_ELIMINATION if (LD_VERSION >= 23600 || LD_CAN_USE_KEEP_IN_OVERLAY) + select HAVE_LD_DEAD_CODE_DATA_ELIMINATION if (LD_VERSION >= 23600 || LD_IS_LLD) && LD_CAN_USE_KEEP_IN_OVERLAY select HAVE_MOD_ARCH_SPECIFIC select HAVE_NMI select HAVE_OPTPROBES if !THUMB2_KERNEL diff --git a/arch/arm/Makefile b/arch/arm/Makefile index aafebf145738..dee8c9fe25a2 100644 --- a/arch/arm/Makefile +++ b/arch/arm/Makefile @@ -149,7 +149,7 @@ endif # Need -Uarm for gcc < 3.x KBUILD_CPPFLAGS +=$(cpp-y) KBUILD_CFLAGS +=$(CFLAGS_ABI) $(CFLAGS_ISA) $(arch-y) $(tune-y) $(call cc-option,-mshort-load-bytes,$(call cc-option,-malignment-traps,)) -msoft-float -Uarm -KBUILD_AFLAGS +=$(CFLAGS_ABI) $(AFLAGS_ISA) -Wa,$(arch-y) $(tune-y) -include asm/unified.h -msoft-float +KBUILD_AFLAGS +=$(CFLAGS_ABI) $(AFLAGS_ISA) -Wa,$(arch-y) $(tune-y) -include $(srctree)/arch/arm/include/asm/unified.h -msoft-float CHECKFLAGS += -D__arm__ diff --git a/arch/arm/boot/dts/nxp/imx/imx6ul-kontron-bl-common.dtsi b/arch/arm/boot/dts/nxp/imx/imx6ul-kontron-bl-common.dtsi index 29d2f86d5e34..f4c45e964daf 100644 --- a/arch/arm/boot/dts/nxp/imx/imx6ul-kontron-bl-common.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx6ul-kontron-bl-common.dtsi @@ -168,7 +168,6 @@ pinctrl-0 = <&pinctrl_uart2>; linux,rs485-enabled-at-boot-time; rs485-rx-during-tx; - rs485-rts-active-low; uart-has-rtscts; status = "okay"; }; diff --git a/arch/arm/boot/dts/nxp/vf/vfxxx.dtsi b/arch/arm/boot/dts/nxp/vf/vfxxx.dtsi index acccf9a3c898..27422a343f14 100644 --- a/arch/arm/boot/dts/nxp/vf/vfxxx.dtsi +++ b/arch/arm/boot/dts/nxp/vf/vfxxx.dtsi @@ -604,7 +604,7 @@ ftm: ftm@400b8000 { compatible = "fsl,ftm-timer"; - reg = <0x400b8000 0x1000 0x400b9000 0x1000>; + reg = <0x400b8000 0x1000>, <0x400b9000 0x1000>; interrupts = <44 IRQ_TYPE_LEVEL_HIGH>; clock-names = "ftm-evt", "ftm-src", "ftm-evt-counter-en", "ftm-src-counter-en"; diff --git a/arch/arm/boot/dts/ti/omap/am335x-boneblack.dts b/arch/arm/boot/dts/ti/omap/am335x-boneblack.dts index 16b567e3cb47..b4fdcf9c02b5 100644 --- a/arch/arm/boot/dts/ti/omap/am335x-boneblack.dts +++ b/arch/arm/boot/dts/ti/omap/am335x-boneblack.dts @@ -35,7 +35,7 @@ "P9_18 [spi0_d1]", "P9_17 [spi0_cs0]", "[mmc0_cd]", - "P8_42A [ecappwm0]", + "P9_42A [ecappwm0]", "P8_35 [lcd d12]", "P8_33 [lcd d13]", "P8_31 [lcd d14]", diff --git a/arch/arm/crypto/aes-neonbs-glue.c b/arch/arm/crypto/aes-neonbs-glue.c index f6be80b5938b..2fad3a0c0563 100644 --- a/arch/arm/crypto/aes-neonbs-glue.c +++ b/arch/arm/crypto/aes-neonbs-glue.c @@ -232,7 +232,7 @@ static int ctr_encrypt(struct skcipher_request *req) while (walk.nbytes > 0) { const u8 *src = walk.src.virt.addr; u8 *dst = walk.dst.virt.addr; - int bytes = walk.nbytes; + unsigned int bytes = walk.nbytes; if (unlikely(bytes < AES_BLOCK_SIZE)) src = dst = memcpy(buf + sizeof(buf) - bytes, diff --git a/arch/arm/mach-omap2/clockdomain.h b/arch/arm/mach-omap2/clockdomain.h index c36fb2721261..86a2f9e5d0ef 100644 --- a/arch/arm/mach-omap2/clockdomain.h +++ b/arch/arm/mach-omap2/clockdomain.h @@ -48,6 +48,7 @@ #define CLKDM_NO_AUTODEPS (1 << 4) #define CLKDM_ACTIVE_WITH_MPU (1 << 5) #define CLKDM_MISSING_IDLE_REPORTING (1 << 6) +#define CLKDM_STANDBY_FORCE_WAKEUP BIT(7) #define CLKDM_CAN_HWSUP (CLKDM_CAN_ENABLE_AUTO | CLKDM_CAN_DISABLE_AUTO) #define CLKDM_CAN_SWSUP (CLKDM_CAN_FORCE_SLEEP | CLKDM_CAN_FORCE_WAKEUP) diff --git a/arch/arm/mach-omap2/clockdomains33xx_data.c b/arch/arm/mach-omap2/clockdomains33xx_data.c index 87f4e927eb18..c05a3c07d448 100644 --- a/arch/arm/mach-omap2/clockdomains33xx_data.c +++ b/arch/arm/mach-omap2/clockdomains33xx_data.c @@ -19,7 +19,7 @@ static struct clockdomain l4ls_am33xx_clkdm = { .pwrdm = { .name = "per_pwrdm" }, .cm_inst = AM33XX_CM_PER_MOD, .clkdm_offs = AM33XX_CM_PER_L4LS_CLKSTCTRL_OFFSET, - .flags = CLKDM_CAN_SWSUP, + .flags = CLKDM_CAN_SWSUP | CLKDM_STANDBY_FORCE_WAKEUP, }; static struct clockdomain l3s_am33xx_clkdm = { diff --git a/arch/arm/mach-omap2/cm33xx.c b/arch/arm/mach-omap2/cm33xx.c index acdf72a541c0..a4dd42abda89 100644 --- a/arch/arm/mach-omap2/cm33xx.c +++ b/arch/arm/mach-omap2/cm33xx.c @@ -20,6 +20,9 @@ #include "cm-regbits-34xx.h" #include "cm-regbits-33xx.h" #include "prm33xx.h" +#if IS_ENABLED(CONFIG_SUSPEND) +#include <linux/suspend.h> +#endif /* * CLKCTRL_IDLEST_*: possible values for the CM_*_CLKCTRL.IDLEST bitfield: @@ -328,8 +331,17 @@ static int am33xx_clkdm_clk_disable(struct clockdomain *clkdm) { bool hwsup = false; +#if IS_ENABLED(CONFIG_SUSPEND) + /* + * In case of standby, Don't put the l4ls clk domain to sleep. + * Since CM3 PM FW doesn't wake-up/enable the l4ls clk domain + * upon wake-up, CM3 PM FW fails to wake-up th MPU. + */ + if (pm_suspend_target_state == PM_SUSPEND_STANDBY && + (clkdm->flags & CLKDM_STANDBY_FORCE_WAKEUP)) + return 0; +#endif hwsup = am33xx_cm_is_clkdm_in_hwsup(clkdm->cm_inst, clkdm->clkdm_offs); - if (!hwsup && (clkdm->flags & CLKDM_CAN_FORCE_SLEEP)) am33xx_clkdm_sleep(clkdm); diff --git a/arch/arm/mach-omap2/pmic-cpcap.c b/arch/arm/mach-omap2/pmic-cpcap.c index 4f31e61c0c90..9f9a20274db8 100644 --- a/arch/arm/mach-omap2/pmic-cpcap.c +++ b/arch/arm/mach-omap2/pmic-cpcap.c @@ -264,7 +264,11 @@ int __init omap4_cpcap_init(void) static int __init cpcap_late_init(void) { - omap4_vc_set_pmic_signaling(PWRDM_POWER_RET); + if (!of_find_compatible_node(NULL, NULL, "motorola,cpcap")) + return 0; + + if (soc_is_omap443x() || soc_is_omap446x() || soc_is_omap447x()) + omap4_vc_set_pmic_signaling(PWRDM_POWER_RET); return 0; } diff --git a/arch/arm/mach-rockchip/platsmp.c b/arch/arm/mach-rockchip/platsmp.c index 36915a073c23..f432d22bfed8 100644 --- a/arch/arm/mach-rockchip/platsmp.c +++ b/arch/arm/mach-rockchip/platsmp.c @@ -279,11 +279,6 @@ static void __init rockchip_smp_prepare_cpus(unsigned int max_cpus) } if (read_cpuid_part() == ARM_CPU_PART_CORTEX_A9) { - if (rockchip_smp_prepare_sram(node)) { - of_node_put(node); - return; - } - /* enable the SCU power domain */ pmu_set_power_domain(PMU_PWRDN_SCU, true); @@ -316,11 +311,19 @@ static void __init rockchip_smp_prepare_cpus(unsigned int max_cpus) asm ("mrc p15, 1, %0, c9, c0, 2\n" : "=r" (l2ctlr)); ncores = ((l2ctlr >> 24) & 0x3) + 1; } - of_node_put(node); /* Make sure that all cores except the first are really off */ for (i = 1; i < ncores; i++) pmu_set_power_domain(0 + i, false); + + if (read_cpuid_part() == ARM_CPU_PART_CORTEX_A9) { + if (rockchip_smp_prepare_sram(node)) { + of_node_put(node); + return; + } + } + + of_node_put(node); } static void __init rk3036_smp_prepare_cpus(unsigned int max_cpus) diff --git a/arch/arm/mach-tegra/reset.c b/arch/arm/mach-tegra/reset.c index d5c805adf7a8..ea706fac6358 100644 --- a/arch/arm/mach-tegra/reset.c +++ b/arch/arm/mach-tegra/reset.c @@ -63,7 +63,7 @@ static void __init tegra_cpu_reset_handler_enable(void) BUG_ON(is_enabled); BUG_ON(tegra_cpu_reset_handler_size > TEGRA_IRAM_RESET_HANDLER_SIZE); - memcpy(iram_base, (void *)__tegra_cpu_reset_handler_start, + memcpy_toio(iram_base, (void *)__tegra_cpu_reset_handler_start, tegra_cpu_reset_handler_size); err = call_firmware_op(set_cpu_boot_addr, 0, reset_address); diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c index 89f1c97f3079..cbf5a03d2b18 100644 --- a/arch/arm/mm/ioremap.c +++ b/arch/arm/mm/ioremap.c @@ -515,7 +515,5 @@ void __init early_ioremap_init(void) bool arch_memremap_can_ram_remap(resource_size_t offset, size_t size, unsigned long flags) { - unsigned long pfn = PHYS_PFN(offset); - - return memblock_is_map_memory(pfn); + return memblock_is_map_memory(offset); } diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 19a4988621ac..88029d38b3c6 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -48,7 +48,7 @@ KBUILD_CFLAGS += $(CC_FLAGS_NO_FPU) \ KBUILD_CFLAGS += $(call cc-disable-warning, psabi) KBUILD_AFLAGS += $(compat_vdso) -ifeq ($(call test-ge, $(CONFIG_RUSTC_VERSION), 108500),y) +ifeq ($(call rustc-min-version, 108500),y) KBUILD_RUSTFLAGS += --target=aarch64-unknown-none-softfloat else KBUILD_RUSTFLAGS += --target=aarch64-unknown-none -Ctarget-feature="-neon" diff --git a/arch/arm64/boot/dts/apple/t8103-jxxx.dtsi b/arch/arm64/boot/dts/apple/t8103-jxxx.dtsi index 5988a4eb6efa..cb78ce7af0b3 100644 --- a/arch/arm64/boot/dts/apple/t8103-jxxx.dtsi +++ b/arch/arm64/boot/dts/apple/t8103-jxxx.dtsi @@ -71,7 +71,7 @@ */ &port00 { bus-range = <1 1>; - wifi0: network@0,0 { + wifi0: wifi@0,0 { compatible = "pci14e4,4425"; reg = <0x10000 0x0 0x0 0x0 0x0>; /* To be filled by the loader */ diff --git a/arch/arm64/boot/dts/exynos/google/gs101.dtsi b/arch/arm64/boot/dts/exynos/google/gs101.dtsi index b8f8255f840b..7caa2f3ef134 100644 --- a/arch/arm64/boot/dts/exynos/google/gs101.dtsi +++ b/arch/arm64/boot/dts/exynos/google/gs101.dtsi @@ -155,6 +155,7 @@ idle-state-name = "c2"; compatible = "arm,idle-state"; arm,psci-suspend-param = <0x0010000>; + local-timer-stop; entry-latency-us = <70>; exit-latency-us = <160>; min-residency-us = <2000>; @@ -164,6 +165,7 @@ idle-state-name = "c2"; compatible = "arm,idle-state"; arm,psci-suspend-param = <0x0010000>; + local-timer-stop; entry-latency-us = <150>; exit-latency-us = <190>; min-residency-us = <2500>; @@ -173,6 +175,7 @@ idle-state-name = "c2"; compatible = "arm,idle-state"; arm,psci-suspend-param = <0x0010000>; + local-timer-stop; entry-latency-us = <235>; exit-latency-us = <220>; min-residency-us = <3500>; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi index 0baf256b4400..983b2f0e8797 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi @@ -687,11 +687,12 @@ }; wdog0: watchdog@2ad0000 { - compatible = "fsl,imx21-wdt"; + compatible = "fsl,ls1046a-wdt", "fsl,imx21-wdt"; reg = <0x0 0x2ad0000 0x0 0x10000>; interrupts = <GIC_SPI 83 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL QORIQ_CLK_PLL_DIV(2)>; + big-endian; }; edma0: dma-controller@2c00000 { diff --git a/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi index 9ba0cb89fa24..c0f00835e47d 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi @@ -286,6 +286,8 @@ pinctrl-0 = <&pinctrl_usdhc3>; pinctrl-1 = <&pinctrl_usdhc3_100mhz>; pinctrl-2 = <&pinctrl_usdhc3_200mhz>; + assigned-clocks = <&clk IMX8MM_CLK_USDHC3>; + assigned-clock-rates = <400000000>; bus-width = <8>; non-removable; status = "okay"; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi index d9b13c87f93b..c579a45273f0 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi @@ -484,6 +484,7 @@ }; reg_nvcc_sd: LDO5 { + regulator-always-on; regulator-max-microvolt = <3300000>; regulator-min-microvolt = <1800000>; regulator-name = "On-module +V3.3_1.8_SD (LDO5)"; diff --git a/arch/arm64/boot/dts/freescale/imx8mn-beacon-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mn-beacon-som.dtsi index bb11590473a4..353d0c9ff35c 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn-beacon-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn-beacon-som.dtsi @@ -297,6 +297,8 @@ pinctrl-0 = <&pinctrl_usdhc3>; pinctrl-1 = <&pinctrl_usdhc3_100mhz>; pinctrl-2 = <&pinctrl_usdhc3_200mhz>; + assigned-clocks = <&clk IMX8MN_CLK_USDHC3>; + assigned-clock-rates = <400000000>; bus-width = <8>; non-removable; status = "okay"; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw71xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw71xx.dtsi index 2f740d74707b..4bf818873fe3 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw71xx.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw71xx.dtsi @@ -70,7 +70,7 @@ tpm@1 { compatible = "atmel,attpm20p", "tcg,tpm_tis-spi"; reg = <0x1>; - spi-max-frequency = <36000000>; + spi-max-frequency = <25000000>; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw72xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw72xx.dtsi index 5ab3ffe9931d..cf747ec6fa16 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw72xx.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw72xx.dtsi @@ -110,7 +110,7 @@ tpm@1 { compatible = "atmel,attpm20p", "tcg,tpm_tis-spi"; reg = <0x1>; - spi-max-frequency = <36000000>; + spi-max-frequency = <25000000>; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi index e2b5e7ac3e46..5eb114d2360a 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi @@ -122,7 +122,7 @@ tpm@1 { compatible = "atmel,attpm20p", "tcg,tpm_tis-spi"; reg = <0x1>; - spi-max-frequency = <36000000>; + spi-max-frequency = <25000000>; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts index d765b7972841..c3647a059d1f 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts @@ -199,7 +199,7 @@ tpm@0 { compatible = "atmel,attpm20p", "tcg,tpm_tis-spi"; reg = <0x0>; - spi-max-frequency = <36000000>; + spi-max-frequency = <25000000>; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx93-tqma9352.dtsi b/arch/arm64/boot/dts/freescale/imx93-tqma9352.dtsi index 2cabdae24227..09385b058664 100644 --- a/arch/arm64/boot/dts/freescale/imx93-tqma9352.dtsi +++ b/arch/arm64/boot/dts/freescale/imx93-tqma9352.dtsi @@ -1,6 +1,6 @@ // SPDX-License-Identifier: (GPL-2.0-or-later OR MIT) /* - * Copyright (c) 2022 TQ-Systems GmbH <linux@ew.tq-group.com>, + * Copyright (c) 2022-2025 TQ-Systems GmbH <linux@ew.tq-group.com>, * D-82229 Seefeld, Germany. * Author: Markus Niebel */ @@ -110,11 +110,11 @@ regulator-ramp-delay = <3125>; }; - /* V_DDRQ - 1.1 LPDDR4 or 0.6 LPDDR4X */ + /* V_DDRQ - 0.6 V for LPDDR4X */ buck2: BUCK2 { regulator-name = "BUCK2"; regulator-min-microvolt = <600000>; - regulator-max-microvolt = <1100000>; + regulator-max-microvolt = <600000>; regulator-boot-on; regulator-always-on; regulator-ramp-delay = <3125>; diff --git a/arch/arm64/boot/dts/freescale/imx95.dtsi b/arch/arm64/boot/dts/freescale/imx95.dtsi index f904d6b1c84b..7365d6538a73 100644 --- a/arch/arm64/boot/dts/freescale/imx95.dtsi +++ b/arch/arm64/boot/dts/freescale/imx95.dtsi @@ -1523,7 +1523,7 @@ <0x9 0 1 0>; reg-names = "dbi","atu", "dbi2", "app", "dma", "addr_space"; num-lanes = <1>; - interrupts = <GIC_SPI 317 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 311 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "dma"; clocks = <&scmi_clk IMX95_CLK_HSIO>, <&scmi_clk IMX95_CLK_HSIOPLL>, diff --git a/arch/arm64/boot/dts/qcom/msm8976.dtsi b/arch/arm64/boot/dts/qcom/msm8976.dtsi index 06af6e5ec578..884b5bb54ba8 100644 --- a/arch/arm64/boot/dts/qcom/msm8976.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8976.dtsi @@ -1330,6 +1330,7 @@ clock-names = "bam_clk"; #dma-cells = <1>; qcom,ee = <0>; + qcom,controlled-remotely; }; blsp1_uart1: serial@78af000 { @@ -1450,6 +1451,7 @@ clock-names = "bam_clk"; #dma-cells = <1>; qcom,ee = <0>; + qcom,controlled-remotely; }; blsp2_uart2: serial@7af0000 { diff --git a/arch/arm64/boot/dts/qcom/sa8775p.dtsi b/arch/arm64/boot/dts/qcom/sa8775p.dtsi index b28fa598cebb..60f3b545304b 100644 --- a/arch/arm64/boot/dts/qcom/sa8775p.dtsi +++ b/arch/arm64/boot/dts/qcom/sa8775p.dtsi @@ -3797,8 +3797,8 @@ interrupts-extended = <&intc GIC_SPI 768 IRQ_TYPE_EDGE_RISING>, <&smp2p_gpdsp0_in 0 0>, - <&smp2p_gpdsp0_in 2 0>, <&smp2p_gpdsp0_in 1 0>, + <&smp2p_gpdsp0_in 2 0>, <&smp2p_gpdsp0_in 3 0>; interrupt-names = "wdog", "fatal", "ready", "handover", "stop-ack"; @@ -3840,8 +3840,8 @@ interrupts-extended = <&intc GIC_SPI 624 IRQ_TYPE_EDGE_RISING>, <&smp2p_gpdsp1_in 0 0>, - <&smp2p_gpdsp1_in 2 0>, <&smp2p_gpdsp1_in 1 0>, + <&smp2p_gpdsp1_in 2 0>, <&smp2p_gpdsp1_in 3 0>; interrupt-names = "wdog", "fatal", "ready", "handover", "stop-ack"; @@ -3965,8 +3965,8 @@ interrupts-extended = <&intc GIC_SPI 578 IRQ_TYPE_EDGE_RISING>, <&smp2p_cdsp0_in 0 IRQ_TYPE_EDGE_RISING>, - <&smp2p_cdsp0_in 2 IRQ_TYPE_EDGE_RISING>, <&smp2p_cdsp0_in 1 IRQ_TYPE_EDGE_RISING>, + <&smp2p_cdsp0_in 2 IRQ_TYPE_EDGE_RISING>, <&smp2p_cdsp0_in 3 IRQ_TYPE_EDGE_RISING>; interrupt-names = "wdog", "fatal", "ready", "handover", "stop-ack"; @@ -4097,8 +4097,8 @@ interrupts-extended = <&intc GIC_SPI 798 IRQ_TYPE_EDGE_RISING>, <&smp2p_cdsp1_in 0 IRQ_TYPE_EDGE_RISING>, - <&smp2p_cdsp1_in 2 IRQ_TYPE_EDGE_RISING>, <&smp2p_cdsp1_in 1 IRQ_TYPE_EDGE_RISING>, + <&smp2p_cdsp1_in 2 IRQ_TYPE_EDGE_RISING>, <&smp2p_cdsp1_in 3 IRQ_TYPE_EDGE_RISING>; interrupt-names = "wdog", "fatal", "ready", "handover", "stop-ack"; @@ -4253,8 +4253,8 @@ interrupts-extended = <&pdc 6 IRQ_TYPE_EDGE_RISING>, <&smp2p_adsp_in 0 IRQ_TYPE_EDGE_RISING>, - <&smp2p_adsp_in 2 IRQ_TYPE_EDGE_RISING>, <&smp2p_adsp_in 1 IRQ_TYPE_EDGE_RISING>, + <&smp2p_adsp_in 2 IRQ_TYPE_EDGE_RISING>, <&smp2p_adsp_in 3 IRQ_TYPE_EDGE_RISING>; interrupt-names = "wdog", "fatal", "ready", "handover", "stop-ack"; diff --git a/arch/arm64/boot/dts/qcom/sc7180.dtsi b/arch/arm64/boot/dts/qcom/sc7180.dtsi index 249b257fc6a7..6ae5ca00c718 100644 --- a/arch/arm64/boot/dts/qcom/sc7180.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7180.dtsi @@ -3524,18 +3524,18 @@ #interrupt-cells = <4>; }; - sram@146aa000 { + sram@14680000 { compatible = "qcom,sc7180-imem", "syscon", "simple-mfd"; - reg = <0 0x146aa000 0 0x2000>; + reg = <0 0x14680000 0 0x2e000>; #address-cells = <1>; #size-cells = <1>; - ranges = <0 0 0x146aa000 0x2000>; + ranges = <0 0 0x14680000 0x2e000>; - pil-reloc@94c { + pil-reloc@2a94c { compatible = "qcom,pil-reloc-info"; - reg = <0x94c 0xc8>; + reg = <0x2a94c 0xc8>; }; }; diff --git a/arch/arm64/boot/dts/qcom/sdm845.dtsi b/arch/arm64/boot/dts/qcom/sdm845.dtsi index 0a0cef9dfcc4..9bf7a405a964 100644 --- a/arch/arm64/boot/dts/qcom/sdm845.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm845.dtsi @@ -5074,18 +5074,18 @@ #interrupt-cells = <4>; }; - sram@146bf000 { + sram@14680000 { compatible = "qcom,sdm845-imem", "syscon", "simple-mfd"; - reg = <0 0x146bf000 0 0x1000>; + reg = <0 0x14680000 0 0x40000>; #address-cells = <1>; #size-cells = <1>; - ranges = <0 0 0x146bf000 0x1000>; + ranges = <0 0 0x14680000 0x40000>; - pil-reloc@94c { + pil-reloc@3f94c { compatible = "qcom,pil-reloc-info"; - reg = <0x94c 0xc8>; + reg = <0x3f94c 0xc8>; }; }; diff --git a/arch/arm64/boot/dts/qcom/sm8650.dtsi b/arch/arm64/boot/dts/qcom/sm8650.dtsi index edde21972f5a..bd91624bd3bf 100644 --- a/arch/arm64/boot/dts/qcom/sm8650.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8650.dtsi @@ -68,18 +68,18 @@ #address-cells = <2>; #size-cells = <0>; - CPU0: cpu@0 { + cpu0: cpu@0 { device_type = "cpu"; compatible = "arm,cortex-a520"; reg = <0 0>; clocks = <&cpufreq_hw 0>; - power-domains = <&CPU_PD0>; + power-domains = <&cpu_pd0>; power-domain-names = "psci"; enable-method = "psci"; - next-level-cache = <&L2_0>; + next-level-cache = <&l2_0>; capacity-dmips-mhz = <1024>; dynamic-power-coefficient = <100>; @@ -87,13 +87,13 @@ #cooling-cells = <2>; - L2_0: l2-cache { + l2_0: l2-cache { compatible = "cache"; cache-level = <2>; cache-unified; - next-level-cache = <&L3_0>; + next-level-cache = <&l3_0>; - L3_0: l3-cache { + l3_0: l3-cache { compatible = "cache"; cache-level = <3>; cache-unified; @@ -101,18 +101,18 @@ }; }; - CPU1: cpu@100 { + cpu1: cpu@100 { device_type = "cpu"; compatible = "arm,cortex-a520"; reg = <0 0x100>; clocks = <&cpufreq_hw 0>; - power-domains = <&CPU_PD1>; + power-domains = <&cpu_pd1>; power-domain-names = "psci"; enable-method = "psci"; - next-level-cache = <&L2_0>; + next-level-cache = <&l2_0>; capacity-dmips-mhz = <1024>; dynamic-power-coefficient = <100>; @@ -121,18 +121,18 @@ #cooling-cells = <2>; }; - CPU2: cpu@200 { + cpu2: cpu@200 { device_type = "cpu"; compatible = "arm,cortex-a720"; reg = <0 0x200>; clocks = <&cpufreq_hw 3>; - power-domains = <&CPU_PD2>; + power-domains = <&cpu_pd2>; power-domain-names = "psci"; enable-method = "psci"; - next-level-cache = <&L2_200>; + next-level-cache = <&l2_200>; capacity-dmips-mhz = <1792>; dynamic-power-coefficient = <238>; @@ -140,46 +140,53 @@ #cooling-cells = <2>; - L2_200: l2-cache { + l2_200: l2-cache { compatible = "cache"; cache-level = <2>; cache-unified; - next-level-cache = <&L3_0>; + next-level-cache = <&l3_0>; }; }; - CPU3: cpu@300 { + cpu3: cpu@300 { device_type = "cpu"; compatible = "arm,cortex-a720"; reg = <0 0x300>; clocks = <&cpufreq_hw 3>; - power-domains = <&CPU_PD3>; + power-domains = <&cpu_pd3>; power-domain-names = "psci"; enable-method = "psci"; - next-level-cache = <&L2_200>; + next-level-cache = <&l2_300>; capacity-dmips-mhz = <1792>; dynamic-power-coefficient = <238>; qcom,freq-domain = <&cpufreq_hw 3>; #cooling-cells = <2>; + + l2_300: l2-cache { + compatible = "cache"; + cache-level = <2>; + cache-unified; + next-level-cache = <&l3_0>; + }; }; - CPU4: cpu@400 { + cpu4: cpu@400 { device_type = "cpu"; compatible = "arm,cortex-a720"; reg = <0 0x400>; clocks = <&cpufreq_hw 3>; - power-domains = <&CPU_PD4>; + power-domains = <&cpu_pd4>; power-domain-names = "psci"; enable-method = "psci"; - next-level-cache = <&L2_400>; + next-level-cache = <&l2_400>; capacity-dmips-mhz = <1792>; dynamic-power-coefficient = <238>; @@ -187,26 +194,26 @@ #cooling-cells = <2>; - L2_400: l2-cache { + l2_400: l2-cache { compatible = "cache"; cache-level = <2>; cache-unified; - next-level-cache = <&L3_0>; + next-level-cache = <&l3_0>; }; }; - CPU5: cpu@500 { + cpu5: cpu@500 { device_type = "cpu"; compatible = "arm,cortex-a720"; reg = <0 0x500>; clocks = <&cpufreq_hw 1>; - power-domains = <&CPU_PD5>; + power-domains = <&cpu_pd5>; power-domain-names = "psci"; enable-method = "psci"; - next-level-cache = <&L2_500>; + next-level-cache = <&l2_500>; capacity-dmips-mhz = <1792>; dynamic-power-coefficient = <238>; @@ -214,26 +221,26 @@ #cooling-cells = <2>; - L2_500: l2-cache { + l2_500: l2-cache { compatible = "cache"; cache-level = <2>; cache-unified; - next-level-cache = <&L3_0>; + next-level-cache = <&l3_0>; }; }; - CPU6: cpu@600 { + cpu6: cpu@600 { device_type = "cpu"; compatible = "arm,cortex-a720"; reg = <0 0x600>; clocks = <&cpufreq_hw 1>; - power-domains = <&CPU_PD6>; + power-domains = <&cpu_pd6>; power-domain-names = "psci"; enable-method = "psci"; - next-level-cache = <&L2_600>; + next-level-cache = <&l2_600>; capacity-dmips-mhz = <1792>; dynamic-power-coefficient = <238>; @@ -241,26 +248,26 @@ #cooling-cells = <2>; - L2_600: l2-cache { + l2_600: l2-cache { compatible = "cache"; cache-level = <2>; cache-unified; - next-level-cache = <&L3_0>; + next-level-cache = <&l3_0>; }; }; - CPU7: cpu@700 { + cpu7: cpu@700 { device_type = "cpu"; compatible = "arm,cortex-x4"; reg = <0 0x700>; clocks = <&cpufreq_hw 2>; - power-domains = <&CPU_PD7>; + power-domains = <&cpu_pd7>; power-domain-names = "psci"; enable-method = "psci"; - next-level-cache = <&L2_700>; + next-level-cache = <&l2_700>; capacity-dmips-mhz = <1894>; dynamic-power-coefficient = <588>; @@ -268,46 +275,46 @@ #cooling-cells = <2>; - L2_700: l2-cache { + l2_700: l2-cache { compatible = "cache"; cache-level = <2>; cache-unified; - next-level-cache = <&L3_0>; + next-level-cache = <&l3_0>; }; }; cpu-map { cluster0 { core0 { - cpu = <&CPU0>; + cpu = <&cpu0>; }; core1 { - cpu = <&CPU1>; + cpu = <&cpu1>; }; core2 { - cpu = <&CPU2>; + cpu = <&cpu2>; }; core3 { - cpu = <&CPU3>; + cpu = <&cpu3>; }; core4 { - cpu = <&CPU4>; + cpu = <&cpu4>; }; core5 { - cpu = <&CPU5>; + cpu = <&cpu5>; }; core6 { - cpu = <&CPU6>; + cpu = <&cpu6>; }; core7 { - cpu = <&CPU7>; + cpu = <&cpu7>; }; }; }; @@ -315,7 +322,7 @@ idle-states { entry-method = "psci"; - SILVER_CPU_SLEEP_0: cpu-sleep-0-0 { + silver_cpu_sleep_0: cpu-sleep-0-0 { compatible = "arm,idle-state"; idle-state-name = "silver-rail-power-collapse"; arm,psci-suspend-param = <0x40000004>; @@ -325,7 +332,7 @@ local-timer-stop; }; - GOLD_CPU_SLEEP_0: cpu-sleep-1-0 { + gold_cpu_sleep_0: cpu-sleep-1-0 { compatible = "arm,idle-state"; idle-state-name = "gold-rail-power-collapse"; arm,psci-suspend-param = <0x40000004>; @@ -335,7 +342,7 @@ local-timer-stop; }; - GOLD_PLUS_CPU_SLEEP_0: cpu-sleep-2-0 { + gold_plus_cpu_sleep_0: cpu-sleep-2-0 { compatible = "arm,idle-state"; idle-state-name = "gold-plus-rail-power-collapse"; arm,psci-suspend-param = <0x40000004>; @@ -347,7 +354,7 @@ }; domain-idle-states { - CLUSTER_SLEEP_0: cluster-sleep-0 { + cluster_sleep_0: cluster-sleep-0 { compatible = "domain-idle-state"; arm,psci-suspend-param = <0x41000044>; entry-latency-us = <750>; @@ -355,7 +362,7 @@ min-residency-us = <9144>; }; - CLUSTER_SLEEP_1: cluster-sleep-1 { + cluster_sleep_1: cluster-sleep-1 { compatible = "domain-idle-state"; arm,psci-suspend-param = <0x4100c344>; entry-latency-us = <2800>; @@ -411,58 +418,58 @@ compatible = "arm,psci-1.0"; method = "smc"; - CPU_PD0: power-domain-cpu0 { + cpu_pd0: power-domain-cpu0 { #power-domain-cells = <0>; - power-domains = <&CLUSTER_PD>; - domain-idle-states = <&SILVER_CPU_SLEEP_0>; + power-domains = <&cluster_pd>; + domain-idle-states = <&silver_cpu_sleep_0>; }; - CPU_PD1: power-domain-cpu1 { + cpu_pd1: power-domain-cpu1 { #power-domain-cells = <0>; - power-domains = <&CLUSTER_PD>; - domain-idle-states = <&SILVER_CPU_SLEEP_0>; + power-domains = <&cluster_pd>; + domain-idle-states = <&silver_cpu_sleep_0>; }; - CPU_PD2: power-domain-cpu2 { + cpu_pd2: power-domain-cpu2 { #power-domain-cells = <0>; - power-domains = <&CLUSTER_PD>; - domain-idle-states = <&SILVER_CPU_SLEEP_0>; + power-domains = <&cluster_pd>; + domain-idle-states = <&gold_cpu_sleep_0>; }; - CPU_PD3: power-domain-cpu3 { + cpu_pd3: power-domain-cpu3 { #power-domain-cells = <0>; - power-domains = <&CLUSTER_PD>; - domain-idle-states = <&GOLD_CPU_SLEEP_0>; + power-domains = <&cluster_pd>; + domain-idle-states = <&gold_cpu_sleep_0>; }; - CPU_PD4: power-domain-cpu4 { + cpu_pd4: power-domain-cpu4 { #power-domain-cells = <0>; - power-domains = <&CLUSTER_PD>; - domain-idle-states = <&GOLD_CPU_SLEEP_0>; + power-domains = <&cluster_pd>; + domain-idle-states = <&gold_cpu_sleep_0>; }; - CPU_PD5: power-domain-cpu5 { + cpu_pd5: power-domain-cpu5 { #power-domain-cells = <0>; - power-domains = <&CLUSTER_PD>; - domain-idle-states = <&GOLD_CPU_SLEEP_0>; + power-domains = <&cluster_pd>; + domain-idle-states = <&gold_cpu_sleep_0>; }; - CPU_PD6: power-domain-cpu6 { + cpu_pd6: power-domain-cpu6 { #power-domain-cells = <0>; - power-domains = <&CLUSTER_PD>; - domain-idle-states = <&GOLD_CPU_SLEEP_0>; + power-domains = <&cluster_pd>; + domain-idle-states = <&gold_cpu_sleep_0>; }; - CPU_PD7: power-domain-cpu7 { + cpu_pd7: power-domain-cpu7 { #power-domain-cells = <0>; - power-domains = <&CLUSTER_PD>; - domain-idle-states = <&GOLD_PLUS_CPU_SLEEP_0>; + power-domains = <&cluster_pd>; + domain-idle-states = <&gold_plus_cpu_sleep_0>; }; - CLUSTER_PD: power-domain-cluster { + cluster_pd: power-domain-cluster { #power-domain-cells = <0>; - domain-idle-states = <&CLUSTER_SLEEP_0>, - <&CLUSTER_SLEEP_1>; + domain-idle-states = <&cluster_sleep_0>, + <&cluster_sleep_1>; }; }; @@ -5233,7 +5240,7 @@ <GIC_SPI 4 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 5 IRQ_TYPE_LEVEL_HIGH>; - power-domains = <&CLUSTER_PD>; + power-domains = <&cluster_pd>; qcom,tcs-offset = <0xd00>; qcom,drv-id = <2>; diff --git a/arch/arm64/boot/dts/qcom/x1e78100-lenovo-thinkpad-t14s.dts b/arch/arm64/boot/dts/qcom/x1e78100-lenovo-thinkpad-t14s.dts index b1fa8f3558b3..02ae736a2205 100644 --- a/arch/arm64/boot/dts/qcom/x1e78100-lenovo-thinkpad-t14s.dts +++ b/arch/arm64/boot/dts/qcom/x1e78100-lenovo-thinkpad-t14s.dts @@ -232,6 +232,7 @@ regulator-min-microvolt = <1200000>; regulator-max-microvolt = <1200000>; regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>; + regulator-always-on; }; vreg_l13b_3p0: ldo13 { @@ -253,6 +254,7 @@ regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>; + regulator-always-on; }; vreg_l17b_2p5: ldo17 { diff --git a/arch/arm64/boot/dts/qcom/x1e80100-crd.dts b/arch/arm64/boot/dts/qcom/x1e80100-crd.dts index 044a2f1432fe..e5d0d7d898c3 100644 --- a/arch/arm64/boot/dts/qcom/x1e80100-crd.dts +++ b/arch/arm64/boot/dts/qcom/x1e80100-crd.dts @@ -419,6 +419,7 @@ regulator-min-microvolt = <1200000>; regulator-max-microvolt = <1200000>; regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>; + regulator-always-on; }; vreg_l13b_3p0: ldo13 { @@ -440,6 +441,7 @@ regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>; + regulator-always-on; }; vreg_l16b_2p9: ldo16 { @@ -657,8 +659,8 @@ vreg_l2j_1p2: ldo2 { regulator-name = "vreg_l2j_1p2"; - regulator-min-microvolt = <1200000>; - regulator-max-microvolt = <1200000>; + regulator-min-microvolt = <1256000>; + regulator-max-microvolt = <1256000>; regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>; }; diff --git a/arch/arm64/boot/dts/renesas/beacon-renesom-som.dtsi b/arch/arm64/boot/dts/renesas/beacon-renesom-som.dtsi index 68b04e56ae56..5a15a956702a 100644 --- a/arch/arm64/boot/dts/renesas/beacon-renesom-som.dtsi +++ b/arch/arm64/boot/dts/renesas/beacon-renesom-som.dtsi @@ -62,8 +62,7 @@ compatible = "ethernet-phy-id0022.1640", "ethernet-phy-ieee802.3-c22"; reg = <0>; - interrupt-parent = <&gpio2>; - interrupts = <11 IRQ_TYPE_LEVEL_LOW>; + interrupts-extended = <&gpio2 11 IRQ_TYPE_LEVEL_LOW>; reset-gpios = <&gpio2 10 GPIO_ACTIVE_LOW>; }; }; diff --git a/arch/arm64/boot/dts/renesas/cat875.dtsi b/arch/arm64/boot/dts/renesas/cat875.dtsi index 8c9da8b4bd60..191b051ecfd4 100644 --- a/arch/arm64/boot/dts/renesas/cat875.dtsi +++ b/arch/arm64/boot/dts/renesas/cat875.dtsi @@ -25,8 +25,7 @@ compatible = "ethernet-phy-id001c.c915", "ethernet-phy-ieee802.3-c22"; reg = <0>; - interrupt-parent = <&gpio2>; - interrupts = <21 IRQ_TYPE_LEVEL_LOW>; + interrupts-extended = <&gpio2 21 IRQ_TYPE_LEVEL_LOW>; reset-gpios = <&gpio1 20 GPIO_ACTIVE_LOW>; }; }; diff --git a/arch/arm64/boot/dts/renesas/condor-common.dtsi b/arch/arm64/boot/dts/renesas/condor-common.dtsi index 8b7c0c34eadc..b2d99dfaa0cd 100644 --- a/arch/arm64/boot/dts/renesas/condor-common.dtsi +++ b/arch/arm64/boot/dts/renesas/condor-common.dtsi @@ -166,8 +166,7 @@ "ethernet-phy-ieee802.3-c22"; rxc-skew-ps = <1500>; reg = <0>; - interrupt-parent = <&gpio4>; - interrupts = <23 IRQ_TYPE_LEVEL_LOW>; + interrupts-extended = <&gpio4 23 IRQ_TYPE_LEVEL_LOW>; reset-gpios = <&gpio4 22 GPIO_ACTIVE_LOW>; }; }; diff --git a/arch/arm64/boot/dts/renesas/draak.dtsi b/arch/arm64/boot/dts/renesas/draak.dtsi index 6f133f54ded5..402112a37d75 100644 --- a/arch/arm64/boot/dts/renesas/draak.dtsi +++ b/arch/arm64/boot/dts/renesas/draak.dtsi @@ -247,8 +247,7 @@ "ethernet-phy-ieee802.3-c22"; rxc-skew-ps = <1500>; reg = <0>; - interrupt-parent = <&gpio5>; - interrupts = <19 IRQ_TYPE_LEVEL_LOW>; + interrupts-extended = <&gpio5 19 IRQ_TYPE_LEVEL_LOW>; reset-gpios = <&gpio5 18 GPIO_ACTIVE_LOW>; /* * TX clock internal delay mode is required for reliable diff --git a/arch/arm64/boot/dts/renesas/ebisu.dtsi b/arch/arm64/boot/dts/renesas/ebisu.dtsi index cba2fde9dd36..1aedd093fb41 100644 --- a/arch/arm64/boot/dts/renesas/ebisu.dtsi +++ b/arch/arm64/boot/dts/renesas/ebisu.dtsi @@ -314,8 +314,7 @@ "ethernet-phy-ieee802.3-c22"; rxc-skew-ps = <1500>; reg = <0>; - interrupt-parent = <&gpio2>; - interrupts = <21 IRQ_TYPE_LEVEL_LOW>; + interrupts-extended = <&gpio2 21 IRQ_TYPE_LEVEL_LOW>; reset-gpios = <&gpio1 20 GPIO_ACTIVE_LOW>; /* * TX clock internal delay mode is required for reliable diff --git a/arch/arm64/boot/dts/renesas/hihope-rzg2-ex.dtsi b/arch/arm64/boot/dts/renesas/hihope-rzg2-ex.dtsi index ad898c6db4e6..4113710d5522 100644 --- a/arch/arm64/boot/dts/renesas/hihope-rzg2-ex.dtsi +++ b/arch/arm64/boot/dts/renesas/hihope-rzg2-ex.dtsi @@ -27,8 +27,7 @@ compatible = "ethernet-phy-id001c.c915", "ethernet-phy-ieee802.3-c22"; reg = <0>; - interrupt-parent = <&gpio2>; - interrupts = <11 IRQ_TYPE_LEVEL_LOW>; + interrupts-extended = <&gpio2 11 IRQ_TYPE_LEVEL_LOW>; reset-gpios = <&gpio2 10 GPIO_ACTIVE_LOW>; }; }; diff --git a/arch/arm64/boot/dts/renesas/r8a77970-eagle.dts b/arch/arm64/boot/dts/renesas/r8a77970-eagle.dts index 0608dce92e40..7dd9e13cf007 100644 --- a/arch/arm64/boot/dts/renesas/r8a77970-eagle.dts +++ b/arch/arm64/boot/dts/renesas/r8a77970-eagle.dts @@ -111,8 +111,7 @@ "ethernet-phy-ieee802.3-c22"; rxc-skew-ps = <1500>; reg = <0>; - interrupt-parent = <&gpio1>; - interrupts = <17 IRQ_TYPE_LEVEL_LOW>; + interrupts-extended = <&gpio1 17 IRQ_TYPE_LEVEL_LOW>; reset-gpios = <&gpio1 16 GPIO_ACTIVE_LOW>; }; }; diff --git a/arch/arm64/boot/dts/renesas/r8a77970-v3msk.dts b/arch/arm64/boot/dts/renesas/r8a77970-v3msk.dts index e36999e91af5..0a103f93b14d 100644 --- a/arch/arm64/boot/dts/renesas/r8a77970-v3msk.dts +++ b/arch/arm64/boot/dts/renesas/r8a77970-v3msk.dts @@ -117,8 +117,7 @@ "ethernet-phy-ieee802.3-c22"; rxc-skew-ps = <1500>; reg = <0>; - interrupt-parent = <&gpio1>; - interrupts = <17 IRQ_TYPE_LEVEL_LOW>; + interrupts-extended = <&gpio1 17 IRQ_TYPE_LEVEL_LOW>; reset-gpios = <&gpio1 16 GPIO_ACTIVE_LOW>; }; }; diff --git a/arch/arm64/boot/dts/renesas/r8a77980-v3hsk.dts b/arch/arm64/boot/dts/renesas/r8a77980-v3hsk.dts index 77d22df25fff..a8a20c748ffc 100644 --- a/arch/arm64/boot/dts/renesas/r8a77980-v3hsk.dts +++ b/arch/arm64/boot/dts/renesas/r8a77980-v3hsk.dts @@ -124,8 +124,7 @@ "ethernet-phy-ieee802.3-c22"; rxc-skew-ps = <1500>; reg = <0>; - interrupt-parent = <&gpio4>; - interrupts = <23 IRQ_TYPE_LEVEL_LOW>; + interrupts-extended = <&gpio4 23 IRQ_TYPE_LEVEL_LOW>; reset-gpios = <&gpio4 22 GPIO_ACTIVE_LOW>; }; }; diff --git a/arch/arm64/boot/dts/renesas/r8a779a0-falcon.dts b/arch/arm64/boot/dts/renesas/r8a779a0-falcon.dts index 63db822e5f46..6bd580737f25 100644 --- a/arch/arm64/boot/dts/renesas/r8a779a0-falcon.dts +++ b/arch/arm64/boot/dts/renesas/r8a779a0-falcon.dts @@ -31,8 +31,7 @@ "ethernet-phy-ieee802.3-c22"; rxc-skew-ps = <1500>; reg = <0>; - interrupt-parent = <&gpio4>; - interrupts = <16 IRQ_TYPE_LEVEL_LOW>; + interrupts-extended = <&gpio4 16 IRQ_TYPE_LEVEL_LOW>; reset-gpios = <&gpio4 15 GPIO_ACTIVE_LOW>; }; }; diff --git a/arch/arm64/boot/dts/renesas/r8a779f0-spider-ethernet.dtsi b/arch/arm64/boot/dts/renesas/r8a779f0-spider-ethernet.dtsi index 33c1015e9ab3..5d38669ed1ec 100644 --- a/arch/arm64/boot/dts/renesas/r8a779f0-spider-ethernet.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a779f0-spider-ethernet.dtsi @@ -60,8 +60,7 @@ u101: ethernet-phy@1 { reg = <1>; compatible = "ethernet-phy-ieee802.3-c45"; - interrupt-parent = <&gpio3>; - interrupts = <10 IRQ_TYPE_LEVEL_LOW>; + interrupts-extended = <&gpio3 10 IRQ_TYPE_LEVEL_LOW>; }; }; }; @@ -78,8 +77,7 @@ u201: ethernet-phy@2 { reg = <2>; compatible = "ethernet-phy-ieee802.3-c45"; - interrupt-parent = <&gpio3>; - interrupts = <11 IRQ_TYPE_LEVEL_LOW>; + interrupts-extended = <&gpio3 11 IRQ_TYPE_LEVEL_LOW>; }; }; }; @@ -96,8 +94,7 @@ u301: ethernet-phy@3 { reg = <3>; compatible = "ethernet-phy-ieee802.3-c45"; - interrupt-parent = <&gpio3>; - interrupts = <9 IRQ_TYPE_LEVEL_LOW>; + interrupts-extended = <&gpio3 9 IRQ_TYPE_LEVEL_LOW>; }; }; }; diff --git a/arch/arm64/boot/dts/renesas/r8a779f4-s4sk.dts b/arch/arm64/boot/dts/renesas/r8a779f4-s4sk.dts index fa910b85859e..5d71d52f9c65 100644 --- a/arch/arm64/boot/dts/renesas/r8a779f4-s4sk.dts +++ b/arch/arm64/boot/dts/renesas/r8a779f4-s4sk.dts @@ -197,8 +197,7 @@ ic99: ethernet-phy@1 { reg = <1>; compatible = "ethernet-phy-ieee802.3-c45"; - interrupt-parent = <&gpio3>; - interrupts = <10 IRQ_TYPE_LEVEL_LOW>; + interrupts-extended = <&gpio3 10 IRQ_TYPE_LEVEL_LOW>; }; }; }; @@ -216,8 +215,7 @@ ic102: ethernet-phy@2 { reg = <2>; compatible = "ethernet-phy-ieee802.3-c45"; - interrupt-parent = <&gpio3>; - interrupts = <11 IRQ_TYPE_LEVEL_LOW>; + interrupts-extended = <&gpio3 11 IRQ_TYPE_LEVEL_LOW>; }; }; }; diff --git a/arch/arm64/boot/dts/renesas/r8a779g2-white-hawk-single.dts b/arch/arm64/boot/dts/renesas/r8a779g2-white-hawk-single.dts index 50a428572d9b..48befde38937 100644 --- a/arch/arm64/boot/dts/renesas/r8a779g2-white-hawk-single.dts +++ b/arch/arm64/boot/dts/renesas/r8a779g2-white-hawk-single.dts @@ -7,71 +7,10 @@ /dts-v1/; #include "r8a779g2.dtsi" -#include "white-hawk-cpu-common.dtsi" -#include "white-hawk-common.dtsi" +#include "white-hawk-single.dtsi" / { model = "Renesas White Hawk Single board based on r8a779g2"; compatible = "renesas,white-hawk-single", "renesas,r8a779g2", "renesas,r8a779g0"; }; - -&hscif0 { - uart-has-rtscts; -}; - -&hscif0_pins { - groups = "hscif0_data", "hscif0_ctrl"; - function = "hscif0"; -}; - -&pfc { - tsn0_pins: tsn0 { - mux { - groups = "tsn0_link", "tsn0_mdio", "tsn0_rgmii", - "tsn0_txcrefclk"; - function = "tsn0"; - }; - - link { - groups = "tsn0_link"; - bias-disable; - }; - - mdio { - groups = "tsn0_mdio"; - drive-strength = <24>; - bias-disable; - }; - - rgmii { - groups = "tsn0_rgmii"; - drive-strength = <24>; - bias-disable; - }; - }; -}; - -&tsn0 { - pinctrl-0 = <&tsn0_pins>; - pinctrl-names = "default"; - phy-mode = "rgmii"; - phy-handle = <&phy3>; - status = "okay"; - - mdio { - #address-cells = <1>; - #size-cells = <0>; - - reset-gpios = <&gpio1 23 GPIO_ACTIVE_LOW>; - reset-post-delay-us = <4000>; - - phy3: ethernet-phy@0 { - compatible = "ethernet-phy-id002b.0980", - "ethernet-phy-ieee802.3-c22"; - reg = <0>; - interrupt-parent = <&gpio4>; - interrupts = <3 IRQ_TYPE_LEVEL_LOW>; - }; - }; -}; diff --git a/arch/arm64/boot/dts/renesas/r8a779h0-gray-hawk-single.dts b/arch/arm64/boot/dts/renesas/r8a779h0-gray-hawk-single.dts index 9a1917b87f61..f4d721a7f505 100644 --- a/arch/arm64/boot/dts/renesas/r8a779h0-gray-hawk-single.dts +++ b/arch/arm64/boot/dts/renesas/r8a779h0-gray-hawk-single.dts @@ -175,8 +175,7 @@ "ethernet-phy-ieee802.3-c22"; rxc-skew-ps = <1500>; reg = <0>; - interrupt-parent = <&gpio7>; - interrupts = <5 IRQ_TYPE_LEVEL_LOW>; + interrupts-extended = <&gpio7 5 IRQ_TYPE_LEVEL_LOW>; reset-gpios = <&gpio7 10 GPIO_ACTIVE_LOW>; }; }; diff --git a/arch/arm64/boot/dts/renesas/rzg2l-smarc-som.dtsi b/arch/arm64/boot/dts/renesas/rzg2l-smarc-som.dtsi index 83f5642d0d35..502d9f17bf16 100644 --- a/arch/arm64/boot/dts/renesas/rzg2l-smarc-som.dtsi +++ b/arch/arm64/boot/dts/renesas/rzg2l-smarc-som.dtsi @@ -102,8 +102,7 @@ compatible = "ethernet-phy-id0022.1640", "ethernet-phy-ieee802.3-c22"; reg = <7>; - interrupt-parent = <&irqc>; - interrupts = <RZG2L_IRQ2 IRQ_TYPE_LEVEL_LOW>; + interrupts-extended = <&irqc RZG2L_IRQ2 IRQ_TYPE_LEVEL_LOW>; rxc-skew-psec = <2400>; txc-skew-psec = <2400>; rxdv-skew-psec = <0>; @@ -130,8 +129,7 @@ compatible = "ethernet-phy-id0022.1640", "ethernet-phy-ieee802.3-c22"; reg = <7>; - interrupt-parent = <&irqc>; - interrupts = <RZG2L_IRQ3 IRQ_TYPE_LEVEL_LOW>; + interrupts-extended = <&irqc RZG2L_IRQ3 IRQ_TYPE_LEVEL_LOW>; rxc-skew-psec = <2400>; txc-skew-psec = <2400>; rxdv-skew-psec = <0>; diff --git a/arch/arm64/boot/dts/renesas/rzg2lc-smarc-som.dtsi b/arch/arm64/boot/dts/renesas/rzg2lc-smarc-som.dtsi index b4ef5ea8a9e3..de39311a77dc 100644 --- a/arch/arm64/boot/dts/renesas/rzg2lc-smarc-som.dtsi +++ b/arch/arm64/boot/dts/renesas/rzg2lc-smarc-som.dtsi @@ -82,8 +82,7 @@ compatible = "ethernet-phy-id0022.1640", "ethernet-phy-ieee802.3-c22"; reg = <7>; - interrupt-parent = <&irqc>; - interrupts = <RZG2L_IRQ0 IRQ_TYPE_LEVEL_LOW>; + interrupts-extended = <&irqc RZG2L_IRQ0 IRQ_TYPE_LEVEL_LOW>; rxc-skew-psec = <2400>; txc-skew-psec = <2400>; rxdv-skew-psec = <0>; diff --git a/arch/arm64/boot/dts/renesas/rzg2ul-smarc-som.dtsi b/arch/arm64/boot/dts/renesas/rzg2ul-smarc-som.dtsi index 79443fb3f581..1a6fd58bd368 100644 --- a/arch/arm64/boot/dts/renesas/rzg2ul-smarc-som.dtsi +++ b/arch/arm64/boot/dts/renesas/rzg2ul-smarc-som.dtsi @@ -78,8 +78,7 @@ compatible = "ethernet-phy-id0022.1640", "ethernet-phy-ieee802.3-c22"; reg = <7>; - interrupt-parent = <&irqc>; - interrupts = <RZG2L_IRQ2 IRQ_TYPE_LEVEL_LOW>; + interrupts-extended = <&irqc RZG2L_IRQ2 IRQ_TYPE_LEVEL_LOW>; rxc-skew-psec = <2400>; txc-skew-psec = <2400>; rxdv-skew-psec = <0>; @@ -107,8 +106,7 @@ compatible = "ethernet-phy-id0022.1640", "ethernet-phy-ieee802.3-c22"; reg = <7>; - interrupt-parent = <&irqc>; - interrupts = <RZG2L_IRQ7 IRQ_TYPE_LEVEL_LOW>; + interrupts-extended = <&irqc RZG2L_IRQ7 IRQ_TYPE_LEVEL_LOW>; rxc-skew-psec = <2400>; txc-skew-psec = <2400>; rxdv-skew-psec = <0>; diff --git a/arch/arm64/boot/dts/renesas/rzg3s-smarc-som.dtsi b/arch/arm64/boot/dts/renesas/rzg3s-smarc-som.dtsi index 612cdc7efabb..d2d367c09abd 100644 --- a/arch/arm64/boot/dts/renesas/rzg3s-smarc-som.dtsi +++ b/arch/arm64/boot/dts/renesas/rzg3s-smarc-som.dtsi @@ -98,8 +98,7 @@ phy0: ethernet-phy@7 { reg = <7>; - interrupt-parent = <&pinctrl>; - interrupts = <RZG2L_GPIO(12, 0) IRQ_TYPE_EDGE_FALLING>; + interrupts-extended = <&pinctrl RZG2L_GPIO(12, 0) IRQ_TYPE_EDGE_FALLING>; rxc-skew-psec = <0>; txc-skew-psec = <0>; rxdv-skew-psec = <0>; @@ -124,8 +123,7 @@ phy1: ethernet-phy@7 { reg = <7>; - interrupt-parent = <&pinctrl>; - interrupts = <RZG2L_GPIO(12, 1) IRQ_TYPE_EDGE_FALLING>; + interrupts-extended = <&pinctrl RZG2L_GPIO(12, 1) IRQ_TYPE_EDGE_FALLING>; rxc-skew-psec = <0>; txc-skew-psec = <0>; rxdv-skew-psec = <0>; diff --git a/arch/arm64/boot/dts/renesas/salvator-common.dtsi b/arch/arm64/boot/dts/renesas/salvator-common.dtsi index 1eb4883b3219..c5035232956a 100644 --- a/arch/arm64/boot/dts/renesas/salvator-common.dtsi +++ b/arch/arm64/boot/dts/renesas/salvator-common.dtsi @@ -353,8 +353,7 @@ "ethernet-phy-ieee802.3-c22"; rxc-skew-ps = <1500>; reg = <0>; - interrupt-parent = <&gpio2>; - interrupts = <11 IRQ_TYPE_LEVEL_LOW>; + interrupts-extended = <&gpio2 11 IRQ_TYPE_LEVEL_LOW>; reset-gpios = <&gpio2 10 GPIO_ACTIVE_LOW>; }; }; diff --git a/arch/arm64/boot/dts/renesas/ulcb.dtsi b/arch/arm64/boot/dts/renesas/ulcb.dtsi index a2f66f916048..4cf141a701c0 100644 --- a/arch/arm64/boot/dts/renesas/ulcb.dtsi +++ b/arch/arm64/boot/dts/renesas/ulcb.dtsi @@ -150,8 +150,7 @@ "ethernet-phy-ieee802.3-c22"; rxc-skew-ps = <1500>; reg = <0>; - interrupt-parent = <&gpio2>; - interrupts = <11 IRQ_TYPE_LEVEL_LOW>; + interrupts-extended = <&gpio2 11 IRQ_TYPE_LEVEL_LOW>; reset-gpios = <&gpio2 10 GPIO_ACTIVE_LOW>; }; }; diff --git a/arch/arm64/boot/dts/renesas/white-hawk-cpu-common.dtsi b/arch/arm64/boot/dts/renesas/white-hawk-cpu-common.dtsi index 3845b413bd24..69e4fddebd4e 100644 --- a/arch/arm64/boot/dts/renesas/white-hawk-cpu-common.dtsi +++ b/arch/arm64/boot/dts/renesas/white-hawk-cpu-common.dtsi @@ -167,8 +167,7 @@ "ethernet-phy-ieee802.3-c22"; rxc-skew-ps = <1500>; reg = <0>; - interrupt-parent = <&gpio7>; - interrupts = <5 IRQ_TYPE_LEVEL_LOW>; + interrupts-extended = <&gpio7 5 IRQ_TYPE_LEVEL_LOW>; reset-gpios = <&gpio7 10 GPIO_ACTIVE_LOW>; }; }; diff --git a/arch/arm64/boot/dts/renesas/white-hawk-ethernet.dtsi b/arch/arm64/boot/dts/renesas/white-hawk-ethernet.dtsi index 595ec4ff4cdd..ad94bf3f5e6c 100644 --- a/arch/arm64/boot/dts/renesas/white-hawk-ethernet.dtsi +++ b/arch/arm64/boot/dts/renesas/white-hawk-ethernet.dtsi @@ -29,8 +29,7 @@ avb1_phy: ethernet-phy@0 { compatible = "ethernet-phy-ieee802.3-c45"; reg = <0>; - interrupt-parent = <&gpio6>; - interrupts = <3 IRQ_TYPE_LEVEL_LOW>; + interrupts-extended = <&gpio6 3 IRQ_TYPE_LEVEL_LOW>; }; }; }; @@ -51,8 +50,7 @@ avb2_phy: ethernet-phy@0 { compatible = "ethernet-phy-ieee802.3-c45"; reg = <0>; - interrupt-parent = <&gpio5>; - interrupts = <4 IRQ_TYPE_LEVEL_LOW>; + interrupts-extended = <&gpio5 4 IRQ_TYPE_LEVEL_LOW>; }; }; }; diff --git a/arch/arm64/boot/dts/renesas/white-hawk-single.dtsi b/arch/arm64/boot/dts/renesas/white-hawk-single.dtsi new file mode 100644 index 000000000000..976a3ab44e5a --- /dev/null +++ b/arch/arm64/boot/dts/renesas/white-hawk-single.dtsi @@ -0,0 +1,77 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* + * Device Tree Source for the White Hawk Single board + * + * Copyright (C) 2023-2024 Glider bv + */ + +#include "white-hawk-cpu-common.dtsi" +#include "white-hawk-common.dtsi" + +/ { + model = "Renesas White Hawk Single board"; + compatible = "renesas,white-hawk-single"; + + aliases { + ethernet3 = &tsn0; + }; +}; + +&hscif0 { + uart-has-rtscts; +}; + +&hscif0_pins { + groups = "hscif0_data", "hscif0_ctrl"; + function = "hscif0"; +}; + +&pfc { + tsn0_pins: tsn0 { + mux { + groups = "tsn0_link", "tsn0_mdio", "tsn0_rgmii", + "tsn0_txcrefclk"; + function = "tsn0"; + }; + + link { + groups = "tsn0_link"; + bias-disable; + }; + + mdio { + groups = "tsn0_mdio"; + drive-strength = <24>; + bias-disable; + }; + + rgmii { + groups = "tsn0_rgmii"; + drive-strength = <24>; + bias-disable; + }; + }; +}; + +&tsn0 { + pinctrl-0 = <&tsn0_pins>; + pinctrl-names = "default"; + phy-mode = "rgmii"; + phy-handle = <&tsn0_phy>; + status = "okay"; + + mdio { + #address-cells = <1>; + #size-cells = <0>; + + reset-gpios = <&gpio1 23 GPIO_ACTIVE_LOW>; + reset-post-delay-us = <4000>; + + tsn0_phy: ethernet-phy@0 { + compatible = "ethernet-phy-id002b.0980", + "ethernet-phy-ieee802.3-c22"; + reg = <0>; + interrupts-extended = <&gpio4 3 IRQ_TYPE_LEVEL_LOW>; + }; + }; +}; diff --git a/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi b/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi index f743aaf78359..c17c2f40194f 100644 --- a/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi +++ b/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi @@ -344,6 +344,18 @@ <0 RK_PA7 RK_FUNC_GPIO &pcfg_pull_up>; }; }; + + spi1 { + spi1_csn0_gpio_pin: spi1-csn0-gpio-pin { + rockchip,pins = + <3 RK_PB1 RK_FUNC_GPIO &pcfg_pull_up_4ma>; + }; + + spi1_csn1_gpio_pin: spi1-csn1-gpio-pin { + rockchip,pins = + <3 RK_PB2 RK_FUNC_GPIO &pcfg_pull_up_4ma>; + }; + }; }; &pmu_io_domains { @@ -361,6 +373,17 @@ vqmmc-supply = <&vccio_sd>; }; +&spi1 { + /* + * Hardware CS has a very slow rise time of about 6us, + * causing transmission errors. + * With cs-gpios we have a rise time of about 20ns. + */ + cs-gpios = <&gpio3 RK_PB1 GPIO_ACTIVE_LOW>, <&gpio3 RK_PB2 GPIO_ACTIVE_LOW>; + pinctrl-names = "default"; + pinctrl-0 = <&spi1_clk &spi1_csn0_gpio_pin &spi1_csn1_gpio_pin &spi1_miso &spi1_mosi>; +}; + &tsadc { status = "okay"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi index 257636d0d2cb..0a73218ea37b 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi @@ -59,17 +59,7 @@ vin-supply = <&vcc5v0_sys>; }; - vcc5v0_host: vcc5v0-host-regulator { - compatible = "regulator-fixed"; - gpio = <&gpio4 RK_PA3 GPIO_ACTIVE_LOW>; - pinctrl-names = "default"; - pinctrl-0 = <&vcc5v0_host_en>; - regulator-name = "vcc5v0_host"; - regulator-always-on; - vin-supply = <&vcc5v0_sys>; - }; - - vcc5v0_sys: vcc5v0-sys { + vcc5v0_sys: regulator-vcc5v0-sys { compatible = "regulator-fixed"; regulator-name = "vcc5v0_sys"; regulator-always-on; @@ -509,10 +499,10 @@ }; }; - usb2 { - vcc5v0_host_en: vcc5v0-host-en { + usb { + cy3304_reset: cy3304-reset { rockchip,pins = - <4 RK_PA3 RK_FUNC_GPIO &pcfg_pull_none>; + <4 RK_PA3 RK_FUNC_GPIO &pcfg_output_high>; }; }; @@ -579,7 +569,6 @@ }; u2phy1_host: host-port { - phy-supply = <&vcc5v0_host>; status = "okay"; }; }; @@ -591,6 +580,29 @@ &usbdrd_dwc3_1 { status = "okay"; dr_mode = "host"; + pinctrl-names = "default"; + pinctrl-0 = <&cy3304_reset>; + #address-cells = <1>; + #size-cells = <0>; + + hub_2_0: hub@1 { + compatible = "usb4b4,6502", "usb4b4,6506"; + reg = <1>; + peer-hub = <&hub_3_0>; + reset-gpios = <&gpio4 RK_PA3 GPIO_ACTIVE_HIGH>; + vdd-supply = <&vcc1v2_phy>; + vdd2-supply = <&vcc3v3_sys>; + + }; + + hub_3_0: hub@2 { + compatible = "usb4b4,6500", "usb4b4,6504"; + reg = <2>; + peer-hub = <&hub_2_0>; + reset-gpios = <&gpio4 RK_PA3 GPIO_ACTIVE_HIGH>; + vdd-supply = <&vcc1v2_phy>; + vdd2-supply = <&vcc3v3_sys>; + }; }; &usb_host1_ehci { diff --git a/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dtsi index 11d99d8b34a2..66d010a9e8c3 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dtsi @@ -227,6 +227,16 @@ vin-supply = <&vcc12v_dcin>; }; + vcca_0v9: vcca-0v9 { + compatible = "regulator-fixed"; + regulator-name = "vcca_0v9"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <900000>; + regulator-max-microvolt = <900000>; + vin-supply = <&vcc3v3_sys>; + }; + vdd_log: vdd-log { compatible = "pwm-regulator"; pwms = <&pwm2 0 25000 1>; @@ -312,6 +322,8 @@ }; &hdmi { + avdd-0v9-supply = <&vcca_0v9>; + avdd-1v8-supply = <&vcc1v8_dvp>; ddc-i2c-bus = <&i2c3>; pinctrl-names = "default"; pinctrl-0 = <&hdmi_cec>; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi index fde8b228f2c7..5825141d2007 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5.dtsi @@ -317,6 +317,7 @@ bus-width = <4>; cap-mmc-highspeed; cap-sd-highspeed; + cd-gpios = <&gpio0 RK_PA4 GPIO_ACTIVE_LOW>; disable-wp; max-frequency = <150000000>; no-sdio; diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-coolpi-4b.dts b/arch/arm64/boot/dts/rockchip/rk3588s-coolpi-4b.dts index 074c316a9a69..9713f05f92e9 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588s-coolpi-4b.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588s-coolpi-4b.dts @@ -438,6 +438,7 @@ bus-width = <4>; cap-mmc-highspeed; cap-sd-highspeed; + cd-gpios = <&gpio0 RK_PA4 GPIO_ACTIVE_LOW>; disable-wp; max-frequency = <150000000>; no-sdio; diff --git a/arch/arm64/boot/dts/st/stm32mp251.dtsi b/arch/arm64/boot/dts/st/stm32mp251.dtsi index cd9b92144a42..ed7804f06189 100644 --- a/arch/arm64/boot/dts/st/stm32mp251.dtsi +++ b/arch/arm64/boot/dts/st/stm32mp251.dtsi @@ -149,7 +149,7 @@ <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>, <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>, <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>; - always-on; + arm,no-tick-in-suspend; }; soc@0 { diff --git a/arch/arm64/boot/dts/ti/k3-am62p-j722s-common-main.dtsi b/arch/arm64/boot/dts/ti/k3-am62p-j722s-common-main.dtsi index 77fe2b27cb58..239acfcc3a5c 100644 --- a/arch/arm64/boot/dts/ti/k3-am62p-j722s-common-main.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am62p-j722s-common-main.dtsi @@ -250,7 +250,7 @@ main_pmx0: pinctrl@f4000 { compatible = "pinctrl-single"; - reg = <0x00 0xf4000 0x00 0x2ac>; + reg = <0x00 0xf4000 0x00 0x2b0>; #pinctrl-cells = <1>; pinctrl-single,register-width = <32>; pinctrl-single,function-mask = <0xffffffff>; diff --git a/arch/arm64/boot/dts/ti/k3-am642-phyboard-electra-rdk.dts b/arch/arm64/boot/dts/ti/k3-am642-phyboard-electra-rdk.dts index 60285d736e07..78df1b43a633 100644 --- a/arch/arm64/boot/dts/ti/k3-am642-phyboard-electra-rdk.dts +++ b/arch/arm64/boot/dts/ti/k3-am642-phyboard-electra-rdk.dts @@ -319,6 +319,8 @@ &icssg0_mdio { pinctrl-names = "default"; pinctrl-0 = <&icssg0_mdio_pins_default &clkout0_pins_default>; + assigned-clocks = <&k3_clks 157 123>; + assigned-clock-parents = <&k3_clks 157 125>; status = "okay"; icssg0_phy1: ethernet-phy@1 { diff --git a/arch/arm64/boot/dts/ti/k3-j722s-evm.dts b/arch/arm64/boot/dts/ti/k3-j722s-evm.dts index 710f80a14b64..98fc1c0f86a4 100644 --- a/arch/arm64/boot/dts/ti/k3-j722s-evm.dts +++ b/arch/arm64/boot/dts/ti/k3-j722s-evm.dts @@ -495,8 +495,8 @@ p05-hog { /* P05 - USB2.0_MUX_SEL */ gpio-hog; - gpios = <5 GPIO_ACTIVE_HIGH>; - output-high; + gpios = <5 GPIO_ACTIVE_LOW>; + output-low; }; p01_hog: p01-hog { diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h index a407f9cd549e..c07a58b96329 100644 --- a/arch/arm64/include/asm/acpi.h +++ b/arch/arm64/include/asm/acpi.h @@ -150,7 +150,7 @@ acpi_set_mailbox_entry(int cpu, struct acpi_madt_generic_interrupt *processor) {} #endif -static inline const char *acpi_get_enable_method(int cpu) +static __always_inline const char *acpi_get_enable_method(int cpu) { if (acpi_psci_present()) return "psci"; diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index c1f45fd6b3e9..d8ffccee8194 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -41,6 +41,11 @@ /* * Save/restore interrupts. */ + .macro save_and_disable_daif, flags + mrs \flags, daif + msr daifset, #0xf + .endm + .macro save_and_disable_irq, flags mrs \flags, daif msr daifset, #3 diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h index 9edbd871c31b..5f12cdc2b967 100644 --- a/arch/arm64/include/asm/tlbflush.h +++ b/arch/arm64/include/asm/tlbflush.h @@ -330,13 +330,14 @@ static inline void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *b } /* - * If mprotect/munmap/etc occurs during TLB batched flushing, we need to - * synchronise all the TLBI issued with a DSB to avoid the race mentioned in - * flush_tlb_batched_pending(). + * If mprotect/munmap/etc occurs during TLB batched flushing, we need to ensure + * all the previously issued TLBIs targeting mm have completed. But since we + * can be executing on a remote CPU, a DSB cannot guarantee this like it can + * for arch_tlbbatch_flush(). Our only option is to flush the entire mm. */ static inline void arch_flush_tlb_batched_pending(struct mm_struct *mm) { - dsb(ish); + flush_tlb_mm(mm); } /* diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c index e6f66491fbe9..862bb1cba4f0 100644 --- a/arch/arm64/kernel/acpi.c +++ b/arch/arm64/kernel/acpi.c @@ -197,6 +197,8 @@ out: */ void __init acpi_boot_table_init(void) { + int ret; + /* * Enable ACPI instead of device tree unless * - ACPI has been disabled explicitly (acpi=off), or @@ -250,10 +252,12 @@ done: * behaviour, use acpi=nospcr to disable console in ACPI SPCR * table as default serial console. */ - acpi_parse_spcr(earlycon_acpi_spcr_enable, + ret = acpi_parse_spcr(earlycon_acpi_spcr_enable, !param_acpi_nospcr); - pr_info("Use ACPI SPCR as default console: %s\n", - param_acpi_nospcr ? "No" : "Yes"); + if (!ret || param_acpi_nospcr || !IS_ENABLED(CONFIG_ACPI_SPCR_TABLE)) + pr_info("Use ACPI SPCR as default console: No\n"); + else + pr_info("Use ACPI SPCR as default console: Yes\n"); if (IS_ENABLED(CONFIG_ACPI_BGRT)) acpi_table_parse(ACPI_SIG_BGRT, acpi_parse_bgrt); diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 05ccf4ec278f..9ca5ffd8d817 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -2959,6 +2959,13 @@ static bool has_sve_feature(const struct arm64_cpu_capabilities *cap, int scope) } #endif +#ifdef CONFIG_ARM64_SME +static bool has_sme_feature(const struct arm64_cpu_capabilities *cap, int scope) +{ + return system_supports_sme() && has_user_cpuid_feature(cap, scope); +} +#endif + static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64ISAR0_EL1, AES, PMULL, CAP_HWCAP, KERNEL_HWCAP_PMULL), HWCAP_CAP(ID_AA64ISAR0_EL1, AES, AES, CAP_HWCAP, KERNEL_HWCAP_AES), @@ -3037,25 +3044,25 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64ISAR2_EL1, BC, IMP, CAP_HWCAP, KERNEL_HWCAP_HBC), #ifdef CONFIG_ARM64_SME HWCAP_CAP(ID_AA64PFR1_EL1, SME, IMP, CAP_HWCAP, KERNEL_HWCAP_SME), - HWCAP_CAP(ID_AA64SMFR0_EL1, FA64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_FA64), - HWCAP_CAP(ID_AA64SMFR0_EL1, LUTv2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_LUTV2), - HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2p1, CAP_HWCAP, KERNEL_HWCAP_SME2P1), - HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2, CAP_HWCAP, KERNEL_HWCAP_SME2), - HWCAP_CAP(ID_AA64SMFR0_EL1, I16I64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I64), - HWCAP_CAP(ID_AA64SMFR0_EL1, F64F64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F64F64), - HWCAP_CAP(ID_AA64SMFR0_EL1, I16I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I32), - HWCAP_CAP(ID_AA64SMFR0_EL1, B16B16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16B16), - HWCAP_CAP(ID_AA64SMFR0_EL1, F16F16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F16), - HWCAP_CAP(ID_AA64SMFR0_EL1, F8F16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F8F16), - HWCAP_CAP(ID_AA64SMFR0_EL1, F8F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F8F32), - HWCAP_CAP(ID_AA64SMFR0_EL1, I8I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I8I32), - HWCAP_CAP(ID_AA64SMFR0_EL1, F16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F32), - HWCAP_CAP(ID_AA64SMFR0_EL1, B16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16F32), - HWCAP_CAP(ID_AA64SMFR0_EL1, BI32I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_BI32I32), - HWCAP_CAP(ID_AA64SMFR0_EL1, F32F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F32F32), - HWCAP_CAP(ID_AA64SMFR0_EL1, SF8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8FMA), - HWCAP_CAP(ID_AA64SMFR0_EL1, SF8DP4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP4), - HWCAP_CAP(ID_AA64SMFR0_EL1, SF8DP2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP2), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, FA64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_FA64), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, LUTv2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_LUTV2), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SMEver, SME2p1, CAP_HWCAP, KERNEL_HWCAP_SME2P1), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SMEver, SME2, CAP_HWCAP, KERNEL_HWCAP_SME2), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, I16I64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I64), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F64F64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F64F64), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, I16I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I32), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, B16B16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16B16), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F16F16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F16), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F8F16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F8F16), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F8F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F8F32), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, I8I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I8I32), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F32), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, B16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16F32), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, BI32I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_BI32I32), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, F32F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F32F32), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SF8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8FMA), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SF8DP4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP4), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SF8DP2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP2), #endif /* CONFIG_ARM64_SME */ HWCAP_CAP(ID_AA64FPFR0_EL1, F8CVT, IMP, CAP_HWCAP, KERNEL_HWCAP_F8CVT), HWCAP_CAP(ID_AA64FPFR0_EL1, F8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_F8FMA), diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 7ef0e127b149..189ce50055d1 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -823,6 +823,7 @@ SYM_CODE_END(__bp_harden_el1_vectors) * */ SYM_FUNC_START(cpu_switch_to) + save_and_disable_daif x11 mov x10, #THREAD_CPU_CONTEXT add x8, x0, x10 mov x9, sp @@ -846,6 +847,7 @@ SYM_FUNC_START(cpu_switch_to) ptrauth_keys_install_kernel x1, x8, x9, x10 scs_save x0 scs_load_current + restore_irq x11 ret SYM_FUNC_END(cpu_switch_to) NOKPROBE(cpu_switch_to) @@ -872,6 +874,7 @@ NOKPROBE(ret_from_fork) * Calls func(regs) using this CPU's irq stack and shadow irq stack. */ SYM_FUNC_START(call_on_irq_stack) + save_and_disable_daif x9 #ifdef CONFIG_SHADOW_CALL_STACK get_current_task x16 scs_save x16 @@ -886,8 +889,10 @@ SYM_FUNC_START(call_on_irq_stack) /* Move to the new stack and call the function there */ add sp, x16, #IRQ_STACK_SIZE + restore_irq x9 blr x1 + save_and_disable_daif x9 /* * Restore the SP from the FP, and restore the FP and LR from the frame * record. @@ -895,6 +900,7 @@ SYM_FUNC_START(call_on_irq_stack) mov sp, x29 ldp x29, x30, [sp], #16 scs_load_current + restore_irq x9 ret SYM_FUNC_END(call_on_irq_stack) NOKPROBE(call_on_irq_stack) diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 2bbcbb11d844..2edf88c1c695 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -544,6 +544,11 @@ static void permission_overlay_switch(struct task_struct *next) current->thread.por_el0 = read_sysreg_s(SYS_POR_EL0); if (current->thread.por_el0 != next->thread.por_el0) { write_sysreg_s(next->thread.por_el0, SYS_POR_EL0); + /* + * No ISB required as we can tolerate spurious Overlay faults - + * the fault handler will check again based on the new value + * of POR_EL0. + */ } } diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 1559a239137f..1a8f4284cb69 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -140,7 +140,7 @@ unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n) addr += n; if (regs_within_kernel_stack(regs, (unsigned long)addr)) - return *addr; + return READ_ONCE_NOCHECK(*addr); else return 0; } diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index 2729faaee4b4..1d60a08a2184 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -123,6 +123,8 @@ kunwind_recover_return_address(struct kunwind_state *state) orig_pc = kretprobe_find_ret_addr(state->task, (void *)state->common.fp, &state->kr_cur); + if (!orig_pc) + return -EINVAL; state->common.pc = orig_pc; } #endif /* CONFIG_KRETPROBES */ diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 563cbce11126..e2e8ffa65aa5 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -921,6 +921,7 @@ void __noreturn panic_bad_stack(struct pt_regs *regs, unsigned long esr, unsigne void __noreturn arm64_serror_panic(struct pt_regs *regs, unsigned long esr) { + add_taint(TAINT_MACHINE_CHECK, LOCKDEP_STILL_OK); console_verbose(); pr_crit("SError Interrupt on CPU%d, code 0x%016lx -- %s\n", diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 8b281cf308b3..2d1ebc0c3437 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -487,17 +487,29 @@ static void do_bad_area(unsigned long far, unsigned long esr, } } -static bool fault_from_pkey(unsigned long esr, struct vm_area_struct *vma, - unsigned int mm_flags) +static bool fault_from_pkey(struct vm_area_struct *vma, unsigned int mm_flags) { - unsigned long iss2 = ESR_ELx_ISS2(esr); - if (!system_supports_poe()) return false; - if (esr_fsc_is_permission_fault(esr) && (iss2 & ESR_ELx_Overlay)) - return true; - + /* + * We do not check whether an Overlay fault has occurred because we + * cannot make a decision based solely on its value: + * + * - If Overlay is set, a fault did occur due to POE, but it may be + * spurious in those cases where we update POR_EL0 without ISB (e.g. + * on context-switch). We would then need to manually check POR_EL0 + * against vma_pkey(vma), which is exactly what + * arch_vma_access_permitted() does. + * + * - If Overlay is not set, we may still need to report a pkey fault. + * This is the case if an access was made within a mapping but with no + * page mapped, and POR_EL0 forbids the access (according to + * vma_pkey()). Such access will result in a SIGSEGV regardless + * because core code checks arch_vma_access_permitted(), but in order + * to report the correct error code - SEGV_PKUERR - we must handle + * that case here. + */ return !arch_vma_access_permitted(vma, mm_flags & FAULT_FLAG_WRITE, mm_flags & FAULT_FLAG_INSTRUCTION, @@ -595,7 +607,7 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr, goto bad_area; } - if (fault_from_pkey(esr, vma, mm_flags)) { + if (fault_from_pkey(vma, mm_flags)) { pkey = vma_pkey(vma); vma_end_read(vma); fault = 0; @@ -639,7 +651,7 @@ retry: goto bad_area; } - if (fault_from_pkey(esr, vma, mm_flags)) { + if (fault_from_pkey(vma, mm_flags)) { pkey = vma_pkey(vma); mmap_read_unlock(mm); fault = 0; @@ -786,6 +798,7 @@ static int do_sea(unsigned long far, unsigned long esr, struct pt_regs *regs) */ siaddr = untagged_addr(far); } + add_taint(TAINT_MACHINE_CHECK, LOCKDEP_STILL_OK); arm64_notify_die(inf->name, regs, inf->sig, inf->code, siaddr, esr); return 0; diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 9bcd51fd67d4..aed8d32979d9 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -1285,7 +1285,8 @@ int pud_free_pmd_page(pud_t *pudp, unsigned long addr) next = addr; end = addr + PUD_SIZE; do { - pmd_free_pte_page(pmdp, next); + if (pmd_present(pmdp_get(pmdp))) + pmd_free_pte_page(pmdp, next); } while (pmdp++, next += PMD_SIZE, next != end); pud_clear(pudp); diff --git a/arch/arm64/mm/ptdump_debugfs.c b/arch/arm64/mm/ptdump_debugfs.c index 68bf1a125502..1e308328c079 100644 --- a/arch/arm64/mm/ptdump_debugfs.c +++ b/arch/arm64/mm/ptdump_debugfs.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/debugfs.h> -#include <linux/memory_hotplug.h> #include <linux/seq_file.h> #include <asm/ptdump.h> @@ -9,9 +8,7 @@ static int ptdump_show(struct seq_file *m, void *v) { struct ptdump_info *info = m->private; - get_online_mems(); ptdump_walk(m, info); - put_online_mems(); return 0; } DEFINE_SHOW_ATTRIBUTE(ptdump); diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 515c411c2c83..5553508c3644 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -399,6 +399,7 @@ static void push_callee_regs(struct jit_ctx *ctx) emit(A64_PUSH(A64_R(23), A64_R(24), A64_SP), ctx); emit(A64_PUSH(A64_R(25), A64_R(26), A64_SP), ctx); emit(A64_PUSH(A64_R(27), A64_R(28), A64_SP), ctx); + ctx->fp_used = true; } else { find_used_callee_regs(ctx); for (i = 0; i + 1 < ctx->nr_used_callee_reg; i += 2) { diff --git a/arch/loongarch/include/asm/irqflags.h b/arch/loongarch/include/asm/irqflags.h index 319a8c616f1f..003172b8406b 100644 --- a/arch/loongarch/include/asm/irqflags.h +++ b/arch/loongarch/include/asm/irqflags.h @@ -14,40 +14,48 @@ static inline void arch_local_irq_enable(void) { u32 flags = CSR_CRMD_IE; + register u32 mask asm("t0") = CSR_CRMD_IE; + __asm__ __volatile__( "csrxchg %[val], %[mask], %[reg]\n\t" : [val] "+r" (flags) - : [mask] "r" (CSR_CRMD_IE), [reg] "i" (LOONGARCH_CSR_CRMD) + : [mask] "r" (mask), [reg] "i" (LOONGARCH_CSR_CRMD) : "memory"); } static inline void arch_local_irq_disable(void) { u32 flags = 0; + register u32 mask asm("t0") = CSR_CRMD_IE; + __asm__ __volatile__( "csrxchg %[val], %[mask], %[reg]\n\t" : [val] "+r" (flags) - : [mask] "r" (CSR_CRMD_IE), [reg] "i" (LOONGARCH_CSR_CRMD) + : [mask] "r" (mask), [reg] "i" (LOONGARCH_CSR_CRMD) : "memory"); } static inline unsigned long arch_local_irq_save(void) { u32 flags = 0; + register u32 mask asm("t0") = CSR_CRMD_IE; + __asm__ __volatile__( "csrxchg %[val], %[mask], %[reg]\n\t" : [val] "+r" (flags) - : [mask] "r" (CSR_CRMD_IE), [reg] "i" (LOONGARCH_CSR_CRMD) + : [mask] "r" (mask), [reg] "i" (LOONGARCH_CSR_CRMD) : "memory"); return flags; } static inline void arch_local_irq_restore(unsigned long flags) { + register u32 mask asm("t0") = CSR_CRMD_IE; + __asm__ __volatile__( "csrxchg %[val], %[mask], %[reg]\n\t" : [val] "+r" (flags) - : [mask] "r" (CSR_CRMD_IE), [reg] "i" (LOONGARCH_CSR_CRMD) + : [mask] "r" (mask), [reg] "i" (LOONGARCH_CSR_CRMD) : "memory"); } diff --git a/arch/loongarch/include/asm/vdso/getrandom.h b/arch/loongarch/include/asm/vdso/getrandom.h index 02f36772541b..7e9edc1cb610 100644 --- a/arch/loongarch/include/asm/vdso/getrandom.h +++ b/arch/loongarch/include/asm/vdso/getrandom.h @@ -20,7 +20,7 @@ static __always_inline ssize_t getrandom_syscall(void *_buffer, size_t _len, uns asm volatile( " syscall 0\n" - : "+r" (ret) + : "=r" (ret) : "r" (nr), "r" (buffer), "r" (len), "r" (flags) : "$t0", "$t1", "$t2", "$t3", "$t4", "$t5", "$t6", "$t7", "$t8", "memory"); diff --git a/arch/loongarch/include/asm/vdso/gettimeofday.h b/arch/loongarch/include/asm/vdso/gettimeofday.h index 89e6b222c2f2..2d1a9c27af29 100644 --- a/arch/loongarch/include/asm/vdso/gettimeofday.h +++ b/arch/loongarch/include/asm/vdso/gettimeofday.h @@ -25,7 +25,7 @@ static __always_inline long gettimeofday_fallback( asm volatile( " syscall 0\n" - : "+r" (ret) + : "=r" (ret) : "r" (nr), "r" (tv), "r" (tz) : "$t0", "$t1", "$t2", "$t3", "$t4", "$t5", "$t6", "$t7", "$t8", "memory"); @@ -44,7 +44,7 @@ static __always_inline long clock_gettime_fallback( asm volatile( " syscall 0\n" - : "+r" (ret) + : "=r" (ret) : "r" (nr), "r" (clkid), "r" (ts) : "$t0", "$t1", "$t2", "$t3", "$t4", "$t5", "$t6", "$t7", "$t8", "memory"); @@ -63,7 +63,7 @@ static __always_inline int clock_getres_fallback( asm volatile( " syscall 0\n" - : "+r" (ret) + : "=r" (ret) : "r" (nr), "r" (clkid), "r" (ts) : "$t0", "$t1", "$t2", "$t3", "$t4", "$t5", "$t6", "$t7", "$t8", "memory"); diff --git a/arch/loongarch/kernel/env.c b/arch/loongarch/kernel/env.c index 27144de5c5fe..c0a5dc9aeae2 100644 --- a/arch/loongarch/kernel/env.c +++ b/arch/loongarch/kernel/env.c @@ -39,16 +39,19 @@ void __init init_environ(void) static int __init init_cpu_fullname(void) { - struct device_node *root; int cpu, ret; - char *model; + char *cpuname; + const char *model; + struct device_node *root; /* Parsing cpuname from DTS model property */ root = of_find_node_by_path("/"); - ret = of_property_read_string(root, "model", (const char **)&model); + ret = of_property_read_string(root, "model", &model); + if (ret == 0) { + cpuname = kstrdup(model, GFP_KERNEL); + loongson_sysconf.cpuname = strsep(&cpuname, " "); + } of_node_put(root); - if (ret == 0) - loongson_sysconf.cpuname = strsep(&model, " "); if (loongson_sysconf.cpuname && !strncmp(loongson_sysconf.cpuname, "Loongson", 8)) { for (cpu = 0; cpu < NR_CPUS; cpu++) diff --git a/arch/loongarch/kernel/relocate_kernel.S b/arch/loongarch/kernel/relocate_kernel.S index 84e6de2fd973..8b5140ac9ea1 100644 --- a/arch/loongarch/kernel/relocate_kernel.S +++ b/arch/loongarch/kernel/relocate_kernel.S @@ -109,4 +109,4 @@ SYM_CODE_END(kexec_smp_wait) relocate_new_kernel_end: .section ".data" -SYM_DATA(relocate_new_kernel_size, .long relocate_new_kernel_end - relocate_new_kernel) +SYM_DATA(relocate_new_kernel_size, .quad relocate_new_kernel_end - relocate_new_kernel) diff --git a/arch/loongarch/kernel/unwind_orc.c b/arch/loongarch/kernel/unwind_orc.c index b25722876331..b4b4ac8dbf41 100644 --- a/arch/loongarch/kernel/unwind_orc.c +++ b/arch/loongarch/kernel/unwind_orc.c @@ -507,7 +507,7 @@ bool unwind_next_frame(struct unwind_state *state) state->pc = bt_address(pc); if (!state->pc) { - pr_err("cannot find unwind pc at %pK\n", (void *)pc); + pr_err("cannot find unwind pc at %p\n", (void *)pc); goto err; } diff --git a/arch/loongarch/mm/hugetlbpage.c b/arch/loongarch/mm/hugetlbpage.c index cea84d7f2b91..02dad4624fe3 100644 --- a/arch/loongarch/mm/hugetlbpage.c +++ b/arch/loongarch/mm/hugetlbpage.c @@ -47,7 +47,8 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, pmd = pmd_offset(pud, addr); } } - return pmd_none(pmdp_get(pmd)) ? NULL : (pte_t *) pmd; + + return (!pmd || pmd_none(pmdp_get(pmd))) ? NULL : (pte_t *) pmd; } uint64_t pmd_to_entrylo(unsigned long pmd_val) diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c index fa1500d4aa3e..5ba3249cea98 100644 --- a/arch/loongarch/net/bpf_jit.c +++ b/arch/loongarch/net/bpf_jit.c @@ -208,11 +208,9 @@ bool bpf_jit_supports_far_kfunc_call(void) return true; } -/* initialized on the first pass of build_body() */ -static int out_offset = -1; -static int emit_bpf_tail_call(struct jit_ctx *ctx) +static int emit_bpf_tail_call(struct jit_ctx *ctx, int insn) { - int off; + int off, tc_ninsn = 0; u8 tcc = tail_call_reg(ctx); u8 a1 = LOONGARCH_GPR_A1; u8 a2 = LOONGARCH_GPR_A2; @@ -222,7 +220,7 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx) const int idx0 = ctx->idx; #define cur_offset (ctx->idx - idx0) -#define jmp_offset (out_offset - (cur_offset)) +#define jmp_offset (tc_ninsn - (cur_offset)) /* * a0: &ctx @@ -232,6 +230,7 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx) * if (index >= array->map.max_entries) * goto out; */ + tc_ninsn = insn ? ctx->offset[insn+1] - ctx->offset[insn] : ctx->offset[0]; off = offsetof(struct bpf_array, map.max_entries); emit_insn(ctx, ldwu, t1, a1, off); /* bgeu $a2, $t1, jmp_offset */ @@ -263,15 +262,6 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx) emit_insn(ctx, ldd, t3, t2, off); __build_epilogue(ctx, true); - /* out: */ - if (out_offset == -1) - out_offset = cur_offset; - if (cur_offset != out_offset) { - pr_err_once("tail_call out_offset = %d, expected %d!\n", - cur_offset, out_offset); - return -1; - } - return 0; toofar: @@ -916,7 +906,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext /* tail call */ case BPF_JMP | BPF_TAIL_CALL: mark_tail_call(ctx); - if (emit_bpf_tail_call(ctx) < 0) + if (emit_bpf_tail_call(ctx, i) < 0) return -EINVAL; break; @@ -1342,7 +1332,6 @@ out: if (tmp_blinded) bpf_jit_prog_release_other(prog, prog == orig_prog ? tmp : orig_prog); - out_offset = -1; return prog; diff --git a/arch/m68k/Kconfig.debug b/arch/m68k/Kconfig.debug index 30638a6e8edc..d036f903864c 100644 --- a/arch/m68k/Kconfig.debug +++ b/arch/m68k/Kconfig.debug @@ -10,7 +10,7 @@ config BOOTPARAM_STRING config EARLY_PRINTK bool "Early printk" - depends on !(SUN3 || M68000 || COLDFIRE) + depends on MMU_MOTOROLA help Write kernel log output directly to a serial port. Where implemented, output goes to the framebuffer as well. diff --git a/arch/m68k/kernel/early_printk.c b/arch/m68k/kernel/early_printk.c index f11ef9f1f56f..521cbb8a150c 100644 --- a/arch/m68k/kernel/early_printk.c +++ b/arch/m68k/kernel/early_printk.c @@ -16,25 +16,10 @@ #include "../mvme147/mvme147.h" #include "../mvme16x/mvme16x.h" -asmlinkage void __init debug_cons_nputs(const char *s, unsigned n); - -static void __ref debug_cons_write(struct console *c, - const char *s, unsigned n) -{ -#if !(defined(CONFIG_SUN3) || defined(CONFIG_M68000) || \ - defined(CONFIG_COLDFIRE)) - if (MACH_IS_MVME147) - mvme147_scc_write(c, s, n); - else if (MACH_IS_MVME16x) - mvme16x_cons_write(c, s, n); - else - debug_cons_nputs(s, n); -#endif -} +asmlinkage void __init debug_cons_nputs(struct console *c, const char *s, unsigned int n); static struct console early_console_instance = { .name = "debug", - .write = debug_cons_write, .flags = CON_PRINTBUFFER | CON_BOOT, .index = -1 }; @@ -44,6 +29,12 @@ static int __init setup_early_printk(char *buf) if (early_console || buf) return 0; + if (MACH_IS_MVME147) + early_console_instance.write = mvme147_scc_write; + else if (MACH_IS_MVME16x) + early_console_instance.write = mvme16x_cons_write; + else + early_console_instance.write = debug_cons_nputs; early_console = &early_console_instance; register_console(early_console); @@ -51,20 +42,15 @@ static int __init setup_early_printk(char *buf) } early_param("earlyprintk", setup_early_printk); -/* - * debug_cons_nputs() defined in arch/m68k/kernel/head.S cannot be called - * after init sections are discarded (for platforms that use it). - */ -#if !(defined(CONFIG_SUN3) || defined(CONFIG_M68000) || \ - defined(CONFIG_COLDFIRE)) - static int __init unregister_early_console(void) { - if (!early_console || MACH_IS_MVME16x) - return 0; + /* + * debug_cons_nputs() defined in arch/m68k/kernel/head.S cannot be + * called after init sections are discarded (for platforms that use it). + */ + if (early_console && early_console->write == debug_cons_nputs) + return unregister_console(early_console); - return unregister_console(early_console); + return 0; } late_initcall(unregister_early_console); - -#endif diff --git a/arch/m68k/kernel/head.S b/arch/m68k/kernel/head.S index 852255cf60de..ba22bc2f3d6d 100644 --- a/arch/m68k/kernel/head.S +++ b/arch/m68k/kernel/head.S @@ -3263,8 +3263,8 @@ func_return putn * turns around and calls the internal routines. This routine * is used by the boot console. * - * The calling parameters are: - * void debug_cons_nputs(const char *str, unsigned length) + * The function signature is - + * void debug_cons_nputs(struct console *c, const char *s, unsigned int n) * * This routine does NOT understand variable arguments only * simple strings! @@ -3273,8 +3273,8 @@ ENTRY(debug_cons_nputs) moveml %d0/%d1/%a0,%sp@- movew %sr,%sp@- ori #0x0700,%sr - movel %sp@(18),%a0 /* fetch parameter */ - movel %sp@(22),%d1 /* fetch parameter */ + movel %sp@(22),%a0 /* char *s */ + movel %sp@(26),%d1 /* unsigned int n */ jra 2f 1: #ifdef CONSOLE_DEBUG diff --git a/arch/mips/include/asm/vpe.h b/arch/mips/include/asm/vpe.h index 61fd4d0aeda4..c0769dc4b853 100644 --- a/arch/mips/include/asm/vpe.h +++ b/arch/mips/include/asm/vpe.h @@ -119,4 +119,12 @@ void cleanup_tc(struct tc *tc); int __init vpe_module_init(void); void __exit vpe_module_exit(void); + +#ifdef CONFIG_MIPS_VPE_LOADER_MT +void *vpe_alloc(void); +int vpe_start(void *vpe, unsigned long start); +int vpe_stop(void *vpe); +int vpe_free(void *vpe); +#endif /* CONFIG_MIPS_VPE_LOADER_MT */ + #endif /* _ASM_VPE_H */ diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index b630604c577f..02aa6a04a21d 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -690,18 +690,20 @@ unsigned long mips_stack_top(void) } /* Space for the VDSO, data page & GIC user page */ - top -= PAGE_ALIGN(current->thread.abi->vdso->size); - top -= PAGE_SIZE; - top -= mips_gic_present() ? PAGE_SIZE : 0; + if (current->thread.abi) { + top -= PAGE_ALIGN(current->thread.abi->vdso->size); + top -= PAGE_SIZE; + top -= mips_gic_present() ? PAGE_SIZE : 0; + + /* Space to randomize the VDSO base */ + if (current->flags & PF_RANDOMIZE) + top -= VDSO_RANDOMIZE_SIZE; + } /* Space for cache colour alignment */ if (cpu_has_dc_aliases) top -= shm_align_mask + 1; - /* Space to randomize the VDSO base */ - if (current->flags & PF_RANDOMIZE) - top -= VDSO_RANDOMIZE_SIZE; - return top; } diff --git a/arch/mips/lantiq/falcon/sysctrl.c b/arch/mips/lantiq/falcon/sysctrl.c index 1187729d8cbb..357543996ee6 100644 --- a/arch/mips/lantiq/falcon/sysctrl.c +++ b/arch/mips/lantiq/falcon/sysctrl.c @@ -214,19 +214,16 @@ void __init ltq_soc_init(void) of_node_put(np_syseth); of_node_put(np_sysgpe); - if ((request_mem_region(res_status.start, resource_size(&res_status), - res_status.name) < 0) || - (request_mem_region(res_ebu.start, resource_size(&res_ebu), - res_ebu.name) < 0) || - (request_mem_region(res_sys[0].start, - resource_size(&res_sys[0]), - res_sys[0].name) < 0) || - (request_mem_region(res_sys[1].start, - resource_size(&res_sys[1]), - res_sys[1].name) < 0) || - (request_mem_region(res_sys[2].start, - resource_size(&res_sys[2]), - res_sys[2].name) < 0)) + if ((!request_mem_region(res_status.start, resource_size(&res_status), + res_status.name)) || + (!request_mem_region(res_ebu.start, resource_size(&res_ebu), + res_ebu.name)) || + (!request_mem_region(res_sys[0].start, resource_size(&res_sys[0]), + res_sys[0].name)) || + (!request_mem_region(res_sys[1].start, resource_size(&res_sys[1]), + res_sys[1].name)) || + (!request_mem_region(res_sys[2].start, resource_size(&res_sys[2]), + res_sys[2].name))) pr_err("Failed to request core resources"); status_membase = ioremap(res_status.start, diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c index 76f3b9c0a9f0..347126dc010d 100644 --- a/arch/mips/mm/tlb-r4k.c +++ b/arch/mips/mm/tlb-r4k.c @@ -508,6 +508,60 @@ static int __init set_ntlb(char *str) __setup("ntlb=", set_ntlb); +/* Initialise all TLB entries with unique values */ +static void r4k_tlb_uniquify(void) +{ + int entry = num_wired_entries(); + + htw_stop(); + write_c0_entrylo0(0); + write_c0_entrylo1(0); + + while (entry < current_cpu_data.tlbsize) { + unsigned long asid_mask = cpu_asid_mask(¤t_cpu_data); + unsigned long asid = 0; + int idx; + + /* Skip wired MMID to make ginvt_mmid work */ + if (cpu_has_mmid) + asid = MMID_KERNEL_WIRED + 1; + + /* Check for match before using UNIQUE_ENTRYHI */ + do { + if (cpu_has_mmid) { + write_c0_memorymapid(asid); + write_c0_entryhi(UNIQUE_ENTRYHI(entry)); + } else { + write_c0_entryhi(UNIQUE_ENTRYHI(entry) | asid); + } + mtc0_tlbw_hazard(); + tlb_probe(); + tlb_probe_hazard(); + idx = read_c0_index(); + /* No match or match is on current entry */ + if (idx < 0 || idx == entry) + break; + /* + * If we hit a match, we need to try again with + * a different ASID. + */ + asid++; + } while (asid < asid_mask); + + if (idx >= 0 && idx != entry) + panic("Unable to uniquify TLB entry %d", idx); + + write_c0_index(entry); + mtc0_tlbw_hazard(); + tlb_write_indexed(); + entry++; + } + + tlbw_use_hazard(); + htw_start(); + flush_micro_tlb(); +} + /* * Configure TLB (for init or after a CPU has been powered off). */ @@ -547,7 +601,7 @@ static void r4k_tlb_configure(void) temp_tlb_entry = current_cpu_data.tlbsize - 1; /* From this point on the ARC firmware is dead. */ - local_flush_tlb_all(); + r4k_tlb_uniquify(); /* Did I tell you that ARC SUCKS? */ } diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile index b289b2c1b294..c729bd687804 100644 --- a/arch/mips/vdso/Makefile +++ b/arch/mips/vdso/Makefile @@ -27,6 +27,7 @@ endif # offsets. cflags-vdso := $(ccflags-vdso) \ $(filter -W%,$(filter-out -Wa$(comma)%,$(KBUILD_CFLAGS))) \ + $(filter -std=%,$(KBUILD_CFLAGS)) \ -O3 -g -fPIC -fno-strict-aliasing -fno-common -fno-builtin -G 0 \ -mrelax-pic-calls $(call cc-option, -mexplicit-relocs) \ -fno-stack-protector -fno-jump-tables -DDISABLE_BRANCH_PROFILING \ diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile index 21b8166a6883..9cd9aa3d16f2 100644 --- a/arch/parisc/Makefile +++ b/arch/parisc/Makefile @@ -139,7 +139,7 @@ palo lifimage: vmlinuz fi @if test ! -f "$(PALOCONF)"; then \ cp $(srctree)/arch/parisc/defpalo.conf $(objtree)/palo.conf; \ - echo 'A generic palo config file ($(objree)/palo.conf) has been created for you.'; \ + echo 'A generic palo config file ($(objtree)/palo.conf) has been created for you.'; \ echo 'You should check it and re-run "make palo".'; \ echo 'WARNING: the "lifimage" file is now placed in this directory by default!'; \ false; \ diff --git a/arch/parisc/boot/compressed/Makefile b/arch/parisc/boot/compressed/Makefile index 92227fa813dc..17c42d718eb3 100644 --- a/arch/parisc/boot/compressed/Makefile +++ b/arch/parisc/boot/compressed/Makefile @@ -18,6 +18,7 @@ KBUILD_CFLAGS += -fno-PIE -mno-space-regs -mdisable-fpregs -Os ifndef CONFIG_64BIT KBUILD_CFLAGS += -mfast-indirect-calls endif +KBUILD_CFLAGS += -std=gnu11 LDFLAGS_vmlinux := -X -e startup --as-needed -T $(obj)/vmlinux: $(obj)/vmlinux.lds $(addprefix $(obj)/, $(OBJECTS)) $(LIBGCC) FORCE diff --git a/arch/parisc/kernel/unaligned.c b/arch/parisc/kernel/unaligned.c index f4626943633a..00e97204783e 100644 --- a/arch/parisc/kernel/unaligned.c +++ b/arch/parisc/kernel/unaligned.c @@ -25,7 +25,7 @@ #define DPRINTF(fmt, args...) #endif -#define RFMT "%#08lx" +#define RFMT "0x%08lx" /* 1111 1100 0000 0000 0001 0011 1100 0000 */ #define OPCODE1(a,b,c) ((a)<<26|(b)<<12|(c)<<6) diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index c06344db0eb3..1c67f64739a0 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -253,7 +253,6 @@ CONFIG_NET_SCH_DSMARK=m CONFIG_NET_SCH_NETEM=m CONFIG_NET_SCH_INGRESS=m CONFIG_NET_CLS_BASIC=m -CONFIG_NET_CLS_TCINDEX=m CONFIG_NET_CLS_ROUTE4=m CONFIG_NET_CLS_FW=m CONFIG_NET_CLS_U32=m diff --git a/arch/powerpc/crypto/Kconfig b/arch/powerpc/crypto/Kconfig index 7012fa55aceb..15783f2307df 100644 --- a/arch/powerpc/crypto/Kconfig +++ b/arch/powerpc/crypto/Kconfig @@ -143,6 +143,7 @@ config CRYPTO_CHACHA20_P10 config CRYPTO_POLY1305_P10 tristate "Hash functions: Poly1305 (P10 or later)" depends on PPC64 && CPU_LITTLE_ENDIAN && VSX + depends on BROKEN # Needs to be fixed to work in softirq context select CRYPTO_HASH select CRYPTO_LIB_POLY1305_GENERIC help diff --git a/arch/powerpc/include/asm/floppy.h b/arch/powerpc/include/asm/floppy.h index f8ce178b43b7..34abf8bea2cc 100644 --- a/arch/powerpc/include/asm/floppy.h +++ b/arch/powerpc/include/asm/floppy.h @@ -144,9 +144,12 @@ static int hard_dma_setup(char *addr, unsigned long size, int mode, int io) bus_addr = 0; } - if (!bus_addr) /* need to map it */ + if (!bus_addr) { /* need to map it */ bus_addr = dma_map_single(&isa_bridge_pcidev->dev, addr, size, dir); + if (dma_mapping_error(&isa_bridge_pcidev->dev, bus_addr)) + return -ENOMEM; + } /* remember this one as prev */ prev_addr = addr; diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h index 02897f4b0dbf..b891910fce8a 100644 --- a/arch/powerpc/include/asm/ppc_asm.h +++ b/arch/powerpc/include/asm/ppc_asm.h @@ -183,7 +183,7 @@ /* * Used to name C functions called from asm */ -#ifdef CONFIG_PPC_KERNEL_PCREL +#if defined(__powerpc64__) && defined(CONFIG_PPC_KERNEL_PCREL) #define CFUNC(name) name@notoc #else #define CFUNC(name) name diff --git a/arch/powerpc/include/uapi/asm/ioctls.h b/arch/powerpc/include/uapi/asm/ioctls.h index 2c145da3b774..b5211e413829 100644 --- a/arch/powerpc/include/uapi/asm/ioctls.h +++ b/arch/powerpc/include/uapi/asm/ioctls.h @@ -23,10 +23,10 @@ #define TCSETSW _IOW('t', 21, struct termios) #define TCSETSF _IOW('t', 22, struct termios) -#define TCGETA _IOR('t', 23, struct termio) -#define TCSETA _IOW('t', 24, struct termio) -#define TCSETAW _IOW('t', 25, struct termio) -#define TCSETAF _IOW('t', 28, struct termio) +#define TCGETA 0x40147417 /* _IOR('t', 23, struct termio) */ +#define TCSETA 0x80147418 /* _IOW('t', 24, struct termio) */ +#define TCSETAW 0x80147419 /* _IOW('t', 25, struct termio) */ +#define TCSETAF 0x8014741c /* _IOW('t', 28, struct termio) */ #define TCSBRK _IO('t', 29) #define TCXONC _IO('t', 30) diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index b4006a4a1121..04d6a1e8ff9a 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -162,9 +162,7 @@ endif obj64-$(CONFIG_PPC_TRANSACTIONAL_MEM) += tm.o -ifneq ($(CONFIG_XMON)$(CONFIG_KEXEC_CORE)$(CONFIG_PPC_BOOK3S),) obj-y += ppc_save_regs.o -endif obj-$(CONFIG_EPAPR_PARAVIRT) += epapr_paravirt.o epapr_hcalls.o obj-$(CONFIG_KVM_GUEST) += kvm.o kvm_emul.o diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 83fe99861eb1..2b5f3323e107 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -1139,6 +1139,7 @@ int eeh_unfreeze_pe(struct eeh_pe *pe) return ret; } +EXPORT_SYMBOL_GPL(eeh_unfreeze_pe); static struct pci_device_id eeh_reset_ids[] = { @@ -1509,6 +1510,8 @@ int eeh_pe_configure(struct eeh_pe *pe) /* Invalid PE ? */ if (!pe) return -ENODEV; + else + ret = eeh_ops->configure_bridge(pe); return ret; } diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 7efe04c68f0f..dd50de91c438 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -257,13 +257,12 @@ static void eeh_pe_report_edev(struct eeh_dev *edev, eeh_report_fn fn, struct pci_driver *driver; enum pci_ers_result new_result; - pci_lock_rescan_remove(); pdev = edev->pdev; if (pdev) get_device(&pdev->dev); - pci_unlock_rescan_remove(); if (!pdev) { eeh_edev_info(edev, "no device"); + *result = PCI_ERS_RESULT_DISCONNECT; return; } device_lock(&pdev->dev); @@ -304,8 +303,9 @@ static void eeh_pe_report(const char *name, struct eeh_pe *root, struct eeh_dev *edev, *tmp; pr_info("EEH: Beginning: '%s'\n", name); - eeh_for_each_pe(root, pe) eeh_pe_for_each_dev(pe, edev, tmp) - eeh_pe_report_edev(edev, fn, result); + eeh_for_each_pe(root, pe) + eeh_pe_for_each_dev(pe, edev, tmp) + eeh_pe_report_edev(edev, fn, result); if (result) pr_info("EEH: Finished:'%s' with aggregate recovery state:'%s'\n", name, pci_ers_result_name(*result)); @@ -383,6 +383,8 @@ static void eeh_dev_restore_state(struct eeh_dev *edev, void *userdata) if (!edev) return; + pci_lock_rescan_remove(); + /* * The content in the config space isn't saved because * the blocked config space on some adapters. We have @@ -393,14 +395,19 @@ static void eeh_dev_restore_state(struct eeh_dev *edev, void *userdata) if (list_is_last(&edev->entry, &edev->pe->edevs)) eeh_pe_restore_bars(edev->pe); + pci_unlock_rescan_remove(); return; } pdev = eeh_dev_to_pci_dev(edev); - if (!pdev) + if (!pdev) { + pci_unlock_rescan_remove(); return; + } pci_restore_state(pdev); + + pci_unlock_rescan_remove(); } /** @@ -647,9 +654,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus, if (any_passed || driver_eeh_aware || (pe->type & EEH_PE_VF)) { eeh_pe_dev_traverse(pe, eeh_rmv_device, rmv_data); } else { - pci_lock_rescan_remove(); pci_hp_remove_devices(bus); - pci_unlock_rescan_remove(); } /* @@ -665,8 +670,6 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus, if (rc) return rc; - pci_lock_rescan_remove(); - /* Restore PE */ eeh_ops->configure_bridge(pe); eeh_pe_restore_bars(pe); @@ -674,7 +677,6 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus, /* Clear frozen state */ rc = eeh_clear_pe_frozen_state(pe, false); if (rc) { - pci_unlock_rescan_remove(); return rc; } @@ -709,7 +711,6 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus, pe->tstamp = tstamp; pe->freeze_count = cnt; - pci_unlock_rescan_remove(); return 0; } @@ -843,10 +844,13 @@ void eeh_handle_normal_event(struct eeh_pe *pe) {LIST_HEAD_INIT(rmv_data.removed_vf_list), 0}; int devices = 0; + pci_lock_rescan_remove(); + bus = eeh_pe_bus_get(pe); if (!bus) { pr_err("%s: Cannot find PCI bus for PHB#%x-PE#%x\n", __func__, pe->phb->global_number, pe->addr); + pci_unlock_rescan_remove(); return; } @@ -1094,10 +1098,15 @@ recover_failed: eeh_pe_state_clear(pe, EEH_PE_PRI_BUS, true); eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED); - pci_lock_rescan_remove(); - pci_hp_remove_devices(bus); - pci_unlock_rescan_remove(); + bus = eeh_pe_bus_get(pe); + if (bus) + pci_hp_remove_devices(bus); + else + pr_err("%s: PCI bus for PHB#%x-PE#%x disappeared\n", + __func__, pe->phb->global_number, pe->addr); + /* The passed PE should no longer be used */ + pci_unlock_rescan_remove(); return; } @@ -1114,6 +1123,8 @@ out: eeh_clear_slot_attention(edev->pdev); eeh_pe_state_clear(pe, EEH_PE_RECOVERING, true); + + pci_unlock_rescan_remove(); } /** @@ -1132,6 +1143,7 @@ void eeh_handle_special_event(void) unsigned long flags; int rc; + pci_lock_rescan_remove(); do { rc = eeh_ops->next_error(&pe); @@ -1171,10 +1183,12 @@ void eeh_handle_special_event(void) break; case EEH_NEXT_ERR_NONE: + pci_unlock_rescan_remove(); return; default: pr_warn("%s: Invalid value %d from next_error()\n", __func__, rc); + pci_unlock_rescan_remove(); return; } @@ -1186,7 +1200,9 @@ void eeh_handle_special_event(void) if (rc == EEH_NEXT_ERR_FROZEN_PE || rc == EEH_NEXT_ERR_FENCED_PHB) { eeh_pe_state_mark(pe, EEH_PE_RECOVERING); + pci_unlock_rescan_remove(); eeh_handle_normal_event(pe); + pci_lock_rescan_remove(); } else { eeh_for_each_pe(pe, tmp_pe) eeh_pe_for_each_dev(tmp_pe, edev, tmp_edev) @@ -1199,7 +1215,6 @@ void eeh_handle_special_event(void) eeh_report_failure, NULL); eeh_set_channel_state(pe, pci_channel_io_perm_failure); - pci_lock_rescan_remove(); list_for_each_entry(hose, &hose_list, list_node) { phb_pe = eeh_phb_pe_get(hose); if (!phb_pe || @@ -1218,7 +1233,6 @@ void eeh_handle_special_event(void) } pci_hp_remove_devices(bus); } - pci_unlock_rescan_remove(); } /* @@ -1228,4 +1242,6 @@ void eeh_handle_special_event(void) if (rc == EEH_NEXT_ERR_DEAD_IOC) break; } while (rc != EEH_NEXT_ERR_NONE); + + pci_unlock_rescan_remove(); } diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index d283d281d28e..e740101fadf3 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -671,10 +671,12 @@ static void eeh_bridge_check_link(struct eeh_dev *edev) eeh_ops->write_config(edev, cap + PCI_EXP_LNKCTL, 2, val); /* Check link */ - if (!edev->pdev->link_active_reporting) { - eeh_edev_dbg(edev, "No link reporting capability\n"); - msleep(1000); - return; + if (edev->pdev) { + if (!edev->pdev->link_active_reporting) { + eeh_edev_dbg(edev, "No link reporting capability\n"); + msleep(1000); + return; + } } /* Wait the link is up until timeout (5s) */ diff --git a/arch/powerpc/kernel/pci-hotplug.c b/arch/powerpc/kernel/pci-hotplug.c index 9ea74973d78d..6f444d0822d8 100644 --- a/arch/powerpc/kernel/pci-hotplug.c +++ b/arch/powerpc/kernel/pci-hotplug.c @@ -141,6 +141,9 @@ void pci_hp_add_devices(struct pci_bus *bus) struct pci_controller *phb; struct device_node *dn = pci_bus_to_OF_node(bus); + if (!dn) + return; + phb = pci_bus_to_host(bus); mode = PCI_PROBE_NORMAL; diff --git a/arch/powerpc/kernel/vdso/Makefile b/arch/powerpc/kernel/vdso/Makefile index c568cad6a22e..6ba68b28ed87 100644 --- a/arch/powerpc/kernel/vdso/Makefile +++ b/arch/powerpc/kernel/vdso/Makefile @@ -53,7 +53,7 @@ ldflags-$(CONFIG_LD_ORPHAN_WARN) += -Wl,--orphan-handling=$(CONFIG_LD_ORPHAN_WAR ldflags-y += $(filter-out $(CC_AUTO_VAR_INIT_ZERO_ENABLER) $(CC_FLAGS_FTRACE) -Wa$(comma)%, $(KBUILD_CFLAGS)) CC32FLAGS := -m32 -CC32FLAGSREMOVE := -mcmodel=medium -mabi=elfv1 -mabi=elfv2 -mcall-aixdesc +CC32FLAGSREMOVE := -mcmodel=medium -mabi=elfv1 -mabi=elfv2 -mcall-aixdesc -mpcrel ifdef CONFIG_CC_IS_CLANG # This flag is supported by clang for 64-bit but not 32-bit so it will cause # an unused command line flag warning for this file. diff --git a/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c b/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c index 9668b052cd4b..f251e0f68262 100644 --- a/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c +++ b/arch/powerpc/platforms/512x/mpc512x_lpbfifo.c @@ -240,10 +240,8 @@ static int mpc512x_lpbfifo_kick(void) dma_conf.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES; /* Make DMA channel work with LPB FIFO data register */ - if (dma_dev->device_config(lpbfifo.chan, &dma_conf)) { - ret = -EINVAL; - goto err_dma_prep; - } + if (dma_dev->device_config(lpbfifo.chan, &dma_conf)) + return -EINVAL; sg_init_table(&sg, 1); diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c index 213aa26dc8b3..979487da6522 100644 --- a/arch/powerpc/platforms/pseries/dlpar.c +++ b/arch/powerpc/platforms/pseries/dlpar.c @@ -404,6 +404,45 @@ get_device_node_with_drc_info(u32 index) return NULL; } +static struct device_node * +get_device_node_with_drc_indexes(u32 drc_index) +{ + struct device_node *np = NULL; + u32 nr_indexes, index; + int i, rc; + + for_each_node_with_property(np, "ibm,drc-indexes") { + /* + * First element in the array is the total number of + * DRC indexes returned. + */ + rc = of_property_read_u32_index(np, "ibm,drc-indexes", + 0, &nr_indexes); + if (rc) + goto out_put_np; + + /* + * Retrieve DRC index from the list and return the + * device node if matched with the specified index. + */ + for (i = 0; i < nr_indexes; i++) { + rc = of_property_read_u32_index(np, "ibm,drc-indexes", + i+1, &index); + if (rc) + goto out_put_np; + + if (drc_index == index) + return np; + } + } + + return NULL; + +out_put_np: + of_node_put(np); + return NULL; +} + static int dlpar_hp_dt_add(u32 index) { struct device_node *np, *nodes; @@ -423,10 +462,19 @@ static int dlpar_hp_dt_add(u32 index) goto out; } + /* + * Recent FW provides ibm,drc-info property. So search + * for the user specified DRC index from ibm,drc-info + * property. If this property is not available, search + * in the indexes array from ibm,drc-indexes property. + */ np = get_device_node_with_drc_info(index); - if (!np) - return -EIO; + if (!np) { + np = get_device_node_with_drc_indexes(index); + if (!np) + return -EIO; + } /* Next, configure the connector. */ nodes = dlpar_configure_connector(cpu_to_be32(index), np); diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c index 6dfb55b52d36..ba98a680a12e 100644 --- a/arch/powerpc/platforms/pseries/msi.c +++ b/arch/powerpc/platforms/pseries/msi.c @@ -524,7 +524,12 @@ static struct msi_domain_info pseries_msi_domain_info = { static void pseries_msi_compose_msg(struct irq_data *data, struct msi_msg *msg) { - __pci_read_msi_msg(irq_data_get_msi_desc(data), msg); + struct pci_dev *dev = msi_desc_to_pci_dev(irq_data_get_msi_desc(data)); + + if (dev->current_state == PCI_D0) + __pci_read_msi_msg(irq_data_get_msi_desc(data), msg); + else + get_cached_msi_msg(data->irq, msg); } static struct irq_chip pseries_msi_irq_chip = { diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h index ebbce134917c..6efa95ad033a 100644 --- a/arch/riscv/include/asm/cmpxchg.h +++ b/arch/riscv/include/asm/cmpxchg.h @@ -169,7 +169,7 @@ break; \ case 4: \ __arch_cmpxchg(".w", ".w" sc_sfx, prepend, append, \ - __ret, __ptr, (long), __old, __new); \ + __ret, __ptr, (long)(int)(long), __old, __new); \ break; \ case 8: \ __arch_cmpxchg(".d", ".d" sc_sfx, prepend, append, \ diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 479550cdb440..03881122506a 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -916,7 +916,6 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte) */ #ifdef CONFIG_64BIT #define TASK_SIZE_64 (PGDIR_SIZE * PTRS_PER_PGD / 2) -#define TASK_SIZE_MAX LONG_MAX #ifdef CONFIG_COMPAT #define TASK_SIZE_32 (_AC(0x80000000, UL) - PAGE_SIZE) diff --git a/arch/riscv/kernel/cpu_ops_sbi.c b/arch/riscv/kernel/cpu_ops_sbi.c index e6fbaaf54956..87d655944803 100644 --- a/arch/riscv/kernel/cpu_ops_sbi.c +++ b/arch/riscv/kernel/cpu_ops_sbi.c @@ -18,10 +18,10 @@ const struct cpu_operations cpu_ops_sbi; /* * Ordered booting via HSM brings one cpu at a time. However, cpu hotplug can - * be invoked from multiple threads in parallel. Define a per cpu data + * be invoked from multiple threads in parallel. Define an array of boot data * to handle that. */ -static DEFINE_PER_CPU(struct sbi_hart_boot_data, boot_data); +static struct sbi_hart_boot_data boot_data[NR_CPUS]; static int sbi_hsm_hart_start(unsigned long hartid, unsigned long saddr, unsigned long priv) @@ -67,7 +67,7 @@ static int sbi_cpu_start(unsigned int cpuid, struct task_struct *tidle) unsigned long boot_addr = __pa_symbol(secondary_start_sbi); unsigned long hartid = cpuid_to_hartid_map(cpuid); unsigned long hsm_data; - struct sbi_hart_boot_data *bdata = &per_cpu(boot_data, cpuid); + struct sbi_hart_boot_data *bdata = &boot_data[cpuid]; /* Make sure tidle is updated */ smp_mb(); diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index 9c83848797a7..80230de167de 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -6,6 +6,7 @@ #include <linux/cpu.h> #include <linux/kernel.h> #include <linux/init.h> +#include <linux/irqflags.h> #include <linux/randomize_kstack.h> #include <linux/sched.h> #include <linux/sched/debug.h> @@ -151,7 +152,9 @@ asmlinkage __visible __trap_section void name(struct pt_regs *regs) \ { \ if (user_mode(regs)) { \ irqentry_enter_from_user_mode(regs); \ + local_irq_enable(); \ do_trap_error(regs, signo, code, regs->epc, "Oops - " str); \ + local_irq_disable(); \ irqentry_exit_to_user_mode(regs); \ } else { \ irqentry_state_t state = irqentry_nmi_enter(regs); \ @@ -173,17 +176,14 @@ asmlinkage __visible __trap_section void do_trap_insn_illegal(struct pt_regs *re if (user_mode(regs)) { irqentry_enter_from_user_mode(regs); - local_irq_enable(); handled = riscv_v_first_use_handler(regs); - - local_irq_disable(); - if (!handled) do_trap_error(regs, SIGILL, ILL_ILLOPC, regs->epc, "Oops - illegal instruction"); + local_irq_disable(); irqentry_exit_to_user_mode(regs); } else { irqentry_state_t state = irqentry_nmi_enter(regs); @@ -308,9 +308,11 @@ asmlinkage __visible __trap_section void do_trap_break(struct pt_regs *regs) { if (user_mode(regs)) { irqentry_enter_from_user_mode(regs); + local_irq_enable(); handle_break(regs); + local_irq_disable(); irqentry_exit_to_user_mode(regs); } else { irqentry_state_t state = irqentry_nmi_enter(regs); diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c index 36ac96eac9c9..4128aa5e0c76 100644 --- a/arch/riscv/kernel/traps_misaligned.c +++ b/arch/riscv/kernel/traps_misaligned.c @@ -429,14 +429,14 @@ int handle_misaligned_load(struct pt_regs *regs) val.data_u64 = 0; if (user_mode(regs)) { - if (copy_from_user_nofault(&val, (u8 __user *)addr, len)) + if (copy_from_user(&val, (u8 __user *)addr, len)) return -1; } else { memcpy(&val, (u8 *)addr, len); } if (!fp) - SET_RD(insn, regs, val.data_ulong << shift >> shift); + SET_RD(insn, regs, (long)(val.data_ulong << shift) >> shift); else if (len == 8) set_f64_rd(insn, regs, val.data_u64); else @@ -530,7 +530,7 @@ int handle_misaligned_store(struct pt_regs *regs) return -EOPNOTSUPP; if (user_mode(regs)) { - if (copy_to_user_nofault((u8 __user *)addr, &val, len)) + if (copy_to_user((u8 __user *)addr, &val, len)) return -1; } else { memcpy((u8 *)addr, &val, len); diff --git a/arch/riscv/kernel/vdso/vdso.lds.S b/arch/riscv/kernel/vdso/vdso.lds.S index cbe2a179331d..99e51f775539 100644 --- a/arch/riscv/kernel/vdso/vdso.lds.S +++ b/arch/riscv/kernel/vdso/vdso.lds.S @@ -31,7 +31,7 @@ SECTIONS *(.data .data.* .gnu.linkonce.d.*) *(.dynbss) *(.bss .bss.* .gnu.linkonce.b.*) - } + } :text .note : { *(.note.*) } :text :note diff --git a/arch/riscv/kvm/vcpu_sbi_replace.c b/arch/riscv/kvm/vcpu_sbi_replace.c index 5fbf3f94f1e8..b17fad091bab 100644 --- a/arch/riscv/kvm/vcpu_sbi_replace.c +++ b/arch/riscv/kvm/vcpu_sbi_replace.c @@ -103,7 +103,7 @@ static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_FENCE_I_SENT); break; case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA: - if (cp->a2 == 0 && cp->a3 == 0) + if ((cp->a2 == 0 && cp->a3 == 0) || cp->a3 == -1UL) kvm_riscv_hfence_vvma_all(vcpu->kvm, hbase, hmask); else kvm_riscv_hfence_vvma_gva(vcpu->kvm, hbase, hmask, @@ -111,7 +111,7 @@ static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_HFENCE_VVMA_SENT); break; case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID: - if (cp->a2 == 0 && cp->a3 == 0) + if ((cp->a2 == 0 && cp->a3 == 0) || cp->a3 == -1UL) kvm_riscv_hfence_vvma_asid_all(vcpu->kvm, hbase, hmask, cp->a4); else @@ -127,9 +127,9 @@ static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run case SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA_ASID: /* * Until nested virtualization is implemented, the - * SBI HFENCE calls should be treated as NOPs + * SBI HFENCE calls should return not supported + * hence fallthrough. */ - break; default: retdata->err_val = SBI_ERR_NOT_SUPPORTED; } diff --git a/arch/riscv/mm/cacheflush.c b/arch/riscv/mm/cacheflush.c index b81672729887..b2e4b81763f8 100644 --- a/arch/riscv/mm/cacheflush.c +++ b/arch/riscv/mm/cacheflush.c @@ -24,7 +24,20 @@ void flush_icache_all(void) if (num_online_cpus() < 2) return; - else if (riscv_use_sbi_for_rfence()) + + /* + * Make sure all previous writes to the D$ are ordered before making + * the IPI. The RISC-V spec states that a hart must execute a data fence + * before triggering a remote fence.i in order to make the modification + * visable for remote harts. + * + * IPIs on RISC-V are triggered by MMIO writes to either CLINT or + * S-IMSIC, so the fence ensures previous data writes "happen before" + * the MMIO. + */ + RISCV_FENCE(w, o); + + if (riscv_use_sbi_for_rfence()) sbi_remote_fence_i(NULL); else on_each_cpu(ipi_remote_fence_i, NULL, 1); diff --git a/arch/riscv/mm/ptdump.c b/arch/riscv/mm/ptdump.c index 9d5f657a251b..1289cc6d3700 100644 --- a/arch/riscv/mm/ptdump.c +++ b/arch/riscv/mm/ptdump.c @@ -6,7 +6,6 @@ #include <linux/efi.h> #include <linux/init.h> #include <linux/debugfs.h> -#include <linux/memory_hotplug.h> #include <linux/seq_file.h> #include <linux/ptdump.h> @@ -371,9 +370,7 @@ bool ptdump_check_wx(void) static int ptdump_show(struct seq_file *m, void *v) { - get_online_mems(); ptdump_walk(m, m->private); - put_online_mems(); return 0; } diff --git a/arch/s390/crypto/sha1_s390.c b/arch/s390/crypto/sha1_s390.c index bc3a22704e09..10950953429e 100644 --- a/arch/s390/crypto/sha1_s390.c +++ b/arch/s390/crypto/sha1_s390.c @@ -38,6 +38,7 @@ static int s390_sha1_init(struct shash_desc *desc) sctx->state[4] = SHA1_H4; sctx->count = 0; sctx->func = CPACF_KIMD_SHA_1; + sctx->first_message_part = 0; return 0; } @@ -62,6 +63,7 @@ static int s390_sha1_import(struct shash_desc *desc, const void *in) memcpy(sctx->state, ictx->state, sizeof(ictx->state)); memcpy(sctx->buf, ictx->buffer, sizeof(ictx->buffer)); sctx->func = CPACF_KIMD_SHA_1; + sctx->first_message_part = 0; return 0; } diff --git a/arch/s390/crypto/sha256_s390.c b/arch/s390/crypto/sha256_s390.c index 6f1ccdf93d3e..0204d4bca340 100644 --- a/arch/s390/crypto/sha256_s390.c +++ b/arch/s390/crypto/sha256_s390.c @@ -31,6 +31,7 @@ static int s390_sha256_init(struct shash_desc *desc) sctx->state[7] = SHA256_H7; sctx->count = 0; sctx->func = CPACF_KIMD_SHA_256; + sctx->first_message_part = 0; return 0; } @@ -55,6 +56,7 @@ static int sha256_import(struct shash_desc *desc, const void *in) memcpy(sctx->state, ictx->state, sizeof(ictx->state)); memcpy(sctx->buf, ictx->buf, sizeof(ictx->buf)); sctx->func = CPACF_KIMD_SHA_256; + sctx->first_message_part = 0; return 0; } @@ -90,6 +92,7 @@ static int s390_sha224_init(struct shash_desc *desc) sctx->state[7] = SHA224_H7; sctx->count = 0; sctx->func = CPACF_KIMD_SHA_256; + sctx->first_message_part = 0; return 0; } diff --git a/arch/s390/crypto/sha512_s390.c b/arch/s390/crypto/sha512_s390.c index 04f11c407763..b53a7793bd24 100644 --- a/arch/s390/crypto/sha512_s390.c +++ b/arch/s390/crypto/sha512_s390.c @@ -32,6 +32,7 @@ static int sha512_init(struct shash_desc *desc) *(__u64 *)&ctx->state[14] = SHA512_H7; ctx->count = 0; ctx->func = CPACF_KIMD_SHA_512; + ctx->first_message_part = 0; return 0; } @@ -60,6 +61,7 @@ static int sha512_import(struct shash_desc *desc, const void *in) memcpy(sctx->state, ictx->state, sizeof(ictx->state)); memcpy(sctx->buf, ictx->buf, sizeof(ictx->buf)); sctx->func = CPACF_KIMD_SHA_512; + sctx->first_message_part = 0; return 0; } @@ -97,6 +99,7 @@ static int sha384_init(struct shash_desc *desc) *(__u64 *)&ctx->state[14] = SHA384_H7; ctx->count = 0; ctx->func = CPACF_KIMD_SHA_512; + ctx->first_message_part = 0; return 0; } diff --git a/arch/s390/include/asm/ap.h b/arch/s390/include/asm/ap.h index 395b02d6a133..352108727d7e 100644 --- a/arch/s390/include/asm/ap.h +++ b/arch/s390/include/asm/ap.h @@ -103,7 +103,7 @@ struct ap_tapq_hwinfo { unsigned int accel : 1; /* A */ unsigned int ep11 : 1; /* X */ unsigned int apxa : 1; /* APXA */ - unsigned int : 1; + unsigned int slcf : 1; /* Cmd filtering avail. */ unsigned int class : 8; unsigned int bs : 2; /* SE bind/assoc */ unsigned int : 14; diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h index 640901f2fbc3..811ec531954b 100644 --- a/arch/s390/include/asm/timex.h +++ b/arch/s390/include/asm/timex.h @@ -192,13 +192,6 @@ static inline unsigned long get_tod_clock_fast(void) asm volatile("stckf %0" : "=Q" (clk) : : "cc"); return clk; } - -static inline cycles_t get_cycles(void) -{ - return (cycles_t) get_tod_clock() >> 2; -} -#define get_cycles get_cycles - int get_phys_clock(unsigned long *clock); void init_cpu_timer(void); @@ -226,6 +219,12 @@ static inline unsigned long get_tod_clock_monotonic(void) return tod; } +static inline cycles_t get_cycles(void) +{ + return (cycles_t)get_tod_clock_monotonic() >> 2; +} +#define get_cycles get_cycles + /** * tod_to_ns - convert a TOD format value to nanoseconds * @todval: to be converted TOD format value diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index 62f8f5a750a3..0c054e2d1e03 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -183,6 +183,7 @@ void __init __do_early_pgm_check(struct pt_regs *regs) regs->int_code = lc->pgm_int_code; regs->int_parm_long = lc->trans_exc_code; + regs->last_break = lc->pgm_last_break; ip = __rewind_psw(regs->psw, regs->int_code >> 16); /* Monitor Event? Might be a warning */ diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index b713effe0579..96fc41f26d7e 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -579,7 +579,7 @@ static int stp_sync_clock(void *data) atomic_dec(&sync->cpus); /* Wait for in_sync to be set. */ while (READ_ONCE(sync->in_sync) == 0) - __udelay(1); + ; } if (sync->in_sync != 1) /* Didn't work. Clear per-cpu in sync bit again. */ diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c index a688351f4ab5..7bc97ebd60d5 100644 --- a/arch/s390/kvm/gaccess.c +++ b/arch/s390/kvm/gaccess.c @@ -317,7 +317,7 @@ enum prot_type { PROT_TYPE_DAT = 3, PROT_TYPE_IEP = 4, /* Dummy value for passing an initialized value when code != PGM_PROTECTION */ - PROT_NONE, + PROT_TYPE_DUMMY, }; static int trans_exc_ending(struct kvm_vcpu *vcpu, int code, unsigned long gva, u8 ar, @@ -333,7 +333,7 @@ static int trans_exc_ending(struct kvm_vcpu *vcpu, int code, unsigned long gva, switch (code) { case PGM_PROTECTION: switch (prot) { - case PROT_NONE: + case PROT_TYPE_DUMMY: /* We should never get here, acts like termination */ WARN_ON_ONCE(1); break; @@ -803,7 +803,7 @@ static int guest_range_to_gpas(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar, gpa = kvm_s390_real_to_abs(vcpu, ga); if (!kvm_is_gpa_in_memslot(vcpu->kvm, gpa)) { rc = PGM_ADDRESSING; - prot = PROT_NONE; + prot = PROT_TYPE_DUMMY; } } if (rc) @@ -961,7 +961,7 @@ int access_guest_with_key(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar, if (rc == PGM_PROTECTION) prot = PROT_TYPE_KEYC; else - prot = PROT_NONE; + prot = PROT_TYPE_DUMMY; rc = trans_exc_ending(vcpu, rc, ga, ar, mode, prot, terminate); } out_unlock: diff --git a/arch/s390/mm/dump_pagetables.c b/arch/s390/mm/dump_pagetables.c index fa54f3bc0c8d..70f184ca648f 100644 --- a/arch/s390/mm/dump_pagetables.c +++ b/arch/s390/mm/dump_pagetables.c @@ -203,11 +203,9 @@ static int ptdump_show(struct seq_file *m, void *v) .marker = markers, }; - get_online_mems(); mutex_lock(&cpa_mutex); ptdump_walk_pgd(&st.ptdump, &init_mm, NULL); mutex_unlock(&cpa_mutex); - put_online_mems(); return 0; } DEFINE_SHOW_ATTRIBUTE(ptdump); diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c index f691e0fb66a2..f5dece935353 100644 --- a/arch/s390/mm/pgalloc.c +++ b/arch/s390/mm/pgalloc.c @@ -219,11 +219,6 @@ void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable) struct ptdesc *ptdesc = virt_to_ptdesc(pgtable); call_rcu(&ptdesc->pt_rcu_head, pte_free_now); - /* - * THPs are not allowed for KVM guests. Warn if pgste ever reaches here. - * Turn to the generic pte_free_defer() version once gmap is removed. - */ - WARN_ON_ONCE(mm_has_pgste(mm)); } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index 665b8228afeb..dd971826652a 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -63,13 +63,12 @@ void *vmem_crst_alloc(unsigned long val) pte_t __ref *vmem_pte_alloc(void) { - unsigned long size = PTRS_PER_PTE * sizeof(pte_t); pte_t *pte; if (slab_is_available()) - pte = (pte_t *) page_table_alloc(&init_mm); + pte = (pte_t *)page_table_alloc(&init_mm); else - pte = (pte_t *) memblock_alloc(size, size); + pte = (pte_t *)memblock_alloc(PAGE_SIZE, PAGE_SIZE); if (!pte) return NULL; memset64((u64 *)pte, _PAGE_INVALID, PTRS_PER_PTE); diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index 64bb8b71013a..ead8d9ba9032 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -544,7 +544,15 @@ static void bpf_jit_plt(struct bpf_plt *plt, void *ret, void *target) { memcpy(plt, &bpf_plt, sizeof(*plt)); plt->ret = ret; - plt->target = target; + /* + * (target == NULL) implies that the branch to this PLT entry was + * patched and became a no-op. However, some CPU could have jumped + * to this PLT entry before patching and may be still executing it. + * + * Since the intention in this case is to make the PLT entry a no-op, + * make the target point to the return label instead of NULL. + */ + plt->target = target ?: ret; } /* diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 88f72745fa59..9e19d6076d3e 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -44,6 +44,7 @@ /* list of all detected zpci devices */ static LIST_HEAD(zpci_list); static DEFINE_SPINLOCK(zpci_list_lock); +static DEFINE_MUTEX(zpci_add_remove_lock); static DECLARE_BITMAP(zpci_domain, ZPCI_DOMAIN_BITMAP_SIZE); static DEFINE_SPINLOCK(zpci_domain_lock); @@ -69,6 +70,15 @@ EXPORT_SYMBOL_GPL(zpci_aipb); struct airq_iv *zpci_aif_sbv; EXPORT_SYMBOL_GPL(zpci_aif_sbv); +void zpci_zdev_put(struct zpci_dev *zdev) +{ + if (!zdev) + return; + mutex_lock(&zpci_add_remove_lock); + kref_put_lock(&zdev->kref, zpci_release_device, &zpci_list_lock); + mutex_unlock(&zpci_add_remove_lock); +} + struct zpci_dev *get_zdev_by_fid(u32 fid) { struct zpci_dev *tmp, *zdev = NULL; @@ -831,6 +841,7 @@ int zpci_add_device(struct zpci_dev *zdev) { int rc; + mutex_lock(&zpci_add_remove_lock); zpci_dbg(1, "add fid:%x, fh:%x, c:%d\n", zdev->fid, zdev->fh, zdev->state); rc = zpci_init_iommu(zdev); if (rc) @@ -844,12 +855,14 @@ int zpci_add_device(struct zpci_dev *zdev) spin_lock(&zpci_list_lock); list_add_tail(&zdev->entry, &zpci_list); spin_unlock(&zpci_list_lock); + mutex_unlock(&zpci_add_remove_lock); return 0; error_destroy_iommu: zpci_destroy_iommu(zdev); error: zpci_dbg(0, "add fid:%x, rc:%d\n", zdev->fid, rc); + mutex_unlock(&zpci_add_remove_lock); return rc; } @@ -919,21 +932,20 @@ int zpci_deconfigure_device(struct zpci_dev *zdev) * @zdev: the zpci_dev that was reserved * * Handle the case that a given zPCI function was reserved by another system. - * After a call to this function the zpci_dev can not be found via - * get_zdev_by_fid() anymore but may still be accessible via existing - * references though it will not be functional anymore. */ void zpci_device_reserved(struct zpci_dev *zdev) { - /* - * Remove device from zpci_list as it is going away. This also - * makes sure we ignore subsequent zPCI events for this device. - */ - spin_lock(&zpci_list_lock); - list_del(&zdev->entry); - spin_unlock(&zpci_list_lock); + lockdep_assert_held(&zdev->state_lock); + /* We may declare the device reserved multiple times */ + if (zdev->state == ZPCI_FN_STATE_RESERVED) + return; zdev->state = ZPCI_FN_STATE_RESERVED; zpci_dbg(3, "rsv fid:%x\n", zdev->fid); + /* + * The underlying device is gone. Allow the zdev to be freed + * as soon as all other references are gone by accounting for + * the removal as a dropped reference. + */ zpci_zdev_put(zdev); } @@ -941,13 +953,14 @@ void zpci_release_device(struct kref *kref) { struct zpci_dev *zdev = container_of(kref, struct zpci_dev, kref); + lockdep_assert_held(&zpci_add_remove_lock); WARN_ON(zdev->state != ZPCI_FN_STATE_RESERVED); - - if (zdev->zbus->bus) - zpci_bus_remove_device(zdev, false); - - if (zdev_enabled(zdev)) - zpci_disable_device(zdev); + /* + * We already hold zpci_list_lock thanks to kref_put_lock(). + * This makes sure no new reference can be taken from the list. + */ + list_del(&zdev->entry); + spin_unlock(&zpci_list_lock); if (zdev->has_hp_slot) zpci_exit_slot(zdev); diff --git a/arch/s390/pci/pci_bus.h b/arch/s390/pci/pci_bus.h index af9f0ac79a1b..3febb3b297c0 100644 --- a/arch/s390/pci/pci_bus.h +++ b/arch/s390/pci/pci_bus.h @@ -17,11 +17,8 @@ int zpci_bus_scan_device(struct zpci_dev *zdev); void zpci_bus_remove_device(struct zpci_dev *zdev, bool set_error); void zpci_release_device(struct kref *kref); -static inline void zpci_zdev_put(struct zpci_dev *zdev) -{ - if (zdev) - kref_put(&zdev->kref, zpci_release_device); -} + +void zpci_zdev_put(struct zpci_dev *zdev); static inline void zpci_zdev_get(struct zpci_dev *zdev) { diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c index 7f7b732b3f3e..ef44feb1a9da 100644 --- a/arch/s390/pci/pci_event.c +++ b/arch/s390/pci/pci_event.c @@ -105,6 +105,10 @@ static pci_ers_result_t zpci_event_do_error_state_clear(struct pci_dev *pdev, struct zpci_dev *zdev = to_zpci(pdev); int rc; + /* The underlying device may have been disabled by the event */ + if (!zdev_enabled(zdev)) + return PCI_ERS_RESULT_NEED_RESET; + pr_info("%s: Unblocking device access for examination\n", pci_name(pdev)); rc = zpci_reset_load_store_blocked(zdev); if (rc) { @@ -260,6 +264,8 @@ static void __zpci_event_error(struct zpci_ccdf_err *ccdf) struct zpci_dev *zdev = get_zdev_by_fid(ccdf->fid); struct pci_dev *pdev = NULL; pci_ers_result_t ers_res; + u32 fh = 0; + int rc; zpci_dbg(3, "err fid:%x, fh:%x, pec:%x\n", ccdf->fid, ccdf->fh, ccdf->pec); @@ -268,6 +274,15 @@ static void __zpci_event_error(struct zpci_ccdf_err *ccdf) if (zdev) { mutex_lock(&zdev->state_lock); + rc = clp_refresh_fh(zdev->fid, &fh); + if (rc) + goto no_pdev; + if (!fh || ccdf->fh != fh) { + /* Ignore events with stale handles */ + zpci_dbg(3, "err fid:%x, fh:%x (stale %x)\n", + ccdf->fid, fh, ccdf->fh); + goto no_pdev; + } zpci_update_fh(zdev, ccdf->fh); if (zdev->zbus->bus) pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn); @@ -322,6 +337,22 @@ static void zpci_event_hard_deconfigured(struct zpci_dev *zdev, u32 fh) zdev->state = ZPCI_FN_STATE_STANDBY; } +static void zpci_event_reappear(struct zpci_dev *zdev) +{ + lockdep_assert_held(&zdev->state_lock); + /* + * The zdev is in the reserved state. This means that it was presumed to + * go away but there are still undropped references. Now, the platform + * announced its availability again. Bring back the lingering zdev + * to standby. This is safe because we hold a temporary reference + * now so that it won't go away. Account for the re-appearance of the + * underlying device by incrementing the reference count. + */ + zdev->state = ZPCI_FN_STATE_STANDBY; + zpci_zdev_get(zdev); + zpci_dbg(1, "rea fid:%x, fh:%x\n", zdev->fid, zdev->fh); +} + static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) { struct zpci_dev *zdev = get_zdev_by_fid(ccdf->fid); @@ -345,8 +376,10 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) break; } } else { + if (zdev->state == ZPCI_FN_STATE_RESERVED) + zpci_event_reappear(zdev); /* the configuration request may be stale */ - if (zdev->state != ZPCI_FN_STATE_STANDBY) + else if (zdev->state != ZPCI_FN_STATE_STANDBY) break; zdev->state = ZPCI_FN_STATE_CONFIGURED; } @@ -362,6 +395,8 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) break; } } else { + if (zdev->state == ZPCI_FN_STATE_RESERVED) + zpci_event_reappear(zdev); zpci_update_fh(zdev, ccdf->fh); } break; diff --git a/arch/s390/pci/pci_mmio.c b/arch/s390/pci/pci_mmio.c index 4779c3cb6cfa..0fa34c501296 100644 --- a/arch/s390/pci/pci_mmio.c +++ b/arch/s390/pci/pci_mmio.c @@ -228,7 +228,7 @@ static inline int __pcilg_mio_inuser( [ioaddr_len] "+&d" (ioaddr_len.pair), [cc] "+d" (cc), [val] "=d" (val), [dst] "+a" (dst), [cnt] "+d" (cnt), [tmp] "=d" (tmp), - [shift] "+d" (shift) + [shift] "+a" (shift) :: "cc", "memory"); /* did we write everything to the user space buffer? */ diff --git a/arch/sh/Makefile b/arch/sh/Makefile index cab2f9c011a8..7b420424b6d7 100644 --- a/arch/sh/Makefile +++ b/arch/sh/Makefile @@ -103,16 +103,16 @@ UTS_MACHINE := sh LDFLAGS_vmlinux += -e _stext ifdef CONFIG_CPU_LITTLE_ENDIAN -ld-bfd := elf32-sh-linux -LDFLAGS_vmlinux += --defsym jiffies=jiffies_64 --oformat $(ld-bfd) +ld_bfd := elf32-sh-linux +LDFLAGS_vmlinux += --defsym jiffies=jiffies_64 --oformat $(ld_bfd) KBUILD_LDFLAGS += -EL else -ld-bfd := elf32-shbig-linux -LDFLAGS_vmlinux += --defsym jiffies=jiffies_64+4 --oformat $(ld-bfd) +ld_bfd := elf32-shbig-linux +LDFLAGS_vmlinux += --defsym jiffies=jiffies_64+4 --oformat $(ld_bfd) KBUILD_LDFLAGS += -EB endif -export ld-bfd +export ld_bfd # Mach groups machdir-$(CONFIG_SOLUTION_ENGINE) += mach-se diff --git a/arch/sh/boot/compressed/Makefile b/arch/sh/boot/compressed/Makefile index 8bc319ff54bf..58df491778b2 100644 --- a/arch/sh/boot/compressed/Makefile +++ b/arch/sh/boot/compressed/Makefile @@ -27,7 +27,7 @@ endif ccflags-remove-$(CONFIG_MCOUNT) += -pg -LDFLAGS_vmlinux := --oformat $(ld-bfd) -Ttext $(IMAGE_OFFSET) -e startup \ +LDFLAGS_vmlinux := --oformat $(ld_bfd) -Ttext $(IMAGE_OFFSET) -e startup \ -T $(obj)/../../kernel/vmlinux.lds KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING @@ -51,7 +51,7 @@ $(obj)/vmlinux.bin.lzo: $(obj)/vmlinux.bin FORCE OBJCOPYFLAGS += -R .empty_zero_page -LDFLAGS_piggy.o := -r --format binary --oformat $(ld-bfd) -T +LDFLAGS_piggy.o := -r --format binary --oformat $(ld_bfd) -T $(obj)/piggy.o: $(obj)/vmlinux.scr $(obj)/vmlinux.bin.$(suffix_y) FORCE $(call if_changed,ld) diff --git a/arch/sh/boot/romimage/Makefile b/arch/sh/boot/romimage/Makefile index c7c8be58400c..17b03df0a8de 100644 --- a/arch/sh/boot/romimage/Makefile +++ b/arch/sh/boot/romimage/Makefile @@ -13,7 +13,7 @@ mmcif-obj-$(CONFIG_CPU_SUBTYPE_SH7724) := $(obj)/mmcif-sh7724.o load-$(CONFIG_ROMIMAGE_MMCIF) := $(mmcif-load-y) obj-$(CONFIG_ROMIMAGE_MMCIF) := $(mmcif-obj-y) -LDFLAGS_vmlinux := --oformat $(ld-bfd) -Ttext $(load-y) -e romstart \ +LDFLAGS_vmlinux := --oformat $(ld_bfd) -Ttext $(load-y) -e romstart \ -T $(obj)/../../kernel/vmlinux.lds $(obj)/vmlinux: $(obj)/head.o $(obj-y) $(obj)/piggy.o FORCE @@ -24,7 +24,7 @@ OBJCOPYFLAGS += -j .empty_zero_page $(obj)/zeropage.bin: vmlinux FORCE $(call if_changed,objcopy) -LDFLAGS_piggy.o := -r --format binary --oformat $(ld-bfd) -T +LDFLAGS_piggy.o := -r --format binary --oformat $(ld_bfd) -T $(obj)/piggy.o: $(obj)/vmlinux.scr $(obj)/zeropage.bin arch/sh/boot/zImage FORCE $(call if_changed,ld) diff --git a/arch/um/drivers/rtc_user.c b/arch/um/drivers/rtc_user.c index 7c3cec4c68cf..006a5a164ea9 100644 --- a/arch/um/drivers/rtc_user.c +++ b/arch/um/drivers/rtc_user.c @@ -28,7 +28,7 @@ int uml_rtc_start(bool timetravel) int err; if (timetravel) { - int err = os_pipe(uml_rtc_irq_fds, 1, 1); + err = os_pipe(uml_rtc_irq_fds, 1, 1); if (err) goto fail; } else { diff --git a/arch/um/drivers/ubd_user.c b/arch/um/drivers/ubd_user.c index b4f8b8e60564..592b899820d6 100644 --- a/arch/um/drivers/ubd_user.c +++ b/arch/um/drivers/ubd_user.c @@ -41,7 +41,7 @@ int start_io_thread(unsigned long sp, int *fd_out) *fd_out = fds[1]; err = os_set_fd_block(*fd_out, 0); - err = os_set_fd_block(kernel_fd, 0); + err |= os_set_fd_block(kernel_fd, 0); if (err) { printk("start_io_thread - failed to set nonblocking I/O.\n"); goto out_close; diff --git a/arch/um/drivers/vector_kern.c b/arch/um/drivers/vector_kern.c index 64c09db392c1..7a88b13d289f 100644 --- a/arch/um/drivers/vector_kern.c +++ b/arch/um/drivers/vector_kern.c @@ -1592,35 +1592,19 @@ static void vector_eth_configure( device->dev = dev; - *vp = ((struct vector_private) - { - .list = LIST_HEAD_INIT(vp->list), - .dev = dev, - .unit = n, - .options = get_transport_options(def), - .rx_irq = 0, - .tx_irq = 0, - .parsed = def, - .max_packet = get_mtu(def) + ETH_HEADER_OTHER, - /* TODO - we need to calculate headroom so that ip header - * is 16 byte aligned all the time - */ - .headroom = get_headroom(def), - .form_header = NULL, - .verify_header = NULL, - .header_rxbuffer = NULL, - .header_txbuffer = NULL, - .header_size = 0, - .rx_header_size = 0, - .rexmit_scheduled = false, - .opened = false, - .transport_data = NULL, - .in_write_poll = false, - .coalesce = 2, - .req_size = get_req_size(def), - .in_error = false, - .bpf = NULL - }); + INIT_LIST_HEAD(&vp->list); + vp->dev = dev; + vp->unit = n; + vp->options = get_transport_options(def); + vp->parsed = def; + vp->max_packet = get_mtu(def) + ETH_HEADER_OTHER; + /* + * TODO - we need to calculate headroom so that ip header + * is 16 byte aligned all the time + */ + vp->headroom = get_headroom(def); + vp->coalesce = 2; + vp->req_size = get_req_size(def); dev->features = dev->hw_features = (NETIF_F_SG | NETIF_F_FRAGLIST); INIT_WORK(&vp->reset_tx, vector_reset_tx); diff --git a/arch/um/include/asm/asm-prototypes.h b/arch/um/include/asm/asm-prototypes.h index 5898a26daa0d..408b31d59127 100644 --- a/arch/um/include/asm/asm-prototypes.h +++ b/arch/um/include/asm/asm-prototypes.h @@ -1 +1,6 @@ #include <asm-generic/asm-prototypes.h> +#include <asm/checksum.h> + +#ifdef CONFIG_UML_X86 +extern void cmpxchg8b_emu(void); +#endif diff --git a/arch/um/include/asm/thread_info.h b/arch/um/include/asm/thread_info.h index c7b4b49826a2..40d823f36c09 100644 --- a/arch/um/include/asm/thread_info.h +++ b/arch/um/include/asm/thread_info.h @@ -68,7 +68,11 @@ static inline struct thread_info *current_thread_info(void) #define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) #define _TIF_MEMDIE (1 << TIF_MEMDIE) #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) +#define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) #define _TIF_SECCOMP (1 << TIF_SECCOMP) #define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP) +#define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL | \ + _TIF_NOTIFY_RESUME) + #endif diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index 9c6cf03ed02b..eaeeedd62930 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -81,14 +81,18 @@ struct task_struct *__switch_to(struct task_struct *from, struct task_struct *to void interrupt_end(void) { struct pt_regs *regs = ¤t->thread.regs; - - if (need_resched()) - schedule(); - if (test_thread_flag(TIF_SIGPENDING) || - test_thread_flag(TIF_NOTIFY_SIGNAL)) - do_signal(regs); - if (test_thread_flag(TIF_NOTIFY_RESUME)) - resume_user_mode_work(regs); + unsigned long thread_flags; + + thread_flags = read_thread_flags(); + while (thread_flags & _TIF_WORK_MASK) { + if (thread_flags & _TIF_NEED_RESCHED) + schedule(); + if (thread_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) + do_signal(regs); + if (thread_flags & _TIF_NOTIFY_RESUME) + resume_user_mode_work(regs); + thread_flags = read_thread_flags(); + } } int get_current_pid(void) diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c index 97c8df9c4401..9077bdb26cc3 100644 --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -18,6 +18,122 @@ #include <skas.h> /* + * NOTE: UML does not have exception tables. As such, this is almost a copy + * of the code in mm/memory.c, only adjusting the logic to simply check whether + * we are coming from the kernel instead of doing an additional lookup in the + * exception table. + * We can do this simplification because we never get here if the exception was + * fixable. + */ +static inline bool get_mmap_lock_carefully(struct mm_struct *mm, bool is_user) +{ + if (likely(mmap_read_trylock(mm))) + return true; + + if (!is_user) + return false; + + return !mmap_read_lock_killable(mm); +} + +static inline bool mmap_upgrade_trylock(struct mm_struct *mm) +{ + /* + * We don't have this operation yet. + * + * It should be easy enough to do: it's basically a + * atomic_long_try_cmpxchg_acquire() + * from RWSEM_READER_BIAS -> RWSEM_WRITER_LOCKED, but + * it also needs the proper lockdep magic etc. + */ + return false; +} + +static inline bool upgrade_mmap_lock_carefully(struct mm_struct *mm, bool is_user) +{ + mmap_read_unlock(mm); + if (!is_user) + return false; + + return !mmap_write_lock_killable(mm); +} + +/* + * Helper for page fault handling. + * + * This is kind of equivalend to "mmap_read_lock()" followed + * by "find_extend_vma()", except it's a lot more careful about + * the locking (and will drop the lock on failure). + * + * For example, if we have a kernel bug that causes a page + * fault, we don't want to just use mmap_read_lock() to get + * the mm lock, because that would deadlock if the bug were + * to happen while we're holding the mm lock for writing. + * + * So this checks the exception tables on kernel faults in + * order to only do this all for instructions that are actually + * expected to fault. + * + * We can also actually take the mm lock for writing if we + * need to extend the vma, which helps the VM layer a lot. + */ +static struct vm_area_struct * +um_lock_mm_and_find_vma(struct mm_struct *mm, + unsigned long addr, bool is_user) +{ + struct vm_area_struct *vma; + + if (!get_mmap_lock_carefully(mm, is_user)) + return NULL; + + vma = find_vma(mm, addr); + if (likely(vma && (vma->vm_start <= addr))) + return vma; + + /* + * Well, dang. We might still be successful, but only + * if we can extend a vma to do so. + */ + if (!vma || !(vma->vm_flags & VM_GROWSDOWN)) { + mmap_read_unlock(mm); + return NULL; + } + + /* + * We can try to upgrade the mmap lock atomically, + * in which case we can continue to use the vma + * we already looked up. + * + * Otherwise we'll have to drop the mmap lock and + * re-take it, and also look up the vma again, + * re-checking it. + */ + if (!mmap_upgrade_trylock(mm)) { + if (!upgrade_mmap_lock_carefully(mm, is_user)) + return NULL; + + vma = find_vma(mm, addr); + if (!vma) + goto fail; + if (vma->vm_start <= addr) + goto success; + if (!(vma->vm_flags & VM_GROWSDOWN)) + goto fail; + } + + if (expand_stack_locked(vma, addr)) + goto fail; + +success: + mmap_write_downgrade(mm); + return vma; + +fail: + mmap_write_unlock(mm); + return NULL; +} + +/* * Note this is constrained to return 0, -EFAULT, -EACCES, -ENOMEM by * segv(). */ @@ -43,21 +159,10 @@ int handle_page_fault(unsigned long address, unsigned long ip, if (is_user) flags |= FAULT_FLAG_USER; retry: - mmap_read_lock(mm); - vma = find_vma(mm, address); - if (!vma) - goto out; - if (vma->vm_start <= address) - goto good_area; - if (!(vma->vm_flags & VM_GROWSDOWN)) - goto out; - if (is_user && !ARCH_IS_STACKGROW(address)) - goto out; - vma = expand_stack(mm, address); + vma = um_lock_mm_and_find_vma(mm, address, is_user); if (!vma) goto out_nosemaphore; -good_area: *code_out = SEGV_ACCERR; if (is_write) { if (!(vma->vm_flags & VM_WRITE)) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 15425c9bdc2b..2df0ae2a5e5d 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -137,7 +137,7 @@ config X86 select ARCH_WANTS_DYNAMIC_TASK_STRUCT select ARCH_WANTS_NO_INSTR select ARCH_WANT_GENERAL_HUGETLB - select ARCH_WANT_HUGE_PMD_SHARE + select ARCH_WANT_HUGE_PMD_SHARE if X86_64 select ARCH_WANT_LD_ORPHAN_WARN select ARCH_WANT_OPTIMIZE_DAX_VMEMMAP if X86_64 select ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP if X86_64 @@ -2760,6 +2760,15 @@ config MITIGATION_ITS disabled, mitigation cannot be enabled via cmdline. See <file:Documentation/admin-guide/hw-vuln/indirect-target-selection.rst> +config MITIGATION_TSA + bool "Mitigate Transient Scheduler Attacks" + depends on CPU_SUP_AMD + default y + help + Enable mitigation for Transient Scheduler Attacks. TSA is a hardware + security vulnerability on AMD CPUs which can lead to forwarding of + invalid info to subsequent instructions and thus can affect their + timing and thereby cause a leakage. endif config ARCH_HAS_ADD_PAGES diff --git a/arch/x86/boot/cpuflags.c b/arch/x86/boot/cpuflags.c index d75237ba7ce9..5660d3229d29 100644 --- a/arch/x86/boot/cpuflags.c +++ b/arch/x86/boot/cpuflags.c @@ -115,5 +115,18 @@ void get_cpuflags(void) cpuid(0x80000001, &ignored, &ignored, &cpu.flags[6], &cpu.flags[1]); } + + if (max_amd_level >= 0x8000001f) { + u32 ebx; + + /* + * The X86_FEATURE_COHERENCY_SFW_NO feature bit is in + * the virtualization flags entry (word 8) and set by + * scattered.c, so the bit needs to be explicitly set. + */ + cpuid(0x8000001f, &ignored, &ebx, &ignored, &ignored); + if (ebx & BIT(31)) + set_bit(X86_FEATURE_COHERENCY_SFW_NO, cpu.flags); + } } } diff --git a/arch/x86/coco/sev/shared.c b/arch/x86/coco/sev/shared.c index 71de53194089..f5936da235c7 100644 --- a/arch/x86/coco/sev/shared.c +++ b/arch/x86/coco/sev/shared.c @@ -1243,6 +1243,24 @@ static void svsm_pval_terminate(struct svsm_pvalidate_call *pc, int ret, u64 svs __pval_terminate(pfn, action, page_size, ret, svsm_ret); } +static inline void sev_evict_cache(void *va, int npages) +{ + volatile u8 val __always_unused; + u8 *bytes = va; + int page_idx; + + /* + * For SEV guests, a read from the first/last cache-lines of a 4K page + * using the guest key is sufficient to cause a flush of all cache-lines + * associated with that 4K page without incurring all the overhead of a + * full CLFLUSH sequence. + */ + for (page_idx = 0; page_idx < npages; page_idx++) { + val = bytes[page_idx * PAGE_SIZE]; + val = bytes[page_idx * PAGE_SIZE + PAGE_SIZE - 1]; + } +} + static void svsm_pval_4k_page(unsigned long paddr, bool validate) { struct svsm_pvalidate_call *pc; @@ -1295,6 +1313,13 @@ static void pvalidate_4k_page(unsigned long vaddr, unsigned long paddr, bool val if (ret) __pval_terminate(PHYS_PFN(paddr), validate, RMP_PG_SIZE_4K, ret, 0); } + + /* + * If validating memory (making it private) and affected by the + * cache-coherency vulnerability, perform the cache eviction mitigation. + */ + if (validate && !has_cpuflag(X86_FEATURE_COHERENCY_SFW_NO)) + sev_evict_cache((void *)vaddr, 1); } static void pval_pages(struct snp_psc_desc *desc) @@ -1479,10 +1504,31 @@ static void svsm_pval_pages(struct snp_psc_desc *desc) static void pvalidate_pages(struct snp_psc_desc *desc) { + struct psc_entry *e; + unsigned int i; + if (snp_vmpl) svsm_pval_pages(desc); else pval_pages(desc); + + /* + * If not affected by the cache-coherency vulnerability there is no need + * to perform the cache eviction mitigation. + */ + if (cpu_feature_enabled(X86_FEATURE_COHERENCY_SFW_NO)) + return; + + for (i = 0; i <= desc->hdr.end_entry; i++) { + e = &desc->entries[i]; + + /* + * If validating memory (making it private) perform the cache + * eviction mitigation. + */ + if (e->operation == SNP_PAGE_STATE_PRIVATE) + sev_evict_cache(pfn_to_kaddr(e->gfn), e->pagesize ? 512 : 1); + } } static int vmgexit_psc(struct ghcb *ghcb, struct snp_psc_desc *desc) diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S index 5b96249734ad..b0d5ab951231 100644 --- a/arch/x86/entry/entry.S +++ b/arch/x86/entry/entry.S @@ -33,20 +33,20 @@ EXPORT_SYMBOL_GPL(entry_ibpb); /* * Define the VERW operand that is disguised as entry code so that - * it can be referenced with KPTI enabled. This ensure VERW can be + * it can be referenced with KPTI enabled. This ensures VERW can be * used late in exit-to-user path after page tables are switched. */ .pushsection .entry.text, "ax" .align L1_CACHE_BYTES, 0xcc -SYM_CODE_START_NOALIGN(mds_verw_sel) +SYM_CODE_START_NOALIGN(x86_verw_sel) UNWIND_HINT_UNDEFINED ANNOTATE_NOENDBR .word __KERNEL_DS .align L1_CACHE_BYTES, 0xcc -SYM_CODE_END(mds_verw_sel); +SYM_CODE_END(x86_verw_sel); /* For KVM */ -EXPORT_SYMBOL_GPL(mds_verw_sel); +EXPORT_SYMBOL_GPL(x86_verw_sel); .popsection diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 95eada2994e1..239f612816e6 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -730,3 +730,36 @@ bool hv_is_hyperv_initialized(void) return hypercall_msr.enable; } EXPORT_SYMBOL_GPL(hv_is_hyperv_initialized); + +int hv_apicid_to_vp_index(u32 apic_id) +{ + u64 control; + u64 status; + unsigned long irq_flags; + struct hv_get_vp_from_apic_id_in *input; + u32 *output, ret; + + local_irq_save(irq_flags); + + input = *this_cpu_ptr(hyperv_pcpu_input_arg); + memset(input, 0, sizeof(*input)); + input->partition_id = HV_PARTITION_ID_SELF; + input->apic_ids[0] = apic_id; + + output = *this_cpu_ptr(hyperv_pcpu_output_arg); + + control = HV_HYPERCALL_REP_COMP_1 | HVCALL_GET_VP_ID_FROM_APIC_ID; + status = hv_do_hypercall(control, input, output); + ret = output[0]; + + local_irq_restore(irq_flags); + + if (!hv_result_success(status)) { + pr_err("failed to get vp index from apic id %d, status %#llx\n", + apic_id, status); + return -EINVAL; + } + + return ret; +} +EXPORT_SYMBOL_GPL(hv_apicid_to_vp_index); diff --git a/arch/x86/hyperv/hv_vtl.c b/arch/x86/hyperv/hv_vtl.c index d04ccd4b3b4a..2510e91b29b0 100644 --- a/arch/x86/hyperv/hv_vtl.c +++ b/arch/x86/hyperv/hv_vtl.c @@ -175,41 +175,9 @@ free_lock: return ret; } -static int hv_vtl_apicid_to_vp_id(u32 apic_id) -{ - u64 control; - u64 status; - unsigned long irq_flags; - struct hv_get_vp_from_apic_id_in *input; - u32 *output, ret; - - local_irq_save(irq_flags); - - input = *this_cpu_ptr(hyperv_pcpu_input_arg); - memset(input, 0, sizeof(*input)); - input->partition_id = HV_PARTITION_ID_SELF; - input->apic_ids[0] = apic_id; - - output = (u32 *)input; - - control = HV_HYPERCALL_REP_COMP_1 | HVCALL_GET_VP_ID_FROM_APIC_ID; - status = hv_do_hypercall(control, input, output); - ret = output[0]; - - local_irq_restore(irq_flags); - - if (!hv_result_success(status)) { - pr_err("failed to get vp id from apic id %d, status %#llx\n", - apic_id, status); - return -EINVAL; - } - - return ret; -} - static int hv_vtl_wakeup_secondary_cpu(u32 apicid, unsigned long start_eip) { - int vp_id, cpu; + int vp_index, cpu; /* Find the logical CPU for the APIC ID */ for_each_present_cpu(cpu) { @@ -220,18 +188,18 @@ static int hv_vtl_wakeup_secondary_cpu(u32 apicid, unsigned long start_eip) return -EINVAL; pr_debug("Bringing up CPU with APIC ID %d in VTL2...\n", apicid); - vp_id = hv_vtl_apicid_to_vp_id(apicid); + vp_index = hv_apicid_to_vp_index(apicid); - if (vp_id < 0) { + if (vp_index < 0) { pr_err("Couldn't find CPU with APIC ID %d\n", apicid); return -EINVAL; } - if (vp_id > ms_hyperv.max_vp_index) { - pr_err("Invalid CPU id %d for APIC ID %d\n", vp_id, apicid); + if (vp_index > ms_hyperv.max_vp_index) { + pr_err("Invalid CPU id %d for APIC ID %d\n", vp_index, apicid); return -EINVAL; } - return hv_vtl_bringup_vcpu(vp_id, cpu, start_eip); + return hv_vtl_bringup_vcpu(vp_index, cpu, start_eip); } int __init hv_vtl_early_init(void) diff --git a/arch/x86/hyperv/irqdomain.c b/arch/x86/hyperv/irqdomain.c index 3215a4a07408..939b7081c5ab 100644 --- a/arch/x86/hyperv/irqdomain.c +++ b/arch/x86/hyperv/irqdomain.c @@ -192,7 +192,6 @@ static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) struct pci_dev *dev; struct hv_interrupt_entry out_entry, *stored_entry; struct irq_cfg *cfg = irqd_cfg(data); - const cpumask_t *affinity; int cpu; u64 status; @@ -204,8 +203,7 @@ static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) return; } - affinity = irq_data_get_effective_affinity_mask(data); - cpu = cpumask_first_and(affinity, cpu_online_mask); + cpu = cpumask_first(irq_data_get_effective_affinity_mask(data)); if (data->chip_data) { /* diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c index 4065f5ef3ae0..af87f440bc2a 100644 --- a/arch/x86/hyperv/ivm.c +++ b/arch/x86/hyperv/ivm.c @@ -10,6 +10,7 @@ #include <linux/hyperv.h> #include <linux/types.h> #include <linux/slab.h> +#include <linux/cpu.h> #include <asm/svm.h> #include <asm/sev.h> #include <asm/io.h> @@ -289,7 +290,7 @@ static void snp_cleanup_vmsa(struct sev_es_save_area *vmsa) free_page((unsigned long)vmsa); } -int hv_snp_boot_ap(u32 cpu, unsigned long start_ip) +int hv_snp_boot_ap(u32 apic_id, unsigned long start_ip) { struct sev_es_save_area *vmsa = (struct sev_es_save_area *) __get_free_page(GFP_KERNEL | __GFP_ZERO); @@ -298,10 +299,27 @@ int hv_snp_boot_ap(u32 cpu, unsigned long start_ip) u64 ret, retry = 5; struct hv_enable_vp_vtl *start_vp_input; unsigned long flags; + int cpu, vp_index; if (!vmsa) return -ENOMEM; + /* Find the Hyper-V VP index which might be not the same as APIC ID */ + vp_index = hv_apicid_to_vp_index(apic_id); + if (vp_index < 0 || vp_index > ms_hyperv.max_vp_index) + return -EINVAL; + + /* + * Find the Linux CPU number for addressing the per-CPU data, and it + * might not be the same as APIC ID. + */ + for_each_present_cpu(cpu) { + if (arch_match_cpu_phys_id(cpu, apic_id)) + break; + } + if (cpu >= nr_cpu_ids) + return -EINVAL; + native_store_gdt(&gdtr); vmsa->gdtr.base = gdtr.address; @@ -349,7 +367,7 @@ int hv_snp_boot_ap(u32 cpu, unsigned long start_ip) start_vp_input = (struct hv_enable_vp_vtl *)ap_start_input_arg; memset(start_vp_input, 0, sizeof(*start_vp_input)); start_vp_input->partition_id = -1; - start_vp_input->vp_index = cpu; + start_vp_input->vp_index = vp_index; start_vp_input->target_vtl.target_vtl = ms_hyperv.vtl; *(u64 *)&start_vp_input->vp_context = __pa(vmsa) | 1; diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h index aa30fd8cad7f..b6099456477c 100644 --- a/arch/x86/include/asm/cpu.h +++ b/arch/x86/include/asm/cpu.h @@ -69,4 +69,16 @@ int intel_microcode_sanity_check(void *mc, bool print_err, int hdr_type); extern struct cpumask cpus_stop_mask; +union zen_patch_rev { + struct { + __u32 rev : 8, + stepping : 4, + model : 4, + __reserved : 4, + ext_model : 4, + ext_fam : 8; + }; + __u32 ucode_rev; +}; + #endif /* _ASM_X86_CPU_H */ diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 308e7d97135c..98e72c1391f2 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -227,6 +227,7 @@ #define X86_FEATURE_FLEXPRIORITY ( 8*32+ 1) /* "flexpriority" Intel FlexPriority */ #define X86_FEATURE_EPT ( 8*32+ 2) /* "ept" Intel Extended Page Table */ #define X86_FEATURE_VPID ( 8*32+ 3) /* "vpid" Intel Virtual Processor ID */ +#define X86_FEATURE_COHERENCY_SFW_NO ( 8*32+ 4) /* SNP cache coherency software work around not needed */ #define X86_FEATURE_VMMCALL ( 8*32+15) /* "vmmcall" Prefer VMMCALL to VMCALL */ #define X86_FEATURE_XENPV ( 8*32+16) /* Xen paravirtual guest */ @@ -455,6 +456,7 @@ #define X86_FEATURE_NO_NESTED_DATA_BP (20*32+ 0) /* No Nested Data Breakpoints */ #define X86_FEATURE_WRMSR_XX_BASE_NS (20*32+ 1) /* WRMSR to {FS,GS,KERNEL_GS}_BASE is non-serializing */ #define X86_FEATURE_LFENCE_RDTSC (20*32+ 2) /* LFENCE always serializing / synchronizes RDTSC */ +#define X86_FEATURE_VERW_CLEAR (20*32+ 5) /* The memory form of VERW mitigates TSA */ #define X86_FEATURE_NULL_SEL_CLR_BASE (20*32+ 6) /* Null Selector Clears Base */ #define X86_FEATURE_AUTOIBRS (20*32+ 8) /* Automatic IBRS */ #define X86_FEATURE_NO_SMM_CTL_MSR (20*32+ 9) /* SMM_CTL MSR is not present */ @@ -477,6 +479,10 @@ #define X86_FEATURE_FAST_CPPC (21*32 + 5) /* AMD Fast CPPC */ #define X86_FEATURE_INDIRECT_THUNK_ITS (21*32 + 6) /* Use thunk for indirect branches in lower half of cacheline */ +#define X86_FEATURE_TSA_SQ_NO (21*32+11) /* AMD CPU not vulnerable to TSA-SQ */ +#define X86_FEATURE_TSA_L1_NO (21*32+12) /* AMD CPU not vulnerable to TSA-L1 */ +#define X86_FEATURE_CLEAR_CPU_BUF_VM (21*32+13) /* Clear CPU buffers using VERW before VMRUN */ + /* * BUG word(s) */ @@ -529,4 +535,5 @@ #define X86_BUG_IBPB_NO_RET X86_BUG(1*32 + 4) /* "ibpb_no_ret" IBPB omits return target predictions */ #define X86_BUG_ITS X86_BUG(1*32 + 5) /* "its" CPU is affected by Indirect Target Selection */ #define X86_BUG_ITS_NATIVE_ONLY X86_BUG(1*32 + 6) /* "its_native_only" CPU is affected by ITS, VMX is not affected */ +#define X86_BUG_TSA X86_BUG( 1*32+ 9) /* "tsa" CPU is affected by Transient Scheduler Attacks */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h index fdbbbfec745a..820b4aeabd0c 100644 --- a/arch/x86/include/asm/debugreg.h +++ b/arch/x86/include/asm/debugreg.h @@ -9,6 +9,14 @@ #include <asm/cpufeature.h> #include <asm/msr.h> +/* + * Define bits that are always set to 1 in DR7, only bit 10 is + * architecturally reserved to '1'. + * + * This is also the init/reset value for DR7. + */ +#define DR7_FIXED_1 0x00000400 + DECLARE_PER_CPU(unsigned long, cpu_dr7); #ifndef CONFIG_PARAVIRT_XXL @@ -100,8 +108,8 @@ static __always_inline void native_set_debugreg(int regno, unsigned long value) static inline void hw_breakpoint_disable(void) { - /* Zero the control register for HW Breakpoint */ - set_debugreg(0UL, 7); + /* Reset the control register for HW Breakpoint */ + set_debugreg(DR7_FIXED_1, 7); /* Zero-out the individual HW breakpoint address registers */ set_debugreg(0UL, 0); @@ -125,9 +133,12 @@ static __always_inline unsigned long local_db_save(void) return 0; get_debugreg(dr7, 7); - dr7 &= ~0x400; /* architecturally set bit */ + + /* Architecturally set bit */ + dr7 &= ~DR7_FIXED_1; if (dr7) - set_debugreg(0, 7); + set_debugreg(DR7_FIXED_1, 7); + /* * Ensure the compiler doesn't lower the above statements into * the critical section; disabling breakpoints late would not diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h index edebf1020e04..6bb3d9a86abe 100644 --- a/arch/x86/include/asm/hw_irq.h +++ b/arch/x86/include/asm/hw_irq.h @@ -92,8 +92,6 @@ struct irq_cfg { extern struct irq_cfg *irq_cfg(unsigned int irq); extern struct irq_cfg *irqd_cfg(struct irq_data *irq_data); -extern void lock_vector_lock(void); -extern void unlock_vector_lock(void); #ifdef CONFIG_SMP extern void vector_schedule_cleanup(struct irq_cfg *); extern void irq_complete_move(struct irq_cfg *cfg); @@ -101,12 +99,16 @@ extern void irq_complete_move(struct irq_cfg *cfg); static inline void vector_schedule_cleanup(struct irq_cfg *c) { } static inline void irq_complete_move(struct irq_cfg *c) { } #endif - extern void apic_ack_edge(struct irq_data *data); -#else /* CONFIG_IRQ_DOMAIN_HIERARCHY */ +#endif /* CONFIG_IRQ_DOMAIN_HIERARCHY */ + +#ifdef CONFIG_X86_LOCAL_APIC +extern void lock_vector_lock(void); +extern void unlock_vector_lock(void); +#else static inline void lock_vector_lock(void) {} static inline void unlock_vector_lock(void) {} -#endif /* CONFIG_IRQ_DOMAIN_HIERARCHY */ +#endif /* Statistics */ extern atomic_t irq_err_count; diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h index 1c2db11a2c3c..2b75fe80fcb2 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -44,13 +44,13 @@ static __always_inline void native_irq_enable(void) static __always_inline void native_safe_halt(void) { - mds_idle_clear_cpu_buffers(); + x86_idle_clear_cpu_buffers(); asm volatile("sti; hlt": : :"memory"); } static __always_inline void native_halt(void) { - mds_idle_clear_cpu_buffers(); + x86_idle_clear_cpu_buffers(); asm volatile("hlt": : :"memory"); } diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index cfb22f8c451a..861d080ed4c6 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -47,7 +47,6 @@ KVM_X86_OP(set_idt) KVM_X86_OP(get_gdt) KVM_X86_OP(set_gdt) KVM_X86_OP(sync_dirty_debug_regs) -KVM_X86_OP(set_dr6) KVM_X86_OP(set_dr7) KVM_X86_OP(cache_reg) KVM_X86_OP(get_rflags) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index e4dd840e0bec..d27df86aa62c 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -31,6 +31,7 @@ #include <asm/apic.h> #include <asm/pvclock-abi.h> +#include <asm/debugreg.h> #include <asm/desc.h> #include <asm/mtrr.h> #include <asm/msr-index.h> @@ -246,7 +247,6 @@ enum x86_intercept_stage; #define DR7_BP_EN_MASK 0x000000ff #define DR7_GE (1 << 9) #define DR7_GD (1 << 13) -#define DR7_FIXED_1 0x00000400 #define DR7_VOLATILE 0xffff2bff #define KVM_GUESTDBG_VALID_MASK \ @@ -1627,6 +1627,12 @@ static inline u16 kvm_lapic_irq_dest_mode(bool dest_mode_logical) return dest_mode_logical ? APIC_DEST_LOGICAL : APIC_DEST_PHYSICAL; } +enum kvm_x86_run_flags { + KVM_RUN_FORCE_IMMEDIATE_EXIT = BIT(0), + KVM_RUN_LOAD_GUEST_DR6 = BIT(1), + KVM_RUN_LOAD_DEBUGCTL = BIT(2), +}; + struct kvm_x86_ops { const char *name; @@ -1654,6 +1660,12 @@ struct kvm_x86_ops { void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu); void (*vcpu_put)(struct kvm_vcpu *vcpu); + /* + * Mask of DEBUGCTL bits that are owned by the host, i.e. that need to + * match the host's value even while the guest is active. + */ + const u64 HOST_OWNED_DEBUGCTL; + void (*update_exception_bitmap)(struct kvm_vcpu *vcpu); int (*get_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr); int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr); @@ -1675,7 +1687,6 @@ struct kvm_x86_ops { void (*get_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void (*set_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void (*sync_dirty_debug_regs)(struct kvm_vcpu *vcpu); - void (*set_dr6)(struct kvm_vcpu *vcpu, unsigned long value); void (*set_dr7)(struct kvm_vcpu *vcpu, unsigned long value); void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg); unsigned long (*get_rflags)(struct kvm_vcpu *vcpu); @@ -1706,7 +1717,7 @@ struct kvm_x86_ops { int (*vcpu_pre_run)(struct kvm_vcpu *vcpu); enum exit_fastpath_completion (*vcpu_run)(struct kvm_vcpu *vcpu, - bool force_immediate_exit); + u64 run_flags); int (*handle_exit)(struct kvm_vcpu *vcpu, enum exit_fastpath_completion exit_fastpath); int (*skip_emulated_instruction)(struct kvm_vcpu *vcpu); diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 5f0bc6a6d025..a42439c2ed24 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -275,11 +275,11 @@ int hv_unmap_ioapic_interrupt(int ioapic_id, struct hv_interrupt_entry *entry); #ifdef CONFIG_AMD_MEM_ENCRYPT bool hv_ghcb_negotiate_protocol(void); void __noreturn hv_ghcb_terminate(unsigned int set, unsigned int reason); -int hv_snp_boot_ap(u32 cpu, unsigned long start_ip); +int hv_snp_boot_ap(u32 apic_id, unsigned long start_ip); #else static inline bool hv_ghcb_negotiate_protocol(void) { return false; } static inline void hv_ghcb_terminate(unsigned int set, unsigned int reason) {} -static inline int hv_snp_boot_ap(u32 cpu, unsigned long start_ip) { return 0; } +static inline int hv_snp_boot_ap(u32 apic_id, unsigned long start_ip) { return 0; } #endif #if defined(CONFIG_AMD_MEM_ENCRYPT) || defined(CONFIG_INTEL_TDX_GUEST) @@ -313,6 +313,7 @@ static __always_inline u64 hv_raw_get_msr(unsigned int reg) { return __rdmsr(reg); } +int hv_apicid_to_vp_index(u32 apic_id); #else /* CONFIG_HYPERV */ static inline void hyperv_init(void) {} @@ -334,6 +335,7 @@ static inline void hv_set_msr(unsigned int reg, u64 value) { } static inline u64 hv_get_msr(unsigned int reg) { return 0; } static inline void hv_set_non_nested_msr(unsigned int reg, u64 value) { } static inline u64 hv_get_non_nested_msr(unsigned int reg) { return 0; } +static inline int hv_apicid_to_vp_index(u32 apic_id) { return -EINVAL; } #endif /* CONFIG_HYPERV */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index ac25f9eb5912..2b6e3127ef4e 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -417,6 +417,7 @@ #define DEBUGCTLMSR_FREEZE_PERFMON_ON_PMI (1UL << 12) #define DEBUGCTLMSR_FREEZE_IN_SMM_BIT 14 #define DEBUGCTLMSR_FREEZE_IN_SMM (1UL << DEBUGCTLMSR_FREEZE_IN_SMM_BIT) +#define DEBUGCTLMSR_RTM_DEBUG BIT(15) #define MSR_PEBS_FRONTEND 0x000003f7 @@ -621,6 +622,7 @@ #define MSR_AMD64_OSVW_STATUS 0xc0010141 #define MSR_AMD_PPIN_CTL 0xc00102f0 #define MSR_AMD_PPIN 0xc00102f1 +#define MSR_AMD64_CPUID_FN_7 0xc0011002 #define MSR_AMD64_CPUID_FN_1 0xc0011004 #define MSR_AMD64_LS_CFG 0xc0011020 #define MSR_AMD64_DC_CFG 0xc0011022 diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h index 3e4e85f71a6a..7f9a97c572fe 100644 --- a/arch/x86/include/asm/mwait.h +++ b/arch/x86/include/asm/mwait.h @@ -44,8 +44,6 @@ static __always_inline void __monitorx(const void *eax, unsigned long ecx, static __always_inline void __mwait(unsigned long eax, unsigned long ecx) { - mds_idle_clear_cpu_buffers(); - /* "mwait %eax, %ecx;" */ asm volatile(".byte 0x0f, 0x01, 0xc9;" :: "a" (eax), "c" (ecx)); @@ -80,7 +78,7 @@ static __always_inline void __mwait(unsigned long eax, unsigned long ecx) static __always_inline void __mwaitx(unsigned long eax, unsigned long ebx, unsigned long ecx) { - /* No MDS buffer clear as this is AMD/HYGON only */ + /* No need for TSA buffer clearing on AMD */ /* "mwaitx %eax, %ebx, %ecx;" */ asm volatile(".byte 0x0f, 0x01, 0xfb;" @@ -98,7 +96,7 @@ static __always_inline void __mwaitx(unsigned long eax, unsigned long ebx, */ static __always_inline void __sti_mwait(unsigned long eax, unsigned long ecx) { - mds_idle_clear_cpu_buffers(); + /* "mwait %eax, %ecx;" */ asm volatile("sti; .byte 0x0f, 0x01, 0xc9;" :: "a" (eax), "c" (ecx)); @@ -116,21 +114,29 @@ static __always_inline void __sti_mwait(unsigned long eax, unsigned long ecx) */ static __always_inline void mwait_idle_with_hints(unsigned long eax, unsigned long ecx) { + if (need_resched()) + return; + + x86_idle_clear_cpu_buffers(); + if (static_cpu_has_bug(X86_BUG_MONITOR) || !current_set_polling_and_test()) { const void *addr = ¤t_thread_info()->flags; alternative_input("", "clflush (%[addr])", X86_BUG_CLFLUSH_MONITOR, [addr] "a" (addr)); __monitor(addr, 0, 0); - if (!need_resched()) { - if (ecx & 1) { - __mwait(eax, ecx); - } else { - __sti_mwait(eax, ecx); - raw_local_irq_disable(); - } + if (need_resched()) + goto out; + + if (ecx & 1) { + __mwait(eax, ecx); + } else { + __sti_mwait(eax, ecx); + raw_local_irq_disable(); } } + +out: current_clr_polling(); } diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index f7bb0016d7d9..331f6a05535d 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -315,25 +315,31 @@ .endm /* - * Macro to execute VERW instruction that mitigate transient data sampling - * attacks such as MDS. On affected systems a microcode update overloaded VERW - * instruction to also clear the CPU buffers. VERW clobbers CFLAGS.ZF. - * + * Macro to execute VERW insns that mitigate transient data sampling + * attacks such as MDS or TSA. On affected systems a microcode update + * overloaded VERW insns to also clear the CPU buffers. VERW clobbers + * CFLAGS.ZF. * Note: Only the memory operand variant of VERW clears the CPU buffers. */ -.macro CLEAR_CPU_BUFFERS +.macro __CLEAR_CPU_BUFFERS feature #ifdef CONFIG_X86_64 - ALTERNATIVE "", "verw mds_verw_sel(%rip)", X86_FEATURE_CLEAR_CPU_BUF + ALTERNATIVE "", "verw x86_verw_sel(%rip)", \feature #else /* * In 32bit mode, the memory operand must be a %cs reference. The data * segments may not be usable (vm86 mode), and the stack segment may not * be flat (ESPFIX32). */ - ALTERNATIVE "", "verw %cs:mds_verw_sel", X86_FEATURE_CLEAR_CPU_BUF + ALTERNATIVE "", "verw %cs:x86_verw_sel", \feature #endif .endm +#define CLEAR_CPU_BUFFERS \ + __CLEAR_CPU_BUFFERS X86_FEATURE_CLEAR_CPU_BUF + +#define VM_CLEAR_CPU_BUFFERS \ + __CLEAR_CPU_BUFFERS X86_FEATURE_CLEAR_CPU_BUF_VM + #ifdef CONFIG_X86_64 .macro CLEAR_BRANCH_HISTORY ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP @@ -582,24 +588,24 @@ DECLARE_STATIC_KEY_FALSE(switch_to_cond_stibp); DECLARE_STATIC_KEY_FALSE(switch_mm_cond_ibpb); DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb); -DECLARE_STATIC_KEY_FALSE(mds_idle_clear); +DECLARE_STATIC_KEY_FALSE(cpu_buf_idle_clear); DECLARE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush); DECLARE_STATIC_KEY_FALSE(mmio_stale_data_clear); -extern u16 mds_verw_sel; +extern u16 x86_verw_sel; #include <asm/segment.h> /** - * mds_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability + * x86_clear_cpu_buffers - Buffer clearing support for different x86 CPU vulns * * This uses the otherwise unused and obsolete VERW instruction in * combination with microcode which triggers a CPU buffer flush when the * instruction is executed. */ -static __always_inline void mds_clear_cpu_buffers(void) +static __always_inline void x86_clear_cpu_buffers(void) { static const u16 ds = __KERNEL_DS; @@ -616,14 +622,15 @@ static __always_inline void mds_clear_cpu_buffers(void) } /** - * mds_idle_clear_cpu_buffers - Mitigation for MDS vulnerability + * x86_idle_clear_cpu_buffers - Buffer clearing support in idle for the MDS + * and TSA vulnerabilities. * * Clear CPU buffers if the corresponding static key is enabled */ -static __always_inline void mds_idle_clear_cpu_buffers(void) +static __always_inline void x86_idle_clear_cpu_buffers(void) { - if (static_branch_likely(&mds_idle_clear)) - mds_clear_cpu_buffers(); + if (static_branch_likely(&cpu_buf_idle_clear)) + x86_clear_cpu_buffers(); } #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h index b5b633294061..2d13ef1f4b05 100644 --- a/arch/x86/include/asm/tdx.h +++ b/arch/x86/include/asm/tdx.h @@ -97,7 +97,7 @@ void tdx_init(void); typedef u64 (*sc_func_t)(u64 fn, struct tdx_module_args *args); -static inline u64 sc_retry(sc_func_t func, u64 fn, +static __always_inline u64 sc_retry(sc_func_t func, u64 fn, struct tdx_module_args *args) { int retry = RDRAND_RETRY_LOOPS; diff --git a/arch/x86/include/uapi/asm/debugreg.h b/arch/x86/include/uapi/asm/debugreg.h index 0007ba077c0c..41da492dfb01 100644 --- a/arch/x86/include/uapi/asm/debugreg.h +++ b/arch/x86/include/uapi/asm/debugreg.h @@ -15,7 +15,26 @@ which debugging register was responsible for the trap. The other bits are either reserved or not of interest to us. */ -/* Define reserved bits in DR6 which are always set to 1 */ +/* + * Define bits in DR6 which are set to 1 by default. + * + * This is also the DR6 architectural value following Power-up, Reset or INIT. + * + * Note, with the introduction of Bus Lock Detection (BLD) and Restricted + * Transactional Memory (RTM), the DR6 register has been modified: + * + * 1) BLD flag (bit 11) is no longer reserved to 1 if the CPU supports + * Bus Lock Detection. The assertion of a bus lock could clear it. + * + * 2) RTM flag (bit 16) is no longer reserved to 1 if the CPU supports + * restricted transactional memory. #DB occurred inside an RTM region + * could clear it. + * + * Apparently, DR6.BLD and DR6.RTM are active low bits. + * + * As a result, DR6_RESERVED is an incorrect name now, but it is kept for + * compatibility. + */ #define DR6_RESERVED (0xFFFF0FF0) #define DR_TRAP0 (0x1) /* db0 */ diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index e432910859cb..4810271302d0 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -368,6 +368,66 @@ static void bsp_determine_snp(struct cpuinfo_x86 *c) #endif } +static bool amd_check_tsa_microcode(void) +{ + struct cpuinfo_x86 *c = &boot_cpu_data; + union zen_patch_rev p; + u32 min_rev = 0; + + p.ext_fam = c->x86 - 0xf; + p.model = c->x86_model; + p.ext_model = c->x86_model >> 4; + p.stepping = c->x86_stepping; + /* reserved bits are expected to be 0 in test below */ + p.__reserved = 0; + + if (cpu_has(c, X86_FEATURE_ZEN3) || + cpu_has(c, X86_FEATURE_ZEN4)) { + switch (p.ucode_rev >> 8) { + case 0xa0011: min_rev = 0x0a0011d7; break; + case 0xa0012: min_rev = 0x0a00123b; break; + case 0xa0082: min_rev = 0x0a00820d; break; + case 0xa1011: min_rev = 0x0a10114c; break; + case 0xa1012: min_rev = 0x0a10124c; break; + case 0xa1081: min_rev = 0x0a108109; break; + case 0xa2010: min_rev = 0x0a20102e; break; + case 0xa2012: min_rev = 0x0a201211; break; + case 0xa4041: min_rev = 0x0a404108; break; + case 0xa5000: min_rev = 0x0a500012; break; + case 0xa6012: min_rev = 0x0a60120a; break; + case 0xa7041: min_rev = 0x0a704108; break; + case 0xa7052: min_rev = 0x0a705208; break; + case 0xa7080: min_rev = 0x0a708008; break; + case 0xa70c0: min_rev = 0x0a70c008; break; + case 0xaa002: min_rev = 0x0aa00216; break; + default: + pr_debug("%s: ucode_rev: 0x%x, current revision: 0x%x\n", + __func__, p.ucode_rev, c->microcode); + return false; + } + } + + if (!min_rev) + return false; + + return c->microcode >= min_rev; +} + +static void tsa_init(struct cpuinfo_x86 *c) +{ + if (cpu_has(c, X86_FEATURE_HYPERVISOR)) + return; + + if (cpu_has(c, X86_FEATURE_ZEN3) || + cpu_has(c, X86_FEATURE_ZEN4)) { + if (amd_check_tsa_microcode()) + setup_force_cpu_cap(X86_FEATURE_VERW_CLEAR); + } else { + setup_force_cpu_cap(X86_FEATURE_TSA_SQ_NO); + setup_force_cpu_cap(X86_FEATURE_TSA_L1_NO); + } +} + static void bsp_init_amd(struct cpuinfo_x86 *c) { if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) { @@ -475,6 +535,9 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) } bsp_determine_snp(c); + + tsa_init(c); + return; warn: @@ -916,6 +979,13 @@ static void init_amd_zen2(struct cpuinfo_x86 *c) init_spectral_chicken(c); fix_erratum_1386(c); zen2_zenbleed_check(c); + + /* Disable RDSEED on AMD Cyan Skillfish because of an error. */ + if (c->x86_model == 0x47 && c->x86_stepping == 0x0) { + clear_cpu_cap(c, X86_FEATURE_RDSEED); + msr_clear_bit(MSR_AMD64_CPUID_FN_7, 18); + pr_emerg("RDSEED is not reliable on this platform; disabling.\n"); + } } static void init_amd_zen3(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 0e9ab0b9a494..31b4b73e5405 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -50,6 +50,7 @@ static void __init l1d_flush_select_mitigation(void); static void __init srso_select_mitigation(void); static void __init gds_select_mitigation(void); static void __init its_select_mitigation(void); +static void __init tsa_select_mitigation(void); /* The base value of the SPEC_CTRL MSR without task-specific bits set */ u64 x86_spec_ctrl_base; @@ -70,10 +71,9 @@ void (*x86_return_thunk)(void) __ro_after_init = __x86_return_thunk; static void __init set_return_thunk(void *thunk) { - if (x86_return_thunk != __x86_return_thunk) - pr_warn("x86/bugs: return thunk changed\n"); - x86_return_thunk = thunk; + + pr_info("active return thunk: %ps\n", thunk); } /* Update SPEC_CTRL MSR and its cached copy unconditionally */ @@ -122,9 +122,9 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_cond_ibpb); /* Control unconditional IBPB in switch_mm() */ DEFINE_STATIC_KEY_FALSE(switch_mm_always_ibpb); -/* Control MDS CPU buffer clear before idling (halt, mwait) */ -DEFINE_STATIC_KEY_FALSE(mds_idle_clear); -EXPORT_SYMBOL_GPL(mds_idle_clear); +/* Control CPU buffer clear before idling (halt, mwait) */ +DEFINE_STATIC_KEY_FALSE(cpu_buf_idle_clear); +EXPORT_SYMBOL_GPL(cpu_buf_idle_clear); /* * Controls whether l1d flush based mitigations are enabled, @@ -185,6 +185,7 @@ void __init cpu_select_mitigations(void) srso_select_mitigation(); gds_select_mitigation(); its_select_mitigation(); + tsa_select_mitigation(); } /* @@ -448,7 +449,7 @@ static void __init mmio_select_mitigation(void) * is required irrespective of SMT state. */ if (!(x86_arch_cap_msr & ARCH_CAP_FBSDP_NO)) - static_branch_enable(&mds_idle_clear); + static_branch_enable(&cpu_buf_idle_clear); /* * Check if the system has the right microcode. @@ -2092,10 +2093,10 @@ static void update_mds_branch_idle(void) return; if (sched_smt_active()) { - static_branch_enable(&mds_idle_clear); + static_branch_enable(&cpu_buf_idle_clear); } else if (mmio_mitigation == MMIO_MITIGATION_OFF || (x86_arch_cap_msr & ARCH_CAP_FBSDP_NO)) { - static_branch_disable(&mds_idle_clear); + static_branch_disable(&cpu_buf_idle_clear); } } @@ -2103,6 +2104,94 @@ static void update_mds_branch_idle(void) #define TAA_MSG_SMT "TAA CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/tsx_async_abort.html for more details.\n" #define MMIO_MSG_SMT "MMIO Stale Data CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/processor_mmio_stale_data.html for more details.\n" +#undef pr_fmt +#define pr_fmt(fmt) "Transient Scheduler Attacks: " fmt + +enum tsa_mitigations { + TSA_MITIGATION_NONE, + TSA_MITIGATION_UCODE_NEEDED, + TSA_MITIGATION_USER_KERNEL, + TSA_MITIGATION_VM, + TSA_MITIGATION_FULL, +}; + +static const char * const tsa_strings[] = { + [TSA_MITIGATION_NONE] = "Vulnerable", + [TSA_MITIGATION_UCODE_NEEDED] = "Vulnerable: Clear CPU buffers attempted, no microcode", + [TSA_MITIGATION_USER_KERNEL] = "Mitigation: Clear CPU buffers: user/kernel boundary", + [TSA_MITIGATION_VM] = "Mitigation: Clear CPU buffers: VM", + [TSA_MITIGATION_FULL] = "Mitigation: Clear CPU buffers", +}; + +static enum tsa_mitigations tsa_mitigation __ro_after_init = + IS_ENABLED(CONFIG_MITIGATION_TSA) ? TSA_MITIGATION_FULL : TSA_MITIGATION_NONE; + +static int __init tsa_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!strcmp(str, "off")) + tsa_mitigation = TSA_MITIGATION_NONE; + else if (!strcmp(str, "on")) + tsa_mitigation = TSA_MITIGATION_FULL; + else if (!strcmp(str, "user")) + tsa_mitigation = TSA_MITIGATION_USER_KERNEL; + else if (!strcmp(str, "vm")) + tsa_mitigation = TSA_MITIGATION_VM; + else + pr_err("Ignoring unknown tsa=%s option.\n", str); + + return 0; +} +early_param("tsa", tsa_parse_cmdline); + +static void __init tsa_select_mitigation(void) +{ + if (tsa_mitigation == TSA_MITIGATION_NONE) + return; + + if (cpu_mitigations_off() || !boot_cpu_has_bug(X86_BUG_TSA)) { + tsa_mitigation = TSA_MITIGATION_NONE; + return; + } + + if (!boot_cpu_has(X86_FEATURE_VERW_CLEAR)) + tsa_mitigation = TSA_MITIGATION_UCODE_NEEDED; + + switch (tsa_mitigation) { + case TSA_MITIGATION_USER_KERNEL: + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); + break; + + case TSA_MITIGATION_VM: + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF_VM); + break; + + case TSA_MITIGATION_UCODE_NEEDED: + if (!boot_cpu_has(X86_FEATURE_HYPERVISOR)) + goto out; + + pr_notice("Forcing mitigation on in a VM\n"); + + /* + * On the off-chance that microcode has been updated + * on the host, enable the mitigation in the guest just + * in case. + */ + fallthrough; + case TSA_MITIGATION_FULL: + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF_VM); + break; + default: + break; + } + +out: + pr_info("%s\n", tsa_strings[tsa_mitigation]); +} + void cpu_bugs_smt_update(void) { mutex_lock(&spec_ctrl_mutex); @@ -2156,6 +2245,24 @@ void cpu_bugs_smt_update(void) break; } + switch (tsa_mitigation) { + case TSA_MITIGATION_USER_KERNEL: + case TSA_MITIGATION_VM: + case TSA_MITIGATION_FULL: + case TSA_MITIGATION_UCODE_NEEDED: + /* + * TSA-SQ can potentially lead to info leakage between + * SMT threads. + */ + if (sched_smt_active()) + static_branch_enable(&cpu_buf_idle_clear); + else + static_branch_disable(&cpu_buf_idle_clear); + break; + case TSA_MITIGATION_NONE: + break; + } + mutex_unlock(&spec_ctrl_mutex); } @@ -3084,6 +3191,11 @@ static ssize_t gds_show_state(char *buf) return sysfs_emit(buf, "%s\n", gds_strings[gds_mitigation]); } +static ssize_t tsa_show_state(char *buf) +{ + return sysfs_emit(buf, "%s\n", tsa_strings[tsa_mitigation]); +} + static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr, char *buf, unsigned int bug) { @@ -3145,6 +3257,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_ITS: return its_show_state(buf); + case X86_BUG_TSA: + return tsa_show_state(buf); + default: break; } @@ -3229,6 +3344,11 @@ ssize_t cpu_show_indirect_target_selection(struct device *dev, struct device_att { return cpu_show_common(dev, attr, buf, X86_BUG_ITS); } + +ssize_t cpu_show_tsa(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_TSA); +} #endif void __warn_thunk(void) diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index b48775445523..976545ec8fdc 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1233,6 +1233,8 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { #define ITS BIT(8) /* CPU is affected by Indirect Target Selection, but guest-host isolation is not affected */ #define ITS_NATIVE_ONLY BIT(9) +/* CPU is affected by Transient Scheduler Attacks */ +#define TSA BIT(10) static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(INTEL_IVYBRIDGE, X86_STEPPING_ANY, SRBDS), @@ -1280,7 +1282,7 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_AMD(0x16, RETBLEED), VULNBL_AMD(0x17, RETBLEED | SMT_RSB | SRSO), VULNBL_HYGON(0x18, RETBLEED | SMT_RSB | SRSO), - VULNBL_AMD(0x19, SRSO), + VULNBL_AMD(0x19, SRSO | TSA), {} }; @@ -1490,6 +1492,16 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) setup_force_cpu_bug(X86_BUG_ITS_NATIVE_ONLY); } + if (c->x86_vendor == X86_VENDOR_AMD) { + if (!cpu_has(c, X86_FEATURE_TSA_SQ_NO) || + !cpu_has(c, X86_FEATURE_TSA_L1_NO)) { + if (cpu_matches(cpu_vuln_blacklist, TSA) || + /* Enable bug on Zen guests to allow for live migration. */ + (cpu_has(c, X86_FEATURE_HYPERVISOR) && cpu_has(c, X86_FEATURE_ZEN))) + setup_force_cpu_bug(X86_BUG_TSA); + } + } + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; @@ -2145,20 +2157,16 @@ EXPORT_PER_CPU_SYMBOL(__stack_chk_guard); #endif /* CONFIG_X86_64 */ -/* - * Clear all 6 debug registers: - */ -static void clear_all_debug_regs(void) +static void initialize_debug_regs(void) { - int i; - - for (i = 0; i < 8; i++) { - /* Ignore db4, db5 */ - if ((i == 4) || (i == 5)) - continue; - - set_debugreg(0, i); - } + /* Control register first -- to make sure everything is disabled. */ + set_debugreg(DR7_FIXED_1, 7); + set_debugreg(DR6_RESERVED, 6); + /* dr5 and dr4 don't exist */ + set_debugreg(0, 3); + set_debugreg(0, 2); + set_debugreg(0, 1); + set_debugreg(0, 0); } #ifdef CONFIG_KGDB @@ -2319,7 +2327,7 @@ void cpu_init(void) load_mm_ldt(&init_mm); - clear_all_debug_regs(); + initialize_debug_regs(); dbg_restore_debug_regs(); doublefault_init_cpu_tss(); diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index 14bf8c232e45..dac4564e1d7c 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -327,7 +327,6 @@ static void smca_configure(unsigned int bank, unsigned int cpu) struct thresh_restart { struct threshold_block *b; - int reset; int set_lvt_off; int lvt_off; u16 old_limit; @@ -422,13 +421,13 @@ static void threshold_restart_bank(void *_tr) rdmsr(tr->b->address, lo, hi); - if (tr->b->threshold_limit < (hi & THRESHOLD_MAX)) - tr->reset = 1; /* limit cannot be lower than err count */ - - if (tr->reset) { /* reset err count and overflow bit */ - hi = - (hi & ~(MASK_ERR_COUNT_HI | MASK_OVERFLOW_HI)) | - (THRESHOLD_MAX - tr->b->threshold_limit); + /* + * Reset error count and overflow bit. + * This is done during init or after handling an interrupt. + */ + if (hi & MASK_OVERFLOW_HI || tr->set_lvt_off) { + hi &= ~(MASK_ERR_COUNT_HI | MASK_OVERFLOW_HI); + hi |= THRESHOLD_MAX - tr->b->threshold_limit; } else if (tr->old_limit) { /* change limit w/o reset */ int new_count = (hi & THRESHOLD_MAX) + (tr->old_limit - tr->b->threshold_limit); @@ -1099,13 +1098,20 @@ static const char *get_name(unsigned int cpu, unsigned int bank, struct threshol } bank_type = smca_get_bank_type(cpu, bank); - if (bank_type >= N_SMCA_BANK_TYPES) - return NULL; if (b && (bank_type == SMCA_UMC || bank_type == SMCA_UMC_V2)) { if (b->block < ARRAY_SIZE(smca_umc_block_names)) return smca_umc_block_names[b->block]; - return NULL; + } + + if (b && b->block) { + snprintf(buf_mcatype, MAX_MCATYPE_NAME_LEN, "th_block_%u", b->block); + return buf_mcatype; + } + + if (bank_type >= N_SMCA_BANK_TYPES) { + snprintf(buf_mcatype, MAX_MCATYPE_NAME_LEN, "th_bank_%u", bank); + return buf_mcatype; } if (per_cpu(smca_bank_counts, cpu)[bank_type] == 1) diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 2a938f429c4d..d8f3d9af8acf 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -1688,6 +1688,11 @@ static void mc_poll_banks_default(void) void (*mc_poll_banks)(void) = mc_poll_banks_default; +static bool should_enable_timer(unsigned long iv) +{ + return !mca_cfg.ignore_ce && iv; +} + static void mce_timer_fn(struct timer_list *t) { struct timer_list *cpu_t = this_cpu_ptr(&mce_timer); @@ -1711,7 +1716,7 @@ static void mce_timer_fn(struct timer_list *t) if (mce_get_storm_mode()) { __start_timer(t, HZ); - } else { + } else if (should_enable_timer(iv)) { __this_cpu_write(mce_next_interval, iv); __start_timer(t, iv); } @@ -2111,11 +2116,10 @@ static void mce_start_timer(struct timer_list *t) { unsigned long iv = check_interval * HZ; - if (mca_cfg.ignore_ce || !iv) - return; - - this_cpu_write(mce_next_interval, iv); - __start_timer(t, iv); + if (should_enable_timer(iv)) { + this_cpu_write(mce_next_interval, iv); + __start_timer(t, iv); + } } static void __mcheck_cpu_setup_timer(void) @@ -2756,15 +2760,9 @@ static int mce_cpu_dead(unsigned int cpu) static int mce_cpu_online(unsigned int cpu) { struct timer_list *t = this_cpu_ptr(&mce_timer); - int ret; mce_device_create(cpu); - - ret = mce_threshold_create_device(cpu); - if (ret) { - mce_device_remove(cpu); - return ret; - } + mce_threshold_create_device(cpu); mce_reenable_cpu(); mce_start_timer(t); return 0; diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c index f6103e6bf69a..bb0a60b1ed63 100644 --- a/arch/x86/kernel/cpu/mce/intel.c +++ b/arch/x86/kernel/cpu/mce/intel.c @@ -477,6 +477,7 @@ void mce_intel_feature_init(struct cpuinfo_x86 *c) void mce_intel_feature_clear(struct cpuinfo_x86 *c) { intel_clear_lmce(); + cmci_clear(); } bool intel_filter_mce(struct mce *m) diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 2f84164b20e0..765b4646648f 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -94,18 +94,6 @@ static struct equiv_cpu_table { struct equiv_cpu_entry *entry; } equiv_table; -union zen_patch_rev { - struct { - __u32 rev : 8, - stepping : 4, - model : 4, - __reserved : 4, - ext_model : 4, - ext_fam : 8; - }; - __u32 ucode_rev; -}; - union cpuid_1_eax { struct { __u32 stepping : 4, diff --git a/arch/x86/kernel/cpu/microcode/amd_shas.c b/arch/x86/kernel/cpu/microcode/amd_shas.c index 2a1655b1fdd8..1fd349cfc802 100644 --- a/arch/x86/kernel/cpu/microcode/amd_shas.c +++ b/arch/x86/kernel/cpu/microcode/amd_shas.c @@ -231,6 +231,13 @@ static const struct patch_digest phashes[] = { 0x0d,0x5b,0x65,0x34,0x69,0xb2,0x62,0x21, } }, + { 0xa0011d7, { + 0x35,0x07,0xcd,0x40,0x94,0xbc,0x81,0x6b, + 0xfc,0x61,0x56,0x1a,0xe2,0xdb,0x96,0x12, + 0x1c,0x1c,0x31,0xb1,0x02,0x6f,0xe5,0xd2, + 0xfe,0x1b,0x04,0x03,0x2c,0x8f,0x4c,0x36, + } + }, { 0xa001223, { 0xfb,0x32,0x5f,0xc6,0x83,0x4f,0x8c,0xb8, 0xa4,0x05,0xf9,0x71,0x53,0x01,0x16,0xc4, @@ -294,6 +301,13 @@ static const struct patch_digest phashes[] = { 0xc0,0xcd,0x33,0xf2,0x8d,0xf9,0xef,0x59, } }, + { 0xa00123b, { + 0xef,0xa1,0x1e,0x71,0xf1,0xc3,0x2c,0xe2, + 0xc3,0xef,0x69,0x41,0x7a,0x54,0xca,0xc3, + 0x8f,0x62,0x84,0xee,0xc2,0x39,0xd9,0x28, + 0x95,0xa7,0x12,0x49,0x1e,0x30,0x71,0x72, + } + }, { 0xa00820c, { 0xa8,0x0c,0x81,0xc0,0xa6,0x00,0xe7,0xf3, 0x5f,0x65,0xd3,0xb9,0x6f,0xea,0x93,0x63, @@ -301,6 +315,13 @@ static const struct patch_digest phashes[] = { 0xe1,0x3b,0x8d,0xb2,0xf8,0x22,0x03,0xe2, } }, + { 0xa00820d, { + 0xf9,0x2a,0xc0,0xf4,0x9e,0xa4,0x87,0xa4, + 0x7d,0x87,0x00,0xfd,0xab,0xda,0x19,0xca, + 0x26,0x51,0x32,0xc1,0x57,0x91,0xdf,0xc1, + 0x05,0xeb,0x01,0x7c,0x5a,0x95,0x21,0xb7, + } + }, { 0xa10113e, { 0x05,0x3c,0x66,0xd7,0xa9,0x5a,0x33,0x10, 0x1b,0xf8,0x9c,0x8f,0xed,0xfc,0xa7,0xa0, @@ -322,6 +343,13 @@ static const struct patch_digest phashes[] = { 0xf1,0x5e,0xb0,0xde,0xb4,0x98,0xae,0xc4, } }, + { 0xa10114c, { + 0x9e,0xb6,0xa2,0xd9,0x87,0x38,0xc5,0x64, + 0xd8,0x88,0xfa,0x78,0x98,0xf9,0x6f,0x74, + 0x39,0x90,0x1b,0xa5,0xcf,0x5e,0xb4,0x2a, + 0x02,0xff,0xd4,0x8c,0x71,0x8b,0xe2,0xc0, + } + }, { 0xa10123e, { 0x03,0xb9,0x2c,0x76,0x48,0x93,0xc9,0x18, 0xfb,0x56,0xfd,0xf7,0xe2,0x1d,0xca,0x4d, @@ -343,6 +371,13 @@ static const struct patch_digest phashes[] = { 0x1b,0x7d,0x64,0x9d,0x4b,0x53,0x13,0x75, } }, + { 0xa10124c, { + 0x29,0xea,0xf1,0x2c,0xb2,0xe4,0xef,0x90, + 0xa4,0xcd,0x1d,0x86,0x97,0x17,0x61,0x46, + 0xfc,0x22,0xcb,0x57,0x75,0x19,0xc8,0xcc, + 0x0c,0xf5,0xbc,0xac,0x81,0x9d,0x9a,0xd2, + } + }, { 0xa108108, { 0xed,0xc2,0xec,0xa1,0x15,0xc6,0x65,0xe9, 0xd0,0xef,0x39,0xaa,0x7f,0x55,0x06,0xc6, @@ -350,6 +385,13 @@ static const struct patch_digest phashes[] = { 0x28,0x1e,0x9c,0x59,0x69,0x99,0x4d,0x16, } }, + { 0xa108109, { + 0x85,0xb4,0xbd,0x7c,0x49,0xa7,0xbd,0xfa, + 0x49,0x36,0x80,0x81,0xc5,0xb7,0x39,0x1b, + 0x9a,0xaa,0x50,0xde,0x9b,0xe9,0x32,0x35, + 0x42,0x7e,0x51,0x4f,0x52,0x2c,0x28,0x59, + } + }, { 0xa20102d, { 0xf9,0x6e,0xf2,0x32,0xd3,0x0f,0x5f,0x11, 0x59,0xa1,0xfe,0xcc,0xcd,0x9b,0x42,0x89, @@ -357,6 +399,13 @@ static const struct patch_digest phashes[] = { 0x8c,0xe9,0x19,0x3e,0xcc,0x3f,0x7b,0xb4, } }, + { 0xa20102e, { + 0xbe,0x1f,0x32,0x04,0x0d,0x3c,0x9c,0xdd, + 0xe1,0xa4,0xbf,0x76,0x3a,0xec,0xc2,0xf6, + 0x11,0x00,0xa7,0xaf,0x0f,0xe5,0x02,0xc5, + 0x54,0x3a,0x1f,0x8c,0x16,0xb5,0xff,0xbe, + } + }, { 0xa201210, { 0xe8,0x6d,0x51,0x6a,0x8e,0x72,0xf3,0xfe, 0x6e,0x16,0xbc,0x62,0x59,0x40,0x17,0xe9, @@ -364,6 +413,13 @@ static const struct patch_digest phashes[] = { 0xf7,0x55,0xf0,0x13,0xbb,0x22,0xf6,0x41, } }, + { 0xa201211, { + 0x69,0xa1,0x17,0xec,0xd0,0xf6,0x6c,0x95, + 0xe2,0x1e,0xc5,0x59,0x1a,0x52,0x0a,0x27, + 0xc4,0xed,0xd5,0x59,0x1f,0xbf,0x00,0xff, + 0x08,0x88,0xb5,0xe1,0x12,0xb6,0xcc,0x27, + } + }, { 0xa404107, { 0xbb,0x04,0x4e,0x47,0xdd,0x5e,0x26,0x45, 0x1a,0xc9,0x56,0x24,0xa4,0x4c,0x82,0xb0, @@ -371,6 +427,13 @@ static const struct patch_digest phashes[] = { 0x13,0xbc,0xc5,0x25,0xe4,0xc5,0xc3,0x99, } }, + { 0xa404108, { + 0x69,0x67,0x43,0x06,0xf8,0x0c,0x62,0xdc, + 0xa4,0x21,0x30,0x4f,0x0f,0x21,0x2c,0xcb, + 0xcc,0x37,0xf1,0x1c,0xc3,0xf8,0x2f,0x19, + 0xdf,0x53,0x53,0x46,0xb1,0x15,0xea,0x00, + } + }, { 0xa500011, { 0x23,0x3d,0x70,0x7d,0x03,0xc3,0xc4,0xf4, 0x2b,0x82,0xc6,0x05,0xda,0x80,0x0a,0xf1, @@ -378,6 +441,13 @@ static const struct patch_digest phashes[] = { 0x11,0x5e,0x96,0x7e,0x71,0xe9,0xfc,0x74, } }, + { 0xa500012, { + 0xeb,0x74,0x0d,0x47,0xa1,0x8e,0x09,0xe4, + 0x93,0x4c,0xad,0x03,0x32,0x4c,0x38,0x16, + 0x10,0x39,0xdd,0x06,0xaa,0xce,0xd6,0x0f, + 0x62,0x83,0x9d,0x8e,0x64,0x55,0xbe,0x63, + } + }, { 0xa601209, { 0x66,0x48,0xd4,0x09,0x05,0xcb,0x29,0x32, 0x66,0xb7,0x9a,0x76,0xcd,0x11,0xf3,0x30, @@ -385,6 +455,13 @@ static const struct patch_digest phashes[] = { 0xe8,0x73,0xe2,0xd6,0xdb,0xd2,0x77,0x1d, } }, + { 0xa60120a, { + 0x0c,0x8b,0x3d,0xfd,0x52,0x52,0x85,0x7d, + 0x20,0x3a,0xe1,0x7e,0xa4,0x21,0x3b,0x7b, + 0x17,0x86,0xae,0xac,0x13,0xb8,0x63,0x9d, + 0x06,0x01,0xd0,0xa0,0x51,0x9a,0x91,0x2c, + } + }, { 0xa704107, { 0xf3,0xc6,0x58,0x26,0xee,0xac,0x3f,0xd6, 0xce,0xa1,0x72,0x47,0x3b,0xba,0x2b,0x93, @@ -392,6 +469,13 @@ static const struct patch_digest phashes[] = { 0x64,0x39,0x71,0x8c,0xce,0xe7,0x41,0x39, } }, + { 0xa704108, { + 0xd7,0x55,0x15,0x2b,0xfe,0xc4,0xbc,0x93, + 0xec,0x91,0xa0,0xae,0x45,0xb7,0xc3,0x98, + 0x4e,0xff,0x61,0x77,0x88,0xc2,0x70,0x49, + 0xe0,0x3a,0x1d,0x84,0x38,0x52,0xbf,0x5a, + } + }, { 0xa705206, { 0x8d,0xc0,0x76,0xbd,0x58,0x9f,0x8f,0xa4, 0x12,0x9d,0x21,0xfb,0x48,0x21,0xbc,0xe7, @@ -399,6 +483,13 @@ static const struct patch_digest phashes[] = { 0x03,0x35,0xe9,0xbe,0xfb,0x06,0xdf,0xfc, } }, + { 0xa705208, { + 0x30,0x1d,0x55,0x24,0xbc,0x6b,0x5a,0x19, + 0x0c,0x7d,0x1d,0x74,0xaa,0xd1,0xeb,0xd2, + 0x16,0x62,0xf7,0x5b,0xe1,0x1f,0x18,0x11, + 0x5c,0xf0,0x94,0x90,0x26,0xec,0x69,0xff, + } + }, { 0xa708007, { 0x6b,0x76,0xcc,0x78,0xc5,0x8a,0xa3,0xe3, 0x32,0x2d,0x79,0xe4,0xc3,0x80,0xdb,0xb2, @@ -406,6 +497,13 @@ static const struct patch_digest phashes[] = { 0xdf,0x92,0x73,0x84,0x87,0x3c,0x73,0x93, } }, + { 0xa708008, { + 0x08,0x6e,0xf0,0x22,0x4b,0x8e,0xc4,0x46, + 0x58,0x34,0xe6,0x47,0xa2,0x28,0xfd,0xab, + 0x22,0x3d,0xdd,0xd8,0x52,0x9e,0x1d,0x16, + 0xfa,0x01,0x68,0x14,0x79,0x3e,0xe8,0x6b, + } + }, { 0xa70c005, { 0x88,0x5d,0xfb,0x79,0x64,0xd8,0x46,0x3b, 0x4a,0x83,0x8e,0x77,0x7e,0xcf,0xb3,0x0f, @@ -413,6 +511,13 @@ static const struct patch_digest phashes[] = { 0xee,0x49,0xac,0xe1,0x8b,0x13,0xc5,0x13, } }, + { 0xa70c008, { + 0x0f,0xdb,0x37,0xa1,0x10,0xaf,0xd4,0x21, + 0x94,0x0d,0xa4,0xa2,0xe9,0x86,0x6c,0x0e, + 0x85,0x7c,0x36,0x30,0xa3,0x3a,0x78,0x66, + 0x18,0x10,0x60,0x0d,0x78,0x3d,0x44,0xd0, + } + }, { 0xaa00116, { 0xe8,0x4c,0x2c,0x88,0xa1,0xac,0x24,0x63, 0x65,0xe5,0xaa,0x2d,0x16,0xa9,0xc3,0xf5, @@ -441,4 +546,11 @@ static const struct patch_digest phashes[] = { 0x68,0x2f,0x46,0xee,0xfe,0xc6,0x6d,0xef, } }, + { 0xaa00216, { + 0x79,0xfb,0x5b,0x9f,0xb6,0xe6,0xa8,0xf5, + 0x4e,0x7c,0x4f,0x8e,0x1d,0xad,0xd0,0x08, + 0xc2,0x43,0x7c,0x8b,0xe6,0xdb,0xd0,0xd2, + 0xe8,0x39,0x26,0xc1,0xe5,0x5a,0x48,0xf1, + } + }, }; diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index c84c30188fdf..c463363ae1d4 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -47,8 +47,11 @@ static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_PROC_FEEDBACK, CPUID_EDX, 11, 0x80000007, 0 }, { X86_FEATURE_FAST_CPPC, CPUID_EDX, 15, 0x80000007, 0 }, { X86_FEATURE_MBA, CPUID_EBX, 6, 0x80000008, 0 }, + { X86_FEATURE_COHERENCY_SFW_NO, CPUID_EBX, 31, 0x8000001f, 0 }, { X86_FEATURE_SMBA, CPUID_EBX, 2, 0x80000020, 0 }, { X86_FEATURE_BMEC, CPUID_EBX, 3, 0x80000020, 0 }, + { X86_FEATURE_TSA_SQ_NO, CPUID_ECX, 1, 0x80000021, 0 }, + { X86_FEATURE_TSA_L1_NO, CPUID_ECX, 2, 0x80000021, 0 }, { X86_FEATURE_PERFMON_V2, CPUID_EAX, 0, 0x80000022, 0 }, { X86_FEATURE_AMD_LBR_V2, CPUID_EAX, 1, 0x80000022, 0 }, { X86_FEATURE_AMD_LBR_PMC_FREEZE, CPUID_EAX, 2, 0x80000022, 0 }, diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c index 9ace84486499..147ea26dfdad 100644 --- a/arch/x86/kernel/cpu/sgx/main.c +++ b/arch/x86/kernel/cpu/sgx/main.c @@ -719,6 +719,8 @@ int arch_memory_failure(unsigned long pfn, int flags) goto out; } + sgx_unmark_page_reclaimable(page); + /* * TBD: Add additional plumbing to enable pre-emptive * action for asynchronous poison notification. Until diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 8f62e0666dea..8abe60919e2f 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -119,7 +119,6 @@ static inline bool save_xstate_epilog(void __user *buf, int ia32_frame, { struct xregs_state __user *x = buf; struct _fpx_sw_bytes sw_bytes = {}; - u32 xfeatures; int err; /* Setup the bytes not touched by the [f]xsave and reserved for SW. */ @@ -133,12 +132,6 @@ static inline bool save_xstate_epilog(void __user *buf, int ia32_frame, (__u32 __user *)(buf + fpstate->user_size)); /* - * Read the xfeatures which we copied (directly from the cpu or - * from the state in task struct) to the user buffers. - */ - err |= __get_user(xfeatures, (__u32 __user *)&x->header.xfeatures); - - /* * For legacy compatible, we always set FP/SSE bits in the bit * vector while saving the state to the user context. This will * enable us capturing any changes(during sigreturn) to @@ -149,9 +142,7 @@ static inline bool save_xstate_epilog(void __user *buf, int ia32_frame, * header as well as change any contents in the memory layout. * xrestore as part of sigreturn will capture all the changes. */ - xfeatures |= XFEATURE_MASK_FPSSE; - - err |= __put_user(xfeatures, (__u32 __user *)&x->header.xfeatures); + err |= set_xfeature_in_sigframe(x, XFEATURE_MASK_FPSSE); return !err; } diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h index aa16f1a1bbcf..f7d8f3d73599 100644 --- a/arch/x86/kernel/fpu/xstate.h +++ b/arch/x86/kernel/fpu/xstate.h @@ -69,21 +69,31 @@ static inline u64 xfeatures_mask_independent(void) return fpu_kernel_cfg.independent_features; } +static inline int set_xfeature_in_sigframe(struct xregs_state __user *xbuf, u64 mask) +{ + u64 xfeatures; + int err; + + /* Read the xfeatures value already saved in the user buffer */ + err = __get_user(xfeatures, &xbuf->header.xfeatures); + xfeatures |= mask; + err |= __put_user(xfeatures, &xbuf->header.xfeatures); + + return err; +} + /* * Update the value of PKRU register that was already pushed onto the signal frame. */ -static inline int update_pkru_in_sigframe(struct xregs_state __user *buf, u64 mask, u32 pkru) +static inline int update_pkru_in_sigframe(struct xregs_state __user *buf, u32 pkru) { - u64 xstate_bv; int err; if (unlikely(!cpu_feature_enabled(X86_FEATURE_OSPKE))) return 0; /* Mark PKRU as in-use so that it is restored correctly. */ - xstate_bv = (mask & xfeatures_in_use()) | XFEATURE_MASK_PKRU; - - err = __put_user(xstate_bv, &buf->header.xfeatures); + err = set_xfeature_in_sigframe(buf, XFEATURE_MASK_PKRU); if (err) return err; @@ -304,7 +314,7 @@ static inline int xsave_to_user_sigframe(struct xregs_state __user *buf, u32 pkr clac(); if (!err) - err = update_pkru_in_sigframe(buf, mask, pkru); + err = update_pkru_in_sigframe(buf, pkru); return err; } diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 85fa2db38dc4..9400730e538e 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -251,26 +251,59 @@ static __always_inline void handle_irq(struct irq_desc *desc, __handle_irq(desc, regs); } -static __always_inline int call_irq_handler(int vector, struct pt_regs *regs) +static struct irq_desc *reevaluate_vector(int vector) { - struct irq_desc *desc; - int ret = 0; + struct irq_desc *desc = __this_cpu_read(vector_irq[vector]); + + if (!IS_ERR_OR_NULL(desc)) + return desc; + + if (desc == VECTOR_UNUSED) + pr_emerg_ratelimited("No irq handler for %d.%u\n", smp_processor_id(), vector); + else + __this_cpu_write(vector_irq[vector], VECTOR_UNUSED); + return NULL; +} + +static __always_inline bool call_irq_handler(int vector, struct pt_regs *regs) +{ + struct irq_desc *desc = __this_cpu_read(vector_irq[vector]); - desc = __this_cpu_read(vector_irq[vector]); if (likely(!IS_ERR_OR_NULL(desc))) { handle_irq(desc, regs); - } else { - ret = -EINVAL; - if (desc == VECTOR_UNUSED) { - pr_emerg_ratelimited("%s: %d.%u No irq handler for vector\n", - __func__, smp_processor_id(), - vector); - } else { - __this_cpu_write(vector_irq[vector], VECTOR_UNUSED); - } + return true; } - return ret; + /* + * Reevaluate with vector_lock held to prevent a race against + * request_irq() setting up the vector: + * + * CPU0 CPU1 + * interrupt is raised in APIC IRR + * but not handled + * free_irq() + * per_cpu(vector_irq, CPU1)[vector] = VECTOR_SHUTDOWN; + * + * request_irq() common_interrupt() + * d = this_cpu_read(vector_irq[vector]); + * + * per_cpu(vector_irq, CPU1)[vector] = desc; + * + * if (d == VECTOR_SHUTDOWN) + * this_cpu_write(vector_irq[vector], VECTOR_UNUSED); + * + * This requires that the same vector on the same target CPU is + * handed out or that a spurious interrupt hits that CPU/vector. + */ + lock_vector_lock(); + desc = reevaluate_vector(vector); + unlock_vector_lock(); + + if (!desc) + return false; + + handle_irq(desc, regs); + return true; } /* @@ -284,7 +317,7 @@ DEFINE_IDTENTRY_IRQ(common_interrupt) /* entry code tells RCU that we're not quiescent. Check it. */ RCU_LOCKDEP_WARN(!rcu_is_watching(), "IRQ failed to wake up RCU"); - if (unlikely(call_irq_handler(vector, regs))) + if (unlikely(!call_irq_handler(vector, regs))) apic_eoi(); set_irq_regs(old_regs); diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index 9c9faa1634fb..e5faeec20b1f 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -385,7 +385,7 @@ static void kgdb_disable_hw_debug(struct pt_regs *regs) struct perf_event *bp; /* Disable hardware debugging while we are in kgdb: */ - set_debugreg(0UL, 7); + set_debugreg(DR7_FIXED_1, 7); for (i = 0; i < HBP_NUM; i++) { if (!breakinfo[i].enabled) continue; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 1dbd7a34645c..4c9c98c5deab 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -911,16 +911,24 @@ static __init bool prefer_mwait_c1_over_halt(void) */ static __cpuidle void mwait_idle(void) { + if (need_resched()) + return; + + x86_idle_clear_cpu_buffers(); + if (!current_set_polling_and_test()) { const void *addr = ¤t_thread_info()->flags; alternative_input("", "clflush (%[addr])", X86_BUG_CLFLUSH_MONITOR, [addr] "a" (addr)); __monitor(addr, 0, 0); - if (!need_resched()) { - __sti_mwait(0, 0); - raw_local_irq_disable(); - } + if (need_resched()) + goto out; + + __sti_mwait(0, 0); + raw_local_irq_disable(); } + +out: __current_clr_polling(); } diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 0917c7f25720..f10c14cb6ef8 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -93,7 +93,7 @@ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode, /* Only print out debug registers if they are in their non-default state. */ if ((d0 == 0) && (d1 == 0) && (d2 == 0) && (d3 == 0) && - (d6 == DR6_RESERVED) && (d7 == 0x400)) + (d6 == DR6_RESERVED) && (d7 == DR7_FIXED_1)) return; printk("%sDR0: %08lx DR1: %08lx DR2: %08lx DR3: %08lx\n", diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 226472332a70..266366a945ed 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -132,7 +132,7 @@ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode, /* Only print out debug registers if they are in their non-default state. */ if (!((d0 == 0) && (d1 == 0) && (d2 == 0) && (d3 == 0) && - (d6 == DR6_RESERVED) && (d7 == 0x400))) { + (d6 == DR6_RESERVED) && (d7 == DR7_FIXED_1))) { printk("%sDR0: %016lx DR1: %016lx DR2: %016lx\n", log_lvl, d0, d1, d2); printk("%sDR3: %016lx DR6: %016lx DR7: %016lx\n", diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index b18fc7539b8d..243f3bc9b4dc 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -977,24 +977,32 @@ static bool is_sysenter_singlestep(struct pt_regs *regs) #endif } -static __always_inline unsigned long debug_read_clear_dr6(void) +static __always_inline unsigned long debug_read_reset_dr6(void) { unsigned long dr6; + get_debugreg(dr6, 6); + dr6 ^= DR6_RESERVED; /* Flip to positive polarity */ + /* * The Intel SDM says: * - * Certain debug exceptions may clear bits 0-3. The remaining - * contents of the DR6 register are never cleared by the - * processor. To avoid confusion in identifying debug - * exceptions, debug handlers should clear the register before - * returning to the interrupted task. + * Certain debug exceptions may clear bits 0-3 of DR6. + * + * BLD induced #DB clears DR6.BLD and any other debug + * exception doesn't modify DR6.BLD. * - * Keep it simple: clear DR6 immediately. + * RTM induced #DB clears DR6.RTM and any other debug + * exception sets DR6.RTM. + * + * To avoid confusion in identifying debug exceptions, + * debug handlers should set DR6.BLD and DR6.RTM, and + * clear other DR6 bits before returning. + * + * Keep it simple: write DR6 with its architectural reset + * value 0xFFFF0FF0, defined as DR6_RESERVED, immediately. */ - get_debugreg(dr6, 6); set_debugreg(DR6_RESERVED, 6); - dr6 ^= DR6_RESERVED; /* Flip to positive polarity */ return dr6; } @@ -1194,13 +1202,13 @@ out: /* IST stack entry */ DEFINE_IDTENTRY_DEBUG(exc_debug) { - exc_debug_kernel(regs, debug_read_clear_dr6()); + exc_debug_kernel(regs, debug_read_reset_dr6()); } /* User entry, runs on regular task stack */ DEFINE_IDTENTRY_DEBUG_USER(exc_debug) { - exc_debug_user(regs, debug_read_clear_dr6()); + exc_debug_user(regs, debug_read_reset_dr6()); } #ifdef CONFIG_X86_FRED @@ -1219,7 +1227,7 @@ DEFINE_FREDENTRY_DEBUG(exc_debug) { /* * FRED #DB stores DR6 on the stack in the format which - * debug_read_clear_dr6() returns for the IDT entry points. + * debug_read_reset_dr6() returns for the IDT entry points. */ unsigned long dr6 = fred_event_data(regs); @@ -1234,7 +1242,7 @@ DEFINE_FREDENTRY_DEBUG(exc_debug) /* 32 bit does not have separate entry points. */ DEFINE_IDTENTRY_RAW(exc_debug) { - unsigned long dr6 = debug_read_clear_dr6(); + unsigned long dr6 = debug_read_reset_dr6(); if (user_mode(regs)) exc_debug_user(regs, dr6); diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index c92e43f2d0c4..8f587c5bb6bc 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -814,6 +814,7 @@ void kvm_set_cpu_caps(void) kvm_cpu_cap_mask(CPUID_8000_0021_EAX, F(NO_NESTED_DATA_BP) | F(LFENCE_RDTSC) | 0 /* SmmPgCfgLock */ | + F(VERW_CLEAR) | F(NULL_SEL_CLR_BASE) | F(AUTOIBRS) | 0 /* PrefetchCtlMsr */ | F(WRMSR_XX_BASE_NS) ); @@ -821,11 +822,19 @@ void kvm_set_cpu_caps(void) kvm_cpu_cap_check_and_set(X86_FEATURE_SBPB); kvm_cpu_cap_check_and_set(X86_FEATURE_IBPB_BRTYPE); kvm_cpu_cap_check_and_set(X86_FEATURE_SRSO_NO); + kvm_cpu_cap_check_and_set(X86_FEATURE_VERW_CLEAR); kvm_cpu_cap_init_kvm_defined(CPUID_8000_0022_EAX, F(PERFMON_V2) ); + kvm_cpu_cap_init_kvm_defined(CPUID_8000_0021_ECX, + F(TSA_SQ_NO) | F(TSA_L1_NO) + ); + + kvm_cpu_cap_check_and_set(X86_FEATURE_TSA_SQ_NO); + kvm_cpu_cap_check_and_set(X86_FEATURE_TSA_L1_NO); + /* * Synthesize "LFENCE is serializing" into the AMD-defined entry in * KVM's supported CPUID if the feature is reported as supported by the @@ -1376,8 +1385,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->eax = entry->ebx = entry->ecx = entry->edx = 0; break; case 0x80000021: - entry->ebx = entry->ecx = entry->edx = 0; + entry->ebx = entry->edx = 0; cpuid_entry_override(entry, CPUID_8000_0021_EAX); + cpuid_entry_override(entry, CPUID_8000_0021_ECX); break; /* AMD Extended Performance Monitoring and Debug */ case 0x80000022: { diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index ad479cfb91bc..f16a7b2c2adc 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -2,7 +2,6 @@ #ifndef ARCH_X86_KVM_CPUID_H #define ARCH_X86_KVM_CPUID_H -#include "x86.h" #include "reverse_cpuid.h" #include <asm/cpu.h> #include <asm/processor.h> diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index e72aed25d721..60986f67c35a 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -651,9 +651,10 @@ static inline u8 ctxt_virt_addr_bits(struct x86_emulate_ctxt *ctxt) } static inline bool emul_is_noncanonical_address(u64 la, - struct x86_emulate_ctxt *ctxt) + struct x86_emulate_ctxt *ctxt, + unsigned int flags) { - return !__is_canonical_address(la, ctxt_virt_addr_bits(ctxt)); + return !ctxt->ops->is_canonical_addr(ctxt, la, flags); } /* @@ -1733,7 +1734,8 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt, if (ret != X86EMUL_CONTINUE) return ret; if (emul_is_noncanonical_address(get_desc_base(&seg_desc) | - ((u64)base3 << 32), ctxt)) + ((u64)base3 << 32), ctxt, + X86EMUL_F_DT_LOAD)) return emulate_gp(ctxt, err_code); } @@ -2516,8 +2518,8 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt) ss_sel = cs_sel + 8; cs.d = 0; cs.l = 1; - if (emul_is_noncanonical_address(rcx, ctxt) || - emul_is_noncanonical_address(rdx, ctxt)) + if (emul_is_noncanonical_address(rcx, ctxt, 0) || + emul_is_noncanonical_address(rdx, ctxt, 0)) return emulate_gp(ctxt, 0); break; } @@ -3494,7 +3496,8 @@ static int em_lgdt_lidt(struct x86_emulate_ctxt *ctxt, bool lgdt) if (rc != X86EMUL_CONTINUE) return rc; if (ctxt->mode == X86EMUL_MODE_PROT64 && - emul_is_noncanonical_address(desc_ptr.address, ctxt)) + emul_is_noncanonical_address(desc_ptr.address, ctxt, + X86EMUL_F_DT_LOAD)) return emulate_gp(ctxt, 0); if (lgdt) ctxt->ops->set_gdt(ctxt, &desc_ptr); diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 44c88537448c..79d06a8a5b7d 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1980,6 +1980,9 @@ int kvm_hv_vcpu_flush_tlb(struct kvm_vcpu *vcpu) if (entries[i] == KVM_HV_TLB_FLUSHALL_ENTRY) goto out_flush_all; + if (is_noncanonical_invlpg_address(entries[i], vcpu)) + continue; + /* * Lower 12 bits of 'address' encode the number of additional * pages to flush. diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h index 55a18e2f2dcd..10495fffb890 100644 --- a/arch/x86/kvm/kvm_emulate.h +++ b/arch/x86/kvm/kvm_emulate.h @@ -94,6 +94,8 @@ struct x86_instruction_info { #define X86EMUL_F_FETCH BIT(1) #define X86EMUL_F_IMPLICIT BIT(2) #define X86EMUL_F_INVLPG BIT(3) +#define X86EMUL_F_MSR BIT(4) +#define X86EMUL_F_DT_LOAD BIT(5) struct x86_emulate_ops { void (*vm_bugged)(struct x86_emulate_ctxt *ctxt); @@ -235,6 +237,9 @@ struct x86_emulate_ops { gva_t (*get_untagged_addr)(struct x86_emulate_ctxt *ctxt, gva_t addr, unsigned int flags); + + bool (*is_canonical_addr)(struct x86_emulate_ctxt *ctxt, gva_t addr, + unsigned int flags); }; /* Type, address-of, and value of an instruction's operand. */ diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 9dc5dd43ae7f..e9322358678b 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -4,6 +4,7 @@ #include <linux/kvm_host.h> #include "kvm_cache_regs.h" +#include "x86.h" #include "cpuid.h" extern bool __read_mostly enable_mmio_caching; diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 4607610ef062..8edfb4e4a73d 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -6234,7 +6234,7 @@ void kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, /* It's actually a GPA for vcpu->arch.guest_mmu. */ if (mmu != &vcpu->arch.guest_mmu) { /* INVLPG on a non-canonical address is a NOP according to the SDM. */ - if (is_noncanonical_address(addr, vcpu)) + if (is_noncanonical_invlpg_address(addr, vcpu)) return; kvm_x86_call(flush_tlb_gva)(vcpu, addr); diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c index 05490b9d8a43..6f74e2b27c1e 100644 --- a/arch/x86/kvm/mtrr.c +++ b/arch/x86/kvm/mtrr.c @@ -19,6 +19,7 @@ #include <asm/mtrr.h> #include "cpuid.h" +#include "x86.h" static u64 *find_mtrr(struct kvm_vcpu *vcpu, unsigned int msr) { diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h index 0d17d6b70639..0ea847b82354 100644 --- a/arch/x86/kvm/reverse_cpuid.h +++ b/arch/x86/kvm/reverse_cpuid.h @@ -18,6 +18,7 @@ enum kvm_only_cpuid_leafs { CPUID_8000_0022_EAX, CPUID_7_2_EDX, CPUID_24_0_EBX, + CPUID_8000_0021_ECX, NR_KVM_CPU_CAPS, NKVMCAPINTS = NR_KVM_CPU_CAPS - NCAPINTS, @@ -68,6 +69,10 @@ enum kvm_only_cpuid_leafs { /* CPUID level 0x80000022 (EAX) */ #define KVM_X86_FEATURE_PERFMON_V2 KVM_X86_FEATURE(CPUID_8000_0022_EAX, 0) +/* CPUID level 0x80000021 (ECX) */ +#define KVM_X86_FEATURE_TSA_SQ_NO KVM_X86_FEATURE(CPUID_8000_0021_ECX, 1) +#define KVM_X86_FEATURE_TSA_L1_NO KVM_X86_FEATURE(CPUID_8000_0021_ECX, 2) + struct cpuid_reg { u32 function; u32 index; @@ -98,6 +103,7 @@ static const struct cpuid_reg reverse_cpuid[] = { [CPUID_8000_0022_EAX] = {0x80000022, 0, CPUID_EAX}, [CPUID_7_2_EDX] = { 7, 2, CPUID_EDX}, [CPUID_24_0_EBX] = { 0x24, 0, CPUID_EBX}, + [CPUID_8000_0021_ECX] = {0x80000021, 0, CPUID_ECX}, }; /* @@ -137,6 +143,8 @@ static __always_inline u32 __feature_translate(int x86_feature) KVM_X86_TRANSLATE_FEATURE(PERFMON_V2); KVM_X86_TRANSLATE_FEATURE(RRSBA_CTRL); KVM_X86_TRANSLATE_FEATURE(BHI_CTRL); + KVM_X86_TRANSLATE_FEATURE(TSA_SQ_NO); + KVM_X86_TRANSLATE_FEATURE(TSA_L1_NO); default: return x86_feature; } diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 6154cb450b44..c4ae73541fc5 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2058,6 +2058,10 @@ static int sev_check_source_vcpus(struct kvm *dst, struct kvm *src) struct kvm_vcpu *src_vcpu; unsigned long i; + if (src->created_vcpus != atomic_read(&src->online_vcpus) || + dst->created_vcpus != atomic_read(&dst->online_vcpus)) + return -EBUSY; + if (!sev_es_guest(src)) return 0; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 7cbacd043921..800f781475c0 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1483,7 +1483,7 @@ static void svm_clear_current_vmcb(struct vmcb *vmcb) { int i; - for_each_online_cpu(i) + for_each_possible_cpu(i) cmpxchg(per_cpu_ptr(&svm_data.current_vmcb, i), vmcb, NULL); } @@ -4226,9 +4226,9 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, bool spec_ctrl_in guest_state_exit_irqoff(); } -static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu, - bool force_immediate_exit) +static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags) { + bool force_immediate_exit = run_flags & KVM_RUN_FORCE_IMMEDIATE_EXIT; struct vcpu_svm *svm = to_svm(vcpu); bool spec_ctrl_intercepted = msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL); @@ -4270,10 +4270,13 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu, svm_hv_update_vp_id(svm->vmcb, vcpu); /* - * Run with all-zero DR6 unless needed, so that we can get the exact cause - * of a #DB. + * Run with all-zero DR6 unless the guest can write DR6 freely, so that + * KVM can get the exact cause of a #DB. Note, loading guest DR6 from + * KVM's snapshot is only necessary when DR accesses won't exit. */ - if (likely(!(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT))) + if (unlikely(run_flags & KVM_RUN_LOAD_GUEST_DR6)) + svm_set_dr6(vcpu, vcpu->arch.dr6); + else if (likely(!(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT))) svm_set_dr6(vcpu, DR6_ACTIVE_LOW); clgi(); @@ -5084,7 +5087,6 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .set_idt = svm_set_idt, .get_gdt = svm_get_gdt, .set_gdt = svm_set_gdt, - .set_dr6 = svm_set_dr6, .set_dr7 = svm_set_dr7, .sync_dirty_debug_regs = svm_sync_dirty_debug_regs, .cache_reg = svm_cache_reg, diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S index 0c61153b275f..235c4af6b692 100644 --- a/arch/x86/kvm/svm/vmenter.S +++ b/arch/x86/kvm/svm/vmenter.S @@ -169,6 +169,9 @@ SYM_FUNC_START(__svm_vcpu_run) #endif mov VCPU_RDI(%_ASM_DI), %_ASM_DI + /* Clobbers EFLAGS.ZF */ + VM_CLEAR_CPU_BUFFERS + /* Enter guest mode */ 3: vmrun %_ASM_AX 4: @@ -335,6 +338,9 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run) mov SVM_current_vmcb(%rdi), %rax mov KVM_VMCB_pa(%rax), %rax + /* Clobbers EFLAGS.ZF */ + VM_CLEAR_CPU_BUFFERS + /* Enter guest mode */ 1: vmrun %rax 2: diff --git a/arch/x86/kvm/vmx/hyperv.c b/arch/x86/kvm/vmx/hyperv.c index fab6a1ad98dc..fa41d036acd4 100644 --- a/arch/x86/kvm/vmx/hyperv.c +++ b/arch/x86/kvm/vmx/hyperv.c @@ -4,6 +4,7 @@ #include <linux/errno.h> #include <linux/smp.h> +#include "x86.h" #include "../cpuid.h" #include "hyperv.h" #include "nested.h" diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c index 47476fcc179a..3f83e36a657b 100644 --- a/arch/x86/kvm/vmx/main.c +++ b/arch/x86/kvm/vmx/main.c @@ -42,6 +42,8 @@ struct kvm_x86_ops vt_x86_ops __initdata = { .vcpu_load = vmx_vcpu_load, .vcpu_put = vmx_vcpu_put, + .HOST_OWNED_DEBUGCTL = DEBUGCTLMSR_FREEZE_IN_SMM, + .update_exception_bitmap = vmx_update_exception_bitmap, .get_feature_msr = vmx_get_feature_msr, .get_msr = vmx_get_msr, @@ -60,7 +62,6 @@ struct kvm_x86_ops vt_x86_ops __initdata = { .set_idt = vmx_set_idt, .get_gdt = vmx_get_gdt, .set_gdt = vmx_set_gdt, - .set_dr6 = vmx_set_dr6, .set_dr7 = vmx_set_dr7, .sync_dirty_debug_regs = vmx_sync_dirty_debug_regs, .cache_reg = vmx_cache_reg, diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 22bee8a71144..60bd2791d933 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -7,6 +7,7 @@ #include <asm/debugreg.h> #include <asm/mmu_context.h> +#include "x86.h" #include "cpuid.h" #include "hyperv.h" #include "mmu.h" @@ -16,7 +17,6 @@ #include "sgx.h" #include "trace.h" #include "vmx.h" -#include "x86.h" #include "smm.h" static bool __read_mostly enable_shadow_vmcs = 1; @@ -2653,10 +2653,11 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, if (vmx->nested.nested_run_pending && (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) { kvm_set_dr(vcpu, 7, vmcs12->guest_dr7); - vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl); + vmx_guest_debugctl_write(vcpu, vmcs12->guest_ia32_debugctl & + vmx_get_supported_debugctl(vcpu, false)); } else { kvm_set_dr(vcpu, 7, vcpu->arch.dr7); - vmcs_write64(GUEST_IA32_DEBUGCTL, vmx->nested.pre_vmenter_debugctl); + vmx_guest_debugctl_write(vcpu, vmx->nested.pre_vmenter_debugctl); } if (kvm_mpx_supported() && (!vmx->nested.nested_run_pending || !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))) @@ -3020,8 +3021,8 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu, CC(!kvm_vcpu_is_legal_cr3(vcpu, vmcs12->host_cr3))) return -EINVAL; - if (CC(is_noncanonical_address(vmcs12->host_ia32_sysenter_esp, vcpu)) || - CC(is_noncanonical_address(vmcs12->host_ia32_sysenter_eip, vcpu))) + if (CC(is_noncanonical_msr_address(vmcs12->host_ia32_sysenter_esp, vcpu)) || + CC(is_noncanonical_msr_address(vmcs12->host_ia32_sysenter_eip, vcpu))) return -EINVAL; if ((vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PAT) && @@ -3055,12 +3056,12 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu, CC(vmcs12->host_ss_selector == 0 && !ia32e)) return -EINVAL; - if (CC(is_noncanonical_address(vmcs12->host_fs_base, vcpu)) || - CC(is_noncanonical_address(vmcs12->host_gs_base, vcpu)) || - CC(is_noncanonical_address(vmcs12->host_gdtr_base, vcpu)) || - CC(is_noncanonical_address(vmcs12->host_idtr_base, vcpu)) || - CC(is_noncanonical_address(vmcs12->host_tr_base, vcpu)) || - CC(is_noncanonical_address(vmcs12->host_rip, vcpu))) + if (CC(is_noncanonical_base_address(vmcs12->host_fs_base, vcpu)) || + CC(is_noncanonical_base_address(vmcs12->host_gs_base, vcpu)) || + CC(is_noncanonical_base_address(vmcs12->host_gdtr_base, vcpu)) || + CC(is_noncanonical_base_address(vmcs12->host_idtr_base, vcpu)) || + CC(is_noncanonical_base_address(vmcs12->host_tr_base, vcpu)) || + CC(is_noncanonical_address(vmcs12->host_rip, vcpu, 0))) return -EINVAL; /* @@ -3135,7 +3136,8 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, return -EINVAL; if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) && - CC(!kvm_dr7_valid(vmcs12->guest_dr7))) + (CC(!kvm_dr7_valid(vmcs12->guest_dr7)) || + CC(!vmx_is_valid_debugctl(vcpu, vmcs12->guest_ia32_debugctl, false)))) return -EINVAL; if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT) && @@ -3178,7 +3180,7 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, } if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS) && - (CC(is_noncanonical_address(vmcs12->guest_bndcfgs & PAGE_MASK, vcpu)) || + (CC(is_noncanonical_msr_address(vmcs12->guest_bndcfgs & PAGE_MASK, vcpu)) || CC((vmcs12->guest_bndcfgs & MSR_IA32_BNDCFGS_RSVD)))) return -EINVAL; @@ -3525,7 +3527,7 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, if (!vmx->nested.nested_run_pending || !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) - vmx->nested.pre_vmenter_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL); + vmx->nested.pre_vmenter_debugctl = vmx_guest_debugctl_read(); if (kvm_mpx_supported() && (!vmx->nested.nested_run_pending || !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))) @@ -4576,6 +4578,12 @@ static void sync_vmcs02_to_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) (vmcs12->vm_entry_controls & ~VM_ENTRY_IA32E_MODE) | (vm_entry_controls_get(to_vmx(vcpu)) & VM_ENTRY_IA32E_MODE); + /* + * Note! Save DR7, but intentionally don't grab DEBUGCTL from vmcs02. + * Writes to DEBUGCTL that aren't intercepted by L1 are immediately + * propagated to vmcs12 (see vmx_set_msr()), as the value loaded into + * vmcs02 doesn't strictly track vmcs12. + */ if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_DEBUG_CONTROLS) vmcs12->guest_dr7 = vcpu->arch.dr7; @@ -4766,7 +4774,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, __vmx_set_segment(vcpu, &seg, VCPU_SREG_LDTR); kvm_set_dr(vcpu, 7, 0x400); - vmcs_write64(GUEST_IA32_DEBUGCTL, 0); + vmx_guest_debugctl_write(vcpu, 0); if (nested_vmx_load_msr(vcpu, vmcs12->vm_exit_msr_load_addr, vmcs12->vm_exit_msr_load_count)) @@ -4821,6 +4829,9 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu) WARN_ON(kvm_set_dr(vcpu, 7, vmcs_readl(GUEST_DR7))); } + /* Reload DEBUGCTL to ensure vmcs01 has a fresh FREEZE_IN_SMM value. */ + vmx_reload_guest_debugctl(vcpu); + /* * Note that calling vmx_set_{efer,cr0,cr4} is important as they * handle a variety of side effects to KVM's software model. @@ -5172,7 +5183,7 @@ int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification, * non-canonical form. This is the only check on the memory * destination for long mode! */ - exn = is_noncanonical_address(*ret, vcpu); + exn = is_noncanonical_address(*ret, vcpu, 0); } else { /* * When not in long mode, the virtual/linear address is @@ -5983,7 +5994,7 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) * invalidation. */ if (!operand.vpid || - is_noncanonical_address(operand.gla, vcpu)) + is_noncanonical_invlpg_address(operand.gla, vcpu)) return nested_vmx_fail(vcpu, VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); vpid_sync_vcpu_addr(vpid02, operand.gla); diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 83382a4d1d66..a5edc623166a 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -365,7 +365,7 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) } break; case MSR_IA32_DS_AREA: - if (is_noncanonical_address(data, vcpu)) + if (is_noncanonical_msr_address(data, vcpu)) return 1; pmu->ds_area = data; @@ -605,11 +605,11 @@ static void intel_pmu_reset(struct kvm_vcpu *vcpu) */ static void intel_pmu_legacy_freezing_lbrs_on_pmi(struct kvm_vcpu *vcpu) { - u64 data = vmcs_read64(GUEST_IA32_DEBUGCTL); + u64 data = vmx_guest_debugctl_read(); if (data & DEBUGCTLMSR_FREEZE_LBRS_ON_PMI) { data &= ~DEBUGCTLMSR_LBR; - vmcs_write64(GUEST_IA32_DEBUGCTL, data); + vmx_guest_debugctl_write(vcpu, data); } } @@ -679,7 +679,7 @@ void vmx_passthrough_lbr_msrs(struct kvm_vcpu *vcpu) if (!lbr_desc->event) { vmx_disable_lbr_msrs_passthrough(vcpu); - if (vmcs_read64(GUEST_IA32_DEBUGCTL) & DEBUGCTLMSR_LBR) + if (vmx_guest_debugctl_read() & DEBUGCTLMSR_LBR) goto warn; if (test_bit(INTEL_PMC_IDX_FIXED_VLBR, pmu->pmc_in_use)) goto warn; @@ -701,7 +701,7 @@ warn: static void intel_pmu_cleanup(struct kvm_vcpu *vcpu) { - if (!(vmcs_read64(GUEST_IA32_DEBUGCTL) & DEBUGCTLMSR_LBR)) + if (!(vmx_guest_debugctl_read() & DEBUGCTLMSR_LBR)) intel_pmu_release_guest_lbr_event(vcpu); } diff --git a/arch/x86/kvm/vmx/sgx.c b/arch/x86/kvm/vmx/sgx.c index a3c3d2a51f47..b352a3ba7354 100644 --- a/arch/x86/kvm/vmx/sgx.c +++ b/arch/x86/kvm/vmx/sgx.c @@ -4,12 +4,11 @@ #include <asm/sgx.h> -#include "cpuid.h" +#include "x86.h" #include "kvm_cache_regs.h" #include "nested.h" #include "sgx.h" #include "vmx.h" -#include "x86.h" bool __read_mostly enable_sgx = 1; module_param_named(sgx, enable_sgx, bool, 0444); @@ -38,7 +37,7 @@ static int sgx_get_encls_gva(struct kvm_vcpu *vcpu, unsigned long offset, fault = true; } else if (likely(is_64_bit_mode(vcpu))) { *gva = vmx_get_untagged_addr(vcpu, *gva, 0); - fault = is_noncanonical_address(*gva, vcpu); + fault = is_noncanonical_address(*gva, vcpu, 0); } else { *gva &= 0xffffffff; fault = (s.unusable) || diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index a3d45b01dbad..6c185a260c5b 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -770,8 +770,11 @@ void vmx_emergency_disable_virtualization_cpu(void) return; list_for_each_entry(v, &per_cpu(loaded_vmcss_on_cpu, cpu), - loaded_vmcss_on_cpu_link) + loaded_vmcss_on_cpu_link) { vmcs_clear(v->vmcs); + if (v->shadow_vmcs) + vmcs_clear(v->shadow_vmcs); + } kvm_cpu_vmxoff(); } @@ -2145,7 +2148,7 @@ int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = vmx->pt_desc.guest.addr_a[index / 2]; break; case MSR_IA32_DEBUGCTLMSR: - msr_info->data = vmcs_read64(GUEST_IA32_DEBUGCTL); + msr_info->data = vmx_guest_debugctl_read(); break; default: find_uret_msr: @@ -2170,7 +2173,7 @@ static u64 nested_vmx_truncate_sysenter_addr(struct kvm_vcpu *vcpu, return (unsigned long)data; } -static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated) +u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated) { u64 debugctl = 0; @@ -2182,9 +2185,25 @@ static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated (host_initiated || intel_pmu_lbr_is_enabled(vcpu))) debugctl |= DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI; + if (boot_cpu_has(X86_FEATURE_RTM) && + (host_initiated || guest_cpuid_has(vcpu, X86_FEATURE_RTM))) + debugctl |= DEBUGCTLMSR_RTM_DEBUG; + return debugctl; } +bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data, bool host_initiated) +{ + u64 invalid; + + invalid = data & ~vmx_get_supported_debugctl(vcpu, host_initiated); + if (invalid & (DEBUGCTLMSR_BTF | DEBUGCTLMSR_LBR)) { + kvm_pr_unimpl_wrmsr(vcpu, MSR_IA32_DEBUGCTLMSR, data); + invalid &= ~(DEBUGCTLMSR_BTF | DEBUGCTLMSR_LBR); + } + return !invalid; +} + /* * Writes msr value into the appropriate "register". * Returns 0 on success, non-0 otherwise. @@ -2253,35 +2272,28 @@ int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) } vmcs_writel(GUEST_SYSENTER_ESP, data); break; - case MSR_IA32_DEBUGCTLMSR: { - u64 invalid; - - invalid = data & ~vmx_get_supported_debugctl(vcpu, msr_info->host_initiated); - if (invalid & (DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR)) { - kvm_pr_unimpl_wrmsr(vcpu, msr_index, data); - data &= ~(DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR); - invalid &= ~(DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR); - } - - if (invalid) + case MSR_IA32_DEBUGCTLMSR: + if (!vmx_is_valid_debugctl(vcpu, data, msr_info->host_initiated)) return 1; + data &= vmx_get_supported_debugctl(vcpu, msr_info->host_initiated); + if (is_guest_mode(vcpu) && get_vmcs12(vcpu)->vm_exit_controls & VM_EXIT_SAVE_DEBUG_CONTROLS) get_vmcs12(vcpu)->guest_ia32_debugctl = data; - vmcs_write64(GUEST_IA32_DEBUGCTL, data); + vmx_guest_debugctl_write(vcpu, data); + if (intel_pmu_lbr_is_enabled(vcpu) && !to_vmx(vcpu)->lbr_desc.event && (data & DEBUGCTLMSR_LBR)) intel_pmu_create_guest_lbr_event(vcpu); return 0; - } case MSR_IA32_BNDCFGS: if (!kvm_mpx_supported() || (!msr_info->host_initiated && !guest_cpuid_has(vcpu, X86_FEATURE_MPX))) return 1; - if (is_noncanonical_address(data & PAGE_MASK, vcpu) || + if (is_noncanonical_msr_address(data & PAGE_MASK, vcpu) || (data & MSR_IA32_BNDCFGS_RSVD)) return 1; @@ -2446,7 +2458,7 @@ int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) index = msr_info->index - MSR_IA32_RTIT_ADDR0_A; if (index >= 2 * vmx->pt_desc.num_address_ranges) return 1; - if (is_noncanonical_address(data, vcpu)) + if (is_noncanonical_msr_address(data, vcpu)) return 1; if (index % 2) vmx->pt_desc.guest.addr_b[index / 2] = data; @@ -4820,7 +4832,8 @@ static void init_vmcs(struct vcpu_vmx *vmx) vmcs_write32(GUEST_SYSENTER_CS, 0); vmcs_writel(GUEST_SYSENTER_ESP, 0); vmcs_writel(GUEST_SYSENTER_EIP, 0); - vmcs_write64(GUEST_IA32_DEBUGCTL, 0); + + vmx_guest_debugctl_write(&vmx->vcpu, 0); if (cpu_has_vmx_tpr_shadow()) { vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, 0); @@ -5627,12 +5640,6 @@ void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu) set_debugreg(DR6_RESERVED, 6); } -void vmx_set_dr6(struct kvm_vcpu *vcpu, unsigned long val) -{ - lockdep_assert_irqs_disabled(); - set_debugreg(vcpu->arch.dr6, 6); -} - void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val) { vmcs_writel(GUEST_DR7, val); @@ -7310,7 +7317,7 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, vmx_l1d_flush(vcpu); else if (static_branch_unlikely(&mmio_stale_data_clear) && kvm_arch_has_assigned_device(vcpu->kvm)) - mds_clear_cpu_buffers(); + x86_clear_cpu_buffers(); vmx_disable_fb_clear(vmx); @@ -7350,8 +7357,9 @@ out: guest_state_exit_irqoff(); } -fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit) +fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags) { + bool force_immediate_exit = run_flags & KVM_RUN_FORCE_IMMEDIATE_EXIT; struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long cr3, cr4; @@ -7396,6 +7404,12 @@ fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit) vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]); vcpu->arch.regs_dirty = 0; + if (run_flags & KVM_RUN_LOAD_GUEST_DR6) + set_debugreg(vcpu->arch.dr6, 6); + + if (run_flags & KVM_RUN_LOAD_DEBUGCTL) + vmx_reload_guest_debugctl(vcpu); + /* * Refresh vmcs.HOST_CR3 if necessary. This must be done immediately * prior to VM-Enter, as the kernel may load a new ASID (PCID) any time diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index cf57fbf12104..a7e2de50d27f 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -435,6 +435,32 @@ static inline void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu); +u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated); +bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data, bool host_initiated); + +static inline void vmx_guest_debugctl_write(struct kvm_vcpu *vcpu, u64 val) +{ + WARN_ON_ONCE(val & DEBUGCTLMSR_FREEZE_IN_SMM); + + val |= vcpu->arch.host_debugctl & DEBUGCTLMSR_FREEZE_IN_SMM; + vmcs_write64(GUEST_IA32_DEBUGCTL, val); +} + +static inline u64 vmx_guest_debugctl_read(void) +{ + return vmcs_read64(GUEST_IA32_DEBUGCTL) & ~DEBUGCTLMSR_FREEZE_IN_SMM; +} + +static inline void vmx_reload_guest_debugctl(struct kvm_vcpu *vcpu) +{ + u64 val = vmcs_read64(GUEST_IA32_DEBUGCTL); + + if (!((val ^ vcpu->arch.host_debugctl) & DEBUGCTLMSR_FREEZE_IN_SMM)) + return; + + vmx_guest_debugctl_write(vcpu, val & ~DEBUGCTLMSR_FREEZE_IN_SMM); +} + /* * Note, early Intel manuals have the write-low and read-high bitmap offsets * the wrong way round. The bitmaps control MSRs 0x00000000-0x00001fff and diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h index 4aba200f435d..5e4ce13ab305 100644 --- a/arch/x86/kvm/vmx/x86_ops.h +++ b/arch/x86/kvm/vmx/x86_ops.h @@ -21,7 +21,7 @@ void vmx_vm_destroy(struct kvm *kvm); int vmx_vcpu_precreate(struct kvm *kvm); int vmx_vcpu_create(struct kvm_vcpu *vcpu); int vmx_vcpu_pre_run(struct kvm_vcpu *vcpu); -fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit); +fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags); void vmx_vcpu_free(struct kvm_vcpu *vcpu); void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event); void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index f378d479fea3..dbd295ef3eba 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1845,7 +1845,7 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data, case MSR_KERNEL_GS_BASE: case MSR_CSTAR: case MSR_LSTAR: - if (is_noncanonical_address(data, vcpu)) + if (is_noncanonical_msr_address(data, vcpu)) return 1; break; case MSR_IA32_SYSENTER_EIP: @@ -1862,7 +1862,7 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data, * value, and that something deterministic happens if the guest * invokes 64-bit SYSENTER. */ - data = __canonical_address(data, vcpu_virt_addr_bits(vcpu)); + data = __canonical_address(data, max_host_virt_addr_bits()); break; case MSR_TSC_AUX: if (!kvm_is_supported_user_return_msr(MSR_TSC_AUX)) @@ -8608,6 +8608,12 @@ static gva_t emulator_get_untagged_addr(struct x86_emulate_ctxt *ctxt, addr, flags); } +static bool emulator_is_canonical_addr(struct x86_emulate_ctxt *ctxt, + gva_t addr, unsigned int flags) +{ + return !is_noncanonical_address(addr, emul_to_vcpu(ctxt), flags); +} + static const struct x86_emulate_ops emulate_ops = { .vm_bugged = emulator_vm_bugged, .read_gpr = emulator_read_gpr, @@ -8654,6 +8660,7 @@ static const struct x86_emulate_ops emulate_ops = { .triple_fault = emulator_triple_fault, .set_xcr = emulator_set_xcr, .get_untagged_addr = emulator_get_untagged_addr, + .is_canonical_addr = emulator_is_canonical_addr, }; static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask) @@ -10704,6 +10711,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) dm_request_for_irq_injection(vcpu) && kvm_cpu_accept_dm_intr(vcpu); fastpath_t exit_fastpath; + u64 run_flags, debug_ctl; bool req_immediate_exit = false; @@ -10948,8 +10956,11 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) goto cancel_injection; } - if (req_immediate_exit) + run_flags = 0; + if (req_immediate_exit) { + run_flags |= KVM_RUN_FORCE_IMMEDIATE_EXIT; kvm_make_request(KVM_REQ_EVENT, vcpu); + } fpregs_assert_state_consistent(); if (test_thread_flag(TIF_NEED_FPU_LOAD)) @@ -10959,19 +10970,29 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) wrmsrl(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err); if (unlikely(vcpu->arch.switch_db_regs)) { - set_debugreg(0, 7); + set_debugreg(DR7_FIXED_1, 7); set_debugreg(vcpu->arch.eff_db[0], 0); set_debugreg(vcpu->arch.eff_db[1], 1); set_debugreg(vcpu->arch.eff_db[2], 2); set_debugreg(vcpu->arch.eff_db[3], 3); /* When KVM_DEBUGREG_WONT_EXIT, dr6 is accessible in guest. */ if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) - kvm_x86_call(set_dr6)(vcpu, vcpu->arch.dr6); + run_flags |= KVM_RUN_LOAD_GUEST_DR6; } else if (unlikely(hw_breakpoint_active())) { - set_debugreg(0, 7); + set_debugreg(DR7_FIXED_1, 7); } - vcpu->arch.host_debugctl = get_debugctlmsr(); + /* + * Refresh the host DEBUGCTL snapshot after disabling IRQs, as DEBUGCTL + * can be modified in IRQ context, e.g. via SMP function calls. Inform + * vendor code if any host-owned bits were changed, e.g. so that the + * value loaded into hardware while running the guest can be updated. + */ + debug_ctl = get_debugctlmsr(); + if ((debug_ctl ^ vcpu->arch.host_debugctl) & kvm_x86_ops.HOST_OWNED_DEBUGCTL && + !vcpu->arch.guest_state_protected) + run_flags |= KVM_RUN_LOAD_DEBUGCTL; + vcpu->arch.host_debugctl = debug_ctl; guest_timing_enter_irqoff(); @@ -10985,8 +11006,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) WARN_ON_ONCE((kvm_vcpu_apicv_activated(vcpu) != kvm_vcpu_apicv_active(vcpu)) && (kvm_get_apic_mode(vcpu) != LAPIC_MODE_DISABLED)); - exit_fastpath = kvm_x86_call(vcpu_run)(vcpu, - req_immediate_exit); + exit_fastpath = kvm_x86_call(vcpu_run)(vcpu, run_flags); if (likely(exit_fastpath != EXIT_FASTPATH_REENTER_GUEST)) break; @@ -10998,6 +11018,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) break; } + run_flags = 0; + /* Note, VM-Exits that go down the "slow" path are accounted below. */ ++vcpu->stat.exits; } @@ -12888,11 +12910,11 @@ void kvm_arch_destroy_vm(struct kvm *kvm) mutex_unlock(&kvm->slots_lock); } kvm_unload_vcpu_mmus(kvm); + kvm_destroy_vcpus(kvm); kvm_x86_call(vm_destroy)(kvm); kvm_free_msr_filter(srcu_dereference_check(kvm->arch.msr_filter, &kvm->srcu, 1)); kvm_pic_destroy(kvm); kvm_ioapic_destroy(kvm); - kvm_destroy_vcpus(kvm); kvfree(rcu_dereference_check(kvm->arch.apic_map, 1)); kfree(srcu_dereference_check(kvm->arch.pmu_event_filter, &kvm->srcu, 1)); kvm_mmu_uninit_vm(kvm); @@ -13756,7 +13778,7 @@ int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva) * invalidation. */ if ((!pcid_enabled && (operand.pcid != 0)) || - is_noncanonical_address(operand.gla, vcpu)) { + is_noncanonical_invlpg_address(operand.gla, vcpu)) { kvm_inject_gp(vcpu, 0); return 1; } diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index a84c48ef5278..ec623d23d13d 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -8,6 +8,7 @@ #include <asm/pvclock.h> #include "kvm_cache_regs.h" #include "kvm_emulate.h" +#include "cpuid.h" struct kvm_caps { /* control of guest tsc rate supported? */ @@ -233,9 +234,52 @@ static inline u8 vcpu_virt_addr_bits(struct kvm_vcpu *vcpu) return kvm_is_cr4_bit_set(vcpu, X86_CR4_LA57) ? 57 : 48; } -static inline bool is_noncanonical_address(u64 la, struct kvm_vcpu *vcpu) +static inline u8 max_host_virt_addr_bits(void) { - return !__is_canonical_address(la, vcpu_virt_addr_bits(vcpu)); + return kvm_cpu_cap_has(X86_FEATURE_LA57) ? 57 : 48; +} + +/* + * x86 MSRs which contain linear addresses, x86 hidden segment bases, and + * IDT/GDT bases have static canonicality checks, the size of which depends + * only on the CPU's support for 5-level paging, rather than on the state of + * CR4.LA57. This applies to both WRMSR and to other instructions that set + * their values, e.g. SGDT. + * + * KVM passes through most of these MSRS and also doesn't intercept the + * instructions that set the hidden segment bases. + * + * Because of this, to be consistent with hardware, even if the guest doesn't + * have LA57 enabled in its CPUID, perform canonicality checks based on *host* + * support for 5 level paging. + * + * Finally, instructions which are related to MMU invalidation of a given + * linear address, also have a similar static canonical check on address. + * This allows for example to invalidate 5-level addresses of a guest from a + * host which uses 4-level paging. + */ +static inline bool is_noncanonical_address(u64 la, struct kvm_vcpu *vcpu, + unsigned int flags) +{ + if (flags & (X86EMUL_F_INVLPG | X86EMUL_F_MSR | X86EMUL_F_DT_LOAD)) + return !__is_canonical_address(la, max_host_virt_addr_bits()); + else + return !__is_canonical_address(la, vcpu_virt_addr_bits(vcpu)); +} + +static inline bool is_noncanonical_msr_address(u64 la, struct kvm_vcpu *vcpu) +{ + return is_noncanonical_address(la, vcpu, X86EMUL_F_MSR); +} + +static inline bool is_noncanonical_base_address(u64 la, struct kvm_vcpu *vcpu) +{ + return is_noncanonical_address(la, vcpu, X86EMUL_F_DT_LOAD); +} + +static inline bool is_noncanonical_invlpg_address(u64 la, struct kvm_vcpu *vcpu) +{ + return is_noncanonical_address(la, vcpu, X86EMUL_F_INVLPG); } static inline void vcpu_cache_mmio_info(struct kvm_vcpu *vcpu, diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index 622fe24da910..1fc2035df404 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -1472,7 +1472,7 @@ static bool kvm_xen_schedop_poll(struct kvm_vcpu *vcpu, bool longmode, if (kvm_read_guest_virt(vcpu, (gva_t)sched_poll.ports, ports, sched_poll.nr_ports * sizeof(*ports), &e)) { *r = -EFAULT; - return true; + goto out; } for (i = 0; i < sched_poll.nr_ports; i++) { @@ -1916,8 +1916,19 @@ int kvm_xen_setup_evtchn(struct kvm *kvm, { struct kvm_vcpu *vcpu; - if (ue->u.xen_evtchn.port >= max_evtchn_port(kvm)) - return -EINVAL; + /* + * Don't check for the port being within range of max_evtchn_port(). + * Userspace can configure what ever targets it likes; events just won't + * be delivered if/while the target is invalid, just like userspace can + * configure MSIs which target non-existent APICs. + * + * This allow on Live Migration and Live Update, the IRQ routing table + * can be restored *independently* of other things like creating vCPUs, + * without imposing an ordering dependency on userspace. In this + * particular case, the problematic ordering would be with setting the + * Xen 'long mode' flag, which changes max_evtchn_port() to allow 4096 + * instead of 1024 event channels. + */ /* We only support 2 level event channels for now */ if (ue->u.xen_evtchn.priority != KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL) diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c index 51986e8a9d35..52e22d3e1a82 100644 --- a/arch/x86/mm/extable.c +++ b/arch/x86/mm/extable.c @@ -122,13 +122,12 @@ static bool ex_handler_sgx(const struct exception_table_entry *fixup, static bool ex_handler_fprestore(const struct exception_table_entry *fixup, struct pt_regs *regs) { - regs->ip = ex_fixup_addr(fixup); - WARN_ONCE(1, "Bad FPU state detected at %pB, reinitializing FPU registers.", (void *)instruction_pointer(regs)); fpu_reset_from_exception_fixup(); - return true; + + return ex_handler_default(fixup, regs); } /* diff --git a/arch/x86/tools/insn_decoder_test.c b/arch/x86/tools/insn_decoder_test.c index 472540aeabc2..08cd913cbd4e 100644 --- a/arch/x86/tools/insn_decoder_test.c +++ b/arch/x86/tools/insn_decoder_test.c @@ -10,8 +10,7 @@ #include <assert.h> #include <unistd.h> #include <stdarg.h> - -#define unlikely(cond) (cond) +#include <linux/kallsyms.h> #include <asm/insn.h> #include <inat.c> @@ -106,7 +105,7 @@ static void parse_args(int argc, char **argv) } } -#define BUFSIZE 256 +#define BUFSIZE (256 + KSYM_NAME_LEN) int main(int argc, char **argv) { diff --git a/arch/x86/um/asm/checksum.h b/arch/x86/um/asm/checksum.h index b07824500363..ddc144657efa 100644 --- a/arch/x86/um/asm/checksum.h +++ b/arch/x86/um/asm/checksum.h @@ -20,6 +20,9 @@ */ extern __wsum csum_partial(const void *buff, int len, __wsum sum); +/* Do not call this directly. Declared for export type visibility. */ +extern __visible __wsum csum_partial_copy_generic(const void *src, void *dst, int len); + /** * csum_fold - Fold and invert a 32bit checksum. * sum: 32bit unfolded sum diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c index 4e2b2e2ac9f9..eb91bc5448de 100644 --- a/arch/x86/virt/vmx/tdx/tdx.c +++ b/arch/x86/virt/vmx/tdx/tdx.c @@ -69,8 +69,9 @@ static inline void seamcall_err_ret(u64 fn, u64 err, args->r9, args->r10, args->r11); } -static inline int sc_retry_prerr(sc_func_t func, sc_err_func_t err_func, - u64 fn, struct tdx_module_args *args) +static __always_inline int sc_retry_prerr(sc_func_t func, + sc_err_func_t err_func, + u64 fn, struct tdx_module_args *args) { u64 sret = sc_retry(func, fn, args); |