diff options
Diffstat (limited to 'arch')
145 files changed, 901 insertions, 580 deletions
diff --git a/arch/Kconfig b/arch/Kconfig index 78c6f05b10f9..24862d15f3a3 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -1105,6 +1105,12 @@ config HAVE_ARCH_PFN_VALID config ARCH_SUPPORTS_DEBUG_PAGEALLOC bool +config ARCH_SPLIT_ARG64 + bool + help + If a 32-bit architecture requires 64-bit arguments to be split into + pairs of 32-bit arguments, select this option. + source "kernel/gcov/Kconfig" source "scripts/gcc-plugins/Kconfig" diff --git a/arch/alpha/include/asm/local64.h b/arch/alpha/include/asm/local64.h deleted file mode 100644 index 36c93b5cc239..000000000000 --- a/arch/alpha/include/asm/local64.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/local64.h> diff --git a/arch/arc/Makefile b/arch/arc/Makefile index 0c6bf0d1df7a..578bdbbb0fa7 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -102,16 +102,22 @@ libs-y += arch/arc/lib/ $(LIBGCC) boot := arch/arc/boot -#default target for make without any arguments. -KBUILD_IMAGE := $(boot)/bootpImage - -all: bootpImage -bootpImage: vmlinux - -boot_targets += uImage uImage.bin uImage.gz +boot_targets := uImage.bin uImage.gz uImage.lzma +PHONY += $(boot_targets) $(boot_targets): vmlinux $(Q)$(MAKE) $(build)=$(boot) $(boot)/$@ +uimage-default-y := uImage.bin +uimage-default-$(CONFIG_KERNEL_GZIP) := uImage.gz +uimage-default-$(CONFIG_KERNEL_LZMA) := uImage.lzma + +PHONY += uImage +uImage: $(uimage-default-y) + @ln -sf $< $(boot)/uImage + @$(kecho) ' Image $(boot)/uImage is ready' + +CLEAN_FILES += $(boot)/uImage + archclean: $(Q)$(MAKE) $(clean)=$(boot) diff --git a/arch/arc/boot/Makefile b/arch/arc/boot/Makefile index 538b92f4dd25..5648748c285f 100644 --- a/arch/arc/boot/Makefile +++ b/arch/arc/boot/Makefile @@ -1,5 +1,4 @@ # SPDX-License-Identifier: GPL-2.0 -targets := vmlinux.bin vmlinux.bin.gz uImage # uImage build relies on mkimage being availble on your host for ARC target # You will need to build u-boot for ARC, rename mkimage to arc-elf32-mkimage @@ -7,23 +6,18 @@ targets := vmlinux.bin vmlinux.bin.gz uImage OBJCOPYFLAGS= -O binary -R .note -R .note.gnu.build-id -R .comment -S -LINUX_START_TEXT = $$(readelf -h vmlinux | \ +LINUX_START_TEXT = $$($(READELF) -h vmlinux | \ grep "Entry point address" | grep -o 0x.*) UIMAGE_LOADADDR = $(CONFIG_LINUX_LINK_BASE) UIMAGE_ENTRYADDR = $(LINUX_START_TEXT) -suffix-y := bin -suffix-$(CONFIG_KERNEL_GZIP) := gz -suffix-$(CONFIG_KERNEL_LZMA) := lzma - -targets += uImage +targets += vmlinux.bin +targets += vmlinux.bin.gz +targets += vmlinux.bin.lzma targets += uImage.bin targets += uImage.gz targets += uImage.lzma -extra-y += vmlinux.bin -extra-y += vmlinux.bin.gz -extra-y += vmlinux.bin.lzma $(obj)/vmlinux.bin: vmlinux FORCE $(call if_changed,objcopy) @@ -42,7 +36,3 @@ $(obj)/uImage.gz: $(obj)/vmlinux.bin.gz FORCE $(obj)/uImage.lzma: $(obj)/vmlinux.bin.lzma FORCE $(call if_changed,uimage,lzma) - -$(obj)/uImage: $(obj)/uImage.$(suffix-y) - @ln -sf $(notdir $<) $@ - @echo ' Image $@ is ready' diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild index 81f4edec0c2a..3c1afa524b9c 100644 --- a/arch/arc/include/asm/Kbuild +++ b/arch/arc/include/asm/Kbuild @@ -1,7 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 generic-y += extable.h generic-y += kvm_para.h -generic-y += local64.h generic-y += mcs_spinlock.h generic-y += parport.h generic-y += user.h diff --git a/arch/arc/include/asm/page.h b/arch/arc/include/asm/page.h index 23e41e890eda..ad9b7fe4dba3 100644 --- a/arch/arc/include/asm/page.h +++ b/arch/arc/include/asm/page.h @@ -10,6 +10,7 @@ #ifndef __ASSEMBLY__ #define clear_page(paddr) memset((paddr), 0, PAGE_SIZE) +#define copy_user_page(to, from, vaddr, pg) copy_page(to, from) #define copy_page(to, from) memcpy((to), (from), PAGE_SIZE) struct vm_area_struct; diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S index 1f5308abf36d..1743506081da 100644 --- a/arch/arc/kernel/entry.S +++ b/arch/arc/kernel/entry.S @@ -307,7 +307,7 @@ resume_user_mode_begin: mov r0, sp ; pt_regs for arg to do_signal()/do_notify_resume() GET_CURR_THR_INFO_FLAGS r9 - and.f 0, r9, TIF_SIGPENDING|TIF_NOTIFY_SIGNAL + and.f 0, r9, _TIF_SIGPENDING|_TIF_NOTIFY_SIGNAL bz .Lchk_notify_resume ; Normal Trap/IRQ entry only saves Scratch (caller-saved) regs diff --git a/arch/arc/plat-hsdk/Kconfig b/arch/arc/plat-hsdk/Kconfig index 6b5c54576f54..a2d10c29fbcc 100644 --- a/arch/arc/plat-hsdk/Kconfig +++ b/arch/arc/plat-hsdk/Kconfig @@ -7,6 +7,7 @@ menuconfig ARC_SOC_HSDK depends on ISA_ARCV2 select ARC_HAS_ACCL_REGS select ARC_IRQ_NO_AUTOSAVE + select ARC_FPU_SAVE_RESTORE select CLK_HSDK select RESET_CONTROLLER select RESET_HSDK diff --git a/arch/arm/boot/dts/omap3-n950-n9.dtsi b/arch/arm/boot/dts/omap3-n950-n9.dtsi index 11d41e86f814..7dde9fbb06d3 100644 --- a/arch/arm/boot/dts/omap3-n950-n9.dtsi +++ b/arch/arm/boot/dts/omap3-n950-n9.dtsi @@ -494,3 +494,11 @@ clock-names = "sysclk"; }; }; + +&aes1_target { + status = "disabled"; +}; + +&aes2_target { + status = "disabled"; +}; diff --git a/arch/arm/boot/dts/picoxcell-pc3x2.dtsi b/arch/arm/boot/dts/picoxcell-pc3x2.dtsi index c4c6c7e9e37b..5898879a3038 100644 --- a/arch/arm/boot/dts/picoxcell-pc3x2.dtsi +++ b/arch/arm/boot/dts/picoxcell-pc3x2.dtsi @@ -45,18 +45,21 @@ emac: gem@30000 { compatible = "cadence,gem"; reg = <0x30000 0x10000>; + interrupt-parent = <&vic0>; interrupts = <31>; }; dmac1: dmac@40000 { compatible = "snps,dw-dmac"; reg = <0x40000 0x10000>; + interrupt-parent = <&vic0>; interrupts = <25>; }; dmac2: dmac@50000 { compatible = "snps,dw-dmac"; reg = <0x50000 0x10000>; + interrupt-parent = <&vic0>; interrupts = <26>; }; @@ -233,6 +236,7 @@ axi2pico@c0000000 { compatible = "picochip,axi2pico-pc3x2"; reg = <0xc0000000 0x10000>; + interrupt-parent = <&vic0>; interrupts = <13 14 15 16 17 18 19 20 21>; }; }; diff --git a/arch/arm/boot/dts/ste-ux500-samsung-golden.dts b/arch/arm/boot/dts/ste-ux500-samsung-golden.dts index 496f9d3ba7b7..60fe6189e728 100644 --- a/arch/arm/boot/dts/ste-ux500-samsung-golden.dts +++ b/arch/arm/boot/dts/ste-ux500-samsung-golden.dts @@ -329,6 +329,7 @@ panel@0 { compatible = "samsung,s6e63m0"; reg = <0>; + max-brightness = <15>; vdd3-supply = <&panel_reg_3v0>; vci-supply = <&panel_reg_1v8>; reset-gpios = <&gpio4 11 GPIO_ACTIVE_LOW>; diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig index 1c11d1557779..b515c31f0ab7 100644 --- a/arch/arm/configs/omap2plus_defconfig +++ b/arch/arm/configs/omap2plus_defconfig @@ -279,6 +279,7 @@ CONFIG_SERIAL_OMAP_CONSOLE=y CONFIG_SERIAL_DEV_BUS=y CONFIG_I2C_CHARDEV=y CONFIG_SPI=y +CONFIG_SPI_GPIO=m CONFIG_SPI_OMAP24XX=y CONFIG_SPI_TI_QSPI=m CONFIG_HSI=m @@ -296,7 +297,6 @@ CONFIG_GPIO_TWL4030=y CONFIG_W1=m CONFIG_HDQ_MASTER_OMAP=m CONFIG_W1_SLAVE_DS250X=m -CONFIG_POWER_AVS=y CONFIG_POWER_RESET=y CONFIG_POWER_RESET_GPIO=y CONFIG_BATTERY_BQ27XXX=m diff --git a/arch/arm/crypto/chacha-glue.c b/arch/arm/crypto/chacha-glue.c index 7b5cf8430c6d..cdde8fd01f8f 100644 --- a/arch/arm/crypto/chacha-glue.c +++ b/arch/arm/crypto/chacha-glue.c @@ -60,6 +60,7 @@ static void chacha_doneon(u32 *state, u8 *dst, const u8 *src, chacha_block_xor_neon(state, d, s, nrounds); if (d != dst) memcpy(dst, buf, bytes); + state[12]++; } } diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild index 4a0848aef207..03657ff8fbe3 100644 --- a/arch/arm/include/asm/Kbuild +++ b/arch/arm/include/asm/Kbuild @@ -2,7 +2,6 @@ generic-y += early_ioremap.h generic-y += extable.h generic-y += flat.h -generic-y += local64.h generic-y += parport.h generated-y += mach-types.h diff --git a/arch/arm/mach-omap2/omap_device.c b/arch/arm/mach-omap2/omap_device.c index f3191704cab9..56d6814bec26 100644 --- a/arch/arm/mach-omap2/omap_device.c +++ b/arch/arm/mach-omap2/omap_device.c @@ -230,10 +230,12 @@ static int _omap_device_notifier_call(struct notifier_block *nb, break; case BUS_NOTIFY_BIND_DRIVER: od = to_omap_device(pdev); - if (od && (od->_state == OMAP_DEVICE_STATE_ENABLED) && - pm_runtime_status_suspended(dev)) { + if (od) { od->_driver_status = BUS_NOTIFY_BIND_DRIVER; - pm_runtime_set_active(dev); + if (od->_state == OMAP_DEVICE_STATE_ENABLED && + pm_runtime_status_suspended(dev)) { + pm_runtime_set_active(dev); + } } break; case BUS_NOTIFY_ADD_DEVICE: diff --git a/arch/arm/mach-omap2/pmic-cpcap.c b/arch/arm/mach-omap2/pmic-cpcap.c index eab281a5fc9f..09076ad0576d 100644 --- a/arch/arm/mach-omap2/pmic-cpcap.c +++ b/arch/arm/mach-omap2/pmic-cpcap.c @@ -71,7 +71,7 @@ static struct omap_voltdm_pmic omap_cpcap_iva = { .vp_vstepmin = OMAP4_VP_VSTEPMIN_VSTEPMIN, .vp_vstepmax = OMAP4_VP_VSTEPMAX_VSTEPMAX, .vddmin = 900000, - .vddmax = 1350000, + .vddmax = 1375000, .vp_timeout_us = OMAP4_VP_VLIMITTO_TIMEOUT_US, .i2c_slave_addr = 0x44, .volt_reg_addr = 0x0, diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index 60e901cd0de6..5a957a9a0984 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -371,7 +371,7 @@ static int __init xen_guest_init(void) } gnttab_init(); if (!xen_initial_domain()) - xenbus_probe(NULL); + xenbus_probe(); /* * Making sure board specific code will not set up ops for diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 05e17351e4f3..f39568b28ec1 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -174,8 +174,6 @@ config ARM64 select HAVE_NMI select HAVE_PATA_PLATFORM select HAVE_PERF_EVENTS - select HAVE_PERF_EVENTS_NMI if ARM64_PSEUDO_NMI && HW_PERF_EVENTS - select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && HAVE_PERF_EVENTS_NMI select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP select HAVE_REGS_AND_STACK_ACCESS_API diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 6be9b3750250..90309208bb28 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -10,7 +10,7 @@ # # Copyright (C) 1995-2001 by Russell King -LDFLAGS_vmlinux :=--no-undefined -X -z norelro +LDFLAGS_vmlinux :=--no-undefined -X ifeq ($(CONFIG_RELOCATABLE), y) # Pass --no-apply-dynamic-relocs to restore pre-binutils-2.27 behaviour @@ -115,16 +115,20 @@ KBUILD_CPPFLAGS += -mbig-endian CHECKFLAGS += -D__AARCH64EB__ # Prefer the baremetal ELF build target, but not all toolchains include # it so fall back to the standard linux version if needed. -KBUILD_LDFLAGS += -EB $(call ld-option, -maarch64elfb, -maarch64linuxb) +KBUILD_LDFLAGS += -EB $(call ld-option, -maarch64elfb, -maarch64linuxb -z norelro) UTS_MACHINE := aarch64_be else KBUILD_CPPFLAGS += -mlittle-endian CHECKFLAGS += -D__AARCH64EL__ # Same as above, prefer ELF but fall back to linux target if needed. -KBUILD_LDFLAGS += -EL $(call ld-option, -maarch64elf, -maarch64linux) +KBUILD_LDFLAGS += -EL $(call ld-option, -maarch64elf, -maarch64linux -z norelro) UTS_MACHINE := aarch64 endif +ifeq ($(CONFIG_LD_IS_LLD), y) +KBUILD_LDFLAGS += -z norelro +endif + CHECKFLAGS += -D__aarch64__ ifeq ($(CONFIG_DYNAMIC_FTRACE_WITH_REGS),y) diff --git a/arch/arm64/boot/dts/bitmain/bm1880.dtsi b/arch/arm64/boot/dts/bitmain/bm1880.dtsi index fa6e6905f588..53a9b76057aa 100644 --- a/arch/arm64/boot/dts/bitmain/bm1880.dtsi +++ b/arch/arm64/boot/dts/bitmain/bm1880.dtsi @@ -127,7 +127,7 @@ compatible = "snps,dw-apb-gpio-port"; gpio-controller; #gpio-cells = <2>; - snps,nr-gpios = <32>; + ngpios = <32>; reg = <0>; interrupt-controller; #interrupt-cells = <2>; @@ -145,7 +145,7 @@ compatible = "snps,dw-apb-gpio-port"; gpio-controller; #gpio-cells = <2>; - snps,nr-gpios = <32>; + ngpios = <32>; reg = <0>; interrupt-controller; #interrupt-cells = <2>; @@ -163,7 +163,7 @@ compatible = "snps,dw-apb-gpio-port"; gpio-controller; #gpio-cells = <2>; - snps,nr-gpios = <8>; + ngpios = <8>; reg = <0>; interrupt-controller; #interrupt-cells = <2>; diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild index ff9cbb631212..07ac208edc89 100644 --- a/arch/arm64/include/asm/Kbuild +++ b/arch/arm64/include/asm/Kbuild @@ -1,6 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 generic-y += early_ioremap.h -generic-y += local64.h generic-y += mcs_spinlock.h generic-y += qrwlock.h generic-y += qspinlock.h diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h index 015ddffaf6ca..b56a4b2bc248 100644 --- a/arch/arm64/include/asm/atomic.h +++ b/arch/arm64/include/asm/atomic.h @@ -17,7 +17,7 @@ #include <asm/lse.h> #define ATOMIC_OP(op) \ -static inline void arch_##op(int i, atomic_t *v) \ +static __always_inline void arch_##op(int i, atomic_t *v) \ { \ __lse_ll_sc_body(op, i, v); \ } @@ -32,7 +32,7 @@ ATOMIC_OP(atomic_sub) #undef ATOMIC_OP #define ATOMIC_FETCH_OP(name, op) \ -static inline int arch_##op##name(int i, atomic_t *v) \ +static __always_inline int arch_##op##name(int i, atomic_t *v) \ { \ return __lse_ll_sc_body(op##name, i, v); \ } @@ -56,7 +56,7 @@ ATOMIC_FETCH_OPS(atomic_sub_return) #undef ATOMIC_FETCH_OPS #define ATOMIC64_OP(op) \ -static inline void arch_##op(long i, atomic64_t *v) \ +static __always_inline void arch_##op(long i, atomic64_t *v) \ { \ __lse_ll_sc_body(op, i, v); \ } @@ -71,7 +71,7 @@ ATOMIC64_OP(atomic64_sub) #undef ATOMIC64_OP #define ATOMIC64_FETCH_OP(name, op) \ -static inline long arch_##op##name(long i, atomic64_t *v) \ +static __always_inline long arch_##op##name(long i, atomic64_t *v) \ { \ return __lse_ll_sc_body(op##name, i, v); \ } @@ -94,7 +94,7 @@ ATOMIC64_FETCH_OPS(atomic64_sub_return) #undef ATOMIC64_FETCH_OP #undef ATOMIC64_FETCH_OPS -static inline long arch_atomic64_dec_if_positive(atomic64_t *v) +static __always_inline long arch_atomic64_dec_if_positive(atomic64_t *v) { return __lse_ll_sc_body(atomic64_dec_if_positive, v); } diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 11beda85ee7e..8fcfab0c2567 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -17,6 +17,7 @@ #include <linux/jump_label.h> #include <linux/kvm_types.h> #include <linux/percpu.h> +#include <linux/psci.h> #include <asm/arch_gicv3.h> #include <asm/barrier.h> #include <asm/cpufeature.h> @@ -240,6 +241,28 @@ struct kvm_host_data { struct kvm_pmu_events pmu_events; }; +struct kvm_host_psci_config { + /* PSCI version used by host. */ + u32 version; + + /* Function IDs used by host if version is v0.1. */ + struct psci_0_1_function_ids function_ids_0_1; + + bool psci_0_1_cpu_suspend_implemented; + bool psci_0_1_cpu_on_implemented; + bool psci_0_1_cpu_off_implemented; + bool psci_0_1_migrate_implemented; +}; + +extern struct kvm_host_psci_config kvm_nvhe_sym(kvm_host_psci_config); +#define kvm_host_psci_config CHOOSE_NVHE_SYM(kvm_host_psci_config) + +extern s64 kvm_nvhe_sym(hyp_physvirt_offset); +#define hyp_physvirt_offset CHOOSE_NVHE_SYM(hyp_physvirt_offset) + +extern u64 kvm_nvhe_sym(hyp_cpu_logical_map)[NR_CPUS]; +#define hyp_cpu_logical_map CHOOSE_NVHE_SYM(hyp_cpu_logical_map) + struct vcpu_reset_state { unsigned long pc; unsigned long r0; diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h index 6f986e09a781..f0fe0cc6abe0 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -176,10 +176,21 @@ static inline void __uaccess_enable_hw_pan(void) * The Tag check override (TCO) bit disables temporarily the tag checking * preventing the issue. */ -static inline void uaccess_disable_privileged(void) +static inline void __uaccess_disable_tco(void) { asm volatile(ALTERNATIVE("nop", SET_PSTATE_TCO(0), ARM64_MTE, CONFIG_KASAN_HW_TAGS)); +} + +static inline void __uaccess_enable_tco(void) +{ + asm volatile(ALTERNATIVE("nop", SET_PSTATE_TCO(1), + ARM64_MTE, CONFIG_KASAN_HW_TAGS)); +} + +static inline void uaccess_disable_privileged(void) +{ + __uaccess_disable_tco(); if (uaccess_ttbr0_disable()) return; @@ -189,8 +200,7 @@ static inline void uaccess_disable_privileged(void) static inline void uaccess_enable_privileged(void) { - asm volatile(ALTERNATIVE("nop", SET_PSTATE_TCO(1), - ARM64_MTE, CONFIG_KASAN_HW_TAGS)); + __uaccess_enable_tco(); if (uaccess_ttbr0_enable()) return; diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index f42fd9e33981..301784463587 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -75,7 +75,7 @@ int main(void) DEFINE(S_SDEI_TTBR1, offsetof(struct pt_regs, sdei_ttbr1)); DEFINE(S_PMR_SAVE, offsetof(struct pt_regs, pmr_save)); DEFINE(S_STACKFRAME, offsetof(struct pt_regs, stackframe)); - DEFINE(S_FRAME_SIZE, sizeof(struct pt_regs)); + DEFINE(PT_REGS_SIZE, sizeof(struct pt_regs)); BLANK(); #ifdef CONFIG_COMPAT DEFINE(COMPAT_SIGFRAME_REGS_OFFSET, offsetof(struct compat_sigframe, uc.uc_mcontext.arm_r0)); diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 7ffb5f1d8b68..e99eddec0a46 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -2568,7 +2568,7 @@ static void verify_hyp_capabilities(void) int parange, ipa_max; unsigned int safe_vmid_bits, vmid_bits; - if (!IS_ENABLED(CONFIG_KVM) || !IS_ENABLED(CONFIG_KVM_ARM_HOST)) + if (!IS_ENABLED(CONFIG_KVM)) return; safe_mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1); diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S index a338f40e64d3..b3e4f9a088b1 100644 --- a/arch/arm64/kernel/entry-ftrace.S +++ b/arch/arm64/kernel/entry-ftrace.S @@ -35,7 +35,7 @@ */ .macro ftrace_regs_entry, allregs=0 /* Make room for pt_regs, plus a callee frame */ - sub sp, sp, #(S_FRAME_SIZE + 16) + sub sp, sp, #(PT_REGS_SIZE + 16) /* Save function arguments (and x9 for simplicity) */ stp x0, x1, [sp, #S_X0] @@ -61,15 +61,15 @@ .endif /* Save the callsite's SP and LR */ - add x10, sp, #(S_FRAME_SIZE + 16) + add x10, sp, #(PT_REGS_SIZE + 16) stp x9, x10, [sp, #S_LR] /* Save the PC after the ftrace callsite */ str x30, [sp, #S_PC] /* Create a frame record for the callsite above pt_regs */ - stp x29, x9, [sp, #S_FRAME_SIZE] - add x29, sp, #S_FRAME_SIZE + stp x29, x9, [sp, #PT_REGS_SIZE] + add x29, sp, #PT_REGS_SIZE /* Create our frame record within pt_regs. */ stp x29, x30, [sp, #S_STACKFRAME] @@ -120,7 +120,7 @@ ftrace_common_return: ldr x9, [sp, #S_PC] /* Restore the callsite's SP */ - add sp, sp, #S_FRAME_SIZE + 16 + add sp, sp, #PT_REGS_SIZE + 16 ret x9 SYM_CODE_END(ftrace_common) @@ -130,7 +130,7 @@ SYM_CODE_START(ftrace_graph_caller) ldr x0, [sp, #S_PC] sub x0, x0, #AARCH64_INSN_SIZE // ip (callsite's BL insn) add x1, sp, #S_LR // parent_ip (callsite's LR) - ldr x2, [sp, #S_FRAME_SIZE] // parent fp (callsite's FP) + ldr x2, [sp, #PT_REGS_SIZE] // parent fp (callsite's FP) bl prepare_ftrace_return b ftrace_common_return SYM_CODE_END(ftrace_graph_caller) diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 2a93fa5f4e49..c9bae73f2621 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -75,7 +75,7 @@ alternative_else_nop_endif .endif #endif - sub sp, sp, #S_FRAME_SIZE + sub sp, sp, #PT_REGS_SIZE #ifdef CONFIG_VMAP_STACK /* * Test whether the SP has overflowed, without corrupting a GPR. @@ -96,7 +96,7 @@ alternative_else_nop_endif * userspace, and can clobber EL0 registers to free up GPRs. */ - /* Stash the original SP (minus S_FRAME_SIZE) in tpidr_el0. */ + /* Stash the original SP (minus PT_REGS_SIZE) in tpidr_el0. */ msr tpidr_el0, x0 /* Recover the original x0 value and stash it in tpidrro_el0 */ @@ -182,7 +182,6 @@ alternative_else_nop_endif mrs_s \tmp2, SYS_GCR_EL1 bfi \tmp2, \tmp, #0, #16 msr_s SYS_GCR_EL1, \tmp2 - isb #endif .endm @@ -194,6 +193,7 @@ alternative_else_nop_endif ldr_l \tmp, gcr_kernel_excl mte_set_gcr \tmp, \tmp2 + isb 1: #endif .endm @@ -253,7 +253,7 @@ alternative_else_nop_endif scs_load tsk, x20 .else - add x21, sp, #S_FRAME_SIZE + add x21, sp, #PT_REGS_SIZE get_current_task tsk .endif /* \el == 0 */ mrs x22, elr_el1 @@ -377,7 +377,7 @@ alternative_else_nop_endif ldp x26, x27, [sp, #16 * 13] ldp x28, x29, [sp, #16 * 14] ldr lr, [sp, #S_LR] - add sp, sp, #S_FRAME_SIZE // restore sp + add sp, sp, #PT_REGS_SIZE // restore sp .if \el == 0 alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0 @@ -580,12 +580,12 @@ __bad_stack: /* * Store the original GPRs to the new stack. The orginal SP (minus - * S_FRAME_SIZE) was stashed in tpidr_el0 by kernel_ventry. + * PT_REGS_SIZE) was stashed in tpidr_el0 by kernel_ventry. */ - sub sp, sp, #S_FRAME_SIZE + sub sp, sp, #PT_REGS_SIZE kernel_entry 1 mrs x0, tpidr_el0 - add x0, x0, #S_FRAME_SIZE + add x0, x0, #PT_REGS_SIZE str x0, [sp, #S_SP] /* Stash the regs for handle_bad_stack */ diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index 38bb07eff872..3605f77ad4df 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -23,8 +23,6 @@ #include <linux/platform_device.h> #include <linux/sched_clock.h> #include <linux/smp.h> -#include <linux/nmi.h> -#include <linux/cpufreq.h> /* ARMv8 Cortex-A53 specific event types. */ #define ARMV8_A53_PERFCTR_PREF_LINEFILL 0xC2 @@ -1250,21 +1248,10 @@ static struct platform_driver armv8_pmu_driver = { static int __init armv8_pmu_driver_init(void) { - int ret; - if (acpi_disabled) - ret = platform_driver_register(&armv8_pmu_driver); + return platform_driver_register(&armv8_pmu_driver); else - ret = arm_pmu_acpi_probe(armv8_pmuv3_init); - - /* - * Try to re-initialize lockup detector after PMU init in - * case PMU events are triggered via NMIs. - */ - if (ret == 0 && arm_pmu_irq_is_nmi()) - lockup_detector_init(); - - return ret; + return arm_pmu_acpi_probe(armv8_pmuv3_init); } device_initcall(armv8_pmu_driver_init) @@ -1322,27 +1309,3 @@ void arch_perf_update_userpage(struct perf_event *event, userpg->cap_user_time_zero = 1; userpg->cap_user_time_short = 1; } - -#ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF -/* - * Safe maximum CPU frequency in case a particular platform doesn't implement - * cpufreq driver. Although, architecture doesn't put any restrictions on - * maximum frequency but 5 GHz seems to be safe maximum given the available - * Arm CPUs in the market which are clocked much less than 5 GHz. On the other - * hand, we can't make it much higher as it would lead to a large hard-lockup - * detection timeout on parts which are running slower (eg. 1GHz on - * Developerbox) and doesn't possess a cpufreq driver. - */ -#define SAFE_MAX_CPU_FREQ 5000000000UL // 5 GHz -u64 hw_nmi_get_sample_period(int watchdog_thresh) -{ - unsigned int cpu = smp_processor_id(); - unsigned long max_cpu_freq; - - max_cpu_freq = cpufreq_get_hw_max_freq(cpu) * 1000UL; - if (!max_cpu_freq) - max_cpu_freq = SAFE_MAX_CPU_FREQ; - - return (u64)max_cpu_freq * watchdog_thresh; -} -#endif diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index 89c64ada8732..66aac2881ba8 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -352,8 +352,8 @@ kprobe_breakpoint_ss_handler(struct pt_regs *regs, unsigned int esr) unsigned long addr = instruction_pointer(regs); struct kprobe *cur = kprobe_running(); - if (cur && (kcb->kprobe_status == KPROBE_HIT_SS) - && ((unsigned long)&cur->ainsn.api.insn[1] == addr)) { + if (cur && (kcb->kprobe_status & (KPROBE_HIT_SS | KPROBE_REENTER)) && + ((unsigned long)&cur->ainsn.api.insn[1] == addr)) { kprobes_restore_local_irqflag(kcb, regs); post_kprobe_handler(cur, kcb, regs); diff --git a/arch/arm64/kernel/probes/kprobes_trampoline.S b/arch/arm64/kernel/probes/kprobes_trampoline.S index 890ca72c5a51..288a84e253cc 100644 --- a/arch/arm64/kernel/probes/kprobes_trampoline.S +++ b/arch/arm64/kernel/probes/kprobes_trampoline.S @@ -25,7 +25,7 @@ stp x24, x25, [sp, #S_X24] stp x26, x27, [sp, #S_X26] stp x28, x29, [sp, #S_X28] - add x0, sp, #S_FRAME_SIZE + add x0, sp, #PT_REGS_SIZE stp lr, x0, [sp, #S_LR] /* * Construct a useful saved PSTATE @@ -62,7 +62,7 @@ .endm SYM_CODE_START(kretprobe_trampoline) - sub sp, sp, #S_FRAME_SIZE + sub sp, sp, #PT_REGS_SIZE save_all_base_regs @@ -76,7 +76,7 @@ SYM_CODE_START(kretprobe_trampoline) restore_all_base_regs - add sp, sp, #S_FRAME_SIZE + add sp, sp, #PT_REGS_SIZE ret SYM_CODE_END(kretprobe_trampoline) diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index f71d6ce4673f..6237486ff6bb 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -914,13 +914,6 @@ static void do_signal(struct pt_regs *regs) asmlinkage void do_notify_resume(struct pt_regs *regs, unsigned long thread_flags) { - /* - * The assembly code enters us with IRQs off, but it hasn't - * informed the tracing code of that for efficiency reasons. - * Update the trace code with the current status. - */ - trace_hardirqs_off(); - do { if (thread_flags & _TIF_NEED_RESCHED) { /* Unmask Debug and SError for the next task */ diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 6bc3a3698c3d..ad00f99ee9b0 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -434,7 +434,7 @@ static void __init hyp_mode_check(void) "CPU: CPUs started in inconsistent modes"); else pr_info("CPU: All CPU(s) started at EL1\n"); - if (IS_ENABLED(CONFIG_KVM)) + if (IS_ENABLED(CONFIG_KVM) && !is_kernel_in_hyp_mode()) kvm_compute_layout(); } @@ -807,7 +807,6 @@ int arch_show_interrupts(struct seq_file *p, int prec) unsigned int cpu, i; for (i = 0; i < NR_IPI; i++) { - unsigned int irq = irq_desc_get_irq(ipi_desc[i]); seq_printf(p, "%*s%u:%s", prec - 1, "IPI", i, prec >= 4 ? " " : ""); for_each_online_cpu(cpu) diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index f61e9d8cc55a..c2877c332f2d 100644 --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -9,6 +9,7 @@ #include <asm/daifflags.h> #include <asm/debug-monitors.h> +#include <asm/exception.h> #include <asm/fpsimd.h> #include <asm/syscall.h> #include <asm/thread_info.h> @@ -165,15 +166,8 @@ 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) && !(flags & _TIF_SINGLESTEP)) { - /* - * We're off to userspace, where interrupts are - * always enabled after we restore the flags from - * the SPSR. - */ - trace_hardirqs_on(); + if (!has_syscall_work(flags) && !(flags & _TIF_SINGLESTEP)) return; - } local_daif_restore(DAIF_PROCCTX); } diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 08156be75569..6895ce777e7f 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -42,7 +42,6 @@ #include <asm/smp.h> #include <asm/stack_pointer.h> #include <asm/stacktrace.h> -#include <asm/exception.h> #include <asm/system_misc.h> #include <asm/sysreg.h> diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile index a8f8e409e2bf..cd9c3fa25902 100644 --- a/arch/arm64/kernel/vdso/Makefile +++ b/arch/arm64/kernel/vdso/Makefile @@ -24,8 +24,7 @@ btildflags-$(CONFIG_ARM64_BTI_KERNEL) += -z force-bti # 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 $(call ld-option, --no-eh-frame-hdr) --build-id=sha1 -n \ - $(btildflags-y) -T + -Bsymbolic --build-id=sha1 -n $(btildflags-y) -T ccflags-y := -fno-common -fno-builtin -fno-stack-protector -ffixed-x18 ccflags-y += -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO diff --git a/arch/arm64/kernel/vdso/vdso.lds.S b/arch/arm64/kernel/vdso/vdso.lds.S index d808ad31e01f..61dbb4c838ef 100644 --- a/arch/arm64/kernel/vdso/vdso.lds.S +++ b/arch/arm64/kernel/vdso/vdso.lds.S @@ -40,9 +40,6 @@ SECTIONS PROVIDE (_etext = .); PROVIDE (etext = .); - .eh_frame_hdr : { *(.eh_frame_hdr) } :text :eh_frame_hdr - .eh_frame : { KEEP (*(.eh_frame)) } :text - .dynamic : { *(.dynamic) } :text :dynamic .rodata : { *(.rodata*) } :text @@ -54,6 +51,7 @@ SECTIONS *(.note.GNU-stack) *(.data .data.* .gnu.linkonce.d.* .sdata*) *(.bss .sbss .dynbss .dynsbss) + *(.eh_frame .eh_frame_hdr) } } @@ -66,7 +64,6 @@ PHDRS text PT_LOAD FLAGS(5) FILEHDR PHDRS; /* PF_R|PF_X */ dynamic PT_DYNAMIC FLAGS(4); /* PF_R */ note PT_NOTE FLAGS(4); /* PF_R */ - eh_frame_hdr PT_GNU_EH_FRAME; } /* diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index 043756db8f6e..3964acf5451e 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -49,14 +49,6 @@ if KVM source "virt/kvm/Kconfig" -config KVM_ARM_PMU - bool "Virtual Performance Monitoring Unit (PMU) support" - depends on HW_PERF_EVENTS - default y - help - Adds support for a virtual Performance Monitoring Unit (PMU) in - virtual machines. - endif # KVM endif # VIRTUALIZATION diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile index 60fd181df624..13b017284bf9 100644 --- a/arch/arm64/kvm/Makefile +++ b/arch/arm64/kvm/Makefile @@ -24,4 +24,4 @@ kvm-y := $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o \ vgic/vgic-mmio-v3.o vgic/vgic-kvm-device.o \ vgic/vgic-its.o vgic/vgic-debug.o -kvm-$(CONFIG_KVM_ARM_PMU) += pmu-emul.o +kvm-$(CONFIG_HW_PERF_EVENTS) += pmu-emul.o diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c index 32ba6fbc3814..74e0699661e9 100644 --- a/arch/arm64/kvm/arch_timer.c +++ b/arch/arm64/kvm/arch_timer.c @@ -1129,9 +1129,10 @@ int kvm_timer_enable(struct kvm_vcpu *vcpu) if (!irqchip_in_kernel(vcpu->kvm)) goto no_vgic; - if (!vgic_initialized(vcpu->kvm)) - return -ENODEV; - + /* + * At this stage, we have the guarantee that the vgic is both + * available and initialized. + */ if (!timer_irqs_are_valid(vcpu)) { kvm_debug("incorrectly configured timer irqs\n"); return -EINVAL; diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 6e637d2b4cfb..04c44853b103 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -65,10 +65,6 @@ static bool vgic_present; static DEFINE_PER_CPU(unsigned char, kvm_arm_hardware_enabled); DEFINE_STATIC_KEY_FALSE(userspace_irqchip_in_use); -extern u64 kvm_nvhe_sym(__cpu_logical_map)[NR_CPUS]; -extern u32 kvm_nvhe_sym(kvm_host_psci_version); -extern struct psci_0_1_function_ids kvm_nvhe_sym(kvm_host_psci_0_1_function_ids); - int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) { return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE; @@ -584,11 +580,9 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu) * Map the VGIC hardware resources before running a vcpu the * first time on this VM. */ - if (unlikely(!vgic_ready(kvm))) { - ret = kvm_vgic_map_resources(kvm); - if (ret) - return ret; - } + ret = kvm_vgic_map_resources(kvm); + if (ret) + return ret; } else { /* * Tell the rest of the code that there are userspace irqchip @@ -1574,12 +1568,12 @@ static struct notifier_block hyp_init_cpu_pm_nb = { .notifier_call = hyp_init_cpu_pm_notifier, }; -static void __init hyp_cpu_pm_init(void) +static void hyp_cpu_pm_init(void) { if (!is_protected_kvm_enabled()) cpu_pm_register_notifier(&hyp_init_cpu_pm_nb); } -static void __init hyp_cpu_pm_exit(void) +static void hyp_cpu_pm_exit(void) { if (!is_protected_kvm_enabled()) cpu_pm_unregister_notifier(&hyp_init_cpu_pm_nb); @@ -1604,9 +1598,12 @@ static void init_cpu_logical_map(void) * allow any other CPUs from the `possible` set to boot. */ for_each_online_cpu(cpu) - kvm_nvhe_sym(__cpu_logical_map)[cpu] = cpu_logical_map(cpu); + hyp_cpu_logical_map[cpu] = cpu_logical_map(cpu); } +#define init_psci_0_1_impl_state(config, what) \ + config.psci_0_1_ ## what ## _implemented = psci_ops.what + static bool init_psci_relay(void) { /* @@ -1618,8 +1615,15 @@ static bool init_psci_relay(void) return false; } - kvm_nvhe_sym(kvm_host_psci_version) = psci_ops.get_version(); - kvm_nvhe_sym(kvm_host_psci_0_1_function_ids) = get_psci_0_1_function_ids(); + kvm_host_psci_config.version = psci_ops.get_version(); + + if (kvm_host_psci_config.version == PSCI_VERSION(0, 1)) { + kvm_host_psci_config.function_ids_0_1 = get_psci_0_1_function_ids(); + init_psci_0_1_impl_state(kvm_host_psci_config, cpu_suspend); + init_psci_0_1_impl_state(kvm_host_psci_config, cpu_on); + init_psci_0_1_impl_state(kvm_host_psci_config, cpu_off); + init_psci_0_1_impl_state(kvm_host_psci_config, migrate); + } return true; } diff --git a/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h b/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h index b1f60923a8fe..61716359035d 100644 --- a/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h +++ b/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h @@ -59,4 +59,13 @@ static inline void __adjust_pc(struct kvm_vcpu *vcpu) } } +/* + * Skip an instruction while host sysregs are live. + * Assumes host is always 64-bit. + */ +static inline void kvm_skip_host_instr(void) +{ + write_sysreg_el2(read_sysreg_el2(SYS_ELR) + 4, SYS_ELR); +} + #endif diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c index bde658d51404..a906f9e2ff34 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c @@ -157,11 +157,6 @@ static void default_host_smc_handler(struct kvm_cpu_context *host_ctxt) __kvm_hyp_host_forward_smc(host_ctxt); } -static void skip_host_instruction(void) -{ - write_sysreg_el2(read_sysreg_el2(SYS_ELR) + 4, SYS_ELR); -} - static void handle_host_smc(struct kvm_cpu_context *host_ctxt) { bool handled; @@ -170,11 +165,8 @@ static void handle_host_smc(struct kvm_cpu_context *host_ctxt) if (!handled) default_host_smc_handler(host_ctxt); - /* - * Unlike HVC, the return address of an SMC is the instruction's PC. - * Move the return address past the instruction. - */ - skip_host_instruction(); + /* SMC was trapped, move ELR past the current PC. */ + kvm_skip_host_instr(); } void handle_trap(struct kvm_cpu_context *host_ctxt) diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-smp.c b/arch/arm64/kvm/hyp/nvhe/hyp-smp.c index cbab0c6246e2..2997aa156d8e 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-smp.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-smp.c @@ -14,14 +14,14 @@ * Other CPUs should not be allowed to boot because their features were * not checked against the finalized system capabilities. */ -u64 __ro_after_init __cpu_logical_map[NR_CPUS] = { [0 ... NR_CPUS-1] = INVALID_HWID }; +u64 __ro_after_init hyp_cpu_logical_map[NR_CPUS] = { [0 ... NR_CPUS-1] = INVALID_HWID }; u64 cpu_logical_map(unsigned int cpu) { - if (cpu >= ARRAY_SIZE(__cpu_logical_map)) + if (cpu >= ARRAY_SIZE(hyp_cpu_logical_map)) hyp_panic(); - return __cpu_logical_map[cpu]; + return hyp_cpu_logical_map[cpu]; } unsigned long __hyp_per_cpu_offset(unsigned int cpu) diff --git a/arch/arm64/kvm/hyp/nvhe/psci-relay.c b/arch/arm64/kvm/hyp/nvhe/psci-relay.c index 08dc9de69314..e3947846ffcb 100644 --- a/arch/arm64/kvm/hyp/nvhe/psci-relay.c +++ b/arch/arm64/kvm/hyp/nvhe/psci-relay.c @@ -7,11 +7,8 @@ #include <asm/kvm_asm.h> #include <asm/kvm_hyp.h> #include <asm/kvm_mmu.h> -#include <kvm/arm_hypercalls.h> #include <linux/arm-smccc.h> #include <linux/kvm_host.h> -#include <linux/psci.h> -#include <kvm/arm_psci.h> #include <uapi/linux/psci.h> #include <nvhe/trap_handler.h> @@ -22,9 +19,8 @@ void kvm_hyp_cpu_resume(unsigned long r0); void __noreturn __host_enter(struct kvm_cpu_context *host_ctxt); /* Config options set by the host. */ -__ro_after_init u32 kvm_host_psci_version; -__ro_after_init struct psci_0_1_function_ids kvm_host_psci_0_1_function_ids; -__ro_after_init s64 hyp_physvirt_offset; +struct kvm_host_psci_config __ro_after_init kvm_host_psci_config; +s64 __ro_after_init hyp_physvirt_offset; #define __hyp_pa(x) ((phys_addr_t)((x)) + hyp_physvirt_offset) @@ -47,19 +43,16 @@ struct psci_boot_args { static DEFINE_PER_CPU(struct psci_boot_args, cpu_on_args) = PSCI_BOOT_ARGS_INIT; static DEFINE_PER_CPU(struct psci_boot_args, suspend_args) = PSCI_BOOT_ARGS_INIT; -static u64 get_psci_func_id(struct kvm_cpu_context *host_ctxt) -{ - DECLARE_REG(u64, func_id, host_ctxt, 0); - - return func_id; -} +#define is_psci_0_1(what, func_id) \ + (kvm_host_psci_config.psci_0_1_ ## what ## _implemented && \ + (func_id) == kvm_host_psci_config.function_ids_0_1.what) static bool is_psci_0_1_call(u64 func_id) { - return (func_id == kvm_host_psci_0_1_function_ids.cpu_suspend) || - (func_id == kvm_host_psci_0_1_function_ids.cpu_on) || - (func_id == kvm_host_psci_0_1_function_ids.cpu_off) || - (func_id == kvm_host_psci_0_1_function_ids.migrate); + return (is_psci_0_1(cpu_suspend, func_id) || + is_psci_0_1(cpu_on, func_id) || + is_psci_0_1(cpu_off, func_id) || + is_psci_0_1(migrate, func_id)); } static bool is_psci_0_2_call(u64 func_id) @@ -69,16 +62,6 @@ static bool is_psci_0_2_call(u64 func_id) (PSCI_0_2_FN64(0) <= func_id && func_id <= PSCI_0_2_FN64(31)); } -static bool is_psci_call(u64 func_id) -{ - switch (kvm_host_psci_version) { - case PSCI_VERSION(0, 1): - return is_psci_0_1_call(func_id); - default: - return is_psci_0_2_call(func_id); - } -} - static unsigned long psci_call(unsigned long fn, unsigned long arg0, unsigned long arg1, unsigned long arg2) { @@ -248,15 +231,14 @@ asmlinkage void __noreturn kvm_host_psci_cpu_entry(bool is_cpu_on) static unsigned long psci_0_1_handler(u64 func_id, struct kvm_cpu_context *host_ctxt) { - if ((func_id == kvm_host_psci_0_1_function_ids.cpu_off) || - (func_id == kvm_host_psci_0_1_function_ids.migrate)) + if (is_psci_0_1(cpu_off, func_id) || is_psci_0_1(migrate, func_id)) return psci_forward(host_ctxt); - else if (func_id == kvm_host_psci_0_1_function_ids.cpu_on) + if (is_psci_0_1(cpu_on, func_id)) return psci_cpu_on(func_id, host_ctxt); - else if (func_id == kvm_host_psci_0_1_function_ids.cpu_suspend) + if (is_psci_0_1(cpu_suspend, func_id)) return psci_cpu_suspend(func_id, host_ctxt); - else - return PSCI_RET_NOT_SUPPORTED; + + return PSCI_RET_NOT_SUPPORTED; } static unsigned long psci_0_2_handler(u64 func_id, struct kvm_cpu_context *host_ctxt) @@ -298,20 +280,23 @@ static unsigned long psci_1_0_handler(u64 func_id, struct kvm_cpu_context *host_ bool kvm_host_psci_handler(struct kvm_cpu_context *host_ctxt) { - u64 func_id = get_psci_func_id(host_ctxt); + DECLARE_REG(u64, func_id, host_ctxt, 0); unsigned long ret; - if (!is_psci_call(func_id)) - return false; - - switch (kvm_host_psci_version) { + switch (kvm_host_psci_config.version) { case PSCI_VERSION(0, 1): + if (!is_psci_0_1_call(func_id)) + return false; ret = psci_0_1_handler(func_id, host_ctxt); break; case PSCI_VERSION(0, 2): + if (!is_psci_0_2_call(func_id)) + return false; ret = psci_0_2_handler(func_id, host_ctxt); break; default: + if (!is_psci_0_2_call(func_id)) + return false; ret = psci_1_0_handler(func_id, host_ctxt); break; } diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index 398f6df1bbe4..4ad66a532e38 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -850,8 +850,6 @@ int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu) return -EINVAL; } - kvm_pmu_vcpu_reset(vcpu); - return 0; } diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 3313dedfa505..42ccc27fb684 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -594,6 +594,10 @@ static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { u64 pmcr, val; + /* No PMU available, PMCR_EL0 may UNDEF... */ + if (!kvm_arm_support_pmu_v3()) + return; + pmcr = read_sysreg(pmcr_el0); /* * Writable bits of PMCR_EL0 (ARMV8_PMU_PMCR_MASK) are reset to UNKNOWN @@ -919,7 +923,7 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, #define reg_to_encoding(x) \ sys_reg((u32)(x)->Op0, (u32)(x)->Op1, \ - (u32)(x)->CRn, (u32)(x)->CRm, (u32)(x)->Op2); + (u32)(x)->CRn, (u32)(x)->CRm, (u32)(x)->Op2) /* Silly macro to expand the DBG{BCR,BVR,WVR,WCR}n_EL1 registers in one go */ #define DBG_BCR_BVR_WCR_WVR_EL1(n) \ diff --git a/arch/arm64/kvm/va_layout.c b/arch/arm64/kvm/va_layout.c index d8cc51bd60bf..70fcd6a12fe1 100644 --- a/arch/arm64/kvm/va_layout.c +++ b/arch/arm64/kvm/va_layout.c @@ -34,17 +34,16 @@ static u64 __early_kern_hyp_va(u64 addr) } /* - * Store a hyp VA <-> PA offset into a hyp-owned variable. + * Store a hyp VA <-> PA offset into a EL2-owned variable. */ static void init_hyp_physvirt_offset(void) { - extern s64 kvm_nvhe_sym(hyp_physvirt_offset); u64 kern_va, hyp_va; /* Compute the offset from the hyp VA and PA of a random symbol. */ - kern_va = (u64)kvm_ksym_ref(__hyp_text_start); + kern_va = (u64)lm_alias(__hyp_text_start); hyp_va = __early_kern_hyp_va(kern_va); - CHOOSE_NVHE_SYM(hyp_physvirt_offset) = (s64)__pa(kern_va) - (s64)hyp_va; + hyp_physvirt_offset = (s64)__pa(kern_va) - (s64)hyp_va; } /* diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index 32e32d67a127..052917deb149 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -419,7 +419,8 @@ int vgic_lazy_init(struct kvm *kvm) * Map the MMIO regions depending on the VGIC model exposed to the guest * called on the first VCPU run. * Also map the virtual CPU interface into the VM. - * v2/v3 derivatives call vgic_init if not already done. + * v2 calls vgic_init() if not already done. + * v3 and derivatives return an error if the VGIC is not initialized. * vgic_ready() returns true if this function has succeeded. * @kvm: kvm struct pointer */ @@ -428,7 +429,13 @@ int kvm_vgic_map_resources(struct kvm *kvm) struct vgic_dist *dist = &kvm->arch.vgic; int ret = 0; + if (likely(vgic_ready(kvm))) + return 0; + mutex_lock(&kvm->lock); + if (vgic_ready(kvm)) + goto out; + if (!irqchip_in_kernel(kvm)) goto out; @@ -439,6 +446,8 @@ int kvm_vgic_map_resources(struct kvm *kvm) if (ret) __kvm_vgic_destroy(kvm); + else + dist->ready = true; out: mutex_unlock(&kvm->lock); diff --git a/arch/arm64/kvm/vgic/vgic-v2.c b/arch/arm64/kvm/vgic/vgic-v2.c index ebf53a4e1296..11934c2af2f4 100644 --- a/arch/arm64/kvm/vgic/vgic-v2.c +++ b/arch/arm64/kvm/vgic/vgic-v2.c @@ -306,20 +306,15 @@ int vgic_v2_map_resources(struct kvm *kvm) struct vgic_dist *dist = &kvm->arch.vgic; int ret = 0; - if (vgic_ready(kvm)) - goto out; - if (IS_VGIC_ADDR_UNDEF(dist->vgic_dist_base) || IS_VGIC_ADDR_UNDEF(dist->vgic_cpu_base)) { kvm_err("Need to set vgic cpu and dist addresses first\n"); - ret = -ENXIO; - goto out; + return -ENXIO; } if (!vgic_v2_check_base(dist->vgic_dist_base, dist->vgic_cpu_base)) { kvm_err("VGIC CPU and dist frames overlap\n"); - ret = -EINVAL; - goto out; + return -EINVAL; } /* @@ -329,13 +324,13 @@ int vgic_v2_map_resources(struct kvm *kvm) ret = vgic_init(kvm); if (ret) { kvm_err("Unable to initialize VGIC dynamic data structures\n"); - goto out; + return ret; } ret = vgic_register_dist_iodev(kvm, dist->vgic_dist_base, VGIC_V2); if (ret) { kvm_err("Unable to register VGIC MMIO regions\n"); - goto out; + return ret; } if (!static_branch_unlikely(&vgic_v2_cpuif_trap)) { @@ -344,14 +339,11 @@ int vgic_v2_map_resources(struct kvm *kvm) KVM_VGIC_V2_CPU_SIZE, true); if (ret) { kvm_err("Unable to remap VGIC CPU to VCPU\n"); - goto out; + return ret; } } - dist->ready = true; - -out: - return ret; + return 0; } DEFINE_STATIC_KEY_FALSE(vgic_v2_cpuif_trap); diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c index 9cdf39a94a63..52915b342351 100644 --- a/arch/arm64/kvm/vgic/vgic-v3.c +++ b/arch/arm64/kvm/vgic/vgic-v3.c @@ -500,29 +500,23 @@ int vgic_v3_map_resources(struct kvm *kvm) int ret = 0; int c; - if (vgic_ready(kvm)) - goto out; - kvm_for_each_vcpu(c, vcpu, kvm) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; if (IS_VGIC_ADDR_UNDEF(vgic_cpu->rd_iodev.base_addr)) { kvm_debug("vcpu %d redistributor base not set\n", c); - ret = -ENXIO; - goto out; + return -ENXIO; } } if (IS_VGIC_ADDR_UNDEF(dist->vgic_dist_base)) { kvm_err("Need to set vgic distributor addresses first\n"); - ret = -ENXIO; - goto out; + return -ENXIO; } if (!vgic_v3_check_base(kvm)) { kvm_err("VGIC redist and dist frames overlap\n"); - ret = -EINVAL; - goto out; + return -EINVAL; } /* @@ -530,22 +524,19 @@ int vgic_v3_map_resources(struct kvm *kvm) * the VGIC before we need to use it. */ if (!vgic_initialized(kvm)) { - ret = -EBUSY; - goto out; + return -EBUSY; } ret = vgic_register_dist_iodev(kvm, dist->vgic_dist_base, VGIC_V3); if (ret) { kvm_err("Unable to register VGICv3 dist MMIO regions\n"); - goto out; + return ret; } if (kvm_vgic_global_state.has_gicv4_1) vgic_v4_configure_vsgis(kvm); - dist->ready = true; -out: - return ret; + return 0; } DEFINE_STATIC_KEY_FALSE(vgic_v3_cpuif_trap); diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 3c40da479899..35d75c60e2b8 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -709,10 +709,11 @@ static int do_tag_check_fault(unsigned long far, unsigned int esr, struct pt_regs *regs) { /* - * The architecture specifies that bits 63:60 of FAR_EL1 are UNKNOWN for tag - * check faults. Mask them out now so that userspace doesn't see them. + * The architecture specifies that bits 63:60 of FAR_EL1 are UNKNOWN + * for tag check faults. Set them to corresponding bits in the untagged + * address. */ - far &= (1UL << 60) - 1; + far = (__untagged_addr(far) & ~MTE_TAG_MASK) | (far & MTE_TAG_MASK); do_bad_area(far, esr, regs); return 0; } diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 75addb36354a..709d98fea90c 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -53,13 +53,13 @@ s64 memstart_addr __ro_after_init = -1; EXPORT_SYMBOL(memstart_addr); /* - * We create both ZONE_DMA and ZONE_DMA32. ZONE_DMA covers the first 1G of - * memory as some devices, namely the Raspberry Pi 4, have peripherals with - * this limited view of the memory. ZONE_DMA32 will cover the rest of the 32 - * bit addressable memory area. + * If the corresponding config options are enabled, we create both ZONE_DMA + * and ZONE_DMA32. By default ZONE_DMA covers the 32-bit addressable memory + * unless restricted on specific platforms (e.g. 30-bit on Raspberry Pi 4). + * In such case, ZONE_DMA32 covers the rest of the 32-bit addressable memory, + * otherwise it is empty. */ phys_addr_t arm64_dma_phys_limit __ro_after_init; -static phys_addr_t arm64_dma32_phys_limit __ro_after_init; #ifdef CONFIG_KEXEC_CORE /* @@ -84,7 +84,7 @@ static void __init reserve_crashkernel(void) if (crash_base == 0) { /* Current arm64 boot protocol requires 2MB alignment */ - crash_base = memblock_find_in_range(0, arm64_dma32_phys_limit, + crash_base = memblock_find_in_range(0, arm64_dma_phys_limit, crash_size, SZ_2M); if (crash_base == 0) { pr_warn("cannot allocate crashkernel (size:0x%llx)\n", @@ -196,6 +196,7 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) unsigned long max_zone_pfns[MAX_NR_ZONES] = {0}; unsigned int __maybe_unused acpi_zone_dma_bits; unsigned int __maybe_unused dt_zone_dma_bits; + phys_addr_t __maybe_unused dma32_phys_limit = max_zone_phys(32); #ifdef CONFIG_ZONE_DMA acpi_zone_dma_bits = fls64(acpi_iort_dma_get_max_cpu_address()); @@ -205,8 +206,12 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) max_zone_pfns[ZONE_DMA] = PFN_DOWN(arm64_dma_phys_limit); #endif #ifdef CONFIG_ZONE_DMA32 - max_zone_pfns[ZONE_DMA32] = PFN_DOWN(arm64_dma32_phys_limit); + max_zone_pfns[ZONE_DMA32] = PFN_DOWN(dma32_phys_limit); + if (!arm64_dma_phys_limit) + arm64_dma_phys_limit = dma32_phys_limit; #endif + if (!arm64_dma_phys_limit) + arm64_dma_phys_limit = PHYS_MASK + 1; max_zone_pfns[ZONE_NORMAL] = max; free_area_init(max_zone_pfns); @@ -394,16 +399,9 @@ void __init arm64_memblock_init(void) early_init_fdt_scan_reserved_mem(); - if (IS_ENABLED(CONFIG_ZONE_DMA32)) - arm64_dma32_phys_limit = max_zone_phys(32); - else - arm64_dma32_phys_limit = PHYS_MASK + 1; - reserve_elfcorehdr(); high_memory = __va(memblock_end_of_DRAM() - 1) + 1; - - dma_contiguous_reserve(arm64_dma32_phys_limit); } void __init bootmem_init(void) @@ -439,6 +437,11 @@ void __init bootmem_init(void) zone_sizes_init(min, max); /* + * Reserve the CMA area after arm64_dma_phys_limit was initialised. + */ + dma_contiguous_reserve(arm64_dma_phys_limit); + + /* * request_standard_resources() depends on crashkernel's memory being * reserved, so do it here. */ @@ -455,7 +458,7 @@ void __init bootmem_init(void) void __init mem_init(void) { if (swiotlb_force == SWIOTLB_FORCE || - max_pfn > PFN_DOWN(arm64_dma_phys_limit ? : arm64_dma32_phys_limit)) + max_pfn > PFN_DOWN(arm64_dma_phys_limit)) swiotlb_init(1); else swiotlb_force = SWIOTLB_NO_FORCE; diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 37a54b57178a..1f7ee8c8b7b8 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -46,7 +46,7 @@ #endif #ifdef CONFIG_KASAN_HW_TAGS -#define TCR_KASAN_HW_FLAGS SYS_TCR_EL1_TCMA1 | TCR_TBI1 +#define TCR_KASAN_HW_FLAGS SYS_TCR_EL1_TCMA1 | TCR_TBI1 | TCR_TBID1 #else #define TCR_KASAN_HW_FLAGS 0 #endif diff --git a/arch/csky/include/asm/Kbuild b/arch/csky/include/asm/Kbuild index 93372255984d..cc24bb8e539f 100644 --- a/arch/csky/include/asm/Kbuild +++ b/arch/csky/include/asm/Kbuild @@ -2,7 +2,6 @@ generic-y += asm-offsets.h generic-y += gpio.h generic-y += kvm_para.h -generic-y += local64.h generic-y += qrwlock.h generic-y += user.h generic-y += vmlinux.lds.h diff --git a/arch/h8300/include/asm/Kbuild b/arch/h8300/include/asm/Kbuild index ddf04f32b546..60ee7f0d60a8 100644 --- a/arch/h8300/include/asm/Kbuild +++ b/arch/h8300/include/asm/Kbuild @@ -2,7 +2,6 @@ generic-y += asm-offsets.h generic-y += extable.h generic-y += kvm_para.h -generic-y += local64.h generic-y += mcs_spinlock.h generic-y += parport.h generic-y += spinlock.h diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild index 373964bb177e..3ece3c93fe08 100644 --- a/arch/hexagon/include/asm/Kbuild +++ b/arch/hexagon/include/asm/Kbuild @@ -2,5 +2,4 @@ generic-y += extable.h generic-y += iomap.h generic-y += kvm_para.h -generic-y += local64.h generic-y += mcs_spinlock.h diff --git a/arch/ia64/include/asm/local64.h b/arch/ia64/include/asm/local64.h deleted file mode 100644 index 36c93b5cc239..000000000000 --- a/arch/ia64/include/asm/local64.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/local64.h> diff --git a/arch/ia64/include/asm/sparsemem.h b/arch/ia64/include/asm/sparsemem.h index dd8c166ffd7b..42ed5248fae9 100644 --- a/arch/ia64/include/asm/sparsemem.h +++ b/arch/ia64/include/asm/sparsemem.h @@ -3,6 +3,7 @@ #define _ASM_IA64_SPARSEMEM_H #ifdef CONFIG_SPARSEMEM +#include <asm/page.h> /* * SECTION_SIZE_BITS 2^N: how big each section will be * MAX_PHYSMEM_BITS 2^N: how much memory we can have in that space diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index 9b5acf8fb092..e76386a3479e 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -536,7 +536,7 @@ virtual_memmap_init(u64 start, u64 end, void *arg) if (map_start < map_end) memmap_init_zone((unsigned long)(map_end - map_start), - args->nid, args->zone, page_to_pfn(map_start), + args->nid, args->zone, page_to_pfn(map_start), page_to_pfn(map_end), MEMINIT_EARLY, NULL, MIGRATE_MOVABLE); return 0; } @@ -546,7 +546,7 @@ memmap_init (unsigned long size, int nid, unsigned long zone, unsigned long start_pfn) { if (!vmem_map) { - memmap_init_zone(size, nid, zone, start_pfn, + memmap_init_zone(size, nid, zone, start_pfn, start_pfn + size, MEMINIT_EARLY, NULL, MIGRATE_MOVABLE); } else { struct page *start; diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild index 1bff55aa2d54..0dbf9c5c6fae 100644 --- a/arch/m68k/include/asm/Kbuild +++ b/arch/m68k/include/asm/Kbuild @@ -2,6 +2,5 @@ generated-y += syscall_table.h generic-y += extable.h generic-y += kvm_para.h -generic-y += local64.h generic-y += mcs_spinlock.h generic-y += spinlock.h diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild index 63bce836b9f1..29b0e557aa7c 100644 --- a/arch/microblaze/include/asm/Kbuild +++ b/arch/microblaze/include/asm/Kbuild @@ -2,7 +2,6 @@ generated-y += syscall_table.h generic-y += extable.h generic-y += kvm_para.h -generic-y += local64.h generic-y += mcs_spinlock.h generic-y += parport.h generic-y += syscalls.h diff --git a/arch/mips/boot/compressed/decompress.c b/arch/mips/boot/compressed/decompress.c index c61c641674e6..e3946b06e840 100644 --- a/arch/mips/boot/compressed/decompress.c +++ b/arch/mips/boot/compressed/decompress.c @@ -13,6 +13,7 @@ #include <linux/libfdt.h> #include <asm/addrspace.h> +#include <asm/unaligned.h> /* * These two variables specify the free mem region @@ -117,7 +118,7 @@ void decompress_kernel(unsigned long boot_heap_start) dtb_size = fdt_totalsize((void *)&__appended_dtb); /* last four bytes is always image size in little endian */ - image_size = le32_to_cpup((void *)&__image_end - 4); + image_size = get_unaligned_le32((void *)&__image_end - 4); /* copy dtb to where the booted kernel will expect it */ memcpy((void *)VMLINUX_LOAD_ADDRESS_ULL + image_size, diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c index bd47e15d02c7..be5d4afcd30f 100644 --- a/arch/mips/cavium-octeon/octeon-irq.c +++ b/arch/mips/cavium-octeon/octeon-irq.c @@ -1444,7 +1444,7 @@ static void octeon_irq_setup_secondary_ciu2(void) static int __init octeon_irq_init_ciu( struct device_node *ciu_node, struct device_node *parent) { - unsigned int i, r; + int i, r; struct irq_chip *chip; struct irq_chip *chip_edge; struct irq_chip *chip_mbox; diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild index 198b3bafdac9..95b4fa7bd0d1 100644 --- a/arch/mips/include/asm/Kbuild +++ b/arch/mips/include/asm/Kbuild @@ -6,7 +6,6 @@ generated-y += syscall_table_64_n64.h generated-y += syscall_table_64_o32.h generic-y += export.h generic-y += kvm_para.h -generic-y += local64.h generic-y += mcs_spinlock.h generic-y += parport.h generic-y += qrwlock.h diff --git a/arch/mips/include/asm/highmem.h b/arch/mips/include/asm/highmem.h index 19edf8e69971..292d0425717f 100644 --- a/arch/mips/include/asm/highmem.h +++ b/arch/mips/include/asm/highmem.h @@ -51,6 +51,7 @@ extern void kmap_flush_tlb(unsigned long addr); #define flush_cache_kmaps() BUG_ON(cpu_has_dc_aliases) +#define arch_kmap_local_set_pte(mm, vaddr, ptep, ptev) set_pte(ptep, ptev) #define arch_kmap_local_post_map(vaddr, pteval) local_flush_tlb_one(vaddr) #define arch_kmap_local_post_unmap(vaddr) local_flush_tlb_one(vaddr) diff --git a/arch/mips/kernel/binfmt_elfn32.c b/arch/mips/kernel/binfmt_elfn32.c index 6ee3f7218c67..c4441416e96b 100644 --- a/arch/mips/kernel/binfmt_elfn32.c +++ b/arch/mips/kernel/binfmt_elfn32.c @@ -103,4 +103,11 @@ jiffies_to_old_timeval32(unsigned long jiffies, struct old_timeval32 *value) #undef ns_to_kernel_old_timeval #define ns_to_kernel_old_timeval ns_to_old_timeval32 +/* + * Some data types as stored in coredump. + */ +#define user_long_t compat_long_t +#define user_siginfo_t compat_siginfo_t +#define copy_siginfo_to_external copy_siginfo_to_external32 + #include "../../../fs/binfmt_elf.c" diff --git a/arch/mips/kernel/binfmt_elfo32.c b/arch/mips/kernel/binfmt_elfo32.c index 6dd103d3cebb..7b2a23f48c1a 100644 --- a/arch/mips/kernel/binfmt_elfo32.c +++ b/arch/mips/kernel/binfmt_elfo32.c @@ -106,4 +106,11 @@ jiffies_to_old_timeval32(unsigned long jiffies, struct old_timeval32 *value) #undef ns_to_kernel_old_timeval #define ns_to_kernel_old_timeval ns_to_old_timeval32 +/* + * Some data types as stored in coredump. + */ +#define user_long_t compat_long_t +#define user_siginfo_t compat_siginfo_t +#define copy_siginfo_to_external copy_siginfo_to_external32 + #include "../../../fs/binfmt_elf.c" diff --git a/arch/mips/kernel/relocate.c b/arch/mips/kernel/relocate.c index 47aeb3350a76..0e365b7c742d 100644 --- a/arch/mips/kernel/relocate.c +++ b/arch/mips/kernel/relocate.c @@ -187,8 +187,14 @@ static int __init relocate_exception_table(long offset) static inline __init unsigned long rotate_xor(unsigned long hash, const void *area, size_t size) { - size_t i; - unsigned long *ptr = (unsigned long *)area; + const typeof(hash) *ptr = PTR_ALIGN(area, sizeof(hash)); + size_t diff, i; + + diff = (void *)ptr - area; + if (unlikely(size < diff + sizeof(hash))) + return hash; + + size = ALIGN_DOWN(size - diff, sizeof(hash)); for (i = 0; i < size / sizeof(hash); i++) { /* Rotate by odd number of bits and XOR. */ diff --git a/arch/nds32/include/asm/Kbuild b/arch/nds32/include/asm/Kbuild index ff1e94299317..82a4453c9c2d 100644 --- a/arch/nds32/include/asm/Kbuild +++ b/arch/nds32/include/asm/Kbuild @@ -4,6 +4,5 @@ generic-y += cmpxchg.h generic-y += export.h generic-y += gpio.h generic-y += kvm_para.h -generic-y += local64.h generic-y += parport.h generic-y += user.h diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild index 442f3d3bcd90..ca5987e11053 100644 --- a/arch/openrisc/include/asm/Kbuild +++ b/arch/openrisc/include/asm/Kbuild @@ -1,7 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 generic-y += extable.h generic-y += kvm_para.h -generic-y += local64.h generic-y += mcs_spinlock.h generic-y += qspinlock_types.h generic-y += qspinlock.h diff --git a/arch/openrisc/include/asm/io.h b/arch/openrisc/include/asm/io.h index 7d6b4a77b379..c298061c70a7 100644 --- a/arch/openrisc/include/asm/io.h +++ b/arch/openrisc/include/asm/io.h @@ -31,7 +31,7 @@ void __iomem *ioremap(phys_addr_t offset, unsigned long size); #define iounmap iounmap -extern void iounmap(void *addr); +extern void iounmap(void __iomem *addr); #include <asm-generic/io.h> diff --git a/arch/openrisc/mm/ioremap.c b/arch/openrisc/mm/ioremap.c index 5aed97a18bac..daae13a76743 100644 --- a/arch/openrisc/mm/ioremap.c +++ b/arch/openrisc/mm/ioremap.c @@ -77,7 +77,7 @@ void __iomem *__ref ioremap(phys_addr_t addr, unsigned long size) } EXPORT_SYMBOL(ioremap); -void iounmap(void *addr) +void iounmap(void __iomem *addr) { /* If the page is from the fixmap pool then we just clear out * the fixmap mapping. diff --git a/arch/parisc/include/asm/Kbuild b/arch/parisc/include/asm/Kbuild index f16c4db80116..4406475a2304 100644 --- a/arch/parisc/include/asm/Kbuild +++ b/arch/parisc/include/asm/Kbuild @@ -3,6 +3,5 @@ generated-y += syscall_table_32.h generated-y += syscall_table_64.h generated-y += syscall_table_c32.h generic-y += kvm_para.h -generic-y += local64.h generic-y += mcs_spinlock.h generic-y += user.h diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild index 90cd5c53af66..e1f9b4ea1c53 100644 --- a/arch/powerpc/include/asm/Kbuild +++ b/arch/powerpc/include/asm/Kbuild @@ -5,7 +5,6 @@ generated-y += syscall_table_c32.h generated-y += syscall_table_spu.h generic-y += export.h generic-y += kvm_types.h -generic-y += local64.h generic-y += mcs_spinlock.h generic-y += qrwlock.h generic-y += vtime.h diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index 1d32b174ab6a..c1a8aac01cf9 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -63,6 +63,12 @@ nop; \ nop; +#define SCV_ENTRY_FLUSH_SLOT \ + SCV_ENTRY_FLUSH_FIXUP_SECTION; \ + nop; \ + nop; \ + nop; + /* * r10 must be free to use, r13 must be paca */ @@ -71,6 +77,13 @@ ENTRY_FLUSH_SLOT /* + * r10, ctr must be free to use, r13 must be paca + */ +#define SCV_INTERRUPT_TO_KERNEL \ + STF_ENTRY_BARRIER_SLOT; \ + SCV_ENTRY_FLUSH_SLOT + +/* * Macros for annotating the expected destination of (h)rfid * * The nop instructions allow us to insert one or more instructions to flush the diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h index f6d2acb57425..ac605fc369c4 100644 --- a/arch/powerpc/include/asm/feature-fixups.h +++ b/arch/powerpc/include/asm/feature-fixups.h @@ -240,6 +240,14 @@ label##3: \ FTR_ENTRY_OFFSET 957b-958b; \ .popsection; +#define SCV_ENTRY_FLUSH_FIXUP_SECTION \ +957: \ + .pushsection __scv_entry_flush_fixup,"a"; \ + .align 2; \ +958: \ + FTR_ENTRY_OFFSET 957b-958b; \ + .popsection; + #define RFI_FLUSH_FIXUP_SECTION \ 951: \ .pushsection __rfi_flush_fixup,"a"; \ @@ -273,10 +281,12 @@ label##3: \ extern long stf_barrier_fallback; extern long entry_flush_fallback; +extern long scv_entry_flush_fallback; extern long __start___stf_entry_barrier_fixup, __stop___stf_entry_barrier_fixup; extern long __start___stf_exit_barrier_fixup, __stop___stf_exit_barrier_fixup; extern long __start___uaccess_flush_fixup, __stop___uaccess_flush_fixup; extern long __start___entry_flush_fixup, __stop___entry_flush_fixup; +extern long __start___scv_entry_flush_fixup, __stop___scv_entry_flush_fixup; extern long __start___rfi_flush_fixup, __stop___rfi_flush_fixup; extern long __start___barrier_nospec_fixup, __stop___barrier_nospec_fixup; extern long __start__btb_flush_fixup, __stop__btb_flush_fixup; diff --git a/arch/powerpc/include/asm/highmem.h b/arch/powerpc/include/asm/highmem.h index 80a5ae771c65..c0fcd1bbdba9 100644 --- a/arch/powerpc/include/asm/highmem.h +++ b/arch/powerpc/include/asm/highmem.h @@ -58,6 +58,8 @@ extern pte_t *pkmap_page_table; #define flush_cache_kmaps() flush_cache_all() +#define arch_kmap_local_set_pte(mm, vaddr, ptep, ptev) \ + __set_pte_at(mm, vaddr, ptep, ptev, 1) #define arch_kmap_local_post_map(vaddr, pteval) \ local_flush_tlb_page(NULL, vaddr) #define arch_kmap_local_post_unmap(vaddr) \ diff --git a/arch/powerpc/include/asm/vdso/gettimeofday.h b/arch/powerpc/include/asm/vdso/gettimeofday.h index 81671aa365b3..77c635c2c90d 100644 --- a/arch/powerpc/include/asm/vdso/gettimeofday.h +++ b/arch/powerpc/include/asm/vdso/gettimeofday.h @@ -103,6 +103,8 @@ int gettimeofday_fallback(struct __kernel_old_timeval *_tv, struct timezone *_tz return do_syscall_2(__NR_gettimeofday, (unsigned long)_tv, (unsigned long)_tz); } +#ifdef __powerpc64__ + static __always_inline int clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) { @@ -115,11 +117,23 @@ int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) return do_syscall_2(__NR_clock_getres, _clkid, (unsigned long)_ts); } -#ifdef CONFIG_VDSO32 +#else #define BUILD_VDSO32 1 static __always_inline +int clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) +{ + return do_syscall_2(__NR_clock_gettime64, _clkid, (unsigned long)_ts); +} + +static __always_inline +int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) +{ + return do_syscall_2(__NR_clock_getres_time64, _clkid, (unsigned long)_ts); +} + +static __always_inline int clock_gettime32_fallback(clockid_t _clkid, struct old_timespec32 *_ts) { return do_syscall_2(__NR_clock_gettime, _clkid, (unsigned long)_ts); diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index aa1af139d947..33ddfeef4fe9 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -75,7 +75,7 @@ BEGIN_FTR_SECTION bne .Ltabort_syscall END_FTR_SECTION_IFSET(CPU_FTR_TM) #endif - INTERRUPT_TO_KERNEL + SCV_INTERRUPT_TO_KERNEL mr r10,r1 ld r1,PACAKSAVE(r13) std r10,0(r1) diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index e02ad6fefa46..6e53f7638737 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -2993,6 +2993,25 @@ TRAMP_REAL_BEGIN(entry_flush_fallback) ld r11,PACA_EXRFI+EX_R11(r13) blr +/* + * The SCV entry flush happens with interrupts enabled, so it must disable + * to prevent EXRFI being clobbered by NMIs (e.g., soft_nmi_common). r10 + * (containing LR) does not need to be preserved here because scv entry + * puts 0 in the pt_regs, CTR can be clobbered for the same reason. + */ +TRAMP_REAL_BEGIN(scv_entry_flush_fallback) + li r10,0 + mtmsrd r10,1 + lbz r10,PACAIRQHAPPENED(r13) + ori r10,r10,PACA_IRQ_HARD_DIS + stb r10,PACAIRQHAPPENED(r13) + std r11,PACA_EXRFI+EX_R11(r13) + L1D_DISPLACEMENT_FLUSH + ld r11,PACA_EXRFI+EX_R11(r13) + li r10,MSR_RI + mtmsrd r10,1 + blr + TRAMP_REAL_BEGIN(rfi_flush_fallback) SET_SCRATCH0(r13); GET_PACA(r13); diff --git a/arch/powerpc/kernel/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S index 349bf3f0c3af..858fbc8b19f3 100644 --- a/arch/powerpc/kernel/head_book3s_32.S +++ b/arch/powerpc/kernel/head_book3s_32.S @@ -260,10 +260,19 @@ __secondary_hold_acknowledge: MachineCheck: EXCEPTION_PROLOG_0 #ifdef CONFIG_PPC_CHRP +#ifdef CONFIG_VMAP_STACK + mtspr SPRN_SPRG_SCRATCH2,r1 + mfspr r1, SPRN_SPRG_THREAD + lwz r1, RTAS_SP(r1) + cmpwi cr1, r1, 0 + bne cr1, 7f + mfspr r1, SPRN_SPRG_SCRATCH2 +#else mfspr r11, SPRN_SPRG_THREAD lwz r11, RTAS_SP(r11) cmpwi cr1, r11, 0 bne cr1, 7f +#endif #endif /* CONFIG_PPC_CHRP */ EXCEPTION_PROLOG_1 for_rtas=1 7: EXCEPTION_PROLOG_2 diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 0318ba436f34..72fa3c00229a 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -85,7 +85,7 @@ SECTIONS ALIGN_FUNCTION(); #endif /* careful! __ftr_alt_* sections need to be close to .text */ - *(.text.hot TEXT_MAIN .text.fixup .text.unlikely .fixup __ftr_alt_* .ref.text); + *(.text.hot .text.hot.* TEXT_MAIN .text.fixup .text.unlikely .text.unlikely.* .fixup __ftr_alt_* .ref.text); #ifdef CONFIG_PPC64 *(.tramp.ftrace.text); #endif @@ -146,6 +146,13 @@ SECTIONS } . = ALIGN(8); + __scv_entry_flush_fixup : AT(ADDR(__scv_entry_flush_fixup) - LOAD_OFFSET) { + __start___scv_entry_flush_fixup = .; + *(__scv_entry_flush_fixup) + __stop___scv_entry_flush_fixup = .; + } + + . = ALIGN(8); __stf_exit_barrier_fixup : AT(ADDR(__stf_exit_barrier_fixup) - LOAD_OFFSET) { __start___stf_exit_barrier_fixup = .; *(__stf_exit_barrier_fixup) @@ -187,6 +194,12 @@ SECTIONS .init.text : AT(ADDR(.init.text) - LOAD_OFFSET) { _sinittext = .; INIT_TEXT + + /* + *.init.text might be RO so we must ensure this section ends on + * a page boundary. + */ + . = ALIGN(PAGE_SIZE); _einittext = .; #ifdef CONFIG_PPC64 *(.tramp.ftrace.init); @@ -200,6 +213,8 @@ SECTIONS EXIT_TEXT } + . = ALIGN(PAGE_SIZE); + INIT_DATA_SECTION(16) . = ALIGN(8); diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c index 47821055b94c..1fd31b4b0e13 100644 --- a/arch/powerpc/lib/feature-fixups.c +++ b/arch/powerpc/lib/feature-fixups.c @@ -290,9 +290,6 @@ void do_entry_flush_fixups(enum l1d_flush_type types) long *start, *end; int i; - start = PTRRELOC(&__start___entry_flush_fixup); - end = PTRRELOC(&__stop___entry_flush_fixup); - instrs[0] = 0x60000000; /* nop */ instrs[1] = 0x60000000; /* nop */ instrs[2] = 0x60000000; /* nop */ @@ -312,6 +309,8 @@ void do_entry_flush_fixups(enum l1d_flush_type types) if (types & L1D_FLUSH_MTTRIG) instrs[i++] = 0x7c12dba6; /* mtspr TRIG2,r0 (SPR #882) */ + start = PTRRELOC(&__start___entry_flush_fixup); + end = PTRRELOC(&__stop___entry_flush_fixup); for (i = 0; start < end; start++, i++) { dest = (void *)start + *start; @@ -328,6 +327,25 @@ void do_entry_flush_fixups(enum l1d_flush_type types) patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2])); } + start = PTRRELOC(&__start___scv_entry_flush_fixup); + end = PTRRELOC(&__stop___scv_entry_flush_fixup); + for (; start < end; start++, i++) { + dest = (void *)start + *start; + + pr_devel("patching dest %lx\n", (unsigned long)dest); + + patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0])); + + if (types == L1D_FLUSH_FALLBACK) + patch_branch((struct ppc_inst *)(dest + 1), (unsigned long)&scv_entry_flush_fallback, + BRANCH_SET_LINK); + else + patch_instruction((struct ppc_inst *)(dest + 1), ppc_inst(instrs[1])); + + patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2])); + } + + printk(KERN_DEBUG "entry-flush: patched %d locations (%s flush)\n", i, (types == L1D_FLUSH_NONE) ? "no" : (types == L1D_FLUSH_FALLBACK) ? "fallback displacement" : diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 81b76d44725d..e9e2c1f0a690 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -137,7 +137,7 @@ config PA_BITS config PAGE_OFFSET hex - default 0xC0000000 if 32BIT && MAXPHYSMEM_2GB + default 0xC0000000 if 32BIT && MAXPHYSMEM_1GB default 0x80000000 if 64BIT && !MMU default 0xffffffff80000000 if 64BIT && MAXPHYSMEM_2GB default 0xffffffe000000000 if 64BIT && MAXPHYSMEM_128GB @@ -247,10 +247,12 @@ config MODULE_SECTIONS choice prompt "Maximum Physical Memory" - default MAXPHYSMEM_2GB if 32BIT + default MAXPHYSMEM_1GB if 32BIT default MAXPHYSMEM_2GB if 64BIT && CMODEL_MEDLOW default MAXPHYSMEM_128GB if 64BIT && CMODEL_MEDANY + config MAXPHYSMEM_1GB + bool "1GiB" config MAXPHYSMEM_2GB bool "2GiB" config MAXPHYSMEM_128GB diff --git a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts index 4a2729f5ca3f..24d75a146e02 100644 --- a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts +++ b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts @@ -88,7 +88,9 @@ phy-mode = "gmii"; phy-handle = <&phy0>; phy0: ethernet-phy@0 { + compatible = "ethernet-phy-id0007.0771"; reg = <0>; + reset-gpios = <&gpio 12 GPIO_ACTIVE_LOW>; }; }; diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index d222d353d86d..8c3d1e451703 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -64,6 +64,8 @@ CONFIG_HW_RANDOM=y CONFIG_HW_RANDOM_VIRTIO=y CONFIG_SPI=y CONFIG_SPI_SIFIVE=y +CONFIG_GPIOLIB=y +CONFIG_GPIO_SIFIVE=y # CONFIG_PTP_1588_CLOCK is not set CONFIG_POWER_RESET=y CONFIG_DRM=y diff --git a/arch/riscv/include/asm/Kbuild b/arch/riscv/include/asm/Kbuild index 59dd7be55005..445ccc97305a 100644 --- a/arch/riscv/include/asm/Kbuild +++ b/arch/riscv/include/asm/Kbuild @@ -3,6 +3,5 @@ generic-y += early_ioremap.h generic-y += extable.h generic-y += flat.h generic-y += kvm_para.h -generic-y += local64.h generic-y += user.h generic-y += vmlinux.lds.h diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 41a72861987c..251e1db088fa 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -99,7 +99,6 @@ | _PAGE_DIRTY) #define PAGE_KERNEL __pgprot(_PAGE_KERNEL) -#define PAGE_KERNEL_EXEC __pgprot(_PAGE_KERNEL | _PAGE_EXEC) #define PAGE_KERNEL_READ __pgprot(_PAGE_KERNEL & ~_PAGE_WRITE) #define PAGE_KERNEL_EXEC __pgprot(_PAGE_KERNEL | _PAGE_EXEC) #define PAGE_KERNEL_READ_EXEC __pgprot((_PAGE_KERNEL & ~_PAGE_WRITE) \ diff --git a/arch/riscv/include/asm/vdso.h b/arch/riscv/include/asm/vdso.h index 8454f746bbfd..1453a2f563bc 100644 --- a/arch/riscv/include/asm/vdso.h +++ b/arch/riscv/include/asm/vdso.h @@ -10,7 +10,7 @@ #include <linux/types.h> -#ifndef GENERIC_TIME_VSYSCALL +#ifndef CONFIG_GENERIC_TIME_VSYSCALL struct vdso_data { }; #endif diff --git a/arch/riscv/kernel/cacheinfo.c b/arch/riscv/kernel/cacheinfo.c index de59dd457b41..d86781357044 100644 --- a/arch/riscv/kernel/cacheinfo.c +++ b/arch/riscv/kernel/cacheinfo.c @@ -26,7 +26,16 @@ cache_get_priv_group(struct cacheinfo *this_leaf) static struct cacheinfo *get_cacheinfo(u32 level, enum cache_type type) { - struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(smp_processor_id()); + /* + * Using raw_smp_processor_id() elides a preemptability check, but this + * is really indicative of a larger problem: the cacheinfo UABI assumes + * that cores have a homonogenous view of the cache hierarchy. That + * happens to be the case for the current set of RISC-V systems, but + * likely won't be true in general. Since there's no way to provide + * correct information for these systems via the current UABI we're + * just eliding the check for now. + */ + struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(raw_smp_processor_id()); struct cacheinfo *this_leaf; int index; diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index 524d918f3601..744f3209c48d 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -124,15 +124,15 @@ skip_context_tracking: REG_L a1, (a1) jr a1 1: -#ifdef CONFIG_TRACE_IRQFLAGS - call trace_hardirqs_on -#endif /* * Exceptions run with interrupts enabled or disabled depending on the * state of SR_PIE in m/sstatus. */ andi t0, s1, SR_PIE beqz t0, 1f +#ifdef CONFIG_TRACE_IRQFLAGS + call trace_hardirqs_on +#endif csrs CSR_STATUS, SR_IE 1: @@ -155,6 +155,15 @@ skip_context_tracking: tail do_trap_unknown handle_syscall: +#ifdef CONFIG_RISCV_M_MODE + /* + * When running is M-Mode (no MMU config), MPIE does not get set. + * As a result, we need to force enable interrupts here because + * handle_exception did not do set SR_IE as it always sees SR_PIE + * being cleared. + */ + csrs CSR_STATUS, SR_IE +#endif #if defined(CONFIG_TRACE_IRQFLAGS) || defined(CONFIG_CONTEXT_TRACKING) /* Recover a0 - a7 for system calls */ REG_L a0, PT_A0(sp) @@ -186,14 +195,7 @@ check_syscall_nr: * Syscall number held in a7. * If syscall number is above allowed value, redirect to ni_syscall. */ - bge a7, t0, 1f - /* - * Check if syscall is rejected by tracer, i.e., a7 == -1. - * If yes, we pretend it was executed. - */ - li t1, -1 - beq a7, t1, ret_from_syscall_rejected - blt a7, t1, 1f + bgeu a7, t0, 1f /* Call syscall */ la s0, sys_call_table slli t0, a7, RISCV_LGPTR diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 1d85e9bf783c..3fa3f26dde85 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -127,7 +127,9 @@ static void __init init_resources(void) { struct memblock_region *region = NULL; struct resource *res = NULL; - int ret = 0; + struct resource *mem_res = NULL; + size_t mem_res_sz = 0; + int ret = 0, i = 0; code_res.start = __pa_symbol(_text); code_res.end = __pa_symbol(_etext) - 1; @@ -145,16 +147,17 @@ static void __init init_resources(void) bss_res.end = __pa_symbol(__bss_stop) - 1; bss_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; + mem_res_sz = (memblock.memory.cnt + memblock.reserved.cnt) * sizeof(*mem_res); + mem_res = memblock_alloc(mem_res_sz, SMP_CACHE_BYTES); + if (!mem_res) + panic("%s: Failed to allocate %zu bytes\n", __func__, mem_res_sz); /* * Start by adding the reserved regions, if they overlap * with /memory regions, insert_resource later on will take * care of it. */ for_each_reserved_mem_region(region) { - res = memblock_alloc(sizeof(struct resource), SMP_CACHE_BYTES); - if (!res) - panic("%s: Failed to allocate %zu bytes\n", __func__, - sizeof(struct resource)); + res = &mem_res[i++]; res->name = "Reserved"; res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; @@ -171,8 +174,10 @@ static void __init init_resources(void) * Ignore any other reserved regions within * system memory. */ - if (memblock_is_memory(res->start)) + if (memblock_is_memory(res->start)) { + memblock_free((phys_addr_t) res, sizeof(struct resource)); continue; + } ret = add_resource(&iomem_resource, res); if (ret < 0) @@ -181,10 +186,7 @@ static void __init init_resources(void) /* Add /memory regions to the resource tree */ for_each_mem_region(region) { - res = memblock_alloc(sizeof(struct resource), SMP_CACHE_BYTES); - if (!res) - panic("%s: Failed to allocate %zu bytes\n", __func__, - sizeof(struct resource)); + res = &mem_res[i++]; if (unlikely(memblock_is_nomap(region))) { res->name = "Reserved"; @@ -205,9 +207,9 @@ static void __init init_resources(void) return; error: - memblock_free((phys_addr_t) res, sizeof(struct resource)); /* Better an empty resource tree than an inconsistent one */ release_child_resources(&iomem_resource); + memblock_free((phys_addr_t) mem_res, mem_res_sz); } diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index 48b870a685b3..df5d2da7c40b 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -14,7 +14,7 @@ #include <asm/stacktrace.h> -register unsigned long sp_in_global __asm__("sp"); +register const unsigned long sp_in_global __asm__("sp"); #ifdef CONFIG_FRAME_POINTER @@ -28,9 +28,8 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, sp = user_stack_pointer(regs); pc = instruction_pointer(regs); } else if (task == NULL || task == current) { - const register unsigned long current_sp = sp_in_global; fp = (unsigned long)__builtin_frame_address(0); - sp = current_sp; + sp = sp_in_global; pc = (unsigned long)walk_stackframe; } else { /* task blocked in __switch_to */ diff --git a/arch/riscv/kernel/time.c b/arch/riscv/kernel/time.c index 4d3a1048ad8b..8a5cf99c0776 100644 --- a/arch/riscv/kernel/time.c +++ b/arch/riscv/kernel/time.c @@ -4,6 +4,7 @@ * Copyright (C) 2017 SiFive */ +#include <linux/of_clk.h> #include <linux/clocksource.h> #include <linux/delay.h> #include <asm/sbi.h> @@ -24,6 +25,8 @@ void __init time_init(void) riscv_timebase = prop; lpj_fine = riscv_timebase / HZ; + + of_clk_init(NULL); timer_probe(); } diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c index 678204231700..3f1d35e7c98a 100644 --- a/arch/riscv/kernel/vdso.c +++ b/arch/riscv/kernel/vdso.c @@ -12,7 +12,7 @@ #include <linux/binfmts.h> #include <linux/err.h> #include <asm/page.h> -#ifdef GENERIC_TIME_VSYSCALL +#ifdef CONFIG_GENERIC_TIME_VSYSCALL #include <vdso/datapage.h> #else #include <asm/vdso.h> diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index bf5379135e39..7cd4993f4ff2 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -157,9 +157,10 @@ disable: void __init setup_bootmem(void) { phys_addr_t mem_start = 0; - phys_addr_t start, end = 0; + phys_addr_t start, dram_end, end = 0; phys_addr_t vmlinux_end = __pa_symbol(&_end); phys_addr_t vmlinux_start = __pa_symbol(&_start); + phys_addr_t max_mapped_addr = __pa(~(ulong)0); u64 i; /* Find the memory region containing the kernel */ @@ -181,7 +182,18 @@ void __init setup_bootmem(void) /* Reserve from the start of the kernel to the end of the kernel */ memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start); - max_pfn = PFN_DOWN(memblock_end_of_DRAM()); + dram_end = memblock_end_of_DRAM(); + + /* + * memblock allocator is not aware of the fact that last 4K bytes of + * the addressable memory can not be mapped because of IS_ERR_VALUE + * macro. Make sure that last 4k bytes are not usable by memblock + * if end of dram is equal to maximum addressable memory. + */ + if (max_mapped_addr == (dram_end - 1)) + memblock_set_current_limit(max_mapped_addr - 4096); + + max_pfn = PFN_DOWN(dram_end); max_low_pfn = max_pfn; dma32_phys_limit = min(4UL * SZ_1G, (unsigned long)PFN_PHYS(max_low_pfn)); set_max_mapnr(max_low_pfn); diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c index 12ddd1f6bf70..a8a2ffd9114a 100644 --- a/arch/riscv/mm/kasan_init.c +++ b/arch/riscv/mm/kasan_init.c @@ -93,8 +93,8 @@ void __init kasan_init(void) VMALLOC_END)); for_each_mem_range(i, &_start, &_end) { - void *start = (void *)_start; - void *end = (void *)_end; + void *start = (void *)__va(_start); + void *end = (void *)__va(_end); if (start >= end) break; diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index e84bdd15150b..c72874f09741 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -54,17 +54,23 @@ config KASAN_SHADOW_OFFSET config S390 def_bool y + # + # Note: keep this list sorted alphabetically + # + imply IMA_SECURE_AND_OR_TRUSTED_BOOT select ARCH_BINFMT_ELF_STATE select ARCH_HAS_DEBUG_VM_PGTABLE select ARCH_HAS_DEBUG_WX select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_ELF_RANDOMIZE + select ARCH_HAS_FORCE_DMA_UNENCRYPTED select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_GIGANTIC_PAGE select ARCH_HAS_KCOV select ARCH_HAS_MEM_ENCRYPT select ARCH_HAS_PTE_SPECIAL + select ARCH_HAS_SCALED_CPUTIME select ARCH_HAS_SET_MEMORY select ARCH_HAS_STRICT_KERNEL_RWX select ARCH_HAS_STRICT_MODULE_RWX @@ -111,8 +117,10 @@ config S390 select ARCH_WANT_IPC_PARSE_VERSION select BUILDTIME_TABLE_SORT select CLONE_BACKWARDS2 + select CPU_NO_EFFICIENT_FFS if !HAVE_MARCH_Z9_109_FEATURES select DMA_OPS if PCI select DYNAMIC_FTRACE if FUNCTION_TRACER + select GENERIC_ALLOCATOR select GENERIC_CPU_AUTOPROBE select GENERIC_CPU_VULNERABILITIES select GENERIC_FIND_FIRST_BIT @@ -126,22 +134,21 @@ config S390 select HAVE_ARCH_JUMP_LABEL_RELATIVE select HAVE_ARCH_KASAN select HAVE_ARCH_KASAN_VMALLOC - select CPU_NO_EFFICIENT_FFS if !HAVE_MARCH_Z9_109_FEATURES select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_SOFT_DIRTY select HAVE_ARCH_TRACEHOOK select HAVE_ARCH_TRANSPARENT_HUGEPAGE select HAVE_ARCH_VMAP_STACK select HAVE_ASM_MODVERSIONS - select HAVE_EBPF_JIT if PACK_STACK && HAVE_MARCH_Z196_FEATURES select HAVE_CMPXCHG_DOUBLE select HAVE_CMPXCHG_LOCAL select HAVE_DEBUG_KMEMLEAK select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE select HAVE_DYNAMIC_FTRACE_WITH_REGS - select HAVE_FAST_GUP + select HAVE_EBPF_JIT if PACK_STACK && HAVE_MARCH_Z196_FEATURES select HAVE_EFFICIENT_UNALIGNED_ACCESS + select HAVE_FAST_GUP select HAVE_FENTRY select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_ERROR_INJECTION @@ -163,16 +170,15 @@ config S390 select HAVE_KRETPROBES select HAVE_KVM select HAVE_LIVEPATCH - select HAVE_PERF_REGS - select HAVE_PERF_USER_STACK_DUMP select HAVE_MEMBLOCK_PHYS_MAP - select MMU_GATHER_NO_GATHER select HAVE_MOD_ARCH_SPECIFIC + select HAVE_NMI select HAVE_NOP_MCOUNT select HAVE_OPROFILE select HAVE_PCI select HAVE_PERF_EVENTS - select MMU_GATHER_RCU_TABLE_FREE + select HAVE_PERF_REGS + select HAVE_PERF_USER_STACK_DUMP select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RELIABLE_STACKTRACE select HAVE_RSEQ @@ -181,6 +187,8 @@ config S390 select HAVE_VIRT_CPU_ACCOUNTING_IDLE select IOMMU_HELPER if PCI select IOMMU_SUPPORT if PCI + select MMU_GATHER_NO_GATHER + select MMU_GATHER_RCU_TABLE_FREE select MODULES_USE_ELF_RELA select NEED_DMA_MAP_STATE if PCI select NEED_SG_DMA_LENGTH if PCI @@ -190,17 +198,12 @@ config S390 select PCI_MSI if PCI select PCI_MSI_ARCH_FALLBACKS if PCI_MSI select SPARSE_IRQ + select SWIOTLB select SYSCTL_EXCEPTION_TRACE select THREAD_INFO_IN_TASK select TTY select VIRT_CPU_ACCOUNTING - select ARCH_HAS_SCALED_CPUTIME - select HAVE_NMI - select ARCH_HAS_FORCE_DMA_UNENCRYPTED - select SWIOTLB - select GENERIC_ALLOCATOR - imply IMA_SECURE_AND_OR_TRUSTED_BOOT - + # Note: keep the above list sorted alphabetically config SCHED_OMIT_FRAME_POINTER def_bool y diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 1be32fcf6f2e..c4f6ff98a612 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -61,7 +61,9 @@ CONFIG_OPROFILE=m CONFIG_KPROBES=y CONFIG_JUMP_LABEL=y CONFIG_STATIC_KEYS_SELFTEST=y +CONFIG_SECCOMP_CACHE_DEBUG=y CONFIG_LOCK_EVENT_COUNTS=y +# CONFIG_GCC_PLUGINS is not set CONFIG_MODULES=y CONFIG_MODULE_FORCE_LOAD=y CONFIG_MODULE_UNLOAD=y @@ -410,12 +412,12 @@ CONFIG_SCSI_ENCLOSURE=m CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_LOGGING=y CONFIG_SCSI_SPI_ATTRS=m -CONFIG_SCSI_FC_ATTRS=y +CONFIG_SCSI_FC_ATTRS=m CONFIG_SCSI_SAS_LIBSAS=m CONFIG_SCSI_SRP_ATTRS=m CONFIG_ISCSI_TCP=m CONFIG_SCSI_DEBUG=m -CONFIG_ZFCP=y +CONFIG_ZFCP=m CONFIG_SCSI_VIRTIO=m CONFIG_SCSI_DH=y CONFIG_SCSI_DH_RDAC=m @@ -444,6 +446,7 @@ CONFIG_DM_MULTIPATH=m CONFIG_DM_MULTIPATH_QL=m CONFIG_DM_MULTIPATH_ST=m CONFIG_DM_MULTIPATH_HST=m +CONFIG_DM_MULTIPATH_IOA=m CONFIG_DM_DELAY=m CONFIG_DM_UEVENT=y CONFIG_DM_FLAKEY=m @@ -542,7 +545,6 @@ CONFIG_INPUT_EVDEV=y # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set CONFIG_LEGACY_PTY_COUNT=0 -CONFIG_NULL_TTY=m CONFIG_VIRTIO_CONSOLE=y CONFIG_HW_RANDOM_VIRTIO=m CONFIG_RAW_DRIVER=m @@ -574,6 +576,7 @@ CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_INPUT=y CONFIG_VHOST_NET=m CONFIG_VHOST_VSOCK=m +# CONFIG_SURFACE_PLATFORMS is not set CONFIG_S390_CCW_IOMMU=y CONFIG_S390_AP_IOMMU=y CONFIG_EXT4_FS=y @@ -655,6 +658,7 @@ CONFIG_CIFS_XATTR=y CONFIG_CIFS_POSIX=y # CONFIG_CIFS_DEBUG is not set CONFIG_CIFS_DFS_UPCALL=y +CONFIG_CIFS_SWN_UPCALL=y CONFIG_NLS_DEFAULT="utf8" CONFIG_NLS_CODEPAGE_437=m CONFIG_NLS_CODEPAGE_850=m @@ -826,6 +830,8 @@ CONFIG_FTRACE_SYSCALLS=y CONFIG_BLK_DEV_IO_TRACE=y CONFIG_BPF_KPROBE_OVERRIDE=y CONFIG_HIST_TRIGGERS=y +CONFIG_FTRACE_STARTUP_TEST=y +# CONFIG_EVENT_TRACE_STARTUP_TEST is not set CONFIG_DEBUG_USER_ASCE=y CONFIG_NOTIFIER_ERROR_INJECTION=m CONFIG_NETDEV_NOTIFIER_ERROR_INJECT=m diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index e2171a008809..51135893cffe 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -58,6 +58,7 @@ CONFIG_S390_UNWIND_SELFTEST=m CONFIG_OPROFILE=m CONFIG_KPROBES=y CONFIG_JUMP_LABEL=y +# CONFIG_GCC_PLUGINS is not set CONFIG_MODULES=y CONFIG_MODULE_FORCE_LOAD=y CONFIG_MODULE_UNLOAD=y @@ -95,7 +96,6 @@ CONFIG_ZSMALLOC_STAT=y CONFIG_DEFERRED_STRUCT_PAGE_INIT=y CONFIG_IDLE_PAGE_TRACKING=y CONFIG_PERCPU_STATS=y -CONFIG_GUP_TEST=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_PACKET_DIAG=m @@ -403,12 +403,12 @@ CONFIG_SCSI_ENCLOSURE=m CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_LOGGING=y CONFIG_SCSI_SPI_ATTRS=m -CONFIG_SCSI_FC_ATTRS=y +CONFIG_SCSI_FC_ATTRS=m CONFIG_SCSI_SAS_LIBSAS=m CONFIG_SCSI_SRP_ATTRS=m CONFIG_ISCSI_TCP=m CONFIG_SCSI_DEBUG=m -CONFIG_ZFCP=y +CONFIG_ZFCP=m CONFIG_SCSI_VIRTIO=m CONFIG_SCSI_DH=y CONFIG_SCSI_DH_RDAC=m @@ -437,6 +437,7 @@ CONFIG_DM_MULTIPATH=m CONFIG_DM_MULTIPATH_QL=m CONFIG_DM_MULTIPATH_ST=m CONFIG_DM_MULTIPATH_HST=m +CONFIG_DM_MULTIPATH_IOA=m CONFIG_DM_DELAY=m CONFIG_DM_UEVENT=y CONFIG_DM_FLAKEY=m @@ -536,7 +537,6 @@ CONFIG_INPUT_EVDEV=y # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set CONFIG_LEGACY_PTY_COUNT=0 -CONFIG_NULL_TTY=m CONFIG_VIRTIO_CONSOLE=y CONFIG_HW_RANDOM_VIRTIO=m CONFIG_RAW_DRIVER=m @@ -568,6 +568,7 @@ CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_INPUT=y CONFIG_VHOST_NET=m CONFIG_VHOST_VSOCK=m +# CONFIG_SURFACE_PLATFORMS is not set CONFIG_S390_CCW_IOMMU=y CONFIG_S390_AP_IOMMU=y CONFIG_EXT4_FS=y @@ -645,6 +646,7 @@ CONFIG_CIFS_XATTR=y CONFIG_CIFS_POSIX=y # CONFIG_CIFS_DEBUG is not set CONFIG_CIFS_DFS_UPCALL=y +CONFIG_CIFS_SWN_UPCALL=y CONFIG_NLS_DEFAULT="utf8" CONFIG_NLS_CODEPAGE_437=m CONFIG_NLS_CODEPAGE_850=m @@ -778,6 +780,7 @@ CONFIG_FTRACE_SYSCALLS=y CONFIG_BLK_DEV_IO_TRACE=y CONFIG_BPF_KPROBE_OVERRIDE=y CONFIG_HIST_TRIGGERS=y +CONFIG_DEBUG_USER_ASCE=y CONFIG_LKDTM=m CONFIG_PERCPU_TEST=m CONFIG_ATOMIC64_SELFTEST=y diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index a302630341ef..1ef211dae77a 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -22,6 +22,7 @@ CONFIG_CRASH_DUMP=y # CONFIG_VIRTUALIZATION is not set # CONFIG_S390_GUEST is not set # CONFIG_SECCOMP is not set +# CONFIG_GCC_PLUGINS is not set CONFIG_PARTITION_ADVANCED=y CONFIG_IBM_PARTITION=y # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set @@ -58,6 +59,7 @@ CONFIG_RAW_DRIVER=y # CONFIG_HID is not set # CONFIG_VIRTIO_MENU is not set # CONFIG_VHOST_MENU is not set +# CONFIG_SURFACE_PLATFORMS is not set # CONFIG_IOMMU_SUPPORT is not set # CONFIG_DNOTIFY is not set # CONFIG_INOTIFY_USER is not set diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild index 319efa0e6d02..1a18d7b82f86 100644 --- a/arch/s390/include/asm/Kbuild +++ b/arch/s390/include/asm/Kbuild @@ -7,5 +7,4 @@ generated-y += unistd_nr.h generic-y += asm-offsets.h generic-y += export.h generic-y += kvm_types.h -generic-y += local64.h generic-y += mcs_spinlock.h diff --git a/arch/sh/include/asm/Kbuild b/arch/sh/include/asm/Kbuild index 7435182ef846..fc44d9c88b41 100644 --- a/arch/sh/include/asm/Kbuild +++ b/arch/sh/include/asm/Kbuild @@ -1,6 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 generated-y += syscall_table.h generic-y += kvm_para.h -generic-y += local64.h generic-y += mcs_spinlock.h generic-y += parport.h diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild index 5269a704801f..3688fdae50e4 100644 --- a/arch/sparc/include/asm/Kbuild +++ b/arch/sparc/include/asm/Kbuild @@ -6,5 +6,4 @@ generated-y += syscall_table_64.h generated-y += syscall_table_c32.h generic-y += export.h generic-y += kvm_para.h -generic-y += local64.h generic-y += mcs_spinlock.h diff --git a/arch/sparc/include/asm/highmem.h b/arch/sparc/include/asm/highmem.h index 875116209ec1..c7b2e208328b 100644 --- a/arch/sparc/include/asm/highmem.h +++ b/arch/sparc/include/asm/highmem.h @@ -50,10 +50,11 @@ extern pte_t *pkmap_page_table; #define flush_cache_kmaps() flush_cache_all() -/* FIXME: Use __flush_tlb_one(vaddr) instead of flush_cache_all() -- Anton */ -#define arch_kmap_local_post_map(vaddr, pteval) flush_cache_all() -#define arch_kmap_local_post_unmap(vaddr) flush_cache_all() - +/* FIXME: Use __flush_*_one(vaddr) instead of flush_*_all() -- Anton */ +#define arch_kmap_local_pre_map(vaddr, pteval) flush_cache_all() +#define arch_kmap_local_pre_unmap(vaddr) flush_cache_all() +#define arch_kmap_local_post_map(vaddr, pteval) flush_tlb_all() +#define arch_kmap_local_post_unmap(vaddr) flush_tlb_all() #endif /* __KERNEL__ */ diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 7b6dd10b162a..21f851179ff0 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -19,6 +19,7 @@ config X86_32 select KMAP_LOCAL select MODULES_USE_ELF_REL select OLD_SIGACTION + select ARCH_SPLIT_ARG64 config X86_64 def_bool y diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 18d8f17f755c..0904f5676e4d 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -73,10 +73,8 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs, unsigned int nr) { if (likely(nr < IA32_NR_syscalls)) { - instrumentation_begin(); nr = array_index_nospec(nr, IA32_NR_syscalls); regs->ax = ia32_sys_call_table[nr](regs); - instrumentation_end(); } } @@ -91,8 +89,11 @@ __visible noinstr void do_int80_syscall_32(struct pt_regs *regs) * or may not be necessary, but it matches the old asm behavior. */ nr = (unsigned int)syscall_enter_from_user_mode(regs, nr); + instrumentation_begin(); do_syscall_32_irqs_on(regs, nr); + + instrumentation_end(); syscall_exit_to_user_mode(regs); } @@ -121,11 +122,12 @@ static noinstr bool __do_fast_syscall_32(struct pt_regs *regs) res = get_user(*(u32 *)®s->bp, (u32 __user __force *)(unsigned long)(u32)regs->sp); } - instrumentation_end(); if (res) { /* User code screwed up. */ regs->ax = -EFAULT; + + instrumentation_end(); syscall_exit_to_user_mode(regs); return false; } @@ -135,6 +137,8 @@ static noinstr bool __do_fast_syscall_32(struct pt_regs *regs) /* Now this is just like a normal syscall. */ do_syscall_32_irqs_on(regs, nr); + + instrumentation_end(); syscall_exit_to_user_mode(regs); return true; } diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index e04d90af4c27..6375967a8244 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -16,6 +16,7 @@ #include <asm/hyperv-tlfs.h> #include <asm/mshyperv.h> #include <asm/idtentry.h> +#include <linux/kexec.h> #include <linux/version.h> #include <linux/vmalloc.h> #include <linux/mm.h> @@ -26,6 +27,8 @@ #include <linux/syscore_ops.h> #include <clocksource/hyperv_timer.h> +int hyperv_init_cpuhp; + void *hv_hypercall_pg; EXPORT_SYMBOL_GPL(hv_hypercall_pg); @@ -312,6 +315,25 @@ static struct syscore_ops hv_syscore_ops = { .resume = hv_resume, }; +static void (* __initdata old_setup_percpu_clockev)(void); + +static void __init hv_stimer_setup_percpu_clockev(void) +{ + /* + * Ignore any errors in setting up stimer clockevents + * as we can run with the LAPIC timer as a fallback. + */ + (void)hv_stimer_alloc(); + + /* + * Still register the LAPIC timer, because the direct-mode STIMER is + * not supported by old versions of Hyper-V. This also allows users + * to switch to LAPIC timer via /sys, if they want to. + */ + if (old_setup_percpu_clockev) + old_setup_percpu_clockev(); +} + /* * This function is to be invoked early in the boot sequence after the * hypervisor has been detected. @@ -390,10 +412,14 @@ void __init hyperv_init(void) wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); /* - * Ignore any errors in setting up stimer clockevents - * as we can run with the LAPIC timer as a fallback. + * hyperv_init() is called before LAPIC is initialized: see + * apic_intr_mode_init() -> x86_platform.apic_post_init() and + * apic_bsp_setup() -> setup_local_APIC(). The direct-mode STIMER + * depends on LAPIC, so hv_stimer_alloc() should be called from + * x86_init.timers.setup_percpu_clockev. */ - (void)hv_stimer_alloc(); + old_setup_percpu_clockev = x86_init.timers.setup_percpu_clockev; + x86_init.timers.setup_percpu_clockev = hv_stimer_setup_percpu_clockev; hv_apic_init(); @@ -401,6 +427,7 @@ void __init hyperv_init(void) register_syscore_ops(&hv_syscore_ops); + hyperv_init_cpuhp = cpuhp; return; remove_cpuhp_state: diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c index 5208ba49c89a..2c87350c1fb0 100644 --- a/arch/x86/hyperv/mmu.c +++ b/arch/x86/hyperv/mmu.c @@ -66,11 +66,17 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus, if (!hv_hypercall_pg) goto do_native; - if (cpumask_empty(cpus)) - return; - local_irq_save(flags); + /* + * Only check the mask _after_ interrupt has been disabled to avoid the + * mask changing under our feet. + */ + if (cpumask_empty(cpus)) { + local_irq_restore(flags); + return; + } + flush_pcpu = (struct hv_tlb_flush **) this_cpu_ptr(hyperv_pcpu_input_arg); diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h index a5aba4ab0224..67a4f1cb2aac 100644 --- a/arch/x86/include/asm/fpu/api.h +++ b/arch/x86/include/asm/fpu/api.h @@ -16,14 +16,25 @@ * Use kernel_fpu_begin/end() if you intend to use FPU in kernel context. It * disables preemption so be careful if you intend to use it for long periods * of time. - * If you intend to use the FPU in softirq you need to check first with + * If you intend to use the FPU in irq/softirq you need to check first with * irq_fpu_usable() if it is possible. */ -extern void kernel_fpu_begin(void); + +/* Kernel FPU states to initialize in kernel_fpu_begin_mask() */ +#define KFPU_387 _BITUL(0) /* 387 state will be initialized */ +#define KFPU_MXCSR _BITUL(1) /* MXCSR will be initialized */ + +extern void kernel_fpu_begin_mask(unsigned int kfpu_mask); extern void kernel_fpu_end(void); extern bool irq_fpu_usable(void); extern void fpregs_mark_activate(void); +/* Code that is unaware of kernel_fpu_begin_mask() can use this */ +static inline void kernel_fpu_begin(void) +{ + kernel_fpu_begin_mask(KFPU_387 | KFPU_MXCSR); +} + /* * Use fpregs_lock() while editing CPU's FPU registers or fpu->state. * A context switch will (and softirq might) save CPU's FPU registers to diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 5e658ba2654a..9abe842dbd84 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -97,6 +97,7 @@ #define INTEL_FAM6_LAKEFIELD 0x8A #define INTEL_FAM6_ALDERLAKE 0x97 +#define INTEL_FAM6_ALDERLAKE_L 0x9A /* "Small Core" Processors (Atom) */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 3ab7b46087b7..3d6616f6f6ef 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1010,9 +1010,21 @@ struct kvm_arch { */ bool tdp_mmu_enabled; - /* List of struct tdp_mmu_pages being used as roots */ + /* + * List of struct kvmp_mmu_pages being used as roots. + * All struct kvm_mmu_pages in the list should have + * tdp_mmu_page set. + * All struct kvm_mmu_pages in the list should have a positive + * root_count except when a thread holds the MMU lock and is removing + * an entry from the list. + */ struct list_head tdp_mmu_roots; - /* List of struct tdp_mmu_pages not being used as roots */ + + /* + * List of struct kvmp_mmu_pages not being used as roots. + * All struct kvm_mmu_pages in the list should have + * tdp_mmu_page set and a root_count of 0. + */ struct list_head tdp_mmu_pages; }; @@ -1287,6 +1299,8 @@ struct kvm_x86_ops { void (*migrate_timers)(struct kvm_vcpu *vcpu); void (*msr_filter_changed)(struct kvm_vcpu *vcpu); int (*complete_emulated_msr)(struct kvm_vcpu *vcpu, int err); + + void (*vcpu_deliver_sipi_vector)(struct kvm_vcpu *vcpu, u8 vector); }; struct kvm_x86_nested_ops { @@ -1468,6 +1482,7 @@ int kvm_fast_pio(struct kvm_vcpu *vcpu, int size, unsigned short port, int in); int kvm_emulate_cpuid(struct kvm_vcpu *vcpu); int kvm_emulate_halt(struct kvm_vcpu *vcpu); int kvm_vcpu_halt(struct kvm_vcpu *vcpu); +int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu); int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu); void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); diff --git a/arch/x86/include/asm/local64.h b/arch/x86/include/asm/local64.h deleted file mode 100644 index 36c93b5cc239..000000000000 --- a/arch/x86/include/asm/local64.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/local64.h> diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index ffc289992d1b..30f76b966857 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -74,6 +74,8 @@ static inline void hv_disable_stimer0_percpu_irq(int irq) {} #if IS_ENABLED(CONFIG_HYPERV) +extern int hyperv_init_cpuhp; + extern void *hv_hypercall_pg; extern void __percpu **hyperv_pcpu_input_arg; diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index 0b4920a7238e..e16cccdd0420 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -86,7 +86,7 @@ static inline void do_trace_rdpmc(unsigned int msr, u64 val, int failed) {} * think of extending them - you will be slapped with a stinking trout or a frozen * shark will reach you, wherever you are! You've been warned. */ -static inline unsigned long long notrace __rdmsr(unsigned int msr) +static __always_inline unsigned long long __rdmsr(unsigned int msr) { DECLARE_ARGS(val, low, high); @@ -98,7 +98,7 @@ static inline unsigned long long notrace __rdmsr(unsigned int msr) return EAX_EDX_VAL(val, low, high); } -static inline void notrace __wrmsr(unsigned int msr, u32 low, u32 high) +static __always_inline void __wrmsr(unsigned int msr, u32 low, u32 high) { asm volatile("1: wrmsr\n" "2:\n" diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 488a8e848754..9239399e5491 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -110,6 +110,8 @@ extern const struct cpumask *cpu_coregroup_mask(int cpu); #define topology_die_id(cpu) (cpu_data(cpu).cpu_die_id) #define topology_core_id(cpu) (cpu_data(cpu).cpu_core_id) +extern unsigned int __max_die_per_package; + #ifdef CONFIG_SMP #define topology_die_cpumask(cpu) (per_cpu(cpu_die_map, cpu)) #define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu)) @@ -118,8 +120,6 @@ extern const struct cpumask *cpu_coregroup_mask(int cpu); extern unsigned int __max_logical_packages; #define topology_max_packages() (__max_logical_packages) -extern unsigned int __max_die_per_package; - static inline int topology_max_die_per_package(void) { return __max_die_per_package; diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index f8ca66f3d861..347a956f71ca 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -542,12 +542,12 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) u32 ecx; ecx = cpuid_ecx(0x8000001e); - nodes_per_socket = ((ecx >> 8) & 7) + 1; + __max_die_per_package = nodes_per_socket = ((ecx >> 8) & 7) + 1; } else if (boot_cpu_has(X86_FEATURE_NODEID_MSR)) { u64 value; rdmsrl(MSR_FAM10H_NODE_ID, value); - nodes_per_socket = ((value >> 3) & 7) + 1; + __max_die_per_package = nodes_per_socket = ((value >> 3) & 7) + 1; } if (!boot_cpu_has(X86_FEATURE_AMD_SSBD) && diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 13d3f1cbda17..e133ce1e562b 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -1992,10 +1992,9 @@ static __always_inline void exc_machine_check_kernel(struct pt_regs *regs) * that out because it's an indirect call. Annotate it. */ instrumentation_begin(); - trace_hardirqs_off_finish(); + machine_check_vector(regs); - if (regs->flags & X86_EFLAGS_IF) - trace_hardirqs_on_prepare(); + instrumentation_end(); irqentry_nmi_exit(regs, irq_state); } @@ -2004,7 +2003,9 @@ static __always_inline void exc_machine_check_user(struct pt_regs *regs) { irqentry_enter_from_user_mode(regs); instrumentation_begin(); + machine_check_vector(regs); + instrumentation_end(); irqentry_exit_to_user_mode(regs); } diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index f628e3dc150f..43b54bef5448 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -135,14 +135,32 @@ static void hv_machine_shutdown(void) { if (kexec_in_progress && hv_kexec_handler) hv_kexec_handler(); + + /* + * Call hv_cpu_die() on all the CPUs, otherwise later the hypervisor + * corrupts the old VP Assist Pages and can crash the kexec kernel. + */ + if (kexec_in_progress && hyperv_init_cpuhp > 0) + cpuhp_remove_state(hyperv_init_cpuhp); + + /* The function calls stop_other_cpus(). */ native_machine_shutdown(); + + /* Disable the hypercall page when there is only 1 active CPU. */ + if (kexec_in_progress) + hyperv_cleanup(); } static void hv_machine_crash_shutdown(struct pt_regs *regs) { if (hv_crash_handler) hv_crash_handler(regs); + + /* The function calls crash_smp_send_stop(). */ native_machine_crash_shutdown(regs); + + /* Disable the hypercall page when there is only 1 active CPU. */ + hyperv_cleanup(); } #endif /* CONFIG_KEXEC_CORE */ #endif /* CONFIG_HYPERV */ diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 23ad8e953dfb..a29997e6cf9e 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -167,9 +167,6 @@ static u8 mtrr_type_lookup_variable(u64 start, u64 end, u64 *partial_end, *repeat = 0; *uniform = 1; - /* Make end inclusive instead of exclusive */ - end--; - prev_match = MTRR_TYPE_INVALID; for (i = 0; i < num_var_ranges; ++i) { unsigned short start_state, end_state, inclusive; @@ -261,6 +258,9 @@ u8 mtrr_type_lookup(u64 start, u64 end, u8 *uniform) int repeat; u64 partial_end; + /* Make end inclusive instead of exclusive */ + end--; + if (!mtrr_state_set) return MTRR_TYPE_INVALID; diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 29ffb95b25ff..460f3e0df106 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -525,89 +525,70 @@ static void rdtgroup_remove(struct rdtgroup *rdtgrp) kfree(rdtgrp); } -struct task_move_callback { - struct callback_head work; - struct rdtgroup *rdtgrp; -}; - -static void move_myself(struct callback_head *head) +static void _update_task_closid_rmid(void *task) { - struct task_move_callback *callback; - struct rdtgroup *rdtgrp; - - callback = container_of(head, struct task_move_callback, work); - rdtgrp = callback->rdtgrp; - /* - * If resource group was deleted before this task work callback - * was invoked, then assign the task to root group and free the - * resource group. + * If the task is still current on this CPU, update PQR_ASSOC MSR. + * Otherwise, the MSR is updated when the task is scheduled in. */ - if (atomic_dec_and_test(&rdtgrp->waitcount) && - (rdtgrp->flags & RDT_DELETED)) { - current->closid = 0; - current->rmid = 0; - rdtgroup_remove(rdtgrp); - } - - if (unlikely(current->flags & PF_EXITING)) - goto out; - - preempt_disable(); - /* update PQR_ASSOC MSR to make resource group go into effect */ - resctrl_sched_in(); - preempt_enable(); + if (task == current) + resctrl_sched_in(); +} -out: - kfree(callback); +static void update_task_closid_rmid(struct task_struct *t) +{ + if (IS_ENABLED(CONFIG_SMP) && task_curr(t)) + smp_call_function_single(task_cpu(t), _update_task_closid_rmid, t, 1); + else + _update_task_closid_rmid(t); } static int __rdtgroup_move_task(struct task_struct *tsk, struct rdtgroup *rdtgrp) { - struct task_move_callback *callback; - int ret; - - callback = kzalloc(sizeof(*callback), GFP_KERNEL); - if (!callback) - return -ENOMEM; - callback->work.func = move_myself; - callback->rdtgrp = rdtgrp; + /* If the task is already in rdtgrp, no need to move the task. */ + if ((rdtgrp->type == RDTCTRL_GROUP && tsk->closid == rdtgrp->closid && + tsk->rmid == rdtgrp->mon.rmid) || + (rdtgrp->type == RDTMON_GROUP && tsk->rmid == rdtgrp->mon.rmid && + tsk->closid == rdtgrp->mon.parent->closid)) + return 0; /* - * Take a refcount, so rdtgrp cannot be freed before the - * callback has been invoked. + * Set the task's closid/rmid before the PQR_ASSOC MSR can be + * updated by them. + * + * For ctrl_mon groups, move both closid and rmid. + * For monitor groups, can move the tasks only from + * their parent CTRL group. */ - atomic_inc(&rdtgrp->waitcount); - ret = task_work_add(tsk, &callback->work, TWA_RESUME); - if (ret) { - /* - * Task is exiting. Drop the refcount and free the callback. - * No need to check the refcount as the group cannot be - * deleted before the write function unlocks rdtgroup_mutex. - */ - atomic_dec(&rdtgrp->waitcount); - kfree(callback); - rdt_last_cmd_puts("Task exited\n"); - } else { - /* - * For ctrl_mon groups move both closid and rmid. - * For monitor groups, can move the tasks only from - * their parent CTRL group. - */ - if (rdtgrp->type == RDTCTRL_GROUP) { - tsk->closid = rdtgrp->closid; + + if (rdtgrp->type == RDTCTRL_GROUP) { + tsk->closid = rdtgrp->closid; + tsk->rmid = rdtgrp->mon.rmid; + } else if (rdtgrp->type == RDTMON_GROUP) { + if (rdtgrp->mon.parent->closid == tsk->closid) { tsk->rmid = rdtgrp->mon.rmid; - } else if (rdtgrp->type == RDTMON_GROUP) { - if (rdtgrp->mon.parent->closid == tsk->closid) { - tsk->rmid = rdtgrp->mon.rmid; - } else { - rdt_last_cmd_puts("Can't move task to different control group\n"); - ret = -EINVAL; - } + } else { + rdt_last_cmd_puts("Can't move task to different control group\n"); + return -EINVAL; } } - return ret; + + /* + * Ensure the task's closid and rmid are written before determining if + * the task is current that will decide if it will be interrupted. + */ + barrier(); + + /* + * By now, the task's closid and rmid are set. If the task is current + * on a CPU, the PQR_ASSOC MSR needs to be updated to make the resource + * group go into effect. If the task is not current, the MSR will be + * updated when the task is scheduled in. + */ + update_task_closid_rmid(tsk); + + return 0; } static bool is_closid_match(struct task_struct *t, struct rdtgroup *r) diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index 1068002c8532..8678864ce712 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -25,10 +25,10 @@ #define BITS_SHIFT_NEXT_LEVEL(eax) ((eax) & 0x1f) #define LEVEL_MAX_SIBLINGS(ebx) ((ebx) & 0xffff) -#ifdef CONFIG_SMP unsigned int __max_die_per_package __read_mostly = 1; EXPORT_SYMBOL(__max_die_per_package); +#ifdef CONFIG_SMP /* * Check if given CPUID extended toplogy "leaf" is implemented */ diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index eb86a2b831b1..571220ac8bea 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -121,7 +121,7 @@ int copy_fpregs_to_fpstate(struct fpu *fpu) } EXPORT_SYMBOL(copy_fpregs_to_fpstate); -void kernel_fpu_begin(void) +void kernel_fpu_begin_mask(unsigned int kfpu_mask) { preempt_disable(); @@ -141,13 +141,14 @@ void kernel_fpu_begin(void) } __cpu_invalidate_fpregs_state(); - if (boot_cpu_has(X86_FEATURE_XMM)) + /* Put sane initial values into the control registers. */ + if (likely(kfpu_mask & KFPU_MXCSR) && boot_cpu_has(X86_FEATURE_XMM)) ldmxcsr(MXCSR_DEFAULT); - if (boot_cpu_has(X86_FEATURE_FPU)) + if (unlikely(kfpu_mask & KFPU_387) && boot_cpu_has(X86_FEATURE_FPU)) asm volatile ("fninit"); } -EXPORT_SYMBOL_GPL(kernel_fpu_begin); +EXPORT_SYMBOL_GPL(kernel_fpu_begin_mask); void kernel_fpu_end(void) { diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 740f3bdb3f61..3412c4595efd 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -661,17 +661,6 @@ static void __init trim_platform_memory_ranges(void) static void __init trim_bios_range(void) { /* - * A special case is the first 4Kb of memory; - * This is a BIOS owned area, not kernel ram, but generally - * not listed as such in the E820 table. - * - * This typically reserves additional memory (64KiB by default) - * since some BIOSes are known to corrupt low memory. See the - * Kconfig help text for X86_RESERVE_LOW. - */ - e820__range_update(0, PAGE_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED); - - /* * special case: Some BIOSes report the PC BIOS * area (640Kb -> 1Mb) as RAM even though it is not. * take them out. @@ -728,6 +717,15 @@ early_param("reservelow", parse_reservelow); static void __init trim_low_memory_range(void) { + /* + * A special case is the first 4Kb of memory; + * This is a BIOS owned area, not kernel ram, but generally + * not listed as such in the E820 table. + * + * This typically reserves additional memory (64KiB by default) + * since some BIOSes are known to corrupt low memory. See the + * Kconfig help text for X86_RESERVE_LOW. + */ memblock_reserve(0, ALIGN(reserve_low, PAGE_SIZE)); } diff --git a/arch/x86/kernel/sev-es-shared.c b/arch/x86/kernel/sev-es-shared.c index 7d04b356d44d..cdc04d091242 100644 --- a/arch/x86/kernel/sev-es-shared.c +++ b/arch/x86/kernel/sev-es-shared.c @@ -305,14 +305,14 @@ static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo) case 0xe4: case 0xe5: *exitinfo |= IOIO_TYPE_IN; - *exitinfo |= (u64)insn->immediate.value << 16; + *exitinfo |= (u8)insn->immediate.value << 16; break; /* OUT immediate opcodes */ case 0xe6: case 0xe7: *exitinfo |= IOIO_TYPE_OUT; - *exitinfo |= (u64)insn->immediate.value << 16; + *exitinfo |= (u8)insn->immediate.value << 16; break; /* IN register opcodes */ diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 0bd1a0fc587e..84c1821819af 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -225,7 +225,7 @@ static inline u64 sev_es_rd_ghcb_msr(void) return __rdmsr(MSR_AMD64_SEV_ES_GHCB); } -static inline void sev_es_wr_ghcb_msr(u64 val) +static __always_inline void sev_es_wr_ghcb_msr(u64 val) { u32 low, high; @@ -286,6 +286,12 @@ static enum es_result vc_write_mem(struct es_em_ctxt *ctxt, u16 d2; u8 d1; + /* If instruction ran in kernel mode and the I/O buffer is in kernel space */ + if (!user_mode(ctxt->regs) && !access_ok(target, size)) { + memcpy(dst, buf, size); + return ES_OK; + } + switch (size) { case 1: memcpy(&d1, buf, 1); @@ -335,6 +341,12 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt, u16 d2; u8 d1; + /* If instruction ran in kernel mode and the I/O buffer is in kernel space */ + if (!user_mode(ctxt->regs) && !access_ok(s, size)) { + memcpy(buf, src, size); + return ES_OK; + } + switch (size) { case 1: if (get_user(d1, s)) diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 8ca66af96a54..117e24fbfd8a 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -56,6 +56,7 @@ #include <linux/numa.h> #include <linux/pgtable.h> #include <linux/overflow.h> +#include <linux/syscore_ops.h> #include <asm/acpi.h> #include <asm/desc.h> @@ -2083,6 +2084,23 @@ static void init_counter_refs(void) this_cpu_write(arch_prev_mperf, mperf); } +#ifdef CONFIG_PM_SLEEP +static struct syscore_ops freq_invariance_syscore_ops = { + .resume = init_counter_refs, +}; + +static void register_freq_invariance_syscore_ops(void) +{ + /* Bail out if registered already. */ + if (freq_invariance_syscore_ops.node.prev) + return; + + register_syscore_ops(&freq_invariance_syscore_ops); +} +#else +static inline void register_freq_invariance_syscore_ops(void) {} +#endif + static void init_freq_invariance(bool secondary, bool cppc_ready) { bool ret = false; @@ -2109,6 +2127,7 @@ static void init_freq_invariance(bool secondary, bool cppc_ready) if (ret) { init_counter_refs(); static_branch_enable(&arch_scale_freq_key); + register_freq_invariance_syscore_ops(); pr_info("Estimated ratio of average max frequency by base frequency (times 1024): %llu\n", arch_max_freq_ratio); } else { pr_debug("Couldn't determine max cpu frequency, necessary for scale-invariant accounting.\n"); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 3136e05831cf..43cceadd073e 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -674,7 +674,7 @@ static bool pv_eoi_get_pending(struct kvm_vcpu *vcpu) (unsigned long long)vcpu->arch.pv_eoi.msr_val); return false; } - return val & 0x1; + return val & KVM_PV_EOI_ENABLED; } static void pv_eoi_set_pending(struct kvm_vcpu *vcpu) @@ -2898,7 +2898,7 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu) /* evaluate pending_events before reading the vector */ smp_rmb(); sipi_vector = apic->sipi_vector; - kvm_vcpu_deliver_sipi_vector(vcpu, sipi_vector); + kvm_x86_ops.vcpu_deliver_sipi_vector(vcpu, sipi_vector); vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; } } diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 9c4a9c8e43d9..581925e476d6 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -49,7 +49,7 @@ static inline u64 rsvd_bits(int s, int e) if (e < s) return 0; - return ((1ULL << (e - s + 1)) - 1) << s; + return ((2ULL << (e - s)) - 1) << s; } void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 access_mask); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index c478904af518..6d16481aa29d 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3493,26 +3493,25 @@ static bool mmio_info_in_cache(struct kvm_vcpu *vcpu, u64 addr, bool direct) * Return the level of the lowest level SPTE added to sptes. * That SPTE may be non-present. */ -static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes) +static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, int *root_level) { struct kvm_shadow_walk_iterator iterator; - int leaf = vcpu->arch.mmu->root_level; + int leaf = -1; u64 spte; - walk_shadow_page_lockless_begin(vcpu); - for (shadow_walk_init(&iterator, vcpu, addr); + for (shadow_walk_init(&iterator, vcpu, addr), + *root_level = iterator.level; shadow_walk_okay(&iterator); __shadow_walk_next(&iterator, spte)) { leaf = iterator.level; spte = mmu_spte_get_lockless(iterator.sptep); - sptes[leaf - 1] = spte; + sptes[leaf] = spte; if (!is_shadow_present_pte(spte)) break; - } walk_shadow_page_lockless_end(vcpu); @@ -3520,14 +3519,12 @@ static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes) return leaf; } -/* return true if reserved bit is detected on spte. */ +/* return true if reserved bit(s) are detected on a valid, non-MMIO SPTE. */ static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) { - u64 sptes[PT64_ROOT_MAX_LEVEL]; + u64 sptes[PT64_ROOT_MAX_LEVEL + 1]; struct rsvd_bits_validate *rsvd_check; - int root = vcpu->arch.mmu->shadow_root_level; - int leaf; - int level; + int root, leaf, level; bool reserved = false; if (!VALID_PAGE(vcpu->arch.mmu->root_hpa)) { @@ -3536,35 +3533,45 @@ static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) } if (is_tdp_mmu_root(vcpu->kvm, vcpu->arch.mmu->root_hpa)) - leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes); + leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes, &root); else - leaf = get_walk(vcpu, addr, sptes); + leaf = get_walk(vcpu, addr, sptes, &root); + + if (unlikely(leaf < 0)) { + *sptep = 0ull; + return reserved; + } + + *sptep = sptes[leaf]; + + /* + * Skip reserved bits checks on the terminal leaf if it's not a valid + * SPTE. Note, this also (intentionally) skips MMIO SPTEs, which, by + * design, always have reserved bits set. The purpose of the checks is + * to detect reserved bits on non-MMIO SPTEs. i.e. buggy SPTEs. + */ + if (!is_shadow_present_pte(sptes[leaf])) + leaf++; rsvd_check = &vcpu->arch.mmu->shadow_zero_check; - for (level = root; level >= leaf; level--) { - if (!is_shadow_present_pte(sptes[level - 1])) - break; + for (level = root; level >= leaf; level--) /* * Use a bitwise-OR instead of a logical-OR to aggregate the * reserved bit and EPT's invalid memtype/XWR checks to avoid * adding a Jcc in the loop. */ - reserved |= __is_bad_mt_xwr(rsvd_check, sptes[level - 1]) | - __is_rsvd_bits_set(rsvd_check, sptes[level - 1], - level); - } + reserved |= __is_bad_mt_xwr(rsvd_check, sptes[level]) | + __is_rsvd_bits_set(rsvd_check, sptes[level], level); if (reserved) { pr_err("%s: detect reserved bits on spte, addr 0x%llx, dump hierarchy:\n", __func__, addr); for (level = root; level >= leaf; level--) pr_err("------ spte 0x%llx level %d.\n", - sptes[level - 1], level); + sptes[level], level); } - *sptep = sptes[leaf - 1]; - return reserved; } diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 4bd2f1dc0172..2ef8615f9dba 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -44,7 +44,48 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) WARN_ON(!list_empty(&kvm->arch.tdp_mmu_roots)); } -#define for_each_tdp_mmu_root(_kvm, _root) \ +static void tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root) +{ + if (kvm_mmu_put_root(kvm, root)) + kvm_tdp_mmu_free_root(kvm, root); +} + +static inline bool tdp_mmu_next_root_valid(struct kvm *kvm, + struct kvm_mmu_page *root) +{ + lockdep_assert_held(&kvm->mmu_lock); + + if (list_entry_is_head(root, &kvm->arch.tdp_mmu_roots, link)) + return false; + + kvm_mmu_get_root(kvm, root); + return true; + +} + +static inline struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, + struct kvm_mmu_page *root) +{ + struct kvm_mmu_page *next_root; + + next_root = list_next_entry(root, link); + tdp_mmu_put_root(kvm, root); + return next_root; +} + +/* + * Note: this iterator gets and puts references to the roots it iterates over. + * This makes it safe to release the MMU lock and yield within the loop, but + * if exiting the loop early, the caller must drop the reference to the most + * recent root. (Unless keeping a live reference is desirable.) + */ +#define for_each_tdp_mmu_root_yield_safe(_kvm, _root) \ + for (_root = list_first_entry(&_kvm->arch.tdp_mmu_roots, \ + typeof(*_root), link); \ + tdp_mmu_next_root_valid(_kvm, _root); \ + _root = tdp_mmu_next_root(_kvm, _root)) + +#define for_each_tdp_mmu_root(_kvm, _root) \ list_for_each_entry(_root, &_kvm->arch.tdp_mmu_roots, link) bool is_tdp_mmu_root(struct kvm *kvm, hpa_t hpa) @@ -447,18 +488,9 @@ bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end) struct kvm_mmu_page *root; bool flush = false; - for_each_tdp_mmu_root(kvm, root) { - /* - * Take a reference on the root so that it cannot be freed if - * this thread releases the MMU lock and yields in this loop. - */ - kvm_mmu_get_root(kvm, root); - + for_each_tdp_mmu_root_yield_safe(kvm, root) flush |= zap_gfn_range(kvm, root, start, end, true); - kvm_mmu_put_root(kvm, root); - } - return flush; } @@ -619,13 +651,7 @@ static int kvm_tdp_mmu_handle_hva_range(struct kvm *kvm, unsigned long start, int ret = 0; int as_id; - for_each_tdp_mmu_root(kvm, root) { - /* - * Take a reference on the root so that it cannot be freed if - * this thread releases the MMU lock and yields in this loop. - */ - kvm_mmu_get_root(kvm, root); - + for_each_tdp_mmu_root_yield_safe(kvm, root) { as_id = kvm_mmu_page_as_id(root); slots = __kvm_memslots(kvm, as_id); kvm_for_each_memslot(memslot, slots) { @@ -647,8 +673,6 @@ static int kvm_tdp_mmu_handle_hva_range(struct kvm *kvm, unsigned long start, ret |= handler(kvm, memslot, root, gfn_start, gfn_end, data); } - - kvm_mmu_put_root(kvm, root); } return ret; @@ -838,21 +862,13 @@ bool kvm_tdp_mmu_wrprot_slot(struct kvm *kvm, struct kvm_memory_slot *slot, int root_as_id; bool spte_set = false; - for_each_tdp_mmu_root(kvm, root) { + for_each_tdp_mmu_root_yield_safe(kvm, root) { root_as_id = kvm_mmu_page_as_id(root); if (root_as_id != slot->as_id) continue; - /* - * Take a reference on the root so that it cannot be freed if - * this thread releases the MMU lock and yields in this loop. - */ - kvm_mmu_get_root(kvm, root); - spte_set |= wrprot_gfn_range(kvm, root, slot->base_gfn, slot->base_gfn + slot->npages, min_level); - - kvm_mmu_put_root(kvm, root); } return spte_set; @@ -906,21 +922,13 @@ bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm, struct kvm_memory_slot *slot) int root_as_id; bool spte_set = false; - for_each_tdp_mmu_root(kvm, root) { + for_each_tdp_mmu_root_yield_safe(kvm, root) { root_as_id = kvm_mmu_page_as_id(root); if (root_as_id != slot->as_id) continue; - /* - * Take a reference on the root so that it cannot be freed if - * this thread releases the MMU lock and yields in this loop. - */ - kvm_mmu_get_root(kvm, root); - spte_set |= clear_dirty_gfn_range(kvm, root, slot->base_gfn, slot->base_gfn + slot->npages); - - kvm_mmu_put_root(kvm, root); } return spte_set; @@ -1029,21 +1037,13 @@ bool kvm_tdp_mmu_slot_set_dirty(struct kvm *kvm, struct kvm_memory_slot *slot) int root_as_id; bool spte_set = false; - for_each_tdp_mmu_root(kvm, root) { + for_each_tdp_mmu_root_yield_safe(kvm, root) { root_as_id = kvm_mmu_page_as_id(root); if (root_as_id != slot->as_id) continue; - /* - * Take a reference on the root so that it cannot be freed if - * this thread releases the MMU lock and yields in this loop. - */ - kvm_mmu_get_root(kvm, root); - spte_set |= set_dirty_gfn_range(kvm, root, slot->base_gfn, slot->base_gfn + slot->npages); - - kvm_mmu_put_root(kvm, root); } return spte_set; } @@ -1089,21 +1089,13 @@ void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm, struct kvm_mmu_page *root; int root_as_id; - for_each_tdp_mmu_root(kvm, root) { + for_each_tdp_mmu_root_yield_safe(kvm, root) { root_as_id = kvm_mmu_page_as_id(root); if (root_as_id != slot->as_id) continue; - /* - * Take a reference on the root so that it cannot be freed if - * this thread releases the MMU lock and yields in this loop. - */ - kvm_mmu_get_root(kvm, root); - zap_collapsible_spte_range(kvm, root, slot->base_gfn, slot->base_gfn + slot->npages); - - kvm_mmu_put_root(kvm, root); } } @@ -1160,16 +1152,19 @@ bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm, * Return the level of the lowest level SPTE added to sptes. * That SPTE may be non-present. */ -int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes) +int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, + int *root_level) { struct tdp_iter iter; struct kvm_mmu *mmu = vcpu->arch.mmu; - int leaf = vcpu->arch.mmu->shadow_root_level; gfn_t gfn = addr >> PAGE_SHIFT; + int leaf = -1; + + *root_level = vcpu->arch.mmu->shadow_root_level; tdp_mmu_for_each_pte(iter, mmu, gfn, gfn + 1) { leaf = iter.level; - sptes[leaf - 1] = iter.old_spte; + sptes[leaf] = iter.old_spte; } return leaf; diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index 556e065503f6..cbbdbadd1526 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -44,5 +44,7 @@ void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm, bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn); -int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes); +int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, + int *root_level); + #endif /* __KVM_X86_MMU_TDP_MMU_H */ diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index b0b667456b2e..cb4c6ee10029 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -199,6 +199,7 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) static bool svm_get_nested_state_pages(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + if (!nested_svm_vmrun_msrpm(svm)) { vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = @@ -595,6 +596,8 @@ int nested_svm_vmexit(struct vcpu_svm *svm) svm->nested.vmcb12_gpa = 0; WARN_ON_ONCE(svm->nested.nested_run_pending); + kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, &svm->vcpu); + /* in case we halted in L2 */ svm->vcpu.arch.mp_state = KVM_MP_STATE_RUNNABLE; @@ -754,6 +757,7 @@ void svm_leave_nested(struct vcpu_svm *svm) leave_guest_mode(&svm->vcpu); copy_vmcb_control_area(&vmcb->control, &hsave->control); nested_svm_uninit_mmu_context(&svm->vcpu); + vmcb_mark_all_dirty(svm->vmcb); } kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, &svm->vcpu); @@ -1194,6 +1198,10 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, * in the registers, the save area of the nested state instead * contains saved L1 state. */ + + svm->nested.nested_run_pending = + !!(kvm_state->flags & KVM_STATE_NESTED_RUN_PENDING); + copy_vmcb_control_area(&hsave->control, &svm->vmcb->control); hsave->save = *save; diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 9858d5ae9ddd..c8ffdbc81709 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -1563,6 +1563,7 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm) goto vmgexit_err; break; case SVM_VMGEXIT_NMI_COMPLETE: + case SVM_VMGEXIT_AP_HLT_LOOP: case SVM_VMGEXIT_AP_JUMP_TABLE: case SVM_VMGEXIT_UNSUPPORTED_EVENT: break; @@ -1888,6 +1889,9 @@ int sev_handle_vmgexit(struct vcpu_svm *svm) case SVM_VMGEXIT_NMI_COMPLETE: ret = svm_invoke_exit_handler(svm, SVM_EXIT_IRET); break; + case SVM_VMGEXIT_AP_HLT_LOOP: + ret = kvm_emulate_ap_reset_hold(&svm->vcpu); + break; case SVM_VMGEXIT_AP_JUMP_TABLE: { struct kvm_sev_info *sev = &to_kvm_svm(svm->vcpu.kvm)->sev_info; @@ -2001,7 +2005,7 @@ void sev_es_vcpu_load(struct vcpu_svm *svm, int cpu) * of which one step is to perform a VMLOAD. Since hardware does not * perform a VMSAVE on VMRUN, the host savearea must be updated. */ - asm volatile(__ex("vmsave") : : "a" (__sme_page_pa(sd->save_area)) : "memory"); + asm volatile(__ex("vmsave %0") : : "a" (__sme_page_pa(sd->save_area)) : "memory"); /* * Certain MSRs are restored on VMEXIT, only save ones that aren't @@ -2040,3 +2044,21 @@ void sev_es_vcpu_put(struct vcpu_svm *svm) wrmsrl(host_save_user_msrs[i].index, svm->host_user_msrs[i]); } } + +void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + /* First SIPI: Use the values as initially set by the VMM */ + if (!svm->received_first_sipi) { + svm->received_first_sipi = true; + return; + } + + /* + * Subsequent SIPI: Return from an AP Reset Hold VMGEXIT, where + * the guest will set the CS and RIP. Set SW_EXIT_INFO_2 to a + * non-zero value. + */ + ghcb_set_sw_exit_info_2(svm->ghcb, 1); +} diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index cce0143a6f80..7ef171790d02 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -3677,8 +3677,6 @@ static fastpath_t svm_exit_handlers_fastpath(struct kvm_vcpu *vcpu) return EXIT_FASTPATH_NONE; } -void __svm_vcpu_run(unsigned long vmcb_pa, unsigned long *regs); - static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, struct vcpu_svm *svm) { @@ -4384,6 +4382,14 @@ static bool svm_apic_init_signal_blocked(struct kvm_vcpu *vcpu) (vmcb_is_intercept(&svm->vmcb->control, INTERCEPT_INIT)); } +static void svm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) +{ + if (!sev_es_guest(vcpu->kvm)) + return kvm_vcpu_deliver_sipi_vector(vcpu, vector); + + sev_vcpu_deliver_sipi_vector(vcpu, vector); +} + static void svm_vm_destroy(struct kvm *kvm) { avic_vm_destroy(kvm); @@ -4526,6 +4532,8 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .msr_filter_changed = svm_msr_filter_changed, .complete_emulated_msr = svm_complete_emulated_msr, + + .vcpu_deliver_sipi_vector = svm_vcpu_deliver_sipi_vector, }; static struct kvm_x86_init_ops svm_init_ops __initdata = { diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 5431e6335e2e..0fe874ae5498 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -185,6 +185,7 @@ struct vcpu_svm { struct vmcb_save_area *vmsa; struct ghcb *ghcb; struct kvm_host_map ghcb_map; + bool received_first_sipi; /* SEV-ES scratch area support */ void *ghcb_sa; @@ -591,6 +592,7 @@ void sev_es_init_vmcb(struct vcpu_svm *svm); void sev_es_create_vcpu(struct vcpu_svm *svm); void sev_es_vcpu_load(struct vcpu_svm *svm, int cpu); void sev_es_vcpu_put(struct vcpu_svm *svm); +void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector); /* vmenter.S */ diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index e2f26564a12d..0fbb46990dfc 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -4442,6 +4442,8 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, /* trying to cancel vmlaunch/vmresume is a bug */ WARN_ON_ONCE(vmx->nested.nested_run_pending); + kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu); + /* Service the TLB flush request for L2 before switching to L1. */ if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu)) kvm_vcpu_flush_tlb_current(vcpu); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 75c9c6a0a3a4..2af05d3b0590 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -7707,6 +7707,8 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .msr_filter_changed = vmx_msr_filter_changed, .complete_emulated_msr = kvm_complete_insn_gp, .cpu_dirty_log_size = vmx_cpu_dirty_log_size, + + .vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector, }; static __init int hardware_setup(void) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 3f7c1fc7a3ce..9a8969a6dd06 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7976,17 +7976,22 @@ void kvm_arch_exit(void) kmem_cache_destroy(x86_fpu_cache); } -int kvm_vcpu_halt(struct kvm_vcpu *vcpu) +static int __kvm_vcpu_halt(struct kvm_vcpu *vcpu, int state, int reason) { ++vcpu->stat.halt_exits; if (lapic_in_kernel(vcpu)) { - vcpu->arch.mp_state = KVM_MP_STATE_HALTED; + vcpu->arch.mp_state = state; return 1; } else { - vcpu->run->exit_reason = KVM_EXIT_HLT; + vcpu->run->exit_reason = reason; return 0; } } + +int kvm_vcpu_halt(struct kvm_vcpu *vcpu) +{ + return __kvm_vcpu_halt(vcpu, KVM_MP_STATE_HALTED, KVM_EXIT_HLT); +} EXPORT_SYMBOL_GPL(kvm_vcpu_halt); int kvm_emulate_halt(struct kvm_vcpu *vcpu) @@ -8000,6 +8005,14 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_emulate_halt); +int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu) +{ + int ret = kvm_skip_emulated_instruction(vcpu); + + return __kvm_vcpu_halt(vcpu, KVM_MP_STATE_AP_RESET_HOLD, KVM_EXIT_AP_RESET_HOLD) && ret; +} +EXPORT_SYMBOL_GPL(kvm_emulate_ap_reset_hold); + #ifdef CONFIG_X86_64 static int kvm_pv_clock_pairing(struct kvm_vcpu *vcpu, gpa_t paddr, unsigned long clock_type) @@ -8789,7 +8802,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (kvm_request_pending(vcpu)) { if (kvm_check_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu)) { - if (unlikely(!kvm_x86_ops.nested_ops->get_nested_state_pages(vcpu))) { + if (WARN_ON_ONCE(!is_guest_mode(vcpu))) + ; + else if (unlikely(!kvm_x86_ops.nested_ops->get_nested_state_pages(vcpu))) { r = 0; goto out; } @@ -9094,6 +9109,7 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) kvm_apic_accept_events(vcpu); switch(vcpu->arch.mp_state) { case KVM_MP_STATE_HALTED: + case KVM_MP_STATE_AP_RESET_HOLD: vcpu->arch.pv.pv_unhalted = false; vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; @@ -9520,8 +9536,9 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, kvm_load_guest_fpu(vcpu); kvm_apic_accept_events(vcpu); - if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED && - vcpu->arch.pv.pv_unhalted) + if ((vcpu->arch.mp_state == KVM_MP_STATE_HALTED || + vcpu->arch.mp_state == KVM_MP_STATE_AP_RESET_HOLD) && + vcpu->arch.pv.pv_unhalted) mp_state->mp_state = KVM_MP_STATE_RUNNABLE; else mp_state->mp_state = vcpu->arch.mp_state; @@ -10152,6 +10169,7 @@ void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) kvm_set_segment(vcpu, &cs, VCPU_SREG_CS); kvm_rip_write(vcpu, 0); } +EXPORT_SYMBOL_GPL(kvm_vcpu_deliver_sipi_vector); int kvm_arch_hardware_enable(void) { diff --git a/arch/x86/lib/mmx_32.c b/arch/x86/lib/mmx_32.c index 4321fa02e18d..419365c48b2a 100644 --- a/arch/x86/lib/mmx_32.c +++ b/arch/x86/lib/mmx_32.c @@ -26,6 +26,16 @@ #include <asm/fpu/api.h> #include <asm/asm.h> +/* + * Use KFPU_387. MMX instructions are not affected by MXCSR, + * but both AMD and Intel documentation states that even integer MMX + * operations will result in #MF if an exception is pending in FCW. + * + * EMMS is not needed afterwards because, after calling kernel_fpu_end(), + * any subsequent user of the 387 stack will reinitialize it using + * KFPU_387. + */ + void *_mmx_memcpy(void *to, const void *from, size_t len) { void *p; @@ -37,7 +47,7 @@ void *_mmx_memcpy(void *to, const void *from, size_t len) p = to; i = len >> 6; /* len/64 */ - kernel_fpu_begin(); + kernel_fpu_begin_mask(KFPU_387); __asm__ __volatile__ ( "1: prefetch (%0)\n" /* This set is 28 bytes */ @@ -127,7 +137,7 @@ static void fast_clear_page(void *page) { int i; - kernel_fpu_begin(); + kernel_fpu_begin_mask(KFPU_387); __asm__ __volatile__ ( " pxor %%mm0, %%mm0\n" : : @@ -160,7 +170,7 @@ static void fast_copy_page(void *to, void *from) { int i; - kernel_fpu_begin(); + kernel_fpu_begin_mask(KFPU_387); /* * maybe the prefetch stuff can go before the expensive fnsave... @@ -247,7 +257,7 @@ static void fast_clear_page(void *page) { int i; - kernel_fpu_begin(); + kernel_fpu_begin_mask(KFPU_387); __asm__ __volatile__ ( " pxor %%mm0, %%mm0\n" : : @@ -282,7 +292,7 @@ static void fast_copy_page(void *to, void *from) { int i; - kernel_fpu_begin(); + kernel_fpu_begin_mask(KFPU_387); __asm__ __volatile__ ( "1: prefetch (%0)\n" diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index dfd82f51ba66..f6a9e2e36642 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -829,6 +829,8 @@ int pud_free_pmd_page(pud_t *pud, unsigned long addr) } free_page((unsigned long)pmd_sv); + + pgtable_pmd_page_dtor(virt_to_page(pmd)); free_page((unsigned long)pmd); return 1; diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c index 9e87ab010c82..e68ea5f4ad1c 100644 --- a/arch/x86/xen/enlighten_hvm.c +++ b/arch/x86/xen/enlighten_hvm.c @@ -164,10 +164,10 @@ static int xen_cpu_up_prepare_hvm(unsigned int cpu) else per_cpu(xen_vcpu_id, cpu) = cpu; rc = xen_vcpu_setup(cpu); - if (rc) + if (rc || !xen_have_vector_callback) return rc; - if (xen_have_vector_callback && xen_feature(XENFEAT_hvm_safe_pvclock)) + if (xen_feature(XENFEAT_hvm_safe_pvclock)) xen_setup_timer(cpu); rc = xen_smp_intr_init(cpu); @@ -188,6 +188,8 @@ static int xen_cpu_dead_hvm(unsigned int cpu) return 0; } +static bool no_vector_callback __initdata; + static void __init xen_hvm_guest_init(void) { if (xen_pv_domain()) @@ -207,7 +209,7 @@ static void __init xen_hvm_guest_init(void) xen_panic_handler_init(); - if (xen_feature(XENFEAT_hvm_callback_vector)) + if (!no_vector_callback && xen_feature(XENFEAT_hvm_callback_vector)) xen_have_vector_callback = 1; xen_hvm_smp_init(); @@ -233,6 +235,13 @@ static __init int xen_parse_nopv(char *arg) } early_param("xen_nopv", xen_parse_nopv); +static __init int xen_parse_no_vector_callback(char *arg) +{ + no_vector_callback = true; + return 0; +} +early_param("xen_no_vector_callback", xen_parse_no_vector_callback); + bool __init xen_hvm_need_lapic(void) { if (xen_pv_domain()) diff --git a/arch/x86/xen/smp_hvm.c b/arch/x86/xen/smp_hvm.c index f5e7db4f82ab..6ff3c887e0b9 100644 --- a/arch/x86/xen/smp_hvm.c +++ b/arch/x86/xen/smp_hvm.c @@ -33,9 +33,11 @@ static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus) int cpu; native_smp_prepare_cpus(max_cpus); - WARN_ON(xen_smp_intr_init(0)); - xen_init_lock_cpu(0); + if (xen_have_vector_callback) { + WARN_ON(xen_smp_intr_init(0)); + xen_init_lock_cpu(0); + } for_each_possible_cpu(cpu) { if (cpu == 0) @@ -50,9 +52,11 @@ static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus) static void xen_hvm_cpu_die(unsigned int cpu) { if (common_cpu_die(cpu) == 0) { - xen_smp_intr_free(cpu); - xen_uninit_lock_cpu(cpu); - xen_teardown_timer(cpu); + if (xen_have_vector_callback) { + xen_smp_intr_free(cpu); + xen_uninit_lock_cpu(cpu); + xen_teardown_timer(cpu); + } } } #else @@ -64,14 +68,19 @@ static void xen_hvm_cpu_die(unsigned int cpu) void __init xen_hvm_smp_init(void) { - if (!xen_have_vector_callback) + smp_ops.smp_prepare_boot_cpu = xen_hvm_smp_prepare_boot_cpu; + smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus; + smp_ops.smp_cpus_done = xen_smp_cpus_done; + smp_ops.cpu_die = xen_hvm_cpu_die; + + if (!xen_have_vector_callback) { +#ifdef CONFIG_PARAVIRT_SPINLOCKS + nopvspin = true; +#endif return; + } - smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus; smp_ops.smp_send_reschedule = xen_smp_send_reschedule; - smp_ops.cpu_die = xen_hvm_cpu_die; smp_ops.send_call_func_ipi = xen_smp_send_call_function_ipi; smp_ops.send_call_func_single_ipi = xen_smp_send_call_function_single_ipi; - smp_ops.smp_prepare_boot_cpu = xen_hvm_smp_prepare_boot_cpu; - smp_ops.smp_cpus_done = xen_smp_cpus_done; } diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild index 9718e9593564..854c5e07e867 100644 --- a/arch/xtensa/include/asm/Kbuild +++ b/arch/xtensa/include/asm/Kbuild @@ -2,7 +2,6 @@ generated-y += syscall_table.h generic-y += extable.h generic-y += kvm_para.h -generic-y += local64.h generic-y += mcs_spinlock.h generic-y += param.h generic-y += qrwlock.h |