diff options
Diffstat (limited to 'arch/x86/include')
104 files changed, 1574 insertions, 1028 deletions
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index a303d7b7d763..2f01eb4d6208 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -142,6 +142,8 @@ static inline u64 acpi_arch_get_root_pointer(void) void acpi_generic_reduced_hw_init(void); +u64 x86_default_get_root_pointer(void); + #else /* !CONFIG_ACPI */ #define acpi_lapic 0 @@ -153,6 +155,11 @@ static inline void disable_acpi(void) { } static inline void acpi_generic_reduced_hw_init(void) { } +static inline u64 x86_default_get_root_pointer(void) +{ + return 0; +} + #endif /* !CONFIG_ACPI */ #define ARCH_HAS_POWER_INIT 1 diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 4cd6a3b71824..0660e14690c8 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -174,7 +174,7 @@ static inline int alternatives_text_reserved(void *start, void *end) /* * Alternative inline assembly with input. * - * Pecularities: + * Peculiarities: * No memory clobber here. * Argument numbers start with 1. * Best is to use constraints that are fixed size (like (%1) ... "r") diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h index fddb6d26239f..1ae4e5791afa 100644 --- a/arch/x86/include/asm/amd_nb.h +++ b/arch/x86/include/asm/amd_nb.h @@ -103,6 +103,9 @@ static inline u16 amd_pci_dev_to_node_id(struct pci_dev *pdev) static inline bool amd_gart_present(void) { + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) + return false; + /* GART present only on Fam15h, upto model 0fh */ if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 || (boot_cpu_data.x86 == 0x15 && boot_cpu_data.x86_model < 0x10)) diff --git a/arch/x86/include/asm/arch_hweight.h b/arch/x86/include/asm/arch_hweight.h index 34a10b2d5b73..fc0693569f7a 100644 --- a/arch/x86/include/asm/arch_hweight.h +++ b/arch/x86/include/asm/arch_hweight.h @@ -5,15 +5,9 @@ #include <asm/cpufeatures.h> #ifdef CONFIG_64BIT -/* popcnt %edi, %eax */ -#define POPCNT32 ".byte 0xf3,0x0f,0xb8,0xc7" -/* popcnt %rdi, %rax */ -#define POPCNT64 ".byte 0xf3,0x48,0x0f,0xb8,0xc7" #define REG_IN "D" #define REG_OUT "a" #else -/* popcnt %eax, %eax */ -#define POPCNT32 ".byte 0xf3,0x0f,0xb8,0xc0" #define REG_IN "a" #define REG_OUT "a" #endif @@ -24,7 +18,7 @@ static __always_inline unsigned int __arch_hweight32(unsigned int w) { unsigned int res; - asm (ALTERNATIVE("call __sw_hweight32", POPCNT32, X86_FEATURE_POPCNT) + asm (ALTERNATIVE("call __sw_hweight32", "popcntl %1, %0", X86_FEATURE_POPCNT) : "="REG_OUT (res) : REG_IN (w)); @@ -52,7 +46,7 @@ static __always_inline unsigned long __arch_hweight64(__u64 w) { unsigned long res; - asm (ALTERNATIVE("call __sw_hweight64", POPCNT64, X86_FEATURE_POPCNT) + asm (ALTERNATIVE("call __sw_hweight64", "popcntq %1, %0", X86_FEATURE_POPCNT) : "="REG_OUT (res) : REG_IN (w)); diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index 990770f9e76b..6467757bb39f 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -130,6 +130,9 @@ # define _ASM_EXTABLE(from, to) \ _ASM_EXTABLE_HANDLE(from, to, ex_handler_default) +# define _ASM_EXTABLE_UA(from, to) \ + _ASM_EXTABLE_HANDLE(from, to, ex_handler_uaccess) + # define _ASM_EXTABLE_FAULT(from, to) \ _ASM_EXTABLE_HANDLE(from, to, ex_handler_fault) @@ -165,8 +168,8 @@ jmp copy_user_handle_tail .previous - _ASM_EXTABLE(100b,103b) - _ASM_EXTABLE(101b,103b) + _ASM_EXTABLE_UA(100b, 103b) + _ASM_EXTABLE_UA(101b, 103b) .endm #else @@ -182,6 +185,9 @@ # define _ASM_EXTABLE(from, to) \ _ASM_EXTABLE_HANDLE(from, to, ex_handler_default) +# define _ASM_EXTABLE_UA(from, to) \ + _ASM_EXTABLE_HANDLE(from, to, ex_handler_uaccess) + # define _ASM_EXTABLE_FAULT(from, to) \ _ASM_EXTABLE_HANDLE(from, to, ex_handler_fault) diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h index ce84388e540c..ea3d95275b43 100644 --- a/arch/x86/include/asm/atomic.h +++ b/arch/x86/include/asm/atomic.h @@ -82,7 +82,7 @@ static __always_inline void arch_atomic_sub(int i, atomic_t *v) */ static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v) { - GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, "er", i, "%0", e); + return GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, e, "er", i); } #define arch_atomic_sub_and_test arch_atomic_sub_and_test @@ -122,7 +122,7 @@ static __always_inline void arch_atomic_dec(atomic_t *v) */ static __always_inline bool arch_atomic_dec_and_test(atomic_t *v) { - GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", e); + return GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, e); } #define arch_atomic_dec_and_test arch_atomic_dec_and_test @@ -136,7 +136,7 @@ static __always_inline bool arch_atomic_dec_and_test(atomic_t *v) */ static __always_inline bool arch_atomic_inc_and_test(atomic_t *v) { - GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", e); + return GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, e); } #define arch_atomic_inc_and_test arch_atomic_inc_and_test @@ -151,7 +151,7 @@ static __always_inline bool arch_atomic_inc_and_test(atomic_t *v) */ static __always_inline bool arch_atomic_add_negative(int i, atomic_t *v) { - GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, "er", i, "%0", s); + return GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, s, "er", i); } #define arch_atomic_add_negative arch_atomic_add_negative diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h index 5f851d92eecd..dadc20adba21 100644 --- a/arch/x86/include/asm/atomic64_64.h +++ b/arch/x86/include/asm/atomic64_64.h @@ -73,7 +73,7 @@ static inline void arch_atomic64_sub(long i, atomic64_t *v) */ static inline bool arch_atomic64_sub_and_test(long i, atomic64_t *v) { - GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, "er", i, "%0", e); + return GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, e, "er", i); } #define arch_atomic64_sub_and_test arch_atomic64_sub_and_test @@ -115,7 +115,7 @@ static __always_inline void arch_atomic64_dec(atomic64_t *v) */ static inline bool arch_atomic64_dec_and_test(atomic64_t *v) { - GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, "%0", e); + return GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, e); } #define arch_atomic64_dec_and_test arch_atomic64_dec_and_test @@ -129,7 +129,7 @@ static inline bool arch_atomic64_dec_and_test(atomic64_t *v) */ static inline bool arch_atomic64_inc_and_test(atomic64_t *v) { - GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, "%0", e); + return GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, e); } #define arch_atomic64_inc_and_test arch_atomic64_inc_and_test @@ -144,7 +144,7 @@ static inline bool arch_atomic64_inc_and_test(atomic64_t *v) */ static inline bool arch_atomic64_add_negative(long i, atomic64_t *v) { - GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, "er", i, "%0", s); + return GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, s, "er", i); } #define arch_atomic64_add_negative arch_atomic64_add_negative diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 9f645ba57dbb..ad7b210aa3f6 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -217,8 +217,7 @@ static __always_inline void change_bit(long nr, volatile unsigned long *addr) */ static __always_inline bool test_and_set_bit(long nr, volatile unsigned long *addr) { - GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(bts), - *addr, "Ir", nr, "%0", c); + return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(bts), *addr, c, "Ir", nr); } /** @@ -264,8 +263,7 @@ static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long * */ static __always_inline bool test_and_clear_bit(long nr, volatile unsigned long *addr) { - GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btr), - *addr, "Ir", nr, "%0", c); + return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btr), *addr, c, "Ir", nr); } /** @@ -318,8 +316,7 @@ static __always_inline bool __test_and_change_bit(long nr, volatile unsigned lon */ static __always_inline bool test_and_change_bit(long nr, volatile unsigned long *addr) { - GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btc), - *addr, "Ir", nr, "%0", c); + return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btc), *addr, c, "Ir", nr); } static __always_inline bool constant_test_bit(long nr, const volatile unsigned long *addr) @@ -451,7 +448,7 @@ static __always_inline int ffs(int x) * set bit if value is nonzero. The last (most significant) bit is * at position 32. */ -static __always_inline int fls(int x) +static __always_inline int fls(unsigned int x) { int r; diff --git a/arch/x86/include/asm/bootparam_utils.h b/arch/x86/include/asm/bootparam_utils.h index a07ffd23e4dd..f6f6ef436599 100644 --- a/arch/x86/include/asm/bootparam_utils.h +++ b/arch/x86/include/asm/bootparam_utils.h @@ -36,6 +36,7 @@ static void sanitize_boot_params(struct boot_params *boot_params) */ if (boot_params->sentinel) { /* fields in boot_params are left uninitialized, clear them */ + boot_params->acpi_rsdp_addr = 0; memset(&boot_params->ext_ramdisk_image, 0, (char *)&boot_params->efi_info - (char *)&boot_params->ext_ramdisk_image); diff --git a/arch/x86/include/asm/cacheinfo.h b/arch/x86/include/asm/cacheinfo.h index e958e28f7ab5..86b63c7feab7 100644 --- a/arch/x86/include/asm/cacheinfo.h +++ b/arch/x86/include/asm/cacheinfo.h @@ -3,5 +3,6 @@ #define _ASM_X86_CACHEINFO_H void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id); +void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id); #endif /* _ASM_X86_CACHEINFO_H */ diff --git a/arch/x86/include/asm/checksum_32.h b/arch/x86/include/asm/checksum_32.h index 7a659c74cd03..f57b94e02c57 100644 --- a/arch/x86/include/asm/checksum_32.h +++ b/arch/x86/include/asm/checksum_32.h @@ -182,7 +182,7 @@ static inline __wsum csum_and_copy_to_user(const void *src, __wsum ret; might_sleep(); - if (access_ok(VERIFY_WRITE, dst, len)) { + if (access_ok(dst, len)) { stac(); ret = csum_partial_copy_generic(src, (__force void *)dst, len, sum, NULL, err_ptr); diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h index a55d79b233d3..a8bfac131256 100644 --- a/arch/x86/include/asm/cmpxchg.h +++ b/arch/x86/include/asm/cmpxchg.h @@ -7,7 +7,7 @@ #include <asm/alternative.h> /* Provides LOCK_PREFIX */ /* - * Non-existant functions to indicate usage errors at link time + * Non-existent functions to indicate usage errors at link time * (or compile-time if the compiler implements __compiletime_error(). */ extern void __xchg_wrong_size(void) @@ -242,10 +242,12 @@ extern void __add_wrong_size(void) BUILD_BUG_ON(sizeof(*(p2)) != sizeof(long)); \ VM_BUG_ON((unsigned long)(p1) % (2 * sizeof(long))); \ VM_BUG_ON((unsigned long)((p1) + 1) != (unsigned long)(p2)); \ - asm volatile(pfx "cmpxchg%c4b %2; sete %0" \ - : "=a" (__ret), "+d" (__old2), \ - "+m" (*(p1)), "+m" (*(p2)) \ - : "i" (2 * sizeof(long)), "a" (__old1), \ + asm volatile(pfx "cmpxchg%c5b %1" \ + CC_SET(e) \ + : CC_OUT(e) (__ret), \ + "+m" (*(p1)), "+m" (*(p2)), \ + "+a" (__old1), "+d" (__old2) \ + : "i" (2 * sizeof(long)), \ "b" (__new1), "c" (__new2)); \ __ret; \ }) diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h index fb97cf7c4137..22c4dfe65992 100644 --- a/arch/x86/include/asm/compat.h +++ b/arch/x86/include/asm/compat.h @@ -12,38 +12,23 @@ #include <asm/user32.h> #include <asm/unistd.h> +#include <asm-generic/compat.h> + #define COMPAT_USER_HZ 100 #define COMPAT_UTS_MACHINE "i686\0\0" -typedef u32 compat_size_t; -typedef s32 compat_ssize_t; -typedef s32 compat_clock_t; -typedef s32 compat_pid_t; typedef u16 __compat_uid_t; typedef u16 __compat_gid_t; typedef u32 __compat_uid32_t; typedef u32 __compat_gid32_t; typedef u16 compat_mode_t; -typedef u32 compat_ino_t; typedef u16 compat_dev_t; -typedef s32 compat_off_t; -typedef s64 compat_loff_t; typedef u16 compat_nlink_t; typedef u16 compat_ipc_pid_t; -typedef s32 compat_daddr_t; typedef u32 compat_caddr_t; typedef __kernel_fsid_t compat_fsid_t; -typedef s32 compat_timer_t; -typedef s32 compat_key_t; - -typedef s32 compat_int_t; -typedef s32 compat_long_t; typedef s64 __attribute__((aligned(4))) compat_s64; -typedef u32 compat_uint_t; -typedef u32 compat_ulong_t; -typedef u32 compat_u32; typedef u64 __attribute__((aligned(4))) compat_u64; -typedef u32 compat_uptr_t; struct compat_stat { compat_dev_t st_dev; @@ -232,14 +217,21 @@ static inline bool in_x32_syscall(void) return false; } -static inline bool in_compat_syscall(void) +static inline bool in_32bit_syscall(void) { return in_ia32_syscall() || in_x32_syscall(); } + +#ifdef CONFIG_COMPAT +static inline bool in_compat_syscall(void) +{ + return in_32bit_syscall(); +} #define in_compat_syscall in_compat_syscall /* override the generic impl */ +#endif struct compat_siginfo; int __copy_siginfo_to_user32(struct compat_siginfo __user *to, - const siginfo_t *from, bool x32_ABI); + const kernel_siginfo_t *from, bool x32_ABI); #endif /* _ASM_X86_COMPAT_H */ diff --git a/arch/x86/include/asm/cpu_entry_area.h b/arch/x86/include/asm/cpu_entry_area.h index 4a7884b8dca5..29c706415443 100644 --- a/arch/x86/include/asm/cpu_entry_area.h +++ b/arch/x86/include/asm/cpu_entry_area.h @@ -30,8 +30,6 @@ struct cpu_entry_area { */ struct tss_struct tss; - char entry_trampoline[PAGE_SIZE]; - #ifdef CONFIG_X86_64 /* * Exception stacks used for IST entries. diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index aced6c9290d6..ce95b8cbd229 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -140,7 +140,7 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit); #define setup_force_cpu_bug(bit) setup_force_cpu_cap(bit) -#if defined(__clang__) && !defined(CC_HAVE_ASM_GOTO) +#if defined(__clang__) && !defined(CONFIG_CC_HAS_ASM_GOTO) /* * Workaround for the sake of BPF compilation which utilizes kernel diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 89a048c2faec..6d6122524711 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -281,9 +281,11 @@ #define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */ #define X86_FEATURE_IRPERF (13*32+ 1) /* Instructions Retired Count */ #define X86_FEATURE_XSAVEERPTR (13*32+ 2) /* Always save/restore FP error pointers */ +#define X86_FEATURE_WBNOINVD (13*32+ 9) /* WBNOINVD instruction */ #define X86_FEATURE_AMD_IBPB (13*32+12) /* "" Indirect Branch Prediction Barrier */ #define X86_FEATURE_AMD_IBRS (13*32+14) /* "" Indirect Branch Restricted Speculation */ #define X86_FEATURE_AMD_STIBP (13*32+15) /* "" Single Thread Indirect Branch Predictors */ +#define X86_FEATURE_AMD_STIBP_ALWAYS_ON (13*32+17) /* "" Single Thread Indirect Branch Predictors always-on preferred */ #define X86_FEATURE_AMD_SSBD (13*32+24) /* "" Speculative Store Bypass Disable */ #define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */ #define X86_FEATURE_AMD_SSB_NO (13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */ @@ -331,6 +333,8 @@ #define X86_FEATURE_LA57 (16*32+16) /* 5-level page tables */ #define X86_FEATURE_RDPID (16*32+22) /* RDPID instruction */ #define X86_FEATURE_CLDEMOTE (16*32+25) /* CLDEMOTE instruction */ +#define X86_FEATURE_MOVDIRI (16*32+27) /* MOVDIRI instruction */ +#define X86_FEATURE_MOVDIR64B (16*32+28) /* MOVDIR64B instruction */ /* AMD-defined CPU features, CPUID level 0x80000007 (EBX), word 17 */ #define X86_FEATURE_OVERFLOW_RECOV (17*32+ 0) /* MCA overflow recovery support */ diff --git a/arch/x86/include/asm/crash.h b/arch/x86/include/asm/crash.h index a7adb2bfbf0b..0acf5ee45a21 100644 --- a/arch/x86/include/asm/crash.h +++ b/arch/x86/include/asm/crash.h @@ -6,5 +6,6 @@ int crash_load_segments(struct kimage *image); int crash_copy_backup_region(struct kimage *image); int crash_setup_memmap_entries(struct kimage *image, struct boot_params *params); +void crash_smp_send_stop(void); #endif /* _ASM_X86_CRASH_H */ diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h index 4505ac2735ad..9e5ca30738e5 100644 --- a/arch/x86/include/asm/debugreg.h +++ b/arch/x86/include/asm/debugreg.h @@ -8,7 +8,7 @@ DECLARE_PER_CPU(unsigned long, cpu_dr7); -#ifndef CONFIG_PARAVIRT +#ifndef CONFIG_PARAVIRT_XXL /* * These special macros can be used to get or set a debugging register */ diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index 13c5ee878a47..68a99d2a5f33 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -108,7 +108,7 @@ static inline int desc_empty(const void *ptr) return !(desc[0] | desc[1]); } -#ifdef CONFIG_PARAVIRT +#ifdef CONFIG_PARAVIRT_XXL #include <asm/paravirt.h> #else #define load_TR_desc() native_load_tr_desc() @@ -134,7 +134,7 @@ static inline void paravirt_alloc_ldt(struct desc_struct *ldt, unsigned entries) static inline void paravirt_free_ldt(struct desc_struct *ldt, unsigned entries) { } -#endif /* CONFIG_PARAVIRT */ +#endif /* CONFIG_PARAVIRT_XXL */ #define store_ldt(ldt) asm("sldt %0" : "=m"(ldt)) diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index 33833d1909af..a5ea841cc6d2 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -16,6 +16,12 @@ # define DISABLE_MPX (1<<(X86_FEATURE_MPX & 31)) #endif +#ifdef CONFIG_X86_SMAP +# define DISABLE_SMAP 0 +#else +# define DISABLE_SMAP (1<<(X86_FEATURE_SMAP & 31)) +#endif + #ifdef CONFIG_X86_INTEL_UMIP # define DISABLE_UMIP 0 #else @@ -68,7 +74,7 @@ #define DISABLED_MASK6 0 #define DISABLED_MASK7 (DISABLE_PTI) #define DISABLED_MASK8 0 -#define DISABLED_MASK9 (DISABLE_MPX) +#define DISABLED_MASK9 (DISABLE_MPX|DISABLE_SMAP) #define DISABLED_MASK10 0 #define DISABLED_MASK11 0 #define DISABLED_MASK12 0 diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index cec5fae23eb3..107283b1eb1e 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -19,7 +19,7 @@ * This is the main reason why we're doing stable VA mappings for RT * services. * - * This flag is used in conjuction with a chicken bit called + * This flag is used in conjunction with a chicken bit called * "efi=old_map" which can be used as a fallback to the old runtime * services mapping method in case there's some b0rkage with a * particular EFI implementation (haha, it is hard to hold up the @@ -82,8 +82,7 @@ struct efi_scratch { #define arch_efi_call_virt_setup() \ ({ \ efi_sync_low_kernel_mappings(); \ - preempt_disable(); \ - __kernel_fpu_begin(); \ + kernel_fpu_begin(); \ firmware_restrict_branch_speculation_start(); \ \ if (!efi_enabled(EFI_OLD_MEMMAP)) \ @@ -99,8 +98,7 @@ struct efi_scratch { efi_switch_mm(efi_scratch.prev_mm); \ \ firmware_restrict_branch_speculation_end(); \ - __kernel_fpu_end(); \ - preempt_enable(); \ + kernel_fpu_end(); \ }) extern void __iomem *__init efi_ioremap(unsigned long addr, unsigned long size, @@ -140,6 +138,9 @@ extern void __init efi_apply_memmap_quirks(void); extern int __init efi_reuse_config(u64 tables, int nr_tables); extern void efi_delete_dummy_variable(void); extern void efi_switch_mm(struct mm_struct *mm); +extern void efi_recover_from_page_fault(unsigned long phys_addr); +extern void efi_free_boot_services(void); +extern void efi_reserve_boot_services(void); struct efi_setup_data { u64 fw_vendor; diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index 0d157d2a1e2a..69c0f892e310 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -10,6 +10,7 @@ #include <asm/ptrace.h> #include <asm/user.h> #include <asm/auxvec.h> +#include <asm/fsgsbase.h> typedef unsigned long elf_greg_t; @@ -62,8 +63,7 @@ typedef struct user_fxsr_struct elf_fpxregset_t; #define R_X86_64_PC16 13 /* 16 bit sign extended pc relative */ #define R_X86_64_8 14 /* Direct 8 bit sign extended */ #define R_X86_64_PC8 15 /* 8 bit sign extended pc relative */ - -#define R_X86_64_NUM 16 +#define R_X86_64_PC64 24 /* Place relative 64-bit signed */ /* * These are used to set parameters in the core dumps. @@ -205,7 +205,6 @@ void set_personality_ia32(bool); #define ELF_CORE_COPY_REGS(pr_reg, regs) \ do { \ - unsigned long base; \ unsigned v; \ (pr_reg)[0] = (regs)->r15; \ (pr_reg)[1] = (regs)->r14; \ @@ -228,8 +227,8 @@ do { \ (pr_reg)[18] = (regs)->flags; \ (pr_reg)[19] = (regs)->sp; \ (pr_reg)[20] = (regs)->ss; \ - rdmsrl(MSR_FS_BASE, base); (pr_reg)[21] = base; \ - rdmsrl(MSR_KERNEL_GS_BASE, base); (pr_reg)[22] = base; \ + (pr_reg)[21] = x86_fsbase_read_cpu(); \ + (pr_reg)[22] = x86_gsbase_read_cpu_inactive(); \ asm("movl %%ds,%0" : "=r" (v)); (pr_reg)[23] = v; \ asm("movl %%es,%0" : "=r" (v)); (pr_reg)[24] = v; \ asm("movl %%fs,%0" : "=r" (v)); (pr_reg)[25] = v; \ diff --git a/arch/x86/include/asm/extable.h b/arch/x86/include/asm/extable.h index f9c3a5d502f4..d8c2198d543b 100644 --- a/arch/x86/include/asm/extable.h +++ b/arch/x86/include/asm/extable.h @@ -29,7 +29,8 @@ struct pt_regs; (b)->handler = (tmp).handler - (delta); \ } while (0) -extern int fixup_exception(struct pt_regs *regs, int trapnr); +extern int fixup_exception(struct pt_regs *regs, int trapnr, + unsigned long error_code, unsigned long fault_addr); extern int fixup_bug(struct pt_regs *regs, int trapnr); extern bool ex_has_fault_handler(unsigned long ip); extern void early_fixup_exception(struct pt_regs *regs, int trapnr); diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index 6390bd8c141b..50ba74a34a37 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -162,7 +162,7 @@ void __native_set_fixmap(enum fixed_addresses idx, pte_t pte); void native_set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t flags); -#ifndef CONFIG_PARAVIRT +#ifndef CONFIG_PARAVIRT_XXL static inline void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t flags) { diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h index a9caac9d4a72..b56d504af654 100644 --- a/arch/x86/include/asm/fpu/api.h +++ b/arch/x86/include/asm/fpu/api.h @@ -12,17 +12,12 @@ #define _ASM_X86_FPU_API_H /* - * Careful: __kernel_fpu_begin/end() must be called with preempt disabled - * and they don't touch the preempt state on their own. - * If you enable preemption after __kernel_fpu_begin(), preempt notifier - * should call the __kernel_fpu_end() to prevent the kernel/user FPU - * state from getting corrupted. KVM for example uses this model. - * - * All other cases use kernel_fpu_begin/end() which disable preemption - * during kernel FPU usage. + * 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 + * irq_fpu_usable() if it is possible. */ -extern void __kernel_fpu_begin(void); -extern void __kernel_fpu_end(void); extern void kernel_fpu_begin(void); extern void kernel_fpu_end(void); extern bool irq_fpu_usable(void); diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 69dcdf195b61..fa2c93cb42a2 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -106,6 +106,9 @@ extern void fpstate_sanitize_xstate(struct fpu *fpu); #define user_insn(insn, output, input...) \ ({ \ int err; \ + \ + might_fault(); \ + \ asm volatile(ASM_STAC "\n" \ "1:" #insn "\n\t" \ "2: " ASM_CLAC "\n" \ diff --git a/arch/x86/include/asm/fsgsbase.h b/arch/x86/include/asm/fsgsbase.h new file mode 100644 index 000000000000..bca4c743de77 --- /dev/null +++ b/arch/x86/include/asm/fsgsbase.h @@ -0,0 +1,56 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_FSGSBASE_H +#define _ASM_FSGSBASE_H + +#ifndef __ASSEMBLY__ + +#ifdef CONFIG_X86_64 + +#include <asm/msr-index.h> + +/* + * Read/write a task's FSBASE or GSBASE. This returns the value that + * the FS/GS base would have (if the task were to be resumed). These + * work on the current task or on a non-running (typically stopped + * ptrace child) task. + */ +extern unsigned long x86_fsbase_read_task(struct task_struct *task); +extern unsigned long x86_gsbase_read_task(struct task_struct *task); +extern void x86_fsbase_write_task(struct task_struct *task, unsigned long fsbase); +extern void x86_gsbase_write_task(struct task_struct *task, unsigned long gsbase); + +/* Helper functions for reading/writing FS/GS base */ + +static inline unsigned long x86_fsbase_read_cpu(void) +{ + unsigned long fsbase; + + rdmsrl(MSR_FS_BASE, fsbase); + + return fsbase; +} + +static inline unsigned long x86_gsbase_read_cpu_inactive(void) +{ + unsigned long gsbase; + + rdmsrl(MSR_KERNEL_GS_BASE, gsbase); + + return gsbase; +} + +static inline void x86_fsbase_write_cpu(unsigned long fsbase) +{ + wrmsrl(MSR_FS_BASE, fsbase); +} + +static inline void x86_gsbase_write_cpu_inactive(unsigned long gsbase) +{ + wrmsrl(MSR_KERNEL_GS_BASE, gsbase); +} + +#endif /* CONFIG_X86_64 */ + +#endif /* __ASSEMBLY__ */ + +#endif /* _ASM_FSGSBASE_H */ diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index c18ed65287d5..cf350639e76d 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -76,9 +76,7 @@ static inline bool arch_syscall_match_sym_name(const char *sym, const char *name #define ARCH_TRACE_IGNORE_COMPAT_SYSCALLS 1 static inline bool arch_trace_is_compat_syscall(struct pt_regs *regs) { - if (in_compat_syscall()) - return true; - return false; + return in_32bit_syscall(); } #endif /* CONFIG_FTRACE_SYSCALLS && CONFIG_IA32_EMULATION */ #endif /* !COMPILE_OFFSETS */ diff --git a/arch/x86/include/asm/futex.h b/arch/x86/include/asm/futex.h index de4d68852d3a..13c83fe97988 100644 --- a/arch/x86/include/asm/futex.h +++ b/arch/x86/include/asm/futex.h @@ -20,7 +20,7 @@ "3:\tmov\t%3, %1\n" \ "\tjmp\t2b\n" \ "\t.previous\n" \ - _ASM_EXTABLE(1b, 3b) \ + _ASM_EXTABLE_UA(1b, 3b) \ : "=r" (oldval), "=r" (ret), "+m" (*uaddr) \ : "i" (-EFAULT), "0" (oparg), "1" (0)) @@ -36,8 +36,8 @@ "4:\tmov\t%5, %1\n" \ "\tjmp\t3b\n" \ "\t.previous\n" \ - _ASM_EXTABLE(1b, 4b) \ - _ASM_EXTABLE(2b, 4b) \ + _ASM_EXTABLE_UA(1b, 4b) \ + _ASM_EXTABLE_UA(2b, 4b) \ : "=&a" (oldval), "=&r" (ret), \ "+m" (*uaddr), "=&r" (tem) \ : "r" (oparg), "i" (-EFAULT), "1" (0)) diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h index 5ed826da5e07..7469d321f072 100644 --- a/arch/x86/include/asm/hugetlb.h +++ b/arch/x86/include/asm/hugetlb.h @@ -13,75 +13,6 @@ static inline int is_hugepage_only_range(struct mm_struct *mm, return 0; } -/* - * If the arch doesn't supply something else, assume that hugepage - * size aligned regions are ok without further preparation. - */ -static inline int prepare_hugepage_range(struct file *file, - unsigned long addr, unsigned long len) -{ - struct hstate *h = hstate_file(file); - if (len & ~huge_page_mask(h)) - return -EINVAL; - if (addr & ~huge_page_mask(h)) - return -EINVAL; - return 0; -} - -static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb, - unsigned long addr, unsigned long end, - unsigned long floor, - unsigned long ceiling) -{ - free_pgd_range(tlb, addr, end, floor, ceiling); -} - -static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte) -{ - set_pte_at(mm, addr, ptep, pte); -} - -static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm, - unsigned long addr, pte_t *ptep) -{ - return ptep_get_and_clear(mm, addr, ptep); -} - -static inline void huge_ptep_clear_flush(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) -{ - ptep_clear_flush(vma, addr, ptep); -} - -static inline int huge_pte_none(pte_t pte) -{ - return pte_none(pte); -} - -static inline pte_t huge_pte_wrprotect(pte_t pte) -{ - return pte_wrprotect(pte); -} - -static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, - unsigned long addr, pte_t *ptep) -{ - ptep_set_wrprotect(mm, addr, ptep); -} - -static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep, - pte_t pte, int dirty) -{ - return ptep_set_access_flags(vma, addr, ptep, pte, dirty); -} - -static inline pte_t huge_ptep_get(pte_t *ptep) -{ - return *ptep; -} - static inline void arch_clear_hugepage_flags(struct page *page) { } diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h index 00e01d215f74..2bdbbbcfa393 100644 --- a/arch/x86/include/asm/hyperv-tlfs.h +++ b/arch/x86/include/asm/hyperv-tlfs.h @@ -10,6 +10,7 @@ #define _ASM_X86_HYPERV_TLFS_H #include <linux/types.h> +#include <asm/page.h> /* * The below CPUID leaves are present if VersionAndFeatures.HypervisorPresent @@ -30,156 +31,150 @@ /* * Feature identification. EAX indicates which features are available * to the partition based upon the current partition privileges. + * These are HYPERV_CPUID_FEATURES.EAX bits. */ /* VP Runtime (HV_X64_MSR_VP_RUNTIME) available */ -#define HV_X64_MSR_VP_RUNTIME_AVAILABLE (1 << 0) +#define HV_X64_MSR_VP_RUNTIME_AVAILABLE BIT(0) /* Partition Reference Counter (HV_X64_MSR_TIME_REF_COUNT) available*/ -#define HV_MSR_TIME_REF_COUNT_AVAILABLE (1 << 1) -/* Partition reference TSC MSR is available */ -#define HV_MSR_REFERENCE_TSC_AVAILABLE (1 << 9) - -/* A partition's reference time stamp counter (TSC) page */ -#define HV_X64_MSR_REFERENCE_TSC 0x40000021 - -/* - * There is a single feature flag that signifies if the partition has access - * to MSRs with local APIC and TSC frequencies. - */ -#define HV_X64_ACCESS_FREQUENCY_MSRS (1 << 11) - -/* AccessReenlightenmentControls privilege */ -#define HV_X64_ACCESS_REENLIGHTENMENT BIT(13) - +#define HV_MSR_TIME_REF_COUNT_AVAILABLE BIT(1) /* * Basic SynIC MSRs (HV_X64_MSR_SCONTROL through HV_X64_MSR_EOM * and HV_X64_MSR_SINT0 through HV_X64_MSR_SINT15) available */ -#define HV_X64_MSR_SYNIC_AVAILABLE (1 << 2) +#define HV_X64_MSR_SYNIC_AVAILABLE BIT(2) /* * Synthetic Timer MSRs (HV_X64_MSR_STIMER0_CONFIG through * HV_X64_MSR_STIMER3_COUNT) available */ -#define HV_MSR_SYNTIMER_AVAILABLE (1 << 3) +#define HV_MSR_SYNTIMER_AVAILABLE BIT(3) /* * APIC access MSRs (HV_X64_MSR_EOI, HV_X64_MSR_ICR and HV_X64_MSR_TPR) * are available */ -#define HV_X64_MSR_APIC_ACCESS_AVAILABLE (1 << 4) +#define HV_X64_MSR_APIC_ACCESS_AVAILABLE BIT(4) /* Hypercall MSRs (HV_X64_MSR_GUEST_OS_ID and HV_X64_MSR_HYPERCALL) available*/ -#define HV_X64_MSR_HYPERCALL_AVAILABLE (1 << 5) +#define HV_X64_MSR_HYPERCALL_AVAILABLE BIT(5) /* Access virtual processor index MSR (HV_X64_MSR_VP_INDEX) available*/ -#define HV_X64_MSR_VP_INDEX_AVAILABLE (1 << 6) +#define HV_X64_MSR_VP_INDEX_AVAILABLE BIT(6) /* Virtual system reset MSR (HV_X64_MSR_RESET) is available*/ -#define HV_X64_MSR_RESET_AVAILABLE (1 << 7) - /* - * Access statistics pages MSRs (HV_X64_MSR_STATS_PARTITION_RETAIL_PAGE, - * HV_X64_MSR_STATS_PARTITION_INTERNAL_PAGE, HV_X64_MSR_STATS_VP_RETAIL_PAGE, - * HV_X64_MSR_STATS_VP_INTERNAL_PAGE) available - */ -#define HV_X64_MSR_STAT_PAGES_AVAILABLE (1 << 8) - -/* Frequency MSRs available */ -#define HV_FEATURE_FREQUENCY_MSRS_AVAILABLE (1 << 8) - -/* Crash MSR available */ -#define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE (1 << 10) - -/* stimer Direct Mode is available */ -#define HV_STIMER_DIRECT_MODE_AVAILABLE (1 << 19) +#define HV_X64_MSR_RESET_AVAILABLE BIT(7) +/* + * Access statistics pages MSRs (HV_X64_MSR_STATS_PARTITION_RETAIL_PAGE, + * HV_X64_MSR_STATS_PARTITION_INTERNAL_PAGE, HV_X64_MSR_STATS_VP_RETAIL_PAGE, + * HV_X64_MSR_STATS_VP_INTERNAL_PAGE) available + */ +#define HV_X64_MSR_STAT_PAGES_AVAILABLE BIT(8) +/* Partition reference TSC MSR is available */ +#define HV_MSR_REFERENCE_TSC_AVAILABLE BIT(9) +/* Partition Guest IDLE MSR is available */ +#define HV_X64_MSR_GUEST_IDLE_AVAILABLE BIT(10) +/* + * There is a single feature flag that signifies if the partition has access + * to MSRs with local APIC and TSC frequencies. + */ +#define HV_X64_ACCESS_FREQUENCY_MSRS BIT(11) +/* AccessReenlightenmentControls privilege */ +#define HV_X64_ACCESS_REENLIGHTENMENT BIT(13) /* - * Feature identification: EBX indicates which flags were specified at - * partition creation. The format is the same as the partition creation - * flag structure defined in section Partition Creation Flags. + * Feature identification: indicates which flags were specified at partition + * creation. The format is the same as the partition creation flag structure + * defined in section Partition Creation Flags. + * These are HYPERV_CPUID_FEATURES.EBX bits. */ -#define HV_X64_CREATE_PARTITIONS (1 << 0) -#define HV_X64_ACCESS_PARTITION_ID (1 << 1) -#define HV_X64_ACCESS_MEMORY_POOL (1 << 2) -#define HV_X64_ADJUST_MESSAGE_BUFFERS (1 << 3) -#define HV_X64_POST_MESSAGES (1 << 4) -#define HV_X64_SIGNAL_EVENTS (1 << 5) -#define HV_X64_CREATE_PORT (1 << 6) -#define HV_X64_CONNECT_PORT (1 << 7) -#define HV_X64_ACCESS_STATS (1 << 8) -#define HV_X64_DEBUGGING (1 << 11) -#define HV_X64_CPU_POWER_MANAGEMENT (1 << 12) -#define HV_X64_CONFIGURE_PROFILER (1 << 13) +#define HV_X64_CREATE_PARTITIONS BIT(0) +#define HV_X64_ACCESS_PARTITION_ID BIT(1) +#define HV_X64_ACCESS_MEMORY_POOL BIT(2) +#define HV_X64_ADJUST_MESSAGE_BUFFERS BIT(3) +#define HV_X64_POST_MESSAGES BIT(4) +#define HV_X64_SIGNAL_EVENTS BIT(5) +#define HV_X64_CREATE_PORT BIT(6) +#define HV_X64_CONNECT_PORT BIT(7) +#define HV_X64_ACCESS_STATS BIT(8) +#define HV_X64_DEBUGGING BIT(11) +#define HV_X64_CPU_POWER_MANAGEMENT BIT(12) /* * Feature identification. EDX indicates which miscellaneous features * are available to the partition. + * These are HYPERV_CPUID_FEATURES.EDX bits. */ /* The MWAIT instruction is available (per section MONITOR / MWAIT) */ -#define HV_X64_MWAIT_AVAILABLE (1 << 0) +#define HV_X64_MWAIT_AVAILABLE BIT(0) /* Guest debugging support is available */ -#define HV_X64_GUEST_DEBUGGING_AVAILABLE (1 << 1) +#define HV_X64_GUEST_DEBUGGING_AVAILABLE BIT(1) /* Performance Monitor support is available*/ -#define HV_X64_PERF_MONITOR_AVAILABLE (1 << 2) +#define HV_X64_PERF_MONITOR_AVAILABLE BIT(2) /* Support for physical CPU dynamic partitioning events is available*/ -#define HV_X64_CPU_DYNAMIC_PARTITIONING_AVAILABLE (1 << 3) +#define HV_X64_CPU_DYNAMIC_PARTITIONING_AVAILABLE BIT(3) /* * Support for passing hypercall input parameter block via XMM * registers is available */ -#define HV_X64_HYPERCALL_PARAMS_XMM_AVAILABLE (1 << 4) +#define HV_X64_HYPERCALL_PARAMS_XMM_AVAILABLE BIT(4) /* Support for a virtual guest idle state is available */ -#define HV_X64_GUEST_IDLE_STATE_AVAILABLE (1 << 5) -/* Guest crash data handler available */ -#define HV_X64_GUEST_CRASH_MSR_AVAILABLE (1 << 10) +#define HV_X64_GUEST_IDLE_STATE_AVAILABLE BIT(5) +/* Frequency MSRs available */ +#define HV_FEATURE_FREQUENCY_MSRS_AVAILABLE BIT(8) +/* Crash MSR available */ +#define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE BIT(10) +/* stimer Direct Mode is available */ +#define HV_STIMER_DIRECT_MODE_AVAILABLE BIT(19) /* * Implementation recommendations. Indicates which behaviors the hypervisor * recommends the OS implement for optimal performance. + * These are HYPERV_CPUID_ENLIGHTMENT_INFO.EAX bits. + */ +/* + * Recommend using hypercall for address space switches rather + * than MOV to CR3 instruction */ - /* - * Recommend using hypercall for address space switches rather - * than MOV to CR3 instruction - */ -#define HV_X64_AS_SWITCH_RECOMMENDED (1 << 0) +#define HV_X64_AS_SWITCH_RECOMMENDED BIT(0) /* Recommend using hypercall for local TLB flushes rather * than INVLPG or MOV to CR3 instructions */ -#define HV_X64_LOCAL_TLB_FLUSH_RECOMMENDED (1 << 1) +#define HV_X64_LOCAL_TLB_FLUSH_RECOMMENDED BIT(1) /* * Recommend using hypercall for remote TLB flushes rather * than inter-processor interrupts */ -#define HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED (1 << 2) +#define HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED BIT(2) /* * Recommend using MSRs for accessing APIC registers * EOI, ICR and TPR rather than their memory-mapped counterparts */ -#define HV_X64_APIC_ACCESS_RECOMMENDED (1 << 3) +#define HV_X64_APIC_ACCESS_RECOMMENDED BIT(3) /* Recommend using the hypervisor-provided MSR to initiate a system RESET */ -#define HV_X64_SYSTEM_RESET_RECOMMENDED (1 << 4) +#define HV_X64_SYSTEM_RESET_RECOMMENDED BIT(4) /* * Recommend using relaxed timing for this partition. If used, * the VM should disable any watchdog timeouts that rely on the * timely delivery of external interrupts */ -#define HV_X64_RELAXED_TIMING_RECOMMENDED (1 << 5) +#define HV_X64_RELAXED_TIMING_RECOMMENDED BIT(5) /* * Recommend not using Auto End-Of-Interrupt feature */ -#define HV_DEPRECATING_AEOI_RECOMMENDED (1 << 9) +#define HV_DEPRECATING_AEOI_RECOMMENDED BIT(9) /* * Recommend using cluster IPI hypercalls. */ -#define HV_X64_CLUSTER_IPI_RECOMMENDED (1 << 10) +#define HV_X64_CLUSTER_IPI_RECOMMENDED BIT(10) /* Recommend using the newer ExProcessorMasks interface */ -#define HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED (1 << 11) +#define HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED BIT(11) /* Recommend using enlightened VMCS */ -#define HV_X64_ENLIGHTENED_VMCS_RECOMMENDED (1 << 14) +#define HV_X64_ENLIGHTENED_VMCS_RECOMMENDED BIT(14) -/* - * Crash notification flags. - */ -#define HV_CRASH_CTL_CRASH_NOTIFY_MSG BIT_ULL(62) -#define HV_CRASH_CTL_CRASH_NOTIFY BIT_ULL(63) +/* Nested features. These are HYPERV_CPUID_NESTED_FEATURES.EAX bits. */ +#define HV_X64_NESTED_GUEST_MAPPING_FLUSH BIT(18) +#define HV_X64_NESTED_MSR_BITMAP BIT(19) + +/* Hyper-V specific model specific registers (MSRs) */ /* MSR used to identify the guest OS. */ #define HV_X64_MSR_GUEST_OS_ID 0x40000000 @@ -199,6 +194,9 @@ /* MSR used to read the per-partition time reference counter */ #define HV_X64_MSR_TIME_REF_COUNT 0x40000020 +/* A partition's reference time stamp counter (TSC) page */ +#define HV_X64_MSR_REFERENCE_TSC 0x40000021 + /* MSR used to retrieve the TSC frequency */ #define HV_X64_MSR_TSC_FREQUENCY 0x40000022 @@ -246,6 +244,9 @@ #define HV_X64_MSR_STIMER3_CONFIG 0x400000B6 #define HV_X64_MSR_STIMER3_COUNT 0x400000B7 +/* Hyper-V guest idle MSR */ +#define HV_X64_MSR_GUEST_IDLE 0x400000F0 + /* Hyper-V guest crash notification MSR's */ #define HV_X64_MSR_CRASH_P0 0x40000100 #define HV_X64_MSR_CRASH_P1 0x40000101 @@ -253,9 +254,11 @@ #define HV_X64_MSR_CRASH_P3 0x40000103 #define HV_X64_MSR_CRASH_P4 0x40000104 #define HV_X64_MSR_CRASH_CTL 0x40000105 -#define HV_X64_MSR_CRASH_CTL_NOTIFY (1ULL << 63) -#define HV_X64_MSR_CRASH_PARAMS \ - (1 + (HV_X64_MSR_CRASH_P4 - HV_X64_MSR_CRASH_P0)) + +/* TSC emulation after migration */ +#define HV_X64_MSR_REENLIGHTENMENT_CONTROL 0x40000106 +#define HV_X64_MSR_TSC_EMULATION_CONTROL 0x40000107 +#define HV_X64_MSR_TSC_EMULATION_STATUS 0x40000108 /* * Declare the MSR used to setup pages used to communicate with the hypervisor. @@ -266,7 +269,7 @@ union hv_x64_msr_hypercall_contents { u64 enable:1; u64 reserved:11; u64 guest_physical_address:52; - }; + } __packed; }; /* @@ -278,7 +281,7 @@ struct ms_hyperv_tsc_page { volatile u64 tsc_scale; volatile s64 tsc_offset; u64 reserved2[509]; -}; +} __packed; /* * The guest OS needs to register the guest ID with the hypervisor. @@ -306,39 +309,37 @@ struct ms_hyperv_tsc_page { #define HV_LINUX_VENDOR_ID 0x8100 -/* TSC emulation after migration */ -#define HV_X64_MSR_REENLIGHTENMENT_CONTROL 0x40000106 - -/* Nested features (CPUID 0x4000000A) EAX */ -#define HV_X64_NESTED_GUEST_MAPPING_FLUSH BIT(18) -#define HV_X64_NESTED_MSR_BITMAP BIT(19) - struct hv_reenlightenment_control { __u64 vector:8; __u64 reserved1:8; __u64 enabled:1; __u64 reserved2:15; __u64 target_vp:32; -}; - -#define HV_X64_MSR_TSC_EMULATION_CONTROL 0x40000107 -#define HV_X64_MSR_TSC_EMULATION_STATUS 0x40000108 +} __packed; struct hv_tsc_emulation_control { __u64 enabled:1; __u64 reserved:63; -}; +} __packed; struct hv_tsc_emulation_status { __u64 inprogress:1; __u64 reserved:63; -}; +} __packed; #define HV_X64_MSR_HYPERCALL_ENABLE 0x00000001 #define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT 12 #define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_MASK \ (~((1ull << HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT) - 1)) +/* + * Crash notification (HV_X64_MSR_CRASH_CTL) flags. + */ +#define HV_CRASH_CTL_CRASH_NOTIFY_MSG BIT_ULL(62) +#define HV_CRASH_CTL_CRASH_NOTIFY BIT_ULL(63) +#define HV_X64_MSR_CRASH_PARAMS \ + (1 + (HV_X64_MSR_CRASH_P4 - HV_X64_MSR_CRASH_P0)) + #define HV_IPI_LOW_VECTOR 0x10 #define HV_IPI_HIGH_VECTOR 0xff @@ -353,6 +354,7 @@ struct hv_tsc_emulation_status { #define HVCALL_POST_MESSAGE 0x005c #define HVCALL_SIGNAL_EVENT 0x005d #define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE 0x00af +#define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_LIST 0x00b0 #define HV_X64_MSR_VP_ASSIST_PAGE_ENABLE 0x00000001 #define HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT 12 @@ -404,7 +406,7 @@ typedef struct _HV_REFERENCE_TSC_PAGE { __u32 res1; __u64 tsc_scale; __s64 tsc_offset; -} HV_REFERENCE_TSC_PAGE, *PHV_REFERENCE_TSC_PAGE; +} __packed HV_REFERENCE_TSC_PAGE, *PHV_REFERENCE_TSC_PAGE; /* Define the number of synthetic interrupt sources. */ #define HV_SYNIC_SINT_COUNT (16) @@ -461,7 +463,7 @@ union hv_message_flags { struct { __u8 msg_pending:1; __u8 reserved:7; - }; + } __packed; }; /* Define port identifier type. */ @@ -470,7 +472,7 @@ union hv_port_id { struct { __u32 id:24; __u32 reserved:8; - } u; + } __packed u; }; /* Define synthetic interrupt controller message header. */ @@ -483,7 +485,7 @@ struct hv_message_header { __u64 sender; union hv_port_id port; }; -}; +} __packed; /* Define synthetic interrupt controller message format. */ struct hv_message { @@ -491,12 +493,12 @@ struct hv_message { union { __u64 payload[HV_MESSAGE_PAYLOAD_QWORD_COUNT]; } u; -}; +} __packed; /* Define the synthetic interrupt message page layout. */ struct hv_message_page { struct hv_message sint_message[HV_SYNIC_SINT_COUNT]; -}; +} __packed; /* Define timer message payload structure. */ struct hv_timer_message_payload { @@ -504,7 +506,7 @@ struct hv_timer_message_payload { __u32 reserved; __u64 expiration_time; /* When the timer expired */ __u64 delivery_time; /* When the message was delivered */ -}; +} __packed; /* Define virtual processor assist page structure. */ struct hv_vp_assist_page { @@ -513,8 +515,9 @@ struct hv_vp_assist_page { __u64 vtl_control[2]; __u64 nested_enlightenments_control[2]; __u32 enlighten_vmentry; + __u32 padding; __u64 current_nested_vmcs; -}; +} __packed; struct hv_enlightened_vmcs { u32 revision_id; @@ -528,6 +531,8 @@ struct hv_enlightened_vmcs { u16 host_gs_selector; u16 host_tr_selector; + u16 padding16_1; + u64 host_ia32_pat; u64 host_ia32_efer; @@ -646,7 +651,7 @@ struct hv_enlightened_vmcs { u64 ept_pointer; u16 virtual_processor_id; - u16 padding16[3]; + u16 padding16_2[3]; u64 padding64_2[5]; u64 guest_physical_address; @@ -688,7 +693,7 @@ struct hv_enlightened_vmcs { u32 nested_flush_hypercall:1; u32 msr_bitmap:1; u32 reserved:30; - } hv_enlightenments_control; + } __packed hv_enlightenments_control; u32 hv_vp_id; u64 hv_vm_id; @@ -698,7 +703,7 @@ struct hv_enlightened_vmcs { u64 padding64_5[7]; u64 xss_exit_bitmap; u64 padding64_6[7]; -}; +} __packed; #define HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE 0 #define HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP BIT(0) @@ -720,36 +725,129 @@ struct hv_enlightened_vmcs { #define HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL 0xFFFF -#define HV_STIMER_ENABLE (1ULL << 0) -#define HV_STIMER_PERIODIC (1ULL << 1) -#define HV_STIMER_LAZY (1ULL << 2) -#define HV_STIMER_AUTOENABLE (1ULL << 3) -#define HV_STIMER_SINT(config) (__u8)(((config) >> 16) & 0x0F) +/* Define synthetic interrupt controller flag constants. */ +#define HV_EVENT_FLAGS_COUNT (256 * 8) +#define HV_EVENT_FLAGS_LONG_COUNT (256 / sizeof(unsigned long)) + +/* + * Synthetic timer configuration. + */ +union hv_stimer_config { + u64 as_uint64; + struct { + u64 enable:1; + u64 periodic:1; + u64 lazy:1; + u64 auto_enable:1; + u64 apic_vector:8; + u64 direct_mode:1; + u64 reserved_z0:3; + u64 sintx:4; + u64 reserved_z1:44; + } __packed; +}; + + +/* Define the synthetic interrupt controller event flags format. */ +union hv_synic_event_flags { + unsigned long flags[HV_EVENT_FLAGS_LONG_COUNT]; +}; + +/* Define SynIC control register. */ +union hv_synic_scontrol { + u64 as_uint64; + struct { + u64 enable:1; + u64 reserved:63; + } __packed; +}; + +/* Define synthetic interrupt source. */ +union hv_synic_sint { + u64 as_uint64; + struct { + u64 vector:8; + u64 reserved1:8; + u64 masked:1; + u64 auto_eoi:1; + u64 reserved2:46; + } __packed; +}; + +/* Define the format of the SIMP register */ +union hv_synic_simp { + u64 as_uint64; + struct { + u64 simp_enabled:1; + u64 preserved:11; + u64 base_simp_gpa:52; + } __packed; +}; + +/* Define the format of the SIEFP register */ +union hv_synic_siefp { + u64 as_uint64; + struct { + u64 siefp_enabled:1; + u64 preserved:11; + u64 base_siefp_gpa:52; + } __packed; +}; struct hv_vpset { u64 format; u64 valid_bank_mask; u64 bank_contents[]; -}; +} __packed; /* HvCallSendSyntheticClusterIpi hypercall */ struct hv_send_ipi { u32 vector; u32 reserved; u64 cpu_mask; -}; +} __packed; /* HvCallSendSyntheticClusterIpiEx hypercall */ struct hv_send_ipi_ex { u32 vector; u32 reserved; struct hv_vpset vp_set; -}; +} __packed; /* HvFlushGuestPhysicalAddressSpace hypercalls */ struct hv_guest_mapping_flush { u64 address_space; u64 flags; +} __packed; + +/* + * HV_MAX_FLUSH_PAGES = "additional_pages" + 1. It's limited + * by the bitwidth of "additional_pages" in union hv_gpa_page_range. + */ +#define HV_MAX_FLUSH_PAGES (2048) + +/* HvFlushGuestPhysicalAddressList hypercall */ +union hv_gpa_page_range { + u64 address_space; + struct { + u64 additional_pages:11; + u64 largepage:1; + u64 basepfn:52; + } page; +}; + +/* + * All input flush parameters should be in single page. The max flush + * count is equal with how many entries of union hv_gpa_page_range can + * be populated into the input parameter page. + */ +#define HV_MAX_FLUSH_REP_COUNT ((PAGE_SIZE - 2 * sizeof(u64)) / \ + sizeof(union hv_gpa_page_range)) + +struct hv_guest_mapping_flush_list { + u64 address_space; + u64 flags; + union hv_gpa_page_range gpa_list[HV_MAX_FLUSH_REP_COUNT]; }; /* HvFlushVirtualAddressSpace, HvFlushVirtualAddressList hypercalls */ @@ -758,7 +856,7 @@ struct hv_tlb_flush { u64 flags; u64 processor_mask; u64 gva_list[]; -}; +} __packed; /* HvFlushVirtualAddressSpaceEx, HvFlushVirtualAddressListEx hypercalls */ struct hv_tlb_flush_ex { @@ -766,6 +864,6 @@ struct hv_tlb_flush_ex { u64 flags; struct hv_vpset hv_vp_set; u64 gva_list[]; -}; +} __packed; #endif diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 7ed08a7c3398..9f15384c504a 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -6,10 +6,7 @@ * "Big Core" Processors (Branded as Core, Xeon, etc...) * * The "_X" parts are generally the EP and EX Xeons, or the - * "Extreme" ones, like Broadwell-E. - * - * Things ending in "2" are usually because we have no better - * name for them. There's no processor called "SILVERMONT2". + * "Extreme" ones, like Broadwell-E, or Atom microserver. * * While adding a new CPUID for a new microarchitecture, add a new * group to keep logically sorted out in chronological order. Within @@ -55,21 +52,28 @@ #define INTEL_FAM6_CANNONLAKE_MOBILE 0x66 +#define INTEL_FAM6_ICELAKE_MOBILE 0x7E + /* "Small Core" Processors (Atom) */ -#define INTEL_FAM6_ATOM_PINEVIEW 0x1C -#define INTEL_FAM6_ATOM_LINCROFT 0x26 -#define INTEL_FAM6_ATOM_PENWELL 0x27 -#define INTEL_FAM6_ATOM_CLOVERVIEW 0x35 -#define INTEL_FAM6_ATOM_CEDARVIEW 0x36 -#define INTEL_FAM6_ATOM_SILVERMONT1 0x37 /* BayTrail/BYT / Valleyview */ -#define INTEL_FAM6_ATOM_SILVERMONT2 0x4D /* Avaton/Rangely */ -#define INTEL_FAM6_ATOM_AIRMONT 0x4C /* CherryTrail / Braswell */ -#define INTEL_FAM6_ATOM_MERRIFIELD 0x4A /* Tangier */ -#define INTEL_FAM6_ATOM_MOOREFIELD 0x5A /* Anniedale */ -#define INTEL_FAM6_ATOM_GOLDMONT 0x5C -#define INTEL_FAM6_ATOM_DENVERTON 0x5F /* Goldmont Microserver */ -#define INTEL_FAM6_ATOM_GEMINI_LAKE 0x7A +#define INTEL_FAM6_ATOM_BONNELL 0x1C /* Diamondville, Pineview */ +#define INTEL_FAM6_ATOM_BONNELL_MID 0x26 /* Silverthorne, Lincroft */ + +#define INTEL_FAM6_ATOM_SALTWELL 0x36 /* Cedarview */ +#define INTEL_FAM6_ATOM_SALTWELL_MID 0x27 /* Penwell */ +#define INTEL_FAM6_ATOM_SALTWELL_TABLET 0x35 /* Cloverview */ + +#define INTEL_FAM6_ATOM_SILVERMONT 0x37 /* Bay Trail, Valleyview */ +#define INTEL_FAM6_ATOM_SILVERMONT_X 0x4D /* Avaton, Rangely */ +#define INTEL_FAM6_ATOM_SILVERMONT_MID 0x4A /* Merriefield */ + +#define INTEL_FAM6_ATOM_AIRMONT 0x4C /* Cherry Trail, Braswell */ +#define INTEL_FAM6_ATOM_AIRMONT_MID 0x5A /* Moorefield */ + +#define INTEL_FAM6_ATOM_GOLDMONT 0x5C /* Apollo Lake */ +#define INTEL_FAM6_ATOM_GOLDMONT_X 0x5F /* Denverton */ +#define INTEL_FAM6_ATOM_GOLDMONT_PLUS 0x7A /* Gemini Lake */ +#define INTEL_FAM6_ATOM_TREMONT_X 0x86 /* Jacobsville */ /* Xeon Phi */ diff --git a/arch/x86/include/asm/intel_pt.h b/arch/x86/include/asm/intel_pt.h index b523f51c5400..634f99b1dc22 100644 --- a/arch/x86/include/asm/intel_pt.h +++ b/arch/x86/include/asm/intel_pt.h @@ -2,10 +2,36 @@ #ifndef _ASM_X86_INTEL_PT_H #define _ASM_X86_INTEL_PT_H +#define PT_CPUID_LEAVES 2 +#define PT_CPUID_REGS_NUM 4 /* number of regsters (eax, ebx, ecx, edx) */ + +enum pt_capabilities { + PT_CAP_max_subleaf = 0, + PT_CAP_cr3_filtering, + PT_CAP_psb_cyc, + PT_CAP_ip_filtering, + PT_CAP_mtc, + PT_CAP_ptwrite, + PT_CAP_power_event_trace, + PT_CAP_topa_output, + PT_CAP_topa_multiple_entries, + PT_CAP_single_range_output, + PT_CAP_output_subsys, + PT_CAP_payloads_lip, + PT_CAP_num_address_ranges, + PT_CAP_mtc_periods, + PT_CAP_cycle_thresholds, + PT_CAP_psb_periods, +}; + #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL) void cpu_emergency_stop_pt(void); +extern u32 intel_pt_validate_hw_cap(enum pt_capabilities cap); +extern u32 intel_pt_validate_cap(u32 *caps, enum pt_capabilities cap); #else static inline void cpu_emergency_stop_pt(void) {} +static inline u32 intel_pt_validate_hw_cap(enum pt_capabilities cap) { return 0; } +static inline u32 intel_pt_validate_cap(u32 *caps, enum pt_capabilities capability) { return 0; } #endif #endif /* _ASM_X86_INTEL_PT_H */ diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index 6de64840dd22..686247db3106 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -187,11 +187,12 @@ extern void __iomem *ioremap_nocache(resource_size_t offset, unsigned long size) #define ioremap_nocache ioremap_nocache extern void __iomem *ioremap_uc(resource_size_t offset, unsigned long size); #define ioremap_uc ioremap_uc - extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size); #define ioremap_cache ioremap_cache extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size, unsigned long prot_val); #define ioremap_prot ioremap_prot +extern void __iomem *ioremap_encrypted(resource_size_t phys_addr, unsigned long size); +#define ioremap_encrypted ioremap_encrypted /** * ioremap - map bus memory into CPU space @@ -220,6 +221,14 @@ extern void set_iounmap_nonlazy(void); #ifdef __KERNEL__ +void memcpy_fromio(void *, const volatile void __iomem *, size_t); +void memcpy_toio(volatile void __iomem *, const void *, size_t); +void memset_io(volatile void __iomem *, int, size_t); + +#define memcpy_fromio memcpy_fromio +#define memcpy_toio memcpy_toio +#define memset_io memset_io + #include <asm-generic/iomap.h> /* @@ -369,18 +378,6 @@ extern void __iomem *ioremap_wt(resource_size_t offset, unsigned long size); extern bool is_early_ioremap_ptep(pte_t *ptep); -#ifdef CONFIG_XEN -#include <xen/xen.h> -struct bio_vec; - -extern bool xen_biovec_phys_mergeable(const struct bio_vec *vec1, - const struct bio_vec *vec2); - -#define BIOVEC_PHYS_MERGEABLE(vec1, vec2) \ - (__BIOVEC_PHYS_MERGEABLE(vec1, vec2) && \ - (!xen_domain() || xen_biovec_phys_mergeable(vec1, vec2))) -#endif /* CONFIG_XEN */ - #define IO_SPACE_LIMIT 0xffff #include <asm-generic/io.h> diff --git a/arch/x86/include/asm/iosf_mbi.h b/arch/x86/include/asm/iosf_mbi.h index 3de0489deade..5270ff39b9af 100644 --- a/arch/x86/include/asm/iosf_mbi.h +++ b/arch/x86/include/asm/iosf_mbi.h @@ -105,8 +105,10 @@ int iosf_mbi_modify(u8 port, u8 opcode, u32 offset, u32 mdr, u32 mask); * the PMIC bus while another driver is also accessing the PMIC bus various bad * things happen. * - * To avoid these problems this function must be called before accessing the - * P-Unit or the PMIC, be it through iosf_mbi* functions or through other means. + * Call this function before sending requests to the P-Unit which may make it + * access the PMIC, be it through iosf_mbi* functions or through other means. + * This function will block all kernel access to the PMIC I2C bus, so that the + * P-Unit can safely access the PMIC over the shared I2C bus. * * Note on these systems the i2c-bus driver will request a sempahore from the * P-Unit for exclusive access to the PMIC bus when i2c drivers are accessing @@ -123,6 +125,31 @@ void iosf_mbi_punit_acquire(void); void iosf_mbi_punit_release(void); /** + * iosf_mbi_block_punit_i2c_access() - Block P-Unit accesses to the PMIC bus + * + * Call this function to block P-Unit access to the PMIC I2C bus, so that the + * kernel can safely access the PMIC over the shared I2C bus. + * + * This function acquires the P-Unit bus semaphore and notifies + * pmic_bus_access_notifier listeners that they may no longer access the + * P-Unit in a way which may cause it to access the shared I2C bus. + * + * Note this function may be called multiple times and the bus will not + * be released until iosf_mbi_unblock_punit_i2c_access() has been called the + * same amount of times. + * + * Return: Nonzero on error + */ +int iosf_mbi_block_punit_i2c_access(void); + +/* + * iosf_mbi_unblock_punit_i2c_access() - Release PMIC I2C bus block + * + * Release i2c access block gotten through iosf_mbi_block_punit_i2c_access(). + */ +void iosf_mbi_unblock_punit_i2c_access(void); + +/** * iosf_mbi_register_pmic_bus_access_notifier - Register PMIC bus notifier * * This function can be used by drivers which may need to acquire P-Unit @@ -159,14 +186,6 @@ int iosf_mbi_unregister_pmic_bus_access_notifier_unlocked( struct notifier_block *nb); /** - * iosf_mbi_call_pmic_bus_access_notifier_chain - Call PMIC bus notifier chain - * - * @val: action to pass into listener's notifier_call function - * @v: data pointer to pass into listener's notifier_call function - */ -int iosf_mbi_call_pmic_bus_access_notifier_chain(unsigned long val, void *v); - -/** * iosf_mbi_assert_punit_acquired - Assert that the P-Unit has been acquired. */ void iosf_mbi_assert_punit_acquired(void); diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h index 2395bb794c7b..fbb16e6b6c18 100644 --- a/arch/x86/include/asm/irq.h +++ b/arch/x86/include/asm/irq.h @@ -30,6 +30,9 @@ extern void fixup_irqs(void); #ifdef CONFIG_HAVE_KVM extern void kvm_set_posted_intr_wakeup_handler(void (*handler)(void)); +extern __visible void smp_kvm_posted_intr_ipi(struct pt_regs *regs); +extern __visible void smp_kvm_posted_intr_wakeup_ipi(struct pt_regs *regs); +extern __visible void smp_kvm_posted_intr_nested_ipi(struct pt_regs *regs); #endif extern void (*x86_platform_ipi_callback)(void); @@ -41,9 +44,13 @@ extern __visible unsigned int do_IRQ(struct pt_regs *regs); extern void init_ISA_irqs(void); +extern void __init init_IRQ(void); + #ifdef CONFIG_X86_LOCAL_APIC void arch_trigger_cpumask_backtrace(const struct cpumask *mask, bool exclude_self); + +extern __visible void smp_x86_platform_ipi(struct pt_regs *regs); #define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace #endif diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h index 5f26962eff42..67ed72f31cc2 100644 --- a/arch/x86/include/asm/irq_remapping.h +++ b/arch/x86/include/asm/irq_remapping.h @@ -45,6 +45,8 @@ struct vcpu_data { #ifdef CONFIG_IRQ_REMAP +extern raw_spinlock_t irq_2_ir_lock; + extern bool irq_remapping_cap(enum irq_remap_cap cap); extern void set_irq_remapping_broken(void); extern int irq_remapping_prepare(void); diff --git a/arch/x86/include/asm/irq_work.h b/arch/x86/include/asm/irq_work.h index 800ffce0db29..80b35e3adf03 100644 --- a/arch/x86/include/asm/irq_work.h +++ b/arch/x86/include/asm/irq_work.h @@ -10,6 +10,7 @@ static inline bool arch_irq_work_has_interrupt(void) return boot_cpu_has(X86_FEATURE_APIC); } extern void arch_irq_work_raise(void); +extern __visible void smp_irq_work_interrupt(struct pt_regs *regs); #else static inline bool arch_irq_work_has_interrupt(void) { diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h index 15450a675031..058e40fed167 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -64,7 +64,7 @@ static inline __cpuidle void native_halt(void) #endif -#ifdef CONFIG_PARAVIRT +#ifdef CONFIG_PARAVIRT_XXL #include <asm/paravirt.h> #else #ifndef __ASSEMBLY__ @@ -123,6 +123,10 @@ static inline notrace unsigned long arch_local_irq_save(void) #define DISABLE_INTERRUPTS(x) cli #ifdef CONFIG_X86_64 +#ifdef CONFIG_DEBUG_ENTRY +#define SAVE_FLAGS(x) pushfq; popq %rax +#endif + #define SWAPGS swapgs /* * Currently paravirt can't handle swapgs nicely when we @@ -135,8 +139,6 @@ static inline notrace unsigned long arch_local_irq_save(void) */ #define SWAPGS_UNSAFE_STACK swapgs -#define PARAVIRT_ADJUST_EXCEPTION_FRAME /* */ - #define INTERRUPT_RETURN jmp native_iret #define USERGS_SYSRET64 \ swapgs; \ @@ -145,18 +147,12 @@ static inline notrace unsigned long arch_local_irq_save(void) swapgs; \ sysretl -#ifdef CONFIG_DEBUG_ENTRY -#define SAVE_FLAGS(x) pushfq; popq %rax -#endif #else #define INTERRUPT_RETURN iret -#define ENABLE_INTERRUPTS_SYSEXIT sti; sysexit -#define GET_CR0_INTO_EAX movl %cr0, %eax #endif - #endif /* __ASSEMBLY__ */ -#endif /* CONFIG_PARAVIRT */ +#endif /* CONFIG_PARAVIRT_XXL */ #ifndef __ASSEMBLY__ static inline int arch_irqs_disabled_flags(unsigned long flags) diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h index 8c0de4282659..65191ce8e1cf 100644 --- a/arch/x86/include/asm/jump_label.h +++ b/arch/x86/include/asm/jump_label.h @@ -2,19 +2,6 @@ #ifndef _ASM_X86_JUMP_LABEL_H #define _ASM_X86_JUMP_LABEL_H -#ifndef HAVE_JUMP_LABEL -/* - * For better or for worse, if jump labels (the gcc extension) are missing, - * then the entire static branch patching infrastructure is compiled out. - * If that happens, the code in here will malfunction. Raise a compiler - * error instead. - * - * In theory, jump labels and the static branch patching infrastructure - * could be decoupled to fix this. - */ -#error asm/jump_label.h included on a non-jump-label kernel -#endif - #define JUMP_LABEL_NOP_SIZE 5 #ifdef CONFIG_X86_64 @@ -37,7 +24,8 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool bran ".byte " __stringify(STATIC_KEY_INIT_NOP) "\n\t" ".pushsection __jump_table, \"aw\" \n\t" _ASM_ALIGN "\n\t" - _ASM_PTR "1b, %l[l_yes], %c0 + %c1 \n\t" + ".long 1b - ., %l[l_yes] - . \n\t" + _ASM_PTR "%c0 + %c1 - .\n\t" ".popsection \n\t" : : "i" (key), "i" (branch) : : l_yes); @@ -53,7 +41,8 @@ static __always_inline bool arch_static_branch_jump(struct static_key *key, bool "2:\n\t" ".pushsection __jump_table, \"aw\" \n\t" _ASM_ALIGN "\n\t" - _ASM_PTR "1b, %l[l_yes], %c0 + %c1 \n\t" + ".long 1b - ., %l[l_yes] - . \n\t" + _ASM_PTR "%c0 + %c1 - .\n\t" ".popsection \n\t" : : "i" (key), "i" (branch) : : l_yes); @@ -62,18 +51,6 @@ l_yes: return true; } -#ifdef CONFIG_X86_64 -typedef u64 jump_label_t; -#else -typedef u32 jump_label_t; -#endif - -struct jump_entry { - jump_label_t code; - jump_label_t target; - jump_label_t key; -}; - #else /* __ASSEMBLY__ */ .macro STATIC_JUMP_IF_TRUE target, key, def @@ -88,7 +65,8 @@ struct jump_entry { .endif .pushsection __jump_table, "aw" _ASM_ALIGN - _ASM_PTR .Lstatic_jump_\@, \target, \key + .long .Lstatic_jump_\@ - ., \target - . + _ASM_PTR \key - . .popsection .endm @@ -104,7 +82,8 @@ struct jump_entry { .endif .pushsection __jump_table, "aw" _ASM_ALIGN - _ASM_PTR .Lstatic_jump_\@, \target, \key + 1 + .long .Lstatic_jump_\@ - ., \target - . + _ASM_PTR \key + 1 - . .popsection .endm diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h index f327236f0fa7..003f2daa3b0f 100644 --- a/arch/x86/include/asm/kexec.h +++ b/arch/x86/include/asm/kexec.h @@ -21,6 +21,7 @@ #ifndef __ASSEMBLY__ #include <linux/string.h> +#include <linux/kernel.h> #include <asm/page.h> #include <asm/ptrace.h> @@ -67,7 +68,7 @@ struct kimage; /* Memory to backup during crash kdump */ #define KEXEC_BACKUP_SRC_START (0UL) -#define KEXEC_BACKUP_SRC_END (640 * 1024UL) /* 640K */ +#define KEXEC_BACKUP_SRC_END (640 * 1024UL - 1) /* 640K */ /* * CPU does not save ss and sp on stack if execution is already @@ -132,7 +133,7 @@ static inline void crash_setup_regs(struct pt_regs *newregs, asm volatile("movl %%cs, %%eax;" :"=a"(newregs->cs)); asm volatile("pushfq; popq %0" :"=m"(newregs->flags)); #endif - newregs->ip = (unsigned long)current_text_addr(); + newregs->ip = _THIS_IP_; } } diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index 0f82cd91cd3c..93c4bf598fb0 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -364,6 +364,10 @@ struct x86_emulate_ctxt { #define X86EMUL_CPUID_VENDOR_AMDisbetterI_ecx 0x21726574 #define X86EMUL_CPUID_VENDOR_AMDisbetterI_edx 0x74656273 +#define X86EMUL_CPUID_VENDOR_HygonGenuine_ebx 0x6f677948 +#define X86EMUL_CPUID_VENDOR_HygonGenuine_ecx 0x656e6975 +#define X86EMUL_CPUID_VENDOR_HygonGenuine_edx 0x6e65476e + #define X86EMUL_CPUID_VENDOR_GenuineIntel_ebx 0x756e6547 #define X86EMUL_CPUID_VENDOR_GenuineIntel_ecx 0x6c65746e #define X86EMUL_CPUID_VENDOR_GenuineIntel_edx 0x49656e69 diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 1c09a0d1771f..180373360e34 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -102,7 +102,15 @@ #define UNMAPPED_GVA (~(gpa_t)0) /* KVM Hugepage definitions for x86 */ -#define KVM_NR_PAGE_SIZES 3 +enum { + PT_PAGE_TABLE_LEVEL = 1, + PT_DIRECTORY_LEVEL = 2, + PT_PDPE_LEVEL = 3, + /* set max level to the biggest one */ + PT_MAX_HUGEPAGE_LEVEL = PT_PDPE_LEVEL, +}; +#define KVM_NR_PAGE_SIZES (PT_MAX_HUGEPAGE_LEVEL - \ + PT_PAGE_TABLE_LEVEL + 1) #define KVM_HPAGE_GFN_SHIFT(x) (((x) - 1) * 9) #define KVM_HPAGE_SHIFT(x) (PAGE_SHIFT + KVM_HPAGE_GFN_SHIFT(x)) #define KVM_HPAGE_SIZE(x) (1UL << KVM_HPAGE_SHIFT(x)) @@ -248,7 +256,7 @@ struct kvm_mmu_memory_cache { * @nxe, @cr0_wp, @smep_andnot_wp and @smap_andnot_wp. */ union kvm_mmu_page_role { - unsigned word; + u32 word; struct { unsigned level:4; unsigned cr4_pae:1; @@ -274,6 +282,35 @@ union kvm_mmu_page_role { }; }; +union kvm_mmu_extended_role { +/* + * This structure complements kvm_mmu_page_role caching everything needed for + * MMU configuration. If nothing in both these structures changed, MMU + * re-configuration can be skipped. @valid bit is set on first usage so we don't + * treat all-zero structure as valid data. + */ + u32 word; + struct { + unsigned int valid:1; + unsigned int execonly:1; + unsigned int cr0_pg:1; + unsigned int cr4_pse:1; + unsigned int cr4_pke:1; + unsigned int cr4_smap:1; + unsigned int cr4_smep:1; + unsigned int cr4_la57:1; + unsigned int maxphyaddr:6; + }; +}; + +union kvm_mmu_role { + u64 as_u64; + struct { + union kvm_mmu_page_role base; + union kvm_mmu_extended_role ext; + }; +}; + struct kvm_rmap_head { unsigned long val; }; @@ -281,18 +318,18 @@ struct kvm_rmap_head { struct kvm_mmu_page { struct list_head link; struct hlist_node hash_link; + bool unsync; /* * The following two entries are used to key the shadow page in the * hash table. */ - gfn_t gfn; union kvm_mmu_page_role role; + gfn_t gfn; u64 *spt; /* hold the gfn of each spte inside spt */ gfn_t *gfns; - bool unsync; int root_count; /* Currently serving as active root */ unsigned int unsync_children; struct kvm_rmap_head parent_ptes; /* rmap pointers to parent sptes */ @@ -361,7 +398,8 @@ struct kvm_mmu { void (*update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, u64 *spte, const void *pte); hpa_t root_hpa; - union kvm_mmu_page_role base_role; + gpa_t root_cr3; + union kvm_mmu_role mmu_role; u8 root_level; u8 shadow_root_level; u8 ept_ad; @@ -403,6 +441,11 @@ struct kvm_mmu { u64 pdptrs[4]; /* pae */ }; +struct kvm_tlb_range { + u64 start_gfn; + u64 pages; +}; + enum pmc_type { KVM_PMC_GP = 0, KVM_PMC_FIXED, @@ -461,7 +504,7 @@ struct kvm_mtrr { struct kvm_vcpu_hv_stimer { struct hrtimer timer; int index; - u64 config; + union hv_stimer_config config; u64 count; u64 exp_time; struct hv_message msg; @@ -491,7 +534,7 @@ struct kvm_vcpu_hv { struct kvm_hyperv_exit exit; struct kvm_vcpu_hv_stimer stimer[HV_SYNIC_STIMER_COUNT]; DECLARE_BITMAP(stimer_pending_bitmap, HV_SYNIC_STIMER_COUNT); - cpumask_t tlb_lush; + cpumask_t tlb_flush; }; struct kvm_vcpu_arch { @@ -535,7 +578,13 @@ struct kvm_vcpu_arch { * the paging mode of the l1 guest. This context is always used to * handle faults. */ - struct kvm_mmu mmu; + struct kvm_mmu *mmu; + + /* Non-nested MMU for L1 */ + struct kvm_mmu root_mmu; + + /* L1 MMU when running nested */ + struct kvm_mmu guest_mmu; /* * Paging state of an L2 guest (used for nested npt) @@ -559,17 +608,16 @@ struct kvm_vcpu_arch { /* * QEMU userspace and the guest each have their own FPU state. - * In vcpu_run, we switch between the user and guest FPU contexts. - * While running a VCPU, the VCPU thread will have the guest FPU - * context. + * In vcpu_run, we switch between the user, maintained in the + * task_struct struct, and guest FPU contexts. While running a VCPU, + * the VCPU thread will have the guest FPU context. * * Note that while the PKRU state lives inside the fpu registers, * it is switched out separately at VMENTER and VMEXIT time. The * "guest_fpu" state here contains the guest FPU context, with the * host PRKU bits. */ - struct fpu user_fpu; - struct fpu guest_fpu; + struct fpu *guest_fpu; u64 xcr0; u64 guest_supported_xcr0; @@ -586,6 +634,8 @@ struct kvm_vcpu_arch { bool has_error_code; u8 nr; u32 error_code; + unsigned long payload; + bool has_payload; u8 nested_apf; } exception; @@ -782,6 +832,9 @@ struct kvm_hv { u64 hv_reenlightenment_control; u64 hv_tsc_emulation_control; u64 hv_tsc_emulation_status; + + /* How many vCPUs have VP index != vCPU index */ + atomic_t num_mismatched_vp_indexes; }; enum kvm_irqchip_mode { @@ -872,6 +925,7 @@ struct kvm_arch { bool x2apic_broadcast_quirk_disabled; bool guest_can_read_msr_platform_info; + bool exception_payload_enabled; }; struct kvm_vm_stat { @@ -994,6 +1048,8 @@ struct kvm_x86_ops { void (*tlb_flush)(struct kvm_vcpu *vcpu, bool invalidate_gpa); int (*tlb_remote_flush)(struct kvm *kvm); + int (*tlb_remote_flush_with_range)(struct kvm *kvm, + struct kvm_tlb_range *range); /* * Flush any TLB entries associated with the given GVA. @@ -1046,7 +1102,8 @@ struct kvm_x86_ops { bool (*has_wbinvd_exit)(void); u64 (*read_l1_tsc_offset)(struct kvm_vcpu *vcpu); - void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset); + /* Returns actual tsc_offset set in active VMCS */ + u64 (*write_l1_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset); void (*get_exit_info)(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2); @@ -1057,6 +1114,7 @@ struct kvm_x86_ops { bool (*mpx_supported)(void); bool (*xsaves_supported)(void); bool (*umip_emulated)(void); + bool (*pt_supported)(void); int (*check_nested_events)(struct kvm_vcpu *vcpu, bool external_intr); void (*request_immediate_exit)(struct kvm_vcpu *vcpu); @@ -1134,6 +1192,10 @@ struct kvm_x86_ops { int (*mem_enc_unreg_region)(struct kvm *kvm, struct kvm_enc_region *argp); int (*get_msr_feature)(struct kvm_msr_entry *entry); + + int (*nested_enable_evmcs)(struct kvm_vcpu *vcpu, + uint16_t *vmcs_version); + uint16_t (*nested_get_evmcs_version)(struct kvm_vcpu *vcpu); }; struct kvm_arch_async_pf { @@ -1144,6 +1206,7 @@ struct kvm_arch_async_pf { }; extern struct kvm_x86_ops *kvm_x86_ops; +extern struct kmem_cache *x86_fpu_cache; #define __KVM_HAVE_ARCH_VM_ALLOC static inline struct kvm *kvm_arch_alloc_vm(void) @@ -1171,7 +1234,6 @@ void kvm_mmu_module_exit(void); void kvm_mmu_destroy(struct kvm_vcpu *vcpu); int kvm_mmu_create(struct kvm_vcpu *vcpu); -void kvm_mmu_setup(struct kvm_vcpu *vcpu); void kvm_mmu_init_vm(struct kvm *kvm); void kvm_mmu_uninit_vm(struct kvm *kvm); void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, @@ -1325,7 +1387,8 @@ void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu); int kvm_mmu_load(struct kvm_vcpu *vcpu); void kvm_mmu_unload(struct kvm_vcpu *vcpu); void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu); -void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, ulong roots_to_free); +void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, + ulong roots_to_free); gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, struct x86_exception *exception); gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, @@ -1440,7 +1503,7 @@ asmlinkage void kvm_spurious_fault(void); "cmpb $0, kvm_rebooting \n\t" \ "jne 668b \n\t" \ __ASM_SIZE(push) " $666b \n\t" \ - "call kvm_spurious_fault \n\t" \ + "jmp kvm_spurious_fault \n\t" \ ".popsection \n\t" \ _ASM_EXTABLE(666b, 667b) @@ -1451,7 +1514,7 @@ asmlinkage void kvm_spurious_fault(void); int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end); int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); -void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); +int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v); int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu); int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu); diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h index 4c723632c036..5ed3cf1c3934 100644 --- a/arch/x86/include/asm/kvm_para.h +++ b/arch/x86/include/asm/kvm_para.h @@ -92,6 +92,7 @@ void kvm_async_pf_task_wait(u32 token, int interrupt_kernel); void kvm_async_pf_task_wake(u32 token); u32 kvm_read_and_reset_pf_reason(void); extern void kvm_disable_steal_time(void); +void do_async_page_fault(struct pt_regs *regs, unsigned long error_code); #ifdef CONFIG_PARAVIRT_SPINLOCKS void __init kvm_spinlock_init(void); diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h index c91083c59845..349a47acaa4a 100644 --- a/arch/x86/include/asm/local.h +++ b/arch/x86/include/asm/local.h @@ -53,7 +53,7 @@ static inline void local_sub(long i, local_t *l) */ static inline bool local_sub_and_test(long i, local_t *l) { - GEN_BINARY_RMWcc(_ASM_SUB, l->a.counter, "er", i, "%0", e); + return GEN_BINARY_RMWcc(_ASM_SUB, l->a.counter, e, "er", i); } /** @@ -66,7 +66,7 @@ static inline bool local_sub_and_test(long i, local_t *l) */ static inline bool local_dec_and_test(local_t *l) { - GEN_UNARY_RMWcc(_ASM_DEC, l->a.counter, "%0", e); + return GEN_UNARY_RMWcc(_ASM_DEC, l->a.counter, e); } /** @@ -79,7 +79,7 @@ static inline bool local_dec_and_test(local_t *l) */ static inline bool local_inc_and_test(local_t *l) { - GEN_UNARY_RMWcc(_ASM_INC, l->a.counter, "%0", e); + return GEN_UNARY_RMWcc(_ASM_INC, l->a.counter, e); } /** @@ -93,7 +93,7 @@ static inline bool local_inc_and_test(local_t *l) */ static inline bool local_add_negative(long i, local_t *l) { - GEN_BINARY_RMWcc(_ASM_ADD, l->a.counter, "er", i, "%0", s); + return GEN_BINARY_RMWcc(_ASM_ADD, l->a.counter, s, "er", i); } /** diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index eb786f90f2d3..c1a812bd5a27 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -10,41 +10,44 @@ /* MCG_CAP register defines */ #define MCG_BANKCNT_MASK 0xff /* Number of Banks */ -#define MCG_CTL_P (1ULL<<8) /* MCG_CTL register available */ -#define MCG_EXT_P (1ULL<<9) /* Extended registers available */ -#define MCG_CMCI_P (1ULL<<10) /* CMCI supported */ +#define MCG_CTL_P BIT_ULL(8) /* MCG_CTL register available */ +#define MCG_EXT_P BIT_ULL(9) /* Extended registers available */ +#define MCG_CMCI_P BIT_ULL(10) /* CMCI supported */ #define MCG_EXT_CNT_MASK 0xff0000 /* Number of Extended registers */ #define MCG_EXT_CNT_SHIFT 16 #define MCG_EXT_CNT(c) (((c) & MCG_EXT_CNT_MASK) >> MCG_EXT_CNT_SHIFT) -#define MCG_SER_P (1ULL<<24) /* MCA recovery/new status bits */ -#define MCG_ELOG_P (1ULL<<26) /* Extended error log supported */ -#define MCG_LMCE_P (1ULL<<27) /* Local machine check supported */ +#define MCG_SER_P BIT_ULL(24) /* MCA recovery/new status bits */ +#define MCG_ELOG_P BIT_ULL(26) /* Extended error log supported */ +#define MCG_LMCE_P BIT_ULL(27) /* Local machine check supported */ /* MCG_STATUS register defines */ -#define MCG_STATUS_RIPV (1ULL<<0) /* restart ip valid */ -#define MCG_STATUS_EIPV (1ULL<<1) /* ip points to correct instruction */ -#define MCG_STATUS_MCIP (1ULL<<2) /* machine check in progress */ -#define MCG_STATUS_LMCES (1ULL<<3) /* LMCE signaled */ +#define MCG_STATUS_RIPV BIT_ULL(0) /* restart ip valid */ +#define MCG_STATUS_EIPV BIT_ULL(1) /* ip points to correct instruction */ +#define MCG_STATUS_MCIP BIT_ULL(2) /* machine check in progress */ +#define MCG_STATUS_LMCES BIT_ULL(3) /* LMCE signaled */ /* MCG_EXT_CTL register defines */ -#define MCG_EXT_CTL_LMCE_EN (1ULL<<0) /* Enable LMCE */ +#define MCG_EXT_CTL_LMCE_EN BIT_ULL(0) /* Enable LMCE */ /* MCi_STATUS register defines */ -#define MCI_STATUS_VAL (1ULL<<63) /* valid error */ -#define MCI_STATUS_OVER (1ULL<<62) /* previous errors lost */ -#define MCI_STATUS_UC (1ULL<<61) /* uncorrected error */ -#define MCI_STATUS_EN (1ULL<<60) /* error enabled */ -#define MCI_STATUS_MISCV (1ULL<<59) /* misc error reg. valid */ -#define MCI_STATUS_ADDRV (1ULL<<58) /* addr reg. valid */ -#define MCI_STATUS_PCC (1ULL<<57) /* processor context corrupt */ -#define MCI_STATUS_S (1ULL<<56) /* Signaled machine check */ -#define MCI_STATUS_AR (1ULL<<55) /* Action required */ +#define MCI_STATUS_VAL BIT_ULL(63) /* valid error */ +#define MCI_STATUS_OVER BIT_ULL(62) /* previous errors lost */ +#define MCI_STATUS_UC BIT_ULL(61) /* uncorrected error */ +#define MCI_STATUS_EN BIT_ULL(60) /* error enabled */ +#define MCI_STATUS_MISCV BIT_ULL(59) /* misc error reg. valid */ +#define MCI_STATUS_ADDRV BIT_ULL(58) /* addr reg. valid */ +#define MCI_STATUS_PCC BIT_ULL(57) /* processor context corrupt */ +#define MCI_STATUS_S BIT_ULL(56) /* Signaled machine check */ +#define MCI_STATUS_AR BIT_ULL(55) /* Action required */ +#define MCI_STATUS_CEC_SHIFT 38 /* Corrected Error Count */ +#define MCI_STATUS_CEC_MASK GENMASK_ULL(52,38) +#define MCI_STATUS_CEC(c) (((c) & MCI_STATUS_CEC_MASK) >> MCI_STATUS_CEC_SHIFT) /* AMD-specific bits */ -#define MCI_STATUS_TCC (1ULL<<55) /* Task context corrupt */ -#define MCI_STATUS_SYNDV (1ULL<<53) /* synd reg. valid */ -#define MCI_STATUS_DEFERRED (1ULL<<44) /* uncorrected error, deferred exception */ -#define MCI_STATUS_POISON (1ULL<<43) /* access poisonous data */ +#define MCI_STATUS_TCC BIT_ULL(55) /* Task context corrupt */ +#define MCI_STATUS_SYNDV BIT_ULL(53) /* synd reg. valid */ +#define MCI_STATUS_DEFERRED BIT_ULL(44) /* uncorrected error, deferred exception */ +#define MCI_STATUS_POISON BIT_ULL(43) /* access poisonous data */ /* * McaX field if set indicates a given bank supports MCA extensions: @@ -84,7 +87,7 @@ #define MCI_MISC_ADDR_GENERIC 7 /* generic */ /* CTL2 register defines */ -#define MCI_CTL2_CMCI_EN (1ULL << 30) +#define MCI_CTL2_CMCI_EN BIT_ULL(30) #define MCI_CTL2_CMCI_THRESHOLD_MASK 0x7fffULL #define MCJ_CTX_MASK 3 @@ -214,6 +217,8 @@ static inline void mce_amd_feature_init(struct cpuinfo_x86 *c) { } static inline int umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr) { return -EINVAL; }; #endif +static inline void mce_hygon_feature_init(struct cpuinfo_x86 *c) { return mce_amd_feature_init(c); } + int mce_available(struct cpuinfo_x86 *c); bool mce_is_memory_error(struct mce *m); bool mce_is_correctable(struct mce *m); diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index eeeb9289c764..19d18fae6ec6 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -16,12 +16,12 @@ extern atomic64_t last_mm_ctx_id; -#ifndef CONFIG_PARAVIRT +#ifndef CONFIG_PARAVIRT_XXL static inline void paravirt_activate_mm(struct mm_struct *prev, struct mm_struct *next) { } -#endif /* !CONFIG_PARAVIRT */ +#endif /* !CONFIG_PARAVIRT_XXL */ #ifdef CONFIG_PERF_EVENTS @@ -178,6 +178,10 @@ static inline void switch_ldt(struct mm_struct *prev, struct mm_struct *next) void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk); +/* + * Init a new mm. Used on mm copies, like at fork() + * and on mm's that are brand-new, like at execve(). + */ static inline int init_new_context(struct task_struct *tsk, struct mm_struct *mm) { @@ -228,8 +232,22 @@ do { \ } while (0) #endif +static inline void arch_dup_pkeys(struct mm_struct *oldmm, + struct mm_struct *mm) +{ +#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS + if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) + return; + + /* Duplicate the oldmm pkey state in mm: */ + mm->context.pkey_allocation_map = oldmm->context.pkey_allocation_map; + mm->context.execute_only_pkey = oldmm->context.execute_only_pkey; +#endif +} + static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) { + arch_dup_pkeys(oldmm, mm); paravirt_arch_dup_mmap(oldmm, mm); return ldt_dup_context(oldmm, mm); } diff --git a/arch/x86/include/asm/mpx.h b/arch/x86/include/asm/mpx.h index 61eb4b63c5ec..d0b1434fb0b6 100644 --- a/arch/x86/include/asm/mpx.h +++ b/arch/x86/include/asm/mpx.h @@ -57,8 +57,14 @@ #define MPX_BNDCFG_ADDR_MASK (~((1UL<<MPX_BNDCFG_TAIL)-1)) #define MPX_BNDSTA_ERROR_CODE 0x3 +struct mpx_fault_info { + void __user *addr; + void __user *lower; + void __user *upper; +}; + #ifdef CONFIG_X86_INTEL_MPX -siginfo_t *mpx_generate_siginfo(struct pt_regs *regs); +int mpx_fault_info(struct mpx_fault_info *info, struct pt_regs *regs); int mpx_handle_bd_fault(void); static inline int kernel_managing_mpx_tables(struct mm_struct *mm) { @@ -78,9 +84,9 @@ void mpx_notify_unmap(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long mpx_unmapped_area_check(unsigned long addr, unsigned long len, unsigned long flags); #else -static inline siginfo_t *mpx_generate_siginfo(struct pt_regs *regs) +static inline int mpx_fault_info(struct mpx_fault_info *info, struct pt_regs *regs) { - return NULL; + return -EINVAL; } static inline int mpx_handle_bd_fault(void) { diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index f37704497d8f..cc60e617931c 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -22,6 +22,11 @@ struct ms_hyperv_info { extern struct ms_hyperv_info ms_hyperv; + +typedef int (*hyperv_fill_flush_list_func)( + struct hv_guest_mapping_flush_list *flush, + void *data); + /* * Generate the guest ID. */ @@ -232,7 +237,7 @@ static inline u64 hv_do_fast_hypercall16(u16 code, u64 input1, u64 input2) : "cc"); } #endif - return hv_status; + return hv_status; } /* @@ -348,9 +353,16 @@ void set_hv_tscchange_cb(void (*cb)(void)); void clear_hv_tscchange_cb(void); void hyperv_stop_tsc_emulation(void); int hyperv_flush_guest_mapping(u64 as); +int hyperv_flush_guest_mapping_range(u64 as, + hyperv_fill_flush_list_func fill_func, void *data); +int hyperv_fill_flush_guest_mapping_list( + struct hv_guest_mapping_flush_list *flush, + u64 start_gfn, u64 end_gfn); #ifdef CONFIG_X86_64 void hv_apic_init(void); +void __init hv_init_spinlocks(void); +bool hv_vcpu_is_preempted(int vcpu); #else static inline void hv_apic_init(void) {} #endif @@ -368,6 +380,11 @@ static inline struct hv_vp_assist_page *hv_get_vp_assist_page(unsigned int cpu) return NULL; } static inline int hyperv_flush_guest_mapping(u64 as) { return -1; } +static inline int hyperv_flush_guest_mapping_range(u64 as, + hyperv_fill_flush_list_func fill_func, void *data) +{ + return -1; +} #endif /* CONFIG_HYPERV */ #ifdef CONFIG_HYPERV_TSCPAGE diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 4731f0cf97c5..8e40c2446fd1 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -41,9 +41,10 @@ #define MSR_IA32_SPEC_CTRL 0x00000048 /* Speculation Control */ #define SPEC_CTRL_IBRS (1 << 0) /* Indirect Branch Restricted Speculation */ -#define SPEC_CTRL_STIBP (1 << 1) /* Single Thread Indirect Branch Predictors */ +#define SPEC_CTRL_STIBP_SHIFT 1 /* Single Thread Indirect Branch Predictor (STIBP) bit */ +#define SPEC_CTRL_STIBP (1 << SPEC_CTRL_STIBP_SHIFT) /* STIBP mask */ #define SPEC_CTRL_SSBD_SHIFT 2 /* Speculative Store Bypass Disable bit */ -#define SPEC_CTRL_SSBD (1 << SPEC_CTRL_SSBD_SHIFT) /* Speculative Store Bypass Disable */ +#define SPEC_CTRL_SSBD (1 << SPEC_CTRL_SSBD_SHIFT) /* Speculative Store Bypass Disable */ #define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */ #define PRED_CMD_IBPB (1 << 0) /* Indirect Branch Prediction Barrier */ @@ -120,7 +121,43 @@ #define MSR_PEBS_LD_LAT_THRESHOLD 0x000003f6 #define MSR_IA32_RTIT_CTL 0x00000570 +#define RTIT_CTL_TRACEEN BIT(0) +#define RTIT_CTL_CYCLEACC BIT(1) +#define RTIT_CTL_OS BIT(2) +#define RTIT_CTL_USR BIT(3) +#define RTIT_CTL_PWR_EVT_EN BIT(4) +#define RTIT_CTL_FUP_ON_PTW BIT(5) +#define RTIT_CTL_FABRIC_EN BIT(6) +#define RTIT_CTL_CR3EN BIT(7) +#define RTIT_CTL_TOPA BIT(8) +#define RTIT_CTL_MTC_EN BIT(9) +#define RTIT_CTL_TSC_EN BIT(10) +#define RTIT_CTL_DISRETC BIT(11) +#define RTIT_CTL_PTW_EN BIT(12) +#define RTIT_CTL_BRANCH_EN BIT(13) +#define RTIT_CTL_MTC_RANGE_OFFSET 14 +#define RTIT_CTL_MTC_RANGE (0x0full << RTIT_CTL_MTC_RANGE_OFFSET) +#define RTIT_CTL_CYC_THRESH_OFFSET 19 +#define RTIT_CTL_CYC_THRESH (0x0full << RTIT_CTL_CYC_THRESH_OFFSET) +#define RTIT_CTL_PSB_FREQ_OFFSET 24 +#define RTIT_CTL_PSB_FREQ (0x0full << RTIT_CTL_PSB_FREQ_OFFSET) +#define RTIT_CTL_ADDR0_OFFSET 32 +#define RTIT_CTL_ADDR0 (0x0full << RTIT_CTL_ADDR0_OFFSET) +#define RTIT_CTL_ADDR1_OFFSET 36 +#define RTIT_CTL_ADDR1 (0x0full << RTIT_CTL_ADDR1_OFFSET) +#define RTIT_CTL_ADDR2_OFFSET 40 +#define RTIT_CTL_ADDR2 (0x0full << RTIT_CTL_ADDR2_OFFSET) +#define RTIT_CTL_ADDR3_OFFSET 44 +#define RTIT_CTL_ADDR3 (0x0full << RTIT_CTL_ADDR3_OFFSET) #define MSR_IA32_RTIT_STATUS 0x00000571 +#define RTIT_STATUS_FILTEREN BIT(0) +#define RTIT_STATUS_CONTEXTEN BIT(1) +#define RTIT_STATUS_TRIGGEREN BIT(2) +#define RTIT_STATUS_BUFFOVF BIT(3) +#define RTIT_STATUS_ERROR BIT(4) +#define RTIT_STATUS_STOPPED BIT(5) +#define RTIT_STATUS_BYTECNT_OFFSET 32 +#define RTIT_STATUS_BYTECNT (0x1ffffull << RTIT_STATUS_BYTECNT_OFFSET) #define MSR_IA32_RTIT_ADDR0_A 0x00000580 #define MSR_IA32_RTIT_ADDR0_B 0x00000581 #define MSR_IA32_RTIT_ADDR1_A 0x00000582 @@ -164,6 +201,7 @@ #define DEBUGCTLMSR_BTS_OFF_OS (1UL << 9) #define DEBUGCTLMSR_BTS_OFF_USR (1UL << 10) #define DEBUGCTLMSR_FREEZE_LBRS_ON_PMI (1UL << 11) +#define DEBUGCTLMSR_FREEZE_PERFMON_ON_PMI (1UL << 12) #define DEBUGCTLMSR_FREEZE_IN_SMM_BIT 14 #define DEBUGCTLMSR_FREEZE_IN_SMM (1UL << DEBUGCTLMSR_FREEZE_IN_SMM_BIT) @@ -388,6 +426,7 @@ #define MSR_F15H_NB_PERF_CTR 0xc0010241 #define MSR_F15H_PTSC 0xc0010280 #define MSR_F15H_IC_CFG 0xc0011021 +#define MSR_F15H_EX_CFG 0xc001102c /* Fam 10h MSRs */ #define MSR_FAM10H_MMIO_CONF_BASE 0xc0010058 @@ -769,6 +808,7 @@ #define VMX_BASIC_INOUT 0x0040000000000000LLU /* MSR_IA32_VMX_MISC bits */ +#define MSR_IA32_VMX_MISC_INTEL_PT (1ULL << 14) #define MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS (1ULL << 29) #define MSR_IA32_VMX_MISC_PREEMPTION_TIMER_SCALE 0x1F /* AMD-V MSRs */ diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index 04addd6e0a4a..91e4cf189914 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -242,7 +242,7 @@ static inline unsigned long long native_read_pmc(int counter) return EAX_EDX_VAL(val, low, high); } -#ifdef CONFIG_PARAVIRT +#ifdef CONFIG_PARAVIRT_XXL #include <asm/paravirt.h> #else #include <linux/errno.h> @@ -305,7 +305,7 @@ do { \ #define rdpmcl(counter, val) ((val) = native_read_pmc(counter)) -#endif /* !CONFIG_PARAVIRT */ +#endif /* !CONFIG_PARAVIRT_XXL */ /* * 64-bit version of wrmsr_safe(): diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index fd2a8c1b88bc..dad12b767ba0 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -3,6 +3,8 @@ #ifndef _ASM_X86_NOSPEC_BRANCH_H_ #define _ASM_X86_NOSPEC_BRANCH_H_ +#include <linux/static_key.h> + #include <asm/alternative.h> #include <asm/alternative-asm.h> #include <asm/cpufeatures.h> @@ -162,29 +164,35 @@ _ASM_PTR " 999b\n\t" \ ".popsection\n\t" -#if defined(CONFIG_X86_64) && defined(RETPOLINE) +#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_X86_64 /* - * Since the inline asm uses the %V modifier which is only in newer GCC, - * the 64-bit one is dependent on RETPOLINE not CONFIG_RETPOLINE. + * Inline asm uses the %V modifier which is only in newer GCC + * which is ensured when CONFIG_RETPOLINE is defined. */ # define CALL_NOSPEC \ ANNOTATE_NOSPEC_ALTERNATIVE \ - ALTERNATIVE( \ + ALTERNATIVE_2( \ ANNOTATE_RETPOLINE_SAFE \ "call *%[thunk_target]\n", \ "call __x86_indirect_thunk_%V[thunk_target]\n", \ - X86_FEATURE_RETPOLINE) + X86_FEATURE_RETPOLINE, \ + "lfence;\n" \ + ANNOTATE_RETPOLINE_SAFE \ + "call *%[thunk_target]\n", \ + X86_FEATURE_RETPOLINE_AMD) # define THUNK_TARGET(addr) [thunk_target] "r" (addr) -#elif defined(CONFIG_X86_32) && defined(CONFIG_RETPOLINE) +#else /* CONFIG_X86_32 */ /* * For i386 we use the original ret-equivalent retpoline, because * otherwise we'll run out of registers. We don't care about CET * here, anyway. */ # define CALL_NOSPEC \ - ALTERNATIVE( \ + ANNOTATE_NOSPEC_ALTERNATIVE \ + ALTERNATIVE_2( \ ANNOTATE_RETPOLINE_SAFE \ "call *%[thunk_target]\n", \ " jmp 904f;\n" \ @@ -199,9 +207,14 @@ " ret;\n" \ " .align 16\n" \ "904: call 901b;\n", \ - X86_FEATURE_RETPOLINE) + X86_FEATURE_RETPOLINE, \ + "lfence;\n" \ + ANNOTATE_RETPOLINE_SAFE \ + "call *%[thunk_target]\n", \ + X86_FEATURE_RETPOLINE_AMD) # define THUNK_TARGET(addr) [thunk_target] "rm" (addr) +#endif #else /* No retpoline for C / inline asm */ # define CALL_NOSPEC "call *%[thunk_target]\n" # define THUNK_TARGET(addr) [thunk_target] "rm" (addr) @@ -210,13 +223,20 @@ /* The Spectre V2 mitigation variants */ enum spectre_v2_mitigation { SPECTRE_V2_NONE, - SPECTRE_V2_RETPOLINE_MINIMAL, - SPECTRE_V2_RETPOLINE_MINIMAL_AMD, SPECTRE_V2_RETPOLINE_GENERIC, SPECTRE_V2_RETPOLINE_AMD, SPECTRE_V2_IBRS_ENHANCED, }; +/* The indirect branch speculation control variants */ +enum spectre_v2_user_mitigation { + SPECTRE_V2_USER_NONE, + SPECTRE_V2_USER_STRICT, + SPECTRE_V2_USER_STRICT_PREFERRED, + SPECTRE_V2_USER_PRCTL, + SPECTRE_V2_USER_SECCOMP, +}; + /* The Speculative Store Bypass disable variants */ enum ssb_mitigation { SPEC_STORE_BYPASS_NONE, @@ -294,6 +314,10 @@ do { \ preempt_enable(); \ } while (0) +DECLARE_STATIC_KEY_FALSE(switch_to_cond_stibp); +DECLARE_STATIC_KEY_FALSE(switch_mm_cond_ibpb); +DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb); + #endif /* __ASSEMBLY__ */ /* diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h index b99d497e342d..0ce558a8150d 100644 --- a/arch/x86/include/asm/page_64_types.h +++ b/arch/x86/include/asm/page_64_types.h @@ -7,7 +7,11 @@ #endif #ifdef CONFIG_KASAN +#ifdef CONFIG_KASAN_EXTRA +#define KASAN_STACK_ORDER 2 +#else #define KASAN_STACK_ORDER 1 +#endif #else #define KASAN_STACK_ORDER 0 #endif @@ -61,13 +65,16 @@ #endif /* - * Kernel image size is limited to 1GiB due to the fixmap living in the - * next 1GiB (see level2_kernel_pgt in arch/x86/kernel/head_64.S). Use - * 512MiB by default, leaving 1.5GiB for modules once the page tables - * are fully set up. If kernel ASLR is configured, it can extend the - * kernel page table mapping, reducing the size of the modules area. + * Maximum kernel image size is limited to 1 GiB, due to the fixmap living + * in the next 1 GiB (see level2_kernel_pgt in arch/x86/kernel/head_64.S). + * + * On KASLR use 1 GiB by default, leaving 1 GiB for modules once the + * page tables are fully set up. + * + * If KASLR is disabled we can shrink it to 0.5 GiB and increase the size + * of the modules area to 1.5 GiB. */ -#if defined(CONFIG_RANDOMIZE_BASE) +#ifdef CONFIG_RANDOMIZE_BASE #define KERNEL_IMAGE_SIZE (1024 * 1024 * 1024) #else #define KERNEL_IMAGE_SIZE (512 * 1024 * 1024) diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index e375d4266b53..a97f28d914d5 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -17,16 +17,78 @@ #include <linux/cpumask.h> #include <asm/frame.h> +static inline unsigned long long paravirt_sched_clock(void) +{ + return PVOP_CALL0(unsigned long long, time.sched_clock); +} + +struct static_key; +extern struct static_key paravirt_steal_enabled; +extern struct static_key paravirt_steal_rq_enabled; + +__visible void __native_queued_spin_unlock(struct qspinlock *lock); +bool pv_is_native_spin_unlock(void); +__visible bool __native_vcpu_is_preempted(long cpu); +bool pv_is_native_vcpu_is_preempted(void); + +static inline u64 paravirt_steal_clock(int cpu) +{ + return PVOP_CALL1(u64, time.steal_clock, cpu); +} + +/* The paravirtualized I/O functions */ +static inline void slow_down_io(void) +{ + pv_ops.cpu.io_delay(); +#ifdef REALLY_SLOW_IO + pv_ops.cpu.io_delay(); + pv_ops.cpu.io_delay(); + pv_ops.cpu.io_delay(); +#endif +} + +static inline void __flush_tlb(void) +{ + PVOP_VCALL0(mmu.flush_tlb_user); +} + +static inline void __flush_tlb_global(void) +{ + PVOP_VCALL0(mmu.flush_tlb_kernel); +} + +static inline void __flush_tlb_one_user(unsigned long addr) +{ + PVOP_VCALL1(mmu.flush_tlb_one_user, addr); +} + +static inline void flush_tlb_others(const struct cpumask *cpumask, + const struct flush_tlb_info *info) +{ + PVOP_VCALL2(mmu.flush_tlb_others, cpumask, info); +} + +static inline void paravirt_tlb_remove_table(struct mmu_gather *tlb, void *table) +{ + PVOP_VCALL2(mmu.tlb_remove_table, tlb, table); +} + +static inline void paravirt_arch_exit_mmap(struct mm_struct *mm) +{ + PVOP_VCALL1(mmu.exit_mmap, mm); +} + +#ifdef CONFIG_PARAVIRT_XXL static inline void load_sp0(unsigned long sp0) { - PVOP_VCALL1(pv_cpu_ops.load_sp0, sp0); + PVOP_VCALL1(cpu.load_sp0, sp0); } /* The paravirtualized CPUID instruction. */ static inline void __cpuid(unsigned int *eax, unsigned int *ebx, unsigned int *ecx, unsigned int *edx) { - PVOP_VCALL4(pv_cpu_ops.cpuid, eax, ebx, ecx, edx); + PVOP_VCALL4(cpu.cpuid, eax, ebx, ecx, edx); } /* @@ -34,98 +96,98 @@ static inline void __cpuid(unsigned int *eax, unsigned int *ebx, */ static inline unsigned long paravirt_get_debugreg(int reg) { - return PVOP_CALL1(unsigned long, pv_cpu_ops.get_debugreg, reg); + return PVOP_CALL1(unsigned long, cpu.get_debugreg, reg); } #define get_debugreg(var, reg) var = paravirt_get_debugreg(reg) static inline void set_debugreg(unsigned long val, int reg) { - PVOP_VCALL2(pv_cpu_ops.set_debugreg, reg, val); + PVOP_VCALL2(cpu.set_debugreg, reg, val); } static inline unsigned long read_cr0(void) { - return PVOP_CALL0(unsigned long, pv_cpu_ops.read_cr0); + return PVOP_CALL0(unsigned long, cpu.read_cr0); } static inline void write_cr0(unsigned long x) { - PVOP_VCALL1(pv_cpu_ops.write_cr0, x); + PVOP_VCALL1(cpu.write_cr0, x); } static inline unsigned long read_cr2(void) { - return PVOP_CALL0(unsigned long, pv_mmu_ops.read_cr2); + return PVOP_CALL0(unsigned long, mmu.read_cr2); } static inline void write_cr2(unsigned long x) { - PVOP_VCALL1(pv_mmu_ops.write_cr2, x); + PVOP_VCALL1(mmu.write_cr2, x); } static inline unsigned long __read_cr3(void) { - return PVOP_CALL0(unsigned long, pv_mmu_ops.read_cr3); + return PVOP_CALL0(unsigned long, mmu.read_cr3); } static inline void write_cr3(unsigned long x) { - PVOP_VCALL1(pv_mmu_ops.write_cr3, x); + PVOP_VCALL1(mmu.write_cr3, x); } static inline void __write_cr4(unsigned long x) { - PVOP_VCALL1(pv_cpu_ops.write_cr4, x); + PVOP_VCALL1(cpu.write_cr4, x); } #ifdef CONFIG_X86_64 static inline unsigned long read_cr8(void) { - return PVOP_CALL0(unsigned long, pv_cpu_ops.read_cr8); + return PVOP_CALL0(unsigned long, cpu.read_cr8); } static inline void write_cr8(unsigned long x) { - PVOP_VCALL1(pv_cpu_ops.write_cr8, x); + PVOP_VCALL1(cpu.write_cr8, x); } #endif static inline void arch_safe_halt(void) { - PVOP_VCALL0(pv_irq_ops.safe_halt); + PVOP_VCALL0(irq.safe_halt); } static inline void halt(void) { - PVOP_VCALL0(pv_irq_ops.halt); + PVOP_VCALL0(irq.halt); } static inline void wbinvd(void) { - PVOP_VCALL0(pv_cpu_ops.wbinvd); + PVOP_VCALL0(cpu.wbinvd); } #define get_kernel_rpl() (pv_info.kernel_rpl) static inline u64 paravirt_read_msr(unsigned msr) { - return PVOP_CALL1(u64, pv_cpu_ops.read_msr, msr); + return PVOP_CALL1(u64, cpu.read_msr, msr); } static inline void paravirt_write_msr(unsigned msr, unsigned low, unsigned high) { - PVOP_VCALL3(pv_cpu_ops.write_msr, msr, low, high); + PVOP_VCALL3(cpu.write_msr, msr, low, high); } static inline u64 paravirt_read_msr_safe(unsigned msr, int *err) { - return PVOP_CALL2(u64, pv_cpu_ops.read_msr_safe, msr, err); + return PVOP_CALL2(u64, cpu.read_msr_safe, msr, err); } static inline int paravirt_write_msr_safe(unsigned msr, unsigned low, unsigned high) { - return PVOP_CALL3(int, pv_cpu_ops.write_msr_safe, msr, low, high); + return PVOP_CALL3(int, cpu.write_msr_safe, msr, low, high); } #define rdmsr(msr, val1, val2) \ @@ -170,23 +232,9 @@ static inline int rdmsrl_safe(unsigned msr, unsigned long long *p) return err; } -static inline unsigned long long paravirt_sched_clock(void) -{ - return PVOP_CALL0(unsigned long long, pv_time_ops.sched_clock); -} - -struct static_key; -extern struct static_key paravirt_steal_enabled; -extern struct static_key paravirt_steal_rq_enabled; - -static inline u64 paravirt_steal_clock(int cpu) -{ - return PVOP_CALL1(u64, pv_time_ops.steal_clock, cpu); -} - static inline unsigned long long paravirt_read_pmc(int counter) { - return PVOP_CALL1(u64, pv_cpu_ops.read_pmc, counter); + return PVOP_CALL1(u64, cpu.read_pmc, counter); } #define rdpmc(counter, low, high) \ @@ -200,166 +248,127 @@ do { \ static inline void paravirt_alloc_ldt(struct desc_struct *ldt, unsigned entries) { - PVOP_VCALL2(pv_cpu_ops.alloc_ldt, ldt, entries); + PVOP_VCALL2(cpu.alloc_ldt, ldt, entries); } static inline void paravirt_free_ldt(struct desc_struct *ldt, unsigned entries) { - PVOP_VCALL2(pv_cpu_ops.free_ldt, ldt, entries); + PVOP_VCALL2(cpu.free_ldt, ldt, entries); } static inline void load_TR_desc(void) { - PVOP_VCALL0(pv_cpu_ops.load_tr_desc); + PVOP_VCALL0(cpu.load_tr_desc); } static inline void load_gdt(const struct desc_ptr *dtr) { - PVOP_VCALL1(pv_cpu_ops.load_gdt, dtr); + PVOP_VCALL1(cpu.load_gdt, dtr); } static inline void load_idt(const struct desc_ptr *dtr) { - PVOP_VCALL1(pv_cpu_ops.load_idt, dtr); + PVOP_VCALL1(cpu.load_idt, dtr); } static inline void set_ldt(const void *addr, unsigned entries) { - PVOP_VCALL2(pv_cpu_ops.set_ldt, addr, entries); + PVOP_VCALL2(cpu.set_ldt, addr, entries); } static inline unsigned long paravirt_store_tr(void) { - return PVOP_CALL0(unsigned long, pv_cpu_ops.store_tr); + return PVOP_CALL0(unsigned long, cpu.store_tr); } + #define store_tr(tr) ((tr) = paravirt_store_tr()) static inline void load_TLS(struct thread_struct *t, unsigned cpu) { - PVOP_VCALL2(pv_cpu_ops.load_tls, t, cpu); + PVOP_VCALL2(cpu.load_tls, t, cpu); } #ifdef CONFIG_X86_64 static inline void load_gs_index(unsigned int gs) { - PVOP_VCALL1(pv_cpu_ops.load_gs_index, gs); + PVOP_VCALL1(cpu.load_gs_index, gs); } #endif static inline void write_ldt_entry(struct desc_struct *dt, int entry, const void *desc) { - PVOP_VCALL3(pv_cpu_ops.write_ldt_entry, dt, entry, desc); + PVOP_VCALL3(cpu.write_ldt_entry, dt, entry, desc); } static inline void write_gdt_entry(struct desc_struct *dt, int entry, void *desc, int type) { - PVOP_VCALL4(pv_cpu_ops.write_gdt_entry, dt, entry, desc, type); + PVOP_VCALL4(cpu.write_gdt_entry, dt, entry, desc, type); } static inline void write_idt_entry(gate_desc *dt, int entry, const gate_desc *g) { - PVOP_VCALL3(pv_cpu_ops.write_idt_entry, dt, entry, g); + PVOP_VCALL3(cpu.write_idt_entry, dt, entry, g); } static inline void set_iopl_mask(unsigned mask) { - PVOP_VCALL1(pv_cpu_ops.set_iopl_mask, mask); -} - -/* The paravirtualized I/O functions */ -static inline void slow_down_io(void) -{ - pv_cpu_ops.io_delay(); -#ifdef REALLY_SLOW_IO - pv_cpu_ops.io_delay(); - pv_cpu_ops.io_delay(); - pv_cpu_ops.io_delay(); -#endif + PVOP_VCALL1(cpu.set_iopl_mask, mask); } static inline void paravirt_activate_mm(struct mm_struct *prev, struct mm_struct *next) { - PVOP_VCALL2(pv_mmu_ops.activate_mm, prev, next); + PVOP_VCALL2(mmu.activate_mm, prev, next); } static inline void paravirt_arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) { - PVOP_VCALL2(pv_mmu_ops.dup_mmap, oldmm, mm); -} - -static inline void paravirt_arch_exit_mmap(struct mm_struct *mm) -{ - PVOP_VCALL1(pv_mmu_ops.exit_mmap, mm); -} - -static inline void __flush_tlb(void) -{ - PVOP_VCALL0(pv_mmu_ops.flush_tlb_user); -} -static inline void __flush_tlb_global(void) -{ - PVOP_VCALL0(pv_mmu_ops.flush_tlb_kernel); -} -static inline void __flush_tlb_one_user(unsigned long addr) -{ - PVOP_VCALL1(pv_mmu_ops.flush_tlb_one_user, addr); -} - -static inline void flush_tlb_others(const struct cpumask *cpumask, - const struct flush_tlb_info *info) -{ - PVOP_VCALL2(pv_mmu_ops.flush_tlb_others, cpumask, info); -} - -static inline void paravirt_tlb_remove_table(struct mmu_gather *tlb, void *table) -{ - PVOP_VCALL2(pv_mmu_ops.tlb_remove_table, tlb, table); + PVOP_VCALL2(mmu.dup_mmap, oldmm, mm); } static inline int paravirt_pgd_alloc(struct mm_struct *mm) { - return PVOP_CALL1(int, pv_mmu_ops.pgd_alloc, mm); + return PVOP_CALL1(int, mmu.pgd_alloc, mm); } static inline void paravirt_pgd_free(struct mm_struct *mm, pgd_t *pgd) { - PVOP_VCALL2(pv_mmu_ops.pgd_free, mm, pgd); + PVOP_VCALL2(mmu.pgd_free, mm, pgd); } static inline void paravirt_alloc_pte(struct mm_struct *mm, unsigned long pfn) { - PVOP_VCALL2(pv_mmu_ops.alloc_pte, mm, pfn); + PVOP_VCALL2(mmu.alloc_pte, mm, pfn); } static inline void paravirt_release_pte(unsigned long pfn) { - PVOP_VCALL1(pv_mmu_ops.release_pte, pfn); + PVOP_VCALL1(mmu.release_pte, pfn); } static inline void paravirt_alloc_pmd(struct mm_struct *mm, unsigned long pfn) { - PVOP_VCALL2(pv_mmu_ops.alloc_pmd, mm, pfn); + PVOP_VCALL2(mmu.alloc_pmd, mm, pfn); } static inline void paravirt_release_pmd(unsigned long pfn) { - PVOP_VCALL1(pv_mmu_ops.release_pmd, pfn); + PVOP_VCALL1(mmu.release_pmd, pfn); } static inline void paravirt_alloc_pud(struct mm_struct *mm, unsigned long pfn) { - PVOP_VCALL2(pv_mmu_ops.alloc_pud, mm, pfn); + PVOP_VCALL2(mmu.alloc_pud, mm, pfn); } static inline void paravirt_release_pud(unsigned long pfn) { - PVOP_VCALL1(pv_mmu_ops.release_pud, pfn); + PVOP_VCALL1(mmu.release_pud, pfn); } static inline void paravirt_alloc_p4d(struct mm_struct *mm, unsigned long pfn) { - PVOP_VCALL2(pv_mmu_ops.alloc_p4d, mm, pfn); + PVOP_VCALL2(mmu.alloc_p4d, mm, pfn); } static inline void paravirt_release_p4d(unsigned long pfn) { - PVOP_VCALL1(pv_mmu_ops.release_p4d, pfn); + PVOP_VCALL1(mmu.release_p4d, pfn); } static inline pte_t __pte(pteval_t val) @@ -367,13 +376,9 @@ static inline pte_t __pte(pteval_t val) pteval_t ret; if (sizeof(pteval_t) > sizeof(long)) - ret = PVOP_CALLEE2(pteval_t, - pv_mmu_ops.make_pte, - val, (u64)val >> 32); + ret = PVOP_CALLEE2(pteval_t, mmu.make_pte, val, (u64)val >> 32); else - ret = PVOP_CALLEE1(pteval_t, - pv_mmu_ops.make_pte, - val); + ret = PVOP_CALLEE1(pteval_t, mmu.make_pte, val); return (pte_t) { .pte = ret }; } @@ -383,11 +388,10 @@ static inline pteval_t pte_val(pte_t pte) pteval_t ret; if (sizeof(pteval_t) > sizeof(long)) - ret = PVOP_CALLEE2(pteval_t, pv_mmu_ops.pte_val, + ret = PVOP_CALLEE2(pteval_t, mmu.pte_val, pte.pte, (u64)pte.pte >> 32); else - ret = PVOP_CALLEE1(pteval_t, pv_mmu_ops.pte_val, - pte.pte); + ret = PVOP_CALLEE1(pteval_t, mmu.pte_val, pte.pte); return ret; } @@ -397,11 +401,9 @@ static inline pgd_t __pgd(pgdval_t val) pgdval_t ret; if (sizeof(pgdval_t) > sizeof(long)) - ret = PVOP_CALLEE2(pgdval_t, pv_mmu_ops.make_pgd, - val, (u64)val >> 32); + ret = PVOP_CALLEE2(pgdval_t, mmu.make_pgd, val, (u64)val >> 32); else - ret = PVOP_CALLEE1(pgdval_t, pv_mmu_ops.make_pgd, - val); + ret = PVOP_CALLEE1(pgdval_t, mmu.make_pgd, val); return (pgd_t) { ret }; } @@ -411,11 +413,10 @@ static inline pgdval_t pgd_val(pgd_t pgd) pgdval_t ret; if (sizeof(pgdval_t) > sizeof(long)) - ret = PVOP_CALLEE2(pgdval_t, pv_mmu_ops.pgd_val, + ret = PVOP_CALLEE2(pgdval_t, mmu.pgd_val, pgd.pgd, (u64)pgd.pgd >> 32); else - ret = PVOP_CALLEE1(pgdval_t, pv_mmu_ops.pgd_val, - pgd.pgd); + ret = PVOP_CALLEE1(pgdval_t, mmu.pgd_val, pgd.pgd); return ret; } @@ -426,8 +427,7 @@ static inline pte_t ptep_modify_prot_start(struct mm_struct *mm, unsigned long a { pteval_t ret; - ret = PVOP_CALL3(pteval_t, pv_mmu_ops.ptep_modify_prot_start, - mm, addr, ptep); + ret = PVOP_CALL3(pteval_t, mmu.ptep_modify_prot_start, mm, addr, ptep); return (pte_t) { .pte = ret }; } @@ -437,20 +437,18 @@ static inline void ptep_modify_prot_commit(struct mm_struct *mm, unsigned long a { if (sizeof(pteval_t) > sizeof(long)) /* 5 arg words */ - pv_mmu_ops.ptep_modify_prot_commit(mm, addr, ptep, pte); + pv_ops.mmu.ptep_modify_prot_commit(mm, addr, ptep, pte); else - PVOP_VCALL4(pv_mmu_ops.ptep_modify_prot_commit, + PVOP_VCALL4(mmu.ptep_modify_prot_commit, mm, addr, ptep, pte.pte); } static inline void set_pte(pte_t *ptep, pte_t pte) { if (sizeof(pteval_t) > sizeof(long)) - PVOP_VCALL3(pv_mmu_ops.set_pte, ptep, - pte.pte, (u64)pte.pte >> 32); + PVOP_VCALL3(mmu.set_pte, ptep, pte.pte, (u64)pte.pte >> 32); else - PVOP_VCALL2(pv_mmu_ops.set_pte, ptep, - pte.pte); + PVOP_VCALL2(mmu.set_pte, ptep, pte.pte); } static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, @@ -458,9 +456,9 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, { if (sizeof(pteval_t) > sizeof(long)) /* 5 arg words */ - pv_mmu_ops.set_pte_at(mm, addr, ptep, pte); + pv_ops.mmu.set_pte_at(mm, addr, ptep, pte); else - PVOP_VCALL4(pv_mmu_ops.set_pte_at, mm, addr, ptep, pte.pte); + PVOP_VCALL4(mmu.set_pte_at, mm, addr, ptep, pte.pte); } static inline void set_pmd(pmd_t *pmdp, pmd_t pmd) @@ -468,9 +466,9 @@ static inline void set_pmd(pmd_t *pmdp, pmd_t pmd) pmdval_t val = native_pmd_val(pmd); if (sizeof(pmdval_t) > sizeof(long)) - PVOP_VCALL3(pv_mmu_ops.set_pmd, pmdp, val, (u64)val >> 32); + PVOP_VCALL3(mmu.set_pmd, pmdp, val, (u64)val >> 32); else - PVOP_VCALL2(pv_mmu_ops.set_pmd, pmdp, val); + PVOP_VCALL2(mmu.set_pmd, pmdp, val); } #if CONFIG_PGTABLE_LEVELS >= 3 @@ -479,11 +477,9 @@ static inline pmd_t __pmd(pmdval_t val) pmdval_t ret; if (sizeof(pmdval_t) > sizeof(long)) - ret = PVOP_CALLEE2(pmdval_t, pv_mmu_ops.make_pmd, - val, (u64)val >> 32); + ret = PVOP_CALLEE2(pmdval_t, mmu.make_pmd, val, (u64)val >> 32); else - ret = PVOP_CALLEE1(pmdval_t, pv_mmu_ops.make_pmd, - val); + ret = PVOP_CALLEE1(pmdval_t, mmu.make_pmd, val); return (pmd_t) { ret }; } @@ -493,11 +489,10 @@ static inline pmdval_t pmd_val(pmd_t pmd) pmdval_t ret; if (sizeof(pmdval_t) > sizeof(long)) - ret = PVOP_CALLEE2(pmdval_t, pv_mmu_ops.pmd_val, + ret = PVOP_CALLEE2(pmdval_t, mmu.pmd_val, pmd.pmd, (u64)pmd.pmd >> 32); else - ret = PVOP_CALLEE1(pmdval_t, pv_mmu_ops.pmd_val, - pmd.pmd); + ret = PVOP_CALLEE1(pmdval_t, mmu.pmd_val, pmd.pmd); return ret; } @@ -507,39 +502,23 @@ static inline void set_pud(pud_t *pudp, pud_t pud) pudval_t val = native_pud_val(pud); if (sizeof(pudval_t) > sizeof(long)) - PVOP_VCALL3(pv_mmu_ops.set_pud, pudp, - val, (u64)val >> 32); + PVOP_VCALL3(mmu.set_pud, pudp, val, (u64)val >> 32); else - PVOP_VCALL2(pv_mmu_ops.set_pud, pudp, - val); + PVOP_VCALL2(mmu.set_pud, pudp, val); } #if CONFIG_PGTABLE_LEVELS >= 4 static inline pud_t __pud(pudval_t val) { pudval_t ret; - if (sizeof(pudval_t) > sizeof(long)) - ret = PVOP_CALLEE2(pudval_t, pv_mmu_ops.make_pud, - val, (u64)val >> 32); - else - ret = PVOP_CALLEE1(pudval_t, pv_mmu_ops.make_pud, - val); + ret = PVOP_CALLEE1(pudval_t, mmu.make_pud, val); return (pud_t) { ret }; } static inline pudval_t pud_val(pud_t pud) { - pudval_t ret; - - if (sizeof(pudval_t) > sizeof(long)) - ret = PVOP_CALLEE2(pudval_t, pv_mmu_ops.pud_val, - pud.pud, (u64)pud.pud >> 32); - else - ret = PVOP_CALLEE1(pudval_t, pv_mmu_ops.pud_val, - pud.pud); - - return ret; + return PVOP_CALLEE1(pudval_t, mmu.pud_val, pud.pud); } static inline void pud_clear(pud_t *pudp) @@ -551,31 +530,26 @@ static inline void set_p4d(p4d_t *p4dp, p4d_t p4d) { p4dval_t val = native_p4d_val(p4d); - if (sizeof(p4dval_t) > sizeof(long)) - PVOP_VCALL3(pv_mmu_ops.set_p4d, p4dp, - val, (u64)val >> 32); - else - PVOP_VCALL2(pv_mmu_ops.set_p4d, p4dp, - val); + PVOP_VCALL2(mmu.set_p4d, p4dp, val); } #if CONFIG_PGTABLE_LEVELS >= 5 static inline p4d_t __p4d(p4dval_t val) { - p4dval_t ret = PVOP_CALLEE1(p4dval_t, pv_mmu_ops.make_p4d, val); + p4dval_t ret = PVOP_CALLEE1(p4dval_t, mmu.make_p4d, val); return (p4d_t) { ret }; } static inline p4dval_t p4d_val(p4d_t p4d) { - return PVOP_CALLEE1(p4dval_t, pv_mmu_ops.p4d_val, p4d.p4d); + return PVOP_CALLEE1(p4dval_t, mmu.p4d_val, p4d.p4d); } static inline void __set_pgd(pgd_t *pgdp, pgd_t pgd) { - PVOP_VCALL2(pv_mmu_ops.set_pgd, pgdp, native_pgd_val(pgd)); + PVOP_VCALL2(mmu.set_pgd, pgdp, native_pgd_val(pgd)); } #define set_pgd(pgdp, pgdval) do { \ @@ -606,19 +580,18 @@ static inline void p4d_clear(p4d_t *p4dp) 64-bit pte atomically */ static inline void set_pte_atomic(pte_t *ptep, pte_t pte) { - PVOP_VCALL3(pv_mmu_ops.set_pte_atomic, ptep, - pte.pte, pte.pte >> 32); + PVOP_VCALL3(mmu.set_pte_atomic, ptep, pte.pte, pte.pte >> 32); } static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - PVOP_VCALL3(pv_mmu_ops.pte_clear, mm, addr, ptep); + PVOP_VCALL3(mmu.pte_clear, mm, addr, ptep); } static inline void pmd_clear(pmd_t *pmdp) { - PVOP_VCALL1(pv_mmu_ops.pmd_clear, pmdp); + PVOP_VCALL1(mmu.pmd_clear, pmdp); } #else /* !CONFIG_X86_PAE */ static inline void set_pte_atomic(pte_t *ptep, pte_t pte) @@ -641,64 +614,68 @@ static inline void pmd_clear(pmd_t *pmdp) #define __HAVE_ARCH_START_CONTEXT_SWITCH static inline void arch_start_context_switch(struct task_struct *prev) { - PVOP_VCALL1(pv_cpu_ops.start_context_switch, prev); + PVOP_VCALL1(cpu.start_context_switch, prev); } static inline void arch_end_context_switch(struct task_struct *next) { - PVOP_VCALL1(pv_cpu_ops.end_context_switch, next); + PVOP_VCALL1(cpu.end_context_switch, next); } #define __HAVE_ARCH_ENTER_LAZY_MMU_MODE static inline void arch_enter_lazy_mmu_mode(void) { - PVOP_VCALL0(pv_mmu_ops.lazy_mode.enter); + PVOP_VCALL0(mmu.lazy_mode.enter); } static inline void arch_leave_lazy_mmu_mode(void) { - PVOP_VCALL0(pv_mmu_ops.lazy_mode.leave); + PVOP_VCALL0(mmu.lazy_mode.leave); } static inline void arch_flush_lazy_mmu_mode(void) { - PVOP_VCALL0(pv_mmu_ops.lazy_mode.flush); + PVOP_VCALL0(mmu.lazy_mode.flush); } static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx, phys_addr_t phys, pgprot_t flags) { - pv_mmu_ops.set_fixmap(idx, phys, flags); + pv_ops.mmu.set_fixmap(idx, phys, flags); } +#endif #if defined(CONFIG_SMP) && defined(CONFIG_PARAVIRT_SPINLOCKS) static __always_inline void pv_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val) { - PVOP_VCALL2(pv_lock_ops.queued_spin_lock_slowpath, lock, val); + PVOP_VCALL2(lock.queued_spin_lock_slowpath, lock, val); } static __always_inline void pv_queued_spin_unlock(struct qspinlock *lock) { - PVOP_VCALLEE1(pv_lock_ops.queued_spin_unlock, lock); + PVOP_VCALLEE1(lock.queued_spin_unlock, lock); } static __always_inline void pv_wait(u8 *ptr, u8 val) { - PVOP_VCALL2(pv_lock_ops.wait, ptr, val); + PVOP_VCALL2(lock.wait, ptr, val); } static __always_inline void pv_kick(int cpu) { - PVOP_VCALL1(pv_lock_ops.kick, cpu); + PVOP_VCALL1(lock.kick, cpu); } static __always_inline bool pv_vcpu_is_preempted(long cpu) { - return PVOP_CALLEE1(bool, pv_lock_ops.vcpu_is_preempted, cpu); + return PVOP_CALLEE1(bool, lock.vcpu_is_preempted, cpu); } +void __raw_callee_save___native_queued_spin_unlock(struct qspinlock *lock); +bool __raw_callee_save___native_vcpu_is_preempted(long cpu); + #endif /* SMP && PARAVIRT_SPINLOCKS */ #ifdef CONFIG_X86_32 @@ -778,24 +755,25 @@ static __always_inline bool pv_vcpu_is_preempted(long cpu) #define __PV_IS_CALLEE_SAVE(func) \ ((struct paravirt_callee_save) { func }) +#ifdef CONFIG_PARAVIRT_XXL static inline notrace unsigned long arch_local_save_flags(void) { - return PVOP_CALLEE0(unsigned long, pv_irq_ops.save_fl); + return PVOP_CALLEE0(unsigned long, irq.save_fl); } static inline notrace void arch_local_irq_restore(unsigned long f) { - PVOP_VCALLEE1(pv_irq_ops.restore_fl, f); + PVOP_VCALLEE1(irq.restore_fl, f); } static inline notrace void arch_local_irq_disable(void) { - PVOP_VCALLEE0(pv_irq_ops.irq_disable); + PVOP_VCALLEE0(irq.irq_disable); } static inline notrace void arch_local_irq_enable(void) { - PVOP_VCALLEE0(pv_irq_ops.irq_enable); + PVOP_VCALLEE0(irq.irq_enable); } static inline notrace unsigned long arch_local_irq_save(void) @@ -806,6 +784,7 @@ static inline notrace unsigned long arch_local_irq_save(void) arch_local_irq_disable(); return f; } +#endif /* Make sure as little as possible of this mess escapes. */ @@ -827,7 +806,7 @@ extern void default_banner(void); #else /* __ASSEMBLY__ */ -#define _PVSITE(ptype, clobbers, ops, word, algn) \ +#define _PVSITE(ptype, ops, word, algn) \ 771:; \ ops; \ 772:; \ @@ -836,7 +815,6 @@ extern void default_banner(void); word 771b; \ .byte ptype; \ .byte 772b-771b; \ - .short clobbers; \ .popsection @@ -868,8 +846,8 @@ extern void default_banner(void); COND_POP(set, CLBR_RCX, rcx); \ COND_POP(set, CLBR_RAX, rax) -#define PARA_PATCH(struct, off) ((PARAVIRT_PATCH_##struct + (off)) / 8) -#define PARA_SITE(ptype, clobbers, ops) _PVSITE(ptype, clobbers, ops, .quad, 8) +#define PARA_PATCH(off) ((off) / 8) +#define PARA_SITE(ptype, ops) _PVSITE(ptype, ops, .quad, 8) #define PARA_INDIRECT(addr) *addr(%rip) #else #define PV_SAVE_REGS(set) \ @@ -883,46 +861,41 @@ extern void default_banner(void); COND_POP(set, CLBR_EDI, edi); \ COND_POP(set, CLBR_EAX, eax) -#define PARA_PATCH(struct, off) ((PARAVIRT_PATCH_##struct + (off)) / 4) -#define PARA_SITE(ptype, clobbers, ops) _PVSITE(ptype, clobbers, ops, .long, 4) +#define PARA_PATCH(off) ((off) / 4) +#define PARA_SITE(ptype, ops) _PVSITE(ptype, ops, .long, 4) #define PARA_INDIRECT(addr) *%cs:addr #endif +#ifdef CONFIG_PARAVIRT_XXL #define INTERRUPT_RETURN \ - PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_iret), CLBR_NONE, \ - ANNOTATE_RETPOLINE_SAFE; \ - jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_iret);) + PARA_SITE(PARA_PATCH(PV_CPU_iret), \ + ANNOTATE_RETPOLINE_SAFE; \ + jmp PARA_INDIRECT(pv_ops+PV_CPU_iret);) #define DISABLE_INTERRUPTS(clobbers) \ - PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_disable), clobbers, \ + PARA_SITE(PARA_PATCH(PV_IRQ_irq_disable), \ PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \ - ANNOTATE_RETPOLINE_SAFE; \ - call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_disable); \ + ANNOTATE_RETPOLINE_SAFE; \ + call PARA_INDIRECT(pv_ops+PV_IRQ_irq_disable); \ PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);) #define ENABLE_INTERRUPTS(clobbers) \ - PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_enable), clobbers, \ + PARA_SITE(PARA_PATCH(PV_IRQ_irq_enable), \ PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \ - ANNOTATE_RETPOLINE_SAFE; \ - call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_enable); \ + ANNOTATE_RETPOLINE_SAFE; \ + call PARA_INDIRECT(pv_ops+PV_IRQ_irq_enable); \ PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);) +#endif -#ifdef CONFIG_X86_32 -#define GET_CR0_INTO_EAX \ - push %ecx; push %edx; \ - ANNOTATE_RETPOLINE_SAFE; \ - call PARA_INDIRECT(pv_cpu_ops+PV_CPU_read_cr0); \ - pop %edx; pop %ecx -#else /* !CONFIG_X86_32 */ - +#ifdef CONFIG_X86_64 +#ifdef CONFIG_PARAVIRT_XXL /* * If swapgs is used while the userspace stack is still current, * there's no way to call a pvop. The PV replacement *must* be * inlined, or the swapgs instruction must be trapped and emulated. */ #define SWAPGS_UNSAFE_STACK \ - PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_swapgs), CLBR_NONE, \ - swapgs) + PARA_SITE(PARA_PATCH(PV_CPU_swapgs), swapgs) /* * Note: swapgs is very special, and in practise is either going to be @@ -931,44 +904,51 @@ extern void default_banner(void); * it. */ #define SWAPGS \ - PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_swapgs), CLBR_NONE, \ - ANNOTATE_RETPOLINE_SAFE; \ - call PARA_INDIRECT(pv_cpu_ops+PV_CPU_swapgs); \ + PARA_SITE(PARA_PATCH(PV_CPU_swapgs), \ + ANNOTATE_RETPOLINE_SAFE; \ + call PARA_INDIRECT(pv_ops+PV_CPU_swapgs); \ ) +#endif #define GET_CR2_INTO_RAX \ ANNOTATE_RETPOLINE_SAFE; \ - call PARA_INDIRECT(pv_mmu_ops+PV_MMU_read_cr2); + call PARA_INDIRECT(pv_ops+PV_MMU_read_cr2); +#ifdef CONFIG_PARAVIRT_XXL #define USERGS_SYSRET64 \ - PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret64), \ - CLBR_NONE, \ - ANNOTATE_RETPOLINE_SAFE; \ - jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret64);) + PARA_SITE(PARA_PATCH(PV_CPU_usergs_sysret64), \ + ANNOTATE_RETPOLINE_SAFE; \ + jmp PARA_INDIRECT(pv_ops+PV_CPU_usergs_sysret64);) #ifdef CONFIG_DEBUG_ENTRY #define SAVE_FLAGS(clobbers) \ - PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_save_fl), clobbers, \ + PARA_SITE(PARA_PATCH(PV_IRQ_save_fl), \ PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \ - ANNOTATE_RETPOLINE_SAFE; \ - call PARA_INDIRECT(pv_irq_ops+PV_IRQ_save_fl); \ + ANNOTATE_RETPOLINE_SAFE; \ + call PARA_INDIRECT(pv_ops+PV_IRQ_save_fl); \ PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);) #endif +#endif #endif /* CONFIG_X86_32 */ #endif /* __ASSEMBLY__ */ #else /* CONFIG_PARAVIRT */ # define default_banner x86_init_noop +#endif /* !CONFIG_PARAVIRT */ + #ifndef __ASSEMBLY__ +#ifndef CONFIG_PARAVIRT_XXL static inline void paravirt_arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) { } +#endif +#ifndef CONFIG_PARAVIRT static inline void paravirt_arch_exit_mmap(struct mm_struct *mm) { } +#endif #endif /* __ASSEMBLY__ */ -#endif /* !CONFIG_PARAVIRT */ #endif /* _ASM_X86_PARAVIRT_H */ diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 4b75acc23b30..488c59686a73 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -66,12 +66,14 @@ struct paravirt_callee_save { /* general info */ struct pv_info { +#ifdef CONFIG_PARAVIRT_XXL unsigned int kernel_rpl; int shared_kernel_pmd; #ifdef CONFIG_X86_64 u16 extra_user_64bit_cs; /* __USER_CS if none */ #endif +#endif const char *name; }; @@ -85,17 +87,18 @@ struct pv_init_ops { * the number of bytes of code generated, as we nop pad the * rest in generic code. */ - unsigned (*patch)(u8 type, u16 clobber, void *insnbuf, + unsigned (*patch)(u8 type, void *insnbuf, unsigned long addr, unsigned len); } __no_randomize_layout; - +#ifdef CONFIG_PARAVIRT_XXL struct pv_lazy_ops { /* Set deferred update mode, used for batching operations. */ void (*enter)(void); void (*leave)(void); void (*flush)(void); } __no_randomize_layout; +#endif struct pv_time_ops { unsigned long long (*sched_clock)(void); @@ -104,6 +107,9 @@ struct pv_time_ops { struct pv_cpu_ops { /* hooks for various privileged instructions */ + void (*io_delay)(void); + +#ifdef CONFIG_PARAVIRT_XXL unsigned long (*get_debugreg)(int regno); void (*set_debugreg)(int regno, unsigned long value); @@ -141,7 +147,6 @@ struct pv_cpu_ops { void (*set_iopl_mask)(unsigned mask); void (*wbinvd)(void); - void (*io_delay)(void); /* cpuid emulation, mostly so that caps bits can be disabled */ void (*cpuid)(unsigned int *eax, unsigned int *ebx, @@ -176,9 +181,11 @@ struct pv_cpu_ops { void (*start_context_switch)(struct task_struct *prev); void (*end_context_switch)(struct task_struct *next); +#endif } __no_randomize_layout; struct pv_irq_ops { +#ifdef CONFIG_PARAVIRT_XXL /* * Get/set interrupt state. save_fl and restore_fl are only * expected to use X86_EFLAGS_IF; all other bits @@ -195,35 +202,34 @@ struct pv_irq_ops { void (*safe_halt)(void); void (*halt)(void); - +#endif } __no_randomize_layout; struct pv_mmu_ops { + /* TLB operations */ + void (*flush_tlb_user)(void); + void (*flush_tlb_kernel)(void); + void (*flush_tlb_one_user)(unsigned long addr); + void (*flush_tlb_others)(const struct cpumask *cpus, + const struct flush_tlb_info *info); + + void (*tlb_remove_table)(struct mmu_gather *tlb, void *table); + + /* Hook for intercepting the destruction of an mm_struct. */ + void (*exit_mmap)(struct mm_struct *mm); + +#ifdef CONFIG_PARAVIRT_XXL unsigned long (*read_cr2)(void); void (*write_cr2)(unsigned long); unsigned long (*read_cr3)(void); void (*write_cr3)(unsigned long); - /* - * Hooks for intercepting the creation/use/destruction of an - * mm_struct. - */ + /* Hooks for intercepting the creation/use of an mm_struct. */ void (*activate_mm)(struct mm_struct *prev, struct mm_struct *next); void (*dup_mmap)(struct mm_struct *oldmm, struct mm_struct *mm); - void (*exit_mmap)(struct mm_struct *mm); - - - /* TLB operations */ - void (*flush_tlb_user)(void); - void (*flush_tlb_kernel)(void); - void (*flush_tlb_one_user)(unsigned long addr); - void (*flush_tlb_others)(const struct cpumask *cpus, - const struct flush_tlb_info *info); - - void (*tlb_remove_table)(struct mmu_gather *tlb, void *table); /* Hooks for allocating and freeing a pagetable top-level */ int (*pgd_alloc)(struct mm_struct *mm); @@ -298,6 +304,7 @@ struct pv_mmu_ops { an mfn. We can tell which is which from the index. */ void (*set_fixmap)(unsigned /* enum fixed_addresses */ idx, phys_addr_t phys, pgprot_t flags); +#endif } __no_randomize_layout; struct arch_spinlock; @@ -321,28 +328,23 @@ struct pv_lock_ops { * number for each function using the offset which we use to indicate * what to patch. */ struct paravirt_patch_template { - struct pv_init_ops pv_init_ops; - struct pv_time_ops pv_time_ops; - struct pv_cpu_ops pv_cpu_ops; - struct pv_irq_ops pv_irq_ops; - struct pv_mmu_ops pv_mmu_ops; - struct pv_lock_ops pv_lock_ops; + struct pv_init_ops init; + struct pv_time_ops time; + struct pv_cpu_ops cpu; + struct pv_irq_ops irq; + struct pv_mmu_ops mmu; + struct pv_lock_ops lock; } __no_randomize_layout; extern struct pv_info pv_info; -extern struct pv_init_ops pv_init_ops; -extern struct pv_time_ops pv_time_ops; -extern struct pv_cpu_ops pv_cpu_ops; -extern struct pv_irq_ops pv_irq_ops; -extern struct pv_mmu_ops pv_mmu_ops; -extern struct pv_lock_ops pv_lock_ops; +extern struct paravirt_patch_template pv_ops; #define PARAVIRT_PATCH(x) \ (offsetof(struct paravirt_patch_template, x) / sizeof(void *)) #define paravirt_type(op) \ [paravirt_typenum] "i" (PARAVIRT_PATCH(op)), \ - [paravirt_opptr] "i" (&(op)) + [paravirt_opptr] "i" (&(pv_ops.op)) #define paravirt_clobber(clobber) \ [paravirt_clobber] "i" (clobber) @@ -371,22 +373,14 @@ extern struct pv_lock_ops pv_lock_ops; __visible extern const char start_##ops##_##name[], end_##ops##_##name[]; \ asm(NATIVE_LABEL("start_", ops, name) code NATIVE_LABEL("end_", ops, name)) -unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len); unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len); -unsigned paravirt_patch_call(void *insnbuf, - const void *target, u16 tgt_clobbers, - unsigned long addr, u16 site_clobbers, - unsigned len); -unsigned paravirt_patch_jmp(void *insnbuf, const void *target, - unsigned long addr, unsigned len); -unsigned paravirt_patch_default(u8 type, u16 clobbers, void *insnbuf, +unsigned paravirt_patch_default(u8 type, void *insnbuf, unsigned long addr, unsigned len); unsigned paravirt_patch_insns(void *insnbuf, unsigned len, const char *start, const char *end); -unsigned native_patch(u8 type, u16 clobbers, void *ibuf, - unsigned long addr, unsigned len); +unsigned native_patch(u8 type, void *ibuf, unsigned long addr, unsigned len); int paravirt_disable_iospace(void); @@ -510,9 +504,9 @@ int paravirt_disable_iospace(void); #endif /* CONFIG_X86_32 */ #ifdef CONFIG_PARAVIRT_DEBUG -#define PVOP_TEST_NULL(op) BUG_ON(op == NULL) +#define PVOP_TEST_NULL(op) BUG_ON(pv_ops.op == NULL) #else -#define PVOP_TEST_NULL(op) ((void)op) +#define PVOP_TEST_NULL(op) ((void)pv_ops.op) #endif #define PVOP_RETMASK(rettype) \ @@ -678,7 +672,6 @@ void paravirt_leave_lazy_mmu(void); void paravirt_flush_lazy_mmu(void); void _paravirt_nop(void); -u32 _paravirt_ident_32(u32); u64 _paravirt_ident_64(u64); #define paravirt_nop ((void *)_paravirt_nop) @@ -688,7 +681,6 @@ struct paravirt_patch_site { u8 *instr; /* original instructions */ u8 instrtype; /* type of this instruction */ u8 len; /* length of original instruction */ - u16 clobbers; /* what registers you may clobber */ }; extern struct paravirt_patch_site __parainstructions[], diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h index 959d618dbb17..73bb404f4d2a 100644 --- a/arch/x86/include/asm/pci_x86.h +++ b/arch/x86/include/asm/pci_x86.h @@ -121,7 +121,14 @@ extern void __init dmi_check_pciprobe(void); extern void __init dmi_check_skip_isa_align(void); /* some common used subsys_initcalls */ +#ifdef CONFIG_PCI extern int __init pci_acpi_init(void); +#else +static inline int __init pci_acpi_init(void) +{ + return -EINVAL; +} +#endif extern void __init pcibios_irq_init(void); extern int __init pcibios_init(void); extern int pci_legacy_init(void); diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 78241b736f2a..8bdf74902293 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -278,6 +278,7 @@ struct perf_guest_switch_msr { extern struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr); extern void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap); extern void perf_check_microcode(void); +extern int x86_perf_rdpmc_index(struct perf_event *event); #else static inline struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr) { diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h index fbd578daa66e..a281e61ec60c 100644 --- a/arch/x86/include/asm/pgalloc.h +++ b/arch/x86/include/asm/pgalloc.h @@ -8,7 +8,7 @@ static inline int __paravirt_pgd_alloc(struct mm_struct *mm) { return 0; } -#ifdef CONFIG_PARAVIRT +#ifdef CONFIG_PARAVIRT_XXL #include <asm/paravirt.h> #else #define paravirt_pgd_alloc(mm) __paravirt_pgd_alloc(mm) @@ -47,8 +47,8 @@ extern gfp_t __userpte_alloc_gfp; extern pgd_t *pgd_alloc(struct mm_struct *); extern void pgd_free(struct mm_struct *mm, pgd_t *pgd); -extern pte_t *pte_alloc_one_kernel(struct mm_struct *, unsigned long); -extern pgtable_t pte_alloc_one(struct mm_struct *, unsigned long); +extern pte_t *pte_alloc_one_kernel(struct mm_struct *); +extern pgtable_t pte_alloc_one(struct mm_struct *); /* Should really implement gc for free page table pages. This could be done with a reference count in struct page. */ @@ -80,6 +80,13 @@ static inline void pmd_populate_kernel(struct mm_struct *mm, set_pmd(pmd, __pmd(__pa(pte) | _PAGE_TABLE)); } +static inline void pmd_populate_kernel_safe(struct mm_struct *mm, + pmd_t *pmd, pte_t *pte) +{ + paravirt_alloc_pte(mm, __pa(pte) >> PAGE_SHIFT); + set_pmd_safe(pmd, __pmd(__pa(pte) | _PAGE_TABLE)); +} + static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, struct page *pte) { @@ -132,6 +139,12 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) paravirt_alloc_pmd(mm, __pa(pmd) >> PAGE_SHIFT); set_pud(pud, __pud(_PAGE_TABLE | __pa(pmd))); } + +static inline void pud_populate_safe(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) +{ + paravirt_alloc_pmd(mm, __pa(pmd) >> PAGE_SHIFT); + set_pud_safe(pud, __pud(_PAGE_TABLE | __pa(pmd))); +} #endif /* CONFIG_X86_PAE */ #if CONFIG_PGTABLE_LEVELS > 3 @@ -141,6 +154,12 @@ static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4d, pud_t *pud) set_p4d(p4d, __p4d(_PAGE_TABLE | __pa(pud))); } +static inline void p4d_populate_safe(struct mm_struct *mm, p4d_t *p4d, pud_t *pud) +{ + paravirt_alloc_pud(mm, __pa(pud) >> PAGE_SHIFT); + set_p4d_safe(p4d, __p4d(_PAGE_TABLE | __pa(pud))); +} + static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) { gfp_t gfp = GFP_KERNEL_ACCOUNT; @@ -173,6 +192,14 @@ static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, p4d_t *p4d) set_pgd(pgd, __pgd(_PAGE_TABLE | __pa(p4d))); } +static inline void pgd_populate_safe(struct mm_struct *mm, pgd_t *pgd, p4d_t *p4d) +{ + if (!pgtable_l5_enabled()) + return; + paravirt_alloc_p4d(mm, __pa(p4d) >> PAGE_SHIFT); + set_pgd_safe(pgd, __pgd(_PAGE_TABLE | __pa(p4d))); +} + static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long addr) { gfp_t gfp = GFP_KERNEL_ACCOUNT; diff --git a/arch/x86/include/asm/pgtable-3level_types.h b/arch/x86/include/asm/pgtable-3level_types.h index 858358a82b14..33845d36897c 100644 --- a/arch/x86/include/asm/pgtable-3level_types.h +++ b/arch/x86/include/asm/pgtable-3level_types.h @@ -20,7 +20,7 @@ typedef union { } pte_t; #endif /* !__ASSEMBLY__ */ -#ifdef CONFIG_PARAVIRT +#ifdef CONFIG_PARAVIRT_XXL #define SHARED_KERNEL_PMD ((!static_cpu_has(X86_FEATURE_PTI) && \ (pv_info.shared_kernel_pmd))) #else diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 690c0307afed..2779ace16d23 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -55,9 +55,9 @@ extern struct mm_struct *pgd_page_get_mm(struct page *page); extern pmdval_t early_pmd_flags; -#ifdef CONFIG_PARAVIRT +#ifdef CONFIG_PARAVIRT_XXL #include <asm/paravirt.h> -#else /* !CONFIG_PARAVIRT */ +#else /* !CONFIG_PARAVIRT_XXL */ #define set_pte(ptep, pte) native_set_pte(ptep, pte) #define set_pte_at(mm, addr, ptep, pte) native_set_pte_at(mm, addr, ptep, pte) @@ -112,8 +112,7 @@ extern pmdval_t early_pmd_flags; #define __pte(x) native_make_pte(x) #define arch_end_context_switch(prev) do {} while(0) - -#endif /* CONFIG_PARAVIRT */ +#endif /* CONFIG_PARAVIRT_XXL */ /* * The following only work if pte_present() is true. @@ -1066,7 +1065,7 @@ static inline void native_set_pte_at(struct mm_struct *mm, unsigned long addr, static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd) { - native_set_pmd(pmdp, pmd); + set_pmd(pmdp, pmd); } static inline void set_pud_at(struct mm_struct *mm, unsigned long addr, diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h index b3ec519e3982..4fe9e7fc74d3 100644 --- a/arch/x86/include/asm/pgtable_32.h +++ b/arch/x86/include/asm/pgtable_32.h @@ -37,7 +37,7 @@ void sync_initial_page_table(void); /* * Define this if things work differently on an i386 and an i486: * it will (on an i486) warn about kernel memory accesses that are - * done without a 'access_ok(VERIFY_WRITE,..)' + * done without a 'access_ok( ..)' */ #undef TEST_ACCESS_OK diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h index 84bd9bdc1987..88bca456da99 100644 --- a/arch/x86/include/asm/pgtable_64_types.h +++ b/arch/x86/include/asm/pgtable_64_types.h @@ -111,6 +111,11 @@ extern unsigned int ptrs_per_p4d; */ #define MAXMEM (1UL << MAX_PHYSMEM_BITS) +#define GUARD_HOLE_PGD_ENTRY -256UL +#define GUARD_HOLE_SIZE (16UL << PGDIR_SHIFT) +#define GUARD_HOLE_BASE_ADDR (GUARD_HOLE_PGD_ENTRY << PGDIR_SHIFT) +#define GUARD_HOLE_END_ADDR (GUARD_HOLE_BASE_ADDR + GUARD_HOLE_SIZE) + #define LDT_PGD_ENTRY -240UL #define LDT_BASE_ADDR (LDT_PGD_ENTRY << PGDIR_SHIFT) #define LDT_END_ADDR (LDT_BASE_ADDR + PGDIR_SIZE) diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 106b7d0e2dae..d6ff0bbdb394 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -564,8 +564,12 @@ extern pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address, unsigned int *level); extern pmd_t *lookup_pmd_address(unsigned long address); extern phys_addr_t slow_virt_to_phys(void *__address); -extern int kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address, - unsigned numpages, unsigned long page_flags); +extern int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, + unsigned long address, + unsigned numpages, + unsigned long page_flags); +extern int __init kernel_unmap_pages_in_pgd(pgd_t *pgd, unsigned long address, + unsigned long numpages); #endif /* !__ASSEMBLY__ */ #endif /* _ASM_X86_PGTABLE_DEFS_H */ diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h index 7f2dbd91fc74..99a7fa9ab0a3 100644 --- a/arch/x86/include/asm/preempt.h +++ b/arch/x86/include/asm/preempt.h @@ -8,6 +8,9 @@ DECLARE_PER_CPU(int, __preempt_count); +/* We use the MSB mostly because its available */ +#define PREEMPT_NEED_RESCHED 0x80000000 + /* * We use the PREEMPT_NEED_RESCHED bit as an inverted NEED_RESCHED such * that a decrement hitting 0 means we can and should reschedule. @@ -88,7 +91,7 @@ static __always_inline void __preempt_count_sub(int val) */ static __always_inline bool __preempt_count_dec_and_test(void) { - GEN_UNARY_RMWcc("decl", __preempt_count, __percpu_arg(0), e); + return GEN_UNARY_RMWcc("decl", __preempt_count, e, __percpu_arg([var])); } /* diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index d53c54b842da..33051436c864 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -42,18 +42,6 @@ struct vm86; #define NET_IP_ALIGN 0 #define HBP_NUM 4 -/* - * Default implementation of macro that returns current - * instruction pointer ("program counter"). - */ -static inline void *current_text_addr(void) -{ - void *pc; - - asm volatile("mov $1f, %0; 1:":"=r" (pc)); - - return pc; -} /* * These alignment constraints are for performance in the vSMP case, @@ -155,7 +143,8 @@ enum cpuid_regs_idx { #define X86_VENDOR_CENTAUR 5 #define X86_VENDOR_TRANSMETA 7 #define X86_VENDOR_NSC 8 -#define X86_VENDOR_NUM 9 +#define X86_VENDOR_HYGON 9 +#define X86_VENDOR_NUM 10 #define X86_VENDOR_UNKNOWN 0xff @@ -315,7 +304,13 @@ struct x86_hw_tss { */ u64 sp1; + /* + * Since Linux does not use ring 2, the 'sp2' slot is unused by + * hardware. entry_SYSCALL_64 uses it as scratch space to stash + * the user RSP value. + */ u64 sp2; + u64 reserved2; u64 ist[7]; u32 reserved3; @@ -578,7 +573,7 @@ static inline bool on_thread_stack(void) current_stack_pointer) < THREAD_SIZE; } -#ifdef CONFIG_PARAVIRT +#ifdef CONFIG_PARAVIRT_XXL #include <asm/paravirt.h> #else #define __cpuid native_cpuid @@ -589,7 +584,7 @@ static inline void load_sp0(unsigned long sp0) } #define set_iopl_mask native_set_iopl_mask -#endif /* CONFIG_PARAVIRT */ +#endif /* CONFIG_PARAVIRT_XXL */ /* Free all resources held by a thread. */ extern void release_thread(struct task_struct *); @@ -972,7 +967,7 @@ static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves) } extern unsigned long arch_align_stack(unsigned long sp); -extern void free_init_pages(char *what, unsigned long begin, unsigned long end); +void free_init_pages(const char *what, unsigned long begin, unsigned long end); extern void free_kernel_image_pages(void *begin, void *end); void default_idle(void); diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 6de1fd3d0097..8a7fc0cca2d1 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -37,8 +37,10 @@ struct pt_regs { unsigned short __esh; unsigned short fs; unsigned short __fsh; + /* On interrupt, gs and __gsh store the vector number. */ unsigned short gs; unsigned short __gsh; + /* On interrupt, this is the error code. */ unsigned long orig_ax; unsigned long ip; unsigned short cs; @@ -144,7 +146,7 @@ static inline int v8086_mode(struct pt_regs *regs) static inline bool user_64bit_mode(struct pt_regs *regs) { #ifdef CONFIG_X86_64 -#ifndef CONFIG_PARAVIRT +#ifndef CONFIG_PARAVIRT_XXL /* * On non-paravirt systems, this is the only long mode CPL 3 * selector. We do not allow long mode selectors in the LDT. @@ -237,23 +239,89 @@ static inline int regs_within_kernel_stack(struct pt_regs *regs, } /** + * regs_get_kernel_stack_nth_addr() - get the address of the Nth entry on stack + * @regs: pt_regs which contains kernel stack pointer. + * @n: stack entry number. + * + * regs_get_kernel_stack_nth() returns the address of the @n th entry of the + * kernel stack which is specified by @regs. If the @n th entry is NOT in + * the kernel stack, this returns NULL. + */ +static inline unsigned long *regs_get_kernel_stack_nth_addr(struct pt_regs *regs, unsigned int n) +{ + unsigned long *addr = (unsigned long *)kernel_stack_pointer(regs); + + addr += n; + if (regs_within_kernel_stack(regs, (unsigned long)addr)) + return addr; + else + return NULL; +} + +/* To avoid include hell, we can't include uaccess.h */ +extern long probe_kernel_read(void *dst, const void *src, size_t size); + +/** * regs_get_kernel_stack_nth() - get Nth entry of the stack * @regs: pt_regs which contains kernel stack pointer. * @n: stack entry number. * * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which - * is specified by @regs. If the @n th entry is NOT in the kernel stack, + * is specified by @regs. If the @n th entry is NOT in the kernel stack * this returns 0. */ static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n) { - unsigned long *addr = (unsigned long *)kernel_stack_pointer(regs); - addr += n; - if (regs_within_kernel_stack(regs, (unsigned long)addr)) - return *addr; - else - return 0; + unsigned long *addr; + unsigned long val; + long ret; + + addr = regs_get_kernel_stack_nth_addr(regs, n); + if (addr) { + ret = probe_kernel_read(&val, addr, sizeof(val)); + if (!ret) + return val; + } + return 0; +} + +/** + * regs_get_kernel_argument() - get Nth function argument in kernel + * @regs: pt_regs of that context + * @n: function argument number (start from 0) + * + * regs_get_argument() returns @n th argument of the function call. + * Note that this chooses most probably assignment, in some case + * it can be incorrect. + * This is expected to be called from kprobes or ftrace with regs + * where the top of stack is the return address. + */ +static inline unsigned long regs_get_kernel_argument(struct pt_regs *regs, + unsigned int n) +{ + static const unsigned int argument_offs[] = { +#ifdef __i386__ + offsetof(struct pt_regs, ax), + offsetof(struct pt_regs, cx), + offsetof(struct pt_regs, dx), +#define NR_REG_ARGUMENTS 3 +#else + offsetof(struct pt_regs, di), + offsetof(struct pt_regs, si), + offsetof(struct pt_regs, dx), + offsetof(struct pt_regs, cx), + offsetof(struct pt_regs, r8), + offsetof(struct pt_regs, r9), +#define NR_REG_ARGUMENTS 6 +#endif + }; + + if (n >= NR_REG_ARGUMENTS) { + n -= NR_REG_ARGUMENTS - 1; + return regs_get_kernel_stack_nth(regs, n); + } else + return regs_get_register(regs, argument_offs[n]); } #define arch_has_single_step() (1) @@ -263,7 +331,7 @@ static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, #define arch_has_block_step() (boot_cpu_data.x86 >= 6) #endif -#define ARCH_HAS_USER_SINGLE_STEP_INFO +#define ARCH_HAS_USER_SINGLE_STEP_REPORT /* * When hitting ptrace_stop(), we cannot return using SYSRET because diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h index 3e70bed8a978..bd5ac6cc37db 100644 --- a/arch/x86/include/asm/qspinlock.h +++ b/arch/x86/include/asm/qspinlock.h @@ -6,9 +6,27 @@ #include <asm/cpufeature.h> #include <asm-generic/qspinlock_types.h> #include <asm/paravirt.h> +#include <asm/rmwcc.h> #define _Q_PENDING_LOOPS (1 << 9) +#define queued_fetch_set_pending_acquire queued_fetch_set_pending_acquire +static __always_inline u32 queued_fetch_set_pending_acquire(struct qspinlock *lock) +{ + u32 val; + + /* + * We can't use GEN_BINARY_RMWcc() inside an if() stmt because asm goto + * and CONFIG_PROFILE_ALL_BRANCHES=y results in a label inside a + * statement expression, which GCC doesn't like. + */ + val = GEN_BINARY_RMWcc(LOCK_PREFIX "btsl", lock->val.counter, c, + "I", _Q_PENDING_OFFSET) * _Q_PENDING_VAL; + val |= atomic_read(&lock->val) & ~_Q_PENDING_MASK; + + return val; +} + #ifdef CONFIG_PARAVIRT_SPINLOCKS extern void native_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val); extern void __pv_init_lock_hash(void); diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h index a671a1145906..04c17be9b5fd 100644 --- a/arch/x86/include/asm/reboot.h +++ b/arch/x86/include/asm/reboot.h @@ -26,6 +26,7 @@ void __noreturn machine_real_restart(unsigned int type); #define MRR_APM 1 typedef void (*nmi_shootdown_cb)(int, struct pt_regs*); +void nmi_panic_self_stop(struct pt_regs *regs); void nmi_shootdown_cpus(nmi_shootdown_cb callback); void run_crash_ipi_callback(struct pt_regs *regs); diff --git a/arch/x86/include/asm/refcount.h b/arch/x86/include/asm/refcount.h index 19b90521954c..dbaed55c1c24 100644 --- a/arch/x86/include/asm/refcount.h +++ b/arch/x86/include/asm/refcount.h @@ -17,7 +17,7 @@ */ #define _REFCOUNT_EXCEPTION \ ".pushsection .text..refcount\n" \ - "111:\tlea %[counter], %%" _ASM_CX "\n" \ + "111:\tlea %[var], %%" _ASM_CX "\n" \ "112:\t" ASM_UD2 "\n" \ ASM_UNREACHABLE \ ".popsection\n" \ @@ -43,7 +43,7 @@ static __always_inline void refcount_add(unsigned int i, refcount_t *r) { asm volatile(LOCK_PREFIX "addl %1,%0\n\t" REFCOUNT_CHECK_LT_ZERO - : [counter] "+m" (r->refs.counter) + : [var] "+m" (r->refs.counter) : "ir" (i) : "cc", "cx"); } @@ -52,7 +52,7 @@ static __always_inline void refcount_inc(refcount_t *r) { asm volatile(LOCK_PREFIX "incl %0\n\t" REFCOUNT_CHECK_LT_ZERO - : [counter] "+m" (r->refs.counter) + : [var] "+m" (r->refs.counter) : : "cc", "cx"); } @@ -60,21 +60,23 @@ static __always_inline void refcount_dec(refcount_t *r) { asm volatile(LOCK_PREFIX "decl %0\n\t" REFCOUNT_CHECK_LE_ZERO - : [counter] "+m" (r->refs.counter) + : [var] "+m" (r->refs.counter) : : "cc", "cx"); } static __always_inline __must_check bool refcount_sub_and_test(unsigned int i, refcount_t *r) { - GEN_BINARY_SUFFIXED_RMWcc(LOCK_PREFIX "subl", REFCOUNT_CHECK_LT_ZERO, - r->refs.counter, "er", i, "%0", e, "cx"); + return GEN_BINARY_SUFFIXED_RMWcc(LOCK_PREFIX "subl", + REFCOUNT_CHECK_LT_ZERO, + r->refs.counter, e, "er", i, "cx"); } static __always_inline __must_check bool refcount_dec_and_test(refcount_t *r) { - GEN_UNARY_SUFFIXED_RMWcc(LOCK_PREFIX "decl", REFCOUNT_CHECK_LT_ZERO, - r->refs.counter, "%0", e, "cx"); + return GEN_UNARY_SUFFIXED_RMWcc(LOCK_PREFIX "decl", + REFCOUNT_CHECK_LT_ZERO, + r->refs.counter, e, "cx"); } static __always_inline __must_check @@ -92,7 +94,7 @@ bool refcount_add_not_zero(unsigned int i, refcount_t *r) /* Did we try to increment from/to an undesirable state? */ if (unlikely(c < 0 || c == INT_MAX || result < c)) { asm volatile(REFCOUNT_ERROR - : : [counter] "m" (r->refs.counter) + : : [var] "m" (r->refs.counter) : "cc", "cx"); break; } diff --git a/arch/x86/include/asm/intel_rdt_sched.h b/arch/x86/include/asm/resctrl_sched.h index 9acb06b6f81e..f6b7fe2833cc 100644 --- a/arch/x86/include/asm/intel_rdt_sched.h +++ b/arch/x86/include/asm/resctrl_sched.h @@ -1,8 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_X86_INTEL_RDT_SCHED_H -#define _ASM_X86_INTEL_RDT_SCHED_H +#ifndef _ASM_X86_RESCTRL_SCHED_H +#define _ASM_X86_RESCTRL_SCHED_H -#ifdef CONFIG_INTEL_RDT +#ifdef CONFIG_X86_CPU_RESCTRL #include <linux/sched.h> #include <linux/jump_label.h> @@ -10,7 +10,7 @@ #define IA32_PQR_ASSOC 0x0c8f /** - * struct intel_pqr_state - State cache for the PQR MSR + * struct resctrl_pqr_state - State cache for the PQR MSR * @cur_rmid: The cached Resource Monitoring ID * @cur_closid: The cached Class Of Service ID * @default_rmid: The user assigned Resource Monitoring ID @@ -24,21 +24,21 @@ * The cache also helps to avoid pointless updates if the value does * not change. */ -struct intel_pqr_state { +struct resctrl_pqr_state { u32 cur_rmid; u32 cur_closid; u32 default_rmid; u32 default_closid; }; -DECLARE_PER_CPU(struct intel_pqr_state, pqr_state); +DECLARE_PER_CPU(struct resctrl_pqr_state, pqr_state); DECLARE_STATIC_KEY_FALSE(rdt_enable_key); DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key); DECLARE_STATIC_KEY_FALSE(rdt_mon_enable_key); /* - * __intel_rdt_sched_in() - Writes the task's CLOSid/RMID to IA32_PQR_MSR + * __resctrl_sched_in() - Writes the task's CLOSid/RMID to IA32_PQR_MSR * * Following considerations are made so that this has minimal impact * on scheduler hot path: @@ -51,9 +51,9 @@ DECLARE_STATIC_KEY_FALSE(rdt_mon_enable_key); * simple as possible. * Must be called with preemption disabled. */ -static void __intel_rdt_sched_in(void) +static void __resctrl_sched_in(void) { - struct intel_pqr_state *state = this_cpu_ptr(&pqr_state); + struct resctrl_pqr_state *state = this_cpu_ptr(&pqr_state); u32 closid = state->default_closid; u32 rmid = state->default_rmid; @@ -78,16 +78,16 @@ static void __intel_rdt_sched_in(void) } } -static inline void intel_rdt_sched_in(void) +static inline void resctrl_sched_in(void) { if (static_branch_likely(&rdt_enable_key)) - __intel_rdt_sched_in(); + __resctrl_sched_in(); } #else -static inline void intel_rdt_sched_in(void) {} +static inline void resctrl_sched_in(void) {} -#endif /* CONFIG_INTEL_RDT */ +#endif /* CONFIG_X86_CPU_RESCTRL */ -#endif /* _ASM_X86_INTEL_RDT_SCHED_H */ +#endif /* _ASM_X86_RESCTRL_SCHED_H */ diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h index 4914a3e7c803..8a9eba191516 100644 --- a/arch/x86/include/asm/rmwcc.h +++ b/arch/x86/include/asm/rmwcc.h @@ -2,56 +2,69 @@ #ifndef _ASM_X86_RMWcc #define _ASM_X86_RMWcc +/* This counts to 12. Any more, it will return 13th argument. */ +#define __RMWcc_ARGS(_0, _1, _2, _3, _4, _5, _6, _7, _8, _9, _10, _11, _12, _n, X...) _n +#define RMWcc_ARGS(X...) __RMWcc_ARGS(, ##X, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0) + +#define __RMWcc_CONCAT(a, b) a ## b +#define RMWcc_CONCAT(a, b) __RMWcc_CONCAT(a, b) + #define __CLOBBERS_MEM(clb...) "memory", ## clb -#if !defined(__GCC_ASM_FLAG_OUTPUTS__) && defined(CC_HAVE_ASM_GOTO) +#if !defined(__GCC_ASM_FLAG_OUTPUTS__) && defined(CONFIG_CC_HAS_ASM_GOTO) /* Use asm goto */ -#define __GEN_RMWcc(fullop, var, cc, clobbers, ...) \ -do { \ +#define __GEN_RMWcc(fullop, _var, cc, clobbers, ...) \ +({ \ + bool c = false; \ asm_volatile_goto (fullop "; j" #cc " %l[cc_label]" \ - : : [counter] "m" (var), ## __VA_ARGS__ \ + : : [var] "m" (_var), ## __VA_ARGS__ \ : clobbers : cc_label); \ - return 0; \ -cc_label: \ - return 1; \ -} while (0) - -#define __BINARY_RMWcc_ARG " %1, " + if (0) { \ +cc_label: c = true; \ + } \ + c; \ +}) - -#else /* defined(__GCC_ASM_FLAG_OUTPUTS__) || !defined(CC_HAVE_ASM_GOTO) */ +#else /* defined(__GCC_ASM_FLAG_OUTPUTS__) || !defined(CONFIG_CC_HAS_ASM_GOTO) */ /* Use flags output or a set instruction */ -#define __GEN_RMWcc(fullop, var, cc, clobbers, ...) \ -do { \ +#define __GEN_RMWcc(fullop, _var, cc, clobbers, ...) \ +({ \ bool c; \ asm volatile (fullop CC_SET(cc) \ - : [counter] "+m" (var), CC_OUT(cc) (c) \ + : [var] "+m" (_var), CC_OUT(cc) (c) \ : __VA_ARGS__ : clobbers); \ - return c; \ -} while (0) - -#define __BINARY_RMWcc_ARG " %2, " + c; \ +}) -#endif /* defined(__GCC_ASM_FLAG_OUTPUTS__) || !defined(CC_HAVE_ASM_GOTO) */ +#endif /* defined(__GCC_ASM_FLAG_OUTPUTS__) || !defined(CONFIG_CC_HAS_ASM_GOTO) */ -#define GEN_UNARY_RMWcc(op, var, arg0, cc) \ +#define GEN_UNARY_RMWcc_4(op, var, cc, arg0) \ __GEN_RMWcc(op " " arg0, var, cc, __CLOBBERS_MEM()) -#define GEN_UNARY_SUFFIXED_RMWcc(op, suffix, var, arg0, cc, clobbers...)\ - __GEN_RMWcc(op " " arg0 "\n\t" suffix, var, cc, \ - __CLOBBERS_MEM(clobbers)) +#define GEN_UNARY_RMWcc_3(op, var, cc) \ + GEN_UNARY_RMWcc_4(op, var, cc, "%[var]") -#define GEN_BINARY_RMWcc(op, var, vcon, val, arg0, cc) \ - __GEN_RMWcc(op __BINARY_RMWcc_ARG arg0, var, cc, \ - __CLOBBERS_MEM(), vcon (val)) +#define GEN_UNARY_RMWcc(X...) RMWcc_CONCAT(GEN_UNARY_RMWcc_, RMWcc_ARGS(X))(X) + +#define GEN_BINARY_RMWcc_6(op, var, cc, vcon, _val, arg0) \ + __GEN_RMWcc(op " %[val], " arg0, var, cc, \ + __CLOBBERS_MEM(), [val] vcon (_val)) + +#define GEN_BINARY_RMWcc_5(op, var, cc, vcon, val) \ + GEN_BINARY_RMWcc_6(op, var, cc, vcon, val, "%[var]") + +#define GEN_BINARY_RMWcc(X...) RMWcc_CONCAT(GEN_BINARY_RMWcc_, RMWcc_ARGS(X))(X) + +#define GEN_UNARY_SUFFIXED_RMWcc(op, suffix, var, cc, clobbers...) \ + __GEN_RMWcc(op " %[var]\n\t" suffix, var, cc, \ + __CLOBBERS_MEM(clobbers)) -#define GEN_BINARY_SUFFIXED_RMWcc(op, suffix, var, vcon, val, arg0, cc, \ - clobbers...) \ - __GEN_RMWcc(op __BINARY_RMWcc_ARG arg0 "\n\t" suffix, var, cc, \ - __CLOBBERS_MEM(clobbers), vcon (val)) +#define GEN_BINARY_SUFFIXED_RMWcc(op, suffix, var, cc, vcon, _val, clobbers...)\ + __GEN_RMWcc(op " %[val], %[var]\n\t" suffix, var, cc, \ + __CLOBBERS_MEM(clobbers), [val] vcon (_val)) #endif /* _ASM_X86_RMWcc */ diff --git a/arch/x86/include/asm/sections.h b/arch/x86/include/asm/sections.h index 4a911a382ade..8ea1cfdbeabc 100644 --- a/arch/x86/include/asm/sections.h +++ b/arch/x86/include/asm/sections.h @@ -11,7 +11,6 @@ extern char __end_rodata_aligned[]; #if defined(CONFIG_X86_64) extern char __end_rodata_hpage_align[]; -extern char __entry_trampoline_start[], __entry_trampoline_end[]; #endif #endif /* _ASM_X86_SECTIONS_H */ diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h index e293c122d0d5..ac3892920419 100644 --- a/arch/x86/include/asm/segment.h +++ b/arch/x86/include/asm/segment.h @@ -186,8 +186,7 @@ #define GDT_ENTRY_TLS_MIN 12 #define GDT_ENTRY_TLS_MAX 14 -/* Abused to load per CPU data from limit */ -#define GDT_ENTRY_PER_CPU 15 +#define GDT_ENTRY_CPUNODE 15 /* * Number of entries in the GDT table: @@ -207,11 +206,11 @@ #define __USER_DS (GDT_ENTRY_DEFAULT_USER_DS*8 + 3) #define __USER32_DS __USER_DS #define __USER_CS (GDT_ENTRY_DEFAULT_USER_CS*8 + 3) -#define __PER_CPU_SEG (GDT_ENTRY_PER_CPU*8 + 3) +#define __CPUNODE_SEG (GDT_ENTRY_CPUNODE*8 + 3) #endif -#ifndef CONFIG_PARAVIRT +#ifndef CONFIG_PARAVIRT_XXL # define get_kernel_rpl() 0 #endif @@ -225,6 +224,47 @@ #define GDT_ENTRY_TLS_ENTRIES 3 #define TLS_SIZE (GDT_ENTRY_TLS_ENTRIES* 8) +#ifdef CONFIG_X86_64 + +/* Bit size and mask of CPU number stored in the per CPU data (and TSC_AUX) */ +#define VDSO_CPUNODE_BITS 12 +#define VDSO_CPUNODE_MASK 0xfff + +#ifndef __ASSEMBLY__ + +/* Helper functions to store/load CPU and node numbers */ + +static inline unsigned long vdso_encode_cpunode(int cpu, unsigned long node) +{ + return (node << VDSO_CPUNODE_BITS) | cpu; +} + +static inline void vdso_read_cpunode(unsigned *cpu, unsigned *node) +{ + unsigned int p; + + /* + * Load CPU and node number from the GDT. LSL is faster than RDTSCP + * and works on all CPUs. This is volatile so that it orders + * correctly with respect to barrier() and to keep GCC from cleverly + * hoisting it out of the calling function. + * + * If RDPID is available, use it. + */ + alternative_io ("lsl %[seg],%[p]", + ".byte 0xf3,0x0f,0xc7,0xf8", /* RDPID %eax/rax */ + X86_FEATURE_RDPID, + [p] "=a" (p), [seg] "r" (__CPUNODE_SEG)); + + if (cpu) + *cpu = (p & VDSO_CPUNODE_MASK); + if (node) + *node = (p >> VDSO_CPUNODE_BITS); +} + +#endif /* !__ASSEMBLY__ */ +#endif /* CONFIG_X86_64 */ + #ifdef __KERNEL__ /* diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index ae13bc974416..ed8ec011a9fd 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -46,6 +46,9 @@ extern unsigned long saved_video_mode; extern void reserve_standard_io_resources(void); extern void i386_reserve_resources(void); +extern unsigned long __startup_64(unsigned long physaddr, struct boot_params *bp); +extern unsigned long __startup_secondary_64(void); +extern int early_make_pgtable(unsigned long address); #ifdef CONFIG_X86_INTEL_MID extern void x86_intel_mid_early_setup(void); diff --git a/arch/x86/include/asm/sighandling.h b/arch/x86/include/asm/sighandling.h index bd26834724e5..2fcbd6f33ef7 100644 --- a/arch/x86/include/asm/sighandling.h +++ b/arch/x86/include/asm/sighandling.h @@ -17,4 +17,9 @@ void signal_fault(struct pt_regs *regs, void __user *frame, char *where); int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate, struct pt_regs *regs, unsigned long mask); + +#ifdef CONFIG_X86_X32_ABI +asmlinkage long sys32_x32_rt_sigreturn(void); +#endif + #endif /* _ASM_X86_SIGHANDLING_H */ diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 547c4fe50711..2e95b6c1bca3 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -148,6 +148,12 @@ void x86_idle_thread_init(unsigned int cpu, struct task_struct *idle); void smp_store_boot_cpu_info(void); void smp_store_cpu_info(int id); + +asmlinkage __visible void smp_reboot_interrupt(void); +__visible void smp_reschedule_interrupt(struct pt_regs *regs); +__visible void smp_call_function_interrupt(struct pt_regs *regs); +__visible void smp_call_function_single_interrupt(struct pt_regs *r); + #define cpu_physical_id(cpu) per_cpu(x86_cpu_to_apicid, cpu) #define cpu_acpi_id(cpu) per_cpu(x86_cpu_to_acpiid, cpu) diff --git a/arch/x86/include/asm/spec-ctrl.h b/arch/x86/include/asm/spec-ctrl.h index ae7c2c5cd7f0..5393babc0598 100644 --- a/arch/x86/include/asm/spec-ctrl.h +++ b/arch/x86/include/asm/spec-ctrl.h @@ -53,12 +53,24 @@ static inline u64 ssbd_tif_to_spec_ctrl(u64 tifn) return (tifn & _TIF_SSBD) >> (TIF_SSBD - SPEC_CTRL_SSBD_SHIFT); } +static inline u64 stibp_tif_to_spec_ctrl(u64 tifn) +{ + BUILD_BUG_ON(TIF_SPEC_IB < SPEC_CTRL_STIBP_SHIFT); + return (tifn & _TIF_SPEC_IB) >> (TIF_SPEC_IB - SPEC_CTRL_STIBP_SHIFT); +} + static inline unsigned long ssbd_spec_ctrl_to_tif(u64 spec_ctrl) { BUILD_BUG_ON(TIF_SSBD < SPEC_CTRL_SSBD_SHIFT); return (spec_ctrl & SPEC_CTRL_SSBD) << (TIF_SSBD - SPEC_CTRL_SSBD_SHIFT); } +static inline unsigned long stibp_spec_ctrl_to_tif(u64 spec_ctrl) +{ + BUILD_BUG_ON(TIF_SPEC_IB < SPEC_CTRL_STIBP_SHIFT); + return (spec_ctrl & SPEC_CTRL_STIBP) << (TIF_SPEC_IB - SPEC_CTRL_STIBP_SHIFT); +} + static inline u64 ssbd_tif_to_amd_ls_cfg(u64 tifn) { return (tifn & _TIF_SSBD) ? x86_amd_ls_cfg_ssbd_mask : 0ULL; @@ -70,11 +82,7 @@ extern void speculative_store_bypass_ht_init(void); static inline void speculative_store_bypass_ht_init(void) { } #endif -extern void speculative_store_bypass_update(unsigned long tif); - -static inline void speculative_store_bypass_update_current(void) -{ - speculative_store_bypass_update(current_thread_info()->flags); -} +extern void speculation_ctrl_update(unsigned long tif); +extern void speculation_ctrl_update_current(void); #endif diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h index 317fc59b512c..43c029cdc3fe 100644 --- a/arch/x86/include/asm/special_insns.h +++ b/arch/x86/include/asm/special_insns.h @@ -141,7 +141,7 @@ static inline unsigned long __read_cr4(void) return native_read_cr4(); } -#ifdef CONFIG_PARAVIRT +#ifdef CONFIG_PARAVIRT_XXL #include <asm/paravirt.h> #else @@ -208,7 +208,7 @@ static inline void load_gs_index(unsigned selector) #endif -#endif/* CONFIG_PARAVIRT */ +#endif /* CONFIG_PARAVIRT_XXL */ static inline void clflush(volatile void *__p) { diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h index d33f92b9fa22..4e4194e21a09 100644 --- a/arch/x86/include/asm/string_64.h +++ b/arch/x86/include/asm/string_64.h @@ -7,24 +7,6 @@ /* Written 2002 by Andi Kleen */ -/* Only used for special circumstances. Stolen from i386/string.h */ -static __always_inline void *__inline_memcpy(void *to, const void *from, size_t n) -{ - unsigned long d0, d1, d2; - asm volatile("rep ; movsl\n\t" - "testb $2,%b4\n\t" - "je 1f\n\t" - "movsw\n" - "1:\ttestb $1,%b4\n\t" - "je 2f\n\t" - "movsb\n" - "2:" - : "=&c" (d0), "=&D" (d1), "=&S" (d2) - : "0" (n / 4), "q" (n), "1" ((long)to), "2" ((long)from) - : "memory"); - return to; -} - /* Even with __builtin_ the compiler may decide to use the out of line function. */ @@ -149,7 +131,25 @@ memcpy_mcsafe(void *dst, const void *src, size_t cnt) #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE #define __HAVE_ARCH_MEMCPY_FLUSHCACHE 1 -void memcpy_flushcache(void *dst, const void *src, size_t cnt); +void __memcpy_flushcache(void *dst, const void *src, size_t cnt); +static __always_inline void memcpy_flushcache(void *dst, const void *src, size_t cnt) +{ + if (__builtin_constant_p(cnt)) { + switch (cnt) { + case 4: + asm ("movntil %1, %0" : "=m"(*(u32 *)dst) : "r"(*(u32 *)src)); + return; + case 8: + asm ("movntiq %1, %0" : "=m"(*(u64 *)dst) : "r"(*(u64 *)src)); + return; + case 16: + asm ("movntiq %1, %0" : "=m"(*(u64 *)dst) : "r"(*(u64 *)src)); + asm ("movntiq %1, %0" : "=m"(*(u64 *)(dst + 8)) : "r"(*(u64 *)(src + 8))); + return; + } + } + __memcpy_flushcache(dst, src, cnt); +} #endif #endif /* __KERNEL__ */ diff --git a/arch/x86/include/asm/suspend.h b/arch/x86/include/asm/suspend.h index ecffe81ff65c..a892494ca5e4 100644 --- a/arch/x86/include/asm/suspend.h +++ b/arch/x86/include/asm/suspend.h @@ -4,3 +4,11 @@ #else # include <asm/suspend_64.h> #endif +extern unsigned long restore_jump_address __visible; +extern unsigned long jump_address_phys; +extern unsigned long restore_cr3 __visible; +extern unsigned long temp_pgt __visible; +extern unsigned long relocated_restore_code __visible; +extern int relocate_restore_code(void); +/* Defined in hibernate_asm_32/64.S */ +extern asmlinkage __visible int restore_image(void); diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h index 8be6afb58471..fdbd9d7b7bca 100644 --- a/arch/x86/include/asm/suspend_32.h +++ b/arch/x86/include/asm/suspend_32.h @@ -32,4 +32,8 @@ struct saved_context { unsigned long return_address; } __attribute__((packed)); +/* routines for saving/restoring kernel state */ +extern char core_restore_code[]; +extern char restore_registers[]; + #endif /* _ASM_X86_SUSPEND_32_H */ diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index 93b462e48067..dec9c1e84c78 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -290,11 +290,4 @@ struct __attribute__ ((__packed__)) vmcb { #define SVM_CR0_SELECTIVE_MASK (X86_CR0_TS | X86_CR0_MP) -#define SVM_VMLOAD ".byte 0x0f, 0x01, 0xda" -#define SVM_VMRUN ".byte 0x0f, 0x01, 0xd8" -#define SVM_VMSAVE ".byte 0x0f, 0x01, 0xdb" -#define SVM_CLGI ".byte 0x0f, 0x01, 0xdd" -#define SVM_STGI ".byte 0x0f, 0x01, 0xdc" -#define SVM_INVLPGA ".byte 0x0f, 0x01, 0xdf" - #endif diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h index 36bd243843d6..7cf1a270d891 100644 --- a/arch/x86/include/asm/switch_to.h +++ b/arch/x86/include/asm/switch_to.h @@ -11,9 +11,6 @@ struct task_struct *__switch_to_asm(struct task_struct *prev, __visible struct task_struct *__switch_to(struct task_struct *prev, struct task_struct *next); -struct tss_struct; -void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, - struct tss_struct *tss); /* This runs runs on the previous thread's stack. */ static inline void prepare_switch_to(struct task_struct *next) diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 2ff2a30a264f..e0eccbcb8447 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -79,10 +79,12 @@ struct thread_info { #define TIF_SIGPENDING 2 /* signal pending */ #define TIF_NEED_RESCHED 3 /* rescheduling necessary */ #define TIF_SINGLESTEP 4 /* reenable singlestep on user return*/ -#define TIF_SSBD 5 /* Reduced data speculation */ +#define TIF_SSBD 5 /* Speculative store bypass disable */ #define TIF_SYSCALL_EMU 6 /* syscall emulation active */ #define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */ #define TIF_SECCOMP 8 /* secure computing */ +#define TIF_SPEC_IB 9 /* Indirect branch speculation mitigation */ +#define TIF_SPEC_FORCE_UPDATE 10 /* Force speculation MSR update in context switch */ #define TIF_USER_RETURN_NOTIFY 11 /* notify kernel of userspace return */ #define TIF_UPROBE 12 /* breakpointed or singlestepping */ #define TIF_PATCH_PENDING 13 /* pending live patching update */ @@ -110,6 +112,8 @@ struct thread_info { #define _TIF_SYSCALL_EMU (1 << TIF_SYSCALL_EMU) #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) #define _TIF_SECCOMP (1 << TIF_SECCOMP) +#define _TIF_SPEC_IB (1 << TIF_SPEC_IB) +#define _TIF_SPEC_FORCE_UPDATE (1 << TIF_SPEC_FORCE_UPDATE) #define _TIF_USER_RETURN_NOTIFY (1 << TIF_USER_RETURN_NOTIFY) #define _TIF_UPROBE (1 << TIF_UPROBE) #define _TIF_PATCH_PENDING (1 << TIF_PATCH_PENDING) @@ -136,17 +140,19 @@ struct thread_info { _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT | \ _TIF_NOHZ) -/* work to do on any return to user space */ -#define _TIF_ALLWORK_MASK \ - (_TIF_SYSCALL_TRACE | _TIF_NOTIFY_RESUME | _TIF_SIGPENDING | \ - _TIF_NEED_RESCHED | _TIF_SINGLESTEP | _TIF_SYSCALL_EMU | \ - _TIF_SYSCALL_AUDIT | _TIF_USER_RETURN_NOTIFY | _TIF_UPROBE | \ - _TIF_PATCH_PENDING | _TIF_NOHZ | _TIF_SYSCALL_TRACEPOINT | \ - _TIF_FSCHECK) - /* flags to check in __switch_to() */ -#define _TIF_WORK_CTXSW \ - (_TIF_IO_BITMAP|_TIF_NOCPUID|_TIF_NOTSC|_TIF_BLOCKSTEP|_TIF_SSBD) +#define _TIF_WORK_CTXSW_BASE \ + (_TIF_IO_BITMAP|_TIF_NOCPUID|_TIF_NOTSC|_TIF_BLOCKSTEP| \ + _TIF_SSBD | _TIF_SPEC_FORCE_UPDATE) + +/* + * Avoid calls to __switch_to_xtra() on UP as STIBP is not evaluated. + */ +#ifdef CONFIG_SMP +# define _TIF_WORK_CTXSW (_TIF_WORK_CTXSW_BASE | _TIF_SPEC_IB) +#else +# define _TIF_WORK_CTXSW (_TIF_WORK_CTXSW_BASE) +#endif #define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY) #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW) diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h index cb0a1f470980..404b8b1d44f5 100644 --- a/arch/x86/include/asm/tlb.h +++ b/arch/x86/include/asm/tlb.h @@ -6,16 +6,23 @@ #define tlb_end_vma(tlb, vma) do { } while (0) #define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0) -#define tlb_flush(tlb) \ -{ \ - if (!tlb->fullmm && !tlb->need_flush_all) \ - flush_tlb_mm_range(tlb->mm, tlb->start, tlb->end, 0UL); \ - else \ - flush_tlb_mm_range(tlb->mm, 0UL, TLB_FLUSH_ALL, 0UL); \ -} +static inline void tlb_flush(struct mmu_gather *tlb); #include <asm-generic/tlb.h> +static inline void tlb_flush(struct mmu_gather *tlb) +{ + unsigned long start = 0UL, end = TLB_FLUSH_ALL; + unsigned int stride_shift = tlb_get_unmap_shift(tlb); + + if (!tlb->fullmm && !tlb->need_flush_all) { + start = tlb->start; + end = tlb->end; + } + + flush_tlb_mm_range(tlb->mm, start, end, stride_shift, tlb->freed_tables); +} + /* * While x86 architecture in general requires an IPI to perform TLB * shootdown, enablement code for several hypervisors overrides diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 0e2130d8d6b1..f4204bf377fc 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -148,22 +148,6 @@ static inline unsigned long build_cr3_noflush(pgd_t *pgd, u16 asid) #define __flush_tlb_one_user(addr) __native_flush_tlb_one_user(addr) #endif -static inline bool tlb_defer_switch_to_init_mm(void) -{ - /* - * If we have PCID, then switching to init_mm is reasonably - * fast. If we don't have PCID, then switching to init_mm is - * quite slow, so we try to defer it in the hopes that we can - * avoid it entirely. The latter approach runs the risk of - * receiving otherwise unnecessary IPIs. - * - * This choice is just a heuristic. The tlb code can handle this - * function returning true or false regardless of whether we have - * PCID. - */ - return !static_cpu_has(X86_FEATURE_PCID); -} - struct tlb_context { u64 ctx_id; u64 tlb_gen; @@ -185,10 +169,14 @@ struct tlb_state { #define LOADED_MM_SWITCHING ((struct mm_struct *)1) + /* Last user mm for optimizing IBPB */ + union { + struct mm_struct *last_user_mm; + unsigned long last_user_mm_ibpb; + }; + u16 loaded_mm_asid; u16 next_asid; - /* last user mm's ctx id */ - u64 last_ctx_id; /* * We can be in one of several states: @@ -553,23 +541,30 @@ struct flush_tlb_info { unsigned long start; unsigned long end; u64 new_tlb_gen; + unsigned int stride_shift; + bool freed_tables; }; #define local_flush_tlb() __flush_tlb() -#define flush_tlb_mm(mm) flush_tlb_mm_range(mm, 0UL, TLB_FLUSH_ALL, 0UL) +#define flush_tlb_mm(mm) \ + flush_tlb_mm_range(mm, 0UL, TLB_FLUSH_ALL, 0UL, true) -#define flush_tlb_range(vma, start, end) \ - flush_tlb_mm_range(vma->vm_mm, start, end, vma->vm_flags) +#define flush_tlb_range(vma, start, end) \ + flush_tlb_mm_range((vma)->vm_mm, start, end, \ + ((vma)->vm_flags & VM_HUGETLB) \ + ? huge_page_shift(hstate_vma(vma)) \ + : PAGE_SHIFT, false) extern void flush_tlb_all(void); extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, - unsigned long end, unsigned long vmflag); + unsigned long end, unsigned int stride_shift, + bool freed_tables); extern void flush_tlb_kernel_range(unsigned long start, unsigned long end); static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long a) { - flush_tlb_mm_range(vma->vm_mm, a, a + PAGE_SIZE, VM_NONE); + flush_tlb_mm_range(vma->vm_mm, a, a + PAGE_SIZE, PAGE_SHIFT, false); } void native_flush_tlb_others(const struct cpumask *cpumask, diff --git a/arch/x86/include/asm/trace/exceptions.h b/arch/x86/include/asm/trace/exceptions.h index 69615e387973..e0e6d7f21399 100644 --- a/arch/x86/include/asm/trace/exceptions.h +++ b/arch/x86/include/asm/trace/exceptions.h @@ -45,6 +45,7 @@ DEFINE_PAGE_FAULT_EVENT(page_fault_user); DEFINE_PAGE_FAULT_EVENT(page_fault_kernel); #undef TRACE_INCLUDE_PATH +#undef TRACE_INCLUDE_FILE #define TRACE_INCLUDE_PATH . #define TRACE_INCLUDE_FILE exceptions #endif /* _TRACE_PAGE_FAULT_H */ diff --git a/arch/x86/include/asm/trace/hyperv.h b/arch/x86/include/asm/trace/hyperv.h index 2e6245a023ef..ace464f09681 100644 --- a/arch/x86/include/asm/trace/hyperv.h +++ b/arch/x86/include/asm/trace/hyperv.h @@ -42,6 +42,20 @@ TRACE_EVENT(hyperv_nested_flush_guest_mapping, TP_printk("address space %llx ret %d", __entry->as, __entry->ret) ); +TRACE_EVENT(hyperv_nested_flush_guest_mapping_range, + TP_PROTO(u64 as, int ret), + TP_ARGS(as, ret), + + TP_STRUCT__entry( + __field(u64, as) + __field(int, ret) + ), + TP_fast_assign(__entry->as = as; + __entry->ret = ret; + ), + TP_printk("address space %llx ret %d", __entry->as, __entry->ret) + ); + TRACE_EVENT(hyperv_send_ipi_mask, TP_PROTO(const struct cpumask *cpus, int vector), diff --git a/arch/x86/include/asm/trace/irq_vectors.h b/arch/x86/include/asm/trace/irq_vectors.h index 0af81b590a0c..33b9d0f0aafe 100644 --- a/arch/x86/include/asm/trace/irq_vectors.h +++ b/arch/x86/include/asm/trace/irq_vectors.h @@ -389,6 +389,7 @@ TRACE_EVENT(vector_free_moved, #endif /* CONFIG_X86_LOCAL_APIC */ #undef TRACE_INCLUDE_PATH +#undef TRACE_INCLUDE_FILE #define TRACE_INCLUDE_PATH . #define TRACE_INCLUDE_FILE irq_vectors #endif /* _TRACE_IRQ_VECTORS_H */ diff --git a/arch/x86/include/asm/trace/mpx.h b/arch/x86/include/asm/trace/mpx.h index 7bd92db09e8d..54133017267c 100644 --- a/arch/x86/include/asm/trace/mpx.h +++ b/arch/x86/include/asm/trace/mpx.h @@ -11,12 +11,12 @@ TRACE_EVENT(mpx_bounds_register_exception, - TP_PROTO(void *addr_referenced, + TP_PROTO(void __user *addr_referenced, const struct mpx_bndreg *bndreg), TP_ARGS(addr_referenced, bndreg), TP_STRUCT__entry( - __field(void *, addr_referenced) + __field(void __user *, addr_referenced) __field(u64, lower_bound) __field(u64, upper_bound) ), diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 3de69330e6c5..7d6f3f3fad78 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -61,34 +61,38 @@ asmlinkage void xen_machine_check(void); asmlinkage void xen_simd_coprocessor_error(void); #endif -dotraplinkage void do_divide_error(struct pt_regs *, long); -dotraplinkage void do_debug(struct pt_regs *, long); -dotraplinkage void do_nmi(struct pt_regs *, long); -dotraplinkage void do_int3(struct pt_regs *, long); -dotraplinkage void do_overflow(struct pt_regs *, long); -dotraplinkage void do_bounds(struct pt_regs *, long); -dotraplinkage void do_invalid_op(struct pt_regs *, long); -dotraplinkage void do_device_not_available(struct pt_regs *, long); -dotraplinkage void do_coprocessor_segment_overrun(struct pt_regs *, long); -dotraplinkage void do_invalid_TSS(struct pt_regs *, long); -dotraplinkage void do_segment_not_present(struct pt_regs *, long); -dotraplinkage void do_stack_segment(struct pt_regs *, long); +dotraplinkage void do_divide_error(struct pt_regs *regs, long error_code); +dotraplinkage void do_debug(struct pt_regs *regs, long error_code); +dotraplinkage void do_nmi(struct pt_regs *regs, long error_code); +dotraplinkage void do_int3(struct pt_regs *regs, long error_code); +dotraplinkage void do_overflow(struct pt_regs *regs, long error_code); +dotraplinkage void do_bounds(struct pt_regs *regs, long error_code); +dotraplinkage void do_invalid_op(struct pt_regs *regs, long error_code); +dotraplinkage void do_device_not_available(struct pt_regs *regs, long error_code); +dotraplinkage void do_coprocessor_segment_overrun(struct pt_regs *regs, long error_code); +dotraplinkage void do_invalid_TSS(struct pt_regs *regs, long error_code); +dotraplinkage void do_segment_not_present(struct pt_regs *regs, long error_code); +dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code); #ifdef CONFIG_X86_64 -dotraplinkage void do_double_fault(struct pt_regs *, long); +dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code); +asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs); +asmlinkage __visible notrace +struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s); +void __init trap_init(void); #endif -dotraplinkage void do_general_protection(struct pt_regs *, long); -dotraplinkage void do_page_fault(struct pt_regs *, unsigned long); -dotraplinkage void do_spurious_interrupt_bug(struct pt_regs *, long); -dotraplinkage void do_coprocessor_error(struct pt_regs *, long); -dotraplinkage void do_alignment_check(struct pt_regs *, long); +dotraplinkage void do_general_protection(struct pt_regs *regs, long error_code); +dotraplinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code); +dotraplinkage void do_spurious_interrupt_bug(struct pt_regs *regs, long error_code); +dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code); +dotraplinkage void do_alignment_check(struct pt_regs *regs, long error_code); #ifdef CONFIG_X86_MCE -dotraplinkage void do_machine_check(struct pt_regs *, long); +dotraplinkage void do_machine_check(struct pt_regs *regs, long error_code); #endif -dotraplinkage void do_simd_coprocessor_error(struct pt_regs *, long); +dotraplinkage void do_simd_coprocessor_error(struct pt_regs *regs, long error_code); #ifdef CONFIG_X86_32 -dotraplinkage void do_iret_error(struct pt_regs *, long); +dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code); #endif -dotraplinkage void do_mce(struct pt_regs *, long); +dotraplinkage void do_mce(struct pt_regs *regs, long error_code); static inline int get_si_code(unsigned long condition) { @@ -104,11 +108,16 @@ extern int panic_on_unrecovered_nmi; void math_emulate(struct math_emu_info *); #ifndef CONFIG_X86_32 -asmlinkage void smp_thermal_interrupt(void); -asmlinkage void smp_threshold_interrupt(void); -asmlinkage void smp_deferred_error_interrupt(void); +asmlinkage void smp_thermal_interrupt(struct pt_regs *regs); +asmlinkage void smp_threshold_interrupt(struct pt_regs *regs); +asmlinkage void smp_deferred_error_interrupt(struct pt_regs *regs); #endif +void smp_apic_timer_interrupt(struct pt_regs *regs); +void smp_spurious_interrupt(struct pt_regs *regs); +void smp_error_interrupt(struct pt_regs *regs); +asmlinkage void smp_irq_move_cleanup_interrupt(void); + extern void ist_enter(struct pt_regs *regs); extern void ist_exit(struct pt_regs *regs); extern void ist_begin_non_atomic(struct pt_regs *regs); diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h index eb5bbfeccb66..8a0c25c6bf09 100644 --- a/arch/x86/include/asm/tsc.h +++ b/arch/x86/include/asm/tsc.h @@ -35,6 +35,7 @@ extern struct system_counterval_t convert_art_ns_to_tsc(u64 art_ns); extern void tsc_early_init(void); extern void tsc_init(void); +extern unsigned long calibrate_delay_is_known(void); extern void mark_tsc_unstable(char *reason); extern int unsynchronized_tsc(void); extern int check_tsc_unstable(void); diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index aae77eb8491c..c1334aaaa78d 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -77,9 +77,6 @@ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, un /** * access_ok: - Checks if a user space pointer is valid - * @type: Type of access: %VERIFY_READ or %VERIFY_WRITE. Note that - * %VERIFY_WRITE is a superset of %VERIFY_READ - if it is safe - * to write to a block, it is always safe to read from it. * @addr: User space pointer to start of block to check * @size: Size of block to check * @@ -95,7 +92,7 @@ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, un * checks that the pointer is in the user space range - after calling * this function, memory access functions may still return -EFAULT. */ -#define access_ok(type, addr, size) \ +#define access_ok(addr, size) \ ({ \ WARN_ON_IN_IRQ(); \ likely(!__range_not_ok(addr, size, user_addr_max())); \ @@ -189,19 +186,14 @@ __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL)) #ifdef CONFIG_X86_32 -#define __put_user_asm_u64(x, addr, err, errret) \ - asm volatile("\n" \ - "1: movl %%eax,0(%2)\n" \ - "2: movl %%edx,4(%2)\n" \ - "3:" \ - ".section .fixup,\"ax\"\n" \ - "4: movl %3,%0\n" \ - " jmp 3b\n" \ - ".previous\n" \ - _ASM_EXTABLE(1b, 4b) \ - _ASM_EXTABLE(2b, 4b) \ - : "=r" (err) \ - : "A" (x), "r" (addr), "i" (errret), "0" (err)) +#define __put_user_goto_u64(x, addr, label) \ + asm_volatile_goto("\n" \ + "1: movl %%eax,0(%1)\n" \ + "2: movl %%edx,4(%1)\n" \ + _ASM_EXTABLE_UA(1b, %l2) \ + _ASM_EXTABLE_UA(2b, %l2) \ + : : "A" (x), "r" (addr) \ + : : label) #define __put_user_asm_ex_u64(x, addr) \ asm volatile("\n" \ @@ -216,8 +208,8 @@ __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL)) asm volatile("call __put_user_8" : "=a" (__ret_pu) \ : "A" ((typeof(*(ptr)))(x)), "c" (ptr) : "ebx") #else -#define __put_user_asm_u64(x, ptr, retval, errret) \ - __put_user_asm(x, ptr, retval, "q", "", "er", errret) +#define __put_user_goto_u64(x, ptr, label) \ + __put_user_goto(x, ptr, "q", "", "er", label) #define __put_user_asm_ex_u64(x, addr) \ __put_user_asm_ex(x, addr, "q", "", "er") #define __put_user_x8(x, ptr, __ret_pu) __put_user_x(8, x, ptr, __ret_pu) @@ -278,23 +270,21 @@ extern void __put_user_8(void); __builtin_expect(__ret_pu, 0); \ }) -#define __put_user_size(x, ptr, size, retval, errret) \ +#define __put_user_size(x, ptr, size, label) \ do { \ - retval = 0; \ __chk_user_ptr(ptr); \ switch (size) { \ case 1: \ - __put_user_asm(x, ptr, retval, "b", "b", "iq", errret); \ + __put_user_goto(x, ptr, "b", "b", "iq", label); \ break; \ case 2: \ - __put_user_asm(x, ptr, retval, "w", "w", "ir", errret); \ + __put_user_goto(x, ptr, "w", "w", "ir", label); \ break; \ case 4: \ - __put_user_asm(x, ptr, retval, "l", "k", "ir", errret); \ + __put_user_goto(x, ptr, "l", "k", "ir", label); \ break; \ case 8: \ - __put_user_asm_u64((__typeof__(*ptr))(x), ptr, retval, \ - errret); \ + __put_user_goto_u64(x, ptr, label); \ break; \ default: \ __put_user_bad(); \ @@ -340,8 +330,8 @@ do { \ " xorl %%edx,%%edx\n" \ " jmp 3b\n" \ ".previous\n" \ - _ASM_EXTABLE(1b, 4b) \ - _ASM_EXTABLE(2b, 4b) \ + _ASM_EXTABLE_UA(1b, 4b) \ + _ASM_EXTABLE_UA(2b, 4b) \ : "=r" (retval), "=&A"(x) \ : "m" (__m(__ptr)), "m" __m(((u32 __user *)(__ptr)) + 1), \ "i" (errret), "0" (retval)); \ @@ -386,7 +376,7 @@ do { \ " xor"itype" %"rtype"1,%"rtype"1\n" \ " jmp 2b\n" \ ".previous\n" \ - _ASM_EXTABLE(1b, 3b) \ + _ASM_EXTABLE_UA(1b, 3b) \ : "=r" (err), ltype(x) \ : "m" (__m(addr)), "i" (errret), "0" (err)) @@ -398,7 +388,7 @@ do { \ "3: mov %3,%0\n" \ " jmp 2b\n" \ ".previous\n" \ - _ASM_EXTABLE(1b, 3b) \ + _ASM_EXTABLE_UA(1b, 3b) \ : "=r" (err), ltype(x) \ : "m" (__m(addr)), "i" (errret), "0" (err)) @@ -439,9 +429,14 @@ do { \ #define __put_user_nocheck(x, ptr, size) \ ({ \ - int __pu_err; \ + __label__ __pu_label; \ + int __pu_err = -EFAULT; \ + __typeof__(*(ptr)) __pu_val; \ + __pu_val = x; \ __uaccess_begin(); \ - __put_user_size((x), (ptr), (size), __pu_err, -EFAULT); \ + __put_user_size(__pu_val, (ptr), (size), __pu_label); \ + __pu_err = 0; \ +__pu_label: \ __uaccess_end(); \ __builtin_expect(__pu_err, 0); \ }) @@ -466,17 +461,23 @@ struct __large_struct { unsigned long buf[100]; }; * we do not write to any memory gcc knows about, so there are no * aliasing issues. */ -#define __put_user_asm(x, addr, err, itype, rtype, ltype, errret) \ - asm volatile("\n" \ - "1: mov"itype" %"rtype"1,%2\n" \ - "2:\n" \ - ".section .fixup,\"ax\"\n" \ - "3: mov %3,%0\n" \ - " jmp 2b\n" \ - ".previous\n" \ - _ASM_EXTABLE(1b, 3b) \ - : "=r"(err) \ - : ltype(x), "m" (__m(addr)), "i" (errret), "0" (err)) +#define __put_user_goto(x, addr, itype, rtype, ltype, label) \ + asm_volatile_goto("\n" \ + "1: mov"itype" %"rtype"0,%1\n" \ + _ASM_EXTABLE_UA(1b, %l2) \ + : : ltype(x), "m" (__m(addr)) \ + : : label) + +#define __put_user_failed(x, addr, itype, rtype, ltype, errret) \ + ({ __label__ __puflab; \ + int __pufret = errret; \ + __put_user_goto(x,addr,itype,rtype,ltype,__puflab); \ + __pufret = 0; \ + __puflab: __pufret; }) + +#define __put_user_asm(x, addr, retval, itype, rtype, ltype, errret) do { \ + retval = __put_user_failed(x, addr, itype, rtype, ltype, errret); \ +} while (0) #define __put_user_asm_ex(x, addr, itype, rtype, ltype) \ asm volatile("1: mov"itype" %"rtype"0,%1\n" \ @@ -602,7 +603,7 @@ extern void __cmpxchg_wrong_size(void) "3:\tmov %3, %0\n" \ "\tjmp 2b\n" \ "\t.previous\n" \ - _ASM_EXTABLE(1b, 3b) \ + _ASM_EXTABLE_UA(1b, 3b) \ : "+r" (__ret), "=a" (__old), "+m" (*(ptr)) \ : "i" (-EFAULT), "q" (__new), "1" (__old) \ : "memory" \ @@ -618,7 +619,7 @@ extern void __cmpxchg_wrong_size(void) "3:\tmov %3, %0\n" \ "\tjmp 2b\n" \ "\t.previous\n" \ - _ASM_EXTABLE(1b, 3b) \ + _ASM_EXTABLE_UA(1b, 3b) \ : "+r" (__ret), "=a" (__old), "+m" (*(ptr)) \ : "i" (-EFAULT), "r" (__new), "1" (__old) \ : "memory" \ @@ -634,7 +635,7 @@ extern void __cmpxchg_wrong_size(void) "3:\tmov %3, %0\n" \ "\tjmp 2b\n" \ "\t.previous\n" \ - _ASM_EXTABLE(1b, 3b) \ + _ASM_EXTABLE_UA(1b, 3b) \ : "+r" (__ret), "=a" (__old), "+m" (*(ptr)) \ : "i" (-EFAULT), "r" (__new), "1" (__old) \ : "memory" \ @@ -653,7 +654,7 @@ extern void __cmpxchg_wrong_size(void) "3:\tmov %3, %0\n" \ "\tjmp 2b\n" \ "\t.previous\n" \ - _ASM_EXTABLE(1b, 3b) \ + _ASM_EXTABLE_UA(1b, 3b) \ : "+r" (__ret), "=a" (__old), "+m" (*(ptr)) \ : "i" (-EFAULT), "r" (__new), "1" (__old) \ : "memory" \ @@ -670,7 +671,7 @@ extern void __cmpxchg_wrong_size(void) #define user_atomic_cmpxchg_inatomic(uval, ptr, old, new) \ ({ \ - access_ok(VERIFY_WRITE, (ptr), sizeof(*(ptr))) ? \ + access_ok((ptr), sizeof(*(ptr))) ? \ __user_atomic_cmpxchg_inatomic((uval), (ptr), \ (old), (new), sizeof(*(ptr))) : \ -EFAULT; \ @@ -708,16 +709,18 @@ extern struct movsl_mask { * checking before using them, but you have to surround them with the * user_access_begin/end() pair. */ -#define user_access_begin() __uaccess_begin() +static __must_check inline bool user_access_begin(const void __user *ptr, size_t len) +{ + if (unlikely(!access_ok(ptr,len))) + return 0; + __uaccess_begin_nospec(); + return 1; +} +#define user_access_begin(a,b) user_access_begin(a,b) #define user_access_end() __uaccess_end() -#define unsafe_put_user(x, ptr, err_label) \ -do { \ - int __pu_err; \ - __typeof__(*(ptr)) __pu_val = (x); \ - __put_user_size(__pu_val, (ptr), sizeof(*(ptr)), __pu_err, -EFAULT); \ - if (unlikely(__pu_err)) goto err_label; \ -} while (0) +#define unsafe_put_user(x, ptr, label) \ + __put_user_size((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)), label) #define unsafe_get_user(x, ptr, err_label) \ do { \ diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h index 51c4eee00732..dc4ed8bc2382 100644 --- a/arch/x86/include/asm/unistd.h +++ b/arch/x86/include/asm/unistd.h @@ -24,6 +24,7 @@ # include <asm/unistd_64.h> # include <asm/unistd_64_x32.h> # define __ARCH_WANT_COMPAT_SYS_TIME +# define __ARCH_WANT_SYS_UTIME32 # define __ARCH_WANT_COMPAT_SYS_PREADV64 # define __ARCH_WANT_COMPAT_SYS_PWRITEV64 # define __ARCH_WANT_COMPAT_SYS_PREADV64V2 @@ -31,13 +32,13 @@ # endif +# define __ARCH_WANT_NEW_STAT # define __ARCH_WANT_OLD_READDIR # define __ARCH_WANT_OLD_STAT # define __ARCH_WANT_SYS_ALARM # define __ARCH_WANT_SYS_FADVISE64 # define __ARCH_WANT_SYS_GETHOSTNAME # define __ARCH_WANT_SYS_GETPGRP -# define __ARCH_WANT_SYS_LLSEEK # define __ARCH_WANT_SYS_NICE # define __ARCH_WANT_SYS_OLDUMOUNT # define __ARCH_WANT_SYS_OLD_GETRLIMIT diff --git a/arch/x86/include/asm/uv/bios.h b/arch/x86/include/asm/uv/bios.h index e652a7cc6186..3f697a9e3f59 100644 --- a/arch/x86/include/asm/uv/bios.h +++ b/arch/x86/include/asm/uv/bios.h @@ -48,7 +48,8 @@ enum { BIOS_STATUS_SUCCESS = 0, BIOS_STATUS_UNIMPLEMENTED = -ENOSYS, BIOS_STATUS_EINVAL = -EINVAL, - BIOS_STATUS_UNAVAIL = -EBUSY + BIOS_STATUS_UNAVAIL = -EBUSY, + BIOS_STATUS_ABORT = -EINTR, }; /* Address map parameters */ @@ -167,4 +168,9 @@ extern long system_serial_number; extern struct kobject *sgi_uv_kobj; /* /sys/firmware/sgi_uv */ +/* + * EFI runtime lock; cf. firmware/efi/runtime-wrappers.c for details + */ +extern struct semaphore __efi_uv_runtime_lock; + #endif /* _ASM_X86_UV_BIOS_H */ diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h index 53748541c487..913a133f8e6f 100644 --- a/arch/x86/include/asm/vgtod.h +++ b/arch/x86/include/asm/vgtod.h @@ -5,33 +5,46 @@ #include <linux/compiler.h> #include <linux/clocksource.h> +#include <uapi/linux/time.h> + #ifdef BUILD_VDSO32_64 typedef u64 gtod_long_t; #else typedef unsigned long gtod_long_t; #endif + +/* + * There is one of these objects in the vvar page for each + * vDSO-accelerated clockid. For high-resolution clocks, this encodes + * the time corresponding to vsyscall_gtod_data.cycle_last. For coarse + * clocks, this encodes the actual time. + * + * To confuse the reader, for high-resolution clocks, nsec is left-shifted + * by vsyscall_gtod_data.shift. + */ +struct vgtod_ts { + u64 sec; + u64 nsec; +}; + +#define VGTOD_BASES (CLOCK_TAI + 1) +#define VGTOD_HRES (BIT(CLOCK_REALTIME) | BIT(CLOCK_MONOTONIC) | BIT(CLOCK_TAI)) +#define VGTOD_COARSE (BIT(CLOCK_REALTIME_COARSE) | BIT(CLOCK_MONOTONIC_COARSE)) + /* * vsyscall_gtod_data will be accessed by 32 and 64 bit code at the same time * so be carefull by modifying this structure. */ struct vsyscall_gtod_data { - unsigned seq; - - int vclock_mode; - u64 cycle_last; - u64 mask; - u32 mult; - u32 shift; - - /* open coded 'struct timespec' */ - u64 wall_time_snsec; - gtod_long_t wall_time_sec; - gtod_long_t monotonic_time_sec; - u64 monotonic_time_snsec; - gtod_long_t wall_time_coarse_sec; - gtod_long_t wall_time_coarse_nsec; - gtod_long_t monotonic_time_coarse_sec; - gtod_long_t monotonic_time_coarse_nsec; + unsigned int seq; + + int vclock_mode; + u64 cycle_last; + u64 mask; + u32 mult; + u32 shift; + + struct vgtod_ts basetime[VGTOD_BASES]; int tz_minuteswest; int tz_dsttime; @@ -44,9 +57,9 @@ static inline bool vclock_was_used(int vclock) return READ_ONCE(vclocks_used) & (1 << vclock); } -static inline unsigned gtod_read_begin(const struct vsyscall_gtod_data *s) +static inline unsigned int gtod_read_begin(const struct vsyscall_gtod_data *s) { - unsigned ret; + unsigned int ret; repeat: ret = READ_ONCE(s->seq); @@ -59,7 +72,7 @@ repeat: } static inline int gtod_read_retry(const struct vsyscall_gtod_data *s, - unsigned start) + unsigned int start) { smp_rmb(); return unlikely(s->seq != start); @@ -77,30 +90,4 @@ static inline void gtod_write_end(struct vsyscall_gtod_data *s) ++s->seq; } -#ifdef CONFIG_X86_64 - -#define VGETCPU_CPU_MASK 0xfff - -static inline unsigned int __getcpu(void) -{ - unsigned int p; - - /* - * Load per CPU data from GDT. LSL is faster than RDTSCP and - * works on all CPUs. This is volatile so that it orders - * correctly wrt barrier() and to keep gcc from cleverly - * hoisting it out of the calling function. - * - * If RDPID is available, use it. - */ - alternative_io ("lsl %[seg],%[p]", - ".byte 0xf3,0x0f,0xc7,0xf8", /* RDPID %eax/rax */ - X86_FEATURE_RDPID, - [p] "=a" (p), [seg] "r" (__PER_CPU_SEG)); - - return p; -} - -#endif /* CONFIG_X86_64 */ - #endif /* _ASM_X86_VGTOD_H */ diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h index 0116b2ee9e64..1fc7a0d1e877 100644 --- a/arch/x86/include/asm/virtext.h +++ b/arch/x86/include/asm/virtext.h @@ -40,7 +40,7 @@ static inline int cpu_has_vmx(void) */ static inline void cpu_vmxoff(void) { - asm volatile (ASM_VMX_VMXOFF : : : "cc"); + asm volatile ("vmxoff"); cr4_clear_bits(X86_CR4_VMXE); } @@ -83,9 +83,10 @@ static inline void cpu_emergency_vmxoff(void) */ static inline int cpu_has_svm(const char **msg) { - if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) { + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD && + boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) { if (msg) - *msg = "not amd"; + *msg = "not amd or hygon"; return 0; } diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 9527ba5d62da..4e4133e86484 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -77,7 +77,10 @@ #define SECONDARY_EXEC_ENCLS_EXITING 0x00008000 #define SECONDARY_EXEC_RDSEED_EXITING 0x00010000 #define SECONDARY_EXEC_ENABLE_PML 0x00020000 +#define SECONDARY_EXEC_PT_CONCEAL_VMX 0x00080000 #define SECONDARY_EXEC_XSAVES 0x00100000 +#define SECONDARY_EXEC_PT_USE_GPA 0x01000000 +#define SECONDARY_EXEC_MODE_BASED_EPT_EXEC 0x00400000 #define SECONDARY_EXEC_TSC_SCALING 0x02000000 #define PIN_BASED_EXT_INTR_MASK 0x00000001 @@ -98,6 +101,8 @@ #define VM_EXIT_LOAD_IA32_EFER 0x00200000 #define VM_EXIT_SAVE_VMX_PREEMPTION_TIMER 0x00400000 #define VM_EXIT_CLEAR_BNDCFGS 0x00800000 +#define VM_EXIT_PT_CONCEAL_PIP 0x01000000 +#define VM_EXIT_CLEAR_IA32_RTIT_CTL 0x02000000 #define VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR 0x00036dff @@ -109,6 +114,8 @@ #define VM_ENTRY_LOAD_IA32_PAT 0x00004000 #define VM_ENTRY_LOAD_IA32_EFER 0x00008000 #define VM_ENTRY_LOAD_BNDCFGS 0x00010000 +#define VM_ENTRY_PT_CONCEAL_PIP 0x00020000 +#define VM_ENTRY_LOAD_IA32_RTIT_CTL 0x00040000 #define VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR 0x000011ff @@ -240,6 +247,8 @@ enum vmcs_field { GUEST_PDPTR3_HIGH = 0x00002811, GUEST_BNDCFGS = 0x00002812, GUEST_BNDCFGS_HIGH = 0x00002813, + GUEST_IA32_RTIT_CTL = 0x00002814, + GUEST_IA32_RTIT_CTL_HIGH = 0x00002815, HOST_IA32_PAT = 0x00002c00, HOST_IA32_PAT_HIGH = 0x00002c01, HOST_IA32_EFER = 0x00002c02, @@ -503,19 +512,6 @@ enum vmcs_field { #define VMX_EPT_IDENTITY_PAGETABLE_ADDR 0xfffbc000ul - -#define ASM_VMX_VMCLEAR_RAX ".byte 0x66, 0x0f, 0xc7, 0x30" -#define ASM_VMX_VMLAUNCH ".byte 0x0f, 0x01, 0xc2" -#define ASM_VMX_VMRESUME ".byte 0x0f, 0x01, 0xc3" -#define ASM_VMX_VMPTRLD_RAX ".byte 0x0f, 0xc7, 0x30" -#define ASM_VMX_VMREAD_RDX_RAX ".byte 0x0f, 0x78, 0xd0" -#define ASM_VMX_VMWRITE_RAX_RDX ".byte 0x0f, 0x79, 0xd0" -#define ASM_VMX_VMWRITE_RSP_RDX ".byte 0x0f, 0x79, 0xd4" -#define ASM_VMX_VMXOFF ".byte 0x0f, 0x01, 0xc4" -#define ASM_VMX_VMXON_RAX ".byte 0xf3, 0x0f, 0xc7, 0x30" -#define ASM_VMX_INVEPT ".byte 0x66, 0x0f, 0x38, 0x80, 0x08" -#define ASM_VMX_INVVPID ".byte 0x66, 0x0f, 0x38, 0x81, 0x08" - struct vmx_msr_entry { u32 index; u32 reserved; diff --git a/arch/x86/include/asm/xen/events.h b/arch/x86/include/asm/xen/events.h index d383140e1dc8..068d9b067c83 100644 --- a/arch/x86/include/asm/xen/events.h +++ b/arch/x86/include/asm/xen/events.h @@ -2,6 +2,8 @@ #ifndef _ASM_X86_XEN_EVENTS_H #define _ASM_X86_XEN_EVENTS_H +#include <xen/xen.h> + enum ipi_vector { XEN_RESCHEDULE_VECTOR, XEN_CALL_FUNCTION_VECTOR, diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 123e669bf363..790ce08e41f2 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -9,7 +9,7 @@ #include <linux/mm.h> #include <linux/device.h> -#include <linux/uaccess.h> +#include <asm/extable.h> #include <asm/page.h> #include <asm/pgtable.h> @@ -93,12 +93,39 @@ clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops, */ static inline int xen_safe_write_ulong(unsigned long *addr, unsigned long val) { - return __put_user(val, (unsigned long __user *)addr); + int ret = 0; + + asm volatile("1: mov %[val], %[ptr]\n" + "2:\n" + ".section .fixup, \"ax\"\n" + "3: sub $1, %[ret]\n" + " jmp 2b\n" + ".previous\n" + _ASM_EXTABLE(1b, 3b) + : [ret] "+r" (ret), [ptr] "=m" (*addr) + : [val] "r" (val)); + + return ret; } -static inline int xen_safe_read_ulong(unsigned long *addr, unsigned long *val) +static inline int xen_safe_read_ulong(const unsigned long *addr, + unsigned long *val) { - return __get_user(*val, (unsigned long __user *)addr); + int ret = 0; + unsigned long rval = ~0ul; + + asm volatile("1: mov %[ptr], %[rval]\n" + "2:\n" + ".section .fixup, \"ax\"\n" + "3: sub $1, %[ret]\n" + " jmp 2b\n" + ".previous\n" + _ASM_EXTABLE(1b, 3b) + : [ret] "+r" (ret), [rval] "+r" (rval) + : [ptr] "m" (*addr)); + *val = rval; + + return ret; } #ifdef CONFIG_XEN_PV diff --git a/arch/x86/include/uapi/asm/Kbuild b/arch/x86/include/uapi/asm/Kbuild index 322681622d1e..f6648e9928b3 100644 --- a/arch/x86/include/uapi/asm/Kbuild +++ b/arch/x86/include/uapi/asm/Kbuild @@ -1,8 +1,5 @@ -# UAPI Header export list include include/uapi/asm-generic/Kbuild.asm -generic-y += bpf_perf_event.h generated-y += unistd_32.h generated-y += unistd_64.h generated-y += unistd_x32.h -generic-y += poll.h diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h index a06cbf019744..60733f137e9a 100644 --- a/arch/x86/include/uapi/asm/bootparam.h +++ b/arch/x86/include/uapi/asm/bootparam.h @@ -155,7 +155,8 @@ struct boot_params { __u8 _pad2[4]; /* 0x054 */ __u64 tboot_addr; /* 0x058 */ struct ist_info ist_info; /* 0x060 */ - __u8 _pad3[16]; /* 0x070 */ + __u64 acpi_rsdp_addr; /* 0x070 */ + __u8 _pad3[8]; /* 0x078 */ __u8 hd0_info[16]; /* obsolete! */ /* 0x080 */ __u8 hd1_info[16]; /* obsolete! */ /* 0x090 */ struct sys_desc_table sys_desc_table; /* obsolete! */ /* 0x0a0 */ diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index fd23d5778ea1..dabfcf7c3941 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -288,6 +288,7 @@ struct kvm_reinject_control { #define KVM_VCPUEVENT_VALID_SIPI_VECTOR 0x00000002 #define KVM_VCPUEVENT_VALID_SHADOW 0x00000004 #define KVM_VCPUEVENT_VALID_SMM 0x00000008 +#define KVM_VCPUEVENT_VALID_PAYLOAD 0x00000010 /* Interrupt shadow states */ #define KVM_X86_SHADOW_INT_MOV_SS 0x01 @@ -299,7 +300,7 @@ struct kvm_vcpu_events { __u8 injected; __u8 nr; __u8 has_error_code; - __u8 pad; + __u8 pending; __u32 error_code; } exception; struct { @@ -322,7 +323,9 @@ struct kvm_vcpu_events { __u8 smm_inside_nmi; __u8 latched_init; } smi; - __u32 reserved[9]; + __u8 reserved[27]; + __u8 exception_has_payload; + __u64 exception_payload; }; /* for KVM_GET/SET_DEBUGREGS */ @@ -381,6 +384,7 @@ struct kvm_sync_regs { #define KVM_STATE_NESTED_GUEST_MODE 0x00000001 #define KVM_STATE_NESTED_RUN_PENDING 0x00000002 +#define KVM_STATE_NESTED_EVMCS 0x00000004 #define KVM_STATE_NESTED_SMM_GUEST_MODE 0x00000001 #define KVM_STATE_NESTED_SMM_VMXON 0x00000002 diff --git a/arch/x86/include/uapi/asm/siginfo.h b/arch/x86/include/uapi/asm/siginfo.h index b3d157957177..6642d8be40c4 100644 --- a/arch/x86/include/uapi/asm/siginfo.h +++ b/arch/x86/include/uapi/asm/siginfo.h @@ -7,8 +7,6 @@ typedef long long __kernel_si_clock_t __attribute__((aligned(4))); # define __ARCH_SI_CLOCK_T __kernel_si_clock_t # define __ARCH_SI_ATTRIBUTES __attribute__((aligned(8))) -# else /* x86-64 */ -# define __ARCH_SI_PREAMBLE_SIZE (4 * sizeof(int)) # endif #endif |