diff options
Diffstat (limited to 'arch')
299 files changed, 2293 insertions, 1248 deletions
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index fddc70029727..197896cfbd23 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -170,6 +170,15 @@ config ARC_CPU_HS endchoice +config ARC_TUNE_MCPU + string "Override default -mcpu compiler flag" + default "" + help + Override default -mcpu=xxx compiler flag (which is set depending on + the ISA version) with the specified value. + NOTE: If specified flag isn't supported by current compiler the + ISA default value will be used as a fallback. + config CPU_BIG_ENDIAN bool "Enable Big Endian Mode" help @@ -465,6 +474,12 @@ config ARC_IRQ_NO_AUTOSAVE This is programmable and can be optionally disabled in which case software INTERRUPT_PROLOGUE/EPILGUE do the needed work +config ARC_LPB_DISABLE + bool "Disable loop buffer (LPB)" + help + On HS cores, loop buffer (LPB) is programmable in runtime and can + be optionally disabled. + endif # ISA_ARCV2 endmenu # "ARC CPU Configuration" diff --git a/arch/arc/Makefile b/arch/arc/Makefile index 20e9ab6cc521..d00f8b8afd08 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -10,8 +10,25 @@ CROSS_COMPILE := $(call cc-cross-prefix, arc-linux- arceb-linux-) endif cflags-y += -fno-common -pipe -fno-builtin -mmedium-calls -D__linux__ -cflags-$(CONFIG_ISA_ARCOMPACT) += -mA7 -cflags-$(CONFIG_ISA_ARCV2) += -mcpu=hs38 + +tune-mcpu-def-$(CONFIG_ISA_ARCOMPACT) := -mcpu=arc700 +tune-mcpu-def-$(CONFIG_ISA_ARCV2) := -mcpu=hs38 + +ifeq ($(CONFIG_ARC_TUNE_MCPU),"") +cflags-y += $(tune-mcpu-def-y) +else +tune-mcpu := $(shell echo $(CONFIG_ARC_TUNE_MCPU)) +tune-mcpu-ok := $(call cc-option-yn, $(tune-mcpu)) +ifeq ($(tune-mcpu-ok),y) +cflags-y += $(tune-mcpu) +else +# The flag provided by 'CONFIG_ARC_TUNE_MCPU' option isn't known by this compiler +# (probably the compiler is too old). Use ISA default mcpu flag instead as a safe option. +$(warning ** WARNING ** CONFIG_ARC_TUNE_MCPU flag '$(tune-mcpu)' is unknown, fallback to '$(tune-mcpu-def-y)') +cflags-y += $(tune-mcpu-def-y) +endif +endif + ifdef CONFIG_ARC_CURR_IN_REG # For a global register defintion, make sure it gets passed to every file diff --git a/arch/arc/include/asm/elf.h b/arch/arc/include/asm/elf.h index c77a0e3671ac..0284ace0e1ab 100644 --- a/arch/arc/include/asm/elf.h +++ b/arch/arc/include/asm/elf.h @@ -19,7 +19,7 @@ #define R_ARC_32_PCREL 0x31 /*to set parameters in the core dumps */ -#define ELF_ARCH EM_ARCOMPACT +#define ELF_ARCH EM_ARC_INUSE #define ELF_CLASS ELFCLASS32 #ifdef CONFIG_CPU_BIG_ENDIAN diff --git a/arch/arc/include/asm/irqflags-compact.h b/arch/arc/include/asm/irqflags-compact.h index 7fc73fef5e29..863d63ad18d6 100644 --- a/arch/arc/include/asm/irqflags-compact.h +++ b/arch/arc/include/asm/irqflags-compact.h @@ -90,6 +90,9 @@ static inline void arch_local_irq_restore(unsigned long flags) /* * Unconditionally Enable IRQs */ +#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS +extern void arch_local_irq_enable(void); +#else static inline void arch_local_irq_enable(void) { unsigned long temp; @@ -102,7 +105,7 @@ static inline void arch_local_irq_enable(void) : "n"((STATUS_E1_MASK | STATUS_E2_MASK)) : "cc", "memory"); } - +#endif /* * Unconditionally Disable IRQs diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S index 60406ec62eb8..ea00c8a17f07 100644 --- a/arch/arc/kernel/entry.S +++ b/arch/arc/kernel/entry.S @@ -165,7 +165,6 @@ END(EV_Extension) tracesys: ; save EFA in case tracer wants the PC of traced task ; using ERET won't work since next-PC has already committed - lr r12, [efa] GET_CURR_TASK_FIELD_PTR TASK_THREAD, r11 st r12, [r11, THREAD_FAULT_ADDR] ; thread.fault_address @@ -208,15 +207,9 @@ tracesys_exit: ; Breakpoint TRAP ; --------------------------------------------- trap_with_param: - - ; stop_pc info by gdb needs this info - lr r0, [efa] + mov r0, r12 ; EFA in case ptracer/gdb wants stop_pc mov r1, sp - ; Now that we have read EFA, it is safe to do "fake" rtie - ; and get out of CPU exception mode - FAKE_RET_FROM_EXCPN - ; Save callee regs in case gdb wants to have a look ; SP will grow up by size of CALLEE Reg-File ; NOTE: clobbers r12 @@ -243,6 +236,10 @@ ENTRY(EV_Trap) EXCEPTION_PROLOGUE + lr r12, [efa] + + FAKE_RET_FROM_EXCPN + ;============ TRAP 1 :breakpoints ; Check ECR for trap with arg (PROLOGUE ensures r10 has ECR) bmsk.f 0, r10, 7 @@ -250,9 +247,6 @@ ENTRY(EV_Trap) ;============ TRAP (no param): syscall top level - ; First return from Exception to pure K mode (Exception/IRQs renabled) - FAKE_RET_FROM_EXCPN - ; If syscall tracing ongoing, invoke pre-post-hooks GET_CURR_THR_INFO_FLAGS r10 btst r10, TIF_SYSCALL_TRACE diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S index 6eb23f1545ee..17fd1ed700cc 100644 --- a/arch/arc/kernel/head.S +++ b/arch/arc/kernel/head.S @@ -59,6 +59,14 @@ bclr r5, r5, STATUS_AD_BIT #endif kflag r5 + +#ifdef CONFIG_ARC_LPB_DISABLE + lr r5, [ARC_REG_LPB_BUILD] + breq r5, 0, 1f ; LPB doesn't exist + mov r5, 1 + sr r5, [ARC_REG_LPB_CTRL] +1: +#endif /* CONFIG_ARC_LPB_DISABLE */ #endif ; Config DSP_CTRL properly, so kernel may use integer multiply, ; multiply-accumulate, and divide operations diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index dad8a656a2f1..41f07b3e594e 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -58,10 +58,12 @@ static const struct id_to_str arc_legacy_rel[] = { { 0x00, NULL } }; -static const struct id_to_str arc_cpu_rel[] = { +static const struct id_to_str arc_hs_ver54_rel[] = { /* UARCH.MAJOR, Release */ { 0, "R3.10a"}, { 1, "R3.50a"}, + { 2, "R3.60a"}, + { 3, "R4.00a"}, { 0xFF, NULL } }; @@ -117,12 +119,6 @@ static void decode_arc_core(struct cpuinfo_arc *cpu) struct bcr_uarch_build_arcv2 uarch; const struct id_to_str *tbl; - /* - * Up until (including) the first core4 release (0x54) things were - * simple: AUX IDENTITY.ARCVER was sufficient to identify arc family - * and release: 0x50 to 0x53 was HS38, 0x54 was HS48 (dual issue) - */ - if (cpu->core.family < 0x54) { /* includes arc700 */ for (tbl = &arc_legacy_rel[0]; tbl->id != 0; tbl++) { @@ -143,11 +139,10 @@ static void decode_arc_core(struct cpuinfo_arc *cpu) } /* - * However the subsequent HS release (same 0x54) allow HS38 or HS48 - * configurations and encode this info in a different BCR. - * The BCR was introduced in 0x54 so can't be read unconditionally. + * Initial HS cores bumped AUX IDENTITY.ARCVER for each release until + * ARCVER 0x54 which introduced AUX MICRO_ARCH_BUILD and subsequent + * releases only update it. */ - READ_BCR(ARC_REG_MICRO_ARCH_BCR, uarch); if (uarch.prod == 4) { @@ -158,7 +153,7 @@ static void decode_arc_core(struct cpuinfo_arc *cpu) cpu->name = "HS38"; } - for (tbl = &arc_cpu_rel[0]; tbl->id != 0xFF; tbl++) { + for (tbl = &arc_hs_ver54_rel[0]; tbl->id != 0xFF; tbl++) { if (uarch.maj == tbl->id) { cpu->release = tbl->str; break; diff --git a/arch/arm/boot/dts/am335x-baltos.dtsi b/arch/arm/boot/dts/am335x-baltos.dtsi index 05e7b5d4a95b..04f0b1227efe 100644 --- a/arch/arm/boot/dts/am335x-baltos.dtsi +++ b/arch/arm/boot/dts/am335x-baltos.dtsi @@ -369,7 +369,7 @@ &mmc2 { status = "okay"; vmmc-supply = <&wl12xx_vmmc>; - ti,non-removable; + non-removable; bus-width = <4>; cap-power-off-card; pinctrl-names = "default"; diff --git a/arch/arm/boot/dts/am335x-boneblack-common.dtsi b/arch/arm/boot/dts/am335x-boneblack-common.dtsi index 91f93bc89716..dd932220a8bf 100644 --- a/arch/arm/boot/dts/am335x-boneblack-common.dtsi +++ b/arch/arm/boot/dts/am335x-boneblack-common.dtsi @@ -22,6 +22,7 @@ pinctrl-0 = <&emmc_pins>; bus-width = <8>; status = "okay"; + non-removable; }; &am33xx_pinmux { diff --git a/arch/arm/boot/dts/am335x-boneblack-wireless.dts b/arch/arm/boot/dts/am335x-boneblack-wireless.dts index 3124d94c0b3c..e07dd7979586 100644 --- a/arch/arm/boot/dts/am335x-boneblack-wireless.dts +++ b/arch/arm/boot/dts/am335x-boneblack-wireless.dts @@ -75,7 +75,6 @@ bus-width = <4>; non-removable; cap-power-off-card; - ti,needs-special-hs-handling; keep-power-in-suspend; pinctrl-names = "default"; pinctrl-0 = <&mmc3_pins &wl18xx_pins>; diff --git a/arch/arm/boot/dts/am335x-boneblue.dts b/arch/arm/boot/dts/am335x-boneblue.dts index 5811fb8d4fdf..83f9452c9cd3 100644 --- a/arch/arm/boot/dts/am335x-boneblue.dts +++ b/arch/arm/boot/dts/am335x-boneblue.dts @@ -367,7 +367,6 @@ bus-width = <4>; non-removable; cap-power-off-card; - ti,needs-special-hs-handling; keep-power-in-suspend; pinctrl-names = "default"; pinctrl-0 = <&mmc3_pins &wl18xx_pins>; diff --git a/arch/arm/boot/dts/am335x-bonegreen-wireless.dts b/arch/arm/boot/dts/am335x-bonegreen-wireless.dts index 4092cd193b8a..609c8db687ec 100644 --- a/arch/arm/boot/dts/am335x-bonegreen-wireless.dts +++ b/arch/arm/boot/dts/am335x-bonegreen-wireless.dts @@ -75,7 +75,6 @@ bus-width = <4>; non-removable; cap-power-off-card; - ti,needs-special-hs-handling; keep-power-in-suspend; pinctrl-names = "default"; pinctrl-0 = <&mmc3_pins &wl18xx_pins>; diff --git a/arch/arm/boot/dts/am335x-evm.dts b/arch/arm/boot/dts/am335x-evm.dts index 68252dab32c3..a4fc6b168a85 100644 --- a/arch/arm/boot/dts/am335x-evm.dts +++ b/arch/arm/boot/dts/am335x-evm.dts @@ -743,8 +743,7 @@ bus-width = <4>; pinctrl-names = "default"; pinctrl-0 = <&mmc3_pins &wlan_pins>; - ti,non-removable; - ti,needs-special-hs-handling; + non-removable; cap-power-off-card; keep-power-in-suspend; diff --git a/arch/arm/boot/dts/am335x-evmsk.dts b/arch/arm/boot/dts/am335x-evmsk.dts index 32f515a295ee..78b6e1f594c9 100644 --- a/arch/arm/boot/dts/am335x-evmsk.dts +++ b/arch/arm/boot/dts/am335x-evmsk.dts @@ -655,7 +655,7 @@ &mmc2 { status = "okay"; vmmc-supply = <&wl12xx_vmmc>; - ti,non-removable; + non-removable; bus-width = <4>; cap-power-off-card; keep-power-in-suspend; diff --git a/arch/arm/boot/dts/am335x-lxm.dts b/arch/arm/boot/dts/am335x-lxm.dts index fef582852820..dbedf729205c 100644 --- a/arch/arm/boot/dts/am335x-lxm.dts +++ b/arch/arm/boot/dts/am335x-lxm.dts @@ -339,7 +339,7 @@ pinctrl-0 = <&emmc_pins>; vmmc-supply = <&vmmcsd_fixed>; bus-width = <8>; - ti,non-removable; + non-removable; status = "okay"; }; diff --git a/arch/arm/boot/dts/am335x-moxa-uc-2100-common.dtsi b/arch/arm/boot/dts/am335x-moxa-uc-2100-common.dtsi index 6495a125c01f..4e90f9c23d2e 100644 --- a/arch/arm/boot/dts/am335x-moxa-uc-2100-common.dtsi +++ b/arch/arm/boot/dts/am335x-moxa-uc-2100-common.dtsi @@ -159,7 +159,7 @@ vmmc-supply = <&vmmcsd_fixed>; bus-width = <8>; pinctrl-0 = <&mmc1_pins_default>; - ti,non-removable; + non-removable; status = "okay"; }; diff --git a/arch/arm/boot/dts/am335x-moxa-uc-8100-me-t.dts b/arch/arm/boot/dts/am335x-moxa-uc-8100-me-t.dts index 244df9c5a537..f03e72cada41 100644 --- a/arch/arm/boot/dts/am335x-moxa-uc-8100-me-t.dts +++ b/arch/arm/boot/dts/am335x-moxa-uc-8100-me-t.dts @@ -451,7 +451,7 @@ vmmc-supply = <&vmmcsd_fixed>; bus-width = <8>; pinctrl-0 = <&mmc2_pins_default>; - ti,non-removable; + non-removable; status = "okay"; }; diff --git a/arch/arm/boot/dts/am335x-pepper.dts b/arch/arm/boot/dts/am335x-pepper.dts index 6d7608d9377b..f9a027b47962 100644 --- a/arch/arm/boot/dts/am335x-pepper.dts +++ b/arch/arm/boot/dts/am335x-pepper.dts @@ -341,7 +341,7 @@ pinctrl-0 = <&emmc_pins>; vmmc-supply = <&ldo3_reg>; bus-width = <8>; - ti,non-removable; + non-removable; }; &mmc3 { @@ -351,7 +351,7 @@ pinctrl-0 = <&wireless_pins>; vmmmc-supply = <&v3v3c_reg>; bus-width = <4>; - ti,non-removable; + non-removable; dmas = <&edma_xbar 12 0 1 &edma_xbar 13 0 2>; dma-names = "tx", "rx"; diff --git a/arch/arm/boot/dts/am335x-phycore-som.dtsi b/arch/arm/boot/dts/am335x-phycore-som.dtsi index 3d0672b53d77..7e46b4c02709 100644 --- a/arch/arm/boot/dts/am335x-phycore-som.dtsi +++ b/arch/arm/boot/dts/am335x-phycore-som.dtsi @@ -69,7 +69,7 @@ pinctrl-0 = <&emmc_pins>; vmmc-supply = <&vmmc_reg>; bus-width = <8>; - ti,non-removable; + non-removable; status = "disabled"; }; diff --git a/arch/arm/boot/dts/am335x-pocketbeagle.dts b/arch/arm/boot/dts/am335x-pocketbeagle.dts index 4da719098028..f0b222201b86 100644 --- a/arch/arm/boot/dts/am335x-pocketbeagle.dts +++ b/arch/arm/boot/dts/am335x-pocketbeagle.dts @@ -88,7 +88,6 @@ AM33XX_PADCONF(AM335X_PIN_MMC0_DAT3, PIN_INPUT_PULLUP, MUX_MODE0) AM33XX_PADCONF(AM335X_PIN_MMC0_CMD, PIN_INPUT_PULLUP, MUX_MODE0) AM33XX_PADCONF(AM335X_PIN_MMC0_CLK, PIN_INPUT_PULLUP, MUX_MODE0) - AM33XX_PADCONF(AM335X_PIN_MCASP0_ACLKR, PIN_INPUT, MUX_MODE4) /* (B12) mcasp0_aclkr.mmc0_sdwp */ >; }; diff --git a/arch/arm/boot/dts/am33xx-l4.dtsi b/arch/arm/boot/dts/am33xx-l4.dtsi index 7ff11d6bf0f2..a9cbefc80c0c 100644 --- a/arch/arm/boot/dts/am33xx-l4.dtsi +++ b/arch/arm/boot/dts/am33xx-l4.dtsi @@ -1335,10 +1335,8 @@ ranges = <0x0 0x60000 0x1000>; mmc1: mmc@0 { - compatible = "ti,omap4-hsmmc"; - ti,dual-volt; + compatible = "ti,am335-sdhci"; ti,needs-special-reset; - ti,needs-special-hs-handling; dmas = <&edma_xbar 24 0 0 &edma_xbar 25 0 0>; dma-names = "tx", "rx"; @@ -1816,7 +1814,7 @@ ranges = <0x0 0xd8000 0x1000>; mmc2: mmc@0 { - compatible = "ti,omap4-hsmmc"; + compatible = "ti,am335-sdhci"; ti,needs-special-reset; dmas = <&edma 2 0 &edma 3 0>; diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi index 3b177c9c4412..5fdce106edbb 100644 --- a/arch/arm/boot/dts/am33xx.dtsi +++ b/arch/arm/boot/dts/am33xx.dtsi @@ -322,10 +322,11 @@ ranges = <0x0 0x47810000 0x1000>; mmc3: mmc@0 { - compatible = "ti,omap4-hsmmc"; + compatible = "ti,am335-sdhci"; ti,needs-special-reset; interrupts = <29>; reg = <0x0 0x1000>; + status = "disabled"; }; }; @@ -335,7 +336,7 @@ <0x47400010 0x4>; reg-names = "rev", "sysc"; ti,sysc-mask = <(SYSC_OMAP4_FREEEMU | - SYSC_OMAP2_SOFTRESET)>; + SYSC_OMAP4_SOFTRESET)>; ti,sysc-midle = <SYSC_IDLE_FORCE>, <SYSC_IDLE_NO>, <SYSC_IDLE_SMART>; @@ -347,7 +348,7 @@ clock-names = "fck"; #address-cells = <1>; #size-cells = <1>; - ranges = <0x0 0x47400000 0x5000>; + ranges = <0x0 0x47400000 0x8000>; usb0_phy: usb-phy@1300 { compatible = "ti,am335x-usb-phy"; diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi index b4861f70f178..51ad9e881a62 100644 --- a/arch/arm/boot/dts/am4372.dtsi +++ b/arch/arm/boot/dts/am4372.dtsi @@ -316,10 +316,11 @@ ranges = <0x0 0x47810000 0x1000>; mmc3: mmc@0 { - compatible = "ti,omap4-hsmmc"; + compatible = "ti,am437-sdhci"; ti,needs-special-reset; interrupts = <GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH>; reg = <0x0 0x1000>; + status = "disabled"; }; }; diff --git a/arch/arm/boot/dts/am437x-cm-t43.dts b/arch/arm/boot/dts/am437x-cm-t43.dts index 063113a5da2d..a6b4fca8626a 100644 --- a/arch/arm/boot/dts/am437x-cm-t43.dts +++ b/arch/arm/boot/dts/am437x-cm-t43.dts @@ -291,7 +291,7 @@ pinctrl-0 = <&emmc_pins>; vmmc-supply = <&vmmc_3v3>; bus-width = <8>; - ti,non-removable; + non-removable; }; &spi0 { diff --git a/arch/arm/boot/dts/am437x-gp-evm.dts b/arch/arm/boot/dts/am437x-gp-evm.dts index d692e3b2812a..77378630e5ec 100644 --- a/arch/arm/boot/dts/am437x-gp-evm.dts +++ b/arch/arm/boot/dts/am437x-gp-evm.dts @@ -91,22 +91,6 @@ backlight = <&lcd_bl>; - panel-timing { - clock-frequency = <33000000>; - hactive = <800>; - vactive = <480>; - hfront-porch = <210>; - hback-porch = <16>; - hsync-len = <30>; - vback-porch = <10>; - vfront-porch = <22>; - vsync-len = <13>; - hsync-active = <0>; - vsync-active = <0>; - de-active = <1>; - pixelclk-active = <1>; - }; - port { lcd_in: endpoint { remote-endpoint = <&dpi_out>; @@ -869,7 +853,7 @@ pinctrl-names = "default", "sleep"; pinctrl-0 = <&emmc_pins_default>; pinctrl-1 = <&emmc_pins_sleep>; - ti,non-removable; + non-removable; }; &mmc3 { @@ -886,7 +870,7 @@ pinctrl-1 = <&mmc3_pins_sleep>; cap-power-off-card; keep-power-in-suspend; - ti,non-removable; + non-removable; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm/boot/dts/am437x-l4.dtsi b/arch/arm/boot/dts/am437x-l4.dtsi index 0d0f9fe4a882..906ac29f017d 100644 --- a/arch/arm/boot/dts/am437x-l4.dtsi +++ b/arch/arm/boot/dts/am437x-l4.dtsi @@ -1083,9 +1083,8 @@ ranges = <0x0 0x60000 0x1000>; mmc1: mmc@0 { - compatible = "ti,omap4-hsmmc"; + compatible = "ti,am437-sdhci"; reg = <0x0 0x1000>; - ti,dual-volt; ti,needs-special-reset; dmas = <&edma 24 0>, <&edma 25 0>; @@ -1541,8 +1540,9 @@ reg = <0xcc020 0x4>; reg-names = "rev"; /* Domains (P, C): per_pwrdm, l4ls_clkdm */ - clocks = <&l4ls_clkctrl AM4_L4LS_D_CAN0_CLKCTRL 0>; - clock-names = "fck"; + clocks = <&l4ls_clkctrl AM4_L4LS_D_CAN0_CLKCTRL 0>, + <&dcan0_fck>; + clock-names = "fck", "osc"; #address-cells = <1>; #size-cells = <1>; ranges = <0x0 0xcc000 0x2000>; @@ -1550,6 +1550,8 @@ dcan0: can@0 { compatible = "ti,am4372-d_can", "ti,am3352-d_can"; reg = <0x0 0x2000>; + clocks = <&dcan0_fck>; + clock-names = "fck"; syscon-raminit = <&scm_conf 0x644 0>; interrupts = <GIC_SPI 52 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; @@ -1561,8 +1563,9 @@ reg = <0xd0020 0x4>; reg-names = "rev"; /* Domains (P, C): per_pwrdm, l4ls_clkdm */ - clocks = <&l4ls_clkctrl AM4_L4LS_D_CAN1_CLKCTRL 0>; - clock-names = "fck"; + clocks = <&l4ls_clkctrl AM4_L4LS_D_CAN1_CLKCTRL 0>, + <&dcan1_fck>; + clock-names = "fck", "osc"; #address-cells = <1>; #size-cells = <1>; ranges = <0x0 0xd0000 0x2000>; @@ -1570,6 +1573,8 @@ dcan1: can@0 { compatible = "ti,am4372-d_can", "ti,am3352-d_can"; reg = <0x0 0x2000>; + clocks = <&dcan1_fck>; + clock-name = "fck"; syscon-raminit = <&scm_conf 0x644 1>; interrupts = <GIC_SPI 49 IRQ_TYPE_LEVEL_HIGH>; status = "disabled"; @@ -1598,7 +1603,7 @@ ranges = <0x0 0xd8000 0x1000>; mmc2: mmc@0 { - compatible = "ti,omap4-hsmmc"; + compatible = "ti,am437-sdhci"; reg = <0x0 0x1000>; ti,needs-special-reset; dmas = <&edma 2 0>, diff --git a/arch/arm/boot/dts/am437x-sk-evm.dts b/arch/arm/boot/dts/am437x-sk-evm.dts index 4d5a7ca2e25d..08eabf0f3cbd 100644 --- a/arch/arm/boot/dts/am437x-sk-evm.dts +++ b/arch/arm/boot/dts/am437x-sk-evm.dts @@ -134,22 +134,6 @@ enable-gpios = <&gpio1 7 GPIO_ACTIVE_HIGH>; - panel-timing { - clock-frequency = <9000000>; - hactive = <480>; - vactive = <272>; - hfront-porch = <2>; - hback-porch = <2>; - hsync-len = <41>; - vfront-porch = <2>; - vback-porch = <2>; - vsync-len = <10>; - hsync-active = <0>; - vsync-active = <0>; - de-active = <1>; - pixelclk-active = <1>; - }; - port { lcd_in: endpoint { remote-endpoint = <&dpi_out>; @@ -719,7 +703,7 @@ pinctrl-1 = <&mmc3_pins_sleep>; cap-power-off-card; keep-power-in-suspend; - ti,non-removable; + non-removable; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm/boot/dts/am43x-epos-evm.dts b/arch/arm/boot/dts/am43x-epos-evm.dts index 27259fd6f741..7d4e0dffde7a 100644 --- a/arch/arm/boot/dts/am43x-epos-evm.dts +++ b/arch/arm/boot/dts/am43x-epos-evm.dts @@ -47,22 +47,6 @@ backlight = <&lcd_bl>; - panel-timing { - clock-frequency = <33000000>; - hactive = <800>; - vactive = <480>; - hfront-porch = <210>; - hback-porch = <16>; - hsync-len = <30>; - vback-porch = <10>; - vfront-porch = <22>; - vsync-len = <13>; - hsync-active = <0>; - vsync-active = <0>; - de-active = <1>; - pixelclk-active = <1>; - }; - port { lcd_in: endpoint { remote-endpoint = <&dpi_out>; diff --git a/arch/arm/boot/dts/am5729-beagleboneai.dts b/arch/arm/boot/dts/am5729-beagleboneai.dts index 9877d7709d41..4c51c6b05e64 100644 --- a/arch/arm/boot/dts/am5729-beagleboneai.dts +++ b/arch/arm/boot/dts/am5729-beagleboneai.dts @@ -505,7 +505,7 @@ &cpsw_emac0 { phy-handle = <&phy0>; - phy-mode = "rgmii"; + phy-mode = "rgmii-rxid"; }; &ocp { diff --git a/arch/arm/boot/dts/bcm-nsp.dtsi b/arch/arm/boot/dts/bcm-nsp.dtsi index da6d70f09ef1..3175266ede64 100644 --- a/arch/arm/boot/dts/bcm-nsp.dtsi +++ b/arch/arm/boot/dts/bcm-nsp.dtsi @@ -200,7 +200,7 @@ status = "disabled"; }; - dma@20000 { + dma: dma@20000 { compatible = "arm,pl330", "arm,primecell"; reg = <0x20000 0x1000>; interrupts = <GIC_SPI 47 IRQ_TYPE_LEVEL_HIGH>, @@ -215,6 +215,8 @@ clocks = <&iprocslow>; clock-names = "apb_pclk"; #dma-cells = <1>; + dma-coherent; + status = "disabled"; }; sdio: sdhci@21000 { @@ -257,10 +259,10 @@ status = "disabled"; }; - mailbox: mailbox@25000 { + mailbox: mailbox@25c00 { compatible = "brcm,iproc-fa2-mbox"; - reg = <0x25000 0x445>; - interrupts = <GIC_SPI 150 IRQ_TYPE_LEVEL_HIGH>; + reg = <0x25c00 0x400>; + interrupts = <GIC_SPI 151 IRQ_TYPE_LEVEL_HIGH>; #mbox-cells = <1>; brcm,rx-status-len = <32>; brcm,use-bcm-hdr; diff --git a/arch/arm/boot/dts/bcm47094-luxul-xwc-2000.dts b/arch/arm/boot/dts/bcm47094-luxul-xwc-2000.dts index 334325390aed..29bbecd36f65 100644 --- a/arch/arm/boot/dts/bcm47094-luxul-xwc-2000.dts +++ b/arch/arm/boot/dts/bcm47094-luxul-xwc-2000.dts @@ -17,6 +17,7 @@ }; memory { + device_type = "memory"; reg = <0x00000000 0x08000000 0x88000000 0x18000000>; }; diff --git a/arch/arm/boot/dts/bcm958522er.dts b/arch/arm/boot/dts/bcm958522er.dts index 8c388eb8a08f..7be4c4e628e0 100644 --- a/arch/arm/boot/dts/bcm958522er.dts +++ b/arch/arm/boot/dts/bcm958522er.dts @@ -58,6 +58,10 @@ /* USB 3 support needed to be complete */ +&dma { + status = "okay"; +}; + &amac0 { status = "okay"; }; diff --git a/arch/arm/boot/dts/bcm958525er.dts b/arch/arm/boot/dts/bcm958525er.dts index c339771bb22e..e58ed7e95346 100644 --- a/arch/arm/boot/dts/bcm958525er.dts +++ b/arch/arm/boot/dts/bcm958525er.dts @@ -58,6 +58,10 @@ /* USB 3 support needed to be complete */ +&dma { + status = "okay"; +}; + &amac0 { status = "okay"; }; diff --git a/arch/arm/boot/dts/bcm958525xmc.dts b/arch/arm/boot/dts/bcm958525xmc.dts index 1c72ec8288de..716da62f5788 100644 --- a/arch/arm/boot/dts/bcm958525xmc.dts +++ b/arch/arm/boot/dts/bcm958525xmc.dts @@ -58,6 +58,10 @@ /* XHCI support needed to be complete */ +&dma { + status = "okay"; +}; + &amac0 { status = "okay"; }; diff --git a/arch/arm/boot/dts/bcm958622hr.dts b/arch/arm/boot/dts/bcm958622hr.dts index 96a021cebd97..a49c2fd21f4a 100644 --- a/arch/arm/boot/dts/bcm958622hr.dts +++ b/arch/arm/boot/dts/bcm958622hr.dts @@ -58,6 +58,10 @@ /* USB 3 and SLIC support needed to be complete */ +&dma { + status = "okay"; +}; + &amac0 { status = "okay"; }; diff --git a/arch/arm/boot/dts/bcm958623hr.dts b/arch/arm/boot/dts/bcm958623hr.dts index b2c7f21d471e..dd6dff6452b8 100644 --- a/arch/arm/boot/dts/bcm958623hr.dts +++ b/arch/arm/boot/dts/bcm958623hr.dts @@ -58,6 +58,10 @@ /* USB 3 and SLIC support needed to be complete */ +&dma { + status = "okay"; +}; + &amac0 { status = "okay"; }; diff --git a/arch/arm/boot/dts/bcm958625hr.dts b/arch/arm/boot/dts/bcm958625hr.dts index 536fb24f38bb..a71371b4065e 100644 --- a/arch/arm/boot/dts/bcm958625hr.dts +++ b/arch/arm/boot/dts/bcm958625hr.dts @@ -69,6 +69,10 @@ status = "okay"; }; +&dma { + status = "okay"; +}; + &amac0 { status = "okay"; }; diff --git a/arch/arm/boot/dts/bcm958625k.dts b/arch/arm/boot/dts/bcm958625k.dts index 3fcca12d83c2..7b84b54436ed 100644 --- a/arch/arm/boot/dts/bcm958625k.dts +++ b/arch/arm/boot/dts/bcm958625k.dts @@ -48,6 +48,10 @@ }; }; +&dma { + status = "okay"; +}; + &amac0 { status = "okay"; }; diff --git a/arch/arm/boot/dts/dra7-evm-common.dtsi b/arch/arm/boot/dts/dra7-evm-common.dtsi index f89a64cbcd53..2cf6a529d4ad 100644 --- a/arch/arm/boot/dts/dra7-evm-common.dtsi +++ b/arch/arm/boot/dts/dra7-evm-common.dtsi @@ -245,26 +245,6 @@ rx-num-evt = <32>; }; -&mailbox5 { - status = "okay"; - mbox_ipu1_ipc3x: mbox_ipu1_ipc3x { - status = "okay"; - }; - mbox_dsp1_ipc3x: mbox_dsp1_ipc3x { - status = "okay"; - }; -}; - -&mailbox6 { - status = "okay"; - mbox_ipu2_ipc3x: mbox_ipu2_ipc3x { - status = "okay"; - }; - mbox_dsp2_ipc3x: mbox_dsp2_ipc3x { - status = "okay"; - }; -}; - &pcie1_rc { status = "okay"; }; diff --git a/arch/arm/boot/dts/dra7-l4.dtsi b/arch/arm/boot/dts/dra7-l4.dtsi index 62ca89551219..0c6f26605506 100644 --- a/arch/arm/boot/dts/dra7-l4.dtsi +++ b/arch/arm/boot/dts/dra7-l4.dtsi @@ -1207,9 +1207,8 @@ <SYSC_IDLE_SMART>, <SYSC_IDLE_SMART_WKUP>; /* Domains (P, C): l4per_pwrdm, l4per_clkdm */ - clocks = <&l4per_clkctrl DRA7_L4PER_TIMER4_CLKCTRL 0>, - <&timer_sys_clk_div>; - clock-names = "fck", "timer_sys_ck"; + clocks = <&l4per_clkctrl DRA7_L4PER_TIMER4_CLKCTRL 0>; + clock-names = "fck"; #address-cells = <1>; #size-cells = <1>; ranges = <0x0 0x36000 0x1000>; @@ -3352,8 +3351,8 @@ <SYSC_IDLE_SMART>, <SYSC_IDLE_SMART_WKUP>; /* Domains (P, C): ipu_pwrdm, ipu_clkdm */ - clocks = <&ipu_clkctrl DRA7_IPU_TIMER5_CLKCTRL 0>, <&timer_sys_clk_div>; - clock-names = "fck", "timer_sys_ck"; + clocks = <&ipu_clkctrl DRA7_IPU_TIMER5_CLKCTRL 0>; + clock-names = "fck"; #address-cells = <1>; #size-cells = <1>; ranges = <0x0 0x20000 0x1000>; @@ -3361,8 +3360,8 @@ timer5: timer@0 { compatible = "ti,omap5430-timer"; reg = <0x0 0x80>; - clocks = <&ipu_clkctrl DRA7_IPU_TIMER5_CLKCTRL 24>; - clock-names = "fck"; + clocks = <&ipu_clkctrl DRA7_IPU_TIMER5_CLKCTRL 24>, <&timer_sys_clk_div>; + clock-names = "fck", "timer_sys_ck"; interrupts = <GIC_SPI 36 IRQ_TYPE_LEVEL_HIGH>; }; }; @@ -3379,9 +3378,8 @@ <SYSC_IDLE_SMART>, <SYSC_IDLE_SMART_WKUP>; /* Domains (P, C): ipu_pwrdm, ipu_clkdm */ - clocks = <&ipu_clkctrl DRA7_IPU_TIMER6_CLKCTRL 0>, - <&timer_sys_clk_div>; - clock-names = "fck", "timer_sys_ck"; + clocks = <&ipu_clkctrl DRA7_IPU_TIMER6_CLKCTRL 0>; + clock-names = "fck"; #address-cells = <1>; #size-cells = <1>; ranges = <0x0 0x22000 0x1000>; @@ -3389,8 +3387,8 @@ timer6: timer@0 { compatible = "ti,omap5430-timer"; reg = <0x0 0x80>; - clocks = <&ipu_clkctrl DRA7_IPU_TIMER6_CLKCTRL 24>; - clock-names = "fck"; + clocks = <&ipu_clkctrl DRA7_IPU_TIMER6_CLKCTRL 24>, <&timer_sys_clk_div>; + clock-names = "fck", "timer_sys_ck"; interrupts = <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>; }; }; @@ -3498,8 +3496,8 @@ timer14: timer@0 { compatible = "ti,omap5430-timer"; reg = <0x0 0x80>; - clocks = <&l4per3_clkctrl DRA7_L4PER3_TIMER14_CLKCTRL 24>; - clock-names = "fck"; + clocks = <&l4per3_clkctrl DRA7_L4PER3_TIMER14_CLKCTRL 24>, <&timer_sys_clk_div>; + clock-names = "fck", "timer_sys_ck"; interrupts = <GIC_SPI 340 IRQ_TYPE_LEVEL_HIGH>; ti,timer-pwm; }; @@ -3526,8 +3524,8 @@ timer15: timer@0 { compatible = "ti,omap5430-timer"; reg = <0x0 0x80>; - clocks = <&l4per3_clkctrl DRA7_L4PER3_TIMER15_CLKCTRL 24>; - clock-names = "fck"; + clocks = <&l4per3_clkctrl DRA7_L4PER3_TIMER15_CLKCTRL 24>, <&timer_sys_clk_div>; + clock-names = "fck", "timer_sys_ck"; interrupts = <GIC_SPI 341 IRQ_TYPE_LEVEL_HIGH>; ti,timer-pwm; }; @@ -3554,8 +3552,8 @@ timer16: timer@0 { compatible = "ti,omap5430-timer"; reg = <0x0 0x80>; - clocks = <&l4per3_clkctrl DRA7_L4PER3_TIMER16_CLKCTRL 24>; - clock-names = "fck"; + clocks = <&l4per3_clkctrl DRA7_L4PER3_TIMER16_CLKCTRL 24>, <&timer_sys_clk_div>; + clock-names = "fck", "timer_sys_ck"; interrupts = <GIC_SPI 342 IRQ_TYPE_LEVEL_HIGH>; ti,timer-pwm; }; diff --git a/arch/arm/boot/dts/imx6qdl-gw551x.dtsi b/arch/arm/boot/dts/imx6qdl-gw551x.dtsi index c38e86eedcc0..8c33510c9519 100644 --- a/arch/arm/boot/dts/imx6qdl-gw551x.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw551x.dtsi @@ -110,7 +110,7 @@ simple-audio-card,frame-master = <&sound_codec>; sound_cpu: simple-audio-card,cpu { - sound-dai = <&ssi2>; + sound-dai = <&ssi1>; }; sound_codec: simple-audio-card,codec { diff --git a/arch/arm/boot/dts/imx6ul-kontron-n6x1x-s.dtsi b/arch/arm/boot/dts/imx6ul-kontron-n6x1x-s.dtsi index f05e91841202..53a25fba34f6 100644 --- a/arch/arm/boot/dts/imx6ul-kontron-n6x1x-s.dtsi +++ b/arch/arm/boot/dts/imx6ul-kontron-n6x1x-s.dtsi @@ -232,13 +232,6 @@ status = "okay"; }; -&wdog1 { - pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_wdog>; - fsl,ext-reset-output; - status = "okay"; -}; - &iomuxc { pinctrl-0 = <&pinctrl_reset_out &pinctrl_gpio>; @@ -409,10 +402,4 @@ MX6UL_PAD_NAND_DATA03__USDHC2_DATA3 0x170f9 >; }; - - pinctrl_wdog: wdoggrp { - fsl,pins = < - MX6UL_PAD_GPIO1_IO09__WDOG1_WDOG_ANY 0x30b0 - >; - }; }; diff --git a/arch/arm/boot/dts/imx6ul-kontron-n6x1x-som-common.dtsi b/arch/arm/boot/dts/imx6ul-kontron-n6x1x-som-common.dtsi index a17af4d9bfdf..61ba21a605a8 100644 --- a/arch/arm/boot/dts/imx6ul-kontron-n6x1x-som-common.dtsi +++ b/arch/arm/boot/dts/imx6ul-kontron-n6x1x-som-common.dtsi @@ -57,6 +57,13 @@ status = "okay"; }; +&wdog1 { + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_wdog>; + fsl,ext-reset-output; + status = "okay"; +}; + &iomuxc { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_reset_out>; @@ -106,4 +113,10 @@ MX6UL_PAD_SNVS_TAMPER9__GPIO5_IO09 0x1b0b0 >; }; + + pinctrl_wdog: wdoggrp { + fsl,pins = < + MX6UL_PAD_GPIO1_IO09__WDOG1_WDOG_ANY 0x18b0 + >; + }; }; diff --git a/arch/arm/boot/dts/meson.dtsi b/arch/arm/boot/dts/meson.dtsi index ae89deaa8c9c..91129dc70d83 100644 --- a/arch/arm/boot/dts/meson.dtsi +++ b/arch/arm/boot/dts/meson.dtsi @@ -11,7 +11,7 @@ #size-cells = <1>; interrupt-parent = <&gic>; - L2: l2-cache-controller@c4200000 { + L2: cache-controller@c4200000 { compatible = "arm,pl310-cache"; reg = <0xc4200000 0x1000>; cache-unified; diff --git a/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi b/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi index e39eee628afd..08a7d3ce383f 100644 --- a/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi +++ b/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi @@ -13,8 +13,10 @@ #interrupt-cells = <2>; #address-cells = <1>; #size-cells = <0>; - spi-max-frequency = <3000000>; + spi-max-frequency = <9600000>; spi-cs-high; + spi-cpol; + spi-cpha; cpcap_adc: adc { compatible = "motorola,mapphone-cpcap-adc"; diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts index 4089d97405c9..3dbcae3d60d2 100644 --- a/arch/arm/boot/dts/omap3-n900.dts +++ b/arch/arm/boot/dts/omap3-n900.dts @@ -105,6 +105,14 @@ linux,code = <SW_FRONT_PROXIMITY>; linux,can-disable; }; + + machine_cover { + label = "Machine Cover"; + gpios = <&gpio6 0 GPIO_ACTIVE_LOW>; /* 160 */ + linux,input-type = <EV_SW>; + linux,code = <SW_MACHINE_COVER>; + linux,can-disable; + }; }; isp1707: isp1707 { @@ -819,10 +827,6 @@ pinctrl-0 = <&mmc1_pins>; vmmc-supply = <&vmmc1>; bus-width = <4>; - /* For debugging, it is often good idea to remove this GPIO. - It means you can remove back cover (to reboot by removing - battery) and still use the MMC card. */ - cd-gpios = <&gpio6 0 GPIO_ACTIVE_LOW>; /* 160 */ }; /* most boards use vaux3, only some old versions use vmmc2 instead */ diff --git a/arch/arm/boot/dts/omap4-duovero-parlor.dts b/arch/arm/boot/dts/omap4-duovero-parlor.dts index 8047e8cdb3af..4548d87534e3 100644 --- a/arch/arm/boot/dts/omap4-duovero-parlor.dts +++ b/arch/arm/boot/dts/omap4-duovero-parlor.dts @@ -139,7 +139,7 @@ ethernet@gpmc { reg = <5 0 0xff>; interrupt-parent = <&gpio2>; - interrupts = <12 IRQ_TYPE_EDGE_FALLING>; /* gpio_44 */ + interrupts = <12 IRQ_TYPE_LEVEL_LOW>; /* gpio_44 */ phy-mode = "mii"; diff --git a/arch/arm/boot/dts/omap4.dtsi b/arch/arm/boot/dts/omap4.dtsi index 6c2b07f0704d..4400f5f8e099 100644 --- a/arch/arm/boot/dts/omap4.dtsi +++ b/arch/arm/boot/dts/omap4.dtsi @@ -662,6 +662,6 @@ ti,no-idle; timer@0 { assigned-clocks = <&l4_wkup_clkctrl OMAP4_TIMER1_CLKCTRL 24>; - assigned-clock-parents = <&sys_clkin_ck>; + assigned-clock-parents = <&sys_32k_ck>; }; }; diff --git a/arch/arm/boot/dts/socfpga.dtsi b/arch/arm/boot/dts/socfpga.dtsi index c2b54af417a2..78f3267d9cbf 100644 --- a/arch/arm/boot/dts/socfpga.dtsi +++ b/arch/arm/boot/dts/socfpga.dtsi @@ -726,7 +726,7 @@ }; }; - L2: l2-cache@fffef000 { + L2: cache-controller@fffef000 { compatible = "arm,pl310-cache"; reg = <0xfffef000 0x1000>; interrupts = <0 38 0x04>; diff --git a/arch/arm/boot/dts/socfpga_arria10.dtsi b/arch/arm/boot/dts/socfpga_arria10.dtsi index 3b8571b8b412..8f614c4b0e3e 100644 --- a/arch/arm/boot/dts/socfpga_arria10.dtsi +++ b/arch/arm/boot/dts/socfpga_arria10.dtsi @@ -636,7 +636,7 @@ reg = <0xffcfb100 0x80>; }; - L2: l2-cache@fffff000 { + L2: cache-controller@fffff000 { compatible = "arm,pl310-cache"; reg = <0xfffff000 0x1000>; interrupts = <0 18 IRQ_TYPE_LEVEL_HIGH>; diff --git a/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi b/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi index e6308fb76183..a88ee5294d35 100644 --- a/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi +++ b/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi @@ -100,79 +100,6 @@ }; }; - mcc { - compatible = "arm,vexpress,config-bus"; - arm,vexpress,config-bridge = <&v2m_sysreg>; - - oscclk0 { - /* MCC static memory clock */ - compatible = "arm,vexpress-osc"; - arm,vexpress-sysreg,func = <1 0>; - freq-range = <25000000 60000000>; - #clock-cells = <0>; - clock-output-names = "v2m:oscclk0"; - }; - - v2m_oscclk1: oscclk1 { - /* CLCD clock */ - compatible = "arm,vexpress-osc"; - arm,vexpress-sysreg,func = <1 1>; - freq-range = <23750000 65000000>; - #clock-cells = <0>; - clock-output-names = "v2m:oscclk1"; - }; - - v2m_oscclk2: oscclk2 { - /* IO FPGA peripheral clock */ - compatible = "arm,vexpress-osc"; - arm,vexpress-sysreg,func = <1 2>; - freq-range = <24000000 24000000>; - #clock-cells = <0>; - clock-output-names = "v2m:oscclk2"; - }; - - volt-vio { - /* Logic level voltage */ - compatible = "arm,vexpress-volt"; - arm,vexpress-sysreg,func = <2 0>; - regulator-name = "VIO"; - regulator-always-on; - label = "VIO"; - }; - - temp-mcc { - /* MCC internal operating temperature */ - compatible = "arm,vexpress-temp"; - arm,vexpress-sysreg,func = <4 0>; - label = "MCC"; - }; - - reset { - compatible = "arm,vexpress-reset"; - arm,vexpress-sysreg,func = <5 0>; - }; - - muxfpga { - compatible = "arm,vexpress-muxfpga"; - arm,vexpress-sysreg,func = <7 0>; - }; - - shutdown { - compatible = "arm,vexpress-shutdown"; - arm,vexpress-sysreg,func = <8 0>; - }; - - reboot { - compatible = "arm,vexpress-reboot"; - arm,vexpress-sysreg,func = <9 0>; - }; - - dvimode { - compatible = "arm,vexpress-dvimode"; - arm,vexpress-sysreg,func = <11 0>; - }; - }; - bus@8000000 { motherboard-bus { model = "V2M-P1"; @@ -435,6 +362,79 @@ }; }; }; + + mcc { + compatible = "arm,vexpress,config-bus"; + arm,vexpress,config-bridge = <&v2m_sysreg>; + + oscclk0 { + /* MCC static memory clock */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 0>; + freq-range = <25000000 60000000>; + #clock-cells = <0>; + clock-output-names = "v2m:oscclk0"; + }; + + v2m_oscclk1: oscclk1 { + /* CLCD clock */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 1>; + freq-range = <23750000 65000000>; + #clock-cells = <0>; + clock-output-names = "v2m:oscclk1"; + }; + + v2m_oscclk2: oscclk2 { + /* IO FPGA peripheral clock */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 2>; + freq-range = <24000000 24000000>; + #clock-cells = <0>; + clock-output-names = "v2m:oscclk2"; + }; + + volt-vio { + /* Logic level voltage */ + compatible = "arm,vexpress-volt"; + arm,vexpress-sysreg,func = <2 0>; + regulator-name = "VIO"; + regulator-always-on; + label = "VIO"; + }; + + temp-mcc { + /* MCC internal operating temperature */ + compatible = "arm,vexpress-temp"; + arm,vexpress-sysreg,func = <4 0>; + label = "MCC"; + }; + + reset { + compatible = "arm,vexpress-reset"; + arm,vexpress-sysreg,func = <5 0>; + }; + + muxfpga { + compatible = "arm,vexpress-muxfpga"; + arm,vexpress-sysreg,func = <7 0>; + }; + + shutdown { + compatible = "arm,vexpress-shutdown"; + arm,vexpress-sysreg,func = <8 0>; + }; + + reboot { + compatible = "arm,vexpress-reboot"; + arm,vexpress-sysreg,func = <9 0>; + }; + + dvimode { + compatible = "arm,vexpress-dvimode"; + arm,vexpress-sysreg,func = <11 0>; + }; + }; }; }; }; diff --git a/arch/arm/include/asm/efi.h b/arch/arm/include/asm/efi.h index 84dc0ba822f5..5dcf3c6011b7 100644 --- a/arch/arm/include/asm/efi.h +++ b/arch/arm/include/asm/efi.h @@ -87,4 +87,11 @@ static inline unsigned long efi_get_max_initrd_addr(unsigned long dram_base, return dram_base + SZ_512M; } +struct efi_arm_entry_state { + u32 cpsr_before_ebs; + u32 sctlr_before_ebs; + u32 cpsr_after_ebs; + u32 sctlr_after_ebs; +}; + #endif /* _ASM_ARM_EFI_H */ diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c index c036a4a2f8e2..a1570c8bab25 100644 --- a/arch/arm/kernel/asm-offsets.c +++ b/arch/arm/kernel/asm-offsets.c @@ -31,15 +31,6 @@ #if defined(__APCS_26__) #error Sorry, your compiler targets APCS-26 but this kernel requires APCS-32 #endif -/* - * GCC 4.8.0-4.8.2: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58854 - * miscompiles find_get_entry(), and can result in EXT3 and EXT4 - * filesystem corruption (possibly other FS too). - */ -#if defined(GCC_VERSION) && GCC_VERSION >= 40800 && GCC_VERSION < 40803 -#error Your compiler is too buggy; it is known to miscompile kernels -#error and result in filesystem corruption and oopses. -#endif int main(void) { diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c index 10499d44964a..9a79ef6b1876 100644 --- a/arch/arm/kernel/ftrace.c +++ b/arch/arm/kernel/ftrace.c @@ -84,7 +84,8 @@ static int ftrace_modify_code(unsigned long pc, unsigned long old, old = __opcode_to_mem_arm(old); if (validate) { - if (probe_kernel_read(&replaced, (void *)pc, MCOUNT_INSN_SIZE)) + if (copy_from_kernel_nofault(&replaced, (void *)pc, + MCOUNT_INSN_SIZE)) return -EFAULT; if (replaced != old) diff --git a/arch/arm/kernel/kgdb.c b/arch/arm/kernel/kgdb.c index 6a95b9296640..7bd30c0a4280 100644 --- a/arch/arm/kernel/kgdb.c +++ b/arch/arm/kernel/kgdb.c @@ -236,7 +236,7 @@ int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt) /* patch_text() only supports int-sized breakpoints */ BUILD_BUG_ON(sizeof(int) != BREAK_INSTR_SIZE); - err = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr, + err = copy_from_kernel_nofault(bpt->saved_instr, (char *)bpt->bpt_addr, BREAK_INSTR_SIZE); if (err) return err; diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index 65a3b1e75480..17d5a785df28 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -396,7 +396,7 @@ int is_valid_bugaddr(unsigned long pc) u32 insn = __opcode_to_mem_arm(BUG_INSTR_VALUE); #endif - if (probe_kernel_address((unsigned *)pc, bkpt)) + if (get_kernel_nofault(bkpt, (void *)pc)) return 0; return bkpt == insn; diff --git a/arch/arm/mach-bcm/Kconfig b/arch/arm/mach-bcm/Kconfig index 6aa938b949db..1df0ee01ee02 100644 --- a/arch/arm/mach-bcm/Kconfig +++ b/arch/arm/mach-bcm/Kconfig @@ -53,6 +53,7 @@ config ARCH_BCM_NSP select ARM_ERRATA_754322 select ARM_ERRATA_775420 select ARM_ERRATA_764369 if SMP + select ARM_TIMER_SP804 select THERMAL select THERMAL_OF help diff --git a/arch/arm/mach-imx/devices/devices-common.h b/arch/arm/mach-imx/devices/devices-common.h index 2a685adec1df..ae84c08e11fa 100644 --- a/arch/arm/mach-imx/devices/devices-common.h +++ b/arch/arm/mach-imx/devices/devices-common.h @@ -289,6 +289,6 @@ struct platform_device *__init imx_add_spi_imx( const struct spi_imx_master *pdata); struct platform_device *imx_add_imx_dma(char *name, resource_size_t iobase, - int irq, int irq_err); + int irq); struct platform_device *imx_add_imx_sdma(char *name, resource_size_t iobase, int irq, struct sdma_platform_data *pdata); diff --git a/arch/arm/mach-imx/devices/platform-gpio-mxc.c b/arch/arm/mach-imx/devices/platform-gpio-mxc.c index 78628ef12672..355de845224c 100644 --- a/arch/arm/mach-imx/devices/platform-gpio-mxc.c +++ b/arch/arm/mach-imx/devices/platform-gpio-mxc.c @@ -24,7 +24,8 @@ struct platform_device *__init mxc_register_gpio(char *name, int id, .flags = IORESOURCE_IRQ, }, }; + unsigned int nres; - return platform_device_register_resndata(&mxc_aips_bus, - name, id, res, ARRAY_SIZE(res), NULL, 0); + nres = irq_high ? ARRAY_SIZE(res) : ARRAY_SIZE(res) - 1; + return platform_device_register_resndata(&mxc_aips_bus, name, id, res, nres, NULL, 0); } diff --git a/arch/arm/mach-imx/devices/platform-imx-dma.c b/arch/arm/mach-imx/devices/platform-imx-dma.c index 26b47b36257b..12656f24ad0d 100644 --- a/arch/arm/mach-imx/devices/platform-imx-dma.c +++ b/arch/arm/mach-imx/devices/platform-imx-dma.c @@ -6,7 +6,7 @@ #include "devices-common.h" struct platform_device __init __maybe_unused *imx_add_imx_dma(char *name, - resource_size_t iobase, int irq, int irq_err) + resource_size_t iobase, int irq) { struct resource res[] = { { @@ -17,10 +17,6 @@ struct platform_device __init __maybe_unused *imx_add_imx_dma(char *name, .start = irq, .end = irq, .flags = IORESOURCE_IRQ, - }, { - .start = irq_err, - .end = irq_err, - .flags = IORESOURCE_IRQ, }, }; diff --git a/arch/arm/mach-imx/mm-imx21.c b/arch/arm/mach-imx/mm-imx21.c index 50a2edac8513..b834026e4615 100644 --- a/arch/arm/mach-imx/mm-imx21.c +++ b/arch/arm/mach-imx/mm-imx21.c @@ -78,8 +78,7 @@ void __init imx21_soc_init(void) mxc_register_gpio("imx21-gpio", 5, MX21_GPIO6_BASE_ADDR, SZ_256, MX21_INT_GPIO, 0); pinctrl_provide_dummies(); - imx_add_imx_dma("imx21-dma", MX21_DMA_BASE_ADDR, - MX21_INT_DMACH0, 0); /* No ERR irq */ + imx_add_imx_dma("imx21-dma", MX21_DMA_BASE_ADDR, MX21_INT_DMACH0); platform_device_register_simple("imx21-audmux", 0, imx21_audmux_res, ARRAY_SIZE(imx21_audmux_res)); } diff --git a/arch/arm/mach-imx/mm-imx27.c b/arch/arm/mach-imx/mm-imx27.c index 4e4125140025..2717614f101d 100644 --- a/arch/arm/mach-imx/mm-imx27.c +++ b/arch/arm/mach-imx/mm-imx27.c @@ -79,8 +79,7 @@ void __init imx27_soc_init(void) mxc_register_gpio("imx21-gpio", 5, MX27_GPIO6_BASE_ADDR, SZ_256, MX27_INT_GPIO, 0); pinctrl_provide_dummies(); - imx_add_imx_dma("imx27-dma", MX27_DMA_BASE_ADDR, - MX27_INT_DMACH0, 0); /* No ERR irq */ + imx_add_imx_dma("imx27-dma", MX27_DMA_BASE_ADDR, MX27_INT_DMACH0); /* imx27 has the imx21 type audmux */ platform_device_register_simple("imx21-audmux", 0, imx27_audmux_res, ARRAY_SIZE(imx27_audmux_res)); diff --git a/arch/arm/mach-imx/pm-imx5.c b/arch/arm/mach-imx/pm-imx5.c index f057df813f83..e9962b48e30c 100644 --- a/arch/arm/mach-imx/pm-imx5.c +++ b/arch/arm/mach-imx/pm-imx5.c @@ -295,14 +295,14 @@ static int __init imx_suspend_alloc_ocram( if (!ocram_pool) { pr_warn("%s: ocram pool unavailable!\n", __func__); ret = -ENODEV; - goto put_node; + goto put_device; } ocram_base = gen_pool_alloc(ocram_pool, size); if (!ocram_base) { pr_warn("%s: unable to alloc ocram!\n", __func__); ret = -ENOMEM; - goto put_node; + goto put_device; } phys = gen_pool_virt_to_phys(ocram_pool, ocram_base); @@ -312,6 +312,8 @@ static int __init imx_suspend_alloc_ocram( if (virt_out) *virt_out = virt; +put_device: + put_device(&pdev->dev); put_node: of_node_put(node); diff --git a/arch/arm/mach-imx/pm-imx6.c b/arch/arm/mach-imx/pm-imx6.c index dd34dff13762..40c74b4c4d73 100644 --- a/arch/arm/mach-imx/pm-imx6.c +++ b/arch/arm/mach-imx/pm-imx6.c @@ -493,14 +493,14 @@ static int __init imx6q_suspend_init(const struct imx6_pm_socdata *socdata) if (!ocram_pool) { pr_warn("%s: ocram pool unavailable!\n", __func__); ret = -ENODEV; - goto put_node; + goto put_device; } ocram_base = gen_pool_alloc(ocram_pool, MX6Q_SUSPEND_OCRAM_SIZE); if (!ocram_base) { pr_warn("%s: unable to alloc ocram!\n", __func__); ret = -ENOMEM; - goto put_node; + goto put_device; } ocram_pbase = gen_pool_virt_to_phys(ocram_pool, ocram_base); @@ -523,7 +523,7 @@ static int __init imx6q_suspend_init(const struct imx6_pm_socdata *socdata) ret = imx6_pm_get_base(&pm_info->mmdc_base, socdata->mmdc_compat); if (ret) { pr_warn("%s: failed to get mmdc base %d!\n", __func__, ret); - goto put_node; + goto put_device; } ret = imx6_pm_get_base(&pm_info->src_base, socdata->src_compat); @@ -570,7 +570,7 @@ static int __init imx6q_suspend_init(const struct imx6_pm_socdata *socdata) &imx6_suspend, MX6Q_SUSPEND_OCRAM_SIZE - sizeof(*pm_info)); - goto put_node; + goto put_device; pl310_cache_map_failed: iounmap(pm_info->gpc_base.vbase); @@ -580,6 +580,8 @@ iomuxc_map_failed: iounmap(pm_info->src_base.vbase); src_map_failed: iounmap(pm_info->mmdc_base.vbase); +put_device: + put_device(&pdev->dev); put_node: of_node_put(node); diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c index 82706af307de..15b29a179c8a 100644 --- a/arch/arm/mach-omap2/omap_hwmod.c +++ b/arch/arm/mach-omap2/omap_hwmod.c @@ -3435,7 +3435,7 @@ static int omap_hwmod_allocate_module(struct device *dev, struct omap_hwmod *oh, regs = ioremap(data->module_pa, data->module_size); if (!regs) - return -ENOMEM; + goto out_free_sysc; } /* @@ -3445,13 +3445,13 @@ static int omap_hwmod_allocate_module(struct device *dev, struct omap_hwmod *oh, if (oh->class->name && strcmp(oh->class->name, data->name)) { class = kmemdup(oh->class, sizeof(*oh->class), GFP_KERNEL); if (!class) - return -ENOMEM; + goto out_unmap; } if (list_empty(&oh->slave_ports)) { oi = kcalloc(1, sizeof(*oi), GFP_KERNEL); if (!oi) - return -ENOMEM; + goto out_free_class; /* * Note that we assume interconnect interface clocks will be @@ -3478,6 +3478,14 @@ static int omap_hwmod_allocate_module(struct device *dev, struct omap_hwmod *oh, spin_unlock_irqrestore(&oh->_lock, flags); return 0; + +out_free_class: + kfree(class); +out_unmap: + iounmap(regs); +out_free_sysc: + kfree(sysc); + return -ENOMEM; } static const struct omap_hwmod_reset omap24xx_reset_quirks[] = { @@ -3489,7 +3497,7 @@ static const struct omap_hwmod_reset dra7_reset_quirks[] = { }; static const struct omap_hwmod_reset omap_reset_quirks[] = { - { .match = "dss", .len = 3, .reset = omap_dss_reset, }, + { .match = "dss_core", .len = 8, .reset = omap_dss_reset, }, { .match = "hdq1w", .len = 5, .reset = omap_hdq1w_reset, }, { .match = "i2c", .len = 3, .reset = omap_i2c_reset, }, { .match = "wd_timer", .len = 8, .reset = omap2_wd_timer_reset, }, diff --git a/arch/arm/mach-sti/board-dt.c b/arch/arm/mach-sti/board-dt.c index dcb98937fcf5..ffecbf29646f 100644 --- a/arch/arm/mach-sti/board-dt.c +++ b/arch/arm/mach-sti/board-dt.c @@ -20,14 +20,6 @@ static const char *const stih41x_dt_match[] __initconst = { NULL }; -static void sti_l2_write_sec(unsigned long val, unsigned reg) -{ - /* - * We can't write to secure registers as we are in non-secure - * mode, until we have some SMI service available. - */ -} - DT_MACHINE_START(STM, "STi SoC with Flattened Device Tree") .dt_compat = stih41x_dt_match, .l2c_aux_val = L2C_AUX_CTRL_SHARED_OVERRIDE | @@ -36,5 +28,4 @@ DT_MACHINE_START(STM, "STi SoC with Flattened Device Tree") L2C_AUX_CTRL_WAY_SIZE(4), .l2c_aux_mask = 0xc0000fff, .smp = smp_ops(sti_smp_ops), - .l2c_write_sec = sti_l2_write_sec, MACHINE_END diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c index 84718eddae60..81a627e6e1c5 100644 --- a/arch/arm/mm/alignment.c +++ b/arch/arm/mm/alignment.c @@ -774,7 +774,7 @@ static int alignment_get_arm(struct pt_regs *regs, u32 *ip, u32 *inst) if (user_mode(regs)) fault = get_user(instr, ip); else - fault = probe_kernel_address(ip, instr); + fault = get_kernel_nofault(instr, ip); *inst = __mem_to_opcode_arm(instr); @@ -789,7 +789,7 @@ static int alignment_get_thumb(struct pt_regs *regs, u16 *ip, u16 *inst) if (user_mode(regs)) fault = get_user(instr, ip); else - fault = probe_kernel_address(ip, instr); + fault = get_kernel_nofault(instr, ip); *inst = __mem_to_opcode_thumb16(instr); diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index fd4e1ce1daf9..e93145d72c26 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -241,7 +241,6 @@ static int __init fdt_find_hyper_node(unsigned long node, const char *uname, * see Documentation/devicetree/bindings/arm/xen.txt for the * documentation of the Xen Device Tree format. */ -#define GRANT_TABLE_PHYSADDR 0 void __init xen_early_init(void) { of_scan_flat_dt(fdt_find_hyper_node, NULL); diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 31380da53689..66dc41fd49f2 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1518,9 +1518,9 @@ config ARM64_PTR_AUTH default y depends on !KVM || ARM64_VHE depends on (CC_HAS_SIGN_RETURN_ADDRESS || CC_HAS_BRANCH_PROT_PAC_RET) && AS_HAS_PAC - # GCC 9.1 and later inserts a .note.gnu.property section note for PAC + # Modern compilers insert a .note.gnu.property section note for PAC # which is only understood by binutils starting with version 2.33.1. - depends on !CC_IS_GCC || GCC_VERSION < 90100 || LD_VERSION >= 233010000 + depends on LD_IS_LLD || LD_VERSION >= 233010000 || (CC_IS_GCC && GCC_VERSION < 90100) depends on !CC_IS_CLANG || AS_HAS_CFI_NEGATE_RA_STATE depends on (!FUNCTION_GRAPH_TRACER || DYNAMIC_FTRACE_WITH_REGS) help @@ -1564,7 +1564,7 @@ config CC_HAS_SIGN_RETURN_ADDRESS def_bool $(cc-option,-msign-return-address=all) config AS_HAS_PAC - def_bool $(as-option,-Wa$(comma)-march=armv8.3-a) + def_bool $(cc-option,-Wa$(comma)-march=armv8.3-a) config AS_HAS_CFI_NEGATE_RA_STATE def_bool $(as-instr,.cfi_startproc\n.cfi_negate_ra_state\n.cfi_endproc\n) @@ -1630,6 +1630,8 @@ config ARM64_BTI_KERNEL depends on CC_HAS_BRANCH_PROT_PAC_RET_BTI # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94697 depends on !CC_IS_GCC || GCC_VERSION >= 100100 + # https://reviews.llvm.org/rGb8ae3fdfa579dbf366b1bb1cbfdbf8c51db7fa55 + depends on !CC_IS_CLANG || CLANG_VERSION >= 100001 depends on !(CC_IS_CLANG && GCOV_KERNEL) depends on (!FUNCTION_GRAPH_TRACER || DYNAMIC_FTRACE_WITH_REGS) help diff --git a/arch/arm64/Kconfig.debug b/arch/arm64/Kconfig.debug index cdf7ec0b975e..265c4461031f 100644 --- a/arch/arm64/Kconfig.debug +++ b/arch/arm64/Kconfig.debug @@ -8,21 +8,6 @@ config PID_IN_CONTEXTIDR instructions during context switch. Say Y here only if you are planning to use hardware trace tools with this kernel. -config ARM64_RANDOMIZE_TEXT_OFFSET - bool "Randomize TEXT_OFFSET at build time" - help - Say Y here if you want the image load offset (AKA TEXT_OFFSET) - of the kernel to be randomized at build-time. When selected, - this option will cause TEXT_OFFSET to be randomized upon any - build of the kernel, and the offset will be reflected in the - text_offset field of the resulting Image. This can be used to - fuzz-test bootloaders which respect text_offset. - - This option is intended for bootloader and/or kernel testing - only. Bootloaders must make no assumptions regarding the value - of TEXT_OFFSET and platforms must not require a specific - value. - config DEBUG_EFI depends on EFI && DEBUG_INFO bool "UEFI debugging" diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 76359cfb328a..70f5905954dd 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -121,13 +121,7 @@ endif head-y := arch/arm64/kernel/head.o # The byte offset of the kernel image in RAM from the start of RAM. -ifeq ($(CONFIG_ARM64_RANDOMIZE_TEXT_OFFSET), y) -TEXT_OFFSET := $(shell awk "BEGIN {srand(); printf \"0x%06x\n\", \ - int(2 * 1024 * 1024 / (2 ^ $(CONFIG_ARM64_PAGE_SHIFT)) * \ - rand()) * (2 ^ $(CONFIG_ARM64_PAGE_SHIFT))}") -else TEXT_OFFSET := 0x0 -endif ifeq ($(CONFIG_KASAN_SW_TAGS), y) KASAN_SHADOW_SCALE_SHIFT := 4 @@ -143,7 +137,7 @@ export TEXT_OFFSET core-y += arch/arm64/ libs-y := arch/arm64/lib/ $(libs-y) -core-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a +libs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a # Default target when executing plain make boot := arch/arm64/boot diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi index d1fc9c2055f4..9498d1de730c 100644 --- a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi +++ b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi @@ -77,7 +77,7 @@ method = "smc"; }; - intc: intc@fffc1000 { + intc: interrupt-controller@fffc1000 { compatible = "arm,gic-400", "arm,cortex-a15-gic"; #interrupt-cells = <3>; interrupt-controller; @@ -302,7 +302,7 @@ status = "disabled"; }; - nand: nand@ffb90000 { + nand: nand-controller@ffb90000 { #address-cells = <1>; #size-cells = <0>; compatible = "altr,socfpga-denali-nand"; @@ -445,7 +445,7 @@ clock-names = "timer"; }; - uart0: serial0@ffc02000 { + uart0: serial@ffc02000 { compatible = "snps,dw-apb-uart"; reg = <0xffc02000 0x100>; interrupts = <0 108 4>; @@ -456,7 +456,7 @@ status = "disabled"; }; - uart1: serial1@ffc02100 { + uart1: serial@ffc02100 { compatible = "snps,dw-apb-uart"; reg = <0xffc02100 0x100>; interrupts = <0 109 4>; diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts index f6c4a15079d3..feadd21bc0dc 100644 --- a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts +++ b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts @@ -155,6 +155,7 @@ }; &qspi { + status = "okay"; flash@0 { #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts index 9946515b8afd..c07966740e14 100644 --- a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts +++ b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts @@ -188,6 +188,7 @@ }; &qspi { + status = "okay"; flash@0 { #address-cells = <1>; #size-cells = <1>; @@ -211,12 +212,12 @@ qspi_boot: partition@0 { label = "Boot and fpga data"; - reg = <0x0 0x034B0000>; + reg = <0x0 0x03FE0000>; }; - qspi_rootfs: partition@4000000 { + qspi_rootfs: partition@3FE0000 { label = "Root Filesystem - JFFS2"; - reg = <0x034B0000 0x0EB50000>; + reg = <0x03FE0000 0x0C020000>; }; }; }; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-libretech-ac.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-libretech-ac.dts index 6a226faab183..9e43f4dca90d 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-libretech-ac.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-libretech-ac.dts @@ -10,7 +10,7 @@ #include <dt-bindings/input/input.h> #include <dt-bindings/sound/meson-aiu.h> -#include "meson-gxl-s905x.dtsi" +#include "meson-gxl-s805x.dtsi" / { compatible = "libretech,aml-s805x-ac", "amlogic,s805x", diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-p241.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-p241.dts index 867e30f1d62b..eb7f5a3fefd4 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-p241.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-p241.dts @@ -9,7 +9,7 @@ #include <dt-bindings/input/input.h> -#include "meson-gxl-s905x.dtsi" +#include "meson-gxl-s805x.dtsi" / { compatible = "amlogic,p241", "amlogic,s805x", "amlogic,meson-gxl"; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s805x.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl-s805x.dtsi new file mode 100644 index 000000000000..f9d705648426 --- /dev/null +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s805x.dtsi @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) +/* + * Copyright (c) 2020 BayLibre SAS + * Author: Neil Armstrong <narmstrong@baylibre.com> + */ + +#include "meson-gxl-s905x.dtsi" + +/ { + compatible = "amlogic,s805x", "amlogic,meson-gxl"; +}; + +/* The S805X Package doesn't seem to handle the 744MHz OPP correctly */ +&mali { + assigned-clocks = <&clkc CLKID_MALI_0_SEL>, + <&clkc CLKID_MALI_0>, + <&clkc CLKID_MALI>; /* Glitch free mux */ + assigned-clock-parents = <&clkc CLKID_FCLK_DIV3>, + <0>, /* Do Nothing */ + <&clkc CLKID_MALI_0>; + assigned-clock-rates = <0>, /* Do Nothing */ + <666666666>, + <0>; /* Do Nothing */ +}; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi index fc59c8534c0f..6c8b189884ca 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi @@ -337,6 +337,11 @@ }; }; +&hwrng { + clocks = <&clkc CLKID_RNG0>; + clock-names = "core"; +}; + &i2c_A { clocks = <&clkc CLKID_I2C>; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi index fb0137a8611c..94911b1707ef 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi @@ -136,7 +136,7 @@ ldo1_reg: LDO1 { regulator-name = "LDO1"; - regulator-min-microvolt = <3000000>; + regulator-min-microvolt = <1600000>; regulator-max-microvolt = <3300000>; regulator-boot-on; regulator-always-on; @@ -144,7 +144,7 @@ ldo2_reg: LDO2 { regulator-name = "LDO2"; - regulator-min-microvolt = <900000>; + regulator-min-microvolt = <800000>; regulator-max-microvolt = <900000>; regulator-boot-on; regulator-always-on; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-evk.dts b/arch/arm64/boot/dts/freescale/imx8mm-evk.dts index e5ec8322796d..0f1d7f8aeac4 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx8mm-evk.dts @@ -208,7 +208,7 @@ ldo1_reg: LDO1 { regulator-name = "LDO1"; - regulator-min-microvolt = <3000000>; + regulator-min-microvolt = <1600000>; regulator-max-microvolt = <3300000>; regulator-boot-on; regulator-always-on; @@ -216,7 +216,7 @@ ldo2_reg: LDO2 { regulator-name = "LDO2"; - regulator-min-microvolt = <900000>; + regulator-min-microvolt = <800000>; regulator-max-microvolt = <900000>; regulator-boot-on; regulator-always-on; diff --git a/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts b/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts index d07e0e6a00cc..a1e5483dbbbe 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts @@ -113,7 +113,7 @@ ldo1_reg: LDO1 { regulator-name = "LDO1"; - regulator-min-microvolt = <3000000>; + regulator-min-microvolt = <1600000>; regulator-max-microvolt = <3300000>; regulator-boot-on; regulator-always-on; @@ -121,7 +121,7 @@ ldo2_reg: LDO2 { regulator-name = "LDO2"; - regulator-min-microvolt = <900000>; + regulator-min-microvolt = <800000>; regulator-max-microvolt = <900000>; regulator-boot-on; regulator-always-on; diff --git a/arch/arm64/boot/dts/intel/socfpga_agilex_socdk.dts b/arch/arm64/boot/dts/intel/socfpga_agilex_socdk.dts index 51d948323bfd..92f478def723 100644 --- a/arch/arm64/boot/dts/intel/socfpga_agilex_socdk.dts +++ b/arch/arm64/boot/dts/intel/socfpga_agilex_socdk.dts @@ -98,6 +98,7 @@ }; &qspi { + status = "okay"; flash@0 { #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts b/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts index c8243da71041..eb01cc96ba7a 100644 --- a/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts +++ b/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts @@ -454,10 +454,7 @@ status = "okay"; phy-mode = "2500base-x"; phys = <&cp1_comphy5 2>; - fixed-link { - speed = <2500>; - full-duplex; - }; + managed = "in-band-status"; }; &cp1_spi1 { diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index 883e8bace3ed..2ca7ba69c318 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -194,7 +194,7 @@ CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_ACPI=y CONFIG_PCI_AARDVARK=y CONFIG_PCI_TEGRA=y -CONFIG_PCIE_RCAR=y +CONFIG_PCIE_RCAR_HOST=y CONFIG_PCI_HOST_GENERIC=y CONFIG_PCI_XGENE=y CONFIG_PCIE_ALTERA=y diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h index 5e5dc05d63a0..12f0eb56a1cc 100644 --- a/arch/arm64/include/asm/alternative.h +++ b/arch/arm64/include/asm/alternative.h @@ -73,11 +73,11 @@ static inline void apply_alternatives_module(void *start, size_t length) { } ".pushsection .altinstructions,\"a\"\n" \ ALTINSTR_ENTRY(feature) \ ".popsection\n" \ - ".pushsection .altinstr_replacement, \"a\"\n" \ + ".subsection 1\n" \ "663:\n\t" \ newinstr "\n" \ "664:\n\t" \ - ".popsection\n\t" \ + ".previous\n\t" \ ".org . - (664b-663b) + (662b-661b)\n\t" \ ".org . - (662b-661b) + (664b-663b)\n" \ ".endif\n" @@ -117,9 +117,9 @@ static inline void apply_alternatives_module(void *start, size_t length) { } 662: .pushsection .altinstructions, "a" altinstruction_entry 661b, 663f, \cap, 662b-661b, 664f-663f .popsection - .pushsection .altinstr_replacement, "ax" + .subsection 1 663: \insn2 -664: .popsection +664: .previous .org . - (664b-663b) + (662b-661b) .org . - (662b-661b) + (664b-663b) .endif @@ -160,7 +160,7 @@ static inline void apply_alternatives_module(void *start, size_t length) { } .pushsection .altinstructions, "a" altinstruction_entry 663f, 661f, \cap, 664f-663f, 662f-661f .popsection - .pushsection .altinstr_replacement, "ax" + .subsection 1 .align 2 /* So GAS knows label 661 is suitably aligned */ 661: .endm @@ -179,9 +179,9 @@ static inline void apply_alternatives_module(void *start, size_t length) { } .macro alternative_else 662: .if .Lasm_alt_mode==0 - .pushsection .altinstr_replacement, "ax" + .subsection 1 .else - .popsection + .previous .endif 663: .endm @@ -192,7 +192,7 @@ static inline void apply_alternatives_module(void *start, size_t length) { } .macro alternative_endif 664: .if .Lasm_alt_mode==0 - .popsection + .previous .endif .org . - (664b-663b) + (662b-661b) .org . - (662b-661b) + (664b-663b) diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h index a358e97572c1..6647ae4f0231 100644 --- a/arch/arm64/include/asm/arch_gicv3.h +++ b/arch/arm64/include/asm/arch_gicv3.h @@ -109,7 +109,7 @@ static inline u32 gic_read_pmr(void) return read_sysreg_s(SYS_ICC_PMR_EL1); } -static inline void gic_write_pmr(u32 val) +static __always_inline void gic_write_pmr(u32 val) { write_sysreg_s(val, SYS_ICC_PMR_EL1); } diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h index 7ae54d7d333a..9f0ec21d6327 100644 --- a/arch/arm64/include/asm/arch_timer.h +++ b/arch/arm64/include/asm/arch_timer.h @@ -58,6 +58,7 @@ struct arch_timer_erratum_workaround { u64 (*read_cntvct_el0)(void); int (*set_next_event_phys)(unsigned long, struct clock_event_device *); int (*set_next_event_virt)(unsigned long, struct clock_event_device *); + bool disable_compat_vdso; }; DECLARE_PER_CPU(const struct arch_timer_erratum_workaround *, diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 5d1f4ae42799..f7c3d1ff091d 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -675,7 +675,7 @@ static inline bool system_supports_generic_auth(void) cpus_have_const_cap(ARM64_HAS_GENERIC_AUTH); } -static inline bool system_uses_irq_prio_masking(void) +static __always_inline bool system_uses_irq_prio_masking(void) { return IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) && cpus_have_const_cap(ARM64_HAS_IRQ_PRIO_MASKING); diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index a87a93f67671..7219cddeba66 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -86,6 +86,7 @@ #define QCOM_CPU_PART_FALKOR 0xC00 #define QCOM_CPU_PART_KRYO 0x200 #define QCOM_CPU_PART_KRYO_3XX_SILVER 0x803 +#define QCOM_CPU_PART_KRYO_4XX_GOLD 0x804 #define QCOM_CPU_PART_KRYO_4XX_SILVER 0x805 #define NVIDIA_CPU_PART_DENVER 0x003 @@ -114,6 +115,7 @@ #define MIDR_QCOM_FALKOR MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR) #define MIDR_QCOM_KRYO MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO) #define MIDR_QCOM_KRYO_3XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_3XX_SILVER) +#define MIDR_QCOM_KRYO_4XX_GOLD MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_4XX_GOLD) #define MIDR_QCOM_KRYO_4XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_4XX_SILVER) #define MIDR_NVIDIA_DENVER MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_DENVER) #define MIDR_NVIDIA_CARMEL MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_CARMEL) diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h index e5ceea213e39..0b298f48f5bf 100644 --- a/arch/arm64/include/asm/debug-monitors.h +++ b/arch/arm64/include/asm/debug-monitors.h @@ -109,6 +109,8 @@ void disable_debug_monitors(enum dbg_active_el el); void user_rewind_single_step(struct task_struct *task); void user_fastforward_single_step(struct task_struct *task); +void user_regs_reset_single_step(struct user_pt_regs *regs, + struct task_struct *task); void kernel_enable_single_step(struct pt_regs *regs); void kernel_disable_single_step(void); diff --git a/arch/arm64/include/asm/linkage.h b/arch/arm64/include/asm/linkage.h index 81fefd2a1d02..ba89a9af820a 100644 --- a/arch/arm64/include/asm/linkage.h +++ b/arch/arm64/include/asm/linkage.h @@ -12,7 +12,6 @@ * instead. */ #define BTI_C hint 34 ; -#define BTI_J hint 36 ; /* * When using in-kernel BTI we need to ensure that PCS-conformant assembly @@ -43,11 +42,6 @@ SYM_START(name, SYM_L_WEAK, SYM_A_NONE) \ BTI_C -#define SYM_INNER_LABEL(name, linkage) \ - .type name SYM_T_NONE ASM_NL \ - SYM_ENTRY(name, linkage, SYM_A_NONE) \ - BTI_J - #endif /* diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h index 68140fdd89d6..8444df000181 100644 --- a/arch/arm64/include/asm/mmu.h +++ b/arch/arm64/include/asm/mmu.h @@ -19,6 +19,9 @@ typedef struct { atomic64_t id; +#ifdef CONFIG_COMPAT + void *sigpage; +#endif void *vdso; unsigned long flags; } mm_context_t; diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h index 2e7e0f452301..4d867c6446c4 100644 --- a/arch/arm64/include/asm/pgtable-prot.h +++ b/arch/arm64/include/asm/pgtable-prot.h @@ -67,7 +67,7 @@ extern bool arm64_use_ng_mappings; #define PAGE_HYP __pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_HYP_XN) #define PAGE_HYP_EXEC __pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY) #define PAGE_HYP_RO __pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY | PTE_HYP_XN) -#define PAGE_HYP_DEVICE __pgprot(PROT_DEVICE_nGnRE | PTE_HYP) +#define PAGE_HYP_DEVICE __pgprot(_PROT_DEFAULT | PTE_ATTRINDX(MT_DEVICE_nGnRE) | PTE_HYP | PTE_HYP_XN) #define PAGE_S2_MEMATTR(attr) \ ({ \ diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 6dbd267ab931..758e2d1577d0 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -416,7 +416,7 @@ static inline pmd_t pmd_mkdevmap(pmd_t pmd) __pgprot((pgprot_val(prot) & ~(mask)) | (bits)) #define pgprot_nx(prot) \ - __pgprot_modify(prot, 0, PTE_PXN) + __pgprot_modify(prot, PTE_MAYBE_GP, PTE_PXN) /* * Mark the prot value as uncacheable and unbufferable. diff --git a/arch/arm64/include/asm/syscall.h b/arch/arm64/include/asm/syscall.h index 65299a2dcf9c..cfc0672013f6 100644 --- a/arch/arm64/include/asm/syscall.h +++ b/arch/arm64/include/asm/syscall.h @@ -34,6 +34,10 @@ static inline long syscall_get_error(struct task_struct *task, struct pt_regs *regs) { unsigned long error = regs->regs[0]; + + if (is_compat_thread(task_thread_info(task))) + error = sign_extend64(error, 31); + return IS_ERR_VALUE(error) ? error : 0; } @@ -47,7 +51,13 @@ static inline void syscall_set_return_value(struct task_struct *task, struct pt_regs *regs, int error, long val) { - regs->regs[0] = (long) error ? error : val; + if (error) + val = error; + + if (is_compat_thread(task_thread_info(task))) + val = lower_32_bits(val); + + regs->regs[0] = val; } #define SYSCALL_MAX_ARGS 6 diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index 6ea8b6a26ae9..5e784e16ee89 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -93,6 +93,7 @@ void arch_release_task_struct(struct task_struct *tsk); #define _TIF_SYSCALL_EMU (1 << TIF_SYSCALL_EMU) #define _TIF_UPROBE (1 << TIF_UPROBE) #define _TIF_FSCHECK (1 << TIF_FSCHECK) +#define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP) #define _TIF_32BIT (1 << TIF_32BIT) #define _TIF_SVE (1 << TIF_SVE) diff --git a/arch/arm64/include/asm/vdso/clocksource.h b/arch/arm64/include/asm/vdso/clocksource.h index df6ea65c1dec..b054d9febfb5 100644 --- a/arch/arm64/include/asm/vdso/clocksource.h +++ b/arch/arm64/include/asm/vdso/clocksource.h @@ -2,7 +2,10 @@ #ifndef __ASM_VDSOCLOCKSOURCE_H #define __ASM_VDSOCLOCKSOURCE_H -#define VDSO_ARCH_CLOCKMODES \ - VDSO_CLOCKMODE_ARCHTIMER +#define VDSO_ARCH_CLOCKMODES \ + /* vdso clocksource for both 32 and 64bit tasks */ \ + VDSO_CLOCKMODE_ARCHTIMER, \ + /* vdso clocksource for 64bit tasks only */ \ + VDSO_CLOCKMODE_ARCHTIMER_NOCOMPAT #endif diff --git a/arch/arm64/include/asm/vdso/compat_gettimeofday.h b/arch/arm64/include/asm/vdso/compat_gettimeofday.h index b6907ae78e53..9a625e8947ff 100644 --- a/arch/arm64/include/asm/vdso/compat_gettimeofday.h +++ b/arch/arm64/include/asm/vdso/compat_gettimeofday.h @@ -111,7 +111,7 @@ static __always_inline u64 __arch_get_hw_counter(s32 clock_mode) * update. Return something. Core will do another round and then * see the mode change and fallback to the syscall. */ - if (clock_mode == VDSO_CLOCKMODE_NONE) + if (clock_mode != VDSO_CLOCKMODE_ARCHTIMER) return 0; /* @@ -152,6 +152,12 @@ static __always_inline const struct vdso_data *__arch_get_vdso_data(void) return ret; } +static inline bool vdso_clocksource_ok(const struct vdso_data *vd) +{ + return vd->clock_mode == VDSO_CLOCKMODE_ARCHTIMER; +} +#define vdso_clocksource_ok vdso_clocksource_ok + #endif /* !__ASSEMBLY__ */ #endif /* __ASM_VDSO_GETTIMEOFDAY_H */ diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 151f28521f1e..a561cbb91d4d 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -29,9 +29,7 @@ $(obj)/%.stub.o: $(obj)/%.o FORCE obj-$(CONFIG_COMPAT) += sys32.o signal32.o \ sys_compat.o -ifneq ($(CONFIG_COMPAT_VDSO), y) obj-$(CONFIG_COMPAT) += sigreturn32.o -endif obj-$(CONFIG_KUSER_HELPERS) += kuser32.o obj-$(CONFIG_FUNCTION_TRACER) += ftrace.o entry-ftrace.o obj-$(CONFIG_MODULES) += module.o diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c index d1757ef1b1e7..73039949b5ce 100644 --- a/arch/arm64/kernel/alternative.c +++ b/arch/arm64/kernel/alternative.c @@ -43,20 +43,8 @@ bool alternative_is_applied(u16 cpufeature) */ static bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc) { - unsigned long replptr; - - if (kernel_text_address(pc)) - return true; - - replptr = (unsigned long)ALT_REPL_PTR(alt); - if (pc >= replptr && pc <= (replptr + alt->alt_len)) - return false; - - /* - * Branching into *another* alternate sequence is doomed, and - * we're not even trying to fix it up. - */ - BUG(); + unsigned long replptr = (unsigned long)ALT_REPL_PTR(alt); + return !(pc >= replptr && pc <= (replptr + alt->alt_len)); } #define align_down(x, a) ((unsigned long)(x) & ~(((unsigned long)(a)) - 1)) diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index ad06d6802d2e..79728bfb5351 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -460,6 +460,8 @@ static const struct midr_range arm64_ssb_cpus[] = { MIDR_ALL_VERSIONS(MIDR_CORTEX_A53), MIDR_ALL_VERSIONS(MIDR_CORTEX_A55), MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53), + MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER), + MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER), {}, }; @@ -470,12 +472,7 @@ static bool has_cortex_a76_erratum_1463225(const struct arm64_cpu_capabilities *entry, int scope) { - u32 midr = read_cpuid_id(); - /* Cortex-A76 r0p0 - r3p1 */ - struct midr_range range = MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 1); - - WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible()); - return is_midr_in_range(midr, &range) && is_kernel_in_hyp_mode(); + return is_affected_midr_range_list(entry, scope) && is_kernel_in_hyp_mode(); } #endif @@ -726,6 +723,8 @@ static const struct midr_range erratum_1418040_list[] = { MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 1), /* Neoverse-N1 r0p0 to r3p1 */ MIDR_RANGE(MIDR_NEOVERSE_N1, 0, 0, 3, 1), + /* Kryo4xx Gold (rcpe to rfpf) => (r0p0 to r3p1) */ + MIDR_RANGE(MIDR_QCOM_KRYO_4XX_GOLD, 0xc, 0xe, 0xf, 0xf), {}, }; #endif @@ -770,11 +769,23 @@ static const struct midr_range erratum_speculative_at_list[] = { #ifdef CONFIG_ARM64_ERRATUM_1530923 /* Cortex A55 r0p0 to r2p0 */ MIDR_RANGE(MIDR_CORTEX_A55, 0, 0, 2, 0), + /* Kryo4xx Silver (rdpe => r1p0) */ + MIDR_REV(MIDR_QCOM_KRYO_4XX_SILVER, 0xd, 0xe), #endif {}, }; #endif +#ifdef CONFIG_ARM64_ERRATUM_1463225 +static const struct midr_range erratum_1463225[] = { + /* Cortex-A76 r0p0 - r3p1 */ + MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 1), + /* Kryo4xx Gold (rcpe to rfpf) => (r0p0 to r3p1) */ + MIDR_RANGE(MIDR_QCOM_KRYO_4XX_GOLD, 0xc, 0xe, 0xf, 0xf), + {}, +}; +#endif + const struct arm64_cpu_capabilities arm64_errata[] = { #ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE { @@ -914,6 +925,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = { .capability = ARM64_WORKAROUND_1463225, .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, .matches = has_cortex_a76_erratum_1463225, + .midr_range_list = erratum_1463225, }, #endif #ifdef CONFIG_CAVIUM_TX2_ERRATUM_219 diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 4ae41670c2e6..9fae0efc80c1 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -1290,6 +1290,8 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry, MIDR_ALL_VERSIONS(MIDR_CORTEX_A73), MIDR_ALL_VERSIONS(MIDR_HISI_TSV110), MIDR_ALL_VERSIONS(MIDR_NVIDIA_CARMEL), + MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER), + MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER), { /* sentinel */ } }; char const *str = "kpti command line option"; @@ -1406,6 +1408,8 @@ static bool cpu_has_broken_dbm(void) static const struct midr_range cpus[] = { #ifdef CONFIG_ARM64_ERRATUM_1024718 MIDR_RANGE(MIDR_CORTEX_A55, 0, 0, 1, 0), // A55 r0p0 -r1p0 + /* Kryo4xx Silver (rdpe => r1p0) */ + MIDR_REV(MIDR_QCOM_KRYO_4XX_SILVER, 0xd, 0xe), #endif {}, }; diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c index 5df49366e9ab..7310a4f7f993 100644 --- a/arch/arm64/kernel/debug-monitors.c +++ b/arch/arm64/kernel/debug-monitors.c @@ -141,17 +141,20 @@ postcore_initcall(debug_monitors_init); /* * Single step API and exception handling. */ -static void set_regs_spsr_ss(struct pt_regs *regs) +static void set_user_regs_spsr_ss(struct user_pt_regs *regs) { regs->pstate |= DBG_SPSR_SS; } -NOKPROBE_SYMBOL(set_regs_spsr_ss); +NOKPROBE_SYMBOL(set_user_regs_spsr_ss); -static void clear_regs_spsr_ss(struct pt_regs *regs) +static void clear_user_regs_spsr_ss(struct user_pt_regs *regs) { regs->pstate &= ~DBG_SPSR_SS; } -NOKPROBE_SYMBOL(clear_regs_spsr_ss); +NOKPROBE_SYMBOL(clear_user_regs_spsr_ss); + +#define set_regs_spsr_ss(r) set_user_regs_spsr_ss(&(r)->user_regs) +#define clear_regs_spsr_ss(r) clear_user_regs_spsr_ss(&(r)->user_regs) static DEFINE_SPINLOCK(debug_hook_lock); static LIST_HEAD(user_step_hook); @@ -391,17 +394,26 @@ void user_rewind_single_step(struct task_struct *task) * If single step is active for this thread, then set SPSR.SS * to 1 to avoid returning to the active-pending state. */ - if (test_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP)) + if (test_tsk_thread_flag(task, TIF_SINGLESTEP)) set_regs_spsr_ss(task_pt_regs(task)); } NOKPROBE_SYMBOL(user_rewind_single_step); void user_fastforward_single_step(struct task_struct *task) { - if (test_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP)) + if (test_tsk_thread_flag(task, TIF_SINGLESTEP)) clear_regs_spsr_ss(task_pt_regs(task)); } +void user_regs_reset_single_step(struct user_pt_regs *regs, + struct task_struct *task) +{ + if (test_tsk_thread_flag(task, TIF_SINGLESTEP)) + set_user_regs_spsr_ss(regs); + else + clear_user_regs_spsr_ss(regs); +} + /* Kernel API */ void kernel_enable_single_step(struct pt_regs *regs) { diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c index 3dbdf9752b11..d3be9dbf5490 100644 --- a/arch/arm64/kernel/entry-common.c +++ b/arch/arm64/kernel/entry-common.c @@ -57,7 +57,7 @@ static void notrace el1_dbg(struct pt_regs *regs, unsigned long esr) /* * The CPU masked interrupts, and we are leaving them masked during * do_debug_exception(). Update PMR as if we had called - * local_mask_daif(). + * local_daif_mask(). */ if (system_uses_irq_prio_masking()) gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 5304d193c79d..35de8ba60e3d 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -126,8 +126,10 @@ alternative_else_nop_endif add \dst, \dst, #(\sym - .entry.tramp.text) .endm - // This macro corrupts x0-x3. It is the caller's duty - // to save/restore them if required. + /* + * This macro corrupts x0-x3. It is the caller's duty to save/restore + * them if required. + */ .macro apply_ssbd, state, tmp1, tmp2 #ifdef CONFIG_ARM64_SSBD alternative_cb arm64_enable_wa2_handling @@ -167,13 +169,28 @@ alternative_cb_end stp x28, x29, [sp, #16 * 14] .if \el == 0 + .if \regsize == 32 + /* + * If we're returning from a 32-bit task on a system affected by + * 1418040 then re-enable userspace access to the virtual counter. + */ +#ifdef CONFIG_ARM64_ERRATUM_1418040 +alternative_if ARM64_WORKAROUND_1418040 + mrs x0, cntkctl_el1 + orr x0, x0, #2 // ARCH_TIMER_USR_VCT_ACCESS_EN + msr cntkctl_el1, x0 +alternative_else_nop_endif +#endif + .endif clear_gp_regs mrs x21, sp_el0 ldr_this_cpu tsk, __entry_task, x20 msr sp_el0, tsk - // Ensure MDSCR_EL1.SS is clear, since we can unmask debug exceptions - // when scheduling. + /* + * Ensure MDSCR_EL1.SS is clear, since we can unmask debug exceptions + * when scheduling. + */ ldr x19, [tsk, #TSK_TI_FLAGS] disable_step_tsk x19, x20 @@ -320,6 +337,14 @@ alternative_else_nop_endif tst x22, #PSR_MODE32_BIT // native task? b.eq 3f +#ifdef CONFIG_ARM64_ERRATUM_1418040 +alternative_if ARM64_WORKAROUND_1418040 + mrs x0, cntkctl_el1 + bic x0, x0, #2 // ARCH_TIMER_USR_VCT_ACCESS_EN + msr cntkctl_el1, x0 +alternative_else_nop_endif +#endif + #ifdef CONFIG_ARM64_ERRATUM_845719 alternative_if ARM64_WORKAROUND_845719 #ifdef CONFIG_PID_IN_CONTEXTIDR @@ -331,21 +356,6 @@ alternative_if ARM64_WORKAROUND_845719 alternative_else_nop_endif #endif 3: -#ifdef CONFIG_ARM64_ERRATUM_1418040 -alternative_if_not ARM64_WORKAROUND_1418040 - b 4f -alternative_else_nop_endif - /* - * if (x22.mode32 == cntkctl_el1.el0vcten) - * cntkctl_el1.el0vcten = ~cntkctl_el1.el0vcten - */ - mrs x1, cntkctl_el1 - eon x0, x1, x22, lsr #3 - tbz x0, #1, 4f - eor x1, x1, #2 // ARCH_TIMER_USR_VCT_ACCESS_EN - msr cntkctl_el1, x1 -4: -#endif scs_save tsk, x0 /* No kernel C function calls after this as user keys are set. */ @@ -377,11 +387,11 @@ alternative_else_nop_endif .if \el == 0 alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 - bne 5f + bne 4f msr far_el1, x30 tramp_alias x30, tramp_exit_native br x30 -5: +4: tramp_alias x30, tramp_exit_compat br x30 #endif diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 35cb5e66c504..55c8f3ec6705 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -12,6 +12,7 @@ #include <linux/bug.h> #include <linux/cache.h> #include <linux/compat.h> +#include <linux/compiler.h> #include <linux/cpu.h> #include <linux/cpu_pm.h> #include <linux/kernel.h> @@ -119,10 +120,20 @@ struct fpsimd_last_state_struct { static DEFINE_PER_CPU(struct fpsimd_last_state_struct, fpsimd_last_state); /* Default VL for tasks that don't set it explicitly: */ -static int sve_default_vl = -1; +static int __sve_default_vl = -1; + +static int get_sve_default_vl(void) +{ + return READ_ONCE(__sve_default_vl); +} #ifdef CONFIG_ARM64_SVE +static void set_sve_default_vl(int val) +{ + WRITE_ONCE(__sve_default_vl, val); +} + /* Maximum supported vector length across all CPUs (initially poisoned) */ int __ro_after_init sve_max_vl = SVE_VL_MIN; int __ro_after_init sve_max_virtualisable_vl = SVE_VL_MIN; @@ -338,13 +349,13 @@ static unsigned int find_supported_vector_length(unsigned int vl) return sve_vl_from_vq(__bit_to_vq(bit)); } -#ifdef CONFIG_SYSCTL +#if defined(CONFIG_ARM64_SVE) && defined(CONFIG_SYSCTL) static int sve_proc_do_default_vl(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; - int vl = sve_default_vl; + int vl = get_sve_default_vl(); struct ctl_table tmp_table = { .data = &vl, .maxlen = sizeof(vl), @@ -361,7 +372,7 @@ static int sve_proc_do_default_vl(struct ctl_table *table, int write, if (!sve_vl_valid(vl)) return -EINVAL; - sve_default_vl = find_supported_vector_length(vl); + set_sve_default_vl(find_supported_vector_length(vl)); return 0; } @@ -383,9 +394,9 @@ static int __init sve_sysctl_init(void) return 0; } -#else /* ! CONFIG_SYSCTL */ +#else /* ! (CONFIG_ARM64_SVE && CONFIG_SYSCTL) */ static int __init sve_sysctl_init(void) { return 0; } -#endif /* ! CONFIG_SYSCTL */ +#endif /* ! (CONFIG_ARM64_SVE && CONFIG_SYSCTL) */ #define ZREG(sve_state, vq, n) ((char *)(sve_state) + \ (SVE_SIG_ZREG_OFFSET(vq, n) - SVE_SIG_REGS_OFFSET)) @@ -868,7 +879,7 @@ void __init sve_setup(void) * For the default VL, pick the maximum supported value <= 64. * VL == 64 is guaranteed not to grow the signal frame. */ - sve_default_vl = find_supported_vector_length(64); + set_sve_default_vl(find_supported_vector_length(64)); bitmap_andnot(tmp_map, sve_vq_partial_map, sve_vq_map, SVE_VQ_MAX); @@ -889,7 +900,7 @@ void __init sve_setup(void) pr_info("SVE: maximum available vector length %u bytes per vector\n", sve_max_vl); pr_info("SVE: default vector length %u bytes per vector\n", - sve_default_vl); + get_sve_default_vl()); /* KVM decides whether to support mismatched systems. Just warn here: */ if (sve_max_virtualisable_vl < sve_max_vl) @@ -1029,13 +1040,13 @@ void fpsimd_flush_thread(void) * vector length configured: no kernel task can become a user * task without an exec and hence a call to this function. * By the time the first call to this function is made, all - * early hardware probing is complete, so sve_default_vl + * early hardware probing is complete, so __sve_default_vl * should be valid. * If a bug causes this to go wrong, we make some noise and * try to fudge thread.sve_vl to a safe value here. */ vl = current->thread.sve_vl_onexec ? - current->thread.sve_vl_onexec : sve_default_vl; + current->thread.sve_vl_onexec : get_sve_default_vl(); if (WARN_ON(!sve_vl_valid(vl))) vl = SVE_VL_MIN; diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index 0b727edf4104..af234a1e08b7 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -730,6 +730,27 @@ static u64 get_distance_from_watchpoint(unsigned long addr, u64 val, return 0; } +static int watchpoint_report(struct perf_event *wp, unsigned long addr, + struct pt_regs *regs) +{ + int step = is_default_overflow_handler(wp); + struct arch_hw_breakpoint *info = counter_arch_bp(wp); + + info->trigger = addr; + + /* + * If we triggered a user watchpoint from a uaccess routine, then + * handle the stepping ourselves since userspace really can't help + * us with this. + */ + if (!user_mode(regs) && info->ctrl.privilege == AARCH64_BREAKPOINT_EL0) + step = 1; + else + perf_bp_event(wp, regs); + + return step; +} + static int watchpoint_handler(unsigned long addr, unsigned int esr, struct pt_regs *regs) { @@ -739,7 +760,6 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr, u64 val; struct perf_event *wp, **slots; struct debug_info *debug_info; - struct arch_hw_breakpoint *info; struct arch_hw_breakpoint_ctrl ctrl; slots = this_cpu_ptr(wp_on_reg); @@ -777,25 +797,13 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr, if (dist != 0) continue; - info = counter_arch_bp(wp); - info->trigger = addr; - perf_bp_event(wp, regs); - - /* Do we need to handle the stepping? */ - if (is_default_overflow_handler(wp)) - step = 1; + step = watchpoint_report(wp, addr, regs); } - if (min_dist > 0 && min_dist != -1) { - /* No exact match found. */ - wp = slots[closest_match]; - info = counter_arch_bp(wp); - info->trigger = addr; - perf_bp_event(wp, regs); - /* Do we need to handle the stepping? */ - if (is_default_overflow_handler(wp)) - step = 1; - } + /* No exact match found? */ + if (min_dist > 0 && min_dist != -1) + step = watchpoint_report(slots[closest_match], addr, regs); + rcu_read_unlock(); if (!step) diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c index 684d871ae38d..a107375005bc 100644 --- a/arch/arm64/kernel/insn.c +++ b/arch/arm64/kernel/insn.c @@ -135,7 +135,7 @@ int __kprobes aarch64_insn_read(void *addr, u32 *insnp) int ret; __le32 val; - ret = probe_kernel_read(&val, addr, AARCH64_INSN_SIZE); + ret = copy_from_kernel_nofault(&val, addr, AARCH64_INSN_SIZE); if (!ret) *insnp = le32_to_cpu(val); @@ -151,7 +151,7 @@ static int __kprobes __aarch64_insn_write(void *addr, __le32 insn) raw_spin_lock_irqsave(&patch_lock, flags); waddr = patch_map(addr, FIX_TEXT_POKE0); - ret = probe_kernel_write(waddr, &insn, AARCH64_INSN_SIZE); + ret = copy_to_kernel_nofault(waddr, &insn, AARCH64_INSN_SIZE); patch_unmap(FIX_TEXT_POKE0); raw_spin_unlock_irqrestore(&patch_lock, flags); diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c index 43119922341f..1a157ca33262 100644 --- a/arch/arm64/kernel/kgdb.c +++ b/arch/arm64/kernel/kgdb.c @@ -252,7 +252,7 @@ static int kgdb_step_brk_fn(struct pt_regs *regs, unsigned int esr) if (!kgdb_single_step) return DBG_HOOK_ERROR; - kgdb_handle_exception(1, SIGTRAP, 0, regs); + kgdb_handle_exception(0, SIGTRAP, 0, regs); return DBG_HOOK_HANDLED; } NOKPROBE_SYMBOL(kgdb_step_brk_fn); diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c index 522e6f517ec0..361a1143e09e 100644 --- a/arch/arm64/kernel/machine_kexec_file.c +++ b/arch/arm64/kernel/machine_kexec_file.c @@ -219,8 +219,7 @@ static int prepare_elf_headers(void **addr, unsigned long *sz) MEMBLOCK_NONE, &start, &end, NULL) nr_ranges++; - cmem = kmalloc(sizeof(struct crash_mem) + - sizeof(struct crash_mem_range) * nr_ranges, GFP_KERNEL); + cmem = kmalloc(struct_size(cmem, ranges, nr_ranges), GFP_KERNEL); if (!cmem) return -ENOMEM; diff --git a/arch/arm64/kernel/perf_regs.c b/arch/arm64/kernel/perf_regs.c index 0bbac612146e..666b225aeb3a 100644 --- a/arch/arm64/kernel/perf_regs.c +++ b/arch/arm64/kernel/perf_regs.c @@ -15,15 +15,34 @@ u64 perf_reg_value(struct pt_regs *regs, int idx) return 0; /* - * Compat (i.e. 32 bit) mode: - * - PC has been set in the pt_regs struct in kernel_entry, - * - Handle SP and LR here. + * Our handling of compat tasks (PERF_SAMPLE_REGS_ABI_32) is weird, but + * we're stuck with it for ABI compatability reasons. + * + * For a 32-bit consumer inspecting a 32-bit task, then it will look at + * the first 16 registers (see arch/arm/include/uapi/asm/perf_regs.h). + * These correspond directly to a prefix of the registers saved in our + * 'struct pt_regs', with the exception of the PC, so we copy that down + * (x15 corresponds to SP_hyp in the architecture). + * + * So far, so good. + * + * The oddity arises when a 64-bit consumer looks at a 32-bit task and + * asks for registers beyond PERF_REG_ARM_MAX. In this case, we return + * SP_usr, LR_usr and PC in the positions where the AArch64 SP, LR and + * PC registers would normally live. The initial idea was to allow a + * 64-bit unwinder to unwind a 32-bit task and, although it's not clear + * how well that works in practice, somebody might be relying on it. + * + * At the time we make a sample, we don't know whether the consumer is + * 32-bit or 64-bit, so we have to cater for both possibilities. */ if (compat_user_mode(regs)) { if ((u32)idx == PERF_REG_ARM64_SP) return regs->compat_sp; if ((u32)idx == PERF_REG_ARM64_LR) return regs->compat_lr; + if (idx == 15) + return regs->pc; } if ((u32)idx == PERF_REG_ARM64_SP) diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index d1c95dcf1d78..5290f17a4d80 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -120,15 +120,9 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) void *alloc_insn_page(void) { - void *page; - - page = vmalloc_exec(PAGE_SIZE); - if (page) { - set_memory_ro((unsigned long)page, 1); - set_vm_flush_reset_perms(page); - } - - return page; + return __vmalloc_node_range(PAGE_SIZE, 1, VMALLOC_START, VMALLOC_END, + GFP_KERNEL, PAGE_KERNEL_ROX, VM_FLUSH_RESET_PERMS, + NUMA_NO_NODE, __builtin_return_address(0)); } /* arm kprobe: install breakpoint in text */ diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 68b7f34a08f5..1e02e98e68dd 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -1811,19 +1811,42 @@ static void tracehook_report_syscall(struct pt_regs *regs, unsigned long saved_reg; /* - * A scratch register (ip(r12) on AArch32, x7 on AArch64) is - * used to denote syscall entry/exit: + * We have some ABI weirdness here in the way that we handle syscall + * exit stops because we indicate whether or not the stop has been + * signalled from syscall entry or syscall exit by clobbering a general + * purpose register (ip/r12 for AArch32, x7 for AArch64) in the tracee + * and restoring its old value after the stop. This means that: + * + * - Any writes by the tracer to this register during the stop are + * ignored/discarded. + * + * - The actual value of the register is not available during the stop, + * so the tracer cannot save it and restore it later. + * + * - Syscall stops behave differently to seccomp and pseudo-step traps + * (the latter do not nobble any registers). */ regno = (is_compat_task() ? 12 : 7); saved_reg = regs->regs[regno]; regs->regs[regno] = dir; - if (dir == PTRACE_SYSCALL_EXIT) + if (dir == PTRACE_SYSCALL_ENTER) { + if (tracehook_report_syscall_entry(regs)) + forget_syscall(regs); + regs->regs[regno] = saved_reg; + } else if (!test_thread_flag(TIF_SINGLESTEP)) { tracehook_report_syscall_exit(regs, 0); - else if (tracehook_report_syscall_entry(regs)) - forget_syscall(regs); + regs->regs[regno] = saved_reg; + } else { + regs->regs[regno] = saved_reg; - regs->regs[regno] = saved_reg; + /* + * Signal a pseudo-step exception since we are stepping but + * tracer modifications to the registers may have rewound the + * state machine. + */ + tracehook_report_syscall_exit(regs, 1); + } } int syscall_trace_enter(struct pt_regs *regs) @@ -1833,12 +1856,12 @@ int syscall_trace_enter(struct pt_regs *regs) if (flags & (_TIF_SYSCALL_EMU | _TIF_SYSCALL_TRACE)) { tracehook_report_syscall(regs, PTRACE_SYSCALL_ENTER); if (!in_syscall(regs) || (flags & _TIF_SYSCALL_EMU)) - return -1; + return NO_SYSCALL; } /* Do the secure computing after ptrace; failures should be fast. */ if (secure_computing() == -1) - return -1; + return NO_SYSCALL; if (test_thread_flag(TIF_SYSCALL_TRACEPOINT)) trace_sys_enter(regs, regs->syscallno); @@ -1851,12 +1874,14 @@ int syscall_trace_enter(struct pt_regs *regs) void syscall_trace_exit(struct pt_regs *regs) { + unsigned long flags = READ_ONCE(current_thread_info()->flags); + audit_syscall_exit(regs); - if (test_thread_flag(TIF_SYSCALL_TRACEPOINT)) + if (flags & _TIF_SYSCALL_TRACEPOINT) trace_sys_exit(regs, regs_return_value(regs)); - if (test_thread_flag(TIF_SYSCALL_TRACE)) + if (flags & (_TIF_SYSCALL_TRACE | _TIF_SINGLESTEP)) tracehook_report_syscall(regs, PTRACE_SYSCALL_EXIT); rseq_syscall(regs); @@ -1934,8 +1959,8 @@ static int valid_native_regs(struct user_pt_regs *regs) */ int valid_user_regs(struct user_pt_regs *regs, struct task_struct *task) { - if (!test_tsk_thread_flag(task, TIF_SINGLESTEP)) - regs->pstate &= ~DBG_SPSR_SS; + /* https://lore.kernel.org/lkml/20191118131525.GA4180@willie-the-truck */ + user_regs_reset_single_step(regs, task); if (is_compat_thread(task_thread_info(task))) return valid_compat_regs(regs); diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 801d56cdf701..3b4f31f35e45 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -800,7 +800,6 @@ static void setup_restart_syscall(struct pt_regs *regs) */ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) { - struct task_struct *tsk = current; sigset_t *oldset = sigmask_to_save(); int usig = ksig->sig; int ret; @@ -824,14 +823,8 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) */ ret |= !valid_user_regs(®s->user_regs, current); - /* - * Fast forward the stepping logic so we step into the signal - * handler. - */ - if (!ret) - user_fastforward_single_step(tsk); - - signal_setup_done(ret, ksig, 0); + /* Step into the signal handler if we are stepping */ + signal_setup_done(ret, ksig, test_thread_flag(TIF_SINGLESTEP)); } /* diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c index 82feca6f7052..2f507f565c48 100644 --- a/arch/arm64/kernel/signal32.c +++ b/arch/arm64/kernel/signal32.c @@ -342,38 +342,13 @@ static void compat_setup_return(struct pt_regs *regs, struct k_sigaction *ka, retcode = ptr_to_compat(ka->sa.sa_restorer); } else { /* Set up sigreturn pointer */ -#ifdef CONFIG_COMPAT_VDSO - void *vdso_base = current->mm->context.vdso; - void *vdso_trampoline; - - if (ka->sa.sa_flags & SA_SIGINFO) { - if (thumb) { - vdso_trampoline = VDSO_SYMBOL(vdso_base, - compat_rt_sigreturn_thumb); - } else { - vdso_trampoline = VDSO_SYMBOL(vdso_base, - compat_rt_sigreturn_arm); - } - } else { - if (thumb) { - vdso_trampoline = VDSO_SYMBOL(vdso_base, - compat_sigreturn_thumb); - } else { - vdso_trampoline = VDSO_SYMBOL(vdso_base, - compat_sigreturn_arm); - } - } - - retcode = ptr_to_compat(vdso_trampoline) + thumb; -#else unsigned int idx = thumb << 1; if (ka->sa.sa_flags & SA_SIGINFO) idx += 3; - retcode = (unsigned long)current->mm->context.vdso + + retcode = (unsigned long)current->mm->context.sigpage + (idx << 2) + thumb; -#endif } regs->regs[0] = usig; diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index 5f5b868292f5..5f0c04863d2c 100644 --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -50,6 +50,9 @@ static void invoke_syscall(struct pt_regs *regs, unsigned int scno, ret = do_ni_syscall(regs, scno); } + if (is_compat_task()) + ret = lower_32_bits(ret); + regs->regs[0] = ret; } @@ -121,7 +124,21 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr, user_exit(); if (has_syscall_work(flags)) { - /* set default errno for user-issued syscall(-1) */ + /* + * The de-facto standard way to skip a system call using ptrace + * is to set the system call to -1 (NO_SYSCALL) and set x0 to a + * suitable error code for consumption by userspace. However, + * this cannot be distinguished from a user-issued syscall(-1) + * and so we must set x0 to -ENOSYS here in case the tracer doesn't + * issue the skip and we fall into trace_exit with x0 preserved. + * + * This is slightly odd because it also means that if a tracer + * sets the system call number to -1 but does not initialise x0, + * then x0 will be preserved for all system calls apart from a + * user-issued syscall(-1). However, requesting a skip and not + * setting the return value is unlikely to do anything sensible + * anyway. + */ if (scno == NO_SYSCALL) regs->regs[0] = -ENOSYS; scno = syscall_trace_enter(regs); @@ -139,7 +156,7 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr, if (!has_syscall_work(flags) && !IS_ENABLED(CONFIG_DEBUG_RSEQ)) { local_daif_mask(); flags = current_thread_info()->flags; - if (!has_syscall_work(flags)) { + if (!has_syscall_work(flags) && !(flags & _TIF_SINGLESTEP)) { /* * We're off to userspace, where interrupts are * always enabled after we restore the flags from diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 50cc30acf106..47f651df781c 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -376,7 +376,7 @@ static int call_undef_hook(struct pt_regs *regs) if (!user_mode(regs)) { __le32 instr_le; - if (probe_kernel_address((__force __le32 *)pc, instr_le)) + if (get_kernel_nofault(instr_le, (__force __le32 *)pc)) goto exit; instr = le32_to_cpu(instr_le); } else if (compat_thumb_mode(regs)) { @@ -813,6 +813,7 @@ asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr) handler[reason], smp_processor_id(), esr, esr_get_class_string(esr)); + __show_regs(regs); local_daif_mask(); panic("bad mode"); } diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c index 4e016574bd91..e546df0efefb 100644 --- a/arch/arm64/kernel/vdso.c +++ b/arch/arm64/kernel/vdso.c @@ -191,15 +191,12 @@ enum aarch32_map { #ifdef CONFIG_COMPAT_VDSO AA32_MAP_VVAR, AA32_MAP_VDSO, -#else - AA32_MAP_SIGPAGE #endif + AA32_MAP_SIGPAGE }; static struct page *aarch32_vectors_page __ro_after_init; -#ifndef CONFIG_COMPAT_VDSO static struct page *aarch32_sig_page __ro_after_init; -#endif static struct vm_special_mapping aarch32_vdso_maps[] = { [AA32_MAP_VECTORS] = { @@ -214,12 +211,11 @@ static struct vm_special_mapping aarch32_vdso_maps[] = { .name = "[vdso]", .mremap = aarch32_vdso_mremap, }, -#else +#endif /* CONFIG_COMPAT_VDSO */ [AA32_MAP_SIGPAGE] = { .name = "[sigpage]", /* ABI */ .pages = &aarch32_sig_page, }, -#endif /* CONFIG_COMPAT_VDSO */ }; static int aarch32_alloc_kuser_vdso_page(void) @@ -242,27 +238,11 @@ static int aarch32_alloc_kuser_vdso_page(void) return 0; } -#ifdef CONFIG_COMPAT_VDSO -static int __aarch32_alloc_vdso_pages(void) -{ - int ret; - - vdso_info[VDSO_ABI_AA32].dm = &aarch32_vdso_maps[AA32_MAP_VVAR]; - vdso_info[VDSO_ABI_AA32].cm = &aarch32_vdso_maps[AA32_MAP_VDSO]; - - ret = __vdso_init(VDSO_ABI_AA32); - if (ret) - return ret; - - return aarch32_alloc_kuser_vdso_page(); -} -#else -static int __aarch32_alloc_vdso_pages(void) +static int aarch32_alloc_sigpage(void) { extern char __aarch32_sigret_code_start[], __aarch32_sigret_code_end[]; int sigret_sz = __aarch32_sigret_code_end - __aarch32_sigret_code_start; unsigned long sigpage; - int ret; sigpage = get_zeroed_page(GFP_ATOMIC); if (!sigpage) @@ -271,18 +251,34 @@ static int __aarch32_alloc_vdso_pages(void) memcpy((void *)sigpage, __aarch32_sigret_code_start, sigret_sz); aarch32_sig_page = virt_to_page(sigpage); flush_dcache_page(aarch32_sig_page); + return 0; +} - ret = aarch32_alloc_kuser_vdso_page(); - if (ret) - free_page(sigpage); +#ifdef CONFIG_COMPAT_VDSO +static int __aarch32_alloc_vdso_pages(void) +{ + vdso_info[VDSO_ABI_AA32].dm = &aarch32_vdso_maps[AA32_MAP_VVAR]; + vdso_info[VDSO_ABI_AA32].cm = &aarch32_vdso_maps[AA32_MAP_VDSO]; - return ret; + return __vdso_init(VDSO_ABI_AA32); } #endif /* CONFIG_COMPAT_VDSO */ static int __init aarch32_alloc_vdso_pages(void) { - return __aarch32_alloc_vdso_pages(); + int ret; + +#ifdef CONFIG_COMPAT_VDSO + ret = __aarch32_alloc_vdso_pages(); + if (ret) + return ret; +#endif + + ret = aarch32_alloc_sigpage(); + if (ret) + return ret; + + return aarch32_alloc_kuser_vdso_page(); } arch_initcall(aarch32_alloc_vdso_pages); @@ -305,7 +301,6 @@ static int aarch32_kuser_helpers_setup(struct mm_struct *mm) return PTR_ERR_OR_ZERO(ret); } -#ifndef CONFIG_COMPAT_VDSO static int aarch32_sigreturn_setup(struct mm_struct *mm) { unsigned long addr; @@ -328,12 +323,11 @@ static int aarch32_sigreturn_setup(struct mm_struct *mm) if (IS_ERR(ret)) goto out; - mm->context.vdso = (void *)addr; + mm->context.sigpage = (void *)addr; out: return PTR_ERR_OR_ZERO(ret); } -#endif /* !CONFIG_COMPAT_VDSO */ int aarch32_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) { @@ -352,10 +346,11 @@ int aarch32_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) mm, bprm, uses_interp); -#else - ret = aarch32_sigreturn_setup(mm); + if (ret) + goto out; #endif /* CONFIG_COMPAT_VDSO */ + ret = aarch32_sigreturn_setup(mm); out: mmap_write_unlock(mm); return ret; diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile index 556d424c6f52..45d5cfe46429 100644 --- a/arch/arm64/kernel/vdso/Makefile +++ b/arch/arm64/kernel/vdso/Makefile @@ -23,13 +23,14 @@ btildflags-$(CONFIG_ARM64_BTI_KERNEL) += -z force-bti # potential future proofing if we end up with internal calls to the exported # routines, as x86 does (see 6f121e548f83 ("x86, vdso: Reimplement vdso.so # preparation in build-time C")). -ldflags-y := -shared -nostdlib -soname=linux-vdso.so.1 --hash-style=sysv \ - -Bsymbolic --eh-frame-hdr --build-id -n $(btildflags-y) -T +ldflags-y := -shared -nostdlib -soname=linux-vdso.so.1 --hash-style=sysv \ + -Bsymbolic $(call ld-option, --no-eh-frame-hdr) --build-id -n \ + $(btildflags-y) -T ccflags-y := -fno-common -fno-builtin -fno-stack-protector -ffixed-x18 ccflags-y += -DDISABLE_BRANCH_PROFILING -CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os $(CC_FLAGS_SCS) +CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os $(CC_FLAGS_SCS) $(GCC_PLUGINS_CFLAGS) KBUILD_CFLAGS += $(DISABLE_LTO) KASAN_SANITIZE := n UBSAN_SANITIZE := n diff --git a/arch/arm64/kernel/vdso/sigreturn.S b/arch/arm64/kernel/vdso/sigreturn.S index 620a3ef837b7..0e18729abc3b 100644 --- a/arch/arm64/kernel/vdso/sigreturn.S +++ b/arch/arm64/kernel/vdso/sigreturn.S @@ -18,29 +18,40 @@ .text +/* + * NOTE!!! You may notice that all of the .cfi directives in this file have + * been commented out. This is because they have been shown to trigger segfaults + * in libgcc when unwinding out of a SIGCANCEL handler to invoke pthread + * cleanup handlers during the thread cancellation dance. By omitting the + * directives, we trigger an arm64-specific fallback path in the unwinder which + * recognises the signal frame and restores many of the registers directly from + * the sigcontext. Re-enabling the cfi directives here therefore needs to be + * much more comprehensive to reduce the risk of further regressions. + */ + /* Ensure that the mysterious NOP can be associated with a function. */ - .cfi_startproc +// .cfi_startproc /* - * .cfi_signal_frame causes the corresponding Frame Description Entry in the - * .eh_frame section to be annotated as a signal frame. This allows DWARF - * unwinders (e.g. libstdc++) to implement _Unwind_GetIPInfo(), which permits - * unwinding out of the signal trampoline without the need for the mysterious - * NOP. + * .cfi_signal_frame causes the corresponding Frame Description Entry (FDE) in + * the .eh_frame section to be annotated as a signal frame. This allows DWARF + * unwinders (e.g. libstdc++) to implement _Unwind_GetIPInfo() and identify + * the next frame using the unmodified return address instead of subtracting 1, + * which may yield the wrong FDE. */ - .cfi_signal_frame +// .cfi_signal_frame /* * Tell the unwinder where to locate the frame record linking back to the - * interrupted context. We don't provide unwind info for registers other - * than the frame pointer and the link register here; in practice, this - * is sufficient for unwinding in C/C++ based runtimes and the values in - * the sigcontext may have been modified by this point anyway. Debuggers + * interrupted context. We don't provide unwind info for registers other than + * the frame pointer and the link register here; in practice, this is likely to + * be insufficient for unwinding in C/C++ based runtimes, especially without a + * means to restore the stack pointer. Thankfully, unwinders and debuggers * already have baked-in strategies for attempting to unwind out of signals. */ - .cfi_def_cfa x29, 0 - .cfi_offset x29, 0 * 8 - .cfi_offset x30, 1 * 8 +// .cfi_def_cfa x29, 0 +// .cfi_offset x29, 0 * 8 +// .cfi_offset x30, 1 * 8 /* * This mysterious NOP is required for some unwinders (e.g. libc++) that @@ -51,16 +62,19 @@ nop // Mysterious NOP /* - * GDB relies on being able to identify the sigreturn instruction sequence to - * unwind from signal handlers. We cannot, therefore, use SYM_FUNC_START() - * here, as it will emit a BTI C instruction and break the unwinder. Thankfully, - * this function is only ever called from a RET and so omitting the landing pad - * is perfectly fine. + * GDB, libgcc and libunwind rely on being able to identify the sigreturn + * instruction sequence to unwind from signal handlers. We cannot, therefore, + * use SYM_FUNC_START() here, as it will emit a BTI C instruction and break the + * unwinder. Thankfully, this function is only ever called from a RET and so + * omitting the landing pad is perfectly fine. */ SYM_CODE_START(__kernel_rt_sigreturn) +// PLEASE DO NOT MODIFY mov x8, #__NR_rt_sigreturn +// PLEASE DO NOT MODIFY svc #0 - .cfi_endproc +// PLEASE DO NOT MODIFY +// .cfi_endproc SYM_CODE_END(__kernel_rt_sigreturn) emit_aarch64_feature_1_and diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile index 7ea1e827e505..5139a5f19256 100644 --- a/arch/arm64/kernel/vdso32/Makefile +++ b/arch/arm64/kernel/vdso32/Makefile @@ -14,7 +14,7 @@ COMPAT_GCC_TOOLCHAIN_DIR := $(dir $(shell which $(CROSS_COMPILE_COMPAT)elfedit)) COMPAT_GCC_TOOLCHAIN := $(realpath $(COMPAT_GCC_TOOLCHAIN_DIR)/..) CC_COMPAT_CLANG_FLAGS := --target=$(notdir $(CROSS_COMPILE_COMPAT:%-=%)) -CC_COMPAT_CLANG_FLAGS += --prefix=$(COMPAT_GCC_TOOLCHAIN_DIR) +CC_COMPAT_CLANG_FLAGS += --prefix=$(COMPAT_GCC_TOOLCHAIN_DIR)$(notdir $(CROSS_COMPILE_COMPAT)) CC_COMPAT_CLANG_FLAGS += -no-integrated-as -Qunused-arguments ifneq ($(COMPAT_GCC_TOOLCHAIN),) CC_COMPAT_CLANG_FLAGS += --gcc-toolchain=$(COMPAT_GCC_TOOLCHAIN) @@ -140,7 +140,6 @@ hostprogs := $(munge) c-obj-vdso := note.o c-obj-vdso-gettimeofday := vgettimeofday.o -asm-obj-vdso := sigreturn.o ifneq ($(c-gettimeofday-y),) VDSO_CFLAGS_gettimeofday_o += -include $(c-gettimeofday-y) diff --git a/arch/arm64/kernel/vdso32/sigreturn.S b/arch/arm64/kernel/vdso32/sigreturn.S deleted file mode 100644 index b0091064c3d6..000000000000 --- a/arch/arm64/kernel/vdso32/sigreturn.S +++ /dev/null @@ -1,58 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * This file provides both A32 and T32 versions, in accordance with the - * arm sigreturn code. - * - * Please read the comments in arch/arm64/kernel/vdso/sigreturn.S to - * understand some of the craziness in here. - * - * Copyright (C) 2018 ARM Limited - */ - -#include <linux/linkage.h> -#include <asm/asm-offsets.h> -#include <asm/unistd.h> - - .text - - .arm - .fnstart - .save {r0-r15} - .pad #COMPAT_SIGFRAME_REGS_OFFSET - nop -SYM_CODE_START(__kernel_sigreturn_arm) - mov r7, #__NR_compat_sigreturn - svc #0 - .fnend -SYM_CODE_END(__kernel_sigreturn_arm) - - .fnstart - .save {r0-r15} - .pad #COMPAT_RT_SIGFRAME_REGS_OFFSET - nop -SYM_CODE_START(__kernel_rt_sigreturn_arm) - mov r7, #__NR_compat_rt_sigreturn - svc #0 - .fnend -SYM_CODE_END(__kernel_rt_sigreturn_arm) - - .thumb - .fnstart - .save {r0-r15} - .pad #COMPAT_SIGFRAME_REGS_OFFSET - nop -SYM_CODE_START(__kernel_sigreturn_thumb) - mov r7, #__NR_compat_sigreturn - svc #0 - .fnend -SYM_CODE_END(__kernel_sigreturn_thumb) - - .fnstart - .save {r0-r15} - .pad #COMPAT_RT_SIGFRAME_REGS_OFFSET - nop -SYM_CODE_START(__kernel_rt_sigreturn_thumb) - mov r7, #__NR_compat_rt_sigreturn - svc #0 - .fnend -SYM_CODE_END(__kernel_rt_sigreturn_thumb) diff --git a/arch/arm64/kernel/vdso32/vdso.lds.S b/arch/arm64/kernel/vdso32/vdso.lds.S index a3944927eaeb..337d03522048 100644 --- a/arch/arm64/kernel/vdso32/vdso.lds.S +++ b/arch/arm64/kernel/vdso32/vdso.lds.S @@ -64,19 +64,7 @@ VERSION __vdso_clock_gettime; __vdso_gettimeofday; __vdso_clock_getres; - __kernel_sigreturn_arm; - __kernel_sigreturn_thumb; - __kernel_rt_sigreturn_arm; - __kernel_rt_sigreturn_thumb; __vdso_clock_gettime64; local: *; }; } - -/* - * Make the sigreturn code visible to the kernel. - */ -VDSO_compat_sigreturn_arm = __kernel_sigreturn_arm; -VDSO_compat_sigreturn_thumb = __kernel_sigreturn_thumb; -VDSO_compat_rt_sigreturn_arm = __kernel_rt_sigreturn_arm; -VDSO_compat_rt_sigreturn_thumb = __kernel_rt_sigreturn_thumb; diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index 6827da7f3aa5..5423ffe0a987 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -165,9 +165,6 @@ SECTIONS *(.altinstructions) __alt_instructions_end = .; } - .altinstr_replacement : { - *(.altinstr_replacement) - } . = ALIGN(SEGMENT_ALIGN); __inittext_end = .; diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S index 6e6ed5581eed..e76c0e89d48e 100644 --- a/arch/arm64/kvm/hyp-init.S +++ b/arch/arm64/kvm/hyp-init.S @@ -136,11 +136,15 @@ SYM_CODE_START(__kvm_handle_stub_hvc) 1: cmp x0, #HVC_RESET_VECTORS b.ne 1f -reset: + /* - * Reset kvm back to the hyp stub. Do not clobber x0-x4 in - * case we coming via HVC_SOFT_RESTART. + * Set the HVC_RESET_VECTORS return code before entering the common + * path so that we do not clobber x0-x2 in case we are coming via + * HVC_SOFT_RESTART. */ + mov x0, xzr +reset: + /* Reset kvm back to the hyp stub. */ mrs x5, sctlr_el2 mov_q x6, SCTLR_ELx_FLAGS bic x5, x5, x6 // Clear SCTL_M and etc @@ -151,7 +155,6 @@ reset: /* Install stub vectors */ adr_l x5, __hyp_stub_vectors msr vbar_el2, x5 - mov x0, xzr eret 1: /* Bad stub call */ diff --git a/arch/arm64/kvm/pmu.c b/arch/arm64/kvm/pmu.c index b5ae3a5d509e..3c224162b3dd 100644 --- a/arch/arm64/kvm/pmu.c +++ b/arch/arm64/kvm/pmu.c @@ -159,7 +159,10 @@ static void kvm_vcpu_pmu_disable_el0(unsigned long events) } /* - * On VHE ensure that only guest events have EL0 counting enabled + * On VHE ensure that only guest events have EL0 counting enabled. + * This is called from both vcpu_{load,put} and the sysreg handling. + * Since the latter is preemptible, special care must be taken to + * disable preemption. */ void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu) { @@ -169,12 +172,14 @@ void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu) if (!has_vhe()) return; + preempt_disable(); host = this_cpu_ptr(&kvm_host_data); events_guest = host->pmu_events.events_guest; events_host = host->pmu_events.events_host; kvm_vcpu_pmu_enable_el0(events_guest); kvm_vcpu_pmu_disable_el0(events_host); + preempt_enable(); } /* diff --git a/arch/arm64/kvm/pvtime.c b/arch/arm64/kvm/pvtime.c index 1e0f4c284888..f7b52ce1557e 100644 --- a/arch/arm64/kvm/pvtime.c +++ b/arch/arm64/kvm/pvtime.c @@ -3,6 +3,7 @@ #include <linux/arm-smccc.h> #include <linux/kvm_host.h> +#include <linux/sched/stat.h> #include <asm/kvm_mmu.h> #include <asm/pvclock-abi.h> @@ -73,6 +74,11 @@ gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu) return base; } +static bool kvm_arm_pvtime_supported(void) +{ + return !!sched_info_on(); +} + int kvm_arm_pvtime_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { @@ -82,7 +88,8 @@ int kvm_arm_pvtime_set_attr(struct kvm_vcpu *vcpu, int ret = 0; int idx; - if (attr->attr != KVM_ARM_VCPU_PVTIME_IPA) + if (!kvm_arm_pvtime_supported() || + attr->attr != KVM_ARM_VCPU_PVTIME_IPA) return -ENXIO; if (get_user(ipa, user)) @@ -110,7 +117,8 @@ int kvm_arm_pvtime_get_attr(struct kvm_vcpu *vcpu, u64 __user *user = (u64 __user *)attr->addr; u64 ipa; - if (attr->attr != KVM_ARM_VCPU_PVTIME_IPA) + if (!kvm_arm_pvtime_supported() || + attr->attr != KVM_ARM_VCPU_PVTIME_IPA) return -ENXIO; ipa = vcpu->arch.steal.base; @@ -125,7 +133,8 @@ int kvm_arm_pvtime_has_attr(struct kvm_vcpu *vcpu, { switch (attr->attr) { case KVM_ARM_VCPU_PVTIME_IPA: - return 0; + if (kvm_arm_pvtime_supported()) + return 0; } return -ENXIO; } diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index d3b209023727..6ed36be51b4b 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -245,7 +245,7 @@ static int kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu) */ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) { - int ret = -EINVAL; + int ret; bool loaded; u32 pstate; @@ -269,15 +269,19 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) if (test_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, vcpu->arch.features) || test_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, vcpu->arch.features)) { - if (kvm_vcpu_enable_ptrauth(vcpu)) + if (kvm_vcpu_enable_ptrauth(vcpu)) { + ret = -EINVAL; goto out; + } } switch (vcpu->arch.target) { default: if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) { - if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1)) + if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1)) { + ret = -EINVAL; goto out; + } pstate = VCPU_RESET_PSTATE_SVC; } else { pstate = VCPU_RESET_PSTATE_EL1; diff --git a/arch/arm64/kvm/vgic/vgic-v4.c b/arch/arm64/kvm/vgic/vgic-v4.c index 27ac833e5ec7..b5fa73c9fd35 100644 --- a/arch/arm64/kvm/vgic/vgic-v4.c +++ b/arch/arm64/kvm/vgic/vgic-v4.c @@ -90,7 +90,15 @@ static irqreturn_t vgic_v4_doorbell_handler(int irq, void *info) !irqd_irq_disabled(&irq_to_desc(irq)->irq_data)) disable_irq_nosync(irq); + /* + * The v4.1 doorbell can fire concurrently with the vPE being + * made non-resident. Ensure we only update pending_last + * *after* the non-residency sequence has completed. + */ + raw_spin_lock(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vpe_lock); vcpu->arch.vgic_cpu.vgic_v3.its_vpe.pending_last = true; + raw_spin_unlock(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vpe_lock); + kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu); kvm_vcpu_kick(vcpu); diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index e631e6425165..1e93cfc7c47a 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -404,11 +404,6 @@ void __init arm64_memblock_init(void) high_memory = __va(memblock_end_of_DRAM() - 1) + 1; dma_contiguous_reserve(arm64_dma32_phys_limit); - -#ifdef CONFIG_ARM64_4K_PAGES - hugetlb_cma_reserve(PUD_SHIFT - PAGE_SHIFT); -#endif - } void __init bootmem_init(void) @@ -424,6 +419,16 @@ void __init bootmem_init(void) min_low_pfn = min; arm64_numa_init(); + + /* + * must be done after arm64_numa_init() which calls numa_init() to + * initialize node_online_map that gets used in hugetlb_cma_reserve() + * while allocating required CMA size across online nodes. + */ +#ifdef CONFIG_ARM64_4K_PAGES + hugetlb_cma_reserve(PUD_SHIFT - PAGE_SHIFT); +#endif + /* * Sparsemem tries to allocate bootmem in memory_present(), so must be * done after the fixed reservations. diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 990929c8837e..1df25f26571d 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -723,6 +723,7 @@ int kern_addr_valid(unsigned long addr) pmd_t *pmdp, pmd; pte_t *ptep, pte; + addr = arch_kasan_reset_tag(addr); if ((((long)addr) >> VA_BITS) != -1UL) return 0; diff --git a/arch/csky/kernel/ftrace.c b/arch/csky/kernel/ftrace.c index 3c425b84e3be..b4a7ec1517ff 100644 --- a/arch/csky/kernel/ftrace.c +++ b/arch/csky/kernel/ftrace.c @@ -72,7 +72,8 @@ static int ftrace_check_current_nop(unsigned long hook) uint16_t olds[7]; unsigned long hook_pos = hook - 2; - if (probe_kernel_read((void *)olds, (void *)hook_pos, sizeof(nops))) + if (copy_from_kernel_nofault((void *)olds, (void *)hook_pos, + sizeof(nops))) return -EFAULT; if (memcmp((void *)nops, (void *)olds, sizeof(nops))) { @@ -97,7 +98,7 @@ static int ftrace_modify_code(unsigned long hook, unsigned long target, make_jbsr(target, hook, call, nolr); - ret = probe_kernel_write((void *)hook_pos, enable ? call : nops, + ret = copy_to_kernel_nofault((void *)hook_pos, enable ? call : nops, sizeof(nops)); if (ret) return -EPERM; diff --git a/arch/ia64/include/asm/sections.h b/arch/ia64/include/asm/sections.h index cea15f2dd38d..3a033d2008b3 100644 --- a/arch/ia64/include/asm/sections.h +++ b/arch/ia64/include/asm/sections.h @@ -35,7 +35,7 @@ static inline void *dereference_function_descriptor(void *ptr) struct fdesc *desc = ptr; void *p; - if (!probe_kernel_address(&desc->ip, p)) + if (!get_kernel_nofault(p, (void *)&desc->ip)) ptr = p; return ptr; } diff --git a/arch/ia64/kernel/ftrace.c b/arch/ia64/kernel/ftrace.c index cee411e647ca..b2ab2d58fb30 100644 --- a/arch/ia64/kernel/ftrace.c +++ b/arch/ia64/kernel/ftrace.c @@ -108,7 +108,7 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code, goto skip_check; /* read the text we want to modify */ - if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE)) + if (copy_from_kernel_nofault(replaced, (void *)ip, MCOUNT_INSN_SIZE)) return -EFAULT; /* Make sure it is what we expect it to be */ @@ -117,7 +117,7 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code, skip_check: /* replace the text with the new text */ - if (probe_kernel_write(((void *)ip), new_code, MCOUNT_INSN_SIZE)) + if (copy_to_kernel_nofault(((void *)ip), new_code, MCOUNT_INSN_SIZE)) return -EPERM; flush_icache_range(ip, ip + MCOUNT_INSN_SIZE); @@ -129,7 +129,7 @@ static int ftrace_make_nop_check(struct dyn_ftrace *rec, unsigned long addr) unsigned char __attribute__((aligned(8))) replaced[MCOUNT_INSN_SIZE]; unsigned long ip = rec->ip; - if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE)) + if (copy_from_kernel_nofault(replaced, (void *)ip, MCOUNT_INSN_SIZE)) return -EFAULT; if (rec->flags & FTRACE_FL_CONVERTED) { struct ftrace_call_insn *call_insn, *tmp_call; diff --git a/arch/m68k/kernel/setup_no.c b/arch/m68k/kernel/setup_no.c index e779b19e0193..f66f4b1d062e 100644 --- a/arch/m68k/kernel/setup_no.c +++ b/arch/m68k/kernel/setup_no.c @@ -138,7 +138,8 @@ void __init setup_arch(char **cmdline_p) pr_debug("MEMORY -> ROMFS=0x%p-0x%06lx MEM=0x%06lx-0x%06lx\n ", __bss_stop, memory_start, memory_start, memory_end); - memblock_add(memory_start, memory_end - memory_start); + memblock_add(_rambase, memory_end - _rambase); + memblock_reserve(_rambase, memory_start - _rambase); /* Keep a copy of command line */ *cmdline_p = &command_line[0]; diff --git a/arch/m68k/mm/mcfmmu.c b/arch/m68k/mm/mcfmmu.c index 29f47923aa46..7d04210d34f0 100644 --- a/arch/m68k/mm/mcfmmu.c +++ b/arch/m68k/mm/mcfmmu.c @@ -174,7 +174,7 @@ void __init cf_bootmem_alloc(void) m68k_memory[0].addr = _rambase; m68k_memory[0].size = _ramend - _rambase; - memblock_add(m68k_memory[0].addr, m68k_memory[0].size); + memblock_add_node(m68k_memory[0].addr, m68k_memory[0].size, 0); /* compute total pages in system */ num_pages = PFN_DOWN(_ramend - _rambase); diff --git a/arch/mips/boot/dts/ingenic/gcw0.dts b/arch/mips/boot/dts/ingenic/gcw0.dts index 8d22828787d8..bc72304a2440 100644 --- a/arch/mips/boot/dts/ingenic/gcw0.dts +++ b/arch/mips/boot/dts/ingenic/gcw0.dts @@ -92,7 +92,7 @@ "MIC1N", "Built-in Mic"; simple-audio-card,pin-switches = "Speaker", "Headphones"; - simple-audio-card,hp-det-gpio = <&gpf 21 GPIO_ACTIVE_HIGH>; + simple-audio-card,hp-det-gpio = <&gpf 21 GPIO_ACTIVE_LOW>; simple-audio-card,aux-devs = <&speaker_amp>, <&headphones_amp>; simple-audio-card,bitclock-master = <&dai_codec>; diff --git a/arch/mips/include/asm/unroll.h b/arch/mips/include/asm/unroll.h index c628747d4ecd..7dd4a80e05d6 100644 --- a/arch/mips/include/asm/unroll.h +++ b/arch/mips/include/asm/unroll.h @@ -19,15 +19,13 @@ \ /* \ * We can't unroll if the number of iterations isn't \ - * compile-time constant. Unfortunately GCC versions \ - * up until 4.6 tend to miss obvious constants & cause \ + * compile-time constant. Unfortunately clang versions \ + * up until 8.0 tend to miss obvious constants & cause \ * this check to fail, even though they go on to \ * generate reasonable code for the switch statement, \ * so we skip the sanity check for those compilers. \ */ \ - BUILD_BUG_ON((CONFIG_GCC_VERSION >= 40700 || \ - CONFIG_CLANG_VERSION >= 80000) && \ - !__builtin_constant_p(times)); \ + BUILD_BUG_ON(!__builtin_constant_p(times)); \ \ switch (times) { \ case 32: fn(__VA_ARGS__); /* fall through */ \ diff --git a/arch/mips/kernel/kprobes.c b/arch/mips/kernel/kprobes.c index 6cfae2411c04..d043c2f897fc 100644 --- a/arch/mips/kernel/kprobes.c +++ b/arch/mips/kernel/kprobes.c @@ -86,9 +86,9 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) goto out; } - if ((probe_kernel_read(&prev_insn, p->addr - 1, - sizeof(mips_instruction)) == 0) && - insn_has_delayslot(prev_insn)) { + if (copy_from_kernel_nofault(&prev_insn, p->addr - 1, + sizeof(mips_instruction)) == 0 && + insn_has_delayslot(prev_insn)) { pr_notice("Kprobes for branch delayslot are not supported\n"); ret = -EINVAL; goto out; diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index 7c32c956156a..f655af68176c 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -723,12 +723,14 @@ static int simulate_loongson3_cpucfg(struct pt_regs *regs, perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, 0); /* Do not emulate on unsupported core models. */ - if (!loongson3_cpucfg_emulation_enabled(¤t_cpu_data)) + preempt_disable(); + if (!loongson3_cpucfg_emulation_enabled(¤t_cpu_data)) { + preempt_enable(); return -1; - + } regs->regs[rd] = loongson3_cpucfg_read_synthesized( ¤t_cpu_data, sel); - + preempt_enable(); return 0; } @@ -2169,6 +2171,7 @@ static void configure_status(void) change_c0_status(ST0_CU|ST0_MX|ST0_RE|ST0_FR|ST0_BEV|ST0_TS|ST0_KX|ST0_SX|ST0_UX, status_set); + back_to_back_c0_hazard(); } unsigned int hwrena; diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c index 5ae82d925197..d242300cacc0 100644 --- a/arch/mips/kvm/emulate.c +++ b/arch/mips/kvm/emulate.c @@ -1722,6 +1722,7 @@ enum emulation_result kvm_mips_emulate_store(union mips_instruction inst, vcpu->arch.gprs[rt], *(u32 *)data); break; +#if defined(CONFIG_64BIT) && defined(CONFIG_KVM_MIPS_VZ) case sdl_op: run->mmio.phys_addr = kvm_mips_callbacks->gva_to_gpa( vcpu->arch.host_cp0_badvaddr) & (~0x7); @@ -1815,6 +1816,7 @@ enum emulation_result kvm_mips_emulate_store(union mips_instruction inst, vcpu->arch.pc, vcpu->arch.host_cp0_badvaddr, vcpu->arch.gprs[rt], *(u64 *)data); break; +#endif #ifdef CONFIG_CPU_LOONGSON64 case sdc2_op: @@ -2002,6 +2004,7 @@ enum emulation_result kvm_mips_emulate_load(union mips_instruction inst, } break; +#if defined(CONFIG_64BIT) && defined(CONFIG_KVM_MIPS_VZ) case ldl_op: run->mmio.phys_addr = kvm_mips_callbacks->gva_to_gpa( vcpu->arch.host_cp0_badvaddr) & (~0x7); @@ -2073,6 +2076,7 @@ enum emulation_result kvm_mips_emulate_load(union mips_instruction inst, break; } break; +#endif #ifdef CONFIG_CPU_LOONGSON64 case ldc2_op: diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index 521bd5891e84..666d3350b4ac 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -67,8 +67,10 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { VCPU_STAT("vz_ghfc", vz_ghfc_exits), VCPU_STAT("vz_gpa", vz_gpa_exits), VCPU_STAT("vz_resvd", vz_resvd_exits), +#ifdef CONFIG_CPU_LOONGSON64 VCPU_STAT("vz_cpucfg", vz_cpucfg_exits), #endif +#endif VCPU_STAT("halt_successful_poll", halt_successful_poll), VCPU_STAT("halt_attempted_poll", halt_attempted_poll), VCPU_STAT("halt_poll_invalid", halt_poll_invalid), diff --git a/arch/mips/lantiq/xway/sysctrl.c b/arch/mips/lantiq/xway/sysctrl.c index aa37545ebe8f..b10342018d19 100644 --- a/arch/mips/lantiq/xway/sysctrl.c +++ b/arch/mips/lantiq/xway/sysctrl.c @@ -514,8 +514,8 @@ void __init ltq_soc_init(void) clkdev_add_pmu("1e10b308.eth", NULL, 0, 0, PMU_SWITCH | PMU_PPE_DP | PMU_PPE_TC); clkdev_add_pmu("1da00000.usif", "NULL", 1, 0, PMU_USIF); - clkdev_add_pmu("1e108000.gswip", "gphy0", 0, 0, PMU_GPHY); - clkdev_add_pmu("1e108000.gswip", "gphy1", 0, 0, PMU_GPHY); + clkdev_add_pmu("1e108000.switch", "gphy0", 0, 0, PMU_GPHY); + clkdev_add_pmu("1e108000.switch", "gphy1", 0, 0, PMU_GPHY); clkdev_add_pmu("1e103100.deu", NULL, 1, 0, PMU_DEU); clkdev_add_pmu("1e116000.mei", "afe", 1, 2, PMU_ANALOG_DSL_AFE); clkdev_add_pmu("1e116000.mei", "dfe", 1, 0, PMU_DFE); @@ -538,8 +538,8 @@ void __init ltq_soc_init(void) PMU_SWITCH | PMU_PPE_DPLUS | PMU_PPE_DPLUM | PMU_PPE_EMA | PMU_PPE_TC | PMU_PPE_SLL01 | PMU_PPE_QSB | PMU_PPE_TOP); - clkdev_add_pmu("1e108000.gswip", "gphy0", 0, 0, PMU_GPHY); - clkdev_add_pmu("1e108000.gswip", "gphy1", 0, 0, PMU_GPHY); + clkdev_add_pmu("1e108000.switch", "gphy0", 0, 0, PMU_GPHY); + clkdev_add_pmu("1e108000.switch", "gphy1", 0, 0, PMU_GPHY); clkdev_add_pmu("1e103000.sdio", NULL, 1, 0, PMU_SDIO); clkdev_add_pmu("1e103100.deu", NULL, 1, 0, PMU_DEU); clkdev_add_pmu("1e116000.mei", "dfe", 1, 0, PMU_DFE); diff --git a/arch/mips/pci/pci-xtalk-bridge.c b/arch/mips/pci/pci-xtalk-bridge.c index 3b2552fb7735..5958217861b8 100644 --- a/arch/mips/pci/pci-xtalk-bridge.c +++ b/arch/mips/pci/pci-xtalk-bridge.c @@ -627,9 +627,10 @@ static int bridge_probe(struct platform_device *pdev) return -ENOMEM; domain = irq_domain_create_hierarchy(parent, 0, 8, fn, &bridge_domain_ops, NULL); - irq_domain_free_fwnode(fn); - if (!domain) + if (!domain) { + irq_domain_free_fwnode(fn); return -ENOMEM; + } pci_set_flags(PCI_PROBE_ONLY); diff --git a/arch/nds32/kernel/ftrace.c b/arch/nds32/kernel/ftrace.c index 22ab77ea27ad..3763b3f8c3db 100644 --- a/arch/nds32/kernel/ftrace.c +++ b/arch/nds32/kernel/ftrace.c @@ -131,13 +131,14 @@ static int __ftrace_modify_code(unsigned long pc, unsigned long *old_insn, unsigned long orig_insn[3]; if (validate) { - if (probe_kernel_read(orig_insn, (void *)pc, MCOUNT_INSN_SIZE)) + if (copy_from_kernel_nofault(orig_insn, (void *)pc, + MCOUNT_INSN_SIZE)) return -EFAULT; if (memcmp(orig_insn, old_insn, MCOUNT_INSN_SIZE)) return -EINVAL; } - if (probe_kernel_write((void *)pc, new_insn, MCOUNT_INSN_SIZE)) + if (copy_to_kernel_nofault((void *)pc, new_insn, MCOUNT_INSN_SIZE)) return -EPERM; return 0; diff --git a/arch/openrisc/kernel/dma.c b/arch/openrisc/kernel/dma.c index c152a68811dd..345727638d52 100644 --- a/arch/openrisc/kernel/dma.c +++ b/arch/openrisc/kernel/dma.c @@ -74,8 +74,11 @@ void *arch_dma_set_uncached(void *cpu_addr, size_t size) * We need to iterate through the pages, clearing the dcache for * them and setting the cache-inhibit bit. */ + mmap_read_lock(&init_mm); error = walk_page_range(&init_mm, va, va + size, &set_nocache_walk_ops, NULL); + mmap_read_unlock(&init_mm); + if (error) return ERR_PTR(error); return cpu_addr; @@ -85,9 +88,11 @@ void arch_dma_clear_uncached(void *cpu_addr, size_t size) { unsigned long va = (unsigned long)cpu_addr; + mmap_read_lock(&init_mm); /* walk_page_range shouldn't be able to fail here */ WARN_ON(walk_page_range(&init_mm, va, va + size, &clear_nocache_walk_ops, NULL)); + mmap_read_unlock(&init_mm); } void arch_sync_dma_for_device(phys_addr_t addr, size_t size, diff --git a/arch/parisc/kernel/ftrace.c b/arch/parisc/kernel/ftrace.c index b836fc61a24f..1df0f67ed667 100644 --- a/arch/parisc/kernel/ftrace.c +++ b/arch/parisc/kernel/ftrace.c @@ -172,7 +172,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) ip = (void *)(rec->ip + 4 - size); - ret = probe_kernel_read(insn, ip, size); + ret = copy_from_kernel_nofault(insn, ip, size); if (ret) return ret; diff --git a/arch/parisc/kernel/kgdb.c b/arch/parisc/kernel/kgdb.c index 664278db9b97..c4554ac13eac 100644 --- a/arch/parisc/kernel/kgdb.c +++ b/arch/parisc/kernel/kgdb.c @@ -154,8 +154,8 @@ void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long ip) int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt) { - int ret = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr, - BREAK_INSTR_SIZE); + int ret = copy_from_kernel_nofault(bpt->saved_instr, + (char *)bpt->bpt_addr, BREAK_INSTR_SIZE); if (ret) return ret; diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index 230a6422b99f..b7abb12edd3a 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -293,7 +293,7 @@ void *dereference_function_descriptor(void *ptr) Elf64_Fdesc *desc = ptr; void *p; - if (!probe_kernel_address(&desc->addr, p)) + if (!get_kernel_nofault(p, (void *)&desc->addr)) ptr = p; return ptr; } diff --git a/arch/parisc/lib/memcpy.c b/arch/parisc/lib/memcpy.c index 94a9fe2702c2..4b75388190b4 100644 --- a/arch/parisc/lib/memcpy.c +++ b/arch/parisc/lib/memcpy.c @@ -57,7 +57,7 @@ void * memcpy(void * dst,const void *src, size_t count) EXPORT_SYMBOL(raw_copy_in_user); EXPORT_SYMBOL(memcpy); -bool probe_kernel_read_allowed(const void *unsafe_src, size_t size) +bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size) { if ((unsigned long)unsafe_src < PAGE_SIZE) return false; diff --git a/arch/powerpc/include/asm/icswx.h b/arch/powerpc/include/asm/icswx.h index 965b1f39b2a5..b0c70a35fd0e 100644 --- a/arch/powerpc/include/asm/icswx.h +++ b/arch/powerpc/include/asm/icswx.h @@ -77,6 +77,8 @@ struct coprocessor_completion_block { #define CSB_CC_CHAIN (37) #define CSB_CC_SEQUENCE (38) #define CSB_CC_HW (39) +/* P9 DD2 NX Workbook 3.2 (Table 4-36): Address translation fault */ +#define CSB_CC_FAULT_ADDRESS (250) #define CSB_SIZE (0x10) #define CSB_ALIGN CSB_SIZE diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h index b56f14160ae5..b0afbdd07740 100644 --- a/arch/powerpc/include/asm/nohash/32/pgtable.h +++ b/arch/powerpc/include/asm/nohash/32/pgtable.h @@ -205,10 +205,6 @@ static inline void pmd_clear(pmd_t *pmdp) *pmdp = __pmd(0); } -/* to find an entry in a page-table-directory */ -#define pgd_index(address) ((address) >> PGDIR_SHIFT) -#define pgd_offset(mm, address) ((mm)->pgd + pgd_index(address)) - /* * PTE updates. This function is called whenever an existing * valid PTE is updated. This does -not- include set_pte_at() @@ -230,6 +226,8 @@ static inline void pmd_clear(pmd_t *pmdp) * For other page sizes, we have a single entry in the table. */ #ifdef CONFIG_PPC_8xx +static pmd_t *pmd_off(struct mm_struct *mm, unsigned long addr); + static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, pte_t *p, unsigned long clr, unsigned long set, int huge) { @@ -237,7 +235,7 @@ static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, p pte_basic_t old = pte_val(*p); pte_basic_t new = (old & ~(pte_basic_t)clr) | set; int num, i; - pmd_t *pmd = pmd_offset(pud_offset(p4d_offset(pgd_offset(mm, addr), addr), addr), addr); + pmd_t *pmd = pmd_off(mm, addr); if (!huge) num = PAGE_SIZE / SZ_4K; @@ -286,6 +284,16 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, return __pte(pte_update(mm, addr, ptep, ~0, 0, 0)); } +#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PPC_16K_PAGES) +#define __HAVE_ARCH_PTEP_GET +static inline pte_t ptep_get(pte_t *ptep) +{ + pte_t pte = {READ_ONCE(ptep->pte), 0, 0, 0}; + + return pte; +} +#endif + #define __HAVE_ARCH_PTEP_SET_WRPROTECT static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h index d19871763ed4..324d7b298ec3 100644 --- a/arch/powerpc/include/asm/sections.h +++ b/arch/powerpc/include/asm/sections.h @@ -85,7 +85,7 @@ static inline void *dereference_function_descriptor(void *ptr) struct ppc64_opd_entry *desc = ptr; void *p; - if (!probe_kernel_address(&desc->funcaddr, p)) + if (!get_kernel_nofault(p, (void *)&desc->funcaddr)) ptr = p; return ptr; } diff --git a/arch/powerpc/include/uapi/asm/papr_pdsm.h b/arch/powerpc/include/uapi/asm/papr_pdsm.h new file mode 100644 index 000000000000..9ccecc1d6840 --- /dev/null +++ b/arch/powerpc/include/uapi/asm/papr_pdsm.h @@ -0,0 +1,132 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * PAPR nvDimm Specific Methods (PDSM) and structs for libndctl + * + * (C) Copyright IBM 2020 + * + * Author: Vaibhav Jain <vaibhav at linux.ibm.com> + */ + +#ifndef _UAPI_ASM_POWERPC_PAPR_PDSM_H_ +#define _UAPI_ASM_POWERPC_PAPR_PDSM_H_ + +#include <linux/types.h> +#include <linux/ndctl.h> + +/* + * PDSM Envelope: + * + * The ioctl ND_CMD_CALL exchange data between user-space and kernel via + * envelope which consists of 2 headers sections and payload sections as + * illustrated below: + * +-----------------+---------------+---------------------------+ + * | 64-Bytes | 8-Bytes | Max 184-Bytes | + * +-----------------+---------------+---------------------------+ + * | ND-HEADER | PDSM-HEADER | PDSM-PAYLOAD | + * +-----------------+---------------+---------------------------+ + * | nd_family | | | + * | nd_size_out | cmd_status | | + * | nd_size_in | reserved | nd_pdsm_payload | + * | nd_command | payload --> | | + * | nd_fw_size | | | + * | nd_payload ---> | | | + * +---------------+-----------------+---------------------------+ + * + * ND Header: + * This is the generic libnvdimm header described as 'struct nd_cmd_pkg' + * which is interpreted by libnvdimm before passed on to papr_scm. Important + * member fields used are: + * 'nd_family' : (In) NVDIMM_FAMILY_PAPR_SCM + * 'nd_size_in' : (In) PDSM-HEADER + PDSM-IN-PAYLOAD (usually 0) + * 'nd_size_out' : (In) PDSM-HEADER + PDSM-RETURN-PAYLOAD + * 'nd_command' : (In) One of PAPR_PDSM_XXX + * 'nd_fw_size' : (Out) PDSM-HEADER + size of actual payload returned + * + * PDSM Header: + * This is papr-scm specific header that precedes the payload. This is defined + * as nd_cmd_pdsm_pkg. Following fields aare available in this header: + * + * 'cmd_status' : (Out) Errors if any encountered while servicing PDSM. + * 'reserved' : Not used, reserved for future and should be set to 0. + * 'payload' : A union of all the possible payload structs + * + * PDSM Payload: + * + * The layout of the PDSM Payload is defined by various structs shared between + * papr_scm and libndctl so that contents of payload can be interpreted. As such + * its defined as a union of all possible payload structs as + * 'union nd_pdsm_payload'. Based on the value of 'nd_cmd_pkg.nd_command' + * appropriate member of the union is accessed. + */ + +/* Max payload size that we can handle */ +#define ND_PDSM_PAYLOAD_MAX_SIZE 184 + +/* Max payload size that we can handle */ +#define ND_PDSM_HDR_SIZE \ + (sizeof(struct nd_pkg_pdsm) - ND_PDSM_PAYLOAD_MAX_SIZE) + +/* Various nvdimm health indicators */ +#define PAPR_PDSM_DIMM_HEALTHY 0 +#define PAPR_PDSM_DIMM_UNHEALTHY 1 +#define PAPR_PDSM_DIMM_CRITICAL 2 +#define PAPR_PDSM_DIMM_FATAL 3 + +/* + * Struct exchanged between kernel & ndctl in for PAPR_PDSM_HEALTH + * Various flags indicate the health status of the dimm. + * + * extension_flags : Any extension fields present in the struct. + * dimm_unarmed : Dimm not armed. So contents wont persist. + * dimm_bad_shutdown : Previous shutdown did not persist contents. + * dimm_bad_restore : Contents from previous shutdown werent restored. + * dimm_scrubbed : Contents of the dimm have been scrubbed. + * dimm_locked : Contents of the dimm cant be modified until CEC reboot + * dimm_encrypted : Contents of dimm are encrypted. + * dimm_health : Dimm health indicator. One of PAPR_PDSM_DIMM_XXXX + */ +struct nd_papr_pdsm_health { + union { + struct { + __u32 extension_flags; + __u8 dimm_unarmed; + __u8 dimm_bad_shutdown; + __u8 dimm_bad_restore; + __u8 dimm_scrubbed; + __u8 dimm_locked; + __u8 dimm_encrypted; + __u16 dimm_health; + }; + __u8 buf[ND_PDSM_PAYLOAD_MAX_SIZE]; + }; +}; + +/* + * Methods to be embedded in ND_CMD_CALL request. These are sent to the kernel + * via 'nd_cmd_pkg.nd_command' member of the ioctl struct + */ +enum papr_pdsm { + PAPR_PDSM_MIN = 0x0, + PAPR_PDSM_HEALTH, + PAPR_PDSM_MAX, +}; + +/* Maximal union that can hold all possible payload types */ +union nd_pdsm_payload { + struct nd_papr_pdsm_health health; + __u8 buf[ND_PDSM_PAYLOAD_MAX_SIZE]; +} __packed; + +/* + * PDSM-header + payload expected with ND_CMD_CALL ioctl from libnvdimm + * Valid member of union 'payload' is identified via 'nd_cmd_pkg.nd_command' + * that should always precede this struct when sent to papr_scm via CMD_CALL + * interface. + */ +struct nd_pkg_pdsm { + __s32 cmd_status; /* Out: Sub-cmd status returned back */ + __u16 reserved[2]; /* Ignored and to be set as '0' */ + union nd_pdsm_payload payload; +} __packed; + +#endif /* _UAPI_ASM_POWERPC_PAPR_PDSM_H_ */ diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index e70ebb5c318c..0fc8bad878b2 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -270,7 +270,7 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFSET(CPU_FTR_CFAR) .endif - ld r10,PACA_EXGEN+EX_CTR(r13) + ld r10,IAREA+EX_CTR(r13) mtctr r10 BEGIN_FTR_SECTION ld r10,IAREA+EX_PPR(r13) @@ -298,7 +298,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) .if IKVM_SKIP 89: mtocrf 0x80,r9 - ld r10,PACA_EXGEN+EX_CTR(r13) + ld r10,IAREA+EX_CTR(r13) mtctr r10 ld r9,IAREA+EX_R9(r13) ld r10,IAREA+EX_R10(r13) @@ -2551,7 +2551,7 @@ EXC_VIRT_NONE(0x5400, 0x100) INT_DEFINE_BEGIN(denorm_exception) IVEC=0x1500 IHSRR=1 - IBRANCH_COMMON=0 + IBRANCH_TO_COMMON=0 IKVM_REAL=1 INT_DEFINE_END(denorm_exception) diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c index 652b2852bea3..409080208a6c 100644 --- a/arch/powerpc/kernel/kgdb.c +++ b/arch/powerpc/kernel/kgdb.c @@ -421,7 +421,7 @@ int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt) unsigned int instr; struct ppc_inst *addr = (struct ppc_inst *)bpt->bpt_addr; - err = probe_kernel_address(addr, instr); + err = get_kernel_nofault(instr, (unsigned *) addr); if (err) return err; diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index 6f96f65ebfe8..9cc792a3a6a9 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -289,7 +289,7 @@ int kprobe_handler(struct pt_regs *regs) if (!p) { unsigned int instr; - if (probe_kernel_address(addr, instr)) + if (get_kernel_nofault(instr, addr)) goto no_kprobe; if (instr != BREAKPOINT_INSTRUCTION) { diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index f4c2fa190192..ae2b188365b1 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -756,7 +756,8 @@ int module_trampoline_target(struct module *mod, unsigned long addr, stub = (struct ppc64_stub_entry *)addr; - if (probe_kernel_read(&magic, &stub->magic, sizeof(magic))) { + if (copy_from_kernel_nofault(&magic, &stub->magic, + sizeof(magic))) { pr_err("%s: fault reading magic for stub %lx for %s\n", __func__, addr, mod->name); return -EFAULT; } @@ -766,7 +767,8 @@ int module_trampoline_target(struct module *mod, unsigned long addr, return -EFAULT; } - if (probe_kernel_read(&funcdata, &stub->funcdata, sizeof(funcdata))) { + if (copy_from_kernel_nofault(&funcdata, &stub->funcdata, + sizeof(funcdata))) { pr_err("%s: fault reading funcdata for stub %lx for %s\n", __func__, addr, mod->name); return -EFAULT; } diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index 2168372b792d..74da65aacbc9 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -87,7 +87,7 @@ static void *__init alloc_shared_lppaca(unsigned long size, unsigned long align, * This is very early in boot, so no harm done if the kernel crashes at * this point. */ - BUG_ON(shared_lppaca_size >= shared_lppaca_total_size); + BUG_ON(shared_lppaca_size > shared_lppaca_total_size); return ptr; } diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 7bb7faf84490..4650b9bb217f 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1252,29 +1252,31 @@ struct task_struct *__switch_to(struct task_struct *prev, static void show_instructions(struct pt_regs *regs) { int i; + unsigned long nip = regs->nip; unsigned long pc = regs->nip - (NR_INSN_TO_PRINT * 3 / 4 * sizeof(int)); printk("Instruction dump:"); + /* + * If we were executing with the MMU off for instructions, adjust pc + * rather than printing XXXXXXXX. + */ + if (!IS_ENABLED(CONFIG_BOOKE) && !(regs->msr & MSR_IR)) { + pc = (unsigned long)phys_to_virt(pc); + nip = (unsigned long)phys_to_virt(regs->nip); + } + for (i = 0; i < NR_INSN_TO_PRINT; i++) { int instr; if (!(i % 8)) pr_cont("\n"); -#if !defined(CONFIG_BOOKE) - /* If executing with the IMMU off, adjust pc rather - * than print XXXXXXXX. - */ - if (!(regs->msr & MSR_IR)) - pc = (unsigned long)phys_to_virt(pc); -#endif - if (!__kernel_text_address(pc) || - probe_kernel_address((const void *)pc, instr)) { + get_kernel_nofault(instr, (const void *)pc)) { pr_cont("XXXXXXXX "); } else { - if (regs->nip == pc) + if (nip == pc) pr_cont("<%08x> ", instr); else pr_cont("%08x ", instr); @@ -1305,7 +1307,8 @@ void show_user_instructions(struct pt_regs *regs) for (i = 0; i < 8 && n; i++, n--, pc += sizeof(int)) { int instr; - if (probe_user_read(&instr, (void __user *)pc, sizeof(instr))) { + if (copy_from_user_nofault(&instr, (void __user *)pc, + sizeof(instr))) { seq_buf_printf(&s, "XXXXXXXX "); continue; } diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c index 5e399628f51a..c1fede6ec934 100644 --- a/arch/powerpc/kernel/trace/ftrace.c +++ b/arch/powerpc/kernel/trace/ftrace.c @@ -226,7 +226,7 @@ __ftrace_make_nop(struct module *mod, unsigned long ip = rec->ip; unsigned long tramp; - if (probe_kernel_read(&op, (void *)ip, MCOUNT_INSN_SIZE)) + if (copy_from_kernel_nofault(&op, (void *)ip, MCOUNT_INSN_SIZE)) return -EFAULT; /* Make sure that that this is still a 24bit jump */ @@ -249,7 +249,7 @@ __ftrace_make_nop(struct module *mod, pr_devel("ip:%lx jumps to %lx", ip, tramp); /* Find where the trampoline jumps to */ - if (probe_kernel_read(jmp, (void *)tramp, sizeof(jmp))) { + if (copy_from_kernel_nofault(jmp, (void *)tramp, sizeof(jmp))) { pr_err("Failed to read %lx\n", tramp); return -EFAULT; } diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index 3cb0c9843d01..6a73714759ba 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -40,7 +40,8 @@ unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid, /* Can't access quadrants 1 or 2 in non-HV mode, call the HV to do it */ if (kvmhv_on_pseries()) return plpar_hcall_norets(H_COPY_TOFROM_GUEST, lpid, pid, eaddr, - __pa(to), __pa(from), n); + (to != NULL) ? __pa(to): 0, + (from != NULL) ? __pa(from): 0, n); quadrant = 1; if (!pid) @@ -64,9 +65,9 @@ unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid, isync(); if (is_load) - ret = probe_user_read(to, (const void __user *)from, n); + ret = copy_from_user_nofault(to, (const void __user *)from, n); else - ret = probe_user_write((void __user *)to, from, n); + ret = copy_to_user_nofault((void __user *)to, from, n); /* switch the pid first to avoid running host with unallocated pid */ if (quadrant == 1 && pid != old_pid) diff --git a/arch/powerpc/lib/inst.c b/arch/powerpc/lib/inst.c index aedfd6e31e53..9cc17eb62462 100644 --- a/arch/powerpc/lib/inst.c +++ b/arch/powerpc/lib/inst.c @@ -15,11 +15,11 @@ int probe_user_read_inst(struct ppc_inst *inst, unsigned int val, suffix; int err; - err = probe_user_read(&val, nip, sizeof(val)); + err = copy_from_user_nofault(&val, nip, sizeof(val)); if (err) return err; if (get_op(val) == OP_PREFIX) { - err = probe_user_read(&suffix, (void __user *)nip + 4, 4); + err = copy_from_user_nofault(&suffix, (void __user *)nip + 4, 4); *inst = ppc_inst_prefix(val, suffix); } else { *inst = ppc_inst(val); @@ -33,11 +33,11 @@ int probe_kernel_read_inst(struct ppc_inst *inst, unsigned int val, suffix; int err; - err = probe_kernel_read(&val, src, sizeof(val)); + err = copy_from_kernel_nofault(&val, src, sizeof(val)); if (err) return err; if (get_op(val) == OP_PREFIX) { - err = probe_kernel_read(&suffix, (void *)src + 4, 4); + err = copy_from_kernel_nofault(&suffix, (void *)src + 4, 4); *inst = ppc_inst_prefix(val, suffix); } else { *inst = ppc_inst(val); @@ -51,7 +51,7 @@ int probe_user_read_inst(struct ppc_inst *inst, unsigned int val; int err; - err = probe_user_read(&val, nip, sizeof(val)); + err = copy_from_user_nofault(&val, nip, sizeof(val)); if (!err) *inst = ppc_inst(val); @@ -64,7 +64,7 @@ int probe_kernel_read_inst(struct ppc_inst *inst, unsigned int val; int err; - err = probe_kernel_read(&val, src, sizeof(val)); + err = copy_from_kernel_nofault(&val, src, sizeof(val)); if (!err) *inst = ppc_inst(val); diff --git a/arch/powerpc/mm/book3s64/pkeys.c b/arch/powerpc/mm/book3s64/pkeys.c index 1199fc2bfaec..d174106bab67 100644 --- a/arch/powerpc/mm/book3s64/pkeys.c +++ b/arch/powerpc/mm/book3s64/pkeys.c @@ -353,16 +353,15 @@ static bool pkey_access_permitted(int pkey, bool write, bool execute) int pkey_shift; u64 amr; - if (!is_pkey_enabled(pkey)) - return true; - pkey_shift = pkeyshift(pkey); - if (execute && !(read_iamr() & (IAMR_EX_BIT << pkey_shift))) - return true; + if (execute) + return !(read_iamr() & (IAMR_EX_BIT << pkey_shift)); + + amr = read_amr(); + if (write) + return !(amr & (AMR_WR_BIT << pkey_shift)); - amr = read_amr(); /* Delay reading amr until absolutely needed */ - return ((!write && !(amr & (AMR_RD_BIT << pkey_shift))) || - (write && !(amr & (AMR_WR_BIT << pkey_shift)))); + return !(amr & (AMR_RD_BIT << pkey_shift)); } bool arch_pte_access_permitted(u64 pte, bool write, bool execute) diff --git a/arch/powerpc/mm/nohash/kaslr_booke.c b/arch/powerpc/mm/nohash/kaslr_booke.c index 4a75f2d9bf0e..bce0e5349978 100644 --- a/arch/powerpc/mm/nohash/kaslr_booke.c +++ b/arch/powerpc/mm/nohash/kaslr_booke.c @@ -14,6 +14,7 @@ #include <linux/memblock.h> #include <linux/libfdt.h> #include <linux/crash_core.h> +#include <asm/cacheflush.h> #include <asm/pgalloc.h> #include <asm/prom.h> #include <asm/kdump.h> diff --git a/arch/powerpc/oprofile/backtrace.c b/arch/powerpc/oprofile/backtrace.c index 6f347fa29f41..9db7ada79d10 100644 --- a/arch/powerpc/oprofile/backtrace.c +++ b/arch/powerpc/oprofile/backtrace.c @@ -33,7 +33,8 @@ static unsigned int user_getsp32(unsigned int sp, int is_first) * which means that we've done all that we can do from * interrupt context. */ - if (probe_user_read(stack_frame, (void __user *)p, sizeof(stack_frame))) + if (copy_from_user_nofault(stack_frame, (void __user *)p, + sizeof(stack_frame))) return 0; if (!is_first) @@ -51,7 +52,8 @@ static unsigned long user_getsp64(unsigned long sp, int is_first) { unsigned long stack_frame[3]; - if (probe_user_read(stack_frame, (void __user *)sp, sizeof(stack_frame))) + if (copy_from_user_nofault(stack_frame, (void __user *)sp, + sizeof(stack_frame))) return 0; if (!is_first) diff --git a/arch/powerpc/perf/callchain_32.c b/arch/powerpc/perf/callchain_32.c index f7d888d39cd3..542e68b8eae0 100644 --- a/arch/powerpc/perf/callchain_32.c +++ b/arch/powerpc/perf/callchain_32.c @@ -44,7 +44,7 @@ static int read_user_stack_32(unsigned int __user *ptr, unsigned int *ret) ((unsigned long)ptr & 3)) return -EFAULT; - rc = probe_user_read(ret, ptr, sizeof(*ret)); + rc = copy_from_user_nofault(ret, ptr, sizeof(*ret)); if (IS_ENABLED(CONFIG_PPC64) && rc) return read_user_stack_slow(ptr, ret, 4); diff --git a/arch/powerpc/perf/callchain_64.c b/arch/powerpc/perf/callchain_64.c index 814d1c2c2b9c..fa2a1b83b9b0 100644 --- a/arch/powerpc/perf/callchain_64.c +++ b/arch/powerpc/perf/callchain_64.c @@ -50,7 +50,7 @@ static int read_user_stack_64(unsigned long __user *ptr, unsigned long *ret) ((unsigned long)ptr & 7)) return -EFAULT; - if (!probe_user_read(ret, ptr, sizeof(*ret))) + if (!copy_from_user_nofault(ret, ptr, sizeof(*ret))) return 0; return read_user_stack_slow(ptr, ret, 8); diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 13b9dd5e4a76..cd6a742ac6ef 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -418,14 +418,16 @@ static __u64 power_pmu_bhrb_to(u64 addr) __u64 target; if (is_kernel_addr(addr)) { - if (probe_kernel_read(&instr, (void *)addr, sizeof(instr))) + if (copy_from_kernel_nofault(&instr, (void *)addr, + sizeof(instr))) return 0; return branch_target((struct ppc_inst *)&instr); } /* Userspace: need copy instruction here then translate it */ - if (probe_user_read(&instr, (unsigned int __user *)addr, sizeof(instr))) + if (copy_from_user_nofault(&instr, (unsigned int __user *)addr, + sizeof(instr))) return 0; target = branch_target((struct ppc_inst *)&instr); diff --git a/arch/powerpc/platforms/cell/spu_callbacks.c b/arch/powerpc/platforms/cell/spu_callbacks.c index cbee3666da07..abdef9bcf432 100644 --- a/arch/powerpc/platforms/cell/spu_callbacks.c +++ b/arch/powerpc/platforms/cell/spu_callbacks.c @@ -35,7 +35,7 @@ */ static void *spu_syscall_table[] = { -#define __SYSCALL(nr, entry) entry, +#define __SYSCALL(nr, entry) [nr] = entry, #include <asm/syscall_table_spu.h> #undef __SYSCALL }; diff --git a/arch/powerpc/platforms/powernv/vas-fault.c b/arch/powerpc/platforms/powernv/vas-fault.c index 266a6ca5e15e..3d21fce254b7 100644 --- a/arch/powerpc/platforms/powernv/vas-fault.c +++ b/arch/powerpc/platforms/powernv/vas-fault.c @@ -79,7 +79,7 @@ static void update_csb(struct vas_window *window, csb_addr = (void __user *)be64_to_cpu(crb->csb_addr); memset(&csb, 0, sizeof(csb)); - csb.cc = CSB_CC_TRANSLATION; + csb.cc = CSB_CC_FAULT_ADDRESS; csb.ce = CSB_CE_TERMINATION; csb.cs = 0; csb.count = 0; diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index f35592423380..9c569078a09f 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -12,16 +12,57 @@ #include <linux/libnvdimm.h> #include <linux/platform_device.h> #include <linux/delay.h> +#include <linux/seq_buf.h> #include <asm/plpar_wrappers.h> +#include <asm/papr_pdsm.h> #define BIND_ANY_ADDR (~0ul) #define PAPR_SCM_DIMM_CMD_MASK \ ((1ul << ND_CMD_GET_CONFIG_SIZE) | \ (1ul << ND_CMD_GET_CONFIG_DATA) | \ - (1ul << ND_CMD_SET_CONFIG_DATA)) - + (1ul << ND_CMD_SET_CONFIG_DATA) | \ + (1ul << ND_CMD_CALL)) + +/* DIMM health bitmap bitmap indicators */ +/* SCM device is unable to persist memory contents */ +#define PAPR_PMEM_UNARMED (1ULL << (63 - 0)) +/* SCM device failed to persist memory contents */ +#define PAPR_PMEM_SHUTDOWN_DIRTY (1ULL << (63 - 1)) +/* SCM device contents are persisted from previous IPL */ +#define PAPR_PMEM_SHUTDOWN_CLEAN (1ULL << (63 - 2)) +/* SCM device contents are not persisted from previous IPL */ +#define PAPR_PMEM_EMPTY (1ULL << (63 - 3)) +/* SCM device memory life remaining is critically low */ +#define PAPR_PMEM_HEALTH_CRITICAL (1ULL << (63 - 4)) +/* SCM device will be garded off next IPL due to failure */ +#define PAPR_PMEM_HEALTH_FATAL (1ULL << (63 - 5)) +/* SCM contents cannot persist due to current platform health status */ +#define PAPR_PMEM_HEALTH_UNHEALTHY (1ULL << (63 - 6)) +/* SCM device is unable to persist memory contents in certain conditions */ +#define PAPR_PMEM_HEALTH_NON_CRITICAL (1ULL << (63 - 7)) +/* SCM device is encrypted */ +#define PAPR_PMEM_ENCRYPTED (1ULL << (63 - 8)) +/* SCM device has been scrubbed and locked */ +#define PAPR_PMEM_SCRUBBED_AND_LOCKED (1ULL << (63 - 9)) + +/* Bits status indicators for health bitmap indicating unarmed dimm */ +#define PAPR_PMEM_UNARMED_MASK (PAPR_PMEM_UNARMED | \ + PAPR_PMEM_HEALTH_UNHEALTHY) + +/* Bits status indicators for health bitmap indicating unflushed dimm */ +#define PAPR_PMEM_BAD_SHUTDOWN_MASK (PAPR_PMEM_SHUTDOWN_DIRTY) + +/* Bits status indicators for health bitmap indicating unrestored dimm */ +#define PAPR_PMEM_BAD_RESTORE_MASK (PAPR_PMEM_EMPTY) + +/* Bit status indicators for smart event notification */ +#define PAPR_PMEM_SMART_EVENT_MASK (PAPR_PMEM_HEALTH_CRITICAL | \ + PAPR_PMEM_HEALTH_FATAL | \ + PAPR_PMEM_HEALTH_UNHEALTHY) + +/* private struct associated with each region */ struct papr_scm_priv { struct platform_device *pdev; struct device_node *dn; @@ -39,6 +80,15 @@ struct papr_scm_priv { struct resource res; struct nd_region *region; struct nd_interleave_set nd_set; + + /* Protect dimm health data from concurrent read/writes */ + struct mutex health_mutex; + + /* Last time the health information of the dimm was updated */ + unsigned long lasthealth_jiffies; + + /* Health information for the dimm */ + u64 health_bitmap; }; static int drc_pmem_bind(struct papr_scm_priv *p) @@ -144,6 +194,61 @@ err_out: return drc_pmem_bind(p); } +/* + * Issue hcall to retrieve dimm health info and populate papr_scm_priv with the + * health information. + */ +static int __drc_pmem_query_health(struct papr_scm_priv *p) +{ + unsigned long ret[PLPAR_HCALL_BUFSIZE]; + long rc; + + /* issue the hcall */ + rc = plpar_hcall(H_SCM_HEALTH, ret, p->drc_index); + if (rc != H_SUCCESS) { + dev_err(&p->pdev->dev, + "Failed to query health information, Err:%ld\n", rc); + return -ENXIO; + } + + p->lasthealth_jiffies = jiffies; + p->health_bitmap = ret[0] & ret[1]; + + dev_dbg(&p->pdev->dev, + "Queried dimm health info. Bitmap:0x%016lx Mask:0x%016lx\n", + ret[0], ret[1]); + + return 0; +} + +/* Min interval in seconds for assuming stable dimm health */ +#define MIN_HEALTH_QUERY_INTERVAL 60 + +/* Query cached health info and if needed call drc_pmem_query_health */ +static int drc_pmem_query_health(struct papr_scm_priv *p) +{ + unsigned long cache_timeout; + int rc; + + /* Protect concurrent modifications to papr_scm_priv */ + rc = mutex_lock_interruptible(&p->health_mutex); + if (rc) + return rc; + + /* Jiffies offset for which the health data is assumed to be same */ + cache_timeout = p->lasthealth_jiffies + + msecs_to_jiffies(MIN_HEALTH_QUERY_INTERVAL * 1000); + + /* Fetch new health info is its older than MIN_HEALTH_QUERY_INTERVAL */ + if (time_after(jiffies, cache_timeout)) + rc = __drc_pmem_query_health(p); + else + /* Assume cached health data is valid */ + rc = 0; + + mutex_unlock(&p->health_mutex); + return rc; +} static int papr_scm_meta_get(struct papr_scm_priv *p, struct nd_cmd_get_config_data_hdr *hdr) @@ -246,16 +351,250 @@ static int papr_scm_meta_set(struct papr_scm_priv *p, return 0; } +/* + * Do a sanity checks on the inputs args to dimm-control function and return + * '0' if valid. Validation of PDSM payloads happens later in + * papr_scm_service_pdsm. + */ +static int is_cmd_valid(struct nvdimm *nvdimm, unsigned int cmd, void *buf, + unsigned int buf_len) +{ + unsigned long cmd_mask = PAPR_SCM_DIMM_CMD_MASK; + struct nd_cmd_pkg *nd_cmd; + struct papr_scm_priv *p; + enum papr_pdsm pdsm; + + /* Only dimm-specific calls are supported atm */ + if (!nvdimm) + return -EINVAL; + + /* get the provider data from struct nvdimm */ + p = nvdimm_provider_data(nvdimm); + + if (!test_bit(cmd, &cmd_mask)) { + dev_dbg(&p->pdev->dev, "Unsupported cmd=%u\n", cmd); + return -EINVAL; + } + + /* For CMD_CALL verify pdsm request */ + if (cmd == ND_CMD_CALL) { + /* Verify the envelope and envelop size */ + if (!buf || + buf_len < (sizeof(struct nd_cmd_pkg) + ND_PDSM_HDR_SIZE)) { + dev_dbg(&p->pdev->dev, "Invalid pkg size=%u\n", + buf_len); + return -EINVAL; + } + + /* Verify that the nd_cmd_pkg.nd_family is correct */ + nd_cmd = (struct nd_cmd_pkg *)buf; + + if (nd_cmd->nd_family != NVDIMM_FAMILY_PAPR) { + dev_dbg(&p->pdev->dev, "Invalid pkg family=0x%llx\n", + nd_cmd->nd_family); + return -EINVAL; + } + + pdsm = (enum papr_pdsm)nd_cmd->nd_command; + + /* Verify if the pdsm command is valid */ + if (pdsm <= PAPR_PDSM_MIN || pdsm >= PAPR_PDSM_MAX) { + dev_dbg(&p->pdev->dev, "PDSM[0x%x]: Invalid PDSM\n", + pdsm); + return -EINVAL; + } + + /* Have enough space to hold returned 'nd_pkg_pdsm' header */ + if (nd_cmd->nd_size_out < ND_PDSM_HDR_SIZE) { + dev_dbg(&p->pdev->dev, "PDSM[0x%x]: Invalid payload\n", + pdsm); + return -EINVAL; + } + } + + /* Let the command be further processed */ + return 0; +} + +/* Fetch the DIMM health info and populate it in provided package. */ +static int papr_pdsm_health(struct papr_scm_priv *p, + union nd_pdsm_payload *payload) +{ + int rc; + + /* Ensure dimm health mutex is taken preventing concurrent access */ + rc = mutex_lock_interruptible(&p->health_mutex); + if (rc) + goto out; + + /* Always fetch upto date dimm health data ignoring cached values */ + rc = __drc_pmem_query_health(p); + if (rc) { + mutex_unlock(&p->health_mutex); + goto out; + } + + /* update health struct with various flags derived from health bitmap */ + payload->health = (struct nd_papr_pdsm_health) { + .extension_flags = 0, + .dimm_unarmed = !!(p->health_bitmap & PAPR_PMEM_UNARMED_MASK), + .dimm_bad_shutdown = !!(p->health_bitmap & PAPR_PMEM_BAD_SHUTDOWN_MASK), + .dimm_bad_restore = !!(p->health_bitmap & PAPR_PMEM_BAD_RESTORE_MASK), + .dimm_scrubbed = !!(p->health_bitmap & PAPR_PMEM_SCRUBBED_AND_LOCKED), + .dimm_locked = !!(p->health_bitmap & PAPR_PMEM_SCRUBBED_AND_LOCKED), + .dimm_encrypted = !!(p->health_bitmap & PAPR_PMEM_ENCRYPTED), + .dimm_health = PAPR_PDSM_DIMM_HEALTHY, + }; + + /* Update field dimm_health based on health_bitmap flags */ + if (p->health_bitmap & PAPR_PMEM_HEALTH_FATAL) + payload->health.dimm_health = PAPR_PDSM_DIMM_FATAL; + else if (p->health_bitmap & PAPR_PMEM_HEALTH_CRITICAL) + payload->health.dimm_health = PAPR_PDSM_DIMM_CRITICAL; + else if (p->health_bitmap & PAPR_PMEM_HEALTH_UNHEALTHY) + payload->health.dimm_health = PAPR_PDSM_DIMM_UNHEALTHY; + + /* struct populated hence can release the mutex now */ + mutex_unlock(&p->health_mutex); + rc = sizeof(struct nd_papr_pdsm_health); + +out: + return rc; +} + +/* + * 'struct pdsm_cmd_desc' + * Identifies supported PDSMs' expected length of in/out payloads + * and pdsm service function. + * + * size_in : Size of input payload if any in the PDSM request. + * size_out : Size of output payload if any in the PDSM request. + * service : Service function for the PDSM request. Return semantics: + * rc < 0 : Error servicing PDSM and rc indicates the error. + * rc >=0 : Serviced successfully and 'rc' indicate number of + * bytes written to payload. + */ +struct pdsm_cmd_desc { + u32 size_in; + u32 size_out; + int (*service)(struct papr_scm_priv *dimm, + union nd_pdsm_payload *payload); +}; + +/* Holds all supported PDSMs' command descriptors */ +static const struct pdsm_cmd_desc __pdsm_cmd_descriptors[] = { + [PAPR_PDSM_MIN] = { + .size_in = 0, + .size_out = 0, + .service = NULL, + }, + /* New PDSM command descriptors to be added below */ + + [PAPR_PDSM_HEALTH] = { + .size_in = 0, + .size_out = sizeof(struct nd_papr_pdsm_health), + .service = papr_pdsm_health, + }, + /* Empty */ + [PAPR_PDSM_MAX] = { + .size_in = 0, + .size_out = 0, + .service = NULL, + }, +}; + +/* Given a valid pdsm cmd return its command descriptor else return NULL */ +static inline const struct pdsm_cmd_desc *pdsm_cmd_desc(enum papr_pdsm cmd) +{ + if (cmd >= 0 || cmd < ARRAY_SIZE(__pdsm_cmd_descriptors)) + return &__pdsm_cmd_descriptors[cmd]; + + return NULL; +} + +/* + * For a given pdsm request call an appropriate service function. + * Returns errors if any while handling the pdsm command package. + */ +static int papr_scm_service_pdsm(struct papr_scm_priv *p, + struct nd_cmd_pkg *pkg) +{ + /* Get the PDSM header and PDSM command */ + struct nd_pkg_pdsm *pdsm_pkg = (struct nd_pkg_pdsm *)pkg->nd_payload; + enum papr_pdsm pdsm = (enum papr_pdsm)pkg->nd_command; + const struct pdsm_cmd_desc *pdsc; + int rc; + + /* Fetch corresponding pdsm descriptor for validation and servicing */ + pdsc = pdsm_cmd_desc(pdsm); + + /* Validate pdsm descriptor */ + /* Ensure that reserved fields are 0 */ + if (pdsm_pkg->reserved[0] || pdsm_pkg->reserved[1]) { + dev_dbg(&p->pdev->dev, "PDSM[0x%x]: Invalid reserved field\n", + pdsm); + return -EINVAL; + } + + /* If pdsm expects some input, then ensure that the size_in matches */ + if (pdsc->size_in && + pkg->nd_size_in != (pdsc->size_in + ND_PDSM_HDR_SIZE)) { + dev_dbg(&p->pdev->dev, "PDSM[0x%x]: Mismatched size_in=%d\n", + pdsm, pkg->nd_size_in); + return -EINVAL; + } + + /* If pdsm wants to return data, then ensure that size_out matches */ + if (pdsc->size_out && + pkg->nd_size_out != (pdsc->size_out + ND_PDSM_HDR_SIZE)) { + dev_dbg(&p->pdev->dev, "PDSM[0x%x]: Mismatched size_out=%d\n", + pdsm, pkg->nd_size_out); + return -EINVAL; + } + + /* Service the pdsm */ + if (pdsc->service) { + dev_dbg(&p->pdev->dev, "PDSM[0x%x]: Servicing..\n", pdsm); + + rc = pdsc->service(p, &pdsm_pkg->payload); + + if (rc < 0) { + /* error encountered while servicing pdsm */ + pdsm_pkg->cmd_status = rc; + pkg->nd_fw_size = ND_PDSM_HDR_SIZE; + } else { + /* pdsm serviced and 'rc' bytes written to payload */ + pdsm_pkg->cmd_status = 0; + pkg->nd_fw_size = ND_PDSM_HDR_SIZE + rc; + } + } else { + dev_dbg(&p->pdev->dev, "PDSM[0x%x]: Unsupported PDSM request\n", + pdsm); + pdsm_pkg->cmd_status = -ENOENT; + pkg->nd_fw_size = ND_PDSM_HDR_SIZE; + } + + return pdsm_pkg->cmd_status; +} + static int papr_scm_ndctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, unsigned int cmd, void *buf, unsigned int buf_len, int *cmd_rc) { struct nd_cmd_get_config_size *get_size_hdr; + struct nd_cmd_pkg *call_pkg = NULL; struct papr_scm_priv *p; + int rc; - /* Only dimm-specific calls are supported atm */ - if (!nvdimm) - return -EINVAL; + rc = is_cmd_valid(nvdimm, cmd, buf, buf_len); + if (rc) { + pr_debug("Invalid cmd=0x%x. Err=%d\n", cmd, rc); + return rc; + } + + /* Use a local variable in case cmd_rc pointer is NULL */ + if (!cmd_rc) + cmd_rc = &rc; p = nvdimm_provider_data(nvdimm); @@ -277,7 +616,13 @@ static int papr_scm_ndctl(struct nvdimm_bus_descriptor *nd_desc, *cmd_rc = papr_scm_meta_set(p, buf); break; + case ND_CMD_CALL: + call_pkg = (struct nd_cmd_pkg *)buf; + *cmd_rc = papr_scm_service_pdsm(p, call_pkg); + break; + default: + dev_dbg(&p->pdev->dev, "Unknown command = %d\n", cmd); return -EINVAL; } @@ -286,6 +631,64 @@ static int papr_scm_ndctl(struct nvdimm_bus_descriptor *nd_desc, return 0; } +static ssize_t flags_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nvdimm *dimm = to_nvdimm(dev); + struct papr_scm_priv *p = nvdimm_provider_data(dimm); + struct seq_buf s; + u64 health; + int rc; + + rc = drc_pmem_query_health(p); + if (rc) + return rc; + + /* Copy health_bitmap locally, check masks & update out buffer */ + health = READ_ONCE(p->health_bitmap); + + seq_buf_init(&s, buf, PAGE_SIZE); + if (health & PAPR_PMEM_UNARMED_MASK) + seq_buf_printf(&s, "not_armed "); + + if (health & PAPR_PMEM_BAD_SHUTDOWN_MASK) + seq_buf_printf(&s, "flush_fail "); + + if (health & PAPR_PMEM_BAD_RESTORE_MASK) + seq_buf_printf(&s, "restore_fail "); + + if (health & PAPR_PMEM_ENCRYPTED) + seq_buf_printf(&s, "encrypted "); + + if (health & PAPR_PMEM_SMART_EVENT_MASK) + seq_buf_printf(&s, "smart_notify "); + + if (health & PAPR_PMEM_SCRUBBED_AND_LOCKED) + seq_buf_printf(&s, "scrubbed locked "); + + if (seq_buf_used(&s)) + seq_buf_printf(&s, "\n"); + + return seq_buf_used(&s); +} +DEVICE_ATTR_RO(flags); + +/* papr_scm specific dimm attributes */ +static struct attribute *papr_nd_attributes[] = { + &dev_attr_flags.attr, + NULL, +}; + +static struct attribute_group papr_nd_attribute_group = { + .name = "papr", + .attrs = papr_nd_attributes, +}; + +static const struct attribute_group *papr_nd_attr_groups[] = { + &papr_nd_attribute_group, + NULL, +}; + static int papr_scm_nvdimm_init(struct papr_scm_priv *p) { struct device *dev = &p->pdev->dev; @@ -312,8 +715,8 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p) dimm_flags = 0; set_bit(NDD_LABELING, &dimm_flags); - p->nvdimm = nvdimm_create(p->bus, p, NULL, dimm_flags, - PAPR_SCM_DIMM_CMD_MASK, 0, NULL); + p->nvdimm = nvdimm_create(p->bus, p, papr_nd_attr_groups, + dimm_flags, PAPR_SCM_DIMM_CMD_MASK, 0, NULL); if (!p->nvdimm) { dev_err(dev, "Error creating DIMM object for %pOF\n", p->dn); goto err; @@ -399,6 +802,9 @@ static int papr_scm_probe(struct platform_device *pdev) if (!p) return -ENOMEM; + /* Initialize the dimm mutex */ + mutex_init(&p->health_mutex); + /* optional DT properties */ of_property_read_u32(dn, "ibm,metadata-size", &metadata_size); diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c index 4a8874bc1057..040b9d01c079 100644 --- a/arch/powerpc/sysdev/fsl_pci.c +++ b/arch/powerpc/sysdev/fsl_pci.c @@ -1066,10 +1066,10 @@ int fsl_pci_mcheck_exception(struct pt_regs *regs) if (is_in_pci_mem_space(addr)) { if (user_mode(regs)) - ret = probe_user_read(&inst, (void __user *)regs->nip, - sizeof(inst)); + ret = copy_from_user_nofault(&inst, + (void __user *)regs->nip, sizeof(inst)); else - ret = probe_kernel_address((void *)regs->nip, inst); + ret = get_kernel_nofault(inst, (void *)regs->nip); if (!ret && mcheck_handle_load(regs, inst)) { regs->nip += 4; diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 128192e14ff2..3230c1d48562 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -23,6 +23,8 @@ config RISCV select ARCH_HAS_SET_DIRECT_MAP select ARCH_HAS_SET_MEMORY select ARCH_HAS_STRICT_KERNEL_RWX if MMU + select ARCH_OPTIONAL_KERNEL_RWX if ARCH_HAS_STRICT_KERNEL_RWX + select ARCH_OPTIONAL_KERNEL_RWX_DEFAULT select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU select ARCH_WANT_FRAME_POINTERS select ARCH_WANT_HUGE_PMD_SHARE if 64BIT diff --git a/arch/riscv/include/asm/barrier.h b/arch/riscv/include/asm/barrier.h index 3f1737f301cc..d0e24aaa2aa0 100644 --- a/arch/riscv/include/asm/barrier.h +++ b/arch/riscv/include/asm/barrier.h @@ -58,8 +58,16 @@ do { \ * The AQ/RL pair provides a RCpc critical section, but there's not really any * way we can take advantage of that here because the ordering is only enforced * on that one lock. Thus, we're just doing a full fence. + * + * Since we allow writeX to be called from preemptive regions we need at least + * an "o" in the predecessor set to ensure device writes are visible before the + * task is marked as available for scheduling on a new hart. While I don't see + * any concrete reason we need a full IO fence, it seems safer to just upgrade + * this in order to avoid any IO crossing a scheduling boundary. In both + * instances the scheduler pairs this with an mb(), so nothing is necessary on + * the new hart. */ -#define smp_mb__after_spinlock() RISCV_FENCE(rw,rw) +#define smp_mb__after_spinlock() RISCV_FENCE(iorw,iorw) #include <asm-generic/barrier.h> diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h index d969bab4a26b..262e5bbb2776 100644 --- a/arch/riscv/include/asm/cmpxchg.h +++ b/arch/riscv/include/asm/cmpxchg.h @@ -179,7 +179,7 @@ " bnez %1, 0b\n" \ "1:\n" \ : "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr) \ - : "rJ" (__old), "rJ" (__new) \ + : "rJ" ((long)__old), "rJ" (__new) \ : "memory"); \ break; \ case 8: \ @@ -224,7 +224,7 @@ RISCV_ACQUIRE_BARRIER \ "1:\n" \ : "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr) \ - : "rJ" (__old), "rJ" (__new) \ + : "rJ" ((long)__old), "rJ" (__new) \ : "memory"); \ break; \ case 8: \ @@ -270,7 +270,7 @@ " bnez %1, 0b\n" \ "1:\n" \ : "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr) \ - : "rJ" (__old), "rJ" (__new) \ + : "rJ" ((long)__old), "rJ" (__new) \ : "memory"); \ break; \ case 8: \ @@ -316,7 +316,7 @@ " fence rw, rw\n" \ "1:\n" \ : "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr) \ - : "rJ" (__old), "rJ" (__new) \ + : "rJ" ((long)__old), "rJ" (__new) \ : "memory"); \ break; \ case 8: \ diff --git a/arch/riscv/include/asm/gdb_xml.h b/arch/riscv/include/asm/gdb_xml.h index 041b45f5b997..09342111f227 100644 --- a/arch/riscv/include/asm/gdb_xml.h +++ b/arch/riscv/include/asm/gdb_xml.h @@ -3,8 +3,7 @@ #ifndef __ASM_GDB_XML_H_ #define __ASM_GDB_XML_H_ -#define kgdb_arch_gdb_stub_feature riscv_gdb_stub_feature -static const char riscv_gdb_stub_feature[64] = +const char riscv_gdb_stub_feature[64] = "PacketSize=800;qXfer:features:read+;"; static const char gdb_xfer_read_target[31] = "qXfer:features:read:target.xml:"; diff --git a/arch/riscv/include/asm/kgdb.h b/arch/riscv/include/asm/kgdb.h index 8177a457caff..46677daf708b 100644 --- a/arch/riscv/include/asm/kgdb.h +++ b/arch/riscv/include/asm/kgdb.h @@ -19,7 +19,6 @@ #ifndef __ASSEMBLY__ -extern int kgdb_has_hit_break(unsigned long addr); extern unsigned long kgdb_compiled_break; static inline void arch_kgdb_breakpoint(void) @@ -106,7 +105,9 @@ static inline void arch_kgdb_breakpoint(void) #define DBG_REG_BADADDR_OFF 34 #define DBG_REG_CAUSE_OFF 35 -#include <asm/gdb_xml.h> +extern const char riscv_gdb_stub_feature[64]; + +#define kgdb_arch_gdb_stub_feature riscv_gdb_stub_feature #endif #endif diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h index 1dd12a0cbb2b..464a2bbc97ea 100644 --- a/arch/riscv/include/asm/thread_info.h +++ b/arch/riscv/include/asm/thread_info.h @@ -12,7 +12,11 @@ #include <linux/const.h> /* thread information allocation */ +#ifdef CONFIG_64BIT +#define THREAD_SIZE_ORDER (2) +#else #define THREAD_SIZE_ORDER (1) +#endif #define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER) #ifndef __ASSEMBLY__ diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c index 08396614d6f4..2ff63d0cbb50 100644 --- a/arch/riscv/kernel/ftrace.c +++ b/arch/riscv/kernel/ftrace.c @@ -38,7 +38,8 @@ static int ftrace_check_current_call(unsigned long hook_pos, * Read the text we want to modify; * return must be -EFAULT on read error */ - if (probe_kernel_read(replaced, (void *)hook_pos, MCOUNT_INSN_SIZE)) + if (copy_from_kernel_nofault(replaced, (void *)hook_pos, + MCOUNT_INSN_SIZE)) return -EFAULT; /* diff --git a/arch/riscv/kernel/kgdb.c b/arch/riscv/kernel/kgdb.c index f16ade84a11f..963ed7edcff2 100644 --- a/arch/riscv/kernel/kgdb.c +++ b/arch/riscv/kernel/kgdb.c @@ -44,25 +44,25 @@ DECLARE_INSN(c_beqz, MATCH_C_BEQZ, MASK_C_BEQZ) DECLARE_INSN(c_bnez, MATCH_C_BNEZ, MASK_C_BNEZ) DECLARE_INSN(sret, MATCH_SRET, MASK_SRET) -int decode_register_index(unsigned long opcode, int offset) +static int decode_register_index(unsigned long opcode, int offset) { return (opcode >> offset) & 0x1F; } -int decode_register_index_short(unsigned long opcode, int offset) +static int decode_register_index_short(unsigned long opcode, int offset) { return ((opcode >> offset) & 0x7) + 8; } /* Calculate the new address for after a step */ -int get_step_address(struct pt_regs *regs, unsigned long *next_addr) +static int get_step_address(struct pt_regs *regs, unsigned long *next_addr) { unsigned long pc = regs->epc; unsigned long *regs_ptr = (unsigned long *)regs; unsigned int rs1_num, rs2_num; int op_code; - if (probe_kernel_address((void *)pc, op_code)) + if (get_kernel_nofault(op_code, (void *)pc)) return -EINVAL; if ((op_code & __INSN_LENGTH_MASK) != __INSN_LENGTH_GE_32) { if (is_c_jalr_insn(op_code) || is_c_jr_insn(op_code)) { @@ -136,7 +136,7 @@ int get_step_address(struct pt_regs *regs, unsigned long *next_addr) return 0; } -int do_single_step(struct pt_regs *regs) +static int do_single_step(struct pt_regs *regs) { /* Determine where the target instruction will send us to */ unsigned long addr = 0; @@ -146,14 +146,14 @@ int do_single_step(struct pt_regs *regs) return error; /* Store the op code in the stepped address */ - error = probe_kernel_address((void *)addr, stepped_opcode); + error = get_kernel_nofault(stepped_opcode, (void *)addr); if (error) return error; stepped_address = addr; /* Replace the op code with the break instruction */ - error = probe_kernel_write((void *)stepped_address, + error = copy_to_kernel_nofault((void *)stepped_address, arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE); /* Flush and return */ @@ -173,7 +173,7 @@ int do_single_step(struct pt_regs *regs) static void undo_single_step(struct pt_regs *regs) { if (stepped_opcode != 0) { - probe_kernel_write((void *)stepped_address, + copy_to_kernel_nofault((void *)stepped_address, (void *)&stepped_opcode, BREAK_INSTR_SIZE); flush_icache_range(stepped_address, stepped_address + BREAK_INSTR_SIZE); @@ -320,7 +320,7 @@ int kgdb_arch_handle_exception(int vector, int signo, int err_code, return err; } -int kgdb_riscv_kgdbbreak(unsigned long addr) +static int kgdb_riscv_kgdbbreak(unsigned long addr) { if (stepped_address == addr) return KGDB_SW_SINGLE_STEP; diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c index d4a64dfed342..3fe7a5296aa5 100644 --- a/arch/riscv/kernel/patch.c +++ b/arch/riscv/kernel/patch.c @@ -63,7 +63,7 @@ static int patch_insn_write(void *addr, const void *insn, size_t len) waddr = patch_map(addr, FIX_TEXT_POKE0); - ret = probe_kernel_write(waddr, insn, len); + ret = copy_to_kernel_nofault(waddr, insn, len); patch_unmap(FIX_TEXT_POKE0); @@ -76,7 +76,7 @@ NOKPROBE_SYMBOL(patch_insn_write); #else static int patch_insn_write(void *addr, const void *insn, size_t len) { - return probe_kernel_write(addr, insn, len); + return copy_to_kernel_nofault(addr, insn, len); } NOKPROBE_SYMBOL(patch_insn_write); #endif /* CONFIG_MMU */ diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c index f3619f59d85c..12f8a7fce78b 100644 --- a/arch/riscv/kernel/sys_riscv.c +++ b/arch/riscv/kernel/sys_riscv.c @@ -8,6 +8,7 @@ #include <linux/syscalls.h> #include <asm/unistd.h> #include <asm/cacheflush.h> +#include <asm-generic/mman-common.h> static long riscv_sys_mmap(unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, @@ -16,6 +17,11 @@ static long riscv_sys_mmap(unsigned long addr, unsigned long len, { if (unlikely(offset & (~PAGE_MASK >> page_shift_offset))) return -EINVAL; + + if ((prot & PROT_WRITE) && (prot & PROT_EXEC)) + if (unlikely(!(prot & PROT_READ))) + return -EINVAL; + return ksys_mmap_pgoff(addr, len, prot, flags, fd, offset >> (PAGE_SHIFT - page_shift_offset)); } diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index ecec1778e3a4..7d95cce5e47c 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -137,7 +137,7 @@ static inline unsigned long get_break_insn_length(unsigned long pc) { bug_insn_t insn; - if (probe_kernel_address((bug_insn_t *)pc, insn)) + if (get_kernel_nofault(insn, (bug_insn_t *)pc)) return 0; return GET_INSN_LENGTH(insn); @@ -165,7 +165,7 @@ int is_valid_bugaddr(unsigned long pc) if (pc < VMALLOC_START) return 0; - if (probe_kernel_address((bug_insn_t *)pc, insn)) + if (get_kernel_nofault(insn, (bug_insn_t *)pc)) return 0; if ((insn & __INSN_LENGTH_MASK) == __INSN_LENGTH_32) return (insn == __BUG_INSN_32); diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile index 38ba55b0eb9d..e4c7c2c8a02f 100644 --- a/arch/riscv/kernel/vdso/Makefile +++ b/arch/riscv/kernel/vdso/Makefile @@ -17,7 +17,7 @@ vdso-syms += flush_icache obj-vdso = $(patsubst %, %.o, $(vdso-syms)) note.o ifneq ($(c-gettimeofday-y),) - CFLAGS_vgettimeofday.o += -include $(c-gettimeofday-y) + CFLAGS_vgettimeofday.o += -fPIC -include $(c-gettimeofday-y) endif # Build rules @@ -27,6 +27,9 @@ obj-vdso := $(addprefix $(obj)/, $(obj-vdso)) obj-y += vdso.o vdso-syms.o CPPFLAGS_vdso.lds += -P -C -U$(ARCH) +# Disable -pg to prevent insert call site +CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os + # Disable gcov profiling for VDSO code GCOV_PROFILE := n diff --git a/arch/riscv/kernel/vdso/vgettimeofday.c b/arch/riscv/kernel/vdso/vgettimeofday.c index d264943e2e47..cc0d80699c31 100644 --- a/arch/riscv/kernel/vdso/vgettimeofday.c +++ b/arch/riscv/kernel/vdso/vgettimeofday.c @@ -9,16 +9,22 @@ #include <linux/time.h> #include <linux/types.h> +extern +int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts); int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts) { return __cvdso_clock_gettime(clock, ts); } +extern +int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz); int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz) { return __cvdso_gettimeofday(tv, tz); } +extern +int __vdso_clock_getres(clockid_t clock_id, struct __kernel_timespec *res); int __vdso_clock_getres(clockid_t clock_id, struct __kernel_timespec *res) { return __cvdso_clock_getres(clock_id, res); diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index f4adb3684f3d..79e9d55bdf1a 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -95,19 +95,40 @@ void __init mem_init(void) #ifdef CONFIG_BLK_DEV_INITRD static void __init setup_initrd(void) { + phys_addr_t start; unsigned long size; - if (initrd_start >= initrd_end) { - pr_info("initrd not found or empty"); + /* Ignore the virtul address computed during device tree parsing */ + initrd_start = initrd_end = 0; + + if (!phys_initrd_size) + return; + /* + * Round the memory region to page boundaries as per free_initrd_mem() + * This allows us to detect whether the pages overlapping the initrd + * are in use, but more importantly, reserves the entire set of pages + * as we don't want these pages allocated for other purposes. + */ + start = round_down(phys_initrd_start, PAGE_SIZE); + size = phys_initrd_size + (phys_initrd_start - start); + size = round_up(size, PAGE_SIZE); + + if (!memblock_is_region_memory(start, size)) { + pr_err("INITRD: 0x%08llx+0x%08lx is not a memory region", + (u64)start, size); goto disable; } - if (__pa_symbol(initrd_end) > PFN_PHYS(max_low_pfn)) { - pr_err("initrd extends beyond end of memory"); + + if (memblock_is_region_reserved(start, size)) { + pr_err("INITRD: 0x%08llx+0x%08lx overlaps in-use memory region\n", + (u64)start, size); goto disable; } - size = initrd_end - initrd_start; - memblock_reserve(__pa_symbol(initrd_start), size); + memblock_reserve(start, size); + /* Now convert initrd to virtual addresses */ + initrd_start = (unsigned long)__va(phys_initrd_start); + initrd_end = initrd_start + phys_initrd_size; initrd_below_start_ok = 1; pr_info("Initial ramdisk at: 0x%p (%lu bytes)\n", @@ -126,33 +147,36 @@ void __init setup_bootmem(void) { struct memblock_region *reg; phys_addr_t mem_size = 0; + phys_addr_t total_mem = 0; + phys_addr_t mem_start, end = 0; phys_addr_t vmlinux_end = __pa_symbol(&_end); phys_addr_t vmlinux_start = __pa_symbol(&_start); /* Find the memory region containing the kernel */ for_each_memblock(memory, reg) { - phys_addr_t end = reg->base + reg->size; - - if (reg->base <= vmlinux_start && vmlinux_end <= end) { - mem_size = min(reg->size, (phys_addr_t)-PAGE_OFFSET); - - /* - * Remove memblock from the end of usable area to the - * end of region - */ - if (reg->base + mem_size < end) - memblock_remove(reg->base + mem_size, - end - reg->base - mem_size); - } + end = reg->base + reg->size; + if (!total_mem) + mem_start = reg->base; + if (reg->base <= vmlinux_start && vmlinux_end <= end) + BUG_ON(reg->size == 0); + total_mem = total_mem + reg->size; } - BUG_ON(mem_size == 0); + + /* + * Remove memblock from the end of usable area to the + * end of region + */ + mem_size = min(total_mem, (phys_addr_t)-PAGE_OFFSET); + if (mem_start + mem_size < end) + memblock_remove(mem_start + mem_size, + end - mem_start - mem_size); /* Reserve from the start of the kernel to the end of the kernel */ memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start); - set_max_mapnr(PFN_DOWN(mem_size)); max_pfn = PFN_DOWN(memblock_end_of_DRAM()); max_low_pfn = max_pfn; + set_max_mapnr(max_low_pfn); #ifdef CONFIG_BLK_DEV_INITRD setup_initrd(); diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c index 4a8b61806633..87b4ab3d3c77 100644 --- a/arch/riscv/mm/kasan_init.c +++ b/arch/riscv/mm/kasan_init.c @@ -44,7 +44,7 @@ asmlinkage void __init kasan_early_init(void) (__pa(((uintptr_t) kasan_early_shadow_pmd))), __pgprot(_PAGE_TABLE))); - flush_tlb_all(); + local_flush_tlb_all(); } static void __init populate(void *start, void *end) @@ -79,7 +79,7 @@ static void __init populate(void *start, void *end) pfn_pgd(PFN_DOWN(__pa(&pmd[offset])), __pgprot(_PAGE_TABLE))); - flush_tlb_all(); + local_flush_tlb_all(); memset(start, 0, end - start); } diff --git a/arch/riscv/mm/pageattr.c b/arch/riscv/mm/pageattr.c index ec2c70f84994..289a9a5ea5b5 100644 --- a/arch/riscv/mm/pageattr.c +++ b/arch/riscv/mm/pageattr.c @@ -151,6 +151,7 @@ int set_memory_nx(unsigned long addr, int numpages) int set_direct_map_invalid_noflush(struct page *page) { + int ret; unsigned long start = (unsigned long)page_address(page); unsigned long end = start + PAGE_SIZE; struct pageattr_masks masks = { @@ -158,11 +159,16 @@ int set_direct_map_invalid_noflush(struct page *page) .clear_mask = __pgprot(_PAGE_PRESENT) }; - return walk_page_range(&init_mm, start, end, &pageattr_ops, &masks); + mmap_read_lock(&init_mm); + ret = walk_page_range(&init_mm, start, end, &pageattr_ops, &masks); + mmap_read_unlock(&init_mm); + + return ret; } int set_direct_map_default_noflush(struct page *page) { + int ret; unsigned long start = (unsigned long)page_address(page); unsigned long end = start + PAGE_SIZE; struct pageattr_masks masks = { @@ -170,7 +176,11 @@ int set_direct_map_default_noflush(struct page *page) .clear_mask = __pgprot(0) }; - return walk_page_range(&init_mm, start, end, &pageattr_ops, &masks); + mmap_read_lock(&init_mm); + ret = walk_page_range(&init_mm, start, end, &pageattr_ops, &masks); + mmap_read_unlock(&init_mm); + + return ret; } void __kernel_map_pages(struct page *page, int numpages, int enable) diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 194824932a60..c7d7ede6300c 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -462,6 +462,7 @@ config NUMA config NODES_SHIFT int + depends on NEED_MULTIPLE_NODES default "1" config SCHED_SMT diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 46038bc58c9e..0cf9a82326a8 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -1,5 +1,6 @@ CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y +CONFIG_WATCH_QUEUE=y CONFIG_AUDIT=y CONFIG_NO_HZ_IDLE=y CONFIG_HIGH_RES_TIMERS=y @@ -14,7 +15,6 @@ CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_NUMA_BALANCING=y CONFIG_MEMCG=y -CONFIG_MEMCG_SWAP=y CONFIG_BLK_CGROUP=y CONFIG_CFS_BANDWIDTH=y CONFIG_RT_GROUP_SCHED=y @@ -31,9 +31,9 @@ CONFIG_NAMESPACES=y CONFIG_USER_NS=y CONFIG_CHECKPOINT_RESTORE=y CONFIG_SCHED_AUTOGROUP=y -CONFIG_BLK_DEV_INITRD=y CONFIG_EXPERT=y # CONFIG_SYSFS_SYSCALL is not set +CONFIG_BPF_LSM=y CONFIG_BPF_SYSCALL=y CONFIG_USERFAULTFD=y # CONFIG_COMPAT_BRK is not set @@ -51,14 +51,11 @@ CONFIG_CHSC_SCH=y CONFIG_VFIO_CCW=m CONFIG_VFIO_AP=m CONFIG_CRASH_DUMP=y -CONFIG_HIBERNATION=y -CONFIG_PM_DEBUG=y CONFIG_PROTECTED_VIRTUALIZATION_GUEST=y CONFIG_CMM=m CONFIG_APPLDATA_BASE=y CONFIG_KVM=m -CONFIG_VHOST_NET=m -CONFIG_VHOST_VSOCK=m +CONFIG_S390_UNWIND_SELFTEST=y CONFIG_OPROFILE=m CONFIG_KPROBES=y CONFIG_JUMP_LABEL=y @@ -77,6 +74,8 @@ CONFIG_BLK_DEV_THROTTLING=y CONFIG_BLK_WBT=y CONFIG_BLK_CGROUP_IOLATENCY=y CONFIG_BLK_CGROUP_IOCOST=y +CONFIG_BLK_INLINE_ENCRYPTION=y +CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK=y CONFIG_PARTITION_ADVANCED=y CONFIG_IBM_PARTITION=y CONFIG_BSD_DISKLABEL=y @@ -96,7 +95,6 @@ CONFIG_CMA_DEBUG=y CONFIG_CMA_DEBUGFS=y CONFIG_MEM_SOFT_DIRTY=y CONFIG_ZSWAP=y -CONFIG_ZBUD=m CONFIG_ZSMALLOC=m CONFIG_ZSMALLOC_STAT=y CONFIG_DEFERRED_STRUCT_PAGE_INIT=y @@ -130,6 +128,7 @@ CONFIG_SYN_COOKIES=y CONFIG_NET_IPVTI=m CONFIG_INET_AH=m CONFIG_INET_ESP=m +CONFIG_INET_ESPINTCP=y CONFIG_INET_IPCOMP=m CONFIG_INET_DIAG=m CONFIG_INET_UDP_DIAG=m @@ -144,6 +143,7 @@ CONFIG_TCP_CONG_ILLINOIS=m CONFIG_IPV6_ROUTER_PREF=y CONFIG_INET6_AH=m CONFIG_INET6_ESP=m +CONFIG_INET6_ESPINTCP=y CONFIG_INET6_IPCOMP=m CONFIG_IPV6_MIP6=m CONFIG_IPV6_VTI=m @@ -151,7 +151,10 @@ CONFIG_IPV6_SIT=m CONFIG_IPV6_GRE=m CONFIG_IPV6_MULTIPLE_TABLES=y CONFIG_IPV6_SUBTREES=y +CONFIG_IPV6_RPL_LWTUNNEL=y +CONFIG_MPTCP=y CONFIG_NETFILTER=y +CONFIG_BRIDGE_NETFILTER=m CONFIG_NF_CONNTRACK=m CONFIG_NF_CONNTRACK_SECMARK=y CONFIG_NF_CONNTRACK_EVENTS=y @@ -317,6 +320,7 @@ CONFIG_L2TP_V3=y CONFIG_L2TP_IP=m CONFIG_L2TP_ETH=m CONFIG_BRIDGE=m +CONFIG_BRIDGE_MRP=y CONFIG_VLAN_8021Q=m CONFIG_VLAN_8021Q_GVRP=y CONFIG_NET_SCHED=y @@ -341,6 +345,7 @@ CONFIG_NET_SCH_CODEL=m CONFIG_NET_SCH_FQ_CODEL=m CONFIG_NET_SCH_INGRESS=m CONFIG_NET_SCH_PLUG=m +CONFIG_NET_SCH_ETS=m CONFIG_NET_CLS_BASIC=m CONFIG_NET_CLS_TCINDEX=m CONFIG_NET_CLS_ROUTE4=m @@ -364,6 +369,7 @@ CONFIG_NET_ACT_PEDIT=m CONFIG_NET_ACT_SIMP=m CONFIG_NET_ACT_SKBEDIT=m CONFIG_NET_ACT_CSUM=m +CONFIG_NET_ACT_GATE=m CONFIG_DNS_RESOLVER=y CONFIG_OPENVSWITCH=m CONFIG_VSOCKETS=m @@ -374,6 +380,7 @@ CONFIG_BPF_JIT=y CONFIG_NET_PKTGEN=m # CONFIG_NET_DROP_MONITOR is not set CONFIG_PCI=y +# CONFIG_PCIEASPM is not set CONFIG_PCI_DEBUG=y CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_S390=y @@ -435,6 +442,7 @@ CONFIG_DM_ZERO=m CONFIG_DM_MULTIPATH=m CONFIG_DM_MULTIPATH_QL=m CONFIG_DM_MULTIPATH_ST=m +CONFIG_DM_MULTIPATH_HST=m CONFIG_DM_DELAY=m CONFIG_DM_UEVENT=y CONFIG_DM_FLAKEY=m @@ -448,6 +456,8 @@ CONFIG_EQUALIZER=m CONFIG_IFB=m CONFIG_MACVLAN=m CONFIG_MACVTAP=m +CONFIG_VXLAN=m +CONFIG_BAREUDP=m CONFIG_TUN=m CONFIG_VETH=m CONFIG_VIRTIO_NET=m @@ -481,7 +491,6 @@ CONFIG_NLMON=m CONFIG_MLX4_EN=m CONFIG_MLX5_CORE=m CONFIG_MLX5_CORE_EN=y -# CONFIG_MLXFW is not set # CONFIG_NET_VENDOR_MICREL is not set # CONFIG_NET_VENDOR_MICROCHIP is not set # CONFIG_NET_VENDOR_MICROSEMI is not set @@ -514,6 +523,7 @@ CONFIG_MLX5_CORE_EN=y # CONFIG_NET_VENDOR_TI is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set +# CONFIG_NET_VENDOR_XILINX is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -561,6 +571,8 @@ CONFIG_VFIO_MDEV_DEVICE=m CONFIG_VIRTIO_PCI=m CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_INPUT=y +CONFIG_VHOST_NET=m +CONFIG_VHOST_VSOCK=m CONFIG_S390_CCW_IOMMU=y CONFIG_S390_AP_IOMMU=y CONFIG_EXT4_FS=y @@ -608,6 +620,7 @@ CONFIG_ZISOFS=y CONFIG_UDF_FS=m CONFIG_MSDOS_FS=m CONFIG_VFAT_FS=m +CONFIG_EXFAT_FS=m CONFIG_NTFS_FS=m CONFIG_NTFS_RW=y CONFIG_PROC_KCORE=y @@ -650,8 +663,8 @@ CONFIG_NLS_UTF8=m CONFIG_DLM=m CONFIG_UNICODE=y CONFIG_PERSISTENT_KEYRINGS=y -CONFIG_BIG_KEYS=y CONFIG_ENCRYPTED_KEYS=m +CONFIG_KEY_NOTIFICATIONS=y CONFIG_SECURITY=y CONFIG_SECURITY_NETWORK=y CONFIG_FORTIFY_SOURCE=y @@ -675,8 +688,11 @@ CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m +CONFIG_CRYPTO_CURVE25519=m +CONFIG_CRYPTO_GCM=y CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_SEQIV=y CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m @@ -685,6 +701,7 @@ CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_CRC32=m +CONFIG_CRYPTO_BLAKE2S=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD128=m CONFIG_CRYPTO_RMD160=m @@ -701,6 +718,7 @@ CONFIG_CRYPTO_BLOWFISH=m CONFIG_CRYPTO_CAMELLIA=m CONFIG_CRYPTO_CAST5=m CONFIG_CRYPTO_CAST6=m +CONFIG_CRYPTO_DES=m CONFIG_CRYPTO_FCRYPT=m CONFIG_CRYPTO_KHAZAD=m CONFIG_CRYPTO_SALSA20=m @@ -719,6 +737,9 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=m CONFIG_CRYPTO_USER_API_RNG=m CONFIG_CRYPTO_USER_API_AEAD=m CONFIG_CRYPTO_STATS=y +CONFIG_CRYPTO_LIB_BLAKE2S=m +CONFIG_CRYPTO_LIB_CURVE25519=m +CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m CONFIG_ZCRYPT=m CONFIG_PKEY=m CONFIG_CRYPTO_PAES_S390=m @@ -774,6 +795,7 @@ CONFIG_DEBUG_SHIRQ=y CONFIG_PANIC_ON_OOPS=y CONFIG_DETECT_HUNG_TASK=y CONFIG_WQ_WATCHDOG=y +CONFIG_TEST_LOCKUP=m CONFIG_DEBUG_TIMEKEEPING=y CONFIG_PROVE_LOCKING=y CONFIG_LOCK_STAT=y @@ -786,7 +808,9 @@ CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_DEBUG_CREDENTIALS=y CONFIG_RCU_TORTURE_TEST=m CONFIG_RCU_CPU_STALL_TIMEOUT=300 +# CONFIG_RCU_TRACE is not set CONFIG_LATENCYTOP=y +CONFIG_BOOTTIME_TRACING=y CONFIG_FUNCTION_PROFILER=y CONFIG_STACK_TRACER=y CONFIG_IRQSOFF_TRACER=y @@ -808,10 +832,12 @@ CONFIG_FAULT_INJECTION_DEBUG_FS=y CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y CONFIG_LKDTM=m CONFIG_TEST_LIST_SORT=y +CONFIG_TEST_MIN_HEAP=y CONFIG_TEST_SORT=y CONFIG_KPROBES_SANITY_TEST=y CONFIG_RBTREE_TEST=y CONFIG_INTERVAL_TREE_TEST=m CONFIG_PERCPU_TEST=m CONFIG_ATOMIC64_SELFTEST=y +CONFIG_TEST_BITOPS=m CONFIG_TEST_BPF=m diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 7cd0648c1f4e..5df9759e8ff6 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -1,5 +1,6 @@ CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y +CONFIG_WATCH_QUEUE=y CONFIG_AUDIT=y CONFIG_NO_HZ_IDLE=y CONFIG_HIGH_RES_TIMERS=y @@ -13,7 +14,6 @@ CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_NUMA_BALANCING=y CONFIG_MEMCG=y -CONFIG_MEMCG_SWAP=y CONFIG_BLK_CGROUP=y CONFIG_CFS_BANDWIDTH=y CONFIG_RT_GROUP_SCHED=y @@ -30,9 +30,9 @@ CONFIG_NAMESPACES=y CONFIG_USER_NS=y CONFIG_CHECKPOINT_RESTORE=y CONFIG_SCHED_AUTOGROUP=y -CONFIG_BLK_DEV_INITRD=y CONFIG_EXPERT=y # CONFIG_SYSFS_SYSCALL is not set +CONFIG_BPF_LSM=y CONFIG_BPF_SYSCALL=y CONFIG_USERFAULTFD=y # CONFIG_COMPAT_BRK is not set @@ -41,7 +41,6 @@ CONFIG_LIVEPATCH=y CONFIG_TUNE_ZEC12=y CONFIG_NR_CPUS=512 CONFIG_NUMA=y -# CONFIG_NUMA_EMU is not set CONFIG_HZ_100=y CONFIG_KEXEC_FILE=y CONFIG_KEXEC_SIG=y @@ -51,14 +50,11 @@ CONFIG_CHSC_SCH=y CONFIG_VFIO_CCW=m CONFIG_VFIO_AP=m CONFIG_CRASH_DUMP=y -CONFIG_HIBERNATION=y -CONFIG_PM_DEBUG=y CONFIG_PROTECTED_VIRTUALIZATION_GUEST=y CONFIG_CMM=m CONFIG_APPLDATA_BASE=y CONFIG_KVM=m -CONFIG_VHOST_NET=m -CONFIG_VHOST_VSOCK=m +CONFIG_S390_UNWIND_SELFTEST=m CONFIG_OPROFILE=m CONFIG_KPROBES=y CONFIG_JUMP_LABEL=y @@ -74,6 +70,8 @@ CONFIG_BLK_DEV_THROTTLING=y CONFIG_BLK_WBT=y CONFIG_BLK_CGROUP_IOLATENCY=y CONFIG_BLK_CGROUP_IOCOST=y +CONFIG_BLK_INLINE_ENCRYPTION=y +CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK=y CONFIG_PARTITION_ADVANCED=y CONFIG_IBM_PARTITION=y CONFIG_BSD_DISKLABEL=y @@ -91,7 +89,6 @@ CONFIG_CLEANCACHE=y CONFIG_FRONTSWAP=y CONFIG_MEM_SOFT_DIRTY=y CONFIG_ZSWAP=y -CONFIG_ZBUD=m CONFIG_ZSMALLOC=m CONFIG_ZSMALLOC_STAT=y CONFIG_DEFERRED_STRUCT_PAGE_INIT=y @@ -125,6 +122,7 @@ CONFIG_SYN_COOKIES=y CONFIG_NET_IPVTI=m CONFIG_INET_AH=m CONFIG_INET_ESP=m +CONFIG_INET_ESPINTCP=y CONFIG_INET_IPCOMP=m CONFIG_INET_DIAG=m CONFIG_INET_UDP_DIAG=m @@ -139,6 +137,7 @@ CONFIG_TCP_CONG_ILLINOIS=m CONFIG_IPV6_ROUTER_PREF=y CONFIG_INET6_AH=m CONFIG_INET6_ESP=m +CONFIG_INET6_ESPINTCP=y CONFIG_INET6_IPCOMP=m CONFIG_IPV6_MIP6=m CONFIG_IPV6_VTI=m @@ -146,7 +145,10 @@ CONFIG_IPV6_SIT=m CONFIG_IPV6_GRE=m CONFIG_IPV6_MULTIPLE_TABLES=y CONFIG_IPV6_SUBTREES=y +CONFIG_IPV6_RPL_LWTUNNEL=y +CONFIG_MPTCP=y CONFIG_NETFILTER=y +CONFIG_BRIDGE_NETFILTER=m CONFIG_NF_CONNTRACK=m CONFIG_NF_CONNTRACK_SECMARK=y CONFIG_NF_CONNTRACK_EVENTS=y @@ -311,6 +313,7 @@ CONFIG_L2TP_V3=y CONFIG_L2TP_IP=m CONFIG_L2TP_ETH=m CONFIG_BRIDGE=m +CONFIG_BRIDGE_MRP=y CONFIG_VLAN_8021Q=m CONFIG_VLAN_8021Q_GVRP=y CONFIG_NET_SCHED=y @@ -335,6 +338,7 @@ CONFIG_NET_SCH_CODEL=m CONFIG_NET_SCH_FQ_CODEL=m CONFIG_NET_SCH_INGRESS=m CONFIG_NET_SCH_PLUG=m +CONFIG_NET_SCH_ETS=m CONFIG_NET_CLS_BASIC=m CONFIG_NET_CLS_TCINDEX=m CONFIG_NET_CLS_ROUTE4=m @@ -358,6 +362,7 @@ CONFIG_NET_ACT_PEDIT=m CONFIG_NET_ACT_SIMP=m CONFIG_NET_ACT_SKBEDIT=m CONFIG_NET_ACT_CSUM=m +CONFIG_NET_ACT_GATE=m CONFIG_DNS_RESOLVER=y CONFIG_OPENVSWITCH=m CONFIG_VSOCKETS=m @@ -368,6 +373,7 @@ CONFIG_BPF_JIT=y CONFIG_NET_PKTGEN=m # CONFIG_NET_DROP_MONITOR is not set CONFIG_PCI=y +# CONFIG_PCIEASPM is not set CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_S390=y CONFIG_UEVENT_HELPER=y @@ -430,6 +436,7 @@ CONFIG_DM_ZERO=m CONFIG_DM_MULTIPATH=m CONFIG_DM_MULTIPATH_QL=m CONFIG_DM_MULTIPATH_ST=m +CONFIG_DM_MULTIPATH_HST=m CONFIG_DM_DELAY=m CONFIG_DM_UEVENT=y CONFIG_DM_FLAKEY=m @@ -444,6 +451,8 @@ CONFIG_EQUALIZER=m CONFIG_IFB=m CONFIG_MACVLAN=m CONFIG_MACVTAP=m +CONFIG_VXLAN=m +CONFIG_BAREUDP=m CONFIG_TUN=m CONFIG_VETH=m CONFIG_VIRTIO_NET=m @@ -477,7 +486,6 @@ CONFIG_NLMON=m CONFIG_MLX4_EN=m CONFIG_MLX5_CORE=m CONFIG_MLX5_CORE_EN=y -# CONFIG_MLXFW is not set # CONFIG_NET_VENDOR_MICREL is not set # CONFIG_NET_VENDOR_MICROCHIP is not set # CONFIG_NET_VENDOR_MICROSEMI is not set @@ -510,6 +518,7 @@ CONFIG_MLX5_CORE_EN=y # CONFIG_NET_VENDOR_TI is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set +# CONFIG_NET_VENDOR_XILINX is not set CONFIG_PPP=m CONFIG_PPP_BSDCOMP=m CONFIG_PPP_DEFLATE=m @@ -557,6 +566,8 @@ CONFIG_VFIO_MDEV_DEVICE=m CONFIG_VIRTIO_PCI=m CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_INPUT=y +CONFIG_VHOST_NET=m +CONFIG_VHOST_VSOCK=m CONFIG_S390_CCW_IOMMU=y CONFIG_S390_AP_IOMMU=y CONFIG_EXT4_FS=y @@ -600,6 +611,7 @@ CONFIG_ZISOFS=y CONFIG_UDF_FS=m CONFIG_MSDOS_FS=m CONFIG_VFAT_FS=m +CONFIG_EXFAT_FS=m CONFIG_NTFS_FS=m CONFIG_NTFS_RW=y CONFIG_PROC_KCORE=y @@ -642,8 +654,8 @@ CONFIG_NLS_UTF8=m CONFIG_DLM=m CONFIG_UNICODE=y CONFIG_PERSISTENT_KEYRINGS=y -CONFIG_BIG_KEYS=y CONFIG_ENCRYPTED_KEYS=m +CONFIG_KEY_NOTIFICATIONS=y CONFIG_SECURITY=y CONFIG_SECURITY_NETWORK=y CONFIG_SECURITY_SELINUX=y @@ -667,8 +679,11 @@ CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m +CONFIG_CRYPTO_CURVE25519=m +CONFIG_CRYPTO_GCM=y CONFIG_CRYPTO_CHACHA20POLY1305=m CONFIG_CRYPTO_AEGIS128=m +CONFIG_CRYPTO_SEQIV=y CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_OFB=m @@ -678,6 +693,7 @@ CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_CRC32=m +CONFIG_CRYPTO_BLAKE2S=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_RMD128=m CONFIG_CRYPTO_RMD160=m @@ -694,6 +710,7 @@ CONFIG_CRYPTO_BLOWFISH=m CONFIG_CRYPTO_CAMELLIA=m CONFIG_CRYPTO_CAST5=m CONFIG_CRYPTO_CAST6=m +CONFIG_CRYPTO_DES=m CONFIG_CRYPTO_FCRYPT=m CONFIG_CRYPTO_KHAZAD=m CONFIG_CRYPTO_SALSA20=m @@ -712,6 +729,9 @@ CONFIG_CRYPTO_USER_API_SKCIPHER=m CONFIG_CRYPTO_USER_API_RNG=m CONFIG_CRYPTO_USER_API_AEAD=m CONFIG_CRYPTO_STATS=y +CONFIG_CRYPTO_LIB_BLAKE2S=m +CONFIG_CRYPTO_LIB_CURVE25519=m +CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m CONFIG_ZCRYPT=m CONFIG_PKEY=m CONFIG_CRYPTO_PAES_S390=m @@ -725,6 +745,7 @@ CONFIG_CRYPTO_AES_S390=m CONFIG_CRYPTO_GHASH_S390=m CONFIG_CRYPTO_CRC32_S390=y CONFIG_CORDIC=m +CONFIG_PRIME_NUMBERS=m CONFIG_CRC4=m CONFIG_CRC7=m CONFIG_CRC8=m @@ -739,10 +760,12 @@ CONFIG_DEBUG_SECTION_MISMATCH=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_MEMORY_INIT=y CONFIG_PANIC_ON_OOPS=y +CONFIG_TEST_LOCKUP=m CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_RCU_TORTURE_TEST=m CONFIG_RCU_CPU_STALL_TIMEOUT=60 CONFIG_LATENCYTOP=y +CONFIG_BOOTTIME_TRACING=y CONFIG_FUNCTION_PROFILER=y CONFIG_STACK_TRACER=y CONFIG_SCHED_TRACER=y diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index 20c51e5d9353..4091c50449cd 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -30,6 +30,7 @@ CONFIG_IBM_PARTITION=y # CONFIG_BOUNCE is not set CONFIG_NET=y # CONFIG_IUCV is not set +# CONFIG_ETHTOOL_NETLINK is not set CONFIG_DEVTMPFS=y CONFIG_BLK_DEV_RAM=y # CONFIG_BLK_DEV_XPRAM is not set @@ -55,6 +56,8 @@ CONFIG_RAW_DRIVER=y # CONFIG_MONWRITER is not set # CONFIG_S390_VMUR is not set # CONFIG_HID is not set +# CONFIG_VIRTIO_MENU is not set +# CONFIG_VHOST_MENU is not set # CONFIG_IOMMU_SUPPORT is not set # CONFIG_DNOTIFY is not set # CONFIG_INOTIFY_USER is not set @@ -62,7 +65,9 @@ CONFIG_CONFIGFS_FS=y # CONFIG_MISC_FILESYSTEMS is not set # CONFIG_NETWORK_FILESYSTEMS is not set CONFIG_LSM="yama,loadpin,safesetid,integrity" +# CONFIG_ZLIB_DFLTCC is not set CONFIG_PRINTK_TIME=y +# CONFIG_SYMBOLIC_ERRNAME is not set CONFIG_DEBUG_INFO=y CONFIG_DEBUG_FS=y CONFIG_DEBUG_KERNEL=y diff --git a/arch/s390/crypto/prng.c b/arch/s390/crypto/prng.c index d977643fa627..e1ae23911ccd 100644 --- a/arch/s390/crypto/prng.c +++ b/arch/s390/crypto/prng.c @@ -693,7 +693,7 @@ static ssize_t prng_chunksize_show(struct device *dev, struct device_attribute *attr, char *buf) { - return snprintf(buf, PAGE_SIZE, "%u\n", prng_chunk_size); + return scnprintf(buf, PAGE_SIZE, "%u\n", prng_chunk_size); } static DEVICE_ATTR(chunksize, 0444, prng_chunksize_show, NULL); @@ -712,7 +712,7 @@ static ssize_t prng_counter_show(struct device *dev, counter = prng_data->prngws.byte_counter; mutex_unlock(&prng_data->mutex); - return snprintf(buf, PAGE_SIZE, "%llu\n", counter); + return scnprintf(buf, PAGE_SIZE, "%llu\n", counter); } static DEVICE_ATTR(byte_counter, 0444, prng_counter_show, NULL); @@ -721,7 +721,7 @@ static ssize_t prng_errorflag_show(struct device *dev, struct device_attribute *attr, char *buf) { - return snprintf(buf, PAGE_SIZE, "%d\n", prng_errorflag); + return scnprintf(buf, PAGE_SIZE, "%d\n", prng_errorflag); } static DEVICE_ATTR(errorflag, 0444, prng_errorflag_show, NULL); @@ -731,9 +731,9 @@ static ssize_t prng_mode_show(struct device *dev, char *buf) { if (prng_mode == PRNG_MODE_TDES) - return snprintf(buf, PAGE_SIZE, "TDES\n"); + return scnprintf(buf, PAGE_SIZE, "TDES\n"); else - return snprintf(buf, PAGE_SIZE, "SHA512\n"); + return scnprintf(buf, PAGE_SIZE, "SHA512\n"); } static DEVICE_ATTR(mode, 0444, prng_mode_show, NULL); @@ -756,7 +756,7 @@ static ssize_t prng_reseed_limit_show(struct device *dev, struct device_attribute *attr, char *buf) { - return snprintf(buf, PAGE_SIZE, "%u\n", prng_reseed_limit); + return scnprintf(buf, PAGE_SIZE, "%u\n", prng_reseed_limit); } static ssize_t prng_reseed_limit_store(struct device *dev, struct device_attribute *attr, @@ -787,7 +787,7 @@ static ssize_t prng_strength_show(struct device *dev, struct device_attribute *attr, char *buf) { - return snprintf(buf, PAGE_SIZE, "256\n"); + return scnprintf(buf, PAGE_SIZE, "256\n"); } static DEVICE_ATTR(strength, 0444, prng_strength_show, NULL); diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index cee3cb6455a2..6ea0820e7c7f 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -31,12 +31,12 @@ #define KVM_USER_MEM_SLOTS 32 /* - * These seem to be used for allocating ->chip in the routing table, - * which we don't use. 4096 is an out-of-thin-air value. If we need - * to look at ->chip later on, we'll need to revisit this. + * These seem to be used for allocating ->chip in the routing table, which we + * don't use. 1 is as small as we can get to reduce the needed memory. If we + * need to look at ->chip later on, we'll need to revisit this. */ #define KVM_NR_IRQCHIPS 1 -#define KVM_IRQCHIP_NUM_PINS 4096 +#define KVM_IRQCHIP_NUM_PINS 1 #define KVM_HALT_POLL_NS_DEFAULT 50000 /* s390-specific vcpu->requests bit members */ diff --git a/arch/s390/include/asm/syscall.h b/arch/s390/include/asm/syscall.h index f073292e9fdb..d9d5de0f67ff 100644 --- a/arch/s390/include/asm/syscall.h +++ b/arch/s390/include/asm/syscall.h @@ -33,7 +33,17 @@ static inline void syscall_rollback(struct task_struct *task, static inline long syscall_get_error(struct task_struct *task, struct pt_regs *regs) { - return IS_ERR_VALUE(regs->gprs[2]) ? regs->gprs[2] : 0; + unsigned long error = regs->gprs[2]; +#ifdef CONFIG_COMPAT + if (test_tsk_thread_flag(task, TIF_31BIT)) { + /* + * Sign-extend the value so (int)-EFOO becomes (long)-EFOO + * and will match correctly in comparisons. + */ + error = (long)(int)error; + } +#endif + return IS_ERR_VALUE(error) ? error : 0; } static inline long syscall_get_return_value(struct task_struct *task, diff --git a/arch/s390/include/asm/vdso.h b/arch/s390/include/asm/vdso.h index 3bcfdeb01395..0cd085cdeb4f 100644 --- a/arch/s390/include/asm/vdso.h +++ b/arch/s390/include/asm/vdso.h @@ -36,6 +36,7 @@ struct vdso_data { __u32 tk_shift; /* Shift used for xtime_nsec 0x60 */ __u32 ts_dir; /* TOD steering direction 0x64 */ __u64 ts_end; /* TOD steering end 0x68 */ + __u32 hrtimer_res; /* hrtimer resolution 0x70 */ }; struct vdso_per_cpu_data { diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index 165031bd3370..5d8cc1864566 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -76,6 +76,7 @@ int main(void) OFFSET(__VDSO_TK_SHIFT, vdso_data, tk_shift); OFFSET(__VDSO_TS_DIR, vdso_data, ts_dir); OFFSET(__VDSO_TS_END, vdso_data, ts_end); + OFFSET(__VDSO_CLOCK_REALTIME_RES, vdso_data, hrtimer_res); OFFSET(__VDSO_ECTG_BASE, vdso_per_cpu_data, ectg_timer_base); OFFSET(__VDSO_ECTG_USER, vdso_per_cpu_data, ectg_user_time); OFFSET(__VDSO_GETCPU_VAL, vdso_per_cpu_data, getcpu_val); @@ -86,7 +87,6 @@ int main(void) DEFINE(__CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE); DEFINE(__CLOCK_MONOTONIC_COARSE, CLOCK_MONOTONIC_COARSE); DEFINE(__CLOCK_THREAD_CPUTIME_ID, CLOCK_THREAD_CPUTIME_ID); - DEFINE(__CLOCK_REALTIME_RES, MONOTONIC_RES_NSEC); DEFINE(__CLOCK_COARSE_RES, LOW_RES_NSEC); BLANK(); /* idle data offsets */ diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c index 636446003a06..263075a1af36 100644 --- a/arch/s390/kernel/debug.c +++ b/arch/s390/kernel/debug.c @@ -198,9 +198,10 @@ static debug_entry_t ***debug_areas_alloc(int pages_per_area, int nr_areas) if (!areas) goto fail_malloc_areas; for (i = 0; i < nr_areas; i++) { + /* GFP_NOWARN to avoid user triggerable WARN, we handle fails */ areas[i] = kmalloc_array(pages_per_area, sizeof(debug_entry_t *), - GFP_KERNEL); + GFP_KERNEL | __GFP_NOWARN); if (!areas[i]) goto fail_malloc_areas2; for (j = 0; j < pages_per_area; j++) { diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index cd241ee66eff..078277231858 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -170,6 +170,8 @@ static noinline __init void setup_lowcore_early(void) psw_t psw; psw.mask = PSW_MASK_BASE | PSW_DEFAULT_KEY | PSW_MASK_EA | PSW_MASK_BA; + if (IS_ENABLED(CONFIG_KASAN)) + psw.mask |= PSW_MASK_DAT; psw.addr = (unsigned long) s390_base_ext_handler; S390_lowcore.external_new_psw = psw; psw.addr = (unsigned long) s390_base_pgm_handler; diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 50ff6dd0f995..969b35b177dd 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -378,9 +378,9 @@ ENTRY(system_call) stmg %r8,%r15,__LC_SAVE_AREA_SYNC BPOFF lg %r12,__LC_CURRENT - lghi %r13,__TASK_thread lghi %r14,_PIF_SYSCALL .Lsysc_per: + lghi %r13,__TASK_thread lg %r15,__LC_KERNEL_STACK la %r11,STACK_FRAME_OVERHEAD(%r15) # pointer to pt_regs UPDATE_VTIME %r8,%r9,__LC_SYNC_ENTER_TIMER @@ -401,9 +401,9 @@ ENTRY(system_call) jnz .Lsysc_nr_ok # svc 0: system call number in %r1 llgfr %r1,%r1 # clear high word in r1 + sth %r1,__PT_INT_CODE+2(%r11) cghi %r1,NR_syscalls jnl .Lsysc_nr_ok - sth %r1,__PT_INT_CODE+2(%r11) slag %r8,%r1,3 .Lsysc_nr_ok: xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index 44e01dd1e624..b388e87a08bf 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -83,7 +83,7 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, { struct ftrace_insn orig, new, old; - if (probe_kernel_read(&old, (void *) rec->ip, sizeof(old))) + if (copy_from_kernel_nofault(&old, (void *) rec->ip, sizeof(old))) return -EFAULT; if (addr == MCOUNT_ADDR) { /* Initial code replacement */ @@ -105,7 +105,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) { struct ftrace_insn orig, new, old; - if (probe_kernel_read(&old, (void *) rec->ip, sizeof(old))) + if (copy_from_kernel_nofault(&old, (void *) rec->ip, sizeof(old))) return -EFAULT; /* Replace nop with an ftrace call. */ ftrace_generate_nop_insn(&orig); diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index ccea9a245867..90a2a17239b0 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -181,7 +181,7 @@ static ssize_t sys_##_prefix##_##_name##_show(struct kobject *kobj, \ struct kobj_attribute *attr, \ char *page) \ { \ - return snprintf(page, PAGE_SIZE, _format, ##args); \ + return scnprintf(page, PAGE_SIZE, _format, ##args); \ } #define IPL_ATTR_CCW_STORE_FN(_prefix, _name, _ipl_blk) \ diff --git a/arch/s390/kernel/perf_cpum_cf_events.c b/arch/s390/kernel/perf_cpum_cf_events.c index 1e3df52b2b65..37265f551a11 100644 --- a/arch/s390/kernel/perf_cpum_cf_events.c +++ b/arch/s390/kernel/perf_cpum_cf_events.c @@ -292,7 +292,7 @@ CPUMF_EVENT_ATTR(cf_z15, TX_C_TABORT_SPECIAL, 0x00f5); CPUMF_EVENT_ATTR(cf_z15, DFLT_ACCESS, 0x00f7); CPUMF_EVENT_ATTR(cf_z15, DFLT_CYCLES, 0x00fc); CPUMF_EVENT_ATTR(cf_z15, DFLT_CC, 0x00108); -CPUMF_EVENT_ATTR(cf_z15, DFLT_CCERROR, 0x00109); +CPUMF_EVENT_ATTR(cf_z15, DFLT_CCFINISH, 0x00109); CPUMF_EVENT_ATTR(cf_z15, MT_DIAG_CYCLES_ONE_THR_ACTIVE, 0x01c0); CPUMF_EVENT_ATTR(cf_z15, MT_DIAG_CYCLES_TWO_THR_ACTIVE, 0x01c1); @@ -629,7 +629,7 @@ static struct attribute *cpumcf_z15_pmu_event_attr[] __initdata = { CPUMF_EVENT_PTR(cf_z15, DFLT_ACCESS), CPUMF_EVENT_PTR(cf_z15, DFLT_CYCLES), CPUMF_EVENT_PTR(cf_z15, DFLT_CC), - CPUMF_EVENT_PTR(cf_z15, DFLT_CCERROR), + CPUMF_EVENT_PTR(cf_z15, DFLT_CCFINISH), CPUMF_EVENT_PTR(cf_z15, MT_DIAG_CYCLES_ONE_THR_ACTIVE), CPUMF_EVENT_PTR(cf_z15, MT_DIAG_CYCLES_TWO_THR_ACTIVE), NULL, diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index 85a711d783eb..4f9e4626df55 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -881,12 +881,21 @@ out: return err; } +static bool is_callchain_event(struct perf_event *event) +{ + u64 sample_type = event->attr.sample_type; + + return sample_type & (PERF_SAMPLE_CALLCHAIN | PERF_SAMPLE_REGS_USER | + PERF_SAMPLE_STACK_USER); +} + static int cpumsf_pmu_event_init(struct perf_event *event) { int err; /* No support for taken branch sampling */ - if (has_branch_stack(event)) + /* No support for callchain, stacks and registers */ + if (has_branch_stack(event) || is_callchain_event(event)) return -EOPNOTSUPP; switch (event->attr.type) { diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index ce60a459a143..3cc15c066298 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -323,6 +323,25 @@ static inline void __poke_user_per(struct task_struct *child, child->thread.per_user.end = data; } +static void fixup_int_code(struct task_struct *child, addr_t data) +{ + struct pt_regs *regs = task_pt_regs(child); + int ilc = regs->int_code >> 16; + u16 insn; + + if (ilc > 6) + return; + + if (ptrace_access_vm(child, regs->psw.addr - (regs->int_code >> 16), + &insn, sizeof(insn), FOLL_FORCE) != sizeof(insn)) + return; + + /* double check that tracee stopped on svc instruction */ + if ((insn >> 8) != 0xa) + return; + + regs->int_code = 0x20000 | (data & 0xffff); +} /* * Write a word to the user area of a process at location addr. This * operation does have an additional problem compared to peek_user. @@ -334,7 +353,9 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data) struct user *dummy = NULL; addr_t offset; + if (addr < (addr_t) &dummy->regs.acrs) { + struct pt_regs *regs = task_pt_regs(child); /* * psw and gprs are stored on the stack */ @@ -352,7 +373,11 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data) /* Invalid addressing mode bits */ return -EINVAL; } - *(addr_t *)((addr_t) &task_pt_regs(child)->psw + addr) = data; + + if (test_pt_regs_flag(regs, PIF_SYSCALL) && + addr == offsetof(struct user, regs.gprs[2])) + fixup_int_code(child, data); + *(addr_t *)((addr_t) ®s->psw + addr) = data; } else if (addr < (addr_t) (&dummy->regs.orig_gpr2)) { /* @@ -718,6 +743,10 @@ static int __poke_user_compat(struct task_struct *child, regs->psw.mask = (regs->psw.mask & ~PSW_MASK_BA) | (__u64)(tmp & PSW32_ADDR_AMODE); } else { + + if (test_pt_regs_flag(regs, PIF_SYSCALL) && + addr == offsetof(struct compat_user, regs.gprs[2])) + fixup_int_code(child, data); /* gpr 0-15 */ *(__u32*)((addr_t) ®s->psw + addr*2 + 4) = tmp; } @@ -837,40 +866,66 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, asmlinkage long do_syscall_trace_enter(struct pt_regs *regs) { unsigned long mask = -1UL; + long ret = -1; + + if (is_compat_task()) + mask = 0xffffffff; /* * The sysc_tracesys code in entry.S stored the system * call number to gprs[2]. */ if (test_thread_flag(TIF_SYSCALL_TRACE) && - (tracehook_report_syscall_entry(regs) || - regs->gprs[2] >= NR_syscalls)) { + tracehook_report_syscall_entry(regs)) { /* - * Tracing decided this syscall should not happen or the - * debugger stored an invalid system call number. Skip + * Tracing decided this syscall should not happen. Skip * the system call and the system call restart handling. */ - clear_pt_regs_flag(regs, PIF_SYSCALL); - return -1; + goto skip; } +#ifdef CONFIG_SECCOMP /* Do the secure computing check after ptrace. */ - if (secure_computing()) { - /* seccomp failures shouldn't expose any additional code. */ - return -1; + if (unlikely(test_thread_flag(TIF_SECCOMP))) { + struct seccomp_data sd; + + if (is_compat_task()) { + sd.instruction_pointer = regs->psw.addr & 0x7fffffff; + sd.arch = AUDIT_ARCH_S390; + } else { + sd.instruction_pointer = regs->psw.addr; + sd.arch = AUDIT_ARCH_S390X; + } + + sd.nr = regs->int_code & 0xffff; + sd.args[0] = regs->orig_gpr2 & mask; + sd.args[1] = regs->gprs[3] & mask; + sd.args[2] = regs->gprs[4] & mask; + sd.args[3] = regs->gprs[5] & mask; + sd.args[4] = regs->gprs[6] & mask; + sd.args[5] = regs->gprs[7] & mask; + + if (__secure_computing(&sd) == -1) + goto skip; } +#endif /* CONFIG_SECCOMP */ if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) - trace_sys_enter(regs, regs->gprs[2]); + trace_sys_enter(regs, regs->int_code & 0xffff); - if (is_compat_task()) - mask = 0xffffffff; - audit_syscall_entry(regs->gprs[2], regs->orig_gpr2 & mask, + audit_syscall_entry(regs->int_code & 0xffff, regs->orig_gpr2 & mask, regs->gprs[3] &mask, regs->gprs[4] &mask, regs->gprs[5] &mask); + if ((signed long)regs->gprs[2] >= NR_syscalls) { + regs->gprs[2] = -ENOSYS; + ret = -ENOSYS; + } return regs->gprs[2]; +skip: + clear_pt_regs_flag(regs, PIF_SYSCALL); + return ret; } asmlinkage void do_syscall_trace_exit(struct pt_regs *regs) diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 5853c9872dfe..07aa15ba43b3 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -1100,6 +1100,7 @@ void __init setup_arch(char **cmdline_p) if (IS_ENABLED(CONFIG_EXPOLINE_AUTO)) nospec_auto_detect(); + jump_label_init(); parse_early_param(); #ifdef CONFIG_CRASH_DUMP /* Deactivate elfcorehdr= kernel parameter */ diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index f9d070d016e3..b1113b519432 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -301,6 +301,7 @@ void update_vsyscall(struct timekeeper *tk) vdso_data->tk_mult = tk->tkr_mono.mult; vdso_data->tk_shift = tk->tkr_mono.shift; + vdso_data->hrtimer_res = hrtimer_resolution; smp_wmb(); ++vdso_data->tb_update_count; } diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c index 66e89b2866d7..c296e5c8dbf9 100644 --- a/arch/s390/kernel/uv.c +++ b/arch/s390/kernel/uv.c @@ -331,7 +331,7 @@ EXPORT_SYMBOL_GPL(arch_make_page_accessible); static ssize_t uv_query_facilities(struct kobject *kobj, struct kobj_attribute *attr, char *page) { - return snprintf(page, PAGE_SIZE, "%lx\n%lx\n%lx\n%lx\n", + return scnprintf(page, PAGE_SIZE, "%lx\n%lx\n%lx\n%lx\n", uv_info.inst_calls_list[0], uv_info.inst_calls_list[1], uv_info.inst_calls_list[2], @@ -344,7 +344,7 @@ static struct kobj_attribute uv_query_facilities_attr = static ssize_t uv_query_max_guest_cpus(struct kobject *kobj, struct kobj_attribute *attr, char *page) { - return snprintf(page, PAGE_SIZE, "%d\n", + return scnprintf(page, PAGE_SIZE, "%d\n", uv_info.max_guest_cpus); } @@ -354,7 +354,7 @@ static struct kobj_attribute uv_query_max_guest_cpus_attr = static ssize_t uv_query_max_guest_vms(struct kobject *kobj, struct kobj_attribute *attr, char *page) { - return snprintf(page, PAGE_SIZE, "%d\n", + return scnprintf(page, PAGE_SIZE, "%d\n", uv_info.max_num_sec_conf); } @@ -364,7 +364,7 @@ static struct kobj_attribute uv_query_max_guest_vms_attr = static ssize_t uv_query_max_guest_addr(struct kobject *kobj, struct kobj_attribute *attr, char *page) { - return snprintf(page, PAGE_SIZE, "%lx\n", + return scnprintf(page, PAGE_SIZE, "%lx\n", uv_info.max_sec_stor_addr); } diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile index bec19e7e6e1c..4a66a1cb919b 100644 --- a/arch/s390/kernel/vdso64/Makefile +++ b/arch/s390/kernel/vdso64/Makefile @@ -18,8 +18,8 @@ KBUILD_AFLAGS_64 += -m64 -s KBUILD_CFLAGS_64 := $(filter-out -m64,$(KBUILD_CFLAGS)) KBUILD_CFLAGS_64 += -m64 -fPIC -shared -fno-common -fno-builtin -KBUILD_CFLAGS_64 += -nostdlib -Wl,-soname=linux-vdso64.so.1 \ - -Wl,--hash-style=both +ldflags-y := -fPIC -shared -nostdlib -soname=linux-vdso64.so.1 \ + --hash-style=both --build-id -T $(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_64) $(targets:%=$(obj)/%.dbg): KBUILD_AFLAGS = $(KBUILD_AFLAGS_64) @@ -37,8 +37,8 @@ KASAN_SANITIZE := n $(obj)/vdso64_wrapper.o : $(obj)/vdso64.so # link rule for the .so file, .lds has to be first -$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) FORCE - $(call if_changed,vdso64ld) +$(obj)/vdso64.so.dbg: $(obj)/vdso64.lds $(obj-vdso64) FORCE + $(call if_changed,ld) # strip rule for the .so file $(obj)/%.so: OBJCOPYFLAGS := -S @@ -50,8 +50,6 @@ $(obj-vdso64): %.o: %.S FORCE $(call if_changed_dep,vdso64as) # actual build commands -quiet_cmd_vdso64ld = VDSO64L $@ - cmd_vdso64ld = $(CC) $(c_flags) -Wl,-T $(filter %.lds %.o,$^) -o $@ quiet_cmd_vdso64as = VDSO64A $@ cmd_vdso64as = $(CC) $(a_flags) -c -o $@ $< diff --git a/arch/s390/kernel/vdso64/clock_getres.S b/arch/s390/kernel/vdso64/clock_getres.S index 081435398e0a..0c79caa32b59 100644 --- a/arch/s390/kernel/vdso64/clock_getres.S +++ b/arch/s390/kernel/vdso64/clock_getres.S @@ -17,12 +17,14 @@ .type __kernel_clock_getres,@function __kernel_clock_getres: CFI_STARTPROC - larl %r1,4f + larl %r1,3f + lg %r0,0(%r1) cghi %r2,__CLOCK_REALTIME_COARSE je 0f cghi %r2,__CLOCK_MONOTONIC_COARSE je 0f - larl %r1,3f + larl %r1,_vdso_data + llgf %r0,__VDSO_CLOCK_REALTIME_RES(%r1) cghi %r2,__CLOCK_REALTIME je 0f cghi %r2,__CLOCK_MONOTONIC @@ -36,7 +38,6 @@ __kernel_clock_getres: jz 2f 0: ltgr %r3,%r3 jz 1f /* res == NULL */ - lg %r0,0(%r1) xc 0(8,%r3),0(%r3) /* set tp->tv_sec to zero */ stg %r0,8(%r3) /* store tp->tv_usec */ 1: lghi %r2,0 @@ -45,6 +46,5 @@ __kernel_clock_getres: svc 0 br %r14 CFI_ENDPROC -3: .quad __CLOCK_REALTIME_RES -4: .quad __CLOCK_COARSE_RES +3: .quad __CLOCK_COARSE_RES .size __kernel_clock_getres,.-__kernel_clock_getres diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 6a24751557f0..d53c2e2ea1fd 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -105,7 +105,7 @@ static int bad_address(void *p) { unsigned long dummy; - return probe_kernel_address((unsigned long *)p, dummy); + return get_kernel_nofault(dummy, (unsigned long *)p); } static void dump_pagetable(unsigned long asce, unsigned long address) diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c index 82df06d720e8..3b5a4d25ca9b 100644 --- a/arch/s390/mm/hugetlbpage.c +++ b/arch/s390/mm/hugetlbpage.c @@ -117,7 +117,7 @@ static inline pte_t __rste_to_pte(unsigned long rste) _PAGE_YOUNG); #ifdef CONFIG_MEM_SOFT_DIRTY pte_val(pte) |= move_set_bit(rste, _SEGMENT_ENTRY_SOFT_DIRTY, - _PAGE_DIRTY); + _PAGE_SOFT_DIRTY); #endif pte_val(pte) |= move_set_bit(rste, _SEGMENT_ENTRY_NOEXEC, _PAGE_NOEXEC); diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c index 22a0be655f27..1d17413b319a 100644 --- a/arch/s390/mm/maccess.c +++ b/arch/s390/mm/maccess.c @@ -62,11 +62,15 @@ notrace void *s390_kernel_write(void *dst, const void *src, size_t size) long copied; spin_lock_irqsave(&s390_kernel_write_lock, flags); - while (size) { - copied = s390_kernel_write_odd(tmp, src, size); - tmp += copied; - src += copied; - size -= copied; + if (!(flags & PSW_MASK_DAT)) { + memcpy(dst, src, size); + } else { + while (size) { + copied = s390_kernel_write_odd(tmp, src, size); + tmp += copied; + src += copied; + size -= copied; + } } spin_unlock_irqrestore(&s390_kernel_write_lock, flags); diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c index 08e1d619398e..fdebd286f402 100644 --- a/arch/s390/pci/pci_event.c +++ b/arch/s390/pci/pci_event.c @@ -94,7 +94,18 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) } zdev->fh = ccdf->fh; zdev->state = ZPCI_FN_STATE_CONFIGURED; - zpci_create_device(zdev); + ret = zpci_enable_device(zdev); + if (ret) + break; + + pdev = pci_scan_single_device(zdev->zbus->bus, zdev->devfn); + if (!pdev) + break; + + pci_bus_add_device(pdev); + pci_lock_rescan_remove(); + pci_bus_add_devices(zdev->zbus->bus); + pci_unlock_rescan_remove(); break; case 0x0302: /* Reserved -> Standby */ if (!zdev) { diff --git a/arch/sh/kernel/ftrace.c b/arch/sh/kernel/ftrace.c index 1b04270e5460..0646c5961846 100644 --- a/arch/sh/kernel/ftrace.c +++ b/arch/sh/kernel/ftrace.c @@ -119,7 +119,7 @@ static void ftrace_mod_code(void) * But if one were to fail, then they all should, and if one were * to succeed, then they all should. */ - mod_code_status = probe_kernel_write(mod_code_ip, mod_code_newcode, + mod_code_status = copy_to_kernel_nofault(mod_code_ip, mod_code_newcode, MCOUNT_INSN_SIZE); /* if we fail, then kill any new writers */ @@ -203,7 +203,7 @@ static int ftrace_modify_code(unsigned long ip, unsigned char *old_code, */ /* read the text we want to modify */ - if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE)) + if (copy_from_kernel_nofault(replaced, (void *)ip, MCOUNT_INSN_SIZE)) return -EFAULT; /* Make sure it is what we expect it to be */ @@ -268,7 +268,7 @@ static int ftrace_mod(unsigned long ip, unsigned long old_addr, { unsigned char code[MCOUNT_INSN_SIZE]; - if (probe_kernel_read(code, (void *)ip, MCOUNT_INSN_SIZE)) + if (copy_from_kernel_nofault(code, (void *)ip, MCOUNT_INSN_SIZE)) return -EFAULT; if (old_addr != __raw_readl((unsigned long *)code)) diff --git a/arch/sh/kernel/traps.c b/arch/sh/kernel/traps.c index a33025451fcd..9c3d32b80038 100644 --- a/arch/sh/kernel/traps.c +++ b/arch/sh/kernel/traps.c @@ -118,7 +118,7 @@ int is_valid_bugaddr(unsigned long addr) if (addr < PAGE_OFFSET) return 0; - if (probe_kernel_address((insn_size_t *)addr, opcode)) + if (get_kernel_nofault(opcode, (insn_size_t *)addr)) return 0; if (opcode == TRAPA_BUG_OPCODE) return 1; diff --git a/arch/um/kernel/maccess.c b/arch/um/kernel/maccess.c index e929c0966696..8ccd56813f68 100644 --- a/arch/um/kernel/maccess.c +++ b/arch/um/kernel/maccess.c @@ -7,7 +7,7 @@ #include <linux/kernel.h> #include <os.h> -bool probe_kernel_read_allowed(const void *src, size_t size) +bool copy_from_kernel_nofault_allowed(const void *src, size_t size) { void *psrc = (void *)rounddown((unsigned long)src, PAGE_SIZE); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 6a0cc524882d..883da0abf779 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -67,7 +67,7 @@ config X86 select ARCH_HAS_FILTER_PGPROT select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_GCOV_PROFILE_ALL - select ARCH_HAS_KCOV if X86_64 + select ARCH_HAS_KCOV if X86_64 && STACK_VALIDATION select ARCH_HAS_MEM_ENCRYPT select ARCH_HAS_MEMBARRIER_SYNC_CORE select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 7619742f91c9..5a828fde7a42 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -90,8 +90,8 @@ endif vmlinux-objs-$(CONFIG_ACPI) += $(obj)/acpi.o -vmlinux-objs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_thunk_$(BITS).o +efi-obj-$(CONFIG_EFI_STUB) = $(objtree)/drivers/firmware/efi/libstub/lib.a # The compressed kernel is built with -fPIC/-fPIE so that a boot loader # can place it anywhere in memory and it will still run. However, since @@ -115,7 +115,7 @@ endef quiet_cmd_check-and-link-vmlinux = LD $@ cmd_check-and-link-vmlinux = $(cmd_check_data_rel); $(cmd_ld) -$(obj)/vmlinux: $(vmlinux-objs-y) FORCE +$(obj)/vmlinux: $(vmlinux-objs-y) $(efi-obj-y) FORCE $(call if_changed,check-and-link-vmlinux) OBJCOPYFLAGS_vmlinux.bin := -R .comment -S diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index e821a7d7d5c4..97d37f0a34f5 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -213,7 +213,6 @@ SYM_FUNC_START(startup_32) * We place all of the values on our mini stack so lret can * used to perform that far jump. */ - pushl $__KERNEL_CS leal startup_64(%ebp), %eax #ifdef CONFIG_EFI_MIXED movl efi32_boot_args(%ebp), %edi @@ -224,11 +223,20 @@ SYM_FUNC_START(startup_32) movl efi32_boot_args+8(%ebp), %edx // saved bootparams pointer cmpl $0, %edx jnz 1f + /* + * efi_pe_entry uses MS calling convention, which requires 32 bytes of + * shadow space on the stack even if all arguments are passed in + * registers. We also need an additional 8 bytes for the space that + * would be occupied by the return address, and this also results in + * the correct stack alignment for entry. + */ + subl $40, %esp leal efi_pe_entry(%ebp), %eax movl %edi, %ecx // MS calling convention movl %esi, %edx 1: #endif + pushl $__KERNEL_CS pushl %eax /* Enter paged protected Mode, activating Long Mode */ @@ -784,6 +792,7 @@ SYM_DATA_LOCAL(boot_heap, .fill BOOT_HEAP_SIZE, 1, 0) SYM_DATA_START_LOCAL(boot_stack) .fill BOOT_STACK_SIZE, 1, 0 + .balign 16 SYM_DATA_END_LABEL(boot_stack, SYM_L_LOCAL, boot_stack_end) /* diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile index b7a5790d8d63..08bf95dbc911 100644 --- a/arch/x86/entry/Makefile +++ b/arch/x86/entry/Makefile @@ -7,12 +7,20 @@ KASAN_SANITIZE := n UBSAN_SANITIZE := n KCOV_INSTRUMENT := n -CFLAGS_REMOVE_common.o = $(CC_FLAGS_FTRACE) -fstack-protector -fstack-protector-strong -CFLAGS_REMOVE_syscall_32.o = $(CC_FLAGS_FTRACE) -fstack-protector -fstack-protector-strong -CFLAGS_REMOVE_syscall_64.o = $(CC_FLAGS_FTRACE) -fstack-protector -fstack-protector-strong +CFLAGS_REMOVE_common.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_syscall_64.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_syscall_32.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_syscall_x32.o = $(CC_FLAGS_FTRACE) + +CFLAGS_common.o += -fno-stack-protector +CFLAGS_syscall_64.o += -fno-stack-protector +CFLAGS_syscall_32.o += -fno-stack-protector +CFLAGS_syscall_x32.o += -fno-stack-protector CFLAGS_syscall_64.o += $(call cc-option,-Wno-override-init,) CFLAGS_syscall_32.o += $(call cc-option,-Wno-override-init,) +CFLAGS_syscall_x32.o += $(call cc-option,-Wno-override-init,) + obj-y := entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o obj-y += common.o diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index bd3f14175193..f09288431f28 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -45,6 +45,32 @@ #define CREATE_TRACE_POINTS #include <trace/events/syscalls.h> +/* Check that the stack and regs on entry from user mode are sane. */ +static noinstr void check_user_regs(struct pt_regs *regs) +{ + if (IS_ENABLED(CONFIG_DEBUG_ENTRY)) { + /* + * Make sure that the entry code gave us a sensible EFLAGS + * register. Native because we want to check the actual CPU + * state, not the interrupt state as imagined by Xen. + */ + unsigned long flags = native_save_fl(); + WARN_ON_ONCE(flags & (X86_EFLAGS_AC | X86_EFLAGS_DF | + X86_EFLAGS_NT)); + + /* We think we came from user mode. Make sure pt_regs agrees. */ + WARN_ON_ONCE(!user_mode(regs)); + + /* + * All entries from user mode (except #DF) should be on the + * normal thread stack and should have user pt_regs in the + * correct location. + */ + WARN_ON_ONCE(!on_thread_stack()); + WARN_ON_ONCE(regs != task_pt_regs(current)); + } +} + #ifdef CONFIG_CONTEXT_TRACKING /** * enter_from_user_mode - Establish state when coming from user mode @@ -127,9 +153,6 @@ static long syscall_trace_enter(struct pt_regs *regs) unsigned long ret = 0; u32 work; - if (IS_ENABLED(CONFIG_DEBUG_ENTRY)) - BUG_ON(regs != task_pt_regs(current)); - work = READ_ONCE(ti->flags); if (work & (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU)) { @@ -271,7 +294,7 @@ static void __prepare_exit_to_usermode(struct pt_regs *regs) #endif } -__visible noinstr void prepare_exit_to_usermode(struct pt_regs *regs) +static noinstr void prepare_exit_to_usermode(struct pt_regs *regs) { instrumentation_begin(); __prepare_exit_to_usermode(regs); @@ -346,6 +369,8 @@ __visible noinstr void do_syscall_64(unsigned long nr, struct pt_regs *regs) { struct thread_info *ti; + check_user_regs(regs); + enter_from_user_mode(); instrumentation_begin(); @@ -409,6 +434,8 @@ static void do_syscall_32_irqs_on(struct pt_regs *regs) /* Handles int $0x80 */ __visible noinstr void do_int80_syscall_32(struct pt_regs *regs) { + check_user_regs(regs); + enter_from_user_mode(); instrumentation_begin(); @@ -460,6 +487,8 @@ __visible noinstr long do_fast_syscall_32(struct pt_regs *regs) vdso_image_32.sym_int80_landing_pad; bool success; + check_user_regs(regs); + /* * SYSENTER loses EIP, and even SYSCALL32 needs us to skip forward * so that 'regs->ip -= 2' lands back on an int $0x80 instruction. @@ -510,6 +539,18 @@ __visible noinstr long do_fast_syscall_32(struct pt_regs *regs) (regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF | X86_EFLAGS_VM)) == 0; #endif } + +/* Returns 0 to return using IRET or 1 to return using SYSEXIT/SYSRETL. */ +__visible noinstr long do_SYSENTER_32(struct pt_regs *regs) +{ + /* SYSENTER loses RSP, but the vDSO saved it in RBP. */ + regs->sp = regs->bp; + + /* SYSENTER clobbers EFLAGS.IF. Assume it was set in usermode. */ + regs->flags |= X86_EFLAGS_IF; + + return do_fast_syscall_32(regs); +} #endif SYSCALL_DEFINE0(ni_syscall) @@ -553,6 +594,7 @@ SYSCALL_DEFINE0(ni_syscall) bool noinstr idtentry_enter_cond_rcu(struct pt_regs *regs) { if (user_mode(regs)) { + check_user_regs(regs); enter_from_user_mode(); return false; } @@ -686,6 +728,7 @@ void noinstr idtentry_exit_cond_rcu(struct pt_regs *regs, bool rcu_exit) */ void noinstr idtentry_enter_user(struct pt_regs *regs) { + check_user_regs(regs); enter_from_user_mode(); } diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 024d7d276cd4..2d0bd5d5f032 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -933,9 +933,8 @@ SYM_FUNC_START(entry_SYSENTER_32) .Lsysenter_past_esp: pushl $__USER_DS /* pt_regs->ss */ - pushl %ebp /* pt_regs->sp (stashed in bp) */ + pushl $0 /* pt_regs->sp (placeholder) */ pushfl /* pt_regs->flags (except IF = 0) */ - orl $X86_EFLAGS_IF, (%esp) /* Fix IF */ pushl $__USER_CS /* pt_regs->cs */ pushl $0 /* pt_regs->ip = 0 (placeholder) */ pushl %eax /* pt_regs->orig_ax */ @@ -965,7 +964,7 @@ SYM_FUNC_START(entry_SYSENTER_32) .Lsysenter_flags_fixed: movl %esp, %eax - call do_fast_syscall_32 + call do_SYSENTER_32 /* XEN PV guests always use IRET path */ ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \ "jmp .Lsyscall_32_done", X86_FEATURE_XENPV diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 0f974ae01e62..541fdaf64045 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -57,29 +57,30 @@ SYM_CODE_START(entry_SYSENTER_compat) movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp - /* - * User tracing code (ptrace or signal handlers) might assume that - * the saved RAX contains a 32-bit number when we're invoking a 32-bit - * syscall. Just in case the high bits are nonzero, zero-extend - * the syscall number. (This could almost certainly be deleted - * with no ill effects.) - */ - movl %eax, %eax - /* Construct struct pt_regs on stack */ pushq $__USER32_DS /* pt_regs->ss */ - pushq %rbp /* pt_regs->sp (stashed in bp) */ + pushq $0 /* pt_regs->sp = 0 (placeholder) */ /* * Push flags. This is nasty. First, interrupts are currently - * off, but we need pt_regs->flags to have IF set. Second, even - * if TF was set when SYSENTER started, it's clear by now. We fix - * that later using TIF_SINGLESTEP. + * off, but we need pt_regs->flags to have IF set. Second, if TS + * was set in usermode, it's still set, and we're singlestepping + * through this code. do_SYSENTER_32() will fix up IF. */ pushfq /* pt_regs->flags (except IF = 0) */ - orl $X86_EFLAGS_IF, (%rsp) /* Fix saved flags */ pushq $__USER32_CS /* pt_regs->cs */ pushq $0 /* pt_regs->ip = 0 (placeholder) */ +SYM_INNER_LABEL(entry_SYSENTER_compat_after_hwframe, SYM_L_GLOBAL) + + /* + * User tracing code (ptrace or signal handlers) might assume that + * the saved RAX contains a 32-bit number when we're invoking a 32-bit + * syscall. Just in case the high bits are nonzero, zero-extend + * the syscall number. (This could almost certainly be deleted + * with no ill effects.) + */ + movl %eax, %eax + pushq %rax /* pt_regs->orig_ax */ pushq %rdi /* pt_regs->di */ pushq %rsi /* pt_regs->si */ @@ -135,7 +136,7 @@ SYM_CODE_START(entry_SYSENTER_compat) .Lsysenter_flags_fixed: movq %rsp, %rdi - call do_fast_syscall_32 + call do_SYSENTER_32 /* XEN PV guests always use IRET path */ ALTERNATIVE "testl %eax, %eax; jz swapgs_restore_regs_and_return_to_usermode", \ "jmp swapgs_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV diff --git a/arch/x86/events/Makefile b/arch/x86/events/Makefile index 12c42eba77ec..9933c0e8e97a 100644 --- a/arch/x86/events/Makefile +++ b/arch/x86/events/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only obj-y += core.o probe.o -obj-$(PERF_EVENTS_INTEL_RAPL) += rapl.o +obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL) += rapl.o obj-y += amd/ obj-$(CONFIG_X86_LOCAL_APIC) += msr.o obj-$(CONFIG_CPU_SUP_INTEL) += intel/ diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index a54c6a401581..6035df1b49e1 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -375,7 +375,10 @@ void __init hyperv_init(void) guest_id = generate_guest_id(0, LINUX_VERSION_CODE, 0); wrmsrl(HV_X64_MSR_GUEST_OS_ID, guest_id); - hv_hypercall_pg = vmalloc_exec(PAGE_SIZE); + hv_hypercall_pg = __vmalloc_node_range(PAGE_SIZE, 1, VMALLOC_START, + VMALLOC_END, GFP_KERNEL, PAGE_KERNEL_ROX, + VM_FLUSH_RESET_PERMS, NUMA_NO_NODE, + __builtin_return_address(0)); if (hv_hypercall_pg == NULL) { wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0); goto remove_cpuhp_state; diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 35460fef39b8..0367efdc5b7a 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -201,12 +201,8 @@ arch_test_and_change_bit(long nr, volatile unsigned long *addr) return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btc), *addr, c, "Ir", nr); } -static __no_kcsan_or_inline bool constant_test_bit(long nr, const volatile unsigned long *addr) +static __always_inline bool constant_test_bit(long nr, const volatile unsigned long *addr) { - /* - * Because this is a plain access, we need to disable KCSAN here to - * avoid double instrumentation via instrumented bitops. - */ return ((1UL << (nr & (BITS_PER_LONG-1))) & (addr[nr >> _BITOPS_LONG_SHIFT])) != 0; } diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index fb34ff641e0a..028189575560 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -75,6 +75,12 @@ do { \ unreachable(); \ } while (0) +/* + * This instrumentation_begin() is strictly speaking incorrect; but it + * suppresses the complaints from WARN()s in noinstr code. If such a WARN() + * were to trigger, we'd rather wreck the machine in an attempt to get the + * message out than not know about it. + */ #define __WARN_FLAGS(flags) \ do { \ instrumentation_begin(); \ diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h index dd17c2da1af5..da78ccbd493b 100644 --- a/arch/x86/include/asm/cpu.h +++ b/arch/x86/include/asm/cpu.h @@ -58,4 +58,9 @@ static inline bool handle_guest_split_lock(unsigned long ip) return false; } #endif +#ifdef CONFIG_IA32_FEAT_CTL +void init_ia32_feat_ctl(struct cpuinfo_x86 *c); +#else +static inline void init_ia32_feat_ctl(struct cpuinfo_x86 *c) {} +#endif #endif /* _ASM_X86_CPU_H */ diff --git a/arch/x86/include/asm/cpumask.h b/arch/x86/include/asm/cpumask.h index 6722ffcef2e6..3afa990d756b 100644 --- a/arch/x86/include/asm/cpumask.h +++ b/arch/x86/include/asm/cpumask.h @@ -11,5 +11,23 @@ extern cpumask_var_t cpu_sibling_setup_mask; extern void setup_cpu_local_masks(void); +/* + * NMI and MCE exceptions need cpu_is_offline() _really_ early, + * provide an arch_ special for them to avoid instrumentation. + */ +#if NR_CPUS > 1 +static __always_inline bool arch_cpu_online(int cpu) +{ + return arch_test_bit(cpu, cpumask_bits(cpu_online_mask)); +} +#else +static __always_inline bool arch_cpu_online(int cpu) +{ + return cpu == 0; +} +#endif + +#define arch_cpu_is_offline(cpu) unlikely(!arch_cpu_online(cpu)) + #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_CPUMASK_H */ diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 42159f45bf9c..845e7481ab77 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -623,6 +623,11 @@ static inline void switch_fpu_finish(struct fpu *new_fpu) * MXCSR and XCR definitions: */ +static inline void ldmxcsr(u32 mxcsr) +{ + asm volatile("ldmxcsr %0" :: "m" (mxcsr)); +} + extern unsigned int mxcsr_feature_mask; #define XCR_XFEATURE_ENABLED_MASK 0x00000000 diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h index cf51c50eb356..80d3b30d3ee3 100644 --- a/arch/x86/include/asm/idtentry.h +++ b/arch/x86/include/asm/idtentry.h @@ -353,10 +353,6 @@ static __always_inline void __##func(struct pt_regs *regs) #else /* CONFIG_X86_64 */ -/* Maps to a regular IDTENTRY on 32bit for now */ -# define DECLARE_IDTENTRY_IST DECLARE_IDTENTRY -# define DEFINE_IDTENTRY_IST DEFINE_IDTENTRY - /** * DECLARE_IDTENTRY_DF - Declare functions for double fault 32bit variant * @vector: Vector number (ignored for C) @@ -387,28 +383,18 @@ __visible noinstr void func(struct pt_regs *regs, \ #endif /* !CONFIG_X86_64 */ /* C-Code mapping */ +#define DECLARE_IDTENTRY_NMI DECLARE_IDTENTRY_RAW +#define DEFINE_IDTENTRY_NMI DEFINE_IDTENTRY_RAW + +#ifdef CONFIG_X86_64 #define DECLARE_IDTENTRY_MCE DECLARE_IDTENTRY_IST #define DEFINE_IDTENTRY_MCE DEFINE_IDTENTRY_IST #define DEFINE_IDTENTRY_MCE_USER DEFINE_IDTENTRY_NOIST -#define DECLARE_IDTENTRY_NMI DECLARE_IDTENTRY_RAW -#define DEFINE_IDTENTRY_NMI DEFINE_IDTENTRY_RAW - #define DECLARE_IDTENTRY_DEBUG DECLARE_IDTENTRY_IST #define DEFINE_IDTENTRY_DEBUG DEFINE_IDTENTRY_IST #define DEFINE_IDTENTRY_DEBUG_USER DEFINE_IDTENTRY_NOIST - -/** - * DECLARE_IDTENTRY_XEN - Declare functions for XEN redirect IDT entry points - * @vector: Vector number (ignored for C) - * @func: Function name of the entry point - * - * Used for xennmi and xendebug redirections. No DEFINE as this is all ASM - * indirection magic. - */ -#define DECLARE_IDTENTRY_XEN(vector, func) \ - asmlinkage void xen_asm_exc_xen##func(void); \ - asmlinkage void asm_exc_xen##func(void) +#endif #else /* !__ASSEMBLY__ */ @@ -455,9 +441,6 @@ __visible noinstr void func(struct pt_regs *regs, \ # define DECLARE_IDTENTRY_MCE(vector, func) \ DECLARE_IDTENTRY(vector, func) -# define DECLARE_IDTENTRY_DEBUG(vector, func) \ - DECLARE_IDTENTRY(vector, func) - /* No ASM emitted for DF as this goes through a C shim */ # define DECLARE_IDTENTRY_DF(vector, func) @@ -469,10 +452,6 @@ __visible noinstr void func(struct pt_regs *regs, \ /* No ASM code emitted for NMI */ #define DECLARE_IDTENTRY_NMI(vector, func) -/* XEN NMI and DB wrapper */ -#define DECLARE_IDTENTRY_XEN(vector, func) \ - idtentry vector asm_exc_xen##func exc_##func has_error_code=0 - /* * ASM code to emit the common vector entry stubs where each stub is * packed into 8 bytes. @@ -490,16 +469,15 @@ __visible noinstr void func(struct pt_regs *regs, \ .align 8 SYM_CODE_START(irq_entries_start) vector=FIRST_EXTERNAL_VECTOR - pos = . .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR) UNWIND_HINT_IRET_REGS +0 : .byte 0x6a, vector jmp asm_common_interrupt nop /* Ensure that the above is 8 bytes max */ - . = pos + 8 - pos=pos+8 - vector=vector+1 + . = 0b + 8 + vector = vector+1 .endr SYM_CODE_END(irq_entries_start) @@ -507,16 +485,15 @@ SYM_CODE_END(irq_entries_start) .align 8 SYM_CODE_START(spurious_entries_start) vector=FIRST_SYSTEM_VECTOR - pos = . .rept (NR_VECTORS - FIRST_SYSTEM_VECTOR) UNWIND_HINT_IRET_REGS +0 : .byte 0x6a, vector jmp asm_spurious_interrupt nop /* Ensure that the above is 8 bytes max */ - . = pos + 8 - pos=pos+8 - vector=vector+1 + . = 0b + 8 + vector = vector+1 .endr SYM_CODE_END(spurious_entries_start) #endif @@ -565,16 +542,28 @@ DECLARE_IDTENTRY_RAW(X86_TRAP_BP, exc_int3); DECLARE_IDTENTRY_RAW_ERRORCODE(X86_TRAP_PF, exc_page_fault); #ifdef CONFIG_X86_MCE +#ifdef CONFIG_X86_64 DECLARE_IDTENTRY_MCE(X86_TRAP_MC, exc_machine_check); +#else +DECLARE_IDTENTRY_RAW(X86_TRAP_MC, exc_machine_check); +#endif #endif /* NMI */ DECLARE_IDTENTRY_NMI(X86_TRAP_NMI, exc_nmi); -DECLARE_IDTENTRY_XEN(X86_TRAP_NMI, nmi); +#if defined(CONFIG_XEN_PV) && defined(CONFIG_X86_64) +DECLARE_IDTENTRY_RAW(X86_TRAP_NMI, xenpv_exc_nmi); +#endif /* #DB */ +#ifdef CONFIG_X86_64 DECLARE_IDTENTRY_DEBUG(X86_TRAP_DB, exc_debug); -DECLARE_IDTENTRY_XEN(X86_TRAP_DB, debug); +#else +DECLARE_IDTENTRY_RAW(X86_TRAP_DB, exc_debug); +#endif +#if defined(CONFIG_XEN_PV) && defined(CONFIG_X86_64) +DECLARE_IDTENTRY_RAW(X86_TRAP_DB, xenpv_exc_debug); +#endif /* #DF */ DECLARE_IDTENTRY_DF(X86_TRAP_DF, exc_double_fault); @@ -635,8 +624,8 @@ DECLARE_IDTENTRY_SYSVEC(POSTED_INTR_NESTED_VECTOR, sysvec_kvm_posted_intr_nested #if IS_ENABLED(CONFIG_HYPERV) DECLARE_IDTENTRY_SYSVEC(HYPERVISOR_CALLBACK_VECTOR, sysvec_hyperv_callback); -DECLARE_IDTENTRY_SYSVEC(HYPERVISOR_REENLIGHTENMENT_VECTOR, sysvec_hyperv_reenlightenment); -DECLARE_IDTENTRY_SYSVEC(HYPERVISOR_STIMER0_VECTOR, sysvec_hyperv_stimer0); +DECLARE_IDTENTRY_SYSVEC(HYPERV_REENLIGHTENMENT_VECTOR, sysvec_hyperv_reenlightenment); +DECLARE_IDTENTRY_SYSVEC(HYPERV_STIMER0_VECTOR, sysvec_hyperv_stimer0); #endif #if IS_ENABLED(CONFIG_ACRN_GUEST) diff --git a/arch/x86/include/asm/io_bitmap.h b/arch/x86/include/asm/io_bitmap.h index ac1a99ffbd8d..7f080f5c7def 100644 --- a/arch/x86/include/asm/io_bitmap.h +++ b/arch/x86/include/asm/io_bitmap.h @@ -19,12 +19,28 @@ struct task_struct; void io_bitmap_share(struct task_struct *tsk); void io_bitmap_exit(struct task_struct *tsk); +static inline void native_tss_invalidate_io_bitmap(void) +{ + /* + * Invalidate the I/O bitmap by moving io_bitmap_base outside the + * TSS limit so any subsequent I/O access from user space will + * trigger a #GP. + * + * This is correct even when VMEXIT rewrites the TSS limit + * to 0x67 as the only requirement is that the base points + * outside the limit. + */ + this_cpu_write(cpu_tss_rw.x86_tss.io_bitmap_base, + IO_BITMAP_OFFSET_INVALID); +} + void native_tss_update_io_bitmap(void); #ifdef CONFIG_PARAVIRT_XXL #include <asm/paravirt.h> #else #define tss_update_io_bitmap native_tss_update_io_bitmap +#define tss_invalidate_io_bitmap native_tss_invalidate_io_bitmap #endif #else diff --git a/arch/x86/include/asm/iosf_mbi.h b/arch/x86/include/asm/iosf_mbi.h index 5270ff39b9af..a1911fea8739 100644 --- a/arch/x86/include/asm/iosf_mbi.h +++ b/arch/x86/include/asm/iosf_mbi.h @@ -39,6 +39,7 @@ #define BT_MBI_UNIT_PMC 0x04 #define BT_MBI_UNIT_GFX 0x06 #define BT_MBI_UNIT_SMI 0x0C +#define BT_MBI_UNIT_CCK 0x14 #define BT_MBI_UNIT_USB 0x43 #define BT_MBI_UNIT_SATA 0xA3 #define BT_MBI_UNIT_PCIE 0xA6 diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index f8998e97457f..be5363b21540 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -943,7 +943,7 @@ struct kvm_arch { atomic_t vapics_in_nmi_mode; struct mutex apic_map_lock; struct kvm_apic_map *apic_map; - bool apic_map_dirty; + atomic_t apic_map_dirty; bool apic_access_page_done; unsigned long apicv_inhibit_reasons; @@ -1220,7 +1220,7 @@ struct kvm_x86_ops { void (*enable_log_dirty_pt_masked)(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t offset, unsigned long mask); - int (*write_log_dirty)(struct kvm_vcpu *vcpu); + int (*write_log_dirty)(struct kvm_vcpu *vcpu, gpa_t l2_gpa); /* pmu operations of sub-arch */ const struct kvm_pmu_ops *pmu_ops; diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h index 73d997aa2966..e039a933aca3 100644 --- a/arch/x86/include/asm/mwait.h +++ b/arch/x86/include/asm/mwait.h @@ -25,8 +25,6 @@ #define TPAUSE_C01_STATE 1 #define TPAUSE_C02_STATE 0 -u32 get_umwait_control_msr(void); - static inline void __monitor(const void *eax, unsigned long ecx, unsigned long edx) { diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 5ca5d297df75..3d2afecde50c 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -302,6 +302,11 @@ static inline void write_idt_entry(gate_desc *dt, int entry, const gate_desc *g) } #ifdef CONFIG_X86_IOPL_IOPERM +static inline void tss_invalidate_io_bitmap(void) +{ + PVOP_VCALL0(cpu.invalidate_io_bitmap); +} + static inline void tss_update_io_bitmap(void) { PVOP_VCALL0(cpu.update_io_bitmap); diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 732f62e04ddb..8dfcb2508e6d 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -141,6 +141,7 @@ struct pv_cpu_ops { void (*load_sp0)(unsigned long sp0); #ifdef CONFIG_X86_IOPL_IOPERM + void (*invalidate_io_bitmap)(void); void (*update_io_bitmap)(void); #endif diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 2da1f95b88d7..816b31c68550 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -194,6 +194,7 @@ enum page_cache_mode { #define _PAGE_TABLE_NOENC (__PP|__RW|_USR|___A| 0|___D| 0| 0) #define _PAGE_TABLE (__PP|__RW|_USR|___A| 0|___D| 0| 0| _ENC) #define __PAGE_KERNEL_RO (__PP| 0| 0|___A|__NX|___D| 0|___G) +#define __PAGE_KERNEL_ROX (__PP| 0| 0|___A| 0|___D| 0|___G) #define __PAGE_KERNEL_NOCACHE (__PP|__RW| 0|___A|__NX|___D| 0|___G| __NC) #define __PAGE_KERNEL_VVAR (__PP| 0|_USR|___A|__NX|___D| 0|___G) #define __PAGE_KERNEL_LARGE (__PP|__RW| 0|___A|__NX|___D|_PSE|___G) @@ -219,6 +220,7 @@ enum page_cache_mode { #define PAGE_KERNEL_RO __pgprot_mask(__PAGE_KERNEL_RO | _ENC) #define PAGE_KERNEL_EXEC __pgprot_mask(__PAGE_KERNEL_EXEC | _ENC) #define PAGE_KERNEL_EXEC_NOENC __pgprot_mask(__PAGE_KERNEL_EXEC | 0) +#define PAGE_KERNEL_ROX __pgprot_mask(__PAGE_KERNEL_ROX | _ENC) #define PAGE_KERNEL_NOCACHE __pgprot_mask(__PAGE_KERNEL_NOCACHE | _ENC) #define PAGE_KERNEL_LARGE __pgprot_mask(__PAGE_KERNEL_LARGE | _ENC) #define PAGE_KERNEL_LARGE_EXEC __pgprot_mask(__PAGE_KERNEL_LARGE_EXEC | _ENC) diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 42cd333616c4..03b7c4ca425a 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -370,7 +370,7 @@ struct x86_hw_tss { #define IO_BITMAP_OFFSET_INVALID (__KERNEL_TSS_LIMIT + 1) struct entry_stack { - unsigned long words[64]; + char stack[PAGE_SIZE]; }; struct entry_stack_page { diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index ebedeab48704..255b2dde2c1b 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -278,7 +278,7 @@ static inline unsigned long *regs_get_kernel_stack_nth_addr(struct pt_regs *regs } /* To avoid include hell, we can't include uaccess.h */ -extern long probe_kernel_read(void *dst, const void *src, size_t size); +extern long copy_from_kernel_nofault(void *dst, const void *src, size_t size); /** * regs_get_kernel_stack_nth() - get Nth entry of the stack @@ -298,7 +298,7 @@ static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, addr = regs_get_kernel_stack_nth_addr(regs, n); if (addr) { - ret = probe_kernel_read(&val, addr, sizeof(val)); + ret = copy_from_kernel_nofault(&val, addr, sizeof(val)); if (!ret) return val; } diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 17c5a038f42d..0780f97c1850 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -408,14 +408,15 @@ struct kvm_vmx_nested_state_data { }; struct kvm_vmx_nested_state_hdr { - __u32 flags; __u64 vmxon_pa; __u64 vmcs12_pa; - __u64 preemption_timer_deadline; struct { __u16 flags; } smm; + + __u32 flags; + __u64 preemption_timer_deadline; }; struct kvm_svm_nested_state_data { diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index ce61e3e7d399..81ffcfbfaef2 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2316,12 +2316,12 @@ static int mp_irqdomain_create(int ioapic) ip->irqdomain = irq_domain_create_linear(fn, hwirqs, cfg->ops, (void *)(long)ioapic); - /* Release fw handle if it was allocated above */ - if (!cfg->dev) - irq_domain_free_fwnode(fn); - - if (!ip->irqdomain) + if (!ip->irqdomain) { + /* Release fw handle if it was allocated above */ + if (!cfg->dev) + irq_domain_free_fwnode(fn); return -ENOMEM; + } ip->irqdomain->parent = parent; diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c index 5cbaca58af95..c2b2911feeef 100644 --- a/arch/x86/kernel/apic/msi.c +++ b/arch/x86/kernel/apic/msi.c @@ -263,12 +263,13 @@ void __init arch_init_msi_domain(struct irq_domain *parent) msi_default_domain = pci_msi_create_irq_domain(fn, &pci_msi_domain_info, parent); - irq_domain_free_fwnode(fn); } - if (!msi_default_domain) + if (!msi_default_domain) { + irq_domain_free_fwnode(fn); pr_warn("failed to initialize irqdomain for MSI/MSI-x.\n"); - else + } else { msi_default_domain->flags |= IRQ_DOMAIN_MSI_NOMASK_QUIRK; + } } #ifdef CONFIG_IRQ_REMAP @@ -301,7 +302,8 @@ struct irq_domain *arch_create_remap_msi_irq_domain(struct irq_domain *parent, if (!fn) return NULL; d = pci_msi_create_irq_domain(fn, &pci_msi_ir_domain_info, parent); - irq_domain_free_fwnode(fn); + if (!d) + irq_domain_free_fwnode(fn); return d; } #endif @@ -364,7 +366,8 @@ static struct irq_domain *dmar_get_irq_domain(void) if (fn) { dmar_domain = msi_create_irq_domain(fn, &dmar_msi_domain_info, x86_vector_domain); - irq_domain_free_fwnode(fn); + if (!dmar_domain) + irq_domain_free_fwnode(fn); } out: mutex_unlock(&dmar_lock); @@ -489,7 +492,10 @@ struct irq_domain *hpet_create_irq_domain(int hpet_id) } d = msi_create_irq_domain(fn, domain_info, parent); - irq_domain_free_fwnode(fn); + if (!d) { + irq_domain_free_fwnode(fn); + kfree(domain_info); + } return d; } diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index c48be6e1f676..7649da2478d8 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -446,12 +446,10 @@ static int x86_vector_activate(struct irq_domain *dom, struct irq_data *irqd, trace_vector_activate(irqd->irq, apicd->is_managed, apicd->can_reserve, reserve); - /* Nothing to do for fixed assigned vectors */ - if (!apicd->can_reserve && !apicd->is_managed) - return 0; - raw_spin_lock_irqsave(&vector_lock, flags); - if (reserve || irqd_is_managed_and_shutdown(irqd)) + if (!apicd->can_reserve && !apicd->is_managed) + assign_irq_vector_any_locked(irqd); + else if (reserve || irqd_is_managed_and_shutdown(irqd)) vector_assign_managed_shutdown(irqd); else if (apicd->is_managed) ret = activate_managed(irqd); @@ -709,7 +707,6 @@ int __init arch_early_irq_init(void) x86_vector_domain = irq_domain_create_tree(fn, &x86_vector_domain_ops, NULL); BUG_ON(x86_vector_domain == NULL); - irq_domain_free_fwnode(fn); irq_set_default_host(x86_vector_domain); arch_init_msi_domain(x86_vector_domain); @@ -775,20 +772,10 @@ void lapic_offline(void) static int apic_set_affinity(struct irq_data *irqd, const struct cpumask *dest, bool force) { - struct apic_chip_data *apicd = apic_chip_data(irqd); int err; - /* - * Core code can call here for inactive interrupts. For inactive - * interrupts which use managed or reservation mode there is no - * point in going through the vector assignment right now as the - * activation will assign a vector which fits the destination - * cpumask. Let the core code store the destination mask and be - * done with it. - */ - if (!irqd_is_activated(irqd) && - (apicd->is_managed || apicd->can_reserve)) - return IRQ_SET_MASK_OK; + if (WARN_ON_ONCE(!irqd_is_activated(irqd))) + return -EIO; raw_spin_lock(&vector_lock); cpumask_and(vector_searchmask, dest, cpu_online_mask); diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index 426792565d86..c5cf336e5077 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -3,6 +3,7 @@ #include <linux/sched.h> #include <linux/sched/clock.h> +#include <asm/cpu.h> #include <asm/cpufeature.h> #include <asm/e820/api.h> #include <asm/mtrr.h> diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 043d93cdcaad..95c090a45b4b 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -347,6 +347,9 @@ out: cr4_clear_bits(X86_CR4_UMIP); } +/* These bits should not change their value after CPU init is finished. */ +static const unsigned long cr4_pinned_mask = + X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_UMIP | X86_CR4_FSGSBASE; static DEFINE_STATIC_KEY_FALSE_RO(cr_pinning); static unsigned long cr4_pinned_bits __ro_after_init; @@ -371,20 +374,20 @@ EXPORT_SYMBOL(native_write_cr0); void native_write_cr4(unsigned long val) { - unsigned long bits_missing = 0; + unsigned long bits_changed = 0; set_register: asm volatile("mov %0,%%cr4": "+r" (val), "+m" (cr4_pinned_bits)); if (static_branch_likely(&cr_pinning)) { - if (unlikely((val & cr4_pinned_bits) != cr4_pinned_bits)) { - bits_missing = ~val & cr4_pinned_bits; - val |= bits_missing; + if (unlikely((val & cr4_pinned_mask) != cr4_pinned_bits)) { + bits_changed = (val & cr4_pinned_mask) ^ cr4_pinned_bits; + val = (val & ~cr4_pinned_mask) | cr4_pinned_bits; goto set_register; } - /* Warn after we've set the missing bits. */ - WARN_ONCE(bits_missing, "CR4 bits went missing: %lx!?\n", - bits_missing); + /* Warn after we've corrected the changed bits. */ + WARN_ONCE(bits_changed, "pinned CR4 bits changed: 0x%lx!?\n", + bits_changed); } } #if IS_MODULE(CONFIG_LKDTM) @@ -419,7 +422,7 @@ void cr4_init(void) if (boot_cpu_has(X86_FEATURE_PCID)) cr4 |= X86_CR4_PCIDE; if (static_branch_likely(&cr_pinning)) - cr4 |= cr4_pinned_bits; + cr4 = (cr4 & ~cr4_pinned_mask) | cr4_pinned_bits; __write_cr4(cr4); @@ -434,10 +437,7 @@ void cr4_init(void) */ static void __init setup_cr_pinning(void) { - unsigned long mask; - - mask = (X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_UMIP); - cr4_pinned_bits = this_cpu_read(cpu_tlbstate.cr4) & mask; + cr4_pinned_bits = this_cpu_read(cpu_tlbstate.cr4) & cr4_pinned_mask; static_key_enable(&cr_pinning.key); } diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index fb538fccd24c..9d033693519a 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -81,8 +81,4 @@ extern void update_srbds_msr(void); extern u64 x86_read_arch_cap_msr(void); -#ifdef CONFIG_IA32_FEAT_CTL -void init_ia32_feat_ctl(struct cpuinfo_x86 *c); -#endif - #endif /* ARCH_X86_CPU_H */ diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index c25a67a34bd3..0ab48f1cdf84 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -50,6 +50,13 @@ static enum split_lock_detect_state sld_state __ro_after_init = sld_off; static u64 msr_test_ctrl_cache __ro_after_init; /* + * With a name like MSR_TEST_CTL it should go without saying, but don't touch + * MSR_TEST_CTL unless the CPU is one of the whitelisted models. Writing it + * on CPUs that do not support SLD can cause fireworks, even when writing '0'. + */ +static bool cpu_model_supports_sld __ro_after_init; + +/* * Processors which have self-snooping capability can handle conflicting * memory type across CPUs by snooping its own cache. However, there exists * CPU models in which having conflicting memory types still leads to @@ -1071,7 +1078,8 @@ static void sld_update_msr(bool on) static void split_lock_init(void) { - split_lock_verify_msr(sld_state != sld_off); + if (cpu_model_supports_sld) + split_lock_verify_msr(sld_state != sld_off); } static void split_lock_warn(unsigned long ip) @@ -1177,5 +1185,6 @@ void __init cpu_set_core_cap_bits(struct cpuinfo_x86 *c) return; } + cpu_model_supports_sld = true; split_lock_setup(); } diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index ce9120c4f740..14e4b4d17ee5 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -1083,7 +1083,7 @@ static noinstr bool mce_check_crashing_cpu(void) { unsigned int cpu = smp_processor_id(); - if (cpu_is_offline(cpu) || + if (arch_cpu_is_offline(cpu) || (crashing_cpu != -1 && crashing_cpu != cpu)) { u64 mcgstatus; @@ -1901,6 +1901,8 @@ void (*machine_check_vector)(struct pt_regs *) = unexpected_machine_check; static __always_inline void exc_machine_check_kernel(struct pt_regs *regs) { + WARN_ON_ONCE(user_mode(regs)); + /* * Only required when from kernel mode. See * mce_check_crashing_cpu() for details. @@ -1954,7 +1956,7 @@ DEFINE_IDTENTRY_MCE_USER(exc_machine_check) } #else /* 32bit unified entry point */ -DEFINE_IDTENTRY_MCE(exc_machine_check) +DEFINE_IDTENTRY_RAW(exc_machine_check) { unsigned long dr7; diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 12f967c6b603..6a9df71c1b9e 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -981,10 +981,10 @@ void resctrl_cpu_detect(struct cpuinfo_x86 *c) c->x86_cache_max_rmid = ecx; c->x86_cache_occ_scale = ebx; - if (c->x86_vendor == X86_VENDOR_INTEL) - c->x86_cache_mbm_width_offset = eax & 0xff; - else - c->x86_cache_mbm_width_offset = -1; + c->x86_cache_mbm_width_offset = eax & 0xff; + + if (c->x86_vendor == X86_VENDOR_AMD && !c->x86_cache_mbm_width_offset) + c->x86_cache_mbm_width_offset = MBM_CNTR_WIDTH_OFFSET_AMD; } } diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index f20a47d120b1..5ffa32256b3b 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -37,6 +37,7 @@ #define MBA_IS_LINEAR 0x4 #define MBA_MAX_MBPS U32_MAX #define MAX_MBA_BW_AMD 0x800 +#define MBM_CNTR_WIDTH_OFFSET_AMD 20 #define RMID_VAL_ERROR BIT_ULL(63) #define RMID_VAL_UNAVAIL BIT_ULL(62) diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 23b4b61319d3..3f844f14fc0a 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -1117,6 +1117,7 @@ static int rdt_cdp_peer_get(struct rdt_resource *r, struct rdt_domain *d, _d_cdp = rdt_find_domain(_r_cdp, d->id, NULL); if (WARN_ON(IS_ERR_OR_NULL(_d_cdp))) { _r_cdp = NULL; + _d_cdp = NULL; ret = -EINVAL; } diff --git a/arch/x86/kernel/cpu/umwait.c b/arch/x86/kernel/cpu/umwait.c index 300e3fd5ade3..ec8064c0ae03 100644 --- a/arch/x86/kernel/cpu/umwait.c +++ b/arch/x86/kernel/cpu/umwait.c @@ -18,12 +18,6 @@ */ static u32 umwait_control_cached = UMWAIT_CTRL_VAL(100000, UMWAIT_C02_ENABLE); -u32 get_umwait_control_msr(void) -{ - return umwait_control_cached; -} -EXPORT_SYMBOL_GPL(get_umwait_control_msr); - /* * Cache the original IA32_UMWAIT_CONTROL MSR value which is configured by * hardware or BIOS before kernel boot. diff --git a/arch/x86/kernel/cpu/zhaoxin.c b/arch/x86/kernel/cpu/zhaoxin.c index df1358ba622b..05fa4ef63490 100644 --- a/arch/x86/kernel/cpu/zhaoxin.c +++ b/arch/x86/kernel/cpu/zhaoxin.c @@ -2,6 +2,7 @@ #include <linux/sched.h> #include <linux/sched/clock.h> +#include <asm/cpu.h> #include <asm/cpufeature.h> #include "cpu.h" diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 456511b2284e..7401cc12c3cc 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -71,6 +71,22 @@ static void printk_stack_address(unsigned long address, int reliable, printk("%s %s%pB\n", log_lvl, reliable ? "" : "? ", (void *)address); } +static int copy_code(struct pt_regs *regs, u8 *buf, unsigned long src, + unsigned int nbytes) +{ + if (!user_mode(regs)) + return copy_from_kernel_nofault(buf, (u8 *)src, nbytes); + + /* + * Make sure userspace isn't trying to trick us into dumping kernel + * memory by pointing the userspace instruction pointer at it. + */ + if (__chk_range_not_ok(src, nbytes, TASK_SIZE_MAX)) + return -EINVAL; + + return copy_from_user_nmi(buf, (void __user *)src, nbytes); +} + /* * There are a couple of reasons for the 2/3rd prologue, courtesy of Linus: * @@ -97,17 +113,8 @@ void show_opcodes(struct pt_regs *regs, const char *loglvl) #define OPCODE_BUFSIZE (PROLOGUE_SIZE + 1 + EPILOGUE_SIZE) u8 opcodes[OPCODE_BUFSIZE]; unsigned long prologue = regs->ip - PROLOGUE_SIZE; - bool bad_ip; - - /* - * Make sure userspace isn't trying to trick us into dumping kernel - * memory by pointing the userspace instruction pointer at it. - */ - bad_ip = user_mode(regs) && - __chk_range_not_ok(prologue, OPCODE_BUFSIZE, TASK_SIZE_MAX); - if (bad_ip || probe_kernel_read(opcodes, (u8 *)prologue, - OPCODE_BUFSIZE)) { + if (copy_code(regs, opcodes, prologue, sizeof(opcodes))) { printk("%sCode: Bad RIP value.\n", loglvl); } else { printk("%sCode: %" __stringify(PROLOGUE_SIZE) "ph <%02x> %" diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 06c818967bb6..15247b96c6ea 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -101,6 +101,12 @@ void kernel_fpu_begin(void) copy_fpregs_to_fpstate(¤t->thread.fpu); } __cpu_invalidate_fpregs_state(); + + if (boot_cpu_has(X86_FEATURE_XMM)) + ldmxcsr(MXCSR_DEFAULT); + + if (boot_cpu_has(X86_FEATURE_FPU)) + asm volatile ("fninit"); } EXPORT_SYMBOL_GPL(kernel_fpu_begin); diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index bda2e5eaca0e..ad3a2b37927d 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -1074,7 +1074,7 @@ int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int of copy_part(offsetof(struct fxregs_state, st_space), 128, &xsave->i387.st_space, &kbuf, &offset_start, &count); if (header.xfeatures & XFEATURE_MASK_SSE) - copy_part(xstate_offsets[XFEATURE_MASK_SSE], 256, + copy_part(xstate_offsets[XFEATURE_SSE], 256, &xsave->i387.xmm_space, &kbuf, &offset_start, &count); /* * Fill xsave->i387.sw_reserved value for ptrace frame: diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index c84d28e90a58..51504566b3a6 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -86,7 +86,7 @@ static int ftrace_verify_code(unsigned long ip, const char *old_code) * sure what we read is what we expected it to be before modifying it. */ /* read the text we want to modify */ - if (probe_kernel_read(cur_code, (void *)ip, MCOUNT_INSN_SIZE)) { + if (copy_from_kernel_nofault(cur_code, (void *)ip, MCOUNT_INSN_SIZE)) { WARN_ON(1); return -EFAULT; } @@ -355,7 +355,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) npages = DIV_ROUND_UP(*tramp_size, PAGE_SIZE); /* Copy ftrace_caller onto the trampoline memory */ - ret = probe_kernel_read(trampoline, (void *)start_offset, size); + ret = copy_from_kernel_nofault(trampoline, (void *)start_offset, size); if (WARN_ON(ret < 0)) goto fail; @@ -363,13 +363,13 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) /* The trampoline ends with ret(q) */ retq = (unsigned long)ftrace_stub; - ret = probe_kernel_read(ip, (void *)retq, RET_SIZE); + ret = copy_from_kernel_nofault(ip, (void *)retq, RET_SIZE); if (WARN_ON(ret < 0)) goto fail; if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) { ip = trampoline + (ftrace_regs_caller_ret - ftrace_regs_caller); - ret = probe_kernel_read(ip, (void *)retq, RET_SIZE); + ret = copy_from_kernel_nofault(ip, (void *)retq, RET_SIZE); if (WARN_ON(ret < 0)) goto fail; } @@ -506,7 +506,7 @@ static void *addr_from_call(void *ptr) union text_poke_insn call; int ret; - ret = probe_kernel_read(&call, ptr, CALL_INSN_SIZE); + ret = copy_from_kernel_nofault(&call, ptr, CALL_INSN_SIZE); if (WARN_ON_ONCE(ret < 0)) return NULL; diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index c44fe7d8d9a4..68acd30c6b87 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -732,11 +732,11 @@ int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt) int err; bpt->type = BP_BREAKPOINT; - err = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr, + err = copy_from_kernel_nofault(bpt->saved_instr, (char *)bpt->bpt_addr, BREAK_INSTR_SIZE); if (err) return err; - err = probe_kernel_write((char *)bpt->bpt_addr, + err = copy_to_kernel_nofault((char *)bpt->bpt_addr, arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE); if (!err) return err; @@ -768,7 +768,7 @@ int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt) return 0; knl_write: - return probe_kernel_write((char *)bpt->bpt_addr, + return copy_to_kernel_nofault((char *)bpt->bpt_addr, (char *)bpt->saved_instr, BREAK_INSTR_SIZE); } diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 3bafe1bd4dc7..ada39ddbc922 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -243,7 +243,7 @@ __recover_probed_insn(kprobe_opcode_t *buf, unsigned long addr) * Fortunately, we know that the original code is the ideal 5-byte * long NOP. */ - if (probe_kernel_read(buf, (void *)addr, + if (copy_from_kernel_nofault(buf, (void *)addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t))) return 0UL; @@ -346,7 +346,8 @@ int __copy_instruction(u8 *dest, u8 *src, u8 *real, struct insn *insn) return 0; /* This can access kernel text if given address is not recovered */ - if (probe_kernel_read(dest, (void *)recovered_insn, MAX_INSN_SIZE)) + if (copy_from_kernel_nofault(dest, (void *)recovered_insn, + MAX_INSN_SIZE)) return 0; kernel_insn_init(insn, dest, MAX_INSN_SIZE); @@ -753,16 +754,11 @@ asm( NOKPROBE_SYMBOL(kretprobe_trampoline); STACK_FRAME_NON_STANDARD(kretprobe_trampoline); -static struct kprobe kretprobe_kprobe = { - .addr = (void *)kretprobe_trampoline, -}; - /* * Called from kretprobe_trampoline */ __used __visible void *trampoline_handler(struct pt_regs *regs) { - struct kprobe_ctlblk *kcb; struct kretprobe_instance *ri = NULL; struct hlist_head *head, empty_rp; struct hlist_node *tmp; @@ -772,16 +768,12 @@ __used __visible void *trampoline_handler(struct pt_regs *regs) void *frame_pointer; bool skipped = false; - preempt_disable(); - /* * Set a dummy kprobe for avoiding kretprobe recursion. * Since kretprobe never run in kprobe handler, kprobe must not * be running at this point. */ - kcb = get_kprobe_ctlblk(); - __this_cpu_write(current_kprobe, &kretprobe_kprobe); - kcb->kprobe_status = KPROBE_HIT_ACTIVE; + kprobe_busy_begin(); INIT_HLIST_HEAD(&empty_rp); kretprobe_hash_lock(current, &head, &flags); @@ -857,7 +849,7 @@ __used __visible void *trampoline_handler(struct pt_regs *regs) __this_cpu_write(current_kprobe, &ri->rp->kp); ri->ret_addr = correct_ret_addr; ri->rp->handler(ri, regs); - __this_cpu_write(current_kprobe, &kretprobe_kprobe); + __this_cpu_write(current_kprobe, &kprobe_busy); } recycle_rp_inst(ri, &empty_rp); @@ -873,8 +865,7 @@ __used __visible void *trampoline_handler(struct pt_regs *regs) kretprobe_hash_unlock(current, &flags); - __this_cpu_write(current_kprobe, NULL); - preempt_enable(); + kprobe_busy_end(); hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 321c19950285..7af4c61dde52 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -56,7 +56,7 @@ found: * overwritten by jump destination address. In this case, original * bytes must be recovered from op->optinsn.copied_insn buffer. */ - if (probe_kernel_read(buf, (void *)addr, + if (copy_from_kernel_nofault(buf, (void *)addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t))) return 0UL; diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index 8748321c4486..b8aee71840ae 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -29,6 +29,8 @@ #include <asm/mmu_context.h> #include <asm/pgtable_areas.h> +#include <xen/xen.h> + /* This is a multiple of PAGE_SIZE. */ #define LDT_SLOT_STRIDE (LDT_ENTRIES * LDT_ENTRY_SIZE) @@ -543,6 +545,28 @@ static int read_default_ldt(void __user *ptr, unsigned long bytecount) return bytecount; } +static bool allow_16bit_segments(void) +{ + if (!IS_ENABLED(CONFIG_X86_16BIT)) + return false; + +#ifdef CONFIG_XEN_PV + /* + * Xen PV does not implement ESPFIX64, which means that 16-bit + * segments will not work correctly. Until either Xen PV implements + * ESPFIX64 and can signal this fact to the guest or unless someone + * provides compelling evidence that allowing broken 16-bit segments + * is worthwhile, disallow 16-bit segments under Xen PV. + */ + if (xen_pv_domain()) { + pr_info_once("Warning: 16-bit segments do not work correctly in a Xen PV guest\n"); + return false; + } +#endif + + return true; +} + static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) { struct mm_struct *mm = current->mm; @@ -574,7 +598,7 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) /* The user wants to clear the entry. */ memset(&ldt, 0, sizeof(ldt)); } else { - if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) { + if (!ldt_info.seg_32bit && !allow_16bit_segments()) { error = -EINVAL; goto out; } diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 2de365f15684..d7c5e44b26f7 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -478,7 +478,7 @@ static DEFINE_PER_CPU(unsigned long, nmi_dr7); DEFINE_IDTENTRY_RAW(exc_nmi) { - if (IS_ENABLED(CONFIG_SMP) && cpu_is_offline(smp_processor_id())) + if (IS_ENABLED(CONFIG_SMP) && arch_cpu_is_offline(smp_processor_id())) return; if (this_cpu_read(nmi_state) != NMI_NOT_RUNNING) { diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 674a7d66d960..de2138ba38e5 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -324,7 +324,8 @@ struct paravirt_patch_template pv_ops = { .cpu.swapgs = native_swapgs, #ifdef CONFIG_X86_IOPL_IOPERM - .cpu.update_io_bitmap = native_tss_update_io_bitmap, + .cpu.invalidate_io_bitmap = native_tss_invalidate_io_bitmap, + .cpu.update_io_bitmap = native_tss_update_io_bitmap, #endif .cpu.start_context_switch = paravirt_nop, diff --git a/arch/x86/kernel/probe_roms.c b/arch/x86/kernel/probe_roms.c index ee0286390a4c..9e1def3744f2 100644 --- a/arch/x86/kernel/probe_roms.c +++ b/arch/x86/kernel/probe_roms.c @@ -94,12 +94,12 @@ static bool match_id(struct pci_dev *pdev, unsigned short vendor, unsigned short } static bool probe_list(struct pci_dev *pdev, unsigned short vendor, - const unsigned char *rom_list) + const void *rom_list) { unsigned short device; do { - if (probe_kernel_address(rom_list, device) != 0) + if (get_kernel_nofault(device, rom_list) != 0) device = 0; if (device && match_id(pdev, vendor, device)) @@ -119,19 +119,19 @@ static struct resource *find_oprom(struct pci_dev *pdev) for (i = 0; i < ARRAY_SIZE(adapter_rom_resources); i++) { struct resource *res = &adapter_rom_resources[i]; unsigned short offset, vendor, device, list, rev; - const unsigned char *rom; + const void *rom; if (res->end == 0) break; rom = isa_bus_to_virt(res->start); - if (probe_kernel_address(rom + 0x18, offset) != 0) + if (get_kernel_nofault(offset, rom + 0x18) != 0) continue; - if (probe_kernel_address(rom + offset + 0x4, vendor) != 0) + if (get_kernel_nofault(vendor, rom + offset + 0x4) != 0) continue; - if (probe_kernel_address(rom + offset + 0x6, device) != 0) + if (get_kernel_nofault(device, rom + offset + 0x6) != 0) continue; if (match_id(pdev, vendor, device)) { @@ -139,8 +139,8 @@ static struct resource *find_oprom(struct pci_dev *pdev) break; } - if (probe_kernel_address(rom + offset + 0x8, list) == 0 && - probe_kernel_address(rom + offset + 0xc, rev) == 0 && + if (get_kernel_nofault(list, rom + offset + 0x8) == 0 && + get_kernel_nofault(rev, rom + offset + 0xc) == 0 && rev >= 3 && list && probe_list(pdev, vendor, rom + offset + list)) { oprom = res; @@ -183,14 +183,14 @@ static int __init romsignature(const unsigned char *rom) const unsigned short * const ptr = (const unsigned short *)rom; unsigned short sig; - return probe_kernel_address(ptr, sig) == 0 && sig == ROMSIGNATURE; + return get_kernel_nofault(sig, ptr) == 0 && sig == ROMSIGNATURE; } static int __init romchecksum(const unsigned char *rom, unsigned long length) { unsigned char sum, c; - for (sum = 0; length && probe_kernel_address(rom++, c) == 0; length--) + for (sum = 0; length && get_kernel_nofault(c, rom++) == 0; length--) sum += c; return !length && !sum; } @@ -211,7 +211,7 @@ void __init probe_roms(void) video_rom_resource.start = start; - if (probe_kernel_address(rom + 2, c) != 0) + if (get_kernel_nofault(c, rom + 2) != 0) continue; /* 0 < length <= 0x7f * 512, historically */ @@ -249,7 +249,7 @@ void __init probe_roms(void) if (!romsignature(rom)) continue; - if (probe_kernel_address(rom + 2, c) != 0) + if (get_kernel_nofault(c, rom + 2) != 0) continue; /* 0 < length <= 0x7f * 512, historically */ diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index f362ce0d5ac0..fe67dbd76e51 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -322,20 +322,6 @@ void arch_setup_new_exec(void) } #ifdef CONFIG_X86_IOPL_IOPERM -static inline void tss_invalidate_io_bitmap(struct tss_struct *tss) -{ - /* - * Invalidate the I/O bitmap by moving io_bitmap_base outside the - * TSS limit so any subsequent I/O access from user space will - * trigger a #GP. - * - * This is correct even when VMEXIT rewrites the TSS limit - * to 0x67 as the only requirement is that the base points - * outside the limit. - */ - tss->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET_INVALID; -} - static inline void switch_to_bitmap(unsigned long tifp) { /* @@ -346,7 +332,7 @@ static inline void switch_to_bitmap(unsigned long tifp) * user mode. */ if (tifp & _TIF_IO_BITMAP) - tss_invalidate_io_bitmap(this_cpu_ptr(&cpu_tss_rw)); + tss_invalidate_io_bitmap(); } static void tss_copy_io_bitmap(struct tss_struct *tss, struct io_bitmap *iobm) @@ -380,7 +366,7 @@ void native_tss_update_io_bitmap(void) u16 *base = &tss->x86_tss.io_bitmap_base; if (!test_thread_flag(TIF_IO_BITMAP)) { - tss_invalidate_io_bitmap(tss); + native_tss_invalidate_io_bitmap(); return; } diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index 6ad43fc44556..2fd698e28e4d 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -58,7 +58,6 @@ int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry, * or a page fault), which can make frame pointers * unreliable. */ - if (IS_ENABLED(CONFIG_FRAME_POINTER)) return -EINVAL; } @@ -81,10 +80,6 @@ int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry, if (unwind_error(&state)) return -EINVAL; - /* Success path for non-user tasks, i.e. kthreads and idle tasks */ - if (!(task->flags & (PF_KTHREAD | PF_IDLE))) - return -EINVAL; - return 0; } diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index af75109485c2..b7cb3e0716f7 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -84,17 +84,16 @@ static inline void cond_local_irq_disable(struct pt_regs *regs) local_irq_disable(); } -int is_valid_bugaddr(unsigned long addr) +__always_inline int is_valid_bugaddr(unsigned long addr) { - unsigned short ud; - if (addr < TASK_SIZE_MAX) return 0; - if (probe_kernel_address((unsigned short *)addr, ud)) - return 0; - - return ud == INSN_UD0 || ud == INSN_UD2; + /* + * We got #UD, if the text isn't readable we'd have gotten + * a different exception. + */ + return *(unsigned short *)addr == INSN_UD2; } static nokprobe_inline int @@ -216,40 +215,45 @@ static inline void handle_invalid_op(struct pt_regs *regs) ILL_ILLOPN, error_get_trap_addr(regs)); } -DEFINE_IDTENTRY_RAW(exc_invalid_op) +static noinstr bool handle_bug(struct pt_regs *regs) { - bool rcu_exit; + bool handled = false; + + if (!is_valid_bugaddr(regs->ip)) + return handled; /* - * Handle BUG/WARN like NMIs instead of like normal idtentries: - * if we bugged/warned in a bad RCU context, for example, the last - * thing we want is to BUG/WARN again in the idtentry code, ad - * infinitum. + * All lies, just get the WARN/BUG out. + */ + instrumentation_begin(); + /* + * Since we're emulating a CALL with exceptions, restore the interrupt + * state to what it was at the exception site. */ - if (!user_mode(regs) && is_valid_bugaddr(regs->ip)) { - enum bug_trap_type type; + if (regs->flags & X86_EFLAGS_IF) + raw_local_irq_enable(); + if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN) { + regs->ip += LEN_UD2; + handled = true; + } + if (regs->flags & X86_EFLAGS_IF) + raw_local_irq_disable(); + instrumentation_end(); - nmi_enter(); - instrumentation_begin(); - trace_hardirqs_off_finish(); - type = report_bug(regs->ip, regs); - if (regs->flags & X86_EFLAGS_IF) - trace_hardirqs_on_prepare(); - instrumentation_end(); - nmi_exit(); + return handled; +} - if (type == BUG_TRAP_TYPE_WARN) { - /* Skip the ud2. */ - regs->ip += LEN_UD2; - return; - } +DEFINE_IDTENTRY_RAW(exc_invalid_op) +{ + bool rcu_exit; - /* - * Else, if this was a BUG and report_bug returns or if this - * was just a normal #UD, we want to continue onward and - * crash. - */ - } + /* + * We use UD2 as a short encoding for 'CALL __WARN', as such + * handle it before exception entry to avoid recursive WARN + * in case exception entry is the one triggering WARNs. + */ + if (!user_mode(regs) && handle_bug(regs)) + return; rcu_exit = idtentry_enter_cond_rcu(regs); instrumentation_begin(); @@ -299,6 +303,8 @@ DEFINE_IDTENTRY_ERRORCODE(exc_alignment_check) do_trap(X86_TRAP_AC, SIGBUS, "alignment check", regs, error_code, BUS_ADRALN, NULL); + + local_irq_disable(); } #ifdef CONFIG_VMAP_STACK @@ -488,7 +494,8 @@ static enum kernel_gp_hint get_kernel_gp_address(struct pt_regs *regs, u8 insn_buf[MAX_INSN_SIZE]; struct insn insn; - if (probe_kernel_read(insn_buf, (void *)regs->ip, MAX_INSN_SIZE)) + if (copy_from_kernel_nofault(insn_buf, (void *)regs->ip, + MAX_INSN_SIZE)) return GP_NO_HINT; kernel_insn_init(&insn, insn_buf, MAX_INSN_SIZE); @@ -690,13 +697,13 @@ struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s) (struct bad_iret_stack *)__this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1; /* Copy the IRET target to the temporary storage. */ - memcpy(&tmp.regs.ip, (void *)s->regs.sp, 5*8); + __memcpy(&tmp.regs.ip, (void *)s->regs.sp, 5*8); /* Copy the remainder of the stack from the current stack. */ - memcpy(&tmp, s, offsetof(struct bad_iret_stack, regs.ip)); + __memcpy(&tmp, s, offsetof(struct bad_iret_stack, regs.ip)); /* Update the entry stack */ - memcpy(new_stack, &tmp, sizeof(tmp)); + __memcpy(new_stack, &tmp, sizeof(tmp)); BUG_ON(!user_mode(&new_stack->regs)); return new_stack; @@ -865,6 +872,12 @@ static __always_inline void exc_debug_kernel(struct pt_regs *regs, trace_hardirqs_off_finish(); /* + * If something gets miswired and we end up here for a user mode + * #DB, we will malfunction. + */ + WARN_ON_ONCE(user_mode(regs)); + + /* * Catch SYSENTER with TF set and clear DR_STEP. If this hit a * watchpoint at the same time then that will still be handled. */ @@ -882,6 +895,12 @@ static __always_inline void exc_debug_kernel(struct pt_regs *regs, static __always_inline void exc_debug_user(struct pt_regs *regs, unsigned long dr6) { + /* + * If something gets miswired and we end up here for a kernel mode + * #DB, we will malfunction. + */ + WARN_ON_ONCE(!user_mode(regs)); + idtentry_enter_user(regs); instrumentation_begin(); @@ -912,7 +931,7 @@ DEFINE_IDTENTRY_DEBUG_USER(exc_debug) } #else /* 32 bit does not have separate entry points. */ -DEFINE_IDTENTRY_DEBUG(exc_debug) +DEFINE_IDTENTRY_RAW(exc_debug) { unsigned long dr6, dr7; diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index 7f969b2d240f..ec88bbe08a32 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -440,8 +440,11 @@ bool unwind_next_frame(struct unwind_state *state) /* * Find the orc_entry associated with the text address. * - * Decrement call return addresses by one so they work for sibling - * calls and calls to noreturn functions. + * For a call frame (as opposed to a signal frame), state->ip points to + * the instruction after the call. That instruction's stack layout + * could be different from the call instruction's layout, for example + * if the call was to a noreturn function. So get the ORC data for the + * call instruction itself. */ orc = orc_find(state->signal ? state->ip : state->ip - 1); if (!orc) { @@ -662,6 +665,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, state->sp = task->thread.sp; state->bp = READ_ONCE_NOCHECK(frame->bp); state->ip = READ_ONCE_NOCHECK(frame->ret_addr); + state->signal = (void *)state->ip == ret_from_fork; } if (get_stack_info((unsigned long *)state->sp, state->task, diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 3bfc8dd8a43d..9a03e5b23135 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -358,6 +358,7 @@ SECTIONS .bss : AT(ADDR(.bss) - LOAD_OFFSET) { __bss_start = .; *(.bss..page_aligned) + . = ALIGN(PAGE_SIZE); *(BSS_MAIN) BSS_DECRYPTED . = ALIGN(PAGE_SIZE); diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index ff2d0e9ca3bc..cfe83d4ae625 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -7,7 +7,7 @@ #define KVM_POSSIBLE_CR0_GUEST_BITS X86_CR0_TS #define KVM_POSSIBLE_CR4_GUEST_BITS \ (X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR \ - | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_PGE) + | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_PGE | X86_CR4_TSD) #define BUILD_KVM_GPR_ACCESSORS(lname, uname) \ static __always_inline unsigned long kvm_##lname##_read(struct kvm_vcpu *vcpu)\ diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 34a7e0533dad..5bf72fc86a8e 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -169,6 +169,18 @@ static void kvm_apic_map_free(struct rcu_head *rcu) kvfree(map); } +/* + * CLEAN -> DIRTY and UPDATE_IN_PROGRESS -> DIRTY changes happen without a lock. + * + * DIRTY -> UPDATE_IN_PROGRESS and UPDATE_IN_PROGRESS -> CLEAN happen with + * apic_map_lock_held. + */ +enum { + CLEAN, + UPDATE_IN_PROGRESS, + DIRTY +}; + void kvm_recalculate_apic_map(struct kvm *kvm) { struct kvm_apic_map *new, *old = NULL; @@ -176,17 +188,17 @@ void kvm_recalculate_apic_map(struct kvm *kvm) int i; u32 max_id = 255; /* enough space for any xAPIC ID */ - if (!kvm->arch.apic_map_dirty) { - /* - * Read kvm->arch.apic_map_dirty before - * kvm->arch.apic_map - */ - smp_rmb(); + /* Read kvm->arch.apic_map_dirty before kvm->arch.apic_map. */ + if (atomic_read_acquire(&kvm->arch.apic_map_dirty) == CLEAN) return; - } mutex_lock(&kvm->arch.apic_map_lock); - if (!kvm->arch.apic_map_dirty) { + /* + * Read kvm->arch.apic_map_dirty before kvm->arch.apic_map + * (if clean) or the APIC registers (if dirty). + */ + if (atomic_cmpxchg_acquire(&kvm->arch.apic_map_dirty, + DIRTY, UPDATE_IN_PROGRESS) == CLEAN) { /* Someone else has updated the map. */ mutex_unlock(&kvm->arch.apic_map_lock); return; @@ -256,11 +268,11 @@ out: lockdep_is_held(&kvm->arch.apic_map_lock)); rcu_assign_pointer(kvm->arch.apic_map, new); /* - * Write kvm->arch.apic_map before - * clearing apic->apic_map_dirty + * Write kvm->arch.apic_map before clearing apic->apic_map_dirty. + * If another update has come in, leave it DIRTY. */ - smp_wmb(); - kvm->arch.apic_map_dirty = false; + atomic_cmpxchg_release(&kvm->arch.apic_map_dirty, + UPDATE_IN_PROGRESS, CLEAN); mutex_unlock(&kvm->arch.apic_map_lock); if (old) @@ -282,20 +294,20 @@ static inline void apic_set_spiv(struct kvm_lapic *apic, u32 val) else static_key_slow_inc(&apic_sw_disabled.key); - apic->vcpu->kvm->arch.apic_map_dirty = true; + atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); } } static inline void kvm_apic_set_xapic_id(struct kvm_lapic *apic, u8 id) { kvm_lapic_set_reg(apic, APIC_ID, id << 24); - apic->vcpu->kvm->arch.apic_map_dirty = true; + atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); } static inline void kvm_apic_set_ldr(struct kvm_lapic *apic, u32 id) { kvm_lapic_set_reg(apic, APIC_LDR, id); - apic->vcpu->kvm->arch.apic_map_dirty = true; + atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); } static inline u32 kvm_apic_calc_x2apic_ldr(u32 id) @@ -311,7 +323,7 @@ static inline void kvm_apic_set_x2apic_id(struct kvm_lapic *apic, u32 id) kvm_lapic_set_reg(apic, APIC_ID, id); kvm_lapic_set_reg(apic, APIC_LDR, ldr); - apic->vcpu->kvm->arch.apic_map_dirty = true; + atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); } static inline int apic_lvt_enabled(struct kvm_lapic *apic, int lvt_type) @@ -1976,7 +1988,7 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) case APIC_DFR: if (!apic_x2apic_mode(apic)) { kvm_lapic_set_reg(apic, APIC_DFR, val | 0x0FFFFFFF); - apic->vcpu->kvm->arch.apic_map_dirty = true; + atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); } else ret = 1; break; @@ -2232,7 +2244,7 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) static_key_slow_dec_deferred(&apic_hw_disabled); } else { static_key_slow_inc(&apic_hw_disabled.key); - vcpu->kvm->arch.apic_map_dirty = true; + atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); } } @@ -2273,7 +2285,6 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) if (!apic) return; - vcpu->kvm->arch.apic_map_dirty = false; /* Stop the timer in case it's a reset to an active apic */ hrtimer_cancel(&apic->lapic_timer.timer); @@ -2567,6 +2578,7 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) } memcpy(vcpu->arch.apic->regs, s->regs, sizeof(*s)); + atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); kvm_recalculate_apic_map(vcpu->kvm); kvm_apic_set_version(vcpu); diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 0ad06bfe2c2c..444bb9c54548 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -222,7 +222,7 @@ void kvm_mmu_gfn_disallow_lpage(struct kvm_memory_slot *slot, gfn_t gfn); void kvm_mmu_gfn_allow_lpage(struct kvm_memory_slot *slot, gfn_t gfn); bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm, struct kvm_memory_slot *slot, u64 gfn); -int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu); +int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu, gpa_t l2_gpa); int kvm_mmu_post_init_vm(struct kvm *kvm); void kvm_mmu_pre_destroy_vm(struct kvm *kvm); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index fdd05c233308..6d6a0ae7800c 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -1745,10 +1745,10 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, * Emulate arch specific page modification logging for the * nested hypervisor */ -int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu) +int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu, gpa_t l2_gpa) { if (kvm_x86_ops.write_log_dirty) - return kvm_x86_ops.write_log_dirty(vcpu); + return kvm_x86_ops.write_log_dirty(vcpu, l2_gpa); return 0; } @@ -4449,7 +4449,7 @@ __reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, nonleaf_bit8_rsvd | rsvd_bits(7, 7) | rsvd_bits(maxphyaddr, 51); rsvd_check->rsvd_bits_mask[0][2] = exb_bit_rsvd | - nonleaf_bit8_rsvd | gbpages_bit_rsvd | + gbpages_bit_rsvd | rsvd_bits(maxphyaddr, 51); rsvd_check->rsvd_bits_mask[0][1] = exb_bit_rsvd | rsvd_bits(maxphyaddr, 51); diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index a6d484ea110b..bd70ece1ef8b 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -235,7 +235,7 @@ static inline unsigned FNAME(gpte_access)(u64 gpte) static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, struct guest_walker *walker, - int write_fault) + gpa_t addr, int write_fault) { unsigned level, index; pt_element_t pte, orig_pte; @@ -260,7 +260,7 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu, !(pte & PT_GUEST_DIRTY_MASK)) { trace_kvm_mmu_set_dirty_bit(table_gfn, index, sizeof(pte)); #if PTTYPE == PTTYPE_EPT - if (kvm_arch_write_log_dirty(vcpu)) + if (kvm_arch_write_log_dirty(vcpu, addr)) return -EINVAL; #endif pte |= PT_GUEST_DIRTY_MASK; @@ -360,7 +360,6 @@ retry_walk: ++walker->level; do { - gfn_t real_gfn; unsigned long host_addr; pt_access = pte_access; @@ -375,7 +374,7 @@ retry_walk: walker->table_gfn[walker->level - 1] = table_gfn; walker->pte_gpa[walker->level - 1] = pte_gpa; - real_gfn = mmu->translate_gpa(vcpu, gfn_to_gpa(table_gfn), + real_gpa = mmu->translate_gpa(vcpu, gfn_to_gpa(table_gfn), nested_access, &walker->fault); @@ -389,12 +388,10 @@ retry_walk: * information to fix the exit_qualification or exit_info_1 * fields. */ - if (unlikely(real_gfn == UNMAPPED_GVA)) + if (unlikely(real_gpa == UNMAPPED_GVA)) return 0; - real_gfn = gpa_to_gfn(real_gfn); - - host_addr = kvm_vcpu_gfn_to_hva_prot(vcpu, real_gfn, + host_addr = kvm_vcpu_gfn_to_hva_prot(vcpu, gpa_to_gfn(real_gpa), &walker->pte_writable[walker->level - 1]); if (unlikely(kvm_is_error_hva(host_addr))) goto error; @@ -457,7 +454,8 @@ retry_walk: (PT_GUEST_DIRTY_SHIFT - PT_GUEST_ACCESSED_SHIFT); if (unlikely(!accessed_dirty)) { - ret = FNAME(update_accessed_dirty_bits)(vcpu, mmu, walker, write_fault); + ret = FNAME(update_accessed_dirty_bits)(vcpu, mmu, walker, + addr, write_fault); if (unlikely(ret < 0)) goto error; else if (ret) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 8ccfa4197d9c..c0da4dd78ac5 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -3344,7 +3344,7 @@ static fastpath_t svm_exit_handlers_fastpath(struct kvm_vcpu *vcpu) void __svm_vcpu_run(unsigned long vmcb_pa, unsigned long *regs); -static fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) +static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) { fastpath_t exit_fastpath; struct vcpu_svm *svm = to_svm(vcpu); diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index d1af20b050a8..d4a4cec034d0 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -4109,7 +4109,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, * CR0_GUEST_HOST_MASK is already set in the original vmcs01 * (KVM doesn't change it); */ - vcpu->arch.cr0_guest_owned_bits = X86_CR0_TS; + vcpu->arch.cr0_guest_owned_bits = KVM_POSSIBLE_CR0_GUEST_BITS; vmx_set_cr0(vcpu, vmcs12->host_cr0); /* Same as above - no reason to call set_cr4_guest_host_mask(). */ @@ -4259,7 +4259,7 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu) */ vmx_set_efer(vcpu, nested_vmx_get_vmcs01_guest_efer(vmx)); - vcpu->arch.cr0_guest_owned_bits = X86_CR0_TS; + vcpu->arch.cr0_guest_owned_bits = KVM_POSSIBLE_CR0_GUEST_BITS; vmx_set_cr0(vcpu, vmcs_readl(CR0_READ_SHADOW)); vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK); @@ -6176,6 +6176,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, goto error_guest_mode; } + vmx->nested.has_preemption_timer_deadline = false; if (kvm_state->hdr.vmx.flags & KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE) { vmx->nested.has_preemption_timer_deadline = true; vmx->nested.preemption_timer_deadline = diff --git a/arch/x86/kvm/vmx/vmcs.h b/arch/x86/kvm/vmx/vmcs.h index 5c0ff80b85c0..7a3675fddec2 100644 --- a/arch/x86/kvm/vmx/vmcs.h +++ b/arch/x86/kvm/vmx/vmcs.h @@ -72,11 +72,24 @@ struct loaded_vmcs { struct vmcs_controls_shadow controls_shadow; }; +static inline bool is_intr_type(u32 intr_info, u32 type) +{ + const u32 mask = INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK; + + return (intr_info & mask) == (INTR_INFO_VALID_MASK | type); +} + +static inline bool is_intr_type_n(u32 intr_info, u32 type, u8 vector) +{ + const u32 mask = INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK | + INTR_INFO_VECTOR_MASK; + + return (intr_info & mask) == (INTR_INFO_VALID_MASK | type | vector); +} + static inline bool is_exception_n(u32 intr_info, u8 vector) { - return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK | - INTR_INFO_VALID_MASK)) == - (INTR_TYPE_HARD_EXCEPTION | vector | INTR_INFO_VALID_MASK); + return is_intr_type_n(intr_info, INTR_TYPE_HARD_EXCEPTION, vector); } static inline bool is_debug(u32 intr_info) @@ -106,28 +119,23 @@ static inline bool is_gp_fault(u32 intr_info) static inline bool is_machine_check(u32 intr_info) { - return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK | - INTR_INFO_VALID_MASK)) == - (INTR_TYPE_HARD_EXCEPTION | MC_VECTOR | INTR_INFO_VALID_MASK); + return is_exception_n(intr_info, MC_VECTOR); } /* Undocumented: icebp/int1 */ static inline bool is_icebp(u32 intr_info) { - return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK)) - == (INTR_TYPE_PRIV_SW_EXCEPTION | INTR_INFO_VALID_MASK); + return is_intr_type(intr_info, INTR_TYPE_PRIV_SW_EXCEPTION); } static inline bool is_nmi(u32 intr_info) { - return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK)) - == (INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK); + return is_intr_type(intr_info, INTR_TYPE_NMI_INTR); } static inline bool is_external_intr(u32 intr_info) { - return (intr_info & (INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK)) - == (INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR); + return is_intr_type(intr_info, INTR_TYPE_EXT_INTR); } enum vmcs_field_width { diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 36c771728c8c..13745f2a5ecd 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -133,9 +133,6 @@ module_param_named(preemption_timer, enable_preemption_timer, bool, S_IRUGO); #define KVM_VM_CR0_ALWAYS_ON \ (KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST | \ X86_CR0_WP | X86_CR0_PG | X86_CR0_PE) -#define KVM_CR4_GUEST_OWNED_BITS \ - (X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR \ - | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_TSD) #define KVM_VM_CR4_ALWAYS_ON_UNRESTRICTED_GUEST X86_CR4_VMXE #define KVM_PMODE_VM_CR4_ALWAYS_ON (X86_CR4_PAE | X86_CR4_VMXE) @@ -4034,9 +4031,9 @@ void vmx_set_constant_host_state(struct vcpu_vmx *vmx) void set_cr4_guest_host_mask(struct vcpu_vmx *vmx) { - vmx->vcpu.arch.cr4_guest_owned_bits = KVM_CR4_GUEST_OWNED_BITS; - if (enable_ept) - vmx->vcpu.arch.cr4_guest_owned_bits |= X86_CR4_PGE; + vmx->vcpu.arch.cr4_guest_owned_bits = KVM_POSSIBLE_CR4_GUEST_BITS; + if (!enable_ept) + vmx->vcpu.arch.cr4_guest_owned_bits &= ~X86_CR4_PGE; if (is_guest_mode(&vmx->vcpu)) vmx->vcpu.arch.cr4_guest_owned_bits &= ~get_vmcs12(&vmx->vcpu)->cr4_guest_host_mask; @@ -4333,8 +4330,8 @@ static void init_vmcs(struct vcpu_vmx *vmx) /* 22.2.1, 20.8.1 */ vm_entry_controls_set(vmx, vmx_vmentry_ctrl()); - vmx->vcpu.arch.cr0_guest_owned_bits = X86_CR0_TS; - vmcs_writel(CR0_GUEST_HOST_MASK, ~X86_CR0_TS); + vmx->vcpu.arch.cr0_guest_owned_bits = KVM_POSSIBLE_CR0_GUEST_BITS; + vmcs_writel(CR0_GUEST_HOST_MASK, ~vmx->vcpu.arch.cr0_guest_owned_bits); set_cr4_guest_host_mask(vmx); @@ -6606,23 +6603,6 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx) msrs[i].host, false); } -static void atomic_switch_umwait_control_msr(struct vcpu_vmx *vmx) -{ - u32 host_umwait_control; - - if (!vmx_has_waitpkg(vmx)) - return; - - host_umwait_control = get_umwait_control_msr(); - - if (vmx->msr_ia32_umwait_control != host_umwait_control) - add_atomic_switch_msr(vmx, MSR_IA32_UMWAIT_CONTROL, - vmx->msr_ia32_umwait_control, - host_umwait_control, false); - else - clear_atomic_switch_msr(vmx, MSR_IA32_UMWAIT_CONTROL); -} - static void vmx_update_hv_timer(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -6728,9 +6708,7 @@ reenter_guest: pt_guest_enter(vmx); - if (vcpu_to_pmu(vcpu)->version) - atomic_switch_perf_msrs(vmx); - atomic_switch_umwait_control_msr(vmx); + atomic_switch_perf_msrs(vmx); if (enable_preemption_timer) vmx_update_hv_timer(vcpu); @@ -7501,11 +7479,11 @@ static void vmx_flush_log_dirty(struct kvm *kvm) kvm_flush_pml_buffers(kvm); } -static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu) +static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu, gpa_t gpa) { struct vmcs12 *vmcs12; struct vcpu_vmx *vmx = to_vmx(vcpu); - gpa_t gpa, dst; + gpa_t dst; if (is_guest_mode(vcpu)) { WARN_ON_ONCE(vmx->nested.pml_full); @@ -7524,7 +7502,7 @@ static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu) return 1; } - gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS) & ~0xFFFull; + gpa &= ~0xFFFull; dst = vmcs12->pml_address + sizeof(u64) * vmcs12->guest_pml_index; if (kvm_write_guest_page(vcpu->kvm, gpa_to_gfn(dst), &gpa, diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 8a83b5edc820..639798e4a6ca 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -288,8 +288,6 @@ struct vcpu_vmx { u64 current_tsc_ratio; - u32 host_pkru; - unsigned long host_debugctlmsr; /* diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 00c88c2f34e4..88c593f83b28 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -975,6 +975,8 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) if (is_long_mode(vcpu)) { if (!(cr4 & X86_CR4_PAE)) return 1; + if ((cr4 ^ old_cr4) & X86_CR4_LA57) + return 1; } else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE) && ((cr4 ^ old_cr4) & pdptr_bits) && !load_pdptrs(vcpu, vcpu->arch.walk_mmu, @@ -2693,6 +2695,9 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data) if (data & 0x30) return 1; + if (!lapic_in_kernel(vcpu)) + return 1; + vcpu->arch.apf.msr_en_val = data; if (!kvm_pv_async_pf_enabled(vcpu)) { @@ -2856,7 +2861,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return kvm_mtrr_set_msr(vcpu, msr, data); case MSR_IA32_APICBASE: return kvm_set_apic_base(vcpu, msr_info); - case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff: + case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff: return kvm_x2apic_msr_write(vcpu, msr, data); case MSR_IA32_TSCDEADLINE: kvm_set_lapic_tscdeadline_msr(vcpu, data); @@ -3196,7 +3201,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_APICBASE: msr_info->data = kvm_get_apic_base(vcpu); break; - case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff: + case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff: return kvm_x2apic_msr_read(vcpu, msr_info->index, &msr_info->data); case MSR_IA32_TSCDEADLINE: msr_info->data = kvm_get_lapic_tscdeadline_msr(vcpu); @@ -4603,7 +4608,8 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = -EINVAL; user_tsc_khz = (u32)arg; - if (user_tsc_khz >= kvm_max_guest_tsc_khz) + if (kvm_has_tsc_control && + user_tsc_khz >= kvm_max_guest_tsc_khz) goto out; if (user_tsc_khz == 0) diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S index 56b243b14c3a..bbcc05bcefad 100644 --- a/arch/x86/lib/memcpy_64.S +++ b/arch/x86/lib/memcpy_64.S @@ -8,6 +8,8 @@ #include <asm/alternative-asm.h> #include <asm/export.h> +.pushsection .noinstr.text, "ax" + /* * We build a jump to memcpy_orig by default which gets NOPped out on * the majority of x86 CPUs which set REP_GOOD. In addition, CPUs which @@ -184,6 +186,8 @@ SYM_FUNC_START_LOCAL(memcpy_orig) retq SYM_FUNC_END(memcpy_orig) +.popsection + #ifndef CONFIG_UML MCSAFE_TEST_CTL diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c index fff28c6f73a2..b0dfac3d3df7 100644 --- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -24,6 +24,7 @@ unsigned long __clear_user(void __user *addr, unsigned long size) asm volatile( " testq %[size8],%[size8]\n" " jz 4f\n" + " .align 16\n" "0: movq $0,(%[dst])\n" " addq $8,%[dst]\n" " decl %%ecx ; jnz 0b\n" diff --git a/arch/x86/math-emu/wm_sqrt.S b/arch/x86/math-emu/wm_sqrt.S index 3b2b58164ec1..40526dd85137 100644 --- a/arch/x86/math-emu/wm_sqrt.S +++ b/arch/x86/math-emu/wm_sqrt.S @@ -209,7 +209,7 @@ sqrt_stage_2_finish: #ifdef PARANOID /* It should be possible to get here only if the arg is ffff....ffff */ - cmp $0xffffffff,FPU_fsqrt_arg_1 + cmpl $0xffffffff,FPU_fsqrt_arg_1 jnz sqrt_stage_2_error #endif /* PARANOID */ diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 66be9bd60307..1ead568c0101 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -99,7 +99,7 @@ check_prefetch_opcode(struct pt_regs *regs, unsigned char *instr, return !instr_lo || (instr_lo>>1) == 1; case 0x00: /* Prefetch instruction is 0x0F0D or 0x0F18 */ - if (probe_kernel_address(instr, opcode)) + if (get_kernel_nofault(opcode, instr)) return 0; *prefetch = (instr_lo == 0xF) && @@ -133,7 +133,7 @@ is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr) while (instr < max_instr) { unsigned char opcode; - if (probe_kernel_address(instr, opcode)) + if (get_kernel_nofault(opcode, instr)) break; instr++; @@ -301,7 +301,7 @@ static int bad_address(void *p) { unsigned long dummy; - return probe_kernel_address((unsigned long *)p, dummy); + return get_kernel_nofault(dummy, (unsigned long *)p); } static void dump_pagetable(unsigned long address) @@ -442,7 +442,7 @@ static void show_ldttss(const struct desc_ptr *gdt, const char *name, u16 index) return; } - if (probe_kernel_read(&desc, (void *)(gdt->address + offset), + if (copy_from_kernel_nofault(&desc, (void *)(gdt->address + offset), sizeof(struct ldttss_desc))) { pr_alert("%s: 0x%hx -- GDT entry is not readable\n", name, index); diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index bda909e3e37e..8b4afad84f4a 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -737,7 +737,7 @@ static void __init test_wp_bit(void) __set_fixmap(FIX_WP_TEST, __pa_symbol(empty_zero_page), PAGE_KERNEL_RO); - if (probe_kernel_write((char *)fix_to_virt(FIX_WP_TEST), &z, 1)) { + if (copy_to_kernel_nofault((char *)fix_to_virt(FIX_WP_TEST), &z, 1)) { clear_fixmap(FIX_WP_TEST); printk(KERN_CONT "Ok.\n"); return; diff --git a/arch/x86/mm/maccess.c b/arch/x86/mm/maccess.c index e1d7d7477c22..92ec176a7293 100644 --- a/arch/x86/mm/maccess.c +++ b/arch/x86/mm/maccess.c @@ -9,7 +9,7 @@ static __always_inline u64 canonical_address(u64 vaddr, u8 vaddr_bits) return ((s64)vaddr << (64 - vaddr_bits)) >> (64 - vaddr_bits); } -bool probe_kernel_read_allowed(const void *unsafe_src, size_t size) +bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size) { unsigned long vaddr = (unsigned long)unsafe_src; @@ -22,7 +22,7 @@ bool probe_kernel_read_allowed(const void *unsafe_src, size_t size) canonical_address(vaddr, boot_cpu_data.x86_virt_bits) == vaddr; } #else -bool probe_kernel_read_allowed(const void *unsafe_src, size_t size) +bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size) { return (unsigned long)unsafe_src >= TASK_SIZE_MAX; } diff --git a/arch/x86/pci/pcbios.c b/arch/x86/pci/pcbios.c index 9c97d814125e..4f15280732ed 100644 --- a/arch/x86/pci/pcbios.c +++ b/arch/x86/pci/pcbios.c @@ -302,7 +302,7 @@ static const struct pci_raw_ops *__init pci_find_bios(void) check <= (union bios32 *) __va(0xffff0); ++check) { long sig; - if (probe_kernel_address(&check->fields.signature, sig)) + if (get_kernel_nofault(sig, &check->fields.signature)) continue; if (check->fields.signature != BIOS32_SIGNATURE) diff --git a/arch/x86/platform/intel-mid/sfi.c b/arch/x86/platform/intel-mid/sfi.c index b8f7f193f383..30bd5714a3d4 100644 --- a/arch/x86/platform/intel-mid/sfi.c +++ b/arch/x86/platform/intel-mid/sfi.c @@ -287,8 +287,8 @@ void intel_scu_devices_create(void) adapter = i2c_get_adapter(i2c_bus[i]); if (adapter) { - client = i2c_new_device(adapter, i2c_devs[i]); - if (!client) + client = i2c_new_client_device(adapter, i2c_devs[i]); + if (IS_ERR(client)) pr_err("can't create i2c device %s\n", i2c_devs[i]->type); } else diff --git a/arch/x86/platform/uv/uv_irq.c b/arch/x86/platform/uv/uv_irq.c index fc13cbbb2dce..abb6075397f0 100644 --- a/arch/x86/platform/uv/uv_irq.c +++ b/arch/x86/platform/uv/uv_irq.c @@ -167,9 +167,10 @@ static struct irq_domain *uv_get_irq_domain(void) goto out; uv_domain = irq_domain_create_tree(fn, &uv_domain_ops, NULL); - irq_domain_free_fwnode(fn); if (uv_domain) uv_domain->parent = x86_vector_domain; + else + irq_domain_free_fwnode(fn); out: mutex_unlock(&uv_lock); diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 7c65102debaf..db1378c6ff26 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -193,6 +193,8 @@ static void fix_processor_context(void) */ static void notrace __restore_processor_state(struct saved_context *ctxt) { + struct cpuinfo_x86 *c; + if (ctxt->misc_enable_saved) wrmsrl(MSR_IA32_MISC_ENABLE, ctxt->misc_enable); /* @@ -263,6 +265,10 @@ static void notrace __restore_processor_state(struct saved_context *ctxt) mtrr_bp_restore(); perf_restore_debug_store(); msr_restore_context(ctxt); + + c = &cpu_data(smp_processor_id()); + if (cpu_has(c, X86_FEATURE_MSR_IA32_FEAT_CTL)) + init_ia32_feat_ctl(c); } /* Needed by apm.c */ diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 33b309d65955..c46b9f2e732f 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -386,7 +386,7 @@ static void set_aliased_prot(void *v, pgprot_t prot) preempt_disable(); - probe_kernel_read(&dummy, v, 1); + copy_from_kernel_nofault(&dummy, v, 1); if (HYPERVISOR_update_va_mapping((unsigned long)v, pte, 0)) BUG(); @@ -598,6 +598,26 @@ static void xen_write_ldt_entry(struct desc_struct *dt, int entrynum, } #ifdef CONFIG_X86_64 +void noist_exc_debug(struct pt_regs *regs); + +DEFINE_IDTENTRY_RAW(xenpv_exc_nmi) +{ + /* On Xen PV, NMI doesn't use IST. The C part is the sane as native. */ + exc_nmi(regs); +} + +DEFINE_IDTENTRY_RAW(xenpv_exc_debug) +{ + /* + * There's no IST on Xen PV, but we still need to dispatch + * to the correct handler. + */ + if (user_mode(regs)) + noist_exc_debug(regs); + else + exc_debug(regs); +} + struct trap_array_entry { void (*orig)(void); void (*xen)(void); @@ -609,18 +629,18 @@ struct trap_array_entry { .xen = xen_asm_##func, \ .ist_okay = ist_ok } -#define TRAP_ENTRY_REDIR(func, xenfunc, ist_ok) { \ +#define TRAP_ENTRY_REDIR(func, ist_ok) { \ .orig = asm_##func, \ - .xen = xen_asm_##xenfunc, \ + .xen = xen_asm_xenpv_##func, \ .ist_okay = ist_ok } static struct trap_array_entry trap_array[] = { - TRAP_ENTRY_REDIR(exc_debug, exc_xendebug, true ), + TRAP_ENTRY_REDIR(exc_debug, true ), TRAP_ENTRY(exc_double_fault, true ), #ifdef CONFIG_X86_MCE TRAP_ENTRY(exc_machine_check, true ), #endif - TRAP_ENTRY_REDIR(exc_nmi, exc_xennmi, true ), + TRAP_ENTRY_REDIR(exc_nmi, true ), TRAP_ENTRY(exc_int3, false ), TRAP_ENTRY(exc_overflow, false ), #ifdef CONFIG_IA32_EMULATION @@ -850,6 +870,17 @@ static void xen_load_sp0(unsigned long sp0) } #ifdef CONFIG_X86_IOPL_IOPERM +static void xen_invalidate_io_bitmap(void) +{ + struct physdev_set_iobitmap iobitmap = { + .bitmap = 0, + .nr_ports = 0, + }; + + native_tss_invalidate_io_bitmap(); + HYPERVISOR_physdev_op(PHYSDEVOP_set_iobitmap, &iobitmap); +} + static void xen_update_io_bitmap(void) { struct physdev_set_iobitmap iobitmap; @@ -1079,6 +1110,7 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = { .load_sp0 = xen_load_sp0, #ifdef CONFIG_X86_IOPL_IOPERM + .invalidate_io_bitmap = xen_invalidate_io_bitmap, .update_io_bitmap = xen_update_io_bitmap, #endif .io_delay = xen_io_delay, diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S index 5d252aaeade8..aab1d99b2b48 100644 --- a/arch/x86/xen/xen-asm_64.S +++ b/arch/x86/xen/xen-asm_64.S @@ -29,10 +29,9 @@ _ASM_NOKPROBE(xen_\name) .endm xen_pv_trap asm_exc_divide_error -xen_pv_trap asm_exc_debug -xen_pv_trap asm_exc_xendebug +xen_pv_trap asm_xenpv_exc_debug xen_pv_trap asm_exc_int3 -xen_pv_trap asm_exc_xennmi +xen_pv_trap asm_xenpv_exc_nmi xen_pv_trap asm_exc_overflow xen_pv_trap asm_exc_bounds xen_pv_trap asm_exc_invalid_op @@ -161,10 +160,22 @@ SYM_FUNC_END(xen_syscall32_target) /* 32-bit compat sysenter target */ SYM_FUNC_START(xen_sysenter_target) - mov 0*8(%rsp), %rcx - mov 1*8(%rsp), %r11 - mov 5*8(%rsp), %rsp - jmp entry_SYSENTER_compat + /* + * NB: Xen is polite and clears TF from EFLAGS for us. This means + * that we don't need to guard against single step exceptions here. + */ + popq %rcx + popq %r11 + + /* + * Neither Xen nor the kernel really knows what the old SS and + * CS were. The kernel expects __USER32_DS and __USER32_CS, so + * report those values even though Xen will guess its own values. + */ + movq $__USER32_DS, 4*8(%rsp) + movq $__USER32_CS, 1*8(%rsp) + + jmp entry_SYSENTER_compat_after_hwframe SYM_FUNC_END(xen_sysenter_target) #else /* !CONFIG_IA32_EMULATION */ diff --git a/arch/xtensa/include/asm/checksum.h b/arch/xtensa/include/asm/checksum.h index d8292cc9ebdf..243a5fe79d3c 100644 --- a/arch/xtensa/include/asm/checksum.h +++ b/arch/xtensa/include/asm/checksum.h @@ -57,7 +57,7 @@ static inline __wsum csum_and_copy_from_user(const void __user *src, void *dst, int len, __wsum sum, int *err_ptr) { - if (access_ok(dst, len)) + if (access_ok(src, len)) return csum_partial_copy_generic((__force const void *)src, dst, len, sum, err_ptr, NULL); if (len) diff --git a/arch/xtensa/kernel/perf_event.c b/arch/xtensa/kernel/perf_event.c index 9bae79f70301..99fcd63ce597 100644 --- a/arch/xtensa/kernel/perf_event.c +++ b/arch/xtensa/kernel/perf_event.c @@ -362,9 +362,7 @@ irqreturn_t xtensa_pmu_irq_handler(int irq, void *dev_id) struct xtensa_pmu_events *ev = this_cpu_ptr(&xtensa_pmu_events); unsigned i; - for (i = find_first_bit(ev->used_mask, XCHAL_NUM_PERF_COUNTERS); - i < XCHAL_NUM_PERF_COUNTERS; - i = find_next_bit(ev->used_mask, XCHAL_NUM_PERF_COUNTERS, i + 1)) { + for_each_set_bit(i, ev->used_mask, XCHAL_NUM_PERF_COUNTERS) { uint32_t v = get_er(XTENSA_PMU_PMSTAT(i)); struct perf_event *event = ev->event[i]; struct hw_perf_event *hwc = &event->hw; diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c index d9204dc2656e..be2c78f71695 100644 --- a/arch/xtensa/kernel/setup.c +++ b/arch/xtensa/kernel/setup.c @@ -724,7 +724,8 @@ c_start(struct seq_file *f, loff_t *pos) static void * c_next(struct seq_file *f, void *v, loff_t *pos) { - return NULL; + ++*pos; + return c_start(f, pos); } static void diff --git a/arch/xtensa/kernel/xtensa_ksyms.c b/arch/xtensa/kernel/xtensa_ksyms.c index 4092555828b1..24cf6972eace 100644 --- a/arch/xtensa/kernel/xtensa_ksyms.c +++ b/arch/xtensa/kernel/xtensa_ksyms.c @@ -87,13 +87,13 @@ void __xtensa_libgcc_window_spill(void) } EXPORT_SYMBOL(__xtensa_libgcc_window_spill); -unsigned long __sync_fetch_and_and_4(unsigned long *p, unsigned long v) +unsigned int __sync_fetch_and_and_4(volatile void *p, unsigned int v) { BUG(); } EXPORT_SYMBOL(__sync_fetch_and_and_4); -unsigned long __sync_fetch_and_or_4(unsigned long *p, unsigned long v) +unsigned int __sync_fetch_and_or_4(volatile void *p, unsigned int v) { BUG(); } |